diff options
Diffstat (limited to 'drivers/net/ethernet/intel')
55 files changed, 1312 insertions, 664 deletions
diff --git a/drivers/net/ethernet/intel/Kconfig b/drivers/net/ethernet/intel/Kconfig index 59e1bc0f609e..31fb76ee9d82 100644 --- a/drivers/net/ethernet/intel/Kconfig +++ b/drivers/net/ethernet/intel/Kconfig @@ -33,7 +33,7 @@ config E100 to identify the adapter. More specific information on configuring the driver is in - <file:Documentation/networking/e100.rst>. + <file:Documentation/networking/device_drivers/intel/e100.rst>. To compile this driver as a module, choose M here. The module will be called e100. @@ -49,7 +49,7 @@ config E1000 <http://support.intel.com> More specific information on configuring the driver is in - <file:Documentation/networking/e1000.rst>. + <file:Documentation/networking/device_drivers/intel/e1000.rst>. To compile this driver as a module, choose M here. The module will be called e1000. @@ -69,7 +69,7 @@ config E1000E <http://support.intel.com> More specific information on configuring the driver is in - <file:Documentation/networking/e1000e.rst>. + <file:Documentation/networking/device_drivers/intel/e1000e.rst>. To compile this driver as a module, choose M here. The module will be called e1000e. @@ -97,7 +97,7 @@ config IGB <http://support.intel.com> More specific information on configuring the driver is in - <file:Documentation/networking/igb.rst>. + <file:Documentation/networking/device_drivers/intel/igb.rst>. To compile this driver as a module, choose M here. The module will be called igb. @@ -133,7 +133,7 @@ config IGBVF <http://support.intel.com> More specific information on configuring the driver is in - <file:Documentation/networking/igbvf.rst>. + <file:Documentation/networking/device_drivers/intel/igbvf.rst>. To compile this driver as a module, choose M here. The module will be called igbvf. @@ -150,7 +150,7 @@ config IXGB <http://support.intel.com> More specific information on configuring the driver is in - <file:Documentation/networking/ixgb.rst>. + <file:Documentation/networking/device_drivers/intel/ixgb.rst>. To compile this driver as a module, choose M here. The module will be called ixgb. @@ -159,6 +159,7 @@ config IXGBE tristate "Intel(R) 10GbE PCI Express adapters support" depends on PCI select MDIO + select MDIO_DEVICE imply PTP_1588_CLOCK ---help--- This driver supports Intel(R) 10GbE PCI Express family of @@ -168,7 +169,7 @@ config IXGBE <http://support.intel.com> More specific information on configuring the driver is in - <file:Documentation/networking/ixgbe.rst>. + <file:Documentation/networking/device_drivers/intel/ixgbe.rst>. To compile this driver as a module, choose M here. The module will be called ixgbe. @@ -220,7 +221,7 @@ config IXGBEVF <http://support.intel.com> More specific information on configuring the driver is in - <file:Documentation/networking/ixgbevf.rst>. + <file:Documentation/networking/device_drivers/intel/ixgbevf.rst>. To compile this driver as a module, choose M here. The module will be called ixgbevf. MSI-X interrupt support is required @@ -247,7 +248,7 @@ config I40E <http://support.intel.com> More specific information on configuring the driver is in - <file:Documentation/networking/i40e.rst>. + <file:Documentation/networking/device_drivers/intel/i40e.rst>. To compile this driver as a module, choose M here. The module will be called i40e. @@ -282,7 +283,7 @@ config I40EVF This driver was formerly named i40evf. More specific information on configuring the driver is in - <file:Documentation/networking/iavf.rst>. + <file:Documentation/networking/device_drivers/intel/iavf.rst>. To compile this driver as a module, choose M here. The module will be called iavf. MSI-X interrupt support is required @@ -300,7 +301,7 @@ config ICE <http://support.intel.com> More specific information on configuring the driver is in - <file:Documentation/networking/ice.rst>. + <file:Documentation/networking/device_drivers/intel/ice.rst>. To compile this driver as a module, choose M here. The module will be called ice. @@ -318,7 +319,7 @@ config FM10K <http://support.intel.com> More specific information on configuring the driver is in - <file:Documentation/networking/fm10k.rst>. + <file:Documentation/networking/device_drivers/intel/fm10k.rst>. To compile this driver as a module, choose M here. The module will be called fm10k. MSI-X interrupt support is required diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 7c4b55482f72..0fd268070fb4 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -1345,8 +1345,8 @@ static inline int e100_load_ucode_wait(struct nic *nic) fw = e100_request_firmware(nic); /* If it's NULL, then no ucode is required */ - if (!fw || IS_ERR(fw)) - return PTR_ERR(fw); + if (IS_ERR_OR_NULL(fw)) + return PTR_ERR_OR_ZERO(fw); if ((err = e100_exec_cb(nic, (void *)fw, e100_setup_ucode))) netif_err(nic, probe, nic->netdev, @@ -2225,11 +2225,13 @@ static int e100_poll(struct napi_struct *napi, int budget) e100_rx_clean(nic, &work_done, budget); e100_tx_clean(nic); - /* If budget not fully consumed, exit the polling mode */ - if (work_done < budget) { - napi_complete_done(napi, work_done); + /* If budget fully consumed, continue polling */ + if (work_done == budget) + return budget; + + /* only re-enable interrupt if stack agrees polling is really done */ + if (likely(napi_complete_done(napi, work_done))) e100_enable_irq(nic); - } return work_done; } diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 43b6d3cec3b3..8fe9af0e2ab7 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -3803,14 +3803,15 @@ static int e1000_clean(struct napi_struct *napi, int budget) adapter->clean_rx(adapter, &adapter->rx_ring[0], &work_done, budget); - if (!tx_clean_complete) - work_done = budget; + if (!tx_clean_complete || work_done == budget) + return budget; - /* If budget not fully consumed, exit the polling mode */ - if (work_done < budget) { + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) { if (likely(adapter->itr_setting & 3)) e1000_set_itr(adapter); - napi_complete_done(napi, work_done); if (!test_bit(__E1000_DOWN, &adapter->flags)) e1000_irq_enable(adapter); } diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index c760dc72c520..be13227f1697 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -505,6 +505,9 @@ extern const struct e1000_info e1000_es2_info; void e1000e_ptp_init(struct e1000_adapter *adapter); void e1000e_ptp_remove(struct e1000_adapter *adapter); +u64 e1000e_read_systim(struct e1000_adapter *adapter, + struct ptp_system_timestamp *sts); + static inline s32 e1000_phy_hw_reset(struct e1000_hw *hw) { return hw->phy.ops.reset(hw); diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index 16a73bd9f4cb..308c006cb41d 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -2651,9 +2651,9 @@ err: /** * e1000e_poll - NAPI Rx polling callback * @napi: struct associated with this polling callback - * @weight: number of packets driver is allowed to process this poll + * @budget: number of packets driver is allowed to process this poll **/ -static int e1000e_poll(struct napi_struct *napi, int weight) +static int e1000e_poll(struct napi_struct *napi, int budget) { struct e1000_adapter *adapter = container_of(napi, struct e1000_adapter, napi); @@ -2667,16 +2667,17 @@ static int e1000e_poll(struct napi_struct *napi, int weight) (adapter->rx_ring->ims_val & adapter->tx_ring->ims_val)) tx_cleaned = e1000_clean_tx_irq(adapter->tx_ring); - adapter->clean_rx(adapter->rx_ring, &work_done, weight); + adapter->clean_rx(adapter->rx_ring, &work_done, budget); - if (!tx_cleaned) - work_done = weight; + if (!tx_cleaned || work_done == budget) + return budget; - /* If weight not fully consumed, exit the polling mode */ - if (work_done < weight) { + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) { if (adapter->itr_setting & 3) e1000_set_itr(adapter); - napi_complete_done(napi, work_done); if (!test_bit(__E1000_DOWN, &adapter->state)) { if (adapter->msix_entries) ew32(IMS, adapter->rx_ring->ims_val); @@ -4319,13 +4320,16 @@ void e1000e_reinit_locked(struct e1000_adapter *adapter) /** * e1000e_sanitize_systim - sanitize raw cycle counter reads * @hw: pointer to the HW structure - * @systim: time value read, sanitized and returned + * @systim: PHC time value read, sanitized and returned + * @sts: structure to hold system time before and after reading SYSTIML, + * may be NULL * * Errata for 82574/82583 possible bad bits read from SYSTIMH/L: * check to see that the time is incrementing at a reasonable * rate and is a multiple of incvalue. **/ -static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim) +static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim, + struct ptp_system_timestamp *sts) { u64 time_delta, rem, temp; u64 systim_next; @@ -4335,7 +4339,9 @@ static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim) incvalue = er32(TIMINCA) & E1000_TIMINCA_INCVALUE_MASK; for (i = 0; i < E1000_MAX_82574_SYSTIM_REREADS; i++) { /* latch SYSTIMH on read of SYSTIML */ + ptp_read_system_prets(sts); systim_next = (u64)er32(SYSTIML); + ptp_read_system_postts(sts); systim_next |= (u64)er32(SYSTIMH) << 32; time_delta = systim_next - systim; @@ -4353,15 +4359,16 @@ static u64 e1000e_sanitize_systim(struct e1000_hw *hw, u64 systim) } /** - * e1000e_cyclecounter_read - read raw cycle counter (used by time counter) - * @cc: cyclecounter structure + * e1000e_read_systim - read SYSTIM register + * @adapter: board private structure + * @sts: structure which will contain system time before and after reading + * SYSTIML, may be NULL **/ -static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc) +u64 e1000e_read_systim(struct e1000_adapter *adapter, + struct ptp_system_timestamp *sts) { - struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter, - cc); struct e1000_hw *hw = &adapter->hw; - u32 systimel, systimeh; + u32 systimel, systimel_2, systimeh; u64 systim; /* SYSTIMH latching upon SYSTIML read does not work well. * This means that if SYSTIML overflows after we read it but before @@ -4369,11 +4376,15 @@ static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc) * will experience a huge non linear increment in the systime value * to fix that we test for overflow and if true, we re-read systime. */ + ptp_read_system_prets(sts); systimel = er32(SYSTIML); + ptp_read_system_postts(sts); systimeh = er32(SYSTIMH); /* Is systimel is so large that overflow is possible? */ if (systimel >= (u32)0xffffffff - E1000_TIMINCA_INCVALUE_MASK) { - u32 systimel_2 = er32(SYSTIML); + ptp_read_system_prets(sts); + systimel_2 = er32(SYSTIML); + ptp_read_system_postts(sts); if (systimel > systimel_2) { /* There was an overflow, read again SYSTIMH, and use * systimel_2 @@ -4386,12 +4397,24 @@ static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc) systim |= (u64)systimeh << 32; if (adapter->flags2 & FLAG2_CHECK_SYSTIM_OVERFLOW) - systim = e1000e_sanitize_systim(hw, systim); + systim = e1000e_sanitize_systim(hw, systim, sts); return systim; } /** + * e1000e_cyclecounter_read - read raw cycle counter (used by time counter) + * @cc: cyclecounter structure + **/ +static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc) +{ + struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter, + cc); + + return e1000e_read_systim(adapter, NULL); +} + +/** * e1000_sw_init - Initialize general software structures (struct e1000_adapter) * @adapter: board private structure to initialize * diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index 37c76945ad9b..1a4c65d9feb4 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -161,22 +161,30 @@ static int e1000e_phc_getcrosststamp(struct ptp_clock_info *ptp, #endif/*CONFIG_E1000E_HWTS*/ /** - * e1000e_phc_gettime - Reads the current time from the hardware clock + * e1000e_phc_gettimex - Reads the current time from the hardware clock and + * system clock * @ptp: ptp clock structure - * @ts: timespec structure to hold the current time value + * @ts: timespec structure to hold the current PHC time + * @sts: structure to hold the current system time * * Read the timecounter and return the correct value in ns after converting * it into a struct timespec. **/ -static int e1000e_phc_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +static int e1000e_phc_gettimex(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) { struct e1000_adapter *adapter = container_of(ptp, struct e1000_adapter, ptp_clock_info); unsigned long flags; - u64 ns; + u64 cycles, ns; spin_lock_irqsave(&adapter->systim_lock, flags); - ns = timecounter_read(&adapter->tc); + + /* NOTE: Non-monotonic SYSTIM readings may be returned */ + cycles = e1000e_read_systim(adapter, sts); + ns = timecounter_cyc2time(&adapter->tc, cycles); + spin_unlock_irqrestore(&adapter->systim_lock, flags); *ts = ns_to_timespec64(ns); @@ -232,9 +240,12 @@ static void e1000e_systim_overflow_work(struct work_struct *work) systim_overflow_work.work); struct e1000_hw *hw = &adapter->hw; struct timespec64 ts; + u64 ns; - adapter->ptp_clock_info.gettime64(&adapter->ptp_clock_info, &ts); + /* Update the timecounter */ + ns = timecounter_read(&adapter->tc); + ts = ns_to_timespec64(ns); e_dbg("SYSTIM overflow check at %lld.%09lu\n", (long long) ts.tv_sec, ts.tv_nsec); @@ -251,7 +262,7 @@ static const struct ptp_clock_info e1000e_ptp_clock_info = { .pps = 0, .adjfreq = e1000e_phc_adjfreq, .adjtime = e1000e_phc_adjtime, - .gettime64 = e1000e_phc_gettime, + .gettimex64 = e1000e_phc_gettimex, .settime64 = e1000e_phc_settime, .enable = e1000e_phc_enable, }; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 5b2a50e5798f..6fd15a734324 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1465,11 +1465,11 @@ static int fm10k_poll(struct napi_struct *napi, int budget) if (!clean_complete) return budget; - /* all work done, exit the polling mode */ - napi_complete_done(napi, work_done); - - /* re-enable the q_vector */ - fm10k_qv_enable(q_vector); + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) + fm10k_qv_enable(q_vector); return min(work_done, budget - 1); } diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 876cac317e79..8de9085bba9e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -122,6 +122,7 @@ enum i40e_state_t { __I40E_MDD_EVENT_PENDING, __I40E_VFLR_EVENT_PENDING, __I40E_RESET_RECOVERY_PENDING, + __I40E_TIMEOUT_RECOVERY_PENDING, __I40E_MISC_IRQ_REQUESTED, __I40E_RESET_INTR_RECEIVED, __I40E_REINIT_REQUESTED, @@ -146,6 +147,7 @@ enum i40e_state_t { __I40E_CLIENT_SERVICE_REQUESTED, __I40E_CLIENT_L2_CHANGE, __I40E_CLIENT_RESET, + __I40E_VIRTCHNL_OP_PENDING, /* This must be last as it determines the size of the BITMAP */ __I40E_STATE_SIZE__, }; @@ -494,7 +496,6 @@ struct i40e_pf { #define I40E_HW_STOP_FW_LLDP BIT(16) #define I40E_HW_PORT_ID_VALID BIT(17) #define I40E_HW_RESTART_AUTONEG BIT(18) -#define I40E_HW_STOPPABLE_FW_LLDP BIT(19) u32 flags; #define I40E_FLAG_RX_CSUM_ENABLED BIT(0) diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 501ee718177f..7ab61f6ebb5f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -588,6 +588,12 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw) hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && hw->aq.api_min_ver >= I40E_MINOR_VER_GET_LINK_INFO_XL710) { hw->flags |= I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE; + hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE; + } + if (hw->mac.type == I40E_MAC_X722 && + hw->aq.api_maj_ver == I40E_FW_API_VERSION_MAJOR && + hw->aq.api_min_ver >= I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722) { + hw->flags |= I40E_HW_FLAG_FW_LLDP_STOPPABLE; } /* Newer versions of firmware require lock when reading the NVM */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 80e3eec6134e..11506102471c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -11,7 +11,7 @@ */ #define I40E_FW_API_VERSION_MAJOR 0x0001 -#define I40E_FW_API_VERSION_MINOR_X722 0x0005 +#define I40E_FW_API_VERSION_MINOR_X722 0x0006 #define I40E_FW_API_VERSION_MINOR_X710 0x0007 #define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \ @@ -20,6 +20,8 @@ /* API version 1.7 implements additional link and PHY-specific APIs */ #define I40E_MINOR_VER_GET_LINK_INFO_XL710 0x0007 +/* API version 1.6 for X722 devices adds ability to stop FW LLDP agent */ +#define I40E_MINOR_VER_FW_LLDP_STOPPABLE_X722 0x0006 struct i40e_aq_desc { __le16 flags; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 85f75b5978fc..97a9b1fb4763 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -3723,6 +3723,9 @@ i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable, (struct i40e_aqc_set_dcb_parameters *)&desc.params.raw; i40e_status status; + if (!(hw->flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE)) + return I40E_ERR_DEVICE_NOT_SUPPORTED; + i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_dcb_parameters); diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 9f8464f80783..a6bc7847346b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -906,6 +906,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, ks->base.speed = SPEED_100; break; default: + ks->base.speed = SPEED_UNKNOWN; break; } ks->base.duplex = DUPLEX_FULL; @@ -1335,6 +1336,7 @@ static int i40e_set_pauseparam(struct net_device *netdev, i40e_status status; u8 aq_failures; int err = 0; + u32 is_an; /* Changing the port's flow control is not supported if this isn't the * port's controlling PF @@ -1347,15 +1349,14 @@ static int i40e_set_pauseparam(struct net_device *netdev, if (vsi != pf->vsi[pf->lan_vsi]) return -EOPNOTSUPP; - if (pause->autoneg != ((hw_link_info->an_info & I40E_AQ_AN_COMPLETED) ? - AUTONEG_ENABLE : AUTONEG_DISABLE)) { + is_an = hw_link_info->an_info & I40E_AQ_AN_COMPLETED; + if (pause->autoneg != is_an) { netdev_info(netdev, "To change autoneg please use: ethtool -s <dev> autoneg <on|off>\n"); return -EOPNOTSUPP; } /* If we have link and don't have autoneg */ - if (!test_bit(__I40E_DOWN, pf->state) && - !(hw_link_info->an_info & I40E_AQ_AN_COMPLETED)) { + if (!test_bit(__I40E_DOWN, pf->state) && !is_an) { /* Send message that it might not necessarily work*/ netdev_info(netdev, "Autoneg did not complete so changing settings may not result in an actual change.\n"); } @@ -1406,7 +1407,7 @@ static int i40e_set_pauseparam(struct net_device *netdev, err = -EAGAIN; } - if (!test_bit(__I40E_DOWN, pf->state)) { + if (!test_bit(__I40E_DOWN, pf->state) && is_an) { /* Give it a little more time to try to come back */ msleep(75); if (!test_bit(__I40E_DOWN, pf->state)) @@ -2377,7 +2378,8 @@ static int i40e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) return -EOPNOTSUPP; /* only magic packet is supported */ - if (wol->wolopts && (wol->wolopts != WAKE_MAGIC)) + if (wol->wolopts && (wol->wolopts != WAKE_MAGIC) + | (wol->wolopts != WAKE_FILTER)) return -EOPNOTSUPP; /* is this a new value? */ @@ -4659,14 +4661,15 @@ flags_complete: return -EOPNOTSUPP; /* If the driver detected FW LLDP was disabled on init, this flag could - * be set, however we do not support _changing_ the flag if NPAR is - * enabled or FW API version < 1.7. There are situations where older - * FW versions/NPAR enabled PFs could disable LLDP, however we _must_ - * not allow the user to enable/disable LLDP with this flag on - * unsupported FW versions. + * be set, however we do not support _changing_ the flag: + * - on XL710 if NPAR is enabled or FW API version < 1.7 + * - on X722 with FW API version < 1.6 + * There are situations where older FW versions/NPAR enabled PFs could + * disable LLDP, however we _must_ not allow the user to enable/disable + * LLDP with this flag on unsupported FW versions. */ if (changed_flags & I40E_FLAG_DISABLE_FW_LLDP) { - if (!(pf->hw_features & I40E_HW_STOPPABLE_FW_LLDP)) { + if (!(pf->hw.flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE)) { dev_warn(&pf->pdev->dev, "Device does not support changing FW LLDP\n"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 0e5dc74b4ef2..4d40878e395a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -26,8 +26,8 @@ static const char i40e_driver_string[] = #define DRV_KERN "-k" #define DRV_VERSION_MAJOR 2 -#define DRV_VERSION_MINOR 3 -#define DRV_VERSION_BUILD 2 +#define DRV_VERSION_MINOR 7 +#define DRV_VERSION_BUILD 6 #define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ __stringify(DRV_VERSION_MINOR) "." \ __stringify(DRV_VERSION_BUILD) DRV_KERN @@ -338,6 +338,10 @@ static void i40e_tx_timeout(struct net_device *netdev) (pf->tx_timeout_last_recovery + netdev->watchdog_timeo))) return; /* don't do any new action before the next timeout */ + /* don't kick off another recovery if one is already pending */ + if (test_and_set_bit(__I40E_TIMEOUT_RECOVERY_PENDING, pf->state)) + return; + if (tx_ring) { head = i40e_get_head(tx_ring); /* Read interrupt register */ @@ -1493,8 +1497,7 @@ int i40e_del_mac_filter(struct i40e_vsi *vsi, const u8 *macaddr) bool found = false; int bkt; - WARN(!spin_is_locked(&vsi->mac_filter_hash_lock), - "Missing mac_filter_hash_lock\n"); + lockdep_assert_held(&vsi->mac_filter_hash_lock); hash_for_each_safe(vsi->mac_filter_hash, bkt, h, f, hlist) { if (ether_addr_equal(macaddr, f->macaddr)) { __i40e_del_filter(vsi, f); @@ -9632,6 +9635,7 @@ end_core_reset: clear_bit(__I40E_RESET_FAILED, pf->state); clear_recovery: clear_bit(__I40E_RESET_RECOVERY_PENDING, pf->state); + clear_bit(__I40E_TIMEOUT_RECOVERY_PENDING, pf->state); } /** @@ -11332,16 +11336,15 @@ static int i40e_sw_init(struct i40e_pf *pf) /* IWARP needs one extra vector for CQP just like MISC.*/ pf->num_iwarp_msix = (int)num_online_cpus() + 1; } - /* Stopping the FW LLDP engine is only supported on the - * XL710 with a FW ver >= 1.7. Also, stopping FW LLDP - * engine is not supported if NPAR is functioning on this - * part + /* Stopping FW LLDP engine is supported on XL710 and X722 + * starting from FW versions determined in i40e_init_adminq. + * Stopping the FW LLDP engine is not supported on XL710 + * if NPAR is functioning so unset this hw flag in this case. */ if (pf->hw.mac.type == I40E_MAC_XL710 && - !pf->hw.func_caps.npar_enable && - (pf->hw.aq.api_maj_ver > 1 || - (pf->hw.aq.api_maj_ver == 1 && pf->hw.aq.api_min_ver > 6))) - pf->hw_features |= I40E_HW_STOPPABLE_FW_LLDP; + pf->hw.func_caps.npar_enable && + (pf->hw.flags & I40E_HW_FLAG_FW_LLDP_STOPPABLE)) + pf->hw.flags &= ~I40E_HW_FLAG_FW_LLDP_STOPPABLE; #ifdef CONFIG_PCI_IOV if (pf->hw.func_caps.num_vfs && pf->hw.partition_id == 1) { @@ -11682,6 +11685,7 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], * @dev: the netdev being configured * @nlh: RTNL message * @flags: bridge flags + * @extack: netlink extended ack * * Inserts a new hardware bridge if not already created and * enables the bridging mode requested (VEB or VEPA). If the @@ -11694,7 +11698,8 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], **/ static int i40e_ndo_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, - u16 flags) + u16 flags, + struct netlink_ext_ack *extack) { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; @@ -12334,6 +12339,9 @@ static int i40e_config_netdev(struct i40e_vsi *vsi) ether_addr_copy(netdev->dev_addr, mac_addr); ether_addr_copy(netdev->perm_addr, mac_addr); + /* i40iw_net_event() reads 16 bytes from neigh->primary_key */ + netdev->neigh_priv_len = sizeof(u32) * 4; + netdev->priv_flags |= IFF_UNICAST_FLT; netdev->priv_flags |= IFF_SUPP_NOFCS; /* Setup netdev TC information */ @@ -14302,23 +14310,23 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) switch (hw->bus.speed) { case i40e_bus_speed_8000: - strncpy(speed, "8.0", PCI_SPEED_SIZE); break; + strlcpy(speed, "8.0", PCI_SPEED_SIZE); break; case i40e_bus_speed_5000: - strncpy(speed, "5.0", PCI_SPEED_SIZE); break; + strlcpy(speed, "5.0", PCI_SPEED_SIZE); break; case i40e_bus_speed_2500: - strncpy(speed, "2.5", PCI_SPEED_SIZE); break; + strlcpy(speed, "2.5", PCI_SPEED_SIZE); break; default: break; } switch (hw->bus.width) { case i40e_bus_width_pcie_x8: - strncpy(width, "8", PCI_WIDTH_SIZE); break; + strlcpy(width, "8", PCI_WIDTH_SIZE); break; case i40e_bus_width_pcie_x4: - strncpy(width, "4", PCI_WIDTH_SIZE); break; + strlcpy(width, "4", PCI_WIDTH_SIZE); break; case i40e_bus_width_pcie_x2: - strncpy(width, "2", PCI_WIDTH_SIZE); break; + strlcpy(width, "2", PCI_WIDTH_SIZE); break; case i40e_bus_width_pcie_x1: - strncpy(width, "1", PCI_WIDTH_SIZE); break; + strlcpy(width, "1", PCI_WIDTH_SIZE); break; default: break; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 1199f0502d6d..5fb4353c742b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -28,19 +28,23 @@ * i40e_ptp_read - Read the PHC time from the device * @pf: Board private structure * @ts: timespec structure to hold the current time value + * @sts: structure to hold the system time before and after reading the PHC * * This function reads the PRTTSYN_TIME registers and stores them in a * timespec. However, since the registers are 64 bits of nanoseconds, we must * convert the result to a timespec before we can return. **/ -static void i40e_ptp_read(struct i40e_pf *pf, struct timespec64 *ts) +static void i40e_ptp_read(struct i40e_pf *pf, struct timespec64 *ts, + struct ptp_system_timestamp *sts) { struct i40e_hw *hw = &pf->hw; u32 hi, lo; u64 ns; /* The timer latches on the lowest register read. */ + ptp_read_system_prets(sts); lo = rd32(hw, I40E_PRTTSYN_TIME_L); + ptp_read_system_postts(sts); hi = rd32(hw, I40E_PRTTSYN_TIME_H); ns = (((u64)hi) << 32) | lo; @@ -146,7 +150,7 @@ static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) mutex_lock(&pf->tmreg_lock); - i40e_ptp_read(pf, &now); + i40e_ptp_read(pf, &now, NULL); timespec64_add_ns(&now, delta); i40e_ptp_write(pf, (const struct timespec64 *)&now); @@ -156,19 +160,21 @@ static int i40e_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) } /** - * i40e_ptp_gettime - Get the time of the PHC + * i40e_ptp_gettimex - Get the time of the PHC * @ptp: The PTP clock structure * @ts: timespec structure to hold the current time value + * @sts: structure to hold the system time before and after reading the PHC * * Read the device clock and return the correct value on ns, after converting it * into a timespec struct. **/ -static int i40e_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +static int i40e_ptp_gettimex(struct ptp_clock_info *ptp, struct timespec64 *ts, + struct ptp_system_timestamp *sts) { struct i40e_pf *pf = container_of(ptp, struct i40e_pf, ptp_caps); mutex_lock(&pf->tmreg_lock); - i40e_ptp_read(pf, ts); + i40e_ptp_read(pf, ts, sts); mutex_unlock(&pf->tmreg_lock); return 0; @@ -694,7 +700,7 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf) if (!IS_ERR_OR_NULL(pf->ptp_clock)) return 0; - strncpy(pf->ptp_caps.name, i40e_driver_name, + strlcpy(pf->ptp_caps.name, i40e_driver_name, sizeof(pf->ptp_caps.name) - 1); pf->ptp_caps.owner = THIS_MODULE; pf->ptp_caps.max_adj = 999999999; @@ -702,7 +708,7 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf) pf->ptp_caps.pps = 0; pf->ptp_caps.adjfreq = i40e_ptp_adjfreq; pf->ptp_caps.adjtime = i40e_ptp_adjtime; - pf->ptp_caps.gettime64 = i40e_ptp_gettime; + pf->ptp_caps.gettimex64 = i40e_ptp_gettimex; pf->ptp_caps.settime64 = i40e_ptp_settime; pf->ptp_caps.enable = i40e_ptp_feature_enable; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index d0a95424ce58..a7e14e98889f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -2648,10 +2648,11 @@ tx_only: if (vsi->back->flags & I40E_TXR_FLAGS_WB_ON_ITR) q_vector->arm_wb_state = false; - /* Work is done so exit the polling mode and re-enable the interrupt */ - napi_complete_done(napi, work_done); - - i40e_update_enable_itr(vsi, q_vector); + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) + i40e_update_enable_itr(vsi, q_vector); return min(work_done, budget - 1); } @@ -3454,6 +3455,8 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, size, td_tag); + skb_tx_timestamp(skb); + /* Force memory writes to complete before letting h/w know there * are new descriptors to fetch. * @@ -3507,6 +3510,7 @@ static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf, u16 i = xdp_ring->next_to_use; struct i40e_tx_buffer *tx_bi; struct i40e_tx_desc *tx_desc; + void *data = xdpf->data; u32 size = xdpf->len; dma_addr_t dma; @@ -3514,8 +3518,7 @@ static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf, xdp_ring->tx_stats.tx_busy++; return I40E_XDP_CONSUMED; } - - dma = dma_map_single(xdp_ring->dev, xdpf->data, size, DMA_TO_DEVICE); + dma = dma_map_single(xdp_ring->dev, data, size, DMA_TO_DEVICE); if (dma_mapping_error(xdp_ring->dev, dma)) return I40E_XDP_CONSUMED; @@ -3633,8 +3636,6 @@ static netdev_tx_t i40e_xmit_frame_ring(struct sk_buff *skb, if (tsyn) tx_flags |= I40E_TX_FLAGS_TSYN; - skb_tx_timestamp(skb); - /* always enable CRC insertion offload */ td_cmd |= I40E_TX_DESC_CMD_ICRC; diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 7df969c59855..2781ab91ca82 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -615,6 +615,7 @@ struct i40e_hw { #define I40E_HW_FLAG_802_1AD_CAPABLE BIT_ULL(1) #define I40E_HW_FLAG_AQ_PHY_ACCESS_CAPABLE BIT_ULL(2) #define I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK BIT_ULL(3) +#define I40E_HW_FLAG_FW_LLDP_STOPPABLE BIT_ULL(4) u64 flags; /* Used in set switch config AQ command */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index ac5698ed0b11..2ac23ebfbf31 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1112,7 +1112,8 @@ static i40e_status i40e_config_vf_promiscuous_mode(struct i40e_vf *vf, if (!i40e_vc_isvalid_vsi_id(vf, vsi_id) || !vsi) return I40E_ERR_PARAM; - if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps)) { + if (!test_bit(I40E_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps) && + (allmulti || alluni)) { dev_err(&pf->pdev->dev, "Unprivileged VF %d is attempting to configure promiscuous mode\n", vf->vf_id); @@ -1675,13 +1676,20 @@ err_out: int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs) { struct i40e_pf *pf = pci_get_drvdata(pdev); + int ret = 0; + + if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { + dev_warn(&pdev->dev, "Unable to configure VFs, other operation is pending.\n"); + return -EAGAIN; + } if (num_vfs) { if (!(pf->flags & I40E_FLAG_VEB_MODE_ENABLED)) { pf->flags |= I40E_FLAG_VEB_MODE_ENABLED; i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } - return i40e_pci_sriov_enable(pdev, num_vfs); + ret = i40e_pci_sriov_enable(pdev, num_vfs); + goto sriov_configure_out; } if (!pci_vfs_assigned(pf->pdev)) { @@ -1690,9 +1698,12 @@ int i40e_pci_sriov_configure(struct pci_dev *pdev, int num_vfs) i40e_do_reset_safe(pf, I40E_PF_RESET_FLAG); } else { dev_warn(&pdev->dev, "Unable to free VFs because some are assigned to VMs.\n"); - return -EINVAL; + ret = -EINVAL; + goto sriov_configure_out; } - return 0; +sriov_configure_out: + clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state); + return ret; } /***********************virtual channel routines******************/ @@ -3893,6 +3904,11 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) goto error_param; } + if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { + dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n"); + return -EAGAIN; + } + if (is_multicast_ether_addr(mac)) { dev_err(&pf->pdev->dev, "Invalid Ethernet address %pM for VF %d\n", mac, vf_id); @@ -3941,6 +3957,7 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) dev_info(&pf->pdev->dev, "Bring down and up the VF interface to make this change effective.\n"); error_param: + clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state); return ret; } @@ -3992,6 +4009,11 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, struct i40e_vf *vf; int ret = 0; + if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { + dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n"); + return -EAGAIN; + } + /* validate the request */ ret = i40e_validate_vf(pf, vf_id); if (ret) @@ -4107,6 +4129,7 @@ int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, ret = 0; error_pvid: + clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state); return ret; } @@ -4128,6 +4151,11 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, struct i40e_vf *vf; int ret = 0; + if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { + dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n"); + return -EAGAIN; + } + /* validate the request */ ret = i40e_validate_vf(pf, vf_id); if (ret) @@ -4154,6 +4182,7 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, vf->tx_rate = max_tx_rate; error: + clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state); return ret; } @@ -4174,6 +4203,11 @@ int i40e_ndo_get_vf_config(struct net_device *netdev, struct i40e_vf *vf; int ret = 0; + if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { + dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n"); + return -EAGAIN; + } + /* validate the request */ ret = i40e_validate_vf(pf, vf_id); if (ret) @@ -4209,6 +4243,7 @@ int i40e_ndo_get_vf_config(struct net_device *netdev, ret = 0; error_param: + clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state); return ret; } @@ -4230,6 +4265,11 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) int abs_vf_id; int ret = 0; + if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { + dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n"); + return -EAGAIN; + } + /* validate the request */ if (vf_id >= pf->num_alloc_vfs) { dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id); @@ -4273,6 +4313,7 @@ int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link) 0, (u8 *)&pfe, sizeof(pfe), NULL); error_out: + clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state); return ret; } @@ -4294,6 +4335,11 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable) struct i40e_vf *vf; int ret = 0; + if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { + dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n"); + return -EAGAIN; + } + /* validate the request */ if (vf_id >= pf->num_alloc_vfs) { dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id); @@ -4327,6 +4373,7 @@ int i40e_ndo_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool enable) ret = -EIO; } out: + clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state); return ret; } @@ -4345,15 +4392,22 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) struct i40e_vf *vf; int ret = 0; + if (test_and_set_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state)) { + dev_warn(&pf->pdev->dev, "Unable to configure VFs, other operation is pending.\n"); + return -EAGAIN; + } + /* validate the request */ if (vf_id >= pf->num_alloc_vfs) { dev_err(&pf->pdev->dev, "Invalid VF Identifier %d\n", vf_id); - return -EINVAL; + ret = -EINVAL; + goto out; } if (pf->flags & I40E_FLAG_MFP_ENABLED) { dev_err(&pf->pdev->dev, "Trusted VF not supported in MFP mode.\n"); - return -EINVAL; + ret = -EINVAL; + goto out; } vf = &pf->vf[vf_id]; @@ -4376,5 +4430,6 @@ int i40e_ndo_set_vf_trust(struct net_device *netdev, int vf_id, bool setting) } out: + clear_bit(__I40E_VIRTCHNL_OP_PENDING, pf->state); return ret; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index bf67d62e2b5f..f9621026beef 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -13,9 +13,9 @@ #define I40E_DEFAULT_NUM_MDD_EVENTS_ALLOWED 3 #define I40E_DEFAULT_NUM_INVALID_MSGS_ALLOWED 10 -#define I40E_VLAN_PRIORITY_SHIFT 12 +#define I40E_VLAN_PRIORITY_SHIFT 13 #define I40E_VLAN_MASK 0xFFF -#define I40E_PRIORITY_MASK 0x7000 +#define I40E_PRIORITY_MASK 0xE000 /* Various queue ctrls */ enum i40e_queue_ctrl { diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index fb9bfad96daf..9b4d7cec2e18 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -1761,10 +1761,11 @@ tx_only: if (vsi->back->flags & IAVF_TXR_FLAGS_WB_ON_ITR) q_vector->arm_wb_state = false; - /* Work is done so exit the polling mode and re-enable the interrupt */ - napi_complete_done(napi, work_done); - - iavf_update_enable_itr(vsi, q_vector); + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) + iavf_update_enable_itr(vsi, q_vector); return min(work_done, budget - 1); } @@ -2343,6 +2344,8 @@ static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb, tx_desc->cmd_type_offset_bsz = build_ctob(td_cmd, td_offset, size, td_tag); + skb_tx_timestamp(skb); + /* Force memory writes to complete before letting h/w know there * are new descriptors to fetch. * @@ -2461,8 +2464,6 @@ static netdev_tx_t iavf_xmit_frame_ring(struct sk_buff *skb, if (tso < 0) goto out_drop; - skb_tx_timestamp(skb); - /* always enable CRC insertion offload */ td_cmd |= IAVF_TX_DESC_CMD_ICRC; diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index b8548370f1c7..a385575600f6 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -52,7 +52,6 @@ extern const char ice_drv_ver[]; #define ICE_MBXQ_LEN 64 #define ICE_MIN_MSIX 2 #define ICE_NO_VSI 0xffff -#define ICE_MAX_VSI_ALLOC 130 #define ICE_MAX_TXQS 2048 #define ICE_MAX_RXQS 2048 #define ICE_VSI_MAP_CONTIG 0 @@ -97,14 +96,14 @@ extern const char ice_drv_ver[]; #define ice_for_each_vsi(pf, i) \ for ((i) = 0; (i) < (pf)->num_alloc_vsi; (i)++) -/* Macros for each tx/rx ring in a VSI */ +/* Macros for each Tx/Rx ring in a VSI */ #define ice_for_each_txq(vsi, i) \ for ((i) = 0; (i) < (vsi)->num_txq; (i)++) #define ice_for_each_rxq(vsi, i) \ for ((i) = 0; (i) < (vsi)->num_rxq; (i)++) -/* Macros for each allocated tx/rx ring whether used or not in a VSI */ +/* Macros for each allocated Tx/Rx ring whether used or not in a VSI */ #define ice_for_each_alloc_txq(vsi, i) \ for ((i) = 0; (i) < (vsi)->alloc_txq; (i)++) @@ -113,7 +112,9 @@ extern const char ice_drv_ver[]; struct ice_tc_info { u16 qoffset; - u16 qcount; + u16 qcount_tx; + u16 qcount_rx; + u8 netdev_tc; }; struct ice_tc_cfg { @@ -149,10 +150,10 @@ enum ice_state { __ICE_RESET_FAILED, /* set by reset/rebuild */ /* When checking for the PF to be in a nominal operating state, the * bits that are grouped at the beginning of the list need to be - * checked. Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will - * be checked. If you need to add a bit into consideration for nominal + * checked. Bits occurring before __ICE_STATE_NOMINAL_CHECK_BITS will + * be checked. If you need to add a bit into consideration for nominal * operating state, it must be added before - * __ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position + * __ICE_STATE_NOMINAL_CHECK_BITS. Do not move this entry's position * without appropriate consideration. */ __ICE_STATE_NOMINAL_CHECK_BITS, @@ -182,8 +183,8 @@ struct ice_vsi { struct ice_sw *vsw; /* switch this VSI is on */ struct ice_pf *back; /* back pointer to PF */ struct ice_port_info *port_info; /* back pointer to port_info */ - struct ice_ring **rx_rings; /* rx ring array */ - struct ice_ring **tx_rings; /* tx ring array */ + struct ice_ring **rx_rings; /* Rx ring array */ + struct ice_ring **tx_rings; /* Tx ring array */ struct ice_q_vector **q_vectors; /* q_vector array */ irqreturn_t (*irq_handler)(int irq, void *data); @@ -200,8 +201,8 @@ struct ice_vsi { int sw_base_vector; /* Irq base for OS reserved vectors */ int hw_base_vector; /* HW (absolute) index of a vector */ enum ice_vsi_type type; - u16 vsi_num; /* HW (absolute) index of this VSI */ - u16 idx; /* software index in pf->vsi[] */ + u16 vsi_num; /* HW (absolute) index of this VSI */ + u16 idx; /* software index in pf->vsi[] */ /* Interrupt thresholds */ u16 work_lmt; @@ -254,8 +255,8 @@ struct ice_q_vector { struct ice_ring_container tx; struct irq_affinity_notify affinity_notify; u16 v_idx; /* index in the vsi->q_vector array. */ - u8 num_ring_tx; /* total number of tx rings in vector */ - u8 num_ring_rx; /* total number of rx rings in vector */ + u8 num_ring_tx; /* total number of Tx rings in vector */ + u8 num_ring_rx; /* total number of Rx rings in vector */ char name[ICE_INT_NAME_STR_LEN]; /* in usecs, need to use ice_intrl_to_usecs_reg() before writing this * value to the device @@ -307,10 +308,10 @@ struct ice_pf { u32 hw_oicr_idx; /* Other interrupt cause vector HW index */ u32 num_avail_hw_msix; /* remaining HW MSIX vectors left unclaimed */ u32 num_lan_msix; /* Total MSIX vectors for base driver */ - u16 num_lan_tx; /* num lan tx queues setup */ - u16 num_lan_rx; /* num lan rx queues setup */ - u16 q_left_tx; /* remaining num tx queues left unclaimed */ - u16 q_left_rx; /* remaining num rx queues left unclaimed */ + u16 num_lan_tx; /* num lan Tx queues setup */ + u16 num_lan_rx; /* num lan Rx queues setup */ + u16 q_left_tx; /* remaining num Tx queues left unclaimed */ + u16 q_left_rx; /* remaining num Rx queues left unclaimed */ u16 next_vsi; /* Next free slot in pf->vsi[] - 0-based! */ u16 num_alloc_vsi; u16 corer_count; /* Core reset count */ diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 6653555f55dd..fcdcd80b18e7 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -5,7 +5,7 @@ #define _ICE_ADMINQ_CMD_H_ /* This header file defines the Admin Queue commands, error codes and - * descriptor format. It is shared between Firmware and Software. + * descriptor format. It is shared between Firmware and Software. */ #define ICE_MAX_VSI 768 @@ -87,6 +87,7 @@ struct ice_aqc_list_caps { /* Device/Function buffer entry, repeated per reported capability */ struct ice_aqc_list_caps_elem { __le16 cap; +#define ICE_AQC_CAPS_VALID_FUNCTIONS 0x0005 #define ICE_AQC_CAPS_SRIOV 0x0012 #define ICE_AQC_CAPS_VF 0x0013 #define ICE_AQC_CAPS_VSI 0x0017 @@ -462,7 +463,7 @@ struct ice_aqc_sw_rules { }; /* Add/Update/Get/Remove lookup Rx/Tx command/response entry - * This structures describes the lookup rules and associated actions. "index" + * This structures describes the lookup rules and associated actions. "index" * is returned as part of a response to a successful Add command, and can be * used to identify the rule for Update/Get/Remove commands. */ @@ -1065,10 +1066,10 @@ struct ice_aqc_nvm { #define ICE_AQC_NVM_LAST_CMD BIT(0) #define ICE_AQC_NVM_PCIR_REQ BIT(0) /* Used by NVM Update reply */ #define ICE_AQC_NVM_PRESERVATION_S 1 -#define ICE_AQC_NVM_PRESERVATION_M (3 << CSR_AQ_NVM_PRESERVATION_S) -#define ICE_AQC_NVM_NO_PRESERVATION (0 << CSR_AQ_NVM_PRESERVATION_S) +#define ICE_AQC_NVM_PRESERVATION_M (3 << ICE_AQC_NVM_PRESERVATION_S) +#define ICE_AQC_NVM_NO_PRESERVATION (0 << ICE_AQC_NVM_PRESERVATION_S) #define ICE_AQC_NVM_PRESERVE_ALL BIT(1) -#define ICE_AQC_NVM_PRESERVE_SELECTED (3 << CSR_AQ_NVM_PRESERVATION_S) +#define ICE_AQC_NVM_PRESERVE_SELECTED (3 << ICE_AQC_NVM_PRESERVATION_S) #define ICE_AQC_NVM_FLASH_ONLY BIT(7) __le16 module_typeid; __le16 length; @@ -1110,7 +1111,7 @@ struct ice_aqc_get_set_rss_keys { }; /* Get/Set RSS LUT (indirect 0x0B05/0x0B03) */ -struct ice_aqc_get_set_rss_lut { +struct ice_aqc_get_set_rss_lut { #define ICE_AQC_GSET_RSS_LUT_VSI_VALID BIT(15) #define ICE_AQC_GSET_RSS_LUT_VSI_ID_S 0 #define ICE_AQC_GSET_RSS_LUT_VSI_ID_M (0x1FF << ICE_AQC_GSET_RSS_LUT_VSI_ID_S) @@ -1314,10 +1315,10 @@ struct ice_aqc_get_clear_fw_log { * @params: command-specific parameters * * Descriptor format for commands the driver posts on the Admin Transmit Queue - * (ATQ). The firmware writes back onto the command descriptor and returns - * the result of the command. Asynchronous events that are not an immediate + * (ATQ). The firmware writes back onto the command descriptor and returns + * the result of the command. Asynchronous events that are not an immediate * result of the command are written to the Admin Receive Queue (ARQ) using - * the same descriptor format. Descriptors are in little-endian notation with + * the same descriptor format. Descriptors are in little-endian notation with * 32-bit words. */ struct ice_aq_desc { @@ -1379,10 +1380,10 @@ struct ice_aq_desc { /* error codes */ enum ice_aq_err { - ICE_AQ_RC_OK = 0, /* success */ + ICE_AQ_RC_OK = 0, /* Success */ ICE_AQ_RC_ENOMEM = 9, /* Out of memory */ ICE_AQ_RC_EBUSY = 12, /* Device or resource busy */ - ICE_AQ_RC_EEXIST = 13, /* object already exists */ + ICE_AQ_RC_EEXIST = 13, /* Object already exists */ ICE_AQ_RC_ENOSPC = 16, /* No space left or allocation failure */ }; diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 554fd707a6d6..4c1d35da940d 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -405,9 +405,7 @@ static enum ice_status ice_init_fltr_mgmt_struct(struct ice_hw *hw) INIT_LIST_HEAD(&sw->vsi_list_map_head); - ice_init_def_sw_recp(hw); - - return 0; + return ice_init_def_sw_recp(hw); } /** @@ -715,7 +713,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw) hw->evb_veb = true; - /* Query the allocated resources for tx scheduler */ + /* Query the allocated resources for Tx scheduler */ status = ice_sched_query_res_alloc(hw); if (status) { ice_debug(hw, ICE_DBG_SCHED, @@ -958,7 +956,7 @@ enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req) * ice_copy_rxq_ctx_to_hw * @hw: pointer to the hardware structure * @ice_rxq_ctx: pointer to the rxq context - * @rxq_index: the index of the rx queue + * @rxq_index: the index of the Rx queue * * Copies rxq context from dense structure to hw register space */ @@ -1014,7 +1012,7 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = { * ice_write_rxq_ctx * @hw: pointer to the hardware structure * @rlan_ctx: pointer to the rxq context - * @rxq_index: the index of the rx queue + * @rxq_index: the index of the Rx queue * * Converts rxq context from sparse to dense structure and then writes * it to hw register space @@ -1387,6 +1385,27 @@ void ice_release_res(struct ice_hw *hw, enum ice_aq_res_ids res) } /** + * ice_get_guar_num_vsi - determine number of guar VSI for a PF + * @hw: pointer to the hw structure + * + * Determine the number of valid functions by going through the bitmap returned + * from parsing capabilities and use this to calculate the number of VSI per PF. + */ +static u32 ice_get_guar_num_vsi(struct ice_hw *hw) +{ + u8 funcs; + +#define ICE_CAPS_VALID_FUNCS_M 0xFF + funcs = hweight8(hw->dev_caps.common_cap.valid_functions & + ICE_CAPS_VALID_FUNCS_M); + + if (!funcs) + return 0; + + return ICE_MAX_VSI / funcs; +} + +/** * ice_parse_caps - parse function/device capabilities * @hw: pointer to the hw struct * @buf: pointer to a buffer containing function/device capability records @@ -1428,6 +1447,12 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, u16 cap = le16_to_cpu(cap_resp->cap); switch (cap) { + case ICE_AQC_CAPS_VALID_FUNCTIONS: + caps->valid_functions = number; + ice_debug(hw, ICE_DBG_INIT, + "HW caps: Valid Functions = %d\n", + caps->valid_functions); + break; case ICE_AQC_CAPS_SRIOV: caps->sr_iov_1_1 = (number == 1); ice_debug(hw, ICE_DBG_INIT, @@ -1457,10 +1482,10 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, "HW caps: Dev.VSI cnt = %d\n", dev_p->num_vsi_allocd_to_host); } else if (func_p) { - func_p->guaranteed_num_vsi = number; + func_p->guar_num_vsi = ice_get_guar_num_vsi(hw); ice_debug(hw, ICE_DBG_INIT, "HW caps: Func.VSI cnt = %d\n", - func_p->guaranteed_num_vsi); + number); } break; case ICE_AQC_CAPS_RSS: @@ -1688,8 +1713,7 @@ void ice_clear_pxe_mode(struct ice_hw *hw) * If no bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned * If more than one bit gets set, ICE_LINK_SPEED_UNKNOWN will be returned */ -static u16 -ice_get_link_speed_based_on_phy_type(u64 phy_type_low) +static u16 ice_get_link_speed_based_on_phy_type(u64 phy_type_low) { u16 speed_phy_type_low = ICE_AQ_LINK_SPEED_UNKNOWN; diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index 84c967294eaf..2bf5e11f559a 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -3,6 +3,26 @@ #include "ice_common.h" +#define ICE_CQ_INIT_REGS(qinfo, prefix) \ +do { \ + (qinfo)->sq.head = prefix##_ATQH; \ + (qinfo)->sq.tail = prefix##_ATQT; \ + (qinfo)->sq.len = prefix##_ATQLEN; \ + (qinfo)->sq.bah = prefix##_ATQBAH; \ + (qinfo)->sq.bal = prefix##_ATQBAL; \ + (qinfo)->sq.len_mask = prefix##_ATQLEN_ATQLEN_M; \ + (qinfo)->sq.len_ena_mask = prefix##_ATQLEN_ATQENABLE_M; \ + (qinfo)->sq.head_mask = prefix##_ATQH_ATQH_M; \ + (qinfo)->rq.head = prefix##_ARQH; \ + (qinfo)->rq.tail = prefix##_ARQT; \ + (qinfo)->rq.len = prefix##_ARQLEN; \ + (qinfo)->rq.bah = prefix##_ARQBAH; \ + (qinfo)->rq.bal = prefix##_ARQBAL; \ + (qinfo)->rq.len_mask = prefix##_ARQLEN_ARQLEN_M; \ + (qinfo)->rq.len_ena_mask = prefix##_ARQLEN_ARQENABLE_M; \ + (qinfo)->rq.head_mask = prefix##_ARQH_ARQH_M; \ +} while (0) + /** * ice_adminq_init_regs - Initialize AdminQ registers * @hw: pointer to the hardware structure @@ -13,23 +33,7 @@ static void ice_adminq_init_regs(struct ice_hw *hw) { struct ice_ctl_q_info *cq = &hw->adminq; - cq->sq.head = PF_FW_ATQH; - cq->sq.tail = PF_FW_ATQT; - cq->sq.len = PF_FW_ATQLEN; - cq->sq.bah = PF_FW_ATQBAH; - cq->sq.bal = PF_FW_ATQBAL; - cq->sq.len_mask = PF_FW_ATQLEN_ATQLEN_M; - cq->sq.len_ena_mask = PF_FW_ATQLEN_ATQENABLE_M; - cq->sq.head_mask = PF_FW_ATQH_ATQH_M; - - cq->rq.head = PF_FW_ARQH; - cq->rq.tail = PF_FW_ARQT; - cq->rq.len = PF_FW_ARQLEN; - cq->rq.bah = PF_FW_ARQBAH; - cq->rq.bal = PF_FW_ARQBAL; - cq->rq.len_mask = PF_FW_ARQLEN_ARQLEN_M; - cq->rq.len_ena_mask = PF_FW_ARQLEN_ARQENABLE_M; - cq->rq.head_mask = PF_FW_ARQH_ARQH_M; + ICE_CQ_INIT_REGS(cq, PF_FW); } /** @@ -42,24 +46,7 @@ static void ice_mailbox_init_regs(struct ice_hw *hw) { struct ice_ctl_q_info *cq = &hw->mailboxq; - /* set head and tail registers in our local struct */ - cq->sq.head = PF_MBX_ATQH; - cq->sq.tail = PF_MBX_ATQT; - cq->sq.len = PF_MBX_ATQLEN; - cq->sq.bah = PF_MBX_ATQBAH; - cq->sq.bal = PF_MBX_ATQBAL; - cq->sq.len_mask = PF_MBX_ATQLEN_ATQLEN_M; - cq->sq.len_ena_mask = PF_MBX_ATQLEN_ATQENABLE_M; - cq->sq.head_mask = PF_MBX_ATQH_ATQH_M; - - cq->rq.head = PF_MBX_ARQH; - cq->rq.tail = PF_MBX_ARQT; - cq->rq.len = PF_MBX_ARQLEN; - cq->rq.bah = PF_MBX_ARQBAH; - cq->rq.bal = PF_MBX_ARQBAL; - cq->rq.len_mask = PF_MBX_ARQLEN_ARQLEN_M; - cq->rq.len_ena_mask = PF_MBX_ARQLEN_ARQENABLE_M; - cq->rq.head_mask = PF_MBX_ARQH_ARQH_M; + ICE_CQ_INIT_REGS(cq, PF_MBX); } /** @@ -131,37 +118,20 @@ ice_alloc_ctrlq_rq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq) } /** - * ice_free_ctrlq_sq_ring - Free Control Transmit Queue (ATQ) rings + * ice_free_cq_ring - Free control queue ring * @hw: pointer to the hardware structure - * @cq: pointer to the specific Control queue + * @ring: pointer to the specific control queue ring * - * This assumes the posted send buffers have already been cleaned + * This assumes the posted buffers have already been cleaned * and de-allocated */ -static void ice_free_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq) +static void ice_free_cq_ring(struct ice_hw *hw, struct ice_ctl_q_ring *ring) { - dmam_free_coherent(ice_hw_to_dev(hw), cq->sq.desc_buf.size, - cq->sq.desc_buf.va, cq->sq.desc_buf.pa); - cq->sq.desc_buf.va = NULL; - cq->sq.desc_buf.pa = 0; - cq->sq.desc_buf.size = 0; -} - -/** - * ice_free_ctrlq_rq_ring - Free Control Receive Queue (ARQ) rings - * @hw: pointer to the hardware structure - * @cq: pointer to the specific Control queue - * - * This assumes the posted receive buffers have already been cleaned - * and de-allocated - */ -static void ice_free_ctrlq_rq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq) -{ - dmam_free_coherent(ice_hw_to_dev(hw), cq->rq.desc_buf.size, - cq->rq.desc_buf.va, cq->rq.desc_buf.pa); - cq->rq.desc_buf.va = NULL; - cq->rq.desc_buf.pa = 0; - cq->rq.desc_buf.size = 0; + dmam_free_coherent(ice_hw_to_dev(hw), ring->desc_buf.size, + ring->desc_buf.va, ring->desc_buf.pa); + ring->desc_buf.va = NULL; + ring->desc_buf.pa = 0; + ring->desc_buf.size = 0; } /** @@ -280,54 +250,23 @@ unwind_alloc_sq_bufs: return ICE_ERR_NO_MEMORY; } -/** - * ice_free_rq_bufs - Free ARQ buffer info elements - * @hw: pointer to the hardware structure - * @cq: pointer to the specific Control queue - */ -static void ice_free_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq) -{ - int i; - - /* free descriptors */ - for (i = 0; i < cq->num_rq_entries; i++) { - dmam_free_coherent(ice_hw_to_dev(hw), cq->rq.r.rq_bi[i].size, - cq->rq.r.rq_bi[i].va, cq->rq.r.rq_bi[i].pa); - cq->rq.r.rq_bi[i].va = NULL; - cq->rq.r.rq_bi[i].pa = 0; - cq->rq.r.rq_bi[i].size = 0; - } - - /* free the dma header */ - devm_kfree(ice_hw_to_dev(hw), cq->rq.dma_head); -} - -/** - * ice_free_sq_bufs - Free ATQ buffer info elements - * @hw: pointer to the hardware structure - * @cq: pointer to the specific Control queue - */ -static void ice_free_sq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq) +static enum ice_status +ice_cfg_cq_regs(struct ice_hw *hw, struct ice_ctl_q_ring *ring, u16 num_entries) { - int i; + /* Clear Head and Tail */ + wr32(hw, ring->head, 0); + wr32(hw, ring->tail, 0); - /* only unmap if the address is non-NULL */ - for (i = 0; i < cq->num_sq_entries; i++) - if (cq->sq.r.sq_bi[i].pa) { - dmam_free_coherent(ice_hw_to_dev(hw), - cq->sq.r.sq_bi[i].size, - cq->sq.r.sq_bi[i].va, - cq->sq.r.sq_bi[i].pa); - cq->sq.r.sq_bi[i].va = NULL; - cq->sq.r.sq_bi[i].pa = 0; - cq->sq.r.sq_bi[i].size = 0; - } + /* set starting point */ + wr32(hw, ring->len, (num_entries | ring->len_ena_mask)); + wr32(hw, ring->bal, lower_32_bits(ring->desc_buf.pa)); + wr32(hw, ring->bah, upper_32_bits(ring->desc_buf.pa)); - /* free the buffer info list */ - devm_kfree(ice_hw_to_dev(hw), cq->sq.cmd_buf); + /* Check one register to verify that config was applied */ + if (rd32(hw, ring->bal) != lower_32_bits(ring->desc_buf.pa)) + return ICE_ERR_AQ_ERROR; - /* free the dma header */ - devm_kfree(ice_hw_to_dev(hw), cq->sq.dma_head); + return 0; } /** @@ -340,23 +279,7 @@ static void ice_free_sq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq) static enum ice_status ice_cfg_sq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq) { - u32 reg = 0; - - /* Clear Head and Tail */ - wr32(hw, cq->sq.head, 0); - wr32(hw, cq->sq.tail, 0); - - /* set starting point */ - wr32(hw, cq->sq.len, (cq->num_sq_entries | cq->sq.len_ena_mask)); - wr32(hw, cq->sq.bal, lower_32_bits(cq->sq.desc_buf.pa)); - wr32(hw, cq->sq.bah, upper_32_bits(cq->sq.desc_buf.pa)); - - /* Check one register to verify that config was applied */ - reg = rd32(hw, cq->sq.bal); - if (reg != lower_32_bits(cq->sq.desc_buf.pa)) - return ICE_ERR_AQ_ERROR; - - return 0; + return ice_cfg_cq_regs(hw, &cq->sq, cq->num_sq_entries); } /** @@ -369,25 +292,15 @@ ice_cfg_sq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq) static enum ice_status ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq) { - u32 reg = 0; - - /* Clear Head and Tail */ - wr32(hw, cq->rq.head, 0); - wr32(hw, cq->rq.tail, 0); + enum ice_status status; - /* set starting point */ - wr32(hw, cq->rq.len, (cq->num_rq_entries | cq->rq.len_ena_mask)); - wr32(hw, cq->rq.bal, lower_32_bits(cq->rq.desc_buf.pa)); - wr32(hw, cq->rq.bah, upper_32_bits(cq->rq.desc_buf.pa)); + status = ice_cfg_cq_regs(hw, &cq->rq, cq->num_rq_entries); + if (status) + return status; /* Update tail in the HW to post pre-allocated buffers */ wr32(hw, cq->rq.tail, (u32)(cq->num_rq_entries - 1)); - /* Check one register to verify that config was applied */ - reg = rd32(hw, cq->rq.bal); - if (reg != lower_32_bits(cq->rq.desc_buf.pa)) - return ICE_ERR_AQ_ERROR; - return 0; } @@ -444,7 +357,7 @@ static enum ice_status ice_init_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) goto init_ctrlq_exit; init_ctrlq_free_rings: - ice_free_ctrlq_sq_ring(hw, cq); + ice_free_cq_ring(hw, &cq->sq); init_ctrlq_exit: return ret_code; @@ -503,12 +416,33 @@ static enum ice_status ice_init_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq) goto init_ctrlq_exit; init_ctrlq_free_rings: - ice_free_ctrlq_rq_ring(hw, cq); + ice_free_cq_ring(hw, &cq->rq); init_ctrlq_exit: return ret_code; } +#define ICE_FREE_CQ_BUFS(hw, qi, ring) \ +do { \ + int i; \ + /* free descriptors */ \ + for (i = 0; i < (qi)->num_##ring##_entries; i++) \ + if ((qi)->ring.r.ring##_bi[i].pa) { \ + dmam_free_coherent(ice_hw_to_dev(hw), \ + (qi)->ring.r.ring##_bi[i].size,\ + (qi)->ring.r.ring##_bi[i].va,\ + (qi)->ring.r.ring##_bi[i].pa);\ + (qi)->ring.r.ring##_bi[i].va = NULL; \ + (qi)->ring.r.ring##_bi[i].pa = 0; \ + (qi)->ring.r.ring##_bi[i].size = 0; \ + } \ + /* free the buffer info list */ \ + if ((qi)->ring.cmd_buf) \ + devm_kfree(ice_hw_to_dev(hw), (qi)->ring.cmd_buf); \ + /* free dma head */ \ + devm_kfree(ice_hw_to_dev(hw), (qi)->ring.dma_head); \ +} while (0) + /** * ice_shutdown_sq - shutdown the Control ATQ * @hw: pointer to the hardware structure @@ -538,8 +472,8 @@ ice_shutdown_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq) cq->sq.count = 0; /* to indicate uninitialized queue */ /* free ring buffers and the ring itself */ - ice_free_sq_bufs(hw, cq); - ice_free_ctrlq_sq_ring(hw, cq); + ICE_FREE_CQ_BUFS(hw, cq, sq); + ice_free_cq_ring(hw, &cq->sq); shutdown_sq_out: mutex_unlock(&cq->sq_lock); @@ -606,8 +540,8 @@ ice_shutdown_rq(struct ice_hw *hw, struct ice_ctl_q_info *cq) cq->rq.count = 0; /* free ring buffers and the ring itself */ - ice_free_rq_bufs(hw, cq); - ice_free_ctrlq_rq_ring(hw, cq); + ICE_FREE_CQ_BUFS(hw, cq, rq); + ice_free_cq_ring(hw, &cq->rq); shutdown_rq_out: mutex_unlock(&cq->rq_lock); @@ -657,7 +591,6 @@ init_ctrlq_free_rq: * - cq->num_rq_entries * - cq->rq_buf_size * - cq->sq_buf_size - * */ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) { @@ -841,7 +774,7 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq) * @buf_size: size of buffer for indirect commands (or 0 for direct commands) * @cd: pointer to command details structure * - * This is the main send command routine for the ATQ. It runs the q, + * This is the main send command routine for the ATQ. It runs the queue, * cleans the queue, etc. */ enum ice_status @@ -1035,7 +968,7 @@ void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode) * @pending: number of events that could be left to process * * This function cleans one Admin Receive Queue element and returns - * the contents through e. It can also return how many events are + * the contents through e. It can also return how many events are * left to process through 'pending'. */ enum ice_status diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 648acdb4c644..3b6e387f5440 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -62,7 +62,7 @@ static const struct ice_stats ice_gstrings_vsi_stats[] = { * The PF_STATs are appended to the netdev stats only when ethtool -S * is queried on the base PF netdev. */ -static struct ice_stats ice_gstrings_pf_stats[] = { +static const struct ice_stats ice_gstrings_pf_stats[] = { ICE_PF_STAT("tx_bytes", stats.eth.tx_bytes), ICE_PF_STAT("rx_bytes", stats.eth.rx_bytes), ICE_PF_STAT("tx_unicast", stats.eth.tx_unicast), @@ -104,7 +104,7 @@ static struct ice_stats ice_gstrings_pf_stats[] = { ICE_PF_STAT("mac_remote_faults", stats.mac_remote_faults), }; -static u32 ice_regs_dump_list[] = { +static const u32 ice_regs_dump_list[] = { PFGEN_STATE, PRTGEN_STATUS, QRX_CTRL(0), @@ -260,10 +260,10 @@ static int ice_get_sset_count(struct net_device *netdev, int sset) * a private ethtool flag). This is due to the nature of the * ethtool stats API. * - * User space programs such as ethtool must make 3 separate + * Userspace programs such as ethtool must make 3 separate * ioctl requests, one for size, one for the strings, and * finally one for the stats. Since these cross into - * user space, changes to the number or size could result in + * userspace, changes to the number or size could result in * undefined memory access or incorrect string<->value * correlations for statistics. * @@ -1392,17 +1392,17 @@ static int ice_nway_reset(struct net_device *netdev) { /* restart autonegotiation */ struct ice_netdev_priv *np = netdev_priv(netdev); - struct ice_link_status *hw_link_info; struct ice_vsi *vsi = np->vsi; struct ice_port_info *pi; enum ice_status status; - bool link_up; pi = vsi->port_info; - hw_link_info = &pi->phy.link_info; - link_up = hw_link_info->link_info & ICE_AQ_LINK_UP; + /* If VSI state is up, then restart autoneg with link up */ + if (!test_bit(__ICE_DOWN, vsi->back->state)) + status = ice_aq_set_link_restart_an(pi, true, NULL); + else + status = ice_aq_set_link_restart_an(pi, false, NULL); - status = ice_aq_set_link_restart_an(pi, link_up, NULL); if (status) { netdev_info(netdev, "link restart failed, err %d aq_err %d\n", status, pi->hw->adminq.sq_last_status); @@ -1441,7 +1441,7 @@ ice_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) /** * ice_set_pauseparam - Set Flow Control parameter * @netdev: network interface device structure - * @pause: return tx/rx flow control status + * @pause: return Tx/Rx flow control status */ static int ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) @@ -1543,7 +1543,7 @@ static u32 ice_get_rxfh_key_size(struct net_device __always_unused *netdev) } /** - * ice_get_rxfh_indir_size - get the rx flow hash indirection table size + * ice_get_rxfh_indir_size - get the Rx flow hash indirection table size * @netdev: network interface device structure * * Returns the table size. @@ -1556,7 +1556,7 @@ static u32 ice_get_rxfh_indir_size(struct net_device *netdev) } /** - * ice_get_rxfh - get the rx flow hash indirection table + * ice_get_rxfh - get the Rx flow hash indirection table * @netdev: network interface device structure * @indir: indirection table * @key: hash key @@ -1603,7 +1603,7 @@ out: } /** - * ice_set_rxfh - set the rx flow hash indirection table + * ice_set_rxfh - set the Rx flow hash indirection table * @netdev: network interface device structure * @indir: indirection table * @key: hash key diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 596b9fb1c510..5507928c8fbe 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -7,6 +7,9 @@ #define _ICE_HW_AUTOGEN_H_ #define QTX_COMM_DBELL(_DBQM) (0x002C0000 + ((_DBQM) * 4)) +#define QTX_COMM_HEAD(_DBQM) (0x000E0000 + ((_DBQM) * 4)) +#define QTX_COMM_HEAD_HEAD_S 0 +#define QTX_COMM_HEAD_HEAD_M ICE_M(0x1FFF, 0) #define PF_FW_ARQBAH 0x00080180 #define PF_FW_ARQBAL 0x00080080 #define PF_FW_ARQH 0x00080380 diff --git a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h index 7d2a66739e3f..bb51dd7defb5 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -6,11 +6,11 @@ union ice_32byte_rx_desc { struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ /* bit 0 of hdr_addr is DD bit */ - __le64 rsvd1; - __le64 rsvd2; + __le64 rsvd1; + __le64 rsvd2; } read; struct { struct { @@ -105,11 +105,11 @@ enum ice_rx_ptype_payload_layer { */ union ice_32b_rx_flex_desc { struct { - __le64 pkt_addr; /* Packet buffer address */ - __le64 hdr_addr; /* Header buffer address */ - /* bit 0 of hdr_addr is DD bit */ - __le64 rsvd1; - __le64 rsvd2; + __le64 pkt_addr; /* Packet buffer address */ + __le64 hdr_addr; /* Header buffer address */ + /* bit 0 of hdr_addr is DD bit */ + __le64 rsvd1; + __le64 rsvd2; } read; struct { /* Qword 0 */ @@ -256,6 +256,9 @@ enum ice_rx_flex_desc_status_error_0_bits { #define ICE_RXQ_CTX_SIZE_DWORDS 8 #define ICE_RXQ_CTX_SZ (ICE_RXQ_CTX_SIZE_DWORDS * sizeof(u32)) +#define ICE_TX_CMPLTNQ_CTX_SIZE_DWORDS 22 +#define ICE_TX_DRBELL_Q_CTX_SIZE_DWORDS 5 +#define GLTCLAN_CQ_CNTX(i, CQ) (GLTCLAN_CQ_CNTX0(CQ) + ((i) * 0x0800)) /* RLAN Rx queue context data * @@ -274,18 +277,18 @@ struct ice_rlan_ctx { u16 dbuf; /* bigger than needed, see above for reason */ #define ICE_RLAN_CTX_HBUF_S 6 u16 hbuf; /* bigger than needed, see above for reason */ - u8 dtype; - u8 dsize; - u8 crcstrip; - u8 l2tsel; - u8 hsplit_0; - u8 hsplit_1; - u8 showiv; + u8 dtype; + u8 dsize; + u8 crcstrip; + u8 l2tsel; + u8 hsplit_0; + u8 hsplit_1; + u8 showiv; u32 rxmax; /* bigger than needed, see above for reason */ - u8 tphrdesc_ena; - u8 tphwdesc_ena; - u8 tphdata_ena; - u8 tphhead_ena; + u8 tphrdesc_ena; + u8 tphwdesc_ena; + u8 tphdata_ena; + u8 tphhead_ena; u16 lrxqthresh; /* bigger than needed, see above for reason */ }; @@ -413,35 +416,35 @@ enum ice_tx_ctx_desc_cmd_bits { struct ice_tlan_ctx { #define ICE_TLAN_CTX_BASE_S 7 u64 base; /* base is defined in 128-byte units */ - u8 port_num; + u8 port_num; u16 cgd_num; /* bigger than needed, see above for reason */ - u8 pf_num; + u8 pf_num; u16 vmvf_num; - u8 vmvf_type; + u8 vmvf_type; #define ICE_TLAN_CTX_VMVF_TYPE_VF 0 #define ICE_TLAN_CTX_VMVF_TYPE_VMQ 1 #define ICE_TLAN_CTX_VMVF_TYPE_PF 2 u16 src_vsi; - u8 tsyn_ena; - u8 alt_vlan; + u8 tsyn_ena; + u8 alt_vlan; u16 cpuid; /* bigger than needed, see above for reason */ - u8 wb_mode; - u8 tphrd_desc; - u8 tphrd; - u8 tphwr_desc; + u8 wb_mode; + u8 tphrd_desc; + u8 tphrd; + u8 tphwr_desc; u16 cmpq_id; u16 qnum_in_func; - u8 itr_notification_mode; - u8 adjust_prof_id; + u8 itr_notification_mode; + u8 adjust_prof_id; u32 qlen; /* bigger than needed, see above for reason */ - u8 quanta_prof_idx; - u8 tso_ena; + u8 quanta_prof_idx; + u8 tso_ena; u16 tso_qnum; - u8 legacy_int; - u8 drop_ena; - u8 cache_prof_idx; - u8 pkt_shaper_prof_idx; - u8 int_q_state; /* width not needed - internal do not write */ + u8 legacy_int; + u8 drop_ena; + u8 cache_prof_idx; + u8 pkt_shaper_prof_idx; + u8 int_q_state; /* width not needed - internal do not write */ }; /* macro to make the table lines short */ diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 1041fa2a7767..29b1dcfd4331 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -20,7 +20,7 @@ static int ice_setup_rx_ctx(struct ice_ring *ring) u16 pf_q; int err; - /* what is RX queue number in global space of 2K Rx queues */ + /* what is Rx queue number in global space of 2K Rx queues */ pf_q = vsi->rxq_map[ring->q_index]; /* clear the context structure first */ @@ -174,15 +174,15 @@ static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena) { int i; - for (i = 0; i < ICE_Q_WAIT_RETRY_LIMIT; i++) { + for (i = 0; i < ICE_Q_WAIT_MAX_RETRY; i++) { u32 rx_reg = rd32(&pf->hw, QRX_CTRL(pf_q)); if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M)) break; - usleep_range(10, 20); + usleep_range(20, 40); } - if (i >= ICE_Q_WAIT_RETRY_LIMIT) + if (i >= ICE_Q_WAIT_MAX_RETRY) return -ETIMEDOUT; return 0; @@ -774,11 +774,13 @@ static void ice_set_dflt_vsi_ctx(struct ice_vsi_ctx *ctxt) */ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) { - u16 offset = 0, qmap = 0, numq_tc; - u16 pow = 0, max_rss = 0, qcount; + u16 offset = 0, qmap = 0, tx_count = 0; u16 qcount_tx = vsi->alloc_txq; u16 qcount_rx = vsi->alloc_rxq; + u16 tx_numq_tc, rx_numq_tc; + u16 pow = 0, max_rss = 0; bool ena_tc0 = false; + u8 netdev_tc = 0; int i; /* at least TC0 should be enabled by default */ @@ -794,7 +796,12 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) vsi->tc_cfg.ena_tc |= 1; } - numq_tc = qcount_rx / vsi->tc_cfg.numtc; + rx_numq_tc = qcount_rx / vsi->tc_cfg.numtc; + if (!rx_numq_tc) + rx_numq_tc = 1; + tx_numq_tc = qcount_tx / vsi->tc_cfg.numtc; + if (!tx_numq_tc) + tx_numq_tc = 1; /* TC mapping is a function of the number of Rx queues assigned to the * VSI for each traffic class and the offset of these queues. @@ -808,7 +815,8 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) * Setup number and offset of Rx queues for all TCs for the VSI */ - qcount = numq_tc; + qcount_rx = rx_numq_tc; + /* qcount will change if RSS is enabled */ if (test_bit(ICE_FLAG_RSS_ENA, vsi->back->flags)) { if (vsi->type == ICE_VSI_PF || vsi->type == ICE_VSI_VF) { @@ -816,37 +824,41 @@ static void ice_vsi_setup_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctxt) max_rss = ICE_MAX_LG_RSS_QS; else max_rss = ICE_MAX_SMALL_RSS_QS; - qcount = min_t(int, numq_tc, max_rss); - qcount = min_t(int, qcount, vsi->rss_size); + qcount_rx = min_t(int, rx_numq_tc, max_rss); + qcount_rx = min_t(int, qcount_rx, vsi->rss_size); } } /* find the (rounded up) power-of-2 of qcount */ - pow = order_base_2(qcount); + pow = order_base_2(qcount_rx); for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) { if (!(vsi->tc_cfg.ena_tc & BIT(i))) { /* TC is not enabled */ vsi->tc_cfg.tc_info[i].qoffset = 0; - vsi->tc_cfg.tc_info[i].qcount = 1; + vsi->tc_cfg.tc_info[i].qcount_rx = 1; + vsi->tc_cfg.tc_info[i].qcount_tx = 1; + vsi->tc_cfg.tc_info[i].netdev_tc = 0; ctxt->info.tc_mapping[i] = 0; continue; } /* TC is enabled */ vsi->tc_cfg.tc_info[i].qoffset = offset; - vsi->tc_cfg.tc_info[i].qcount = qcount; + vsi->tc_cfg.tc_info[i].qcount_rx = qcount_rx; + vsi->tc_cfg.tc_info[i].qcount_tx = tx_numq_tc; + vsi->tc_cfg.tc_info[i].netdev_tc = netdev_tc++; qmap = ((offset << ICE_AQ_VSI_TC_Q_OFFSET_S) & ICE_AQ_VSI_TC_Q_OFFSET_M) | ((pow << ICE_AQ_VSI_TC_Q_NUM_S) & ICE_AQ_VSI_TC_Q_NUM_M); - offset += qcount; + offset += qcount_rx; + tx_count += tx_numq_tc; ctxt->info.tc_mapping[i] = cpu_to_le16(qmap); } - - vsi->num_txq = qcount_tx; vsi->num_rxq = offset; + vsi->num_txq = tx_count; if (vsi->type == ICE_VSI_VF && vsi->num_txq != vsi->num_rxq) { dev_dbg(&vsi->back->pdev->dev, "VF VSI should have same number of Tx and Rx queues. Hence making them equal\n"); @@ -1000,7 +1012,7 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi) * @vsi: the VSI being configured * @v_idx: index of the vector in the VSI struct * - * We allocate one q_vector. If allocation fails we return -ENOMEM. + * We allocate one q_vector. If allocation fails we return -ENOMEM. */ static int ice_vsi_alloc_q_vector(struct ice_vsi *vsi, int v_idx) { @@ -1039,7 +1051,7 @@ out: * ice_vsi_alloc_q_vectors - Allocate memory for interrupt vectors * @vsi: the VSI being configured * - * We allocate one q_vector per queue interrupt. If allocation fails we + * We allocate one q_vector per queue interrupt. If allocation fails we * return -ENOMEM. */ static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi) @@ -1188,7 +1200,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) struct ice_pf *pf = vsi->back; int i; - /* Allocate tx_rings */ + /* Allocate Tx rings */ for (i = 0; i < vsi->alloc_txq; i++) { struct ice_ring *ring; @@ -1207,7 +1219,7 @@ static int ice_vsi_alloc_rings(struct ice_vsi *vsi) vsi->tx_rings[i] = ring; } - /* Allocate rx_rings */ + /* Allocate Rx rings */ for (i = 0; i < vsi->alloc_rxq; i++) { struct ice_ring *ring; @@ -1611,55 +1623,62 @@ int ice_vsi_cfg_txqs(struct ice_vsi *vsi) struct ice_aqc_add_tx_qgrp *qg_buf; struct ice_aqc_add_txqs_perq *txq; struct ice_pf *pf = vsi->back; + u8 num_q_grps, q_idx = 0; enum ice_status status; u16 buf_len, i, pf_q; int err = 0, tc = 0; - u8 num_q_grps; buf_len = sizeof(struct ice_aqc_add_tx_qgrp); qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL); if (!qg_buf) return -ENOMEM; - if (vsi->num_txq > ICE_MAX_TXQ_PER_TXQG) { - err = -EINVAL; - goto err_cfg_txqs; - } qg_buf->num_txqs = 1; num_q_grps = 1; - /* set up and configure the Tx queues */ - ice_for_each_txq(vsi, i) { - struct ice_tlan_ctx tlan_ctx = { 0 }; + /* set up and configure the Tx queues for each enabled TC */ + for (tc = 0; tc < ICE_MAX_TRAFFIC_CLASS; tc++) { + if (!(vsi->tc_cfg.ena_tc & BIT(tc))) + break; - pf_q = vsi->txq_map[i]; - ice_setup_tx_ctx(vsi->tx_rings[i], &tlan_ctx, pf_q); - /* copy context contents into the qg_buf */ - qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q); - ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx, - ice_tlan_ctx_info); + for (i = 0; i < vsi->tc_cfg.tc_info[tc].qcount_tx; i++) { + struct ice_tlan_ctx tlan_ctx = { 0 }; + + pf_q = vsi->txq_map[q_idx]; + ice_setup_tx_ctx(vsi->tx_rings[q_idx], &tlan_ctx, + pf_q); + /* copy context contents into the qg_buf */ + qg_buf->txqs[0].txq_id = cpu_to_le16(pf_q); + ice_set_ctx((u8 *)&tlan_ctx, qg_buf->txqs[0].txq_ctx, + ice_tlan_ctx_info); + + /* init queue specific tail reg. It is referred as + * transmit comm scheduler queue doorbell. + */ + vsi->tx_rings[q_idx]->tail = + pf->hw.hw_addr + QTX_COMM_DBELL(pf_q); + status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, + num_q_grps, qg_buf, buf_len, + NULL); + if (status) { + dev_err(&vsi->back->pdev->dev, + "Failed to set LAN Tx queue context, error: %d\n", + status); + err = -ENODEV; + goto err_cfg_txqs; + } - /* init queue specific tail reg. It is referred as transmit - * comm scheduler queue doorbell. - */ - vsi->tx_rings[i]->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q); - status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, - num_q_grps, qg_buf, buf_len, NULL); - if (status) { - dev_err(&vsi->back->pdev->dev, - "Failed to set LAN Tx queue context, error: %d\n", - status); - err = -ENODEV; - goto err_cfg_txqs; - } + /* Add Tx Queue TEID into the VSI Tx ring from the + * response. This will complete configuring and + * enabling the queue. + */ + txq = &qg_buf->txqs[0]; + if (pf_q == le16_to_cpu(txq->txq_id)) + vsi->tx_rings[q_idx]->txq_teid = + le32_to_cpu(txq->q_teid); - /* Add Tx Queue TEID into the VSI Tx ring from the response - * This will complete configuring and enabling the queue. - */ - txq = &qg_buf->txqs[0]; - if (pf_q == le16_to_cpu(txq->txq_id)) - vsi->tx_rings[i]->txq_teid = - le32_to_cpu(txq->q_teid); + q_idx++; + } } err_cfg_txqs: devm_kfree(&pf->pdev->dev, qg_buf); @@ -1908,7 +1927,8 @@ int ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, ice_for_each_txq(vsi, i) { u16 v_idx; - if (!vsi->tx_rings || !vsi->tx_rings[i]) { + if (!vsi->tx_rings || !vsi->tx_rings[i] || + !vsi->tx_rings[i]->q_vector) { err = -EINVAL; goto err_out; } @@ -2056,6 +2076,9 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, /* set RSS capabilities */ ice_vsi_set_rss_params(vsi); + /* set tc configuration */ + ice_vsi_set_tc_cfg(vsi); + /* create the VSI */ ret = ice_vsi_init(vsi); if (ret) @@ -2113,17 +2136,13 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, pf->q_left_rx -= vsi->alloc_rxq; break; default: - /* if VSI type is not recognized, clean up the resources and - * exit - */ + /* clean up the resources and exit */ goto unroll_vsi_init; } - ice_vsi_set_tc_cfg(vsi); - /* configure VSI nodes based on number of queues and TC's */ for (i = 0; i < vsi->tc_cfg.numtc; i++) - max_txqs[i] = vsi->num_txq; + max_txqs[i] = pf->num_lan_tx; ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, max_txqs); @@ -2314,7 +2333,7 @@ static int ice_search_res(struct ice_res_tracker *res, u16 needed, u16 id) int start = res->search_hint; int end = start; - if ((start + needed) > res->num_entries) + if ((start + needed) > res->num_entries) return -ENOMEM; id |= ICE_RES_VALID_BIT; @@ -2491,6 +2510,7 @@ int ice_vsi_release(struct ice_vsi *vsi) } ice_remove_vsi_fltr(&pf->hw, vsi->idx); + ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); ice_vsi_delete(vsi); ice_vsi_free_q_vectors(vsi); ice_vsi_clear_rings(vsi); @@ -2518,11 +2538,14 @@ int ice_vsi_release(struct ice_vsi *vsi) int ice_vsi_rebuild(struct ice_vsi *vsi) { u16 max_txqs[ICE_MAX_TRAFFIC_CLASS] = { 0 }; + struct ice_pf *pf; int ret, i; if (!vsi) return -EINVAL; + pf = vsi->back; + ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx); ice_vsi_free_q_vectors(vsi); ice_free_res(vsi->back->sw_irq_tracker, vsi->sw_base_vector, vsi->idx); ice_free_res(vsi->back->hw_irq_tracker, vsi->hw_base_vector, vsi->idx); @@ -2532,6 +2555,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) ice_vsi_free_arrays(vsi, false); ice_dev_onetime_setup(&vsi->back->hw); ice_vsi_set_num_qs(vsi); + ice_vsi_set_tc_cfg(vsi); /* Initialize VSI struct elements and create VSI in FW */ ret = ice_vsi_init(vsi); @@ -2578,11 +2602,9 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) break; } - ice_vsi_set_tc_cfg(vsi); - /* configure VSI nodes based on number of queues and TC's */ for (i = 0; i < vsi->tc_cfg.numtc; i++) - max_txqs[i] = vsi->num_txq; + max_txqs[i] = pf->num_lan_tx; ret = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, max_txqs); diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 333312a1d595..8725569d11f0 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -349,6 +349,9 @@ ice_prepare_for_reset(struct ice_pf *pf) /* disable the VSIs and their queues that are not already DOWN */ ice_pf_dis_all_vsi(pf); + if (hw->port_info) + ice_sched_clear_port(hw->port_info); + ice_shutdown_all_ctrlq(hw); set_bit(__ICE_PREPARED_FOR_RESET, pf->state); @@ -405,7 +408,7 @@ static void ice_reset_subtask(struct ice_pf *pf) /* When a CORER/GLOBR/EMPR is about to happen, the hardware triggers an * OICR interrupt. The OICR handler (ice_misc_intr) determines what type * of reset is pending and sets bits in pf->state indicating the reset - * type and __ICE_RESET_OICR_RECV. So, if the latter bit is set + * type and __ICE_RESET_OICR_RECV. So, if the latter bit is set * prepare for pending reset if not already (for PF software-initiated * global resets the software should already be prepared for it as * indicated by __ICE_PREPARED_FOR_RESET; for global resets initiated @@ -1379,7 +1382,7 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf) * @pf: board private structure * * This sets up the handler for MSIX 0, which is used to manage the - * non-queue interrupts, e.g. AdminQ and errors. This is not used + * non-queue interrupts, e.g. AdminQ and errors. This is not used * when in MSI or Legacy interrupt mode. */ static int ice_req_irq_msix_misc(struct ice_pf *pf) @@ -1783,7 +1786,7 @@ static void ice_determine_q_usage(struct ice_pf *pf) pf->num_lan_tx = min_t(int, q_left_tx, num_online_cpus()); - /* only 1 rx queue unless RSS is enabled */ + /* only 1 Rx queue unless RSS is enabled */ if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) pf->num_lan_rx = 1; else @@ -2091,8 +2094,7 @@ static int ice_probe(struct pci_dev *pdev, ice_determine_q_usage(pf); - pf->num_alloc_vsi = min_t(u16, ICE_MAX_VSI_ALLOC, - hw->func_caps.guaranteed_num_vsi); + pf->num_alloc_vsi = hw->func_caps.guar_num_vsi; if (!pf->num_alloc_vsi) { err = -EIO; goto err_init_pf_unroll; @@ -2544,7 +2546,6 @@ static int ice_vsi_cfg(struct ice_vsi *vsi) if (err) return err; } - err = ice_vsi_cfg_txqs(vsi); if (!err) err = ice_vsi_cfg_rxqs(vsi); @@ -2563,8 +2564,12 @@ static void ice_napi_enable_all(struct ice_vsi *vsi) if (!vsi->netdev) return; - for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) - napi_enable(&vsi->q_vectors[q_idx]->napi); + for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) { + struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; + + if (q_vector->rx.ring || q_vector->tx.ring) + napi_enable(&q_vector->napi); + } } /** @@ -2931,8 +2936,12 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) if (!vsi->netdev) return; - for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) - napi_disable(&vsi->q_vectors[q_idx]->napi); + for (q_idx = 0; q_idx < vsi->num_q_vectors; q_idx++) { + struct ice_q_vector *q_vector = vsi->q_vectors[q_idx]; + + if (q_vector->rx.ring || q_vector->tx.ring) + napi_disable(&q_vector->napi); + } } /** @@ -3138,8 +3147,9 @@ static void ice_vsi_release_all(struct ice_pf *pf) /** * ice_dis_vsi - pause a VSI * @vsi: the VSI being paused + * @locked: is the rtnl_lock already held */ -static void ice_dis_vsi(struct ice_vsi *vsi) +static void ice_dis_vsi(struct ice_vsi *vsi, bool locked) { if (test_bit(__ICE_DOWN, vsi->state)) return; @@ -3148,9 +3158,13 @@ static void ice_dis_vsi(struct ice_vsi *vsi) if (vsi->type == ICE_VSI_PF && vsi->netdev) { if (netif_running(vsi->netdev)) { - rtnl_lock(); - vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); - rtnl_unlock(); + if (!locked) { + rtnl_lock(); + vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); + rtnl_unlock(); + } else { + vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); + } } else { ice_vsi_close(vsi); } @@ -3189,7 +3203,7 @@ static void ice_pf_dis_all_vsi(struct ice_pf *pf) ice_for_each_vsi(pf, v) if (pf->vsi[v]) - ice_dis_vsi(pf->vsi[v]); + ice_dis_vsi(pf->vsi[v], false); } /** @@ -3618,6 +3632,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode) * @dev: the netdev being configured * @nlh: RTNL message * @flags: bridge setlink flags + * @extack: netlink extended ack * * Sets the bridge mode (VEB/VEPA) of the switch to which the netdev (VSI) is * hooked up to. Iterates through the PF VSI list and sets the loopback mode (if @@ -3626,7 +3641,7 @@ static int ice_vsi_update_bridge_mode(struct ice_vsi *vsi, u16 bmode) */ static int ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, - u16 __always_unused flags) + u16 __always_unused flags, struct netlink_ext_ack *extack) { struct ice_netdev_priv *np = netdev_priv(dev); struct ice_pf *pf = np->vsi->back; @@ -3668,7 +3683,7 @@ ice_bridge_setlink(struct net_device *dev, struct nlmsghdr *nlh, */ status = ice_update_sw_rule_bridge_mode(hw); if (status) { - netdev_err(dev, "update SW_RULE for bridge mode failed, = %d err %d aq_err %d\n", + netdev_err(dev, "switch rule update failed, mode = %d err %d aq_err %d\n", mode, status, hw->adminq.sq_last_status); /* revert hw->evb_veb */ hw->evb_veb = (pf_sw->bridge_mode == BRIDGE_MODE_VEB); @@ -3691,40 +3706,36 @@ static void ice_tx_timeout(struct net_device *netdev) struct ice_ring *tx_ring = NULL; struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; - u32 head, val = 0, i; int hung_queue = -1; + u32 i; pf->tx_timeout_count++; - /* find the stopped queue the same way the stack does */ + /* find the stopped queue the same way dev_watchdog() does */ for (i = 0; i < netdev->num_tx_queues; i++) { - struct netdev_queue *q; unsigned long trans_start; + struct netdev_queue *q; q = netdev_get_tx_queue(netdev, i); trans_start = q->trans_start; if (netif_xmit_stopped(q) && time_after(jiffies, - (trans_start + netdev->watchdog_timeo))) { + trans_start + netdev->watchdog_timeo)) { hung_queue = i; break; } } - if (i == netdev->num_tx_queues) { + if (i == netdev->num_tx_queues) netdev_info(netdev, "tx_timeout: no netdev hung queue found\n"); - } else { + else /* now that we have an index, find the tx_ring struct */ - for (i = 0; i < vsi->num_txq; i++) { - if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) { - if (hung_queue == - vsi->tx_rings[i]->q_index) { + for (i = 0; i < vsi->num_txq; i++) + if (vsi->tx_rings[i] && vsi->tx_rings[i]->desc) + if (hung_queue == vsi->tx_rings[i]->q_index) { tx_ring = vsi->tx_rings[i]; break; } - } - } - } /* Reset recovery level if enough time has elapsed after last timeout. * Also ensure no new reset action happens before next timeout period. @@ -3736,17 +3747,20 @@ static void ice_tx_timeout(struct net_device *netdev) return; if (tx_ring) { - head = tx_ring->next_to_clean; + struct ice_hw *hw = &pf->hw; + u32 head, val = 0; + + head = (rd32(hw, QTX_COMM_HEAD(vsi->txq_map[hung_queue])) & + QTX_COMM_HEAD_HEAD_M) >> QTX_COMM_HEAD_HEAD_S; /* Read interrupt register */ if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - val = rd32(&pf->hw, + val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->v_idx + - tx_ring->vsi->hw_base_vector)); + tx_ring->vsi->hw_base_vector)); - netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HWB: 0x%x, NTU: 0x%x, TAIL: 0x%x, INT: 0x%x\n", + netdev_info(netdev, "tx_timeout: VSI_num: %d, Q %d, NTC: 0x%x, HW_HEAD: 0x%x, NTU: 0x%x, INT: 0x%x\n", vsi->vsi_num, hung_queue, tx_ring->next_to_clean, - head, tx_ring->next_to_use, - readl(tx_ring->tail), val); + head, tx_ring->next_to_use, val); } pf->tx_timeout_last_recovery = jiffies; @@ -3780,7 +3794,7 @@ static void ice_tx_timeout(struct net_device *netdev) * @netdev: network interface device structure * * The open entry point is called when a network interface is made - * active by the system (IFF_UP). At this point all resources needed + * active by the system (IFF_UP). At this point all resources needed * for transmit and receive operations are allocated, the interrupt * handler is registered with the OS, the netdev watchdog is enabled, * and the stack is notified that the interface is ready. @@ -3813,7 +3827,7 @@ static int ice_open(struct net_device *netdev) * @netdev: network interface device structure * * The stop entry point is called when an interface is de-activated by the OS, - * and the netdevice enters the DOWN state. The hardware is still under the + * and the netdevice enters the DOWN state. The hardware is still under the * driver's control, but the netdev interface is disabled. * * Returns success only - not allowed to fail @@ -3842,14 +3856,14 @@ ice_features_check(struct sk_buff *skb, size_t len; /* No point in doing any of this if neither checksum nor GSO are - * being requested for this frame. We can rule out both by just + * being requested for this frame. We can rule out both by just * checking for CHECKSUM_PARTIAL */ if (skb->ip_summed != CHECKSUM_PARTIAL) return features; /* We cannot support GSO if the MSS is going to be less than - * 64 bytes. If it is then we need to drop support for GSO. + * 64 bytes. If it is then we need to drop support for GSO. */ if (skb_is_gso(skb) && (skb_shinfo(skb)->gso_size < 64)) features &= ~NETIF_F_GSO_MASK; diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 7cc8aa18a22b..a1681853df2e 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -630,7 +630,7 @@ static void ice_sched_clear_tx_topo(struct ice_port_info *pi) * * Cleanup scheduling elements from SW DB */ -static void ice_sched_clear_port(struct ice_port_info *pi) +void ice_sched_clear_port(struct ice_port_info *pi) { if (!pi || pi->port_state != ICE_SCHED_PORT_STATE_READY) return; @@ -894,8 +894,7 @@ static u8 ice_sched_get_vsi_layer(struct ice_hw *hw) * This function removes the leaf node that was created by the FW * during initialization */ -static void -ice_rm_dflt_leaf_node(struct ice_port_info *pi) +static void ice_rm_dflt_leaf_node(struct ice_port_info *pi) { struct ice_sched_node *node; @@ -923,8 +922,7 @@ ice_rm_dflt_leaf_node(struct ice_port_info *pi) * This function frees all the nodes except root and TC that were created by * the FW during initialization */ -static void -ice_sched_rm_dflt_nodes(struct ice_port_info *pi) +static void ice_sched_rm_dflt_nodes(struct ice_port_info *pi) { struct ice_sched_node *node; @@ -1339,7 +1337,7 @@ ice_sched_rm_vsi_child_nodes(struct ice_port_info *pi, * @num_nodes: pointer to num nodes array * * This function calculates the number of supported nodes needed to add this - * VSI into tx tree including the VSI, parent and intermediate nodes in below + * VSI into Tx tree including the VSI, parent and intermediate nodes in below * layers */ static void @@ -1376,13 +1374,13 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, } /** - * ice_sched_add_vsi_support_nodes - add VSI supported nodes into tx tree + * ice_sched_add_vsi_support_nodes - add VSI supported nodes into Tx tree * @pi: port information structure * @vsi_handle: software VSI handle * @tc_node: pointer to TC node * @num_nodes: pointer to num nodes array * - * This function adds the VSI supported nodes into tx tree including the + * This function adds the VSI supported nodes into Tx tree including the * VSI, its parent and intermediate nodes in below layers */ static enum ice_status @@ -1527,7 +1525,7 @@ ice_sched_update_vsi_child_nodes(struct ice_port_info *pi, u16 vsi_handle, } /** - * ice_sched_cfg_vsi - configure the new/exisiting VSI + * ice_sched_cfg_vsi - configure the new/existing VSI * @pi: port information structure * @vsi_handle: software VSI handle * @tc: TC number @@ -1605,3 +1603,109 @@ ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, return status; } + +/** + * ice_sched_rm_agg_vsi_entry - remove agg related VSI info entry + * @pi: port information structure + * @vsi_handle: software VSI handle + * + * This function removes single aggregator VSI info entry from + * aggregator list. + */ +static void +ice_sched_rm_agg_vsi_info(struct ice_port_info *pi, u16 vsi_handle) +{ + struct ice_sched_agg_info *agg_info; + struct ice_sched_agg_info *atmp; + + list_for_each_entry_safe(agg_info, atmp, &pi->agg_list, list_entry) { + struct ice_sched_agg_vsi_info *agg_vsi_info; + struct ice_sched_agg_vsi_info *vtmp; + + list_for_each_entry_safe(agg_vsi_info, vtmp, + &agg_info->agg_vsi_list, list_entry) + if (agg_vsi_info->vsi_handle == vsi_handle) { + list_del(&agg_vsi_info->list_entry); + devm_kfree(ice_hw_to_dev(pi->hw), + agg_vsi_info); + return; + } + } +} + +/** + * ice_sched_rm_vsi_cfg - remove the VSI and its children nodes + * @pi: port information structure + * @vsi_handle: software VSI handle + * @owner: LAN or RDMA + * + * This function removes the VSI and its LAN or RDMA children nodes from the + * scheduler tree. + */ +static enum ice_status +ice_sched_rm_vsi_cfg(struct ice_port_info *pi, u16 vsi_handle, u8 owner) +{ + enum ice_status status = ICE_ERR_PARAM; + struct ice_vsi_ctx *vsi_ctx; + u8 i, j = 0; + + if (!ice_is_vsi_valid(pi->hw, vsi_handle)) + return status; + mutex_lock(&pi->sched_lock); + vsi_ctx = ice_get_vsi_ctx(pi->hw, vsi_handle); + if (!vsi_ctx) + goto exit_sched_rm_vsi_cfg; + + for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) { + struct ice_sched_node *vsi_node, *tc_node; + + tc_node = ice_sched_get_tc_node(pi, i); + if (!tc_node) + continue; + + vsi_node = ice_sched_get_vsi_node(pi->hw, tc_node, vsi_handle); + if (!vsi_node) + continue; + + while (j < vsi_node->num_children) { + if (vsi_node->children[j]->owner == owner) { + ice_free_sched_node(pi, vsi_node->children[j]); + + /* reset the counter again since the num + * children will be updated after node removal + */ + j = 0; + } else { + j++; + } + } + /* remove the VSI if it has no children */ + if (!vsi_node->num_children) { + ice_free_sched_node(pi, vsi_node); + vsi_ctx->sched.vsi_node[i] = NULL; + + /* clean up agg related vsi info if any */ + ice_sched_rm_agg_vsi_info(pi, vsi_handle); + } + if (owner == ICE_SCHED_NODE_OWNER_LAN) + vsi_ctx->sched.max_lanq[i] = 0; + } + status = 0; + +exit_sched_rm_vsi_cfg: + mutex_unlock(&pi->sched_lock); + return status; +} + +/** + * ice_rm_vsi_lan_cfg - remove VSI and its LAN children nodes + * @pi: port information structure + * @vsi_handle: software VSI handle + * + * This function clears the VSI and its LAN children nodes from scheduler tree + * for all TCs. + */ +enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle) +{ + return ice_sched_rm_vsi_cfg(pi, vsi_handle, ICE_SCHED_NODE_OWNER_LAN); +} diff --git a/drivers/net/ethernet/intel/ice/ice_sched.h b/drivers/net/ethernet/intel/ice/ice_sched.h index 5dc9cfa04c58..da5b4c166da8 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.h +++ b/drivers/net/ethernet/intel/ice/ice_sched.h @@ -12,6 +12,7 @@ struct ice_sched_agg_vsi_info { struct list_head list_entry; DECLARE_BITMAP(tc_bitmap, ICE_MAX_TRAFFIC_CLASS); + u16 vsi_handle; }; struct ice_sched_agg_info { @@ -25,6 +26,7 @@ struct ice_sched_agg_info { /* FW AQ command calls */ enum ice_status ice_sched_init_port(struct ice_port_info *pi); enum ice_status ice_sched_query_res_alloc(struct ice_hw *hw); +void ice_sched_clear_port(struct ice_port_info *pi); void ice_sched_cleanup_all(struct ice_hw *hw); struct ice_sched_node * ice_sched_find_node_by_teid(struct ice_sched_node *start_node, u32 teid); @@ -39,4 +41,5 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, enum ice_status ice_sched_cfg_vsi(struct ice_port_info *pi, u16 vsi_handle, u8 tc, u16 maxqs, u8 owner, bool enable); +enum ice_status ice_rm_vsi_lan_cfg(struct ice_port_info *pi, u16 vsi_handle); #endif /* _ICE_SCHED_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c index 027eba4e13f8..533b989a23e1 100644 --- a/drivers/net/ethernet/intel/ice/ice_sriov.c +++ b/drivers/net/ethernet/intel/ice/ice_sriov.c @@ -46,7 +46,7 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval, * @link_speed: variable containing the link_speed to be converted * * Convert link speed supported by HW to link speed supported by virtchnl. - * If adv_link_support is true, then return link speed in Mbps. Else return + * If adv_link_support is true, then return link speed in Mbps. Else return * link speed as a VIRTCHNL_LINK_SPEED_* casted to a u32. Note that the caller * needs to cast back to an enum virtchnl_link_speed in the case where * adv_link_support is false, but when adv_link_support is true the caller can diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 40c9c6558956..2e5693107fa4 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -92,8 +92,7 @@ ice_aq_alloc_free_res(struct ice_hw *hw, u16 num_entries, * Allocate memory for the entire recipe table and initialize the structures/ * entries corresponding to basic recipes. */ -enum ice_status -ice_init_def_sw_recp(struct ice_hw *hw) +enum ice_status ice_init_def_sw_recp(struct ice_hw *hw) { struct ice_sw_recipe *recps; u8 i; @@ -130,7 +129,7 @@ ice_init_def_sw_recp(struct ice_hw *hw) * * NOTE: *req_desc is both an input/output parameter. * The caller of this function first calls this function with *request_desc set - * to 0. If the response from f/w has *req_desc set to 0, all the switch + * to 0. If the response from f/w has *req_desc set to 0, all the switch * configuration information has been returned; if non-zero (meaning not all * the information was returned), the caller should call this function again * with *req_desc set to the previous value returned by f/w to get the @@ -629,25 +628,36 @@ enum ice_status ice_get_initial_sw_cfg(struct ice_hw *hw) /** * ice_fill_sw_info - Helper function to populate lb_en and lan_en * @hw: pointer to the hardware structure - * @f_info: filter info structure to fill/update + * @fi: filter info structure to fill/update * * This helper function populates the lb_en and lan_en elements of the provided * ice_fltr_info struct using the switch's type and characteristics of the * switch rule being configured. */ -static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *f_info) +static void ice_fill_sw_info(struct ice_hw *hw, struct ice_fltr_info *fi) { - f_info->lb_en = false; - f_info->lan_en = false; - if ((f_info->flag & ICE_FLTR_TX) && - (f_info->fltr_act == ICE_FWD_TO_VSI || - f_info->fltr_act == ICE_FWD_TO_VSI_LIST || - f_info->fltr_act == ICE_FWD_TO_Q || - f_info->fltr_act == ICE_FWD_TO_QGRP)) { - f_info->lb_en = true; - if (!(hw->evb_veb && f_info->lkup_type == ICE_SW_LKUP_MAC && - is_unicast_ether_addr(f_info->l_data.mac.mac_addr))) - f_info->lan_en = true; + fi->lb_en = false; + fi->lan_en = false; + if ((fi->flag & ICE_FLTR_TX) && + (fi->fltr_act == ICE_FWD_TO_VSI || + fi->fltr_act == ICE_FWD_TO_VSI_LIST || + fi->fltr_act == ICE_FWD_TO_Q || + fi->fltr_act == ICE_FWD_TO_QGRP)) { + fi->lb_en = true; + /* Do not set lan_en to TRUE if + * 1. The switch is a VEB AND + * 2 + * 2.1 The lookup is MAC with unicast addr for MAC, OR + * 2.2 The lookup is MAC_VLAN with unicast addr for MAC + * + * In all other cases, the LAN enable has to be set to true. + */ + if (!(hw->evb_veb && + ((fi->lkup_type == ICE_SW_LKUP_MAC && + is_unicast_ether_addr(fi->l_data.mac.mac_addr)) || + (fi->lkup_type == ICE_SW_LKUP_MAC_VLAN && + is_unicast_ether_addr(fi->l_data.mac_vlan.mac_addr))))) + fi->lan_en = true; } } @@ -817,7 +827,7 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, /* Create two back-to-back switch rules and submit them to the HW using * one memory buffer: * 1. Large Action - * 2. Look up tx rx + * 2. Look up Tx Rx */ lg_act_size = (u16)ICE_SW_RULE_LG_ACT_SIZE(num_lg_acts); rules_size = lg_act_size + ICE_SW_RULE_RX_TX_ETH_HDR_SIZE; @@ -861,7 +871,7 @@ ice_add_marker_act(struct ice_hw *hw, struct ice_fltr_mgmt_list_entry *m_ent, lg_act->pdata.lg_act.act[2] = cpu_to_le32(act); - /* call the fill switch rule to fill the lookup tx rx structure */ + /* call the fill switch rule to fill the lookup Tx Rx structure */ ice_fill_sw_rule(hw, &m_ent->fltr_info, rx_tx, ice_aqc_opc_update_sw_rules); @@ -1158,8 +1168,8 @@ enum ice_status ice_update_sw_rule_bridge_mode(struct ice_hw *hw) * Call AQ command to add or update previously created VSI list with new VSI. * * Helper function to do book keeping associated with adding filter information - * The algorithm to do the booking keeping is described below : - * When a VSI needs to subscribe to a given filter( MAC/VLAN/Ethtype etc.) + * The algorithm to do the book keeping is described below : + * When a VSI needs to subscribe to a given filter (MAC/VLAN/Ethtype etc.) * if only one VSI has been added till now * Allocate a new VSI list and add two VSIs * to this list using switch rule command @@ -1237,6 +1247,9 @@ ice_add_update_vsi_list(struct ice_hw *hw, u16 vsi_handle = new_fltr->vsi_handle; enum ice_adminq_opc opcode; + if (!m_entry->vsi_list_info) + return ICE_ERR_CFG; + /* A rule already exists with the new VSI being added */ if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map)) return 0; @@ -1853,7 +1866,7 @@ ice_add_vlan_internal(struct ice_hw *hw, struct ice_fltr_list_entry *f_entry) tmp_fltr.fwd_id.vsi_list_id = vsi_list_id; tmp_fltr.fltr_act = ICE_FWD_TO_VSI_LIST; /* Update the previous switch rule to a new VSI list which - * includes current VSI thats requested + * includes current VSI that is requested */ status = ice_update_pkt_fwd_rule(hw, &tmp_fltr); if (status) diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index fe5bbabbb41e..49fc38094185 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -219,7 +219,7 @@ static bool ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring, /** * ice_setup_tx_ring - Allocate the Tx descriptors - * @tx_ring: the tx ring to set up + * @tx_ring: the Tx ring to set up * * Return 0 on success, negative on error */ @@ -324,7 +324,7 @@ void ice_free_rx_ring(struct ice_ring *rx_ring) /** * ice_setup_rx_ring - Allocate the Rx descriptors - * @rx_ring: the rx ring to set up + * @rx_ring: the Rx ring to set up * * Return 0 on success, negative on error */ @@ -377,7 +377,7 @@ static void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val) rx_ring->next_to_alloc = val; /* Force memory writes to complete before letting h/w - * know there are new descriptors to fetch. (Only + * know there are new descriptors to fetch. (Only * applicable for weak-ordered memory model archs, * such as IA-64). */ @@ -586,7 +586,7 @@ static bool ice_add_rx_frag(struct ice_rx_buf *rx_buf, /** * ice_reuse_rx_page - page flip buffer and store it back on the ring - * @rx_ring: rx descriptor ring to store buffers on + * @rx_ring: Rx descriptor ring to store buffers on * @old_buf: donor buffer to have page reused * * Synchronizes page for reuse by the adapter @@ -609,7 +609,7 @@ static void ice_reuse_rx_page(struct ice_ring *rx_ring, /** * ice_fetch_rx_buf - Allocate skb and populate it - * @rx_ring: rx descriptor ring to transact packets on + * @rx_ring: Rx descriptor ring to transact packets on * @rx_desc: descriptor containing info written by hardware * * This function allocates an skb on the fly, and populates it with the page @@ -686,7 +686,7 @@ static struct sk_buff *ice_fetch_rx_buf(struct ice_ring *rx_ring, * ice_pull_tail - ice specific version of skb_pull_tail * @skb: pointer to current skb being adjusted * - * This function is an ice specific version of __pskb_pull_tail. The + * This function is an ice specific version of __pskb_pull_tail. The * main difference between this version and the original function is that * this function can make several assumptions about the state of things * that allow for significant optimizations versus the standard function. @@ -768,7 +768,7 @@ static bool ice_test_staterr(union ice_32b_rx_flex_desc *rx_desc, * @rx_desc: Rx descriptor for current buffer * @skb: Current socket buffer containing buffer in progress * - * This function updates next to clean. If the buffer is an EOP buffer + * This function updates next to clean. If the buffer is an EOP buffer * this function exits returning false, otherwise it will place the * sk_buff in the next buffer to be chained and return true indicating * that this is in fact a non-EOP buffer. @@ -904,7 +904,7 @@ checksum_fail: /** * ice_process_skb_fields - Populate skb header fields from Rx descriptor - * @rx_ring: rx descriptor ring packet is being transacted on + * @rx_ring: Rx descriptor ring packet is being transacted on * @rx_desc: pointer to the EOP Rx descriptor * @skb: pointer to current skb being populated * @ptype: the packet type decoded by hardware @@ -927,7 +927,7 @@ static void ice_process_skb_fields(struct ice_ring *rx_ring, /** * ice_receive_skb - Send a completed packet up the stack - * @rx_ring: rx ring in play + * @rx_ring: Rx ring in play * @skb: packet to send up * @vlan_tag: vlan tag for packet * @@ -946,11 +946,11 @@ static void ice_receive_skb(struct ice_ring *rx_ring, struct sk_buff *skb, /** * ice_clean_rx_irq - Clean completed descriptors from Rx ring - bounce buf - * @rx_ring: rx descriptor ring to transact packets on + * @rx_ring: Rx descriptor ring to transact packets on * @budget: Total limit on number of packets to process * * This function provides a "bounce buffer" approach to Rx interrupt - * processing. The advantage to this is that on systems that have + * processing. The advantage to this is that on systems that have * expensive overhead for IOMMU access this provides a means of avoiding * it by maintaining the mapping of the page to the system. * @@ -1103,11 +1103,14 @@ int ice_napi_poll(struct napi_struct *napi, int budget) if (!clean_complete) return budget; - /* Work is done so exit the polling mode and re-enable the interrupt */ - napi_complete_done(napi, work_done); - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - ice_irq_dynamic_ena(&vsi->back->hw, vsi, q_vector); - return 0; + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) + if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) + ice_irq_dynamic_ena(&vsi->back->hw, vsi, q_vector); + + return min(work_done, budget - 1); } /* helper function for building cmd/type/offset */ @@ -1122,7 +1125,7 @@ build_ctob(u64 td_cmd, u64 td_offset, unsigned int size, u64 td_tag) } /** - * __ice_maybe_stop_tx - 2nd level check for tx stop conditions + * __ice_maybe_stop_tx - 2nd level check for Tx stop conditions * @tx_ring: the ring to be checked * @size: the size buffer we want to assure is available * @@ -1145,7 +1148,7 @@ static int __ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size) } /** - * ice_maybe_stop_tx - 1st level check for tx stop conditions + * ice_maybe_stop_tx - 1st level check for Tx stop conditions * @tx_ring: the ring to be checked * @size: the size buffer we want to assure is available * @@ -1155,6 +1158,7 @@ static int ice_maybe_stop_tx(struct ice_ring *tx_ring, unsigned int size) { if (likely(ICE_DESC_UNUSED(tx_ring) >= size)) return 0; + return __ice_maybe_stop_tx(tx_ring, size); } @@ -1552,7 +1556,7 @@ int ice_tso(struct ice_tx_buf *first, struct ice_tx_offload_params *off) * Finally, we add one to round up. Because 256 isn't an exact multiple of * 3, we'll underestimate near each multiple of 12K. This is actually more * accurate as we have 4K - 1 of wiggle room that we can fit into the last - * segment. For our purposes this is accurate out to 1M which is orders of + * segment. For our purposes this is accurate out to 1M which is orders of * magnitude greater than our largest possible GSO size. * * This would then be implemented as: @@ -1568,7 +1572,7 @@ static unsigned int ice_txd_use_count(unsigned int size) } /** - * ice_xmit_desc_count - calculate number of tx descriptors needed + * ice_xmit_desc_count - calculate number of Tx descriptors needed * @skb: send buffer * * Returns number of data descriptors needed for this skb. @@ -1620,7 +1624,7 @@ static bool __ice_chk_linearize(struct sk_buff *skb) nr_frags -= ICE_MAX_BUF_TXD - 2; frag = &skb_shinfo(skb)->frags[0]; - /* Initialize size to the negative value of gso_size minus 1. We + /* Initialize size to the negative value of gso_size minus 1. We * use this as the worst case scenerio in which the frag ahead * of us only provides one byte which is why we are limited to 6 * descriptors for a single transmit as the header and previous diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index f4dbc81c1988..0ea428104215 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -124,6 +124,8 @@ struct ice_phy_info { /* Common HW capabilities for SW use */ struct ice_hw_common_caps { + u32 valid_functions; + /* TX/RX queues */ u16 num_rxq; /* Number/Total RX queues */ u16 rxq_first_id; /* First queue ID for RX queues */ @@ -150,7 +152,7 @@ struct ice_hw_func_caps { struct ice_hw_common_caps common_cap; u32 num_allocd_vfs; /* Number of allocated VFs */ u32 vf_base_id; /* Logical ID of the first VF */ - u32 guaranteed_num_vsi; + u32 guar_num_vsi; }; /* Device wide capabilities */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index e71065f9d391..05ff4f910649 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -156,8 +156,6 @@ static void ice_free_vf_res(struct ice_vf *vf) clear_bit(ICE_VF_STATE_UC_PROMISC, vf->vf_states); } -/***********************enable_vf routines*****************************/ - /** * ice_dis_vf_mappings * @vf: pointer to the VF structure @@ -215,6 +213,15 @@ void ice_free_vfs(struct ice_pf *pf) while (test_and_set_bit(__ICE_VF_DIS, pf->state)) usleep_range(1000, 2000); + /* Disable IOV before freeing resources. This lets any VF drivers + * running in the host get themselves cleaned up before we yank + * the carpet out from underneath their feet. + */ + if (!pci_vfs_assigned(pf->pdev)) + pci_disable_sriov(pf->pdev); + else + dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n"); + /* Avoid wait time by stopping all VFs at the same time */ for (i = 0; i < pf->num_alloc_vfs; i++) { if (!test_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states)) @@ -228,15 +235,6 @@ void ice_free_vfs(struct ice_pf *pf) clear_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states); } - /* Disable IOV before freeing resources. This lets any VF drivers - * running in the host get themselves cleaned up before we yank - * the carpet out from underneath their feet. - */ - if (!pci_vfs_assigned(pf->pdev)) - pci_disable_sriov(pf->pdev); - else - dev_warn(&pf->pdev->dev, "VFs are assigned - not disabling SR-IOV\n"); - tmp = pf->num_alloc_vfs; pf->num_vf_qps = 0; pf->num_alloc_vfs = 0; @@ -454,7 +452,7 @@ static int ice_alloc_vsi_res(struct ice_vf *vf) /* Clear this bit after VF initialization since we shouldn't reclaim * and reassign interrupts for synchronous or asynchronous VFR events. - * We don't want to reconfigure interrupts since AVF driver doesn't + * We dont want to reconfigure interrupts since AVF driver doesn't * expect vector assignment to be changed unless there is a request for * more vectors. */ @@ -1105,7 +1103,7 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) * ice_process_vflr_event - Free VF resources via IRQ calls * @pf: pointer to the PF structure * - * called from the VLFR IRQ handler to + * called from the VFLR IRQ handler to * free up VF resources and state variables */ void ice_process_vflr_event(struct ice_pf *pf) @@ -1764,7 +1762,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) /* copy Tx queue info from VF into VSI */ vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr; vsi->tx_rings[i]->count = qpi->txq.ring_len; - /* copy Rx queue info from VF into vsi */ + /* copy Rx queue info from VF into VSI */ vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; vsi->rx_rings[i]->count = qpi->rxq.ring_len; if (qpi->rxq.databuffer_size > ((16 * 1024) - 128)) { @@ -1830,7 +1828,7 @@ static bool ice_can_vf_change_mac(struct ice_vf *vf) * @msg: pointer to the msg buffer * @set: true if mac filters are being set, false otherwise * - * add guest mac address filter + * add guest MAC address filter */ static int ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) @@ -1968,9 +1966,9 @@ static int ice_vc_del_mac_addr_msg(struct ice_vf *vf, u8 *msg) * @msg: pointer to the msg buffer * * VFs get a default number of queues but can use this message to request a - * different number. If the request is successful, PF will reset the VF and + * different number. If the request is successful, PF will reset the VF and * return 0. If unsuccessful, PF will send message informing VF of number of - * available queue pairs via virtchnl message response to VF. + * available queue pairs via virtchnl message response to vf. */ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg) { @@ -1991,7 +1989,7 @@ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg) tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx); if (req_queues <= 0) { dev_err(&pf->pdev->dev, - "VF %d tried to request %d queues. Ignoring.\n", + "VF %d tried to request %d queues. Ignoring.\n", vf->vf_id, req_queues); } else if (req_queues > ICE_MAX_QS_PER_VF) { dev_err(&pf->pdev->dev, diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index 10131e0180f9..01470a8ee03a 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -70,7 +70,7 @@ struct ice_vf { u8 spoofchk; u16 num_mac; u16 num_vlan; - u8 num_req_qs; /* num of queue pairs requested by VF */ + u8 num_req_qs; /* num of queue pairs requested by VF */ }; #ifdef CONFIG_PCI_IOV diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index 8a28f3388f69..01fcfc6f3415 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -334,6 +334,7 @@ #define I210_RXPBSIZE_DEFAULT 0x000000A2 /* RXPBSIZE default */ #define I210_RXPBSIZE_MASK 0x0000003F +#define I210_RXPBSIZE_PB_30KB 0x0000001E #define I210_RXPBSIZE_PB_32KB 0x00000020 #define I210_TXPBSIZE_DEFAULT 0x04000014 /* TXPBSIZE default */ #define I210_TXPBSIZE_MASK 0xC0FFFFFF diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index ca54e268d157..fe1592ae8769 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -515,7 +515,7 @@ struct igb_adapter { /* OS defined structs */ struct pci_dev *pdev; - spinlock_t stats64_lock; + struct mutex stats64_lock; struct rtnl_link_stats64 stats64; /* structs defined in e1000_hw.h */ diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 5acf3b743876..7426060b678f 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2113,7 +2113,7 @@ static int igb_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { struct igb_adapter *adapter = netdev_priv(netdev); - if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE)) + if (wol->wolopts & (WAKE_ARP | WAKE_MAGICSECURE | WAKE_FILTER)) return -EOPNOTSUPP; if (!(adapter->flags & IGB_FLAG_WOL_SUPPORTED)) @@ -2295,7 +2295,7 @@ static void igb_get_ethtool_stats(struct net_device *netdev, int i, j; char *p; - spin_lock(&adapter->stats64_lock); + mutex_lock(&adapter->stats64_lock); igb_update_stats(adapter); for (i = 0; i < IGB_GLOBAL_STATS_LEN; i++) { @@ -2338,7 +2338,7 @@ static void igb_get_ethtool_stats(struct net_device *netdev, } while (u64_stats_fetch_retry_irq(&ring->rx_syncp, start)); i += IGB_RX_QUEUE_STATS_LEN; } - spin_unlock(&adapter->stats64_lock); + mutex_unlock(&adapter->stats64_lock); } static void igb_get_strings(struct net_device *netdev, u32 stringset, u8 *data) diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 5df88ad8ac81..87bdf1604ae2 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1850,13 +1850,12 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue) * configuration' in respect to these parameters. */ - netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d \ - idleslope %d sendslope %d hiCredit %d \ - locredit %d\n", - (ring->cbs_enable) ? "enabled" : "disabled", - (ring->launchtime_enable) ? "enabled" : "disabled", queue, - ring->idleslope, ring->sendslope, ring->hicredit, - ring->locredit); + netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n", + ring->cbs_enable ? "enabled" : "disabled", + ring->launchtime_enable ? "enabled" : "disabled", + queue, + ring->idleslope, ring->sendslope, + ring->hicredit, ring->locredit); } static int igb_save_txtime_params(struct igb_adapter *adapter, int queue, @@ -1935,7 +1934,7 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter) val = rd32(E1000_RXPBS); val &= ~I210_RXPBSIZE_MASK; - val |= I210_RXPBSIZE_PB_32KB; + val |= I210_RXPBSIZE_PB_30KB; wr32(E1000_RXPBS, val); /* Section 8.12.9 states that MAX_TPKT_SIZE from DTXMXPKTSZ @@ -2204,9 +2203,9 @@ void igb_down(struct igb_adapter *adapter) del_timer_sync(&adapter->phy_info_timer); /* record the stats before reset*/ - spin_lock(&adapter->stats64_lock); + mutex_lock(&adapter->stats64_lock); igb_update_stats(adapter); - spin_unlock(&adapter->stats64_lock); + mutex_unlock(&adapter->stats64_lock); adapter->link_speed = 0; adapter->link_duplex = 0; @@ -3841,7 +3840,7 @@ static int igb_sw_init(struct igb_adapter *adapter) adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN; spin_lock_init(&adapter->nfc_lock); - spin_lock_init(&adapter->stats64_lock); + mutex_init(&adapter->stats64_lock); #ifdef CONFIG_PCI_IOV switch (hw->mac.type) { case e1000_82576: @@ -5407,9 +5406,9 @@ no_wait: } } - spin_lock(&adapter->stats64_lock); + mutex_lock(&adapter->stats64_lock); igb_update_stats(adapter); - spin_unlock(&adapter->stats64_lock); + mutex_unlock(&adapter->stats64_lock); for (i = 0; i < adapter->num_tx_queues; i++) { struct igb_ring *tx_ring = adapter->tx_ring[i]; @@ -6019,6 +6018,8 @@ static int igb_tx_map(struct igb_ring *tx_ring, /* set the timestamp */ first->time_stamp = jiffies; + skb_tx_timestamp(skb); + /* Force memory writes to complete before letting h/w know there * are new descriptors to fetch. (Only applicable for weak-ordered * memory model archs, such as IA-64). @@ -6147,8 +6148,6 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, else if (!tso) igb_tx_csum(tx_ring, first); - skb_tx_timestamp(skb); - if (igb_tx_map(tx_ring, first, hdr_len)) goto cleanup_tx_tstamp; @@ -6236,10 +6235,10 @@ static void igb_get_stats64(struct net_device *netdev, { struct igb_adapter *adapter = netdev_priv(netdev); - spin_lock(&adapter->stats64_lock); + mutex_lock(&adapter->stats64_lock); igb_update_stats(adapter); memcpy(stats, &adapter->stats64, sizeof(*stats)); - spin_unlock(&adapter->stats64_lock); + mutex_unlock(&adapter->stats64_lock); } /** @@ -7753,11 +7752,13 @@ static int igb_poll(struct napi_struct *napi, int budget) if (!clean_complete) return budget; - /* If not enough Rx work done, exit the polling mode */ - napi_complete_done(napi, work_done); - igb_ring_irq_enable(q_vector); + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) + igb_ring_irq_enable(q_vector); - return 0; + return min(work_done, budget - 1); } /** @@ -8770,9 +8771,11 @@ static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake, rtnl_unlock(); #ifdef CONFIG_PM - retval = pci_save_state(pdev); - if (retval) - return retval; + if (!runtime) { + retval = pci_save_state(pdev); + if (retval) + return retval; + } #endif status = rd32(E1000_STATUS); diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 2b95dc9c7a6a..fd3071f55bd3 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -277,17 +277,53 @@ static int igb_ptp_adjtime_i210(struct ptp_clock_info *ptp, s64 delta) return 0; } -static int igb_ptp_gettime_82576(struct ptp_clock_info *ptp, - struct timespec64 *ts) +static int igb_ptp_gettimex_82576(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) { struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); + struct e1000_hw *hw = &igb->hw; unsigned long flags; + u32 lo, hi; u64 ns; spin_lock_irqsave(&igb->tmreg_lock, flags); - ns = timecounter_read(&igb->tc); + ptp_read_system_prets(sts); + lo = rd32(E1000_SYSTIML); + ptp_read_system_postts(sts); + hi = rd32(E1000_SYSTIMH); + + ns = timecounter_cyc2time(&igb->tc, ((u64)hi << 32) | lo); + + spin_unlock_irqrestore(&igb->tmreg_lock, flags); + + *ts = ns_to_timespec64(ns); + + return 0; +} + +static int igb_ptp_gettimex_82580(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) +{ + struct igb_adapter *igb = container_of(ptp, struct igb_adapter, + ptp_caps); + struct e1000_hw *hw = &igb->hw; + unsigned long flags; + u32 lo, hi; + u64 ns; + + spin_lock_irqsave(&igb->tmreg_lock, flags); + + ptp_read_system_prets(sts); + rd32(E1000_SYSTIMR); + ptp_read_system_postts(sts); + lo = rd32(E1000_SYSTIML); + hi = rd32(E1000_SYSTIMH); + + ns = timecounter_cyc2time(&igb->tc, ((u64)hi << 32) | lo); spin_unlock_irqrestore(&igb->tmreg_lock, flags); @@ -296,16 +332,22 @@ static int igb_ptp_gettime_82576(struct ptp_clock_info *ptp, return 0; } -static int igb_ptp_gettime_i210(struct ptp_clock_info *ptp, - struct timespec64 *ts) +static int igb_ptp_gettimex_i210(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) { struct igb_adapter *igb = container_of(ptp, struct igb_adapter, ptp_caps); + struct e1000_hw *hw = &igb->hw; unsigned long flags; spin_lock_irqsave(&igb->tmreg_lock, flags); - igb_ptp_read_i210(igb, ts); + ptp_read_system_prets(sts); + rd32(E1000_SYSTIMR); + ptp_read_system_postts(sts); + ts->tv_nsec = rd32(E1000_SYSTIML); + ts->tv_sec = rd32(E1000_SYSTIMH); spin_unlock_irqrestore(&igb->tmreg_lock, flags); @@ -658,9 +700,12 @@ static void igb_ptp_overflow_check(struct work_struct *work) struct igb_adapter *igb = container_of(work, struct igb_adapter, ptp_overflow_work.work); struct timespec64 ts; + u64 ns; - igb->ptp_caps.gettime64(&igb->ptp_caps, &ts); + /* Update the timecounter */ + ns = timecounter_read(&igb->tc); + ts = ns_to_timespec64(ns); pr_debug("igb overflow check at %lld.%09lu\n", (long long) ts.tv_sec, ts.tv_nsec); @@ -1126,7 +1171,7 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.pps = 0; adapter->ptp_caps.adjfreq = igb_ptp_adjfreq_82576; adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576; - adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576; + adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_82576; adapter->ptp_caps.settime64 = igb_ptp_settime_82576; adapter->ptp_caps.enable = igb_ptp_feature_enable; adapter->cc.read = igb_ptp_read_82576; @@ -1145,7 +1190,7 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.pps = 0; adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580; adapter->ptp_caps.adjtime = igb_ptp_adjtime_82576; - adapter->ptp_caps.gettime64 = igb_ptp_gettime_82576; + adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_82580; adapter->ptp_caps.settime64 = igb_ptp_settime_82576; adapter->ptp_caps.enable = igb_ptp_feature_enable; adapter->cc.read = igb_ptp_read_82580; @@ -1173,7 +1218,7 @@ void igb_ptp_init(struct igb_adapter *adapter) adapter->ptp_caps.pin_config = adapter->sdp_config; adapter->ptp_caps.adjfine = igb_ptp_adjfine_82580; adapter->ptp_caps.adjtime = igb_ptp_adjtime_i210; - adapter->ptp_caps.gettime64 = igb_ptp_gettime_i210; + adapter->ptp_caps.gettimex64 = igb_ptp_gettimex_i210; adapter->ptp_caps.settime64 = igb_ptp_settime_i210; adapter->ptp_caps.enable = igb_ptp_feature_enable_i210; adapter->ptp_caps.verify = igb_ptp_verify_pin; diff --git a/drivers/net/ethernet/intel/igbvf/mbx.c b/drivers/net/ethernet/intel/igbvf/mbx.c index 163e5838f7c2..a3cd7ac48d4b 100644 --- a/drivers/net/ethernet/intel/igbvf/mbx.c +++ b/drivers/net/ethernet/intel/igbvf/mbx.c @@ -241,7 +241,7 @@ static s32 e1000_write_mbx_vf(struct e1000_hw *hw, u32 *msg, u16 size) s32 err; u16 i; - WARN_ON_ONCE(!spin_is_locked(&hw->mbx_lock)); + lockdep_assert_held(&hw->mbx_lock); /* lock the mailbox to prevent pf/vf race condition */ err = e1000_obtain_mbx_lock_vf(hw); @@ -279,7 +279,7 @@ static s32 e1000_read_mbx_vf(struct e1000_hw *hw, u32 *msg, u16 size) s32 err; u16 i; - WARN_ON_ONCE(!spin_is_locked(&hw->mbx_lock)); + lockdep_assert_held(&hw->mbx_lock); /* lock the mailbox to prevent pf/vf race condition */ err = e1000_obtain_mbx_lock_vf(hw); diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 820d49eb41ab..4eab83faec62 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1186,10 +1186,13 @@ static int igbvf_poll(struct napi_struct *napi, int budget) igbvf_clean_rx_irq(adapter, &work_done, budget); - /* If not enough Rx work done, exit the polling mode */ - if (work_done < budget) { - napi_complete_done(napi, work_done); + if (work_done == budget) + return budget; + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) { if (adapter->requested_itr & 3) igbvf_set_itr(adapter); diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index cdf18a5d9e08..b1039dd3dd13 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -5,23 +5,12 @@ #define _IGC_H_ #include <linux/kobject.h> - #include <linux/pci.h> #include <linux/netdevice.h> #include <linux/vmalloc.h> - #include <linux/ethtool.h> - #include <linux/sctp.h> -#define IGC_ERR(args...) pr_err("igc: " args) - -#define PFX "igc: " - -#include <linux/timecounter.h> -#include <linux/net_tstamp.h> -#include <linux/ptp_clock_kernel.h> - #include "igc_hw.h" /* main */ diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c index 832da609d9a7..df40af759542 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.c +++ b/drivers/net/ethernet/intel/igc/igc_base.c @@ -237,7 +237,6 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw) { struct igc_phy_info *phy = &hw->phy; s32 ret_val = 0; - u32 ctrl_ext; if (hw->phy.media_type != igc_media_type_copper) { phy->type = igc_phy_none; @@ -247,8 +246,6 @@ static s32 igc_init_phy_params_base(struct igc_hw *hw) phy->autoneg_mask = AUTONEG_ADVERTISE_SPEED_DEFAULT_2500; phy->reset_delay_us = 100; - ctrl_ext = rd32(IGC_CTRL_EXT); - /* set lan id */ hw->bus.func = (rd32(IGC_STATUS) & IGC_STATUS_FUNC_MASK) >> IGC_STATUS_FUNC_SHIFT; @@ -287,8 +284,6 @@ out: static s32 igc_get_invariants_base(struct igc_hw *hw) { struct igc_mac_info *mac = &hw->mac; - u32 link_mode = 0; - u32 ctrl_ext = 0; s32 ret_val = 0; switch (hw->device_id) { @@ -302,9 +297,6 @@ static s32 igc_get_invariants_base(struct igc_hw *hw) hw->phy.media_type = igc_media_type_copper; - ctrl_ext = rd32(IGC_CTRL_EXT); - link_mode = ctrl_ext & IGC_CTRL_EXT_LINK_MODE_MASK; - /* mac initialization and operations */ ret_val = igc_init_mac_params_base(hw); if (ret_val) diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index 9d85707e8a81..f20183037fb2 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -865,6 +865,8 @@ static int igc_tx_map(struct igc_ring *tx_ring, /* set the timestamp */ first->time_stamp = jiffies; + skb_tx_timestamp(skb); + /* Force memory writes to complete before letting h/w know there * are new descriptors to fetch. (Only applicable for weak-ordered * memory model archs, such as IA-64). @@ -959,8 +961,6 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, first->bytecount = skb->len; first->gso_segs = 1; - skb_tx_timestamp(skb); - /* record initial flags and protocol */ first->tx_flags = tx_flags; first->protocol = protocol; @@ -1108,7 +1108,7 @@ static struct sk_buff *igc_build_skb(struct igc_ring *rx_ring, /* update pointers within the skb to store the data */ skb_reserve(skb, IGC_SKB_PAD); - __skb_put(skb, size); + __skb_put(skb, size); /* update buffer offset */ #if (PAGE_SIZE < 8192) @@ -1160,9 +1160,9 @@ static struct sk_buff *igc_construct_skb(struct igc_ring *rx_ring, (va + headlen) - page_address(rx_buffer->page), size, truesize); #if (PAGE_SIZE < 8192) - rx_buffer->page_offset ^= truesize; + rx_buffer->page_offset ^= truesize; #else - rx_buffer->page_offset += truesize; + rx_buffer->page_offset += truesize; #endif } else { rx_buffer->pagecnt_bias++; @@ -1668,8 +1668,8 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) tx_buffer->next_to_watch, jiffies, tx_buffer->next_to_watch->wb.status); - netif_stop_subqueue(tx_ring->netdev, - tx_ring->queue_index); + netif_stop_subqueue(tx_ring->netdev, + tx_ring->queue_index); /* we are about to reset, no point in enabling stuff */ return true; @@ -1700,20 +1700,6 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget) } /** - * igc_ioctl - I/O control method - * @netdev: network interface device structure - * @ifreq: frequency - * @cmd: command - */ -static int igc_ioctl(struct net_device *netdev, struct ifreq *ifr, int cmd) -{ - switch (cmd) { - default: - return -EOPNOTSUPP; - } -} - -/** * igc_up - Open the interface and prepare it to handle traffic * @adapter: board private structure */ @@ -2866,11 +2852,13 @@ static int igc_poll(struct napi_struct *napi, int budget) if (!clean_complete) return budget; - /* If not enough Rx work done, exit the polling mode */ - napi_complete_done(napi, work_done); - igc_ring_irq_enable(q_vector); + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) + igc_ring_irq_enable(q_vector); - return 0; + return min(work_done, budget - 1); } /** @@ -3358,7 +3346,7 @@ static int __igc_open(struct net_device *netdev, bool resuming) goto err_req_irq; /* Notify the stack of the actual queue counts. */ - netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); + err = netif_set_real_num_tx_queues(netdev, adapter->num_tx_queues); if (err) goto err_set_queues; @@ -3445,7 +3433,6 @@ static const struct net_device_ops igc_netdev_ops = { .ndo_set_mac_address = igc_set_mac, .ndo_change_mtu = igc_change_mtu, .ndo_get_stats = igc_get_stats, - .ndo_do_ioctl = igc_ioctl, }; /* PCIe configuration access */ @@ -3532,26 +3519,23 @@ static int igc_probe(struct pci_dev *pdev, struct net_device *netdev; struct igc_hw *hw; const struct igc_info *ei = igc_info_tbl[ent->driver_data]; - int err, pci_using_dac; + int err; err = pci_enable_device_mem(pdev); if (err) return err; - pci_using_dac = 0; err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(64)); if (!err) { err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64)); - if (!err) - pci_using_dac = 1; } else { err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err) { err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32)); if (err) { - IGC_ERR("Wrong DMA configuration, aborting\n"); + dev_err(&pdev->dev, "igc: Wrong DMA config\n"); goto err_dma; } } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 143bdd5ee2a0..08d85e336bd4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -12,6 +12,7 @@ #include <linux/aer.h> #include <linux/if_vlan.h> #include <linux/jiffies.h> +#include <linux/phy.h> #include <linux/timecounter.h> #include <linux/net_tstamp.h> @@ -561,6 +562,7 @@ struct ixgbe_adapter { struct net_device *netdev; struct bpf_prog *xdp_prog; struct pci_dev *pdev; + struct mii_bus *mii_bus; unsigned long state; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 732b1e6ecc43..acba067cc15a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -2206,7 +2206,8 @@ static int ixgbe_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) { struct ixgbe_adapter *adapter = netdev_priv(netdev); - if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE)) + if (wol->wolopts & (WAKE_PHY | WAKE_ARP | WAKE_MAGICSECURE | + WAKE_FILTER)) return -EOPNOTSUPP; if (ixgbe_wol_exclusion(adapter, wol)) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index fd1b0546fd67..ff85ce5791a3 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -4,6 +4,7 @@ #include "ixgbe.h" #include <net/xfrm.h> #include <crypto/aead.h> +#include <linux/if_bridge.h> #define IXGBE_IPSEC_KEY_BITS 160 static const char aes_gcm_name[] = "rfc4106(gcm(aes))"; @@ -693,7 +694,8 @@ static int ixgbe_ipsec_add_sa(struct xfrm_state *xs) } else { struct tx_sa tsa; - if (adapter->num_vfs) + if (adapter->num_vfs && + adapter->bridge_mode != BRIDGE_MODE_VEPA) return -EOPNOTSUPP; /* find the first unused index */ @@ -1063,11 +1065,13 @@ int ixgbe_ipsec_tx(struct ixgbe_ring *tx_ring, struct ixgbe_adapter *adapter = netdev_priv(tx_ring->netdev); struct ixgbe_ipsec *ipsec = adapter->ipsec; struct xfrm_state *xs; + struct sec_path *sp; struct tx_sa *tsa; - if (unlikely(!first->skb->sp->len)) { + sp = skb_sec_path(first->skb); + if (unlikely(!sp->len)) { netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n", - __func__, first->skb->sp->len); + __func__, sp->len); return 0; } @@ -1157,6 +1161,7 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring, struct xfrm_state *xs = NULL; struct ipv6hdr *ip6 = NULL; struct iphdr *ip4 = NULL; + struct sec_path *sp; void *daddr; __be32 spi; u8 *c_hdr; @@ -1196,12 +1201,12 @@ void ixgbe_ipsec_rx(struct ixgbe_ring *rx_ring, if (unlikely(!xs)) return; - skb->sp = secpath_dup(skb->sp); - if (unlikely(!skb->sp)) + sp = secpath_set(skb); + if (unlikely(!sp)) return; - skb->sp->xvec[skb->sp->len++] = xs; - skb->sp->olen++; + sp->xvec[sp->len++] = xs; + sp->olen++; xo = xfrm_offload(skb); xo->flags = CRYPTO_DONE; xo->status = CRYPTO_SUCCESS; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 113b38e0defb..daff8183534b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -39,6 +39,7 @@ #include "ixgbe.h" #include "ixgbe_common.h" #include "ixgbe_dcb_82599.h" +#include "ixgbe_phy.h" #include "ixgbe_sriov.h" #include "ixgbe_model.h" #include "ixgbe_txrx_common.h" @@ -6077,9 +6078,9 @@ void ixgbe_down(struct ixgbe_adapter *adapter) /* Disable Rx */ ixgbe_disable_rx(adapter); - /* synchronize_sched() needed for pending XDP buffers to drain */ + /* synchronize_rcu() needed for pending XDP buffers to drain */ if (adapter->xdp_ring[0]) - synchronize_sched(); + synchronize_rcu(); ixgbe_irq_disable(adapter); @@ -8269,6 +8270,8 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring, /* set the timestamp */ first->time_stamp = jiffies; + skb_tx_timestamp(skb); + /* * Force memory writes to complete before letting h/w know there * are new descriptors to fetch. (Only applicable for weak-ordered @@ -8646,8 +8649,6 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, } } - skb_tx_timestamp(skb); - #ifdef CONFIG_PCI_IOV /* * Use the l2switch_enable flag - would be false if the DMA @@ -8695,7 +8696,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, #endif /* IXGBE_FCOE */ #ifdef CONFIG_IXGBE_IPSEC - if (skb->sp && !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx)) + if (secpath_exists(skb) && + !ixgbe_ipsec_tx(tx_ring, first, &ipsec_tx)) goto out_drop; #endif tso = ixgbe_tso(tx_ring, first, &hdr_len, &ipsec_tx); @@ -8789,6 +8791,15 @@ ixgbe_mdio_read(struct net_device *netdev, int prtad, int devad, u16 addr) u16 value; int rc; + if (adapter->mii_bus) { + int regnum = addr; + + if (devad != MDIO_DEVAD_NONE) + regnum |= (devad << 16) | MII_ADDR_C45; + + return mdiobus_read(adapter->mii_bus, prtad, regnum); + } + if (prtad != hw->phy.mdio.prtad) return -EINVAL; rc = hw->phy.ops.read_reg(hw, addr, devad, &value); @@ -8803,6 +8814,15 @@ static int ixgbe_mdio_write(struct net_device *netdev, int prtad, int devad, struct ixgbe_adapter *adapter = netdev_priv(netdev); struct ixgbe_hw *hw = &adapter->hw; + if (adapter->mii_bus) { + int regnum = addr; + + if (devad != MDIO_DEVAD_NONE) + regnum |= (devad << 16) | MII_ADDR_C45; + + return mdiobus_write(adapter->mii_bus, prtad, regnum, value); + } + if (prtad != hw->phy.mdio.prtad) return -EINVAL; return hw->phy.ops.write_reg(hw, addr, devad, value); @@ -9979,7 +9999,8 @@ static int ixgbe_configure_bridge_mode(struct ixgbe_adapter *adapter, } static int ixgbe_ndo_bridge_setlink(struct net_device *dev, - struct nlmsghdr *nlh, u16 flags) + struct nlmsghdr *nlh, u16 flags, + struct netlink_ext_ack *extack) { struct ixgbe_adapter *adapter = netdev_priv(dev); struct nlattr *attr, *br_spec; @@ -10191,7 +10212,7 @@ ixgbe_features_check(struct sk_buff *skb, struct net_device *dev, */ if (skb->encapsulation && !(features & NETIF_F_TSO_MANGLEID)) { #ifdef CONFIG_IXGBE_IPSEC - if (!skb->sp) + if (!secpath_exists(skb)) #endif features &= ~NETIF_F_TSO; } @@ -10476,7 +10497,7 @@ void ixgbe_txrx_ring_disable(struct ixgbe_adapter *adapter, int ring) ixgbe_disable_rxr_hw(adapter, rx_ring); if (xdp_ring) - synchronize_sched(); + synchronize_rcu(); /* Rx/Tx/XDP Tx share the same napi context. */ napi_disable(&rx_ring->q_vector->napi); @@ -10517,7 +10538,8 @@ void ixgbe_txrx_ring_enable(struct ixgbe_adapter *adapter, int ring) ixgbe_configure_rx_ring(adapter, rx_ring); clear_bit(__IXGBE_TX_DISABLED, &tx_ring->state); - clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state); + if (xdp_ring) + clear_bit(__IXGBE_TX_DISABLED, &xdp_ring->state); } /** @@ -11119,6 +11141,8 @@ skip_sriov: IXGBE_LINK_SPEED_10GB_FULL | IXGBE_LINK_SPEED_1GB_FULL, true); + ixgbe_mii_bus_init(hw); + return 0; err_register: @@ -11169,6 +11193,8 @@ static void ixgbe_remove(struct pci_dev *pdev) set_bit(__IXGBE_REMOVING, &adapter->state); cancel_work_sync(&adapter->service_task); + if (adapter->mii_bus) + mdiobus_unregister(adapter->mii_bus); #ifdef CONFIG_IXGBE_DCA if (adapter->flags & IXGBE_FLAG_DCA_ENABLED) { diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 919a7af84b42..cc4907f9ff02 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -3,6 +3,7 @@ #include <linux/pci.h> #include <linux/delay.h> +#include <linux/iopoll.h> #include <linux/sched.h> #include "ixgbe.h" @@ -658,6 +659,304 @@ s32 ixgbe_write_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, return status; } +#define IXGBE_HW_READ_REG(addr) IXGBE_READ_REG(hw, addr) + +/** + * ixgbe_msca_cmd - Write the command register and poll for completion/timeout + * @hw: pointer to hardware structure + * @cmd: command register value to write + **/ +static s32 ixgbe_msca_cmd(struct ixgbe_hw *hw, u32 cmd) +{ + IXGBE_WRITE_REG(hw, IXGBE_MSCA, cmd); + + return readx_poll_timeout(IXGBE_HW_READ_REG, IXGBE_MSCA, cmd, + !(cmd & IXGBE_MSCA_MDI_COMMAND), 10, + 10 * IXGBE_MDIO_COMMAND_TIMEOUT); +} + +/** + * ixgbe_mii_bus_read_generic - Read a clause 22/45 register with gssr flags + * @hw: pointer to hardware structure + * @addr: address + * @regnum: register number + * @gssr: semaphore flags to acquire + **/ +static s32 ixgbe_mii_bus_read_generic(struct ixgbe_hw *hw, int addr, + int regnum, u32 gssr) +{ + u32 hwaddr, cmd; + s32 data; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr)) + return -EBUSY; + + hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT; + if (regnum & MII_ADDR_C45) { + hwaddr |= regnum & GENMASK(21, 0); + cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND; + } else { + hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT; + cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL | + IXGBE_MSCA_READ_AUTOINC | IXGBE_MSCA_MDI_COMMAND; + } + + data = ixgbe_msca_cmd(hw, cmd); + if (data < 0) + goto mii_bus_read_done; + + /* For a clause 45 access the address cycle just completed, we still + * need to do the read command, otherwise just get the data + */ + if (!(regnum & MII_ADDR_C45)) + goto do_mii_bus_read; + + cmd = hwaddr | IXGBE_MSCA_READ | IXGBE_MSCA_MDI_COMMAND; + data = ixgbe_msca_cmd(hw, cmd); + if (data < 0) + goto mii_bus_read_done; + +do_mii_bus_read: + data = IXGBE_READ_REG(hw, IXGBE_MSRWD); + data = (data >> IXGBE_MSRWD_READ_DATA_SHIFT) & GENMASK(16, 0); + +mii_bus_read_done: + hw->mac.ops.release_swfw_sync(hw, gssr); + return data; +} + +/** + * ixgbe_mii_bus_write_generic - Write a clause 22/45 register with gssr flags + * @hw: pointer to hardware structure + * @addr: address + * @regnum: register number + * @val: value to write + * @gssr: semaphore flags to acquire + **/ +static s32 ixgbe_mii_bus_write_generic(struct ixgbe_hw *hw, int addr, + int regnum, u16 val, u32 gssr) +{ + u32 hwaddr, cmd; + s32 err; + + if (hw->mac.ops.acquire_swfw_sync(hw, gssr)) + return -EBUSY; + + IXGBE_WRITE_REG(hw, IXGBE_MSRWD, (u32)val); + + hwaddr = addr << IXGBE_MSCA_PHY_ADDR_SHIFT; + if (regnum & MII_ADDR_C45) { + hwaddr |= regnum & GENMASK(21, 0); + cmd = hwaddr | IXGBE_MSCA_ADDR_CYCLE | IXGBE_MSCA_MDI_COMMAND; + } else { + hwaddr |= (regnum & GENMASK(5, 0)) << IXGBE_MSCA_DEV_TYPE_SHIFT; + cmd = hwaddr | IXGBE_MSCA_OLD_PROTOCOL | IXGBE_MSCA_WRITE | + IXGBE_MSCA_MDI_COMMAND; + } + + /* For clause 45 this is an address cycle, for clause 22 this is the + * entire transaction + */ + err = ixgbe_msca_cmd(hw, cmd); + if (err < 0 || !(regnum & MII_ADDR_C45)) + goto mii_bus_write_done; + + cmd = hwaddr | IXGBE_MSCA_WRITE | IXGBE_MSCA_MDI_COMMAND; + err = ixgbe_msca_cmd(hw, cmd); + +mii_bus_write_done: + hw->mac.ops.release_swfw_sync(hw, gssr); + return err; +} + +/** + * ixgbe_mii_bus_read - Read a clause 22/45 register + * @hw: pointer to hardware structure + * @addr: address + * @regnum: register number + **/ +static s32 ixgbe_mii_bus_read(struct mii_bus *bus, int addr, int regnum) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr); +} + +/** + * ixgbe_mii_bus_write - Write a clause 22/45 register + * @hw: pointer to hardware structure + * @addr: address + * @regnum: register number + * @val: value to write + **/ +static s32 ixgbe_mii_bus_write(struct mii_bus *bus, int addr, int regnum, + u16 val) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr); +} + +/** + * ixgbe_x550em_a_mii_bus_read - Read a clause 22/45 register on x550em_a + * @hw: pointer to hardware structure + * @addr: address + * @regnum: register number + **/ +static s32 ixgbe_x550em_a_mii_bus_read(struct mii_bus *bus, int addr, + int regnum) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM; + return ixgbe_mii_bus_read_generic(hw, addr, regnum, gssr); +} + +/** + * ixgbe_x550em_a_mii_bus_write - Write a clause 22/45 register on x550em_a + * @hw: pointer to hardware structure + * @addr: address + * @regnum: register number + * @val: value to write + **/ +static s32 ixgbe_x550em_a_mii_bus_write(struct mii_bus *bus, int addr, + int regnum, u16 val) +{ + struct ixgbe_adapter *adapter = bus->priv; + struct ixgbe_hw *hw = &adapter->hw; + u32 gssr = hw->phy.phy_semaphore_mask; + + gssr |= IXGBE_GSSR_TOKEN_SM | IXGBE_GSSR_PHY0_SM; + return ixgbe_mii_bus_write_generic(hw, addr, regnum, val, gssr); +} + +/** + * ixgbe_get_first_secondary_devfn - get first device downstream of root port + * @devfn: PCI_DEVFN of root port on domain 0, bus 0 + * + * Returns pci_dev pointer to PCI_DEVFN(0, 0) on subordinate side of root + * on domain 0, bus 0, devfn = 'devfn' + **/ +static struct pci_dev *ixgbe_get_first_secondary_devfn(unsigned int devfn) +{ + struct pci_dev *rp_pdev; + int bus; + + rp_pdev = pci_get_domain_bus_and_slot(0, 0, devfn); + if (rp_pdev && rp_pdev->subordinate) { + bus = rp_pdev->subordinate->number; + return pci_get_domain_bus_and_slot(0, bus, 0); + } + + return NULL; +} + +/** + * ixgbe_x550em_a_has_mii - is this the first ixgbe x550em_a PCI function? + * @hw: pointer to hardware structure + * + * Returns true if hw points to lowest numbered PCI B:D.F x550_em_a device in + * the SoC. There are up to 4 MACs sharing a single MDIO bus on the x550em_a, + * but we only want to register one MDIO bus. + **/ +static bool ixgbe_x550em_a_has_mii(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + struct pci_dev *pdev = adapter->pdev; + struct pci_dev *func0_pdev; + + /* For the C3000 family of SoCs (x550em_a) the internal ixgbe devices + * are always downstream of root ports @ 0000:00:16.0 & 0000:00:17.0 + * It's not valid for function 0 to be disabled and function 1 is up, + * so the lowest numbered ixgbe dev will be device 0 function 0 on one + * of those two root ports + */ + func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x16, 0)); + if (func0_pdev) { + if (func0_pdev == pdev) + return true; + else + return false; + } + func0_pdev = ixgbe_get_first_secondary_devfn(PCI_DEVFN(0x17, 0)); + if (func0_pdev == pdev) + return true; + + return false; +} + +/** + * ixgbe_mii_bus_init - mii_bus structure setup + * @hw: pointer to hardware structure + * + * Returns 0 on success, negative on failure + * + * ixgbe_mii_bus_init initializes a mii_bus structure in adapter + **/ +s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw) +{ + struct ixgbe_adapter *adapter = hw->back; + struct pci_dev *pdev = adapter->pdev; + struct device *dev = &adapter->netdev->dev; + struct mii_bus *bus; + + adapter->mii_bus = devm_mdiobus_alloc(dev); + if (!adapter->mii_bus) + return -ENOMEM; + + bus = adapter->mii_bus; + + switch (hw->device_id) { + /* C3000 SoCs */ + case IXGBE_DEV_ID_X550EM_A_KR: + case IXGBE_DEV_ID_X550EM_A_KR_L: + case IXGBE_DEV_ID_X550EM_A_SFP_N: + case IXGBE_DEV_ID_X550EM_A_SGMII: + case IXGBE_DEV_ID_X550EM_A_SGMII_L: + case IXGBE_DEV_ID_X550EM_A_10G_T: + case IXGBE_DEV_ID_X550EM_A_SFP: + case IXGBE_DEV_ID_X550EM_A_1G_T: + case IXGBE_DEV_ID_X550EM_A_1G_T_L: + if (!ixgbe_x550em_a_has_mii(hw)) + goto ixgbe_no_mii_bus; + bus->read = &ixgbe_x550em_a_mii_bus_read; + bus->write = &ixgbe_x550em_a_mii_bus_write; + break; + default: + bus->read = &ixgbe_mii_bus_read; + bus->write = &ixgbe_mii_bus_write; + break; + } + + /* Use the position of the device in the PCI hierarchy as the id */ + snprintf(bus->id, MII_BUS_ID_SIZE, "%s-mdio-%s", ixgbe_driver_name, + pci_name(pdev)); + + bus->name = "ixgbe-mdio"; + bus->priv = adapter; + bus->parent = dev; + bus->phy_mask = GENMASK(31, 0); + + /* Support clause 22/45 natively. ixgbe_probe() sets MDIO_EMULATE_C22 + * unfortunately that causes some clause 22 frames to be sent with + * clause 45 addressing. We don't want that. + */ + hw->phy.mdio.mode_support = MDIO_SUPPORTS_C45 | MDIO_SUPPORTS_C22; + + return mdiobus_register(bus); + +ixgbe_no_mii_bus: + devm_mdiobus_free(dev, bus); + adapter->mii_bus = NULL; + return -ENODEV; +} + /** * ixgbe_setup_phy_link_generic - Set and restart autoneg * @hw: pointer to hardware structure diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index 64e44e01c973..214b01085718 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -120,6 +120,8 @@ /* SFP+ SFF-8472 Compliance code */ #define IXGBE_SFF_SFF_8472_UNSUP 0x00 +s32 ixgbe_mii_bus_init(struct ixgbe_hw *hw); + s32 ixgbe_identify_phy_generic(struct ixgbe_hw *hw); s32 ixgbe_reset_phy_generic(struct ixgbe_hw *hw); s32 ixgbe_read_phy_reg_generic(struct ixgbe_hw *hw, u32 reg_addr, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index b3e0d8bb5cbd..d81a50dc9535 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -443,22 +443,52 @@ static int ixgbe_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) } /** - * ixgbe_ptp_gettime + * ixgbe_ptp_gettimex * @ptp: the ptp clock structure - * @ts: timespec structure to hold the current time value + * @ts: timespec to hold the PHC timestamp + * @sts: structure to hold the system time before and after reading the PHC * * read the timecounter and return the correct value on ns, * after converting it into a struct timespec. */ -static int ixgbe_ptp_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) +static int ixgbe_ptp_gettimex(struct ptp_clock_info *ptp, + struct timespec64 *ts, + struct ptp_system_timestamp *sts) { struct ixgbe_adapter *adapter = container_of(ptp, struct ixgbe_adapter, ptp_caps); + struct ixgbe_hw *hw = &adapter->hw; unsigned long flags; - u64 ns; + u64 ns, stamp; spin_lock_irqsave(&adapter->tmreg_lock, flags); - ns = timecounter_read(&adapter->hw_tc); + + switch (adapter->hw.mac.type) { + case ixgbe_mac_X550: + case ixgbe_mac_X550EM_x: + case ixgbe_mac_x550em_a: + /* Upper 32 bits represent billions of cycles, lower 32 bits + * represent cycles. However, we use timespec64_to_ns for the + * correct math even though the units haven't been corrected + * yet. + */ + ptp_read_system_prets(sts); + IXGBE_READ_REG(hw, IXGBE_SYSTIMR); + ptp_read_system_postts(sts); + ts->tv_nsec = IXGBE_READ_REG(hw, IXGBE_SYSTIML); + ts->tv_sec = IXGBE_READ_REG(hw, IXGBE_SYSTIMH); + stamp = timespec64_to_ns(ts); + break; + default: + ptp_read_system_prets(sts); + stamp = IXGBE_READ_REG(hw, IXGBE_SYSTIML); + ptp_read_system_postts(sts); + stamp |= (u64)IXGBE_READ_REG(hw, IXGBE_SYSTIMH) << 32; + break; + } + + ns = timecounter_cyc2time(&adapter->hw_tc, stamp); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); *ts = ns_to_timespec64(ns); @@ -567,10 +597,14 @@ void ixgbe_ptp_overflow_check(struct ixgbe_adapter *adapter) { bool timeout = time_is_before_jiffies(adapter->last_overflow_check + IXGBE_OVERFLOW_PERIOD); - struct timespec64 ts; + unsigned long flags; if (timeout) { - ixgbe_ptp_gettime(&adapter->ptp_caps, &ts); + /* Update the timecounter */ + spin_lock_irqsave(&adapter->tmreg_lock, flags); + timecounter_read(&adapter->hw_tc); + spin_unlock_irqrestore(&adapter->tmreg_lock, flags); + adapter->last_overflow_check = jiffies; } } @@ -1216,7 +1250,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter) adapter->ptp_caps.pps = 1; adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_82599; adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime; - adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime; + adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex; adapter->ptp_caps.settime64 = ixgbe_ptp_settime; adapter->ptp_caps.enable = ixgbe_ptp_feature_enable; adapter->ptp_setup_sdp = ixgbe_ptp_setup_sdp_x540; @@ -1233,7 +1267,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter) adapter->ptp_caps.pps = 0; adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_82599; adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime; - adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime; + adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex; adapter->ptp_caps.settime64 = ixgbe_ptp_settime; adapter->ptp_caps.enable = ixgbe_ptp_feature_enable; break; @@ -1249,7 +1283,7 @@ static long ixgbe_ptp_create_clock(struct ixgbe_adapter *adapter) adapter->ptp_caps.pps = 0; adapter->ptp_caps.adjfreq = ixgbe_ptp_adjfreq_X550; adapter->ptp_caps.adjtime = ixgbe_ptp_adjtime; - adapter->ptp_caps.gettime64 = ixgbe_ptp_gettime; + adapter->ptp_caps.gettimex64 = ixgbe_ptp_gettimex; adapter->ptp_caps.settime64 = ixgbe_ptp_settime; adapter->ptp_caps.enable = ixgbe_ptp_feature_enable; adapter->ptp_setup_sdp = NULL; diff --git a/drivers/net/ethernet/intel/ixgbevf/ipsec.c b/drivers/net/ethernet/intel/ixgbevf/ipsec.c index e8a3231be0bf..5170dd9d8705 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ipsec.c +++ b/drivers/net/ethernet/intel/ixgbevf/ipsec.c @@ -450,12 +450,14 @@ int ixgbevf_ipsec_tx(struct ixgbevf_ring *tx_ring, struct ixgbevf_adapter *adapter = netdev_priv(tx_ring->netdev); struct ixgbevf_ipsec *ipsec = adapter->ipsec; struct xfrm_state *xs; + struct sec_path *sp; struct tx_sa *tsa; u16 sa_idx; - if (unlikely(!first->skb->sp->len)) { + sp = skb_sec_path(first->skb); + if (unlikely(!sp->len)) { netdev_err(tx_ring->netdev, "%s: no xfrm state len = %d\n", - __func__, first->skb->sp->len); + __func__, sp->len); return 0; } @@ -546,6 +548,7 @@ void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring, struct xfrm_state *xs = NULL; struct ipv6hdr *ip6 = NULL; struct iphdr *ip4 = NULL; + struct sec_path *sp; void *daddr; __be32 spi; u8 *c_hdr; @@ -585,12 +588,12 @@ void ixgbevf_ipsec_rx(struct ixgbevf_ring *rx_ring, if (unlikely(!xs)) return; - skb->sp = secpath_dup(skb->sp); - if (unlikely(!skb->sp)) + sp = secpath_set(skb); + if (unlikely(!sp)) return; - skb->sp->xvec[skb->sp->len++] = xs; - skb->sp->olen++; + sp->xvec[sp->len++] = xs; + sp->olen++; xo = xfrm_offload(skb); xo->flags = CRYPTO_DONE; xo->status = CRYPTO_SUCCESS; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 5e47ede7e832..49e23afa05a2 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1293,16 +1293,20 @@ static int ixgbevf_poll(struct napi_struct *napi, int budget) /* If all work not completed, return budget and keep polling */ if (!clean_complete) return budget; - /* all work done, exit the polling mode */ - napi_complete_done(napi, work_done); - if (adapter->rx_itr_setting == 1) - ixgbevf_set_itr(q_vector); - if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && - !test_bit(__IXGBEVF_REMOVING, &adapter->state)) - ixgbevf_irq_enable_queues(adapter, - BIT(q_vector->v_idx)); - return 0; + /* Exit the polling mode, but don't re-enable interrupts if stack might + * poll us due to busy-polling + */ + if (likely(napi_complete_done(napi, work_done))) { + if (adapter->rx_itr_setting == 1) + ixgbevf_set_itr(q_vector); + if (!test_bit(__IXGBEVF_DOWN, &adapter->state) && + !test_bit(__IXGBEVF_REMOVING, &adapter->state)) + ixgbevf_irq_enable_queues(adapter, + BIT(q_vector->v_idx)); + } + + return min(work_done, budget - 1); } /** @@ -4016,6 +4020,8 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, /* set the timestamp */ first->time_stamp = jiffies; + skb_tx_timestamp(skb); + /* Force memory writes to complete before letting h/w know there * are new descriptors to fetch. (Only applicable for weak-ordered * memory model archs, such as IA-64). @@ -4151,7 +4157,7 @@ static int ixgbevf_xmit_frame_ring(struct sk_buff *skb, first->protocol = vlan_get_protocol(skb); #ifdef CONFIG_IXGBEVF_IPSEC - if (skb->sp && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx)) + if (secpath_exists(skb) && !ixgbevf_ipsec_tx(tx_ring, first, &ipsec_tx)) goto out_drop; #endif tso = ixgbevf_tso(tx_ring, first, &hdr_len, &ipsec_tx); |