* [PATCH 6/6] sky2: version 1.26
From: Stephen Hemminger @ 2009-10-29 16:37 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20091029163704.793246334@vyatta.com>
[-- Attachment #1: sky2-1.26.patch --]
[-- Type: text/plain, Size: 343 bytes --]
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
--- a/drivers/net/sky2.c 2009-10-29 08:57:43.512001253 -0700
+++ b/drivers/net/sky2.c 2009-10-29 08:59:34.782375629 -0700
@@ -50,7 +50,7 @@
#include "sky2.h"
#define DRV_NAME "sky2"
-#define DRV_VERSION "1.25"
+#define DRV_VERSION "1.26"
#define PFX DRV_NAME " "
/*
--
^ permalink raw reply
* [PATCH 2/6] sky2: add register definitions for new chips
From: Stephen Hemminger @ 2009-10-29 16:37 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20091029163704.793246334@vyatta.com>
[-- Attachment #1: sky2-reg-update.patch --]
[-- Type: text/plain, Size: 11754 bytes --]
This adds infrastructure for the newer chip versions and workarounds.
Extracted from the vendor (GPL) driver.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
--- a/drivers/net/sky2.h 2009-10-29 08:34:51.778438561 -0700
+++ b/drivers/net/sky2.h 2009-10-29 08:35:53.313438448 -0700
@@ -16,6 +16,13 @@ enum {
PCI_DEV_REG5 = 0x88,
PCI_CFG_REG_0 = 0x90,
PCI_CFG_REG_1 = 0x94,
+
+ PSM_CONFIG_REG0 = 0x98,
+ PSM_CONFIG_REG1 = 0x9C,
+ PSM_CONFIG_REG2 = 0x160,
+ PSM_CONFIG_REG3 = 0x164,
+ PSM_CONFIG_REG4 = 0x168,
+
};
/* Yukon-2 */
@@ -48,6 +55,37 @@ enum pci_dev_reg_2 {
PCI_USEDATA64 = 1<<0, /* Use 64Bit Data bus ext */
};
+/* PCI_OUR_REG_3 32 bit Our Register 3 (Yukon-ECU only) */
+enum pci_dev_reg_3 {
+ P_CLK_ASF_REGS_DIS = 1<<18,/* Disable Clock ASF (Yukon-Ext.) */
+ P_CLK_COR_REGS_D0_DIS = 1<<17,/* Disable Clock Core Regs D0 */
+ P_CLK_MACSEC_DIS = 1<<17,/* Disable Clock MACSec (Yukon-Ext.) */
+ P_CLK_PCI_REGS_D0_DIS = 1<<16,/* Disable Clock PCI Regs D0 */
+ P_CLK_COR_YTB_ARB_DIS = 1<<15,/* Disable Clock YTB Arbiter */
+ P_CLK_MAC_LNK1_D3_DIS = 1<<14,/* Disable Clock MAC Link1 D3 */
+ P_CLK_COR_LNK1_D0_DIS = 1<<13,/* Disable Clock Core Link1 D0 */
+ P_CLK_MAC_LNK1_D0_DIS = 1<<12,/* Disable Clock MAC Link1 D0 */
+ P_CLK_COR_LNK1_D3_DIS = 1<<11,/* Disable Clock Core Link1 D3 */
+ P_CLK_PCI_MST_ARB_DIS = 1<<10,/* Disable Clock PCI Master Arb. */
+ P_CLK_COR_REGS_D3_DIS = 1<<9, /* Disable Clock Core Regs D3 */
+ P_CLK_PCI_REGS_D3_DIS = 1<<8, /* Disable Clock PCI Regs D3 */
+ P_CLK_REF_LNK1_GM_DIS = 1<<7, /* Disable Clock Ref. Link1 GMAC */
+ P_CLK_COR_LNK1_GM_DIS = 1<<6, /* Disable Clock Core Link1 GMAC */
+ P_CLK_PCI_COMMON_DIS = 1<<5, /* Disable Clock PCI Common */
+ P_CLK_COR_COMMON_DIS = 1<<4, /* Disable Clock Core Common */
+ P_CLK_PCI_LNK1_BMU_DIS = 1<<3, /* Disable Clock PCI Link1 BMU */
+ P_CLK_COR_LNK1_BMU_DIS = 1<<2, /* Disable Clock Core Link1 BMU */
+ P_CLK_PCI_LNK1_BIU_DIS = 1<<1, /* Disable Clock PCI Link1 BIU */
+ P_CLK_COR_LNK1_BIU_DIS = 1<<0, /* Disable Clock Core Link1 BIU */
+ PCIE_OUR3_WOL_D3_COLD_SET = P_CLK_ASF_REGS_DIS |
+ P_CLK_COR_REGS_D0_DIS |
+ P_CLK_COR_LNK1_D0_DIS |
+ P_CLK_MAC_LNK1_D0_DIS |
+ P_CLK_PCI_MST_ARB_DIS |
+ P_CLK_COR_COMMON_DIS |
+ P_CLK_COR_LNK1_BMU_DIS,
+};
+
/* PCI_OUR_REG_4 32 bit Our Register 4 (Yukon-ECU only) */
enum pci_dev_reg_4 {
/* (Link Training & Status State Machine) */
@@ -114,7 +152,7 @@ enum pci_dev_reg_5 {
P_GAT_PCIE_RX_EL_IDLE,
};
-#/* PCI_CFG_REG_1 32 bit Config Register 1 (Yukon-Ext only) */
+/* PCI_CFG_REG_1 32 bit Config Register 1 (Yukon-Ext only) */
enum pci_cfg_reg1 {
P_CF1_DIS_REL_EVT_RST = 1<<24, /* Dis. Rel. Event during PCIE reset */
/* Bit 23..21: Release Clock on Event */
@@ -145,6 +183,72 @@ enum pci_cfg_reg1 {
P_CF1_ENA_TXBMU_WR_IDLE,
};
+/* Yukon-Optima */
+enum {
+ PSM_CONFIG_REG1_AC_PRESENT_STATUS = 1<<31, /* AC Present Status */
+
+ PSM_CONFIG_REG1_PTP_CLK_SEL = 1<<29, /* PTP Clock Select */
+ PSM_CONFIG_REG1_PTP_MODE = 1<<28, /* PTP Mode */
+
+ PSM_CONFIG_REG1_MUX_PHY_LINK = 1<<27, /* PHY Energy Detect Event */
+
+ PSM_CONFIG_REG1_EN_PIN63_AC_PRESENT = 1<<26, /* Enable LED_DUPLEX for ac_present */
+ PSM_CONFIG_REG1_EN_PCIE_TIMER = 1<<25, /* Enable PCIe Timer */
+ PSM_CONFIG_REG1_EN_SPU_TIMER = 1<<24, /* Enable SPU Timer */
+ PSM_CONFIG_REG1_POLARITY_AC_PRESENT = 1<<23, /* AC Present Polarity */
+
+ PSM_CONFIG_REG1_EN_AC_PRESENT = 1<<21, /* Enable AC Present */
+
+ PSM_CONFIG_REG1_EN_GPHY_INT_PSM = 1<<20, /* Enable GPHY INT for PSM */
+ PSM_CONFIG_REG1_DIS_PSM_TIMER = 1<<19, /* Disable PSM Timer */
+};
+
+/* Yukon-Supreme */
+enum {
+ PSM_CONFIG_REG1_GPHY_ENERGY_STS = 1<<31, /* GPHY Energy Detect Status */
+
+ PSM_CONFIG_REG1_UART_MODE_MSK = 3<<29, /* UART_Mode */
+ PSM_CONFIG_REG1_CLK_RUN_ASF = 1<<28, /* Enable Clock Free Running for ASF Subsystem */
+ PSM_CONFIG_REG1_UART_CLK_DISABLE= 1<<27, /* Disable UART clock */
+ PSM_CONFIG_REG1_VAUX_ONE = 1<<26, /* Tie internal Vaux to 1'b1 */
+ PSM_CONFIG_REG1_UART_FC_RI_VAL = 1<<25, /* Default value for UART_RI_n */
+ PSM_CONFIG_REG1_UART_FC_DCD_VAL = 1<<24, /* Default value for UART_DCD_n */
+ PSM_CONFIG_REG1_UART_FC_DSR_VAL = 1<<23, /* Default value for UART_DSR_n */
+ PSM_CONFIG_REG1_UART_FC_CTS_VAL = 1<<22, /* Default value for UART_CTS_n */
+ PSM_CONFIG_REG1_LATCH_VAUX = 1<<21, /* Enable Latch current Vaux_avlbl */
+ PSM_CONFIG_REG1_FORCE_TESTMODE_INPUT= 1<<20, /* Force Testmode pin as input PAD */
+ PSM_CONFIG_REG1_UART_RST = 1<<19, /* UART_RST */
+ PSM_CONFIG_REG1_PSM_PCIE_L1_POL = 1<<18, /* PCIE L1 Event Polarity for PSM */
+ PSM_CONFIG_REG1_TIMER_STAT = 1<<17, /* PSM Timer Status */
+ PSM_CONFIG_REG1_GPHY_INT = 1<<16, /* GPHY INT Status */
+ PSM_CONFIG_REG1_FORCE_TESTMODE_ZERO= 1<<15, /* Force internal Testmode as 1'b0 */
+ PSM_CONFIG_REG1_EN_INT_ASPM_CLKREQ = 1<<14, /* ENABLE INT for CLKRUN on ASPM and CLKREQ */
+ PSM_CONFIG_REG1_EN_SND_TASK_ASPM_CLKREQ = 1<<13, /* ENABLE Snd_task for CLKRUN on ASPM and CLKREQ */
+ PSM_CONFIG_REG1_DIS_CLK_GATE_SND_TASK = 1<<12, /* Disable CLK_GATE control snd_task */
+ PSM_CONFIG_REG1_DIS_FF_CHIAN_SND_INTA = 1<<11, /* Disable flip-flop chain for sndmsg_inta */
+
+ PSM_CONFIG_REG1_DIS_LOADER = 1<<9, /* Disable Loader SM after PSM Goes back to IDLE */
+ PSM_CONFIG_REG1_DO_PWDN = 1<<8, /* Do Power Down, Start PSM Scheme */
+ PSM_CONFIG_REG1_DIS_PIG = 1<<7, /* Disable Plug-in-Go SM after PSM Goes back to IDLE */
+ PSM_CONFIG_REG1_DIS_PERST = 1<<6, /* Disable Internal PCIe Reset after PSM Goes back to IDLE */
+ PSM_CONFIG_REG1_EN_REG18_PD = 1<<5, /* Enable REG18 Power Down for PSM */
+ PSM_CONFIG_REG1_EN_PSM_LOAD = 1<<4, /* Disable EEPROM Loader after PSM Goes back to IDLE */
+ PSM_CONFIG_REG1_EN_PSM_HOT_RST = 1<<3, /* Enable PCIe Hot Reset for PSM */
+ PSM_CONFIG_REG1_EN_PSM_PERST = 1<<2, /* Enable PCIe Reset Event for PSM */
+ PSM_CONFIG_REG1_EN_PSM_PCIE_L1 = 1<<1, /* Enable PCIe L1 Event for PSM */
+ PSM_CONFIG_REG1_EN_PSM = 1<<0, /* Enable PSM Scheme */
+};
+
+/* PSM_CONFIG_REG4 0x0168 PSM Config Register 4 */
+enum {
+ /* PHY Link Detect Timer */
+ PSM_CONFIG_REG4_TIMER_PHY_LINK_DETECT_MSK = 0xf<<4,
+ PSM_CONFIG_REG4_TIMER_PHY_LINK_DETECT_BASE = 4,
+
+ PSM_CONFIG_REG4_DEBUG_TIMER = 1<<1, /* Debug Timer */
+ PSM_CONFIG_REG4_RST_PHY_LINK_DETECT = 1<<0, /* Reset GPHY Link Detect */
+};
+
#define PCI_STATUS_ERROR_BITS (PCI_STATUS_DETECTED_PARITY | \
PCI_STATUS_SIG_SYSTEM_ERROR | \
@@ -197,6 +301,9 @@ enum csr_regs {
B2_I2C_IRQ = 0x0168,
B2_I2C_SW = 0x016c,
+ Y2_PEX_PHY_DATA = 0x0170,
+ Y2_PEX_PHY_ADDR = 0x0172,
+
B3_RAM_ADDR = 0x0180,
B3_RAM_DATA_LO = 0x0184,
B3_RAM_DATA_HI = 0x0188,
@@ -317,6 +424,10 @@ enum {
Y2_IS_CHK_TXS2 = 1<<9, /* Descriptor error TXS 2 */
Y2_IS_CHK_TXA2 = 1<<8, /* Descriptor error TXA 2 */
+ Y2_IS_PSM_ACK = 1<<7, /* PSM Acknowledge (Yukon-Optima only) */
+ Y2_IS_PTP_TIST = 1<<6, /* PTP Time Stamp (Yukon-Optima only) */
+ Y2_IS_PHY_QLNK = 1<<5, /* PHY Quick Link (Yukon-Optima only) */
+
Y2_IS_IRQ_PHY1 = 1<<4, /* Interrupt from PHY 1 */
Y2_IS_IRQ_MAC1 = 1<<3, /* Interrupt from MAC 1 */
Y2_IS_CHK_RX1 = 1<<2, /* Descriptor error Rx 1 */
@@ -435,6 +546,7 @@ enum {
CHIP_ID_YUKON_FE_P = 0xb8, /* YUKON-2 FE+ */
CHIP_ID_YUKON_SUPR = 0xb9, /* YUKON-2 Supreme */
CHIP_ID_YUKON_UL_2 = 0xba, /* YUKON-2 Ultra 2 */
+ CHIP_ID_YUKON_OPT = 0xbc, /* YUKON-2 Optima */
};
enum yukon_ec_rev {
CHIP_REV_YU_EC_A1 = 0, /* Chip Rev. for Yukon-EC A1/A0 */
@@ -459,6 +571,8 @@ enum yukon_ex_rev {
};
enum yukon_supr_rev {
CHIP_REV_YU_SU_A0 = 0,
+ CHIP_REV_YU_SU_B0 = 1,
+ CHIP_REV_YU_SU_B1 = 3,
};
@@ -513,6 +627,12 @@ enum {
TIM_T_STEP = 1<<0, /* Test step */
};
+/* Y2_PEX_PHY_ADDR/DATA PEX PHY address and data reg (Yukon-2 only) */
+enum {
+ PEX_RD_ACCESS = 1<<31, /* Access Mode Read = 1, Write = 0 */
+ PEX_DB_ACCESS = 1<<30, /* Access to debug register */
+};
+
/* B3_RAM_ADDR 32 bit RAM Address, to read or write */
/* Bit 31..19: reserved */
#define RAM_ADR_RAN 0x0007ffffL /* Bit 18.. 0: RAM Address Range */
@@ -754,6 +874,42 @@ enum {
BMU_TX_CLR_IRQ_TCP = 1<<11, /* Clear IRQ on TCP segment length mismatch */
};
+/* TBMU_TEST 0x06B8 Transmit BMU Test Register */
+enum {
+ TBMU_TEST_BMU_TX_CHK_AUTO_OFF = 1<<31, /* BMU Tx Checksum Auto Calculation Disable */
+ TBMU_TEST_BMU_TX_CHK_AUTO_ON = 1<<30, /* BMU Tx Checksum Auto Calculation Enable */
+ TBMU_TEST_HOME_ADD_PAD_FIX1_EN = 1<<29, /* Home Address Paddiing FIX1 Enable */
+ TBMU_TEST_HOME_ADD_PAD_FIX1_DIS = 1<<28, /* Home Address Paddiing FIX1 Disable */
+ TBMU_TEST_ROUTING_ADD_FIX_EN = 1<<27, /* Routing Address Fix Enable */
+ TBMU_TEST_ROUTING_ADD_FIX_DIS = 1<<26, /* Routing Address Fix Disable */
+ TBMU_TEST_HOME_ADD_FIX_EN = 1<<25, /* Home address checksum fix enable */
+ TBMU_TEST_HOME_ADD_FIX_DIS = 1<<24, /* Home address checksum fix disable */
+
+ TBMU_TEST_TEST_RSPTR_ON = 1<<22, /* Testmode Shadow Read Ptr On */
+ TBMU_TEST_TEST_RSPTR_OFF = 1<<21, /* Testmode Shadow Read Ptr Off */
+ TBMU_TEST_TESTSTEP_RSPTR = 1<<20, /* Teststep Shadow Read Ptr */
+
+ TBMU_TEST_TEST_RPTR_ON = 1<<18, /* Testmode Read Ptr On */
+ TBMU_TEST_TEST_RPTR_OFF = 1<<17, /* Testmode Read Ptr Off */
+ TBMU_TEST_TESTSTEP_RPTR = 1<<16, /* Teststep Read Ptr */
+
+ TBMU_TEST_TEST_WSPTR_ON = 1<<14, /* Testmode Shadow Write Ptr On */
+ TBMU_TEST_TEST_WSPTR_OFF = 1<<13, /* Testmode Shadow Write Ptr Off */
+ TBMU_TEST_TESTSTEP_WSPTR = 1<<12, /* Teststep Shadow Write Ptr */
+
+ TBMU_TEST_TEST_WPTR_ON = 1<<10, /* Testmode Write Ptr On */
+ TBMU_TEST_TEST_WPTR_OFF = 1<<9, /* Testmode Write Ptr Off */
+ TBMU_TEST_TESTSTEP_WPTR = 1<<8, /* Teststep Write Ptr */
+
+ TBMU_TEST_TEST_REQ_NB_ON = 1<<6, /* Testmode Req Nbytes/Addr On */
+ TBMU_TEST_TEST_REQ_NB_OFF = 1<<5, /* Testmode Req Nbytes/Addr Off */
+ TBMU_TEST_TESTSTEP_REQ_NB = 1<<4, /* Teststep Req Nbytes/Addr */
+
+ TBMU_TEST_TEST_DONE_IDX_ON = 1<<2, /* Testmode Done Index On */
+ TBMU_TEST_TEST_DONE_IDX_OFF = 1<<1, /* Testmode Done Index Off */
+ TBMU_TEST_TESTSTEP_DONE_IDX = 1<<0, /* Teststep Done Index */
+};
+
/* Queue Prefetch Unit Offsets, use Y2_QADDR() to address (Yukon-2 only)*/
/* PREF_UNIT_CTRL 32 bit Prefetch Control register */
enum {
@@ -1674,6 +1830,12 @@ enum {
/* RX_GMF_CTRL_T 32 bit Rx GMAC FIFO Control/Test */
enum {
+ RX_GCLKMAC_ENA = 1<<31, /* RX MAC Clock Gating Enable */
+ RX_GCLKMAC_OFF = 1<<30,
+
+ RX_STFW_DIS = 1<<29, /* RX Store and Forward Enable */
+ RX_STFW_ENA = 1<<28,
+
RX_TRUNC_ON = 1<<27, /* enable packet truncation */
RX_TRUNC_OFF = 1<<26, /* disable packet truncation */
RX_VLAN_STRIP_ON = 1<<25, /* enable VLAN stripping */
@@ -1711,6 +1873,20 @@ enum {
GMF_RX_CTRL_DEF = GMF_OPER_ON | GMF_RX_F_FL_ON,
};
+/* RX_GMF_FL_CTRL 16 bit Rx GMAC FIFO Flush Control (Yukon-Supreme) */
+enum {
+ RX_IPV6_SA_MOB_ENA = 1<<9, /* IPv6 SA Mobility Support Enable */
+ RX_IPV6_SA_MOB_DIS = 1<<8, /* IPv6 SA Mobility Support Disable */
+ RX_IPV6_DA_MOB_ENA = 1<<7, /* IPv6 DA Mobility Support Enable */
+ RX_IPV6_DA_MOB_DIS = 1<<6, /* IPv6 DA Mobility Support Disable */
+ RX_PTR_SYNCDLY_ENA = 1<<5, /* Pointers Delay Synch Enable */
+ RX_PTR_SYNCDLY_DIS = 1<<4, /* Pointers Delay Synch Disable */
+ RX_ASF_NEWFLAG_ENA = 1<<3, /* RX ASF Flag New Logic Enable */
+ RX_ASF_NEWFLAG_DIS = 1<<2, /* RX ASF Flag New Logic Disable */
+ RX_FLSH_MISSPKT_ENA = 1<<1, /* RX Flush Miss-Packet Enable */
+ RX_FLSH_MISSPKT_DIS = 1<<0, /* RX Flush Miss-Packet Disable */
+};
+
/* TX_GMF_EA 32 bit Tx GMAC FIFO End Address */
enum {
TX_DYN_WM_ENA = 3, /* Yukon-FE+ specific */
--
^ permalink raw reply
* [PATCH 0/6] sky2: driver update
From: Stephen Hemminger @ 2009-10-29 16:37 UTC (permalink / raw)
To: David Miller; +Cc: netdev
This patch set adds support for Yukon Optima (88E8059) based
on the vendor driver. Hopefully, it can go in 2.6.32.
--
^ permalink raw reply
* [PATCH 1/6] sky2: add SK-9E21M device id
From: Stephen Hemminger @ 2009-10-29 16:37 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20091029163704.793246334@vyatta.com>
[-- Attachment #1: sky2-sk-9e21m.patch --]
[-- Type: text/plain, Size: 749 bytes --]
This is a new ID that just showed up in latest vendor driver.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
--- a/drivers/net/sky2.c 2009-10-28 11:01:10.454251343 -0700
+++ b/drivers/net/sky2.c 2009-10-28 11:01:44.867001737 -0700
@@ -102,6 +102,7 @@ MODULE_PARM_DESC(disable_msi, "Disable M
static DEFINE_PCI_DEVICE_TABLE(sky2_id_table) = {
{ PCI_DEVICE(PCI_VENDOR_ID_SYSKONNECT, 0x9000) }, /* SK-9Sxx */
{ PCI_DEVICE(PCI_VENDOR_ID_SYSKONNECT, 0x9E00) }, /* SK-9Exx */
+ { PCI_DEVICE(PCI_VENDOR_ID_SYSKONNECT, 0x9E01) }, /* SK-9E21M */
{ PCI_DEVICE(PCI_VENDOR_ID_DLINK, 0x4b00) }, /* DGE-560T */
{ PCI_DEVICE(PCI_VENDOR_ID_DLINK, 0x4001) }, /* DGE-550SX */
{ PCI_DEVICE(PCI_VENDOR_ID_DLINK, 0x4B02) }, /* DGE-560SX */
--
^ permalink raw reply
* [PATCH 4/6] sky2: workarounds for Yukon-2 supreme
From: Stephen Hemminger @ 2009-10-29 16:37 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20091029163704.793246334@vyatta.com>
[-- Attachment #1: sky2-supr2.patch --]
[-- Type: text/plain, Size: 2178 bytes --]
Changes related to support of Yukon supreme chip.
Don't have this chip version to test on,
these are reverse engineered from the vendor (GPL) driver.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
--- a/drivers/net/sky2.c 2009-10-29 08:52:37.995315808 -0700
+++ b/drivers/net/sky2.c 2009-10-29 08:55:47.116003224 -0700
@@ -787,8 +787,7 @@ static void sky2_set_tx_stfwd(struct sky
if ( (hw->chip_id == CHIP_ID_YUKON_EX &&
hw->chip_rev != CHIP_REV_YU_EX_A0) ||
- hw->chip_id == CHIP_ID_YUKON_FE_P ||
- hw->chip_id == CHIP_ID_YUKON_SUPR) {
+ hw->chip_id >= CHIP_ID_YUKON_FE_P) {
/* Yukon-Extreme B0 and further Extreme devices */
/* enable Store & Forward mode for TX */
@@ -1404,6 +1403,31 @@ static int sky2_rx_start(struct sky2_por
/* Tell chip about available buffers */
sky2_rx_update(sky2, rxq);
+
+ if (hw->chip_id == CHIP_ID_YUKON_EX ||
+ hw->chip_id == CHIP_ID_YUKON_SUPR) {
+ /*
+ * Disable flushing of non ASF packets;
+ * must be done after initializing the BMUs;
+ * drivers without ASF support should do this too, otherwise
+ * it may happen that they cannot run on ASF devices;
+ * remember that the MAC FIFO isn't reset during initialization.
+ */
+ sky2_write32(hw, SK_REG(sky2->port, RX_GMF_CTRL_T), RX_MACSEC_FLUSH_OFF);
+ }
+
+ if (hw->chip_id >= CHIP_ID_YUKON_SUPR) {
+ /* Enable RX Home Address & Routing Header checksum fix */
+ sky2_write16(hw, SK_REG(sky2->port, RX_GMF_FL_CTRL),
+ RX_IPV6_SA_MOB_ENA | RX_IPV6_DA_MOB_ENA);
+
+ /* Enable TX Home Address & Routing Header checksum fix */
+ sky2_write32(hw, Q_ADDR(txqaddr[sky2->port], Q_TEST),
+ TBMU_TEST_HOME_ADD_FIX_EN | TBMU_TEST_ROUTING_ADD_FIX_EN);
+ }
+
+
+
return 0;
nomem:
sky2_rx_clean(sky2);
@@ -2993,6 +3017,12 @@ static void sky2_reset(struct sky2_hw *h
sky2_write16(hw, SK_REG(i, GMAC_CTRL),
GMC_BYP_MACSECRX_ON | GMC_BYP_MACSECTX_ON
| GMC_BYP_RETR_ON);
+
+ }
+
+ if (hw->chip_id == CHIP_ID_YUKON_SUPR && hw->chip_rev > CHIP_REV_YU_SU_B0) {
+ /* enable MACSec clock gating */
+ sky2_pci_write32(hw, PCI_DEV_REG3, P_CLK_MACSEC_DIS);
}
/* Clear I2C IRQ noise */
--
^ permalink raw reply
* [PATCH 3/6] sky2: fix receive pause thresholds
From: Stephen Hemminger @ 2009-10-29 16:37 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20091029163704.793246334@vyatta.com>
[-- Attachment #1: sky2-rxthresh.patch --]
[-- Type: text/plain, Size: 1964 bytes --]
Program the receive pause thresholds differently depending on
chip version. This cloned from from the vendor (GPL) driver.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
--- a/drivers/net/sky2.h 2009-10-29 08:35:53.313438448 -0700
+++ b/drivers/net/sky2.h 2009-10-29 08:37:04.959438572 -0700
@@ -808,10 +808,11 @@ enum {
RX_GMF_AF_THR = 0x0c44,/* 32 bit Rx GMAC FIFO Almost Full Thresh. */
RX_GMF_CTRL_T = 0x0c48,/* 32 bit Rx GMAC FIFO Control/Test */
RX_GMF_FL_MSK = 0x0c4c,/* 32 bit Rx GMAC FIFO Flush Mask */
- RX_GMF_FL_THR = 0x0c50,/* 32 bit Rx GMAC FIFO Flush Threshold */
+ RX_GMF_FL_THR = 0x0c50,/* 16 bit Rx GMAC FIFO Flush Threshold */
+ RX_GMF_FL_CTRL = 0x0c52,/* 16 bit Rx GMAC FIFO Flush Control */
RX_GMF_TR_THR = 0x0c54,/* 32 bit Rx Truncation Threshold (Yukon-2) */
- RX_GMF_UP_THR = 0x0c58,/* 8 bit Rx Upper Pause Thr (Yukon-EC_U) */
- RX_GMF_LP_THR = 0x0c5a,/* 8 bit Rx Lower Pause Thr (Yukon-EC_U) */
+ RX_GMF_UP_THR = 0x0c58,/* 16 bit Rx Upper Pause Thr (Yukon-EC_U) */
+ RX_GMF_LP_THR = 0x0c5a,/* 16 bit Rx Lower Pause Thr (Yukon-EC_U) */
RX_GMF_VLAN = 0x0c5c,/* 32 bit Rx VLAN Type Register (Yukon-2) */
RX_GMF_WP = 0x0c60,/* 32 bit Rx GMAC FIFO Write Pointer */
--- a/drivers/net/sky2.c 2009-10-29 08:34:04.765191254 -0700
+++ b/drivers/net/sky2.c 2009-10-29 08:52:37.995315808 -0700
@@ -926,8 +926,14 @@ static void sky2_mac_init(struct sky2_hw
/* On chips without ram buffer, pause is controled by MAC level */
if (!(hw->flags & SKY2_HW_RAM_BUFFER)) {
- sky2_write8(hw, SK_REG(port, RX_GMF_LP_THR), 768/8);
- sky2_write8(hw, SK_REG(port, RX_GMF_UP_THR), 1024/8);
+ /* Pause threshold is scaled by 8 in bytes */
+ if (hw->chip_id == CHIP_ID_YUKON_FE_P
+ && hw->chip_rev == CHIP_REV_YU_FE2_A0)
+ reg = 1568 / 8;
+ else
+ reg = 1024 / 8;
+ sky2_write16(hw, SK_REG(port, RX_GMF_UP_THR), reg);
+ sky2_write16(hw, SK_REG(port, RX_GMF_LP_THR), 768 / 8);
sky2_set_tx_stfwd(hw, port);
}
--
^ permalink raw reply
* [PATCH 5/6] sky2: 88E8059 support
From: Stephen Hemminger @ 2009-10-29 16:37 UTC (permalink / raw)
To: David Miller; +Cc: netdev
In-Reply-To: <20091029163704.793246334@vyatta.com>
[-- Attachment #1: sky2-yukon-ul_2.patch --]
[-- Type: text/plain, Size: 4547 bytes --]
Tentative support for newer Marvell hardware including
the Yukon-2 Optima chip. Do not have hatdware to test this yet,
code is based on vendor driver.
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
--- a/drivers/net/sky2.c 2009-10-28 11:02:38.031251525 -0700
+++ b/drivers/net/sky2.c 2009-10-28 11:02:44.719000693 -0700
@@ -140,6 +140,7 @@ static DEFINE_PCI_DEVICE_TABLE(sky2_id_t
{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x436D) }, /* 88E8055 */
{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4370) }, /* 88E8075 */
{ PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4380) }, /* 88E8057 */
+ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL, 0x4381) }, /* 88E8059 */
{ 0 }
};
@@ -603,6 +604,16 @@ static void sky2_phy_init(struct sky2_hw
/* apply workaround for integrated resistors calibration */
gm_phy_write(hw, port, PHY_MARV_PAGE_ADDR, 17);
gm_phy_write(hw, port, PHY_MARV_PAGE_DATA, 0x3f60);
+ } else if (hw->chip_id == CHIP_ID_YUKON_OPT && hw->chip_rev == 0) {
+ /* apply fixes in PHY AFE */
+ gm_phy_write(hw, port, PHY_MARV_EXT_ADR, 0x00ff);
+
+ /* apply RDAC termination workaround */
+ gm_phy_write(hw, port, 24, 0x2800);
+ gm_phy_write(hw, port, 23, 0x2001);
+
+ /* set page register back to 0 */
+ gm_phy_write(hw, port, PHY_MARV_EXT_ADR, 0);
} else if (hw->chip_id != CHIP_ID_YUKON_EX &&
hw->chip_id < CHIP_ID_YUKON_SUPR) {
/* no effect on Yukon-XL */
@@ -2133,6 +2144,25 @@ out:
spin_unlock(&sky2->phy_lock);
}
+/* Special quick link interrupt (Yukon-2 Optima only) */
+static void sky2_qlink_intr(struct sky2_hw *hw)
+{
+ struct sky2_port *sky2 = netdev_priv(hw->dev[0]);
+ u32 imask;
+ u16 phy;
+
+ /* disable irq */
+ imask = sky2_read32(hw, B0_IMSK);
+ imask &= ~Y2_IS_PHY_QLNK;
+ sky2_write32(hw, B0_IMSK, imask);
+
+ /* reset PHY Link Detect */
+ phy = sky2_pci_read16(hw, PSM_CONFIG_REG4);
+ sky2_pci_write16(hw, PSM_CONFIG_REG4, phy | 1);
+
+ sky2_link_up(sky2);
+}
+
/* Transmit timeout is only called if we are running, carrier is up
* and tx queue is full (stopped).
*/
@@ -2803,6 +2833,9 @@ static int sky2_poll(struct napi_struct
if (status & Y2_IS_IRQ_PHY2)
sky2_phy_intr(hw, 1);
+ if (status & Y2_IS_PHY_QLNK)
+ sky2_qlink_intr(hw);
+
while ((idx = sky2_read16(hw, STAT_PUT_IDX)) != hw->st_idx) {
work_done += sky2_status_intr(hw, work_limit - work_done, idx);
@@ -2852,6 +2885,7 @@ static u32 sky2_mhz(const struct sky2_hw
case CHIP_ID_YUKON_EX:
case CHIP_ID_YUKON_SUPR:
case CHIP_ID_YUKON_UL_2:
+ case CHIP_ID_YUKON_OPT:
return 125;
case CHIP_ID_YUKON_FE:
@@ -2941,6 +2975,7 @@ static int __devinit sky2_init(struct sk
break;
case CHIP_ID_YUKON_UL_2:
+ case CHIP_ID_YUKON_OPT:
hw->flags = SKY2_HW_GIGABIT
| SKY2_HW_ADV_POWER_CTL;
break;
@@ -3031,6 +3066,46 @@ static void sky2_reset(struct sky2_hw *h
sky2_pci_write32(hw, PCI_DEV_REG3, P_CLK_MACSEC_DIS);
}
+ if (hw->chip_id == CHIP_ID_YUKON_OPT) {
+ u16 reg;
+ u32 msk;
+
+ if (hw->chip_rev == 0) {
+ /* disable PCI-E PHY power down (set PHY reg 0x80, bit 7 */
+ sky2_write32(hw, Y2_PEX_PHY_DATA, (0x80UL << 16) | (1 << 7));
+
+ /* set PHY Link Detect Timer to 1.1 second (11x 100ms) */
+ reg = 10;
+ } else {
+ /* set PHY Link Detect Timer to 0.4 second (4x 100ms) */
+ reg = 3;
+ }
+
+ reg <<= PSM_CONFIG_REG4_TIMER_PHY_LINK_DETECT_BASE;
+
+ /* reset PHY Link Detect */
+ sky2_pci_write16(hw, PSM_CONFIG_REG4,
+ reg | PSM_CONFIG_REG4_RST_PHY_LINK_DETECT);
+ sky2_pci_write16(hw, PSM_CONFIG_REG4, reg);
+
+
+ /* enable PHY Quick Link */
+ msk = sky2_read32(hw, B0_IMSK);
+ msk |= Y2_IS_PHY_QLNK;
+ sky2_write32(hw, B0_IMSK, msk);
+
+ /* check if PSMv2 was running before */
+ reg = sky2_pci_read16(hw, PSM_CONFIG_REG3);
+ if (reg & PCI_EXP_LNKCTL_ASPMC) {
+ int cap = pci_find_capability(pdev, PCI_CAP_ID_EXP);
+ /* restore the PCIe Link Control register */
+ sky2_pci_write16(hw, cap + PCI_EXP_LNKCTL, reg);
+ }
+
+ /* re-enable PEX PM in PEX PHY debug reg. 8 (clear bit 12) */
+ sky2_write32(hw, Y2_PEX_PHY_DATA, PEX_DB_ACCESS | (0x08UL << 16));
+ }
+
/* Clear I2C IRQ noise */
sky2_write32(hw, B2_I2C_IRQ, 1);
@@ -4451,9 +4526,11 @@ static const char *sky2_name(u8 chipid,
"FE+", /* 0xb8 */
"Supreme", /* 0xb9 */
"UL 2", /* 0xba */
+ "Unknown", /* 0xbb */
+ "Optima", /* 0xbc */
};
- if (chipid >= CHIP_ID_YUKON_XL && chipid < CHIP_ID_YUKON_UL_2)
+ if (chipid >= CHIP_ID_YUKON_XL && chipid < CHIP_ID_YUKON_OPT)
strncpy(buf, name[chipid - CHIP_ID_YUKON_XL], sz);
else
snprintf(buf, sz, "(chip %#x)", chipid);
--
^ permalink raw reply
* RE: [PATCH] udev: create empty regular files to represent net interfaces
From: Narendra_K @ 2009-10-29 16:44 UTC (permalink / raw)
To: greg, Matt_Domsch
Cc: kay.sievers, dannf, linux-hotplug, netdev, Jordan_Hargrave,
Charles_Rose, bhutchings
In-Reply-To: <20091029142554.GA16869@kroah.com>
[-- Attachment #1: Type: text/plain, Size: 3054 bytes --]
>> Netdev team - are you in agreement that having multiple names to
>> address the same netdevice is a worthwhile thing to add, to allow a
>> variety of naming schemes to exist simultaneously? If not,
>this whole
>> discussion will be moot, and my basic problem, that the ethX naming
>> convention is nondeterministic, but we need determinism, remains
>> unresolved.
>
>I'm still totally confused as to why you think this. What is
>wrong with what we do today, which is name network devices in
>a deterministic manner by their MAC in userspace? That name
>goes into the kernel, and everyone uses the same name and is happy.
The interface name as assigned by the OS is determined by how the
interface is named first during the OS installation. This name is made
persistent by associating the name with it's MAC address in userspace,
either by udev or ifcfg-eth files. In cases where there are one or more
add-in cards along with one or more integrated cards (Lan on
Motherboard), the integrated port 1, which is designated as Gb1 on the
chassis may or may not get the name "eth0". And that is the customer
expectation, most of the times.
Unattended installs and large scale image based installs are the most
affected scenarios.
>If you don't like naming by MAC, then pick some other
>deterministic naming scheme that works for your hardware and
>write udev rules for it.
>
>You could easily name them in a way that could keep the lowest number
>(eth0) for the lowest PCI id if you so desired and your BIOS
>guaranteed it.
>
This is how the lspci tree view on a PER710 (PowerEdge R710) server with
Four BCM5709 integrated NIC ports and One add-in Intel NIC port looks
like. The integrated ports are always found before the add-in nic (or
nics) by the BIOS consistently and BIOS guarantees it across every
reboot. If the OS also found and named the network ports in the same
manner, then there is no issue as integrated NIC port 1, designated Gb1
on the chassis, is always named as "eth0". But the observation is that,
it is not the case always.
-[0000:00]-+-00.0 Intel Corporation 5520 I/O Hub to ESI Port
+-01.0-[0000:01]--+-00.0 Broadcom Corporation NetXtreme II
BCM5709 Gigabit Ethernet
| \-00.1 Broadcom Corporation NetXtreme II
BCM5709 Gigabit Ethernet
+-03.0-[0000:02]--+-00.0 Broadcom Corporation NetXtreme II
BCM5709 Gigabit Ethernet
| \-00.1 Broadcom Corporation NetXtreme II
BCM5709 Gigabit Ethernet
+-04.0-[0000:03]----00.0 LSI Logic / Symbios Logic MegaRAID
SAS 1078
+-05.0-[0000:04]--
+-06.0-[0000:05]--
+-07.0-[0000:06]--
+-09.0-[0000:07]----00.0 Intel Corporation 82598EB
10-Gigabit AT Network Connection
In such cases, pathnames like Embedded_NIC_1 -> eth[01..], point to the
right interface, and communicate a more meaningful name without any
state embedded in them.
With regards,
Narendra K
[-- Attachment #2: PER710-lspci-tv.output --]
[-- Type: application/octet-stream, Size: 735 bytes --]
-[0000:00]-+-00.0 Intel Corporation 5520 I/O Hub to ESI Port
+-01.0-[0000:01]--+-00.0 Broadcom Corporation NetXtreme II BCM5709 Gigabit Ethernet
| \-00.1 Broadcom Corporation NetXtreme II BCM5709 Gigabit Ethernet
+-03.0-[0000:02]--+-00.0 Broadcom Corporation NetXtreme II BCM5709 Gigabit Ethernet
| \-00.1 Broadcom Corporation NetXtreme II BCM5709 Gigabit Ethernet
+-04.0-[0000:03]----00.0 LSI Logic / Symbios Logic MegaRAID SAS 1078
+-05.0-[0000:04]--
+-06.0-[0000:05]--
+-07.0-[0000:06]--
+-09.0-[0000:07]----00.0 Intel Corporation 82598EB 10-Gigabit AT Network Connection
^ permalink raw reply
* Re: [PATCH] udev: create empty regular files to represent net interfaces
From: Ben Hutchings @ 2009-10-29 16:49 UTC (permalink / raw)
To: Greg KH
Cc: Matt Domsch, Kay Sievers, dann frazier, linux-hotplug, Narendra_K,
netdev, Jordan_Hargrave, Charles_Rose
In-Reply-To: <20091029142554.GA16869@kroah.com>
On Thu, 2009-10-29 at 07:25 -0700, Greg KH wrote:
> On Thu, Oct 29, 2009 at 08:11:25AM -0500, Matt Domsch wrote:
> > Netdev team - are you in agreement that having multiple names to
> > address the same netdevice is a worthwhile thing to add, to allow a
> > variety of naming schemes to exist simultaneously? If not, this whole
> > discussion will be moot, and my basic problem, that the ethX naming
> > convention is nondeterministic, but we need determinism, remains
> > unresolved.
>
> I'm still totally confused as to why you think this. What is wrong with
> what we do today, which is name network devices in a deterministic
> manner by their MAC in userspace? That name goes into the kernel, and
> everyone uses the same name and is happy.
>
> If you don't like naming by MAC, then pick some other deterministic
> naming scheme that works for your hardware and write udev rules for it.
>
> You could easily name them in a way that could keep the lowest number
> (eth0) for the lowest PCI id if you so desired and your BIOS guaranteed
> it.
>
> This way the kernel has only one name, and so does userspace, and
> everyone is happy.
I thought there was a general trend in udev development to provide
default rules that work for almost everyone, so few users/administrators
need to override or add to them. Compare disks and net devices:
1. Stable kernel device id
Disks: block device number
Net devices: ifindex
2. Unique identifier (across reboot)
Disks: label or UUID (each with limitations)
Net devices: (MAC address, subtype)
3. Name assignment mechanism
Disks: kernel suggests a name; udev can assign any number
Net devices: kernel assigns a single name; udev can override it
4. Default name assignment policy
Disks: names disk by device path (id), label and UUID
Net devices: assigns arbitrary stable names per (MAC address, subtype)
5. Naming by users
Disks: user can identify by any method without having to choose on a
system-wide basis
Net devices: user must identify by single name; policy can be overridden
on a system-wide basis
I fully understand the technical reasons for differences 3-5, but why
should users have to put up with it?
Ben.
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
--
To unsubscribe from this list: send the line "unsubscribe linux-hotplug" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH] udev: create empty regular files to represent net interfaces
From: Greg KH @ 2009-10-29 16:52 UTC (permalink / raw)
To: Narendra_K
Cc: Matt_Domsch, kay.sievers, dannf, linux-hotplug, netdev,
Jordan_Hargrave, Charles_Rose, bhutchings
In-Reply-To: <EDA0A4495861324DA2618B4C45DCB3EE589662@blrx3m08.blr.amer.dell.com>
On Thu, Oct 29, 2009 at 10:14:08PM +0530, Narendra_K@Dell.com wrote:
>
> >> Netdev team - are you in agreement that having multiple names to
> >> address the same netdevice is a worthwhile thing to add, to allow a
> >> variety of naming schemes to exist simultaneously? If not,
> >this whole
> >> discussion will be moot, and my basic problem, that the ethX naming
> >> convention is nondeterministic, but we need determinism, remains
> >> unresolved.
> >
> >I'm still totally confused as to why you think this. What is
> >wrong with what we do today, which is name network devices in
> >a deterministic manner by their MAC in userspace? That name
> >goes into the kernel, and everyone uses the same name and is happy.
>
> The interface name as assigned by the OS is determined by how the
> interface is named first during the OS installation.
That sounds like a distro install issue to me, why not fix it there?
> This name is made persistent by associating the name with it's MAC
> address in userspace, either by udev or ifcfg-eth files. In cases
> where there are one or more add-in cards along with one or more
> integrated cards (Lan on Motherboard), the integrated port 1, which is
> designated as Gb1 on the chassis may or may not get the name "eth0".
Exactly, who cares about "eth0" as a name?
> And that is the customer expectation, most of the times.
Then again, fix the installer to allow you to either pick the name, or
specify some rule in which to use to pick the name.
> Unattended installs and large scale image based installs are the most
> affected scenarios.
Then fix the installer.
> >If you don't like naming by MAC, then pick some other
> >deterministic naming scheme that works for your hardware and
> >write udev rules for it.
> >
> >You could easily name them in a way that could keep the lowest number
> >(eth0) for the lowest PCI id if you so desired and your BIOS
> >guaranteed it.
> >
>
> This is how the lspci tree view on a PER710 (PowerEdge R710) server with
> Four BCM5709 integrated NIC ports and One add-in Intel NIC port looks
> like. The integrated ports are always found before the add-in nic (or
> nics) by the BIOS consistently and BIOS guarantees it across every
> reboot.
Great, then you are set to write a udev rule for this, right?
> If the OS also found and named the network ports in the same manner,
> then there is no issue as integrated NIC port 1, designated Gb1 on the
> chassis, is always named as "eth0". But the observation is that, it is
> not the case always.
Sure, it's never guaranteed by the kernel that this will happen,
especially as we speed up the boot process by doing things async.
So again, just fix your installer, or write a new udev rule for your
hardware platforms, or both. But I still fail to see why multiple names
for network devices _in the kernel_ is a solution for your issue.
> In such cases, pathnames like Embedded_NIC_1 -> eth[01..], point to the
> right interface, and communicate a more meaningful name without any
> state embedded in them.
Yes, pathnames would be nice to work for network devices, but
unfortunatly, that's just not how network devices work :)
thanks,
greg k-h
^ permalink raw reply
* Re: [PATCH 2/3] net: TCP thin linear timeouts
From: apetlund @ 2009-10-29 16:54 UTC (permalink / raw)
To: Arnd Hannemann
Cc: Andreas Petlund, Eric Dumazet, netdev@vger.kernel.org,
linux-kernel@vger.kernel.org, shemminger@vyatta.com,
ilpo.jarvinen@helsinki.fi, davem@davemloft.net
> Andreas Petlund schrieb:
>> We have found no noticeable degradation of the goodput in a series of
experiments we have performed in order to map the effects of the
modifications. Furthermore, the modifications implemented in the
patches
>> are explicitly enabled only for applications where the developer knows
that streams will be thin, thus only a small subset of the streams will
apply the modifications.
>> Graphs presenting results from experiments performed to analyse latency
and fairness issues can be found here:
>> http://folk.uio.no/apetlund/lktmp/
>
> How often did you hit consecutive RTOs in these measurements?
> As I see you did a measurement with 512 thick vs. 512 thin streams. Lets
do a hypothetical calculation with only 512 "thin" streams. Lets further
assume the rtt is low, so that RTO is around 200ms. Assume each segment
has 128 Bytes (already very small...).
> Assume after a period of normal operation all streams are in
> timeout-based loss recovery. (e.g. because destination endpoint
> suddenly behaves like a black hole)
> As all streams are in timeout-based loss recovery, each stream
> will transmit 5 segments each second with your modification.
> This would result in a throughput around 512*5*1024bit = 2560 kbit/s and
a goodput of 0 kbit/s (because the receiver is a black hole). So you can
easily saturate a 2 MBit/s link, only with retransmissions.
I have not yet performed experiments where the receiver becomes a black
hole, but I recognise the problem. Eric Dumazet suggested that the
mechanism switch to exponential backoff after 6 linear retries. This would
avoid situation where the link stays congested indefinitely, and I will
implement this in the next iteration.
> Unfortunately in Germany an ADSL uplink of 786 kbit/s is still quite
common, and its already called "broadband"...
I believe that a subscriber for such an uplink would not keep several
hundred thin-stream connections, though accidents do happen.
> Regarding the "small subset", why have a global sysctl option, then? And
I think "tcp_stream_is_thin(tp)" will be true for every flow in the RTO
case, at least for consecutive RTOs.
The sysctl is ment for cases of proprietary code that will benefit from
the modifications. In our experiments, we have found it useful in many
cases for such applications (like game clients).
Regards,
Andreas
^ permalink raw reply
* Re: [PATCH] udev: create empty regular files to represent net interfaces
From: Greg KH @ 2009-10-29 16:55 UTC (permalink / raw)
To: Ben Hutchings
Cc: Matt Domsch, Kay Sievers, dann frazier, linux-hotplug, Narendra_K,
netdev, Jordan_Hargrave, Charles_Rose
In-Reply-To: <1256834975.2827.63.camel@achroite>
On Thu, Oct 29, 2009 at 04:49:35PM +0000, Ben Hutchings wrote:
> 3. Name assignment mechanism
> Disks: kernel suggests a name; udev can assign any number
> ???Net devices: kernel assigns a single name; udev can override it
>
> 4. Default name assignment policy
> Disks: names disk by device path (id), label and UUID
> ???Net devices: assigns arbitrary stable names per (MAC address, subtype)
>
> 5. Naming by users
> Disks: user can identify by any method without having to choose on a
> system-wide basis
> Net devices: user must identify by single name; policy can be overridden
> on a system-wide basis
>
> I fully understand the technical reasons for differences 3-5, but why
> should users have to put up with it?
That is because network devices are not referred to by /dev/ nodes where
multiple symlinks would solve the naming problem.
thanks,
greg k-h
^ permalink raw reply
* Re: [PATCH 2/3] net: TCP thin linear timeouts
From: Rick Jones @ 2009-10-29 17:01 UTC (permalink / raw)
To: Andreas Petlund
Cc: Ilpo Järvinen, Arnd Hannemann, Eric Dumazet, Netdev, LKML,
shemminger, David Miller
In-Reply-To: <58396856-6D7E-4CE1-8D66-D1F11205B0D5@simula.no>
Just how thin can a thin stream be when a thin stream is found thin? (to the
cadence of "How much wood could a woodchuck chuck if a woodchuck could chuck wood?")
Does a stream get so thin that a user's send could not be split into four,
sub-MSS TCP segments?
rick jones
^ permalink raw reply
* RE: [Pv-drivers] [PATCH] vmxnet3: remove duplicate #include
From: Shreyas Bhatewara @ 2009-10-29 17:06 UTC (permalink / raw)
To: David Miller, Bhavesh Davda; +Cc: pv-drivers@vmware.com, netdev@vger.kernel.org
In-Reply-To: <20091029.065011.19666108.davem@davemloft.net>
> -----Original Message-----
> From: David Miller [mailto:davem@davemloft.net]
> Sent: Thursday, October 29, 2009 6:50 AM
> To: Bhavesh Davda
> Cc: Shreyas Bhatewara; pv-drivers@vmware.com; netdev@vger.kernel.org;
> weiyi.huang@gmail.com
> Subject: Re: [Pv-drivers] [PATCH] vmxnet3: remove duplicate #include
>
> From: Bhavesh Davda <bhavesh@vmware.com>
> Date: Thu, 29 Oct 2009 06:35:35 -0700
>
> > In other words, don't just trivially remove the X86 Kconfig
> > requirement for this driver.
>
> Then I assume you're going to add the endianness handling
> and send me a patch soon?
Yes, I will post a patch soon.
Thanks.
->Shreyas
^ permalink raw reply
* Re: [PATCH] udev: create empty regular files to represent net interfaces
From: Ben Hutchings @ 2009-10-29 17:12 UTC (permalink / raw)
To: Greg KH
Cc: Matt Domsch, Kay Sievers, dann frazier, linux-hotplug, Narendra_K,
netdev, Jordan_Hargrave, Charles_Rose
In-Reply-To: <20091029165556.GA9846@kroah.com>
On Thu, 2009-10-29 at 09:55 -0700, Greg KH wrote:
> On Thu, Oct 29, 2009 at 04:49:35PM +0000, Ben Hutchings wrote:
> > 3. Name assignment mechanism
> > Disks: kernel suggests a name; udev can assign any number
> > ???Net devices: kernel assigns a single name; udev can override it
> >
> > 4. Default name assignment policy
> > Disks: names disk by device path (id), label and UUID
> > ???Net devices: assigns arbitrary stable names per (MAC address, subtype)
> >
> > 5. Naming by users
> > Disks: user can identify by any method without having to choose on a
> > system-wide basis
> > Net devices: user must identify by single name; policy can be overridden
> > on a system-wide basis
> >
> > I fully understand the technical reasons for differences 3-5, but why
> > should users have to put up with it?
>
> That is because network devices are not referred to by /dev/ nodes where
> multiple symlinks would solve the naming problem.
Did you even read the last sentence?
Ben.
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply
* [PATCH 1/4] gro: Name the GRO result enumeration type
From: Ben Hutchings @ 2009-10-29 17:17 UTC (permalink / raw)
To: David Miller; +Cc: Herbert Xu, netdev, linux-net-drivers
This clarifies which return and parameter types are GRO result codes
and not RX result codes.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
include/linux/netdevice.h | 10 ++++++----
net/8021q/vlan_core.c | 5 +++--
net/core/dev.c | 12 +++++++-----
3 files changed, 16 insertions(+), 11 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8380009..9fdf48e 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -348,13 +348,14 @@ enum
NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */
};
-enum {
+enum gro_result {
GRO_MERGED,
GRO_MERGED_FREE,
GRO_HELD,
GRO_NORMAL,
GRO_DROP,
};
+typedef enum gro_result gro_result_t;
extern void __napi_schedule(struct napi_struct *n);
@@ -1467,16 +1468,17 @@ extern int netif_rx_ni(struct sk_buff *skb);
#define HAVE_NETIF_RECEIVE_SKB 1
extern int netif_receive_skb(struct sk_buff *skb);
extern void napi_gro_flush(struct napi_struct *napi);
-extern int dev_gro_receive(struct napi_struct *napi,
+extern gro_result_t dev_gro_receive(struct napi_struct *napi,
struct sk_buff *skb);
-extern int napi_skb_finish(int ret, struct sk_buff *skb);
+extern int napi_skb_finish(gro_result_t ret, struct sk_buff *skb);
extern int napi_gro_receive(struct napi_struct *napi,
struct sk_buff *skb);
extern void napi_reuse_skb(struct napi_struct *napi,
struct sk_buff *skb);
extern struct sk_buff * napi_get_frags(struct napi_struct *napi);
extern int napi_frags_finish(struct napi_struct *napi,
- struct sk_buff *skb, int ret);
+ struct sk_buff *skb,
+ gro_result_t ret);
extern struct sk_buff * napi_frags_skb(struct napi_struct *napi);
extern int napi_gro_frags(struct napi_struct *napi);
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 7f7de1a..47a80d6 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -74,8 +74,9 @@ u16 vlan_dev_vlan_id(const struct net_device *dev)
}
EXPORT_SYMBOL(vlan_dev_vlan_id);
-static int vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp,
- unsigned int vlan_tci, struct sk_buff *skb)
+static gro_result_t
+vlan_gro_common(struct napi_struct *napi, struct vlan_group *grp,
+ unsigned int vlan_tci, struct sk_buff *skb)
{
struct sk_buff *p;
diff --git a/net/core/dev.c b/net/core/dev.c
index 28b0b9e..421dc93 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2439,7 +2439,7 @@ void napi_gro_flush(struct napi_struct *napi)
}
EXPORT_SYMBOL(napi_gro_flush);
-int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff **pp = NULL;
struct packet_type *ptype;
@@ -2447,7 +2447,7 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
struct list_head *head = &ptype_base[ntohs(type) & PTYPE_HASH_MASK];
int same_flow;
int mac_len;
- int ret;
+ enum gro_result ret;
if (!(skb->dev->features & NETIF_F_GRO))
goto normal;
@@ -2531,7 +2531,8 @@ normal:
}
EXPORT_SYMBOL(dev_gro_receive);
-static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+static gro_result_t
+__napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
struct sk_buff *p;
@@ -2548,7 +2549,7 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
return dev_gro_receive(napi, skb);
}
-int napi_skb_finish(int ret, struct sk_buff *skb)
+int napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
{
int err = NET_RX_SUCCESS;
@@ -2615,7 +2616,8 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
}
EXPORT_SYMBOL(napi_get_frags);
-int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, int ret)
+int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
+ gro_result_t ret)
{
int err = NET_RX_SUCCESS;
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply related
* [PATCH 2/4] gro: Change all receive functions to return GRO result codes
From: Ben Hutchings @ 2009-10-29 17:18 UTC (permalink / raw)
To: David Miller; +Cc: Herbert Xu, netdev, linux-net-drivers
This will allow drivers to adjust their receive path dynamically
based on whether GRO is being applied successfully.
Currently all in-tree callers ignore the return values of these
functions and do not need to be changed.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
include/linux/if_vlan.h | 25 ++++++++++++++-----------
include/linux/netdevice.h | 8 ++++----
net/8021q/vlan_core.c | 16 +++++++++-------
net/core/dev.c | 38 +++++++++++++++-----------------------
4 files changed, 42 insertions(+), 45 deletions(-)
diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 7ff9af1..5be7680 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -115,10 +115,12 @@ extern u16 vlan_dev_vlan_id(const struct net_device *dev);
extern int __vlan_hwaccel_rx(struct sk_buff *skb, struct vlan_group *grp,
u16 vlan_tci, int polling);
extern int vlan_hwaccel_do_receive(struct sk_buff *skb);
-extern int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
- unsigned int vlan_tci, struct sk_buff *skb);
-extern int vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp,
- unsigned int vlan_tci);
+extern gro_result_t
+vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
+ unsigned int vlan_tci, struct sk_buff *skb);
+extern gro_result_t
+vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp,
+ unsigned int vlan_tci);
#else
static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev)
@@ -145,17 +147,18 @@ static inline int vlan_hwaccel_do_receive(struct sk_buff *skb)
return 0;
}
-static inline int vlan_gro_receive(struct napi_struct *napi,
- struct vlan_group *grp,
- unsigned int vlan_tci, struct sk_buff *skb)
+static inline gro_result_t
+vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
+ unsigned int vlan_tci, struct sk_buff *skb)
{
- return NET_RX_DROP;
+ return GRO_DROP;
}
-static inline int vlan_gro_frags(struct napi_struct *napi,
- struct vlan_group *grp, unsigned int vlan_tci)
+static inline gro_result_t
+vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp,
+ unsigned int vlan_tci)
{
- return NET_RX_DROP;
+ return GRO_DROP;
}
#endif
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9fdf48e..218a0f6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1470,17 +1470,17 @@ extern int netif_receive_skb(struct sk_buff *skb);
extern void napi_gro_flush(struct napi_struct *napi);
extern gro_result_t dev_gro_receive(struct napi_struct *napi,
struct sk_buff *skb);
-extern int napi_skb_finish(gro_result_t ret, struct sk_buff *skb);
-extern int napi_gro_receive(struct napi_struct *napi,
+extern gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb);
+extern gro_result_t napi_gro_receive(struct napi_struct *napi,
struct sk_buff *skb);
extern void napi_reuse_skb(struct napi_struct *napi,
struct sk_buff *skb);
extern struct sk_buff * napi_get_frags(struct napi_struct *napi);
-extern int napi_frags_finish(struct napi_struct *napi,
+extern gro_result_t napi_frags_finish(struct napi_struct *napi,
struct sk_buff *skb,
gro_result_t ret);
extern struct sk_buff * napi_frags_skb(struct napi_struct *napi);
-extern int napi_gro_frags(struct napi_struct *napi);
+extern gro_result_t napi_gro_frags(struct napi_struct *napi);
static inline void napi_free_frags(struct napi_struct *napi)
{
diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c
index 47a80d6..8d5ca2a 100644
--- a/net/8021q/vlan_core.c
+++ b/net/8021q/vlan_core.c
@@ -102,11 +102,12 @@ drop:
return GRO_DROP;
}
-int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
- unsigned int vlan_tci, struct sk_buff *skb)
+gro_result_t vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
+ unsigned int vlan_tci, struct sk_buff *skb)
{
if (netpoll_rx_on(skb))
- return vlan_hwaccel_receive_skb(skb, grp, vlan_tci);
+ return vlan_hwaccel_receive_skb(skb, grp, vlan_tci)
+ ? GRO_DROP : GRO_NORMAL;
skb_gro_reset_offset(skb);
@@ -114,17 +115,18 @@ int vlan_gro_receive(struct napi_struct *napi, struct vlan_group *grp,
}
EXPORT_SYMBOL(vlan_gro_receive);
-int vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp,
- unsigned int vlan_tci)
+gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp,
+ unsigned int vlan_tci)
{
struct sk_buff *skb = napi_frags_skb(napi);
if (!skb)
- return NET_RX_DROP;
+ return GRO_DROP;
if (netpoll_rx_on(skb)) {
skb->protocol = eth_type_trans(skb, skb->dev);
- return vlan_hwaccel_receive_skb(skb, grp, vlan_tci);
+ return vlan_hwaccel_receive_skb(skb, grp, vlan_tci)
+ ? GRO_DROP : GRO_NORMAL;
}
return napi_frags_finish(napi, skb,
diff --git a/net/core/dev.c b/net/core/dev.c
index 421dc93..f1bf49f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2549,24 +2549,21 @@ __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
return dev_gro_receive(napi, skb);
}
-int napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
+gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb)
{
- int err = NET_RX_SUCCESS;
-
switch (ret) {
case GRO_NORMAL:
- return netif_receive_skb(skb);
+ if (netif_receive_skb(skb))
+ ret = GRO_DROP;
+ break;
case GRO_DROP:
- err = NET_RX_DROP;
- /* fall through */
-
case GRO_MERGED_FREE:
kfree_skb(skb);
break;
}
- return err;
+ return ret;
}
EXPORT_SYMBOL(napi_skb_finish);
@@ -2586,7 +2583,7 @@ void skb_gro_reset_offset(struct sk_buff *skb)
}
EXPORT_SYMBOL(skb_gro_reset_offset);
-int napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
+gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
{
skb_gro_reset_offset(skb);
@@ -2616,32 +2613,27 @@ struct sk_buff *napi_get_frags(struct napi_struct *napi)
}
EXPORT_SYMBOL(napi_get_frags);
-int napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
- gro_result_t ret)
+gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb,
+ gro_result_t ret)
{
- int err = NET_RX_SUCCESS;
-
switch (ret) {
case GRO_NORMAL:
case GRO_HELD:
skb->protocol = eth_type_trans(skb, napi->dev);
- if (ret == GRO_NORMAL)
- return netif_receive_skb(skb);
-
- skb_gro_pull(skb, -ETH_HLEN);
+ if (ret == GRO_HELD)
+ skb_gro_pull(skb, -ETH_HLEN);
+ else if (netif_receive_skb(skb))
+ ret = GRO_DROP;
break;
case GRO_DROP:
- err = NET_RX_DROP;
- /* fall through */
-
case GRO_MERGED_FREE:
napi_reuse_skb(napi, skb);
break;
}
- return err;
+ return ret;
}
EXPORT_SYMBOL(napi_frags_finish);
@@ -2682,12 +2674,12 @@ out:
}
EXPORT_SYMBOL(napi_frags_skb);
-int napi_gro_frags(struct napi_struct *napi)
+gro_result_t napi_gro_frags(struct napi_struct *napi)
{
struct sk_buff *skb = napi_frags_skb(napi);
if (!skb)
- return NET_RX_DROP;
+ return GRO_DROP;
return napi_frags_finish(napi, skb, __napi_gro_receive(napi, skb));
}
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply related
* Re: [PATCH] udev: create empty regular files to represent net interfaces
From: Greg KH @ 2009-10-29 17:20 UTC (permalink / raw)
To: Ben Hutchings
Cc: Matt Domsch, Kay Sievers, dann frazier, linux-hotplug, Narendra_K,
netdev, Jordan_Hargrave, Charles_Rose
In-Reply-To: <1256836333.2827.65.camel@achroite>
On Thu, Oct 29, 2009 at 05:12:13PM +0000, Ben Hutchings wrote:
> On Thu, 2009-10-29 at 09:55 -0700, Greg KH wrote:
> > On Thu, Oct 29, 2009 at 04:49:35PM +0000, Ben Hutchings wrote:
> > > 3. Name assignment mechanism
> > > Disks: kernel suggests a name; udev can assign any number
> > > ???Net devices: kernel assigns a single name; udev can override it
> > >
> > > 4. Default name assignment policy
> > > Disks: names disk by device path (id), label and UUID
> > > ???Net devices: assigns arbitrary stable names per (MAC address, subtype)
> > >
> > > 5. Naming by users
> > > Disks: user can identify by any method without having to choose on a
> > > system-wide basis
> > > Net devices: user must identify by single name; policy can be overridden
> > > on a system-wide basis
> > >
> > > I fully understand the technical reasons for differences 3-5, but why
> > > should users have to put up with it?
> >
> > That is because network devices are not referred to by /dev/ nodes where
> > multiple symlinks would solve the naming problem.
>
> Did you even read the last sentence?
Yes, the technical reason is the reason why users have to put up
with it :)
^ permalink raw reply
* [PATCH 3/4] sfc: Feed GRO result into RX allocation policy and interrupt moderation
From: Ben Hutchings @ 2009-10-29 17:21 UTC (permalink / raw)
To: David Miller; +Cc: netdev, linux-net-drivers
When GRO is successfully merging received packets, we should allocate
raw page buffers rather than skbs that will be discarded by GRO.
Otherwise, we should allocate skbs.
GRO also benefits from higher interrupt moderation, so increase the
score for mergeable RX packets.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
drivers/net/sfc/rx.c | 13 +++++++++++--
1 files changed, 11 insertions(+), 2 deletions(-)
diff --git a/drivers/net/sfc/rx.c b/drivers/net/sfc/rx.c
index 4b65c62..9277e9a 100644
--- a/drivers/net/sfc/rx.c
+++ b/drivers/net/sfc/rx.c
@@ -445,6 +445,7 @@ static void efx_rx_packet_lro(struct efx_channel *channel,
bool checksummed)
{
struct napi_struct *napi = &channel->napi_str;
+ gro_result_t gro_result;
/* Pass the skb/page into the LRO engine */
if (rx_buf->page) {
@@ -452,6 +453,7 @@ static void efx_rx_packet_lro(struct efx_channel *channel,
if (!skb) {
put_page(rx_buf->page);
+ gro_result = GRO_DROP;
goto out;
}
@@ -467,7 +469,7 @@ static void efx_rx_packet_lro(struct efx_channel *channel,
skb->ip_summed =
checksummed ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE;
- napi_gro_frags(napi);
+ gro_result = napi_gro_frags(napi);
out:
EFX_BUG_ON_PARANOID(rx_buf->skb);
@@ -476,9 +478,16 @@ out:
EFX_BUG_ON_PARANOID(!rx_buf->skb);
EFX_BUG_ON_PARANOID(!checksummed);
- napi_gro_receive(napi, rx_buf->skb);
+ gro_result = napi_gro_receive(napi, rx_buf->skb);
rx_buf->skb = NULL;
}
+
+ if (gro_result == GRO_NORMAL) {
+ channel->rx_alloc_level += RX_ALLOC_FACTOR_SKB;
+ } else if (gro_result != GRO_DROP) {
+ channel->rx_alloc_level += RX_ALLOC_FACTOR_LRO;
+ channel->irq_mod_score += 2;
+ }
}
void efx_rx_packet(struct efx_rx_queue *rx_queue, unsigned int index,
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply related
* [PATCH 4/4] sfc: Enable heuristic selection between page and skb RX buffers
From: Ben Hutchings @ 2009-10-29 17:21 UTC (permalink / raw)
To: David Miller; +Cc: netdev, linux-net-drivers
Now that we can tell whether GRO is being applied, this heuristic is
effective once more.
Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
---
drivers/net/sfc/rx.c | 2 +-
1 files changed, 1 insertions(+), 1 deletions(-)
diff --git a/drivers/net/sfc/rx.c b/drivers/net/sfc/rx.c
index 9277e9a..a60c718 100644
--- a/drivers/net/sfc/rx.c
+++ b/drivers/net/sfc/rx.c
@@ -61,7 +61,7 @@
* rx_alloc_method = (rx_alloc_level > RX_ALLOC_LEVEL_LRO ?
* RX_ALLOC_METHOD_PAGE : RX_ALLOC_METHOD_SKB)
*/
-static int rx_alloc_method = RX_ALLOC_METHOD_PAGE;
+static int rx_alloc_method = RX_ALLOC_METHOD_AUTO;
#define RX_ALLOC_LEVEL_LRO 0x2000
#define RX_ALLOC_LEVEL_MAX 0x3000
--
Ben Hutchings, Senior Software Engineer, Solarflare Communications
Not speaking for my employer; that's the marketing department's job.
They asked us to note that Solarflare product names are trademarked.
^ permalink raw reply related
* RE: [PATCH] udev: create empty regular files to represent netinterfaces
From: Narendra_K @ 2009-10-29 17:22 UTC (permalink / raw)
To: greg
Cc: Matt_Domsch, kay.sievers, dannf, linux-hotplug, netdev,
Jordan_Hargrave, Charles_Rose, bhutchings
In-Reply-To: <20091029165259.GA9692@kroah.com>
>Sure, it's never guaranteed by the kernel that this will
>happen, especially as we speed up the boot process by doing
>things async.
>So again, just fix your installer, or write a new udev rule
>for your hardware platforms, or both. But I still fail to see
>why multiple names for network devices _in the kernel_ is a
>solution for your issue.
>
The char device nodes solution does not propose having multiple names
for the network interfaces _in the kernel_. It is suggesting that we
have alternate names for kernel assigned names in user space and user
space utilities refer to the interface by these alternate names. The
userspace utilities would have to map the pathnames to kernel names
before issuing the ioctls. That way there is determinism without
embedding MAC or any other attribute. An Embedded_NIC_1 interface would
always refer to the Gb1 without having to depend on any attribute.
With regards,
Narendra K
^ permalink raw reply
* Re: [PATCH 4/6] vlan: Optimize multiple unregistration
From: Patrick McHardy @ 2009-10-29 17:25 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David S. Miller, Linux Netdev List
In-Reply-To: <4AE9AA01.3020805@gmail.com>
Eric Dumazet wrote:
> Patrick McHardy a écrit :
>
>> Indeed, but unregister_vlan_dev() destroys the group once the
>> count has reached zero, so we must not access it after that.
>
> Well, I hoped call_rcu() callback doesnt fire and kfree(grp) until we exited
> from unregister_vlan_dev_alls(), with RTNL locked...
The RTNL is a mutex, so it shouldn't prevent call_rcu from firing.
^ permalink raw reply
* Re: [PATCH] udev: create empty regular files to represent net interfaces
From: dann frazier @ 2009-10-29 17:46 UTC (permalink / raw)
To: Greg KH
Cc: Matt Domsch, Kay Sievers, linux-hotplug, Narendra_K, netdev,
Jordan_Hargrave, Charles_Rose, Ben Hutchings
In-Reply-To: <20091029142554.GA16869@kroah.com>
On Thu, Oct 29, 2009 at 07:25:54AM -0700, Greg KH wrote:
> On Thu, Oct 29, 2009 at 08:11:25AM -0500, Matt Domsch wrote:
> > Netdev team - are you in agreement that having multiple names to
> > address the same netdevice is a worthwhile thing to add, to allow a
> > variety of naming schemes to exist simultaneously? If not, this whole
> > discussion will be moot, and my basic problem, that the ethX naming
> > convention is nondeterministic, but we need determinism, remains
> > unresolved.
>
> I'm still totally confused as to why you think this. What is wrong with
> what we do today, which is name network devices in a deterministic
> manner by their MAC in userspace? That name goes into the kernel, and
> everyone uses the same name and is happy.
>
> If you don't like naming by MAC, then pick some other deterministic
> naming scheme that works for your hardware and write udev rules for it.
>
> You could easily name them in a way that could keep the lowest number
> (eth0) for the lowest PCI id if you so desired and your BIOS guaranteed
> it.
>
> This way the kernel has only one name, and so does userspace, and
> everyone is happy.
There are two issues, which really seem distinct to me.
Users expect eth0 to map to first-onboard-nic. That's an installer
issue (since the BIOS can already export this info) and I agree that
if we want to "fix" that, we should fix it there.
Users also want to have a name that matches the way they think of
their hardware - pci slot, bios-exposed-name, mac address,
whatever. This can be done today w/ custom udev rules, and I can
visualize an installer that would generate these rules for you:
Configure a NIC
\-> Choose NIC by: MAC/CHASSIS-NAME/PCI-SLOT
[ Present list of unconfigured NICs by selected property ]
\-> What name would you like to use for this interface [eth3]?
How do you want this configured (DHCP/STATIC/..)
...
That would make a lot of users much happier (myself included), but it
does restrict us into one view. At different times, admins think of
their NICs by different properties. I may want to do IP assignment by
the chassis name, but then run ethereal on a specific mac address. Or
I may want to see the routes assigned to all NICs in a given PCI
slot. Sure, I can lookup all of these properties and map them back to
an interface name by hand, but aliasing provides a nice way to
short-circuit that. And, by providing a library that translates the
aliases for us, we can help ensure that all apps that want to provide
aliasing can do so in a common way.
--
dann frazier
^ permalink raw reply
* Re: [PATCH 1/4] gro: Name the GRO result enumeration type
From: Herbert Xu @ 2009-10-29 17:48 UTC (permalink / raw)
To: Ben Hutchings; +Cc: David Miller, netdev, linux-net-drivers
In-Reply-To: <1256836629.2827.69.camel@achroite>
On Thu, Oct 29, 2009 at 05:17:09PM +0000, Ben Hutchings wrote:
> This clarifies which return and parameter types are GRO result codes
> and not RX result codes.
>
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
* Re: [PATCH 2/4] gro: Change all receive functions to return GRO result codes
From: Herbert Xu @ 2009-10-29 17:48 UTC (permalink / raw)
To: Ben Hutchings; +Cc: David Miller, netdev, linux-net-drivers
In-Reply-To: <1256836695.2827.71.camel@achroite>
On Thu, Oct 29, 2009 at 05:18:15PM +0000, Ben Hutchings wrote:
> This will allow drivers to adjust their receive path dynamically
> based on whether GRO is being applied successfully.
>
> Currently all in-tree callers ignore the return values of these
> functions and do not need to be changed.
>
> Signed-off-by: Ben Hutchings <bhutchings@solarflare.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox