diff options
390 files changed, 13099 insertions, 6490 deletions
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt index b959659..ccb6048 100644 --- a/Documentation/feature-removal-schedule.txt +++ b/Documentation/feature-removal-schedule.txt @@ -603,3 +603,10 @@ Why: The adm9240, w83792d and w83793 hardware monitoring drivers have Who: Jean Delvare <khali@linux-fr.org> ---------------------------- + +What: xt_connlimit rev 0 +When: 2012 +Who: Jan Engelhardt <jengelh@medozas.de> +Files: net/netfilter/xt_connlimit.c + +---------------------------- diff --git a/drivers/net/atl1c/atl1c_hw.c b/drivers/net/atl1c/atl1c_hw.c index 1bf6720..23f2ab0 100644 --- a/drivers/net/atl1c/atl1c_hw.c +++ b/drivers/net/atl1c/atl1c_hw.c @@ -345,7 +345,7 @@ int atl1c_write_phy_reg(struct atl1c_hw *hw, u32 reg_addr, u16 phy_data) */ static int atl1c_phy_setup_adv(struct atl1c_hw *hw) { - u16 mii_adv_data = ADVERTISE_DEFAULT_CAP & ~ADVERTISE_SPEED_MASK; + u16 mii_adv_data = ADVERTISE_DEFAULT_CAP & ~ADVERTISE_ALL; u16 mii_giga_ctrl_data = GIGA_CR_1000T_DEFAULT_CAP & ~GIGA_CR_1000T_SPEED_MASK; @@ -373,7 +373,7 @@ static int atl1c_phy_setup_adv(struct atl1c_hw *hw) } if (atl1c_write_phy_reg(hw, MII_ADVERTISE, mii_adv_data) != 0 || - atl1c_write_phy_reg(hw, MII_GIGA_CR, mii_giga_ctrl_data) != 0) + atl1c_write_phy_reg(hw, MII_CTRL1000, mii_giga_ctrl_data) != 0) return -1; return 0; } @@ -517,19 +517,18 @@ int atl1c_phy_init(struct atl1c_hw *hw) "Error Setting up Auto-Negotiation\n"); return ret_val; } - mii_bmcr_data |= BMCR_AUTO_NEG_EN | BMCR_RESTART_AUTO_NEG; + mii_bmcr_data |= BMCR_ANENABLE | BMCR_ANRESTART; break; case MEDIA_TYPE_100M_FULL: - mii_bmcr_data |= BMCR_SPEED_100 | BMCR_FULL_DUPLEX; + mii_bmcr_data |= BMCR_SPEED100 | BMCR_FULLDPLX; break; case MEDIA_TYPE_100M_HALF: - mii_bmcr_data |= BMCR_SPEED_100; + mii_bmcr_data |= BMCR_SPEED100; break; case MEDIA_TYPE_10M_FULL: - mii_bmcr_data |= BMCR_SPEED_10 | BMCR_FULL_DUPLEX; + mii_bmcr_data |= BMCR_FULLDPLX; break; case MEDIA_TYPE_10M_HALF: - mii_bmcr_data |= BMCR_SPEED_10; break; default: if (netif_msg_link(adapter)) @@ -657,7 +656,7 @@ int atl1c_restart_autoneg(struct atl1c_hw *hw) err = atl1c_phy_setup_adv(hw); if (err) return err; - mii_bmcr_data |= BMCR_AUTO_NEG_EN | BMCR_RESTART_AUTO_NEG; + mii_bmcr_data |= BMCR_ANENABLE | BMCR_ANRESTART; return atl1c_write_phy_reg(hw, MII_BMCR, mii_bmcr_data); } diff --git a/drivers/net/atl1c/atl1c_hw.h b/drivers/net/atl1c/atl1c_hw.h index 3dd6759..655fc6c 100644 --- a/drivers/net/atl1c/atl1c_hw.h +++ b/drivers/net/atl1c/atl1c_hw.h @@ -736,55 +736,16 @@ int atl1c_phy_power_saving(struct atl1c_hw *hw); #define REG_DEBUG_DATA0 0x1900 #define REG_DEBUG_DATA1 0x1904 -/* PHY Control Register */ -#define MII_BMCR 0x00 -#define BMCR_SPEED_SELECT_MSB 0x0040 /* bits 6,13: 10=1000, 01=100, 00=10 */ -#define BMCR_COLL_TEST_ENABLE 0x0080 /* Collision test enable */ -#define BMCR_FULL_DUPLEX 0x0100 /* FDX =1, half duplex =0 */ -#define BMCR_RESTART_AUTO_NEG 0x0200 /* Restart auto negotiation */ -#define BMCR_ISOLATE 0x0400 /* Isolate PHY from MII */ -#define BMCR_POWER_DOWN 0x0800 /* Power down */ -#define BMCR_AUTO_NEG_EN 0x1000 /* Auto Neg Enable */ -#define BMCR_SPEED_SELECT_LSB 0x2000 /* bits 6,13: 10=1000, 01=100, 00=10 */ -#define BMCR_LOOPBACK 0x4000 /* 0 = normal, 1 = loopback */ -#define BMCR_RESET 0x8000 /* 0 = normal, 1 = PHY reset */ -#define BMCR_SPEED_MASK 0x2040 -#define BMCR_SPEED_1000 0x0040 -#define BMCR_SPEED_100 0x2000 -#define BMCR_SPEED_10 0x0000 - -/* PHY Status Register */ -#define MII_BMSR 0x01 -#define BMMSR_EXTENDED_CAPS 0x0001 /* Extended register capabilities */ -#define BMSR_JABBER_DETECT 0x0002 /* Jabber Detected */ -#define BMSR_LINK_STATUS 0x0004 /* Link Status 1 = link */ -#define BMSR_AUTONEG_CAPS 0x0008 /* Auto Neg Capable */ -#define BMSR_REMOTE_FAULT 0x0010 /* Remote Fault Detect */ -#define BMSR_AUTONEG_COMPLETE 0x0020 /* Auto Neg Complete */ -#define BMSR_PREAMBLE_SUPPRESS 0x0040 /* Preamble may be suppressed */ -#define BMSR_EXTENDED_STATUS 0x0100 /* Ext. status info in Reg 0x0F */ -#define BMSR_100T2_HD_CAPS 0x0200 /* 100T2 Half Duplex Capable */ -#define BMSR_100T2_FD_CAPS 0x0400 /* 100T2 Full Duplex Capable */ -#define BMSR_10T_HD_CAPS 0x0800 /* 10T Half Duplex Capable */ -#define BMSR_10T_FD_CAPS 0x1000 /* 10T Full Duplex Capable */ -#define BMSR_100X_HD_CAPS 0x2000 /* 100X Half Duplex Capable */ -#define BMMII_SR_100X_FD_CAPS 0x4000 /* 100X Full Duplex Capable */ -#define BMMII_SR_100T4_CAPS 0x8000 /* 100T4 Capable */ - -#define MII_PHYSID1 0x02 -#define MII_PHYSID2 0x03 #define L1D_MPW_PHYID1 0xD01C /* V7 */ #define L1D_MPW_PHYID2 0xD01D /* V1-V6 */ #define L1D_MPW_PHYID3 0xD01E /* V8 */ /* Autoneg Advertisement Register */ -#define MII_ADVERTISE 0x04 -#define ADVERTISE_SPEED_MASK 0x01E0 -#define ADVERTISE_DEFAULT_CAP 0x0DE0 +#define ADVERTISE_DEFAULT_CAP \ + (ADVERTISE_ALL | ADVERTISE_PAUSE_CAP | ADVERTISE_PAUSE_ASYM) /* 1000BASE-T Control Register */ -#define MII_GIGA_CR 0x09 #define GIGA_CR_1000T_REPEATER_DTE 0x0400 /* 1=Repeater/switch device port 0=DTE device */ #define GIGA_CR_1000T_MS_VALUE 0x0800 /* 1=Configure PHY as Master 0=Configure PHY as Slave */ diff --git a/drivers/net/atl1e/atl1e_ethtool.c b/drivers/net/atl1e/atl1e_ethtool.c index 6943a6c..1209297 100644 --- a/drivers/net/atl1e/atl1e_ethtool.c +++ b/drivers/net/atl1e/atl1e_ethtool.c @@ -95,18 +95,18 @@ static int atl1e_set_settings(struct net_device *netdev, ecmd->advertising = hw->autoneg_advertised | ADVERTISED_TP | ADVERTISED_Autoneg; - adv4 = hw->mii_autoneg_adv_reg & ~MII_AR_SPEED_MASK; + adv4 = hw->mii_autoneg_adv_reg & ~ADVERTISE_ALL; adv9 = hw->mii_1000t_ctrl_reg & ~MII_AT001_CR_1000T_SPEED_MASK; if (hw->autoneg_advertised & ADVERTISE_10_HALF) - adv4 |= MII_AR_10T_HD_CAPS; + adv4 |= ADVERTISE_10HALF; if (hw->autoneg_advertised & ADVERTISE_10_FULL) - adv4 |= MII_AR_10T_FD_CAPS; + adv4 |= ADVERTISE_10FULL; if (hw->autoneg_advertised & ADVERTISE_100_HALF) - adv4 |= MII_AR_100TX_HD_CAPS; + adv4 |= ADVERTISE_100HALF; if (hw->autoneg_advertised & ADVERTISE_100_FULL) - adv4 |= MII_AR_100TX_FD_CAPS; + adv4 |= ADVERTISE_100FULL; if (hw->autoneg_advertised & ADVERTISE_1000_FULL) - adv9 |= MII_AT001_CR_1000T_FD_CAPS; + adv9 |= ADVERTISE_1000FULL; if (adv4 != hw->mii_autoneg_adv_reg || adv9 != hw->mii_1000t_ctrl_reg) { diff --git a/drivers/net/atl1e/atl1e_hw.c b/drivers/net/atl1e/atl1e_hw.c index 76cc043..923063d 100644 --- a/drivers/net/atl1e/atl1e_hw.c +++ b/drivers/net/atl1e/atl1e_hw.c @@ -318,7 +318,7 @@ static int atl1e_phy_setup_autoneg_adv(struct atl1e_hw *hw) * Advertisement Register (Address 4) and the 1000 mb speed bits in * the 1000Base-T control Register (Address 9). */ - mii_autoneg_adv_reg &= ~MII_AR_SPEED_MASK; + mii_autoneg_adv_reg &= ~ADVERTISE_ALL; mii_1000t_ctrl_reg &= ~MII_AT001_CR_1000T_SPEED_MASK; /* @@ -327,44 +327,37 @@ static int atl1e_phy_setup_autoneg_adv(struct atl1e_hw *hw) */ switch (hw->media_type) { case MEDIA_TYPE_AUTO_SENSOR: - mii_autoneg_adv_reg |= (MII_AR_10T_HD_CAPS | - MII_AR_10T_FD_CAPS | - MII_AR_100TX_HD_CAPS | - MII_AR_100TX_FD_CAPS); - hw->autoneg_advertised = ADVERTISE_10_HALF | - ADVERTISE_10_FULL | - ADVERTISE_100_HALF | - ADVERTISE_100_FULL; + mii_autoneg_adv_reg |= ADVERTISE_ALL; + hw->autoneg_advertised = ADVERTISE_ALL; if (hw->nic_type == athr_l1e) { - mii_1000t_ctrl_reg |= - MII_AT001_CR_1000T_FD_CAPS; + mii_1000t_ctrl_reg |= ADVERTISE_1000FULL; hw->autoneg_advertised |= ADVERTISE_1000_FULL; } break; case MEDIA_TYPE_100M_FULL: - mii_autoneg_adv_reg |= MII_AR_100TX_FD_CAPS; + mii_autoneg_adv_reg |= ADVERTISE_100FULL; hw->autoneg_advertised = ADVERTISE_100_FULL; break; case MEDIA_TYPE_100M_HALF: - mii_autoneg_adv_reg |= MII_AR_100TX_HD_CAPS; + mii_autoneg_adv_reg |= ADVERTISE_100_HALF; hw->autoneg_advertised = ADVERTISE_100_HALF; break; case MEDIA_TYPE_10M_FULL: - mii_autoneg_adv_reg |= MII_AR_10T_FD_CAPS; + mii_autoneg_adv_reg |= ADVERTISE_10_FULL; hw->autoneg_advertised = ADVERTISE_10_FULL; break; default: - mii_autoneg_adv_reg |= MII_AR_10T_HD_CAPS; + mii_autoneg_adv_reg |= ADVERTISE_10_HALF; hw->autoneg_advertised = ADVERTISE_10_HALF; break; } /* flow control fixed to enable all */ - mii_autoneg_adv_reg |= (MII_AR_ASM_DIR | MII_AR_PAUSE); + mii_autoneg_adv_reg |= (ADVERTISE_PAUSE_ASYM | ADVERTISE_PAUSE_CAP); hw->mii_autoneg_adv_reg = mii_autoneg_adv_reg; hw->mii_1000t_ctrl_reg = mii_1000t_ctrl_reg; @@ -374,7 +367,7 @@ static int atl1e_phy_setup_autoneg_adv(struct atl1e_hw *hw) return ret_val; if (hw->nic_type == athr_l1e || hw->nic_type == athr_l2e_revA) { - ret_val = atl1e_write_phy_reg(hw, MII_AT001_CR, + ret_val = atl1e_write_phy_reg(hw, MII_CTRL1000, mii_1000t_ctrl_reg); if (ret_val) return ret_val; @@ -397,7 +390,7 @@ int atl1e_phy_commit(struct atl1e_hw *hw) int ret_val; u16 phy_data; - phy_data = MII_CR_RESET | MII_CR_AUTO_NEG_EN | MII_CR_RESTART_AUTO_NEG; + phy_data = BMCR_RESET | BMCR_ANENABLE | BMCR_ANRESTART; ret_val = atl1e_write_phy_reg(hw, MII_BMCR, phy_data); if (ret_val) { @@ -645,15 +638,14 @@ int atl1e_restart_autoneg(struct atl1e_hw *hw) return err; if (hw->nic_type == athr_l1e || hw->nic_type == athr_l2e_revA) { - err = atl1e_write_phy_reg(hw, MII_AT001_CR, + err = atl1e_write_phy_reg(hw, MII_CTRL1000, hw->mii_1000t_ctrl_reg); if (err) return err; } err = atl1e_write_phy_reg(hw, MII_BMCR, - MII_CR_RESET | MII_CR_AUTO_NEG_EN | - MII_CR_RESTART_AUTO_NEG); + BMCR_RESET | BMCR_ANENABLE | BMCR_ANRESTART); return err; } diff --git a/drivers/net/atl1e/atl1e_hw.h b/drivers/net/atl1e/atl1e_hw.h index 5ea2f4d..74df16a 100644 --- a/drivers/net/atl1e/atl1e_hw.h +++ b/drivers/net/atl1e/atl1e_hw.h @@ -629,127 +629,24 @@ s32 atl1e_restart_autoneg(struct atl1e_hw *hw); /***************************** MII definition ***************************************/ /* PHY Common Register */ -#define MII_BMCR 0x00 -#define MII_BMSR 0x01 -#define MII_PHYSID1 0x02 -#define MII_PHYSID2 0x03 -#define MII_ADVERTISE 0x04 -#define MII_LPA 0x05 -#define MII_EXPANSION 0x06 -#define MII_AT001_CR 0x09 -#define MII_AT001_SR 0x0A -#define MII_AT001_ESR 0x0F #define MII_AT001_PSCR 0x10 #define MII_AT001_PSSR 0x11 #define MII_INT_CTRL 0x12 #define MII_INT_STATUS 0x13 #define MII_SMARTSPEED 0x14 -#define MII_RERRCOUNTER 0x15 -#define MII_SREVISION 0x16 -#define MII_RESV1 0x17 #define MII_LBRERROR 0x18 -#define MII_PHYADDR 0x19 #define MII_RESV2 0x1a -#define MII_TPISTATUS 0x1b -#define MII_NCONFIG 0x1c #define MII_DBG_ADDR 0x1D #define MII_DBG_DATA 0x1E - -/* PHY Control Register */ -#define MII_CR_SPEED_SELECT_MSB 0x0040 /* bits 6,13: 10=1000, 01=100, 00=10 */ -#define MII_CR_COLL_TEST_ENABLE 0x0080 /* Collision test enable */ -#define MII_CR_FULL_DUPLEX 0x0100 /* FDX =1, half duplex =0 */ -#define MII_CR_RESTART_AUTO_NEG 0x0200 /* Restart auto negotiation */ -#define MII_CR_ISOLATE 0x0400 /* Isolate PHY from MII */ -#define MII_CR_POWER_DOWN 0x0800 /* Power down */ -#define MII_CR_AUTO_NEG_EN 0x1000 /* Auto Neg Enable */ -#define MII_CR_SPEED_SELECT_LSB 0x2000 /* bits 6,13: 10=1000, 01=100, 00=10 */ -#define MII_CR_LOOPBACK 0x4000 /* 0 = normal, 1 = loopback */ -#define MII_CR_RESET 0x8000 /* 0 = normal, 1 = PHY reset */ -#define MII_CR_SPEED_MASK 0x2040 -#define MII_CR_SPEED_1000 0x0040 -#define MII_CR_SPEED_100 0x2000 -#define MII_CR_SPEED_10 0x0000 - - -/* PHY Status Register */ -#define MII_SR_EXTENDED_CAPS 0x0001 /* Extended register capabilities */ -#define MII_SR_JABBER_DETECT 0x0002 /* Jabber Detected */ -#define MII_SR_LINK_STATUS 0x0004 /* Link Status 1 = link */ -#define MII_SR_AUTONEG_CAPS 0x0008 /* Auto Neg Capable */ -#define MII_SR_REMOTE_FAULT 0x0010 /* Remote Fault Detect */ -#define MII_SR_AUTONEG_COMPLETE 0x0020 /* Auto Neg Complete */ -#define MII_SR_PREAMBLE_SUPPRESS 0x0040 /* Preamble may be suppressed */ -#define MII_SR_EXTENDED_STATUS 0x0100 /* Ext. status info in Reg 0x0F */ -#define MII_SR_100T2_HD_CAPS 0x0200 /* 100T2 Half Duplex Capable */ -#define MII_SR_100T2_FD_CAPS 0x0400 /* 100T2 Full Duplex Capable */ -#define MII_SR_10T_HD_CAPS 0x0800 /* 10T Half Duplex Capable */ -#define MII_SR_10T_FD_CAPS 0x1000 /* 10T Full Duplex Capable */ -#define MII_SR_100X_HD_CAPS 0x2000 /* 100X Half Duplex Capable */ -#define MII_SR_100X_FD_CAPS 0x4000 /* 100X Full Duplex Capable */ -#define MII_SR_100T4_CAPS 0x8000 /* 100T4 Capable */ - -/* Link partner ability register. */ -#define MII_LPA_SLCT 0x001f /* Same as advertise selector */ -#define MII_LPA_10HALF 0x0020 /* Can do 10mbps half-duplex */ -#define MII_LPA_10FULL 0x0040 /* Can do 10mbps full-duplex */ -#define MII_LPA_100HALF 0x0080 /* Can do 100mbps half-duplex */ -#define MII_LPA_100FULL 0x0100 /* Can do 100mbps full-duplex */ -#define MII_LPA_100BASE4 0x0200 /* 100BASE-T4 */ -#define MII_LPA_PAUSE 0x0400 /* PAUSE */ -#define MII_LPA_ASYPAUSE 0x0800 /* Asymmetrical PAUSE */ -#define MII_LPA_RFAULT 0x2000 /* Link partner faulted */ -#define MII_LPA_LPACK 0x4000 /* Link partner acked us */ -#define MII_LPA_NPAGE 0x8000 /* Next page bit */ - /* Autoneg Advertisement Register */ -#define MII_AR_SELECTOR_FIELD 0x0001 /* indicates IEEE 802.3 CSMA/CD */ -#define MII_AR_10T_HD_CAPS 0x0020 /* 10T Half Duplex Capable */ -#define MII_AR_10T_FD_CAPS 0x0040 /* 10T Full Duplex Capable */ -#define MII_AR_100TX_HD_CAPS 0x0080 /* 100TX Half Duplex Capable */ -#define MII_AR_100TX_FD_CAPS 0x0100 /* 100TX Full Duplex Capable */ -#define MII_AR_100T4_CAPS 0x0200 /* 100T4 Capable */ -#define MII_AR_PAUSE 0x0400 /* Pause operation desired */ -#define MII_AR_ASM_DIR 0x0800 /* Asymmetric Pause Direction bit */ -#define MII_AR_REMOTE_FAULT 0x2000 /* Remote Fault detected */ -#define MII_AR_NEXT_PAGE 0x8000 /* Next Page ability supported */ -#define MII_AR_SPEED_MASK 0x01E0 -#define MII_AR_DEFAULT_CAP_MASK 0x0DE0 +#define MII_AR_DEFAULT_CAP_MASK 0 /* 1000BASE-T Control Register */ -#define MII_AT001_CR_1000T_HD_CAPS 0x0100 /* Advertise 1000T HD capability */ -#define MII_AT001_CR_1000T_FD_CAPS 0x0200 /* Advertise 1000T FD capability */ -#define MII_AT001_CR_1000T_REPEATER_DTE 0x0400 /* 1=Repeater/switch device port */ -/* 0=DTE device */ -#define MII_AT001_CR_1000T_MS_VALUE 0x0800 /* 1=Configure PHY as Master */ -/* 0=Configure PHY as Slave */ -#define MII_AT001_CR_1000T_MS_ENABLE 0x1000 /* 1=Master/Slave manual config value */ -/* 0=Automatic Master/Slave config */ -#define MII_AT001_CR_1000T_TEST_MODE_NORMAL 0x0000 /* Normal Operation */ -#define MII_AT001_CR_1000T_TEST_MODE_1 0x2000 /* Transmit Waveform test */ -#define MII_AT001_CR_1000T_TEST_MODE_2 0x4000 /* Master Transmit Jitter test */ -#define MII_AT001_CR_1000T_TEST_MODE_3 0x6000 /* Slave Transmit Jitter test */ -#define MII_AT001_CR_1000T_TEST_MODE_4 0x8000 /* Transmitter Distortion test */ -#define MII_AT001_CR_1000T_SPEED_MASK 0x0300 -#define MII_AT001_CR_1000T_DEFAULT_CAP_MASK 0x0300 - -/* 1000BASE-T Status Register */ -#define MII_AT001_SR_1000T_LP_HD_CAPS 0x0400 /* LP is 1000T HD capable */ -#define MII_AT001_SR_1000T_LP_FD_CAPS 0x0800 /* LP is 1000T FD capable */ -#define MII_AT001_SR_1000T_REMOTE_RX_STATUS 0x1000 /* Remote receiver OK */ -#define MII_AT001_SR_1000T_LOCAL_RX_STATUS 0x2000 /* Local receiver OK */ -#define MII_AT001_SR_1000T_MS_CONFIG_RES 0x4000 /* 1=Local TX is Master, 0=Slave */ -#define MII_AT001_SR_1000T_MS_CONFIG_FAULT 0x8000 /* Master/Slave config fault */ -#define MII_AT001_SR_1000T_REMOTE_RX_STATUS_SHIFT 12 -#define MII_AT001_SR_1000T_LOCAL_RX_STATUS_SHIFT 13 - -/* Extended Status Register */ -#define MII_AT001_ESR_1000T_HD_CAPS 0x1000 /* 1000T HD capable */ -#define MII_AT001_ESR_1000T_FD_CAPS 0x2000 /* 1000T FD capable */ -#define MII_AT001_ESR_1000X_HD_CAPS 0x4000 /* 1000X HD capable */ -#define MII_AT001_ESR_1000X_FD_CAPS 0x8000 /* 1000X FD capable */ +#define MII_AT001_CR_1000T_SPEED_MASK \ + (ADVERTISE_1000FULL | ADVERTISE_1000HALF) +#define MII_AT001_CR_1000T_DEFAULT_CAP_MASK MII_AT001_CR_1000T_SPEED_MASK /* AT001 PHY Specific Control Register */ #define MII_AT001_PSCR_JABBER_DISABLE 0x0001 /* 1=Jabber Function disabled */ diff --git a/drivers/net/atl1e/atl1e_main.c b/drivers/net/atl1e/atl1e_main.c index e28f8ba..bf7500c 100644 --- a/drivers/net/atl1e/atl1e_main.c +++ b/drivers/net/atl1e/atl1e_main.c @@ -2051,9 +2051,9 @@ static int atl1e_suspend(struct pci_dev *pdev, pm_message_t state) atl1e_read_phy_reg(hw, MII_BMSR, (u16 *)&mii_bmsr_data); atl1e_read_phy_reg(hw, MII_BMSR, (u16 *)&mii_bmsr_data); - mii_advertise_data = MII_AR_10T_HD_CAPS; + mii_advertise_data = ADVERTISE_10HALF; - if ((atl1e_write_phy_reg(hw, MII_AT001_CR, 0) != 0) || + if ((atl1e_write_phy_reg(hw, MII_CTRL1000, 0) != 0) || (atl1e_write_phy_reg(hw, MII_ADVERTISE, mii_advertise_data) != 0) || (atl1e_phy_commit(hw)) != 0) { diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c index 0ba59d5..2a961b7 100644 --- a/drivers/net/bnx2.c +++ b/drivers/net/bnx2.c @@ -435,7 +435,8 @@ bnx2_cnic_stop(struct bnx2 *bp) struct cnic_ctl_info info; mutex_lock(&bp->cnic_lock); - c_ops = bp->cnic_ops; + c_ops = rcu_dereference_protected(bp->cnic_ops, + lockdep_is_held(&bp->cnic_lock)); if (c_ops) { info.cmd = CNIC_CTL_STOP_CMD; c_ops->cnic_ctl(bp->cnic_data, &info); @@ -450,7 +451,8 @@ bnx2_cnic_start(struct bnx2 *bp) struct cnic_ctl_info info; mutex_lock(&bp->cnic_lock); - c_ops = bp->cnic_ops; + c_ops = rcu_dereference_protected(bp->cnic_ops, + lockdep_is_held(&bp->cnic_lock)); if (c_ops) { if (!(bp->flags & BNX2_FLAG_USING_MSIX)) { struct bnx2_napi *bnapi = &bp->bnx2_napi[0]; @@ -8315,7 +8317,7 @@ static const struct net_device_ops bnx2_netdev_ops = { #endif }; -static void inline vlan_features_add(struct net_device *dev, unsigned long flags) +static void inline vlan_features_add(struct net_device *dev, u32 flags) { dev->vlan_features |= flags; } diff --git a/drivers/net/bnx2.h b/drivers/net/bnx2.h index f459fb2..0132ea9 100644 --- a/drivers/net/bnx2.h +++ b/drivers/net/bnx2.h @@ -6759,7 +6759,7 @@ struct bnx2 { u32 tx_wake_thresh; #ifdef BCM_CNIC - struct cnic_ops *cnic_ops; + struct cnic_ops __rcu *cnic_ops; void *cnic_data; #endif diff --git a/drivers/net/bnx2x/bnx2x.h b/drivers/net/bnx2x/bnx2x.h index 653c624..50a34d9 100644 --- a/drivers/net/bnx2x/bnx2x.h +++ b/drivers/net/bnx2x/bnx2x.h @@ -1110,7 +1110,7 @@ struct bnx2x { #define BNX2X_CNIC_FLAG_MAC_SET 1 void *t2; dma_addr_t t2_mapping; - struct cnic_ops *cnic_ops; + struct cnic_ops __rcu *cnic_ops; void *cnic_data; u32 cnic_tag; struct cnic_eth_dev cnic_eth_dev; diff --git a/drivers/net/bnx2x/bnx2x_main.c b/drivers/net/bnx2x/bnx2x_main.c index 404d93e..2215a39 100644 --- a/drivers/net/bnx2x/bnx2x_main.c +++ b/drivers/net/bnx2x/bnx2x_main.c @@ -9866,7 +9866,8 @@ static int bnx2x_cnic_ctl_send(struct bnx2x *bp, struct cnic_ctl_info *ctl) int rc = 0; mutex_lock(&bp->cnic_mutex); - c_ops = bp->cnic_ops; + c_ops = rcu_dereference_protected(bp->cnic_ops, + lockdep_is_held(&bp->cnic_mutex)); if (c_ops) rc = c_ops->cnic_ctl(bp->cnic_data, ctl); mutex_unlock(&bp->cnic_mutex); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 163e0b0..1df9f0e 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1372,8 +1372,8 @@ static int bond_compute_features(struct bonding *bond) { struct slave *slave; struct net_device *bond_dev = bond->dev; - unsigned long features = bond_dev->features; - unsigned long vlan_features = 0; + u32 features = bond_dev->features; + u32 vlan_features = 0; unsigned short max_hard_header_len = max((u16)ETH_HLEN, bond_dev->hard_header_len); int i; @@ -1400,8 +1400,8 @@ static int bond_compute_features(struct bonding *bond) done: features |= (bond_dev->features & BOND_VLAN_FEATURES); - bond_dev->features = netdev_fix_features(features, NULL); - bond_dev->vlan_features = netdev_fix_features(vlan_features, NULL); + bond_dev->features = netdev_fix_features(bond_dev, features); + bond_dev->vlan_features = netdev_fix_features(bond_dev, vlan_features); bond_dev->hard_header_len = max_hard_header_len; return 0; diff --git a/drivers/net/bonding/bond_sysfs.c b/drivers/net/bonding/bond_sysfs.c index 8fd0174..72bb0f6 100644 --- a/drivers/net/bonding/bond_sysfs.c +++ b/drivers/net/bonding/bond_sysfs.c @@ -1198,7 +1198,7 @@ static ssize_t bonding_store_carrier(struct device *d, bond->dev->name, new_value); } out: - return count; + return ret; } static DEVICE_ATTR(use_carrier, S_IRUGO | S_IWUSR, bonding_show_carrier, bonding_store_carrier); @@ -1595,7 +1595,7 @@ static ssize_t bonding_store_slaves_active(struct device *d, } } out: - return count; + return ret; } static DEVICE_ATTR(all_slaves_active, S_IRUGO | S_IWUSR, bonding_show_slaves_active, bonding_store_slaves_active); diff --git a/drivers/net/cnic.c b/drivers/net/cnic.c index 7ff170c..c820496 100644 --- a/drivers/net/cnic.c +++ b/drivers/net/cnic.c @@ -65,7 +65,14 @@ static LIST_HEAD(cnic_udev_list); static DEFINE_RWLOCK(cnic_dev_lock); static DEFINE_MUTEX(cnic_lock); -static struct cnic_ulp_ops *cnic_ulp_tbl[MAX_CNIC_ULP_TYPE]; +static struct cnic_ulp_ops __rcu *cnic_ulp_tbl[MAX_CNIC_ULP_TYPE]; + +/* helper function, assuming cnic_lock is held */ +static inline struct cnic_ulp_ops *cnic_ulp_tbl_prot(int type) +{ + return rcu_dereference_protected(cnic_ulp_tbl[type], + lockdep_is_held(&cnic_lock)); +} static int cnic_service_bnx2(void *, void *); static int cnic_service_bnx2x(void *, void *); @@ -435,7 +442,7 @@ int cnic_register_driver(int ulp_type, struct cnic_ulp_ops *ulp_ops) return -EINVAL; } mutex_lock(&cnic_lock); - if (cnic_ulp_tbl[ulp_type]) { + if (cnic_ulp_tbl_prot(ulp_type)) { pr_err("%s: Type %d has already been registered\n", __func__, ulp_type); mutex_unlock(&cnic_lock); @@ -478,7 +485,7 @@ int cnic_unregister_driver(int ulp_type) return -EINVAL; } mutex_lock(&cnic_lock); - ulp_ops = cnic_ulp_tbl[ulp_type]; + ulp_ops = cnic_ulp_tbl_prot(ulp_type); if (!ulp_ops) { pr_err("%s: Type %d has not been registered\n", __func__, ulp_type); @@ -529,7 +536,7 @@ static int cnic_register_device(struct cnic_dev *dev, int ulp_type, return -EINVAL; } mutex_lock(&cnic_lock); - if (cnic_ulp_tbl[ulp_type] == NULL) { + if (cnic_ulp_tbl_prot(ulp_type) == NULL) { pr_err("%s: Driver with type %d has not been registered\n", __func__, ulp_type); mutex_unlock(&cnic_lock); @@ -544,7 +551,7 @@ static int cnic_register_device(struct cnic_dev *dev, int ulp_type, clear_bit(ULP_F_START, &cp->ulp_flags[ulp_type]); cp->ulp_handle[ulp_type] = ulp_ctx; - ulp_ops = cnic_ulp_tbl[ulp_type]; + ulp_ops = cnic_ulp_tbl_prot(ulp_type); rcu_assign_pointer(cp->ulp_ops[ulp_type], ulp_ops); cnic_hold(dev); @@ -2953,7 +2960,8 @@ static void cnic_ulp_stop(struct cnic_dev *dev) struct cnic_ulp_ops *ulp_ops; mutex_lock(&cnic_lock); - ulp_ops = cp->ulp_ops[if_type]; + ulp_ops = rcu_dereference_protected(cp->ulp_ops[if_type], + lockdep_is_held(&cnic_lock)); if (!ulp_ops) { mutex_unlock(&cnic_lock); continue; @@ -2977,7 +2985,8 @@ static void cnic_ulp_start(struct cnic_dev *dev) struct cnic_ulp_ops *ulp_ops; mutex_lock(&cnic_lock); - ulp_ops = cp->ulp_ops[if_type]; + ulp_ops = rcu_dereference_protected(cp->ulp_ops[if_type], + lockdep_is_held(&cnic_lock)); if (!ulp_ops || !ulp_ops->cnic_start) { mutex_unlock(&cnic_lock); continue; @@ -3041,7 +3050,7 @@ static void cnic_ulp_init(struct cnic_dev *dev) struct cnic_ulp_ops *ulp_ops; mutex_lock(&cnic_lock); - ulp_ops = cnic_ulp_tbl[i]; + ulp_ops = cnic_ulp_tbl_prot(i); if (!ulp_ops || !ulp_ops->cnic_init) { mutex_unlock(&cnic_lock); continue; @@ -3065,7 +3074,7 @@ static void cnic_ulp_exit(struct cnic_dev *dev) struct cnic_ulp_ops *ulp_ops; mutex_lock(&cnic_lock); - ulp_ops = cnic_ulp_tbl[i]; + ulp_ops = cnic_ulp_tbl_prot(i); if (!ulp_ops || !ulp_ops->cnic_exit) { mutex_unlock(&cnic_lock); continue; diff --git a/drivers/net/cnic.h b/drivers/net/cnic.h index b328f6c..4456260 100644 --- a/drivers/net/cnic.h +++ b/drivers/net/cnic.h @@ -220,7 +220,7 @@ struct cnic_local { #define ULP_F_INIT 0 #define ULP_F_START 1 #define ULP_F_CALL_PENDING 2 - struct cnic_ulp_ops *ulp_ops[MAX_CNIC_ULP_TYPE]; + struct cnic_ulp_ops __rcu *ulp_ops[MAX_CNIC_ULP_TYPE]; unsigned long cnic_local_flags; #define CNIC_LCL_FL_KWQ_INIT 0x0 diff --git a/drivers/net/e1000e/e1000.h b/drivers/net/e1000e/e1000.h index e610e13..00bf595 100644 --- a/drivers/net/e1000e/e1000.h +++ b/drivers/net/e1000e/e1000.h @@ -364,6 +364,7 @@ struct e1000_adapter { /* structs defined in e1000_hw.h */ struct e1000_hw hw; + spinlock_t stats64_lock; struct e1000_hw_stats stats; struct e1000_phy_info phy_info; struct e1000_phy_stats phy_stats; @@ -494,7 +495,9 @@ extern int e1000e_setup_rx_resources(struct e1000_adapter *adapter); extern int e1000e_setup_tx_resources(struct e1000_adapter *adapter); extern void e1000e_free_rx_resources(struct e1000_adapter *adapter); extern void e1000e_free_tx_resources(struct e1000_adapter *adapter); -extern void e1000e_update_stats(struct e1000_adapter *adapter); +extern struct rtnl_link_stats64 *e1000e_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 + *stats); extern void e1000e_set_interrupt_capability(struct e1000_adapter *adapter); extern void e1000e_reset_interrupt_capability(struct e1000_adapter *adapter); extern void e1000e_get_hw_control(struct e1000_adapter *adapter); diff --git a/drivers/net/e1000e/ethtool.c b/drivers/net/e1000e/ethtool.c index fa08b63..daa7fe4 100644 --- a/drivers/net/e1000e/ethtool.c +++ b/drivers/net/e1000e/ethtool.c @@ -46,15 +46,15 @@ struct e1000_stats { }; #define E1000_STAT(str, m) { \ - .stat_string = str, \ - .type = E1000_STATS, \ - .sizeof_stat = sizeof(((struct e1000_adapter *)0)->m), \ - .stat_offset = offsetof(struct e1000_adapter, m) } + .stat_string = str, \ + .type = E1000_STATS, \ + .sizeof_stat = sizeof(((struct e1000_adapter *)0)->m), \ + .stat_offset = offsetof(struct e1000_adapter, m) } #define E1000_NETDEV_STAT(str, m) { \ - .stat_string = str, \ - .type = NETDEV_STATS, \ - .sizeof_stat = sizeof(((struct net_device *)0)->m), \ - .stat_offset = offsetof(struct net_device, m) } + .stat_string = str, \ + .type = NETDEV_STATS, \ + .sizeof_stat = sizeof(((struct rtnl_link_stats64 *)0)->m), \ + .stat_offset = offsetof(struct rtnl_link_stats64, m) } static const struct e1000_stats e1000_gstrings_stats[] = { E1000_STAT("rx_packets", stats.gprc), @@ -65,21 +65,21 @@ static const struct e1000_stats e1000_gstrings_stats[] = { E1000_STAT("tx_broadcast", stats.bptc), E1000_STAT("rx_multicast", stats.mprc), E1000_STAT("tx_multicast", stats.mptc), - E1000_NETDEV_STAT("rx_errors", stats.rx_errors), - E1000_NETDEV_STAT("tx_errors", stats.tx_errors), - E1000_NETDEV_STAT("tx_dropped", stats.tx_dropped), + E1000_NETDEV_STAT("rx_errors", rx_errors), + E1000_NETDEV_STAT("tx_errors", tx_errors), + E1000_NETDEV_STAT("tx_dropped", tx_dropped), E1000_STAT("multicast", stats.mprc), E1000_STAT("collisions", stats.colc), - E1000_NETDEV_STAT("rx_length_errors", stats.rx_length_errors), - E1000_NETDEV_STAT("rx_over_errors", stats.rx_over_errors), + E1000_NETDEV_STAT("rx_length_errors", rx_length_errors), + E1000_NETDEV_STAT("rx_over_errors", rx_over_errors), E1000_STAT("rx_crc_errors", stats.crcerrs), - E1000_NETDEV_STAT("rx_frame_errors", stats.rx_frame_errors), + E1000_NETDEV_STAT("rx_frame_errors", rx_frame_errors), E1000_STAT("rx_no_buffer_count", stats.rnbc), E1000_STAT("rx_missed_errors", stats.mpc), E1000_STAT("tx_aborted_errors", stats.ecol), E1000_STAT("tx_carrier_errors", stats.tncrs), - E1000_NETDEV_STAT("tx_fifo_errors", stats.tx_fifo_errors), - E1000_NETDEV_STAT("tx_heartbeat_errors", stats.tx_heartbeat_errors), + E1000_NETDEV_STAT("tx_fifo_errors", tx_fifo_errors), + E1000_NETDEV_STAT("tx_heartbeat_errors", tx_heartbeat_errors), E1000_STAT("tx_window_errors", stats.latecol), E1000_STAT("tx_abort_late_coll", stats.latecol), E1000_STAT("tx_deferred_ok", stats.dc), @@ -684,20 +684,13 @@ static int e1000_set_ringparam(struct net_device *netdev, rx_old = adapter->rx_ring; err = -ENOMEM; - tx_ring = kzalloc(sizeof(struct e1000_ring), GFP_KERNEL); + tx_ring = kmemdup(tx_old, sizeof(struct e1000_ring), GFP_KERNEL); if (!tx_ring) goto err_alloc_tx; - /* - * use a memcpy to save any previously configured - * items like napi structs from having to be - * reinitialized - */ - memcpy(tx_ring, tx_old, sizeof(struct e1000_ring)); - rx_ring = kzalloc(sizeof(struct e1000_ring), GFP_KERNEL); + rx_ring = kmemdup(rx_old, sizeof(struct e1000_ring), GFP_KERNEL); if (!rx_ring) goto err_alloc_rx; - memcpy(rx_ring, rx_old, sizeof(struct e1000_ring)); adapter->tx_ring = tx_ring; adapter->rx_ring = rx_ring; @@ -1255,7 +1248,6 @@ static int e1000_integrated_phy_loopback(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 ctrl_reg = 0; - u32 stat_reg = 0; u16 phy_reg = 0; s32 ret_val = 0; @@ -1363,8 +1355,7 @@ static int e1000_integrated_phy_loopback(struct e1000_adapter *adapter) * Set the ILOS bit on the fiber Nic if half duplex link is * detected. */ - stat_reg = er32(STATUS); - if ((stat_reg & E1000_STATUS_FD) == 0) + if ((er32(STATUS) & E1000_STATUS_FD) == 0) ctrl_reg |= (E1000_CTRL_ILOS | E1000_CTRL_SLU); } @@ -1982,14 +1973,15 @@ static void e1000_get_ethtool_stats(struct net_device *netdev, u64 *data) { struct e1000_adapter *adapter = netdev_priv(netdev); + struct rtnl_link_stats64 net_stats; int i; char *p = NULL; - e1000e_update_stats(adapter); + e1000e_get_stats64(netdev, &net_stats); for (i = 0; i < E1000_GLOBAL_STATS_LEN; i++) { switch (e1000_gstrings_stats[i].type) { case NETDEV_STATS: - p = (char *) netdev + + p = (char *) &net_stats + e1000_gstrings_stats[i].stat_offset; break; case E1000_STATS: diff --git a/drivers/net/e1000e/ich8lan.c b/drivers/net/e1000e/ich8lan.c index fb46974..232b42b 100644 --- a/drivers/net/e1000e/ich8lan.c +++ b/drivers/net/e1000e/ich8lan.c @@ -2104,7 +2104,6 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw) { union ich8_hws_flash_status hsfsts; s32 ret_val = -E1000_ERR_NVM; - s32 i = 0; hsfsts.regval = er16flash(ICH_FLASH_HSFSTS); @@ -2140,6 +2139,8 @@ static s32 e1000_flash_cycle_init_ich8lan(struct e1000_hw *hw) ew16flash(ICH_FLASH_HSFSTS, hsfsts.regval); ret_val = 0; } else { + s32 i = 0; + /* * Otherwise poll for sometime so the current * cycle has a chance to end before giving up. diff --git a/drivers/net/e1000e/lib.c b/drivers/net/e1000e/lib.c index 68aa174..96921de 100644 --- a/drivers/net/e1000e/lib.c +++ b/drivers/net/e1000e/lib.c @@ -1978,15 +1978,15 @@ static s32 e1000_ready_nvm_eeprom(struct e1000_hw *hw) { struct e1000_nvm_info *nvm = &hw->nvm; u32 eecd = er32(EECD); - u16 timeout = 0; u8 spi_stat_reg; if (nvm->type == e1000_nvm_eeprom_spi) { + u16 timeout = NVM_MAX_RETRY_SPI; + /* Clear SK and CS */ eecd &= ~(E1000_EECD_CS | E1000_EECD_SK); ew32(EECD, eecd); udelay(1); - timeout = NVM_MAX_RETRY_SPI; /* * Read "Status Register" repeatedly until the LSB is cleared. diff --git a/drivers/net/e1000e/netdev.c b/drivers/net/e1000e/netdev.c index 1c18f26..5b916b0 100644 --- a/drivers/net/e1000e/netdev.c +++ b/drivers/net/e1000e/netdev.c @@ -900,8 +900,6 @@ next_desc: adapter->total_rx_bytes += total_rx_bytes; adapter->total_rx_packets += total_rx_packets; - netdev->stats.rx_bytes += total_rx_bytes; - netdev->stats.rx_packets += total_rx_packets; return cleaned; } @@ -1057,8 +1055,6 @@ static bool e1000_clean_tx_irq(struct e1000_adapter *adapter) } adapter->total_tx_bytes += total_tx_bytes; adapter->total_tx_packets += total_tx_packets; - netdev->stats.tx_bytes += total_tx_bytes; - netdev->stats.tx_packets += total_tx_packets; return count < tx_ring->count; } @@ -1245,8 +1241,6 @@ next_desc: adapter->total_rx_bytes += total_rx_bytes; adapter->total_rx_packets += total_rx_packets; - netdev->stats.rx_bytes += total_rx_bytes; - netdev->stats.rx_packets += total_rx_packets; return cleaned; } @@ -1426,8 +1420,6 @@ next_desc: adapter->total_rx_bytes += total_rx_bytes; adapter->total_rx_packets += total_rx_packets; - netdev->stats.rx_bytes += total_rx_bytes; - netdev->stats.rx_packets += total_rx_packets; return cleaned; } @@ -2728,7 +2720,6 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; u32 rctl, rfctl; - u32 psrctl = 0; u32 pages = 0; /* Workaround Si errata on 82579 - configure jumbo frame flow */ @@ -2827,6 +2818,8 @@ static void e1000_setup_rctl(struct e1000_adapter *adapter) adapter->rx_ps_pages = 0; if (adapter->rx_ps_pages) { + u32 psrctl = 0; + /* Configure extra packet-split registers */ rfctl = er32(RFCTL); rfctl |= E1000_RFCTL_EXTEN; @@ -3028,7 +3021,6 @@ static void e1000_set_multi(struct net_device *netdev) struct netdev_hw_addr *ha; u8 *mta_list; u32 rctl; - int i; /* Check for Promiscuous and All Multicast modes */ @@ -3051,12 +3043,13 @@ static void e1000_set_multi(struct net_device *netdev) ew32(RCTL, rctl); if (!netdev_mc_empty(netdev)) { + int i = 0; + mta_list = kmalloc(netdev_mc_count(netdev) * 6, GFP_ATOMIC); if (!mta_list) return; /* prepare a packed array of only addresses. */ - i = 0; netdev_for_each_mc_addr(ha, netdev) memcpy(mta_list + (i++ * ETH_ALEN), ha->addr, ETH_ALEN); @@ -3338,6 +3331,8 @@ int e1000e_up(struct e1000_adapter *adapter) return 0; } +static void e1000e_update_stats(struct e1000_adapter *adapter); + void e1000e_down(struct e1000_adapter *adapter) { struct net_device *netdev = adapter->netdev; @@ -3372,6 +3367,11 @@ void e1000e_down(struct e1000_adapter *adapter) del_timer_sync(&adapter->phy_info_timer); netif_carrier_off(netdev); + + spin_lock(&adapter->stats64_lock); + e1000e_update_stats(adapter); + spin_unlock(&adapter->stats64_lock); + adapter->link_speed = 0; adapter->link_duplex = 0; @@ -3413,6 +3413,8 @@ static int __devinit e1000_sw_init(struct e1000_adapter *adapter) adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN; adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; + spin_lock_init(&adapter->stats64_lock); + e1000e_set_interrupt_capability(adapter); if (e1000_alloc_queues(adapter)) @@ -3886,7 +3888,7 @@ release: * e1000e_update_stats - Update the board statistics counters * @adapter: board private structure **/ -void e1000e_update_stats(struct e1000_adapter *adapter) +static void e1000e_update_stats(struct e1000_adapter *adapter) { struct net_device *netdev = adapter->netdev; struct e1000_hw *hw = &adapter->hw; @@ -3998,10 +4000,11 @@ static void e1000_phy_read_status(struct e1000_adapter *adapter) { struct e1000_hw *hw = &adapter->hw; struct e1000_phy_regs *phy = &adapter->phy_regs; - int ret_val; if ((er32(STATUS) & E1000_STATUS_LU) && (adapter->hw.phy.media_type == e1000_media_type_copper)) { + int ret_val; + ret_val = e1e_rphy(hw, PHY_CONTROL, &phy->bmcr); ret_val |= e1e_rphy(hw, PHY_STATUS, &phy->bmsr); ret_val |= e1e_rphy(hw, PHY_AUTONEG_ADV, &phy->advertise); @@ -4147,7 +4150,6 @@ static void e1000_watchdog_task(struct work_struct *work) struct e1000_ring *tx_ring = adapter->tx_ring; struct e1000_hw *hw = &adapter->hw; u32 link, tctl; - int tx_pending = 0; link = e1000e_has_link(adapter); if ((netif_carrier_ok(netdev)) && link) { @@ -4285,7 +4287,9 @@ static void e1000_watchdog_task(struct work_struct *work) } link_up: + spin_lock(&adapter->stats64_lock); e1000e_update_stats(adapter); + spin_unlock(&adapter->stats64_lock); mac->tx_packet_delta = adapter->stats.tpt - adapter->tpt_old; adapter->tpt_old = adapter->stats.tpt; @@ -4299,21 +4303,18 @@ link_up: e1000e_update_adaptive(&adapter->hw); - if (!netif_carrier_ok(netdev)) { - tx_pending = (e1000_desc_unused(tx_ring) + 1 < - tx_ring->count); - if (tx_pending) { - /* - * We've lost link, so the controller stops DMA, - * but we've got queued Tx work that's never going - * to get done, so reset controller to flush Tx. - * (Do the reset outside of interrupt context). - */ - adapter->tx_timeout_count++; - schedule_work(&adapter->reset_task); - /* return immediately since reset is imminent */ - return; - } + if (!netif_carrier_ok(netdev) && + (e1000_desc_unused(tx_ring) + 1 < tx_ring->count)) { + /* + * We've lost link, so the controller stops DMA, + * but we've got queued Tx work that's never going + * to get done, so reset controller to flush Tx. + * (Do the reset outside of interrupt context). + */ + adapter->tx_timeout_count++; + schedule_work(&adapter->reset_task); + /* return immediately since reset is imminent */ + return; } /* Simple mode for Interrupt Throttle Rate (ITR) */ @@ -4384,13 +4385,13 @@ static int e1000_tso(struct e1000_adapter *adapter, u32 cmd_length = 0; u16 ipcse = 0, tucse, mss; u8 ipcss, ipcso, tucss, tucso, hdr_len; - int err; if (!skb_is_gso(skb)) return 0; if (skb_header_cloned(skb)) { - err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + int err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); + if (err) return err; } @@ -4897,16 +4898,55 @@ static void e1000_reset_task(struct work_struct *work) } /** - * e1000_get_stats - Get System Network Statistics + * e1000_get_stats64 - Get System Network Statistics * @netdev: network interface device structure + * @stats: rtnl_link_stats64 pointer * * Returns the address of the device statistics structure. - * The statistics are actually updated from the timer callback. **/ -static struct net_device_stats *e1000_get_stats(struct net_device *netdev) +struct rtnl_link_stats64 *e1000e_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *stats) { - /* only return the current stats */ - return &netdev->stats; + struct e1000_adapter *adapter = netdev_priv(netdev); + + memset(stats, 0, sizeof(struct rtnl_link_stats64)); + spin_lock(&adapter->stats64_lock); + e1000e_update_stats(adapter); + /* Fill out the OS statistics structure */ + stats->rx_bytes = adapter->stats.gorc; + stats->rx_packets = adapter->stats.gprc; + stats->tx_bytes = adapter->stats.gotc; + stats->tx_packets = adapter->stats.gptc; + stats->multicast = adapter->stats.mprc; + stats->collisions = adapter->stats.colc; + + /* Rx Errors */ + + /* + * RLEC on some newer hardware can be incorrect so build + * our own version based on RUC and ROC + */ + stats->rx_errors = adapter->stats.rxerrc + + adapter->stats.crcerrs + adapter->stats.algnerrc + + adapter->stats.ruc + adapter->stats.roc + + adapter->stats.cexterr; + stats->rx_length_errors = adapter->stats.ruc + + adapter->stats.roc; + stats->rx_crc_errors = adapter->stats.crcerrs; + stats->rx_frame_errors = adapter->stats.algnerrc; + stats->rx_missed_errors = adapter->stats.mpc; + + /* Tx Errors */ + stats->tx_errors = adapter->stats.ecol + + adapter->stats.latecol; + stats->tx_aborted_errors = adapter->stats.ecol; + stats->tx_window_errors = adapter->stats.latecol; + stats->tx_carrier_errors = adapter->stats.tncrs; + + /* Tx Dropped needs to be maintained elsewhere */ + + spin_unlock(&adapter->stats64_lock); + return stats; } /** @@ -5476,9 +5516,10 @@ static irqreturn_t e1000_intr_msix(int irq, void *data) { struct net_device *netdev = data; struct e1000_adapter *adapter = netdev_priv(netdev); - int vector, msix_irq; if (adapter->msix_entries) { + int vector, msix_irq; + vector = 0; msix_irq = adapter->msix_entries[vector].vector; disable_irq(msix_irq); @@ -5675,7 +5716,7 @@ static const struct net_device_ops e1000e_netdev_ops = { .ndo_open = e1000_open, .ndo_stop = e1000_close, .ndo_start_xmit = e1000_xmit_frame, - .ndo_get_stats = e1000_get_stats, + .ndo_get_stats64 = e1000e_get_stats64, .ndo_set_multicast_list = e1000_set_multi, .ndo_set_mac_address = e1000_set_mac, .ndo_change_mtu = e1000_change_mtu, diff --git a/drivers/net/e1000e/phy.c b/drivers/net/e1000e/phy.c index 6bea051..6ae31fc 100644 --- a/drivers/net/e1000e/phy.c +++ b/drivers/net/e1000e/phy.c @@ -2409,9 +2409,7 @@ static u32 e1000_get_phy_addr_for_bm_page(u32 page, u32 reg) s32 e1000e_write_phy_reg_bm(struct e1000_hw *hw, u32 offset, u16 data) { s32 ret_val; - u32 page_select = 0; u32 page = offset >> IGP_PAGE_SHIFT; - u32 page_shift = 0; ret_val = hw->phy.ops.acquire(hw); if (ret_val) @@ -2427,6 +2425,8 @@ s32 e1000e_write_phy_reg_bm(struct e1000_hw *hw, u32 offset, u16 data) hw->phy.addr = e1000_get_phy_addr_for_bm_page(page, offset); if (offset > MAX_PHY_MULTI_PAGE_REG) { + u32 page_shift, page_select; + /* * Page select is register 31 for phy address 1 and 22 for * phy address 2 and 3. Page select is shifted only for @@ -2468,9 +2468,7 @@ out: s32 e1000e_read_phy_reg_bm(struct e1000_hw *hw, u32 offset, u16 *data) { s32 ret_val; - u32 page_select = 0; u32 page = offset >> IGP_PAGE_SHIFT; - u32 page_shift = 0; ret_val = hw->phy.ops.acquire(hw); if (ret_val) @@ -2486,6 +2484,8 @@ s32 e1000e_read_phy_reg_bm(struct e1000_hw *hw, u32 offset, u16 *data) hw->phy.addr = e1000_get_phy_addr_for_bm_page(page, offset); if (offset > MAX_PHY_MULTI_PAGE_REG) { + u32 page_shift, page_select; + /* * Page select is register 31 for phy address 1 and 22 for * phy address 2 and 3. Page select is shifted only for diff --git a/drivers/net/enic/enic.h b/drivers/net/enic/enic.h index a937f49..ca3be4f 100644 --- a/drivers/net/enic/enic.h +++ b/drivers/net/enic/enic.h @@ -32,8 +32,8 @@ #define DRV_NAME "enic" #define DRV_DESCRIPTION "Cisco VIC Ethernet NIC Driver" -#define DRV_VERSION "1.4.1.10" -#define DRV_COPYRIGHT "Copyright 2008-2010 Cisco Systems, Inc" +#define DRV_VERSION "2.1.1.2" +#define DRV_COPYRIGHT "Copyright 2008-2011 Cisco Systems, Inc" #define ENIC_BARS_MAX 6 @@ -49,7 +49,7 @@ struct enic_msix_entry { void *devid; }; -#define ENIC_SET_APPLIED (1 << 0) +#define ENIC_PORT_REQUEST_APPLIED (1 << 0) #define ENIC_SET_REQUEST (1 << 1) #define ENIC_SET_NAME (1 << 2) #define ENIC_SET_INSTANCE (1 << 3) diff --git a/drivers/net/enic/enic_main.c b/drivers/net/enic/enic_main.c index a0af48c..89664c6 100644 --- a/drivers/net/enic/enic_main.c +++ b/drivers/net/enic/enic_main.c @@ -1318,18 +1318,20 @@ static int enic_set_port_profile(struct enic *enic, u8 *mac) vic_provinfo_free(vp); if (err) return err; - - enic->pp.set |= ENIC_SET_APPLIED; break; case PORT_REQUEST_DISASSOCIATE: - enic->pp.set &= ~ENIC_SET_APPLIED; break; default: return -EINVAL; } + /* Set flag to indicate that the port assoc/disassoc + * request has been sent out to fw + */ + enic->pp.set |= ENIC_PORT_REQUEST_APPLIED; + return 0; } @@ -1411,7 +1413,7 @@ static int enic_get_vf_port(struct net_device *netdev, int vf, int err, error, done; u16 response = PORT_PROFILE_RESPONSE_SUCCESS; - if (!(enic->pp.set & ENIC_SET_APPLIED)) + if (!(enic->pp.set & ENIC_PORT_REQUEST_APPLIED)) return -ENODATA; err = enic_dev_init_done(enic, &done, &error); diff --git a/drivers/net/hamradio/bpqether.c b/drivers/net/hamradio/bpqether.c index ac1d323..8931168 100644 --- a/drivers/net/hamradio/bpqether.c +++ b/drivers/net/hamradio/bpqether.c @@ -400,13 +400,14 @@ static void *bpq_seq_start(struct seq_file *seq, loff_t *pos) static void *bpq_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct list_head *p; + struct bpqdev *bpqdev = v; ++*pos; if (v == SEQ_START_TOKEN) - p = rcu_dereference(bpq_devices.next); + p = rcu_dereference(list_next_rcu(&bpq_devices)); else - p = rcu_dereference(((struct bpqdev *)v)->bpq_list.next); + p = rcu_dereference(list_next_rcu(&bpqdev->bpq_list)); return (p == &bpq_devices) ? NULL : list_entry(p, struct bpqdev, bpq_list); diff --git a/drivers/net/igb/e1000_82575.c b/drivers/net/igb/e1000_82575.c index 0a2368f..c1552b6 100644 --- a/drivers/net/igb/e1000_82575.c +++ b/drivers/net/igb/e1000_82575.c @@ -129,6 +129,7 @@ static s32 igb_get_invariants_82575(struct e1000_hw *hw) break; case E1000_DEV_ID_82580_COPPER: case E1000_DEV_ID_82580_FIBER: + case E1000_DEV_ID_82580_QUAD_FIBER: case E1000_DEV_ID_82580_SERDES: case E1000_DEV_ID_82580_SGMII: case E1000_DEV_ID_82580_COPPER_DUAL: diff --git a/drivers/net/igb/e1000_hw.h b/drivers/net/igb/e1000_hw.h index e2638af..281324e 100644 --- a/drivers/net/igb/e1000_hw.h +++ b/drivers/net/igb/e1000_hw.h @@ -54,6 +54,7 @@ struct e1000_hw; #define E1000_DEV_ID_82580_SERDES 0x1510 #define E1000_DEV_ID_82580_SGMII 0x1511 #define E1000_DEV_ID_82580_COPPER_DUAL 0x1516 +#define E1000_DEV_ID_82580_QUAD_FIBER 0x1527 #define E1000_DEV_ID_DH89XXCC_SGMII 0x0438 #define E1000_DEV_ID_DH89XXCC_SERDES 0x043A #define E1000_DEV_ID_DH89XXCC_BACKPLANE 0x043C diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index 58c665b..200cc32 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -68,6 +68,7 @@ static DEFINE_PCI_DEVICE_TABLE(igb_pci_tbl) = { { PCI_VDEVICE(INTEL, E1000_DEV_ID_I350_SGMII), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_COPPER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_FIBER), board_82575 }, + { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_QUAD_FIBER), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_SERDES), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_SGMII), board_82575 }, { PCI_VDEVICE(INTEL, E1000_DEV_ID_82580_COPPER_DUAL), board_82575 }, diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 5933621..2300e45 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -39,7 +39,7 @@ struct macvtap_queue { struct socket sock; struct socket_wq wq; int vnet_hdr_sz; - struct macvlan_dev *vlan; + struct macvlan_dev __rcu *vlan; struct file *file; unsigned int flags; }; @@ -141,7 +141,8 @@ static void macvtap_put_queue(struct macvtap_queue *q) struct macvlan_dev *vlan; spin_lock(&macvtap_lock); - vlan = rcu_dereference(q->vlan); + vlan = rcu_dereference_protected(q->vlan, + lockdep_is_held(&macvtap_lock)); if (vlan) { int index = get_slot(vlan, q); @@ -219,7 +220,8 @@ static void macvtap_del_queues(struct net_device *dev) /* macvtap_put_queue can free some slots, so go through all slots */ spin_lock(&macvtap_lock); for (i = 0; i < MAX_MACVTAP_QUEUES && vlan->numvtaps; i++) { - q = rcu_dereference(vlan->taps[i]); + q = rcu_dereference_protected(vlan->taps[i], + lockdep_is_held(&macvtap_lock)); if (q) { qlist[j++] = q; rcu_assign_pointer(vlan->taps[i], NULL); @@ -569,7 +571,7 @@ static ssize_t macvtap_get_user(struct macvtap_queue *q, } rcu_read_lock_bh(); - vlan = rcu_dereference(q->vlan); + vlan = rcu_dereference_bh(q->vlan); if (vlan) macvlan_start_xmit(skb, vlan->dev); else @@ -583,7 +585,7 @@ err_kfree: err: rcu_read_lock_bh(); - vlan = rcu_dereference(q->vlan); + vlan = rcu_dereference_bh(q->vlan); if (vlan) vlan->dev->stats.tx_dropped++; rcu_read_unlock_bh(); @@ -631,7 +633,7 @@ static ssize_t macvtap_put_user(struct macvtap_queue *q, ret = skb_copy_datagram_const_iovec(skb, 0, iv, vnet_hdr_len, len); rcu_read_lock_bh(); - vlan = rcu_dereference(q->vlan); + vlan = rcu_dereference_bh(q->vlan); if (vlan) macvlan_count_rx(vlan, len, ret == 0, 0); rcu_read_unlock_bh(); @@ -727,7 +729,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, case TUNGETIFF: rcu_read_lock_bh(); - vlan = rcu_dereference(q->vlan); + vlan = rcu_dereference_bh(q->vlan); if (vlan) dev_hold(vlan->dev); rcu_read_unlock_bh(); @@ -736,7 +738,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, return -ENOLINK; ret = 0; - if (copy_to_user(&ifr->ifr_name, q->vlan->dev->name, IFNAMSIZ) || + if (copy_to_user(&ifr->ifr_name, vlan->dev->name, IFNAMSIZ) || put_user(q->flags, &ifr->ifr_flags)) ret = -EFAULT; dev_put(vlan->dev); diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c index ea5cfe2..a7f2eed 100644 --- a/drivers/net/myri10ge/myri10ge.c +++ b/drivers/net/myri10ge/myri10ge.c @@ -253,7 +253,7 @@ struct myri10ge_priv { unsigned long serial_number; int vendor_specific_offset; int fw_multicast_support; - unsigned long features; + u32 features; u32 max_tso6; u32 read_dma; u32 write_dma; @@ -1776,7 +1776,7 @@ static int myri10ge_set_rx_csum(struct net_device *netdev, u32 csum_enabled) static int myri10ge_set_tso(struct net_device *netdev, u32 tso_enabled) { struct myri10ge_priv *mgp = netdev_priv(netdev); - unsigned long flags = mgp->features & (NETIF_F_TSO6 | NETIF_F_TSO); + u32 flags = mgp->features & (NETIF_F_TSO6 | NETIF_F_TSO); if (tso_enabled) netdev->features |= flags; diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c index c7a6c44..9f6d670 100644 --- a/drivers/net/ppp_generic.c +++ b/drivers/net/ppp_generic.c @@ -592,8 +592,8 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) ppp_release(NULL, file); err = 0; } else - printk(KERN_DEBUG "PPPIOCDETACH file->f_count=%ld\n", - atomic_long_read(&file->f_count)); + pr_warn("PPPIOCDETACH file->f_count=%ld\n", + atomic_long_read(&file->f_count)); mutex_unlock(&ppp_mutex); return err; } @@ -630,7 +630,7 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) if (pf->kind != INTERFACE) { /* can't happen */ - printk(KERN_ERR "PPP: not interface or channel??\n"); + pr_err("PPP: not interface or channel??\n"); return -EINVAL; } @@ -704,7 +704,8 @@ static long ppp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) } vj = slhc_init(val2+1, val+1); if (!vj) { - printk(KERN_ERR "PPP: no memory (VJ compressor)\n"); + netdev_err(ppp->dev, + "PPP: no memory (VJ compressor)\n"); err = -ENOMEM; break; } @@ -898,17 +899,17 @@ static int __init ppp_init(void) { int err; - printk(KERN_INFO "PPP generic driver version " PPP_VERSION "\n"); + pr_info("PPP generic driver version " PPP_VERSION "\n"); err = register_pernet_device(&ppp_net_ops); if (err) { - printk(KERN_ERR "failed to register PPP pernet device (%d)\n", err); + pr_err("failed to register PPP pernet device (%d)\n", err); goto out; } err = register_chrdev(PPP_MAJOR, "ppp", &ppp_device_fops); if (err) { - printk(KERN_ERR "failed to register PPP device (%d)\n", err); + pr_err("failed to register PPP device (%d)\n", err); goto out_net; } @@ -1078,7 +1079,7 @@ pad_compress_skb(struct ppp *ppp, struct sk_buff *skb) new_skb = alloc_skb(new_skb_size, GFP_ATOMIC); if (!new_skb) { if (net_ratelimit()) - printk(KERN_ERR "PPP: no memory (comp pkt)\n"); + netdev_err(ppp->dev, "PPP: no memory (comp pkt)\n"); return NULL; } if (ppp->dev->hard_header_len > PPP_HDRLEN) @@ -1108,7 +1109,7 @@ pad_compress_skb(struct ppp *ppp, struct sk_buff *skb) * the same number. */ if (net_ratelimit()) - printk(KERN_ERR "ppp: compressor dropped pkt\n"); + netdev_err(ppp->dev, "ppp: compressor dropped pkt\n"); kfree_skb(skb); kfree_skb(new_skb); new_skb = NULL; @@ -1138,7 +1139,9 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) if (ppp->pass_filter && sk_run_filter(skb, ppp->pass_filter) == 0) { if (ppp->debug & 1) - printk(KERN_DEBUG "PPP: outbound frame not passed\n"); + netdev_printk(KERN_DEBUG, ppp->dev, + "PPP: outbound frame " + "not passed\n"); kfree_skb(skb); return; } @@ -1164,7 +1167,7 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) new_skb = alloc_skb(skb->len + ppp->dev->hard_header_len - 2, GFP_ATOMIC); if (!new_skb) { - printk(KERN_ERR "PPP: no memory (VJ comp pkt)\n"); + netdev_err(ppp->dev, "PPP: no memory (VJ comp pkt)\n"); goto drop; } skb_reserve(new_skb, ppp->dev->hard_header_len - 2); @@ -1202,7 +1205,9 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb) proto != PPP_LCP && proto != PPP_CCP) { if (!(ppp->flags & SC_CCP_UP) && (ppp->flags & SC_MUST_COMP)) { if (net_ratelimit()) - printk(KERN_ERR "ppp: compression required but down - pkt dropped.\n"); + netdev_err(ppp->dev, + "ppp: compression required but " + "down - pkt dropped.\n"); goto drop; } skb = pad_compress_skb(ppp, skb); @@ -1505,7 +1510,7 @@ static int ppp_mp_explode(struct ppp *ppp, struct sk_buff *skb) noskb: spin_unlock_bh(&pch->downl); if (ppp->debug & 1) - printk(KERN_ERR "PPP: no memory (fragment)\n"); + netdev_err(ppp->dev, "PPP: no memory (fragment)\n"); ++ppp->dev->stats.tx_errors; ++ppp->nxseq; return 1; /* abandon the frame */ @@ -1686,7 +1691,8 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) /* copy to a new sk_buff with more tailroom */ ns = dev_alloc_skb(skb->len + 128); if (!ns) { - printk(KERN_ERR"PPP: no memory (VJ decomp)\n"); + netdev_err(ppp->dev, "PPP: no memory " + "(VJ decomp)\n"); goto err; } skb_reserve(ns, 2); @@ -1699,7 +1705,8 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) len = slhc_uncompress(ppp->vj, skb->data + 2, skb->len - 2); if (len <= 0) { - printk(KERN_DEBUG "PPP: VJ decompression error\n"); + netdev_printk(KERN_DEBUG, ppp->dev, + "PPP: VJ decompression error\n"); goto err; } len += 2; @@ -1721,7 +1728,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) goto err; if (slhc_remember(ppp->vj, skb->data + 2, skb->len - 2) <= 0) { - printk(KERN_ERR "PPP: VJ uncompressed error\n"); + netdev_err(ppp->dev, "PPP: VJ uncompressed error\n"); goto err; } proto = PPP_IP; @@ -1762,8 +1769,9 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb) if (ppp->pass_filter && sk_run_filter(skb, ppp->pass_filter) == 0) { if (ppp->debug & 1) - printk(KERN_DEBUG "PPP: inbound frame " - "not passed\n"); + netdev_printk(KERN_DEBUG, ppp->dev, + "PPP: inbound frame " + "not passed\n"); kfree_skb(skb); return; } @@ -1821,7 +1829,8 @@ ppp_decompress_frame(struct ppp *ppp, struct sk_buff *skb) ns = dev_alloc_skb(obuff_size); if (!ns) { - printk(KERN_ERR "ppp_decompress_frame: no memory\n"); + netdev_err(ppp->dev, "ppp_decompress_frame: " + "no memory\n"); goto err; } /* the decompressor still expects the A/C bytes in the hdr */ @@ -1989,7 +1998,7 @@ ppp_mp_reconstruct(struct ppp *ppp) u32 seq = ppp->nextseq; u32 minseq = ppp->minseq; struct sk_buff_head *list = &ppp->mrq; - struct sk_buff *p, *next; + struct sk_buff *p, *tmp; struct sk_buff *head, *tail; struct sk_buff *skb = NULL; int lost = 0, len = 0; @@ -1998,13 +2007,15 @@ ppp_mp_reconstruct(struct ppp *ppp) return NULL; head = list->next; tail = NULL; - for (p = head; p != (struct sk_buff *) list; p = next) { - next = p->next; + skb_queue_walk_safe(list, p, tmp) { + again: if (seq_before(PPP_MP_CB(p)->sequence, seq)) { /* this can't happen, anyway ignore the skb */ - printk(KERN_ERR "ppp_mp_reconstruct bad seq %u < %u\n", - PPP_MP_CB(p)->sequence, seq); - head = next; + netdev_err(ppp->dev, "ppp_mp_reconstruct bad " + "seq %u < %u\n", + PPP_MP_CB(p)->sequence, seq); + __skb_unlink(p, list); + kfree_skb(p); continue; } if (PPP_MP_CB(p)->sequence != seq) { @@ -2016,8 +2027,7 @@ ppp_mp_reconstruct(struct ppp *ppp) lost = 1; seq = seq_before(minseq, PPP_MP_CB(p)->sequence)? minseq + 1: PPP_MP_CB(p)->sequence; - next = p; - continue; + goto again; } /* @@ -2042,17 +2052,9 @@ ppp_mp_reconstruct(struct ppp *ppp) (PPP_MP_CB(head)->BEbits & B)) { if (len > ppp->mrru + 2) { ++ppp->dev->stats.rx_length_errors; - printk(KERN_DEBUG "PPP: reconstructed packet" - " is too long (%d)\n", len); - } else if (p == head) { - /* fragment is complete packet - reuse skb */ - tail = p; - skb = skb_get(p); - break; - } else if ((skb = dev_alloc_skb(len)) == NULL) { - ++ppp->dev->stats.rx_missed_errors; - printk(KERN_DEBUG "PPP: no memory for " - "reconstructed packet"); + netdev_printk(KERN_DEBUG, ppp->dev, + "PPP: reconstructed packet" + " is too long (%d)\n", len); } else { tail = p; break; @@ -2065,9 +2067,17 @@ ppp_mp_reconstruct(struct ppp *ppp) * and we haven't found a complete valid packet yet, * we can discard up to and including this fragment. */ - if (PPP_MP_CB(p)->BEbits & E) - head = next; + if (PPP_MP_CB(p)->BEbits & E) { + struct sk_buff *tmp2; + skb_queue_reverse_walk_from_safe(list, p, tmp2) { + __skb_unlink(p, list); + kfree_skb(p); + } + head = skb_peek(list); + if (!head) + break; + } ++seq; } @@ -2077,26 +2087,37 @@ ppp_mp_reconstruct(struct ppp *ppp) signal a receive error. */ if (PPP_MP_CB(head)->sequence != ppp->nextseq) { if (ppp->debug & 1) - printk(KERN_DEBUG " missed pkts %u..%u\n", - ppp->nextseq, - PPP_MP_CB(head)->sequence-1); + netdev_printk(KERN_DEBUG, ppp->dev, + " missed pkts %u..%u\n", + ppp->nextseq, + PPP_MP_CB(head)->sequence-1); ++ppp->dev->stats.rx_dropped; ppp_receive_error(ppp); } - if (head != tail) - /* copy to a single skb */ - for (p = head; p != tail->next; p = p->next) - skb_copy_bits(p, 0, skb_put(skb, p->len), p->len); - ppp->nextseq = PPP_MP_CB(tail)->sequence + 1; - head = tail->next; - } + skb = head; + if (head != tail) { + struct sk_buff **fragpp = &skb_shinfo(skb)->frag_list; + p = skb_queue_next(list, head); + __skb_unlink(skb, list); + skb_queue_walk_from_safe(list, p, tmp) { + __skb_unlink(p, list); + *fragpp = p; + p->next = NULL; + fragpp = &p->next; + + skb->len += p->len; + skb->data_len += p->len; + skb->truesize += p->len; + + if (p == tail) + break; + } + } else { + __skb_unlink(skb, list); + } - /* Discard all the skbuffs that we have copied the data out of - or that we can't use. */ - while ((p = list->next) != head) { - __skb_unlink(p, list); - kfree_skb(p); + ppp->nextseq = PPP_MP_CB(tail)->sequence + 1; } return skb; @@ -2617,8 +2638,8 @@ ppp_create_interface(struct net *net, int unit, int *retp) ret = register_netdev(dev); if (ret != 0) { unit_put(&pn->units_idr, unit); - printk(KERN_ERR "PPP: couldn't register device %s (%d)\n", - dev->name, ret); + netdev_err(ppp->dev, "PPP: couldn't register device %s (%d)\n", + dev->name, ret); goto out2; } @@ -2690,9 +2711,9 @@ static void ppp_destroy_interface(struct ppp *ppp) if (!ppp->file.dead || ppp->n_channels) { /* "can't happen" */ - printk(KERN_ERR "ppp: destroying ppp struct %p but dead=%d " - "n_channels=%d !\n", ppp, ppp->file.dead, - ppp->n_channels); + netdev_err(ppp->dev, "ppp: destroying ppp struct %p " + "but dead=%d n_channels=%d !\n", + ppp, ppp->file.dead, ppp->n_channels); return; } @@ -2834,8 +2855,7 @@ static void ppp_destroy_channel(struct channel *pch) if (!pch->file.dead) { /* "can't happen" */ - printk(KERN_ERR "ppp: destroying undead channel %p !\n", - pch); + pr_err("ppp: destroying undead channel %p !\n", pch); return; } skb_queue_purge(&pch->file.xq); @@ -2847,7 +2867,7 @@ static void __exit ppp_cleanup(void) { /* should never happen */ if (atomic_read(&ppp_unit_count) || atomic_read(&channel_count)) - printk(KERN_ERR "PPP: removing module but units remain!\n"); + pr_err("PPP: removing module but units remain!\n"); unregister_chrdev(PPP_MAJOR, "ppp"); device_destroy(ppp_class, MKDEV(PPP_MAJOR, 0)); class_destroy(ppp_class); @@ -2865,7 +2885,7 @@ static int __unit_alloc(struct idr *p, void *ptr, int n) again: if (!idr_pre_get(p, GFP_KERNEL)) { - printk(KERN_ERR "PPP: No free memory for idr\n"); + pr_err("PPP: No free memory for idr\n"); return -ENOMEM; } diff --git a/drivers/net/sfc/ethtool.c b/drivers/net/sfc/ethtool.c index 0e8bb19..713969a 100644 --- a/drivers/net/sfc/ethtool.c +++ b/drivers/net/sfc/ethtool.c @@ -502,7 +502,7 @@ static void efx_ethtool_get_stats(struct net_device *net_dev, static int efx_ethtool_set_tso(struct net_device *net_dev, u32 enable) { struct efx_nic *efx __attribute__ ((unused)) = netdev_priv(net_dev); - unsigned long features; + u32 features; features = NETIF_F_TSO; if (efx->type->offload_features & NETIF_F_V6_CSUM) @@ -519,7 +519,7 @@ static int efx_ethtool_set_tso(struct net_device *net_dev, u32 enable) static int efx_ethtool_set_tx_csum(struct net_device *net_dev, u32 enable) { struct efx_nic *efx = netdev_priv(net_dev); - unsigned long features = efx->type->offload_features & NETIF_F_ALL_CSUM; + u32 features = efx->type->offload_features & NETIF_F_ALL_CSUM; if (enable) net_dev->features |= features; diff --git a/drivers/net/sfc/net_driver.h b/drivers/net/sfc/net_driver.h index 28df866..c652702 100644 --- a/drivers/net/sfc/net_driver.h +++ b/drivers/net/sfc/net_driver.h @@ -906,7 +906,7 @@ struct efx_nic_type { unsigned int phys_addr_channels; unsigned int tx_dc_base; unsigned int rx_dc_base; - unsigned long offload_features; + u32 offload_features; u32 reset_world_flags; }; diff --git a/drivers/net/smc91x.c b/drivers/net/smc91x.c index 726df61..43654a3 100644 --- a/drivers/net/smc91x.c +++ b/drivers/net/smc91x.c @@ -81,6 +81,7 @@ static const char version[] = #include <linux/ethtool.h> #include <linux/mii.h> #include <linux/workqueue.h> +#include <linux/of.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> @@ -2394,6 +2395,15 @@ static int smc_drv_resume(struct device *dev) return 0; } +#ifdef CONFIG_OF +static const struct of_device_id smc91x_match[] = { + { .compatible = "smsc,lan91c94", }, + { .compatible = "smsc,lan91c111", }, + {}, +} +MODULE_DEVICE_TABLE(of, smc91x_match); +#endif + static struct dev_pm_ops smc_drv_pm_ops = { .suspend = smc_drv_suspend, .resume = smc_drv_resume, @@ -2406,6 +2416,9 @@ static struct platform_driver smc_driver = { .name = CARDNAME, .owner = THIS_MODULE, .pm = &smc_drv_pm_ops, +#ifdef CONFIG_OF + .of_match_table = smc91x_match, +#endif }, }; diff --git a/drivers/net/sungem.c b/drivers/net/sungem.c index 1c5408f..c1a3448 100644 --- a/drivers/net/sungem.c +++ b/drivers/net/sungem.c @@ -320,28 +320,28 @@ static int gem_txmac_interrupt(struct net_device *dev, struct gem *gp, u32 gem_s if (txmac_stat & MAC_TXSTAT_URUN) { netdev_err(dev, "TX MAC xmit underrun\n"); - gp->net_stats.tx_fifo_errors++; + dev->stats.tx_fifo_errors++; } if (txmac_stat & MAC_TXSTAT_MPE) { netdev_err(dev, "TX MAC max packet size error\n"); - gp->net_stats.tx_errors++; + dev->stats.tx_errors++; } /* The rest are all cases of one of the 16-bit TX * counters expiring. */ if (txmac_stat & MAC_TXSTAT_NCE) - gp->net_stats.collisions += 0x10000; + dev->stats.collisions += 0x10000; if (txmac_stat & MAC_TXSTAT_ECE) { - gp->net_stats.tx_aborted_errors += 0x10000; - gp->net_stats.collisions += 0x10000; + dev->stats.tx_aborted_errors += 0x10000; + dev->stats.collisions += 0x10000; } if (txmac_stat & MAC_TXSTAT_LCE) { - gp->net_stats.tx_aborted_errors += 0x10000; - gp->net_stats.collisions += 0x10000; + dev->stats.tx_aborted_errors += 0x10000; + dev->stats.collisions += 0x10000; } /* We do not keep track of MAC_TXSTAT_FCE and @@ -469,20 +469,20 @@ static int gem_rxmac_interrupt(struct net_device *dev, struct gem *gp, u32 gem_s u32 smac = readl(gp->regs + MAC_SMACHINE); netdev_err(dev, "RX MAC fifo overflow smac[%08x]\n", smac); - gp->net_stats.rx_over_errors++; - gp->net_stats.rx_fifo_errors++; + dev->stats.rx_over_errors++; + dev->stats.rx_fifo_errors++; ret = gem_rxmac_reset(gp); } if (rxmac_stat & MAC_RXSTAT_ACE) - gp->net_stats.rx_frame_errors += 0x10000; + dev->stats.rx_frame_errors += 0x10000; if (rxmac_stat & MAC_RXSTAT_CCE) - gp->net_stats.rx_crc_errors += 0x10000; + dev->stats.rx_crc_errors += 0x10000; if (rxmac_stat & MAC_RXSTAT_LCE) - gp->net_stats.rx_length_errors += 0x10000; + dev->stats.rx_length_errors += 0x10000; /* We do not track MAC_RXSTAT_FCE and MAC_RXSTAT_VCE * events. @@ -594,7 +594,7 @@ static int gem_abnormal_irq(struct net_device *dev, struct gem *gp, u32 gem_stat if (netif_msg_rx_err(gp)) printk(KERN_DEBUG "%s: no buffer for rx frame\n", gp->dev->name); - gp->net_stats.rx_dropped++; + dev->stats.rx_dropped++; } if (gem_status & GREG_STAT_RXTAGERR) { @@ -602,7 +602,7 @@ static int gem_abnormal_irq(struct net_device *dev, struct gem *gp, u32 gem_stat if (netif_msg_rx_err(gp)) printk(KERN_DEBUG "%s: corrupt rx tag framing\n", gp->dev->name); - gp->net_stats.rx_errors++; + dev->stats.rx_errors++; goto do_reset; } @@ -684,7 +684,7 @@ static __inline__ void gem_tx(struct net_device *dev, struct gem *gp, u32 gem_st break; } gp->tx_skbs[entry] = NULL; - gp->net_stats.tx_bytes += skb->len; + dev->stats.tx_bytes += skb->len; for (frag = 0; frag <= skb_shinfo(skb)->nr_frags; frag++) { txd = &gp->init_block->txd[entry]; @@ -696,7 +696,7 @@ static __inline__ void gem_tx(struct net_device *dev, struct gem *gp, u32 gem_st entry = NEXT_TX(entry); } - gp->net_stats.tx_packets++; + dev->stats.tx_packets++; dev_kfree_skb_irq(skb); } gp->tx_old = entry; @@ -738,6 +738,7 @@ static __inline__ void gem_post_rxds(struct gem *gp, int limit) static int gem_rx(struct gem *gp, int work_to_do) { + struct net_device *dev = gp->dev; int entry, drops, work_done = 0; u32 done; __sum16 csum; @@ -782,15 +783,15 @@ static int gem_rx(struct gem *gp, int work_to_do) len = (status & RXDCTRL_BUFSZ) >> 16; if ((len < ETH_ZLEN) || (status & RXDCTRL_BAD)) { - gp->net_stats.rx_errors++; + dev->stats.rx_errors++; if (len < ETH_ZLEN) - gp->net_stats.rx_length_errors++; + dev->stats.rx_length_errors++; if (len & RXDCTRL_BAD) - gp->net_stats.rx_crc_errors++; + dev->stats.rx_crc_errors++; /* We'll just return it to GEM. */ drop_it: - gp->net_stats.rx_dropped++; + dev->stats.rx_dropped++; goto next; } @@ -843,8 +844,8 @@ static int gem_rx(struct gem *gp, int work_to_do) netif_receive_skb(skb); - gp->net_stats.rx_packets++; - gp->net_stats.rx_bytes += len; + dev->stats.rx_packets++; + dev->stats.rx_bytes += len; next: entry = NEXT_RX(entry); @@ -2472,7 +2473,6 @@ static int gem_resume(struct pci_dev *pdev) static struct net_device_stats *gem_get_stats(struct net_device *dev) { struct gem *gp = netdev_priv(dev); - struct net_device_stats *stats = &gp->net_stats; spin_lock_irq(&gp->lock); spin_lock(&gp->tx_lock); @@ -2481,17 +2481,17 @@ static struct net_device_stats *gem_get_stats(struct net_device *dev) * so we shield against this */ if (gp->running) { - stats->rx_crc_errors += readl(gp->regs + MAC_FCSERR); + dev->stats.rx_crc_errors += readl(gp->regs + MAC_FCSERR); writel(0, gp->regs + MAC_FCSERR); - stats->rx_frame_errors += readl(gp->regs + MAC_AERR); + dev->stats.rx_frame_errors += readl(gp->regs + MAC_AERR); writel(0, gp->regs + MAC_AERR); - stats->rx_length_errors += readl(gp->regs + MAC_LERR); + dev->stats.rx_length_errors += readl(gp->regs + MAC_LERR); writel(0, gp->regs + MAC_LERR); - stats->tx_aborted_errors += readl(gp->regs + MAC_ECOLL); - stats->collisions += + dev->stats.tx_aborted_errors += readl(gp->regs + MAC_ECOLL); + dev->stats.collisions += (readl(gp->regs + MAC_ECOLL) + readl(gp->regs + MAC_LCOLL)); writel(0, gp->regs + MAC_ECOLL); @@ -2501,7 +2501,7 @@ static struct net_device_stats *gem_get_stats(struct net_device *dev) spin_unlock(&gp->tx_lock); spin_unlock_irq(&gp->lock); - return &gp->net_stats; + return &dev->stats; } static int gem_set_mac_address(struct net_device *dev, void *addr) diff --git a/drivers/net/sungem.h b/drivers/net/sungem.h index 1990546..ede0178 100644 --- a/drivers/net/sungem.h +++ b/drivers/net/sungem.h @@ -994,7 +994,6 @@ struct gem { u32 status; struct napi_struct napi; - struct net_device_stats net_stats; int tx_fifo_sz; int rx_fifo_sz; diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c index 93b32d3..cc06952 100644 --- a/drivers/net/tg3.c +++ b/drivers/net/tg3.c @@ -4,7 +4,7 @@ * Copyright (C) 2001, 2002, 2003, 2004 David S. Miller (davem@redhat.com) * Copyright (C) 2001, 2002, 2003 Jeff Garzik (jgarzik@pobox.com) * Copyright (C) 2004 Sun Microsystems Inc. - * Copyright (C) 2005-2010 Broadcom Corporation. + * Copyright (C) 2005-2011 Broadcom Corporation. * * Firmware is: * Derived from proprietary unpublished source code, @@ -64,10 +64,10 @@ #define DRV_MODULE_NAME "tg3" #define TG3_MAJ_NUM 3 -#define TG3_MIN_NUM 116 +#define TG3_MIN_NUM 117 #define DRV_MODULE_VERSION \ __stringify(TG3_MAJ_NUM) "." __stringify(TG3_MIN_NUM) -#define DRV_MODULE_RELDATE "December 3, 2010" +#define DRV_MODULE_RELDATE "January 25, 2011" #define TG3_DEF_MAC_MODE 0 #define TG3_DEF_RX_MODE 0 @@ -1776,9 +1776,29 @@ static void tg3_phy_eee_adjust(struct tg3 *tp, u32 current_link_up) tg3_phy_cl45_read(tp, MDIO_MMD_AN, TG3_CL45_D7_EEERES_STAT, &val); - if (val == TG3_CL45_D7_EEERES_STAT_LP_1000T || - val == TG3_CL45_D7_EEERES_STAT_LP_100TX) + switch (val) { + case TG3_CL45_D7_EEERES_STAT_LP_1000T: + switch (GET_ASIC_REV(tp->pci_chip_rev_id)) { + case ASIC_REV_5717: + case ASIC_REV_5719: + case ASIC_REV_57765: + /* Enable SM_DSP clock and tx 6dB coding. */ + val = MII_TG3_AUXCTL_SHDWSEL_AUXCTL | + MII_TG3_AUXCTL_ACTL_SMDSP_ENA | + MII_TG3_AUXCTL_ACTL_TX_6DB; + tg3_writephy(tp, MII_TG3_AUX_CTRL, val); + + tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, 0x0000); + + /* Turn off SM_DSP clock. */ + val = MII_TG3_AUXCTL_SHDWSEL_AUXCTL | + MII_TG3_AUXCTL_ACTL_TX_6DB; + tg3_writephy(tp, MII_TG3_AUX_CTRL, val); + } + /* Fallthrough */ + case TG3_CL45_D7_EEERES_STAT_LP_100TX: tp->setlpicnt = 2; + } } if (!tp->setlpicnt) { @@ -2968,11 +2988,19 @@ static void tg3_phy_copper_begin(struct tg3 *tp) MII_TG3_AUXCTL_ACTL_TX_6DB; tg3_writephy(tp, MII_TG3_AUX_CTRL, val); - if ((GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5717 || - GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_57765) && - !tg3_phydsp_read(tp, MII_TG3_DSP_CH34TP2, &val)) - tg3_phydsp_write(tp, MII_TG3_DSP_CH34TP2, - val | MII_TG3_DSP_CH34TP2_HIBW01); + switch (GET_ASIC_REV(tp->pci_chip_rev_id)) { + case ASIC_REV_5717: + case ASIC_REV_57765: + if (!tg3_phydsp_read(tp, MII_TG3_DSP_CH34TP2, &val)) + tg3_phydsp_write(tp, MII_TG3_DSP_CH34TP2, val | + MII_TG3_DSP_CH34TP2_HIBW01); + /* Fall through */ + case ASIC_REV_5719: + val = MII_TG3_DSP_TAP26_ALNOKO | + MII_TG3_DSP_TAP26_RMRXSTO | + MII_TG3_DSP_TAP26_OPCSINPT; + tg3_phydsp_write(tp, MII_TG3_DSP_TAP26, val); + } val = 0; if (tp->link_config.autoneg == AUTONEG_ENABLE) { @@ -7801,7 +7829,7 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) TG3_CPMU_DBTMR1_LNKIDLE_2047US); tw32_f(TG3_CPMU_EEE_DBTMR2, - TG3_CPMU_DBTMR1_APE_TX_2047US | + TG3_CPMU_DBTMR2_APE_TX_2047US | TG3_CPMU_DBTMR2_TXIDXEQ_2047US); } @@ -8075,8 +8103,9 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) /* Program the jumbo buffer descriptor ring control * blocks on those devices that have them. */ - if ((tp->tg3_flags & TG3_FLAG_JUMBO_CAPABLE) && - !(tp->tg3_flags2 & TG3_FLG2_5780_CLASS)) { + if (tp->pci_chip_rev_id == CHIPREV_ID_5719_A0 || + ((tp->tg3_flags & TG3_FLAG_JUMBO_CAPABLE) && + !(tp->tg3_flags2 & TG3_FLG2_5780_CLASS))) { /* Setup replenish threshold. */ tw32(RCVBDI_JUMBO_THRESH, tp->rx_jumbo_pending / 8); @@ -8194,8 +8223,12 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) (tp->tg3_flags3 & TG3_FLG3_5717_PLUS)) { val = tr32(TG3_RDMA_RSRVCTRL_REG); if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719) { - val &= ~TG3_RDMA_RSRVCTRL_TXMRGN_MASK; - val |= TG3_RDMA_RSRVCTRL_TXMRGN_320B; + val &= ~(TG3_RDMA_RSRVCTRL_TXMRGN_MASK | + TG3_RDMA_RSRVCTRL_FIFO_LWM_MASK | + TG3_RDMA_RSRVCTRL_FIFO_HWM_MASK); + val |= TG3_RDMA_RSRVCTRL_TXMRGN_320B | + TG3_RDMA_RSRVCTRL_FIFO_LWM_1_5K | + TG3_RDMA_RSRVCTRL_FIFO_HWM_1_5K; } tw32(TG3_RDMA_RSRVCTRL_REG, val | TG3_RDMA_RSRVCTRL_FIFO_OFLW_FIX); @@ -8317,7 +8350,8 @@ static int tg3_reset_hw(struct tg3 *tp, int reset_phy) tw32_f(GRC_LOCAL_CTRL, tp->grc_local_ctrl); udelay(100); - if (tp->tg3_flags2 & TG3_FLG2_USING_MSIX) { + if ((tp->tg3_flags2 & TG3_FLG2_USING_MSIX) && + tp->irq_cnt > 1) { val = tr32(MSGINT_MODE); val |= MSGINT_MODE_MULTIVEC_EN | MSGINT_MODE_ENABLE; tw32(MSGINT_MODE, val); @@ -9057,7 +9091,8 @@ static void tg3_ints_init(struct tg3 *tp) if (tp->tg3_flags2 & TG3_FLG2_USING_MSI_OR_MSIX) { u32 msi_mode = tr32(MSGINT_MODE); - if (tp->tg3_flags2 & TG3_FLG2_USING_MSIX) + if ((tp->tg3_flags2 & TG3_FLG2_USING_MSIX) && + tp->irq_cnt > 1) msi_mode |= MSGINT_MODE_MULTIVEC_EN; tw32(MSGINT_MODE, msi_mode | MSGINT_MODE_ENABLE); } @@ -10833,13 +10868,16 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode) if (loopback_mode == TG3_MAC_LOOPBACK) { /* HW errata - mac loopback fails in some cases on 5780. * Normal traffic and PHY loopback are not affected by - * errata. + * errata. Also, the MAC loopback test is deprecated for + * all newer ASIC revisions. */ - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5780) + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5780 || + (tp->tg3_flags & TG3_FLAG_CPMU_PRESENT)) return 0; - mac_mode = (tp->mac_mode & ~MAC_MODE_PORT_MODE_MASK) | - MAC_MODE_PORT_INT_LPBACK; + mac_mode = tp->mac_mode & + ~(MAC_MODE_PORT_MODE_MASK | MAC_MODE_HALF_DUPLEX); + mac_mode |= MAC_MODE_PORT_INT_LPBACK; if (!(tp->tg3_flags2 & TG3_FLG2_5705_PLUS)) mac_mode |= MAC_MODE_LINK_POLARITY; if (tp->phy_flags & TG3_PHYFLG_10_100_ONLY) @@ -10861,7 +10899,8 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode) tg3_writephy(tp, MII_BMCR, val); udelay(40); - mac_mode = tp->mac_mode & ~MAC_MODE_PORT_MODE_MASK; + mac_mode = tp->mac_mode & + ~(MAC_MODE_PORT_MODE_MASK | MAC_MODE_HALF_DUPLEX); if (tp->phy_flags & TG3_PHYFLG_IS_FET) { tg3_writephy(tp, MII_TG3_FET_PTEST, MII_TG3_FET_PTEST_FRC_TX_LINK | @@ -10889,6 +10928,13 @@ static int tg3_run_loopback(struct tg3 *tp, int loopback_mode) MII_TG3_EXT_CTRL_LNK3_LED_MODE); } tw32(MAC_MODE, mac_mode); + + /* Wait for link */ + for (i = 0; i < 100; i++) { + if (tr32(MAC_TX_STATUS) & TX_STATUS_LINK_UP) + break; + mdelay(1); + } } else { return -EINVAL; } @@ -10995,14 +11041,19 @@ out: static int tg3_test_loopback(struct tg3 *tp) { int err = 0; - u32 cpmuctrl = 0; + u32 eee_cap, cpmuctrl = 0; if (!netif_running(tp->dev)) return TG3_LOOPBACK_FAILED; + eee_cap = tp->phy_flags & TG3_PHYFLG_EEE_CAP; + tp->phy_flags &= ~TG3_PHYFLG_EEE_CAP; + err = tg3_reset_hw(tp, 1); - if (err) - return TG3_LOOPBACK_FAILED; + if (err) { + err = TG3_LOOPBACK_FAILED; + goto done; + } /* Turn off gphy autopowerdown. */ if (tp->phy_flags & TG3_PHYFLG_ENABLE_APD) @@ -11022,8 +11073,10 @@ static int tg3_test_loopback(struct tg3 *tp) udelay(10); } - if (status != CPMU_MUTEX_GNT_DRIVER) - return TG3_LOOPBACK_FAILED; + if (status != CPMU_MUTEX_GNT_DRIVER) { + err = TG3_LOOPBACK_FAILED; + goto done; + } /* Turn off link-based power management. */ cpmuctrl = tr32(TG3_CPMU_CTRL); @@ -11052,6 +11105,9 @@ static int tg3_test_loopback(struct tg3 *tp) if (tp->phy_flags & TG3_PHYFLG_ENABLE_APD) tg3_phy_toggle_apd(tp, true); +done: + tp->phy_flags |= eee_cap; + return err; } @@ -11158,7 +11214,9 @@ static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (tp->phy_flags & TG3_PHYFLG_PHY_SERDES) break; /* We have no PHY */ - if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) + if ((tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) || + ((tp->tg3_flags & TG3_FLAG_ENABLE_ASF) && + !netif_running(dev))) return -EAGAIN; spin_lock_bh(&tp->lock); @@ -11174,7 +11232,9 @@ static int tg3_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) if (tp->phy_flags & TG3_PHYFLG_PHY_SERDES) break; /* We have no PHY */ - if (tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) + if ((tp->phy_flags & TG3_PHYFLG_IS_LOW_POWER) || + ((tp->tg3_flags & TG3_FLAG_ENABLE_ASF) && + !netif_running(dev))) return -EAGAIN; spin_lock_bh(&tp->lock); @@ -13258,7 +13318,9 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) } /* Determine TSO capabilities */ - if (tp->tg3_flags3 & TG3_FLG3_5717_PLUS) + if (tp->pci_chip_rev_id == CHIPREV_ID_5719_A0) + ; /* Do nothing. HW bug. */ + else if (tp->tg3_flags3 & TG3_FLG3_5717_PLUS) tp->tg3_flags2 |= TG3_FLG2_HW_TSO_3; else if ((tp->tg3_flags3 & TG3_FLG3_5755_PLUS) || GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5906) @@ -13309,7 +13371,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) tp->tg3_flags3 |= TG3_FLG3_40BIT_DMA_LIMIT_BUG; } - if (tp->tg3_flags3 & TG3_FLG3_5717_PLUS) + if ((tp->tg3_flags3 & TG3_FLG3_5717_PLUS) && + tp->pci_chip_rev_id != CHIPREV_ID_5719_A0) tp->tg3_flags3 |= TG3_FLG3_USE_JUMBO_BDFLAG; if (!(tp->tg3_flags2 & TG3_FLG2_5705_PLUS) || @@ -13327,42 +13390,8 @@ static int __devinit tg3_get_invariants(struct tg3 *tp) tp->tg3_flags2 |= TG3_FLG2_PCI_EXPRESS; tp->pcie_readrq = 4096; - if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719) { - u16 word; - - pci_read_config_word(tp->pdev, - tp->pcie_cap + PCI_EXP_LNKSTA, - &word); - switch (word & PCI_EXP_LNKSTA_CLS) { - case PCI_EXP_LNKSTA_CLS_2_5GB: - word &= PCI_EXP_LNKSTA_NLW; - word >>= PCI_EXP_LNKSTA_NLW_SHIFT; - switch (word) { - case 2: - tp->pcie_readrq = 2048; - break; - case 4: - tp->pcie_readrq = 1024; - break; - } - break; - - case PCI_EXP_LNKSTA_CLS_5_0GB: - word &= PCI_EXP_LNKSTA_NLW; - word >>= PCI_EXP_LNKSTA_NLW_SHIFT; - switch (word) { - case 1: - tp->pcie_readrq = 2048; - break; - case 2: - tp->pcie_readrq = 1024; - break; - case 4: - tp->pcie_readrq = 512; - break; - } - } - } + if (GET_ASIC_REV(tp->pci_chip_rev_id) == ASIC_REV_5719) + tp->pcie_readrq = 2048; pcie_set_readrq(tp->pdev, tp->pcie_readrq); diff --git a/drivers/net/tg3.h b/drivers/net/tg3.h index f528243..73884b6 100644 --- a/drivers/net/tg3.h +++ b/drivers/net/tg3.h @@ -4,7 +4,7 @@ * Copyright (C) 2001, 2002, 2003, 2004 David S. Miller (davem@redhat.com) * Copyright (C) 2001 Jeff Garzik (jgarzik@pobox.com) * Copyright (C) 2004 Sun Microsystems Inc. - * Copyright (C) 2007-2010 Broadcom Corporation. + * Copyright (C) 2007-2011 Broadcom Corporation. */ #ifndef _T3_H @@ -141,6 +141,7 @@ #define CHIPREV_ID_57780_A1 0x57780001 #define CHIPREV_ID_5717_A0 0x05717000 #define CHIPREV_ID_57765_A0 0x57785000 +#define CHIPREV_ID_5719_A0 0x05719000 #define GET_ASIC_REV(CHIP_REV_ID) ((CHIP_REV_ID) >> 12) #define ASIC_REV_5700 0x07 #define ASIC_REV_5701 0x00 @@ -1105,7 +1106,7 @@ #define TG3_CPMU_DBTMR1_PCIEXIT_2047US 0x07ff0000 #define TG3_CPMU_DBTMR1_LNKIDLE_2047US 0x000070ff #define TG3_CPMU_EEE_DBTMR2 0x000036b8 -#define TG3_CPMU_DBTMR1_APE_TX_2047US 0x07ff0000 +#define TG3_CPMU_DBTMR2_APE_TX_2047US 0x07ff0000 #define TG3_CPMU_DBTMR2_TXIDXEQ_2047US 0x000070ff #define TG3_CPMU_EEE_LNKIDL_CTRL 0x000036bc #define TG3_CPMU_EEE_LNKIDL_PCIE_NL0 0x01000000 @@ -1333,6 +1334,10 @@ #define TG3_RDMA_RSRVCTRL_REG 0x00004900 #define TG3_RDMA_RSRVCTRL_FIFO_OFLW_FIX 0x00000004 +#define TG3_RDMA_RSRVCTRL_FIFO_LWM_1_5K 0x00000c00 +#define TG3_RDMA_RSRVCTRL_FIFO_LWM_MASK 0x00000ff0 +#define TG3_RDMA_RSRVCTRL_FIFO_HWM_1_5K 0x000c0000 +#define TG3_RDMA_RSRVCTRL_FIFO_HWM_MASK 0x000ff000 #define TG3_RDMA_RSRVCTRL_TXMRGN_320B 0x28000000 #define TG3_RDMA_RSRVCTRL_TXMRGN_MASK 0xffe00000 /* 0x4904 --> 0x4910 unused */ @@ -2108,6 +2113,10 @@ #define MII_TG3_DSP_TAP1 0x0001 #define MII_TG3_DSP_TAP1_AGCTGT_DFLT 0x0007 +#define MII_TG3_DSP_TAP26 0x001a +#define MII_TG3_DSP_TAP26_ALNOKO 0x0001 +#define MII_TG3_DSP_TAP26_RMRXSTO 0x0002 +#define MII_TG3_DSP_TAP26_OPCSINPT 0x0004 #define MII_TG3_DSP_AADJ1CH0 0x001f #define MII_TG3_DSP_CH34TP2 0x4022 #define MII_TG3_DSP_CH34TP2_HIBW01 0x0010 diff --git a/drivers/net/tlan.c b/drivers/net/tlan.c index f8e463c..0678e7e 100644 --- a/drivers/net/tlan.c +++ b/drivers/net/tlan.c @@ -63,45 +63,45 @@ * - Other minor stuff * * v1.4 Feb 10, 2000 - Updated with more changes required after Dave's - * network cleanup in 2.3.43pre7 (Tigran & myself) - * - Minor stuff. + * network cleanup in 2.3.43pre7 (Tigran & myself) + * - Minor stuff. * - * v1.5 March 22, 2000 - Fixed another timer bug that would hang the driver - * if no cable/link were present. + * v1.5 March 22, 2000 - Fixed another timer bug that would hang the + * driver if no cable/link were present. * - Cosmetic changes. * - TODO: Port completely to new PCI/DMA API - * Auto-Neg fallback. - * - * v1.6 April 04, 2000 - Fixed driver support for kernel-parameters. Haven't - * tested it though, as the kernel support is currently - * broken (2.3.99p4p3). - * - Updated tlan.txt accordingly. - * - Adjusted minimum/maximum frame length. - * - There is now a TLAN website up at - * http://hp.sourceforge.net/ - * - * v1.7 April 07, 2000 - Started to implement custom ioctls. Driver now - * reports PHY information when used with Donald - * Beckers userspace MII diagnostics utility. - * - * v1.8 April 23, 2000 - Fixed support for forced speed/duplex settings. - * - Added link information to Auto-Neg and forced - * modes. When NIC operates with auto-neg the driver - * will report Link speed & duplex modes as well as - * link partner abilities. When forced link is used, - * the driver will report status of the established - * link. - * Please read tlan.txt for additional information. - * - Removed call to check_region(), and used - * return value of request_region() instead. + * Auto-Neg fallback. + * + * v1.6 April 04, 2000 - Fixed driver support for kernel-parameters. + * Haven't tested it though, as the kernel support + * is currently broken (2.3.99p4p3). + * - Updated tlan.txt accordingly. + * - Adjusted minimum/maximum frame length. + * - There is now a TLAN website up at + * http://hp.sourceforge.net/ + * + * v1.7 April 07, 2000 - Started to implement custom ioctls. Driver now + * reports PHY information when used with Donald + * Beckers userspace MII diagnostics utility. + * + * v1.8 April 23, 2000 - Fixed support for forced speed/duplex settings. + * - Added link information to Auto-Neg and forced + * modes. When NIC operates with auto-neg the driver + * will report Link speed & duplex modes as well as + * link partner abilities. When forced link is used, + * the driver will report status of the established + * link. + * Please read tlan.txt for additional information. + * - Removed call to check_region(), and used + * return value of request_region() instead. * * v1.8a May 28, 2000 - Minor updates. * * v1.9 July 25, 2000 - Fixed a few remaining Full-Duplex issues. - * - Updated with timer fixes from Andrew Morton. - * - Fixed module race in TLan_Open. - * - Added routine to monitor PHY status. - * - Added activity led support for Proliant devices. + * - Updated with timer fixes from Andrew Morton. + * - Fixed module race in TLan_Open. + * - Added routine to monitor PHY status. + * - Added activity led support for Proliant devices. * * v1.10 Aug 30, 2000 - Added support for EISA based tlan controllers * like the Compaq NetFlex3/E. @@ -111,8 +111,8 @@ * hardware probe is done with kernel API and * TLan_EisaProbe. * - Adjusted debug information for probing. - * - Fixed bug that would cause general debug information - * to be printed after driver removal. + * - Fixed bug that would cause general debug + * information to be printed after driver removal. * - Added transmit timeout handling. * - Fixed OOM return values in tlan_probe. * - Fixed possible mem leak in tlan_exit @@ -136,8 +136,8 @@ * * v1.12 Oct 12, 2000 - Minor fixes (memleak, init, etc.) * - * v1.13 Nov 28, 2000 - Stop flooding console with auto-neg issues - * when link can't be established. + * v1.13 Nov 28, 2000 - Stop flooding console with auto-neg issues + * when link can't be established. * - Added the bbuf option as a kernel parameter. * - Fixed ioaddr probe bug. * - Fixed stupid deadlock with MII interrupts. @@ -147,28 +147,30 @@ * TLAN v1.0 silicon. This needs to be investigated * further. * - * v1.14 Dec 16, 2000 - Added support for servicing multiple frames per. - * interrupt. Thanks goes to - * Adam Keys <adam@ti.com> - * Denis Beaudoin <dbeaudoin@ti.com> - * for providing the patch. - * - Fixed auto-neg output when using multiple - * adapters. - * - Converted to use new taskq interface. + * v1.14 Dec 16, 2000 - Added support for servicing multiple frames per. + * interrupt. Thanks goes to + * Adam Keys <adam@ti.com> + * Denis Beaudoin <dbeaudoin@ti.com> + * for providing the patch. + * - Fixed auto-neg output when using multiple + * adapters. + * - Converted to use new taskq interface. * - * v1.14a Jan 6, 2001 - Minor adjustments (spinlocks, etc.) + * v1.14a Jan 6, 2001 - Minor adjustments (spinlocks, etc.) * * Samuel Chessman <chessman@tux.org> New Maintainer! * * v1.15 Apr 4, 2002 - Correct operation when aui=1 to be - * 10T half duplex no loopback - * Thanks to Gunnar Eikman + * 10T half duplex no loopback + * Thanks to Gunnar Eikman * * Sakari Ailus <sakari.ailus@iki.fi>: * * v1.15a Dec 15 2008 - Remove bbuf support, it doesn't work anyway. + * v1.16 Jan 6 2011 - Make checkpatch.pl happy. + * v1.17 Jan 6 2011 - Add suspend/resume support. * - *******************************************************************************/ + ******************************************************************************/ #include <linux/module.h> #include <linux/init.h> @@ -185,13 +187,11 @@ #include "tlan.h" -typedef u32 (TLanIntVectorFunc)( struct net_device *, u16 ); - /* For removing EISA devices */ -static struct net_device *TLan_Eisa_Devices; +static struct net_device *tlan_eisa_devices; -static int TLanDevicesInstalled; +static int tlan_devices_installed; /* Set speed, duplex and aui settings */ static int aui[MAX_TLAN_BOARDS]; @@ -202,7 +202,8 @@ module_param_array(aui, int, NULL, 0); module_param_array(duplex, int, NULL, 0); module_param_array(speed, int, NULL, 0); MODULE_PARM_DESC(aui, "ThunderLAN use AUI port(s) (0-1)"); -MODULE_PARM_DESC(duplex, "ThunderLAN duplex setting(s) (0-default, 1-half, 2-full)"); +MODULE_PARM_DESC(duplex, + "ThunderLAN duplex setting(s) (0-default, 1-half, 2-full)"); MODULE_PARM_DESC(speed, "ThunderLAN port speen setting(s) (0,10,100)"); MODULE_AUTHOR("Maintainer: Samuel Chessman <chessman@tux.org>"); @@ -218,139 +219,144 @@ static int debug; module_param(debug, int, 0); MODULE_PARM_DESC(debug, "ThunderLAN debug mask"); -static const char TLanSignature[] = "TLAN"; -static const char tlan_banner[] = "ThunderLAN driver v1.15a\n"; +static const char tlan_signature[] = "TLAN"; +static const char tlan_banner[] = "ThunderLAN driver v1.17\n"; static int tlan_have_pci; static int tlan_have_eisa; -static const char *media[] = { - "10BaseT-HD ", "10BaseT-FD ","100baseTx-HD ", - "100baseTx-FD", "100baseT4", NULL +static const char * const media[] = { + "10BaseT-HD", "10BaseT-FD", "100baseTx-HD", + "100BaseTx-FD", "100BaseT4", NULL }; static struct board { - const char *deviceLabel; - u32 flags; - u16 addrOfs; + const char *device_label; + u32 flags; + u16 addr_ofs; } board_info[] = { { "Compaq Netelligent 10 T PCI UTP", TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, - { "Compaq Netelligent 10/100 TX PCI UTP", TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, + { "Compaq Netelligent 10/100 TX PCI UTP", + TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, { "Compaq Integrated NetFlex-3/P", TLAN_ADAPTER_NONE, 0x83 }, { "Compaq NetFlex-3/P", TLAN_ADAPTER_UNMANAGED_PHY | TLAN_ADAPTER_BIT_RATE_PHY, 0x83 }, { "Compaq NetFlex-3/P", TLAN_ADAPTER_NONE, 0x83 }, { "Compaq Netelligent Integrated 10/100 TX UTP", TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, - { "Compaq Netelligent Dual 10/100 TX PCI UTP", TLAN_ADAPTER_NONE, 0x83 }, - { "Compaq Netelligent 10/100 TX Embedded UTP", TLAN_ADAPTER_NONE, 0x83 }, + { "Compaq Netelligent Dual 10/100 TX PCI UTP", + TLAN_ADAPTER_NONE, 0x83 }, + { "Compaq Netelligent 10/100 TX Embedded UTP", + TLAN_ADAPTER_NONE, 0x83 }, { "Olicom OC-2183/2185", TLAN_ADAPTER_USE_INTERN_10, 0x83 }, - { "Olicom OC-2325", TLAN_ADAPTER_UNMANAGED_PHY, 0xF8 }, - { "Olicom OC-2326", TLAN_ADAPTER_USE_INTERN_10, 0xF8 }, + { "Olicom OC-2325", TLAN_ADAPTER_UNMANAGED_PHY, 0xf8 }, + { "Olicom OC-2326", TLAN_ADAPTER_USE_INTERN_10, 0xf8 }, { "Compaq Netelligent 10/100 TX UTP", TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, - { "Compaq Netelligent 10 T/2 PCI UTP/Coax", TLAN_ADAPTER_NONE, 0x83 }, + { "Compaq Netelligent 10 T/2 PCI UTP/coax", TLAN_ADAPTER_NONE, 0x83 }, { "Compaq NetFlex-3/E", - TLAN_ADAPTER_ACTIVITY_LED | /* EISA card */ + TLAN_ADAPTER_ACTIVITY_LED | /* EISA card */ TLAN_ADAPTER_UNMANAGED_PHY | TLAN_ADAPTER_BIT_RATE_PHY, 0x83 }, - { "Compaq NetFlex-3/E", TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, /* EISA card */ + { "Compaq NetFlex-3/E", + TLAN_ADAPTER_ACTIVITY_LED, 0x83 }, /* EISA card */ }; static DEFINE_PCI_DEVICE_TABLE(tlan_pci_tbl) = { { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETEL10, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETEL100, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 1 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 1 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETFLEX3I, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 2 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 2 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_THUNDER, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 3 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 3 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETFLEX3B, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 4 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 4 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETEL100PI, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 5 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 5 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETEL100D, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 6 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 6 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_COMPAQ_NETEL100I, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 7 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 7 }, { PCI_VENDOR_ID_OLICOM, PCI_DEVICE_ID_OLICOM_OC2183, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 8 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 8 }, { PCI_VENDOR_ID_OLICOM, PCI_DEVICE_ID_OLICOM_OC2325, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 9 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 9 }, { PCI_VENDOR_ID_OLICOM, PCI_DEVICE_ID_OLICOM_OC2326, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 10 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 10 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_NETELLIGENT_10_100_WS_5100, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 11 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 11 }, { PCI_VENDOR_ID_COMPAQ, PCI_DEVICE_ID_NETELLIGENT_10_T2, - PCI_ANY_ID, PCI_ANY_ID, 0, 0, 12 }, + PCI_ANY_ID, PCI_ANY_ID, 0, 0, 12 }, { 0,} }; MODULE_DEVICE_TABLE(pci, tlan_pci_tbl); -static void TLan_EisaProbe( void ); -static void TLan_Eisa_Cleanup( void ); -static int TLan_Init( struct net_device * ); -static int TLan_Open( struct net_device *dev ); -static netdev_tx_t TLan_StartTx( struct sk_buff *, struct net_device *); -static irqreturn_t TLan_HandleInterrupt( int, void *); -static int TLan_Close( struct net_device *); -static struct net_device_stats *TLan_GetStats( struct net_device *); -static void TLan_SetMulticastList( struct net_device *); -static int TLan_ioctl( struct net_device *dev, struct ifreq *rq, int cmd); -static int TLan_probe1( struct pci_dev *pdev, long ioaddr, - int irq, int rev, const struct pci_device_id *ent); -static void TLan_tx_timeout( struct net_device *dev); -static void TLan_tx_timeout_work(struct work_struct *work); -static int tlan_init_one( struct pci_dev *pdev, const struct pci_device_id *ent); - -static u32 TLan_HandleTxEOF( struct net_device *, u16 ); -static u32 TLan_HandleStatOverflow( struct net_device *, u16 ); -static u32 TLan_HandleRxEOF( struct net_device *, u16 ); -static u32 TLan_HandleDummy( struct net_device *, u16 ); -static u32 TLan_HandleTxEOC( struct net_device *, u16 ); -static u32 TLan_HandleStatusCheck( struct net_device *, u16 ); -static u32 TLan_HandleRxEOC( struct net_device *, u16 ); - -static void TLan_Timer( unsigned long ); - -static void TLan_ResetLists( struct net_device * ); -static void TLan_FreeLists( struct net_device * ); -static void TLan_PrintDio( u16 ); -static void TLan_PrintList( TLanList *, char *, int ); -static void TLan_ReadAndClearStats( struct net_device *, int ); -static void TLan_ResetAdapter( struct net_device * ); -static void TLan_FinishReset( struct net_device * ); -static void TLan_SetMac( struct net_device *, int areg, char *mac ); - -static void TLan_PhyPrint( struct net_device * ); -static void TLan_PhyDetect( struct net_device * ); -static void TLan_PhyPowerDown( struct net_device * ); -static void TLan_PhyPowerUp( struct net_device * ); -static void TLan_PhyReset( struct net_device * ); -static void TLan_PhyStartLink( struct net_device * ); -static void TLan_PhyFinishAutoNeg( struct net_device * ); +static void tlan_eisa_probe(void); +static void tlan_eisa_cleanup(void); +static int tlan_init(struct net_device *); +static int tlan_open(struct net_device *dev); +static netdev_tx_t tlan_start_tx(struct sk_buff *, struct net_device *); +static irqreturn_t tlan_handle_interrupt(int, void *); +static int tlan_close(struct net_device *); +static struct net_device_stats *tlan_get_stats(struct net_device *); +static void tlan_set_multicast_list(struct net_device *); +static int tlan_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); +static int tlan_probe1(struct pci_dev *pdev, long ioaddr, + int irq, int rev, const struct pci_device_id *ent); +static void tlan_tx_timeout(struct net_device *dev); +static void tlan_tx_timeout_work(struct work_struct *work); +static int tlan_init_one(struct pci_dev *pdev, + const struct pci_device_id *ent); + +static u32 tlan_handle_tx_eof(struct net_device *, u16); +static u32 tlan_handle_stat_overflow(struct net_device *, u16); +static u32 tlan_handle_rx_eof(struct net_device *, u16); +static u32 tlan_handle_dummy(struct net_device *, u16); +static u32 tlan_handle_tx_eoc(struct net_device *, u16); +static u32 tlan_handle_status_check(struct net_device *, u16); +static u32 tlan_handle_rx_eoc(struct net_device *, u16); + +static void tlan_timer(unsigned long); + +static void tlan_reset_lists(struct net_device *); +static void tlan_free_lists(struct net_device *); +static void tlan_print_dio(u16); +static void tlan_print_list(struct tlan_list *, char *, int); +static void tlan_read_and_clear_stats(struct net_device *, int); +static void tlan_reset_adapter(struct net_device *); +static void tlan_finish_reset(struct net_device *); +static void tlan_set_mac(struct net_device *, int areg, char *mac); + +static void tlan_phy_print(struct net_device *); +static void tlan_phy_detect(struct net_device *); +static void tlan_phy_power_down(struct net_device *); +static void tlan_phy_power_up(struct net_device *); +static void tlan_phy_reset(struct net_device *); +static void tlan_phy_start_link(struct net_device *); +static void tlan_phy_finish_auto_neg(struct net_device *); #ifdef MONITOR -static void TLan_PhyMonitor( struct net_device * ); +static void tlan_phy_monitor(struct net_device *); #endif /* -static int TLan_PhyNop( struct net_device * ); -static int TLan_PhyInternalCheck( struct net_device * ); -static int TLan_PhyInternalService( struct net_device * ); -static int TLan_PhyDp83840aCheck( struct net_device * ); + static int tlan_phy_nop(struct net_device *); + static int tlan_phy_internal_check(struct net_device *); + static int tlan_phy_internal_service(struct net_device *); + static int tlan_phy_dp83840a_check(struct net_device *); */ -static bool TLan_MiiReadReg( struct net_device *, u16, u16, u16 * ); -static void TLan_MiiSendData( u16, u32, unsigned ); -static void TLan_MiiSync( u16 ); -static void TLan_MiiWriteReg( struct net_device *, u16, u16, u16 ); +static bool tlan_mii_read_reg(struct net_device *, u16, u16, u16 *); +static void tlan_mii_send_data(u16, u32, unsigned); +static void tlan_mii_sync(u16); +static void tlan_mii_write_reg(struct net_device *, u16, u16, u16); -static void TLan_EeSendStart( u16 ); -static int TLan_EeSendByte( u16, u8, int ); -static void TLan_EeReceiveByte( u16, u8 *, int ); -static int TLan_EeReadByte( struct net_device *, u8, u8 * ); +static void tlan_ee_send_start(u16); +static int tlan_ee_send_byte(u16, u8, int); +static void tlan_ee_receive_byte(u16, u8 *, int); +static int tlan_ee_read_byte(struct net_device *, u8, u8 *); static inline void -TLan_StoreSKB( struct tlan_list_tag *tag, struct sk_buff *skb) +tlan_store_skb(struct tlan_list *tag, struct sk_buff *skb) { unsigned long addr = (unsigned long)skb; tag->buffer[9].address = addr; @@ -358,7 +364,7 @@ TLan_StoreSKB( struct tlan_list_tag *tag, struct sk_buff *skb) } static inline struct sk_buff * -TLan_GetSKB( const struct tlan_list_tag *tag) +tlan_get_skb(const struct tlan_list *tag) { unsigned long addr; @@ -367,50 +373,50 @@ TLan_GetSKB( const struct tlan_list_tag *tag) return (struct sk_buff *) addr; } - -static TLanIntVectorFunc *TLanIntVector[TLAN_INT_NUMBER_OF_INTS] = { +static u32 +(*tlan_int_vector[TLAN_INT_NUMBER_OF_INTS])(struct net_device *, u16) = { NULL, - TLan_HandleTxEOF, - TLan_HandleStatOverflow, - TLan_HandleRxEOF, - TLan_HandleDummy, - TLan_HandleTxEOC, - TLan_HandleStatusCheck, - TLan_HandleRxEOC + tlan_handle_tx_eof, + tlan_handle_stat_overflow, + tlan_handle_rx_eof, + tlan_handle_dummy, + tlan_handle_tx_eoc, + tlan_handle_status_check, + tlan_handle_rx_eoc }; static inline void -TLan_SetTimer( struct net_device *dev, u32 ticks, u32 type ) +tlan_set_timer(struct net_device *dev, u32 ticks, u32 type) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); unsigned long flags = 0; if (!in_irq()) spin_lock_irqsave(&priv->lock, flags); - if ( priv->timer.function != NULL && - priv->timerType != TLAN_TIMER_ACTIVITY ) { + if (priv->timer.function != NULL && + priv->timer_type != TLAN_TIMER_ACTIVITY) { if (!in_irq()) spin_unlock_irqrestore(&priv->lock, flags); return; } - priv->timer.function = TLan_Timer; + priv->timer.function = tlan_timer; if (!in_irq()) spin_unlock_irqrestore(&priv->lock, flags); priv->timer.data = (unsigned long) dev; - priv->timerSetAt = jiffies; - priv->timerType = type; + priv->timer_set_at = jiffies; + priv->timer_type = type; mod_timer(&priv->timer, jiffies + ticks); -} /* TLan_SetTimer */ +} /***************************************************************************** ****************************************************************************** - ThunderLAN Driver Primary Functions +ThunderLAN driver primary functions - These functions are more or less common to all Linux network drivers. +these functions are more or less common to all linux network drivers. ****************************************************************************** *****************************************************************************/ @@ -419,49 +425,117 @@ TLan_SetTimer( struct net_device *dev, u32 ticks, u32 type ) - /*************************************************************** - * tlan_remove_one - * - * Returns: - * Nothing - * Parms: - * None - * - * Goes through the TLanDevices list and frees the device - * structs and memory associated with each device (lists - * and buffers). It also ureserves the IO port regions - * associated with this device. - * - **************************************************************/ +/*************************************************************** + * tlan_remove_one + * + * Returns: + * Nothing + * Parms: + * None + * + * Goes through the TLanDevices list and frees the device + * structs and memory associated with each device (lists + * and buffers). It also ureserves the IO port regions + * associated with this device. + * + **************************************************************/ -static void __devexit tlan_remove_one( struct pci_dev *pdev) +static void __devexit tlan_remove_one(struct pci_dev *pdev) { - struct net_device *dev = pci_get_drvdata( pdev ); - TLanPrivateInfo *priv = netdev_priv(dev); + struct net_device *dev = pci_get_drvdata(pdev); + struct tlan_priv *priv = netdev_priv(dev); - unregister_netdev( dev ); + unregister_netdev(dev); - if ( priv->dmaStorage ) { - pci_free_consistent(priv->pciDev, - priv->dmaSize, priv->dmaStorage, - priv->dmaStorageDMA ); + if (priv->dma_storage) { + pci_free_consistent(priv->pci_dev, + priv->dma_size, priv->dma_storage, + priv->dma_storage_dma); } #ifdef CONFIG_PCI pci_release_regions(pdev); #endif - free_netdev( dev ); + free_netdev(dev); + + pci_set_drvdata(pdev, NULL); +} + +static void tlan_start(struct net_device *dev) +{ + tlan_reset_lists(dev); + /* NOTE: It might not be necessary to read the stats before a + reset if you don't care what the values are. + */ + tlan_read_and_clear_stats(dev, TLAN_IGNORE); + tlan_reset_adapter(dev); + netif_wake_queue(dev); +} + +static void tlan_stop(struct net_device *dev) +{ + struct tlan_priv *priv = netdev_priv(dev); + + tlan_read_and_clear_stats(dev, TLAN_RECORD); + outl(TLAN_HC_AD_RST, dev->base_addr + TLAN_HOST_CMD); + /* Reset and power down phy */ + tlan_reset_adapter(dev); + if (priv->timer.function != NULL) { + del_timer_sync(&priv->timer); + priv->timer.function = NULL; + } +} + +#ifdef CONFIG_PM + +static int tlan_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct net_device *dev = pci_get_drvdata(pdev); + + if (netif_running(dev)) + tlan_stop(dev); + + netif_device_detach(dev); + pci_save_state(pdev); + pci_disable_device(pdev); + pci_wake_from_d3(pdev, false); + pci_set_power_state(pdev, PCI_D3hot); - pci_set_drvdata( pdev, NULL ); + return 0; } +static int tlan_resume(struct pci_dev *pdev) +{ + struct net_device *dev = pci_get_drvdata(pdev); + + pci_set_power_state(pdev, PCI_D0); + pci_restore_state(pdev); + pci_enable_wake(pdev, 0, 0); + netif_device_attach(dev); + + if (netif_running(dev)) + tlan_start(dev); + + return 0; +} + +#else /* CONFIG_PM */ + +#define tlan_suspend NULL +#define tlan_resume NULL + +#endif /* CONFIG_PM */ + + static struct pci_driver tlan_driver = { .name = "tlan", .id_table = tlan_pci_tbl, .probe = tlan_init_one, .remove = __devexit_p(tlan_remove_one), + .suspend = tlan_suspend, + .resume = tlan_resume, }; static int __init tlan_probe(void) @@ -482,13 +556,13 @@ static int __init tlan_probe(void) } TLAN_DBG(TLAN_DEBUG_PROBE, "Starting EISA Probe....\n"); - TLan_EisaProbe(); + tlan_eisa_probe(); printk(KERN_INFO "TLAN: %d device%s installed, PCI: %d EISA: %d\n", - TLanDevicesInstalled, TLanDevicesInstalled == 1 ? "" : "s", - tlan_have_pci, tlan_have_eisa); + tlan_devices_installed, tlan_devices_installed == 1 ? "" : "s", + tlan_have_pci, tlan_have_eisa); - if (TLanDevicesInstalled == 0) { + if (tlan_devices_installed == 0) { rc = -ENODEV; goto err_out_pci_unreg; } @@ -501,39 +575,39 @@ err_out_pci_free: } -static int __devinit tlan_init_one( struct pci_dev *pdev, - const struct pci_device_id *ent) +static int __devinit tlan_init_one(struct pci_dev *pdev, + const struct pci_device_id *ent) { - return TLan_probe1( pdev, -1, -1, 0, ent); + return tlan_probe1(pdev, -1, -1, 0, ent); } /* - *************************************************************** - * tlan_probe1 - * - * Returns: - * 0 on success, error code on error - * Parms: - * none - * - * The name is lower case to fit in with all the rest of - * the netcard_probe names. This function looks for - * another TLan based adapter, setting it up with the - * allocated device struct if one is found. - * tlan_probe has been ported to the new net API and - * now allocates its own device structure. This function - * is also used by modules. - * - **************************************************************/ - -static int __devinit TLan_probe1(struct pci_dev *pdev, +*************************************************************** +* tlan_probe1 +* +* Returns: +* 0 on success, error code on error +* Parms: +* none +* +* The name is lower case to fit in with all the rest of +* the netcard_probe names. This function looks for +* another TLan based adapter, setting it up with the +* allocated device struct if one is found. +* tlan_probe has been ported to the new net API and +* now allocates its own device structure. This function +* is also used by modules. +* +**************************************************************/ + +static int __devinit tlan_probe1(struct pci_dev *pdev, long ioaddr, int irq, int rev, - const struct pci_device_id *ent ) + const struct pci_device_id *ent) { struct net_device *dev; - TLanPrivateInfo *priv; + struct tlan_priv *priv; u16 device_id; int reg, rc = -ENODEV; @@ -543,7 +617,7 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, if (rc) return rc; - rc = pci_request_regions(pdev, TLanSignature); + rc = pci_request_regions(pdev, tlan_signature); if (rc) { printk(KERN_ERR "TLAN: Could not reserve IO regions\n"); goto err_out; @@ -551,7 +625,7 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, } #endif /* CONFIG_PCI */ - dev = alloc_etherdev(sizeof(TLanPrivateInfo)); + dev = alloc_etherdev(sizeof(struct tlan_priv)); if (dev == NULL) { printk(KERN_ERR "TLAN: Could not allocate memory for device.\n"); rc = -ENOMEM; @@ -561,26 +635,28 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, priv = netdev_priv(dev); - priv->pciDev = pdev; + priv->pci_dev = pdev; priv->dev = dev; /* Is this a PCI device? */ if (pdev) { - u32 pci_io_base = 0; + u32 pci_io_base = 0; priv->adapter = &board_info[ent->driver_data]; rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (rc) { - printk(KERN_ERR "TLAN: No suitable PCI mapping available.\n"); + printk(KERN_ERR + "TLAN: No suitable PCI mapping available.\n"); goto err_out_free_dev; } - for ( reg= 0; reg <= 5; reg ++ ) { + for (reg = 0; reg <= 5; reg++) { if (pci_resource_flags(pdev, reg) & IORESOURCE_IO) { pci_io_base = pci_resource_start(pdev, reg); - TLAN_DBG( TLAN_DEBUG_GNRL, "IO mapping is available at %x.\n", - pci_io_base); + TLAN_DBG(TLAN_DEBUG_GNRL, + "IO mapping is available at %x.\n", + pci_io_base); break; } } @@ -592,7 +668,7 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, dev->base_addr = pci_io_base; dev->irq = pdev->irq; - priv->adapterRev = pdev->revision; + priv->adapter_rev = pdev->revision; pci_set_master(pdev); pci_set_drvdata(pdev, dev); @@ -602,11 +678,11 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, device_id = inw(ioaddr + EISA_ID2); priv->is_eisa = 1; if (device_id == 0x20F1) { - priv->adapter = &board_info[13]; /* NetFlex-3/E */ - priv->adapterRev = 23; /* TLAN 2.3 */ + priv->adapter = &board_info[13]; /* NetFlex-3/E */ + priv->adapter_rev = 23; /* TLAN 2.3 */ } else { priv->adapter = &board_info[14]; - priv->adapterRev = 10; /* TLAN 1.0 */ + priv->adapter_rev = 10; /* TLAN 1.0 */ } dev->base_addr = ioaddr; dev->irq = irq; @@ -620,11 +696,11 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, priv->speed = ((dev->mem_start & 0x18) == 0x18) ? 0 : (dev->mem_start & 0x18) >> 3; - if (priv->speed == 0x1) { + if (priv->speed == 0x1) priv->speed = TLAN_SPEED_10; - } else if (priv->speed == 0x2) { + else if (priv->speed == 0x2) priv->speed = TLAN_SPEED_100; - } + debug = priv->debug = dev->mem_end; } else { priv->aui = aui[boards_found]; @@ -635,11 +711,11 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, /* This will be used when we get an adapter error from * within our irq handler */ - INIT_WORK(&priv->tlan_tqueue, TLan_tx_timeout_work); + INIT_WORK(&priv->tlan_tqueue, tlan_tx_timeout_work); spin_lock_init(&priv->lock); - rc = TLan_Init(dev); + rc = tlan_init(dev); if (rc) { printk(KERN_ERR "TLAN: Could not set up device.\n"); goto err_out_free_dev; @@ -652,29 +728,29 @@ static int __devinit TLan_probe1(struct pci_dev *pdev, } - TLanDevicesInstalled++; + tlan_devices_installed++; boards_found++; /* pdev is NULL if this is an EISA device */ if (pdev) tlan_have_pci++; else { - priv->nextDevice = TLan_Eisa_Devices; - TLan_Eisa_Devices = dev; + priv->next_device = tlan_eisa_devices; + tlan_eisa_devices = dev; tlan_have_eisa++; } printk(KERN_INFO "TLAN: %s irq=%2d, io=%04x, %s, Rev. %d\n", - dev->name, - (int) dev->irq, - (int) dev->base_addr, - priv->adapter->deviceLabel, - priv->adapterRev); + dev->name, + (int) dev->irq, + (int) dev->base_addr, + priv->adapter->device_label, + priv->adapter_rev); return 0; err_out_uninit: - pci_free_consistent(priv->pciDev, priv->dmaSize, priv->dmaStorage, - priv->dmaStorageDMA ); + pci_free_consistent(priv->pci_dev, priv->dma_size, priv->dma_storage, + priv->dma_storage_dma); err_out_free_dev: free_netdev(dev); err_out_regions: @@ -689,22 +765,23 @@ err_out: } -static void TLan_Eisa_Cleanup(void) +static void tlan_eisa_cleanup(void) { struct net_device *dev; - TLanPrivateInfo *priv; + struct tlan_priv *priv; - while( tlan_have_eisa ) { - dev = TLan_Eisa_Devices; + while (tlan_have_eisa) { + dev = tlan_eisa_devices; priv = netdev_priv(dev); - if (priv->dmaStorage) { - pci_free_consistent(priv->pciDev, priv->dmaSize, - priv->dmaStorage, priv->dmaStorageDMA ); + if (priv->dma_storage) { + pci_free_consistent(priv->pci_dev, priv->dma_size, + priv->dma_storage, + priv->dma_storage_dma); } - release_region( dev->base_addr, 0x10); - unregister_netdev( dev ); - TLan_Eisa_Devices = priv->nextDevice; - free_netdev( dev ); + release_region(dev->base_addr, 0x10); + unregister_netdev(dev); + tlan_eisa_devices = priv->next_device; + free_netdev(dev); tlan_have_eisa--; } } @@ -715,7 +792,7 @@ static void __exit tlan_exit(void) pci_unregister_driver(&tlan_driver); if (tlan_have_eisa) - TLan_Eisa_Cleanup(); + tlan_eisa_cleanup(); } @@ -726,24 +803,24 @@ module_exit(tlan_exit); - /************************************************************** - * TLan_EisaProbe - * - * Returns: 0 on success, 1 otherwise - * - * Parms: None - * - * - * This functions probes for EISA devices and calls - * TLan_probe1 when one is found. - * - *************************************************************/ +/************************************************************** + * tlan_eisa_probe + * + * Returns: 0 on success, 1 otherwise + * + * Parms: None + * + * + * This functions probes for EISA devices and calls + * TLan_probe1 when one is found. + * + *************************************************************/ -static void __init TLan_EisaProbe (void) +static void __init tlan_eisa_probe(void) { - long ioaddr; - int rc = -ENODEV; - int irq; + long ioaddr; + int rc = -ENODEV; + int irq; u16 device_id; if (!EISA_bus) { @@ -754,15 +831,16 @@ static void __init TLan_EisaProbe (void) /* Loop through all slots of the EISA bus */ for (ioaddr = 0x1000; ioaddr < 0x9000; ioaddr += 0x1000) { - TLAN_DBG(TLAN_DEBUG_PROBE,"EISA_ID 0x%4x: 0x%4x\n", - (int) ioaddr + 0xC80, inw(ioaddr + EISA_ID)); - TLAN_DBG(TLAN_DEBUG_PROBE,"EISA_ID 0x%4x: 0x%4x\n", - (int) ioaddr + 0xC82, inw(ioaddr + EISA_ID2)); + TLAN_DBG(TLAN_DEBUG_PROBE, "EISA_ID 0x%4x: 0x%4x\n", + (int) ioaddr + 0xc80, inw(ioaddr + EISA_ID)); + TLAN_DBG(TLAN_DEBUG_PROBE, "EISA_ID 0x%4x: 0x%4x\n", + (int) ioaddr + 0xc82, inw(ioaddr + EISA_ID2)); - TLAN_DBG(TLAN_DEBUG_PROBE, "Probing for EISA adapter at IO: 0x%4x : ", - (int) ioaddr); - if (request_region(ioaddr, 0x10, TLanSignature) == NULL) + TLAN_DBG(TLAN_DEBUG_PROBE, + "Probing for EISA adapter at IO: 0x%4x : ", + (int) ioaddr); + if (request_region(ioaddr, 0x10, tlan_signature) == NULL) goto out; if (inw(ioaddr + EISA_ID) != 0x110E) { @@ -772,326 +850,326 @@ static void __init TLan_EisaProbe (void) device_id = inw(ioaddr + EISA_ID2); if (device_id != 0x20F1 && device_id != 0x40F1) { - release_region (ioaddr, 0x10); + release_region(ioaddr, 0x10); goto out; } - if (inb(ioaddr + EISA_CR) != 0x1) { /* Check if adapter is enabled */ - release_region (ioaddr, 0x10); + /* check if adapter is enabled */ + if (inb(ioaddr + EISA_CR) != 0x1) { + release_region(ioaddr, 0x10); goto out2; } if (debug == 0x10) - printk("Found one\n"); + printk(KERN_INFO "Found one\n"); /* Get irq from board */ - switch (inb(ioaddr + 0xCC0)) { - case(0x10): - irq=5; - break; - case(0x20): - irq=9; - break; - case(0x40): - irq=10; - break; - case(0x80): - irq=11; - break; - default: - goto out; + switch (inb(ioaddr + 0xcc0)) { + case(0x10): + irq = 5; + break; + case(0x20): + irq = 9; + break; + case(0x40): + irq = 10; + break; + case(0x80): + irq = 11; + break; + default: + goto out; } /* Setup the newly found eisa adapter */ - rc = TLan_probe1( NULL, ioaddr, irq, - 12, NULL); + rc = tlan_probe1(NULL, ioaddr, irq, + 12, NULL); continue; - out: - if (debug == 0x10) - printk("None found\n"); - continue; +out: + if (debug == 0x10) + printk(KERN_INFO "None found\n"); + continue; - out2: if (debug == 0x10) - printk("Card found but it is not enabled, skipping\n"); - continue; +out2: + if (debug == 0x10) + printk(KERN_INFO "Card found but it is not enabled, skipping\n"); + continue; } -} /* TLan_EisaProbe */ +} #ifdef CONFIG_NET_POLL_CONTROLLER -static void TLan_Poll(struct net_device *dev) +static void tlan_poll(struct net_device *dev) { disable_irq(dev->irq); - TLan_HandleInterrupt(dev->irq, dev); + tlan_handle_interrupt(dev->irq, dev); enable_irq(dev->irq); } #endif -static const struct net_device_ops TLan_netdev_ops = { - .ndo_open = TLan_Open, - .ndo_stop = TLan_Close, - .ndo_start_xmit = TLan_StartTx, - .ndo_tx_timeout = TLan_tx_timeout, - .ndo_get_stats = TLan_GetStats, - .ndo_set_multicast_list = TLan_SetMulticastList, - .ndo_do_ioctl = TLan_ioctl, +static const struct net_device_ops tlan_netdev_ops = { + .ndo_open = tlan_open, + .ndo_stop = tlan_close, + .ndo_start_xmit = tlan_start_tx, + .ndo_tx_timeout = tlan_tx_timeout, + .ndo_get_stats = tlan_get_stats, + .ndo_set_multicast_list = tlan_set_multicast_list, + .ndo_do_ioctl = tlan_ioctl, .ndo_change_mtu = eth_change_mtu, - .ndo_set_mac_address = eth_mac_addr, + .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, #ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = TLan_Poll, + .ndo_poll_controller = tlan_poll, #endif }; - /*************************************************************** - * TLan_Init - * - * Returns: - * 0 on success, error code otherwise. - * Parms: - * dev The structure of the device to be - * init'ed. - * - * This function completes the initialization of the - * device structure and driver. It reserves the IO - * addresses, allocates memory for the lists and bounce - * buffers, retrieves the MAC address from the eeprom - * and assignes the device's methods. - * - **************************************************************/ - -static int TLan_Init( struct net_device *dev ) +/*************************************************************** + * tlan_init + * + * Returns: + * 0 on success, error code otherwise. + * Parms: + * dev The structure of the device to be + * init'ed. + * + * This function completes the initialization of the + * device structure and driver. It reserves the IO + * addresses, allocates memory for the lists and bounce + * buffers, retrieves the MAC address from the eeprom + * and assignes the device's methods. + * + **************************************************************/ + +static int tlan_init(struct net_device *dev) { int dma_size; - int err; + int err; int i; - TLanPrivateInfo *priv; + struct tlan_priv *priv; priv = netdev_priv(dev); - dma_size = ( TLAN_NUM_RX_LISTS + TLAN_NUM_TX_LISTS ) - * ( sizeof(TLanList) ); - priv->dmaStorage = pci_alloc_consistent(priv->pciDev, - dma_size, &priv->dmaStorageDMA); - priv->dmaSize = dma_size; - - if ( priv->dmaStorage == NULL ) { - printk(KERN_ERR "TLAN: Could not allocate lists and buffers for %s.\n", - dev->name ); + dma_size = (TLAN_NUM_RX_LISTS + TLAN_NUM_TX_LISTS) + * (sizeof(struct tlan_list)); + priv->dma_storage = pci_alloc_consistent(priv->pci_dev, + dma_size, + &priv->dma_storage_dma); + priv->dma_size = dma_size; + + if (priv->dma_storage == NULL) { + printk(KERN_ERR + "TLAN: Could not allocate lists and buffers for %s.\n", + dev->name); return -ENOMEM; } - memset( priv->dmaStorage, 0, dma_size ); - priv->rxList = (TLanList *) ALIGN((unsigned long)priv->dmaStorage, 8); - priv->rxListDMA = ALIGN(priv->dmaStorageDMA, 8); - priv->txList = priv->rxList + TLAN_NUM_RX_LISTS; - priv->txListDMA = priv->rxListDMA + sizeof(TLanList) * TLAN_NUM_RX_LISTS; + memset(priv->dma_storage, 0, dma_size); + priv->rx_list = (struct tlan_list *) + ALIGN((unsigned long)priv->dma_storage, 8); + priv->rx_list_dma = ALIGN(priv->dma_storage_dma, 8); + priv->tx_list = priv->rx_list + TLAN_NUM_RX_LISTS; + priv->tx_list_dma = + priv->rx_list_dma + sizeof(struct tlan_list)*TLAN_NUM_RX_LISTS; err = 0; - for ( i = 0; i < 6 ; i++ ) - err |= TLan_EeReadByte( dev, - (u8) priv->adapter->addrOfs + i, - (u8 *) &dev->dev_addr[i] ); - if ( err ) { + for (i = 0; i < 6 ; i++) + err |= tlan_ee_read_byte(dev, + (u8) priv->adapter->addr_ofs + i, + (u8 *) &dev->dev_addr[i]); + if (err) { printk(KERN_ERR "TLAN: %s: Error reading MAC from eeprom: %d\n", - dev->name, - err ); + dev->name, + err); } dev->addr_len = 6; netif_carrier_off(dev); /* Device methods */ - dev->netdev_ops = &TLan_netdev_ops; + dev->netdev_ops = &tlan_netdev_ops; dev->watchdog_timeo = TX_TIMEOUT; return 0; -} /* TLan_Init */ +} - /*************************************************************** - * TLan_Open - * - * Returns: - * 0 on success, error code otherwise. - * Parms: - * dev Structure of device to be opened. - * - * This routine puts the driver and TLAN adapter in a - * state where it is ready to send and receive packets. - * It allocates the IRQ, resets and brings the adapter - * out of reset, and allows interrupts. It also delays - * the startup for autonegotiation or sends a Rx GO - * command to the adapter, as appropriate. - * - **************************************************************/ +/*************************************************************** + * tlan_open + * + * Returns: + * 0 on success, error code otherwise. + * Parms: + * dev Structure of device to be opened. + * + * This routine puts the driver and TLAN adapter in a + * state where it is ready to send and receive packets. + * It allocates the IRQ, resets and brings the adapter + * out of reset, and allows interrupts. It also delays + * the startup for autonegotiation or sends a Rx GO + * command to the adapter, as appropriate. + * + **************************************************************/ -static int TLan_Open( struct net_device *dev ) +static int tlan_open(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int err; - priv->tlanRev = TLan_DioRead8( dev->base_addr, TLAN_DEF_REVISION ); - err = request_irq( dev->irq, TLan_HandleInterrupt, IRQF_SHARED, - dev->name, dev ); + priv->tlan_rev = tlan_dio_read8(dev->base_addr, TLAN_DEF_REVISION); + err = request_irq(dev->irq, tlan_handle_interrupt, IRQF_SHARED, + dev->name, dev); - if ( err ) { + if (err) { pr_err("TLAN: Cannot open %s because IRQ %d is already in use.\n", - dev->name, dev->irq ); + dev->name, dev->irq); return err; } init_timer(&priv->timer); - netif_start_queue(dev); - /* NOTE: It might not be necessary to read the stats before a - reset if you don't care what the values are. - */ - TLan_ResetLists( dev ); - TLan_ReadAndClearStats( dev, TLAN_IGNORE ); - TLan_ResetAdapter( dev ); + tlan_start(dev); - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Opened. TLAN Chip Rev: %x\n", - dev->name, priv->tlanRev ); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Opened. TLAN Chip Rev: %x\n", + dev->name, priv->tlan_rev); return 0; -} /* TLan_Open */ +} - /************************************************************** - * TLan_ioctl - * - * Returns: - * 0 on success, error code otherwise - * Params: - * dev structure of device to receive ioctl. - * - * rq ifreq structure to hold userspace data. - * - * cmd ioctl command. - * - * - *************************************************************/ +/************************************************************** + * tlan_ioctl + * + * Returns: + * 0 on success, error code otherwise + * Params: + * dev structure of device to receive ioctl. + * + * rq ifreq structure to hold userspace data. + * + * cmd ioctl command. + * + * + *************************************************************/ -static int TLan_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +static int tlan_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); struct mii_ioctl_data *data = if_mii(rq); - u32 phy = priv->phy[priv->phyNum]; + u32 phy = priv->phy[priv->phy_num]; - if (!priv->phyOnline) + if (!priv->phy_online) return -EAGAIN; - switch(cmd) { - case SIOCGMIIPHY: /* Get address of MII PHY in use. */ - data->phy_id = phy; + switch (cmd) { + case SIOCGMIIPHY: /* get address of MII PHY in use. */ + data->phy_id = phy; - case SIOCGMIIREG: /* Read MII PHY register. */ - TLan_MiiReadReg(dev, data->phy_id & 0x1f, - data->reg_num & 0x1f, &data->val_out); - return 0; + case SIOCGMIIREG: /* read MII PHY register. */ + tlan_mii_read_reg(dev, data->phy_id & 0x1f, + data->reg_num & 0x1f, &data->val_out); + return 0; - case SIOCSMIIREG: /* Write MII PHY register. */ - TLan_MiiWriteReg(dev, data->phy_id & 0x1f, - data->reg_num & 0x1f, data->val_in); - return 0; - default: - return -EOPNOTSUPP; + case SIOCSMIIREG: /* write MII PHY register. */ + tlan_mii_write_reg(dev, data->phy_id & 0x1f, + data->reg_num & 0x1f, data->val_in); + return 0; + default: + return -EOPNOTSUPP; } -} /* tlan_ioctl */ +} - /*************************************************************** - * TLan_tx_timeout - * - * Returns: nothing - * - * Params: - * dev structure of device which timed out - * during transmit. - * - **************************************************************/ +/*************************************************************** + * tlan_tx_timeout + * + * Returns: nothing + * + * Params: + * dev structure of device which timed out + * during transmit. + * + **************************************************************/ -static void TLan_tx_timeout(struct net_device *dev) +static void tlan_tx_timeout(struct net_device *dev) { - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Transmit timed out.\n", dev->name); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Transmit timed out.\n", dev->name); /* Ok so we timed out, lets see what we can do about it...*/ - TLan_FreeLists( dev ); - TLan_ResetLists( dev ); - TLan_ReadAndClearStats( dev, TLAN_IGNORE ); - TLan_ResetAdapter( dev ); + tlan_free_lists(dev); + tlan_reset_lists(dev); + tlan_read_and_clear_stats(dev, TLAN_IGNORE); + tlan_reset_adapter(dev); dev->trans_start = jiffies; /* prevent tx timeout */ - netif_wake_queue( dev ); + netif_wake_queue(dev); } - /*************************************************************** - * TLan_tx_timeout_work - * - * Returns: nothing - * - * Params: - * work work item of device which timed out - * - **************************************************************/ +/*************************************************************** + * tlan_tx_timeout_work + * + * Returns: nothing + * + * Params: + * work work item of device which timed out + * + **************************************************************/ -static void TLan_tx_timeout_work(struct work_struct *work) +static void tlan_tx_timeout_work(struct work_struct *work) { - TLanPrivateInfo *priv = - container_of(work, TLanPrivateInfo, tlan_tqueue); + struct tlan_priv *priv = + container_of(work, struct tlan_priv, tlan_tqueue); - TLan_tx_timeout(priv->dev); + tlan_tx_timeout(priv->dev); } - /*************************************************************** - * TLan_StartTx - * - * Returns: - * 0 on success, non-zero on failure. - * Parms: - * skb A pointer to the sk_buff containing the - * frame to be sent. - * dev The device to send the data on. - * - * This function adds a frame to the Tx list to be sent - * ASAP. First it verifies that the adapter is ready and - * there is room in the queue. Then it sets up the next - * available list, copies the frame to the corresponding - * buffer. If the adapter Tx channel is idle, it gives - * the adapter a Tx Go command on the list, otherwise it - * sets the forward address of the previous list to point - * to this one. Then it frees the sk_buff. - * - **************************************************************/ - -static netdev_tx_t TLan_StartTx( struct sk_buff *skb, struct net_device *dev ) +/*************************************************************** + * tlan_start_tx + * + * Returns: + * 0 on success, non-zero on failure. + * Parms: + * skb A pointer to the sk_buff containing the + * frame to be sent. + * dev The device to send the data on. + * + * This function adds a frame to the Tx list to be sent + * ASAP. First it verifies that the adapter is ready and + * there is room in the queue. Then it sets up the next + * available list, copies the frame to the corresponding + * buffer. If the adapter Tx channel is idle, it gives + * the adapter a Tx Go command on the list, otherwise it + * sets the forward address of the previous list to point + * to this one. Then it frees the sk_buff. + * + **************************************************************/ + +static netdev_tx_t tlan_start_tx(struct sk_buff *skb, struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); dma_addr_t tail_list_phys; - TLanList *tail_list; + struct tlan_list *tail_list; unsigned long flags; unsigned int txlen; - if ( ! priv->phyOnline ) { - TLAN_DBG( TLAN_DEBUG_TX, "TRANSMIT: %s PHY is not ready\n", - dev->name ); + if (!priv->phy_online) { + TLAN_DBG(TLAN_DEBUG_TX, "TRANSMIT: %s PHY is not ready\n", + dev->name); dev_kfree_skb_any(skb); return NETDEV_TX_OK; } @@ -1100,218 +1178,214 @@ static netdev_tx_t TLan_StartTx( struct sk_buff *skb, struct net_device *dev ) return NETDEV_TX_OK; txlen = max(skb->len, (unsigned int)TLAN_MIN_FRAME_SIZE); - tail_list = priv->txList + priv->txTail; - tail_list_phys = priv->txListDMA + sizeof(TLanList) * priv->txTail; + tail_list = priv->tx_list + priv->tx_tail; + tail_list_phys = + priv->tx_list_dma + sizeof(struct tlan_list)*priv->tx_tail; - if ( tail_list->cStat != TLAN_CSTAT_UNUSED ) { - TLAN_DBG( TLAN_DEBUG_TX, - "TRANSMIT: %s is busy (Head=%d Tail=%d)\n", - dev->name, priv->txHead, priv->txTail ); + if (tail_list->c_stat != TLAN_CSTAT_UNUSED) { + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: %s is busy (Head=%d Tail=%d)\n", + dev->name, priv->tx_head, priv->tx_tail); netif_stop_queue(dev); - priv->txBusyCount++; + priv->tx_busy_count++; return NETDEV_TX_BUSY; } tail_list->forward = 0; - tail_list->buffer[0].address = pci_map_single(priv->pciDev, + tail_list->buffer[0].address = pci_map_single(priv->pci_dev, skb->data, txlen, PCI_DMA_TODEVICE); - TLan_StoreSKB(tail_list, skb); + tlan_store_skb(tail_list, skb); - tail_list->frameSize = (u16) txlen; + tail_list->frame_size = (u16) txlen; tail_list->buffer[0].count = TLAN_LAST_BUFFER | (u32) txlen; tail_list->buffer[1].count = 0; tail_list->buffer[1].address = 0; spin_lock_irqsave(&priv->lock, flags); - tail_list->cStat = TLAN_CSTAT_READY; - if ( ! priv->txInProgress ) { - priv->txInProgress = 1; - TLAN_DBG( TLAN_DEBUG_TX, - "TRANSMIT: Starting TX on buffer %d\n", priv->txTail ); - outl( tail_list_phys, dev->base_addr + TLAN_CH_PARM ); - outl( TLAN_HC_GO, dev->base_addr + TLAN_HOST_CMD ); + tail_list->c_stat = TLAN_CSTAT_READY; + if (!priv->tx_in_progress) { + priv->tx_in_progress = 1; + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: Starting TX on buffer %d\n", + priv->tx_tail); + outl(tail_list_phys, dev->base_addr + TLAN_CH_PARM); + outl(TLAN_HC_GO, dev->base_addr + TLAN_HOST_CMD); } else { - TLAN_DBG( TLAN_DEBUG_TX, "TRANSMIT: Adding buffer %d to TX channel\n", - priv->txTail ); - if ( priv->txTail == 0 ) { - ( priv->txList + ( TLAN_NUM_TX_LISTS - 1 ) )->forward + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: Adding buffer %d to TX channel\n", + priv->tx_tail); + if (priv->tx_tail == 0) { + (priv->tx_list + (TLAN_NUM_TX_LISTS - 1))->forward = tail_list_phys; } else { - ( priv->txList + ( priv->txTail - 1 ) )->forward + (priv->tx_list + (priv->tx_tail - 1))->forward = tail_list_phys; } } spin_unlock_irqrestore(&priv->lock, flags); - CIRC_INC( priv->txTail, TLAN_NUM_TX_LISTS ); + CIRC_INC(priv->tx_tail, TLAN_NUM_TX_LISTS); return NETDEV_TX_OK; -} /* TLan_StartTx */ +} - /*************************************************************** - * TLan_HandleInterrupt - * - * Returns: - * Nothing - * Parms: - * irq The line on which the interrupt - * occurred. - * dev_id A pointer to the device assigned to - * this irq line. - * - * This function handles an interrupt generated by its - * assigned TLAN adapter. The function deactivates - * interrupts on its adapter, records the type of - * interrupt, executes the appropriate subhandler, and - * acknowdges the interrupt to the adapter (thus - * re-enabling adapter interrupts. - * - **************************************************************/ +/*************************************************************** + * tlan_handle_interrupt + * + * Returns: + * Nothing + * Parms: + * irq The line on which the interrupt + * occurred. + * dev_id A pointer to the device assigned to + * this irq line. + * + * This function handles an interrupt generated by its + * assigned TLAN adapter. The function deactivates + * interrupts on its adapter, records the type of + * interrupt, executes the appropriate subhandler, and + * acknowdges the interrupt to the adapter (thus + * re-enabling adapter interrupts. + * + **************************************************************/ -static irqreturn_t TLan_HandleInterrupt(int irq, void *dev_id) +static irqreturn_t tlan_handle_interrupt(int irq, void *dev_id) { struct net_device *dev = dev_id; - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 host_int; u16 type; spin_lock(&priv->lock); - host_int = inw( dev->base_addr + TLAN_HOST_INT ); - type = ( host_int & TLAN_HI_IT_MASK ) >> 2; - if ( type ) { + host_int = inw(dev->base_addr + TLAN_HOST_INT); + type = (host_int & TLAN_HI_IT_MASK) >> 2; + if (type) { u32 ack; u32 host_cmd; - outw( host_int, dev->base_addr + TLAN_HOST_INT ); - ack = TLanIntVector[type]( dev, host_int ); + outw(host_int, dev->base_addr + TLAN_HOST_INT); + ack = tlan_int_vector[type](dev, host_int); - if ( ack ) { - host_cmd = TLAN_HC_ACK | ack | ( type << 18 ); - outl( host_cmd, dev->base_addr + TLAN_HOST_CMD ); + if (ack) { + host_cmd = TLAN_HC_ACK | ack | (type << 18); + outl(host_cmd, dev->base_addr + TLAN_HOST_CMD); } } spin_unlock(&priv->lock); return IRQ_RETVAL(type); -} /* TLan_HandleInterrupts */ +} - /*************************************************************** - * TLan_Close - * - * Returns: - * An error code. - * Parms: - * dev The device structure of the device to - * close. - * - * This function shuts down the adapter. It records any - * stats, puts the adapter into reset state, deactivates - * its time as needed, and frees the irq it is using. - * - **************************************************************/ +/*************************************************************** + * tlan_close + * + * Returns: + * An error code. + * Parms: + * dev The device structure of the device to + * close. + * + * This function shuts down the adapter. It records any + * stats, puts the adapter into reset state, deactivates + * its time as needed, and frees the irq it is using. + * + **************************************************************/ -static int TLan_Close(struct net_device *dev) +static int tlan_close(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); - netif_stop_queue(dev); priv->neg_be_verbose = 0; + tlan_stop(dev); - TLan_ReadAndClearStats( dev, TLAN_RECORD ); - outl( TLAN_HC_AD_RST, dev->base_addr + TLAN_HOST_CMD ); - if ( priv->timer.function != NULL ) { - del_timer_sync( &priv->timer ); - priv->timer.function = NULL; - } - - free_irq( dev->irq, dev ); - TLan_FreeLists( dev ); - TLAN_DBG( TLAN_DEBUG_GNRL, "Device %s closed.\n", dev->name ); + free_irq(dev->irq, dev); + tlan_free_lists(dev); + TLAN_DBG(TLAN_DEBUG_GNRL, "Device %s closed.\n", dev->name); return 0; -} /* TLan_Close */ +} - /*************************************************************** - * TLan_GetStats - * - * Returns: - * A pointer to the device's statistics structure. - * Parms: - * dev The device structure to return the - * stats for. - * - * This function updates the devices statistics by reading - * the TLAN chip's onboard registers. Then it returns the - * address of the statistics structure. - * - **************************************************************/ +/*************************************************************** + * tlan_get_stats + * + * Returns: + * A pointer to the device's statistics structure. + * Parms: + * dev The device structure to return the + * stats for. + * + * This function updates the devices statistics by reading + * the TLAN chip's onboard registers. Then it returns the + * address of the statistics structure. + * + **************************************************************/ -static struct net_device_stats *TLan_GetStats( struct net_device *dev ) +static struct net_device_stats *tlan_get_stats(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int i; /* Should only read stats if open ? */ - TLan_ReadAndClearStats( dev, TLAN_RECORD ); + tlan_read_and_clear_stats(dev, TLAN_RECORD); - TLAN_DBG( TLAN_DEBUG_RX, "RECEIVE: %s EOC count = %d\n", dev->name, - priv->rxEocCount ); - TLAN_DBG( TLAN_DEBUG_TX, "TRANSMIT: %s Busy count = %d\n", dev->name, - priv->txBusyCount ); - if ( debug & TLAN_DEBUG_GNRL ) { - TLan_PrintDio( dev->base_addr ); - TLan_PhyPrint( dev ); + TLAN_DBG(TLAN_DEBUG_RX, "RECEIVE: %s EOC count = %d\n", dev->name, + priv->rx_eoc_count); + TLAN_DBG(TLAN_DEBUG_TX, "TRANSMIT: %s Busy count = %d\n", dev->name, + priv->tx_busy_count); + if (debug & TLAN_DEBUG_GNRL) { + tlan_print_dio(dev->base_addr); + tlan_phy_print(dev); } - if ( debug & TLAN_DEBUG_LIST ) { - for ( i = 0; i < TLAN_NUM_RX_LISTS; i++ ) - TLan_PrintList( priv->rxList + i, "RX", i ); - for ( i = 0; i < TLAN_NUM_TX_LISTS; i++ ) - TLan_PrintList( priv->txList + i, "TX", i ); + if (debug & TLAN_DEBUG_LIST) { + for (i = 0; i < TLAN_NUM_RX_LISTS; i++) + tlan_print_list(priv->rx_list + i, "RX", i); + for (i = 0; i < TLAN_NUM_TX_LISTS; i++) + tlan_print_list(priv->tx_list + i, "TX", i); } return &dev->stats; -} /* TLan_GetStats */ +} - /*************************************************************** - * TLan_SetMulticastList - * - * Returns: - * Nothing - * Parms: - * dev The device structure to set the - * multicast list for. - * - * This function sets the TLAN adaptor to various receive - * modes. If the IFF_PROMISC flag is set, promiscuous - * mode is acitviated. Otherwise, promiscuous mode is - * turned off. If the IFF_ALLMULTI flag is set, then - * the hash table is set to receive all group addresses. - * Otherwise, the first three multicast addresses are - * stored in AREG_1-3, and the rest are selected via the - * hash table, as necessary. - * - **************************************************************/ +/*************************************************************** + * tlan_set_multicast_list + * + * Returns: + * Nothing + * Parms: + * dev The device structure to set the + * multicast list for. + * + * This function sets the TLAN adaptor to various receive + * modes. If the IFF_PROMISC flag is set, promiscuous + * mode is acitviated. Otherwise, promiscuous mode is + * turned off. If the IFF_ALLMULTI flag is set, then + * the hash table is set to receive all group addresses. + * Otherwise, the first three multicast addresses are + * stored in AREG_1-3, and the rest are selected via the + * hash table, as necessary. + * + **************************************************************/ -static void TLan_SetMulticastList( struct net_device *dev ) +static void tlan_set_multicast_list(struct net_device *dev) { struct netdev_hw_addr *ha; u32 hash1 = 0; @@ -1320,53 +1394,56 @@ static void TLan_SetMulticastList( struct net_device *dev ) u32 offset; u8 tmp; - if ( dev->flags & IFF_PROMISC ) { - tmp = TLan_DioRead8( dev->base_addr, TLAN_NET_CMD ); - TLan_DioWrite8( dev->base_addr, - TLAN_NET_CMD, tmp | TLAN_NET_CMD_CAF ); + if (dev->flags & IFF_PROMISC) { + tmp = tlan_dio_read8(dev->base_addr, TLAN_NET_CMD); + tlan_dio_write8(dev->base_addr, + TLAN_NET_CMD, tmp | TLAN_NET_CMD_CAF); } else { - tmp = TLan_DioRead8( dev->base_addr, TLAN_NET_CMD ); - TLan_DioWrite8( dev->base_addr, - TLAN_NET_CMD, tmp & ~TLAN_NET_CMD_CAF ); - if ( dev->flags & IFF_ALLMULTI ) { - for ( i = 0; i < 3; i++ ) - TLan_SetMac( dev, i + 1, NULL ); - TLan_DioWrite32( dev->base_addr, TLAN_HASH_1, 0xFFFFFFFF ); - TLan_DioWrite32( dev->base_addr, TLAN_HASH_2, 0xFFFFFFFF ); + tmp = tlan_dio_read8(dev->base_addr, TLAN_NET_CMD); + tlan_dio_write8(dev->base_addr, + TLAN_NET_CMD, tmp & ~TLAN_NET_CMD_CAF); + if (dev->flags & IFF_ALLMULTI) { + for (i = 0; i < 3; i++) + tlan_set_mac(dev, i + 1, NULL); + tlan_dio_write32(dev->base_addr, TLAN_HASH_1, + 0xffffffff); + tlan_dio_write32(dev->base_addr, TLAN_HASH_2, + 0xffffffff); } else { i = 0; netdev_for_each_mc_addr(ha, dev) { - if ( i < 3 ) { - TLan_SetMac( dev, i + 1, + if (i < 3) { + tlan_set_mac(dev, i + 1, (char *) &ha->addr); } else { - offset = TLan_HashFunc((u8 *)&ha->addr); - if ( offset < 32 ) - hash1 |= ( 1 << offset ); + offset = + tlan_hash_func((u8 *)&ha->addr); + if (offset < 32) + hash1 |= (1 << offset); else - hash2 |= ( 1 << ( offset - 32 ) ); + hash2 |= (1 << (offset - 32)); } i++; } - for ( ; i < 3; i++ ) - TLan_SetMac( dev, i + 1, NULL ); - TLan_DioWrite32( dev->base_addr, TLAN_HASH_1, hash1 ); - TLan_DioWrite32( dev->base_addr, TLAN_HASH_2, hash2 ); + for ( ; i < 3; i++) + tlan_set_mac(dev, i + 1, NULL); + tlan_dio_write32(dev->base_addr, TLAN_HASH_1, hash1); + tlan_dio_write32(dev->base_addr, TLAN_HASH_2, hash2); } } -} /* TLan_SetMulticastList */ +} /***************************************************************************** ****************************************************************************** - ThunderLAN Driver Interrupt Vectors and Table +ThunderLAN driver interrupt vectors and table - Please see Chap. 4, "Interrupt Handling" of the "ThunderLAN - Programmer's Guide" for more informations on handling interrupts - generated by TLAN based adapters. +please see chap. 4, "Interrupt Handling" of the "ThunderLAN +Programmer's Guide" for more informations on handling interrupts +generated by TLAN based adapters. ****************************************************************************** *****************************************************************************/ @@ -1374,46 +1451,48 @@ static void TLan_SetMulticastList( struct net_device *dev ) - /*************************************************************** - * TLan_HandleTxEOF - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This function handles Tx EOF interrupts which are raised - * by the adapter when it has completed sending the - * contents of a buffer. If detemines which list/buffer - * was completed and resets it. If the buffer was the last - * in the channel (EOC), then the function checks to see if - * another buffer is ready to send, and if so, sends a Tx - * Go command. Finally, the driver activates/continues the - * activity LED. - * - **************************************************************/ - -static u32 TLan_HandleTxEOF( struct net_device *dev, u16 host_int ) +/*************************************************************** + * tlan_handle_tx_eof + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This function handles Tx EOF interrupts which are raised + * by the adapter when it has completed sending the + * contents of a buffer. If detemines which list/buffer + * was completed and resets it. If the buffer was the last + * in the channel (EOC), then the function checks to see if + * another buffer is ready to send, and if so, sends a Tx + * Go command. Finally, the driver activates/continues the + * activity LED. + * + **************************************************************/ + +static u32 tlan_handle_tx_eof(struct net_device *dev, u16 host_int) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int eoc = 0; - TLanList *head_list; + struct tlan_list *head_list; dma_addr_t head_list_phys; u32 ack = 0; - u16 tmpCStat; + u16 tmp_c_stat; - TLAN_DBG( TLAN_DEBUG_TX, "TRANSMIT: Handling TX EOF (Head=%d Tail=%d)\n", - priv->txHead, priv->txTail ); - head_list = priv->txList + priv->txHead; + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: Handling TX EOF (Head=%d Tail=%d)\n", + priv->tx_head, priv->tx_tail); + head_list = priv->tx_list + priv->tx_head; - while (((tmpCStat = head_list->cStat ) & TLAN_CSTAT_FRM_CMP) && (ack < 255)) { - struct sk_buff *skb = TLan_GetSKB(head_list); + while (((tmp_c_stat = head_list->c_stat) & TLAN_CSTAT_FRM_CMP) + && (ack < 255)) { + struct sk_buff *skb = tlan_get_skb(head_list); ack++; - pci_unmap_single(priv->pciDev, head_list->buffer[0].address, + pci_unmap_single(priv->pci_dev, head_list->buffer[0].address, max(skb->len, (unsigned int)TLAN_MIN_FRAME_SIZE), PCI_DMA_TODEVICE); @@ -1421,304 +1500,311 @@ static u32 TLan_HandleTxEOF( struct net_device *dev, u16 host_int ) head_list->buffer[8].address = 0; head_list->buffer[9].address = 0; - if ( tmpCStat & TLAN_CSTAT_EOC ) + if (tmp_c_stat & TLAN_CSTAT_EOC) eoc = 1; - dev->stats.tx_bytes += head_list->frameSize; + dev->stats.tx_bytes += head_list->frame_size; - head_list->cStat = TLAN_CSTAT_UNUSED; + head_list->c_stat = TLAN_CSTAT_UNUSED; netif_start_queue(dev); - CIRC_INC( priv->txHead, TLAN_NUM_TX_LISTS ); - head_list = priv->txList + priv->txHead; + CIRC_INC(priv->tx_head, TLAN_NUM_TX_LISTS); + head_list = priv->tx_list + priv->tx_head; } if (!ack) - printk(KERN_INFO "TLAN: Received interrupt for uncompleted TX frame.\n"); - - if ( eoc ) { - TLAN_DBG( TLAN_DEBUG_TX, - "TRANSMIT: Handling TX EOC (Head=%d Tail=%d)\n", - priv->txHead, priv->txTail ); - head_list = priv->txList + priv->txHead; - head_list_phys = priv->txListDMA + sizeof(TLanList) * priv->txHead; - if ( ( head_list->cStat & TLAN_CSTAT_READY ) == TLAN_CSTAT_READY ) { - outl(head_list_phys, dev->base_addr + TLAN_CH_PARM ); + printk(KERN_INFO + "TLAN: Received interrupt for uncompleted TX frame.\n"); + + if (eoc) { + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: handling TX EOC (Head=%d Tail=%d)\n", + priv->tx_head, priv->tx_tail); + head_list = priv->tx_list + priv->tx_head; + head_list_phys = priv->tx_list_dma + + sizeof(struct tlan_list)*priv->tx_head; + if (head_list->c_stat & TLAN_CSTAT_READY) { + outl(head_list_phys, dev->base_addr + TLAN_CH_PARM); ack |= TLAN_HC_GO; } else { - priv->txInProgress = 0; + priv->tx_in_progress = 0; } } - if ( priv->adapter->flags & TLAN_ADAPTER_ACTIVITY_LED ) { - TLan_DioWrite8( dev->base_addr, - TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT ); - if ( priv->timer.function == NULL ) { - priv->timer.function = TLan_Timer; - priv->timer.data = (unsigned long) dev; - priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY; - priv->timerSetAt = jiffies; - priv->timerType = TLAN_TIMER_ACTIVITY; - add_timer(&priv->timer); - } else if ( priv->timerType == TLAN_TIMER_ACTIVITY ) { - priv->timerSetAt = jiffies; + if (priv->adapter->flags & TLAN_ADAPTER_ACTIVITY_LED) { + tlan_dio_write8(dev->base_addr, + TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT); + if (priv->timer.function == NULL) { + priv->timer.function = tlan_timer; + priv->timer.data = (unsigned long) dev; + priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY; + priv->timer_set_at = jiffies; + priv->timer_type = TLAN_TIMER_ACTIVITY; + add_timer(&priv->timer); + } else if (priv->timer_type == TLAN_TIMER_ACTIVITY) { + priv->timer_set_at = jiffies; } } return ack; -} /* TLan_HandleTxEOF */ +} - /*************************************************************** - * TLan_HandleStatOverflow - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This function handles the Statistics Overflow interrupt - * which means that one or more of the TLAN statistics - * registers has reached 1/2 capacity and needs to be read. - * - **************************************************************/ +/*************************************************************** + * TLan_HandleStatOverflow + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This function handles the Statistics Overflow interrupt + * which means that one or more of the TLAN statistics + * registers has reached 1/2 capacity and needs to be read. + * + **************************************************************/ -static u32 TLan_HandleStatOverflow( struct net_device *dev, u16 host_int ) +static u32 tlan_handle_stat_overflow(struct net_device *dev, u16 host_int) { - TLan_ReadAndClearStats( dev, TLAN_RECORD ); + tlan_read_and_clear_stats(dev, TLAN_RECORD); return 1; -} /* TLan_HandleStatOverflow */ - - - - - /*************************************************************** - * TLan_HandleRxEOF - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This function handles the Rx EOF interrupt which - * indicates a frame has been received by the adapter from - * the net and the frame has been transferred to memory. - * The function determines the bounce buffer the frame has - * been loaded into, creates a new sk_buff big enough to - * hold the frame, and sends it to protocol stack. It - * then resets the used buffer and appends it to the end - * of the list. If the frame was the last in the Rx - * channel (EOC), the function restarts the receive channel - * by sending an Rx Go command to the adapter. Then it - * activates/continues the activity LED. - * - **************************************************************/ - -static u32 TLan_HandleRxEOF( struct net_device *dev, u16 host_int ) +} + + + + +/*************************************************************** + * TLan_HandleRxEOF + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This function handles the Rx EOF interrupt which + * indicates a frame has been received by the adapter from + * the net and the frame has been transferred to memory. + * The function determines the bounce buffer the frame has + * been loaded into, creates a new sk_buff big enough to + * hold the frame, and sends it to protocol stack. It + * then resets the used buffer and appends it to the end + * of the list. If the frame was the last in the Rx + * channel (EOC), the function restarts the receive channel + * by sending an Rx Go command to the adapter. Then it + * activates/continues the activity LED. + * + **************************************************************/ + +static u32 tlan_handle_rx_eof(struct net_device *dev, u16 host_int) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u32 ack = 0; int eoc = 0; - TLanList *head_list; + struct tlan_list *head_list; struct sk_buff *skb; - TLanList *tail_list; - u16 tmpCStat; + struct tlan_list *tail_list; + u16 tmp_c_stat; dma_addr_t head_list_phys; - TLAN_DBG( TLAN_DEBUG_RX, "RECEIVE: Handling RX EOF (Head=%d Tail=%d)\n", - priv->rxHead, priv->rxTail ); - head_list = priv->rxList + priv->rxHead; - head_list_phys = priv->rxListDMA + sizeof(TLanList) * priv->rxHead; + TLAN_DBG(TLAN_DEBUG_RX, "RECEIVE: handling RX EOF (Head=%d Tail=%d)\n", + priv->rx_head, priv->rx_tail); + head_list = priv->rx_list + priv->rx_head; + head_list_phys = + priv->rx_list_dma + sizeof(struct tlan_list)*priv->rx_head; - while (((tmpCStat = head_list->cStat) & TLAN_CSTAT_FRM_CMP) && (ack < 255)) { - dma_addr_t frameDma = head_list->buffer[0].address; - u32 frameSize = head_list->frameSize; + while (((tmp_c_stat = head_list->c_stat) & TLAN_CSTAT_FRM_CMP) + && (ack < 255)) { + dma_addr_t frame_dma = head_list->buffer[0].address; + u32 frame_size = head_list->frame_size; struct sk_buff *new_skb; ack++; - if (tmpCStat & TLAN_CSTAT_EOC) + if (tmp_c_stat & TLAN_CSTAT_EOC) eoc = 1; new_skb = netdev_alloc_skb_ip_align(dev, TLAN_MAX_FRAME_SIZE + 5); - if ( !new_skb ) + if (!new_skb) goto drop_and_reuse; - skb = TLan_GetSKB(head_list); - pci_unmap_single(priv->pciDev, frameDma, + skb = tlan_get_skb(head_list); + pci_unmap_single(priv->pci_dev, frame_dma, TLAN_MAX_FRAME_SIZE, PCI_DMA_FROMDEVICE); - skb_put( skb, frameSize ); + skb_put(skb, frame_size); - dev->stats.rx_bytes += frameSize; + dev->stats.rx_bytes += frame_size; - skb->protocol = eth_type_trans( skb, dev ); - netif_rx( skb ); + skb->protocol = eth_type_trans(skb, dev); + netif_rx(skb); - head_list->buffer[0].address = pci_map_single(priv->pciDev, - new_skb->data, - TLAN_MAX_FRAME_SIZE, - PCI_DMA_FROMDEVICE); + head_list->buffer[0].address = + pci_map_single(priv->pci_dev, new_skb->data, + TLAN_MAX_FRAME_SIZE, PCI_DMA_FROMDEVICE); - TLan_StoreSKB(head_list, new_skb); + tlan_store_skb(head_list, new_skb); drop_and_reuse: head_list->forward = 0; - head_list->cStat = 0; - tail_list = priv->rxList + priv->rxTail; + head_list->c_stat = 0; + tail_list = priv->rx_list + priv->rx_tail; tail_list->forward = head_list_phys; - CIRC_INC( priv->rxHead, TLAN_NUM_RX_LISTS ); - CIRC_INC( priv->rxTail, TLAN_NUM_RX_LISTS ); - head_list = priv->rxList + priv->rxHead; - head_list_phys = priv->rxListDMA + sizeof(TLanList) * priv->rxHead; + CIRC_INC(priv->rx_head, TLAN_NUM_RX_LISTS); + CIRC_INC(priv->rx_tail, TLAN_NUM_RX_LISTS); + head_list = priv->rx_list + priv->rx_head; + head_list_phys = priv->rx_list_dma + + sizeof(struct tlan_list)*priv->rx_head; } if (!ack) - printk(KERN_INFO "TLAN: Received interrupt for uncompleted RX frame.\n"); - - - if ( eoc ) { - TLAN_DBG( TLAN_DEBUG_RX, - "RECEIVE: Handling RX EOC (Head=%d Tail=%d)\n", - priv->rxHead, priv->rxTail ); - head_list = priv->rxList + priv->rxHead; - head_list_phys = priv->rxListDMA + sizeof(TLanList) * priv->rxHead; - outl(head_list_phys, dev->base_addr + TLAN_CH_PARM ); + printk(KERN_INFO + "TLAN: Received interrupt for uncompleted RX frame.\n"); + + + if (eoc) { + TLAN_DBG(TLAN_DEBUG_RX, + "RECEIVE: handling RX EOC (Head=%d Tail=%d)\n", + priv->rx_head, priv->rx_tail); + head_list = priv->rx_list + priv->rx_head; + head_list_phys = priv->rx_list_dma + + sizeof(struct tlan_list)*priv->rx_head; + outl(head_list_phys, dev->base_addr + TLAN_CH_PARM); ack |= TLAN_HC_GO | TLAN_HC_RT; - priv->rxEocCount++; + priv->rx_eoc_count++; } - if ( priv->adapter->flags & TLAN_ADAPTER_ACTIVITY_LED ) { - TLan_DioWrite8( dev->base_addr, - TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT ); - if ( priv->timer.function == NULL ) { - priv->timer.function = TLan_Timer; + if (priv->adapter->flags & TLAN_ADAPTER_ACTIVITY_LED) { + tlan_dio_write8(dev->base_addr, + TLAN_LED_REG, TLAN_LED_LINK | TLAN_LED_ACT); + if (priv->timer.function == NULL) { + priv->timer.function = tlan_timer; priv->timer.data = (unsigned long) dev; priv->timer.expires = jiffies + TLAN_TIMER_ACT_DELAY; - priv->timerSetAt = jiffies; - priv->timerType = TLAN_TIMER_ACTIVITY; + priv->timer_set_at = jiffies; + priv->timer_type = TLAN_TIMER_ACTIVITY; add_timer(&priv->timer); - } else if ( priv->timerType == TLAN_TIMER_ACTIVITY ) { - priv->timerSetAt = jiffies; + } else if (priv->timer_type == TLAN_TIMER_ACTIVITY) { + priv->timer_set_at = jiffies; } } return ack; -} /* TLan_HandleRxEOF */ +} - /*************************************************************** - * TLan_HandleDummy - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This function handles the Dummy interrupt, which is - * raised whenever a test interrupt is generated by setting - * the Req_Int bit of HOST_CMD to 1. - * - **************************************************************/ +/*************************************************************** + * tlan_handle_dummy + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This function handles the Dummy interrupt, which is + * raised whenever a test interrupt is generated by setting + * the Req_Int bit of HOST_CMD to 1. + * + **************************************************************/ -static u32 TLan_HandleDummy( struct net_device *dev, u16 host_int ) +static u32 tlan_handle_dummy(struct net_device *dev, u16 host_int) { - printk( "TLAN: Test interrupt on %s.\n", dev->name ); + pr_info("TLAN: Test interrupt on %s.\n", dev->name); return 1; -} /* TLan_HandleDummy */ +} - /*************************************************************** - * TLan_HandleTxEOC - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This driver is structured to determine EOC occurrences by - * reading the CSTAT member of the list structure. Tx EOC - * interrupts are disabled via the DIO INTDIS register. - * However, TLAN chips before revision 3.0 didn't have this - * functionality, so process EOC events if this is the - * case. - * - **************************************************************/ +/*************************************************************** + * tlan_handle_tx_eoc + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This driver is structured to determine EOC occurrences by + * reading the CSTAT member of the list structure. Tx EOC + * interrupts are disabled via the DIO INTDIS register. + * However, TLAN chips before revision 3.0 didn't have this + * functionality, so process EOC events if this is the + * case. + * + **************************************************************/ -static u32 TLan_HandleTxEOC( struct net_device *dev, u16 host_int ) +static u32 tlan_handle_tx_eoc(struct net_device *dev, u16 host_int) { - TLanPrivateInfo *priv = netdev_priv(dev); - TLanList *head_list; + struct tlan_priv *priv = netdev_priv(dev); + struct tlan_list *head_list; dma_addr_t head_list_phys; u32 ack = 1; host_int = 0; - if ( priv->tlanRev < 0x30 ) { - TLAN_DBG( TLAN_DEBUG_TX, - "TRANSMIT: Handling TX EOC (Head=%d Tail=%d) -- IRQ\n", - priv->txHead, priv->txTail ); - head_list = priv->txList + priv->txHead; - head_list_phys = priv->txListDMA + sizeof(TLanList) * priv->txHead; - if ( ( head_list->cStat & TLAN_CSTAT_READY ) == TLAN_CSTAT_READY ) { + if (priv->tlan_rev < 0x30) { + TLAN_DBG(TLAN_DEBUG_TX, + "TRANSMIT: handling TX EOC (Head=%d Tail=%d) -- IRQ\n", + priv->tx_head, priv->tx_tail); + head_list = priv->tx_list + priv->tx_head; + head_list_phys = priv->tx_list_dma + + sizeof(struct tlan_list)*priv->tx_head; + if (head_list->c_stat & TLAN_CSTAT_READY) { netif_stop_queue(dev); - outl( head_list_phys, dev->base_addr + TLAN_CH_PARM ); + outl(head_list_phys, dev->base_addr + TLAN_CH_PARM); ack |= TLAN_HC_GO; } else { - priv->txInProgress = 0; + priv->tx_in_progress = 0; } } return ack; -} /* TLan_HandleTxEOC */ +} - /*************************************************************** - * TLan_HandleStatusCheck - * - * Returns: - * 0 if Adapter check, 1 if Network Status check. - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This function handles Adapter Check/Network Status - * interrupts generated by the adapter. It checks the - * vector in the HOST_INT register to determine if it is - * an Adapter Check interrupt. If so, it resets the - * adapter. Otherwise it clears the status registers - * and services the PHY. - * - **************************************************************/ +/*************************************************************** + * tlan_handle_status_check + * + * Returns: + * 0 if Adapter check, 1 if Network Status check. + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This function handles Adapter Check/Network Status + * interrupts generated by the adapter. It checks the + * vector in the HOST_INT register to determine if it is + * an Adapter Check interrupt. If so, it resets the + * adapter. Otherwise it clears the status registers + * and services the PHY. + * + **************************************************************/ -static u32 TLan_HandleStatusCheck( struct net_device *dev, u16 host_int ) +static u32 tlan_handle_status_check(struct net_device *dev, u16 host_int) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u32 ack; u32 error; u8 net_sts; @@ -1727,92 +1813,94 @@ static u32 TLan_HandleStatusCheck( struct net_device *dev, u16 host_int ) u16 tlphy_sts; ack = 1; - if ( host_int & TLAN_HI_IV_MASK ) { - netif_stop_queue( dev ); - error = inl( dev->base_addr + TLAN_CH_PARM ); - printk( "TLAN: %s: Adaptor Error = 0x%x\n", dev->name, error ); - TLan_ReadAndClearStats( dev, TLAN_RECORD ); - outl( TLAN_HC_AD_RST, dev->base_addr + TLAN_HOST_CMD ); + if (host_int & TLAN_HI_IV_MASK) { + netif_stop_queue(dev); + error = inl(dev->base_addr + TLAN_CH_PARM); + pr_info("TLAN: %s: Adaptor Error = 0x%x\n", dev->name, error); + tlan_read_and_clear_stats(dev, TLAN_RECORD); + outl(TLAN_HC_AD_RST, dev->base_addr + TLAN_HOST_CMD); schedule_work(&priv->tlan_tqueue); netif_wake_queue(dev); ack = 0; } else { - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Status Check\n", dev->name ); - phy = priv->phy[priv->phyNum]; - - net_sts = TLan_DioRead8( dev->base_addr, TLAN_NET_STS ); - if ( net_sts ) { - TLan_DioWrite8( dev->base_addr, TLAN_NET_STS, net_sts ); - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Net_Sts = %x\n", - dev->name, (unsigned) net_sts ); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Status Check\n", dev->name); + phy = priv->phy[priv->phy_num]; + + net_sts = tlan_dio_read8(dev->base_addr, TLAN_NET_STS); + if (net_sts) { + tlan_dio_write8(dev->base_addr, TLAN_NET_STS, net_sts); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Net_Sts = %x\n", + dev->name, (unsigned) net_sts); } - if ( ( net_sts & TLAN_NET_STS_MIRQ ) && ( priv->phyNum == 0 ) ) { - TLan_MiiReadReg( dev, phy, TLAN_TLPHY_STS, &tlphy_sts ); - TLan_MiiReadReg( dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl ); - if ( ! ( tlphy_sts & TLAN_TS_POLOK ) && - ! ( tlphy_ctl & TLAN_TC_SWAPOL ) ) { - tlphy_ctl |= TLAN_TC_SWAPOL; - TLan_MiiWriteReg( dev, phy, TLAN_TLPHY_CTL, tlphy_ctl); - } else if ( ( tlphy_sts & TLAN_TS_POLOK ) && - ( tlphy_ctl & TLAN_TC_SWAPOL ) ) { - tlphy_ctl &= ~TLAN_TC_SWAPOL; - TLan_MiiWriteReg( dev, phy, TLAN_TLPHY_CTL, tlphy_ctl); - } - - if (debug) { - TLan_PhyPrint( dev ); + if ((net_sts & TLAN_NET_STS_MIRQ) && (priv->phy_num == 0)) { + tlan_mii_read_reg(dev, phy, TLAN_TLPHY_STS, &tlphy_sts); + tlan_mii_read_reg(dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl); + if (!(tlphy_sts & TLAN_TS_POLOK) && + !(tlphy_ctl & TLAN_TC_SWAPOL)) { + tlphy_ctl |= TLAN_TC_SWAPOL; + tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, + tlphy_ctl); + } else if ((tlphy_sts & TLAN_TS_POLOK) && + (tlphy_ctl & TLAN_TC_SWAPOL)) { + tlphy_ctl &= ~TLAN_TC_SWAPOL; + tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, + tlphy_ctl); } + + if (debug) + tlan_phy_print(dev); } } return ack; -} /* TLan_HandleStatusCheck */ +} - /*************************************************************** - * TLan_HandleRxEOC - * - * Returns: - * 1 - * Parms: - * dev Device assigned the IRQ that was - * raised. - * host_int The contents of the HOST_INT - * port. - * - * This driver is structured to determine EOC occurrences by - * reading the CSTAT member of the list structure. Rx EOC - * interrupts are disabled via the DIO INTDIS register. - * However, TLAN chips before revision 3.0 didn't have this - * CSTAT member or a INTDIS register, so if this chip is - * pre-3.0, process EOC interrupts normally. - * - **************************************************************/ +/*************************************************************** + * tlan_handle_rx_eoc + * + * Returns: + * 1 + * Parms: + * dev Device assigned the IRQ that was + * raised. + * host_int The contents of the HOST_INT + * port. + * + * This driver is structured to determine EOC occurrences by + * reading the CSTAT member of the list structure. Rx EOC + * interrupts are disabled via the DIO INTDIS register. + * However, TLAN chips before revision 3.0 didn't have this + * CSTAT member or a INTDIS register, so if this chip is + * pre-3.0, process EOC interrupts normally. + * + **************************************************************/ -static u32 TLan_HandleRxEOC( struct net_device *dev, u16 host_int ) +static u32 tlan_handle_rx_eoc(struct net_device *dev, u16 host_int) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); dma_addr_t head_list_phys; u32 ack = 1; - if ( priv->tlanRev < 0x30 ) { - TLAN_DBG( TLAN_DEBUG_RX, - "RECEIVE: Handling RX EOC (Head=%d Tail=%d) -- IRQ\n", - priv->rxHead, priv->rxTail ); - head_list_phys = priv->rxListDMA + sizeof(TLanList) * priv->rxHead; - outl( head_list_phys, dev->base_addr + TLAN_CH_PARM ); + if (priv->tlan_rev < 0x30) { + TLAN_DBG(TLAN_DEBUG_RX, + "RECEIVE: Handling RX EOC (head=%d tail=%d) -- IRQ\n", + priv->rx_head, priv->rx_tail); + head_list_phys = priv->rx_list_dma + + sizeof(struct tlan_list)*priv->rx_head; + outl(head_list_phys, dev->base_addr + TLAN_CH_PARM); ack |= TLAN_HC_GO | TLAN_HC_RT; - priv->rxEocCount++; + priv->rx_eoc_count++; } return ack; -} /* TLan_HandleRxEOC */ +} @@ -1820,98 +1908,98 @@ static u32 TLan_HandleRxEOC( struct net_device *dev, u16 host_int ) /***************************************************************************** ****************************************************************************** - ThunderLAN Driver Timer Function +ThunderLAN driver timer function ****************************************************************************** *****************************************************************************/ - /*************************************************************** - * TLan_Timer - * - * Returns: - * Nothing - * Parms: - * data A value given to add timer when - * add_timer was called. - * - * This function handles timed functionality for the - * TLAN driver. The two current timer uses are for - * delaying for autonegotionation and driving the ACT LED. - * - Autonegotiation requires being allowed about - * 2 1/2 seconds before attempting to transmit a - * packet. It would be a very bad thing to hang - * the kernel this long, so the driver doesn't - * allow transmission 'til after this time, for - * certain PHYs. It would be much nicer if all - * PHYs were interrupt-capable like the internal - * PHY. - * - The ACT LED, which shows adapter activity, is - * driven by the driver, and so must be left on - * for a short period to power up the LED so it - * can be seen. This delay can be changed by - * changing the TLAN_TIMER_ACT_DELAY in tlan.h, - * if desired. 100 ms produces a slightly - * sluggish response. - * - **************************************************************/ - -static void TLan_Timer( unsigned long data ) +/*************************************************************** + * tlan_timer + * + * Returns: + * Nothing + * Parms: + * data A value given to add timer when + * add_timer was called. + * + * This function handles timed functionality for the + * TLAN driver. The two current timer uses are for + * delaying for autonegotionation and driving the ACT LED. + * - Autonegotiation requires being allowed about + * 2 1/2 seconds before attempting to transmit a + * packet. It would be a very bad thing to hang + * the kernel this long, so the driver doesn't + * allow transmission 'til after this time, for + * certain PHYs. It would be much nicer if all + * PHYs were interrupt-capable like the internal + * PHY. + * - The ACT LED, which shows adapter activity, is + * driven by the driver, and so must be left on + * for a short period to power up the LED so it + * can be seen. This delay can be changed by + * changing the TLAN_TIMER_ACT_DELAY in tlan.h, + * if desired. 100 ms produces a slightly + * sluggish response. + * + **************************************************************/ + +static void tlan_timer(unsigned long data) { struct net_device *dev = (struct net_device *) data; - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u32 elapsed; unsigned long flags = 0; priv->timer.function = NULL; - switch ( priv->timerType ) { + switch (priv->timer_type) { #ifdef MONITOR - case TLAN_TIMER_LINK_BEAT: - TLan_PhyMonitor( dev ); - break; + case TLAN_TIMER_LINK_BEAT: + tlan_phy_monitor(dev); + break; #endif - case TLAN_TIMER_PHY_PDOWN: - TLan_PhyPowerDown( dev ); - break; - case TLAN_TIMER_PHY_PUP: - TLan_PhyPowerUp( dev ); - break; - case TLAN_TIMER_PHY_RESET: - TLan_PhyReset( dev ); - break; - case TLAN_TIMER_PHY_START_LINK: - TLan_PhyStartLink( dev ); - break; - case TLAN_TIMER_PHY_FINISH_AN: - TLan_PhyFinishAutoNeg( dev ); - break; - case TLAN_TIMER_FINISH_RESET: - TLan_FinishReset( dev ); - break; - case TLAN_TIMER_ACTIVITY: - spin_lock_irqsave(&priv->lock, flags); - if ( priv->timer.function == NULL ) { - elapsed = jiffies - priv->timerSetAt; - if ( elapsed >= TLAN_TIMER_ACT_DELAY ) { - TLan_DioWrite8( dev->base_addr, - TLAN_LED_REG, TLAN_LED_LINK ); - } else { - priv->timer.function = TLan_Timer; - priv->timer.expires = priv->timerSetAt - + TLAN_TIMER_ACT_DELAY; - spin_unlock_irqrestore(&priv->lock, flags); - add_timer( &priv->timer ); - break; - } + case TLAN_TIMER_PHY_PDOWN: + tlan_phy_power_down(dev); + break; + case TLAN_TIMER_PHY_PUP: + tlan_phy_power_up(dev); + break; + case TLAN_TIMER_PHY_RESET: + tlan_phy_reset(dev); + break; + case TLAN_TIMER_PHY_START_LINK: + tlan_phy_start_link(dev); + break; + case TLAN_TIMER_PHY_FINISH_AN: + tlan_phy_finish_auto_neg(dev); + break; + case TLAN_TIMER_FINISH_RESET: + tlan_finish_reset(dev); + break; + case TLAN_TIMER_ACTIVITY: + spin_lock_irqsave(&priv->lock, flags); + if (priv->timer.function == NULL) { + elapsed = jiffies - priv->timer_set_at; + if (elapsed >= TLAN_TIMER_ACT_DELAY) { + tlan_dio_write8(dev->base_addr, + TLAN_LED_REG, TLAN_LED_LINK); + } else { + priv->timer.function = tlan_timer; + priv->timer.expires = priv->timer_set_at + + TLAN_TIMER_ACT_DELAY; + spin_unlock_irqrestore(&priv->lock, flags); + add_timer(&priv->timer); + break; } - spin_unlock_irqrestore(&priv->lock, flags); - break; - default: - break; + } + spin_unlock_irqrestore(&priv->lock, flags); + break; + default: + break; } -} /* TLan_Timer */ +} @@ -1919,39 +2007,39 @@ static void TLan_Timer( unsigned long data ) /***************************************************************************** ****************************************************************************** - ThunderLAN Driver Adapter Related Routines +ThunderLAN driver adapter related routines ****************************************************************************** *****************************************************************************/ - /*************************************************************** - * TLan_ResetLists - * - * Returns: - * Nothing - * Parms: - * dev The device structure with the list - * stuctures to be reset. - * - * This routine sets the variables associated with managing - * the TLAN lists to their initial values. - * - **************************************************************/ - -static void TLan_ResetLists( struct net_device *dev ) +/*************************************************************** + * tlan_reset_lists + * + * Returns: + * Nothing + * Parms: + * dev The device structure with the list + * stuctures to be reset. + * + * This routine sets the variables associated with managing + * the TLAN lists to their initial values. + * + **************************************************************/ + +static void tlan_reset_lists(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int i; - TLanList *list; + struct tlan_list *list; dma_addr_t list_phys; struct sk_buff *skb; - priv->txHead = 0; - priv->txTail = 0; - for ( i = 0; i < TLAN_NUM_TX_LISTS; i++ ) { - list = priv->txList + i; - list->cStat = TLAN_CSTAT_UNUSED; + priv->tx_head = 0; + priv->tx_tail = 0; + for (i = 0; i < TLAN_NUM_TX_LISTS; i++) { + list = priv->tx_list + i; + list->c_stat = TLAN_CSTAT_UNUSED; list->buffer[0].address = 0; list->buffer[2].count = 0; list->buffer[2].address = 0; @@ -1959,169 +2047,169 @@ static void TLan_ResetLists( struct net_device *dev ) list->buffer[9].address = 0; } - priv->rxHead = 0; - priv->rxTail = TLAN_NUM_RX_LISTS - 1; - for ( i = 0; i < TLAN_NUM_RX_LISTS; i++ ) { - list = priv->rxList + i; - list_phys = priv->rxListDMA + sizeof(TLanList) * i; - list->cStat = TLAN_CSTAT_READY; - list->frameSize = TLAN_MAX_FRAME_SIZE; + priv->rx_head = 0; + priv->rx_tail = TLAN_NUM_RX_LISTS - 1; + for (i = 0; i < TLAN_NUM_RX_LISTS; i++) { + list = priv->rx_list + i; + list_phys = priv->rx_list_dma + sizeof(struct tlan_list)*i; + list->c_stat = TLAN_CSTAT_READY; + list->frame_size = TLAN_MAX_FRAME_SIZE; list->buffer[0].count = TLAN_MAX_FRAME_SIZE | TLAN_LAST_BUFFER; skb = netdev_alloc_skb_ip_align(dev, TLAN_MAX_FRAME_SIZE + 5); - if ( !skb ) { - pr_err("TLAN: out of memory for received data.\n" ); + if (!skb) { + pr_err("TLAN: out of memory for received data.\n"); break; } - list->buffer[0].address = pci_map_single(priv->pciDev, + list->buffer[0].address = pci_map_single(priv->pci_dev, skb->data, TLAN_MAX_FRAME_SIZE, PCI_DMA_FROMDEVICE); - TLan_StoreSKB(list, skb); + tlan_store_skb(list, skb); list->buffer[1].count = 0; list->buffer[1].address = 0; - list->forward = list_phys + sizeof(TLanList); + list->forward = list_phys + sizeof(struct tlan_list); } /* in case ran out of memory early, clear bits */ while (i < TLAN_NUM_RX_LISTS) { - TLan_StoreSKB(priv->rxList + i, NULL); + tlan_store_skb(priv->rx_list + i, NULL); ++i; } list->forward = 0; -} /* TLan_ResetLists */ +} -static void TLan_FreeLists( struct net_device *dev ) +static void tlan_free_lists(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int i; - TLanList *list; + struct tlan_list *list; struct sk_buff *skb; - for ( i = 0; i < TLAN_NUM_TX_LISTS; i++ ) { - list = priv->txList + i; - skb = TLan_GetSKB(list); - if ( skb ) { + for (i = 0; i < TLAN_NUM_TX_LISTS; i++) { + list = priv->tx_list + i; + skb = tlan_get_skb(list); + if (skb) { pci_unmap_single( - priv->pciDev, + priv->pci_dev, list->buffer[0].address, max(skb->len, (unsigned int)TLAN_MIN_FRAME_SIZE), PCI_DMA_TODEVICE); - dev_kfree_skb_any( skb ); + dev_kfree_skb_any(skb); list->buffer[8].address = 0; list->buffer[9].address = 0; } } - for ( i = 0; i < TLAN_NUM_RX_LISTS; i++ ) { - list = priv->rxList + i; - skb = TLan_GetSKB(list); - if ( skb ) { - pci_unmap_single(priv->pciDev, + for (i = 0; i < TLAN_NUM_RX_LISTS; i++) { + list = priv->rx_list + i; + skb = tlan_get_skb(list); + if (skb) { + pci_unmap_single(priv->pci_dev, list->buffer[0].address, TLAN_MAX_FRAME_SIZE, PCI_DMA_FROMDEVICE); - dev_kfree_skb_any( skb ); + dev_kfree_skb_any(skb); list->buffer[8].address = 0; list->buffer[9].address = 0; } } -} /* TLan_FreeLists */ +} - /*************************************************************** - * TLan_PrintDio - * - * Returns: - * Nothing - * Parms: - * io_base Base IO port of the device of - * which to print DIO registers. - * - * This function prints out all the internal (DIO) - * registers of a TLAN chip. - * - **************************************************************/ +/*************************************************************** + * tlan_print_dio + * + * Returns: + * Nothing + * Parms: + * io_base Base IO port of the device of + * which to print DIO registers. + * + * This function prints out all the internal (DIO) + * registers of a TLAN chip. + * + **************************************************************/ -static void TLan_PrintDio( u16 io_base ) +static void tlan_print_dio(u16 io_base) { u32 data0, data1; int i; - printk( "TLAN: Contents of internal registers for io base 0x%04hx.\n", - io_base ); - printk( "TLAN: Off. +0 +4\n" ); - for ( i = 0; i < 0x4C; i+= 8 ) { - data0 = TLan_DioRead32( io_base, i ); - data1 = TLan_DioRead32( io_base, i + 0x4 ); - printk( "TLAN: 0x%02x 0x%08x 0x%08x\n", i, data0, data1 ); + pr_info("TLAN: Contents of internal registers for io base 0x%04hx.\n", + io_base); + pr_info("TLAN: Off. +0 +4\n"); + for (i = 0; i < 0x4C; i += 8) { + data0 = tlan_dio_read32(io_base, i); + data1 = tlan_dio_read32(io_base, i + 0x4); + pr_info("TLAN: 0x%02x 0x%08x 0x%08x\n", i, data0, data1); } -} /* TLan_PrintDio */ +} - /*************************************************************** - * TLan_PrintList - * - * Returns: - * Nothing - * Parms: - * list A pointer to the TLanList structure to - * be printed. - * type A string to designate type of list, - * "Rx" or "Tx". - * num The index of the list. - * - * This function prints out the contents of the list - * pointed to by the list parameter. - * - **************************************************************/ +/*************************************************************** + * TLan_PrintList + * + * Returns: + * Nothing + * Parms: + * list A pointer to the struct tlan_list structure to + * be printed. + * type A string to designate type of list, + * "Rx" or "Tx". + * num The index of the list. + * + * This function prints out the contents of the list + * pointed to by the list parameter. + * + **************************************************************/ -static void TLan_PrintList( TLanList *list, char *type, int num) +static void tlan_print_list(struct tlan_list *list, char *type, int num) { int i; - printk( "TLAN: %s List %d at %p\n", type, num, list ); - printk( "TLAN: Forward = 0x%08x\n", list->forward ); - printk( "TLAN: CSTAT = 0x%04hx\n", list->cStat ); - printk( "TLAN: Frame Size = 0x%04hx\n", list->frameSize ); - /* for ( i = 0; i < 10; i++ ) { */ - for ( i = 0; i < 2; i++ ) { - printk( "TLAN: Buffer[%d].count, addr = 0x%08x, 0x%08x\n", - i, list->buffer[i].count, list->buffer[i].address ); + pr_info("TLAN: %s List %d at %p\n", type, num, list); + pr_info("TLAN: Forward = 0x%08x\n", list->forward); + pr_info("TLAN: CSTAT = 0x%04hx\n", list->c_stat); + pr_info("TLAN: Frame Size = 0x%04hx\n", list->frame_size); + /* for (i = 0; i < 10; i++) { */ + for (i = 0; i < 2; i++) { + pr_info("TLAN: Buffer[%d].count, addr = 0x%08x, 0x%08x\n", + i, list->buffer[i].count, list->buffer[i].address); } -} /* TLan_PrintList */ +} - /*************************************************************** - * TLan_ReadAndClearStats - * - * Returns: - * Nothing - * Parms: - * dev Pointer to device structure of adapter - * to which to read stats. - * record Flag indicating whether to add - * - * This functions reads all the internal status registers - * of the TLAN chip, which clears them as a side effect. - * It then either adds the values to the device's status - * struct, or discards them, depending on whether record - * is TLAN_RECORD (!=0) or TLAN_IGNORE (==0). - * - **************************************************************/ +/*************************************************************** + * tlan_read_and_clear_stats + * + * Returns: + * Nothing + * Parms: + * dev Pointer to device structure of adapter + * to which to read stats. + * record Flag indicating whether to add + * + * This functions reads all the internal status registers + * of the TLAN chip, which clears them as a side effect. + * It then either adds the values to the device's status + * struct, or discards them, depending on whether record + * is TLAN_RECORD (!=0) or TLAN_IGNORE (==0). + * + **************************************************************/ -static void TLan_ReadAndClearStats( struct net_device *dev, int record ) +static void tlan_read_and_clear_stats(struct net_device *dev, int record) { u32 tx_good, tx_under; u32 rx_good, rx_over; @@ -2129,41 +2217,42 @@ static void TLan_ReadAndClearStats( struct net_device *dev, int record ) u32 multi_col, single_col; u32 excess_col, late_col, loss; - outw( TLAN_GOOD_TX_FRMS, dev->base_addr + TLAN_DIO_ADR ); - tx_good = inb( dev->base_addr + TLAN_DIO_DATA ); - tx_good += inb( dev->base_addr + TLAN_DIO_DATA + 1 ) << 8; - tx_good += inb( dev->base_addr + TLAN_DIO_DATA + 2 ) << 16; - tx_under = inb( dev->base_addr + TLAN_DIO_DATA + 3 ); - - outw( TLAN_GOOD_RX_FRMS, dev->base_addr + TLAN_DIO_ADR ); - rx_good = inb( dev->base_addr + TLAN_DIO_DATA ); - rx_good += inb( dev->base_addr + TLAN_DIO_DATA + 1 ) << 8; - rx_good += inb( dev->base_addr + TLAN_DIO_DATA + 2 ) << 16; - rx_over = inb( dev->base_addr + TLAN_DIO_DATA + 3 ); - - outw( TLAN_DEFERRED_TX, dev->base_addr + TLAN_DIO_ADR ); - def_tx = inb( dev->base_addr + TLAN_DIO_DATA ); - def_tx += inb( dev->base_addr + TLAN_DIO_DATA + 1 ) << 8; - crc = inb( dev->base_addr + TLAN_DIO_DATA + 2 ); - code = inb( dev->base_addr + TLAN_DIO_DATA + 3 ); - - outw( TLAN_MULTICOL_FRMS, dev->base_addr + TLAN_DIO_ADR ); - multi_col = inb( dev->base_addr + TLAN_DIO_DATA ); - multi_col += inb( dev->base_addr + TLAN_DIO_DATA + 1 ) << 8; - single_col = inb( dev->base_addr + TLAN_DIO_DATA + 2 ); - single_col += inb( dev->base_addr + TLAN_DIO_DATA + 3 ) << 8; - - outw( TLAN_EXCESSCOL_FRMS, dev->base_addr + TLAN_DIO_ADR ); - excess_col = inb( dev->base_addr + TLAN_DIO_DATA ); - late_col = inb( dev->base_addr + TLAN_DIO_DATA + 1 ); - loss = inb( dev->base_addr + TLAN_DIO_DATA + 2 ); - - if ( record ) { + outw(TLAN_GOOD_TX_FRMS, dev->base_addr + TLAN_DIO_ADR); + tx_good = inb(dev->base_addr + TLAN_DIO_DATA); + tx_good += inb(dev->base_addr + TLAN_DIO_DATA + 1) << 8; + tx_good += inb(dev->base_addr + TLAN_DIO_DATA + 2) << 16; + tx_under = inb(dev->base_addr + TLAN_DIO_DATA + 3); + + outw(TLAN_GOOD_RX_FRMS, dev->base_addr + TLAN_DIO_ADR); + rx_good = inb(dev->base_addr + TLAN_DIO_DATA); + rx_good += inb(dev->base_addr + TLAN_DIO_DATA + 1) << 8; + rx_good += inb(dev->base_addr + TLAN_DIO_DATA + 2) << 16; + rx_over = inb(dev->base_addr + TLAN_DIO_DATA + 3); + + outw(TLAN_DEFERRED_TX, dev->base_addr + TLAN_DIO_ADR); + def_tx = inb(dev->base_addr + TLAN_DIO_DATA); + def_tx += inb(dev->base_addr + TLAN_DIO_DATA + 1) << 8; + crc = inb(dev->base_addr + TLAN_DIO_DATA + 2); + code = inb(dev->base_addr + TLAN_DIO_DATA + 3); + + outw(TLAN_MULTICOL_FRMS, dev->base_addr + TLAN_DIO_ADR); + multi_col = inb(dev->base_addr + TLAN_DIO_DATA); + multi_col += inb(dev->base_addr + TLAN_DIO_DATA + 1) << 8; + single_col = inb(dev->base_addr + TLAN_DIO_DATA + 2); + single_col += inb(dev->base_addr + TLAN_DIO_DATA + 3) << 8; + + outw(TLAN_EXCESSCOL_FRMS, dev->base_addr + TLAN_DIO_ADR); + excess_col = inb(dev->base_addr + TLAN_DIO_DATA); + late_col = inb(dev->base_addr + TLAN_DIO_DATA + 1); + loss = inb(dev->base_addr + TLAN_DIO_DATA + 2); + + if (record) { dev->stats.rx_packets += rx_good; dev->stats.rx_errors += rx_over + crc + code; dev->stats.tx_packets += tx_good; dev->stats.tx_errors += tx_under + loss; - dev->stats.collisions += multi_col + single_col + excess_col + late_col; + dev->stats.collisions += multi_col + + single_col + excess_col + late_col; dev->stats.rx_over_errors += rx_over; dev->stats.rx_crc_errors += crc; @@ -2173,39 +2262,39 @@ static void TLan_ReadAndClearStats( struct net_device *dev, int record ) dev->stats.tx_carrier_errors += loss; } -} /* TLan_ReadAndClearStats */ +} - /*************************************************************** - * TLan_Reset - * - * Returns: - * 0 - * Parms: - * dev Pointer to device structure of adapter - * to be reset. - * - * This function resets the adapter and it's physical - * device. See Chap. 3, pp. 9-10 of the "ThunderLAN - * Programmer's Guide" for details. The routine tries to - * implement what is detailed there, though adjustments - * have been made. - * - **************************************************************/ +/*************************************************************** + * TLan_Reset + * + * Returns: + * 0 + * Parms: + * dev Pointer to device structure of adapter + * to be reset. + * + * This function resets the adapter and it's physical + * device. See Chap. 3, pp. 9-10 of the "ThunderLAN + * Programmer's Guide" for details. The routine tries to + * implement what is detailed there, though adjustments + * have been made. + * + **************************************************************/ static void -TLan_ResetAdapter( struct net_device *dev ) +tlan_reset_adapter(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); int i; u32 addr; u32 data; u8 data8; - priv->tlanFullDuplex = false; - priv->phyOnline=0; + priv->tlan_full_duplex = false; + priv->phy_online = 0; netif_carrier_off(dev); /* 1. Assert reset bit. */ @@ -2216,7 +2305,7 @@ TLan_ResetAdapter( struct net_device *dev ) udelay(1000); -/* 2. Turn off interrupts. ( Probably isn't necessary ) */ +/* 2. Turn off interrupts. (Probably isn't necessary) */ data = inl(dev->base_addr + TLAN_HOST_CMD); data |= TLAN_HC_INT_OFF; @@ -2224,207 +2313,208 @@ TLan_ResetAdapter( struct net_device *dev ) /* 3. Clear AREGs and HASHs. */ - for ( i = TLAN_AREG_0; i <= TLAN_HASH_2; i += 4 ) { - TLan_DioWrite32( dev->base_addr, (u16) i, 0 ); - } + for (i = TLAN_AREG_0; i <= TLAN_HASH_2; i += 4) + tlan_dio_write32(dev->base_addr, (u16) i, 0); /* 4. Setup NetConfig register. */ data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN | TLAN_NET_CFG_PHY_EN; - TLan_DioWrite16( dev->base_addr, TLAN_NET_CONFIG, (u16) data ); + tlan_dio_write16(dev->base_addr, TLAN_NET_CONFIG, (u16) data); /* 5. Load Ld_Tmr and Ld_Thr in HOST_CMD. */ - outl( TLAN_HC_LD_TMR | 0x3f, dev->base_addr + TLAN_HOST_CMD ); - outl( TLAN_HC_LD_THR | 0x9, dev->base_addr + TLAN_HOST_CMD ); + outl(TLAN_HC_LD_TMR | 0x3f, dev->base_addr + TLAN_HOST_CMD); + outl(TLAN_HC_LD_THR | 0x9, dev->base_addr + TLAN_HOST_CMD); /* 6. Unreset the MII by setting NMRST (in NetSio) to 1. */ - outw( TLAN_NET_SIO, dev->base_addr + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, dev->base_addr + TLAN_DIO_ADR); addr = dev->base_addr + TLAN_DIO_DATA + TLAN_NET_SIO; - TLan_SetBit( TLAN_NET_SIO_NMRST, addr ); + tlan_set_bit(TLAN_NET_SIO_NMRST, addr); /* 7. Setup the remaining registers. */ - if ( priv->tlanRev >= 0x30 ) { + if (priv->tlan_rev >= 0x30) { data8 = TLAN_ID_TX_EOC | TLAN_ID_RX_EOC; - TLan_DioWrite8( dev->base_addr, TLAN_INT_DIS, data8 ); + tlan_dio_write8(dev->base_addr, TLAN_INT_DIS, data8); } - TLan_PhyDetect( dev ); + tlan_phy_detect(dev); data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN; - if ( priv->adapter->flags & TLAN_ADAPTER_BIT_RATE_PHY ) { + if (priv->adapter->flags & TLAN_ADAPTER_BIT_RATE_PHY) { data |= TLAN_NET_CFG_BIT; - if ( priv->aui == 1 ) { - TLan_DioWrite8( dev->base_addr, TLAN_ACOMMIT, 0x0a ); - } else if ( priv->duplex == TLAN_DUPLEX_FULL ) { - TLan_DioWrite8( dev->base_addr, TLAN_ACOMMIT, 0x00 ); - priv->tlanFullDuplex = true; + if (priv->aui == 1) { + tlan_dio_write8(dev->base_addr, TLAN_ACOMMIT, 0x0a); + } else if (priv->duplex == TLAN_DUPLEX_FULL) { + tlan_dio_write8(dev->base_addr, TLAN_ACOMMIT, 0x00); + priv->tlan_full_duplex = true; } else { - TLan_DioWrite8( dev->base_addr, TLAN_ACOMMIT, 0x08 ); + tlan_dio_write8(dev->base_addr, TLAN_ACOMMIT, 0x08); } } - if ( priv->phyNum == 0 ) { + if (priv->phy_num == 0) data |= TLAN_NET_CFG_PHY_EN; - } - TLan_DioWrite16( dev->base_addr, TLAN_NET_CONFIG, (u16) data ); + tlan_dio_write16(dev->base_addr, TLAN_NET_CONFIG, (u16) data); - if ( priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY ) { - TLan_FinishReset( dev ); - } else { - TLan_PhyPowerDown( dev ); - } + if (priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY) + tlan_finish_reset(dev); + else + tlan_phy_power_down(dev); -} /* TLan_ResetAdapter */ +} static void -TLan_FinishReset( struct net_device *dev ) +tlan_finish_reset(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u8 data; u32 phy; u8 sio; u16 status; u16 partner; u16 tlphy_ctl; - u16 tlphy_par; + u16 tlphy_par; u16 tlphy_id1, tlphy_id2; - int i; + int i; - phy = priv->phy[priv->phyNum]; + phy = priv->phy[priv->phy_num]; data = TLAN_NET_CMD_NRESET | TLAN_NET_CMD_NWRAP; - if ( priv->tlanFullDuplex ) { + if (priv->tlan_full_duplex) data |= TLAN_NET_CMD_DUPLEX; - } - TLan_DioWrite8( dev->base_addr, TLAN_NET_CMD, data ); + tlan_dio_write8(dev->base_addr, TLAN_NET_CMD, data); data = TLAN_NET_MASK_MASK4 | TLAN_NET_MASK_MASK5; - if ( priv->phyNum == 0 ) { + if (priv->phy_num == 0) data |= TLAN_NET_MASK_MASK7; - } - TLan_DioWrite8( dev->base_addr, TLAN_NET_MASK, data ); - TLan_DioWrite16( dev->base_addr, TLAN_MAX_RX, ((1536)+7)&~7 ); - TLan_MiiReadReg( dev, phy, MII_GEN_ID_HI, &tlphy_id1 ); - TLan_MiiReadReg( dev, phy, MII_GEN_ID_LO, &tlphy_id2 ); + tlan_dio_write8(dev->base_addr, TLAN_NET_MASK, data); + tlan_dio_write16(dev->base_addr, TLAN_MAX_RX, ((1536)+7)&~7); + tlan_mii_read_reg(dev, phy, MII_GEN_ID_HI, &tlphy_id1); + tlan_mii_read_reg(dev, phy, MII_GEN_ID_LO, &tlphy_id2); - if ( ( priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY ) || - ( priv->aui ) ) { + if ((priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY) || + (priv->aui)) { status = MII_GS_LINK; - printk( "TLAN: %s: Link forced.\n", dev->name ); + pr_info("TLAN: %s: Link forced.\n", dev->name); } else { - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &status ); - udelay( 1000 ); - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &status ); - if ( (status & MII_GS_LINK) && - /* We only support link info on Nat.Sem. PHY's */ - (tlphy_id1 == NAT_SEM_ID1) && - (tlphy_id2 == NAT_SEM_ID2) ) { - TLan_MiiReadReg( dev, phy, MII_AN_LPA, &partner ); - TLan_MiiReadReg( dev, phy, TLAN_TLPHY_PAR, &tlphy_par ); - - printk( "TLAN: %s: Link active with ", dev->name ); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &status); + udelay(1000); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &status); + if ((status & MII_GS_LINK) && + /* We only support link info on Nat.Sem. PHY's */ + (tlphy_id1 == NAT_SEM_ID1) && + (tlphy_id2 == NAT_SEM_ID2)) { + tlan_mii_read_reg(dev, phy, MII_AN_LPA, &partner); + tlan_mii_read_reg(dev, phy, TLAN_TLPHY_PAR, &tlphy_par); + + pr_info("TLAN: %s: Link active with ", dev->name); if (!(tlphy_par & TLAN_PHY_AN_EN_STAT)) { - printk( "forced 10%sMbps %s-Duplex\n", - tlphy_par & TLAN_PHY_SPEED_100 ? "" : "0", - tlphy_par & TLAN_PHY_DUPLEX_FULL ? "Full" : "Half"); + pr_info("forced 10%sMbps %s-Duplex\n", + tlphy_par & TLAN_PHY_SPEED_100 + ? "" : "0", + tlphy_par & TLAN_PHY_DUPLEX_FULL + ? "Full" : "Half"); } else { - printk( "AutoNegotiation enabled, at 10%sMbps %s-Duplex\n", - tlphy_par & TLAN_PHY_SPEED_100 ? "" : "0", - tlphy_par & TLAN_PHY_DUPLEX_FULL ? "Full" : "Half"); - printk("TLAN: Partner capability: "); - for (i = 5; i <= 10; i++) - if (partner & (1<<i)) - printk("%s",media[i-5]); + pr_info("Autonegotiation enabled, at 10%sMbps %s-Duplex\n", + tlphy_par & TLAN_PHY_SPEED_100 + ? "" : "0", + tlphy_par & TLAN_PHY_DUPLEX_FULL + ? "Full" : "half"); + pr_info("TLAN: Partner capability: "); + for (i = 5; i <= 10; i++) + if (partner & (1<<i)) + printk("%s", media[i-5]); printk("\n"); } - TLan_DioWrite8( dev->base_addr, TLAN_LED_REG, TLAN_LED_LINK ); + tlan_dio_write8(dev->base_addr, TLAN_LED_REG, + TLAN_LED_LINK); #ifdef MONITOR /* We have link beat..for now anyway */ - priv->link = 1; - /*Enabling link beat monitoring */ - TLan_SetTimer( dev, (10*HZ), TLAN_TIMER_LINK_BEAT ); + priv->link = 1; + /*Enabling link beat monitoring */ + tlan_set_timer(dev, (10*HZ), TLAN_TIMER_LINK_BEAT); #endif } else if (status & MII_GS_LINK) { - printk( "TLAN: %s: Link active\n", dev->name ); - TLan_DioWrite8( dev->base_addr, TLAN_LED_REG, TLAN_LED_LINK ); + pr_info("TLAN: %s: Link active\n", dev->name); + tlan_dio_write8(dev->base_addr, TLAN_LED_REG, + TLAN_LED_LINK); } } - if ( priv->phyNum == 0 ) { - TLan_MiiReadReg( dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl ); - tlphy_ctl |= TLAN_TC_INTEN; - TLan_MiiWriteReg( dev, phy, TLAN_TLPHY_CTL, tlphy_ctl ); - sio = TLan_DioRead8( dev->base_addr, TLAN_NET_SIO ); - sio |= TLAN_NET_SIO_MINTEN; - TLan_DioWrite8( dev->base_addr, TLAN_NET_SIO, sio ); - } - - if ( status & MII_GS_LINK ) { - TLan_SetMac( dev, 0, dev->dev_addr ); - priv->phyOnline = 1; - outb( ( TLAN_HC_INT_ON >> 8 ), dev->base_addr + TLAN_HOST_CMD + 1 ); - if ( debug >= 1 && debug != TLAN_DEBUG_PROBE ) { - outb( ( TLAN_HC_REQ_INT >> 8 ), dev->base_addr + TLAN_HOST_CMD + 1 ); - } - outl( priv->rxListDMA, dev->base_addr + TLAN_CH_PARM ); - outl( TLAN_HC_GO | TLAN_HC_RT, dev->base_addr + TLAN_HOST_CMD ); + if (priv->phy_num == 0) { + tlan_mii_read_reg(dev, phy, TLAN_TLPHY_CTL, &tlphy_ctl); + tlphy_ctl |= TLAN_TC_INTEN; + tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, tlphy_ctl); + sio = tlan_dio_read8(dev->base_addr, TLAN_NET_SIO); + sio |= TLAN_NET_SIO_MINTEN; + tlan_dio_write8(dev->base_addr, TLAN_NET_SIO, sio); + } + + if (status & MII_GS_LINK) { + tlan_set_mac(dev, 0, dev->dev_addr); + priv->phy_online = 1; + outb((TLAN_HC_INT_ON >> 8), dev->base_addr + TLAN_HOST_CMD + 1); + if (debug >= 1 && debug != TLAN_DEBUG_PROBE) + outb((TLAN_HC_REQ_INT >> 8), + dev->base_addr + TLAN_HOST_CMD + 1); + outl(priv->rx_list_dma, dev->base_addr + TLAN_CH_PARM); + outl(TLAN_HC_GO | TLAN_HC_RT, dev->base_addr + TLAN_HOST_CMD); netif_carrier_on(dev); } else { - printk( "TLAN: %s: Link inactive, will retry in 10 secs...\n", - dev->name ); - TLan_SetTimer( dev, (10*HZ), TLAN_TIMER_FINISH_RESET ); + pr_info("TLAN: %s: Link inactive, will retry in 10 secs...\n", + dev->name); + tlan_set_timer(dev, (10*HZ), TLAN_TIMER_FINISH_RESET); return; } - TLan_SetMulticastList(dev); + tlan_set_multicast_list(dev); -} /* TLan_FinishReset */ +} - /*************************************************************** - * TLan_SetMac - * - * Returns: - * Nothing - * Parms: - * dev Pointer to device structure of adapter - * on which to change the AREG. - * areg The AREG to set the address in (0 - 3). - * mac A pointer to an array of chars. Each - * element stores one byte of the address. - * IE, it isn't in ascii. - * - * This function transfers a MAC address to one of the - * TLAN AREGs (address registers). The TLAN chip locks - * the register on writing to offset 0 and unlocks the - * register after writing to offset 5. If NULL is passed - * in mac, then the AREG is filled with 0's. - * - **************************************************************/ +/*************************************************************** + * tlan_set_mac + * + * Returns: + * Nothing + * Parms: + * dev Pointer to device structure of adapter + * on which to change the AREG. + * areg The AREG to set the address in (0 - 3). + * mac A pointer to an array of chars. Each + * element stores one byte of the address. + * IE, it isn't in ascii. + * + * This function transfers a MAC address to one of the + * TLAN AREGs (address registers). The TLAN chip locks + * the register on writing to offset 0 and unlocks the + * register after writing to offset 5. If NULL is passed + * in mac, then the AREG is filled with 0's. + * + **************************************************************/ -static void TLan_SetMac( struct net_device *dev, int areg, char *mac ) +static void tlan_set_mac(struct net_device *dev, int areg, char *mac) { int i; areg *= 6; - if ( mac != NULL ) { - for ( i = 0; i < 6; i++ ) - TLan_DioWrite8( dev->base_addr, - TLAN_AREG_0 + areg + i, mac[i] ); + if (mac != NULL) { + for (i = 0; i < 6; i++) + tlan_dio_write8(dev->base_addr, + TLAN_AREG_0 + areg + i, mac[i]); } else { - for ( i = 0; i < 6; i++ ) - TLan_DioWrite8( dev->base_addr, - TLAN_AREG_0 + areg + i, 0 ); + for (i = 0; i < 6; i++) + tlan_dio_write8(dev->base_addr, + TLAN_AREG_0 + areg + i, 0); } -} /* TLan_SetMac */ +} @@ -2432,205 +2522,202 @@ static void TLan_SetMac( struct net_device *dev, int areg, char *mac ) /***************************************************************************** ****************************************************************************** - ThunderLAN Driver PHY Layer Routines +ThunderLAN driver PHY layer routines ****************************************************************************** *****************************************************************************/ - /********************************************************************* - * TLan_PhyPrint - * - * Returns: - * Nothing - * Parms: - * dev A pointer to the device structure of the - * TLAN device having the PHYs to be detailed. - * - * This function prints the registers a PHY (aka transceiver). - * - ********************************************************************/ +/********************************************************************* + * tlan_phy_print + * + * Returns: + * Nothing + * Parms: + * dev A pointer to the device structure of the + * TLAN device having the PHYs to be detailed. + * + * This function prints the registers a PHY (aka transceiver). + * + ********************************************************************/ -static void TLan_PhyPrint( struct net_device *dev ) +static void tlan_phy_print(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 i, data0, data1, data2, data3, phy; - phy = priv->phy[priv->phyNum]; - - if ( priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY ) { - printk( "TLAN: Device %s, Unmanaged PHY.\n", dev->name ); - } else if ( phy <= TLAN_PHY_MAX_ADDR ) { - printk( "TLAN: Device %s, PHY 0x%02x.\n", dev->name, phy ); - printk( "TLAN: Off. +0 +1 +2 +3\n" ); - for ( i = 0; i < 0x20; i+= 4 ) { - printk( "TLAN: 0x%02x", i ); - TLan_MiiReadReg( dev, phy, i, &data0 ); - printk( " 0x%04hx", data0 ); - TLan_MiiReadReg( dev, phy, i + 1, &data1 ); - printk( " 0x%04hx", data1 ); - TLan_MiiReadReg( dev, phy, i + 2, &data2 ); - printk( " 0x%04hx", data2 ); - TLan_MiiReadReg( dev, phy, i + 3, &data3 ); - printk( " 0x%04hx\n", data3 ); + phy = priv->phy[priv->phy_num]; + + if (priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY) { + pr_info("TLAN: Device %s, Unmanaged PHY.\n", dev->name); + } else if (phy <= TLAN_PHY_MAX_ADDR) { + pr_info("TLAN: Device %s, PHY 0x%02x.\n", dev->name, phy); + pr_info("TLAN: Off. +0 +1 +2 +3\n"); + for (i = 0; i < 0x20; i += 4) { + pr_info("TLAN: 0x%02x", i); + tlan_mii_read_reg(dev, phy, i, &data0); + printk(" 0x%04hx", data0); + tlan_mii_read_reg(dev, phy, i + 1, &data1); + printk(" 0x%04hx", data1); + tlan_mii_read_reg(dev, phy, i + 2, &data2); + printk(" 0x%04hx", data2); + tlan_mii_read_reg(dev, phy, i + 3, &data3); + printk(" 0x%04hx\n", data3); } } else { - printk( "TLAN: Device %s, Invalid PHY.\n", dev->name ); + pr_info("TLAN: Device %s, Invalid PHY.\n", dev->name); } -} /* TLan_PhyPrint */ +} - /********************************************************************* - * TLan_PhyDetect - * - * Returns: - * Nothing - * Parms: - * dev A pointer to the device structure of the adapter - * for which the PHY needs determined. - * - * So far I've found that adapters which have external PHYs - * may also use the internal PHY for part of the functionality. - * (eg, AUI/Thinnet). This function finds out if this TLAN - * chip has an internal PHY, and then finds the first external - * PHY (starting from address 0) if it exists). - * - ********************************************************************/ +/********************************************************************* + * tlan_phy_detect + * + * Returns: + * Nothing + * Parms: + * dev A pointer to the device structure of the adapter + * for which the PHY needs determined. + * + * So far I've found that adapters which have external PHYs + * may also use the internal PHY for part of the functionality. + * (eg, AUI/Thinnet). This function finds out if this TLAN + * chip has an internal PHY, and then finds the first external + * PHY (starting from address 0) if it exists). + * + ********************************************************************/ -static void TLan_PhyDetect( struct net_device *dev ) +static void tlan_phy_detect(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 control; u16 hi; u16 lo; u32 phy; - if ( priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY ) { - priv->phyNum = 0xFFFF; + if (priv->adapter->flags & TLAN_ADAPTER_UNMANAGED_PHY) { + priv->phy_num = 0xffff; return; } - TLan_MiiReadReg( dev, TLAN_PHY_MAX_ADDR, MII_GEN_ID_HI, &hi ); + tlan_mii_read_reg(dev, TLAN_PHY_MAX_ADDR, MII_GEN_ID_HI, &hi); - if ( hi != 0xFFFF ) { + if (hi != 0xffff) priv->phy[0] = TLAN_PHY_MAX_ADDR; - } else { + else priv->phy[0] = TLAN_PHY_NONE; - } priv->phy[1] = TLAN_PHY_NONE; - for ( phy = 0; phy <= TLAN_PHY_MAX_ADDR; phy++ ) { - TLan_MiiReadReg( dev, phy, MII_GEN_CTL, &control ); - TLan_MiiReadReg( dev, phy, MII_GEN_ID_HI, &hi ); - TLan_MiiReadReg( dev, phy, MII_GEN_ID_LO, &lo ); - if ( ( control != 0xFFFF ) || - ( hi != 0xFFFF ) || ( lo != 0xFFFF ) ) { - TLAN_DBG( TLAN_DEBUG_GNRL, - "PHY found at %02x %04x %04x %04x\n", - phy, control, hi, lo ); - if ( ( priv->phy[1] == TLAN_PHY_NONE ) && - ( phy != TLAN_PHY_MAX_ADDR ) ) { + for (phy = 0; phy <= TLAN_PHY_MAX_ADDR; phy++) { + tlan_mii_read_reg(dev, phy, MII_GEN_CTL, &control); + tlan_mii_read_reg(dev, phy, MII_GEN_ID_HI, &hi); + tlan_mii_read_reg(dev, phy, MII_GEN_ID_LO, &lo); + if ((control != 0xffff) || + (hi != 0xffff) || (lo != 0xffff)) { + TLAN_DBG(TLAN_DEBUG_GNRL, + "PHY found at %02x %04x %04x %04x\n", + phy, control, hi, lo); + if ((priv->phy[1] == TLAN_PHY_NONE) && + (phy != TLAN_PHY_MAX_ADDR)) { priv->phy[1] = phy; } } } - if ( priv->phy[1] != TLAN_PHY_NONE ) { - priv->phyNum = 1; - } else if ( priv->phy[0] != TLAN_PHY_NONE ) { - priv->phyNum = 0; - } else { - printk( "TLAN: Cannot initialize device, no PHY was found!\n" ); - } + if (priv->phy[1] != TLAN_PHY_NONE) + priv->phy_num = 1; + else if (priv->phy[0] != TLAN_PHY_NONE) + priv->phy_num = 0; + else + pr_info("TLAN: Cannot initialize device, no PHY was found!\n"); -} /* TLan_PhyDetect */ +} -static void TLan_PhyPowerDown( struct net_device *dev ) +static void tlan_phy_power_down(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 value; - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Powering down PHY(s).\n", dev->name ); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Powering down PHY(s).\n", dev->name); value = MII_GC_PDOWN | MII_GC_LOOPBK | MII_GC_ISOLATE; - TLan_MiiSync( dev->base_addr ); - TLan_MiiWriteReg( dev, priv->phy[priv->phyNum], MII_GEN_CTL, value ); - if ( ( priv->phyNum == 0 ) && - ( priv->phy[1] != TLAN_PHY_NONE ) && - ( ! ( priv->adapter->flags & TLAN_ADAPTER_USE_INTERN_10 ) ) ) { - TLan_MiiSync( dev->base_addr ); - TLan_MiiWriteReg( dev, priv->phy[1], MII_GEN_CTL, value ); + tlan_mii_sync(dev->base_addr); + tlan_mii_write_reg(dev, priv->phy[priv->phy_num], MII_GEN_CTL, value); + if ((priv->phy_num == 0) && + (priv->phy[1] != TLAN_PHY_NONE) && + (!(priv->adapter->flags & TLAN_ADAPTER_USE_INTERN_10))) { + tlan_mii_sync(dev->base_addr); + tlan_mii_write_reg(dev, priv->phy[1], MII_GEN_CTL, value); } /* Wait for 50 ms and powerup * This is abitrary. It is intended to make sure the * transceiver settles. */ - TLan_SetTimer( dev, (HZ/20), TLAN_TIMER_PHY_PUP ); + tlan_set_timer(dev, (HZ/20), TLAN_TIMER_PHY_PUP); -} /* TLan_PhyPowerDown */ +} -static void TLan_PhyPowerUp( struct net_device *dev ) +static void tlan_phy_power_up(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 value; - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Powering up PHY.\n", dev->name ); - TLan_MiiSync( dev->base_addr ); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Powering up PHY.\n", dev->name); + tlan_mii_sync(dev->base_addr); value = MII_GC_LOOPBK; - TLan_MiiWriteReg( dev, priv->phy[priv->phyNum], MII_GEN_CTL, value ); - TLan_MiiSync(dev->base_addr); + tlan_mii_write_reg(dev, priv->phy[priv->phy_num], MII_GEN_CTL, value); + tlan_mii_sync(dev->base_addr); /* Wait for 500 ms and reset the * transceiver. The TLAN docs say both 50 ms and * 500 ms, so do the longer, just in case. */ - TLan_SetTimer( dev, (HZ/20), TLAN_TIMER_PHY_RESET ); + tlan_set_timer(dev, (HZ/20), TLAN_TIMER_PHY_RESET); -} /* TLan_PhyPowerUp */ +} -static void TLan_PhyReset( struct net_device *dev ) +static void tlan_phy_reset(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 phy; u16 value; - phy = priv->phy[priv->phyNum]; + phy = priv->phy[priv->phy_num]; - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Reseting PHY.\n", dev->name ); - TLan_MiiSync( dev->base_addr ); + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Reseting PHY.\n", dev->name); + tlan_mii_sync(dev->base_addr); value = MII_GC_LOOPBK | MII_GC_RESET; - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, value ); - TLan_MiiReadReg( dev, phy, MII_GEN_CTL, &value ); - while ( value & MII_GC_RESET ) { - TLan_MiiReadReg( dev, phy, MII_GEN_CTL, &value ); - } + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, value); + tlan_mii_read_reg(dev, phy, MII_GEN_CTL, &value); + while (value & MII_GC_RESET) + tlan_mii_read_reg(dev, phy, MII_GEN_CTL, &value); /* Wait for 500 ms and initialize. * I don't remember why I wait this long. * I've changed this to 50ms, as it seems long enough. */ - TLan_SetTimer( dev, (HZ/20), TLAN_TIMER_PHY_START_LINK ); + tlan_set_timer(dev, (HZ/20), TLAN_TIMER_PHY_START_LINK); -} /* TLan_PhyReset */ +} -static void TLan_PhyStartLink( struct net_device *dev ) +static void tlan_phy_start_link(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 ability; u16 control; u16 data; @@ -2638,86 +2725,88 @@ static void TLan_PhyStartLink( struct net_device *dev ) u16 status; u16 tctl; - phy = priv->phy[priv->phyNum]; - TLAN_DBG( TLAN_DEBUG_GNRL, "%s: Trying to activate link.\n", dev->name ); - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &status ); - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &ability ); + phy = priv->phy[priv->phy_num]; + TLAN_DBG(TLAN_DEBUG_GNRL, "%s: Trying to activate link.\n", dev->name); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &status); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &ability); - if ( ( status & MII_GS_AUTONEG ) && - ( ! priv->aui ) ) { + if ((status & MII_GS_AUTONEG) && + (!priv->aui)) { ability = status >> 11; - if ( priv->speed == TLAN_SPEED_10 && - priv->duplex == TLAN_DUPLEX_HALF) { - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x0000); - } else if ( priv->speed == TLAN_SPEED_10 && - priv->duplex == TLAN_DUPLEX_FULL) { - priv->tlanFullDuplex = true; - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x0100); - } else if ( priv->speed == TLAN_SPEED_100 && - priv->duplex == TLAN_DUPLEX_HALF) { - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x2000); - } else if ( priv->speed == TLAN_SPEED_100 && - priv->duplex == TLAN_DUPLEX_FULL) { - priv->tlanFullDuplex = true; - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x2100); + if (priv->speed == TLAN_SPEED_10 && + priv->duplex == TLAN_DUPLEX_HALF) { + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x0000); + } else if (priv->speed == TLAN_SPEED_10 && + priv->duplex == TLAN_DUPLEX_FULL) { + priv->tlan_full_duplex = true; + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x0100); + } else if (priv->speed == TLAN_SPEED_100 && + priv->duplex == TLAN_DUPLEX_HALF) { + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x2000); + } else if (priv->speed == TLAN_SPEED_100 && + priv->duplex == TLAN_DUPLEX_FULL) { + priv->tlan_full_duplex = true; + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x2100); } else { /* Set Auto-Neg advertisement */ - TLan_MiiWriteReg( dev, phy, MII_AN_ADV, (ability << 5) | 1); + tlan_mii_write_reg(dev, phy, MII_AN_ADV, + (ability << 5) | 1); /* Enablee Auto-Neg */ - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x1000 ); + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x1000); /* Restart Auto-Neg */ - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, 0x1200 ); + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, 0x1200); /* Wait for 4 sec for autonegotiation - * to complete. The max spec time is less than this - * but the card need additional time to start AN. - * .5 sec should be plenty extra. - */ - printk( "TLAN: %s: Starting autonegotiation.\n", dev->name ); - TLan_SetTimer( dev, (2*HZ), TLAN_TIMER_PHY_FINISH_AN ); + * to complete. The max spec time is less than this + * but the card need additional time to start AN. + * .5 sec should be plenty extra. + */ + pr_info("TLAN: %s: Starting autonegotiation.\n", + dev->name); + tlan_set_timer(dev, (2*HZ), TLAN_TIMER_PHY_FINISH_AN); return; } } - if ( ( priv->aui ) && ( priv->phyNum != 0 ) ) { - priv->phyNum = 0; - data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN | TLAN_NET_CFG_PHY_EN; - TLan_DioWrite16( dev->base_addr, TLAN_NET_CONFIG, data ); - TLan_SetTimer( dev, (40*HZ/1000), TLAN_TIMER_PHY_PDOWN ); + if ((priv->aui) && (priv->phy_num != 0)) { + priv->phy_num = 0; + data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN + | TLAN_NET_CFG_PHY_EN; + tlan_dio_write16(dev->base_addr, TLAN_NET_CONFIG, data); + tlan_set_timer(dev, (40*HZ/1000), TLAN_TIMER_PHY_PDOWN); return; - } else if ( priv->phyNum == 0 ) { + } else if (priv->phy_num == 0) { control = 0; - TLan_MiiReadReg( dev, phy, TLAN_TLPHY_CTL, &tctl ); - if ( priv->aui ) { - tctl |= TLAN_TC_AUISEL; + tlan_mii_read_reg(dev, phy, TLAN_TLPHY_CTL, &tctl); + if (priv->aui) { + tctl |= TLAN_TC_AUISEL; } else { - tctl &= ~TLAN_TC_AUISEL; - if ( priv->duplex == TLAN_DUPLEX_FULL ) { + tctl &= ~TLAN_TC_AUISEL; + if (priv->duplex == TLAN_DUPLEX_FULL) { control |= MII_GC_DUPLEX; - priv->tlanFullDuplex = true; + priv->tlan_full_duplex = true; } - if ( priv->speed == TLAN_SPEED_100 ) { + if (priv->speed == TLAN_SPEED_100) control |= MII_GC_SPEEDSEL; - } } - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, control ); - TLan_MiiWriteReg( dev, phy, TLAN_TLPHY_CTL, tctl ); + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, control); + tlan_mii_write_reg(dev, phy, TLAN_TLPHY_CTL, tctl); } /* Wait for 2 sec to give the transceiver time * to establish link. */ - TLan_SetTimer( dev, (4*HZ), TLAN_TIMER_FINISH_RESET ); + tlan_set_timer(dev, (4*HZ), TLAN_TIMER_FINISH_RESET); -} /* TLan_PhyStartLink */ +} -static void TLan_PhyFinishAutoNeg( struct net_device *dev ) +static void tlan_phy_finish_auto_neg(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 an_adv; u16 an_lpa; u16 data; @@ -2725,115 +2814,118 @@ static void TLan_PhyFinishAutoNeg( struct net_device *dev ) u16 phy; u16 status; - phy = priv->phy[priv->phyNum]; + phy = priv->phy[priv->phy_num]; - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &status ); - udelay( 1000 ); - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &status ); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &status); + udelay(1000); + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &status); - if ( ! ( status & MII_GS_AUTOCMPLT ) ) { + if (!(status & MII_GS_AUTOCMPLT)) { /* Wait for 8 sec to give the process * more time. Perhaps we should fail after a while. */ - if (!priv->neg_be_verbose++) { - pr_info("TLAN: Giving autonegotiation more time.\n"); - pr_info("TLAN: Please check that your adapter has\n"); - pr_info("TLAN: been properly connected to a HUB or Switch.\n"); - pr_info("TLAN: Trying to establish link in the background...\n"); - } - TLan_SetTimer( dev, (8*HZ), TLAN_TIMER_PHY_FINISH_AN ); + if (!priv->neg_be_verbose++) { + pr_info("TLAN: Giving autonegotiation more time.\n"); + pr_info("TLAN: Please check that your adapter has\n"); + pr_info("TLAN: been properly connected to a HUB or Switch.\n"); + pr_info("TLAN: Trying to establish link in the background...\n"); + } + tlan_set_timer(dev, (8*HZ), TLAN_TIMER_PHY_FINISH_AN); return; } - printk( "TLAN: %s: Autonegotiation complete.\n", dev->name ); - TLan_MiiReadReg( dev, phy, MII_AN_ADV, &an_adv ); - TLan_MiiReadReg( dev, phy, MII_AN_LPA, &an_lpa ); + pr_info("TLAN: %s: Autonegotiation complete.\n", dev->name); + tlan_mii_read_reg(dev, phy, MII_AN_ADV, &an_adv); + tlan_mii_read_reg(dev, phy, MII_AN_LPA, &an_lpa); mode = an_adv & an_lpa & 0x03E0; - if ( mode & 0x0100 ) { - priv->tlanFullDuplex = true; - } else if ( ! ( mode & 0x0080 ) && ( mode & 0x0040 ) ) { - priv->tlanFullDuplex = true; - } - - if ( ( ! ( mode & 0x0180 ) ) && - ( priv->adapter->flags & TLAN_ADAPTER_USE_INTERN_10 ) && - ( priv->phyNum != 0 ) ) { - priv->phyNum = 0; - data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN | TLAN_NET_CFG_PHY_EN; - TLan_DioWrite16( dev->base_addr, TLAN_NET_CONFIG, data ); - TLan_SetTimer( dev, (400*HZ/1000), TLAN_TIMER_PHY_PDOWN ); + if (mode & 0x0100) + priv->tlan_full_duplex = true; + else if (!(mode & 0x0080) && (mode & 0x0040)) + priv->tlan_full_duplex = true; + + if ((!(mode & 0x0180)) && + (priv->adapter->flags & TLAN_ADAPTER_USE_INTERN_10) && + (priv->phy_num != 0)) { + priv->phy_num = 0; + data = TLAN_NET_CFG_1FRAG | TLAN_NET_CFG_1CHAN + | TLAN_NET_CFG_PHY_EN; + tlan_dio_write16(dev->base_addr, TLAN_NET_CONFIG, data); + tlan_set_timer(dev, (400*HZ/1000), TLAN_TIMER_PHY_PDOWN); return; } - if ( priv->phyNum == 0 ) { - if ( ( priv->duplex == TLAN_DUPLEX_FULL ) || - ( an_adv & an_lpa & 0x0040 ) ) { - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, - MII_GC_AUTOENB | MII_GC_DUPLEX ); - pr_info("TLAN: Starting internal PHY with FULL-DUPLEX\n" ); + if (priv->phy_num == 0) { + if ((priv->duplex == TLAN_DUPLEX_FULL) || + (an_adv & an_lpa & 0x0040)) { + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, + MII_GC_AUTOENB | MII_GC_DUPLEX); + pr_info("TLAN: Starting internal PHY with FULL-DUPLEX\n"); } else { - TLan_MiiWriteReg( dev, phy, MII_GEN_CTL, MII_GC_AUTOENB ); - pr_info( "TLAN: Starting internal PHY with HALF-DUPLEX\n" ); + tlan_mii_write_reg(dev, phy, MII_GEN_CTL, + MII_GC_AUTOENB); + pr_info("TLAN: Starting internal PHY with HALF-DUPLEX\n"); } } /* Wait for 100 ms. No reason in partiticular. */ - TLan_SetTimer( dev, (HZ/10), TLAN_TIMER_FINISH_RESET ); + tlan_set_timer(dev, (HZ/10), TLAN_TIMER_FINISH_RESET); -} /* TLan_PhyFinishAutoNeg */ +} #ifdef MONITOR - /********************************************************************* - * - * TLan_phyMonitor - * - * Returns: - * None - * - * Params: - * dev The device structure of this device. - * - * - * This function monitors PHY condition by reading the status - * register via the MII bus. This can be used to give info - * about link changes (up/down), and possible switch to alternate - * media. - * - * ******************************************************************/ - -void TLan_PhyMonitor( struct net_device *dev ) +/********************************************************************* + * + * tlan_phy_monitor + * + * Returns: + * None + * + * Params: + * dev The device structure of this device. + * + * + * This function monitors PHY condition by reading the status + * register via the MII bus. This can be used to give info + * about link changes (up/down), and possible switch to alternate + * media. + * + *******************************************************************/ + +void tlan_phy_monitor(struct net_device *dev) { - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); u16 phy; u16 phy_status; - phy = priv->phy[priv->phyNum]; + phy = priv->phy[priv->phy_num]; - /* Get PHY status register */ - TLan_MiiReadReg( dev, phy, MII_GEN_STS, &phy_status ); + /* Get PHY status register */ + tlan_mii_read_reg(dev, phy, MII_GEN_STS, &phy_status); - /* Check if link has been lost */ - if (!(phy_status & MII_GS_LINK)) { - if (priv->link) { - priv->link = 0; - printk(KERN_DEBUG "TLAN: %s has lost link\n", dev->name); - netif_carrier_off(dev); - TLan_SetTimer( dev, (2*HZ), TLAN_TIMER_LINK_BEAT ); - return; + /* Check if link has been lost */ + if (!(phy_status & MII_GS_LINK)) { + if (priv->link) { + priv->link = 0; + printk(KERN_DEBUG "TLAN: %s has lost link\n", + dev->name); + netif_carrier_off(dev); + tlan_set_timer(dev, (2*HZ), TLAN_TIMER_LINK_BEAT); + return; } } - /* Link restablished? */ - if ((phy_status & MII_GS_LINK) && !priv->link) { - priv->link = 1; - printk(KERN_DEBUG "TLAN: %s has reestablished link\n", dev->name); + /* Link restablished? */ + if ((phy_status & MII_GS_LINK) && !priv->link) { + priv->link = 1; + printk(KERN_DEBUG "TLAN: %s has reestablished link\n", + dev->name); netif_carrier_on(dev); - } + } /* Setup a new monitor */ - TLan_SetTimer( dev, (2*HZ), TLAN_TIMER_LINK_BEAT ); + tlan_set_timer(dev, (2*HZ), TLAN_TIMER_LINK_BEAT); } #endif /* MONITOR */ @@ -2842,47 +2934,48 @@ void TLan_PhyMonitor( struct net_device *dev ) /***************************************************************************** ****************************************************************************** - ThunderLAN Driver MII Routines +ThunderLAN driver MII routines - These routines are based on the information in Chap. 2 of the - "ThunderLAN Programmer's Guide", pp. 15-24. +these routines are based on the information in chap. 2 of the +"ThunderLAN Programmer's Guide", pp. 15-24. ****************************************************************************** *****************************************************************************/ - /*************************************************************** - * TLan_MiiReadReg - * - * Returns: - * false if ack received ok - * true if no ack received or other error - * - * Parms: - * dev The device structure containing - * The io address and interrupt count - * for this device. - * phy The address of the PHY to be queried. - * reg The register whose contents are to be - * retrieved. - * val A pointer to a variable to store the - * retrieved value. - * - * This function uses the TLAN's MII bus to retrieve the contents - * of a given register on a PHY. It sends the appropriate info - * and then reads the 16-bit register value from the MII bus via - * the TLAN SIO register. - * - **************************************************************/ - -static bool TLan_MiiReadReg( struct net_device *dev, u16 phy, u16 reg, u16 *val ) +/*************************************************************** + * tlan_mii_read_reg + * + * Returns: + * false if ack received ok + * true if no ack received or other error + * + * Parms: + * dev The device structure containing + * The io address and interrupt count + * for this device. + * phy The address of the PHY to be queried. + * reg The register whose contents are to be + * retrieved. + * val A pointer to a variable to store the + * retrieved value. + * + * This function uses the TLAN's MII bus to retrieve the contents + * of a given register on a PHY. It sends the appropriate info + * and then reads the 16-bit register value from the MII bus via + * the TLAN SIO register. + * + **************************************************************/ + +static bool +tlan_mii_read_reg(struct net_device *dev, u16 phy, u16 reg, u16 *val) { u8 nack; u16 sio, tmp; - u32 i; + u32 i; bool err; int minten; - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); unsigned long flags = 0; err = false; @@ -2892,48 +2985,48 @@ static bool TLan_MiiReadReg( struct net_device *dev, u16 phy, u16 reg, u16 *val if (!in_irq()) spin_lock_irqsave(&priv->lock, flags); - TLan_MiiSync(dev->base_addr); + tlan_mii_sync(dev->base_addr); - minten = TLan_GetBit( TLAN_NET_SIO_MINTEN, sio ); - if ( minten ) - TLan_ClearBit(TLAN_NET_SIO_MINTEN, sio); + minten = tlan_get_bit(TLAN_NET_SIO_MINTEN, sio); + if (minten) + tlan_clear_bit(TLAN_NET_SIO_MINTEN, sio); - TLan_MiiSendData( dev->base_addr, 0x1, 2 ); /* Start ( 01b ) */ - TLan_MiiSendData( dev->base_addr, 0x2, 2 ); /* Read ( 10b ) */ - TLan_MiiSendData( dev->base_addr, phy, 5 ); /* Device # */ - TLan_MiiSendData( dev->base_addr, reg, 5 ); /* Register # */ + tlan_mii_send_data(dev->base_addr, 0x1, 2); /* start (01b) */ + tlan_mii_send_data(dev->base_addr, 0x2, 2); /* read (10b) */ + tlan_mii_send_data(dev->base_addr, phy, 5); /* device # */ + tlan_mii_send_data(dev->base_addr, reg, 5); /* register # */ - TLan_ClearBit(TLAN_NET_SIO_MTXEN, sio); /* Change direction */ + tlan_clear_bit(TLAN_NET_SIO_MTXEN, sio); /* change direction */ - TLan_ClearBit(TLAN_NET_SIO_MCLK, sio); /* Clock Idle bit */ - TLan_SetBit(TLAN_NET_SIO_MCLK, sio); - TLan_ClearBit(TLAN_NET_SIO_MCLK, sio); /* Wait 300ns */ + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); /* clock idle bit */ + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); /* wait 300ns */ - nack = TLan_GetBit(TLAN_NET_SIO_MDATA, sio); /* Check for ACK */ - TLan_SetBit(TLAN_NET_SIO_MCLK, sio); /* Finish ACK */ - if (nack) { /* No ACK, so fake it */ + nack = tlan_get_bit(TLAN_NET_SIO_MDATA, sio); /* check for ACK */ + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); /* finish ACK */ + if (nack) { /* no ACK, so fake it */ for (i = 0; i < 16; i++) { - TLan_ClearBit(TLAN_NET_SIO_MCLK, sio); - TLan_SetBit(TLAN_NET_SIO_MCLK, sio); + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); } tmp = 0xffff; err = true; } else { /* ACK, so read data */ for (tmp = 0, i = 0x8000; i; i >>= 1) { - TLan_ClearBit(TLAN_NET_SIO_MCLK, sio); - if (TLan_GetBit(TLAN_NET_SIO_MDATA, sio)) + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); + if (tlan_get_bit(TLAN_NET_SIO_MDATA, sio)) tmp |= i; - TLan_SetBit(TLAN_NET_SIO_MCLK, sio); + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); } } - TLan_ClearBit(TLAN_NET_SIO_MCLK, sio); /* Idle cycle */ - TLan_SetBit(TLAN_NET_SIO_MCLK, sio); + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); /* idle cycle */ + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); - if ( minten ) - TLan_SetBit(TLAN_NET_SIO_MINTEN, sio); + if (minten) + tlan_set_bit(TLAN_NET_SIO_MINTEN, sio); *val = tmp; @@ -2942,116 +3035,117 @@ static bool TLan_MiiReadReg( struct net_device *dev, u16 phy, u16 reg, u16 *val return err; -} /* TLan_MiiReadReg */ +} - /*************************************************************** - * TLan_MiiSendData - * - * Returns: - * Nothing - * Parms: - * base_port The base IO port of the adapter in - * question. - * dev The address of the PHY to be queried. - * data The value to be placed on the MII bus. - * num_bits The number of bits in data that are to - * be placed on the MII bus. - * - * This function sends on sequence of bits on the MII - * configuration bus. - * - **************************************************************/ +/*************************************************************** + * tlan_mii_send_data + * + * Returns: + * Nothing + * Parms: + * base_port The base IO port of the adapter in + * question. + * dev The address of the PHY to be queried. + * data The value to be placed on the MII bus. + * num_bits The number of bits in data that are to + * be placed on the MII bus. + * + * This function sends on sequence of bits on the MII + * configuration bus. + * + **************************************************************/ -static void TLan_MiiSendData( u16 base_port, u32 data, unsigned num_bits ) +static void tlan_mii_send_data(u16 base_port, u32 data, unsigned num_bits) { u16 sio; u32 i; - if ( num_bits == 0 ) + if (num_bits == 0) return; - outw( TLAN_NET_SIO, base_port + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, base_port + TLAN_DIO_ADR); sio = base_port + TLAN_DIO_DATA + TLAN_NET_SIO; - TLan_SetBit( TLAN_NET_SIO_MTXEN, sio ); + tlan_set_bit(TLAN_NET_SIO_MTXEN, sio); - for ( i = ( 0x1 << ( num_bits - 1 ) ); i; i >>= 1 ) { - TLan_ClearBit( TLAN_NET_SIO_MCLK, sio ); - (void) TLan_GetBit( TLAN_NET_SIO_MCLK, sio ); - if ( data & i ) - TLan_SetBit( TLAN_NET_SIO_MDATA, sio ); + for (i = (0x1 << (num_bits - 1)); i; i >>= 1) { + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); + (void) tlan_get_bit(TLAN_NET_SIO_MCLK, sio); + if (data & i) + tlan_set_bit(TLAN_NET_SIO_MDATA, sio); else - TLan_ClearBit( TLAN_NET_SIO_MDATA, sio ); - TLan_SetBit( TLAN_NET_SIO_MCLK, sio ); - (void) TLan_GetBit( TLAN_NET_SIO_MCLK, sio ); + tlan_clear_bit(TLAN_NET_SIO_MDATA, sio); + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); + (void) tlan_get_bit(TLAN_NET_SIO_MCLK, sio); } -} /* TLan_MiiSendData */ +} - /*************************************************************** - * TLan_MiiSync - * - * Returns: - * Nothing - * Parms: - * base_port The base IO port of the adapter in - * question. - * - * This functions syncs all PHYs in terms of the MII configuration - * bus. - * - **************************************************************/ +/*************************************************************** + * TLan_MiiSync + * + * Returns: + * Nothing + * Parms: + * base_port The base IO port of the adapter in + * question. + * + * This functions syncs all PHYs in terms of the MII configuration + * bus. + * + **************************************************************/ -static void TLan_MiiSync( u16 base_port ) +static void tlan_mii_sync(u16 base_port) { int i; u16 sio; - outw( TLAN_NET_SIO, base_port + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, base_port + TLAN_DIO_ADR); sio = base_port + TLAN_DIO_DATA + TLAN_NET_SIO; - TLan_ClearBit( TLAN_NET_SIO_MTXEN, sio ); - for ( i = 0; i < 32; i++ ) { - TLan_ClearBit( TLAN_NET_SIO_MCLK, sio ); - TLan_SetBit( TLAN_NET_SIO_MCLK, sio ); + tlan_clear_bit(TLAN_NET_SIO_MTXEN, sio); + for (i = 0; i < 32; i++) { + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); } -} /* TLan_MiiSync */ +} - /*************************************************************** - * TLan_MiiWriteReg - * - * Returns: - * Nothing - * Parms: - * dev The device structure for the device - * to write to. - * phy The address of the PHY to be written to. - * reg The register whose contents are to be - * written. - * val The value to be written to the register. - * - * This function uses the TLAN's MII bus to write the contents of a - * given register on a PHY. It sends the appropriate info and then - * writes the 16-bit register value from the MII configuration bus - * via the TLAN SIO register. - * - **************************************************************/ +/*************************************************************** + * tlan_mii_write_reg + * + * Returns: + * Nothing + * Parms: + * dev The device structure for the device + * to write to. + * phy The address of the PHY to be written to. + * reg The register whose contents are to be + * written. + * val The value to be written to the register. + * + * This function uses the TLAN's MII bus to write the contents of a + * given register on a PHY. It sends the appropriate info and then + * writes the 16-bit register value from the MII configuration bus + * via the TLAN SIO register. + * + **************************************************************/ -static void TLan_MiiWriteReg( struct net_device *dev, u16 phy, u16 reg, u16 val ) +static void +tlan_mii_write_reg(struct net_device *dev, u16 phy, u16 reg, u16 val) { u16 sio; int minten; unsigned long flags = 0; - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); outw(TLAN_NET_SIO, dev->base_addr + TLAN_DIO_ADR); sio = dev->base_addr + TLAN_DIO_DATA + TLAN_NET_SIO; @@ -3059,30 +3153,30 @@ static void TLan_MiiWriteReg( struct net_device *dev, u16 phy, u16 reg, u16 val if (!in_irq()) spin_lock_irqsave(&priv->lock, flags); - TLan_MiiSync( dev->base_addr ); + tlan_mii_sync(dev->base_addr); - minten = TLan_GetBit( TLAN_NET_SIO_MINTEN, sio ); - if ( minten ) - TLan_ClearBit( TLAN_NET_SIO_MINTEN, sio ); + minten = tlan_get_bit(TLAN_NET_SIO_MINTEN, sio); + if (minten) + tlan_clear_bit(TLAN_NET_SIO_MINTEN, sio); - TLan_MiiSendData( dev->base_addr, 0x1, 2 ); /* Start ( 01b ) */ - TLan_MiiSendData( dev->base_addr, 0x1, 2 ); /* Write ( 01b ) */ - TLan_MiiSendData( dev->base_addr, phy, 5 ); /* Device # */ - TLan_MiiSendData( dev->base_addr, reg, 5 ); /* Register # */ + tlan_mii_send_data(dev->base_addr, 0x1, 2); /* start (01b) */ + tlan_mii_send_data(dev->base_addr, 0x1, 2); /* write (01b) */ + tlan_mii_send_data(dev->base_addr, phy, 5); /* device # */ + tlan_mii_send_data(dev->base_addr, reg, 5); /* register # */ - TLan_MiiSendData( dev->base_addr, 0x2, 2 ); /* Send ACK */ - TLan_MiiSendData( dev->base_addr, val, 16 ); /* Send Data */ + tlan_mii_send_data(dev->base_addr, 0x2, 2); /* send ACK */ + tlan_mii_send_data(dev->base_addr, val, 16); /* send data */ - TLan_ClearBit( TLAN_NET_SIO_MCLK, sio ); /* Idle cycle */ - TLan_SetBit( TLAN_NET_SIO_MCLK, sio ); + tlan_clear_bit(TLAN_NET_SIO_MCLK, sio); /* idle cycle */ + tlan_set_bit(TLAN_NET_SIO_MCLK, sio); - if ( minten ) - TLan_SetBit( TLAN_NET_SIO_MINTEN, sio ); + if (minten) + tlan_set_bit(TLAN_NET_SIO_MINTEN, sio); if (!in_irq()) spin_unlock_irqrestore(&priv->lock, flags); -} /* TLan_MiiWriteReg */ +} @@ -3090,229 +3184,226 @@ static void TLan_MiiWriteReg( struct net_device *dev, u16 phy, u16 reg, u16 val /***************************************************************************** ****************************************************************************** - ThunderLAN Driver Eeprom routines +ThunderLAN driver eeprom routines - The Compaq Netelligent 10 and 10/100 cards use a Microchip 24C02A - EEPROM. These functions are based on information in Microchip's - data sheet. I don't know how well this functions will work with - other EEPROMs. +the Compaq netelligent 10 and 10/100 cards use a microchip 24C02A +EEPROM. these functions are based on information in microchip's +data sheet. I don't know how well this functions will work with +other Eeproms. ****************************************************************************** *****************************************************************************/ - /*************************************************************** - * TLan_EeSendStart - * - * Returns: - * Nothing - * Parms: - * io_base The IO port base address for the - * TLAN device with the EEPROM to - * use. - * - * This function sends a start cycle to an EEPROM attached - * to a TLAN chip. - * - **************************************************************/ - -static void TLan_EeSendStart( u16 io_base ) +/*************************************************************** + * tlan_ee_send_start + * + * Returns: + * Nothing + * Parms: + * io_base The IO port base address for the + * TLAN device with the EEPROM to + * use. + * + * This function sends a start cycle to an EEPROM attached + * to a TLAN chip. + * + **************************************************************/ + +static void tlan_ee_send_start(u16 io_base) { u16 sio; - outw( TLAN_NET_SIO, io_base + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, io_base + TLAN_DIO_ADR); sio = io_base + TLAN_DIO_DATA + TLAN_NET_SIO; - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_SetBit( TLAN_NET_SIO_EDATA, sio ); - TLan_SetBit( TLAN_NET_SIO_ETXEN, sio ); - TLan_ClearBit( TLAN_NET_SIO_EDATA, sio ); - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); - -} /* TLan_EeSendStart */ - - - - - /*************************************************************** - * TLan_EeSendByte - * - * Returns: - * If the correct ack was received, 0, otherwise 1 - * Parms: io_base The IO port base address for the - * TLAN device with the EEPROM to - * use. - * data The 8 bits of information to - * send to the EEPROM. - * stop If TLAN_EEPROM_STOP is passed, a - * stop cycle is sent after the - * byte is sent after the ack is - * read. - * - * This function sends a byte on the serial EEPROM line, - * driving the clock to send each bit. The function then - * reverses transmission direction and reads an acknowledge - * bit. - * - **************************************************************/ - -static int TLan_EeSendByte( u16 io_base, u8 data, int stop ) + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_set_bit(TLAN_NET_SIO_EDATA, sio); + tlan_set_bit(TLAN_NET_SIO_ETXEN, sio); + tlan_clear_bit(TLAN_NET_SIO_EDATA, sio); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); + +} + + + + +/*************************************************************** + * tlan_ee_send_byte + * + * Returns: + * If the correct ack was received, 0, otherwise 1 + * Parms: io_base The IO port base address for the + * TLAN device with the EEPROM to + * use. + * data The 8 bits of information to + * send to the EEPROM. + * stop If TLAN_EEPROM_STOP is passed, a + * stop cycle is sent after the + * byte is sent after the ack is + * read. + * + * This function sends a byte on the serial EEPROM line, + * driving the clock to send each bit. The function then + * reverses transmission direction and reads an acknowledge + * bit. + * + **************************************************************/ + +static int tlan_ee_send_byte(u16 io_base, u8 data, int stop) { int err; u8 place; u16 sio; - outw( TLAN_NET_SIO, io_base + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, io_base + TLAN_DIO_ADR); sio = io_base + TLAN_DIO_DATA + TLAN_NET_SIO; /* Assume clock is low, tx is enabled; */ - for ( place = 0x80; place != 0; place >>= 1 ) { - if ( place & data ) - TLan_SetBit( TLAN_NET_SIO_EDATA, sio ); + for (place = 0x80; place != 0; place >>= 1) { + if (place & data) + tlan_set_bit(TLAN_NET_SIO_EDATA, sio); else - TLan_ClearBit( TLAN_NET_SIO_EDATA, sio ); - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); + tlan_clear_bit(TLAN_NET_SIO_EDATA, sio); + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); } - TLan_ClearBit( TLAN_NET_SIO_ETXEN, sio ); - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - err = TLan_GetBit( TLAN_NET_SIO_EDATA, sio ); - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_SetBit( TLAN_NET_SIO_ETXEN, sio ); + tlan_clear_bit(TLAN_NET_SIO_ETXEN, sio); + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + err = tlan_get_bit(TLAN_NET_SIO_EDATA, sio); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_set_bit(TLAN_NET_SIO_ETXEN, sio); - if ( ( ! err ) && stop ) { + if ((!err) && stop) { /* STOP, raise data while clock is high */ - TLan_ClearBit( TLAN_NET_SIO_EDATA, sio ); - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_SetBit( TLAN_NET_SIO_EDATA, sio ); + tlan_clear_bit(TLAN_NET_SIO_EDATA, sio); + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_set_bit(TLAN_NET_SIO_EDATA, sio); } return err; -} /* TLan_EeSendByte */ - - - - - /*************************************************************** - * TLan_EeReceiveByte - * - * Returns: - * Nothing - * Parms: - * io_base The IO port base address for the - * TLAN device with the EEPROM to - * use. - * data An address to a char to hold the - * data sent from the EEPROM. - * stop If TLAN_EEPROM_STOP is passed, a - * stop cycle is sent after the - * byte is received, and no ack is - * sent. - * - * This function receives 8 bits of data from the EEPROM - * over the serial link. It then sends and ack bit, or no - * ack and a stop bit. This function is used to retrieve - * data after the address of a byte in the EEPROM has been - * sent. - * - **************************************************************/ - -static void TLan_EeReceiveByte( u16 io_base, u8 *data, int stop ) +} + + + + +/*************************************************************** + * tlan_ee_receive_byte + * + * Returns: + * Nothing + * Parms: + * io_base The IO port base address for the + * TLAN device with the EEPROM to + * use. + * data An address to a char to hold the + * data sent from the EEPROM. + * stop If TLAN_EEPROM_STOP is passed, a + * stop cycle is sent after the + * byte is received, and no ack is + * sent. + * + * This function receives 8 bits of data from the EEPROM + * over the serial link. It then sends and ack bit, or no + * ack and a stop bit. This function is used to retrieve + * data after the address of a byte in the EEPROM has been + * sent. + * + **************************************************************/ + +static void tlan_ee_receive_byte(u16 io_base, u8 *data, int stop) { u8 place; u16 sio; - outw( TLAN_NET_SIO, io_base + TLAN_DIO_ADR ); + outw(TLAN_NET_SIO, io_base + TLAN_DIO_ADR); sio = io_base + TLAN_DIO_DATA + TLAN_NET_SIO; *data = 0; /* Assume clock is low, tx is enabled; */ - TLan_ClearBit( TLAN_NET_SIO_ETXEN, sio ); - for ( place = 0x80; place; place >>= 1 ) { - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - if ( TLan_GetBit( TLAN_NET_SIO_EDATA, sio ) ) + tlan_clear_bit(TLAN_NET_SIO_ETXEN, sio); + for (place = 0x80; place; place >>= 1) { + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + if (tlan_get_bit(TLAN_NET_SIO_EDATA, sio)) *data |= place; - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); } - TLan_SetBit( TLAN_NET_SIO_ETXEN, sio ); - if ( ! stop ) { - TLan_ClearBit( TLAN_NET_SIO_EDATA, sio ); /* Ack = 0 */ - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); + tlan_set_bit(TLAN_NET_SIO_ETXEN, sio); + if (!stop) { + tlan_clear_bit(TLAN_NET_SIO_EDATA, sio); /* ack = 0 */ + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); } else { - TLan_SetBit( TLAN_NET_SIO_EDATA, sio ); /* No ack = 1 (?) */ - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_ClearBit( TLAN_NET_SIO_ECLOK, sio ); + tlan_set_bit(TLAN_NET_SIO_EDATA, sio); /* no ack = 1 (?) */ + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_clear_bit(TLAN_NET_SIO_ECLOK, sio); /* STOP, raise data while clock is high */ - TLan_ClearBit( TLAN_NET_SIO_EDATA, sio ); - TLan_SetBit( TLAN_NET_SIO_ECLOK, sio ); - TLan_SetBit( TLAN_NET_SIO_EDATA, sio ); - } - -} /* TLan_EeReceiveByte */ - - - - - /*************************************************************** - * TLan_EeReadByte - * - * Returns: - * No error = 0, else, the stage at which the error - * occurred. - * Parms: - * io_base The IO port base address for the - * TLAN device with the EEPROM to - * use. - * ee_addr The address of the byte in the - * EEPROM whose contents are to be - * retrieved. - * data An address to a char to hold the - * data obtained from the EEPROM. - * - * This function reads a byte of information from an byte - * cell in the EEPROM. - * - **************************************************************/ - -static int TLan_EeReadByte( struct net_device *dev, u8 ee_addr, u8 *data ) + tlan_clear_bit(TLAN_NET_SIO_EDATA, sio); + tlan_set_bit(TLAN_NET_SIO_ECLOK, sio); + tlan_set_bit(TLAN_NET_SIO_EDATA, sio); + } + +} + + + + +/*************************************************************** + * tlan_ee_read_byte + * + * Returns: + * No error = 0, else, the stage at which the error + * occurred. + * Parms: + * io_base The IO port base address for the + * TLAN device with the EEPROM to + * use. + * ee_addr The address of the byte in the + * EEPROM whose contents are to be + * retrieved. + * data An address to a char to hold the + * data obtained from the EEPROM. + * + * This function reads a byte of information from an byte + * cell in the EEPROM. + * + **************************************************************/ + +static int tlan_ee_read_byte(struct net_device *dev, u8 ee_addr, u8 *data) { int err; - TLanPrivateInfo *priv = netdev_priv(dev); + struct tlan_priv *priv = netdev_priv(dev); unsigned long flags = 0; - int ret=0; + int ret = 0; spin_lock_irqsave(&priv->lock, flags); - TLan_EeSendStart( dev->base_addr ); - err = TLan_EeSendByte( dev->base_addr, 0xA0, TLAN_EEPROM_ACK ); - if (err) - { - ret=1; + tlan_ee_send_start(dev->base_addr); + err = tlan_ee_send_byte(dev->base_addr, 0xa0, TLAN_EEPROM_ACK); + if (err) { + ret = 1; goto fail; } - err = TLan_EeSendByte( dev->base_addr, ee_addr, TLAN_EEPROM_ACK ); - if (err) - { - ret=2; + err = tlan_ee_send_byte(dev->base_addr, ee_addr, TLAN_EEPROM_ACK); + if (err) { + ret = 2; goto fail; } - TLan_EeSendStart( dev->base_addr ); - err = TLan_EeSendByte( dev->base_addr, 0xA1, TLAN_EEPROM_ACK ); - if (err) - { - ret=3; + tlan_ee_send_start(dev->base_addr); + err = tlan_ee_send_byte(dev->base_addr, 0xa1, TLAN_EEPROM_ACK); + if (err) { + ret = 3; goto fail; } - TLan_EeReceiveByte( dev->base_addr, data, TLAN_EEPROM_STOP ); + tlan_ee_receive_byte(dev->base_addr, data, TLAN_EEPROM_STOP); fail: spin_unlock_irqrestore(&priv->lock, flags); return ret; -} /* TLan_EeReadByte */ +} diff --git a/drivers/net/tlan.h b/drivers/net/tlan.h index 3315ced..5fc98a8 100644 --- a/drivers/net/tlan.h +++ b/drivers/net/tlan.h @@ -20,8 +20,8 @@ ********************************************************************/ -#include <asm/io.h> -#include <asm/types.h> +#include <linux/io.h> +#include <linux/types.h> #include <linux/netdevice.h> @@ -40,8 +40,11 @@ #define TLAN_IGNORE 0 #define TLAN_RECORD 1 -#define TLAN_DBG(lvl, format, args...) \ - do { if (debug&lvl) printk(KERN_DEBUG "TLAN: " format, ##args ); } while(0) +#define TLAN_DBG(lvl, format, args...) \ + do { \ + if (debug&lvl) \ + printk(KERN_DEBUG "TLAN: " format, ##args); \ + } while (0) #define TLAN_DEBUG_GNRL 0x0001 #define TLAN_DEBUG_TX 0x0002 @@ -50,7 +53,8 @@ #define TLAN_DEBUG_PROBE 0x0010 #define TX_TIMEOUT (10*HZ) /* We need time for auto-neg */ -#define MAX_TLAN_BOARDS 8 /* Max number of boards installed at a time */ +#define MAX_TLAN_BOARDS 8 /* Max number of boards installed + at a time */ /***************************************************************** @@ -70,13 +74,13 @@ #define PCI_DEVICE_ID_OLICOM_OC2326 0x0014 #endif -typedef struct tlan_adapter_entry { - u16 vendorId; - u16 deviceId; - char *deviceLabel; +struct tlan_adapter_entry { + u16 vendor_id; + u16 device_id; + char *device_label; u32 flags; - u16 addrOfs; -} TLanAdapterEntry; + u16 addr_ofs; +}; #define TLAN_ADAPTER_NONE 0x00000000 #define TLAN_ADAPTER_UNMANAGED_PHY 0x00000001 @@ -129,18 +133,18 @@ typedef struct tlan_adapter_entry { #define TLAN_CSTAT_DP_PR 0x0100 -typedef struct tlan_buffer_ref_tag { +struct tlan_buffer { u32 count; u32 address; -} TLanBufferRef; +}; -typedef struct tlan_list_tag { +struct tlan_list { u32 forward; - u16 cStat; - u16 frameSize; - TLanBufferRef buffer[TLAN_BUFFERS_PER_LIST]; -} TLanList; + u16 c_stat; + u16 frame_size; + struct tlan_buffer buffer[TLAN_BUFFERS_PER_LIST]; +}; typedef u8 TLanBuffer[TLAN_MAX_FRAME_SIZE]; @@ -164,49 +168,49 @@ typedef u8 TLanBuffer[TLAN_MAX_FRAME_SIZE]; * ****************************************************************/ -typedef struct tlan_private_tag { - struct net_device *nextDevice; - struct pci_dev *pciDev; +struct tlan_priv { + struct net_device *next_device; + struct pci_dev *pci_dev; struct net_device *dev; - void *dmaStorage; - dma_addr_t dmaStorageDMA; - unsigned int dmaSize; - u8 *padBuffer; - TLanList *rxList; - dma_addr_t rxListDMA; - u8 *rxBuffer; - dma_addr_t rxBufferDMA; - u32 rxHead; - u32 rxTail; - u32 rxEocCount; - TLanList *txList; - dma_addr_t txListDMA; - u8 *txBuffer; - dma_addr_t txBufferDMA; - u32 txHead; - u32 txInProgress; - u32 txTail; - u32 txBusyCount; - u32 phyOnline; - u32 timerSetAt; - u32 timerType; + void *dma_storage; + dma_addr_t dma_storage_dma; + unsigned int dma_size; + u8 *pad_buffer; + struct tlan_list *rx_list; + dma_addr_t rx_list_dma; + u8 *rx_buffer; + dma_addr_t rx_buffer_dma; + u32 rx_head; + u32 rx_tail; + u32 rx_eoc_count; + struct tlan_list *tx_list; + dma_addr_t tx_list_dma; + u8 *tx_buffer; + dma_addr_t tx_buffer_dma; + u32 tx_head; + u32 tx_in_progress; + u32 tx_tail; + u32 tx_busy_count; + u32 phy_online; + u32 timer_set_at; + u32 timer_type; struct timer_list timer; struct board *adapter; - u32 adapterRev; + u32 adapter_rev; u32 aui; u32 debug; u32 duplex; u32 phy[2]; - u32 phyNum; + u32 phy_num; u32 speed; - u8 tlanRev; - u8 tlanFullDuplex; + u8 tlan_rev; + u8 tlan_full_duplex; spinlock_t lock; u8 link; u8 is_eisa; struct work_struct tlan_tqueue; u8 neg_be_verbose; -} TLanPrivateInfo; +}; @@ -247,7 +251,7 @@ typedef struct tlan_private_tag { ****************************************************************/ #define TLAN_HOST_CMD 0x00 -#define TLAN_HC_GO 0x80000000 +#define TLAN_HC_GO 0x80000000 #define TLAN_HC_STOP 0x40000000 #define TLAN_HC_ACK 0x20000000 #define TLAN_HC_CS_MASK 0x1FE00000 @@ -283,7 +287,7 @@ typedef struct tlan_private_tag { #define TLAN_NET_CMD_TRFRAM 0x02 #define TLAN_NET_CMD_TXPACE 0x01 #define TLAN_NET_SIO 0x01 -#define TLAN_NET_SIO_MINTEN 0x80 +#define TLAN_NET_SIO_MINTEN 0x80 #define TLAN_NET_SIO_ECLOK 0x40 #define TLAN_NET_SIO_ETXEN 0x20 #define TLAN_NET_SIO_EDATA 0x10 @@ -304,7 +308,7 @@ typedef struct tlan_private_tag { #define TLAN_NET_MASK_MASK4 0x10 #define TLAN_NET_MASK_RSRVD 0x0F #define TLAN_NET_CONFIG 0x04 -#define TLAN_NET_CFG_RCLK 0x8000 +#define TLAN_NET_CFG_RCLK 0x8000 #define TLAN_NET_CFG_TCLK 0x4000 #define TLAN_NET_CFG_BIT 0x2000 #define TLAN_NET_CFG_RXCRC 0x1000 @@ -372,7 +376,7 @@ typedef struct tlan_private_tag { /* Generic MII/PHY Registers */ #define MII_GEN_CTL 0x00 -#define MII_GC_RESET 0x8000 +#define MII_GC_RESET 0x8000 #define MII_GC_LOOPBK 0x4000 #define MII_GC_SPEEDSEL 0x2000 #define MII_GC_AUTOENB 0x1000 @@ -397,9 +401,9 @@ typedef struct tlan_private_tag { #define MII_GS_EXTCAP 0x0001 #define MII_GEN_ID_HI 0x02 #define MII_GEN_ID_LO 0x03 -#define MII_GIL_OUI 0xFC00 -#define MII_GIL_MODEL 0x03F0 -#define MII_GIL_REVISION 0x000F +#define MII_GIL_OUI 0xFC00 +#define MII_GIL_MODEL 0x03F0 +#define MII_GIL_REVISION 0x000F #define MII_AN_ADV 0x04 #define MII_AN_LPA 0x05 #define MII_AN_EXP 0x06 @@ -408,7 +412,7 @@ typedef struct tlan_private_tag { #define TLAN_TLPHY_ID 0x10 #define TLAN_TLPHY_CTL 0x11 -#define TLAN_TC_IGLINK 0x8000 +#define TLAN_TC_IGLINK 0x8000 #define TLAN_TC_SWAPOL 0x4000 #define TLAN_TC_AUISEL 0x2000 #define TLAN_TC_SQEEN 0x1000 @@ -435,41 +439,41 @@ typedef struct tlan_private_tag { #define LEVEL1_ID1 0x7810 #define LEVEL1_ID2 0x0000 -#define CIRC_INC( a, b ) if ( ++a >= b ) a = 0 +#define CIRC_INC(a, b) if (++a >= b) a = 0 /* Routines to access internal registers. */ -static inline u8 TLan_DioRead8(u16 base_addr, u16 internal_addr) +static inline u8 tlan_dio_read8(u16 base_addr, u16 internal_addr) { outw(internal_addr, base_addr + TLAN_DIO_ADR); return inb((base_addr + TLAN_DIO_DATA) + (internal_addr & 0x3)); -} /* TLan_DioRead8 */ +} -static inline u16 TLan_DioRead16(u16 base_addr, u16 internal_addr) +static inline u16 tlan_dio_read16(u16 base_addr, u16 internal_addr) { outw(internal_addr, base_addr + TLAN_DIO_ADR); return inw((base_addr + TLAN_DIO_DATA) + (internal_addr & 0x2)); -} /* TLan_DioRead16 */ +} -static inline u32 TLan_DioRead32(u16 base_addr, u16 internal_addr) +static inline u32 tlan_dio_read32(u16 base_addr, u16 internal_addr) { outw(internal_addr, base_addr + TLAN_DIO_ADR); return inl(base_addr + TLAN_DIO_DATA); -} /* TLan_DioRead32 */ +} -static inline void TLan_DioWrite8(u16 base_addr, u16 internal_addr, u8 data) +static inline void tlan_dio_write8(u16 base_addr, u16 internal_addr, u8 data) { outw(internal_addr, base_addr + TLAN_DIO_ADR); outb(data, base_addr + TLAN_DIO_DATA + (internal_addr & 0x3)); @@ -479,7 +483,7 @@ static inline void TLan_DioWrite8(u16 base_addr, u16 internal_addr, u8 data) -static inline void TLan_DioWrite16(u16 base_addr, u16 internal_addr, u16 data) +static inline void tlan_dio_write16(u16 base_addr, u16 internal_addr, u16 data) { outw(internal_addr, base_addr + TLAN_DIO_ADR); outw(data, base_addr + TLAN_DIO_DATA + (internal_addr & 0x2)); @@ -489,16 +493,16 @@ static inline void TLan_DioWrite16(u16 base_addr, u16 internal_addr, u16 data) -static inline void TLan_DioWrite32(u16 base_addr, u16 internal_addr, u32 data) +static inline void tlan_dio_write32(u16 base_addr, u16 internal_addr, u32 data) { outw(internal_addr, base_addr + TLAN_DIO_ADR); outl(data, base_addr + TLAN_DIO_DATA + (internal_addr & 0x2)); } -#define TLan_ClearBit( bit, port ) outb_p(inb_p(port) & ~bit, port) -#define TLan_GetBit( bit, port ) ((int) (inb_p(port) & bit)) -#define TLan_SetBit( bit, port ) outb_p(inb_p(port) | bit, port) +#define tlan_clear_bit(bit, port) outb_p(inb_p(port) & ~bit, port) +#define tlan_get_bit(bit, port) ((int) (inb_p(port) & bit)) +#define tlan_set_bit(bit, port) outb_p(inb_p(port) | bit, port) /* * given 6 bytes, view them as 8 6-bit numbers and return the XOR of those @@ -506,37 +510,37 @@ static inline void TLan_DioWrite32(u16 base_addr, u16 internal_addr, u32 data) * * The original code was: * - * u32 xor( u32 a, u32 b ) { return ( ( a && ! b ) || ( ! a && b ) ); } + * u32 xor(u32 a, u32 b) { return ((a && !b ) || (! a && b )); } * - * #define XOR8( a, b, c, d, e, f, g, h ) \ - * xor( a, xor( b, xor( c, xor( d, xor( e, xor( f, xor( g, h ) ) ) ) ) ) ) - * #define DA( a, bit ) ( ( (u8) a[bit/8] ) & ( (u8) ( 1 << bit%8 ) ) ) + * #define XOR8(a, b, c, d, e, f, g, h) \ + * xor(a, xor(b, xor(c, xor(d, xor(e, xor(f, xor(g, h)) ) ) ) ) ) + * #define DA(a, bit) (( (u8) a[bit/8] ) & ( (u8) (1 << bit%8)) ) * - * hash = XOR8( DA(a,0), DA(a, 6), DA(a,12), DA(a,18), DA(a,24), - * DA(a,30), DA(a,36), DA(a,42) ); - * hash |= XOR8( DA(a,1), DA(a, 7), DA(a,13), DA(a,19), DA(a,25), - * DA(a,31), DA(a,37), DA(a,43) ) << 1; - * hash |= XOR8( DA(a,2), DA(a, 8), DA(a,14), DA(a,20), DA(a,26), - * DA(a,32), DA(a,38), DA(a,44) ) << 2; - * hash |= XOR8( DA(a,3), DA(a, 9), DA(a,15), DA(a,21), DA(a,27), - * DA(a,33), DA(a,39), DA(a,45) ) << 3; - * hash |= XOR8( DA(a,4), DA(a,10), DA(a,16), DA(a,22), DA(a,28), - * DA(a,34), DA(a,40), DA(a,46) ) << 4; - * hash |= XOR8( DA(a,5), DA(a,11), DA(a,17), DA(a,23), DA(a,29), - * DA(a,35), DA(a,41), DA(a,47) ) << 5; + * hash = XOR8(DA(a,0), DA(a, 6), DA(a,12), DA(a,18), DA(a,24), + * DA(a,30), DA(a,36), DA(a,42)); + * hash |= XOR8(DA(a,1), DA(a, 7), DA(a,13), DA(a,19), DA(a,25), + * DA(a,31), DA(a,37), DA(a,43)) << 1; + * hash |= XOR8(DA(a,2), DA(a, 8), DA(a,14), DA(a,20), DA(a,26), + * DA(a,32), DA(a,38), DA(a,44)) << 2; + * hash |= XOR8(DA(a,3), DA(a, 9), DA(a,15), DA(a,21), DA(a,27), + * DA(a,33), DA(a,39), DA(a,45)) << 3; + * hash |= XOR8(DA(a,4), DA(a,10), DA(a,16), DA(a,22), DA(a,28), + * DA(a,34), DA(a,40), DA(a,46)) << 4; + * hash |= XOR8(DA(a,5), DA(a,11), DA(a,17), DA(a,23), DA(a,29), + * DA(a,35), DA(a,41), DA(a,47)) << 5; * */ -static inline u32 TLan_HashFunc( const u8 *a ) +static inline u32 tlan_hash_func(const u8 *a) { - u8 hash; + u8 hash; - hash = (a[0]^a[3]); /* & 077 */ - hash ^= ((a[0]^a[3])>>6); /* & 003 */ - hash ^= ((a[1]^a[4])<<2); /* & 074 */ - hash ^= ((a[1]^a[4])>>4); /* & 017 */ - hash ^= ((a[2]^a[5])<<4); /* & 060 */ - hash ^= ((a[2]^a[5])>>2); /* & 077 */ + hash = (a[0]^a[3]); /* & 077 */ + hash ^= ((a[0]^a[3])>>6); /* & 003 */ + hash ^= ((a[1]^a[4])<<2); /* & 074 */ + hash ^= ((a[1]^a[4])>>4); /* & 017 */ + hash ^= ((a[2]^a[5])<<4); /* & 060 */ + hash ^= ((a[2]^a[5])>>2); /* & 077 */ - return hash & 077; + return hash & 077; } #endif diff --git a/drivers/net/tun.c b/drivers/net/tun.c index b100bd5..55786a0 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -1142,7 +1142,7 @@ static int tun_get_iff(struct net *net, struct tun_struct *tun, * privs required. */ static int set_offload(struct net_device *dev, unsigned long arg) { - unsigned int old_features, features; + u32 old_features, features; old_features = dev->features; /* Unset features, set them as we chew on the arg. */ diff --git a/drivers/net/typhoon.c b/drivers/net/typhoon.c index a3c46f6..7fa5ec2 100644 --- a/drivers/net/typhoon.c +++ b/drivers/net/typhoon.c @@ -123,12 +123,11 @@ static const int multicast_filter_limit = 32; #include <linux/in6.h> #include <linux/dma-mapping.h> #include <linux/firmware.h> -#include <generated/utsrelease.h> #include "typhoon.h" MODULE_AUTHOR("David Dillow <dave@thedillows.org>"); -MODULE_VERSION(UTS_RELEASE); +MODULE_VERSION("1.0"); MODULE_LICENSE("GPL"); MODULE_FIRMWARE(FIRMWARE_NAME); MODULE_DESCRIPTION("3Com Typhoon Family (3C990, 3CR990, and variants)"); diff --git a/drivers/net/veth.c b/drivers/net/veth.c index cc83fa7..105d7f0 100644 --- a/drivers/net/veth.c +++ b/drivers/net/veth.c @@ -403,17 +403,6 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, if (tb[IFLA_ADDRESS] == NULL) random_ether_addr(dev->dev_addr); - if (tb[IFLA_IFNAME]) - nla_strlcpy(dev->name, tb[IFLA_IFNAME], IFNAMSIZ); - else - snprintf(dev->name, IFNAMSIZ, DRV_NAME "%%d"); - - if (strchr(dev->name, '%')) { - err = dev_alloc_name(dev, dev->name); - if (err < 0) - goto err_alloc_name; - } - err = register_netdevice(dev); if (err < 0) goto err_register_dev; @@ -433,7 +422,6 @@ static int veth_newlink(struct net *src_net, struct net_device *dev, err_register_dev: /* nothing to do */ -err_alloc_name: err_configure_peer: unregister_netdevice(peer); return err; diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c index 09cac70..0d6fec6 100644 --- a/drivers/net/via-velocity.c +++ b/drivers/net/via-velocity.c @@ -2923,6 +2923,7 @@ static u16 wol_calc_crc(int size, u8 *pattern, u8 *mask_pattern) static int velocity_set_wol(struct velocity_info *vptr) { struct mac_regs __iomem *regs = vptr->mac_regs; + enum speed_opt spd_dpx = vptr->options.spd_dpx; static u8 buf[256]; int i; @@ -2968,6 +2969,12 @@ static int velocity_set_wol(struct velocity_info *vptr) writew(0x0FFF, ®s->WOLSRClr); + if (spd_dpx == SPD_DPX_1000_FULL) + goto mac_done; + + if (spd_dpx != SPD_DPX_AUTO) + goto advertise_done; + if (vptr->mii_status & VELOCITY_AUTONEG_ENABLE) { if (PHYID_GET_PHY_ID(vptr->phy_id) == PHYID_CICADA_CS8201) MII_REG_BITS_ON(AUXCR_MDPPS, MII_NCONFIG, vptr->mac_regs); @@ -2978,6 +2985,7 @@ static int velocity_set_wol(struct velocity_info *vptr) if (vptr->mii_status & VELOCITY_SPEED_1000) MII_REG_BITS_ON(BMCR_ANRESTART, MII_BMCR, vptr->mac_regs); +advertise_done: BYTE_REG_BITS_ON(CHIPGCR_FCMODE, ®s->CHIPGCR); { @@ -2987,6 +2995,7 @@ static int velocity_set_wol(struct velocity_info *vptr) writeb(GCR, ®s->CHIPGCR); } +mac_done: BYTE_REG_BITS_OFF(ISR_PWEI, ®s->ISR); /* Turn on SWPTAG just before entering power mode */ BYTE_REG_BITS_ON(STICKHW_SWPTAG, ®s->STICKHW); diff --git a/drivers/net/via-velocity.h b/drivers/net/via-velocity.h index aa2e69b..d722753 100644 --- a/drivers/net/via-velocity.h +++ b/drivers/net/via-velocity.h @@ -361,7 +361,7 @@ enum velocity_owner { #define MAC_REG_CHIPGSR 0x9C #define MAC_REG_TESTCFG 0x9D #define MAC_REG_DEBUG 0x9E -#define MAC_REG_CHIPGCR 0x9F +#define MAC_REG_CHIPGCR 0x9F /* Chip Operation and Diagnostic Control */ #define MAC_REG_WOLCR0_SET 0xA0 #define MAC_REG_WOLCR1_SET 0xA1 #define MAC_REG_PWCFG_SET 0xA2 @@ -848,10 +848,10 @@ enum velocity_owner { * Bits in CHIPGCR register */ -#define CHIPGCR_FCGMII 0x80 /* enable GMII mode */ -#define CHIPGCR_FCFDX 0x40 +#define CHIPGCR_FCGMII 0x80 /* force GMII (else MII only) */ +#define CHIPGCR_FCFDX 0x40 /* force full duplex */ #define CHIPGCR_FCRESV 0x20 -#define CHIPGCR_FCMODE 0x10 +#define CHIPGCR_FCMODE 0x10 /* enable MAC forced mode */ #define CHIPGCR_LPSOPT 0x08 #define CHIPGCR_TM1US 0x04 #define CHIPGCR_TM0US 0x02 diff --git a/drivers/net/vxge/vxge-config.c b/drivers/net/vxge/vxge-config.c index 01c05f5..77097e3 100644 --- a/drivers/net/vxge/vxge-config.c +++ b/drivers/net/vxge/vxge-config.c @@ -387,8 +387,8 @@ vxge_hw_vpath_eprom_img_ver_get(struct __vxge_hw_device *hldev, data1 = steer_ctrl = 0; status = vxge_hw_vpath_fw_api(vpath, - VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO, VXGE_HW_FW_API_GET_EPROM_REV, + VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO, 0, &data0, &data1, &steer_ctrl); if (status != VXGE_HW_OK) break; @@ -2868,6 +2868,8 @@ __vxge_hw_ring_create(struct __vxge_hw_vpath_handle *vp, ring->rxd_init = attr->rxd_init; ring->rxd_term = attr->rxd_term; ring->buffer_mode = config->buffer_mode; + ring->tim_rti_cfg1_saved = vp->vpath->tim_rti_cfg1_saved; + ring->tim_rti_cfg3_saved = vp->vpath->tim_rti_cfg3_saved; ring->rxds_limit = config->rxds_limit; ring->rxd_size = vxge_hw_ring_rxd_size_get(config->buffer_mode); @@ -3511,6 +3513,8 @@ __vxge_hw_fifo_create(struct __vxge_hw_vpath_handle *vp, /* apply "interrupts per txdl" attribute */ fifo->interrupt_type = VXGE_HW_FIFO_TXD_INT_TYPE_UTILZ; + fifo->tim_tti_cfg1_saved = vpath->tim_tti_cfg1_saved; + fifo->tim_tti_cfg3_saved = vpath->tim_tti_cfg3_saved; if (fifo->config->intr) fifo->interrupt_type = VXGE_HW_FIFO_TXD_INT_TYPE_PER_LIST; @@ -4377,6 +4381,8 @@ __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id) } writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]); + vpath->tim_tti_cfg1_saved = val64; + val64 = readq(&vp_reg->tim_cfg2_int_num[VXGE_HW_VPATH_INTR_TX]); if (config->tti.uec_a != VXGE_HW_USE_FLASH_DEFAULT) { @@ -4433,6 +4439,7 @@ __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id) } writeq(val64, &vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_TX]); + vpath->tim_tti_cfg3_saved = val64; } if (config->ring.enable == VXGE_HW_RING_ENABLE) { @@ -4481,6 +4488,8 @@ __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id) } writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_RX]); + vpath->tim_rti_cfg1_saved = val64; + val64 = readq(&vp_reg->tim_cfg2_int_num[VXGE_HW_VPATH_INTR_RX]); if (config->rti.uec_a != VXGE_HW_USE_FLASH_DEFAULT) { @@ -4537,6 +4546,7 @@ __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id) } writeq(val64, &vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_RX]); + vpath->tim_rti_cfg3_saved = val64; } val64 = 0; @@ -4555,26 +4565,6 @@ __vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id) return status; } -void vxge_hw_vpath_tti_ci_set(struct __vxge_hw_device *hldev, u32 vp_id) -{ - struct __vxge_hw_virtualpath *vpath; - struct vxge_hw_vpath_reg __iomem *vp_reg; - struct vxge_hw_vp_config *config; - u64 val64; - - vpath = &hldev->virtual_paths[vp_id]; - vp_reg = vpath->vp_reg; - config = vpath->vp_config; - - if (config->fifo.enable == VXGE_HW_FIFO_ENABLE && - config->tti.timer_ci_en != VXGE_HW_TIM_TIMER_CI_ENABLE) { - config->tti.timer_ci_en = VXGE_HW_TIM_TIMER_CI_ENABLE; - val64 = readq(&vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]); - val64 |= VXGE_HW_TIM_CFG1_INT_NUM_TIMER_CI; - writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]); - } -} - /* * __vxge_hw_vpath_initialize * This routine is the final phase of init which initializes the diff --git a/drivers/net/vxge/vxge-config.h b/drivers/net/vxge/vxge-config.h index e249e28..3c53aa7 100644 --- a/drivers/net/vxge/vxge-config.h +++ b/drivers/net/vxge/vxge-config.h @@ -682,6 +682,10 @@ struct __vxge_hw_virtualpath { u32 vsport_number; u32 max_kdfc_db; u32 max_nofl_db; + u64 tim_tti_cfg1_saved; + u64 tim_tti_cfg3_saved; + u64 tim_rti_cfg1_saved; + u64 tim_rti_cfg3_saved; struct __vxge_hw_ring *____cacheline_aligned ringh; struct __vxge_hw_fifo *____cacheline_aligned fifoh; @@ -921,6 +925,9 @@ struct __vxge_hw_ring { u32 doorbell_cnt; u32 total_db_cnt; u64 rxds_limit; + u32 rtimer; + u64 tim_rti_cfg1_saved; + u64 tim_rti_cfg3_saved; enum vxge_hw_status (*callback)( struct __vxge_hw_ring *ringh, @@ -1000,6 +1007,9 @@ struct __vxge_hw_fifo { u32 per_txdl_space; u32 vp_id; u32 tx_intr_num; + u32 rtimer; + u64 tim_tti_cfg1_saved; + u64 tim_tti_cfg3_saved; enum vxge_hw_status (*callback)( struct __vxge_hw_fifo *fifo_handle, diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c index c81a651..e40f619 100644 --- a/drivers/net/vxge/vxge-main.c +++ b/drivers/net/vxge/vxge-main.c @@ -371,9 +371,6 @@ vxge_rx_1b_compl(struct __vxge_hw_ring *ringh, void *dtr, struct vxge_hw_ring_rxd_info ext_info; vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d", ring->ndev->name, __func__, __LINE__); - ring->pkts_processed = 0; - - vxge_hw_ring_replenish(ringh); do { prefetch((char *)dtr + L1_CACHE_BYTES); @@ -1588,6 +1585,36 @@ static int vxge_reset_vpath(struct vxgedev *vdev, int vp_id) return ret; } +/* Configure CI */ +static void vxge_config_ci_for_tti_rti(struct vxgedev *vdev) +{ + int i = 0; + + /* Enable CI for RTI */ + if (vdev->config.intr_type == MSI_X) { + for (i = 0; i < vdev->no_of_vpath; i++) { + struct __vxge_hw_ring *hw_ring; + + hw_ring = vdev->vpaths[i].ring.handle; + vxge_hw_vpath_dynamic_rti_ci_set(hw_ring); + } + } + + /* Enable CI for TTI */ + for (i = 0; i < vdev->no_of_vpath; i++) { + struct __vxge_hw_fifo *hw_fifo = vdev->vpaths[i].fifo.handle; + vxge_hw_vpath_tti_ci_set(hw_fifo); + /* + * For Inta (with or without napi), Set CI ON for only one + * vpath. (Have only one free running timer). + */ + if ((vdev->config.intr_type == INTA) && (i == 0)) + break; + } + + return; +} + static int do_vxge_reset(struct vxgedev *vdev, int event) { enum vxge_hw_status status; @@ -1753,6 +1780,9 @@ static int do_vxge_reset(struct vxgedev *vdev, int event) netif_tx_wake_all_queues(vdev->ndev); } + /* configure CI */ + vxge_config_ci_for_tti_rti(vdev); + out: vxge_debug_entryexit(VXGE_TRACE, "%s:%d Exiting...", __func__, __LINE__); @@ -1793,22 +1823,29 @@ static void vxge_reset(struct work_struct *work) */ static int vxge_poll_msix(struct napi_struct *napi, int budget) { - struct vxge_ring *ring = - container_of(napi, struct vxge_ring, napi); + struct vxge_ring *ring = container_of(napi, struct vxge_ring, napi); + int pkts_processed; int budget_org = budget; - ring->budget = budget; + ring->budget = budget; + ring->pkts_processed = 0; vxge_hw_vpath_poll_rx(ring->handle); + pkts_processed = ring->pkts_processed; if (ring->pkts_processed < budget_org) { napi_complete(napi); + /* Re enable the Rx interrupts for the vpath */ vxge_hw_channel_msix_unmask( (struct __vxge_hw_channel *)ring->handle, ring->rx_vector_no); + mmiowb(); } - return ring->pkts_processed; + /* We are copying and returning the local variable, in case if after + * clearing the msix interrupt above, if the interrupt fires right + * away which can preempt this NAPI thread */ + return pkts_processed; } static int vxge_poll_inta(struct napi_struct *napi, int budget) @@ -1824,6 +1861,7 @@ static int vxge_poll_inta(struct napi_struct *napi, int budget) for (i = 0; i < vdev->no_of_vpath; i++) { ring = &vdev->vpaths[i].ring; ring->budget = budget; + ring->pkts_processed = 0; vxge_hw_vpath_poll_rx(ring->handle); pkts_processed += ring->pkts_processed; budget -= ring->pkts_processed; @@ -2054,6 +2092,7 @@ static int vxge_open_vpaths(struct vxgedev *vdev) netdev_get_tx_queue(vdev->ndev, 0); vpath->fifo.indicate_max_pkts = vdev->config.fifo_indicate_max_pkts; + vpath->fifo.tx_vector_no = 0; vpath->ring.rx_vector_no = 0; vpath->ring.rx_csum = vdev->rx_csum; vpath->ring.rx_hwts = vdev->rx_hwts; @@ -2079,6 +2118,61 @@ static int vxge_open_vpaths(struct vxgedev *vdev) return VXGE_HW_OK; } +/** + * adaptive_coalesce_tx_interrupts - Changes the interrupt coalescing + * if the interrupts are not within a range + * @fifo: pointer to transmit fifo structure + * Description: The function changes boundary timer and restriction timer + * value depends on the traffic + * Return Value: None + */ +static void adaptive_coalesce_tx_interrupts(struct vxge_fifo *fifo) +{ + fifo->interrupt_count++; + if (jiffies > fifo->jiffies + HZ / 100) { + struct __vxge_hw_fifo *hw_fifo = fifo->handle; + + fifo->jiffies = jiffies; + if (fifo->interrupt_count > VXGE_T1A_MAX_TX_INTERRUPT_COUNT && + hw_fifo->rtimer != VXGE_TTI_RTIMER_ADAPT_VAL) { + hw_fifo->rtimer = VXGE_TTI_RTIMER_ADAPT_VAL; + vxge_hw_vpath_dynamic_tti_rtimer_set(hw_fifo); + } else if (hw_fifo->rtimer != 0) { + hw_fifo->rtimer = 0; + vxge_hw_vpath_dynamic_tti_rtimer_set(hw_fifo); + } + fifo->interrupt_count = 0; + } +} + +/** + * adaptive_coalesce_rx_interrupts - Changes the interrupt coalescing + * if the interrupts are not within a range + * @ring: pointer to receive ring structure + * Description: The function increases of decreases the packet counts within + * the ranges of traffic utilization, if the interrupts due to this ring are + * not within a fixed range. + * Return Value: Nothing + */ +static void adaptive_coalesce_rx_interrupts(struct vxge_ring *ring) +{ + ring->interrupt_count++; + if (jiffies > ring->jiffies + HZ / 100) { + struct __vxge_hw_ring *hw_ring = ring->handle; + + ring->jiffies = jiffies; + if (ring->interrupt_count > VXGE_T1A_MAX_INTERRUPT_COUNT && + hw_ring->rtimer != VXGE_RTI_RTIMER_ADAPT_VAL) { + hw_ring->rtimer = VXGE_RTI_RTIMER_ADAPT_VAL; + vxge_hw_vpath_dynamic_rti_rtimer_set(hw_ring); + } else if (hw_ring->rtimer != 0) { + hw_ring->rtimer = 0; + vxge_hw_vpath_dynamic_rti_rtimer_set(hw_ring); + } + ring->interrupt_count = 0; + } +} + /* * vxge_isr_napi * @irq: the irq of the device. @@ -2139,24 +2233,39 @@ static irqreturn_t vxge_isr_napi(int irq, void *dev_id) #ifdef CONFIG_PCI_MSI -static irqreturn_t -vxge_tx_msix_handle(int irq, void *dev_id) +static irqreturn_t vxge_tx_msix_handle(int irq, void *dev_id) { struct vxge_fifo *fifo = (struct vxge_fifo *)dev_id; + adaptive_coalesce_tx_interrupts(fifo); + + vxge_hw_channel_msix_mask((struct __vxge_hw_channel *)fifo->handle, + fifo->tx_vector_no); + + vxge_hw_channel_msix_clear((struct __vxge_hw_channel *)fifo->handle, + fifo->tx_vector_no); + VXGE_COMPLETE_VPATH_TX(fifo); + vxge_hw_channel_msix_unmask((struct __vxge_hw_channel *)fifo->handle, + fifo->tx_vector_no); + + mmiowb(); + return IRQ_HANDLED; } -static irqreturn_t -vxge_rx_msix_napi_handle(int irq, void *dev_id) +static irqreturn_t vxge_rx_msix_napi_handle(int irq, void *dev_id) { struct vxge_ring *ring = (struct vxge_ring *)dev_id; - /* MSIX_IDX for Rx is 1 */ + adaptive_coalesce_rx_interrupts(ring); + vxge_hw_channel_msix_mask((struct __vxge_hw_channel *)ring->handle, - ring->rx_vector_no); + ring->rx_vector_no); + + vxge_hw_channel_msix_clear((struct __vxge_hw_channel *)ring->handle, + ring->rx_vector_no); napi_schedule(&ring->napi); return IRQ_HANDLED; @@ -2173,14 +2282,20 @@ vxge_alarm_msix_handle(int irq, void *dev_id) VXGE_HW_VPATH_MSIX_ACTIVE) + VXGE_ALARM_MSIX_ID; for (i = 0; i < vdev->no_of_vpath; i++) { + /* Reduce the chance of loosing alarm interrupts by masking + * the vector. A pending bit will be set if an alarm is + * generated and on unmask the interrupt will be fired. + */ vxge_hw_vpath_msix_mask(vdev->vpaths[i].handle, msix_id); + vxge_hw_vpath_msix_clear(vdev->vpaths[i].handle, msix_id); + mmiowb(); status = vxge_hw_vpath_alarm_process(vdev->vpaths[i].handle, vdev->exec_mode); if (status == VXGE_HW_OK) { - vxge_hw_vpath_msix_unmask(vdev->vpaths[i].handle, - msix_id); + msix_id); + mmiowb(); continue; } vxge_debug_intr(VXGE_ERR, @@ -2299,6 +2414,9 @@ static int vxge_enable_msix(struct vxgedev *vdev) vpath->ring.rx_vector_no = (vpath->device_id * VXGE_HW_VPATH_MSIX_ACTIVE) + 1; + vpath->fifo.tx_vector_no = (vpath->device_id * + VXGE_HW_VPATH_MSIX_ACTIVE); + vxge_hw_vpath_msix_set(vpath->handle, tim_msix_id, VXGE_ALARM_MSIX_ID); } @@ -2474,8 +2592,9 @@ INTA_MODE: "%s:vxge:INTA", vdev->ndev->name); vxge_hw_device_set_intr_type(vdev->devh, VXGE_HW_INTR_MODE_IRQLINE); - vxge_hw_vpath_tti_ci_set(vdev->devh, - vdev->vpaths[0].device_id); + + vxge_hw_vpath_tti_ci_set(vdev->vpaths[0].fifo.handle); + ret = request_irq((int) vdev->pdev->irq, vxge_isr_napi, IRQF_SHARED, vdev->desc[0], vdev); @@ -2745,6 +2864,10 @@ static int vxge_open(struct net_device *dev) } netif_tx_start_all_queues(vdev->ndev); + + /* configure CI */ + vxge_config_ci_for_tti_rti(vdev); + goto out0; out2: @@ -3348,7 +3471,7 @@ static int __devinit vxge_device_register(struct __vxge_hw_device *hldev, vxge_debug_init(VXGE_ERR, "%s: vpath memory allocation failed", vdev->ndev->name); - ret = -ENODEV; + ret = -ENOMEM; goto _out1; } @@ -3369,11 +3492,11 @@ static int __devinit vxge_device_register(struct __vxge_hw_device *hldev, if (vdev->config.gro_enable) ndev->features |= NETIF_F_GRO; - if (register_netdev(ndev)) { + ret = register_netdev(ndev); + if (ret) { vxge_debug_init(vxge_hw_device_trace_level_get(hldev), "%s: %s : device registration failed!", ndev->name, __func__); - ret = -ENODEV; goto _out2; } @@ -3444,6 +3567,11 @@ static void vxge_device_unregister(struct __vxge_hw_device *hldev) /* in 2.6 will call stop() if device is up */ unregister_netdev(dev); + kfree(vdev->vpaths); + + /* we are safe to free it now */ + free_netdev(dev); + vxge_debug_init(vdev->level_trace, "%s: ethernet device unregistered", buf); vxge_debug_entryexit(vdev->level_trace, "%s: %s:%d Exiting...", buf, @@ -3799,7 +3927,7 @@ static void __devinit vxge_device_config_init( break; case MSI_X: - device_config->intr_mode = VXGE_HW_INTR_MODE_MSIX; + device_config->intr_mode = VXGE_HW_INTR_MODE_MSIX_ONE_SHOT; break; } @@ -4335,10 +4463,10 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre) goto _exit1; } - if (pci_request_region(pdev, 0, VXGE_DRIVER_NAME)) { + ret = pci_request_region(pdev, 0, VXGE_DRIVER_NAME); + if (ret) { vxge_debug_init(VXGE_ERR, "%s : request regions failed", __func__); - ret = -ENODEV; goto _exit1; } @@ -4446,7 +4574,7 @@ vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre) if (!img[i].is_valid) break; vxge_debug_init(VXGE_TRACE, "%s: EPROM %d, version " - "%d.%d.%d.%d\n", VXGE_DRIVER_NAME, i, + "%d.%d.%d.%d", VXGE_DRIVER_NAME, i, VXGE_EPROM_IMG_MAJOR(img[i].version), VXGE_EPROM_IMG_MINOR(img[i].version), VXGE_EPROM_IMG_FIX(img[i].version), @@ -4643,8 +4771,9 @@ _exit6: _exit5: vxge_device_unregister(hldev); _exit4: - pci_disable_sriov(pdev); + pci_set_drvdata(pdev, NULL); vxge_hw_device_terminate(hldev); + pci_disable_sriov(pdev); _exit3: iounmap(attr.bar0); _exit2: @@ -4655,7 +4784,7 @@ _exit0: kfree(ll_config); kfree(device_config); driver_config->config_dev_cnt--; - pci_set_drvdata(pdev, NULL); + driver_config->total_dev_cnt--; return ret; } @@ -4668,45 +4797,34 @@ _exit0: static void __devexit vxge_remove(struct pci_dev *pdev) { struct __vxge_hw_device *hldev; - struct vxgedev *vdev = NULL; - struct net_device *dev; - int i = 0; + struct vxgedev *vdev; + int i; hldev = pci_get_drvdata(pdev); - if (hldev == NULL) return; - dev = hldev->ndev; - vdev = netdev_priv(dev); + vdev = netdev_priv(hldev->ndev); vxge_debug_entryexit(vdev->level_trace, "%s:%d", __func__, __LINE__); - vxge_debug_init(vdev->level_trace, "%s : removing PCI device...", __func__); - vxge_device_unregister(hldev); - for (i = 0; i < vdev->no_of_vpath; i++) { + for (i = 0; i < vdev->no_of_vpath; i++) vxge_free_mac_add_list(&vdev->vpaths[i]); - vdev->vpaths[i].mcast_addr_cnt = 0; - vdev->vpaths[i].mac_addr_cnt = 0; - } - - kfree(vdev->vpaths); + vxge_device_unregister(hldev); + pci_set_drvdata(pdev, NULL); + /* Do not call pci_disable_sriov here, as it will break child devices */ + vxge_hw_device_terminate(hldev); iounmap(vdev->bar0); - - /* we are safe to free it now */ - free_netdev(dev); + pci_release_region(pdev, 0); + pci_disable_device(pdev); + driver_config->config_dev_cnt--; + driver_config->total_dev_cnt--; vxge_debug_init(vdev->level_trace, "%s:%d Device unregistered", __func__, __LINE__); - - vxge_hw_device_terminate(hldev); - - pci_disable_device(pdev); - pci_release_region(pdev, 0); - pci_set_drvdata(pdev, NULL); vxge_debug_entryexit(vdev->level_trace, "%s:%d Exiting...", __func__, __LINE__); } diff --git a/drivers/net/vxge/vxge-main.h b/drivers/net/vxge/vxge-main.h index 5746fed..40474f0 100644 --- a/drivers/net/vxge/vxge-main.h +++ b/drivers/net/vxge/vxge-main.h @@ -59,11 +59,13 @@ #define VXGE_TTI_LTIMER_VAL 1000 #define VXGE_T1A_TTI_LTIMER_VAL 80 #define VXGE_TTI_RTIMER_VAL 0 +#define VXGE_TTI_RTIMER_ADAPT_VAL 10 #define VXGE_T1A_TTI_RTIMER_VAL 400 #define VXGE_RTI_BTIMER_VAL 250 #define VXGE_RTI_LTIMER_VAL 100 #define VXGE_RTI_RTIMER_VAL 0 -#define VXGE_FIFO_INDICATE_MAX_PKTS VXGE_DEF_FIFO_LENGTH +#define VXGE_RTI_RTIMER_ADAPT_VAL 15 +#define VXGE_FIFO_INDICATE_MAX_PKTS VXGE_DEF_FIFO_LENGTH #define VXGE_ISR_POLLING_CNT 8 #define VXGE_MAX_CONFIG_DEV 0xFF #define VXGE_EXEC_MODE_DISABLE 0 @@ -107,6 +109,14 @@ #define RTI_T1A_RX_UFC_C 50 #define RTI_T1A_RX_UFC_D 60 +/* + * The interrupt rate is maintained at 3k per second with the moderation + * parameters for most traffic but not all. This is the maximum interrupt + * count allowed per function with INTA or per vector in the case of + * MSI-X in a 10 millisecond time period. Enabled only for Titan 1A. + */ +#define VXGE_T1A_MAX_INTERRUPT_COUNT 100 +#define VXGE_T1A_MAX_TX_INTERRUPT_COUNT 200 /* Milli secs timer period */ #define VXGE_TIMER_DELAY 10000 @@ -247,6 +257,11 @@ struct vxge_fifo { int tx_steering_type; int indicate_max_pkts; + /* Adaptive interrupt moderation parameters used in T1A */ + unsigned long interrupt_count; + unsigned long jiffies; + + u32 tx_vector_no; /* Tx stats */ struct vxge_fifo_stats stats; } ____cacheline_aligned; @@ -271,6 +286,10 @@ struct vxge_ring { */ int driver_id; + /* Adaptive interrupt moderation parameters used in T1A */ + unsigned long interrupt_count; + unsigned long jiffies; + /* copy of the flag indicating whether rx_csum is to be used */ u32 rx_csum:1, rx_hwts:1; @@ -286,7 +305,7 @@ struct vxge_ring { int vlan_tag_strip; struct vlan_group *vlgrp; - int rx_vector_no; + u32 rx_vector_no; enum vxge_hw_status last_status; /* Rx stats */ diff --git a/drivers/net/vxge/vxge-traffic.c b/drivers/net/vxge/vxge-traffic.c index 4c10d6c..8674f33 100644 --- a/drivers/net/vxge/vxge-traffic.c +++ b/drivers/net/vxge/vxge-traffic.c @@ -218,6 +218,68 @@ exit: return status; } +void vxge_hw_vpath_tti_ci_set(struct __vxge_hw_fifo *fifo) +{ + struct vxge_hw_vpath_reg __iomem *vp_reg; + struct vxge_hw_vp_config *config; + u64 val64; + + if (fifo->config->enable != VXGE_HW_FIFO_ENABLE) + return; + + vp_reg = fifo->vp_reg; + config = container_of(fifo->config, struct vxge_hw_vp_config, fifo); + + if (config->tti.timer_ci_en != VXGE_HW_TIM_TIMER_CI_ENABLE) { + config->tti.timer_ci_en = VXGE_HW_TIM_TIMER_CI_ENABLE; + val64 = readq(&vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]); + val64 |= VXGE_HW_TIM_CFG1_INT_NUM_TIMER_CI; + fifo->tim_tti_cfg1_saved = val64; + writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]); + } +} + +void vxge_hw_vpath_dynamic_rti_ci_set(struct __vxge_hw_ring *ring) +{ + u64 val64 = ring->tim_rti_cfg1_saved; + + val64 |= VXGE_HW_TIM_CFG1_INT_NUM_TIMER_CI; + ring->tim_rti_cfg1_saved = val64; + writeq(val64, &ring->vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_RX]); +} + +void vxge_hw_vpath_dynamic_tti_rtimer_set(struct __vxge_hw_fifo *fifo) +{ + u64 val64 = fifo->tim_tti_cfg3_saved; + u64 timer = (fifo->rtimer * 1000) / 272; + + val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(0x3ffffff); + if (timer) + val64 |= VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(timer) | + VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_EVENT_SF(5); + + writeq(val64, &fifo->vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_TX]); + /* tti_cfg3_saved is not updated again because it is + * initialized at one place only - init time. + */ +} + +void vxge_hw_vpath_dynamic_rti_rtimer_set(struct __vxge_hw_ring *ring) +{ + u64 val64 = ring->tim_rti_cfg3_saved; + u64 timer = (ring->rtimer * 1000) / 272; + + val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(0x3ffffff); + if (timer) + val64 |= VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(timer) | + VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_EVENT_SF(4); + + writeq(val64, &ring->vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_RX]); + /* rti_cfg3_saved is not updated again because it is + * initialized at one place only - init time. + */ +} + /** * vxge_hw_channel_msix_mask - Mask MSIX Vector. * @channeh: Channel for rx or tx handle @@ -254,6 +316,23 @@ vxge_hw_channel_msix_unmask(struct __vxge_hw_channel *channel, int msix_id) } /** + * vxge_hw_channel_msix_clear - Unmask the MSIX Vector. + * @channel: Channel for rx or tx handle + * @msix_id: MSI ID + * + * The function unmasks the msix interrupt for the given msix_id + * if configured in MSIX oneshot mode + * + * Returns: 0 + */ +void vxge_hw_channel_msix_clear(struct __vxge_hw_channel *channel, int msix_id) +{ + __vxge_hw_pio_mem_write32_upper( + (u32) vxge_bVALn(vxge_mBIT(msix_id >> 2), 0, 32), + &channel->common_reg->clr_msix_one_shot_vec[msix_id % 4]); +} + +/** * vxge_hw_device_set_intr_type - Updates the configuration * with new interrupt type. * @hldev: HW device handle. @@ -2191,19 +2270,14 @@ vxge_hw_vpath_msix_set(struct __vxge_hw_vpath_handle *vp, int *tim_msix_id, if (vpath->hldev->config.intr_mode == VXGE_HW_INTR_MODE_MSIX_ONE_SHOT) { __vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn( + VXGE_HW_ONE_SHOT_VECT0_EN_ONE_SHOT_VECT0_EN, + 0, 32), &vp_reg->one_shot_vect0_en); + __vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn( VXGE_HW_ONE_SHOT_VECT1_EN_ONE_SHOT_VECT1_EN, 0, 32), &vp_reg->one_shot_vect1_en); - } - - if (vpath->hldev->config.intr_mode == - VXGE_HW_INTR_MODE_MSIX_ONE_SHOT) { __vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn( VXGE_HW_ONE_SHOT_VECT2_EN_ONE_SHOT_VECT2_EN, 0, 32), &vp_reg->one_shot_vect2_en); - - __vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn( - VXGE_HW_ONE_SHOT_VECT3_EN_ONE_SHOT_VECT3_EN, - 0, 32), &vp_reg->one_shot_vect3_en); } } @@ -2229,6 +2303,32 @@ vxge_hw_vpath_msix_mask(struct __vxge_hw_vpath_handle *vp, int msix_id) } /** + * vxge_hw_vpath_msix_clear - Clear MSIX Vector. + * @vp: Virtual Path handle. + * @msix_id: MSI ID + * + * The function clears the msix interrupt for the given msix_id + * + * Returns: 0, + * Otherwise, VXGE_HW_ERR_WRONG_IRQ if the msix index is out of range + * status. + * See also: + */ +void vxge_hw_vpath_msix_clear(struct __vxge_hw_vpath_handle *vp, int msix_id) +{ + struct __vxge_hw_device *hldev = vp->vpath->hldev; + + if ((hldev->config.intr_mode == VXGE_HW_INTR_MODE_MSIX_ONE_SHOT)) + __vxge_hw_pio_mem_write32_upper( + (u32) vxge_bVALn(vxge_mBIT((msix_id >> 2)), 0, 32), + &hldev->common_reg->clr_msix_one_shot_vec[msix_id % 4]); + else + __vxge_hw_pio_mem_write32_upper( + (u32) vxge_bVALn(vxge_mBIT((msix_id >> 2)), 0, 32), + &hldev->common_reg->clear_msix_mask_vect[msix_id % 4]); +} + +/** * vxge_hw_vpath_msix_unmask - Unmask the MSIX Vector. * @vp: Virtual Path handle. * @msix_id: MSI ID diff --git a/drivers/net/vxge/vxge-traffic.h b/drivers/net/vxge/vxge-traffic.h index d48486d..9d9dfda 100644 --- a/drivers/net/vxge/vxge-traffic.h +++ b/drivers/net/vxge/vxge-traffic.h @@ -2142,6 +2142,10 @@ void vxge_hw_device_clear_tx_rx( * Virtual Paths */ +void vxge_hw_vpath_dynamic_rti_rtimer_set(struct __vxge_hw_ring *ring); + +void vxge_hw_vpath_dynamic_tti_rtimer_set(struct __vxge_hw_fifo *fifo); + u32 vxge_hw_vpath_id( struct __vxge_hw_vpath_handle *vpath_handle); @@ -2245,6 +2249,8 @@ void vxge_hw_vpath_msix_mask(struct __vxge_hw_vpath_handle *vpath_handle, int msix_id); +void vxge_hw_vpath_msix_clear(struct __vxge_hw_vpath_handle *vp, int msix_id); + void vxge_hw_device_flush_io(struct __vxge_hw_device *devh); void @@ -2270,6 +2276,9 @@ void vxge_hw_channel_msix_unmask(struct __vxge_hw_channel *channelh, int msix_id); void +vxge_hw_channel_msix_clear(struct __vxge_hw_channel *channelh, int msix_id); + +void vxge_hw_channel_dtr_try_complete(struct __vxge_hw_channel *channel, void **dtrh); @@ -2282,7 +2291,8 @@ vxge_hw_channel_dtr_free(struct __vxge_hw_channel *channel, void *dtrh); int vxge_hw_channel_dtr_count(struct __vxge_hw_channel *channel); -void -vxge_hw_vpath_tti_ci_set(struct __vxge_hw_device *hldev, u32 vp_id); +void vxge_hw_vpath_tti_ci_set(struct __vxge_hw_fifo *fifo); + +void vxge_hw_vpath_dynamic_rti_ci_set(struct __vxge_hw_ring *ring); #endif diff --git a/drivers/net/vxge/vxge-version.h b/drivers/net/vxge/vxge-version.h index ad2f99b..581e215 100644 --- a/drivers/net/vxge/vxge-version.h +++ b/drivers/net/vxge/vxge-version.h @@ -16,8 +16,8 @@ #define VXGE_VERSION_MAJOR "2" #define VXGE_VERSION_MINOR "5" -#define VXGE_VERSION_FIX "1" -#define VXGE_VERSION_BUILD "22082" +#define VXGE_VERSION_FIX "2" +#define VXGE_VERSION_BUILD "22259" #define VXGE_VERSION_FOR "k" #define VXGE_FW_VER(maj, min, bld) (((maj) << 16) + ((min) << 8) + (bld)) diff --git a/drivers/net/wireless/ath/ar9170/main.c b/drivers/net/wireless/ath/ar9170/main.c index 32bf79e..a9111e1 100644 --- a/drivers/net/wireless/ath/ar9170/main.c +++ b/drivers/net/wireless/ath/ar9170/main.c @@ -1945,7 +1945,8 @@ static int ar9170_conf_tx(struct ieee80211_hw *hw, u16 queue, static int ar9170_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { switch (action) { case IEEE80211_AMPDU_RX_START: diff --git a/drivers/net/wireless/ath/ath.h b/drivers/net/wireless/ath/ath.h index e43210c..a6c6a46 100644 --- a/drivers/net/wireless/ath/ath.h +++ b/drivers/net/wireless/ath/ath.h @@ -108,12 +108,14 @@ enum ath_cipher { * struct ath_ops - Register read/write operations * * @read: Register read + * @multi_read: Multiple register read * @write: Register write * @enable_write_buffer: Enable multiple register writes * @write_flush: flush buffered register writes and disable buffering */ struct ath_ops { unsigned int (*read)(void *, u32 reg_offset); + void (*multi_read)(void *, u32 *addr, u32 *val, u16 count); void (*write)(void *, u32 val, u32 reg_offset); void (*enable_write_buffer)(void *); void (*write_flush) (void *); diff --git a/drivers/net/wireless/ath/ath5k/ahb.c b/drivers/net/wireless/ath/ath5k/ahb.c index 707cde1..ae84b86 100644 --- a/drivers/net/wireless/ath/ath5k/ahb.c +++ b/drivers/net/wireless/ath/ath5k/ahb.c @@ -31,7 +31,8 @@ static void ath5k_ahb_read_cachesize(struct ath_common *common, int *csz) *csz = L1_CACHE_BYTES >> 2; } -bool ath5k_ahb_eeprom_read(struct ath_common *common, u32 off, u16 *data) +static bool +ath5k_ahb_eeprom_read(struct ath_common *common, u32 off, u16 *data) { struct ath5k_softc *sc = common->priv; struct platform_device *pdev = to_platform_device(sc->dev); @@ -46,10 +47,10 @@ bool ath5k_ahb_eeprom_read(struct ath_common *common, u32 off, u16 *data) eeprom += off; if (eeprom > eeprom_end) - return -EINVAL; + return false; *data = *eeprom; - return 0; + return true; } int ath5k_hw_read_srev(struct ath5k_hw *ah) diff --git a/drivers/net/wireless/ath/ath5k/base.c b/drivers/net/wireless/ath/ath5k/base.c index 09ae4ef..dae0bdc 100644 --- a/drivers/net/wireless/ath/ath5k/base.c +++ b/drivers/net/wireless/ath/ath5k/base.c @@ -242,73 +242,68 @@ static int ath5k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *re \********************/ /* - * Convert IEEE channel number to MHz frequency. - */ -static inline short -ath5k_ieee2mhz(short chan) -{ - if (chan <= 14 || chan >= 27) - return ieee80211chan2mhz(chan); - else - return 2212 + chan * 20; -} - -/* * Returns true for the channel numbers used without all_channels modparam. */ -static bool ath5k_is_standard_channel(short chan) +static bool ath5k_is_standard_channel(short chan, enum ieee80211_band band) { - return ((chan <= 14) || - /* UNII 1,2 */ - ((chan & 3) == 0 && chan >= 36 && chan <= 64) || + if (band == IEEE80211_BAND_2GHZ && chan <= 14) + return true; + + return /* UNII 1,2 */ + (((chan & 3) == 0 && chan >= 36 && chan <= 64) || /* midband */ ((chan & 3) == 0 && chan >= 100 && chan <= 140) || /* UNII-3 */ - ((chan & 3) == 1 && chan >= 149 && chan <= 165)); + ((chan & 3) == 1 && chan >= 149 && chan <= 165) || + /* 802.11j 5.030-5.080 GHz (20MHz) */ + (chan == 8 || chan == 12 || chan == 16) || + /* 802.11j 4.9GHz (20MHz) */ + (chan == 184 || chan == 188 || chan == 192 || chan == 196)); } static unsigned int -ath5k_copy_channels(struct ath5k_hw *ah, - struct ieee80211_channel *channels, - unsigned int mode, - unsigned int max) +ath5k_setup_channels(struct ath5k_hw *ah, struct ieee80211_channel *channels, + unsigned int mode, unsigned int max) { - unsigned int i, count, size, chfreq, freq, ch; - - if (!test_bit(mode, ah->ah_modes)) - return 0; + unsigned int count, size, chfreq, freq, ch; + enum ieee80211_band band; switch (mode) { case AR5K_MODE_11A: /* 1..220, but 2GHz frequencies are filtered by check_channel */ - size = 220 ; + size = 220; chfreq = CHANNEL_5GHZ; + band = IEEE80211_BAND_5GHZ; break; case AR5K_MODE_11B: case AR5K_MODE_11G: size = 26; chfreq = CHANNEL_2GHZ; + band = IEEE80211_BAND_2GHZ; break; default: ATH5K_WARN(ah->ah_sc, "bad mode, not copying channels\n"); return 0; } - for (i = 0, count = 0; i < size && max > 0; i++) { - ch = i + 1 ; - freq = ath5k_ieee2mhz(ch); + count = 0; + for (ch = 1; ch <= size && count < max; ch++) { + freq = ieee80211_channel_to_frequency(ch, band); + + if (freq == 0) /* mapping failed - not a standard channel */ + continue; /* Check if channel is supported by the chipset */ if (!ath5k_channel_ok(ah, freq, chfreq)) continue; - if (!modparam_all_channels && !ath5k_is_standard_channel(ch)) + if (!modparam_all_channels && + !ath5k_is_standard_channel(ch, band)) continue; /* Write channel info and increment counter */ channels[count].center_freq = freq; - channels[count].band = (chfreq == CHANNEL_2GHZ) ? - IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ; + channels[count].band = band; switch (mode) { case AR5K_MODE_11A: case AR5K_MODE_11G: @@ -319,7 +314,6 @@ ath5k_copy_channels(struct ath5k_hw *ah, } count++; - max--; } return count; @@ -364,7 +358,7 @@ ath5k_setup_bands(struct ieee80211_hw *hw) sband->n_bitrates = 12; sband->channels = sc->channels; - sband->n_channels = ath5k_copy_channels(ah, sband->channels, + sband->n_channels = ath5k_setup_channels(ah, sband->channels, AR5K_MODE_11G, max_c); hw->wiphy->bands[IEEE80211_BAND_2GHZ] = sband; @@ -390,7 +384,7 @@ ath5k_setup_bands(struct ieee80211_hw *hw) } sband->channels = sc->channels; - sband->n_channels = ath5k_copy_channels(ah, sband->channels, + sband->n_channels = ath5k_setup_channels(ah, sband->channels, AR5K_MODE_11B, max_c); hw->wiphy->bands[IEEE80211_BAND_2GHZ] = sband; @@ -410,7 +404,7 @@ ath5k_setup_bands(struct ieee80211_hw *hw) sband->n_bitrates = 8; sband->channels = &sc->channels[count_c]; - sband->n_channels = ath5k_copy_channels(ah, sband->channels, + sband->n_channels = ath5k_setup_channels(ah, sband->channels, AR5K_MODE_11A, max_c); hw->wiphy->bands[IEEE80211_BAND_5GHZ] = sband; @@ -445,18 +439,6 @@ ath5k_chan_set(struct ath5k_softc *sc, struct ieee80211_channel *chan) return ath5k_reset(sc, chan, true); } -static void -ath5k_setcurmode(struct ath5k_softc *sc, unsigned int mode) -{ - sc->curmode = mode; - - if (mode == AR5K_MODE_11A) { - sc->curband = &sc->sbands[IEEE80211_BAND_5GHZ]; - } else { - sc->curband = &sc->sbands[IEEE80211_BAND_2GHZ]; - } -} - struct ath_vif_iter_data { const u8 *hw_macaddr; u8 mask[ETH_ALEN]; @@ -569,7 +551,7 @@ ath5k_hw_to_driver_rix(struct ath5k_softc *sc, int hw_rix) "hw_rix out of bounds: %x\n", hw_rix)) return 0; - rix = sc->rate_idx[sc->curband->band][hw_rix]; + rix = sc->rate_idx[sc->curchan->band][hw_rix]; if (WARN(rix < 0, "invalid hw_rix: %x\n", hw_rix)) rix = 0; @@ -1379,7 +1361,7 @@ ath5k_receive_frame(struct ath5k_softc *sc, struct sk_buff *skb, rxs->flag |= RX_FLAG_TSFT; rxs->freq = sc->curchan->center_freq; - rxs->band = sc->curband->band; + rxs->band = sc->curchan->band; rxs->signal = sc->ah->ah_noise_floor + rs->rs_rssi; @@ -1394,7 +1376,7 @@ ath5k_receive_frame(struct ath5k_softc *sc, struct sk_buff *skb, rxs->flag |= ath5k_rx_decrypted(sc, skb, rs); if (rxs->rate_idx >= 0 && rs->rs_rate == - sc->curband->bitrates[rxs->rate_idx].hw_value_short) + sc->sbands[sc->curchan->band].bitrates[rxs->rate_idx].hw_value_short) rxs->flag |= RX_FLAG_SHORTPRE; ath5k_debug_dump_skb(sc, skb, "RX ", 0); @@ -2554,7 +2536,6 @@ ath5k_init_hw(struct ath5k_softc *sc) * and then setup of the interrupt mask. */ sc->curchan = sc->hw->conf.channel; - sc->curband = &sc->sbands[sc->curchan->band]; sc->imask = AR5K_INT_RXOK | AR5K_INT_RXERR | AR5K_INT_RXEOL | AR5K_INT_RXORN | AR5K_INT_TXDESC | AR5K_INT_TXEOL | AR5K_INT_FATAL | AR5K_INT_GLOBAL | AR5K_INT_MIB; @@ -2681,10 +2662,8 @@ ath5k_reset(struct ath5k_softc *sc, struct ieee80211_channel *chan, * so we should also free any remaining * tx buffers */ ath5k_drain_tx_buffs(sc); - if (chan) { + if (chan) sc->curchan = chan; - sc->curband = &sc->sbands[chan->band]; - } ret = ath5k_hw_reset(ah, sc->opmode, sc->curchan, chan != NULL, skip_pcu); if (ret) { @@ -2782,12 +2761,6 @@ ath5k_init(struct ieee80211_hw *hw) goto err; } - /* NB: setup here so ath5k_rate_update is happy */ - if (test_bit(AR5K_MODE_11A, ah->ah_modes)) - ath5k_setcurmode(sc, AR5K_MODE_11A); - else - ath5k_setcurmode(sc, AR5K_MODE_11B); - /* * Allocate tx+rx descriptors and populate the lists. */ diff --git a/drivers/net/wireless/ath/ath5k/base.h b/drivers/net/wireless/ath/ath5k/base.h index 6d51147..8f919dc 100644 --- a/drivers/net/wireless/ath/ath5k/base.h +++ b/drivers/net/wireless/ath/ath5k/base.h @@ -183,8 +183,6 @@ struct ath5k_softc { enum nl80211_iftype opmode; struct ath5k_hw *ah; /* Atheros HW */ - struct ieee80211_supported_band *curband; - #ifdef CONFIG_ATH5K_DEBUG struct ath5k_dbg_info debug; /* debug info */ #endif /* CONFIG_ATH5K_DEBUG */ @@ -202,7 +200,6 @@ struct ath5k_softc { #define ATH_STAT_STARTED 4 /* opened & irqs enabled */ unsigned int filter_flags; /* HW flags, AR5K_RX_FILTER_* */ - unsigned int curmode; /* current phy mode */ struct ieee80211_channel *curchan; /* current h/w channel */ u16 nvifs; diff --git a/drivers/net/wireless/ath/ath5k/eeprom.c b/drivers/net/wireless/ath/ath5k/eeprom.c index 80e6256..b6561f7 100644 --- a/drivers/net/wireless/ath/ath5k/eeprom.c +++ b/drivers/net/wireless/ath/ath5k/eeprom.c @@ -72,7 +72,6 @@ static int ath5k_eeprom_init_header(struct ath5k_hw *ah) { struct ath5k_eeprom_info *ee = &ah->ah_capabilities.cap_eeprom; - int ret; u16 val; u32 cksum, offset, eep_max = AR5K_EEPROM_INFO_MAX; @@ -192,7 +191,7 @@ static int ath5k_eeprom_read_ants(struct ath5k_hw *ah, u32 *offset, struct ath5k_eeprom_info *ee = &ah->ah_capabilities.cap_eeprom; u32 o = *offset; u16 val; - int ret, i = 0; + int i = 0; AR5K_EEPROM_READ(o++, val); ee->ee_switch_settling[mode] = (val >> 8) & 0x7f; @@ -252,7 +251,6 @@ static int ath5k_eeprom_read_modes(struct ath5k_hw *ah, u32 *offset, struct ath5k_eeprom_info *ee = &ah->ah_capabilities.cap_eeprom; u32 o = *offset; u16 val; - int ret; ee->ee_n_piers[mode] = 0; AR5K_EEPROM_READ(o++, val); @@ -515,7 +513,6 @@ ath5k_eeprom_read_freq_list(struct ath5k_hw *ah, int *offset, int max, int o = *offset; int i = 0; u8 freq1, freq2; - int ret; u16 val; ee->ee_n_piers[mode] = 0; @@ -551,7 +548,7 @@ ath5k_eeprom_init_11a_pcal_freq(struct ath5k_hw *ah, int offset) { struct ath5k_eeprom_info *ee = &ah->ah_capabilities.cap_eeprom; struct ath5k_chan_pcal_info *pcal = ee->ee_pwr_cal_a; - int i, ret; + int i; u16 val; u8 mask; @@ -970,7 +967,6 @@ ath5k_eeprom_read_pcal_info_5112(struct ath5k_hw *ah, int mode) u32 offset; u8 i, c; u16 val; - int ret; u8 pd_gains = 0; /* Count how many curves we have and @@ -1228,7 +1224,7 @@ ath5k_eeprom_read_pcal_info_2413(struct ath5k_hw *ah, int mode) struct ath5k_chan_pcal_info *chinfo; u8 *pdgain_idx = ee->ee_pdc_to_idx[mode]; u32 offset; - int idx, i, ret; + int idx, i; u16 val; u8 pd_gains = 0; @@ -1419,7 +1415,7 @@ ath5k_eeprom_read_target_rate_pwr_info(struct ath5k_hw *ah, unsigned int mode) u8 *rate_target_pwr_num; u32 offset; u16 val; - int ret, i; + int i; offset = AR5K_EEPROM_TARGET_PWRSTART(ee->ee_misc1); rate_target_pwr_num = &ee->ee_rate_target_pwr_num[mode]; @@ -1593,7 +1589,7 @@ ath5k_eeprom_read_ctl_info(struct ath5k_hw *ah) struct ath5k_edge_power *rep; unsigned int fmask, pmask; unsigned int ctl_mode; - int ret, i, j; + int i, j; u32 offset; u16 val; @@ -1733,16 +1729,12 @@ int ath5k_eeprom_read_mac(struct ath5k_hw *ah, u8 *mac) u8 mac_d[ETH_ALEN] = {}; u32 total, offset; u16 data; - int octet, ret; + int octet; - ret = ath5k_hw_nvram_read(ah, 0x20, &data); - if (ret) - return ret; + AR5K_EEPROM_READ(0x20, data); for (offset = 0x1f, octet = 0, total = 0; offset >= 0x1d; offset--) { - ret = ath5k_hw_nvram_read(ah, offset, &data); - if (ret) - return ret; + AR5K_EEPROM_READ(offset, data); total += data; mac_d[octet + 1] = data & 0xff; diff --git a/drivers/net/wireless/ath/ath5k/eeprom.h b/drivers/net/wireless/ath/ath5k/eeprom.h index 7c09e15..6511c27 100644 --- a/drivers/net/wireless/ath/ath5k/eeprom.h +++ b/drivers/net/wireless/ath/ath5k/eeprom.h @@ -241,9 +241,8 @@ enum ath5k_eeprom_freq_bands{ #define AR5K_SPUR_SYMBOL_WIDTH_TURBO_100Hz 6250 #define AR5K_EEPROM_READ(_o, _v) do { \ - ret = ath5k_hw_nvram_read(ah, (_o), &(_v)); \ - if (ret) \ - return ret; \ + if (!ath5k_hw_nvram_read(ah, (_o), &(_v))) \ + return -EIO; \ } while (0) #define AR5K_EEPROM_READ_HDR(_o, _v) \ @@ -269,29 +268,6 @@ enum ath5k_ctl_mode { AR5K_CTL_MODE_M = 15, }; -/* Default CTL ids for the 3 main reg domains. - * Atheros only uses these by default but vendors - * can have up to 32 different CTLs for different - * scenarios. Note that theese values are ORed with - * the mode id (above) so we can have up to 24 CTL - * datasets out of these 3 main regdomains. That leaves - * 8 ids that can be used by vendors and since 0x20 is - * missing from HAL sources i guess this is the set of - * custom CTLs vendors can use. */ -#define AR5K_CTL_FCC 0x10 -#define AR5K_CTL_CUSTOM 0x20 -#define AR5K_CTL_ETSI 0x30 -#define AR5K_CTL_MKK 0x40 - -/* Indicates a CTL with only mode set and - * no reg domain mapping, such CTLs are used - * for world roaming domains or simply when - * a reg domain is not set */ -#define AR5K_CTL_NO_REGDOMAIN 0xf0 - -/* Indicates an empty (invalid) CTL */ -#define AR5K_CTL_NO_CTL 0xff - /* Per channel calibration data, used for power table setup */ struct ath5k_chan_pcal_info_rf5111 { /* Power levels in half dbm units diff --git a/drivers/net/wireless/ath/ath5k/pci.c b/drivers/net/wireless/ath/ath5k/pci.c index 7f8c5b0..66598a0 100644 --- a/drivers/net/wireless/ath/ath5k/pci.c +++ b/drivers/net/wireless/ath/ath5k/pci.c @@ -69,7 +69,8 @@ static void ath5k_pci_read_cachesize(struct ath_common *common, int *csz) /* * Read from eeprom */ -bool ath5k_pci_eeprom_read(struct ath_common *common, u32 offset, u16 *data) +static bool +ath5k_pci_eeprom_read(struct ath_common *common, u32 offset, u16 *data) { struct ath5k_hw *ah = (struct ath5k_hw *) common->ah; u32 status, timeout; @@ -90,15 +91,15 @@ bool ath5k_pci_eeprom_read(struct ath_common *common, u32 offset, u16 *data) status = ath5k_hw_reg_read(ah, AR5K_EEPROM_STATUS); if (status & AR5K_EEPROM_STAT_RDDONE) { if (status & AR5K_EEPROM_STAT_RDERR) - return -EIO; + return false; *data = (u16)(ath5k_hw_reg_read(ah, AR5K_EEPROM_DATA) & 0xffff); - return 0; + return true; } udelay(15); } - return -ETIMEDOUT; + return false; } int ath5k_hw_read_srev(struct ath5k_hw *ah) diff --git a/drivers/net/wireless/ath/ath9k/ar9002_calib.c b/drivers/net/wireless/ath/ath9k/ar9002_calib.c index 5e300bd..76388c6 100644 --- a/drivers/net/wireless/ath/ath9k/ar9002_calib.c +++ b/drivers/net/wireless/ath/ath9k/ar9002_calib.c @@ -805,7 +805,10 @@ static bool ar9002_hw_init_cal(struct ath_hw *ah, struct ath9k_channel *chan) { struct ath_common *common = ath9k_hw_common(ah); - if (AR_SREV_9271(ah) || AR_SREV_9285_12_OR_LATER(ah)) { + if (AR_SREV_9271(ah)) { + if (!ar9285_hw_cl_cal(ah, chan)) + return false; + } else if (AR_SREV_9285_12_OR_LATER(ah)) { if (!ar9285_hw_clc(ah, chan)) return false; } else { diff --git a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c index 4819747..a256556 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_eeprom.c @@ -3959,19 +3959,19 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) { #define POW_SM(_r, _s) (((_r) & 0x3f) << (_s)) /* make sure forced gain is not set */ - REG_WRITE(ah, 0xa458, 0); + REG_WRITE(ah, AR_PHY_TX_FORCED_GAIN, 0); /* Write the OFDM power per rate set */ /* 6 (LSB), 9, 12, 18 (MSB) */ - REG_WRITE(ah, 0xa3c0, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(0), POW_SM(pPwrArray[ALL_TARGET_LEGACY_6_24], 24) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_6_24], 16) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_6_24], 8) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_6_24], 0)); /* 24 (LSB), 36, 48, 54 (MSB) */ - REG_WRITE(ah, 0xa3c4, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(1), POW_SM(pPwrArray[ALL_TARGET_LEGACY_54], 24) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_48], 16) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_36], 8) | @@ -3980,14 +3980,14 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) /* Write the CCK power per rate set */ /* 1L (LSB), reserved, 2L, 2S (MSB) */ - REG_WRITE(ah, 0xa3c8, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(2), POW_SM(pPwrArray[ALL_TARGET_LEGACY_1L_5L], 24) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_1L_5L], 16) | /* POW_SM(txPowerTimes2, 8) | this is reserved for AR9003 */ POW_SM(pPwrArray[ALL_TARGET_LEGACY_1L_5L], 0)); /* 5.5L (LSB), 5.5S, 11L, 11S (MSB) */ - REG_WRITE(ah, 0xa3cc, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(3), POW_SM(pPwrArray[ALL_TARGET_LEGACY_11S], 24) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_11L], 16) | POW_SM(pPwrArray[ALL_TARGET_LEGACY_5S], 8) | @@ -3997,7 +3997,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) /* Write the HT20 power per rate set */ /* 0/8/16 (LSB), 1-3/9-11/17-19, 4, 5 (MSB) */ - REG_WRITE(ah, 0xa3d0, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(4), POW_SM(pPwrArray[ALL_TARGET_HT20_5], 24) | POW_SM(pPwrArray[ALL_TARGET_HT20_4], 16) | POW_SM(pPwrArray[ALL_TARGET_HT20_1_3_9_11_17_19], 8) | @@ -4005,7 +4005,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) ); /* 6 (LSB), 7, 12, 13 (MSB) */ - REG_WRITE(ah, 0xa3d4, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(5), POW_SM(pPwrArray[ALL_TARGET_HT20_13], 24) | POW_SM(pPwrArray[ALL_TARGET_HT20_12], 16) | POW_SM(pPwrArray[ALL_TARGET_HT20_7], 8) | @@ -4013,7 +4013,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) ); /* 14 (LSB), 15, 20, 21 */ - REG_WRITE(ah, 0xa3e4, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(9), POW_SM(pPwrArray[ALL_TARGET_HT20_21], 24) | POW_SM(pPwrArray[ALL_TARGET_HT20_20], 16) | POW_SM(pPwrArray[ALL_TARGET_HT20_15], 8) | @@ -4023,7 +4023,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) /* Mixed HT20 and HT40 rates */ /* HT20 22 (LSB), HT20 23, HT40 22, HT40 23 (MSB) */ - REG_WRITE(ah, 0xa3e8, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(10), POW_SM(pPwrArray[ALL_TARGET_HT40_23], 24) | POW_SM(pPwrArray[ALL_TARGET_HT40_22], 16) | POW_SM(pPwrArray[ALL_TARGET_HT20_23], 8) | @@ -4035,7 +4035,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) * correct PAR difference between HT40 and HT20/LEGACY * 0/8/16 (LSB), 1-3/9-11/17-19, 4, 5 (MSB) */ - REG_WRITE(ah, 0xa3d8, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(6), POW_SM(pPwrArray[ALL_TARGET_HT40_5], 24) | POW_SM(pPwrArray[ALL_TARGET_HT40_4], 16) | POW_SM(pPwrArray[ALL_TARGET_HT40_1_3_9_11_17_19], 8) | @@ -4043,7 +4043,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) ); /* 6 (LSB), 7, 12, 13 (MSB) */ - REG_WRITE(ah, 0xa3dc, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(7), POW_SM(pPwrArray[ALL_TARGET_HT40_13], 24) | POW_SM(pPwrArray[ALL_TARGET_HT40_12], 16) | POW_SM(pPwrArray[ALL_TARGET_HT40_7], 8) | @@ -4051,7 +4051,7 @@ static int ar9003_hw_tx_power_regwrite(struct ath_hw *ah, u8 * pPwrArray) ); /* 14 (LSB), 15, 20, 21 */ - REG_WRITE(ah, 0xa3ec, + REG_WRITE(ah, AR_PHY_POWER_TX_RATE(11), POW_SM(pPwrArray[ALL_TARGET_HT40_21], 24) | POW_SM(pPwrArray[ALL_TARGET_HT40_20], 16) | POW_SM(pPwrArray[ALL_TARGET_HT40_15], 8) | diff --git a/drivers/net/wireless/ath/ath9k/ar9003_mac.c b/drivers/net/wireless/ath/ath9k/ar9003_mac.c index 4ceddbb..038a0cb 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_mac.c +++ b/drivers/net/wireless/ath/ath9k/ar9003_mac.c @@ -615,7 +615,7 @@ int ath9k_hw_process_rxdesc_edma(struct ath_hw *ah, struct ath_rx_status *rxs, */ if (rxsp->status11 & AR_CRCErr) rxs->rs_status |= ATH9K_RXERR_CRC; - if (rxsp->status11 & AR_PHYErr) { + else if (rxsp->status11 & AR_PHYErr) { phyerr = MS(rxsp->status11, AR_PHYErrCode); /* * If we reach a point here where AR_PostDelimCRCErr is @@ -638,11 +638,11 @@ int ath9k_hw_process_rxdesc_edma(struct ath_hw *ah, struct ath_rx_status *rxs, rxs->rs_phyerr = phyerr; } - } - if (rxsp->status11 & AR_DecryptCRCErr) + } else if (rxsp->status11 & AR_DecryptCRCErr) rxs->rs_status |= ATH9K_RXERR_DECRYPT; - if (rxsp->status11 & AR_MichaelErr) + else if (rxsp->status11 & AR_MichaelErr) rxs->rs_status |= ATH9K_RXERR_MIC; + if (rxsp->status11 & AR_KeyMiss) rxs->rs_status |= ATH9K_RXERR_DECRYPT; } diff --git a/drivers/net/wireless/ath/ath9k/ar9003_phy.h b/drivers/net/wireless/ath/ath9k/ar9003_phy.h index 59bab6b..8bdda2c 100644 --- a/drivers/net/wireless/ath/ath9k/ar9003_phy.h +++ b/drivers/net/wireless/ath/ath9k/ar9003_phy.h @@ -486,6 +486,8 @@ #define AR_PHY_HEAVYCLIP_40 (AR_SM_BASE + 0x1ac) #define AR_PHY_ILLEGAL_TXRATE (AR_SM_BASE + 0x1b0) +#define AR_PHY_POWER_TX_RATE(_d) (AR_SM_BASE + 0x1c0 + ((_d) << 2)) + #define AR_PHY_PWRTX_MAX (AR_SM_BASE + 0x1f0) #define AR_PHY_POWER_TX_SUB (AR_SM_BASE + 0x1f4) diff --git a/drivers/net/wireless/ath/ath9k/ath9k.h b/drivers/net/wireless/ath/ath9k/ath9k.h index 3681caf5..6636f3c 100644 --- a/drivers/net/wireless/ath/ath9k/ath9k.h +++ b/drivers/net/wireless/ath/ath9k/ath9k.h @@ -95,9 +95,9 @@ struct ath_config { * @BUF_XRETRY: To denote excessive retries of the buffer */ enum buffer_type { - BUF_AMPDU = BIT(2), - BUF_AGGR = BIT(3), - BUF_XRETRY = BIT(5), + BUF_AMPDU = BIT(0), + BUF_AGGR = BIT(1), + BUF_XRETRY = BIT(2), }; #define bf_isampdu(bf) (bf->bf_state.bf_type & BUF_AMPDU) @@ -137,7 +137,6 @@ void ath_descdma_cleanup(struct ath_softc *sc, struct ath_descdma *dd, (((_tid) == 4) || ((_tid) == 5)) ? WME_AC_VI : \ WME_AC_VO) -#define ADDBA_EXCHANGE_ATTEMPTS 10 #define ATH_AGGR_DELIM_SZ 4 #define ATH_AGGR_MINPLEN 256 /* in bytes, minimum packet length */ /* number of delimiters for encryption padding */ @@ -184,7 +183,8 @@ enum ATH_AGGR_STATUS { #define ATH_TXFIFO_DEPTH 8 struct ath_txq { - u32 axq_qnum; + int mac80211_qnum; /* mac80211 queue number, -1 means not mac80211 Q */ + u32 axq_qnum; /* ath9k hardware queue number */ u32 *axq_link; struct list_head axq_q; spinlock_t axq_lock; @@ -254,7 +254,10 @@ struct ath_atx_tid { }; struct ath_node { - struct ath_common *common; +#ifdef CONFIG_ATH9K_DEBUGFS + struct list_head list; /* for sc->nodes */ + struct ieee80211_sta *sta; /* station struct we're part of */ +#endif struct ath_atx_tid tid[WME_NUM_TID]; struct ath_atx_ac ac[WME_NUM_AC]; u16 maxampdu; @@ -277,6 +280,11 @@ struct ath_tx_control { #define ATH_TX_XRETRY 0x02 #define ATH_TX_BAR 0x04 +/** + * @txq_map: Index is mac80211 queue number. This is + * not necessarily the same as the hardware queue number + * (axq_qnum). + */ struct ath_tx { u16 seq_no; u32 txqsetup; @@ -342,7 +350,6 @@ struct ath_vif { __le64 tsf_adjust; /* TSF adjustment for staggered beacons */ enum nl80211_iftype av_opmode; struct ath_buf *av_bcbuf; - struct ath_tx_control av_btxctl; u8 bssid[ETH_ALEN]; /* current BSSID from config_interface */ }; @@ -560,6 +567,20 @@ struct ath_ant_comb { struct ath_wiphy; struct ath_rate_table; +struct ath9k_vif_iter_data { + const u8 *hw_macaddr; /* phy's hardware address, set + * before starting iteration for + * valid bssid mask. + */ + u8 mask[ETH_ALEN]; /* bssid mask */ + int naps; /* number of AP vifs */ + int nmeshes; /* number of mesh vifs */ + int nstations; /* number of station vifs */ + int nwds; /* number of nwd vifs */ + int nadhocs; /* number of adhoc vifs */ + int nothers; /* number of vifs not specified above. */ +}; + struct ath_softc { struct ieee80211_hw *hw; struct device *dev; @@ -599,10 +620,10 @@ struct ath_softc { u32 sc_flags; /* SC_OP_* */ u16 ps_flags; /* PS_* */ u16 curtxpow; - u8 nbcnvifs; - u16 nvifs; bool ps_enabled; bool ps_idle; + short nbcnvifs; + short nvifs; unsigned long ps_usecount; struct ath_config config; @@ -625,6 +646,9 @@ struct ath_softc { #ifdef CONFIG_ATH9K_DEBUGFS struct ath9k_debug debug; + spinlock_t nodes_lock; + struct list_head nodes; /* basically, stations */ + unsigned int tx_complete_poll_work_seen; #endif struct ath_beacon_config cur_beacon_conf; struct delayed_work tx_complete_work; @@ -683,6 +707,7 @@ int ath_set_channel(struct ath_softc *sc, struct ieee80211_hw *hw, void ath_radio_enable(struct ath_softc *sc, struct ieee80211_hw *hw); void ath_radio_disable(struct ath_softc *sc, struct ieee80211_hw *hw); bool ath9k_setpower(struct ath_softc *sc, enum ath9k_power_mode mode); +bool ath9k_uses_beacons(int type); #ifdef CONFIG_PCI int ath_pci_init(void); @@ -727,5 +752,9 @@ bool ath_mac80211_start_queue(struct ath_softc *sc, u16 skb_queue); void ath_start_rfkill_poll(struct ath_softc *sc); extern void ath9k_rfkill_poll_state(struct ieee80211_hw *hw); +void ath9k_calculate_iter_data(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ath9k_vif_iter_data *iter_data); + #endif /* ATH9K_H */ diff --git a/drivers/net/wireless/ath/ath9k/beacon.c b/drivers/net/wireless/ath/ath9k/beacon.c index 385ba03..ab8c05c 100644 --- a/drivers/net/wireless/ath/ath9k/beacon.c +++ b/drivers/net/wireless/ath/ath9k/beacon.c @@ -244,9 +244,7 @@ int ath_beacon_alloc(struct ath_wiphy *aphy, struct ieee80211_vif *vif) struct ath_buf, list); list_del(&avp->av_bcbuf->list); - if (sc->sc_ah->opmode == NL80211_IFTYPE_AP || - sc->sc_ah->opmode == NL80211_IFTYPE_ADHOC || - sc->sc_ah->opmode == NL80211_IFTYPE_MESH_POINT) { + if (ath9k_uses_beacons(vif->type)) { int slot; /* * Assign the vif to a beacon xmit slot. As @@ -281,10 +279,8 @@ int ath_beacon_alloc(struct ath_wiphy *aphy, struct ieee80211_vif *vif) /* NB: the beacon data buffer must be 32-bit aligned. */ skb = ieee80211_beacon_get(sc->hw, vif); - if (skb == NULL) { - ath_dbg(common, ATH_DBG_BEACON, "cannot get skb\n"); + if (skb == NULL) return -ENOMEM; - } tstamp = ((struct ieee80211_mgmt *)skb->data)->u.beacon.timestamp; sc->beacon.bc_tstamp = le64_to_cpu(tstamp); @@ -720,10 +716,10 @@ void ath_beacon_config(struct ath_softc *sc, struct ieee80211_vif *vif) iftype = sc->sc_ah->opmode; } - cur_conf->listen_interval = 1; - cur_conf->dtim_count = 1; - cur_conf->bmiss_timeout = - ATH_DEFAULT_BMISS_LIMIT * cur_conf->beacon_interval; + cur_conf->listen_interval = 1; + cur_conf->dtim_count = 1; + cur_conf->bmiss_timeout = + ATH_DEFAULT_BMISS_LIMIT * cur_conf->beacon_interval; /* * It looks like mac80211 may end up using beacon interval of zero in diff --git a/drivers/net/wireless/ath/ath9k/calib.c b/drivers/net/wireless/ath/ath9k/calib.c index b68a1ac..b4a92a4 100644 --- a/drivers/net/wireless/ath/ath9k/calib.c +++ b/drivers/net/wireless/ath/ath9k/calib.c @@ -382,9 +382,8 @@ void ath9k_init_nfcal_hist_buffer(struct ath_hw *ah, s16 default_nf; int i, j; - if (!ah->caldata) - return; - + ah->caldata->channel = chan->channel; + ah->caldata->channelFlags = chan->channelFlags & ~CHANNEL_CW_INT; h = ah->caldata->nfCalHist; default_nf = ath9k_hw_get_default_nf(ah, chan); for (i = 0; i < NUM_NF_READINGS; i++) { diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c index 3586c43..f0c80ec 100644 --- a/drivers/net/wireless/ath/ath9k/debug.c +++ b/drivers/net/wireless/ath/ath9k/debug.c @@ -587,26 +587,60 @@ static const struct file_operations fops_wiphy = { sc->debug.stats.txstats[WME_AC_BK].elem, \ sc->debug.stats.txstats[WME_AC_VI].elem, \ sc->debug.stats.txstats[WME_AC_VO].elem); \ + if (len >= size) \ + goto done; \ } while(0) +#define PRX(str, elem) \ +do { \ + len += snprintf(buf + len, size - len, \ + "%s%13u%11u%10u%10u\n", str, \ + (unsigned int)(sc->tx.txq[ATH_TXQ_AC_BE].elem), \ + (unsigned int)(sc->tx.txq[ATH_TXQ_AC_BK].elem), \ + (unsigned int)(sc->tx.txq[ATH_TXQ_AC_VI].elem), \ + (unsigned int)(sc->tx.txq[ATH_TXQ_AC_VO].elem)); \ + if (len >= size) \ + goto done; \ +} while(0) + +#define PRQLE(str, elem) \ +do { \ + len += snprintf(buf + len, size - len, \ + "%s%13i%11i%10i%10i\n", str, \ + list_empty(&sc->tx.txq[ATH_TXQ_AC_BE].elem), \ + list_empty(&sc->tx.txq[ATH_TXQ_AC_BK].elem), \ + list_empty(&sc->tx.txq[ATH_TXQ_AC_VI].elem), \ + list_empty(&sc->tx.txq[ATH_TXQ_AC_VO].elem)); \ + if (len >= size) \ + goto done; \ +} while (0) + static ssize_t read_file_xmit(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct ath_softc *sc = file->private_data; char *buf; - unsigned int len = 0, size = 2048; + unsigned int len = 0, size = 8000; + int i; ssize_t retval = 0; + char tmp[32]; buf = kzalloc(size, GFP_KERNEL); if (buf == NULL) return -ENOMEM; - len += sprintf(buf, "%30s %10s%10s%10s\n\n", "BE", "BK", "VI", "VO"); + len += sprintf(buf, "Num-Tx-Queues: %i tx-queues-setup: 0x%x" + " poll-work-seen: %u\n" + "%30s %10s%10s%10s\n\n", + ATH9K_NUM_TX_QUEUES, sc->tx.txqsetup, + sc->tx_complete_poll_work_seen, + "BE", "BK", "VI", "VO"); PR("MPDUs Queued: ", queued); PR("MPDUs Completed: ", completed); PR("Aggregates: ", a_aggr); - PR("AMPDUs Queued: ", a_queued); + PR("AMPDUs Queued HW:", a_queued_hw); + PR("AMPDUs Queued SW:", a_queued_sw); PR("AMPDUs Completed:", a_completed); PR("AMPDUs Retried: ", a_retries); PR("AMPDUs XRetried: ", a_xretries); @@ -618,6 +652,223 @@ static ssize_t read_file_xmit(struct file *file, char __user *user_buf, PR("DELIM Underrun: ", delim_underrun); PR("TX-Pkts-All: ", tx_pkts_all); PR("TX-Bytes-All: ", tx_bytes_all); + PR("hw-put-tx-buf: ", puttxbuf); + PR("hw-tx-start: ", txstart); + PR("hw-tx-proc-desc: ", txprocdesc); + len += snprintf(buf + len, size - len, + "%s%11p%11p%10p%10p\n", "txq-memory-address:", + &(sc->tx.txq[ATH_TXQ_AC_BE]), + &(sc->tx.txq[ATH_TXQ_AC_BK]), + &(sc->tx.txq[ATH_TXQ_AC_VI]), + &(sc->tx.txq[ATH_TXQ_AC_VO])); + if (len >= size) + goto done; + + PRX("axq-qnum: ", axq_qnum); + PRX("axq-depth: ", axq_depth); + PRX("axq-ampdu_depth: ", axq_ampdu_depth); + PRX("axq-stopped ", stopped); + PRX("tx-in-progress ", axq_tx_inprogress); + PRX("pending-frames ", pending_frames); + PRX("txq_headidx: ", txq_headidx); + PRX("txq_tailidx: ", txq_headidx); + + PRQLE("axq_q empty: ", axq_q); + PRQLE("axq_acq empty: ", axq_acq); + PRQLE("txq_fifo_pending: ", txq_fifo_pending); + for (i = 0; i < ATH_TXFIFO_DEPTH; i++) { + snprintf(tmp, sizeof(tmp) - 1, "txq_fifo[%i] empty: ", i); + PRQLE(tmp, txq_fifo[i]); + } + + /* Print out more detailed queue-info */ + for (i = 0; i <= WME_AC_BK; i++) { + struct ath_txq *txq = &(sc->tx.txq[i]); + struct ath_atx_ac *ac; + struct ath_atx_tid *tid; + if (len >= size) + goto done; + spin_lock_bh(&txq->axq_lock); + if (!list_empty(&txq->axq_acq)) { + ac = list_first_entry(&txq->axq_acq, struct ath_atx_ac, + list); + len += snprintf(buf + len, size - len, + "txq[%i] first-ac: %p sched: %i\n", + i, ac, ac->sched); + if (list_empty(&ac->tid_q) || (len >= size)) + goto done_for; + tid = list_first_entry(&ac->tid_q, struct ath_atx_tid, + list); + len += snprintf(buf + len, size - len, + " first-tid: %p sched: %i paused: %i\n", + tid, tid->sched, tid->paused); + } + done_for: + spin_unlock_bh(&txq->axq_lock); + } + +done: + if (len > size) + len = size; + + retval = simple_read_from_buffer(user_buf, count, ppos, buf, len); + kfree(buf); + + return retval; +} + +static ssize_t read_file_stations(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ath_softc *sc = file->private_data; + char *buf; + unsigned int len = 0, size = 64000; + struct ath_node *an = NULL; + ssize_t retval = 0; + int q; + + buf = kzalloc(size, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + len += snprintf(buf + len, size - len, + "Stations:\n" + " tid: addr sched paused buf_q-empty an ac\n" + " ac: addr sched tid_q-empty txq\n"); + + spin_lock(&sc->nodes_lock); + list_for_each_entry(an, &sc->nodes, list) { + len += snprintf(buf + len, size - len, + "%pM\n", an->sta->addr); + if (len >= size) + goto done; + + for (q = 0; q < WME_NUM_TID; q++) { + struct ath_atx_tid *tid = &(an->tid[q]); + len += snprintf(buf + len, size - len, + " tid: %p %s %s %i %p %p\n", + tid, tid->sched ? "sched" : "idle", + tid->paused ? "paused" : "running", + list_empty(&tid->buf_q), + tid->an, tid->ac); + if (len >= size) + goto done; + } + + for (q = 0; q < WME_NUM_AC; q++) { + struct ath_atx_ac *ac = &(an->ac[q]); + len += snprintf(buf + len, size - len, + " ac: %p %s %i %p\n", + ac, ac->sched ? "sched" : "idle", + list_empty(&ac->tid_q), ac->txq); + if (len >= size) + goto done; + } + } + +done: + spin_unlock(&sc->nodes_lock); + if (len > size) + len = size; + + retval = simple_read_from_buffer(user_buf, count, ppos, buf, len); + kfree(buf); + + return retval; +} + +static ssize_t read_file_misc(struct file *file, char __user *user_buf, + size_t count, loff_t *ppos) +{ + struct ath_softc *sc = file->private_data; + struct ath_common *common = ath9k_hw_common(sc->sc_ah); + struct ath_hw *ah = sc->sc_ah; + struct ieee80211_hw *hw = sc->hw; + char *buf; + unsigned int len = 0, size = 8000; + ssize_t retval = 0; + const char *tmp; + unsigned int reg; + struct ath9k_vif_iter_data iter_data; + + ath9k_calculate_iter_data(hw, NULL, &iter_data); + + buf = kzalloc(size, GFP_KERNEL); + if (buf == NULL) + return -ENOMEM; + + switch (sc->sc_ah->opmode) { + case NL80211_IFTYPE_ADHOC: + tmp = "ADHOC"; + break; + case NL80211_IFTYPE_MESH_POINT: + tmp = "MESH"; + break; + case NL80211_IFTYPE_AP: + tmp = "AP"; + break; + case NL80211_IFTYPE_STATION: + tmp = "STATION"; + break; + default: + tmp = "???"; + break; + } + + len += snprintf(buf + len, size - len, + "curbssid: %pM\n" + "OP-Mode: %s(%i)\n" + "Beacon-Timer-Register: 0x%x\n", + common->curbssid, + tmp, (int)(sc->sc_ah->opmode), + REG_READ(ah, AR_BEACON_PERIOD)); + + reg = REG_READ(ah, AR_TIMER_MODE); + len += snprintf(buf + len, size - len, "Timer-Mode-Register: 0x%x (", + reg); + if (reg & AR_TBTT_TIMER_EN) + len += snprintf(buf + len, size - len, "TBTT "); + if (reg & AR_DBA_TIMER_EN) + len += snprintf(buf + len, size - len, "DBA "); + if (reg & AR_SWBA_TIMER_EN) + len += snprintf(buf + len, size - len, "SWBA "); + if (reg & AR_HCF_TIMER_EN) + len += snprintf(buf + len, size - len, "HCF "); + if (reg & AR_TIM_TIMER_EN) + len += snprintf(buf + len, size - len, "TIM "); + if (reg & AR_DTIM_TIMER_EN) + len += snprintf(buf + len, size - len, "DTIM "); + len += snprintf(buf + len, size - len, ")\n"); + + reg = sc->sc_ah->imask; + len += snprintf(buf + len, size - len, "imask: 0x%x (", reg); + if (reg & ATH9K_INT_SWBA) + len += snprintf(buf + len, size - len, "SWBA "); + if (reg & ATH9K_INT_BMISS) + len += snprintf(buf + len, size - len, "BMISS "); + if (reg & ATH9K_INT_CST) + len += snprintf(buf + len, size - len, "CST "); + if (reg & ATH9K_INT_RX) + len += snprintf(buf + len, size - len, "RX "); + if (reg & ATH9K_INT_RXHP) + len += snprintf(buf + len, size - len, "RXHP "); + if (reg & ATH9K_INT_RXLP) + len += snprintf(buf + len, size - len, "RXLP "); + if (reg & ATH9K_INT_BB_WATCHDOG) + len += snprintf(buf + len, size - len, "BB_WATCHDOG "); + /* there are other IRQs if one wanted to add them. */ + len += snprintf(buf + len, size - len, ")\n"); + + len += snprintf(buf + len, size - len, + "VIF Counts: AP: %i STA: %i MESH: %i WDS: %i" + " ADHOC: %i OTHER: %i nvifs: %hi beacon-vifs: %hi\n", + iter_data.naps, iter_data.nstations, iter_data.nmeshes, + iter_data.nwds, iter_data.nadhocs, iter_data.nothers, + sc->nvifs, sc->nbcnvifs); + + len += snprintf(buf + len, size - len, + "Calculated-BSSID-Mask: %pM\n", + iter_data.mask); if (len > size) len = size; @@ -666,6 +917,20 @@ static const struct file_operations fops_xmit = { .llseek = default_llseek, }; +static const struct file_operations fops_stations = { + .read = read_file_stations, + .open = ath9k_debugfs_open, + .owner = THIS_MODULE, + .llseek = default_llseek, +}; + +static const struct file_operations fops_misc = { + .read = read_file_misc, + .open = ath9k_debugfs_open, + .owner = THIS_MODULE, + .llseek = default_llseek, +}; + static ssize_t read_file_recv(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { @@ -903,6 +1168,14 @@ int ath9k_init_debug(struct ath_hw *ah) sc, &fops_xmit)) goto err; + if (!debugfs_create_file("stations", S_IRUSR, sc->debug.debugfs_phy, + sc, &fops_stations)) + goto err; + + if (!debugfs_create_file("misc", S_IRUSR, sc->debug.debugfs_phy, + sc, &fops_misc)) + goto err; + if (!debugfs_create_file("recv", S_IRUSR, sc->debug.debugfs_phy, sc, &fops_recv)) goto err; diff --git a/drivers/net/wireless/ath/ath9k/debug.h b/drivers/net/wireless/ath/ath9k/debug.h index 1e5078b..980c9fa 100644 --- a/drivers/net/wireless/ath/ath9k/debug.h +++ b/drivers/net/wireless/ath/ath9k/debug.h @@ -89,7 +89,8 @@ struct ath_interrupt_stats { * @queued: Total MPDUs (non-aggr) queued * @completed: Total MPDUs (non-aggr) completed * @a_aggr: Total no. of aggregates queued - * @a_queued: Total AMPDUs queued + * @a_queued_hw: Total AMPDUs queued to hardware + * @a_queued_sw: Total AMPDUs queued to software queues * @a_completed: Total AMPDUs completed * @a_retries: No. of AMPDUs retried (SW) * @a_xretries: No. of AMPDUs dropped due to xretries @@ -102,6 +103,9 @@ struct ath_interrupt_stats { * @desc_cfg_err: Descriptor configuration errors * @data_urn: TX data underrun errors * @delim_urn: TX delimiter underrun errors + * @puttxbuf: Number of times hardware was given txbuf to write. + * @txstart: Number of times hardware was told to start tx. + * @txprocdesc: Number of times tx descriptor was processed */ struct ath_tx_stats { u32 tx_pkts_all; @@ -109,7 +113,8 @@ struct ath_tx_stats { u32 queued; u32 completed; u32 a_aggr; - u32 a_queued; + u32 a_queued_hw; + u32 a_queued_sw; u32 a_completed; u32 a_retries; u32 a_xretries; @@ -119,6 +124,9 @@ struct ath_tx_stats { u32 desc_cfg_err; u32 data_underrun; u32 delim_underrun; + u32 puttxbuf; + u32 txstart; + u32 txprocdesc; }; /** diff --git a/drivers/net/wireless/ath/ath9k/eeprom.c b/drivers/net/wireless/ath/ath9k/eeprom.c index d051631..8c18bed 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom.c +++ b/drivers/net/wireless/ath/ath9k/eeprom.c @@ -89,6 +89,38 @@ bool ath9k_hw_get_lower_upper_index(u8 target, u8 *pList, u16 listSize, return false; } +void ath9k_hw_usb_gen_fill_eeprom(struct ath_hw *ah, u16 *eep_data, + int eep_start_loc, int size) +{ + int i = 0, j, addr; + u32 addrdata[8]; + u32 data[8]; + + for (addr = 0; addr < size; addr++) { + addrdata[i] = AR5416_EEPROM_OFFSET + + ((addr + eep_start_loc) << AR5416_EEPROM_S); + i++; + if (i == 8) { + REG_READ_MULTI(ah, addrdata, data, i); + + for (j = 0; j < i; j++) { + *eep_data = data[j]; + eep_data++; + } + i = 0; + } + } + + if (i != 0) { + REG_READ_MULTI(ah, addrdata, data, i); + + for (j = 0; j < i; j++) { + *eep_data = data[j]; + eep_data++; + } + } +} + bool ath9k_hw_nvram_read(struct ath_common *common, u32 off, u16 *data) { return common->bus_ops->eeprom_read(common, off, data); diff --git a/drivers/net/wireless/ath/ath9k/eeprom.h b/drivers/net/wireless/ath/ath9k/eeprom.h index 58e2ddc..bd82447 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom.h +++ b/drivers/net/wireless/ath/ath9k/eeprom.h @@ -665,6 +665,8 @@ int16_t ath9k_hw_interpolate(u16 target, u16 srcLeft, u16 srcRight, bool ath9k_hw_get_lower_upper_index(u8 target, u8 *pList, u16 listSize, u16 *indexL, u16 *indexR); bool ath9k_hw_nvram_read(struct ath_common *common, u32 off, u16 *data); +void ath9k_hw_usb_gen_fill_eeprom(struct ath_hw *ah, u16 *eep_data, + int eep_start_loc, int size); void ath9k_hw_fill_vpd_table(u8 pwrMin, u8 pwrMax, u8 *pPwrList, u8 *pVpdList, u16 numIntercepts, u8 *pRetVpdList); diff --git a/drivers/net/wireless/ath/ath9k/eeprom_4k.c b/drivers/net/wireless/ath/ath9k/eeprom_4k.c index fbdff7e..bc77a30 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom_4k.c +++ b/drivers/net/wireless/ath/ath9k/eeprom_4k.c @@ -27,19 +27,13 @@ static int ath9k_hw_4k_get_eeprom_rev(struct ath_hw *ah) return ((ah->eeprom.map4k.baseEepHeader.version) & 0xFFF); } -static bool ath9k_hw_4k_fill_eeprom(struct ath_hw *ah) -{ #define SIZE_EEPROM_4K (sizeof(struct ar5416_eeprom_4k) / sizeof(u16)) + +static bool __ath9k_hw_4k_fill_eeprom(struct ath_hw *ah) +{ struct ath_common *common = ath9k_hw_common(ah); u16 *eep_data = (u16 *)&ah->eeprom.map4k; - int addr, eep_start_loc = 0; - - eep_start_loc = 64; - - if (!ath9k_hw_use_flash(ah)) { - ath_dbg(common, ATH_DBG_EEPROM, - "Reading from EEPROM, not flash\n"); - } + int addr, eep_start_loc = 64; for (addr = 0; addr < SIZE_EEPROM_4K; addr++) { if (!ath9k_hw_nvram_read(common, addr + eep_start_loc, eep_data)) { @@ -51,9 +45,34 @@ static bool ath9k_hw_4k_fill_eeprom(struct ath_hw *ah) } return true; -#undef SIZE_EEPROM_4K } +static bool __ath9k_hw_usb_4k_fill_eeprom(struct ath_hw *ah) +{ + u16 *eep_data = (u16 *)&ah->eeprom.map4k; + + ath9k_hw_usb_gen_fill_eeprom(ah, eep_data, 64, SIZE_EEPROM_4K); + + return true; +} + +static bool ath9k_hw_4k_fill_eeprom(struct ath_hw *ah) +{ + struct ath_common *common = ath9k_hw_common(ah); + + if (!ath9k_hw_use_flash(ah)) { + ath_dbg(common, ATH_DBG_EEPROM, + "Reading from EEPROM, not flash\n"); + } + + if (common->bus_ops->ath_bus_type == ATH_USB) + return __ath9k_hw_usb_4k_fill_eeprom(ah); + else + return __ath9k_hw_4k_fill_eeprom(ah); +} + +#undef SIZE_EEPROM_4K + static int ath9k_hw_4k_check_eeprom(struct ath_hw *ah) { #define EEPROM_4K_SIZE (sizeof(struct ar5416_eeprom_4k) / sizeof(u16)) diff --git a/drivers/net/wireless/ath/ath9k/eeprom_9287.c b/drivers/net/wireless/ath/ath9k/eeprom_9287.c index 9b6bc8a..8cd8333 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom_9287.c +++ b/drivers/net/wireless/ath/ath9k/eeprom_9287.c @@ -17,7 +17,7 @@ #include "hw.h" #include "ar9002_phy.h" -#define NUM_EEP_WORDS (sizeof(struct ar9287_eeprom) / sizeof(u16)) +#define SIZE_EEPROM_AR9287 (sizeof(struct ar9287_eeprom) / sizeof(u16)) static int ath9k_hw_ar9287_get_eeprom_ver(struct ath_hw *ah) { @@ -29,25 +29,15 @@ static int ath9k_hw_ar9287_get_eeprom_rev(struct ath_hw *ah) return (ah->eeprom.map9287.baseEepHeader.version) & 0xFFF; } -static bool ath9k_hw_ar9287_fill_eeprom(struct ath_hw *ah) +static bool __ath9k_hw_ar9287_fill_eeprom(struct ath_hw *ah) { struct ar9287_eeprom *eep = &ah->eeprom.map9287; struct ath_common *common = ath9k_hw_common(ah); u16 *eep_data; - int addr, eep_start_loc; + int addr, eep_start_loc = AR9287_EEP_START_LOC; eep_data = (u16 *)eep; - if (common->bus_ops->ath_bus_type == ATH_USB) - eep_start_loc = AR9287_HTC_EEP_START_LOC; - else - eep_start_loc = AR9287_EEP_START_LOC; - - if (!ath9k_hw_use_flash(ah)) { - ath_dbg(common, ATH_DBG_EEPROM, - "Reading from EEPROM, not flash\n"); - } - - for (addr = 0; addr < NUM_EEP_WORDS; addr++) { + for (addr = 0; addr < SIZE_EEPROM_AR9287; addr++) { if (!ath9k_hw_nvram_read(common, addr + eep_start_loc, eep_data)) { ath_dbg(common, ATH_DBG_EEPROM, @@ -60,6 +50,31 @@ static bool ath9k_hw_ar9287_fill_eeprom(struct ath_hw *ah) return true; } +static bool __ath9k_hw_usb_ar9287_fill_eeprom(struct ath_hw *ah) +{ + u16 *eep_data = (u16 *)&ah->eeprom.map9287; + + ath9k_hw_usb_gen_fill_eeprom(ah, eep_data, + AR9287_HTC_EEP_START_LOC, + SIZE_EEPROM_AR9287); + return true; +} + +static bool ath9k_hw_ar9287_fill_eeprom(struct ath_hw *ah) +{ + struct ath_common *common = ath9k_hw_common(ah); + + if (!ath9k_hw_use_flash(ah)) { + ath_dbg(common, ATH_DBG_EEPROM, + "Reading from EEPROM, not flash\n"); + } + + if (common->bus_ops->ath_bus_type == ATH_USB) + return __ath9k_hw_usb_ar9287_fill_eeprom(ah); + else + return __ath9k_hw_ar9287_fill_eeprom(ah); +} + static int ath9k_hw_ar9287_check_eeprom(struct ath_hw *ah) { u32 sum = 0, el, integer; @@ -86,7 +101,7 @@ static int ath9k_hw_ar9287_check_eeprom(struct ath_hw *ah) need_swap = true; eepdata = (u16 *)(&ah->eeprom); - for (addr = 0; addr < NUM_EEP_WORDS; addr++) { + for (addr = 0; addr < SIZE_EEPROM_AR9287; addr++) { temp = swab16(*eepdata); *eepdata = temp; eepdata++; diff --git a/drivers/net/wireless/ath/ath9k/eeprom_def.c b/drivers/net/wireless/ath/ath9k/eeprom_def.c index 749a936..c9318ff 100644 --- a/drivers/net/wireless/ath/ath9k/eeprom_def.c +++ b/drivers/net/wireless/ath/ath9k/eeprom_def.c @@ -86,9 +86,10 @@ static int ath9k_hw_def_get_eeprom_rev(struct ath_hw *ah) return ((ah->eeprom.def.baseEepHeader.version) & 0xFFF); } -static bool ath9k_hw_def_fill_eeprom(struct ath_hw *ah) -{ #define SIZE_EEPROM_DEF (sizeof(struct ar5416_eeprom_def) / sizeof(u16)) + +static bool __ath9k_hw_def_fill_eeprom(struct ath_hw *ah) +{ struct ath_common *common = ath9k_hw_common(ah); u16 *eep_data = (u16 *)&ah->eeprom.def; int addr, ar5416_eep_start_loc = 0x100; @@ -103,9 +104,34 @@ static bool ath9k_hw_def_fill_eeprom(struct ath_hw *ah) eep_data++; } return true; -#undef SIZE_EEPROM_DEF } +static bool __ath9k_hw_usb_def_fill_eeprom(struct ath_hw *ah) +{ + u16 *eep_data = (u16 *)&ah->eeprom.def; + + ath9k_hw_usb_gen_fill_eeprom(ah, eep_data, + 0x100, SIZE_EEPROM_DEF); + return true; +} + +static bool ath9k_hw_def_fill_eeprom(struct ath_hw *ah) +{ + struct ath_common *common = ath9k_hw_common(ah); + + if (!ath9k_hw_use_flash(ah)) { + ath_dbg(common, ATH_DBG_EEPROM, + "Reading from EEPROM, not flash\n"); + } + + if (common->bus_ops->ath_bus_type == ATH_USB) + return __ath9k_hw_usb_def_fill_eeprom(ah); + else + return __ath9k_hw_def_fill_eeprom(ah); +} + +#undef SIZE_EEPROM_DEF + static int ath9k_hw_def_check_eeprom(struct ath_hw *ah) { struct ar5416_eeprom_def *eep = diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h index 780ac5e..6354986 100644 --- a/drivers/net/wireless/ath/ath9k/htc.h +++ b/drivers/net/wireless/ath/ath9k/htc.h @@ -366,7 +366,7 @@ struct ath9k_htc_priv { u16 seq_no; u32 bmiss_cnt; - struct ath9k_hw_cal_data caldata[ATH9K_NUM_CHANNELS]; + struct ath9k_hw_cal_data caldata; spinlock_t beacon_lock; diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_init.c b/drivers/net/wireless/ath/ath9k/htc_drv_init.c index 38433f9..8e04586 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_init.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_init.c @@ -297,6 +297,34 @@ static unsigned int ath9k_regread(void *hw_priv, u32 reg_offset) return be32_to_cpu(val); } +static void ath9k_multi_regread(void *hw_priv, u32 *addr, + u32 *val, u16 count) +{ + struct ath_hw *ah = (struct ath_hw *) hw_priv; + struct ath_common *common = ath9k_hw_common(ah); + struct ath9k_htc_priv *priv = (struct ath9k_htc_priv *) common->priv; + __be32 tmpaddr[8]; + __be32 tmpval[8]; + int i, ret; + + for (i = 0; i < count; i++) { + tmpaddr[i] = cpu_to_be32(addr[i]); + } + + ret = ath9k_wmi_cmd(priv->wmi, WMI_REG_READ_CMDID, + (u8 *)tmpaddr , sizeof(u32) * count, + (u8 *)tmpval, sizeof(u32) * count, + 100); + if (unlikely(ret)) { + ath_dbg(common, ATH_DBG_WMI, + "Multiple REGISTER READ FAILED (count: %d)\n", count); + } + + for (i = 0; i < count; i++) { + val[i] = be32_to_cpu(tmpval[i]); + } +} + static void ath9k_regwrite_single(void *hw_priv, u32 val, u32 reg_offset) { struct ath_hw *ah = (struct ath_hw *) hw_priv; @@ -407,6 +435,7 @@ static void ath9k_regwrite_flush(void *hw_priv) static const struct ath_ops ath9k_common_ops = { .read = ath9k_regread, + .multi_read = ath9k_multi_regread, .write = ath9k_regwrite, .enable_write_buffer = ath9k_enable_regwrite_buffer, .write_flush = ath9k_regwrite_flush, diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_main.c b/drivers/net/wireless/ath/ath9k/htc_drv_main.c index f4d576b..f14f37d 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_main.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_main.c @@ -121,7 +121,7 @@ void ath9k_htc_reset(struct ath9k_htc_priv *priv) struct ath_hw *ah = priv->ah; struct ath_common *common = ath9k_hw_common(ah); struct ieee80211_channel *channel = priv->hw->conf.channel; - struct ath9k_hw_cal_data *caldata; + struct ath9k_hw_cal_data *caldata = NULL; enum htc_phymode mode; __be16 htc_mode; u8 cmd_rsp; @@ -139,7 +139,7 @@ void ath9k_htc_reset(struct ath9k_htc_priv *priv) WMI_CMD(WMI_DRAIN_TXQ_ALL_CMDID); WMI_CMD(WMI_STOP_RECV_CMDID); - caldata = &priv->caldata[channel->hw_value]; + caldata = &priv->caldata; ret = ath9k_hw_reset(ah, ah->curchan, caldata, false); if (ret) { ath_err(common, @@ -202,7 +202,8 @@ static int ath9k_htc_set_channel(struct ath9k_htc_priv *priv, channel->center_freq, conf_is_ht(conf), conf_is_ht40(conf), fastcc); - caldata = &priv->caldata[channel->hw_value]; + if (!fastcc) + caldata = &priv->caldata; ret = ath9k_hw_reset(ah, hchan, caldata, fastcc); if (ret) { ath_err(common, @@ -1548,7 +1549,7 @@ static int ath9k_htc_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, - u16 tid, u16 *ssn) + u16 tid, u16 *ssn, u8 buf_size) { struct ath9k_htc_priv *priv = hw->priv; struct ath9k_htc_sta *ista; diff --git a/drivers/net/wireless/ath/ath9k/hw.c b/drivers/net/wireless/ath/ath9k/hw.c index 9f01e50..4615fd9 100644 --- a/drivers/net/wireless/ath/ath9k/hw.c +++ b/drivers/net/wireless/ath/ath9k/hw.c @@ -495,6 +495,17 @@ static int __ath9k_hw_init(struct ath_hw *ah) if (ah->hw_version.devid == AR5416_AR9100_DEVID) ah->hw_version.macVersion = AR_SREV_VERSION_9100; + ath9k_hw_read_revisions(ah); + + /* + * Read back AR_WA into a permanent copy and set bits 14 and 17. + * We need to do this to avoid RMW of this register. We cannot + * read the reg when chip is asleep. + */ + ah->WARegVal = REG_READ(ah, AR_WA); + ah->WARegVal |= (AR_WA_D3_L1_DISABLE | + AR_WA_ASPM_TIMER_BASED_DISABLE); + if (!ath9k_hw_set_reset_reg(ah, ATH9K_RESET_POWER_ON)) { ath_err(common, "Couldn't reset chip\n"); return -EIO; @@ -563,14 +574,6 @@ static int __ath9k_hw_init(struct ath_hw *ah) ath9k_hw_init_mode_regs(ah); - /* - * Read back AR_WA into a permanent copy and set bits 14 and 17. - * We need to do this to avoid RMW of this register. We cannot - * read the reg when chip is asleep. - */ - ah->WARegVal = REG_READ(ah, AR_WA); - ah->WARegVal |= (AR_WA_D3_L1_DISABLE | - AR_WA_ASPM_TIMER_BASED_DISABLE); if (ah->is_pciexpress) ath9k_hw_configpcipowersave(ah, 0, 0); @@ -1082,8 +1085,6 @@ static bool ath9k_hw_set_reset_power_on(struct ath_hw *ah) return false; } - ath9k_hw_read_revisions(ah); - return ath9k_hw_set_reset(ah, ATH9K_RESET_WARM); } diff --git a/drivers/net/wireless/ath/ath9k/hw.h b/drivers/net/wireless/ath/ath9k/hw.h index ea9fde6..ad8c2c7 100644 --- a/drivers/net/wireless/ath/ath9k/hw.h +++ b/drivers/net/wireless/ath/ath9k/hw.h @@ -70,6 +70,9 @@ #define REG_READ(_ah, _reg) \ ath9k_hw_common(_ah)->ops->read((_ah), (_reg)) +#define REG_READ_MULTI(_ah, _addr, _val, _cnt) \ + ath9k_hw_common(_ah)->ops->multi_read((_ah), (_addr), (_val), (_cnt)) + #define ENABLE_REGWRITE_BUFFER(_ah) \ do { \ if (ath9k_hw_common(_ah)->ops->enable_write_buffer) \ diff --git a/drivers/net/wireless/ath/ath9k/init.c b/drivers/net/wireless/ath/ath9k/init.c index 767d8b8..5279653 100644 --- a/drivers/net/wireless/ath/ath9k/init.c +++ b/drivers/net/wireless/ath/ath9k/init.c @@ -442,9 +442,10 @@ static int ath9k_init_queues(struct ath_softc *sc) sc->config.cabqReadytime = ATH_CABQ_READY_TIME; ath_cabq_update(sc); - for (i = 0; i < WME_NUM_AC; i++) + for (i = 0; i < WME_NUM_AC; i++) { sc->tx.txq_map[i] = ath_txq_setup(sc, ATH9K_TX_QUEUE_DATA, i); - + sc->tx.txq_map[i]->mac80211_qnum = i; + } return 0; } @@ -537,6 +538,7 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc, u16 subsysid, if (!ah) return -ENOMEM; + ah->hw = sc->hw; ah->hw_version.devid = devid; ah->hw_version.subsysid = subsysid; sc->sc_ah = ah; @@ -558,6 +560,10 @@ static int ath9k_init_softc(u16 devid, struct ath_softc *sc, u16 subsysid, spin_lock_init(&sc->sc_serial_rw); spin_lock_init(&sc->sc_pm_lock); mutex_init(&sc->mutex); +#ifdef CONFIG_ATH9K_DEBUGFS + spin_lock_init(&sc->nodes_lock); + INIT_LIST_HEAD(&sc->nodes); +#endif tasklet_init(&sc->intr_tq, ath9k_tasklet, (unsigned long)sc); tasklet_init(&sc->bcon_tasklet, ath_beacon_tasklet, (unsigned long)sc); diff --git a/drivers/net/wireless/ath/ath9k/mac.c b/drivers/net/wireless/ath/ath9k/mac.c index 180170d..c75d40f 100644 --- a/drivers/net/wireless/ath/ath9k/mac.c +++ b/drivers/net/wireless/ath/ath9k/mac.c @@ -690,17 +690,23 @@ int ath9k_hw_rxprocdesc(struct ath_hw *ah, struct ath_desc *ds, rs->rs_flags |= ATH9K_RX_DECRYPT_BUSY; if ((ads.ds_rxstatus8 & AR_RxFrameOK) == 0) { + /* + * Treat these errors as mutually exclusive to avoid spurious + * extra error reports from the hardware. If a CRC error is + * reported, then decryption and MIC errors are irrelevant, + * the frame is going to be dropped either way + */ if (ads.ds_rxstatus8 & AR_CRCErr) rs->rs_status |= ATH9K_RXERR_CRC; - if (ads.ds_rxstatus8 & AR_PHYErr) { + else if (ads.ds_rxstatus8 & AR_PHYErr) { rs->rs_status |= ATH9K_RXERR_PHY; phyerr = MS(ads.ds_rxstatus8, AR_PHYErrCode); rs->rs_phyerr = phyerr; - } - if (ads.ds_rxstatus8 & AR_DecryptCRCErr) + } else if (ads.ds_rxstatus8 & AR_DecryptCRCErr) rs->rs_status |= ATH9K_RXERR_DECRYPT; - if (ads.ds_rxstatus8 & AR_MichaelErr) + else if (ads.ds_rxstatus8 & AR_MichaelErr) rs->rs_status |= ATH9K_RXERR_MIC; + if (ads.ds_rxstatus8 & AR_KeyMiss) rs->rs_status |= ATH9K_RXERR_DECRYPT; } diff --git a/drivers/net/wireless/ath/ath9k/main.c b/drivers/net/wireless/ath/ath9k/main.c index c79c97b..facff10 100644 --- a/drivers/net/wireless/ath/ath9k/main.c +++ b/drivers/net/wireless/ath/ath9k/main.c @@ -251,6 +251,9 @@ int ath_set_channel(struct ath_softc *sc, struct ieee80211_hw *hw, if (!ath_stoprecv(sc)) stopped = false; + if (!ath9k_hw_check_alive(ah)) + stopped = false; + /* XXX: do not flush receive queue here. We don't want * to flush data frames already in queue because of * changing channel. */ @@ -545,6 +548,12 @@ static void ath_node_attach(struct ath_softc *sc, struct ieee80211_sta *sta) struct ath_hw *ah = sc->sc_ah; an = (struct ath_node *)sta->drv_priv; +#ifdef CONFIG_ATH9K_DEBUGFS + spin_lock(&sc->nodes_lock); + list_add(&an->list, &sc->nodes); + spin_unlock(&sc->nodes_lock); + an->sta = sta; +#endif if ((ah->caps.hw_caps) & ATH9K_HW_CAP_APM) sc->sc_flags |= SC_OP_ENABLE_APM; @@ -560,6 +569,13 @@ static void ath_node_detach(struct ath_softc *sc, struct ieee80211_sta *sta) { struct ath_node *an = (struct ath_node *)sta->drv_priv; +#ifdef CONFIG_ATH9K_DEBUGFS + spin_lock(&sc->nodes_lock); + list_del(&an->list); + spin_unlock(&sc->nodes_lock); + an->sta = NULL; +#endif + if (sc->sc_flags & SC_OP_TXAGGR) ath_tx_node_cleanup(sc, an); } @@ -600,7 +616,15 @@ void ath9k_tasklet(unsigned long data) ath9k_ps_wakeup(sc); spin_lock(&sc->sc_pcu_lock); - if (!ath9k_hw_check_alive(ah)) + /* + * Only run the baseband hang check if beacons stop working in AP or + * IBSS mode, because it has a high false positive rate. For station + * mode it should not be necessary, since the upper layers will detect + * this through a beacon miss automatically and the following channel + * change will trigger a hardware reset anyway + */ + if (ath9k_hw_numtxpending(ah, sc->beacon.beaconq) != 0 && + !ath9k_hw_check_alive(ah)) ieee80211_queue_work(sc->hw, &sc->hw_check_work); if (ah->caps.hw_caps & ATH9K_HW_CAP_EDMA) @@ -1341,112 +1365,251 @@ static void ath9k_stop(struct ieee80211_hw *hw) ath_dbg(common, ATH_DBG_CONFIG, "Driver halt\n"); } -static int ath9k_add_interface(struct ieee80211_hw *hw, - struct ieee80211_vif *vif) +bool ath9k_uses_beacons(int type) +{ + switch (type) { + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_MESH_POINT: + return true; + default: + return false; + } +} + +static void ath9k_reclaim_beacon(struct ath_softc *sc, + struct ieee80211_vif *vif) { - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; - struct ath_hw *ah = sc->sc_ah; - struct ath_common *common = ath9k_hw_common(ah); struct ath_vif *avp = (void *)vif->drv_priv; - enum nl80211_iftype ic_opmode = NL80211_IFTYPE_UNSPECIFIED; - int ret = 0; - mutex_lock(&sc->mutex); + /* Disable SWBA interrupt */ + sc->sc_ah->imask &= ~ATH9K_INT_SWBA; + ath9k_ps_wakeup(sc); + ath9k_hw_set_interrupts(sc->sc_ah, sc->sc_ah->imask); + ath9k_hw_stoptxdma(sc->sc_ah, sc->beacon.beaconq); + tasklet_kill(&sc->bcon_tasklet); + ath9k_ps_restore(sc); + + ath_beacon_return(sc, avp); + sc->sc_flags &= ~SC_OP_BEACONS; + + if (sc->nbcnvifs > 0) { + /* Re-enable beaconing */ + sc->sc_ah->imask |= ATH9K_INT_SWBA; + ath9k_ps_wakeup(sc); + ath9k_hw_set_interrupts(sc->sc_ah, sc->sc_ah->imask); + ath9k_ps_restore(sc); + } +} + +static void ath9k_vif_iter(void *data, u8 *mac, struct ieee80211_vif *vif) +{ + struct ath9k_vif_iter_data *iter_data = data; + int i; + + if (iter_data->hw_macaddr) + for (i = 0; i < ETH_ALEN; i++) + iter_data->mask[i] &= + ~(iter_data->hw_macaddr[i] ^ mac[i]); switch (vif->type) { - case NL80211_IFTYPE_STATION: - ic_opmode = NL80211_IFTYPE_STATION; + case NL80211_IFTYPE_AP: + iter_data->naps++; break; - case NL80211_IFTYPE_WDS: - ic_opmode = NL80211_IFTYPE_WDS; + case NL80211_IFTYPE_STATION: + iter_data->nstations++; break; case NL80211_IFTYPE_ADHOC: - case NL80211_IFTYPE_AP: + iter_data->nadhocs++; + break; case NL80211_IFTYPE_MESH_POINT: - if (sc->nbcnvifs >= ATH_BCBUF) { - ret = -ENOBUFS; - goto out; - } - ic_opmode = vif->type; + iter_data->nmeshes++; + break; + case NL80211_IFTYPE_WDS: + iter_data->nwds++; break; default: - ath_err(common, "Interface type %d not yet supported\n", - vif->type); - ret = -EOPNOTSUPP; - goto out; + iter_data->nothers++; + break; } +} - ath_dbg(common, ATH_DBG_CONFIG, - "Attach a VIF of type: %d\n", ic_opmode); +/* Called with sc->mutex held. */ +void ath9k_calculate_iter_data(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + struct ath9k_vif_iter_data *iter_data) +{ + struct ath_wiphy *aphy = hw->priv; + struct ath_softc *sc = aphy->sc; + struct ath_hw *ah = sc->sc_ah; + struct ath_common *common = ath9k_hw_common(ah); + int i; - /* Set the VIF opmode */ - avp->av_opmode = ic_opmode; - avp->av_bslot = -1; + /* + * Use the hardware MAC address as reference, the hardware uses it + * together with the BSSID mask when matching addresses. + */ + memset(iter_data, 0, sizeof(*iter_data)); + iter_data->hw_macaddr = common->macaddr; + memset(&iter_data->mask, 0xff, ETH_ALEN); - sc->nvifs++; + if (vif) + ath9k_vif_iter(iter_data, vif->addr, vif); - ath9k_set_bssid_mask(hw, vif); + /* Get list of all active MAC addresses */ + spin_lock_bh(&sc->wiphy_lock); + ieee80211_iterate_active_interfaces_atomic(sc->hw, ath9k_vif_iter, + iter_data); + for (i = 0; i < sc->num_sec_wiphy; i++) { + if (sc->sec_wiphy[i] == NULL) + continue; + ieee80211_iterate_active_interfaces_atomic( + sc->sec_wiphy[i]->hw, ath9k_vif_iter, iter_data); + } + spin_unlock_bh(&sc->wiphy_lock); +} - if (sc->nvifs > 1) - goto out; /* skip global settings for secondary vif */ +/* Called with sc->mutex held. */ +static void ath9k_calculate_summary_state(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) +{ + struct ath_wiphy *aphy = hw->priv; + struct ath_softc *sc = aphy->sc; + struct ath_hw *ah = sc->sc_ah; + struct ath_common *common = ath9k_hw_common(ah); + struct ath9k_vif_iter_data iter_data; + + ath9k_calculate_iter_data(hw, vif, &iter_data); - if (ic_opmode == NL80211_IFTYPE_AP) { + /* Set BSSID mask. */ + memcpy(common->bssidmask, iter_data.mask, ETH_ALEN); + ath_hw_setbssidmask(common); + + /* Set op-mode & TSF */ + if (iter_data.naps > 0) { ath9k_hw_set_tsfadjust(ah, 1); sc->sc_flags |= SC_OP_TSF_RESET; - } + ah->opmode = NL80211_IFTYPE_AP; + } else { + ath9k_hw_set_tsfadjust(ah, 0); + sc->sc_flags &= ~SC_OP_TSF_RESET; - /* Set the device opmode */ - ah->opmode = ic_opmode; + if (iter_data.nwds + iter_data.nmeshes) + ah->opmode = NL80211_IFTYPE_AP; + else if (iter_data.nadhocs) + ah->opmode = NL80211_IFTYPE_ADHOC; + else + ah->opmode = NL80211_IFTYPE_STATION; + } /* * Enable MIB interrupts when there are hardware phy counters. - * Note we only do this (at the moment) for station mode. */ - if ((vif->type == NL80211_IFTYPE_STATION) || - (vif->type == NL80211_IFTYPE_ADHOC) || - (vif->type == NL80211_IFTYPE_MESH_POINT)) { + if ((iter_data.nstations + iter_data.nadhocs + iter_data.nmeshes) > 0) { if (ah->config.enable_ani) ah->imask |= ATH9K_INT_MIB; ah->imask |= ATH9K_INT_TSFOOR; + } else { + ah->imask &= ~ATH9K_INT_MIB; + ah->imask &= ~ATH9K_INT_TSFOOR; } ath9k_hw_set_interrupts(ah, ah->imask); - if (vif->type == NL80211_IFTYPE_AP || - vif->type == NL80211_IFTYPE_ADHOC) { + /* Set up ANI */ + if ((iter_data.naps + iter_data.nadhocs) > 0) { sc->sc_flags |= SC_OP_ANI_RUN; ath_start_ani(common); + } else { + sc->sc_flags &= ~SC_OP_ANI_RUN; + del_timer_sync(&common->ani.timer); } +} -out: - mutex_unlock(&sc->mutex); - return ret; +/* Called with sc->mutex held, vif counts set up properly. */ +static void ath9k_do_vif_add_setup(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) +{ + struct ath_wiphy *aphy = hw->priv; + struct ath_softc *sc = aphy->sc; + + ath9k_calculate_summary_state(hw, vif); + + if (ath9k_uses_beacons(vif->type)) { + int error; + ath9k_hw_stoptxdma(sc->sc_ah, sc->beacon.beaconq); + /* This may fail because upper levels do not have beacons + * properly configured yet. That's OK, we assume it + * will be properly configured and then we will be notified + * in the info_changed method and set up beacons properly + * there. + */ + error = ath_beacon_alloc(aphy, vif); + if (error) + ath9k_reclaim_beacon(sc, vif); + else + ath_beacon_config(sc, vif); + } } -static void ath9k_reclaim_beacon(struct ath_softc *sc, - struct ieee80211_vif *vif) + +static int ath9k_add_interface(struct ieee80211_hw *hw, + struct ieee80211_vif *vif) { + struct ath_wiphy *aphy = hw->priv; + struct ath_softc *sc = aphy->sc; + struct ath_hw *ah = sc->sc_ah; + struct ath_common *common = ath9k_hw_common(ah); struct ath_vif *avp = (void *)vif->drv_priv; + int ret = 0; - /* Disable SWBA interrupt */ - sc->sc_ah->imask &= ~ATH9K_INT_SWBA; - ath9k_ps_wakeup(sc); - ath9k_hw_set_interrupts(sc->sc_ah, sc->sc_ah->imask); - ath9k_hw_stoptxdma(sc->sc_ah, sc->beacon.beaconq); - tasklet_kill(&sc->bcon_tasklet); - ath9k_ps_restore(sc); + mutex_lock(&sc->mutex); - ath_beacon_return(sc, avp); - sc->sc_flags &= ~SC_OP_BEACONS; + switch (vif->type) { + case NL80211_IFTYPE_STATION: + case NL80211_IFTYPE_WDS: + case NL80211_IFTYPE_ADHOC: + case NL80211_IFTYPE_AP: + case NL80211_IFTYPE_MESH_POINT: + break; + default: + ath_err(common, "Interface type %d not yet supported\n", + vif->type); + ret = -EOPNOTSUPP; + goto out; + } - if (sc->nbcnvifs > 0) { - /* Re-enable beaconing */ - sc->sc_ah->imask |= ATH9K_INT_SWBA; - ath9k_ps_wakeup(sc); - ath9k_hw_set_interrupts(sc->sc_ah, sc->sc_ah->imask); - ath9k_ps_restore(sc); + if (ath9k_uses_beacons(vif->type)) { + if (sc->nbcnvifs >= ATH_BCBUF) { + ath_err(common, "Not enough beacon buffers when adding" + " new interface of type: %i\n", + vif->type); + ret = -ENOBUFS; + goto out; + } } + + if ((vif->type == NL80211_IFTYPE_ADHOC) && + sc->nvifs > 0) { + ath_err(common, "Cannot create ADHOC interface when other" + " interfaces already exist.\n"); + ret = -EINVAL; + goto out; + } + + ath_dbg(common, ATH_DBG_CONFIG, + "Attach a VIF of type: %d\n", vif->type); + + /* Set the VIF opmode */ + avp->av_opmode = vif->type; + avp->av_bslot = -1; + + sc->nvifs++; + + ath9k_do_vif_add_setup(hw, vif); +out: + mutex_unlock(&sc->mutex); + return ret; } static int ath9k_change_interface(struct ieee80211_hw *hw, @@ -1462,32 +1625,33 @@ static int ath9k_change_interface(struct ieee80211_hw *hw, ath_dbg(common, ATH_DBG_CONFIG, "Change Interface\n"); mutex_lock(&sc->mutex); - switch (new_type) { - case NL80211_IFTYPE_AP: - case NL80211_IFTYPE_ADHOC: + /* See if new interface type is valid. */ + if ((new_type == NL80211_IFTYPE_ADHOC) && + (sc->nvifs > 1)) { + ath_err(common, "When using ADHOC, it must be the only" + " interface.\n"); + ret = -EINVAL; + goto out; + } + + if (ath9k_uses_beacons(new_type) && + !ath9k_uses_beacons(vif->type)) { if (sc->nbcnvifs >= ATH_BCBUF) { ath_err(common, "No beacon slot available\n"); ret = -ENOBUFS; goto out; } - break; - case NL80211_IFTYPE_STATION: - /* Stop ANI */ - sc->sc_flags &= ~SC_OP_ANI_RUN; - del_timer_sync(&common->ani.timer); - if ((vif->type == NL80211_IFTYPE_AP) || - (vif->type == NL80211_IFTYPE_ADHOC)) - ath9k_reclaim_beacon(sc, vif); - break; - default: - ath_err(common, "Interface type %d not yet supported\n", - vif->type); - ret = -ENOTSUPP; - goto out; } + + /* Clean up old vif stuff */ + if (ath9k_uses_beacons(vif->type)) + ath9k_reclaim_beacon(sc, vif); + + /* Add new settings */ vif->type = new_type; vif->p2p = p2p; + ath9k_do_vif_add_setup(hw, vif); out: mutex_unlock(&sc->mutex); return ret; @@ -1504,17 +1668,13 @@ static void ath9k_remove_interface(struct ieee80211_hw *hw, mutex_lock(&sc->mutex); - /* Stop ANI */ - sc->sc_flags &= ~SC_OP_ANI_RUN; - del_timer_sync(&common->ani.timer); + sc->nvifs--; /* Reclaim beacon resources */ - if ((sc->sc_ah->opmode == NL80211_IFTYPE_AP) || - (sc->sc_ah->opmode == NL80211_IFTYPE_ADHOC) || - (sc->sc_ah->opmode == NL80211_IFTYPE_MESH_POINT)) + if (ath9k_uses_beacons(vif->type)) ath9k_reclaim_beacon(sc, vif); - sc->nvifs--; + ath9k_calculate_summary_state(hw, NULL); mutex_unlock(&sc->mutex); } @@ -2020,7 +2180,7 @@ static int ath9k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, - u16 tid, u16 *ssn) + u16 tid, u16 *ssn, u8 buf_size) { struct ath_wiphy *aphy = hw->priv; struct ath_softc *sc = aphy->sc; diff --git a/drivers/net/wireless/ath/ath9k/recv.c b/drivers/net/wireless/ath/ath9k/recv.c index b2497b8..116f058 100644 --- a/drivers/net/wireless/ath/ath9k/recv.c +++ b/drivers/net/wireless/ath/ath9k/recv.c @@ -588,8 +588,14 @@ static void ath_rx_ps_beacon(struct ath_softc *sc, struct sk_buff *skb) return; mgmt = (struct ieee80211_mgmt *)skb->data; - if (memcmp(common->curbssid, mgmt->bssid, ETH_ALEN) != 0) + if (memcmp(common->curbssid, mgmt->bssid, ETH_ALEN) != 0) { + /* TODO: This doesn't work well if you have stations + * associated to two different APs because curbssid + * is just the last AP that any of the stations associated + * with. + */ return; /* not from our current AP */ + } sc->ps_flags &= ~PS_WAIT_FOR_BEACON; @@ -984,8 +990,14 @@ static void ath9k_process_rssi(struct ath_common *common, fc = hdr->frame_control; if (!ieee80211_is_beacon(fc) || - compare_ether_addr(hdr->addr3, common->curbssid)) + compare_ether_addr(hdr->addr3, common->curbssid)) { + /* TODO: This doesn't work well if you have stations + * associated to two different APs because curbssid + * is just the last AP that any of the stations associated + * with. + */ return; + } if (rx_stats->rs_rssi != ATH9K_RSSI_BAD && !rx_stats->rs_moreaggr) ATH_RSSI_LPF(aphy->last_rssi, rx_stats->rs_rssi); diff --git a/drivers/net/wireless/ath/ath9k/virtual.c b/drivers/net/wireless/ath/ath9k/virtual.c index 2dc7095..d205c66 100644 --- a/drivers/net/wireless/ath/ath9k/virtual.c +++ b/drivers/net/wireless/ath/ath9k/virtual.c @@ -18,54 +18,6 @@ #include "ath9k.h" -struct ath9k_vif_iter_data { - const u8 *hw_macaddr; - u8 mask[ETH_ALEN]; -}; - -static void ath9k_vif_iter(void *data, u8 *mac, struct ieee80211_vif *vif) -{ - struct ath9k_vif_iter_data *iter_data = data; - int i; - - for (i = 0; i < ETH_ALEN; i++) - iter_data->mask[i] &= ~(iter_data->hw_macaddr[i] ^ mac[i]); -} - -void ath9k_set_bssid_mask(struct ieee80211_hw *hw, struct ieee80211_vif *vif) -{ - struct ath_wiphy *aphy = hw->priv; - struct ath_softc *sc = aphy->sc; - struct ath_common *common = ath9k_hw_common(sc->sc_ah); - struct ath9k_vif_iter_data iter_data; - int i; - - /* - * Use the hardware MAC address as reference, the hardware uses it - * together with the BSSID mask when matching addresses. - */ - iter_data.hw_macaddr = common->macaddr; - memset(&iter_data.mask, 0xff, ETH_ALEN); - - if (vif) - ath9k_vif_iter(&iter_data, vif->addr, vif); - - /* Get list of all active MAC addresses */ - spin_lock_bh(&sc->wiphy_lock); - ieee80211_iterate_active_interfaces_atomic(sc->hw, ath9k_vif_iter, - &iter_data); - for (i = 0; i < sc->num_sec_wiphy; i++) { - if (sc->sec_wiphy[i] == NULL) - continue; - ieee80211_iterate_active_interfaces_atomic( - sc->sec_wiphy[i]->hw, ath9k_vif_iter, &iter_data); - } - spin_unlock_bh(&sc->wiphy_lock); - - memcpy(common->bssidmask, iter_data.mask, ETH_ALEN); - ath_hw_setbssidmask(common); -} - int ath9k_wiphy_add(struct ath_softc *sc) { int i, error; diff --git a/drivers/net/wireless/ath/ath9k/xmit.c b/drivers/net/wireless/ath/ath9k/xmit.c index 33a37ed..dcac811 100644 --- a/drivers/net/wireless/ath/ath9k/xmit.c +++ b/drivers/net/wireless/ath/ath9k/xmit.c @@ -19,7 +19,6 @@ #define BITS_PER_BYTE 8 #define OFDM_PLCP_BITS 22 -#define HT_RC_2_MCS(_rc) ((_rc) & 0x1f) #define HT_RC_2_STREAMS(_rc) ((((_rc) & 0x78) >> 3) + 1) #define L_STF 8 #define L_LTF 8 @@ -32,7 +31,6 @@ #define NUM_SYMBOLS_PER_USEC(_usec) (_usec >> 2) #define NUM_SYMBOLS_PER_USEC_HALFGI(_usec) (((_usec*5)-4)/18) -#define OFDM_SIFS_TIME 16 static u16 bits_per_symbol[][2] = { /* 20MHz 40MHz */ @@ -169,7 +167,7 @@ static void ath_tx_flush_tid(struct ath_softc *sc, struct ath_atx_tid *tid) ath_tx_update_baw(sc, tid, fi->seqno); ath_tx_complete_buf(sc, bf, txq, &bf_head, &ts, 0, 0); } else { - ath_tx_send_normal(sc, txq, tid, &bf_head); + ath_tx_send_normal(sc, txq, NULL, &bf_head); } spin_lock_bh(&txq->axq_lock); } @@ -429,7 +427,7 @@ static void ath_tx_complete_aggr(struct ath_softc *sc, struct ath_txq *txq, ath_tx_count_frames(sc, bf, ts, txok, &nframes, &nbad); while (bf) { - txfail = txpending = 0; + txfail = txpending = sendbar = 0; bf_next = bf->bf_next; skb = bf->bf_mpdu; @@ -856,7 +854,10 @@ int ath_tx_aggr_start(struct ath_softc *sc, struct ieee80211_sta *sta, txtid->state |= AGGR_ADDBA_PROGRESS; txtid->paused = true; - *ssn = txtid->seq_start; + *ssn = txtid->seq_start = txtid->seq_next; + + memset(txtid->tx_buf, 0, sizeof(txtid->tx_buf)); + txtid->baw_head = txtid->baw_tail = 0; return 0; } @@ -942,7 +943,7 @@ struct ath_txq *ath_txq_setup(struct ath_softc *sc, int qtype, int subtype) [WME_AC_VI] = ATH_TXQ_AC_VI, [WME_AC_VO] = ATH_TXQ_AC_VO, }; - int qnum, i; + int axq_qnum, i; memset(&qi, 0, sizeof(qi)); qi.tqi_subtype = subtype_txq_to_hwq[subtype]; @@ -976,24 +977,25 @@ struct ath_txq *ath_txq_setup(struct ath_softc *sc, int qtype, int subtype) qi.tqi_qflags = TXQ_FLAG_TXEOLINT_ENABLE | TXQ_FLAG_TXDESCINT_ENABLE; } - qnum = ath9k_hw_setuptxqueue(ah, qtype, &qi); - if (qnum == -1) { + axq_qnum = ath9k_hw_setuptxqueue(ah, qtype, &qi); + if (axq_qnum == -1) { /* * NB: don't print a message, this happens * normally on parts with too few tx queues */ return NULL; } - if (qnum >= ARRAY_SIZE(sc->tx.txq)) { + if (axq_qnum >= ARRAY_SIZE(sc->tx.txq)) { ath_err(common, "qnum %u out of range, max %zu!\n", - qnum, ARRAY_SIZE(sc->tx.txq)); - ath9k_hw_releasetxqueue(ah, qnum); + axq_qnum, ARRAY_SIZE(sc->tx.txq)); + ath9k_hw_releasetxqueue(ah, axq_qnum); return NULL; } - if (!ATH_TXQ_SETUP(sc, qnum)) { - struct ath_txq *txq = &sc->tx.txq[qnum]; + if (!ATH_TXQ_SETUP(sc, axq_qnum)) { + struct ath_txq *txq = &sc->tx.txq[axq_qnum]; - txq->axq_qnum = qnum; + txq->axq_qnum = axq_qnum; + txq->mac80211_qnum = -1; txq->axq_link = NULL; INIT_LIST_HEAD(&txq->axq_q); INIT_LIST_HEAD(&txq->axq_acq); @@ -1001,14 +1003,14 @@ struct ath_txq *ath_txq_setup(struct ath_softc *sc, int qtype, int subtype) txq->axq_depth = 0; txq->axq_ampdu_depth = 0; txq->axq_tx_inprogress = false; - sc->tx.txqsetup |= 1<<qnum; + sc->tx.txqsetup |= 1<<axq_qnum; txq->txq_headidx = txq->txq_tailidx = 0; for (i = 0; i < ATH_TXFIFO_DEPTH; i++) INIT_LIST_HEAD(&txq->txq_fifo[i]); INIT_LIST_HEAD(&txq->txq_fifo_pending); } - return &sc->tx.txq[qnum]; + return &sc->tx.txq[axq_qnum]; } int ath_txq_update(struct ath_softc *sc, int qnum, @@ -1218,46 +1220,59 @@ void ath_tx_cleanupq(struct ath_softc *sc, struct ath_txq *txq) sc->tx.txqsetup &= ~(1<<txq->axq_qnum); } +/* For each axq_acq entry, for each tid, try to schedule packets + * for transmit until ampdu_depth has reached min Q depth. + */ void ath_txq_schedule(struct ath_softc *sc, struct ath_txq *txq) { - struct ath_atx_ac *ac; - struct ath_atx_tid *tid; + struct ath_atx_ac *ac, *ac_tmp, *last_ac; + struct ath_atx_tid *tid, *last_tid; - if (list_empty(&txq->axq_acq)) + if (list_empty(&txq->axq_acq) || + txq->axq_ampdu_depth >= ATH_AGGR_MIN_QDEPTH) return; ac = list_first_entry(&txq->axq_acq, struct ath_atx_ac, list); - list_del(&ac->list); - ac->sched = false; + last_ac = list_entry(txq->axq_acq.prev, struct ath_atx_ac, list); - do { - if (list_empty(&ac->tid_q)) - return; + list_for_each_entry_safe(ac, ac_tmp, &txq->axq_acq, list) { + last_tid = list_entry(ac->tid_q.prev, struct ath_atx_tid, list); + list_del(&ac->list); + ac->sched = false; - tid = list_first_entry(&ac->tid_q, struct ath_atx_tid, list); - list_del(&tid->list); - tid->sched = false; + while (!list_empty(&ac->tid_q)) { + tid = list_first_entry(&ac->tid_q, struct ath_atx_tid, + list); + list_del(&tid->list); + tid->sched = false; - if (tid->paused) - continue; + if (tid->paused) + continue; - ath_tx_sched_aggr(sc, txq, tid); + ath_tx_sched_aggr(sc, txq, tid); - /* - * add tid to round-robin queue if more frames - * are pending for the tid - */ - if (!list_empty(&tid->buf_q)) - ath_tx_queue_tid(txq, tid); + /* + * add tid to round-robin queue if more frames + * are pending for the tid + */ + if (!list_empty(&tid->buf_q)) + ath_tx_queue_tid(txq, tid); - break; - } while (!list_empty(&ac->tid_q)); + if (tid == last_tid || + txq->axq_ampdu_depth >= ATH_AGGR_MIN_QDEPTH) + break; + } - if (!list_empty(&ac->tid_q)) { - if (!ac->sched) { - ac->sched = true; - list_add_tail(&ac->list, &txq->axq_acq); + if (!list_empty(&ac->tid_q)) { + if (!ac->sched) { + ac->sched = true; + list_add_tail(&ac->list, &txq->axq_acq); + } } + + if (ac == last_ac || + txq->axq_ampdu_depth >= ATH_AGGR_MIN_QDEPTH) + return; } } @@ -1301,6 +1316,7 @@ static void ath_tx_txqaddbuf(struct ath_softc *sc, struct ath_txq *txq, INIT_LIST_HEAD(&txq->txq_fifo[txq->txq_headidx]); list_splice_init(head, &txq->txq_fifo[txq->txq_headidx]); INCR(txq->txq_headidx, ATH_TXFIFO_DEPTH); + TX_STAT_INC(txq->axq_qnum, puttxbuf); ath9k_hw_puttxbuf(ah, txq->axq_qnum, bf->bf_daddr); ath_dbg(common, ATH_DBG_XMIT, "TXDP[%u] = %llx (%p)\n", txq->axq_qnum, ito64(bf->bf_daddr), bf->bf_desc); @@ -1308,6 +1324,7 @@ static void ath_tx_txqaddbuf(struct ath_softc *sc, struct ath_txq *txq, list_splice_tail_init(head, &txq->axq_q); if (txq->axq_link == NULL) { + TX_STAT_INC(txq->axq_qnum, puttxbuf); ath9k_hw_puttxbuf(ah, txq->axq_qnum, bf->bf_daddr); ath_dbg(common, ATH_DBG_XMIT, "TXDP[%u] = %llx (%p)\n", txq->axq_qnum, ito64(bf->bf_daddr), @@ -1321,6 +1338,7 @@ static void ath_tx_txqaddbuf(struct ath_softc *sc, struct ath_txq *txq, } ath9k_hw_get_desc_link(ah, bf->bf_lastbf->bf_desc, &txq->axq_link); + TX_STAT_INC(txq->axq_qnum, txstart); ath9k_hw_txstart(ah, txq->axq_qnum); } txq->axq_depth++; @@ -1335,7 +1353,6 @@ static void ath_tx_send_ampdu(struct ath_softc *sc, struct ath_atx_tid *tid, struct list_head bf_head; bf->bf_state.bf_type |= BUF_AMPDU; - TX_STAT_INC(txctl->txq->axq_qnum, a_queued); /* * Do not queue to h/w when any of the following conditions is true: @@ -1351,6 +1368,7 @@ static void ath_tx_send_ampdu(struct ath_softc *sc, struct ath_atx_tid *tid, * Add this frame to software queue for scheduling later * for aggregation. */ + TX_STAT_INC(txctl->txq->axq_qnum, a_queued_sw); list_add_tail(&bf->list, &tid->buf_q); ath_tx_queue_tid(txctl->txq, tid); return; @@ -1364,6 +1382,7 @@ static void ath_tx_send_ampdu(struct ath_softc *sc, struct ath_atx_tid *tid, ath_tx_addto_baw(sc, tid, fi->seqno); /* Queue to h/w without aggregation */ + TX_STAT_INC(txctl->txq->axq_qnum, a_queued_hw); bf->bf_lastbf = bf; ath_buf_set_rate(sc, bf, fi->framelen); ath_tx_txqaddbuf(sc, txctl->txq, &bf_head); @@ -1966,17 +1985,16 @@ static void ath_tx_rc_status(struct ath_buf *bf, struct ath_tx_status *ts, tx_info->status.rates[tx_rateindex].count = ts->ts_longretry + 1; } -static void ath_wake_mac80211_queue(struct ath_softc *sc, int qnum) +/* Has no locking. Must hold spin_lock_bh(&txq->axq_lock) + * before calling this. + */ +static void __ath_wake_mac80211_queue(struct ath_softc *sc, struct ath_txq *txq) { - struct ath_txq *txq; - - txq = sc->tx.txq_map[qnum]; - spin_lock_bh(&txq->axq_lock); - if (txq->stopped && txq->pending_frames < ATH_MAX_QDEPTH) { - if (ath_mac80211_start_queue(sc, qnum)) + if (txq->mac80211_qnum >= 0 && + txq->stopped && txq->pending_frames < ATH_MAX_QDEPTH) { + if (ath_mac80211_start_queue(sc, txq->mac80211_qnum)) txq->stopped = 0; } - spin_unlock_bh(&txq->axq_lock); } static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) @@ -1999,6 +2017,8 @@ static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) spin_lock_bh(&txq->axq_lock); if (list_empty(&txq->axq_q)) { txq->axq_link = NULL; + if (sc->sc_flags & SC_OP_TXAGGR) + ath_txq_schedule(sc, txq); spin_unlock_bh(&txq->axq_lock); break; } @@ -2033,6 +2053,7 @@ static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) spin_unlock_bh(&txq->axq_lock); break; } + TX_STAT_INC(txq->axq_qnum, txprocdesc); /* * Remove ath_buf's of the same transmit unit from txq, @@ -2076,10 +2097,9 @@ static void ath_tx_processq(struct ath_softc *sc, struct ath_txq *txq) else ath_tx_complete_buf(sc, bf, txq, &bf_head, &ts, txok, 0); - if (txq == sc->tx.txq_map[qnum]) - ath_wake_mac80211_queue(sc, qnum); - spin_lock_bh(&txq->axq_lock); + __ath_wake_mac80211_queue(sc, txq); + if (sc->sc_flags & SC_OP_TXAGGR) ath_txq_schedule(sc, txq); spin_unlock_bh(&txq->axq_lock); @@ -2093,6 +2113,9 @@ static void ath_tx_complete_poll_work(struct work_struct *work) struct ath_txq *txq; int i; bool needreset = false; +#ifdef CONFIG_ATH9K_DEBUGFS + sc->tx_complete_poll_work_seen++; +#endif for (i = 0; i < ATH9K_NUM_TX_QUEUES; i++) if (ATH_TXQ_SETUP(sc, i)) { @@ -2106,6 +2129,34 @@ static void ath_tx_complete_poll_work(struct work_struct *work) } else { txq->axq_tx_inprogress = true; } + } else { + /* If the queue has pending buffers, then it + * should be doing tx work (and have axq_depth). + * Shouldn't get to this state I think..but + * we do. + */ + if (!(sc->sc_flags & (SC_OP_OFFCHANNEL)) && + (txq->pending_frames > 0 || + !list_empty(&txq->axq_acq) || + txq->stopped)) { + ath_err(ath9k_hw_common(sc->sc_ah), + "txq: %p axq_qnum: %u," + " mac80211_qnum: %i" + " axq_link: %p" + " pending frames: %i" + " axq_acq empty: %i" + " stopped: %i" + " axq_depth: 0 Attempting to" + " restart tx logic.\n", + txq, txq->axq_qnum, + txq->mac80211_qnum, + txq->axq_link, + txq->pending_frames, + list_empty(&txq->axq_acq), + txq->stopped); + __ath_wake_mac80211_queue(sc, txq); + ath_txq_schedule(sc, txq); + } } spin_unlock_bh(&txq->axq_lock); } @@ -2200,10 +2251,9 @@ void ath_tx_edma_tasklet(struct ath_softc *sc) ath_tx_complete_buf(sc, bf, txq, &bf_head, &txs, txok, 0); - if (txq == sc->tx.txq_map[qnum]) - ath_wake_mac80211_queue(sc, qnum); - spin_lock_bh(&txq->axq_lock); + __ath_wake_mac80211_queue(sc, txq); + if (!list_empty(&txq->txq_fifo_pending)) { INIT_LIST_HEAD(&bf_head); bf = list_first_entry(&txq->txq_fifo_pending, diff --git a/drivers/net/wireless/ath/carl9170/carl9170.h b/drivers/net/wireless/ath/carl9170/carl9170.h index d07ff7f..420d437 100644 --- a/drivers/net/wireless/ath/carl9170/carl9170.h +++ b/drivers/net/wireless/ath/carl9170/carl9170.h @@ -283,6 +283,7 @@ struct ar9170 { unsigned int mem_blocks; unsigned int mem_block_size; unsigned int rx_size; + unsigned int tx_seq_table; } fw; /* reset / stuck frames/queue detection */ diff --git a/drivers/net/wireless/ath/carl9170/fw.c b/drivers/net/wireless/ath/carl9170/fw.c index 546b4e4..9517ede 100644 --- a/drivers/net/wireless/ath/carl9170/fw.c +++ b/drivers/net/wireless/ath/carl9170/fw.c @@ -150,6 +150,7 @@ static int carl9170_fw(struct ar9170 *ar, const __u8 *data, size_t len) const struct carl9170fw_otus_desc *otus_desc; const struct carl9170fw_chk_desc *chk_desc; const struct carl9170fw_last_desc *last_desc; + const struct carl9170fw_txsq_desc *txsq_desc; last_desc = carl9170_fw_find_desc(ar, LAST_MAGIC, sizeof(*last_desc), CARL9170FW_LAST_DESC_CUR_VER); @@ -264,6 +265,9 @@ static int carl9170_fw(struct ar9170 *ar, const __u8 *data, size_t len) FIF_PROMISC_IN_BSS; } + if (SUPP(CARL9170FW_WOL)) + device_set_wakeup_enable(&ar->udev->dev, true); + ar->fw.vif_num = otus_desc->vif_num; ar->fw.cmd_bufs = otus_desc->cmd_bufs; ar->fw.address = le32_to_cpu(otus_desc->fw_address); @@ -296,6 +300,17 @@ static int carl9170_fw(struct ar9170 *ar, const __u8 *data, size_t len) } } + txsq_desc = carl9170_fw_find_desc(ar, TXSQ_MAGIC, + sizeof(*txsq_desc), CARL9170FW_TXSQ_DESC_CUR_VER); + + if (txsq_desc) { + ar->fw.tx_seq_table = le32_to_cpu(txsq_desc->seq_table_addr); + if (!valid_cpu_addr(ar->fw.tx_seq_table)) + return -EINVAL; + } else { + ar->fw.tx_seq_table = 0; + } + #undef SUPPORTED return 0; } diff --git a/drivers/net/wireless/ath/carl9170/fwcmd.h b/drivers/net/wireless/ath/carl9170/fwcmd.h index 3680dfc7..30449d2 100644 --- a/drivers/net/wireless/ath/carl9170/fwcmd.h +++ b/drivers/net/wireless/ath/carl9170/fwcmd.h @@ -167,6 +167,7 @@ struct carl9170_rx_filter_cmd { #define CARL9170_RX_FILTER_CTL_BACKR 0x20 #define CARL9170_RX_FILTER_MGMT 0x40 #define CARL9170_RX_FILTER_DATA 0x80 +#define CARL9170_RX_FILTER_EVERYTHING (~0) struct carl9170_bcn_ctrl_cmd { __le32 vif_id; diff --git a/drivers/net/wireless/ath/carl9170/fwdesc.h b/drivers/net/wireless/ath/carl9170/fwdesc.h index 71f3821..9210668 100644 --- a/drivers/net/wireless/ath/carl9170/fwdesc.h +++ b/drivers/net/wireless/ath/carl9170/fwdesc.h @@ -69,6 +69,9 @@ enum carl9170fw_feature_list { /* Firmware RX filter | CARL9170_CMD_RX_FILTER */ CARL9170FW_RX_FILTER, + /* Wake up on WLAN */ + CARL9170FW_WOL, + /* KEEP LAST */ __CARL9170FW_FEATURE_NUM }; @@ -78,6 +81,7 @@ enum carl9170fw_feature_list { #define FIX_MAGIC "FIX\0" #define DBG_MAGIC "DBG\0" #define CHK_MAGIC "CHK\0" +#define TXSQ_MAGIC "TXSQ" #define LAST_MAGIC "LAST" #define CARL9170FW_SET_DAY(d) (((d) - 1) % 31) @@ -88,8 +92,10 @@ enum carl9170fw_feature_list { #define CARL9170FW_GET_MONTH(m) ((((m) / 31) % 12) + 1) #define CARL9170FW_GET_YEAR(y) ((y) / 372 + 10) +#define CARL9170FW_MAGIC_SIZE 4 + struct carl9170fw_desc_head { - u8 magic[4]; + u8 magic[CARL9170FW_MAGIC_SIZE]; __le16 length; u8 min_ver; u8 cur_ver; @@ -170,6 +176,16 @@ struct carl9170fw_chk_desc { #define CARL9170FW_CHK_DESC_SIZE \ (sizeof(struct carl9170fw_chk_desc)) +#define CARL9170FW_TXSQ_DESC_MIN_VER 1 +#define CARL9170FW_TXSQ_DESC_CUR_VER 1 +struct carl9170fw_txsq_desc { + struct carl9170fw_desc_head head; + + __le32 seq_table_addr; +} __packed; +#define CARL9170FW_TXSQ_DESC_SIZE \ + (sizeof(struct carl9170fw_txsq_desc)) + #define CARL9170FW_LAST_DESC_MIN_VER 1 #define CARL9170FW_LAST_DESC_CUR_VER 2 struct carl9170fw_last_desc { @@ -189,8 +205,8 @@ struct carl9170fw_last_desc { } static inline void carl9170fw_fill_desc(struct carl9170fw_desc_head *head, - u8 magic[4], __le16 length, - u8 min_ver, u8 cur_ver) + u8 magic[CARL9170FW_MAGIC_SIZE], + __le16 length, u8 min_ver, u8 cur_ver) { head->magic[0] = magic[0]; head->magic[1] = magic[1]; @@ -204,7 +220,7 @@ static inline void carl9170fw_fill_desc(struct carl9170fw_desc_head *head, #define carl9170fw_for_each_hdr(desc, fw_desc) \ for (desc = fw_desc; \ - memcmp(desc->magic, LAST_MAGIC, 4) && \ + memcmp(desc->magic, LAST_MAGIC, CARL9170FW_MAGIC_SIZE) && \ le16_to_cpu(desc->length) >= CARL9170FW_DESC_HEAD_SIZE && \ le16_to_cpu(desc->length) < CARL9170FW_DESC_MAX_LENGTH; \ desc = (void *)((unsigned long)desc + le16_to_cpu(desc->length))) @@ -218,8 +234,8 @@ static inline bool carl9170fw_supports(__le32 list, u8 feature) } static inline bool carl9170fw_desc_cmp(const struct carl9170fw_desc_head *head, - const u8 descid[4], u16 min_len, - u8 compatible_revision) + const u8 descid[CARL9170FW_MAGIC_SIZE], + u16 min_len, u8 compatible_revision) { if (descid[0] == head->magic[0] && descid[1] == head->magic[1] && descid[2] == head->magic[2] && descid[3] == head->magic[3] && diff --git a/drivers/net/wireless/ath/carl9170/hw.h b/drivers/net/wireless/ath/carl9170/hw.h index e85df6e..4e30762 100644 --- a/drivers/net/wireless/ath/carl9170/hw.h +++ b/drivers/net/wireless/ath/carl9170/hw.h @@ -463,6 +463,8 @@ #define AR9170_PWR_REG_CHIP_REVISION (AR9170_PWR_REG_BASE + 0x010) #define AR9170_PWR_REG_PLL_ADDAC (AR9170_PWR_REG_BASE + 0x014) +#define AR9170_PWR_PLL_ADDAC_DIV_S 2 +#define AR9170_PWR_PLL_ADDAC_DIV 0xffc #define AR9170_PWR_REG_WATCH_DOG_MAGIC (AR9170_PWR_REG_BASE + 0x020) /* Faraday USB Controller */ @@ -471,6 +473,9 @@ #define AR9170_USB_REG_MAIN_CTRL (AR9170_USB_REG_BASE + 0x000) #define AR9170_USB_MAIN_CTRL_REMOTE_WAKEUP BIT(0) #define AR9170_USB_MAIN_CTRL_ENABLE_GLOBAL_INT BIT(2) +#define AR9170_USB_MAIN_CTRL_GO_TO_SUSPEND BIT(3) +#define AR9170_USB_MAIN_CTRL_RESET BIT(4) +#define AR9170_USB_MAIN_CTRL_CHIP_ENABLE BIT(5) #define AR9170_USB_MAIN_CTRL_HIGHSPEED BIT(6) #define AR9170_USB_REG_DEVICE_ADDRESS (AR9170_USB_REG_BASE + 0x001) @@ -499,6 +504,13 @@ #define AR9170_USB_REG_INTR_GROUP (AR9170_USB_REG_BASE + 0x020) #define AR9170_USB_REG_INTR_SOURCE_0 (AR9170_USB_REG_BASE + 0x021) +#define AR9170_USB_INTR_SRC0_SETUP BIT(0) +#define AR9170_USB_INTR_SRC0_IN BIT(1) +#define AR9170_USB_INTR_SRC0_OUT BIT(2) +#define AR9170_USB_INTR_SRC0_FAIL BIT(3) /* ??? */ +#define AR9170_USB_INTR_SRC0_END BIT(4) /* ??? */ +#define AR9170_USB_INTR_SRC0_ABORT BIT(7) + #define AR9170_USB_REG_INTR_SOURCE_1 (AR9170_USB_REG_BASE + 0x022) #define AR9170_USB_REG_INTR_SOURCE_2 (AR9170_USB_REG_BASE + 0x023) #define AR9170_USB_REG_INTR_SOURCE_3 (AR9170_USB_REG_BASE + 0x024) @@ -506,6 +518,15 @@ #define AR9170_USB_REG_INTR_SOURCE_5 (AR9170_USB_REG_BASE + 0x026) #define AR9170_USB_REG_INTR_SOURCE_6 (AR9170_USB_REG_BASE + 0x027) #define AR9170_USB_REG_INTR_SOURCE_7 (AR9170_USB_REG_BASE + 0x028) +#define AR9170_USB_INTR_SRC7_USB_RESET BIT(1) +#define AR9170_USB_INTR_SRC7_USB_SUSPEND BIT(2) +#define AR9170_USB_INTR_SRC7_USB_RESUME BIT(3) +#define AR9170_USB_INTR_SRC7_ISO_SEQ_ERR BIT(4) +#define AR9170_USB_INTR_SRC7_ISO_SEQ_ABORT BIT(5) +#define AR9170_USB_INTR_SRC7_TX0BYTE BIT(6) +#define AR9170_USB_INTR_SRC7_RX0BYTE BIT(7) + +#define AR9170_USB_REG_IDLE_COUNT (AR9170_USB_REG_BASE + 0x02f) #define AR9170_USB_REG_EP_MAP (AR9170_USB_REG_BASE + 0x030) #define AR9170_USB_REG_EP1_MAP (AR9170_USB_REG_BASE + 0x030) @@ -581,6 +602,10 @@ #define AR9170_USB_REG_MAX_AGG_UPLOAD (AR9170_USB_REG_BASE + 0x110) #define AR9170_USB_REG_UPLOAD_TIME_CTL (AR9170_USB_REG_BASE + 0x114) + +#define AR9170_USB_REG_WAKE_UP (AR9170_USB_REG_BASE + 0x120) +#define AR9170_USB_WAKE_UP_WAKE BIT(0) + #define AR9170_USB_REG_CBUS_CTRL (AR9170_USB_REG_BASE + 0x1f0) #define AR9170_USB_CBUS_CTRL_BUFFER_END (BIT(1)) diff --git a/drivers/net/wireless/ath/carl9170/main.c b/drivers/net/wireless/ath/carl9170/main.c index 870df8c..ede3d7e 100644 --- a/drivers/net/wireless/ath/carl9170/main.c +++ b/drivers/net/wireless/ath/carl9170/main.c @@ -662,6 +662,13 @@ init: goto unlock; } + if (ar->fw.tx_seq_table) { + err = carl9170_write_reg(ar, ar->fw.tx_seq_table + vif_id * 4, + 0); + if (err) + goto unlock; + } + unlock: if (err && (vif_id >= 0)) { vif_priv->active = false; @@ -1279,7 +1286,7 @@ static int carl9170_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, - u16 tid, u16 *ssn) + u16 tid, u16 *ssn, u8 buf_size) { struct ar9170 *ar = hw->priv; struct carl9170_sta_info *sta_info = (void *) sta->drv_priv; diff --git a/drivers/net/wireless/ath/carl9170/tx.c b/drivers/net/wireless/ath/carl9170/tx.c index 6cc58e0..6f41e21 100644 --- a/drivers/net/wireless/ath/carl9170/tx.c +++ b/drivers/net/wireless/ath/carl9170/tx.c @@ -862,6 +862,9 @@ static int carl9170_tx_prepare(struct ar9170 *ar, struct sk_buff *skb) if (unlikely(info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM)) txc->s.misc |= CARL9170_TX_SUPER_MISC_CAB; + if (unlikely(info->flags & IEEE80211_TX_CTL_ASSIGN_SEQ)) + txc->s.misc |= CARL9170_TX_SUPER_MISC_ASSIGN_SEQ; + if (unlikely(ieee80211_is_probe_resp(hdr->frame_control))) txc->s.misc |= CARL9170_TX_SUPER_MISC_FILL_IN_TSF; diff --git a/drivers/net/wireless/ath/carl9170/version.h b/drivers/net/wireless/ath/carl9170/version.h index ee0f84f..15095c0 100644 --- a/drivers/net/wireless/ath/carl9170/version.h +++ b/drivers/net/wireless/ath/carl9170/version.h @@ -1,7 +1,7 @@ #ifndef __CARL9170_SHARED_VERSION_H #define __CARL9170_SHARED_VERSION_H -#define CARL9170FW_VERSION_YEAR 10 -#define CARL9170FW_VERSION_MONTH 10 -#define CARL9170FW_VERSION_DAY 29 -#define CARL9170FW_VERSION_GIT "1.9.0" +#define CARL9170FW_VERSION_YEAR 11 +#define CARL9170FW_VERSION_MONTH 1 +#define CARL9170FW_VERSION_DAY 22 +#define CARL9170FW_VERSION_GIT "1.9.2" #endif /* __CARL9170_SHARED_VERSION_H */ diff --git a/drivers/net/wireless/ath/carl9170/wlan.h b/drivers/net/wireless/ath/carl9170/wlan.h index 24d63b5..9e1324b 100644 --- a/drivers/net/wireless/ath/carl9170/wlan.h +++ b/drivers/net/wireless/ath/carl9170/wlan.h @@ -251,7 +251,7 @@ struct carl9170_tx_superdesc { u8 ampdu_commit_factor:1; u8 ampdu_unused_bit:1; u8 queue:2; - u8 reserved:1; + u8 assign_seq:1; u8 vif_id:3; u8 fill_in_tsf:1; u8 cab:1; @@ -299,6 +299,7 @@ struct _ar9170_tx_hwdesc { #define CARL9170_TX_SUPER_MISC_QUEUE 0x3 #define CARL9170_TX_SUPER_MISC_QUEUE_S 0 +#define CARL9170_TX_SUPER_MISC_ASSIGN_SEQ 0x4 #define CARL9170_TX_SUPER_MISC_VIF_ID 0x38 #define CARL9170_TX_SUPER_MISC_VIF_ID_S 3 #define CARL9170_TX_SUPER_MISC_FILL_IN_TSF 0x40 @@ -413,6 +414,23 @@ enum ar9170_txq { __AR9170_NUM_TXQ, }; +/* + * This is an workaround for several undocumented bugs. + * Don't mess with the QoS/AC <-> HW Queue map, if you don't + * know what you are doing. + * + * Known problems [hardware]: + * * The MAC does not aggregate frames on anything other + * than the first HW queue. + * * when an AMPDU is placed [in the first hw queue] and + * additional frames are already queued on a different + * hw queue, the MAC will ALWAYS freeze. + * + * In a nutshell: The hardware can either do QoS or + * Aggregation but not both at the same time. As a + * result, this makes the device pretty much useless + * for any serious 802.11n setup. + */ static const u8 ar9170_qmap[__AR9170_NUM_TXQ] = { 2, 1, 0, 3 }; #define AR9170_TXQ_DEPTH 32 diff --git a/drivers/net/wireless/iwlwifi/Kconfig b/drivers/net/wireless/iwlwifi/Kconfig index ed42457..e1e3b1c 100644 --- a/drivers/net/wireless/iwlwifi/Kconfig +++ b/drivers/net/wireless/iwlwifi/Kconfig @@ -2,6 +2,10 @@ config IWLWIFI tristate "Intel Wireless Wifi" depends on PCI && MAC80211 select FW_LOADER + select NEW_LEDS + select LEDS_CLASS + select LEDS_TRIGGERS + select MAC80211_LEDS menu "Debugging Options" depends on IWLWIFI @@ -106,9 +110,27 @@ config IWL5000 Intel WiFi Link 1000BGN Intel Wireless WiFi 5150AGN Intel Wireless WiFi 5100AGN, 5300AGN, and 5350AGN - Intel 6000 Gen 2 Series Wi-Fi Adapters (6000G2A and 6000G2B) - Intel WIreless WiFi Link 6050BGN Gen 2 Adapter + Intel 6005 Series Wi-Fi Adapters + Intel 6030 Series Wi-Fi Adapters + Intel Wireless WiFi Link 6150BGN 2 Adapter Intel 100 Series Wi-Fi Adapters (100BGN and 130BGN) + Intel 2000 Series Wi-Fi Adapters + +config IWL_P2P + bool "iwlwifi experimental P2P support" + depends on IWL5000 + help + This option enables experimental P2P support for some devices + based on microcode support. Since P2P support is still under + development, this option may even enable it for some devices + now that turn out to not support it in the future due to + microcode restrictions. + + To determine if your microcode supports the experimental P2P + offered by this option, check if the driver advertises AP + support when it is loaded. + + Say Y only if you want to experiment with P2P. config IWL3945 tristate "Intel PRO/Wireless 3945ABG/BG Network Connection (iwl3945)" diff --git a/drivers/net/wireless/iwlwifi/Makefile b/drivers/net/wireless/iwlwifi/Makefile index 93380f9..25be742 100644 --- a/drivers/net/wireless/iwlwifi/Makefile +++ b/drivers/net/wireless/iwlwifi/Makefile @@ -26,6 +26,7 @@ iwlagn-$(CONFIG_IWL5000) += iwl-agn-rxon.o iwl-agn-hcmd.o iwl-agn-ict.o iwlagn-$(CONFIG_IWL5000) += iwl-5000.o iwlagn-$(CONFIG_IWL5000) += iwl-6000.o iwlagn-$(CONFIG_IWL5000) += iwl-1000.o +iwlagn-$(CONFIG_IWL5000) += iwl-2000.o # 3945 obj-$(CONFIG_IWL3945) += iwl3945.o diff --git a/drivers/net/wireless/iwlwifi/iwl-1000.c b/drivers/net/wireless/iwlwifi/iwl-1000.c index ba78bc8..127723e 100644 --- a/drivers/net/wireless/iwlwifi/iwl-1000.c +++ b/drivers/net/wireless/iwlwifi/iwl-1000.c @@ -270,6 +270,7 @@ static struct iwl_base_params iwl1000_base_params = { .ucode_tracing = true, .sensitivity_calib_by_driver = true, .chain_noise_calib_by_driver = true, + .supports_idle = true, }; static struct iwl_ht_params iwl1000_ht_params = { .ht_greenfield_support = true, diff --git a/drivers/net/wireless/iwlwifi/iwl-2000.c b/drivers/net/wireless/iwlwifi/iwl-2000.c new file mode 100644 index 0000000..3c9e1b5 --- /dev/null +++ b/drivers/net/wireless/iwlwifi/iwl-2000.c @@ -0,0 +1,556 @@ +/****************************************************************************** + * + * Copyright(c) 2008 - 2010 Intel Corporation. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of version 2 of the GNU General Public License 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., + * 51 Franklin Street, Fifth Floor, Boston, MA 02110, USA + * + * The full GNU General Public License is included in this distribution in the + * file called LICENSE. + * + * Contact Information: + * Intel Linux Wireless <ilw@linux.intel.com> + * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 + * + *****************************************************************************/ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/dma-mapping.h> +#include <linux/delay.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/wireless.h> +#include <net/mac80211.h> +#include <linux/etherdevice.h> +#include <asm/unaligned.h> + +#include "iwl-eeprom.h" +#include "iwl-dev.h" +#include "iwl-core.h" +#include "iwl-io.h" +#include "iwl-sta.h" +#include "iwl-agn.h" +#include "iwl-helpers.h" +#include "iwl-agn-hw.h" +#include "iwl-6000-hw.h" +#include "iwl-agn-led.h" +#include "iwl-agn-debugfs.h" + +/* Highest firmware API version supported */ +#define IWL2030_UCODE_API_MAX 5 +#define IWL2000_UCODE_API_MAX 5 +#define IWL200_UCODE_API_MAX 5 + +/* Lowest firmware API version supported */ +#define IWL2030_UCODE_API_MIN 5 +#define IWL2000_UCODE_API_MIN 5 +#define IWL200_UCODE_API_MIN 5 + +#define IWL2030_FW_PRE "iwlwifi-2030-" +#define _IWL2030_MODULE_FIRMWARE(api) IWL2030_FW_PRE #api ".ucode" +#define IWL2030_MODULE_FIRMWARE(api) _IWL2030_MODULE_FIRMWARE(api) + +#define IWL2000_FW_PRE "iwlwifi-2000-" +#define _IWL2000_MODULE_FIRMWARE(api) IWL2000_FW_PRE #api ".ucode" +#define IWL2000_MODULE_FIRMWARE(api) _IWL2000_MODULE_FIRMWARE(api) + +#define IWL200_FW_PRE "iwlwifi-200-" +#define _IWL200_MODULE_FIRMWARE(api) IWL200_FW_PRE #api ".ucode" +#define IWL200_MODULE_FIRMWARE(api) _IWL200_MODULE_FIRMWARE(api) + +static void iwl2000_set_ct_threshold(struct iwl_priv *priv) +{ + /* want Celsius */ + priv->hw_params.ct_kill_threshold = CT_KILL_THRESHOLD; + priv->hw_params.ct_kill_exit_threshold = CT_KILL_EXIT_THRESHOLD; +} + +/* NIC configuration for 2000 series */ +static void iwl2000_nic_config(struct iwl_priv *priv) +{ + u16 radio_cfg; + + radio_cfg = iwl_eeprom_query16(priv, EEPROM_RADIO_CONFIG); + + /* write radio config values to register */ + if (EEPROM_RF_CFG_TYPE_MSK(radio_cfg) <= EEPROM_RF_CONFIG_TYPE_MAX) + iwl_set_bit(priv, CSR_HW_IF_CONFIG_REG, + EEPROM_RF_CFG_TYPE_MSK(radio_cfg) | + EEPROM_RF_CFG_STEP_MSK(radio_cfg) | + EEPROM_RF_CFG_DASH_MSK(radio_cfg)); + + /* set CSR_HW_CONFIG_REG for uCode use */ + iwl_set_bit(priv, CSR_HW_IF_CONFIG_REG, + CSR_HW_IF_CONFIG_REG_BIT_RADIO_SI | + CSR_HW_IF_CONFIG_REG_BIT_MAC_SI); + +} + +static struct iwl_sensitivity_ranges iwl2000_sensitivity = { + .min_nrg_cck = 97, + .max_nrg_cck = 0, /* not used, set to 0 */ + .auto_corr_min_ofdm = 80, + .auto_corr_min_ofdm_mrc = 128, + .auto_corr_min_ofdm_x1 = 105, + .auto_corr_min_ofdm_mrc_x1 = 192, + + .auto_corr_max_ofdm = 145, + .auto_corr_max_ofdm_mrc = 232, + .auto_corr_max_ofdm_x1 = 110, + .auto_corr_max_ofdm_mrc_x1 = 232, + + .auto_corr_min_cck = 125, + .auto_corr_max_cck = 175, + .auto_corr_min_cck_mrc = 160, + .auto_corr_max_cck_mrc = 310, + .nrg_th_cck = 97, + .nrg_th_ofdm = 100, + + .barker_corr_th_min = 190, + .barker_corr_th_min_mrc = 390, + .nrg_th_cca = 62, +}; + +static int iwl2000_hw_set_hw_params(struct iwl_priv *priv) +{ + if (priv->cfg->mod_params->num_of_queues >= IWL_MIN_NUM_QUEUES && + priv->cfg->mod_params->num_of_queues <= IWLAGN_NUM_QUEUES) + priv->cfg->base_params->num_of_queues = + priv->cfg->mod_params->num_of_queues; + + priv->hw_params.max_txq_num = priv->cfg->base_params->num_of_queues; + priv->hw_params.dma_chnl_num = FH50_TCSR_CHNL_NUM; + priv->hw_params.scd_bc_tbls_size = + priv->cfg->base_params->num_of_queues * + sizeof(struct iwlagn_scd_bc_tbl); + priv->hw_params.tfd_size = sizeof(struct iwl_tfd); + priv->hw_params.max_stations = IWLAGN_STATION_COUNT; + priv->contexts[IWL_RXON_CTX_BSS].bcast_sta_id = IWLAGN_BROADCAST_ID; + + priv->hw_params.max_data_size = IWL60_RTC_DATA_SIZE; + priv->hw_params.max_inst_size = IWL60_RTC_INST_SIZE; + + priv->hw_params.max_bsm_size = 0; + priv->hw_params.ht40_channel = BIT(IEEE80211_BAND_2GHZ) | + BIT(IEEE80211_BAND_5GHZ); + priv->hw_params.rx_wrt_ptr_reg = FH_RSCSR_CHNL0_WPTR; + + priv->hw_params.tx_chains_num = num_of_ant(priv->cfg->valid_tx_ant); + if (priv->cfg->rx_with_siso_diversity) + priv->hw_params.rx_chains_num = 1; + else + priv->hw_params.rx_chains_num = + num_of_ant(priv->cfg->valid_rx_ant); + priv->hw_params.valid_tx_ant = priv->cfg->valid_tx_ant; + priv->hw_params.valid_rx_ant = priv->cfg->valid_rx_ant; + + iwl2000_set_ct_threshold(priv); + + /* Set initial sensitivity parameters */ + /* Set initial calibration set */ + priv->hw_params.sens = &iwl2000_sensitivity; + priv->hw_params.calib_init_cfg = + BIT(IWL_CALIB_XTAL) | + BIT(IWL_CALIB_LO) | + BIT(IWL_CALIB_TX_IQ) | + BIT(IWL_CALIB_BASE_BAND); + if (priv->cfg->need_dc_calib) + priv->hw_params.calib_rt_cfg |= BIT(IWL_CALIB_CFG_DC_IDX); + if (priv->cfg->need_temp_offset_calib) + priv->hw_params.calib_init_cfg |= BIT(IWL_CALIB_TEMP_OFFSET); + + priv->hw_params.beacon_time_tsf_bits = IWLAGN_EXT_BEACON_TIME_POS; + + return 0; +} + +static int iwl2030_hw_channel_switch(struct iwl_priv *priv, + struct ieee80211_channel_switch *ch_switch) +{ + /* + * MULTI-FIXME + * See iwl_mac_channel_switch. + */ + struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_BSS]; + struct iwl6000_channel_switch_cmd cmd; + const struct iwl_channel_info *ch_info; + u32 switch_time_in_usec, ucode_switch_time; + u16 ch; + u32 tsf_low; + u8 switch_count; + u16 beacon_interval = le16_to_cpu(ctx->timing.beacon_interval); + struct ieee80211_vif *vif = ctx->vif; + struct iwl_host_cmd hcmd = { + .id = REPLY_CHANNEL_SWITCH, + .len = sizeof(cmd), + .flags = CMD_SYNC, + .data = &cmd, + }; + + cmd.band = priv->band == IEEE80211_BAND_2GHZ; + ch = ch_switch->channel->hw_value; + IWL_DEBUG_11H(priv, "channel switch from %u to %u\n", + ctx->active.channel, ch); + cmd.channel = cpu_to_le16(ch); + cmd.rxon_flags = ctx->staging.flags; + cmd.rxon_filter_flags = ctx->staging.filter_flags; + switch_count = ch_switch->count; + tsf_low = ch_switch->timestamp & 0x0ffffffff; + /* + * calculate the ucode channel switch time + * adding TSF as one of the factor for when to switch + */ + if ((priv->ucode_beacon_time > tsf_low) && beacon_interval) { + if (switch_count > ((priv->ucode_beacon_time - tsf_low) / + beacon_interval)) { + switch_count -= (priv->ucode_beacon_time - + tsf_low) / beacon_interval; + } else + switch_count = 0; + } + if (switch_count <= 1) + cmd.switch_time = cpu_to_le32(priv->ucode_beacon_time); + else { + switch_time_in_usec = + vif->bss_conf.beacon_int * switch_count * TIME_UNIT; + ucode_switch_time = iwl_usecs_to_beacons(priv, + switch_time_in_usec, + beacon_interval); + cmd.switch_time = iwl_add_beacon_time(priv, + priv->ucode_beacon_time, + ucode_switch_time, + beacon_interval); + } + IWL_DEBUG_11H(priv, "uCode time for the switch is 0x%x\n", + cmd.switch_time); + ch_info = iwl_get_channel_info(priv, priv->band, ch); + if (ch_info) + cmd.expect_beacon = is_channel_radar(ch_info); + else { + IWL_ERR(priv, "invalid channel switch from %u to %u\n", + ctx->active.channel, ch); + return -EFAULT; + } + priv->switch_rxon.channel = cmd.channel; + priv->switch_rxon.switch_in_progress = true; + + return iwl_send_cmd_sync(priv, &hcmd); +} + +static struct iwl_lib_ops iwl2000_lib = { + .set_hw_params = iwl2000_hw_set_hw_params, + .txq_update_byte_cnt_tbl = iwlagn_txq_update_byte_cnt_tbl, + .txq_inval_byte_cnt_tbl = iwlagn_txq_inval_byte_cnt_tbl, + .txq_set_sched = iwlagn_txq_set_sched, + .txq_agg_enable = iwlagn_txq_agg_enable, + .txq_agg_disable = iwlagn_txq_agg_disable, + .txq_attach_buf_to_tfd = iwl_hw_txq_attach_buf_to_tfd, + .txq_free_tfd = iwl_hw_txq_free_tfd, + .txq_init = iwl_hw_tx_queue_init, + .rx_handler_setup = iwlagn_rx_handler_setup, + .setup_deferred_work = iwlagn_setup_deferred_work, + .is_valid_rtc_data_addr = iwlagn_hw_valid_rtc_data_addr, + .load_ucode = iwlagn_load_ucode, + .dump_nic_event_log = iwl_dump_nic_event_log, + .dump_nic_error_log = iwl_dump_nic_error_log, + .dump_csr = iwl_dump_csr, + .dump_fh = iwl_dump_fh, + .init_alive_start = iwlagn_init_alive_start, + .alive_notify = iwlagn_alive_notify, + .send_tx_power = iwlagn_send_tx_power, + .update_chain_flags = iwl_update_chain_flags, + .set_channel_switch = iwl2030_hw_channel_switch, + .apm_ops = { + .init = iwl_apm_init, + .config = iwl2000_nic_config, + }, + .eeprom_ops = { + .regulatory_bands = { + EEPROM_REG_BAND_1_CHANNELS, + EEPROM_REG_BAND_2_CHANNELS, + EEPROM_REG_BAND_3_CHANNELS, + EEPROM_REG_BAND_4_CHANNELS, + EEPROM_REG_BAND_5_CHANNELS, + EEPROM_6000_REG_BAND_24_HT40_CHANNELS, + EEPROM_REG_BAND_52_HT40_CHANNELS + }, + .acquire_semaphore = iwlcore_eeprom_acquire_semaphore, + .release_semaphore = iwlcore_eeprom_release_semaphore, + .calib_version = iwlagn_eeprom_calib_version, + .query_addr = iwlagn_eeprom_query_addr, + .update_enhanced_txpower = iwlcore_eeprom_enhanced_txpower, + }, + .isr_ops = { + .isr = iwl_isr_ict, + .free = iwl_free_isr_ict, + .alloc = iwl_alloc_isr_ict, + .reset = iwl_reset_ict, + .disable = iwl_disable_ict, + }, + .temp_ops = { + .temperature = iwlagn_temperature, + }, + .debugfs_ops = { + .rx_stats_read = iwl_ucode_rx_stats_read, + .tx_stats_read = iwl_ucode_tx_stats_read, + .general_stats_read = iwl_ucode_general_stats_read, + .bt_stats_read = iwl_ucode_bt_stats_read, + .reply_tx_error = iwl_reply_tx_error_read, + }, + .check_plcp_health = iwl_good_plcp_health, + .check_ack_health = iwl_good_ack_health, + .txfifo_flush = iwlagn_txfifo_flush, + .dev_txfifo_flush = iwlagn_dev_txfifo_flush, + .tt_ops = { + .lower_power_detection = iwl_tt_is_low_power_state, + .tt_power_mode = iwl_tt_current_power_mode, + .ct_kill_check = iwl_check_for_ct_kill, + } +}; + +static const struct iwl_ops iwl2000_ops = { + .lib = &iwl2000_lib, + .hcmd = &iwlagn_hcmd, + .utils = &iwlagn_hcmd_utils, + .led = &iwlagn_led_ops, + .ieee80211_ops = &iwlagn_hw_ops, +}; + +static const struct iwl_ops iwl2030_ops = { + .lib = &iwl2000_lib, + .hcmd = &iwlagn_bt_hcmd, + .utils = &iwlagn_hcmd_utils, + .led = &iwlagn_led_ops, + .ieee80211_ops = &iwlagn_hw_ops, +}; + +static const struct iwl_ops iwl200_ops = { + .lib = &iwl2000_lib, + .hcmd = &iwlagn_hcmd, + .utils = &iwlagn_hcmd_utils, + .led = &iwlagn_led_ops, + .ieee80211_ops = &iwlagn_hw_ops, +}; + +static const struct iwl_ops iwl230_ops = { + .lib = &iwl2000_lib, + .hcmd = &iwlagn_bt_hcmd, + .utils = &iwlagn_hcmd_utils, + .led = &iwlagn_led_ops, + .ieee80211_ops = &iwlagn_hw_ops, +}; + +static struct iwl_base_params iwl2000_base_params = { + .eeprom_size = OTP_LOW_IMAGE_SIZE, + .num_of_queues = IWLAGN_NUM_QUEUES, + .num_of_ampdu_queues = IWLAGN_NUM_AMPDU_QUEUES, + .pll_cfg_val = 0, + .set_l0s = true, + .use_bsm = false, + .max_ll_items = OTP_MAX_LL_ITEMS_2x00, + .shadow_ram_support = true, + .led_compensation = 51, + .chain_noise_num_beacons = IWL_CAL_NUM_BEACONS, + .supports_idle = true, + .adv_thermal_throttle = true, + .support_ct_kill_exit = true, + .plcp_delta_threshold = IWL_MAX_PLCP_ERR_THRESHOLD_DEF, + .chain_noise_scale = 1000, + .wd_timeout = IWL_DEF_WD_TIMEOUT, + .max_event_log_size = 512, + .ucode_tracing = true, + .sensitivity_calib_by_driver = true, + .chain_noise_calib_by_driver = true, + .shadow_reg_enable = true, +}; + + +static struct iwl_base_params iwl2030_base_params = { + .eeprom_size = OTP_LOW_IMAGE_SIZE, + .num_of_queues = IWLAGN_NUM_QUEUES, + .num_of_ampdu_queues = IWLAGN_NUM_AMPDU_QUEUES, + .pll_cfg_val = 0, + .set_l0s = true, + .use_bsm = false, + .max_ll_items = OTP_MAX_LL_ITEMS_2x00, + .shadow_ram_support = true, + .led_compensation = 57, + .chain_noise_num_beacons = IWL_CAL_NUM_BEACONS, + .supports_idle = true, + .adv_thermal_throttle = true, + .support_ct_kill_exit = true, + .plcp_delta_threshold = IWL_MAX_PLCP_ERR_THRESHOLD_DEF, + .chain_noise_scale = 1000, + .wd_timeout = IWL_LONG_WD_TIMEOUT, + .max_event_log_size = 512, + .ucode_tracing = true, + .sensitivity_calib_by_driver = true, + .chain_noise_calib_by_driver = true, + .shadow_reg_enable = true, +}; + +static struct iwl_ht_params iwl2000_ht_params = { + .ht_greenfield_support = true, + .use_rts_for_aggregation = true, /* use rts/cts protection */ +}; + +static struct iwl_bt_params iwl2030_bt_params = { + .bt_statistics = true, + /* Due to bluetooth, we transmit 2.4 GHz probes only on antenna A */ + .advanced_bt_coexist = true, + .agg_time_limit = BT_AGG_THRESHOLD_DEF, + .bt_init_traffic_load = IWL_BT_COEX_TRAFFIC_LOAD_NONE, + .bt_prio_boost = IWLAGN_BT_PRIO_BOOST_DEFAULT, + .bt_sco_disable = true, +}; + +#define IWL_DEVICE_2000 \ + .fw_name_pre = IWL2000_FW_PRE, \ + .ucode_api_max = IWL2000_UCODE_API_MAX, \ + .ucode_api_min = IWL2000_UCODE_API_MIN, \ + .eeprom_ver = EEPROM_2000_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_2000_TX_POWER_VERSION, \ + .ops = &iwl2000_ops, \ + .mod_params = &iwlagn_mod_params, \ + .base_params = &iwl2000_base_params, \ + .need_dc_calib = true, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE \ + +struct iwl_cfg iwl2000_2bgn_cfg = { + .name = "2000 Series 2x2 BGN", + IWL_DEVICE_2000, + .ht_params = &iwl2000_ht_params, +}; + +struct iwl_cfg iwl2000_2bg_cfg = { + .name = "2000 Series 2x2 BG", + IWL_DEVICE_2000, +}; + +#define IWL_DEVICE_2030 \ + .fw_name_pre = IWL2030_FW_PRE, \ + .ucode_api_max = IWL2030_UCODE_API_MAX, \ + .ucode_api_min = IWL2030_UCODE_API_MIN, \ + .eeprom_ver = EEPROM_2000_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_2000_TX_POWER_VERSION, \ + .ops = &iwl2030_ops, \ + .mod_params = &iwlagn_mod_params, \ + .base_params = &iwl2030_base_params, \ + .bt_params = &iwl2030_bt_params, \ + .need_dc_calib = true, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE, \ + .adv_pm = true \ + +struct iwl_cfg iwl2030_2bgn_cfg = { + .name = "2000 Series 2x2 BGN/BT", + IWL_DEVICE_2000, + .ht_params = &iwl2000_ht_params, +}; + +struct iwl_cfg iwl2030_2bg_cfg = { + .name = "2000 Series 2x2 BG/BT", + IWL_DEVICE_2000, +}; + +#define IWL_DEVICE_6035 \ + .fw_name_pre = IWL2030_FW_PRE, \ + .ucode_api_max = IWL2030_UCODE_API_MAX, \ + .ucode_api_min = IWL2030_UCODE_API_MIN, \ + .eeprom_ver = EEPROM_6035_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_6035_TX_POWER_VERSION, \ + .ops = &iwl2030_ops, \ + .mod_params = &iwlagn_mod_params, \ + .base_params = &iwl2030_base_params, \ + .bt_params = &iwl2030_bt_params, \ + .need_dc_calib = true, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE, \ + .adv_pm = true \ + +struct iwl_cfg iwl6035_2agn_cfg = { + .name = "2000 Series 2x2 AGN/BT", + IWL_DEVICE_6035, + .ht_params = &iwl2000_ht_params, +}; + +struct iwl_cfg iwl6035_2abg_cfg = { + .name = "2000 Series 2x2 ABG/BT", + IWL_DEVICE_6035, +}; + +struct iwl_cfg iwl6035_2bg_cfg = { + .name = "2000 Series 2x2 BG/BT", + IWL_DEVICE_6035, +}; + +#define IWL_DEVICE_200 \ + .fw_name_pre = IWL200_FW_PRE, \ + .ucode_api_max = IWL200_UCODE_API_MAX, \ + .ucode_api_min = IWL200_UCODE_API_MIN, \ + .eeprom_ver = EEPROM_2000_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_2000_TX_POWER_VERSION, \ + .ops = &iwl200_ops, \ + .mod_params = &iwlagn_mod_params, \ + .base_params = &iwl2000_base_params, \ + .need_dc_calib = true, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE, \ + .adv_pm = true, \ + .rx_with_siso_diversity = true \ + +struct iwl_cfg iwl200_bg_cfg = { + .name = "200 Series 1x1 BG", + IWL_DEVICE_200, +}; + +struct iwl_cfg iwl200_bgn_cfg = { + .name = "200 Series 1x1 BGN", + IWL_DEVICE_200, + .ht_params = &iwl2000_ht_params, +}; + +#define IWL_DEVICE_230 \ + .fw_name_pre = IWL200_FW_PRE, \ + .ucode_api_max = IWL200_UCODE_API_MAX, \ + .ucode_api_min = IWL200_UCODE_API_MIN, \ + .eeprom_ver = EEPROM_2000_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_2000_TX_POWER_VERSION, \ + .ops = &iwl230_ops, \ + .mod_params = &iwlagn_mod_params, \ + .base_params = &iwl2030_base_params, \ + .bt_params = &iwl2030_bt_params, \ + .need_dc_calib = true, \ + .need_temp_offset_calib = true, \ + .led_mode = IWL_LED_RF_STATE, \ + .adv_pm = true, \ + .rx_with_siso_diversity = true \ + +struct iwl_cfg iwl230_bg_cfg = { + .name = "200 Series 1x1 BG/BT", + IWL_DEVICE_230, +}; + +struct iwl_cfg iwl230_bgn_cfg = { + .name = "200 Series 1x1 BGN/BT", + IWL_DEVICE_230, + .ht_params = &iwl2000_ht_params, +}; + +MODULE_FIRMWARE(IWL2000_MODULE_FIRMWARE(IWL2000_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL2030_MODULE_FIRMWARE(IWL2030_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL200_MODULE_FIRMWARE(IWL200_UCODE_API_MAX)); diff --git a/drivers/net/wireless/iwlwifi/iwl-3945-led.c b/drivers/net/wireless/iwlwifi/iwl-3945-led.c index abe2b73..dc7c3a4 100644 --- a/drivers/net/wireless/iwlwifi/iwl-3945-led.c +++ b/drivers/net/wireless/iwlwifi/iwl-3945-led.c @@ -59,33 +59,6 @@ static int iwl3945_send_led_cmd(struct iwl_priv *priv, return iwl_send_cmd(priv, &cmd); } -/* Set led on command */ -static int iwl3945_led_on(struct iwl_priv *priv) -{ - struct iwl_led_cmd led_cmd = { - .id = IWL_LED_LINK, - .on = IWL_LED_SOLID, - .off = 0, - .interval = IWL_DEF_LED_INTRVL - }; - return iwl3945_send_led_cmd(priv, &led_cmd); -} - -/* Set led off command */ -static int iwl3945_led_off(struct iwl_priv *priv) -{ - struct iwl_led_cmd led_cmd = { - .id = IWL_LED_LINK, - .on = 0, - .off = 0, - .interval = IWL_DEF_LED_INTRVL - }; - IWL_DEBUG_LED(priv, "led off\n"); - return iwl3945_send_led_cmd(priv, &led_cmd); -} - const struct iwl_led_ops iwl3945_led_ops = { .cmd = iwl3945_send_led_cmd, - .on = iwl3945_led_on, - .off = iwl3945_led_off, }; diff --git a/drivers/net/wireless/iwlwifi/iwl-3945.c b/drivers/net/wireless/iwlwifi/iwl-3945.c index a9b852b..1d9dcd7 100644 --- a/drivers/net/wireless/iwlwifi/iwl-3945.c +++ b/drivers/net/wireless/iwlwifi/iwl-3945.c @@ -594,10 +594,11 @@ static void iwl3945_rx_reply_rx(struct iwl_priv *priv, rx_status.flag = 0; rx_status.mactime = le64_to_cpu(rx_end->timestamp); - rx_status.freq = - ieee80211_channel_to_frequency(le16_to_cpu(rx_hdr->channel)); rx_status.band = (rx_hdr->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ? IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ; + rx_status.freq = + ieee80211_channel_to_frequency(le16_to_cpu(rx_hdr->channel), + rx_status.band); rx_status.rate_idx = iwl3945_hwrate_to_plcp_idx(rx_hdr->rate); if (rx_status.band == IEEE80211_BAND_5GHZ) diff --git a/drivers/net/wireless/iwlwifi/iwl-4965.c b/drivers/net/wireless/iwlwifi/iwl-4965.c index 91a9f52..313e92e 100644 --- a/drivers/net/wireless/iwlwifi/iwl-4965.c +++ b/drivers/net/wireless/iwlwifi/iwl-4965.c @@ -2316,6 +2316,11 @@ static void iwl4965_rx_handler_setup(struct iwl_priv *priv) priv->rx_handlers[REPLY_RX] = iwlagn_rx_reply_rx; /* Tx response */ priv->rx_handlers[REPLY_TX] = iwl4965_rx_reply_tx; + + /* set up notification wait support */ + spin_lock_init(&priv->_agn.notif_wait_lock); + INIT_LIST_HEAD(&priv->_agn.notif_waits); + init_waitqueue_head(&priv->_agn.notif_waitq); } static void iwl4965_setup_deferred_work(struct iwl_priv *priv) diff --git a/drivers/net/wireless/iwlwifi/iwl-6000.c b/drivers/net/wireless/iwlwifi/iwl-6000.c index af505bc..c195674 100644 --- a/drivers/net/wireless/iwlwifi/iwl-6000.c +++ b/drivers/net/wireless/iwlwifi/iwl-6000.c @@ -67,13 +67,13 @@ #define _IWL6050_MODULE_FIRMWARE(api) IWL6050_FW_PRE #api ".ucode" #define IWL6050_MODULE_FIRMWARE(api) _IWL6050_MODULE_FIRMWARE(api) -#define IWL6000G2A_FW_PRE "iwlwifi-6000g2a-" -#define _IWL6000G2A_MODULE_FIRMWARE(api) IWL6000G2A_FW_PRE #api ".ucode" -#define IWL6000G2A_MODULE_FIRMWARE(api) _IWL6000G2A_MODULE_FIRMWARE(api) +#define IWL6005_FW_PRE "iwlwifi-6000g2a-" +#define _IWL6005_MODULE_FIRMWARE(api) IWL6005_FW_PRE #api ".ucode" +#define IWL6005_MODULE_FIRMWARE(api) _IWL6005_MODULE_FIRMWARE(api) -#define IWL6000G2B_FW_PRE "iwlwifi-6000g2b-" -#define _IWL6000G2B_MODULE_FIRMWARE(api) IWL6000G2B_FW_PRE #api ".ucode" -#define IWL6000G2B_MODULE_FIRMWARE(api) _IWL6000G2B_MODULE_FIRMWARE(api) +#define IWL6030_FW_PRE "iwlwifi-6000g2b-" +#define _IWL6030_MODULE_FIRMWARE(api) IWL6030_FW_PRE #api ".ucode" +#define IWL6030_MODULE_FIRMWARE(api) _IWL6030_MODULE_FIRMWARE(api) static void iwl6000_set_ct_threshold(struct iwl_priv *priv) { @@ -90,7 +90,7 @@ static void iwl6050_additional_nic_config(struct iwl_priv *priv) CSR_GP_DRIVER_REG_BIT_CALIB_VERSION6); } -static void iwl6050g2_additional_nic_config(struct iwl_priv *priv) +static void iwl6150_additional_nic_config(struct iwl_priv *priv) { /* Indicate calibration version to uCode. */ if (priv->cfg->ops->lib->eeprom_ops.calib_version(priv) >= 6) @@ -354,7 +354,7 @@ static struct iwl_lib_ops iwl6000_lib = { } }; -static struct iwl_lib_ops iwl6000g2b_lib = { +static struct iwl_lib_ops iwl6030_lib = { .set_hw_params = iwl6000_hw_set_hw_params, .txq_update_byte_cnt_tbl = iwlagn_txq_update_byte_cnt_tbl, .txq_inval_byte_cnt_tbl = iwlagn_txq_inval_byte_cnt_tbl, @@ -430,8 +430,8 @@ static struct iwl_nic_ops iwl6050_nic_ops = { .additional_nic_config = &iwl6050_additional_nic_config, }; -static struct iwl_nic_ops iwl6050g2_nic_ops = { - .additional_nic_config = &iwl6050g2_additional_nic_config, +static struct iwl_nic_ops iwl6150_nic_ops = { + .additional_nic_config = &iwl6150_additional_nic_config, }; static const struct iwl_ops iwl6000_ops = { @@ -451,17 +451,17 @@ static const struct iwl_ops iwl6050_ops = { .ieee80211_ops = &iwlagn_hw_ops, }; -static const struct iwl_ops iwl6050g2_ops = { +static const struct iwl_ops iwl6150_ops = { .lib = &iwl6000_lib, .hcmd = &iwlagn_hcmd, .utils = &iwlagn_hcmd_utils, .led = &iwlagn_led_ops, - .nic = &iwl6050g2_nic_ops, + .nic = &iwl6150_nic_ops, .ieee80211_ops = &iwlagn_hw_ops, }; -static const struct iwl_ops iwl6000g2b_ops = { - .lib = &iwl6000g2b_lib, +static const struct iwl_ops iwl6030_ops = { + .lib = &iwl6030_lib, .hcmd = &iwlagn_bt_hcmd, .utils = &iwlagn_hcmd_utils, .led = &iwlagn_led_ops, @@ -555,11 +555,11 @@ static struct iwl_bt_params iwl6000_bt_params = { }; #define IWL_DEVICE_6005 \ - .fw_name_pre = IWL6000G2A_FW_PRE, \ + .fw_name_pre = IWL6005_FW_PRE, \ .ucode_api_max = IWL6000G2_UCODE_API_MAX, \ .ucode_api_min = IWL6000G2_UCODE_API_MIN, \ - .eeprom_ver = EEPROM_6000G2_EEPROM_VERSION, \ - .eeprom_calib_ver = EEPROM_6000G2_TX_POWER_VERSION, \ + .eeprom_ver = EEPROM_6005_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_6005_TX_POWER_VERSION, \ .ops = &iwl6000_ops, \ .mod_params = &iwlagn_mod_params, \ .base_params = &iwl6000_g2_base_params, \ @@ -584,12 +584,12 @@ struct iwl_cfg iwl6005_2bg_cfg = { }; #define IWL_DEVICE_6030 \ - .fw_name_pre = IWL6000G2B_FW_PRE, \ + .fw_name_pre = IWL6030_FW_PRE, \ .ucode_api_max = IWL6000G2_UCODE_API_MAX, \ .ucode_api_min = IWL6000G2_UCODE_API_MIN, \ - .eeprom_ver = EEPROM_6000G2_EEPROM_VERSION, \ - .eeprom_calib_ver = EEPROM_6000G2_TX_POWER_VERSION, \ - .ops = &iwl6000g2b_ops, \ + .eeprom_ver = EEPROM_6030_EEPROM_VERSION, \ + .eeprom_calib_ver = EEPROM_6030_TX_POWER_VERSION, \ + .ops = &iwl6030_ops, \ .mod_params = &iwlagn_mod_params, \ .base_params = &iwl6000_g2_base_params, \ .bt_params = &iwl6000_bt_params, \ @@ -706,9 +706,9 @@ struct iwl_cfg iwl6150_bgn_cfg = { .fw_name_pre = IWL6050_FW_PRE, .ucode_api_max = IWL6050_UCODE_API_MAX, .ucode_api_min = IWL6050_UCODE_API_MIN, - .eeprom_ver = EEPROM_6050G2_EEPROM_VERSION, - .eeprom_calib_ver = EEPROM_6050G2_TX_POWER_VERSION, - .ops = &iwl6050g2_ops, + .eeprom_ver = EEPROM_6150_EEPROM_VERSION, + .eeprom_calib_ver = EEPROM_6150_TX_POWER_VERSION, + .ops = &iwl6150_ops, .mod_params = &iwlagn_mod_params, .base_params = &iwl6050_base_params, .ht_params = &iwl6000_ht_params, @@ -734,5 +734,5 @@ struct iwl_cfg iwl6000_3agn_cfg = { MODULE_FIRMWARE(IWL6000_MODULE_FIRMWARE(IWL6000_UCODE_API_MAX)); MODULE_FIRMWARE(IWL6050_MODULE_FIRMWARE(IWL6050_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL6000G2A_MODULE_FIRMWARE(IWL6000G2_UCODE_API_MAX)); -MODULE_FIRMWARE(IWL6000G2B_MODULE_FIRMWARE(IWL6000G2_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL6005_MODULE_FIRMWARE(IWL6000G2_UCODE_API_MAX)); +MODULE_FIRMWARE(IWL6030_MODULE_FIRMWARE(IWL6000G2_UCODE_API_MAX)); diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c b/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c index 366340f..41543ad 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-hcmd.c @@ -305,7 +305,11 @@ static int iwlagn_set_pan_params(struct iwl_priv *priv) cmd.slots[0].type = 0; /* BSS */ cmd.slots[1].type = 1; /* PAN */ - if (ctx_bss->vif && ctx_pan->vif) { + if (priv->_agn.hw_roc_channel) { + /* both contexts must be used for this to happen */ + slot1 = priv->_agn.hw_roc_duration; + slot0 = IWL_MIN_SLOT_TIME; + } else if (ctx_bss->vif && ctx_pan->vif) { int bcnint = ctx_pan->vif->bss_conf.beacon_int; int dtim = ctx_pan->vif->bss_conf.dtim_period ?: 1; @@ -330,12 +334,12 @@ static int iwlagn_set_pan_params(struct iwl_priv *priv) if (test_bit(STATUS_SCAN_HW, &priv->status) || (!ctx_bss->vif->bss_conf.idle && !ctx_bss->vif->bss_conf.assoc)) { - slot0 = dtim * bcnint * 3 - 20; - slot1 = 20; + slot0 = dtim * bcnint * 3 - IWL_MIN_SLOT_TIME; + slot1 = IWL_MIN_SLOT_TIME; } else if (!ctx_pan->vif->bss_conf.idle && !ctx_pan->vif->bss_conf.assoc) { - slot1 = bcnint * 3 - 20; - slot0 = 20; + slot1 = bcnint * 3 - IWL_MIN_SLOT_TIME; + slot0 = IWL_MIN_SLOT_TIME; } } else if (ctx_pan->vif) { slot0 = 0; @@ -344,8 +348,8 @@ static int iwlagn_set_pan_params(struct iwl_priv *priv) slot1 = max_t(int, DEFAULT_BEACON_INTERVAL, slot1); if (test_bit(STATUS_SCAN_HW, &priv->status)) { - slot0 = slot1 * 3 - 20; - slot1 = 20; + slot0 = slot1 * 3 - IWL_MIN_SLOT_TIME; + slot1 = IWL_MIN_SLOT_TIME; } } diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-led.c b/drivers/net/wireless/iwlwifi/iwl-agn-led.c index 1a24946..c1190d9 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-led.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-led.c @@ -63,23 +63,11 @@ static int iwl_send_led_cmd(struct iwl_priv *priv, struct iwl_led_cmd *led_cmd) } /* Set led register off */ -static int iwl_led_on_reg(struct iwl_priv *priv) +void iwlagn_led_enable(struct iwl_priv *priv) { - IWL_DEBUG_LED(priv, "led on\n"); iwl_write32(priv, CSR_LED_REG, CSR_LED_REG_TRUN_ON); - return 0; -} - -/* Set led register off */ -static int iwl_led_off_reg(struct iwl_priv *priv) -{ - IWL_DEBUG_LED(priv, "LED Reg off\n"); - iwl_write32(priv, CSR_LED_REG, CSR_LED_REG_TRUN_OFF); - return 0; } const struct iwl_led_ops iwlagn_led_ops = { .cmd = iwl_send_led_cmd, - .on = iwl_led_on_reg, - .off = iwl_led_off_reg, }; diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-led.h b/drivers/net/wireless/iwlwifi/iwl-agn-led.h index a594e4f..96f323d 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-led.h +++ b/drivers/net/wireless/iwlwifi/iwl-agn-led.h @@ -28,5 +28,6 @@ #define __iwl_agn_led_h__ extern const struct iwl_led_ops iwlagn_led_ops; +void iwlagn_led_enable(struct iwl_priv *priv); #endif /* __iwl_agn_led_h__ */ diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c index 3dee87e..c7d0387 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-lib.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-lib.c @@ -473,6 +473,11 @@ void iwlagn_rx_handler_setup(struct iwl_priv *priv) priv->rx_handlers[CALIBRATION_COMPLETE_NOTIFICATION] = iwlagn_rx_calib_complete; priv->rx_handlers[REPLY_TX] = iwlagn_rx_reply_tx; + + /* set up notification wait support */ + spin_lock_init(&priv->_agn.notif_wait_lock); + INIT_LIST_HEAD(&priv->_agn.notif_waits); + init_waitqueue_head(&priv->_agn.notif_waitq); } void iwlagn_setup_deferred_work(struct iwl_priv *priv) @@ -1157,10 +1162,11 @@ void iwlagn_rx_reply_rx(struct iwl_priv *priv, /* rx_status carries information about the packet to mac80211 */ rx_status.mactime = le64_to_cpu(phy_res->timestamp); - rx_status.freq = - ieee80211_channel_to_frequency(le16_to_cpu(phy_res->channel)); rx_status.band = (phy_res->phy_flags & RX_RES_PHY_FLAGS_BAND_24_MSK) ? IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ; + rx_status.freq = + ieee80211_channel_to_frequency(le16_to_cpu(phy_res->channel), + rx_status.band); rx_status.rate_idx = iwlagn_hwrate_to_mac80211_idx(rate_n_flags, rx_status.band); rx_status.flag = 0; @@ -2389,3 +2395,44 @@ int iwl_dump_fh(struct iwl_priv *priv, char **buf, bool display) } return 0; } + +/* notification wait support */ +void iwlagn_init_notification_wait(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry, + void (*fn)(struct iwl_priv *priv, + struct iwl_rx_packet *pkt), + u8 cmd) +{ + wait_entry->fn = fn; + wait_entry->cmd = cmd; + wait_entry->triggered = false; + + spin_lock_bh(&priv->_agn.notif_wait_lock); + list_add(&wait_entry->list, &priv->_agn.notif_waits); + spin_unlock_bh(&priv->_agn.notif_wait_lock); +} + +signed long iwlagn_wait_notification(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry, + unsigned long timeout) +{ + int ret; + + ret = wait_event_timeout(priv->_agn.notif_waitq, + &wait_entry->triggered, + timeout); + + spin_lock_bh(&priv->_agn.notif_wait_lock); + list_del(&wait_entry->list); + spin_unlock_bh(&priv->_agn.notif_wait_lock); + + return ret; +} + +void iwlagn_remove_notification(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry) +{ + spin_lock_bh(&priv->_agn.notif_wait_lock); + list_del(&wait_entry->list); + spin_unlock_bh(&priv->_agn.notif_wait_lock); +} diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c index 6d140bd..2a4ff83 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-rxon.c @@ -52,10 +52,14 @@ static int iwlagn_disable_pan(struct iwl_priv *priv, struct iwl_rxon_context *ctx, struct iwl_rxon_cmd *send) { + struct iwl_notification_wait disable_wait; __le32 old_filter = send->filter_flags; u8 old_dev_type = send->dev_type; int ret; + iwlagn_init_notification_wait(priv, &disable_wait, NULL, + REPLY_WIPAN_DEACTIVATION_COMPLETE); + send->filter_flags &= ~RXON_FILTER_ASSOC_MSK; send->dev_type = RXON_DEV_TYPE_P2P; ret = iwl_send_cmd_pdu(priv, ctx->rxon_cmd, sizeof(*send), send); @@ -63,11 +67,18 @@ static int iwlagn_disable_pan(struct iwl_priv *priv, send->filter_flags = old_filter; send->dev_type = old_dev_type; - if (ret) + if (ret) { IWL_ERR(priv, "Error disabling PAN (%d)\n", ret); - - /* FIXME: WAIT FOR PAN DISABLE */ - msleep(300); + iwlagn_remove_notification(priv, &disable_wait); + } else { + signed long wait_res; + + wait_res = iwlagn_wait_notification(priv, &disable_wait, HZ); + if (wait_res == 0) { + IWL_ERR(priv, "Timed out waiting for PAN disable\n"); + ret = -EIO; + } + } return ret; } @@ -145,6 +156,23 @@ int iwlagn_commit_rxon(struct iwl_priv *priv, struct iwl_rxon_context *ctx) /* always get timestamp with Rx frame */ ctx->staging.flags |= RXON_FLG_TSF2HOST_MSK; + if (ctx->ctxid == IWL_RXON_CTX_PAN && priv->_agn.hw_roc_channel) { + struct ieee80211_channel *chan = priv->_agn.hw_roc_channel; + + iwl_set_rxon_channel(priv, chan, ctx); + iwl_set_flags_for_band(priv, ctx, chan->band, NULL); + ctx->staging.filter_flags |= + RXON_FILTER_ASSOC_MSK | + RXON_FILTER_PROMISC_MSK | + RXON_FILTER_CTL2HOST_MSK; + ctx->staging.dev_type = RXON_DEV_TYPE_P2P; + new_assoc = true; + + if (memcmp(&ctx->staging, &ctx->active, + sizeof(ctx->staging)) == 0) + return 0; + } + if ((ctx->vif && ctx->vif->bss_conf.use_short_slot) || !(ctx->staging.flags & RXON_FLG_BAND_24G_MSK)) ctx->staging.flags |= RXON_FLG_SHORT_SLOT_MSK; @@ -546,12 +574,10 @@ void iwlagn_bss_info_changed(struct ieee80211_hw *hw, if (changes & BSS_CHANGED_ASSOC) { if (bss_conf->assoc) { - iwl_led_associate(priv); priv->timestamp = bss_conf->timestamp; ctx->staging.filter_flags |= RXON_FILTER_ASSOC_MSK; } else { ctx->staging.filter_flags &= ~RXON_FILTER_ASSOC_MSK; - iwl_led_disassociate(priv); } } diff --git a/drivers/net/wireless/iwlwifi/iwl-agn-tx.c b/drivers/net/wireless/iwlwifi/iwl-agn-tx.c index 24a11b8..266490d 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn-tx.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn-tx.c @@ -539,7 +539,14 @@ int iwlagn_tx_skb(struct iwl_priv *priv, struct sk_buff *skb) unsigned long flags; bool is_agg = false; - if (info->control.vif) + /* + * If the frame needs to go out off-channel, then + * we'll have put the PAN context to that channel, + * so make the frame go out there. + */ + if (info->flags & IEEE80211_TX_CTL_TX_OFFCHAN) + ctx = &priv->contexts[IWL_RXON_CTX_PAN]; + else if (info->control.vif) ctx = iwl_rxon_ctx_from_vif(info->control.vif); spin_lock_irqsave(&priv->lock, flags); diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c index 36335b1..eb16647 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn.c +++ b/drivers/net/wireless/iwlwifi/iwl-agn.c @@ -59,6 +59,7 @@ #include "iwl-sta.h" #include "iwl-agn-calib.h" #include "iwl-agn.h" +#include "iwl-agn-led.h" /****************************************************************************** @@ -846,7 +847,7 @@ static void iwl_setup_rx_handlers(struct iwl_priv *priv) * the appropriate handlers, including command responses, * frame-received notifications, and other notifications. */ -void iwl_rx_handle(struct iwl_priv *priv) +static void iwl_rx_handle(struct iwl_priv *priv) { struct iwl_rx_mem_buffer *rxb; struct iwl_rx_packet *pkt; @@ -910,6 +911,27 @@ void iwl_rx_handle(struct iwl_priv *priv) (pkt->hdr.cmd != STATISTICS_NOTIFICATION) && (pkt->hdr.cmd != REPLY_TX); + /* + * Do the notification wait before RX handlers so + * even if the RX handler consumes the RXB we have + * access to it in the notification wait entry. + */ + if (!list_empty(&priv->_agn.notif_waits)) { + struct iwl_notification_wait *w; + + spin_lock(&priv->_agn.notif_wait_lock); + list_for_each_entry(w, &priv->_agn.notif_waits, list) { + if (w->cmd == pkt->hdr.cmd) { + w->triggered = true; + if (w->fn) + w->fn(priv, pkt); + } + } + spin_unlock(&priv->_agn.notif_wait_lock); + + wake_up_all(&priv->_agn.notif_waitq); + } + /* Based on type of command response or notification, * handle those that need handling via function in * rx_handlers table. See iwl_setup_rx_handlers() */ @@ -2720,8 +2742,6 @@ static void iwl_alive_start(struct iwl_priv *priv) /* At this point, the NIC is initialized and operational */ iwl_rf_kill_ct_config(priv); - iwl_leds_init(priv); - IWL_DEBUG_INFO(priv, "ALIVE processing complete.\n"); wake_up_interruptible(&priv->wait_command_queue); @@ -3188,6 +3208,8 @@ static int iwl_mac_setup_register(struct iwl_priv *priv, hw->wiphy->interface_modes |= ctx->exclusive_interface_modes; } + hw->wiphy->max_remain_on_channel_duration = 1000; + hw->wiphy->flags |= WIPHY_FLAG_CUSTOM_REGULATORY | WIPHY_FLAG_DISABLE_BEACON_HINTS; @@ -3213,6 +3235,8 @@ static int iwl_mac_setup_register(struct iwl_priv *priv, priv->hw->wiphy->bands[IEEE80211_BAND_5GHZ] = &priv->bands[IEEE80211_BAND_5GHZ]; + iwl_leds_init(priv); + ret = ieee80211_register_hw(priv->hw); if (ret) { IWL_ERR(priv, "Failed to register hw (error %d)\n", ret); @@ -3257,7 +3281,7 @@ int iwlagn_mac_start(struct ieee80211_hw *hw) } } - iwl_led_start(priv); + iwlagn_led_enable(priv); out: priv->is_open = 1; @@ -3393,7 +3417,8 @@ int iwlagn_mac_set_key(struct ieee80211_hw *hw, enum set_key_cmd cmd, int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { struct iwl_priv *priv = hw->priv; int ret = -EINVAL; @@ -3703,6 +3728,95 @@ done: IWL_DEBUG_MAC80211(priv, "leave\n"); } +static void iwlagn_disable_roc(struct iwl_priv *priv) +{ + struct iwl_rxon_context *ctx = &priv->contexts[IWL_RXON_CTX_PAN]; + struct ieee80211_channel *chan = ACCESS_ONCE(priv->hw->conf.channel); + + lockdep_assert_held(&priv->mutex); + + if (!ctx->is_active) + return; + + ctx->staging.dev_type = RXON_DEV_TYPE_2STA; + ctx->staging.filter_flags &= ~RXON_FILTER_ASSOC_MSK; + iwl_set_rxon_channel(priv, chan, ctx); + iwl_set_flags_for_band(priv, ctx, chan->band, NULL); + + priv->_agn.hw_roc_channel = NULL; + + iwlagn_commit_rxon(priv, ctx); + + ctx->is_active = false; +} + +static void iwlagn_bg_roc_done(struct work_struct *work) +{ + struct iwl_priv *priv = container_of(work, struct iwl_priv, + _agn.hw_roc_work.work); + + mutex_lock(&priv->mutex); + ieee80211_remain_on_channel_expired(priv->hw); + iwlagn_disable_roc(priv); + mutex_unlock(&priv->mutex); +} + +static int iwl_mac_remain_on_channel(struct ieee80211_hw *hw, + struct ieee80211_channel *channel, + enum nl80211_channel_type channel_type, + int duration) +{ + struct iwl_priv *priv = hw->priv; + int err = 0; + + if (!(priv->valid_contexts & BIT(IWL_RXON_CTX_PAN))) + return -EOPNOTSUPP; + + if (!(priv->contexts[IWL_RXON_CTX_PAN].interface_modes & + BIT(NL80211_IFTYPE_P2P_CLIENT))) + return -EOPNOTSUPP; + + mutex_lock(&priv->mutex); + + if (priv->contexts[IWL_RXON_CTX_PAN].is_active || + test_bit(STATUS_SCAN_HW, &priv->status)) { + err = -EBUSY; + goto out; + } + + priv->contexts[IWL_RXON_CTX_PAN].is_active = true; + priv->_agn.hw_roc_channel = channel; + priv->_agn.hw_roc_chantype = channel_type; + priv->_agn.hw_roc_duration = DIV_ROUND_UP(duration * 1000, 1024); + iwlagn_commit_rxon(priv, &priv->contexts[IWL_RXON_CTX_PAN]); + queue_delayed_work(priv->workqueue, &priv->_agn.hw_roc_work, + msecs_to_jiffies(duration + 20)); + + msleep(IWL_MIN_SLOT_TIME); /* TU is almost ms */ + ieee80211_ready_on_channel(priv->hw); + + out: + mutex_unlock(&priv->mutex); + + return err; +} + +static int iwl_mac_cancel_remain_on_channel(struct ieee80211_hw *hw) +{ + struct iwl_priv *priv = hw->priv; + + if (!(priv->valid_contexts & BIT(IWL_RXON_CTX_PAN))) + return -EOPNOTSUPP; + + cancel_delayed_work_sync(&priv->_agn.hw_roc_work); + + mutex_lock(&priv->mutex); + iwlagn_disable_roc(priv); + mutex_unlock(&priv->mutex); + + return 0; +} + /***************************************************************************** * * driver setup and teardown @@ -3724,6 +3838,7 @@ static void iwl_setup_deferred_work(struct iwl_priv *priv) INIT_WORK(&priv->bt_runtime_config, iwl_bg_bt_runtime_config); INIT_DELAYED_WORK(&priv->init_alive_start, iwl_bg_init_alive_start); INIT_DELAYED_WORK(&priv->alive_start, iwl_bg_alive_start); + INIT_DELAYED_WORK(&priv->_agn.hw_roc_work, iwlagn_bg_roc_done); iwl_setup_scan_deferred_work(priv); @@ -3892,6 +4007,8 @@ struct ieee80211_ops iwlagn_hw_ops = { .channel_switch = iwlagn_mac_channel_switch, .flush = iwlagn_mac_flush, .tx_last_beacon = iwl_mac_tx_last_beacon, + .remain_on_channel = iwl_mac_remain_on_channel, + .cancel_remain_on_channel = iwl_mac_cancel_remain_on_channel, }; #endif @@ -4019,6 +4136,10 @@ static int iwl_pci_probe(struct pci_dev *pdev, const struct pci_device_id *ent) priv->contexts[IWL_RXON_CTX_PAN].mcast_queue = IWL_IPAN_MCAST_QUEUE; priv->contexts[IWL_RXON_CTX_PAN].interface_modes = BIT(NL80211_IFTYPE_STATION) | BIT(NL80211_IFTYPE_AP); +#ifdef CONFIG_IWL_P2P + priv->contexts[IWL_RXON_CTX_PAN].interface_modes |= + BIT(NL80211_IFTYPE_P2P_CLIENT) | BIT(NL80211_IFTYPE_P2P_GO); +#endif priv->contexts[IWL_RXON_CTX_PAN].ap_devtype = RXON_DEV_TYPE_CP; priv->contexts[IWL_RXON_CTX_PAN].station_devtype = RXON_DEV_TYPE_2STA; priv->contexts[IWL_RXON_CTX_PAN].unused_devtype = RXON_DEV_TYPE_P2P; @@ -4266,6 +4387,9 @@ static void __devexit iwl_pci_remove(struct pci_dev *pdev) * we need to set STATUS_EXIT_PENDING bit. */ set_bit(STATUS_EXIT_PENDING, &priv->status); + + iwl_leds_exit(priv); + if (priv->mac80211_registered) { ieee80211_unregister_hw(priv->hw); priv->mac80211_registered = 0; @@ -4486,6 +4610,49 @@ static DEFINE_PCI_DEVICE_TABLE(iwl_hw_card_ids) = { {IWL_PCI_DEVICE(0x0896, 0x5025, iwl130_bgn_cfg)}, {IWL_PCI_DEVICE(0x0896, 0x5027, iwl130_bg_cfg)}, +/* 2x00 Series */ + {IWL_PCI_DEVICE(0x0890, 0x4022, iwl2000_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0891, 0x4222, iwl2000_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0890, 0x4422, iwl2000_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0890, 0x4026, iwl2000_2bg_cfg)}, + {IWL_PCI_DEVICE(0x0891, 0x4226, iwl2000_2bg_cfg)}, + {IWL_PCI_DEVICE(0x0890, 0x4426, iwl2000_2bg_cfg)}, + +/* 2x30 Series */ + {IWL_PCI_DEVICE(0x0887, 0x4062, iwl2030_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0888, 0x4262, iwl2030_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0887, 0x4462, iwl2030_2bgn_cfg)}, + {IWL_PCI_DEVICE(0x0887, 0x4066, iwl2030_2bg_cfg)}, + {IWL_PCI_DEVICE(0x0888, 0x4266, iwl2030_2bg_cfg)}, + {IWL_PCI_DEVICE(0x0887, 0x4466, iwl2030_2bg_cfg)}, + +/* 6x35 Series */ + {IWL_PCI_DEVICE(0x088E, 0x4060, iwl6035_2agn_cfg)}, + {IWL_PCI_DEVICE(0x088F, 0x4260, iwl6035_2agn_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x4460, iwl6035_2agn_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x4064, iwl6035_2abg_cfg)}, + {IWL_PCI_DEVICE(0x088F, 0x4264, iwl6035_2abg_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x4464, iwl6035_2abg_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x4066, iwl6035_2bg_cfg)}, + {IWL_PCI_DEVICE(0x088F, 0x4266, iwl6035_2bg_cfg)}, + {IWL_PCI_DEVICE(0x088E, 0x4466, iwl6035_2bg_cfg)}, + +/* 200 Series */ + {IWL_PCI_DEVICE(0x0894, 0x0022, iwl200_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0895, 0x0222, iwl200_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0894, 0x0422, iwl200_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0894, 0x0026, iwl200_bg_cfg)}, + {IWL_PCI_DEVICE(0x0895, 0x0226, iwl200_bg_cfg)}, + {IWL_PCI_DEVICE(0x0894, 0x0426, iwl200_bg_cfg)}, + +/* 230 Series */ + {IWL_PCI_DEVICE(0x0892, 0x0062, iwl230_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0893, 0x0262, iwl230_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0892, 0x0462, iwl230_bgn_cfg)}, + {IWL_PCI_DEVICE(0x0892, 0x0066, iwl230_bg_cfg)}, + {IWL_PCI_DEVICE(0x0893, 0x0266, iwl230_bg_cfg)}, + {IWL_PCI_DEVICE(0x0892, 0x0466, iwl230_bg_cfg)}, + #endif /* CONFIG_IWL5000 */ {0} diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.h b/drivers/net/wireless/iwlwifi/iwl-agn.h index da30358..d00e1ea 100644 --- a/drivers/net/wireless/iwlwifi/iwl-agn.h +++ b/drivers/net/wireless/iwlwifi/iwl-agn.h @@ -96,6 +96,17 @@ extern struct iwl_cfg iwl100_bgn_cfg; extern struct iwl_cfg iwl100_bg_cfg; extern struct iwl_cfg iwl130_bgn_cfg; extern struct iwl_cfg iwl130_bg_cfg; +extern struct iwl_cfg iwl2000_2bgn_cfg; +extern struct iwl_cfg iwl2000_2bg_cfg; +extern struct iwl_cfg iwl2030_2bgn_cfg; +extern struct iwl_cfg iwl2030_2bg_cfg; +extern struct iwl_cfg iwl6035_2agn_cfg; +extern struct iwl_cfg iwl6035_2abg_cfg; +extern struct iwl_cfg iwl6035_2bg_cfg; +extern struct iwl_cfg iwl200_bg_cfg; +extern struct iwl_cfg iwl200_bgn_cfg; +extern struct iwl_cfg iwl230_bg_cfg; +extern struct iwl_cfg iwl230_bgn_cfg; extern struct iwl_mod_params iwlagn_mod_params; extern struct iwl_hcmd_ops iwlagn_hcmd; @@ -185,7 +196,6 @@ void iwlagn_rx_reply_rx(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb); void iwlagn_rx_reply_rx_phy(struct iwl_priv *priv, struct iwl_rx_mem_buffer *rxb); -void iwl_rx_handle(struct iwl_priv *priv); /* tx */ void iwl_hw_txq_free_tfd(struct iwl_priv *priv, struct iwl_tx_queue *txq); @@ -330,6 +340,21 @@ void iwl_eeprom_get_mac(const struct iwl_priv *priv, u8 *mac); int iwlcore_eeprom_acquire_semaphore(struct iwl_priv *priv); void iwlcore_eeprom_release_semaphore(struct iwl_priv *priv); +/* notification wait support */ +void __acquires(wait_entry) +iwlagn_init_notification_wait(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry, + void (*fn)(struct iwl_priv *priv, + struct iwl_rx_packet *pkt), + u8 cmd); +signed long __releases(wait_entry) +iwlagn_wait_notification(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry, + unsigned long timeout); +void __releases(wait_entry) +iwlagn_remove_notification(struct iwl_priv *priv, + struct iwl_notification_wait *wait_entry); + /* mac80211 handlers (for 4965) */ int iwlagn_mac_tx(struct ieee80211_hw *hw, struct sk_buff *skb); int iwlagn_mac_start(struct ieee80211_hw *hw); @@ -349,7 +374,8 @@ void iwlagn_mac_update_tkip_key(struct ieee80211_hw *hw, int iwlagn_mac_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn); + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size); int iwlagn_mac_sta_add(struct ieee80211_hw *hw, struct ieee80211_vif *vif, struct ieee80211_sta *sta); diff --git a/drivers/net/wireless/iwlwifi/iwl-commands.h b/drivers/net/wireless/iwlwifi/iwl-commands.h index f893d4a..935b19e 100644 --- a/drivers/net/wireless/iwlwifi/iwl-commands.h +++ b/drivers/net/wireless/iwlwifi/iwl-commands.h @@ -189,6 +189,7 @@ enum { REPLY_WIPAN_WEPKEY = 0xb8, /* use REPLY_WEPKEY structure */ REPLY_WIPAN_P2P_CHANNEL_SWITCH = 0xb9, REPLY_WIPAN_NOA_NOTIFICATION = 0xbc, + REPLY_WIPAN_DEACTIVATION_COMPLETE = 0xbd, REPLY_MAX = 0xff }; @@ -4369,6 +4370,11 @@ int iwl_agn_check_rxon_cmd(struct iwl_priv *priv); * REPLY_WIPAN_PARAMS = 0xb2 (Commands and Notification) */ +/* + * Minimum slot time in TU + */ +#define IWL_MIN_SLOT_TIME 20 + /** * struct iwl_wipan_slot * @width: Time in TU diff --git a/drivers/net/wireless/iwlwifi/iwl-core.c b/drivers/net/wireless/iwlwifi/iwl-core.c index efbde1f..a46ad60 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.c +++ b/drivers/net/wireless/iwlwifi/iwl-core.c @@ -227,7 +227,8 @@ int iwlcore_init_geos(struct iwl_priv *priv) geo_ch = &sband->channels[sband->n_channels++]; geo_ch->center_freq = - ieee80211_channel_to_frequency(ch->channel); + ieee80211_channel_to_frequency(ch->channel, + sband->band); geo_ch->max_power = ch->max_power_avg; geo_ch->max_antenna_gain = 0xff; geo_ch->hw_value = ch->channel; @@ -1403,9 +1404,10 @@ int iwl_mac_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) struct iwl_vif_priv *vif_priv = (void *)vif->drv_priv; struct iwl_rxon_context *tmp, *ctx = NULL; int err; + enum nl80211_iftype viftype = ieee80211_vif_type_p2p(vif); IWL_DEBUG_MAC80211(priv, "enter: type %d, addr %pM\n", - vif->type, vif->addr); + viftype, vif->addr); mutex_lock(&priv->mutex); @@ -1429,7 +1431,7 @@ int iwl_mac_add_interface(struct ieee80211_hw *hw, struct ieee80211_vif *vif) continue; } - if (!(possible_modes & BIT(vif->type))) + if (!(possible_modes & BIT(viftype))) continue; /* have maybe usable context w/o interface */ @@ -1675,7 +1677,6 @@ void iwl_clear_traffic_stats(struct iwl_priv *priv) { memset(&priv->tx_stats, 0, sizeof(struct traffic_stats)); memset(&priv->rx_stats, 0, sizeof(struct traffic_stats)); - priv->led_tpt = 0; } /* @@ -1768,7 +1769,6 @@ void iwl_update_stats(struct iwl_priv *priv, bool is_tx, __le16 fc, u16 len) stats->data_cnt++; stats->data_bytes += len; } - iwl_leds_background(priv); } EXPORT_SYMBOL(iwl_update_stats); #endif diff --git a/drivers/net/wireless/iwlwifi/iwl-core.h b/drivers/net/wireless/iwlwifi/iwl-core.h index a347437..bbc5aa7 100644 --- a/drivers/net/wireless/iwlwifi/iwl-core.h +++ b/drivers/net/wireless/iwlwifi/iwl-core.h @@ -227,8 +227,6 @@ struct iwl_lib_ops { struct iwl_led_ops { int (*cmd)(struct iwl_priv *priv, struct iwl_led_cmd *led_cmd); - int (*on)(struct iwl_priv *priv); - int (*off)(struct iwl_priv *priv); }; /* NIC specific ops */ @@ -494,18 +492,6 @@ static inline void iwl_dbg_log_rx_data_frame(struct iwl_priv *priv, static inline void iwl_update_stats(struct iwl_priv *priv, bool is_tx, __le16 fc, u16 len) { - struct traffic_stats *stats; - - if (is_tx) - stats = &priv->tx_stats; - else - stats = &priv->rx_stats; - - if (ieee80211_is_data(fc)) { - /* data */ - stats->data_bytes += len; - } - iwl_leds_background(priv); } #endif /***************************************************** diff --git a/drivers/net/wireless/iwlwifi/iwl-csr.h b/drivers/net/wireless/iwlwifi/iwl-csr.h index b80bf7d..6c2b2df 100644 --- a/drivers/net/wireless/iwlwifi/iwl-csr.h +++ b/drivers/net/wireless/iwlwifi/iwl-csr.h @@ -290,7 +290,7 @@ /* HW REV */ -#define CSR_HW_REV_TYPE_MSK (0x00000F0) +#define CSR_HW_REV_TYPE_MSK (0x00001F0) #define CSR_HW_REV_TYPE_3945 (0x00000D0) #define CSR_HW_REV_TYPE_4965 (0x0000000) #define CSR_HW_REV_TYPE_5300 (0x0000020) @@ -300,9 +300,15 @@ #define CSR_HW_REV_TYPE_1000 (0x0000060) #define CSR_HW_REV_TYPE_6x00 (0x0000070) #define CSR_HW_REV_TYPE_6x50 (0x0000080) -#define CSR_HW_REV_TYPE_6x50g2 (0x0000084) -#define CSR_HW_REV_TYPE_6x00g2 (0x00000B0) -#define CSR_HW_REV_TYPE_NONE (0x00000F0) +#define CSR_HW_REV_TYPE_6150 (0x0000084) +#define CSR_HW_REV_TYPE_6x05 (0x00000B0) +#define CSR_HW_REV_TYPE_6x30 CSR_HW_REV_TYPE_6x05 +#define CSR_HW_REV_TYPE_6x35 CSR_HW_REV_TYPE_6x05 +#define CSR_HW_REV_TYPE_2x30 (0x00000C0) +#define CSR_HW_REV_TYPE_2x00 (0x0000100) +#define CSR_HW_REV_TYPE_200 (0x0000110) +#define CSR_HW_REV_TYPE_230 (0x0000120) +#define CSR_HW_REV_TYPE_NONE (0x00001F0) /* EEPROM REG */ #define CSR_EEPROM_REG_READ_VALID_MSK (0x00000001) diff --git a/drivers/net/wireless/iwlwifi/iwl-debugfs.c b/drivers/net/wireless/iwlwifi/iwl-debugfs.c index 6fe80b5..418c8ac 100644 --- a/drivers/net/wireless/iwlwifi/iwl-debugfs.c +++ b/drivers/net/wireless/iwlwifi/iwl-debugfs.c @@ -207,18 +207,19 @@ static ssize_t iwl_dbgfs_rx_statistics_read(struct file *file, return ret; } -#define BYTE1_MASK 0x000000ff; -#define BYTE2_MASK 0x0000ffff; -#define BYTE3_MASK 0x00ffffff; static ssize_t iwl_dbgfs_sram_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { - u32 val; + u32 val = 0; char *buf; ssize_t ret; - int i; + int i = 0; + bool device_format = false; + int offset = 0; + int len = 0; int pos = 0; + int sram; struct iwl_priv *priv = file->private_data; size_t bufsz; @@ -230,35 +231,62 @@ static ssize_t iwl_dbgfs_sram_read(struct file *file, else priv->dbgfs_sram_len = priv->ucode_data.len; } - bufsz = 30 + priv->dbgfs_sram_len * sizeof(char) * 10; + len = priv->dbgfs_sram_len; + + if (len == -4) { + device_format = true; + len = 4; + } + + bufsz = 50 + len * 4; buf = kmalloc(bufsz, GFP_KERNEL); if (!buf) return -ENOMEM; + pos += scnprintf(buf + pos, bufsz - pos, "sram_len: 0x%x\n", - priv->dbgfs_sram_len); + len); pos += scnprintf(buf + pos, bufsz - pos, "sram_offset: 0x%x\n", priv->dbgfs_sram_offset); - for (i = priv->dbgfs_sram_len; i > 0; i -= 4) { - val = iwl_read_targ_mem(priv, priv->dbgfs_sram_offset + \ - priv->dbgfs_sram_len - i); - if (i < 4) { - switch (i) { - case 1: - val &= BYTE1_MASK; - break; - case 2: - val &= BYTE2_MASK; - break; - case 3: - val &= BYTE3_MASK; - break; - } + + /* adjust sram address since reads are only on even u32 boundaries */ + offset = priv->dbgfs_sram_offset & 0x3; + sram = priv->dbgfs_sram_offset & ~0x3; + + /* read the first u32 from sram */ + val = iwl_read_targ_mem(priv, sram); + + for (; len; len--) { + /* put the address at the start of every line */ + if (i == 0) + pos += scnprintf(buf + pos, bufsz - pos, + "%08X: ", sram + offset); + + if (device_format) + pos += scnprintf(buf + pos, bufsz - pos, + "%02x", (val >> (8 * (3 - offset))) & 0xff); + else + pos += scnprintf(buf + pos, bufsz - pos, + "%02x ", (val >> (8 * offset)) & 0xff); + + /* if all bytes processed, read the next u32 from sram */ + if (++offset == 4) { + sram += 4; + offset = 0; + val = iwl_read_targ_mem(priv, sram); } - if (!(i % 16)) + + /* put in extra spaces and split lines for human readability */ + if (++i == 16) { + i = 0; pos += scnprintf(buf + pos, bufsz - pos, "\n"); - pos += scnprintf(buf + pos, bufsz - pos, "0x%08x ", val); + } else if (!(i & 7)) { + pos += scnprintf(buf + pos, bufsz - pos, " "); + } else if (!(i & 3)) { + pos += scnprintf(buf + pos, bufsz - pos, " "); + } } - pos += scnprintf(buf + pos, bufsz - pos, "\n"); + if (i) + pos += scnprintf(buf + pos, bufsz - pos, "\n"); ret = simple_read_from_buffer(user_buf, count, ppos, buf, pos); kfree(buf); @@ -282,6 +310,9 @@ static ssize_t iwl_dbgfs_sram_write(struct file *file, if (sscanf(buf, "%x,%x", &offset, &len) == 2) { priv->dbgfs_sram_offset = offset; priv->dbgfs_sram_len = len; + } else if (sscanf(buf, "%x", &offset) == 1) { + priv->dbgfs_sram_offset = offset; + priv->dbgfs_sram_len = -4; } else { priv->dbgfs_sram_offset = 0; priv->dbgfs_sram_len = 0; @@ -668,29 +699,6 @@ static ssize_t iwl_dbgfs_qos_read(struct file *file, char __user *user_buf, return simple_read_from_buffer(user_buf, count, ppos, buf, pos); } -static ssize_t iwl_dbgfs_led_read(struct file *file, char __user *user_buf, - size_t count, loff_t *ppos) -{ - struct iwl_priv *priv = file->private_data; - int pos = 0; - char buf[256]; - const size_t bufsz = sizeof(buf); - - pos += scnprintf(buf + pos, bufsz - pos, - "allow blinking: %s\n", - (priv->allow_blinking) ? "True" : "False"); - if (priv->allow_blinking) { - pos += scnprintf(buf + pos, bufsz - pos, - "Led blinking rate: %u\n", - priv->last_blink_rate); - pos += scnprintf(buf + pos, bufsz - pos, - "Last blink time: %lu\n", - priv->last_blink_time); - } - - return simple_read_from_buffer(user_buf, count, ppos, buf, pos); -} - static ssize_t iwl_dbgfs_thermal_throttling_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) @@ -856,7 +864,6 @@ DEBUGFS_READ_FILE_OPS(channels); DEBUGFS_READ_FILE_OPS(status); DEBUGFS_READ_WRITE_FILE_OPS(interrupt); DEBUGFS_READ_FILE_OPS(qos); -DEBUGFS_READ_FILE_OPS(led); DEBUGFS_READ_FILE_OPS(thermal_throttling); DEBUGFS_READ_WRITE_FILE_OPS(disable_ht40); DEBUGFS_READ_WRITE_FILE_OPS(sleep_level_override); @@ -1725,7 +1732,6 @@ int iwl_dbgfs_register(struct iwl_priv *priv, const char *name) DEBUGFS_ADD_FILE(status, dir_data, S_IRUSR); DEBUGFS_ADD_FILE(interrupt, dir_data, S_IWUSR | S_IRUSR); DEBUGFS_ADD_FILE(qos, dir_data, S_IRUSR); - DEBUGFS_ADD_FILE(led, dir_data, S_IRUSR); if (!priv->cfg->base_params->broken_powersave) { DEBUGFS_ADD_FILE(sleep_level_override, dir_data, S_IWUSR | S_IRUSR); diff --git a/drivers/net/wireless/iwlwifi/iwl-dev.h b/drivers/net/wireless/iwlwifi/iwl-dev.h index 8dda678..6fa1383 100644 --- a/drivers/net/wireless/iwlwifi/iwl-dev.h +++ b/drivers/net/wireless/iwlwifi/iwl-dev.h @@ -34,6 +34,8 @@ #include <linux/pci.h> /* for struct pci_device_id */ #include <linux/kernel.h> +#include <linux/wait.h> +#include <linux/leds.h> #include <net/ieee80211_radiotap.h> #include "iwl-eeprom.h" @@ -995,7 +997,6 @@ struct reply_agg_tx_error_statistics { u32 unknown; }; -#ifdef CONFIG_IWLWIFI_DEBUGFS /* management statistics */ enum iwl_mgmt_stats { MANAGEMENT_ASSOC_REQ = 0, @@ -1026,16 +1027,13 @@ enum iwl_ctrl_stats { }; struct traffic_stats { +#ifdef CONFIG_IWLWIFI_DEBUGFS u32 mgmt[MANAGEMENT_MAX]; u32 ctrl[CONTROL_MAX]; u32 data_cnt; u64 data_bytes; -}; -#else -struct traffic_stats { - u64 data_bytes; -}; #endif +}; /* * iwl_switch_rxon: "channel switch" structure @@ -1139,6 +1137,33 @@ struct iwl_force_reset { */ #define IWLAGN_EXT_BEACON_TIME_POS 22 +/** + * struct iwl_notification_wait - notification wait entry + * @list: list head for global list + * @fn: function called with the notification + * @cmd: command ID + * + * This structure is not used directly, to wait for a + * notification declare it on the stack, and call + * iwlagn_init_notification_wait() with appropriate + * parameters. Then do whatever will cause the ucode + * to notify the driver, and to wait for that then + * call iwlagn_wait_notification(). + * + * Each notification is one-shot. If at some point we + * need to support multi-shot notifications (which + * can't be allocated on the stack) we need to modify + * the code for them. + */ +struct iwl_notification_wait { + struct list_head list; + + void (*fn)(struct iwl_priv *priv, struct iwl_rx_packet *pkt); + + u8 cmd; + bool triggered; +}; + enum iwl_rxon_context_id { IWL_RXON_CTX_BSS, IWL_RXON_CTX_PAN, @@ -1310,11 +1335,6 @@ struct iwl_priv { struct iwl_init_alive_resp card_alive_init; struct iwl_alive_resp card_alive; - unsigned long last_blink_time; - u8 last_blink_rate; - u8 allow_blinking; - u64 led_tpt; - u16 active_rate; u8 start_calib; @@ -1463,6 +1483,17 @@ struct iwl_priv { struct iwl_bt_notif_statistics delta_statistics_bt; struct iwl_bt_notif_statistics max_delta_bt; #endif + + /* notification wait support */ + struct list_head notif_waits; + spinlock_t notif_wait_lock; + wait_queue_head_t notif_waitq; + + /* remain-on-channel offload support */ + struct ieee80211_channel *hw_roc_channel; + struct delayed_work hw_roc_work; + enum nl80211_channel_type hw_roc_chantype; + int hw_roc_duration; } _agn; #endif }; @@ -1547,6 +1578,10 @@ struct iwl_priv { bool hw_ready; struct iwl_event_log event_log; + + struct led_classdev led; + unsigned long blink_on, blink_off; + bool led_registered; }; /*iwl_priv */ static inline void iwl_txq_ctx_activate(struct iwl_priv *priv, int txq_id) diff --git a/drivers/net/wireless/iwlwifi/iwl-eeprom.h b/drivers/net/wireless/iwlwifi/iwl-eeprom.h index 9e6f313..98aa8af 100644 --- a/drivers/net/wireless/iwlwifi/iwl-eeprom.h +++ b/drivers/net/wireless/iwlwifi/iwl-eeprom.h @@ -247,13 +247,26 @@ struct iwl_eeprom_enhanced_txpwr { #define EEPROM_6050_TX_POWER_VERSION (4) #define EEPROM_6050_EEPROM_VERSION (0x532) -/* 6x50g2 Specific */ -#define EEPROM_6050G2_TX_POWER_VERSION (6) -#define EEPROM_6050G2_EEPROM_VERSION (0x553) +/* 6150 Specific */ +#define EEPROM_6150_TX_POWER_VERSION (6) +#define EEPROM_6150_EEPROM_VERSION (0x553) + +/* 6x05 Specific */ +#define EEPROM_6005_TX_POWER_VERSION (6) +#define EEPROM_6005_EEPROM_VERSION (0x709) + +/* 6x30 Specific */ +#define EEPROM_6030_TX_POWER_VERSION (6) +#define EEPROM_6030_EEPROM_VERSION (0x709) + +/* 2x00 Specific */ +#define EEPROM_2000_TX_POWER_VERSION (6) +#define EEPROM_2000_EEPROM_VERSION (0x805) + +/* 6x35 Specific */ +#define EEPROM_6035_TX_POWER_VERSION (6) +#define EEPROM_6035_EEPROM_VERSION (0x753) -/* 6x00g2 Specific */ -#define EEPROM_6000G2_TX_POWER_VERSION (6) -#define EEPROM_6000G2_EEPROM_VERSION (0x709) /* OTP */ /* lower blocks contain EEPROM image and calibration data */ @@ -264,6 +277,7 @@ struct iwl_eeprom_enhanced_txpwr { #define OTP_MAX_LL_ITEMS_1000 (3) /* OTP blocks for 1000 */ #define OTP_MAX_LL_ITEMS_6x00 (4) /* OTP blocks for 6x00 */ #define OTP_MAX_LL_ITEMS_6x50 (7) /* OTP blocks for 6x50 */ +#define OTP_MAX_LL_ITEMS_2x00 (4) /* OTP blocks for 2x00 */ /* 2.4 GHz */ extern const u8 iwl_eeprom_band_1[14]; diff --git a/drivers/net/wireless/iwlwifi/iwl-hcmd.c b/drivers/net/wireless/iwlwifi/iwl-hcmd.c index c373b53..e4b953d 100644 --- a/drivers/net/wireless/iwlwifi/iwl-hcmd.c +++ b/drivers/net/wireless/iwlwifi/iwl-hcmd.c @@ -108,6 +108,7 @@ const char *get_cmd_string(u8 cmd) IWL_CMD(REPLY_WIPAN_WEPKEY); IWL_CMD(REPLY_WIPAN_P2P_CHANNEL_SWITCH); IWL_CMD(REPLY_WIPAN_NOA_NOTIFICATION); + IWL_CMD(REPLY_WIPAN_DEACTIVATION_COMPLETE); default: return "UNKNOWN"; diff --git a/drivers/net/wireless/iwlwifi/iwl-led.c b/drivers/net/wireless/iwlwifi/iwl-led.c index 46ccdf4..074ad22 100644 --- a/drivers/net/wireless/iwlwifi/iwl-led.c +++ b/drivers/net/wireless/iwlwifi/iwl-led.c @@ -48,31 +48,19 @@ module_param(led_mode, int, S_IRUGO); MODULE_PARM_DESC(led_mode, "0=system default, " "1=On(RF On)/Off(RF Off), 2=blinking"); -static const struct { - u16 tpt; /* Mb/s */ - u8 on_time; - u8 off_time; -} blink_tbl[] = -{ - {300, 25, 25}, - {200, 40, 40}, - {100, 55, 55}, - {70, 65, 65}, - {50, 75, 75}, - {20, 85, 85}, - {10, 95, 95}, - {5, 110, 110}, - {1, 130, 130}, - {0, 167, 167}, - /* SOLID_ON */ - {-1, IWL_LED_SOLID, 0} +static const struct ieee80211_tpt_blink iwl_blink[] = { + { .throughput = 0 * 1024 - 1, .blink_time = 334 }, + { .throughput = 1 * 1024 - 1, .blink_time = 260 }, + { .throughput = 5 * 1024 - 1, .blink_time = 220 }, + { .throughput = 10 * 1024 - 1, .blink_time = 190 }, + { .throughput = 20 * 1024 - 1, .blink_time = 170 }, + { .throughput = 50 * 1024 - 1, .blink_time = 150 }, + { .throughput = 70 * 1024 - 1, .blink_time = 130 }, + { .throughput = 100 * 1024 - 1, .blink_time = 110 }, + { .throughput = 200 * 1024 - 1, .blink_time = 80 }, + { .throughput = 300 * 1024 - 1, .blink_time = 50 }, }; -#define IWL_1MB_RATE (128 * 1024) -#define IWL_LED_THRESHOLD (16) -#define IWL_MAX_BLINK_TBL (ARRAY_SIZE(blink_tbl) - 1) /* exclude SOLID_ON */ -#define IWL_SOLID_BLINK_IDX (ARRAY_SIZE(blink_tbl) - 1) - /* * Adjust led blink rate to compensate on a MAC Clock difference on every HW * Led blink rate analysis showed an average deviation of 0% on 3945, @@ -97,133 +85,104 @@ static inline u8 iwl_blink_compensation(struct iwl_priv *priv, } /* Set led pattern command */ -static int iwl_led_pattern(struct iwl_priv *priv, unsigned int idx) +static int iwl_led_cmd(struct iwl_priv *priv, + unsigned long on, + unsigned long off) { struct iwl_led_cmd led_cmd = { .id = IWL_LED_LINK, .interval = IWL_DEF_LED_INTRVL }; + int ret; - BUG_ON(idx > IWL_MAX_BLINK_TBL); + if (!test_bit(STATUS_READY, &priv->status)) + return -EBUSY; - IWL_DEBUG_LED(priv, "Led blink time compensation= %u\n", + if (priv->blink_on == on && priv->blink_off == off) + return 0; + + IWL_DEBUG_LED(priv, "Led blink time compensation=%u\n", priv->cfg->base_params->led_compensation); - led_cmd.on = - iwl_blink_compensation(priv, blink_tbl[idx].on_time, + led_cmd.on = iwl_blink_compensation(priv, on, priv->cfg->base_params->led_compensation); - led_cmd.off = - iwl_blink_compensation(priv, blink_tbl[idx].off_time, + led_cmd.off = iwl_blink_compensation(priv, off, priv->cfg->base_params->led_compensation); - return priv->cfg->ops->led->cmd(priv, &led_cmd); + ret = priv->cfg->ops->led->cmd(priv, &led_cmd); + if (!ret) { + priv->blink_on = on; + priv->blink_off = off; + } + return ret; } -int iwl_led_start(struct iwl_priv *priv) +static void iwl_led_brightness_set(struct led_classdev *led_cdev, + enum led_brightness brightness) { - return priv->cfg->ops->led->on(priv); -} -EXPORT_SYMBOL(iwl_led_start); + struct iwl_priv *priv = container_of(led_cdev, struct iwl_priv, led); + unsigned long on = 0; -int iwl_led_associate(struct iwl_priv *priv) -{ - IWL_DEBUG_LED(priv, "Associated\n"); - if (priv->cfg->led_mode == IWL_LED_BLINK) - priv->allow_blinking = 1; - priv->last_blink_time = jiffies; + if (brightness > 0) + on = IWL_LED_SOLID; - return 0; + iwl_led_cmd(priv, on, 0); } -EXPORT_SYMBOL(iwl_led_associate); -int iwl_led_disassociate(struct iwl_priv *priv) +static int iwl_led_blink_set(struct led_classdev *led_cdev, + unsigned long *delay_on, + unsigned long *delay_off) { - priv->allow_blinking = 0; + struct iwl_priv *priv = container_of(led_cdev, struct iwl_priv, led); - return 0; + return iwl_led_cmd(priv, *delay_on, *delay_off); } -EXPORT_SYMBOL(iwl_led_disassociate); -/* - * calculate blink rate according to last second Tx/Rx activities - */ -static int iwl_get_blink_rate(struct iwl_priv *priv) -{ - int i; - /* count both tx and rx traffic to be able to - * handle traffic in either direction - */ - u64 current_tpt = priv->tx_stats.data_bytes + - priv->rx_stats.data_bytes; - s64 tpt = current_tpt - priv->led_tpt; - - if (tpt < 0) /* wraparound */ - tpt = -tpt; - - IWL_DEBUG_LED(priv, "tpt %lld current_tpt %llu\n", - (long long)tpt, - (unsigned long long)current_tpt); - priv->led_tpt = current_tpt; - - if (!priv->allow_blinking) - i = IWL_MAX_BLINK_TBL; - else - for (i = 0; i < IWL_MAX_BLINK_TBL; i++) - if (tpt > (blink_tbl[i].tpt * IWL_1MB_RATE)) - break; - - IWL_DEBUG_LED(priv, "LED BLINK IDX=%d\n", i); - return i; -} - -/* - * this function called from handler. Since setting Led command can - * happen very frequent we postpone led command to be called from - * REPLY handler so we know ucode is up - */ -void iwl_leds_background(struct iwl_priv *priv) +void iwl_leds_init(struct iwl_priv *priv) { - u8 blink_idx; - - if (test_bit(STATUS_EXIT_PENDING, &priv->status)) { - priv->last_blink_time = 0; - return; - } - if (iwl_is_rfkill(priv)) { - priv->last_blink_time = 0; - return; + int mode = led_mode; + int ret; + + if (mode == IWL_LED_DEFAULT) + mode = priv->cfg->led_mode; + + priv->led.name = kasprintf(GFP_KERNEL, "%s-led", + wiphy_name(priv->hw->wiphy)); + priv->led.brightness_set = iwl_led_brightness_set; + priv->led.blink_set = iwl_led_blink_set; + priv->led.max_brightness = 1; + + switch (mode) { + case IWL_LED_DEFAULT: + WARN_ON(1); + break; + case IWL_LED_BLINK: + priv->led.default_trigger = + ieee80211_create_tpt_led_trigger(priv->hw, + IEEE80211_TPT_LEDTRIG_FL_CONNECTED, + iwl_blink, ARRAY_SIZE(iwl_blink)); + break; + case IWL_LED_RF_STATE: + priv->led.default_trigger = + ieee80211_get_radio_led_name(priv->hw); + break; } - if (!priv->allow_blinking) { - priv->last_blink_time = 0; - if (priv->last_blink_rate != IWL_SOLID_BLINK_IDX) { - priv->last_blink_rate = IWL_SOLID_BLINK_IDX; - iwl_led_pattern(priv, IWL_SOLID_BLINK_IDX); - } + ret = led_classdev_register(&priv->pci_dev->dev, &priv->led); + if (ret) { + kfree(priv->led.name); return; } - if (!priv->last_blink_time || - !time_after(jiffies, priv->last_blink_time + - msecs_to_jiffies(1000))) - return; - - blink_idx = iwl_get_blink_rate(priv); - /* call only if blink rate change */ - if (blink_idx != priv->last_blink_rate) - iwl_led_pattern(priv, blink_idx); - - priv->last_blink_time = jiffies; - priv->last_blink_rate = blink_idx; + priv->led_registered = true; } -EXPORT_SYMBOL(iwl_leds_background); +EXPORT_SYMBOL(iwl_leds_init); -void iwl_leds_init(struct iwl_priv *priv) +void iwl_leds_exit(struct iwl_priv *priv) { - priv->last_blink_rate = 0; - priv->last_blink_time = 0; - priv->allow_blinking = 0; - if (led_mode != IWL_LED_DEFAULT && - led_mode != priv->cfg->led_mode) - priv->cfg->led_mode = led_mode; + if (!priv->led_registered) + return; + + led_classdev_unregister(&priv->led); + kfree(priv->led.name); } -EXPORT_SYMBOL(iwl_leds_init); +EXPORT_SYMBOL(iwl_leds_exit); diff --git a/drivers/net/wireless/iwlwifi/iwl-led.h b/drivers/net/wireless/iwlwifi/iwl-led.h index 9079b33..101eef1 100644 --- a/drivers/net/wireless/iwlwifi/iwl-led.h +++ b/drivers/net/wireless/iwlwifi/iwl-led.h @@ -31,23 +31,14 @@ struct iwl_priv; #define IWL_LED_SOLID 11 -#define IWL_LED_NAME_LEN 31 #define IWL_DEF_LED_INTRVL cpu_to_le32(1000) #define IWL_LED_ACTIVITY (0<<1) #define IWL_LED_LINK (1<<1) -enum led_type { - IWL_LED_TRG_TX, - IWL_LED_TRG_RX, - IWL_LED_TRG_ASSOC, - IWL_LED_TRG_RADIO, - IWL_LED_TRG_MAX, -}; - /* * LED mode - * IWL_LED_DEFAULT: use system default + * IWL_LED_DEFAULT: use device default * IWL_LED_RF_STATE: turn LED on/off based on RF state * LED ON = RF ON * LED OFF = RF OFF @@ -60,9 +51,6 @@ enum iwl_led_mode { }; void iwl_leds_init(struct iwl_priv *priv); -void iwl_leds_background(struct iwl_priv *priv); -int iwl_led_start(struct iwl_priv *priv); -int iwl_led_associate(struct iwl_priv *priv); -int iwl_led_disassociate(struct iwl_priv *priv); +void iwl_leds_exit(struct iwl_priv *priv); #endif /* __iwl_leds_h__ */ diff --git a/drivers/net/wireless/iwlwifi/iwl-legacy.c b/drivers/net/wireless/iwlwifi/iwl-legacy.c index bb1a742..927fe37 100644 --- a/drivers/net/wireless/iwlwifi/iwl-legacy.c +++ b/drivers/net/wireless/iwlwifi/iwl-legacy.c @@ -332,7 +332,6 @@ static inline void iwl_set_no_assoc(struct iwl_priv *priv, { struct iwl_rxon_context *ctx = iwl_rxon_ctx_from_vif(vif); - iwl_led_disassociate(priv); /* * inform the ucode that there is no longer an * association and that no more packets should be @@ -520,8 +519,6 @@ void iwl_legacy_mac_bss_info_changed(struct ieee80211_hw *hw, if (bss_conf->assoc) { priv->timestamp = bss_conf->timestamp; - iwl_led_associate(priv); - if (!iwl_is_rfkill(priv)) priv->cfg->ops->legacy->post_associate(priv); } else @@ -545,7 +542,6 @@ void iwl_legacy_mac_bss_info_changed(struct ieee80211_hw *hw, memcpy(ctx->staging.bssid_addr, bss_conf->bssid, ETH_ALEN); memcpy(priv->bssid, bss_conf->bssid, ETH_ALEN); - iwl_led_associate(priv); priv->cfg->ops->legacy->config_ap(priv); } else iwl_set_no_assoc(priv, vif); diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c index 371abbf..9c986f2 100644 --- a/drivers/net/wireless/iwlwifi/iwl3945-base.c +++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c @@ -2540,8 +2540,6 @@ static void iwl3945_alive_start(struct iwl_priv *priv) iwl3945_reg_txpower_periodic(priv); - iwl_leds_init(priv); - IWL_DEBUG_INFO(priv, "ALIVE processing complete.\n"); set_bit(STATUS_READY, &priv->status); wake_up_interruptible(&priv->wait_command_queue); @@ -3170,8 +3168,6 @@ static int iwl3945_mac_start(struct ieee80211_hw *hw) * no need to poll the killswitch state anymore */ cancel_delayed_work(&priv->_3945.rfkill_poll); - iwl_led_start(priv); - priv->is_open = 1; IWL_DEBUG_MAC80211(priv, "leave\n"); return 0; @@ -3935,6 +3931,8 @@ static int iwl3945_setup_mac(struct iwl_priv *priv) priv->hw->wiphy->bands[IEEE80211_BAND_5GHZ] = &priv->bands[IEEE80211_BAND_5GHZ]; + iwl_leds_init(priv); + ret = ieee80211_register_hw(priv->hw); if (ret) { IWL_ERR(priv, "Failed to register hw (error %d)\n", ret); @@ -4194,6 +4192,8 @@ static void __devexit iwl3945_pci_remove(struct pci_dev *pdev) set_bit(STATUS_EXIT_PENDING, &priv->status); + iwl_leds_exit(priv); + if (priv->mac80211_registered) { ieee80211_unregister_hw(priv->hw); priv->mac80211_registered = 0; diff --git a/drivers/net/wireless/iwmc3200wifi/cfg80211.c b/drivers/net/wireless/iwmc3200wifi/cfg80211.c index 5a49822..ed57e44 100644 --- a/drivers/net/wireless/iwmc3200wifi/cfg80211.c +++ b/drivers/net/wireless/iwmc3200wifi/cfg80211.c @@ -287,7 +287,8 @@ int iwm_cfg80211_inform_bss(struct iwm_priv *iwm) return -EINVAL; } - freq = ieee80211_channel_to_frequency(umac_bss->channel); + freq = ieee80211_channel_to_frequency(umac_bss->channel, + band->band); channel = ieee80211_get_channel(wiphy, freq); signal = umac_bss->rssi * 100; diff --git a/drivers/net/wireless/iwmc3200wifi/rx.c b/drivers/net/wireless/iwmc3200wifi/rx.c index a944893..9a57cf6 100644 --- a/drivers/net/wireless/iwmc3200wifi/rx.c +++ b/drivers/net/wireless/iwmc3200wifi/rx.c @@ -543,7 +543,10 @@ static int iwm_mlme_assoc_complete(struct iwm_priv *iwm, u8 *buf, switch (le32_to_cpu(complete->status)) { case UMAC_ASSOC_COMPLETE_SUCCESS: chan = ieee80211_get_channel(wiphy, - ieee80211_channel_to_frequency(complete->channel)); + ieee80211_channel_to_frequency(complete->channel, + complete->band == UMAC_BAND_2GHZ ? + IEEE80211_BAND_2GHZ : + IEEE80211_BAND_5GHZ)); if (!chan || chan->flags & IEEE80211_CHAN_DISABLED) { /* Associated to a unallowed channel, disassociate. */ __iwm_invalidate_mlme_profile(iwm); @@ -841,7 +844,7 @@ static int iwm_mlme_update_bss_table(struct iwm_priv *iwm, u8 *buf, goto err; } - freq = ieee80211_channel_to_frequency(umac_bss->channel); + freq = ieee80211_channel_to_frequency(umac_bss->channel, band->band); channel = ieee80211_get_channel(wiphy, freq); signal = umac_bss->rssi * 100; diff --git a/drivers/net/wireless/libertas/cfg.c b/drivers/net/wireless/libertas/cfg.c index 698a1f7..30ef035 100644 --- a/drivers/net/wireless/libertas/cfg.c +++ b/drivers/net/wireless/libertas/cfg.c @@ -607,7 +607,8 @@ static int lbs_ret_scan(struct lbs_private *priv, unsigned long dummy, /* No channel, no luck */ if (chan_no != -1) { struct wiphy *wiphy = priv->wdev->wiphy; - int freq = ieee80211_channel_to_frequency(chan_no); + int freq = ieee80211_channel_to_frequency(chan_no, + IEEE80211_BAND_2GHZ); struct ieee80211_channel *channel = ieee80211_get_channel(wiphy, freq); @@ -1597,7 +1598,8 @@ static int lbs_get_survey(struct wiphy *wiphy, struct net_device *dev, lbs_deb_enter(LBS_DEB_CFG80211); survey->channel = ieee80211_get_channel(wiphy, - ieee80211_channel_to_frequency(priv->channel)); + ieee80211_channel_to_frequency(priv->channel, + IEEE80211_BAND_2GHZ)); ret = lbs_get_rssi(priv, &signal, &noise); if (ret == 0) { diff --git a/drivers/net/wireless/mac80211_hwsim.c b/drivers/net/wireless/mac80211_hwsim.c index 454f045..5d39b28 100644 --- a/drivers/net/wireless/mac80211_hwsim.c +++ b/drivers/net/wireless/mac80211_hwsim.c @@ -943,7 +943,8 @@ static int mac80211_hwsim_testmode_cmd(struct ieee80211_hw *hw, static int mac80211_hwsim_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { switch (action) { case IEEE80211_AMPDU_TX_START: diff --git a/drivers/net/wireless/mwl8k.c b/drivers/net/wireless/mwl8k.c index 9ecf840..af4f2c6 100644 --- a/drivers/net/wireless/mwl8k.c +++ b/drivers/net/wireless/mwl8k.c @@ -232,6 +232,9 @@ struct mwl8k_priv { struct completion firmware_loading_complete; }; +#define MAX_WEP_KEY_LEN 13 +#define NUM_WEP_KEYS 4 + /* Per interface specific private data */ struct mwl8k_vif { struct list_head list; @@ -242,8 +245,21 @@ struct mwl8k_vif { /* Non AMPDU sequence number assigned by driver. */ u16 seqno; + + /* Saved WEP keys */ + struct { + u8 enabled; + u8 key[sizeof(struct ieee80211_key_conf) + MAX_WEP_KEY_LEN]; + } wep_key_conf[NUM_WEP_KEYS]; + + /* BSSID */ + u8 bssid[ETH_ALEN]; + + /* A flag to indicate is HW crypto is enabled for this bssid */ + bool is_hw_crypto_enabled; }; #define MWL8K_VIF(_vif) ((struct mwl8k_vif *)&((_vif)->drv_priv)) +#define IEEE80211_KEY_CONF(_u8) ((struct ieee80211_key_conf *)(_u8)) struct mwl8k_sta { /* Index into station database. Returned by UPDATE_STADB. */ @@ -337,6 +353,7 @@ static const struct ieee80211_rate mwl8k_rates_50[] = { #define MWL8K_CMD_SET_RATEADAPT_MODE 0x0203 #define MWL8K_CMD_BSS_START 0x1100 /* per-vif */ #define MWL8K_CMD_SET_NEW_STN 0x1111 /* per-vif */ +#define MWL8K_CMD_UPDATE_ENCRYPTION 0x1122 /* per-vif */ #define MWL8K_CMD_UPDATE_STADB 0x1123 static const char *mwl8k_cmd_name(__le16 cmd, char *buf, int bufsize) @@ -375,6 +392,7 @@ static const char *mwl8k_cmd_name(__le16 cmd, char *buf, int bufsize) MWL8K_CMDNAME(SET_RATEADAPT_MODE); MWL8K_CMDNAME(BSS_START); MWL8K_CMDNAME(SET_NEW_STN); + MWL8K_CMDNAME(UPDATE_ENCRYPTION); MWL8K_CMDNAME(UPDATE_STADB); default: snprintf(buf, bufsize, "0x%x", cmd); @@ -715,10 +733,12 @@ static inline void mwl8k_remove_dma_header(struct sk_buff *skb, __le16 qos) skb_pull(skb, sizeof(*tr) - hdrlen); } -static inline void mwl8k_add_dma_header(struct sk_buff *skb) +static void +mwl8k_add_dma_header(struct sk_buff *skb, int tail_pad) { struct ieee80211_hdr *wh; int hdrlen; + int reqd_hdrlen; struct mwl8k_dma_data *tr; /* @@ -730,11 +750,13 @@ static inline void mwl8k_add_dma_header(struct sk_buff *skb) wh = (struct ieee80211_hdr *)skb->data; hdrlen = ieee80211_hdrlen(wh->frame_control); - if (hdrlen != sizeof(*tr)) - skb_push(skb, sizeof(*tr) - hdrlen); + reqd_hdrlen = sizeof(*tr); + + if (hdrlen != reqd_hdrlen) + skb_push(skb, reqd_hdrlen - hdrlen); if (ieee80211_is_data_qos(wh->frame_control)) - hdrlen -= 2; + hdrlen -= IEEE80211_QOS_CTL_LEN; tr = (struct mwl8k_dma_data *)skb->data; if (wh != &tr->wh) @@ -747,9 +769,52 @@ static inline void mwl8k_add_dma_header(struct sk_buff *skb) * payload". That is, everything except for the 802.11 header. * This includes all crypto material including the MIC. */ - tr->fwlen = cpu_to_le16(skb->len - sizeof(*tr)); + tr->fwlen = cpu_to_le16(skb->len - sizeof(*tr) + tail_pad); } +static void mwl8k_encapsulate_tx_frame(struct sk_buff *skb) +{ + struct ieee80211_hdr *wh; + struct ieee80211_tx_info *tx_info; + struct ieee80211_key_conf *key_conf; + int data_pad; + + wh = (struct ieee80211_hdr *)skb->data; + + tx_info = IEEE80211_SKB_CB(skb); + + key_conf = NULL; + if (ieee80211_is_data(wh->frame_control)) + key_conf = tx_info->control.hw_key; + + /* + * Make sure the packet header is in the DMA header format (4-address + * without QoS), the necessary crypto padding between the header and the + * payload has already been provided by mac80211, but it doesn't add tail + * padding when HW crypto is enabled. + * + * We have the following trailer padding requirements: + * - WEP: 4 trailer bytes (ICV) + * - TKIP: 12 trailer bytes (8 MIC + 4 ICV) + * - CCMP: 8 trailer bytes (MIC) + */ + data_pad = 0; + if (key_conf != NULL) { + switch (key_conf->cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + data_pad = 4; + break; + case WLAN_CIPHER_SUITE_TKIP: + data_pad = 12; + break; + case WLAN_CIPHER_SUITE_CCMP: + data_pad = 8; + break; + } + } + mwl8k_add_dma_header(skb, data_pad); +} /* * Packet reception for 88w8366 AP firmware. @@ -778,6 +843,13 @@ struct mwl8k_rxd_8366_ap { #define MWL8K_8366_AP_RX_CTRL_OWNED_BY_HOST 0x80 +/* 8366 AP rx_status bits */ +#define MWL8K_8366_AP_RXSTAT_DECRYPT_ERR_MASK 0x80 +#define MWL8K_8366_AP_RXSTAT_GENERAL_DECRYPT_ERR 0xFF +#define MWL8K_8366_AP_RXSTAT_TKIP_DECRYPT_MIC_ERR 0x02 +#define MWL8K_8366_AP_RXSTAT_WEP_DECRYPT_ICV_ERR 0x04 +#define MWL8K_8366_AP_RXSTAT_TKIP_DECRYPT_ICV_ERR 0x08 + static void mwl8k_rxd_8366_ap_init(void *_rxd, dma_addr_t next_dma_addr) { struct mwl8k_rxd_8366_ap *rxd = _rxd; @@ -834,10 +906,16 @@ mwl8k_rxd_8366_ap_process(void *_rxd, struct ieee80211_rx_status *status, } else { status->band = IEEE80211_BAND_2GHZ; } - status->freq = ieee80211_channel_to_frequency(rxd->channel); + status->freq = ieee80211_channel_to_frequency(rxd->channel, + status->band); *qos = rxd->qos_control; + if ((rxd->rx_status != MWL8K_8366_AP_RXSTAT_GENERAL_DECRYPT_ERR) && + (rxd->rx_status & MWL8K_8366_AP_RXSTAT_DECRYPT_ERR_MASK) && + (rxd->rx_status & MWL8K_8366_AP_RXSTAT_TKIP_DECRYPT_MIC_ERR)) + status->flag |= RX_FLAG_MMIC_ERROR; + return le16_to_cpu(rxd->pkt_len); } @@ -876,6 +954,11 @@ struct mwl8k_rxd_sta { #define MWL8K_STA_RATE_INFO_MCS_FORMAT 0x0001 #define MWL8K_STA_RX_CTRL_OWNED_BY_HOST 0x02 +#define MWL8K_STA_RX_CTRL_DECRYPT_ERROR 0x04 +/* ICV=0 or MIC=1 */ +#define MWL8K_STA_RX_CTRL_DEC_ERR_TYPE 0x08 +/* Key is uploaded only in failure case */ +#define MWL8K_STA_RX_CTRL_KEY_INDEX 0x30 static void mwl8k_rxd_sta_init(void *_rxd, dma_addr_t next_dma_addr) { @@ -931,9 +1014,13 @@ mwl8k_rxd_sta_process(void *_rxd, struct ieee80211_rx_status *status, } else { status->band = IEEE80211_BAND_2GHZ; } - status->freq = ieee80211_channel_to_frequency(rxd->channel); + status->freq = ieee80211_channel_to_frequency(rxd->channel, + status->band); *qos = rxd->qos_control; + if ((rxd->rx_ctrl & MWL8K_STA_RX_CTRL_DECRYPT_ERROR) && + (rxd->rx_ctrl & MWL8K_STA_RX_CTRL_DEC_ERR_TYPE)) + status->flag |= RX_FLAG_MMIC_ERROR; return le16_to_cpu(rxd->pkt_len); } @@ -1092,9 +1179,25 @@ static inline void mwl8k_save_beacon(struct ieee80211_hw *hw, ieee80211_queue_work(hw, &priv->finalize_join_worker); } +static inline struct mwl8k_vif *mwl8k_find_vif_bss(struct list_head *vif_list, + u8 *bssid) +{ + struct mwl8k_vif *mwl8k_vif; + + list_for_each_entry(mwl8k_vif, + vif_list, list) { + if (memcmp(bssid, mwl8k_vif->bssid, + ETH_ALEN) == 0) + return mwl8k_vif; + } + + return NULL; +} + static int rxq_process(struct ieee80211_hw *hw, int index, int limit) { struct mwl8k_priv *priv = hw->priv; + struct mwl8k_vif *mwl8k_vif = NULL; struct mwl8k_rx_queue *rxq = priv->rxq + index; int processed; @@ -1104,6 +1207,7 @@ static int rxq_process(struct ieee80211_hw *hw, int index, int limit) void *rxd; int pkt_len; struct ieee80211_rx_status status; + struct ieee80211_hdr *wh; __le16 qos; skb = rxq->buf[rxq->head].skb; @@ -1130,8 +1234,7 @@ static int rxq_process(struct ieee80211_hw *hw, int index, int limit) rxq->rxd_count--; - skb_put(skb, pkt_len); - mwl8k_remove_dma_header(skb, qos); + wh = &((struct mwl8k_dma_data *)skb->data)->wh; /* * Check for a pending join operation. Save a @@ -1141,6 +1244,46 @@ static int rxq_process(struct ieee80211_hw *hw, int index, int limit) if (mwl8k_capture_bssid(priv, (void *)skb->data)) mwl8k_save_beacon(hw, skb); + if (ieee80211_has_protected(wh->frame_control)) { + + /* Check if hw crypto has been enabled for + * this bss. If yes, set the status flags + * accordingly + */ + mwl8k_vif = mwl8k_find_vif_bss(&priv->vif_list, + wh->addr1); + + if (mwl8k_vif != NULL && + mwl8k_vif->is_hw_crypto_enabled == true) { + /* + * When MMIC ERROR is encountered + * by the firmware, payload is + * dropped and only 32 bytes of + * mwl8k Firmware header is sent + * to the host. + * + * We need to add four bytes of + * key information. In it + * MAC80211 expects keyidx set to + * 0 for triggering Counter + * Measure of MMIC failure. + */ + if (status.flag & RX_FLAG_MMIC_ERROR) { + struct mwl8k_dma_data *tr; + tr = (struct mwl8k_dma_data *)skb->data; + memset((void *)&(tr->data), 0, 4); + pkt_len += 4; + } + + if (!ieee80211_is_auth(wh->frame_control)) + status.flag |= RX_FLAG_IV_STRIPPED | + RX_FLAG_DECRYPTED | + RX_FLAG_MMIC_STRIPPED; + } + } + + skb_put(skb, pkt_len); + mwl8k_remove_dma_header(skb, qos); memcpy(IEEE80211_SKB_RXCB(skb), &status, sizeof(status)); ieee80211_rx_irqsafe(hw, skb); @@ -1443,7 +1586,11 @@ mwl8k_txq_xmit(struct ieee80211_hw *hw, int index, struct sk_buff *skb) else qos = 0; - mwl8k_add_dma_header(skb); + if (priv->ap_fw) + mwl8k_encapsulate_tx_frame(skb); + else + mwl8k_add_dma_header(skb, 0); + wh = &((struct mwl8k_dma_data *)skb->data)->wh; tx_info = IEEE80211_SKB_CB(skb); @@ -3099,6 +3246,274 @@ static int mwl8k_cmd_set_new_stn_del(struct ieee80211_hw *hw, } /* + * CMD_UPDATE_ENCRYPTION. + */ + +#define MAX_ENCR_KEY_LENGTH 16 +#define MIC_KEY_LENGTH 8 + +struct mwl8k_cmd_update_encryption { + struct mwl8k_cmd_pkt header; + + __le32 action; + __le32 reserved; + __u8 mac_addr[6]; + __u8 encr_type; + +} __attribute__((packed)); + +struct mwl8k_cmd_set_key { + struct mwl8k_cmd_pkt header; + + __le32 action; + __le32 reserved; + __le16 length; + __le16 key_type_id; + __le32 key_info; + __le32 key_id; + __le16 key_len; + __u8 key_material[MAX_ENCR_KEY_LENGTH]; + __u8 tkip_tx_mic_key[MIC_KEY_LENGTH]; + __u8 tkip_rx_mic_key[MIC_KEY_LENGTH]; + __le16 tkip_rsc_low; + __le32 tkip_rsc_high; + __le16 tkip_tsc_low; + __le32 tkip_tsc_high; + __u8 mac_addr[6]; +} __attribute__((packed)); + +enum { + MWL8K_ENCR_ENABLE, + MWL8K_ENCR_SET_KEY, + MWL8K_ENCR_REMOVE_KEY, + MWL8K_ENCR_SET_GROUP_KEY, +}; + +#define MWL8K_UPDATE_ENCRYPTION_TYPE_WEP 0 +#define MWL8K_UPDATE_ENCRYPTION_TYPE_DISABLE 1 +#define MWL8K_UPDATE_ENCRYPTION_TYPE_TKIP 4 +#define MWL8K_UPDATE_ENCRYPTION_TYPE_MIXED 7 +#define MWL8K_UPDATE_ENCRYPTION_TYPE_AES 8 + +enum { + MWL8K_ALG_WEP, + MWL8K_ALG_TKIP, + MWL8K_ALG_CCMP, +}; + +#define MWL8K_KEY_FLAG_TXGROUPKEY 0x00000004 +#define MWL8K_KEY_FLAG_PAIRWISE 0x00000008 +#define MWL8K_KEY_FLAG_TSC_VALID 0x00000040 +#define MWL8K_KEY_FLAG_WEP_TXKEY 0x01000000 +#define MWL8K_KEY_FLAG_MICKEY_VALID 0x02000000 + +static int mwl8k_cmd_update_encryption_enable(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u8 *addr, + u8 encr_type) +{ + struct mwl8k_cmd_update_encryption *cmd; + int rc; + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (cmd == NULL) + return -ENOMEM; + + cmd->header.code = cpu_to_le16(MWL8K_CMD_UPDATE_ENCRYPTION); + cmd->header.length = cpu_to_le16(sizeof(*cmd)); + cmd->action = cpu_to_le32(MWL8K_ENCR_ENABLE); + memcpy(cmd->mac_addr, addr, ETH_ALEN); + cmd->encr_type = encr_type; + + rc = mwl8k_post_pervif_cmd(hw, vif, &cmd->header); + kfree(cmd); + + return rc; +} + +static int mwl8k_encryption_set_cmd_info(struct mwl8k_cmd_set_key *cmd, + u8 *addr, + struct ieee80211_key_conf *key) +{ + cmd->header.code = cpu_to_le16(MWL8K_CMD_UPDATE_ENCRYPTION); + cmd->header.length = cpu_to_le16(sizeof(*cmd)); + cmd->length = cpu_to_le16(sizeof(*cmd) - + offsetof(struct mwl8k_cmd_set_key, length)); + cmd->key_id = cpu_to_le32(key->keyidx); + cmd->key_len = cpu_to_le16(key->keylen); + memcpy(cmd->mac_addr, addr, ETH_ALEN); + + switch (key->cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + cmd->key_type_id = cpu_to_le16(MWL8K_ALG_WEP); + if (key->keyidx == 0) + cmd->key_info = cpu_to_le32(MWL8K_KEY_FLAG_WEP_TXKEY); + + break; + case WLAN_CIPHER_SUITE_TKIP: + cmd->key_type_id = cpu_to_le16(MWL8K_ALG_TKIP); + cmd->key_info = (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) + ? cpu_to_le32(MWL8K_KEY_FLAG_PAIRWISE) + : cpu_to_le32(MWL8K_KEY_FLAG_TXGROUPKEY); + cmd->key_info |= cpu_to_le32(MWL8K_KEY_FLAG_MICKEY_VALID + | MWL8K_KEY_FLAG_TSC_VALID); + break; + case WLAN_CIPHER_SUITE_CCMP: + cmd->key_type_id = cpu_to_le16(MWL8K_ALG_CCMP); + cmd->key_info = (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) + ? cpu_to_le32(MWL8K_KEY_FLAG_PAIRWISE) + : cpu_to_le32(MWL8K_KEY_FLAG_TXGROUPKEY); + break; + default: + return -ENOTSUPP; + } + + return 0; +} + +static int mwl8k_cmd_encryption_set_key(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u8 *addr, + struct ieee80211_key_conf *key) +{ + struct mwl8k_cmd_set_key *cmd; + int rc; + int keymlen; + u32 action; + u8 idx; + struct mwl8k_vif *mwl8k_vif = MWL8K_VIF(vif); + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (cmd == NULL) + return -ENOMEM; + + rc = mwl8k_encryption_set_cmd_info(cmd, addr, key); + if (rc < 0) + goto done; + + idx = key->keyidx; + + if (key->flags & IEEE80211_KEY_FLAG_PAIRWISE) + action = MWL8K_ENCR_SET_KEY; + else + action = MWL8K_ENCR_SET_GROUP_KEY; + + switch (key->cipher) { + case WLAN_CIPHER_SUITE_WEP40: + case WLAN_CIPHER_SUITE_WEP104: + if (!mwl8k_vif->wep_key_conf[idx].enabled) { + memcpy(mwl8k_vif->wep_key_conf[idx].key, key, + sizeof(*key) + key->keylen); + mwl8k_vif->wep_key_conf[idx].enabled = 1; + } + + keymlen = 0; + action = MWL8K_ENCR_SET_KEY; + break; + case WLAN_CIPHER_SUITE_TKIP: + keymlen = MAX_ENCR_KEY_LENGTH + 2 * MIC_KEY_LENGTH; + break; + case WLAN_CIPHER_SUITE_CCMP: + keymlen = key->keylen; + break; + default: + rc = -ENOTSUPP; + goto done; + } + + memcpy(cmd->key_material, key->key, keymlen); + cmd->action = cpu_to_le32(action); + + rc = mwl8k_post_pervif_cmd(hw, vif, &cmd->header); +done: + kfree(cmd); + + return rc; +} + +static int mwl8k_cmd_encryption_remove_key(struct ieee80211_hw *hw, + struct ieee80211_vif *vif, + u8 *addr, + struct ieee80211_key_conf *key) +{ + struct mwl8k_cmd_set_key *cmd; + int rc; + struct mwl8k_vif *mwl8k_vif = MWL8K_VIF(vif); + + cmd = kzalloc(sizeof(*cmd), GFP_KERNEL); + if (cmd == NULL) + return -ENOMEM; + + rc = mwl8k_encryption_set_cmd_info(cmd, addr, key); + if (rc < 0) + goto done; + + if (key->cipher == WLAN_CIPHER_SUITE_WEP40 || + WLAN_CIPHER_SUITE_WEP104) + mwl8k_vif->wep_key_conf[key->keyidx].enabled = 0; + + cmd->action = cpu_to_le32(MWL8K_ENCR_REMOVE_KEY); + + rc = mwl8k_post_pervif_cmd(hw, vif, &cmd->header); +done: + kfree(cmd); + + return rc; +} + +static int mwl8k_set_key(struct ieee80211_hw *hw, + enum set_key_cmd cmd_param, + struct ieee80211_vif *vif, + struct ieee80211_sta *sta, + struct ieee80211_key_conf *key) +{ + int rc = 0; + u8 encr_type; + u8 *addr; + struct mwl8k_vif *mwl8k_vif = MWL8K_VIF(vif); + + if (vif->type == NL80211_IFTYPE_STATION) + return -EOPNOTSUPP; + + if (sta == NULL) + addr = hw->wiphy->perm_addr; + else + addr = sta->addr; + + if (cmd_param == SET_KEY) { + key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV; + rc = mwl8k_cmd_encryption_set_key(hw, vif, addr, key); + if (rc) + goto out; + + if ((key->cipher == WLAN_CIPHER_SUITE_WEP40) + || (key->cipher == WLAN_CIPHER_SUITE_WEP104)) + encr_type = MWL8K_UPDATE_ENCRYPTION_TYPE_WEP; + else + encr_type = MWL8K_UPDATE_ENCRYPTION_TYPE_MIXED; + + rc = mwl8k_cmd_update_encryption_enable(hw, vif, addr, + encr_type); + if (rc) + goto out; + + mwl8k_vif->is_hw_crypto_enabled = true; + + } else { + rc = mwl8k_cmd_encryption_remove_key(hw, vif, addr, key); + + if (rc) + goto out; + + mwl8k_vif->is_hw_crypto_enabled = false; + + } +out: + return rc; +} + +/* * CMD_UPDATE_STADB. */ struct ewc_ht_info { @@ -3469,6 +3884,8 @@ static int mwl8k_add_interface(struct ieee80211_hw *hw, mwl8k_vif->vif = vif; mwl8k_vif->macid = macid; mwl8k_vif->seqno = 0; + memcpy(mwl8k_vif->bssid, vif->addr, ETH_ALEN); + mwl8k_vif->is_hw_crypto_enabled = false; /* Set the mac address. */ mwl8k_cmd_set_mac_addr(hw, vif, vif->addr); @@ -3866,18 +4283,27 @@ static int mwl8k_sta_add(struct ieee80211_hw *hw, { struct mwl8k_priv *priv = hw->priv; int ret; + int i; + struct mwl8k_vif *mwl8k_vif = MWL8K_VIF(vif); + struct ieee80211_key_conf *key; if (!priv->ap_fw) { ret = mwl8k_cmd_update_stadb_add(hw, vif, sta); if (ret >= 0) { MWL8K_STA(sta)->peer_id = ret; - return 0; + ret = 0; } - return ret; + } else { + ret = mwl8k_cmd_set_new_stn_add(hw, vif, sta); } - return mwl8k_cmd_set_new_stn_add(hw, vif, sta); + for (i = 0; i < NUM_WEP_KEYS; i++) { + key = IEEE80211_KEY_CONF(mwl8k_vif->wep_key_conf[i].key); + if (mwl8k_vif->wep_key_conf[i].enabled) + mwl8k_set_key(hw, SET_KEY, vif, sta, key); + } + return ret; } static int mwl8k_conf_tx(struct ieee80211_hw *hw, u16 queue, @@ -3932,7 +4358,8 @@ static int mwl8k_get_survey(struct ieee80211_hw *hw, int idx, static int mwl8k_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { switch (action) { case IEEE80211_AMPDU_RX_START: @@ -3955,6 +4382,7 @@ static const struct ieee80211_ops mwl8k_ops = { .bss_info_changed = mwl8k_bss_info_changed, .prepare_multicast = mwl8k_prepare_multicast, .configure_filter = mwl8k_configure_filter, + .set_key = mwl8k_set_key, .set_rts_threshold = mwl8k_set_rts_threshold, .sta_add = mwl8k_sta_add, .sta_remove = mwl8k_sta_remove, diff --git a/drivers/net/wireless/rt2x00/rt2800.h b/drivers/net/wireless/rt2x00/rt2800.h index 4c55e85..c7e615c 100644 --- a/drivers/net/wireless/rt2x00/rt2800.h +++ b/drivers/net/wireless/rt2x00/rt2800.h @@ -1805,6 +1805,12 @@ struct mac_iveiv_entry { #define RFCSR30_RF_CALIBRATION FIELD8(0x80) /* + * RFCSR 31: + */ +#define RFCSR31_RX_AGC_FC FIELD8(0x1f) +#define RFCSR31_RX_H20M FIELD8(0x20) + +/* * RF registers */ diff --git a/drivers/net/wireless/rt2x00/rt2800lib.c b/drivers/net/wireless/rt2x00/rt2800lib.c index 54917a2..f8ba01c 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.c +++ b/drivers/net/wireless/rt2x00/rt2800lib.c @@ -2436,6 +2436,10 @@ static u8 rt2800_init_rx_filter(struct rt2x00_dev *rt2x00dev, rt2x00_set_field8(&bbp, BBP4_BANDWIDTH, 2 * bw40); rt2800_bbp_write(rt2x00dev, 4, bbp); + rt2800_rfcsr_read(rt2x00dev, 31, &rfcsr); + rt2x00_set_field8(&rfcsr, RFCSR31_RX_H20M, bw40); + rt2800_rfcsr_write(rt2x00dev, 31, rfcsr); + rt2800_rfcsr_read(rt2x00dev, 22, &rfcsr); rt2x00_set_field8(&rfcsr, RFCSR22_BASEBAND_LOOPBACK, 1); rt2800_rfcsr_write(rt2x00dev, 22, rfcsr); @@ -2510,7 +2514,7 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) rt2800_rfcsr_write(rt2x00dev, 4, 0x40); rt2800_rfcsr_write(rt2x00dev, 5, 0x03); rt2800_rfcsr_write(rt2x00dev, 6, 0x02); - rt2800_rfcsr_write(rt2x00dev, 7, 0x70); + rt2800_rfcsr_write(rt2x00dev, 7, 0x60); rt2800_rfcsr_write(rt2x00dev, 9, 0x0f); rt2800_rfcsr_write(rt2x00dev, 10, 0x41); rt2800_rfcsr_write(rt2x00dev, 11, 0x21); @@ -2602,12 +2606,12 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) rt2800_register_write(rt2x00dev, LDO_CFG0, reg); } else if (rt2x00_rt(rt2x00dev, RT3071) || rt2x00_rt(rt2x00dev, RT3090)) { + rt2800_rfcsr_write(rt2x00dev, 31, 0x14); + rt2800_rfcsr_read(rt2x00dev, 6, &rfcsr); rt2x00_set_field8(&rfcsr, RFCSR6_R2, 1); rt2800_rfcsr_write(rt2x00dev, 6, rfcsr); - rt2800_rfcsr_write(rt2x00dev, 31, 0x14); - rt2800_register_read(rt2x00dev, LDO_CFG0, ®); rt2x00_set_field32(®, LDO_CFG0_BGSEL, 1); if (rt2x00_rt_rev_lt(rt2x00dev, RT3071, REV_RT3071E) || @@ -2619,6 +2623,10 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) rt2x00_set_field32(®, LDO_CFG0_LDO_CORE_VLEVEL, 0); } rt2800_register_write(rt2x00dev, LDO_CFG0, reg); + + rt2800_register_read(rt2x00dev, GPIO_SWITCH, ®); + rt2x00_set_field32(®, GPIO_SWITCH_5, 0); + rt2800_register_write(rt2x00dev, GPIO_SWITCH, reg); } else if (rt2x00_rt(rt2x00dev, RT3390)) { rt2800_register_read(rt2x00dev, GPIO_SWITCH, ®); rt2x00_set_field32(®, GPIO_SWITCH_5, 0); @@ -2670,10 +2678,11 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) rt2800_rfcsr_read(rt2x00dev, 17, &rfcsr); rt2x00_set_field8(&rfcsr, RFCSR17_TX_LO1_EN, 0); - if (rt2x00_rt_rev_lt(rt2x00dev, RT3071, REV_RT3071E) || + if (rt2x00_rt(rt2x00dev, RT3070) || + rt2x00_rt_rev_lt(rt2x00dev, RT3071, REV_RT3071E) || rt2x00_rt_rev_lt(rt2x00dev, RT3090, REV_RT3090E) || rt2x00_rt_rev_lt(rt2x00dev, RT3390, REV_RT3390E)) { - if (test_bit(CONFIG_EXTERNAL_LNA_BG, &rt2x00dev->flags)) + if (!test_bit(CONFIG_EXTERNAL_LNA_BG, &rt2x00dev->flags)) rt2x00_set_field8(&rfcsr, RFCSR17_R, 1); } rt2x00_eeprom_read(rt2x00dev, EEPROM_TXMIXER_GAIN_BG, &eeprom); @@ -2686,6 +2695,7 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) if (rt2x00_rt(rt2x00dev, RT3090)) { rt2800_bbp_read(rt2x00dev, 138, &bbp); + /* Turn off unused DAC1 and ADC1 to reduce power consumption */ rt2x00_eeprom_read(rt2x00dev, EEPROM_NIC_CONF0, &eeprom); if (rt2x00_get_field16(eeprom, EEPROM_NIC_CONF0_RXPATH) == 1) rt2x00_set_field8(&bbp, BBP138_RX_ADC1, 0); @@ -2719,10 +2729,9 @@ static int rt2800_init_rfcsr(struct rt2x00_dev *rt2x00dev) rt2800_rfcsr_write(rt2x00dev, 21, rfcsr); } - if (rt2x00_rt(rt2x00dev, RT3070) || rt2x00_rt(rt2x00dev, RT3071)) { + if (rt2x00_rt(rt2x00dev, RT3070)) { rt2800_rfcsr_read(rt2x00dev, 27, &rfcsr); - if (rt2x00_rt_rev_lt(rt2x00dev, RT3070, REV_RT3070F) || - rt2x00_rt_rev_lt(rt2x00dev, RT3071, REV_RT3071E)) + if (rt2x00_rt_rev_lt(rt2x00dev, RT3070, REV_RT3070F)) rt2x00_set_field8(&rfcsr, RFCSR27_R1, 3); else rt2x00_set_field8(&rfcsr, RFCSR27_R1, 0); @@ -2810,10 +2819,7 @@ void rt2800_disable_radio(struct rt2x00_dev *rt2x00dev) rt2800_register_read(rt2x00dev, WPDMA_GLO_CFG, ®); rt2x00_set_field32(®, WPDMA_GLO_CFG_ENABLE_TX_DMA, 0); - rt2x00_set_field32(®, WPDMA_GLO_CFG_TX_DMA_BUSY, 0); rt2x00_set_field32(®, WPDMA_GLO_CFG_ENABLE_RX_DMA, 0); - rt2x00_set_field32(®, WPDMA_GLO_CFG_RX_DMA_BUSY, 0); - rt2x00_set_field32(®, WPDMA_GLO_CFG_TX_WRITEBACK_DONE, 1); rt2800_register_write(rt2x00dev, WPDMA_GLO_CFG, reg); /* Wait for DMA, ignore error */ @@ -2823,9 +2829,6 @@ void rt2800_disable_radio(struct rt2x00_dev *rt2x00dev) rt2x00_set_field32(®, MAC_SYS_CTRL_ENABLE_TX, 0); rt2x00_set_field32(®, MAC_SYS_CTRL_ENABLE_RX, 0); rt2800_register_write(rt2x00dev, MAC_SYS_CTRL, reg); - - rt2800_register_write(rt2x00dev, PWR_PIN_CFG, 0); - rt2800_register_write(rt2x00dev, TX_PIN_CFG, 0); } EXPORT_SYMBOL_GPL(rt2800_disable_radio); @@ -3530,7 +3533,8 @@ EXPORT_SYMBOL_GPL(rt2800_get_tsf); int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { int ret = 0; diff --git a/drivers/net/wireless/rt2x00/rt2800lib.h b/drivers/net/wireless/rt2x00/rt2800lib.h index e3c995a..3efafb7 100644 --- a/drivers/net/wireless/rt2x00/rt2800lib.h +++ b/drivers/net/wireless/rt2x00/rt2800lib.h @@ -198,7 +198,8 @@ int rt2800_conf_tx(struct ieee80211_hw *hw, u16 queue_idx, u64 rt2800_get_tsf(struct ieee80211_hw *hw); int rt2800_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn); + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size); int rt2800_get_survey(struct ieee80211_hw *hw, int idx, struct survey_info *survey); diff --git a/drivers/net/wireless/rt2x00/rt2800pci.c b/drivers/net/wireless/rt2x00/rt2800pci.c index aa97971..bfc2fc5 100644 --- a/drivers/net/wireless/rt2x00/rt2800pci.c +++ b/drivers/net/wireless/rt2x00/rt2800pci.c @@ -475,39 +475,23 @@ static int rt2800pci_enable_radio(struct rt2x00_dev *rt2x00dev) static void rt2800pci_disable_radio(struct rt2x00_dev *rt2x00dev) { - u32 reg; - - rt2800_disable_radio(rt2x00dev); - - rt2800_register_write(rt2x00dev, PBF_SYS_CTRL, 0x00001280); - - rt2800_register_read(rt2x00dev, WPDMA_RST_IDX, ®); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX0, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX1, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX2, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX3, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX4, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DTX_IDX5, 1); - rt2x00_set_field32(®, WPDMA_RST_IDX_DRX_IDX0, 1); - rt2800_register_write(rt2x00dev, WPDMA_RST_IDX, reg); - - rt2800_register_write(rt2x00dev, PBF_SYS_CTRL, 0x00000e1f); - rt2800_register_write(rt2x00dev, PBF_SYS_CTRL, 0x00000e00); + if (rt2x00_is_soc(rt2x00dev)) { + rt2800_disable_radio(rt2x00dev); + rt2800_register_write(rt2x00dev, PWR_PIN_CFG, 0); + rt2800_register_write(rt2x00dev, TX_PIN_CFG, 0); + } } static int rt2800pci_set_state(struct rt2x00_dev *rt2x00dev, enum dev_state state) { - /* - * Always put the device to sleep (even when we intend to wakeup!) - * if the device is booting and wasn't asleep it will return - * failure when attempting to wakeup. - */ - rt2800_mcu_request(rt2x00dev, MCU_SLEEP, 0xff, 0xff, 2); - if (state == STATE_AWAKE) { - rt2800_mcu_request(rt2x00dev, MCU_WAKEUP, TOKEN_WAKUP, 0, 0); + rt2800_mcu_request(rt2x00dev, MCU_WAKEUP, TOKEN_WAKUP, 0, 0x02); rt2800pci_mcu_status(rt2x00dev, TOKEN_WAKUP); + } else if (state == STATE_SLEEP) { + rt2800_register_write(rt2x00dev, H2M_MAILBOX_STATUS, 0xffffffff); + rt2800_register_write(rt2x00dev, H2M_MAILBOX_CID, 0xffffffff); + rt2800_mcu_request(rt2x00dev, MCU_SLEEP, 0x01, 0xff, 0x01); } return 0; diff --git a/drivers/net/wireless/rt2x00/rt2x00dev.c b/drivers/net/wireless/rt2x00/rt2x00dev.c index 9597a03..31b7db0 100644 --- a/drivers/net/wireless/rt2x00/rt2x00dev.c +++ b/drivers/net/wireless/rt2x00/rt2x00dev.c @@ -649,7 +649,10 @@ static void rt2x00lib_channel(struct ieee80211_channel *entry, const int channel, const int tx_power, const int value) { - entry->center_freq = ieee80211_channel_to_frequency(channel); + /* XXX: this assumption about the band is wrong for 802.11j */ + entry->band = channel <= 14 ? IEEE80211_BAND_2GHZ : IEEE80211_BAND_5GHZ; + entry->center_freq = ieee80211_channel_to_frequency(channel, + entry->band); entry->hw_value = value; entry->max_power = tx_power; entry->max_antenna_gain = 0xff; diff --git a/drivers/net/wireless/rtlwifi/core.c b/drivers/net/wireless/rtlwifi/core.c index d6a924a..25d2d66 100644 --- a/drivers/net/wireless/rtlwifi/core.c +++ b/drivers/net/wireless/rtlwifi/core.c @@ -748,7 +748,8 @@ static void rtl_op_sta_notify(struct ieee80211_hw *hw, static int rtl_op_ampdu_action(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 * ssn) + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size) { struct rtl_priv *rtlpriv = rtl_priv(hw); diff --git a/drivers/net/wireless/wl1251/rx.c b/drivers/net/wireless/wl1251/rx.c index efa5360..86eef45 100644 --- a/drivers/net/wireless/wl1251/rx.c +++ b/drivers/net/wireless/wl1251/rx.c @@ -78,7 +78,8 @@ static void wl1251_rx_status(struct wl1251 *wl, */ wl->noise = desc->rssi - desc->snr / 2; - status->freq = ieee80211_channel_to_frequency(desc->channel); + status->freq = ieee80211_channel_to_frequency(desc->channel, + status->band); status->flag |= RX_FLAG_TSFT; diff --git a/drivers/net/wireless/wl12xx/rx.c b/drivers/net/wireless/wl12xx/rx.c index 682304c..ec8d843 100644 --- a/drivers/net/wireless/wl12xx/rx.c +++ b/drivers/net/wireless/wl12xx/rx.c @@ -76,7 +76,7 @@ static void wl1271_rx_status(struct wl1271 *wl, */ wl->noise = desc->rssi - (desc->snr >> 1); - status->freq = ieee80211_channel_to_frequency(desc->channel); + status->freq = ieee80211_channel_to_frequency(desc->channel, desc_band); if (desc->flags & WL1271_RX_DESC_ENCRYPT_MASK) { status->flag |= RX_FLAG_IV_STRIPPED | RX_FLAG_MMIC_STRIPPED; diff --git a/include/linux/audit.h b/include/linux/audit.h index 359df04..9d339eb 100644 --- a/include/linux/audit.h +++ b/include/linux/audit.h @@ -103,6 +103,8 @@ #define AUDIT_BPRM_FCAPS 1321 /* Information about fcaps increasing perms */ #define AUDIT_CAPSET 1322 /* Record showing argument to sys_capset */ #define AUDIT_MMAP 1323 /* Record showing descriptor and flags in mmap */ +#define AUDIT_NETFILTER_PKT 1324 /* Packets traversing netfilter chains */ +#define AUDIT_NETFILTER_CFG 1325 /* Netfilter chain modifications */ #define AUDIT_AVC 1400 /* SE Linux avc denial or grant */ #define AUDIT_SELINUX_ERR 1401 /* Internal SE Linux Errors */ diff --git a/include/linux/cpu_rmap.h b/include/linux/cpu_rmap.h new file mode 100644 index 0000000..473771a --- /dev/null +++ b/include/linux/cpu_rmap.h @@ -0,0 +1,73 @@ +/* + * cpu_rmap.c: CPU affinity reverse-map support + * 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. + */ + +#include <linux/cpumask.h> +#include <linux/gfp.h> +#include <linux/slab.h> + +/** + * struct cpu_rmap - CPU affinity reverse-map + * @size: Number of objects to be reverse-mapped + * @used: Number of objects added + * @obj: Pointer to array of object pointers + * @near: For each CPU, the index and distance to the nearest object, + * based on affinity masks + */ +struct cpu_rmap { + u16 size, used; + void **obj; + struct { + u16 index; + u16 dist; + } near[0]; +}; +#define CPU_RMAP_DIST_INF 0xffff + +extern struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags); + +/** + * free_cpu_rmap - free CPU affinity reverse-map + * @rmap: Reverse-map allocated with alloc_cpu_rmap(), or %NULL + */ +static inline void free_cpu_rmap(struct cpu_rmap *rmap) +{ + kfree(rmap); +} + +extern int cpu_rmap_add(struct cpu_rmap *rmap, void *obj); +extern int cpu_rmap_update(struct cpu_rmap *rmap, u16 index, + const struct cpumask *affinity); + +static inline u16 cpu_rmap_lookup_index(struct cpu_rmap *rmap, unsigned int cpu) +{ + return rmap->near[cpu].index; +} + +static inline void *cpu_rmap_lookup_obj(struct cpu_rmap *rmap, unsigned int cpu) +{ + return rmap->obj[rmap->near[cpu].index]; +} + +#ifdef CONFIG_GENERIC_HARDIRQS + +/** + * alloc_irq_cpu_rmap - allocate CPU affinity reverse-map for IRQs + * @size: Number of objects to be mapped + * + * Must be called in process context. + */ +static inline struct cpu_rmap *alloc_irq_cpu_rmap(unsigned int size) +{ + return alloc_cpu_rmap(size, GFP_KERNEL); +} +extern void free_irq_cpu_rmap(struct cpu_rmap *rmap); + +extern int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq); + +#endif diff --git a/include/linux/dccp.h b/include/linux/dccp.h index 010e2d8..d638e85 100644 --- a/include/linux/dccp.h +++ b/include/linux/dccp.h @@ -279,8 +279,6 @@ enum dccp_state { DCCP_MAX_STATES }; -#define DCCP_STATE_MASK 0x1f - enum { DCCPF_OPEN = TCPF_ESTABLISHED, DCCPF_REQUESTING = TCPF_SYN_SENT, diff --git a/include/linux/if_link.h b/include/linux/if_link.h index 6485d2a..f4a2e6b 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -135,6 +135,7 @@ enum { IFLA_VF_PORTS, IFLA_PORT_SELF, IFLA_AF_SPEC, + IFLA_GROUP, /* Group the device belongs to */ __IFLA_MAX }; diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 55e0d42..63c5ad7 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -14,6 +14,8 @@ #include <linux/smp.h> #include <linux/percpu.h> #include <linux/hrtimer.h> +#include <linux/kref.h> +#include <linux/workqueue.h> #include <asm/atomic.h> #include <asm/ptrace.h> @@ -240,6 +242,35 @@ extern int irq_can_set_affinity(unsigned int irq); extern int irq_select_affinity(unsigned int irq); extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m); + +/** + * struct irq_affinity_notify - context for notification of IRQ affinity changes + * @irq: Interrupt to which notification applies + * @kref: Reference count, for internal use + * @work: Work item, for internal use + * @notify: Function to be called on change. This will be + * called in process context. + * @release: Function to be called on release. This will be + * called in process context. Once registered, the + * structure must only be freed when this function is + * called or later. + */ +struct irq_affinity_notify { + unsigned int irq; + struct kref kref; + struct work_struct work; + void (*notify)(struct irq_affinity_notify *, const cpumask_t *mask); + void (*release)(struct kref *ref); +}; + +extern int +irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify); + +static inline void irq_run_affinity_notifiers(void) +{ + flush_scheduled_work(); +} + #else /* CONFIG_SMP */ static inline int irq_set_affinity(unsigned int irq, const struct cpumask *m) @@ -255,7 +286,7 @@ static inline int irq_can_set_affinity(unsigned int irq) static inline int irq_select_affinity(unsigned int irq) { return 0; } static inline int irq_set_affinity_hint(unsigned int irq, - const struct cpumask *m) + const struct cpumask *m) { return -EINVAL; } diff --git a/include/linux/ip_vs.h b/include/linux/ip_vs.h index 5f43a3b..4deb383 100644 --- a/include/linux/ip_vs.h +++ b/include/linux/ip_vs.h @@ -89,6 +89,14 @@ #define IP_VS_CONN_F_TEMPLATE 0x1000 /* template, not connection */ #define IP_VS_CONN_F_ONE_PACKET 0x2000 /* forward only one packet */ +#define IP_VS_CONN_F_BACKUP_MASK (IP_VS_CONN_F_FWD_MASK | \ + IP_VS_CONN_F_NOOUTPUT | \ + IP_VS_CONN_F_INACTIVE | \ + IP_VS_CONN_F_SEQ_MASK | \ + IP_VS_CONN_F_NO_CPORT | \ + IP_VS_CONN_F_TEMPLATE \ + ) + /* Flags that are not sent to backup server start from bit 16 */ #define IP_VS_CONN_F_NFCT (1 << 16) /* use netfilter conntrack */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index c1a95b7..bfef56d 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -8,6 +8,7 @@ * For now it's included from <linux/irq.h> */ +struct irq_affinity_notify; struct proc_dir_entry; struct timer_rand_state; /** @@ -24,6 +25,7 @@ struct timer_rand_state; * @last_unhandled: aging timer for unhandled count * @irqs_unhandled: stats field for spurious unhandled interrupts * @lock: locking for SMP + * @affinity_notify: context for notification of affinity changes * @pending_mask: pending rebalanced interrupts * @threads_active: number of irqaction threads currently running * @wait_for_threads: wait queue for sync_irq to wait for threaded handlers @@ -70,6 +72,7 @@ struct irq_desc { raw_spinlock_t lock; #ifdef CONFIG_SMP const struct cpumask *affinity_hint; + struct irq_affinity_notify *affinity_notify; #ifdef CONFIG_GENERIC_PENDING_IRQ cpumask_var_t pending_mask; #endif diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d971346..c7d7074 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -75,6 +75,9 @@ struct wireless_dev; #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ +/* Initial net device group. All devices belong to group 0 by default. */ +#define INIT_NETDEV_GROUP 0 + /* * Transmit return codes: transmit return codes originate from three different * namespaces: @@ -551,14 +554,16 @@ struct rps_map { #define RPS_MAP_SIZE(_num) (sizeof(struct rps_map) + (_num * sizeof(u16))) /* - * The rps_dev_flow structure contains the mapping of a flow to a CPU and the - * tail pointer for that CPU's input queue at the time of last enqueue. + * The rps_dev_flow structure contains the mapping of a flow to a CPU, the + * tail pointer for that CPU's input queue at the time of last enqueue, and + * a hardware filter index. */ struct rps_dev_flow { u16 cpu; - u16 fill; + u16 filter; unsigned int last_qtail; }; +#define RPS_NO_FILTER 0xffff /* * The rps_dev_flow_table structure contains a table of flow mappings. @@ -608,6 +613,11 @@ static inline void rps_reset_sock_flow(struct rps_sock_flow_table *table, extern struct rps_sock_flow_table __rcu *rps_sock_flow_table; +#ifdef CONFIG_RFS_ACCEL +extern bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, + u32 flow_id, u16 filter_id); +#endif + /* This structure contains an instance of an RX queue. */ struct netdev_rx_queue { struct rps_map __rcu *rps_map; @@ -643,6 +653,14 @@ struct xps_dev_maps { (nr_cpu_ids * sizeof(struct xps_map *))) #endif /* CONFIG_XPS */ +#define TC_MAX_QUEUE 16 +#define TC_BITMASK 15 +/* HW offloaded queuing disciplines txq count and offset maps */ +struct netdev_tc_txq { + u16 count; + u16 offset; +}; + /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are @@ -753,6 +771,18 @@ struct xps_dev_maps { * int (*ndo_set_vf_port)(struct net_device *dev, int vf, * struct nlattr *port[]); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + * int (*ndo_setup_tc)(struct net_device *dev, u8 tc) + * Called to setup 'tc' number of traffic classes in the net device. This + * is always called from the stack with the rtnl lock held and netif tx + * queues stopped. This allows the netdevice to perform queue management + * safely. + * + * RFS acceleration. + * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, + * u16 rxq_index, u32 flow_id); + * Set hardware filter for RFS. rxq_index is the target queue index; + * flow_id is a flow ID to be passed to rps_may_expire_flow() later. + * Return the filter ID on success, or a negative error code. */ #define HAVE_NET_DEVICE_OPS struct net_device_ops { @@ -811,6 +841,7 @@ struct net_device_ops { struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); + int (*ndo_setup_tc)(struct net_device *dev, u8 tc); #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); @@ -825,6 +856,12 @@ struct net_device_ops { int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); #endif +#ifdef CONFIG_RFS_ACCEL + int (*ndo_rx_flow_steer)(struct net_device *dev, + const struct sk_buff *skb, + u16 rxq_index, + u32 flow_id); +#endif }; /* @@ -877,7 +914,11 @@ struct net_device { struct list_head unreg_list; /* Net device features */ - unsigned long features; + u32 features; + + /* VLAN feature mask */ + u32 vlan_features; + #define NETIF_F_SG 1 /* Scatter/gather IO. */ #define NETIF_F_IP_CSUM 2 /* Can checksum TCP/UDP over IPv4. */ #define NETIF_F_NO_CSUM 4 /* Does not require checksum. F.e. loopack. */ @@ -1039,6 +1080,13 @@ struct net_device { /* Number of RX queues currently active in device */ unsigned int real_num_rx_queues; + +#ifdef CONFIG_RFS_ACCEL + /* CPU reverse-mapping for RX completion interrupts, indexed + * by RX queue number. Assigned by driver. This must only be + * set if the ndo_rx_flow_steer operation is defined. */ + struct cpu_rmap *rx_cpu_rmap; +#endif #endif rx_handler_func_t __rcu *rx_handler; @@ -1132,9 +1180,6 @@ struct net_device { /* rtnetlink link ops */ const struct rtnl_link_ops *rtnl_link_ops; - /* VLAN feature mask */ - unsigned long vlan_features; - /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SIZE 65536 unsigned int gso_max_size; @@ -1143,6 +1188,9 @@ struct net_device { /* Data Center Bridging netlink ops */ const struct dcbnl_rtnl_ops *dcbnl_ops; #endif + u8 num_tc; + struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; + u8 prio_tc_map[TC_BITMASK + 1]; #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) /* max exchange id for FCoE LRO by ddp */ @@ -1153,12 +1201,66 @@ struct net_device { /* phy device may attach itself for hardware timestamping */ struct phy_device *phydev; + + /* group the device belongs to */ + int group; }; #define to_net_dev(d) container_of(d, struct net_device, dev) #define NETDEV_ALIGN 32 static inline +int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio) +{ + return dev->prio_tc_map[prio & TC_BITMASK]; +} + +static inline +int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) +{ + if (tc >= dev->num_tc) + return -EINVAL; + + dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK; + return 0; +} + +static inline +void netdev_reset_tc(struct net_device *dev) +{ + dev->num_tc = 0; + memset(dev->tc_to_txq, 0, sizeof(dev->tc_to_txq)); + memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map)); +} + +static inline +int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset) +{ + if (tc >= dev->num_tc) + return -EINVAL; + + dev->tc_to_txq[tc].count = count; + dev->tc_to_txq[tc].offset = offset; + return 0; +} + +static inline +int netdev_set_num_tc(struct net_device *dev, u8 num_tc) +{ + if (num_tc > TC_MAX_QUEUE) + return -EINVAL; + + dev->num_tc = num_tc; + return 0; +} + +static inline +int netdev_get_num_tc(struct net_device *dev) +{ + return dev->num_tc; +} + +static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) { @@ -1300,7 +1402,7 @@ struct packet_type { struct packet_type *, struct net_device *); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); int (*gso_send_check)(struct sk_buff *skb); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); @@ -1345,7 +1447,7 @@ static inline struct net_device *next_net_device_rcu(struct net_device *dev) struct net *net; net = dev_net(dev); - lh = rcu_dereference(dev->dev_list.next); + lh = rcu_dereference(list_next_rcu(&dev->dev_list)); return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } @@ -1355,6 +1457,13 @@ static inline struct net_device *first_net_device(struct net *net) net_device_entry(net->dev_base_head.next); } +static inline struct net_device *first_net_device_rcu(struct net *net) +{ + struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head)); + + return lh == &net->dev_base_head ? NULL : net_device_entry(lh); +} + extern int netdev_boot_setup_check(struct net_device *dev); extern unsigned long netdev_boot_base(const char *prefix, int unit); extern struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, @@ -1844,6 +1953,7 @@ extern int dev_set_alias(struct net_device *, const char *, size_t); extern int dev_change_net_namespace(struct net_device *, struct net *, const char *); extern int dev_set_mtu(struct net_device *, int); +extern void dev_set_group(struct net_device *, int); extern int dev_set_mac_address(struct net_device *, struct sockaddr *); extern int dev_hard_start_xmit(struct sk_buff *skb, @@ -2268,7 +2378,7 @@ extern int netdev_tstamp_prequeue; extern int weight_p; extern int netdev_set_master(struct net_device *dev, struct net_device *master); extern int skb_checksum_help(struct sk_buff *skb); -extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features); +extern struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features); #ifdef CONFIG_BUG extern void netdev_rx_csum_fault(struct net_device *dev); #else @@ -2295,22 +2405,21 @@ extern char *netdev_drivername(const struct net_device *dev, char *buffer, int l extern void linkwatch_run_queue(void); -unsigned long netdev_increment_features(unsigned long all, unsigned long one, - unsigned long mask); -unsigned long netdev_fix_features(unsigned long features, const char *name); +u32 netdev_increment_features(u32 all, u32 one, u32 mask); +u32 netdev_fix_features(struct net_device *dev, u32 features); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); -int netif_skb_features(struct sk_buff *skb); +u32 netif_skb_features(struct sk_buff *skb); -static inline int net_gso_ok(int features, int gso_type) +static inline int net_gso_ok(u32 features, int gso_type) { int feature = gso_type << NETIF_F_GSO_SHIFT; return (features & feature) == feature; } -static inline int skb_gso_ok(struct sk_buff *skb, int features) +static inline int skb_gso_ok(struct sk_buff *skb, u32 features) { return net_gso_ok(features, skb_shinfo(skb)->gso_type) && (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST)); diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h index 1893837..eeec00a 100644 --- a/include/linux/netfilter.h +++ b/include/linux/netfilter.h @@ -24,16 +24,20 @@ #define NF_MAX_VERDICT NF_STOP /* we overload the higher bits for encoding auxiliary data such as the queue - * number. Not nice, but better than additional function arguments. */ -#define NF_VERDICT_MASK 0x0000ffff -#define NF_VERDICT_BITS 16 + * number or errno values. Not nice, but better than additional function + * arguments. */ +#define NF_VERDICT_MASK 0x000000ff + +/* extra verdict flags have mask 0x0000ff00 */ +#define NF_VERDICT_FLAG_QUEUE_BYPASS 0x00008000 +/* queue number (NF_QUEUE) or errno (NF_DROP) */ #define NF_VERDICT_QMASK 0xffff0000 #define NF_VERDICT_QBITS 16 -#define NF_QUEUE_NR(x) ((((x) << NF_VERDICT_BITS) & NF_VERDICT_QMASK) | NF_QUEUE) +#define NF_QUEUE_NR(x) ((((x) << 16) & NF_VERDICT_QMASK) | NF_QUEUE) -#define NF_DROP_ERR(x) (((-x) << NF_VERDICT_BITS) | NF_DROP) +#define NF_DROP_ERR(x) (((-x) << 16) | NF_DROP) /* only for userspace compatibility */ #ifndef __KERNEL__ @@ -41,6 +45,9 @@ <= 0x2000 is used for protocol-flags. */ #define NFC_UNKNOWN 0x4000 #define NFC_ALTERED 0x8000 + +/* NF_VERDICT_BITS should be 8 now, but userspace might break if this changes */ +#define NF_VERDICT_BITS 16 #endif enum nf_inet_hooks { @@ -72,6 +79,10 @@ union nf_inet_addr { #ifdef __KERNEL__ #ifdef CONFIG_NETFILTER +static inline int NF_DROP_GETERR(int verdict) +{ + return -(verdict >> NF_VERDICT_QBITS); +} static inline int nf_inet_addr_cmp(const union nf_inet_addr *a1, const union nf_inet_addr *a2) @@ -267,7 +278,7 @@ struct nf_afinfo { int route_key_size; }; -extern const struct nf_afinfo *nf_afinfo[NFPROTO_NUMPROTO]; +extern const struct nf_afinfo __rcu *nf_afinfo[NFPROTO_NUMPROTO]; static inline const struct nf_afinfo *nf_get_afinfo(unsigned short family) { return rcu_dereference(nf_afinfo[family]); @@ -357,9 +368,9 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family) #endif /*CONFIG_NETFILTER*/ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) -extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *); +extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu; extern void nf_ct_attach(struct sk_buff *, struct sk_buff *); -extern void (*nf_ct_destroy)(struct nf_conntrack *); +extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu; #else static inline void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) {} #endif diff --git a/include/linux/netfilter/Kbuild b/include/linux/netfilter/Kbuild index 9d40eff..89c0d1e 100644 --- a/include/linux/netfilter/Kbuild +++ b/include/linux/netfilter/Kbuild @@ -9,6 +9,7 @@ header-y += nfnetlink_conntrack.h header-y += nfnetlink_log.h header-y += nfnetlink_queue.h header-y += x_tables.h +header-y += xt_AUDIT.h header-y += xt_CHECKSUM.h header-y += xt_CLASSIFY.h header-y += xt_CONNMARK.h @@ -55,6 +56,7 @@ header-y += xt_rateest.h header-y += xt_realm.h header-y += xt_recent.h header-y += xt_sctp.h +header-y += xt_socket.h header-y += xt_state.h header-y += xt_statistic.h header-y += xt_string.h diff --git a/include/linux/netfilter/nf_conntrack_snmp.h b/include/linux/netfilter/nf_conntrack_snmp.h new file mode 100644 index 0000000..064bc63 --- /dev/null +++ b/include/linux/netfilter/nf_conntrack_snmp.h @@ -0,0 +1,9 @@ +#ifndef _NF_CONNTRACK_SNMP_H +#define _NF_CONNTRACK_SNMP_H + +extern int (*nf_nat_snmp_hook)(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo); + +#endif /* _NF_CONNTRACK_SNMP_H */ diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h index 19711e3..debf1ae 100644 --- a/include/linux/netfilter/nfnetlink_conntrack.h +++ b/include/linux/netfilter/nfnetlink_conntrack.h @@ -42,6 +42,7 @@ enum ctattr_type { CTA_SECMARK, /* obsolete */ CTA_ZONE, CTA_SECCTX, + CTA_TIMESTAMP, __CTA_MAX }; #define CTA_MAX (__CTA_MAX - 1) @@ -127,6 +128,14 @@ enum ctattr_counters { }; #define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1) +enum ctattr_tstamp { + CTA_TIMESTAMP_UNSPEC, + CTA_TIMESTAMP_START, + CTA_TIMESTAMP_STOP, + __CTA_TIMESTAMP_MAX +}; +#define CTA_TIMESTAMP_MAX (__CTA_TIMESTAMP_MAX - 1) + enum ctattr_nat { CTA_NAT_UNSPEC, CTA_NAT_MINIP, diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h index 6712e71..3721952 100644 --- a/include/linux/netfilter/x_tables.h +++ b/include/linux/netfilter/x_tables.h @@ -611,8 +611,9 @@ struct _compat_xt_align { extern void xt_compat_lock(u_int8_t af); extern void xt_compat_unlock(u_int8_t af); -extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta); +extern int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta); extern void xt_compat_flush_offsets(u_int8_t af); +extern void xt_compat_init_offsets(u_int8_t af, unsigned int number); extern int xt_compat_calc_jump(u_int8_t af, unsigned int offset); extern int xt_compat_match_offset(const struct xt_match *match); diff --git a/include/linux/netfilter/xt_AUDIT.h b/include/linux/netfilter/xt_AUDIT.h new file mode 100644 index 0000000..38751d2 --- /dev/null +++ b/include/linux/netfilter/xt_AUDIT.h @@ -0,0 +1,30 @@ +/* + * Header file for iptables xt_AUDIT target + * + * (C) 2010-2011 Thomas Graf <tgraf@redhat.com> + * (C) 2010-2011 Red Hat, 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. + */ + +#ifndef _XT_AUDIT_TARGET_H +#define _XT_AUDIT_TARGET_H + +#include <linux/types.h> + +enum { + XT_AUDIT_TYPE_ACCEPT = 0, + XT_AUDIT_TYPE_DROP, + XT_AUDIT_TYPE_REJECT, + __XT_AUDIT_TYPE_MAX, +}; + +#define XT_AUDIT_TYPE_MAX (__XT_AUDIT_TYPE_MAX - 1) + +struct xt_audit_info { + __u8 type; /* XT_AUDIT_TYPE_* */ +}; + +#endif /* _XT_AUDIT_TARGET_H */ diff --git a/include/linux/netfilter/xt_CT.h b/include/linux/netfilter/xt_CT.h index 1b56410..b56e768 100644 --- a/include/linux/netfilter/xt_CT.h +++ b/include/linux/netfilter/xt_CT.h @@ -1,14 +1,16 @@ #ifndef _XT_CT_H #define _XT_CT_H +#include <linux/types.h> + #define XT_CT_NOTRACK 0x1 struct xt_ct_target_info { - u_int16_t flags; - u_int16_t zone; - u_int32_t ct_events; - u_int32_t exp_events; - char helper[16]; + __u16 flags; + __u16 zone; + __u32 ct_events; + __u32 exp_events; + char helper[16]; /* Used internally by the kernel */ struct nf_conn *ct __attribute__((aligned(8))); diff --git a/include/linux/netfilter/xt_NFQUEUE.h b/include/linux/netfilter/xt_NFQUEUE.h index 2584f4a..9eafdbb 100644 --- a/include/linux/netfilter/xt_NFQUEUE.h +++ b/include/linux/netfilter/xt_NFQUEUE.h @@ -20,4 +20,10 @@ struct xt_NFQ_info_v1 { __u16 queues_total; }; +struct xt_NFQ_info_v2 { + __u16 queuenum; + __u16 queues_total; + __u16 bypass; +}; + #endif /* _XT_NFQ_TARGET_H */ diff --git a/include/linux/netfilter/xt_TCPOPTSTRIP.h b/include/linux/netfilter/xt_TCPOPTSTRIP.h index 2db5432..7157318 100644 --- a/include/linux/netfilter/xt_TCPOPTSTRIP.h +++ b/include/linux/netfilter/xt_TCPOPTSTRIP.h @@ -1,13 +1,15 @@ #ifndef _XT_TCPOPTSTRIP_H #define _XT_TCPOPTSTRIP_H +#include <linux/types.h> + #define tcpoptstrip_set_bit(bmap, idx) \ (bmap[(idx) >> 5] |= 1U << (idx & 31)) #define tcpoptstrip_test_bit(bmap, idx) \ (((1U << (idx & 31)) & bmap[(idx) >> 5]) != 0) struct xt_tcpoptstrip_target_info { - u_int32_t strip_bmap[8]; + __u32 strip_bmap[8]; }; #endif /* _XT_TCPOPTSTRIP_H */ diff --git a/include/linux/netfilter/xt_TPROXY.h b/include/linux/netfilter/xt_TPROXY.h index 3f3d693..902043c 100644 --- a/include/linux/netfilter/xt_TPROXY.h +++ b/include/linux/netfilter/xt_TPROXY.h @@ -1,19 +1,21 @@ #ifndef _XT_TPROXY_H #define _XT_TPROXY_H +#include <linux/types.h> + /* TPROXY target is capable of marking the packet to perform * redirection. We can get rid of that whenever we get support for * mutliple targets in the same rule. */ struct xt_tproxy_target_info { - u_int32_t mark_mask; - u_int32_t mark_value; + __u32 mark_mask; + __u32 mark_value; __be32 laddr; __be16 lport; }; struct xt_tproxy_target_info_v1 { - u_int32_t mark_mask; - u_int32_t mark_value; + __u32 mark_mask; + __u32 mark_value; union nf_inet_addr laddr; __be16 lport; }; diff --git a/include/linux/netfilter/xt_cluster.h b/include/linux/netfilter/xt_cluster.h index 8866826..9b883c8 100644 --- a/include/linux/netfilter/xt_cluster.h +++ b/include/linux/netfilter/xt_cluster.h @@ -1,15 +1,17 @@ #ifndef _XT_CLUSTER_MATCH_H #define _XT_CLUSTER_MATCH_H +#include <linux/types.h> + enum xt_cluster_flags { XT_CLUSTER_F_INV = (1 << 0) }; struct xt_cluster_match_info { - u_int32_t total_nodes; - u_int32_t node_mask; - u_int32_t hash_seed; - u_int32_t flags; + __u32 total_nodes; + __u32 node_mask; + __u32 hash_seed; + __u32 flags; }; #define XT_CLUSTER_NODES_MAX 32 diff --git a/include/linux/netfilter/xt_comment.h b/include/linux/netfilter/xt_comment.h index eacfedc..0ea5e79 100644 --- a/include/linux/netfilter/xt_comment.h +++ b/include/linux/netfilter/xt_comment.h @@ -4,7 +4,7 @@ #define XT_MAX_COMMENT_LEN 256 struct xt_comment_info { - unsigned char comment[XT_MAX_COMMENT_LEN]; + char comment[XT_MAX_COMMENT_LEN]; }; #endif /* XT_COMMENT_H */ diff --git a/include/linux/netfilter/xt_connlimit.h b/include/linux/netfilter/xt_connlimit.h index 7e3284b..0ca66e9 100644 --- a/include/linux/netfilter/xt_connlimit.h +++ b/include/linux/netfilter/xt_connlimit.h @@ -1,8 +1,15 @@ #ifndef _XT_CONNLIMIT_H #define _XT_CONNLIMIT_H +#include <linux/types.h> + struct xt_connlimit_data; +enum { + XT_CONNLIMIT_INVERT = 1 << 0, + XT_CONNLIMIT_DADDR = 1 << 1, +}; + struct xt_connlimit_info { union { union nf_inet_addr mask; @@ -13,7 +20,14 @@ struct xt_connlimit_info { }; #endif }; - unsigned int limit, inverse; + unsigned int limit; + union { + /* revision 0 */ + unsigned int inverse; + + /* revision 1 */ + __u32 flags; + }; /* Used internally by the kernel */ struct xt_connlimit_data *data __attribute__((aligned(8))); diff --git a/include/linux/netfilter/xt_conntrack.h b/include/linux/netfilter/xt_conntrack.h index 54f47a2..74b904d 100644 --- a/include/linux/netfilter/xt_conntrack.h +++ b/include/linux/netfilter/xt_conntrack.h @@ -58,4 +58,19 @@ struct xt_conntrack_mtinfo2 { __u16 state_mask, status_mask; }; +struct xt_conntrack_mtinfo3 { + union nf_inet_addr origsrc_addr, origsrc_mask; + union nf_inet_addr origdst_addr, origdst_mask; + union nf_inet_addr replsrc_addr, replsrc_mask; + union nf_inet_addr repldst_addr, repldst_mask; + __u32 expires_min, expires_max; + __u16 l4proto; + __u16 origsrc_port, origdst_port; + __u16 replsrc_port, repldst_port; + __u16 match_flags, invert_flags; + __u16 state_mask, status_mask; + __u16 origsrc_port_high, origdst_port_high; + __u16 replsrc_port_high, repldst_port_high; +}; + #endif /*_XT_CONNTRACK_H*/ diff --git a/include/linux/netfilter/xt_quota.h b/include/linux/netfilter/xt_quota.h index b0d28c6..ca6e03e 100644 --- a/include/linux/netfilter/xt_quota.h +++ b/include/linux/netfilter/xt_quota.h @@ -1,6 +1,8 @@ #ifndef _XT_QUOTA_H #define _XT_QUOTA_H +#include <linux/types.h> + enum xt_quota_flags { XT_QUOTA_INVERT = 0x1, }; @@ -9,9 +11,9 @@ enum xt_quota_flags { struct xt_quota_priv; struct xt_quota_info { - u_int32_t flags; - u_int32_t pad; - aligned_u64 quota; + __u32 flags; + __u32 pad; + aligned_u64 quota; /* Used internally by the kernel */ struct xt_quota_priv *master; diff --git a/include/linux/netfilter/xt_socket.h b/include/linux/netfilter/xt_socket.h index 6f475b8..26d7217 100644 --- a/include/linux/netfilter/xt_socket.h +++ b/include/linux/netfilter/xt_socket.h @@ -1,6 +1,8 @@ #ifndef _XT_SOCKET_H #define _XT_SOCKET_H +#include <linux/types.h> + enum { XT_SOCKET_TRANSPARENT = 1 << 0, }; diff --git a/include/linux/netfilter/xt_time.h b/include/linux/netfilter/xt_time.h index 14b6df4..7c37fac 100644 --- a/include/linux/netfilter/xt_time.h +++ b/include/linux/netfilter/xt_time.h @@ -1,14 +1,16 @@ #ifndef _XT_TIME_H #define _XT_TIME_H 1 +#include <linux/types.h> + struct xt_time_info { - u_int32_t date_start; - u_int32_t date_stop; - u_int32_t daytime_start; - u_int32_t daytime_stop; - u_int32_t monthdays_match; - u_int8_t weekdays_match; - u_int8_t flags; + __u32 date_start; + __u32 date_stop; + __u32 daytime_start; + __u32 daytime_stop; + __u32 monthdays_match; + __u8 weekdays_match; + __u8 flags; }; enum { diff --git a/include/linux/netfilter/xt_u32.h b/include/linux/netfilter/xt_u32.h index 9947f56..04d1bfe 100644 --- a/include/linux/netfilter/xt_u32.h +++ b/include/linux/netfilter/xt_u32.h @@ -1,6 +1,8 @@ #ifndef _XT_U32_H #define _XT_U32_H 1 +#include <linux/types.h> + enum xt_u32_ops { XT_U32_AND, XT_U32_LEFTSH, @@ -9,13 +11,13 @@ enum xt_u32_ops { }; struct xt_u32_location_element { - u_int32_t number; - u_int8_t nextop; + __u32 number; + __u8 nextop; }; struct xt_u32_value_element { - u_int32_t min; - u_int32_t max; + __u32 min; + __u32 max; }; /* @@ -27,14 +29,14 @@ struct xt_u32_value_element { struct xt_u32_test { struct xt_u32_location_element location[XT_U32_MAXSIZE+1]; struct xt_u32_value_element value[XT_U32_MAXSIZE+1]; - u_int8_t nnums; - u_int8_t nvalues; + __u8 nnums; + __u8 nvalues; }; struct xt_u32 { struct xt_u32_test tests[XT_U32_MAXSIZE+1]; - u_int8_t ntests; - u_int8_t invert; + __u8 ntests; + __u8 invert; }; #endif /* _XT_U32_H */ diff --git a/include/linux/netfilter_bridge/ebt_802_3.h b/include/linux/netfilter_bridge/ebt_802_3.h index c73ef0b..be5be15 100644 --- a/include/linux/netfilter_bridge/ebt_802_3.h +++ b/include/linux/netfilter_bridge/ebt_802_3.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_802_3_H #define __LINUX_BRIDGE_EBT_802_3_H +#include <linux/types.h> + #define EBT_802_3_SAP 0x01 #define EBT_802_3_TYPE 0x02 @@ -24,24 +26,24 @@ /* ui has one byte ctrl, ni has two */ struct hdr_ui { - uint8_t dsap; - uint8_t ssap; - uint8_t ctrl; - uint8_t orig[3]; + __u8 dsap; + __u8 ssap; + __u8 ctrl; + __u8 orig[3]; __be16 type; }; struct hdr_ni { - uint8_t dsap; - uint8_t ssap; + __u8 dsap; + __u8 ssap; __be16 ctrl; - uint8_t orig[3]; + __u8 orig[3]; __be16 type; }; struct ebt_802_3_hdr { - uint8_t daddr[6]; - uint8_t saddr[6]; + __u8 daddr[6]; + __u8 saddr[6]; __be16 len; union { struct hdr_ui ui; @@ -59,10 +61,10 @@ static inline struct ebt_802_3_hdr *ebt_802_3_hdr(const struct sk_buff *skb) #endif struct ebt_802_3_info { - uint8_t sap; + __u8 sap; __be16 type; - uint8_t bitmask; - uint8_t invflags; + __u8 bitmask; + __u8 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_among.h b/include/linux/netfilter_bridge/ebt_among.h index 0009558..bd4e3ad 100644 --- a/include/linux/netfilter_bridge/ebt_among.h +++ b/include/linux/netfilter_bridge/ebt_among.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_AMONG_H #define __LINUX_BRIDGE_EBT_AMONG_H +#include <linux/types.h> + #define EBT_AMONG_DST 0x01 #define EBT_AMONG_SRC 0x02 @@ -30,7 +32,7 @@ */ struct ebt_mac_wormhash_tuple { - uint32_t cmp[2]; + __u32 cmp[2]; __be32 ip; }; diff --git a/include/linux/netfilter_bridge/ebt_arp.h b/include/linux/netfilter_bridge/ebt_arp.h index cbf4843..522f3e4 100644 --- a/include/linux/netfilter_bridge/ebt_arp.h +++ b/include/linux/netfilter_bridge/ebt_arp.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_ARP_H #define __LINUX_BRIDGE_EBT_ARP_H +#include <linux/types.h> + #define EBT_ARP_OPCODE 0x01 #define EBT_ARP_HTYPE 0x02 #define EBT_ARP_PTYPE 0x04 @@ -27,8 +29,8 @@ struct ebt_arp_info unsigned char smmsk[ETH_ALEN]; unsigned char dmaddr[ETH_ALEN]; unsigned char dmmsk[ETH_ALEN]; - uint8_t bitmask; - uint8_t invflags; + __u8 bitmask; + __u8 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ip.h b/include/linux/netfilter_bridge/ebt_ip.h index 6a708fb..c4bbc41 100644 --- a/include/linux/netfilter_bridge/ebt_ip.h +++ b/include/linux/netfilter_bridge/ebt_ip.h @@ -15,6 +15,8 @@ #ifndef __LINUX_BRIDGE_EBT_IP_H #define __LINUX_BRIDGE_EBT_IP_H +#include <linux/types.h> + #define EBT_IP_SOURCE 0x01 #define EBT_IP_DEST 0x02 #define EBT_IP_TOS 0x04 @@ -31,12 +33,12 @@ struct ebt_ip_info { __be32 daddr; __be32 smsk; __be32 dmsk; - uint8_t tos; - uint8_t protocol; - uint8_t bitmask; - uint8_t invflags; - uint16_t sport[2]; - uint16_t dport[2]; + __u8 tos; + __u8 protocol; + __u8 bitmask; + __u8 invflags; + __u16 sport[2]; + __u16 dport[2]; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ip6.h b/include/linux/netfilter_bridge/ebt_ip6.h index e5de987..42b8896 100644 --- a/include/linux/netfilter_bridge/ebt_ip6.h +++ b/include/linux/netfilter_bridge/ebt_ip6.h @@ -12,14 +12,19 @@ #ifndef __LINUX_BRIDGE_EBT_IP6_H #define __LINUX_BRIDGE_EBT_IP6_H +#include <linux/types.h> + #define EBT_IP6_SOURCE 0x01 #define EBT_IP6_DEST 0x02 #define EBT_IP6_TCLASS 0x04 #define EBT_IP6_PROTO 0x08 #define EBT_IP6_SPORT 0x10 #define EBT_IP6_DPORT 0x20 +#define EBT_IP6_ICMP6 0x40 + #define EBT_IP6_MASK (EBT_IP6_SOURCE | EBT_IP6_DEST | EBT_IP6_TCLASS |\ - EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT) + EBT_IP6_PROTO | EBT_IP6_SPORT | EBT_IP6_DPORT | \ + EBT_IP6_ICMP6) #define EBT_IP6_MATCH "ip6" /* the same values are used for the invflags */ @@ -28,12 +33,18 @@ struct ebt_ip6_info { struct in6_addr daddr; struct in6_addr smsk; struct in6_addr dmsk; - uint8_t tclass; - uint8_t protocol; - uint8_t bitmask; - uint8_t invflags; - uint16_t sport[2]; - uint16_t dport[2]; + __u8 tclass; + __u8 protocol; + __u8 bitmask; + __u8 invflags; + union { + __u16 sport[2]; + __u8 icmpv6_type[2]; + }; + union { + __u16 dport[2]; + __u8 icmpv6_code[2]; + }; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_limit.h b/include/linux/netfilter_bridge/ebt_limit.h index 4bf76b7..66d80b3 100644 --- a/include/linux/netfilter_bridge/ebt_limit.h +++ b/include/linux/netfilter_bridge/ebt_limit.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_LIMIT_H #define __LINUX_BRIDGE_EBT_LIMIT_H +#include <linux/types.h> + #define EBT_LIMIT_MATCH "limit" /* timings are in milliseconds. */ @@ -10,13 +12,13 @@ seconds, or one every 59 hours. */ struct ebt_limit_info { - u_int32_t avg; /* Average secs between packets * scale */ - u_int32_t burst; /* Period multiplier for upper limit. */ + __u32 avg; /* Average secs between packets * scale */ + __u32 burst; /* Period multiplier for upper limit. */ /* Used internally by the kernel */ unsigned long prev; - u_int32_t credit; - u_int32_t credit_cap, cost; + __u32 credit; + __u32 credit_cap, cost; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_log.h b/include/linux/netfilter_bridge/ebt_log.h index cc2cdfb..7e7f1d1 100644 --- a/include/linux/netfilter_bridge/ebt_log.h +++ b/include/linux/netfilter_bridge/ebt_log.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_LOG_H #define __LINUX_BRIDGE_EBT_LOG_H +#include <linux/types.h> + #define EBT_LOG_IP 0x01 /* if the frame is made by ip, log the ip information */ #define EBT_LOG_ARP 0x02 #define EBT_LOG_NFLOG 0x04 @@ -10,9 +12,9 @@ #define EBT_LOG_WATCHER "log" struct ebt_log_info { - uint8_t loglevel; - uint8_t prefix[EBT_LOG_PREFIX_SIZE]; - uint32_t bitmask; + __u8 loglevel; + __u8 prefix[EBT_LOG_PREFIX_SIZE]; + __u32 bitmask; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_mark_m.h b/include/linux/netfilter_bridge/ebt_mark_m.h index 9ceb10e..410f9e5 100644 --- a/include/linux/netfilter_bridge/ebt_mark_m.h +++ b/include/linux/netfilter_bridge/ebt_mark_m.h @@ -1,13 +1,15 @@ #ifndef __LINUX_BRIDGE_EBT_MARK_M_H #define __LINUX_BRIDGE_EBT_MARK_M_H +#include <linux/types.h> + #define EBT_MARK_AND 0x01 #define EBT_MARK_OR 0x02 #define EBT_MARK_MASK (EBT_MARK_AND | EBT_MARK_OR) struct ebt_mark_m_info { unsigned long mark, mask; - uint8_t invert; - uint8_t bitmask; + __u8 invert; + __u8 bitmask; }; #define EBT_MARK_MATCH "mark_m" diff --git a/include/linux/netfilter_bridge/ebt_nflog.h b/include/linux/netfilter_bridge/ebt_nflog.h index 0528178..df829fc 100644 --- a/include/linux/netfilter_bridge/ebt_nflog.h +++ b/include/linux/netfilter_bridge/ebt_nflog.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_NFLOG_H #define __LINUX_BRIDGE_EBT_NFLOG_H +#include <linux/types.h> + #define EBT_NFLOG_MASK 0x0 #define EBT_NFLOG_PREFIX_SIZE 64 @@ -10,11 +12,11 @@ #define EBT_NFLOG_DEFAULT_THRESHOLD 1 struct ebt_nflog_info { - u_int32_t len; - u_int16_t group; - u_int16_t threshold; - u_int16_t flags; - u_int16_t pad; + __u32 len; + __u16 group; + __u16 threshold; + __u16 flags; + __u16 pad; char prefix[EBT_NFLOG_PREFIX_SIZE]; }; diff --git a/include/linux/netfilter_bridge/ebt_pkttype.h b/include/linux/netfilter_bridge/ebt_pkttype.h index 51a7998..c241bad 100644 --- a/include/linux/netfilter_bridge/ebt_pkttype.h +++ b/include/linux/netfilter_bridge/ebt_pkttype.h @@ -1,9 +1,11 @@ #ifndef __LINUX_BRIDGE_EBT_PKTTYPE_H #define __LINUX_BRIDGE_EBT_PKTTYPE_H +#include <linux/types.h> + struct ebt_pkttype_info { - uint8_t pkt_type; - uint8_t invert; + __u8 pkt_type; + __u8 invert; }; #define EBT_PKTTYPE_MATCH "pkttype" diff --git a/include/linux/netfilter_bridge/ebt_stp.h b/include/linux/netfilter_bridge/ebt_stp.h index e503a0a..1025b9f 100644 --- a/include/linux/netfilter_bridge/ebt_stp.h +++ b/include/linux/netfilter_bridge/ebt_stp.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_STP_H #define __LINUX_BRIDGE_EBT_STP_H +#include <linux/types.h> + #define EBT_STP_TYPE 0x0001 #define EBT_STP_FLAGS 0x0002 @@ -21,24 +23,24 @@ #define EBT_STP_MATCH "stp" struct ebt_stp_config_info { - uint8_t flags; - uint16_t root_priol, root_priou; + __u8 flags; + __u16 root_priol, root_priou; char root_addr[6], root_addrmsk[6]; - uint32_t root_costl, root_costu; - uint16_t sender_priol, sender_priou; + __u32 root_costl, root_costu; + __u16 sender_priol, sender_priou; char sender_addr[6], sender_addrmsk[6]; - uint16_t portl, portu; - uint16_t msg_agel, msg_ageu; - uint16_t max_agel, max_ageu; - uint16_t hello_timel, hello_timeu; - uint16_t forward_delayl, forward_delayu; + __u16 portl, portu; + __u16 msg_agel, msg_ageu; + __u16 max_agel, max_ageu; + __u16 hello_timel, hello_timeu; + __u16 forward_delayl, forward_delayu; }; struct ebt_stp_info { - uint8_t type; + __u8 type; struct ebt_stp_config_info config; - uint16_t bitmask; - uint16_t invflags; + __u16 bitmask; + __u16 invflags; }; #endif diff --git a/include/linux/netfilter_bridge/ebt_ulog.h b/include/linux/netfilter_bridge/ebt_ulog.h index b677e26..89a6bec 100644 --- a/include/linux/netfilter_bridge/ebt_ulog.h +++ b/include/linux/netfilter_bridge/ebt_ulog.h @@ -1,6 +1,8 @@ #ifndef _EBT_ULOG_H #define _EBT_ULOG_H +#include <linux/types.h> + #define EBT_ULOG_DEFAULT_NLGROUP 0 #define EBT_ULOG_DEFAULT_QTHRESHOLD 1 #define EBT_ULOG_MAXNLGROUPS 32 /* hardcoded netlink max */ @@ -10,7 +12,7 @@ #define EBT_ULOG_VERSION 1 struct ebt_ulog_info { - uint32_t nlgroup; + __u32 nlgroup; unsigned int cprange; unsigned int qthreshold; char prefix[EBT_ULOG_PREFIX_LEN]; diff --git a/include/linux/netfilter_bridge/ebt_vlan.h b/include/linux/netfilter_bridge/ebt_vlan.h index 1d98be4..967d1d5 100644 --- a/include/linux/netfilter_bridge/ebt_vlan.h +++ b/include/linux/netfilter_bridge/ebt_vlan.h @@ -1,6 +1,8 @@ #ifndef __LINUX_BRIDGE_EBT_VLAN_H #define __LINUX_BRIDGE_EBT_VLAN_H +#include <linux/types.h> + #define EBT_VLAN_ID 0x01 #define EBT_VLAN_PRIO 0x02 #define EBT_VLAN_ENCAP 0x04 @@ -8,12 +10,12 @@ #define EBT_VLAN_MATCH "vlan" struct ebt_vlan_info { - uint16_t id; /* VLAN ID {1-4095} */ - uint8_t prio; /* VLAN User Priority {0-7} */ + __u16 id; /* VLAN ID {1-4095} */ + __u8 prio; /* VLAN User Priority {0-7} */ __be16 encap; /* VLAN Encapsulated frame code {0-65535} */ - uint8_t bitmask; /* Args bitmask bit 1=1 - ID arg, + __u8 bitmask; /* Args bitmask bit 1=1 - ID arg, bit 2=1 User-Priority arg, bit 3=1 encap*/ - uint8_t invflags; /* Inverse bitmask bit 1=1 - inversed ID arg, + __u8 invflags; /* Inverse bitmask bit 1=1 - inversed ID arg, bit 2=1 - inversed Pirority arg */ }; diff --git a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h index e5a3687..c6a204c 100644 --- a/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h +++ b/include/linux/netfilter_ipv4/ipt_CLUSTERIP.h @@ -1,6 +1,8 @@ #ifndef _IPT_CLUSTERIP_H_target #define _IPT_CLUSTERIP_H_target +#include <linux/types.h> + enum clusterip_hashmode { CLUSTERIP_HASHMODE_SIP = 0, CLUSTERIP_HASHMODE_SIP_SPT, @@ -17,15 +19,15 @@ struct clusterip_config; struct ipt_clusterip_tgt_info { - u_int32_t flags; + __u32 flags; /* only relevant for new ones */ - u_int8_t clustermac[6]; - u_int16_t num_total_nodes; - u_int16_t num_local_nodes; - u_int16_t local_nodes[CLUSTERIP_MAX_NODES]; - u_int32_t hash_mode; - u_int32_t hash_initval; + __u8 clustermac[6]; + __u16 num_total_nodes; + __u16 num_local_nodes; + __u16 local_nodes[CLUSTERIP_MAX_NODES]; + __u32 hash_mode; + __u32 hash_initval; /* Used internally by the kernel */ struct clusterip_config *config; diff --git a/include/linux/netfilter_ipv4/ipt_ECN.h b/include/linux/netfilter_ipv4/ipt_ECN.h index 7ca4591..bb88d53 100644 --- a/include/linux/netfilter_ipv4/ipt_ECN.h +++ b/include/linux/netfilter_ipv4/ipt_ECN.h @@ -8,6 +8,8 @@ */ #ifndef _IPT_ECN_TARGET_H #define _IPT_ECN_TARGET_H + +#include <linux/types.h> #include <linux/netfilter/xt_DSCP.h> #define IPT_ECN_IP_MASK (~XT_DSCP_MASK) @@ -19,11 +21,11 @@ #define IPT_ECN_OP_MASK 0xce struct ipt_ECN_info { - u_int8_t operation; /* bitset of operations */ - u_int8_t ip_ect; /* ECT codepoint of IPv4 header, pre-shifted */ + __u8 operation; /* bitset of operations */ + __u8 ip_ect; /* ECT codepoint of IPv4 header, pre-shifted */ union { struct { - u_int8_t ece:1, cwr:1; /* TCP ECT bits */ + __u8 ece:1, cwr:1; /* TCP ECT bits */ } tcp; } proto; }; diff --git a/include/linux/netfilter_ipv4/ipt_SAME.h b/include/linux/netfilter_ipv4/ipt_SAME.h index 2529660..5bca782 100644 --- a/include/linux/netfilter_ipv4/ipt_SAME.h +++ b/include/linux/netfilter_ipv4/ipt_SAME.h @@ -1,15 +1,17 @@ #ifndef _IPT_SAME_H #define _IPT_SAME_H +#include <linux/types.h> + #define IPT_SAME_MAX_RANGE 10 #define IPT_SAME_NODST 0x01 struct ipt_same_info { unsigned char info; - u_int32_t rangesize; - u_int32_t ipnum; - u_int32_t *iparray; + __u32 rangesize; + __u32 ipnum; + __u32 *iparray; /* hangs off end. */ struct nf_nat_range range[IPT_SAME_MAX_RANGE]; diff --git a/include/linux/netfilter_ipv4/ipt_TTL.h b/include/linux/netfilter_ipv4/ipt_TTL.h index ee6611e..f6ac169 100644 --- a/include/linux/netfilter_ipv4/ipt_TTL.h +++ b/include/linux/netfilter_ipv4/ipt_TTL.h @@ -4,6 +4,8 @@ #ifndef _IPT_TTL_H #define _IPT_TTL_H +#include <linux/types.h> + enum { IPT_TTL_SET = 0, IPT_TTL_INC, @@ -13,8 +15,8 @@ enum { #define IPT_TTL_MAXMODE IPT_TTL_DEC struct ipt_TTL_info { - u_int8_t mode; - u_int8_t ttl; + __u8 mode; + __u8 ttl; }; diff --git a/include/linux/netfilter_ipv4/ipt_addrtype.h b/include/linux/netfilter_ipv4/ipt_addrtype.h index 446de6a..0da4223 100644 --- a/include/linux/netfilter_ipv4/ipt_addrtype.h +++ b/include/linux/netfilter_ipv4/ipt_addrtype.h @@ -1,6 +1,8 @@ #ifndef _IPT_ADDRTYPE_H #define _IPT_ADDRTYPE_H +#include <linux/types.h> + enum { IPT_ADDRTYPE_INVERT_SOURCE = 0x0001, IPT_ADDRTYPE_INVERT_DEST = 0x0002, @@ -9,17 +11,17 @@ enum { }; struct ipt_addrtype_info_v1 { - u_int16_t source; /* source-type mask */ - u_int16_t dest; /* dest-type mask */ - u_int32_t flags; + __u16 source; /* source-type mask */ + __u16 dest; /* dest-type mask */ + __u32 flags; }; /* revision 0 */ struct ipt_addrtype_info { - u_int16_t source; /* source-type mask */ - u_int16_t dest; /* dest-type mask */ - u_int32_t invert_source; - u_int32_t invert_dest; + __u16 source; /* source-type mask */ + __u16 dest; /* dest-type mask */ + __u32 invert_source; + __u32 invert_dest; }; #endif diff --git a/include/linux/netfilter_ipv4/ipt_ah.h b/include/linux/netfilter_ipv4/ipt_ah.h index 2e555b4..4e02bb0 100644 --- a/include/linux/netfilter_ipv4/ipt_ah.h +++ b/include/linux/netfilter_ipv4/ipt_ah.h @@ -1,9 +1,11 @@ #ifndef _IPT_AH_H #define _IPT_AH_H +#include <linux/types.h> + struct ipt_ah { - u_int32_t spis[2]; /* Security Parameter Index */ - u_int8_t invflags; /* Inverse flags */ + __u32 spis[2]; /* Security Parameter Index */ + __u8 invflags; /* Inverse flags */ }; diff --git a/include/linux/netfilter_ipv4/ipt_ecn.h b/include/linux/netfilter_ipv4/ipt_ecn.h index 9945baa..eabf95f 100644 --- a/include/linux/netfilter_ipv4/ipt_ecn.h +++ b/include/linux/netfilter_ipv4/ipt_ecn.h @@ -8,6 +8,8 @@ */ #ifndef _IPT_ECN_H #define _IPT_ECN_H + +#include <linux/types.h> #include <linux/netfilter/xt_dscp.h> #define IPT_ECN_IP_MASK (~XT_DSCP_MASK) @@ -20,12 +22,12 @@ /* match info */ struct ipt_ecn_info { - u_int8_t operation; - u_int8_t invert; - u_int8_t ip_ect; + __u8 operation; + __u8 invert; + __u8 ip_ect; union { struct { - u_int8_t ect; + __u8 ect; } tcp; } proto; }; diff --git a/include/linux/netfilter_ipv4/ipt_ttl.h b/include/linux/netfilter_ipv4/ipt_ttl.h index ee24fd8..37bee44 100644 --- a/include/linux/netfilter_ipv4/ipt_ttl.h +++ b/include/linux/netfilter_ipv4/ipt_ttl.h @@ -4,6 +4,8 @@ #ifndef _IPT_TTL_H #define _IPT_TTL_H +#include <linux/types.h> + enum { IPT_TTL_EQ = 0, /* equals */ IPT_TTL_NE, /* not equals */ @@ -13,8 +15,8 @@ enum { struct ipt_ttl_info { - u_int8_t mode; - u_int8_t ttl; + __u8 mode; + __u8 ttl; }; diff --git a/include/linux/netfilter_ipv6/ip6t_HL.h b/include/linux/netfilter_ipv6/ip6t_HL.h index afb7813..ebd8ead 100644 --- a/include/linux/netfilter_ipv6/ip6t_HL.h +++ b/include/linux/netfilter_ipv6/ip6t_HL.h @@ -5,6 +5,8 @@ #ifndef _IP6T_HL_H #define _IP6T_HL_H +#include <linux/types.h> + enum { IP6T_HL_SET = 0, IP6T_HL_INC, @@ -14,8 +16,8 @@ enum { #define IP6T_HL_MAXMODE IP6T_HL_DEC struct ip6t_HL_info { - u_int8_t mode; - u_int8_t hop_limit; + __u8 mode; + __u8 hop_limit; }; diff --git a/include/linux/netfilter_ipv6/ip6t_REJECT.h b/include/linux/netfilter_ipv6/ip6t_REJECT.h index 6be6504..205ed62 100644 --- a/include/linux/netfilter_ipv6/ip6t_REJECT.h +++ b/include/linux/netfilter_ipv6/ip6t_REJECT.h @@ -1,6 +1,8 @@ #ifndef _IP6T_REJECT_H #define _IP6T_REJECT_H +#include <linux/types.h> + enum ip6t_reject_with { IP6T_ICMP6_NO_ROUTE, IP6T_ICMP6_ADM_PROHIBITED, @@ -12,7 +14,7 @@ enum ip6t_reject_with { }; struct ip6t_reject_info { - u_int32_t with; /* reject type */ + __u32 with; /* reject type */ }; #endif /*_IP6T_REJECT_H*/ diff --git a/include/linux/netfilter_ipv6/ip6t_ah.h b/include/linux/netfilter_ipv6/ip6t_ah.h index 17a745c..5da2b65 100644 --- a/include/linux/netfilter_ipv6/ip6t_ah.h +++ b/include/linux/netfilter_ipv6/ip6t_ah.h @@ -1,11 +1,13 @@ #ifndef _IP6T_AH_H #define _IP6T_AH_H +#include <linux/types.h> + struct ip6t_ah { - u_int32_t spis[2]; /* Security Parameter Index */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t hdrres; /* Test of the Reserved Filed */ - u_int8_t invflags; /* Inverse flags */ + __u32 spis[2]; /* Security Parameter Index */ + __u32 hdrlen; /* Header Length */ + __u8 hdrres; /* Test of the Reserved Filed */ + __u8 invflags; /* Inverse flags */ }; #define IP6T_AH_SPI 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_frag.h b/include/linux/netfilter_ipv6/ip6t_frag.h index 3724d08..b47f61b 100644 --- a/include/linux/netfilter_ipv6/ip6t_frag.h +++ b/include/linux/netfilter_ipv6/ip6t_frag.h @@ -1,11 +1,13 @@ #ifndef _IP6T_FRAG_H #define _IP6T_FRAG_H +#include <linux/types.h> + struct ip6t_frag { - u_int32_t ids[2]; /* Security Parameter Index */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ + __u32 ids[2]; /* Security Parameter Index */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ }; #define IP6T_FRAG_IDS 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_hl.h b/include/linux/netfilter_ipv6/ip6t_hl.h index 5ef91b8..6e76dbc 100644 --- a/include/linux/netfilter_ipv6/ip6t_hl.h +++ b/include/linux/netfilter_ipv6/ip6t_hl.h @@ -5,6 +5,8 @@ #ifndef _IP6T_HL_H #define _IP6T_HL_H +#include <linux/types.h> + enum { IP6T_HL_EQ = 0, /* equals */ IP6T_HL_NE, /* not equals */ @@ -14,8 +16,8 @@ enum { struct ip6t_hl_info { - u_int8_t mode; - u_int8_t hop_limit; + __u8 mode; + __u8 hop_limit; }; diff --git a/include/linux/netfilter_ipv6/ip6t_ipv6header.h b/include/linux/netfilter_ipv6/ip6t_ipv6header.h index 01dfd44..efae3a2 100644 --- a/include/linux/netfilter_ipv6/ip6t_ipv6header.h +++ b/include/linux/netfilter_ipv6/ip6t_ipv6header.h @@ -8,10 +8,12 @@ on whether they contain certain headers */ #ifndef __IPV6HEADER_H #define __IPV6HEADER_H +#include <linux/types.h> + struct ip6t_ipv6header_info { - u_int8_t matchflags; - u_int8_t invflags; - u_int8_t modeflag; + __u8 matchflags; + __u8 invflags; + __u8 modeflag; }; #define MASK_HOPOPTS 128 diff --git a/include/linux/netfilter_ipv6/ip6t_mh.h b/include/linux/netfilter_ipv6/ip6t_mh.h index 18549bc..a7729a5 100644 --- a/include/linux/netfilter_ipv6/ip6t_mh.h +++ b/include/linux/netfilter_ipv6/ip6t_mh.h @@ -1,10 +1,12 @@ #ifndef _IP6T_MH_H #define _IP6T_MH_H +#include <linux/types.h> + /* MH matching stuff */ struct ip6t_mh { - u_int8_t types[2]; /* MH type range */ - u_int8_t invflags; /* Inverse flags */ + __u8 types[2]; /* MH type range */ + __u8 invflags; /* Inverse flags */ }; /* Values for "invflags" field in struct ip6t_mh. */ diff --git a/include/linux/netfilter_ipv6/ip6t_opts.h b/include/linux/netfilter_ipv6/ip6t_opts.h index 62d89bc..17d419a 100644 --- a/include/linux/netfilter_ipv6/ip6t_opts.h +++ b/include/linux/netfilter_ipv6/ip6t_opts.h @@ -1,14 +1,16 @@ #ifndef _IP6T_OPTS_H #define _IP6T_OPTS_H +#include <linux/types.h> + #define IP6T_OPTS_OPTSNR 16 struct ip6t_opts { - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ - u_int16_t opts[IP6T_OPTS_OPTSNR]; /* opts */ - u_int8_t optsnr; /* Nr of OPts */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ + __u16 opts[IP6T_OPTS_OPTSNR]; /* opts */ + __u8 optsnr; /* Nr of OPts */ }; #define IP6T_OPTS_LEN 0x01 diff --git a/include/linux/netfilter_ipv6/ip6t_rt.h b/include/linux/netfilter_ipv6/ip6t_rt.h index ab91bfd..7605a5f 100644 --- a/include/linux/netfilter_ipv6/ip6t_rt.h +++ b/include/linux/netfilter_ipv6/ip6t_rt.h @@ -1,18 +1,19 @@ #ifndef _IP6T_RT_H #define _IP6T_RT_H +#include <linux/types.h> /*#include <linux/in6.h>*/ #define IP6T_RT_HOPS 16 struct ip6t_rt { - u_int32_t rt_type; /* Routing Type */ - u_int32_t segsleft[2]; /* Segments Left */ - u_int32_t hdrlen; /* Header Length */ - u_int8_t flags; /* */ - u_int8_t invflags; /* Inverse flags */ + __u32 rt_type; /* Routing Type */ + __u32 segsleft[2]; /* Segments Left */ + __u32 hdrlen; /* Header Length */ + __u8 flags; /* */ + __u8 invflags; /* Inverse flags */ struct in6_addr addrs[IP6T_RT_HOPS]; /* Hops */ - u_int8_t addrnr; /* Nr of Addresses */ + __u8 addrnr; /* Nr of Addresses */ }; #define IP6T_RT_TYP 0x01 diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h index 2cfa4bc..776cd93 100644 --- a/include/linux/pkt_sched.h +++ b/include/linux/pkt_sched.h @@ -481,4 +481,16 @@ struct tc_drr_stats { __u32 deficit; }; +/* MQPRIO */ +#define TC_QOPT_BITMASK 15 +#define TC_QOPT_MAX_QUEUE 16 + +struct tc_mqprio_qopt { + __u8 num_tc; + __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; + __u8 hw; + __u16 count[TC_QOPT_MAX_QUEUE]; + __u16 offset[TC_QOPT_MAX_QUEUE]; +}; + #endif diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bf221d6..31f02d0 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1801,6 +1801,15 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) prefetch(skb->prev), (skb != (struct sk_buff *)(queue)); \ skb = skb->prev) +#define skb_queue_reverse_walk_safe(queue, skb, tmp) \ + for (skb = (queue)->prev, tmp = skb->prev; \ + skb != (struct sk_buff *)(queue); \ + skb = tmp, tmp = skb->prev) + +#define skb_queue_reverse_walk_from_safe(queue, skb, tmp) \ + for (tmp = skb->prev; \ + skb != (struct sk_buff *)(queue); \ + skb = tmp, tmp = skb->prev) static inline bool skb_has_frag_list(const struct sk_buff *skb) { @@ -1868,7 +1877,7 @@ extern void skb_split(struct sk_buff *skb, extern int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen); -extern struct sk_buff *skb_segment(struct sk_buff *skb, int features); +extern struct sk_buff *skb_segment(struct sk_buff *skb, u32 features); static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 1322695..679a049 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1790,8 +1790,9 @@ static inline void *wdev_priv(struct wireless_dev *wdev) /** * ieee80211_channel_to_frequency - convert channel number to frequency * @chan: channel number + * @band: band, necessary due to channel number overlap */ -extern int ieee80211_channel_to_frequency(int chan); +extern int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band); /** * ieee80211_frequency_to_channel - convert frequency to channel number diff --git a/include/net/dst.h b/include/net/dst.h index 93b0310..484f80b 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -40,24 +40,10 @@ struct dst_entry { struct rcu_head rcu_head; struct dst_entry *child; struct net_device *dev; - short error; - short obsolete; - int flags; -#define DST_HOST 0x0001 -#define DST_NOXFRM 0x0002 -#define DST_NOPOLICY 0x0004 -#define DST_NOHASH 0x0008 -#define DST_NOCACHE 0x0010 + struct dst_ops *ops; + unsigned long _metrics; unsigned long expires; - - unsigned short header_len; /* more space at head required */ - unsigned short trailer_len; /* space to reserve at tail */ - - unsigned int rate_tokens; - unsigned long rate_last; /* rate limiting for ICMP */ - struct dst_entry *path; - struct neighbour *neighbour; struct hh_cache *hh; #ifdef CONFIG_XFRM @@ -68,17 +54,16 @@ struct dst_entry { int (*input)(struct sk_buff*); int (*output)(struct sk_buff*); - struct dst_ops *ops; - - u32 _metrics[RTAX_MAX]; - -#ifdef CONFIG_NET_CLS_ROUTE + short error; + short obsolete; + unsigned short header_len; /* more space at head required */ + unsigned short trailer_len; /* space to reserve at tail */ +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 tclassid; #else __u32 __pad2; #endif - /* * Align __refcnt to a 64 bytes alignment * (L1_CACHE_SIZE would be too much) @@ -93,6 +78,14 @@ struct dst_entry { atomic_t __refcnt; /* client references */ int __use; unsigned long lastuse; + unsigned long rate_last; /* rate limiting for ICMP */ + unsigned int rate_tokens; + int flags; +#define DST_HOST 0x0001 +#define DST_NOXFRM 0x0002 +#define DST_NOPOLICY 0x0004 +#define DST_NOHASH 0x0008 +#define DST_NOCACHE 0x0010 union { struct dst_entry *next; struct rtable __rcu *rt_next; @@ -103,10 +96,70 @@ struct dst_entry { #ifdef __KERNEL__ +extern u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old); +extern const u32 dst_default_metrics[RTAX_MAX]; + +#define DST_METRICS_READ_ONLY 0x1UL +#define __DST_METRICS_PTR(Y) \ + ((u32 *)((Y) & ~DST_METRICS_READ_ONLY)) +#define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics) + +static inline bool dst_metrics_read_only(const struct dst_entry *dst) +{ + return dst->_metrics & DST_METRICS_READ_ONLY; +} + +extern void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old); + +static inline void dst_destroy_metrics_generic(struct dst_entry *dst) +{ + unsigned long val = dst->_metrics; + if (!(val & DST_METRICS_READ_ONLY)) + __dst_destroy_metrics_generic(dst, val); +} + +static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst) +{ + unsigned long p = dst->_metrics; + + if (p & DST_METRICS_READ_ONLY) + return dst->ops->cow_metrics(dst, p); + return __DST_METRICS_PTR(p); +} + +/* This may only be invoked before the entry has reached global + * visibility. + */ +static inline void dst_init_metrics(struct dst_entry *dst, + const u32 *src_metrics, + bool read_only) +{ + dst->_metrics = ((unsigned long) src_metrics) | + (read_only ? DST_METRICS_READ_ONLY : 0); +} + +static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) +{ + u32 *dst_metrics = dst_metrics_write_ptr(dest); + + if (dst_metrics) { + u32 *src_metrics = DST_METRICS_PTR(src); + + memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32)); + } +} + +static inline u32 *dst_metrics_ptr(struct dst_entry *dst) +{ + return DST_METRICS_PTR(dst); +} + static inline u32 dst_metric_raw(const struct dst_entry *dst, const int metric) { - return dst->_metrics[metric-1]; + u32 *p = DST_METRICS_PTR(dst); + + return p[metric-1]; } static inline u32 @@ -131,22 +184,10 @@ dst_metric_advmss(const struct dst_entry *dst) static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val) { - dst->_metrics[metric-1] = val; -} - -static inline void dst_import_metrics(struct dst_entry *dst, const u32 *src_metrics) -{ - memcpy(dst->_metrics, src_metrics, RTAX_MAX * sizeof(u32)); -} + u32 *p = dst_metrics_write_ptr(dst); -static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src) -{ - dst_import_metrics(dest, src->_metrics); -} - -static inline u32 *dst_metrics_ptr(struct dst_entry *dst) -{ - return dst->_metrics; + if (p) + p[metric-1] = val; } static inline u32 diff --git a/include/net/dst_ops.h b/include/net/dst_ops.h index 21a320b..dc07463 100644 --- a/include/net/dst_ops.h +++ b/include/net/dst_ops.h @@ -18,6 +18,7 @@ struct dst_ops { struct dst_entry * (*check)(struct dst_entry *, __u32 cookie); unsigned int (*default_advmss)(const struct dst_entry *); unsigned int (*default_mtu)(const struct dst_entry *); + u32 * (*cow_metrics)(struct dst_entry *, unsigned long); void (*destroy)(struct dst_entry *); void (*ifdown)(struct dst_entry *, struct net_device *dev, int how); diff --git a/include/net/flow.h b/include/net/flow.h index 240b7f3..1ae901f 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -48,7 +48,8 @@ struct flowi { __u8 proto; __u8 flags; -#define FLOWI_FLAG_ANYSRC 0x01 +#define FLOWI_FLAG_ANYSRC 0x01 +#define FLOWI_FLAG_PRECOW_METRICS 0x02 union { struct { __be16 sport; diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 8181498..6e6dfd7 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -219,7 +219,13 @@ static inline struct request_sock *inet_reqsk_alloc(struct request_sock_ops *ops static inline __u8 inet_sk_flowi_flags(const struct sock *sk) { - return inet_sk(sk)->transparent ? FLOWI_FLAG_ANYSRC : 0; + __u8 flags = 0; + + if (inet_sk(sk)->transparent) + flags |= FLOWI_FLAG_ANYSRC; + if (sk->sk_protocol == IPPROTO_TCP) + flags |= FLOWI_FLAG_PRECOW_METRICS; + return flags; } #endif /* _INET_SOCK_H */ diff --git a/include/net/inetpeer.h b/include/net/inetpeer.h index 599d96e..61f2c66 100644 --- a/include/net/inetpeer.h +++ b/include/net/inetpeer.h @@ -11,6 +11,7 @@ #include <linux/init.h> #include <linux/jiffies.h> #include <linux/spinlock.h> +#include <linux/rtnetlink.h> #include <net/ipv6.h> #include <asm/atomic.h> @@ -33,8 +34,8 @@ struct inet_peer { atomic_t refcnt; /* * Once inet_peer is queued for deletion (refcnt == -1), following fields - * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp - * We can share memory with rcu_head to keep inet_peer small + * are not available: rid, ip_id_count, tcp_ts, tcp_ts_stamp, metrics + * We can share memory with rcu_head to help keep inet_peer small. */ union { struct { @@ -42,6 +43,7 @@ struct inet_peer { atomic_t ip_id_count; /* IP ID for the next packet */ __u32 tcp_ts; __u32 tcp_ts_stamp; + u32 metrics[RTAX_MAX]; }; struct rcu_head rcu; }; @@ -49,6 +51,13 @@ struct inet_peer { void inet_initpeers(void) __init; +#define INETPEER_METRICS_NEW (~(u32) 0) + +static inline bool inet_metrics_new(const struct inet_peer *p) +{ + return p->metrics[RTAX_LOCK-1] == INETPEER_METRICS_NEW; +} + /* can be called with or without local BH being disabled */ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create); diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h index 07bdb5e..2c0508a 100644 --- a/include/net/ip_fib.h +++ b/include/net/ip_fib.h @@ -55,7 +55,7 @@ struct fib_nh { int nh_weight; int nh_power; #endif -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif int nh_oif; @@ -77,7 +77,7 @@ struct fib_info { int fib_protocol; __be32 fib_prefsrc; u32 fib_priority; - u32 fib_metrics[RTAX_MAX]; + u32 *fib_metrics; #define fib_mtu fib_metrics[RTAX_MTU-1] #define fib_window fib_metrics[RTAX_WINDOW-1] #define fib_rtt fib_metrics[RTAX_RTT-1] @@ -201,7 +201,7 @@ static inline int fib_lookup(struct net *net, const struct flowi *flp, extern int __net_init fib4_rules_init(struct net *net); extern void __net_exit fib4_rules_exit(struct net *net); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID extern u32 fib_rules_tclass(struct fib_result *res); #endif @@ -235,7 +235,7 @@ extern struct fib_table *fib_hash_table(u32 id); static inline void fib_combine_itag(u32 *itag, struct fib_result *res) { -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index b7bbd6c..b23bea6 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -28,6 +28,80 @@ #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) #include <net/netfilter/nf_conntrack.h> #endif +#include <net/net_namespace.h> /* Netw namespace */ + +/* + * Generic access of ipvs struct + */ +static inline struct netns_ipvs *net_ipvs(struct net* net) +{ + return net->ipvs; +} +/* + * Get net ptr from skb in traffic cases + * use skb_sknet when call is from userland (ioctl or netlink) + */ +static inline struct net *skb_net(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS +#ifdef CONFIG_IP_VS_DEBUG + /* + * This is used for debug only. + * Start with the most likely hit + * End with BUG + */ + if (likely(skb->dev && skb->dev->nd_net)) + return dev_net(skb->dev); + if (skb_dst(skb)->dev) + return dev_net(skb_dst(skb)->dev); + WARN(skb->sk, "Maybe skb_sknet should be used in %s() at line:%d\n", + __func__, __LINE__); + if (likely(skb->sk && skb->sk->sk_net)) + return sock_net(skb->sk); + pr_err("There is no net ptr to find in the skb in %s() line:%d\n", + __func__, __LINE__); + BUG(); +#else + return dev_net(skb->dev ? : skb_dst(skb)->dev); +#endif +#else + return &init_net; +#endif +} + +static inline struct net *skb_sknet(const struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS +#ifdef CONFIG_IP_VS_DEBUG + /* Start with the most likely hit */ + if (likely(skb->sk && skb->sk->sk_net)) + return sock_net(skb->sk); + WARN(skb->dev, "Maybe skb_net should be used instead in %s() line:%d\n", + __func__, __LINE__); + if (likely(skb->dev && skb->dev->nd_net)) + return dev_net(skb->dev); + pr_err("There is no net ptr to find in the skb in %s() line:%d\n", + __func__, __LINE__); + BUG(); +#else + return sock_net(skb->sk); +#endif +#else + return &init_net; +#endif +} +/* + * This one needed for single_open_net since net is stored directly in + * private not as a struct i.e. seq_file_net cant be used. + */ +static inline struct net *seq_file_single_net(struct seq_file *seq) +{ +#ifdef CONFIG_NET_NS + return (struct net *)seq->private; +#else + return &init_net; +#endif +} /* Connections' size value needed by ip_vs_ctl.c */ extern int ip_vs_conn_tab_size; @@ -258,6 +332,23 @@ struct ip_vs_seq { before last resized pkt */ }; +/* + * counters per cpu + */ +struct ip_vs_counters { + __u32 conns; /* connections scheduled */ + __u32 inpkts; /* incoming packets */ + __u32 outpkts; /* outgoing packets */ + __u64 inbytes; /* incoming bytes */ + __u64 outbytes; /* outgoing bytes */ +}; +/* + * Stats per cpu + */ +struct ip_vs_cpu_stats { + struct ip_vs_counters ustats; + struct u64_stats_sync syncp; +}; /* * IPVS statistics objects @@ -279,17 +370,34 @@ struct ip_vs_estimator { }; struct ip_vs_stats { - struct ip_vs_stats_user ustats; /* statistics */ + struct ip_vs_stats_user ustats; /* statistics */ struct ip_vs_estimator est; /* estimator */ - - spinlock_t lock; /* spin lock */ + struct ip_vs_cpu_stats *cpustats; /* per cpu counters */ + spinlock_t lock; /* spin lock */ }; +/* + * Helper Macros for per cpu + * ipvs->tot_stats->ustats.count + */ +#define IPVS_STAT_INC(ipvs, count) \ + __this_cpu_inc((ipvs)->ustats->count) + +#define IPVS_STAT_ADD(ipvs, count, value) \ + do {\ + write_seqcount_begin(per_cpu_ptr((ipvs)->ustats_seq, \ + raw_smp_processor_id())); \ + __this_cpu_add((ipvs)->ustats->count, value); \ + write_seqcount_end(per_cpu_ptr((ipvs)->ustats_seq, \ + raw_smp_processor_id())); \ + } while (0) + struct dst_entry; struct iphdr; struct ip_vs_conn; struct ip_vs_app; struct sk_buff; +struct ip_vs_proto_data; struct ip_vs_protocol { struct ip_vs_protocol *next; @@ -297,21 +405,22 @@ struct ip_vs_protocol { u16 protocol; u16 num_states; int dont_defrag; - atomic_t appcnt; /* counter of proto app incs */ - int *timeout_table; /* protocol timeout table */ void (*init)(struct ip_vs_protocol *pp); void (*exit)(struct ip_vs_protocol *pp); + void (*init_netns)(struct net *net, struct ip_vs_proto_data *pd); + + void (*exit_netns)(struct net *net, struct ip_vs_proto_data *pd); + int (*conn_schedule)(int af, struct sk_buff *skb, - struct ip_vs_protocol *pp, + struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp); struct ip_vs_conn * (*conn_in_get)(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -319,7 +428,6 @@ struct ip_vs_protocol { struct ip_vs_conn * (*conn_out_get)(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -337,11 +445,11 @@ struct ip_vs_protocol { int (*state_transition)(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_protocol *pp); + struct ip_vs_proto_data *pd); - int (*register_app)(struct ip_vs_app *inc); + int (*register_app)(struct net *net, struct ip_vs_app *inc); - void (*unregister_app)(struct ip_vs_app *inc); + void (*unregister_app)(struct net *net, struct ip_vs_app *inc); int (*app_conn_bind)(struct ip_vs_conn *cp); @@ -350,14 +458,26 @@ struct ip_vs_protocol { int offset, const char *msg); - void (*timeout_change)(struct ip_vs_protocol *pp, int flags); + void (*timeout_change)(struct ip_vs_proto_data *pd, int flags); +}; - int (*set_state_timeout)(struct ip_vs_protocol *pp, char *sname, int to); +/* + * protocol data per netns + */ +struct ip_vs_proto_data { + struct ip_vs_proto_data *next; + struct ip_vs_protocol *pp; + int *timeout_table; /* protocol timeout table */ + atomic_t appcnt; /* counter of proto app incs. */ + struct tcp_states_t *tcp_state_table; }; -extern struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto); +extern struct ip_vs_protocol *ip_vs_proto_get(unsigned short proto); +extern struct ip_vs_proto_data *ip_vs_proto_data_get(struct net *net, + unsigned short proto); struct ip_vs_conn_param { + struct net *net; const union nf_inet_addr *caddr; const union nf_inet_addr *vaddr; __be16 cport; @@ -375,16 +495,19 @@ struct ip_vs_conn_param { */ struct ip_vs_conn { struct list_head c_list; /* hashed list heads */ - +#ifdef CONFIG_NET_NS + struct net *net; /* Name space */ +#endif /* Protocol, addresses and port numbers */ - u16 af; /* address family */ - union nf_inet_addr caddr; /* client address */ - union nf_inet_addr vaddr; /* virtual address */ - union nf_inet_addr daddr; /* destination address */ - volatile __u32 flags; /* status flags */ - __be16 cport; - __be16 vport; - __be16 dport; + u16 af; /* address family */ + __be16 cport; + __be16 vport; + __be16 dport; + __u32 fwmark; /* Fire wall mark from skb */ + union nf_inet_addr caddr; /* client address */ + union nf_inet_addr vaddr; /* virtual address */ + union nf_inet_addr daddr; /* destination address */ + volatile __u32 flags; /* status flags */ __u16 protocol; /* Which protocol (TCP/UDP) */ /* counter and timer */ @@ -422,10 +545,38 @@ struct ip_vs_conn { struct ip_vs_seq in_seq; /* incoming seq. struct */ struct ip_vs_seq out_seq; /* outgoing seq. struct */ + const struct ip_vs_pe *pe; char *pe_data; __u8 pe_data_len; }; +/* + * To save some memory in conn table when name space is disabled. + */ +static inline struct net *ip_vs_conn_net(const struct ip_vs_conn *cp) +{ +#ifdef CONFIG_NET_NS + return cp->net; +#else + return &init_net; +#endif +} +static inline void ip_vs_conn_net_set(struct ip_vs_conn *cp, struct net *net) +{ +#ifdef CONFIG_NET_NS + cp->net = net; +#endif +} + +static inline int ip_vs_conn_net_eq(const struct ip_vs_conn *cp, + struct net *net) +{ +#ifdef CONFIG_NET_NS + return cp->net == net; +#else + return 1; +#endif +} /* * Extended internal versions of struct ip_vs_service_user and @@ -485,6 +636,7 @@ struct ip_vs_service { unsigned flags; /* service status flags */ unsigned timeout; /* persistent timeout in ticks */ __be32 netmask; /* grouping granularity */ + struct net *net; struct list_head destinations; /* real server d-linked list */ __u32 num_dests; /* number of servers */ @@ -510,8 +662,8 @@ struct ip_vs_dest { struct list_head d_list; /* for table with all the dests */ u16 af; /* address family */ - union nf_inet_addr addr; /* IP address of the server */ __be16 port; /* port number of the server */ + union nf_inet_addr addr; /* IP address of the server */ volatile unsigned flags; /* dest status flags */ atomic_t conn_flags; /* flags to copy to conn */ atomic_t weight; /* server weight */ @@ -538,8 +690,8 @@ struct ip_vs_dest { /* for virtual service */ struct ip_vs_service *svc; /* service it belongs to */ __u16 protocol; /* which protocol (TCP/UDP) */ - union nf_inet_addr vaddr; /* virtual IP address */ __be16 vport; /* virtual port number */ + union nf_inet_addr vaddr; /* virtual IP address */ __u32 vfwmark; /* firewall mark of service */ }; @@ -674,13 +826,14 @@ enum { IP_VS_DIR_LAST, }; -static inline void ip_vs_conn_fill_param(int af, int protocol, +static inline void ip_vs_conn_fill_param(struct net *net, int af, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { + p->net = net; p->af = af; p->protocol = protocol; p->caddr = caddr; @@ -695,7 +848,6 @@ struct ip_vs_conn *ip_vs_conn_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -703,7 +855,6 @@ struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p); struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse); @@ -719,14 +870,14 @@ extern void ip_vs_conn_fill_cport(struct ip_vs_conn *cp, __be16 cport); struct ip_vs_conn *ip_vs_conn_new(const struct ip_vs_conn_param *p, const union nf_inet_addr *daddr, __be16 dport, unsigned flags, - struct ip_vs_dest *dest); + struct ip_vs_dest *dest, __u32 fwmark); extern void ip_vs_conn_expire_now(struct ip_vs_conn *cp); extern const char * ip_vs_state_name(__u16 proto, int state); -extern void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp); +extern void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp); extern int ip_vs_check_template(struct ip_vs_conn *ct); -extern void ip_vs_random_dropentry(void); +extern void ip_vs_random_dropentry(struct net *net); extern int ip_vs_conn_init(void); extern void ip_vs_conn_cleanup(void); @@ -796,12 +947,12 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) * (from ip_vs_app.c) */ #define IP_VS_APP_MAX_PORTS 8 -extern int register_ip_vs_app(struct ip_vs_app *app); -extern void unregister_ip_vs_app(struct ip_vs_app *app); +extern int register_ip_vs_app(struct net *net, struct ip_vs_app *app); +extern void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app); extern int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp); extern void ip_vs_unbind_app(struct ip_vs_conn *cp); -extern int -register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port); +extern int register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, + __u16 proto, __u16 port); extern int ip_vs_app_inc_get(struct ip_vs_app *inc); extern void ip_vs_app_inc_put(struct ip_vs_app *inc); @@ -814,15 +965,27 @@ void ip_vs_bind_pe(struct ip_vs_service *svc, struct ip_vs_pe *pe); void ip_vs_unbind_pe(struct ip_vs_service *svc); int register_ip_vs_pe(struct ip_vs_pe *pe); int unregister_ip_vs_pe(struct ip_vs_pe *pe); -extern struct ip_vs_pe *ip_vs_pe_get(const char *name); -extern void ip_vs_pe_put(struct ip_vs_pe *pe); +struct ip_vs_pe *ip_vs_pe_getbyname(const char *name); +struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name); + +static inline void ip_vs_pe_get(const struct ip_vs_pe *pe) +{ + if (pe && pe->module) + __module_get(pe->module); +} + +static inline void ip_vs_pe_put(const struct ip_vs_pe *pe) +{ + if (pe && pe->module) + module_put(pe->module); +} /* * IPVS protocol functions (from ip_vs_proto.c) */ extern int ip_vs_protocol_init(void); extern void ip_vs_protocol_cleanup(void); -extern void ip_vs_protocol_timeout_change(int flags); +extern void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags); extern int *ip_vs_create_timeout_table(int *table, int size); extern int ip_vs_set_state_timeout(int *table, int num, const char *const *names, @@ -852,26 +1015,21 @@ extern struct ip_vs_scheduler *ip_vs_scheduler_get(const char *sched_name); extern void ip_vs_scheduler_put(struct ip_vs_scheduler *scheduler); extern struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp, int *ignored); + struct ip_vs_proto_data *pd, int *ignored); extern int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp); + struct ip_vs_proto_data *pd); /* * IPVS control data and functions (from ip_vs_ctl.c) */ -extern int sysctl_ip_vs_cache_bypass; -extern int sysctl_ip_vs_expire_nodest_conn; -extern int sysctl_ip_vs_expire_quiescent_template; -extern int sysctl_ip_vs_sync_threshold[2]; -extern int sysctl_ip_vs_nat_icmp_send; -extern int sysctl_ip_vs_conntrack; -extern int sysctl_ip_vs_snat_reroute; extern struct ip_vs_stats ip_vs_stats; extern const struct ctl_path net_vs_ctl_path[]; +extern int sysctl_ip_vs_sync_ver; +extern void ip_vs_sync_switch_mode(struct net *net, int mode); extern struct ip_vs_service * -ip_vs_service_get(int af, __u32 fwmark, __u16 protocol, +ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport); static inline void ip_vs_service_put(struct ip_vs_service *svc) @@ -880,7 +1038,7 @@ static inline void ip_vs_service_put(struct ip_vs_service *svc) } extern struct ip_vs_dest * -ip_vs_lookup_real_service(int af, __u16 protocol, +ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport); extern int ip_vs_use_count_inc(void); @@ -888,8 +1046,9 @@ extern void ip_vs_use_count_dec(void); extern int ip_vs_control_init(void); extern void ip_vs_control_cleanup(void); extern struct ip_vs_dest * -ip_vs_find_dest(int af, const union nf_inet_addr *daddr, __be16 dport, - const union nf_inet_addr *vaddr, __be16 vport, __u16 protocol); +ip_vs_find_dest(struct net *net, int af, const union nf_inet_addr *daddr, + __be16 dport, const union nf_inet_addr *vaddr, __be16 vport, + __u16 protocol, __u32 fwmark); extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); @@ -897,14 +1056,12 @@ extern struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp); * IPVS sync daemon data and function prototypes * (from ip_vs_sync.c) */ -extern volatile int ip_vs_sync_state; -extern volatile int ip_vs_master_syncid; -extern volatile int ip_vs_backup_syncid; -extern char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -extern char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -extern int start_sync_thread(int state, char *mcast_ifn, __u8 syncid); -extern int stop_sync_thread(int state); -extern void ip_vs_sync_conn(struct ip_vs_conn *cp); +extern int start_sync_thread(struct net *net, int state, char *mcast_ifn, + __u8 syncid); +extern int stop_sync_thread(struct net *net, int state); +extern void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp); +extern int ip_vs_sync_init(void); +extern void ip_vs_sync_cleanup(void); /* @@ -912,8 +1069,8 @@ extern void ip_vs_sync_conn(struct ip_vs_conn *cp); */ extern int ip_vs_estimator_init(void); extern void ip_vs_estimator_cleanup(void); -extern void ip_vs_new_estimator(struct ip_vs_stats *stats); -extern void ip_vs_kill_estimator(struct ip_vs_stats *stats); +extern void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats); +extern void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats); extern void ip_vs_zero_estimator(struct ip_vs_stats *stats); /* @@ -955,11 +1112,13 @@ extern int ip_vs_icmp_xmit_v6 extern int ip_vs_drop_rate; extern int ip_vs_drop_counter; -static __inline__ int ip_vs_todrop(void) +static inline int ip_vs_todrop(struct netns_ipvs *ipvs) { - if (!ip_vs_drop_rate) return 0; - if (--ip_vs_drop_counter > 0) return 0; - ip_vs_drop_counter = ip_vs_drop_rate; + if (!ipvs->drop_rate) + return 0; + if (--ipvs->drop_counter > 0) + return 0; + ipvs->drop_counter = ipvs->drop_rate; return 1; } @@ -1047,9 +1206,9 @@ static inline void ip_vs_notrack(struct sk_buff *skb) * Netfilter connection tracking * (from ip_vs_nfct.c) */ -static inline int ip_vs_conntrack_enabled(void) +static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs) { - return sysctl_ip_vs_conntrack; + return ipvs->sysctl_conntrack; } extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, @@ -1062,7 +1221,7 @@ extern void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp); #else -static inline int ip_vs_conntrack_enabled(void) +static inline int ip_vs_conntrack_enabled(struct netns_ipvs *ipvs) { return 0; } diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 62c0ce2..d6b0045 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -1147,6 +1147,17 @@ enum ieee80211_hw_flags { * @napi_weight: weight used for NAPI polling. You must specify an * appropriate value here if a napi_poll operation is provided * by your driver. + + * @max_rx_aggregation_subframes: maximum buffer size (number of + * sub-frames) to be used for A-MPDU block ack receiver + * aggregation. + * This is only relevant if the device has restrictions on the + * number of subframes, if it relies on mac80211 to do reordering + * it shouldn't be set. + * + * @max_tx_aggregation_subframes: maximum number of subframes in an + * aggregate an HT driver will transmit, used by the peer as a + * hint to size its reorder buffer. */ struct ieee80211_hw { struct ieee80211_conf conf; @@ -1165,6 +1176,8 @@ struct ieee80211_hw { u8 max_rates; u8 max_report_rates; u8 max_rate_tries; + u8 max_rx_aggregation_subframes; + u8 max_tx_aggregation_subframes; }; /** @@ -1723,6 +1736,10 @@ enum ieee80211_ampdu_mlme_action { * ieee80211_ampdu_mlme_action. Starting sequence number (@ssn) * is the first frame we expect to perform the action on. Notice * that TX/RX_STOP can pass NULL for this parameter. + * The @buf_size parameter is only valid when the action is set to + * %IEEE80211_AMPDU_TX_OPERATIONAL and indicates the peer's reorder + * buffer size (number of subframes) for this session -- aggregates + * containing more subframes than this may not be transmitted to the peer. * Returns a negative error code on failure. * The callback can sleep. * @@ -1825,7 +1842,8 @@ struct ieee80211_ops { int (*ampdu_action)(struct ieee80211_hw *hw, struct ieee80211_vif *vif, enum ieee80211_ampdu_mlme_action action, - struct ieee80211_sta *sta, u16 tid, u16 *ssn); + struct ieee80211_sta *sta, u16 tid, u16 *ssn, + u8 buf_size); int (*get_survey)(struct ieee80211_hw *hw, int idx, struct survey_info *survey); void (*rfkill_poll)(struct ieee80211_hw *hw); diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index 1bf812b..b3b4a34 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -20,6 +20,7 @@ #include <net/netns/conntrack.h> #endif #include <net/netns/xfrm.h> +#include <net/netns/ip_vs.h> struct proc_dir_entry; struct net_device; @@ -94,6 +95,7 @@ struct net { #ifdef CONFIG_XFRM struct netns_xfrm xfrm; #endif + struct netns_ipvs *ipvs; }; diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h index d85cff1..d0d1337 100644 --- a/include/net/netfilter/nf_conntrack.h +++ b/include/net/netfilter/nf_conntrack.h @@ -50,11 +50,24 @@ union nf_conntrack_expect_proto { /* per conntrack: application helper private data */ union nf_conntrack_help { /* insert conntrack helper private data (master) here */ +#if defined(CONFIG_NF_CONNTRACK_FTP) || defined(CONFIG_NF_CONNTRACK_FTP_MODULE) struct nf_ct_ftp_master ct_ftp_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_PPTP) || \ + defined(CONFIG_NF_CONNTRACK_PPTP_MODULE) struct nf_ct_pptp_master ct_pptp_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_H323) || \ + defined(CONFIG_NF_CONNTRACK_H323_MODULE) struct nf_ct_h323_master ct_h323_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_SANE) || \ + defined(CONFIG_NF_CONNTRACK_SANE_MODULE) struct nf_ct_sane_master ct_sane_info; +#endif +#if defined(CONFIG_NF_CONNTRACK_SIP) || defined(CONFIG_NF_CONNTRACK_SIP_MODULE) struct nf_ct_sip_master ct_sip_info; +#endif }; #include <linux/types.h> @@ -116,14 +129,14 @@ struct nf_conn { u_int32_t secmark; #endif - /* Storage reserved for other modules: */ - union nf_conntrack_proto proto; - /* Extensions */ struct nf_ct_ext *ext; #ifdef CONFIG_NET_NS struct net *ct_net; #endif + + /* Storage reserved for other modules, must be the last member */ + union nf_conntrack_proto proto; }; static inline struct nf_conn * @@ -189,9 +202,9 @@ extern void nf_ct_l3proto_module_put(unsigned short l3proto); * Allocate a hashtable of hlist_head (if nulls == 0), * or hlist_nulls_head (if nulls == 1) */ -extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls); +extern void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls); -extern void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size); +extern void nf_ct_free_hashtable(void *hash, unsigned int size); extern struct nf_conntrack_tuple_hash * __nf_conntrack_find(struct net *net, u16 zone, diff --git a/include/net/netfilter/nf_conntrack_ecache.h b/include/net/netfilter/nf_conntrack_ecache.h index 96ba5f7..8fdb04b 100644 --- a/include/net/netfilter/nf_conntrack_ecache.h +++ b/include/net/netfilter/nf_conntrack_ecache.h @@ -23,12 +23,17 @@ struct nf_conntrack_ecache { static inline struct nf_conntrack_ecache * nf_ct_ecache_find(const struct nf_conn *ct) { +#ifdef CONFIG_NF_CONNTRACK_EVENTS return nf_ct_ext_find(ct, NF_CT_EXT_ECACHE); +#else + return NULL; +#endif } static inline struct nf_conntrack_ecache * nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) { +#ifdef CONFIG_NF_CONNTRACK_EVENTS struct net *net = nf_ct_net(ct); struct nf_conntrack_ecache *e; @@ -45,6 +50,9 @@ nf_ct_ecache_ext_add(struct nf_conn *ct, u16 ctmask, u16 expmask, gfp_t gfp) e->expmask = expmask; } return e; +#else + return NULL; +#endif }; #ifdef CONFIG_NF_CONNTRACK_EVENTS @@ -59,7 +67,7 @@ struct nf_ct_event_notifier { int (*fcn)(unsigned int events, struct nf_ct_event *item); }; -extern struct nf_ct_event_notifier *nf_conntrack_event_cb; +extern struct nf_ct_event_notifier __rcu *nf_conntrack_event_cb; extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb); extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb); @@ -159,7 +167,7 @@ struct nf_exp_event_notifier { int (*fcn)(unsigned int events, struct nf_exp_event *item); }; -extern struct nf_exp_event_notifier *nf_expect_event_cb; +extern struct nf_exp_event_notifier __rcu *nf_expect_event_cb; extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb); extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb); diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h index 0772d29..2dcf317 100644 --- a/include/net/netfilter/nf_conntrack_extend.h +++ b/include/net/netfilter/nf_conntrack_extend.h @@ -7,10 +7,19 @@ enum nf_ct_ext_id { NF_CT_EXT_HELPER, +#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) NF_CT_EXT_NAT, +#endif NF_CT_EXT_ACCT, +#ifdef CONFIG_NF_CONNTRACK_EVENTS NF_CT_EXT_ECACHE, +#endif +#ifdef CONFIG_NF_CONNTRACK_ZONES NF_CT_EXT_ZONE, +#endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + NF_CT_EXT_TSTAMP, +#endif NF_CT_EXT_NUM, }; @@ -19,6 +28,7 @@ enum nf_ct_ext_id { #define NF_CT_EXT_ACCT_TYPE struct nf_conn_counter #define NF_CT_EXT_ECACHE_TYPE struct nf_conntrack_ecache #define NF_CT_EXT_ZONE_TYPE struct nf_conntrack_zone +#define NF_CT_EXT_TSTAMP_TYPE struct nf_conn_tstamp /* Extensions: optional stuff which isn't permanently in struct. */ struct nf_ct_ext { diff --git a/include/net/netfilter/nf_conntrack_helper.h b/include/net/netfilter/nf_conntrack_helper.h index 32c305d..f1c1311 100644 --- a/include/net/netfilter/nf_conntrack_helper.h +++ b/include/net/netfilter/nf_conntrack_helper.h @@ -63,4 +63,10 @@ static inline struct nf_conn_help *nfct_help(const struct nf_conn *ct) extern int nf_conntrack_helper_init(void); extern void nf_conntrack_helper_fini(void); +extern int nf_conntrack_broadcast_help(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int timeout); + #endif /*_NF_CONNTRACK_HELPER_H*/ diff --git a/include/net/netfilter/nf_conntrack_l3proto.h b/include/net/netfilter/nf_conntrack_l3proto.h index a754761..e8010f4 100644 --- a/include/net/netfilter/nf_conntrack_l3proto.h +++ b/include/net/netfilter/nf_conntrack_l3proto.h @@ -73,7 +73,7 @@ struct nf_conntrack_l3proto { struct module *me; }; -extern struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX]; +extern struct nf_conntrack_l3proto __rcu *nf_ct_l3protos[AF_MAX]; /* Protocol registration. */ extern int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto); diff --git a/include/net/netfilter/nf_conntrack_timestamp.h b/include/net/netfilter/nf_conntrack_timestamp.h new file mode 100644 index 0000000..fc9c82b --- /dev/null +++ b/include/net/netfilter/nf_conntrack_timestamp.h @@ -0,0 +1,65 @@ +#ifndef _NF_CONNTRACK_TSTAMP_H +#define _NF_CONNTRACK_TSTAMP_H + +#include <net/net_namespace.h> +#include <linux/netfilter/nf_conntrack_common.h> +#include <linux/netfilter/nf_conntrack_tuple_common.h> +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_extend.h> + +struct nf_conn_tstamp { + u_int64_t start; + u_int64_t stop; +}; + +static inline +struct nf_conn_tstamp *nf_conn_tstamp_find(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + return nf_ct_ext_find(ct, NF_CT_EXT_TSTAMP); +#else + return NULL; +#endif +} + +static inline +struct nf_conn_tstamp *nf_ct_tstamp_ext_add(struct nf_conn *ct, gfp_t gfp) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + struct net *net = nf_ct_net(ct); + + if (!net->ct.sysctl_tstamp) + return NULL; + + return nf_ct_ext_add(ct, NF_CT_EXT_TSTAMP, gfp); +#else + return NULL; +#endif +}; + +static inline bool nf_ct_tstamp_enabled(struct net *net) +{ + return net->ct.sysctl_tstamp != 0; +} + +static inline void nf_ct_set_tstamp(struct net *net, bool enable) +{ + net->ct.sysctl_tstamp = enable; +} + +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP +extern int nf_conntrack_tstamp_init(struct net *net); +extern void nf_conntrack_tstamp_fini(struct net *net); +#else +static inline int nf_conntrack_tstamp_init(struct net *net) +{ + return 0; +} + +static inline void nf_conntrack_tstamp_fini(struct net *net) +{ + return; +} +#endif /* CONFIG_NF_CONNTRACK_TIMESTAMP */ + +#endif /* _NF_CONNTRACK_TSTAMP_H */ diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index f5f09f0..aff80b1 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -56,7 +56,9 @@ struct nf_nat_multi_range_compat { /* per conntrack: nat application helper private data */ union nf_conntrack_nat_help { /* insert nat helper private data here */ +#if defined(CONFIG_NF_NAT_PPTP) || defined(CONFIG_NF_NAT_PPTP_MODULE) struct nf_nat_pptp nat_pptp_info; +#endif }; struct nf_conn; @@ -84,7 +86,11 @@ extern int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, static inline struct nf_conn_nat *nfct_nat(const struct nf_conn *ct) { +#if defined(CONFIG_NF_NAT) || defined(CONFIG_NF_NAT_MODULE) return nf_ct_ext_find(ct, NF_CT_EXT_NAT); +#else + return NULL; +#endif } #else /* !__KERNEL__: iptables wants this to compile. */ diff --git a/include/net/netfilter/nf_nat_core.h b/include/net/netfilter/nf_nat_core.h index 33602ab..3dc7b98 100644 --- a/include/net/netfilter/nf_nat_core.h +++ b/include/net/netfilter/nf_nat_core.h @@ -21,9 +21,9 @@ static inline int nf_nat_initialized(struct nf_conn *ct, enum nf_nat_manip_type manip) { if (manip == IP_NAT_MANIP_SRC) - return test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status); + return ct->status & IPS_SRC_NAT_DONE; else - return test_bit(IPS_DST_NAT_DONE_BIT, &ct->status); + return ct->status & IPS_DST_NAT_DONE; } struct nlattr; diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h index d4958d4..341eb08 100644 --- a/include/net/netns/conntrack.h +++ b/include/net/netns/conntrack.h @@ -21,15 +21,15 @@ struct netns_ct { int sysctl_events; unsigned int sysctl_events_retry_timeout; int sysctl_acct; + int sysctl_tstamp; int sysctl_checksum; unsigned int sysctl_log_invalid; /* Log invalid packets */ #ifdef CONFIG_SYSCTL struct ctl_table_header *sysctl_header; struct ctl_table_header *acct_sysctl_header; + struct ctl_table_header *tstamp_sysctl_header; struct ctl_table_header *event_sysctl_header; #endif - int hash_vmalloc; - int expect_vmalloc; char *slabname; }; #endif diff --git a/include/net/netns/ip_vs.h b/include/net/netns/ip_vs.h new file mode 100644 index 0000000..259ebac --- /dev/null +++ b/include/net/netns/ip_vs.h @@ -0,0 +1,143 @@ +/* + * IP Virtual Server + * Data structure for network namspace + * + */ + +#ifndef IP_VS_H_ +#define IP_VS_H_ + +#include <linux/list.h> +#include <linux/mutex.h> +#include <linux/list_nulls.h> +#include <linux/ip_vs.h> +#include <asm/atomic.h> +#include <linux/in.h> + +struct ip_vs_stats; +struct ip_vs_sync_buff; +struct ctl_table_header; + +struct netns_ipvs { + int gen; /* Generation */ + /* + * Hash table: for real service lookups + */ + #define IP_VS_RTAB_BITS 4 + #define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS) + #define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1) + + struct list_head rs_table[IP_VS_RTAB_SIZE]; + /* ip_vs_app */ + struct list_head app_list; + struct mutex app_mutex; + struct lock_class_key app_key; /* mutex debuging */ + + /* ip_vs_proto */ + #define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */ + struct ip_vs_proto_data *proto_data_table[IP_VS_PROTO_TAB_SIZE]; + /* ip_vs_proto_tcp */ +#ifdef CONFIG_IP_VS_PROTO_TCP + #define TCP_APP_TAB_BITS 4 + #define TCP_APP_TAB_SIZE (1 << TCP_APP_TAB_BITS) + #define TCP_APP_TAB_MASK (TCP_APP_TAB_SIZE - 1) + struct list_head tcp_apps[TCP_APP_TAB_SIZE]; + spinlock_t tcp_app_lock; +#endif + /* ip_vs_proto_udp */ +#ifdef CONFIG_IP_VS_PROTO_UDP + #define UDP_APP_TAB_BITS 4 + #define UDP_APP_TAB_SIZE (1 << UDP_APP_TAB_BITS) + #define UDP_APP_TAB_MASK (UDP_APP_TAB_SIZE - 1) + struct list_head udp_apps[UDP_APP_TAB_SIZE]; + spinlock_t udp_app_lock; +#endif + /* ip_vs_proto_sctp */ +#ifdef CONFIG_IP_VS_PROTO_SCTP + #define SCTP_APP_TAB_BITS 4 + #define SCTP_APP_TAB_SIZE (1 << SCTP_APP_TAB_BITS) + #define SCTP_APP_TAB_MASK (SCTP_APP_TAB_SIZE - 1) + /* Hash table for SCTP application incarnations */ + struct list_head sctp_apps[SCTP_APP_TAB_SIZE]; + spinlock_t sctp_app_lock; +#endif + /* ip_vs_conn */ + atomic_t conn_count; /* connection counter */ + + /* ip_vs_ctl */ + struct ip_vs_stats *tot_stats; /* Statistics & est. */ + struct ip_vs_cpu_stats __percpu *cpustats; /* Stats per cpu */ + seqcount_t *ustats_seq; /* u64 read retry */ + + int num_services; /* no of virtual services */ + /* 1/rate drop and drop-entry variables */ + struct delayed_work defense_work; /* Work handler */ + int drop_rate; + int drop_counter; + atomic_t dropentry; + /* locks in ctl.c */ + spinlock_t dropentry_lock; /* drop entry handling */ + spinlock_t droppacket_lock; /* drop packet handling */ + spinlock_t securetcp_lock; /* state and timeout tables */ + rwlock_t rs_lock; /* real services table */ + /* semaphore for IPVS sockopts. And, [gs]etsockopt may sleep. */ + struct lock_class_key ctl_key; /* ctl_mutex debuging */ + /* Trash for destinations */ + struct list_head dest_trash; + /* Service counters */ + atomic_t ftpsvc_counter; + atomic_t nullsvc_counter; + + /* sys-ctl struct */ + struct ctl_table_header *sysctl_hdr; + struct ctl_table *sysctl_tbl; + /* sysctl variables */ + int sysctl_amemthresh; + int sysctl_am_droprate; + int sysctl_drop_entry; + int sysctl_drop_packet; + int sysctl_secure_tcp; +#ifdef CONFIG_IP_VS_NFCT + int sysctl_conntrack; +#endif + int sysctl_snat_reroute; + int sysctl_sync_ver; + int sysctl_cache_bypass; + int sysctl_expire_nodest_conn; + int sysctl_expire_quiescent_template; + int sysctl_sync_threshold[2]; + int sysctl_nat_icmp_send; + + /* ip_vs_lblc */ + int sysctl_lblc_expiration; + struct ctl_table_header *lblc_ctl_header; + struct ctl_table *lblc_ctl_table; + /* ip_vs_lblcr */ + int sysctl_lblcr_expiration; + struct ctl_table_header *lblcr_ctl_header; + struct ctl_table *lblcr_ctl_table; + /* ip_vs_est */ + struct list_head est_list; /* estimator list */ + spinlock_t est_lock; + struct timer_list est_timer; /* Estimation timer */ + /* ip_vs_sync */ + struct list_head sync_queue; + spinlock_t sync_lock; + struct ip_vs_sync_buff *sync_buff; + spinlock_t sync_buff_lock; + struct sockaddr_in sync_mcast_addr; + struct task_struct *master_thread; + struct task_struct *backup_thread; + int send_mesg_maxlen; + int recv_mesg_maxlen; + volatile int sync_state; + volatile int master_syncid; + volatile int backup_syncid; + /* multicast interface name */ + char master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; + char backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; + /* net name space ptr */ + struct net *net; /* Needed by timer routines */ +}; + +#endif /* IP_VS_H_ */ diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index d68c3f1..e2e2ef5 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -43,7 +43,6 @@ struct netns_ipv4 { struct xt_table *nat_table; struct hlist_head *nat_bysource; unsigned int nat_htable_size; - int nat_vmalloced; #endif int sysctl_icmp_echo_ignore_all; diff --git a/include/net/protocol.h b/include/net/protocol.h index dc07495..6f7eb80 100644 --- a/include/net/protocol.h +++ b/include/net/protocol.h @@ -38,7 +38,7 @@ struct net_protocol { void (*err_handler)(struct sk_buff *skb, u32 info); int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); @@ -57,7 +57,7 @@ struct inet6_protocol { int (*gso_send_check)(struct sk_buff *skb); struct sk_buff *(*gso_segment)(struct sk_buff *skb, - int features); + u32 features); struct sk_buff **(*gro_receive)(struct sk_buff **head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb); diff --git a/include/net/route.h b/include/net/route.h index 93e10c4..e586465 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -49,6 +49,7 @@ struct fib_nh; struct inet_peer; +struct fib_info; struct rtable { struct dst_entry dst; @@ -69,6 +70,7 @@ struct rtable { /* Miscellaneous cached information */ __be32 rt_spec_dst; /* RFC1122 specific destination */ struct inet_peer *peer; /* long-living peer info */ + struct fib_info *fi; /* for client ref to shared metrics */ }; static inline bool rt_is_input_route(struct rtable *rt) @@ -180,6 +182,8 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst, if (inet_sk(sk)->transparent) fl.flags |= FLOWI_FLAG_ANYSRC; + if (protocol == IPPROTO_TCP) + fl.flags |= FLOWI_FLAG_PRECOW_METRICS; if (!dst || !src) { err = __ip_route_output_key(net, rp, &fl); @@ -207,6 +211,8 @@ static inline int ip_route_newports(struct rtable **rp, u8 protocol, fl.proto = protocol; if (inet_sk(sk)->transparent) fl.flags |= FLOWI_FLAG_ANYSRC; + if (protocol == IPPROTO_TCP) + fl.flags |= FLOWI_FLAG_PRECOW_METRICS; ip_rt_put(*rp); *rp = NULL; security_sk_classify_flow(sk, &fl); diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h index 160a407..16626a0 100644 --- a/include/net/sch_generic.h +++ b/include/net/sch_generic.h @@ -31,10 +31,12 @@ enum qdisc_state_t { * following bits are only changed while qdisc lock is held */ enum qdisc___state_t { - __QDISC___STATE_RUNNING, + __QDISC___STATE_RUNNING = 1, + __QDISC___STATE_THROTTLED = 2, }; struct qdisc_size_table { + struct rcu_head rcu; struct list_head list; struct tc_sizespec szopts; int refcnt; @@ -46,14 +48,13 @@ struct Qdisc { struct sk_buff * (*dequeue)(struct Qdisc *dev); unsigned flags; #define TCQ_F_BUILTIN 1 -#define TCQ_F_THROTTLED 2 -#define TCQ_F_INGRESS 4 -#define TCQ_F_CAN_BYPASS 8 -#define TCQ_F_MQROOT 16 +#define TCQ_F_INGRESS 2 +#define TCQ_F_CAN_BYPASS 4 +#define TCQ_F_MQROOT 8 #define TCQ_F_WARN_NONWC (1 << 16) int padded; struct Qdisc_ops *ops; - struct qdisc_size_table *stab; + struct qdisc_size_table __rcu *stab; struct list_head list; u32 handle; u32 parent; @@ -78,25 +79,43 @@ struct Qdisc { unsigned long state; struct sk_buff_head q; struct gnet_stats_basic_packed bstats; - unsigned long __state; + unsigned int __state; struct gnet_stats_queue qstats; struct rcu_head rcu_head; spinlock_t busylock; }; -static inline bool qdisc_is_running(struct Qdisc *qdisc) +static inline bool qdisc_is_running(const struct Qdisc *qdisc) { - return test_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + return (qdisc->__state & __QDISC___STATE_RUNNING) ? true : false; } static inline bool qdisc_run_begin(struct Qdisc *qdisc) { - return !__test_and_set_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + if (qdisc_is_running(qdisc)) + return false; + qdisc->__state |= __QDISC___STATE_RUNNING; + return true; } static inline void qdisc_run_end(struct Qdisc *qdisc) { - __clear_bit(__QDISC___STATE_RUNNING, &qdisc->__state); + qdisc->__state &= ~__QDISC___STATE_RUNNING; +} + +static inline bool qdisc_is_throttled(const struct Qdisc *qdisc) +{ + return (qdisc->__state & __QDISC___STATE_THROTTLED) ? true : false; +} + +static inline void qdisc_throttled(struct Qdisc *qdisc) +{ + qdisc->__state |= __QDISC___STATE_THROTTLED; +} + +static inline void qdisc_unthrottled(struct Qdisc *qdisc) +{ + qdisc->__state &= ~__QDISC___STATE_THROTTLED; } struct Qdisc_class_ops { @@ -331,8 +350,8 @@ extern struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, struct Qdisc_ops *ops); extern struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, struct Qdisc_ops *ops, u32 parentid); -extern void qdisc_calculate_pkt_len(struct sk_buff *skb, - struct qdisc_size_table *stab); +extern void __qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct qdisc_size_table *stab); extern void tcf_destroy(struct tcf_proto *tp); extern void tcf_destroy_chain(struct tcf_proto **fl); @@ -411,12 +430,20 @@ enum net_xmit_qdisc_t { #define net_xmit_drop_count(e) (1) #endif -static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +static inline void qdisc_calculate_pkt_len(struct sk_buff *skb, + const struct Qdisc *sch) { #ifdef CONFIG_NET_SCHED - if (sch->stab) - qdisc_calculate_pkt_len(skb, sch->stab); + struct qdisc_size_table *stab = rcu_dereference_bh(sch->stab); + + if (stab) + __qdisc_calculate_pkt_len(skb, stab); #endif +} + +static inline int qdisc_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + qdisc_calculate_pkt_len(skb, sch); return sch->enqueue(skb, sch); } diff --git a/include/net/sock.h b/include/net/sock.h index bc1cf7d8..e3893a2 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1191,7 +1191,7 @@ extern void sk_filter_release_rcu(struct rcu_head *rcu); static inline void sk_filter_release(struct sk_filter *fp) { if (atomic_dec_and_test(&fp->refcnt)) - call_rcu_bh(&fp->rcu, sk_filter_release_rcu); + call_rcu(&fp->rcu, sk_filter_release_rcu); } static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp) diff --git a/include/net/tcp.h b/include/net/tcp.h index 38509f0..9179111 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1404,7 +1404,7 @@ extern struct request_sock_ops tcp6_request_sock_ops; extern void tcp_v4_destroy_sock(struct sock *sk); extern int tcp_v4_gso_send_check(struct sk_buff *skb); -extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features); +extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features); extern struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb); extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head, diff --git a/include/net/udp.h b/include/net/udp.h index bb967dd..e82f3a8 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -245,5 +245,5 @@ extern void udp4_proc_exit(void); extern void udp_init(void); extern int udp4_ufo_send_check(struct sk_buff *skb); -extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features); +extern struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features); #endif /* _UDP_H */ diff --git a/kernel/audit.c b/kernel/audit.c index e495624..162e88e 100644 --- a/kernel/audit.c +++ b/kernel/audit.c @@ -74,6 +74,8 @@ static int audit_initialized; int audit_enabled; int audit_ever_enabled; +EXPORT_SYMBOL_GPL(audit_enabled); + /* Default state when kernel boots without any parameters. */ static int audit_default; diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c index 0caa59f..0587c5c 100644 --- a/kernel/irq/manage.c +++ b/kernel/irq/manage.c @@ -134,6 +134,10 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask) irq_set_thread_affinity(desc); } #endif + if (desc->affinity_notify) { + kref_get(&desc->affinity_notify->kref); + schedule_work(&desc->affinity_notify->work); + } desc->status |= IRQ_AFFINITY_SET; raw_spin_unlock_irqrestore(&desc->lock, flags); return 0; @@ -155,6 +159,79 @@ int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m) } EXPORT_SYMBOL_GPL(irq_set_affinity_hint); +static void irq_affinity_notify(struct work_struct *work) +{ + struct irq_affinity_notify *notify = + container_of(work, struct irq_affinity_notify, work); + struct irq_desc *desc = irq_to_desc(notify->irq); + cpumask_var_t cpumask; + unsigned long flags; + + if (!desc) + goto out; + + if (!alloc_cpumask_var(&cpumask, GFP_KERNEL)) + goto out; + + raw_spin_lock_irqsave(&desc->lock, flags); +#ifdef CONFIG_GENERIC_PENDING_IRQ + if (desc->status & IRQ_MOVE_PENDING) + cpumask_copy(cpumask, desc->pending_mask); + else +#endif + cpumask_copy(cpumask, desc->affinity); + raw_spin_unlock_irqrestore(&desc->lock, flags); + + notify->notify(notify, cpumask); + + free_cpumask_var(cpumask); +out: + kref_put(¬ify->kref, notify->release); +} + +/** + * irq_set_affinity_notifier - control notification of IRQ affinity changes + * @irq: Interrupt for which to enable/disable notification + * @notify: Context for notification, or %NULL to disable + * notification. Function pointers must be initialised; + * the other fields will be initialised by this function. + * + * Must be called in process context. Notification may only be enabled + * after the IRQ is allocated and must be disabled before the IRQ is + * freed using free_irq(). + */ +int +irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify) +{ + struct irq_desc *desc = irq_to_desc(irq); + struct irq_affinity_notify *old_notify; + unsigned long flags; + + /* The release function is promised process context */ + might_sleep(); + + if (!desc) + return -EINVAL; + + /* Complete initialisation of *notify */ + if (notify) { + notify->irq = irq; + kref_init(¬ify->kref); + INIT_WORK(¬ify->work, irq_affinity_notify); + } + + raw_spin_lock_irqsave(&desc->lock, flags); + old_notify = desc->affinity_notify; + desc->affinity_notify = notify; + raw_spin_unlock_irqrestore(&desc->lock, flags); + + if (old_notify) + kref_put(&old_notify->kref, old_notify->release); + + return 0; +} +EXPORT_SYMBOL_GPL(irq_set_affinity_notifier); + #ifndef CONFIG_AUTO_IRQ_AFFINITY /* * Generic version of the affinity autoselector. @@ -1004,6 +1081,11 @@ void free_irq(unsigned int irq, void *dev_id) if (!desc) return; +#ifdef CONFIG_SMP + if (WARN_ON(desc->affinity_notify)) + desc->affinity_notify = NULL; +#endif + chip_bus_lock(desc); kfree(__free_irq(irq, dev_id)); chip_bus_sync_unlock(desc); diff --git a/lib/Kconfig b/lib/Kconfig index 0ee67e0..8334342 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -201,6 +201,10 @@ config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS depends on EXPERIMENTAL && BROKEN +config CPU_RMAP + bool + depends on SMP + # # Netlink attribute parsing support is select'ed if needed # diff --git a/lib/Makefile b/lib/Makefile index cbb774f..b73ba01 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -110,6 +110,8 @@ obj-$(CONFIG_ATOMIC64_SELFTEST) += atomic64_test.o obj-$(CONFIG_AVERAGE) += average.o +obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o + hostprogs-y := gen_crc32table clean-files := crc32table.h diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c new file mode 100644 index 0000000..987acfa --- /dev/null +++ b/lib/cpu_rmap.c @@ -0,0 +1,269 @@ +/* + * cpu_rmap.c: CPU affinity reverse-map support + * 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. + */ + +#include <linux/cpu_rmap.h> +#ifdef CONFIG_GENERIC_HARDIRQS +#include <linux/interrupt.h> +#endif +#include <linux/module.h> + +/* + * These functions maintain a mapping from CPUs to some ordered set of + * objects with CPU affinities. This can be seen as a reverse-map of + * CPU affinity. However, we do not assume that the object affinities + * cover all CPUs in the system. For those CPUs not directly covered + * by object affinities, we attempt to find a nearest object based on + * CPU topology. + */ + +/** + * alloc_cpu_rmap - allocate CPU affinity reverse-map + * @size: Number of objects to be mapped + * @flags: Allocation flags e.g. %GFP_KERNEL + */ +struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags) +{ + struct cpu_rmap *rmap; + unsigned int cpu; + size_t obj_offset; + + /* This is a silly number of objects, and we use u16 indices. */ + if (size > 0xffff) + return NULL; + + /* Offset of object pointer array from base structure */ + obj_offset = ALIGN(offsetof(struct cpu_rmap, near[nr_cpu_ids]), + sizeof(void *)); + + rmap = kzalloc(obj_offset + size * sizeof(rmap->obj[0]), flags); + if (!rmap) + return NULL; + + rmap->obj = (void **)((char *)rmap + obj_offset); + + /* Initially assign CPUs to objects on a rota, since we have + * no idea where the objects are. Use infinite distance, so + * any object with known distance is preferable. Include the + * CPUs that are not present/online, since we definitely want + * any newly-hotplugged CPUs to have some object assigned. + */ + for_each_possible_cpu(cpu) { + rmap->near[cpu].index = cpu % size; + rmap->near[cpu].dist = CPU_RMAP_DIST_INF; + } + + rmap->size = size; + return rmap; +} +EXPORT_SYMBOL(alloc_cpu_rmap); + +/* Reevaluate nearest object for given CPU, comparing with the given + * neighbours at the given distance. + */ +static bool cpu_rmap_copy_neigh(struct cpu_rmap *rmap, unsigned int cpu, + const struct cpumask *mask, u16 dist) +{ + int neigh; + + for_each_cpu(neigh, mask) { + if (rmap->near[cpu].dist > dist && + rmap->near[neigh].dist <= dist) { + rmap->near[cpu].index = rmap->near[neigh].index; + rmap->near[cpu].dist = dist; + return true; + } + } + return false; +} + +#ifdef DEBUG +static void debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix) +{ + unsigned index; + unsigned int cpu; + + pr_info("cpu_rmap %p, %s:\n", rmap, prefix); + + for_each_possible_cpu(cpu) { + index = rmap->near[cpu].index; + pr_info("cpu %d -> obj %u (distance %u)\n", + cpu, index, rmap->near[cpu].dist); + } +} +#else +static inline void +debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix) +{ +} +#endif + +/** + * cpu_rmap_add - add object to a rmap + * @rmap: CPU rmap allocated with alloc_cpu_rmap() + * @obj: Object to add to rmap + * + * Return index of object. + */ +int cpu_rmap_add(struct cpu_rmap *rmap, void *obj) +{ + u16 index; + + BUG_ON(rmap->used >= rmap->size); + index = rmap->used++; + rmap->obj[index] = obj; + return index; +} +EXPORT_SYMBOL(cpu_rmap_add); + +/** + * cpu_rmap_update - update CPU rmap following a change of object affinity + * @rmap: CPU rmap to update + * @index: Index of object whose affinity changed + * @affinity: New CPU affinity of object + */ +int cpu_rmap_update(struct cpu_rmap *rmap, u16 index, + const struct cpumask *affinity) +{ + cpumask_var_t update_mask; + unsigned int cpu; + + if (unlikely(!zalloc_cpumask_var(&update_mask, GFP_KERNEL))) + return -ENOMEM; + + /* Invalidate distance for all CPUs for which this used to be + * the nearest object. Mark those CPUs for update. + */ + for_each_online_cpu(cpu) { + if (rmap->near[cpu].index == index) { + rmap->near[cpu].dist = CPU_RMAP_DIST_INF; + cpumask_set_cpu(cpu, update_mask); + } + } + + debug_print_rmap(rmap, "after invalidating old distances"); + + /* Set distance to 0 for all CPUs in the new affinity mask. + * Mark all CPUs within their NUMA nodes for update. + */ + for_each_cpu(cpu, affinity) { + rmap->near[cpu].index = index; + rmap->near[cpu].dist = 0; + cpumask_or(update_mask, update_mask, + cpumask_of_node(cpu_to_node(cpu))); + } + + debug_print_rmap(rmap, "after updating neighbours"); + + /* Update distances based on topology */ + for_each_cpu(cpu, update_mask) { + if (cpu_rmap_copy_neigh(rmap, cpu, + topology_thread_cpumask(cpu), 1)) + continue; + if (cpu_rmap_copy_neigh(rmap, cpu, + topology_core_cpumask(cpu), 2)) + continue; + if (cpu_rmap_copy_neigh(rmap, cpu, + cpumask_of_node(cpu_to_node(cpu)), 3)) + continue; + /* We could continue into NUMA node distances, but for now + * we give up. + */ + } + + debug_print_rmap(rmap, "after copying neighbours"); + + free_cpumask_var(update_mask); + return 0; +} +EXPORT_SYMBOL(cpu_rmap_update); + +#ifdef CONFIG_GENERIC_HARDIRQS + +/* Glue between IRQ affinity notifiers and CPU rmaps */ + +struct irq_glue { + struct irq_affinity_notify notify; + struct cpu_rmap *rmap; + u16 index; +}; + +/** + * free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs + * @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL + * + * Must be called in process context, before freeing the IRQs, and + * without holding any locks required by global workqueue items. + */ +void free_irq_cpu_rmap(struct cpu_rmap *rmap) +{ + struct irq_glue *glue; + u16 index; + + if (!rmap) + return; + + for (index = 0; index < rmap->used; index++) { + glue = rmap->obj[index]; + irq_set_affinity_notifier(glue->notify.irq, NULL); + } + irq_run_affinity_notifiers(); + + kfree(rmap); +} +EXPORT_SYMBOL(free_irq_cpu_rmap); + +static void +irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask) +{ + struct irq_glue *glue = + container_of(notify, struct irq_glue, notify); + int rc; + + rc = cpu_rmap_update(glue->rmap, glue->index, mask); + if (rc) + pr_warning("irq_cpu_rmap_notify: update failed: %d\n", rc); +} + +static void irq_cpu_rmap_release(struct kref *ref) +{ + struct irq_glue *glue = + container_of(ref, struct irq_glue, notify.kref); + kfree(glue); +} + +/** + * irq_cpu_rmap_add - add an IRQ to a CPU affinity reverse-map + * @rmap: The reverse-map + * @irq: The IRQ number + * + * This adds an IRQ affinity notifier that will update the reverse-map + * automatically. + * + * Must be called in process context, after the IRQ is allocated but + * before it is bound with request_irq(). + */ +int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq) +{ + struct irq_glue *glue = kzalloc(sizeof(*glue), GFP_KERNEL); + int rc; + + if (!glue) + return -ENOMEM; + glue->notify.notify = irq_cpu_rmap_notify; + glue->notify.release = irq_cpu_rmap_release; + glue->rmap = rmap; + glue->index = cpu_rmap_add(rmap, glue); + rc = irq_set_affinity_notifier(irq, &glue->notify); + if (rc) + kfree(glue); + return rc; +} +EXPORT_SYMBOL(irq_cpu_rmap_add); + +#endif /* CONFIG_GENERIC_HARDIRQS */ diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 6e64f7c..7850412 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -327,7 +327,7 @@ static void vlan_sync_address(struct net_device *dev, static void vlan_transfer_features(struct net_device *dev, struct net_device *vlandev) { - unsigned long old_features = vlandev->features; + u32 old_features = vlandev->features; vlandev->features &= ~dev->vlan_features; vlandev->features |= dev->features & dev->vlan_features; diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c index 17c5ba7..29a54cc 100644 --- a/net/9p/trans_rdma.c +++ b/net/9p/trans_rdma.c @@ -59,7 +59,6 @@ * safely advertise a maxsize * of 64k */ -#define P9_RDMA_MAX_SGE (P9_RDMA_MAXSIZE >> PAGE_SHIFT) /** * struct p9_trans_rdma - RDMA transport instance * diff --git a/net/Kconfig b/net/Kconfig index 7284062..79cabf1 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -221,6 +221,12 @@ config RPS depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS default y +config RFS_ACCEL + boolean + depends on RPS && GENERIC_HARDIRQS + select CPU_RMAP + default y + config XPS boolean depends on SMP && SYSFS && USE_GENERIC_SMP_HELPERS diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index d9d1e2b..2a6801d 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -365,7 +365,7 @@ int br_min_mtu(const struct net_bridge *br) void br_features_recompute(struct net_bridge *br) { struct net_bridge_port *p; - unsigned long features, mask; + u32 features, mask; features = mask = br->feature_mask; if (list_empty(&br->port_list)) @@ -379,7 +379,7 @@ void br_features_recompute(struct net_bridge *br) } done: - br->dev->features = netdev_fix_features(features, NULL); + br->dev->features = netdev_fix_features(br->dev, features); } /* called with RTNL */ diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 84aac77..9f22898 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -182,7 +182,7 @@ struct net_bridge struct br_cpu_netstats __percpu *stats; spinlock_t hash_lock; struct hlist_head hash[BR_HASH_SIZE]; - unsigned long feature_mask; + u32 feature_mask; #ifdef CONFIG_BRIDGE_NETFILTER struct rtable fake_rtable; bool nf_call_iptables; diff --git a/net/bridge/netfilter/ebt_ip6.c b/net/bridge/netfilter/ebt_ip6.c index 50a46af..2ed0056 100644 --- a/net/bridge/netfilter/ebt_ip6.c +++ b/net/bridge/netfilter/ebt_ip6.c @@ -22,9 +22,15 @@ #include <linux/netfilter_bridge/ebtables.h> #include <linux/netfilter_bridge/ebt_ip6.h> -struct tcpudphdr { - __be16 src; - __be16 dst; +union pkthdr { + struct { + __be16 src; + __be16 dst; + } tcpudphdr; + struct { + u8 type; + u8 code; + } icmphdr; }; static bool @@ -33,8 +39,8 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par) const struct ebt_ip6_info *info = par->matchinfo; const struct ipv6hdr *ih6; struct ipv6hdr _ip6h; - const struct tcpudphdr *pptr; - struct tcpudphdr _ports; + const union pkthdr *pptr; + union pkthdr _pkthdr; ih6 = skb_header_pointer(skb, 0, sizeof(_ip6h), &_ip6h); if (ih6 == NULL) @@ -56,26 +62,34 @@ ebt_ip6_mt(const struct sk_buff *skb, struct xt_action_param *par) return false; if (FWINV(info->protocol != nexthdr, EBT_IP6_PROTO)) return false; - if (!(info->bitmask & EBT_IP6_DPORT) && - !(info->bitmask & EBT_IP6_SPORT)) + if (!(info->bitmask & ( EBT_IP6_DPORT | + EBT_IP6_SPORT | EBT_IP6_ICMP6))) return true; - pptr = skb_header_pointer(skb, offset_ph, sizeof(_ports), - &_ports); + + /* min icmpv6 headersize is 4, so sizeof(_pkthdr) is ok. */ + pptr = skb_header_pointer(skb, offset_ph, sizeof(_pkthdr), + &_pkthdr); if (pptr == NULL) return false; if (info->bitmask & EBT_IP6_DPORT) { - u32 dst = ntohs(pptr->dst); + u16 dst = ntohs(pptr->tcpudphdr.dst); if (FWINV(dst < info->dport[0] || dst > info->dport[1], EBT_IP6_DPORT)) return false; } if (info->bitmask & EBT_IP6_SPORT) { - u32 src = ntohs(pptr->src); + u16 src = ntohs(pptr->tcpudphdr.src); if (FWINV(src < info->sport[0] || src > info->sport[1], EBT_IP6_SPORT)) return false; } - return true; + if ((info->bitmask & EBT_IP6_ICMP6) && + FWINV(pptr->icmphdr.type < info->icmpv6_type[0] || + pptr->icmphdr.type > info->icmpv6_type[1] || + pptr->icmphdr.code < info->icmpv6_code[0] || + pptr->icmphdr.code > info->icmpv6_code[1], + EBT_IP6_ICMP6)) + return false; } return true; } @@ -103,6 +117,14 @@ static int ebt_ip6_mt_check(const struct xt_mtchk_param *par) return -EINVAL; if (info->bitmask & EBT_IP6_SPORT && info->sport[0] > info->sport[1]) return -EINVAL; + if (info->bitmask & EBT_IP6_ICMP6) { + if ((info->invflags & EBT_IP6_PROTO) || + info->protocol != IPPROTO_ICMPV6) + return -EINVAL; + if (info->icmpv6_type[0] > info->icmpv6_type[1] || + info->icmpv6_code[0] > info->icmpv6_code[1]) + return -EINVAL; + } return 0; } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 16df053..5f1825d 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1764,6 +1764,7 @@ static int compat_table_info(const struct ebt_table_info *info, newinfo->entries_size = size; + xt_compat_init_offsets(AF_INET, info->nentries); return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); } diff --git a/net/caif/cfcnfg.c b/net/caif/cfcnfg.c index c665de7..f1f98d9 100644 --- a/net/caif/cfcnfg.c +++ b/net/caif/cfcnfg.c @@ -23,10 +23,8 @@ #include <asm/atomic.h> #define MAX_PHY_LAYERS 7 -#define PHY_NAME_LEN 20 #define container_obj(layr) container_of(layr, struct cfcnfg, layer) -#define RFM_FRAGMENT_SIZE 4030 /* Information about CAIF physical interfaces held by Config Module in order * to manage physical interfaces diff --git a/net/caif/cfdgml.c b/net/caif/cfdgml.c index d3ed264..27dab26 100644 --- a/net/caif/cfdgml.c +++ b/net/caif/cfdgml.c @@ -18,7 +18,6 @@ #define DGM_CMD_BIT 0x80 #define DGM_FLOW_OFF 0x81 #define DGM_FLOW_ON 0x80 -#define DGM_CTRL_PKT_SIZE 1 #define DGM_MTU 1500 static int cfdgml_receive(struct cflayer *layr, struct cfpkt *pkt); diff --git a/net/caif/cfserl.c b/net/caif/cfserl.c index 9297f7d..8303fe3 100644 --- a/net/caif/cfserl.c +++ b/net/caif/cfserl.c @@ -25,7 +25,6 @@ struct cfserl { spinlock_t sync; bool usestx; }; -#define STXLEN(layr) (layr->usestx ? 1 : 0) static int cfserl_receive(struct cflayer *layr, struct cfpkt *pkt); static int cfserl_transmit(struct cflayer *layr, struct cfpkt *pkt); diff --git a/net/caif/cfutill.c b/net/caif/cfutill.c index efad410..315c0d6 100644 --- a/net/caif/cfutill.c +++ b/net/caif/cfutill.c @@ -20,7 +20,7 @@ #define UTIL_REMOTE_SHUTDOWN 0x82 #define UTIL_FLOW_OFF 0x81 #define UTIL_FLOW_ON 0x80 -#define UTIL_CTRL_PKT_SIZE 1 + static int cfutill_receive(struct cflayer *layr, struct cfpkt *pkt); static int cfutill_transmit(struct cflayer *layr, struct cfpkt *pkt); diff --git a/net/caif/cfveil.c b/net/caif/cfveil.c index 3b425b1..c3b1dec 100644 --- a/net/caif/cfveil.c +++ b/net/caif/cfveil.c @@ -17,7 +17,7 @@ #define VEI_FLOW_OFF 0x81 #define VEI_FLOW_ON 0x80 #define VEI_SET_PIN 0x82 -#define VEI_CTRL_PKT_SIZE 1 + #define container_obj(layr) container_of(layr, struct cfsrvl, layer) static int cfvei_receive(struct cflayer *layr, struct cfpkt *pkt); diff --git a/net/core/dev.c b/net/core/dev.c index 93e44db..9109e26 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -132,6 +132,7 @@ #include <trace/events/skb.h> #include <linux/pci.h> #include <linux/inetdevice.h> +#include <linux/cpu_rmap.h> #include "net-sysfs.h" @@ -1286,7 +1287,7 @@ static int __dev_close(struct net_device *dev) return __dev_close_many(&single); } -int dev_close_many(struct list_head *head) +static int dev_close_many(struct list_head *head) { struct net_device *dev, *tmp; LIST_HEAD(tmp_list); @@ -1594,6 +1595,48 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_unlock(); } +/* netif_setup_tc - Handle tc mappings on real_num_tx_queues change + * @dev: Network device + * @txq: number of queues available + * + * If real_num_tx_queues is changed the tc mappings may no longer be + * valid. To resolve this verify the tc mapping remains valid and if + * not NULL the mapping. With no priorities mapping to this + * offset/count pair it will no longer be used. In the worst case TC0 + * is invalid nothing can be done so disable priority mappings. If is + * expected that drivers will fix this mapping if they can before + * calling netif_set_real_num_tx_queues. + */ +static void netif_setup_tc(struct net_device *dev, unsigned int txq) +{ + int i; + struct netdev_tc_txq *tc = &dev->tc_to_txq[0]; + + /* If TC0 is invalidated disable TC mapping */ + if (tc->offset + tc->count > txq) { + pr_warning("Number of in use tx queues changed " + "invalidating tc mappings. Priority " + "traffic classification disabled!\n"); + dev->num_tc = 0; + return; + } + + /* Invalidated prio to tc mappings set to TC0 */ + for (i = 1; i < TC_BITMASK + 1; i++) { + int q = netdev_get_prio_tc_map(dev, i); + + tc = &dev->tc_to_txq[q]; + if (tc->offset + tc->count > txq) { + pr_warning("Number of in use tx queues " + "changed. Priority %i to tc " + "mapping %i is no longer valid " + "setting map to 0\n", + i, q); + netdev_set_prio_tc_map(dev, i, 0); + } + } +} + /* * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. @@ -1613,6 +1656,9 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (rc) return rc; + if (dev->num_tc) + netif_setup_tc(dev, txq); + if (txq < dev->real_num_tx_queues) qdisc_reset_all_tx_gt(dev, txq); } @@ -1812,7 +1858,7 @@ EXPORT_SYMBOL(skb_checksum_help); * It may return NULL if the skb requires no segmentation. This is * only possible when GSO is used for verifying header integrity. */ -struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) +struct sk_buff *skb_gso_segment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_type *ptype; @@ -2000,7 +2046,7 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol) protocol == htons(ETH_P_FCOE))); } -static int harmonize_features(struct sk_buff *skb, __be16 protocol, int features) +static u32 harmonize_features(struct sk_buff *skb, __be16 protocol, u32 features) { if (!can_checksum_protocol(features, protocol)) { features &= ~NETIF_F_ALL_CSUM; @@ -2012,10 +2058,10 @@ static int harmonize_features(struct sk_buff *skb, __be16 protocol, int features return features; } -int netif_skb_features(struct sk_buff *skb) +u32 netif_skb_features(struct sk_buff *skb) { __be16 protocol = skb->protocol; - int features = skb->dev->features; + u32 features = skb->dev->features; if (protocol == htons(ETH_P_8021Q)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; @@ -2060,7 +2106,7 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int rc = NETDEV_TX_OK; if (likely(!skb->next)) { - int features; + u32 features; /* * If device doesnt need skb->dst, release it right now while @@ -2162,6 +2208,8 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, unsigned int num_tx_queues) { u32 hash; + u16 qoffset = 0; + u16 qcount = num_tx_queues; if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); @@ -2170,13 +2218,19 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, return hash; } + if (dev->num_tc) { + u8 tc = netdev_get_prio_tc_map(dev, skb->priority); + qoffset = dev->tc_to_txq[tc].offset; + qcount = dev->tc_to_txq[tc].count; + } + if (skb->sk && skb->sk->sk_hash) hash = skb->sk->sk_hash; else hash = (__force u16) skb->protocol ^ skb->rxhash; hash = jhash_1word(hash, hashrnd); - return (u16) (((u64) hash * num_tx_queues) >> 32); + return (u16) (((u64) hash * qcount) >> 32) + qoffset; } EXPORT_SYMBOL(__skb_tx_hash); @@ -2273,15 +2327,18 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct netdev_queue *txq) { spinlock_t *root_lock = qdisc_lock(q); - bool contended = qdisc_is_running(q); + bool contended; int rc; + qdisc_skb_cb(skb)->pkt_len = skb->len; + qdisc_calculate_pkt_len(skb, q); /* * Heuristic to force contended enqueues to serialize on a * separate lock before trying to get qdisc main lock. * This permits __QDISC_STATE_RUNNING owner to get the lock more often * and dequeue packets faster. */ + contended = qdisc_is_running(q); if (unlikely(contended)) spin_lock(&q->busylock); @@ -2299,7 +2356,6 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE)) skb_dst_force(skb); - qdisc_skb_cb(skb)->pkt_len = skb->len; qdisc_bstats_update(q, skb); if (sch_direct_xmit(skb, q, dev, txq, root_lock)) { @@ -2314,7 +2370,7 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, rc = NET_XMIT_SUCCESS; } else { skb_dst_force(skb); - rc = qdisc_enqueue_root(skb, q); + rc = q->enqueue(skb, q) & NET_XMIT_MASK; if (qdisc_run_begin(q)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -2533,6 +2589,53 @@ EXPORT_SYMBOL(__skb_get_rxhash); struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; EXPORT_SYMBOL(rps_sock_flow_table); +static struct rps_dev_flow * +set_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow *rflow, u16 next_cpu) +{ + u16 tcpu; + + tcpu = rflow->cpu = next_cpu; + if (tcpu != RPS_NO_CPU) { +#ifdef CONFIG_RFS_ACCEL + struct netdev_rx_queue *rxqueue; + struct rps_dev_flow_table *flow_table; + struct rps_dev_flow *old_rflow; + u32 flow_id; + u16 rxq_index; + int rc; + + /* Should we steer this flow to a different hardware queue? */ + if (!skb_rx_queue_recorded(skb) || !dev->rx_cpu_rmap) + goto out; + rxq_index = cpu_rmap_lookup_index(dev->rx_cpu_rmap, next_cpu); + if (rxq_index == skb_get_rx_queue(skb)) + goto out; + + rxqueue = dev->_rx + rxq_index; + flow_table = rcu_dereference(rxqueue->rps_flow_table); + if (!flow_table) + goto out; + flow_id = skb->rxhash & flow_table->mask; + rc = dev->netdev_ops->ndo_rx_flow_steer(dev, skb, + rxq_index, flow_id); + if (rc < 0) + goto out; + old_rflow = rflow; + rflow = &flow_table->flows[flow_id]; + rflow->cpu = next_cpu; + rflow->filter = rc; + if (old_rflow->filter == rflow->filter) + old_rflow->filter = RPS_NO_FILTER; + out: +#endif + rflow->last_qtail = + per_cpu(softnet_data, tcpu).input_queue_head; + } + + return rflow; +} + /* * get_rps_cpu is called from netif_receive_skb and returns the target * CPU from the RPS map of the receiving queue for a given skb. @@ -2603,12 +2706,9 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, if (unlikely(tcpu != next_cpu) && (tcpu == RPS_NO_CPU || !cpu_online(tcpu) || ((int)(per_cpu(softnet_data, tcpu).input_queue_head - - rflow->last_qtail)) >= 0)) { - tcpu = rflow->cpu = next_cpu; - if (tcpu != RPS_NO_CPU) - rflow->last_qtail = per_cpu(softnet_data, - tcpu).input_queue_head; - } + rflow->last_qtail)) >= 0)) + rflow = set_rps_cpu(dev, skb, rflow, next_cpu); + if (tcpu != RPS_NO_CPU && cpu_online(tcpu)) { *rflowp = rflow; cpu = tcpu; @@ -2629,6 +2729,46 @@ done: return cpu; } +#ifdef CONFIG_RFS_ACCEL + +/** + * rps_may_expire_flow - check whether an RFS hardware filter may be removed + * @dev: Device on which the filter was set + * @rxq_index: RX queue index + * @flow_id: Flow ID passed to ndo_rx_flow_steer() + * @filter_id: Filter ID returned by ndo_rx_flow_steer() + * + * Drivers that implement ndo_rx_flow_steer() should periodically call + * this function for each installed filter and remove the filters for + * which it returns %true. + */ +bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, + u32 flow_id, u16 filter_id) +{ + struct netdev_rx_queue *rxqueue = dev->_rx + rxq_index; + struct rps_dev_flow_table *flow_table; + struct rps_dev_flow *rflow; + bool expire = true; + int cpu; + + rcu_read_lock(); + flow_table = rcu_dereference(rxqueue->rps_flow_table); + if (flow_table && flow_id <= flow_table->mask) { + rflow = &flow_table->flows[flow_id]; + cpu = ACCESS_ONCE(rflow->cpu); + if (rflow->filter == filter_id && cpu != RPS_NO_CPU && + ((int)(per_cpu(softnet_data, cpu).input_queue_head - + rflow->last_qtail) < + (int)(10 * flow_table->mask))) + expire = false; + } + rcu_read_unlock(); + return expire; +} +EXPORT_SYMBOL(rps_may_expire_flow); + +#endif /* CONFIG_RFS_ACCEL */ + /* Called from hardirq (IPI) context */ static void rps_trigger_softirq(void *data) { @@ -3912,12 +4052,15 @@ void *dev_seq_start(struct seq_file *seq, loff_t *pos) void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct net_device *dev = (v == SEQ_START_TOKEN) ? - first_net_device(seq_file_net(seq)) : - next_net_device((struct net_device *)v); + struct net_device *dev = v; + + if (v == SEQ_START_TOKEN) + dev = first_net_device_rcu(seq_file_net(seq)); + else + dev = next_net_device_rcu(dev); ++*pos; - return rcu_dereference(dev); + return dev; } void dev_seq_stop(struct seq_file *seq, void *v) @@ -4574,6 +4717,17 @@ int dev_set_mtu(struct net_device *dev, int new_mtu) EXPORT_SYMBOL(dev_set_mtu); /** + * dev_set_group - Change group this device belongs to + * @dev: device + * @new_group: group this device should belong to + */ +void dev_set_group(struct net_device *dev, int new_group) +{ + dev->group = new_group; +} +EXPORT_SYMBOL(dev_set_group); + +/** * dev_set_mac_address - Change Media Access Control Address * @dev: device * @sa: new address @@ -5063,41 +5217,49 @@ static void rollback_registered(struct net_device *dev) rollback_registered_many(&single); } -unsigned long netdev_fix_features(unsigned long features, const char *name) +u32 netdev_fix_features(struct net_device *dev, u32 features) { + /* Fix illegal checksum combinations */ + if ((features & NETIF_F_HW_CSUM) && + (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { + netdev_info(dev, "mixed HW and IP checksum settings.\n"); + features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); + } + + if ((features & NETIF_F_NO_CSUM) && + (features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { + netdev_info(dev, "mixed no checksumming and other settings.\n"); + features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM); + } + /* Fix illegal SG+CSUM combinations. */ if ((features & NETIF_F_SG) && !(features & NETIF_F_ALL_CSUM)) { - if (name) - printk(KERN_NOTICE "%s: Dropping NETIF_F_SG since no " - "checksum feature.\n", name); + netdev_info(dev, + "Dropping NETIF_F_SG since no checksum feature.\n"); features &= ~NETIF_F_SG; } /* TSO requires that SG is present as well. */ if ((features & NETIF_F_TSO) && !(features & NETIF_F_SG)) { - if (name) - printk(KERN_NOTICE "%s: Dropping NETIF_F_TSO since no " - "SG feature.\n", name); + netdev_info(dev, "Dropping NETIF_F_TSO since no SG feature.\n"); features &= ~NETIF_F_TSO; } + /* UFO needs SG and checksumming */ if (features & NETIF_F_UFO) { /* maybe split UFO into V4 and V6? */ if (!((features & NETIF_F_GEN_CSUM) || (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - if (name) - printk(KERN_ERR "%s: Dropping NETIF_F_UFO " - "since no checksum offload features.\n", - name); + netdev_info(dev, + "Dropping NETIF_F_UFO since no checksum offload features.\n"); features &= ~NETIF_F_UFO; } if (!(features & NETIF_F_SG)) { - if (name) - printk(KERN_ERR "%s: Dropping NETIF_F_UFO " - "since no NETIF_F_SG feature.\n", name); + netdev_info(dev, + "Dropping NETIF_F_UFO since no NETIF_F_SG feature.\n"); features &= ~NETIF_F_UFO; } } @@ -5240,22 +5402,7 @@ int register_netdevice(struct net_device *dev) if (dev->iflink == -1) dev->iflink = dev->ifindex; - /* Fix illegal checksum combinations */ - if ((dev->features & NETIF_F_HW_CSUM) && - (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - printk(KERN_NOTICE "%s: mixed HW and IP checksum settings.\n", - dev->name); - dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); - } - - if ((dev->features & NETIF_F_NO_CSUM) && - (dev->features & (NETIF_F_HW_CSUM|NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { - printk(KERN_NOTICE "%s: mixed no checksumming and other settings.\n", - dev->name); - dev->features &= ~(NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM|NETIF_F_HW_CSUM); - } - - dev->features = netdev_fix_features(dev->features, dev->name); + dev->features = netdev_fix_features(dev, dev->features); /* Enable software GSO if SG is supported. */ if (dev->features & NETIF_F_SG) @@ -5680,6 +5827,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); strcpy(dev->name, name); + dev->group = INIT_NETDEV_GROUP; return dev; free_pcpu: @@ -5990,8 +6138,7 @@ static int dev_cpu_callback(struct notifier_block *nfb, * @one to the master device with current feature set @all. Will not * enable anything that is off in @mask. Returns the new feature set. */ -unsigned long netdev_increment_features(unsigned long all, unsigned long one, - unsigned long mask) +u32 netdev_increment_features(u32 all, u32 one, u32 mask) { /* If device needs checksumming, downgrade to it. */ if (all & NETIF_F_NO_CSUM && !(one & NETIF_F_NO_CSUM)) diff --git a/net/core/dst.c b/net/core/dst.c index b99c7c7..c1674fd 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -164,6 +164,8 @@ int dst_discard(struct sk_buff *skb) } EXPORT_SYMBOL(dst_discard); +const u32 dst_default_metrics[RTAX_MAX]; + void *dst_alloc(struct dst_ops *ops) { struct dst_entry *dst; @@ -180,6 +182,7 @@ void *dst_alloc(struct dst_ops *ops) dst->lastuse = jiffies; dst->path = dst; dst->input = dst->output = dst_discard; + dst_init_metrics(dst, dst_default_metrics, true); #if RT_CACHE_DEBUG >= 2 atomic_inc(&dst_total); #endif @@ -282,6 +285,42 @@ void dst_release(struct dst_entry *dst) } EXPORT_SYMBOL(dst_release); +u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old) +{ + u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC); + + if (p) { + u32 *old_p = __DST_METRICS_PTR(old); + unsigned long prev, new; + + memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + kfree(p); + p = __DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; + } + } + return p; +} +EXPORT_SYMBOL(dst_cow_metrics_generic); + +/* Caller asserts that dst_metrics_read_only(dst) is false. */ +void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old) +{ + unsigned long prev, new; + + new = (unsigned long) dst_default_metrics; + prev = cmpxchg(&dst->_metrics, old, new); + if (prev == old) + kfree(__DST_METRICS_PTR(old)); +} +EXPORT_SYMBOL(__dst_destroy_metrics_generic); + /** * skb_dst_set_noref - sets skb dst, without a reference * @skb: buffer diff --git a/net/core/ethtool.c b/net/core/ethtool.c index ff23029..5984ee0 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1458,7 +1458,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) void __user *useraddr = ifr->ifr_data; u32 ethcmd; int rc; - unsigned long old_features; + u32 old_features; if (!dev || !netif_device_present(dev)) return -ENODEV; diff --git a/net/core/filter.c b/net/core/filter.c index afc5837..232b187 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -142,14 +142,14 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) if (err) return err; - rcu_read_lock_bh(); - filter = rcu_dereference_bh(sk->sk_filter); + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); if (filter) { unsigned int pkt_len = sk_run_filter(skb, filter->insns); err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } - rcu_read_unlock_bh(); + rcu_read_unlock(); return err; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 60a9029..799f06e 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -316,7 +316,7 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries) { size_t size = entries * sizeof(struct neighbour *); struct neigh_hash_table *ret; - struct neighbour **buckets; + struct neighbour __rcu **buckets; ret = kmalloc(sizeof(*ret), GFP_ATOMIC); if (!ret) @@ -324,14 +324,14 @@ static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries) if (size <= PAGE_SIZE) buckets = kzalloc(size, GFP_ATOMIC); else - buckets = (struct neighbour **) + buckets = (struct neighbour __rcu **) __get_free_pages(GFP_ATOMIC | __GFP_ZERO, get_order(size)); if (!buckets) { kfree(ret); return NULL; } - rcu_assign_pointer(ret->hash_buckets, buckets); + ret->hash_buckets = buckets; ret->hash_mask = entries - 1; get_random_bytes(&ret->hash_rnd, sizeof(ret->hash_rnd)); return ret; @@ -343,7 +343,7 @@ static void neigh_hash_free_rcu(struct rcu_head *head) struct neigh_hash_table, rcu); size_t size = (nht->hash_mask + 1) * sizeof(struct neighbour *); - struct neighbour **buckets = nht->hash_buckets; + struct neighbour __rcu **buckets = nht->hash_buckets; if (size <= PAGE_SIZE) kfree(buckets); @@ -1540,7 +1540,7 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) panic("cannot create neighbour proc dir entry"); #endif - tbl->nht = neigh_hash_alloc(8); + RCU_INIT_POINTER(tbl->nht, neigh_hash_alloc(8)); phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *); tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL); @@ -1602,7 +1602,8 @@ int neigh_table_clear(struct neigh_table *tbl) } write_unlock(&neigh_tbl_lock); - call_rcu(&tbl->nht->rcu, neigh_hash_free_rcu); + call_rcu(&rcu_dereference_protected(tbl->nht, 1)->rcu, + neigh_hash_free_rcu); tbl->nht = NULL; kfree(tbl->phash_buckets); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index e23c01b..2e4a393 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -99,7 +99,7 @@ NETDEVICE_SHOW(addr_assign_type, fmt_dec); NETDEVICE_SHOW(addr_len, fmt_dec); NETDEVICE_SHOW(iflink, fmt_dec); NETDEVICE_SHOW(ifindex, fmt_dec); -NETDEVICE_SHOW(features, fmt_long_hex); +NETDEVICE_SHOW(features, fmt_hex); NETDEVICE_SHOW(type, fmt_dec); NETDEVICE_SHOW(link_mode, fmt_dec); @@ -295,6 +295,20 @@ static ssize_t show_ifalias(struct device *dev, return ret; } +NETDEVICE_SHOW(group, fmt_dec); + +static int change_group(struct net_device *net, unsigned long new_group) +{ + dev_set_group(net, (int) new_group); + return 0; +} + +static ssize_t store_group(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + return netdev_store(dev, attr, buf, len, change_group); +} + static struct device_attribute net_class_attributes[] = { __ATTR(addr_assign_type, S_IRUGO, show_addr_assign_type, NULL), __ATTR(addr_len, S_IRUGO, show_addr_len, NULL), @@ -316,6 +330,7 @@ static struct device_attribute net_class_attributes[] = { __ATTR(flags, S_IRUGO | S_IWUSR, show_flags, store_flags), __ATTR(tx_queue_len, S_IRUGO | S_IWUSR, show_tx_queue_len, store_tx_queue_len), + __ATTR(group, S_IRUGO | S_IWUSR, show_group, store_group), {} }; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index a9e7fc4..d73b77a 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -251,6 +251,7 @@ struct pktgen_dev { int max_pkt_size; /* = ETH_ZLEN; */ int pkt_overhead; /* overhead for MPLS, VLANs, IPSEC etc */ int nfrags; + struct page *page; u64 delay; /* nano-seconds */ __u64 count; /* Default No packets to send */ @@ -1134,6 +1135,10 @@ static ssize_t pktgen_if_write(struct file *file, if (node_possible(value)) { pkt_dev->node = value; sprintf(pg_result, "OK: node=%d", pkt_dev->node); + if (pkt_dev->page) { + put_page(pkt_dev->page); + pkt_dev->page = NULL; + } } else sprintf(pg_result, "ERROR: node not possible"); @@ -2605,6 +2610,90 @@ static inline __be16 build_tci(unsigned int id, unsigned int cfi, return htons(id | (cfi << 12) | (prio << 13)); } +static void pktgen_finalize_skb(struct pktgen_dev *pkt_dev, struct sk_buff *skb, + int datalen) +{ + struct timeval timestamp; + struct pktgen_hdr *pgh; + + pgh = (struct pktgen_hdr *)skb_put(skb, sizeof(*pgh)); + datalen -= sizeof(*pgh); + + if (pkt_dev->nfrags <= 0) { + pgh = (struct pktgen_hdr *)skb_put(skb, datalen); + memset(pgh + 1, 0, datalen); + } else { + int frags = pkt_dev->nfrags; + int i, len; + + + if (frags > MAX_SKB_FRAGS) + frags = MAX_SKB_FRAGS; + len = datalen - frags * PAGE_SIZE; + if (len > 0) { + memset(skb_put(skb, len), 0, len); + datalen = frags * PAGE_SIZE; + } + + i = 0; + while (datalen > 0) { + if (unlikely(!pkt_dev->page)) { + int node = numa_node_id(); + + if (pkt_dev->node >= 0 && (pkt_dev->flags & F_NODE)) + node = pkt_dev->node; + pkt_dev->page = alloc_pages_node(node, GFP_KERNEL | __GFP_ZERO, 0); + if (!pkt_dev->page) + break; + } + skb_shinfo(skb)->frags[i].page = pkt_dev->page; + get_page(pkt_dev->page); + skb_shinfo(skb)->frags[i].page_offset = 0; + skb_shinfo(skb)->frags[i].size = + (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); + datalen -= skb_shinfo(skb)->frags[i].size; + skb->len += skb_shinfo(skb)->frags[i].size; + skb->data_len += skb_shinfo(skb)->frags[i].size; + i++; + skb_shinfo(skb)->nr_frags = i; + } + + while (i < frags) { + int rem; + + if (i == 0) + break; + + rem = skb_shinfo(skb)->frags[i - 1].size / 2; + if (rem == 0) + break; + + skb_shinfo(skb)->frags[i - 1].size -= rem; + + skb_shinfo(skb)->frags[i] = + skb_shinfo(skb)->frags[i - 1]; + get_page(skb_shinfo(skb)->frags[i].page); + skb_shinfo(skb)->frags[i].page = + skb_shinfo(skb)->frags[i - 1].page; + skb_shinfo(skb)->frags[i].page_offset += + skb_shinfo(skb)->frags[i - 1].size; + skb_shinfo(skb)->frags[i].size = rem; + i++; + skb_shinfo(skb)->nr_frags = i; + } + } + + /* Stamp the time, and sequence number, + * convert them to network byte order + */ + pgh->pgh_magic = htonl(PKTGEN_MAGIC); + pgh->seq_num = htonl(pkt_dev->seq_num); + + do_gettimeofday(×tamp); + pgh->tv_sec = htonl(timestamp.tv_sec); + pgh->tv_usec = htonl(timestamp.tv_usec); +} + static struct sk_buff *fill_packet_ipv4(struct net_device *odev, struct pktgen_dev *pkt_dev) { @@ -2613,7 +2702,6 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, struct udphdr *udph; int datalen, iplen; struct iphdr *iph; - struct pktgen_hdr *pgh = NULL; __be16 protocol = htons(ETH_P_IP); __be32 *mpls; __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ @@ -2729,76 +2817,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, pkt_dev->pkt_overhead); skb->dev = odev; skb->pkt_type = PACKET_HOST; - - if (pkt_dev->nfrags <= 0) { - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); - memset(pgh + 1, 0, datalen - sizeof(struct pktgen_hdr)); - } else { - int frags = pkt_dev->nfrags; - int i, len; - - pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8); - - if (frags > MAX_SKB_FRAGS) - frags = MAX_SKB_FRAGS; - if (datalen > frags * PAGE_SIZE) { - len = datalen - frags * PAGE_SIZE; - memset(skb_put(skb, len), 0, len); - datalen = frags * PAGE_SIZE; - } - - i = 0; - while (datalen > 0) { - struct page *page = alloc_pages(GFP_KERNEL | __GFP_ZERO, 0); - skb_shinfo(skb)->frags[i].page = page; - skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); - datalen -= skb_shinfo(skb)->frags[i].size; - skb->len += skb_shinfo(skb)->frags[i].size; - skb->data_len += skb_shinfo(skb)->frags[i].size; - i++; - skb_shinfo(skb)->nr_frags = i; - } - - while (i < frags) { - int rem; - - if (i == 0) - break; - - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; - - skb_shinfo(skb)->frags[i - 1].size -= rem; - - skb_shinfo(skb)->frags[i] = - skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = - skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += - skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; - } - } - - /* Stamp the time, and sequence number, - * convert them to network byte order - */ - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); - - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } + pktgen_finalize_skb(pkt_dev, skb, datalen); #ifdef CONFIG_XFRM if (!process_ipsec(pkt_dev, skb, protocol)) @@ -2980,7 +2999,6 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, struct udphdr *udph; int datalen; struct ipv6hdr *iph; - struct pktgen_hdr *pgh = NULL; __be16 protocol = htons(ETH_P_IPV6); __be32 *mpls; __be16 *vlan_tci = NULL; /* Encapsulates priority and VLAN ID */ @@ -3083,75 +3101,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb->dev = odev; skb->pkt_type = PACKET_HOST; - if (pkt_dev->nfrags <= 0) - pgh = (struct pktgen_hdr *)skb_put(skb, datalen); - else { - int frags = pkt_dev->nfrags; - int i; - - pgh = (struct pktgen_hdr *)(((char *)(udph)) + 8); - - if (frags > MAX_SKB_FRAGS) - frags = MAX_SKB_FRAGS; - if (datalen > frags * PAGE_SIZE) { - skb_put(skb, datalen - frags * PAGE_SIZE); - datalen = frags * PAGE_SIZE; - } - - i = 0; - while (datalen > 0) { - struct page *page = alloc_pages(GFP_KERNEL, 0); - skb_shinfo(skb)->frags[i].page = page; - skb_shinfo(skb)->frags[i].page_offset = 0; - skb_shinfo(skb)->frags[i].size = - (datalen < PAGE_SIZE ? datalen : PAGE_SIZE); - datalen -= skb_shinfo(skb)->frags[i].size; - skb->len += skb_shinfo(skb)->frags[i].size; - skb->data_len += skb_shinfo(skb)->frags[i].size; - i++; - skb_shinfo(skb)->nr_frags = i; - } - - while (i < frags) { - int rem; - - if (i == 0) - break; - - rem = skb_shinfo(skb)->frags[i - 1].size / 2; - if (rem == 0) - break; - - skb_shinfo(skb)->frags[i - 1].size -= rem; - - skb_shinfo(skb)->frags[i] = - skb_shinfo(skb)->frags[i - 1]; - get_page(skb_shinfo(skb)->frags[i].page); - skb_shinfo(skb)->frags[i].page = - skb_shinfo(skb)->frags[i - 1].page; - skb_shinfo(skb)->frags[i].page_offset += - skb_shinfo(skb)->frags[i - 1].size; - skb_shinfo(skb)->frags[i].size = rem; - i++; - skb_shinfo(skb)->nr_frags = i; - } - } - - /* Stamp the time, and sequence number, - * convert them to network byte order - * should we update cloned packets too ? - */ - if (pgh) { - struct timeval timestamp; - - pgh->pgh_magic = htonl(PKTGEN_MAGIC); - pgh->seq_num = htonl(pkt_dev->seq_num); - - do_gettimeofday(×tamp); - pgh->tv_sec = htonl(timestamp.tv_sec); - pgh->tv_usec = htonl(timestamp.tv_usec); - } - /* pkt_dev->seq_num++; FF: you really mean this? */ + pktgen_finalize_skb(pkt_dev, skb, datalen); return skb; } @@ -3884,6 +3834,8 @@ static int pktgen_remove_device(struct pktgen_thread *t, free_SAs(pkt_dev); #endif vfree(pkt_dev->flows); + if (pkt_dev->page) + put_page(pkt_dev->page); kfree(pkt_dev); return 0; } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 2d65c6b..da0fe45 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -868,6 +868,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, netif_running(dev) ? dev->operstate : IF_OPER_DOWN); NLA_PUT_U8(skb, IFLA_LINKMODE, dev->link_mode); NLA_PUT_U32(skb, IFLA_MTU, dev->mtu); + NLA_PUT_U32(skb, IFLA_GROUP, dev->group); if (dev->ifindex != dev->iflink) NLA_PUT_U32(skb, IFLA_LINK, dev->iflink); @@ -1264,6 +1265,11 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, modified = 1; } + if (tb[IFLA_GROUP]) { + dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); + modified = 1; + } + /* * Interface selected by interface index but interface * name provided implies that a name change has been @@ -1541,6 +1547,8 @@ struct net_device *rtnl_create_link(struct net *src_net, struct net *net, set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE])); if (tb[IFLA_LINKMODE]) dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]); + if (tb[IFLA_GROUP]) + dev_set_group(dev, nla_get_u32(tb[IFLA_GROUP])); return dev; @@ -1551,6 +1559,24 @@ err: } EXPORT_SYMBOL(rtnl_create_link); +static int rtnl_group_changelink(struct net *net, int group, + struct ifinfomsg *ifm, + struct nlattr **tb) +{ + struct net_device *dev; + int err; + + for_each_netdev(net, dev) { + if (dev->group == group) { + err = do_setlink(dev, ifm, tb, NULL, 0); + if (err < 0) + return err; + } + } + + return 0; +} + static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); @@ -1578,10 +1604,12 @@ replay: ifm = nlmsg_data(nlh); if (ifm->ifi_index > 0) dev = __dev_get_by_index(net, ifm->ifi_index); - else if (ifname[0]) - dev = __dev_get_by_name(net, ifname); - else - dev = NULL; + else { + if (ifname[0]) + dev = __dev_get_by_name(net, ifname); + else + dev = NULL; + } err = validate_linkmsg(dev, tb); if (err < 0) @@ -1645,8 +1673,13 @@ replay: return do_setlink(dev, ifm, tb, ifname, modified); } - if (!(nlh->nlmsg_flags & NLM_F_CREATE)) + if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { + if (ifm->ifi_index == 0 && tb[IFLA_GROUP]) + return rtnl_group_changelink(net, + nla_get_u32(tb[IFLA_GROUP]), + ifm, tb); return -ENODEV; + } if (ifm->ifi_index) return -EOPNOTSUPP; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index d883dcc..14cf560 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2498,7 +2498,7 @@ EXPORT_SYMBOL_GPL(skb_pull_rcsum); * a pointer to the first in a list of new skbs for the segments. * In case of error it returns ERR_PTR(err). */ -struct sk_buff *skb_segment(struct sk_buff *skb, int features) +struct sk_buff *skb_segment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = NULL; struct sk_buff *tail = NULL; @@ -2508,7 +2508,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) unsigned int offset = doffset; unsigned int headroom; unsigned int len; - int sg = features & NETIF_F_SG; + int sg = !!(features & NETIF_F_SG); int nfrags = skb_shinfo(skb)->nr_frags; int err = -ENOMEM; int i = 0; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index 5e63636..42c9c62 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -112,6 +112,7 @@ static int dn_dst_gc(struct dst_ops *ops); static struct dst_entry *dn_dst_check(struct dst_entry *, __u32); static unsigned int dn_dst_default_advmss(const struct dst_entry *dst); static unsigned int dn_dst_default_mtu(const struct dst_entry *dst); +static void dn_dst_destroy(struct dst_entry *); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); static void dn_dst_update_pmtu(struct dst_entry *dst, u32 mtu); @@ -133,11 +134,18 @@ static struct dst_ops dn_dst_ops = { .check = dn_dst_check, .default_advmss = dn_dst_default_advmss, .default_mtu = dn_dst_default_mtu, + .cow_metrics = dst_cow_metrics_generic, + .destroy = dn_dst_destroy, .negative_advice = dn_dst_negative_advice, .link_failure = dn_dst_link_failure, .update_pmtu = dn_dst_update_pmtu, }; +static void dn_dst_destroy(struct dst_entry *dst) +{ + dst_destroy_metrics_generic(dst); +} + static __inline__ unsigned dn_hash(__le16 src, __le16 dst) { __u16 tmp = (__u16 __force)(src ^ dst); @@ -814,14 +822,14 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) { struct dn_fib_info *fi = res->fi; struct net_device *dev = rt->dst.dev; + unsigned int mss_metric; struct neighbour *n; - unsigned int metric; if (fi) { if (DN_FIB_RES_GW(*res) && DN_FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) rt->rt_gateway = DN_FIB_RES_GW(*res); - dst_import_metrics(&rt->dst, fi->fib_metrics); + dst_init_metrics(&rt->dst, fi->fib_metrics, true); } rt->rt_type = res->type; @@ -834,10 +842,10 @@ static int dn_rt_set_next_hop(struct dn_route *rt, struct dn_fib_res *res) if (dst_metric(&rt->dst, RTAX_MTU) > rt->dst.dev->mtu) dst_metric_set(&rt->dst, RTAX_MTU, rt->dst.dev->mtu); - metric = dst_metric_raw(&rt->dst, RTAX_ADVMSS); - if (metric) { + mss_metric = dst_metric_raw(&rt->dst, RTAX_ADVMSS); + if (mss_metric) { unsigned int mss = dn_mss_from_pmtu(dev, dst_mtu(&rt->dst)); - if (metric > mss) + if (mss_metric > mss) dst_metric_set(&rt->dst, RTAX_ADVMSS, mss); } return 0; diff --git a/net/decnet/dn_table.c b/net/decnet/dn_table.c index f2abd37..b66600b 100644 --- a/net/decnet/dn_table.c +++ b/net/decnet/dn_table.c @@ -59,7 +59,6 @@ struct dn_hash }; #define dz_key_0(key) ((key).datum = 0) -#define dz_prefix(key,dz) ((key).datum) #define for_nexthops(fi) { int nhsel; const struct dn_fib_nh *nh;\ for(nhsel = 0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++) diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index a5a1050..8949a05 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -140,6 +140,9 @@ config IP_ROUTE_VERBOSE handled by the klogd daemon which is responsible for kernel messages ("man klogd"). +config IP_ROUTE_CLASSID + bool + config IP_PNP bool "IP: kernel level autoconfiguration" help @@ -657,4 +660,3 @@ config TCP_MD5SIG on the Internet. If unsure, say N. - diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 45b89d7..7ceb804 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1231,7 +1231,7 @@ out: return err; } -static struct sk_buff *inet_gso_segment(struct sk_buff *skb, int features) +static struct sk_buff *inet_gso_segment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct iphdr *iph; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 7981a24..9cefe72 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -41,12 +41,12 @@ struct fib4_rule { __be32 srcmask; __be32 dst; __be32 dstmask; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID u32 tclassid; #endif }; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID u32 fib_rules_tclass(struct fib_result *res) { return res->r ? ((struct fib4_rule *) res->r)->tclassid : 0; @@ -165,7 +165,7 @@ static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, if (frh->dst_len) rule4->dst = nla_get_be32(tb[FRA_DST]); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (tb[FRA_FLOW]) rule4->tclassid = nla_get_u32(tb[FRA_FLOW]); #endif @@ -195,7 +195,7 @@ static int fib4_rule_compare(struct fib_rule *rule, struct fib_rule_hdr *frh, if (frh->tos && (rule4->tos != frh->tos)) return 0; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (tb[FRA_FLOW] && (rule4->tclassid != nla_get_u32(tb[FRA_FLOW]))) return 0; #endif @@ -224,7 +224,7 @@ static int fib4_rule_fill(struct fib_rule *rule, struct sk_buff *skb, if (rule4->src_len) NLA_PUT_BE32(skb, FRA_SRC, rule4->src); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (rule4->tclassid) NLA_PUT_U32(skb, FRA_FLOW, rule4->tclassid); #endif diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 12d3dc3..48e93a5 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -152,6 +152,8 @@ static void free_fib_info_rcu(struct rcu_head *head) { struct fib_info *fi = container_of(head, struct fib_info, rcu); + if (fi->fib_metrics != (u32 *) dst_default_metrics) + kfree(fi->fib_metrics); kfree(fi); } @@ -200,7 +202,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) #ifdef CONFIG_IP_ROUTE_MULTIPATH nh->nh_weight != onh->nh_weight || #endif -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid != onh->nh_tclassid || #endif ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_F_DEAD)) @@ -422,7 +424,7 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, nla = nla_find(attrs, attrlen, RTA_GATEWAY); nexthop_nh->nh_gw = nla ? nla_get_be32(nla) : 0; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID nla = nla_find(attrs, attrlen, RTA_FLOW); nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0; #endif @@ -476,7 +478,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) nla = nla_find(attrs, attrlen, RTA_GATEWAY); if (nla && nla_get_be32(nla) != nh->nh_gw) return 1; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID nla = nla_find(attrs, attrlen, RTA_FLOW); if (nla && nla_get_u32(nla) != nh->nh_tclassid) return 1; @@ -742,6 +744,12 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); if (fi == NULL) goto failure; + if (cfg->fc_mx) { + fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); + if (!fi->fib_metrics) + goto failure; + } else + fi->fib_metrics = (u32 *) dst_default_metrics; fib_info_cnt++; fi->fib_net = hold_net(net); @@ -779,7 +787,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto err_inval; if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw) goto err_inval; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow) goto err_inval; #endif @@ -792,7 +800,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg) nh->nh_oif = cfg->fc_oif; nh->nh_gw = cfg->fc_gw; nh->nh_flags = cfg->fc_flags; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid = cfg->fc_flow; #endif #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -1002,7 +1010,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, if (fi->fib_nh->nh_oif) NLA_PUT_U32(skb, RTA_OIF, fi->fib_nh->nh_oif); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (fi->fib_nh[0].nh_tclassid) NLA_PUT_U32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid); #endif @@ -1027,7 +1035,7 @@ int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, if (nh->nh_gw) NLA_PUT_BE32(skb, RTA_GATEWAY, nh->nh_gw); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (nh->nh_tclassid) NLA_PUT_U32(skb, RTA_FLOW, nh->nh_tclassid); #endif diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index a96e656..b6513b1 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -512,6 +512,7 @@ struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) atomic_set(&p->rid, 0); atomic_set(&p->ip_id_count, secure_ip_id(daddr->a4)); p->tcp_ts_stamp = 0; + p->metrics[RTAX_LOCK-1] = INETPEER_METRICS_NEW; INIT_LIST_HEAD(&p->unused); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index d859bcc..d7b2b09 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -340,7 +340,7 @@ static int ip_rcv_finish(struct sk_buff *skb) } } -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (unlikely(skb_dst(skb)->tclassid)) { struct ip_rt_acct *st = this_cpu_ptr(ip_rt_acct); u32 idx = skb_dst(skb)->tclassid; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index babd1a2..f926a31 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -206,8 +206,9 @@ config IP_NF_TARGET_REDIRECT config NF_NAT_SNMP_BASIC tristate "Basic SNMP-ALG support" - depends on NF_NAT + depends on NF_CONNTRACK_SNMP && NF_NAT depends on NETFILTER_ADVANCED + default NF_NAT && NF_CONNTRACK_SNMP ---help--- This module implements an Application Layer Gateway (ALG) for diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index e855fff..e95054c 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -866,6 +866,7 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries[raw_smp_processor_id()]; + xt_compat_init_offsets(NFPROTO_ARP, info->number); xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) @@ -1333,6 +1334,7 @@ static int translate_compat_table(const char *name, duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(NFPROTO_ARP); + xt_compat_init_offsets(NFPROTO_ARP, number); /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, total_size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 652efea..ef7d7b9 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1063,6 +1063,7 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries[raw_smp_processor_id()]; + xt_compat_init_offsets(AF_INET, info->number); xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) @@ -1664,6 +1665,7 @@ translate_compat_table(struct net *net, duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(AF_INET); + xt_compat_init_offsets(AF_INET, number); /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, total_size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 1e26a48..403ca57 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -300,13 +300,8 @@ clusterip_tg(struct sk_buff *skb, const struct xt_action_param *par) * that the ->target() function isn't called after ->destroy() */ ct = nf_ct_get(skb, &ctinfo); - if (ct == NULL) { - pr_info("no conntrack!\n"); - /* FIXME: need to drop invalid ones, since replies - * to outgoing connections of other nodes will be - * marked as INVALID */ + if (ct == NULL) return NF_DROP; - } /* special case: ICMP error handling. conntrack distinguishes between * error messages (RELATED) and information requests (see below) */ diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index 72ffc8f..d76d6c9 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -442,8 +442,7 @@ ipt_log_packet(u_int8_t pf, } #endif - /* MAC logging for input path only. */ - if (in && !out) + if (in != NULL) dump_mac_header(m, loginfo, skb); dump_packet(m, loginfo, skb, 0); diff --git a/net/ipv4/netfilter/iptable_mangle.c b/net/ipv4/netfilter/iptable_mangle.c index 294a2a3..aef5d1f 100644 --- a/net/ipv4/netfilter/iptable_mangle.c +++ b/net/ipv4/netfilter/iptable_mangle.c @@ -60,7 +60,7 @@ ipt_mangle_out(struct sk_buff *skb, const struct net_device *out) ret = ipt_do_table(skb, NF_INET_LOCAL_OUT, NULL, out, dev_net(out)->ipv4.iptable_mangle); /* Reroute for ANY change. */ - if (ret != NF_DROP && ret != NF_STOLEN && ret != NF_QUEUE) { + if (ret != NF_DROP && ret != NF_STOLEN) { iph = ip_hdr(skb); if (iph->saddr != saddr || diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 63f60fc..5585980 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -20,6 +20,7 @@ #include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_acct.h> +#include <linux/rculist_nulls.h> struct ct_iter_state { struct seq_net_private p; @@ -35,7 +36,8 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) for (st->bucket = 0; st->bucket < net->ct.htable_size; st->bucket++) { - n = rcu_dereference(net->ct.hash[st->bucket].first); + n = rcu_dereference( + hlist_nulls_first_rcu(&net->ct.hash[st->bucket])); if (!is_a_nulls(n)) return n; } @@ -48,13 +50,14 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct ct_iter_state *st = seq->private; - head = rcu_dereference(head->next); + head = rcu_dereference(hlist_nulls_next_rcu(head)); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { if (++st->bucket >= net->ct.htable_size) return NULL; } - head = rcu_dereference(net->ct.hash[st->bucket].first); + head = rcu_dereference( + hlist_nulls_first_rcu(&net->ct.hash[st->bucket])); } return head; } @@ -217,7 +220,8 @@ static struct hlist_node *ct_expect_get_first(struct seq_file *seq) struct hlist_node *n; for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) { - n = rcu_dereference(net->ct.expect_hash[st->bucket].first); + n = rcu_dereference( + hlist_first_rcu(&net->ct.expect_hash[st->bucket])); if (n) return n; } @@ -230,11 +234,12 @@ static struct hlist_node *ct_expect_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct ct_expect_iter_state *st = seq->private; - head = rcu_dereference(head->next); + head = rcu_dereference(hlist_next_rcu(head)); while (head == NULL) { if (++st->bucket >= nf_ct_expect_hsize) return NULL; - head = rcu_dereference(net->ct.expect_hash[st->bucket].first); + head = rcu_dereference( + hlist_first_rcu(&net->ct.expect_hash[st->bucket])); } return head; } diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index 0f23b3f..703f366f 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -44,13 +44,13 @@ static unsigned int help(struct sk_buff *skb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { - int ret; + int res; exp->tuple.dst.u.tcp.port = htons(port); - ret = nf_ct_expect_related(exp); - if (ret == 0) + res = nf_ct_expect_related(exp); + if (res == 0) break; - else if (ret != -EBUSY) { + else if (res != -EBUSY) { port = 0; break; } diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index c04787c..21bcf47 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -221,7 +221,14 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, manips not an issue. */ if (maniptype == IP_NAT_MANIP_SRC && !(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) { - if (find_appropriate_src(net, zone, orig_tuple, tuple, range)) { + /* try the original tuple first */ + if (in_range(orig_tuple, range)) { + if (!nf_nat_used_tuple(orig_tuple, ct)) { + *tuple = *orig_tuple; + return; + } + } else if (find_appropriate_src(net, zone, orig_tuple, tuple, + range)) { pr_debug("get_unique_tuple: Found current src map\n"); if (!nf_nat_used_tuple(tuple, ct)) return; @@ -266,7 +273,6 @@ nf_nat_setup_info(struct nf_conn *ct, struct net *net = nf_ct_net(ct); struct nf_conntrack_tuple curr_tuple, new_tuple; struct nf_conn_nat *nat; - int have_to_hash = !(ct->status & IPS_NAT_DONE_MASK); /* nat helper or nfctnetlink also setup binding */ nat = nfct_nat(ct); @@ -306,8 +312,7 @@ nf_nat_setup_info(struct nf_conn *ct, ct->status |= IPS_DST_NAT; } - /* Place in source hash if this is the first time. */ - if (have_to_hash) { + if (maniptype == IP_NAT_MANIP_SRC) { unsigned int srchash; srchash = hash_by_src(net, nf_ct_zone(ct), @@ -323,9 +328,9 @@ nf_nat_setup_info(struct nf_conn *ct, /* It's done. */ if (maniptype == IP_NAT_MANIP_DST) - set_bit(IPS_DST_NAT_DONE_BIT, &ct->status); + ct->status |= IPS_DST_NAT_DONE; else - set_bit(IPS_SRC_NAT_DONE_BIT, &ct->status); + ct->status |= IPS_SRC_NAT_DONE; return NF_ACCEPT; } @@ -502,7 +507,10 @@ int nf_nat_protocol_register(const struct nf_nat_protocol *proto) int ret = 0; spin_lock_bh(&nf_nat_lock); - if (nf_nat_protos[proto->protonum] != &nf_nat_unknown_protocol) { + if (rcu_dereference_protected( + nf_nat_protos[proto->protonum], + lockdep_is_held(&nf_nat_lock) + ) != &nf_nat_unknown_protocol) { ret = -EBUSY; goto out; } @@ -532,7 +540,7 @@ static void nf_nat_cleanup_conntrack(struct nf_conn *ct) if (nat == NULL || nat->ct == NULL) return; - NF_CT_ASSERT(nat->ct->status & IPS_NAT_DONE_MASK); + NF_CT_ASSERT(nat->ct->status & IPS_SRC_NAT_DONE); spin_lock_bh(&nf_nat_lock); hlist_del_rcu(&nat->bysource); @@ -545,11 +553,10 @@ static void nf_nat_move_storage(void *new, void *old) struct nf_conn_nat *old_nat = old; struct nf_conn *ct = old_nat->ct; - if (!ct || !(ct->status & IPS_NAT_DONE_MASK)) + if (!ct || !(ct->status & IPS_SRC_NAT_DONE)) return; spin_lock_bh(&nf_nat_lock); - new_nat->ct = ct; hlist_replace_rcu(&old_nat->bysource, &new_nat->bysource); spin_unlock_bh(&nf_nat_lock); } @@ -679,8 +686,7 @@ static int __net_init nf_nat_net_init(struct net *net) { /* Leave them the same for the moment. */ net->ipv4.nat_htable_size = net->ct.htable_size; - net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size, - &net->ipv4.nat_vmalloced, 0); + net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size, 0); if (!net->ipv4.nat_bysource) return -ENOMEM; return 0; @@ -702,8 +708,7 @@ static void __net_exit nf_nat_net_exit(struct net *net) { nf_ct_iterate_cleanup(net, &clean_nat, NULL); synchronize_rcu(); - nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_vmalloced, - net->ipv4.nat_htable_size); + nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_htable_size); } static struct pernet_operations nf_nat_net_ops = { diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index ee5f419..8812a02 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -54,6 +54,7 @@ #include <net/netfilter/nf_conntrack_expect.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_nat_helper.h> +#include <linux/netfilter/nf_conntrack_snmp.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>"); @@ -1310,9 +1311,9 @@ static int __init nf_nat_snmp_basic_init(void) { int ret = 0; - ret = nf_conntrack_helper_register(&snmp_helper); - if (ret < 0) - return ret; + BUG_ON(nf_nat_snmp_hook != NULL); + rcu_assign_pointer(nf_nat_snmp_hook, help); + ret = nf_conntrack_helper_register(&snmp_trap_helper); if (ret < 0) { nf_conntrack_helper_unregister(&snmp_helper); @@ -1323,7 +1324,7 @@ static int __init nf_nat_snmp_basic_init(void) static void __exit nf_nat_snmp_basic_fini(void) { - nf_conntrack_helper_unregister(&snmp_helper); + rcu_assign_pointer(nf_nat_snmp_hook, NULL); nf_conntrack_helper_unregister(&snmp_trap_helper); } diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 351dc4e..b1e5d3a 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -152,6 +152,41 @@ static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, { } +static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) +{ + struct rtable *rt = (struct rtable *) dst; + struct inet_peer *peer; + u32 *p = NULL; + + if (!rt->peer) + rt_bind_peer(rt, 1); + + peer = rt->peer; + if (peer) { + u32 *old_p = __DST_METRICS_PTR(old); + unsigned long prev, new; + + p = peer->metrics; + if (inet_metrics_new(peer)) + memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + p = __DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; + } else { + if (rt->fi) { + fib_info_put(rt->fi); + rt->fi = NULL; + } + } + } + return p; +} + static struct dst_ops ipv4_dst_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), @@ -159,6 +194,7 @@ static struct dst_ops ipv4_dst_ops = { .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, .default_mtu = ipv4_default_mtu, + .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, .negative_advice = ipv4_negative_advice, @@ -514,7 +550,7 @@ static const struct file_operations rt_cpu_seq_fops = { .release = seq_release, }; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID static int rt_acct_proc_show(struct seq_file *m, void *v) { struct ip_rt_acct *dst, *src; @@ -567,14 +603,14 @@ static int __net_init ip_rt_do_proc_init(struct net *net) if (!pde) goto err2; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops); if (!pde) goto err3; #endif return 0; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID err3: remove_proc_entry("rt_cache", net->proc_net_stat); #endif @@ -588,7 +624,7 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net) { remove_proc_entry("rt_cache", net->proc_net_stat); remove_proc_entry("rt_cache", net->proc_net); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID remove_proc_entry("rt_acct", net->proc_net); #endif } @@ -1441,6 +1477,8 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, if (rt->peer) atomic_inc(&rt->peer->refcnt); + if (rt->fi) + atomic_inc(&rt->fi->fib_clntref); if (arp_bind_neighbour(&rt->dst) || !(rt->dst.neighbour->nud_state & @@ -1720,6 +1758,10 @@ static void ipv4_dst_destroy(struct dst_entry *dst) struct rtable *rt = (struct rtable *) dst; struct inet_peer *peer = rt->peer; + if (rt->fi) { + fib_info_put(rt->fi); + rt->fi = NULL; + } if (peer) { rt->peer = NULL; inet_putpeer(peer); @@ -1775,7 +1817,7 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt) memcpy(addr, &src, 4); } -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID static void set_class_tag(struct rtable *rt, u32 tag) { if (!(rt->dst.tclassid & 0xFFFF)) @@ -1815,6 +1857,30 @@ static unsigned int ipv4_default_mtu(const struct dst_entry *dst) return mtu; } +static void rt_init_metrics(struct rtable *rt, struct fib_info *fi) +{ + if (!(rt->fl.flags & FLOWI_FLAG_PRECOW_METRICS)) { + no_cow: + if (fi->fib_metrics != (u32 *) dst_default_metrics) { + rt->fi = fi; + atomic_inc(&fi->fib_clntref); + } + dst_init_metrics(&rt->dst, fi->fib_metrics, true); + } else { + struct inet_peer *peer; + + if (!rt->peer) + rt_bind_peer(rt, 1); + peer = rt->peer; + if (!peer) + goto no_cow; + if (inet_metrics_new(peer)) + memcpy(peer->metrics, fi->fib_metrics, + sizeof(u32) * RTAX_MAX); + dst_init_metrics(&rt->dst, peer->metrics, false); + } +} + static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag) { struct dst_entry *dst = &rt->dst; @@ -1824,8 +1890,8 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag) if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) rt->rt_gateway = FIB_RES_GW(*res); - dst_import_metrics(dst, fi->fib_metrics); -#ifdef CONFIG_NET_CLS_ROUTE + rt_init_metrics(rt, fi); +#ifdef CONFIG_IP_ROUTE_CLASSID dst->tclassid = FIB_RES_NH(*res).nh_tclassid; #endif } @@ -1835,7 +1901,7 @@ static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag) if (dst_metric_raw(dst, RTAX_ADVMSS) > 65535 - 40) dst_metric_set(dst, RTAX_ADVMSS, 65535 - 40); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES set_class_tag(rt, fib_rules_tclass(res)); #endif @@ -1891,7 +1957,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->fl.mark = skb->mark; rth->fl.fl4_src = saddr; rth->rt_src = saddr; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->rt_iif = @@ -2208,7 +2274,7 @@ local_input: rth->fl.mark = skb->mark; rth->fl.fl4_src = saddr; rth->rt_src = saddr; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->rt_iif = @@ -2752,6 +2818,9 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi rt->peer = ort->peer; if (rt->peer) atomic_inc(&rt->peer->refcnt); + rt->fi = ort->fi; + if (rt->fi) + atomic_inc(&rt->fi->fib_clntref); dst_free(new); } @@ -2828,7 +2897,7 @@ static int rt_fill_info(struct net *net, } if (rt->dst.dev) NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex); -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (rt->dst.tclassid) NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid); #endif @@ -3249,9 +3318,9 @@ static __net_initdata struct pernet_operations rt_genid_ops = { }; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; -#endif /* CONFIG_NET_CLS_ROUTE */ +#endif /* CONFIG_IP_ROUTE_CLASSID */ static __initdata unsigned long rhash_entries; static int __init set_rhash_entries(char *str) @@ -3267,7 +3336,7 @@ int __init ip_rt_init(void) { int rc = 0; -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) panic("IP: failed to allocate ip_rt_acct\n"); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 6c11eec..f9867d2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2653,7 +2653,7 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL(compat_tcp_getsockopt); #endif -struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features) +struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct tcphdr *th; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 8157b17..d37baaa 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -2199,7 +2199,7 @@ int udp4_ufo_send_check(struct sk_buff *skb) return 0; } -struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features) +struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index b057d40..19fbdec 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -196,8 +196,11 @@ static void xfrm4_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; + dst_destroy_metrics_generic(dst); + if (likely(xdst->u.rt.peer)) inet_putpeer(xdst->u.rt.peer); + xfrm_dst_destroy(xdst); } @@ -215,6 +218,7 @@ static struct dst_ops xfrm4_dst_ops = { .protocol = cpu_to_be16(ETH_P_IP), .gc = xfrm4_garbage_collect, .update_pmtu = xfrm4_update_pmtu, + .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, .local_out = __ip_local_out, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 978e80e..3194aa9 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -772,7 +772,7 @@ out: return err; } -static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, int features) +static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct ipv6hdr *ipv6h; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 7d227c6..47b7b8d 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1076,6 +1076,7 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries[raw_smp_processor_id()]; + xt_compat_init_offsets(AF_INET6, info->number); xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) @@ -1679,6 +1680,7 @@ translate_compat_table(struct net *net, duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(AF_INET6); + xt_compat_init_offsets(AF_INET6, number); /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, total_size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 09c8889..05027b7 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -452,8 +452,7 @@ ip6t_log_packet(u_int8_t pf, in ? in->name : "", out ? out->name : ""); - /* MAC logging for input path only. */ - if (in && !out) + if (in != NULL) dump_mac_header(m, loginfo, skb); dump_packet(m, loginfo, skb, skb_network_offset(skb), 1); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 79d43aa..0857272 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -45,6 +45,7 @@ #include <linux/netfilter_ipv6.h> #include <linux/kernel.h> #include <linux/module.h> +#include <net/netfilter/ipv6/nf_defrag_ipv6.h> struct nf_ct_frag6_skb_cb @@ -73,7 +74,7 @@ static struct inet_frags nf_frags; static struct netns_frags nf_init_frags; #ifdef CONFIG_SYSCTL -struct ctl_table nf_ct_frag6_sysctl_table[] = { +static struct ctl_table nf_ct_frag6_sysctl_table[] = { { .procname = "nf_conntrack_frag6_timeout", .data = &nf_init_frags.timeout, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 86c3952..2bc6cd7 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -123,18 +123,18 @@ static __inline__ int icmpv6_filter(struct sock *sk, struct sk_buff *skb) } #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) -static int (*mh_filter)(struct sock *sock, struct sk_buff *skb); +typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); -int rawv6_mh_filter_register(int (*filter)(struct sock *sock, - struct sk_buff *skb)) +static mh_filter_t __rcu *mh_filter __read_mostly; + +int rawv6_mh_filter_register(mh_filter_t filter) { rcu_assign_pointer(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); -int rawv6_mh_filter_unregister(int (*filter)(struct sock *sock, - struct sk_buff *skb)) +int rawv6_mh_filter_unregister(mh_filter_t filter) { rcu_assign_pointer(mh_filter, NULL); synchronize_rcu(); @@ -192,10 +192,10 @@ static int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) * policy is placed in rawv6_rcv() because it is * required for each socket. */ - int (*filter)(struct sock *sock, struct sk_buff *skb); + mh_filter_t *filter; filter = rcu_dereference(mh_filter); - filtered = filter ? filter(sk, skb) : 0; + filtered = filter ? (*filter)(sk, skb) : 0; break; } #endif diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 28a85fc..72609f1 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -97,6 +97,36 @@ static struct rt6_info *rt6_get_route_info(struct net *net, struct in6_addr *gwaddr, int ifindex); #endif +static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) +{ + struct rt6_info *rt = (struct rt6_info *) dst; + struct inet_peer *peer; + u32 *p = NULL; + + if (!rt->rt6i_peer) + rt6_bind_peer(rt, 1); + + peer = rt->rt6i_peer; + if (peer) { + u32 *old_p = __DST_METRICS_PTR(old); + unsigned long prev, new; + + p = peer->metrics; + if (inet_metrics_new(peer)) + memcpy(p, old_p, sizeof(u32) * RTAX_MAX); + + new = (unsigned long) p; + prev = cmpxchg(&dst->_metrics, old, new); + + if (prev != old) { + p = __DST_METRICS_PTR(prev); + if (prev & DST_METRICS_READ_ONLY) + p = NULL; + } + } + return p; +} + static struct dst_ops ip6_dst_ops_template = { .family = AF_INET6, .protocol = cpu_to_be16(ETH_P_IPV6), @@ -105,6 +135,7 @@ static struct dst_ops ip6_dst_ops_template = { .check = ip6_dst_check, .default_advmss = ip6_default_advmss, .default_mtu = ip6_default_mtu, + .cow_metrics = ipv6_cow_metrics, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, @@ -125,6 +156,10 @@ static struct dst_ops ip6_dst_blackhole_ops = { .update_pmtu = ip6_rt_blackhole_update_pmtu, }; +static const u32 ip6_template_metrics[RTAX_MAX] = { + [RTAX_HOPLIMIT - 1] = 255, +}; + static struct rt6_info ip6_null_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), @@ -2677,7 +2712,8 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_null_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; - dst_metric_set(&net->ipv6.ip6_null_entry->dst, RTAX_HOPLIMIT, 255); + dst_init_metrics(&net->ipv6.ip6_null_entry->dst, + ip6_template_metrics, true); #ifdef CONFIG_IPV6_MULTIPLE_TABLES net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template, @@ -2688,7 +2724,8 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_prohibit_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_prohibit_entry; net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops; - dst_metric_set(&net->ipv6.ip6_prohibit_entry->dst, RTAX_HOPLIMIT, 255); + dst_init_metrics(&net->ipv6.ip6_prohibit_entry->dst, + ip6_template_metrics, true); net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template, sizeof(*net->ipv6.ip6_blk_hole_entry), @@ -2698,7 +2735,8 @@ static int __net_init ip6_route_net_init(struct net *net) net->ipv6.ip6_blk_hole_entry->dst.path = (struct dst_entry *)net->ipv6.ip6_blk_hole_entry; net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops; - dst_metric_set(&net->ipv6.ip6_blk_hole_entry->dst, RTAX_HOPLIMIT, 255); + dst_init_metrics(&net->ipv6.ip6_blk_hole_entry->dst, + ip6_template_metrics, true); #endif net->ipv6.sysctl.flush_delay = 0; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 8ce38f1..b1599a3 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -412,7 +412,7 @@ static void prl_list_destroy_rcu(struct rcu_head *head) p = container_of(head, struct ip_tunnel_prl_entry, rcu_head); do { - n = p->next; + n = rcu_dereference_protected(p->next, 1); kfree(p); p = n; } while (p); @@ -421,15 +421,17 @@ static void prl_list_destroy_rcu(struct rcu_head *head) static int ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) { - struct ip_tunnel_prl_entry *x, **p; + struct ip_tunnel_prl_entry *x; + struct ip_tunnel_prl_entry __rcu **p; int err = 0; ASSERT_RTNL(); if (a && a->addr != htonl(INADDR_ANY)) { - for (p = &t->prl; *p; p = &(*p)->next) { - if ((*p)->addr == a->addr) { - x = *p; + for (p = &t->prl; + (x = rtnl_dereference(*p)) != NULL; + p = &x->next) { + if (x->addr == a->addr) { *p = x->next; call_rcu(&x->rcu_head, prl_entry_destroy_rcu); t->prl_count--; @@ -438,9 +440,9 @@ ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) } err = -ENXIO; } else { - if (t->prl) { + x = rtnl_dereference(t->prl); + if (x) { t->prl_count = 0; - x = t->prl; call_rcu(&x->rcu_head, prl_list_destroy_rcu); t->prl = NULL; } @@ -1179,7 +1181,7 @@ static int __net_init ipip6_fb_tunnel_init(struct net_device *dev) if (!dev->tstats) return -ENOMEM; dev_hold(dev); - sitn->tunnels_wc[0] = tunnel; + rcu_assign_pointer(sitn->tunnels_wc[0], tunnel); return 0; } @@ -1196,11 +1198,12 @@ static void __net_exit sit_destroy_tunnels(struct sit_net *sitn, struct list_hea for (prio = 1; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t = sitn->tunnels[prio][h]; + struct ip_tunnel *t; + t = rtnl_dereference(sitn->tunnels[prio][h]); while (t != NULL) { unregister_netdevice_queue(t->dev, head); - t = t->next; + t = rtnl_dereference(t->next); } } } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9a009c6..a419a78 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1299,7 +1299,7 @@ static int udp6_ufo_send_check(struct sk_buff *skb) return 0; } -static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, int features) +static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, u32 features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index da87428..834dc02 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -220,6 +220,7 @@ static void xfrm6_dst_destroy(struct dst_entry *dst) if (likely(xdst->u.rt6.rt6i_idev)) in6_dev_put(xdst->u.rt6.rt6i_idev); + dst_destroy_metrics_generic(dst); if (likely(xdst->u.rt6.rt6i_peer)) inet_putpeer(xdst->u.rt6.rt6i_peer); xfrm_dst_destroy(xdst); @@ -257,6 +258,7 @@ static struct dst_ops xfrm6_dst_ops = { .protocol = cpu_to_be16(ETH_P_IPV6), .gc = xfrm6_garbage_collect, .update_pmtu = xfrm6_update_pmtu, + .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, diff --git a/net/mac80211/agg-rx.c b/net/mac80211/agg-rx.c index 227ca82..0c9d0c0 100644 --- a/net/mac80211/agg-rx.c +++ b/net/mac80211/agg-rx.c @@ -76,7 +76,7 @@ void ___ieee80211_stop_rx_ba_session(struct sta_info *sta, u16 tid, #endif /* CONFIG_MAC80211_HT_DEBUG */ if (drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_STOP, - &sta->sta, tid, NULL)) + &sta->sta, tid, NULL, 0)) printk(KERN_DEBUG "HW problem - can not stop rx " "aggregation for tid %d\n", tid); @@ -232,6 +232,9 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, if (buf_size == 0) buf_size = IEEE80211_MAX_AMPDU_BUF; + /* make sure the size doesn't exceed the maximum supported by the hw */ + if (buf_size > local->hw.max_rx_aggregation_subframes) + buf_size = local->hw.max_rx_aggregation_subframes; /* examine state machine */ mutex_lock(&sta->ampdu_mlme.mtx); @@ -287,7 +290,7 @@ void ieee80211_process_addba_request(struct ieee80211_local *local, } ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_RX_START, - &sta->sta, tid, &start_seq_num); + &sta->sta, tid, &start_seq_num, 0); #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "Rx A-MPDU request on tid %d result %d\n", tid, ret); #endif /* CONFIG_MAC80211_HT_DEBUG */ diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 9cc472c..63d852c 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -190,7 +190,7 @@ int ___ieee80211_stop_tx_ba_session(struct sta_info *sta, u16 tid, ret = drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_TX_STOP, - &sta->sta, tid, NULL); + &sta->sta, tid, NULL, 0); /* HW shall not deny going back to legacy */ if (WARN_ON(ret)) { @@ -311,7 +311,7 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) start_seq_num = sta->tid_seq[tid] >> 4; ret = drv_ampdu_action(local, sdata, IEEE80211_AMPDU_TX_START, - &sta->sta, tid, &start_seq_num); + &sta->sta, tid, &start_seq_num, 0); if (ret) { #ifdef CONFIG_MAC80211_HT_DEBUG printk(KERN_DEBUG "BA request denied - HW unavailable for" @@ -342,7 +342,8 @@ void ieee80211_tx_ba_session_handle_start(struct sta_info *sta, int tid) /* send AddBA request */ ieee80211_send_addba_request(sdata, sta->sta.addr, tid, tid_tx->dialog_token, start_seq_num, - 0x40, tid_tx->timeout); + local->hw.max_tx_aggregation_subframes, + tid_tx->timeout); } int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid, @@ -487,7 +488,8 @@ static void ieee80211_agg_tx_operational(struct ieee80211_local *local, drv_ampdu_action(local, sta->sdata, IEEE80211_AMPDU_TX_OPERATIONAL, - &sta->sta, tid, NULL); + &sta->sta, tid, NULL, + sta->ampdu_mlme.tid_tx[tid]->buf_size); /* * synchronize with TX path, while splicing the TX path @@ -742,9 +744,11 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, { struct tid_ampdu_tx *tid_tx; u16 capab, tid; + u8 buf_size; capab = le16_to_cpu(mgmt->u.action.u.addba_resp.capab); tid = (capab & IEEE80211_ADDBA_PARAM_TID_MASK) >> 2; + buf_size = (capab & IEEE80211_ADDBA_PARAM_BUF_SIZE_MASK) >> 6; mutex_lock(&sta->ampdu_mlme.mtx); @@ -767,12 +771,23 @@ void ieee80211_process_addba_resp(struct ieee80211_local *local, if (le16_to_cpu(mgmt->u.action.u.addba_resp.status) == WLAN_STATUS_SUCCESS) { + /* + * IEEE 802.11-2007 7.3.1.14: + * In an ADDBA Response frame, when the Status Code field + * is set to 0, the Buffer Size subfield is set to a value + * of at least 1. + */ + if (!buf_size) + goto out; + if (test_and_set_bit(HT_AGG_STATE_RESPONSE_RECEIVED, &tid_tx->state)) { /* ignore duplicate response */ goto out; } + tid_tx->buf_size = buf_size; + if (test_bit(HT_AGG_STATE_DRV_READY, &tid_tx->state)) ieee80211_agg_tx_operational(local, sta, tid); diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 98d5899..78af32d 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -382,17 +382,17 @@ static inline int drv_ampdu_action(struct ieee80211_local *local, struct ieee80211_sub_if_data *sdata, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, - u16 *ssn) + u16 *ssn, u8 buf_size) { int ret = -EOPNOTSUPP; might_sleep(); - trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn); + trace_drv_ampdu_action(local, sdata, action, sta, tid, ssn, buf_size); if (local->ops->ampdu_action) ret = local->ops->ampdu_action(&local->hw, &sdata->vif, action, - sta, tid, ssn); + sta, tid, ssn, buf_size); trace_drv_return_int(local, ret); diff --git a/net/mac80211/driver-trace.h b/net/mac80211/driver-trace.h index 49c8421..e5cce19 100644 --- a/net/mac80211/driver-trace.h +++ b/net/mac80211/driver-trace.h @@ -9,6 +9,11 @@ #undef TRACE_EVENT #define TRACE_EVENT(name, proto, ...) \ static inline void trace_ ## name(proto) {} +#undef DECLARE_EVENT_CLASS +#define DECLARE_EVENT_CLASS(...) +#undef DEFINE_EVENT +#define DEFINE_EVENT(evt_class, name, proto, ...) \ +static inline void trace_ ## name(proto) {} #endif #undef TRACE_SYSTEM @@ -38,7 +43,7 @@ static inline void trace_ ## name(proto) {} * Tracing for driver callbacks. */ -TRACE_EVENT(drv_return_void, +DECLARE_EVENT_CLASS(local_only_evt, TP_PROTO(struct ieee80211_local *local), TP_ARGS(local), TP_STRUCT__entry( @@ -50,6 +55,11 @@ TRACE_EVENT(drv_return_void, TP_printk(LOCAL_PR_FMT, LOCAL_PR_ARG) ); +DEFINE_EVENT(local_only_evt, drv_return_void, + TP_PROTO(struct ieee80211_local *local), + TP_ARGS(local) +); + TRACE_EVENT(drv_return_int, TP_PROTO(struct ieee80211_local *local, int ret), TP_ARGS(local, ret), @@ -78,40 +88,14 @@ TRACE_EVENT(drv_return_u64, TP_printk(LOCAL_PR_FMT " - %llu", LOCAL_PR_ARG, __entry->ret) ); -TRACE_EVENT(drv_start, +DEFINE_EVENT(local_only_evt, drv_start, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); -TRACE_EVENT(drv_stop, +DEFINE_EVENT(local_only_evt, drv_stop, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); TRACE_EVENT(drv_add_interface, @@ -439,40 +423,14 @@ TRACE_EVENT(drv_hw_scan, ) ); -TRACE_EVENT(drv_sw_scan_start, +DEFINE_EVENT(local_only_evt, drv_sw_scan_start, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); -TRACE_EVENT(drv_sw_scan_complete, +DEFINE_EVENT(local_only_evt, drv_sw_scan_complete, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); TRACE_EVENT(drv_get_stats, @@ -702,23 +660,9 @@ TRACE_EVENT(drv_conf_tx, ) ); -TRACE_EVENT(drv_get_tsf, +DEFINE_EVENT(local_only_evt, drv_get_tsf, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, - LOCAL_PR_ARG - ) + TP_ARGS(local) ); TRACE_EVENT(drv_set_tsf, @@ -742,41 +686,14 @@ TRACE_EVENT(drv_set_tsf, ) ); -TRACE_EVENT(drv_reset_tsf, +DEFINE_EVENT(local_only_evt, drv_reset_tsf, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); -TRACE_EVENT(drv_tx_last_beacon, +DEFINE_EVENT(local_only_evt, drv_tx_last_beacon, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, - LOCAL_PR_ARG - ) + TP_ARGS(local) ); TRACE_EVENT(drv_ampdu_action, @@ -784,9 +701,9 @@ TRACE_EVENT(drv_ampdu_action, struct ieee80211_sub_if_data *sdata, enum ieee80211_ampdu_mlme_action action, struct ieee80211_sta *sta, u16 tid, - u16 *ssn), + u16 *ssn, u8 buf_size), - TP_ARGS(local, sdata, action, sta, tid, ssn), + TP_ARGS(local, sdata, action, sta, tid, ssn, buf_size), TP_STRUCT__entry( LOCAL_ENTRY @@ -794,6 +711,7 @@ TRACE_EVENT(drv_ampdu_action, __field(u32, action) __field(u16, tid) __field(u16, ssn) + __field(u8, buf_size) VIF_ENTRY ), @@ -804,11 +722,13 @@ TRACE_EVENT(drv_ampdu_action, __entry->action = action; __entry->tid = tid; __entry->ssn = ssn ? *ssn : 0; + __entry->buf_size = buf_size; ), TP_printk( - LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d", - LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->action, __entry->tid + LOCAL_PR_FMT VIF_PR_FMT STA_PR_FMT " action:%d tid:%d buf:%d", + LOCAL_PR_ARG, VIF_PR_ARG, STA_PR_ARG, __entry->action, + __entry->tid, __entry->buf_size ) ); @@ -959,22 +879,9 @@ TRACE_EVENT(drv_remain_on_channel, ) ); -TRACE_EVENT(drv_cancel_remain_on_channel, +DEFINE_EVENT(local_only_evt, drv_cancel_remain_on_channel, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); /* @@ -1069,23 +976,9 @@ TRACE_EVENT(api_stop_tx_ba_cb, ) ); -TRACE_EVENT(api_restart_hw, +DEFINE_EVENT(local_only_evt, api_restart_hw, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, - LOCAL_PR_ARG - ) + TP_ARGS(local) ); TRACE_EVENT(api_beacon_loss, @@ -1214,40 +1107,14 @@ TRACE_EVENT(api_chswitch_done, ) ); -TRACE_EVENT(api_ready_on_channel, +DEFINE_EVENT(local_only_evt, api_ready_on_channel, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); -TRACE_EVENT(api_remain_on_channel_expired, +DEFINE_EVENT(local_only_evt, api_remain_on_channel_expired, TP_PROTO(struct ieee80211_local *local), - - TP_ARGS(local), - - TP_STRUCT__entry( - LOCAL_ENTRY - ), - - TP_fast_assign( - LOCAL_ASSIGN; - ), - - TP_printk( - LOCAL_PR_FMT, LOCAL_PR_ARG - ) + TP_ARGS(local) ); /* diff --git a/net/mac80211/ibss.c b/net/mac80211/ibss.c index 53c7077..775fb63 100644 --- a/net/mac80211/ibss.c +++ b/net/mac80211/ibss.c @@ -270,7 +270,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, enum ieee80211_band band = rx_status->band; if (elems->ds_params && elems->ds_params_len == 1) - freq = ieee80211_channel_to_frequency(elems->ds_params[0]); + freq = ieee80211_channel_to_frequency(elems->ds_params[0], + band); else freq = rx_status->freq; diff --git a/net/mac80211/main.c b/net/mac80211/main.c index a46ff06..09a2744 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -554,6 +554,7 @@ struct ieee80211_hw *ieee80211_alloc_hw(size_t priv_data_len, local->hw.queues = 1; local->hw.max_rates = 1; local->hw.max_report_rates = 0; + local->hw.max_rx_aggregation_subframes = IEEE80211_MAX_AMPDU_BUF; local->hw.conf.long_frame_max_tx_count = wiphy->retry_long; local->hw.conf.short_frame_max_tx_count = wiphy->retry_short; local->user_power_level = -1; diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index ca3af46..2a57cc0 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -574,7 +574,7 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, &elems); if (elems.ds_params && elems.ds_params_len == 1) - freq = ieee80211_channel_to_frequency(elems.ds_params[0]); + freq = ieee80211_channel_to_frequency(elems.ds_params[0], band); else freq = rx_status->freq; @@ -645,7 +645,7 @@ void ieee80211_mesh_work(struct ieee80211_sub_if_data *sdata) if (test_and_clear_bit(MESH_WORK_GROW_MPATH_TABLE, &ifmsh->wrkq_flags)) mesh_mpath_table_grow(); - if (test_and_clear_bit(MESH_WORK_GROW_MPATH_TABLE, &ifmsh->wrkq_flags)) + if (test_and_clear_bit(MESH_WORK_GROW_MPP_TABLE, &ifmsh->wrkq_flags)) mesh_mpp_table_grow(); if (test_and_clear_bit(MESH_WORK_HOUSEKEEPING, &ifmsh->wrkq_flags)) diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index 45fbb9e..3221069 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -176,7 +176,7 @@ static u32 ieee80211_enable_ht(struct ieee80211_sub_if_data *sdata, /* check that channel matches the right operating channel */ if (local->hw.conf.channel->center_freq != - ieee80211_channel_to_frequency(hti->control_chan)) + ieee80211_channel_to_frequency(hti->control_chan, sband->band)) enable_ht = false; if (enable_ht) { @@ -429,7 +429,8 @@ void ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, container_of((void *)bss, struct cfg80211_bss, priv); struct ieee80211_channel *new_ch; struct ieee80211_if_managed *ifmgd = &sdata->u.mgd; - int new_freq = ieee80211_channel_to_frequency(sw_elem->new_ch_num); + int new_freq = ieee80211_channel_to_frequency(sw_elem->new_ch_num, + cbss->channel->band); ASSERT_MGD_MTX(ifmgd); @@ -1519,7 +1520,8 @@ static void ieee80211_rx_bss_info(struct ieee80211_sub_if_data *sdata, } if (elems->ds_params && elems->ds_params_len == 1) - freq = ieee80211_channel_to_frequency(elems->ds_params[0]); + freq = ieee80211_channel_to_frequency(elems->ds_params[0], + rx_status->band); else freq = rx_status->freq; @@ -1972,9 +1974,9 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) #ifdef CONFIG_MAC80211_VERBOSE_DEBUG wiphy_debug(local->hw.wiphy, "%s: No ack for nullfunc frame to" - " AP %pM, try %d\n", + " AP %pM, try %d/%i\n", sdata->name, bssid, - ifmgd->probe_send_count); + ifmgd->probe_send_count, max_tries); #endif ieee80211_mgd_probe_ap_send(sdata); } else { @@ -2001,10 +2003,10 @@ void ieee80211_sta_work(struct ieee80211_sub_if_data *sdata) #ifdef CONFIG_MAC80211_VERBOSE_DEBUG wiphy_debug(local->hw.wiphy, "%s: No probe response from AP %pM" - " after %dms, try %d\n", + " after %dms, try %d/%i\n", sdata->name, bssid, (1000 * IEEE80211_PROBE_WAIT)/HZ, - ifmgd->probe_send_count); + ifmgd->probe_send_count, max_tries); #endif ieee80211_mgd_probe_ap_send(sdata); } else { diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index a6701ed..f36d70f 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1556,17 +1556,36 @@ __ieee80211_data_to_8023(struct ieee80211_rx_data *rx) { struct ieee80211_sub_if_data *sdata = rx->sdata; struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)rx->skb->data; + bool check_port_control = false; + struct ethhdr *ehdr; + int ret; if (ieee80211_has_a4(hdr->frame_control) && sdata->vif.type == NL80211_IFTYPE_AP_VLAN && !sdata->u.vlan.sta) return -1; + if (sdata->vif.type == NL80211_IFTYPE_STATION && + !!sdata->u.mgd.use_4addr != !!ieee80211_has_a4(hdr->frame_control)) { + + if (!sdata->u.mgd.use_4addr) + return -1; + else + check_port_control = true; + } + if (is_multicast_ether_addr(hdr->addr1) && - ((sdata->vif.type == NL80211_IFTYPE_AP_VLAN && sdata->u.vlan.sta) || - (sdata->vif.type == NL80211_IFTYPE_STATION && sdata->u.mgd.use_4addr))) + sdata->vif.type == NL80211_IFTYPE_AP_VLAN && sdata->u.vlan.sta) return -1; - return ieee80211_data_to_8023(rx->skb, sdata->vif.addr, sdata->vif.type); + ret = ieee80211_data_to_8023(rx->skb, sdata->vif.addr, sdata->vif.type); + if (ret < 0 || !check_port_control) + return ret; + + ehdr = (struct ethhdr *) rx->skb->data; + if (ehdr->h_proto != rx->sdata->control_port_protocol) + return -1; + + return 0; } /* @@ -2692,7 +2711,7 @@ static bool ieee80211_prepare_and_rx_handle(struct ieee80211_rx_data *rx, if (!skb) { if (net_ratelimit()) wiphy_debug(local->hw.wiphy, - "failed to copy multicast frame for %s\n", + "failed to copy skb for %s\n", sdata->name); return true; } diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c index fb274db..1ef73be 100644 --- a/net/mac80211/scan.c +++ b/net/mac80211/scan.c @@ -196,7 +196,8 @@ ieee80211_scan_rx(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb) ieee802_11_parse_elems(elements, skb->len - baselen, &elems); if (elems.ds_params && elems.ds_params_len == 1) - freq = ieee80211_channel_to_frequency(elems.ds_params[0]); + freq = ieee80211_channel_to_frequency(elems.ds_params[0], + rx_status->band); else freq = rx_status->freq; diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index bbdd2a8..ca0b690 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -82,6 +82,7 @@ enum ieee80211_sta_info_flags { * @state: session state (see above) * @stop_initiator: initiator of a session stop * @tx_stop: TX DelBA frame when stopping + * @buf_size: reorder buffer size at receiver * * This structure's lifetime is managed by RCU, assignments to * the array holding it must hold the aggregation mutex. @@ -101,6 +102,7 @@ struct tid_ampdu_tx { u8 dialog_token; u8 stop_initiator; bool tx_stop; + u8 buf_size; }; /** diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index b64b42b..ffc6749 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1750,7 +1750,7 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, __le16 fc; struct ieee80211_hdr hdr; struct ieee80211s_hdr mesh_hdr __maybe_unused; - struct mesh_path *mppath = NULL; + struct mesh_path __maybe_unused *mppath = NULL; const u8 *encaps_data; int encaps_len, skip_header_bytes; int nh_pos, h_pos; @@ -1815,19 +1815,19 @@ netdev_tx_t ieee80211_subif_start_xmit(struct sk_buff *skb, mppath = mpp_path_lookup(skb->data, sdata); /* - * Do not use address extension, if it is a packet from - * the same interface and the destination is not being - * proxied by any other mest point. + * Use address extension if it is a packet from + * another interface or if we know the destination + * is being proxied by a portal (i.e. portal address + * differs from proxied address) */ if (compare_ether_addr(sdata->vif.addr, skb->data + ETH_ALEN) == 0 && - (!mppath || !compare_ether_addr(mppath->mpp, skb->data))) { + !(mppath && compare_ether_addr(mppath->mpp, skb->data))) { hdrlen = ieee80211_fill_mesh_addresses(&hdr, &fc, skb->data, skb->data + ETH_ALEN); meshhdrlen = ieee80211_new_mesh_header(&mesh_hdr, sdata, NULL, NULL); } else { - /* packet from other interface */ int is_mesh_mcast = 1; const u8 *mesh_da; @@ -2302,6 +2302,11 @@ struct sk_buff *ieee80211_beacon_get_tim(struct ieee80211_hw *hw, struct ieee80211_mgmt *mgmt; u8 *pos; +#ifdef CONFIG_MAC80211_MESH + if (!sdata->u.mesh.mesh_id_len) + goto out; +#endif + /* headroom, head length, tail length and maximum TIM length */ skb = dev_alloc_skb(local->tx_headroom + 400 + sdata->u.mesh.vendor_ie_len); diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 1534f2b..faf7412 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -85,6 +85,17 @@ config NF_CONNTRACK_EVENTS If unsure, say `N'. +config NF_CONNTRACK_TIMESTAMP + bool 'Connection tracking timestamping' + depends on NETFILTER_ADVANCED + help + This option enables support for connection tracking timestamping. + This allows you to store the flow start-time and to obtain + the flow-stop time (once it has been destroyed) via Connection + tracking events. + + If unsure, say `N'. + config NF_CT_PROTO_DCCP tristate 'DCCP protocol connection tracking support (EXPERIMENTAL)' depends on EXPERIMENTAL @@ -185,9 +196,13 @@ config NF_CONNTRACK_IRC To compile it as a module, choose M here. If unsure, say N. +config NF_CONNTRACK_BROADCAST + tristate + config NF_CONNTRACK_NETBIOS_NS tristate "NetBIOS name service protocol support" depends on NETFILTER_ADVANCED + select NF_CONNTRACK_BROADCAST help NetBIOS name service requests are sent as broadcast messages from an unprivileged port and responded to with unicast messages to the @@ -204,6 +219,21 @@ config NF_CONNTRACK_NETBIOS_NS To compile it as a module, choose M here. If unsure, say N. +config NF_CONNTRACK_SNMP + tristate "SNMP service protocol support" + depends on NETFILTER_ADVANCED + select NF_CONNTRACK_BROADCAST + help + SNMP service requests are sent as broadcast messages from an + unprivileged port and responded to with unicast messages to the + same port. This make them hard to firewall properly because connection + tracking doesn't deal with broadcasts. This helper tracks locally + originating SNMP service requests and the corresponding + responses. It relies on correct IP address configuration, specifically + netmask and broadcast address. + + To compile it as a module, choose M here. If unsure, say N. + config NF_CONNTRACK_PPTP tristate "PPtP protocol support" depends on NETFILTER_ADVANCED @@ -326,6 +356,16 @@ config NETFILTER_XT_CONNMARK comment "Xtables targets" +config NETFILTER_XT_TARGET_AUDIT + tristate "AUDIT target support" + depends on AUDIT + depends on NETFILTER_ADVANCED + ---help--- + This option adds a 'AUDIT' target, which can be used to create + audit records for packets dropped/accepted. + + To compileit as a module, choose M here. If unsure, say N. + config NETFILTER_XT_TARGET_CHECKSUM tristate "CHECKSUM target support" depends on IP_NF_MANGLE || IP6_NF_MANGLE @@ -477,6 +517,7 @@ config NETFILTER_XT_TARGET_NFLOG config NETFILTER_XT_TARGET_NFQUEUE tristate '"NFQUEUE" target Support' depends on NETFILTER_ADVANCED + select NETFILTER_NETLINK_QUEUE help This target replaced the old obsolete QUEUE target. @@ -886,7 +927,7 @@ config NETFILTER_XT_MATCH_RATEEST config NETFILTER_XT_MATCH_REALM tristate '"realm" match support' depends on NETFILTER_ADVANCED - select NET_CLS_ROUTE + select IP_ROUTE_CLASSID help This option adds a `realm' match, which allows you to use the realm key from the routing subsystem inside iptables. diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 441050f..9ae6878 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -1,6 +1,7 @@ netfilter-objs := core.o nf_log.o nf_queue.o nf_sockopt.o nf_conntrack-y := nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_expect.o nf_conntrack_helper.o nf_conntrack_proto.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o nf_conntrack_extend.o nf_conntrack_acct.o +nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o obj-$(CONFIG_NETFILTER) = netfilter.o @@ -28,7 +29,9 @@ obj-$(CONFIG_NF_CONNTRACK_AMANDA) += nf_conntrack_amanda.o obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o obj-$(CONFIG_NF_CONNTRACK_H323) += nf_conntrack_h323.o obj-$(CONFIG_NF_CONNTRACK_IRC) += nf_conntrack_irc.o +obj-$(CONFIG_NF_CONNTRACK_BROADCAST) += nf_conntrack_broadcast.o obj-$(CONFIG_NF_CONNTRACK_NETBIOS_NS) += nf_conntrack_netbios_ns.o +obj-$(CONFIG_NF_CONNTRACK_SNMP) += nf_conntrack_snmp.o obj-$(CONFIG_NF_CONNTRACK_PPTP) += nf_conntrack_pptp.o obj-$(CONFIG_NF_CONNTRACK_SANE) += nf_conntrack_sane.o obj-$(CONFIG_NF_CONNTRACK_SIP) += nf_conntrack_sip.o @@ -45,6 +48,7 @@ obj-$(CONFIG_NETFILTER_XT_MARK) += xt_mark.o obj-$(CONFIG_NETFILTER_XT_CONNMARK) += xt_connmark.o # targets +obj-$(CONFIG_NETFILTER_XT_TARGET_AUDIT) += xt_AUDIT.o obj-$(CONFIG_NETFILTER_XT_TARGET_CHECKSUM) += xt_CHECKSUM.o obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o diff --git a/net/netfilter/core.c b/net/netfilter/core.c index 32fcbe2..1e00bf7 100644 --- a/net/netfilter/core.c +++ b/net/netfilter/core.c @@ -175,13 +175,21 @@ next_hook: ret = 1; } else if ((verdict & NF_VERDICT_MASK) == NF_DROP) { kfree_skb(skb); - ret = -(verdict >> NF_VERDICT_BITS); + ret = NF_DROP_GETERR(verdict); if (ret == 0) ret = -EPERM; } else if ((verdict & NF_VERDICT_MASK) == NF_QUEUE) { - if (!nf_queue(skb, elem, pf, hook, indev, outdev, okfn, - verdict >> NF_VERDICT_BITS)) - goto next_hook; + ret = nf_queue(skb, elem, pf, hook, indev, outdev, okfn, + verdict >> NF_VERDICT_QBITS); + if (ret < 0) { + if (ret == -ECANCELED) + goto next_hook; + if (ret == -ESRCH && + (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) + goto next_hook; + kfree_skb(skb); + } + ret = 0; } rcu_read_unlock(); return ret; @@ -214,7 +222,7 @@ EXPORT_SYMBOL(skb_make_writable); /* This does not belong here, but locally generated errors need it if connection tracking in use: without this, connection may not be in hash table, and hence manufactured ICMP or RST packets will not be associated with it. */ -void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *); +void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu __read_mostly; EXPORT_SYMBOL(ip_ct_attach); void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) @@ -231,7 +239,7 @@ void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb) } EXPORT_SYMBOL(nf_ct_attach); -void (*nf_ct_destroy)(struct nf_conntrack *); +void (*nf_ct_destroy)(struct nf_conntrack *) __rcu __read_mostly; EXPORT_SYMBOL(nf_ct_destroy); void nf_conntrack_destroy(struct nf_conntrack *nfct) diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index a475ede..5c48ffb 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -43,11 +43,6 @@ EXPORT_SYMBOL(register_ip_vs_app); EXPORT_SYMBOL(unregister_ip_vs_app); EXPORT_SYMBOL(register_ip_vs_app_inc); -/* ipvs application list head */ -static LIST_HEAD(ip_vs_app_list); -static DEFINE_MUTEX(__ip_vs_app_mutex); - - /* * Get an ip_vs_app object */ @@ -67,7 +62,8 @@ static inline void ip_vs_app_put(struct ip_vs_app *app) * Allocate/initialize app incarnation and register it in proto apps. */ static int -ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port) +ip_vs_app_inc_new(struct net *net, struct ip_vs_app *app, __u16 proto, + __u16 port) { struct ip_vs_protocol *pp; struct ip_vs_app *inc; @@ -98,7 +94,7 @@ ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port) } } - ret = pp->register_app(inc); + ret = pp->register_app(net, inc); if (ret) goto out; @@ -119,7 +115,7 @@ ip_vs_app_inc_new(struct ip_vs_app *app, __u16 proto, __u16 port) * Release app incarnation */ static void -ip_vs_app_inc_release(struct ip_vs_app *inc) +ip_vs_app_inc_release(struct net *net, struct ip_vs_app *inc) { struct ip_vs_protocol *pp; @@ -127,7 +123,7 @@ ip_vs_app_inc_release(struct ip_vs_app *inc) return; if (pp->unregister_app) - pp->unregister_app(inc); + pp->unregister_app(net, inc); IP_VS_DBG(9, "%s App %s:%u unregistered\n", pp->name, inc->name, ntohs(inc->port)); @@ -168,15 +164,17 @@ void ip_vs_app_inc_put(struct ip_vs_app *inc) * Register an application incarnation in protocol applications */ int -register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port) +register_ip_vs_app_inc(struct net *net, struct ip_vs_app *app, __u16 proto, + __u16 port) { + struct netns_ipvs *ipvs = net_ipvs(net); int result; - mutex_lock(&__ip_vs_app_mutex); + mutex_lock(&ipvs->app_mutex); - result = ip_vs_app_inc_new(app, proto, port); + result = ip_vs_app_inc_new(net, app, proto, port); - mutex_unlock(&__ip_vs_app_mutex); + mutex_unlock(&ipvs->app_mutex); return result; } @@ -185,16 +183,17 @@ register_ip_vs_app_inc(struct ip_vs_app *app, __u16 proto, __u16 port) /* * ip_vs_app registration routine */ -int register_ip_vs_app(struct ip_vs_app *app) +int register_ip_vs_app(struct net *net, struct ip_vs_app *app) { + struct netns_ipvs *ipvs = net_ipvs(net); /* increase the module use count */ ip_vs_use_count_inc(); - mutex_lock(&__ip_vs_app_mutex); + mutex_lock(&ipvs->app_mutex); - list_add(&app->a_list, &ip_vs_app_list); + list_add(&app->a_list, &ipvs->app_list); - mutex_unlock(&__ip_vs_app_mutex); + mutex_unlock(&ipvs->app_mutex); return 0; } @@ -204,19 +203,20 @@ int register_ip_vs_app(struct ip_vs_app *app) * ip_vs_app unregistration routine * We are sure there are no app incarnations attached to services */ -void unregister_ip_vs_app(struct ip_vs_app *app) +void unregister_ip_vs_app(struct net *net, struct ip_vs_app *app) { + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_app *inc, *nxt; - mutex_lock(&__ip_vs_app_mutex); + mutex_lock(&ipvs->app_mutex); list_for_each_entry_safe(inc, nxt, &app->incs_list, a_list) { - ip_vs_app_inc_release(inc); + ip_vs_app_inc_release(net, inc); } list_del(&app->a_list); - mutex_unlock(&__ip_vs_app_mutex); + mutex_unlock(&ipvs->app_mutex); /* decrease the module use count */ ip_vs_use_count_dec(); @@ -226,7 +226,8 @@ void unregister_ip_vs_app(struct ip_vs_app *app) /* * Bind ip_vs_conn to its ip_vs_app (called by cp constructor) */ -int ip_vs_bind_app(struct ip_vs_conn *cp, struct ip_vs_protocol *pp) +int ip_vs_bind_app(struct ip_vs_conn *cp, + struct ip_vs_protocol *pp) { return pp->app_conn_bind(cp); } @@ -481,11 +482,11 @@ int ip_vs_app_pkt_in(struct ip_vs_conn *cp, struct sk_buff *skb) * /proc/net/ip_vs_app entry function */ -static struct ip_vs_app *ip_vs_app_idx(loff_t pos) +static struct ip_vs_app *ip_vs_app_idx(struct netns_ipvs *ipvs, loff_t pos) { struct ip_vs_app *app, *inc; - list_for_each_entry(app, &ip_vs_app_list, a_list) { + list_for_each_entry(app, &ipvs->app_list, a_list) { list_for_each_entry(inc, &app->incs_list, a_list) { if (pos-- == 0) return inc; @@ -497,19 +498,24 @@ static struct ip_vs_app *ip_vs_app_idx(loff_t pos) static void *ip_vs_app_seq_start(struct seq_file *seq, loff_t *pos) { - mutex_lock(&__ip_vs_app_mutex); + struct net *net = seq_file_net(seq); + struct netns_ipvs *ipvs = net_ipvs(net); - return *pos ? ip_vs_app_idx(*pos - 1) : SEQ_START_TOKEN; + mutex_lock(&ipvs->app_mutex); + + return *pos ? ip_vs_app_idx(ipvs, *pos - 1) : SEQ_START_TOKEN; } static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_vs_app *inc, *app; struct list_head *e; + struct net *net = seq_file_net(seq); + struct netns_ipvs *ipvs = net_ipvs(net); ++*pos; if (v == SEQ_START_TOKEN) - return ip_vs_app_idx(0); + return ip_vs_app_idx(ipvs, 0); inc = v; app = inc->app; @@ -518,7 +524,7 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos) return list_entry(e, struct ip_vs_app, a_list); /* go on to next application */ - for (e = app->a_list.next; e != &ip_vs_app_list; e = e->next) { + for (e = app->a_list.next; e != &ipvs->app_list; e = e->next) { app = list_entry(e, struct ip_vs_app, a_list); list_for_each_entry(inc, &app->incs_list, a_list) { return inc; @@ -529,7 +535,9 @@ static void *ip_vs_app_seq_next(struct seq_file *seq, void *v, loff_t *pos) static void ip_vs_app_seq_stop(struct seq_file *seq, void *v) { - mutex_unlock(&__ip_vs_app_mutex); + struct netns_ipvs *ipvs = net_ipvs(seq_file_net(seq)); + + mutex_unlock(&ipvs->app_mutex); } static int ip_vs_app_seq_show(struct seq_file *seq, void *v) @@ -557,7 +565,8 @@ static const struct seq_operations ip_vs_app_seq_ops = { static int ip_vs_app_open(struct inode *inode, struct file *file) { - return seq_open(file, &ip_vs_app_seq_ops); + return seq_open_net(inode, file, &ip_vs_app_seq_ops, + sizeof(struct seq_net_private)); } static const struct file_operations ip_vs_app_fops = { @@ -569,15 +578,36 @@ static const struct file_operations ip_vs_app_fops = { }; #endif -int __init ip_vs_app_init(void) +static int __net_init __ip_vs_app_init(struct net *net) { - /* we will replace it with proc_net_ipvs_create() soon */ - proc_net_fops_create(&init_net, "ip_vs_app", 0, &ip_vs_app_fops); + struct netns_ipvs *ipvs = net_ipvs(net); + + INIT_LIST_HEAD(&ipvs->app_list); + __mutex_init(&ipvs->app_mutex, "ipvs->app_mutex", &ipvs->app_key); + proc_net_fops_create(net, "ip_vs_app", 0, &ip_vs_app_fops); return 0; } +static void __net_exit __ip_vs_app_cleanup(struct net *net) +{ + proc_net_remove(net, "ip_vs_app"); +} + +static struct pernet_operations ip_vs_app_ops = { + .init = __ip_vs_app_init, + .exit = __ip_vs_app_cleanup, +}; + +int __init ip_vs_app_init(void) +{ + int rv; + + rv = register_pernet_subsys(&ip_vs_app_ops); + return rv; +} + void ip_vs_app_cleanup(void) { - proc_net_remove(&init_net, "ip_vs_app"); + unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index e9adecd..83233fe 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -48,35 +48,32 @@ /* * Connection hash size. Default is what was selected at compile time. */ -int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; +static int ip_vs_conn_tab_bits = CONFIG_IP_VS_TAB_BITS; module_param_named(conn_tab_bits, ip_vs_conn_tab_bits, int, 0444); MODULE_PARM_DESC(conn_tab_bits, "Set connections' hash size"); /* size and mask values */ -int ip_vs_conn_tab_size; -int ip_vs_conn_tab_mask; +int ip_vs_conn_tab_size __read_mostly; +static int ip_vs_conn_tab_mask __read_mostly; /* * Connection hash table: for input and output packets lookups of IPVS */ -static struct list_head *ip_vs_conn_tab; +static struct list_head *ip_vs_conn_tab __read_mostly; /* SLAB cache for IPVS connections */ static struct kmem_cache *ip_vs_conn_cachep __read_mostly; -/* counter for current IPVS connections */ -static atomic_t ip_vs_conn_count = ATOMIC_INIT(0); - /* counter for no client port connections */ static atomic_t ip_vs_conn_no_cport_cnt = ATOMIC_INIT(0); /* random value for IPVS connection hash */ -static unsigned int ip_vs_conn_rnd; +static unsigned int ip_vs_conn_rnd __read_mostly; /* * Fine locking granularity for big connection hash table */ -#define CT_LOCKARRAY_BITS 4 +#define CT_LOCKARRAY_BITS 5 #define CT_LOCKARRAY_SIZE (1<<CT_LOCKARRAY_BITS) #define CT_LOCKARRAY_MASK (CT_LOCKARRAY_SIZE-1) @@ -133,19 +130,19 @@ static inline void ct_write_unlock_bh(unsigned key) /* * Returns hash value for IPVS connection entry */ -static unsigned int ip_vs_conn_hashkey(int af, unsigned proto, +static unsigned int ip_vs_conn_hashkey(struct net *net, int af, unsigned proto, const union nf_inet_addr *addr, __be16 port) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) - return jhash_3words(jhash(addr, 16, ip_vs_conn_rnd), - (__force u32)port, proto, ip_vs_conn_rnd) - & ip_vs_conn_tab_mask; + return (jhash_3words(jhash(addr, 16, ip_vs_conn_rnd), + (__force u32)port, proto, ip_vs_conn_rnd) ^ + ((size_t)net>>8)) & ip_vs_conn_tab_mask; #endif - return jhash_3words((__force u32)addr->ip, (__force u32)port, proto, - ip_vs_conn_rnd) - & ip_vs_conn_tab_mask; + return (jhash_3words((__force u32)addr->ip, (__force u32)port, proto, + ip_vs_conn_rnd) ^ + ((size_t)net>>8)) & ip_vs_conn_tab_mask; } static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p, @@ -166,18 +163,18 @@ static unsigned int ip_vs_conn_hashkey_param(const struct ip_vs_conn_param *p, port = p->vport; } - return ip_vs_conn_hashkey(p->af, p->protocol, addr, port); + return ip_vs_conn_hashkey(p->net, p->af, p->protocol, addr, port); } static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp) { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(cp->af, cp->protocol, &cp->caddr, cp->cport, - NULL, 0, &p); + ip_vs_conn_fill_param(ip_vs_conn_net(cp), cp->af, cp->protocol, + &cp->caddr, cp->cport, NULL, 0, &p); - if (cp->dest && cp->dest->svc->pe) { - p.pe = cp->dest->svc->pe; + if (cp->pe) { + p.pe = cp->pe; p.pe_data = cp->pe_data; p.pe_data_len = cp->pe_data_len; } @@ -186,7 +183,7 @@ static unsigned int ip_vs_conn_hashkey_conn(const struct ip_vs_conn *cp) } /* - * Hashes ip_vs_conn in ip_vs_conn_tab by proto,addr,port. + * Hashes ip_vs_conn in ip_vs_conn_tab by netns,proto,addr,port. * returns bool success. */ static inline int ip_vs_conn_hash(struct ip_vs_conn *cp) @@ -269,11 +266,12 @@ __ip_vs_conn_in_get(const struct ip_vs_conn_param *p) list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->af == p->af && + p->cport == cp->cport && p->vport == cp->vport && ip_vs_addr_equal(p->af, p->caddr, &cp->caddr) && ip_vs_addr_equal(p->af, p->vaddr, &cp->vaddr) && - p->cport == cp->cport && p->vport == cp->vport && ((!p->cport) ^ (!(cp->flags & IP_VS_CONN_F_NO_CPORT))) && - p->protocol == cp->protocol) { + p->protocol == cp->protocol && + ip_vs_conn_net_eq(cp, p->net)) { /* HIT */ atomic_inc(&cp->refcnt); ct_read_unlock(hash); @@ -313,23 +311,23 @@ ip_vs_conn_fill_param_proto(int af, const struct sk_buff *skb, struct ip_vs_conn_param *p) { __be16 _ports[2], *pptr; + struct net *net = skb_net(skb); pptr = skb_header_pointer(skb, proto_off, sizeof(_ports), _ports); if (pptr == NULL) return 1; if (likely(!inverse)) - ip_vs_conn_fill_param(af, iph->protocol, &iph->saddr, pptr[0], - &iph->daddr, pptr[1], p); + ip_vs_conn_fill_param(net, af, iph->protocol, &iph->saddr, + pptr[0], &iph->daddr, pptr[1], p); else - ip_vs_conn_fill_param(af, iph->protocol, &iph->daddr, pptr[1], - &iph->saddr, pptr[0], p); + ip_vs_conn_fill_param(net, af, iph->protocol, &iph->daddr, + pptr[1], &iph->saddr, pptr[0], p); return 0; } struct ip_vs_conn * ip_vs_conn_in_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse) { @@ -353,8 +351,10 @@ struct ip_vs_conn *ip_vs_ct_in_get(const struct ip_vs_conn_param *p) ct_read_lock(hash); list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { + if (!ip_vs_conn_net_eq(cp, p->net)) + continue; if (p->pe_data && p->pe->ct_match) { - if (p->pe->ct_match(p, cp)) + if (p->pe == cp->pe && p->pe->ct_match(p, cp)) goto out; continue; } @@ -404,10 +404,11 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) list_for_each_entry(cp, &ip_vs_conn_tab[hash], c_list) { if (cp->af == p->af && + p->vport == cp->cport && p->cport == cp->dport && ip_vs_addr_equal(p->af, p->vaddr, &cp->caddr) && ip_vs_addr_equal(p->af, p->caddr, &cp->daddr) && - p->vport == cp->cport && p->cport == cp->dport && - p->protocol == cp->protocol) { + p->protocol == cp->protocol && + ip_vs_conn_net_eq(cp, p->net)) { /* HIT */ atomic_inc(&cp->refcnt); ret = cp; @@ -428,7 +429,6 @@ struct ip_vs_conn *ip_vs_conn_out_get(const struct ip_vs_conn_param *p) struct ip_vs_conn * ip_vs_conn_out_get_proto(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse) { @@ -611,9 +611,9 @@ struct ip_vs_dest *ip_vs_try_bind_dest(struct ip_vs_conn *cp) struct ip_vs_dest *dest; if ((cp) && (!cp->dest)) { - dest = ip_vs_find_dest(cp->af, &cp->daddr, cp->dport, - &cp->vaddr, cp->vport, - cp->protocol); + dest = ip_vs_find_dest(ip_vs_conn_net(cp), cp->af, &cp->daddr, + cp->dport, &cp->vaddr, cp->vport, + cp->protocol, cp->fwmark); ip_vs_bind_dest(cp, dest); return dest; } else @@ -686,13 +686,14 @@ static inline void ip_vs_unbind_dest(struct ip_vs_conn *cp) int ip_vs_check_template(struct ip_vs_conn *ct) { struct ip_vs_dest *dest = ct->dest; + struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(ct)); /* * Checking the dest server status. */ if ((dest == NULL) || !(dest->flags & IP_VS_DEST_F_AVAILABLE) || - (sysctl_ip_vs_expire_quiescent_template && + (ipvs->sysctl_expire_quiescent_template && (atomic_read(&dest->weight) == 0))) { IP_VS_DBG_BUF(9, "check_template: dest not available for " "protocol %s s:%s:%d v:%s:%d " @@ -730,6 +731,7 @@ int ip_vs_check_template(struct ip_vs_conn *ct) static void ip_vs_conn_expire(unsigned long data) { struct ip_vs_conn *cp = (struct ip_vs_conn *)data; + struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); cp->timeout = 60*HZ; @@ -765,13 +767,14 @@ static void ip_vs_conn_expire(unsigned long data) if (cp->flags & IP_VS_CONN_F_NFCT) ip_vs_conn_drop_conntrack(cp); + ip_vs_pe_put(cp->pe); kfree(cp->pe_data); if (unlikely(cp->app != NULL)) ip_vs_unbind_app(cp); ip_vs_unbind_dest(cp); if (cp->flags & IP_VS_CONN_F_NO_CPORT) atomic_dec(&ip_vs_conn_no_cport_cnt); - atomic_dec(&ip_vs_conn_count); + atomic_dec(&ipvs->conn_count); kmem_cache_free(ip_vs_conn_cachep, cp); return; @@ -802,10 +805,12 @@ void ip_vs_conn_expire_now(struct ip_vs_conn *cp) struct ip_vs_conn * ip_vs_conn_new(const struct ip_vs_conn_param *p, const union nf_inet_addr *daddr, __be16 dport, unsigned flags, - struct ip_vs_dest *dest) + struct ip_vs_dest *dest, __u32 fwmark) { struct ip_vs_conn *cp; - struct ip_vs_protocol *pp = ip_vs_proto_get(p->protocol); + struct netns_ipvs *ipvs = net_ipvs(p->net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(p->net, + p->protocol); cp = kmem_cache_zalloc(ip_vs_conn_cachep, GFP_ATOMIC); if (cp == NULL) { @@ -815,6 +820,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, INIT_LIST_HEAD(&cp->c_list); setup_timer(&cp->timer, ip_vs_conn_expire, (unsigned long)cp); + ip_vs_conn_net_set(cp, p->net); cp->af = p->af; cp->protocol = p->protocol; ip_vs_addr_copy(p->af, &cp->caddr, p->caddr); @@ -826,7 +832,10 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, &cp->daddr, daddr); cp->dport = dport; cp->flags = flags; - if (flags & IP_VS_CONN_F_TEMPLATE && p->pe_data) { + cp->fwmark = fwmark; + if (flags & IP_VS_CONN_F_TEMPLATE && p->pe) { + ip_vs_pe_get(p->pe); + cp->pe = p->pe; cp->pe_data = p->pe_data; cp->pe_data_len = p->pe_data_len; } @@ -842,7 +851,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, atomic_set(&cp->n_control, 0); atomic_set(&cp->in_pkts, 0); - atomic_inc(&ip_vs_conn_count); + atomic_inc(&ipvs->conn_count); if (flags & IP_VS_CONN_F_NO_CPORT) atomic_inc(&ip_vs_conn_no_cport_cnt); @@ -861,8 +870,8 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, #endif ip_vs_bind_xmit(cp); - if (unlikely(pp && atomic_read(&pp->appcnt))) - ip_vs_bind_app(cp, pp); + if (unlikely(pd && atomic_read(&pd->appcnt))) + ip_vs_bind_app(cp, pd->pp); /* * Allow conntrack to be preserved. By default, conntrack @@ -871,7 +880,7 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, * IP_VS_CONN_F_ONE_PACKET too. */ - if (ip_vs_conntrack_enabled()) + if (ip_vs_conntrack_enabled(ipvs)) cp->flags |= IP_VS_CONN_F_NFCT; /* Hash it in the ip_vs_conn_tab finally */ @@ -884,17 +893,22 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p, * /proc/net/ip_vs_conn entries */ #ifdef CONFIG_PROC_FS +struct ip_vs_iter_state { + struct seq_net_private p; + struct list_head *l; +}; static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) { int idx; struct ip_vs_conn *cp; + struct ip_vs_iter_state *iter = seq->private; for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { ct_read_lock_bh(idx); list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { if (pos-- == 0) { - seq->private = &ip_vs_conn_tab[idx]; + iter->l = &ip_vs_conn_tab[idx]; return cp; } } @@ -906,14 +920,17 @@ static void *ip_vs_conn_array(struct seq_file *seq, loff_t pos) static void *ip_vs_conn_seq_start(struct seq_file *seq, loff_t *pos) { - seq->private = NULL; + struct ip_vs_iter_state *iter = seq->private; + + iter->l = NULL; return *pos ? ip_vs_conn_array(seq, *pos - 1) :SEQ_START_TOKEN; } static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_vs_conn *cp = v; - struct list_head *e, *l = seq->private; + struct ip_vs_iter_state *iter = seq->private; + struct list_head *e, *l = iter->l; int idx; ++*pos; @@ -930,18 +947,19 @@ static void *ip_vs_conn_seq_next(struct seq_file *seq, void *v, loff_t *pos) while (++idx < ip_vs_conn_tab_size) { ct_read_lock_bh(idx); list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { - seq->private = &ip_vs_conn_tab[idx]; + iter->l = &ip_vs_conn_tab[idx]; return cp; } ct_read_unlock_bh(idx); } - seq->private = NULL; + iter->l = NULL; return NULL; } static void ip_vs_conn_seq_stop(struct seq_file *seq, void *v) { - struct list_head *l = seq->private; + struct ip_vs_iter_state *iter = seq->private; + struct list_head *l = iter->l; if (l) ct_read_unlock_bh(l - ip_vs_conn_tab); @@ -955,18 +973,19 @@ static int ip_vs_conn_seq_show(struct seq_file *seq, void *v) "Pro FromIP FPrt ToIP TPrt DestIP DPrt State Expires PEName PEData\n"); else { const struct ip_vs_conn *cp = v; + struct net *net = seq_file_net(seq); char pe_data[IP_VS_PENAME_MAXLEN + IP_VS_PEDATA_MAXLEN + 3]; size_t len = 0; - if (cp->dest && cp->pe_data && - cp->dest->svc->pe->show_pe_data) { + if (!ip_vs_conn_net_eq(cp, net)) + return 0; + if (cp->pe_data) { pe_data[0] = ' '; - len = strlen(cp->dest->svc->pe->name); - memcpy(pe_data + 1, cp->dest->svc->pe->name, len); + len = strlen(cp->pe->name); + memcpy(pe_data + 1, cp->pe->name, len); pe_data[len + 1] = ' '; len += 2; - len += cp->dest->svc->pe->show_pe_data(cp, - pe_data + len); + len += cp->pe->show_pe_data(cp, pe_data + len); } pe_data[len] = '\0'; @@ -1004,7 +1023,8 @@ static const struct seq_operations ip_vs_conn_seq_ops = { static int ip_vs_conn_open(struct inode *inode, struct file *file) { - return seq_open(file, &ip_vs_conn_seq_ops); + return seq_open_net(inode, file, &ip_vs_conn_seq_ops, + sizeof(struct ip_vs_iter_state)); } static const struct file_operations ip_vs_conn_fops = { @@ -1031,6 +1051,10 @@ static int ip_vs_conn_sync_seq_show(struct seq_file *seq, void *v) "Pro FromIP FPrt ToIP TPrt DestIP DPrt State Origin Expires\n"); else { const struct ip_vs_conn *cp = v; + struct net *net = seq_file_net(seq); + + if (!ip_vs_conn_net_eq(cp, net)) + return 0; #ifdef CONFIG_IP_VS_IPV6 if (cp->af == AF_INET6) @@ -1067,7 +1091,8 @@ static const struct seq_operations ip_vs_conn_sync_seq_ops = { static int ip_vs_conn_sync_open(struct inode *inode, struct file *file) { - return seq_open(file, &ip_vs_conn_sync_seq_ops); + return seq_open_net(inode, file, &ip_vs_conn_sync_seq_ops, + sizeof(struct ip_vs_iter_state)); } static const struct file_operations ip_vs_conn_sync_fops = { @@ -1113,7 +1138,7 @@ static inline int todrop_entry(struct ip_vs_conn *cp) } /* Called from keventd and must protect itself from softirqs */ -void ip_vs_random_dropentry(void) +void ip_vs_random_dropentry(struct net *net) { int idx; struct ip_vs_conn *cp; @@ -1133,7 +1158,8 @@ void ip_vs_random_dropentry(void) if (cp->flags & IP_VS_CONN_F_TEMPLATE) /* connection template */ continue; - + if (!ip_vs_conn_net_eq(cp, net)) + continue; if (cp->protocol == IPPROTO_TCP) { switch(cp->state) { case IP_VS_TCP_S_SYN_RECV: @@ -1168,12 +1194,13 @@ void ip_vs_random_dropentry(void) /* * Flush all the connection entries in the ip_vs_conn_tab */ -static void ip_vs_conn_flush(void) +static void ip_vs_conn_flush(struct net *net) { int idx; struct ip_vs_conn *cp; + struct netns_ipvs *ipvs = net_ipvs(net); - flush_again: +flush_again: for (idx = 0; idx < ip_vs_conn_tab_size; idx++) { /* * Lock is actually needed in this loop. @@ -1181,7 +1208,8 @@ static void ip_vs_conn_flush(void) ct_write_lock_bh(idx); list_for_each_entry(cp, &ip_vs_conn_tab[idx], c_list) { - + if (!ip_vs_conn_net_eq(cp, net)) + continue; IP_VS_DBG(4, "del connection\n"); ip_vs_conn_expire_now(cp); if (cp->control) { @@ -1194,16 +1222,41 @@ static void ip_vs_conn_flush(void) /* the counter may be not NULL, because maybe some conn entries are run by slow timer handler or unhashed but still referred */ - if (atomic_read(&ip_vs_conn_count) != 0) { + if (atomic_read(&ipvs->conn_count) != 0) { schedule(); goto flush_again; } } +/* + * per netns init and exit + */ +int __net_init __ip_vs_conn_init(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + atomic_set(&ipvs->conn_count, 0); + + proc_net_fops_create(net, "ip_vs_conn", 0, &ip_vs_conn_fops); + proc_net_fops_create(net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops); + return 0; +} +static void __net_exit __ip_vs_conn_cleanup(struct net *net) +{ + /* flush all the connection entries first */ + ip_vs_conn_flush(net); + proc_net_remove(net, "ip_vs_conn"); + proc_net_remove(net, "ip_vs_conn_sync"); +} +static struct pernet_operations ipvs_conn_ops = { + .init = __ip_vs_conn_init, + .exit = __ip_vs_conn_cleanup, +}; int __init ip_vs_conn_init(void) { int idx; + int retc; /* Compute size and mask */ ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; @@ -1241,24 +1294,18 @@ int __init ip_vs_conn_init(void) rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); } - proc_net_fops_create(&init_net, "ip_vs_conn", 0, &ip_vs_conn_fops); - proc_net_fops_create(&init_net, "ip_vs_conn_sync", 0, &ip_vs_conn_sync_fops); + retc = register_pernet_subsys(&ipvs_conn_ops); /* calculate the random value for connection hash */ get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); - return 0; + return retc; } - void ip_vs_conn_cleanup(void) { - /* flush all the connection entries first */ - ip_vs_conn_flush(); - + unregister_pernet_subsys(&ipvs_conn_ops); /* Release the empty cache */ kmem_cache_destroy(ip_vs_conn_cachep); - proc_net_remove(&init_net, "ip_vs_conn"); - proc_net_remove(&init_net, "ip_vs_conn_sync"); vfree(ip_vs_conn_tab); } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index b4e51e9..d889f4f 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -41,6 +41,7 @@ #include <net/icmp.h> /* for icmp_send */ #include <net/route.h> #include <net/ip6_checksum.h> +#include <net/netns/generic.h> /* net_generic() */ #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> @@ -68,6 +69,12 @@ EXPORT_SYMBOL(ip_vs_conn_put); EXPORT_SYMBOL(ip_vs_get_debug_level); #endif +int ip_vs_net_id __read_mostly; +#ifdef IP_VS_GENERIC_NETNS +EXPORT_SYMBOL(ip_vs_net_id); +#endif +/* netns cnt used for uniqueness */ +static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0); /* ID used in ICMP lookups */ #define icmp_id(icmph) (((icmph)->un).echo.id) @@ -108,21 +115,28 @@ static inline void ip_vs_in_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; + struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); + if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { - spin_lock(&dest->stats.lock); - dest->stats.ustats.inpkts++; - dest->stats.ustats.inbytes += skb->len; - spin_unlock(&dest->stats.lock); - - spin_lock(&dest->svc->stats.lock); - dest->svc->stats.ustats.inpkts++; - dest->svc->stats.ustats.inbytes += skb->len; - spin_unlock(&dest->svc->stats.lock); - - spin_lock(&ip_vs_stats.lock); - ip_vs_stats.ustats.inpkts++; - ip_vs_stats.ustats.inbytes += skb->len; - spin_unlock(&ip_vs_stats.lock); + struct ip_vs_cpu_stats *s; + + s = this_cpu_ptr(dest->stats.cpustats); + s->ustats.inpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.inbytes += skb->len; + u64_stats_update_end(&s->syncp); + + s = this_cpu_ptr(dest->svc->stats.cpustats); + s->ustats.inpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.inbytes += skb->len; + u64_stats_update_end(&s->syncp); + + s = this_cpu_ptr(ipvs->cpustats); + s->ustats.inpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.inbytes += skb->len; + u64_stats_update_end(&s->syncp); } } @@ -131,21 +145,28 @@ static inline void ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) { struct ip_vs_dest *dest = cp->dest; + struct netns_ipvs *ipvs = net_ipvs(skb_net(skb)); + if (dest && (dest->flags & IP_VS_DEST_F_AVAILABLE)) { - spin_lock(&dest->stats.lock); - dest->stats.ustats.outpkts++; - dest->stats.ustats.outbytes += skb->len; - spin_unlock(&dest->stats.lock); - - spin_lock(&dest->svc->stats.lock); - dest->svc->stats.ustats.outpkts++; - dest->svc->stats.ustats.outbytes += skb->len; - spin_unlock(&dest->svc->stats.lock); - - spin_lock(&ip_vs_stats.lock); - ip_vs_stats.ustats.outpkts++; - ip_vs_stats.ustats.outbytes += skb->len; - spin_unlock(&ip_vs_stats.lock); + struct ip_vs_cpu_stats *s; + + s = this_cpu_ptr(dest->stats.cpustats); + s->ustats.outpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.outbytes += skb->len; + u64_stats_update_end(&s->syncp); + + s = this_cpu_ptr(dest->svc->stats.cpustats); + s->ustats.outpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.outbytes += skb->len; + u64_stats_update_end(&s->syncp); + + s = this_cpu_ptr(ipvs->cpustats); + s->ustats.outpkts++; + u64_stats_update_begin(&s->syncp); + s->ustats.outbytes += skb->len; + u64_stats_update_end(&s->syncp); } } @@ -153,41 +174,44 @@ ip_vs_out_stats(struct ip_vs_conn *cp, struct sk_buff *skb) static inline void ip_vs_conn_stats(struct ip_vs_conn *cp, struct ip_vs_service *svc) { - spin_lock(&cp->dest->stats.lock); - cp->dest->stats.ustats.conns++; - spin_unlock(&cp->dest->stats.lock); + struct netns_ipvs *ipvs = net_ipvs(svc->net); + struct ip_vs_cpu_stats *s; + + s = this_cpu_ptr(cp->dest->stats.cpustats); + s->ustats.conns++; - spin_lock(&svc->stats.lock); - svc->stats.ustats.conns++; - spin_unlock(&svc->stats.lock); + s = this_cpu_ptr(svc->stats.cpustats); + s->ustats.conns++; - spin_lock(&ip_vs_stats.lock); - ip_vs_stats.ustats.conns++; - spin_unlock(&ip_vs_stats.lock); + s = this_cpu_ptr(ipvs->cpustats); + s->ustats.conns++; } static inline int ip_vs_set_state(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_protocol *pp) + struct ip_vs_proto_data *pd) { - if (unlikely(!pp->state_transition)) + if (unlikely(!pd->pp->state_transition)) return 0; - return pp->state_transition(cp, direction, skb, pp); + return pd->pp->state_transition(cp, direction, skb, pd); } -static inline void +static inline int ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, struct sk_buff *skb, int protocol, const union nf_inet_addr *caddr, __be16 cport, const union nf_inet_addr *vaddr, __be16 vport, struct ip_vs_conn_param *p) { - ip_vs_conn_fill_param(svc->af, protocol, caddr, cport, vaddr, vport, p); + ip_vs_conn_fill_param(svc->net, svc->af, protocol, caddr, cport, vaddr, + vport, p); p->pe = svc->pe; if (p->pe && p->pe->fill_param) - p->pe->fill_param(p, skb); + return p->pe->fill_param(p, skb); + + return 0; } /* @@ -200,7 +224,7 @@ ip_vs_conn_fill_param_persist(const struct ip_vs_service *svc, static struct ip_vs_conn * ip_vs_sched_persist(struct ip_vs_service *svc, struct sk_buff *skb, - __be16 ports[2]) + __be16 src_port, __be16 dst_port, int *ignored) { struct ip_vs_conn *cp = NULL; struct ip_vs_iphdr iph; @@ -224,8 +248,8 @@ ip_vs_sched_persist(struct ip_vs_service *svc, IP_VS_DBG_BUF(6, "p-schedule: src %s:%u dest %s:%u " "mnet %s\n", - IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(ports[0]), - IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(ports[1]), + IP_VS_DBG_ADDR(svc->af, &iph.saddr), ntohs(src_port), + IP_VS_DBG_ADDR(svc->af, &iph.daddr), ntohs(dst_port), IP_VS_DBG_ADDR(svc->af, &snet)); /* @@ -247,14 +271,14 @@ ip_vs_sched_persist(struct ip_vs_service *svc, const union nf_inet_addr fwmark = { .ip = htonl(svc->fwmark) }; __be16 vport = 0; - if (ports[1] == svc->port) { + if (dst_port == svc->port) { /* non-FTP template: * <protocol, caddr, 0, vaddr, vport, daddr, dport> * FTP template: * <protocol, caddr, 0, vaddr, 0, daddr, 0> */ if (svc->port != FTPPORT) - vport = ports[1]; + vport = dst_port; } else { /* Note: persistent fwmark-based services and * persistent port zero service are handled here. @@ -268,24 +292,31 @@ ip_vs_sched_persist(struct ip_vs_service *svc, vaddr = &fwmark; } } - ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, - vaddr, vport, ¶m); + /* return *ignored = -1 so NF_DROP can be used */ + if (ip_vs_conn_fill_param_persist(svc, skb, protocol, &snet, 0, + vaddr, vport, ¶m) < 0) { + *ignored = -1; + return NULL; + } } /* Check if a template already exists */ ct = ip_vs_ct_in_get(¶m); if (!ct || !ip_vs_check_template(ct)) { - /* No template found or the dest of the connection + /* + * No template found or the dest of the connection * template is not available. + * return *ignored=0 i.e. ICMP and NF_DROP */ dest = svc->scheduler->schedule(svc, skb); if (!dest) { IP_VS_DBG(1, "p-schedule: no dest found.\n"); kfree(param.pe_data); + *ignored = 0; return NULL; } - if (ports[1] == svc->port && svc->port != FTPPORT) + if (dst_port == svc->port && svc->port != FTPPORT) dport = dest->port; /* Create a template @@ -293,9 +324,10 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * and thus param.pe_data will be destroyed * when the template expires */ ct = ip_vs_conn_new(¶m, &dest->addr, dport, - IP_VS_CONN_F_TEMPLATE, dest); + IP_VS_CONN_F_TEMPLATE, dest, skb->mark); if (ct == NULL) { kfree(param.pe_data); + *ignored = -1; return NULL; } @@ -306,7 +338,7 @@ ip_vs_sched_persist(struct ip_vs_service *svc, kfree(param.pe_data); } - dport = ports[1]; + dport = dst_port; if (dport == svc->port && dest->port) dport = dest->port; @@ -317,11 +349,13 @@ ip_vs_sched_persist(struct ip_vs_service *svc, /* * Create a new connection according to the template */ - ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, ports[0], - &iph.daddr, ports[1], ¶m); - cp = ip_vs_conn_new(¶m, &dest->addr, dport, flags, dest); + ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr, + src_port, &iph.daddr, dst_port, ¶m); + + cp = ip_vs_conn_new(¶m, &dest->addr, dport, flags, dest, skb->mark); if (cp == NULL) { ip_vs_conn_put(ct); + *ignored = -1; return NULL; } @@ -341,11 +375,27 @@ ip_vs_sched_persist(struct ip_vs_service *svc, * It selects a server according to the virtual service, and * creates a connection entry. * Protocols supported: TCP, UDP + * + * Usage of *ignored + * + * 1 : protocol tried to schedule (eg. on SYN), found svc but the + * svc/scheduler decides that this packet should be accepted with + * NF_ACCEPT because it must not be scheduled. + * + * 0 : scheduler can not find destination, so try bypass or + * return ICMP and then NF_DROP (ip_vs_leave). + * + * -1 : scheduler tried to schedule but fatal error occurred, eg. + * ip_vs_conn_new failure (ENOMEM) or ip_vs_sip_fill_param + * failure such as missing Call-ID, ENOMEM on skb_linearize + * or pe_data. In this case we should return NF_DROP without + * any attempts to send ICMP with ip_vs_leave. */ struct ip_vs_conn * ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp, int *ignored) + struct ip_vs_proto_data *pd, int *ignored) { + struct ip_vs_protocol *pp = pd->pp; struct ip_vs_conn *cp = NULL; struct ip_vs_iphdr iph; struct ip_vs_dest *dest; @@ -371,12 +421,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, } /* - * Do not schedule replies from local real server. It is risky - * for fwmark services but mostly for persistent services. + * Do not schedule replies from local real server. */ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK) && - (svc->flags & IP_VS_SVC_F_PERSISTENT || svc->fwmark) && - (cp = pp->conn_in_get(svc->af, skb, pp, &iph, iph.len, 1))) { + (cp = pp->conn_in_get(svc->af, skb, &iph, iph.len, 1))) { IP_VS_DBG_PKT(12, svc->af, pp, skb, 0, "Not scheduling reply for existing connection"); __ip_vs_conn_put(cp); @@ -386,10 +434,10 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, /* * Persistent service */ - if (svc->flags & IP_VS_SVC_F_PERSISTENT) { - *ignored = 0; - return ip_vs_sched_persist(svc, skb, pptr); - } + if (svc->flags & IP_VS_SVC_F_PERSISTENT) + return ip_vs_sched_persist(svc, skb, pptr[0], pptr[1], ignored); + + *ignored = 0; /* * Non-persistent service @@ -402,8 +450,6 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, return NULL; } - *ignored = 0; - dest = svc->scheduler->schedule(svc, skb); if (dest == NULL) { IP_VS_DBG(1, "Schedule: no dest found.\n"); @@ -419,13 +465,17 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, */ { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(svc->af, iph.protocol, &iph.saddr, - pptr[0], &iph.daddr, pptr[1], &p); + + ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, + &iph.saddr, pptr[0], &iph.daddr, pptr[1], + &p); cp = ip_vs_conn_new(&p, &dest->addr, dest->port ? dest->port : pptr[1], - flags, dest); - if (!cp) + flags, dest, skb->mark); + if (!cp) { + *ignored = -1; return NULL; + } } IP_VS_DBG_BUF(6, "Schedule fwd:%c c:%s:%u v:%s:%u " @@ -447,11 +497,14 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, * no destination is available for a new connection. */ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, - struct ip_vs_protocol *pp) + struct ip_vs_proto_data *pd) { + struct net *net; + struct netns_ipvs *ipvs; __be16 _ports[2], *pptr; struct ip_vs_iphdr iph; int unicast; + ip_vs_fill_iphdr(svc->af, skb_network_header(skb), &iph); pptr = skb_header_pointer(skb, iph.len, sizeof(_ports), _ports); @@ -459,18 +512,20 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_service_put(svc); return NF_DROP; } + net = skb_net(skb); #ifdef CONFIG_IP_VS_IPV6 if (svc->af == AF_INET6) unicast = ipv6_addr_type(&iph.daddr.in6) & IPV6_ADDR_UNICAST; else #endif - unicast = (inet_addr_type(&init_net, iph.daddr.ip) == RTN_UNICAST); + unicast = (inet_addr_type(net, iph.daddr.ip) == RTN_UNICAST); /* if it is fwmark-based service, the cache_bypass sysctl is up and the destination is a non-local unicast, then create a cache_bypass connection entry */ - if (sysctl_ip_vs_cache_bypass && svc->fwmark && unicast) { + ipvs = net_ipvs(net); + if (ipvs->sysctl_cache_bypass && svc->fwmark && unicast) { int ret, cs; struct ip_vs_conn *cp; unsigned int flags = (svc->flags & IP_VS_SVC_F_ONEPACKET && @@ -484,12 +539,12 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, IP_VS_DBG(6, "%s(): create a cache_bypass entry\n", __func__); { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(svc->af, iph.protocol, + ip_vs_conn_fill_param(svc->net, svc->af, iph.protocol, &iph.saddr, pptr[0], &iph.daddr, pptr[1], &p); cp = ip_vs_conn_new(&p, &daddr, 0, IP_VS_CONN_F_BYPASS | flags, - NULL); + NULL, skb->mark); if (!cp) return NF_DROP; } @@ -498,10 +553,10 @@ int ip_vs_leave(struct ip_vs_service *svc, struct sk_buff *skb, ip_vs_in_stats(cp, skb); /* set state */ - cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp); + cs = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); /* transmit the first SYN packet */ - ret = cp->packet_xmit(skb, cp, pp); + ret = cp->packet_xmit(skb, cp, pd->pp); /* do not touch skb anymore */ atomic_inc(&cp->in_pkts); @@ -682,6 +737,7 @@ static int handle_response_icmp(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, unsigned int offset, unsigned int ihl) { + struct netns_ipvs *ipvs; unsigned int verdict = NF_DROP; if (IP_VS_FWD_METHOD(cp) != 0) { @@ -703,6 +759,8 @@ static int handle_response_icmp(int af, struct sk_buff *skb, if (!skb_make_writable(skb, offset)) goto out; + ipvs = net_ipvs(skb_net(skb)); + #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_nat_icmp_v6(skb, pp, cp, 1); @@ -712,11 +770,11 @@ static int handle_response_icmp(int af, struct sk_buff *skb, #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0) + if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0) goto out; } else #endif - if ((sysctl_ip_vs_snat_reroute || + if ((ipvs->sysctl_snat_reroute || skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(skb, RTN_LOCAL) != 0) goto out; @@ -808,7 +866,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, ip_vs_fill_iphdr(AF_INET, cih, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1); + cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1); if (!cp) return NF_ACCEPT; @@ -885,7 +943,7 @@ static int ip_vs_out_icmp_v6(struct sk_buff *skb, int *related, ip_vs_fill_iphdr(AF_INET6, cih, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1); + cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1); if (!cp) return NF_ACCEPT; @@ -924,9 +982,12 @@ static inline int is_tcp_reset(const struct sk_buff *skb, int nh_len) * Used for NAT and local client. */ static unsigned int -handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, +handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int ihl) { + struct ip_vs_protocol *pp = pd->pp; + struct netns_ipvs *ipvs; + IP_VS_DBG_PKT(11, af, pp, skb, 0, "Outgoing packet"); if (!skb_make_writable(skb, ihl)) @@ -961,13 +1022,15 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * if it came from this machine itself. So re-compute * the routing information. */ + ipvs = net_ipvs(skb_net(skb)); + #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { - if (sysctl_ip_vs_snat_reroute && ip6_route_me_harder(skb) != 0) + if (ipvs->sysctl_snat_reroute && ip6_route_me_harder(skb) != 0) goto drop; } else #endif - if ((sysctl_ip_vs_snat_reroute || + if ((ipvs->sysctl_snat_reroute || skb_rtable(skb)->rt_flags & RTCF_LOCAL) && ip_route_me_harder(skb, RTN_LOCAL) != 0) goto drop; @@ -975,7 +1038,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, IP_VS_DBG_PKT(10, af, pp, skb, 0, "After SNAT"); ip_vs_out_stats(cp, skb); - ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp); + ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pd); skb->ipvs_property = 1; if (!(cp->flags & IP_VS_CONN_F_NFCT)) ip_vs_notrack(skb); @@ -999,9 +1062,12 @@ drop: static unsigned int ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) { + struct net *net = NULL; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; + struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; + struct netns_ipvs *ipvs; EnterFunction(11); @@ -1022,6 +1088,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) if (unlikely(!skb_dst(skb))) return NF_ACCEPT; + net = skb_net(skb); ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { @@ -1045,9 +1112,10 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } - pp = ip_vs_proto_get(iph.protocol); - if (unlikely(!pp)) + pd = ip_vs_proto_data_get(net, iph.protocol); + if (unlikely(!pd)) return NF_ACCEPT; + pp = pd->pp; /* reassemble IP fragments */ #ifdef CONFIG_IP_VS_IPV6 @@ -1073,11 +1141,12 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(af, skb, pp, &iph, iph.len, 0); + cp = pp->conn_out_get(af, skb, &iph, iph.len, 0); + ipvs = net_ipvs(net); if (likely(cp)) - return handle_response(af, skb, pp, cp, iph.len); - if (sysctl_ip_vs_nat_icmp_send && + return handle_response(af, skb, pd, cp, iph.len); + if (ipvs->sysctl_nat_icmp_send && (pp->protocol == IPPROTO_TCP || pp->protocol == IPPROTO_UDP || pp->protocol == IPPROTO_SCTP)) { @@ -1087,7 +1156,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) sizeof(_ports), _ports); if (pptr == NULL) return NF_ACCEPT; /* Not for me */ - if (ip_vs_lookup_real_service(af, iph.protocol, + if (ip_vs_lookup_real_service(net, af, iph.protocol, &iph.saddr, pptr[0])) { /* @@ -1202,12 +1271,14 @@ ip_vs_local_reply6(unsigned int hooknum, struct sk_buff *skb, static int ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) { + struct net *net = NULL; struct iphdr *iph; struct icmphdr _icmph, *ic; struct iphdr _ciph, *cih; /* The ip header contained within the ICMP */ struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; + struct ip_vs_proto_data *pd; unsigned int offset, ihl, verdict; union nf_inet_addr snet; @@ -1249,9 +1320,11 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ - pp = ip_vs_proto_get(cih->protocol); - if (!pp) + net = skb_net(skb); + pd = ip_vs_proto_data_get(net, cih->protocol); + if (!pd) return NF_ACCEPT; + pp = pd->pp; /* Is the embedded protocol header present? */ if (unlikely(cih->frag_off & htons(IP_OFFSET) && @@ -1265,10 +1338,10 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) ip_vs_fill_iphdr(AF_INET, cih, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_in_get(AF_INET, skb, pp, &ciph, offset, 1); + cp = pp->conn_in_get(AF_INET, skb, &ciph, offset, 1); if (!cp) { /* The packet could also belong to a local client */ - cp = pp->conn_out_get(AF_INET, skb, pp, &ciph, offset, 1); + cp = pp->conn_out_get(AF_INET, skb, &ciph, offset, 1); if (cp) { snet.ip = iph->saddr; return handle_response_icmp(AF_INET, skb, &snet, @@ -1312,6 +1385,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) static int ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) { + struct net *net = NULL; struct ipv6hdr *iph; struct icmp6hdr _icmph, *ic; struct ipv6hdr _ciph, *cih; /* The ip header contained @@ -1319,6 +1393,7 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) struct ip_vs_iphdr ciph; struct ip_vs_conn *cp; struct ip_vs_protocol *pp; + struct ip_vs_proto_data *pd; unsigned int offset, verdict; union nf_inet_addr snet; struct rt6_info *rt; @@ -1361,9 +1436,11 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) if (cih == NULL) return NF_ACCEPT; /* The packet looks wrong, ignore */ - pp = ip_vs_proto_get(cih->nexthdr); - if (!pp) + net = skb_net(skb); + pd = ip_vs_proto_data_get(net, cih->nexthdr); + if (!pd) return NF_ACCEPT; + pp = pd->pp; /* Is the embedded protocol header present? */ /* TODO: we don't support fragmentation at the moment anyways */ @@ -1377,10 +1454,10 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) ip_vs_fill_iphdr(AF_INET6, cih, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_in_get(AF_INET6, skb, pp, &ciph, offset, 1); + cp = pp->conn_in_get(AF_INET6, skb, &ciph, offset, 1); if (!cp) { /* The packet could also belong to a local client */ - cp = pp->conn_out_get(AF_INET6, skb, pp, &ciph, offset, 1); + cp = pp->conn_out_get(AF_INET6, skb, &ciph, offset, 1); if (cp) { ipv6_addr_copy(&snet.in6, &iph->saddr); return handle_response_icmp(AF_INET6, skb, &snet, @@ -1423,10 +1500,13 @@ ip_vs_in_icmp_v6(struct sk_buff *skb, int *related, unsigned int hooknum) static unsigned int ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) { + struct net *net; struct ip_vs_iphdr iph; struct ip_vs_protocol *pp; + struct ip_vs_proto_data *pd; struct ip_vs_conn *cp; int ret, restart, pkts; + struct netns_ipvs *ipvs; /* Already marked as IPVS request or reply? */ if (skb->ipvs_property) @@ -1480,20 +1560,21 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } + net = skb_net(skb); /* Protocol supported? */ - pp = ip_vs_proto_get(iph.protocol); - if (unlikely(!pp)) + pd = ip_vs_proto_data_get(net, iph.protocol); + if (unlikely(!pd)) return NF_ACCEPT; - + pp = pd->pp; /* * Check if the packet belongs to an existing connection entry */ - cp = pp->conn_in_get(af, skb, pp, &iph, iph.len, 0); + cp = pp->conn_in_get(af, skb, &iph, iph.len, 0); if (unlikely(!cp)) { int v; - if (!pp->conn_schedule(af, skb, pp, &v, &cp)) + if (!pp->conn_schedule(af, skb, pd, &v, &cp)) return v; } @@ -1505,12 +1586,13 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); - + net = skb_net(skb); + ipvs = net_ipvs(net); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { /* the destination server is not available */ - if (sysctl_ip_vs_expire_nodest_conn) { + if (ipvs->sysctl_expire_nodest_conn) { /* try to expire the connection immediately */ ip_vs_conn_expire_now(cp); } @@ -1521,7 +1603,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } ip_vs_in_stats(cp, skb); - restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pp); + restart = ip_vs_set_state(cp, IP_VS_DIR_INPUT, skb, pd); if (cp->packet_xmit) ret = cp->packet_xmit(skb, cp, pp); /* do not touch skb anymore */ @@ -1535,35 +1617,41 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) * * Sync connection if it is about to close to * encorage the standby servers to update the connections timeout + * + * For ONE_PKT let ip_vs_sync_conn() do the filter work. */ - pkts = atomic_add_return(1, &cp->in_pkts); - if (af == AF_INET && (ip_vs_sync_state & IP_VS_STATE_MASTER) && + + if (cp->flags & IP_VS_CONN_F_ONE_PACKET) + pkts = ipvs->sysctl_sync_threshold[0]; + else + pkts = atomic_add_return(1, &cp->in_pkts); + + if ((ipvs->sync_state & IP_VS_STATE_MASTER) && cp->protocol == IPPROTO_SCTP) { if ((cp->state == IP_VS_SCTP_S_ESTABLISHED && - (pkts % sysctl_ip_vs_sync_threshold[1] - == sysctl_ip_vs_sync_threshold[0])) || + (pkts % ipvs->sysctl_sync_threshold[1] + == ipvs->sysctl_sync_threshold[0])) || (cp->old_state != cp->state && ((cp->state == IP_VS_SCTP_S_CLOSED) || (cp->state == IP_VS_SCTP_S_SHUT_ACK_CLI) || (cp->state == IP_VS_SCTP_S_SHUT_ACK_SER)))) { - ip_vs_sync_conn(cp); + ip_vs_sync_conn(net, cp); goto out; } } /* Keep this block last: TCP and others with pp->num_states <= 1 */ - else if (af == AF_INET && - (ip_vs_sync_state & IP_VS_STATE_MASTER) && + else if ((ipvs->sync_state & IP_VS_STATE_MASTER) && (((cp->protocol != IPPROTO_TCP || cp->state == IP_VS_TCP_S_ESTABLISHED) && - (pkts % sysctl_ip_vs_sync_threshold[1] - == sysctl_ip_vs_sync_threshold[0])) || + (pkts % ipvs->sysctl_sync_threshold[1] + == ipvs->sysctl_sync_threshold[0])) || ((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) && ((cp->state == IP_VS_TCP_S_FIN_WAIT) || (cp->state == IP_VS_TCP_S_CLOSE) || (cp->state == IP_VS_TCP_S_CLOSE_WAIT) || (cp->state == IP_VS_TCP_S_TIME_WAIT))))) - ip_vs_sync_conn(cp); + ip_vs_sync_conn(net, cp); out: cp->old_state = cp->state; @@ -1782,7 +1870,39 @@ static struct nf_hook_ops ip_vs_ops[] __read_mostly = { }, #endif }; +/* + * Initialize IP Virtual Server netns mem. + */ +static int __net_init __ip_vs_init(struct net *net) +{ + struct netns_ipvs *ipvs; + + ipvs = net_generic(net, ip_vs_net_id); + if (ipvs == NULL) { + pr_err("%s(): no memory.\n", __func__); + return -ENOMEM; + } + ipvs->net = net; + /* Counters used for creating unique names */ + ipvs->gen = atomic_read(&ipvs_netns_cnt); + atomic_inc(&ipvs_netns_cnt); + net->ipvs = ipvs; + printk(KERN_INFO "IPVS: Creating netns size=%lu id=%d\n", + sizeof(struct netns_ipvs), ipvs->gen); + return 0; +} +static void __net_exit __ip_vs_cleanup(struct net *net) +{ + IP_VS_DBG(10, "ipvs netns %d released\n", net_ipvs(net)->gen); +} + +static struct pernet_operations ipvs_core_ops = { + .init = __ip_vs_init, + .exit = __ip_vs_cleanup, + .id = &ip_vs_net_id, + .size = sizeof(struct netns_ipvs), +}; /* * Initialize IP Virtual Server @@ -1791,8 +1911,11 @@ static int __init ip_vs_init(void) { int ret; - ip_vs_estimator_init(); + ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ + if (ret < 0) + return ret; + ip_vs_estimator_init(); ret = ip_vs_control_init(); if (ret < 0) { pr_err("can't setup control.\n"); @@ -1813,15 +1936,23 @@ static int __init ip_vs_init(void) goto cleanup_app; } + ret = ip_vs_sync_init(); + if (ret < 0) { + pr_err("can't setup sync data.\n"); + goto cleanup_conn; + } + ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); if (ret < 0) { pr_err("can't register hooks.\n"); - goto cleanup_conn; + goto cleanup_sync; } pr_info("ipvs loaded.\n"); return ret; +cleanup_sync: + ip_vs_sync_cleanup(); cleanup_conn: ip_vs_conn_cleanup(); cleanup_app: @@ -1831,17 +1962,20 @@ static int __init ip_vs_init(void) ip_vs_control_cleanup(); cleanup_estimator: ip_vs_estimator_cleanup(); + unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ return ret; } static void __exit ip_vs_cleanup(void) { nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); + ip_vs_sync_cleanup(); ip_vs_conn_cleanup(); ip_vs_app_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); ip_vs_estimator_cleanup(); + unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ pr_info("ipvs unloaded.\n"); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 22f7ad5..98df59a 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -38,6 +38,7 @@ #include <linux/mutex.h> #include <net/net_namespace.h> +#include <linux/nsproxy.h> #include <net/ip.h> #ifdef CONFIG_IP_VS_IPV6 #include <net/ipv6.h> @@ -57,42 +58,7 @@ static DEFINE_MUTEX(__ip_vs_mutex); /* lock for service table */ static DEFINE_RWLOCK(__ip_vs_svc_lock); -/* lock for table with the real services */ -static DEFINE_RWLOCK(__ip_vs_rs_lock); - -/* lock for state and timeout tables */ -static DEFINE_SPINLOCK(ip_vs_securetcp_lock); - -/* lock for drop entry handling */ -static DEFINE_SPINLOCK(__ip_vs_dropentry_lock); - -/* lock for drop packet handling */ -static DEFINE_SPINLOCK(__ip_vs_droppacket_lock); - -/* 1/rate drop and drop-entry variables */ -int ip_vs_drop_rate = 0; -int ip_vs_drop_counter = 0; -static atomic_t ip_vs_dropentry = ATOMIC_INIT(0); - -/* number of virtual services */ -static int ip_vs_num_services = 0; - /* sysctl variables */ -static int sysctl_ip_vs_drop_entry = 0; -static int sysctl_ip_vs_drop_packet = 0; -static int sysctl_ip_vs_secure_tcp = 0; -static int sysctl_ip_vs_amemthresh = 1024; -static int sysctl_ip_vs_am_droprate = 10; -int sysctl_ip_vs_cache_bypass = 0; -int sysctl_ip_vs_expire_nodest_conn = 0; -int sysctl_ip_vs_expire_quiescent_template = 0; -int sysctl_ip_vs_sync_threshold[2] = { 3, 50 }; -int sysctl_ip_vs_nat_icmp_send = 0; -#ifdef CONFIG_IP_VS_NFCT -int sysctl_ip_vs_conntrack; -#endif -int sysctl_ip_vs_snat_reroute = 1; - #ifdef CONFIG_IP_VS_DEBUG static int sysctl_ip_vs_debug_level = 0; @@ -105,7 +71,8 @@ int ip_vs_get_debug_level(void) #ifdef CONFIG_IP_VS_IPV6 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ -static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr) +static int __ip_vs_addr_is_local_v6(struct net *net, + const struct in6_addr *addr) { struct rt6_info *rt; struct flowi fl = { @@ -114,7 +81,7 @@ static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr) .fl6_src = { .s6_addr32 = {0, 0, 0, 0} }, }; - rt = (struct rt6_info *)ip6_route_output(&init_net, NULL, &fl); + rt = (struct rt6_info *)ip6_route_output(net, NULL, &fl); if (rt && rt->rt6i_dev && (rt->rt6i_dev->flags & IFF_LOOPBACK)) return 1; @@ -125,7 +92,7 @@ static int __ip_vs_addr_is_local_v6(const struct in6_addr *addr) * update_defense_level is called from keventd and from sysctl, * so it needs to protect itself from softirqs */ -static void update_defense_level(void) +static void update_defense_level(struct netns_ipvs *ipvs) { struct sysinfo i; static int old_secure_tcp = 0; @@ -141,73 +108,73 @@ static void update_defense_level(void) /* si_swapinfo(&i); */ /* availmem = availmem - (i.totalswap - i.freeswap); */ - nomem = (availmem < sysctl_ip_vs_amemthresh); + nomem = (availmem < ipvs->sysctl_amemthresh); local_bh_disable(); /* drop_entry */ - spin_lock(&__ip_vs_dropentry_lock); - switch (sysctl_ip_vs_drop_entry) { + spin_lock(&ipvs->dropentry_lock); + switch (ipvs->sysctl_drop_entry) { case 0: - atomic_set(&ip_vs_dropentry, 0); + atomic_set(&ipvs->dropentry, 0); break; case 1: if (nomem) { - atomic_set(&ip_vs_dropentry, 1); - sysctl_ip_vs_drop_entry = 2; + atomic_set(&ipvs->dropentry, 1); + ipvs->sysctl_drop_entry = 2; } else { - atomic_set(&ip_vs_dropentry, 0); + atomic_set(&ipvs->dropentry, 0); } break; case 2: if (nomem) { - atomic_set(&ip_vs_dropentry, 1); + atomic_set(&ipvs->dropentry, 1); } else { - atomic_set(&ip_vs_dropentry, 0); - sysctl_ip_vs_drop_entry = 1; + atomic_set(&ipvs->dropentry, 0); + ipvs->sysctl_drop_entry = 1; }; break; case 3: - atomic_set(&ip_vs_dropentry, 1); + atomic_set(&ipvs->dropentry, 1); break; } - spin_unlock(&__ip_vs_dropentry_lock); + spin_unlock(&ipvs->dropentry_lock); /* drop_packet */ - spin_lock(&__ip_vs_droppacket_lock); - switch (sysctl_ip_vs_drop_packet) { + spin_lock(&ipvs->droppacket_lock); + switch (ipvs->sysctl_drop_packet) { case 0: - ip_vs_drop_rate = 0; + ipvs->drop_rate = 0; break; case 1: if (nomem) { - ip_vs_drop_rate = ip_vs_drop_counter - = sysctl_ip_vs_amemthresh / - (sysctl_ip_vs_amemthresh-availmem); - sysctl_ip_vs_drop_packet = 2; + ipvs->drop_rate = ipvs->drop_counter + = ipvs->sysctl_amemthresh / + (ipvs->sysctl_amemthresh-availmem); + ipvs->sysctl_drop_packet = 2; } else { - ip_vs_drop_rate = 0; + ipvs->drop_rate = 0; } break; case 2: if (nomem) { - ip_vs_drop_rate = ip_vs_drop_counter - = sysctl_ip_vs_amemthresh / - (sysctl_ip_vs_amemthresh-availmem); + ipvs->drop_rate = ipvs->drop_counter + = ipvs->sysctl_amemthresh / + (ipvs->sysctl_amemthresh-availmem); } else { - ip_vs_drop_rate = 0; - sysctl_ip_vs_drop_packet = 1; + ipvs->drop_rate = 0; + ipvs->sysctl_drop_packet = 1; } break; case 3: - ip_vs_drop_rate = sysctl_ip_vs_am_droprate; + ipvs->drop_rate = ipvs->sysctl_am_droprate; break; } - spin_unlock(&__ip_vs_droppacket_lock); + spin_unlock(&ipvs->droppacket_lock); /* secure_tcp */ - spin_lock(&ip_vs_securetcp_lock); - switch (sysctl_ip_vs_secure_tcp) { + spin_lock(&ipvs->securetcp_lock); + switch (ipvs->sysctl_secure_tcp) { case 0: if (old_secure_tcp >= 2) to_change = 0; @@ -216,7 +183,7 @@ static void update_defense_level(void) if (nomem) { if (old_secure_tcp < 2) to_change = 1; - sysctl_ip_vs_secure_tcp = 2; + ipvs->sysctl_secure_tcp = 2; } else { if (old_secure_tcp >= 2) to_change = 0; @@ -229,7 +196,7 @@ static void update_defense_level(void) } else { if (old_secure_tcp >= 2) to_change = 0; - sysctl_ip_vs_secure_tcp = 1; + ipvs->sysctl_secure_tcp = 1; } break; case 3: @@ -237,10 +204,11 @@ static void update_defense_level(void) to_change = 1; break; } - old_secure_tcp = sysctl_ip_vs_secure_tcp; + old_secure_tcp = ipvs->sysctl_secure_tcp; if (to_change >= 0) - ip_vs_protocol_timeout_change(sysctl_ip_vs_secure_tcp>1); - spin_unlock(&ip_vs_securetcp_lock); + ip_vs_protocol_timeout_change(ipvs, + ipvs->sysctl_secure_tcp > 1); + spin_unlock(&ipvs->securetcp_lock); local_bh_enable(); } @@ -250,16 +218,16 @@ static void update_defense_level(void) * Timer for checking the defense */ #define DEFENSE_TIMER_PERIOD 1*HZ -static void defense_work_handler(struct work_struct *work); -static DECLARE_DELAYED_WORK(defense_work, defense_work_handler); static void defense_work_handler(struct work_struct *work) { - update_defense_level(); - if (atomic_read(&ip_vs_dropentry)) - ip_vs_random_dropentry(); + struct netns_ipvs *ipvs = + container_of(work, struct netns_ipvs, defense_work.work); - schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD); + update_defense_level(ipvs); + if (atomic_read(&ipvs->dropentry)) + ip_vs_random_dropentry(ipvs->net); + schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD); } int @@ -287,33 +255,13 @@ static struct list_head ip_vs_svc_table[IP_VS_SVC_TAB_SIZE]; /* the service table hashed by fwmark */ static struct list_head ip_vs_svc_fwm_table[IP_VS_SVC_TAB_SIZE]; -/* - * Hash table: for real service lookups - */ -#define IP_VS_RTAB_BITS 4 -#define IP_VS_RTAB_SIZE (1 << IP_VS_RTAB_BITS) -#define IP_VS_RTAB_MASK (IP_VS_RTAB_SIZE - 1) - -static struct list_head ip_vs_rtable[IP_VS_RTAB_SIZE]; - -/* - * Trash for destinations - */ -static LIST_HEAD(ip_vs_dest_trash); - -/* - * FTP & NULL virtual service counters - */ -static atomic_t ip_vs_ftpsvc_counter = ATOMIC_INIT(0); -static atomic_t ip_vs_nullsvc_counter = ATOMIC_INIT(0); - /* * Returns hash value for virtual service */ -static __inline__ unsigned -ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr, - __be16 port) +static inline unsigned +ip_vs_svc_hashkey(struct net *net, int af, unsigned proto, + const union nf_inet_addr *addr, __be16 port) { register unsigned porth = ntohs(port); __be32 addr_fold = addr->ip; @@ -323,6 +271,7 @@ ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr, addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif + addr_fold ^= ((size_t)net>>8); return (proto^ntohl(addr_fold)^(porth>>IP_VS_SVC_TAB_BITS)^porth) & IP_VS_SVC_TAB_MASK; @@ -331,13 +280,13 @@ ip_vs_svc_hashkey(int af, unsigned proto, const union nf_inet_addr *addr, /* * Returns hash value of fwmark for virtual service lookup */ -static __inline__ unsigned ip_vs_svc_fwm_hashkey(__u32 fwmark) +static inline unsigned ip_vs_svc_fwm_hashkey(struct net *net, __u32 fwmark) { - return fwmark & IP_VS_SVC_TAB_MASK; + return (((size_t)net>>8) ^ fwmark) & IP_VS_SVC_TAB_MASK; } /* - * Hashes a service in the ip_vs_svc_table by <proto,addr,port> + * Hashes a service in the ip_vs_svc_table by <netns,proto,addr,port> * or in the ip_vs_svc_fwm_table by fwmark. * Should be called with locked tables. */ @@ -353,16 +302,16 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) if (svc->fwmark == 0) { /* - * Hash it by <protocol,addr,port> in ip_vs_svc_table + * Hash it by <netns,protocol,addr,port> in ip_vs_svc_table */ - hash = ip_vs_svc_hashkey(svc->af, svc->protocol, &svc->addr, - svc->port); + hash = ip_vs_svc_hashkey(svc->net, svc->af, svc->protocol, + &svc->addr, svc->port); list_add(&svc->s_list, &ip_vs_svc_table[hash]); } else { /* - * Hash it by fwmark in ip_vs_svc_fwm_table + * Hash it by fwmark in svc_fwm_table */ - hash = ip_vs_svc_fwm_hashkey(svc->fwmark); + hash = ip_vs_svc_fwm_hashkey(svc->net, svc->fwmark); list_add(&svc->f_list, &ip_vs_svc_fwm_table[hash]); } @@ -374,7 +323,7 @@ static int ip_vs_svc_hash(struct ip_vs_service *svc) /* - * Unhashes a service from ip_vs_svc_table/ip_vs_svc_fwm_table. + * Unhashes a service from svc_table / svc_fwm_table. * Should be called with locked tables. */ static int ip_vs_svc_unhash(struct ip_vs_service *svc) @@ -386,10 +335,10 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc) } if (svc->fwmark == 0) { - /* Remove it from the ip_vs_svc_table table */ + /* Remove it from the svc_table table */ list_del(&svc->s_list); } else { - /* Remove it from the ip_vs_svc_fwm_table table */ + /* Remove it from the svc_fwm_table table */ list_del(&svc->f_list); } @@ -400,23 +349,24 @@ static int ip_vs_svc_unhash(struct ip_vs_service *svc) /* - * Get service by {proto,addr,port} in the service table. + * Get service by {netns, proto,addr,port} in the service table. */ static inline struct ip_vs_service * -__ip_vs_service_find(int af, __u16 protocol, const union nf_inet_addr *vaddr, - __be16 vport) +__ip_vs_service_find(struct net *net, int af, __u16 protocol, + const union nf_inet_addr *vaddr, __be16 vport) { unsigned hash; struct ip_vs_service *svc; /* Check for "full" addressed entries */ - hash = ip_vs_svc_hashkey(af, protocol, vaddr, vport); + hash = ip_vs_svc_hashkey(net, af, protocol, vaddr, vport); list_for_each_entry(svc, &ip_vs_svc_table[hash], s_list){ if ((svc->af == af) && ip_vs_addr_equal(af, &svc->addr, vaddr) && (svc->port == vport) - && (svc->protocol == protocol)) { + && (svc->protocol == protocol) + && net_eq(svc->net, net)) { /* HIT */ return svc; } @@ -430,16 +380,17 @@ __ip_vs_service_find(int af, __u16 protocol, const union nf_inet_addr *vaddr, * Get service by {fwmark} in the service table. */ static inline struct ip_vs_service * -__ip_vs_svc_fwm_find(int af, __u32 fwmark) +__ip_vs_svc_fwm_find(struct net *net, int af, __u32 fwmark) { unsigned hash; struct ip_vs_service *svc; /* Check for fwmark addressed entries */ - hash = ip_vs_svc_fwm_hashkey(fwmark); + hash = ip_vs_svc_fwm_hashkey(net, fwmark); list_for_each_entry(svc, &ip_vs_svc_fwm_table[hash], f_list) { - if (svc->fwmark == fwmark && svc->af == af) { + if (svc->fwmark == fwmark && svc->af == af + && net_eq(svc->net, net)) { /* HIT */ return svc; } @@ -449,42 +400,44 @@ __ip_vs_svc_fwm_find(int af, __u32 fwmark) } struct ip_vs_service * -ip_vs_service_get(int af, __u32 fwmark, __u16 protocol, +ip_vs_service_get(struct net *net, int af, __u32 fwmark, __u16 protocol, const union nf_inet_addr *vaddr, __be16 vport) { struct ip_vs_service *svc; + struct netns_ipvs *ipvs = net_ipvs(net); read_lock(&__ip_vs_svc_lock); /* * Check the table hashed by fwmark first */ - if (fwmark && (svc = __ip_vs_svc_fwm_find(af, fwmark))) + svc = __ip_vs_svc_fwm_find(net, af, fwmark); + if (fwmark && svc) goto out; /* * Check the table hashed by <protocol,addr,port> * for "full" addressed entries */ - svc = __ip_vs_service_find(af, protocol, vaddr, vport); + svc = __ip_vs_service_find(net, af, protocol, vaddr, vport); if (svc == NULL && protocol == IPPROTO_TCP - && atomic_read(&ip_vs_ftpsvc_counter) + && atomic_read(&ipvs->ftpsvc_counter) && (vport == FTPDATA || ntohs(vport) >= PROT_SOCK)) { /* * Check if ftp service entry exists, the packet * might belong to FTP data connections. */ - svc = __ip_vs_service_find(af, protocol, vaddr, FTPPORT); + svc = __ip_vs_service_find(net, af, protocol, vaddr, FTPPORT); } if (svc == NULL - && atomic_read(&ip_vs_nullsvc_counter)) { + && atomic_read(&ipvs->nullsvc_counter)) { /* * Check if the catch-all port (port zero) exists */ - svc = __ip_vs_service_find(af, protocol, vaddr, 0); + svc = __ip_vs_service_find(net, af, protocol, vaddr, 0); } out: @@ -519,6 +472,7 @@ __ip_vs_unbind_svc(struct ip_vs_dest *dest) svc->fwmark, IP_VS_DBG_ADDR(svc->af, &svc->addr), ntohs(svc->port), atomic_read(&svc->usecnt)); + free_percpu(svc->stats.cpustats); kfree(svc); } } @@ -545,10 +499,10 @@ static inline unsigned ip_vs_rs_hashkey(int af, } /* - * Hashes ip_vs_dest in ip_vs_rtable by <proto,addr,port>. + * Hashes ip_vs_dest in rs_table by <proto,addr,port>. * should be called with locked tables. */ -static int ip_vs_rs_hash(struct ip_vs_dest *dest) +static int ip_vs_rs_hash(struct netns_ipvs *ipvs, struct ip_vs_dest *dest) { unsigned hash; @@ -562,19 +516,19 @@ static int ip_vs_rs_hash(struct ip_vs_dest *dest) */ hash = ip_vs_rs_hashkey(dest->af, &dest->addr, dest->port); - list_add(&dest->d_list, &ip_vs_rtable[hash]); + list_add(&dest->d_list, &ipvs->rs_table[hash]); return 1; } /* - * UNhashes ip_vs_dest from ip_vs_rtable. + * UNhashes ip_vs_dest from rs_table. * should be called with locked tables. */ static int ip_vs_rs_unhash(struct ip_vs_dest *dest) { /* - * Remove it from the ip_vs_rtable table. + * Remove it from the rs_table table. */ if (!list_empty(&dest->d_list)) { list_del(&dest->d_list); @@ -588,10 +542,11 @@ static int ip_vs_rs_unhash(struct ip_vs_dest *dest) * Lookup real service by <proto,addr,port> in the real service table. */ struct ip_vs_dest * -ip_vs_lookup_real_service(int af, __u16 protocol, +ip_vs_lookup_real_service(struct net *net, int af, __u16 protocol, const union nf_inet_addr *daddr, __be16 dport) { + struct netns_ipvs *ipvs = net_ipvs(net); unsigned hash; struct ip_vs_dest *dest; @@ -601,19 +556,19 @@ ip_vs_lookup_real_service(int af, __u16 protocol, */ hash = ip_vs_rs_hashkey(af, daddr, dport); - read_lock(&__ip_vs_rs_lock); - list_for_each_entry(dest, &ip_vs_rtable[hash], d_list) { + read_lock(&ipvs->rs_lock); + list_for_each_entry(dest, &ipvs->rs_table[hash], d_list) { if ((dest->af == af) && ip_vs_addr_equal(af, &dest->addr, daddr) && (dest->port == dport) && ((dest->protocol == protocol) || dest->vfwmark)) { /* HIT */ - read_unlock(&__ip_vs_rs_lock); + read_unlock(&ipvs->rs_lock); return dest; } } - read_unlock(&__ip_vs_rs_lock); + read_unlock(&ipvs->rs_lock); return NULL; } @@ -652,15 +607,16 @@ ip_vs_lookup_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, * ip_vs_lookup_real_service() looked promissing, but * seems not working as expected. */ -struct ip_vs_dest *ip_vs_find_dest(int af, const union nf_inet_addr *daddr, +struct ip_vs_dest *ip_vs_find_dest(struct net *net, int af, + const union nf_inet_addr *daddr, __be16 dport, const union nf_inet_addr *vaddr, - __be16 vport, __u16 protocol) + __be16 vport, __u16 protocol, __u32 fwmark) { struct ip_vs_dest *dest; struct ip_vs_service *svc; - svc = ip_vs_service_get(af, 0, protocol, vaddr, vport); + svc = ip_vs_service_get(net, af, fwmark, protocol, vaddr, vport); if (!svc) return NULL; dest = ip_vs_lookup_dest(svc, daddr, dport); @@ -685,11 +641,12 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, __be16 dport) { struct ip_vs_dest *dest, *nxt; + struct netns_ipvs *ipvs = net_ipvs(svc->net); /* * Find the destination in trash */ - list_for_each_entry_safe(dest, nxt, &ip_vs_dest_trash, n_list) { + list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) { IP_VS_DBG_BUF(3, "Destination %u/%s:%u still in trash, " "dest->refcnt=%d\n", dest->vfwmark, @@ -720,6 +677,7 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, list_del(&dest->n_list); ip_vs_dst_reset(dest); __ip_vs_unbind_svc(dest); + free_percpu(dest->stats.cpustats); kfree(dest); } } @@ -737,14 +695,16 @@ ip_vs_trash_get_dest(struct ip_vs_service *svc, const union nf_inet_addr *daddr, * are expired, and the refcnt of each destination in the trash must * be 1, so we simply release them here. */ -static void ip_vs_trash_cleanup(void) +static void ip_vs_trash_cleanup(struct net *net) { struct ip_vs_dest *dest, *nxt; + struct netns_ipvs *ipvs = net_ipvs(net); - list_for_each_entry_safe(dest, nxt, &ip_vs_dest_trash, n_list) { + list_for_each_entry_safe(dest, nxt, &ipvs->dest_trash, n_list) { list_del(&dest->n_list); ip_vs_dst_reset(dest); __ip_vs_unbind_svc(dest); + free_percpu(dest->stats.cpustats); kfree(dest); } } @@ -768,6 +728,7 @@ static void __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, struct ip_vs_dest_user_kern *udest, int add) { + struct netns_ipvs *ipvs = net_ipvs(svc->net); int conn_flags; /* set the weight and the flags */ @@ -780,12 +741,12 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, conn_flags |= IP_VS_CONN_F_NOOUTPUT; } else { /* - * Put the real service in ip_vs_rtable if not present. + * Put the real service in rs_table if not present. * For now only for NAT! */ - write_lock_bh(&__ip_vs_rs_lock); - ip_vs_rs_hash(dest); - write_unlock_bh(&__ip_vs_rs_lock); + write_lock_bh(&ipvs->rs_lock); + ip_vs_rs_hash(ipvs, dest); + write_unlock_bh(&ipvs->rs_lock); } atomic_set(&dest->conn_flags, conn_flags); @@ -813,7 +774,7 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, spin_unlock(&dest->dst_lock); if (add) - ip_vs_new_estimator(&dest->stats); + ip_vs_new_estimator(svc->net, &dest->stats); write_lock_bh(&__ip_vs_svc_lock); @@ -850,12 +811,12 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, atype = ipv6_addr_type(&udest->addr.in6); if ((!(atype & IPV6_ADDR_UNICAST) || atype & IPV6_ADDR_LINKLOCAL) && - !__ip_vs_addr_is_local_v6(&udest->addr.in6)) + !__ip_vs_addr_is_local_v6(svc->net, &udest->addr.in6)) return -EINVAL; } else #endif { - atype = inet_addr_type(&init_net, udest->addr.ip); + atype = inet_addr_type(svc->net, udest->addr.ip); if (atype != RTN_LOCAL && atype != RTN_UNICAST) return -EINVAL; } @@ -865,6 +826,11 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, pr_err("%s(): no memory.\n", __func__); return -ENOMEM; } + dest->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); + if (!dest->stats.cpustats) { + pr_err("%s() alloc_percpu failed\n", __func__); + goto err_alloc; + } dest->af = svc->af; dest->protocol = svc->protocol; @@ -888,6 +854,10 @@ ip_vs_new_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest, LeaveFunction(2); return 0; + +err_alloc: + kfree(dest); + return -ENOMEM; } @@ -1006,16 +976,18 @@ ip_vs_edit_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) /* * Delete a destination (must be already unlinked from the service) */ -static void __ip_vs_del_dest(struct ip_vs_dest *dest) +static void __ip_vs_del_dest(struct net *net, struct ip_vs_dest *dest) { - ip_vs_kill_estimator(&dest->stats); + struct netns_ipvs *ipvs = net_ipvs(net); + + ip_vs_kill_estimator(net, &dest->stats); /* * Remove it from the d-linked list with the real services. */ - write_lock_bh(&__ip_vs_rs_lock); + write_lock_bh(&ipvs->rs_lock); ip_vs_rs_unhash(dest); - write_unlock_bh(&__ip_vs_rs_lock); + write_unlock_bh(&ipvs->rs_lock); /* * Decrease the refcnt of the dest, and free the dest @@ -1034,6 +1006,7 @@ static void __ip_vs_del_dest(struct ip_vs_dest *dest) and only one user context can update virtual service at a time, so the operation here is OK */ atomic_dec(&dest->svc->refcnt); + free_percpu(dest->stats.cpustats); kfree(dest); } else { IP_VS_DBG_BUF(3, "Moving dest %s:%u into trash, " @@ -1041,7 +1014,7 @@ static void __ip_vs_del_dest(struct ip_vs_dest *dest) IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port), atomic_read(&dest->refcnt)); - list_add(&dest->n_list, &ip_vs_dest_trash); + list_add(&dest->n_list, &ipvs->dest_trash); atomic_inc(&dest->refcnt); } } @@ -1105,7 +1078,7 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) /* * Delete the destination */ - __ip_vs_del_dest(dest); + __ip_vs_del_dest(svc->net, dest); LeaveFunction(2); @@ -1117,13 +1090,14 @@ ip_vs_del_dest(struct ip_vs_service *svc, struct ip_vs_dest_user_kern *udest) * Add a service into the service hash table */ static int -ip_vs_add_service(struct ip_vs_service_user_kern *u, +ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, struct ip_vs_service **svc_p) { int ret = 0; struct ip_vs_scheduler *sched = NULL; struct ip_vs_pe *pe = NULL; struct ip_vs_service *svc = NULL; + struct netns_ipvs *ipvs = net_ipvs(net); /* increase the module use count */ ip_vs_use_count_inc(); @@ -1137,7 +1111,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, } if (u->pe_name && *u->pe_name) { - pe = ip_vs_pe_get(u->pe_name); + pe = ip_vs_pe_getbyname(u->pe_name); if (pe == NULL) { pr_info("persistence engine module ip_vs_pe_%s " "not found\n", u->pe_name); @@ -1159,6 +1133,11 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, ret = -ENOMEM; goto out_err; } + svc->stats.cpustats = alloc_percpu(struct ip_vs_cpu_stats); + if (!svc->stats.cpustats) { + pr_err("%s() alloc_percpu failed\n", __func__); + goto out_err; + } /* I'm the first user of the service */ atomic_set(&svc->usecnt, 0); @@ -1172,6 +1151,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, svc->flags = u->flags; svc->timeout = u->timeout * HZ; svc->netmask = u->netmask; + svc->net = net; INIT_LIST_HEAD(&svc->destinations); rwlock_init(&svc->sched_lock); @@ -1189,15 +1169,15 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, /* Update the virtual service counters */ if (svc->port == FTPPORT) - atomic_inc(&ip_vs_ftpsvc_counter); + atomic_inc(&ipvs->ftpsvc_counter); else if (svc->port == 0) - atomic_inc(&ip_vs_nullsvc_counter); + atomic_inc(&ipvs->nullsvc_counter); - ip_vs_new_estimator(&svc->stats); + ip_vs_new_estimator(net, &svc->stats); /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) - ip_vs_num_services++; + ipvs->num_services++; /* Hash the service into the service table */ write_lock_bh(&__ip_vs_svc_lock); @@ -1207,6 +1187,7 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, *svc_p = svc; return 0; + out_err: if (svc != NULL) { ip_vs_unbind_scheduler(svc); @@ -1215,6 +1196,8 @@ ip_vs_add_service(struct ip_vs_service_user_kern *u, ip_vs_app_inc_put(svc->inc); local_bh_enable(); } + if (svc->stats.cpustats) + free_percpu(svc->stats.cpustats); kfree(svc); } ip_vs_scheduler_put(sched); @@ -1248,7 +1231,7 @@ ip_vs_edit_service(struct ip_vs_service *svc, struct ip_vs_service_user_kern *u) old_sched = sched; if (u->pe_name && *u->pe_name) { - pe = ip_vs_pe_get(u->pe_name); + pe = ip_vs_pe_getbyname(u->pe_name); if (pe == NULL) { pr_info("persistence engine module ip_vs_pe_%s " "not found\n", u->pe_name); @@ -1334,14 +1317,15 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) struct ip_vs_dest *dest, *nxt; struct ip_vs_scheduler *old_sched; struct ip_vs_pe *old_pe; + struct netns_ipvs *ipvs = net_ipvs(svc->net); pr_info("%s: enter\n", __func__); /* Count only IPv4 services for old get/setsockopt interface */ if (svc->af == AF_INET) - ip_vs_num_services--; + ipvs->num_services--; - ip_vs_kill_estimator(&svc->stats); + ip_vs_kill_estimator(svc->net, &svc->stats); /* Unbind scheduler */ old_sched = svc->scheduler; @@ -1364,16 +1348,16 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) */ list_for_each_entry_safe(dest, nxt, &svc->destinations, n_list) { __ip_vs_unlink_dest(svc, dest, 0); - __ip_vs_del_dest(dest); + __ip_vs_del_dest(svc->net, dest); } /* * Update the virtual service counters */ if (svc->port == FTPPORT) - atomic_dec(&ip_vs_ftpsvc_counter); + atomic_dec(&ipvs->ftpsvc_counter); else if (svc->port == 0) - atomic_dec(&ip_vs_nullsvc_counter); + atomic_dec(&ipvs->nullsvc_counter); /* * Free the service if nobody refers to it @@ -1383,6 +1367,7 @@ static void __ip_vs_del_service(struct ip_vs_service *svc) svc->fwmark, IP_VS_DBG_ADDR(svc->af, &svc->addr), ntohs(svc->port), atomic_read(&svc->usecnt)); + free_percpu(svc->stats.cpustats); kfree(svc); } @@ -1428,17 +1413,19 @@ static int ip_vs_del_service(struct ip_vs_service *svc) /* * Flush all the virtual services */ -static int ip_vs_flush(void) +static int ip_vs_flush(struct net *net) { int idx; struct ip_vs_service *svc, *nxt; /* - * Flush the service table hashed by <protocol,addr,port> + * Flush the service table hashed by <netns,protocol,addr,port> */ for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { - list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx], s_list) { - ip_vs_unlink_service(svc); + list_for_each_entry_safe(svc, nxt, &ip_vs_svc_table[idx], + s_list) { + if (net_eq(svc->net, net)) + ip_vs_unlink_service(svc); } } @@ -1448,7 +1435,8 @@ static int ip_vs_flush(void) for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry_safe(svc, nxt, &ip_vs_svc_fwm_table[idx], f_list) { - ip_vs_unlink_service(svc); + if (net_eq(svc->net, net)) + ip_vs_unlink_service(svc); } } @@ -1472,24 +1460,26 @@ static int ip_vs_zero_service(struct ip_vs_service *svc) return 0; } -static int ip_vs_zero_all(void) +static int ip_vs_zero_all(struct net *net) { int idx; struct ip_vs_service *svc; for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { - ip_vs_zero_service(svc); + if (net_eq(svc->net, net)) + ip_vs_zero_service(svc); } } for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { - ip_vs_zero_service(svc); + if (net_eq(svc->net, net)) + ip_vs_zero_service(svc); } } - ip_vs_zero_stats(&ip_vs_stats); + ip_vs_zero_stats(net_ipvs(net)->tot_stats); return 0; } @@ -1498,6 +1488,7 @@ static int proc_do_defense_mode(ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + struct net *net = current->nsproxy->net_ns; int *valp = table->data; int val = *valp; int rc; @@ -1508,7 +1499,7 @@ proc_do_defense_mode(ctl_table *table, int write, /* Restore the correct value */ *valp = val; } else { - update_defense_level(); + update_defense_level(net_ipvs(net)); } } return rc; @@ -1534,45 +1525,54 @@ proc_do_sync_threshold(ctl_table *table, int write, return rc; } +static int +proc_do_sync_mode(ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int *valp = table->data; + int val = *valp; + int rc; + + rc = proc_dointvec(table, write, buffer, lenp, ppos); + if (write && (*valp != val)) { + if ((*valp < 0) || (*valp > 1)) { + /* Restore the correct value */ + *valp = val; + } else { + struct net *net = current->nsproxy->net_ns; + ip_vs_sync_switch_mode(net, val); + } + } + return rc; +} /* * IPVS sysctl table (under the /proc/sys/net/ipv4/vs/) + * Do not change order or insert new entries without + * align with netns init in __ip_vs_control_init() */ static struct ctl_table vs_vars[] = { { .procname = "amemthresh", - .data = &sysctl_ip_vs_amemthresh, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, -#ifdef CONFIG_IP_VS_DEBUG - { - .procname = "debug_level", - .data = &sysctl_ip_vs_debug_level, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, -#endif { .procname = "am_droprate", - .data = &sysctl_ip_vs_am_droprate, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "drop_entry", - .data = &sysctl_ip_vs_drop_entry, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_defense_mode, }, { .procname = "drop_packet", - .data = &sysctl_ip_vs_drop_packet, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_defense_mode, @@ -1580,7 +1580,6 @@ static struct ctl_table vs_vars[] = { #ifdef CONFIG_IP_VS_NFCT { .procname = "conntrack", - .data = &sysctl_ip_vs_conntrack, .maxlen = sizeof(int), .mode = 0644, .proc_handler = &proc_dointvec, @@ -1588,18 +1587,62 @@ static struct ctl_table vs_vars[] = { #endif { .procname = "secure_tcp", - .data = &sysctl_ip_vs_secure_tcp, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_do_defense_mode, }, { .procname = "snat_reroute", - .data = &sysctl_ip_vs_snat_reroute, .maxlen = sizeof(int), .mode = 0644, .proc_handler = &proc_dointvec, }, + { + .procname = "sync_version", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = &proc_do_sync_mode, + }, + { + .procname = "cache_bypass", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "expire_nodest_conn", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "expire_quiescent_template", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + { + .procname = "sync_threshold", + .maxlen = + sizeof(((struct netns_ipvs *)0)->sysctl_sync_threshold), + .mode = 0644, + .proc_handler = proc_do_sync_threshold, + }, + { + .procname = "nat_icmp_send", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_IP_VS_DEBUG + { + .procname = "debug_level", + .data = &sysctl_ip_vs_debug_level, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif #if 0 { .procname = "timeout_established", @@ -1686,41 +1729,6 @@ static struct ctl_table vs_vars[] = { .proc_handler = proc_dointvec_jiffies, }, #endif - { - .procname = "cache_bypass", - .data = &sysctl_ip_vs_cache_bypass, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "expire_nodest_conn", - .data = &sysctl_ip_vs_expire_nodest_conn, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "expire_quiescent_template", - .data = &sysctl_ip_vs_expire_quiescent_template, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "sync_threshold", - .data = &sysctl_ip_vs_sync_threshold, - .maxlen = sizeof(sysctl_ip_vs_sync_threshold), - .mode = 0644, - .proc_handler = proc_do_sync_threshold, - }, - { - .procname = "nat_icmp_send", - .data = &sysctl_ip_vs_nat_icmp_send, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, { } }; @@ -1732,11 +1740,10 @@ const struct ctl_path net_vs_ctl_path[] = { }; EXPORT_SYMBOL_GPL(net_vs_ctl_path); -static struct ctl_table_header * sysctl_header; - #ifdef CONFIG_PROC_FS struct ip_vs_iter { + struct seq_net_private p; /* Do not move this, netns depends upon it*/ struct list_head *table; int bucket; }; @@ -1763,6 +1770,7 @@ static inline const char *ip_vs_fwd_name(unsigned flags) /* Get the Nth entry in the two lists */ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) { + struct net *net = seq_file_net(seq); struct ip_vs_iter *iter = seq->private; int idx; struct ip_vs_service *svc; @@ -1770,7 +1778,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) /* look in hash by protocol */ for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { - if (pos-- == 0){ + if (net_eq(svc->net, net) && pos-- == 0) { iter->table = ip_vs_svc_table; iter->bucket = idx; return svc; @@ -1781,7 +1789,7 @@ static struct ip_vs_service *ip_vs_info_array(struct seq_file *seq, loff_t pos) /* keep looking in fwmark */ for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { - if (pos-- == 0) { + if (net_eq(svc->net, net) && pos-- == 0) { iter->table = ip_vs_svc_fwm_table; iter->bucket = idx; return svc; @@ -1935,7 +1943,7 @@ static const struct seq_operations ip_vs_info_seq_ops = { static int ip_vs_info_open(struct inode *inode, struct file *file) { - return seq_open_private(file, &ip_vs_info_seq_ops, + return seq_open_net(inode, file, &ip_vs_info_seq_ops, sizeof(struct ip_vs_iter)); } @@ -1949,13 +1957,11 @@ static const struct file_operations ip_vs_info_fops = { #endif -struct ip_vs_stats ip_vs_stats = { - .lock = __SPIN_LOCK_UNLOCKED(ip_vs_stats.lock), -}; - #ifdef CONFIG_PROC_FS static int ip_vs_stats_show(struct seq_file *seq, void *v) { + struct net *net = seq_file_single_net(seq); + struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats; /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, @@ -1963,29 +1969,29 @@ static int ip_vs_stats_show(struct seq_file *seq, void *v) seq_printf(seq, " Conns Packets Packets Bytes Bytes\n"); - spin_lock_bh(&ip_vs_stats.lock); - seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", ip_vs_stats.ustats.conns, - ip_vs_stats.ustats.inpkts, ip_vs_stats.ustats.outpkts, - (unsigned long long) ip_vs_stats.ustats.inbytes, - (unsigned long long) ip_vs_stats.ustats.outbytes); + spin_lock_bh(&tot_stats->lock); + seq_printf(seq, "%8X %8X %8X %16LX %16LX\n\n", tot_stats->ustats.conns, + tot_stats->ustats.inpkts, tot_stats->ustats.outpkts, + (unsigned long long) tot_stats->ustats.inbytes, + (unsigned long long) tot_stats->ustats.outbytes); /* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ seq_puts(seq, " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); seq_printf(seq,"%8X %8X %8X %16X %16X\n", - ip_vs_stats.ustats.cps, - ip_vs_stats.ustats.inpps, - ip_vs_stats.ustats.outpps, - ip_vs_stats.ustats.inbps, - ip_vs_stats.ustats.outbps); - spin_unlock_bh(&ip_vs_stats.lock); + tot_stats->ustats.cps, + tot_stats->ustats.inpps, + tot_stats->ustats.outpps, + tot_stats->ustats.inbps, + tot_stats->ustats.outbps); + spin_unlock_bh(&tot_stats->lock); return 0; } static int ip_vs_stats_seq_open(struct inode *inode, struct file *file) { - return single_open(file, ip_vs_stats_show, NULL); + return single_open_net(inode, file, ip_vs_stats_show); } static const struct file_operations ip_vs_stats_fops = { @@ -1996,13 +2002,70 @@ static const struct file_operations ip_vs_stats_fops = { .release = single_release, }; +static int ip_vs_stats_percpu_show(struct seq_file *seq, void *v) +{ + struct net *net = seq_file_single_net(seq); + struct ip_vs_stats *tot_stats = net_ipvs(net)->tot_stats; + int i; + +/* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ + seq_puts(seq, + " Total Incoming Outgoing Incoming Outgoing\n"); + seq_printf(seq, + "CPU Conns Packets Packets Bytes Bytes\n"); + + for_each_possible_cpu(i) { + struct ip_vs_cpu_stats *u = per_cpu_ptr(net->ipvs->cpustats, i); + seq_printf(seq, "%3X %8X %8X %8X %16LX %16LX\n", + i, u->ustats.conns, u->ustats.inpkts, + u->ustats.outpkts, (__u64)u->ustats.inbytes, + (__u64)u->ustats.outbytes); + } + + spin_lock_bh(&tot_stats->lock); + seq_printf(seq, " ~ %8X %8X %8X %16LX %16LX\n\n", + tot_stats->ustats.conns, tot_stats->ustats.inpkts, + tot_stats->ustats.outpkts, + (unsigned long long) tot_stats->ustats.inbytes, + (unsigned long long) tot_stats->ustats.outbytes); + +/* 01234567 01234567 01234567 0123456701234567 0123456701234567 */ + seq_puts(seq, + " Conns/s Pkts/s Pkts/s Bytes/s Bytes/s\n"); + seq_printf(seq, " %8X %8X %8X %16X %16X\n", + tot_stats->ustats.cps, + tot_stats->ustats.inpps, + tot_stats->ustats.outpps, + tot_stats->ustats.inbps, + tot_stats->ustats.outbps); + spin_unlock_bh(&tot_stats->lock); + + return 0; +} + +static int ip_vs_stats_percpu_seq_open(struct inode *inode, struct file *file) +{ + return single_open_net(inode, file, ip_vs_stats_percpu_show); +} + +static const struct file_operations ip_vs_stats_percpu_fops = { + .owner = THIS_MODULE, + .open = ip_vs_stats_percpu_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif /* * Set timeout values for tcp tcpfin udp in the timeout_table. */ -static int ip_vs_set_timeout(struct ip_vs_timeout_user *u) +static int ip_vs_set_timeout(struct net *net, struct ip_vs_timeout_user *u) { +#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) + struct ip_vs_proto_data *pd; +#endif + IP_VS_DBG(2, "Setting timeout tcp:%d tcpfin:%d udp:%d\n", u->tcp_timeout, u->tcp_fin_timeout, @@ -2010,19 +2073,22 @@ static int ip_vs_set_timeout(struct ip_vs_timeout_user *u) #ifdef CONFIG_IP_VS_PROTO_TCP if (u->tcp_timeout) { - ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_ESTABLISHED] + pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] = u->tcp_timeout * HZ; } if (u->tcp_fin_timeout) { - ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_FIN_WAIT] + pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] = u->tcp_fin_timeout * HZ; } #endif #ifdef CONFIG_IP_VS_PROTO_UDP if (u->udp_timeout) { - ip_vs_protocol_udp.timeout_table[IP_VS_UDP_S_NORMAL] + pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + pd->timeout_table[IP_VS_UDP_S_NORMAL] = u->udp_timeout * HZ; } #endif @@ -2087,6 +2153,7 @@ static void ip_vs_copy_udest_compat(struct ip_vs_dest_user_kern *udest, static int do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) { + struct net *net = sock_net(sk); int ret; unsigned char arg[MAX_ARG_LEN]; struct ip_vs_service_user *usvc_compat; @@ -2121,19 +2188,20 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (cmd == IP_VS_SO_SET_FLUSH) { /* Flush the virtual service */ - ret = ip_vs_flush(); + ret = ip_vs_flush(net); goto out_unlock; } else if (cmd == IP_VS_SO_SET_TIMEOUT) { /* Set timeout values for (tcp tcpfin udp) */ - ret = ip_vs_set_timeout((struct ip_vs_timeout_user *)arg); + ret = ip_vs_set_timeout(net, (struct ip_vs_timeout_user *)arg); goto out_unlock; } else if (cmd == IP_VS_SO_SET_STARTDAEMON) { struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; - ret = start_sync_thread(dm->state, dm->mcast_ifn, dm->syncid); + ret = start_sync_thread(net, dm->state, dm->mcast_ifn, + dm->syncid); goto out_unlock; } else if (cmd == IP_VS_SO_SET_STOPDAEMON) { struct ip_vs_daemon_user *dm = (struct ip_vs_daemon_user *)arg; - ret = stop_sync_thread(dm->state); + ret = stop_sync_thread(net, dm->state); goto out_unlock; } @@ -2148,7 +2216,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (cmd == IP_VS_SO_SET_ZERO) { /* if no service address is set, zero counters in all */ if (!usvc.fwmark && !usvc.addr.ip && !usvc.port) { - ret = ip_vs_zero_all(); + ret = ip_vs_zero_all(net); goto out_unlock; } } @@ -2165,10 +2233,10 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) /* Lookup the exact service by <protocol, addr, port> or fwmark */ if (usvc.fwmark == 0) - svc = __ip_vs_service_find(usvc.af, usvc.protocol, + svc = __ip_vs_service_find(net, usvc.af, usvc.protocol, &usvc.addr, usvc.port); else - svc = __ip_vs_svc_fwm_find(usvc.af, usvc.fwmark); + svc = __ip_vs_svc_fwm_find(net, usvc.af, usvc.fwmark); if (cmd != IP_VS_SO_SET_ADD && (svc == NULL || svc->protocol != usvc.protocol)) { @@ -2181,7 +2249,7 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (svc != NULL) ret = -EEXIST; else - ret = ip_vs_add_service(&usvc, &svc); + ret = ip_vs_add_service(net, &usvc, &svc); break; case IP_VS_SO_SET_EDIT: ret = ip_vs_edit_service(svc, &usvc); @@ -2241,7 +2309,8 @@ ip_vs_copy_service(struct ip_vs_service_entry *dst, struct ip_vs_service *src) } static inline int -__ip_vs_get_service_entries(const struct ip_vs_get_services *get, +__ip_vs_get_service_entries(struct net *net, + const struct ip_vs_get_services *get, struct ip_vs_get_services __user *uptr) { int idx, count=0; @@ -2252,7 +2321,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get, for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { /* Only expose IPv4 entries to old interface */ - if (svc->af != AF_INET) + if (svc->af != AF_INET || !net_eq(svc->net, net)) continue; if (count >= get->num_services) @@ -2271,7 +2340,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get, for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { /* Only expose IPv4 entries to old interface */ - if (svc->af != AF_INET) + if (svc->af != AF_INET || !net_eq(svc->net, net)) continue; if (count >= get->num_services) @@ -2291,7 +2360,7 @@ __ip_vs_get_service_entries(const struct ip_vs_get_services *get, } static inline int -__ip_vs_get_dest_entries(const struct ip_vs_get_dests *get, +__ip_vs_get_dest_entries(struct net *net, const struct ip_vs_get_dests *get, struct ip_vs_get_dests __user *uptr) { struct ip_vs_service *svc; @@ -2299,9 +2368,9 @@ __ip_vs_get_dest_entries(const struct ip_vs_get_dests *get, int ret = 0; if (get->fwmark) - svc = __ip_vs_svc_fwm_find(AF_INET, get->fwmark); + svc = __ip_vs_svc_fwm_find(net, AF_INET, get->fwmark); else - svc = __ip_vs_service_find(AF_INET, get->protocol, &addr, + svc = __ip_vs_service_find(net, AF_INET, get->protocol, &addr, get->port); if (svc) { @@ -2336,17 +2405,21 @@ __ip_vs_get_dest_entries(const struct ip_vs_get_dests *get, } static inline void -__ip_vs_get_timeouts(struct ip_vs_timeout_user *u) +__ip_vs_get_timeouts(struct net *net, struct ip_vs_timeout_user *u) { +#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) + struct ip_vs_proto_data *pd; +#endif + #ifdef CONFIG_IP_VS_PROTO_TCP - u->tcp_timeout = - ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ; - u->tcp_fin_timeout = - ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ; + pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + u->tcp_timeout = pd->timeout_table[IP_VS_TCP_S_ESTABLISHED] / HZ; + u->tcp_fin_timeout = pd->timeout_table[IP_VS_TCP_S_FIN_WAIT] / HZ; #endif #ifdef CONFIG_IP_VS_PROTO_UDP + pd = ip_vs_proto_data_get(net, IPPROTO_UDP); u->udp_timeout = - ip_vs_protocol_udp.timeout_table[IP_VS_UDP_S_NORMAL] / HZ; + pd->timeout_table[IP_VS_UDP_S_NORMAL] / HZ; #endif } @@ -2375,7 +2448,10 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) unsigned char arg[128]; int ret = 0; unsigned int copylen; + struct net *net = sock_net(sk); + struct netns_ipvs *ipvs = net_ipvs(net); + BUG_ON(!net); if (!capable(CAP_NET_ADMIN)) return -EPERM; @@ -2418,7 +2494,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) struct ip_vs_getinfo info; info.version = IP_VS_VERSION_CODE; info.size = ip_vs_conn_tab_size; - info.num_services = ip_vs_num_services; + info.num_services = ipvs->num_services; if (copy_to_user(user, &info, sizeof(info)) != 0) ret = -EFAULT; } @@ -2437,7 +2513,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) ret = -EINVAL; goto out; } - ret = __ip_vs_get_service_entries(get, user); + ret = __ip_vs_get_service_entries(net, get, user); } break; @@ -2450,10 +2526,11 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) entry = (struct ip_vs_service_entry *)arg; addr.ip = entry->addr; if (entry->fwmark) - svc = __ip_vs_svc_fwm_find(AF_INET, entry->fwmark); + svc = __ip_vs_svc_fwm_find(net, AF_INET, entry->fwmark); else - svc = __ip_vs_service_find(AF_INET, entry->protocol, - &addr, entry->port); + svc = __ip_vs_service_find(net, AF_INET, + entry->protocol, &addr, + entry->port); if (svc) { ip_vs_copy_service(entry, svc); if (copy_to_user(user, entry, sizeof(*entry)) != 0) @@ -2476,7 +2553,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) ret = -EINVAL; goto out; } - ret = __ip_vs_get_dest_entries(get, user); + ret = __ip_vs_get_dest_entries(net, get, user); } break; @@ -2484,7 +2561,7 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) { struct ip_vs_timeout_user t; - __ip_vs_get_timeouts(&t); + __ip_vs_get_timeouts(net, &t); if (copy_to_user(user, &t, sizeof(t)) != 0) ret = -EFAULT; } @@ -2495,15 +2572,17 @@ do_ip_vs_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) struct ip_vs_daemon_user d[2]; memset(&d, 0, sizeof(d)); - if (ip_vs_sync_state & IP_VS_STATE_MASTER) { + if (ipvs->sync_state & IP_VS_STATE_MASTER) { d[0].state = IP_VS_STATE_MASTER; - strlcpy(d[0].mcast_ifn, ip_vs_master_mcast_ifn, sizeof(d[0].mcast_ifn)); - d[0].syncid = ip_vs_master_syncid; + strlcpy(d[0].mcast_ifn, ipvs->master_mcast_ifn, + sizeof(d[0].mcast_ifn)); + d[0].syncid = ipvs->master_syncid; } - if (ip_vs_sync_state & IP_VS_STATE_BACKUP) { + if (ipvs->sync_state & IP_VS_STATE_BACKUP) { d[1].state = IP_VS_STATE_BACKUP; - strlcpy(d[1].mcast_ifn, ip_vs_backup_mcast_ifn, sizeof(d[1].mcast_ifn)); - d[1].syncid = ip_vs_backup_syncid; + strlcpy(d[1].mcast_ifn, ipvs->backup_mcast_ifn, + sizeof(d[1].mcast_ifn)); + d[1].syncid = ipvs->backup_syncid; } if (copy_to_user(user, &d, sizeof(d)) != 0) ret = -EFAULT; @@ -2542,6 +2621,7 @@ static struct genl_family ip_vs_genl_family = { .name = IPVS_GENL_NAME, .version = IPVS_GENL_VERSION, .maxattr = IPVS_CMD_MAX, + .netnsok = true, /* Make ipvsadm to work on netns */ }; /* Policy used for first-level command attributes */ @@ -2696,11 +2776,12 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb, int idx = 0, i; int start = cb->args[0]; struct ip_vs_service *svc; + struct net *net = skb_sknet(skb); mutex_lock(&__ip_vs_mutex); for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { list_for_each_entry(svc, &ip_vs_svc_table[i], s_list) { - if (++idx <= start) + if (++idx <= start || !net_eq(svc->net, net)) continue; if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { idx--; @@ -2711,7 +2792,7 @@ static int ip_vs_genl_dump_services(struct sk_buff *skb, for (i = 0; i < IP_VS_SVC_TAB_SIZE; i++) { list_for_each_entry(svc, &ip_vs_svc_fwm_table[i], f_list) { - if (++idx <= start) + if (++idx <= start || !net_eq(svc->net, net)) continue; if (ip_vs_genl_dump_service(skb, svc, cb) < 0) { idx--; @@ -2727,7 +2808,8 @@ nla_put_failure: return skb->len; } -static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, +static int ip_vs_genl_parse_service(struct net *net, + struct ip_vs_service_user_kern *usvc, struct nlattr *nla, int full_entry, struct ip_vs_service **ret_svc) { @@ -2770,9 +2852,9 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, } if (usvc->fwmark) - svc = __ip_vs_svc_fwm_find(usvc->af, usvc->fwmark); + svc = __ip_vs_svc_fwm_find(net, usvc->af, usvc->fwmark); else - svc = __ip_vs_service_find(usvc->af, usvc->protocol, + svc = __ip_vs_service_find(net, usvc->af, usvc->protocol, &usvc->addr, usvc->port); *ret_svc = svc; @@ -2809,13 +2891,14 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc, return 0; } -static struct ip_vs_service *ip_vs_genl_find_service(struct nlattr *nla) +static struct ip_vs_service *ip_vs_genl_find_service(struct net *net, + struct nlattr *nla) { struct ip_vs_service_user_kern usvc; struct ip_vs_service *svc; int ret; - ret = ip_vs_genl_parse_service(&usvc, nla, 0, &svc); + ret = ip_vs_genl_parse_service(net, &usvc, nla, 0, &svc); return ret ? ERR_PTR(ret) : svc; } @@ -2883,6 +2966,7 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb, struct ip_vs_service *svc; struct ip_vs_dest *dest; struct nlattr *attrs[IPVS_CMD_ATTR_MAX + 1]; + struct net *net = skb_sknet(skb); mutex_lock(&__ip_vs_mutex); @@ -2891,7 +2975,8 @@ static int ip_vs_genl_dump_dests(struct sk_buff *skb, IPVS_CMD_ATTR_MAX, ip_vs_cmd_policy)) goto out_err; - svc = ip_vs_genl_find_service(attrs[IPVS_CMD_ATTR_SERVICE]); + + svc = ip_vs_genl_find_service(net, attrs[IPVS_CMD_ATTR_SERVICE]); if (IS_ERR(svc) || svc == NULL) goto out_err; @@ -3005,20 +3090,23 @@ nla_put_failure: static int ip_vs_genl_dump_daemons(struct sk_buff *skb, struct netlink_callback *cb) { + struct net *net = skb_net(skb); + struct netns_ipvs *ipvs = net_ipvs(net); + mutex_lock(&__ip_vs_mutex); - if ((ip_vs_sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) { + if ((ipvs->sync_state & IP_VS_STATE_MASTER) && !cb->args[0]) { if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_MASTER, - ip_vs_master_mcast_ifn, - ip_vs_master_syncid, cb) < 0) + ipvs->master_mcast_ifn, + ipvs->master_syncid, cb) < 0) goto nla_put_failure; cb->args[0] = 1; } - if ((ip_vs_sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) { + if ((ipvs->sync_state & IP_VS_STATE_BACKUP) && !cb->args[1]) { if (ip_vs_genl_dump_daemon(skb, IP_VS_STATE_BACKUP, - ip_vs_backup_mcast_ifn, - ip_vs_backup_syncid, cb) < 0) + ipvs->backup_mcast_ifn, + ipvs->backup_syncid, cb) < 0) goto nla_put_failure; cb->args[1] = 1; @@ -3030,31 +3118,33 @@ nla_put_failure: return skb->len; } -static int ip_vs_genl_new_daemon(struct nlattr **attrs) +static int ip_vs_genl_new_daemon(struct net *net, struct nlattr **attrs) { if (!(attrs[IPVS_DAEMON_ATTR_STATE] && attrs[IPVS_DAEMON_ATTR_MCAST_IFN] && attrs[IPVS_DAEMON_ATTR_SYNC_ID])) return -EINVAL; - return start_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]), + return start_sync_thread(net, + nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE]), nla_data(attrs[IPVS_DAEMON_ATTR_MCAST_IFN]), nla_get_u32(attrs[IPVS_DAEMON_ATTR_SYNC_ID])); } -static int ip_vs_genl_del_daemon(struct nlattr **attrs) +static int ip_vs_genl_del_daemon(struct net *net, struct nlattr **attrs) { if (!attrs[IPVS_DAEMON_ATTR_STATE]) return -EINVAL; - return stop_sync_thread(nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); + return stop_sync_thread(net, + nla_get_u32(attrs[IPVS_DAEMON_ATTR_STATE])); } -static int ip_vs_genl_set_config(struct nlattr **attrs) +static int ip_vs_genl_set_config(struct net *net, struct nlattr **attrs) { struct ip_vs_timeout_user t; - __ip_vs_get_timeouts(&t); + __ip_vs_get_timeouts(net, &t); if (attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]) t.tcp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_TCP]); @@ -3066,7 +3156,7 @@ static int ip_vs_genl_set_config(struct nlattr **attrs) if (attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]) t.udp_timeout = nla_get_u32(attrs[IPVS_CMD_ATTR_TIMEOUT_UDP]); - return ip_vs_set_timeout(&t); + return ip_vs_set_timeout(net, &t); } static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) @@ -3076,16 +3166,20 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) struct ip_vs_dest_user_kern udest; int ret = 0, cmd; int need_full_svc = 0, need_full_dest = 0; + struct net *net; + struct netns_ipvs *ipvs; + net = skb_sknet(skb); + ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; mutex_lock(&__ip_vs_mutex); if (cmd == IPVS_CMD_FLUSH) { - ret = ip_vs_flush(); + ret = ip_vs_flush(net); goto out; } else if (cmd == IPVS_CMD_SET_CONFIG) { - ret = ip_vs_genl_set_config(info->attrs); + ret = ip_vs_genl_set_config(net, info->attrs); goto out; } else if (cmd == IPVS_CMD_NEW_DAEMON || cmd == IPVS_CMD_DEL_DAEMON) { @@ -3101,13 +3195,13 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) } if (cmd == IPVS_CMD_NEW_DAEMON) - ret = ip_vs_genl_new_daemon(daemon_attrs); + ret = ip_vs_genl_new_daemon(net, daemon_attrs); else - ret = ip_vs_genl_del_daemon(daemon_attrs); + ret = ip_vs_genl_del_daemon(net, daemon_attrs); goto out; } else if (cmd == IPVS_CMD_ZERO && !info->attrs[IPVS_CMD_ATTR_SERVICE]) { - ret = ip_vs_zero_all(); + ret = ip_vs_zero_all(net); goto out; } @@ -3117,7 +3211,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) if (cmd == IPVS_CMD_NEW_SERVICE || cmd == IPVS_CMD_SET_SERVICE) need_full_svc = 1; - ret = ip_vs_genl_parse_service(&usvc, + ret = ip_vs_genl_parse_service(net, &usvc, info->attrs[IPVS_CMD_ATTR_SERVICE], need_full_svc, &svc); if (ret) @@ -3147,7 +3241,7 @@ static int ip_vs_genl_set_cmd(struct sk_buff *skb, struct genl_info *info) switch (cmd) { case IPVS_CMD_NEW_SERVICE: if (svc == NULL) - ret = ip_vs_add_service(&usvc, &svc); + ret = ip_vs_add_service(net, &usvc, &svc); else ret = -EEXIST; break; @@ -3185,7 +3279,11 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) struct sk_buff *msg; void *reply; int ret, cmd, reply_cmd; + struct net *net; + struct netns_ipvs *ipvs; + net = skb_sknet(skb); + ipvs = net_ipvs(net); cmd = info->genlhdr->cmd; if (cmd == IPVS_CMD_GET_SERVICE) @@ -3214,7 +3312,8 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) { struct ip_vs_service *svc; - svc = ip_vs_genl_find_service(info->attrs[IPVS_CMD_ATTR_SERVICE]); + svc = ip_vs_genl_find_service(net, + info->attrs[IPVS_CMD_ATTR_SERVICE]); if (IS_ERR(svc)) { ret = PTR_ERR(svc); goto out_err; @@ -3234,7 +3333,7 @@ static int ip_vs_genl_get_cmd(struct sk_buff *skb, struct genl_info *info) { struct ip_vs_timeout_user t; - __ip_vs_get_timeouts(&t); + __ip_vs_get_timeouts(net, &t); #ifdef CONFIG_IP_VS_PROTO_TCP NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP, t.tcp_timeout); NLA_PUT_U32(msg, IPVS_CMD_ATTR_TIMEOUT_TCP_FIN, @@ -3380,62 +3479,172 @@ static void ip_vs_genl_unregister(void) /* End of Generic Netlink interface definitions */ +/* + * per netns intit/exit func. + */ +int __net_init __ip_vs_control_init(struct net *net) +{ + int idx; + struct netns_ipvs *ipvs = net_ipvs(net); + struct ctl_table *tbl; + + atomic_set(&ipvs->dropentry, 0); + spin_lock_init(&ipvs->dropentry_lock); + spin_lock_init(&ipvs->droppacket_lock); + spin_lock_init(&ipvs->securetcp_lock); + ipvs->rs_lock = __RW_LOCK_UNLOCKED(ipvs->rs_lock); + + /* Initialize rs_table */ + for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++) + INIT_LIST_HEAD(&ipvs->rs_table[idx]); + + INIT_LIST_HEAD(&ipvs->dest_trash); + atomic_set(&ipvs->ftpsvc_counter, 0); + atomic_set(&ipvs->nullsvc_counter, 0); + + /* procfs stats */ + ipvs->tot_stats = kzalloc(sizeof(struct ip_vs_stats), GFP_KERNEL); + if (ipvs->tot_stats == NULL) { + pr_err("%s(): no memory.\n", __func__); + return -ENOMEM; + } + ipvs->cpustats = alloc_percpu(struct ip_vs_cpu_stats); + if (!ipvs->cpustats) { + pr_err("%s() alloc_percpu failed\n", __func__); + goto err_alloc; + } + spin_lock_init(&ipvs->tot_stats->lock); + + for (idx = 0; idx < IP_VS_RTAB_SIZE; idx++) + INIT_LIST_HEAD(&ipvs->rs_table[idx]); + + proc_net_fops_create(net, "ip_vs", 0, &ip_vs_info_fops); + proc_net_fops_create(net, "ip_vs_stats", 0, &ip_vs_stats_fops); + proc_net_fops_create(net, "ip_vs_stats_percpu", 0, + &ip_vs_stats_percpu_fops); + + if (!net_eq(net, &init_net)) { + tbl = kmemdup(vs_vars, sizeof(vs_vars), GFP_KERNEL); + if (tbl == NULL) + goto err_dup; + } else + tbl = vs_vars; + /* Initialize sysctl defaults */ + idx = 0; + ipvs->sysctl_amemthresh = 1024; + tbl[idx++].data = &ipvs->sysctl_amemthresh; + ipvs->sysctl_am_droprate = 10; + tbl[idx++].data = &ipvs->sysctl_am_droprate; + tbl[idx++].data = &ipvs->sysctl_drop_entry; + tbl[idx++].data = &ipvs->sysctl_drop_packet; +#ifdef CONFIG_IP_VS_NFCT + tbl[idx++].data = &ipvs->sysctl_conntrack; +#endif + tbl[idx++].data = &ipvs->sysctl_secure_tcp; + ipvs->sysctl_snat_reroute = 1; + tbl[idx++].data = &ipvs->sysctl_snat_reroute; + ipvs->sysctl_sync_ver = 1; + tbl[idx++].data = &ipvs->sysctl_sync_ver; + tbl[idx++].data = &ipvs->sysctl_cache_bypass; + tbl[idx++].data = &ipvs->sysctl_expire_nodest_conn; + tbl[idx++].data = &ipvs->sysctl_expire_quiescent_template; + ipvs->sysctl_sync_threshold[0] = 3; + ipvs->sysctl_sync_threshold[1] = 50; + tbl[idx].data = &ipvs->sysctl_sync_threshold; + tbl[idx++].maxlen = sizeof(ipvs->sysctl_sync_threshold); + tbl[idx++].data = &ipvs->sysctl_nat_icmp_send; + + + ipvs->sysctl_hdr = register_net_sysctl_table(net, net_vs_ctl_path, + tbl); + if (ipvs->sysctl_hdr == NULL) + goto err_reg; + ip_vs_new_estimator(net, ipvs->tot_stats); + ipvs->sysctl_tbl = tbl; + /* Schedule defense work */ + INIT_DELAYED_WORK(&ipvs->defense_work, defense_work_handler); + schedule_delayed_work(&ipvs->defense_work, DEFENSE_TIMER_PERIOD); + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(tbl); +err_dup: + free_percpu(ipvs->cpustats); +err_alloc: + kfree(ipvs->tot_stats); + return -ENOMEM; +} + +static void __net_exit __ip_vs_control_cleanup(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + ip_vs_trash_cleanup(net); + ip_vs_kill_estimator(net, ipvs->tot_stats); + cancel_delayed_work_sync(&ipvs->defense_work); + cancel_work_sync(&ipvs->defense_work.work); + unregister_net_sysctl_table(ipvs->sysctl_hdr); + proc_net_remove(net, "ip_vs_stats_percpu"); + proc_net_remove(net, "ip_vs_stats"); + proc_net_remove(net, "ip_vs"); + free_percpu(ipvs->cpustats); + kfree(ipvs->tot_stats); +} + +static struct pernet_operations ipvs_control_ops = { + .init = __ip_vs_control_init, + .exit = __ip_vs_control_cleanup, +}; int __init ip_vs_control_init(void) { - int ret; int idx; + int ret; EnterFunction(2); - /* Initialize ip_vs_svc_table, ip_vs_svc_fwm_table, ip_vs_rtable */ + /* Initialize svc_table, ip_vs_svc_fwm_table, rs_table */ for(idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { INIT_LIST_HEAD(&ip_vs_svc_table[idx]); INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); } - for(idx = 0; idx < IP_VS_RTAB_SIZE; idx++) { - INIT_LIST_HEAD(&ip_vs_rtable[idx]); + + ret = register_pernet_subsys(&ipvs_control_ops); + if (ret) { + pr_err("cannot register namespace.\n"); + goto err; } - smp_wmb(); + + smp_wmb(); /* Do we really need it now ? */ ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); - return ret; + goto err_net; } ret = ip_vs_genl_register(); if (ret) { pr_err("cannot register Generic Netlink interface.\n"); nf_unregister_sockopt(&ip_vs_sockopts); - return ret; + goto err_net; } - proc_net_fops_create(&init_net, "ip_vs", 0, &ip_vs_info_fops); - proc_net_fops_create(&init_net, "ip_vs_stats",0, &ip_vs_stats_fops); - - sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars); - - ip_vs_new_estimator(&ip_vs_stats); - - /* Hook the defense timer */ - schedule_delayed_work(&defense_work, DEFENSE_TIMER_PERIOD); - LeaveFunction(2); return 0; + +err_net: + unregister_pernet_subsys(&ipvs_control_ops); +err: + return ret; } void ip_vs_control_cleanup(void) { EnterFunction(2); - ip_vs_trash_cleanup(); - cancel_delayed_work_sync(&defense_work); - cancel_work_sync(&defense_work.work); - ip_vs_kill_estimator(&ip_vs_stats); - unregister_sysctl_table(sysctl_header); - proc_net_remove(&init_net, "ip_vs_stats"); - proc_net_remove(&init_net, "ip_vs"); + unregister_pernet_subsys(&ipvs_control_ops); ip_vs_genl_unregister(); nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index ff28801..f560a05 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -8,8 +8,12 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * Changes: - * + * Changes: Hans Schillstrom <hans.schillstrom@ericsson.com> + * Network name space (netns) aware. + * Global data moved to netns i.e struct netns_ipvs + * Affected data: est_list and est_lock. + * estimation_timer() runs with timer per netns. + * get_stats()) do the per cpu summing. */ #define KMSG_COMPONENT "IPVS" @@ -48,11 +52,42 @@ */ -static void estimation_timer(unsigned long arg); +/* + * Make a summary from each cpu + */ +static void ip_vs_read_cpu_stats(struct ip_vs_stats_user *sum, + struct ip_vs_cpu_stats *stats) +{ + int i; + + for_each_possible_cpu(i) { + struct ip_vs_cpu_stats *s = per_cpu_ptr(stats, i); + unsigned int start; + __u64 inbytes, outbytes; + if (i) { + sum->conns += s->ustats.conns; + sum->inpkts += s->ustats.inpkts; + sum->outpkts += s->ustats.outpkts; + do { + start = u64_stats_fetch_begin_bh(&s->syncp); + inbytes = s->ustats.inbytes; + outbytes = s->ustats.outbytes; + } while (u64_stats_fetch_retry_bh(&s->syncp, start)); + sum->inbytes += inbytes; + sum->outbytes += outbytes; + } else { + sum->conns = s->ustats.conns; + sum->inpkts = s->ustats.inpkts; + sum->outpkts = s->ustats.outpkts; + do { + start = u64_stats_fetch_begin_bh(&s->syncp); + sum->inbytes = s->ustats.inbytes; + sum->outbytes = s->ustats.outbytes; + } while (u64_stats_fetch_retry_bh(&s->syncp, start)); + } + } +} -static LIST_HEAD(est_list); -static DEFINE_SPINLOCK(est_lock); -static DEFINE_TIMER(est_timer, estimation_timer, 0, 0); static void estimation_timer(unsigned long arg) { @@ -62,11 +97,16 @@ static void estimation_timer(unsigned long arg) u32 n_inpkts, n_outpkts; u64 n_inbytes, n_outbytes; u32 rate; + struct net *net = (struct net *)arg; + struct netns_ipvs *ipvs; - spin_lock(&est_lock); - list_for_each_entry(e, &est_list, list) { + ipvs = net_ipvs(net); + ip_vs_read_cpu_stats(&ipvs->tot_stats->ustats, ipvs->cpustats); + spin_lock(&ipvs->est_lock); + list_for_each_entry(e, &ipvs->est_list, list) { s = container_of(e, struct ip_vs_stats, est); + ip_vs_read_cpu_stats(&s->ustats, s->cpustats); spin_lock(&s->lock); n_conns = s->ustats.conns; n_inpkts = s->ustats.inpkts; @@ -75,38 +115,39 @@ static void estimation_timer(unsigned long arg) n_outbytes = s->ustats.outbytes; /* scaled by 2^10, but divided 2 seconds */ - rate = (n_conns - e->last_conns)<<9; + rate = (n_conns - e->last_conns) << 9; e->last_conns = n_conns; - e->cps += ((long)rate - (long)e->cps)>>2; - s->ustats.cps = (e->cps+0x1FF)>>10; + e->cps += ((long)rate - (long)e->cps) >> 2; + s->ustats.cps = (e->cps + 0x1FF) >> 10; - rate = (n_inpkts - e->last_inpkts)<<9; + rate = (n_inpkts - e->last_inpkts) << 9; e->last_inpkts = n_inpkts; - e->inpps += ((long)rate - (long)e->inpps)>>2; - s->ustats.inpps = (e->inpps+0x1FF)>>10; + e->inpps += ((long)rate - (long)e->inpps) >> 2; + s->ustats.inpps = (e->inpps + 0x1FF) >> 10; - rate = (n_outpkts - e->last_outpkts)<<9; + rate = (n_outpkts - e->last_outpkts) << 9; e->last_outpkts = n_outpkts; - e->outpps += ((long)rate - (long)e->outpps)>>2; - s->ustats.outpps = (e->outpps+0x1FF)>>10; + e->outpps += ((long)rate - (long)e->outpps) >> 2; + s->ustats.outpps = (e->outpps + 0x1FF) >> 10; - rate = (n_inbytes - e->last_inbytes)<<4; + rate = (n_inbytes - e->last_inbytes) << 4; e->last_inbytes = n_inbytes; - e->inbps += ((long)rate - (long)e->inbps)>>2; - s->ustats.inbps = (e->inbps+0xF)>>5; + e->inbps += ((long)rate - (long)e->inbps) >> 2; + s->ustats.inbps = (e->inbps + 0xF) >> 5; - rate = (n_outbytes - e->last_outbytes)<<4; + rate = (n_outbytes - e->last_outbytes) << 4; e->last_outbytes = n_outbytes; - e->outbps += ((long)rate - (long)e->outbps)>>2; - s->ustats.outbps = (e->outbps+0xF)>>5; + e->outbps += ((long)rate - (long)e->outbps) >> 2; + s->ustats.outbps = (e->outbps + 0xF) >> 5; spin_unlock(&s->lock); } - spin_unlock(&est_lock); - mod_timer(&est_timer, jiffies + 2*HZ); + spin_unlock(&ipvs->est_lock); + mod_timer(&ipvs->est_timer, jiffies + 2*HZ); } -void ip_vs_new_estimator(struct ip_vs_stats *stats) +void ip_vs_new_estimator(struct net *net, struct ip_vs_stats *stats) { + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_estimator *est = &stats->est; INIT_LIST_HEAD(&est->list); @@ -126,18 +167,19 @@ void ip_vs_new_estimator(struct ip_vs_stats *stats) est->last_outbytes = stats->ustats.outbytes; est->outbps = stats->ustats.outbps<<5; - spin_lock_bh(&est_lock); - list_add(&est->list, &est_list); - spin_unlock_bh(&est_lock); + spin_lock_bh(&ipvs->est_lock); + list_add(&est->list, &ipvs->est_list); + spin_unlock_bh(&ipvs->est_lock); } -void ip_vs_kill_estimator(struct ip_vs_stats *stats) +void ip_vs_kill_estimator(struct net *net, struct ip_vs_stats *stats) { + struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_estimator *est = &stats->est; - spin_lock_bh(&est_lock); + spin_lock_bh(&ipvs->est_lock); list_del(&est->list); - spin_unlock_bh(&est_lock); + spin_unlock_bh(&ipvs->est_lock); } void ip_vs_zero_estimator(struct ip_vs_stats *stats) @@ -157,13 +199,35 @@ void ip_vs_zero_estimator(struct ip_vs_stats *stats) est->outbps = 0; } -int __init ip_vs_estimator_init(void) +static int __net_init __ip_vs_estimator_init(struct net *net) { - mod_timer(&est_timer, jiffies + 2 * HZ); + struct netns_ipvs *ipvs = net_ipvs(net); + + INIT_LIST_HEAD(&ipvs->est_list); + spin_lock_init(&ipvs->est_lock); + setup_timer(&ipvs->est_timer, estimation_timer, (unsigned long)net); + mod_timer(&ipvs->est_timer, jiffies + 2 * HZ); return 0; } +static void __net_exit __ip_vs_estimator_exit(struct net *net) +{ + del_timer_sync(&net_ipvs(net)->est_timer); +} +static struct pernet_operations ip_vs_app_ops = { + .init = __ip_vs_estimator_init, + .exit = __ip_vs_estimator_exit, +}; + +int __init ip_vs_estimator_init(void) +{ + int rv; + + rv = register_pernet_subsys(&ip_vs_app_ops); + return rv; +} + void ip_vs_estimator_cleanup(void) { - del_timer_sync(&est_timer); + unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 7545500..6b5dd6d 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -157,6 +157,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, int ret = 0; enum ip_conntrack_info ctinfo; struct nf_conn *ct; + struct net *net; #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, @@ -197,18 +198,20 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, */ { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(AF_INET, iph->protocol, - &from, port, &cp->caddr, 0, &p); + ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET, + iph->protocol, &from, port, + &cp->caddr, 0, &p); n_cp = ip_vs_conn_out_get(&p); } if (!n_cp) { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(AF_INET, IPPROTO_TCP, &cp->caddr, + ip_vs_conn_fill_param(ip_vs_conn_net(cp), + AF_INET, IPPROTO_TCP, &cp->caddr, 0, &cp->vaddr, port, &p); n_cp = ip_vs_conn_new(&p, &from, port, IP_VS_CONN_F_NO_CPORT | IP_VS_CONN_F_NFCT, - cp->dest); + cp->dest, skb->mark); if (!n_cp) return 0; @@ -257,8 +260,9 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp, * would be adjusted twice. */ + net = skb_net(skb); cp->app_data = NULL; - ip_vs_tcp_conn_listen(n_cp); + ip_vs_tcp_conn_listen(net, n_cp); ip_vs_conn_put(n_cp); return ret; } @@ -287,6 +291,7 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, union nf_inet_addr to; __be16 port; struct ip_vs_conn *n_cp; + struct net *net; #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, @@ -358,14 +363,15 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, { struct ip_vs_conn_param p; - ip_vs_conn_fill_param(AF_INET, iph->protocol, &to, port, - &cp->vaddr, htons(ntohs(cp->vport)-1), - &p); + ip_vs_conn_fill_param(ip_vs_conn_net(cp), AF_INET, + iph->protocol, &to, port, &cp->vaddr, + htons(ntohs(cp->vport)-1), &p); n_cp = ip_vs_conn_in_get(&p); if (!n_cp) { n_cp = ip_vs_conn_new(&p, &cp->daddr, htons(ntohs(cp->dport)-1), - IP_VS_CONN_F_NFCT, cp->dest); + IP_VS_CONN_F_NFCT, cp->dest, + skb->mark); if (!n_cp) return 0; @@ -377,7 +383,8 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, /* * Move tunnel to listen state */ - ip_vs_tcp_conn_listen(n_cp); + net = skb_net(skb); + ip_vs_tcp_conn_listen(net, n_cp); ip_vs_conn_put(n_cp); return 1; @@ -398,23 +405,22 @@ static struct ip_vs_app ip_vs_ftp = { .pkt_in = ip_vs_ftp_in, }; - /* - * ip_vs_ftp initialization + * per netns ip_vs_ftp initialization */ -static int __init ip_vs_ftp_init(void) +static int __net_init __ip_vs_ftp_init(struct net *net) { int i, ret; struct ip_vs_app *app = &ip_vs_ftp; - ret = register_ip_vs_app(app); + ret = register_ip_vs_app(net, app); if (ret) return ret; for (i=0; i<IP_VS_APP_MAX_PORTS; i++) { if (!ports[i]) continue; - ret = register_ip_vs_app_inc(app, app->protocol, ports[i]); + ret = register_ip_vs_app_inc(net, app, app->protocol, ports[i]); if (ret) break; pr_info("%s: loaded support on port[%d] = %d\n", @@ -422,18 +428,39 @@ static int __init ip_vs_ftp_init(void) } if (ret) - unregister_ip_vs_app(app); + unregister_ip_vs_app(net, app); return ret; } +/* + * netns exit + */ +static void __ip_vs_ftp_exit(struct net *net) +{ + struct ip_vs_app *app = &ip_vs_ftp; + + unregister_ip_vs_app(net, app); +} + +static struct pernet_operations ip_vs_ftp_ops = { + .init = __ip_vs_ftp_init, + .exit = __ip_vs_ftp_exit, +}; +int __init ip_vs_ftp_init(void) +{ + int rv; + + rv = register_pernet_subsys(&ip_vs_ftp_ops); + return rv; +} /* * ip_vs_ftp finish. */ static void __exit ip_vs_ftp_exit(void) { - unregister_ip_vs_app(&ip_vs_ftp); + unregister_pernet_subsys(&ip_vs_ftp_ops); } diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 9323f89..d5bec33 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -70,7 +70,6 @@ * entries that haven't been touched for a day. */ #define COUNT_FOR_FULL_EXPIRATION 30 -static int sysctl_ip_vs_lblc_expiration = 24*60*60*HZ; /* @@ -117,7 +116,7 @@ struct ip_vs_lblc_table { static ctl_table vs_vars_table[] = { { .procname = "lblc_expiration", - .data = &sysctl_ip_vs_lblc_expiration, + .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -125,8 +124,6 @@ static ctl_table vs_vars_table[] = { { } }; -static struct ctl_table_header * sysctl_header; - static inline void ip_vs_lblc_free(struct ip_vs_lblc_entry *en) { list_del(&en->list); @@ -248,6 +245,7 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) struct ip_vs_lblc_entry *en, *nxt; unsigned long now = jiffies; int i, j; + struct netns_ipvs *ipvs = net_ipvs(svc->net); for (i=0, j=tbl->rover; i<IP_VS_LBLC_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLC_TAB_MASK; @@ -255,7 +253,8 @@ static inline void ip_vs_lblc_full_check(struct ip_vs_service *svc) write_lock(&svc->sched_lock); list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) { if (time_before(now, - en->lastuse + sysctl_ip_vs_lblc_expiration)) + en->lastuse + + ipvs->sysctl_lblc_expiration)) continue; ip_vs_lblc_free(en); @@ -543,23 +542,73 @@ static struct ip_vs_scheduler ip_vs_lblc_scheduler = .schedule = ip_vs_lblc_schedule, }; +/* + * per netns init. + */ +static int __net_init __ip_vs_lblc_init(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + if (!net_eq(net, &init_net)) { + ipvs->lblc_ctl_table = kmemdup(vs_vars_table, + sizeof(vs_vars_table), + GFP_KERNEL); + if (ipvs->lblc_ctl_table == NULL) + goto err_dup; + } else + ipvs->lblc_ctl_table = vs_vars_table; + ipvs->sysctl_lblc_expiration = 24*60*60*HZ; + ipvs->lblc_ctl_table[0].data = &ipvs->sysctl_lblc_expiration; + + ipvs->lblc_ctl_header = + register_net_sysctl_table(net, net_vs_ctl_path, + ipvs->lblc_ctl_table); + if (!ipvs->lblc_ctl_header) + goto err_reg; + + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(ipvs->lblc_ctl_table); + +err_dup: + return -ENOMEM; +} + +static void __net_exit __ip_vs_lblc_exit(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + unregister_net_sysctl_table(ipvs->lblc_ctl_header); + + if (!net_eq(net, &init_net)) + kfree(ipvs->lblc_ctl_table); +} + +static struct pernet_operations ip_vs_lblc_ops = { + .init = __ip_vs_lblc_init, + .exit = __ip_vs_lblc_exit, +}; static int __init ip_vs_lblc_init(void) { int ret; - sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table); + ret = register_pernet_subsys(&ip_vs_lblc_ops); + if (ret) + return ret; + ret = register_ip_vs_scheduler(&ip_vs_lblc_scheduler); if (ret) - unregister_sysctl_table(sysctl_header); + unregister_pernet_subsys(&ip_vs_lblc_ops); return ret; } - static void __exit ip_vs_lblc_cleanup(void) { - unregister_sysctl_table(sysctl_header); unregister_ip_vs_scheduler(&ip_vs_lblc_scheduler); + unregister_pernet_subsys(&ip_vs_lblc_ops); } diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index dbeed8e..61ae8cf 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -70,8 +70,6 @@ * entries that haven't been touched for a day. */ #define COUNT_FOR_FULL_EXPIRATION 30 -static int sysctl_ip_vs_lblcr_expiration = 24*60*60*HZ; - /* * for IPVS lblcr entry hash table @@ -296,7 +294,7 @@ struct ip_vs_lblcr_table { static ctl_table vs_vars_table[] = { { .procname = "lblcr_expiration", - .data = &sysctl_ip_vs_lblcr_expiration, + .data = NULL, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, @@ -304,8 +302,6 @@ static ctl_table vs_vars_table[] = { { } }; -static struct ctl_table_header * sysctl_header; - static inline void ip_vs_lblcr_free(struct ip_vs_lblcr_entry *en) { list_del(&en->list); @@ -425,14 +421,15 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc) unsigned long now = jiffies; int i, j; struct ip_vs_lblcr_entry *en, *nxt; + struct netns_ipvs *ipvs = net_ipvs(svc->net); for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) { j = (j + 1) & IP_VS_LBLCR_TAB_MASK; write_lock(&svc->sched_lock); list_for_each_entry_safe(en, nxt, &tbl->bucket[j], list) { - if (time_after(en->lastuse+sysctl_ip_vs_lblcr_expiration, - now)) + if (time_after(en->lastuse + + ipvs->sysctl_lblcr_expiration, now)) continue; ip_vs_lblcr_free(en); @@ -664,6 +661,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) read_lock(&svc->sched_lock); en = ip_vs_lblcr_get(svc->af, tbl, &iph.daddr); if (en) { + struct netns_ipvs *ipvs = net_ipvs(svc->net); /* We only hold a read lock, but this is atomic */ en->lastuse = jiffies; @@ -675,7 +673,7 @@ ip_vs_lblcr_schedule(struct ip_vs_service *svc, const struct sk_buff *skb) /* More than one destination + enough time passed by, cleanup */ if (atomic_read(&en->set.size) > 1 && time_after(jiffies, en->set.lastmod + - sysctl_ip_vs_lblcr_expiration)) { + ipvs->sysctl_lblcr_expiration)) { struct ip_vs_dest *m; write_lock(&en->set.lock); @@ -744,23 +742,73 @@ static struct ip_vs_scheduler ip_vs_lblcr_scheduler = .schedule = ip_vs_lblcr_schedule, }; +/* + * per netns init. + */ +static int __net_init __ip_vs_lblcr_init(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + if (!net_eq(net, &init_net)) { + ipvs->lblcr_ctl_table = kmemdup(vs_vars_table, + sizeof(vs_vars_table), + GFP_KERNEL); + if (ipvs->lblcr_ctl_table == NULL) + goto err_dup; + } else + ipvs->lblcr_ctl_table = vs_vars_table; + ipvs->sysctl_lblcr_expiration = 24*60*60*HZ; + ipvs->lblcr_ctl_table[0].data = &ipvs->sysctl_lblcr_expiration; + + ipvs->lblcr_ctl_header = + register_net_sysctl_table(net, net_vs_ctl_path, + ipvs->lblcr_ctl_table); + if (!ipvs->lblcr_ctl_header) + goto err_reg; + + return 0; + +err_reg: + if (!net_eq(net, &init_net)) + kfree(ipvs->lblcr_ctl_table); + +err_dup: + return -ENOMEM; +} + +static void __net_exit __ip_vs_lblcr_exit(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + unregister_net_sysctl_table(ipvs->lblcr_ctl_header); + + if (!net_eq(net, &init_net)) + kfree(ipvs->lblcr_ctl_table); +} + +static struct pernet_operations ip_vs_lblcr_ops = { + .init = __ip_vs_lblcr_init, + .exit = __ip_vs_lblcr_exit, +}; static int __init ip_vs_lblcr_init(void) { int ret; - sysctl_header = register_sysctl_paths(net_vs_ctl_path, vs_vars_table); + ret = register_pernet_subsys(&ip_vs_lblcr_ops); + if (ret) + return ret; + ret = register_ip_vs_scheduler(&ip_vs_lblcr_scheduler); if (ret) - unregister_sysctl_table(sysctl_header); + unregister_pernet_subsys(&ip_vs_lblcr_ops); return ret; } - static void __exit ip_vs_lblcr_cleanup(void) { - unregister_sysctl_table(sysctl_header); unregister_ip_vs_scheduler(&ip_vs_lblcr_scheduler); + unregister_pernet_subsys(&ip_vs_lblcr_ops); } diff --git a/net/netfilter/ipvs/ip_vs_nfct.c b/net/netfilter/ipvs/ip_vs_nfct.c index 4680647..f454c80 100644 --- a/net/netfilter/ipvs/ip_vs_nfct.c +++ b/net/netfilter/ipvs/ip_vs_nfct.c @@ -141,6 +141,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, struct nf_conntrack_tuple *orig, new_reply; struct ip_vs_conn *cp; struct ip_vs_conn_param p; + struct net *net = nf_ct_net(ct); if (exp->tuple.src.l3num != PF_INET) return; @@ -155,7 +156,7 @@ static void ip_vs_nfct_expect_callback(struct nf_conn *ct, /* RS->CLIENT */ orig = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; - ip_vs_conn_fill_param(exp->tuple.src.l3num, orig->dst.protonum, + ip_vs_conn_fill_param(net, exp->tuple.src.l3num, orig->dst.protonum, &orig->src.u3, orig->src.u.tcp.port, &orig->dst.u3, orig->dst.u.tcp.port, &p); cp = ip_vs_conn_out_get(&p); @@ -268,7 +269,8 @@ void ip_vs_conn_drop_conntrack(struct ip_vs_conn *cp) " for conn " FMT_CONN "\n", __func__, ARG_TUPLE(&tuple), ARG_CONN(cp)); - h = nf_conntrack_find_get(&init_net, NF_CT_DEFAULT_ZONE, &tuple); + h = nf_conntrack_find_get(ip_vs_conn_net(cp), NF_CT_DEFAULT_ZONE, + &tuple); if (h) { ct = nf_ct_tuplehash_to_ctrack(h); /* Show what happens instead of calling nf_ct_kill() */ diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c index 3414af7..5cf859c 100644 --- a/net/netfilter/ipvs/ip_vs_pe.c +++ b/net/netfilter/ipvs/ip_vs_pe.c @@ -29,12 +29,11 @@ void ip_vs_unbind_pe(struct ip_vs_service *svc) } /* Get pe in the pe list by name */ -static struct ip_vs_pe * -ip_vs_pe_getbyname(const char *pe_name) +struct ip_vs_pe *__ip_vs_pe_getbyname(const char *pe_name) { struct ip_vs_pe *pe; - IP_VS_DBG(2, "%s(): pe_name \"%s\"\n", __func__, + IP_VS_DBG(10, "%s(): pe_name \"%s\"\n", __func__, pe_name); spin_lock_bh(&ip_vs_pe_lock); @@ -60,28 +59,22 @@ ip_vs_pe_getbyname(const char *pe_name) } /* Lookup pe and try to load it if it doesn't exist */ -struct ip_vs_pe *ip_vs_pe_get(const char *name) +struct ip_vs_pe *ip_vs_pe_getbyname(const char *name) { struct ip_vs_pe *pe; /* Search for the pe by name */ - pe = ip_vs_pe_getbyname(name); + pe = __ip_vs_pe_getbyname(name); /* If pe not found, load the module and search again */ if (!pe) { request_module("ip_vs_pe_%s", name); - pe = ip_vs_pe_getbyname(name); + pe = __ip_vs_pe_getbyname(name); } return pe; } -void ip_vs_pe_put(struct ip_vs_pe *pe) -{ - if (pe && pe->module) - module_put(pe->module); -} - /* Register a pe in the pe list */ int register_ip_vs_pe(struct ip_vs_pe *pe) { diff --git a/net/netfilter/ipvs/ip_vs_pe_sip.c b/net/netfilter/ipvs/ip_vs_pe_sip.c index b8b4e96..0d83bc0 100644 --- a/net/netfilter/ipvs/ip_vs_pe_sip.c +++ b/net/netfilter/ipvs/ip_vs_pe_sip.c @@ -71,6 +71,7 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) struct ip_vs_iphdr iph; unsigned int dataoff, datalen, matchoff, matchlen; const char *dptr; + int retc; ip_vs_fill_iphdr(p->af, skb_network_header(skb), &iph); @@ -83,6 +84,8 @@ ip_vs_sip_fill_param(struct ip_vs_conn_param *p, struct sk_buff *skb) if (dataoff >= skb->len) return -EINVAL; + if ((retc=skb_linearize(skb)) < 0) + return retc; dptr = skb->data + dataoff; datalen = skb->len - dataoff; diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index c539983..17484a4 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -60,6 +60,35 @@ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp) return 0; } +#if defined(CONFIG_IP_VS_PROTO_TCP) || defined(CONFIG_IP_VS_PROTO_UDP) || \ + defined(CONFIG_IP_VS_PROTO_SCTP) || defined(CONFIG_IP_VS_PROTO_AH) || \ + defined(CONFIG_IP_VS_PROTO_ESP) +/* + * register an ipvs protocols netns related data + */ +static int +register_ip_vs_proto_netns(struct net *net, struct ip_vs_protocol *pp) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + unsigned hash = IP_VS_PROTO_HASH(pp->protocol); + struct ip_vs_proto_data *pd = + kzalloc(sizeof(struct ip_vs_proto_data), GFP_ATOMIC); + + if (!pd) { + pr_err("%s(): no memory.\n", __func__); + return -ENOMEM; + } + pd->pp = pp; /* For speed issues */ + pd->next = ipvs->proto_data_table[hash]; + ipvs->proto_data_table[hash] = pd; + atomic_set(&pd->appcnt, 0); /* Init app counter */ + + if (pp->init_netns != NULL) + pp->init_netns(net, pd); + + return 0; +} +#endif /* * unregister an ipvs protocol @@ -82,6 +111,29 @@ static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp) return -ESRCH; } +/* + * unregister an ipvs protocols netns data + */ +static int +unregister_ip_vs_proto_netns(struct net *net, struct ip_vs_proto_data *pd) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data **pd_p; + unsigned hash = IP_VS_PROTO_HASH(pd->pp->protocol); + + pd_p = &ipvs->proto_data_table[hash]; + for (; *pd_p; pd_p = &(*pd_p)->next) { + if (*pd_p == pd) { + *pd_p = pd->next; + if (pd->pp->exit_netns != NULL) + pd->pp->exit_netns(net, pd); + kfree(pd); + return 0; + } + } + + return -ESRCH; +} /* * get ip_vs_protocol object by its proto. @@ -100,19 +152,44 @@ struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto) } EXPORT_SYMBOL(ip_vs_proto_get); +/* + * get ip_vs_protocol object data by netns and proto + */ +struct ip_vs_proto_data * +__ipvs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) +{ + struct ip_vs_proto_data *pd; + unsigned hash = IP_VS_PROTO_HASH(proto); + + for (pd = ipvs->proto_data_table[hash]; pd; pd = pd->next) { + if (pd->pp->protocol == proto) + return pd; + } + + return NULL; +} + +struct ip_vs_proto_data * +ip_vs_proto_data_get(struct net *net, unsigned short proto) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + return __ipvs_proto_data_get(ipvs, proto); +} +EXPORT_SYMBOL(ip_vs_proto_data_get); /* * Propagate event for state change to all protocols */ -void ip_vs_protocol_timeout_change(int flags) +void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags) { - struct ip_vs_protocol *pp; + struct ip_vs_proto_data *pd; int i; for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { - for (pp = ip_vs_proto_table[i]; pp; pp = pp->next) { - if (pp->timeout_change) - pp->timeout_change(pp, flags); + for (pd = ipvs->proto_data_table[i]; pd; pd = pd->next) { + if (pd->pp->timeout_change) + pd->pp->timeout_change(pd, flags); } } } @@ -236,6 +313,46 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, ip_vs_tcpudp_debug_packet_v4(pp, skb, offset, msg); } +/* + * per network name-space init + */ +static int __net_init __ip_vs_protocol_init(struct net *net) +{ +#ifdef CONFIG_IP_VS_PROTO_TCP + register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp); +#endif +#ifdef CONFIG_IP_VS_PROTO_UDP + register_ip_vs_proto_netns(net, &ip_vs_protocol_udp); +#endif +#ifdef CONFIG_IP_VS_PROTO_SCTP + register_ip_vs_proto_netns(net, &ip_vs_protocol_sctp); +#endif +#ifdef CONFIG_IP_VS_PROTO_AH + register_ip_vs_proto_netns(net, &ip_vs_protocol_ah); +#endif +#ifdef CONFIG_IP_VS_PROTO_ESP + register_ip_vs_proto_netns(net, &ip_vs_protocol_esp); +#endif + return 0; +} + +static void __net_exit __ip_vs_protocol_cleanup(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd; + int i; + + /* unregister all the ipvs proto data for this netns */ + for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { + while ((pd = ipvs->proto_data_table[i]) != NULL) + unregister_ip_vs_proto_netns(net, pd); + } +} + +static struct pernet_operations ipvs_proto_ops = { + .init = __ip_vs_protocol_init, + .exit = __ip_vs_protocol_cleanup, +}; int __init ip_vs_protocol_init(void) { @@ -265,6 +382,7 @@ int __init ip_vs_protocol_init(void) REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif pr_info("Registered protocols (%s)\n", &protocols[2]); + return register_pernet_subsys(&ipvs_proto_ops); return 0; } @@ -275,6 +393,7 @@ void ip_vs_protocol_cleanup(void) struct ip_vs_protocol *pp; int i; + unregister_pernet_subsys(&ipvs_proto_ops); /* unregister all the ipvs protocols */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pp = ip_vs_proto_table[i]) != NULL) diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 3a04611..5b8eb8b 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -41,28 +41,30 @@ struct isakmp_hdr { #define PORT_ISAKMP 500 static void -ah_esp_conn_fill_param_proto(int af, const struct ip_vs_iphdr *iph, - int inverse, struct ip_vs_conn_param *p) +ah_esp_conn_fill_param_proto(struct net *net, int af, + const struct ip_vs_iphdr *iph, int inverse, + struct ip_vs_conn_param *p) { if (likely(!inverse)) - ip_vs_conn_fill_param(af, IPPROTO_UDP, + ip_vs_conn_fill_param(net, af, IPPROTO_UDP, &iph->saddr, htons(PORT_ISAKMP), &iph->daddr, htons(PORT_ISAKMP), p); else - ip_vs_conn_fill_param(af, IPPROTO_UDP, + ip_vs_conn_fill_param(net, af, IPPROTO_UDP, &iph->daddr, htons(PORT_ISAKMP), &iph->saddr, htons(PORT_ISAKMP), p); } static struct ip_vs_conn * -ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, +ah_esp_conn_in_get(int af, const struct sk_buff *skb, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; + struct net *net = skb_net(skb); - ah_esp_conn_fill_param_proto(af, iph, inverse, &p); + ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p); cp = ip_vs_conn_in_get(&p); if (!cp) { /* @@ -72,7 +74,7 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for outin packet " "%s%s %s->%s\n", inverse ? "ICMP+" : "", - pp->name, + ip_vs_proto_get(iph->protocol)->name, IP_VS_DBG_ADDR(af, &iph->saddr), IP_VS_DBG_ADDR(af, &iph->daddr)); } @@ -83,21 +85,21 @@ ah_esp_conn_in_get(int af, const struct sk_buff *skb, struct ip_vs_protocol *pp, static struct ip_vs_conn * ah_esp_conn_out_get(int af, const struct sk_buff *skb, - struct ip_vs_protocol *pp, const struct ip_vs_iphdr *iph, unsigned int proto_off, int inverse) { struct ip_vs_conn *cp; struct ip_vs_conn_param p; + struct net *net = skb_net(skb); - ah_esp_conn_fill_param_proto(af, iph, inverse, &p); + ah_esp_conn_fill_param_proto(net, af, iph, inverse, &p); cp = ip_vs_conn_out_get(&p); if (!cp) { IP_VS_DBG_BUF(12, "Unknown ISAKMP entry for inout packet " "%s%s %s->%s\n", inverse ? "ICMP+" : "", - pp->name, + ip_vs_proto_get(iph->protocol)->name, IP_VS_DBG_ADDR(af, &iph->saddr), IP_VS_DBG_ADDR(af, &iph->daddr)); } @@ -107,7 +109,7 @@ ah_esp_conn_out_get(int af, const struct sk_buff *skb, static int -ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, +ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp) { /* @@ -117,26 +119,14 @@ ah_esp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, return 0; } -static void ah_esp_init(struct ip_vs_protocol *pp) -{ - /* nothing to do now */ -} - - -static void ah_esp_exit(struct ip_vs_protocol *pp) -{ - /* nothing to do now */ -} - - #ifdef CONFIG_IP_VS_PROTO_AH struct ip_vs_protocol ip_vs_protocol_ah = { .name = "AH", .protocol = IPPROTO_AH, .num_states = 1, .dont_defrag = 1, - .init = ah_esp_init, - .exit = ah_esp_exit, + .init = NULL, + .exit = NULL, .conn_schedule = ah_esp_conn_schedule, .conn_in_get = ah_esp_conn_in_get, .conn_out_get = ah_esp_conn_out_get, @@ -149,7 +139,6 @@ struct ip_vs_protocol ip_vs_protocol_ah = { .app_conn_bind = NULL, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = NULL, /* ISAKMP */ - .set_state_timeout = NULL, }; #endif @@ -159,8 +148,8 @@ struct ip_vs_protocol ip_vs_protocol_esp = { .protocol = IPPROTO_ESP, .num_states = 1, .dont_defrag = 1, - .init = ah_esp_init, - .exit = ah_esp_exit, + .init = NULL, + .exit = NULL, .conn_schedule = ah_esp_conn_schedule, .conn_in_get = ah_esp_conn_in_get, .conn_out_get = ah_esp_conn_out_get, diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index 1ea96bc..fb2d04a 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -9,9 +9,10 @@ #include <net/ip_vs.h> static int -sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, +sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp) { + struct net *net; struct ip_vs_service *svc; sctp_chunkhdr_t _schunkh, *sch; sctp_sctphdr_t *sh, _sctph; @@ -27,13 +28,13 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, sizeof(_schunkh), &_schunkh); if (sch == NULL) return 0; - + net = skb_net(skb); if ((sch->type == SCTP_CID_INIT) && - (svc = ip_vs_service_get(af, skb->mark, iph.protocol, + (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol, &iph.daddr, sh->dest))) { int ignored; - if (ip_vs_todrop()) { + if (ip_vs_todrop(net_ipvs(net))) { /* * It seems that we are very loaded. * We have to drop this packet :( @@ -46,14 +47,19 @@ sctp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb, pp, &ignored); - if (!*cpp && !ignored) { - *verdict = ip_vs_leave(svc, skb, pp); + *cpp = ip_vs_schedule(svc, skb, pd, &ignored); + if (!*cpp && ignored <= 0) { + if (!ignored) + *verdict = ip_vs_leave(svc, skb, pd); + else { + ip_vs_service_put(svc); + *verdict = NF_DROP; + } return 0; } ip_vs_service_put(svc); } - + /* NF_ACCEPT */ return 1; } @@ -856,7 +862,7 @@ static struct ipvs_sctp_nextstate /* * Timeout table[state] */ -static int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = { +static const int sctp_timeouts[IP_VS_SCTP_S_LAST + 1] = { [IP_VS_SCTP_S_NONE] = 2 * HZ, [IP_VS_SCTP_S_INIT_CLI] = 1 * 60 * HZ, [IP_VS_SCTP_S_INIT_SER] = 1 * 60 * HZ, @@ -900,20 +906,8 @@ static const char *sctp_state_name(int state) return "?"; } -static void sctp_timeout_change(struct ip_vs_protocol *pp, int flags) -{ -} - -static int -sctp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to) -{ - -return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_SCTP_S_LAST, - sctp_state_name_table, sname, to); -} - static inline int -set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, +set_sctp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int direction, const struct sk_buff *skb) { sctp_chunkhdr_t _sctpch, *sch; @@ -971,7 +965,7 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, IP_VS_DBG_BUF(8, "%s %s %s:%d->" "%s:%d state: %s->%s conn->refcnt:%d\n", - pp->name, + pd->pp->name, ((direction == IP_VS_DIR_OUTPUT) ? "output " : "input "), IP_VS_DBG_ADDR(cp->af, &cp->daddr), @@ -995,75 +989,73 @@ set_sctp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, } } } + if (likely(pd)) + cp->timeout = pd->timeout_table[cp->state = next_state]; + else /* What to do ? */ + cp->timeout = sctp_timeouts[cp->state = next_state]; - cp->timeout = pp->timeout_table[cp->state = next_state]; - - return 1; + return 1; } static int sctp_state_transition(struct ip_vs_conn *cp, int direction, - const struct sk_buff *skb, struct ip_vs_protocol *pp) + const struct sk_buff *skb, struct ip_vs_proto_data *pd) { int ret = 0; spin_lock(&cp->lock); - ret = set_sctp_state(pp, cp, direction, skb); + ret = set_sctp_state(pd, cp, direction, skb); spin_unlock(&cp->lock); return ret; } -/* - * Hash table for SCTP application incarnations - */ -#define SCTP_APP_TAB_BITS 4 -#define SCTP_APP_TAB_SIZE (1 << SCTP_APP_TAB_BITS) -#define SCTP_APP_TAB_MASK (SCTP_APP_TAB_SIZE - 1) - -static struct list_head sctp_apps[SCTP_APP_TAB_SIZE]; -static DEFINE_SPINLOCK(sctp_app_lock); - static inline __u16 sctp_app_hashkey(__be16 port) { return (((__force u16)port >> SCTP_APP_TAB_BITS) ^ (__force u16)port) & SCTP_APP_TAB_MASK; } -static int sctp_register_app(struct ip_vs_app *inc) +static int sctp_register_app(struct net *net, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP); hash = sctp_app_hashkey(port); - spin_lock_bh(&sctp_app_lock); - list_for_each_entry(i, &sctp_apps[hash], p_list) { + spin_lock_bh(&ipvs->sctp_app_lock); + list_for_each_entry(i, &ipvs->sctp_apps[hash], p_list) { if (i->port == port) { ret = -EEXIST; goto out; } } - list_add(&inc->p_list, &sctp_apps[hash]); - atomic_inc(&ip_vs_protocol_sctp.appcnt); + list_add(&inc->p_list, &ipvs->sctp_apps[hash]); + atomic_inc(&pd->appcnt); out: - spin_unlock_bh(&sctp_app_lock); + spin_unlock_bh(&ipvs->sctp_app_lock); return ret; } -static void sctp_unregister_app(struct ip_vs_app *inc) +static void sctp_unregister_app(struct net *net, struct ip_vs_app *inc) { - spin_lock_bh(&sctp_app_lock); - atomic_dec(&ip_vs_protocol_sctp.appcnt); + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_SCTP); + + spin_lock_bh(&ipvs->sctp_app_lock); + atomic_dec(&pd->appcnt); list_del(&inc->p_list); - spin_unlock_bh(&sctp_app_lock); + spin_unlock_bh(&ipvs->sctp_app_lock); } static int sctp_app_conn_bind(struct ip_vs_conn *cp) { + struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); int hash; struct ip_vs_app *inc; int result = 0; @@ -1074,12 +1066,12 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp) /* Lookup application incarnations and bind the right one */ hash = sctp_app_hashkey(cp->vport); - spin_lock(&sctp_app_lock); - list_for_each_entry(inc, &sctp_apps[hash], p_list) { + spin_lock(&ipvs->sctp_app_lock); + list_for_each_entry(inc, &ipvs->sctp_apps[hash], p_list) { if (inc->port == cp->vport) { if (unlikely(!ip_vs_app_inc_get(inc))) break; - spin_unlock(&sctp_app_lock); + spin_unlock(&ipvs->sctp_app_lock); IP_VS_DBG_BUF(9, "%s: Binding conn %s:%u->" "%s:%u to app %s on port %u\n", @@ -1095,43 +1087,50 @@ static int sctp_app_conn_bind(struct ip_vs_conn *cp) goto out; } } - spin_unlock(&sctp_app_lock); + spin_unlock(&ipvs->sctp_app_lock); out: return result; } -static void ip_vs_sctp_init(struct ip_vs_protocol *pp) +/* --------------------------------------------- + * timeouts is netns related now. + * --------------------------------------------- + */ +static void __ip_vs_sctp_init(struct net *net, struct ip_vs_proto_data *pd) { - IP_VS_INIT_HASH_TABLE(sctp_apps); - pp->timeout_table = sctp_timeouts; -} + struct netns_ipvs *ipvs = net_ipvs(net); + ip_vs_init_hash_table(ipvs->sctp_apps, SCTP_APP_TAB_SIZE); + spin_lock_init(&ipvs->tcp_app_lock); + pd->timeout_table = ip_vs_create_timeout_table((int *)sctp_timeouts, + sizeof(sctp_timeouts)); +} -static void ip_vs_sctp_exit(struct ip_vs_protocol *pp) +static void __ip_vs_sctp_exit(struct net *net, struct ip_vs_proto_data *pd) { - + kfree(pd->timeout_table); } struct ip_vs_protocol ip_vs_protocol_sctp = { - .name = "SCTP", - .protocol = IPPROTO_SCTP, - .num_states = IP_VS_SCTP_S_LAST, - .dont_defrag = 0, - .appcnt = ATOMIC_INIT(0), - .init = ip_vs_sctp_init, - .exit = ip_vs_sctp_exit, - .register_app = sctp_register_app, + .name = "SCTP", + .protocol = IPPROTO_SCTP, + .num_states = IP_VS_SCTP_S_LAST, + .dont_defrag = 0, + .init = NULL, + .exit = NULL, + .init_netns = __ip_vs_sctp_init, + .exit_netns = __ip_vs_sctp_exit, + .register_app = sctp_register_app, .unregister_app = sctp_unregister_app, - .conn_schedule = sctp_conn_schedule, - .conn_in_get = ip_vs_conn_in_get_proto, - .conn_out_get = ip_vs_conn_out_get_proto, - .snat_handler = sctp_snat_handler, - .dnat_handler = sctp_dnat_handler, - .csum_check = sctp_csum_check, - .state_name = sctp_state_name, + .conn_schedule = sctp_conn_schedule, + .conn_in_get = ip_vs_conn_in_get_proto, + .conn_out_get = ip_vs_conn_out_get_proto, + .snat_handler = sctp_snat_handler, + .dnat_handler = sctp_dnat_handler, + .csum_check = sctp_csum_check, + .state_name = sctp_state_name, .state_transition = sctp_state_transition, - .app_conn_bind = sctp_app_conn_bind, - .debug_packet = ip_vs_tcpudp_debug_packet, - .timeout_change = sctp_timeout_change, - .set_state_timeout = sctp_set_state_timeout, + .app_conn_bind = sctp_app_conn_bind, + .debug_packet = ip_vs_tcpudp_debug_packet, + .timeout_change = NULL, }; diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index f6c5200..c0cc341 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -9,8 +9,12 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * Changes: + * Changes: Hans Schillstrom <hans.schillstrom@ericsson.com> * + * Network name space (netns) aware. + * Global data moved to netns i.e struct netns_ipvs + * tcp_timeouts table has copy per netns in a hash table per + * protocol ip_vs_proto_data and is handled by netns */ #define KMSG_COMPONENT "IPVS" @@ -28,9 +32,10 @@ #include <net/ip_vs.h> static int -tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, +tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp) { + struct net *net; struct ip_vs_service *svc; struct tcphdr _tcph, *th; struct ip_vs_iphdr iph; @@ -42,14 +47,14 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, *verdict = NF_DROP; return 0; } - + net = skb_net(skb); /* No !th->ack check to allow scheduling on SYN+ACK for Active FTP */ if (th->syn && - (svc = ip_vs_service_get(af, skb->mark, iph.protocol, &iph.daddr, - th->dest))) { + (svc = ip_vs_service_get(net, af, skb->mark, iph.protocol, + &iph.daddr, th->dest))) { int ignored; - if (ip_vs_todrop()) { + if (ip_vs_todrop(net_ipvs(net))) { /* * It seems that we are very loaded. * We have to drop this packet :( @@ -63,13 +68,19 @@ tcp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb, pp, &ignored); - if (!*cpp && !ignored) { - *verdict = ip_vs_leave(svc, skb, pp); + *cpp = ip_vs_schedule(svc, skb, pd, &ignored); + if (!*cpp && ignored <= 0) { + if (!ignored) + *verdict = ip_vs_leave(svc, skb, pd); + else { + ip_vs_service_put(svc); + *verdict = NF_DROP; + } return 0; } ip_vs_service_put(svc); } + /* NF_ACCEPT */ return 1; } @@ -338,7 +349,7 @@ static const int tcp_state_off[IP_VS_DIR_LAST] = { /* * Timeout table[state] */ -static int tcp_timeouts[IP_VS_TCP_S_LAST+1] = { +static const int tcp_timeouts[IP_VS_TCP_S_LAST+1] = { [IP_VS_TCP_S_NONE] = 2*HZ, [IP_VS_TCP_S_ESTABLISHED] = 15*60*HZ, [IP_VS_TCP_S_SYN_SENT] = 2*60*HZ, @@ -437,10 +448,7 @@ static struct tcp_states_t tcp_states_dos [] = { /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; -static struct tcp_states_t *tcp_state_table = tcp_states; - - -static void tcp_timeout_change(struct ip_vs_protocol *pp, int flags) +static void tcp_timeout_change(struct ip_vs_proto_data *pd, int flags) { int on = (flags & 1); /* secure_tcp */ @@ -450,14 +458,7 @@ static void tcp_timeout_change(struct ip_vs_protocol *pp, int flags) ** for most if not for all of the applications. Something ** like "capabilities" (flags) for each object. */ - tcp_state_table = (on? tcp_states_dos : tcp_states); -} - -static int -tcp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to) -{ - return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_TCP_S_LAST, - tcp_state_name_table, sname, to); + pd->tcp_state_table = (on ? tcp_states_dos : tcp_states); } static inline int tcp_state_idx(struct tcphdr *th) @@ -474,7 +475,7 @@ static inline int tcp_state_idx(struct tcphdr *th) } static inline void -set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, +set_tcp_state(struct ip_vs_proto_data *pd, struct ip_vs_conn *cp, int direction, struct tcphdr *th) { int state_idx; @@ -497,7 +498,8 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, goto tcp_state_out; } - new_state = tcp_state_table[state_off+state_idx].next_state[cp->state]; + new_state = + pd->tcp_state_table[state_off+state_idx].next_state[cp->state]; tcp_state_out: if (new_state != cp->state) { @@ -505,7 +507,7 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, IP_VS_DBG_BUF(8, "%s %s [%c%c%c%c] %s:%d->" "%s:%d state: %s->%s conn->refcnt:%d\n", - pp->name, + pd->pp->name, ((state_off == TCP_DIR_OUTPUT) ? "output " : "input "), th->syn ? 'S' : '.', @@ -535,17 +537,19 @@ set_tcp_state(struct ip_vs_protocol *pp, struct ip_vs_conn *cp, } } - cp->timeout = pp->timeout_table[cp->state = new_state]; + if (likely(pd)) + cp->timeout = pd->timeout_table[cp->state = new_state]; + else /* What to do ? */ + cp->timeout = tcp_timeouts[cp->state = new_state]; } - /* * Handle state transitions */ static int tcp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_protocol *pp) + struct ip_vs_proto_data *pd) { struct tcphdr _tcph, *th; @@ -560,23 +564,12 @@ tcp_state_transition(struct ip_vs_conn *cp, int direction, return 0; spin_lock(&cp->lock); - set_tcp_state(pp, cp, direction, th); + set_tcp_state(pd, cp, direction, th); spin_unlock(&cp->lock); return 1; } - -/* - * Hash table for TCP application incarnations - */ -#define TCP_APP_TAB_BITS 4 -#define TCP_APP_TAB_SIZE (1 << TCP_APP_TAB_BITS) -#define TCP_APP_TAB_MASK (TCP_APP_TAB_SIZE - 1) - -static struct list_head tcp_apps[TCP_APP_TAB_SIZE]; -static DEFINE_SPINLOCK(tcp_app_lock); - static inline __u16 tcp_app_hashkey(__be16 port) { return (((__force u16)port >> TCP_APP_TAB_BITS) ^ (__force u16)port) @@ -584,44 +577,50 @@ static inline __u16 tcp_app_hashkey(__be16 port) } -static int tcp_register_app(struct ip_vs_app *inc) +static int tcp_register_app(struct net *net, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); hash = tcp_app_hashkey(port); - spin_lock_bh(&tcp_app_lock); - list_for_each_entry(i, &tcp_apps[hash], p_list) { + spin_lock_bh(&ipvs->tcp_app_lock); + list_for_each_entry(i, &ipvs->tcp_apps[hash], p_list) { if (i->port == port) { ret = -EEXIST; goto out; } } - list_add(&inc->p_list, &tcp_apps[hash]); - atomic_inc(&ip_vs_protocol_tcp.appcnt); + list_add(&inc->p_list, &ipvs->tcp_apps[hash]); + atomic_inc(&pd->appcnt); out: - spin_unlock_bh(&tcp_app_lock); + spin_unlock_bh(&ipvs->tcp_app_lock); return ret; } static void -tcp_unregister_app(struct ip_vs_app *inc) +tcp_unregister_app(struct net *net, struct ip_vs_app *inc) { - spin_lock_bh(&tcp_app_lock); - atomic_dec(&ip_vs_protocol_tcp.appcnt); + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + + spin_lock_bh(&ipvs->tcp_app_lock); + atomic_dec(&pd->appcnt); list_del(&inc->p_list); - spin_unlock_bh(&tcp_app_lock); + spin_unlock_bh(&ipvs->tcp_app_lock); } static int tcp_app_conn_bind(struct ip_vs_conn *cp) { + struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); int hash; struct ip_vs_app *inc; int result = 0; @@ -633,12 +632,12 @@ tcp_app_conn_bind(struct ip_vs_conn *cp) /* Lookup application incarnations and bind the right one */ hash = tcp_app_hashkey(cp->vport); - spin_lock(&tcp_app_lock); - list_for_each_entry(inc, &tcp_apps[hash], p_list) { + spin_lock(&ipvs->tcp_app_lock); + list_for_each_entry(inc, &ipvs->tcp_apps[hash], p_list) { if (inc->port == cp->vport) { if (unlikely(!ip_vs_app_inc_get(inc))) break; - spin_unlock(&tcp_app_lock); + spin_unlock(&ipvs->tcp_app_lock); IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->" "%s:%u to app %s on port %u\n", @@ -655,7 +654,7 @@ tcp_app_conn_bind(struct ip_vs_conn *cp) goto out; } } - spin_unlock(&tcp_app_lock); + spin_unlock(&ipvs->tcp_app_lock); out: return result; @@ -665,24 +664,35 @@ tcp_app_conn_bind(struct ip_vs_conn *cp) /* * Set LISTEN timeout. (ip_vs_conn_put will setup timer) */ -void ip_vs_tcp_conn_listen(struct ip_vs_conn *cp) +void ip_vs_tcp_conn_listen(struct net *net, struct ip_vs_conn *cp) { + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_TCP); + spin_lock(&cp->lock); cp->state = IP_VS_TCP_S_LISTEN; - cp->timeout = ip_vs_protocol_tcp.timeout_table[IP_VS_TCP_S_LISTEN]; + cp->timeout = (pd ? pd->timeout_table[IP_VS_TCP_S_LISTEN] + : tcp_timeouts[IP_VS_TCP_S_LISTEN]); spin_unlock(&cp->lock); } - -static void ip_vs_tcp_init(struct ip_vs_protocol *pp) +/* --------------------------------------------- + * timeouts is netns related now. + * --------------------------------------------- + */ +static void __ip_vs_tcp_init(struct net *net, struct ip_vs_proto_data *pd) { - IP_VS_INIT_HASH_TABLE(tcp_apps); - pp->timeout_table = tcp_timeouts; -} + struct netns_ipvs *ipvs = net_ipvs(net); + ip_vs_init_hash_table(ipvs->tcp_apps, TCP_APP_TAB_SIZE); + spin_lock_init(&ipvs->tcp_app_lock); + pd->timeout_table = ip_vs_create_timeout_table((int *)tcp_timeouts, + sizeof(tcp_timeouts)); + pd->tcp_state_table = tcp_states; +} -static void ip_vs_tcp_exit(struct ip_vs_protocol *pp) +static void __ip_vs_tcp_exit(struct net *net, struct ip_vs_proto_data *pd) { + kfree(pd->timeout_table); } @@ -691,9 +701,10 @@ struct ip_vs_protocol ip_vs_protocol_tcp = { .protocol = IPPROTO_TCP, .num_states = IP_VS_TCP_S_LAST, .dont_defrag = 0, - .appcnt = ATOMIC_INIT(0), - .init = ip_vs_tcp_init, - .exit = ip_vs_tcp_exit, + .init = NULL, + .exit = NULL, + .init_netns = __ip_vs_tcp_init, + .exit_netns = __ip_vs_tcp_exit, .register_app = tcp_register_app, .unregister_app = tcp_unregister_app, .conn_schedule = tcp_conn_schedule, @@ -707,5 +718,4 @@ struct ip_vs_protocol ip_vs_protocol_tcp = { .app_conn_bind = tcp_app_conn_bind, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = tcp_timeout_change, - .set_state_timeout = tcp_set_state_timeout, }; diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 9d106a0..f1282cb 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -9,7 +9,8 @@ * as published by the Free Software Foundation; either version * 2 of the License, or (at your option) any later version. * - * Changes: + * Changes: Hans Schillstrom <hans.schillstrom@ericsson.com> + * Network name space (netns) aware. * */ @@ -28,9 +29,10 @@ #include <net/ip6_checksum.h> static int -udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, +udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp) { + struct net *net; struct ip_vs_service *svc; struct udphdr _udph, *uh; struct ip_vs_iphdr iph; @@ -42,13 +44,13 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, *verdict = NF_DROP; return 0; } - - svc = ip_vs_service_get(af, skb->mark, iph.protocol, + net = skb_net(skb); + svc = ip_vs_service_get(net, af, skb->mark, iph.protocol, &iph.daddr, uh->dest); if (svc) { int ignored; - if (ip_vs_todrop()) { + if (ip_vs_todrop(net_ipvs(net))) { /* * It seems that we are very loaded. * We have to drop this packet :( @@ -62,13 +64,19 @@ udp_conn_schedule(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, * Let the virtual server select a real server for the * incoming connection, and create a connection entry. */ - *cpp = ip_vs_schedule(svc, skb, pp, &ignored); - if (!*cpp && !ignored) { - *verdict = ip_vs_leave(svc, skb, pp); + *cpp = ip_vs_schedule(svc, skb, pd, &ignored); + if (!*cpp && ignored <= 0) { + if (!ignored) + *verdict = ip_vs_leave(svc, skb, pd); + else { + ip_vs_service_put(svc); + *verdict = NF_DROP; + } return 0; } ip_vs_service_put(svc); } + /* NF_ACCEPT */ return 1; } @@ -338,19 +346,6 @@ udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp) return 1; } - -/* - * Note: the caller guarantees that only one of register_app, - * unregister_app or app_conn_bind is called each time. - */ - -#define UDP_APP_TAB_BITS 4 -#define UDP_APP_TAB_SIZE (1 << UDP_APP_TAB_BITS) -#define UDP_APP_TAB_MASK (UDP_APP_TAB_SIZE - 1) - -static struct list_head udp_apps[UDP_APP_TAB_SIZE]; -static DEFINE_SPINLOCK(udp_app_lock); - static inline __u16 udp_app_hashkey(__be16 port) { return (((__force u16)port >> UDP_APP_TAB_BITS) ^ (__force u16)port) @@ -358,44 +353,50 @@ static inline __u16 udp_app_hashkey(__be16 port) } -static int udp_register_app(struct ip_vs_app *inc) +static int udp_register_app(struct net *net, struct ip_vs_app *inc) { struct ip_vs_app *i; __u16 hash; __be16 port = inc->port; int ret = 0; + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP); hash = udp_app_hashkey(port); - spin_lock_bh(&udp_app_lock); - list_for_each_entry(i, &udp_apps[hash], p_list) { + spin_lock_bh(&ipvs->udp_app_lock); + list_for_each_entry(i, &ipvs->udp_apps[hash], p_list) { if (i->port == port) { ret = -EEXIST; goto out; } } - list_add(&inc->p_list, &udp_apps[hash]); - atomic_inc(&ip_vs_protocol_udp.appcnt); + list_add(&inc->p_list, &ipvs->udp_apps[hash]); + atomic_inc(&pd->appcnt); out: - spin_unlock_bh(&udp_app_lock); + spin_unlock_bh(&ipvs->udp_app_lock); return ret; } static void -udp_unregister_app(struct ip_vs_app *inc) +udp_unregister_app(struct net *net, struct ip_vs_app *inc) { - spin_lock_bh(&udp_app_lock); - atomic_dec(&ip_vs_protocol_udp.appcnt); + struct ip_vs_proto_data *pd = ip_vs_proto_data_get(net, IPPROTO_UDP); + struct netns_ipvs *ipvs = net_ipvs(net); + + spin_lock_bh(&ipvs->udp_app_lock); + atomic_dec(&pd->appcnt); list_del(&inc->p_list); - spin_unlock_bh(&udp_app_lock); + spin_unlock_bh(&ipvs->udp_app_lock); } static int udp_app_conn_bind(struct ip_vs_conn *cp) { + struct netns_ipvs *ipvs = net_ipvs(ip_vs_conn_net(cp)); int hash; struct ip_vs_app *inc; int result = 0; @@ -407,12 +408,12 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp) /* Lookup application incarnations and bind the right one */ hash = udp_app_hashkey(cp->vport); - spin_lock(&udp_app_lock); - list_for_each_entry(inc, &udp_apps[hash], p_list) { + spin_lock(&ipvs->udp_app_lock); + list_for_each_entry(inc, &ipvs->udp_apps[hash], p_list) { if (inc->port == cp->vport) { if (unlikely(!ip_vs_app_inc_get(inc))) break; - spin_unlock(&udp_app_lock); + spin_unlock(&ipvs->udp_app_lock); IP_VS_DBG_BUF(9, "%s(): Binding conn %s:%u->" "%s:%u to app %s on port %u\n", @@ -429,14 +430,14 @@ static int udp_app_conn_bind(struct ip_vs_conn *cp) goto out; } } - spin_unlock(&udp_app_lock); + spin_unlock(&ipvs->udp_app_lock); out: return result; } -static int udp_timeouts[IP_VS_UDP_S_LAST+1] = { +static const int udp_timeouts[IP_VS_UDP_S_LAST+1] = { [IP_VS_UDP_S_NORMAL] = 5*60*HZ, [IP_VS_UDP_S_LAST] = 2*HZ, }; @@ -446,14 +447,6 @@ static const char *const udp_state_name_table[IP_VS_UDP_S_LAST+1] = { [IP_VS_UDP_S_LAST] = "BUG!", }; - -static int -udp_set_state_timeout(struct ip_vs_protocol *pp, char *sname, int to) -{ - return ip_vs_set_state_timeout(pp->timeout_table, IP_VS_UDP_S_LAST, - udp_state_name_table, sname, to); -} - static const char * udp_state_name(int state) { if (state >= IP_VS_UDP_S_LAST) @@ -464,20 +457,30 @@ static const char * udp_state_name(int state) static int udp_state_transition(struct ip_vs_conn *cp, int direction, const struct sk_buff *skb, - struct ip_vs_protocol *pp) + struct ip_vs_proto_data *pd) { - cp->timeout = pp->timeout_table[IP_VS_UDP_S_NORMAL]; + if (unlikely(!pd)) { + pr_err("UDP no ns data\n"); + return 0; + } + + cp->timeout = pd->timeout_table[IP_VS_UDP_S_NORMAL]; return 1; } -static void udp_init(struct ip_vs_protocol *pp) +static void __udp_init(struct net *net, struct ip_vs_proto_data *pd) { - IP_VS_INIT_HASH_TABLE(udp_apps); - pp->timeout_table = udp_timeouts; + struct netns_ipvs *ipvs = net_ipvs(net); + + ip_vs_init_hash_table(ipvs->udp_apps, UDP_APP_TAB_SIZE); + spin_lock_init(&ipvs->udp_app_lock); + pd->timeout_table = ip_vs_create_timeout_table((int *)udp_timeouts, + sizeof(udp_timeouts)); } -static void udp_exit(struct ip_vs_protocol *pp) +static void __udp_exit(struct net *net, struct ip_vs_proto_data *pd) { + kfree(pd->timeout_table); } @@ -486,8 +489,10 @@ struct ip_vs_protocol ip_vs_protocol_udp = { .protocol = IPPROTO_UDP, .num_states = IP_VS_UDP_S_LAST, .dont_defrag = 0, - .init = udp_init, - .exit = udp_exit, + .init = NULL, + .exit = NULL, + .init_netns = __udp_init, + .exit_netns = __udp_exit, .conn_schedule = udp_conn_schedule, .conn_in_get = ip_vs_conn_in_get_proto, .conn_out_get = ip_vs_conn_out_get_proto, @@ -501,5 +506,4 @@ struct ip_vs_protocol ip_vs_protocol_udp = { .app_conn_bind = udp_app_conn_bind, .debug_packet = ip_vs_tcpudp_debug_packet, .timeout_change = NULL, - .set_state_timeout = udp_set_state_timeout, }; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index ab85aed..d5a6e64 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -5,6 +5,18 @@ * high-performance and highly available server based on a * cluster of servers. * + * Version 1, is capable of handling both version 0 and 1 messages. + * Version 0 is the plain old format. + * Note Version 0 receivers will just drop Ver 1 messages. + * Version 1 is capable of handle IPv6, Persistence data, + * time-outs, and firewall marks. + * In ver.1 "ip_vs_sync_conn_options" will be sent in netw. order. + * Ver. 0 can be turned on by sysctl -w net.ipv4.vs.sync_version=0 + * + * Definitions Message: is a complete datagram + * Sync_conn: is a part of a Message + * Param Data is an option to a Sync_conn. + * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * * ip_vs_sync: sync connection info from master load balancer to backups @@ -15,6 +27,8 @@ * Alexandre Cassen : Added SyncID support for incoming sync * messages filtering. * Justin Ossevoort : Fix endian problem on sync message size. + * Hans Schillstrom : Added Version 1: i.e. IPv6, + * Persistence support, fwmark and time-out. */ #define KMSG_COMPONENT "IPVS" @@ -35,6 +49,8 @@ #include <linux/wait.h> #include <linux/kernel.h> +#include <asm/unaligned.h> /* Used for ntoh_seq and hton_seq */ + #include <net/ip.h> #include <net/sock.h> @@ -43,11 +59,13 @@ #define IP_VS_SYNC_GROUP 0xe0000051 /* multicast addr - 224.0.0.81 */ #define IP_VS_SYNC_PORT 8848 /* multicast port */ +#define SYNC_PROTO_VER 1 /* Protocol version in header */ /* * IPVS sync connection entry + * Version 0, i.e. original version. */ -struct ip_vs_sync_conn { +struct ip_vs_sync_conn_v0 { __u8 reserved; /* Protocol, addresses and port numbers */ @@ -71,41 +89,159 @@ struct ip_vs_sync_conn_options { struct ip_vs_seq out_seq; /* outgoing seq. struct */ }; +/* + Sync Connection format (sync_conn) + + 0 1 2 3 + 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Type | Protocol | Ver. | Size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Flags | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | State | cport | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | vport | dport | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | fwmark | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | timeout (in sec.) | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | ... | + | IP-Addresses (v4 or v6) | + | ... | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + Optional Parameters. + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Param. Type | Param. Length | Param. data | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | + | ... | + | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | | Param Type | Param. Length | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Param data | + | Last Param data should be padded for 32 bit alignment | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ +*/ + +/* + * Type 0, IPv4 sync connection format + */ +struct ip_vs_sync_v4 { + __u8 type; + __u8 protocol; /* Which protocol (TCP/UDP) */ + __be16 ver_size; /* Version msb 4 bits */ + /* Flags and state transition */ + __be32 flags; /* status flags */ + __be16 state; /* state info */ + /* Protocol, addresses and port numbers */ + __be16 cport; + __be16 vport; + __be16 dport; + __be32 fwmark; /* Firewall mark from skb */ + __be32 timeout; /* cp timeout */ + __be32 caddr; /* client address */ + __be32 vaddr; /* virtual address */ + __be32 daddr; /* destination address */ + /* The sequence options start here */ + /* PE data padded to 32bit alignment after seq. options */ +}; +/* + * Type 2 messages IPv6 + */ +struct ip_vs_sync_v6 { + __u8 type; + __u8 protocol; /* Which protocol (TCP/UDP) */ + __be16 ver_size; /* Version msb 4 bits */ + /* Flags and state transition */ + __be32 flags; /* status flags */ + __be16 state; /* state info */ + /* Protocol, addresses and port numbers */ + __be16 cport; + __be16 vport; + __be16 dport; + __be32 fwmark; /* Firewall mark from skb */ + __be32 timeout; /* cp timeout */ + struct in6_addr caddr; /* client address */ + struct in6_addr vaddr; /* virtual address */ + struct in6_addr daddr; /* destination address */ + /* The sequence options start here */ + /* PE data padded to 32bit alignment after seq. options */ +}; + +union ip_vs_sync_conn { + struct ip_vs_sync_v4 v4; + struct ip_vs_sync_v6 v6; +}; + +/* Bits in Type field in above */ +#define STYPE_INET6 0 +#define STYPE_F_INET6 (1 << STYPE_INET6) + +#define SVER_SHIFT 12 /* Shift to get version */ +#define SVER_MASK 0x0fff /* Mask to strip version */ + +#define IPVS_OPT_SEQ_DATA 1 +#define IPVS_OPT_PE_DATA 2 +#define IPVS_OPT_PE_NAME 3 +#define IPVS_OPT_PARAM 7 + +#define IPVS_OPT_F_SEQ_DATA (1 << (IPVS_OPT_SEQ_DATA-1)) +#define IPVS_OPT_F_PE_DATA (1 << (IPVS_OPT_PE_DATA-1)) +#define IPVS_OPT_F_PE_NAME (1 << (IPVS_OPT_PE_NAME-1)) +#define IPVS_OPT_F_PARAM (1 << (IPVS_OPT_PARAM-1)) + struct ip_vs_sync_thread_data { + struct net *net; struct socket *sock; char *buf; }; -#define SIMPLE_CONN_SIZE (sizeof(struct ip_vs_sync_conn)) +/* Version 0 definition of packet sizes */ +#define SIMPLE_CONN_SIZE (sizeof(struct ip_vs_sync_conn_v0)) #define FULL_CONN_SIZE \ -(sizeof(struct ip_vs_sync_conn) + sizeof(struct ip_vs_sync_conn_options)) +(sizeof(struct ip_vs_sync_conn_v0) + sizeof(struct ip_vs_sync_conn_options)) /* - The master mulitcasts messages to the backup load balancers in the - following format. + The master mulitcasts messages (Datagrams) to the backup load balancers + in the following format. + + Version 1: + Note, first byte should be Zero, so ver 0 receivers will drop the packet. 0 1 2 3 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ - | Count Conns | SyncID | Size | + | 0 | SyncID | Size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Count Conns | Version | Reserved, set to Zero | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | | IPVS Sync Connection (1) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | . | - | . | + ~ . ~ | . | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ | | | IPVS Sync Connection (n) | +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + + Version 0 Header + 0 1 2 3 + 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | Count Conns | SyncID | Size | + +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ + | IPVS Sync Connection (1) | */ #define SYNC_MESG_HEADER_LEN 4 #define MAX_CONNS_PER_SYNCBUFF 255 /* nr_conns in ip_vs_sync_mesg is 8 bit */ -struct ip_vs_sync_mesg { +/* Version 0 header */ +struct ip_vs_sync_mesg_v0 { __u8 nr_conns; __u8 syncid; __u16 size; @@ -113,9 +249,16 @@ struct ip_vs_sync_mesg { /* ip_vs_sync_conn entries start here */ }; -/* the maximum length of sync (sending/receiving) message */ -static int sync_send_mesg_maxlen; -static int sync_recv_mesg_maxlen; +/* Version 1 header */ +struct ip_vs_sync_mesg { + __u8 reserved; /* must be zero */ + __u8 syncid; + __u16 size; + __u8 nr_conns; + __s8 version; /* SYNC_PROTO_VER */ + __u16 spare; + /* ip_vs_sync_conn entries start here */ +}; struct ip_vs_sync_buff { struct list_head list; @@ -127,28 +270,6 @@ struct ip_vs_sync_buff { unsigned char *end; }; - -/* the sync_buff list head and the lock */ -static LIST_HEAD(ip_vs_sync_queue); -static DEFINE_SPINLOCK(ip_vs_sync_lock); - -/* current sync_buff for accepting new conn entries */ -static struct ip_vs_sync_buff *curr_sb = NULL; -static DEFINE_SPINLOCK(curr_sb_lock); - -/* ipvs sync daemon state */ -volatile int ip_vs_sync_state = IP_VS_STATE_NONE; -volatile int ip_vs_master_syncid = 0; -volatile int ip_vs_backup_syncid = 0; - -/* multicast interface name */ -char ip_vs_master_mcast_ifn[IP_VS_IFNAME_MAXLEN]; -char ip_vs_backup_mcast_ifn[IP_VS_IFNAME_MAXLEN]; - -/* sync daemon tasks */ -static struct task_struct *sync_master_thread; -static struct task_struct *sync_backup_thread; - /* multicast addr */ static struct sockaddr_in mcast_addr = { .sin_family = AF_INET, @@ -156,41 +277,71 @@ static struct sockaddr_in mcast_addr = { .sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP), }; +/* + * Copy of struct ip_vs_seq + * From unaligned network order to aligned host order + */ +static void ntoh_seq(struct ip_vs_seq *no, struct ip_vs_seq *ho) +{ + ho->init_seq = get_unaligned_be32(&no->init_seq); + ho->delta = get_unaligned_be32(&no->delta); + ho->previous_delta = get_unaligned_be32(&no->previous_delta); +} + +/* + * Copy of struct ip_vs_seq + * From Aligned host order to unaligned network order + */ +static void hton_seq(struct ip_vs_seq *ho, struct ip_vs_seq *no) +{ + put_unaligned_be32(ho->init_seq, &no->init_seq); + put_unaligned_be32(ho->delta, &no->delta); + put_unaligned_be32(ho->previous_delta, &no->previous_delta); +} -static inline struct ip_vs_sync_buff *sb_dequeue(void) +static inline struct ip_vs_sync_buff *sb_dequeue(struct netns_ipvs *ipvs) { struct ip_vs_sync_buff *sb; - spin_lock_bh(&ip_vs_sync_lock); - if (list_empty(&ip_vs_sync_queue)) { + spin_lock_bh(&ipvs->sync_lock); + if (list_empty(&ipvs->sync_queue)) { sb = NULL; } else { - sb = list_entry(ip_vs_sync_queue.next, + sb = list_entry(ipvs->sync_queue.next, struct ip_vs_sync_buff, list); list_del(&sb->list); } - spin_unlock_bh(&ip_vs_sync_lock); + spin_unlock_bh(&ipvs->sync_lock); return sb; } -static inline struct ip_vs_sync_buff * ip_vs_sync_buff_create(void) +/* + * Create a new sync buffer for Version 1 proto. + */ +static inline struct ip_vs_sync_buff * +ip_vs_sync_buff_create(struct netns_ipvs *ipvs) { struct ip_vs_sync_buff *sb; if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC))) return NULL; - if (!(sb->mesg=kmalloc(sync_send_mesg_maxlen, GFP_ATOMIC))) { + sb->mesg = kmalloc(ipvs->send_mesg_maxlen, GFP_ATOMIC); + if (!sb->mesg) { kfree(sb); return NULL; } + sb->mesg->reserved = 0; /* old nr_conns i.e. must be zeo now */ + sb->mesg->version = SYNC_PROTO_VER; + sb->mesg->syncid = ipvs->master_syncid; + sb->mesg->size = sizeof(struct ip_vs_sync_mesg); sb->mesg->nr_conns = 0; - sb->mesg->syncid = ip_vs_master_syncid; - sb->mesg->size = 4; - sb->head = (unsigned char *)sb->mesg + 4; - sb->end = (unsigned char *)sb->mesg + sync_send_mesg_maxlen; + sb->mesg->spare = 0; + sb->head = (unsigned char *)sb->mesg + sizeof(struct ip_vs_sync_mesg); + sb->end = (unsigned char *)sb->mesg + ipvs->send_mesg_maxlen; + sb->firstuse = jiffies; return sb; } @@ -201,14 +352,16 @@ static inline void ip_vs_sync_buff_release(struct ip_vs_sync_buff *sb) kfree(sb); } -static inline void sb_queue_tail(struct ip_vs_sync_buff *sb) +static inline void sb_queue_tail(struct netns_ipvs *ipvs) { - spin_lock(&ip_vs_sync_lock); - if (ip_vs_sync_state & IP_VS_STATE_MASTER) - list_add_tail(&sb->list, &ip_vs_sync_queue); + struct ip_vs_sync_buff *sb = ipvs->sync_buff; + + spin_lock(&ipvs->sync_lock); + if (ipvs->sync_state & IP_VS_STATE_MASTER) + list_add_tail(&sb->list, &ipvs->sync_queue); else ip_vs_sync_buff_release(sb); - spin_unlock(&ip_vs_sync_lock); + spin_unlock(&ipvs->sync_lock); } /* @@ -216,36 +369,101 @@ static inline void sb_queue_tail(struct ip_vs_sync_buff *sb) * than the specified time or the specified time is zero. */ static inline struct ip_vs_sync_buff * -get_curr_sync_buff(unsigned long time) +get_curr_sync_buff(struct netns_ipvs *ipvs, unsigned long time) { struct ip_vs_sync_buff *sb; - spin_lock_bh(&curr_sb_lock); - if (curr_sb && (time == 0 || - time_before(jiffies - curr_sb->firstuse, time))) { - sb = curr_sb; - curr_sb = NULL; + spin_lock_bh(&ipvs->sync_buff_lock); + if (ipvs->sync_buff && (time == 0 || + time_before(jiffies - ipvs->sync_buff->firstuse, time))) { + sb = ipvs->sync_buff; + ipvs->sync_buff = NULL; } else sb = NULL; - spin_unlock_bh(&curr_sb_lock); + spin_unlock_bh(&ipvs->sync_buff_lock); return sb; } +/* + * Switch mode from sending version 0 or 1 + * - must handle sync_buf + */ +void ip_vs_sync_switch_mode(struct net *net, int mode) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + if (!ipvs->sync_state & IP_VS_STATE_MASTER) + return; + if (mode == ipvs->sysctl_sync_ver || !ipvs->sync_buff) + return; + + spin_lock_bh(&ipvs->sync_buff_lock); + /* Buffer empty ? then let buf_create do the job */ + if (ipvs->sync_buff->mesg->size <= sizeof(struct ip_vs_sync_mesg)) { + kfree(ipvs->sync_buff); + ipvs->sync_buff = NULL; + } else { + spin_lock_bh(&ipvs->sync_lock); + if (ipvs->sync_state & IP_VS_STATE_MASTER) + list_add_tail(&ipvs->sync_buff->list, + &ipvs->sync_queue); + else + ip_vs_sync_buff_release(ipvs->sync_buff); + spin_unlock_bh(&ipvs->sync_lock); + } + spin_unlock_bh(&ipvs->sync_buff_lock); +} /* + * Create a new sync buffer for Version 0 proto. + */ +static inline struct ip_vs_sync_buff * +ip_vs_sync_buff_create_v0(struct netns_ipvs *ipvs) +{ + struct ip_vs_sync_buff *sb; + struct ip_vs_sync_mesg_v0 *mesg; + + if (!(sb=kmalloc(sizeof(struct ip_vs_sync_buff), GFP_ATOMIC))) + return NULL; + + sb->mesg = kmalloc(ipvs->send_mesg_maxlen, GFP_ATOMIC); + if (!sb->mesg) { + kfree(sb); + return NULL; + } + mesg = (struct ip_vs_sync_mesg_v0 *)sb->mesg; + mesg->nr_conns = 0; + mesg->syncid = ipvs->master_syncid; + mesg->size = sizeof(struct ip_vs_sync_mesg_v0); + sb->head = (unsigned char *)mesg + sizeof(struct ip_vs_sync_mesg_v0); + sb->end = (unsigned char *)mesg + ipvs->send_mesg_maxlen; + sb->firstuse = jiffies; + return sb; +} + +/* + * Version 0 , could be switched in by sys_ctl. * Add an ip_vs_conn information into the current sync_buff. - * Called by ip_vs_in. */ -void ip_vs_sync_conn(struct ip_vs_conn *cp) +void ip_vs_sync_conn_v0(struct net *net, struct ip_vs_conn *cp) { - struct ip_vs_sync_mesg *m; - struct ip_vs_sync_conn *s; + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_sync_mesg_v0 *m; + struct ip_vs_sync_conn_v0 *s; int len; - spin_lock(&curr_sb_lock); - if (!curr_sb) { - if (!(curr_sb=ip_vs_sync_buff_create())) { - spin_unlock(&curr_sb_lock); + if (unlikely(cp->af != AF_INET)) + return; + /* Do not sync ONE PACKET */ + if (cp->flags & IP_VS_CONN_F_ONE_PACKET) + return; + + spin_lock(&ipvs->sync_buff_lock); + if (!ipvs->sync_buff) { + ipvs->sync_buff = + ip_vs_sync_buff_create_v0(ipvs); + if (!ipvs->sync_buff) { + spin_unlock(&ipvs->sync_buff_lock); pr_err("ip_vs_sync_buff_create failed.\n"); return; } @@ -253,10 +471,11 @@ void ip_vs_sync_conn(struct ip_vs_conn *cp) len = (cp->flags & IP_VS_CONN_F_SEQ_MASK) ? FULL_CONN_SIZE : SIMPLE_CONN_SIZE; - m = curr_sb->mesg; - s = (struct ip_vs_sync_conn *)curr_sb->head; + m = (struct ip_vs_sync_mesg_v0 *)ipvs->sync_buff->mesg; + s = (struct ip_vs_sync_conn_v0 *)ipvs->sync_buff->head; /* copy members */ + s->reserved = 0; s->protocol = cp->protocol; s->cport = cp->cport; s->vport = cp->vport; @@ -274,83 +493,366 @@ void ip_vs_sync_conn(struct ip_vs_conn *cp) m->nr_conns++; m->size += len; - curr_sb->head += len; + ipvs->sync_buff->head += len; /* check if there is a space for next one */ - if (curr_sb->head+FULL_CONN_SIZE > curr_sb->end) { - sb_queue_tail(curr_sb); - curr_sb = NULL; + if (ipvs->sync_buff->head + FULL_CONN_SIZE > ipvs->sync_buff->end) { + sb_queue_tail(ipvs); + ipvs->sync_buff = NULL; } - spin_unlock(&curr_sb_lock); + spin_unlock(&ipvs->sync_buff_lock); /* synchronize its controller if it has */ if (cp->control) - ip_vs_sync_conn(cp->control); + ip_vs_sync_conn(net, cp->control); +} + +/* + * Add an ip_vs_conn information into the current sync_buff. + * Called by ip_vs_in. + * Sending Version 1 messages + */ +void ip_vs_sync_conn(struct net *net, struct ip_vs_conn *cp) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_sync_mesg *m; + union ip_vs_sync_conn *s; + __u8 *p; + unsigned int len, pe_name_len, pad; + + /* Handle old version of the protocol */ + if (ipvs->sysctl_sync_ver == 0) { + ip_vs_sync_conn_v0(net, cp); + return; + } + /* Do not sync ONE PACKET */ + if (cp->flags & IP_VS_CONN_F_ONE_PACKET) + goto control; +sloop: + /* Sanity checks */ + pe_name_len = 0; + if (cp->pe_data_len) { + if (!cp->pe_data || !cp->dest) { + IP_VS_ERR_RL("SYNC, connection pe_data invalid\n"); + return; + } + pe_name_len = strnlen(cp->pe->name, IP_VS_PENAME_MAXLEN); + } + + spin_lock(&ipvs->sync_buff_lock); + +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) + len = sizeof(struct ip_vs_sync_v6); + else +#endif + len = sizeof(struct ip_vs_sync_v4); + + if (cp->flags & IP_VS_CONN_F_SEQ_MASK) + len += sizeof(struct ip_vs_sync_conn_options) + 2; + + if (cp->pe_data_len) + len += cp->pe_data_len + 2; /* + Param hdr field */ + if (pe_name_len) + len += pe_name_len + 2; + + /* check if there is a space for this one */ + pad = 0; + if (ipvs->sync_buff) { + pad = (4 - (size_t)ipvs->sync_buff->head) & 3; + if (ipvs->sync_buff->head + len + pad > ipvs->sync_buff->end) { + sb_queue_tail(ipvs); + ipvs->sync_buff = NULL; + pad = 0; + } + } + + if (!ipvs->sync_buff) { + ipvs->sync_buff = ip_vs_sync_buff_create(ipvs); + if (!ipvs->sync_buff) { + spin_unlock(&ipvs->sync_buff_lock); + pr_err("ip_vs_sync_buff_create failed.\n"); + return; + } + } + + m = ipvs->sync_buff->mesg; + p = ipvs->sync_buff->head; + ipvs->sync_buff->head += pad + len; + m->size += pad + len; + /* Add ev. padding from prev. sync_conn */ + while (pad--) + *(p++) = 0; + + s = (union ip_vs_sync_conn *)p; + + /* Set message type & copy members */ + s->v4.type = (cp->af == AF_INET6 ? STYPE_F_INET6 : 0); + s->v4.ver_size = htons(len & SVER_MASK); /* Version 0 */ + s->v4.flags = htonl(cp->flags & ~IP_VS_CONN_F_HASHED); + s->v4.state = htons(cp->state); + s->v4.protocol = cp->protocol; + s->v4.cport = cp->cport; + s->v4.vport = cp->vport; + s->v4.dport = cp->dport; + s->v4.fwmark = htonl(cp->fwmark); + s->v4.timeout = htonl(cp->timeout / HZ); + m->nr_conns++; + +#ifdef CONFIG_IP_VS_IPV6 + if (cp->af == AF_INET6) { + p += sizeof(struct ip_vs_sync_v6); + ipv6_addr_copy(&s->v6.caddr, &cp->caddr.in6); + ipv6_addr_copy(&s->v6.vaddr, &cp->vaddr.in6); + ipv6_addr_copy(&s->v6.daddr, &cp->daddr.in6); + } else +#endif + { + p += sizeof(struct ip_vs_sync_v4); /* options ptr */ + s->v4.caddr = cp->caddr.ip; + s->v4.vaddr = cp->vaddr.ip; + s->v4.daddr = cp->daddr.ip; + } + if (cp->flags & IP_VS_CONN_F_SEQ_MASK) { + *(p++) = IPVS_OPT_SEQ_DATA; + *(p++) = sizeof(struct ip_vs_sync_conn_options); + hton_seq((struct ip_vs_seq *)p, &cp->in_seq); + p += sizeof(struct ip_vs_seq); + hton_seq((struct ip_vs_seq *)p, &cp->out_seq); + p += sizeof(struct ip_vs_seq); + } + /* Handle pe data */ + if (cp->pe_data_len && cp->pe_data) { + *(p++) = IPVS_OPT_PE_DATA; + *(p++) = cp->pe_data_len; + memcpy(p, cp->pe_data, cp->pe_data_len); + p += cp->pe_data_len; + if (pe_name_len) { + /* Add PE_NAME */ + *(p++) = IPVS_OPT_PE_NAME; + *(p++) = pe_name_len; + memcpy(p, cp->pe->name, pe_name_len); + p += pe_name_len; + } + } + + spin_unlock(&ipvs->sync_buff_lock); + +control: + /* synchronize its controller if it has */ + cp = cp->control; + if (!cp) + return; + /* + * Reduce sync rate for templates + * i.e only increment in_pkts for Templates. + */ + if (cp->flags & IP_VS_CONN_F_TEMPLATE) { + int pkts = atomic_add_return(1, &cp->in_pkts); + + if (pkts % ipvs->sysctl_sync_threshold[1] != 1) + return; + } + goto sloop; } +/* + * fill_param used by version 1 + */ static inline int -ip_vs_conn_fill_param_sync(int af, int protocol, - const union nf_inet_addr *caddr, __be16 cport, - const union nf_inet_addr *vaddr, __be16 vport, - struct ip_vs_conn_param *p) +ip_vs_conn_fill_param_sync(struct net *net, int af, union ip_vs_sync_conn *sc, + struct ip_vs_conn_param *p, + __u8 *pe_data, unsigned int pe_data_len, + __u8 *pe_name, unsigned int pe_name_len) { - /* XXX: Need to take into account persistence engine */ - ip_vs_conn_fill_param(af, protocol, caddr, cport, vaddr, vport, p); +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + ip_vs_conn_fill_param(net, af, sc->v6.protocol, + (const union nf_inet_addr *)&sc->v6.caddr, + sc->v6.cport, + (const union nf_inet_addr *)&sc->v6.vaddr, + sc->v6.vport, p); + else +#endif + ip_vs_conn_fill_param(net, af, sc->v4.protocol, + (const union nf_inet_addr *)&sc->v4.caddr, + sc->v4.cport, + (const union nf_inet_addr *)&sc->v4.vaddr, + sc->v4.vport, p); + /* Handle pe data */ + if (pe_data_len) { + if (pe_name_len) { + char buff[IP_VS_PENAME_MAXLEN+1]; + + memcpy(buff, pe_name, pe_name_len); + buff[pe_name_len]=0; + p->pe = __ip_vs_pe_getbyname(buff); + if (!p->pe) { + IP_VS_DBG(3, "BACKUP, no %s engine found/loaded\n", + buff); + return 1; + } + } else { + IP_VS_ERR_RL("BACKUP, Invalid PE parameters\n"); + return 1; + } + + p->pe_data = kmalloc(pe_data_len, GFP_ATOMIC); + if (!p->pe_data) { + if (p->pe->module) + module_put(p->pe->module); + return -ENOMEM; + } + memcpy(p->pe_data, pe_data, pe_data_len); + p->pe_data_len = pe_data_len; + } return 0; } /* - * Process received multicast message and create the corresponding - * ip_vs_conn entries. + * Connection Add / Update. + * Common for version 0 and 1 reception of backup sync_conns. + * Param: ... + * timeout is in sec. */ -static void ip_vs_process_message(const char *buffer, const size_t buflen) +static void ip_vs_proc_conn(struct net *net, struct ip_vs_conn_param *param, + unsigned int flags, unsigned int state, + unsigned int protocol, unsigned int type, + const union nf_inet_addr *daddr, __be16 dport, + unsigned long timeout, __u32 fwmark, + struct ip_vs_sync_conn_options *opt) { - struct ip_vs_sync_mesg *m = (struct ip_vs_sync_mesg *)buffer; - struct ip_vs_sync_conn *s; - struct ip_vs_sync_conn_options *opt; - struct ip_vs_conn *cp; - struct ip_vs_protocol *pp; struct ip_vs_dest *dest; - struct ip_vs_conn_param param; - char *p; - int i; + struct ip_vs_conn *cp; + struct netns_ipvs *ipvs = net_ipvs(net); - if (buflen < sizeof(struct ip_vs_sync_mesg)) { - IP_VS_ERR_RL("sync message header too short\n"); - return; - } + if (!(flags & IP_VS_CONN_F_TEMPLATE)) + cp = ip_vs_conn_in_get(param); + else + cp = ip_vs_ct_in_get(param); - /* Convert size back to host byte order */ - m->size = ntohs(m->size); + if (cp && param->pe_data) /* Free pe_data */ + kfree(param->pe_data); + if (!cp) { + /* + * Find the appropriate destination for the connection. + * If it is not found the connection will remain unbound + * but still handled. + */ + dest = ip_vs_find_dest(net, type, daddr, dport, param->vaddr, + param->vport, protocol, fwmark); - if (buflen != m->size) { - IP_VS_ERR_RL("bogus sync message size\n"); - return; + /* Set the approprite ativity flag */ + if (protocol == IPPROTO_TCP) { + if (state != IP_VS_TCP_S_ESTABLISHED) + flags |= IP_VS_CONN_F_INACTIVE; + else + flags &= ~IP_VS_CONN_F_INACTIVE; + } else if (protocol == IPPROTO_SCTP) { + if (state != IP_VS_SCTP_S_ESTABLISHED) + flags |= IP_VS_CONN_F_INACTIVE; + else + flags &= ~IP_VS_CONN_F_INACTIVE; + } + cp = ip_vs_conn_new(param, daddr, dport, flags, dest, fwmark); + if (dest) + atomic_dec(&dest->refcnt); + if (!cp) { + if (param->pe_data) + kfree(param->pe_data); + IP_VS_DBG(2, "BACKUP, add new conn. failed\n"); + return; + } + } else if (!cp->dest) { + dest = ip_vs_try_bind_dest(cp); + if (dest) + atomic_dec(&dest->refcnt); + } else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) && + (cp->state != state)) { + /* update active/inactive flag for the connection */ + dest = cp->dest; + if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && + (state != IP_VS_TCP_S_ESTABLISHED)) { + atomic_dec(&dest->activeconns); + atomic_inc(&dest->inactconns); + cp->flags |= IP_VS_CONN_F_INACTIVE; + } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && + (state == IP_VS_TCP_S_ESTABLISHED)) { + atomic_inc(&dest->activeconns); + atomic_dec(&dest->inactconns); + cp->flags &= ~IP_VS_CONN_F_INACTIVE; + } + } else if ((cp->dest) && (cp->protocol == IPPROTO_SCTP) && + (cp->state != state)) { + dest = cp->dest; + if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && + (state != IP_VS_SCTP_S_ESTABLISHED)) { + atomic_dec(&dest->activeconns); + atomic_inc(&dest->inactconns); + cp->flags &= ~IP_VS_CONN_F_INACTIVE; + } } - /* SyncID sanity check */ - if (ip_vs_backup_syncid != 0 && m->syncid != ip_vs_backup_syncid) { - IP_VS_DBG(7, "Ignoring incoming msg with syncid = %d\n", - m->syncid); - return; + if (opt) + memcpy(&cp->in_seq, opt, sizeof(*opt)); + atomic_set(&cp->in_pkts, ipvs->sysctl_sync_threshold[0]); + cp->state = state; + cp->old_state = cp->state; + /* + * For Ver 0 messages style + * - Not possible to recover the right timeout for templates + * - can not find the right fwmark + * virtual service. If needed, we can do it for + * non-fwmark persistent services. + * Ver 1 messages style. + * - No problem. + */ + if (timeout) { + if (timeout > MAX_SCHEDULE_TIMEOUT / HZ) + timeout = MAX_SCHEDULE_TIMEOUT / HZ; + cp->timeout = timeout*HZ; + } else { + struct ip_vs_proto_data *pd; + + pd = ip_vs_proto_data_get(net, protocol); + if (!(flags & IP_VS_CONN_F_TEMPLATE) && pd && pd->timeout_table) + cp->timeout = pd->timeout_table[state]; + else + cp->timeout = (3*60*HZ); } + ip_vs_conn_put(cp); +} - p = (char *)buffer + sizeof(struct ip_vs_sync_mesg); +/* + * Process received multicast message for Version 0 + */ +static void ip_vs_process_message_v0(struct net *net, const char *buffer, + const size_t buflen) +{ + struct ip_vs_sync_mesg_v0 *m = (struct ip_vs_sync_mesg_v0 *)buffer; + struct ip_vs_sync_conn_v0 *s; + struct ip_vs_sync_conn_options *opt; + struct ip_vs_protocol *pp; + struct ip_vs_conn_param param; + char *p; + int i; + + p = (char *)buffer + sizeof(struct ip_vs_sync_mesg_v0); for (i=0; i<m->nr_conns; i++) { unsigned flags, state; if (p + SIMPLE_CONN_SIZE > buffer+buflen) { - IP_VS_ERR_RL("bogus conn in sync message\n"); + IP_VS_ERR_RL("BACKUP v0, bogus conn\n"); return; } - s = (struct ip_vs_sync_conn *) p; + s = (struct ip_vs_sync_conn_v0 *) p; flags = ntohs(s->flags) | IP_VS_CONN_F_SYNC; flags &= ~IP_VS_CONN_F_HASHED; if (flags & IP_VS_CONN_F_SEQ_MASK) { opt = (struct ip_vs_sync_conn_options *)&s[1]; p += FULL_CONN_SIZE; if (p > buffer+buflen) { - IP_VS_ERR_RL("bogus conn options in sync message\n"); + IP_VS_ERR_RL("BACKUP v0, Dropping buffer bogus conn options\n"); return; } } else { @@ -362,118 +864,286 @@ static void ip_vs_process_message(const char *buffer, const size_t buflen) if (!(flags & IP_VS_CONN_F_TEMPLATE)) { pp = ip_vs_proto_get(s->protocol); if (!pp) { - IP_VS_ERR_RL("Unsupported protocol %u in sync msg\n", + IP_VS_DBG(2, "BACKUP v0, Unsupported protocol %u\n", s->protocol); continue; } if (state >= pp->num_states) { - IP_VS_DBG(2, "Invalid %s state %u in sync msg\n", + IP_VS_DBG(2, "BACKUP v0, Invalid %s state %u\n", pp->name, state); continue; } } else { /* protocol in templates is not used for state/timeout */ - pp = NULL; if (state > 0) { - IP_VS_DBG(2, "Invalid template state %u in sync msg\n", + IP_VS_DBG(2, "BACKUP v0, Invalid template state %u\n", state); state = 0; } } - { - if (ip_vs_conn_fill_param_sync(AF_INET, s->protocol, - (union nf_inet_addr *)&s->caddr, - s->cport, - (union nf_inet_addr *)&s->vaddr, - s->vport, ¶m)) { - pr_err("ip_vs_conn_fill_param_sync failed"); - return; + ip_vs_conn_fill_param(net, AF_INET, s->protocol, + (const union nf_inet_addr *)&s->caddr, + s->cport, + (const union nf_inet_addr *)&s->vaddr, + s->vport, ¶m); + + /* Send timeout as Zero */ + ip_vs_proc_conn(net, ¶m, flags, state, s->protocol, AF_INET, + (union nf_inet_addr *)&s->daddr, s->dport, + 0, 0, opt); + } +} + +/* + * Handle options + */ +static inline int ip_vs_proc_seqopt(__u8 *p, unsigned int plen, + __u32 *opt_flags, + struct ip_vs_sync_conn_options *opt) +{ + struct ip_vs_sync_conn_options *topt; + + topt = (struct ip_vs_sync_conn_options *)p; + + if (plen != sizeof(struct ip_vs_sync_conn_options)) { + IP_VS_DBG(2, "BACKUP, bogus conn options length\n"); + return -EINVAL; + } + if (*opt_flags & IPVS_OPT_F_SEQ_DATA) { + IP_VS_DBG(2, "BACKUP, conn options found twice\n"); + return -EINVAL; + } + ntoh_seq(&topt->in_seq, &opt->in_seq); + ntoh_seq(&topt->out_seq, &opt->out_seq); + *opt_flags |= IPVS_OPT_F_SEQ_DATA; + return 0; +} + +static int ip_vs_proc_str(__u8 *p, unsigned int plen, unsigned int *data_len, + __u8 **data, unsigned int maxlen, + __u32 *opt_flags, __u32 flag) +{ + if (plen > maxlen) { + IP_VS_DBG(2, "BACKUP, bogus par.data len > %d\n", maxlen); + return -EINVAL; + } + if (*opt_flags & flag) { + IP_VS_DBG(2, "BACKUP, Par.data found twice 0x%x\n", flag); + return -EINVAL; + } + *data_len = plen; + *data = p; + *opt_flags |= flag; + return 0; +} +/* + * Process a Version 1 sync. connection + */ +static inline int ip_vs_proc_sync_conn(struct net *net, __u8 *p, __u8 *msg_end) +{ + struct ip_vs_sync_conn_options opt; + union ip_vs_sync_conn *s; + struct ip_vs_protocol *pp; + struct ip_vs_conn_param param; + __u32 flags; + unsigned int af, state, pe_data_len=0, pe_name_len=0; + __u8 *pe_data=NULL, *pe_name=NULL; + __u32 opt_flags=0; + int retc=0; + + s = (union ip_vs_sync_conn *) p; + + if (s->v6.type & STYPE_F_INET6) { +#ifdef CONFIG_IP_VS_IPV6 + af = AF_INET6; + p += sizeof(struct ip_vs_sync_v6); +#else + IP_VS_DBG(3,"BACKUP, IPv6 msg received, and IPVS is not compiled for IPv6\n"); + retc = 10; + goto out; +#endif + } else if (!s->v4.type) { + af = AF_INET; + p += sizeof(struct ip_vs_sync_v4); + } else { + return -10; + } + if (p > msg_end) + return -20; + + /* Process optional params check Type & Len. */ + while (p < msg_end) { + int ptype; + int plen; + + if (p+2 > msg_end) + return -30; + ptype = *(p++); + plen = *(p++); + + if (!plen || ((p + plen) > msg_end)) + return -40; + /* Handle seq option p = param data */ + switch (ptype & ~IPVS_OPT_F_PARAM) { + case IPVS_OPT_SEQ_DATA: + if (ip_vs_proc_seqopt(p, plen, &opt_flags, &opt)) + return -50; + break; + + case IPVS_OPT_PE_DATA: + if (ip_vs_proc_str(p, plen, &pe_data_len, &pe_data, + IP_VS_PEDATA_MAXLEN, &opt_flags, + IPVS_OPT_F_PE_DATA)) + return -60; + break; + + case IPVS_OPT_PE_NAME: + if (ip_vs_proc_str(p, plen,&pe_name_len, &pe_name, + IP_VS_PENAME_MAXLEN, &opt_flags, + IPVS_OPT_F_PE_NAME)) + return -70; + break; + + default: + /* Param data mandatory ? */ + if (!(ptype & IPVS_OPT_F_PARAM)) { + IP_VS_DBG(3, "BACKUP, Unknown mandatory param %d found\n", + ptype & ~IPVS_OPT_F_PARAM); + retc = 20; + goto out; } - if (!(flags & IP_VS_CONN_F_TEMPLATE)) - cp = ip_vs_conn_in_get(¶m); - else - cp = ip_vs_ct_in_get(¶m); } - if (!cp) { - /* - * Find the appropriate destination for the connection. - * If it is not found the connection will remain unbound - * but still handled. - */ - dest = ip_vs_find_dest(AF_INET, - (union nf_inet_addr *)&s->daddr, - s->dport, - (union nf_inet_addr *)&s->vaddr, - s->vport, - s->protocol); - /* Set the approprite ativity flag */ - if (s->protocol == IPPROTO_TCP) { - if (state != IP_VS_TCP_S_ESTABLISHED) - flags |= IP_VS_CONN_F_INACTIVE; - else - flags &= ~IP_VS_CONN_F_INACTIVE; - } else if (s->protocol == IPPROTO_SCTP) { - if (state != IP_VS_SCTP_S_ESTABLISHED) - flags |= IP_VS_CONN_F_INACTIVE; - else - flags &= ~IP_VS_CONN_F_INACTIVE; + p += plen; /* Next option */ + } + + /* Get flags and Mask off unsupported */ + flags = ntohl(s->v4.flags) & IP_VS_CONN_F_BACKUP_MASK; + flags |= IP_VS_CONN_F_SYNC; + state = ntohs(s->v4.state); + + if (!(flags & IP_VS_CONN_F_TEMPLATE)) { + pp = ip_vs_proto_get(s->v4.protocol); + if (!pp) { + IP_VS_DBG(3,"BACKUP, Unsupported protocol %u\n", + s->v4.protocol); + retc = 30; + goto out; + } + if (state >= pp->num_states) { + IP_VS_DBG(3, "BACKUP, Invalid %s state %u\n", + pp->name, state); + retc = 40; + goto out; + } + } else { + /* protocol in templates is not used for state/timeout */ + if (state > 0) { + IP_VS_DBG(3, "BACKUP, Invalid template state %u\n", + state); + state = 0; + } + } + if (ip_vs_conn_fill_param_sync(net, af, s, ¶m, pe_data, + pe_data_len, pe_name, pe_name_len)) { + retc = 50; + goto out; + } + /* If only IPv4, just silent skip IPv6 */ + if (af == AF_INET) + ip_vs_proc_conn(net, ¶m, flags, state, s->v4.protocol, af, + (union nf_inet_addr *)&s->v4.daddr, s->v4.dport, + ntohl(s->v4.timeout), ntohl(s->v4.fwmark), + (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) + ); +#ifdef CONFIG_IP_VS_IPV6 + else + ip_vs_proc_conn(net, ¶m, flags, state, s->v6.protocol, af, + (union nf_inet_addr *)&s->v6.daddr, s->v6.dport, + ntohl(s->v6.timeout), ntohl(s->v6.fwmark), + (opt_flags & IPVS_OPT_F_SEQ_DATA ? &opt : NULL) + ); +#endif + return 0; + /* Error exit */ +out: + IP_VS_DBG(2, "BACKUP, Single msg dropped err:%d\n", retc); + return retc; + +} +/* + * Process received multicast message and create the corresponding + * ip_vs_conn entries. + * Handles Version 0 & 1 + */ +static void ip_vs_process_message(struct net *net, __u8 *buffer, + const size_t buflen) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + struct ip_vs_sync_mesg *m2 = (struct ip_vs_sync_mesg *)buffer; + __u8 *p, *msg_end; + int i, nr_conns; + + if (buflen < sizeof(struct ip_vs_sync_mesg_v0)) { + IP_VS_DBG(2, "BACKUP, message header too short\n"); + return; + } + /* Convert size back to host byte order */ + m2->size = ntohs(m2->size); + + if (buflen != m2->size) { + IP_VS_DBG(2, "BACKUP, bogus message size\n"); + return; + } + /* SyncID sanity check */ + if (ipvs->backup_syncid != 0 && m2->syncid != ipvs->backup_syncid) { + IP_VS_DBG(7, "BACKUP, Ignoring syncid = %d\n", m2->syncid); + return; + } + /* Handle version 1 message */ + if ((m2->version == SYNC_PROTO_VER) && (m2->reserved == 0) + && (m2->spare == 0)) { + + msg_end = buffer + sizeof(struct ip_vs_sync_mesg); + nr_conns = m2->nr_conns; + + for (i=0; i<nr_conns; i++) { + union ip_vs_sync_conn *s; + unsigned size; + int retc; + + p = msg_end; + if (p + sizeof(s->v4) > buffer+buflen) { + IP_VS_ERR_RL("BACKUP, Dropping buffer, to small\n"); + return; } - cp = ip_vs_conn_new(¶m, - (union nf_inet_addr *)&s->daddr, - s->dport, flags, dest); - if (dest) - atomic_dec(&dest->refcnt); - if (!cp) { - pr_err("ip_vs_conn_new failed\n"); + s = (union ip_vs_sync_conn *)p; + size = ntohs(s->v4.ver_size) & SVER_MASK; + msg_end = p + size; + /* Basic sanity checks */ + if (msg_end > buffer+buflen) { + IP_VS_ERR_RL("BACKUP, Dropping buffer, msg > buffer\n"); return; } - } else if (!cp->dest) { - dest = ip_vs_try_bind_dest(cp); - if (dest) - atomic_dec(&dest->refcnt); - } else if ((cp->dest) && (cp->protocol == IPPROTO_TCP) && - (cp->state != state)) { - /* update active/inactive flag for the connection */ - dest = cp->dest; - if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && - (state != IP_VS_TCP_S_ESTABLISHED)) { - atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); - cp->flags |= IP_VS_CONN_F_INACTIVE; - } else if ((cp->flags & IP_VS_CONN_F_INACTIVE) && - (state == IP_VS_TCP_S_ESTABLISHED)) { - atomic_inc(&dest->activeconns); - atomic_dec(&dest->inactconns); - cp->flags &= ~IP_VS_CONN_F_INACTIVE; + if (ntohs(s->v4.ver_size) >> SVER_SHIFT) { + IP_VS_ERR_RL("BACKUP, Dropping buffer, Unknown version %d\n", + ntohs(s->v4.ver_size) >> SVER_SHIFT); + return; } - } else if ((cp->dest) && (cp->protocol == IPPROTO_SCTP) && - (cp->state != state)) { - dest = cp->dest; - if (!(cp->flags & IP_VS_CONN_F_INACTIVE) && - (state != IP_VS_SCTP_S_ESTABLISHED)) { - atomic_dec(&dest->activeconns); - atomic_inc(&dest->inactconns); - cp->flags &= ~IP_VS_CONN_F_INACTIVE; + /* Process a single sync_conn */ + retc = ip_vs_proc_sync_conn(net, p, msg_end); + if (retc < 0) { + IP_VS_ERR_RL("BACKUP, Dropping buffer, Err: %d in decoding\n", + retc); + return; } + /* Make sure we have 32 bit alignment */ + msg_end = p + ((size + 3) & ~3); } - - if (opt) - memcpy(&cp->in_seq, opt, sizeof(*opt)); - atomic_set(&cp->in_pkts, sysctl_ip_vs_sync_threshold[0]); - cp->state = state; - cp->old_state = cp->state; - /* - * We can not recover the right timeout for templates - * in all cases, we can not find the right fwmark - * virtual service. If needed, we can do it for - * non-fwmark persistent services. - */ - if (!(flags & IP_VS_CONN_F_TEMPLATE) && pp->timeout_table) - cp->timeout = pp->timeout_table[state]; - else - cp->timeout = (3*60*HZ); - ip_vs_conn_put(cp); + } else { + /* Old type of message */ + ip_vs_process_message_v0(net, buffer, buflen); + return; } } @@ -511,8 +1181,10 @@ static int set_mcast_if(struct sock *sk, char *ifname) { struct net_device *dev; struct inet_sock *inet = inet_sk(sk); + struct net *net = sock_net(sk); - if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL) + dev = __dev_get_by_name(net, ifname); + if (!dev) return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) @@ -531,30 +1203,33 @@ static int set_mcast_if(struct sock *sk, char *ifname) * Set the maximum length of sync message according to the * specified interface's MTU. */ -static int set_sync_mesg_maxlen(int sync_state) +static int set_sync_mesg_maxlen(struct net *net, int sync_state) { + struct netns_ipvs *ipvs = net_ipvs(net); struct net_device *dev; int num; if (sync_state == IP_VS_STATE_MASTER) { - if ((dev = __dev_get_by_name(&init_net, ip_vs_master_mcast_ifn)) == NULL) + dev = __dev_get_by_name(net, ipvs->master_mcast_ifn); + if (!dev) return -ENODEV; num = (dev->mtu - sizeof(struct iphdr) - sizeof(struct udphdr) - SYNC_MESG_HEADER_LEN - 20) / SIMPLE_CONN_SIZE; - sync_send_mesg_maxlen = SYNC_MESG_HEADER_LEN + + ipvs->send_mesg_maxlen = SYNC_MESG_HEADER_LEN + SIMPLE_CONN_SIZE * min(num, MAX_CONNS_PER_SYNCBUFF); IP_VS_DBG(7, "setting the maximum length of sync sending " - "message %d.\n", sync_send_mesg_maxlen); + "message %d.\n", ipvs->send_mesg_maxlen); } else if (sync_state == IP_VS_STATE_BACKUP) { - if ((dev = __dev_get_by_name(&init_net, ip_vs_backup_mcast_ifn)) == NULL) + dev = __dev_get_by_name(net, ipvs->backup_mcast_ifn); + if (!dev) return -ENODEV; - sync_recv_mesg_maxlen = dev->mtu - + ipvs->recv_mesg_maxlen = dev->mtu - sizeof(struct iphdr) - sizeof(struct udphdr); IP_VS_DBG(7, "setting the maximum length of sync receiving " - "message %d.\n", sync_recv_mesg_maxlen); + "message %d.\n", ipvs->recv_mesg_maxlen); } return 0; @@ -569,6 +1244,7 @@ static int set_sync_mesg_maxlen(int sync_state) static int join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) { + struct net *net = sock_net(sk); struct ip_mreqn mreq; struct net_device *dev; int ret; @@ -576,7 +1252,8 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) memset(&mreq, 0, sizeof(mreq)); memcpy(&mreq.imr_multiaddr, addr, sizeof(struct in_addr)); - if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL) + dev = __dev_get_by_name(net, ifname); + if (!dev) return -ENODEV; if (sk->sk_bound_dev_if && dev->ifindex != sk->sk_bound_dev_if) return -EINVAL; @@ -593,11 +1270,13 @@ join_mcast_group(struct sock *sk, struct in_addr *addr, char *ifname) static int bind_mcastif_addr(struct socket *sock, char *ifname) { + struct net *net = sock_net(sock->sk); struct net_device *dev; __be32 addr; struct sockaddr_in sin; - if ((dev = __dev_get_by_name(&init_net, ifname)) == NULL) + dev = __dev_get_by_name(net, ifname); + if (!dev) return -ENODEV; addr = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE); @@ -619,19 +1298,20 @@ static int bind_mcastif_addr(struct socket *sock, char *ifname) /* * Set up sending multicast socket over UDP */ -static struct socket * make_send_sock(void) +static struct socket *make_send_sock(struct net *net) { + struct netns_ipvs *ipvs = net_ipvs(net); struct socket *sock; int result; /* First create a socket */ - result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - result = set_mcast_if(sock->sk, ip_vs_master_mcast_ifn); + result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); goto error; @@ -640,7 +1320,7 @@ static struct socket * make_send_sock(void) set_mcast_loop(sock->sk, 0); set_mcast_ttl(sock->sk, 1); - result = bind_mcastif_addr(sock, ip_vs_master_mcast_ifn); + result = bind_mcastif_addr(sock, ipvs->master_mcast_ifn); if (result < 0) { pr_err("Error binding address of the mcast interface\n"); goto error; @@ -664,13 +1344,14 @@ static struct socket * make_send_sock(void) /* * Set up receiving multicast socket over UDP */ -static struct socket * make_receive_sock(void) +static struct socket *make_receive_sock(struct net *net) { + struct netns_ipvs *ipvs = net_ipvs(net); struct socket *sock; int result; /* First create a socket */ - result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); + result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); @@ -689,7 +1370,7 @@ static struct socket * make_receive_sock(void) /* join the multicast group */ result = join_mcast_group(sock->sk, (struct in_addr *) &mcast_addr.sin_addr, - ip_vs_backup_mcast_ifn); + ipvs->backup_mcast_ifn); if (result < 0) { pr_err("Error joining to the multicast group\n"); goto error; @@ -760,20 +1441,21 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen) static int sync_thread_master(void *data) { struct ip_vs_sync_thread_data *tinfo = data; + struct netns_ipvs *ipvs = net_ipvs(tinfo->net); struct ip_vs_sync_buff *sb; pr_info("sync thread started: state = MASTER, mcast_ifn = %s, " "syncid = %d\n", - ip_vs_master_mcast_ifn, ip_vs_master_syncid); + ipvs->master_mcast_ifn, ipvs->master_syncid); while (!kthread_should_stop()) { - while ((sb = sb_dequeue())) { + while ((sb = sb_dequeue(ipvs))) { ip_vs_send_sync_msg(tinfo->sock, sb->mesg); ip_vs_sync_buff_release(sb); } - /* check if entries stay in curr_sb for 2 seconds */ - sb = get_curr_sync_buff(2 * HZ); + /* check if entries stay in ipvs->sync_buff for 2 seconds */ + sb = get_curr_sync_buff(ipvs, 2 * HZ); if (sb) { ip_vs_send_sync_msg(tinfo->sock, sb->mesg); ip_vs_sync_buff_release(sb); @@ -783,14 +1465,13 @@ static int sync_thread_master(void *data) } /* clean up the sync_buff queue */ - while ((sb=sb_dequeue())) { + while ((sb = sb_dequeue(ipvs))) ip_vs_sync_buff_release(sb); - } /* clean up the current sync_buff */ - if ((sb = get_curr_sync_buff(0))) { + sb = get_curr_sync_buff(ipvs, 0); + if (sb) ip_vs_sync_buff_release(sb); - } /* release the sending multicast socket */ sock_release(tinfo->sock); @@ -803,11 +1484,12 @@ static int sync_thread_master(void *data) static int sync_thread_backup(void *data) { struct ip_vs_sync_thread_data *tinfo = data; + struct netns_ipvs *ipvs = net_ipvs(tinfo->net); int len; pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " "syncid = %d\n", - ip_vs_backup_mcast_ifn, ip_vs_backup_syncid); + ipvs->backup_mcast_ifn, ipvs->backup_syncid); while (!kthread_should_stop()) { wait_event_interruptible(*sk_sleep(tinfo->sock->sk), @@ -817,7 +1499,7 @@ static int sync_thread_backup(void *data) /* do we have data now? */ while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) { len = ip_vs_receive(tinfo->sock, tinfo->buf, - sync_recv_mesg_maxlen); + ipvs->recv_mesg_maxlen); if (len <= 0) { pr_err("receiving message error\n"); break; @@ -826,7 +1508,7 @@ static int sync_thread_backup(void *data) /* disable bottom half, because it accesses the data shared by softirq while getting/creating conns */ local_bh_disable(); - ip_vs_process_message(tinfo->buf, len); + ip_vs_process_message(tinfo->net, tinfo->buf, len); local_bh_enable(); } } @@ -840,41 +1522,42 @@ static int sync_thread_backup(void *data) } -int start_sync_thread(int state, char *mcast_ifn, __u8 syncid) +int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid) { struct ip_vs_sync_thread_data *tinfo; struct task_struct **realtask, *task; struct socket *sock; + struct netns_ipvs *ipvs = net_ipvs(net); char *name, *buf = NULL; int (*threadfn)(void *data); int result = -ENOMEM; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %Zd bytes\n", - sizeof(struct ip_vs_sync_conn)); + sizeof(struct ip_vs_sync_conn_v0)); if (state == IP_VS_STATE_MASTER) { - if (sync_master_thread) + if (ipvs->master_thread) return -EEXIST; - strlcpy(ip_vs_master_mcast_ifn, mcast_ifn, - sizeof(ip_vs_master_mcast_ifn)); - ip_vs_master_syncid = syncid; - realtask = &sync_master_thread; - name = "ipvs_syncmaster"; + strlcpy(ipvs->master_mcast_ifn, mcast_ifn, + sizeof(ipvs->master_mcast_ifn)); + ipvs->master_syncid = syncid; + realtask = &ipvs->master_thread; + name = "ipvs_master:%d"; threadfn = sync_thread_master; - sock = make_send_sock(); + sock = make_send_sock(net); } else if (state == IP_VS_STATE_BACKUP) { - if (sync_backup_thread) + if (ipvs->backup_thread) return -EEXIST; - strlcpy(ip_vs_backup_mcast_ifn, mcast_ifn, - sizeof(ip_vs_backup_mcast_ifn)); - ip_vs_backup_syncid = syncid; - realtask = &sync_backup_thread; - name = "ipvs_syncbackup"; + strlcpy(ipvs->backup_mcast_ifn, mcast_ifn, + sizeof(ipvs->backup_mcast_ifn)); + ipvs->backup_syncid = syncid; + realtask = &ipvs->backup_thread; + name = "ipvs_backup:%d"; threadfn = sync_thread_backup; - sock = make_receive_sock(); + sock = make_receive_sock(net); } else { return -EINVAL; } @@ -884,9 +1567,9 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid) goto out; } - set_sync_mesg_maxlen(state); + set_sync_mesg_maxlen(net, state); if (state == IP_VS_STATE_BACKUP) { - buf = kmalloc(sync_recv_mesg_maxlen, GFP_KERNEL); + buf = kmalloc(ipvs->recv_mesg_maxlen, GFP_KERNEL); if (!buf) goto outsocket; } @@ -895,10 +1578,11 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid) if (!tinfo) goto outbuf; + tinfo->net = net; tinfo->sock = sock; tinfo->buf = buf; - task = kthread_run(threadfn, tinfo, name); + task = kthread_run(threadfn, tinfo, name, ipvs->gen); if (IS_ERR(task)) { result = PTR_ERR(task); goto outtinfo; @@ -906,7 +1590,7 @@ int start_sync_thread(int state, char *mcast_ifn, __u8 syncid) /* mark as active */ *realtask = task; - ip_vs_sync_state |= state; + ipvs->sync_state |= state; /* increase the module use count */ ip_vs_use_count_inc(); @@ -924,16 +1608,18 @@ out: } -int stop_sync_thread(int state) +int stop_sync_thread(struct net *net, int state) { + struct netns_ipvs *ipvs = net_ipvs(net); + IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); if (state == IP_VS_STATE_MASTER) { - if (!sync_master_thread) + if (!ipvs->master_thread) return -ESRCH; pr_info("stopping master sync thread %d ...\n", - task_pid_nr(sync_master_thread)); + task_pid_nr(ipvs->master_thread)); /* * The lock synchronizes with sb_queue_tail(), so that we don't @@ -941,21 +1627,21 @@ int stop_sync_thread(int state) * progress of stopping the master sync daemon. */ - spin_lock_bh(&ip_vs_sync_lock); - ip_vs_sync_state &= ~IP_VS_STATE_MASTER; - spin_unlock_bh(&ip_vs_sync_lock); - kthread_stop(sync_master_thread); - sync_master_thread = NULL; + spin_lock_bh(&ipvs->sync_lock); + ipvs->sync_state &= ~IP_VS_STATE_MASTER; + spin_unlock_bh(&ipvs->sync_lock); + kthread_stop(ipvs->master_thread); + ipvs->master_thread = NULL; } else if (state == IP_VS_STATE_BACKUP) { - if (!sync_backup_thread) + if (!ipvs->backup_thread) return -ESRCH; pr_info("stopping backup sync thread %d ...\n", - task_pid_nr(sync_backup_thread)); + task_pid_nr(ipvs->backup_thread)); - ip_vs_sync_state &= ~IP_VS_STATE_BACKUP; - kthread_stop(sync_backup_thread); - sync_backup_thread = NULL; + ipvs->sync_state &= ~IP_VS_STATE_BACKUP; + kthread_stop(ipvs->backup_thread); + ipvs->backup_thread = NULL; } else { return -EINVAL; } @@ -965,3 +1651,42 @@ int stop_sync_thread(int state) return 0; } + +/* + * Initialize data struct for each netns + */ +static int __net_init __ip_vs_sync_init(struct net *net) +{ + struct netns_ipvs *ipvs = net_ipvs(net); + + INIT_LIST_HEAD(&ipvs->sync_queue); + spin_lock_init(&ipvs->sync_lock); + spin_lock_init(&ipvs->sync_buff_lock); + + ipvs->sync_mcast_addr.sin_family = AF_INET; + ipvs->sync_mcast_addr.sin_port = cpu_to_be16(IP_VS_SYNC_PORT); + ipvs->sync_mcast_addr.sin_addr.s_addr = cpu_to_be32(IP_VS_SYNC_GROUP); + return 0; +} + +static void __ip_vs_sync_cleanup(struct net *net) +{ + stop_sync_thread(net, IP_VS_STATE_MASTER); + stop_sync_thread(net, IP_VS_STATE_BACKUP); +} + +static struct pernet_operations ipvs_sync_ops = { + .init = __ip_vs_sync_init, + .exit = __ip_vs_sync_cleanup, +}; + + +int __init ip_vs_sync_init(void) +{ + return register_pernet_subsys(&ipvs_sync_ops); +} + +void __exit ip_vs_sync_cleanup(void) +{ + unregister_pernet_subsys(&ipvs_sync_ops); +} diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 5325a3f..1f2a4e3 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -175,7 +175,6 @@ __ip_vs_reroute_locally(struct sk_buff *skb) .fl4_tos = RT_TOS(iph->tos), .mark = skb->mark, }; - struct rtable *rt; if (ip_route_output_key(net, &rt, &fl)) return 0; @@ -390,7 +389,8 @@ ip_vs_bypass_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) { + if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) && + !skb_is_gso(skb)) { ip_rt_put(rt); icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL("%s(): frag needed\n", __func__); @@ -443,7 +443,7 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if (skb->len > mtu) { + if (skb->len > mtu && !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -543,7 +543,8 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF))) { + if ((skb->len > mtu) && (iph->frag_off & htons(IP_DF)) && + !skb_is_gso(skb)) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL_PKT(0, AF_INET, pp, skb, 0, "ip_vs_nat_xmit(): frag needed for"); @@ -658,7 +659,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if (skb->len > mtu) { + if (skb->len > mtu && !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -773,8 +774,8 @@ ip_vs_tunnel_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, df |= (old_iph->frag_off & htons(IP_DF)); - if ((old_iph->frag_off & htons(IP_DF)) - && mtu < ntohs(old_iph->tot_len)) { + if ((old_iph->frag_off & htons(IP_DF) && + mtu < ntohs(old_iph->tot_len) && !skb_is_gso(skb))) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; @@ -886,7 +887,8 @@ ip_vs_tunnel_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, if (skb_dst(skb)) skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); - if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr)) { + if (mtu < ntohs(old_iph->payload_len) + sizeof(struct ipv6hdr) && + !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); @@ -991,7 +993,8 @@ ip_vs_dr_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu) { + if ((iph->frag_off & htons(IP_DF)) && skb->len > mtu && + !skb_is_gso(skb)) { icmp_send(skb, ICMP_DEST_UNREACH,ICMP_FRAG_NEEDED, htonl(mtu)); ip_rt_put(rt); IP_VS_DBG_RL("%s(): frag needed\n", __func__); @@ -1158,7 +1161,8 @@ ip_vs_icmp_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF))) { + if ((skb->len > mtu) && (ip_hdr(skb)->frag_off & htons(IP_DF)) && + !skb_is_gso(skb)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); IP_VS_DBG_RL("%s(): frag needed\n", __func__); goto tx_error_put; @@ -1272,7 +1276,7 @@ ip_vs_icmp_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, /* MTU checking */ mtu = dst_mtu(&rt->dst); - if (skb->len > mtu) { + if (skb->len > mtu && !skb_is_gso(skb)) { if (!skb->dev) { struct net *net = dev_net(skb_dst(skb)->dev); diff --git a/net/netfilter/nf_conntrack_broadcast.c b/net/netfilter/nf_conntrack_broadcast.c new file mode 100644 index 0000000..4e99cca --- /dev/null +++ b/net/netfilter/nf_conntrack_broadcast.c @@ -0,0 +1,82 @@ +/* + * broadcast connection tracking helper + * + * (c) 2005 Patrick McHardy <kaber@trash.net> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/ip.h> +#include <net/route.h> +#include <linux/inetdevice.h> +#include <linux/skbuff.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_expect.h> + +int nf_conntrack_broadcast_help(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo, + unsigned int timeout) +{ + struct nf_conntrack_expect *exp; + struct iphdr *iph = ip_hdr(skb); + struct rtable *rt = skb_rtable(skb); + struct in_device *in_dev; + struct nf_conn_help *help = nfct_help(ct); + __be32 mask = 0; + + /* we're only interested in locally generated packets */ + if (skb->sk == NULL) + goto out; + if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST)) + goto out; + if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) + goto out; + + rcu_read_lock(); + in_dev = __in_dev_get_rcu(rt->dst.dev); + if (in_dev != NULL) { + for_primary_ifa(in_dev) { + if (ifa->ifa_broadcast == iph->daddr) { + mask = ifa->ifa_mask; + break; + } + } endfor_ifa(in_dev); + } + rcu_read_unlock(); + + if (mask == 0) + goto out; + + exp = nf_ct_expect_alloc(ct); + if (exp == NULL) + goto out; + + exp->tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; + exp->tuple.src.u.udp.port = help->helper->tuple.src.u.udp.port; + + exp->mask.src.u3.ip = mask; + exp->mask.src.u.udp.port = htons(0xFFFF); + + exp->expectfn = NULL; + exp->flags = NF_CT_EXPECT_PERMANENT; + exp->class = NF_CT_EXPECT_CLASS_DEFAULT; + exp->helper = NULL; + + nf_ct_expect_related(exp); + nf_ct_expect_put(exp); + + nf_ct_refresh(ct, skb, timeout * HZ); +out: + return NF_ACCEPT; +} +EXPORT_SYMBOL_GPL(nf_conntrack_broadcast_help); + +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e615119..1909311 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -43,6 +43,7 @@ #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_ecache.h> #include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_conntrack_timestamp.h> #include <net/netfilter/nf_nat.h> #include <net/netfilter/nf_nat_core.h> @@ -282,6 +283,11 @@ EXPORT_SYMBOL_GPL(nf_ct_insert_dying_list); static void death_by_timeout(unsigned long ul_conntrack) { struct nf_conn *ct = (void *)ul_conntrack; + struct nf_conn_tstamp *tstamp; + + tstamp = nf_conn_tstamp_find(ct); + if (tstamp && tstamp->stop == 0) + tstamp->stop = ktime_to_ns(ktime_get_real()); if (!test_bit(IPS_DYING_BIT, &ct->status) && unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) { @@ -419,6 +425,7 @@ __nf_conntrack_confirm(struct sk_buff *skb) struct nf_conntrack_tuple_hash *h; struct nf_conn *ct; struct nf_conn_help *help; + struct nf_conn_tstamp *tstamp; struct hlist_nulls_node *n; enum ip_conntrack_info ctinfo; struct net *net; @@ -486,8 +493,16 @@ __nf_conntrack_confirm(struct sk_buff *skb) ct->timeout.expires += jiffies; add_timer(&ct->timeout); atomic_inc(&ct->ct_general.use); - set_bit(IPS_CONFIRMED_BIT, &ct->status); + ct->status |= IPS_CONFIRMED; + + /* set conntrack timestamp, if enabled. */ + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) { + if (skb->tstamp.tv64 == 0) + __net_timestamp((struct sk_buff *)skb); + tstamp->start = ktime_to_ns(skb->tstamp); + } /* Since the lookup is lockless, hash insertion must be done after * starting the timer and setting the CONFIRMED bit. The RCU barriers * guarantee that no other CPU can find the conntrack before the above @@ -655,7 +670,8 @@ __nf_conntrack_alloc(struct net *net, u16 zone, * and ct->tuplehash[IP_CT_DIR_REPLY].hnnode.next unchanged. */ memset(&ct->tuplehash[IP_CT_DIR_MAX], 0, - sizeof(*ct) - offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX])); + offsetof(struct nf_conn, proto) - + offsetof(struct nf_conn, tuplehash[IP_CT_DIR_MAX])); spin_lock_init(&ct->lock); ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig; ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode.pprev = NULL; @@ -745,6 +761,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, } nf_ct_acct_ext_add(ct, GFP_ATOMIC); + nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); ecache = tmpl ? nf_ct_ecache_find(tmpl) : NULL; nf_ct_ecache_ext_add(ct, ecache ? ecache->ctmask : 0, @@ -1185,6 +1202,11 @@ struct __nf_ct_flush_report { static int kill_report(struct nf_conn *i, void *data) { struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data; + struct nf_conn_tstamp *tstamp; + + tstamp = nf_conn_tstamp_find(i); + if (tstamp && tstamp->stop == 0) + tstamp->stop = ktime_to_ns(ktime_get_real()); /* If we fail to deliver the event, death_by_timeout() will retry */ if (nf_conntrack_event_report(IPCT_DESTROY, i, @@ -1201,9 +1223,9 @@ static int kill_all(struct nf_conn *i, void *data) return 1; } -void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size) +void nf_ct_free_hashtable(void *hash, unsigned int size) { - if (vmalloced) + if (is_vmalloc_addr(hash)) vfree(hash); else free_pages((unsigned long)hash, @@ -1270,8 +1292,7 @@ static void nf_conntrack_cleanup_net(struct net *net) goto i_see_dead_people; } - nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc, - net->ct.htable_size); + nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); nf_conntrack_ecache_fini(net); nf_conntrack_acct_fini(net); nf_conntrack_expect_fini(net); @@ -1300,21 +1321,18 @@ void nf_conntrack_cleanup(struct net *net) } } -void *nf_ct_alloc_hashtable(unsigned int *sizep, int *vmalloced, int nulls) +void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls) { struct hlist_nulls_head *hash; unsigned int nr_slots, i; size_t sz; - *vmalloced = 0; - BUILD_BUG_ON(sizeof(struct hlist_nulls_head) != sizeof(struct hlist_head)); nr_slots = *sizep = roundup(*sizep, PAGE_SIZE / sizeof(struct hlist_nulls_head)); sz = nr_slots * sizeof(struct hlist_nulls_head); hash = (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, get_order(sz)); if (!hash) { - *vmalloced = 1; printk(KERN_WARNING "nf_conntrack: falling back to vmalloc.\n"); hash = __vmalloc(sz, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL); @@ -1330,7 +1348,7 @@ EXPORT_SYMBOL_GPL(nf_ct_alloc_hashtable); int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) { - int i, bucket, vmalloced, old_vmalloced; + int i, bucket; unsigned int hashsize, old_size; struct hlist_nulls_head *hash, *old_hash; struct nf_conntrack_tuple_hash *h; @@ -1347,7 +1365,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) if (!hashsize) return -EINVAL; - hash = nf_ct_alloc_hashtable(&hashsize, &vmalloced, 1); + hash = nf_ct_alloc_hashtable(&hashsize, 1); if (!hash) return -ENOMEM; @@ -1369,15 +1387,13 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp) } } old_size = init_net.ct.htable_size; - old_vmalloced = init_net.ct.hash_vmalloc; old_hash = init_net.ct.hash; init_net.ct.htable_size = nf_conntrack_htable_size = hashsize; - init_net.ct.hash_vmalloc = vmalloced; init_net.ct.hash = hash; spin_unlock_bh(&nf_conntrack_lock); - nf_ct_free_hashtable(old_hash, old_vmalloced, old_size); + nf_ct_free_hashtable(old_hash, old_size); return 0; } EXPORT_SYMBOL_GPL(nf_conntrack_set_hashsize); @@ -1490,8 +1506,7 @@ static int nf_conntrack_init_net(struct net *net) } net->ct.htable_size = nf_conntrack_htable_size; - net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, - &net->ct.hash_vmalloc, 1); + net->ct.hash = nf_ct_alloc_hashtable(&net->ct.htable_size, 1); if (!net->ct.hash) { ret = -ENOMEM; printk(KERN_ERR "Unable to create nf_conntrack_hash\n"); @@ -1503,6 +1518,9 @@ static int nf_conntrack_init_net(struct net *net) ret = nf_conntrack_acct_init(net); if (ret < 0) goto err_acct; + ret = nf_conntrack_tstamp_init(net); + if (ret < 0) + goto err_tstamp; ret = nf_conntrack_ecache_init(net); if (ret < 0) goto err_ecache; @@ -1510,12 +1528,13 @@ static int nf_conntrack_init_net(struct net *net) return 0; err_ecache: + nf_conntrack_tstamp_fini(net); +err_tstamp: nf_conntrack_acct_fini(net); err_acct: nf_conntrack_expect_fini(net); err_expect: - nf_ct_free_hashtable(net->ct.hash, net->ct.hash_vmalloc, - net->ct.htable_size); + nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size); err_hash: kmem_cache_destroy(net->ct.nf_conntrack_cachep); err_cache: diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index a20fb0b..cd1e8e0 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -319,7 +319,8 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) const struct nf_conntrack_expect_policy *p; unsigned int h = nf_ct_expect_dst_hash(&exp->tuple); - atomic_inc(&exp->use); + /* two references : one for hash insert, one for the timer */ + atomic_add(2, &exp->use); if (master_help) { hlist_add_head(&exp->lnode, &master_help->expectations); @@ -333,12 +334,14 @@ static void nf_ct_expect_insert(struct nf_conntrack_expect *exp) setup_timer(&exp->timeout, nf_ct_expectation_timed_out, (unsigned long)exp); if (master_help) { - p = &master_help->helper->expect_policy[exp->class]; + p = &rcu_dereference_protected( + master_help->helper, + lockdep_is_held(&nf_conntrack_lock) + )->expect_policy[exp->class]; exp->timeout.expires = jiffies + p->timeout * HZ; } add_timer(&exp->timeout); - atomic_inc(&exp->use); NF_CT_STAT_INC(net, expect_create); } @@ -369,7 +372,10 @@ static inline int refresh_timer(struct nf_conntrack_expect *i) if (!del_timer(&i->timeout)) return 0; - p = &master_help->helper->expect_policy[i->class]; + p = &rcu_dereference_protected( + master_help->helper, + lockdep_is_held(&nf_conntrack_lock) + )->expect_policy[i->class]; i->timeout.expires = jiffies + p->timeout * HZ; add_timer(&i->timeout); return 1; @@ -407,7 +413,10 @@ static inline int __nf_ct_expect_check(struct nf_conntrack_expect *expect) } /* Will be over limit? */ if (master_help) { - p = &master_help->helper->expect_policy[expect->class]; + p = &rcu_dereference_protected( + master_help->helper, + lockdep_is_held(&nf_conntrack_lock) + )->expect_policy[expect->class]; if (p->max_expected && master_help->expecting[expect->class] >= p->max_expected) { evict_oldest_expect(master, expect); @@ -478,7 +487,7 @@ static struct hlist_node *ct_expect_get_first(struct seq_file *seq) struct hlist_node *n; for (st->bucket = 0; st->bucket < nf_ct_expect_hsize; st->bucket++) { - n = rcu_dereference(net->ct.expect_hash[st->bucket].first); + n = rcu_dereference(hlist_first_rcu(&net->ct.expect_hash[st->bucket])); if (n) return n; } @@ -491,11 +500,11 @@ static struct hlist_node *ct_expect_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct ct_expect_iter_state *st = seq->private; - head = rcu_dereference(head->next); + head = rcu_dereference(hlist_next_rcu(head)); while (head == NULL) { if (++st->bucket >= nf_ct_expect_hsize) return NULL; - head = rcu_dereference(net->ct.expect_hash[st->bucket].first); + head = rcu_dereference(hlist_first_rcu(&net->ct.expect_hash[st->bucket])); } return head; } @@ -630,8 +639,7 @@ int nf_conntrack_expect_init(struct net *net) } net->ct.expect_count = 0; - net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, - &net->ct.expect_vmalloc, 0); + net->ct.expect_hash = nf_ct_alloc_hashtable(&nf_ct_expect_hsize, 0); if (net->ct.expect_hash == NULL) goto err1; @@ -653,8 +661,7 @@ err3: if (net_eq(net, &init_net)) kmem_cache_destroy(nf_ct_expect_cachep); err2: - nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc, - nf_ct_expect_hsize); + nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize); err1: return err; } @@ -666,6 +673,5 @@ void nf_conntrack_expect_fini(struct net *net) rcu_barrier(); /* Wait for call_rcu() before destroy */ kmem_cache_destroy(nf_ct_expect_cachep); } - nf_ct_free_hashtable(net->ct.expect_hash, net->ct.expect_vmalloc, - nf_ct_expect_hsize); + nf_ct_free_hashtable(net->ct.expect_hash, nf_ct_expect_hsize); } diff --git a/net/netfilter/nf_conntrack_extend.c b/net/netfilter/nf_conntrack_extend.c index bd82450..80a23ed 100644 --- a/net/netfilter/nf_conntrack_extend.c +++ b/net/netfilter/nf_conntrack_extend.c @@ -140,15 +140,16 @@ static void update_alloc_size(struct nf_ct_ext_type *type) /* This assumes that extended areas in conntrack for the types whose NF_CT_EXT_F_PREALLOC bit set are allocated in order */ for (i = min; i <= max; i++) { - t1 = nf_ct_ext_types[i]; + t1 = rcu_dereference_protected(nf_ct_ext_types[i], + lockdep_is_held(&nf_ct_ext_type_mutex)); if (!t1) continue; - t1->alloc_size = sizeof(struct nf_ct_ext) - + ALIGN(sizeof(struct nf_ct_ext), t1->align) - + t1->len; + t1->alloc_size = ALIGN(sizeof(struct nf_ct_ext), t1->align) + + t1->len; for (j = 0; j < NF_CT_EXT_NUM; j++) { - t2 = nf_ct_ext_types[j]; + t2 = rcu_dereference_protected(nf_ct_ext_types[j], + lockdep_is_held(&nf_ct_ext_type_mutex)); if (t2 == NULL || t2 == t1 || (t2->flags & NF_CT_EXT_F_PREALLOC) == 0) continue; diff --git a/net/netfilter/nf_conntrack_helper.c b/net/netfilter/nf_conntrack_helper.c index 59e1a4c..1bdfea3 100644 --- a/net/netfilter/nf_conntrack_helper.c +++ b/net/netfilter/nf_conntrack_helper.c @@ -33,7 +33,6 @@ static DEFINE_MUTEX(nf_ct_helper_mutex); static struct hlist_head *nf_ct_helper_hash __read_mostly; static unsigned int nf_ct_helper_hsize __read_mostly; static unsigned int nf_ct_helper_count __read_mostly; -static int nf_ct_helper_vmalloc; /* Stupid hash, but collision free for the default registrations of the @@ -158,7 +157,10 @@ static inline int unhelp(struct nf_conntrack_tuple_hash *i, struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(i); struct nf_conn_help *help = nfct_help(ct); - if (help && help->helper == me) { + if (help && rcu_dereference_protected( + help->helper, + lockdep_is_held(&nf_conntrack_lock) + ) == me) { nf_conntrack_event(IPCT_HELPER, ct); rcu_assign_pointer(help->helper, NULL); } @@ -210,7 +212,10 @@ static void __nf_conntrack_helper_unregister(struct nf_conntrack_helper *me, hlist_for_each_entry_safe(exp, n, next, &net->ct.expect_hash[i], hnode) { struct nf_conn_help *help = nfct_help(exp->master); - if ((help->helper == me || exp->helper == me) && + if ((rcu_dereference_protected( + help->helper, + lockdep_is_held(&nf_conntrack_lock) + ) == me || exp->helper == me) && del_timer(&exp->timeout)) { nf_ct_unlink_expect(exp); nf_ct_expect_put(exp); @@ -261,8 +266,7 @@ int nf_conntrack_helper_init(void) int err; nf_ct_helper_hsize = 1; /* gets rounded up to use one page */ - nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize, - &nf_ct_helper_vmalloc, 0); + nf_ct_helper_hash = nf_ct_alloc_hashtable(&nf_ct_helper_hsize, 0); if (!nf_ct_helper_hash) return -ENOMEM; @@ -273,14 +277,12 @@ int nf_conntrack_helper_init(void) return 0; err1: - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_vmalloc, - nf_ct_helper_hsize); + nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); return err; } void nf_conntrack_helper_fini(void) { nf_ct_extend_unregister(&helper_extend); - nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_vmalloc, - nf_ct_helper_hsize); + nf_ct_free_hashtable(nf_ct_helper_hash, nf_ct_helper_hsize); } diff --git a/net/netfilter/nf_conntrack_netbios_ns.c b/net/netfilter/nf_conntrack_netbios_ns.c index aadde01..4c8f30a 100644 --- a/net/netfilter/nf_conntrack_netbios_ns.c +++ b/net/netfilter/nf_conntrack_netbios_ns.c @@ -18,14 +18,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/init.h> -#include <linux/skbuff.h> -#include <linux/netdevice.h> -#include <linux/inetdevice.h> -#include <linux/if_addr.h> #include <linux/in.h> -#include <linux/ip.h> -#include <linux/netfilter.h> -#include <net/route.h> #include <net/netfilter/nf_conntrack.h> #include <net/netfilter/nf_conntrack_helper.h> @@ -40,75 +33,26 @@ MODULE_ALIAS("ip_conntrack_netbios_ns"); MODULE_ALIAS_NFCT_HELPER("netbios_ns"); static unsigned int timeout __read_mostly = 3; -module_param(timeout, uint, 0400); +module_param(timeout, uint, S_IRUSR); MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds"); -static int help(struct sk_buff *skb, unsigned int protoff, - struct nf_conn *ct, enum ip_conntrack_info ctinfo) -{ - struct nf_conntrack_expect *exp; - struct iphdr *iph = ip_hdr(skb); - struct rtable *rt = skb_rtable(skb); - struct in_device *in_dev; - __be32 mask = 0; - - /* we're only interested in locally generated packets */ - if (skb->sk == NULL) - goto out; - if (rt == NULL || !(rt->rt_flags & RTCF_BROADCAST)) - goto out; - if (CTINFO2DIR(ctinfo) != IP_CT_DIR_ORIGINAL) - goto out; - - rcu_read_lock(); - in_dev = __in_dev_get_rcu(rt->dst.dev); - if (in_dev != NULL) { - for_primary_ifa(in_dev) { - if (ifa->ifa_broadcast == iph->daddr) { - mask = ifa->ifa_mask; - break; - } - } endfor_ifa(in_dev); - } - rcu_read_unlock(); - - if (mask == 0) - goto out; - - exp = nf_ct_expect_alloc(ct); - if (exp == NULL) - goto out; - - exp->tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - exp->tuple.src.u.udp.port = htons(NMBD_PORT); - - exp->mask.src.u3.ip = mask; - exp->mask.src.u.udp.port = htons(0xFFFF); - - exp->expectfn = NULL; - exp->flags = NF_CT_EXPECT_PERMANENT; - exp->class = NF_CT_EXPECT_CLASS_DEFAULT; - exp->helper = NULL; - - nf_ct_expect_related(exp); - nf_ct_expect_put(exp); - - nf_ct_refresh(ct, skb, timeout * HZ); -out: - return NF_ACCEPT; -} - static struct nf_conntrack_expect_policy exp_policy = { .max_expected = 1, }; +static int netbios_ns_help(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, enum ip_conntrack_info ctinfo) +{ + return nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout); +} + static struct nf_conntrack_helper helper __read_mostly = { .name = "netbios-ns", - .tuple.src.l3num = AF_INET, + .tuple.src.l3num = NFPROTO_IPV4, .tuple.src.u.udp.port = cpu_to_be16(NMBD_PORT), .tuple.dst.protonum = IPPROTO_UDP, .me = THIS_MODULE, - .help = help, + .help = netbios_ns_help, .expect_policy = &exp_policy, }; diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 93297aa..3fec12c 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -42,6 +42,7 @@ #include <net/netfilter/nf_conntrack_tuple.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_conntrack_timestamp.h> #ifdef CONFIG_NF_NAT_NEEDED #include <net/netfilter/nf_nat_core.h> #include <net/netfilter/nf_nat_protocol.h> @@ -230,6 +231,33 @@ nla_put_failure: return -1; } +static int +ctnetlink_dump_timestamp(struct sk_buff *skb, const struct nf_conn *ct) +{ + struct nlattr *nest_count; + const struct nf_conn_tstamp *tstamp; + + tstamp = nf_conn_tstamp_find(ct); + if (!tstamp) + return 0; + + nest_count = nla_nest_start(skb, CTA_TIMESTAMP | NLA_F_NESTED); + if (!nest_count) + goto nla_put_failure; + + NLA_PUT_BE64(skb, CTA_TIMESTAMP_START, cpu_to_be64(tstamp->start)); + if (tstamp->stop != 0) { + NLA_PUT_BE64(skb, CTA_TIMESTAMP_STOP, + cpu_to_be64(tstamp->stop)); + } + nla_nest_end(skb, nest_count); + + return 0; + +nla_put_failure: + return -1; +} + #ifdef CONFIG_NF_CONNTRACK_MARK static inline int ctnetlink_dump_mark(struct sk_buff *skb, const struct nf_conn *ct) @@ -404,6 +432,7 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq, ctnetlink_dump_timeout(skb, ct) < 0 || ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 || ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 || + ctnetlink_dump_timestamp(skb, ct) < 0 || ctnetlink_dump_protoinfo(skb, ct) < 0 || ctnetlink_dump_helpinfo(skb, ct) < 0 || ctnetlink_dump_mark(skb, ct) < 0 || @@ -471,6 +500,18 @@ ctnetlink_secctx_size(const struct nf_conn *ct) } static inline size_t +ctnetlink_timestamp_size(const struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP + if (!nf_ct_ext_exist(ct, NF_CT_EXT_TSTAMP)) + return 0; + return nla_total_size(0) + 2 * nla_total_size(sizeof(uint64_t)); +#else + return 0; +#endif +} + +static inline size_t ctnetlink_nlmsg_size(const struct nf_conn *ct) { return NLMSG_ALIGN(sizeof(struct nfgenmsg)) @@ -481,6 +522,7 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */ + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */ + ctnetlink_counters_size(ct) + + ctnetlink_timestamp_size(ct) + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */ + nla_total_size(0) /* CTA_PROTOINFO */ + nla_total_size(0) /* CTA_HELP */ @@ -571,7 +613,8 @@ ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item) if (events & (1 << IPCT_DESTROY)) { if (ctnetlink_dump_counters(skb, ct, IP_CT_DIR_ORIGINAL) < 0 || - ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0) + ctnetlink_dump_counters(skb, ct, IP_CT_DIR_REPLY) < 0 || + ctnetlink_dump_timestamp(skb, ct) < 0) goto nla_put_failure; } else { if (ctnetlink_dump_timeout(skb, ct) < 0) @@ -1357,6 +1400,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, } nf_ct_acct_ext_add(ct, GFP_ATOMIC); + nf_ct_tstamp_ext_add(ct, GFP_ATOMIC); nf_ct_ecache_ext_add(ct, 0, 0, GFP_ATOMIC); /* we must add conntrack extensions before confirmation. */ ct->status |= IPS_CONFIRMED; @@ -1375,6 +1419,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, } #endif + memset(&ct->proto, 0, sizeof(ct->proto)); if (cda[CTA_PROTOINFO]) { err = ctnetlink_change_protoinfo(ct, cda); if (err < 0) diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index dc7bb74..5701c8d 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -166,6 +166,7 @@ static void nf_ct_l3proto_unregister_sysctl(struct nf_conntrack_l3proto *l3proto int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto) { int ret = 0; + struct nf_conntrack_l3proto *old; if (proto->l3proto >= AF_MAX) return -EBUSY; @@ -174,7 +175,9 @@ int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto) return -EINVAL; mutex_lock(&nf_ct_proto_mutex); - if (nf_ct_l3protos[proto->l3proto] != &nf_conntrack_l3proto_generic) { + old = rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], + lockdep_is_held(&nf_ct_proto_mutex)); + if (old != &nf_conntrack_l3proto_generic) { ret = -EBUSY; goto out_unlock; } @@ -201,7 +204,9 @@ void nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto) BUG_ON(proto->l3proto >= AF_MAX); mutex_lock(&nf_ct_proto_mutex); - BUG_ON(nf_ct_l3protos[proto->l3proto] != proto); + BUG_ON(rcu_dereference_protected(nf_ct_l3protos[proto->l3proto], + lockdep_is_held(&nf_ct_proto_mutex) + ) != proto); rcu_assign_pointer(nf_ct_l3protos[proto->l3proto], &nf_conntrack_l3proto_generic); nf_ct_l3proto_unregister_sysctl(proto); @@ -279,7 +284,7 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto) mutex_lock(&nf_ct_proto_mutex); if (!nf_ct_protos[l4proto->l3proto]) { /* l3proto may be loaded latter. */ - struct nf_conntrack_l4proto **proto_array; + struct nf_conntrack_l4proto __rcu **proto_array; int i; proto_array = kmalloc(MAX_NF_CT_PROTO * @@ -291,7 +296,7 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto) } for (i = 0; i < MAX_NF_CT_PROTO; i++) - proto_array[i] = &nf_conntrack_l4proto_generic; + RCU_INIT_POINTER(proto_array[i], &nf_conntrack_l4proto_generic); /* Before making proto_array visible to lockless readers, * we must make sure its content is committed to memory. @@ -299,8 +304,10 @@ int nf_conntrack_l4proto_register(struct nf_conntrack_l4proto *l4proto) smp_wmb(); nf_ct_protos[l4proto->l3proto] = proto_array; - } else if (nf_ct_protos[l4proto->l3proto][l4proto->l4proto] != - &nf_conntrack_l4proto_generic) { + } else if (rcu_dereference_protected( + nf_ct_protos[l4proto->l3proto][l4proto->l4proto], + lockdep_is_held(&nf_ct_proto_mutex) + ) != &nf_conntrack_l4proto_generic) { ret = -EBUSY; goto out_unlock; } @@ -331,7 +338,10 @@ void nf_conntrack_l4proto_unregister(struct nf_conntrack_l4proto *l4proto) BUG_ON(l4proto->l3proto >= PF_MAX); mutex_lock(&nf_ct_proto_mutex); - BUG_ON(nf_ct_protos[l4proto->l3proto][l4proto->l4proto] != l4proto); + BUG_ON(rcu_dereference_protected( + nf_ct_protos[l4proto->l3proto][l4proto->l4proto], + lockdep_is_held(&nf_ct_proto_mutex) + ) != l4proto); rcu_assign_pointer(nf_ct_protos[l4proto->l3proto][l4proto->l4proto], &nf_conntrack_l4proto_generic); nf_ct_l4proto_unregister_sysctl(l4proto); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 5292560..9ae57c5 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -452,6 +452,9 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT; ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER; ct->proto.dccp.state = CT_DCCP_NONE; + ct->proto.dccp.last_pkt = DCCP_PKT_REQUEST; + ct->proto.dccp.last_dir = IP_CT_DIR_ORIGINAL; + ct->proto.dccp.handshake_seq = 0; return true; out_invalid: diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index c6049c2..6f4ee70 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -413,6 +413,7 @@ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb, test_bit(SCTP_CID_COOKIE_ACK, map)) return false; + memset(&ct->proto.sctp, 0, sizeof(ct->proto.sctp)); new_state = SCTP_CONNTRACK_MAX; for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) { /* Don't need lock here: this conntrack not in circulation yet */ diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 3fb2b73..6f38d0e 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1066,9 +1066,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, BUG_ON(th == NULL); /* Don't need lock here: this conntrack not in circulation yet */ - new_state - = tcp_conntracks[0][get_conntrack_index(th)] - [TCP_CONNTRACK_NONE]; + new_state = tcp_conntracks[0][get_conntrack_index(th)][TCP_CONNTRACK_NONE]; /* Invalid: delete conntrack */ if (new_state >= TCP_CONNTRACK_MAX) { @@ -1077,6 +1075,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, } if (new_state == TCP_CONNTRACK_SYN_SENT) { + memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp)); /* SYN packet */ ct->proto.tcp.seen[0].td_end = segment_seq_plus_len(ntohl(th->seq), skb->len, @@ -1088,11 +1087,11 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.tcp.seen[0].td_end; tcp_options(skb, dataoff, th, &ct->proto.tcp.seen[0]); - ct->proto.tcp.seen[1].flags = 0; } else if (nf_ct_tcp_loose == 0) { /* Don't try to pick up connections. */ return false; } else { + memset(&ct->proto.tcp, 0, sizeof(ct->proto.tcp)); /* * We are in the middle of a connection, * its history is lost for us. @@ -1107,7 +1106,6 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.tcp.seen[0].td_maxend = ct->proto.tcp.seen[0].td_end + ct->proto.tcp.seen[0].td_maxwin; - ct->proto.tcp.seen[0].td_scale = 0; /* We assume SACK and liberal window checking to handle * window scaling */ @@ -1116,13 +1114,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, IP_CT_TCP_FLAG_BE_LIBERAL; } - ct->proto.tcp.seen[1].td_end = 0; - ct->proto.tcp.seen[1].td_maxend = 0; - ct->proto.tcp.seen[1].td_maxwin = 0; - ct->proto.tcp.seen[1].td_scale = 0; - /* tcp_packet will set them */ - ct->proto.tcp.state = TCP_CONNTRACK_NONE; ct->proto.tcp.last_index = TCP_NONE_SET; pr_debug("tcp_new: sender end=%u maxend=%u maxwin=%u scale=%i " diff --git a/net/netfilter/nf_conntrack_snmp.c b/net/netfilter/nf_conntrack_snmp.c new file mode 100644 index 0000000..6e545e2 --- /dev/null +++ b/net/netfilter/nf_conntrack_snmp.c @@ -0,0 +1,77 @@ +/* + * SNMP service broadcast connection tracking helper + * + * (c) 2011 Jiri Olsa <jolsa@redhat.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/in.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_helper.h> +#include <net/netfilter/nf_conntrack_expect.h> + +#define SNMP_PORT 161 + +MODULE_AUTHOR("Jiri Olsa <jolsa@redhat.com>"); +MODULE_DESCRIPTION("SNMP service broadcast connection tracking helper"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NFCT_HELPER("snmp"); + +static unsigned int timeout __read_mostly = 30; +module_param(timeout, uint, S_IRUSR); +MODULE_PARM_DESC(timeout, "timeout for master connection/replies in seconds"); + +int (*nf_nat_snmp_hook)(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo); +EXPORT_SYMBOL_GPL(nf_nat_snmp_hook); + +static int snmp_conntrack_help(struct sk_buff *skb, unsigned int protoff, + struct nf_conn *ct, enum ip_conntrack_info ctinfo) +{ + typeof(nf_nat_snmp_hook) nf_nat_snmp; + + nf_conntrack_broadcast_help(skb, protoff, ct, ctinfo, timeout); + + nf_nat_snmp = rcu_dereference(nf_nat_snmp_hook); + if (nf_nat_snmp && ct->status & IPS_NAT_MASK) + return nf_nat_snmp(skb, protoff, ct, ctinfo); + + return NF_ACCEPT; +} + +static struct nf_conntrack_expect_policy exp_policy = { + .max_expected = 1, +}; + +static struct nf_conntrack_helper helper __read_mostly = { + .name = "snmp", + .tuple.src.l3num = NFPROTO_IPV4, + .tuple.src.u.udp.port = cpu_to_be16(SNMP_PORT), + .tuple.dst.protonum = IPPROTO_UDP, + .me = THIS_MODULE, + .help = snmp_conntrack_help, + .expect_policy = &exp_policy, +}; + +static int __init nf_conntrack_snmp_init(void) +{ + exp_policy.timeout = timeout; + return nf_conntrack_helper_register(&helper); +} + +static void __exit nf_conntrack_snmp_fini(void) +{ + nf_conntrack_helper_unregister(&helper); +} + +module_init(nf_conntrack_snmp_init); +module_exit(nf_conntrack_snmp_fini); diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index b4d7f0f..0ae1428 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -29,6 +29,8 @@ #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_acct.h> #include <net/netfilter/nf_conntrack_zones.h> +#include <net/netfilter/nf_conntrack_timestamp.h> +#include <linux/rculist_nulls.h> MODULE_LICENSE("GPL"); @@ -45,6 +47,7 @@ EXPORT_SYMBOL_GPL(print_tuple); struct ct_iter_state { struct seq_net_private p; unsigned int bucket; + u_int64_t time_now; }; static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) @@ -56,7 +59,7 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq) for (st->bucket = 0; st->bucket < net->ct.htable_size; st->bucket++) { - n = rcu_dereference(net->ct.hash[st->bucket].first); + n = rcu_dereference(hlist_nulls_first_rcu(&net->ct.hash[st->bucket])); if (!is_a_nulls(n)) return n; } @@ -69,13 +72,15 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq, struct net *net = seq_file_net(seq); struct ct_iter_state *st = seq->private; - head = rcu_dereference(head->next); + head = rcu_dereference(hlist_nulls_next_rcu(head)); while (is_a_nulls(head)) { if (likely(get_nulls_value(head) == st->bucket)) { if (++st->bucket >= net->ct.htable_size) return NULL; } - head = rcu_dereference(net->ct.hash[st->bucket].first); + head = rcu_dereference( + hlist_nulls_first_rcu( + &net->ct.hash[st->bucket])); } return head; } @@ -93,6 +98,9 @@ static struct hlist_nulls_node *ct_get_idx(struct seq_file *seq, loff_t pos) static void *ct_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { + struct ct_iter_state *st = seq->private; + + st->time_now = ktime_to_ns(ktime_get_real()); rcu_read_lock(); return ct_get_idx(seq, *pos); } @@ -132,6 +140,34 @@ static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) } #endif +#ifdef CONFIG_NF_CONNTRACK_TIMESTAMP +static int ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) +{ + struct ct_iter_state *st = s->private; + struct nf_conn_tstamp *tstamp; + s64 delta_time; + + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) { + delta_time = st->time_now - tstamp->start; + if (delta_time > 0) + delta_time = div_s64(delta_time, NSEC_PER_SEC); + else + delta_time = 0; + + return seq_printf(s, "delta-time=%llu ", + (unsigned long long)delta_time); + } + return 0; +} +#else +static inline int +ct_show_delta_time(struct seq_file *s, const struct nf_conn *ct) +{ + return 0; +} +#endif + /* return 0 on success, 1 in case of error */ static int ct_seq_show(struct seq_file *s, void *v) { @@ -200,6 +236,9 @@ static int ct_seq_show(struct seq_file *s, void *v) goto release; #endif + if (ct_show_delta_time(s, ct)) + goto release; + if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use))) goto release; diff --git a/net/netfilter/nf_conntrack_timestamp.c b/net/netfilter/nf_conntrack_timestamp.c new file mode 100644 index 0000000..af7dd31 --- /dev/null +++ b/net/netfilter/nf_conntrack_timestamp.c @@ -0,0 +1,120 @@ +/* + * (C) 2010 Pablo Neira Ayuso <pablo@netfilter.org> + * + * 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 (or any later at your option). + */ + +#include <linux/netfilter.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/moduleparam.h> + +#include <net/netfilter/nf_conntrack.h> +#include <net/netfilter/nf_conntrack_extend.h> +#include <net/netfilter/nf_conntrack_timestamp.h> + +static int nf_ct_tstamp __read_mostly; + +module_param_named(tstamp, nf_ct_tstamp, bool, 0644); +MODULE_PARM_DESC(tstamp, "Enable connection tracking flow timestamping."); + +#ifdef CONFIG_SYSCTL +static struct ctl_table tstamp_sysctl_table[] = { + { + .procname = "nf_conntrack_timestamp", + .data = &init_net.ct.sysctl_tstamp, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + {} +}; +#endif /* CONFIG_SYSCTL */ + +static struct nf_ct_ext_type tstamp_extend __read_mostly = { + .len = sizeof(struct nf_conn_tstamp), + .align = __alignof__(struct nf_conn_tstamp), + .id = NF_CT_EXT_TSTAMP, +}; + +#ifdef CONFIG_SYSCTL +static int nf_conntrack_tstamp_init_sysctl(struct net *net) +{ + struct ctl_table *table; + + table = kmemdup(tstamp_sysctl_table, sizeof(tstamp_sysctl_table), + GFP_KERNEL); + if (!table) + goto out; + + table[0].data = &net->ct.sysctl_tstamp; + + net->ct.tstamp_sysctl_header = register_net_sysctl_table(net, + nf_net_netfilter_sysctl_path, table); + if (!net->ct.tstamp_sysctl_header) { + printk(KERN_ERR "nf_ct_tstamp: can't register to sysctl.\n"); + goto out_register; + } + return 0; + +out_register: + kfree(table); +out: + return -ENOMEM; +} + +static void nf_conntrack_tstamp_fini_sysctl(struct net *net) +{ + struct ctl_table *table; + + table = net->ct.tstamp_sysctl_header->ctl_table_arg; + unregister_net_sysctl_table(net->ct.tstamp_sysctl_header); + kfree(table); +} +#else +static int nf_conntrack_tstamp_init_sysctl(struct net *net) +{ + return 0; +} + +static void nf_conntrack_tstamp_fini_sysctl(struct net *net) +{ +} +#endif + +int nf_conntrack_tstamp_init(struct net *net) +{ + int ret; + + net->ct.sysctl_tstamp = nf_ct_tstamp; + + if (net_eq(net, &init_net)) { + ret = nf_ct_extend_register(&tstamp_extend); + if (ret < 0) { + printk(KERN_ERR "nf_ct_tstamp: Unable to register " + "extension\n"); + goto out_extend_register; + } + } + + ret = nf_conntrack_tstamp_init_sysctl(net); + if (ret < 0) + goto out_sysctl; + + return 0; + +out_sysctl: + if (net_eq(net, &init_net)) + nf_ct_extend_unregister(&tstamp_extend); +out_extend_register: + return ret; +} + +void nf_conntrack_tstamp_fini(struct net *net) +{ + nf_conntrack_tstamp_fini_sysctl(net); + if (net_eq(net, &init_net)) + nf_ct_extend_unregister(&tstamp_extend); +} diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index b07393e..20c775c 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -161,7 +161,8 @@ static int seq_show(struct seq_file *s, void *v) struct nf_logger *t; int ret; - logger = nf_loggers[*pos]; + logger = rcu_dereference_protected(nf_loggers[*pos], + lockdep_is_held(&nf_log_mutex)); if (!logger) ret = seq_printf(s, "%2lld NONE (", *pos); @@ -249,7 +250,8 @@ static int nf_log_proc_dostring(ctl_table *table, int write, mutex_unlock(&nf_log_mutex); } else { mutex_lock(&nf_log_mutex); - logger = nf_loggers[tindex]; + logger = rcu_dereference_protected(nf_loggers[tindex], + lockdep_is_held(&nf_log_mutex)); if (!logger) table->data = "NONE"; else diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 74aebed..5ab22e2 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -27,14 +27,17 @@ static DEFINE_MUTEX(queue_handler_mutex); int nf_register_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh) { int ret; + const struct nf_queue_handler *old; if (pf >= ARRAY_SIZE(queue_handler)) return -EINVAL; mutex_lock(&queue_handler_mutex); - if (queue_handler[pf] == qh) + old = rcu_dereference_protected(queue_handler[pf], + lockdep_is_held(&queue_handler_mutex)); + if (old == qh) ret = -EEXIST; - else if (queue_handler[pf]) + else if (old) ret = -EBUSY; else { rcu_assign_pointer(queue_handler[pf], qh); @@ -49,11 +52,15 @@ EXPORT_SYMBOL(nf_register_queue_handler); /* The caller must flush their queue before this */ int nf_unregister_queue_handler(u_int8_t pf, const struct nf_queue_handler *qh) { + const struct nf_queue_handler *old; + if (pf >= ARRAY_SIZE(queue_handler)) return -EINVAL; mutex_lock(&queue_handler_mutex); - if (queue_handler[pf] && queue_handler[pf] != qh) { + old = rcu_dereference_protected(queue_handler[pf], + lockdep_is_held(&queue_handler_mutex)); + if (old && old != qh) { mutex_unlock(&queue_handler_mutex); return -EINVAL; } @@ -73,7 +80,10 @@ void nf_unregister_queue_handlers(const struct nf_queue_handler *qh) mutex_lock(&queue_handler_mutex); for (pf = 0; pf < ARRAY_SIZE(queue_handler); pf++) { - if (queue_handler[pf] == qh) + if (rcu_dereference_protected( + queue_handler[pf], + lockdep_is_held(&queue_handler_mutex) + ) == qh) rcu_assign_pointer(queue_handler[pf], NULL); } mutex_unlock(&queue_handler_mutex); @@ -115,7 +125,7 @@ static int __nf_queue(struct sk_buff *skb, int (*okfn)(struct sk_buff *), unsigned int queuenum) { - int status; + int status = -ENOENT; struct nf_queue_entry *entry = NULL; #ifdef CONFIG_BRIDGE_NETFILTER struct net_device *physindev; @@ -128,16 +138,20 @@ static int __nf_queue(struct sk_buff *skb, rcu_read_lock(); qh = rcu_dereference(queue_handler[pf]); - if (!qh) + if (!qh) { + status = -ESRCH; goto err_unlock; + } afinfo = nf_get_afinfo(pf); if (!afinfo) goto err_unlock; entry = kmalloc(sizeof(*entry) + afinfo->route_key_size, GFP_ATOMIC); - if (!entry) + if (!entry) { + status = -ENOMEM; goto err_unlock; + } *entry = (struct nf_queue_entry) { .skb = skb, @@ -151,11 +165,9 @@ static int __nf_queue(struct sk_buff *skb, /* If it's going away, ignore hook. */ if (!try_module_get(entry->elem->owner)) { - rcu_read_unlock(); - kfree(entry); - return 0; + status = -ECANCELED; + goto err_unlock; } - /* Bump dev refs so they don't vanish while packet is out */ if (indev) dev_hold(indev); @@ -182,14 +194,13 @@ static int __nf_queue(struct sk_buff *skb, goto err; } - return 1; + return 0; err_unlock: rcu_read_unlock(); err: - kfree_skb(skb); kfree(entry); - return 1; + return status; } int nf_queue(struct sk_buff *skb, @@ -201,6 +212,8 @@ int nf_queue(struct sk_buff *skb, unsigned int queuenum) { struct sk_buff *segs; + int err; + unsigned int queued; if (!skb_is_gso(skb)) return __nf_queue(skb, elem, pf, hook, indev, outdev, okfn, @@ -216,20 +229,35 @@ int nf_queue(struct sk_buff *skb, } segs = skb_gso_segment(skb, 0); - kfree_skb(skb); + /* Does not use PTR_ERR to limit the number of error codes that can be + * returned by nf_queue. For instance, callers rely on -ECANCELED to mean + * 'ignore this hook'. + */ if (IS_ERR(segs)) - return 1; + return -EINVAL; + queued = 0; + err = 0; do { struct sk_buff *nskb = segs->next; segs->next = NULL; - if (!__nf_queue(segs, elem, pf, hook, indev, outdev, okfn, - queuenum)) + if (err == 0) + err = __nf_queue(segs, elem, pf, hook, indev, + outdev, okfn, queuenum); + if (err == 0) + queued++; + else kfree_skb(segs); segs = nskb; } while (segs); - return 1; + + /* also free orig skb if only some segments were queued */ + if (unlikely(err && queued)) + err = 0; + if (err == 0) + kfree_skb(skb); + return err; } void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) @@ -237,6 +265,7 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) struct sk_buff *skb = entry->skb; struct list_head *elem = &entry->elem->list; const struct nf_afinfo *afinfo; + int err; rcu_read_lock(); @@ -270,10 +299,17 @@ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) local_bh_enable(); break; case NF_QUEUE: - if (!__nf_queue(skb, elem, entry->pf, entry->hook, - entry->indev, entry->outdev, entry->okfn, - verdict >> NF_VERDICT_BITS)) - goto next_hook; + err = __nf_queue(skb, elem, entry->pf, entry->hook, + entry->indev, entry->outdev, entry->okfn, + verdict >> NF_VERDICT_QBITS); + if (err < 0) { + if (err == -ECANCELED) + goto next_hook; + if (err == -ESRCH && + (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) + goto next_hook; + kfree_skb(skb); + } break; case NF_STOLEN: default: diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 6a1572b..91592da 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -874,19 +874,19 @@ static struct hlist_node *get_first(struct iter_state *st) for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) { if (!hlist_empty(&instance_table[st->bucket])) - return rcu_dereference_bh(instance_table[st->bucket].first); + return rcu_dereference_bh(hlist_first_rcu(&instance_table[st->bucket])); } return NULL; } static struct hlist_node *get_next(struct iter_state *st, struct hlist_node *h) { - h = rcu_dereference_bh(h->next); + h = rcu_dereference_bh(hlist_next_rcu(h)); while (!h) { if (++st->bucket >= INSTANCE_BUCKETS) return NULL; - h = rcu_dereference_bh(instance_table[st->bucket].first); + h = rcu_dereference_bh(hlist_first_rcu(&instance_table[st->bucket])); } return h; } diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index 68e67d1..b83123f 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -387,25 +387,31 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) { struct sk_buff *nskb; struct nfqnl_instance *queue; - int err; + int err = -ENOBUFS; /* rcu_read_lock()ed by nf_hook_slow() */ queue = instance_lookup(queuenum); - if (!queue) + if (!queue) { + err = -ESRCH; goto err_out; + } - if (queue->copy_mode == NFQNL_COPY_NONE) + if (queue->copy_mode == NFQNL_COPY_NONE) { + err = -EINVAL; goto err_out; + } nskb = nfqnl_build_packet_message(queue, entry); - if (nskb == NULL) + if (nskb == NULL) { + err = -ENOMEM; goto err_out; - + } spin_lock_bh(&queue->lock); - if (!queue->peer_pid) + if (!queue->peer_pid) { + err = -EINVAL; goto err_out_free_nskb; - + } if (queue->queue_total >= queue->queue_maxlen) { queue->queue_dropped++; if (net_ratelimit()) @@ -432,7 +438,7 @@ err_out_free_nskb: err_out_unlock: spin_unlock_bh(&queue->lock); err_out: - return -1; + return err; } static int diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index c942376..0a77d2f 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -23,6 +23,7 @@ #include <linux/mutex.h> #include <linux/mm.h> #include <linux/slab.h> +#include <linux/audit.h> #include <net/net_namespace.h> #include <linux/netfilter/x_tables.h> @@ -38,9 +39,8 @@ MODULE_DESCRIPTION("{ip,ip6,arp,eb}_tables backend module"); #define SMP_ALIGN(x) (((x) + SMP_CACHE_BYTES-1) & ~(SMP_CACHE_BYTES-1)) struct compat_delta { - struct compat_delta *next; - unsigned int offset; - int delta; + unsigned int offset; /* offset in kernel */ + int delta; /* delta in 32bit user land */ }; struct xt_af { @@ -49,7 +49,9 @@ struct xt_af { struct list_head target; #ifdef CONFIG_COMPAT struct mutex compat_mutex; - struct compat_delta *compat_offsets; + struct compat_delta *compat_tab; + unsigned int number; /* number of slots in compat_tab[] */ + unsigned int cur; /* number of used slots in compat_tab[] */ #endif }; @@ -414,54 +416,67 @@ int xt_check_match(struct xt_mtchk_param *par, EXPORT_SYMBOL_GPL(xt_check_match); #ifdef CONFIG_COMPAT -int xt_compat_add_offset(u_int8_t af, unsigned int offset, short delta) +int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta) { - struct compat_delta *tmp; + struct xt_af *xp = &xt[af]; - tmp = kmalloc(sizeof(struct compat_delta), GFP_KERNEL); - if (!tmp) - return -ENOMEM; + if (!xp->compat_tab) { + if (!xp->number) + return -EINVAL; + xp->compat_tab = vmalloc(sizeof(struct compat_delta) * xp->number); + if (!xp->compat_tab) + return -ENOMEM; + xp->cur = 0; + } - tmp->offset = offset; - tmp->delta = delta; + if (xp->cur >= xp->number) + return -EINVAL; - if (xt[af].compat_offsets) { - tmp->next = xt[af].compat_offsets->next; - xt[af].compat_offsets->next = tmp; - } else { - xt[af].compat_offsets = tmp; - tmp->next = NULL; - } + if (xp->cur) + delta += xp->compat_tab[xp->cur - 1].delta; + xp->compat_tab[xp->cur].offset = offset; + xp->compat_tab[xp->cur].delta = delta; + xp->cur++; return 0; } EXPORT_SYMBOL_GPL(xt_compat_add_offset); void xt_compat_flush_offsets(u_int8_t af) { - struct compat_delta *tmp, *next; - - if (xt[af].compat_offsets) { - for (tmp = xt[af].compat_offsets; tmp; tmp = next) { - next = tmp->next; - kfree(tmp); - } - xt[af].compat_offsets = NULL; + if (xt[af].compat_tab) { + vfree(xt[af].compat_tab); + xt[af].compat_tab = NULL; + xt[af].number = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); int xt_compat_calc_jump(u_int8_t af, unsigned int offset) { - struct compat_delta *tmp; - int delta; - - for (tmp = xt[af].compat_offsets, delta = 0; tmp; tmp = tmp->next) - if (tmp->offset < offset) - delta += tmp->delta; - return delta; + struct compat_delta *tmp = xt[af].compat_tab; + int mid, left = 0, right = xt[af].cur - 1; + + while (left <= right) { + mid = (left + right) >> 1; + if (offset > tmp[mid].offset) + left = mid + 1; + else if (offset < tmp[mid].offset) + right = mid - 1; + else + return mid ? tmp[mid - 1].delta : 0; + } + WARN_ON_ONCE(1); + return 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); +void xt_compat_init_offsets(u_int8_t af, unsigned int number) +{ + xt[af].number = number; + xt[af].cur = 0; +} +EXPORT_SYMBOL(xt_compat_init_offsets); + int xt_compat_match_offset(const struct xt_match *match) { u_int16_t csize = match->compatsize ? : match->matchsize; @@ -820,6 +835,21 @@ xt_replace_table(struct xt_table *table, */ local_bh_enable(); +#ifdef CONFIG_AUDIT + if (audit_enabled) { + struct audit_buffer *ab; + + ab = audit_log_start(current->audit_context, GFP_KERNEL, + AUDIT_NETFILTER_CFG); + if (ab) { + audit_log_format(ab, "table=%s family=%u entries=%u", + table->name, table->af, + private->number); + audit_log_end(ab); + } + } +#endif + return private; } EXPORT_SYMBOL_GPL(xt_replace_table); @@ -1338,7 +1368,7 @@ static int __init xt_init(void) mutex_init(&xt[i].mutex); #ifdef CONFIG_COMPAT mutex_init(&xt[i].compat_mutex); - xt[i].compat_offsets = NULL; + xt[i].compat_tab = NULL; #endif INIT_LIST_HEAD(&xt[i].target); INIT_LIST_HEAD(&xt[i].match); diff --git a/net/netfilter/xt_AUDIT.c b/net/netfilter/xt_AUDIT.c new file mode 100644 index 0000000..81802d2 --- /dev/null +++ b/net/netfilter/xt_AUDIT.c @@ -0,0 +1,204 @@ +/* + * Creates audit record for dropped/accepted packets + * + * (C) 2010-2011 Thomas Graf <tgraf@redhat.com> + * (C) 2010-2011 Red Hat, 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. +*/ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/audit.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/if_arp.h> +#include <linux/netfilter/x_tables.h> +#include <linux/netfilter/xt_AUDIT.h> +#include <net/ipv6.h> +#include <net/ip.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Thomas Graf <tgraf@redhat.com>"); +MODULE_DESCRIPTION("Xtables: creates audit records for dropped/accepted packets"); +MODULE_ALIAS("ipt_AUDIT"); +MODULE_ALIAS("ip6t_AUDIT"); +MODULE_ALIAS("ebt_AUDIT"); +MODULE_ALIAS("arpt_AUDIT"); + +static void audit_proto(struct audit_buffer *ab, struct sk_buff *skb, + unsigned int proto, unsigned int offset) +{ + switch (proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_UDPLITE: { + const __be16 *pptr; + __be16 _ports[2]; + + pptr = skb_header_pointer(skb, offset, sizeof(_ports), _ports); + if (pptr == NULL) { + audit_log_format(ab, " truncated=1"); + return; + } + + audit_log_format(ab, " sport=%hu dport=%hu", + ntohs(pptr[0]), ntohs(pptr[1])); + } + break; + + case IPPROTO_ICMP: + case IPPROTO_ICMPV6: { + const u8 *iptr; + u8 _ih[2]; + + iptr = skb_header_pointer(skb, offset, sizeof(_ih), &_ih); + if (iptr == NULL) { + audit_log_format(ab, " truncated=1"); + return; + } + + audit_log_format(ab, " icmptype=%hhu icmpcode=%hhu", + iptr[0], iptr[1]); + + } + break; + } +} + +static void audit_ip4(struct audit_buffer *ab, struct sk_buff *skb) +{ + struct iphdr _iph; + const struct iphdr *ih; + + ih = skb_header_pointer(skb, 0, sizeof(_iph), &_iph); + if (!ih) { + audit_log_format(ab, " truncated=1"); + return; + } + + audit_log_format(ab, " saddr=%pI4 daddr=%pI4 ipid=%hu proto=%hhu", + &ih->saddr, &ih->daddr, ntohs(ih->id), ih->protocol); + + if (ntohs(ih->frag_off) & IP_OFFSET) { + audit_log_format(ab, " frag=1"); + return; + } + + audit_proto(ab, skb, ih->protocol, ih->ihl * 4); +} + +static void audit_ip6(struct audit_buffer *ab, struct sk_buff *skb) +{ + struct ipv6hdr _ip6h; + const struct ipv6hdr *ih; + u8 nexthdr; + int offset; + + ih = skb_header_pointer(skb, skb_network_offset(skb), sizeof(_ip6h), &_ip6h); + if (!ih) { + audit_log_format(ab, " truncated=1"); + return; + } + + nexthdr = ih->nexthdr; + offset = ipv6_skip_exthdr(skb, skb_network_offset(skb) + sizeof(_ip6h), + &nexthdr); + + audit_log_format(ab, " saddr=%pI6c daddr=%pI6c proto=%hhu", + &ih->saddr, &ih->daddr, nexthdr); + + if (offset) + audit_proto(ab, skb, nexthdr, offset); +} + +static unsigned int +audit_tg(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct xt_audit_info *info = par->targinfo; + struct audit_buffer *ab; + + ab = audit_log_start(NULL, GFP_ATOMIC, AUDIT_NETFILTER_PKT); + if (ab == NULL) + goto errout; + + audit_log_format(ab, "action=%hhu hook=%u len=%u inif=%s outif=%s", + info->type, par->hooknum, skb->len, + par->in ? par->in->name : "?", + par->out ? par->out->name : "?"); + + if (skb->mark) + audit_log_format(ab, " mark=%#x", skb->mark); + + if (skb->dev && skb->dev->type == ARPHRD_ETHER) { + audit_log_format(ab, " smac=%pM dmac=%pM macproto=0x%04x", + eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, + ntohs(eth_hdr(skb)->h_proto)); + + if (par->family == NFPROTO_BRIDGE) { + switch (eth_hdr(skb)->h_proto) { + case __constant_htons(ETH_P_IP): + audit_ip4(ab, skb); + break; + + case __constant_htons(ETH_P_IPV6): + audit_ip6(ab, skb); + break; + } + } + } + + switch (par->family) { + case NFPROTO_IPV4: + audit_ip4(ab, skb); + break; + + case NFPROTO_IPV6: + audit_ip6(ab, skb); + break; + } + + audit_log_end(ab); + +errout: + return XT_CONTINUE; +} + +static int audit_tg_check(const struct xt_tgchk_param *par) +{ + const struct xt_audit_info *info = par->targinfo; + + if (info->type > XT_AUDIT_TYPE_MAX) { + pr_info("Audit type out of range (valid range: 0..%hhu)\n", + XT_AUDIT_TYPE_MAX); + return -ERANGE; + } + + return 0; +} + +static struct xt_target audit_tg_reg __read_mostly = { + .name = "AUDIT", + .family = NFPROTO_UNSPEC, + .target = audit_tg, + .targetsize = sizeof(struct xt_audit_info), + .checkentry = audit_tg_check, + .me = THIS_MODULE, +}; + +static int __init audit_tg_init(void) +{ + return xt_register_target(&audit_tg_reg); +} + +static void __exit audit_tg_exit(void) +{ + xt_unregister_target(&audit_tg_reg); +} + +module_init(audit_tg_init); +module_exit(audit_tg_exit); diff --git a/net/netfilter/xt_CLASSIFY.c b/net/netfilter/xt_CLASSIFY.c index c2c0e4a..af9c4da 100644 --- a/net/netfilter/xt_CLASSIFY.c +++ b/net/netfilter/xt_CLASSIFY.c @@ -19,12 +19,14 @@ #include <linux/netfilter_ipv6.h> #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_CLASSIFY.h> +#include <linux/netfilter_arp.h> MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Xtables: Qdisc classification"); MODULE_ALIAS("ipt_CLASSIFY"); MODULE_ALIAS("ip6t_CLASSIFY"); +MODULE_ALIAS("arpt_CLASSIFY"); static unsigned int classify_tg(struct sk_buff *skb, const struct xt_action_param *par) @@ -35,26 +37,36 @@ classify_tg(struct sk_buff *skb, const struct xt_action_param *par) return XT_CONTINUE; } -static struct xt_target classify_tg_reg __read_mostly = { - .name = "CLASSIFY", - .revision = 0, - .family = NFPROTO_UNSPEC, - .table = "mangle", - .hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | - (1 << NF_INET_POST_ROUTING), - .target = classify_tg, - .targetsize = sizeof(struct xt_classify_target_info), - .me = THIS_MODULE, +static struct xt_target classify_tg_reg[] __read_mostly = { + { + .name = "CLASSIFY", + .revision = 0, + .family = NFPROTO_UNSPEC, + .hooks = (1 << NF_INET_LOCAL_OUT) | (1 << NF_INET_FORWARD) | + (1 << NF_INET_POST_ROUTING), + .target = classify_tg, + .targetsize = sizeof(struct xt_classify_target_info), + .me = THIS_MODULE, + }, + { + .name = "CLASSIFY", + .revision = 0, + .family = NFPROTO_ARP, + .hooks = (1 << NF_ARP_OUT) | (1 << NF_ARP_FORWARD), + .target = classify_tg, + .targetsize = sizeof(struct xt_classify_target_info), + .me = THIS_MODULE, + }, }; static int __init classify_tg_init(void) { - return xt_register_target(&classify_tg_reg); + return xt_register_targets(classify_tg_reg, ARRAY_SIZE(classify_tg_reg)); } static void __exit classify_tg_exit(void) { - xt_unregister_target(&classify_tg_reg); + xt_unregister_targets(classify_tg_reg, ARRAY_SIZE(classify_tg_reg)); } module_init(classify_tg_init); diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c index be1f22e..3bdd443 100644 --- a/net/netfilter/xt_IDLETIMER.c +++ b/net/netfilter/xt_IDLETIMER.c @@ -313,3 +313,5 @@ MODULE_AUTHOR("Timo Teras <ext-timo.teras@nokia.com>"); MODULE_AUTHOR("Luciano Coelho <luciano.coelho@nokia.com>"); MODULE_DESCRIPTION("Xtables: idle time monitor"); MODULE_LICENSE("GPL v2"); +MODULE_ALIAS("ipt_IDLETIMER"); +MODULE_ALIAS("ip6t_IDLETIMER"); diff --git a/net/netfilter/xt_LED.c b/net/netfilter/xt_LED.c index a414050..993de2b 100644 --- a/net/netfilter/xt_LED.c +++ b/net/netfilter/xt_LED.c @@ -31,6 +31,8 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Adam Nielsen <a.nielsen@shikadi.net>"); MODULE_DESCRIPTION("Xtables: trigger LED devices on packet match"); +MODULE_ALIAS("ipt_LED"); +MODULE_ALIAS("ip6t_LED"); static LIST_HEAD(xt_led_triggers); static DEFINE_MUTEX(xt_led_mutex); diff --git a/net/netfilter/xt_NFQUEUE.c b/net/netfilter/xt_NFQUEUE.c index 039cce1..d4f4b5d 100644 --- a/net/netfilter/xt_NFQUEUE.c +++ b/net/netfilter/xt_NFQUEUE.c @@ -72,18 +72,31 @@ nfqueue_tg_v1(struct sk_buff *skb, const struct xt_action_param *par) if (info->queues_total > 1) { if (par->family == NFPROTO_IPV4) - queue = hash_v4(skb) % info->queues_total + queue; + queue = (((u64) hash_v4(skb) * info->queues_total) >> + 32) + queue; #if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE) else if (par->family == NFPROTO_IPV6) - queue = hash_v6(skb) % info->queues_total + queue; + queue = (((u64) hash_v6(skb) * info->queues_total) >> + 32) + queue; #endif } return NF_QUEUE_NR(queue); } -static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par) +static unsigned int +nfqueue_tg_v2(struct sk_buff *skb, const struct xt_action_param *par) { - const struct xt_NFQ_info_v1 *info = par->targinfo; + const struct xt_NFQ_info_v2 *info = par->targinfo; + unsigned int ret = nfqueue_tg_v1(skb, par); + + if (info->bypass) + ret |= NF_VERDICT_FLAG_QUEUE_BYPASS; + return ret; +} + +static int nfqueue_tg_check(const struct xt_tgchk_param *par) +{ + const struct xt_NFQ_info_v2 *info = par->targinfo; u32 maxid; if (unlikely(!rnd_inited)) { @@ -100,6 +113,8 @@ static int nfqueue_tg_v1_check(const struct xt_tgchk_param *par) info->queues_total, maxid); return -ERANGE; } + if (par->target->revision == 2 && info->bypass > 1) + return -EINVAL; return 0; } @@ -115,11 +130,20 @@ static struct xt_target nfqueue_tg_reg[] __read_mostly = { .name = "NFQUEUE", .revision = 1, .family = NFPROTO_UNSPEC, - .checkentry = nfqueue_tg_v1_check, + .checkentry = nfqueue_tg_check, .target = nfqueue_tg_v1, .targetsize = sizeof(struct xt_NFQ_info_v1), .me = THIS_MODULE, }, + { + .name = "NFQUEUE", + .revision = 2, + .family = NFPROTO_UNSPEC, + .checkentry = nfqueue_tg_check, + .target = nfqueue_tg_v2, + .targetsize = sizeof(struct xt_NFQ_info_v2), + .me = THIS_MODULE, + }, }; static int __init nfqueue_tg_init(void) diff --git a/net/netfilter/xt_connlimit.c b/net/netfilter/xt_connlimit.c index 5c5b6b9..e029c48 100644 --- a/net/netfilter/xt_connlimit.c +++ b/net/netfilter/xt_connlimit.c @@ -185,18 +185,24 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) int connections; ct = nf_ct_get(skb, &ctinfo); - if (ct != NULL) - tuple_ptr = &ct->tuplehash[0].tuple; - else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), - par->family, &tuple)) + if (ct != NULL) { + if (info->flags & XT_CONNLIMIT_DADDR) + tuple_ptr = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; + else + tuple_ptr = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + } else if (!nf_ct_get_tuplepr(skb, skb_network_offset(skb), + par->family, &tuple)) { goto hotdrop; + } if (par->family == NFPROTO_IPV6) { const struct ipv6hdr *iph = ipv6_hdr(skb); - memcpy(&addr.ip6, &iph->saddr, sizeof(iph->saddr)); + memcpy(&addr.ip6, (info->flags & XT_CONNLIMIT_DADDR) ? + &iph->daddr : &iph->saddr, sizeof(addr.ip6)); } else { const struct iphdr *iph = ip_hdr(skb); - addr.ip = iph->saddr; + addr.ip = (info->flags & XT_CONNLIMIT_DADDR) ? + iph->daddr : iph->saddr; } spin_lock_bh(&info->data->lock); @@ -204,13 +210,12 @@ connlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) &info->mask, par->family); spin_unlock_bh(&info->data->lock); - if (connections < 0) { + if (connections < 0) /* kmalloc failed, drop it entirely */ - par->hotdrop = true; - return false; - } + goto hotdrop; - return (connections > info->limit) ^ info->inverse; + return (connections > info->limit) ^ + !!(info->flags & XT_CONNLIMIT_INVERT); hotdrop: par->hotdrop = true; @@ -268,25 +273,38 @@ static void connlimit_mt_destroy(const struct xt_mtdtor_param *par) kfree(info->data); } -static struct xt_match connlimit_mt_reg __read_mostly = { - .name = "connlimit", - .revision = 0, - .family = NFPROTO_UNSPEC, - .checkentry = connlimit_mt_check, - .match = connlimit_mt, - .matchsize = sizeof(struct xt_connlimit_info), - .destroy = connlimit_mt_destroy, - .me = THIS_MODULE, +static struct xt_match connlimit_mt_reg[] __read_mostly = { + { + .name = "connlimit", + .revision = 0, + .family = NFPROTO_UNSPEC, + .checkentry = connlimit_mt_check, + .match = connlimit_mt, + .matchsize = sizeof(struct xt_connlimit_info), + .destroy = connlimit_mt_destroy, + .me = THIS_MODULE, + }, + { + .name = "connlimit", + .revision = 1, + .family = NFPROTO_UNSPEC, + .checkentry = connlimit_mt_check, + .match = connlimit_mt, + .matchsize = sizeof(struct xt_connlimit_info), + .destroy = connlimit_mt_destroy, + .me = THIS_MODULE, + }, }; static int __init connlimit_mt_init(void) { - return xt_register_match(&connlimit_mt_reg); + return xt_register_matches(connlimit_mt_reg, + ARRAY_SIZE(connlimit_mt_reg)); } static void __exit connlimit_mt_exit(void) { - xt_unregister_match(&connlimit_mt_reg); + xt_unregister_matches(connlimit_mt_reg, ARRAY_SIZE(connlimit_mt_reg)); } module_init(connlimit_mt_init); diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index e536710..4ef1b63 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -112,6 +112,54 @@ ct_proto_port_check(const struct xt_conntrack_mtinfo2 *info, return true; } +static inline bool +port_match(u16 min, u16 max, u16 port, bool invert) +{ + return (port >= min && port <= max) ^ invert; +} + +static inline bool +ct_proto_port_check_v3(const struct xt_conntrack_mtinfo3 *info, + const struct nf_conn *ct) +{ + const struct nf_conntrack_tuple *tuple; + + tuple = &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple; + if ((info->match_flags & XT_CONNTRACK_PROTO) && + (nf_ct_protonum(ct) == info->l4proto) ^ + !(info->invert_flags & XT_CONNTRACK_PROTO)) + return false; + + /* Shortcut to match all recognized protocols by using ->src.all. */ + if ((info->match_flags & XT_CONNTRACK_ORIGSRC_PORT) && + !port_match(info->origsrc_port, info->origsrc_port_high, + ntohs(tuple->src.u.all), + info->invert_flags & XT_CONNTRACK_ORIGSRC_PORT)) + return false; + + if ((info->match_flags & XT_CONNTRACK_ORIGDST_PORT) && + !port_match(info->origdst_port, info->origdst_port_high, + ntohs(tuple->dst.u.all), + info->invert_flags & XT_CONNTRACK_ORIGDST_PORT)) + return false; + + tuple = &ct->tuplehash[IP_CT_DIR_REPLY].tuple; + + if ((info->match_flags & XT_CONNTRACK_REPLSRC_PORT) && + !port_match(info->replsrc_port, info->replsrc_port_high, + ntohs(tuple->src.u.all), + info->invert_flags & XT_CONNTRACK_REPLSRC_PORT)) + return false; + + if ((info->match_flags & XT_CONNTRACK_REPLDST_PORT) && + !port_match(info->repldst_port, info->repldst_port_high, + ntohs(tuple->dst.u.all), + info->invert_flags & XT_CONNTRACK_REPLDST_PORT)) + return false; + + return true; +} + static bool conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par, u16 state_mask, u16 status_mask) @@ -170,8 +218,13 @@ conntrack_mt(const struct sk_buff *skb, struct xt_action_param *par, !(info->invert_flags & XT_CONNTRACK_REPLDST)) return false; - if (!ct_proto_port_check(info, ct)) - return false; + if (par->match->revision != 3) { + if (!ct_proto_port_check(info, ct)) + return false; + } else { + if (!ct_proto_port_check_v3(par->matchinfo, ct)) + return false; + } if ((info->match_flags & XT_CONNTRACK_STATUS) && (!!(status_mask & ct->status) ^ @@ -207,6 +260,14 @@ conntrack_mt_v2(const struct sk_buff *skb, struct xt_action_param *par) return conntrack_mt(skb, par, info->state_mask, info->status_mask); } +static bool +conntrack_mt_v3(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_conntrack_mtinfo3 *info = par->matchinfo; + + return conntrack_mt(skb, par, info->state_mask, info->status_mask); +} + static int conntrack_mt_check(const struct xt_mtchk_param *par) { int ret; @@ -244,6 +305,16 @@ static struct xt_match conntrack_mt_reg[] __read_mostly = { .destroy = conntrack_mt_destroy, .me = THIS_MODULE, }, + { + .name = "conntrack", + .revision = 3, + .family = NFPROTO_UNSPEC, + .matchsize = sizeof(struct xt_conntrack_mtinfo3), + .match = conntrack_mt_v3, + .checkentry = conntrack_mt_check, + .destroy = conntrack_mt_destroy, + .me = THIS_MODULE, + }, }; static int __init conntrack_mt_init(void) diff --git a/net/netfilter/xt_cpu.c b/net/netfilter/xt_cpu.c index b39db8a..c7a2e54 100644 --- a/net/netfilter/xt_cpu.c +++ b/net/netfilter/xt_cpu.c @@ -22,6 +22,8 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Eric Dumazet <eric.dumazet@gmail.com>"); MODULE_DESCRIPTION("Xtables: CPU match"); +MODULE_ALIAS("ipt_cpu"); +MODULE_ALIAS("ip6t_cpu"); static int cpu_mt_check(const struct xt_mtchk_param *par) { diff --git a/net/netfilter/xt_iprange.c b/net/netfilter/xt_iprange.c index 88f7c35..d3eb5ed 100644 --- a/net/netfilter/xt_iprange.c +++ b/net/netfilter/xt_iprange.c @@ -31,7 +31,7 @@ iprange_mt4(const struct sk_buff *skb, struct xt_action_param *par) pr_debug("src IP %pI4 NOT in range %s%pI4-%pI4\n", &iph->saddr, (info->flags & IPRANGE_SRC_INV) ? "(INV) " : "", - &info->src_max.ip, + &info->src_min.ip, &info->src_max.ip); return false; } @@ -78,15 +78,27 @@ iprange_mt6(const struct sk_buff *skb, struct xt_action_param *par) m = iprange_ipv6_sub(&iph->saddr, &info->src_min.in6) < 0; m |= iprange_ipv6_sub(&iph->saddr, &info->src_max.in6) > 0; m ^= !!(info->flags & IPRANGE_SRC_INV); - if (m) + if (m) { + pr_debug("src IP %pI6 NOT in range %s%pI6-%pI6\n", + &iph->saddr, + (info->flags & IPRANGE_SRC_INV) ? "(INV) " : "", + &info->src_min.in6, + &info->src_max.in6); return false; + } } if (info->flags & IPRANGE_DST) { m = iprange_ipv6_sub(&iph->daddr, &info->dst_min.in6) < 0; m |= iprange_ipv6_sub(&iph->daddr, &info->dst_max.in6) > 0; m ^= !!(info->flags & IPRANGE_DST_INV); - if (m) + if (m) { + pr_debug("dst IP %pI6 NOT in range %s%pI6-%pI6\n", + &iph->daddr, + (info->flags & IPRANGE_DST_INV) ? "(INV) " : "", + &info->dst_min.in6, + &info->dst_max.in6); return false; + } } return true; } diff --git a/net/netfilter/xt_ipvs.c b/net/netfilter/xt_ipvs.c index 9127a3d..bb10b07 100644 --- a/net/netfilter/xt_ipvs.c +++ b/net/netfilter/xt_ipvs.c @@ -85,7 +85,7 @@ ipvs_mt(const struct sk_buff *skb, struct xt_action_param *par) /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(family, skb, pp, &iph, iph.len, 1 /* inverse */); + cp = pp->conn_out_get(family, skb, &iph, iph.len, 1 /* inverse */); if (unlikely(cp == NULL)) { match = false; goto out; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 91cb1d7..c60649e 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -164,7 +164,6 @@ struct packet_mreq_max { static int packet_set_ring(struct sock *sk, struct tpacket_req *req, int closing, int tx_ring); -#define PGV_FROM_VMALLOC 1 struct pgv { char *buffer; }; @@ -523,11 +522,11 @@ static inline unsigned int run_filter(const struct sk_buff *skb, { struct sk_filter *filter; - rcu_read_lock_bh(); - filter = rcu_dereference_bh(sk->sk_filter); + rcu_read_lock(); + filter = rcu_dereference(sk->sk_filter); if (filter != NULL) res = sk_run_filter(skb, filter->insns); - rcu_read_unlock_bh(); + rcu_read_unlock(); return res; } diff --git a/net/rds/rds.h b/net/rds/rds.h index 9542449..da8adac 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -50,7 +50,6 @@ rdsdebug(char *fmt, ...) #define RDS_FRAG_SIZE ((unsigned int)(1 << RDS_FRAG_SHIFT)) #define RDS_CONG_MAP_BYTES (65536 / 8) -#define RDS_CONG_MAP_LONGS (RDS_CONG_MAP_BYTES / sizeof(unsigned long)) #define RDS_CONG_MAP_PAGES (PAGE_ALIGN(RDS_CONG_MAP_BYTES) / PAGE_SIZE) #define RDS_CONG_MAP_PAGE_BITS (PAGE_SIZE * 8) diff --git a/net/sched/Kconfig b/net/sched/Kconfig index f04d4a4..e318f45 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -205,6 +205,18 @@ config NET_SCH_DRR If unsure, say N. +config NET_SCH_MQPRIO + tristate "Multi-queue priority scheduler (MQPRIO)" + help + Say Y here if you want to use the Multi-queue Priority scheduler. + This scheduler allows QOS to be offloaded on NICs that have support + for offloading QOS schedulers. + + To compile this driver as a module, choose M here: the module will + be called sch_mqprio. + + If unsure, say N. + config NET_SCH_INGRESS tristate "Ingress Qdisc" depends on NET_CLS_ACT @@ -243,7 +255,7 @@ config NET_CLS_TCINDEX config NET_CLS_ROUTE4 tristate "Routing decision (ROUTE)" - select NET_CLS_ROUTE + select IP_ROUTE_CLASSID select NET_CLS ---help--- If you say Y here, you will be able to classify packets @@ -252,9 +264,6 @@ config NET_CLS_ROUTE4 To compile this code as a module, choose M here: the module will be called cls_route. -config NET_CLS_ROUTE - bool - config NET_CLS_FW tristate "Netfilter mark (FW)" select NET_CLS diff --git a/net/sched/Makefile b/net/sched/Makefile index 960f5db..26ce681 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -32,6 +32,7 @@ obj-$(CONFIG_NET_SCH_MULTIQ) += sch_multiq.o obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o +obj-$(CONFIG_NET_SCH_MQPRIO) += sch_mqprio.o obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o diff --git a/net/sched/act_api.c b/net/sched/act_api.c index 23b25f8..15873e1 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -78,7 +78,7 @@ static int tcf_dump_walker(struct sk_buff *skb, struct netlink_callback *cb, struct tc_action *a, struct tcf_hashinfo *hinfo) { struct tcf_common *p; - int err = 0, index = -1,i = 0, s_i = 0, n_i = 0; + int err = 0, index = -1, i = 0, s_i = 0, n_i = 0; struct nlattr *nest; read_lock_bh(hinfo->lock); @@ -126,7 +126,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, { struct tcf_common *p, *s_p; struct nlattr *nest; - int i= 0, n_i = 0; + int i = 0, n_i = 0; nest = nla_nest_start(skb, a->order); if (nest == NULL) @@ -138,7 +138,7 @@ static int tcf_del_walker(struct sk_buff *skb, struct tc_action *a, while (p != NULL) { s_p = p->tcfc_next; if (ACT_P_DELETED == tcf_hash_release(p, 0, hinfo)) - module_put(a->ops->owner); + module_put(a->ops->owner); n_i++; p = s_p; } @@ -447,7 +447,8 @@ tcf_action_dump_1(struct sk_buff *skb, struct tc_action *a, int bind, int ref) nest = nla_nest_start(skb, TCA_OPTIONS); if (nest == NULL) goto nla_put_failure; - if ((err = tcf_action_dump_old(skb, a, bind, ref)) > 0) { + err = tcf_action_dump_old(skb, a, bind, ref); + if (err > 0) { nla_nest_end(skb, nest); return err; } @@ -491,7 +492,7 @@ struct tc_action *tcf_action_init_1(struct nlattr *nla, struct nlattr *est, struct tc_action *a; struct tc_action_ops *a_o; char act_name[IFNAMSIZ]; - struct nlattr *tb[TCA_ACT_MAX+1]; + struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; int err; @@ -549,9 +550,9 @@ struct tc_action *tcf_action_init_1(struct nlattr *nla, struct nlattr *est, goto err_free; /* module count goes up only when brand new policy is created - if it exists and is only bound to in a_o->init() then - ACT_P_CREATED is not returned (a zero is). - */ + * if it exists and is only bound to in a_o->init() then + * ACT_P_CREATED is not returned (a zero is). + */ if (err != ACT_P_CREATED) module_put(a_o->owner); a->ops = a_o; @@ -569,7 +570,7 @@ err_out: struct tc_action *tcf_action_init(struct nlattr *nla, struct nlattr *est, char *name, int ovr, int bind) { - struct nlattr *tb[TCA_ACT_MAX_PRIO+1]; + struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *head = NULL, *act, *act_prev = NULL; int err; int i; @@ -697,7 +698,7 @@ act_get_notify(struct net *net, u32 pid, struct nlmsghdr *n, static struct tc_action * tcf_action_get_1(struct nlattr *nla, struct nlmsghdr *n, u32 pid) { - struct nlattr *tb[TCA_ACT_MAX+1]; + struct nlattr *tb[TCA_ACT_MAX + 1]; struct tc_action *a; int index; int err; @@ -770,7 +771,7 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, struct tcamsg *t; struct netlink_callback dcb; struct nlattr *nest; - struct nlattr *tb[TCA_ACT_MAX+1]; + struct nlattr *tb[TCA_ACT_MAX + 1]; struct nlattr *kind; struct tc_action *a = create_a(0); int err = -ENOMEM; @@ -821,7 +822,8 @@ static int tca_action_flush(struct net *net, struct nlattr *nla, nlh->nlmsg_flags |= NLM_F_ROOT; module_put(a->ops->owner); kfree(a); - err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, n->nlmsg_flags&NLM_F_ECHO); + err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); if (err > 0) return 0; @@ -842,14 +844,14 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, u32 pid, int event) { int i, ret; - struct nlattr *tb[TCA_ACT_MAX_PRIO+1]; + struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct tc_action *head = NULL, *act, *act_prev = NULL; ret = nla_parse_nested(tb, TCA_ACT_MAX_PRIO, nla, NULL); if (ret < 0) return ret; - if (event == RTM_DELACTION && n->nlmsg_flags&NLM_F_ROOT) { + if (event == RTM_DELACTION && n->nlmsg_flags & NLM_F_ROOT) { if (tb[1] != NULL) return tca_action_flush(net, tb[1], n, pid); else @@ -892,7 +894,7 @@ tca_action_gd(struct net *net, struct nlattr *nla, struct nlmsghdr *n, /* now do the delete */ tcf_action_destroy(head, 0); ret = rtnetlink_send(skb, net, pid, RTNLGRP_TC, - n->nlmsg_flags&NLM_F_ECHO); + n->nlmsg_flags & NLM_F_ECHO); if (ret > 0) return 0; return ret; @@ -936,7 +938,7 @@ static int tcf_add_notify(struct net *net, struct tc_action *a, nlh->nlmsg_len = skb_tail_pointer(skb) - b; NETLINK_CB(skb).dst_group = RTNLGRP_TC; - err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, flags&NLM_F_ECHO); + err = rtnetlink_send(skb, net, pid, RTNLGRP_TC, flags & NLM_F_ECHO); if (err > 0) err = 0; return err; @@ -967,7 +969,7 @@ tcf_action_add(struct net *net, struct nlattr *nla, struct nlmsghdr *n, /* dump then free all the actions after update; inserted policy * stays intact - * */ + */ ret = tcf_add_notify(net, act, pid, seq, RTM_NEWACTION, n->nlmsg_flags); for (a = act; a; a = act) { act = a->next; @@ -993,8 +995,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) return -EINVAL; } - /* n->nlmsg_flags&NLM_F_CREATE - * */ + /* n->nlmsg_flags & NLM_F_CREATE */ switch (n->nlmsg_type) { case RTM_NEWACTION: /* we are going to assume all other flags @@ -1003,7 +1004,7 @@ static int tc_ctl_action(struct sk_buff *skb, struct nlmsghdr *n, void *arg) * but since we want avoid ambiguity (eg when flags * is zero) then just set this */ - if (n->nlmsg_flags&NLM_F_REPLACE) + if (n->nlmsg_flags & NLM_F_REPLACE) ovr = 1; replay: ret = tcf_action_add(net, tca[TCA_ACT_TAB], n, pid, ovr); @@ -1028,7 +1029,7 @@ replay: static struct nlattr * find_dump_kind(const struct nlmsghdr *n) { - struct nlattr *tb1, *tb2[TCA_ACT_MAX+1]; + struct nlattr *tb1, *tb2[TCA_ACT_MAX + 1]; struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; struct nlattr *nla[TCAA_MAX + 1]; struct nlattr *kind; @@ -1071,9 +1072,8 @@ tc_dump_action(struct sk_buff *skb, struct netlink_callback *cb) } a_o = tc_lookup_action(kind); - if (a_o == NULL) { + if (a_o == NULL) return 0; - } memset(&a, 0, sizeof(struct tc_action)); a.ops = a_o; diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 83ddfc0..6cdf9ab 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -63,7 +63,7 @@ static int tcf_csum_init(struct nlattr *nla, struct nlattr *est, if (nla == NULL) return -EINVAL; - err = nla_parse_nested(tb, TCA_CSUM_MAX, nla,csum_policy); + err = nla_parse_nested(tb, TCA_CSUM_MAX, nla, csum_policy); if (err < 0) return err; diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index c2ed90a..2b4ab4b 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -50,7 +50,7 @@ static int gact_determ(struct tcf_gact *gact) } typedef int (*g_rand)(struct tcf_gact *gact); -static g_rand gact_rand[MAX_RAND]= { NULL, gact_net_rand, gact_determ }; +static g_rand gact_rand[MAX_RAND] = { NULL, gact_net_rand, gact_determ }; #endif /* CONFIG_GACT_PROB */ static const struct nla_policy gact_policy[TCA_GACT_MAX + 1] = { @@ -89,7 +89,7 @@ static int tcf_gact_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*gact), bind, &gact_idx_gen, &gact_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); ret = ACT_P_CREATED; } else { if (!ovr) { @@ -205,9 +205,9 @@ MODULE_LICENSE("GPL"); static int __init gact_init_module(void) { #ifdef CONFIG_GACT_PROB - printk(KERN_INFO "GACT probability on\n"); + pr_info("GACT probability on\n"); #else - printk(KERN_INFO "GACT probability NOT on\n"); + pr_info("GACT probability NOT on\n"); #endif return tcf_register_action(&act_gact_ops); } diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index c2a7c20..9fc211a 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -138,7 +138,7 @@ static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(index, est, a, sizeof(*ipt), bind, &ipt_idx_gen, &ipt_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); ret = ACT_P_CREATED; } else { if (!ovr) { @@ -162,7 +162,8 @@ static int tcf_ipt_init(struct nlattr *nla, struct nlattr *est, if (unlikely(!t)) goto err2; - if ((err = ipt_init_target(t, tname, hook)) < 0) + err = ipt_init_target(t, tname, hook); + if (err < 0) goto err3; spin_lock_bh(&ipt->tcf_lock); @@ -212,8 +213,9 @@ static int tcf_ipt(struct sk_buff *skb, struct tc_action *a, bstats_update(&ipt->tcf_bstats, skb); /* yes, we have to worry about both in and out dev - worry later - danger - this API seems to have changed - from earlier kernels */ + * worry later - danger - this API seems to have changed + * from earlier kernels + */ par.in = skb->dev; par.out = NULL; par.hooknum = ipt->tcfi_hook; @@ -253,9 +255,9 @@ static int tcf_ipt_dump(struct sk_buff *skb, struct tc_action *a, int bind, int struct tc_cnt c; /* for simple targets kernel size == user size - ** user name = target name - ** for foolproof you need to not assume this - */ + * user name = target name + * for foolproof you need to not assume this + */ t = kmemdup(ipt->tcfi_t, ipt->tcfi_t->u.user.target_size, GFP_ATOMIC); if (unlikely(!t)) diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index d765067..961386e 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -41,13 +41,13 @@ static struct tcf_hashinfo mirred_hash_info = { .lock = &mirred_lock, }; -static inline int tcf_mirred_release(struct tcf_mirred *m, int bind) +static int tcf_mirred_release(struct tcf_mirred *m, int bind) { if (m) { if (bind) m->tcf_bindcnt--; m->tcf_refcnt--; - if(!m->tcf_bindcnt && m->tcf_refcnt <= 0) { + if (!m->tcf_bindcnt && m->tcf_refcnt <= 0) { list_del(&m->tcfm_list); if (m->tcfm_dev) dev_put(m->tcfm_dev); diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index 178a4bd..762b027 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -69,7 +69,7 @@ static int tcf_nat_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, &nat_idx_gen, &nat_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); p = to_tcf_nat(pc); ret = ACT_P_CREATED; } else { diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 445bef7..50c7c06 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -70,7 +70,7 @@ static int tcf_pedit_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*p), bind, &pedit_idx_gen, &pedit_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); p = to_pedit(pc); keys = kmalloc(ksize, GFP_KERNEL); if (keys == NULL) { @@ -127,11 +127,9 @@ static int tcf_pedit(struct sk_buff *skb, struct tc_action *a, int i, munged = 0; unsigned int off; - if (skb_cloned(skb)) { - if (pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) { - return p->tcf_action; - } - } + if (skb_cloned(skb) && + pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) + return p->tcf_action; off = skb_network_offset(skb); diff --git a/net/sched/act_police.c b/net/sched/act_police.c index e2f08b1..8a16307 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -22,8 +22,8 @@ #include <net/act_api.h> #include <net/netlink.h> -#define L2T(p,L) qdisc_l2t((p)->tcfp_R_tab, L) -#define L2T_P(p,L) qdisc_l2t((p)->tcfp_P_tab, L) +#define L2T(p, L) qdisc_l2t((p)->tcfp_R_tab, L) +#define L2T_P(p, L) qdisc_l2t((p)->tcfp_P_tab, L) #define POL_TAB_MASK 15 static struct tcf_common *tcf_police_ht[POL_TAB_MASK + 1]; @@ -37,8 +37,7 @@ static struct tcf_hashinfo police_hash_info = { }; /* old policer structure from before tc actions */ -struct tc_police_compat -{ +struct tc_police_compat { u32 index; int action; u32 limit; @@ -139,7 +138,7 @@ static const struct nla_policy police_policy[TCA_POLICE_MAX + 1] = { static int tcf_act_police_locate(struct nlattr *nla, struct nlattr *est, struct tc_action *a, int ovr, int bind) { - unsigned h; + unsigned int h; int ret = 0, err; struct nlattr *tb[TCA_POLICE_MAX + 1]; struct tc_police *parm; diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 7287cff..a34a22d 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -47,7 +47,7 @@ static int tcf_simp(struct sk_buff *skb, struct tc_action *a, struct tcf_result /* print policy string followed by _ then packet count * Example if this was the 3rd packet and the string was "hello" * then it would look like "hello_3" (without quotes) - **/ + */ pr_info("simple: %s_%d\n", (char *)d->tcfd_defdata, d->tcf_bstats.packets); spin_unlock(&d->tcf_lock); @@ -125,7 +125,7 @@ static int tcf_simp_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, &simp_idx_gen, &simp_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); d = to_defact(pc); ret = alloc_defdata(d, defdata); @@ -149,7 +149,7 @@ static int tcf_simp_init(struct nlattr *nla, struct nlattr *est, return ret; } -static inline int tcf_simp_cleanup(struct tc_action *a, int bind) +static int tcf_simp_cleanup(struct tc_action *a, int bind) { struct tcf_defact *d = a->priv; @@ -158,8 +158,8 @@ static inline int tcf_simp_cleanup(struct tc_action *a, int bind) return 0; } -static inline int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, - int bind, int ref) +static int tcf_simp_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_defact *d = a->priv; diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 836f5fe..5f6f0c7 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -113,7 +113,7 @@ static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, pc = tcf_hash_create(parm->index, est, a, sizeof(*d), bind, &skbedit_idx_gen, &skbedit_hash_info); if (IS_ERR(pc)) - return PTR_ERR(pc); + return PTR_ERR(pc); d = to_skbedit(pc); ret = ACT_P_CREATED; @@ -144,7 +144,7 @@ static int tcf_skbedit_init(struct nlattr *nla, struct nlattr *est, return ret; } -static inline int tcf_skbedit_cleanup(struct tc_action *a, int bind) +static int tcf_skbedit_cleanup(struct tc_action *a, int bind) { struct tcf_skbedit *d = a->priv; @@ -153,8 +153,8 @@ static inline int tcf_skbedit_cleanup(struct tc_action *a, int bind) return 0; } -static inline int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, - int bind, int ref) +static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, + int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_skbedit *d = a->priv; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 5fd0c28..bb2c523 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -85,7 +85,7 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) int rc = -ENOENT; write_lock(&cls_mod_lock); - for (tp = &tcf_proto_base; (t=*tp) != NULL; tp = &t->next) + for (tp = &tcf_proto_base; (t = *tp) != NULL; tp = &t->next) if (t == ops) break; @@ -111,7 +111,7 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) u32 first = TC_H_MAKE(0xC0000000U, 0U); if (tp) - first = tp->prio-1; + first = tp->prio - 1; return first; } @@ -149,7 +149,8 @@ replay: if (prio == 0) { /* If no priority is given, user wants we allocated it. */ - if (n->nlmsg_type != RTM_NEWTFILTER || !(n->nlmsg_flags&NLM_F_CREATE)) + if (n->nlmsg_type != RTM_NEWTFILTER || + !(n->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; prio = TC_H_MAKE(0x80000000U, 0U); } @@ -176,7 +177,8 @@ replay: } /* Is it classful? */ - if ((cops = q->ops->cl_ops) == NULL) + cops = q->ops->cl_ops; + if (!cops) return -EINVAL; if (cops->tcf_chain == NULL) @@ -196,10 +198,11 @@ replay: goto errout; /* Check the chain for existence of proto-tcf with this priority */ - for (back = chain; (tp=*back) != NULL; back = &tp->next) { + for (back = chain; (tp = *back) != NULL; back = &tp->next) { if (tp->prio >= prio) { if (tp->prio == prio) { - if (!nprio || (tp->protocol != protocol && protocol)) + if (!nprio || + (tp->protocol != protocol && protocol)) goto errout; } else tp = NULL; @@ -216,7 +219,8 @@ replay: goto errout; err = -ENOENT; - if (n->nlmsg_type != RTM_NEWTFILTER || !(n->nlmsg_flags&NLM_F_CREATE)) + if (n->nlmsg_type != RTM_NEWTFILTER || + !(n->nlmsg_flags & NLM_F_CREATE)) goto errout; @@ -420,7 +424,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm))) return skb->len; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return skb->len; if (!tcm->tcm_parent) @@ -429,7 +434,8 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); if (!q) goto out; - if ((cops = q->ops->cl_ops) == NULL) + cops = q->ops->cl_ops; + if (!cops) goto errout; if (cops->tcf_chain == NULL) goto errout; @@ -444,8 +450,9 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) s_t = cb->args[0]; - for (tp=*chain, t=0; tp; tp = tp->next, t++) { - if (t < s_t) continue; + for (tp = *chain, t = 0; tp; tp = tp->next, t++) { + if (t < s_t) + continue; if (TC_H_MAJ(tcm->tcm_info) && TC_H_MAJ(tcm->tcm_info) != tp->prio) continue; @@ -468,10 +475,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) arg.skb = skb; arg.cb = cb; arg.w.stop = 0; - arg.w.skip = cb->args[1]-1; + arg.w.skip = cb->args[1] - 1; arg.w.count = 0; tp->ops->walk(tp, &arg.w); - cb->args[1] = arg.w.count+1; + cb->args[1] = arg.w.count + 1; if (arg.w.stop) break; } diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index f23d915..8be8872 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -21,14 +21,12 @@ #include <net/act_api.h> #include <net/pkt_cls.h> -struct basic_head -{ +struct basic_head { u32 hgenerator; struct list_head flist; }; -struct basic_filter -{ +struct basic_filter { u32 handle; struct tcf_exts exts; struct tcf_ematch_tree ematches; @@ -92,8 +90,7 @@ static int basic_init(struct tcf_proto *tp) return 0; } -static inline void basic_delete_filter(struct tcf_proto *tp, - struct basic_filter *f) +static void basic_delete_filter(struct tcf_proto *tp, struct basic_filter *f) { tcf_unbind_filter(tp, &f->res); tcf_exts_destroy(tp, &f->exts); @@ -135,9 +132,9 @@ static const struct nla_policy basic_policy[TCA_BASIC_MAX + 1] = { [TCA_BASIC_EMATCHES] = { .type = NLA_NESTED }, }; -static inline int basic_set_parms(struct tcf_proto *tp, struct basic_filter *f, - unsigned long base, struct nlattr **tb, - struct nlattr *est) +static int basic_set_parms(struct tcf_proto *tp, struct basic_filter *f, + unsigned long base, struct nlattr **tb, + struct nlattr *est) { int err = -EINVAL; struct tcf_exts e; @@ -203,7 +200,7 @@ static int basic_change(struct tcf_proto *tp, unsigned long base, u32 handle, } while (--i > 0 && basic_get(tp, head->hgenerator)); if (i <= 0) { - printk(KERN_ERR "Insufficient number of handles\n"); + pr_err("Insufficient number of handles\n"); goto errout; } diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index d49c40f..32a3351 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -56,7 +56,8 @@ static struct cgroup_subsys_state *cgrp_create(struct cgroup_subsys *ss, { struct cgroup_cls_state *cs; - if (!(cs = kzalloc(sizeof(*cs), GFP_KERNEL))) + cs = kzalloc(sizeof(*cs), GFP_KERNEL); + if (!cs) return ERR_PTR(-ENOMEM); if (cgrp->parent) @@ -94,8 +95,7 @@ static int cgrp_populate(struct cgroup_subsys *ss, struct cgroup *cgrp) return cgroup_add_files(cgrp, ss, ss_files, ARRAY_SIZE(ss_files)); } -struct cls_cgroup_head -{ +struct cls_cgroup_head { u32 handle; struct tcf_exts exts; struct tcf_ematch_tree ematches; @@ -166,7 +166,7 @@ static int cls_cgroup_change(struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, unsigned long *arg) { - struct nlattr *tb[TCA_CGROUP_MAX+1]; + struct nlattr *tb[TCA_CGROUP_MAX + 1]; struct cls_cgroup_head *head = tp->root; struct tcf_ematch_tree t; struct tcf_exts e; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 5b271a1..8ec0139 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -121,7 +121,7 @@ static u32 flow_get_proto_src(struct sk_buff *skb) if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + if (iph->frag_off & htons(IP_MF | IP_OFFSET)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && @@ -163,7 +163,7 @@ static u32 flow_get_proto_dst(struct sk_buff *skb) if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + if (iph->frag_off & htons(IP_MF | IP_OFFSET)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && @@ -276,7 +276,7 @@ fallback: static u32 flow_get_rtclassid(const struct sk_buff *skb) { -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID if (skb_dst(skb)) return skb_dst(skb)->tclassid; #endif diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 93b0a7b..26e7bc4 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -31,14 +31,12 @@ #define HTSIZE (PAGE_SIZE/sizeof(struct fw_filter *)) -struct fw_head -{ +struct fw_head { struct fw_filter *ht[HTSIZE]; u32 mask; }; -struct fw_filter -{ +struct fw_filter { struct fw_filter *next; u32 id; struct tcf_result res; @@ -53,7 +51,7 @@ static const struct tcf_ext_map fw_ext_map = { .police = TCA_FW_POLICE }; -static __inline__ int fw_hash(u32 handle) +static inline int fw_hash(u32 handle) { if (HTSIZE == 4096) return ((handle >> 24) & 0xFFF) ^ @@ -82,14 +80,14 @@ static __inline__ int fw_hash(u32 handle) static int fw_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; struct fw_filter *f; int r; u32 id = skb->mark; if (head != NULL) { id &= head->mask; - for (f=head->ht[fw_hash(id)]; f; f=f->next) { + for (f = head->ht[fw_hash(id)]; f; f = f->next) { if (f->id == id) { *res = f->res; #ifdef CONFIG_NET_CLS_IND @@ -105,7 +103,8 @@ static int fw_classify(struct sk_buff *skb, struct tcf_proto *tp, } } else { /* old method */ - if (id && (TC_H_MAJ(id) == 0 || !(TC_H_MAJ(id^tp->q->handle)))) { + if (id && (TC_H_MAJ(id) == 0 || + !(TC_H_MAJ(id ^ tp->q->handle)))) { res->classid = id; res->class = 0; return 0; @@ -117,13 +116,13 @@ static int fw_classify(struct sk_buff *skb, struct tcf_proto *tp, static unsigned long fw_get(struct tcf_proto *tp, u32 handle) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; struct fw_filter *f; if (head == NULL) return 0; - for (f=head->ht[fw_hash(handle)]; f; f=f->next) { + for (f = head->ht[fw_hash(handle)]; f; f = f->next) { if (f->id == handle) return (unsigned long)f; } @@ -139,8 +138,7 @@ static int fw_init(struct tcf_proto *tp) return 0; } -static inline void -fw_delete_filter(struct tcf_proto *tp, struct fw_filter *f) +static void fw_delete_filter(struct tcf_proto *tp, struct fw_filter *f) { tcf_unbind_filter(tp, &f->res); tcf_exts_destroy(tp, &f->exts); @@ -156,8 +154,8 @@ static void fw_destroy(struct tcf_proto *tp) if (head == NULL) return; - for (h=0; h<HTSIZE; h++) { - while ((f=head->ht[h]) != NULL) { + for (h = 0; h < HTSIZE; h++) { + while ((f = head->ht[h]) != NULL) { head->ht[h] = f->next; fw_delete_filter(tp, f); } @@ -167,14 +165,14 @@ static void fw_destroy(struct tcf_proto *tp) static int fw_delete(struct tcf_proto *tp, unsigned long arg) { - struct fw_head *head = (struct fw_head*)tp->root; - struct fw_filter *f = (struct fw_filter*)arg; + struct fw_head *head = (struct fw_head *)tp->root; + struct fw_filter *f = (struct fw_filter *)arg; struct fw_filter **fp; if (head == NULL || f == NULL) goto out; - for (fp=&head->ht[fw_hash(f->id)]; *fp; fp = &(*fp)->next) { + for (fp = &head->ht[fw_hash(f->id)]; *fp; fp = &(*fp)->next) { if (*fp == f) { tcf_tree_lock(tp); *fp = f->next; @@ -240,7 +238,7 @@ static int fw_change(struct tcf_proto *tp, unsigned long base, struct nlattr **tca, unsigned long *arg) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; struct fw_filter *f = (struct fw_filter *) *arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_FW_MAX + 1]; @@ -302,7 +300,7 @@ errout: static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) { - struct fw_head *head = (struct fw_head*)tp->root; + struct fw_head *head = (struct fw_head *)tp->root; int h; if (head == NULL) @@ -332,7 +330,7 @@ static int fw_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { struct fw_head *head = (struct fw_head *)tp->root; - struct fw_filter *f = (struct fw_filter*)fh; + struct fw_filter *f = (struct fw_filter *)fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 694dcd8..d580cdf 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -23,34 +23,30 @@ #include <net/pkt_cls.h> /* - 1. For now we assume that route tags < 256. - It allows to use direct table lookups, instead of hash tables. - 2. For now we assume that "from TAG" and "fromdev DEV" statements - are mutually exclusive. - 3. "to TAG from ANY" has higher priority, than "to ANY from XXX" + * 1. For now we assume that route tags < 256. + * It allows to use direct table lookups, instead of hash tables. + * 2. For now we assume that "from TAG" and "fromdev DEV" statements + * are mutually exclusive. + * 3. "to TAG from ANY" has higher priority, than "to ANY from XXX" */ -struct route4_fastmap -{ +struct route4_fastmap { struct route4_filter *filter; u32 id; int iif; }; -struct route4_head -{ +struct route4_head { struct route4_fastmap fastmap[16]; - struct route4_bucket *table[256+1]; + struct route4_bucket *table[256 + 1]; }; -struct route4_bucket -{ +struct route4_bucket { /* 16 FROM buckets + 16 IIF buckets + 1 wildcard bucket */ - struct route4_filter *ht[16+16+1]; + struct route4_filter *ht[16 + 16 + 1]; }; -struct route4_filter -{ +struct route4_filter { struct route4_filter *next; u32 id; int iif; @@ -61,20 +57,20 @@ struct route4_filter struct route4_bucket *bkt; }; -#define ROUTE4_FAILURE ((struct route4_filter*)(-1L)) +#define ROUTE4_FAILURE ((struct route4_filter *)(-1L)) static const struct tcf_ext_map route_ext_map = { .police = TCA_ROUTE4_POLICE, .action = TCA_ROUTE4_ACT }; -static __inline__ int route4_fastmap_hash(u32 id, int iif) +static inline int route4_fastmap_hash(u32 id, int iif) { - return id&0xF; + return id & 0xF; } -static inline -void route4_reset_fastmap(struct Qdisc *q, struct route4_head *head, u32 id) +static void +route4_reset_fastmap(struct Qdisc *q, struct route4_head *head, u32 id) { spinlock_t *root_lock = qdisc_root_sleeping_lock(q); @@ -83,32 +79,33 @@ void route4_reset_fastmap(struct Qdisc *q, struct route4_head *head, u32 id) spin_unlock_bh(root_lock); } -static inline void +static void route4_set_fastmap(struct route4_head *head, u32 id, int iif, struct route4_filter *f) { int h = route4_fastmap_hash(id, iif); + head->fastmap[h].id = id; head->fastmap[h].iif = iif; head->fastmap[h].filter = f; } -static __inline__ int route4_hash_to(u32 id) +static inline int route4_hash_to(u32 id) { - return id&0xFF; + return id & 0xFF; } -static __inline__ int route4_hash_from(u32 id) +static inline int route4_hash_from(u32 id) { - return (id>>16)&0xF; + return (id >> 16) & 0xF; } -static __inline__ int route4_hash_iif(int iif) +static inline int route4_hash_iif(int iif) { - return 16 + ((iif>>16)&0xF); + return 16 + ((iif >> 16) & 0xF); } -static __inline__ int route4_hash_wild(void) +static inline int route4_hash_wild(void) { return 32; } @@ -131,21 +128,22 @@ static __inline__ int route4_hash_wild(void) static int route4_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { - struct route4_head *head = (struct route4_head*)tp->root; + struct route4_head *head = (struct route4_head *)tp->root; struct dst_entry *dst; struct route4_bucket *b; struct route4_filter *f; u32 id, h; int iif, dont_cache = 0; - if ((dst = skb_dst(skb)) == NULL) + dst = skb_dst(skb); + if (!dst) goto failure; id = dst->tclassid; if (head == NULL) goto old_method; - iif = ((struct rtable*)dst)->fl.iif; + iif = ((struct rtable *)dst)->fl.iif; h = route4_fastmap_hash(id, iif); if (id == head->fastmap[h].id && @@ -161,7 +159,8 @@ static int route4_classify(struct sk_buff *skb, struct tcf_proto *tp, h = route4_hash_to(id); restart: - if ((b = head->table[h]) != NULL) { + b = head->table[h]; + if (b) { for (f = b->ht[route4_hash_from(id)]; f; f = f->next) if (f->id == id) ROUTE4_APPLY_RESULT(); @@ -197,8 +196,9 @@ old_method: static inline u32 to_hash(u32 id) { - u32 h = id&0xFF; - if (id&0x8000) + u32 h = id & 0xFF; + + if (id & 0x8000) h += 256; return h; } @@ -211,17 +211,17 @@ static inline u32 from_hash(u32 id) if (!(id & 0x8000)) { if (id > 255) return 256; - return id&0xF; + return id & 0xF; } - return 16 + (id&0xF); + return 16 + (id & 0xF); } static unsigned long route4_get(struct tcf_proto *tp, u32 handle) { - struct route4_head *head = (struct route4_head*)tp->root; + struct route4_head *head = (struct route4_head *)tp->root; struct route4_bucket *b; struct route4_filter *f; - unsigned h1, h2; + unsigned int h1, h2; if (!head) return 0; @@ -230,11 +230,12 @@ static unsigned long route4_get(struct tcf_proto *tp, u32 handle) if (h1 > 256) return 0; - h2 = from_hash(handle>>16); + h2 = from_hash(handle >> 16); if (h2 > 32) return 0; - if ((b = head->table[h1]) != NULL) { + b = head->table[h1]; + if (b) { for (f = b->ht[h2]; f; f = f->next) if (f->handle == handle) return (unsigned long)f; @@ -251,7 +252,7 @@ static int route4_init(struct tcf_proto *tp) return 0; } -static inline void +static void route4_delete_filter(struct tcf_proto *tp, struct route4_filter *f) { tcf_unbind_filter(tp, &f->res); @@ -267,11 +268,12 @@ static void route4_destroy(struct tcf_proto *tp) if (head == NULL) return; - for (h1=0; h1<=256; h1++) { + for (h1 = 0; h1 <= 256; h1++) { struct route4_bucket *b; - if ((b = head->table[h1]) != NULL) { - for (h2=0; h2<=32; h2++) { + b = head->table[h1]; + if (b) { + for (h2 = 0; h2 <= 32; h2++) { struct route4_filter *f; while ((f = b->ht[h2]) != NULL) { @@ -287,9 +289,9 @@ static void route4_destroy(struct tcf_proto *tp) static int route4_delete(struct tcf_proto *tp, unsigned long arg) { - struct route4_head *head = (struct route4_head*)tp->root; - struct route4_filter **fp, *f = (struct route4_filter*)arg; - unsigned h = 0; + struct route4_head *head = (struct route4_head *)tp->root; + struct route4_filter **fp, *f = (struct route4_filter *)arg; + unsigned int h = 0; struct route4_bucket *b; int i; @@ -299,7 +301,7 @@ static int route4_delete(struct tcf_proto *tp, unsigned long arg) h = f->handle; b = f->bkt; - for (fp = &b->ht[from_hash(h>>16)]; *fp; fp = &(*fp)->next) { + for (fp = &b->ht[from_hash(h >> 16)]; *fp; fp = &(*fp)->next) { if (*fp == f) { tcf_tree_lock(tp); *fp = f->next; @@ -310,7 +312,7 @@ static int route4_delete(struct tcf_proto *tp, unsigned long arg) /* Strip tree */ - for (i=0; i<=32; i++) + for (i = 0; i <= 32; i++) if (b->ht[i]) return 0; @@ -380,7 +382,8 @@ static int route4_set_parms(struct tcf_proto *tp, unsigned long base, } h1 = to_hash(nhandle); - if ((b = head->table[h1]) == NULL) { + b = head->table[h1]; + if (!b) { err = -ENOBUFS; b = kzalloc(sizeof(struct route4_bucket), GFP_KERNEL); if (b == NULL) @@ -391,6 +394,7 @@ static int route4_set_parms(struct tcf_proto *tp, unsigned long base, tcf_tree_unlock(tp); } else { unsigned int h2 = from_hash(nhandle >> 16); + err = -EEXIST; for (fp = b->ht[h2]; fp; fp = fp->next) if (fp->handle == f->handle) @@ -444,7 +448,8 @@ static int route4_change(struct tcf_proto *tp, unsigned long base, if (err < 0) return err; - if ((f = (struct route4_filter*)*arg) != NULL) { + f = (struct route4_filter *)*arg; + if (f) { if (f->handle != handle && handle) return -EINVAL; @@ -481,7 +486,7 @@ static int route4_change(struct tcf_proto *tp, unsigned long base, reinsert: h = from_hash(f->handle >> 16); - for (fp = &f->bkt->ht[h]; (f1=*fp) != NULL; fp = &f1->next) + for (fp = &f->bkt->ht[h]; (f1 = *fp) != NULL; fp = &f1->next) if (f->handle < f1->handle) break; @@ -492,7 +497,8 @@ reinsert: if (old_handle && f->handle != old_handle) { th = to_hash(old_handle); h = from_hash(old_handle >> 16); - if ((b = head->table[th]) != NULL) { + b = head->table[th]; + if (b) { for (fp = &b->ht[h]; *fp; fp = &(*fp)->next) { if (*fp == f) { *fp = f->next; @@ -515,7 +521,7 @@ errout: static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) { struct route4_head *head = tp->root; - unsigned h, h1; + unsigned int h, h1; if (head == NULL) arg->stop = 1; @@ -549,7 +555,7 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) static int route4_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct route4_filter *f = (struct route4_filter*)fh; + struct route4_filter *f = (struct route4_filter *)fh; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; u32 id; @@ -563,15 +569,15 @@ static int route4_dump(struct tcf_proto *tp, unsigned long fh, if (nest == NULL) goto nla_put_failure; - if (!(f->handle&0x8000)) { - id = f->id&0xFF; + if (!(f->handle & 0x8000)) { + id = f->id & 0xFF; NLA_PUT_U32(skb, TCA_ROUTE4_TO, id); } - if (f->handle&0x80000000) { - if ((f->handle>>16) != 0xFFFF) + if (f->handle & 0x80000000) { + if ((f->handle >> 16) != 0xFFFF) NLA_PUT_U32(skb, TCA_ROUTE4_IIF, f->iif); } else { - id = f->id>>16; + id = f->id >> 16; NLA_PUT_U32(skb, TCA_ROUTE4_FROM, id); } if (f->res.classid) diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 425a179..402c44b 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -66,28 +66,25 @@ powerful classification engine. */ -struct rsvp_head -{ +struct rsvp_head { u32 tmap[256/32]; u32 hgenerator; u8 tgenerator; struct rsvp_session *ht[256]; }; -struct rsvp_session -{ +struct rsvp_session { struct rsvp_session *next; __be32 dst[RSVP_DST_LEN]; struct tc_rsvp_gpi dpi; u8 protocol; u8 tunnelid; /* 16 (src,sport) hash slots, and one wildcard source slot */ - struct rsvp_filter *ht[16+1]; + struct rsvp_filter *ht[16 + 1]; }; -struct rsvp_filter -{ +struct rsvp_filter { struct rsvp_filter *next; __be32 src[RSVP_DST_LEN]; struct tc_rsvp_gpi spi; @@ -100,17 +97,19 @@ struct rsvp_filter struct rsvp_session *sess; }; -static __inline__ unsigned hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) +static inline unsigned int hash_dst(__be32 *dst, u8 protocol, u8 tunnelid) { - unsigned h = (__force __u32)dst[RSVP_DST_LEN-1]; + unsigned int h = (__force __u32)dst[RSVP_DST_LEN - 1]; + h ^= h>>16; h ^= h>>8; return (h ^ protocol ^ tunnelid) & 0xFF; } -static __inline__ unsigned hash_src(__be32 *src) +static inline unsigned int hash_src(__be32 *src) { - unsigned h = (__force __u32)src[RSVP_DST_LEN-1]; + unsigned int h = (__force __u32)src[RSVP_DST_LEN-1]; + h ^= h>>16; h ^= h>>8; h ^= h>>4; @@ -134,10 +133,10 @@ static struct tcf_ext_map rsvp_ext_map = { static int rsvp_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { - struct rsvp_session **sht = ((struct rsvp_head*)tp->root)->ht; + struct rsvp_session **sht = ((struct rsvp_head *)tp->root)->ht; struct rsvp_session *s; struct rsvp_filter *f; - unsigned h1, h2; + unsigned int h1, h2; __be32 *dst, *src; u8 protocol; u8 tunnelid = 0; @@ -162,13 +161,13 @@ restart: src = &nhptr->saddr.s6_addr32[0]; dst = &nhptr->daddr.s6_addr32[0]; protocol = nhptr->nexthdr; - xprt = ((u8*)nhptr) + sizeof(struct ipv6hdr); + xprt = ((u8 *)nhptr) + sizeof(struct ipv6hdr); #else src = &nhptr->saddr; dst = &nhptr->daddr; protocol = nhptr->protocol; - xprt = ((u8*)nhptr) + (nhptr->ihl<<2); - if (nhptr->frag_off & htons(IP_MF|IP_OFFSET)) + xprt = ((u8 *)nhptr) + (nhptr->ihl<<2); + if (nhptr->frag_off & htons(IP_MF | IP_OFFSET)) return -1; #endif @@ -176,10 +175,10 @@ restart: h2 = hash_src(src); for (s = sht[h1]; s; s = s->next) { - if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && + if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN - 1] && protocol == s->protocol && !(s->dpi.mask & - (*(u32*)(xprt+s->dpi.offset)^s->dpi.key)) && + (*(u32 *)(xprt + s->dpi.offset) ^ s->dpi.key)) && #if RSVP_DST_LEN == 4 dst[0] == s->dst[0] && dst[1] == s->dst[1] && @@ -188,8 +187,8 @@ restart: tunnelid == s->tunnelid) { for (f = s->ht[h2]; f; f = f->next) { - if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN-1] && - !(f->spi.mask & (*(u32*)(xprt+f->spi.offset)^f->spi.key)) + if (src[RSVP_DST_LEN-1] == f->src[RSVP_DST_LEN - 1] && + !(f->spi.mask & (*(u32 *)(xprt + f->spi.offset) ^ f->spi.key)) #if RSVP_DST_LEN == 4 && src[0] == f->src[0] && @@ -205,7 +204,7 @@ matched: return 0; tunnelid = f->res.classid; - nhptr = (void*)(xprt + f->tunnelhdr - sizeof(*nhptr)); + nhptr = (void *)(xprt + f->tunnelhdr - sizeof(*nhptr)); goto restart; } } @@ -224,11 +223,11 @@ matched: static unsigned long rsvp_get(struct tcf_proto *tp, u32 handle) { - struct rsvp_session **sht = ((struct rsvp_head*)tp->root)->ht; + struct rsvp_session **sht = ((struct rsvp_head *)tp->root)->ht; struct rsvp_session *s; struct rsvp_filter *f; - unsigned h1 = handle&0xFF; - unsigned h2 = (handle>>8)&0xFF; + unsigned int h1 = handle & 0xFF; + unsigned int h2 = (handle >> 8) & 0xFF; if (h2 > 16) return 0; @@ -258,7 +257,7 @@ static int rsvp_init(struct tcf_proto *tp) return -ENOBUFS; } -static inline void +static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) { tcf_unbind_filter(tp, &f->res); @@ -277,13 +276,13 @@ static void rsvp_destroy(struct tcf_proto *tp) sht = data->ht; - for (h1=0; h1<256; h1++) { + for (h1 = 0; h1 < 256; h1++) { struct rsvp_session *s; while ((s = sht[h1]) != NULL) { sht[h1] = s->next; - for (h2=0; h2<=16; h2++) { + for (h2 = 0; h2 <= 16; h2++) { struct rsvp_filter *f; while ((f = s->ht[h2]) != NULL) { @@ -299,13 +298,13 @@ static void rsvp_destroy(struct tcf_proto *tp) static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) { - struct rsvp_filter **fp, *f = (struct rsvp_filter*)arg; - unsigned h = f->handle; + struct rsvp_filter **fp, *f = (struct rsvp_filter *)arg; + unsigned int h = f->handle; struct rsvp_session **sp; struct rsvp_session *s = f->sess; int i; - for (fp = &s->ht[(h>>8)&0xFF]; *fp; fp = &(*fp)->next) { + for (fp = &s->ht[(h >> 8) & 0xFF]; *fp; fp = &(*fp)->next) { if (*fp == f) { tcf_tree_lock(tp); *fp = f->next; @@ -314,12 +313,12 @@ static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) /* Strip tree */ - for (i=0; i<=16; i++) + for (i = 0; i <= 16; i++) if (s->ht[i]) return 0; /* OK, session has no flows */ - for (sp = &((struct rsvp_head*)tp->root)->ht[h&0xFF]; + for (sp = &((struct rsvp_head *)tp->root)->ht[h & 0xFF]; *sp; sp = &(*sp)->next) { if (*sp == s) { tcf_tree_lock(tp); @@ -337,13 +336,14 @@ static int rsvp_delete(struct tcf_proto *tp, unsigned long arg) return 0; } -static unsigned gen_handle(struct tcf_proto *tp, unsigned salt) +static unsigned int gen_handle(struct tcf_proto *tp, unsigned salt) { struct rsvp_head *data = tp->root; int i = 0xFFFF; while (i-- > 0) { u32 h; + if ((data->hgenerator += 0x10000) == 0) data->hgenerator = 0x10000; h = data->hgenerator|salt; @@ -355,10 +355,10 @@ static unsigned gen_handle(struct tcf_proto *tp, unsigned salt) static int tunnel_bts(struct rsvp_head *data) { - int n = data->tgenerator>>5; - u32 b = 1<<(data->tgenerator&0x1F); + int n = data->tgenerator >> 5; + u32 b = 1 << (data->tgenerator & 0x1F); - if (data->tmap[n]&b) + if (data->tmap[n] & b) return 0; data->tmap[n] |= b; return 1; @@ -372,10 +372,10 @@ static void tunnel_recycle(struct rsvp_head *data) memset(tmap, 0, sizeof(tmap)); - for (h1=0; h1<256; h1++) { + for (h1 = 0; h1 < 256; h1++) { struct rsvp_session *s; for (s = sht[h1]; s; s = s->next) { - for (h2=0; h2<=16; h2++) { + for (h2 = 0; h2 <= 16; h2++) { struct rsvp_filter *f; for (f = s->ht[h2]; f; f = f->next) { @@ -395,8 +395,8 @@ static u32 gen_tunnel(struct rsvp_head *data) { int i, k; - for (k=0; k<2; k++) { - for (i=255; i>0; i--) { + for (k = 0; k < 2; k++) { + for (i = 255; i > 0; i--) { if (++data->tgenerator == 0) data->tgenerator = 1; if (tunnel_bts(data)) @@ -428,7 +428,7 @@ static int rsvp_change(struct tcf_proto *tp, unsigned long base, struct nlattr *opt = tca[TCA_OPTIONS-1]; struct nlattr *tb[TCA_RSVP_MAX + 1]; struct tcf_exts e; - unsigned h1, h2; + unsigned int h1, h2; __be32 *dst; int err; @@ -443,7 +443,8 @@ static int rsvp_change(struct tcf_proto *tp, unsigned long base, if (err < 0) return err; - if ((f = (struct rsvp_filter*)*arg) != NULL) { + f = (struct rsvp_filter *)*arg; + if (f) { /* Node exists: adjust only classid */ if (f->handle != handle && handle) @@ -500,7 +501,7 @@ static int rsvp_change(struct tcf_proto *tp, unsigned long base, goto errout; } - for (sp = &data->ht[h1]; (s=*sp) != NULL; sp = &s->next) { + for (sp = &data->ht[h1]; (s = *sp) != NULL; sp = &s->next) { if (dst[RSVP_DST_LEN-1] == s->dst[RSVP_DST_LEN-1] && pinfo && pinfo->protocol == s->protocol && memcmp(&pinfo->dpi, &s->dpi, sizeof(s->dpi)) == 0 && @@ -523,7 +524,7 @@ insert: tcf_exts_change(tp, &f->exts, &e); for (fp = &s->ht[h2]; *fp; fp = &(*fp)->next) - if (((*fp)->spi.mask&f->spi.mask) != f->spi.mask) + if (((*fp)->spi.mask & f->spi.mask) != f->spi.mask) break; f->next = *fp; wmb(); @@ -567,7 +568,7 @@ errout2: static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) { struct rsvp_head *head = tp->root; - unsigned h, h1; + unsigned int h, h1; if (arg->stop) return; @@ -598,7 +599,7 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct rsvp_filter *f = (struct rsvp_filter*)fh; + struct rsvp_filter *f = (struct rsvp_filter *)fh; struct rsvp_session *s; unsigned char *b = skb_tail_pointer(skb); struct nlattr *nest; @@ -624,7 +625,7 @@ static int rsvp_dump(struct tcf_proto *tp, unsigned long fh, NLA_PUT(skb, TCA_RSVP_PINFO, sizeof(pinfo), &pinfo); if (f->res.classid) NLA_PUT_U32(skb, TCA_RSVP_CLASSID, f->res.classid); - if (((f->handle>>8)&0xFF) != 16) + if (((f->handle >> 8) & 0xFF) != 16) NLA_PUT(skb, TCA_RSVP_SRC, sizeof(f->src), f->src); if (tcf_exts_dump(skb, &f->exts, &rsvp_ext_map) < 0) diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 20ef330..36667fa 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -249,7 +249,7 @@ tcindex_set_parms(struct tcf_proto *tp, unsigned long base, u32 handle, * of the hashing index is below the threshold. */ if ((cp.mask >> cp.shift) < PERFECT_HASH_THRESHOLD) - cp.hash = (cp.mask >> cp.shift)+1; + cp.hash = (cp.mask >> cp.shift) + 1; else cp.hash = DEFAULT_HASH_SIZE; } diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index b0c2a82..966920c 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -42,8 +42,7 @@ #include <net/act_api.h> #include <net/pkt_cls.h> -struct tc_u_knode -{ +struct tc_u_knode { struct tc_u_knode *next; u32 handle; struct tc_u_hnode *ht_up; @@ -63,19 +62,17 @@ struct tc_u_knode struct tc_u32_sel sel; }; -struct tc_u_hnode -{ +struct tc_u_hnode { struct tc_u_hnode *next; u32 handle; u32 prio; struct tc_u_common *tp_c; int refcnt; - unsigned divisor; + unsigned int divisor; struct tc_u_knode *ht[1]; }; -struct tc_u_common -{ +struct tc_u_common { struct tc_u_hnode *hlist; struct Qdisc *q; int refcnt; @@ -87,9 +84,11 @@ static const struct tcf_ext_map u32_ext_map = { .police = TCA_U32_POLICE }; -static __inline__ unsigned u32_hash_fold(__be32 key, struct tc_u32_sel *sel, u8 fshift) +static inline unsigned int u32_hash_fold(__be32 key, + const struct tc_u32_sel *sel, + u8 fshift) { - unsigned h = ntohl(key & sel->hmask)>>fshift; + unsigned int h = ntohl(key & sel->hmask) >> fshift; return h; } @@ -101,7 +100,7 @@ static int u32_classify(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_re unsigned int off; } stack[TC_U32_MAXDEPTH]; - struct tc_u_hnode *ht = (struct tc_u_hnode*)tp->root; + struct tc_u_hnode *ht = (struct tc_u_hnode *)tp->root; unsigned int off = skb_network_offset(skb); struct tc_u_knode *n; int sdepth = 0; @@ -120,7 +119,7 @@ next_knode: struct tc_u32_key *key = n->sel.keys; #ifdef CONFIG_CLS_U32_PERF - n->pf->rcnt +=1; + n->pf->rcnt += 1; j = 0; #endif @@ -133,7 +132,7 @@ next_knode: } #endif - for (i = n->sel.nkeys; i>0; i--, key++) { + for (i = n->sel.nkeys; i > 0; i--, key++) { int toff = off + key->off + (off2 & key->offmask); __be32 *data, _data; @@ -148,13 +147,13 @@ next_knode: goto next_knode; } #ifdef CONFIG_CLS_U32_PERF - n->pf->kcnts[j] +=1; + n->pf->kcnts[j] += 1; j++; #endif } if (n->ht_down == NULL) { check_terminal: - if (n->sel.flags&TC_U32_TERMINAL) { + if (n->sel.flags & TC_U32_TERMINAL) { *res = n->res; #ifdef CONFIG_NET_CLS_IND @@ -164,7 +163,7 @@ check_terminal: } #endif #ifdef CONFIG_CLS_U32_PERF - n->pf->rhit +=1; + n->pf->rhit += 1; #endif r = tcf_exts_exec(skb, &n->exts, res); if (r < 0) { @@ -197,10 +196,10 @@ check_terminal: sel = ht->divisor & u32_hash_fold(*data, &n->sel, n->fshift); } - if (!(n->sel.flags&(TC_U32_VAROFFSET|TC_U32_OFFSET|TC_U32_EAT))) + if (!(n->sel.flags & (TC_U32_VAROFFSET | TC_U32_OFFSET | TC_U32_EAT))) goto next_ht; - if (n->sel.flags&(TC_U32_OFFSET|TC_U32_VAROFFSET)) { + if (n->sel.flags & (TC_U32_OFFSET | TC_U32_VAROFFSET)) { off2 = n->sel.off + 3; if (n->sel.flags & TC_U32_VAROFFSET) { __be16 *data, _data; @@ -215,7 +214,7 @@ check_terminal: } off2 &= ~3; } - if (n->sel.flags&TC_U32_EAT) { + if (n->sel.flags & TC_U32_EAT) { off += off2; off2 = 0; } @@ -236,11 +235,11 @@ out: deadloop: if (net_ratelimit()) - printk(KERN_WARNING "cls_u32: dead loop\n"); + pr_warning("cls_u32: dead loop\n"); return -1; } -static __inline__ struct tc_u_hnode * +static struct tc_u_hnode * u32_lookup_ht(struct tc_u_common *tp_c, u32 handle) { struct tc_u_hnode *ht; @@ -252,10 +251,10 @@ u32_lookup_ht(struct tc_u_common *tp_c, u32 handle) return ht; } -static __inline__ struct tc_u_knode * +static struct tc_u_knode * u32_lookup_key(struct tc_u_hnode *ht, u32 handle) { - unsigned sel; + unsigned int sel; struct tc_u_knode *n = NULL; sel = TC_U32_HASH(handle); @@ -300,7 +299,7 @@ static u32 gen_new_htid(struct tc_u_common *tp_c) do { if (++tp_c->hgenerator == 0x7FF) tp_c->hgenerator = 1; - } while (--i>0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20)); + } while (--i > 0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20)); return i > 0 ? (tp_c->hgenerator|0x800)<<20 : 0; } @@ -378,9 +377,9 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode* key) static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht) { struct tc_u_knode *n; - unsigned h; + unsigned int h; - for (h=0; h<=ht->divisor; h++) { + for (h = 0; h <= ht->divisor; h++) { while ((n = ht->ht[h]) != NULL) { ht->ht[h] = n->next; @@ -446,13 +445,13 @@ static void u32_destroy(struct tcf_proto *tp) static int u32_delete(struct tcf_proto *tp, unsigned long arg) { - struct tc_u_hnode *ht = (struct tc_u_hnode*)arg; + struct tc_u_hnode *ht = (struct tc_u_hnode *)arg; if (ht == NULL) return 0; if (TC_U32_KEY(ht->handle)) - return u32_delete_key(tp, (struct tc_u_knode*)ht); + return u32_delete_key(tp, (struct tc_u_knode *)ht); if (tp->root == ht) return -EINVAL; @@ -470,14 +469,14 @@ static int u32_delete(struct tcf_proto *tp, unsigned long arg) static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle) { struct tc_u_knode *n; - unsigned i = 0x7FF; + unsigned int i = 0x7FF; - for (n=ht->ht[TC_U32_HASH(handle)]; n; n = n->next) + for (n = ht->ht[TC_U32_HASH(handle)]; n; n = n->next) if (i < TC_U32_NODE(n->handle)) i = TC_U32_NODE(n->handle); i++; - return handle|(i>0xFFF ? 0xFFF : i); + return handle | (i > 0xFFF ? 0xFFF : i); } static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { @@ -566,7 +565,8 @@ static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle, if (err < 0) return err; - if ((n = (struct tc_u_knode*)*arg) != NULL) { + n = (struct tc_u_knode *)*arg; + if (n) { if (TC_U32_KEY(n->handle) == 0) return -EINVAL; @@ -574,7 +574,7 @@ static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle, } if (tb[TCA_U32_DIVISOR]) { - unsigned divisor = nla_get_u32(tb[TCA_U32_DIVISOR]); + unsigned int divisor = nla_get_u32(tb[TCA_U32_DIVISOR]); if (--divisor > 0x100) return -EINVAL; @@ -585,7 +585,7 @@ static int u32_change(struct tcf_proto *tp, unsigned long base, u32 handle, if (handle == 0) return -ENOMEM; } - ht = kzalloc(sizeof(*ht) + divisor*sizeof(void*), GFP_KERNEL); + ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL); if (ht == NULL) return -ENOBUFS; ht->tp_c = tp_c; @@ -683,7 +683,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; struct tc_u_knode *n; - unsigned h; + unsigned int h; if (arg->stop) return; @@ -717,7 +717,7 @@ static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) static int u32_dump(struct tcf_proto *tp, unsigned long fh, struct sk_buff *skb, struct tcmsg *t) { - struct tc_u_knode *n = (struct tc_u_knode*)fh; + struct tc_u_knode *n = (struct tc_u_knode *)fh; struct nlattr *nest; if (n == NULL) @@ -730,8 +730,9 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; if (TC_U32_KEY(n->handle) == 0) { - struct tc_u_hnode *ht = (struct tc_u_hnode*)fh; - u32 divisor = ht->divisor+1; + struct tc_u_hnode *ht = (struct tc_u_hnode *)fh; + u32 divisor = ht->divisor + 1; + NLA_PUT_U32(skb, TCA_U32_DIVISOR, divisor); } else { NLA_PUT(skb, TCA_U32_SEL, @@ -755,7 +756,7 @@ static int u32_dump(struct tcf_proto *tp, unsigned long fh, goto nla_put_failure; #ifdef CONFIG_NET_CLS_IND - if(strlen(n->indev)) + if (strlen(n->indev)) NLA_PUT_STRING(skb, TCA_U32_INDEV, n->indev); #endif #ifdef CONFIG_CLS_U32_PERF diff --git a/net/sched/em_cmp.c b/net/sched/em_cmp.c index bc45039..1c8360a 100644 --- a/net/sched/em_cmp.c +++ b/net/sched/em_cmp.c @@ -33,40 +33,41 @@ static int em_cmp_match(struct sk_buff *skb, struct tcf_ematch *em, return 0; switch (cmp->align) { - case TCF_EM_ALIGN_U8: - val = *ptr; - break; + case TCF_EM_ALIGN_U8: + val = *ptr; + break; - case TCF_EM_ALIGN_U16: - val = get_unaligned_be16(ptr); + case TCF_EM_ALIGN_U16: + val = get_unaligned_be16(ptr); - if (cmp_needs_transformation(cmp)) - val = be16_to_cpu(val); - break; + if (cmp_needs_transformation(cmp)) + val = be16_to_cpu(val); + break; - case TCF_EM_ALIGN_U32: - /* Worth checking boundries? The branching seems - * to get worse. Visit again. */ - val = get_unaligned_be32(ptr); + case TCF_EM_ALIGN_U32: + /* Worth checking boundries? The branching seems + * to get worse. Visit again. + */ + val = get_unaligned_be32(ptr); - if (cmp_needs_transformation(cmp)) - val = be32_to_cpu(val); - break; + if (cmp_needs_transformation(cmp)) + val = be32_to_cpu(val); + break; - default: - return 0; + default: + return 0; } if (cmp->mask) val &= cmp->mask; switch (cmp->opnd) { - case TCF_EM_OPND_EQ: - return val == cmp->val; - case TCF_EM_OPND_LT: - return val < cmp->val; - case TCF_EM_OPND_GT: - return val > cmp->val; + case TCF_EM_OPND_EQ: + return val == cmp->val; + case TCF_EM_OPND_LT: + return val < cmp->val; + case TCF_EM_OPND_GT: + return val > cmp->val; } return 0; diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 34da5e2..a889d09 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -73,21 +73,18 @@ #include <net/pkt_cls.h> #include <net/sock.h> -struct meta_obj -{ +struct meta_obj { unsigned long value; unsigned int len; }; -struct meta_value -{ +struct meta_value { struct tcf_meta_val hdr; unsigned long val; unsigned int len; }; -struct meta_match -{ +struct meta_match { struct meta_value lvalue; struct meta_value rvalue; }; @@ -255,7 +252,7 @@ META_COLLECTOR(int_rtclassid) if (unlikely(skb_dst(skb) == NULL)) *err = -1; else -#ifdef CONFIG_NET_CLS_ROUTE +#ifdef CONFIG_IP_ROUTE_CLASSID dst->value = skb_dst(skb)->tclassid; #else dst->value = 0; @@ -483,8 +480,7 @@ META_COLLECTOR(int_sk_write_pend) * Meta value collectors assignment table **************************************************************************/ -struct meta_ops -{ +struct meta_ops { void (*get)(struct sk_buff *, struct tcf_pkt_info *, struct meta_value *, struct meta_obj *, int *); }; @@ -494,7 +490,7 @@ struct meta_ops /* Meta value operations table listing all meta value collectors and * assigns them to a type and meta id. */ -static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { +static struct meta_ops __meta_ops[TCF_META_TYPE_MAX + 1][TCF_META_ID_MAX + 1] = { [TCF_META_TYPE_VAR] = { [META_ID(DEV)] = META_FUNC(var_dev), [META_ID(SK_BOUND_IF)] = META_FUNC(var_sk_bound_if), @@ -550,7 +546,7 @@ static struct meta_ops __meta_ops[TCF_META_TYPE_MAX+1][TCF_META_ID_MAX+1] = { } }; -static inline struct meta_ops * meta_ops(struct meta_value *val) +static inline struct meta_ops *meta_ops(struct meta_value *val) { return &__meta_ops[meta_type(val)][meta_id(val)]; } @@ -649,9 +645,8 @@ static int meta_int_dump(struct sk_buff *skb, struct meta_value *v, int tlv) { if (v->len == sizeof(unsigned long)) NLA_PUT(skb, tlv, sizeof(unsigned long), &v->val); - else if (v->len == sizeof(u32)) { + else if (v->len == sizeof(u32)) NLA_PUT_U32(skb, tlv, v->val); - } return 0; @@ -663,8 +658,7 @@ nla_put_failure: * Type specific operations table **************************************************************************/ -struct meta_type_ops -{ +struct meta_type_ops { void (*destroy)(struct meta_value *); int (*compare)(struct meta_obj *, struct meta_obj *); int (*change)(struct meta_value *, struct nlattr *); @@ -672,7 +666,7 @@ struct meta_type_ops int (*dump)(struct sk_buff *, struct meta_value *, int); }; -static struct meta_type_ops __meta_type_ops[TCF_META_TYPE_MAX+1] = { +static struct meta_type_ops __meta_type_ops[TCF_META_TYPE_MAX + 1] = { [TCF_META_TYPE_VAR] = { .destroy = meta_var_destroy, .compare = meta_var_compare, @@ -688,7 +682,7 @@ static struct meta_type_ops __meta_type_ops[TCF_META_TYPE_MAX+1] = { } }; -static inline struct meta_type_ops * meta_type_ops(struct meta_value *v) +static inline struct meta_type_ops *meta_type_ops(struct meta_value *v) { return &__meta_type_ops[meta_type(v)]; } @@ -713,7 +707,7 @@ static int meta_get(struct sk_buff *skb, struct tcf_pkt_info *info, return err; if (meta_type_ops(v)->apply_extras) - meta_type_ops(v)->apply_extras(v, dst); + meta_type_ops(v)->apply_extras(v, dst); return 0; } @@ -732,12 +726,12 @@ static int em_meta_match(struct sk_buff *skb, struct tcf_ematch *m, r = meta_type_ops(&meta->lvalue)->compare(&l_value, &r_value); switch (meta->lvalue.hdr.op) { - case TCF_EM_OPND_EQ: - return !r; - case TCF_EM_OPND_LT: - return r < 0; - case TCF_EM_OPND_GT: - return r > 0; + case TCF_EM_OPND_EQ: + return !r; + case TCF_EM_OPND_LT: + return r < 0; + case TCF_EM_OPND_GT: + return r > 0; } return 0; @@ -771,7 +765,7 @@ static inline int meta_change_data(struct meta_value *dst, struct nlattr *nla) static inline int meta_is_supported(struct meta_value *val) { - return (!meta_id(val) || meta_ops(val)->get); + return !meta_id(val) || meta_ops(val)->get; } static const struct nla_policy meta_policy[TCA_EM_META_MAX + 1] = { diff --git a/net/sched/em_nbyte.c b/net/sched/em_nbyte.c index 1a4176a..a3bed07 100644 --- a/net/sched/em_nbyte.c +++ b/net/sched/em_nbyte.c @@ -18,8 +18,7 @@ #include <linux/tc_ematch/tc_em_nbyte.h> #include <net/pkt_cls.h> -struct nbyte_data -{ +struct nbyte_data { struct tcf_em_nbyte hdr; char pattern[0]; }; diff --git a/net/sched/em_text.c b/net/sched/em_text.c index ea8f566..15d353d 100644 --- a/net/sched/em_text.c +++ b/net/sched/em_text.c @@ -19,8 +19,7 @@ #include <linux/tc_ematch/tc_em_text.h> #include <net/pkt_cls.h> -struct text_match -{ +struct text_match { u16 from_offset; u16 to_offset; u8 from_layer; diff --git a/net/sched/em_u32.c b/net/sched/em_u32.c index 953f147..797bdb8 100644 --- a/net/sched/em_u32.c +++ b/net/sched/em_u32.c @@ -35,7 +35,7 @@ static int em_u32_match(struct sk_buff *skb, struct tcf_ematch *em, if (!tcf_valid_offset(skb, ptr, sizeof(u32))) return 0; - return !(((*(__be32*) ptr) ^ key->val) & key->mask); + return !(((*(__be32 *) ptr) ^ key->val) & key->mask); } static struct tcf_ematch_ops em_u32_ops = { diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 5e37da9..88d93eb 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -93,7 +93,7 @@ static LIST_HEAD(ematch_ops); static DEFINE_RWLOCK(ematch_mod_lock); -static inline struct tcf_ematch_ops * tcf_em_lookup(u16 kind) +static struct tcf_ematch_ops *tcf_em_lookup(u16 kind) { struct tcf_ematch_ops *e = NULL; @@ -163,8 +163,8 @@ void tcf_em_unregister(struct tcf_ematch_ops *ops) } EXPORT_SYMBOL(tcf_em_unregister); -static inline struct tcf_ematch * tcf_em_get_match(struct tcf_ematch_tree *tree, - int index) +static inline struct tcf_ematch *tcf_em_get_match(struct tcf_ematch_tree *tree, + int index) { return &tree->matches[index]; } @@ -184,7 +184,8 @@ static int tcf_em_validate(struct tcf_proto *tp, if (em_hdr->kind == TCF_EM_CONTAINER) { /* Special ematch called "container", carries an index - * referencing an external ematch sequence. */ + * referencing an external ematch sequence. + */ u32 ref; if (data_len < sizeof(ref)) @@ -195,7 +196,8 @@ static int tcf_em_validate(struct tcf_proto *tp, goto errout; /* We do not allow backward jumps to avoid loops and jumps - * to our own position are of course illegal. */ + * to our own position are of course illegal. + */ if (ref <= idx) goto errout; @@ -208,7 +210,8 @@ static int tcf_em_validate(struct tcf_proto *tp, * which automatically releases the reference again, therefore * the module MUST not be given back under any circumstances * here. Be aware, the destroy function assumes that the - * module is held if the ops field is non zero. */ + * module is held if the ops field is non zero. + */ em->ops = tcf_em_lookup(em_hdr->kind); if (em->ops == NULL) { @@ -221,7 +224,8 @@ static int tcf_em_validate(struct tcf_proto *tp, if (em->ops) { /* We dropped the RTNL mutex in order to * perform the module load. Tell the caller - * to replay the request. */ + * to replay the request. + */ module_put(em->ops->owner); err = -EAGAIN; } @@ -230,7 +234,8 @@ static int tcf_em_validate(struct tcf_proto *tp, } /* ematch module provides expected length of data, so we - * can do a basic sanity check. */ + * can do a basic sanity check. + */ if (em->ops->datalen && data_len < em->ops->datalen) goto errout; @@ -246,7 +251,8 @@ static int tcf_em_validate(struct tcf_proto *tp, * TCF_EM_SIMPLE may be specified stating that the * data only consists of a u32 integer and the module * does not expected a memory reference but rather - * the value carried. */ + * the value carried. + */ if (em_hdr->flags & TCF_EM_SIMPLE) { if (data_len < sizeof(u32)) goto errout; @@ -334,7 +340,8 @@ int tcf_em_tree_validate(struct tcf_proto *tp, struct nlattr *nla, * The array of rt attributes is parsed in the order as they are * provided, their type must be incremental from 1 to n. Even * if it does not serve any real purpose, a failure of sticking - * to this policy will result in parsing failure. */ + * to this policy will result in parsing failure. + */ for (idx = 0; nla_ok(rt_match, list_len); idx++) { err = -EINVAL; @@ -359,7 +366,8 @@ int tcf_em_tree_validate(struct tcf_proto *tp, struct nlattr *nla, /* Check if the number of matches provided by userspace actually * complies with the array of matches. The number was used for * the validation of references and a mismatch could lead to - * undefined references during the matching process. */ + * undefined references during the matching process. + */ if (idx != tree_hdr->nmatches) { err = -EINVAL; goto errout_abort; @@ -449,7 +457,7 @@ int tcf_em_tree_dump(struct sk_buff *skb, struct tcf_ematch_tree *tree, int tlv) .flags = em->flags }; - NLA_PUT(skb, i+1, sizeof(em_hdr), &em_hdr); + NLA_PUT(skb, i + 1, sizeof(em_hdr), &em_hdr); if (em->ops && em->ops->dump) { if (em->ops->dump(skb, em) < 0) @@ -478,6 +486,7 @@ static inline int tcf_em_match(struct sk_buff *skb, struct tcf_ematch *em, struct tcf_pkt_info *info) { int r = em->ops->match(skb, em, info); + return tcf_em_is_inverted(em) ? !r : r; } @@ -527,8 +536,8 @@ pop_stack: stack_overflow: if (net_ratelimit()) - printk(KERN_WARNING "tc ematch: local stack overflow," - " increase NET_EMATCH_STACK\n"); + pr_warning("tc ematch: local stack overflow," + " increase NET_EMATCH_STACK\n"); return -1; } EXPORT_SYMBOL(__tcf_em_tree_match); diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index b22ca2d..1507415 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -187,7 +187,7 @@ int unregister_qdisc(struct Qdisc_ops *qops) int err = -ENOENT; write_lock(&qdisc_mod_lock); - for (qp = &qdisc_base; (q=*qp)!=NULL; qp = &q->next) + for (qp = &qdisc_base; (q = *qp) != NULL; qp = &q->next) if (q == qops) break; if (q) { @@ -321,7 +321,9 @@ void qdisc_put_rtab(struct qdisc_rate_table *tab) if (!tab || --tab->refcnt) return; - for (rtabp = &qdisc_rtab_list; (rtab=*rtabp) != NULL; rtabp = &rtab->next) { + for (rtabp = &qdisc_rtab_list; + (rtab = *rtabp) != NULL; + rtabp = &rtab->next) { if (rtab == tab) { *rtabp = rtab->next; kfree(rtab); @@ -396,6 +398,11 @@ static struct qdisc_size_table *qdisc_get_stab(struct nlattr *opt) return stab; } +static void stab_kfree_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct qdisc_size_table, rcu)); +} + void qdisc_put_stab(struct qdisc_size_table *tab) { if (!tab) @@ -405,7 +412,7 @@ void qdisc_put_stab(struct qdisc_size_table *tab) if (--tab->refcnt == 0) { list_del(&tab->list); - kfree(tab); + call_rcu_bh(&tab->rcu, stab_kfree_rcu); } spin_unlock(&qdisc_stab_lock); @@ -428,7 +435,7 @@ nla_put_failure: return -1; } -void qdisc_calculate_pkt_len(struct sk_buff *skb, struct qdisc_size_table *stab) +void __qdisc_calculate_pkt_len(struct sk_buff *skb, const struct qdisc_size_table *stab) { int pkt_len, slot; @@ -454,14 +461,13 @@ out: pkt_len = 1; qdisc_skb_cb(skb)->pkt_len = pkt_len; } -EXPORT_SYMBOL(qdisc_calculate_pkt_len); +EXPORT_SYMBOL(__qdisc_calculate_pkt_len); void qdisc_warn_nonwc(char *txt, struct Qdisc *qdisc) { if (!(qdisc->flags & TCQ_F_WARN_NONWC)) { - printk(KERN_WARNING - "%s: %s qdisc %X: is non-work-conserving?\n", - txt, qdisc->ops->id, qdisc->handle >> 16); + pr_warn("%s: %s qdisc %X: is non-work-conserving?\n", + txt, qdisc->ops->id, qdisc->handle >> 16); qdisc->flags |= TCQ_F_WARN_NONWC; } } @@ -472,7 +478,7 @@ static enum hrtimer_restart qdisc_watchdog(struct hrtimer *timer) struct qdisc_watchdog *wd = container_of(timer, struct qdisc_watchdog, timer); - wd->qdisc->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(wd->qdisc); __netif_schedule(qdisc_root(wd->qdisc)); return HRTIMER_NORESTART; @@ -494,7 +500,7 @@ void qdisc_watchdog_schedule(struct qdisc_watchdog *wd, psched_time_t expires) &qdisc_root_sleeping(wd->qdisc)->state)) return; - wd->qdisc->flags |= TCQ_F_THROTTLED; + qdisc_throttled(wd->qdisc); time = ktime_set(0, 0); time = ktime_add_ns(time, PSCHED_TICKS2NS(expires)); hrtimer_start(&wd->timer, time, HRTIMER_MODE_ABS); @@ -504,7 +510,7 @@ EXPORT_SYMBOL(qdisc_watchdog_schedule); void qdisc_watchdog_cancel(struct qdisc_watchdog *wd) { hrtimer_cancel(&wd->timer); - wd->qdisc->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(wd->qdisc); } EXPORT_SYMBOL(qdisc_watchdog_cancel); @@ -625,7 +631,7 @@ static u32 qdisc_alloc_handle(struct net_device *dev) autohandle = TC_H_MAKE(0x80000000U, 0); } while (qdisc_lookup(dev, autohandle) && --i > 0); - return i>0 ? autohandle : 0; + return i > 0 ? autohandle : 0; } void qdisc_tree_decrease_qlen(struct Qdisc *sch, unsigned int n) @@ -834,7 +840,7 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue, err = PTR_ERR(stab); goto err_out4; } - sch->stab = stab; + rcu_assign_pointer(sch->stab, stab); } if (tca[TCA_RATE]) { spinlock_t *root_lock; @@ -874,7 +880,7 @@ err_out4: * Any broken qdiscs that would require a ops->reset() here? * The qdisc was never in action so it shouldn't be necessary. */ - qdisc_put_stab(sch->stab); + qdisc_put_stab(rtnl_dereference(sch->stab)); if (ops->destroy) ops->destroy(sch); goto err_out3; @@ -882,7 +888,7 @@ err_out4: static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) { - struct qdisc_size_table *stab = NULL; + struct qdisc_size_table *ostab, *stab = NULL; int err = 0; if (tca[TCA_OPTIONS]) { @@ -899,8 +905,9 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca) return PTR_ERR(stab); } - qdisc_put_stab(sch->stab); - sch->stab = stab; + ostab = rtnl_dereference(sch->stab); + rcu_assign_pointer(sch->stab, stab); + qdisc_put_stab(ostab); if (tca[TCA_RATE]) { /* NB: ignores errors from replace_estimator @@ -915,9 +922,8 @@ out: return 0; } -struct check_loop_arg -{ - struct qdisc_walker w; +struct check_loop_arg { + struct qdisc_walker w; struct Qdisc *p; int depth; }; @@ -970,7 +976,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) struct Qdisc *p = NULL; int err; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return -ENODEV; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -980,12 +987,12 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) if (clid) { if (clid != TC_H_ROOT) { if (TC_H_MAJ(clid) != TC_H_MAJ(TC_H_INGRESS)) { - if ((p = qdisc_lookup(dev, TC_H_MAJ(clid))) == NULL) + p = qdisc_lookup(dev, TC_H_MAJ(clid)); + if (!p) return -ENOENT; q = qdisc_leaf(p, clid); - } else { /* ingress */ - if (dev_ingress_queue(dev)) - q = dev_ingress_queue(dev)->qdisc_sleeping; + } else if (dev_ingress_queue(dev)) { + q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = dev->qdisc; @@ -996,7 +1003,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) if (tcm->tcm_handle && q->handle != tcm->tcm_handle) return -EINVAL; } else { - if ((q = qdisc_lookup(dev, tcm->tcm_handle)) == NULL) + q = qdisc_lookup(dev, tcm->tcm_handle); + if (!q) return -ENOENT; } @@ -1008,7 +1016,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) return -EINVAL; if (q->handle == 0) return -ENOENT; - if ((err = qdisc_graft(dev, p, skb, n, clid, NULL, q)) != 0) + err = qdisc_graft(dev, p, skb, n, clid, NULL, q); + if (err != 0) return err; } else { qdisc_notify(net, skb, n, clid, NULL, q); @@ -1017,7 +1026,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) } /* - Create/change qdisc. + * Create/change qdisc. */ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, void *arg) @@ -1036,7 +1045,8 @@ replay: clid = tcm->tcm_parent; q = p = NULL; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return -ENODEV; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -1046,12 +1056,12 @@ replay: if (clid) { if (clid != TC_H_ROOT) { if (clid != TC_H_INGRESS) { - if ((p = qdisc_lookup(dev, TC_H_MAJ(clid))) == NULL) + p = qdisc_lookup(dev, TC_H_MAJ(clid)); + if (!p) return -ENOENT; q = qdisc_leaf(p, clid); - } else { /* ingress */ - if (dev_ingress_queue_create(dev)) - q = dev_ingress_queue(dev)->qdisc_sleeping; + } else if (dev_ingress_queue_create(dev)) { + q = dev_ingress_queue(dev)->qdisc_sleeping; } } else { q = dev->qdisc; @@ -1063,13 +1073,14 @@ replay: if (!q || !tcm->tcm_handle || q->handle != tcm->tcm_handle) { if (tcm->tcm_handle) { - if (q && !(n->nlmsg_flags&NLM_F_REPLACE)) + if (q && !(n->nlmsg_flags & NLM_F_REPLACE)) return -EEXIST; if (TC_H_MIN(tcm->tcm_handle)) return -EINVAL; - if ((q = qdisc_lookup(dev, tcm->tcm_handle)) == NULL) + q = qdisc_lookup(dev, tcm->tcm_handle); + if (!q) goto create_n_graft; - if (n->nlmsg_flags&NLM_F_EXCL) + if (n->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) return -EINVAL; @@ -1079,7 +1090,7 @@ replay: atomic_inc(&q->refcnt); goto graft; } else { - if (q == NULL) + if (!q) goto create_n_graft; /* This magic test requires explanation. @@ -1101,9 +1112,9 @@ replay: * For now we select create/graft, if * user gave KIND, which does not match existing. */ - if ((n->nlmsg_flags&NLM_F_CREATE) && - (n->nlmsg_flags&NLM_F_REPLACE) && - ((n->nlmsg_flags&NLM_F_EXCL) || + if ((n->nlmsg_flags & NLM_F_CREATE) && + (n->nlmsg_flags & NLM_F_REPLACE) && + ((n->nlmsg_flags & NLM_F_EXCL) || (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)))) goto create_n_graft; @@ -1118,7 +1129,7 @@ replay: /* Change qdisc parameters */ if (q == NULL) return -ENOENT; - if (n->nlmsg_flags&NLM_F_EXCL) + if (n->nlmsg_flags & NLM_F_EXCL) return -EEXIST; if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], q->ops->id)) return -EINVAL; @@ -1128,7 +1139,7 @@ replay: return err; create_n_graft: - if (!(n->nlmsg_flags&NLM_F_CREATE)) + if (!(n->nlmsg_flags & NLM_F_CREATE)) return -ENOENT; if (clid == TC_H_INGRESS) { if (dev_ingress_queue(dev)) @@ -1175,6 +1186,7 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, struct nlmsghdr *nlh; unsigned char *b = skb_tail_pointer(skb); struct gnet_dump d; + struct qdisc_size_table *stab; nlh = NLMSG_NEW(skb, pid, seq, event, sizeof(*tcm), flags); tcm = NLMSG_DATA(nlh); @@ -1190,7 +1202,8 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid, goto nla_put_failure; q->qstats.qlen = q->q.qlen; - if (q->stab && qdisc_dump_stab(skb, q->stab) < 0) + stab = rtnl_dereference(q->stab); + if (stab && qdisc_dump_stab(skb, stab) < 0) goto nla_put_failure; if (gnet_stats_start_copy_compat(skb, TCA_STATS2, TCA_STATS, TCA_XSTATS, @@ -1234,16 +1247,19 @@ static int qdisc_notify(struct net *net, struct sk_buff *oskb, return -ENOBUFS; if (old && !tc_qdisc_dump_ignore(old)) { - if (tc_fill_qdisc(skb, old, clid, pid, n->nlmsg_seq, 0, RTM_DELQDISC) < 0) + if (tc_fill_qdisc(skb, old, clid, pid, n->nlmsg_seq, + 0, RTM_DELQDISC) < 0) goto err_out; } if (new && !tc_qdisc_dump_ignore(new)) { - if (tc_fill_qdisc(skb, new, clid, pid, n->nlmsg_seq, old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) + if (tc_fill_qdisc(skb, new, clid, pid, n->nlmsg_seq, + old ? NLM_F_REPLACE : 0, RTM_NEWQDISC) < 0) goto err_out; } if (skb->len) - return rtnetlink_send(skb, net, pid, RTNLGRP_TC, n->nlmsg_flags&NLM_F_ECHO); + return rtnetlink_send(skb, net, pid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); err_out: kfree_skb(skb); @@ -1275,7 +1291,7 @@ static int tc_dump_qdisc_root(struct Qdisc *root, struct sk_buff *skb, q_idx++; continue; } - if (!tc_qdisc_dump_ignore(q) && + if (!tc_qdisc_dump_ignore(q) && tc_fill_qdisc(skb, q, q->parent, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWQDISC) <= 0) goto done; @@ -1356,7 +1372,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) u32 qid = TC_H_MAJ(clid); int err; - if ((dev = __dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = __dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return -ENODEV; err = nlmsg_parse(n, sizeof(*tcm), tca, TCA_MAX, NULL); @@ -1391,9 +1408,9 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) qid = dev->qdisc->handle; /* Now qid is genuine qdisc handle consistent - both with parent and child. - - TC_H_MAJ(pid) still may be unspecified, complete it now. + * both with parent and child. + * + * TC_H_MAJ(pid) still may be unspecified, complete it now. */ if (pid) pid = TC_H_MAKE(qid, pid); @@ -1403,7 +1420,8 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) } /* OK. Locate qdisc */ - if ((q = qdisc_lookup(dev, qid)) == NULL) + q = qdisc_lookup(dev, qid); + if (!q) return -ENOENT; /* An check that it supports classes */ @@ -1423,13 +1441,14 @@ static int tc_ctl_tclass(struct sk_buff *skb, struct nlmsghdr *n, void *arg) if (cl == 0) { err = -ENOENT; - if (n->nlmsg_type != RTM_NEWTCLASS || !(n->nlmsg_flags&NLM_F_CREATE)) + if (n->nlmsg_type != RTM_NEWTCLASS || + !(n->nlmsg_flags & NLM_F_CREATE)) goto out; } else { switch (n->nlmsg_type) { case RTM_NEWTCLASS: err = -EEXIST; - if (n->nlmsg_flags&NLM_F_EXCL) + if (n->nlmsg_flags & NLM_F_EXCL) goto out; break; case RTM_DELTCLASS: @@ -1521,14 +1540,14 @@ static int tclass_notify(struct net *net, struct sk_buff *oskb, return -EINVAL; } - return rtnetlink_send(skb, net, pid, RTNLGRP_TC, n->nlmsg_flags&NLM_F_ECHO); + return rtnetlink_send(skb, net, pid, RTNLGRP_TC, + n->nlmsg_flags & NLM_F_ECHO); } -struct qdisc_dump_args -{ - struct qdisc_walker w; - struct sk_buff *skb; - struct netlink_callback *cb; +struct qdisc_dump_args { + struct qdisc_walker w; + struct sk_buff *skb; + struct netlink_callback *cb; }; static int qdisc_class_dump(struct Qdisc *q, unsigned long cl, struct qdisc_walker *arg) @@ -1590,7 +1609,7 @@ static int tc_dump_tclass_root(struct Qdisc *root, struct sk_buff *skb, static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) { - struct tcmsg *tcm = (struct tcmsg*)NLMSG_DATA(cb->nlh); + struct tcmsg *tcm = (struct tcmsg *)NLMSG_DATA(cb->nlh); struct net *net = sock_net(skb->sk); struct netdev_queue *dev_queue; struct net_device *dev; @@ -1598,7 +1617,8 @@ static int tc_dump_tclass(struct sk_buff *skb, struct netlink_callback *cb) if (cb->nlh->nlmsg_len < NLMSG_LENGTH(sizeof(*tcm))) return 0; - if ((dev = dev_get_by_index(net, tcm->tcm_ifindex)) == NULL) + dev = dev_get_by_index(net, tcm->tcm_ifindex); + if (!dev) return 0; s_t = cb->args[0]; @@ -1621,19 +1641,22 @@ done: } /* Main classifier routine: scans classifier chain attached - to this qdisc, (optionally) tests for protocol and asks - specific classifiers. + * to this qdisc, (optionally) tests for protocol and asks + * specific classifiers. */ int tc_classify_compat(struct sk_buff *skb, struct tcf_proto *tp, struct tcf_result *res) { __be16 protocol = skb->protocol; - int err = 0; + int err; for (; tp; tp = tp->next) { - if ((tp->protocol == protocol || - tp->protocol == htons(ETH_P_ALL)) && - (err = tp->classify(skb, tp, res)) >= 0) { + if (tp->protocol != protocol && + tp->protocol != htons(ETH_P_ALL)) + continue; + err = tp->classify(skb, tp, res); + + if (err >= 0) { #ifdef CONFIG_NET_CLS_ACT if (err != TC_ACT_RECLASSIFY && skb->tc_verd) skb->tc_verd = SET_TC_VERD(skb->tc_verd, 0); @@ -1664,11 +1687,11 @@ reclassify: if (verd++ >= MAX_REC_LOOP) { if (net_ratelimit()) - printk(KERN_NOTICE - "%s: packet reclassify loop" + pr_notice("%s: packet reclassify loop" " rule prio %u protocol %02x\n", - tp->q->ops->id, - tp->prio & 0xffff, ntohs(tp->protocol)); + tp->q->ops->id, + tp->prio & 0xffff, + ntohs(tp->protocol)); return TC_ACT_SHOT; } skb->tc_verd = SET_TC_VERD(skb->tc_verd, verd); @@ -1761,7 +1784,7 @@ static int __init pktsched_init(void) err = register_pernet_subsys(&psched_net_ops); if (err) { - printk(KERN_ERR "pktsched_init: " + pr_err("pktsched_init: " "cannot initialize per netns operations\n"); return err; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index 943d733..3f08158 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -319,7 +319,7 @@ static int atm_tc_delete(struct Qdisc *sch, unsigned long arg) * creation), and one for the reference held when calling delete. */ if (flow->ref < 2) { - printk(KERN_ERR "atm_tc_delete: flow->ref == %d\n", flow->ref); + pr_err("atm_tc_delete: flow->ref == %d\n", flow->ref); return -EINVAL; } if (flow->ref > 2) @@ -384,12 +384,12 @@ static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch) } } flow = NULL; - done: - ; +done: + ; } - if (!flow) + if (!flow) { flow = &p->link; - else { + } else { if (flow->vcc) ATM_SKB(skb)->atm_options = flow->vcc->atm_options; /*@@@ looks good ... but it's not supposed to work :-) */ @@ -576,8 +576,7 @@ static void atm_tc_destroy(struct Qdisc *sch) list_for_each_entry_safe(flow, tmp, &p->flows, list) { if (flow->ref > 1) - printk(KERN_ERR "atm_destroy: %p->ref = %d\n", flow, - flow->ref); + pr_err("atm_destroy: %p->ref = %d\n", flow, flow->ref); atm_tc_put(sch, (unsigned long)flow); } tasklet_kill(&p->task); @@ -616,9 +615,8 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, } if (flow->excess) NLA_PUT_U32(skb, TCA_ATM_EXCESS, flow->classid); - else { + else NLA_PUT_U32(skb, TCA_ATM_EXCESS, 0); - } nla_nest_end(skb, nest); return skb->len; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 5f63ec5..24d94c0 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -72,8 +72,7 @@ struct cbq_sched_data; -struct cbq_class -{ +struct cbq_class { struct Qdisc_class_common common; struct cbq_class *next_alive; /* next class with backlog in this priority band */ @@ -139,19 +138,18 @@ struct cbq_class int refcnt; int filters; - struct cbq_class *defaults[TC_PRIO_MAX+1]; + struct cbq_class *defaults[TC_PRIO_MAX + 1]; }; -struct cbq_sched_data -{ +struct cbq_sched_data { struct Qdisc_class_hash clhash; /* Hash table of all classes */ - int nclasses[TC_CBQ_MAXPRIO+1]; - unsigned quanta[TC_CBQ_MAXPRIO+1]; + int nclasses[TC_CBQ_MAXPRIO + 1]; + unsigned int quanta[TC_CBQ_MAXPRIO + 1]; struct cbq_class link; - unsigned activemask; - struct cbq_class *active[TC_CBQ_MAXPRIO+1]; /* List of all classes + unsigned int activemask; + struct cbq_class *active[TC_CBQ_MAXPRIO + 1]; /* List of all classes with backlog */ #ifdef CONFIG_NET_CLS_ACT @@ -162,7 +160,7 @@ struct cbq_sched_data int tx_len; psched_time_t now; /* Cached timestamp */ psched_time_t now_rt; /* Cached real time */ - unsigned pmask; + unsigned int pmask; struct hrtimer delay_timer; struct qdisc_watchdog watchdog; /* Watchdog timer, @@ -175,9 +173,9 @@ struct cbq_sched_data }; -#define L2T(cl,len) qdisc_l2t((cl)->R_tab,len) +#define L2T(cl, len) qdisc_l2t((cl)->R_tab, len) -static __inline__ struct cbq_class * +static inline struct cbq_class * cbq_class_lookup(struct cbq_sched_data *q, u32 classid) { struct Qdisc_class_common *clc; @@ -193,25 +191,27 @@ cbq_class_lookup(struct cbq_sched_data *q, u32 classid) static struct cbq_class * cbq_reclassify(struct sk_buff *skb, struct cbq_class *this) { - struct cbq_class *cl, *new; + struct cbq_class *cl; - for (cl = this->tparent; cl; cl = cl->tparent) - if ((new = cl->defaults[TC_PRIO_BESTEFFORT]) != NULL && new != this) - return new; + for (cl = this->tparent; cl; cl = cl->tparent) { + struct cbq_class *new = cl->defaults[TC_PRIO_BESTEFFORT]; + if (new != NULL && new != this) + return new; + } return NULL; } #endif /* Classify packet. The procedure is pretty complicated, but - it allows us to combine link sharing and priority scheduling - transparently. - - Namely, you can put link sharing rules (f.e. route based) at root of CBQ, - so that it resolves to split nodes. Then packets are classified - by logical priority, or a more specific classifier may be attached - to the split node. + * it allows us to combine link sharing and priority scheduling + * transparently. + * + * Namely, you can put link sharing rules (f.e. route based) at root of CBQ, + * so that it resolves to split nodes. Then packets are classified + * by logical priority, or a more specific classifier may be attached + * to the split node. */ static struct cbq_class * @@ -227,7 +227,7 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) /* * Step 1. If skb->priority points to one of our classes, use it. */ - if (TC_H_MAJ(prio^sch->handle) == 0 && + if (TC_H_MAJ(prio ^ sch->handle) == 0 && (cl = cbq_class_lookup(q, prio)) != NULL) return cl; @@ -243,10 +243,11 @@ cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) (result = tc_classify_compat(skb, head->filter_list, &res)) < 0) goto fallback; - if ((cl = (void*)res.class) == NULL) { + cl = (void *)res.class; + if (!cl) { if (TC_H_MAJ(res.classid)) cl = cbq_class_lookup(q, res.classid); - else if ((cl = defmap[res.classid&TC_PRIO_MAX]) == NULL) + else if ((cl = defmap[res.classid & TC_PRIO_MAX]) == NULL) cl = defmap[TC_PRIO_BESTEFFORT]; if (cl == NULL || cl->level >= head->level) @@ -282,7 +283,7 @@ fallback: * Step 4. No success... */ if (TC_H_MAJ(prio) == 0 && - !(cl = head->defaults[prio&TC_PRIO_MAX]) && + !(cl = head->defaults[prio & TC_PRIO_MAX]) && !(cl = head->defaults[TC_PRIO_BESTEFFORT])) return head; @@ -290,12 +291,12 @@ fallback: } /* - A packet has just been enqueued on the empty class. - cbq_activate_class adds it to the tail of active class list - of its priority band. + * A packet has just been enqueued on the empty class. + * cbq_activate_class adds it to the tail of active class list + * of its priority band. */ -static __inline__ void cbq_activate_class(struct cbq_class *cl) +static inline void cbq_activate_class(struct cbq_class *cl) { struct cbq_sched_data *q = qdisc_priv(cl->qdisc); int prio = cl->cpriority; @@ -314,9 +315,9 @@ static __inline__ void cbq_activate_class(struct cbq_class *cl) } /* - Unlink class from active chain. - Note that this same procedure is done directly in cbq_dequeue* - during round-robin procedure. + * Unlink class from active chain. + * Note that this same procedure is done directly in cbq_dequeue* + * during round-robin procedure. */ static void cbq_deactivate_class(struct cbq_class *this) @@ -350,7 +351,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) { int toplevel = q->toplevel; - if (toplevel > cl->level && !(cl->q->flags&TCQ_F_THROTTLED)) { + if (toplevel > cl->level && !(qdisc_is_throttled(cl->q))) { psched_time_t now; psched_tdiff_t incr; @@ -363,7 +364,7 @@ cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) q->toplevel = cl->level; return; } - } while ((cl=cl->borrow) != NULL && toplevel > cl->level); + } while ((cl = cl->borrow) != NULL && toplevel > cl->level); } } @@ -417,11 +418,11 @@ static void cbq_ovl_classic(struct cbq_class *cl) delay += cl->offtime; /* - Class goes to sleep, so that it will have no - chance to work avgidle. Let's forgive it 8) - - BTW cbq-2.0 has a crap in this - place, apparently they forgot to shift it by cl->ewma_log. + * Class goes to sleep, so that it will have no + * chance to work avgidle. Let's forgive it 8) + * + * BTW cbq-2.0 has a crap in this + * place, apparently they forgot to shift it by cl->ewma_log. */ if (cl->avgidle < 0) delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log); @@ -438,8 +439,8 @@ static void cbq_ovl_classic(struct cbq_class *cl) q->wd_expires = delay; /* Dirty work! We must schedule wakeups based on - real available rate, rather than leaf rate, - which may be tiny (even zero). + * real available rate, rather than leaf rate, + * which may be tiny (even zero). */ if (q->toplevel == TC_CBQ_MAXLEVEL) { struct cbq_class *b; @@ -459,7 +460,7 @@ static void cbq_ovl_classic(struct cbq_class *cl) } /* TC_CBQ_OVL_RCLASSIC: penalize by offtime classes in hierarchy, when - they go overlimit + * they go overlimit */ static void cbq_ovl_rclassic(struct cbq_class *cl) @@ -594,7 +595,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) struct Qdisc *sch = q->watchdog.qdisc; psched_time_t now; psched_tdiff_t delay = 0; - unsigned pmask; + unsigned int pmask; now = psched_get_time(); @@ -623,7 +624,7 @@ static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS); } - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); __netif_schedule(qdisc_root(sch)); return HRTIMER_NORESTART; } @@ -663,15 +664,15 @@ static int cbq_reshape_fail(struct sk_buff *skb, struct Qdisc *child) #endif /* - It is mission critical procedure. - - We "regenerate" toplevel cutoff, if transmitting class - has backlog and it is not regulated. It is not part of - original CBQ description, but looks more reasonable. - Probably, it is wrong. This question needs further investigation. -*/ + * It is mission critical procedure. + * + * We "regenerate" toplevel cutoff, if transmitting class + * has backlog and it is not regulated. It is not part of + * original CBQ description, but looks more reasonable. + * Probably, it is wrong. This question needs further investigation. + */ -static __inline__ void +static inline void cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, struct cbq_class *borrowed) { @@ -682,7 +683,7 @@ cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, q->toplevel = borrowed->level; return; } - } while ((borrowed=borrowed->borrow) != NULL); + } while ((borrowed = borrowed->borrow) != NULL); } #if 0 /* It is not necessary now. Uncommenting it @@ -710,10 +711,10 @@ cbq_update(struct cbq_sched_data *q) cl->bstats.bytes += len; /* - (now - last) is total time between packet right edges. - (last_pktlen/rate) is "virtual" busy time, so that - - idle = (now - last) - last_pktlen/rate + * (now - last) is total time between packet right edges. + * (last_pktlen/rate) is "virtual" busy time, so that + * + * idle = (now - last) - last_pktlen/rate */ idle = q->now - cl->last; @@ -723,9 +724,9 @@ cbq_update(struct cbq_sched_data *q) idle -= L2T(cl, len); /* true_avgidle := (1-W)*true_avgidle + W*idle, - where W=2^{-ewma_log}. But cl->avgidle is scaled: - cl->avgidle == true_avgidle/W, - hence: + * where W=2^{-ewma_log}. But cl->avgidle is scaled: + * cl->avgidle == true_avgidle/W, + * hence: */ avgidle += idle - (avgidle>>cl->ewma_log); } @@ -739,22 +740,22 @@ cbq_update(struct cbq_sched_data *q) cl->avgidle = avgidle; /* Calculate expected time, when this class - will be allowed to send. - It will occur, when: - (1-W)*true_avgidle + W*delay = 0, i.e. - idle = (1/W - 1)*(-true_avgidle) - or - idle = (1 - W)*(-cl->avgidle); + * will be allowed to send. + * It will occur, when: + * (1-W)*true_avgidle + W*delay = 0, i.e. + * idle = (1/W - 1)*(-true_avgidle) + * or + * idle = (1 - W)*(-cl->avgidle); */ idle = (-avgidle) - ((-avgidle) >> cl->ewma_log); /* - That is not all. - To maintain the rate allocated to the class, - we add to undertime virtual clock, - necessary to complete transmitted packet. - (len/phys_bandwidth has been already passed - to the moment of cbq_update) + * That is not all. + * To maintain the rate allocated to the class, + * we add to undertime virtual clock, + * necessary to complete transmitted packet. + * (len/phys_bandwidth has been already passed + * to the moment of cbq_update) */ idle -= L2T(&q->link, len); @@ -776,7 +777,7 @@ cbq_update(struct cbq_sched_data *q) cbq_update_toplevel(q, this, q->tx_borrowed); } -static __inline__ struct cbq_class * +static inline struct cbq_class * cbq_under_limit(struct cbq_class *cl) { struct cbq_sched_data *q = qdisc_priv(cl->qdisc); @@ -792,16 +793,17 @@ cbq_under_limit(struct cbq_class *cl) do { /* It is very suspicious place. Now overlimit - action is generated for not bounded classes - only if link is completely congested. - Though it is in agree with ancestor-only paradigm, - it looks very stupid. Particularly, - it means that this chunk of code will either - never be called or result in strong amplification - of burstiness. Dangerous, silly, and, however, - no another solution exists. + * action is generated for not bounded classes + * only if link is completely congested. + * Though it is in agree with ancestor-only paradigm, + * it looks very stupid. Particularly, + * it means that this chunk of code will either + * never be called or result in strong amplification + * of burstiness. Dangerous, silly, and, however, + * no another solution exists. */ - if ((cl = cl->borrow) == NULL) { + cl = cl->borrow; + if (!cl) { this_cl->qstats.overlimits++; this_cl->overlimit(this_cl); return NULL; @@ -814,7 +816,7 @@ cbq_under_limit(struct cbq_class *cl) return cl; } -static __inline__ struct sk_buff * +static inline struct sk_buff * cbq_dequeue_prio(struct Qdisc *sch, int prio) { struct cbq_sched_data *q = qdisc_priv(sch); @@ -838,7 +840,7 @@ cbq_dequeue_prio(struct Qdisc *sch, int prio) if (cl->deficit <= 0) { /* Class exhausted its allotment per - this round. Switch to the next one. + * this round. Switch to the next one. */ deficit = 1; cl->deficit += cl->quantum; @@ -848,8 +850,8 @@ cbq_dequeue_prio(struct Qdisc *sch, int prio) skb = cl->q->dequeue(cl->q); /* Class did not give us any skb :-( - It could occur even if cl->q->q.qlen != 0 - f.e. if cl->q == "tbf" + * It could occur even if cl->q->q.qlen != 0 + * f.e. if cl->q == "tbf" */ if (skb == NULL) goto skip_class; @@ -878,7 +880,7 @@ cbq_dequeue_prio(struct Qdisc *sch, int prio) skip_class: if (cl->q->q.qlen == 0 || prio != cl->cpriority) { /* Class is empty or penalized. - Unlink it from active chain. + * Unlink it from active chain. */ cl_prev->next_alive = cl->next_alive; cl->next_alive = NULL; @@ -917,14 +919,14 @@ next_class: return NULL; } -static __inline__ struct sk_buff * +static inline struct sk_buff * cbq_dequeue_1(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; - unsigned activemask; + unsigned int activemask; - activemask = q->activemask&0xFF; + activemask = q->activemask & 0xFF; while (activemask) { int prio = ffz(~activemask); activemask &= ~(1<<prio); @@ -949,11 +951,11 @@ cbq_dequeue(struct Qdisc *sch) if (q->tx_class) { psched_tdiff_t incr2; /* Time integrator. We calculate EOS time - by adding expected packet transmission time. - If real time is greater, we warp artificial clock, - so that: - - cbq_time = max(real_time, work); + * by adding expected packet transmission time. + * If real time is greater, we warp artificial clock, + * so that: + * + * cbq_time = max(real_time, work); */ incr2 = L2T(&q->link, q->tx_len); q->now += incr2; @@ -971,27 +973,27 @@ cbq_dequeue(struct Qdisc *sch) if (skb) { qdisc_bstats_update(sch, skb); sch->q.qlen--; - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); return skb; } /* All the classes are overlimit. - - It is possible, if: - - 1. Scheduler is empty. - 2. Toplevel cutoff inhibited borrowing. - 3. Root class is overlimit. - - Reset 2d and 3d conditions and retry. - - Note, that NS and cbq-2.0 are buggy, peeking - an arbitrary class is appropriate for ancestor-only - sharing, but not for toplevel algorithm. - - Our version is better, but slower, because it requires - two passes, but it is unavoidable with top-level sharing. - */ + * + * It is possible, if: + * + * 1. Scheduler is empty. + * 2. Toplevel cutoff inhibited borrowing. + * 3. Root class is overlimit. + * + * Reset 2d and 3d conditions and retry. + * + * Note, that NS and cbq-2.0 are buggy, peeking + * an arbitrary class is appropriate for ancestor-only + * sharing, but not for toplevel algorithm. + * + * Our version is better, but slower, because it requires + * two passes, but it is unavoidable with top-level sharing. + */ if (q->toplevel == TC_CBQ_MAXLEVEL && q->link.undertime == PSCHED_PASTPERFECT) @@ -1002,7 +1004,8 @@ cbq_dequeue(struct Qdisc *sch) } /* No packets in scheduler or nobody wants to give them to us :-( - Sigh... start watchdog timer in the last case. */ + * Sigh... start watchdog timer in the last case. + */ if (sch->q.qlen) { sch->qstats.overlimits++; @@ -1024,13 +1027,14 @@ static void cbq_adjust_levels(struct cbq_class *this) int level = 0; struct cbq_class *cl; - if ((cl = this->children) != NULL) { + cl = this->children; + if (cl) { do { if (cl->level > level) level = cl->level; } while ((cl = cl->sibling) != this->children); } - this->level = level+1; + this->level = level + 1; } while ((this = this->tparent) != NULL); } @@ -1046,14 +1050,15 @@ static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) for (h = 0; h < q->clhash.hashsize; h++) { hlist_for_each_entry(cl, n, &q->clhash.hash[h], common.hnode) { /* BUGGGG... Beware! This expression suffer of - arithmetic overflows! + * arithmetic overflows! */ if (cl->priority == prio) { cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/ q->quanta[prio]; } if (cl->quantum <= 0 || cl->quantum>32*qdisc_dev(cl->qdisc)->mtu) { - printk(KERN_WARNING "CBQ: class %08x has bad quantum==%ld, repaired.\n", cl->common.classid, cl->quantum); + pr_warning("CBQ: class %08x has bad quantum==%ld, repaired.\n", + cl->common.classid, cl->quantum); cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1; } } @@ -1064,18 +1069,18 @@ static void cbq_sync_defmap(struct cbq_class *cl) { struct cbq_sched_data *q = qdisc_priv(cl->qdisc); struct cbq_class *split = cl->split; - unsigned h; + unsigned int h; int i; if (split == NULL) return; - for (i=0; i<=TC_PRIO_MAX; i++) { - if (split->defaults[i] == cl && !(cl->defmap&(1<<i))) + for (i = 0; i <= TC_PRIO_MAX; i++) { + if (split->defaults[i] == cl && !(cl->defmap & (1<<i))) split->defaults[i] = NULL; } - for (i=0; i<=TC_PRIO_MAX; i++) { + for (i = 0; i <= TC_PRIO_MAX; i++) { int level = split->level; if (split->defaults[i]) @@ -1088,7 +1093,7 @@ static void cbq_sync_defmap(struct cbq_class *cl) hlist_for_each_entry(c, n, &q->clhash.hash[h], common.hnode) { if (c->split == split && c->level < level && - c->defmap&(1<<i)) { + c->defmap & (1<<i)) { split->defaults[i] = c; level = c->level; } @@ -1102,7 +1107,8 @@ static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 ma struct cbq_class *split = NULL; if (splitid == 0) { - if ((split = cl->split) == NULL) + split = cl->split; + if (!split) return; splitid = split->common.classid; } @@ -1120,9 +1126,9 @@ static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 ma cl->defmap = 0; cbq_sync_defmap(cl); cl->split = split; - cl->defmap = def&mask; + cl->defmap = def & mask; } else - cl->defmap = (cl->defmap&~mask)|(def&mask); + cl->defmap = (cl->defmap & ~mask) | (def & mask); cbq_sync_defmap(cl); } @@ -1135,7 +1141,7 @@ static void cbq_unlink_class(struct cbq_class *this) qdisc_class_hash_remove(&q->clhash, &this->common); if (this->tparent) { - clp=&this->sibling; + clp = &this->sibling; cl = *clp; do { if (cl == this) { @@ -1174,7 +1180,7 @@ static void cbq_link_class(struct cbq_class *this) } } -static unsigned int cbq_drop(struct Qdisc* sch) +static unsigned int cbq_drop(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl, *cl_head; @@ -1182,7 +1188,8 @@ static unsigned int cbq_drop(struct Qdisc* sch) unsigned int len; for (prio = TC_CBQ_MAXPRIO; prio >= 0; prio--) { - if ((cl_head = q->active[prio]) == NULL) + cl_head = q->active[prio]; + if (!cl_head) continue; cl = cl_head; @@ -1199,13 +1206,13 @@ static unsigned int cbq_drop(struct Qdisc* sch) } static void -cbq_reset(struct Qdisc* sch) +cbq_reset(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl; struct hlist_node *n; int prio; - unsigned h; + unsigned int h; q->activemask = 0; q->pmask = 0; @@ -1237,21 +1244,21 @@ cbq_reset(struct Qdisc* sch) static int cbq_set_lss(struct cbq_class *cl, struct tc_cbq_lssopt *lss) { - if (lss->change&TCF_CBQ_LSS_FLAGS) { - cl->share = (lss->flags&TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; - cl->borrow = (lss->flags&TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; + if (lss->change & TCF_CBQ_LSS_FLAGS) { + cl->share = (lss->flags & TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; + cl->borrow = (lss->flags & TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; } - if (lss->change&TCF_CBQ_LSS_EWMA) + if (lss->change & TCF_CBQ_LSS_EWMA) cl->ewma_log = lss->ewma_log; - if (lss->change&TCF_CBQ_LSS_AVPKT) + if (lss->change & TCF_CBQ_LSS_AVPKT) cl->avpkt = lss->avpkt; - if (lss->change&TCF_CBQ_LSS_MINIDLE) + if (lss->change & TCF_CBQ_LSS_MINIDLE) cl->minidle = -(long)lss->minidle; - if (lss->change&TCF_CBQ_LSS_MAXIDLE) { + if (lss->change & TCF_CBQ_LSS_MAXIDLE) { cl->maxidle = lss->maxidle; cl->avgidle = lss->maxidle; } - if (lss->change&TCF_CBQ_LSS_OFFTIME) + if (lss->change & TCF_CBQ_LSS_OFFTIME) cl->offtime = lss->offtime; return 0; } @@ -1279,10 +1286,10 @@ static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr) if (wrr->weight) cl->weight = wrr->weight; if (wrr->priority) { - cl->priority = wrr->priority-1; + cl->priority = wrr->priority - 1; cl->cpriority = cl->priority; if (cl->priority >= cl->priority2) - cl->priority2 = TC_CBQ_MAXPRIO-1; + cl->priority2 = TC_CBQ_MAXPRIO - 1; } cbq_addprio(q, cl); @@ -1299,10 +1306,10 @@ static int cbq_set_overlimit(struct cbq_class *cl, struct tc_cbq_ovl *ovl) cl->overlimit = cbq_ovl_delay; break; case TC_CBQ_OVL_LOWPRIO: - if (ovl->priority2-1 >= TC_CBQ_MAXPRIO || - ovl->priority2-1 <= cl->priority) + if (ovl->priority2 - 1 >= TC_CBQ_MAXPRIO || + ovl->priority2 - 1 <= cl->priority) return -EINVAL; - cl->priority2 = ovl->priority2-1; + cl->priority2 = ovl->priority2 - 1; cl->overlimit = cbq_ovl_lowprio; break; case TC_CBQ_OVL_DROP: @@ -1381,9 +1388,9 @@ static int cbq_init(struct Qdisc *sch, struct nlattr *opt) if (!q->link.q) q->link.q = &noop_qdisc; - q->link.priority = TC_CBQ_MAXPRIO-1; - q->link.priority2 = TC_CBQ_MAXPRIO-1; - q->link.cpriority = TC_CBQ_MAXPRIO-1; + q->link.priority = TC_CBQ_MAXPRIO - 1; + q->link.priority2 = TC_CBQ_MAXPRIO - 1; + q->link.cpriority = TC_CBQ_MAXPRIO - 1; q->link.ovl_strategy = TC_CBQ_OVL_CLASSIC; q->link.overlimit = cbq_ovl_classic; q->link.allot = psched_mtu(qdisc_dev(sch)); @@ -1414,7 +1421,7 @@ put_rtab: return err; } -static __inline__ int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); @@ -1426,7 +1433,7 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_lssopt opt; @@ -1451,15 +1458,15 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_wrropt opt; opt.flags = 0; opt.allot = cl->allot; - opt.priority = cl->priority+1; - opt.cpriority = cl->cpriority+1; + opt.priority = cl->priority + 1; + opt.cpriority = cl->cpriority + 1; opt.weight = cl->weight; NLA_PUT(skb, TCA_CBQ_WRROPT, sizeof(opt), &opt); return skb->len; @@ -1469,13 +1476,13 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_ovl(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_ovl opt; opt.strategy = cl->ovl_strategy; - opt.priority2 = cl->priority2+1; + opt.priority2 = cl->priority2 + 1; opt.pad = 0; opt.penalty = cl->penalty; NLA_PUT(skb, TCA_CBQ_OVL_STRATEGY, sizeof(opt), &opt); @@ -1486,7 +1493,7 @@ nla_put_failure: return -1; } -static __inline__ int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_fopt opt; @@ -1505,7 +1512,7 @@ nla_put_failure: } #ifdef CONFIG_NET_CLS_ACT -static __inline__ int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl) +static int cbq_dump_police(struct sk_buff *skb, struct cbq_class *cl) { unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_police opt; @@ -1569,7 +1576,7 @@ static int cbq_dump_class(struct Qdisc *sch, unsigned long arg, struct sk_buff *skb, struct tcmsg *tcm) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; struct nlattr *nest; if (cl->tparent) @@ -1597,7 +1604,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d) { struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; cl->qstats.qlen = cl->q->q.qlen; cl->xstats.avgidle = cl->avgidle; @@ -1617,7 +1624,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct Qdisc **old) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; if (new == NULL) { new = qdisc_create_dflt(sch->dev_queue, @@ -1640,10 +1647,9 @@ static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, return 0; } -static struct Qdisc * -cbq_leaf(struct Qdisc *sch, unsigned long arg) +static struct Qdisc *cbq_leaf(struct Qdisc *sch, unsigned long arg) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; return cl->q; } @@ -1682,13 +1688,12 @@ static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) kfree(cl); } -static void -cbq_destroy(struct Qdisc* sch) +static void cbq_destroy(struct Qdisc *sch) { struct cbq_sched_data *q = qdisc_priv(sch); struct hlist_node *n, *next; struct cbq_class *cl; - unsigned h; + unsigned int h; #ifdef CONFIG_NET_CLS_ACT q->rx_class = NULL; @@ -1712,7 +1717,7 @@ cbq_destroy(struct Qdisc* sch) static void cbq_put(struct Qdisc *sch, unsigned long arg) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; if (--cl->refcnt == 0) { #ifdef CONFIG_NET_CLS_ACT @@ -1735,7 +1740,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t { int err; struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class*)*arg; + struct cbq_class *cl = (struct cbq_class *)*arg; struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_CBQ_MAX + 1]; struct cbq_class *parent; @@ -1827,13 +1832,14 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t if (classid) { err = -EINVAL; - if (TC_H_MAJ(classid^sch->handle) || cbq_class_lookup(q, classid)) + if (TC_H_MAJ(classid ^ sch->handle) || + cbq_class_lookup(q, classid)) goto failure; } else { int i; - classid = TC_H_MAKE(sch->handle,0x8000); + classid = TC_H_MAKE(sch->handle, 0x8000); - for (i=0; i<0x8000; i++) { + for (i = 0; i < 0x8000; i++) { if (++q->hgenerator >= 0x8000) q->hgenerator = 1; if (cbq_class_lookup(q, classid|q->hgenerator) == NULL) @@ -1890,11 +1896,11 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t cl->minidle = -0x7FFFFFFF; cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - if (cl->ewma_log==0) + if (cl->ewma_log == 0) cl->ewma_log = q->link.ewma_log; - if (cl->maxidle==0) + if (cl->maxidle == 0) cl->maxidle = q->link.maxidle; - if (cl->avpkt==0) + if (cl->avpkt == 0) cl->avpkt = q->link.avpkt; cl->overlimit = cbq_ovl_classic; if (tb[TCA_CBQ_OVL_STRATEGY]) @@ -1920,7 +1926,7 @@ failure: static int cbq_delete(struct Qdisc *sch, unsigned long arg) { struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; unsigned int qlen; if (cl->filters || cl->children || cl == &q->link) @@ -1978,7 +1984,7 @@ static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, u32 classid) { struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *p = (struct cbq_class*)parent; + struct cbq_class *p = (struct cbq_class *)parent; struct cbq_class *cl = cbq_class_lookup(q, classid); if (cl) { @@ -1992,7 +1998,7 @@ static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, static void cbq_unbind_filter(struct Qdisc *sch, unsigned long arg) { - struct cbq_class *cl = (struct cbq_class*)arg; + struct cbq_class *cl = (struct cbq_class *)arg; cl->filters--; } @@ -2002,7 +2008,7 @@ static void cbq_walk(struct Qdisc *sch, struct qdisc_walker *arg) struct cbq_sched_data *q = qdisc_priv(sch); struct cbq_class *cl; struct hlist_node *n; - unsigned h; + unsigned int h; if (arg->stop) return; diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 0f7bf3f..2c79020 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -137,10 +137,10 @@ static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, mask = nla_get_u8(tb[TCA_DSMARK_MASK]); if (tb[TCA_DSMARK_VALUE]) - p->value[*arg-1] = nla_get_u8(tb[TCA_DSMARK_VALUE]); + p->value[*arg - 1] = nla_get_u8(tb[TCA_DSMARK_VALUE]); if (tb[TCA_DSMARK_MASK]) - p->mask[*arg-1] = mask; + p->mask[*arg - 1] = mask; err = 0; @@ -155,8 +155,8 @@ static int dsmark_delete(struct Qdisc *sch, unsigned long arg) if (!dsmark_valid_index(p, arg)) return -EINVAL; - p->mask[arg-1] = 0xff; - p->value[arg-1] = 0; + p->mask[arg - 1] = 0xff; + p->value[arg - 1] = 0; return 0; } @@ -175,7 +175,7 @@ static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) if (p->mask[i] == 0xff && !p->value[i]) goto ignore; if (walker->count >= walker->skip) { - if (walker->fn(sch, i+1, walker) < 0) { + if (walker->fn(sch, i + 1, walker) < 0) { walker->stop = 1; break; } @@ -304,9 +304,8 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) * and don't need yet another qdisc as a bypass. */ if (p->mask[index] != 0xff || p->value[index]) - printk(KERN_WARNING - "dsmark_dequeue: unsupported protocol %d\n", - ntohs(skb->protocol)); + pr_warning("dsmark_dequeue: unsupported protocol %d\n", + ntohs(skb->protocol)); break; } @@ -424,14 +423,14 @@ static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, if (!dsmark_valid_index(p, cl)) return -EINVAL; - tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl-1); + tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1); tcm->tcm_info = p->q->handle; opts = nla_nest_start(skb, TCA_OPTIONS); if (opts == NULL) goto nla_put_failure; - NLA_PUT_U8(skb, TCA_DSMARK_MASK, p->mask[cl-1]); - NLA_PUT_U8(skb, TCA_DSMARK_VALUE, p->value[cl-1]); + NLA_PUT_U8(skb, TCA_DSMARK_MASK, p->mask[cl - 1]); + NLA_PUT_U8(skb, TCA_DSMARK_VALUE, p->value[cl - 1]); return nla_nest_end(skb, opts); diff --git a/net/sched/sch_fifo.c b/net/sched/sch_fifo.c index d468b47..be33f9d 100644 --- a/net/sched/sch_fifo.c +++ b/net/sched/sch_fifo.c @@ -19,12 +19,11 @@ /* 1 band FIFO pseudo-"scheduler" */ -struct fifo_sched_data -{ +struct fifo_sched_data { u32 limit; }; -static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct fifo_sched_data *q = qdisc_priv(sch); @@ -34,7 +33,7 @@ static int bfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) return qdisc_reshape_fail(skb, sch); } -static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct fifo_sched_data *q = qdisc_priv(sch); @@ -44,7 +43,7 @@ static int pfifo_enqueue(struct sk_buff *skb, struct Qdisc* sch) return qdisc_reshape_fail(skb, sch); } -static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct fifo_sched_data *q = qdisc_priv(sch); @@ -62,11 +61,13 @@ static int pfifo_tail_enqueue(struct sk_buff *skb, struct Qdisc* sch) static int fifo_init(struct Qdisc *sch, struct nlattr *opt) { struct fifo_sched_data *q = qdisc_priv(sch); + bool bypass; + bool is_bfifo = sch->ops == &bfifo_qdisc_ops; if (opt == NULL) { u32 limit = qdisc_dev(sch)->tx_queue_len ? : 1; - if (sch->ops == &bfifo_qdisc_ops) + if (is_bfifo) limit *= psched_mtu(qdisc_dev(sch)); q->limit = limit; @@ -79,6 +80,15 @@ static int fifo_init(struct Qdisc *sch, struct nlattr *opt) q->limit = ctl->limit; } + if (is_bfifo) + bypass = q->limit >= psched_mtu(qdisc_dev(sch)); + else + bypass = q->limit >= 1; + + if (bypass) + sch->flags |= TCQ_F_CAN_BYPASS; + else + sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 34dc598..0da09d5 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -87,8 +87,8 @@ static inline int handle_dev_cpu_collision(struct sk_buff *skb, */ kfree_skb(skb); if (net_ratelimit()) - printk(KERN_WARNING "Dead loop on netdevice %s, " - "fix it urgently!\n", dev_queue->dev->name); + pr_warning("Dead loop on netdevice %s, fix it urgently!\n", + dev_queue->dev->name); ret = qdisc_qlen(q); } else { /* @@ -137,8 +137,8 @@ int sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, } else { /* Driver returned NETDEV_TX_BUSY - requeue skb */ if (unlikely (ret != NETDEV_TX_BUSY && net_ratelimit())) - printk(KERN_WARNING "BUG %s code %d qlen %d\n", - dev->name, ret, q->q.qlen); + pr_warning("BUG %s code %d qlen %d\n", + dev->name, ret, q->q.qlen); ret = dev_requeue_skb(skb, q); } @@ -412,8 +412,9 @@ static struct Qdisc noqueue_qdisc = { }; -static const u8 prio2band[TC_PRIO_MAX+1] = - { 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 }; +static const u8 prio2band[TC_PRIO_MAX + 1] = { + 1, 2, 2, 2, 1, 2, 0, 0 , 1, 1, 1, 1, 1, 1, 1, 1 +}; /* 3-band FIFO queue: old style, but should be a bit faster than generic prio+fifo combination. @@ -445,7 +446,7 @@ static inline struct sk_buff_head *band2list(struct pfifo_fast_priv *priv, return priv->q + band; } -static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) +static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc) { if (skb_queue_len(&qdisc->q) < qdisc_dev(qdisc)->tx_queue_len) { int band = prio2band[skb->priority & TC_PRIO_MAX]; @@ -460,7 +461,7 @@ static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc* qdisc) return qdisc_drop(skb, qdisc); } -static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc) +static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); int band = bitmap2band[priv->bitmap]; @@ -479,7 +480,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc* qdisc) return NULL; } -static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc) +static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); int band = bitmap2band[priv->bitmap]; @@ -493,7 +494,7 @@ static struct sk_buff *pfifo_fast_peek(struct Qdisc* qdisc) return NULL; } -static void pfifo_fast_reset(struct Qdisc* qdisc) +static void pfifo_fast_reset(struct Qdisc *qdisc) { int prio; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); @@ -510,7 +511,7 @@ static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) { struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS }; - memcpy(&opt.priomap, prio2band, TC_PRIO_MAX+1); + memcpy(&opt.priomap, prio2band, TC_PRIO_MAX + 1); NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); return skb->len; @@ -526,6 +527,8 @@ static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt) for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) skb_queue_head_init(band2list(priv, prio)); + /* Can by-pass the queue discipline */ + qdisc->flags |= TCQ_F_CAN_BYPASS; return 0; } @@ -540,6 +543,7 @@ struct Qdisc_ops pfifo_fast_ops __read_mostly = { .dump = pfifo_fast_dump, .owner = THIS_MODULE, }; +EXPORT_SYMBOL(pfifo_fast_ops); struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, struct Qdisc_ops *ops) @@ -630,7 +634,7 @@ void qdisc_destroy(struct Qdisc *qdisc) #ifdef CONFIG_NET_SCHED qdisc_list_del(qdisc); - qdisc_put_stab(qdisc->stab); + qdisc_put_stab(rtnl_dereference(qdisc->stab)); #endif gen_kill_estimator(&qdisc->bstats, &qdisc->rate_est); if (ops->reset) @@ -674,25 +678,21 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, return oqdisc; } +EXPORT_SYMBOL(dev_graft_qdisc); static void attach_one_default_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) { - struct Qdisc *qdisc; + struct Qdisc *qdisc = &noqueue_qdisc; if (dev->tx_queue_len) { qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops, TC_H_ROOT); if (!qdisc) { - printk(KERN_INFO "%s: activation failed\n", dev->name); + netdev_info(dev, "activation failed\n"); return; } - - /* Can by-pass the queue discipline for default qdisc */ - qdisc->flags |= TCQ_F_CAN_BYPASS; - } else { - qdisc = &noqueue_qdisc; } dev_queue->qdisc_sleeping = qdisc; } @@ -761,6 +761,7 @@ void dev_activate(struct net_device *dev) dev_watchdog_up(dev); } } +EXPORT_SYMBOL(dev_activate); static void dev_deactivate_queue(struct net_device *dev, struct netdev_queue *dev_queue, @@ -840,6 +841,7 @@ void dev_deactivate(struct net_device *dev) list_add(&dev->unreg_list, &single); dev_deactivate_many(&single); } +EXPORT_SYMBOL(dev_deactivate); static void dev_init_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, diff --git a/net/sched/sch_gred.c b/net/sched/sch_gred.c index 51dcc2a..b9493a0 100644 --- a/net/sched/sch_gred.c +++ b/net/sched/sch_gred.c @@ -32,8 +32,7 @@ struct gred_sched_data; struct gred_sched; -struct gred_sched_data -{ +struct gred_sched_data { u32 limit; /* HARD maximal queue length */ u32 DP; /* the drop pramaters */ u32 bytesin; /* bytes seen on virtualQ so far*/ @@ -50,8 +49,7 @@ enum { GRED_RIO_MODE, }; -struct gred_sched -{ +struct gred_sched { struct gred_sched_data *tab[MAX_DPs]; unsigned long flags; u32 red_flags; @@ -150,17 +148,18 @@ static inline int gred_use_harddrop(struct gred_sched *t) return t->red_flags & TC_RED_HARDDROP; } -static int gred_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int gred_enqueue(struct sk_buff *skb, struct Qdisc *sch) { - struct gred_sched_data *q=NULL; - struct gred_sched *t= qdisc_priv(sch); + struct gred_sched_data *q = NULL; + struct gred_sched *t = qdisc_priv(sch); unsigned long qavg = 0; u16 dp = tc_index_to_dp(skb); - if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { + if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { dp = t->def; - if ((q = t->tab[dp]) == NULL) { + q = t->tab[dp]; + if (!q) { /* Pass through packets not assigned to a DP * if no default DP has been configured. This * allows for DP flows to be left untouched. @@ -183,7 +182,7 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc* sch) for (i = 0; i < t->DPs; i++) { if (t->tab[i] && t->tab[i]->prio < q->prio && !red_is_idling(&t->tab[i]->parms)) - qavg +=t->tab[i]->parms.qavg; + qavg += t->tab[i]->parms.qavg; } } @@ -203,28 +202,28 @@ static int gred_enqueue(struct sk_buff *skb, struct Qdisc* sch) gred_store_wred_set(t, q); switch (red_action(&q->parms, q->parms.qavg + qavg)) { - case RED_DONT_MARK: - break; - - case RED_PROB_MARK: - sch->qstats.overlimits++; - if (!gred_use_ecn(t) || !INET_ECN_set_ce(skb)) { - q->stats.prob_drop++; - goto congestion_drop; - } - - q->stats.prob_mark++; - break; - - case RED_HARD_MARK: - sch->qstats.overlimits++; - if (gred_use_harddrop(t) || !gred_use_ecn(t) || - !INET_ECN_set_ce(skb)) { - q->stats.forced_drop++; - goto congestion_drop; - } - q->stats.forced_mark++; - break; + case RED_DONT_MARK: + break; + + case RED_PROB_MARK: + sch->qstats.overlimits++; + if (!gred_use_ecn(t) || !INET_ECN_set_ce(skb)) { + q->stats.prob_drop++; + goto congestion_drop; + } + + q->stats.prob_mark++; + break; + + case RED_HARD_MARK: + sch->qstats.overlimits++; + if (gred_use_harddrop(t) || !gred_use_ecn(t) || + !INET_ECN_set_ce(skb)) { + q->stats.forced_drop++; + goto congestion_drop; + } + q->stats.forced_mark++; + break; } if (q->backlog + qdisc_pkt_len(skb) <= q->limit) { @@ -241,7 +240,7 @@ congestion_drop: return NET_XMIT_CN; } -static struct sk_buff *gred_dequeue(struct Qdisc* sch) +static struct sk_buff *gred_dequeue(struct Qdisc *sch) { struct sk_buff *skb; struct gred_sched *t = qdisc_priv(sch); @@ -254,9 +253,9 @@ static struct sk_buff *gred_dequeue(struct Qdisc* sch) if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { if (net_ratelimit()) - printk(KERN_WARNING "GRED: Unable to relocate " - "VQ 0x%x after dequeue, screwing up " - "backlog.\n", tc_index_to_dp(skb)); + pr_warning("GRED: Unable to relocate VQ 0x%x " + "after dequeue, screwing up " + "backlog.\n", tc_index_to_dp(skb)); } else { q->backlog -= qdisc_pkt_len(skb); @@ -273,7 +272,7 @@ static struct sk_buff *gred_dequeue(struct Qdisc* sch) return NULL; } -static unsigned int gred_drop(struct Qdisc* sch) +static unsigned int gred_drop(struct Qdisc *sch) { struct sk_buff *skb; struct gred_sched *t = qdisc_priv(sch); @@ -286,9 +285,9 @@ static unsigned int gred_drop(struct Qdisc* sch) if (dp >= t->DPs || (q = t->tab[dp]) == NULL) { if (net_ratelimit()) - printk(KERN_WARNING "GRED: Unable to relocate " - "VQ 0x%x while dropping, screwing up " - "backlog.\n", tc_index_to_dp(skb)); + pr_warning("GRED: Unable to relocate VQ 0x%x " + "while dropping, screwing up " + "backlog.\n", tc_index_to_dp(skb)); } else { q->backlog -= len; q->stats.other++; @@ -308,7 +307,7 @@ static unsigned int gred_drop(struct Qdisc* sch) } -static void gred_reset(struct Qdisc* sch) +static void gred_reset(struct Qdisc *sch) { int i; struct gred_sched *t = qdisc_priv(sch); @@ -369,8 +368,8 @@ static inline int gred_change_table_def(struct Qdisc *sch, struct nlattr *dps) for (i = table->DPs; i < MAX_DPs; i++) { if (table->tab[i]) { - printk(KERN_WARNING "GRED: Warning: Destroying " - "shadowed VQ 0x%x\n", i); + pr_warning("GRED: Warning: Destroying " + "shadowed VQ 0x%x\n", i); gred_destroy_vq(table->tab[i]); table->tab[i] = NULL; } diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c index 14a799d..6488e64 100644 --- a/net/sched/sch_hfsc.c +++ b/net/sched/sch_hfsc.c @@ -81,8 +81,7 @@ * that are expensive on 32-bit architectures. */ -struct internal_sc -{ +struct internal_sc { u64 sm1; /* scaled slope of the 1st segment */ u64 ism1; /* scaled inverse-slope of the 1st segment */ u64 dx; /* the x-projection of the 1st segment */ @@ -92,8 +91,7 @@ struct internal_sc }; /* runtime service curve */ -struct runtime_sc -{ +struct runtime_sc { u64 x; /* current starting position on x-axis */ u64 y; /* current starting position on y-axis */ u64 sm1; /* scaled slope of the 1st segment */ @@ -104,15 +102,13 @@ struct runtime_sc u64 ism2; /* scaled inverse-slope of the 2nd segment */ }; -enum hfsc_class_flags -{ +enum hfsc_class_flags { HFSC_RSC = 0x1, HFSC_FSC = 0x2, HFSC_USC = 0x4 }; -struct hfsc_class -{ +struct hfsc_class { struct Qdisc_class_common cl_common; unsigned int refcnt; /* usage count */ @@ -140,8 +136,8 @@ struct hfsc_class u64 cl_cumul; /* cumulative work in bytes done by real-time criteria */ - u64 cl_d; /* deadline*/ - u64 cl_e; /* eligible time */ + u64 cl_d; /* deadline*/ + u64 cl_e; /* eligible time */ u64 cl_vt; /* virtual time */ u64 cl_f; /* time when this class will fit for link-sharing, max(myf, cfmin) */ @@ -176,8 +172,7 @@ struct hfsc_class unsigned long cl_nactive; /* number of active children */ }; -struct hfsc_sched -{ +struct hfsc_sched { u16 defcls; /* default class id */ struct hfsc_class root; /* root class */ struct Qdisc_class_hash clhash; /* class hash */ @@ -693,7 +688,7 @@ init_vf(struct hfsc_class *cl, unsigned int len) if (go_active) { n = rb_last(&cl->cl_parent->vt_tree); if (n != NULL) { - max_cl = rb_entry(n, struct hfsc_class,vt_node); + max_cl = rb_entry(n, struct hfsc_class, vt_node); /* * set vt to the average of the min and max * classes. if the parent's period didn't @@ -1177,8 +1172,10 @@ hfsc_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) return NULL; } #endif - if ((cl = (struct hfsc_class *)res.class) == NULL) { - if ((cl = hfsc_find_class(res.classid, sch)) == NULL) + cl = (struct hfsc_class *)res.class; + if (!cl) { + cl = hfsc_find_class(res.classid, sch); + if (!cl) break; /* filter selected invalid classid */ if (cl->level >= head->level) break; /* filter may only point downwards */ @@ -1316,7 +1313,7 @@ hfsc_dump_sc(struct sk_buff *skb, int attr, struct internal_sc *sc) return -1; } -static inline int +static int hfsc_dump_curves(struct sk_buff *skb, struct hfsc_class *cl) { if ((cl->cl_flags & HFSC_RSC) && @@ -1420,7 +1417,8 @@ hfsc_schedule_watchdog(struct Qdisc *sch) struct hfsc_class *cl; u64 next_time = 0; - if ((cl = eltree_get_minel(q)) != NULL) + cl = eltree_get_minel(q); + if (cl) next_time = cl->cl_e; if (q->root.cl_cfmin != 0) { if (next_time == 0 || next_time > q->root.cl_cfmin) @@ -1625,7 +1623,8 @@ hfsc_dequeue(struct Qdisc *sch) * find the class with the minimum deadline among * the eligible classes. */ - if ((cl = eltree_get_mindl(q, cur_time)) != NULL) { + cl = eltree_get_mindl(q, cur_time); + if (cl) { realtime = 1; } else { /* @@ -1664,7 +1663,7 @@ hfsc_dequeue(struct Qdisc *sch) set_passive(cl); } - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); qdisc_bstats_update(sch, skb); sch->q.qlen--; diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index fc12fe6..e1429a8 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -99,9 +99,10 @@ struct htb_class { struct rb_root feed[TC_HTB_NUMPRIO]; /* feed trees */ struct rb_node *ptr[TC_HTB_NUMPRIO]; /* current class ptr */ /* When class changes from state 1->2 and disconnects from - parent's feed then we lost ptr value and start from the - first child again. Here we store classid of the - last valid ptr (used when ptr is NULL). */ + * parent's feed then we lost ptr value and start from the + * first child again. Here we store classid of the + * last valid ptr (used when ptr is NULL). + */ u32 last_ptr_id[TC_HTB_NUMPRIO]; } inner; } un; @@ -185,7 +186,7 @@ static inline struct htb_class *htb_find(u32 handle, struct Qdisc *sch) * have no valid leaf we try to use MAJOR:default leaf. It still unsuccessfull * then finish and return direct queue. */ -#define HTB_DIRECT (struct htb_class*)-1 +#define HTB_DIRECT ((struct htb_class *)-1L) static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) @@ -197,11 +198,13 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, int result; /* allow to select class by setting skb->priority to valid classid; - note that nfmark can be used too by attaching filter fw with no - rules in it */ + * note that nfmark can be used too by attaching filter fw with no + * rules in it + */ if (skb->priority == sch->handle) return HTB_DIRECT; /* X:0 (direct flow) selected */ - if ((cl = htb_find(skb->priority, sch)) != NULL && cl->level == 0) + cl = htb_find(skb->priority, sch); + if (cl && cl->level == 0) return cl; *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; @@ -216,10 +219,12 @@ static struct htb_class *htb_classify(struct sk_buff *skb, struct Qdisc *sch, return NULL; } #endif - if ((cl = (void *)res.class) == NULL) { + cl = (void *)res.class; + if (!cl) { if (res.classid == sch->handle) return HTB_DIRECT; /* X:0 (direct flow) */ - if ((cl = htb_find(res.classid, sch)) == NULL) + cl = htb_find(res.classid, sch); + if (!cl) break; /* filter selected invalid classid */ } if (!cl->level) @@ -378,7 +383,8 @@ static void htb_activate_prios(struct htb_sched *q, struct htb_class *cl) if (p->un.inner.feed[prio].rb_node) /* parent already has its feed in use so that - reset bit in mask as parent is already ok */ + * reset bit in mask as parent is already ok + */ mask &= ~(1 << prio); htb_add_to_id_tree(p->un.inner.feed + prio, cl, prio); @@ -413,8 +419,9 @@ static void htb_deactivate_prios(struct htb_sched *q, struct htb_class *cl) if (p->un.inner.ptr[prio] == cl->node + prio) { /* we are removing child which is pointed to from - parent feed - forget the pointer but remember - classid */ + * parent feed - forget the pointer but remember + * classid + */ p->un.inner.last_ptr_id[prio] = cl->common.classid; p->un.inner.ptr[prio] = NULL; } @@ -663,8 +670,9 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level, unsigned long start) { /* don't run for longer than 2 jiffies; 2 is used instead of - 1 to simplify things when jiffy is going to be incremented - too soon */ + * 1 to simplify things when jiffy is going to be incremented + * too soon + */ unsigned long stop_at = start + 2; while (time_before(jiffies, stop_at)) { struct htb_class *cl; @@ -687,7 +695,7 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level, /* too much load - let's continue after a break for scheduling */ if (!(q->warned & HTB_WARN_TOOMANYEVENTS)) { - printk(KERN_WARNING "htb: too many events!\n"); + pr_warning("htb: too many events!\n"); q->warned |= HTB_WARN_TOOMANYEVENTS; } @@ -695,7 +703,8 @@ static psched_time_t htb_do_events(struct htb_sched *q, int level, } /* Returns class->node+prio from id-tree where classe's id is >= id. NULL - is no such one exists. */ + * is no such one exists. + */ static struct rb_node *htb_id_find_next_upper(int prio, struct rb_node *n, u32 id) { @@ -739,12 +748,14 @@ static struct htb_class *htb_lookup_leaf(struct rb_root *tree, int prio, for (i = 0; i < 65535; i++) { if (!*sp->pptr && *sp->pid) { /* ptr was invalidated but id is valid - try to recover - the original or next ptr */ + * the original or next ptr + */ *sp->pptr = htb_id_find_next_upper(prio, sp->root, *sp->pid); } *sp->pid = 0; /* ptr is valid now so that remove this hint as it - can become out of date quickly */ + * can become out of date quickly + */ if (!*sp->pptr) { /* we are at right end; rewind & go up */ *sp->pptr = sp->root; while ((*sp->pptr)->rb_left) @@ -772,7 +783,8 @@ static struct htb_class *htb_lookup_leaf(struct rb_root *tree, int prio, } /* dequeues packet at given priority and level; call only if - you are sure that there is active class at prio/level */ + * you are sure that there is active class at prio/level + */ static struct sk_buff *htb_dequeue_tree(struct htb_sched *q, int prio, int level) { @@ -789,9 +801,10 @@ next: return NULL; /* class can be empty - it is unlikely but can be true if leaf - qdisc drops packets in enqueue routine or if someone used - graft operation on the leaf since last dequeue; - simply deactivate and skip such class */ + * qdisc drops packets in enqueue routine or if someone used + * graft operation on the leaf since last dequeue; + * simply deactivate and skip such class + */ if (unlikely(cl->un.leaf.q->q.qlen == 0)) { struct htb_class *next; htb_deactivate(q, cl); @@ -831,7 +844,8 @@ next: ptr[0]) + prio); } /* this used to be after charge_class but this constelation - gives us slightly better performance */ + * gives us slightly better performance + */ if (!cl->un.leaf.q->q.qlen) htb_deactivate(q, cl); htb_charge_class(q, cl, level, skb); @@ -852,7 +866,7 @@ static struct sk_buff *htb_dequeue(struct Qdisc *sch) if (skb != NULL) { ok: qdisc_bstats_update(sch, skb); - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); sch->q.qlen--; return skb; } @@ -883,6 +897,7 @@ ok: m = ~q->row_mask[level]; while (m != (int)(-1)) { int prio = ffz(m); + m |= 1 << prio; skb = htb_dequeue_tree(q, prio, level); if (likely(skb != NULL)) @@ -987,13 +1002,12 @@ static int htb_init(struct Qdisc *sch, struct nlattr *opt) return err; if (tb[TCA_HTB_INIT] == NULL) { - printk(KERN_ERR "HTB: hey probably you have bad tc tool ?\n"); + pr_err("HTB: hey probably you have bad tc tool ?\n"); return -EINVAL; } gopt = nla_data(tb[TCA_HTB_INIT]); if (gopt->version != HTB_VER >> 16) { - printk(KERN_ERR - "HTB: need tc/htb version %d (minor is %d), you have %d\n", + pr_err("HTB: need tc/htb version %d (minor is %d), you have %d\n", HTB_VER >> 16, HTB_VER & 0xffff, gopt->version); return -EINVAL; } @@ -1206,9 +1220,10 @@ static void htb_destroy(struct Qdisc *sch) cancel_work_sync(&q->work); qdisc_watchdog_cancel(&q->watchdog); /* This line used to be after htb_destroy_class call below - and surprisingly it worked in 2.4. But it must precede it - because filter need its target class alive to be able to call - unbind_filter on it (without Oops). */ + * and surprisingly it worked in 2.4. But it must precede it + * because filter need its target class alive to be able to call + * unbind_filter on it (without Oops). + */ tcf_destroy_chain(&q->filter_list); for (i = 0; i < q->clhash.hashsize; i++) { @@ -1342,11 +1357,12 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, /* check maximal depth */ if (parent && parent->parent && parent->parent->level < 2) { - printk(KERN_ERR "htb: tree is too deep\n"); + pr_err("htb: tree is too deep\n"); goto failure; } err = -ENOBUFS; - if ((cl = kzalloc(sizeof(*cl), GFP_KERNEL)) == NULL) + cl = kzalloc(sizeof(*cl), GFP_KERNEL); + if (!cl) goto failure; err = gen_new_estimator(&cl->bstats, &cl->rate_est, @@ -1366,8 +1382,9 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, RB_CLEAR_NODE(&cl->node[prio]); /* create leaf qdisc early because it uses kmalloc(GFP_KERNEL) - so that can't be used inside of sch_tree_lock - -- thanks to Karlis Peisenieks */ + * so that can't be used inside of sch_tree_lock + * -- thanks to Karlis Peisenieks + */ new_q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid); sch_tree_lock(sch); @@ -1419,17 +1436,18 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, } /* it used to be a nasty bug here, we have to check that node - is really leaf before changing cl->un.leaf ! */ + * is really leaf before changing cl->un.leaf ! + */ if (!cl->level) { cl->quantum = rtab->rate.rate / q->rate2quantum; if (!hopt->quantum && cl->quantum < 1000) { - printk(KERN_WARNING + pr_warning( "HTB: quantum of class %X is small. Consider r2q change.\n", cl->common.classid); cl->quantum = 1000; } if (!hopt->quantum && cl->quantum > 200000) { - printk(KERN_WARNING + pr_warning( "HTB: quantum of class %X is big. Consider r2q change.\n", cl->common.classid); cl->quantum = 200000; @@ -1478,13 +1496,13 @@ static unsigned long htb_bind_filter(struct Qdisc *sch, unsigned long parent, struct htb_class *cl = htb_find(classid, sch); /*if (cl && !cl->level) return 0; - The line above used to be there to prevent attaching filters to - leaves. But at least tc_index filter uses this just to get class - for other reasons so that we have to allow for it. - ---- - 19.6.2002 As Werner explained it is ok - bind filter is just - another way to "lock" the class - unlike "get" this lock can - be broken by class during destroy IIUC. + * The line above used to be there to prevent attaching filters to + * leaves. But at least tc_index filter uses this just to get class + * for other reasons so that we have to allow for it. + * ---- + * 19.6.2002 As Werner explained it is ok - bind filter is just + * another way to "lock" the class - unlike "get" this lock can + * be broken by class during destroy IIUC. */ if (cl) cl->filter_cnt++; diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index ecc302f..ec5cbc8 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -61,7 +61,6 @@ static int mq_init(struct Qdisc *sch, struct nlattr *opt) TC_H_MIN(ntx + 1))); if (qdisc == NULL) goto err; - qdisc->flags |= TCQ_F_CAN_BYPASS; priv->qdiscs[ntx] = qdisc; } diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c new file mode 100644 index 0000000..effd4ee --- /dev/null +++ b/net/sched/sch_mqprio.c @@ -0,0 +1,416 @@ +/* + * net/sched/sch_mqprio.c + * + * Copyright (c) 2010 John Fastabend <john.r.fastabend@intel.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + */ + +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <net/netlink.h> +#include <net/pkt_sched.h> +#include <net/sch_generic.h> + +struct mqprio_sched { + struct Qdisc **qdiscs; + int hw_owned; +}; + +static void mqprio_destroy(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + unsigned int ntx; + + if (!priv->qdiscs) + return; + + for (ntx = 0; ntx < dev->num_tx_queues && priv->qdiscs[ntx]; ntx++) + qdisc_destroy(priv->qdiscs[ntx]); + + if (priv->hw_owned && dev->netdev_ops->ndo_setup_tc) + dev->netdev_ops->ndo_setup_tc(dev, 0); + else + netdev_set_num_tc(dev, 0); + + kfree(priv->qdiscs); +} + +static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt) +{ + int i, j; + + /* Verify num_tc is not out of max range */ + if (qopt->num_tc > TC_MAX_QUEUE) + return -EINVAL; + + /* Verify priority mapping uses valid tcs */ + for (i = 0; i < TC_BITMASK + 1; i++) { + if (qopt->prio_tc_map[i] >= qopt->num_tc) + return -EINVAL; + } + + /* net_device does not support requested operation */ + if (qopt->hw && !dev->netdev_ops->ndo_setup_tc) + return -EINVAL; + + /* if hw owned qcount and qoffset are taken from LLD so + * no reason to verify them here + */ + if (qopt->hw) + return 0; + + for (i = 0; i < qopt->num_tc; i++) { + unsigned int last = qopt->offset[i] + qopt->count[i]; + + /* Verify the queue count is in tx range being equal to the + * real_num_tx_queues indicates the last queue is in use. + */ + if (qopt->offset[i] >= dev->real_num_tx_queues || + !qopt->count[i] || + last > dev->real_num_tx_queues) + return -EINVAL; + + /* Verify that the offset and counts do not overlap */ + for (j = i + 1; j < qopt->num_tc; j++) { + if (last > qopt->offset[j]) + return -EINVAL; + } + } + + return 0; +} + +static int mqprio_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + struct netdev_queue *dev_queue; + struct Qdisc *qdisc; + int i, err = -EOPNOTSUPP; + struct tc_mqprio_qopt *qopt = NULL; + + BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE); + BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK); + + if (sch->parent != TC_H_ROOT) + return -EOPNOTSUPP; + + if (!netif_is_multiqueue(dev)) + return -EOPNOTSUPP; + + if (nla_len(opt) < sizeof(*qopt)) + return -EINVAL; + + qopt = nla_data(opt); + if (mqprio_parse_opt(dev, qopt)) + return -EINVAL; + + /* pre-allocate qdisc, attachment can't fail */ + priv->qdiscs = kcalloc(dev->num_tx_queues, sizeof(priv->qdiscs[0]), + GFP_KERNEL); + if (priv->qdiscs == NULL) { + err = -ENOMEM; + goto err; + } + + for (i = 0; i < dev->num_tx_queues; i++) { + dev_queue = netdev_get_tx_queue(dev, i); + qdisc = qdisc_create_dflt(dev_queue, &pfifo_fast_ops, + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(i + 1))); + if (qdisc == NULL) { + err = -ENOMEM; + goto err; + } + priv->qdiscs[i] = qdisc; + } + + /* If the mqprio options indicate that hardware should own + * the queue mapping then run ndo_setup_tc otherwise use the + * supplied and verified mapping + */ + if (qopt->hw) { + priv->hw_owned = 1; + err = dev->netdev_ops->ndo_setup_tc(dev, qopt->num_tc); + if (err) + goto err; + } else { + netdev_set_num_tc(dev, qopt->num_tc); + for (i = 0; i < qopt->num_tc; i++) + netdev_set_tc_queue(dev, i, + qopt->count[i], qopt->offset[i]); + } + + /* Always use supplied priority mappings */ + for (i = 0; i < TC_BITMASK + 1; i++) + netdev_set_prio_tc_map(dev, i, qopt->prio_tc_map[i]); + + sch->flags |= TCQ_F_MQROOT; + return 0; + +err: + mqprio_destroy(sch); + return err; +} + +static void mqprio_attach(struct Qdisc *sch) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + struct Qdisc *qdisc; + unsigned int ntx; + + /* Attach underlying qdisc */ + for (ntx = 0; ntx < dev->num_tx_queues; ntx++) { + qdisc = priv->qdiscs[ntx]; + qdisc = dev_graft_qdisc(qdisc->dev_queue, qdisc); + if (qdisc) + qdisc_destroy(qdisc); + } + kfree(priv->qdiscs); + priv->qdiscs = NULL; +} + +static struct netdev_queue *mqprio_queue_get(struct Qdisc *sch, + unsigned long cl) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx = cl - 1 - netdev_get_num_tc(dev); + + if (ntx >= dev->num_tx_queues) + return NULL; + return netdev_get_tx_queue(dev, ntx); +} + +static int mqprio_graft(struct Qdisc *sch, unsigned long cl, struct Qdisc *new, + struct Qdisc **old) +{ + struct net_device *dev = qdisc_dev(sch); + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + + if (!dev_queue) + return -EINVAL; + + if (dev->flags & IFF_UP) + dev_deactivate(dev); + + *old = dev_graft_qdisc(dev_queue, new); + + if (dev->flags & IFF_UP) + dev_activate(dev); + + return 0; +} + +static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct net_device *dev = qdisc_dev(sch); + struct mqprio_sched *priv = qdisc_priv(sch); + unsigned char *b = skb_tail_pointer(skb); + struct tc_mqprio_qopt opt = { 0 }; + struct Qdisc *qdisc; + unsigned int i; + + sch->q.qlen = 0; + memset(&sch->bstats, 0, sizeof(sch->bstats)); + memset(&sch->qstats, 0, sizeof(sch->qstats)); + + for (i = 0; i < dev->num_tx_queues; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc; + spin_lock_bh(qdisc_lock(qdisc)); + sch->q.qlen += qdisc->q.qlen; + sch->bstats.bytes += qdisc->bstats.bytes; + sch->bstats.packets += qdisc->bstats.packets; + sch->qstats.qlen += qdisc->qstats.qlen; + sch->qstats.backlog += qdisc->qstats.backlog; + sch->qstats.drops += qdisc->qstats.drops; + sch->qstats.requeues += qdisc->qstats.requeues; + sch->qstats.overlimits += qdisc->qstats.overlimits; + spin_unlock_bh(qdisc_lock(qdisc)); + } + + opt.num_tc = netdev_get_num_tc(dev); + memcpy(opt.prio_tc_map, dev->prio_tc_map, sizeof(opt.prio_tc_map)); + opt.hw = priv->hw_owned; + + for (i = 0; i < netdev_get_num_tc(dev); i++) { + opt.count[i] = dev->tc_to_txq[i].count; + opt.offset[i] = dev->tc_to_txq[i].offset; + } + + NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); + + return skb->len; +nla_put_failure: + nlmsg_trim(skb, b); + return -1; +} + +static struct Qdisc *mqprio_leaf(struct Qdisc *sch, unsigned long cl) +{ + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + + if (!dev_queue) + return NULL; + + return dev_queue->qdisc_sleeping; +} + +static unsigned long mqprio_get(struct Qdisc *sch, u32 classid) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned int ntx = TC_H_MIN(classid); + + if (ntx > dev->num_tx_queues + netdev_get_num_tc(dev)) + return 0; + return ntx; +} + +static void mqprio_put(struct Qdisc *sch, unsigned long cl) +{ +} + +static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct net_device *dev = qdisc_dev(sch); + + if (cl <= netdev_get_num_tc(dev)) { + tcm->tcm_parent = TC_H_ROOT; + tcm->tcm_info = 0; + } else { + int i; + struct netdev_queue *dev_queue; + + dev_queue = mqprio_queue_get(sch, cl); + tcm->tcm_parent = 0; + for (i = 0; i < netdev_get_num_tc(dev); i++) { + struct netdev_tc_txq tc = dev->tc_to_txq[i]; + int q_idx = cl - netdev_get_num_tc(dev); + + if (q_idx > tc.offset && + q_idx <= tc.offset + tc.count) { + tcm->tcm_parent = + TC_H_MAKE(TC_H_MAJ(sch->handle), + TC_H_MIN(i + 1)); + break; + } + } + tcm->tcm_info = dev_queue->qdisc_sleeping->handle; + } + tcm->tcm_handle |= TC_H_MIN(cl); + return 0; +} + +static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, + struct gnet_dump *d) +{ + struct net_device *dev = qdisc_dev(sch); + + if (cl <= netdev_get_num_tc(dev)) { + int i; + struct Qdisc *qdisc; + struct gnet_stats_queue qstats = {0}; + struct gnet_stats_basic_packed bstats = {0}; + struct netdev_tc_txq tc = dev->tc_to_txq[cl - 1]; + + /* Drop lock here it will be reclaimed before touching + * statistics this is required because the d->lock we + * hold here is the look on dev_queue->qdisc_sleeping + * also acquired below. + */ + spin_unlock_bh(d->lock); + + for (i = tc.offset; i < tc.offset + tc.count; i++) { + qdisc = netdev_get_tx_queue(dev, i)->qdisc; + spin_lock_bh(qdisc_lock(qdisc)); + bstats.bytes += qdisc->bstats.bytes; + bstats.packets += qdisc->bstats.packets; + qstats.qlen += qdisc->qstats.qlen; + qstats.backlog += qdisc->qstats.backlog; + qstats.drops += qdisc->qstats.drops; + qstats.requeues += qdisc->qstats.requeues; + qstats.overlimits += qdisc->qstats.overlimits; + spin_unlock_bh(qdisc_lock(qdisc)); + } + /* Reclaim root sleeping lock before completing stats */ + spin_lock_bh(d->lock); + if (gnet_stats_copy_basic(d, &bstats) < 0 || + gnet_stats_copy_queue(d, &qstats) < 0) + return -1; + } else { + struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); + + sch = dev_queue->qdisc_sleeping; + sch->qstats.qlen = sch->q.qlen; + if (gnet_stats_copy_basic(d, &sch->bstats) < 0 || + gnet_stats_copy_queue(d, &sch->qstats) < 0) + return -1; + } + return 0; +} + +static void mqprio_walk(struct Qdisc *sch, struct qdisc_walker *arg) +{ + struct net_device *dev = qdisc_dev(sch); + unsigned long ntx; + + if (arg->stop) + return; + + /* Walk hierarchy with a virtual class per tc */ + arg->count = arg->skip; + for (ntx = arg->skip; + ntx < dev->num_tx_queues + netdev_get_num_tc(dev); + ntx++) { + if (arg->fn(sch, ntx + 1, arg) < 0) { + arg->stop = 1; + break; + } + arg->count++; + } +} + +static const struct Qdisc_class_ops mqprio_class_ops = { + .graft = mqprio_graft, + .leaf = mqprio_leaf, + .get = mqprio_get, + .put = mqprio_put, + .walk = mqprio_walk, + .dump = mqprio_dump_class, + .dump_stats = mqprio_dump_class_stats, +}; + +struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { + .cl_ops = &mqprio_class_ops, + .id = "mqprio", + .priv_size = sizeof(struct mqprio_sched), + .init = mqprio_init, + .destroy = mqprio_destroy, + .attach = mqprio_attach, + .dump = mqprio_dump, + .owner = THIS_MODULE, +}; + +static int __init mqprio_module_init(void) +{ + return register_qdisc(&mqprio_qdisc_ops); +} + +static void __exit mqprio_module_exit(void) +{ + unregister_qdisc(&mqprio_qdisc_ops); +} + +module_init(mqprio_module_init); +module_exit(mqprio_module_exit); + +MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index 436a2e7..edc1950 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -156,7 +156,7 @@ static unsigned int multiq_drop(struct Qdisc *sch) unsigned int len; struct Qdisc *qdisc; - for (band = q->bands-1; band >= 0; band--) { + for (band = q->bands - 1; band >= 0; band--) { qdisc = q->queues[band]; if (qdisc->ops->drop) { len = qdisc->ops->drop(qdisc); @@ -265,7 +265,7 @@ static int multiq_init(struct Qdisc *sch, struct nlattr *opt) for (i = 0; i < q->max_bands; i++) q->queues[i] = &noop_qdisc; - err = multiq_tune(sch,opt); + err = multiq_tune(sch, opt); if (err) kfree(q->queues); @@ -346,7 +346,7 @@ static int multiq_dump_class(struct Qdisc *sch, unsigned long cl, struct multiq_sched_data *q = qdisc_priv(sch); tcm->tcm_handle |= TC_H_MIN(cl); - tcm->tcm_info = q->queues[cl-1]->handle; + tcm->tcm_info = q->queues[cl - 1]->handle; return 0; } @@ -378,7 +378,7 @@ static void multiq_walk(struct Qdisc *sch, struct qdisc_walker *arg) arg->count++; continue; } - if (arg->fn(sch, band+1, arg) < 0) { + if (arg->fn(sch, band + 1, arg) < 0) { arg->stop = 1; break; } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 6a3006b..64f0d32 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -211,8 +211,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) } cb = netem_skb_cb(skb); - if (q->gap == 0 || /* not doing reordering */ - q->counter < q->gap || /* inside last reordering gap */ + if (q->gap == 0 || /* not doing reordering */ + q->counter < q->gap || /* inside last reordering gap */ q->reorder < get_crandom(&q->reorder_cor)) { psched_time_t now; psched_tdiff_t delay; @@ -248,7 +248,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) return ret; } -static unsigned int netem_drop(struct Qdisc* sch) +static unsigned int netem_drop(struct Qdisc *sch) { struct netem_sched_data *q = qdisc_priv(sch); unsigned int len = 0; @@ -265,7 +265,7 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) struct netem_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; - if (sch->flags & TCQ_F_THROTTLED) + if (qdisc_is_throttled(sch)) return NULL; skb = q->qdisc->ops->peek(q->qdisc); diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index fbd710d..2a318f2 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -22,8 +22,7 @@ #include <net/pkt_sched.h> -struct prio_sched_data -{ +struct prio_sched_data { int bands; struct tcf_proto *filter_list; u8 prio2band[TC_PRIO_MAX+1]; @@ -54,7 +53,7 @@ prio_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) if (!q->filter_list || err < 0) { if (TC_H_MAJ(band)) band = 0; - return q->queues[q->prio2band[band&TC_PRIO_MAX]]; + return q->queues[q->prio2band[band & TC_PRIO_MAX]]; } band = res.classid; } @@ -106,7 +105,7 @@ static struct sk_buff *prio_peek(struct Qdisc *sch) return NULL; } -static struct sk_buff *prio_dequeue(struct Qdisc* sch) +static struct sk_buff *prio_dequeue(struct Qdisc *sch) { struct prio_sched_data *q = qdisc_priv(sch); int prio; @@ -124,7 +123,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc* sch) } -static unsigned int prio_drop(struct Qdisc* sch) +static unsigned int prio_drop(struct Qdisc *sch) { struct prio_sched_data *q = qdisc_priv(sch); int prio; @@ -143,24 +142,24 @@ static unsigned int prio_drop(struct Qdisc* sch) static void -prio_reset(struct Qdisc* sch) +prio_reset(struct Qdisc *sch) { int prio; struct prio_sched_data *q = qdisc_priv(sch); - for (prio=0; prio<q->bands; prio++) + for (prio = 0; prio < q->bands; prio++) qdisc_reset(q->queues[prio]); sch->q.qlen = 0; } static void -prio_destroy(struct Qdisc* sch) +prio_destroy(struct Qdisc *sch) { int prio; struct prio_sched_data *q = qdisc_priv(sch); tcf_destroy_chain(&q->filter_list); - for (prio=0; prio<q->bands; prio++) + for (prio = 0; prio < q->bands; prio++) qdisc_destroy(q->queues[prio]); } @@ -177,7 +176,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) if (qopt->bands > TCQ_PRIO_BANDS || qopt->bands < 2) return -EINVAL; - for (i=0; i<=TC_PRIO_MAX; i++) { + for (i = 0; i <= TC_PRIO_MAX; i++) { if (qopt->priomap[i] >= qopt->bands) return -EINVAL; } @@ -186,7 +185,7 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) q->bands = qopt->bands; memcpy(q->prio2band, qopt->priomap, TC_PRIO_MAX+1); - for (i=q->bands; i<TCQ_PRIO_BANDS; i++) { + for (i = q->bands; i < TCQ_PRIO_BANDS; i++) { struct Qdisc *child = q->queues[i]; q->queues[i] = &noop_qdisc; if (child != &noop_qdisc) { @@ -196,9 +195,10 @@ static int prio_tune(struct Qdisc *sch, struct nlattr *opt) } sch_tree_unlock(sch); - for (i=0; i<q->bands; i++) { + for (i = 0; i < q->bands; i++) { if (q->queues[i] == &noop_qdisc) { struct Qdisc *child, *old; + child = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, TC_H_MAKE(sch->handle, i + 1)); @@ -224,7 +224,7 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) struct prio_sched_data *q = qdisc_priv(sch); int i; - for (i=0; i<TCQ_PRIO_BANDS; i++) + for (i = 0; i < TCQ_PRIO_BANDS; i++) q->queues[i] = &noop_qdisc; if (opt == NULL) { @@ -232,7 +232,7 @@ static int prio_init(struct Qdisc *sch, struct nlattr *opt) } else { int err; - if ((err= prio_tune(sch, opt)) != 0) + if ((err = prio_tune(sch, opt)) != 0) return err; } return 0; @@ -245,7 +245,7 @@ static int prio_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_prio_qopt opt; opt.bands = q->bands; - memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX+1); + memcpy(&opt.priomap, q->prio2band, TC_PRIO_MAX + 1); NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); @@ -342,7 +342,7 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) arg->count++; continue; } - if (arg->fn(sch, prio+1, arg) < 0) { + if (arg->fn(sch, prio + 1, arg) < 0) { arg->stop = 1; break; } @@ -350,7 +350,7 @@ static void prio_walk(struct Qdisc *sch, struct qdisc_walker *arg) } } -static struct tcf_proto ** prio_find_tcf(struct Qdisc *sch, unsigned long cl) +static struct tcf_proto **prio_find_tcf(struct Qdisc *sch, unsigned long cl) { struct prio_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_red.c b/net/sched/sch_red.c index 9f98dbd..6649463 100644 --- a/net/sched/sch_red.c +++ b/net/sched/sch_red.c @@ -36,8 +36,7 @@ if RED works correctly. */ -struct red_sched_data -{ +struct red_sched_data { u32 limit; /* HARD maximal queue length */ unsigned char flags; struct red_parms parms; @@ -55,7 +54,7 @@ static inline int red_use_harddrop(struct red_sched_data *q) return q->flags & TC_RED_HARDDROP; } -static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; @@ -67,29 +66,29 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc* sch) red_end_of_idle_period(&q->parms); switch (red_action(&q->parms, q->parms.qavg)) { - case RED_DONT_MARK: - break; - - case RED_PROB_MARK: - sch->qstats.overlimits++; - if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) { - q->stats.prob_drop++; - goto congestion_drop; - } - - q->stats.prob_mark++; - break; - - case RED_HARD_MARK: - sch->qstats.overlimits++; - if (red_use_harddrop(q) || !red_use_ecn(q) || - !INET_ECN_set_ce(skb)) { - q->stats.forced_drop++; - goto congestion_drop; - } - - q->stats.forced_mark++; - break; + case RED_DONT_MARK: + break; + + case RED_PROB_MARK: + sch->qstats.overlimits++; + if (!red_use_ecn(q) || !INET_ECN_set_ce(skb)) { + q->stats.prob_drop++; + goto congestion_drop; + } + + q->stats.prob_mark++; + break; + + case RED_HARD_MARK: + sch->qstats.overlimits++; + if (red_use_harddrop(q) || !red_use_ecn(q) || + !INET_ECN_set_ce(skb)) { + q->stats.forced_drop++; + goto congestion_drop; + } + + q->stats.forced_mark++; + break; } ret = qdisc_enqueue(skb, child); @@ -106,7 +105,7 @@ congestion_drop: return NET_XMIT_CN; } -static struct sk_buff * red_dequeue(struct Qdisc* sch) +static struct sk_buff *red_dequeue(struct Qdisc *sch) { struct sk_buff *skb; struct red_sched_data *q = qdisc_priv(sch); @@ -123,7 +122,7 @@ static struct sk_buff * red_dequeue(struct Qdisc* sch) return skb; } -static struct sk_buff * red_peek(struct Qdisc* sch) +static struct sk_buff *red_peek(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; @@ -131,7 +130,7 @@ static struct sk_buff * red_peek(struct Qdisc* sch) return child->ops->peek(child); } -static unsigned int red_drop(struct Qdisc* sch) +static unsigned int red_drop(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); struct Qdisc *child = q->qdisc; @@ -150,7 +149,7 @@ static unsigned int red_drop(struct Qdisc* sch) return 0; } -static void red_reset(struct Qdisc* sch) +static void red_reset(struct Qdisc *sch) { struct red_sched_data *q = qdisc_priv(sch); @@ -217,7 +216,7 @@ static int red_change(struct Qdisc *sch, struct nlattr *opt) return 0; } -static int red_init(struct Qdisc* sch, struct nlattr *opt) +static int red_init(struct Qdisc *sch, struct nlattr *opt) { struct red_sched_data *q = qdisc_priv(sch); diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index edea8ce..4cff442 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -21,6 +21,7 @@ #include <linux/skbuff.h> #include <linux/jhash.h> #include <linux/slab.h> +#include <linux/vmalloc.h> #include <net/ip.h> #include <net/netlink.h> #include <net/pkt_sched.h> @@ -76,7 +77,8 @@ #define SFQ_DEPTH 128 /* max number of packets per flow */ #define SFQ_SLOTS 128 /* max number of flows */ #define SFQ_EMPTY_SLOT 255 -#define SFQ_HASH_DIVISOR 1024 +#define SFQ_DEFAULT_HASH_DIVISOR 1024 + /* We use 16 bits to store allot, and want to handle packets up to 64K * Scale allot by 8 (1<<3) so that no overflow occurs. */ @@ -92,8 +94,7 @@ typedef unsigned char sfq_index; * while following values [SFQ_SLOTS ... SFQ_SLOTS + SFQ_DEPTH - 1] * are 'pointers' to dep[] array */ -struct sfq_head -{ +struct sfq_head { sfq_index next; sfq_index prev; }; @@ -108,13 +109,12 @@ struct sfq_slot { short allot; /* credit for this slot */ }; -struct sfq_sched_data -{ +struct sfq_sched_data { /* Parameters */ int perturb_period; - unsigned quantum; /* Allotment per round: MUST BE >= MTU */ + unsigned int quantum; /* Allotment per round: MUST BE >= MTU */ int limit; - + unsigned int divisor; /* number of slots in hash table */ /* Variables */ struct tcf_proto *filter_list; struct timer_list perturb_timer; @@ -122,7 +122,7 @@ struct sfq_sched_data sfq_index cur_depth; /* depth of longest slot */ unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ struct sfq_slot *tail; /* current slot in round */ - sfq_index ht[SFQ_HASH_DIVISOR]; /* Hash table */ + sfq_index *ht; /* Hash table (divisor slots) */ struct sfq_slot slots[SFQ_SLOTS]; struct sfq_head dep[SFQ_DEPTH]; /* Linked list of slots, indexed by depth */ }; @@ -137,12 +137,12 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index return &q->dep[val - SFQ_SLOTS]; } -static __inline__ unsigned sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1) +static unsigned int sfq_fold_hash(struct sfq_sched_data *q, u32 h, u32 h1) { - return jhash_2words(h, h1, q->perturbation) & (SFQ_HASH_DIVISOR - 1); + return jhash_2words(h, h1, q->perturbation) & (q->divisor - 1); } -static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) +static unsigned int sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) { u32 h, h2; @@ -157,13 +157,13 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) iph = ip_hdr(skb); h = (__force u32)iph->daddr; h2 = (__force u32)iph->saddr ^ iph->protocol; - if (iph->frag_off & htons(IP_MF|IP_OFFSET)) + if (iph->frag_off & htons(IP_MF | IP_OFFSET)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && pskb_network_may_pull(skb, iph->ihl * 4 + 4 + poff)) { iph = ip_hdr(skb); - h2 ^= *(u32*)((void *)iph + iph->ihl * 4 + poff); + h2 ^= *(u32 *)((void *)iph + iph->ihl * 4 + poff); } break; } @@ -181,7 +181,7 @@ static unsigned sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) if (poff >= 0 && pskb_network_may_pull(skb, sizeof(*iph) + 4 + poff)) { iph = ipv6_hdr(skb); - h2 ^= *(u32*)((void *)iph + sizeof(*iph) + poff); + h2 ^= *(u32 *)((void *)iph + sizeof(*iph) + poff); } break; } @@ -203,7 +203,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, if (TC_H_MAJ(skb->priority) == sch->handle && TC_H_MIN(skb->priority) > 0 && - TC_H_MIN(skb->priority) <= SFQ_HASH_DIVISOR) + TC_H_MIN(skb->priority) <= q->divisor) return TC_H_MIN(skb->priority); if (!q->filter_list) @@ -221,7 +221,7 @@ static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, return 0; } #endif - if (TC_H_MIN(res.classid) <= SFQ_HASH_DIVISOR) + if (TC_H_MIN(res.classid) <= q->divisor) return TC_H_MIN(res.classid); } return 0; @@ -497,7 +497,11 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) q->perturb_period = ctl->perturb_period * HZ; if (ctl->limit) q->limit = min_t(u32, ctl->limit, SFQ_DEPTH - 1); - + if (ctl->divisor) { + if (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536) + return -EINVAL; + q->divisor = ctl->divisor; + } qlen = sch->q.qlen; while (sch->q.qlen > q->limit) sfq_drop(sch); @@ -515,15 +519,13 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) static int sfq_init(struct Qdisc *sch, struct nlattr *opt) { struct sfq_sched_data *q = qdisc_priv(sch); + size_t sz; int i; q->perturb_timer.function = sfq_perturbation; q->perturb_timer.data = (unsigned long)sch; init_timer_deferrable(&q->perturb_timer); - for (i = 0; i < SFQ_HASH_DIVISOR; i++) - q->ht[i] = SFQ_EMPTY_SLOT; - for (i = 0; i < SFQ_DEPTH; i++) { q->dep[i].next = i + SFQ_SLOTS; q->dep[i].prev = i + SFQ_SLOTS; @@ -532,6 +534,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) q->limit = SFQ_DEPTH - 1; q->cur_depth = 0; q->tail = NULL; + q->divisor = SFQ_DEFAULT_HASH_DIVISOR; if (opt == NULL) { q->quantum = psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); @@ -543,10 +546,23 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt) return err; } + sz = sizeof(q->ht[0]) * q->divisor; + q->ht = kmalloc(sz, GFP_KERNEL); + if (!q->ht && sz > PAGE_SIZE) + q->ht = vmalloc(sz); + if (!q->ht) + return -ENOMEM; + for (i = 0; i < q->divisor; i++) + q->ht[i] = SFQ_EMPTY_SLOT; + for (i = 0; i < SFQ_SLOTS; i++) { slot_queue_init(&q->slots[i]); sfq_link(q, i); } + if (q->limit >= 1) + sch->flags |= TCQ_F_CAN_BYPASS; + else + sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } @@ -557,6 +573,10 @@ static void sfq_destroy(struct Qdisc *sch) tcf_destroy_chain(&q->filter_list); q->perturb_period = 0; del_timer_sync(&q->perturb_timer); + if (is_vmalloc_addr(q->ht)) + vfree(q->ht); + else + kfree(q->ht); } static int sfq_dump(struct Qdisc *sch, struct sk_buff *skb) @@ -569,7 +589,7 @@ static int sfq_dump(struct Qdisc *sch, struct sk_buff *skb) opt.perturb_period = q->perturb_period / HZ; opt.limit = q->limit; - opt.divisor = SFQ_HASH_DIVISOR; + opt.divisor = q->divisor; opt.flows = q->limit; NLA_PUT(skb, TCA_OPTIONS, sizeof(opt), &opt); @@ -594,6 +614,8 @@ static unsigned long sfq_get(struct Qdisc *sch, u32 classid) static unsigned long sfq_bind(struct Qdisc *sch, unsigned long parent, u32 classid) { + /* we cannot bypass queue discipline anymore */ + sch->flags &= ~TCQ_F_CAN_BYPASS; return 0; } @@ -647,7 +669,7 @@ static void sfq_walk(struct Qdisc *sch, struct qdisc_walker *arg) if (arg->stop) return; - for (i = 0; i < SFQ_HASH_DIVISOR; i++) { + for (i = 0; i < q->divisor; i++) { if (q->ht[i] == SFQ_EMPTY_SLOT || arg->count < arg->skip) { arg->count++; diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index e931658..1dcfb52 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -97,8 +97,7 @@ changed the limit is not effective anymore. */ -struct tbf_sched_data -{ +struct tbf_sched_data { /* Parameters */ u32 limit; /* Maximal length of backlog: bytes */ u32 buffer; /* Token bucket depth/rate: MUST BE >= MTU/B */ @@ -115,10 +114,10 @@ struct tbf_sched_data struct qdisc_watchdog watchdog; /* Watchdog timer */ }; -#define L2T(q,L) qdisc_l2t((q)->R_tab,L) -#define L2T_P(q,L) qdisc_l2t((q)->P_tab,L) +#define L2T(q, L) qdisc_l2t((q)->R_tab, L) +#define L2T_P(q, L) qdisc_l2t((q)->P_tab, L) -static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) +static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); int ret; @@ -137,7 +136,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch) return NET_XMIT_SUCCESS; } -static unsigned int tbf_drop(struct Qdisc* sch) +static unsigned int tbf_drop(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); unsigned int len = 0; @@ -149,7 +148,7 @@ static unsigned int tbf_drop(struct Qdisc* sch) return len; } -static struct sk_buff *tbf_dequeue(struct Qdisc* sch) +static struct sk_buff *tbf_dequeue(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); struct sk_buff *skb; @@ -185,7 +184,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc* sch) q->tokens = toks; q->ptokens = ptoks; sch->q.qlen--; - sch->flags &= ~TCQ_F_THROTTLED; + qdisc_unthrottled(sch); qdisc_bstats_update(sch, skb); return skb; } @@ -209,7 +208,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc* sch) return NULL; } -static void tbf_reset(struct Qdisc* sch) +static void tbf_reset(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -227,7 +226,7 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = { [TCA_TBF_PTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE }, }; -static int tbf_change(struct Qdisc* sch, struct nlattr *opt) +static int tbf_change(struct Qdisc *sch, struct nlattr *opt) { int err; struct tbf_sched_data *q = qdisc_priv(sch); @@ -236,7 +235,7 @@ static int tbf_change(struct Qdisc* sch, struct nlattr *opt) struct qdisc_rate_table *rtab = NULL; struct qdisc_rate_table *ptab = NULL; struct Qdisc *child = NULL; - int max_size,n; + int max_size, n; err = nla_parse_nested(tb, TCA_TBF_PTAB, opt, tbf_policy); if (err < 0) @@ -259,15 +258,18 @@ static int tbf_change(struct Qdisc* sch, struct nlattr *opt) } for (n = 0; n < 256; n++) - if (rtab->data[n] > qopt->buffer) break; - max_size = (n << qopt->rate.cell_log)-1; + if (rtab->data[n] > qopt->buffer) + break; + max_size = (n << qopt->rate.cell_log) - 1; if (ptab) { int size; for (n = 0; n < 256; n++) - if (ptab->data[n] > qopt->mtu) break; - size = (n << qopt->peakrate.cell_log)-1; - if (size < max_size) max_size = size; + if (ptab->data[n] > qopt->mtu) + break; + size = (n << qopt->peakrate.cell_log) - 1; + if (size < max_size) + max_size = size; } if (max_size < 0) goto done; @@ -310,7 +312,7 @@ done: return err; } -static int tbf_init(struct Qdisc* sch, struct nlattr *opt) +static int tbf_init(struct Qdisc *sch, struct nlattr *opt) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -422,8 +424,7 @@ static void tbf_walk(struct Qdisc *sch, struct qdisc_walker *walker) } } -static const struct Qdisc_class_ops tbf_class_ops = -{ +static const struct Qdisc_class_ops tbf_class_ops = { .graft = tbf_graft, .leaf = tbf_leaf, .get = tbf_get, diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index d84e732..45cd300 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -53,8 +53,7 @@ which will not break load balancing, though native slave traffic will have the highest priority. */ -struct teql_master -{ +struct teql_master { struct Qdisc_ops qops; struct net_device *dev; struct Qdisc *slaves; @@ -65,22 +64,21 @@ struct teql_master unsigned long tx_dropped; }; -struct teql_sched_data -{ +struct teql_sched_data { struct Qdisc *next; struct teql_master *m; struct neighbour *ncache; struct sk_buff_head q; }; -#define NEXT_SLAVE(q) (((struct teql_sched_data*)qdisc_priv(q))->next) +#define NEXT_SLAVE(q) (((struct teql_sched_data *)qdisc_priv(q))->next) -#define FMASK (IFF_BROADCAST|IFF_POINTOPOINT) +#define FMASK (IFF_BROADCAST | IFF_POINTOPOINT) /* "teql*" qdisc routines */ static int -teql_enqueue(struct sk_buff *skb, struct Qdisc* sch) +teql_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct net_device *dev = qdisc_dev(sch); struct teql_sched_data *q = qdisc_priv(sch); @@ -96,7 +94,7 @@ teql_enqueue(struct sk_buff *skb, struct Qdisc* sch) } static struct sk_buff * -teql_dequeue(struct Qdisc* sch) +teql_dequeue(struct Qdisc *sch) { struct teql_sched_data *dat = qdisc_priv(sch); struct netdev_queue *dat_queue; @@ -118,13 +116,13 @@ teql_dequeue(struct Qdisc* sch) } static struct sk_buff * -teql_peek(struct Qdisc* sch) +teql_peek(struct Qdisc *sch) { /* teql is meant to be used as root qdisc */ return NULL; } -static __inline__ void +static inline void teql_neigh_release(struct neighbour *n) { if (n) @@ -132,7 +130,7 @@ teql_neigh_release(struct neighbour *n) } static void -teql_reset(struct Qdisc* sch) +teql_reset(struct Qdisc *sch) { struct teql_sched_data *dat = qdisc_priv(sch); @@ -142,13 +140,14 @@ teql_reset(struct Qdisc* sch) } static void -teql_destroy(struct Qdisc* sch) +teql_destroy(struct Qdisc *sch) { struct Qdisc *q, *prev; struct teql_sched_data *dat = qdisc_priv(sch); struct teql_master *master = dat->m; - if ((prev = master->slaves) != NULL) { + prev = master->slaves; + if (prev) { do { q = NEXT_SLAVE(prev); if (q == sch) { @@ -180,7 +179,7 @@ teql_destroy(struct Qdisc* sch) static int teql_qdisc_init(struct Qdisc *sch, struct nlattr *opt) { struct net_device *dev = qdisc_dev(sch); - struct teql_master *m = (struct teql_master*)sch->ops; + struct teql_master *m = (struct teql_master *)sch->ops; struct teql_sched_data *q = qdisc_priv(sch); if (dev->hard_header_len > m->dev->hard_header_len) @@ -291,7 +290,8 @@ restart: nores = 0; busy = 0; - if ((q = start) == NULL) + q = start; + if (!q) goto drop; do { @@ -356,10 +356,10 @@ drop: static int teql_master_open(struct net_device *dev) { - struct Qdisc * q; + struct Qdisc *q; struct teql_master *m = netdev_priv(dev); int mtu = 0xFFFE; - unsigned flags = IFF_NOARP|IFF_MULTICAST; + unsigned int flags = IFF_NOARP | IFF_MULTICAST; if (m->slaves == NULL) return -EUNATCH; @@ -427,7 +427,7 @@ static int teql_master_mtu(struct net_device *dev, int new_mtu) do { if (new_mtu > qdisc_dev(q)->mtu) return -EINVAL; - } while ((q=NEXT_SLAVE(q)) != m->slaves); + } while ((q = NEXT_SLAVE(q)) != m->slaves); } dev->mtu = new_mtu; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index dd419d2..d8d98d5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1475,6 +1475,12 @@ restart: goto out_free; } + if (sk_filter(other, skb) < 0) { + /* Toss the packet but do not return any error to the sender */ + err = len; + goto out_free; + } + unix_state_lock(other); err = -EPERM; if (!unix_may_send(sk, other)) @@ -1978,36 +1984,38 @@ static int unix_shutdown(struct socket *sock, int mode) mode = (mode+1)&(RCV_SHUTDOWN|SEND_SHUTDOWN); - if (mode) { - unix_state_lock(sk); - sk->sk_shutdown |= mode; - other = unix_peer(sk); - if (other) - sock_hold(other); - unix_state_unlock(sk); - sk->sk_state_change(sk); - - if (other && - (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) { - - int peer_mode = 0; - - if (mode&RCV_SHUTDOWN) - peer_mode |= SEND_SHUTDOWN; - if (mode&SEND_SHUTDOWN) - peer_mode |= RCV_SHUTDOWN; - unix_state_lock(other); - other->sk_shutdown |= peer_mode; - unix_state_unlock(other); - other->sk_state_change(other); - if (peer_mode == SHUTDOWN_MASK) - sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP); - else if (peer_mode & RCV_SHUTDOWN) - sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN); - } - if (other) - sock_put(other); + if (!mode) + return 0; + + unix_state_lock(sk); + sk->sk_shutdown |= mode; + other = unix_peer(sk); + if (other) + sock_hold(other); + unix_state_unlock(sk); + sk->sk_state_change(sk); + + if (other && + (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)) { + + int peer_mode = 0; + + if (mode&RCV_SHUTDOWN) + peer_mode |= SEND_SHUTDOWN; + if (mode&SEND_SHUTDOWN) + peer_mode |= RCV_SHUTDOWN; + unix_state_lock(other); + other->sk_shutdown |= peer_mode; + unix_state_unlock(other); + other->sk_state_change(other); + if (peer_mode == SHUTDOWN_MASK) + sk_wake_async(other, SOCK_WAKE_WAITD, POLL_HUP); + else if (peer_mode & RCV_SHUTDOWN) + sk_wake_async(other, SOCK_WAKE_WAITD, POLL_IN); } + if (other) + sock_put(other); + return 0; } diff --git a/net/wanrouter/wanmain.c b/net/wanrouter/wanmain.c index 74944a2..788a12c 100644 --- a/net/wanrouter/wanmain.c +++ b/net/wanrouter/wanmain.c @@ -59,8 +59,6 @@ #include <asm/uaccess.h> /* copy_to/from_user */ #include <linux/init.h> /* __initfunc et al. */ -#define KMEM_SAFETYZONE 8 - #define DEV_TO_SLAVE(dev) (*((struct net_device **)netdev_priv(dev))) /* diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 37693b6..c565689 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -1801,9 +1801,9 @@ void regulatory_hint_disconnect(void) static bool freq_is_chan_12_13_14(u16 freq) { - if (freq == ieee80211_channel_to_frequency(12) || - freq == ieee80211_channel_to_frequency(13) || - freq == ieee80211_channel_to_frequency(14)) + if (freq == ieee80211_channel_to_frequency(12, IEEE80211_BAND_2GHZ) || + freq == ieee80211_channel_to_frequency(13, IEEE80211_BAND_2GHZ) || + freq == ieee80211_channel_to_frequency(14, IEEE80211_BAND_2GHZ)) return true; return false; } diff --git a/net/wireless/util.c b/net/wireless/util.c index 7620ae2..4ed065d 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -29,29 +29,37 @@ ieee80211_get_response_rate(struct ieee80211_supported_band *sband, } EXPORT_SYMBOL(ieee80211_get_response_rate); -int ieee80211_channel_to_frequency(int chan) +int ieee80211_channel_to_frequency(int chan, enum ieee80211_band band) { - if (chan < 14) - return 2407 + chan * 5; - - if (chan == 14) - return 2484; - - /* FIXME: 802.11j 17.3.8.3.2 */ - return (chan + 1000) * 5; + /* see 802.11 17.3.8.3.2 and Annex J + * there are overlapping channel numbers in 5GHz and 2GHz bands */ + if (band == IEEE80211_BAND_5GHZ) { + if (chan >= 182 && chan <= 196) + return 4000 + chan * 5; + else + return 5000 + chan * 5; + } else { /* IEEE80211_BAND_2GHZ */ + if (chan == 14) + return 2484; + else if (chan < 14) + return 2407 + chan * 5; + else + return 0; /* not supported */ + } } EXPORT_SYMBOL(ieee80211_channel_to_frequency); int ieee80211_frequency_to_channel(int freq) { + /* see 802.11 17.3.8.3.2 and Annex J */ if (freq == 2484) return 14; - - if (freq < 2484) + else if (freq < 2484) return (freq - 2407) / 5; - - /* FIXME: 802.11j 17.3.8.3.2 */ - return freq/5 - 1000; + else if (freq >= 4910 && freq <= 4980) + return (freq - 4000) / 5; + else + return (freq - 5000) / 5; } EXPORT_SYMBOL(ieee80211_frequency_to_channel); diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 3e5dbd4..7f1f4ec 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -267,9 +267,12 @@ int cfg80211_wext_freq(struct wiphy *wiphy, struct iw_freq *freq) * -EINVAL for impossible things. */ if (freq->e == 0) { + enum ieee80211_band band = IEEE80211_BAND_2GHZ; if (freq->m < 0) return 0; - return ieee80211_channel_to_frequency(freq->m); + if (freq->m > 14) + band = IEEE80211_BAND_5GHZ; + return ieee80211_channel_to_frequency(freq->m, band); } else { int i, div = 1000000; for (i = 0; i < freq->e; i++) |