diff options
| author |   Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-18 12:34:53 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2019-09-18 12:34:53 -0700 |
| commit | 81160dda9a7aad13c04e78bb2cfd3c4630e3afab (patch) | |
| tree | 4bf79ffa9fc7dc5e2915ff978778c3402c491113 /drivers/net/ethernet | |
| parent | Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6 (diff) | |
| parent | Merge ra.kernel.org:/pub/scm/linux/kernel/git/netdev/net (diff) | |
| download | linux-dev-81160dda9a7aad13c04e78bb2cfd3c4630e3afab.tar.xz linux-dev-81160dda9a7aad13c04e78bb2cfd3c4630e3afab.zip | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next
Pull networking updates from David Miller:
1) Support IPV6 RA Captive Portal Identifier, from Maciej Żenczykowski.
2) Use bio_vec in the networking instead of custom skb_frag_t, from
Matthew Wilcox.
3) Make use of xmit_more in r8169 driver, from Heiner Kallweit.
4) Add devmap_hash to xdp, from Toke Høiland-Jørgensen.
5) Support all variants of 5750X bnxt_en chips, from Michael Chan.
6) More RTNL avoidance work in the core and mlx5 driver, from Vlad
Buslov.
7) Add TCP syn cookies bpf helper, from Petar Penkov.
8) Add 'nettest' to selftests and use it, from David Ahern.
9) Add extack support to drop_monitor, add packet alert mode and
support for HW drops, from Ido Schimmel.
10) Add VLAN offload to stmmac, from Jose Abreu.
11) Lots of devm_platform_ioremap_resource() conversions, from
YueHaibing.
12) Add IONIC driver, from Shannon Nelson.
13) Several kTLS cleanups, from Jakub Kicinski.
* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1930 commits)
mlxsw: spectrum_buffers: Add the ability to query the CPU port's shared buffer
mlxsw: spectrum: Register CPU port with devlink
mlxsw: spectrum_buffers: Prevent changing CPU port's configuration
net: ena: fix incorrect update of intr_delay_resolution
net: ena: fix retrieval of nonadaptive interrupt moderation intervals
net: ena: fix update of interrupt moderation register
net: ena: remove all old adaptive rx interrupt moderation code from ena_com
net: ena: remove ena_restore_ethtool_params() and relevant fields
net: ena: remove old adaptive interrupt moderation code from ena_netdev
net: ena: remove code duplication in ena_com_update_nonadaptive_moderation_interval _*()
net: ena: enable the interrupt_moderation in driver_supported_features
net: ena: reimplement set/get_coalesce()
net: ena: switch to dim algorithm for rx adaptive interrupt moderation
net: ena: add intr_moder_rx_interval to struct ena_com_dev and use it
net: phy: adin: implement Energy Detect Powerdown mode via phy-tunable
ethtool: implement Energy Detect Powerdown support via phy-tunable
xen-netfront: do not assume sk_buff_head list is empty in error handling
s390/ctcm: Delete unnecessary checks before the macro call “dev_kfree_skb”
net: ena: don't wake up tx queue when down
drop_monitor: Better sanitize notified packets
...
Diffstat (limited to 'drivers/net/ethernet')
487 files changed, 48230 insertions, 21091 deletions
diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 147051404194..8785c2ff3825 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -847,8 +847,7 @@ static void poll_vortex(struct net_device *dev) static int vortex_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *ndev = pci_get_drvdata(pdev); + struct net_device *ndev = dev_get_drvdata(dev); if (!ndev || !netif_running(ndev)) return 0; @@ -861,8 +860,7 @@ static int vortex_suspend(struct device *dev) static int vortex_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *ndev = pci_get_drvdata(pdev); + struct net_device *ndev = dev_get_drvdata(dev); int err; if (!ndev || !netif_running(ndev)) @@ -2175,7 +2173,7 @@ boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev) dma_addr = skb_frag_dma_map(vp->gendev, frag, 0, - frag->size, + skb_frag_size(frag), DMA_TO_DEVICE); if (dma_mapping_error(vp->gendev, dma_addr)) { for(i = i-1; i >= 0; i--) diff --git a/drivers/net/ethernet/Kconfig b/drivers/net/ethernet/Kconfig index dc9dee55976b..1e2de9d062bf 100644 --- a/drivers/net/ethernet/Kconfig +++ b/drivers/net/ethernet/Kconfig @@ -167,6 +167,7 @@ config ETHOC source "drivers/net/ethernet/packetengines/Kconfig" source "drivers/net/ethernet/pasemi/Kconfig" +source "drivers/net/ethernet/pensando/Kconfig" source "drivers/net/ethernet/qlogic/Kconfig" source "drivers/net/ethernet/qualcomm/Kconfig" source "drivers/net/ethernet/rdc/Kconfig" diff --git a/drivers/net/ethernet/Makefile b/drivers/net/ethernet/Makefile index 4bc3c95562bf..77f9838a76c9 100644 --- a/drivers/net/ethernet/Makefile +++ b/drivers/net/ethernet/Makefile @@ -96,3 +96,4 @@ obj-$(CONFIG_NET_VENDOR_WIZNET) += wiznet/ obj-$(CONFIG_NET_VENDOR_XILINX) += xilinx/ obj-$(CONFIG_NET_VENDOR_XIRCOM) += xircom/ obj-$(CONFIG_NET_VENDOR_SYNOPSYS) += synopsys/ +obj-$(CONFIG_NET_VENDOR_PENSANDO) += pensando/ diff --git a/drivers/net/ethernet/aeroflex/greth.c b/drivers/net/ethernet/aeroflex/greth.c index 010a2f48aea5..2a9f8643629c 100644 --- a/drivers/net/ethernet/aeroflex/greth.c +++ b/drivers/net/ethernet/aeroflex/greth.c @@ -110,7 +110,7 @@ static void greth_print_tx_packet(struct sk_buff *skb) print_hex_dump(KERN_DEBUG, "TX: ", DUMP_PREFIX_OFFSET, 16, 1, skb_frag_address(&skb_shinfo(skb)->frags[i]), - skb_shinfo(skb)->frags[i].size, true); + skb_frag_size(&skb_shinfo(skb)->frags[i]), true); } } diff --git a/drivers/net/ethernet/agere/et131x.c b/drivers/net/ethernet/agere/et131x.c index edbb4b3604c7..174344c450af 100644 --- a/drivers/net/ethernet/agere/et131x.c +++ b/drivers/net/ethernet/agere/et131x.c @@ -2426,7 +2426,7 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb) u32 thiscopy, remainder; struct sk_buff *skb = tcb->skb; u32 nr_frags = skb_shinfo(skb)->nr_frags + 1; - struct skb_frag_struct *frags = &skb_shinfo(skb)->frags[0]; + skb_frag_t *frags = &skb_shinfo(skb)->frags[0]; struct phy_device *phydev = adapter->netdev->phydev; dma_addr_t dma_addr; struct tx_ring *tx_ring = &adapter->tx_ring; @@ -2488,11 +2488,11 @@ static int nic_send_packet(struct et131x_adapter *adapter, struct tcb *tcb) frag++; } } else { - desc[frag].len_vlan = frags[i - 1].size; + desc[frag].len_vlan = skb_frag_size(&frags[i - 1]); dma_addr = skb_frag_dma_map(&adapter->pdev->dev, &frags[i - 1], 0, - frags[i - 1].size, + desc[frag].len_vlan, DMA_TO_DEVICE); desc[frag].addr_lo = lower_32_bits(dma_addr); desc[frag].addr_hi = upper_32_bits(dma_addr); diff --git a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h index d19f2ecf8e84..8baf847e8622 100644 --- a/drivers/net/ethernet/amazon/ena/ena_admin_defs.h +++ b/drivers/net/ethernet/amazon/ena/ena_admin_defs.h @@ -808,6 +808,12 @@ struct ena_admin_host_info { u16 num_cpus; u16 reserved; + + /* 1 :0 : reserved + * 2 : interrupt_moderation + * 31:3 : reserved + */ + u32 driver_supported_features; }; struct ena_admin_rss_ind_table_entry { @@ -1110,6 +1116,8 @@ struct ena_admin_ena_mmio_req_read_less_resp { #define ENA_ADMIN_HOST_INFO_DEVICE_MASK GENMASK(7, 3) #define ENA_ADMIN_HOST_INFO_BUS_SHIFT 8 #define ENA_ADMIN_HOST_INFO_BUS_MASK GENMASK(15, 8) +#define ENA_ADMIN_HOST_INFO_INTERRUPT_MODERATION_SHIFT 2 +#define ENA_ADMIN_HOST_INFO_INTERRUPT_MODERATION_MASK BIT(2) /* aenq_common_desc */ #define ENA_ADMIN_AENQ_COMMON_DESC_PHASE_MASK BIT(0) diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c index 911a2e7a375a..ea62604fdf8c 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.c +++ b/drivers/net/ethernet/amazon/ena/ena_com.c @@ -1278,40 +1278,33 @@ static int ena_com_ind_tbl_convert_from_device(struct ena_com_dev *ena_dev) return 0; } -static int ena_com_init_interrupt_moderation_table(struct ena_com_dev *ena_dev) -{ - size_t size; - - size = sizeof(struct ena_intr_moder_entry) * ENA_INTR_MAX_NUM_OF_LEVELS; - - ena_dev->intr_moder_tbl = - devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL); - if (!ena_dev->intr_moder_tbl) - return -ENOMEM; - - ena_com_config_default_interrupt_moderation_table(ena_dev); - - return 0; -} - static void ena_com_update_intr_delay_resolution(struct ena_com_dev *ena_dev, u16 intr_delay_resolution) { - struct ena_intr_moder_entry *intr_moder_tbl = ena_dev->intr_moder_tbl; - unsigned int i; + /* Initial value of intr_delay_resolution might be 0 */ + u16 prev_intr_delay_resolution = + ena_dev->intr_delay_resolution ? + ena_dev->intr_delay_resolution : + ENA_DEFAULT_INTR_DELAY_RESOLUTION; if (!intr_delay_resolution) { pr_err("Illegal intr_delay_resolution provided. Going to use default 1 usec resolution\n"); - intr_delay_resolution = 1; + intr_delay_resolution = ENA_DEFAULT_INTR_DELAY_RESOLUTION; } - ena_dev->intr_delay_resolution = intr_delay_resolution; /* update Rx */ - for (i = 0; i < ENA_INTR_MAX_NUM_OF_LEVELS; i++) - intr_moder_tbl[i].intr_moder_interval /= intr_delay_resolution; + ena_dev->intr_moder_rx_interval = + ena_dev->intr_moder_rx_interval * + prev_intr_delay_resolution / + intr_delay_resolution; /* update Tx */ - ena_dev->intr_moder_tx_interval /= intr_delay_resolution; + ena_dev->intr_moder_tx_interval = + ena_dev->intr_moder_tx_interval * + prev_intr_delay_resolution / + intr_delay_resolution; + + ena_dev->intr_delay_resolution = intr_delay_resolution; } /*****************************************************************************/ @@ -2776,42 +2769,34 @@ bool ena_com_interrupt_moderation_supported(struct ena_com_dev *ena_dev) ENA_ADMIN_INTERRUPT_MODERATION); } -int ena_com_update_nonadaptive_moderation_interval_tx(struct ena_com_dev *ena_dev, - u32 tx_coalesce_usecs) +static int ena_com_update_nonadaptive_moderation_interval(u32 coalesce_usecs, + u32 intr_delay_resolution, + u32 *intr_moder_interval) { - if (!ena_dev->intr_delay_resolution) { + if (!intr_delay_resolution) { pr_err("Illegal interrupt delay granularity value\n"); return -EFAULT; } - ena_dev->intr_moder_tx_interval = tx_coalesce_usecs / - ena_dev->intr_delay_resolution; + *intr_moder_interval = coalesce_usecs / intr_delay_resolution; return 0; } -int ena_com_update_nonadaptive_moderation_interval_rx(struct ena_com_dev *ena_dev, - u32 rx_coalesce_usecs) +int ena_com_update_nonadaptive_moderation_interval_tx(struct ena_com_dev *ena_dev, + u32 tx_coalesce_usecs) { - if (!ena_dev->intr_delay_resolution) { - pr_err("Illegal interrupt delay granularity value\n"); - return -EFAULT; - } - - /* We use LOWEST entry of moderation table for storing - * nonadaptive interrupt coalescing values - */ - ena_dev->intr_moder_tbl[ENA_INTR_MODER_LOWEST].intr_moder_interval = - rx_coalesce_usecs / ena_dev->intr_delay_resolution; - - return 0; + return ena_com_update_nonadaptive_moderation_interval(tx_coalesce_usecs, + ena_dev->intr_delay_resolution, + &ena_dev->intr_moder_tx_interval); } -void ena_com_destroy_interrupt_moderation(struct ena_com_dev *ena_dev) +int ena_com_update_nonadaptive_moderation_interval_rx(struct ena_com_dev *ena_dev, + u32 rx_coalesce_usecs) { - if (ena_dev->intr_moder_tbl) - devm_kfree(ena_dev->dmadev, ena_dev->intr_moder_tbl); - ena_dev->intr_moder_tbl = NULL; + return ena_com_update_nonadaptive_moderation_interval(rx_coalesce_usecs, + ena_dev->intr_delay_resolution, + &ena_dev->intr_moder_rx_interval); } int ena_com_init_interrupt_moderation(struct ena_com_dev *ena_dev) @@ -2838,66 +2823,14 @@ int ena_com_init_interrupt_moderation(struct ena_com_dev *ena_dev) return rc; } - rc = ena_com_init_interrupt_moderation_table(ena_dev); - if (rc) - goto err; - /* if moderation is supported by device we set adaptive moderation */ delay_resolution = get_resp.u.intr_moderation.intr_delay_resolution; ena_com_update_intr_delay_resolution(ena_dev, delay_resolution); - /* Disable adaptive moderation by default - can be enabled from - * ethtool - */ + /* Disable adaptive moderation by default - can be enabled later */ ena_com_disable_adaptive_moderation(ena_dev); return 0; -err: - ena_com_destroy_interrupt_moderation(ena_dev); - return rc; -} - -void ena_com_config_default_interrupt_moderation_table(struct ena_com_dev *ena_dev) -{ - struct ena_intr_moder_entry *intr_moder_tbl = ena_dev->intr_moder_tbl; - - if (!intr_moder_tbl) - return; - - intr_moder_tbl[ENA_INTR_MODER_LOWEST].intr_moder_interval = - ENA_INTR_LOWEST_USECS; - intr_moder_tbl[ENA_INTR_MODER_LOWEST].pkts_per_interval = - ENA_INTR_LOWEST_PKTS; - intr_moder_tbl[ENA_INTR_MODER_LOWEST].bytes_per_interval = - ENA_INTR_LOWEST_BYTES; - - intr_moder_tbl[ENA_INTR_MODER_LOW].intr_moder_interval = - ENA_INTR_LOW_USECS; - intr_moder_tbl[ENA_INTR_MODER_LOW].pkts_per_interval = - ENA_INTR_LOW_PKTS; - intr_moder_tbl[ENA_INTR_MODER_LOW].bytes_per_interval = - ENA_INTR_LOW_BYTES; - - intr_moder_tbl[ENA_INTR_MODER_MID].intr_moder_interval = - ENA_INTR_MID_USECS; - intr_moder_tbl[ENA_INTR_MODER_MID].pkts_per_interval = - ENA_INTR_MID_PKTS; - intr_moder_tbl[ENA_INTR_MODER_MID].bytes_per_interval = - ENA_INTR_MID_BYTES; - - intr_moder_tbl[ENA_INTR_MODER_HIGH].intr_moder_interval = - ENA_INTR_HIGH_USECS; - intr_moder_tbl[ENA_INTR_MODER_HIGH].pkts_per_interval = - ENA_INTR_HIGH_PKTS; - intr_moder_tbl[ENA_INTR_MODER_HIGH].bytes_per_interval = - ENA_INTR_HIGH_BYTES; - - intr_moder_tbl[ENA_INTR_MODER_HIGHEST].intr_moder_interval = - ENA_INTR_HIGHEST_USECS; - intr_moder_tbl[ENA_INTR_MODER_HIGHEST].pkts_per_interval = - ENA_INTR_HIGHEST_PKTS; - intr_moder_tbl[ENA_INTR_MODER_HIGHEST].bytes_per_interval = - ENA_INTR_HIGHEST_BYTES; } unsigned int ena_com_get_nonadaptive_moderation_interval_tx(struct ena_com_dev *ena_dev) @@ -2907,49 +2840,7 @@ unsigned int ena_com_get_nonadaptive_moderation_interval_tx(struct ena_com_dev * unsigned int ena_com_get_nonadaptive_moderation_interval_rx(struct ena_com_dev *ena_dev) { - struct ena_intr_moder_entry *intr_moder_tbl = ena_dev->intr_moder_tbl; - - if (intr_moder_tbl) - return intr_moder_tbl[ENA_INTR_MODER_LOWEST].intr_moder_interval; - - return 0; -} - -void ena_com_init_intr_moderation_entry(struct ena_com_dev *ena_dev, - enum ena_intr_moder_level level, - struct ena_intr_moder_entry *entry) -{ - struct ena_intr_moder_entry *intr_moder_tbl = ena_dev->intr_moder_tbl; - - if (level >= ENA_INTR_MAX_NUM_OF_LEVELS) - return; - - intr_moder_tbl[level].intr_moder_interval = entry->intr_moder_interval; - if (ena_dev->intr_delay_resolution) - intr_moder_tbl[level].intr_moder_interval /= - ena_dev->intr_delay_resolution; - intr_moder_tbl[level].pkts_per_interval = entry->pkts_per_interval; - - /* use hardcoded value until ethtool supports bytecount parameter */ - if (entry->bytes_per_interval != ENA_INTR_BYTE_COUNT_NOT_SUPPORTED) - intr_moder_tbl[level].bytes_per_interval = entry->bytes_per_interval; -} - -void ena_com_get_intr_moderation_entry(struct ena_com_dev *ena_dev, - enum ena_intr_moder_level level, - struct ena_intr_moder_entry *entry) -{ - struct ena_intr_moder_entry *intr_moder_tbl = ena_dev->intr_moder_tbl; - - if (level >= ENA_INTR_MAX_NUM_OF_LEVELS) - return; - - entry->intr_moder_interval = intr_moder_tbl[level].intr_moder_interval; - if (ena_dev->intr_delay_resolution) - entry->intr_moder_interval *= ena_dev->intr_delay_resolution; - entry->pkts_per_interval = - intr_moder_tbl[level].pkts_per_interval; - entry->bytes_per_interval = intr_moder_tbl[level].bytes_per_interval; + return ena_dev->intr_moder_rx_interval; } int ena_com_config_dev_mode(struct ena_com_dev *ena_dev, diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h index 0d3664fe260d..7c941eba0bc9 100644 --- a/drivers/net/ethernet/amazon/ena/ena_com.h +++ b/drivers/net/ethernet/amazon/ena/ena_com.h @@ -72,46 +72,14 @@ /*****************************************************************************/ /* ENA adaptive interrupt moderation settings */ -#define ENA_INTR_LOWEST_USECS (0) -#define ENA_INTR_LOWEST_PKTS (3) -#define ENA_INTR_LOWEST_BYTES (2 * 1524) - -#define ENA_INTR_LOW_USECS (32) -#define ENA_INTR_LOW_PKTS (12) -#define ENA_INTR_LOW_BYTES (16 * 1024) - -#define ENA_INTR_MID_USECS (80) -#define ENA_INTR_MID_PKTS (48) -#define ENA_INTR_MID_BYTES (64 * 1024) - -#define ENA_INTR_HIGH_USECS (128) -#define ENA_INTR_HIGH_PKTS (96) -#define ENA_INTR_HIGH_BYTES (128 * 1024) - -#define ENA_INTR_HIGHEST_USECS (192) -#define ENA_INTR_HIGHEST_PKTS (128) -#define ENA_INTR_HIGHEST_BYTES (192 * 1024) - #define ENA_INTR_INITIAL_TX_INTERVAL_USECS 196 -#define ENA_INTR_INITIAL_RX_INTERVAL_USECS 4 -#define ENA_INTR_DELAY_OLD_VALUE_WEIGHT 6 -#define ENA_INTR_DELAY_NEW_VALUE_WEIGHT 4 -#define ENA_INTR_MODER_LEVEL_STRIDE 2 -#define ENA_INTR_BYTE_COUNT_NOT_SUPPORTED 0xFFFFFF +#define ENA_INTR_INITIAL_RX_INTERVAL_USECS 0 +#define ENA_DEFAULT_INTR_DELAY_RESOLUTION 1 #define ENA_HW_HINTS_NO_TIMEOUT 0xFFFF #define ENA_FEATURE_MAX_QUEUE_EXT_VER 1 -enum ena_intr_moder_level { - ENA_INTR_MODER_LOWEST = 0, - ENA_INTR_MODER_LOW, - ENA_INTR_MODER_MID, - ENA_INTR_MODER_HIGH, - ENA_INTR_MODER_HIGHEST, - ENA_INTR_MAX_NUM_OF_LEVELS, -}; - struct ena_llq_configurations { enum ena_admin_llq_header_location llq_header_location; enum ena_admin_llq_ring_entry_size llq_ring_entry_size; @@ -120,12 +88,6 @@ struct ena_llq_configurations { u16 llq_ring_entry_size_value; }; -struct ena_intr_moder_entry { - unsigned int intr_moder_interval; - unsigned int pkts_per_interval; - unsigned int bytes_per_interval; -}; - enum queue_direction { ENA_COM_IO_QUEUE_DIRECTION_TX, ENA_COM_IO_QUEUE_DIRECTION_RX @@ -376,7 +338,13 @@ struct ena_com_dev { struct ena_host_attribute host_attr; bool adaptive_coalescing; u16 intr_delay_resolution; + + /* interrupt moderation intervals are in usec divided by + * intr_delay_resolution, which is supplied by the device. + */ u32 intr_moder_tx_interval; + u32 intr_moder_rx_interval; + struct ena_intr_moder_entry *intr_moder_tbl; struct ena_com_llq_info llq_info; @@ -914,11 +882,6 @@ int ena_com_execute_admin_command(struct ena_com_admin_queue *admin_queue, */ int ena_com_init_interrupt_moderation(struct ena_com_dev *ena_dev); -/* ena_com_destroy_interrupt_moderation - Destroy interrupt moderation resources - * @ena_dev: ENA communication layer struct - */ -void ena_com_destroy_interrupt_moderation(struct ena_com_dev *ena_dev); - /* ena_com_interrupt_moderation_supported - Return if interrupt moderation * capability is supported by the device. * @@ -926,12 +889,6 @@ void ena_com_destroy_interrupt_moderation(struct ena_com_dev *ena_dev); */ bool ena_com_interrupt_moderation_supported(struct ena_com_dev *ena_dev); -/* ena_com_config_default_interrupt_moderation_table - Restore the interrupt - * moderation table back to the default parameters. - * @ena_dev: ENA communication layer struct - */ -void ena_com_config_default_interrupt_moderation_table(struct ena_com_dev *ena_dev); - /* ena_com_update_nonadaptive_moderation_interval_tx - Update the * non-adaptive interval in Tx direction. * @ena_dev: ENA communication layer struct @@ -968,29 +925,6 @@ unsigned int ena_com_get_nonadaptive_moderation_interval_tx(struct ena_com_dev * */ unsigned int ena_com_get_nonadaptive_moderation_interval_rx(struct ena_com_dev *ena_dev); -/* ena_com_init_intr_moderation_entry - Update a single entry in the interrupt - * moderation table. - * @ena_dev: ENA communication layer struct - * @level: Interrupt moderation table level - * @entry: Entry value - * - * Update a single entry in the interrupt moderation table. - */ -void ena_com_init_intr_moderation_entry(struct ena_com_dev *ena_dev, - enum ena_intr_moder_level level, - struct ena_intr_moder_entry *entry); - -/* ena_com_get_intr_moderation_entry - Init ena_intr_moder_entry. - * @ena_dev: ENA communication layer struct - * @level: Interrupt moderation table level - * @entry: Entry to fill. - * - * Initialize the entry according to the adaptive interrupt moderation table. - */ -void ena_com_get_intr_moderation_entry(struct ena_com_dev *ena_dev, - enum ena_intr_moder_level level, - struct ena_intr_moder_entry *entry); - /* ena_com_config_dev_mode - Configure the placement policy of the device. * @ena_dev: ENA communication layer struct * @llq_features: LLQ feature descriptor, retrieve via @@ -1016,75 +950,6 @@ static inline void ena_com_disable_adaptive_moderation(struct ena_com_dev *ena_d ena_dev->adaptive_coalescing = false; } -/* ena_com_calculate_interrupt_delay - Calculate new interrupt delay - * @ena_dev: ENA communication layer struct - * @pkts: Number of packets since the last update - * @bytes: Number of bytes received since the last update. - * @smoothed_interval: Returned interval - * @moder_tbl_idx: Current table level as input update new level as return - * value. - */ -static inline void ena_com_calculate_interrupt_delay(struct ena_com_dev *ena_dev, - unsigned int pkts, - unsigned int bytes, - unsigned int *smoothed_interval, - unsigned int *moder_tbl_idx) -{ - enum ena_intr_moder_level curr_moder_idx, new_moder_idx; - struct ena_intr_moder_entry *curr_moder_entry; - struct ena_intr_moder_entry *pred_moder_entry; - struct ena_intr_moder_entry *new_moder_entry; - struct ena_intr_moder_entry *intr_moder_tbl = ena_dev->intr_moder_tbl; - unsigned int interval; - - /* We apply adaptive moderation on Rx path only. - * Tx uses static interrupt moderation. - */ - if (!pkts || !bytes) - /* Tx interrupt, or spurious interrupt, - * in both cases we just use same delay values - */ - return; - - curr_moder_idx = (enum ena_intr_moder_level)(*moder_tbl_idx); - if (unlikely(curr_moder_idx >= ENA_INTR_MAX_NUM_OF_LEVELS)) { - pr_err("Wrong moderation index %u\n", curr_moder_idx); - return; - } - - curr_moder_entry = &intr_moder_tbl[curr_moder_idx]; - new_moder_idx = curr_moder_idx; - - if (curr_moder_idx == ENA_INTR_MODER_LOWEST) { - if ((pkts > curr_moder_entry->pkts_per_interval) || - (bytes > curr_moder_entry->bytes_per_interval)) - new_moder_idx = - (enum ena_intr_moder_level)(curr_moder_idx + ENA_INTR_MODER_LEVEL_STRIDE); - } else { - pred_moder_entry = &intr_moder_tbl[curr_moder_idx - ENA_INTR_MODER_LEVEL_STRIDE]; - - if ((pkts <= pred_moder_entry->pkts_per_interval) || - (bytes <= pred_moder_entry->bytes_per_interval)) - new_moder_idx = - (enum ena_intr_moder_level)(curr_moder_idx - ENA_INTR_MODER_LEVEL_STRIDE); - else if ((pkts > curr_moder_entry->pkts_per_interval) || - (bytes > curr_moder_entry->bytes_per_interval)) { - if (curr_moder_idx != ENA_INTR_MODER_HIGHEST) - new_moder_idx = - (enum ena_intr_moder_level)(curr_moder_idx + ENA_INTR_MODER_LEVEL_STRIDE); - } - } - new_moder_entry = &intr_moder_tbl[new_moder_idx]; - - interval = new_moder_entry->intr_moder_interval; - *smoothed_interval = ( - (interval * ENA_INTR_DELAY_NEW_VALUE_WEIGHT + - ENA_INTR_DELAY_OLD_VALUE_WEIGHT * (*smoothed_interval)) + 5) / - 10; - - *moder_tbl_idx = new_moder_idx; -} - /* ena_com_update_intr_reg - Prepare interrupt register * @intr_reg: interrupt register to update. * @rx_delay_interval: Rx interval in usecs diff --git a/drivers/net/ethernet/amazon/ena/ena_ethtool.c b/drivers/net/ethernet/amazon/ena/ena_ethtool.c index b997c3ce9e2b..16553d92fad2 100644 --- a/drivers/net/ethernet/amazon/ena/ena_ethtool.c +++ b/drivers/net/ethernet/amazon/ena/ena_ethtool.c @@ -305,32 +305,21 @@ static int ena_get_coalesce(struct net_device *net_dev, { struct ena_adapter *adapter = netdev_priv(net_dev); struct ena_com_dev *ena_dev = adapter->ena_dev; - struct ena_intr_moder_entry intr_moder_entry; if (!ena_com_interrupt_moderation_supported(ena_dev)) { /* the devie doesn't support interrupt moderation */ return -EOPNOTSUPP; } + coalesce->tx_coalesce_usecs = - ena_com_get_nonadaptive_moderation_interval_tx(ena_dev) / + ena_com_get_nonadaptive_moderation_interval_tx(ena_dev) * ena_dev->intr_delay_resolution; - if (!ena_com_get_adaptive_moderation_enabled(ena_dev)) { + + if (!ena_com_get_adaptive_moderation_enabled(ena_dev)) coalesce->rx_coalesce_usecs = ena_com_get_nonadaptive_moderation_interval_rx(ena_dev) - / ena_dev->intr_delay_resolution; - } else { - ena_com_get_intr_moderation_entry(adapter->ena_dev, ENA_INTR_MODER_LOWEST, &intr_moder_entry); - coalesce->rx_coalesce_usecs_low = intr_moder_entry.intr_moder_interval; - coalesce->rx_max_coalesced_frames_low = intr_moder_entry.pkts_per_interval; - - ena_com_get_intr_moderation_entry(adapter->ena_dev, ENA_INTR_MODER_MID, &intr_moder_entry); - coalesce->rx_coalesce_usecs = intr_moder_entry.intr_moder_interval; - coalesce->rx_max_coalesced_frames = intr_moder_entry.pkts_per_interval; - - ena_com_get_intr_moderation_entry(adapter->ena_dev, ENA_INTR_MODER_HIGHEST, &intr_moder_entry); - coalesce->rx_coalesce_usecs_high = intr_moder_entry.intr_moder_interval; - coalesce->rx_max_coalesced_frames_high = intr_moder_entry.pkts_per_interval; - } + * ena_dev->intr_delay_resolution; + coalesce->use_adaptive_rx_coalesce = ena_com_get_adaptive_moderation_enabled(ena_dev); @@ -348,12 +337,22 @@ static void ena_update_tx_rings_intr_moderation(struct ena_adapter *adapter) adapter->tx_ring[i].smoothed_interval = val; } +static void ena_update_rx_rings_intr_moderation(struct ena_adapter *adapter) +{ + unsigned int val; + int i; + + val = ena_com_get_nonadaptive_moderation_interval_rx(adapter->ena_dev); + + for (i = 0; i < adapter->num_queues; i++) + adapter->rx_ring[i].smoothed_interval = val; +} + static int ena_set_coalesce(struct net_device *net_dev, struct ethtool_coalesce *coalesce) { struct ena_adapter *adapter = netdev_priv(net_dev); struct ena_com_dev *ena_dev = adapter->ena_dev; - struct ena_intr_moder_entry intr_moder_entry; int rc; if (!ena_com_interrupt_moderation_supported(ena_dev)) { @@ -361,22 +360,6 @@ static int ena_set_coalesce(struct net_device *net_dev, return -EOPNOTSUPP; } - if (coalesce->rx_coalesce_usecs_irq || - coalesce->rx_max_coalesced_frames_irq || - coalesce->tx_coalesce_usecs_irq || - coalesce->tx_max_coalesced_frames || - coalesce->tx_max_coalesced_frames_irq || - coalesce->stats_block_coalesce_usecs || - coalesce->use_adaptive_tx_coalesce || - coalesce->pkt_rate_low || - coalesce->tx_coalesce_usecs_low || - coalesce->tx_max_coalesced_frames_low || - coalesce->pkt_rate_high || - coalesce->tx_coalesce_usecs_high || - coalesce->tx_max_coalesced_frames_high || - coalesce->rate_sample_interval) - return -EINVAL; - rc = ena_com_update_nonadaptive_moderation_interval_tx(ena_dev, coalesce->tx_coalesce_usecs); if (rc) @@ -384,37 +367,23 @@ static int ena_set_coalesce(struct net_device *net_dev, ena_update_tx_rings_intr_moderation(adapter); - if (ena_com_get_adaptive_moderation_enabled(ena_dev)) { - if (!coalesce->use_adaptive_rx_coalesce) { - ena_com_disable_adaptive_moderation(ena_dev); - rc = ena_com_update_nonadaptive_moderation_interval_rx(ena_dev, - coalesce->rx_coalesce_usecs); - return rc; - } - } else { /* was in non-adaptive mode */ - if (coalesce->use_adaptive_rx_coalesce) { + if (coalesce->use_adaptive_rx_coalesce) { + if (!ena_com_get_adaptive_moderation_enabled(ena_dev)) ena_com_enable_adaptive_moderation(ena_dev); - } else { - rc = ena_com_update_nonadaptive_moderation_interval_rx(ena_dev, - coalesce->rx_coalesce_usecs); - return rc; - } + return 0; } - intr_moder_entry.intr_moder_interval = coalesce->rx_coalesce_usecs_low; - intr_moder_entry.pkts_per_interval = coalesce->rx_max_coalesced_frames_low; - intr_moder_entry.bytes_per_interval = ENA_INTR_BYTE_COUNT_NOT_SUPPORTED; - ena_com_init_intr_moderation_entry(adapter->ena_dev, ENA_INTR_MODER_LOWEST, &intr_moder_entry); + rc = ena_com_update_nonadaptive_moderation_interval_rx(ena_dev, + coalesce->rx_coalesce_usecs); + if (rc) + return rc; - intr_moder_entry.intr_moder_interval = coalesce->rx_coalesce_usecs; - intr_moder_entry.pkts_per_interval = coalesce->rx_max_coalesced_frames; - intr_moder_entry.bytes_per_interval = ENA_INTR_BYTE_COUNT_NOT_SUPPORTED; - ena_com_init_intr_moderation_entry(adapter->ena_dev, ENA_INTR_MODER_MID, &intr_moder_entry); + ena_update_rx_rings_intr_moderation(adapter); - intr_moder_entry.intr_moder_interval = coalesce->rx_coalesce_usecs_high; - intr_moder_entry.pkts_per_interval = coalesce->rx_max_coalesced_frames_high; - intr_moder_entry.bytes_per_interval = ENA_INTR_BYTE_COUNT_NOT_SUPPORTED; - ena_com_init_intr_moderation_entry(adapter->ena_dev, ENA_INTR_MODER_HIGHEST, &intr_moder_entry); + if (!coalesce->use_adaptive_rx_coalesce) { + if (ena_com_get_adaptive_moderation_enabled(ena_dev)) + ena_com_disable_adaptive_moderation(ena_dev); + } return 0; } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.c b/drivers/net/ethernet/amazon/ena/ena_netdev.c index 664e3ed97ea9..c487d2a7d6dd 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.c +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.c @@ -158,7 +158,6 @@ static void ena_init_io_rings_common(struct ena_adapter *adapter, ring->adapter = adapter; ring->ena_dev = adapter->ena_dev; ring->per_napi_packets = 0; - ring->per_napi_bytes = 0; ring->cpu = 0; ring->first_interrupt = false; ring->no_interrupt_event_cnt = 0; @@ -196,6 +195,7 @@ static void ena_init_io_rings(struct ena_adapter *adapter) rxr->smoothed_interval = ena_com_get_nonadaptive_moderation_interval_rx(ena_dev); rxr->empty_rx_queue = 0; + adapter->ena_napi[i].dim.mode = DIM_CQ_PERIOD_MODE_START_FROM_EQE; } } @@ -712,6 +712,7 @@ static void ena_destroy_all_rx_queues(struct ena_adapter *adapter) for (i = 0; i < adapter->num_queues; i++) { ena_qid = ENA_IO_RXQ_IDX(i); + cancel_work_sync(&adapter->ena_napi[i].dim.work); ena_com_destroy_io_queue(adapter->ena_dev, ena_qid); } } @@ -823,7 +824,8 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget) above_thresh = ena_com_sq_have_enough_space(tx_ring->ena_com_io_sq, ENA_TX_WAKEUP_THRESH); - if (netif_tx_queue_stopped(txq) && above_thresh) { + if (netif_tx_queue_stopped(txq) && above_thresh && + test_bit(ENA_FLAG_DEV_UP, &tx_ring->adapter->flags)) { netif_tx_wake_queue(txq); u64_stats_update_begin(&tx_ring->syncp); tx_ring->tx_stats.queue_wakeup++; @@ -832,9 +834,6 @@ static int ena_clean_tx_irq(struct ena_ring *tx_ring, u32 budget) __netif_tx_unlock(txq); } - tx_ring->per_napi_bytes += tx_bytes; - tx_ring->per_napi_packets += tx_pkts; - return tx_pkts; } @@ -1118,7 +1117,6 @@ static int ena_clean_rx_irq(struct ena_ring *rx_ring, struct napi_struct *napi, } while (likely(res_budget)); work_done = budget - res_budget; - rx_ring->per_napi_bytes += total_len; rx_ring->per_napi_packets += work_done; u64_stats_update_begin(&rx_ring->syncp); rx_ring->rx_stats.bytes += total_len; @@ -1155,35 +1153,50 @@ error: return 0; } -void ena_adjust_intr_moderation(struct ena_ring *rx_ring, - struct ena_ring *tx_ring) +static void ena_dim_work(struct work_struct *w) { - /* We apply adaptive moderation on Rx path only. - * Tx uses static interrupt moderation. - */ - ena_com_calculate_interrupt_delay(rx_ring->ena_dev, - rx_ring->per_napi_packets, - rx_ring->per_napi_bytes, - &rx_ring->smoothed_interval, - &rx_ring->moder_tbl_idx); - - /* Reset per napi packets/bytes */ - tx_ring->per_napi_packets = 0; - tx_ring->per_napi_bytes = 0; + struct dim *dim = container_of(w, struct dim, work); + struct dim_cq_moder cur_moder = + net_dim_get_rx_moderation(dim->mode, dim->profile_ix); + struct ena_napi *ena_napi = container_of(dim, struct ena_napi, dim); + + ena_napi->rx_ring->smoothed_interval = cur_moder.usec; + dim->state = DIM_START_MEASURE; +} + +static void ena_adjust_adaptive_rx_intr_moderation(struct ena_napi *ena_napi) +{ + struct dim_sample dim_sample; + struct ena_ring *rx_ring = ena_napi->rx_ring; + + if (!rx_ring->per_napi_packets) + return; + + rx_ring->non_empty_napi_events++; + + dim_update_sample(rx_ring->non_empty_napi_events, + rx_ring->rx_stats.cnt, + rx_ring->rx_stats.bytes, + &dim_sample); + + net_dim(&ena_napi->dim, dim_sample); + rx_ring->per_napi_packets = 0; - rx_ring->per_napi_bytes = 0; } static void ena_unmask_interrupt(struct ena_ring *tx_ring, struct ena_ring *rx_ring) { struct ena_eth_io_intr_reg intr_reg; + u32 rx_interval = ena_com_get_adaptive_moderation_enabled(rx_ring->ena_dev) ? + rx_ring->smoothed_interval : + ena_com_get_nonadaptive_moderation_interval_rx(rx_ring->ena_dev); /* Update intr register: rx intr delay, * tx intr delay and interrupt unmask */ ena_com_update_intr_reg(&intr_reg, - rx_ring->smoothed_interval, + rx_interval, tx_ring->smoothed_interval, true); @@ -1260,9 +1273,11 @@ static int ena_io_poll(struct napi_struct *napi, int budget) * from the interrupt context (vs from sk_busy_loop) */ if (napi_complete_done(napi, rx_work_done)) { - /* Tx and Rx share the same interrupt vector */ + /* We apply adaptive moderation on Rx path only. + * Tx uses static interrupt moderation. + */ if (ena_com_get_adaptive_moderation_enabled(rx_ring->ena_dev)) - ena_adjust_intr_moderation(rx_ring, tx_ring); + ena_adjust_adaptive_rx_intr_moderation(ena_napi); ena_unmask_interrupt(tx_ring, rx_ring); } @@ -1552,14 +1567,6 @@ static void ena_napi_enable_all(struct ena_adapter *adapter) napi_enable(&adapter->ena_napi[i].napi); } -static void ena_restore_ethtool_params(struct ena_adapter *adapter) -{ - adapter->tx_usecs = 0; - adapter->rx_usecs = 0; - adapter->tx_frames = 1; - adapter->rx_frames = 1; -} - /* Configure the Rx forwarding */ static int ena_rss_configure(struct ena_adapter *adapter) { @@ -1609,8 +1616,6 @@ static int ena_up_complete(struct ena_adapter *adapter) /* enable transmits */ netif_tx_start_all_queues(adapter->netdev); - ena_restore_ethtool_params(adapter); - ena_napi_enable_all(adapter); return 0; @@ -1740,13 +1745,16 @@ static int ena_create_all_io_rx_queues(struct ena_adapter *adapter) rc = ena_create_io_rx_queue(adapter, i); if (rc) goto create_err; + INIT_WORK(&adapter->ena_napi[i].dim.work, ena_dim_work); } return 0; create_err: - while (i--) + while (i--) { + cancel_work_sync(&adapter->ena_napi[i].dim.work); ena_com_destroy_io_queue(ena_dev, ENA_IO_RXQ_IDX(i)); + } return rc; } @@ -2419,6 +2427,9 @@ static void ena_config_host_info(struct ena_com_dev *ena_dev, ("K"[0] << ENA_ADMIN_HOST_INFO_MODULE_TYPE_SHIFT); host_info->num_cpus = num_online_cpus(); + host_info->driver_supported_features = + ENA_ADMIN_HOST_INFO_INTERRUPT_MODERATION_MASK; + rc = ena_com_set_host_attributes(ena_dev); if (rc) { if (rc == -EOPNOTSUPP) @@ -3485,10 +3496,12 @@ static int ena_probe(struct pci_dev *pdev, const struct pci_device_id *ent) calc_queue_ctx.get_feat_ctx = &get_feat_ctx; calc_queue_ctx.pdev = pdev; - /* initial Tx interrupt delay, Assumes 1 usec granularity. + /* Initial Tx and RX interrupt delay. Assumes 1 usec granularity. * Updated during device initialization with the real granularity */ ena_dev->intr_moder_tx_interval = ENA_INTR_INITIAL_TX_INTERVAL_USECS; + ena_dev->intr_moder_rx_interval = ENA_INTR_INITIAL_RX_INTERVAL_USECS; + ena_dev->intr_delay_resolution = ENA_DEFAULT_INTR_DELAY_RESOLUTION; io_queue_num = ena_calc_io_queue_num(pdev, ena_dev, &get_feat_ctx); rc = ena_calc_queue_size(&calc_queue_ctx); if (rc || io_queue_num <= 0) { @@ -3618,7 +3631,6 @@ err_free_msix: ena_free_mgmnt_irq(adapter); ena_disable_msix(adapter); err_worker_destroy: - ena_com_destroy_interrupt_moderation(ena_dev); del_timer(&adapter->timer_service); err_netdev_destroy: free_netdev(netdev); @@ -3679,8 +3691,6 @@ static void ena_remove(struct pci_dev *pdev) pci_disable_device(pdev); - ena_com_destroy_interrupt_moderation(ena_dev); - vfree(ena_dev); } diff --git a/drivers/net/ethernet/amazon/ena/ena_netdev.h b/drivers/net/ethernet/amazon/ena/ena_netdev.h index efbcffd22215..72ee51a82ec7 100644 --- a/drivers/net/ethernet/amazon/ena/ena_netdev.h +++ b/drivers/net/ethernet/amazon/ena/ena_netdev.h @@ -34,6 +34,7 @@ #define ENA_H #include <linux/bitops.h> +#include <linux/dim.h> #include <linux/etherdevice.h> #include <linux/inetdevice.h> #include <linux/interrupt.h> @@ -153,6 +154,7 @@ struct ena_napi { struct ena_ring *tx_ring; struct ena_ring *rx_ring; u32 qid; + struct dim dim; }; struct ena_calc_queue_size_ctx { @@ -278,8 +280,7 @@ struct ena_ring { struct ena_com_rx_buf_info ena_bufs[ENA_PKT_MAX_BUFS]; u32 smoothed_interval; u32 per_napi_packets; - u32 per_napi_bytes; - enum ena_intr_moder_level moder_tbl_idx; + u16 non_empty_napi_events; struct u64_stats_sync syncp; union { struct ena_stats_tx tx_stats; @@ -329,9 +330,6 @@ struct ena_adapter { u32 missing_tx_completion_threshold; - u32 tx_usecs, rx_usecs; /* interrupt moderation */ - u32 tx_frames, rx_frames; /* interrupt moderation */ - u32 requested_tx_ring_size; u32 requested_rx_ring_size; diff --git a/drivers/net/ethernet/amd/au1000_eth.c b/drivers/net/ethernet/amd/au1000_eth.c index 650d1bae5f56..1793950f0582 100644 --- a/drivers/net/ethernet/amd/au1000_eth.c +++ b/drivers/net/ethernet/amd/au1000_eth.c @@ -1100,7 +1100,6 @@ static int au1000_probe(struct platform_device *pdev) irq = platform_get_irq(pdev, 0); if (irq < 0) { - dev_err(&pdev->dev, "failed to retrieve IRQ\n"); err = -ENODEV; goto out; } diff --git a/drivers/net/ethernet/amd/ni65.c b/drivers/net/ethernet/amd/ni65.c index 87ff5d6d1b22..c6c2a54c1121 100644 --- a/drivers/net/ethernet/amd/ni65.c +++ b/drivers/net/ethernet/amd/ni65.c @@ -697,16 +697,14 @@ static void ni65_free_buffer(struct priv *p) for(i=0;i<TMDNUM;i++) { kfree(p->tmdbounce[i]); #ifdef XMT_VIA_SKB - if(p->tmd_skb[i]) - dev_kfree_skb(p->tmd_skb[i]); + dev_kfree_skb(p->tmd_skb[i]); #endif } for(i=0;i<RMDNUM;i++) { #ifdef RCV_VIA_SKB - if(p->recv_skb[i]) - dev_kfree_skb(p->recv_skb[i]); + dev_kfree_skb(p->recv_skb[i]); #else kfree(p->recvbounce[i]); #endif diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c index b91143947ed2..b0a6c96b6ef4 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-debugfs.c @@ -438,7 +438,6 @@ static const struct file_operations xi2c_reg_value_fops = { void xgbe_debugfs_init(struct xgbe_prv_data *pdata) { - struct dentry *pfile; char *buf; /* Set defaults */ @@ -451,88 +450,48 @@ void xgbe_debugfs_init(struct xgbe_prv_data *pdata) return; pdata->xgbe_debugfs = debugfs_create_dir(buf, NULL); - if (!pdata->xgbe_debugfs) { - netdev_err(pdata->netdev, "debugfs_create_dir failed\n"); - kfree(buf); - return; - } - pfile = debugfs_create_file("xgmac_register", 0600, - pdata->xgbe_debugfs, pdata, - &xgmac_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xgmac_register", 0600, pdata->xgbe_debugfs, pdata, + &xgmac_reg_addr_fops); - pfile = debugfs_create_file("xgmac_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xgmac_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xgmac_register_value", 0600, pdata->xgbe_debugfs, + pdata, &xgmac_reg_value_fops); - pfile = debugfs_create_file("xpcs_mmd", 0600, - pdata->xgbe_debugfs, pdata, - &xpcs_mmd_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xpcs_mmd", 0600, pdata->xgbe_debugfs, pdata, + &xpcs_mmd_fops); - pfile = debugfs_create_file("xpcs_register", 0600, - pdata->xgbe_debugfs, pdata, - &xpcs_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xpcs_register", 0600, pdata->xgbe_debugfs, pdata, + &xpcs_reg_addr_fops); - pfile = debugfs_create_file("xpcs_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xpcs_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_create_file failed\n"); + debugfs_create_file("xpcs_register_value", 0600, pdata->xgbe_debugfs, + pdata, &xpcs_reg_value_fops); if (pdata->xprop_regs) { - pfile = debugfs_create_file("xprop_register", 0600, - pdata->xgbe_debugfs, pdata, - &xprop_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); - - pfile = debugfs_create_file("xprop_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xprop_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); + debugfs_create_file("xprop_register", 0600, pdata->xgbe_debugfs, + pdata, &xprop_reg_addr_fops); + + debugfs_create_file("xprop_register_value", 0600, + pdata->xgbe_debugfs, pdata, + &xprop_reg_value_fops); } if (pdata->xi2c_regs) { - pfile = debugfs_create_file("xi2c_register", 0600, - pdata->xgbe_debugfs, pdata, - &xi2c_reg_addr_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); - - pfile = debugfs_create_file("xi2c_register_value", 0600, - pdata->xgbe_debugfs, pdata, - &xi2c_reg_value_fops); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_file failed\n"); + debugfs_create_file("xi2c_register", 0600, pdata->xgbe_debugfs, + pdata, &xi2c_reg_addr_fops); + + debugfs_create_file("xi2c_register_value", 0600, + pdata->xgbe_debugfs, pdata, + &xi2c_reg_value_fops); } if (pdata->vdata->an_cdr_workaround) { - pfile = debugfs_create_bool("an_cdr_workaround", 0600, - pdata->xgbe_debugfs, - &pdata->debugfs_an_cdr_workaround); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_bool failed\n"); - - pfile = debugfs_create_bool("an_cdr_track_early", 0600, - pdata->xgbe_debugfs, - &pdata->debugfs_an_cdr_track_early); - if (!pfile) - netdev_err(pdata->netdev, - "debugfs_create_bool failed\n"); + debugfs_create_bool("an_cdr_workaround", 0600, + pdata->xgbe_debugfs, + &pdata->debugfs_an_cdr_workaround); + + debugfs_create_bool("an_cdr_track_early", 0600, + pdata->xgbe_debugfs, + &pdata->debugfs_an_cdr_track_early); } kfree(buf); @@ -546,7 +505,6 @@ void xgbe_debugfs_exit(struct xgbe_prv_data *pdata) void xgbe_debugfs_rename(struct xgbe_prv_data *pdata) { - struct dentry *pfile; char *buf; if (!pdata->xgbe_debugfs) @@ -559,11 +517,8 @@ void xgbe_debugfs_rename(struct xgbe_prv_data *pdata) if (!strcmp(pdata->xgbe_debugfs->d_name.name, buf)) goto out; - pfile = debugfs_rename(pdata->xgbe_debugfs->d_parent, - pdata->xgbe_debugfs, - pdata->xgbe_debugfs->d_parent, buf); - if (!pfile) - netdev_err(pdata->netdev, "debugfs_rename failed\n"); + debugfs_rename(pdata->xgbe_debugfs->d_parent, pdata->xgbe_debugfs, + pdata->xgbe_debugfs->d_parent, buf); out: kfree(buf); diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c index 533094233659..230726d7b74f 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-desc.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-desc.c @@ -526,7 +526,7 @@ static int xgbe_map_tx_skb(struct xgbe_channel *channel, struct sk_buff *skb) struct xgbe_ring *ring = channel->tx_ring; struct xgbe_ring_data *rdata; struct xgbe_packet_data *packet; - struct skb_frag_struct *frag; + skb_frag_t *frag; dma_addr_t skb_dma; unsigned int start_index, cur_index; unsigned int offset, tso, vlan, datalen, len; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 3dd0cecddba8..98f8f2033154 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1833,7 +1833,7 @@ static void xgbe_packet_info(struct xgbe_prv_data *pdata, struct xgbe_ring *ring, struct sk_buff *skb, struct xgbe_packet_data *packet) { - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned int context_desc; unsigned int len; unsigned int i; diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c index d0f3dfb88202..4ebd2410185a 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-platform.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-platform.c @@ -301,7 +301,6 @@ static int xgbe_platform_probe(struct platform_device *pdev) struct xgbe_prv_data *pdata; struct device *dev = &pdev->dev; struct platform_device *phy_pdev; - struct resource *res; const char *phy_mode; unsigned int phy_memnum, phy_irqnum; unsigned int dma_irqnum, dma_irqend; @@ -353,8 +352,7 @@ static int xgbe_platform_probe(struct platform_device *pdev) } /* Obtain the mmio areas for the device */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - pdata->xgmac_regs = devm_ioremap_resource(dev, res); + pdata->xgmac_regs = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(pdata->xgmac_regs)) { dev_err(dev, "xgmac ioremap failed\n"); ret = PTR_ERR(pdata->xgmac_regs); @@ -363,8 +361,7 @@ static int xgbe_platform_probe(struct platform_device *pdev) if (netif_msg_probe(pdata)) dev_dbg(dev, "xgmac_regs = %p\n", pdata->xgmac_regs); - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - pdata->xpcs_regs = devm_ioremap_resource(dev, res); + pdata->xpcs_regs = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(pdata->xpcs_regs)) { dev_err(dev, "xpcs ioremap failed\n"); ret = PTR_ERR(pdata->xpcs_regs); @@ -373,8 +370,8 @@ static int xgbe_platform_probe(struct platform_device *pdev) if (netif_msg_probe(pdata)) dev_dbg(dev, "xpcs_regs = %p\n", pdata->xpcs_regs); - res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++); - pdata->rxtx_regs = devm_ioremap_resource(dev, res); + pdata->rxtx_regs = devm_platform_ioremap_resource(phy_pdev, + phy_memnum++); if (IS_ERR(pdata->rxtx_regs)) { dev_err(dev, "rxtx ioremap failed\n"); ret = PTR_ERR(pdata->rxtx_regs); @@ -383,8 +380,8 @@ static int xgbe_platform_probe(struct platform_device *pdev) if (netif_msg_probe(pdata)) dev_dbg(dev, "rxtx_regs = %p\n", pdata->rxtx_regs); - res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++); - pdata->sir0_regs = devm_ioremap_resource(dev, res); + pdata->sir0_regs = devm_platform_ioremap_resource(phy_pdev, + phy_memnum++); if (IS_ERR(pdata->sir0_regs)) { dev_err(dev, "sir0 ioremap failed\n"); ret = PTR_ERR(pdata->sir0_regs); @@ -393,8 +390,8 @@ static int xgbe_platform_probe(struct platform_device *pdev) if (netif_msg_probe(pdata)) dev_dbg(dev, "sir0_regs = %p\n", pdata->sir0_regs); - res = platform_get_resource(phy_pdev, IORESOURCE_MEM, phy_memnum++); - pdata->sir1_regs = devm_ioremap_resource(dev, res); + pdata->sir1_regs = devm_platform_ioremap_resource(phy_pdev, + phy_memnum++); if (IS_ERR(pdata->sir1_regs)) { dev_err(dev, "sir1 ioremap failed\n"); ret = PTR_ERR(pdata->sir1_regs); @@ -467,10 +464,8 @@ static int xgbe_platform_probe(struct platform_device *pdev) /* Get the device interrupt */ ret = platform_get_irq(pdev, 0); - if (ret < 0) { - dev_err(dev, "platform_get_irq 0 failed\n"); + if (ret < 0) goto err_io; - } pdata->dev_irq = ret; /* Get the per channel DMA interrupts */ @@ -479,12 +474,8 @@ static int xgbe_platform_probe(struct platform_device *pdev) for (i = 0; (i < max) && (dma_irqnum < dma_irqend); i++) { ret = platform_get_irq(pdata->platdev, dma_irqnum++); - if (ret < 0) { - netdev_err(pdata->netdev, - "platform_get_irq %u failed\n", - dma_irqnum - 1); + if (ret < 0) goto err_io; - } pdata->channel_irq[i] = ret; } @@ -496,10 +487,8 @@ static int xgbe_platform_probe(struct platform_device *pdev) /* Get the auto-negotiation interrupt */ ret = platform_get_irq(phy_pdev, phy_irqnum++); - if (ret < 0) { - dev_err(dev, "platform_get_irq phy 0 failed\n"); + if (ret < 0) goto err_io; - } pdata->an_irq = ret; /* Configure the netdev resource */ diff --git a/drivers/net/ethernet/apm/xgene-v2/main.c b/drivers/net/ethernet/apm/xgene-v2/main.c index 79048cc46703..02b4f3af02b5 100644 --- a/drivers/net/ethernet/apm/xgene-v2/main.c +++ b/drivers/net/ethernet/apm/xgene-v2/main.c @@ -54,10 +54,8 @@ static int xge_get_resources(struct xge_pdata *pdata) } ret = platform_get_irq(pdev, 0); - if (ret < 0) { - dev_err(dev, "Unable to get irq\n"); + if (ret < 0) return ret; - } pdata->resources.irq = ret; return 0; diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c index 61a465097cb8..5f657879134e 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_hw.c @@ -712,11 +712,11 @@ static int xgene_enet_reset(struct xgene_enet_pdata *pdata) udelay(5); } else { #ifdef CONFIG_ACPI - if (acpi_has_method(ACPI_HANDLE(&pdata->pdev->dev), "_RST")) { - acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), - "_RST", NULL, NULL); - } else if (acpi_has_method(ACPI_HANDLE(&pdata->pdev->dev), - "_INI")) { + acpi_status status; + + status = acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), + "_RST", NULL, NULL); + if (ACPI_FAILURE(status)) { acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), "_INI", NULL, NULL); } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c index 10b1c053e70a..d8612131c55e 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_main.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_main.c @@ -340,7 +340,8 @@ static int xgene_enet_work_msg(struct sk_buff *skb, u64 *hopinfo) nr_frags = skb_shinfo(skb)->nr_frags; for (i = 0; i < 2 && i < nr_frags; i++) - len += skb_shinfo(skb)->frags[i].size; + len += skb_frag_size( + &skb_shinfo(skb)->frags[i]); /* HW requires header must reside in 3 buffer */ if (unlikely(hdr_len > len)) { @@ -1616,7 +1617,6 @@ static int xgene_get_rx_delay(struct xgene_enet_pdata *pdata) static int xgene_enet_get_irqs(struct xgene_enet_pdata *pdata) { struct platform_device *pdev = pdata->pdev; - struct device *dev = &pdev->dev; int i, ret, max_irqs; if (phy_interface_mode_is_rgmii(pdata->phy_mode)) @@ -1636,9 +1636,7 @@ static int xgene_enet_get_irqs(struct xgene_enet_pdata *pdata) pdata->cq_cnt = max_irqs / 2; break; } - dev_err(dev, "Unable to get ENET IRQ\n"); - ret = ret ? : -ENXIO; - return ret; + return ret ? : -ENXIO; } pdata->irqs[i] = ret; } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c index 6453fc2ebb1f..f482ced2cadd 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c @@ -460,12 +460,14 @@ static int xgene_enet_reset(struct xgene_enet_pdata *p) } } else { #ifdef CONFIG_ACPI - if (acpi_has_method(ACPI_HANDLE(&p->pdev->dev), "_RST")) - acpi_evaluate_object(ACPI_HANDLE(&p->pdev->dev), - "_RST", NULL, NULL); - else if (acpi_has_method(ACPI_HANDLE(&p->pdev->dev), "_INI")) + acpi_status status; + + status = acpi_evaluate_object(ACPI_HANDLE(&p->pdev->dev), + "_RST", NULL, NULL); + if (ACPI_FAILURE(status)) { acpi_evaluate_object(ACPI_HANDLE(&p->pdev->dev), "_INI", NULL, NULL); + } #endif } diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c index 133eb91c542e..304b5d43f236 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_xgmac.c @@ -393,11 +393,11 @@ static int xgene_enet_reset(struct xgene_enet_pdata *pdata) udelay(5); } else { #ifdef CONFIG_ACPI - if (acpi_has_method(ACPI_HANDLE(&pdata->pdev->dev), "_RST")) { - acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), - "_RST", NULL, NULL); - } else if (acpi_has_method(ACPI_HANDLE(&pdata->pdev->dev), - "_INI")) { + acpi_status status; + + status = acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), + "_RST", NULL, NULL); + if (ACPI_FAILURE(status)) { acpi_evaluate_object(ACPI_HANDLE(&pdata->pdev->dev), "_INI", NULL, NULL); } diff --git a/drivers/net/ethernet/apple/bmac.c b/drivers/net/ethernet/apple/bmac.c index c40daad515d5..a58185b1d8bf 100644 --- a/drivers/net/ethernet/apple/bmac.c +++ b/drivers/net/ethernet/apple/bmac.c @@ -815,8 +815,8 @@ static int reverse6[64] = { static unsigned int crc416(unsigned int curval, unsigned short nxtval) { - register unsigned int counter, cur = curval, next = nxtval; - register int high_crc_set, low_data_set; + unsigned int counter, cur = curval, next = nxtval; + int high_crc_set, low_data_set; /* Swap bytes */ next = ((next & 0x00FF) << 8) | (next >> 8); diff --git a/drivers/net/ethernet/atheros/ag71xx.c b/drivers/net/ethernet/atheros/ag71xx.c index 6703960c7cf5..7548247455d7 100644 --- a/drivers/net/ethernet/atheros/ag71xx.c +++ b/drivers/net/ethernet/atheros/ag71xx.c @@ -1148,7 +1148,7 @@ static int ag71xx_rings_init(struct ag71xx *ag) return -ENOMEM; } - rx->buf = &tx->buf[BIT(tx->order)]; + rx->buf = &tx->buf[tx_size]; rx->descs_cpu = ((void *)tx->descs_cpu) + tx_size * AG71XX_DESC_SIZE; rx->descs_dma = tx->descs_dma + tx_size * AG71XX_DESC_SIZE; @@ -1686,7 +1686,7 @@ static int ag71xx_probe(struct platform_device *pdev) } ag->mac_base = devm_ioremap_nocache(&pdev->dev, res->start, - res->end - res->start + 1); + resource_size(res)); if (!ag->mac_base) { err = -ENOMEM; goto err_free; diff --git a/drivers/net/ethernet/atheros/alx/main.c b/drivers/net/ethernet/atheros/alx/main.c index e3538ba7d0e7..d4bbcdfd691a 100644 --- a/drivers/net/ethernet/atheros/alx/main.c +++ b/drivers/net/ethernet/atheros/alx/main.c @@ -1465,9 +1465,7 @@ static int alx_map_tx_skb(struct alx_tx_queue *txq, struct sk_buff *skb) tpd->len = cpu_to_le16(maplen); for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { - struct skb_frag_struct *frag; - - frag = &skb_shinfo(skb)->frags[f]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; if (++txq->write_idx == txq->count) txq->write_idx = 0; @@ -1879,8 +1877,7 @@ static void alx_remove(struct pci_dev *pdev) #ifdef CONFIG_PM_SLEEP static int alx_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct alx_priv *alx = pci_get_drvdata(pdev); + struct alx_priv *alx = dev_get_drvdata(dev); if (!netif_running(alx->dev)) return 0; @@ -1891,8 +1888,7 @@ static int alx_suspend(struct device *dev) static int alx_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct alx_priv *alx = pci_get_drvdata(pdev); + struct alx_priv *alx = dev_get_drvdata(dev); struct alx_hw *hw = &alx->hw; int err; diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c index be7f9cebb675..2b239ecea05f 100644 --- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c +++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c @@ -2150,9 +2150,7 @@ static int atl1c_tx_map(struct atl1c_adapter *adapter, } for (f = 0; f < nr_frags; f++) { - struct skb_frag_struct *frag; - - frag = &skb_shinfo(skb)->frags[f]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; use_tpd = atl1c_get_tpd(adapter, type); memcpy(use_tpd, tpd, sizeof(struct atl1c_tpd_desc)); @@ -2422,8 +2420,7 @@ static int atl1c_close(struct net_device *netdev) static int atl1c_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct atl1c_adapter *adapter = netdev_priv(netdev); struct atl1c_hw *hw = &adapter->hw; u32 wufc = adapter->wol; @@ -2437,7 +2434,7 @@ static int atl1c_suspend(struct device *dev) if (wufc) if (atl1c_phy_to_ps_link(hw) != 0) - dev_dbg(&pdev->dev, "phy power saving failed"); + dev_dbg(dev, "phy power saving failed"); atl1c_power_saving(hw, wufc); @@ -2447,8 +2444,7 @@ static int atl1c_suspend(struct device *dev) #ifdef CONFIG_PM_SLEEP static int atl1c_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct atl1c_adapter *adapter = netdev_priv(netdev); AT_WRITE_REG(&adapter->hw, REG_WOL_CTRL, 0); diff --git a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c index 7f14e010bfeb..4f7b65825c15 100644 --- a/drivers/net/ethernet/atheros/atl1e/atl1e_main.c +++ b/drivers/net/ethernet/atheros/atl1e/atl1e_main.c @@ -1770,11 +1770,10 @@ static int atl1e_tx_map(struct atl1e_adapter *adapter, } for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; u16 i; u16 seg_num; - frag = &skb_shinfo(skb)->frags[f]; buf_len = skb_frag_size(frag); seg_num = (buf_len + MAX_TX_BUF_LEN - 1) / MAX_TX_BUF_LEN; diff --git a/drivers/net/ethernet/atheros/atlx/atl1.c b/drivers/net/ethernet/atheros/atlx/atl1.c index b5c6dc914720..b498fd6a47d0 100644 --- a/drivers/net/ethernet/atheros/atlx/atl1.c +++ b/drivers/net/ethernet/atheros/atlx/atl1.c @@ -2256,10 +2256,9 @@ static void atl1_tx_map(struct atl1_adapter *adapter, struct sk_buff *skb, } for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; u16 i, nseg; - frag = &skb_shinfo(skb)->frags[f]; buf_len = skb_frag_size(frag); nseg = (buf_len + ATL1_MAX_TX_BUF_LEN - 1) / @@ -2754,8 +2753,7 @@ static int atl1_close(struct net_device *netdev) #ifdef CONFIG_PM_SLEEP static int atl1_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct atl1_adapter *adapter = netdev_priv(netdev); struct atl1_hw *hw = &adapter->hw; u32 ctrl = 0; @@ -2780,7 +2778,7 @@ static int atl1_suspend(struct device *dev) val = atl1_get_speed_and_duplex(hw, &speed, &duplex); if (val) { if (netif_msg_ifdown(adapter)) - dev_printk(KERN_DEBUG, &pdev->dev, + dev_printk(KERN_DEBUG, dev, "error getting speed/duplex\n"); goto disable_wol; } @@ -2837,8 +2835,7 @@ static int atl1_suspend(struct device *dev) static int atl1_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct atl1_adapter *adapter = netdev_priv(netdev); iowrite32(0, adapter->hw.hw_addr + REG_WOL_CTRL); diff --git a/drivers/net/ethernet/aurora/nb8800.c b/drivers/net/ethernet/aurora/nb8800.c index 3b3370a94a9c..37752d9514e7 100644 --- a/drivers/net/ethernet/aurora/nb8800.c +++ b/drivers/net/ethernet/aurora/nb8800.c @@ -1351,10 +1351,8 @@ static int nb8800_probe(struct platform_device *pdev) ops = match->data; irq = platform_get_irq(pdev, 0); - if (irq <= 0) { - dev_err(&pdev->dev, "No IRQ\n"); + if (irq <= 0) return -EINVAL; - } res = platform_get_resource(pdev, IORESOURCE_MEM, 0); base = devm_ioremap_resource(&pdev->dev, res); diff --git a/drivers/net/ethernet/broadcom/bcm63xx_enet.c b/drivers/net/ethernet/broadcom/bcm63xx_enet.c index 291e4afd4a1a..620cd3fc1fbc 100644 --- a/drivers/net/ethernet/broadcom/bcm63xx_enet.c +++ b/drivers/net/ethernet/broadcom/bcm63xx_enet.c @@ -1693,7 +1693,7 @@ static int bcm_enet_probe(struct platform_device *pdev) struct bcm_enet_priv *priv; struct net_device *dev; struct bcm63xx_enet_platform_data *pd; - struct resource *res_mem, *res_irq, *res_irq_rx, *res_irq_tx; + struct resource *res_irq, *res_irq_rx, *res_irq_tx; struct mii_bus *bus; int i, ret; @@ -1719,8 +1719,7 @@ static int bcm_enet_probe(struct platform_device *pdev) if (ret) goto out; - res_mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->base = devm_ioremap_resource(&pdev->dev, res_mem); + priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) { ret = PTR_ERR(priv->base); goto out; @@ -2762,15 +2761,13 @@ struct platform_driver bcm63xx_enetsw_driver = { /* reserve & remap memory space shared between all macs */ static int bcm_enet_shared_probe(struct platform_device *pdev) { - struct resource *res; void __iomem *p[3]; unsigned int i; memset(bcm_enet_shared_base, 0, sizeof(bcm_enet_shared_base)); for (i = 0; i < 3; i++) { - res = platform_get_resource(pdev, IORESOURCE_MEM, i); - p[i] = devm_ioremap_resource(&pdev->dev, res); + p[i] = devm_platform_ioremap_resource(pdev, i); if (IS_ERR(p[i])) return PTR_ERR(p[i]); } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 9483553ce444..7df887e4024c 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -708,8 +708,7 @@ static int bcm_sysport_alloc_rx_bufs(struct bcm_sysport_priv *priv) for (i = 0; i < priv->num_rx_bds; i++) { cb = &priv->rx_cbs[i]; skb = bcm_sysport_rx_refill(priv, cb); - if (skb) - dev_kfree_skb(skb); + dev_kfree_skb(skb); if (!cb->skb) return -ENOMEM; } @@ -2420,12 +2419,10 @@ static int bcm_sysport_probe(struct platform_device *pdev) struct device_node *dn; struct net_device *dev; const void *macaddr; - struct resource *r; u32 txq, rxq; int ret; dn = pdev->dev.of_node; - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); of_id = of_match_node(bcm_sysport_of_match, dn); if (!of_id || !of_id->data) return -EINVAL; @@ -2473,7 +2470,7 @@ static int bcm_sysport_probe(struct platform_device *pdev) goto err_free_netdev; } - priv->base = devm_ioremap_resource(&pdev->dev, r); + priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) { ret = PTR_ERR(priv->base); goto err_free_netdev; diff --git a/drivers/net/ethernet/broadcom/bgmac-platform.c b/drivers/net/ethernet/broadcom/bgmac-platform.c index 6dc0dd91ad11..c46c1b1416f7 100644 --- a/drivers/net/ethernet/broadcom/bgmac-platform.c +++ b/drivers/net/ethernet/broadcom/bgmac-platform.c @@ -199,10 +199,8 @@ static int bgmac_probe(struct platform_device *pdev) dev_warn(&pdev->dev, "MAC address not present in device tree\n"); bgmac->irq = platform_get_irq(pdev, 0); - if (bgmac->irq < 0) { - dev_err(&pdev->dev, "Unable to obtain IRQ\n"); + if (bgmac->irq < 0) return bgmac->irq; - } regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "amac_base"); if (!regs) { diff --git a/drivers/net/ethernet/broadcom/bgmac.c b/drivers/net/ethernet/broadcom/bgmac.c index 4632dd5dbad1..148734b166f0 100644 --- a/drivers/net/ethernet/broadcom/bgmac.c +++ b/drivers/net/ethernet/broadcom/bgmac.c @@ -172,7 +172,7 @@ static netdev_tx_t bgmac_dma_tx_add(struct bgmac *bgmac, flags = 0; for (i = 0; i < nr_frags; i++) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int len = skb_frag_size(frag); index = (index + 1) % BGMAC_TX_RING_SLOTS; diff --git a/drivers/net/ethernet/broadcom/bnx2.c b/drivers/net/ethernet/broadcom/bnx2.c index dfdd14eadd57..fbc196b480b6 100644 --- a/drivers/net/ethernet/broadcom/bnx2.c +++ b/drivers/net/ethernet/broadcom/bnx2.c @@ -8673,8 +8673,7 @@ bnx2_remove_one(struct pci_dev *pdev) static int bnx2_suspend(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct bnx2 *bp = netdev_priv(dev); if (netif_running(dev)) { @@ -8693,8 +8692,7 @@ bnx2_suspend(struct device *device) static int bnx2_resume(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct bnx2 *bp = netdev_priv(dev); if (!netif_running(dev)) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index 8dce4069472b..b4a8cf620a0c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -116,6 +116,9 @@ enum board_idx { BCM57508, BCM57504, BCM57502, + BCM57508_NPAR, + BCM57504_NPAR, + BCM57502_NPAR, BCM58802, BCM58804, BCM58808, @@ -161,6 +164,9 @@ static const struct { [BCM57508] = { "Broadcom BCM57508 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" }, [BCM57504] = { "Broadcom BCM57504 NetXtreme-E 10Gb/25Gb/50Gb/100Gb/200Gb Ethernet" }, [BCM57502] = { "Broadcom BCM57502 NetXtreme-E 10Gb/25Gb/50Gb Ethernet" }, + [BCM57508_NPAR] = { "Broadcom BCM57508 NetXtreme-E Ethernet Partition" }, + [BCM57504_NPAR] = { "Broadcom BCM57504 NetXtreme-E Ethernet Partition" }, + [BCM57502_NPAR] = { "Broadcom BCM57502 NetXtreme-E Ethernet Partition" }, [BCM58802] = { "Broadcom BCM58802 NetXtreme-S 10Gb/25Gb/40Gb/50Gb Ethernet" }, [BCM58804] = { "Broadcom BCM58804 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" }, [BCM58808] = { "Broadcom BCM58808 NetXtreme-S 10Gb/25Gb/40Gb/50Gb/100Gb Ethernet" }, @@ -209,6 +215,12 @@ static const struct pci_device_id bnxt_pci_tbl[] = { { PCI_VDEVICE(BROADCOM, 0x1750), .driver_data = BCM57508 }, { PCI_VDEVICE(BROADCOM, 0x1751), .driver_data = BCM57504 }, { PCI_VDEVICE(BROADCOM, 0x1752), .driver_data = BCM57502 }, + { PCI_VDEVICE(BROADCOM, 0x1800), .driver_data = BCM57508_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1801), .driver_data = BCM57504_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1802), .driver_data = BCM57502_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1803), .driver_data = BCM57508_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1804), .driver_data = BCM57504_NPAR }, + { PCI_VDEVICE(BROADCOM, 0x1805), .driver_data = BCM57502_NPAR }, { PCI_VDEVICE(BROADCOM, 0xd802), .driver_data = BCM58802 }, { PCI_VDEVICE(BROADCOM, 0xd804), .driver_data = BCM58804 }, #ifdef CONFIG_BNXT_SRIOV @@ -242,6 +254,8 @@ static const u16 bnxt_async_events_arr[] = { ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED, ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE, ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE, + ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY, + ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY, }; static struct workqueue_struct *bnxt_pf_wq; @@ -828,16 +842,41 @@ static inline int bnxt_alloc_rx_page(struct bnxt *bp, return 0; } -static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 cp_cons, - u32 agg_bufs) +static struct rx_agg_cmp *bnxt_get_agg(struct bnxt *bp, + struct bnxt_cp_ring_info *cpr, + u16 cp_cons, u16 curr) +{ + struct rx_agg_cmp *agg; + + cp_cons = RING_CMP(ADV_RAW_CMP(cp_cons, curr)); + agg = (struct rx_agg_cmp *) + &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + return agg; +} + +static struct rx_agg_cmp *bnxt_get_tpa_agg_p5(struct bnxt *bp, + struct bnxt_rx_ring_info *rxr, + u16 agg_id, u16 curr) +{ + struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[agg_id]; + + return &tpa_info->agg_arr[curr]; +} + +static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 idx, + u16 start, u32 agg_bufs, bool tpa) { struct bnxt_napi *bnapi = cpr->bnapi; struct bnxt *bp = bnapi->bp; struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; u16 prod = rxr->rx_agg_prod; u16 sw_prod = rxr->rx_sw_agg_prod; + bool p5_tpa = false; u32 i; + if ((bp->flags & BNXT_FLAG_CHIP_P5) && tpa) + p5_tpa = true; + for (i = 0; i < agg_bufs; i++) { u16 cons; struct rx_agg_cmp *agg; @@ -845,8 +884,10 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 cp_cons, struct rx_bd *prod_bd; struct page *page; - agg = (struct rx_agg_cmp *) - &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + if (p5_tpa) + agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, start + i); + else + agg = bnxt_get_agg(bp, cpr, idx, start + i); cons = agg->rx_agg_cmp_opaque; __clear_bit(cons, rxr->rx_agg_bmap); @@ -874,7 +915,6 @@ static void bnxt_reuse_rx_agg_bufs(struct bnxt_cp_ring_info *cpr, u16 cp_cons, prod = NEXT_RX_AGG(prod); sw_prod = NEXT_RX_AGG(sw_prod); - cp_cons = NEXT_CMP(cp_cons); } rxr->rx_agg_prod = prod; rxr->rx_sw_agg_prod = sw_prod; @@ -888,7 +928,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, { unsigned int payload = offset_and_len >> 16; unsigned int len = offset_and_len & 0xffff; - struct skb_frag_struct *frag; + skb_frag_t *frag; struct page *page = data; u16 prod = rxr->rx_prod; struct sk_buff *skb; @@ -919,7 +959,7 @@ static struct sk_buff *bnxt_rx_page_skb(struct bnxt *bp, frag = &skb_shinfo(skb)->frags[0]; skb_frag_size_sub(frag, payload); - frag->page_offset += payload; + skb_frag_off_add(frag, payload); skb->data_len -= payload; skb->tail += payload; @@ -957,15 +997,19 @@ static struct sk_buff *bnxt_rx_skb(struct bnxt *bp, static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, - struct sk_buff *skb, u16 cp_cons, - u32 agg_bufs) + struct sk_buff *skb, u16 idx, + u32 agg_bufs, bool tpa) { struct bnxt_napi *bnapi = cpr->bnapi; struct pci_dev *pdev = bp->pdev; struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; u16 prod = rxr->rx_agg_prod; + bool p5_tpa = false; u32 i; + if ((bp->flags & BNXT_FLAG_CHIP_P5) && tpa) + p5_tpa = true; + for (i = 0; i < agg_bufs; i++) { u16 cons, frag_len; struct rx_agg_cmp *agg; @@ -973,8 +1017,10 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, struct page *page; dma_addr_t mapping; - agg = (struct rx_agg_cmp *) - &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + if (p5_tpa) + agg = bnxt_get_tpa_agg_p5(bp, rxr, idx, i); + else + agg = bnxt_get_agg(bp, cpr, idx, i); cons = agg->rx_agg_cmp_opaque; frag_len = (le32_to_cpu(agg->rx_agg_cmp_len_flags_type) & RX_AGG_CMP_LEN) >> RX_AGG_CMP_LEN_SHIFT; @@ -1008,7 +1054,7 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, * allocated already. */ rxr->rx_agg_prod = prod; - bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs - i); + bnxt_reuse_rx_agg_bufs(cpr, idx, i, agg_bufs - i, tpa); return NULL; } @@ -1021,7 +1067,6 @@ static struct sk_buff *bnxt_rx_pages(struct bnxt *bp, skb->truesize += PAGE_SIZE; prod = NEXT_RX_AGG(prod); - cp_cons = NEXT_CMP(cp_cons); } rxr->rx_agg_prod = prod; return skb; @@ -1081,9 +1126,10 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } else if (cmp_type == CMP_TYPE_RX_L2_TPA_END_CMP) { struct rx_tpa_end_cmp *tpa_end = cmp; - agg_bufs = (le32_to_cpu(tpa_end->rx_tpa_end_cmp_misc_v1) & - RX_TPA_END_CMP_AGG_BUFS) >> - RX_TPA_END_CMP_AGG_BUFS_SHIFT; + if (bp->flags & BNXT_FLAG_CHIP_P5) + return 0; + + agg_bufs = TPA_END_AGG_BUFS(tpa_end); } if (agg_bufs) { @@ -1094,6 +1140,14 @@ static int bnxt_discard_rx(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, return 0; } +static void bnxt_queue_fw_reset_work(struct bnxt *bp, unsigned long delay) +{ + if (BNXT_PF(bp)) + queue_delayed_work(bnxt_pf_wq, &bp->fw_reset_task, delay); + else + schedule_delayed_work(&bp->fw_reset_task, delay); +} + static void bnxt_queue_sp_work(struct bnxt *bp) { if (BNXT_PF(bp)) @@ -1120,26 +1174,60 @@ static void bnxt_sched_reset(struct bnxt *bp, struct bnxt_rx_ring_info *rxr) rxr->rx_next_cons = 0xffff; } +static u16 bnxt_alloc_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id) +{ + struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map; + u16 idx = agg_id & MAX_TPA_P5_MASK; + + if (test_bit(idx, map->agg_idx_bmap)) + idx = find_first_zero_bit(map->agg_idx_bmap, + BNXT_AGG_IDX_BMAP_SIZE); + __set_bit(idx, map->agg_idx_bmap); + map->agg_id_tbl[agg_id] = idx; + return idx; +} + +static void bnxt_free_agg_idx(struct bnxt_rx_ring_info *rxr, u16 idx) +{ + struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map; + + __clear_bit(idx, map->agg_idx_bmap); +} + +static u16 bnxt_lookup_agg_idx(struct bnxt_rx_ring_info *rxr, u16 agg_id) +{ + struct bnxt_tpa_idx_map *map = rxr->rx_tpa_idx_map; + + return map->agg_id_tbl[agg_id]; +} + static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, struct rx_tpa_start_cmp *tpa_start, struct rx_tpa_start_cmp_ext *tpa_start1) { - u8 agg_id = TPA_START_AGG_ID(tpa_start); - u16 cons, prod; - struct bnxt_tpa_info *tpa_info; struct bnxt_sw_rx_bd *cons_rx_buf, *prod_rx_buf; + struct bnxt_tpa_info *tpa_info; + u16 cons, prod, agg_id; struct rx_bd *prod_bd; dma_addr_t mapping; + if (bp->flags & BNXT_FLAG_CHIP_P5) { + agg_id = TPA_START_AGG_ID_P5(tpa_start); + agg_id = bnxt_alloc_agg_idx(rxr, agg_id); + } else { + agg_id = TPA_START_AGG_ID(tpa_start); + } cons = tpa_start->rx_tpa_start_cmp_opaque; prod = rxr->rx_prod; cons_rx_buf = &rxr->rx_buf_ring[cons]; prod_rx_buf = &rxr->rx_buf_ring[prod]; tpa_info = &rxr->rx_tpa[agg_id]; - if (unlikely(cons != rxr->rx_next_cons)) { - netdev_warn(bp->dev, "TPA cons %x != expected cons %x\n", - cons, rxr->rx_next_cons); + if (unlikely(cons != rxr->rx_next_cons || + TPA_START_ERROR(tpa_start))) { + netdev_warn(bp->dev, "TPA cons %x, expected cons %x, error code %x\n", + cons, rxr->rx_next_cons, + TPA_START_ERROR_CODE(tpa_start1)); bnxt_sched_reset(bp, rxr); return; } @@ -1184,6 +1272,7 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, tpa_info->flags2 = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_flags2); tpa_info->metadata = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_metadata); tpa_info->hdr_info = le32_to_cpu(tpa_start1->rx_tpa_start_cmp_hdr_info); + tpa_info->agg_count = 0; rxr->rx_prod = NEXT_RX(prod); cons = NEXT_RX(cons); @@ -1195,12 +1284,36 @@ static void bnxt_tpa_start(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, cons_rx_buf->data = NULL; } -static void bnxt_abort_tpa(struct bnxt_cp_ring_info *cpr, u16 cp_cons, - u32 agg_bufs) +static void bnxt_abort_tpa(struct bnxt_cp_ring_info *cpr, u16 idx, u32 agg_bufs) { if (agg_bufs) - bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs); + bnxt_reuse_rx_agg_bufs(cpr, idx, 0, agg_bufs, true); +} + +#ifdef CONFIG_INET +static void bnxt_gro_tunnel(struct sk_buff *skb, __be16 ip_proto) +{ + struct udphdr *uh = NULL; + + if (ip_proto == htons(ETH_P_IP)) { + struct iphdr *iph = (struct iphdr *)skb->data; + + if (iph->protocol == IPPROTO_UDP) + uh = (struct udphdr *)(iph + 1); + } else { + struct ipv6hdr *iph = (struct ipv6hdr *)skb->data; + + if (iph->nexthdr == IPPROTO_UDP) + uh = (struct udphdr *)(iph + 1); + } + if (uh) { + if (uh->check) + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM; + else + skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; + } } +#endif static struct sk_buff *bnxt_gro_func_5731x(struct bnxt_tpa_info *tpa_info, int payload_off, int tcp_ts, @@ -1259,28 +1372,39 @@ static struct sk_buff *bnxt_gro_func_5731x(struct bnxt_tpa_info *tpa_info, } if (inner_mac_off) { /* tunnel */ - struct udphdr *uh = NULL; __be16 proto = *((__be16 *)(skb->data + outer_ip_off - ETH_HLEN - 2)); - if (proto == htons(ETH_P_IP)) { - struct iphdr *iph = (struct iphdr *)skb->data; + bnxt_gro_tunnel(skb, proto); + } +#endif + return skb; +} - if (iph->protocol == IPPROTO_UDP) - uh = (struct udphdr *)(iph + 1); - } else { - struct ipv6hdr *iph = (struct ipv6hdr *)skb->data; +static struct sk_buff *bnxt_gro_func_5750x(struct bnxt_tpa_info *tpa_info, + int payload_off, int tcp_ts, + struct sk_buff *skb) +{ +#ifdef CONFIG_INET + u16 outer_ip_off, inner_ip_off, inner_mac_off; + u32 hdr_info = tpa_info->hdr_info; + int iphdr_len, nw_off; - if (iph->nexthdr == IPPROTO_UDP) - uh = (struct udphdr *)(iph + 1); - } - if (uh) { - if (uh->check) - skb_shinfo(skb)->gso_type |= - SKB_GSO_UDP_TUNNEL_CSUM; - else - skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; - } + inner_ip_off = BNXT_TPA_INNER_L3_OFF(hdr_info); + inner_mac_off = BNXT_TPA_INNER_L2_OFF(hdr_info); + outer_ip_off = BNXT_TPA_OUTER_L3_OFF(hdr_info); + + nw_off = inner_ip_off - ETH_HLEN; + skb_set_network_header(skb, nw_off); + iphdr_len = (tpa_info->flags2 & RX_TPA_START_CMP_FLAGS2_IP_TYPE) ? + sizeof(struct ipv6hdr) : sizeof(struct iphdr); + skb_set_transport_header(skb, nw_off + iphdr_len); + + if (inner_mac_off) { /* tunnel */ + __be16 proto = *((__be16 *)(skb->data + outer_ip_off - + ETH_HLEN - 2)); + + bnxt_gro_tunnel(skb, proto); } #endif return skb; @@ -1327,28 +1451,8 @@ static struct sk_buff *bnxt_gro_func_5730x(struct bnxt_tpa_info *tpa_info, return NULL; } - if (nw_off) { /* tunnel */ - struct udphdr *uh = NULL; - - if (skb->protocol == htons(ETH_P_IP)) { - struct iphdr *iph = (struct iphdr *)skb->data; - - if (iph->protocol == IPPROTO_UDP) - uh = (struct udphdr *)(iph + 1); - } else { - struct ipv6hdr *iph = (struct ipv6hdr *)skb->data; - - if (iph->nexthdr == IPPROTO_UDP) - uh = (struct udphdr *)(iph + 1); - } - if (uh) { - if (uh->check) - skb_shinfo(skb)->gso_type |= - SKB_GSO_UDP_TUNNEL_CSUM; - else - skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL; - } - } + if (nw_off) /* tunnel */ + bnxt_gro_tunnel(skb, skb->protocol); #endif return skb; } @@ -1371,9 +1475,10 @@ static inline struct sk_buff *bnxt_gro_skb(struct bnxt *bp, skb_shinfo(skb)->gso_size = le32_to_cpu(tpa_end1->rx_tpa_end_cmp_seg_len); skb_shinfo(skb)->gso_type = tpa_info->gso_type; - payload_off = (le32_to_cpu(tpa_end->rx_tpa_end_cmp_misc_v1) & - RX_TPA_END_CMP_PAYLOAD_OFFSET) >> - RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT; + if (bp->flags & BNXT_FLAG_CHIP_P5) + payload_off = TPA_END_PAYLOAD_OFF_P5(tpa_end1); + else + payload_off = TPA_END_PAYLOAD_OFF(tpa_end); skb = bp->gro_func(tpa_info, payload_off, TPA_END_GRO_TS(tpa_end), skb); if (likely(skb)) tcp_gro_complete(skb); @@ -1401,14 +1506,14 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, { struct bnxt_napi *bnapi = cpr->bnapi; struct bnxt_rx_ring_info *rxr = bnapi->rx_ring; - u8 agg_id = TPA_END_AGG_ID(tpa_end); u8 *data_ptr, agg_bufs; - u16 cp_cons = RING_CMP(*raw_cons); unsigned int len; struct bnxt_tpa_info *tpa_info; dma_addr_t mapping; struct sk_buff *skb; + u16 idx = 0, agg_id; void *data; + bool gro; if (unlikely(bnapi->in_reset)) { int rc = bnxt_discard_rx(bp, cpr, raw_cons, tpa_end); @@ -1418,26 +1523,43 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, return NULL; } - tpa_info = &rxr->rx_tpa[agg_id]; + if (bp->flags & BNXT_FLAG_CHIP_P5) { + agg_id = TPA_END_AGG_ID_P5(tpa_end); + agg_id = bnxt_lookup_agg_idx(rxr, agg_id); + agg_bufs = TPA_END_AGG_BUFS_P5(tpa_end1); + tpa_info = &rxr->rx_tpa[agg_id]; + if (unlikely(agg_bufs != tpa_info->agg_count)) { + netdev_warn(bp->dev, "TPA end agg_buf %d != expected agg_bufs %d\n", + agg_bufs, tpa_info->agg_count); + agg_bufs = tpa_info->agg_count; + } + tpa_info->agg_count = 0; + *event |= BNXT_AGG_EVENT; + bnxt_free_agg_idx(rxr, agg_id); + idx = agg_id; + gro = !!(bp->flags & BNXT_FLAG_GRO); + } else { + agg_id = TPA_END_AGG_ID(tpa_end); + agg_bufs = TPA_END_AGG_BUFS(tpa_end); + tpa_info = &rxr->rx_tpa[agg_id]; + idx = RING_CMP(*raw_cons); + if (agg_bufs) { + if (!bnxt_agg_bufs_valid(bp, cpr, agg_bufs, raw_cons)) + return ERR_PTR(-EBUSY); + + *event |= BNXT_AGG_EVENT; + idx = NEXT_CMP(idx); + } + gro = !!TPA_END_GRO(tpa_end); + } data = tpa_info->data; data_ptr = tpa_info->data_ptr; prefetch(data_ptr); len = tpa_info->len; mapping = tpa_info->mapping; - agg_bufs = (le32_to_cpu(tpa_end->rx_tpa_end_cmp_misc_v1) & - RX_TPA_END_CMP_AGG_BUFS) >> RX_TPA_END_CMP_AGG_BUFS_SHIFT; - - if (agg_bufs) { - if (!bnxt_agg_bufs_valid(bp, cpr, agg_bufs, raw_cons)) - return ERR_PTR(-EBUSY); - - *event |= BNXT_AGG_EVENT; - cp_cons = NEXT_CMP(cp_cons); - } - if (unlikely(agg_bufs > MAX_SKB_FRAGS || TPA_END_ERRORS(tpa_end1))) { - bnxt_abort_tpa(cpr, cp_cons, agg_bufs); + bnxt_abort_tpa(cpr, idx, agg_bufs); if (agg_bufs > MAX_SKB_FRAGS) netdev_warn(bp->dev, "TPA frags %d exceeded MAX_SKB_FRAGS %d\n", agg_bufs, (int)MAX_SKB_FRAGS); @@ -1447,7 +1569,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, if (len <= bp->rx_copy_thresh) { skb = bnxt_copy_skb(bnapi, data_ptr, len, mapping); if (!skb) { - bnxt_abort_tpa(cpr, cp_cons, agg_bufs); + bnxt_abort_tpa(cpr, idx, agg_bufs); return NULL; } } else { @@ -1456,7 +1578,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, new_data = __bnxt_alloc_rx_data(bp, &new_mapping, GFP_ATOMIC); if (!new_data) { - bnxt_abort_tpa(cpr, cp_cons, agg_bufs); + bnxt_abort_tpa(cpr, idx, agg_bufs); return NULL; } @@ -1471,7 +1593,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, if (!skb) { kfree(data); - bnxt_abort_tpa(cpr, cp_cons, agg_bufs); + bnxt_abort_tpa(cpr, idx, agg_bufs); return NULL; } skb_reserve(skb, bp->rx_offset); @@ -1479,7 +1601,7 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, } if (agg_bufs) { - skb = bnxt_rx_pages(bp, cpr, skb, cp_cons, agg_bufs); + skb = bnxt_rx_pages(bp, cpr, skb, idx, agg_bufs, true); if (!skb) { /* Page reuse already handled by bnxt_rx_pages(). */ return NULL; @@ -1508,12 +1630,24 @@ static inline struct sk_buff *bnxt_tpa_end(struct bnxt *bp, (tpa_info->flags2 & RX_CMP_FLAGS2_T_L4_CS_CALC) >> 3; } - if (TPA_END_GRO(tpa_end)) + if (gro) skb = bnxt_gro_skb(bp, tpa_info, tpa_end, tpa_end1, skb); return skb; } +static void bnxt_tpa_agg(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, + struct rx_agg_cmp *rx_agg) +{ + u16 agg_id = TPA_AGG_AGG_ID(rx_agg); + struct bnxt_tpa_info *tpa_info; + + agg_id = bnxt_lookup_agg_idx(rxr, agg_id); + tpa_info = &rxr->rx_tpa[agg_id]; + BUG_ON(tpa_info->agg_count >= MAX_SKB_FRAGS); + tpa_info->agg_arr[tpa_info->agg_count++] = *rx_agg; +} + static void bnxt_deliver_skb(struct bnxt *bp, struct bnxt_napi *bnapi, struct sk_buff *skb) { @@ -1555,6 +1689,13 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, rxcmp = (struct rx_cmp *) &cpr->cp_desc_ring[CP_RING(cp_cons)][CP_IDX(cp_cons)]; + cmp_type = RX_CMP_TYPE(rxcmp); + + if (cmp_type == CMP_TYPE_RX_TPA_AGG_CMP) { + bnxt_tpa_agg(bp, rxr, (struct rx_agg_cmp *)rxcmp); + goto next_rx_no_prod_no_len; + } + tmp_raw_cons = NEXT_RAW_CMP(tmp_raw_cons); cp_cons = RING_CMP(tmp_raw_cons); rxcmp1 = (struct rx_cmp_ext *) @@ -1563,8 +1704,6 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, if (!RX_CMP_VALID(rxcmp1, tmp_raw_cons)) return -EBUSY; - cmp_type = RX_CMP_TYPE(rxcmp); - prod = rxr->rx_prod; if (cmp_type == CMP_TYPE_RX_L2_TPA_START_CMP) { @@ -1623,7 +1762,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, bnxt_reuse_rx_data(rxr, cons, data); if (agg_bufs) - bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs); + bnxt_reuse_rx_agg_bufs(cpr, cp_cons, 0, agg_bufs, + false); rc = -EIO; if (rx_err & RX_CMPL_ERRORS_BUFFER_ERROR_MASK) { @@ -1646,7 +1786,8 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, bnxt_reuse_rx_data(rxr, cons, data); if (!skb) { if (agg_bufs) - bnxt_reuse_rx_agg_bufs(cpr, cp_cons, agg_bufs); + bnxt_reuse_rx_agg_bufs(cpr, cp_cons, 0, + agg_bufs, false); rc = -ENOMEM; goto next_rx; } @@ -1666,7 +1807,7 @@ static int bnxt_rx_pkt(struct bnxt *bp, struct bnxt_cp_ring_info *cpr, } if (agg_bufs) { - skb = bnxt_rx_pages(bp, cpr, skb, cp_cons, agg_bufs); + skb = bnxt_rx_pages(bp, cpr, skb, cp_cons, agg_bufs, false); if (!skb) { rc = -ENOMEM; goto next_rx; @@ -1765,6 +1906,33 @@ static int bnxt_force_rx_discard(struct bnxt *bp, return bnxt_rx_pkt(bp, cpr, raw_cons, event); } +u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx) +{ + struct bnxt_fw_health *fw_health = bp->fw_health; + u32 reg = fw_health->regs[reg_idx]; + u32 reg_type, reg_off, val = 0; + + reg_type = BNXT_FW_HEALTH_REG_TYPE(reg); + reg_off = BNXT_FW_HEALTH_REG_OFF(reg); + switch (reg_type) { + case BNXT_FW_HEALTH_REG_TYPE_CFG: + pci_read_config_dword(bp->pdev, reg_off, &val); + break; + case BNXT_FW_HEALTH_REG_TYPE_GRC: + reg_off = fw_health->mapped_regs[reg_idx]; + /* fall through */ + case BNXT_FW_HEALTH_REG_TYPE_BAR0: + val = readl(bp->bar0 + reg_off); + break; + case BNXT_FW_HEALTH_REG_TYPE_BAR1: + val = readl(bp->bar1 + reg_off); + break; + } + if (reg_idx == BNXT_FW_RESET_INPROG_REG) + val &= fw_health->fw_reset_inprog_reg_mask; + return val; +} + #define BNXT_GET_EVENT_PORT(data) \ ((data) & \ ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_MASK) @@ -1820,6 +1988,55 @@ static int bnxt_async_event_process(struct bnxt *bp, goto async_event_process_exit; set_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event); break; + case ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY: { + u32 data1 = le32_to_cpu(cmpl->event_data1); + + bp->fw_reset_timestamp = jiffies; + bp->fw_reset_min_dsecs = cmpl->timestamp_lo; + if (!bp->fw_reset_min_dsecs) + bp->fw_reset_min_dsecs = BNXT_DFLT_FW_RST_MIN_DSECS; + bp->fw_reset_max_dsecs = le16_to_cpu(cmpl->timestamp_hi); + if (!bp->fw_reset_max_dsecs) + bp->fw_reset_max_dsecs = BNXT_DFLT_FW_RST_MAX_DSECS; + if (EVENT_DATA1_RESET_NOTIFY_FATAL(data1)) { + netdev_warn(bp->dev, "Firmware fatal reset event received\n"); + set_bit(BNXT_STATE_FW_FATAL_COND, &bp->state); + } else { + netdev_warn(bp->dev, "Firmware non-fatal reset event received, max wait time %d msec\n", + bp->fw_reset_max_dsecs * 100); + } + set_bit(BNXT_FW_RESET_NOTIFY_SP_EVENT, &bp->sp_event); + break; + } + case ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY: { + struct bnxt_fw_health *fw_health = bp->fw_health; + u32 data1 = le32_to_cpu(cmpl->event_data1); + + if (!fw_health) + goto async_event_process_exit; + + fw_health->enabled = EVENT_DATA1_RECOVERY_ENABLED(data1); + fw_health->master = EVENT_DATA1_RECOVERY_MASTER_FUNC(data1); + if (!fw_health->enabled) + break; + + if (netif_msg_drv(bp)) + netdev_info(bp->dev, "Error recovery info: error recovery[%d], master[%d], reset count[0x%x], health status: 0x%x\n", + fw_health->enabled, fw_health->master, + bnxt_fw_health_readl(bp, + BNXT_FW_RESET_CNT_REG), + bnxt_fw_health_readl(bp, + BNXT_FW_HEALTH_REG)); + fw_health->tmr_multiplier = + DIV_ROUND_UP(fw_health->polling_dsecs * HZ, + bp->current_interval * 10); + fw_health->tmr_counter = fw_health->tmr_multiplier; + fw_health->last_fw_heartbeat = + bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG); + fw_health->last_fw_reset_cnt = + bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); + goto async_event_process_exit; + } default: goto async_event_process_exit; } @@ -2325,10 +2542,11 @@ static void bnxt_free_rx_skbs(struct bnxt *bp) max_agg_idx = bp->rx_agg_nr_pages * RX_DESC_CNT; for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + struct bnxt_tpa_idx_map *map; int j; if (rxr->rx_tpa) { - for (j = 0; j < MAX_TPA; j++) { + for (j = 0; j < bp->max_tpa; j++) { struct bnxt_tpa_info *tpa_info = &rxr->rx_tpa[j]; u8 *data = tpa_info->data; @@ -2395,6 +2613,9 @@ static void bnxt_free_rx_skbs(struct bnxt *bp) __free_page(rxr->rx_page); rxr->rx_page = NULL; } + map = rxr->rx_tpa_idx_map; + if (map) + memset(map->agg_idx_bmap, 0, sizeof(map->agg_idx_bmap)); } } @@ -2483,6 +2704,61 @@ static int bnxt_alloc_ring(struct bnxt *bp, struct bnxt_ring_mem_info *rmem) return 0; } +static void bnxt_free_tpa_info(struct bnxt *bp) +{ + int i; + + for (i = 0; i < bp->rx_nr_rings; i++) { + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + + kfree(rxr->rx_tpa_idx_map); + rxr->rx_tpa_idx_map = NULL; + if (rxr->rx_tpa) { + kfree(rxr->rx_tpa[0].agg_arr); + rxr->rx_tpa[0].agg_arr = NULL; + } + kfree(rxr->rx_tpa); + rxr->rx_tpa = NULL; + } +} + +static int bnxt_alloc_tpa_info(struct bnxt *bp) +{ + int i, j, total_aggs = 0; + + bp->max_tpa = MAX_TPA; + if (bp->flags & BNXT_FLAG_CHIP_P5) { + if (!bp->max_tpa_v2) + return 0; + bp->max_tpa = max_t(u16, bp->max_tpa_v2, MAX_TPA_P5); + total_aggs = bp->max_tpa * MAX_SKB_FRAGS; + } + + for (i = 0; i < bp->rx_nr_rings; i++) { + struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; + struct rx_agg_cmp *agg; + + rxr->rx_tpa = kcalloc(bp->max_tpa, sizeof(struct bnxt_tpa_info), + GFP_KERNEL); + if (!rxr->rx_tpa) + return -ENOMEM; + + if (!(bp->flags & BNXT_FLAG_CHIP_P5)) + continue; + agg = kcalloc(total_aggs, sizeof(*agg), GFP_KERNEL); + rxr->rx_tpa[0].agg_arr = agg; + if (!agg) + return -ENOMEM; + for (j = 1; j < bp->max_tpa; j++) + rxr->rx_tpa[j].agg_arr = agg + j * MAX_SKB_FRAGS; + rxr->rx_tpa_idx_map = kzalloc(sizeof(*rxr->rx_tpa_idx_map), + GFP_KERNEL); + if (!rxr->rx_tpa_idx_map) + return -ENOMEM; + } + return 0; +} + static void bnxt_free_rx_rings(struct bnxt *bp) { int i; @@ -2490,6 +2766,7 @@ static void bnxt_free_rx_rings(struct bnxt *bp) if (!bp->rx_ring) return; + bnxt_free_tpa_info(bp); for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; struct bnxt_ring_struct *ring; @@ -2503,9 +2780,6 @@ static void bnxt_free_rx_rings(struct bnxt *bp) page_pool_destroy(rxr->page_pool); rxr->page_pool = NULL; - kfree(rxr->rx_tpa); - rxr->rx_tpa = NULL; - kfree(rxr->rx_agg_bmap); rxr->rx_agg_bmap = NULL; @@ -2539,7 +2813,7 @@ static int bnxt_alloc_rx_page_pool(struct bnxt *bp, static int bnxt_alloc_rx_rings(struct bnxt *bp) { - int i, rc, agg_rings = 0, tpa_rings = 0; + int i, rc = 0, agg_rings = 0; if (!bp->rx_ring) return -ENOMEM; @@ -2547,9 +2821,6 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp) if (bp->flags & BNXT_FLAG_AGG_RINGS) agg_rings = 1; - if (bp->flags & BNXT_FLAG_TPA) - tpa_rings = 1; - for (i = 0; i < bp->rx_nr_rings; i++) { struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i]; struct bnxt_ring_struct *ring; @@ -2591,17 +2862,11 @@ static int bnxt_alloc_rx_rings(struct bnxt *bp) rxr->rx_agg_bmap = kzalloc(mem_size, GFP_KERNEL); if (!rxr->rx_agg_bmap) return -ENOMEM; - - if (tpa_rings) { - rxr->rx_tpa = kcalloc(MAX_TPA, - sizeof(struct bnxt_tpa_info), - GFP_KERNEL); - if (!rxr->rx_tpa) - return -ENOMEM; - } } } - return 0; + if (bp->flags & BNXT_FLAG_TPA) + rc = bnxt_alloc_tpa_info(bp); + return rc; } static void bnxt_free_tx_rings(struct bnxt *bp) @@ -2953,7 +3218,7 @@ static int bnxt_init_one_rx_ring(struct bnxt *bp, int ring_nr) u8 *data; dma_addr_t mapping; - for (i = 0; i < MAX_TPA; i++) { + for (i = 0; i < bp->max_tpa; i++) { data = __bnxt_alloc_rx_data(bp, &mapping, GFP_KERNEL); if (!data) @@ -3376,6 +3641,9 @@ static int bnxt_alloc_kong_hwrm_resources(struct bnxt *bp) { struct pci_dev *pdev = bp->pdev; + if (bp->hwrm_cmd_kong_resp_addr) + return 0; + bp->hwrm_cmd_kong_resp_addr = dma_alloc_coherent(&pdev->dev, PAGE_SIZE, &bp->hwrm_cmd_kong_resp_dma_addr, @@ -3415,6 +3683,9 @@ static int bnxt_alloc_hwrm_short_cmd_req(struct bnxt *bp) { struct pci_dev *pdev = bp->pdev; + if (bp->hwrm_short_cmd_req_addr) + return 0; + bp->hwrm_short_cmd_req_addr = dma_alloc_coherent(&pdev->dev, bp->hwrm_max_ext_req_len, &bp->hwrm_short_cmd_req_dma_addr, @@ -3468,7 +3739,7 @@ static void bnxt_free_ring_stats(struct bnxt *bp) if (!bp->bnapi) return; - size = sizeof(struct ctx_hw_stats); + size = bp->hw_ring_stats_size; for (i = 0; i < bp->cp_nr_rings; i++) { struct bnxt_napi *bnapi = bp->bnapi[i]; @@ -3487,7 +3758,7 @@ static int bnxt_alloc_stats(struct bnxt *bp) u32 size, i; struct pci_dev *pdev = bp->pdev; - size = sizeof(struct ctx_hw_stats); + size = bp->hw_ring_stats_size; for (i = 0; i < bp->cp_nr_rings; i++) { struct bnxt_napi *bnapi = bp->bnapi[i]; @@ -3869,6 +4140,32 @@ void bnxt_hwrm_cmd_hdr_init(struct bnxt *bp, void *request, u16 req_type, req->resp_addr = cpu_to_le64(bp->hwrm_cmd_resp_dma_addr); } +static int bnxt_hwrm_to_stderr(u32 hwrm_err) +{ + switch (hwrm_err) { + case HWRM_ERR_CODE_SUCCESS: + return 0; + case HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED: + return -EACCES; + case HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR: + return -ENOSPC; + case HWRM_ERR_CODE_INVALID_PARAMS: + case HWRM_ERR_CODE_INVALID_FLAGS: + case HWRM_ERR_CODE_INVALID_ENABLES: + case HWRM_ERR_CODE_UNSUPPORTED_TLV: + case HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR: + return -EINVAL; + case HWRM_ERR_CODE_NO_BUFFER: + return -ENOMEM; + case HWRM_ERR_CODE_HOT_RESET_PROGRESS: + return -EAGAIN; + case HWRM_ERR_CODE_CMD_NOT_SUPPORTED: + return -EOPNOTSUPP; + default: + return -EIO; + } +} + static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, int timeout, bool silent) { @@ -3886,6 +4183,9 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, u32 bar_offset = BNXT_GRCPF_REG_CHIMP_COMM; u16 dst = BNXT_HWRM_CHNL_CHIMP; + if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + return -EBUSY; + if (msg_len > BNXT_HWRM_MAX_REQ_LEN) { if (msg_len > bp->hwrm_max_ext_req_len || !bp->hwrm_short_cmd_req_addr) @@ -3950,6 +4250,9 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, /* Ring channel doorbell */ writel(1, bp->bar0 + doorbell_offset); + if (!pci_is_enabled(bp->pdev)) + return 0; + if (!timeout) timeout = DFLT_HWRM_CMD_TIMEOUT; /* convert timeout to usec */ @@ -3981,9 +4284,10 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, } if (bp->hwrm_intr_seq_id != (u16)~seq_id) { - netdev_err(bp->dev, "Resp cmpl intr err msg: 0x%x\n", - le16_to_cpu(req->req_type)); - return -1; + if (!silent) + netdev_err(bp->dev, "Resp cmpl intr err msg: 0x%x\n", + le16_to_cpu(req->req_type)); + return -EBUSY; } len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >> HWRM_RESP_LEN_SFT; @@ -4007,11 +4311,12 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, } if (i >= tmo_count) { - netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d\n", - HWRM_TOTAL_TIMEOUT(i), - le16_to_cpu(req->req_type), - le16_to_cpu(req->seq_id), len); - return -1; + if (!silent) + netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d\n", + HWRM_TOTAL_TIMEOUT(i), + le16_to_cpu(req->req_type), + le16_to_cpu(req->seq_id), len); + return -EBUSY; } /* Last byte of resp contains valid bit */ @@ -4025,11 +4330,13 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, } if (j >= HWRM_VALID_BIT_DELAY_USEC) { - netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d v:%d\n", - HWRM_TOTAL_TIMEOUT(i), - le16_to_cpu(req->req_type), - le16_to_cpu(req->seq_id), len, *valid); - return -1; + if (!silent) + netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d v:%d\n", + HWRM_TOTAL_TIMEOUT(i), + le16_to_cpu(req->req_type), + le16_to_cpu(req->seq_id), len, + *valid); + return -EBUSY; } } @@ -4043,7 +4350,7 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, netdev_err(bp->dev, "hwrm req_type 0x%x seq id 0x%x error 0x%x\n", le16_to_cpu(resp->req_type), le16_to_cpu(resp->seq_id), rc); - return rc; + return bnxt_hwrm_to_stderr(rc); } int _hwrm_send_message(struct bnxt *bp, void *msg, u32 msg_len, int timeout) @@ -4092,9 +4399,14 @@ int bnxt_hwrm_func_rgtr_async_events(struct bnxt *bp, unsigned long *bmap, cpu_to_le32(FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD); memset(async_events_bmap, 0, sizeof(async_events_bmap)); - for (i = 0; i < ARRAY_SIZE(bnxt_async_events_arr); i++) - __set_bit(bnxt_async_events_arr[i], async_events_bmap); + for (i = 0; i < ARRAY_SIZE(bnxt_async_events_arr); i++) { + u16 event_id = bnxt_async_events_arr[i]; + if (event_id == ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY && + !(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)) + continue; + __set_bit(bnxt_async_events_arr[i], async_events_bmap); + } if (bmap && bmap_size) { for (i = 0; i < bmap_size; i++) { if (test_bit(i, bmap)) @@ -4112,6 +4424,7 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp) { struct hwrm_func_drv_rgtr_output *resp = bp->hwrm_cmd_resp_addr; struct hwrm_func_drv_rgtr_input req = {0}; + u32 flags; int rc; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_DRV_RGTR, -1, -1); @@ -4121,7 +4434,11 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp) FUNC_DRV_RGTR_REQ_ENABLES_VER); req.os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX); - req.flags = cpu_to_le32(FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE); + flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE | + FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT; + if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) + flags |= FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT; + req.flags = cpu_to_le32(flags); req.ver_maj_8b = DRV_VER_MAJ; req.ver_min_8b = DRV_VER_MIN; req.ver_upd_8b = DRV_VER_UPD; @@ -4156,10 +4473,8 @@ static int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp) mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - rc = -EIO; - else if (resp->flags & - cpu_to_le32(FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED)) + if (!rc && (resp->flags & + cpu_to_le32(FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED))) bp->fw_cap |= BNXT_FW_CAP_IF_CHANGE; mutex_unlock(&bp->hwrm_cmd_lock); return rc; @@ -4414,6 +4729,7 @@ static int bnxt_hwrm_clear_vnic_filter(struct bnxt *bp) static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags) { struct bnxt_vnic_info *vnic = &bp->vnic_info[vnic_id]; + u16 max_aggs = VNIC_TPA_CFG_REQ_MAX_AGGS_MAX; struct hwrm_vnic_tpa_cfg_input req = {0}; if (vnic->fw_vnic_id == INVALID_HW_RING_ID) @@ -4453,9 +4769,14 @@ static int bnxt_hwrm_vnic_set_tpa(struct bnxt *bp, u16 vnic_id, u32 tpa_flags) nsegs = (MAX_SKB_FRAGS - n) / n; } - segs = ilog2(nsegs); + if (bp->flags & BNXT_FLAG_CHIP_P5) { + segs = MAX_TPA_SEGS_P5; + max_aggs = bp->max_tpa; + } else { + segs = ilog2(nsegs); + } req.max_agg_segs = cpu_to_le16(segs); - req.max_aggs = cpu_to_le16(VNIC_TPA_CFG_REQ_MAX_AGGS_MAX); + req.max_aggs = cpu_to_le16(max_aggs); req.min_agg_len = cpu_to_le32(512); } @@ -4576,7 +4897,7 @@ static int bnxt_hwrm_vnic_set_rss_p5(struct bnxt *bp, u16 vnic_id, bool set_rss) } rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - return -EIO; + return rc; } return 0; } @@ -4739,8 +5060,6 @@ static int bnxt_hwrm_vnic_free_one(struct bnxt *bp, u16 vnic_id) cpu_to_le32(bp->vnic_info[vnic_id].fw_vnic_id); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - return rc; bp->vnic_info[vnic_id].fw_vnic_id = INVALID_HW_RING_ID; } return rc; @@ -4800,6 +5119,8 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp) struct hwrm_vnic_qcaps_input req = {0}; int rc; + bp->hw_ring_stats_size = sizeof(struct ctx_hw_stats); + bp->flags &= ~(BNXT_FLAG_NEW_RSS_CAP | BNXT_FLAG_ROCE_MIRROR_CAP); if (bp->hwrm_spec_code < 0x10600) return 0; @@ -4815,6 +5136,10 @@ static int bnxt_hwrm_vnic_qcaps(struct bnxt *bp) if (flags & VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP) bp->flags |= BNXT_FLAG_ROCE_MIRROR_CAP; + bp->max_tpa_v2 = le16_to_cpu(resp->max_aggs_supported); + if (bp->max_tpa_v2) + bp->hw_ring_stats_size = + sizeof(struct ctx_hw_stats_ext); } mutex_unlock(&bp->hwrm_cmd_lock); return rc; @@ -4874,8 +5199,6 @@ static int bnxt_hwrm_ring_grp_free(struct bnxt *bp) rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - break; bp->grp_info[i].fw_grp_id = INVALID_HW_RING_ID; } mutex_unlock(&bp->hwrm_cmd_lock); @@ -5194,6 +5517,9 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp, struct hwrm_ring_free_output *resp = bp->hwrm_cmd_resp_addr; u16 error_code; + if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + return 0; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_RING_FREE, cmpl_ring_id, -1); req.ring_type = ring_type; req.ring_id = cpu_to_le16(ring->fw_ring_id); @@ -5331,7 +5657,7 @@ static int bnxt_hwrm_get_rings(struct bnxt *bp) rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) { mutex_unlock(&bp->hwrm_cmd_lock); - return -EIO; + return rc; } hw_resc->resv_tx_rings = le16_to_cpu(resp->alloc_tx_rings); @@ -5495,7 +5821,7 @@ bnxt_hwrm_reserve_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings, rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - return -ENOMEM; + return rc; if (bp->hwrm_spec_code < 0x10601) bp->hw_resc.resv_tx_rings = tx_rings; @@ -5520,7 +5846,7 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings, cp_rings, stats, vnics); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) - return -ENOMEM; + return rc; rc = bnxt_hwrm_get_rings(bp); return rc; @@ -5701,9 +6027,7 @@ static int bnxt_hwrm_check_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings, req.flags = cpu_to_le32(flags); rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - return -ENOMEM; - return 0; + return rc; } static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings, @@ -5731,9 +6055,7 @@ static int bnxt_hwrm_check_pf_rings(struct bnxt *bp, int tx_rings, int rx_rings, req.flags = cpu_to_le32(flags); rc = hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - return -ENOMEM; - return 0; + return rc; } static int bnxt_hwrm_check_rings(struct bnxt *bp, int tx_rings, int rx_rings, @@ -5995,8 +6317,6 @@ static int bnxt_hwrm_stat_ctx_free(struct bnxt *bp) rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - break; cpr->hw_stats_ctx_id = INVALID_STATS_CTX_ID; } @@ -6016,6 +6336,7 @@ static int bnxt_hwrm_stat_ctx_alloc(struct bnxt *bp) bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_STAT_CTX_ALLOC, -1, -1); + req.stats_dma_length = cpu_to_le16(bp->hw_ring_stats_size); req.update_period_ms = cpu_to_le32(bp->stats_coal_ticks / 1000); mutex_lock(&bp->hwrm_cmd_lock); @@ -6057,6 +6378,8 @@ static int bnxt_hwrm_func_qcfg(struct bnxt *bp) struct bnxt_vf_info *vf = &bp->vf; vf->vlan = le16_to_cpu(resp->vlan) & VLAN_VID_MASK; + } else { + bp->pf.registered_vfs = le16_to_cpu(resp->registered_vfs); } #endif flags = le16_to_cpu(resp->flags); @@ -6292,8 +6615,6 @@ static int bnxt_hwrm_func_backing_store_cfg(struct bnxt *bp, u32 enables) } req.flags = cpu_to_le32(flags); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - rc = -EIO; return rc; } @@ -6555,10 +6876,8 @@ int bnxt_hwrm_func_resc_qcaps(struct bnxt *bp, bool all) mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message_silent(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) { - rc = -EIO; + if (rc) goto hwrm_func_resc_qcaps_exit; - } hw_resc->max_tx_sch_inputs = le16_to_cpu(resp->max_tx_scheduler_inputs); if (!all) @@ -6626,6 +6945,10 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) bp->fw_cap |= BNXT_FW_CAP_PCIE_STATS_SUPPORTED; if (flags & FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED) bp->fw_cap |= BNXT_FW_CAP_EXT_STATS_SUPPORTED; + if (flags & FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE) + bp->fw_cap |= BNXT_FW_CAP_ERROR_RECOVERY; + if (flags & FUNC_QCAPS_RESP_FLAGS_ERR_RECOVER_RELOAD) + bp->fw_cap |= BNXT_FW_CAP_ERR_RECOVER_RELOAD; bp->tx_push_thresh = 0; if (flags & FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED) @@ -6657,6 +6980,7 @@ static int __bnxt_hwrm_func_qcaps(struct bnxt *bp) pf->max_tx_wm_flows = le32_to_cpu(resp->max_tx_wm_flows); pf->max_rx_em_flows = le32_to_cpu(resp->max_rx_em_flows); pf->max_rx_wm_flows = le32_to_cpu(resp->max_rx_wm_flows); + bp->flags &= ~BNXT_FLAG_WOL_CAP; if (flags & FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED) bp->flags |= BNXT_FLAG_WOL_CAP; } else { @@ -6726,6 +7050,103 @@ hwrm_cfa_adv_qcaps_exit: return rc; } +static int bnxt_map_fw_health_regs(struct bnxt *bp) +{ + struct bnxt_fw_health *fw_health = bp->fw_health; + u32 reg_base = 0xffffffff; + int i; + + /* Only pre-map the monitoring GRC registers using window 3 */ + for (i = 0; i < 4; i++) { + u32 reg = fw_health->regs[i]; + + if (BNXT_FW_HEALTH_REG_TYPE(reg) != BNXT_FW_HEALTH_REG_TYPE_GRC) + continue; + if (reg_base == 0xffffffff) + reg_base = reg & BNXT_GRC_BASE_MASK; + if ((reg & BNXT_GRC_BASE_MASK) != reg_base) + return -ERANGE; + fw_health->mapped_regs[i] = BNXT_FW_HEALTH_WIN_BASE + + (reg & BNXT_GRC_OFFSET_MASK); + } + if (reg_base == 0xffffffff) + return 0; + + writel(reg_base, bp->bar0 + BNXT_GRCPF_REG_WINDOW_BASE_OUT + + BNXT_FW_HEALTH_WIN_MAP_OFF); + return 0; +} + +static int bnxt_hwrm_error_recovery_qcfg(struct bnxt *bp) +{ + struct hwrm_error_recovery_qcfg_output *resp = bp->hwrm_cmd_resp_addr; + struct bnxt_fw_health *fw_health = bp->fw_health; + struct hwrm_error_recovery_qcfg_input req = {0}; + int rc, i; + + if (!(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)) + return 0; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_ERROR_RECOVERY_QCFG, -1, -1); + mutex_lock(&bp->hwrm_cmd_lock); + rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + goto err_recovery_out; + if (!fw_health) { + fw_health = kzalloc(sizeof(*fw_health), GFP_KERNEL); + bp->fw_health = fw_health; + if (!fw_health) { + rc = -ENOMEM; + goto err_recovery_out; + } + } + fw_health->flags = le32_to_cpu(resp->flags); + if ((fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) && + !(bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL)) { + rc = -EINVAL; + goto err_recovery_out; + } + fw_health->polling_dsecs = le32_to_cpu(resp->driver_polling_freq); + fw_health->master_func_wait_dsecs = + le32_to_cpu(resp->master_func_wait_period); + fw_health->normal_func_wait_dsecs = + le32_to_cpu(resp->normal_func_wait_period); + fw_health->post_reset_wait_dsecs = + le32_to_cpu(resp->master_func_wait_period_after_reset); + fw_health->post_reset_max_wait_dsecs = + le32_to_cpu(resp->max_bailout_time_after_reset); + fw_health->regs[BNXT_FW_HEALTH_REG] = + le32_to_cpu(resp->fw_health_status_reg); + fw_health->regs[BNXT_FW_HEARTBEAT_REG] = + le32_to_cpu(resp->fw_heartbeat_reg); + fw_health->regs[BNXT_FW_RESET_CNT_REG] = + le32_to_cpu(resp->fw_reset_cnt_reg); + fw_health->regs[BNXT_FW_RESET_INPROG_REG] = + le32_to_cpu(resp->reset_inprogress_reg); + fw_health->fw_reset_inprog_reg_mask = + le32_to_cpu(resp->reset_inprogress_reg_mask); + fw_health->fw_reset_seq_cnt = resp->reg_array_cnt; + if (fw_health->fw_reset_seq_cnt >= 16) { + rc = -EINVAL; + goto err_recovery_out; + } + for (i = 0; i < fw_health->fw_reset_seq_cnt; i++) { + fw_health->fw_reset_seq_regs[i] = + le32_to_cpu(resp->reset_reg[i]); + fw_health->fw_reset_seq_vals[i] = + le32_to_cpu(resp->reset_reg_val[i]); + fw_health->fw_reset_seq_delay_msec[i] = + resp->delay_after_reset[i]; + } +err_recovery_out: + mutex_unlock(&bp->hwrm_cmd_lock); + if (!rc) + rc = bnxt_map_fw_health_regs(bp); + if (rc) + bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY; + return rc; +} + static int bnxt_hwrm_func_reset(struct bnxt *bp) { struct hwrm_func_reset_input req = {0}; @@ -6785,20 +7206,30 @@ qportcfg_exit: return rc; } -static int bnxt_hwrm_ver_get(struct bnxt *bp) +static int __bnxt_hwrm_ver_get(struct bnxt *bp, bool silent) { - int rc; struct hwrm_ver_get_input req = {0}; - struct hwrm_ver_get_output *resp = bp->hwrm_cmd_resp_addr; - u32 dev_caps_cfg; + int rc; - bp->hwrm_max_req_len = HWRM_MAX_REQ_LEN; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_VER_GET, -1, -1); req.hwrm_intf_maj = HWRM_VERSION_MAJOR; req.hwrm_intf_min = HWRM_VERSION_MINOR; req.hwrm_intf_upd = HWRM_VERSION_UPDATE; + + rc = bnxt_hwrm_do_send_msg(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT, + silent); + return rc; +} + +static int bnxt_hwrm_ver_get(struct bnxt *bp) +{ + struct hwrm_ver_get_output *resp = bp->hwrm_cmd_resp_addr; + u32 dev_caps_cfg; + int rc; + + bp->hwrm_max_req_len = HWRM_MAX_REQ_LEN; mutex_lock(&bp->hwrm_cmd_lock); - rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + rc = __bnxt_hwrm_ver_get(bp, false); if (rc) goto hwrm_ver_get_exit; @@ -7001,6 +7432,8 @@ static int bnxt_set_tpa(struct bnxt *bp, bool set_tpa) if (set_tpa) tpa_flags = bp->flags & BNXT_FLAG_TPA; + else if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + return 0; for (i = 0; i < bp->nr_vnics; i++) { rc = bnxt_hwrm_vnic_set_tpa(bp, i, tpa_flags); if (rc) { @@ -7066,8 +7499,6 @@ static int bnxt_hwrm_set_br_mode(struct bnxt *bp, u16 br_mode) else return -EINVAL; rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - rc = -EIO; return rc; } @@ -7087,8 +7518,6 @@ static int bnxt_hwrm_set_cache_line_size(struct bnxt *bp, int size) req.options = FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128; rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - rc = -EIO; return rc; } @@ -7971,6 +8400,9 @@ static int bnxt_hwrm_phy_qcaps(struct bnxt *bp) struct hwrm_port_phy_qcaps_output *resp = bp->hwrm_cmd_resp_addr; struct bnxt_link_info *link_info = &bp->link_info; + bp->flags &= ~BNXT_FLAG_EEE_CAP; + if (bp->test_info) + bp->test_info->flags &= ~BNXT_TEST_FL_EXT_LPBK; if (bp->hwrm_spec_code < 0x10201) return 0; @@ -8292,11 +8724,14 @@ static int bnxt_hwrm_shutdown_link(struct bnxt *bp) return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); } +static int bnxt_fw_init_one(struct bnxt *bp); + static int bnxt_hwrm_if_change(struct bnxt *bp, bool up) { struct hwrm_func_drv_if_change_output *resp = bp->hwrm_cmd_resp_addr; struct hwrm_func_drv_if_change_input req = {0}; - bool resc_reinit = false; + bool resc_reinit = false, fw_reset = false; + u32 flags = 0; int rc; if (!(bp->fw_cap & BNXT_FW_CAP_IF_CHANGE)) @@ -8307,26 +8742,57 @@ static int bnxt_hwrm_if_change(struct bnxt *bp, bool up) req.flags = cpu_to_le32(FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP); mutex_lock(&bp->hwrm_cmd_lock); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (!rc && (resp->flags & - cpu_to_le32(FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE))) - resc_reinit = true; + if (!rc) + flags = le32_to_cpu(resp->flags); mutex_unlock(&bp->hwrm_cmd_lock); + if (rc) + return rc; - if (up && resc_reinit && BNXT_NEW_RM(bp)) { - struct bnxt_hw_resc *hw_resc = &bp->hw_resc; + if (!up) + return 0; - rc = bnxt_hwrm_func_resc_qcaps(bp, true); - hw_resc->resv_cp_rings = 0; - hw_resc->resv_stat_ctxs = 0; - hw_resc->resv_irqs = 0; - hw_resc->resv_tx_rings = 0; - hw_resc->resv_rx_rings = 0; - hw_resc->resv_hw_ring_grps = 0; - hw_resc->resv_vnics = 0; - bp->tx_nr_rings = 0; - bp->rx_nr_rings = 0; + if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE) + resc_reinit = true; + if (flags & FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE) + fw_reset = true; + + if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state) && !fw_reset) { + netdev_err(bp->dev, "RESET_DONE not set during FW reset.\n"); + return -ENODEV; } - return rc; + if (resc_reinit || fw_reset) { + if (fw_reset) { + rc = bnxt_fw_init_one(bp); + if (rc) { + set_bit(BNXT_STATE_ABORT_ERR, &bp->state); + return rc; + } + bnxt_clear_int_mode(bp); + rc = bnxt_init_int_mode(bp); + if (rc) { + netdev_err(bp->dev, "init int mode failed\n"); + return rc; + } + set_bit(BNXT_STATE_FW_RESET_DET, &bp->state); + } + if (BNXT_NEW_RM(bp)) { + struct bnxt_hw_resc *hw_resc = &bp->hw_resc; + + rc = bnxt_hwrm_func_resc_qcaps(bp, true); + hw_resc->resv_cp_rings = 0; + hw_resc->resv_stat_ctxs = 0; + hw_resc->resv_irqs = 0; + hw_resc->resv_tx_rings = 0; + hw_resc->resv_rx_rings = 0; + hw_resc->resv_hw_ring_grps = 0; + hw_resc->resv_vnics = 0; + if (!fw_reset) { + bp->tx_nr_rings = 0; + bp->rx_nr_rings = 0; + } + } + } + return 0; } static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp) @@ -8336,6 +8802,7 @@ static int bnxt_hwrm_port_led_qcaps(struct bnxt *bp) struct bnxt_pf_info *pf = &bp->pf; int rc; + bp->num_leds = 0; if (BNXT_VF(bp) || bp->hwrm_spec_code < 0x10601) return 0; @@ -8430,6 +8897,7 @@ static void bnxt_get_wol_settings(struct bnxt *bp) { u16 handle = 0; + bp->wol = 0; if (!BNXT_PF(bp) || !(bp->flags & BNXT_FLAG_WOL_CAP)) return; @@ -8476,6 +8944,9 @@ static void bnxt_hwmon_open(struct bnxt *bp) { struct pci_dev *pdev = bp->pdev; + if (bp->hwmon_dev) + return; + bp->hwmon_dev = hwmon_device_register_with_groups(&pdev->dev, DRV_MODULE_NAME, bp, bnxt_groups); @@ -8741,12 +9212,28 @@ static int bnxt_open(struct net_device *dev) struct bnxt *bp = netdev_priv(dev); int rc; - bnxt_hwrm_if_change(bp, true); - rc = __bnxt_open_nic(bp, true, true); + if (test_bit(BNXT_STATE_ABORT_ERR, &bp->state)) { + netdev_err(bp->dev, "A previous firmware reset did not complete, aborting\n"); + return -ENODEV; + } + + rc = bnxt_hwrm_if_change(bp, true); if (rc) + return rc; + rc = __bnxt_open_nic(bp, true, true); + if (rc) { bnxt_hwrm_if_change(bp, false); + } else { + if (test_and_clear_bit(BNXT_STATE_FW_RESET_DET, &bp->state) && + BNXT_PF(bp)) { + struct bnxt_pf_info *pf = &bp->pf; + int n = pf->active_vfs; - bnxt_hwmon_open(bp); + if (n) + bnxt_cfg_hw_sriov(bp, &n, true); + } + bnxt_hwmon_open(bp); + } return rc; } @@ -8783,6 +9270,10 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bnxt_debug_dev_exit(bp); bnxt_disable_napi(bp); del_timer_sync(&bp->timer); + if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state) && + pci_is_enabled(bp->pdev)) + pci_disable_device(bp->pdev); + bnxt_free_skbs(bp); /* Save ring stats before shutdown */ @@ -8799,6 +9290,18 @@ int bnxt_close_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) { int rc = 0; + if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { + /* If we get here, it means firmware reset is in progress + * while we are trying to close. We can safely proceed with + * the close because we are holding rtnl_lock(). Some firmware + * messages may fail as we proceed to close. We set the + * ABORT_ERR flag here so that the FW reset thread will later + * abort when it gets the rtnl_lock() and sees the flag. + */ + netdev_warn(bp->dev, "FW reset in progress during close, FW reset will be aborted\n"); + set_bit(BNXT_STATE_ABORT_ERR, &bp->state); + } + #ifdef CONFIG_BNXT_SRIOV if (bp->sriov_cfg) { rc = wait_event_interruptible_timeout(bp->sriov_cfg_wait, @@ -9056,14 +9559,16 @@ static bool bnxt_uc_list_updated(struct bnxt *bp) static void bnxt_set_rx_mode(struct net_device *dev) { struct bnxt *bp = netdev_priv(dev); - struct bnxt_vnic_info *vnic = &bp->vnic_info[0]; - u32 mask = vnic->rx_mask; + struct bnxt_vnic_info *vnic; bool mc_update = false; bool uc_update; + u32 mask; - if (!netif_running(dev)) + if (!test_bit(BNXT_STATE_OPEN, &bp->state)) return; + vnic = &bp->vnic_info[0]; + mask = vnic->rx_mask; mask &= ~(CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS | CFA_L2_SET_RX_MASK_REQ_MASK_MCAST | CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST | @@ -9306,7 +9811,8 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) if (changes & BNXT_FLAG_TPA) { update_tpa = true; if ((bp->flags & BNXT_FLAG_TPA) == 0 || - (flags & BNXT_FLAG_TPA) == 0) + (flags & BNXT_FLAG_TPA) == 0 || + (bp->flags & BNXT_FLAG_CHIP_P5)) re_init = true; } @@ -9316,9 +9822,8 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) if (flags != bp->flags) { u32 old_flags = bp->flags; - bp->flags = flags; - if (!test_bit(BNXT_STATE_OPEN, &bp->state)) { + bp->flags = flags; if (update_tpa) bnxt_set_ring_params(bp); return rc; @@ -9326,12 +9831,14 @@ static int bnxt_set_features(struct net_device *dev, netdev_features_t features) if (re_init) { bnxt_close_nic(bp, false, false); + bp->flags = flags; if (update_tpa) bnxt_set_ring_params(bp); return bnxt_open_nic(bp, false, false); } if (update_tpa) { + bp->flags = flags; rc = bnxt_set_tpa(bp, (flags & BNXT_FLAG_TPA) ? true : false); @@ -9438,6 +9945,38 @@ static void bnxt_tx_timeout(struct net_device *dev) bnxt_queue_sp_work(bp); } +static void bnxt_fw_health_check(struct bnxt *bp) +{ + struct bnxt_fw_health *fw_health = bp->fw_health; + u32 val; + + if (!fw_health || !fw_health->enabled || + test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) + return; + + if (fw_health->tmr_counter) { + fw_health->tmr_counter--; + return; + } + + val = bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG); + if (val == fw_health->last_fw_heartbeat) + goto fw_reset; + + fw_health->last_fw_heartbeat = val; + + val = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); + if (val != fw_health->last_fw_reset_cnt) + goto fw_reset; + + fw_health->tmr_counter = fw_health->tmr_multiplier; + return; + +fw_reset: + set_bit(BNXT_FW_EXCEPTION_SP_EVENT, &bp->sp_event); + bnxt_queue_sp_work(bp); +} + static void bnxt_timer(struct timer_list *t) { struct bnxt *bp = from_timer(bp, t, timer); @@ -9449,6 +9988,9 @@ static void bnxt_timer(struct timer_list *t) if (atomic_read(&bp->intr_sem) != 0) goto bnxt_restart_timer; + if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY) + bnxt_fw_health_check(bp); + if (bp->link_info.link_up && (bp->flags & BNXT_FLAG_PORT_STATS) && bp->stats_coal_ticks) { set_bit(BNXT_PERIODIC_STATS_SP_EVENT, &bp->sp_event); @@ -9504,6 +10046,138 @@ static void bnxt_reset(struct bnxt *bp, bool silent) bnxt_rtnl_unlock_sp(bp); } +static void bnxt_fw_reset_close(struct bnxt *bp) +{ + __bnxt_close_nic(bp, true, false); + bnxt_ulp_irq_stop(bp); + bnxt_clear_int_mode(bp); + bnxt_hwrm_func_drv_unrgtr(bp); + bnxt_free_ctx_mem(bp); + kfree(bp->ctx); + bp->ctx = NULL; +} + +static bool is_bnxt_fw_ok(struct bnxt *bp) +{ + struct bnxt_fw_health *fw_health = bp->fw_health; + bool no_heartbeat = false, has_reset = false; + u32 val; + + val = bnxt_fw_health_readl(bp, BNXT_FW_HEARTBEAT_REG); + if (val == fw_health->last_fw_heartbeat) + no_heartbeat = true; + + val = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); + if (val != fw_health->last_fw_reset_cnt) + has_reset = true; + + if (!no_heartbeat && has_reset) + return true; + + return false; +} + +/* rtnl_lock is acquired before calling this function */ +static void bnxt_force_fw_reset(struct bnxt *bp) +{ + struct bnxt_fw_health *fw_health = bp->fw_health; + u32 wait_dsecs; + + if (!test_bit(BNXT_STATE_OPEN, &bp->state) || + test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) + return; + + set_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + bnxt_fw_reset_close(bp); + wait_dsecs = fw_health->master_func_wait_dsecs; + if (fw_health->master) { + if (fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) + wait_dsecs = 0; + bp->fw_reset_state = BNXT_FW_RESET_STATE_RESET_FW; + } else { + bp->fw_reset_timestamp = jiffies + wait_dsecs * HZ / 10; + wait_dsecs = fw_health->normal_func_wait_dsecs; + bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV; + } + + bp->fw_reset_min_dsecs = fw_health->post_reset_wait_dsecs; + bp->fw_reset_max_dsecs = fw_health->post_reset_max_wait_dsecs; + bnxt_queue_fw_reset_work(bp, wait_dsecs * HZ / 10); +} + +void bnxt_fw_exception(struct bnxt *bp) +{ + set_bit(BNXT_STATE_FW_FATAL_COND, &bp->state); + bnxt_rtnl_lock_sp(bp); + bnxt_force_fw_reset(bp); + bnxt_rtnl_unlock_sp(bp); +} + +/* Returns the number of registered VFs, or 1 if VF configuration is pending, or + * < 0 on error. + */ +static int bnxt_get_registered_vfs(struct bnxt *bp) +{ +#ifdef CONFIG_BNXT_SRIOV + int rc; + + if (!BNXT_PF(bp)) + return 0; + + rc = bnxt_hwrm_func_qcfg(bp); + if (rc) { + netdev_err(bp->dev, "func_qcfg cmd failed, rc = %d\n", rc); + return rc; + } + if (bp->pf.registered_vfs) + return bp->pf.registered_vfs; + if (bp->sriov_cfg) + return 1; +#endif + return 0; +} + +void bnxt_fw_reset(struct bnxt *bp) +{ + bnxt_rtnl_lock_sp(bp); + if (test_bit(BNXT_STATE_OPEN, &bp->state) && + !test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { + int n = 0, tmo; + + set_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + if (bp->pf.active_vfs && + !test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) + n = bnxt_get_registered_vfs(bp); + if (n < 0) { + netdev_err(bp->dev, "Firmware reset aborted, rc = %d\n", + n); + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + dev_close(bp->dev); + goto fw_reset_exit; + } else if (n > 0) { + u16 vf_tmo_dsecs = n * 10; + + if (bp->fw_reset_max_dsecs < vf_tmo_dsecs) + bp->fw_reset_max_dsecs = vf_tmo_dsecs; + bp->fw_reset_state = + BNXT_FW_RESET_STATE_POLL_VF; + bnxt_queue_fw_reset_work(bp, HZ / 10); + goto fw_reset_exit; + } + bnxt_fw_reset_close(bp); + if (bp->fw_cap & BNXT_FW_CAP_ERR_RECOVER_RELOAD) { + bp->fw_reset_state = BNXT_FW_RESET_STATE_POLL_FW_DOWN; + tmo = HZ / 10; + } else { + bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV; + tmo = bp->fw_reset_min_dsecs * HZ / 10; + } + bnxt_queue_fw_reset_work(bp, tmo); + } +fw_reset_exit: + bnxt_rtnl_unlock_sp(bp); +} + static void bnxt_chk_missed_irq(struct bnxt *bp) { int i; @@ -9634,6 +10308,15 @@ static void bnxt_sp_task(struct work_struct *work) if (test_and_clear_bit(BNXT_RESET_TASK_SILENT_SP_EVENT, &bp->sp_event)) bnxt_reset(bp, true); + if (test_and_clear_bit(BNXT_FW_RESET_NOTIFY_SP_EVENT, &bp->sp_event)) + bnxt_devlink_health_report(bp, BNXT_FW_RESET_NOTIFY_SP_EVENT); + + if (test_and_clear_bit(BNXT_FW_EXCEPTION_SP_EVENT, &bp->sp_event)) { + if (!is_bnxt_fw_ok(bp)) + bnxt_devlink_health_report(bp, + BNXT_FW_EXCEPTION_SP_EVENT); + } + smp_mb__before_atomic(); clear_bit(BNXT_STATE_IN_SP_TASK, &bp->state); } @@ -9728,6 +10411,336 @@ static void bnxt_init_dflt_coal(struct bnxt *bp) bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS; } +static int bnxt_fw_init_one_p1(struct bnxt *bp) +{ + int rc; + + bp->fw_cap = 0; + rc = bnxt_hwrm_ver_get(bp); + if (rc) + return rc; + + if (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL) { + rc = bnxt_alloc_kong_hwrm_resources(bp); + if (rc) + bp->fw_cap &= ~BNXT_FW_CAP_KONG_MB_CHNL; + } + + if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) || + bp->hwrm_max_ext_req_len > BNXT_HWRM_MAX_REQ_LEN) { + rc = bnxt_alloc_hwrm_short_cmd_req(bp); + if (rc) + return rc; + } + rc = bnxt_hwrm_func_reset(bp); + if (rc) + return -ENODEV; + + bnxt_hwrm_fw_set_time(bp); + return 0; +} + +static int bnxt_fw_init_one_p2(struct bnxt *bp) +{ + int rc; + + /* Get the MAX capabilities for this function */ + rc = bnxt_hwrm_func_qcaps(bp); + if (rc) { + netdev_err(bp->dev, "hwrm query capability failure rc: %x\n", + rc); + return -ENODEV; + } + + rc = bnxt_hwrm_cfa_adv_flow_mgnt_qcaps(bp); + if (rc) + netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n", + rc); + + rc = bnxt_hwrm_error_recovery_qcfg(bp); + if (rc) + netdev_warn(bp->dev, "hwrm query error recovery failure rc: %d\n", + rc); + + rc = bnxt_hwrm_func_drv_rgtr(bp); + if (rc) + return -ENODEV; + + rc = bnxt_hwrm_func_rgtr_async_events(bp, NULL, 0); + if (rc) + return -ENODEV; + + bnxt_hwrm_func_qcfg(bp); + bnxt_hwrm_vnic_qcaps(bp); + bnxt_hwrm_port_led_qcaps(bp); + bnxt_ethtool_init(bp); + bnxt_dcb_init(bp); + return 0; +} + +static void bnxt_set_dflt_rss_hash_type(struct bnxt *bp) +{ + bp->flags &= ~BNXT_FLAG_UDP_RSS_CAP; + bp->rss_hash_cfg = VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 | + VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 | + VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 | + VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6; + if (BNXT_CHIP_P4(bp) && bp->hwrm_spec_code >= 0x10501) { + bp->flags |= BNXT_FLAG_UDP_RSS_CAP; + bp->rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 | + VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6; + } +} + +static void bnxt_set_dflt_rfs(struct bnxt *bp) +{ + struct net_device *dev = bp->dev; + + dev->hw_features &= ~NETIF_F_NTUPLE; + dev->features &= ~NETIF_F_NTUPLE; + bp->flags &= ~BNXT_FLAG_RFS; + if (bnxt_rfs_supported(bp)) { + dev->hw_features |= NETIF_F_NTUPLE; + if (bnxt_rfs_capable(bp)) { + bp->flags |= BNXT_FLAG_RFS; + dev->features |= NETIF_F_NTUPLE; + } + } +} + +static void bnxt_fw_init_one_p3(struct bnxt *bp) +{ + struct pci_dev *pdev = bp->pdev; + + bnxt_set_dflt_rss_hash_type(bp); + bnxt_set_dflt_rfs(bp); + + bnxt_get_wol_settings(bp); + if (bp->flags & BNXT_FLAG_WOL_CAP) + device_set_wakeup_enable(&pdev->dev, bp->wol); + else + device_set_wakeup_capable(&pdev->dev, false); + + bnxt_hwrm_set_cache_line_size(bp, cache_line_size()); + bnxt_hwrm_coal_params_qcaps(bp); +} + +static int bnxt_fw_init_one(struct bnxt *bp) +{ + int rc; + + rc = bnxt_fw_init_one_p1(bp); + if (rc) { + netdev_err(bp->dev, "Firmware init phase 1 failed\n"); + return rc; + } + rc = bnxt_fw_init_one_p2(bp); + if (rc) { + netdev_err(bp->dev, "Firmware init phase 2 failed\n"); + return rc; + } + rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false); + if (rc) + return rc; + bnxt_fw_init_one_p3(bp); + return 0; +} + +static void bnxt_fw_reset_writel(struct bnxt *bp, int reg_idx) +{ + struct bnxt_fw_health *fw_health = bp->fw_health; + u32 reg = fw_health->fw_reset_seq_regs[reg_idx]; + u32 val = fw_health->fw_reset_seq_vals[reg_idx]; + u32 reg_type, reg_off, delay_msecs; + + delay_msecs = fw_health->fw_reset_seq_delay_msec[reg_idx]; + reg_type = BNXT_FW_HEALTH_REG_TYPE(reg); + reg_off = BNXT_FW_HEALTH_REG_OFF(reg); + switch (reg_type) { + case BNXT_FW_HEALTH_REG_TYPE_CFG: + pci_write_config_dword(bp->pdev, reg_off, val); + break; + case BNXT_FW_HEALTH_REG_TYPE_GRC: + writel(reg_off & BNXT_GRC_BASE_MASK, + bp->bar0 + BNXT_GRCPF_REG_WINDOW_BASE_OUT + 4); + reg_off = (reg_off & BNXT_GRC_OFFSET_MASK) + 0x2000; + /* fall through */ + case BNXT_FW_HEALTH_REG_TYPE_BAR0: + writel(val, bp->bar0 + reg_off); + break; + case BNXT_FW_HEALTH_REG_TYPE_BAR1: + writel(val, bp->bar1 + reg_off); + break; + } + if (delay_msecs) { + pci_read_config_dword(bp->pdev, 0, &val); + msleep(delay_msecs); + } +} + +static void bnxt_reset_all(struct bnxt *bp) +{ + struct bnxt_fw_health *fw_health = bp->fw_health; + int i; + + if (fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_HOST) { + for (i = 0; i < fw_health->fw_reset_seq_cnt; i++) + bnxt_fw_reset_writel(bp, i); + } else if (fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) { + struct hwrm_fw_reset_input req = {0}; + int rc; + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FW_RESET, -1, -1); + req.resp_addr = cpu_to_le64(bp->hwrm_cmd_kong_resp_dma_addr); + req.embedded_proc_type = FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP; + req.selfrst_status = FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP; + req.flags = FW_RESET_REQ_FLAGS_RESET_GRACEFUL; + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + netdev_warn(bp->dev, "Unable to reset FW rc=%d\n", rc); + } + bp->fw_reset_timestamp = jiffies; +} + +static void bnxt_fw_reset_task(struct work_struct *work) +{ + struct bnxt *bp = container_of(work, struct bnxt, fw_reset_task.work); + int rc; + + if (!test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { + netdev_err(bp->dev, "bnxt_fw_reset_task() called when not in fw reset mode!\n"); + return; + } + + switch (bp->fw_reset_state) { + case BNXT_FW_RESET_STATE_POLL_VF: { + int n = bnxt_get_registered_vfs(bp); + int tmo; + + if (n < 0) { + netdev_err(bp->dev, "Firmware reset aborted, subsequent func_qcfg cmd failed, rc = %d, %d msecs since reset timestamp\n", + n, jiffies_to_msecs(jiffies - + bp->fw_reset_timestamp)); + goto fw_reset_abort; + } else if (n > 0) { + if (time_after(jiffies, bp->fw_reset_timestamp + + (bp->fw_reset_max_dsecs * HZ / 10))) { + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + bp->fw_reset_state = 0; + netdev_err(bp->dev, "Firmware reset aborted, bnxt_get_registered_vfs() returns %d\n", + n); + return; + } + bnxt_queue_fw_reset_work(bp, HZ / 10); + return; + } + bp->fw_reset_timestamp = jiffies; + rtnl_lock(); + bnxt_fw_reset_close(bp); + if (bp->fw_cap & BNXT_FW_CAP_ERR_RECOVER_RELOAD) { + bp->fw_reset_state = BNXT_FW_RESET_STATE_POLL_FW_DOWN; + tmo = HZ / 10; + } else { + bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV; + tmo = bp->fw_reset_min_dsecs * HZ / 10; + } + rtnl_unlock(); + bnxt_queue_fw_reset_work(bp, tmo); + return; + } + case BNXT_FW_RESET_STATE_POLL_FW_DOWN: { + u32 val; + + val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG); + if (!(val & BNXT_FW_STATUS_SHUTDOWN) && + !time_after(jiffies, bp->fw_reset_timestamp + + (bp->fw_reset_max_dsecs * HZ / 10))) { + bnxt_queue_fw_reset_work(bp, HZ / 5); + return; + } + + if (!bp->fw_health->master) { + u32 wait_dsecs = bp->fw_health->normal_func_wait_dsecs; + + bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV; + bnxt_queue_fw_reset_work(bp, wait_dsecs * HZ / 10); + return; + } + bp->fw_reset_state = BNXT_FW_RESET_STATE_RESET_FW; + } + /* fall through */ + case BNXT_FW_RESET_STATE_RESET_FW: { + u32 wait_dsecs = bp->fw_health->post_reset_wait_dsecs; + + bnxt_reset_all(bp); + bp->fw_reset_state = BNXT_FW_RESET_STATE_ENABLE_DEV; + bnxt_queue_fw_reset_work(bp, wait_dsecs * HZ / 10); + return; + } + case BNXT_FW_RESET_STATE_ENABLE_DEV: + if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) && + bp->fw_health) { + u32 val; + + val = bnxt_fw_health_readl(bp, + BNXT_FW_RESET_INPROG_REG); + if (val) + netdev_warn(bp->dev, "FW reset inprog %x after min wait time.\n", + val); + } + clear_bit(BNXT_STATE_FW_FATAL_COND, &bp->state); + if (pci_enable_device(bp->pdev)) { + netdev_err(bp->dev, "Cannot re-enable PCI device\n"); + goto fw_reset_abort; + } + pci_set_master(bp->pdev); + bp->fw_reset_state = BNXT_FW_RESET_STATE_POLL_FW; + /* fall through */ + case BNXT_FW_RESET_STATE_POLL_FW: + bp->hwrm_cmd_timeout = SHORT_HWRM_CMD_TIMEOUT; + rc = __bnxt_hwrm_ver_get(bp, true); + if (rc) { + if (time_after(jiffies, bp->fw_reset_timestamp + + (bp->fw_reset_max_dsecs * HZ / 10))) { + netdev_err(bp->dev, "Firmware reset aborted\n"); + goto fw_reset_abort; + } + bnxt_queue_fw_reset_work(bp, HZ / 5); + return; + } + bp->hwrm_cmd_timeout = DFLT_HWRM_CMD_TIMEOUT; + bp->fw_reset_state = BNXT_FW_RESET_STATE_OPENING; + /* fall through */ + case BNXT_FW_RESET_STATE_OPENING: + while (!rtnl_trylock()) { + bnxt_queue_fw_reset_work(bp, HZ / 10); + return; + } + rc = bnxt_open(bp->dev); + if (rc) { + netdev_err(bp->dev, "bnxt_open_nic() failed\n"); + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + dev_close(bp->dev); + } + bnxt_ulp_irq_restart(bp, rc); + rtnl_unlock(); + + bp->fw_reset_state = 0; + /* Make sure fw_reset_state is 0 before clearing the flag */ + smp_mb__before_atomic(); + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + break; + } + return; + +fw_reset_abort: + clear_bit(BNXT_STATE_IN_FW_RESET, &bp->state); + bp->fw_reset_state = 0; + rtnl_lock(); + dev_close(bp->dev); + rtnl_unlock(); +} + static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) { int rc; @@ -9790,6 +10803,7 @@ static int bnxt_init_board(struct pci_dev *pdev, struct net_device *dev) pci_enable_pcie_error_reporting(pdev); INIT_WORK(&bp->sp_task, bnxt_sp_task); + INIT_DELAYED_WORK(&bp->fw_reset_task, bnxt_fw_reset_task); spin_lock_init(&bp->ntp_fltr_lock); #if BITS_PER_LONG == 32 @@ -10333,7 +11347,7 @@ static void bnxt_remove_one(struct pci_dev *pdev) free_netdev(dev); } -static int bnxt_probe_phy(struct bnxt *bp) +static int bnxt_probe_phy(struct bnxt *bp, bool fw_dflt) { int rc = 0; struct bnxt_link_info *link_info = &bp->link_info; @@ -10344,8 +11358,6 @@ static int bnxt_probe_phy(struct bnxt *bp) rc); return rc; } - mutex_init(&bp->link_lock); - rc = bnxt_update_link(bp, false); if (rc) { netdev_err(bp->dev, "Probe phy can't update link (rc: %x)\n", @@ -10359,6 +11371,9 @@ static int bnxt_probe_phy(struct bnxt *bp) if (link_info->auto_link_speeds && !link_info->support_auto_speeds) link_info->support_auto_speeds = link_info->support_speeds; + if (!fw_dflt) + return 0; + /*initialize the ethool setting copy with NVM settings */ if (BNXT_AUTO_MODE(link_info->auto_mode)) { link_info->autoneg = BNXT_AUTONEG_SPEED; @@ -10379,7 +11394,7 @@ static int bnxt_probe_phy(struct bnxt *bp) link_info->auto_pause_setting & BNXT_LINK_PAUSE_BOTH; else link_info->req_flow_ctrl = link_info->force_pause_setting; - return rc; + return 0; } static int bnxt_get_max_irq(struct pci_dev *pdev) @@ -10683,32 +11698,19 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto init_err_pci_clean; mutex_init(&bp->hwrm_cmd_lock); - rc = bnxt_hwrm_ver_get(bp); + mutex_init(&bp->link_lock); + + rc = bnxt_fw_init_one_p1(bp); if (rc) goto init_err_pci_clean; - if (bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL) { - rc = bnxt_alloc_kong_hwrm_resources(bp); - if (rc) - bp->fw_cap &= ~BNXT_FW_CAP_KONG_MB_CHNL; - } - - if ((bp->fw_cap & BNXT_FW_CAP_SHORT_CMD) || - bp->hwrm_max_ext_req_len > BNXT_HWRM_MAX_REQ_LEN) { - rc = bnxt_alloc_hwrm_short_cmd_req(bp); - if (rc) - goto init_err_pci_clean; - } - if (BNXT_CHIP_P5(bp)) bp->flags |= BNXT_FLAG_CHIP_P5; - rc = bnxt_hwrm_func_reset(bp); + rc = bnxt_fw_init_one_p2(bp); if (rc) goto init_err_pci_clean; - bnxt_hwrm_fw_set_time(bp); - dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_SG | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_GRE | @@ -10746,41 +11748,14 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) bp->gro_func = bnxt_gro_func_5730x; if (BNXT_CHIP_P4(bp)) bp->gro_func = bnxt_gro_func_5731x; + else if (BNXT_CHIP_P5(bp)) + bp->gro_func = bnxt_gro_func_5750x; } if (!BNXT_CHIP_P4_PLUS(bp)) bp->flags |= BNXT_FLAG_DOUBLE_DB; - rc = bnxt_hwrm_func_drv_rgtr(bp); - if (rc) - goto init_err_pci_clean; - - rc = bnxt_hwrm_func_rgtr_async_events(bp, NULL, 0); - if (rc) - goto init_err_pci_clean; - bp->ulp_probe = bnxt_ulp_probe; - rc = bnxt_hwrm_queue_qportcfg(bp); - if (rc) { - netdev_err(bp->dev, "hwrm query qportcfg failure rc: %x\n", - rc); - rc = -1; - goto init_err_pci_clean; - } - /* Get the MAX capabilities for this function */ - rc = bnxt_hwrm_func_qcaps(bp); - if (rc) { - netdev_err(bp->dev, "hwrm query capability failure rc: %x\n", - rc); - rc = -1; - goto init_err_pci_clean; - } - - rc = bnxt_hwrm_cfa_adv_flow_mgnt_qcaps(bp); - if (rc) - netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n", - rc); - rc = bnxt_init_mac_addr(bp); if (rc) { dev_err(&pdev->dev, "Unable to initialize mac address.\n"); @@ -10794,17 +11769,12 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) goto init_err_pci_clean; } - bnxt_hwrm_func_qcfg(bp); - bnxt_hwrm_vnic_qcaps(bp); - bnxt_hwrm_port_led_qcaps(bp); - bnxt_ethtool_init(bp); - bnxt_dcb_init(bp); /* MTU range: 60 - FW defined max */ dev->min_mtu = ETH_ZLEN; dev->max_mtu = bp->max_mtu; - rc = bnxt_probe_phy(bp); + rc = bnxt_probe_phy(bp, true); if (rc) goto init_err_pci_clean; @@ -10818,24 +11788,7 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) goto init_err_pci_clean; } - /* Default RSS hash cfg. */ - bp->rss_hash_cfg = VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4 | - VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4 | - VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6 | - VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6; - if (BNXT_CHIP_P4(bp) && bp->hwrm_spec_code >= 0x10501) { - bp->flags |= BNXT_FLAG_UDP_RSS_CAP; - bp->rss_hash_cfg |= VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4 | - VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6; - } - - if (bnxt_rfs_supported(bp)) { - dev->hw_features |= NETIF_F_NTUPLE; - if (bnxt_rfs_capable(bp)) { - bp->flags |= BNXT_FLAG_RFS; - dev->features |= NETIF_F_NTUPLE; - } - } + bnxt_fw_init_one_p3(bp); if (dev->hw_features & NETIF_F_HW_VLAN_CTAG_RX) bp->flags |= BNXT_FLAG_STRIP_VLAN; @@ -10849,16 +11802,6 @@ static int bnxt_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) */ bp->tx_nr_rings_per_tc = bp->tx_nr_rings; - bnxt_get_wol_settings(bp); - if (bp->flags & BNXT_FLAG_WOL_CAP) - device_set_wakeup_enable(&pdev->dev, bp->wol); - else - device_set_wakeup_capable(&pdev->dev, false); - - bnxt_hwrm_set_cache_line_size(bp, cache_line_size()); - - bnxt_hwrm_coal_params_qcaps(bp); - if (BNXT_PF(bp)) { if (!bnxt_pf_wq) { bnxt_pf_wq = @@ -10895,6 +11838,8 @@ init_err_pci_clean: bnxt_free_ctx_mem(bp); kfree(bp->ctx); bp->ctx = NULL; + kfree(bp->fw_health); + bp->fw_health = NULL; bnxt_cleanup_pci(bp); init_err_free: @@ -10934,8 +11879,7 @@ shutdown_exit: #ifdef CONFIG_PM_SLEEP static int bnxt_suspend(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct bnxt *bp = netdev_priv(dev); int rc = 0; @@ -10951,8 +11895,7 @@ static int bnxt_suspend(struct device *device) static int bnxt_resume(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct bnxt *bp = netdev_priv(dev); int rc = 0; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 16694b704d15..d333589811a5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -113,6 +113,7 @@ struct tx_cmp { #define CMP_TYPE_RX_AGG_CMP 18 #define CMP_TYPE_RX_L2_TPA_START_CMP 19 #define CMP_TYPE_RX_L2_TPA_END_CMP 21 + #define CMP_TYPE_RX_TPA_AGG_CMP 22 #define CMP_TYPE_STATUS_CMP 32 #define CMP_TYPE_REMOTE_DRIVER_REQ 34 #define CMP_TYPE_REMOTE_DRIVER_RESP 36 @@ -263,14 +264,21 @@ struct rx_agg_cmp { u32 rx_agg_cmp_opaque; __le32 rx_agg_cmp_v; #define RX_AGG_CMP_V (1 << 0) + #define RX_AGG_CMP_AGG_ID (0xffff << 16) + #define RX_AGG_CMP_AGG_ID_SHIFT 16 __le32 rx_agg_cmp_unused; }; +#define TPA_AGG_AGG_ID(rx_agg) \ + ((le32_to_cpu((rx_agg)->rx_agg_cmp_v) & \ + RX_AGG_CMP_AGG_ID) >> RX_AGG_CMP_AGG_ID_SHIFT) + struct rx_tpa_start_cmp { __le32 rx_tpa_start_cmp_len_flags_type; #define RX_TPA_START_CMP_TYPE (0x3f << 0) #define RX_TPA_START_CMP_FLAGS (0x3ff << 6) #define RX_TPA_START_CMP_FLAGS_SHIFT 6 + #define RX_TPA_START_CMP_FLAGS_ERROR (0x1 << 6) #define RX_TPA_START_CMP_FLAGS_PLACEMENT (0x7 << 7) #define RX_TPA_START_CMP_FLAGS_PLACEMENT_SHIFT 7 #define RX_TPA_START_CMP_FLAGS_PLACEMENT_JUMBO (0x1 << 7) @@ -278,6 +286,7 @@ struct rx_tpa_start_cmp { #define RX_TPA_START_CMP_FLAGS_PLACEMENT_GRO_JUMBO (0x5 << 7) #define RX_TPA_START_CMP_FLAGS_PLACEMENT_GRO_HDS (0x6 << 7) #define RX_TPA_START_CMP_FLAGS_RSS_VALID (0x1 << 10) + #define RX_TPA_START_CMP_FLAGS_TIMESTAMP (0x1 << 11) #define RX_TPA_START_CMP_FLAGS_ITYPES (0xf << 12) #define RX_TPA_START_CMP_FLAGS_ITYPES_SHIFT 12 #define RX_TPA_START_CMP_FLAGS_ITYPE_TCP (0x2 << 12) @@ -291,6 +300,8 @@ struct rx_tpa_start_cmp { #define RX_TPA_START_CMP_RSS_HASH_TYPE_SHIFT 9 #define RX_TPA_START_CMP_AGG_ID (0x7f << 25) #define RX_TPA_START_CMP_AGG_ID_SHIFT 25 + #define RX_TPA_START_CMP_AGG_ID_P5 (0xffff << 16) + #define RX_TPA_START_CMP_AGG_ID_SHIFT_P5 16 __le32 rx_tpa_start_cmp_rss_hash; }; @@ -308,6 +319,14 @@ struct rx_tpa_start_cmp { ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) & \ RX_TPA_START_CMP_AGG_ID) >> RX_TPA_START_CMP_AGG_ID_SHIFT) +#define TPA_START_AGG_ID_P5(rx_tpa_start) \ + ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_misc_v1) & \ + RX_TPA_START_CMP_AGG_ID_P5) >> RX_TPA_START_CMP_AGG_ID_SHIFT_P5) + +#define TPA_START_ERROR(rx_tpa_start) \ + ((rx_tpa_start)->rx_tpa_start_cmp_len_flags_type & \ + cpu_to_le32(RX_TPA_START_CMP_FLAGS_ERROR)) + struct rx_tpa_start_cmp_ext { __le32 rx_tpa_start_cmp_flags2; #define RX_TPA_START_CMP_FLAGS2_IP_CS_CALC (0x1 << 0) @@ -315,10 +334,20 @@ struct rx_tpa_start_cmp_ext { #define RX_TPA_START_CMP_FLAGS2_T_IP_CS_CALC (0x1 << 2) #define RX_TPA_START_CMP_FLAGS2_T_L4_CS_CALC (0x1 << 3) #define RX_TPA_START_CMP_FLAGS2_IP_TYPE (0x1 << 8) + #define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL_VALID (0x1 << 9) + #define RX_TPA_START_CMP_FLAGS2_EXT_META_FORMAT (0x3 << 10) + #define RX_TPA_START_CMP_FLAGS2_EXT_META_FORMAT_SHIFT 10 + #define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL (0xffff << 16) + #define RX_TPA_START_CMP_FLAGS2_CSUM_CMPL_SHIFT 16 __le32 rx_tpa_start_cmp_metadata; __le32 rx_tpa_start_cmp_cfa_code_v2; #define RX_TPA_START_CMP_V2 (0x1 << 0) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_MASK (0x7 << 1) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_SHIFT 1 + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_NO_BUFFER (0x0 << 1) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_BAD_FORMAT (0x3 << 1) + #define RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_FLUSH (0x5 << 1) #define RX_TPA_START_CMP_CFA_CODE (0xffff << 16) #define RX_TPA_START_CMPL_CFA_CODE_SHIFT 16 __le32 rx_tpa_start_cmp_hdr_info; @@ -332,6 +361,11 @@ struct rx_tpa_start_cmp_ext { (!!((rx_tpa_start)->rx_tpa_start_cmp_flags2 & \ cpu_to_le32(RX_TPA_START_CMP_FLAGS2_IP_TYPE))) +#define TPA_START_ERROR_CODE(rx_tpa_start) \ + ((le32_to_cpu((rx_tpa_start)->rx_tpa_start_cmp_cfa_code_v2) & \ + RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_MASK) >> \ + RX_TPA_START_CMP_ERRORS_BUFFER_ERROR_SHIFT) + struct rx_tpa_end_cmp { __le32 rx_tpa_end_cmp_len_flags_type; #define RX_TPA_END_CMP_TYPE (0x3f << 0) @@ -361,6 +395,8 @@ struct rx_tpa_end_cmp { #define RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT 16 #define RX_TPA_END_CMP_AGG_ID (0x7f << 25) #define RX_TPA_END_CMP_AGG_ID_SHIFT 25 + #define RX_TPA_END_CMP_AGG_ID_P5 (0xffff << 16) + #define RX_TPA_END_CMP_AGG_ID_SHIFT_P5 16 __le32 rx_tpa_end_cmp_tsdelta; #define RX_TPA_END_GRO_TS (0x1 << 31) @@ -370,6 +406,18 @@ struct rx_tpa_end_cmp { ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ RX_TPA_END_CMP_AGG_ID) >> RX_TPA_END_CMP_AGG_ID_SHIFT) +#define TPA_END_AGG_ID_P5(rx_tpa_end) \ + ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ + RX_TPA_END_CMP_AGG_ID_P5) >> RX_TPA_END_CMP_AGG_ID_SHIFT_P5) + +#define TPA_END_PAYLOAD_OFF(rx_tpa_end) \ + ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ + RX_TPA_END_CMP_PAYLOAD_OFFSET) >> RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT) + +#define TPA_END_AGG_BUFS(rx_tpa_end) \ + ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ + RX_TPA_END_CMP_AGG_BUFS) >> RX_TPA_END_CMP_AGG_BUFS_SHIFT) + #define TPA_END_TPA_SEGS(rx_tpa_end) \ ((le32_to_cpu((rx_tpa_end)->rx_tpa_end_cmp_misc_v1) & \ RX_TPA_END_CMP_TPA_SEGS) >> RX_TPA_END_CMP_TPA_SEGS_SHIFT) @@ -389,6 +437,10 @@ struct rx_tpa_end_cmp { struct rx_tpa_end_cmp_ext { __le32 rx_tpa_end_cmp_dup_acks; #define RX_TPA_END_CMP_TPA_DUP_ACKS (0xf << 0) + #define RX_TPA_END_CMP_PAYLOAD_OFFSET_P5 (0xff << 16) + #define RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT_P5 16 + #define RX_TPA_END_CMP_AGG_BUFS_P5 (0xff << 24) + #define RX_TPA_END_CMP_AGG_BUFS_SHIFT_P5 24 __le32 rx_tpa_end_cmp_seg_len; #define RX_TPA_END_CMP_TPA_SEG_LEN (0xffff << 0) @@ -396,7 +448,13 @@ struct rx_tpa_end_cmp_ext { __le32 rx_tpa_end_cmp_errors_v2; #define RX_TPA_END_CMP_V2 (0x1 << 0) #define RX_TPA_END_CMP_ERRORS (0x3 << 1) + #define RX_TPA_END_CMP_ERRORS_P5 (0x7 << 1) #define RX_TPA_END_CMPL_ERRORS_SHIFT 1 + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_NO_BUFFER (0x0 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_NOT_ON_CHIP (0x2 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_BAD_FORMAT (0x3 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_RSV_ERROR (0x4 << 1) + #define RX_TPA_END_CMP_ERRORS_BUFFER_ERROR_FLUSH (0x5 << 1) u32 rx_tpa_end_cmp_start_opaque; }; @@ -405,6 +463,28 @@ struct rx_tpa_end_cmp_ext { ((rx_tpa_end_ext)->rx_tpa_end_cmp_errors_v2 & \ cpu_to_le32(RX_TPA_END_CMP_ERRORS)) +#define TPA_END_PAYLOAD_OFF_P5(rx_tpa_end_ext) \ + ((le32_to_cpu((rx_tpa_end_ext)->rx_tpa_end_cmp_dup_acks) & \ + RX_TPA_END_CMP_PAYLOAD_OFFSET_P5) >> \ + RX_TPA_END_CMP_PAYLOAD_OFFSET_SHIFT_P5) + +#define TPA_END_AGG_BUFS_P5(rx_tpa_end_ext) \ + ((le32_to_cpu((rx_tpa_end_ext)->rx_tpa_end_cmp_dup_acks) & \ + RX_TPA_END_CMP_AGG_BUFS_P5) >> RX_TPA_END_CMP_AGG_BUFS_SHIFT_P5) + +#define EVENT_DATA1_RESET_NOTIFY_FATAL(data1) \ + (((data1) & \ + ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK) ==\ + ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL) + +#define EVENT_DATA1_RECOVERY_MASTER_FUNC(data1) \ + !!((data1) & \ + ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC) + +#define EVENT_DATA1_RECOVERY_ENABLED(data1) \ + !!((data1) & \ + ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED) + struct nqe_cn { __le16 type; #define NQ_CN_TYPE_MASK 0x3fUL @@ -487,6 +567,9 @@ struct nqe_cn { #define BNXT_DEFAULT_TX_RING_SIZE 511 #define MAX_TPA 64 +#define MAX_TPA_P5 256 +#define MAX_TPA_P5_MASK (MAX_TPA_P5 - 1) +#define MAX_TPA_SEGS_P5 0x3f #if (BNXT_PAGE_SHIFT == 16) #define MAX_RX_PAGES 1 @@ -562,8 +645,10 @@ struct nqe_cn { #define BNXT_HWRM_MAX_REQ_LEN (bp->hwrm_max_req_len) #define BNXT_HWRM_SHORT_REQ_LEN sizeof(struct hwrm_short_input) #define DFLT_HWRM_CMD_TIMEOUT 500 +#define SHORT_HWRM_CMD_TIMEOUT 20 #define HWRM_CMD_TIMEOUT (bp->hwrm_cmd_timeout) #define HWRM_RESET_TIMEOUT ((HWRM_CMD_TIMEOUT) * 4) +#define HWRM_COREDUMP_TIMEOUT ((HWRM_CMD_TIMEOUT) * 12) #define HWRM_RESP_ERR_CODE_MASK 0xffff #define HWRM_RESP_LEN_OFFSET 4 #define HWRM_RESP_LEN_MASK 0xffff0000 @@ -768,6 +853,15 @@ struct bnxt_tpa_info { ((hdr_info) & 0x1ff) u16 cfa_code; /* cfa_code in TPA start compl */ + u8 agg_count; + struct rx_agg_cmp *agg_arr; +}; + +#define BNXT_AGG_IDX_BMAP_SIZE (MAX_TPA_P5 / BITS_PER_LONG) + +struct bnxt_tpa_idx_map { + u16 agg_id_tbl[1024]; + unsigned long agg_idx_bmap[BNXT_AGG_IDX_BMAP_SIZE]; }; struct bnxt_rx_ring_info { @@ -797,6 +891,7 @@ struct bnxt_rx_ring_info { dma_addr_t rx_agg_desc_mapping[MAX_RX_AGG_PAGES]; struct bnxt_tpa_info *rx_tpa; + struct bnxt_tpa_idx_map *rx_tpa_idx_map; struct bnxt_ring_struct rx_ring_struct; struct bnxt_ring_struct rx_agg_ring_struct; @@ -978,6 +1073,7 @@ struct bnxt_pf_info { u8 mac_addr[ETH_ALEN]; u32 first_vf_id; u16 active_vfs; + u16 registered_vfs; u16 max_vfs; u32 max_encap_records; u32 max_decap_records; @@ -1137,6 +1233,9 @@ struct bnxt_test_info { #define BNXT_GRCPF_REG_KONG_COMM 0xA00 #define BNXT_GRCPF_REG_KONG_COMM_TRIGGER 0xB00 +#define BNXT_GRC_BASE_MASK 0xfffff000 +#define BNXT_GRC_OFFSET_MASK 0x00000ffc + struct bnxt_tc_flow_stats { u64 packets; u64 bytes; @@ -1253,6 +1352,54 @@ struct bnxt_ctx_mem_info { struct bnxt_ctx_pg_info *tqm_mem[9]; }; +struct bnxt_fw_health { + u32 flags; + u32 polling_dsecs; + u32 master_func_wait_dsecs; + u32 normal_func_wait_dsecs; + u32 post_reset_wait_dsecs; + u32 post_reset_max_wait_dsecs; + u32 regs[4]; + u32 mapped_regs[4]; +#define BNXT_FW_HEALTH_REG 0 +#define BNXT_FW_HEARTBEAT_REG 1 +#define BNXT_FW_RESET_CNT_REG 2 +#define BNXT_FW_RESET_INPROG_REG 3 + u32 fw_reset_inprog_reg_mask; + u32 last_fw_heartbeat; + u32 last_fw_reset_cnt; + u8 enabled:1; + u8 master:1; + u8 tmr_multiplier; + u8 tmr_counter; + u8 fw_reset_seq_cnt; + u32 fw_reset_seq_regs[16]; + u32 fw_reset_seq_vals[16]; + u32 fw_reset_seq_delay_msec[16]; + struct devlink_health_reporter *fw_reporter; + struct devlink_health_reporter *fw_reset_reporter; + struct devlink_health_reporter *fw_fatal_reporter; +}; + +struct bnxt_fw_reporter_ctx { + unsigned long sp_event; +}; + +#define BNXT_FW_HEALTH_REG_TYPE_MASK 3 +#define BNXT_FW_HEALTH_REG_TYPE_CFG 0 +#define BNXT_FW_HEALTH_REG_TYPE_GRC 1 +#define BNXT_FW_HEALTH_REG_TYPE_BAR0 2 +#define BNXT_FW_HEALTH_REG_TYPE_BAR1 3 + +#define BNXT_FW_HEALTH_REG_TYPE(reg) ((reg) & BNXT_FW_HEALTH_REG_TYPE_MASK) +#define BNXT_FW_HEALTH_REG_OFF(reg) ((reg) & ~BNXT_FW_HEALTH_REG_TYPE_MASK) + +#define BNXT_FW_HEALTH_WIN_BASE 0x3000 +#define BNXT_FW_HEALTH_WIN_MAP_OFF 8 + +#define BNXT_FW_STATUS_HEALTHY 0x8000 +#define BNXT_FW_STATUS_SHUTDOWN 0x100000 + struct bnxt { void __iomem *bar0; void __iomem *bar1; @@ -1282,7 +1429,9 @@ struct bnxt { #define CHIP_NUM_5745X 0xd730 -#define CHIP_NUM_57500 0x1750 +#define CHIP_NUM_57508 0x1750 +#define CHIP_NUM_57504 0x1751 +#define CHIP_NUM_57502 0x1752 #define CHIP_NUM_58802 0xd802 #define CHIP_NUM_58804 0xd804 @@ -1379,12 +1528,14 @@ struct bnxt { #define BNXT_CHIP_TYPE_NITRO_A0(bp) ((bp)->flags & BNXT_FLAG_CHIP_NITRO_A0) #define BNXT_RX_PAGE_MODE(bp) ((bp)->flags & BNXT_FLAG_RX_PAGE_MODE) #define BNXT_SUPPORTS_TPA(bp) (!BNXT_CHIP_TYPE_NITRO_A0(bp) && \ - !(bp->flags & BNXT_FLAG_CHIP_P5) && \ - !is_kdump_kernel()) + (!((bp)->flags & BNXT_FLAG_CHIP_P5) || \ + (bp)->max_tpa_v2) && !is_kdump_kernel()) /* Chip class phase 5 */ #define BNXT_CHIP_P5(bp) \ - ((bp)->chip_num == CHIP_NUM_57500) + ((bp)->chip_num == CHIP_NUM_57508 || \ + (bp)->chip_num == CHIP_NUM_57504 || \ + (bp)->chip_num == CHIP_NUM_57502) /* Chip class phase 4.x */ #define BNXT_CHIP_P4(bp) \ @@ -1414,6 +1565,8 @@ struct bnxt { u16, void *, u8 *, dma_addr_t, unsigned int); + u16 max_tpa_v2; + u16 max_tpa; u32 rx_buf_size; u32 rx_buf_use_size; /* useable size */ u16 rx_offset; @@ -1469,6 +1622,10 @@ struct bnxt { #define BNXT_STATE_OPEN 0 #define BNXT_STATE_IN_SP_TASK 1 #define BNXT_STATE_READ_STATS 2 +#define BNXT_STATE_FW_RESET_DET 3 +#define BNXT_STATE_IN_FW_RESET 4 +#define BNXT_STATE_ABORT_ERR 5 +#define BNXT_STATE_FW_FATAL_COND 6 struct bnxt_irq *irq_tbl; int total_irqs; @@ -1493,11 +1650,13 @@ struct bnxt { #define BNXT_FW_CAP_KONG_MB_CHNL 0x00000080 #define BNXT_FW_CAP_OVS_64BIT_HANDLE 0x00000400 #define BNXT_FW_CAP_TRUSTED_VF 0x00000800 + #define BNXT_FW_CAP_ERROR_RECOVERY 0x00002000 #define BNXT_FW_CAP_PKG_VER 0x00004000 #define BNXT_FW_CAP_CFA_ADV_FLOW 0x00008000 #define BNXT_FW_CAP_CFA_RFS_RING_TBL_IDX 0x00010000 #define BNXT_FW_CAP_PCIE_STATS_SUPPORTED 0x00020000 #define BNXT_FW_CAP_EXT_STATS_SUPPORTED 0x00040000 + #define BNXT_FW_CAP_ERR_RECOVER_RELOAD 0x00100000 #define BNXT_NEW_RM(bp) ((bp)->fw_cap & BNXT_FW_CAP_NEW_RM) u32 hwrm_spec_code; @@ -1525,6 +1684,7 @@ struct bnxt { int hw_port_stats_size; u16 fw_rx_stats_ext_size; u16 fw_tx_stats_ext_size; + u16 hw_ring_stats_size; u8 pri2cos[8]; u8 pri2cos_valid; @@ -1576,6 +1736,25 @@ struct bnxt { #define BNXT_FLOW_STATS_SP_EVENT 15 #define BNXT_UPDATE_PHY_SP_EVENT 16 #define BNXT_RING_COAL_NOW_SP_EVENT 17 +#define BNXT_FW_RESET_NOTIFY_SP_EVENT 18 +#define BNXT_FW_EXCEPTION_SP_EVENT 19 + + struct delayed_work fw_reset_task; + int fw_reset_state; +#define BNXT_FW_RESET_STATE_POLL_VF 1 +#define BNXT_FW_RESET_STATE_RESET_FW 2 +#define BNXT_FW_RESET_STATE_ENABLE_DEV 3 +#define BNXT_FW_RESET_STATE_POLL_FW 4 +#define BNXT_FW_RESET_STATE_OPENING 5 +#define BNXT_FW_RESET_STATE_POLL_FW_DOWN 6 + + u16 fw_reset_min_dsecs; +#define BNXT_DFLT_FW_RST_MIN_DSECS 20 + u16 fw_reset_max_dsecs; +#define BNXT_DFLT_FW_RST_MAX_DSECS 60 + unsigned long fw_reset_timestamp; + + struct bnxt_fw_health *fw_health; struct bnxt_hw_resc hw_resc; struct bnxt_pf_info pf; @@ -1637,7 +1816,6 @@ struct bnxt { u8 switch_id[8]; struct bnxt_tc_info *tc_info; struct dentry *debugfs_pdev; - struct dentry *debugfs_dim; struct device *hwmon_dev; }; @@ -1782,6 +1960,7 @@ extern const u16 bnxt_lhint_arr[]; int bnxt_alloc_rx_data(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 prod, gfp_t gfp); void bnxt_reuse_rx_data(struct bnxt_rx_ring_info *rxr, u16 cons, void *data); +u32 bnxt_fw_health_readl(struct bnxt *bp, int reg_idx); void bnxt_set_tpa_flags(struct bnxt *bp); void bnxt_set_ring_params(struct bnxt *); int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode); @@ -1814,6 +1993,8 @@ int bnxt_open_nic(struct bnxt *, bool, bool); int bnxt_half_open_nic(struct bnxt *bp); void bnxt_half_close_nic(struct bnxt *bp); int bnxt_close_nic(struct bnxt *, bool, bool); +void bnxt_fw_exception(struct bnxt *bp); +void bnxt_fw_reset(struct bnxt *bp); int bnxt_check_rings(struct bnxt *bp, int tx, int rx, bool sh, int tcs, int tx_xdp); int bnxt_setup_mq_tc(struct net_device *dev, u8 tc); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index 07301cb87c03..fb6f30d0d1d0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -377,8 +377,6 @@ static int bnxt_hwrm_set_dcbx_app(struct bnxt *bp, struct dcb_app *app, set.data_len = cpu_to_le16(sizeof(*data) + sizeof(*fw_app) * n); set.hdr_cnt = 1; rc = hwrm_send_message(bp, &set, sizeof(set), HWRM_CMD_TIMEOUT); - if (rc) - rc = -EIO; set_app_exit: dma_free_coherent(&bp->pdev->dev, data_len, data, mapping); @@ -391,6 +389,7 @@ static int bnxt_hwrm_queue_dscp_qcaps(struct bnxt *bp) struct hwrm_queue_dscp_qcaps_input req = {0}; int rc; + bp->max_dscp_value = 0; if (bp->hwrm_spec_code < 0x10800 || BNXT_VF(bp)) return 0; @@ -433,8 +432,6 @@ static int bnxt_hwrm_queue_dscp2pri_cfg(struct bnxt *bp, struct dcb_app *app, dscp2pri->pri = app->priority; req.entry_cnt = cpu_to_le16(1); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - rc = -EIO; dma_free_coherent(&bp->pdev->dev, sizeof(*dscp2pri), dscp2pri, mapping); return rc; @@ -722,6 +719,7 @@ static const struct dcbnl_rtnl_ops dcbnl_ops = { void bnxt_dcb_init(struct bnxt *bp) { + bp->dcbx_cap = 0; if (bp->hwrm_spec_code < 0x10501) return; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c index 61393f351a77..156c2404854f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c @@ -61,45 +61,30 @@ static const struct file_operations debugfs_dim_fops = { .read = debugfs_dim_read, }; -static struct dentry *debugfs_dim_ring_init(struct dim *dim, int ring_idx, - struct dentry *dd) +static void debugfs_dim_ring_init(struct dim *dim, int ring_idx, + struct dentry *dd) { static char qname[16]; snprintf(qname, 10, "%d", ring_idx); - return debugfs_create_file(qname, 0600, dd, - dim, &debugfs_dim_fops); + debugfs_create_file(qname, 0600, dd, dim, &debugfs_dim_fops); } void bnxt_debug_dev_init(struct bnxt *bp) { const char *pname = pci_name(bp->pdev); - struct dentry *pdevf; + struct dentry *dir; int i; bp->debugfs_pdev = debugfs_create_dir(pname, bnxt_debug_mnt); - if (bp->debugfs_pdev) { - pdevf = debugfs_create_dir("dim", bp->debugfs_pdev); - if (!pdevf) { - pr_err("failed to create debugfs entry %s/dim\n", - pname); - return; - } - bp->debugfs_dim = pdevf; - /* create files for each rx ring */ - for (i = 0; i < bp->cp_nr_rings; i++) { - struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring; + dir = debugfs_create_dir("dim", bp->debugfs_pdev); - if (cpr && bp->bnapi[i]->rx_ring) { - pdevf = debugfs_dim_ring_init(&cpr->dim, i, - bp->debugfs_dim); - if (!pdevf) - pr_err("failed to create debugfs entry %s/dim/%d\n", - pname, i); - } - } - } else { - pr_err("failed to create debugfs entry %s\n", pname); + /* create files for each rx ring */ + for (i = 0; i < bp->cp_nr_rings; i++) { + struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring; + + if (cpr && bp->bnapi[i]->rx_ring) + debugfs_dim_ring_init(&cpr->dim, i, dir); } } @@ -114,8 +99,6 @@ void bnxt_debug_dev_exit(struct bnxt *bp) void bnxt_debug_init(void) { bnxt_debug_mnt = debugfs_create_dir("bnxt_en", NULL); - if (!bnxt_debug_mnt) - pr_err("failed to init bnxt_en debugfs\n"); } void bnxt_debug_exit(void) diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index c05d663212b2..e664392dccc0 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -15,6 +15,192 @@ #include "bnxt_vfr.h" #include "bnxt_devlink.h" +static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg) +{ + struct bnxt *bp = devlink_health_reporter_priv(reporter); + struct bnxt_fw_health *health = bp->fw_health; + u32 val, health_status; + int rc; + + if (!health || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) + return 0; + + val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG); + health_status = val & 0xffff; + + if (health_status == BNXT_FW_STATUS_HEALTHY) { + rc = devlink_fmsg_string_pair_put(fmsg, "FW status", + "Healthy;"); + if (rc) + return rc; + } else if (health_status < BNXT_FW_STATUS_HEALTHY) { + rc = devlink_fmsg_string_pair_put(fmsg, "FW status", + "Not yet completed initialization;"); + if (rc) + return rc; + } else if (health_status > BNXT_FW_STATUS_HEALTHY) { + rc = devlink_fmsg_string_pair_put(fmsg, "FW status", + "Encountered fatal error and cannot recover;"); + if (rc) + return rc; + } + + if (val >> 16) { + rc = devlink_fmsg_u32_pair_put(fmsg, "Error", val >> 16); + if (rc) + return rc; + } + + val = bnxt_fw_health_readl(bp, BNXT_FW_RESET_CNT_REG); + rc = devlink_fmsg_u32_pair_put(fmsg, "Reset count", val); + if (rc) + return rc; + + return 0; +} + +static const struct devlink_health_reporter_ops bnxt_dl_fw_reporter_ops = { + .name = "fw", + .diagnose = bnxt_fw_reporter_diagnose, +}; + +static int bnxt_fw_reset_recover(struct devlink_health_reporter *reporter, + void *priv_ctx) +{ + struct bnxt *bp = devlink_health_reporter_priv(reporter); + + if (!priv_ctx) + return -EOPNOTSUPP; + + bnxt_fw_reset(bp); + return 0; +} + +static const +struct devlink_health_reporter_ops bnxt_dl_fw_reset_reporter_ops = { + .name = "fw_reset", + .recover = bnxt_fw_reset_recover, +}; + +static int bnxt_fw_fatal_recover(struct devlink_health_reporter *reporter, + void *priv_ctx) +{ + struct bnxt *bp = devlink_health_reporter_priv(reporter); + struct bnxt_fw_reporter_ctx *fw_reporter_ctx = priv_ctx; + unsigned long event; + + if (!priv_ctx) + return -EOPNOTSUPP; + + event = fw_reporter_ctx->sp_event; + if (event == BNXT_FW_RESET_NOTIFY_SP_EVENT) + bnxt_fw_reset(bp); + else if (event == BNXT_FW_EXCEPTION_SP_EVENT) + bnxt_fw_exception(bp); + + return 0; +} + +static const +struct devlink_health_reporter_ops bnxt_dl_fw_fatal_reporter_ops = { + .name = "fw_fatal", + .recover = bnxt_fw_fatal_recover, +}; + +static void bnxt_dl_fw_reporters_create(struct bnxt *bp) +{ + struct bnxt_fw_health *health = bp->fw_health; + + if (!health) + return; + + health->fw_reporter = + devlink_health_reporter_create(bp->dl, &bnxt_dl_fw_reporter_ops, + 0, false, bp); + if (IS_ERR(health->fw_reporter)) { + netdev_warn(bp->dev, "Failed to create FW health reporter, rc = %ld\n", + PTR_ERR(health->fw_reporter)); + health->fw_reporter = NULL; + } + + health->fw_reset_reporter = + devlink_health_reporter_create(bp->dl, + &bnxt_dl_fw_reset_reporter_ops, + 0, true, bp); + if (IS_ERR(health->fw_reset_reporter)) { + netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n", + PTR_ERR(health->fw_reset_reporter)); + health->fw_reset_reporter = NULL; + } + + health->fw_fatal_reporter = + devlink_health_reporter_create(bp->dl, + &bnxt_dl_fw_fatal_reporter_ops, + 0, true, bp); + if (IS_ERR(health->fw_fatal_reporter)) { + netdev_warn(bp->dev, "Failed to create FW fatal health reporter, rc = %ld\n", + PTR_ERR(health->fw_fatal_reporter)); + health->fw_fatal_reporter = NULL; + } +} + +static void bnxt_dl_fw_reporters_destroy(struct bnxt *bp) +{ + struct bnxt_fw_health *health = bp->fw_health; + + if (!health) + return; + + if (health->fw_reporter) + devlink_health_reporter_destroy(health->fw_reporter); + + if (health->fw_reset_reporter) + devlink_health_reporter_destroy(health->fw_reset_reporter); + + if (health->fw_fatal_reporter) + devlink_health_reporter_destroy(health->fw_fatal_reporter); +} + +void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event) +{ + struct bnxt_fw_health *fw_health = bp->fw_health; + struct bnxt_fw_reporter_ctx fw_reporter_ctx; + + if (!fw_health) + return; + + fw_reporter_ctx.sp_event = event; + switch (event) { + case BNXT_FW_RESET_NOTIFY_SP_EVENT: + if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) { + if (!fw_health->fw_fatal_reporter) + return; + + devlink_health_report(fw_health->fw_fatal_reporter, + "FW fatal async event received", + &fw_reporter_ctx); + return; + } + if (!fw_health->fw_reset_reporter) + return; + + devlink_health_report(fw_health->fw_reset_reporter, + "FW non-fatal reset event received", + &fw_reporter_ctx); + return; + + case BNXT_FW_EXCEPTION_SP_EVENT: + if (!fw_health->fw_fatal_reporter) + return; + + devlink_health_report(fw_health->fw_fatal_reporter, + "FW fatal error reported", + &fw_reporter_ctx); + return; + } +} + static const struct devlink_ops bnxt_dl_ops = { #ifdef CONFIG_BNXT_SRIOV .eswitch_mode_set = bnxt_dl_eswitch_mode_set, @@ -109,13 +295,9 @@ static int bnxt_hwrm_nvm_req(struct bnxt *bp, u32 param_id, void *msg, memcpy(buf, data_addr, bytesize); dma_free_coherent(&bp->pdev->dev, bytesize, data_addr, data_dma_addr); - if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) { + if (rc == -EACCES) netdev_err(bp->dev, "PF does not have admin privileges to modify NVM config\n"); - return -EACCES; - } else if (rc) { - return -EIO; - } - return 0; + return rc; } static int bnxt_dl_nvm_param_get(struct devlink *dl, u32 id, @@ -251,6 +433,8 @@ int bnxt_dl_register(struct bnxt *bp) devlink_params_publish(dl); + bnxt_dl_fw_reporters_create(bp); + return 0; err_dl_port_unreg: @@ -273,6 +457,7 @@ void bnxt_dl_unregister(struct bnxt *bp) if (!dl) return; + bnxt_dl_fw_reporters_destroy(bp); devlink_port_params_unregister(&bp->dl_port, bnxt_dl_port_params, ARRAY_SIZE(bnxt_dl_port_params)); devlink_port_unregister(&bp->dl_port); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h index 5b6b2c7d97cf..b97e0baeb42d 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.h @@ -55,6 +55,7 @@ struct bnxt_dl_nvm_param { u16 num_bits; }; +void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event); int bnxt_dl_register(struct bnxt *bp); void bnxt_dl_unregister(struct bnxt *bp); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 8445a0cce849..51c140476717 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -137,7 +137,44 @@ reset_coalesce: return rc; } -#define BNXT_NUM_STATS 22 +static const char * const bnxt_ring_stats_str[] = { + "rx_ucast_packets", + "rx_mcast_packets", + "rx_bcast_packets", + "rx_discards", + "rx_drops", + "rx_ucast_bytes", + "rx_mcast_bytes", + "rx_bcast_bytes", + "tx_ucast_packets", + "tx_mcast_packets", + "tx_bcast_packets", + "tx_discards", + "tx_drops", + "tx_ucast_bytes", + "tx_mcast_bytes", + "tx_bcast_bytes", +}; + +static const char * const bnxt_ring_tpa_stats_str[] = { + "tpa_packets", + "tpa_bytes", + "tpa_events", + "tpa_aborts", +}; + +static const char * const bnxt_ring_tpa2_stats_str[] = { + "rx_tpa_eligible_pkt", + "rx_tpa_eligible_bytes", + "rx_tpa_pkt", + "rx_tpa_bytes", + "rx_tpa_errors", +}; + +static const char * const bnxt_ring_sw_stats_str[] = { + "rx_l4_csum_errors", + "missed_irqs", +}; #define BNXT_RX_STATS_ENTRY(counter) \ { BNXT_RX_STATS_OFFSET(counter), __stringify(counter) } @@ -207,6 +244,20 @@ reset_coalesce: BNXT_TX_STATS_EXT_COS_ENTRY(6), \ BNXT_TX_STATS_EXT_COS_ENTRY(7) \ +#define BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(n) \ + BNXT_RX_STATS_EXT_ENTRY(rx_discard_bytes_cos##n), \ + BNXT_RX_STATS_EXT_ENTRY(rx_discard_packets_cos##n) + +#define BNXT_RX_STATS_EXT_DISCARD_COS_ENTRIES \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(0), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(1), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(2), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(3), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(4), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(5), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(6), \ + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRY(7) + #define BNXT_RX_STATS_PRI_ENTRY(counter, n) \ { BNXT_RX_STATS_EXT_OFFSET(counter##_cos0), \ __stringify(counter##_pri##n) } @@ -352,6 +403,7 @@ static const struct { BNXT_RX_STATS_EXT_ENTRY(rx_buffer_passed_threshold), BNXT_RX_STATS_EXT_ENTRY(rx_pcs_symbol_err), BNXT_RX_STATS_EXT_ENTRY(rx_corrected_bits), + BNXT_RX_STATS_EXT_DISCARD_COS_ENTRIES, }; static const struct { @@ -417,9 +469,29 @@ static const struct { ARRAY_SIZE(bnxt_tx_pkts_pri_arr)) #define BNXT_NUM_PCIE_STATS ARRAY_SIZE(bnxt_pcie_stats_arr) +static int bnxt_get_num_tpa_ring_stats(struct bnxt *bp) +{ + if (BNXT_SUPPORTS_TPA(bp)) { + if (bp->max_tpa_v2) + return ARRAY_SIZE(bnxt_ring_tpa2_stats_str); + return ARRAY_SIZE(bnxt_ring_tpa_stats_str); + } + return 0; +} + +static int bnxt_get_num_ring_stats(struct bnxt *bp) +{ + int num_stats; + + num_stats = ARRAY_SIZE(bnxt_ring_stats_str) + + ARRAY_SIZE(bnxt_ring_sw_stats_str) + + bnxt_get_num_tpa_ring_stats(bp); + return num_stats * bp->cp_nr_rings; +} + static int bnxt_get_num_stats(struct bnxt *bp) { - int num_stats = BNXT_NUM_STATS * bp->cp_nr_rings; + int num_stats = bnxt_get_num_ring_stats(bp); num_stats += BNXT_NUM_SW_FUNC_STATS; @@ -460,10 +532,11 @@ static void bnxt_get_ethtool_stats(struct net_device *dev, { u32 i, j = 0; struct bnxt *bp = netdev_priv(dev); - u32 stat_fields = sizeof(struct ctx_hw_stats) / 8; + u32 stat_fields = ARRAY_SIZE(bnxt_ring_stats_str) + + bnxt_get_num_tpa_ring_stats(bp); if (!bp->bnapi) { - j += BNXT_NUM_STATS * bp->cp_nr_rings + BNXT_NUM_SW_FUNC_STATS; + j += bnxt_get_num_ring_stats(bp) + BNXT_NUM_SW_FUNC_STATS; goto skip_ring_stats; } @@ -551,56 +624,39 @@ skip_ring_stats: static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf) { struct bnxt *bp = netdev_priv(dev); - u32 i; + static const char * const *str; + u32 i, j, num_str; switch (stringset) { - /* The number of strings must match BNXT_NUM_STATS defined above. */ case ETH_SS_STATS: for (i = 0; i < bp->cp_nr_rings; i++) { - sprintf(buf, "[%d]: rx_ucast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_mcast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_bcast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_discards", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_drops", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_ucast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_mcast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_bcast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_ucast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_mcast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_bcast_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_discards", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_drops", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_ucast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_mcast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tx_bcast_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tpa_packets", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tpa_bytes", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tpa_events", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: tpa_aborts", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: rx_l4_csum_errors", i); - buf += ETH_GSTRING_LEN; - sprintf(buf, "[%d]: missed_irqs", i); - buf += ETH_GSTRING_LEN; + num_str = ARRAY_SIZE(bnxt_ring_stats_str); + for (j = 0; j < num_str; j++) { + sprintf(buf, "[%d]: %s", i, + bnxt_ring_stats_str[j]); + buf += ETH_GSTRING_LEN; + } + if (!BNXT_SUPPORTS_TPA(bp)) + goto skip_tpa_stats; + + if (bp->max_tpa_v2) { + num_str = ARRAY_SIZE(bnxt_ring_tpa2_stats_str); + str = bnxt_ring_tpa2_stats_str; + } else { + num_str = ARRAY_SIZE(bnxt_ring_tpa_stats_str); + str = bnxt_ring_tpa_stats_str; + } + for (j = 0; j < num_str; j++) { + sprintf(buf, "[%d]: %s", i, str[j]); + buf += ETH_GSTRING_LEN; + } +skip_tpa_stats: + num_str = ARRAY_SIZE(bnxt_ring_sw_stats_str); + for (j = 0; j < num_str; j++) { + sprintf(buf, "[%d]: %s", i, + bnxt_ring_sw_stats_str[j]); + buf += ETH_GSTRING_LEN; + } } for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++) { strcpy(buf, bnxt_sw_func_stats[i].string); @@ -1643,6 +1699,11 @@ static u32 bnxt_get_link(struct net_device *dev) return bp->link_info.link_up; } +static void bnxt_print_admin_err(struct bnxt *bp) +{ + netdev_info(bp->dev, "PF does not have admin privileges to flash or reset the device\n"); +} + static int bnxt_find_nvram_item(struct net_device *dev, u16 type, u16 ordinal, u16 ext, u16 *index, u32 *item_length, u32 *data_length); @@ -1682,13 +1743,8 @@ static int bnxt_flash_nvram(struct net_device *dev, rc = hwrm_send_message(bp, &req, sizeof(req), FLASH_NVRAM_TIMEOUT); dma_free_coherent(&bp->pdev->dev, data_len, kmem, dma_handle); - if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) { - netdev_info(dev, - "PF does not have admin privileges to flash the device\n"); - rc = -EACCES; - } else if (rc) { - rc = -EIO; - } + if (rc == -EACCES) + bnxt_print_admin_err(bp); return rc; } @@ -1738,13 +1794,8 @@ static int bnxt_firmware_reset(struct net_device *dev, } rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) { - netdev_info(dev, - "PF does not have admin privileges to reset the device\n"); - rc = -EACCES; - } else if (rc) { - rc = -EIO; - } + if (rc == -EACCES) + bnxt_print_admin_err(bp); return rc; } @@ -2039,13 +2090,8 @@ static int bnxt_flash_package_from_file(struct net_device *dev, flash_pkg_exit: mutex_unlock(&bp->hwrm_cmd_lock); err_exit: - if (hwrm_err == HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED) { - netdev_info(dev, - "PF does not have admin privileges to flash the device\n"); - rc = -EACCES; - } else if (hwrm_err) { - rc = -EOPNOTSUPP; - } + if (hwrm_err == -EACCES) + bnxt_print_admin_err(bp); return rc; } @@ -2584,8 +2630,6 @@ static int bnxt_set_phys_id(struct net_device *dev, led_cfg->led_group_id = bp->leds[i].led_group_id; } rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - rc = -EIO; return rc; } @@ -3068,7 +3112,7 @@ static int bnxt_hwrm_dbg_coredump_initiate(struct bnxt *bp, u16 component_id, req.component_id = cpu_to_le16(component_id); req.segment_id = cpu_to_le16(segment_id); - return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + return hwrm_send_message(bp, &req, sizeof(req), HWRM_COREDUMP_TIMEOUT); } static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id, @@ -3306,6 +3350,7 @@ void bnxt_ethtool_init(struct bnxt *bp) if (!(bp->fw_cap & BNXT_FW_CAP_PKG_VER)) bnxt_get_pkgver(dev); + bp->num_tests = 0; if (bp->hwrm_spec_code < 0x10704 || !BNXT_SINGLE_PF(bp)) return; @@ -3315,7 +3360,9 @@ void bnxt_ethtool_init(struct bnxt *bp) if (rc) goto ethtool_init_exit; - test_info = kzalloc(sizeof(*bp->test_info), GFP_KERNEL); + test_info = bp->test_info; + if (!test_info) + test_info = kzalloc(sizeof(*bp->test_info), GFP_KERNEL); if (!test_info) goto ethtool_init_exit; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h index 12bbb2a207d0..03b197eb793b 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h @@ -1,7 +1,8 @@ /* Broadcom NetXtreme-C/E network driver. * * Copyright (c) 2014-2016 Broadcom Corporation - * Copyright (c) 2016-2019 Broadcom Limited + * Copyright (c) 2014-2018 Broadcom Limited + * Copyright (c) 2018-2019 Broadcom Inc. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -39,15 +40,16 @@ struct hwrm_resp_hdr { #define TLV_TYPE_ROCE_SP_COMMAND 0x3UL #define TLV_TYPE_QUERY_ROCE_CC_GEN1 0x4UL #define TLV_TYPE_MODIFY_ROCE_CC_GEN1 0x5UL -#define TLV_TYPE_ENGINE_CKV_DEVICE_SERIAL_NUMBER 0x8001UL -#define TLV_TYPE_ENGINE_CKV_NONCE 0x8002UL +#define TLV_TYPE_ENGINE_CKV_ALIAS_ECC_PUBLIC_KEY 0x8001UL #define TLV_TYPE_ENGINE_CKV_IV 0x8003UL #define TLV_TYPE_ENGINE_CKV_AUTH_TAG 0x8004UL #define TLV_TYPE_ENGINE_CKV_CIPHERTEXT 0x8005UL -#define TLV_TYPE_ENGINE_CKV_ALGORITHMS 0x8006UL -#define TLV_TYPE_ENGINE_CKV_ECC_PUBLIC_KEY 0x8007UL +#define TLV_TYPE_ENGINE_CKV_HOST_ALGORITHMS 0x8006UL +#define TLV_TYPE_ENGINE_CKV_HOST_ECC_PUBLIC_KEY 0x8007UL #define TLV_TYPE_ENGINE_CKV_ECDSA_SIGNATURE 0x8008UL -#define TLV_TYPE_LAST TLV_TYPE_ENGINE_CKV_ECDSA_SIGNATURE +#define TLV_TYPE_ENGINE_CKV_FW_ECC_PUBLIC_KEY 0x8009UL +#define TLV_TYPE_ENGINE_CKV_FW_ALGORITHMS 0x800aUL +#define TLV_TYPE_LAST TLV_TYPE_ENGINE_CKV_FW_ALGORITHMS /* tlv (size:64b/8B) */ @@ -200,10 +202,16 @@ struct cmd_nums { #define HWRM_PORT_QSTATS_EXT 0xb4UL #define HWRM_PORT_PHY_MDIO_WRITE 0xb5UL #define HWRM_PORT_PHY_MDIO_READ 0xb6UL + #define HWRM_PORT_PHY_MDIO_BUS_ACQUIRE 0xb7UL + #define HWRM_PORT_PHY_MDIO_BUS_RELEASE 0xb8UL #define HWRM_FW_RESET 0xc0UL #define HWRM_FW_QSTATUS 0xc1UL #define HWRM_FW_HEALTH_CHECK 0xc2UL #define HWRM_FW_SYNC 0xc3UL + #define HWRM_FW_STATE_BUFFER_QCAPS 0xc4UL + #define HWRM_FW_STATE_QUIESCE 0xc5UL + #define HWRM_FW_STATE_BACKUP 0xc6UL + #define HWRM_FW_STATE_RESTORE 0xc7UL #define HWRM_FW_SET_TIME 0xc8UL #define HWRM_FW_GET_TIME 0xc9UL #define HWRM_FW_SET_STRUCTURED_DATA 0xcaUL @@ -215,7 +223,10 @@ struct cmd_nums { #define HWRM_FWD_ASYNC_EVENT_CMPL 0xd3UL #define HWRM_OEM_CMD 0xd4UL #define HWRM_PORT_PRBS_TEST 0xd5UL + #define HWRM_PORT_SFP_SIDEBAND_CFG 0xd6UL + #define HWRM_PORT_SFP_SIDEBAND_QCFG 0xd7UL #define HWRM_TEMP_MONITOR_QUERY 0xe0UL + #define HWRM_REG_POWER_QUERY 0xe1UL #define HWRM_WOL_FILTER_ALLOC 0xf0UL #define HWRM_WOL_FILTER_FREE 0xf1UL #define HWRM_WOL_FILTER_QCFG 0xf2UL @@ -267,7 +278,6 @@ struct cmd_nums { #define HWRM_CFA_EEM_OP 0x123UL #define HWRM_CFA_ADV_FLOW_MGNT_QCAPS 0x124UL #define HWRM_CFA_TFLIB 0x125UL - #define HWRM_ENGINE_CKV_HELLO 0x12dUL #define HWRM_ENGINE_CKV_STATUS 0x12eUL #define HWRM_ENGINE_CKV_CKEK_ADD 0x12fUL #define HWRM_ENGINE_CKV_CKEK_DELETE 0x130UL @@ -313,6 +323,7 @@ struct cmd_nums { #define HWRM_FUNC_BACKING_STORE_QCFG 0x194UL #define HWRM_FUNC_VF_BW_CFG 0x195UL #define HWRM_FUNC_VF_BW_QCFG 0x196UL + #define HWRM_FUNC_HOST_PF_IDS_QUERY 0x197UL #define HWRM_SELFTEST_QLIST 0x200UL #define HWRM_SELFTEST_EXEC 0x201UL #define HWRM_SELFTEST_IRQ 0x202UL @@ -410,8 +421,8 @@ struct hwrm_err_output { #define HWRM_VERSION_MAJOR 1 #define HWRM_VERSION_MINOR 10 #define HWRM_VERSION_UPDATE 0 -#define HWRM_VERSION_RSVD 69 -#define HWRM_VERSION_STR "1.10.0.69" +#define HWRM_VERSION_RSVD 100 +#define HWRM_VERSION_STR "1.10.0.100" /* hwrm_ver_get_input (size:192b/24B) */ struct hwrm_ver_get_input { @@ -624,6 +635,8 @@ struct hwrm_async_event_cmpl { #define ASYNC_EVENT_CMPL_EVENT_ID_TCP_FLAG_ACTION_CHANGE 0x3aUL #define ASYNC_EVENT_CMPL_EVENT_ID_EEM_FLOW_ACTIVE 0x3bUL #define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CFG_CHANGE 0x3cUL + #define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_DEFAULT_VNIC_CHANGE 0x3dUL + #define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_LINK_STATUS_CHANGE 0x3eUL #define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG 0xfeUL #define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR 0xffUL #define ASYNC_EVENT_CMPL_EVENT_ID_LAST ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR @@ -802,6 +815,37 @@ struct hwrm_async_event_cmpl_vf_cfg_change { #define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_TRUSTED_VF_CFG_CHANGE 0x10UL }; +/* hwrm_async_event_cmpl_default_vnic_change (size:128b/16B) */ +struct hwrm_async_event_cmpl_default_vnic_change { + __le16 type; + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_MASK 0x3fUL + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_SFT 0 + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_HWRM_ASYNC_EVENT 0x2eUL + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_LAST ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_HWRM_ASYNC_EVENT + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_UNUSED1_MASK 0xffc0UL + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_UNUSED1_SFT 6 + __le16 event_id; + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_ALLOC_FREE_NOTIFICATION 0x35UL + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_LAST ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_ALLOC_FREE_NOTIFICATION + __le32 event_data2; + u8 opaque_v; + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_V 0x1UL + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_OPAQUE_MASK 0xfeUL + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_OPAQUE_SFT 1 + u8 timestamp_lo; + __le16 timestamp_hi; + __le32 event_data1; + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_MASK 0x3UL + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_SFT 0 + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_ALLOC 0x1UL + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_FREE 0x2UL + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_LAST ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_FREE + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_PF_ID_MASK 0x3fcUL + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_PF_ID_SFT 2 + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_VF_ID_MASK 0x3fffc00UL + #define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_VF_ID_SFT 10 +}; + /* hwrm_async_event_cmpl_hw_flow_aged (size:128b/16B) */ struct hwrm_async_event_cmpl_hw_flow_aged { __le16 type; @@ -1044,31 +1088,33 @@ struct hwrm_func_qcaps_output { __le16 fid; __le16 port_id; __le32 flags; - #define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED 0x1UL - #define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING 0x2UL - #define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED 0x4UL - #define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED 0x8UL - #define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED 0x10UL - #define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED 0x20UL - #define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED 0x40UL - #define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED 0x80UL - #define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED 0x100UL - #define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED 0x200UL - #define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED 0x400UL - #define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED 0x800UL - #define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED 0x1000UL - #define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED 0x2000UL - #define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED 0x4000UL - #define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED 0x8000UL - #define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED 0x10000UL - #define FUNC_QCAPS_RESP_FLAGS_ADOPTED_PF_SUPPORTED 0x20000UL - #define FUNC_QCAPS_RESP_FLAGS_ADMIN_PF_SUPPORTED 0x40000UL - #define FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED 0x80000UL - #define FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE 0x100000UL - #define FUNC_QCAPS_RESP_FLAGS_DYNAMIC_TX_RING_ALLOC 0x200000UL - #define FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE 0x400000UL - #define FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE 0x800000UL - #define FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED 0x1000000UL + #define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED 0x1UL + #define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING 0x2UL + #define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED 0x4UL + #define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED 0x8UL + #define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED 0x10UL + #define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED 0x20UL + #define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED 0x40UL + #define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED 0x80UL + #define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED 0x100UL + #define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED 0x200UL + #define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED 0x400UL + #define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED 0x800UL + #define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED 0x1000UL + #define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED 0x2000UL + #define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED 0x4000UL + #define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED 0x8000UL + #define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED 0x10000UL + #define FUNC_QCAPS_RESP_FLAGS_ADOPTED_PF_SUPPORTED 0x20000UL + #define FUNC_QCAPS_RESP_FLAGS_ADMIN_PF_SUPPORTED 0x40000UL + #define FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED 0x80000UL + #define FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE 0x100000UL + #define FUNC_QCAPS_RESP_FLAGS_DYNAMIC_TX_RING_ALLOC 0x200000UL + #define FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE 0x400000UL + #define FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE 0x800000UL + #define FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED 0x1000000UL + #define FUNC_QCAPS_RESP_FLAGS_ERR_RECOVER_RELOAD 0x2000000UL + #define FUNC_QCAPS_RESP_FLAGS_NOTIFY_VF_DEF_VNIC_CHNG_SUPPORTED 0x4000000UL u8 mac_address[6]; __le16 max_rsscos_ctx; __le16 max_cmpl_rings; @@ -1122,6 +1168,7 @@ struct hwrm_func_qcfg_output { #define FUNC_QCFG_RESP_FLAGS_MULTI_HOST 0x20UL #define FUNC_QCFG_RESP_FLAGS_TRUSTED_VF 0x40UL #define FUNC_QCFG_RESP_FLAGS_SECURE_MODE_ENABLED 0x80UL + #define FUNC_QCFG_RESP_FLAGS_PREBOOT_LEGACY_L2_RINGS 0x100UL u8 mac_address[6]; __le16 pci_id; __le16 alloc_rsscos_ctx; @@ -1204,7 +1251,8 @@ struct hwrm_func_qcfg_output { __le16 alloc_stat_ctx; __le16 alloc_msix; __le16 registered_vfs; - u8 unused_1[3]; + __le16 l2_doorbell_bar_size_kb; + u8 unused_1; u8 always_1; __le32 reset_addr_poll; u8 unused_2[3]; @@ -1241,6 +1289,7 @@ struct hwrm_func_cfg_input { #define FUNC_CFG_REQ_FLAGS_DYNAMIC_TX_RING_ALLOC 0x400000UL #define FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST 0x800000UL #define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE 0x1000000UL + #define FUNC_CFG_REQ_FLAGS_PREBOOT_LEGACY_L2_RINGS 0x2000000UL __le32 enables; #define FUNC_CFG_REQ_ENABLES_MTU 0x1UL #define FUNC_CFG_REQ_ENABLES_MRU 0x2UL @@ -1358,7 +1407,11 @@ struct hwrm_func_qstats_input { __le16 target_id; __le64 resp_addr; __le16 fid; - u8 unused_0[6]; + u8 flags; + #define FUNC_QSTATS_REQ_FLAGS_UNUSED 0x0UL + #define FUNC_QSTATS_REQ_FLAGS_ROCE_ONLY 0x1UL + #define FUNC_QSTATS_REQ_FLAGS_LAST FUNC_QSTATS_REQ_FLAGS_ROCE_ONLY + u8 unused_0[5]; }; /* hwrm_func_qstats_output (size:1408b/176B) */ @@ -2916,7 +2969,7 @@ struct tx_port_stats_ext { __le64 pfc_pri7_tx_transitions; }; -/* rx_port_stats_ext (size:2624b/328B) */ +/* rx_port_stats_ext (size:3648b/456B) */ struct rx_port_stats_ext { __le64 link_down_events; __le64 continuous_pause_events; @@ -2959,6 +3012,22 @@ struct rx_port_stats_ext { __le64 rx_buffer_passed_threshold; __le64 rx_pcs_symbol_err; __le64 rx_corrected_bits; + __le64 rx_discard_bytes_cos0; + __le64 rx_discard_bytes_cos1; + __le64 rx_discard_bytes_cos2; + __le64 rx_discard_bytes_cos3; + __le64 rx_discard_bytes_cos4; + __le64 rx_discard_bytes_cos5; + __le64 rx_discard_bytes_cos6; + __le64 rx_discard_bytes_cos7; + __le64 rx_discard_packets_cos0; + __le64 rx_discard_packets_cos1; + __le64 rx_discard_packets_cos2; + __le64 rx_discard_packets_cos3; + __le64 rx_discard_packets_cos4; + __le64 rx_discard_packets_cos5; + __le64 rx_discard_packets_cos6; + __le64 rx_discard_packets_cos7; }; /* hwrm_port_qstats_ext_input (size:320b/40B) */ @@ -4693,7 +4762,7 @@ struct hwrm_vnic_free_output { u8 valid; }; -/* hwrm_vnic_cfg_input (size:320b/40B) */ +/* hwrm_vnic_cfg_input (size:384b/48B) */ struct hwrm_vnic_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -4716,6 +4785,7 @@ struct hwrm_vnic_cfg_input { #define VNIC_CFG_REQ_ENABLES_MRU 0x10UL #define VNIC_CFG_REQ_ENABLES_DEFAULT_RX_RING_ID 0x20UL #define VNIC_CFG_REQ_ENABLES_DEFAULT_CMPL_RING_ID 0x40UL + #define VNIC_CFG_REQ_ENABLES_QUEUE_ID 0x80UL __le16 vnic_id; __le16 dflt_ring_grp; __le16 rss_rule; @@ -4724,6 +4794,8 @@ struct hwrm_vnic_cfg_input { __le16 mru; __le16 default_rx_ring_id; __le16 default_cmpl_ring_id; + __le16 queue_id; + u8 unused0[6]; }; /* hwrm_vnic_cfg_output (size:128b/16B) */ @@ -4764,6 +4836,7 @@ struct hwrm_vnic_qcaps_output { #define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP 0x20UL #define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP 0x40UL #define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_CAP 0x80UL + #define VNIC_QCAPS_RESP_FLAGS_COS_ASSIGNMENT_CAP 0x100UL __le16 max_aggs_supported; u8 unused_1[5]; u8 valid; @@ -6115,6 +6188,21 @@ struct hwrm_cfa_flow_alloc_output { u8 valid; }; +/* hwrm_cfa_flow_alloc_cmd_err (size:64b/8B) */ +struct hwrm_cfa_flow_alloc_cmd_err { + u8 code; + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_UNKNOWN 0x0UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_L2_CONTEXT_TCAM 0x1UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_ACTION_RECORD 0x2UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_COUNTER 0x3UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_WILD_CARD_TCAM 0x4UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_HASH_COLLISION 0x5UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_KEY_EXISTS 0x6UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB 0x7UL + #define CFA_FLOW_ALLOC_CMD_ERR_CODE_LAST CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB + u8 unused_0[7]; +}; + /* hwrm_cfa_flow_free_input (size:256b/32B) */ struct hwrm_cfa_flow_free_input { __le16 req_type; @@ -6305,7 +6393,7 @@ struct hwrm_cfa_eem_qcaps_input { __le32 unused_0; }; -/* hwrm_cfa_eem_qcaps_output (size:256b/32B) */ +/* hwrm_cfa_eem_qcaps_output (size:320b/40B) */ struct hwrm_cfa_eem_qcaps_output { __le16 error_code; __le16 req_type; @@ -6322,15 +6410,17 @@ struct hwrm_cfa_eem_qcaps_output { #define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY1_TABLE 0x2UL #define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_RECORD_TABLE 0x4UL #define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_FLOW_COUNTERS_TABLE 0x8UL + #define CFA_EEM_QCAPS_RESP_SUPPORTED_FID_TABLE 0x10UL __le32 max_entries_supported; __le16 key_entry_size; __le16 record_entry_size; __le16 efc_entry_size; - u8 unused_1; + __le16 fid_entry_size; + u8 unused_1[7]; u8 valid; }; -/* hwrm_cfa_eem_cfg_input (size:320b/40B) */ +/* hwrm_cfa_eem_cfg_input (size:384b/48B) */ struct hwrm_cfa_eem_cfg_input { __le16 req_type; __le16 cmpl_ring; @@ -6350,6 +6440,9 @@ struct hwrm_cfa_eem_cfg_input { __le16 key1_ctx_id; __le16 record_ctx_id; __le16 efc_ctx_id; + __le16 fid_ctx_id; + __le16 unused_2; + __le32 unused_3; }; /* hwrm_cfa_eem_cfg_output (size:128b/16B) */ @@ -6375,7 +6468,7 @@ struct hwrm_cfa_eem_qcfg_input { __le32 unused_0; }; -/* hwrm_cfa_eem_qcfg_output (size:192b/24B) */ +/* hwrm_cfa_eem_qcfg_output (size:256b/32B) */ struct hwrm_cfa_eem_qcfg_output { __le16 error_code; __le16 req_type; @@ -6386,7 +6479,12 @@ struct hwrm_cfa_eem_qcfg_output { #define CFA_EEM_QCFG_RESP_FLAGS_PATH_RX 0x2UL #define CFA_EEM_QCFG_RESP_FLAGS_PREFERRED_OFFLOAD 0x4UL __le32 num_entries; - u8 unused_0[7]; + __le16 key0_ctx_id; + __le16 key1_ctx_id; + __le16 record_ctx_id; + __le16 efc_ctx_id; + __le16 fid_ctx_id; + u8 unused_2[5]; u8 valid; }; @@ -6567,6 +6665,31 @@ struct ctx_hw_stats { __le64 tpa_aborts; }; +/* ctx_hw_stats_ext (size:1344b/168B) */ +struct ctx_hw_stats_ext { + __le64 rx_ucast_pkts; + __le64 rx_mcast_pkts; + __le64 rx_bcast_pkts; + __le64 rx_discard_pkts; + __le64 rx_drop_pkts; + __le64 rx_ucast_bytes; + __le64 rx_mcast_bytes; + __le64 rx_bcast_bytes; + __le64 tx_ucast_pkts; + __le64 tx_mcast_pkts; + __le64 tx_bcast_pkts; + __le64 tx_discard_pkts; + __le64 tx_drop_pkts; + __le64 tx_ucast_bytes; + __le64 tx_mcast_bytes; + __le64 tx_bcast_bytes; + __le64 rx_tpa_eligible_pkt; + __le64 rx_tpa_eligible_bytes; + __le64 rx_tpa_pkt; + __le64 rx_tpa_bytes; + __le64 rx_tpa_errors; +}; + /* hwrm_stat_ctx_alloc_input (size:256b/32B) */ struct hwrm_stat_ctx_alloc_input { __le16 req_type; @@ -6578,7 +6701,8 @@ struct hwrm_stat_ctx_alloc_input { __le32 update_period_ms; u8 stat_ctx_flags; #define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE 0x1UL - u8 unused_0[3]; + u8 unused_0; + __le16 stats_dma_length; }; /* hwrm_stat_ctx_alloc_output (size:128b/16B) */ @@ -6722,15 +6846,16 @@ struct hwrm_fw_reset_input { __le16 target_id; __le64 resp_addr; u8 embedded_proc_type; - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_BOOT 0x0UL - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT 0x1UL - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL 0x2UL - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE 0x3UL - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST 0x4UL - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP 0x5UL - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP 0x6UL - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST_RESOURCE_REINIT 0x7UL - #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_LAST FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST_RESOURCE_REINIT + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_BOOT 0x0UL + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT 0x1UL + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL 0x2UL + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE 0x3UL + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST 0x4UL + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP 0x5UL + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP 0x6UL + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST_RESOURCE_REINIT 0x7UL + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_IMPACTLESS_ACTIVATION 0x8UL + #define FW_RESET_REQ_EMBEDDED_PROC_TYPE_LAST FW_RESET_REQ_EMBEDDED_PROC_TYPE_IMPACTLESS_ACTIVATION u8 selfrst_status; #define FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE 0x0UL #define FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP 0x1UL @@ -7053,7 +7178,14 @@ struct hwrm_temp_monitor_query_output { __le16 seq_id; __le16 resp_len; u8 temp; - u8 unused_0[6]; + u8 phy_temp; + u8 om_temp; + u8 flags; + #define TEMP_MONITOR_QUERY_RESP_FLAGS_TEMP_NOT_AVAILABLE 0x1UL + #define TEMP_MONITOR_QUERY_RESP_FLAGS_PHY_TEMP_NOT_AVAILABLE 0x2UL + #define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_NOT_PRESENT 0x4UL + #define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_TEMP_NOT_AVAILABLE 0x8UL + u8 unused_0[3]; u8 valid; }; @@ -7204,7 +7336,9 @@ struct coredump_segment_record { u8 version_hi; u8 version_low; u8 seg_flags; - u8 unused_0[7]; + u8 compress_flags; + #define SFLAG_COMPRESSED_ZLIB 0x1UL + u8 unused_0[6]; }; /* hwrm_dbg_coredump_list_input (size:256b/32B) */ @@ -7729,6 +7863,9 @@ struct hwrm_nvm_set_variable_input { #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_AES256 (0x2UL << 1) #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH (0x3UL << 1) #define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH + #define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_MASK 0x70UL + #define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_SFT 4 + #define NVM_SET_VARIABLE_REQ_FLAGS_FACTORY_DEFAULT 0x80UL u8 unused_0; }; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index 2b90a2bb1a1d..f6f3454d6059 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -25,7 +25,6 @@ static int bnxt_hwrm_fwd_async_event_cmpl(struct bnxt *bp, struct bnxt_vf_info *vf, u16 event_id) { - struct hwrm_fwd_async_event_cmpl_output *resp = bp->hwrm_cmd_resp_addr; struct hwrm_fwd_async_event_cmpl_input req = {0}; struct hwrm_async_event_cmpl *async_cmpl; int rc = 0; @@ -40,23 +39,10 @@ static int bnxt_hwrm_fwd_async_event_cmpl(struct bnxt *bp, async_cmpl->type = cpu_to_le16(ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT); async_cmpl->event_id = cpu_to_le16(event_id); - mutex_lock(&bp->hwrm_cmd_lock); - rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - - if (rc) { + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) netdev_err(bp->dev, "hwrm_fwd_async_event_cmpl failed. rc:%d\n", rc); - goto fwd_async_event_cmpl_exit; - } - - if (resp->error_code) { - netdev_err(bp->dev, "hwrm_fwd_async_event_cmpl error %d\n", - resp->error_code); - rc = -1; - } - -fwd_async_event_cmpl_exit: - mutex_unlock(&bp->hwrm_cmd_lock); return rc; } @@ -133,7 +119,7 @@ static int bnxt_hwrm_func_qcfg_flags(struct bnxt *bp, struct bnxt_vf_info *vf) rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) { mutex_unlock(&bp->hwrm_cmd_lock); - return -EIO; + return rc; } vf->func_qcfg_flags = le16_to_cpu(resp->flags); mutex_unlock(&bp->hwrm_cmd_lock); @@ -164,9 +150,7 @@ static int bnxt_hwrm_set_trusted_vf(struct bnxt *bp, struct bnxt_vf_info *vf) else req.flags = cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - return -EIO; - return 0; + return rc; } int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trusted) @@ -486,10 +470,43 @@ static int bnxt_hwrm_func_buf_rgtr(struct bnxt *bp) return hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); } +/* Caller holds bp->hwrm_cmd_lock mutex lock */ +static void __bnxt_set_vf_params(struct bnxt *bp, int vf_id) +{ + struct hwrm_func_cfg_input req = {0}; + struct bnxt_vf_info *vf; + + vf = &bp->pf.vf[vf_id]; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FUNC_CFG, -1, -1); + req.fid = cpu_to_le16(vf->fw_fid); + req.flags = cpu_to_le32(vf->func_flags); + + if (is_valid_ether_addr(vf->mac_addr)) { + req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR); + memcpy(req.dflt_mac_addr, vf->mac_addr, ETH_ALEN); + } + if (vf->vlan) { + req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_DFLT_VLAN); + req.dflt_vlan = cpu_to_le16(vf->vlan); + } + if (vf->max_tx_rate) { + req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MAX_BW); + req.max_bw = cpu_to_le32(vf->max_tx_rate); +#ifdef HAVE_IFLA_TX_RATE + req.enables |= cpu_to_le32(FUNC_CFG_REQ_ENABLES_MIN_BW); + req.min_bw = cpu_to_le32(vf->min_tx_rate); +#endif + } + if (vf->flags & BNXT_VF_TRUST) + req.flags |= cpu_to_le32(FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE); + + _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); +} + /* Only called by PF to reserve resources for VFs, returns actual number of * VFs configured, or < 0 on error. */ -static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs) +static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs, bool reset) { struct hwrm_func_vf_resource_cfg_input req = {0}; struct bnxt_hw_resc *hw_resc = &bp->hw_resc; @@ -561,13 +578,14 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs) mutex_lock(&bp->hwrm_cmd_lock); for (i = 0; i < num_vfs; i++) { + if (reset) + __bnxt_set_vf_params(bp, i); + req.vf_id = cpu_to_le16(pf->first_vf_id + i); rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) { - rc = -ENOMEM; + if (rc) break; - } pf->active_vfs = i + 1; pf->vf[i].fw_fid = pf->first_vf_id + i; } @@ -664,8 +682,6 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs) total_vf_tx_rings += vf_tx_rsvd; } mutex_unlock(&bp->hwrm_cmd_lock); - if (rc) - rc = -ENOMEM; if (pf->active_vfs) { hw_resc->max_tx_rings -= total_vf_tx_rings; hw_resc->max_rx_rings -= vf_rx_rings * num_vfs; @@ -679,14 +695,40 @@ static int bnxt_hwrm_func_cfg(struct bnxt *bp, int num_vfs) return rc; } -static int bnxt_func_cfg(struct bnxt *bp, int num_vfs) +static int bnxt_func_cfg(struct bnxt *bp, int num_vfs, bool reset) { if (BNXT_NEW_RM(bp)) - return bnxt_hwrm_func_vf_resc_cfg(bp, num_vfs); + return bnxt_hwrm_func_vf_resc_cfg(bp, num_vfs, reset); else return bnxt_hwrm_func_cfg(bp, num_vfs); } +int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset) +{ + int rc; + + /* Register buffers for VFs */ + rc = bnxt_hwrm_func_buf_rgtr(bp); + if (rc) + return rc; + + /* Reserve resources for VFs */ + rc = bnxt_func_cfg(bp, *num_vfs, reset); + if (rc != *num_vfs) { + if (rc <= 0) { + netdev_warn(bp->dev, "Unable to reserve resources for SRIOV.\n"); + *num_vfs = 0; + return rc; + } + netdev_warn(bp->dev, "Only able to reserve resources for %d VFs.\n", + rc); + *num_vfs = rc; + } + + bnxt_ulp_sriov_cfg(bp, *num_vfs); + return 0; +} + static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs) { int rc = 0, vfs_supported; @@ -752,25 +794,10 @@ static int bnxt_sriov_enable(struct bnxt *bp, int *num_vfs) if (rc) goto err_out1; - /* Reserve resources for VFs */ - rc = bnxt_func_cfg(bp, *num_vfs); - if (rc != *num_vfs) { - if (rc <= 0) { - netdev_warn(bp->dev, "Unable to reserve resources for SRIOV.\n"); - *num_vfs = 0; - goto err_out2; - } - netdev_warn(bp->dev, "Only able to reserve resources for %d VFs.\n", rc); - *num_vfs = rc; - } - - /* Register buffers for VFs */ - rc = bnxt_hwrm_func_buf_rgtr(bp); + rc = bnxt_cfg_hw_sriov(bp, num_vfs, false); if (rc) goto err_out2; - bnxt_ulp_sriov_cfg(bp, *num_vfs); - rc = pci_enable_sriov(bp->pdev, *num_vfs); if (rc) goto err_out2; @@ -837,6 +864,11 @@ int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs) rtnl_unlock(); return 0; } + if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state)) { + netdev_warn(dev, "Reject SRIOV config request when FW reset is in progress\n"); + rtnl_unlock(); + return 0; + } bp->sriov_cfg = true; rtnl_unlock(); @@ -870,7 +902,6 @@ static int bnxt_hwrm_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf, { int rc = 0; struct hwrm_fwd_resp_input req = {0}; - struct hwrm_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr; if (BNXT_FWD_RESP_SIZE_ERR(msg_size)) return -EINVAL; @@ -885,22 +916,9 @@ static int bnxt_hwrm_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf, req.encap_resp_cmpl_ring = encap_resp_cpr; memcpy(req.encap_resp, encap_resp, msg_size); - mutex_lock(&bp->hwrm_cmd_lock); - rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - - if (rc) { + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) netdev_err(bp->dev, "hwrm_fwd_resp failed. rc:%d\n", rc); - goto fwd_resp_exit; - } - - if (resp->error_code) { - netdev_err(bp->dev, "hwrm_fwd_resp error %d\n", - resp->error_code); - rc = -1; - } - -fwd_resp_exit: - mutex_unlock(&bp->hwrm_cmd_lock); return rc; } @@ -909,7 +927,6 @@ static int bnxt_hwrm_fwd_err_resp(struct bnxt *bp, struct bnxt_vf_info *vf, { int rc = 0; struct hwrm_reject_fwd_resp_input req = {0}; - struct hwrm_reject_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr; if (BNXT_REJ_FWD_RESP_SIZE_ERR(msg_size)) return -EINVAL; @@ -920,22 +937,9 @@ static int bnxt_hwrm_fwd_err_resp(struct bnxt *bp, struct bnxt_vf_info *vf, req.encap_resp_target_id = cpu_to_le16(vf->fw_fid); memcpy(req.encap_request, vf->hwrm_cmd_req_addr, msg_size); - mutex_lock(&bp->hwrm_cmd_lock); - rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - - if (rc) { + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) netdev_err(bp->dev, "hwrm_fwd_err_resp failed. rc:%d\n", rc); - goto fwd_err_resp_exit; - } - - if (resp->error_code) { - netdev_err(bp->dev, "hwrm_fwd_err_resp error %d\n", - resp->error_code); - rc = -1; - } - -fwd_err_resp_exit: - mutex_unlock(&bp->hwrm_cmd_lock); return rc; } @@ -944,7 +948,6 @@ static int bnxt_hwrm_exec_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf, { int rc = 0; struct hwrm_exec_fwd_resp_input req = {0}; - struct hwrm_exec_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr; if (BNXT_EXEC_FWD_RESP_SIZE_ERR(msg_size)) return -EINVAL; @@ -955,22 +958,9 @@ static int bnxt_hwrm_exec_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf, req.encap_resp_target_id = cpu_to_le16(vf->fw_fid); memcpy(req.encap_request, vf->hwrm_cmd_req_addr, msg_size); - mutex_lock(&bp->hwrm_cmd_lock); - rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - - if (rc) { + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) netdev_err(bp->dev, "hwrm_exec_fw_resp failed. rc:%d\n", rc); - goto exec_fwd_resp_exit; - } - - if (resp->error_code) { - netdev_err(bp->dev, "hwrm_exec_fw_resp error %d\n", - resp->error_code); - rc = -1; - } - -exec_fwd_resp_exit: - mutex_unlock(&bp->hwrm_cmd_lock); return rc; } @@ -1190,6 +1180,13 @@ mac_done: } #else +int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset) +{ + if (*num_vfs) + return -EOPNOTSUPP; + return 0; +} + void bnxt_sriov_disable(struct bnxt *bp) { } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h index 2eed9eda1195..629641bf6fc5 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -36,6 +36,7 @@ int bnxt_set_vf_link_state(struct net_device *, int, int); int bnxt_set_vf_spoofchk(struct net_device *, int, bool); int bnxt_set_vf_trust(struct net_device *dev, int vf_id, bool trust); int bnxt_sriov_configure(struct pci_dev *pdev, int num_vfs); +int bnxt_cfg_hw_sriov(struct bnxt *bp, int *num_vfs, bool reset); void bnxt_sriov_disable(struct bnxt *); void bnxt_hwrm_exec_fwd_req(struct bnxt *); void bnxt_update_vf_mac(struct bnxt *); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c index dd621f6bd127..c8062d020d1e 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c @@ -319,8 +319,6 @@ static int bnxt_hwrm_cfa_flow_free(struct bnxt *bp, if (rc) netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); - if (rc) - rc = -EIO; return rc; } @@ -515,11 +513,6 @@ static int bnxt_hwrm_cfa_flow_alloc(struct bnxt *bp, struct bnxt_tc_flow *flow, } } mutex_unlock(&bp->hwrm_cmd_lock); - - if (rc == HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR) - rc = -ENOSPC; - else if (rc) - rc = -EIO; return rc; } @@ -591,8 +584,6 @@ static int hwrm_cfa_decap_filter_alloc(struct bnxt *bp, } mutex_unlock(&bp->hwrm_cmd_lock); - if (rc) - rc = -EIO; return rc; } @@ -609,8 +600,6 @@ static int hwrm_cfa_decap_filter_free(struct bnxt *bp, if (rc) netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); - if (rc) - rc = -EIO; return rc; } @@ -660,8 +649,6 @@ static int hwrm_cfa_encap_record_alloc(struct bnxt *bp, } mutex_unlock(&bp->hwrm_cmd_lock); - if (rc) - rc = -EIO; return rc; } @@ -678,8 +665,6 @@ static int hwrm_cfa_encap_record_free(struct bnxt *bp, if (rc) netdev_info(bp->dev, "%s: Error rc=%d", __func__, rc); - if (rc) - rc = -EIO; return rc; } @@ -1457,8 +1442,6 @@ bnxt_hwrm_cfa_flow_stats_get(struct bnxt *bp, int num_flows, } mutex_unlock(&bp->hwrm_cmd_lock); - if (rc) - rc = -EIO; return rc; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c index fc77caf0a076..b2c160947fc8 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c @@ -226,6 +226,9 @@ static int bnxt_send_msg(struct bnxt_en_dev *edev, int ulp_id, struct input *req; int rc; + if (ulp_id != BNXT_ROCE_ULP && bp->fw_reset_state) + return -EBUSY; + mutex_lock(&bp->hwrm_cmd_lock); req = fw_msg->msg; req->resp_addr = cpu_to_le64(bp->hwrm_cmd_resp_dma_addr); diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 57dc3cbff36e..155599dcee76 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -4096,12 +4096,16 @@ static int cnic_cm_alloc_mem(struct cnic_dev *dev) { struct cnic_local *cp = dev->cnic_priv; u32 port_id; + int i; cp->csk_tbl = kvcalloc(MAX_CM_SK_TBL_SZ, sizeof(struct cnic_sock), GFP_KERNEL); if (!cp->csk_tbl) return -ENOMEM; + for (i = 0; i < MAX_CM_SK_TBL_SZ; i++) + atomic_set(&cp->csk_tbl[i].ref_count, 0); + port_id = prandom_u32(); port_id %= CNIC_LOCAL_PORT_RANGE; if (cnic_init_id_tbl(&cp->csk_port_tbl, CNIC_LOCAL_PORT_RANGE, @@ -5480,6 +5484,7 @@ static struct cnic_dev *cnic_alloc_dev(struct net_device *dev, cdev->unregister_device = cnic_unregister_device; cdev->iscsi_nl_msg_recv = cnic_iscsi_nl_msg_recv; cdev->get_fc_npiv_tbl = cnic_get_fc_npiv_tbl; + atomic_set(&cdev->ref_count, 0); cp = cdev->cnic_priv; cp->dev = cdev; diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index b22196880d6d..12cb77ef1081 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -2516,19 +2516,14 @@ static int bcmgenet_dma_teardown(struct bcmgenet_priv *priv) static void bcmgenet_fini_dma(struct bcmgenet_priv *priv) { struct netdev_queue *txq; - struct sk_buff *skb; - struct enet_cb *cb; int i; bcmgenet_fini_rx_napi(priv); bcmgenet_fini_tx_napi(priv); - for (i = 0; i < priv->num_tx_bds; i++) { - cb = priv->tx_cbs + i; - skb = bcmgenet_free_tx_cb(&priv->pdev->dev, cb); - if (skb) - dev_kfree_skb(skb); - } + for (i = 0; i < priv->num_tx_bds; i++) + dev_kfree_skb(bcmgenet_free_tx_cb(&priv->pdev->dev, + priv->tx_cbs + i)); for (i = 0; i < priv->hw_params->tx_queues; i++) { txq = netdev_get_tx_queue(priv->dev, priv->tx_rings[i].queue); @@ -3438,7 +3433,6 @@ static int bcmgenet_probe(struct platform_device *pdev) struct bcmgenet_priv *priv; struct net_device *dev; const void *macaddr; - struct resource *r; unsigned int i; int err = -EIO; const char *phy_mode_str; @@ -3478,8 +3472,7 @@ static int bcmgenet_probe(struct platform_device *pdev) macaddr = pd->mac_address; } - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->base = devm_ioremap_resource(&pdev->dev, r); + priv->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->base)) { err = PTR_ERR(priv->base); goto err; diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 4c404d2213f9..77f3511b97de 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -18041,8 +18041,7 @@ static void tg3_remove_one(struct pci_dev *pdev) #ifdef CONFIG_PM_SLEEP static int tg3_suspend(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct tg3 *tp = netdev_priv(dev); int err = 0; @@ -18098,8 +18097,7 @@ unlock: static int tg3_resume(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct tg3 *tp = netdev_priv(dev); int err = 0; diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c index 7767ae6fa1fd..e338272931d1 100644 --- a/drivers/net/ethernet/brocade/bna/bnad.c +++ b/drivers/net/ethernet/brocade/bna/bnad.c @@ -3032,7 +3032,7 @@ bnad_start_xmit(struct sk_buff *skb, struct net_device *netdev) head_unmap->nvecs++; for (i = 0, vect_id = 0; i < vectors - 1; i++) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; u32 size = skb_frag_size(frag); if (unlikely(size == 0)) { diff --git a/drivers/net/ethernet/calxeda/xgmac.c b/drivers/net/ethernet/calxeda/xgmac.c index 99f49d059414..f96a42af1014 100644 --- a/drivers/net/ethernet/calxeda/xgmac.c +++ b/drivers/net/ethernet/calxeda/xgmac.c @@ -1104,7 +1104,7 @@ static netdev_tx_t xgmac_xmit(struct sk_buff *skb, struct net_device *dev) for (i = 0; i < nfrags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - len = frag->size; + len = skb_frag_size(frag); paddr = skb_frag_dma_map(priv->device, frag, 0, len, DMA_TO_DEVICE); diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index eab805579f96..7f3b2e3b0868 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -1492,11 +1492,11 @@ static void free_netsgbuf(void *buf) i = 1; while (frags--) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; pci_unmap_page((lio->oct_dev)->pci_dev, g->sg[(i >> 2)].ptr[(i & 3)], - frag->size, DMA_TO_DEVICE); + skb_frag_size(frag), DMA_TO_DEVICE); i++; } @@ -1535,11 +1535,11 @@ static void free_netsgbuf_with_resp(void *buf) i = 1; while (frags--) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; pci_unmap_page((lio->oct_dev)->pci_dev, g->sg[(i >> 2)].ptr[(i & 3)], - frag->size, DMA_TO_DEVICE); + skb_frag_size(frag), DMA_TO_DEVICE); i++; } @@ -2424,7 +2424,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) } else { int i, frags; - struct skb_frag_struct *frag; + skb_frag_t *frag; struct octnic_gather *g; spin_lock(&lio->glist_lock[q_idx]); @@ -2462,11 +2462,9 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) frag = &skb_shinfo(skb)->frags[i - 1]; g->sg[(i >> 2)].ptr[(i & 3)] = - dma_map_page(&oct->pci_dev->dev, - frag->page.p, - frag->page_offset, - frag->size, - DMA_TO_DEVICE); + skb_frag_dma_map(&oct->pci_dev->dev, + frag, 0, skb_frag_size(frag), + DMA_TO_DEVICE); if (dma_mapping_error(&oct->pci_dev->dev, g->sg[i >> 2].ptr[i & 3])) { @@ -2478,7 +2476,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) frag = &skb_shinfo(skb)->frags[j - 1]; dma_unmap_page(&oct->pci_dev->dev, g->sg[j >> 2].ptr[j & 3], - frag->size, + skb_frag_size(frag), DMA_TO_DEVICE); } dev_err(&oct->pci_dev->dev, "%s DMA mapping error 3\n", @@ -2486,7 +2484,8 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_BUSY; } - add_sg_size(&g->sg[(i >> 2)], frag->size, (i & 3)); + add_sg_size(&g->sg[(i >> 2)], skb_frag_size(frag), + (i & 3)); i++; } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index db0b90555acb..370d76822ee0 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -837,11 +837,11 @@ static void free_netsgbuf(void *buf) i = 1; while (frags--) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; pci_unmap_page((lio->oct_dev)->pci_dev, g->sg[(i >> 2)].ptr[(i & 3)], - frag->size, DMA_TO_DEVICE); + skb_frag_size(frag), DMA_TO_DEVICE); i++; } @@ -881,11 +881,11 @@ static void free_netsgbuf_with_resp(void *buf) i = 1; while (frags--) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i - 1]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1]; pci_unmap_page((lio->oct_dev)->pci_dev, g->sg[(i >> 2)].ptr[(i & 3)], - frag->size, DMA_TO_DEVICE); + skb_frag_size(frag), DMA_TO_DEVICE); i++; } @@ -1497,7 +1497,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) ndata.reqtype = REQTYPE_NORESP_NET; } else { - struct skb_frag_struct *frag; + skb_frag_t *frag; struct octnic_gather *g; int i, frags; @@ -1535,11 +1535,9 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) frag = &skb_shinfo(skb)->frags[i - 1]; g->sg[(i >> 2)].ptr[(i & 3)] = - dma_map_page(&oct->pci_dev->dev, - frag->page.p, - frag->page_offset, - frag->size, - DMA_TO_DEVICE); + skb_frag_dma_map(&oct->pci_dev->dev, + frag, 0, skb_frag_size(frag), + DMA_TO_DEVICE); if (dma_mapping_error(&oct->pci_dev->dev, g->sg[i >> 2].ptr[i & 3])) { dma_unmap_single(&oct->pci_dev->dev, @@ -1550,7 +1548,7 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) frag = &skb_shinfo(skb)->frags[j - 1]; dma_unmap_page(&oct->pci_dev->dev, g->sg[j >> 2].ptr[j & 3], - frag->size, + skb_frag_size(frag), DMA_TO_DEVICE); } dev_err(&oct->pci_dev->dev, "%s DMA mapping error 3\n", @@ -1558,7 +1556,8 @@ static netdev_tx_t liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) return NETDEV_TX_BUSY; } - add_sg_size(&g->sg[(i >> 2)], frag->size, (i & 3)); + add_sg_size(&g->sg[(i >> 2)], skb_frag_size(frag), + (i & 3)); i++; } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c index 021d99cd1665..614d07be7181 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c @@ -260,9 +260,7 @@ static int octeon_mbox_process_cmd(struct octeon_mbox *mbox, dev_info(&oct->pci_dev->dev, "got a request for FLR from VF that owns DPI ring %u\n", mbox->q_no); - pcie_capability_set_word( - oct->sriov_info.dpiring_to_vfpcidev_lut[mbox->q_no], - PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR); + pcie_flr(oct->sriov_info.dpiring_to_vfpcidev_lut[mbox->q_no]); break; case OCTEON_PF_CHANGED_VF_MACADDR: diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c index 192bc92da881..4ab57d33a87e 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_queues.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_queues.c @@ -1588,15 +1588,13 @@ int nicvf_sq_append_skb(struct nicvf *nic, struct snd_queue *sq, goto doorbell; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - const struct skb_frag_struct *frag; - - frag = &skb_shinfo(skb)->frags[i]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; qentry = nicvf_get_nxt_sqentry(sq, qentry); size = skb_frag_size(frag); dma_addr = dma_map_page_attrs(&nic->pdev->dev, skb_frag_page(frag), - frag->page_offset, size, + skb_frag_off(frag), size, DMA_TO_DEVICE, DMA_ATTR_SKIP_CPU_SYNC); if (dma_mapping_error(&nic->pdev->dev, dma_addr)) { diff --git a/drivers/net/ethernet/chelsio/cxgb3/sge.c b/drivers/net/ethernet/chelsio/cxgb3/sge.c index 89db739b7819..6dabbf1502c7 100644 --- a/drivers/net/ethernet/chelsio/cxgb3/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb3/sge.c @@ -2132,7 +2132,7 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs, struct port_info *pi = netdev_priv(qs->netdev); struct sk_buff *skb = NULL; struct cpl_rx_pkt *cpl; - struct skb_frag_struct *rx_frag; + skb_frag_t *rx_frag; int nr_frags; int offset = 0; @@ -2182,7 +2182,7 @@ static void lro_add_page(struct adapter *adap, struct sge_qset *qs, rx_frag += nr_frags; __skb_frag_set_page(rx_frag, sd->pg_chunk.page); - rx_frag->page_offset = sd->pg_chunk.offset + offset; + skb_frag_off_set(rx_frag, sd->pg_chunk.offset + offset); skb_frag_size_set(rx_frag, len); skb->len += len; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c index d692251ee252..ae6a47dd7dc9 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_debugfs.c @@ -3531,7 +3531,6 @@ int t4_setup_debugfs(struct adapter *adap) { int i; u32 size = 0; - struct dentry *de; static struct t4_debugfs_entry t4_debugfs_files[] = { { "cim_la", &cim_la_fops, 0400, 0 }, @@ -3642,8 +3641,8 @@ int t4_setup_debugfs(struct adapter *adap) } } - de = debugfs_create_file_size("flash", 0400, adap->debugfs_root, adap, - &flash_debugfs_fops, adap->params.sf_size); + debugfs_create_file_size("flash", 0400, adap->debugfs_root, adap, + &flash_debugfs_fops, adap->params.sf_size); debugfs_create_bool("use_backdoor", 0600, adap->debugfs_root, &adap->use_bd); debugfs_create_bool("trace_rss", 0600, diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 4311ad9c84b2..71854a19cebe 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -6269,10 +6269,7 @@ static int __init cxgb4_init_module(void) { int ret; - /* Debugfs support is optional, just warn if this fails */ cxgb4_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL); - if (!cxgb4_debugfs_root) - pr_warn("could not create debugfs entry, continuing\n"); ret = pci_register_driver(&cxgb4_driver); if (ret < 0) diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.c b/drivers/net/ethernet/chelsio/cxgb4/smt.c index eaf1fb74689c..01c65d13fc0e 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/smt.c +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.c @@ -57,7 +57,7 @@ struct smt_data *t4_init_smt(void) s->smtab[i].state = SMT_STATE_UNUSED; memset(&s->smtab[i].src_mac, 0, ETH_ALEN); spin_lock_init(&s->smtab[i].lock); - atomic_set(&s->smtab[i].refcnt, 0); + s->smtab[i].refcnt = 0; } return s; } @@ -68,7 +68,7 @@ static struct smt_entry *find_or_alloc_smte(struct smt_data *s, u8 *smac) struct smt_entry *e, *end; for (e = &s->smtab[0], end = &s->smtab[s->smt_size]; e != end; ++e) { - if (atomic_read(&e->refcnt) == 0) { + if (e->refcnt == 0) { if (!first_free) first_free = e; } else { @@ -97,11 +97,9 @@ found_reuse: static void t4_smte_free(struct smt_entry *e) { - spin_lock_bh(&e->lock); - if (atomic_read(&e->refcnt) == 0) { /* hasn't been recycled */ + if (e->refcnt == 0) { /* hasn't been recycled */ e->state = SMT_STATE_UNUSED; } - spin_unlock_bh(&e->lock); } /** @@ -111,8 +109,10 @@ static void t4_smte_free(struct smt_entry *e) */ void cxgb4_smt_release(struct smt_entry *e) { - if (atomic_dec_and_test(&e->refcnt)) + spin_lock_bh(&e->lock); + if ((--e->refcnt) == 0) t4_smte_free(e); + spin_unlock_bh(&e->lock); } EXPORT_SYMBOL(cxgb4_smt_release); @@ -215,14 +215,14 @@ static struct smt_entry *t4_smt_alloc_switching(struct adapter *adap, u16 pfvf, e = find_or_alloc_smte(s, smac); if (e) { spin_lock(&e->lock); - if (!atomic_read(&e->refcnt)) { - atomic_set(&e->refcnt, 1); + if (!e->refcnt) { + e->refcnt = 1; e->state = SMT_STATE_SWITCHING; e->pfvf = pfvf; memcpy(e->src_mac, smac, ETH_ALEN); write_smt_entry(adap, e); } else { - atomic_inc(&e->refcnt); + ++e->refcnt; } spin_unlock(&e->lock); } diff --git a/drivers/net/ethernet/chelsio/cxgb4/smt.h b/drivers/net/ethernet/chelsio/cxgb4/smt.h index d6c2cc271398..1268d6e93a47 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/smt.h +++ b/drivers/net/ethernet/chelsio/cxgb4/smt.h @@ -59,7 +59,7 @@ struct smt_entry { u16 idx; u16 pfvf; u8 src_mac[ETH_ALEN]; - atomic_t refcnt; + int refcnt; spinlock_t lock; /* protect smt entry add,removal */ }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c index f7fc553356f2..f2a7824da42b 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_hw.c @@ -329,7 +329,7 @@ int t4_wr_mbox_meat_timeout(struct adapter *adap, int mbox, const void *cmd, for (i = 0; ; i += ms) { /* If we've waited too long, return a busy indication. This * really ought to be based on our initial position in the - * mailbox access list but this is a start. We very rearely + * mailbox access list but this is a start. We very rarely * contend on access to the mailbox ... */ pcie_fw = t4_read_reg(adap, PCIE_FW_A); @@ -606,7 +606,7 @@ void t4_memory_rw_residual(struct adapter *adap, u32 off, u32 addr, u8 *buf, * * Reads/writes an [almost] arbitrary memory region in the firmware: the * firmware memory address and host buffer must be aligned on 32-bit - * boudaries; the length may be arbitrary. The memory is transferred as + * boundaries; the length may be arbitrary. The memory is transferred as * a raw byte sequence from/to the firmware's memory. If this memory * contains data structures which contain multi-byte integers, it's the * caller's responsibility to perform appropriate byte order conversions. @@ -3774,7 +3774,7 @@ int t4_phy_fw_ver(struct adapter *adap, int *phy_fw_ver) * A negative error number will be returned if an error occurs. If * version number support is available and there's no need to upgrade * the firmware, 0 will be returned. If firmware is successfully - * transferred to the adapter, 1 will be retured. + * transferred to the adapter, 1 will be returned. * * NOTE: some adapters only have local RAM to store the PHY firmware. As * a result, a RESET of the adapter would cause that RAM to lose its @@ -3808,7 +3808,7 @@ int t4_load_phy_fw(struct adapter *adap, } /* Ask the firmware where it wants us to copy the PHY firmware image. - * The size of the file requires a special version of the READ coommand + * The size of the file requires a special version of the READ command * which will pass the file size via the values field in PARAMS_CMD and * retrieve the return value from firmware and place it in the same * buffer values @@ -4082,7 +4082,7 @@ static inline fw_port_cap32_t cc_to_fwcap_pause(enum cc_pause cc_pause) fw_pause |= FW_PORT_CAP32_FORCE_PAUSE; /* Translate orthogonal Pause controls into IEEE 802.3 Pause, - * Asymetrical Pause for use in reporting to upper layer OS code, etc. + * Asymmetrical Pause for use in reporting to upper layer OS code, etc. * Note that these bits are ignored in L1 Configure commands. */ if (cc_pause & PAUSE_RX) { @@ -4151,7 +4151,7 @@ fw_port_cap32_t t4_link_acaps(struct adapter *adapter, unsigned int port, /* Convert Common Code Forward Error Control settings into the * Firmware's API. If the current Requested FEC has "Automatic" * (IEEE 802.3) specified, then we use whatever the Firmware - * sent us as part of it's IEEE 802.3-based interpratation of + * sent us as part of its IEEE 802.3-based interpretation of * the Transceiver Module EPROM FEC parameters. Otherwise we * use whatever is in the current Requested FEC settings. */ @@ -4248,7 +4248,7 @@ int t4_link_l1cfg_core(struct adapter *adapter, unsigned int mbox, /* Unfortunately, even if the Requested Port Capabilities "fit" within * the Physical Port Capabilities, some combinations of features may - * still not be leagal. For example, 40Gb/s and Reed-Solomon Forward + * still not be legal. For example, 40Gb/s and Reed-Solomon Forward * Error Correction. So if the Firmware rejects the L1 Configure * request, flag that here. */ @@ -6797,7 +6797,7 @@ int t4_sge_ctxt_flush(struct adapter *adap, unsigned int mbox, int ctxt_type) } /** - * t4_read_sge_dbqtimers - reag SGE Doorbell Queue Timer values + * t4_read_sge_dbqtimers - read SGE Doorbell Queue Timer values * @adap - the adapter * @ndbqtimers: size of the provided SGE Doorbell Queue Timer table * @dbqtimers: SGE Doorbell Queue Timer table @@ -6925,8 +6925,8 @@ retry: waiting -= 50; /* - * If neither Error nor Initialialized are indicated - * by the firmware keep waiting till we exaust our + * If neither Error nor Initialized are indicated + * by the firmware keep waiting till we exhaust our * timeout ... and then retry if we haven't exhausted * our retries ... */ @@ -7238,7 +7238,7 @@ int t4_fl_pkt_align(struct adapter *adap) * separately. The actual Ingress Packet Data alignment boundary * within Packed Buffer Mode is the maximum of these two * specifications. (Note that it makes no real practical sense to - * have the Pading Boudary be larger than the Packing Boundary but you + * have the Padding Boundary be larger than the Packing Boundary but you * could set the chip up that way and, in fact, legacy T4 code would * end doing this because it would initialize the Padding Boundary and * leave the Packing Boundary initialized to 0 (16 bytes).) @@ -8973,10 +8973,10 @@ static int t4_get_flash_params(struct adapter *adap) goto found; } - /* Decode Flash part size. The code below looks repetative with + /* Decode Flash part size. The code below looks repetitive with * common encodings, but that's not guaranteed in the JEDEC - * specification for the Read JADEC ID command. The only thing that - * we're guaranteed by the JADEC specification is where the + * specification for the Read JEDEC ID command. The only thing that + * we're guaranteed by the JEDEC specification is where the * Manufacturer ID is in the returned result. After that each * Manufacturer ~could~ encode things completely differently. * Note, all Flash parts must have 64KB sectors. @@ -9317,7 +9317,7 @@ int t4_init_devlog_params(struct adapter *adap) struct fw_devlog_cmd devlog_cmd; int ret; - /* If we're dealing with newer firmware, the Device Log Paramerters + /* If we're dealing with newer firmware, the Device Log Parameters * are stored in a designated register which allows us to access the * Device Log even if we can't talk to the firmware. */ diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 6d4cf3d0b2f0..f6fc0875d5b0 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -2478,11 +2478,10 @@ static int setup_debugfs(struct adapter *adapter) * Debugfs support is best effort. */ for (i = 0; i < ARRAY_SIZE(debugfs_files); i++) - (void)debugfs_create_file(debugfs_files[i].name, - debugfs_files[i].mode, - adapter->debugfs_root, - (void *)adapter, - debugfs_files[i].fops); + debugfs_create_file(debugfs_files[i].name, + debugfs_files[i].mode, + adapter->debugfs_root, (void *)adapter, + debugfs_files[i].fops); return 0; } @@ -3257,11 +3256,7 @@ static int cxgb4vf_pci_probe(struct pci_dev *pdev, adapter->debugfs_root = debugfs_create_dir(pci_name(pdev), cxgb4vf_debugfs_root); - if (IS_ERR_OR_NULL(adapter->debugfs_root)) - dev_warn(&pdev->dev, "could not create debugfs" - " directory"); - else - setup_debugfs(adapter); + setup_debugfs(adapter); } /* @@ -3486,13 +3481,11 @@ static int __init cxgb4vf_module_init(void) return -EINVAL; } - /* Debugfs support is optional, just warn if this fails */ + /* Debugfs support is optional, debugfs will warn if this fails */ cxgb4vf_debugfs_root = debugfs_create_dir(KBUILD_MODNAME, NULL); - if (IS_ERR_OR_NULL(cxgb4vf_debugfs_root)) - pr_warn("could not create debugfs entry, continuing\n"); ret = pci_register_driver(&cxgb4vf_driver); - if (ret < 0 && !IS_ERR_OR_NULL(cxgb4vf_debugfs_root)) + if (ret < 0) debugfs_remove(cxgb4vf_debugfs_root); return ret; } diff --git a/drivers/net/ethernet/cirrus/cs89x0.c b/drivers/net/ethernet/cirrus/cs89x0.c index b3e7fafee3df..c9aebcde403a 100644 --- a/drivers/net/ethernet/cirrus/cs89x0.c +++ b/drivers/net/ethernet/cirrus/cs89x0.c @@ -1844,16 +1844,12 @@ cleanup_module(void) static int __init cs89x0_platform_probe(struct platform_device *pdev) { struct net_device *dev = alloc_etherdev(sizeof(struct net_local)); - struct net_local *lp; - struct resource *mem_res; void __iomem *virt_addr; int err; if (!dev) return -ENOMEM; - lp = netdev_priv(dev); - dev->irq = platform_get_irq(pdev, 0); if (dev->irq <= 0) { dev_warn(&dev->dev, "interrupt resource missing\n"); @@ -1861,8 +1857,7 @@ static int __init cs89x0_platform_probe(struct platform_device *pdev) goto free; } - mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - virt_addr = devm_ioremap_resource(&pdev->dev, mem_res); + virt_addr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(virt_addr)) { err = PTR_ERR(virt_addr); goto free; diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 9003eb6716cd..e736ce2c58ca 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1182,9 +1182,8 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb, buflen = skb_headlen(skb); } else { skb_frag = skb_si->frags + frag; - buffer = page_address(skb_frag_page(skb_frag)) + - skb_frag->page_offset; - buflen = skb_frag->size; + buffer = skb_frag_address(skb_frag); + buflen = skb_frag_size(skb_frag); } if (frag == last_frag) { @@ -2423,10 +2422,8 @@ static int gemini_ethernet_port_probe(struct platform_device *pdev) /* Interrupt */ irq = platform_get_irq(pdev, 0); - if (irq <= 0) { - dev_err(dev, "no IRQ\n"); + if (irq <= 0) return irq ? irq : -ENODEV; - } port->irq = irq; /* Clock the port */ diff --git a/drivers/net/ethernet/davicom/dm9000.c b/drivers/net/ethernet/davicom/dm9000.c index 386bdc1378d1..cce90b5925d9 100644 --- a/drivers/net/ethernet/davicom/dm9000.c +++ b/drivers/net/ethernet/davicom/dm9000.c @@ -1500,8 +1500,6 @@ dm9000_probe(struct platform_device *pdev) ndev->irq = platform_get_irq(pdev, 0); if (ndev->irq < 0) { - dev_err(db->dev, "interrupt resource unavailable: %d\n", - ndev->irq); ret = ndev->irq; goto out; } diff --git a/drivers/net/ethernet/emulex/benet/be.h b/drivers/net/ethernet/emulex/benet/be.h index f287b5da5546..cf3e6f2892ff 100644 --- a/drivers/net/ethernet/emulex/benet/be.h +++ b/drivers/net/ethernet/emulex/benet/be.h @@ -192,7 +192,6 @@ struct be_eq_obj { } ____cacheline_aligned_in_smp; struct be_aic_obj { /* Adaptive interrupt coalescing (AIC) info */ - bool enable; u32 min_eqd; /* in usecs */ u32 max_eqd; /* in usecs */ u32 prev_eqd; /* in usecs */ @@ -589,6 +588,7 @@ struct be_adapter { struct be_drv_stats drv_stats; struct be_aic_obj aic_obj[MAX_EVT_QS]; + bool aic_enabled; u8 vlan_prio_bmap; /* Available Priority BitMap */ u16 recommended_prio_bits;/* Recommended Priority bits in vlan tag */ struct be_dma_mem rx_filter; /* Cmd DMA mem for rx-filter */ diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c index 323976c811e9..701c12c9e033 100644 --- a/drivers/net/ethernet/emulex/benet/be_cmds.c +++ b/drivers/net/ethernet/emulex/benet/be_cmds.c @@ -2756,7 +2756,7 @@ static int be_flash_BEx(struct be_adapter *adapter, bool crc_match; const u8 *p; - struct flash_comp gen3_flash_types[] = { + static const struct flash_comp gen3_flash_types[] = { { BE3_ISCSI_PRIMARY_IMAGE_START, OPTYPE_ISCSI_ACTIVE, BE3_COMP_MAX_SIZE, IMAGE_FIRMWARE_ISCSI}, { BE3_REDBOOT_START, OPTYPE_REDBOOT, @@ -2779,7 +2779,7 @@ static int be_flash_BEx(struct be_adapter *adapter, BE3_PHY_FW_COMP_MAX_SIZE, IMAGE_FIRMWARE_PHY} }; - struct flash_comp gen2_flash_types[] = { + static const struct flash_comp gen2_flash_types[] = { { BE2_ISCSI_PRIMARY_IMAGE_START, OPTYPE_ISCSI_ACTIVE, BE2_COMP_MAX_SIZE, IMAGE_FIRMWARE_ISCSI}, { BE2_REDBOOT_START, OPTYPE_REDBOOT, diff --git a/drivers/net/ethernet/emulex/benet/be_ethtool.c b/drivers/net/ethernet/emulex/benet/be_ethtool.c index 492f8769ac12..5bb5abf99588 100644 --- a/drivers/net/ethernet/emulex/benet/be_ethtool.c +++ b/drivers/net/ethernet/emulex/benet/be_ethtool.c @@ -329,8 +329,8 @@ static int be_get_coalesce(struct net_device *netdev, et->tx_coalesce_usecs_high = aic->max_eqd; et->tx_coalesce_usecs_low = aic->min_eqd; - et->use_adaptive_rx_coalesce = aic->enable; - et->use_adaptive_tx_coalesce = aic->enable; + et->use_adaptive_rx_coalesce = adapter->aic_enabled; + et->use_adaptive_tx_coalesce = adapter->aic_enabled; return 0; } @@ -346,8 +346,9 @@ static int be_set_coalesce(struct net_device *netdev, struct be_eq_obj *eqo; int i; + adapter->aic_enabled = et->use_adaptive_rx_coalesce; + for_all_evt_queues(adapter, eqo, i) { - aic->enable = et->use_adaptive_rx_coalesce; aic->max_eqd = min(et->rx_coalesce_usecs_high, BE_MAX_EQD); aic->min_eqd = min(et->rx_coalesce_usecs_low, aic->max_eqd); aic->et_eqd = min(et->rx_coalesce_usecs, aic->max_eqd); diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index 4d8e40ac66d2..39eb7d525043 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1014,7 +1014,7 @@ static u32 be_xmit_enqueue(struct be_adapter *adapter, struct be_tx_obj *txo, } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; len = skb_frag_size(frag); busaddr = skb_frag_dma_map(dev, frag, 0, len, DMA_TO_DEVICE); @@ -2147,7 +2147,7 @@ static int be_get_new_eqd(struct be_eq_obj *eqo) int i; aic = &adapter->aic_obj[eqo->idx]; - if (!aic->enable) { + if (!adapter->aic_enabled) { if (aic->jiffies) aic->jiffies = 0; eqd = aic->et_eqd; @@ -2204,7 +2204,7 @@ static u32 be_get_eq_delay_mult_enc(struct be_eq_obj *eqo) int eqd; u32 mult_enc; - if (!aic->enable) + if (!adapter->aic_enabled) return 0; if (jiffies_to_msecs(now - aic->jiffies) < 1) @@ -2346,8 +2346,8 @@ static void skb_fill_rx_data(struct be_rx_obj *rxo, struct sk_buff *skb, memcpy(skb->data, start, hdr_len); skb_shinfo(skb)->nr_frags = 1; skb_frag_set_page(skb, 0, page_info->page); - skb_shinfo(skb)->frags[0].page_offset = - page_info->page_offset + hdr_len; + skb_frag_off_set(&skb_shinfo(skb)->frags[0], + page_info->page_offset + hdr_len); skb_frag_size_set(&skb_shinfo(skb)->frags[0], curr_frag_len - hdr_len); skb->data_len = curr_frag_len - hdr_len; @@ -2372,8 +2372,8 @@ static void skb_fill_rx_data(struct be_rx_obj *rxo, struct sk_buff *skb, /* Fresh page */ j++; skb_frag_set_page(skb, j, page_info->page); - skb_shinfo(skb)->frags[j].page_offset = - page_info->page_offset; + skb_frag_off_set(&skb_shinfo(skb)->frags[j], + page_info->page_offset); skb_frag_size_set(&skb_shinfo(skb)->frags[j], 0); skb_shinfo(skb)->nr_frags++; } else { @@ -2454,8 +2454,8 @@ static void be_rx_compl_process_gro(struct be_rx_obj *rxo, /* First frag or Fresh page */ j++; skb_frag_set_page(skb, j, page_info->page); - skb_shinfo(skb)->frags[j].page_offset = - page_info->page_offset; + skb_frag_off_set(&skb_shinfo(skb)->frags[j], + page_info->page_offset); skb_frag_size_set(&skb_shinfo(skb)->frags[j], 0); } else { put_page(page_info->page); @@ -2959,6 +2959,8 @@ static int be_evt_queues_create(struct be_adapter *adapter) max(adapter->cfg_num_rx_irqs, adapter->cfg_num_tx_irqs)); + adapter->aic_enabled = true; + for_all_evt_queues(adapter, eqo, i) { int numa_node = dev_to_node(&adapter->pdev->dev); @@ -2966,7 +2968,6 @@ static int be_evt_queues_create(struct be_adapter *adapter) eqo->adapter = adapter; eqo->idx = i; aic->max_eqd = BE_MAX_EQD; - aic->enable = true; eq = &eqo->q; rc = be_queue_alloc(adapter, eq, EVNT_Q_LEN, diff --git a/drivers/net/ethernet/ezchip/nps_enet.c b/drivers/net/ethernet/ezchip/nps_enet.c index 027225e1ade2..815fb62c4b02 100644 --- a/drivers/net/ethernet/ezchip/nps_enet.c +++ b/drivers/net/ethernet/ezchip/nps_enet.c @@ -576,7 +576,6 @@ static s32 nps_enet_probe(struct platform_device *pdev) struct nps_enet_priv *priv; s32 err = 0; const char *mac_addr; - struct resource *res_regs; if (!dev->of_node) return -ENODEV; @@ -595,8 +594,7 @@ static s32 nps_enet_probe(struct platform_device *pdev) /* FIXME :: no multicast support yet */ ndev->flags &= ~IFF_MULTICAST; - res_regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->regs_base = devm_ioremap_resource(dev, res_regs); + priv->regs_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->regs_base)) { err = PTR_ERR(priv->regs_base); goto out_netdev; diff --git a/drivers/net/ethernet/faraday/Kconfig b/drivers/net/ethernet/faraday/Kconfig index a9b105803fb7..73e4f2648e49 100644 --- a/drivers/net/ethernet/faraday/Kconfig +++ b/drivers/net/ethernet/faraday/Kconfig @@ -32,6 +32,7 @@ config FTGMAC100 depends on ARM || NDS32 || COMPILE_TEST depends on !64BIT || BROKEN select PHYLIB + select MDIO_ASPEED if MACH_ASPEED_G6 ---help--- This driver supports the FTGMAC100 Gigabit Ethernet controller from Faraday. It is used on Faraday A369, Andes AG102 and some diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c index 030fed65393e..9b7af94a40bb 100644 --- a/drivers/net/ethernet/faraday/ftgmac100.c +++ b/drivers/net/ethernet/faraday/ftgmac100.c @@ -17,6 +17,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/of.h> +#include <linux/of_mdio.h> #include <linux/phy.h> #include <linux/platform_device.h> #include <linux/property.h> @@ -774,7 +775,7 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb, for (i = 0; i < nfrags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - len = frag->size; + len = skb_frag_size(frag); /* Map it */ map = skb_frag_dma_map(priv->dev, frag, 0, len, @@ -1619,8 +1620,13 @@ static int ftgmac100_setup_mdio(struct net_device *netdev) if (!priv->mii_bus) return -EIO; - if (priv->is_aspeed) { - /* This driver supports the old MDIO interface */ + if (of_device_is_compatible(np, "aspeed,ast2400-mac") || + of_device_is_compatible(np, "aspeed,ast2500-mac")) { + /* The AST2600 has a separate MDIO controller */ + + /* For the AST2400 and AST2500 this driver only supports the + * old MDIO interface + */ reg = ioread32(priv->base + FTGMAC100_OFFSET_REVR); reg &= ~FTGMAC100_REVR_NEW_MDIO_INTERFACE; iowrite32(reg, priv->base + FTGMAC100_OFFSET_REVR); @@ -1797,7 +1803,8 @@ static int ftgmac100_probe(struct platform_device *pdev) np = pdev->dev.of_node; if (np && (of_device_is_compatible(np, "aspeed,ast2400-mac") || - of_device_is_compatible(np, "aspeed,ast2500-mac"))) { + of_device_is_compatible(np, "aspeed,ast2500-mac") || + of_device_is_compatible(np, "aspeed,ast2600-mac"))) { priv->rxdes0_edorr_mask = BIT(30); priv->txdes0_edotr_mask = BIT(30); priv->is_aspeed = true; @@ -1817,7 +1824,29 @@ static int ftgmac100_probe(struct platform_device *pdev) priv->ndev = ncsi_register_dev(netdev, ftgmac100_ncsi_handler); if (!priv->ndev) goto err_ncsi_dev; - } else { + } else if (np && of_get_property(np, "phy-handle", NULL)) { + struct phy_device *phy; + + phy = of_phy_get_and_connect(priv->netdev, np, + &ftgmac100_adjust_link); + if (!phy) { + dev_err(&pdev->dev, "Failed to connect to phy\n"); + goto err_setup_mdio; + } + + /* Indicate that we support PAUSE frames (see comment in + * Documentation/networking/phy.txt) + */ + phy_support_asym_pause(phy); + + /* Display what we found */ + phy_attached_info(phy); + } else if (np && !of_get_child_by_name(np, "mdio")) { + /* Support legacy ASPEED devicetree descriptions that decribe a + * MAC with an embedded MDIO controller but have no "mdio" + * child node. Automatically scan the MDIO bus for available + * PHYs. + */ priv->use_ncsi = false; err = ftgmac100_setup_mdio(netdev); if (err) diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c index f38c3fa7d705..b4b82b9c5cd6 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c @@ -485,7 +485,7 @@ static struct dpaa_bp *dpaa_bpid2pool(int bpid) static bool dpaa_bpid2pool_use(int bpid) { if (dpaa_bpid2pool(bpid)) { - atomic_inc(&dpaa_bp_array[bpid]->refs); + refcount_inc(&dpaa_bp_array[bpid]->refs); return true; } @@ -496,7 +496,7 @@ static bool dpaa_bpid2pool_use(int bpid) static void dpaa_bpid2pool_map(int bpid, struct dpaa_bp *dpaa_bp) { dpaa_bp_array[bpid] = dpaa_bp; - atomic_set(&dpaa_bp->refs, 1); + refcount_set(&dpaa_bp->refs, 1); } static int dpaa_bp_alloc_pool(struct dpaa_bp *dpaa_bp) @@ -584,7 +584,7 @@ static void dpaa_bp_free(struct dpaa_bp *dpaa_bp) if (!bp) return; - if (!atomic_dec_and_test(&bp->refs)) + if (!refcount_dec_and_test(&bp->refs)) return; if (bp->free_buf_cb) @@ -1958,7 +1958,7 @@ static int skb_to_sg_fd(struct dpaa_priv *priv, /* populate the rest of SGT entries */ for (i = 0; i < nr_frags; i++) { frag = &skb_shinfo(skb)->frags[i]; - frag_len = frag->size; + frag_len = skb_frag_size(frag); WARN_ON(!skb_frag_page(frag)); addr = skb_frag_dma_map(dev, frag, 0, frag_len, dma_dir); diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h index af320f83c742..f7e59e8db075 100644 --- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h +++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.h @@ -32,6 +32,7 @@ #define __DPAA_H #include <linux/netdevice.h> +#include <linux/refcount.h> #include <soc/fsl/qman.h> #include <soc/fsl/bman.h> @@ -99,7 +100,7 @@ struct dpaa_bp { int (*seed_cb)(struct dpaa_bp *); /* bpool can be emptied before freeing by this cb */ void (*free_buf_cb)(const struct dpaa_bp *, struct bm_buffer *); - atomic_t refs; + refcount_t refs; }; struct dpaa_rx_errors { diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c index a027f4a9d0cc..a9afe46b837f 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.c @@ -164,70 +164,30 @@ static const struct file_operations dpaa2_dbg_ch_ops = { void dpaa2_dbg_add(struct dpaa2_eth_priv *priv) { - if (!dpaa2_dbg_root) - return; + struct dentry *dir; /* Create a directory for the interface */ - priv->dbg.dir = debugfs_create_dir(priv->net_dev->name, - dpaa2_dbg_root); - if (!priv->dbg.dir) { - netdev_err(priv->net_dev, "debugfs_create_dir() failed\n"); - return; - } + dir = debugfs_create_dir(priv->net_dev->name, dpaa2_dbg_root); + priv->dbg.dir = dir; /* per-cpu stats file */ - priv->dbg.cpu_stats = debugfs_create_file("cpu_stats", 0444, - priv->dbg.dir, priv, - &dpaa2_dbg_cpu_ops); - if (!priv->dbg.cpu_stats) { - netdev_err(priv->net_dev, "debugfs_create_file() failed\n"); - goto err_cpu_stats; - } + debugfs_create_file("cpu_stats", 0444, dir, priv, &dpaa2_dbg_cpu_ops); /* per-fq stats file */ - priv->dbg.fq_stats = debugfs_create_file("fq_stats", 0444, - priv->dbg.dir, priv, - &dpaa2_dbg_fq_ops); - if (!priv->dbg.fq_stats) { - netdev_err(priv->net_dev, "debugfs_create_file() failed\n"); - goto err_fq_stats; - } + debugfs_create_file("fq_stats", 0444, dir, priv, &dpaa2_dbg_fq_ops); /* per-fq stats file */ - priv->dbg.ch_stats = debugfs_create_file("ch_stats", 0444, - priv->dbg.dir, priv, - &dpaa2_dbg_ch_ops); - if (!priv->dbg.fq_stats) { - netdev_err(priv->net_dev, "debugfs_create_file() failed\n"); - goto err_ch_stats; - } - - return; - -err_ch_stats: - debugfs_remove(priv->dbg.fq_stats); -err_fq_stats: - debugfs_remove(priv->dbg.cpu_stats); -err_cpu_stats: - debugfs_remove(priv->dbg.dir); + debugfs_create_file("ch_stats", 0444, dir, priv, &dpaa2_dbg_ch_ops); } void dpaa2_dbg_remove(struct dpaa2_eth_priv *priv) { - debugfs_remove(priv->dbg.fq_stats); - debugfs_remove(priv->dbg.ch_stats); - debugfs_remove(priv->dbg.cpu_stats); - debugfs_remove(priv->dbg.dir); + debugfs_remove_recursive(priv->dbg.dir); } void dpaa2_eth_dbg_init(void) { dpaa2_dbg_root = debugfs_create_dir(DPAA2_ETH_DBG_ROOT, NULL); - if (!dpaa2_dbg_root) { - pr_err("DPAA2-ETH: debugfs create failed\n"); - return; - } - pr_debug("DPAA2-ETH: debugfs created\n"); } diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h index 4f63de997a26..15598b28f03b 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth-debugfs.h @@ -11,9 +11,6 @@ struct dpaa2_eth_priv; struct dpaa2_debugfs { struct dentry *dir; - struct dentry *fq_stats; - struct dentry *ch_stats; - struct dentry *cpu_stats; }; #ifdef CONFIG_DEBUG_FS diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c index 0acb11557ed1..162d7d8fb295 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c @@ -1208,9 +1208,37 @@ static void disable_ch_napi(struct dpaa2_eth_priv *priv) } } +static void dpaa2_eth_set_rx_taildrop(struct dpaa2_eth_priv *priv, bool enable) +{ + struct dpni_taildrop td = {0}; + int i, err; + + if (priv->rx_td_enabled == enable) + return; + + td.enable = enable; + td.threshold = DPAA2_ETH_TAILDROP_THRESH; + + for (i = 0; i < priv->num_fqs; i++) { + if (priv->fq[i].type != DPAA2_RX_FQ) + continue; + err = dpni_set_taildrop(priv->mc_io, 0, priv->mc_token, + DPNI_CP_QUEUE, DPNI_QUEUE_RX, 0, + priv->fq[i].flowid, &td); + if (err) { + netdev_err(priv->net_dev, + "dpni_set_taildrop() failed\n"); + break; + } + } + + priv->rx_td_enabled = enable; +} + static int link_state_update(struct dpaa2_eth_priv *priv) { struct dpni_link_state state = {0}; + bool tx_pause; int err; err = dpni_get_link_state(priv->mc_io, 0, priv->mc_token, &state); @@ -1220,11 +1248,18 @@ static int link_state_update(struct dpaa2_eth_priv *priv) return err; } + /* If Tx pause frame settings have changed, we need to update + * Rx FQ taildrop configuration as well. We configure taildrop + * only when pause frame generation is disabled. + */ + tx_pause = !!(state.options & DPNI_LINK_OPT_PAUSE) ^ + !!(state.options & DPNI_LINK_OPT_ASYM_PAUSE); + dpaa2_eth_set_rx_taildrop(priv, !tx_pause); + /* Chech link state; speed / duplex changes are not treated yet */ if (priv->link_state.up == state.up) - return 0; + goto out; - priv->link_state = state; if (state.up) { netif_carrier_on(priv->net_dev); netif_tx_start_all_queues(priv->net_dev); @@ -1236,6 +1271,9 @@ static int link_state_update(struct dpaa2_eth_priv *priv) netdev_info(priv->net_dev, "Link Event: state %s\n", state.up ? "up" : "down"); +out: + priv->link_state = state; + return 0; } @@ -1310,7 +1348,7 @@ static u32 ingress_fq_count(struct dpaa2_eth_priv *priv) return total; } -static void wait_for_fq_empty(struct dpaa2_eth_priv *priv) +static void wait_for_ingress_fq_empty(struct dpaa2_eth_priv *priv) { int retries = 10; u32 pending; @@ -1322,6 +1360,31 @@ static void wait_for_fq_empty(struct dpaa2_eth_priv *priv) } while (pending && --retries); } +#define DPNI_TX_PENDING_VER_MAJOR 7 +#define DPNI_TX_PENDING_VER_MINOR 13 +static void wait_for_egress_fq_empty(struct dpaa2_eth_priv *priv) +{ + union dpni_statistics stats; + int retries = 10; + int err; + + if (dpaa2_eth_cmp_dpni_ver(priv, DPNI_TX_PENDING_VER_MAJOR, + DPNI_TX_PENDING_VER_MINOR) < 0) + goto out; + + do { + err = dpni_get_statistics(priv->mc_io, 0, priv->mc_token, 6, + &stats); + if (err) + goto out; + if (stats.page_6.tx_pending_frames == 0) + return; + } while (--retries); + +out: + msleep(500); +} + static int dpaa2_eth_stop(struct net_device *net_dev) { struct dpaa2_eth_priv *priv = netdev_priv(net_dev); @@ -1341,7 +1404,7 @@ static int dpaa2_eth_stop(struct net_device *net_dev) * on WRIOP. After it finishes, wait until all remaining frames on Rx * and Tx conf queues are consumed on NAPI poll. */ - msleep(500); + wait_for_egress_fq_empty(priv); do { dpni_disable(priv->mc_io, 0, priv->mc_token); @@ -1357,7 +1420,7 @@ static int dpaa2_eth_stop(struct net_device *net_dev) */ } - wait_for_fq_empty(priv); + wait_for_ingress_fq_empty(priv); disable_ch_napi(priv); /* Empty the buffer pool */ @@ -2443,6 +2506,33 @@ static void set_enqueue_mode(struct dpaa2_eth_priv *priv) priv->enqueue = dpaa2_eth_enqueue_fq; } +static int set_pause(struct dpaa2_eth_priv *priv) +{ + struct device *dev = priv->net_dev->dev.parent; + struct dpni_link_cfg link_cfg = {0}; + int err; + + /* Get the default link options so we don't override other flags */ + err = dpni_get_link_cfg(priv->mc_io, 0, priv->mc_token, &link_cfg); + if (err) { + dev_err(dev, "dpni_get_link_cfg() failed\n"); + return err; + } + + /* By default, enable both Rx and Tx pause frames */ + link_cfg.options |= DPNI_LINK_OPT_PAUSE; + link_cfg.options &= ~DPNI_LINK_OPT_ASYM_PAUSE; + err = dpni_set_link_cfg(priv->mc_io, 0, priv->mc_token, &link_cfg); + if (err) { + dev_err(dev, "dpni_set_link_cfg() failed\n"); + return err; + } + + priv->link_state.options = link_cfg.options; + + return 0; +} + /* Configure the DPNI object this interface is associated with */ static int setup_dpni(struct fsl_mc_device *ls_dev) { @@ -2498,6 +2588,13 @@ static int setup_dpni(struct fsl_mc_device *ls_dev) set_enqueue_mode(priv); + /* Enable pause frame support */ + if (dpaa2_eth_has_pause_support(priv)) { + err = set_pause(priv); + if (err) + goto close; + } + priv->cls_rules = devm_kzalloc(dev, sizeof(struct dpaa2_eth_cls_rule) * dpaa2_eth_fs_count(priv), GFP_KERNEL); if (!priv->cls_rules) @@ -2529,7 +2626,6 @@ static int setup_rx_flow(struct dpaa2_eth_priv *priv, struct device *dev = priv->net_dev->dev.parent; struct dpni_queue queue; struct dpni_queue_id qid; - struct dpni_taildrop td; int err; err = dpni_get_queue(priv->mc_io, 0, priv->mc_token, @@ -2554,15 +2650,6 @@ static int setup_rx_flow(struct dpaa2_eth_priv *priv, return err; } - td.enable = 1; - td.threshold = DPAA2_ETH_TAILDROP_THRESH; - err = dpni_set_taildrop(priv->mc_io, 0, priv->mc_token, DPNI_CP_QUEUE, - DPNI_QUEUE_RX, 0, fq->flowid, &td); - if (err) { - dev_err(dev, "dpni_set_threshold() failed\n"); - return err; - } - /* xdp_rxq setup */ err = xdp_rxq_info_reg(&fq->channel->xdp_rxq, priv->net_dev, fq->flowid); diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h index 9af18c24221f..8a0e65b3267f 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.h @@ -392,6 +392,7 @@ struct dpaa2_eth_priv { struct dpaa2_eth_drv_stats __percpu *percpu_extras; u16 mc_token; + u8 rx_td_enabled; struct dpni_link_state link_state; bool do_link_poll; @@ -476,6 +477,12 @@ enum dpaa2_eth_rx_dist { #define DPAA2_ETH_DIST_L4DST BIT(8) #define DPAA2_ETH_DIST_ALL (~0ULL) +#define DPNI_PAUSE_VER_MAJOR 7 +#define DPNI_PAUSE_VER_MINOR 13 +#define dpaa2_eth_has_pause_support(priv) \ + (dpaa2_eth_cmp_dpni_ver((priv), DPNI_PAUSE_VER_MAJOR, \ + DPNI_PAUSE_VER_MINOR) >= 0) + static inline unsigned int dpaa2_eth_needed_headroom(struct dpaa2_eth_priv *priv, struct sk_buff *skb) diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c index 7b182f4b263c..0aa1c34019bb 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-ethtool.c @@ -28,6 +28,11 @@ static char dpaa2_ethtool_stats[][ETH_GSTRING_LEN] = { "[hw] rx nobuffer discards", "[hw] tx discarded frames", "[hw] tx confirmed frames", + "[hw] tx dequeued bytes", + "[hw] tx dequeued frames", + "[hw] tx rejected bytes", + "[hw] tx rejected frames", + "[hw] tx pending frames", }; #define DPAA2_ETH_NUM_STATS ARRAY_SIZE(dpaa2_ethtool_stats) @@ -78,71 +83,67 @@ static int dpaa2_eth_get_link_ksettings(struct net_device *net_dev, struct ethtool_link_ksettings *link_settings) { - struct dpni_link_state state = {0}; - int err = 0; struct dpaa2_eth_priv *priv = netdev_priv(net_dev); - err = dpni_get_link_state(priv->mc_io, 0, priv->mc_token, &state); - if (err) { - netdev_err(net_dev, "ERROR %d getting link state\n", err); - goto out; - } - - /* At the moment, we have no way of interrogating the DPMAC - * from the DPNI side - and for that matter there may exist - * no DPMAC at all. So for now we just don't report anything - * beyond the DPNI attributes. - */ - if (state.options & DPNI_LINK_OPT_AUTONEG) - link_settings->base.autoneg = AUTONEG_ENABLE; - if (!(state.options & DPNI_LINK_OPT_HALF_DUPLEX)) + link_settings->base.autoneg = AUTONEG_DISABLE; + if (!(priv->link_state.options & DPNI_LINK_OPT_HALF_DUPLEX)) link_settings->base.duplex = DUPLEX_FULL; - link_settings->base.speed = state.rate; + link_settings->base.speed = priv->link_state.rate; -out: - return err; + return 0; } -#define DPNI_DYNAMIC_LINK_SET_VER_MAJOR 7 -#define DPNI_DYNAMIC_LINK_SET_VER_MINOR 1 -static int -dpaa2_eth_set_link_ksettings(struct net_device *net_dev, - const struct ethtool_link_ksettings *link_settings) +static void dpaa2_eth_get_pauseparam(struct net_device *net_dev, + struct ethtool_pauseparam *pause) { - struct dpni_link_cfg cfg = {0}; struct dpaa2_eth_priv *priv = netdev_priv(net_dev); - int err = 0; + u64 link_options = priv->link_state.options; - /* If using an older MC version, the DPNI must be down - * in order to be able to change link settings. Taking steps to let - * the user know that. - */ - if (dpaa2_eth_cmp_dpni_ver(priv, DPNI_DYNAMIC_LINK_SET_VER_MAJOR, - DPNI_DYNAMIC_LINK_SET_VER_MINOR) < 0) { - if (netif_running(net_dev)) { - netdev_info(net_dev, "Interface must be brought down first.\n"); - return -EACCES; - } + pause->rx_pause = !!(link_options & DPNI_LINK_OPT_PAUSE); + pause->tx_pause = pause->rx_pause ^ + !!(link_options & DPNI_LINK_OPT_ASYM_PAUSE); + pause->autoneg = AUTONEG_DISABLE; +} + +static int dpaa2_eth_set_pauseparam(struct net_device *net_dev, + struct ethtool_pauseparam *pause) +{ + struct dpaa2_eth_priv *priv = netdev_priv(net_dev); + struct dpni_link_cfg cfg = {0}; + int err; + + if (!dpaa2_eth_has_pause_support(priv)) { + netdev_info(net_dev, "No pause frame support for DPNI version < %d.%d\n", + DPNI_PAUSE_VER_MAJOR, DPNI_PAUSE_VER_MINOR); + return -EOPNOTSUPP; } - cfg.rate = link_settings->base.speed; - if (link_settings->base.autoneg == AUTONEG_ENABLE) - cfg.options |= DPNI_LINK_OPT_AUTONEG; + if (pause->autoneg) + return -EOPNOTSUPP; + + cfg.rate = priv->link_state.rate; + cfg.options = priv->link_state.options; + if (pause->rx_pause) + cfg.options |= DPNI_LINK_OPT_PAUSE; else - cfg.options &= ~DPNI_LINK_OPT_AUTONEG; - if (link_settings->base.duplex == DUPLEX_HALF) - cfg.options |= DPNI_LINK_OPT_HALF_DUPLEX; + cfg.options &= ~DPNI_LINK_OPT_PAUSE; + if (!!pause->rx_pause ^ !!pause->tx_pause) + cfg.options |= DPNI_LINK_OPT_ASYM_PAUSE; else - cfg.options &= ~DPNI_LINK_OPT_HALF_DUPLEX; + cfg.options &= ~DPNI_LINK_OPT_ASYM_PAUSE; + + if (cfg.options == priv->link_state.options) + return 0; err = dpni_set_link_cfg(priv->mc_io, 0, priv->mc_token, &cfg); - if (err) - /* ethtool will be loud enough if we return an error; no point - * in putting our own error message on the console by default - */ - netdev_dbg(net_dev, "ERROR %d setting link cfg\n", err); + if (err) { + netdev_err(net_dev, "dpni_set_link_state failed\n"); + return err; + } - return err; + priv->link_state.options = cfg.options; + + return 0; } static void dpaa2_eth_get_strings(struct net_device *netdev, u32 stringset, @@ -192,27 +193,33 @@ static void dpaa2_eth_get_ethtool_stats(struct net_device *net_dev, struct dpaa2_eth_priv *priv = netdev_priv(net_dev); struct dpaa2_eth_drv_stats *extras; struct dpaa2_eth_ch_stats *ch_stats; + int dpni_stats_page_size[DPNI_STATISTICS_CNT] = { + sizeof(dpni_stats.page_0), + sizeof(dpni_stats.page_1), + sizeof(dpni_stats.page_2), + sizeof(dpni_stats.page_3), + sizeof(dpni_stats.page_4), + sizeof(dpni_stats.page_5), + sizeof(dpni_stats.page_6), + }; memset(data, 0, sizeof(u64) * (DPAA2_ETH_NUM_STATS + DPAA2_ETH_NUM_EXTRA_STATS)); /* Print standard counters, from DPNI statistics */ - for (j = 0; j <= 2; j++) { + for (j = 0; j <= 6; j++) { + /* We're not interested in pages 4 & 5 for now */ + if (j == 4 || j == 5) + continue; err = dpni_get_statistics(priv->mc_io, 0, priv->mc_token, j, &dpni_stats); - if (err != 0) + if (err == -EINVAL) + /* Older firmware versions don't support all pages */ + memset(&dpni_stats, 0, sizeof(dpni_stats)); + else netdev_warn(net_dev, "dpni_get_stats(%d) failed\n", j); - switch (j) { - case 0: - num_cnt = sizeof(dpni_stats.page_0) / sizeof(u64); - break; - case 1: - num_cnt = sizeof(dpni_stats.page_1) / sizeof(u64); - break; - case 2: - num_cnt = sizeof(dpni_stats.page_2) / sizeof(u64); - break; - } + + num_cnt = dpni_stats_page_size[j] / sizeof(u64); for (k = 0; k < num_cnt; k++) *(data + i++) = dpni_stats.raw.counter[k]; } @@ -721,7 +728,8 @@ const struct ethtool_ops dpaa2_ethtool_ops = { .get_drvinfo = dpaa2_eth_get_drvinfo, .get_link = ethtool_op_get_link, .get_link_ksettings = dpaa2_eth_get_link_ksettings, - .set_link_ksettings = dpaa2_eth_set_link_ksettings, + .get_pauseparam = dpaa2_eth_get_pauseparam, + .set_pauseparam = dpaa2_eth_set_pauseparam, .get_sset_count = dpaa2_eth_get_sset_count, .get_ethtool_stats = dpaa2_eth_get_ethtool_stats, .get_strings = dpaa2_eth_get_strings, diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h index 7b44d7d9b19a..d9b6918807af 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni-cmd.h @@ -84,6 +84,7 @@ #define DPNI_CMDID_SET_RX_FS_DIST DPNI_CMD(0x273) #define DPNI_CMDID_SET_RX_HASH_DIST DPNI_CMD(0x274) +#define DPNI_CMDID_GET_LINK_CFG DPNI_CMD(0x278) /* Macros for accessing command fields smaller than 1byte */ #define DPNI_MASK(field) \ @@ -284,7 +285,7 @@ struct dpni_rsp_get_statistics { __le64 counter[DPNI_STATISTICS_CNT]; }; -struct dpni_cmd_set_link_cfg { +struct dpni_cmd_link_cfg { /* cmd word 0 */ __le64 pad0; /* cmd word 1 */ diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.c b/drivers/net/ethernet/freescale/dpaa2/dpni.c index 220dfc806a24..dd54e6953aeb 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni.c +++ b/drivers/net/ethernet/freescale/dpaa2/dpni.c @@ -838,13 +838,13 @@ int dpni_set_link_cfg(struct fsl_mc_io *mc_io, const struct dpni_link_cfg *cfg) { struct fsl_mc_command cmd = { 0 }; - struct dpni_cmd_set_link_cfg *cmd_params; + struct dpni_cmd_link_cfg *cmd_params; /* prepare command */ cmd.header = mc_encode_cmd_header(DPNI_CMDID_SET_LINK_CFG, cmd_flags, token); - cmd_params = (struct dpni_cmd_set_link_cfg *)cmd.params; + cmd_params = (struct dpni_cmd_link_cfg *)cmd.params; cmd_params->rate = cpu_to_le32(cfg->rate); cmd_params->options = cpu_to_le64(cfg->options); @@ -853,6 +853,42 @@ int dpni_set_link_cfg(struct fsl_mc_io *mc_io, } /** + * dpni_get_link_cfg() - return the link configuration + * @mc_io: Pointer to MC portal's I/O object + * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' + * @token: Token of DPNI object + * @cfg: Link configuration from dpni object + * + * Return: '0' on Success; Error code otherwise. + */ +int dpni_get_link_cfg(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + struct dpni_link_cfg *cfg) +{ + struct fsl_mc_command cmd = { 0 }; + struct dpni_cmd_link_cfg *rsp_params; + int err; + + /* prepare command */ + cmd.header = mc_encode_cmd_header(DPNI_CMDID_GET_LINK_CFG, + cmd_flags, + token); + + /* send command to mc*/ + err = mc_send_command(mc_io, &cmd); + if (err) + return err; + + /* retrieve response parameters */ + rsp_params = (struct dpni_cmd_link_cfg *)cmd.params; + cfg->rate = le32_to_cpu(rsp_params->rate); + cfg->options = le64_to_cpu(rsp_params->options); + + return err; +} + +/** * dpni_get_link_state() - Return the link state (either up or down) * @mc_io: Pointer to MC portal's I/O object * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' @@ -1434,7 +1470,7 @@ int dpni_get_queue(struct fsl_mc_io *mc_io, * @cmd_flags: Command flags; one or more of 'MC_CMD_FLAG_' * @token: Token of DPNI object * @page: Selects the statistics page to retrieve, see - * DPNI_GET_STATISTICS output. Pages are numbered 0 to 2. + * DPNI_GET_STATISTICS output. Pages are numbered 0 to 6. * @stat: Structure containing the statistics * * Return: '0' on Success; Error code otherwise. diff --git a/drivers/net/ethernet/freescale/dpaa2/dpni.h b/drivers/net/ethernet/freescale/dpaa2/dpni.h index a521242e2353..fd583911b6c0 100644 --- a/drivers/net/ethernet/freescale/dpaa2/dpni.h +++ b/drivers/net/ethernet/freescale/dpaa2/dpni.h @@ -416,6 +416,26 @@ int dpni_get_tx_data_offset(struct fsl_mc_io *mc_io, * lack of buffers * @page_2.egress_discarded_frames: Egress discarded frame count * @page_2.egress_confirmed_frames: Egress confirmed frame count + * @page3: Page_3 statistics structure + * @page_3.egress_dequeue_bytes: Cumulative count of the number of bytes + * dequeued from egress FQs + * @page_3.egress_dequeue_frames: Cumulative count of the number of frames + * dequeued from egress FQs + * @page_3.egress_reject_bytes: Cumulative count of the number of bytes in + * egress frames whose enqueue was rejected + * @page_3.egress_reject_frames: Cumulative count of the number of egress + * frames whose enqueue was rejected + * @page_4: Page_4 statistics structure: congestion points + * @page_4.cgr_reject_frames: number of rejected frames due to congestion point + * @page_4.cgr_reject_bytes: number of rejected bytes due to congestion point + * @page_5: Page_5 statistics structure: policer + * @page_5.policer_cnt_red: NUmber of red colored frames + * @page_5.policer_cnt_yellow: number of yellow colored frames + * @page_5.policer_cnt_green: number of green colored frames + * @page_5.policer_cnt_re_red: number of recolored red frames + * @page_5.policer_cnt_re_yellow: number of recolored yellow frames + * @page_6: Page_6 statistics structure + * @page_6.tx_pending_frames: total number of frames pending in egress FQs * @raw: raw statistics structure, used to index counters */ union dpni_statistics { @@ -443,6 +463,26 @@ union dpni_statistics { u64 egress_confirmed_frames; } page_2; struct { + u64 egress_dequeue_bytes; + u64 egress_dequeue_frames; + u64 egress_reject_bytes; + u64 egress_reject_frames; + } page_3; + struct { + u64 cgr_reject_frames; + u64 cgr_reject_bytes; + } page_4; + struct { + u64 policer_cnt_red; + u64 policer_cnt_yellow; + u64 policer_cnt_green; + u64 policer_cnt_re_red; + u64 policer_cnt_re_yellow; + } page_5; + struct { + u64 tx_pending_frames; + } page_6; + struct { u64 counter[DPNI_STATISTICS_CNT]; } raw; }; @@ -485,6 +525,11 @@ int dpni_set_link_cfg(struct fsl_mc_io *mc_io, u16 token, const struct dpni_link_cfg *cfg); +int dpni_get_link_cfg(struct fsl_mc_io *mc_io, + u32 cmd_flags, + u16 token, + struct dpni_link_cfg *cfg); + /** * struct dpni_link_state - Structure representing DPNI link state * @rate: Rate diff --git a/drivers/net/ethernet/freescale/enetc/Kconfig b/drivers/net/ethernet/freescale/enetc/Kconfig index 04a59db03f2b..c219587bd334 100644 --- a/drivers/net/ethernet/freescale/enetc/Kconfig +++ b/drivers/net/ethernet/freescale/enetc/Kconfig @@ -20,6 +20,15 @@ config FSL_ENETC_VF If compiled as module (M), the module name is fsl-enetc-vf. +config FSL_ENETC_MDIO + tristate "ENETC MDIO driver" + depends on PCI && (ARCH_LAYERSCAPE || COMPILE_TEST) + help + This driver supports NXP ENETC Central MDIO controller as a PCIe + physical function (PF) device. + + If compiled as module (M), the module name is fsl-enetc-mdio. + config FSL_ENETC_PTP_CLOCK tristate "ENETC PTP clock driver" depends on PTP_1588_CLOCK_QORIQ && (FSL_ENETC || FSL_ENETC_VF) diff --git a/drivers/net/ethernet/freescale/enetc/Makefile b/drivers/net/ethernet/freescale/enetc/Makefile index 7139e414dccf..d200c27c3bf6 100644 --- a/drivers/net/ethernet/freescale/enetc/Makefile +++ b/drivers/net/ethernet/freescale/enetc/Makefile @@ -1,19 +1,16 @@ # SPDX-License-Identifier: GPL-2.0 + +common-objs := enetc.o enetc_cbdr.o enetc_ethtool.o + obj-$(CONFIG_FSL_ENETC) += fsl-enetc.o -fsl-enetc-$(CONFIG_FSL_ENETC) += enetc.o enetc_cbdr.o enetc_ethtool.o \ - enetc_mdio.o +fsl-enetc-y := enetc_pf.o enetc_mdio.o $(common-objs) fsl-enetc-$(CONFIG_PCI_IOV) += enetc_msg.o -fsl-enetc-objs := enetc_pf.o $(fsl-enetc-y) obj-$(CONFIG_FSL_ENETC_VF) += fsl-enetc-vf.o +fsl-enetc-vf-y := enetc_vf.o $(common-objs) -ifeq ($(CONFIG_FSL_ENETC)$(CONFIG_FSL_ENETC_VF), yy) -fsl-enetc-vf-objs := enetc_vf.o -else -fsl-enetc-vf-$(CONFIG_FSL_ENETC_VF) += enetc.o enetc_cbdr.o \ - enetc_ethtool.o -fsl-enetc-vf-objs := enetc_vf.o $(fsl-enetc-vf-y) -endif +obj-$(CONFIG_FSL_ENETC_MDIO) += fsl-enetc-mdio.o +fsl-enetc-mdio-y := enetc_pci_mdio.o enetc_mdio.o obj-$(CONFIG_FSL_ENETC_PTP_CLOCK) += fsl-enetc-ptp.o -fsl-enetc-ptp-$(CONFIG_FSL_ENETC_PTP_CLOCK) += enetc_ptp.o +fsl-enetc-ptp-y := enetc_ptp.o diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c index 223709443ea4..b6ff89307409 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc.c +++ b/drivers/net/ethernet/freescale/enetc/enetc.c @@ -110,7 +110,7 @@ static int enetc_map_tx_buffs(struct enetc_bdr *tx_ring, struct sk_buff *skb, int active_offloads) { struct enetc_tx_swbd *tx_swbd; - struct skb_frag_struct *frag; + skb_frag_t *frag; int len = skb_headlen(skb); union enetc_tx_bd temp_bd; union enetc_tx_bd *txbd; diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c index 77b9cd10ba2b..149883c8f0b8 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_mdio.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.c @@ -6,18 +6,20 @@ #include <linux/iopoll.h> #include <linux/of.h> -#include "enetc_pf.h" +#include "enetc_mdio.h" -struct enetc_mdio_regs { - u32 mdio_cfg; /* MDIO configuration and status */ - u32 mdio_ctl; /* MDIO control */ - u32 mdio_data; /* MDIO data */ - u32 mdio_addr; /* MDIO address */ -}; +#define ENETC_MDIO_REG_OFFSET 0x1c00 +#define ENETC_MDIO_CFG 0x0 /* MDIO configuration and status */ +#define ENETC_MDIO_CTL 0x4 /* MDIO control */ +#define ENETC_MDIO_DATA 0x8 /* MDIO data */ +#define ENETC_MDIO_ADDR 0xc /* MDIO address */ -#define bus_to_enetc_regs(bus) (struct enetc_mdio_regs __iomem *)((bus)->priv) +#define enetc_mdio_rd(hw, off) \ + enetc_port_rd(hw, ENETC_##off + ENETC_MDIO_REG_OFFSET) +#define enetc_mdio_wr(hw, off, val) \ + enetc_port_wr(hw, ENETC_##off + ENETC_MDIO_REG_OFFSET, val) +#define enetc_mdio_rd_reg(off) enetc_mdio_rd(hw, off) -#define ENETC_MDIO_REG_OFFSET 0x1c00 #define ENETC_MDC_DIV 258 #define MDIO_CFG_CLKDIV(x) ((((x) >> 1) & 0xff) << 8) @@ -33,18 +35,18 @@ struct enetc_mdio_regs { #define MDIO_DATA(x) ((x) & 0xffff) #define TIMEOUT 1000 -static int enetc_mdio_wait_complete(struct enetc_mdio_regs __iomem *regs) +static int enetc_mdio_wait_complete(struct enetc_hw *hw) { u32 val; - return readx_poll_timeout(enetc_rd_reg, ®s->mdio_cfg, val, + return readx_poll_timeout(enetc_mdio_rd_reg, MDIO_CFG, val, !(val & MDIO_CFG_BSY), 10, 10 * TIMEOUT); } -static int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, - u16 value) +int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value) { - struct enetc_mdio_regs __iomem *regs = bus_to_enetc_regs(bus); + struct enetc_mdio_priv *mdio_priv = bus->priv; + struct enetc_hw *hw = mdio_priv->hw; u32 mdio_ctl, mdio_cfg; u16 dev_addr; int ret; @@ -59,38 +61,39 @@ static int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, mdio_cfg &= ~MDIO_CFG_ENC45; } - enetc_wr_reg(®s->mdio_cfg, mdio_cfg); + enetc_mdio_wr(hw, MDIO_CFG, mdio_cfg); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; /* set port and dev addr */ mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr); - enetc_wr_reg(®s->mdio_ctl, mdio_ctl); + enetc_mdio_wr(hw, MDIO_CTL, mdio_ctl); /* set the register address */ if (regnum & MII_ADDR_C45) { - enetc_wr_reg(®s->mdio_addr, regnum & 0xffff); + enetc_mdio_wr(hw, MDIO_ADDR, regnum & 0xffff); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; } /* write the value */ - enetc_wr_reg(®s->mdio_data, MDIO_DATA(value)); + enetc_mdio_wr(hw, MDIO_DATA, MDIO_DATA(value)); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; return 0; } -static int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) +int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) { - struct enetc_mdio_regs __iomem *regs = bus_to_enetc_regs(bus); + struct enetc_mdio_priv *mdio_priv = bus->priv; + struct enetc_hw *hw = mdio_priv->hw; u32 mdio_ctl, mdio_cfg; u16 dev_addr, value; int ret; @@ -104,41 +107,41 @@ static int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) mdio_cfg &= ~MDIO_CFG_ENC45; } - enetc_wr_reg(®s->mdio_cfg, mdio_cfg); + enetc_mdio_wr(hw, MDIO_CFG, mdio_cfg); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; /* set port and device addr */ mdio_ctl = MDIO_CTL_PORT_ADDR(phy_id) | MDIO_CTL_DEV_ADDR(dev_addr); - enetc_wr_reg(®s->mdio_ctl, mdio_ctl); + enetc_mdio_wr(hw, MDIO_CTL, mdio_ctl); /* set the register address */ if (regnum & MII_ADDR_C45) { - enetc_wr_reg(®s->mdio_addr, regnum & 0xffff); + enetc_mdio_wr(hw, MDIO_ADDR, regnum & 0xffff); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; } /* initiate the read */ - enetc_wr_reg(®s->mdio_ctl, mdio_ctl | MDIO_CTL_READ); + enetc_mdio_wr(hw, MDIO_CTL, mdio_ctl | MDIO_CTL_READ); - ret = enetc_mdio_wait_complete(regs); + ret = enetc_mdio_wait_complete(hw); if (ret) return ret; /* return all Fs if nothing was there */ - if (enetc_rd_reg(®s->mdio_cfg) & MDIO_CFG_RD_ER) { + if (enetc_mdio_rd(hw, MDIO_CFG) & MDIO_CFG_RD_ER) { dev_dbg(&bus->dev, "Error while reading PHY%d reg at %d.%hhu\n", phy_id, dev_addr, regnum); return 0xffff; } - value = enetc_rd_reg(®s->mdio_data) & 0xffff; + value = enetc_mdio_rd(hw, MDIO_DATA) & 0xffff; return value; } @@ -146,12 +149,12 @@ static int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum) int enetc_mdio_probe(struct enetc_pf *pf) { struct device *dev = &pf->si->pdev->dev; - struct enetc_mdio_regs __iomem *regs; + struct enetc_mdio_priv *mdio_priv; struct device_node *np; struct mii_bus *bus; - int ret; + int err; - bus = mdiobus_alloc_size(sizeof(regs)); + bus = devm_mdiobus_alloc_size(dev, sizeof(*mdio_priv)); if (!bus) return -ENOMEM; @@ -159,41 +162,31 @@ int enetc_mdio_probe(struct enetc_pf *pf) bus->read = enetc_mdio_read; bus->write = enetc_mdio_write; bus->parent = dev; + mdio_priv = bus->priv; + mdio_priv->hw = &pf->si->hw; snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev)); - /* store the enetc mdio base address for this bus */ - regs = pf->si->hw.port + ENETC_MDIO_REG_OFFSET; - bus->priv = regs; - np = of_get_child_by_name(dev->of_node, "mdio"); if (!np) { dev_err(dev, "MDIO node missing\n"); - ret = -EINVAL; - goto err_registration; + return -EINVAL; } - ret = of_mdiobus_register(bus, np); - if (ret) { + err = of_mdiobus_register(bus, np); + if (err) { of_node_put(np); dev_err(dev, "cannot register MDIO bus\n"); - goto err_registration; + return err; } of_node_put(np); pf->mdio = bus; return 0; - -err_registration: - mdiobus_free(bus); - - return ret; } void enetc_mdio_remove(struct enetc_pf *pf) { - if (pf->mdio) { + if (pf->mdio) mdiobus_unregister(pf->mdio); - mdiobus_free(pf->mdio); - } } diff --git a/drivers/net/ethernet/freescale/enetc/enetc_mdio.h b/drivers/net/ethernet/freescale/enetc/enetc_mdio.h new file mode 100644 index 000000000000..60c9a3889824 --- /dev/null +++ b/drivers/net/ethernet/freescale/enetc/enetc_mdio.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) */ +/* Copyright 2019 NXP */ + +#include <linux/phy.h> +#include "enetc_pf.h" + +struct enetc_mdio_priv { + struct enetc_hw *hw; +}; + +int enetc_mdio_write(struct mii_bus *bus, int phy_id, int regnum, u16 value); +int enetc_mdio_read(struct mii_bus *bus, int phy_id, int regnum); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c new file mode 100644 index 000000000000..fbd41ce01f06 --- /dev/null +++ b/drivers/net/ethernet/freescale/enetc/enetc_pci_mdio.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: (GPL-2.0+ OR BSD-3-Clause) +/* Copyright 2019 NXP */ +#include <linux/of_mdio.h> +#include "enetc_mdio.h" + +#define ENETC_MDIO_DEV_ID 0xee01 +#define ENETC_MDIO_DEV_NAME "FSL PCIe IE Central MDIO" +#define ENETC_MDIO_BUS_NAME ENETC_MDIO_DEV_NAME " Bus" +#define ENETC_MDIO_DRV_NAME ENETC_MDIO_DEV_NAME " driver" + +static int enetc_pci_mdio_probe(struct pci_dev *pdev, + const struct pci_device_id *ent) +{ + struct enetc_mdio_priv *mdio_priv; + struct device *dev = &pdev->dev; + struct enetc_hw *hw; + struct mii_bus *bus; + int err; + + hw = devm_kzalloc(dev, sizeof(*hw), GFP_KERNEL); + if (!hw) + return -ENOMEM; + + bus = devm_mdiobus_alloc_size(dev, sizeof(*mdio_priv)); + if (!bus) + return -ENOMEM; + + bus->name = ENETC_MDIO_BUS_NAME; + bus->read = enetc_mdio_read; + bus->write = enetc_mdio_write; + bus->parent = dev; + mdio_priv = bus->priv; + mdio_priv->hw = hw; + snprintf(bus->id, MII_BUS_ID_SIZE, "%s", dev_name(dev)); + + pcie_flr(pdev); + err = pci_enable_device_mem(pdev); + if (err) { + dev_err(dev, "device enable failed\n"); + return err; + } + + err = pci_request_region(pdev, 0, KBUILD_MODNAME); + if (err) { + dev_err(dev, "pci_request_region failed\n"); + goto err_pci_mem_reg; + } + + hw->port = pci_iomap(pdev, 0, 0); + if (!hw->port) { + err = -ENXIO; + dev_err(dev, "iomap failed\n"); + goto err_ioremap; + } + + err = of_mdiobus_register(bus, dev->of_node); + if (err) + goto err_mdiobus_reg; + + pci_set_drvdata(pdev, bus); + + return 0; + +err_mdiobus_reg: + iounmap(mdio_priv->hw->port); +err_ioremap: + pci_release_mem_regions(pdev); +err_pci_mem_reg: + pci_disable_device(pdev); + + return err; +} + +static void enetc_pci_mdio_remove(struct pci_dev *pdev) +{ + struct mii_bus *bus = pci_get_drvdata(pdev); + struct enetc_mdio_priv *mdio_priv; + + mdiobus_unregister(bus); + mdio_priv = bus->priv; + iounmap(mdio_priv->hw->port); + pci_release_mem_regions(pdev); + pci_disable_device(pdev); +} + +static const struct pci_device_id enetc_pci_mdio_id_table[] = { + { PCI_DEVICE(PCI_VENDOR_ID_FREESCALE, ENETC_MDIO_DEV_ID) }, + { 0, } /* End of table. */ +}; +MODULE_DEVICE_TABLE(pci, enetc_pci_mdio_id_table); + +static struct pci_driver enetc_pci_mdio_driver = { + .name = KBUILD_MODNAME, + .id_table = enetc_pci_mdio_id_table, + .probe = enetc_pci_mdio_probe, + .remove = enetc_pci_mdio_remove, +}; +module_pci_driver(enetc_pci_mdio_driver); + +MODULE_DESCRIPTION(ENETC_MDIO_DRV_NAME); +MODULE_LICENSE("Dual BSD/GPL"); diff --git a/drivers/net/ethernet/freescale/enetc/enetc_pf.c b/drivers/net/ethernet/freescale/enetc/enetc_pf.c index 258b3cb38a6f..7d6513ff8507 100644 --- a/drivers/net/ethernet/freescale/enetc/enetc_pf.c +++ b/drivers/net/ethernet/freescale/enetc/enetc_pf.c @@ -750,6 +750,7 @@ static int enetc_of_get_phy(struct enetc_ndev_priv *priv) { struct enetc_pf *pf = enetc_si_priv(priv->si); struct device_node *np = priv->dev->of_node; + struct device_node *mdio_np; int err; if (!np) { @@ -773,7 +774,9 @@ static int enetc_of_get_phy(struct enetc_ndev_priv *priv) priv->phy_node = of_node_get(np); } - if (!of_phy_is_fixed_link(np)) { + mdio_np = of_get_child_by_name(np, "mdio"); + if (mdio_np) { + of_node_put(mdio_np); err = enetc_mdio_probe(pf); if (err) { of_node_put(priv->phy_node); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index e5610a4da539..d4d4c72adf49 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -208,8 +208,11 @@ MODULE_PARM_DESC(macaddr, "FEC Ethernet MAC address"); /* FEC MII MMFR bits definition */ #define FEC_MMFR_ST (1 << 30) +#define FEC_MMFR_ST_C45 (0) #define FEC_MMFR_OP_READ (2 << 28) +#define FEC_MMFR_OP_READ_C45 (3 << 28) #define FEC_MMFR_OP_WRITE (1 << 28) +#define FEC_MMFR_OP_ADDR_WRITE (0) #define FEC_MMFR_PA(v) ((v & 0x1f) << 23) #define FEC_MMFR_RA(v) ((v & 0x1f) << 18) #define FEC_MMFR_TA (2 << 16) @@ -365,7 +368,7 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq, status = fec16_to_cpu(bdp->cbd_sc); status &= ~BD_ENET_TX_STATS; status |= (BD_ENET_TX_TC | BD_ENET_TX_READY); - frag_len = skb_shinfo(skb)->frags[frag].size; + frag_len = skb_frag_size(&skb_shinfo(skb)->frags[frag]); /* Handle the last BD specially */ if (frag == nr_frags - 1) { @@ -387,7 +390,7 @@ fec_enet_txq_submit_frag_skb(struct fec_enet_priv_tx_q *txq, ebdp->cbd_esc = cpu_to_fec32(estatus); } - bufaddr = page_address(this_frag->page.p) + this_frag->page_offset; + bufaddr = skb_frag_address(this_frag); index = fec_enet_get_bd_index(bdp, &txq->bd); if (((unsigned long) bufaddr) & fep->tx_align || @@ -1767,7 +1770,8 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) struct fec_enet_private *fep = bus->priv; struct device *dev = &fep->pdev->dev; unsigned long time_left; - int ret = 0; + int ret = 0, frame_start, frame_addr, frame_op; + bool is_c45 = !!(regnum & MII_ADDR_C45); ret = pm_runtime_get_sync(dev); if (ret < 0) @@ -1775,9 +1779,37 @@ static int fec_enet_mdio_read(struct mii_bus *bus, int mii_id, int regnum) reinit_completion(&fep->mdio_done); + if (is_c45) { + frame_start = FEC_MMFR_ST_C45; + + /* write address */ + frame_addr = (regnum >> 16); + writel(frame_start | FEC_MMFR_OP_ADDR_WRITE | + FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(frame_addr) | + FEC_MMFR_TA | (regnum & 0xFFFF), + fep->hwp + FEC_MII_DATA); + + /* wait for end of transfer */ + time_left = wait_for_completion_timeout(&fep->mdio_done, + usecs_to_jiffies(FEC_MII_TIMEOUT)); + if (time_left == 0) { + netdev_err(fep->netdev, "MDIO address write timeout\n"); + ret = -ETIMEDOUT; + goto out; + } + + frame_op = FEC_MMFR_OP_READ_C45; + + } else { + /* C22 read */ + frame_op = FEC_MMFR_OP_READ; + frame_start = FEC_MMFR_ST; + frame_addr = regnum; + } + /* start a read op */ - writel(FEC_MMFR_ST | FEC_MMFR_OP_READ | - FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(regnum) | + writel(frame_start | frame_op | + FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(frame_addr) | FEC_MMFR_TA, fep->hwp + FEC_MII_DATA); /* wait for end of transfer */ @@ -1804,7 +1836,8 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, struct fec_enet_private *fep = bus->priv; struct device *dev = &fep->pdev->dev; unsigned long time_left; - int ret; + int ret, frame_start, frame_addr; + bool is_c45 = !!(regnum & MII_ADDR_C45); ret = pm_runtime_get_sync(dev); if (ret < 0) @@ -1814,9 +1847,33 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, reinit_completion(&fep->mdio_done); + if (is_c45) { + frame_start = FEC_MMFR_ST_C45; + + /* write address */ + frame_addr = (regnum >> 16); + writel(frame_start | FEC_MMFR_OP_ADDR_WRITE | + FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(frame_addr) | + FEC_MMFR_TA | (regnum & 0xFFFF), + fep->hwp + FEC_MII_DATA); + + /* wait for end of transfer */ + time_left = wait_for_completion_timeout(&fep->mdio_done, + usecs_to_jiffies(FEC_MII_TIMEOUT)); + if (time_left == 0) { + netdev_err(fep->netdev, "MDIO address write timeout\n"); + ret = -ETIMEDOUT; + goto out; + } + } else { + /* C22 write */ + frame_start = FEC_MMFR_ST; + frame_addr = regnum; + } + /* start a write op */ - writel(FEC_MMFR_ST | FEC_MMFR_OP_WRITE | - FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(regnum) | + writel(frame_start | FEC_MMFR_OP_WRITE | + FEC_MMFR_PA(mii_id) | FEC_MMFR_RA(frame_addr) | FEC_MMFR_TA | FEC_MMFR_DATA(value), fep->hwp + FEC_MII_DATA); @@ -1828,6 +1885,7 @@ static int fec_enet_mdio_write(struct mii_bus *bus, int mii_id, int regnum, ret = -ETIMEDOUT; } +out: pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); @@ -3338,7 +3396,6 @@ fec_probe(struct platform_device *pdev) struct fec_platform_data *pdata; struct net_device *ndev; int i, irq, ret = 0; - struct resource *r; const struct of_device_id *of_id; static int dev_id; struct device_node *np = pdev->dev.of_node, *phy_node; @@ -3378,8 +3435,7 @@ fec_probe(struct platform_device *pdev) /* Select default pin state */ pinctrl_pm_select_default_state(&pdev->dev); - r = platform_get_resource(pdev, IORESOURCE_MEM, 0); - fep->hwp = devm_ioremap_resource(&pdev->dev, r); + fep->hwp = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(fep->hwp)) { ret = PTR_ERR(fep->hwp); goto failed_ioremap; diff --git a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c index 5fad73b2e123..3981c06f082f 100644 --- a/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c +++ b/drivers/net/ethernet/freescale/fs_enet/fs_enet-main.c @@ -501,7 +501,7 @@ fs_enet_start_xmit(struct sk_buff *skb, struct net_device *dev) nr_frags = skb_shinfo(skb)->nr_frags; frag = skb_shinfo(skb)->frags; for (i = 0; i < nr_frags; i++, frag++) { - if (!IS_ALIGNED(frag->page_offset, 4)) { + if (!IS_ALIGNED(skb_frag_off(frag), 4)) { is_aligned = 0; break; } diff --git a/drivers/net/ethernet/freescale/gianfar.c b/drivers/net/ethernet/freescale/gianfar.c index 7ea19e173339..24bf7f68375f 100644 --- a/drivers/net/ethernet/freescale/gianfar.c +++ b/drivers/net/ethernet/freescale/gianfar.c @@ -105,43 +105,6 @@ const char gfar_driver_version[] = "2.0"; -static int gfar_enet_open(struct net_device *dev); -static netdev_tx_t gfar_start_xmit(struct sk_buff *skb, struct net_device *dev); -static void gfar_reset_task(struct work_struct *work); -static void gfar_timeout(struct net_device *dev); -static int gfar_close(struct net_device *dev); -static void gfar_alloc_rx_buffs(struct gfar_priv_rx_q *rx_queue, - int alloc_cnt); -static int gfar_set_mac_address(struct net_device *dev); -static int gfar_change_mtu(struct net_device *dev, int new_mtu); -static irqreturn_t gfar_error(int irq, void *dev_id); -static irqreturn_t gfar_transmit(int irq, void *dev_id); -static irqreturn_t gfar_interrupt(int irq, void *dev_id); -static void adjust_link(struct net_device *dev); -static noinline void gfar_update_link_state(struct gfar_private *priv); -static int init_phy(struct net_device *dev); -static int gfar_probe(struct platform_device *ofdev); -static int gfar_remove(struct platform_device *ofdev); -static void free_skb_resources(struct gfar_private *priv); -static void gfar_set_multi(struct net_device *dev); -static void gfar_set_hash_for_addr(struct net_device *dev, u8 *addr); -static void gfar_configure_serdes(struct net_device *dev); -static int gfar_poll_rx(struct napi_struct *napi, int budget); -static int gfar_poll_tx(struct napi_struct *napi, int budget); -static int gfar_poll_rx_sq(struct napi_struct *napi, int budget); -static int gfar_poll_tx_sq(struct napi_struct *napi, int budget); -#ifdef CONFIG_NET_POLL_CONTROLLER -static void gfar_netpoll(struct net_device *dev); -#endif -int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit); -static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue); -static void gfar_process_frame(struct net_device *ndev, struct sk_buff *skb); -static void gfar_halt_nodisable(struct gfar_private *priv); -static void gfar_clear_exact_match(struct net_device *dev); -static void gfar_set_mac_for_addr(struct net_device *dev, int num, - const u8 *addr); -static int gfar_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); - MODULE_AUTHOR("Freescale Semiconductor, Inc"); MODULE_DESCRIPTION("Gianfar Ethernet Driver"); MODULE_LICENSE("GPL"); @@ -162,138 +125,6 @@ static void gfar_init_rxbdp(struct gfar_priv_rx_q *rx_queue, struct rxbd8 *bdp, bdp->lstatus = cpu_to_be32(lstatus); } -static void gfar_init_bds(struct net_device *ndev) -{ - struct gfar_private *priv = netdev_priv(ndev); - struct gfar __iomem *regs = priv->gfargrp[0].regs; - struct gfar_priv_tx_q *tx_queue = NULL; - struct gfar_priv_rx_q *rx_queue = NULL; - struct txbd8 *txbdp; - u32 __iomem *rfbptr; - int i, j; - - for (i = 0; i < priv->num_tx_queues; i++) { - tx_queue = priv->tx_queue[i]; - /* Initialize some variables in our dev structure */ - tx_queue->num_txbdfree = tx_queue->tx_ring_size; - tx_queue->dirty_tx = tx_queue->tx_bd_base; - tx_queue->cur_tx = tx_queue->tx_bd_base; - tx_queue->skb_curtx = 0; - tx_queue->skb_dirtytx = 0; - - /* Initialize Transmit Descriptor Ring */ - txbdp = tx_queue->tx_bd_base; - for (j = 0; j < tx_queue->tx_ring_size; j++) { - txbdp->lstatus = 0; - txbdp->bufPtr = 0; - txbdp++; - } - - /* Set the last descriptor in the ring to indicate wrap */ - txbdp--; - txbdp->status = cpu_to_be16(be16_to_cpu(txbdp->status) | - TXBD_WRAP); - } - - rfbptr = ®s->rfbptr0; - for (i = 0; i < priv->num_rx_queues; i++) { - rx_queue = priv->rx_queue[i]; - - rx_queue->next_to_clean = 0; - rx_queue->next_to_use = 0; - rx_queue->next_to_alloc = 0; - - /* make sure next_to_clean != next_to_use after this - * by leaving at least 1 unused descriptor - */ - gfar_alloc_rx_buffs(rx_queue, gfar_rxbd_unused(rx_queue)); - - rx_queue->rfbptr = rfbptr; - rfbptr += 2; - } -} - -static int gfar_alloc_skb_resources(struct net_device *ndev) -{ - void *vaddr; - dma_addr_t addr; - int i, j; - struct gfar_private *priv = netdev_priv(ndev); - struct device *dev = priv->dev; - struct gfar_priv_tx_q *tx_queue = NULL; - struct gfar_priv_rx_q *rx_queue = NULL; - - priv->total_tx_ring_size = 0; - for (i = 0; i < priv->num_tx_queues; i++) - priv->total_tx_ring_size += priv->tx_queue[i]->tx_ring_size; - - priv->total_rx_ring_size = 0; - for (i = 0; i < priv->num_rx_queues; i++) - priv->total_rx_ring_size += priv->rx_queue[i]->rx_ring_size; - - /* Allocate memory for the buffer descriptors */ - vaddr = dma_alloc_coherent(dev, - (priv->total_tx_ring_size * - sizeof(struct txbd8)) + - (priv->total_rx_ring_size * - sizeof(struct rxbd8)), - &addr, GFP_KERNEL); - if (!vaddr) - return -ENOMEM; - - for (i = 0; i < priv->num_tx_queues; i++) { - tx_queue = priv->tx_queue[i]; - tx_queue->tx_bd_base = vaddr; - tx_queue->tx_bd_dma_base = addr; - tx_queue->dev = ndev; - /* enet DMA only understands physical addresses */ - addr += sizeof(struct txbd8) * tx_queue->tx_ring_size; - vaddr += sizeof(struct txbd8) * tx_queue->tx_ring_size; - } - - /* Start the rx descriptor ring where the tx ring leaves off */ - for (i = 0; i < priv->num_rx_queues; i++) { - rx_queue = priv->rx_queue[i]; - rx_queue->rx_bd_base = vaddr; - rx_queue->rx_bd_dma_base = addr; - rx_queue->ndev = ndev; - rx_queue->dev = dev; - addr += sizeof(struct rxbd8) * rx_queue->rx_ring_size; - vaddr += sizeof(struct rxbd8) * rx_queue->rx_ring_size; - } - - /* Setup the skbuff rings */ - for (i = 0; i < priv->num_tx_queues; i++) { - tx_queue = priv->tx_queue[i]; - tx_queue->tx_skbuff = - kmalloc_array(tx_queue->tx_ring_size, - sizeof(*tx_queue->tx_skbuff), - GFP_KERNEL); - if (!tx_queue->tx_skbuff) - goto cleanup; - - for (j = 0; j < tx_queue->tx_ring_size; j++) - tx_queue->tx_skbuff[j] = NULL; - } - - for (i = 0; i < priv->num_rx_queues; i++) { - rx_queue = priv->rx_queue[i]; - rx_queue->rx_buff = kcalloc(rx_queue->rx_ring_size, - sizeof(*rx_queue->rx_buff), - GFP_KERNEL); - if (!rx_queue->rx_buff) - goto cleanup; - } - - gfar_init_bds(ndev); - - return 0; - -cleanup: - free_skb_resources(priv); - return -ENOMEM; -} - static void gfar_init_tx_rx_base(struct gfar_private *priv) { struct gfar __iomem *regs = priv->gfargrp[0].regs; @@ -444,7 +275,7 @@ static void gfar_configure_coalescing(struct gfar_private *priv, } } -void gfar_configure_coalescing_all(struct gfar_private *priv) +static void gfar_configure_coalescing_all(struct gfar_private *priv) { gfar_configure_coalescing(priv, 0xFF, 0xFF); } @@ -477,6 +308,62 @@ static struct net_device_stats *gfar_get_stats(struct net_device *dev) return &dev->stats; } +/* Set the appropriate hash bit for the given addr */ +/* The algorithm works like so: + * 1) Take the Destination Address (ie the multicast address), and + * do a CRC on it (little endian), and reverse the bits of the + * result. + * 2) Use the 8 most significant bits as a hash into a 256-entry + * table. The table is controlled through 8 32-bit registers: + * gaddr0-7. gaddr0's MSB is entry 0, and gaddr7's LSB is + * gaddr7. This means that the 3 most significant bits in the + * hash index which gaddr register to use, and the 5 other bits + * indicate which bit (assuming an IBM numbering scheme, which + * for PowerPC (tm) is usually the case) in the register holds + * the entry. + */ +static void gfar_set_hash_for_addr(struct net_device *dev, u8 *addr) +{ + u32 tempval; + struct gfar_private *priv = netdev_priv(dev); + u32 result = ether_crc(ETH_ALEN, addr); + int width = priv->hash_width; + u8 whichbit = (result >> (32 - width)) & 0x1f; + u8 whichreg = result >> (32 - width + 5); + u32 value = (1 << (31-whichbit)); + + tempval = gfar_read(priv->hash_regs[whichreg]); + tempval |= value; + gfar_write(priv->hash_regs[whichreg], tempval); +} + +/* There are multiple MAC Address register pairs on some controllers + * This function sets the numth pair to a given address + */ +static void gfar_set_mac_for_addr(struct net_device *dev, int num, + const u8 *addr) +{ + struct gfar_private *priv = netdev_priv(dev); + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 tempval; + u32 __iomem *macptr = ®s->macstnaddr1; + + macptr += num*2; + + /* For a station address of 0x12345678ABCD in transmission + * order (BE), MACnADDR1 is set to 0xCDAB7856 and + * MACnADDR2 is set to 0x34120000. + */ + tempval = (addr[5] << 24) | (addr[4] << 16) | + (addr[3] << 8) | addr[2]; + + gfar_write(macptr, tempval); + + tempval = (addr[1] << 24) | (addr[0] << 16); + + gfar_write(macptr+1, tempval); +} + static int gfar_set_mac_addr(struct net_device *dev, void *p) { eth_mac_addr(dev, p); @@ -486,24 +373,6 @@ static int gfar_set_mac_addr(struct net_device *dev, void *p) return 0; } -static const struct net_device_ops gfar_netdev_ops = { - .ndo_open = gfar_enet_open, - .ndo_start_xmit = gfar_start_xmit, - .ndo_stop = gfar_close, - .ndo_change_mtu = gfar_change_mtu, - .ndo_set_features = gfar_set_features, - .ndo_set_rx_mode = gfar_set_multi, - .ndo_tx_timeout = gfar_timeout, - .ndo_do_ioctl = gfar_ioctl, - .ndo_get_stats = gfar_get_stats, - .ndo_change_carrier = fixed_phy_change_carrier, - .ndo_set_mac_address = gfar_set_mac_addr, - .ndo_validate_addr = eth_validate_addr, -#ifdef CONFIG_NET_POLL_CONTROLLER - .ndo_poll_controller = gfar_netpoll, -#endif -}; - static void gfar_ints_disable(struct gfar_private *priv) { int i; @@ -723,10 +592,53 @@ static int gfar_of_group_count(struct device_node *np) return num; } +/* Reads the controller's registers to determine what interface + * connects it to the PHY. + */ +static phy_interface_t gfar_get_interface(struct net_device *dev) +{ + struct gfar_private *priv = netdev_priv(dev); + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 ecntrl; + + ecntrl = gfar_read(®s->ecntrl); + + if (ecntrl & ECNTRL_SGMII_MODE) + return PHY_INTERFACE_MODE_SGMII; + + if (ecntrl & ECNTRL_TBI_MODE) { + if (ecntrl & ECNTRL_REDUCED_MODE) + return PHY_INTERFACE_MODE_RTBI; + else + return PHY_INTERFACE_MODE_TBI; + } + + if (ecntrl & ECNTRL_REDUCED_MODE) { + if (ecntrl & ECNTRL_REDUCED_MII_MODE) { + return PHY_INTERFACE_MODE_RMII; + } + else { + phy_interface_t interface = priv->interface; + + /* This isn't autodetected right now, so it must + * be set by the device tree or platform code. + */ + if (interface == PHY_INTERFACE_MODE_RGMII_ID) + return PHY_INTERFACE_MODE_RGMII_ID; + + return PHY_INTERFACE_MODE_RGMII; + } + } + + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT) + return PHY_INTERFACE_MODE_GMII; + + return PHY_INTERFACE_MODE_MII; +} + static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) { const char *model; - const char *ctype; const void *mac_addr; int err = 0, i; struct net_device *dev = NULL; @@ -889,13 +801,15 @@ static int gfar_of_init(struct platform_device *ofdev, struct net_device **pdev) FSL_GIANFAR_DEV_HAS_TIMER | FSL_GIANFAR_DEV_HAS_RX_FILER; - err = of_property_read_string(np, "phy-connection-type", &ctype); - - /* We only care about rgmii-id. The rest are autodetected */ - if (err == 0 && !strcmp(ctype, "rgmii-id")) - priv->interface = PHY_INTERFACE_MODE_RGMII_ID; + /* Use PHY connection type from the DT node if one is specified there. + * rgmii-id really needs to be specified. Other types can be + * detected by hardware + */ + err = of_get_phy_mode(np); + if (err >= 0) + priv->interface = err; else - priv->interface = PHY_INTERFACE_MODE_MII; + priv->interface = gfar_get_interface(dev); if (of_find_property(np, "fsl,magic-packet", NULL)) priv->device_flags |= FSL_GIANFAR_DEV_HAS_MAGIC_PACKET; @@ -931,85 +845,6 @@ tx_alloc_failed: return err; } -static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr) -{ - struct hwtstamp_config config; - struct gfar_private *priv = netdev_priv(netdev); - - if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) - return -EFAULT; - - /* reserved for future extensions */ - if (config.flags) - return -EINVAL; - - switch (config.tx_type) { - case HWTSTAMP_TX_OFF: - priv->hwts_tx_en = 0; - break; - case HWTSTAMP_TX_ON: - if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)) - return -ERANGE; - priv->hwts_tx_en = 1; - break; - default: - return -ERANGE; - } - - switch (config.rx_filter) { - case HWTSTAMP_FILTER_NONE: - if (priv->hwts_rx_en) { - priv->hwts_rx_en = 0; - reset_gfar(netdev); - } - break; - default: - if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)) - return -ERANGE; - if (!priv->hwts_rx_en) { - priv->hwts_rx_en = 1; - reset_gfar(netdev); - } - config.rx_filter = HWTSTAMP_FILTER_ALL; - break; - } - - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; -} - -static int gfar_hwtstamp_get(struct net_device *netdev, struct ifreq *ifr) -{ - struct hwtstamp_config config; - struct gfar_private *priv = netdev_priv(netdev); - - config.flags = 0; - config.tx_type = priv->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; - config.rx_filter = (priv->hwts_rx_en ? - HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE); - - return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? - -EFAULT : 0; -} - -static int gfar_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) -{ - struct phy_device *phydev = dev->phydev; - - if (!netif_running(dev)) - return -EINVAL; - - if (cmd == SIOCSHWTSTAMP) - return gfar_hwtstamp_set(dev, rq); - if (cmd == SIOCGHWTSTAMP) - return gfar_hwtstamp_get(dev, rq); - - if (!phydev) - return -ENODEV; - - return phy_mii_ioctl(phydev, rq, cmd); -} - static u32 cluster_entry_per_class(struct gfar_private *priv, u32 rqfar, u32 class) { @@ -1133,135 +968,6 @@ static void gfar_detect_errata(struct gfar_private *priv) priv->errata); } -void gfar_mac_reset(struct gfar_private *priv) -{ - struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 tempval; - - /* Reset MAC layer */ - gfar_write(®s->maccfg1, MACCFG1_SOFT_RESET); - - /* We need to delay at least 3 TX clocks */ - udelay(3); - - /* the soft reset bit is not self-resetting, so we need to - * clear it before resuming normal operation - */ - gfar_write(®s->maccfg1, 0); - - udelay(3); - - gfar_rx_offload_en(priv); - - /* Initialize the max receive frame/buffer lengths */ - gfar_write(®s->maxfrm, GFAR_JUMBO_FRAME_SIZE); - gfar_write(®s->mrblr, GFAR_RXB_SIZE); - - /* Initialize the Minimum Frame Length Register */ - gfar_write(®s->minflr, MINFLR_INIT_SETTINGS); - - /* Initialize MACCFG2. */ - tempval = MACCFG2_INIT_SETTINGS; - - /* eTSEC74 erratum: Rx frames of length MAXFRM or MAXFRM-1 - * are marked as truncated. Avoid this by MACCFG2[Huge Frame]=1, - * and by checking RxBD[LG] and discarding larger than MAXFRM. - */ - if (gfar_has_errata(priv, GFAR_ERRATA_74)) - tempval |= MACCFG2_HUGEFRAME | MACCFG2_LENGTHCHECK; - - gfar_write(®s->maccfg2, tempval); - - /* Clear mac addr hash registers */ - gfar_write(®s->igaddr0, 0); - gfar_write(®s->igaddr1, 0); - gfar_write(®s->igaddr2, 0); - gfar_write(®s->igaddr3, 0); - gfar_write(®s->igaddr4, 0); - gfar_write(®s->igaddr5, 0); - gfar_write(®s->igaddr6, 0); - gfar_write(®s->igaddr7, 0); - - gfar_write(®s->gaddr0, 0); - gfar_write(®s->gaddr1, 0); - gfar_write(®s->gaddr2, 0); - gfar_write(®s->gaddr3, 0); - gfar_write(®s->gaddr4, 0); - gfar_write(®s->gaddr5, 0); - gfar_write(®s->gaddr6, 0); - gfar_write(®s->gaddr7, 0); - - if (priv->extended_hash) - gfar_clear_exact_match(priv->ndev); - - gfar_mac_rx_config(priv); - - gfar_mac_tx_config(priv); - - gfar_set_mac_address(priv->ndev); - - gfar_set_multi(priv->ndev); - - /* clear ievent and imask before configuring coalescing */ - gfar_ints_disable(priv); - - /* Configure the coalescing support */ - gfar_configure_coalescing_all(priv); -} - -static void gfar_hw_init(struct gfar_private *priv) -{ - struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 attrs; - - /* Stop the DMA engine now, in case it was running before - * (The firmware could have used it, and left it running). - */ - gfar_halt(priv); - - gfar_mac_reset(priv); - - /* Zero out the rmon mib registers if it has them */ - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) { - memset_io(&(regs->rmon), 0, sizeof(struct rmon_mib)); - - /* Mask off the CAM interrupts */ - gfar_write(®s->rmon.cam1, 0xffffffff); - gfar_write(®s->rmon.cam2, 0xffffffff); - } - - /* Initialize ECNTRL */ - gfar_write(®s->ecntrl, ECNTRL_INIT_SETTINGS); - - /* Set the extraction length and index */ - attrs = ATTRELI_EL(priv->rx_stash_size) | - ATTRELI_EI(priv->rx_stash_index); - - gfar_write(®s->attreli, attrs); - - /* Start with defaults, and add stashing - * depending on driver parameters - */ - attrs = ATTR_INIT_SETTINGS; - - if (priv->bd_stash_en) - attrs |= ATTR_BDSTASH; - - if (priv->rx_stash_size != 0) - attrs |= ATTR_BUFSTASH; - - gfar_write(®s->attr, attrs); - - /* FIFO configs */ - gfar_write(®s->fifo_tx_thr, DEFAULT_FIFO_TX_THR); - gfar_write(®s->fifo_tx_starve, DEFAULT_FIFO_TX_STARVE); - gfar_write(®s->fifo_tx_starve_shutoff, DEFAULT_FIFO_TX_STARVE_OFF); - - /* Program the interrupt steering regs, only for MG devices */ - if (priv->num_grps > 1) - gfar_write_isrg(priv); -} - static void gfar_init_addr_hash_table(struct gfar_private *priv) { struct gfar __iomem *regs = priv->gfargrp[0].regs; @@ -1302,578 +1008,6 @@ static void gfar_init_addr_hash_table(struct gfar_private *priv) } } -/* Set up the ethernet device structure, private data, - * and anything else we need before we start - */ -static int gfar_probe(struct platform_device *ofdev) -{ - struct device_node *np = ofdev->dev.of_node; - struct net_device *dev = NULL; - struct gfar_private *priv = NULL; - int err = 0, i; - - err = gfar_of_init(ofdev, &dev); - - if (err) - return err; - - priv = netdev_priv(dev); - priv->ndev = dev; - priv->ofdev = ofdev; - priv->dev = &ofdev->dev; - SET_NETDEV_DEV(dev, &ofdev->dev); - - INIT_WORK(&priv->reset_task, gfar_reset_task); - - platform_set_drvdata(ofdev, priv); - - gfar_detect_errata(priv); - - /* Set the dev->base_addr to the gfar reg region */ - dev->base_addr = (unsigned long) priv->gfargrp[0].regs; - - /* Fill in the dev structure */ - dev->watchdog_timeo = TX_TIMEOUT; - /* MTU range: 50 - 9586 */ - dev->mtu = 1500; - dev->min_mtu = 50; - dev->max_mtu = GFAR_JUMBO_FRAME_SIZE - ETH_HLEN; - dev->netdev_ops = &gfar_netdev_ops; - dev->ethtool_ops = &gfar_ethtool_ops; - - /* Register for napi ...We are registering NAPI for each grp */ - for (i = 0; i < priv->num_grps; i++) { - if (priv->poll_mode == GFAR_SQ_POLLING) { - netif_napi_add(dev, &priv->gfargrp[i].napi_rx, - gfar_poll_rx_sq, GFAR_DEV_WEIGHT); - netif_tx_napi_add(dev, &priv->gfargrp[i].napi_tx, - gfar_poll_tx_sq, 2); - } else { - netif_napi_add(dev, &priv->gfargrp[i].napi_rx, - gfar_poll_rx, GFAR_DEV_WEIGHT); - netif_tx_napi_add(dev, &priv->gfargrp[i].napi_tx, - gfar_poll_tx, 2); - } - } - - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM) { - dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG | - NETIF_F_RXCSUM; - dev->features |= NETIF_F_IP_CSUM | NETIF_F_SG | - NETIF_F_RXCSUM | NETIF_F_HIGHDMA; - } - - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_VLAN) { - dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX; - dev->features |= NETIF_F_HW_VLAN_CTAG_RX; - } - - dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; - - gfar_init_addr_hash_table(priv); - - /* Insert receive time stamps into padding alignment bytes, and - * plus 2 bytes padding to ensure the cpu alignment. - */ - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) - priv->padding = 8 + DEFAULT_PADDING; - - if (dev->features & NETIF_F_IP_CSUM || - priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) - dev->needed_headroom = GMAC_FCB_LEN; - - /* Initializing some of the rx/tx queue level parameters */ - for (i = 0; i < priv->num_tx_queues; i++) { - priv->tx_queue[i]->tx_ring_size = DEFAULT_TX_RING_SIZE; - priv->tx_queue[i]->num_txbdfree = DEFAULT_TX_RING_SIZE; - priv->tx_queue[i]->txcoalescing = DEFAULT_TX_COALESCE; - priv->tx_queue[i]->txic = DEFAULT_TXIC; - } - - for (i = 0; i < priv->num_rx_queues; i++) { - priv->rx_queue[i]->rx_ring_size = DEFAULT_RX_RING_SIZE; - priv->rx_queue[i]->rxcoalescing = DEFAULT_RX_COALESCE; - priv->rx_queue[i]->rxic = DEFAULT_RXIC; - } - - /* Always enable rx filer if available */ - priv->rx_filer_enable = - (priv->device_flags & FSL_GIANFAR_DEV_HAS_RX_FILER) ? 1 : 0; - /* Enable most messages by default */ - priv->msg_enable = (NETIF_MSG_IFUP << 1 ) - 1; - /* use pritority h/w tx queue scheduling for single queue devices */ - if (priv->num_tx_queues == 1) - priv->prio_sched_en = 1; - - set_bit(GFAR_DOWN, &priv->state); - - gfar_hw_init(priv); - - /* Carrier starts down, phylib will bring it up */ - netif_carrier_off(dev); - - err = register_netdev(dev); - - if (err) { - pr_err("%s: Cannot register net device, aborting\n", dev->name); - goto register_fail; - } - - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) - priv->wol_supported |= GFAR_WOL_MAGIC; - - if ((priv->device_flags & FSL_GIANFAR_DEV_HAS_WAKE_ON_FILER) && - priv->rx_filer_enable) - priv->wol_supported |= GFAR_WOL_FILER_UCAST; - - device_set_wakeup_capable(&ofdev->dev, priv->wol_supported); - - /* fill out IRQ number and name fields */ - for (i = 0; i < priv->num_grps; i++) { - struct gfar_priv_grp *grp = &priv->gfargrp[i]; - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { - sprintf(gfar_irq(grp, TX)->name, "%s%s%c%s", - dev->name, "_g", '0' + i, "_tx"); - sprintf(gfar_irq(grp, RX)->name, "%s%s%c%s", - dev->name, "_g", '0' + i, "_rx"); - sprintf(gfar_irq(grp, ER)->name, "%s%s%c%s", - dev->name, "_g", '0' + i, "_er"); - } else - strcpy(gfar_irq(grp, TX)->name, dev->name); - } - - /* Initialize the filer table */ - gfar_init_filer_table(priv); - - /* Print out the device info */ - netdev_info(dev, "mac: %pM\n", dev->dev_addr); - - /* Even more device info helps when determining which kernel - * provided which set of benchmarks. - */ - netdev_info(dev, "Running with NAPI enabled\n"); - for (i = 0; i < priv->num_rx_queues; i++) - netdev_info(dev, "RX BD ring size for Q[%d]: %d\n", - i, priv->rx_queue[i]->rx_ring_size); - for (i = 0; i < priv->num_tx_queues; i++) - netdev_info(dev, "TX BD ring size for Q[%d]: %d\n", - i, priv->tx_queue[i]->tx_ring_size); - - return 0; - -register_fail: - if (of_phy_is_fixed_link(np)) - of_phy_deregister_fixed_link(np); - unmap_group_regs(priv); - gfar_free_rx_queues(priv); - gfar_free_tx_queues(priv); - of_node_put(priv->phy_node); - of_node_put(priv->tbi_node); - free_gfar_dev(priv); - return err; -} - -static int gfar_remove(struct platform_device *ofdev) -{ - struct gfar_private *priv = platform_get_drvdata(ofdev); - struct device_node *np = ofdev->dev.of_node; - - of_node_put(priv->phy_node); - of_node_put(priv->tbi_node); - - unregister_netdev(priv->ndev); - - if (of_phy_is_fixed_link(np)) - of_phy_deregister_fixed_link(np); - - unmap_group_regs(priv); - gfar_free_rx_queues(priv); - gfar_free_tx_queues(priv); - free_gfar_dev(priv); - - return 0; -} - -#ifdef CONFIG_PM - -static void __gfar_filer_disable(struct gfar_private *priv) -{ - struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 temp; - - temp = gfar_read(®s->rctrl); - temp &= ~(RCTRL_FILREN | RCTRL_PRSDEP_INIT); - gfar_write(®s->rctrl, temp); -} - -static void __gfar_filer_enable(struct gfar_private *priv) -{ - struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 temp; - - temp = gfar_read(®s->rctrl); - temp |= RCTRL_FILREN | RCTRL_PRSDEP_INIT; - gfar_write(®s->rctrl, temp); -} - -/* Filer rules implementing wol capabilities */ -static void gfar_filer_config_wol(struct gfar_private *priv) -{ - unsigned int i; - u32 rqfcr; - - __gfar_filer_disable(priv); - - /* clear the filer table, reject any packet by default */ - rqfcr = RQFCR_RJE | RQFCR_CMP_MATCH; - for (i = 0; i <= MAX_FILER_IDX; i++) - gfar_write_filer(priv, i, rqfcr, 0); - - i = 0; - if (priv->wol_opts & GFAR_WOL_FILER_UCAST) { - /* unicast packet, accept it */ - struct net_device *ndev = priv->ndev; - /* get the default rx queue index */ - u8 qindex = (u8)priv->gfargrp[0].rx_queue->qindex; - u32 dest_mac_addr = (ndev->dev_addr[0] << 16) | - (ndev->dev_addr[1] << 8) | - ndev->dev_addr[2]; - - rqfcr = (qindex << 10) | RQFCR_AND | - RQFCR_CMP_EXACT | RQFCR_PID_DAH; - - gfar_write_filer(priv, i++, rqfcr, dest_mac_addr); - - dest_mac_addr = (ndev->dev_addr[3] << 16) | - (ndev->dev_addr[4] << 8) | - ndev->dev_addr[5]; - rqfcr = (qindex << 10) | RQFCR_GPI | - RQFCR_CMP_EXACT | RQFCR_PID_DAL; - gfar_write_filer(priv, i++, rqfcr, dest_mac_addr); - } - - __gfar_filer_enable(priv); -} - -static void gfar_filer_restore_table(struct gfar_private *priv) -{ - u32 rqfcr, rqfpr; - unsigned int i; - - __gfar_filer_disable(priv); - - for (i = 0; i <= MAX_FILER_IDX; i++) { - rqfcr = priv->ftp_rqfcr[i]; - rqfpr = priv->ftp_rqfpr[i]; - gfar_write_filer(priv, i, rqfcr, rqfpr); - } - - __gfar_filer_enable(priv); -} - -/* gfar_start() for Rx only and with the FGPI filer interrupt enabled */ -static void gfar_start_wol_filer(struct gfar_private *priv) -{ - struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 tempval; - int i = 0; - - /* Enable Rx hw queues */ - gfar_write(®s->rqueue, priv->rqueue); - - /* Initialize DMACTRL to have WWR and WOP */ - tempval = gfar_read(®s->dmactrl); - tempval |= DMACTRL_INIT_SETTINGS; - gfar_write(®s->dmactrl, tempval); - - /* Make sure we aren't stopped */ - tempval = gfar_read(®s->dmactrl); - tempval &= ~DMACTRL_GRS; - gfar_write(®s->dmactrl, tempval); - - for (i = 0; i < priv->num_grps; i++) { - regs = priv->gfargrp[i].regs; - /* Clear RHLT, so that the DMA starts polling now */ - gfar_write(®s->rstat, priv->gfargrp[i].rstat); - /* enable the Filer General Purpose Interrupt */ - gfar_write(®s->imask, IMASK_FGPI); - } - - /* Enable Rx DMA */ - tempval = gfar_read(®s->maccfg1); - tempval |= MACCFG1_RX_EN; - gfar_write(®s->maccfg1, tempval); -} - -static int gfar_suspend(struct device *dev) -{ - struct gfar_private *priv = dev_get_drvdata(dev); - struct net_device *ndev = priv->ndev; - struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 tempval; - u16 wol = priv->wol_opts; - - if (!netif_running(ndev)) - return 0; - - disable_napi(priv); - netif_tx_lock(ndev); - netif_device_detach(ndev); - netif_tx_unlock(ndev); - - gfar_halt(priv); - - if (wol & GFAR_WOL_MAGIC) { - /* Enable interrupt on Magic Packet */ - gfar_write(®s->imask, IMASK_MAG); - - /* Enable Magic Packet mode */ - tempval = gfar_read(®s->maccfg2); - tempval |= MACCFG2_MPEN; - gfar_write(®s->maccfg2, tempval); - - /* re-enable the Rx block */ - tempval = gfar_read(®s->maccfg1); - tempval |= MACCFG1_RX_EN; - gfar_write(®s->maccfg1, tempval); - - } else if (wol & GFAR_WOL_FILER_UCAST) { - gfar_filer_config_wol(priv); - gfar_start_wol_filer(priv); - - } else { - phy_stop(ndev->phydev); - } - - return 0; -} - -static int gfar_resume(struct device *dev) -{ - struct gfar_private *priv = dev_get_drvdata(dev); - struct net_device *ndev = priv->ndev; - struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 tempval; - u16 wol = priv->wol_opts; - - if (!netif_running(ndev)) - return 0; - - if (wol & GFAR_WOL_MAGIC) { - /* Disable Magic Packet mode */ - tempval = gfar_read(®s->maccfg2); - tempval &= ~MACCFG2_MPEN; - gfar_write(®s->maccfg2, tempval); - - } else if (wol & GFAR_WOL_FILER_UCAST) { - /* need to stop rx only, tx is already down */ - gfar_halt(priv); - gfar_filer_restore_table(priv); - - } else { - phy_start(ndev->phydev); - } - - gfar_start(priv); - - netif_device_attach(ndev); - enable_napi(priv); - - return 0; -} - -static int gfar_restore(struct device *dev) -{ - struct gfar_private *priv = dev_get_drvdata(dev); - struct net_device *ndev = priv->ndev; - - if (!netif_running(ndev)) { - netif_device_attach(ndev); - - return 0; - } - - gfar_init_bds(ndev); - - gfar_mac_reset(priv); - - gfar_init_tx_rx_base(priv); - - gfar_start(priv); - - priv->oldlink = 0; - priv->oldspeed = 0; - priv->oldduplex = -1; - - if (ndev->phydev) - phy_start(ndev->phydev); - - netif_device_attach(ndev); - enable_napi(priv); - - return 0; -} - -static const struct dev_pm_ops gfar_pm_ops = { - .suspend = gfar_suspend, - .resume = gfar_resume, - .freeze = gfar_suspend, - .thaw = gfar_resume, - .restore = gfar_restore, -}; - -#define GFAR_PM_OPS (&gfar_pm_ops) - -#else - -#define GFAR_PM_OPS NULL - -#endif - -/* Reads the controller's registers to determine what interface - * connects it to the PHY. - */ -static phy_interface_t gfar_get_interface(struct net_device *dev) -{ - struct gfar_private *priv = netdev_priv(dev); - struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 ecntrl; - - ecntrl = gfar_read(®s->ecntrl); - - if (ecntrl & ECNTRL_SGMII_MODE) - return PHY_INTERFACE_MODE_SGMII; - - if (ecntrl & ECNTRL_TBI_MODE) { - if (ecntrl & ECNTRL_REDUCED_MODE) - return PHY_INTERFACE_MODE_RTBI; - else - return PHY_INTERFACE_MODE_TBI; - } - - if (ecntrl & ECNTRL_REDUCED_MODE) { - if (ecntrl & ECNTRL_REDUCED_MII_MODE) { - return PHY_INTERFACE_MODE_RMII; - } - else { - phy_interface_t interface = priv->interface; - - /* This isn't autodetected right now, so it must - * be set by the device tree or platform code. - */ - if (interface == PHY_INTERFACE_MODE_RGMII_ID) - return PHY_INTERFACE_MODE_RGMII_ID; - - return PHY_INTERFACE_MODE_RGMII; - } - } - - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT) - return PHY_INTERFACE_MODE_GMII; - - return PHY_INTERFACE_MODE_MII; -} - - -/* Initializes driver's PHY state, and attaches to the PHY. - * Returns 0 on success. - */ -static int init_phy(struct net_device *dev) -{ - __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; - struct gfar_private *priv = netdev_priv(dev); - phy_interface_t interface; - struct phy_device *phydev; - struct ethtool_eee edata; - - linkmode_set_bit_array(phy_10_100_features_array, - ARRAY_SIZE(phy_10_100_features_array), - mask); - linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask); - linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask); - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT) - linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, mask); - - priv->oldlink = 0; - priv->oldspeed = 0; - priv->oldduplex = -1; - - interface = gfar_get_interface(dev); - - phydev = of_phy_connect(dev, priv->phy_node, &adjust_link, 0, - interface); - if (!phydev) { - dev_err(&dev->dev, "could not attach to PHY\n"); - return -ENODEV; - } - - if (interface == PHY_INTERFACE_MODE_SGMII) - gfar_configure_serdes(dev); - - /* Remove any features not supported by the controller */ - linkmode_and(phydev->supported, phydev->supported, mask); - linkmode_copy(phydev->advertising, phydev->supported); - - /* Add support for flow control */ - phy_support_asym_pause(phydev); - - /* disable EEE autoneg, EEE not supported by eTSEC */ - memset(&edata, 0, sizeof(struct ethtool_eee)); - phy_ethtool_set_eee(phydev, &edata); - - return 0; -} - -/* Initialize TBI PHY interface for communicating with the - * SERDES lynx PHY on the chip. We communicate with this PHY - * through the MDIO bus on each controller, treating it as a - * "normal" PHY at the address found in the TBIPA register. We assume - * that the TBIPA register is valid. Either the MDIO bus code will set - * it to a value that doesn't conflict with other PHYs on the bus, or the - * value doesn't matter, as there are no other PHYs on the bus. - */ -static void gfar_configure_serdes(struct net_device *dev) -{ - struct gfar_private *priv = netdev_priv(dev); - struct phy_device *tbiphy; - - if (!priv->tbi_node) { - dev_warn(&dev->dev, "error: SGMII mode requires that the " - "device tree specify a tbi-handle\n"); - return; - } - - tbiphy = of_phy_find_device(priv->tbi_node); - if (!tbiphy) { - dev_err(&dev->dev, "error: Could not get TBI device\n"); - return; - } - - /* If the link is already up, we must already be ok, and don't need to - * configure and reset the TBI<->SerDes link. Maybe U-Boot configured - * everything for us? Resetting it takes the link down and requires - * several seconds for it to come back. - */ - if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS) { - put_device(&tbiphy->mdio.dev); - return; - } - - /* Single clk mode, mii mode off(for serdes communication) */ - phy_write(tbiphy, MII_TBICON, TBICON_CLK_SELECT); - - phy_write(tbiphy, MII_ADVERTISE, - ADVERTISE_1000XFULL | ADVERTISE_1000XPAUSE | - ADVERTISE_1000XPSE_ASYM); - - phy_write(tbiphy, MII_BMCR, - BMCR_ANENABLE | BMCR_ANRESTART | BMCR_FULLDPLX | - BMCR_SPEED1000); - - put_device(&tbiphy->mdio.dev); -} - static int __gfar_is_rx_idle(struct gfar_private *priv) { u32 res; @@ -1930,7 +1064,7 @@ retry: } /* Halt the receive and transmit queues */ -void gfar_halt(struct gfar_private *priv) +static void gfar_halt(struct gfar_private *priv) { struct gfar __iomem *regs = priv->gfargrp[0].regs; u32 tempval; @@ -1949,26 +1083,6 @@ void gfar_halt(struct gfar_private *priv) gfar_write(®s->maccfg1, tempval); } -void stop_gfar(struct net_device *dev) -{ - struct gfar_private *priv = netdev_priv(dev); - - netif_tx_stop_all_queues(dev); - - smp_mb__before_atomic(); - set_bit(GFAR_DOWN, &priv->state); - smp_mb__after_atomic(); - - disable_napi(priv); - - /* disable ints and gracefully shut down Rx/Tx DMA */ - gfar_halt(priv); - - phy_stop(dev->phydev); - - free_skb_resources(priv); -} - static void free_skb_tx_queue(struct gfar_priv_tx_q *tx_queue) { struct txbd8 *txbdp; @@ -2005,8 +1119,7 @@ static void free_skb_rx_queue(struct gfar_priv_rx_q *rx_queue) struct rxbd8 *rxbdp = rx_queue->rx_bd_base; - if (rx_queue->skb) - dev_kfree_skb(rx_queue->skb); + dev_kfree_skb(rx_queue->skb); for (i = 0; i < rx_queue->rx_ring_size; i++) { struct gfar_rx_buff *rxb = &rx_queue->rx_buff[i]; @@ -2062,7 +1175,27 @@ static void free_skb_resources(struct gfar_private *priv) priv->tx_queue[0]->tx_bd_dma_base); } -void gfar_start(struct gfar_private *priv) +void stop_gfar(struct net_device *dev) +{ + struct gfar_private *priv = netdev_priv(dev); + + netif_tx_stop_all_queues(dev); + + smp_mb__before_atomic(); + set_bit(GFAR_DOWN, &priv->state); + smp_mb__after_atomic(); + + disable_napi(priv); + + /* disable ints and gracefully shut down Rx/Tx DMA */ + gfar_halt(priv); + + phy_stop(dev->phydev); + + free_skb_resources(priv); +} + +static void gfar_start(struct gfar_private *priv) { struct gfar __iomem *regs = priv->gfargrp[0].regs; u32 tempval; @@ -2099,103 +1232,207 @@ void gfar_start(struct gfar_private *priv) netif_trans_update(priv->ndev); /* prevent tx timeout */ } -static void free_grp_irqs(struct gfar_priv_grp *grp) +static bool gfar_new_page(struct gfar_priv_rx_q *rxq, struct gfar_rx_buff *rxb) { - free_irq(gfar_irq(grp, TX)->irq, grp); - free_irq(gfar_irq(grp, RX)->irq, grp); - free_irq(gfar_irq(grp, ER)->irq, grp); + struct page *page; + dma_addr_t addr; + + page = dev_alloc_page(); + if (unlikely(!page)) + return false; + + addr = dma_map_page(rxq->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); + if (unlikely(dma_mapping_error(rxq->dev, addr))) { + __free_page(page); + + return false; + } + + rxb->dma = addr; + rxb->page = page; + rxb->page_offset = 0; + + return true; } -static int register_grp_irqs(struct gfar_priv_grp *grp) +static void gfar_rx_alloc_err(struct gfar_priv_rx_q *rx_queue) { - struct gfar_private *priv = grp->priv; - struct net_device *dev = priv->ndev; - int err; + struct gfar_private *priv = netdev_priv(rx_queue->ndev); + struct gfar_extra_stats *estats = &priv->extra_stats; - /* If the device has multiple interrupts, register for - * them. Otherwise, only register for the one - */ - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { - /* Install our interrupt handlers for Error, - * Transmit, and Receive - */ - err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0, - gfar_irq(grp, ER)->name, grp); - if (err < 0) { - netif_err(priv, intr, dev, "Can't get IRQ %d\n", - gfar_irq(grp, ER)->irq); + netdev_err(rx_queue->ndev, "Can't alloc RX buffers\n"); + atomic64_inc(&estats->rx_alloc_err); +} - goto err_irq_fail; - } - enable_irq_wake(gfar_irq(grp, ER)->irq); +static void gfar_alloc_rx_buffs(struct gfar_priv_rx_q *rx_queue, + int alloc_cnt) +{ + struct rxbd8 *bdp; + struct gfar_rx_buff *rxb; + int i; - err = request_irq(gfar_irq(grp, TX)->irq, gfar_transmit, 0, - gfar_irq(grp, TX)->name, grp); - if (err < 0) { - netif_err(priv, intr, dev, "Can't get IRQ %d\n", - gfar_irq(grp, TX)->irq); - goto tx_irq_fail; + i = rx_queue->next_to_use; + bdp = &rx_queue->rx_bd_base[i]; + rxb = &rx_queue->rx_buff[i]; + + while (alloc_cnt--) { + /* try reuse page */ + if (unlikely(!rxb->page)) { + if (unlikely(!gfar_new_page(rx_queue, rxb))) { + gfar_rx_alloc_err(rx_queue); + break; + } } - err = request_irq(gfar_irq(grp, RX)->irq, gfar_receive, 0, - gfar_irq(grp, RX)->name, grp); - if (err < 0) { - netif_err(priv, intr, dev, "Can't get IRQ %d\n", - gfar_irq(grp, RX)->irq); - goto rx_irq_fail; + + /* Setup the new RxBD */ + gfar_init_rxbdp(rx_queue, bdp, + rxb->dma + rxb->page_offset + RXBUF_ALIGNMENT); + + /* Update to the next pointer */ + bdp++; + rxb++; + + if (unlikely(++i == rx_queue->rx_ring_size)) { + i = 0; + bdp = rx_queue->rx_bd_base; + rxb = rx_queue->rx_buff; } - enable_irq_wake(gfar_irq(grp, RX)->irq); + } - } else { - err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0, - gfar_irq(grp, TX)->name, grp); - if (err < 0) { - netif_err(priv, intr, dev, "Can't get IRQ %d\n", - gfar_irq(grp, TX)->irq); - goto err_irq_fail; + rx_queue->next_to_use = i; + rx_queue->next_to_alloc = i; +} + +static void gfar_init_bds(struct net_device *ndev) +{ + struct gfar_private *priv = netdev_priv(ndev); + struct gfar __iomem *regs = priv->gfargrp[0].regs; + struct gfar_priv_tx_q *tx_queue = NULL; + struct gfar_priv_rx_q *rx_queue = NULL; + struct txbd8 *txbdp; + u32 __iomem *rfbptr; + int i, j; + + for (i = 0; i < priv->num_tx_queues; i++) { + tx_queue = priv->tx_queue[i]; + /* Initialize some variables in our dev structure */ + tx_queue->num_txbdfree = tx_queue->tx_ring_size; + tx_queue->dirty_tx = tx_queue->tx_bd_base; + tx_queue->cur_tx = tx_queue->tx_bd_base; + tx_queue->skb_curtx = 0; + tx_queue->skb_dirtytx = 0; + + /* Initialize Transmit Descriptor Ring */ + txbdp = tx_queue->tx_bd_base; + for (j = 0; j < tx_queue->tx_ring_size; j++) { + txbdp->lstatus = 0; + txbdp->bufPtr = 0; + txbdp++; } - enable_irq_wake(gfar_irq(grp, TX)->irq); + + /* Set the last descriptor in the ring to indicate wrap */ + txbdp--; + txbdp->status = cpu_to_be16(be16_to_cpu(txbdp->status) | + TXBD_WRAP); } - return 0; + rfbptr = ®s->rfbptr0; + for (i = 0; i < priv->num_rx_queues; i++) { + rx_queue = priv->rx_queue[i]; -rx_irq_fail: - free_irq(gfar_irq(grp, TX)->irq, grp); -tx_irq_fail: - free_irq(gfar_irq(grp, ER)->irq, grp); -err_irq_fail: - return err; + rx_queue->next_to_clean = 0; + rx_queue->next_to_use = 0; + rx_queue->next_to_alloc = 0; + + /* make sure next_to_clean != next_to_use after this + * by leaving at least 1 unused descriptor + */ + gfar_alloc_rx_buffs(rx_queue, gfar_rxbd_unused(rx_queue)); + rx_queue->rfbptr = rfbptr; + rfbptr += 2; + } } -static void gfar_free_irq(struct gfar_private *priv) +static int gfar_alloc_skb_resources(struct net_device *ndev) { - int i; + void *vaddr; + dma_addr_t addr; + int i, j; + struct gfar_private *priv = netdev_priv(ndev); + struct device *dev = priv->dev; + struct gfar_priv_tx_q *tx_queue = NULL; + struct gfar_priv_rx_q *rx_queue = NULL; - /* Free the IRQs */ - if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { - for (i = 0; i < priv->num_grps; i++) - free_grp_irqs(&priv->gfargrp[i]); - } else { - for (i = 0; i < priv->num_grps; i++) - free_irq(gfar_irq(&priv->gfargrp[i], TX)->irq, - &priv->gfargrp[i]); + priv->total_tx_ring_size = 0; + for (i = 0; i < priv->num_tx_queues; i++) + priv->total_tx_ring_size += priv->tx_queue[i]->tx_ring_size; + + priv->total_rx_ring_size = 0; + for (i = 0; i < priv->num_rx_queues; i++) + priv->total_rx_ring_size += priv->rx_queue[i]->rx_ring_size; + + /* Allocate memory for the buffer descriptors */ + vaddr = dma_alloc_coherent(dev, + (priv->total_tx_ring_size * + sizeof(struct txbd8)) + + (priv->total_rx_ring_size * + sizeof(struct rxbd8)), + &addr, GFP_KERNEL); + if (!vaddr) + return -ENOMEM; + + for (i = 0; i < priv->num_tx_queues; i++) { + tx_queue = priv->tx_queue[i]; + tx_queue->tx_bd_base = vaddr; + tx_queue->tx_bd_dma_base = addr; + tx_queue->dev = ndev; + /* enet DMA only understands physical addresses */ + addr += sizeof(struct txbd8) * tx_queue->tx_ring_size; + vaddr += sizeof(struct txbd8) * tx_queue->tx_ring_size; } -} -static int gfar_request_irq(struct gfar_private *priv) -{ - int err, i, j; + /* Start the rx descriptor ring where the tx ring leaves off */ + for (i = 0; i < priv->num_rx_queues; i++) { + rx_queue = priv->rx_queue[i]; + rx_queue->rx_bd_base = vaddr; + rx_queue->rx_bd_dma_base = addr; + rx_queue->ndev = ndev; + rx_queue->dev = dev; + addr += sizeof(struct rxbd8) * rx_queue->rx_ring_size; + vaddr += sizeof(struct rxbd8) * rx_queue->rx_ring_size; + } - for (i = 0; i < priv->num_grps; i++) { - err = register_grp_irqs(&priv->gfargrp[i]); - if (err) { - for (j = 0; j < i; j++) - free_grp_irqs(&priv->gfargrp[j]); - return err; - } + /* Setup the skbuff rings */ + for (i = 0; i < priv->num_tx_queues; i++) { + tx_queue = priv->tx_queue[i]; + tx_queue->tx_skbuff = + kmalloc_array(tx_queue->tx_ring_size, + sizeof(*tx_queue->tx_skbuff), + GFP_KERNEL); + if (!tx_queue->tx_skbuff) + goto cleanup; + + for (j = 0; j < tx_queue->tx_ring_size; j++) + tx_queue->tx_skbuff[j] = NULL; } + for (i = 0; i < priv->num_rx_queues; i++) { + rx_queue = priv->rx_queue[i]; + rx_queue->rx_buff = kcalloc(rx_queue->rx_ring_size, + sizeof(*rx_queue->rx_buff), + GFP_KERNEL); + if (!rx_queue->rx_buff) + goto cleanup; + } + + gfar_init_bds(ndev); + return 0; + +cleanup: + free_skb_resources(priv); + return -ENOMEM; } /* Bring the controller up and running */ @@ -2233,27 +1470,245 @@ int startup_gfar(struct net_device *ndev) return 0; } -/* Called when something needs to use the ethernet device - * Returns 0 for success. +static u32 gfar_get_flowctrl_cfg(struct gfar_private *priv) +{ + struct net_device *ndev = priv->ndev; + struct phy_device *phydev = ndev->phydev; + u32 val = 0; + + if (!phydev->duplex) + return val; + + if (!priv->pause_aneg_en) { + if (priv->tx_pause_en) + val |= MACCFG1_TX_FLOW; + if (priv->rx_pause_en) + val |= MACCFG1_RX_FLOW; + } else { + u16 lcl_adv, rmt_adv; + u8 flowctrl; + /* get link partner capabilities */ + rmt_adv = 0; + if (phydev->pause) + rmt_adv = LPA_PAUSE_CAP; + if (phydev->asym_pause) + rmt_adv |= LPA_PAUSE_ASYM; + + lcl_adv = linkmode_adv_to_lcl_adv_t(phydev->advertising); + flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); + if (flowctrl & FLOW_CTRL_TX) + val |= MACCFG1_TX_FLOW; + if (flowctrl & FLOW_CTRL_RX) + val |= MACCFG1_RX_FLOW; + } + + return val; +} + +static noinline void gfar_update_link_state(struct gfar_private *priv) +{ + struct gfar __iomem *regs = priv->gfargrp[0].regs; + struct net_device *ndev = priv->ndev; + struct phy_device *phydev = ndev->phydev; + struct gfar_priv_rx_q *rx_queue = NULL; + int i; + + if (unlikely(test_bit(GFAR_RESETTING, &priv->state))) + return; + + if (phydev->link) { + u32 tempval1 = gfar_read(®s->maccfg1); + u32 tempval = gfar_read(®s->maccfg2); + u32 ecntrl = gfar_read(®s->ecntrl); + u32 tx_flow_oldval = (tempval1 & MACCFG1_TX_FLOW); + + if (phydev->duplex != priv->oldduplex) { + if (!(phydev->duplex)) + tempval &= ~(MACCFG2_FULL_DUPLEX); + else + tempval |= MACCFG2_FULL_DUPLEX; + + priv->oldduplex = phydev->duplex; + } + + if (phydev->speed != priv->oldspeed) { + switch (phydev->speed) { + case 1000: + tempval = + ((tempval & ~(MACCFG2_IF)) | MACCFG2_GMII); + + ecntrl &= ~(ECNTRL_R100); + break; + case 100: + case 10: + tempval = + ((tempval & ~(MACCFG2_IF)) | MACCFG2_MII); + + /* Reduced mode distinguishes + * between 10 and 100 + */ + if (phydev->speed == SPEED_100) + ecntrl |= ECNTRL_R100; + else + ecntrl &= ~(ECNTRL_R100); + break; + default: + netif_warn(priv, link, priv->ndev, + "Ack! Speed (%d) is not 10/100/1000!\n", + phydev->speed); + break; + } + + priv->oldspeed = phydev->speed; + } + + tempval1 &= ~(MACCFG1_TX_FLOW | MACCFG1_RX_FLOW); + tempval1 |= gfar_get_flowctrl_cfg(priv); + + /* Turn last free buffer recording on */ + if ((tempval1 & MACCFG1_TX_FLOW) && !tx_flow_oldval) { + for (i = 0; i < priv->num_rx_queues; i++) { + u32 bdp_dma; + + rx_queue = priv->rx_queue[i]; + bdp_dma = gfar_rxbd_dma_lastfree(rx_queue); + gfar_write(rx_queue->rfbptr, bdp_dma); + } + + priv->tx_actual_en = 1; + } + + if (unlikely(!(tempval1 & MACCFG1_TX_FLOW) && tx_flow_oldval)) + priv->tx_actual_en = 0; + + gfar_write(®s->maccfg1, tempval1); + gfar_write(®s->maccfg2, tempval); + gfar_write(®s->ecntrl, ecntrl); + + if (!priv->oldlink) + priv->oldlink = 1; + + } else if (priv->oldlink) { + priv->oldlink = 0; + priv->oldspeed = 0; + priv->oldduplex = -1; + } + + if (netif_msg_link(priv)) + phy_print_status(phydev); +} + +/* Called every time the controller might need to be made + * aware of new link state. The PHY code conveys this + * information through variables in the phydev structure, and this + * function converts those variables into the appropriate + * register values, and can bring down the device if needed. */ -static int gfar_enet_open(struct net_device *dev) +static void adjust_link(struct net_device *dev) { struct gfar_private *priv = netdev_priv(dev); - int err; + struct phy_device *phydev = dev->phydev; - err = init_phy(dev); - if (err) - return err; + if (unlikely(phydev->link != priv->oldlink || + (phydev->link && (phydev->duplex != priv->oldduplex || + phydev->speed != priv->oldspeed)))) + gfar_update_link_state(priv); +} - err = gfar_request_irq(priv); - if (err) - return err; +/* Initialize TBI PHY interface for communicating with the + * SERDES lynx PHY on the chip. We communicate with this PHY + * through the MDIO bus on each controller, treating it as a + * "normal" PHY at the address found in the TBIPA register. We assume + * that the TBIPA register is valid. Either the MDIO bus code will set + * it to a value that doesn't conflict with other PHYs on the bus, or the + * value doesn't matter, as there are no other PHYs on the bus. + */ +static void gfar_configure_serdes(struct net_device *dev) +{ + struct gfar_private *priv = netdev_priv(dev); + struct phy_device *tbiphy; - err = startup_gfar(dev); - if (err) - return err; + if (!priv->tbi_node) { + dev_warn(&dev->dev, "error: SGMII mode requires that the " + "device tree specify a tbi-handle\n"); + return; + } - return err; + tbiphy = of_phy_find_device(priv->tbi_node); + if (!tbiphy) { + dev_err(&dev->dev, "error: Could not get TBI device\n"); + return; + } + + /* If the link is already up, we must already be ok, and don't need to + * configure and reset the TBI<->SerDes link. Maybe U-Boot configured + * everything for us? Resetting it takes the link down and requires + * several seconds for it to come back. + */ + if (phy_read(tbiphy, MII_BMSR) & BMSR_LSTATUS) { + put_device(&tbiphy->mdio.dev); + return; + } + + /* Single clk mode, mii mode off(for serdes communication) */ + phy_write(tbiphy, MII_TBICON, TBICON_CLK_SELECT); + + phy_write(tbiphy, MII_ADVERTISE, + ADVERTISE_1000XFULL | ADVERTISE_1000XPAUSE | + ADVERTISE_1000XPSE_ASYM); + + phy_write(tbiphy, MII_BMCR, + BMCR_ANENABLE | BMCR_ANRESTART | BMCR_FULLDPLX | + BMCR_SPEED1000); + + put_device(&tbiphy->mdio.dev); +} + +/* Initializes driver's PHY state, and attaches to the PHY. + * Returns 0 on success. + */ +static int init_phy(struct net_device *dev) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + struct gfar_private *priv = netdev_priv(dev); + phy_interface_t interface = priv->interface; + struct phy_device *phydev; + struct ethtool_eee edata; + + linkmode_set_bit_array(phy_10_100_features_array, + ARRAY_SIZE(phy_10_100_features_array), + mask); + linkmode_set_bit(ETHTOOL_LINK_MODE_Autoneg_BIT, mask); + linkmode_set_bit(ETHTOOL_LINK_MODE_MII_BIT, mask); + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_GIGABIT) + linkmode_set_bit(ETHTOOL_LINK_MODE_1000baseT_Full_BIT, mask); + + priv->oldlink = 0; + priv->oldspeed = 0; + priv->oldduplex = -1; + + phydev = of_phy_connect(dev, priv->phy_node, &adjust_link, 0, + interface); + if (!phydev) { + dev_err(&dev->dev, "could not attach to PHY\n"); + return -ENODEV; + } + + if (interface == PHY_INTERFACE_MODE_SGMII) + gfar_configure_serdes(dev); + + /* Remove any features not supported by the controller */ + linkmode_and(phydev->supported, phydev->supported, mask); + linkmode_copy(phydev->advertising, phydev->supported); + + /* Add support for flow control */ + phy_support_asym_pause(phydev); + + /* disable EEE autoneg, EEE not supported by eTSEC */ + memset(&edata, 0, sizeof(struct ethtool_eee)); + phy_ethtool_set_eee(phydev, &edata); + + return 0; } static inline struct txfcb *gfar_add_fcb(struct sk_buff *skb) @@ -2584,22 +2039,6 @@ dma_map_err: return NETDEV_TX_OK; } -/* Stops the kernel queue, and halts the controller */ -static int gfar_close(struct net_device *dev) -{ - struct gfar_private *priv = netdev_priv(dev); - - cancel_work_sync(&priv->reset_task); - stop_gfar(dev); - - /* Disconnect from the PHY */ - phy_disconnect(dev->phydev); - - gfar_free_irq(priv); - - return 0; -} - /* Changes the mac address if the controller is not running. */ static int gfar_set_mac_address(struct net_device *dev) { @@ -2661,6 +2100,85 @@ static void gfar_timeout(struct net_device *dev) schedule_work(&priv->reset_task); } +static int gfar_hwtstamp_set(struct net_device *netdev, struct ifreq *ifr) +{ + struct hwtstamp_config config; + struct gfar_private *priv = netdev_priv(netdev); + + if (copy_from_user(&config, ifr->ifr_data, sizeof(config))) + return -EFAULT; + + /* reserved for future extensions */ + if (config.flags) + return -EINVAL; + + switch (config.tx_type) { + case HWTSTAMP_TX_OFF: + priv->hwts_tx_en = 0; + break; + case HWTSTAMP_TX_ON: + if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)) + return -ERANGE; + priv->hwts_tx_en = 1; + break; + default: + return -ERANGE; + } + + switch (config.rx_filter) { + case HWTSTAMP_FILTER_NONE: + if (priv->hwts_rx_en) { + priv->hwts_rx_en = 0; + reset_gfar(netdev); + } + break; + default: + if (!(priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER)) + return -ERANGE; + if (!priv->hwts_rx_en) { + priv->hwts_rx_en = 1; + reset_gfar(netdev); + } + config.rx_filter = HWTSTAMP_FILTER_ALL; + break; + } + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +static int gfar_hwtstamp_get(struct net_device *netdev, struct ifreq *ifr) +{ + struct hwtstamp_config config; + struct gfar_private *priv = netdev_priv(netdev); + + config.flags = 0; + config.tx_type = priv->hwts_tx_en ? HWTSTAMP_TX_ON : HWTSTAMP_TX_OFF; + config.rx_filter = (priv->hwts_rx_en ? + HWTSTAMP_FILTER_ALL : HWTSTAMP_FILTER_NONE); + + return copy_to_user(ifr->ifr_data, &config, sizeof(config)) ? + -EFAULT : 0; +} + +static int gfar_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) +{ + struct phy_device *phydev = dev->phydev; + + if (!netif_running(dev)) + return -EINVAL; + + if (cmd == SIOCSHWTSTAMP) + return gfar_hwtstamp_set(dev, rq); + if (cmd == SIOCGHWTSTAMP) + return gfar_hwtstamp_get(dev, rq); + + if (!phydev) + return -ENODEV; + + return phy_mii_ioctl(phydev, rq, cmd); +} + /* Interrupt Handler for Transmit complete */ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) { @@ -2768,77 +2286,6 @@ static void gfar_clean_tx_ring(struct gfar_priv_tx_q *tx_queue) netdev_tx_completed_queue(txq, howmany, bytes_sent); } -static bool gfar_new_page(struct gfar_priv_rx_q *rxq, struct gfar_rx_buff *rxb) -{ - struct page *page; - dma_addr_t addr; - - page = dev_alloc_page(); - if (unlikely(!page)) - return false; - - addr = dma_map_page(rxq->dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE); - if (unlikely(dma_mapping_error(rxq->dev, addr))) { - __free_page(page); - - return false; - } - - rxb->dma = addr; - rxb->page = page; - rxb->page_offset = 0; - - return true; -} - -static void gfar_rx_alloc_err(struct gfar_priv_rx_q *rx_queue) -{ - struct gfar_private *priv = netdev_priv(rx_queue->ndev); - struct gfar_extra_stats *estats = &priv->extra_stats; - - netdev_err(rx_queue->ndev, "Can't alloc RX buffers\n"); - atomic64_inc(&estats->rx_alloc_err); -} - -static void gfar_alloc_rx_buffs(struct gfar_priv_rx_q *rx_queue, - int alloc_cnt) -{ - struct rxbd8 *bdp; - struct gfar_rx_buff *rxb; - int i; - - i = rx_queue->next_to_use; - bdp = &rx_queue->rx_bd_base[i]; - rxb = &rx_queue->rx_buff[i]; - - while (alloc_cnt--) { - /* try reuse page */ - if (unlikely(!rxb->page)) { - if (unlikely(!gfar_new_page(rx_queue, rxb))) { - gfar_rx_alloc_err(rx_queue); - break; - } - } - - /* Setup the new RxBD */ - gfar_init_rxbdp(rx_queue, bdp, - rxb->dma + rxb->page_offset + RXBUF_ALIGNMENT); - - /* Update to the next pointer */ - bdp++; - rxb++; - - if (unlikely(++i == rx_queue->rx_ring_size)) { - i = 0; - bdp = rx_queue->rx_bd_base; - rxb = rx_queue->rx_buff; - } - } - - rx_queue->next_to_use = i; - rx_queue->next_to_alloc = i; -} - static void count_errors(u32 lstatus, struct net_device *ndev) { struct gfar_private *priv = netdev_priv(ndev); @@ -2876,7 +2323,7 @@ static void count_errors(u32 lstatus, struct net_device *ndev) } } -irqreturn_t gfar_receive(int irq, void *grp_id) +static irqreturn_t gfar_receive(int irq, void *grp_id) { struct gfar_priv_grp *grp = (struct gfar_priv_grp *)grp_id; unsigned long flags; @@ -3078,7 +2525,8 @@ static void gfar_process_frame(struct net_device *ndev, struct sk_buff *skb) * until the budget/quota has been reached. Returns the number * of frames handled */ -int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, int rx_work_limit) +static int gfar_clean_rx_ring(struct gfar_priv_rx_q *rx_queue, + int rx_work_limit) { struct net_device *ndev = rx_queue->ndev; struct gfar_private *priv = netdev_priv(ndev); @@ -3328,6 +2776,98 @@ static int gfar_poll_tx(struct napi_struct *napi, int budget) return 0; } +/* GFAR error interrupt handler */ +static irqreturn_t gfar_error(int irq, void *grp_id) +{ + struct gfar_priv_grp *gfargrp = grp_id; + struct gfar __iomem *regs = gfargrp->regs; + struct gfar_private *priv= gfargrp->priv; + struct net_device *dev = priv->ndev; + + /* Save ievent for future reference */ + u32 events = gfar_read(®s->ievent); + + /* Clear IEVENT */ + gfar_write(®s->ievent, events & IEVENT_ERR_MASK); + + /* Magic Packet is not an error. */ + if ((priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) && + (events & IEVENT_MAG)) + events &= ~IEVENT_MAG; + + /* Hmm... */ + if (netif_msg_rx_err(priv) || netif_msg_tx_err(priv)) + netdev_dbg(dev, + "error interrupt (ievent=0x%08x imask=0x%08x)\n", + events, gfar_read(®s->imask)); + + /* Update the error counters */ + if (events & IEVENT_TXE) { + dev->stats.tx_errors++; + + if (events & IEVENT_LC) + dev->stats.tx_window_errors++; + if (events & IEVENT_CRL) + dev->stats.tx_aborted_errors++; + if (events & IEVENT_XFUN) { + netif_dbg(priv, tx_err, dev, + "TX FIFO underrun, packet dropped\n"); + dev->stats.tx_dropped++; + atomic64_inc(&priv->extra_stats.tx_underrun); + + schedule_work(&priv->reset_task); + } + netif_dbg(priv, tx_err, dev, "Transmit Error\n"); + } + if (events & IEVENT_BSY) { + dev->stats.rx_over_errors++; + atomic64_inc(&priv->extra_stats.rx_bsy); + + netif_dbg(priv, rx_err, dev, "busy error (rstat: %x)\n", + gfar_read(®s->rstat)); + } + if (events & IEVENT_BABR) { + dev->stats.rx_errors++; + atomic64_inc(&priv->extra_stats.rx_babr); + + netif_dbg(priv, rx_err, dev, "babbling RX error\n"); + } + if (events & IEVENT_EBERR) { + atomic64_inc(&priv->extra_stats.eberr); + netif_dbg(priv, rx_err, dev, "bus error\n"); + } + if (events & IEVENT_RXC) + netif_dbg(priv, rx_status, dev, "control frame\n"); + + if (events & IEVENT_BABT) { + atomic64_inc(&priv->extra_stats.tx_babt); + netif_dbg(priv, tx_err, dev, "babbling TX error\n"); + } + return IRQ_HANDLED; +} + +/* The interrupt handler for devices with one interrupt */ +static irqreturn_t gfar_interrupt(int irq, void *grp_id) +{ + struct gfar_priv_grp *gfargrp = grp_id; + + /* Save ievent for future reference */ + u32 events = gfar_read(&gfargrp->regs->ievent); + + /* Check for reception */ + if (events & IEVENT_RX_MASK) + gfar_receive(irq, grp_id); + + /* Check for transmit completion */ + if (events & IEVENT_TX_MASK) + gfar_transmit(irq, grp_id); + + /* Check for errors */ + if (events & IEVENT_ERR_MASK) + gfar_error(irq, grp_id); + + return IRQ_HANDLED; +} #ifdef CONFIG_NET_POLL_CONTROLLER /* Polling 'interrupt' - used by things like netconsole to send skbs @@ -3364,44 +2904,154 @@ static void gfar_netpoll(struct net_device *dev) } #endif -/* The interrupt handler for devices with one interrupt */ -static irqreturn_t gfar_interrupt(int irq, void *grp_id) +static void free_grp_irqs(struct gfar_priv_grp *grp) { - struct gfar_priv_grp *gfargrp = grp_id; + free_irq(gfar_irq(grp, TX)->irq, grp); + free_irq(gfar_irq(grp, RX)->irq, grp); + free_irq(gfar_irq(grp, ER)->irq, grp); +} - /* Save ievent for future reference */ - u32 events = gfar_read(&gfargrp->regs->ievent); +static int register_grp_irqs(struct gfar_priv_grp *grp) +{ + struct gfar_private *priv = grp->priv; + struct net_device *dev = priv->ndev; + int err; - /* Check for reception */ - if (events & IEVENT_RX_MASK) - gfar_receive(irq, grp_id); + /* If the device has multiple interrupts, register for + * them. Otherwise, only register for the one + */ + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { + /* Install our interrupt handlers for Error, + * Transmit, and Receive + */ + err = request_irq(gfar_irq(grp, ER)->irq, gfar_error, 0, + gfar_irq(grp, ER)->name, grp); + if (err < 0) { + netif_err(priv, intr, dev, "Can't get IRQ %d\n", + gfar_irq(grp, ER)->irq); - /* Check for transmit completion */ - if (events & IEVENT_TX_MASK) - gfar_transmit(irq, grp_id); + goto err_irq_fail; + } + enable_irq_wake(gfar_irq(grp, ER)->irq); - /* Check for errors */ - if (events & IEVENT_ERR_MASK) - gfar_error(irq, grp_id); + err = request_irq(gfar_irq(grp, TX)->irq, gfar_transmit, 0, + gfar_irq(grp, TX)->name, grp); + if (err < 0) { + netif_err(priv, intr, dev, "Can't get IRQ %d\n", + gfar_irq(grp, TX)->irq); + goto tx_irq_fail; + } + err = request_irq(gfar_irq(grp, RX)->irq, gfar_receive, 0, + gfar_irq(grp, RX)->name, grp); + if (err < 0) { + netif_err(priv, intr, dev, "Can't get IRQ %d\n", + gfar_irq(grp, RX)->irq); + goto rx_irq_fail; + } + enable_irq_wake(gfar_irq(grp, RX)->irq); + + } else { + err = request_irq(gfar_irq(grp, TX)->irq, gfar_interrupt, 0, + gfar_irq(grp, TX)->name, grp); + if (err < 0) { + netif_err(priv, intr, dev, "Can't get IRQ %d\n", + gfar_irq(grp, TX)->irq); + goto err_irq_fail; + } + enable_irq_wake(gfar_irq(grp, TX)->irq); + } + + return 0; + +rx_irq_fail: + free_irq(gfar_irq(grp, TX)->irq, grp); +tx_irq_fail: + free_irq(gfar_irq(grp, ER)->irq, grp); +err_irq_fail: + return err; - return IRQ_HANDLED; } -/* Called every time the controller might need to be made - * aware of new link state. The PHY code conveys this - * information through variables in the phydev structure, and this - * function converts those variables into the appropriate - * register values, and can bring down the device if needed. +static void gfar_free_irq(struct gfar_private *priv) +{ + int i; + + /* Free the IRQs */ + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { + for (i = 0; i < priv->num_grps; i++) + free_grp_irqs(&priv->gfargrp[i]); + } else { + for (i = 0; i < priv->num_grps; i++) + free_irq(gfar_irq(&priv->gfargrp[i], TX)->irq, + &priv->gfargrp[i]); + } +} + +static int gfar_request_irq(struct gfar_private *priv) +{ + int err, i, j; + + for (i = 0; i < priv->num_grps; i++) { + err = register_grp_irqs(&priv->gfargrp[i]); + if (err) { + for (j = 0; j < i; j++) + free_grp_irqs(&priv->gfargrp[j]); + return err; + } + } + + return 0; +} + +/* Called when something needs to use the ethernet device + * Returns 0 for success. */ -static void adjust_link(struct net_device *dev) +static int gfar_enet_open(struct net_device *dev) { struct gfar_private *priv = netdev_priv(dev); - struct phy_device *phydev = dev->phydev; + int err; - if (unlikely(phydev->link != priv->oldlink || - (phydev->link && (phydev->duplex != priv->oldduplex || - phydev->speed != priv->oldspeed)))) - gfar_update_link_state(priv); + err = init_phy(dev); + if (err) + return err; + + err = gfar_request_irq(priv); + if (err) + return err; + + err = startup_gfar(dev); + if (err) + return err; + + return err; +} + +/* Stops the kernel queue, and halts the controller */ +static int gfar_close(struct net_device *dev) +{ + struct gfar_private *priv = netdev_priv(dev); + + cancel_work_sync(&priv->reset_task); + stop_gfar(dev); + + /* Disconnect from the PHY */ + phy_disconnect(dev->phydev); + + gfar_free_irq(priv); + + return 0; +} + +/* Clears each of the exact match registers to zero, so they + * don't interfere with normal reception + */ +static void gfar_clear_exact_match(struct net_device *dev) +{ + int idx; + static const u8 zero_arr[ETH_ALEN] = {0, 0, 0, 0, 0, 0}; + + for (idx = 1; idx < GFAR_EM_NUM + 1; idx++) + gfar_set_mac_for_addr(dev, idx, zero_arr); } /* Update the hash table based on the current list of multicast @@ -3495,274 +3145,582 @@ static void gfar_set_multi(struct net_device *dev) } } - -/* Clears each of the exact match registers to zero, so they - * don't interfere with normal reception - */ -static void gfar_clear_exact_match(struct net_device *dev) +void gfar_mac_reset(struct gfar_private *priv) { - int idx; - static const u8 zero_arr[ETH_ALEN] = {0, 0, 0, 0, 0, 0}; + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 tempval; - for (idx = 1; idx < GFAR_EM_NUM + 1; idx++) - gfar_set_mac_for_addr(dev, idx, zero_arr); -} + /* Reset MAC layer */ + gfar_write(®s->maccfg1, MACCFG1_SOFT_RESET); -/* Set the appropriate hash bit for the given addr */ -/* The algorithm works like so: - * 1) Take the Destination Address (ie the multicast address), and - * do a CRC on it (little endian), and reverse the bits of the - * result. - * 2) Use the 8 most significant bits as a hash into a 256-entry - * table. The table is controlled through 8 32-bit registers: - * gaddr0-7. gaddr0's MSB is entry 0, and gaddr7's LSB is - * gaddr7. This means that the 3 most significant bits in the - * hash index which gaddr register to use, and the 5 other bits - * indicate which bit (assuming an IBM numbering scheme, which - * for PowerPC (tm) is usually the case) in the register holds - * the entry. - */ -static void gfar_set_hash_for_addr(struct net_device *dev, u8 *addr) -{ - u32 tempval; - struct gfar_private *priv = netdev_priv(dev); - u32 result = ether_crc(ETH_ALEN, addr); - int width = priv->hash_width; - u8 whichbit = (result >> (32 - width)) & 0x1f; - u8 whichreg = result >> (32 - width + 5); - u32 value = (1 << (31-whichbit)); + /* We need to delay at least 3 TX clocks */ + udelay(3); - tempval = gfar_read(priv->hash_regs[whichreg]); - tempval |= value; - gfar_write(priv->hash_regs[whichreg], tempval); -} + /* the soft reset bit is not self-resetting, so we need to + * clear it before resuming normal operation + */ + gfar_write(®s->maccfg1, 0); + udelay(3); -/* There are multiple MAC Address register pairs on some controllers - * This function sets the numth pair to a given address - */ -static void gfar_set_mac_for_addr(struct net_device *dev, int num, - const u8 *addr) + gfar_rx_offload_en(priv); + + /* Initialize the max receive frame/buffer lengths */ + gfar_write(®s->maxfrm, GFAR_JUMBO_FRAME_SIZE); + gfar_write(®s->mrblr, GFAR_RXB_SIZE); + + /* Initialize the Minimum Frame Length Register */ + gfar_write(®s->minflr, MINFLR_INIT_SETTINGS); + + /* Initialize MACCFG2. */ + tempval = MACCFG2_INIT_SETTINGS; + + /* eTSEC74 erratum: Rx frames of length MAXFRM or MAXFRM-1 + * are marked as truncated. Avoid this by MACCFG2[Huge Frame]=1, + * and by checking RxBD[LG] and discarding larger than MAXFRM. + */ + if (gfar_has_errata(priv, GFAR_ERRATA_74)) + tempval |= MACCFG2_HUGEFRAME | MACCFG2_LENGTHCHECK; + + gfar_write(®s->maccfg2, tempval); + + /* Clear mac addr hash registers */ + gfar_write(®s->igaddr0, 0); + gfar_write(®s->igaddr1, 0); + gfar_write(®s->igaddr2, 0); + gfar_write(®s->igaddr3, 0); + gfar_write(®s->igaddr4, 0); + gfar_write(®s->igaddr5, 0); + gfar_write(®s->igaddr6, 0); + gfar_write(®s->igaddr7, 0); + + gfar_write(®s->gaddr0, 0); + gfar_write(®s->gaddr1, 0); + gfar_write(®s->gaddr2, 0); + gfar_write(®s->gaddr3, 0); + gfar_write(®s->gaddr4, 0); + gfar_write(®s->gaddr5, 0); + gfar_write(®s->gaddr6, 0); + gfar_write(®s->gaddr7, 0); + + if (priv->extended_hash) + gfar_clear_exact_match(priv->ndev); + + gfar_mac_rx_config(priv); + + gfar_mac_tx_config(priv); + + gfar_set_mac_address(priv->ndev); + + gfar_set_multi(priv->ndev); + + /* clear ievent and imask before configuring coalescing */ + gfar_ints_disable(priv); + + /* Configure the coalescing support */ + gfar_configure_coalescing_all(priv); +} + +static void gfar_hw_init(struct gfar_private *priv) { - struct gfar_private *priv = netdev_priv(dev); struct gfar __iomem *regs = priv->gfargrp[0].regs; - u32 tempval; - u32 __iomem *macptr = ®s->macstnaddr1; + u32 attrs; - macptr += num*2; + /* Stop the DMA engine now, in case it was running before + * (The firmware could have used it, and left it running). + */ + gfar_halt(priv); - /* For a station address of 0x12345678ABCD in transmission - * order (BE), MACnADDR1 is set to 0xCDAB7856 and - * MACnADDR2 is set to 0x34120000. + gfar_mac_reset(priv); + + /* Zero out the rmon mib registers if it has them */ + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_RMON) { + memset_io(&(regs->rmon), 0, sizeof(struct rmon_mib)); + + /* Mask off the CAM interrupts */ + gfar_write(®s->rmon.cam1, 0xffffffff); + gfar_write(®s->rmon.cam2, 0xffffffff); + } + + /* Initialize ECNTRL */ + gfar_write(®s->ecntrl, ECNTRL_INIT_SETTINGS); + + /* Set the extraction length and index */ + attrs = ATTRELI_EL(priv->rx_stash_size) | + ATTRELI_EI(priv->rx_stash_index); + + gfar_write(®s->attreli, attrs); + + /* Start with defaults, and add stashing + * depending on driver parameters */ - tempval = (addr[5] << 24) | (addr[4] << 16) | - (addr[3] << 8) | addr[2]; + attrs = ATTR_INIT_SETTINGS; - gfar_write(macptr, tempval); + if (priv->bd_stash_en) + attrs |= ATTR_BDSTASH; - tempval = (addr[1] << 24) | (addr[0] << 16); + if (priv->rx_stash_size != 0) + attrs |= ATTR_BUFSTASH; - gfar_write(macptr+1, tempval); + gfar_write(®s->attr, attrs); + + /* FIFO configs */ + gfar_write(®s->fifo_tx_thr, DEFAULT_FIFO_TX_THR); + gfar_write(®s->fifo_tx_starve, DEFAULT_FIFO_TX_STARVE); + gfar_write(®s->fifo_tx_starve_shutoff, DEFAULT_FIFO_TX_STARVE_OFF); + + /* Program the interrupt steering regs, only for MG devices */ + if (priv->num_grps > 1) + gfar_write_isrg(priv); } -/* GFAR error interrupt handler */ -static irqreturn_t gfar_error(int irq, void *grp_id) +static const struct net_device_ops gfar_netdev_ops = { + .ndo_open = gfar_enet_open, + .ndo_start_xmit = gfar_start_xmit, + .ndo_stop = gfar_close, + .ndo_change_mtu = gfar_change_mtu, + .ndo_set_features = gfar_set_features, + .ndo_set_rx_mode = gfar_set_multi, + .ndo_tx_timeout = gfar_timeout, + .ndo_do_ioctl = gfar_ioctl, + .ndo_get_stats = gfar_get_stats, + .ndo_change_carrier = fixed_phy_change_carrier, + .ndo_set_mac_address = gfar_set_mac_addr, + .ndo_validate_addr = eth_validate_addr, +#ifdef CONFIG_NET_POLL_CONTROLLER + .ndo_poll_controller = gfar_netpoll, +#endif +}; + +/* Set up the ethernet device structure, private data, + * and anything else we need before we start + */ +static int gfar_probe(struct platform_device *ofdev) { - struct gfar_priv_grp *gfargrp = grp_id; - struct gfar __iomem *regs = gfargrp->regs; - struct gfar_private *priv= gfargrp->priv; - struct net_device *dev = priv->ndev; + struct device_node *np = ofdev->dev.of_node; + struct net_device *dev = NULL; + struct gfar_private *priv = NULL; + int err = 0, i; - /* Save ievent for future reference */ - u32 events = gfar_read(®s->ievent); + err = gfar_of_init(ofdev, &dev); - /* Clear IEVENT */ - gfar_write(®s->ievent, events & IEVENT_ERR_MASK); + if (err) + return err; - /* Magic Packet is not an error. */ - if ((priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) && - (events & IEVENT_MAG)) - events &= ~IEVENT_MAG; + priv = netdev_priv(dev); + priv->ndev = dev; + priv->ofdev = ofdev; + priv->dev = &ofdev->dev; + SET_NETDEV_DEV(dev, &ofdev->dev); - /* Hmm... */ - if (netif_msg_rx_err(priv) || netif_msg_tx_err(priv)) - netdev_dbg(dev, - "error interrupt (ievent=0x%08x imask=0x%08x)\n", - events, gfar_read(®s->imask)); + INIT_WORK(&priv->reset_task, gfar_reset_task); - /* Update the error counters */ - if (events & IEVENT_TXE) { - dev->stats.tx_errors++; + platform_set_drvdata(ofdev, priv); - if (events & IEVENT_LC) - dev->stats.tx_window_errors++; - if (events & IEVENT_CRL) - dev->stats.tx_aborted_errors++; - if (events & IEVENT_XFUN) { - netif_dbg(priv, tx_err, dev, - "TX FIFO underrun, packet dropped\n"); - dev->stats.tx_dropped++; - atomic64_inc(&priv->extra_stats.tx_underrun); + gfar_detect_errata(priv); - schedule_work(&priv->reset_task); + /* Set the dev->base_addr to the gfar reg region */ + dev->base_addr = (unsigned long) priv->gfargrp[0].regs; + + /* Fill in the dev structure */ + dev->watchdog_timeo = TX_TIMEOUT; + /* MTU range: 50 - 9586 */ + dev->mtu = 1500; + dev->min_mtu = 50; + dev->max_mtu = GFAR_JUMBO_FRAME_SIZE - ETH_HLEN; + dev->netdev_ops = &gfar_netdev_ops; + dev->ethtool_ops = &gfar_ethtool_ops; + + /* Register for napi ...We are registering NAPI for each grp */ + for (i = 0; i < priv->num_grps; i++) { + if (priv->poll_mode == GFAR_SQ_POLLING) { + netif_napi_add(dev, &priv->gfargrp[i].napi_rx, + gfar_poll_rx_sq, GFAR_DEV_WEIGHT); + netif_tx_napi_add(dev, &priv->gfargrp[i].napi_tx, + gfar_poll_tx_sq, 2); + } else { + netif_napi_add(dev, &priv->gfargrp[i].napi_rx, + gfar_poll_rx, GFAR_DEV_WEIGHT); + netif_tx_napi_add(dev, &priv->gfargrp[i].napi_tx, + gfar_poll_tx, 2); } - netif_dbg(priv, tx_err, dev, "Transmit Error\n"); } - if (events & IEVENT_BSY) { - dev->stats.rx_over_errors++; - atomic64_inc(&priv->extra_stats.rx_bsy); - netif_dbg(priv, rx_err, dev, "busy error (rstat: %x)\n", - gfar_read(®s->rstat)); + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_CSUM) { + dev->hw_features = NETIF_F_IP_CSUM | NETIF_F_SG | + NETIF_F_RXCSUM; + dev->features |= NETIF_F_IP_CSUM | NETIF_F_SG | + NETIF_F_RXCSUM | NETIF_F_HIGHDMA; } - if (events & IEVENT_BABR) { - dev->stats.rx_errors++; - atomic64_inc(&priv->extra_stats.rx_babr); - netif_dbg(priv, rx_err, dev, "babbling RX error\n"); + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_VLAN) { + dev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX; + dev->features |= NETIF_F_HW_VLAN_CTAG_RX; } - if (events & IEVENT_EBERR) { - atomic64_inc(&priv->extra_stats.eberr); - netif_dbg(priv, rx_err, dev, "bus error\n"); + + dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; + + gfar_init_addr_hash_table(priv); + + /* Insert receive time stamps into padding alignment bytes, and + * plus 2 bytes padding to ensure the cpu alignment. + */ + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) + priv->padding = 8 + DEFAULT_PADDING; + + if (dev->features & NETIF_F_IP_CSUM || + priv->device_flags & FSL_GIANFAR_DEV_HAS_TIMER) + dev->needed_headroom = GMAC_FCB_LEN; + + /* Initializing some of the rx/tx queue level parameters */ + for (i = 0; i < priv->num_tx_queues; i++) { + priv->tx_queue[i]->tx_ring_size = DEFAULT_TX_RING_SIZE; + priv->tx_queue[i]->num_txbdfree = DEFAULT_TX_RING_SIZE; + priv->tx_queue[i]->txcoalescing = DEFAULT_TX_COALESCE; + priv->tx_queue[i]->txic = DEFAULT_TXIC; } - if (events & IEVENT_RXC) - netif_dbg(priv, rx_status, dev, "control frame\n"); - if (events & IEVENT_BABT) { - atomic64_inc(&priv->extra_stats.tx_babt); - netif_dbg(priv, tx_err, dev, "babbling TX error\n"); + for (i = 0; i < priv->num_rx_queues; i++) { + priv->rx_queue[i]->rx_ring_size = DEFAULT_RX_RING_SIZE; + priv->rx_queue[i]->rxcoalescing = DEFAULT_RX_COALESCE; + priv->rx_queue[i]->rxic = DEFAULT_RXIC; } - return IRQ_HANDLED; + + /* Always enable rx filer if available */ + priv->rx_filer_enable = + (priv->device_flags & FSL_GIANFAR_DEV_HAS_RX_FILER) ? 1 : 0; + /* Enable most messages by default */ + priv->msg_enable = (NETIF_MSG_IFUP << 1 ) - 1; + /* use pritority h/w tx queue scheduling for single queue devices */ + if (priv->num_tx_queues == 1) + priv->prio_sched_en = 1; + + set_bit(GFAR_DOWN, &priv->state); + + gfar_hw_init(priv); + + /* Carrier starts down, phylib will bring it up */ + netif_carrier_off(dev); + + err = register_netdev(dev); + + if (err) { + pr_err("%s: Cannot register net device, aborting\n", dev->name); + goto register_fail; + } + + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MAGIC_PACKET) + priv->wol_supported |= GFAR_WOL_MAGIC; + + if ((priv->device_flags & FSL_GIANFAR_DEV_HAS_WAKE_ON_FILER) && + priv->rx_filer_enable) + priv->wol_supported |= GFAR_WOL_FILER_UCAST; + + device_set_wakeup_capable(&ofdev->dev, priv->wol_supported); + + /* fill out IRQ number and name fields */ + for (i = 0; i < priv->num_grps; i++) { + struct gfar_priv_grp *grp = &priv->gfargrp[i]; + if (priv->device_flags & FSL_GIANFAR_DEV_HAS_MULTI_INTR) { + sprintf(gfar_irq(grp, TX)->name, "%s%s%c%s", + dev->name, "_g", '0' + i, "_tx"); + sprintf(gfar_irq(grp, RX)->name, "%s%s%c%s", + dev->name, "_g", '0' + i, "_rx"); + sprintf(gfar_irq(grp, ER)->name, "%s%s%c%s", + dev->name, "_g", '0' + i, "_er"); + } else + strcpy(gfar_irq(grp, TX)->name, dev->name); + } + + /* Initialize the filer table */ + gfar_init_filer_table(priv); + + /* Print out the device info */ + netdev_info(dev, "mac: %pM\n", dev->dev_addr); + + /* Even more device info helps when determining which kernel + * provided which set of benchmarks. + */ + netdev_info(dev, "Running with NAPI enabled\n"); + for (i = 0; i < priv->num_rx_queues; i++) + netdev_info(dev, "RX BD ring size for Q[%d]: %d\n", + i, priv->rx_queue[i]->rx_ring_size); + for (i = 0; i < priv->num_tx_queues; i++) + netdev_info(dev, "TX BD ring size for Q[%d]: %d\n", + i, priv->tx_queue[i]->tx_ring_size); + + return 0; + +register_fail: + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + unmap_group_regs(priv); + gfar_free_rx_queues(priv); + gfar_free_tx_queues(priv); + of_node_put(priv->phy_node); + of_node_put(priv->tbi_node); + free_gfar_dev(priv); + return err; } -static u32 gfar_get_flowctrl_cfg(struct gfar_private *priv) +static int gfar_remove(struct platform_device *ofdev) { - struct net_device *ndev = priv->ndev; - struct phy_device *phydev = ndev->phydev; - u32 val = 0; + struct gfar_private *priv = platform_get_drvdata(ofdev); + struct device_node *np = ofdev->dev.of_node; - if (!phydev->duplex) - return val; + of_node_put(priv->phy_node); + of_node_put(priv->tbi_node); - if (!priv->pause_aneg_en) { - if (priv->tx_pause_en) - val |= MACCFG1_TX_FLOW; - if (priv->rx_pause_en) - val |= MACCFG1_RX_FLOW; - } else { - u16 lcl_adv, rmt_adv; - u8 flowctrl; - /* get link partner capabilities */ - rmt_adv = 0; - if (phydev->pause) - rmt_adv = LPA_PAUSE_CAP; - if (phydev->asym_pause) - rmt_adv |= LPA_PAUSE_ASYM; + unregister_netdev(priv->ndev); - lcl_adv = linkmode_adv_to_lcl_adv_t(phydev->advertising); - flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); - if (flowctrl & FLOW_CTRL_TX) - val |= MACCFG1_TX_FLOW; - if (flowctrl & FLOW_CTRL_RX) - val |= MACCFG1_RX_FLOW; + if (of_phy_is_fixed_link(np)) + of_phy_deregister_fixed_link(np); + + unmap_group_regs(priv); + gfar_free_rx_queues(priv); + gfar_free_tx_queues(priv); + free_gfar_dev(priv); + + return 0; +} + +#ifdef CONFIG_PM + +static void __gfar_filer_disable(struct gfar_private *priv) +{ + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 temp; + + temp = gfar_read(®s->rctrl); + temp &= ~(RCTRL_FILREN | RCTRL_PRSDEP_INIT); + gfar_write(®s->rctrl, temp); +} + +static void __gfar_filer_enable(struct gfar_private *priv) +{ + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 temp; + + temp = gfar_read(®s->rctrl); + temp |= RCTRL_FILREN | RCTRL_PRSDEP_INIT; + gfar_write(®s->rctrl, temp); +} + +/* Filer rules implementing wol capabilities */ +static void gfar_filer_config_wol(struct gfar_private *priv) +{ + unsigned int i; + u32 rqfcr; + + __gfar_filer_disable(priv); + + /* clear the filer table, reject any packet by default */ + rqfcr = RQFCR_RJE | RQFCR_CMP_MATCH; + for (i = 0; i <= MAX_FILER_IDX; i++) + gfar_write_filer(priv, i, rqfcr, 0); + + i = 0; + if (priv->wol_opts & GFAR_WOL_FILER_UCAST) { + /* unicast packet, accept it */ + struct net_device *ndev = priv->ndev; + /* get the default rx queue index */ + u8 qindex = (u8)priv->gfargrp[0].rx_queue->qindex; + u32 dest_mac_addr = (ndev->dev_addr[0] << 16) | + (ndev->dev_addr[1] << 8) | + ndev->dev_addr[2]; + + rqfcr = (qindex << 10) | RQFCR_AND | + RQFCR_CMP_EXACT | RQFCR_PID_DAH; + + gfar_write_filer(priv, i++, rqfcr, dest_mac_addr); + + dest_mac_addr = (ndev->dev_addr[3] << 16) | + (ndev->dev_addr[4] << 8) | + ndev->dev_addr[5]; + rqfcr = (qindex << 10) | RQFCR_GPI | + RQFCR_CMP_EXACT | RQFCR_PID_DAL; + gfar_write_filer(priv, i++, rqfcr, dest_mac_addr); } - return val; + __gfar_filer_enable(priv); } -static noinline void gfar_update_link_state(struct gfar_private *priv) +static void gfar_filer_restore_table(struct gfar_private *priv) +{ + u32 rqfcr, rqfpr; + unsigned int i; + + __gfar_filer_disable(priv); + + for (i = 0; i <= MAX_FILER_IDX; i++) { + rqfcr = priv->ftp_rqfcr[i]; + rqfpr = priv->ftp_rqfpr[i]; + gfar_write_filer(priv, i, rqfcr, rqfpr); + } + + __gfar_filer_enable(priv); +} + +/* gfar_start() for Rx only and with the FGPI filer interrupt enabled */ +static void gfar_start_wol_filer(struct gfar_private *priv) { struct gfar __iomem *regs = priv->gfargrp[0].regs; - struct net_device *ndev = priv->ndev; - struct phy_device *phydev = ndev->phydev; - struct gfar_priv_rx_q *rx_queue = NULL; - int i; + u32 tempval; + int i = 0; - if (unlikely(test_bit(GFAR_RESETTING, &priv->state))) - return; + /* Enable Rx hw queues */ + gfar_write(®s->rqueue, priv->rqueue); - if (phydev->link) { - u32 tempval1 = gfar_read(®s->maccfg1); - u32 tempval = gfar_read(®s->maccfg2); - u32 ecntrl = gfar_read(®s->ecntrl); - u32 tx_flow_oldval = (tempval1 & MACCFG1_TX_FLOW); + /* Initialize DMACTRL to have WWR and WOP */ + tempval = gfar_read(®s->dmactrl); + tempval |= DMACTRL_INIT_SETTINGS; + gfar_write(®s->dmactrl, tempval); - if (phydev->duplex != priv->oldduplex) { - if (!(phydev->duplex)) - tempval &= ~(MACCFG2_FULL_DUPLEX); - else - tempval |= MACCFG2_FULL_DUPLEX; + /* Make sure we aren't stopped */ + tempval = gfar_read(®s->dmactrl); + tempval &= ~DMACTRL_GRS; + gfar_write(®s->dmactrl, tempval); - priv->oldduplex = phydev->duplex; - } + for (i = 0; i < priv->num_grps; i++) { + regs = priv->gfargrp[i].regs; + /* Clear RHLT, so that the DMA starts polling now */ + gfar_write(®s->rstat, priv->gfargrp[i].rstat); + /* enable the Filer General Purpose Interrupt */ + gfar_write(®s->imask, IMASK_FGPI); + } - if (phydev->speed != priv->oldspeed) { - switch (phydev->speed) { - case 1000: - tempval = - ((tempval & ~(MACCFG2_IF)) | MACCFG2_GMII); + /* Enable Rx DMA */ + tempval = gfar_read(®s->maccfg1); + tempval |= MACCFG1_RX_EN; + gfar_write(®s->maccfg1, tempval); +} - ecntrl &= ~(ECNTRL_R100); - break; - case 100: - case 10: - tempval = - ((tempval & ~(MACCFG2_IF)) | MACCFG2_MII); +static int gfar_suspend(struct device *dev) +{ + struct gfar_private *priv = dev_get_drvdata(dev); + struct net_device *ndev = priv->ndev; + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 tempval; + u16 wol = priv->wol_opts; - /* Reduced mode distinguishes - * between 10 and 100 - */ - if (phydev->speed == SPEED_100) - ecntrl |= ECNTRL_R100; - else - ecntrl &= ~(ECNTRL_R100); - break; - default: - netif_warn(priv, link, priv->ndev, - "Ack! Speed (%d) is not 10/100/1000!\n", - phydev->speed); - break; - } + if (!netif_running(ndev)) + return 0; - priv->oldspeed = phydev->speed; - } + disable_napi(priv); + netif_tx_lock(ndev); + netif_device_detach(ndev); + netif_tx_unlock(ndev); - tempval1 &= ~(MACCFG1_TX_FLOW | MACCFG1_RX_FLOW); - tempval1 |= gfar_get_flowctrl_cfg(priv); + gfar_halt(priv); - /* Turn last free buffer recording on */ - if ((tempval1 & MACCFG1_TX_FLOW) && !tx_flow_oldval) { - for (i = 0; i < priv->num_rx_queues; i++) { - u32 bdp_dma; + if (wol & GFAR_WOL_MAGIC) { + /* Enable interrupt on Magic Packet */ + gfar_write(®s->imask, IMASK_MAG); - rx_queue = priv->rx_queue[i]; - bdp_dma = gfar_rxbd_dma_lastfree(rx_queue); - gfar_write(rx_queue->rfbptr, bdp_dma); - } + /* Enable Magic Packet mode */ + tempval = gfar_read(®s->maccfg2); + tempval |= MACCFG2_MPEN; + gfar_write(®s->maccfg2, tempval); - priv->tx_actual_en = 1; - } + /* re-enable the Rx block */ + tempval = gfar_read(®s->maccfg1); + tempval |= MACCFG1_RX_EN; + gfar_write(®s->maccfg1, tempval); - if (unlikely(!(tempval1 & MACCFG1_TX_FLOW) && tx_flow_oldval)) - priv->tx_actual_en = 0; + } else if (wol & GFAR_WOL_FILER_UCAST) { + gfar_filer_config_wol(priv); + gfar_start_wol_filer(priv); - gfar_write(®s->maccfg1, tempval1); + } else { + phy_stop(ndev->phydev); + } + + return 0; +} + +static int gfar_resume(struct device *dev) +{ + struct gfar_private *priv = dev_get_drvdata(dev); + struct net_device *ndev = priv->ndev; + struct gfar __iomem *regs = priv->gfargrp[0].regs; + u32 tempval; + u16 wol = priv->wol_opts; + + if (!netif_running(ndev)) + return 0; + + if (wol & GFAR_WOL_MAGIC) { + /* Disable Magic Packet mode */ + tempval = gfar_read(®s->maccfg2); + tempval &= ~MACCFG2_MPEN; gfar_write(®s->maccfg2, tempval); - gfar_write(®s->ecntrl, ecntrl); - if (!priv->oldlink) - priv->oldlink = 1; + } else if (wol & GFAR_WOL_FILER_UCAST) { + /* need to stop rx only, tx is already down */ + gfar_halt(priv); + gfar_filer_restore_table(priv); - } else if (priv->oldlink) { - priv->oldlink = 0; - priv->oldspeed = 0; - priv->oldduplex = -1; + } else { + phy_start(ndev->phydev); } - if (netif_msg_link(priv)) - phy_print_status(phydev); + gfar_start(priv); + + netif_device_attach(ndev); + enable_napi(priv); + + return 0; +} + +static int gfar_restore(struct device *dev) +{ + struct gfar_private *priv = dev_get_drvdata(dev); + struct net_device *ndev = priv->ndev; + + if (!netif_running(ndev)) { + netif_device_attach(ndev); + + return 0; + } + + gfar_init_bds(ndev); + + gfar_mac_reset(priv); + + gfar_init_tx_rx_base(priv); + + gfar_start(priv); + + priv->oldlink = 0; + priv->oldspeed = 0; + priv->oldduplex = -1; + + if (ndev->phydev) + phy_start(ndev->phydev); + + netif_device_attach(ndev); + enable_napi(priv); + + return 0; } +static const struct dev_pm_ops gfar_pm_ops = { + .suspend = gfar_suspend, + .resume = gfar_resume, + .freeze = gfar_suspend, + .thaw = gfar_resume, + .restore = gfar_restore, +}; + +#define GFAR_PM_OPS (&gfar_pm_ops) + +#else + +#define GFAR_PM_OPS NULL + +#endif + static const struct of_device_id gfar_match[] = { { diff --git a/drivers/net/ethernet/freescale/gianfar.h b/drivers/net/ethernet/freescale/gianfar.h index f2af96349c7b..f472a6dbbe6f 100644 --- a/drivers/net/ethernet/freescale/gianfar.h +++ b/drivers/net/ethernet/freescale/gianfar.h @@ -67,8 +67,6 @@ struct ethtool_rx_list { /* Number of bytes to align the rx bufs to */ #define RXBUF_ALIGNMENT 64 -#define PHY_INIT_TIMEOUT 100000 - #define DRV_NAME "gfar-enet" extern const char gfar_driver_version[]; @@ -88,10 +86,6 @@ extern const char gfar_driver_version[]; #define GFAR_RX_MAX_RING_SIZE 256 #define GFAR_TX_MAX_RING_SIZE 256 -#define GFAR_MAX_FIFO_THRESHOLD 511 -#define GFAR_MAX_FIFO_STARVE 511 -#define GFAR_MAX_FIFO_STARVE_OFF 511 - #define FBTHR_SHIFT 24 #define DEFAULT_RX_LFC_THR 16 #define DEFAULT_LFC_PTVVAL 4 @@ -109,9 +103,6 @@ extern const char gfar_driver_version[]; #define DEFAULT_FIFO_TX_THR 0x100 #define DEFAULT_FIFO_TX_STARVE 0x40 #define DEFAULT_FIFO_TX_STARVE_OFF 0x80 -#define DEFAULT_BD_STASH 1 -#define DEFAULT_STASH_LENGTH 96 -#define DEFAULT_STASH_INDEX 0 /* The number of Exact Match registers */ #define GFAR_EM_NUM 15 @@ -139,15 +130,6 @@ extern const char gfar_driver_version[]; #define DEFAULT_RX_COALESCE 0 #define DEFAULT_RXCOUNT 0 -#define GFAR_SUPPORTED (SUPPORTED_10baseT_Half \ - | SUPPORTED_10baseT_Full \ - | SUPPORTED_100baseT_Half \ - | SUPPORTED_100baseT_Full \ - | SUPPORTED_Autoneg \ - | SUPPORTED_MII) - -#define GFAR_SUPPORTED_GBIT SUPPORTED_1000baseT_Full - /* TBI register addresses */ #define MII_TBICON 0x11 @@ -185,8 +167,6 @@ extern const char gfar_driver_version[]; #define ECNTRL_REDUCED_MII_MODE 0x00000004 #define ECNTRL_SGMII_MODE 0x00000002 -#define MRBLR_INIT_SETTINGS DEFAULT_RX_BUFFER_SIZE - #define MINFLR_INIT_SETTINGS 0x00000040 /* Tqueue control */ @@ -266,12 +246,6 @@ extern const char gfar_driver_version[]; #define DEFAULT_TXIC mk_ic_value(DEFAULT_TXCOUNT, DEFAULT_TXTIME) #define DEFAULT_RXIC mk_ic_value(DEFAULT_RXCOUNT, DEFAULT_RXTIME) -#define skip_bd(bdp, stride, base, ring_size) ({ \ - typeof(bdp) new_bd = (bdp) + (stride); \ - (new_bd >= (base) + (ring_size)) ? (new_bd - (ring_size)) : new_bd; }) - -#define next_bd(bdp, base, ring_size) skip_bd(bdp, 1, base, ring_size) - #define RCTRL_TS_ENABLE 0x01000000 #define RCTRL_PAL_MASK 0x001f0000 #define RCTRL_LFC 0x00004000 @@ -385,11 +359,6 @@ extern const char gfar_driver_version[]; #define IMASK_RX_DISABLED ((~(IMASK_RX_DEFAULT)) & IMASK_DEFAULT) #define IMASK_TX_DISABLED ((~(IMASK_TX_DEFAULT)) & IMASK_DEFAULT) -/* Fifo management */ -#define FIFO_TX_THR_MASK 0x01ff -#define FIFO_TX_STARVE_MASK 0x01ff -#define FIFO_TX_STARVE_OFF_MASK 0x01ff - /* Attribute fields */ /* This enables rx snooping for buffers and descriptors */ @@ -1326,16 +1295,9 @@ static inline u32 gfar_rxbd_dma_lastfree(struct gfar_priv_rx_q *rxq) return bdp_dma; } -irqreturn_t gfar_receive(int irq, void *dev_id); int startup_gfar(struct net_device *dev); void stop_gfar(struct net_device *dev); -void reset_gfar(struct net_device *dev); void gfar_mac_reset(struct gfar_private *priv); -void gfar_halt(struct gfar_private *priv); -void gfar_start(struct gfar_private *priv); -void gfar_phy_test(struct mii_bus *bus, struct phy_device *phydev, int enable, - u32 regnum, u32 read); -void gfar_configure_coalescing_all(struct gfar_private *priv); int gfar_set_features(struct net_device *dev, netdev_features_t features); extern const struct ethtool_ops gfar_ethtool_ops; @@ -1348,13 +1310,6 @@ extern const struct ethtool_ops gfar_ethtool_ops; #define RQFCR_PID_PORT_MASK 0xFFFF0000 #define RQFCR_PID_MAC_MASK 0xFF000000 -struct gfar_mask_entry { - unsigned int mask; /* The mask value which is valid form start to end */ - unsigned int start; - unsigned int end; - unsigned int block; /* Same block values indicate depended entries */ -}; - /* Represents a receive filer table entry */ struct gfar_filer_entry { u32 ctrl; diff --git a/drivers/net/ethernet/freescale/gianfar_ethtool.c b/drivers/net/ethernet/freescale/gianfar_ethtool.c index 3433b46b90c1..3c8e4e2efc07 100644 --- a/drivers/net/ethernet/freescale/gianfar_ethtool.c +++ b/drivers/net/ethernet/freescale/gianfar_ethtool.c @@ -45,19 +45,6 @@ #define GFAR_MAX_COAL_USECS 0xffff #define GFAR_MAX_COAL_FRAMES 0xff -static void gfar_fill_stats(struct net_device *dev, struct ethtool_stats *dummy, - u64 *buf); -static void gfar_gstrings(struct net_device *dev, u32 stringset, u8 * buf); -static int gfar_gcoalesce(struct net_device *dev, - struct ethtool_coalesce *cvals); -static int gfar_scoalesce(struct net_device *dev, - struct ethtool_coalesce *cvals); -static void gfar_gringparam(struct net_device *dev, - struct ethtool_ringparam *rvals); -static int gfar_sringparam(struct net_device *dev, - struct ethtool_ringparam *rvals); -static void gfar_gdrvinfo(struct net_device *dev, - struct ethtool_drvinfo *drvinfo); static const char stat_gstrings[][ETH_GSTRING_LEN] = { /* extra stats */ diff --git a/drivers/net/ethernet/hisilicon/hisi_femac.c b/drivers/net/ethernet/hisilicon/hisi_femac.c index 689f18e3100f..90ab7ade44c4 100644 --- a/drivers/net/ethernet/hisilicon/hisi_femac.c +++ b/drivers/net/ethernet/hisilicon/hisi_femac.c @@ -877,7 +877,6 @@ static int hisi_femac_drv_probe(struct platform_device *pdev) ndev->irq = platform_get_irq(pdev, 0); if (ndev->irq <= 0) { - dev_err(dev, "No irq resource\n"); ret = -ENODEV; goto out_disconnect_phy; } diff --git a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c index 349970557c52..95a6b0926170 100644 --- a/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c +++ b/drivers/net/ethernet/hisilicon/hix5hd2_gmac.c @@ -719,7 +719,7 @@ static int hix5hd2_fill_sg_desc(struct hix5hd2_priv *priv, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - int len = frag->size; + int len = skb_frag_size(frag); addr = skb_frag_dma_map(priv->dev, frag, 0, len, DMA_TO_DEVICE); ret = dma_mapping_error(priv->dev, addr); diff --git a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c index c1eba421ba82..3a14bbc26ea2 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_dsaf_main.c @@ -24,7 +24,7 @@ #include "hns_dsaf_rcb.h" #include "hns_dsaf_misc.h" -const static char *g_dsaf_mode_match[DSAF_MODE_MAX] = { +static const char *g_dsaf_mode_match[DSAF_MODE_MAX] = { [DSAF_MODE_DISABLE_2PORT_64VM] = "2port-64vf", [DSAF_MODE_DISABLE_6PORT_0VM] = "6port-16rss", [DSAF_MODE_DISABLE_6PORT_16VM] = "6port-16vf", diff --git a/drivers/net/ethernet/hisilicon/hns/hns_enet.c b/drivers/net/ethernet/hisilicon/hns/hns_enet.c index 2235dd55fab2..a48396dd4ebb 100644 --- a/drivers/net/ethernet/hisilicon/hns/hns_enet.c +++ b/drivers/net/ethernet/hisilicon/hns/hns_enet.c @@ -245,7 +245,7 @@ static int hns_nic_maybe_stop_tso( int frag_num; struct sk_buff *skb = *out_skb; struct sk_buff *new_skb = NULL; - struct skb_frag_struct *frag; + skb_frag_t *frag; size = skb_headlen(skb); buf_num = (size + BD_MAX_SEND_SIZE - 1) / BD_MAX_SEND_SIZE; @@ -309,7 +309,7 @@ netdev_tx_t hns_nic_net_xmit_hw(struct net_device *ndev, struct hnae_ring *ring = ring_data->ring; struct device *dev = ring_to_dev(ring); struct netdev_queue *dev_queue; - struct skb_frag_struct *frag; + skb_frag_t *frag; int buf_num; int seg_num; dma_addr_t dma; @@ -1182,6 +1182,8 @@ int hns_nic_init_phy(struct net_device *ndev, struct hnae_handle *h) if (unlikely(ret)) return -ENODEV; + phy_attached_info(phy_dev); + return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h index 75329ab775a6..f8a87f8ca983 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h +++ b/drivers/net/ethernet/hisilicon/hns3/hclge_mbx.h @@ -47,6 +47,8 @@ enum HCLGE_MBX_OPCODE { HCLGE_MBX_GET_MEDIA_TYPE, /* (VF -> PF) get media type */ HCLGE_MBX_GET_VF_FLR_STATUS = 200, /* (M7 -> PF) get vf reset status */ + HCLGE_MBX_PUSH_LINK_STATUS, /* (M7 -> PF) get port link status */ + HCLGE_MBX_NCSI_ERROR, /* (M7 -> PF) receive a NCSI error */ }; /* below are per-VF mac-vlan subcodes */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.c b/drivers/net/ethernet/hisilicon/hns3/hnae3.c index 908d4f45c06a..03ca7d925e8e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.c +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.c @@ -46,7 +46,7 @@ void hnae3_set_client_init_flag(struct hnae3_client *client, EXPORT_SYMBOL(hnae3_set_client_init_flag); static int hnae3_get_client_init_flag(struct hnae3_client *client, - struct hnae3_ae_dev *ae_dev) + struct hnae3_ae_dev *ae_dev) { int inited = 0; @@ -104,7 +104,6 @@ int hnae3_register_client(struct hnae3_client *client) { struct hnae3_client *client_tmp; struct hnae3_ae_dev *ae_dev; - int ret = 0; if (!client) return -ENODEV; @@ -123,7 +122,7 @@ int hnae3_register_client(struct hnae3_client *client) /* if the client could not be initialized on current port, for * any error reasons, move on to next available port */ - ret = hnae3_init_client_instance(client, ae_dev); + int ret = hnae3_init_client_instance(client, ae_dev); if (ret) dev_err(&ae_dev->pdev->dev, "match and instantiation failed for port, ret = %d\n", @@ -139,12 +138,28 @@ EXPORT_SYMBOL(hnae3_register_client); void hnae3_unregister_client(struct hnae3_client *client) { + struct hnae3_client *client_tmp; struct hnae3_ae_dev *ae_dev; + bool existed = false; if (!client) return; mutex_lock(&hnae3_common_lock); + + list_for_each_entry(client_tmp, &hnae3_client_list, node) { + if (client_tmp->type == client->type) { + existed = true; + break; + } + } + + if (!existed) { + mutex_unlock(&hnae3_common_lock); + pr_err("client %s does not exist!\n", client->name); + return; + } + /* un-initialize the client on every matched port */ list_for_each_entry(ae_dev, &hnae3_ae_dev_list, node) { hnae3_uninit_client_instance(client, ae_dev); @@ -164,7 +179,7 @@ void hnae3_register_ae_algo(struct hnae3_ae_algo *ae_algo) const struct pci_device_id *id; struct hnae3_ae_dev *ae_dev; struct hnae3_client *client; - int ret = 0; + int ret; if (!ae_algo) return; @@ -258,7 +273,7 @@ int hnae3_register_ae_dev(struct hnae3_ae_dev *ae_dev) const struct pci_device_id *id; struct hnae3_ae_algo *ae_algo; struct hnae3_client *client; - int ret = 0; + int ret; if (!ae_dev) return -ENODEV; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 48c7b70fc2c4..c4b7bf851a28 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -58,10 +58,10 @@ BIT(HNAE3_DEV_SUPPORT_ROCE_B)) #define hnae3_dev_roce_supported(hdev) \ - hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B) + hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_ROCE_B) #define hnae3_dev_dcb_supported(hdev) \ - hnae3_get_bit(hdev->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B) + hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_DCB_B) #define hnae3_dev_fd_supported(hdev) \ hnae3_get_bit((hdev)->ae_dev->flag, HNAE3_DEV_SUPPORT_FD_B) @@ -85,13 +85,18 @@ struct hnae3_queue { void __iomem *io_base; struct hnae3_ae_algo *ae_algo; struct hnae3_handle *handle; - int tqp_index; /* index in a handle */ - u32 buf_size; /* size for hnae_desc->addr, preset by AE */ - u16 tx_desc_num;/* total number of tx desc */ - u16 rx_desc_num;/* total number of rx desc */ + int tqp_index; /* index in a handle */ + u32 buf_size; /* size for hnae_desc->addr, preset by AE */ + u16 tx_desc_num; /* total number of tx desc */ + u16 rx_desc_num; /* total number of rx desc */ }; -/*hnae3 loop mode*/ +struct hns3_mac_stats { + u64 tx_pause_cnt; + u64 rx_pause_cnt; +}; + +/* hnae3 loop mode */ enum hnae3_loop { HNAE3_LOOP_APP, HNAE3_LOOP_SERIAL_SERDES, @@ -141,6 +146,12 @@ enum hnae3_reset_notify_type { HNAE3_RESTORE_CLIENT, }; +enum hnae3_hw_error_type { + HNAE3_PPU_POISON_ERROR, + HNAE3_CMDQ_ECC_ERROR, + HNAE3_IMP_RD_POISON_ERROR, +}; + enum hnae3_reset_type { HNAE3_VF_RESET, HNAE3_VF_FUNC_RESET, @@ -179,6 +190,15 @@ struct hnae3_vector_info { #define HNAE3_RING_GL_RX 0 #define HNAE3_RING_GL_TX 1 +#define HNAE3_FW_VERSION_BYTE3_SHIFT 24 +#define HNAE3_FW_VERSION_BYTE3_MASK GENMASK(31, 24) +#define HNAE3_FW_VERSION_BYTE2_SHIFT 16 +#define HNAE3_FW_VERSION_BYTE2_MASK GENMASK(23, 16) +#define HNAE3_FW_VERSION_BYTE1_SHIFT 8 +#define HNAE3_FW_VERSION_BYTE1_MASK GENMASK(15, 8) +#define HNAE3_FW_VERSION_BYTE0_SHIFT 0 +#define HNAE3_FW_VERSION_BYTE0_MASK GENMASK(7, 0) + struct hnae3_ring_chain_node { struct hnae3_ring_chain_node *next; u32 tqp_index; @@ -196,7 +216,8 @@ struct hnae3_client_ops { int (*setup_tc)(struct hnae3_handle *handle, u8 tc); int (*reset_notify)(struct hnae3_handle *handle, enum hnae3_reset_notify_type type); - enum hnae3_reset_type (*process_hw_error)(struct hnae3_handle *handle); + void (*process_hw_error)(struct hnae3_handle *handle, + enum hnae3_hw_error_type); }; #define HNAE3_CLIENT_NAME_LENGTH 16 @@ -289,6 +310,8 @@ struct hnae3_ae_dev { * Remove multicast address from mac table * update_stats() * Update Old network device statistics + * get_mac_stats() + * get mac pause statistics including tx_cnt and rx_cnt * get_ethtool_stats() * Get ethtool network device statistics * get_strings() @@ -417,8 +440,8 @@ struct hnae3_ae_ops { void (*update_stats)(struct hnae3_handle *handle, struct net_device_stats *net_stats); void (*get_stats)(struct hnae3_handle *handle, u64 *data); - void (*get_mac_pause_stats)(struct hnae3_handle *handle, u64 *tx_cnt, - u64 *rx_cnt); + void (*get_mac_stats)(struct hnae3_handle *handle, + struct hns3_mac_stats *mac_stats); void (*get_strings)(struct hnae3_handle *handle, u32 stringset, u8 *data); int (*get_sset_count)(struct hnae3_handle *handle, int stringset); @@ -605,7 +628,7 @@ struct hnae3_handle { struct pci_dev *pdev; void *priv; struct hnae3_ae_algo *ae_algo; /* the class who provides this handle */ - u64 flags; /* Indicate the capabilities for this handle*/ + u64 flags; /* Indicate the capabilities for this handle */ union { struct net_device *netdev; /* first member */ diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c index a4b937286f55..28961a68e333 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c @@ -8,6 +8,7 @@ #include "hns3_enet.h" #define HNS3_DBG_READ_LEN 256 +#define HNS3_DBG_WRITE_LEN 1024 static struct dentry *hns3_dbgfs_root; @@ -38,7 +39,7 @@ static int hns3_dbg_queue_info(struct hnae3_handle *h, if (queue_num >= h->kinfo.num_tqps) { dev_err(&h->pdev->dev, - "Queue number(%u) is out of range(%u)\n", queue_num, + "Queue number(%u) is out of range(0-%u)\n", queue_num, h->kinfo.num_tqps - 1); return -EINVAL; } @@ -165,6 +166,7 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf) struct hns3_enet_ring *ring; u32 tx_index, rx_index; u32 q_num, value; + dma_addr_t addr; int cnt; cnt = sscanf(&cmd_buf[8], "%u %u", &q_num, &tx_index); @@ -176,7 +178,7 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf) } if (q_num >= h->kinfo.num_tqps) { - dev_err(dev, "Queue number(%u) is out of range(%u)\n", q_num, + dev_err(dev, "Queue number(%u) is out of range(0-%u)\n", q_num, h->kinfo.num_tqps - 1); return -EINVAL; } @@ -187,14 +189,15 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf) tx_index = (cnt == 1) ? value : tx_index; if (tx_index >= ring->desc_num) { - dev_err(dev, "bd index (%u) is out of range(%u)\n", tx_index, + dev_err(dev, "bd index(%u) is out of range(0-%u)\n", tx_index, ring->desc_num - 1); return -EINVAL; } tx_desc = &ring->desc[tx_index]; + addr = le64_to_cpu(tx_desc->addr); dev_info(dev, "TX Queue Num: %u, BD Index: %u\n", q_num, tx_index); - dev_info(dev, "(TX) addr: 0x%llx\n", tx_desc->addr); + dev_info(dev, "(TX)addr: %pad\n", &addr); dev_info(dev, "(TX)vlan_tag: %u\n", tx_desc->tx.vlan_tag); dev_info(dev, "(TX)send_size: %u\n", tx_desc->tx.send_size); dev_info(dev, "(TX)vlan_tso: %u\n", tx_desc->tx.type_cs_vlan_tso); @@ -216,8 +219,10 @@ static int hns3_dbg_bd_info(struct hnae3_handle *h, const char *cmd_buf) rx_index = (cnt == 1) ? value : tx_index; rx_desc = &ring->desc[rx_index]; + addr = le64_to_cpu(rx_desc->addr); dev_info(dev, "RX Queue Num: %u, BD Index: %u\n", q_num, rx_index); - dev_info(dev, "(RX)addr: 0x%llx\n", rx_desc->addr); + dev_info(dev, "(RX)addr: %pad\n", &addr); + dev_info(dev, "(RX)l234_info: %u\n", rx_desc->rx.l234_info); dev_info(dev, "(RX)pkt_len: %u\n", rx_desc->rx.pkt_len); dev_info(dev, "(RX)size: %u\n", rx_desc->rx.size); dev_info(dev, "(RX)rss_hash: %u\n", rx_desc->rx.rss_hash); @@ -237,16 +242,16 @@ static void hns3_dbg_help(struct hnae3_handle *h) char printf_buf[HNS3_DBG_BUF_LEN]; dev_info(&h->pdev->dev, "available commands\n"); - dev_info(&h->pdev->dev, "queue info [number]\n"); + dev_info(&h->pdev->dev, "queue info <number>\n"); dev_info(&h->pdev->dev, "queue map\n"); - dev_info(&h->pdev->dev, "bd info [q_num] <bd index>\n"); + dev_info(&h->pdev->dev, "bd info <q_num> <bd index>\n"); if (!hns3_is_phys_func(h->pdev)) return; dev_info(&h->pdev->dev, "dump fd tcam\n"); dev_info(&h->pdev->dev, "dump tc\n"); - dev_info(&h->pdev->dev, "dump tm map [q_num]\n"); + dev_info(&h->pdev->dev, "dump tm map <q_num>\n"); dev_info(&h->pdev->dev, "dump tm\n"); dev_info(&h->pdev->dev, "dump qos pause cfg\n"); dev_info(&h->pdev->dev, "dump qos pri map\n"); @@ -258,20 +263,20 @@ static void hns3_dbg_help(struct hnae3_handle *h) dev_info(&h->pdev->dev, "dump mac tnl status\n"); memset(printf_buf, 0, HNS3_DBG_BUF_LEN); - strncat(printf_buf, "dump reg [[bios common] [ssu <prt_id>]", + strncat(printf_buf, "dump reg [[bios common] [ssu <port_id>]", HNS3_DBG_BUF_LEN - 1); strncat(printf_buf + strlen(printf_buf), - " [igu egu <prt_id>] [rpu <tc_queue_num>]", + " [igu egu <port_id>] [rpu <tc_queue_num>]", HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1); strncat(printf_buf + strlen(printf_buf), - " [rtc] [ppp] [rcb] [tqp <q_num>]]\n", + " [rtc] [ppp] [rcb] [tqp <queue_num>]]\n", HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1); dev_info(&h->pdev->dev, "%s", printf_buf); memset(printf_buf, 0, HNS3_DBG_BUF_LEN); - strncat(printf_buf, "dump reg dcb [port_id] [pri_id] [pg_id]", + strncat(printf_buf, "dump reg dcb <port_id> <pri_id> <pg_id>", HNS3_DBG_BUF_LEN - 1); - strncat(printf_buf + strlen(printf_buf), " [rq_id] [nq_id] [qset_id]\n", + strncat(printf_buf + strlen(printf_buf), " <rq_id> <nq_id> <qset_id>\n", HNS3_DBG_BUF_LEN - strlen(printf_buf) - 1); dev_info(&h->pdev->dev, "%s", printf_buf); } @@ -322,6 +327,9 @@ static ssize_t hns3_dbg_cmd_write(struct file *filp, const char __user *buffer, test_bit(HNS3_NIC_STATE_RESETTING, &priv->state)) return 0; + if (count > HNS3_DBG_WRITE_LEN) + return -ENOSPC; + cmd_buf = kzalloc(count + 1, GFP_KERNEL); if (!cmd_buf) return count; @@ -372,20 +380,11 @@ static const struct file_operations hns3_dbg_cmd_fops = { void hns3_dbg_init(struct hnae3_handle *handle) { const char *name = pci_name(handle->pdev); - struct dentry *pfile; handle->hnae3_dbgfs = debugfs_create_dir(name, hns3_dbgfs_root); - if (!handle->hnae3_dbgfs) - return; - pfile = debugfs_create_file("cmd", 0600, handle->hnae3_dbgfs, handle, - &hns3_dbg_cmd_fops); - if (!pfile) { - debugfs_remove_recursive(handle->hnae3_dbgfs); - handle->hnae3_dbgfs = NULL; - dev_warn(&handle->pdev->dev, "create file for %s fail\n", - name); - } + debugfs_create_file("cmd", 0600, handle->hnae3_dbgfs, handle, + &hns3_dbg_cmd_fops); } void hns3_dbg_uninit(struct hnae3_handle *handle) @@ -397,10 +396,6 @@ void hns3_dbg_uninit(struct hnae3_handle *handle) void hns3_dbg_register_debugfs(const char *debugfs_dir_name) { hns3_dbgfs_root = debugfs_create_dir(debugfs_dir_name, NULL); - if (!hns3_dbgfs_root) { - pr_warn("Register debugfs for %s fail\n", debugfs_dir_name); - return; - } } void hns3_dbg_unregister_debugfs(void) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 310afa708831..616cad0faa21 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -28,6 +28,12 @@ #define hns3_set_field(origin, shift, val) ((origin) |= ((val) << (shift))) #define hns3_tx_bd_count(S) DIV_ROUND_UP(S, HNS3_MAX_BD_SIZE) +#define hns3_rl_err(fmt, ...) \ + do { \ + if (net_ratelimit()) \ + netdev_err(fmt, ##__VA_ARGS__); \ + } while (0) + static void hns3_clear_all_ring(struct hnae3_handle *h, bool force); static void hns3_remove_hw_addr(struct net_device *netdev); @@ -45,6 +51,9 @@ MODULE_PARM_DESC(debug, " Network interface message level setting"); #define DEFAULT_MSG_LEVEL (NETIF_MSG_PROBE | NETIF_MSG_LINK | \ NETIF_MSG_IFDOWN | NETIF_MSG_IFUP) +#define HNS3_INNER_VLAN_TAG 1 +#define HNS3_OUTER_VLAN_TAG 2 + /* hns3_pci_tbl - PCI Device ID Table * * Last entry must be all 0s @@ -220,9 +229,9 @@ static void hns3_vector_gl_rl_init(struct hns3_enet_tqp_vector *tqp_vector, /* initialize the configuration for interrupt coalescing. * 1. GL (Interrupt Gap Limiter) * 2. RL (Interrupt Rate Limiter) + * + * Default: enable interrupt coalescing self-adaptive and GL */ - - /* Default: enable interrupt coalescing self-adaptive and GL */ tqp_vector->tx_group.coal.gl_adapt_enable = 1; tqp_vector->rx_group.coal.gl_adapt_enable = 1; @@ -459,6 +468,9 @@ static int hns3_nic_net_open(struct net_device *netdev) h->ae_algo->ops->set_timer_task(priv->ae_handle, true); hns3_config_xps(priv); + + netif_dbg(h, drv, netdev, "net open\n"); + return 0; } @@ -519,6 +531,8 @@ static int hns3_nic_net_stop(struct net_device *netdev) if (test_and_set_bit(HNS3_NIC_STATE_DOWN, &priv->state)) return 0; + netif_dbg(h, drv, netdev, "net stop\n"); + if (h->ae_algo->ops->set_timer_task) h->ae_algo->ops->set_timer_task(priv->ae_handle, false); @@ -956,16 +970,16 @@ static void hns3_set_txbd_baseinfo(u16 *bdtp_fe_sc_vld_ra_ri, int frag_end) hns3_set_field(*bdtp_fe_sc_vld_ra_ri, HNS3_TXD_VLD_B, 1U); } -static int hns3_fill_desc_vtags(struct sk_buff *skb, - struct hns3_enet_ring *tx_ring, - u32 *inner_vlan_flag, - u32 *out_vlan_flag, - u16 *inner_vtag, - u16 *out_vtag) +static int hns3_handle_vtags(struct hns3_enet_ring *tx_ring, + struct sk_buff *skb) { -#define HNS3_TX_VLAN_PRIO_SHIFT 13 - struct hnae3_handle *handle = tx_ring->tqp->handle; + struct vlan_ethhdr *vhdr; + int rc; + + if (!(skb->protocol == htons(ETH_P_8021Q) || + skb_vlan_tag_present(skb))) + return 0; /* Since HW limitation, if port based insert VLAN enabled, only one VLAN * header is allowed in skb, otherwise it will cause RAS error. @@ -976,8 +990,7 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb, return -EINVAL; if (skb->protocol == htons(ETH_P_8021Q) && - !(tx_ring->tqp->handle->kinfo.netdev->features & - NETIF_F_HW_VLAN_CTAG_TX)) { + !(handle->kinfo.netdev->features & NETIF_F_HW_VLAN_CTAG_TX)) { /* When HW VLAN acceleration is turned off, and the stack * sets the protocol to 802.1q, the driver just need to * set the protocol to the encapsulated ethertype. @@ -987,45 +1000,107 @@ static int hns3_fill_desc_vtags(struct sk_buff *skb, } if (skb_vlan_tag_present(skb)) { - u16 vlan_tag; - - vlan_tag = skb_vlan_tag_get(skb); - vlan_tag |= (skb->priority & 0x7) << HNS3_TX_VLAN_PRIO_SHIFT; - /* Based on hw strategy, use out_vtag in two layer tag case, * and use inner_vtag in one tag case. */ - if (skb->protocol == htons(ETH_P_8021Q)) { - if (handle->port_base_vlan_state == - HNAE3_PORT_BASE_VLAN_DISABLE){ - hns3_set_field(*out_vlan_flag, - HNS3_TXD_OVLAN_B, 1); - *out_vtag = vlan_tag; - } else { - hns3_set_field(*inner_vlan_flag, - HNS3_TXD_VLAN_B, 1); - *inner_vtag = vlan_tag; - } - } else { - hns3_set_field(*inner_vlan_flag, HNS3_TXD_VLAN_B, 1); - *inner_vtag = vlan_tag; - } - } else if (skb->protocol == htons(ETH_P_8021Q)) { - struct vlan_ethhdr *vhdr; - int rc; + if (skb->protocol == htons(ETH_P_8021Q) && + handle->port_base_vlan_state == + HNAE3_PORT_BASE_VLAN_DISABLE) + rc = HNS3_OUTER_VLAN_TAG; + else + rc = HNS3_INNER_VLAN_TAG; - rc = skb_cow_head(skb, 0); - if (unlikely(rc < 0)) - return rc; - vhdr = (struct vlan_ethhdr *)skb->data; - vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority & 0x7) - << HNS3_TX_VLAN_PRIO_SHIFT); + skb->protocol = vlan_get_protocol(skb); + return rc; } + rc = skb_cow_head(skb, 0); + if (unlikely(rc < 0)) + return rc; + + vhdr = (struct vlan_ethhdr *)skb->data; + vhdr->h_vlan_TCI |= cpu_to_be16((skb->priority << VLAN_PRIO_SHIFT) + & VLAN_PRIO_MASK); + skb->protocol = vlan_get_protocol(skb); return 0; } +static int hns3_fill_skb_desc(struct hns3_enet_ring *ring, + struct sk_buff *skb, struct hns3_desc *desc) +{ + u32 ol_type_vlan_len_msec = 0; + u32 type_cs_vlan_tso = 0; + u32 paylen = skb->len; + u16 inner_vtag = 0; + u16 out_vtag = 0; + u16 mss = 0; + int ret; + + ret = hns3_handle_vtags(ring, skb); + if (unlikely(ret < 0)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_vlan_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } else if (ret == HNS3_INNER_VLAN_TAG) { + inner_vtag = skb_vlan_tag_get(skb); + inner_vtag |= (skb->priority << VLAN_PRIO_SHIFT) & + VLAN_PRIO_MASK; + hns3_set_field(type_cs_vlan_tso, HNS3_TXD_VLAN_B, 1); + } else if (ret == HNS3_OUTER_VLAN_TAG) { + out_vtag = skb_vlan_tag_get(skb); + out_vtag |= (skb->priority << VLAN_PRIO_SHIFT) & + VLAN_PRIO_MASK; + hns3_set_field(ol_type_vlan_len_msec, HNS3_TXD_OVLAN_B, + 1); + } + + if (skb->ip_summed == CHECKSUM_PARTIAL) { + u8 ol4_proto, il4_proto; + + skb_reset_mac_len(skb); + + ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto); + if (unlikely(ret)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_l4_proto_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } + + ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto, + &type_cs_vlan_tso, + &ol_type_vlan_len_msec); + if (unlikely(ret)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_l2l3l4_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } + + ret = hns3_set_tso(skb, &paylen, &mss, + &type_cs_vlan_tso); + if (unlikely(ret)) { + u64_stats_update_begin(&ring->syncp); + ring->stats.tx_tso_err++; + u64_stats_update_end(&ring->syncp); + return ret; + } + } + + /* Set txbd */ + desc->tx.ol_type_vlan_len_msec = + cpu_to_le32(ol_type_vlan_len_msec); + desc->tx.type_cs_vlan_tso_len = cpu_to_le32(type_cs_vlan_tso); + desc->tx.paylen = cpu_to_le32(paylen); + desc->tx.mss = cpu_to_le16(mss); + desc->tx.vlan_tag = cpu_to_le16(inner_vtag); + desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag); + + return 0; +} + static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, unsigned int size, int frag_end, enum hns_desc_type type) @@ -1033,65 +1108,29 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use]; struct hns3_desc *desc = &ring->desc[ring->next_to_use]; struct device *dev = ring_to_dev(ring); - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned int frag_buf_num; int k, sizeoflast; dma_addr_t dma; if (type == DESC_TYPE_SKB) { struct sk_buff *skb = (struct sk_buff *)priv; - u32 ol_type_vlan_len_msec = 0; - u32 type_cs_vlan_tso = 0; - u32 paylen = skb->len; - u16 inner_vtag = 0; - u16 out_vtag = 0; - u16 mss = 0; int ret; - ret = hns3_fill_desc_vtags(skb, ring, &type_cs_vlan_tso, - &ol_type_vlan_len_msec, - &inner_vtag, &out_vtag); + ret = hns3_fill_skb_desc(ring, skb, desc); if (unlikely(ret)) return ret; - if (skb->ip_summed == CHECKSUM_PARTIAL) { - u8 ol4_proto, il4_proto; - - skb_reset_mac_len(skb); - - ret = hns3_get_l4_protocol(skb, &ol4_proto, &il4_proto); - if (unlikely(ret)) - return ret; - - ret = hns3_set_l2l3l4(skb, ol4_proto, il4_proto, - &type_cs_vlan_tso, - &ol_type_vlan_len_msec); - if (unlikely(ret)) - return ret; - - ret = hns3_set_tso(skb, &paylen, &mss, - &type_cs_vlan_tso); - if (unlikely(ret)) - return ret; - } - - /* Set txbd */ - desc->tx.ol_type_vlan_len_msec = - cpu_to_le32(ol_type_vlan_len_msec); - desc->tx.type_cs_vlan_tso_len = cpu_to_le32(type_cs_vlan_tso); - desc->tx.paylen = cpu_to_le32(paylen); - desc->tx.mss = cpu_to_le16(mss); - desc->tx.vlan_tag = cpu_to_le16(inner_vtag); - desc->tx.outer_vlan_tag = cpu_to_le16(out_vtag); - dma = dma_map_single(dev, skb->data, size, DMA_TO_DEVICE); } else { - frag = (struct skb_frag_struct *)priv; + frag = (skb_frag_t *)priv; dma = skb_frag_dma_map(dev, frag, 0, size, DMA_TO_DEVICE); } if (unlikely(dma_mapping_error(dev, dma))) { + u64_stats_update_begin(&ring->syncp); ring->stats.sw_err_cnt++; + u64_stats_update_end(&ring->syncp); return -ENOMEM; } @@ -1147,28 +1186,20 @@ static int hns3_fill_desc(struct hns3_enet_ring *ring, void *priv, return 0; } -static int hns3_nic_bd_num(struct sk_buff *skb) +static unsigned int hns3_nic_bd_num(struct sk_buff *skb) { - int size = skb_headlen(skb); - int i, bd_num; + unsigned int bd_num; + int i; /* if the total len is within the max bd limit */ if (likely(skb->len <= HNS3_MAX_BD_SIZE)) return skb_shinfo(skb)->nr_frags + 1; - bd_num = hns3_tx_bd_count(size); + bd_num = hns3_tx_bd_count(skb_headlen(skb)); for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; - int frag_bd_num; - - size = skb_frag_size(frag); - frag_bd_num = hns3_tx_bd_count(size); - - if (unlikely(frag_bd_num > HNS3_MAX_BD_PER_FRAG)) - return -ENOMEM; - - bd_num += frag_bd_num; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + bd_num += hns3_tx_bd_count(skb_frag_size(frag)); } return bd_num; @@ -1189,7 +1220,7 @@ static unsigned int hns3_gso_hdr_len(struct sk_buff *skb) */ static bool hns3_skb_need_linearized(struct sk_buff *skb) { - int bd_limit = HNS3_MAX_BD_PER_FRAG - 1; + int bd_limit = HNS3_MAX_BD_NUM_NORMAL - 1; unsigned int tot_len = 0; int i; @@ -1219,21 +1250,16 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring, struct sk_buff **out_skb) { struct sk_buff *skb = *out_skb; - int bd_num; + unsigned int bd_num; bd_num = hns3_nic_bd_num(skb); - if (bd_num < 0) - return bd_num; - - if (unlikely(bd_num > HNS3_MAX_BD_PER_FRAG)) { + if (unlikely(bd_num > HNS3_MAX_BD_NUM_NORMAL)) { struct sk_buff *new_skb; - if (skb_is_gso(skb) && !hns3_skb_need_linearized(skb)) + if (skb_is_gso(skb) && bd_num <= HNS3_MAX_BD_NUM_TSO && + !hns3_skb_need_linearized(skb)) goto out; - bd_num = hns3_tx_bd_count(skb->len); - if (unlikely(ring_space(ring) < bd_num)) - return -EBUSY; /* manual split the send packet */ new_skb = skb_copy(skb, GFP_ATOMIC); if (!new_skb) @@ -1241,6 +1267,11 @@ static int hns3_nic_maybe_stop_tx(struct hns3_enet_ring *ring, dev_kfree_skb_any(skb); *out_skb = new_skb; + bd_num = hns3_nic_bd_num(new_skb); + if ((skb_is_gso(new_skb) && bd_num > HNS3_MAX_BD_NUM_TSO) || + (!skb_is_gso(new_skb) && bd_num > HNS3_MAX_BD_NUM_NORMAL)) + return -ENOMEM; + u64_stats_update_begin(&ring->syncp); ring->stats.tx_copy++; u64_stats_update_end(&ring->syncp); @@ -1290,7 +1321,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) &tx_ring_data(priv, skb->queue_mapping); struct hns3_enet_ring *ring = ring_data->ring; struct netdev_queue *dev_queue; - struct skb_frag_struct *frag; + skb_frag_t *frag; int next_to_use_head; int buf_num; int seg_num; @@ -1314,9 +1345,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) u64_stats_update_end(&ring->syncp); } - if (net_ratelimit()) - netdev_err(netdev, "xmit error: %d!\n", buf_num); - + hns3_rl_err(netdev, "xmit error: %d!\n", buf_num); goto out_err_tx_ok; } @@ -1482,7 +1511,15 @@ static void hns3_nic_get_stats64(struct net_device *netdev, tx_bytes += ring->stats.tx_bytes; tx_pkts += ring->stats.tx_pkts; tx_drop += ring->stats.sw_err_cnt; + tx_drop += ring->stats.tx_vlan_err; + tx_drop += ring->stats.tx_l4_proto_err; + tx_drop += ring->stats.tx_l2l3l4_err; + tx_drop += ring->stats.tx_tso_err; tx_errors += ring->stats.sw_err_cnt; + tx_errors += ring->stats.tx_vlan_err; + tx_errors += ring->stats.tx_l4_proto_err; + tx_errors += ring->stats.tx_l2l3l4_err; + tx_errors += ring->stats.tx_tso_err; } while (u64_stats_fetch_retry_irq(&ring->syncp, start)); /* fetch the rx stats */ @@ -1550,6 +1587,8 @@ static int hns3_setup_tc(struct net_device *netdev, void *type_data) h = hns3_get_handle(netdev); kinfo = &h->kinfo; + netif_dbg(h, drv, netdev, "setup tc: num_tc=%u\n", tc); + return (kinfo->dcb_ops && kinfo->dcb_ops->setup_tc) ? kinfo->dcb_ops->setup_tc(h, tc, prio_tc) : -EOPNOTSUPP; } @@ -1593,6 +1632,10 @@ static int hns3_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, struct hnae3_handle *h = hns3_get_handle(netdev); int ret = -EIO; + netif_dbg(h, drv, netdev, + "set vf vlan: vf=%d, vlan=%u, qos=%u, vlan_proto=%u\n", + vf, vlan, qos, vlan_proto); + if (h->ae_algo->ops->set_vf_vlan_filter) ret = h->ae_algo->ops->set_vf_vlan_filter(h, vf, vlan, qos, vlan_proto); @@ -1611,6 +1654,9 @@ static int hns3_nic_change_mtu(struct net_device *netdev, int new_mtu) if (!h->ae_algo->ops->set_mtu) return -EOPNOTSUPP; + netif_dbg(h, drv, netdev, + "change mtu from %u to %d\n", netdev->mtu, new_mtu); + ret = h->ae_algo->ops->set_mtu(h, new_mtu); if (ret) netdev_err(netdev, "failed to change MTU in hardware %d\n", @@ -1680,15 +1726,12 @@ static bool hns3_get_tx_timeo_queue_info(struct net_device *ndev) /* When mac received many pause frames continuous, it's unable to send * packets, which may cause tx timeout */ - if (h->ae_algo->ops->update_stats && - h->ae_algo->ops->get_mac_pause_stats) { - u64 tx_pause_cnt, rx_pause_cnt; + if (h->ae_algo->ops->get_mac_stats) { + struct hns3_mac_stats mac_stats; - h->ae_algo->ops->update_stats(h, &ndev->stats); - h->ae_algo->ops->get_mac_pause_stats(h, &tx_pause_cnt, - &rx_pause_cnt); + h->ae_algo->ops->get_mac_stats(h, &mac_stats); netdev_info(ndev, "tx_pause_cnt: %llu, rx_pause_cnt: %llu\n", - tx_pause_cnt, rx_pause_cnt); + mac_stats.tx_pause_cnt, mac_stats.rx_pause_cnt); } hw_head = readl_relaxed(tx_ring->tqp->io_base + @@ -1963,7 +2006,8 @@ static pci_ers_result_t hns3_slot_reset(struct pci_dev *pdev) ops = ae_dev->ops; /* request the reset */ - if (ops->reset_event) { + if (ops->reset_event && ops->get_reset_level && + ops->set_default_reset_request) { if (ae_dev->hw_err_reset_req) { reset_type = ops->get_reset_level(ae_dev, &ae_dev->hw_err_reset_req); @@ -2067,7 +2111,7 @@ static void hns3_set_default_feature(struct net_device *netdev) static int hns3_alloc_buffer(struct hns3_enet_ring *ring, struct hns3_desc_cb *cb) { - unsigned int order = hnae3_page_order(ring); + unsigned int order = hns3_page_order(ring); struct page *p; p = dev_alloc_pages(order); @@ -2078,7 +2122,7 @@ static int hns3_alloc_buffer(struct hns3_enet_ring *ring, cb->page_offset = 0; cb->reuse_flag = 0; cb->buf = page_address(p); - cb->length = hnae3_page_size(ring); + cb->length = hns3_page_size(ring); cb->type = DESC_TYPE_PAGE; return 0; @@ -2357,8 +2401,9 @@ static void hns3_nic_alloc_rx_buffers(struct hns3_enet_ring *ring, ring->stats.sw_err_cnt++; u64_stats_update_end(&ring->syncp); - netdev_err(ring->tqp->handle->kinfo.netdev, - "hnae reserve buffer map failed.\n"); + hns3_rl_err(ring->tqp_vector->napi.dev, + "alloc rx buffer failed: %d\n", + ret); break; } hns3_replace_buffer(ring, ring->next_to_use, &res_cbs); @@ -2381,7 +2426,7 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i, { struct hns3_desc *desc = &ring->desc[ring->next_to_clean]; int size = le16_to_cpu(desc->rx.size); - u32 truesize = hnae3_buf_size(ring); + u32 truesize = hns3_buf_size(ring); skb_add_rx_frag(skb, i, desc_cb->priv, desc_cb->page_offset + pull_len, size - pull_len, truesize); @@ -2396,7 +2441,7 @@ static void hns3_nic_reuse_page(struct sk_buff *skb, int i, /* Move offset up to the next cache line */ desc_cb->page_offset += truesize; - if (desc_cb->page_offset + truesize <= hnae3_page_size(ring)) { + if (desc_cb->page_offset + truesize <= hns3_page_size(ring)) { desc_cb->reuse_flag = 1; /* Bump ref count on page before it is given */ get_page(desc_cb->priv); @@ -2443,9 +2488,9 @@ static int hns3_gro_complete(struct sk_buff *skb, u32 l234info) th->check = ~tcp_v6_check(skb->len - depth, &iph->saddr, &iph->daddr, 0); } else { - netdev_err(skb->dev, - "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n", - be16_to_cpu(type), depth); + hns3_rl_err(skb->dev, + "Error: FW GRO supports only IPv4/IPv6, not 0x%04x, depth: %d\n", + be16_to_cpu(type), depth); return -EFAULT; } @@ -2587,7 +2632,7 @@ static int hns3_alloc_skb(struct hns3_enet_ring *ring, unsigned int length, ring->skb = napi_alloc_skb(&ring->tqp_vector->napi, HNS3_RX_HEAD_SIZE); skb = ring->skb; if (unlikely(!skb)) { - netdev_err(netdev, "alloc rx skb fail\n"); + hns3_rl_err(netdev, "alloc rx skb fail\n"); u64_stats_update_begin(&ring->syncp); ring->stats.sw_err_cnt++; @@ -2662,8 +2707,8 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc, new_skb = napi_alloc_skb(&ring->tqp_vector->napi, HNS3_RX_HEAD_SIZE); if (unlikely(!new_skb)) { - netdev_err(ring->tqp->handle->kinfo.netdev, - "alloc rx skb frag fail\n"); + hns3_rl_err(ring->tqp_vector->napi.dev, + "alloc rx fraglist skb fail\n"); return -ENXIO; } ring->frag_num = 0; @@ -2678,7 +2723,7 @@ static int hns3_add_frag(struct hns3_enet_ring *ring, struct hns3_desc *desc, } if (ring->tail_skb) { - head_skb->truesize += hnae3_buf_size(ring); + head_skb->truesize += hns3_buf_size(ring); head_skb->data_len += le16_to_cpu(desc->rx.size); head_skb->len += le16_to_cpu(desc->rx.size); skb = ring->tail_skb; @@ -2895,24 +2940,22 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, void (*rx_fn)(struct hns3_enet_ring *, struct sk_buff *)) { #define RCB_NOF_ALLOC_RX_BUFF_ONCE 16 - int recv_pkts, recv_bds, clean_count, err; int unused_count = hns3_desc_unused(ring); struct sk_buff *skb = ring->skb; - int num; + int recv_pkts = 0; + int recv_bds = 0; + int err, num; num = readl_relaxed(ring->tqp->io_base + HNS3_RING_RX_RING_FBDNUM_REG); rmb(); /* Make sure num taken effect before the other data is touched */ - recv_pkts = 0, recv_bds = 0, clean_count = 0; num -= unused_count; unused_count -= ring->pending_buf; while (recv_pkts < budget && recv_bds < num) { /* Reuse or realloc buffers */ - if (clean_count + unused_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) { - hns3_nic_alloc_rx_buffers(ring, - clean_count + unused_count); - clean_count = 0; + if (unused_count >= RCB_NOF_ALLOC_RX_BUFF_ONCE) { + hns3_nic_alloc_rx_buffers(ring, unused_count); unused_count = hns3_desc_unused(ring) - ring->pending_buf; } @@ -2926,7 +2969,7 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, goto out; } else if (unlikely(err)) { /* Do jump the err */ recv_bds += ring->pending_buf; - clean_count += ring->pending_buf; + unused_count += ring->pending_buf; ring->skb = NULL; ring->pending_buf = 0; continue; @@ -2934,7 +2977,7 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, rx_fn(ring, skb); recv_bds += ring->pending_buf; - clean_count += ring->pending_buf; + unused_count += ring->pending_buf; ring->skb = NULL; ring->pending_buf = 0; @@ -2943,8 +2986,8 @@ int hns3_clean_rx_ring(struct hns3_enet_ring *ring, int budget, out: /* Make all data has been write before submit */ - if (clean_count + unused_count > 0) - hns3_nic_alloc_rx_buffers(ring, clean_count + unused_count); + if (unused_count > 0) + hns3_nic_alloc_rx_buffers(ring, unused_count); return recv_pkts; } @@ -3574,7 +3617,7 @@ out: return ret; } -static void hns3_fini_ring(struct hns3_enet_ring *ring) +void hns3_fini_ring(struct hns3_enet_ring *ring) { hns3_free_desc(ring); devm_kfree(ring_to_dev(ring), ring->desc_cb); @@ -4165,8 +4208,8 @@ int hns3_nic_reset_all_ring(struct hnae3_handle *h) static void hns3_store_coal(struct hns3_nic_priv *priv) { /* ethtool only support setting and querying one coal - * configuation for now, so save the vector 0' coal - * configuation here in order to restore it. + * configuration for now, so save the vector 0' coal + * configuration here in order to restore it. */ memcpy(&priv->tx_coal, &priv->tqp_vector[0].tx_group.coal, sizeof(struct hns3_enet_coalesce)); @@ -4368,6 +4411,30 @@ static int hns3_reset_notify(struct hnae3_handle *handle, return ret; } +static int hns3_change_channels(struct hnae3_handle *handle, u32 new_tqp_num, + bool rxfh_configured) +{ + int ret; + + ret = handle->ae_algo->ops->set_channels(handle, new_tqp_num, + rxfh_configured); + if (ret) { + dev_err(&handle->pdev->dev, + "Change tqp num(%u) fail.\n", new_tqp_num); + return ret; + } + + ret = hns3_reset_notify(handle, HNAE3_INIT_CLIENT); + if (ret) + return ret; + + ret = hns3_reset_notify(handle, HNAE3_UP_CLIENT); + if (ret) + hns3_reset_notify(handle, HNAE3_UNINIT_CLIENT); + + return ret; +} + int hns3_set_channels(struct net_device *netdev, struct ethtool_channels *ch) { @@ -4378,6 +4445,9 @@ int hns3_set_channels(struct net_device *netdev, u16 org_tqp_num; int ret; + if (hns3_nic_resetting(netdev)) + return -EBUSY; + if (ch->rx_count || ch->tx_count) return -EINVAL; @@ -4392,6 +4462,10 @@ int hns3_set_channels(struct net_device *netdev, if (kinfo->rss_size == new_tqp_num) return 0; + netif_dbg(h, drv, netdev, + "set channels: tqp_num=%u, rxfh=%d\n", + new_tqp_num, rxfh_configured); + ret = hns3_reset_notify(h, HNAE3_DOWN_CLIENT); if (ret) return ret; @@ -4401,24 +4475,46 @@ int hns3_set_channels(struct net_device *netdev, return ret; org_tqp_num = h->kinfo.num_tqps; - ret = h->ae_algo->ops->set_channels(h, new_tqp_num, rxfh_configured); + ret = hns3_change_channels(h, new_tqp_num, rxfh_configured); if (ret) { - ret = h->ae_algo->ops->set_channels(h, org_tqp_num, - rxfh_configured); - if (ret) { - /* If revert to old tqp failed, fatal error occurred */ - dev_err(&netdev->dev, - "Revert to old tqp num fail, ret=%d", ret); - return ret; + int ret1; + + netdev_warn(netdev, + "Change channels fail, revert to old value\n"); + ret1 = hns3_change_channels(h, org_tqp_num, rxfh_configured); + if (ret1) { + netdev_err(netdev, + "revert to old channel fail\n"); + return ret1; } - dev_info(&netdev->dev, - "Change tqp num fail, Revert to old tqp num"); - } - ret = hns3_reset_notify(h, HNAE3_INIT_CLIENT); - if (ret) + return ret; + } + + return 0; +} + +static const struct hns3_hw_error_info hns3_hw_err[] = { + { .type = HNAE3_PPU_POISON_ERROR, + .msg = "PPU poison" }, + { .type = HNAE3_CMDQ_ECC_ERROR, + .msg = "IMP CMDQ error" }, + { .type = HNAE3_IMP_RD_POISON_ERROR, + .msg = "IMP RD poison" }, +}; - return hns3_reset_notify(h, HNAE3_UP_CLIENT); +static void hns3_process_hw_error(struct hnae3_handle *handle, + enum hnae3_hw_error_type type) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(hns3_hw_err); i++) { + if (hns3_hw_err[i].type == type) { + dev_err(&handle->pdev->dev, "Detected %s!\n", + hns3_hw_err[i].msg); + break; + } + } } static const struct hnae3_client_ops client_ops = { @@ -4427,6 +4523,7 @@ static const struct hnae3_client_ops client_ops = { .link_status_change = hns3_link_status_change, .setup_tc = hns3_client_setup_tc, .reset_notify = hns3_reset_notify, + .process_hw_error = hns3_process_hw_error, }; /* hns3_init_module - Driver registration routine diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index 848b866761df..2110fa3b4479 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -75,7 +75,7 @@ enum hns3_nic_state { #define HNS3_TX_TIMEOUT (5 * HZ) #define HNS3_RING_NAME_LEN 16 #define HNS3_BUFFER_SIZE_2048 2048 -#define HNS3_RING_MAX_PENDING 32768 +#define HNS3_RING_MAX_PENDING 32760 #define HNS3_RING_MIN_PENDING 24 #define HNS3_RING_BD_MULTIPLE 8 /* max frame size of mac */ @@ -195,7 +195,8 @@ enum hns3_nic_state { #define HNS3_VECTOR_INITED 1 #define HNS3_MAX_BD_SIZE 65535 -#define HNS3_MAX_BD_PER_FRAG 8 +#define HNS3_MAX_BD_NUM_NORMAL 8 +#define HNS3_MAX_BD_NUM_TSO 63 #define HNS3_MAX_BD_PER_PKT MAX_SKB_FRAGS #define HNS3_VECTOR_GL0_OFFSET 0x100 @@ -301,7 +302,7 @@ struct hns3_desc_cb { dma_addr_t dma; /* dma address of this desc */ void *buf; /* cpu addr for a desc */ - /* priv data for the desc, e.g. skb when use with ip stack*/ + /* priv data for the desc, e.g. skb when use with ip stack */ void *priv; u32 page_offset; u32 length; /* length of the buffer */ @@ -324,11 +325,11 @@ enum hns3_pkt_l3type { HNS3_L3_TYPE_MAC_PAUSE, HNS3_L3_TYPE_PFC_PAUSE,/* 0x9*/ - /* reserved for 0xA~0xB*/ + /* reserved for 0xA~0xB */ HNS3_L3_TYPE_CNM = 0xc, - /* reserved for 0xD~0xE*/ + /* reserved for 0xD~0xE */ HNS3_L3_TYPE_PARSE_FAIL = 0xf /* must be last */ }; @@ -353,7 +354,7 @@ enum hns3_pkt_ol3type { HNS3_OL3_TYPE_IPV4_OPT = 4, HNS3_OL3_TYPE_IPV6_EXT, - /* reserved for 0x6~0xE*/ + /* reserved for 0x6~0xE */ HNS3_OL3_TYPE_PARSE_FAIL = 0xf /* must be last */ }; @@ -377,6 +378,10 @@ struct ring_stats { u64 restart_queue; u64 tx_busy; u64 tx_copy; + u64 tx_vlan_err; + u64 tx_l4_proto_err; + u64 tx_l2l3l4_err; + u64 tx_tso_err; }; struct { u64 rx_pkts; @@ -547,6 +552,11 @@ union l4_hdr_info { unsigned char *hdr; }; +struct hns3_hw_error_info { + enum hnae3_hw_error_type type; + const char *msg; +}; + static inline int ring_space(struct hns3_enet_ring *ring) { /* This smp_load_acquire() pairs with smp_store_release() in @@ -608,9 +618,18 @@ static inline bool hns3_nic_resetting(struct net_device *netdev) #define tx_ring_data(priv, idx) ((priv)->ring_data[idx]) -#define hnae3_buf_size(_ring) ((_ring)->buf_size) -#define hnae3_page_order(_ring) (get_order(hnae3_buf_size(_ring))) -#define hnae3_page_size(_ring) (PAGE_SIZE << (u32)hnae3_page_order(_ring)) +#define hns3_buf_size(_ring) ((_ring)->buf_size) + +static inline unsigned int hns3_page_order(struct hns3_enet_ring *ring) +{ +#if (PAGE_SIZE < 8192) + if (ring->buf_size > (PAGE_SIZE / 2)) + return 1; +#endif + return 0; +} + +#define hns3_page_size(_ring) (PAGE_SIZE << hns3_page_order(_ring)) /* iterator for handling rings in ring group */ #define hns3_for_each_ring(pos, head) \ @@ -633,6 +652,7 @@ void hns3_clean_tx_ring(struct hns3_enet_ring *ring); int hns3_init_all_ring(struct hns3_nic_priv *priv); int hns3_uninit_all_ring(struct hns3_nic_priv *priv); int hns3_nic_reset_all_ring(struct hnae3_handle *h); +void hns3_fini_ring(struct hns3_enet_ring *ring); netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev); bool hns3_is_phys_func(struct pci_dev *pdev); int hns3_clean_rx_ring( diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index 5bff98a9b0dc..680c3508876d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -30,6 +30,10 @@ static const struct hns3_stats hns3_txq_stats[] = { HNS3_TQP_STAT("wake", restart_queue), HNS3_TQP_STAT("busy", tx_busy), HNS3_TQP_STAT("copy", tx_copy), + HNS3_TQP_STAT("vlan_err", tx_vlan_err), + HNS3_TQP_STAT("l4_proto_err", tx_l4_proto_err), + HNS3_TQP_STAT("l2l3l4_err", tx_l2l3l4_err), + HNS3_TQP_STAT("tso_err", tx_tso_err), }; #define HNS3_TXQ_STATS_COUNT ARRAY_SIZE(hns3_txq_stats) @@ -55,7 +59,7 @@ static const struct hns3_stats hns3_rxq_stats[] = { #define HNS3_TQP_STATS_COUNT (HNS3_TXQ_STATS_COUNT + HNS3_RXQ_STATS_COUNT) -#define HNS3_SELF_TEST_TYPE_NUM 3 +#define HNS3_SELF_TEST_TYPE_NUM 4 #define HNS3_NIC_LB_TEST_PKT_NUM 1 #define HNS3_NIC_LB_TEST_RING_ID 0 #define HNS3_NIC_LB_TEST_PACKET_SIZE 128 @@ -85,6 +89,7 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en) case HNAE3_LOOP_SERIAL_SERDES: case HNAE3_LOOP_PARALLEL_SERDES: case HNAE3_LOOP_APP: + case HNAE3_LOOP_PHY: ret = h->ae_algo->ops->set_loopback(h, loop, en); break; default: @@ -92,7 +97,7 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en) break; } - if (ret) + if (ret || h->pdev->revision >= 0x21) return ret; if (en) { @@ -139,7 +144,10 @@ static int hns3_lp_down(struct net_device *ndev, enum hnae3_loop loop_mode) static void hns3_lp_setup_skb(struct sk_buff *skb) { +#define HNS3_NIC_LB_DST_MAC_ADDR 0x1f + struct net_device *ndev = skb->dev; + struct hnae3_handle *handle; unsigned char *packet; struct ethhdr *ethh; unsigned int i; @@ -155,7 +163,9 @@ static void hns3_lp_setup_skb(struct sk_buff *skb) * before the packet reaches mac or serdes, which will defect * the purpose of mac or serdes selftest. */ - ethh->h_dest[5] += 0x1f; + handle = hns3_get_handle(ndev); + if (handle->pdev->revision == 0x20) + ethh->h_dest[5] += HNS3_NIC_LB_DST_MAC_ADDR; eth_zero_addr(ethh->h_source); ethh->h_proto = htons(ETH_P_ARP); skb_reset_mac_header(skb); @@ -311,6 +321,8 @@ static void hns3_self_test(struct net_device *ndev, if (eth_test->flags != ETH_TEST_FL_OFFLINE) return; + netif_dbg(h, drv, ndev, "self test start"); + st_param[HNAE3_LOOP_APP][0] = HNAE3_LOOP_APP; st_param[HNAE3_LOOP_APP][1] = h->flags & HNAE3_SUPPORT_APP_LOOPBACK; @@ -324,6 +336,10 @@ static void hns3_self_test(struct net_device *ndev, st_param[HNAE3_LOOP_PARALLEL_SERDES][1] = h->flags & HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK; + st_param[HNAE3_LOOP_PHY][0] = HNAE3_LOOP_PHY; + st_param[HNAE3_LOOP_PHY][1] = + h->flags & HNAE3_SUPPORT_PHY_LOOPBACK; + if (if_running) ndev->netdev_ops->ndo_stop(ndev); @@ -374,6 +390,8 @@ static void hns3_self_test(struct net_device *ndev, if (if_running) ndev->netdev_ops->ndo_open(ndev); + + netif_dbg(h, drv, ndev, "self test end\n"); } static int hns3_get_sset_count(struct net_device *netdev, int stringset) @@ -527,6 +545,7 @@ static void hns3_get_drvinfo(struct net_device *netdev, { struct hns3_nic_priv *priv = netdev_priv(netdev); struct hnae3_handle *h = priv->ae_handle; + u32 fw_version; if (!h->ae_algo->ops->get_fw_version) { netdev_err(netdev, "could not get fw version!\n"); @@ -545,8 +564,18 @@ static void hns3_get_drvinfo(struct net_device *netdev, sizeof(drvinfo->bus_info)); drvinfo->bus_info[ETHTOOL_BUSINFO_LEN - 1] = '\0'; - snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), "0x%08x", - priv->ae_handle->ae_algo->ops->get_fw_version(h)); + fw_version = priv->ae_handle->ae_algo->ops->get_fw_version(h); + + snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), + "%lu.%lu.%lu.%lu", + hnae3_get_field(fw_version, HNAE3_FW_VERSION_BYTE3_MASK, + HNAE3_FW_VERSION_BYTE3_SHIFT), + hnae3_get_field(fw_version, HNAE3_FW_VERSION_BYTE2_MASK, + HNAE3_FW_VERSION_BYTE2_SHIFT), + hnae3_get_field(fw_version, HNAE3_FW_VERSION_BYTE1_MASK, + HNAE3_FW_VERSION_BYTE1_SHIFT), + hnae3_get_field(fw_version, HNAE3_FW_VERSION_BYTE0_MASK, + HNAE3_FW_VERSION_BYTE0_SHIFT)); } static u32 hns3_get_link(struct net_device *netdev) @@ -593,6 +622,10 @@ static int hns3_set_pauseparam(struct net_device *netdev, { struct hnae3_handle *h = hns3_get_handle(netdev); + netif_dbg(h, drv, netdev, + "set pauseparam: autoneg=%u, rx:%u, tx:%u\n", + param->autoneg, param->rx_pause, param->tx_pause); + if (h->ae_algo->ops->set_pauseparam) return h->ae_algo->ops->set_pauseparam(h, param->autoneg, param->rx_pause, @@ -612,7 +645,7 @@ static void hns3_get_ksettings(struct hnae3_handle *h, &cmd->base.speed, &cmd->base.duplex); - /* 2.get link mode*/ + /* 2.get link mode */ if (ops->get_link_mode) ops->get_link_mode(h, cmd->link_modes.supported, @@ -681,7 +714,7 @@ static int hns3_get_link_ksettings(struct net_device *netdev, return 0; } -static int hns3_check_ksettings_param(struct net_device *netdev, +static int hns3_check_ksettings_param(const struct net_device *netdev, const struct ethtool_link_ksettings *cmd) { struct hnae3_handle *handle = hns3_get_handle(netdev); @@ -693,6 +726,12 @@ static int hns3_check_ksettings_param(struct net_device *netdev, u8 duplex; int ret; + /* hw doesn't support use specified speed and duplex to negotiate, + * unnecessary to check them when autoneg on. + */ + if (cmd->base.autoneg) + return 0; + if (ops->get_ksettings_an_result) { ops->get_ksettings_an_result(handle, &autoneg, &speed, &duplex); if (cmd->base.autoneg == autoneg && cmd->base.speed == speed && @@ -726,12 +765,17 @@ static int hns3_set_link_ksettings(struct net_device *netdev, { struct hnae3_handle *handle = hns3_get_handle(netdev); const struct hnae3_ae_ops *ops = handle->ae_algo->ops; - int ret = 0; + int ret; /* Chip don't support this mode. */ if (cmd->base.speed == SPEED_1000 && cmd->base.duplex == DUPLEX_HALF) return -EINVAL; + netif_dbg(handle, drv, netdev, + "set link(%s): autoneg=%u, speed=%u, duplex=%u\n", + netdev->phydev ? "phy" : "mac", + cmd->base.autoneg, cmd->base.speed, cmd->base.duplex); + /* Only support ksettings_set for netdev with phy attached for now */ if (netdev->phydev) return phy_ethtool_ksettings_set(netdev->phydev, cmd); @@ -749,6 +793,15 @@ static int hns3_set_link_ksettings(struct net_device *netdev, return ret; } + /* hw doesn't support use specified speed and duplex to negotiate, + * ignore them when autoneg on. + */ + if (cmd->base.autoneg) { + netdev_info(netdev, + "autoneg is on, ignore the speed and duplex\n"); + return 0; + } + if (ops->cfg_mac_speed_dup_h) ret = ops->cfg_mac_speed_dup_h(handle, cmd->base.speed, cmd->base.duplex); @@ -843,8 +896,8 @@ static int hns3_get_rxnfc(struct net_device *netdev, } } -static int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, - u32 tx_desc_num, u32 rx_desc_num) +static void hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, + u32 tx_desc_num, u32 rx_desc_num) { struct hnae3_handle *h = priv->ae_handle; int i; @@ -857,21 +910,31 @@ static int hns3_change_all_ring_bd_num(struct hns3_nic_priv *priv, priv->ring_data[i + h->kinfo.num_tqps].ring->desc_num = rx_desc_num; } - - return hns3_init_all_ring(priv); } -static int hns3_set_ringparam(struct net_device *ndev, - struct ethtool_ringparam *param) +static struct hns3_enet_ring *hns3_backup_ringparam(struct hns3_nic_priv *priv) { - struct hns3_nic_priv *priv = netdev_priv(ndev); - struct hnae3_handle *h = priv->ae_handle; - bool if_running = netif_running(ndev); - u32 old_tx_desc_num, new_tx_desc_num; - u32 old_rx_desc_num, new_rx_desc_num; - int queue_num = h->kinfo.num_tqps; - int ret; + struct hnae3_handle *handle = priv->ae_handle; + struct hns3_enet_ring *tmp_rings; + int i; + + tmp_rings = kcalloc(handle->kinfo.num_tqps * 2, + sizeof(struct hns3_enet_ring), GFP_KERNEL); + if (!tmp_rings) + return NULL; + + for (i = 0; i < handle->kinfo.num_tqps * 2; i++) { + memcpy(&tmp_rings[i], priv->ring_data[i].ring, + sizeof(struct hns3_enet_ring)); + tmp_rings[i].skb = NULL; + } + + return tmp_rings; +} +static int hns3_check_ringparam(struct net_device *ndev, + struct ethtool_ringparam *param) +{ if (hns3_nic_resetting(ndev)) return -EBUSY; @@ -887,6 +950,25 @@ static int hns3_set_ringparam(struct net_device *ndev, return -EINVAL; } + return 0; +} + +static int hns3_set_ringparam(struct net_device *ndev, + struct ethtool_ringparam *param) +{ + struct hns3_nic_priv *priv = netdev_priv(ndev); + struct hnae3_handle *h = priv->ae_handle; + struct hns3_enet_ring *tmp_rings; + bool if_running = netif_running(ndev); + u32 old_tx_desc_num, new_tx_desc_num; + u32 old_rx_desc_num, new_rx_desc_num; + u16 queue_num = h->kinfo.num_tqps; + int ret, i; + + ret = hns3_check_ringparam(ndev, param); + if (ret) + return ret; + /* Hardware requires that its descriptors must be multiple of eight */ new_tx_desc_num = ALIGN(param->tx_pending, HNS3_RING_BD_MULTIPLE); new_rx_desc_num = ALIGN(param->rx_pending, HNS3_RING_BD_MULTIPLE); @@ -896,6 +978,13 @@ static int hns3_set_ringparam(struct net_device *ndev, old_rx_desc_num == new_rx_desc_num) return 0; + tmp_rings = hns3_backup_ringparam(priv); + if (!tmp_rings) { + netdev_err(ndev, + "backup ring param failed by allocating memory fail\n"); + return -ENOMEM; + } + netdev_info(ndev, "Changing Tx/Rx ring depth from %d/%d to %d/%d\n", old_tx_desc_num, old_rx_desc_num, @@ -904,22 +993,24 @@ static int hns3_set_ringparam(struct net_device *ndev, if (if_running) ndev->netdev_ops->ndo_stop(ndev); - ret = hns3_uninit_all_ring(priv); - if (ret) - return ret; - - ret = hns3_change_all_ring_bd_num(priv, new_tx_desc_num, - new_rx_desc_num); + hns3_change_all_ring_bd_num(priv, new_tx_desc_num, new_rx_desc_num); + ret = hns3_init_all_ring(priv); if (ret) { - ret = hns3_change_all_ring_bd_num(priv, old_tx_desc_num, - old_rx_desc_num); - if (ret) { - netdev_err(ndev, - "Revert to old bd num fail, ret=%d.\n", ret); - return ret; - } + netdev_err(ndev, "Change bd num fail, revert to old value(%d)\n", + ret); + + hns3_change_all_ring_bd_num(priv, old_tx_desc_num, + old_rx_desc_num); + for (i = 0; i < h->kinfo.num_tqps * 2; i++) + memcpy(priv->ring_data[i].ring, &tmp_rings[i], + sizeof(struct hns3_enet_ring)); + } else { + for (i = 0; i < h->kinfo.num_tqps * 2; i++) + hns3_fini_ring(&tmp_rings[i]); } + kfree(tmp_rings); + if (if_running) ret = ndev->netdev_ops->ndo_open(ndev); @@ -973,6 +1064,9 @@ static int hns3_nway_reset(struct net_device *netdev) return -EINVAL; } + netif_dbg(handle, drv, netdev, + "nway reset (using %s)\n", phy ? "phy" : "mac"); + if (phy) return genphy_restart_aneg(phy); @@ -1297,6 +1391,9 @@ static int hns3_set_fecparam(struct net_device *netdev, if (!ops->set_fec) return -EOPNOTSUPP; fec_mode = eth_to_loc_fec(fec->fec); + + netif_dbg(handle, drv, netdev, "set fecparam: mode=%u\n", fec_mode); + return ops->set_fec(handle, fec_mode); } @@ -1315,6 +1412,7 @@ static const struct ethtool_ops hns3vf_ethtool_ops = { .set_rxfh = hns3_set_rss, .get_link_ksettings = hns3_get_link_ksettings, .get_channels = hns3_get_channels, + .set_channels = hns3_set_channels, .get_coalesce = hns3_get_coalesce, .set_coalesce = hns3_set_coalesce, .get_regs_len = hns3_get_regs_len, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index 22f6acd45d9a..ecf58cfd253d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -103,14 +103,17 @@ static void hclge_cmd_config_regs(struct hclge_cmq_ring *ring) dma_addr_t dma = ring->desc_dma_addr; struct hclge_dev *hdev = ring->dev; struct hclge_hw *hw = &hdev->hw; + u32 reg_val; if (ring->ring_type == HCLGE_TYPE_CSQ) { hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_L_REG, lower_32_bits(dma)); hclge_write_dev(hw, HCLGE_NIC_CSQ_BASEADDR_H_REG, upper_32_bits(dma)); - hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG, - ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S); + reg_val = hclge_read_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG); + reg_val &= HCLGE_NIC_SW_RST_RDY; + reg_val |= ring->desc_num >> HCLGE_NIC_CMQ_DESC_NUM_S; + hclge_write_dev(hw, HCLGE_NIC_CSQ_DEPTH_REG, reg_val); hclge_write_dev(hw, HCLGE_NIC_CSQ_HEAD_REG, 0); hclge_write_dev(hw, HCLGE_NIC_CSQ_TAIL_REG, 0); } else { @@ -383,6 +386,23 @@ err_csq: return ret; } +static int hclge_firmware_compat_config(struct hclge_dev *hdev) +{ + struct hclge_firmware_compat_cmd *req; + struct hclge_desc desc; + u32 compat = 0; + + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_M7_COMPAT_CFG, false); + + req = (struct hclge_firmware_compat_cmd *)desc.data; + + hnae3_set_bit(compat, HCLGE_LINK_EVENT_REPORT_EN_B, 1); + hnae3_set_bit(compat, HCLGE_NCSI_ERROR_REPORT_EN_B, 1); + req->compat = cpu_to_le32(compat); + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + int hclge_cmd_init(struct hclge_dev *hdev) { u32 version; @@ -419,7 +439,24 @@ int hclge_cmd_init(struct hclge_dev *hdev) } hdev->fw_version = version; - dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version); + dev_info(&hdev->pdev->dev, "The firmware version is %lu.%lu.%lu.%lu\n", + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE3_MASK, + HNAE3_FW_VERSION_BYTE3_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE2_MASK, + HNAE3_FW_VERSION_BYTE2_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE1_MASK, + HNAE3_FW_VERSION_BYTE1_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE0_MASK, + HNAE3_FW_VERSION_BYTE0_SHIFT)); + + /* ask the firmware to enable some features, driver can work without + * it. + */ + ret = hclge_firmware_compat_config(hdev); + if (ret) + dev_warn(&hdev->pdev->dev, + "Firmware compatible features not enabled(%d).\n", + ret); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h index 96840d8f3e24..4821fe08b5e4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.h @@ -86,6 +86,8 @@ enum hclge_opcode_type { HCLGE_OPC_QUERY_PF_RSRC = 0x0023, HCLGE_OPC_QUERY_VF_RSRC = 0x0024, HCLGE_OPC_GET_CFG_PARAM = 0x0025, + HCLGE_OPC_PF_RST_DONE = 0x0026, + HCLGE_OPC_QUERY_VF_RST_RDY = 0x0027, HCLGE_OPC_STATS_64_BIT = 0x0030, HCLGE_OPC_STATS_32_BIT = 0x0031, @@ -221,6 +223,9 @@ enum hclge_opcode_type { HCLGE_OPC_MAC_ETHTYPE_ADD = 0x1010, HCLGE_OPC_MAC_ETHTYPE_REMOVE = 0x1011, + /* MAC VLAN commands */ + HCLGE_OPC_MAC_VLAN_SWITCH_PARAM = 0x1033, + /* VLAN commands */ HCLGE_OPC_VLAN_FILTER_CTRL = 0x1100, HCLGE_OPC_VLAN_FILTER_PF_CFG = 0x1101, @@ -257,6 +262,7 @@ enum hclge_opcode_type { /* M7 stats command */ HCLGE_OPC_M7_STATS_BD = 0x7012, HCLGE_OPC_M7_STATS_INFO = 0x7013, + HCLGE_OPC_M7_COMPAT_CFG = 0x701A, /* SFP command */ HCLGE_OPC_GET_SFP_INFO = 0x7104, @@ -586,6 +592,12 @@ struct hclge_config_mac_mode_cmd { u8 rsv[20]; }; +struct hclge_pf_rst_sync_cmd { +#define HCLGE_PF_RST_ALL_VF_RDY_B 0 + u8 all_vf_ready; + u8 rsv[23]; +}; + #define HCLGE_CFG_SPEED_S 0 #define HCLGE_CFG_SPEED_M GENMASK(5, 0) @@ -762,6 +774,31 @@ struct hclge_vlan_filter_vf_cfg_cmd { u8 vf_bitmap[16]; }; +#define HCLGE_SWITCH_ANTI_SPOOF_B 0U +#define HCLGE_SWITCH_ALW_LPBK_B 1U +#define HCLGE_SWITCH_ALW_LCL_LPBK_B 2U +#define HCLGE_SWITCH_ALW_DST_OVRD_B 3U +#define HCLGE_SWITCH_NO_MASK 0x0 +#define HCLGE_SWITCH_ANTI_SPOOF_MASK 0xFE +#define HCLGE_SWITCH_ALW_LPBK_MASK 0xFD +#define HCLGE_SWITCH_ALW_LCL_LPBK_MASK 0xFB +#define HCLGE_SWITCH_LW_DST_OVRD_MASK 0xF7 + +struct hclge_mac_vlan_switch_cmd { + u8 roce_sel; + u8 rsv1[3]; + __le32 func_id; + u8 switch_param; + u8 rsv2[3]; + u8 param_mask; + u8 rsv3[11]; +}; + +enum hclge_mac_vlan_cfg_sel { + HCLGE_MAC_VLAN_NIC_SEL = 0, + HCLGE_MAC_VLAN_ROCE_SEL, +}; + #define HCLGE_ACCEPT_TAG1_B 0 #define HCLGE_ACCEPT_UNTAG1_B 1 #define HCLGE_PORT_INS_TAG1_EN_B 2 @@ -827,7 +864,7 @@ struct hclge_mac_ethertype_idx_rd_cmd { u8 flags; u8 resp_code; __le16 vlan_tag; - u8 mac_add[6]; + u8 mac_addr[6]; __le16 index; __le16 ethter_type; __le16 egress_port; @@ -877,6 +914,13 @@ struct hclge_reset_cmd { u8 rsv[22]; }; +#define HCLGE_PF_RESET_DONE_BIT BIT(0) + +struct hclge_pf_rst_done_cmd { + u8 pf_rst_done; + u8 rsv[23]; +}; + #define HCLGE_CMD_SERDES_SERIAL_INNER_LOOP_B BIT(0) #define HCLGE_CMD_SERDES_PARALLEL_INNER_LOOP_B BIT(2) #define HCLGE_CMD_SERDES_DONE_B BIT(0) @@ -906,8 +950,11 @@ struct hclge_serdes_lb_cmd { #define HCLGE_NIC_CRQ_DEPTH_REG 0x27020 #define HCLGE_NIC_CRQ_TAIL_REG 0x27024 #define HCLGE_NIC_CRQ_HEAD_REG 0x27028 -#define HCLGE_NIC_CMQ_EN_B 16 -#define HCLGE_NIC_CMQ_ENABLE BIT(HCLGE_NIC_CMQ_EN_B) + +/* this bit indicates that the driver is ready for hardware reset */ +#define HCLGE_NIC_SW_RST_RDY_B 16 +#define HCLGE_NIC_SW_RST_RDY BIT(HCLGE_NIC_SW_RST_RDY_B) + #define HCLGE_NIC_CMQ_DESC_NUM 1024 #define HCLGE_NIC_CMQ_DESC_NUM_S 3 @@ -1009,6 +1056,13 @@ struct hclge_query_ppu_pf_other_int_dfx_cmd { u8 rsv[4]; }; +#define HCLGE_LINK_EVENT_REPORT_EN_B 0 +#define HCLGE_NCSI_ERROR_REPORT_EN_B 1 +struct hclge_firmware_compat_cmd { + __le32 compat; + u8 rsv[20]; +}; + int hclge_cmd_init(struct hclge_dev *hdev); static inline void hclge_write_reg(void __iomem *base, u32 reg, u32 value) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c index bac4ce13f6ae..c063301d6060 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_dcb.c @@ -198,9 +198,32 @@ static int hclge_client_setup_tc(struct hclge_dev *hdev) return 0; } +static int hclge_notify_down_uinit(struct hclge_dev *hdev) +{ + int ret; + + ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT); + if (ret) + return ret; + + return hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT); +} + +static int hclge_notify_init_up(struct hclge_dev *hdev) +{ + int ret; + + ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT); + if (ret) + return ret; + + return hclge_notify_client(hdev, HNAE3_UP_CLIENT); +} + static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) { struct hclge_vport *vport = hclge_get_vport(h); + struct net_device *netdev = h->kinfo.netdev; struct hclge_dev *hdev = vport->back; bool map_changed = false; u8 num_tc = 0; @@ -215,11 +238,9 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) return ret; if (map_changed) { - ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT); - if (ret) - return ret; + netif_dbg(h, drv, netdev, "set ets\n"); - ret = hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT); + ret = hclge_notify_down_uinit(hdev); if (ret) return ret; } @@ -239,11 +260,7 @@ static int hclge_ieee_setets(struct hnae3_handle *h, struct ieee_ets *ets) if (ret) goto err_out; - ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT); - if (ret) - return ret; - - ret = hclge_notify_client(hdev, HNAE3_UP_CLIENT); + ret = hclge_notify_init_up(hdev); if (ret) return ret; } @@ -254,10 +271,8 @@ err_out: if (!map_changed) return ret; - if (hclge_notify_client(hdev, HNAE3_INIT_CLIENT)) - return ret; + hclge_notify_init_up(hdev); - hclge_notify_client(hdev, HNAE3_UP_CLIENT); return ret; } @@ -300,6 +315,7 @@ static int hclge_ieee_getpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) { struct hclge_vport *vport = hclge_get_vport(h); + struct net_device *netdev = h->kinfo.netdev; struct hclge_dev *hdev = vport->back; u8 i, j, pfc_map, *prio_tc; @@ -325,6 +341,10 @@ static int hclge_ieee_setpfc(struct hnae3_handle *h, struct ieee_pfc *pfc) hdev->tm_info.hw_pfc_map = pfc_map; hdev->tm_info.pfc_en = pfc->pfc_en; + netif_dbg(h, drv, netdev, + "set pfc: pfc_en=%x, pfc_map=%x, num_tc=%u\n", + pfc->pfc_en, pfc_map, hdev->tm_info.num_tc); + hclge_tm_pfc_info_update(hdev); return hclge_pause_setup_hw(hdev, false); @@ -345,8 +365,11 @@ static u8 hclge_getdcbx(struct hnae3_handle *h) static u8 hclge_setdcbx(struct hnae3_handle *h, u8 mode) { struct hclge_vport *vport = hclge_get_vport(h); + struct net_device *netdev = h->kinfo.netdev; struct hclge_dev *hdev = vport->back; + netif_dbg(h, drv, netdev, "set dcbx: mode=%u\n", mode); + /* No support for LLD_MANAGED modes or CEE */ if ((mode & DCB_CAP_DCBX_LLD_MANAGED) || (mode & DCB_CAP_DCBX_VER_CEE) || @@ -372,11 +395,7 @@ static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc) if (ret) return -EINVAL; - ret = hclge_notify_client(hdev, HNAE3_DOWN_CLIENT); - if (ret) - return ret; - - ret = hclge_notify_client(hdev, HNAE3_UNINIT_CLIENT); + ret = hclge_notify_down_uinit(hdev); if (ret) return ret; @@ -398,17 +417,11 @@ static int hclge_setup_tc(struct hnae3_handle *h, u8 tc, u8 *prio_tc) else hdev->flag &= ~HCLGE_FLAG_MQPRIO_ENABLE; - ret = hclge_notify_client(hdev, HNAE3_INIT_CLIENT); - if (ret) - return ret; - - return hclge_notify_client(hdev, HNAE3_UP_CLIENT); + return hclge_notify_init_up(hdev); err_out: - if (hclge_notify_client(hdev, HNAE3_INIT_CLIENT)) - return ret; + hclge_notify_init_up(hdev); - hclge_notify_client(hdev, HNAE3_UP_CLIENT); return ret; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c index ab625c757a95..d0128d792717 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.c @@ -4,32 +4,92 @@ #include <linux/device.h> #include "hclge_debugfs.h" -#include "hclge_cmd.h" #include "hclge_main.h" #include "hclge_tm.h" #include "hnae3.h" +static struct hclge_dbg_reg_type_info hclge_dbg_reg_info[] = { + { .reg_type = "bios common", + .dfx_msg = &hclge_dbg_bios_common_reg[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_bios_common_reg), + .offset = HCLGE_DBG_DFX_BIOS_OFFSET, + .cmd = HCLGE_OPC_DFX_BIOS_COMMON_REG } }, + { .reg_type = "ssu", + .dfx_msg = &hclge_dbg_ssu_reg_0[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ssu_reg_0), + .offset = HCLGE_DBG_DFX_SSU_0_OFFSET, + .cmd = HCLGE_OPC_DFX_SSU_REG_0 } }, + { .reg_type = "ssu", + .dfx_msg = &hclge_dbg_ssu_reg_1[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ssu_reg_1), + .offset = HCLGE_DBG_DFX_SSU_1_OFFSET, + .cmd = HCLGE_OPC_DFX_SSU_REG_1 } }, + { .reg_type = "ssu", + .dfx_msg = &hclge_dbg_ssu_reg_2[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ssu_reg_2), + .offset = HCLGE_DBG_DFX_SSU_2_OFFSET, + .cmd = HCLGE_OPC_DFX_SSU_REG_2 } }, + { .reg_type = "igu egu", + .dfx_msg = &hclge_dbg_igu_egu_reg[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_igu_egu_reg), + .offset = HCLGE_DBG_DFX_IGU_OFFSET, + .cmd = HCLGE_OPC_DFX_IGU_EGU_REG } }, + { .reg_type = "rpu", + .dfx_msg = &hclge_dbg_rpu_reg_0[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rpu_reg_0), + .offset = HCLGE_DBG_DFX_RPU_0_OFFSET, + .cmd = HCLGE_OPC_DFX_RPU_REG_0 } }, + { .reg_type = "rpu", + .dfx_msg = &hclge_dbg_rpu_reg_1[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rpu_reg_1), + .offset = HCLGE_DBG_DFX_RPU_1_OFFSET, + .cmd = HCLGE_OPC_DFX_RPU_REG_1 } }, + { .reg_type = "ncsi", + .dfx_msg = &hclge_dbg_ncsi_reg[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ncsi_reg), + .offset = HCLGE_DBG_DFX_NCSI_OFFSET, + .cmd = HCLGE_OPC_DFX_NCSI_REG } }, + { .reg_type = "rtc", + .dfx_msg = &hclge_dbg_rtc_reg[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rtc_reg), + .offset = HCLGE_DBG_DFX_RTC_OFFSET, + .cmd = HCLGE_OPC_DFX_RTC_REG } }, + { .reg_type = "ppp", + .dfx_msg = &hclge_dbg_ppp_reg[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_ppp_reg), + .offset = HCLGE_DBG_DFX_PPP_OFFSET, + .cmd = HCLGE_OPC_DFX_PPP_REG } }, + { .reg_type = "rcb", + .dfx_msg = &hclge_dbg_rcb_reg[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_rcb_reg), + .offset = HCLGE_DBG_DFX_RCB_OFFSET, + .cmd = HCLGE_OPC_DFX_RCB_REG } }, + { .reg_type = "tqp", + .dfx_msg = &hclge_dbg_tqp_reg[0], + .reg_msg = { .msg_num = ARRAY_SIZE(hclge_dbg_tqp_reg), + .offset = HCLGE_DBG_DFX_TQP_OFFSET, + .cmd = HCLGE_OPC_DFX_TQP_REG } }, +}; + static int hclge_dbg_get_dfx_bd_num(struct hclge_dev *hdev, int offset) { - struct hclge_desc desc[4]; - int ret; +#define HCLGE_GET_DFX_REG_TYPE_CNT 4 - hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true); - desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); - hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true); - desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); - hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true); - desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); - hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true); + struct hclge_desc desc[HCLGE_GET_DFX_REG_TYPE_CNT]; + int entries_per_desc; + int index; + int ret; - ret = hclge_cmd_send(&hdev->hw, desc, 4); - if (ret != HCLGE_CMD_EXEC_SUCCESS) { + ret = hclge_query_bd_num_cmd_send(hdev, desc); + if (ret) { dev_err(&hdev->pdev->dev, - "get dfx bdnum fail, status is %d.\n", ret); + "get dfx bdnum fail, ret = %d\n", ret); return ret; } - return (int)desc[offset / 6].data[offset % 6]; + entries_per_desc = ARRAY_SIZE(desc[0].data); + index = offset % entries_per_desc; + return (int)desc[offset / entries_per_desc].data[index]; } static int hclge_dbg_cmd_send(struct hclge_dev *hdev, @@ -50,35 +110,40 @@ static int hclge_dbg_cmd_send(struct hclge_dev *hdev, } ret = hclge_cmd_send(&hdev->hw, desc_src, bd_num); - if (ret) { + if (ret) dev_err(&hdev->pdev->dev, - "read reg cmd send fail, status is %d.\n", ret); - return ret; - } - + "cmd(0x%x) send fail, ret = %d\n", cmd, ret); return ret; } static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev, - struct hclge_dbg_dfx_message *dfx_message, - const char *cmd_buf, int msg_num, - int offset, enum hclge_opcode_type cmd) + struct hclge_dbg_reg_type_info *reg_info, + const char *cmd_buf) { -#define BD_DATA_NUM 6 +#define IDX_OFFSET 1 + const char *s = &cmd_buf[strlen(reg_info->reg_type) + IDX_OFFSET]; + struct hclge_dbg_dfx_message *dfx_message = reg_info->dfx_msg; + struct hclge_dbg_reg_common_msg *reg_msg = ®_info->reg_msg; struct hclge_desc *desc_src; struct hclge_desc *desc; + int entries_per_desc; int bd_num, buf_len; + int index = 0; + int min_num; int ret, i; - int index; - int max; - ret = kstrtouint(cmd_buf, 10, &index); - index = (ret != 0) ? 0 : index; + if (*s) { + ret = kstrtouint(s, 0, &index); + index = (ret != 0) ? 0 : index; + } - bd_num = hclge_dbg_get_dfx_bd_num(hdev, offset); - if (bd_num <= 0) + bd_num = hclge_dbg_get_dfx_bd_num(hdev, reg_msg->offset); + if (bd_num <= 0) { + dev_err(&hdev->pdev->dev, "get cmd(%d) bd num(%d) failed\n", + reg_msg->offset, bd_num); return; + } buf_len = sizeof(struct hclge_desc) * bd_num; desc_src = kzalloc(buf_len, GFP_KERNEL); @@ -88,22 +153,23 @@ static void hclge_dbg_dump_reg_common(struct hclge_dev *hdev, } desc = desc_src; - ret = hclge_dbg_cmd_send(hdev, desc, index, bd_num, cmd); - if (ret != HCLGE_CMD_EXEC_SUCCESS) { + ret = hclge_dbg_cmd_send(hdev, desc, index, bd_num, reg_msg->cmd); + if (ret) { kfree(desc_src); return; } - max = (bd_num * BD_DATA_NUM) <= msg_num ? - (bd_num * BD_DATA_NUM) : msg_num; + entries_per_desc = ARRAY_SIZE(desc->data); + min_num = min_t(int, bd_num * entries_per_desc, reg_msg->msg_num); desc = desc_src; - for (i = 0; i < max; i++) { - ((i > 0) && ((i % BD_DATA_NUM) == 0)) ? desc++ : desc; + for (i = 0; i < min_num; i++) { + if (i > 0 && (i % entries_per_desc) == 0) + desc++; if (dfx_message->flag) dev_info(&hdev->pdev->dev, "%s: 0x%x\n", dfx_message->message, - desc->data[i % BD_DATA_NUM]); + desc->data[i % entries_per_desc]); dfx_message++; } @@ -213,95 +279,25 @@ static void hclge_dbg_dump_dcb(struct hclge_dev *hdev, const char *cmd_buf) static void hclge_dbg_dump_reg_cmd(struct hclge_dev *hdev, const char *cmd_buf) { - int msg_num; - - if (strncmp(&cmd_buf[9], "bios common", 11) == 0) { - msg_num = sizeof(hclge_dbg_bios_common_reg) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_bios_common_reg, - &cmd_buf[21], msg_num, - HCLGE_DBG_DFX_BIOS_OFFSET, - HCLGE_OPC_DFX_BIOS_COMMON_REG); - } else if (strncmp(&cmd_buf[9], "ssu", 3) == 0) { - msg_num = sizeof(hclge_dbg_ssu_reg_0) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_ssu_reg_0, - &cmd_buf[13], msg_num, - HCLGE_DBG_DFX_SSU_0_OFFSET, - HCLGE_OPC_DFX_SSU_REG_0); - - msg_num = sizeof(hclge_dbg_ssu_reg_1) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_ssu_reg_1, - &cmd_buf[13], msg_num, - HCLGE_DBG_DFX_SSU_1_OFFSET, - HCLGE_OPC_DFX_SSU_REG_1); - - msg_num = sizeof(hclge_dbg_ssu_reg_2) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_ssu_reg_2, - &cmd_buf[13], msg_num, - HCLGE_DBG_DFX_SSU_2_OFFSET, - HCLGE_OPC_DFX_SSU_REG_2); - } else if (strncmp(&cmd_buf[9], "igu egu", 7) == 0) { - msg_num = sizeof(hclge_dbg_igu_egu_reg) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_igu_egu_reg, - &cmd_buf[17], msg_num, - HCLGE_DBG_DFX_IGU_OFFSET, - HCLGE_OPC_DFX_IGU_EGU_REG); - } else if (strncmp(&cmd_buf[9], "rpu", 3) == 0) { - msg_num = sizeof(hclge_dbg_rpu_reg_0) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_rpu_reg_0, - &cmd_buf[13], msg_num, - HCLGE_DBG_DFX_RPU_0_OFFSET, - HCLGE_OPC_DFX_RPU_REG_0); - - msg_num = sizeof(hclge_dbg_rpu_reg_1) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_rpu_reg_1, - &cmd_buf[13], msg_num, - HCLGE_DBG_DFX_RPU_1_OFFSET, - HCLGE_OPC_DFX_RPU_REG_1); - } else if (strncmp(&cmd_buf[9], "ncsi", 4) == 0) { - msg_num = sizeof(hclge_dbg_ncsi_reg) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_ncsi_reg, - &cmd_buf[14], msg_num, - HCLGE_DBG_DFX_NCSI_OFFSET, - HCLGE_OPC_DFX_NCSI_REG); - } else if (strncmp(&cmd_buf[9], "rtc", 3) == 0) { - msg_num = sizeof(hclge_dbg_rtc_reg) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_rtc_reg, - &cmd_buf[13], msg_num, - HCLGE_DBG_DFX_RTC_OFFSET, - HCLGE_OPC_DFX_RTC_REG); - } else if (strncmp(&cmd_buf[9], "ppp", 3) == 0) { - msg_num = sizeof(hclge_dbg_ppp_reg) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_ppp_reg, - &cmd_buf[13], msg_num, - HCLGE_DBG_DFX_PPP_OFFSET, - HCLGE_OPC_DFX_PPP_REG); - } else if (strncmp(&cmd_buf[9], "rcb", 3) == 0) { - msg_num = sizeof(hclge_dbg_rcb_reg) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_rcb_reg, - &cmd_buf[13], msg_num, - HCLGE_DBG_DFX_RCB_OFFSET, - HCLGE_OPC_DFX_RCB_REG); - } else if (strncmp(&cmd_buf[9], "tqp", 3) == 0) { - msg_num = sizeof(hclge_dbg_tqp_reg) / - sizeof(struct hclge_dbg_dfx_message); - hclge_dbg_dump_reg_common(hdev, hclge_dbg_tqp_reg, - &cmd_buf[13], msg_num, - HCLGE_DBG_DFX_TQP_OFFSET, - HCLGE_OPC_DFX_TQP_REG); - } else if (strncmp(&cmd_buf[9], "dcb", 3) == 0) { - hclge_dbg_dump_dcb(hdev, &cmd_buf[13]); - } else { + struct hclge_dbg_reg_type_info *reg_info; + bool has_dump = false; + int i; + + for (i = 0; i < ARRAY_SIZE(hclge_dbg_reg_info); i++) { + reg_info = &hclge_dbg_reg_info[i]; + if (!strncmp(cmd_buf, reg_info->reg_type, + strlen(reg_info->reg_type))) { + hclge_dbg_dump_reg_common(hdev, reg_info, cmd_buf); + has_dump = true; + } + } + + if (strncmp(cmd_buf, "dcb", 3) == 0) { + hclge_dbg_dump_dcb(hdev, &cmd_buf[sizeof("dcb")]); + has_dump = true; + } + + if (!has_dump) { dev_info(&hdev->pdev->dev, "unknown command\n"); return; } @@ -325,11 +321,17 @@ static void hclge_dbg_dump_tc(struct hclge_dev *hdev) struct hclge_desc desc; int i, ret; + if (!hnae3_dev_dcb_supported(hdev)) { + dev_info(&hdev->pdev->dev, + "Only DCB-supported dev supports tc\n"); + return; + } + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_ETS_TC_WEIGHT, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { - dev_err(&hdev->pdev->dev, "dump tc fail, status is %d.\n", ret); + dev_err(&hdev->pdev->dev, "dump tc fail, ret = %d\n", ret); return; } @@ -409,6 +411,12 @@ static void hclge_dbg_dump_tm_pg(struct hclge_dev *hdev) dev_info(&hdev->pdev->dev, "QS_SCH qs_id: %u\n", desc.data[0]); + if (!hnae3_dev_dcb_supported(hdev)) { + dev_info(&hdev->pdev->dev, + "Only DCB-supported dev supports tm mapping\n"); + return; + } + cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING; hclge_cmd_setup_basic_desc(&desc, cmd, true); ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -425,7 +433,7 @@ static void hclge_dbg_dump_tm_pg(struct hclge_dev *hdev) return; err_tm_pg_cmd_send: - dev_err(&hdev->pdev->dev, "dump tm_pg fail(0x%x), status is %d\n", + dev_err(&hdev->pdev->dev, "dump tm_pg fail(0x%x), ret = %d\n", cmd, ret); } @@ -537,7 +545,7 @@ static void hclge_dbg_dump_tm(struct hclge_dev *hdev) return; err_tm_cmd_send: - dev_err(&hdev->pdev->dev, "dump tm fail(0x%x), status is %d\n", + dev_err(&hdev->pdev->dev, "dump tm fail(0x%x), ret = %d\n", cmd, ret); } @@ -556,7 +564,7 @@ static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev, int pri_id, ret; u32 i; - ret = kstrtouint(&cmd_buf[12], 10, &queue_id); + ret = kstrtouint(cmd_buf, 0, &queue_id); queue_id = (ret != 0) ? 0 : queue_id; cmd = HCLGE_OPC_TM_NQ_TO_QS_LINK; @@ -590,6 +598,12 @@ static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev, dev_info(&hdev->pdev->dev, "%04d | %04d | %02d | %02d\n", queue_id, qset_id, pri_id, tc_id); + if (!hnae3_dev_dcb_supported(hdev)) { + dev_info(&hdev->pdev->dev, + "Only DCB-supported dev supports tm mapping\n"); + return; + } + cmd = HCLGE_OPC_TM_BP_TO_QSET_MAPPING; bp_to_qs_map_cmd = (struct hclge_bp_to_qs_map_cmd *)desc.data; for (group_id = 0; group_id < 32; group_id++) { @@ -620,7 +634,7 @@ static void hclge_dbg_dump_tm_map(struct hclge_dev *hdev, return; err_tm_map_cmd_send: - dev_err(&hdev->pdev->dev, "dump tqp map fail(0x%x), status is %d\n", + dev_err(&hdev->pdev->dev, "dump tqp map fail(0x%x), ret = %d\n", cmd, ret); } @@ -634,7 +648,7 @@ static void hclge_dbg_dump_qos_pause_cfg(struct hclge_dev *hdev) ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { - dev_err(&hdev->pdev->dev, "dump checksum fail, status is %d.\n", + dev_err(&hdev->pdev->dev, "dump checksum fail, ret = %d\n", ret); return; } @@ -658,7 +672,7 @@ static void hclge_dbg_dump_qos_pri_map(struct hclge_dev *hdev) ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { dev_err(&hdev->pdev->dev, - "dump qos pri map fail, status is %d.\n", ret); + "dump qos pri map fail, ret = %d\n", ret); return; } @@ -715,6 +729,34 @@ static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev) dev_info(&hdev->pdev->dev, "rx_share_buf: 0x%x\n", rx_buf_cmd->shared_buf); + cmd = HCLGE_OPC_RX_COM_WL_ALLOC; + hclge_cmd_setup_basic_desc(desc, cmd, true); + ret = hclge_cmd_send(&hdev->hw, desc, 1); + if (ret) + goto err_qos_cmd_send; + + rx_com_wl = (struct hclge_rx_com_wl *)desc[0].data; + dev_info(&hdev->pdev->dev, "\n"); + dev_info(&hdev->pdev->dev, "rx_com_wl: high: 0x%x, low: 0x%x\n", + rx_com_wl->com_wl.high, rx_com_wl->com_wl.low); + + cmd = HCLGE_OPC_RX_GBL_PKT_CNT; + hclge_cmd_setup_basic_desc(desc, cmd, true); + ret = hclge_cmd_send(&hdev->hw, desc, 1); + if (ret) + goto err_qos_cmd_send; + + rx_packet_cnt = (struct hclge_rx_com_wl *)desc[0].data; + dev_info(&hdev->pdev->dev, + "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n", + rx_packet_cnt->com_wl.high, rx_packet_cnt->com_wl.low); + dev_info(&hdev->pdev->dev, "\n"); + + if (!hnae3_dev_dcb_supported(hdev)) { + dev_info(&hdev->pdev->dev, + "Only DCB-supported dev supports rx priv wl\n"); + return; + } cmd = HCLGE_OPC_RX_PRIV_WL_ALLOC; hclge_cmd_setup_basic_desc(&desc[0], cmd, true); desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); @@ -723,7 +765,6 @@ static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev) if (ret) goto err_qos_cmd_send; - dev_info(&hdev->pdev->dev, "\n"); rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[0].data; for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++) dev_info(&hdev->pdev->dev, @@ -733,7 +774,8 @@ static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev) rx_priv_wl = (struct hclge_rx_priv_wl_buf *)desc[1].data; for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++) dev_info(&hdev->pdev->dev, - "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n", i + 4, + "rx_priv_wl_tc_%d: high: 0x%x, low: 0x%x\n", + i + HCLGE_TC_NUM_ONE_DESC, rx_priv_wl->tc_wl[i].high, rx_priv_wl->tc_wl[i].low); cmd = HCLGE_OPC_RX_COM_THRD_ALLOC; @@ -755,37 +797,15 @@ static void hclge_dbg_dump_qos_buf_cfg(struct hclge_dev *hdev) rx_com_thrd = (struct hclge_rx_com_thrd *)desc[1].data; for (i = 0; i < HCLGE_TC_NUM_ONE_DESC; i++) dev_info(&hdev->pdev->dev, - "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", i + 4, + "rx_com_thrd_tc_%d: high: 0x%x, low: 0x%x\n", + i + HCLGE_TC_NUM_ONE_DESC, rx_com_thrd->com_thrd[i].high, rx_com_thrd->com_thrd[i].low); - - cmd = HCLGE_OPC_RX_COM_WL_ALLOC; - hclge_cmd_setup_basic_desc(desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, desc, 1); - if (ret) - goto err_qos_cmd_send; - - rx_com_wl = (struct hclge_rx_com_wl *)desc[0].data; - dev_info(&hdev->pdev->dev, "\n"); - dev_info(&hdev->pdev->dev, "rx_com_wl: high: 0x%x, low: 0x%x\n", - rx_com_wl->com_wl.high, rx_com_wl->com_wl.low); - - cmd = HCLGE_OPC_RX_GBL_PKT_CNT; - hclge_cmd_setup_basic_desc(desc, cmd, true); - ret = hclge_cmd_send(&hdev->hw, desc, 1); - if (ret) - goto err_qos_cmd_send; - - rx_packet_cnt = (struct hclge_rx_com_wl *)desc[0].data; - dev_info(&hdev->pdev->dev, - "rx_global_packet_cnt: high: 0x%x, low: 0x%x\n", - rx_packet_cnt->com_wl.high, rx_packet_cnt->com_wl.low); - return; err_qos_cmd_send: dev_err(&hdev->pdev->dev, - "dump qos buf cfg fail(0x%x), status is %d\n", cmd, ret); + "dump qos buf cfg fail(0x%x), ret = %d\n", cmd, ret); } static void hclge_dbg_dump_mng_table(struct hclge_dev *hdev) @@ -825,9 +845,9 @@ static void hclge_dbg_dump_mng_table(struct hclge_dev *hdev) memset(printf_buf, 0, HCLGE_DBG_BUF_LEN); snprintf(printf_buf, HCLGE_DBG_BUF_LEN, "%02u |%02x:%02x:%02x:%02x:%02x:%02x|", - req0->index, req0->mac_add[0], req0->mac_add[1], - req0->mac_add[2], req0->mac_add[3], req0->mac_add[4], - req0->mac_add[5]); + req0->index, req0->mac_addr[0], req0->mac_addr[1], + req0->mac_addr[2], req0->mac_addr[3], + req0->mac_addr[4], req0->mac_addr[5]); snprintf(printf_buf + strlen(printf_buf), HCLGE_DBG_BUF_LEN - strlen(printf_buf), @@ -883,14 +903,17 @@ static void hclge_dbg_fd_tcam_read(struct hclge_dev *hdev, u8 stage, dev_info(&hdev->pdev->dev, " read result tcam key %s(%u):\n", sel_x ? "x" : "y", loc); + /* tcam_data0 ~ tcam_data1 */ req = (u32 *)req1->tcam_data; for (i = 0; i < 2; i++) dev_info(&hdev->pdev->dev, "%08x\n", *req++); + /* tcam_data2 ~ tcam_data7 */ req = (u32 *)req2->tcam_data; for (i = 0; i < 6; i++) dev_info(&hdev->pdev->dev, "%08x\n", *req++); + /* tcam_data8 ~ tcam_data12 */ req = (u32 *)req3->tcam_data; for (i = 0; i < 5; i++) dev_info(&hdev->pdev->dev, "%08x\n", *req++); @@ -908,25 +931,39 @@ static void hclge_dbg_fd_tcam(struct hclge_dev *hdev) static void hclge_dbg_dump_rst_info(struct hclge_dev *hdev) { - dev_info(&hdev->pdev->dev, "PF reset count: %d\n", + dev_info(&hdev->pdev->dev, "PF reset count: %u\n", hdev->rst_stats.pf_rst_cnt); - dev_info(&hdev->pdev->dev, "FLR reset count: %d\n", + dev_info(&hdev->pdev->dev, "FLR reset count: %u\n", hdev->rst_stats.flr_rst_cnt); - dev_info(&hdev->pdev->dev, "CORE reset count: %d\n", - hdev->rst_stats.core_rst_cnt); - dev_info(&hdev->pdev->dev, "GLOBAL reset count: %d\n", + dev_info(&hdev->pdev->dev, "GLOBAL reset count: %u\n", hdev->rst_stats.global_rst_cnt); - dev_info(&hdev->pdev->dev, "IMP reset count: %d\n", + dev_info(&hdev->pdev->dev, "IMP reset count: %u\n", hdev->rst_stats.imp_rst_cnt); - dev_info(&hdev->pdev->dev, "reset done count: %d\n", + dev_info(&hdev->pdev->dev, "reset done count: %u\n", hdev->rst_stats.reset_done_cnt); - dev_info(&hdev->pdev->dev, "HW reset done count: %d\n", + dev_info(&hdev->pdev->dev, "HW reset done count: %u\n", hdev->rst_stats.hw_reset_done_cnt); - dev_info(&hdev->pdev->dev, "reset count: %d\n", + dev_info(&hdev->pdev->dev, "reset count: %u\n", + hdev->rst_stats.reset_cnt); + dev_info(&hdev->pdev->dev, "reset count: %u\n", hdev->rst_stats.reset_cnt); + dev_info(&hdev->pdev->dev, "reset fail count: %u\n", + hdev->rst_stats.reset_fail_cnt); + dev_info(&hdev->pdev->dev, "vector0 interrupt enable status: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_REG_BASE)); + dev_info(&hdev->pdev->dev, "reset interrupt source: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG)); + dev_info(&hdev->pdev->dev, "reset interrupt status: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS)); + dev_info(&hdev->pdev->dev, "hardware reset status: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG)); + dev_info(&hdev->pdev->dev, "handshake status: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG)); + dev_info(&hdev->pdev->dev, "function reset status: 0x%x\n", + hclge_read_dev(&hdev->hw, HCLGE_FUN_RST_ING)); } -void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev) +static void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev) { struct hclge_desc *desc_src, *desc_tmp; struct hclge_get_m7_bd_cmd *req; @@ -940,7 +977,7 @@ void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev) ret = hclge_cmd_send(&hdev->hw, &desc, 1); if (ret) { dev_err(&hdev->pdev->dev, - "get firmware statistics bd number failed, ret=%d\n", + "get firmware statistics bd number failed, ret = %d\n", ret); return; } @@ -961,7 +998,7 @@ void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev) if (ret) { kfree(desc_src); dev_err(&hdev->pdev->dev, - "get firmware statistics failed, ret=%d\n", ret); + "get firmware statistics failed, ret = %d\n", ret); return; } @@ -981,6 +1018,33 @@ void hclge_dbg_get_m7_stats_info(struct hclge_dev *hdev) kfree(desc_src); } +#define HCLGE_CMD_NCL_CONFIG_BD_NUM 5 + +static void hclge_ncl_config_data_print(struct hclge_dev *hdev, + struct hclge_desc *desc, int *offset, + int *length) +{ +#define HCLGE_CMD_DATA_NUM 6 + + int i; + int j; + + for (i = 0; i < HCLGE_CMD_NCL_CONFIG_BD_NUM; i++) { + for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) { + if (i == 0 && j == 0) + continue; + + dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n", + *offset, + le32_to_cpu(desc[i].data[j])); + *offset += sizeof(u32); + *length -= sizeof(u32); + if (*length <= 0) + return; + } + } +} + /* hclge_dbg_dump_ncl_config: print specified range of NCL_CONFIG file * @hdev: pointer to struct hclge_dev * @cmd_buf: string that contains offset and length @@ -990,17 +1054,13 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, { #define HCLGE_MAX_NCL_CONFIG_OFFSET 4096 #define HCLGE_MAX_NCL_CONFIG_LENGTH (20 + 24 * 4) -#define HCLGE_CMD_DATA_NUM 6 - struct hclge_desc desc[5]; - u32 byte_offset; - int bd_num = 5; + struct hclge_desc desc[HCLGE_CMD_NCL_CONFIG_BD_NUM]; + int bd_num = HCLGE_CMD_NCL_CONFIG_BD_NUM; int offset; int length; int data0; int ret; - int i; - int j; ret = sscanf(cmd_buf, "%x %x", &offset, &length); if (ret != 2 || offset >= HCLGE_MAX_NCL_CONFIG_OFFSET || @@ -1026,22 +1086,7 @@ static void hclge_dbg_dump_ncl_config(struct hclge_dev *hdev, if (ret) return; - byte_offset = offset; - for (i = 0; i < bd_num; i++) { - for (j = 0; j < HCLGE_CMD_DATA_NUM; j++) { - if (i == 0 && j == 0) - continue; - - dev_info(&hdev->pdev->dev, "0x%04x | 0x%08x\n", - byte_offset, - le32_to_cpu(desc[i].data[j])); - byte_offset += sizeof(u32); - length -= sizeof(u32); - if (length <= 0) - return; - } - } - offset += HCLGE_MAX_NCL_CONFIG_LENGTH; + hclge_ncl_config_data_print(hdev, desc, &offset, &length); } } @@ -1067,6 +1112,9 @@ static void hclge_dbg_dump_mac_tnl_status(struct hclge_dev *hdev) int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf) { +#define DUMP_REG "dump reg" +#define DUMP_TM_MAP "dump tm map" + struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; @@ -1074,8 +1122,8 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf) hclge_dbg_fd_tcam(hdev); } else if (strncmp(cmd_buf, "dump tc", 7) == 0) { hclge_dbg_dump_tc(hdev); - } else if (strncmp(cmd_buf, "dump tm map", 11) == 0) { - hclge_dbg_dump_tm_map(hdev, cmd_buf); + } else if (strncmp(cmd_buf, DUMP_TM_MAP, strlen(DUMP_TM_MAP)) == 0) { + hclge_dbg_dump_tm_map(hdev, &cmd_buf[sizeof(DUMP_TM_MAP)]); } else if (strncmp(cmd_buf, "dump tm", 7) == 0) { hclge_dbg_dump_tm(hdev); } else if (strncmp(cmd_buf, "dump qos pause cfg", 18) == 0) { @@ -1086,8 +1134,8 @@ int hclge_dbg_run_cmd(struct hnae3_handle *handle, const char *cmd_buf) hclge_dbg_dump_qos_buf_cfg(hdev); } else if (strncmp(cmd_buf, "dump mng tbl", 12) == 0) { hclge_dbg_dump_mng_table(hdev); - } else if (strncmp(cmd_buf, "dump reg", 8) == 0) { - hclge_dbg_dump_reg_cmd(hdev, cmd_buf); + } else if (strncmp(cmd_buf, DUMP_REG, strlen(DUMP_REG)) == 0) { + hclge_dbg_dump_reg_cmd(hdev, &cmd_buf[sizeof(DUMP_REG)]); } else if (strncmp(cmd_buf, "dump reset info", 15) == 0) { hclge_dbg_dump_rst_info(hdev); } else if (strncmp(cmd_buf, "dump m7 info", 12) == 0) { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h index d055fda41775..38b79321c4c4 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_debugfs.h @@ -4,6 +4,9 @@ #ifndef __HCLGE_DEBUGFS_H #define __HCLGE_DEBUGFS_H +#include <linux/etherdevice.h> +#include "hclge_cmd.h" + #define HCLGE_DBG_BUF_LEN 256 #define HCLGE_DBG_MNG_TBL_MAX 64 @@ -63,9 +66,23 @@ struct hclge_dbg_bitmap_cmd { }; }; +struct hclge_dbg_reg_common_msg { + int msg_num; + int offset; + enum hclge_opcode_type cmd; +}; + +#define HCLGE_DBG_MAX_DFX_MSG_LEN 60 struct hclge_dbg_dfx_message { int flag; - char message[60]; + char message[HCLGE_DBG_MAX_DFX_MSG_LEN]; +}; + +#define HCLGE_DBG_MAC_REG_TYPE_LEN 32 +struct hclge_dbg_reg_type_info { + const char *reg_type; + struct hclge_dbg_dfx_message *dfx_msg; + struct hclge_dbg_reg_common_msg reg_msg; }; #pragma pack() diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c index 85a3b062371d..87dece0e745d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c @@ -637,8 +637,8 @@ static void hclge_log_error(struct device *dev, char *reg, { while (err->msg) { if (err->int_msk & err_sts) { - dev_warn(dev, "%s %s found [error status=0x%x]\n", - reg, err->msg, err_sts); + dev_err(dev, "%s %s found [error status=0x%x]\n", + reg, err->msg, err_sts); if (err->reset_level && err->reset_level != HNAE3_NONE_RESET) set_bit(err->reset_level, reset_requests); @@ -652,16 +652,11 @@ static void hclge_log_error(struct device *dev, char *reg, * @desc: descriptor for describing the command * @cmd: command opcode * @flag: flag for extended command structure - * @w_num: offset for setting the read interrupt type. - * @int_type: select which type of the interrupt for which the error - * info will be read(RAS-CE/RAS-NFE/RAS-FE etc). * * This function query the error info from hw register/s using command */ static int hclge_cmd_query_error(struct hclge_dev *hdev, - struct hclge_desc *desc, u32 cmd, - u16 flag, u8 w_num, - enum hclge_err_int_type int_type) + struct hclge_desc *desc, u32 cmd, u16 flag) { struct device *dev = &hdev->pdev->dev; int desc_num = 1; @@ -673,8 +668,6 @@ static int hclge_cmd_query_error(struct hclge_dev *hdev, hclge_cmd_setup_basic_desc(&desc[1], cmd, true); desc_num = 2; } - if (w_num) - desc[0].data[w_num] = cpu_to_le32(int_type); ret = hclge_cmd_send(&hdev->hw, &desc[0], desc_num); if (ret) @@ -872,8 +865,7 @@ static int hclge_config_tm_hw_err_int(struct hclge_dev *hdev, bool en) } /* configure TM QCN hw errors */ - ret = hclge_cmd_query_error(hdev, &desc, HCLGE_TM_QCN_MEM_INT_CFG, - 0, 0, 0); + ret = hclge_cmd_query_error(hdev, &desc, HCLGE_TM_QCN_MEM_INT_CFG, 0); if (ret) { dev_err(dev, "fail(%d) to read TM QCN CFG status\n", ret); return ret; @@ -938,32 +930,44 @@ static int hclge_config_ppu_error_interrupts(struct hclge_dev *hdev, u32 cmd, /* configure PPU error interrupts */ if (cmd == HCLGE_PPU_MPF_ECC_INT_CMD) { hclge_cmd_setup_basic_desc(&desc[0], cmd, false); - desc[0].flag |= HCLGE_CMD_FLAG_NEXT; + desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); hclge_cmd_setup_basic_desc(&desc[1], cmd, false); if (en) { - desc[0].data[0] = HCLGE_PPU_MPF_ABNORMAL_INT0_EN; - desc[0].data[1] = HCLGE_PPU_MPF_ABNORMAL_INT1_EN; - desc[1].data[3] = HCLGE_PPU_MPF_ABNORMAL_INT3_EN; - desc[1].data[4] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN; + desc[0].data[0] = + cpu_to_le32(HCLGE_PPU_MPF_ABNORMAL_INT0_EN); + desc[0].data[1] = + cpu_to_le32(HCLGE_PPU_MPF_ABNORMAL_INT1_EN); + desc[1].data[3] = + cpu_to_le32(HCLGE_PPU_MPF_ABNORMAL_INT3_EN); + desc[1].data[4] = + cpu_to_le32(HCLGE_PPU_MPF_ABNORMAL_INT2_EN); } - desc[1].data[0] = HCLGE_PPU_MPF_ABNORMAL_INT0_EN_MASK; - desc[1].data[1] = HCLGE_PPU_MPF_ABNORMAL_INT1_EN_MASK; - desc[1].data[2] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN_MASK; - desc[1].data[3] |= HCLGE_PPU_MPF_ABNORMAL_INT3_EN_MASK; + desc[1].data[0] = + cpu_to_le32(HCLGE_PPU_MPF_ABNORMAL_INT0_EN_MASK); + desc[1].data[1] = + cpu_to_le32(HCLGE_PPU_MPF_ABNORMAL_INT1_EN_MASK); + desc[1].data[2] = + cpu_to_le32(HCLGE_PPU_MPF_ABNORMAL_INT2_EN_MASK); + desc[1].data[3] |= + cpu_to_le32(HCLGE_PPU_MPF_ABNORMAL_INT3_EN_MASK); desc_num = 2; } else if (cmd == HCLGE_PPU_MPF_OTHER_INT_CMD) { hclge_cmd_setup_basic_desc(&desc[0], cmd, false); if (en) - desc[0].data[0] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN2; + desc[0].data[0] = + cpu_to_le32(HCLGE_PPU_MPF_ABNORMAL_INT2_EN2); - desc[0].data[2] = HCLGE_PPU_MPF_ABNORMAL_INT2_EN2_MASK; + desc[0].data[2] = + cpu_to_le32(HCLGE_PPU_MPF_ABNORMAL_INT2_EN2_MASK); } else if (cmd == HCLGE_PPU_PF_OTHER_INT_CMD) { hclge_cmd_setup_basic_desc(&desc[0], cmd, false); if (en) - desc[0].data[0] = HCLGE_PPU_PF_ABNORMAL_INT_EN; + desc[0].data[0] = + cpu_to_le32(HCLGE_PPU_PF_ABNORMAL_INT_EN); - desc[0].data[2] = HCLGE_PPU_PF_ABNORMAL_INT_EN_MASK; + desc[0].data[2] = + cpu_to_le32(HCLGE_PPU_PF_ABNORMAL_INT_EN_MASK); } else { dev_err(dev, "Invalid cmd to configure PPU error interrupts\n"); return -EINVAL; @@ -1171,8 +1175,8 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev, status = le32_to_cpu(*(desc_data + 3)) & BIT(0); if (status) { - dev_warn(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_mem32_ecc_mbit_err found [error status=0x%x]\n", - status); + dev_err(dev, "SSU_ECC_MULTI_BIT_INT_1 ssu_mem32_ecc_mbit_err found [error status=0x%x]\n", + status); set_bit(HNAE3_GLOBAL_RESET, &ae_dev->hw_err_reset_req); } @@ -1208,8 +1212,8 @@ static int hclge_handle_mpf_ras_error(struct hclge_dev *hdev, desc_data = (__le32 *)&desc[5]; status = le32_to_cpu(*(desc_data + 1)); if (status) { - dev_warn(dev, "PPU_MPF_ABNORMAL_INT_ST1 %s found\n", - "rpu_rx_pkt_ecc_mbit_err"); + dev_err(dev, + "PPU_MPF_ABNORMAL_INT_ST1 rpu_rx_pkt_ecc_mbit_err found\n"); set_bit(HNAE3_GLOBAL_RESET, &ae_dev->hw_err_reset_req); } @@ -1321,10 +1325,12 @@ static int hclge_handle_pf_ras_error(struct hclge_dev *hdev, /* log PPU(RCB) errors */ desc_data = (__le32 *)&desc[3]; status = le32_to_cpu(*desc_data) & HCLGE_PPU_PF_INT_RAS_MASK; - if (status) + if (status) { hclge_log_error(dev, "PPU_PF_ABNORMAL_INT_ST0", &hclge_ppu_pf_abnormal_int[0], status, &ae_dev->hw_err_reset_req); + hclge_report_hw_error(hdev, HNAE3_PPU_POISON_ERROR); + } /* clear all PF RAS errors */ hclge_cmd_reuse_desc(&desc[0], false); @@ -1387,17 +1393,17 @@ static int hclge_log_rocee_axi_error(struct hclge_dev *hdev) return ret; } - dev_info(dev, "AXI1: %08X %08X %08X %08X %08X %08X\n", - le32_to_cpu(desc[0].data[0]), le32_to_cpu(desc[0].data[1]), - le32_to_cpu(desc[0].data[2]), le32_to_cpu(desc[0].data[3]), - le32_to_cpu(desc[0].data[4]), le32_to_cpu(desc[0].data[5])); - dev_info(dev, "AXI2: %08X %08X %08X %08X %08X %08X\n", - le32_to_cpu(desc[1].data[0]), le32_to_cpu(desc[1].data[1]), - le32_to_cpu(desc[1].data[2]), le32_to_cpu(desc[1].data[3]), - le32_to_cpu(desc[1].data[4]), le32_to_cpu(desc[1].data[5])); - dev_info(dev, "AXI3: %08X %08X %08X %08X\n", - le32_to_cpu(desc[2].data[0]), le32_to_cpu(desc[2].data[1]), - le32_to_cpu(desc[2].data[2]), le32_to_cpu(desc[2].data[3])); + dev_err(dev, "AXI1: %08X %08X %08X %08X %08X %08X\n", + le32_to_cpu(desc[0].data[0]), le32_to_cpu(desc[0].data[1]), + le32_to_cpu(desc[0].data[2]), le32_to_cpu(desc[0].data[3]), + le32_to_cpu(desc[0].data[4]), le32_to_cpu(desc[0].data[5])); + dev_err(dev, "AXI2: %08X %08X %08X %08X %08X %08X\n", + le32_to_cpu(desc[1].data[0]), le32_to_cpu(desc[1].data[1]), + le32_to_cpu(desc[1].data[2]), le32_to_cpu(desc[1].data[3]), + le32_to_cpu(desc[1].data[4]), le32_to_cpu(desc[1].data[5])); + dev_err(dev, "AXI3: %08X %08X %08X %08X\n", + le32_to_cpu(desc[2].data[0]), le32_to_cpu(desc[2].data[1]), + le32_to_cpu(desc[2].data[2]), le32_to_cpu(desc[2].data[3])); return 0; } @@ -1410,18 +1416,18 @@ static int hclge_log_rocee_ecc_error(struct hclge_dev *hdev) ret = hclge_cmd_query_error(hdev, &desc[0], HCLGE_QUERY_ROCEE_ECC_RAS_INFO_CMD, - HCLGE_CMD_FLAG_NEXT, 0, 0); + HCLGE_CMD_FLAG_NEXT); if (ret) { dev_err(dev, "failed(%d) to query ROCEE ECC error sts\n", ret); return ret; } - dev_info(dev, "ECC1: %08X %08X %08X %08X %08X %08X\n", - le32_to_cpu(desc[0].data[0]), le32_to_cpu(desc[0].data[1]), - le32_to_cpu(desc[0].data[2]), le32_to_cpu(desc[0].data[3]), - le32_to_cpu(desc[0].data[4]), le32_to_cpu(desc[0].data[5])); - dev_info(dev, "ECC2: %08X %08X %08X\n", le32_to_cpu(desc[1].data[0]), - le32_to_cpu(desc[1].data[1]), le32_to_cpu(desc[1].data[2])); + dev_err(dev, "ECC1: %08X %08X %08X %08X %08X %08X\n", + le32_to_cpu(desc[0].data[0]), le32_to_cpu(desc[0].data[1]), + le32_to_cpu(desc[0].data[2]), le32_to_cpu(desc[0].data[3]), + le32_to_cpu(desc[0].data[4]), le32_to_cpu(desc[0].data[5])); + dev_err(dev, "ECC2: %08X %08X %08X\n", le32_to_cpu(desc[1].data[0]), + le32_to_cpu(desc[1].data[1]), le32_to_cpu(desc[1].data[2])); return 0; } @@ -1434,7 +1440,7 @@ static int hclge_log_rocee_ovf_error(struct hclge_dev *hdev) /* read overflow error status */ ret = hclge_cmd_query_error(hdev, &desc[0], HCLGE_ROCEE_PF_RAS_INT_CMD, - 0, 0, 0); + 0); if (ret) { dev_err(dev, "failed(%d) to query ROCEE OVF error sts\n", ret); return ret; @@ -1450,9 +1456,9 @@ static int hclge_log_rocee_ovf_error(struct hclge_dev *hdev) le32_to_cpu(desc[0].data[0]); while (err->msg) { if (err->int_msk == err_sts) { - dev_warn(dev, "%s [error status=0x%x] found\n", - err->msg, - le32_to_cpu(desc[0].data[0])); + dev_err(dev, "%s [error status=0x%x] found\n", + err->msg, + le32_to_cpu(desc[0].data[0])); break; } err++; @@ -1460,13 +1466,13 @@ static int hclge_log_rocee_ovf_error(struct hclge_dev *hdev) } if (le32_to_cpu(desc[0].data[1]) & HCLGE_ROCEE_OVF_ERR_INT_MASK) { - dev_warn(dev, "ROCEE TSP OVF [error status=0x%x] found\n", - le32_to_cpu(desc[0].data[1])); + dev_err(dev, "ROCEE TSP OVF [error status=0x%x] found\n", + le32_to_cpu(desc[0].data[1])); } if (le32_to_cpu(desc[0].data[2]) & HCLGE_ROCEE_OVF_ERR_INT_MASK) { - dev_warn(dev, "ROCEE SCC OVF [error status=0x%x] found\n", - le32_to_cpu(desc[0].data[2])); + dev_err(dev, "ROCEE SCC OVF [error status=0x%x] found\n", + le32_to_cpu(desc[0].data[2])); } return 0; @@ -1483,8 +1489,7 @@ hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev) /* read RAS error interrupt status */ ret = hclge_cmd_query_error(hdev, &desc[0], - HCLGE_QUERY_CLEAR_ROCEE_RAS_INT, - 0, 0, 0); + HCLGE_QUERY_CLEAR_ROCEE_RAS_INT, 0); if (ret) { dev_err(dev, "failed(%d) to query ROCEE RAS INT SRC\n", ret); /* reset everything for now */ @@ -1495,10 +1500,10 @@ hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev) if (status & HCLGE_ROCEE_AXI_ERR_INT_MASK) { if (status & HCLGE_ROCEE_RERR_INT_MASK) - dev_warn(dev, "ROCEE RAS AXI rresp error\n"); + dev_err(dev, "ROCEE RAS AXI rresp error\n"); if (status & HCLGE_ROCEE_BERR_INT_MASK) - dev_warn(dev, "ROCEE RAS AXI bresp error\n"); + dev_err(dev, "ROCEE RAS AXI bresp error\n"); reset_type = HNAE3_FUNC_RESET; @@ -1508,7 +1513,7 @@ hclge_log_and_clear_rocee_ras_error(struct hclge_dev *hdev) } if (status & HCLGE_ROCEE_ECC_INT_MASK) { - dev_warn(dev, "ROCEE RAS 2bit ECC error\n"); + dev_err(dev, "ROCEE RAS 2bit ECC error\n"); reset_type = HNAE3_GLOBAL_RESET; ret = hclge_log_rocee_ecc_error(hdev); @@ -1566,8 +1571,8 @@ int hclge_config_rocee_ras_interrupt(struct hclge_dev *hdev, bool en) static void hclge_handle_rocee_ras_error(struct hnae3_ae_dev *ae_dev) { - enum hnae3_reset_type reset_type = HNAE3_NONE_RESET; struct hclge_dev *hdev = ae_dev->priv; + enum hnae3_reset_type reset_type; if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) || hdev->pdev->revision < 0x21) @@ -1649,16 +1654,16 @@ pci_ers_result_t hclge_handle_hw_ras_error(struct hnae3_ae_dev *ae_dev) /* Handling Non-fatal HNS RAS errors */ if (status & HCLGE_RAS_REG_NFE_MASK) { - dev_warn(dev, - "HNS Non-Fatal RAS error(status=0x%x) identified\n", - status); + dev_err(dev, + "HNS Non-Fatal RAS error(status=0x%x) identified\n", + status); hclge_handle_all_ras_errors(hdev); } /* Handling Non-fatal Rocee RAS errors */ if (hdev->pdev->revision >= 0x21 && status & HCLGE_RAS_REG_ROCEE_ERR_MASK) { - dev_warn(dev, "ROCEE Non-Fatal RAS error identified\n"); + dev_err(dev, "ROCEE Non-Fatal RAS error identified\n"); hclge_handle_rocee_ras_error(ae_dev); } @@ -1737,8 +1742,8 @@ static void hclge_handle_over_8bd_err(struct hclge_dev *hdev, return; } - dev_warn(dev, "PPU_PF_ABNORMAL_INT_ST over_8bd_no_fe found, vf_id(%d), queue_id(%d)\n", - vf_id, q_id); + dev_err(dev, "PPU_PF_ABNORMAL_INT_ST over_8bd_no_fe found, vf_id(%u), queue_id(%u)\n", + vf_id, q_id); if (vf_id) { if (vf_id >= hdev->num_alloc_vport) { @@ -1755,8 +1760,8 @@ static void hclge_handle_over_8bd_err(struct hclge_dev *hdev, ret = hclge_inform_reset_assert_to_vf(&hdev->vport[vf_id]); if (ret) - dev_warn(dev, "inform reset to vf(%d) failed %d!\n", - hdev->vport->vport_id, ret); + dev_err(dev, "inform reset to vf(%u) failed %d!\n", + hdev->vport->vport_id, ret); } else { set_bit(HNAE3_FUNC_RESET, reset_requests); } @@ -1802,8 +1807,8 @@ static int hclge_handle_mpf_msix_error(struct hclge_dev *hdev, status = le32_to_cpu(*(desc_data + 2)) & HCLGE_PPU_MPF_INT_ST2_MSIX_MASK; if (status) - dev_warn(dev, "PPU_MPF_ABNORMAL_INT_ST2 rx_q_search_miss found [dfx status=0x%x\n]", - status); + dev_err(dev, "PPU_MPF_ABNORMAL_INT_ST2 rx_q_search_miss found [dfx status=0x%x\n]", + status); /* clear all main PF MSIx errors */ ret = hclge_clear_hw_msix_error(hdev, desc, true, mpf_bd_num); @@ -1997,7 +2002,7 @@ void hclge_handle_all_hns_hw_errors(struct hnae3_ae_dev *ae_dev) /* Handle Non-fatal HNS RAS errors */ if (status & HCLGE_RAS_REG_NFE_MASK) { - dev_warn(dev, "HNS hw error(RAS) identified during init\n"); + dev_err(dev, "HNS hw error(RAS) identified during init\n"); hclge_handle_all_ras_errors(hdev); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h index 7ea8bb28a0cb..876fd81ad2f1 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.h @@ -5,6 +5,7 @@ #define __HCLGE_ERR_H #include "hclge_main.h" +#include "hnae3.h" #define HCLGE_MPF_RAS_INT_MIN_BD_NUM 10 #define HCLGE_PF_RAS_INT_MIN_BD_NUM 4 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 3fde5471e1c0..fd7f94372ff0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -35,6 +35,25 @@ #define BUF_RESERVE_PERCENT 90 #define HCLGE_RESET_MAX_FAIL_CNT 5 +#define HCLGE_RESET_SYNC_TIME 100 +#define HCLGE_PF_RESET_SYNC_TIME 20 +#define HCLGE_PF_RESET_SYNC_CNT 1500 + +/* Get DFX BD number offset */ +#define HCLGE_DFX_BIOS_BD_OFFSET 1 +#define HCLGE_DFX_SSU_0_BD_OFFSET 2 +#define HCLGE_DFX_SSU_1_BD_OFFSET 3 +#define HCLGE_DFX_IGU_BD_OFFSET 4 +#define HCLGE_DFX_RPU_0_BD_OFFSET 5 +#define HCLGE_DFX_RPU_1_BD_OFFSET 6 +#define HCLGE_DFX_NCSI_BD_OFFSET 7 +#define HCLGE_DFX_RTC_BD_OFFSET 8 +#define HCLGE_DFX_PPP_BD_OFFSET 9 +#define HCLGE_DFX_RCB_BD_OFFSET 10 +#define HCLGE_DFX_TQP_BD_OFFSET 11 +#define HCLGE_DFX_SSU_2_BD_OFFSET 12 + +#define HCLGE_LINK_STATUS_MS 10 static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps); static int hclge_init_vlan_config(struct hclge_dev *hdev); @@ -47,6 +66,7 @@ static void hclge_rfs_filter_expire(struct hclge_dev *hdev); static void hclge_clear_arfs_rules(struct hnae3_handle *handle); static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev, unsigned long *addr); +static int hclge_set_default_loopback(struct hclge_dev *hdev); static struct hnae3_ae_algo ae_algo; @@ -317,6 +337,80 @@ static const u8 hclge_hash_key[] = { 0x6A, 0x42, 0xB7, 0x3B, 0xBE, 0xAC, 0x01, 0xFA }; +static const u32 hclge_dfx_bd_offset_list[] = { + HCLGE_DFX_BIOS_BD_OFFSET, + HCLGE_DFX_SSU_0_BD_OFFSET, + HCLGE_DFX_SSU_1_BD_OFFSET, + HCLGE_DFX_IGU_BD_OFFSET, + HCLGE_DFX_RPU_0_BD_OFFSET, + HCLGE_DFX_RPU_1_BD_OFFSET, + HCLGE_DFX_NCSI_BD_OFFSET, + HCLGE_DFX_RTC_BD_OFFSET, + HCLGE_DFX_PPP_BD_OFFSET, + HCLGE_DFX_RCB_BD_OFFSET, + HCLGE_DFX_TQP_BD_OFFSET, + HCLGE_DFX_SSU_2_BD_OFFSET +}; + +static const enum hclge_opcode_type hclge_dfx_reg_opcode_list[] = { + HCLGE_OPC_DFX_BIOS_COMMON_REG, + HCLGE_OPC_DFX_SSU_REG_0, + HCLGE_OPC_DFX_SSU_REG_1, + HCLGE_OPC_DFX_IGU_EGU_REG, + HCLGE_OPC_DFX_RPU_REG_0, + HCLGE_OPC_DFX_RPU_REG_1, + HCLGE_OPC_DFX_NCSI_REG, + HCLGE_OPC_DFX_RTC_REG, + HCLGE_OPC_DFX_PPP_REG, + HCLGE_OPC_DFX_RCB_REG, + HCLGE_OPC_DFX_TQP_REG, + HCLGE_OPC_DFX_SSU_REG_2 +}; + +static const struct key_info meta_data_key_info[] = { + { PACKET_TYPE_ID, 6}, + { IP_FRAGEMENT, 1}, + { ROCE_TYPE, 1}, + { NEXT_KEY, 5}, + { VLAN_NUMBER, 2}, + { SRC_VPORT, 12}, + { DST_VPORT, 12}, + { TUNNEL_PACKET, 1}, +}; + +static const struct key_info tuple_key_info[] = { + { OUTER_DST_MAC, 48}, + { OUTER_SRC_MAC, 48}, + { OUTER_VLAN_TAG_FST, 16}, + { OUTER_VLAN_TAG_SEC, 16}, + { OUTER_ETH_TYPE, 16}, + { OUTER_L2_RSV, 16}, + { OUTER_IP_TOS, 8}, + { OUTER_IP_PROTO, 8}, + { OUTER_SRC_IP, 32}, + { OUTER_DST_IP, 32}, + { OUTER_L3_RSV, 16}, + { OUTER_SRC_PORT, 16}, + { OUTER_DST_PORT, 16}, + { OUTER_L4_RSV, 32}, + { OUTER_TUN_VNI, 24}, + { OUTER_TUN_FLOW_ID, 8}, + { INNER_DST_MAC, 48}, + { INNER_SRC_MAC, 48}, + { INNER_VLAN_TAG_FST, 16}, + { INNER_VLAN_TAG_SEC, 16}, + { INNER_ETH_TYPE, 16}, + { INNER_L2_RSV, 16}, + { INNER_IP_TOS, 8}, + { INNER_IP_PROTO, 8}, + { INNER_SRC_IP, 32}, + { INNER_DST_IP, 32}, + { INNER_L3_RSV, 16}, + { INNER_SRC_PORT, 16}, + { INNER_DST_PORT, 16}, + { INNER_L4_RSV, 32}, +}; + static int hclge_mac_update_stats_defective(struct hclge_dev *hdev) { #define HCLGE_MAC_CMD_NUM 21 @@ -364,9 +458,13 @@ static int hclge_mac_update_stats_complete(struct hclge_dev *hdev, u32 desc_num) u16 i, k, n; int ret; - desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_KERNEL); + /* This may be called inside atomic sections, + * so GFP_ATOMIC is more suitalbe here + */ + desc = kcalloc(desc_num, sizeof(struct hclge_desc), GFP_ATOMIC); if (!desc) return -ENOMEM; + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_STATS_MAC_ALL, true); ret = hclge_cmd_send(&hdev->hw, desc, desc_num); if (ret) { @@ -647,6 +745,12 @@ static int hclge_get_sset_count(struct hnae3_handle *handle, int stringset) count += 2; handle->flags |= HNAE3_SUPPORT_SERDES_SERIAL_LOOPBACK; handle->flags |= HNAE3_SUPPORT_SERDES_PARALLEL_LOOPBACK; + + if (hdev->hw.mac.phydev) { + count += 1; + handle->flags |= HNAE3_SUPPORT_PHY_LOOPBACK; + } + } else if (stringset == ETH_SS_STATS) { count = ARRAY_SIZE(g_mac_stats_string) + hclge_tqps_get_sset_count(handle, stringset); @@ -702,14 +806,16 @@ static void hclge_get_stats(struct hnae3_handle *handle, u64 *data) p = hclge_tqps_get_stats(handle, p); } -static void hclge_get_mac_pause_stat(struct hnae3_handle *handle, u64 *tx_cnt, - u64 *rx_cnt) +static void hclge_get_mac_stat(struct hnae3_handle *handle, + struct hns3_mac_stats *mac_stats) { struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_dev *hdev = vport->back; - *tx_cnt = hdev->hw_stats.mac_stats.mac_tx_mac_pause_num; - *rx_cnt = hdev->hw_stats.mac_stats.mac_rx_mac_pause_num; + hclge_update_stats(handle, NULL); + + mac_stats->tx_pause_cnt = hdev->hw_stats.mac_stats.mac_tx_mac_pause_num; + mac_stats->rx_pause_cnt = hdev->hw_stats.mac_stats.mac_rx_mac_pause_num; } static int hclge_parse_func_status(struct hclge_dev *hdev, @@ -1075,6 +1181,7 @@ static void hclge_parse_link_mode(struct hclge_dev *hdev, u8 speed_ability) else if (media_type == HNAE3_MEDIA_TYPE_BACKPLANE) hclge_parse_backplane_link_mode(hdev, speed_ability); } + static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) { struct hclge_cfg_param_cmd *req; @@ -1270,6 +1377,12 @@ static int hclge_configure(struct hclge_dev *hdev) hclge_init_kdump_kernel_config(hdev); + /* Set the init affinity based on pci func number */ + i = cpumask_weight(cpumask_of_node(dev_to_node(&hdev->pdev->dev))); + i = i ? PCI_FUNC(hdev->pdev->devfn) % i : 0; + cpumask_set_cpu(cpumask_local_spread(i, dev_to_node(&hdev->pdev->dev)), + &hdev->affinity_mask); + return ret; } @@ -2487,6 +2600,10 @@ static int hclge_mac_init(struct hclge_dev *hdev) return ret; } + ret = hclge_set_default_loopback(hdev); + if (ret) + return ret; + ret = hclge_buffer_alloc(hdev); if (ret) dev_err(&hdev->pdev->dev, @@ -2499,22 +2616,29 @@ static void hclge_mbx_task_schedule(struct hclge_dev *hdev) { if (!test_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state) && !test_and_set_bit(HCLGE_STATE_MBX_SERVICE_SCHED, &hdev->state)) - schedule_work(&hdev->mbx_service_task); + queue_work_on(cpumask_first(&hdev->affinity_mask), system_wq, + &hdev->mbx_service_task); } static void hclge_reset_task_schedule(struct hclge_dev *hdev) { if (!test_bit(HCLGE_STATE_REMOVING, &hdev->state) && !test_and_set_bit(HCLGE_STATE_RST_SERVICE_SCHED, &hdev->state)) - schedule_work(&hdev->rst_service_task); + queue_work_on(cpumask_first(&hdev->affinity_mask), system_wq, + &hdev->rst_service_task); } -static void hclge_task_schedule(struct hclge_dev *hdev) +void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time) { if (!test_bit(HCLGE_STATE_DOWN, &hdev->state) && !test_bit(HCLGE_STATE_REMOVING, &hdev->state) && - !test_and_set_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state)) - (void)schedule_work(&hdev->service_task); + !test_and_set_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state)) { + hdev->hw_stats.stats_timer++; + hdev->fd_arfs_expire_timer++; + mod_delayed_work_on(cpumask_first(&hdev->affinity_mask), + system_wq, &hdev->service_task, + delay_time); + } } static int hclge_get_mac_link_status(struct hclge_dev *hdev) @@ -2729,25 +2853,6 @@ static int hclge_get_status(struct hnae3_handle *handle) return hdev->hw.mac.link; } -static void hclge_service_timer(struct timer_list *t) -{ - struct hclge_dev *hdev = from_timer(hdev, t, service_timer); - - mod_timer(&hdev->service_timer, jiffies + HZ); - hdev->hw_stats.stats_timer++; - hdev->fd_arfs_expire_timer++; - hclge_task_schedule(hdev); -} - -static void hclge_service_complete(struct hclge_dev *hdev) -{ - WARN_ON(!test_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state)); - - /* Flush memory before next watchdog */ - smp_mb__before_atomic(); - clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state); -} - static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) { u32 rst_src_reg, cmdq_src_reg, msix_src_reg; @@ -2763,9 +2868,9 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) * defer the processing of the mailbox events. Since, we would have not * cleared RX CMDQ event this time we would receive again another * interrupt from H/W just for the mailbox. + * + * check for vector0 reset event sources */ - - /* check for vector0 reset event sources */ if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & rst_src_reg) { dev_info(&hdev->pdev->dev, "IMP reset interrupt\n"); set_bit(HNAE3_IMP_RESET, &hdev->reset_pending); @@ -2882,10 +2987,15 @@ static irqreturn_t hclge_misc_irq_handle(int irq, void *data) break; } - /* clear the source of interrupt if it is not cause by reset */ + hclge_clear_event_cause(hdev, event_cause, clearval); + + /* Enable interrupt if it is not cause by reset. And when + * clearval equal to 0, it means interrupt status may be + * cleared by hardware before driver reads status register. + * For this case, vector0 interrupt also should be enabled. + */ if (!clearval || event_cause == HCLGE_VECTOR0_EVENT_MBX) { - hclge_clear_event_cause(hdev, event_cause, clearval); hclge_enable_vector(&hdev->misc_vector, true); } @@ -2918,6 +3028,36 @@ static void hclge_get_misc_vector(struct hclge_dev *hdev) hdev->num_msi_used += 1; } +static void hclge_irq_affinity_notify(struct irq_affinity_notify *notify, + const cpumask_t *mask) +{ + struct hclge_dev *hdev = container_of(notify, struct hclge_dev, + affinity_notify); + + cpumask_copy(&hdev->affinity_mask, mask); +} + +static void hclge_irq_affinity_release(struct kref *ref) +{ +} + +static void hclge_misc_affinity_setup(struct hclge_dev *hdev) +{ + irq_set_affinity_hint(hdev->misc_vector.vector_irq, + &hdev->affinity_mask); + + hdev->affinity_notify.notify = hclge_irq_affinity_notify; + hdev->affinity_notify.release = hclge_irq_affinity_release; + irq_set_affinity_notifier(hdev->misc_vector.vector_irq, + &hdev->affinity_notify); +} + +static void hclge_misc_affinity_teardown(struct hclge_dev *hdev) +{ + irq_set_affinity_notifier(hdev->misc_vector.vector_irq, NULL); + irq_set_affinity_hint(hdev->misc_vector.vector_irq, NULL); +} + static int hclge_misc_irq_init(struct hclge_dev *hdev) { int ret; @@ -3105,6 +3245,71 @@ static int hclge_set_all_vf_rst(struct hclge_dev *hdev, bool reset) return 0; } +static int hclge_func_reset_sync_vf(struct hclge_dev *hdev) +{ + struct hclge_pf_rst_sync_cmd *req; + struct hclge_desc desc; + int cnt = 0; + int ret; + + req = (struct hclge_pf_rst_sync_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QUERY_VF_RST_RDY, true); + + do { + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + /* for compatible with old firmware, wait + * 100 ms for VF to stop IO + */ + if (ret == -EOPNOTSUPP) { + msleep(HCLGE_RESET_SYNC_TIME); + return 0; + } else if (ret) { + dev_err(&hdev->pdev->dev, "sync with VF fail %d!\n", + ret); + return ret; + } else if (req->all_vf_ready) { + return 0; + } + msleep(HCLGE_PF_RESET_SYNC_TIME); + hclge_cmd_reuse_desc(&desc, true); + } while (cnt++ < HCLGE_PF_RESET_SYNC_CNT); + + dev_err(&hdev->pdev->dev, "sync with VF timeout!\n"); + return -ETIME; +} + +void hclge_report_hw_error(struct hclge_dev *hdev, + enum hnae3_hw_error_type type) +{ + struct hnae3_client *client = hdev->nic_client; + u16 i; + + if (!client || !client->ops->process_hw_error || + !test_bit(HCLGE_STATE_NIC_REGISTERED, &hdev->state)) + return; + + for (i = 0; i < hdev->num_vmdq_vport + 1; i++) + client->ops->process_hw_error(&hdev->vport[i].nic, type); +} + +static void hclge_handle_imp_error(struct hclge_dev *hdev) +{ + u32 reg_val; + + reg_val = hclge_read_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG); + if (reg_val & BIT(HCLGE_VECTOR0_IMP_RD_POISON_B)) { + hclge_report_hw_error(hdev, HNAE3_IMP_RD_POISON_ERROR); + reg_val &= ~BIT(HCLGE_VECTOR0_IMP_RD_POISON_B); + hclge_write_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG, reg_val); + } + + if (reg_val & BIT(HCLGE_VECTOR0_IMP_CMDQ_ERR_B)) { + hclge_report_hw_error(hdev, HNAE3_CMDQ_ECC_ERROR); + reg_val &= ~BIT(HCLGE_VECTOR0_IMP_CMDQ_ERR_B); + hclge_write_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG, reg_val); + } +} + int hclge_func_reset_cmd(struct hclge_dev *hdev, int func_id) { struct hclge_desc desc; @@ -3229,7 +3434,13 @@ static void hclge_clear_reset_cause(struct hclge_dev *hdev) if (!clearval) return; - hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, clearval); + /* For revision 0x20, the reset interrupt source + * can only be cleared after hardware reset done + */ + if (hdev->pdev->revision == 0x20) + hclge_write_dev(&hdev->hw, HCLGE_MISC_RESET_STS_REG, + clearval); + hclge_enable_vector(&hdev->misc_vector, true); } @@ -3250,19 +3461,33 @@ static int hclge_reset_prepare_down(struct hclge_dev *hdev) return ret; } -static int hclge_reset_prepare_wait(struct hclge_dev *hdev) +static void hclge_reset_handshake(struct hclge_dev *hdev, bool enable) { -#define HCLGE_RESET_SYNC_TIME 100 + u32 reg_val; + reg_val = hclge_read_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG); + if (enable) + reg_val |= HCLGE_NIC_SW_RST_RDY; + else + reg_val &= ~HCLGE_NIC_SW_RST_RDY; + + hclge_write_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG, reg_val); +} + +static int hclge_reset_prepare_wait(struct hclge_dev *hdev) +{ u32 reg_val; int ret = 0; switch (hdev->reset_type) { case HNAE3_FUNC_RESET: - /* There is no mechanism for PF to know if VF has stopped IO - * for now, just wait 100 ms for VF to stop IO + /* to confirm whether all running VF is ready + * before request PF reset */ - msleep(HCLGE_RESET_SYNC_TIME); + ret = hclge_func_reset_sync_vf(hdev); + if (ret) + return ret; + ret = hclge_func_reset_cmd(hdev, 0); if (ret) { dev_err(&hdev->pdev->dev, @@ -3279,15 +3504,19 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev) hdev->rst_stats.pf_rst_cnt++; break; case HNAE3_FLR_RESET: - /* There is no mechanism for PF to know if VF has stopped IO - * for now, just wait 100 ms for VF to stop IO + /* to confirm whether all running VF is ready + * before request PF reset */ - msleep(HCLGE_RESET_SYNC_TIME); + ret = hclge_func_reset_sync_vf(hdev); + if (ret) + return ret; + set_bit(HCLGE_STATE_CMD_DISABLE, &hdev->state); set_bit(HNAE3_FLR_DOWN, &hdev->flr_state); hdev->rst_stats.flr_rst_cnt++; break; case HNAE3_IMP_RESET: + hclge_handle_imp_error(hdev); reg_val = hclge_read_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG); hclge_write_dev(&hdev->hw, HCLGE_PF_OTHER_INT_REG, BIT(HCLGE_VECTOR0_IMP_RESET_INT_B) | reg_val); @@ -3298,14 +3527,13 @@ static int hclge_reset_prepare_wait(struct hclge_dev *hdev) /* inform hardware that preparatory work is done */ msleep(HCLGE_RESET_SYNC_TIME); - hclge_write_dev(&hdev->hw, HCLGE_NIC_CSQ_DEPTH_REG, - HCLGE_NIC_CMQ_ENABLE); + hclge_reset_handshake(hdev, true); dev_info(&hdev->pdev->dev, "prepare wait ok\n"); return ret; } -static bool hclge_reset_err_handle(struct hclge_dev *hdev, bool is_timeout) +static bool hclge_reset_err_handle(struct hclge_dev *hdev) { #define MAX_RESET_FAIL_CNT 5 @@ -3313,36 +3541,42 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev, bool is_timeout) dev_info(&hdev->pdev->dev, "Reset pending %lu\n", hdev->reset_pending); return true; - } else if ((hdev->reset_type != HNAE3_IMP_RESET) && - (hclge_read_dev(&hdev->hw, HCLGE_GLOBAL_RESET_REG) & - BIT(HCLGE_IMP_RESET_BIT))) { + } else if (hclge_read_dev(&hdev->hw, HCLGE_MISC_VECTOR_INT_STS) & + HCLGE_RESET_INT_M) { dev_info(&hdev->pdev->dev, - "reset failed because IMP Reset is pending\n"); + "reset failed because new reset interrupt\n"); hclge_clear_reset_cause(hdev); return false; - } else if (hdev->reset_fail_cnt < MAX_RESET_FAIL_CNT) { - hdev->reset_fail_cnt++; - if (is_timeout) { - set_bit(hdev->reset_type, &hdev->reset_pending); - dev_info(&hdev->pdev->dev, - "re-schedule to wait for hw reset done\n"); - return true; - } - - dev_info(&hdev->pdev->dev, "Upgrade reset level\n"); - hclge_clear_reset_cause(hdev); - set_bit(HNAE3_GLOBAL_RESET, &hdev->default_reset_request); - mod_timer(&hdev->reset_timer, - jiffies + HCLGE_RESET_INTERVAL); - - return false; + } else if (hdev->rst_stats.reset_fail_cnt < MAX_RESET_FAIL_CNT) { + hdev->rst_stats.reset_fail_cnt++; + set_bit(hdev->reset_type, &hdev->reset_pending); + dev_info(&hdev->pdev->dev, + "re-schedule reset task(%d)\n", + hdev->rst_stats.reset_fail_cnt); + return true; } hclge_clear_reset_cause(hdev); + + /* recover the handshake status when reset fail */ + hclge_reset_handshake(hdev, true); + dev_err(&hdev->pdev->dev, "Reset fail!\n"); return false; } +static int hclge_set_rst_done(struct hclge_dev *hdev) +{ + struct hclge_pf_rst_done_cmd *req; + struct hclge_desc desc; + + req = (struct hclge_pf_rst_done_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_PF_RST_DONE, false); + req->pf_rst_done |= HCLGE_PF_RESET_DONE_BIT; + + return hclge_cmd_send(&hdev->hw, &desc, 1); +} + static int hclge_reset_prepare_up(struct hclge_dev *hdev) { int ret = 0; @@ -3353,10 +3587,18 @@ static int hclge_reset_prepare_up(struct hclge_dev *hdev) case HNAE3_FLR_RESET: ret = hclge_set_all_vf_rst(hdev, false); break; + case HNAE3_GLOBAL_RESET: + /* fall through */ + case HNAE3_IMP_RESET: + ret = hclge_set_rst_done(hdev); + break; default: break; } + /* clear up the handshake status after re-initialize done */ + hclge_reset_handshake(hdev, false); + return ret; } @@ -3382,7 +3624,7 @@ static int hclge_reset_stack(struct hclge_dev *hdev) static void hclge_reset(struct hclge_dev *hdev) { struct hnae3_ae_dev *ae_dev = pci_get_drvdata(hdev->pdev); - bool is_timeout = false; + enum hnae3_reset_type reset_level; int ret; /* Initialize ae_dev reset status as well, in case enet layer wants to @@ -3410,10 +3652,8 @@ static void hclge_reset(struct hclge_dev *hdev) if (ret) goto err_reset; - if (hclge_reset_wait(hdev)) { - is_timeout = true; + if (hclge_reset_wait(hdev)) goto err_reset; - } hdev->rst_stats.hw_reset_done_cnt++; @@ -3439,7 +3679,8 @@ static void hclge_reset(struct hclge_dev *hdev) /* ignore RoCE notify error if it fails HCLGE_RESET_MAX_FAIL_CNT - 1 * times */ - if (ret && hdev->reset_fail_cnt < HCLGE_RESET_MAX_FAIL_CNT - 1) + if (ret && + hdev->rst_stats.reset_fail_cnt < HCLGE_RESET_MAX_FAIL_CNT - 1) goto err_reset; rtnl_lock(); @@ -3455,17 +3696,25 @@ static void hclge_reset(struct hclge_dev *hdev) goto err_reset; hdev->last_reset_time = jiffies; - hdev->reset_fail_cnt = 0; + hdev->rst_stats.reset_fail_cnt = 0; hdev->rst_stats.reset_done_cnt++; ae_dev->reset_type = HNAE3_NONE_RESET; - del_timer(&hdev->reset_timer); + + /* if default_reset_request has a higher level reset request, + * it should be handled as soon as possible. since some errors + * need this kind of reset to fix. + */ + reset_level = hclge_get_reset_level(ae_dev, + &hdev->default_reset_request); + if (reset_level != HNAE3_NONE_RESET) + set_bit(reset_level, &hdev->reset_request); return; err_reset_lock: rtnl_unlock(); err_reset: - if (hclge_reset_err_handle(hdev, is_timeout)) + if (hclge_reset_err_handle(hdev)) hclge_reset_task_schedule(hdev); } @@ -3493,16 +3742,17 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle) handle = &hdev->vport[0].nic; if (time_before(jiffies, (hdev->last_reset_time + - HCLGE_RESET_INTERVAL))) + HCLGE_RESET_INTERVAL))) { + mod_timer(&hdev->reset_timer, jiffies + HCLGE_RESET_INTERVAL); return; - else if (hdev->default_reset_request) + } else if (hdev->default_reset_request) hdev->reset_level = hclge_get_reset_level(ae_dev, &hdev->default_reset_request); else if (time_after(jiffies, (hdev->last_reset_time + 4 * 5 * HZ))) hdev->reset_level = HNAE3_FUNC_RESET; - dev_info(&hdev->pdev->dev, "received reset event , reset type is %d", + dev_info(&hdev->pdev->dev, "received reset event, reset type is %d\n", hdev->reset_level); /* request reset & schedule reset task */ @@ -3525,6 +3775,12 @@ static void hclge_reset_timer(struct timer_list *t) { struct hclge_dev *hdev = from_timer(hdev, t, reset_timer); + /* if default_reset_request has no value, it means that this reset + * request has already be handled, so just return here + */ + if (!hdev->default_reset_request) + return; + dev_info(&hdev->pdev->dev, "triggering reset in reset timer\n"); hclge_reset_event(hdev->pdev, NULL); @@ -3606,7 +3862,9 @@ static void hclge_update_vport_alive(struct hclge_dev *hdev) static void hclge_service_task(struct work_struct *work) { struct hclge_dev *hdev = - container_of(work, struct hclge_dev, service_task); + container_of(work, struct hclge_dev, service_task.work); + + clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state); if (hdev->hw_stats.stats_timer >= HCLGE_STATS_TIMER_INTERVAL) { hclge_update_stats_for_all(hdev); @@ -3621,7 +3879,8 @@ static void hclge_service_task(struct work_struct *work) hclge_rfs_filter_expire(hdev); hdev->fd_arfs_expire_timer = 0; } - hclge_service_complete(hdev); + + hclge_task_schedule(hdev, round_jiffies_relative(HZ)); } struct hclge_vport *hclge_get_vport(struct hnae3_handle *handle) @@ -4197,8 +4456,8 @@ int hclge_bind_ring_with_vector(struct hclge_vport *vport, struct hclge_dev *hdev = vport->back; struct hnae3_ring_chain_node *node; struct hclge_desc desc; - struct hclge_ctrl_vector_chain_cmd *req - = (struct hclge_ctrl_vector_chain_cmd *)desc.data; + struct hclge_ctrl_vector_chain_cmd *req = + (struct hclge_ctrl_vector_chain_cmd *)desc.data; enum hclge_cmd_status status; enum hclge_opcode_type op; u16 tqp_type_and_id; @@ -5808,7 +6067,7 @@ static int hclge_add_fd_entry_by_arfs(struct hnae3_handle *handle, u16 queue_id, return -ENOSPC; } - rule = kzalloc(sizeof(*rule), GFP_KERNEL); + rule = kzalloc(sizeof(*rule), GFP_ATOMIC); if (!rule) { spin_unlock_bh(&hdev->fd_rule_lock); @@ -5921,7 +6180,7 @@ static void hclge_enable_fd(struct hnae3_handle *handle, bool enable) bool clear; hdev->fd_en = enable; - clear = hdev->fd_active_type == HCLGE_FD_ARFS_ACTIVE ? true : false; + clear = hdev->fd_active_type == HCLGE_FD_ARFS_ACTIVE; if (!enable) hclge_del_all_fd_entries(handle, clear); else @@ -5959,6 +6218,89 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) "mac enable fail, ret =%d.\n", ret); } +static int hclge_config_switch_param(struct hclge_dev *hdev, int vfid, + u8 switch_param, u8 param_mask) +{ + struct hclge_mac_vlan_switch_cmd *req; + struct hclge_desc desc; + u32 func_id; + int ret; + + func_id = hclge_get_port_number(HOST_PORT, 0, vfid, 0); + req = (struct hclge_mac_vlan_switch_cmd *)desc.data; + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_MAC_VLAN_SWITCH_PARAM, + false); + req->roce_sel = HCLGE_MAC_VLAN_NIC_SEL; + req->func_id = cpu_to_le32(func_id); + req->switch_param = switch_param; + req->param_mask = param_mask; + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "set mac vlan switch parameter fail, ret = %d\n", ret); + return ret; +} + +static void hclge_phy_link_status_wait(struct hclge_dev *hdev, + int link_ret) +{ +#define HCLGE_PHY_LINK_STATUS_NUM 200 + + struct phy_device *phydev = hdev->hw.mac.phydev; + int i = 0; + int ret; + + do { + ret = phy_read_status(phydev); + if (ret) { + dev_err(&hdev->pdev->dev, + "phy update link status fail, ret = %d\n", ret); + return; + } + + if (phydev->link == link_ret) + break; + + msleep(HCLGE_LINK_STATUS_MS); + } while (++i < HCLGE_PHY_LINK_STATUS_NUM); +} + +static int hclge_mac_link_status_wait(struct hclge_dev *hdev, int link_ret) +{ +#define HCLGE_MAC_LINK_STATUS_NUM 100 + + int i = 0; + int ret; + + do { + ret = hclge_get_mac_link_status(hdev); + if (ret < 0) + return ret; + else if (ret == link_ret) + return 0; + + msleep(HCLGE_LINK_STATUS_MS); + } while (++i < HCLGE_MAC_LINK_STATUS_NUM); + return -EBUSY; +} + +static int hclge_mac_phy_link_status_wait(struct hclge_dev *hdev, bool en, + bool is_phy) +{ +#define HCLGE_LINK_STATUS_DOWN 0 +#define HCLGE_LINK_STATUS_UP 1 + + int link_ret; + + link_ret = en ? HCLGE_LINK_STATUS_UP : HCLGE_LINK_STATUS_DOWN; + + if (is_phy) + hclge_phy_link_status_wait(hdev, link_ret); + + return hclge_mac_link_status_wait(hdev, link_ret); +} + static int hclge_set_app_loopback(struct hclge_dev *hdev, bool en) { struct hclge_config_mac_mode_cmd *req; @@ -5995,20 +6337,14 @@ static int hclge_set_app_loopback(struct hclge_dev *hdev, bool en) return ret; } -static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en, +static int hclge_cfg_serdes_loopback(struct hclge_dev *hdev, bool en, enum hnae3_loop loop_mode) { #define HCLGE_SERDES_RETRY_MS 10 #define HCLGE_SERDES_RETRY_NUM 100 -#define HCLGE_MAC_LINK_STATUS_MS 10 -#define HCLGE_MAC_LINK_STATUS_NUM 100 -#define HCLGE_MAC_LINK_STATUS_DOWN 0 -#define HCLGE_MAC_LINK_STATUS_UP 1 - struct hclge_serdes_lb_cmd *req; struct hclge_desc desc; - int mac_link_ret = 0; int ret, i = 0; u8 loop_mode_b; @@ -6031,10 +6367,8 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en, if (en) { req->enable = loop_mode_b; req->mask = loop_mode_b; - mac_link_ret = HCLGE_MAC_LINK_STATUS_UP; } else { req->mask = loop_mode_b; - mac_link_ret = HCLGE_MAC_LINK_STATUS_DOWN; } ret = hclge_cmd_send(&hdev->hw, &desc, 1); @@ -6064,21 +6398,84 @@ static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en, dev_err(&hdev->pdev->dev, "serdes loopback set failed in fw\n"); return -EIO; } + return ret; +} + +static int hclge_set_serdes_loopback(struct hclge_dev *hdev, bool en, + enum hnae3_loop loop_mode) +{ + int ret; + + ret = hclge_cfg_serdes_loopback(hdev, en, loop_mode); + if (ret) + return ret; hclge_cfg_mac_mode(hdev, en); - i = 0; - do { - /* serdes Internal loopback, independent of the network cable.*/ - msleep(HCLGE_MAC_LINK_STATUS_MS); - ret = hclge_get_mac_link_status(hdev); - if (ret == mac_link_ret) - return 0; - } while (++i < HCLGE_MAC_LINK_STATUS_NUM); + ret = hclge_mac_phy_link_status_wait(hdev, en, FALSE); + if (ret) + dev_err(&hdev->pdev->dev, + "serdes loopback config mac mode timeout\n"); - dev_err(&hdev->pdev->dev, "config mac mode timeout\n"); + return ret; +} - return -EBUSY; +static int hclge_enable_phy_loopback(struct hclge_dev *hdev, + struct phy_device *phydev) +{ + int ret; + + if (!phydev->suspended) { + ret = phy_suspend(phydev); + if (ret) + return ret; + } + + ret = phy_resume(phydev); + if (ret) + return ret; + + return phy_loopback(phydev, true); +} + +static int hclge_disable_phy_loopback(struct hclge_dev *hdev, + struct phy_device *phydev) +{ + int ret; + + ret = phy_loopback(phydev, false); + if (ret) + return ret; + + return phy_suspend(phydev); +} + +static int hclge_set_phy_loopback(struct hclge_dev *hdev, bool en) +{ + struct phy_device *phydev = hdev->hw.mac.phydev; + int ret; + + if (!phydev) + return -ENOTSUPP; + + if (en) + ret = hclge_enable_phy_loopback(hdev, phydev); + else + ret = hclge_disable_phy_loopback(hdev, phydev); + if (ret) { + dev_err(&hdev->pdev->dev, + "set phy loopback fail, ret = %d\n", ret); + return ret; + } + + hclge_cfg_mac_mode(hdev, en); + + ret = hclge_mac_phy_link_status_wait(hdev, en, TRUE); + if (ret) + dev_err(&hdev->pdev->dev, + "phy loopback config mac mode timeout\n"); + + return ret; } static int hclge_tqp_enable(struct hclge_dev *hdev, unsigned int tqp_id, @@ -6110,6 +6507,20 @@ static int hclge_set_loopback(struct hnae3_handle *handle, struct hclge_dev *hdev = vport->back; int i, ret; + /* Loopback can be enabled in three places: SSU, MAC, and serdes. By + * default, SSU loopback is enabled, so if the SMAC and the DMAC are + * the same, the packets are looped back in the SSU. If SSU loopback + * is disabled, packets can reach MAC even if SMAC is the same as DMAC. + */ + if (hdev->pdev->revision >= 0x21) { + u8 switch_param = en ? 0 : BIT(HCLGE_SWITCH_ALW_LPBK_B); + + ret = hclge_config_switch_param(hdev, PF_VPORT_ID, switch_param, + HCLGE_SWITCH_ALW_LPBK_MASK); + if (ret) + return ret; + } + switch (loop_mode) { case HNAE3_LOOP_APP: ret = hclge_set_app_loopback(hdev, en); @@ -6118,6 +6529,9 @@ static int hclge_set_loopback(struct hnae3_handle *handle, case HNAE3_LOOP_PARALLEL_SERDES: ret = hclge_set_serdes_loopback(hdev, en, loop_mode); break; + case HNAE3_LOOP_PHY: + ret = hclge_set_phy_loopback(hdev, en); + break; default: ret = -ENOTSUPP; dev_err(&hdev->pdev->dev, @@ -6138,6 +6552,22 @@ static int hclge_set_loopback(struct hnae3_handle *handle, return 0; } +static int hclge_set_default_loopback(struct hclge_dev *hdev) +{ + int ret; + + ret = hclge_set_app_loopback(hdev, false); + if (ret) + return ret; + + ret = hclge_cfg_serdes_loopback(hdev, false, HNAE3_LOOP_SERIAL_SERDES); + if (ret) + return ret; + + return hclge_cfg_serdes_loopback(hdev, false, + HNAE3_LOOP_PARALLEL_SERDES); +} + static void hclge_reset_tqp_stats(struct hnae3_handle *handle) { struct hclge_vport *vport = hclge_get_vport(handle); @@ -6160,10 +6590,13 @@ static void hclge_set_timer_task(struct hnae3_handle *handle, bool enable) struct hclge_dev *hdev = vport->back; if (enable) { - mod_timer(&hdev->service_timer, jiffies + HZ); + hclge_task_schedule(hdev, round_jiffies_relative(HZ)); } else { - del_timer_sync(&hdev->service_timer); - cancel_work_sync(&hdev->service_task); + /* Set the DOWN flag here to disable the service to be + * scheduled again + */ + set_bit(HCLGE_STATE_DOWN, &hdev->state); + cancel_delayed_work_sync(&hdev->service_task); clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state); } } @@ -6202,12 +6635,15 @@ static void hclge_ae_stop(struct hnae3_handle *handle) if (test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state) && hdev->reset_type != HNAE3_FUNC_RESET) { hclge_mac_stop_phy(hdev); + hclge_update_link_status(hdev); return; } for (i = 0; i < handle->kinfo.num_tqps; i++) hclge_reset_tqp(handle, i); + hclge_config_mac_tnl_int(hdev, false); + /* Mac disable */ hclge_cfg_mac_mode(hdev, false); @@ -6249,7 +6685,6 @@ static int hclge_get_mac_vlan_cmd_status(struct hclge_vport *vport, enum hclge_mac_vlan_tbl_opcode op) { struct hclge_dev *hdev = vport->back; - int return_status = -EIO; if (cmdq_resp) { dev_err(&hdev->pdev->dev, @@ -6260,52 +6695,53 @@ static int hclge_get_mac_vlan_cmd_status(struct hclge_vport *vport, if (op == HCLGE_MAC_VLAN_ADD) { if ((!resp_code) || (resp_code == 1)) { - return_status = 0; + return 0; } else if (resp_code == HCLGE_ADD_UC_OVERFLOW) { - return_status = -ENOSPC; dev_err(&hdev->pdev->dev, "add mac addr failed for uc_overflow.\n"); + return -ENOSPC; } else if (resp_code == HCLGE_ADD_MC_OVERFLOW) { - return_status = -ENOSPC; dev_err(&hdev->pdev->dev, "add mac addr failed for mc_overflow.\n"); - } else { - dev_err(&hdev->pdev->dev, - "add mac addr failed for undefined, code=%d.\n", - resp_code); + return -ENOSPC; } + + dev_err(&hdev->pdev->dev, + "add mac addr failed for undefined, code=%u.\n", + resp_code); + return -EIO; } else if (op == HCLGE_MAC_VLAN_REMOVE) { if (!resp_code) { - return_status = 0; + return 0; } else if (resp_code == 1) { - return_status = -ENOENT; dev_dbg(&hdev->pdev->dev, "remove mac addr failed for miss.\n"); - } else { - dev_err(&hdev->pdev->dev, - "remove mac addr failed for undefined, code=%d.\n", - resp_code); + return -ENOENT; } + + dev_err(&hdev->pdev->dev, + "remove mac addr failed for undefined, code=%u.\n", + resp_code); + return -EIO; } else if (op == HCLGE_MAC_VLAN_LKUP) { if (!resp_code) { - return_status = 0; + return 0; } else if (resp_code == 1) { - return_status = -ENOENT; dev_dbg(&hdev->pdev->dev, "lookup mac addr failed for miss.\n"); - } else { - dev_err(&hdev->pdev->dev, - "lookup mac addr failed for undefined, code=%d.\n", - resp_code); + return -ENOENT; } - } else { - return_status = -EINVAL; + dev_err(&hdev->pdev->dev, - "unknown opcode for get_mac_vlan_cmd_status,opcode=%d.\n", - op); + "lookup mac addr failed for undefined, code=%u.\n", + resp_code); + return -EIO; } - return return_status; + dev_err(&hdev->pdev->dev, + "unknown opcode for get_mac_vlan_cmd_status, opcode=%d.\n", op); + + return -EINVAL; } static int hclge_update_desc_vfid(struct hclge_desc *desc, int vfid, bool clr) @@ -7019,7 +7455,7 @@ static int hclge_set_mac_addr(struct hnae3_handle *handle, void *p, is_broadcast_ether_addr(new_addr) || is_multicast_ether_addr(new_addr)) { dev_err(&hdev->pdev->dev, - "Change uc mac err! invalid mac:%p.\n", + "Change uc mac err! invalid mac:%pM.\n", new_addr); return -EINVAL; } @@ -7124,7 +7560,7 @@ static void hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable) } static int hclge_set_vf_vlan_common(struct hclge_dev *hdev, u16 vfid, - bool is_kill, u16 vlan, u8 qos, + bool is_kill, u16 vlan, __be16 proto) { #define HCLGE_MAX_VF_BYTES 16 @@ -7235,7 +7671,7 @@ static int hclge_set_port_vlan_filter(struct hclge_dev *hdev, __be16 proto, } static int hclge_set_vlan_filter_hw(struct hclge_dev *hdev, __be16 proto, - u16 vport_id, u16 vlan_id, u8 qos, + u16 vport_id, u16 vlan_id, bool is_kill) { u16 vport_idx, vport_num = 0; @@ -7245,7 +7681,7 @@ static int hclge_set_vlan_filter_hw(struct hclge_dev *hdev, __be16 proto, return 0; ret = hclge_set_vf_vlan_common(hdev, vport_id, is_kill, vlan_id, - 0, proto); + proto); if (ret) { dev_err(&hdev->pdev->dev, "Set %d vport vlan filter config fail, ret =%d.\n", @@ -7289,6 +7725,7 @@ static int hclge_set_vlan_tx_offload_cfg(struct hclge_vport *vport) struct hclge_vport_vtag_tx_cfg_cmd *req; struct hclge_dev *hdev = vport->back; struct hclge_desc desc; + u16 bmap_index; int status; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_PORT_TX_CFG, false); @@ -7311,8 +7748,10 @@ static int hclge_set_vlan_tx_offload_cfg(struct hclge_vport *vport) hnae3_set_bit(req->vport_vlan_cfg, HCLGE_CFG_NIC_ROCE_SEL_B, 0); req->vf_offset = vport->vport_id / HCLGE_VF_NUM_PER_CMD; - req->vf_bitmap[req->vf_offset] = - 1 << (vport->vport_id % HCLGE_VF_NUM_PER_BYTE); + bmap_index = vport->vport_id % HCLGE_VF_NUM_PER_CMD / + HCLGE_VF_NUM_PER_BYTE; + req->vf_bitmap[bmap_index] = + 1U << (vport->vport_id % HCLGE_VF_NUM_PER_BYTE); status = hclge_cmd_send(&hdev->hw, &desc, 1); if (status) @@ -7329,6 +7768,7 @@ static int hclge_set_vlan_rx_offload_cfg(struct hclge_vport *vport) struct hclge_vport_vtag_rx_cfg_cmd *req; struct hclge_dev *hdev = vport->back; struct hclge_desc desc; + u16 bmap_index; int status; hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_VLAN_PORT_RX_CFG, false); @@ -7344,8 +7784,10 @@ static int hclge_set_vlan_rx_offload_cfg(struct hclge_vport *vport) vcfg->vlan2_vlan_prionly ? 1 : 0); req->vf_offset = vport->vport_id / HCLGE_VF_NUM_PER_CMD; - req->vf_bitmap[req->vf_offset] = - 1 << (vport->vport_id % HCLGE_VF_NUM_PER_BYTE); + bmap_index = vport->vport_id % HCLGE_VF_NUM_PER_CMD / + HCLGE_VF_NUM_PER_BYTE; + req->vf_bitmap[bmap_index] = + 1U << (vport->vport_id % HCLGE_VF_NUM_PER_BYTE); status = hclge_cmd_send(&hdev->hw, &desc, 1); if (status) @@ -7532,7 +7974,7 @@ static int hclge_add_vport_all_vlan_table(struct hclge_vport *vport) if (!vlan->hd_tbl_status) { ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), vport->vport_id, - vlan->vlan_id, 0, false); + vlan->vlan_id, false); if (ret) { dev_err(&hdev->pdev->dev, "restore vport vlan list failed, ret=%d\n", @@ -7558,7 +8000,7 @@ static void hclge_rm_vport_vlan_table(struct hclge_vport *vport, u16 vlan_id, hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), vport->vport_id, - vlan_id, 0, + vlan_id, true); list_del(&vlan->node); @@ -7578,7 +8020,7 @@ void hclge_rm_vport_all_vlan_table(struct hclge_vport *vport, bool is_del_list) hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), vport->vport_id, - vlan->vlan_id, 0, + vlan->vlan_id, true); vlan->hd_tbl_status = false; @@ -7611,7 +8053,7 @@ static void hclge_restore_vlan_table(struct hnae3_handle *handle) struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_vport_vlan_cfg *vlan, *tmp; struct hclge_dev *hdev = vport->back; - u16 vlan_proto, qos; + u16 vlan_proto; u16 state, vlan_id; int i; @@ -7620,12 +8062,11 @@ static void hclge_restore_vlan_table(struct hnae3_handle *handle) vport = &hdev->vport[i]; vlan_proto = vport->port_base_vlan_cfg.vlan_info.vlan_proto; vlan_id = vport->port_base_vlan_cfg.vlan_info.vlan_tag; - qos = vport->port_base_vlan_cfg.vlan_info.qos; state = vport->port_base_vlan_cfg.state; if (state != HNAE3_PORT_BASE_VLAN_DISABLE) { hclge_set_vlan_filter_hw(hdev, htons(vlan_proto), - vport->vport_id, vlan_id, qos, + vport->vport_id, vlan_id, false); continue; } @@ -7635,7 +8076,7 @@ static void hclge_restore_vlan_table(struct hnae3_handle *handle) hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), vport->vport_id, - vlan->vlan_id, 0, + vlan->vlan_id, false); } } @@ -7675,12 +8116,12 @@ static int hclge_update_vlan_filter_entries(struct hclge_vport *vport, htons(new_info->vlan_proto), vport->vport_id, new_info->vlan_tag, - new_info->qos, false); + false); } ret = hclge_set_vlan_filter_hw(hdev, htons(old_info->vlan_proto), vport->vport_id, old_info->vlan_tag, - old_info->qos, true); + true); if (ret) return ret; @@ -7707,7 +8148,7 @@ int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state, htons(vlan_info->vlan_proto), vport->vport_id, vlan_info->vlan_tag, - vlan_info->qos, false); + false); if (ret) return ret; @@ -7716,7 +8157,7 @@ int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state, htons(old_vlan_info->vlan_proto), vport->vport_id, old_vlan_info->vlan_tag, - old_vlan_info->qos, true); + true); if (ret) return ret; @@ -7829,7 +8270,7 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, return -EBUSY; } - /* When port base vlan enabled, we use port base vlan as the vlan + /* when port base vlan enabled, we use port base vlan as the vlan * filter entry. In this case, we don't update vlan filter table * when user add new vlan or remove exist vlan, just update the vport * vlan list. The vlan id in vlan list will be writen in vlan filter @@ -7837,7 +8278,7 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, */ if (handle->port_base_vlan_state == HNAE3_PORT_BASE_VLAN_DISABLE) { ret = hclge_set_vlan_filter_hw(hdev, proto, vport->vport_id, - vlan_id, 0, is_kill); + vlan_id, is_kill); writen_to_tbl = true; } @@ -7848,7 +8289,7 @@ int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, hclge_add_vport_vlan_table(vport, vlan_id, writen_to_tbl); } else if (is_kill) { - /* When remove hw vlan filter failed, record the vlan id, + /* when remove hw vlan filter failed, record the vlan id, * and try to remove it from hw later, to be consistence * with stack */ @@ -7873,7 +8314,7 @@ static void hclge_sync_vlan_filter(struct hclge_dev *hdev) while (vlan_id != VLAN_N_VID) { ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), vport->vport_id, vlan_id, - 0, true); + true); if (ret && ret != -EINVAL) return; @@ -8044,11 +8485,12 @@ int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id) } while (reset_try_times++ < HCLGE_TQP_RESET_TRY_TIMES) { - /* Wait for tqp hw reset */ - msleep(20); reset_status = hclge_get_reset_status(hdev, queue_gid); if (reset_status) break; + + /* Wait for tqp hw reset */ + usleep_range(1000, 1200); } if (reset_try_times >= HCLGE_TQP_RESET_TRY_TIMES) { @@ -8082,11 +8524,12 @@ void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id) } while (reset_try_times++ < HCLGE_TQP_RESET_TRY_TIMES) { - /* Wait for tqp hw reset */ - msleep(20); reset_status = hclge_get_reset_status(hdev, queue_gid); if (reset_status) break; + + /* Wait for tqp hw reset */ + usleep_range(1000, 1200); } if (reset_try_times >= HCLGE_TQP_RESET_TRY_TIMES) { @@ -8122,28 +8565,15 @@ static int hclge_cfg_pauseparam(struct hclge_dev *hdev, u32 rx_en, u32 tx_en) { int ret; - if (rx_en && tx_en) - hdev->fc_mode_last_time = HCLGE_FC_FULL; - else if (rx_en && !tx_en) - hdev->fc_mode_last_time = HCLGE_FC_RX_PAUSE; - else if (!rx_en && tx_en) - hdev->fc_mode_last_time = HCLGE_FC_TX_PAUSE; - else - hdev->fc_mode_last_time = HCLGE_FC_NONE; - if (hdev->tm_info.fc_mode == HCLGE_FC_PFC) return 0; ret = hclge_mac_pause_en_cfg(hdev, tx_en, rx_en); - if (ret) { - dev_err(&hdev->pdev->dev, "configure pauseparam error, ret = %d.\n", - ret); - return ret; - } - - hdev->tm_info.fc_mode = hdev->fc_mode_last_time; + if (ret) + dev_err(&hdev->pdev->dev, + "configure pauseparam error, ret = %d.\n", ret); - return 0; + return ret; } int hclge_cfg_flowctrl(struct hclge_dev *hdev) @@ -8208,6 +8638,21 @@ static void hclge_get_pauseparam(struct hnae3_handle *handle, u32 *auto_neg, } } +static void hclge_record_user_pauseparam(struct hclge_dev *hdev, + u32 rx_en, u32 tx_en) +{ + if (rx_en && tx_en) + hdev->fc_mode_last_time = HCLGE_FC_FULL; + else if (rx_en && !tx_en) + hdev->fc_mode_last_time = HCLGE_FC_RX_PAUSE; + else if (!rx_en && tx_en) + hdev->fc_mode_last_time = HCLGE_FC_TX_PAUSE; + else + hdev->fc_mode_last_time = HCLGE_FC_NONE; + + hdev->tm_info.fc_mode = hdev->fc_mode_last_time; +} + static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg, u32 rx_en, u32 tx_en) { @@ -8233,6 +8678,8 @@ static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg, hclge_set_flowctrl_adv(hdev, rx_en, tx_en); + hclge_record_user_pauseparam(hdev, rx_en, tx_en); + if (!auto_neg) return hclge_cfg_pauseparam(hdev, rx_en, tx_en); @@ -8481,7 +8928,7 @@ static int hclge_init_client_instance(struct hnae3_client *client, } } - return ret; + return 0; clear_nic: hdev->nic_client = NULL; @@ -8602,12 +9049,10 @@ static void hclge_state_uninit(struct hclge_dev *hdev) set_bit(HCLGE_STATE_DOWN, &hdev->state); set_bit(HCLGE_STATE_REMOVING, &hdev->state); - if (hdev->service_timer.function) - del_timer_sync(&hdev->service_timer); if (hdev->reset_timer.function) del_timer_sync(&hdev->reset_timer); - if (hdev->service_task.func) - cancel_work_sync(&hdev->service_task); + if (hdev->service_task.work.func) + cancel_delayed_work_sync(&hdev->service_task); if (hdev->rst_service_task.func) cancel_work_sync(&hdev->rst_service_task); if (hdev->mbx_service_task.func) @@ -8812,12 +9257,16 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_dcb_ops_set(hdev); - timer_setup(&hdev->service_timer, hclge_service_timer, 0); timer_setup(&hdev->reset_timer, hclge_reset_timer, 0); - INIT_WORK(&hdev->service_task, hclge_service_task); + INIT_DELAYED_WORK(&hdev->service_task, hclge_service_task); INIT_WORK(&hdev->rst_service_task, hclge_reset_service_task); INIT_WORK(&hdev->mbx_service_task, hclge_mailbox_service_task); + /* Setup affinity after service timer setup because add_timer_on + * is called in affinity notify. + */ + hclge_misc_affinity_setup(hdev); + hclge_clear_all_event_cause(hdev); hclge_clear_resetting_state(hdev); @@ -8842,7 +9291,9 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hclge_state_init(hdev); hdev->last_reset_time = jiffies; - pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME); + dev_info(&hdev->pdev->dev, "%s driver initialization finished.\n", + HCLGE_DRIVER_NAME); + return 0; err_mdiobus_unreg: @@ -8979,6 +9430,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev) struct hclge_dev *hdev = ae_dev->priv; struct hclge_mac *mac = &hdev->hw.mac; + hclge_misc_affinity_teardown(hdev); hclge_state_uninit(hdev); if (mac->phydev) @@ -9238,106 +9690,314 @@ static int hclge_get_64_bit_regs(struct hclge_dev *hdev, u32 regs_num, } #define MAX_SEPARATE_NUM 4 -#define SEPARATOR_VALUE 0xFFFFFFFF +#define SEPARATOR_VALUE 0xFDFCFBFA #define REG_NUM_PER_LINE 4 #define REG_LEN_PER_LINE (REG_NUM_PER_LINE * sizeof(u32)) +#define REG_SEPARATOR_LINE 1 +#define REG_NUM_REMAIN_MASK 3 +#define BD_LIST_MAX_NUM 30 -static int hclge_get_regs_len(struct hnae3_handle *handle) +int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, struct hclge_desc *desc) { - int cmdq_lines, common_lines, ring_lines, tqp_intr_lines; - struct hnae3_knic_private_info *kinfo = &handle->kinfo; - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - u32 regs_num_32_bit, regs_num_64_bit; + /*prepare 4 commands to query DFX BD number*/ + hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_DFX_BD_NUM, true); + desc[0].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[1], HCLGE_OPC_DFX_BD_NUM, true); + desc[1].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[2], HCLGE_OPC_DFX_BD_NUM, true); + desc[2].flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + hclge_cmd_setup_basic_desc(&desc[3], HCLGE_OPC_DFX_BD_NUM, true); + + return hclge_cmd_send(&hdev->hw, desc, 4); +} + +static int hclge_get_dfx_reg_bd_num(struct hclge_dev *hdev, + int *bd_num_list, + u32 type_num) +{ +#define HCLGE_DFX_REG_BD_NUM 4 + + u32 entries_per_desc, desc_index, index, offset, i; + struct hclge_desc desc[HCLGE_DFX_REG_BD_NUM]; int ret; - ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + ret = hclge_query_bd_num_cmd_send(hdev, desc); if (ret) { dev_err(&hdev->pdev->dev, - "Get register number failed, ret = %d.\n", ret); - return -EOPNOTSUPP; + "Get dfx bd num fail, status is %d.\n", ret); + return ret; } - cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + 1; - common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + 1; - ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + 1; - tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + 1; + entries_per_desc = ARRAY_SIZE(desc[0].data); + for (i = 0; i < type_num; i++) { + offset = hclge_dfx_bd_offset_list[i]; + index = offset % entries_per_desc; + desc_index = offset / entries_per_desc; + bd_num_list[i] = le32_to_cpu(desc[desc_index].data[index]); + } - return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps + - tqp_intr_lines * (hdev->num_msi_used - 1)) * REG_LEN_PER_LINE + - regs_num_32_bit * sizeof(u32) + regs_num_64_bit * sizeof(u64); + return ret; } -static void hclge_get_regs(struct hnae3_handle *handle, u32 *version, - void *data) +static int hclge_dfx_reg_cmd_send(struct hclge_dev *hdev, + struct hclge_desc *desc_src, int bd_num, + enum hclge_opcode_type cmd) { - struct hnae3_knic_private_info *kinfo = &handle->kinfo; - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - u32 regs_num_32_bit, regs_num_64_bit; - int i, j, reg_um, separator_num; + struct hclge_desc *desc = desc_src; + int i, ret; + + hclge_cmd_setup_basic_desc(desc, cmd, true); + for (i = 0; i < bd_num - 1; i++) { + desc->flag |= cpu_to_le16(HCLGE_CMD_FLAG_NEXT); + desc++; + hclge_cmd_setup_basic_desc(desc, cmd, true); + } + + desc = desc_src; + ret = hclge_cmd_send(&hdev->hw, desc, bd_num); + if (ret) + dev_err(&hdev->pdev->dev, + "Query dfx reg cmd(0x%x) send fail, status is %d.\n", + cmd, ret); + + return ret; +} + +static int hclge_dfx_reg_fetch_data(struct hclge_desc *desc_src, int bd_num, + void *data) +{ + int entries_per_desc, reg_num, separator_num, desc_index, index, i; + struct hclge_desc *desc = desc_src; u32 *reg = data; + + entries_per_desc = ARRAY_SIZE(desc->data); + reg_num = entries_per_desc * bd_num; + separator_num = REG_NUM_PER_LINE - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < reg_num; i++) { + index = i % entries_per_desc; + desc_index = i / entries_per_desc; + *reg++ = le32_to_cpu(desc[desc_index].data[index]); + } + for (i = 0; i < separator_num; i++) + *reg++ = SEPARATOR_VALUE; + + return reg_num + separator_num; +} + +static int hclge_get_dfx_reg_len(struct hclge_dev *hdev, int *len) +{ + u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list); + int data_len_per_desc, data_len, bd_num, i; + int bd_num_list[BD_LIST_MAX_NUM]; int ret; - *version = hdev->fw_version; + ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg bd num fail, status is %d.\n", ret); + return ret; + } - ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + data_len_per_desc = FIELD_SIZEOF(struct hclge_desc, data); + *len = 0; + for (i = 0; i < dfx_reg_type_num; i++) { + bd_num = bd_num_list[i]; + data_len = data_len_per_desc * bd_num; + *len += (data_len / REG_LEN_PER_LINE + 1) * REG_LEN_PER_LINE; + } + + return ret; +} + +static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data) +{ + u32 dfx_reg_type_num = ARRAY_SIZE(hclge_dfx_bd_offset_list); + int bd_num, bd_num_max, buf_len, i; + int bd_num_list[BD_LIST_MAX_NUM]; + struct hclge_desc *desc_src; + u32 *reg = data; + int ret; + + ret = hclge_get_dfx_reg_bd_num(hdev, bd_num_list, dfx_reg_type_num); if (ret) { dev_err(&hdev->pdev->dev, - "Get register number failed, ret = %d.\n", ret); - return; + "Get dfx reg bd num fail, status is %d.\n", ret); + return ret; } + bd_num_max = bd_num_list[0]; + for (i = 1; i < dfx_reg_type_num; i++) + bd_num_max = max_t(int, bd_num_max, bd_num_list[i]); + + buf_len = sizeof(*desc_src) * bd_num_max; + desc_src = kzalloc(buf_len, GFP_KERNEL); + if (!desc_src) { + dev_err(&hdev->pdev->dev, "%s kzalloc failed\n", __func__); + return -ENOMEM; + } + + for (i = 0; i < dfx_reg_type_num; i++) { + bd_num = bd_num_list[i]; + ret = hclge_dfx_reg_cmd_send(hdev, desc_src, bd_num, + hclge_dfx_reg_opcode_list[i]); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg fail, status is %d.\n", ret); + break; + } + + reg += hclge_dfx_reg_fetch_data(desc_src, bd_num, reg); + } + + kfree(desc_src); + return ret; +} + +static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data, + struct hnae3_knic_private_info *kinfo) +{ +#define HCLGE_RING_REG_OFFSET 0x200 +#define HCLGE_RING_INT_REG_OFFSET 0x4 + + int i, j, reg_num, separator_num; + int data_num_sum; + u32 *reg = data; + /* fetching per-PF registers valus from PF PCIe register space */ - reg_um = sizeof(cmdq_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; - for (i = 0; i < reg_um; i++) + reg_num = ARRAY_SIZE(cmdq_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, cmdq_reg_addr_list[i]); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; + data_num_sum = reg_num + separator_num; - reg_um = sizeof(common_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; - for (i = 0; i < reg_um; i++) + reg_num = ARRAY_SIZE(common_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, common_reg_addr_list[i]); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; + data_num_sum += reg_num + separator_num; - reg_um = sizeof(ring_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; + reg_num = ARRAY_SIZE(ring_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); for (j = 0; j < kinfo->num_tqps; j++) { - for (i = 0; i < reg_um; i++) + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, ring_reg_addr_list[i] + - 0x200 * j); + HCLGE_RING_REG_OFFSET * j); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; } + data_num_sum += (reg_num + separator_num) * kinfo->num_tqps; - reg_um = sizeof(tqp_intr_reg_addr_list) / sizeof(u32); - separator_num = MAX_SEPARATE_NUM - reg_um % REG_NUM_PER_LINE; + reg_num = ARRAY_SIZE(tqp_intr_reg_addr_list); + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); for (j = 0; j < hdev->num_msi_used - 1; j++) { - for (i = 0; i < reg_um; i++) + for (i = 0; i < reg_num; i++) *reg++ = hclge_read_dev(&hdev->hw, tqp_intr_reg_addr_list[i] + - 4 * j); + HCLGE_RING_INT_REG_OFFSET * j); for (i = 0; i < separator_num; i++) *reg++ = SEPARATOR_VALUE; } + data_num_sum += (reg_num + separator_num) * (hdev->num_msi_used - 1); + + return data_num_sum; +} + +static int hclge_get_regs_len(struct hnae3_handle *handle) +{ + int cmdq_lines, common_lines, ring_lines, tqp_intr_lines; + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + int regs_num_32_bit, regs_num_64_bit, dfx_regs_len; + int regs_lines_32_bit, regs_lines_64_bit; + int ret; + + ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get register number failed, ret = %d.\n", ret); + return ret; + } + + ret = hclge_get_dfx_reg_len(hdev, &dfx_regs_len); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get dfx reg len failed, ret = %d.\n", ret); + return ret; + } + + cmdq_lines = sizeof(cmdq_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + common_lines = sizeof(common_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + ring_lines = sizeof(ring_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + tqp_intr_lines = sizeof(tqp_intr_reg_addr_list) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + regs_lines_32_bit = regs_num_32_bit * sizeof(u32) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + regs_lines_64_bit = regs_num_64_bit * sizeof(u64) / REG_LEN_PER_LINE + + REG_SEPARATOR_LINE; + + return (cmdq_lines + common_lines + ring_lines * kinfo->num_tqps + + tqp_intr_lines * (hdev->num_msi_used - 1) + regs_lines_32_bit + + regs_lines_64_bit) * REG_LEN_PER_LINE + dfx_regs_len; +} + +static void hclge_get_regs(struct hnae3_handle *handle, u32 *version, + void *data) +{ + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + u32 regs_num_32_bit, regs_num_64_bit; + int i, reg_num, separator_num, ret; + u32 *reg = data; + + *version = hdev->fw_version; + + ret = hclge_get_regs_num(hdev, ®s_num_32_bit, ®s_num_64_bit); + if (ret) { + dev_err(&hdev->pdev->dev, + "Get register number failed, ret = %d.\n", ret); + return; + } + + reg += hclge_fetch_pf_reg(hdev, reg, kinfo); - /* fetching PF common registers values from firmware */ ret = hclge_get_32_bit_regs(hdev, regs_num_32_bit, reg); if (ret) { dev_err(&hdev->pdev->dev, "Get 32 bit register failed, ret = %d.\n", ret); return; } + reg_num = regs_num_32_bit; + reg += reg_num; + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < separator_num; i++) + *reg++ = SEPARATOR_VALUE; - reg += regs_num_32_bit; ret = hclge_get_64_bit_regs(hdev, regs_num_64_bit, reg); - if (ret) + if (ret) { dev_err(&hdev->pdev->dev, "Get 64 bit register failed, ret = %d.\n", ret); + return; + } + reg_num = regs_num_64_bit * 2; + reg += reg_num; + separator_num = MAX_SEPARATE_NUM - (reg_num & REG_NUM_REMAIN_MASK); + for (i = 0; i < separator_num; i++) + *reg++ = SEPARATOR_VALUE; + + ret = hclge_get_dfx_reg(hdev, reg); + if (ret) + dev_err(&hdev->pdev->dev, + "Get dfx register failed, ret = %d.\n", ret); } static int hclge_set_led_status(struct hclge_dev *hdev, u8 locate_led_status) @@ -9452,7 +10112,7 @@ static const struct hnae3_ae_ops hclge_ops = { .set_mtu = hclge_set_mtu, .reset_queue = hclge_reset_tqp, .get_stats = hclge_get_stats, - .get_mac_pause_stats = hclge_get_mac_pause_stat, + .get_mac_stats = hclge_get_mac_stat, .update_stats = hclge_update_stats, .get_strings = hclge_get_strings, .get_sset_count = hclge_get_sset_count, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 6a12285f4c76..3e9574a9e22d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -119,7 +119,7 @@ #define HCLGE_DEFAULT_UMV_SPACE_PER_PF \ (HCLGE_UMV_TBL_SIZE / HCLGE_MAX_PF_NUM) -#define HCLGE_TQP_RESET_TRY_TIMES 10 +#define HCLGE_TQP_RESET_TRY_TIMES 200 #define HCLGE_PHY_PAGE_MDIX 0 #define HCLGE_PHY_PAGE_COPPER 0 @@ -148,6 +148,8 @@ enum HLCGE_PORT_TYPE { NETWORK_PORT }; +#define PF_VPORT_ID 0 + #define HCLGE_PF_ID_S 0 #define HCLGE_PF_ID_M GENMASK(2, 0) #define HCLGE_VF_ID_S 3 @@ -164,6 +166,7 @@ enum HLCGE_PORT_TYPE { #define HCLGE_GLOBAL_RESET_BIT 0 #define HCLGE_CORE_RESET_BIT 1 #define HCLGE_IMP_RESET_BIT 2 +#define HCLGE_RESET_INT_M GENMASK(2, 0) #define HCLGE_FUN_RST_ING 0x20C00 #define HCLGE_FUN_RST_ING_B 0 @@ -178,6 +181,8 @@ enum HLCGE_PORT_TYPE { #define HCLGE_VECTOR0_RX_CMDQ_INT_B 1 #define HCLGE_VECTOR0_IMP_RESET_INT_B 1 +#define HCLGE_VECTOR0_IMP_CMDQ_ERR_B 4U +#define HCLGE_VECTOR0_IMP_RD_POISON_B 5U #define HCLGE_MAC_DEFAULT_FRAME \ (ETH_HLEN + ETH_FCS_LEN + 2 * VLAN_HLEN + ETH_DATA_LEN) @@ -302,6 +307,13 @@ enum hclge_fc_mode { HCLGE_FC_DEFAULT }; +enum hclge_link_fail_code { + HCLGE_LF_NORMAL, + HCLGE_LF_REF_CLOCK_LOST, + HCLGE_LF_XSFP_TX_DISABLE, + HCLGE_LF_XSFP_ABSENT, +}; + #define HCLGE_PG_NUM 4 #define HCLGE_SCH_MODE_SP 0 #define HCLGE_SCH_MODE_DWRR 1 @@ -532,50 +544,6 @@ struct key_info { u8 key_length; /* use bit as unit */ }; -static const struct key_info meta_data_key_info[] = { - { PACKET_TYPE_ID, 6}, - { IP_FRAGEMENT, 1}, - { ROCE_TYPE, 1}, - { NEXT_KEY, 5}, - { VLAN_NUMBER, 2}, - { SRC_VPORT, 12}, - { DST_VPORT, 12}, - { TUNNEL_PACKET, 1}, -}; - -static const struct key_info tuple_key_info[] = { - { OUTER_DST_MAC, 48}, - { OUTER_SRC_MAC, 48}, - { OUTER_VLAN_TAG_FST, 16}, - { OUTER_VLAN_TAG_SEC, 16}, - { OUTER_ETH_TYPE, 16}, - { OUTER_L2_RSV, 16}, - { OUTER_IP_TOS, 8}, - { OUTER_IP_PROTO, 8}, - { OUTER_SRC_IP, 32}, - { OUTER_DST_IP, 32}, - { OUTER_L3_RSV, 16}, - { OUTER_SRC_PORT, 16}, - { OUTER_DST_PORT, 16}, - { OUTER_L4_RSV, 32}, - { OUTER_TUN_VNI, 24}, - { OUTER_TUN_FLOW_ID, 8}, - { INNER_DST_MAC, 48}, - { INNER_SRC_MAC, 48}, - { INNER_VLAN_TAG_FST, 16}, - { INNER_VLAN_TAG_SEC, 16}, - { INNER_ETH_TYPE, 16}, - { INNER_L2_RSV, 16}, - { INNER_IP_TOS, 8}, - { INNER_IP_PROTO, 8}, - { INNER_SRC_IP, 32}, - { INNER_DST_IP, 32}, - { INNER_L3_RSV, 16}, - { INNER_SRC_PORT, 16}, - { INNER_DST_PORT, 16}, - { INNER_L4_RSV, 32}, -}; - #define MAX_KEY_LENGTH 400 #define MAX_KEY_DWORDS DIV_ROUND_UP(MAX_KEY_LENGTH / 8, 4) #define MAX_KEY_BYTES (MAX_KEY_DWORDS * 4) @@ -691,6 +659,7 @@ struct hclge_rst_stats { u32 global_rst_cnt; /* the number of GLOBAL */ u32 imp_rst_cnt; /* the number of IMP reset */ u32 reset_cnt; /* the number of reset */ + u32 reset_fail_cnt; /* the number of reset fail */ }; /* time and register status when mac tunnel interruption occur */ @@ -757,7 +726,6 @@ struct hclge_dev { unsigned long reset_request; /* reset has been requested */ unsigned long reset_pending; /* client rst is pending to be served */ struct hclge_rst_stats rst_stats; - u32 reset_fail_cnt; u32 fw_version; u16 num_vmdq_vport; /* Num vmdq vport this PF has set up */ u16 num_tqps; /* Num task queue pairs of this PF */ @@ -806,9 +774,8 @@ struct hclge_dev { u16 adminq_work_limit; /* Num of admin receive queue desc to process */ unsigned long service_timer_period; unsigned long service_timer_previous; - struct timer_list service_timer; struct timer_list reset_timer; - struct work_struct service_task; + struct delayed_work service_task; struct work_struct rst_service_task; struct work_struct mbx_service_task; @@ -864,6 +831,10 @@ struct hclge_dev { DECLARE_KFIFO(mac_tnl_log, struct hclge_mac_tnl_stats, HCLGE_MAC_TNL_LOG_SIZE); + + /* affinity mask and notify for misc interrupt */ + cpumask_t affinity_mask; + struct irq_affinity_notify affinity_notify; }; /* VPort level vlan tag configuration for TX direction */ @@ -990,7 +961,6 @@ int hclge_buffer_alloc(struct hclge_dev *hdev); int hclge_rss_init_hw(struct hclge_dev *hdev); void hclge_rss_indir_init_cfg(struct hclge_dev *hdev); -int hclge_inform_reset_assert_to_vf(struct hclge_vport *vport); void hclge_mbx_handler(struct hclge_dev *hdev); int hclge_reset_tqp(struct hnae3_handle *handle, u16 queue_id); void hclge_reset_vf_queue(struct hclge_vport *vport, u16 queue_id); @@ -1018,4 +988,9 @@ int hclge_update_port_base_vlan_cfg(struct hclge_vport *vport, u16 state, int hclge_push_vf_port_base_vlan_info(struct hclge_vport *vport, u8 vfid, u16 state, u16 vlan_tag, u16 qos, u16 vlan_proto); +void hclge_task_schedule(struct hclge_dev *hdev, unsigned long delay_time); +int hclge_query_bd_num_cmd_send(struct hclge_dev *hdev, + struct hclge_desc *desc); +void hclge_report_hw_error(struct hclge_dev *hdev, + enum hnae3_hw_error_type type); #endif diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index 690b9990215c..f5da28a60d00 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -479,7 +479,7 @@ static void hclge_mbx_reset_vf_queue(struct hclge_vport *vport, hclge_reset_vf_queue(vport, queue_id); - /* send response msg to VF after queue reset complete*/ + /* send response msg to VF after queue reset complete */ hclge_gen_resp_to_vf(vport, mbx_req, 0, NULL, 0); } @@ -545,6 +545,36 @@ static int hclge_get_rss_key(struct hclge_vport *vport, HCLGE_RSS_MBX_RESP_LEN); } +static void hclge_link_fail_parse(struct hclge_dev *hdev, u8 link_fail_code) +{ + switch (link_fail_code) { + case HCLGE_LF_REF_CLOCK_LOST: + dev_warn(&hdev->pdev->dev, "Reference clock lost!\n"); + break; + case HCLGE_LF_XSFP_TX_DISABLE: + dev_warn(&hdev->pdev->dev, "SFP tx is disabled!\n"); + break; + case HCLGE_LF_XSFP_ABSENT: + dev_warn(&hdev->pdev->dev, "SFP is absent!\n"); + break; + default: + break; + } +} + +static void hclge_handle_link_change_event(struct hclge_dev *hdev, + struct hclge_mbx_vf_to_pf_cmd *req) +{ +#define LINK_STATUS_OFFSET 1 +#define LINK_FAIL_CODE_OFFSET 2 + + clear_bit(HCLGE_STATE_SERVICE_SCHED, &hdev->state); + hclge_task_schedule(hdev, 0); + + if (!req->msg[LINK_STATUS_OFFSET]) + hclge_link_fail_parse(hdev, req->msg[LINK_FAIL_CODE_OFFSET]); +} + static bool hclge_cmd_crq_empty(struct hclge_hw *hw) { u32 tail = hclge_read_dev(hw, HCLGE_NIC_CRQ_TAIL_REG); @@ -552,6 +582,15 @@ static bool hclge_cmd_crq_empty(struct hclge_hw *hw) return tail == hw->cmq.crq.next_to_use; } +static void hclge_handle_ncsi_error(struct hclge_dev *hdev) +{ + struct hnae3_ae_dev *ae_dev = hdev->ae_dev; + + ae_dev->ops->set_default_reset_request(ae_dev, HNAE3_GLOBAL_RESET); + dev_warn(&hdev->pdev->dev, "requesting reset due to NCSI error\n"); + ae_dev->ops->reset_event(hdev->pdev, NULL); +} + void hclge_mbx_handler(struct hclge_dev *hdev) { struct hclge_cmq_ring *crq = &hdev->hw.cmq.crq; @@ -707,6 +746,12 @@ void hclge_mbx_handler(struct hclge_dev *hdev) "PF fail(%d) to media type for VF\n", ret); break; + case HCLGE_MBX_PUSH_LINK_STATUS: + hclge_handle_link_change_event(hdev, req); + break; + case HCLGE_MBX_NCSI_ERROR: + hclge_handle_ncsi_error(hdev); + break; default: dev_err(&hdev->pdev->dev, "un-supported mailbox message, code = %d\n", diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index abb1b438564e..dc4dfd4602ab 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -231,6 +231,8 @@ int hclge_mac_connect_phy(struct hnae3_handle *handle) linkmode_clear_bit(ETHTOOL_LINK_MODE_Asym_Pause_BIT, phydev->advertising); + phy_attached_info(phydev); + return 0; } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 3f41fa2bc414..9f0e35f27789 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -81,16 +81,13 @@ static int hclge_shaper_para_calc(u32 ir, u8 shaper_level, return 0; } else if (ir_calc > ir) { /* Increasing the denominator to select ir_s value */ - while (ir_calc > ir) { + while (ir_calc >= ir && ir) { ir_s_calc++; ir_calc = DIVISOR_IR_B_126 / (tick * (1 << ir_s_calc)); } - if (ir_calc == ir) - *ir_b = 126; - else - *ir_b = (ir * tick * (1 << ir_s_calc) + - (DIVISOR_CLK >> 1)) / DIVISOR_CLK; + *ir_b = (ir * tick * (1 << ir_s_calc) + (DIVISOR_CLK >> 1)) / + DIVISOR_CLK; } else { /* Increasing the numerator to select ir_u value */ u32 numerator; @@ -104,7 +101,7 @@ static int hclge_shaper_para_calc(u32 ir, u8 shaper_level, if (ir_calc == ir) { *ir_b = 126; } else { - u32 denominator = (DIVISOR_CLK * (1 << --ir_u_calc)); + u32 denominator = DIVISOR_CLK * (1 << --ir_u_calc); *ir_b = (ir * tick + (denominator >> 1)) / denominator; } } @@ -404,8 +401,8 @@ static int hclge_tm_port_shaper_cfg(struct hclge_dev *hdev) { struct hclge_port_shapping_cmd *shap_cfg_cmd; struct hclge_desc desc; - u32 shapping_para = 0; u8 ir_u, ir_b, ir_s; + u32 shapping_para; int ret; ret = hclge_shaper_para_calc(hdev->hw.mac.speed, @@ -650,12 +647,8 @@ static void hclge_pfc_info_init(struct hclge_dev *hdev) } } -static int hclge_tm_schd_info_init(struct hclge_dev *hdev) +static void hclge_tm_schd_info_init(struct hclge_dev *hdev) { - if ((hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE) && - (hdev->tm_info.num_pg != 1)) - return -EINVAL; - hclge_tm_pg_info_init(hdev); hclge_tm_tc_info_init(hdev); @@ -663,8 +656,6 @@ static int hclge_tm_schd_info_init(struct hclge_dev *hdev) hclge_tm_vport_info_update(hdev); hclge_pfc_info_init(hdev); - - return 0; } static int hclge_tm_pg_to_pri_map(struct hclge_dev *hdev) @@ -1428,15 +1419,15 @@ int hclge_tm_init_hw(struct hclge_dev *hdev, bool init) int hclge_tm_schd_init(struct hclge_dev *hdev) { - int ret; - /* fc_mode is HCLGE_FC_FULL on reset */ hdev->tm_info.fc_mode = HCLGE_FC_FULL; hdev->fc_mode_last_time = hdev->tm_info.fc_mode; - ret = hclge_tm_schd_info_init(hdev); - if (ret) - return ret; + if (hdev->tx_sch_mode != HCLGE_FLAG_TC_BASE_SCH_MODE && + hdev->tm_info.num_pg != 1) + return -EINVAL; + + hclge_tm_schd_info_init(hdev); return hclge_tm_init_hw(hdev, true); } diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c index 652b796044e3..d5d1cc5d1b6e 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.c @@ -43,7 +43,7 @@ static int hclgevf_cmd_csq_clean(struct hclgevf_hw *hw) { struct hclgevf_dev *hdev = container_of(hw, struct hclgevf_dev, hw); struct hclgevf_cmq_ring *csq = &hw->cmq.csq; - int clean = 0; + int clean; u32 head; head = hclgevf_read_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG); @@ -74,7 +74,7 @@ static bool hclgevf_cmd_csq_done(struct hclgevf_hw *hw) static bool hclgevf_is_special_opcode(u16 opcode) { - u16 spec_opcode[] = {0x30, 0x31, 0x32}; + static const u16 spec_opcode[] = {0x30, 0x31, 0x32}; int i; for (i = 0; i < ARRAY_SIZE(spec_opcode); i++) { @@ -97,7 +97,9 @@ static void hclgevf_cmd_config_regs(struct hclgevf_cmq_ring *ring) reg_val = (u32)((ring->desc_dma_addr >> 31) >> 1); hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_BASEADDR_H_REG, reg_val); - reg_val = (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S); + reg_val = hclgevf_read_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG); + reg_val &= HCLGEVF_NIC_SW_RST_RDY; + reg_val |= (ring->desc_num >> HCLGEVF_NIC_CMQ_DESC_NUM_S); hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_DEPTH_REG, reg_val); hclgevf_write_dev(hw, HCLGEVF_NIC_CSQ_HEAD_REG, 0); @@ -405,7 +407,15 @@ int hclgevf_cmd_init(struct hclgevf_dev *hdev) } hdev->fw_version = version; - dev_info(&hdev->pdev->dev, "The firmware version is %08x\n", version); + dev_info(&hdev->pdev->dev, "The firmware version is %lu.%lu.%lu.%lu\n", + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE3_MASK, + HNAE3_FW_VERSION_BYTE3_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE2_MASK, + HNAE3_FW_VERSION_BYTE2_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE1_MASK, + HNAE3_FW_VERSION_BYTE1_SHIFT), + hnae3_get_field(version, HNAE3_FW_VERSION_BYTE0_MASK, + HNAE3_FW_VERSION_BYTE0_SHIFT)); return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h index 127a434a56f3..f830eef02e5c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_cmd.h @@ -244,8 +244,11 @@ struct hclgevf_cfg_tx_queue_pointer_cmd { #define HCLGEVF_NIC_CRQ_DEPTH_REG 0x27020 #define HCLGEVF_NIC_CRQ_TAIL_REG 0x27024 #define HCLGEVF_NIC_CRQ_HEAD_REG 0x27028 -#define HCLGEVF_NIC_CMQ_EN_B 16 -#define HCLGEVF_NIC_CMQ_ENABLE BIT(HCLGEVF_NIC_CMQ_EN_B) + +/* this bit indicates that the driver is ready for hardware reset */ +#define HCLGEVF_NIC_SW_RST_RDY_B 16 +#define HCLGEVF_NIC_SW_RST_RDY BIT(HCLGEVF_NIC_SW_RST_RDY_B) + #define HCLGEVF_NIC_CMQ_DESC_NUM 1024 #define HCLGEVF_NIC_CMQ_DESC_NUM_S 3 #define HCLGEVF_NIC_CMDQ_INT_SRC_REG 0x27100 diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index a13a0e101c3b..e3090b3dab1d 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -743,7 +743,7 @@ static int hclgevf_get_rss(struct hnae3_handle *handle, u32 *indir, u8 *key, } static int hclgevf_set_rss(struct hnae3_handle *handle, const u32 *indir, - const u8 *key, const u8 hfunc) + const u8 *key, const u8 hfunc) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg; @@ -1269,7 +1269,7 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle, HCLGE_MBX_VLAN_FILTER, msg_data, HCLGEVF_VLAN_MBX_MSG_LEN, false, NULL, 0); - /* When remove hw vlan filter failed, record the vlan id, + /* when remove hw vlan filter failed, record the vlan id, * and try to remove it from hw later, to be consistence * with stack. */ @@ -1396,19 +1396,22 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev) u32 val; int ret; - /* wait to check the hardware reset completion status */ - val = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING); - dev_info(&hdev->pdev->dev, "checking vf resetting status: %x\n", val); - if (hdev->reset_type == HNAE3_FLR_RESET) return hclgevf_flr_poll_timeout(hdev, HCLGEVF_RESET_WAIT_US, HCLGEVF_RESET_WAIT_CNT); - - ret = readl_poll_timeout(hdev->hw.io_base + HCLGEVF_RST_ING, val, - !(val & HCLGEVF_RST_ING_BITS), - HCLGEVF_RESET_WAIT_US, - HCLGEVF_RESET_WAIT_TIMEOUT_US); + else if (hdev->reset_type == HNAE3_VF_RESET) + ret = readl_poll_timeout(hdev->hw.io_base + + HCLGEVF_VF_RST_ING, val, + !(val & HCLGEVF_VF_RST_ING_BIT), + HCLGEVF_RESET_WAIT_US, + HCLGEVF_RESET_WAIT_TIMEOUT_US); + else + ret = readl_poll_timeout(hdev->hw.io_base + + HCLGEVF_RST_ING, val, + !(val & HCLGEVF_RST_ING_BITS), + HCLGEVF_RESET_WAIT_US, + HCLGEVF_RESET_WAIT_TIMEOUT_US); /* hardware completion status should be available by this time */ if (ret) { @@ -1426,6 +1429,20 @@ static int hclgevf_reset_wait(struct hclgevf_dev *hdev) return 0; } +static void hclgevf_reset_handshake(struct hclgevf_dev *hdev, bool enable) +{ + u32 reg_val; + + reg_val = hclgevf_read_dev(&hdev->hw, HCLGEVF_NIC_CSQ_DEPTH_REG); + if (enable) + reg_val |= HCLGEVF_NIC_SW_RST_RDY; + else + reg_val &= ~HCLGEVF_NIC_SW_RST_RDY; + + hclgevf_write_dev(&hdev->hw, HCLGEVF_NIC_CSQ_DEPTH_REG, + reg_val); +} + static int hclgevf_reset_stack(struct hclgevf_dev *hdev) { int ret; @@ -1448,7 +1465,14 @@ static int hclgevf_reset_stack(struct hclgevf_dev *hdev) if (ret) return ret; - return hclgevf_notify_client(hdev, HNAE3_RESTORE_CLIENT); + ret = hclgevf_notify_client(hdev, HNAE3_RESTORE_CLIENT); + if (ret) + return ret; + + /* clear handshake status with IMP */ + hclgevf_reset_handshake(hdev, false); + + return 0; } static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev) @@ -1474,8 +1498,7 @@ static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev) set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state); /* inform hardware that preparatory work is done */ msleep(HCLGEVF_RESET_SYNC_TIME); - hclgevf_write_dev(&hdev->hw, HCLGEVF_NIC_CSQ_DEPTH_REG, - HCLGEVF_NIC_CMQ_ENABLE); + hclgevf_reset_handshake(hdev, true); dev_info(&hdev->pdev->dev, "prepare reset(%d) wait done, ret:%d\n", hdev->reset_type, ret); @@ -1484,6 +1507,8 @@ static int hclgevf_reset_prepare_wait(struct hclgevf_dev *hdev) static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev) { + /* recover handshake status with IMP when reset fail */ + hclgevf_reset_handshake(hdev, true); hdev->rst_stats.rst_fail_cnt++; dev_err(&hdev->pdev->dev, "failed to reset VF(%d)\n", hdev->rst_stats.rst_fail_cnt); @@ -1494,9 +1519,6 @@ static void hclgevf_reset_err_handle(struct hclgevf_dev *hdev) if (hclgevf_is_reset_pending(hdev)) { set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); hclgevf_reset_task_schedule(hdev); - } else { - hclgevf_write_dev(&hdev->hw, HCLGEVF_NIC_CSQ_DEPTH_REG, - HCLGEVF_NIC_CMQ_ENABLE); } } @@ -1539,7 +1561,7 @@ static int hclgevf_reset(struct hclgevf_dev *hdev) rtnl_lock(); - /* now, re-initialize the nic client and ae device*/ + /* now, re-initialize the nic client and ae device */ ret = hclgevf_reset_stack(hdev); if (ret) { dev_err(&hdev->pdev->dev, "failed to reset VF stack\n"); @@ -1762,9 +1784,8 @@ static void hclgevf_reset_service_task(struct work_struct *work) * 1b and 2. cases but we will not get any intimation about 1a * from PF as cmdq would be in unreliable state i.e. mailbox * communication between PF and VF would be broken. - */ - - /* if we are never geting into pending state it means either: + * + * if we are never geting into pending state it means either: * 1. PF is not receiving our request which could be due to IMP * reset * 2. PF is screwed @@ -1867,29 +1888,45 @@ static void hclgevf_clear_event_cause(struct hclgevf_dev *hdev, u32 regclr) static enum hclgevf_evt_cause hclgevf_check_evt_cause(struct hclgevf_dev *hdev, u32 *clearval) { - u32 cmdq_src_reg, rst_ing_reg; + u32 val, cmdq_stat_reg, rst_ing_reg; /* fetch the events from their corresponding regs */ - cmdq_src_reg = hclgevf_read_dev(&hdev->hw, - HCLGEVF_VECTOR0_CMDQ_SRC_REG); + cmdq_stat_reg = hclgevf_read_dev(&hdev->hw, + HCLGEVF_VECTOR0_CMDQ_STAT_REG); - if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_src_reg) { + if (BIT(HCLGEVF_VECTOR0_RST_INT_B) & cmdq_stat_reg) { rst_ing_reg = hclgevf_read_dev(&hdev->hw, HCLGEVF_RST_ING); dev_info(&hdev->pdev->dev, "receive reset interrupt 0x%x!\n", rst_ing_reg); set_bit(HNAE3_VF_RESET, &hdev->reset_pending); set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); set_bit(HCLGEVF_STATE_CMD_DISABLE, &hdev->state); - cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RST_INT_B); - *clearval = cmdq_src_reg; + *clearval = ~(1U << HCLGEVF_VECTOR0_RST_INT_B); hdev->rst_stats.vf_rst_cnt++; + /* set up VF hardware reset status, its PF will clear + * this status when PF has initialized done. + */ + val = hclgevf_read_dev(&hdev->hw, HCLGEVF_VF_RST_ING); + hclgevf_write_dev(&hdev->hw, HCLGEVF_VF_RST_ING, + val | HCLGEVF_VF_RST_ING_BIT); return HCLGEVF_VECTOR0_EVENT_RST; } /* check for vector0 mailbox(=CMDQ RX) event source */ - if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_src_reg) { - cmdq_src_reg &= ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B); - *clearval = cmdq_src_reg; + if (BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B) & cmdq_stat_reg) { + /* for revision 0x21, clearing interrupt is writing bit 0 + * to the clear register, writing bit 1 means to keep the + * old value. + * for revision 0x20, the clear register is a read & write + * register, so we should just write 0 to the bit we are + * handling, and keep other bits as cmdq_stat_reg. + */ + if (hdev->pdev->revision >= 0x21) + *clearval = ~(1U << HCLGEVF_VECTOR0_RX_CMDQ_INT_B); + else + *clearval = cmdq_stat_reg & + ~BIT(HCLGEVF_VECTOR0_RX_CMDQ_INT_B); + return HCLGEVF_VECTOR0_EVENT_MBX; } @@ -2023,9 +2060,10 @@ static int hclgevf_config_gro(struct hclgevf_dev *hdev, bool en) static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev) { struct hclgevf_rss_cfg *rss_cfg = &hdev->rss_cfg; - int i, ret; + int ret; + u32 i; - rss_cfg->rss_size = hdev->rss_size_max; + rss_cfg->rss_size = hdev->nic.kinfo.rss_size; if (hdev->pdev->revision >= 0x21) { rss_cfg->hash_algo = HCLGEVF_RSS_HASH_ALGO_SIMPLE; @@ -2062,13 +2100,13 @@ static int hclgevf_rss_init_hw(struct hclgevf_dev *hdev) /* Initialize RSS indirect table */ for (i = 0; i < HCLGEVF_RSS_IND_TBL_SIZE; i++) - rss_cfg->rss_indirection_tbl[i] = i % hdev->rss_size_max; + rss_cfg->rss_indirection_tbl[i] = i % rss_cfg->rss_size; ret = hclgevf_set_rss_indir_table(hdev); if (ret) return ret; - return hclgevf_set_rss_tc_mode(hdev, hdev->rss_size_max); + return hclgevf_set_rss_tc_mode(hdev, rss_cfg->rss_size); } static int hclgevf_init_vlan_config(struct hclgevf_dev *hdev) @@ -2265,7 +2303,7 @@ static void hclgevf_uninit_msi(struct hclgevf_dev *hdev) static int hclgevf_misc_irq_init(struct hclgevf_dev *hdev) { - int ret = 0; + int ret; hclgevf_get_misc_vector(hdev); @@ -2695,7 +2733,8 @@ static int hclgevf_init_hdev(struct hclgevf_dev *hdev) } hdev->last_reset_time = jiffies; - pr_info("finished initializing %s driver\n", HCLGEVF_DRIVER_NAME); + dev_info(&hdev->pdev->dev, "finished initializing %s driver\n", + HCLGEVF_DRIVER_NAME); return 0; @@ -2797,6 +2836,77 @@ static void hclgevf_get_tqps_and_rss_info(struct hnae3_handle *handle, *max_rss_size = hdev->rss_size_max; } +static void hclgevf_update_rss_size(struct hnae3_handle *handle, + u32 new_tqps_num) +{ + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + u16 max_rss_size; + + kinfo->req_rss_size = new_tqps_num; + + max_rss_size = min_t(u16, hdev->rss_size_max, + hdev->num_tqps / kinfo->num_tc); + + /* Use the user's configuration when it is not larger than + * max_rss_size, otherwise, use the maximum specification value. + */ + if (kinfo->req_rss_size != kinfo->rss_size && kinfo->req_rss_size && + kinfo->req_rss_size <= max_rss_size) + kinfo->rss_size = kinfo->req_rss_size; + else if (kinfo->rss_size > max_rss_size || + (!kinfo->req_rss_size && kinfo->rss_size < max_rss_size)) + kinfo->rss_size = max_rss_size; + + kinfo->num_tqps = kinfo->num_tc * kinfo->rss_size; +} + +static int hclgevf_set_channels(struct hnae3_handle *handle, u32 new_tqps_num, + bool rxfh_configured) +{ + struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + struct hnae3_knic_private_info *kinfo = &handle->kinfo; + u16 cur_rss_size = kinfo->rss_size; + u16 cur_tqps = kinfo->num_tqps; + u32 *rss_indir; + unsigned int i; + int ret; + + hclgevf_update_rss_size(handle, new_tqps_num); + + ret = hclgevf_set_rss_tc_mode(hdev, kinfo->rss_size); + if (ret) + return ret; + + /* RSS indirection table has been configuared by user */ + if (rxfh_configured) + goto out; + + /* Reinitializes the rss indirect table according to the new RSS size */ + rss_indir = kcalloc(HCLGEVF_RSS_IND_TBL_SIZE, sizeof(u32), GFP_KERNEL); + if (!rss_indir) + return -ENOMEM; + + for (i = 0; i < HCLGEVF_RSS_IND_TBL_SIZE; i++) + rss_indir[i] = i % kinfo->rss_size; + + ret = hclgevf_set_rss(handle, rss_indir, NULL, 0); + if (ret) + dev_err(&hdev->pdev->dev, "set rss indir table fail, ret=%d\n", + ret); + + kfree(rss_indir); + +out: + if (!ret) + dev_info(&hdev->pdev->dev, + "Channels changed, rss_size from %u to %u, tqps from %u to %u", + cur_rss_size, kinfo->rss_size, + cur_tqps, kinfo->rss_size * kinfo->num_tc); + + return ret; +} + static int hclgevf_get_status(struct hnae3_handle *handle) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); @@ -3004,6 +3114,7 @@ static const struct hnae3_ae_ops hclgevf_ops = { .enable_hw_strip_rxvtag = hclgevf_en_hw_strip_rxvtag, .reset_event = hclgevf_reset_event, .set_default_reset_request = hclgevf_set_def_reset_request, + .set_channels = hclgevf_set_channels, .get_channels = hclgevf_get_channels, .get_tqps_and_rss_info = hclgevf_get_tqps_and_rss_info, .get_regs_len = hclgevf_get_regs_len, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h index 5a9e30998a8f..bdde3afc286b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.h @@ -87,6 +87,8 @@ /* Vector0 interrupt CMDQ event source register(RW) */ #define HCLGEVF_VECTOR0_CMDQ_SRC_REG 0x27100 +/* Vector0 interrupt CMDQ event status register(RO) */ +#define HCLGEVF_VECTOR0_CMDQ_STAT_REG 0x27104 /* CMDQ register bits for RX event(=MBX event) */ #define HCLGEVF_VECTOR0_RX_CMDQ_INT_B 1 /* RST register bits for RESET event */ @@ -103,6 +105,9 @@ (HCLGEVF_FUN_RST_ING_BIT | HCLGEVF_GLOBAL_RST_ING_BIT | \ HCLGEVF_CORE_RST_ING_BIT | HCLGEVF_IMP_RST_ING_BIT) +#define HCLGEVF_VF_RST_ING 0x07008 +#define HCLGEVF_VF_RST_ING_BIT BIT(16) + #define HCLGEVF_RSS_IND_TBL_SIZE 512 #define HCLGEVF_RSS_SET_BITMAP_MSK 0xffff #define HCLGEVF_RSS_KEY_SIZE 40 @@ -120,7 +125,7 @@ #define HCLGEVF_S_IP_BIT BIT(3) #define HCLGEVF_V_TAG_BIT BIT(4) -#define HCLGEVF_STATS_TIMER_INTERVAL (36) +#define HCLGEVF_STATS_TIMER_INTERVAL 36U enum hclgevf_evt_cause { HCLGEVF_VECTOR0_EVENT_RST, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c index 6a96987bd8f0..a108191c9e50 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_mbx.c @@ -277,9 +277,9 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev) switch (msg_q[0]) { case HCLGE_MBX_LINK_STAT_CHANGE: - link_status = le16_to_cpu(msg_q[1]); + link_status = msg_q[1]; memcpy(&speed, &msg_q[2], sizeof(speed)); - duplex = (u8)le16_to_cpu(msg_q[4]); + duplex = (u8)msg_q[4]; /* update upper layer with new link link status */ hclgevf_update_link_status(hdev, link_status); @@ -287,7 +287,7 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev) break; case HCLGE_MBX_LINK_STAT_MODE: - idx = (u8)le16_to_cpu(msg_q[1]); + idx = (u8)msg_q[1]; if (idx) memcpy(&hdev->hw.mac.supported, &msg_q[2], sizeof(unsigned long)); @@ -301,14 +301,14 @@ void hclgevf_mbx_async_handler(struct hclgevf_dev *hdev) * has been completely reset. After this stack should * eventually be re-initialized. */ - reset_type = le16_to_cpu(msg_q[1]); + reset_type = (enum hnae3_reset_type)msg_q[1]; set_bit(reset_type, &hdev->reset_pending); set_bit(HCLGEVF_RESET_PENDING, &hdev->reset_state); hclgevf_reset_task_schedule(hdev); break; case HCLGE_MBX_PUSH_VLAN_INFO: - state = le16_to_cpu(msg_q[1]); + state = msg_q[1]; vlan_info = &msg_q[1]; hclgevf_update_port_base_vlan_info(hdev, state, (u8 *)vlan_info, 8); diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index 9c78251f9c39..0e13d1c7e474 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -136,7 +136,7 @@ static int tx_map_skb(struct hinic_dev *nic_dev, struct sk_buff *skb, struct hinic_hwdev *hwdev = nic_dev->hwdev; struct hinic_hwif *hwif = hwdev->hwif; struct pci_dev *pdev = hwif->pdev; - struct skb_frag_struct *frag; + skb_frag_t *frag; dma_addr_t dma_addr; int i, j; diff --git a/drivers/net/ethernet/ibm/ehea/ehea_main.c b/drivers/net/ethernet/ibm/ehea/ehea_main.c index cca71ba7a74a..13e30eba5349 100644 --- a/drivers/net/ethernet/ibm/ehea/ehea_main.c +++ b/drivers/net/ethernet/ibm/ehea/ehea_main.c @@ -1577,20 +1577,16 @@ static int ehea_clean_portres(struct ehea_port *port, struct ehea_port_res *pr) ehea_destroy_eq(pr->eq); for (i = 0; i < pr->rq1_skba.len; i++) - if (pr->rq1_skba.arr[i]) - dev_kfree_skb(pr->rq1_skba.arr[i]); + dev_kfree_skb(pr->rq1_skba.arr[i]); for (i = 0; i < pr->rq2_skba.len; i++) - if (pr->rq2_skba.arr[i]) - dev_kfree_skb(pr->rq2_skba.arr[i]); + dev_kfree_skb(pr->rq2_skba.arr[i]); for (i = 0; i < pr->rq3_skba.len; i++) - if (pr->rq3_skba.arr[i]) - dev_kfree_skb(pr->rq3_skba.arr[i]); + dev_kfree_skb(pr->rq3_skba.arr[i]); for (i = 0; i < pr->sq_skba.len; i++) - if (pr->sq_skba.arr[i]) - dev_kfree_skb(pr->sq_skba.arr[i]); + dev_kfree_skb(pr->sq_skba.arr[i]); vfree(pr->rq1_skba.arr); vfree(pr->rq2_skba.arr); diff --git a/drivers/net/ethernet/ibm/emac/core.c b/drivers/net/ethernet/ibm/emac/core.c index 395dde444483..9e43c9ace9c2 100644 --- a/drivers/net/ethernet/ibm/emac/core.c +++ b/drivers/net/ethernet/ibm/emac/core.c @@ -1549,7 +1549,7 @@ emac_start_xmit_sg(struct sk_buff *skb, struct net_device *ndev) ctrl); /* skb fragments */ for (i = 0; i < nr_frags; ++i) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; len = skb_frag_size(frag); if (unlikely(dev->tx_cnt + mal_tx_chunks(len) >= NUM_TX_BUFF)) diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c index 5cb55ea671e3..2e5172f61564 100644 --- a/drivers/net/ethernet/ibm/ibmvnic.c +++ b/drivers/net/ethernet/ibm/ibmvnic.c @@ -1485,7 +1485,7 @@ static netdev_tx_t ibmvnic_xmit(struct sk_buff *skb, struct net_device *netdev) memcpy(dst + cur, page_address(skb_frag_page(frag)) + - frag->page_offset, skb_frag_size(frag)); + skb_frag_off(frag), skb_frag_size(frag)); cur += skb_frag_size(frag); } } else { diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index a41008523c98..71d3d8854d8f 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -937,8 +937,7 @@ static void e1000_free_desc_rings(struct e1000_adapter *adapter) txdr->buffer_info[i].dma, txdr->buffer_info[i].length, DMA_TO_DEVICE); - if (txdr->buffer_info[i].skb) - dev_kfree_skb(txdr->buffer_info[i].skb); + dev_kfree_skb(txdr->buffer_info[i].skb); } } diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index f703fa58458e..86493fea56e4 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -2889,9 +2889,8 @@ static int e1000_tx_map(struct e1000_adapter *adapter, } for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; - frag = &skb_shinfo(skb)->frags[f]; len = skb_frag_size(frag); offset = 0; @@ -4176,8 +4175,7 @@ static bool e1000_clean_jumbo_rx_irq(struct e1000_adapter *adapter, /* an error means any chain goes out the window * too */ - if (rx_ring->rx_skb_top) - dev_kfree_skb(rx_ring->rx_skb_top); + dev_kfree_skb(rx_ring->rx_skb_top); rx_ring->rx_skb_top = NULL; goto next_desc; } diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 08342698386d..de8c5818a305 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -1126,8 +1126,7 @@ static void e1000_free_desc_rings(struct e1000_adapter *adapter) buffer_info->dma, buffer_info->length, DMA_TO_DEVICE); - if (buffer_info->skb) - dev_kfree_skb(buffer_info->skb); + dev_kfree_skb(buffer_info->skb); } } @@ -1139,8 +1138,7 @@ static void e1000_free_desc_rings(struct e1000_adapter *adapter) dma_unmap_single(&pdev->dev, buffer_info->dma, 2048, DMA_FROM_DEVICE); - if (buffer_info->skb) - dev_kfree_skb(buffer_info->skb); + dev_kfree_skb(buffer_info->skb); } } diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 395b05701480..a1fab77b2096 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1429,6 +1429,16 @@ static s32 e1000_check_for_copper_link_ich8lan(struct e1000_hw *hw) else phy_reg |= 0xFA; e1e_wphy_locked(hw, I217_PLL_CLOCK_GATE_REG, phy_reg); + + if (speed == SPEED_1000) { + hw->phy.ops.read_reg_locked(hw, HV_PM_CTRL, + &phy_reg); + + phy_reg |= HV_PM_CTRL_K1_CLK_REQ; + + hw->phy.ops.write_reg_locked(hw, HV_PM_CTRL, + phy_reg); + } } hw->phy.ops.release(hw); diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index eb09c755fa17..1502895eb45d 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -210,7 +210,7 @@ /* PHY Power Management Control */ #define HV_PM_CTRL PHY_REG(770, 17) -#define HV_PM_CTRL_PLL_STOP_IN_K1_GIGA 0x100 +#define HV_PM_CTRL_K1_CLK_REQ 0x200 #define HV_PM_CTRL_K1_ENABLE 0x4000 #define I217_PLL_CLOCK_GATE_REG PHY_REG(772, 28) diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index e4baa13b3cda..d7d56e42a6aa 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1780,8 +1780,8 @@ static irqreturn_t e1000_intr_msi(int __always_unused irq, void *data) } /* guard against interrupt when we're going down */ if (!test_bit(__E1000_DOWN, &adapter->state)) - queue_delayed_work(adapter->e1000_workqueue, - &adapter->watchdog_task, 1); + mod_delayed_work(adapter->e1000_workqueue, + &adapter->watchdog_task, HZ); } /* Reset on uncorrectable ECC error */ @@ -1861,8 +1861,8 @@ static irqreturn_t e1000_intr(int __always_unused irq, void *data) } /* guard against interrupt when we're going down */ if (!test_bit(__E1000_DOWN, &adapter->state)) - queue_delayed_work(adapter->e1000_workqueue, - &adapter->watchdog_task, 1); + mod_delayed_work(adapter->e1000_workqueue, + &adapter->watchdog_task, HZ); } /* Reset on uncorrectable ECC error */ @@ -1907,8 +1907,8 @@ static irqreturn_t e1000_msix_other(int __always_unused irq, void *data) hw->mac.get_link_status = true; /* guard against interrupt when we're going down */ if (!test_bit(__E1000_DOWN, &adapter->state)) - queue_delayed_work(adapter->e1000_workqueue, - &adapter->watchdog_task, 1); + mod_delayed_work(adapter->e1000_workqueue, + &adapter->watchdog_task, HZ); } if (!test_bit(__E1000_DOWN, &adapter->state)) @@ -5579,9 +5579,8 @@ static int e1000_tx_map(struct e1000_ring *tx_ring, struct sk_buff *skb, } for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; - frag = &skb_shinfo(skb)->frags[f]; len = skb_frag_size(frag); offset = 0; @@ -6297,7 +6296,7 @@ fl_out: static int e1000e_pm_freeze(struct device *dev) { - struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); + struct net_device *netdev = dev_get_drvdata(dev); struct e1000_adapter *adapter = netdev_priv(netdev); netif_device_detach(netdev); @@ -6630,7 +6629,7 @@ static int __e1000_resume(struct pci_dev *pdev) #ifdef CONFIG_PM_SLEEP static int e1000e_pm_thaw(struct device *dev) { - struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev)); + struct net_device *netdev = dev_get_drvdata(dev); struct e1000_adapter *adapter = netdev_priv(netdev); e1000e_set_interrupt_capability(adapter); @@ -6679,8 +6678,7 @@ static int e1000e_pm_resume(struct device *dev) static int e1000e_pm_runtime_idle(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct e1000_adapter *adapter = netdev_priv(netdev); u16 eee_lp; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index 7d42582ed48d..b14441944b4b 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #ifndef _FM10K_H_ #define _FM10K_H_ @@ -177,14 +177,10 @@ static inline struct netdev_queue *txring_txq(const struct fm10k_ring *ring) #define MIN_Q_VECTORS 1 enum fm10k_non_q_vectors { FM10K_MBX_VECTOR, -#define NON_Q_VECTORS_VF NON_Q_VECTORS_PF - NON_Q_VECTORS_PF + NON_Q_VECTORS }; -#define NON_Q_VECTORS(hw) (((hw)->mac.type == fm10k_mac_pf) ? \ - NON_Q_VECTORS_PF : \ - NON_Q_VECTORS_VF) -#define MIN_MSIX_COUNT(hw) (MIN_Q_VECTORS + NON_Q_VECTORS(hw)) +#define MIN_MSIX_COUNT(hw) (MIN_Q_VECTORS + NON_Q_VECTORS) struct fm10k_q_vector { struct fm10k_intfc *interface; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c index 20768ac7f17e..c45315472245 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k.h" @@ -36,7 +36,7 @@ static int fm10k_dcbnl_ieee_getets(struct net_device *dev, struct ieee_ets *ets) static int fm10k_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets) { u8 num_tc = 0; - int i, err; + int i; /* verify type and determine num_tcs needed */ for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { @@ -57,7 +57,7 @@ static int fm10k_dcbnl_ieee_setets(struct net_device *dev, struct ieee_ets *ets) /* update TC hardware mapping if necessary */ if (num_tc != netdev_get_num_tc(dev)) { - err = fm10k_setup_tc(dev, num_tc); + int err = fm10k_setup_tc(dev, num_tc); if (err) return err; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c index dca104121c05..1d27b2fb23af 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c @@ -160,8 +160,6 @@ void fm10k_dbg_q_vector_init(struct fm10k_q_vector *q_vector) snprintf(name, sizeof(name), "q_vector.%03d", q_vector->v_idx); q_vector->dbg_q_vector = debugfs_create_dir(name, interface->dbg_intfc); - if (!q_vector->dbg_q_vector) - return; /* Generate a file for each rx ring in the q_vector */ for (i = 0; i < q_vector->tx.count; i++) { diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 4895dd83dd08..c681d2d28107 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include <linux/vmalloc.h> @@ -222,7 +222,6 @@ static void __fm10k_add_ethtool_stats(u64 **data, void *pointer, const unsigned int size) { unsigned int i; - char *p; if (!pointer) { /* memory is not zero allocated so we have to clear it */ @@ -232,7 +231,7 @@ static void __fm10k_add_ethtool_stats(u64 **data, void *pointer, } for (i = 0; i < size; i++) { - p = (char *)pointer + stats[i].stat_offset; + char *p = (char *)pointer + stats[i].stat_offset; switch (stats[i].sizeof_stat) { case sizeof(u64): @@ -651,7 +650,6 @@ static int fm10k_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) { struct fm10k_intfc *interface = netdev_priv(dev); - struct fm10k_q_vector *qv; u16 tx_itr, rx_itr; int i; @@ -677,7 +675,8 @@ static int fm10k_set_coalesce(struct net_device *dev, /* update q_vectors */ for (i = 0; i < interface->num_q_vectors; i++) { - qv = interface->q_vector[i]; + struct fm10k_q_vector *qv = interface->q_vector[i]; + qv->tx.itr = tx_itr; qv->rx.itr = rx_itr; } @@ -1115,13 +1114,12 @@ static void fm10k_get_channels(struct net_device *dev, struct ethtool_channels *ch) { struct fm10k_intfc *interface = netdev_priv(dev); - struct fm10k_hw *hw = &interface->hw; /* report maximum channels */ ch->max_combined = fm10k_max_channels(dev); /* report info for other vector */ - ch->max_other = NON_Q_VECTORS(hw); + ch->max_other = NON_Q_VECTORS; ch->other_count = ch->max_other; /* record RSS queues */ @@ -1133,14 +1131,13 @@ static int fm10k_set_channels(struct net_device *dev, { struct fm10k_intfc *interface = netdev_priv(dev); unsigned int count = ch->combined_count; - struct fm10k_hw *hw = &interface->hw; /* verify they are not requesting separate vectors */ if (!count || ch->rx_count || ch->tx_count) return -EINVAL; /* verify other_count has not changed */ - if (ch->other_count != NON_Q_VECTORS(hw)) + if (ch->other_count != NON_Q_VECTORS) return -EINVAL; /* verify the number of channels does not exceed hardware limits */ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 8de77155f2e7..afe1fafd2447 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k.h" #include "fm10k_vf.h" @@ -426,7 +426,7 @@ static s32 fm10k_iov_alloc_data(struct pci_dev *pdev, int num_vfs) struct fm10k_iov_data *iov_data = interface->iov_data; struct fm10k_hw *hw = &interface->hw; size_t size; - int i, err; + int i; /* return error if iov_data is already populated */ if (iov_data) @@ -452,6 +452,7 @@ static s32 fm10k_iov_alloc_data(struct pci_dev *pdev, int num_vfs) /* loop through vf_info structures initializing each entry */ for (i = 0; i < num_vfs; i++) { struct fm10k_vf_info *vf_info = &iov_data->vf_info[i]; + int err; /* Record VF VSI value */ vf_info->vsi = i + 1; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index 90270b4a1682..2be9222510e7 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include <linux/types.h> #include <linux/module.h> @@ -17,7 +17,7 @@ const char fm10k_driver_version[] = DRV_VERSION; char fm10k_driver_name[] = "fm10k"; static const char fm10k_driver_string[] = DRV_SUMMARY; static const char fm10k_copyright[] = - "Copyright(c) 2013 - 2018 Intel Corporation."; + "Copyright(c) 2013 - 2019 Intel Corporation."; MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); @@ -315,7 +315,7 @@ static struct sk_buff *fm10k_fetch_rx_buffer(struct fm10k_ring *rx_ring, /* prefetch first cache line of first page */ prefetch(page_addr); #if L1_CACHE_BYTES < 128 - prefetch(page_addr + L1_CACHE_BYTES); + prefetch((void *)((u8 *)page_addr + L1_CACHE_BYTES)); #endif /* allocate a skb to store the frags */ @@ -946,7 +946,7 @@ static void fm10k_tx_map(struct fm10k_ring *tx_ring, struct sk_buff *skb = first->skb; struct fm10k_tx_buffer *tx_buffer; struct fm10k_tx_desc *tx_desc; - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned char *data; dma_addr_t dma; unsigned int data_len, size; @@ -1073,8 +1073,11 @@ netdev_tx_t fm10k_xmit_frame_ring(struct sk_buff *skb, * + 2 desc gap to keep tail from touching head * otherwise try next time */ - for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; + + count += TXD_USE_COUNT(skb_frag_size(frag)); + } if (fm10k_maybe_stop_tx(tx_ring, count + 3)) { tx_ring->tx_stats.tx_busy++; @@ -1823,7 +1826,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) v_budget = min_t(u16, v_budget, num_online_cpus()); /* account for vectors not related to queues */ - v_budget += NON_Q_VECTORS(hw); + v_budget += NON_Q_VECTORS; /* At the same time, hardware can only support a maximum of * hw.mac->max_msix_vectors vectors. With features @@ -1855,7 +1858,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) } /* record the number of queues available for q_vectors */ - interface->num_q_vectors = v_budget - NON_Q_VECTORS(hw); + interface->num_q_vectors = v_budget - NON_Q_VECTORS; return 0; } @@ -1869,7 +1872,7 @@ static int fm10k_init_msix_capability(struct fm10k_intfc *interface) static bool fm10k_cache_ring_qos(struct fm10k_intfc *interface) { struct net_device *dev = interface->netdev; - int pc, offset, rss_i, i, q_idx; + int pc, offset, rss_i, i; u16 pc_stride = interface->ring_feature[RING_F_QOS].mask + 1; u8 num_pcs = netdev_get_num_tc(dev); @@ -1879,7 +1882,8 @@ static bool fm10k_cache_ring_qos(struct fm10k_intfc *interface) rss_i = interface->ring_feature[RING_F_RSS].indices; for (pc = 0, offset = 0; pc < num_pcs; pc++, offset += rss_i) { - q_idx = pc; + int q_idx = pc; + for (i = 0; i < rss_i; i++) { interface->tx_ring[offset + i]->reg_idx = q_idx; interface->tx_ring[offset + i]->qos_pc = pc; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index 21021fe4f1c3..75e51f91036c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_common.h" @@ -297,13 +297,14 @@ static u16 fm10k_mbx_validate_msg_size(struct fm10k_mbx_info *mbx, u16 len) { struct fm10k_mbx_fifo *fifo = &mbx->rx; u16 total_len = 0, msg_len; - u32 *msg; /* length should include previous amounts pushed */ len += mbx->pushed; /* offset in message is based off of current message size */ do { + u32 *msg; + msg = fifo->buffer + fm10k_fifo_tail_offset(fifo, total_len); msg_len = FM10K_TLV_DWORD_LEN(*msg); total_len += msg_len; @@ -1920,7 +1921,6 @@ static void fm10k_sm_mbx_transmit(struct fm10k_hw *hw, /* reduce length by 1 to convert to a mask */ u16 mbmem_len = mbx->mbmem_len - 1; u16 tail_len, len = 0; - u32 *msg; /* push head behind tail */ if (mbx->tail < head) @@ -1930,6 +1930,8 @@ static void fm10k_sm_mbx_transmit(struct fm10k_hw *hw, /* determine msg aligned offset for end of buffer */ do { + u32 *msg; + msg = fifo->buffer + fm10k_fifo_head_offset(fifo, len); tail_len = len; len += FM10K_TLV_DWORD_LEN(*msg); @@ -2132,7 +2134,8 @@ fifo_err: * DWORDs, not bytes. Any invalid values will cause the mailbox to return * error. **/ -s32 fm10k_sm_mbx_init(struct fm10k_hw *hw, struct fm10k_mbx_info *mbx, +s32 fm10k_sm_mbx_init(struct fm10k_hw __always_unused *hw, + struct fm10k_mbx_info *mbx, const struct fm10k_msg_data *msg_data) { mbx->mbx_reg = FM10K_GMBX; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 538a8467f434..09f7a246e134 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k.h" #include <linux/vmalloc.h> @@ -54,7 +54,7 @@ err: **/ static int fm10k_setup_all_tx_resources(struct fm10k_intfc *interface) { - int i, err = 0; + int i, err; for (i = 0; i < interface->num_tx_queues; i++) { err = fm10k_setup_tx_resources(interface->tx_ring[i]); @@ -121,7 +121,7 @@ err: **/ static int fm10k_setup_all_rx_resources(struct fm10k_intfc *interface) { - int i, err = 0; + int i, err; for (i = 0; i < interface->num_rx_queues; i++) { err = fm10k_setup_rx_resources(interface->rx_ring[i]); @@ -169,7 +169,6 @@ void fm10k_unmap_and_free_tx_resource(struct fm10k_ring *ring, **/ static void fm10k_clean_tx_ring(struct fm10k_ring *tx_ring) { - struct fm10k_tx_buffer *tx_buffer; unsigned long size; u16 i; @@ -179,7 +178,8 @@ static void fm10k_clean_tx_ring(struct fm10k_ring *tx_ring) /* Free all the Tx ring sk_buffs */ for (i = 0; i < tx_ring->count; i++) { - tx_buffer = &tx_ring->tx_buffer[i]; + struct fm10k_tx_buffer *tx_buffer = &tx_ring->tx_buffer[i]; + fm10k_unmap_and_free_tx_resource(tx_ring, tx_buffer); } @@ -253,8 +253,7 @@ static void fm10k_clean_rx_ring(struct fm10k_ring *rx_ring) if (!rx_ring->rx_buffer) return; - if (rx_ring->skb) - dev_kfree_skb(rx_ring->skb); + dev_kfree_skb(rx_ring->skb); rx_ring->skb = NULL; /* Free all the Rx ring sk_buffs */ @@ -871,7 +870,7 @@ static int fm10k_uc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err = -EHOSTDOWN; + int err; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; @@ -891,7 +890,7 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev, u16 glort = interface->glort; u16 vid = interface->vid; bool set = !!(vid / VLAN_N_VID); - int err = -EHOSTDOWN; + int err; /* drop any leading bits on the VLAN ID */ vid &= VLAN_N_VID - 1; @@ -1444,11 +1443,11 @@ static int __fm10k_setup_tc(struct net_device *dev, enum tc_setup_type type, static void fm10k_assign_l2_accel(struct fm10k_intfc *interface, struct fm10k_l2_accel *l2_accel) { - struct fm10k_ring *ring; int i; for (i = 0; i < interface->num_rx_queues; i++) { - ring = interface->rx_ring[i]; + struct fm10k_ring *ring = interface->rx_ring[i]; + rcu_assign_pointer(ring->l2_accel, l2_accel); } @@ -1463,7 +1462,7 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, struct fm10k_l2_accel *old_l2_accel = NULL; struct fm10k_dglort_cfg dglort = { 0 }; struct fm10k_hw *hw = &interface->hw; - int size = 0, i; + int size, i; u16 vid, glort; /* The hardware supported by fm10k only filters on the destination MAC diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index e49fb51d3613..bb236fa44048 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include <linux/module.h> #include <linux/interrupt.h> @@ -344,7 +344,6 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface) struct net_device *netdev = interface->netdev; u32 __iomem *hw_addr; u32 value; - int err; /* do nothing if netdev is still present or hw_addr is set */ if (netif_device_present(netdev) || interface->hw.hw_addr) @@ -362,6 +361,8 @@ static void fm10k_detach_subtask(struct fm10k_intfc *interface) hw_addr = READ_ONCE(interface->uc_addr); value = readl(hw_addr); if (~value) { + int err; + /* Make sure the reset was initiated because we detached, * otherwise we might race with a different reset flow. */ @@ -697,8 +698,6 @@ static void fm10k_watchdog_subtask(struct fm10k_intfc *interface) */ static void fm10k_check_hang_subtask(struct fm10k_intfc *interface) { - int i; - /* If we're down or resetting, just bail */ if (test_bit(__FM10K_DOWN, interface->state) || test_bit(__FM10K_RESETTING, interface->state)) @@ -710,6 +709,8 @@ static void fm10k_check_hang_subtask(struct fm10k_intfc *interface) interface->next_tx_hang_check = jiffies + (2 * HZ); if (netif_carrier_ok(interface->netdev)) { + int i; + /* Force detection of hung controller */ for (i = 0; i < interface->num_tx_queues; i++) set_check_for_tx_hang(interface->tx_ring[i]); @@ -897,7 +898,7 @@ static void fm10k_configure_tx_ring(struct fm10k_intfc *interface, /* Map interrupt */ if (ring->q_vector) { - txint = ring->q_vector->v_idx + NON_Q_VECTORS(hw); + txint = ring->q_vector->v_idx + NON_Q_VECTORS; txint |= FM10K_INT_MAP_TIMER0; } @@ -1036,7 +1037,7 @@ static void fm10k_configure_rx_ring(struct fm10k_intfc *interface, /* Map interrupt */ if (ring->q_vector) { - rxint = ring->q_vector->v_idx + NON_Q_VECTORS(hw); + rxint = ring->q_vector->v_idx + NON_Q_VECTORS; rxint |= FM10K_INT_MAP_TIMER1; } @@ -1719,10 +1720,9 @@ int fm10k_mbx_request_irq(struct fm10k_intfc *interface) void fm10k_qv_free_irq(struct fm10k_intfc *interface) { int vector = interface->num_q_vectors; - struct fm10k_hw *hw = &interface->hw; struct msix_entry *entry; - entry = &interface->msix_entries[NON_Q_VECTORS(hw) + vector]; + entry = &interface->msix_entries[NON_Q_VECTORS + vector]; while (vector) { struct fm10k_q_vector *q_vector; @@ -1759,7 +1759,7 @@ int fm10k_qv_request_irq(struct fm10k_intfc *interface) unsigned int ri = 0, ti = 0; int vector, err; - entry = &interface->msix_entries[NON_Q_VECTORS(hw)]; + entry = &interface->msix_entries[NON_Q_VECTORS]; for (vector = 0; vector < interface->num_q_vectors; vector++) { struct fm10k_q_vector *q_vector = interface->q_vector[vector]; @@ -2339,7 +2339,7 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) /* Restart the MAC/VLAN request queue in-case of outstanding events */ fm10k_macvlan_schedule(interface); - return err; + return 0; } /** @@ -2352,7 +2352,7 @@ static int fm10k_handle_resume(struct fm10k_intfc *interface) **/ static int __maybe_unused fm10k_resume(struct device *dev) { - struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev)); + struct fm10k_intfc *interface = dev_get_drvdata(dev); struct net_device *netdev = interface->netdev; struct fm10k_hw *hw = &interface->hw; int err; @@ -2379,7 +2379,7 @@ static int __maybe_unused fm10k_resume(struct device *dev) **/ static int __maybe_unused fm10k_suspend(struct device *dev) { - struct fm10k_intfc *interface = pci_get_drvdata(to_pci_dev(dev)); + struct fm10k_intfc *interface = dev_get_drvdata(dev); struct net_device *netdev = interface->netdev; netif_device_detach(netdev); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index cb4d02629b86..be07bfdb0bb4 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_pf.h" #include "fm10k_vf.h" @@ -1152,7 +1152,7 @@ static void fm10k_iov_update_stats_pf(struct fm10k_hw *hw, * assumption is that in this case it is acceptable to just directly * hand off the message from the VF to the underlying shared code. **/ -s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 **results, +s32 fm10k_iov_msg_msix_pf(struct fm10k_hw *hw, u32 __always_unused **results, struct fm10k_mbx_info *mbx) { struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; @@ -1352,7 +1352,6 @@ s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *hw, u32 **results, struct fm10k_mbx_info *mbx) { struct fm10k_vf_info *vf_info = (struct fm10k_vf_info *)mbx; - u32 *result; s32 err = 0; u32 msg[2]; u8 mode = 0; @@ -1362,7 +1361,7 @@ s32 fm10k_iov_msg_lport_state_pf(struct fm10k_hw *hw, u32 **results, return FM10K_ERR_PARAM; if (!!results[FM10K_LPORT_STATE_MSG_XCAST_MODE]) { - result = results[FM10K_LPORT_STATE_MSG_XCAST_MODE]; + u32 *result = results[FM10K_LPORT_STATE_MSG_XCAST_MODE]; /* XCAST mode update requested */ err = fm10k_tlv_attr_get_u8(result, &mode); @@ -1566,7 +1565,7 @@ static s32 fm10k_get_fault_pf(struct fm10k_hw *hw, int type, /* read remaining fields */ fault->address = fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_HI); fault->address <<= 32; - fault->address = fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_LO); + fault->address |= fm10k_read_reg(hw, type + FM10K_FAULT_ADDR_LO); fault->specinfo = fm10k_read_reg(hw, type + FM10K_FAULT_SPECINFO); /* clear valid bit to allow for next error */ @@ -1642,7 +1641,7 @@ const struct fm10k_tlv_attr fm10k_lport_map_msg_attr[] = { * switch API. **/ s32 fm10k_msg_lport_map_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u16 glort, mask; u32 dglort_map; @@ -1685,7 +1684,7 @@ const struct fm10k_tlv_attr fm10k_update_pvid_msg_attr[] = { * This handler configures the default VLAN for the PF **/ static s32 fm10k_msg_update_pvid_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u16 glort, pvid; u32 pvid_update; @@ -1746,7 +1745,7 @@ const struct fm10k_tlv_attr fm10k_err_msg_attr[] = { * messages that the PF has sent. **/ s32 fm10k_msg_err_pf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { struct fm10k_swapi_error err_msg; s32 err; diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c index 2a7a40bf2b1c..21eff0895a7a 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_tlv.h" @@ -472,7 +472,7 @@ static s32 fm10k_tlv_attr_parse(u32 *attr, u32 **results, const struct fm10k_tlv_attr *tlv_attr) { u32 i, attr_id, offset = 0; - s32 err = 0; + s32 err; u16 len; /* verify pointers are not NULL */ @@ -587,8 +587,9 @@ s32 fm10k_tlv_msg_parse(struct fm10k_hw *hw, u32 *msg, * a minimum it just indicates that the message requested was * unimplemented. **/ -s32 fm10k_tlv_msg_error(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) +s32 fm10k_tlv_msg_error(struct fm10k_hw __always_unused *hw, + u32 __always_unused **results, + struct fm10k_mbx_info __always_unused *mbx) { return FM10K_NOT_IMPLEMENTED; } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h index 9fb9fca375e3..15ac1c7885bc 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #ifndef _FM10K_TYPE_H_ #define _FM10K_TYPE_H_ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c index a8519c1f0406..dc8ccd378ec9 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright(c) 2013 - 2018 Intel Corporation. */ +/* Copyright(c) 2013 - 2019 Intel Corporation. */ #include "fm10k_vf.h" @@ -198,7 +198,7 @@ static s32 fm10k_update_vlan_vf(struct fm10k_hw *hw, u32 vid, u8 vsi, bool set) * This function should determine the MAC address for the VF **/ s32 fm10k_msg_mac_vlan_vf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { u8 perm_addr[ETH_ALEN]; u16 vid; @@ -267,8 +267,10 @@ static s32 fm10k_read_mac_addr_vf(struct fm10k_hw *hw) * This function is used to add or remove unicast MAC addresses for * the VF. **/ -static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, u16 glort, - const u8 *mac, u16 vid, bool add, u8 flags) +static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, + u16 __always_unused glort, + const u8 *mac, u16 vid, bool add, + u8 __always_unused flags) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[7]; @@ -309,7 +311,8 @@ static s32 fm10k_update_uc_addr_vf(struct fm10k_hw *hw, u16 glort, * This function is used to add or remove multicast MAC addresses for * the VF. **/ -static s32 fm10k_update_mc_addr_vf(struct fm10k_hw *hw, u16 glort, +static s32 fm10k_update_mc_addr_vf(struct fm10k_hw *hw, + u16 __always_unused glort, const u8 *mac, u16 vid, bool add) { struct fm10k_mbx_info *mbx = &hw->mbx; @@ -373,7 +376,7 @@ const struct fm10k_tlv_attr fm10k_lport_state_msg_attr[] = { * are ready to bring up the interface. **/ s32 fm10k_msg_lport_state_vf(struct fm10k_hw *hw, u32 **results, - struct fm10k_mbx_info *mbx) + struct fm10k_mbx_info __always_unused *mbx) { hw->mac.dglort_map = !results[FM10K_LPORT_STATE_MSG_READY] ? FM10K_DGLORTMAP_NONE : FM10K_DGLORTMAP_ZERO; @@ -392,8 +395,9 @@ s32 fm10k_msg_lport_state_vf(struct fm10k_hw *hw, u32 **results, * enabled we can add filters, if it is disabled all filters for this * logical port are flushed. **/ -static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, u16 glort, - u16 count, bool enable) +static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, + u16 __always_unused glort, + u16 __always_unused count, bool enable) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[2]; @@ -420,7 +424,8 @@ static s32 fm10k_update_lport_state_vf(struct fm10k_hw *hw, u16 glort, * so that it can enable either multicast, multicast promiscuous, or * promiscuous mode of operation. **/ -static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw, u16 glort, u8 mode) +static s32 fm10k_update_xcast_mode_vf(struct fm10k_hw *hw, + u16 __always_unused glort, u8 mode) { struct fm10k_mbx_info *mbx = &hw->mbx; u32 msg[3]; @@ -475,7 +480,7 @@ static void fm10k_rebind_hw_stats_vf(struct fm10k_hw *hw, * that information to then populate a DGLORTMAP/DEC entry and the queues * to which it has been assigned. **/ -static s32 fm10k_configure_dglort_map_vf(struct fm10k_hw *hw, +static s32 fm10k_configure_dglort_map_vf(struct fm10k_hw __always_unused *hw, struct fm10k_dglort_cfg *dglort) { /* verify the dglort pointer */ diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index 84bd06901014..2af9f6308f84 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -131,7 +131,6 @@ enum i40e_state_t { __I40E_PF_RESET_REQUESTED, __I40E_CORE_RESET_REQUESTED, __I40E_GLOBAL_RESET_REQUESTED, - __I40E_EMP_RESET_REQUESTED, __I40E_EMP_RESET_INTR_RECEIVED, __I40E_SUSPENDED, __I40E_PTP_TX_IN_PROGRESS, @@ -244,11 +243,11 @@ struct i40e_fdir_filter { u32 fd_id; }; -#define I40E_CLOUD_FIELD_OMAC 0x01 -#define I40E_CLOUD_FIELD_IMAC 0x02 -#define I40E_CLOUD_FIELD_IVLAN 0x04 -#define I40E_CLOUD_FIELD_TEN_ID 0x08 -#define I40E_CLOUD_FIELD_IIP 0x10 +#define I40E_CLOUD_FIELD_OMAC BIT(0) +#define I40E_CLOUD_FIELD_IMAC BIT(1) +#define I40E_CLOUD_FIELD_IVLAN BIT(2) +#define I40E_CLOUD_FIELD_TEN_ID BIT(3) +#define I40E_CLOUD_FIELD_IIP BIT(4) #define I40E_CLOUD_FILTER_FLAGS_OMAC I40E_CLOUD_FIELD_OMAC #define I40E_CLOUD_FILTER_FLAGS_IMAC I40E_CLOUD_FIELD_IMAC @@ -1021,6 +1020,7 @@ i40e_find_vsi_by_type(struct i40e_pf *pf, u16 type) return NULL; } void i40e_update_stats(struct i40e_vsi *vsi); +void i40e_update_veb_stats(struct i40e_veb *veb); void i40e_update_eth_stats(struct i40e_vsi *vsi); struct rtnl_link_stats64 *i40e_get_vsi_stats_struct(struct i40e_vsi *vsi); int i40e_fetch_switch_configuration(struct i40e_pf *pf, diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 814acbe79ffd..72c04881d290 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -610,8 +610,10 @@ i40e_status i40e_init_adminq(struct i40e_hw *hw) if (hw->aq.api_maj_ver > 1 || (hw->aq.api_maj_ver == 1 && - hw->aq.api_min_ver >= 8)) + hw->aq.api_min_ver >= 8)) { hw->flags |= I40E_HW_FLAG_FW_LLDP_PERSISTENT; + hw->flags |= I40E_HW_FLAG_DROP_MODE; + } if (hw->aq.api_maj_ver > I40E_FW_API_VERSION_MAJOR) { ret_code = I40E_ERR_FIRMWARE_API_VERSION; diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 6536023fa074..530613f31527 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -11,8 +11,8 @@ */ #define I40E_FW_API_VERSION_MAJOR 0x0001 -#define I40E_FW_API_VERSION_MINOR_X722 0x0008 -#define I40E_FW_API_VERSION_MINOR_X710 0x0008 +#define I40E_FW_API_VERSION_MINOR_X722 0x0009 +#define I40E_FW_API_VERSION_MINOR_X710 0x0009 #define I40E_FW_MINOR_VERSION(_h) ((_h)->mac.type == I40E_MAC_XL710 ? \ I40E_FW_API_VERSION_MINOR_X710 : \ @@ -1382,7 +1382,7 @@ struct i40e_aqc_cloud_filters_element_data { #define I40E_AQC_ADD_CLOUD_FILTER_MASK (0x3F << \ I40E_AQC_ADD_CLOUD_FILTER_SHIFT) /* 0x0000 reserved */ -#define I40E_AQC_ADD_CLOUD_FILTER_OIP 0x0001 +/* 0x0001 reserved */ /* 0x0002 reserved */ #define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN 0x0003 #define I40E_AQC_ADD_CLOUD_FILTER_IMAC_IVLAN_TEN_ID 0x0004 @@ -1394,6 +1394,9 @@ struct i40e_aqc_cloud_filters_element_data { #define I40E_AQC_ADD_CLOUD_FILTER_IMAC 0x000A #define I40E_AQC_ADD_CLOUD_FILTER_OMAC_TEN_ID_IMAC 0x000B #define I40E_AQC_ADD_CLOUD_FILTER_IIP 0x000C +/* 0x000D reserved */ +/* 0x000E reserved */ +/* 0x000F reserved */ /* 0x0010 to 0x0017 is for custom filters */ #define I40E_AQC_ADD_CLOUD_FILTER_IP_PORT 0x0010 /* Dest IP + L4 Port */ #define I40E_AQC_ADD_CLOUD_FILTER_MAC_PORT 0x0011 /* Dest MAC + L4 Port */ @@ -2051,20 +2054,21 @@ I40E_CHECK_CMD_LENGTH(i40e_aq_set_phy_config); struct i40e_aq_set_mac_config { __le16 max_frame_size; u8 params; -#define I40E_AQ_SET_MAC_CONFIG_CRC_EN 0x04 -#define I40E_AQ_SET_MAC_CONFIG_PACING_MASK 0x78 -#define I40E_AQ_SET_MAC_CONFIG_PACING_SHIFT 3 -#define I40E_AQ_SET_MAC_CONFIG_PACING_NONE 0x0 -#define I40E_AQ_SET_MAC_CONFIG_PACING_1B_13TX 0xF -#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_9TX 0x9 -#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_4TX 0x8 -#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_7TX 0x7 -#define I40E_AQ_SET_MAC_CONFIG_PACING_2DW_3TX 0x6 -#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_1TX 0x5 -#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_2TX 0x4 -#define I40E_AQ_SET_MAC_CONFIG_PACING_7DW_3TX 0x3 -#define I40E_AQ_SET_MAC_CONFIG_PACING_4DW_1TX 0x2 -#define I40E_AQ_SET_MAC_CONFIG_PACING_9DW_1TX 0x1 +#define I40E_AQ_SET_MAC_CONFIG_CRC_EN 0x04 +#define I40E_AQ_SET_MAC_CONFIG_PACING_MASK 0x78 +#define I40E_AQ_SET_MAC_CONFIG_PACING_SHIFT 3 +#define I40E_AQ_SET_MAC_CONFIG_PACING_NONE 0x0 +#define I40E_AQ_SET_MAC_CONFIG_PACING_1B_13TX 0xF +#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_9TX 0x9 +#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_4TX 0x8 +#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_7TX 0x7 +#define I40E_AQ_SET_MAC_CONFIG_PACING_2DW_3TX 0x6 +#define I40E_AQ_SET_MAC_CONFIG_PACING_1DW_1TX 0x5 +#define I40E_AQ_SET_MAC_CONFIG_PACING_3DW_2TX 0x4 +#define I40E_AQ_SET_MAC_CONFIG_PACING_7DW_3TX 0x3 +#define I40E_AQ_SET_MAC_CONFIG_PACING_4DW_1TX 0x2 +#define I40E_AQ_SET_MAC_CONFIG_PACING_9DW_1TX 0x1 +#define I40E_AQ_SET_MAC_CONFIG_DROP_BLOCKING_PACKET_EN 0x80 u8 tx_timer_priority; /* bitmap */ __le16 tx_timer_value; __le16 fc_refresh_threshold; diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index 906cf68d3453..d37c6e0e5f08 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include "i40e.h" #include "i40e_type.h" #include "i40e_adminq.h" #include "i40e_prototype.h" @@ -13,7 +14,7 @@ * This function sets the mac type of the adapter based on the * vendor ID and device ID stored in the hw structure. **/ -static i40e_status i40e_set_mac_type(struct i40e_hw *hw) +i40e_status i40e_set_mac_type(struct i40e_hw *hw) { i40e_status status = 0; @@ -1577,19 +1578,22 @@ i40e_status i40e_aq_get_phy_capabilities(struct i40e_hw *hw, status = i40e_asq_send_command(hw, &desc, abilities, abilities_size, cmd_details); - if (status) - break; - - if (hw->aq.asq_last_status == I40E_AQ_RC_EIO) { + switch (hw->aq.asq_last_status) { + case I40E_AQ_RC_EIO: status = I40E_ERR_UNKNOWN_PHY; break; - } else if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN) { + case I40E_AQ_RC_EAGAIN: usleep_range(1000, 2000); total_delay++; status = I40E_ERR_TIMEOUT; + break; + /* also covers I40E_AQ_RC_OK */ + default: + break; } - } while ((hw->aq.asq_last_status != I40E_AQ_RC_OK) && - (total_delay < max_delay)); + + } while ((hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN) && + (total_delay < max_delay)); if (status) return status; @@ -1643,25 +1647,15 @@ enum i40e_status_code i40e_aq_set_phy_config(struct i40e_hw *hw, return status; } -/** - * i40e_set_fc - * @hw: pointer to the hw struct - * @aq_failures: buffer to return AdminQ failure information - * @atomic_restart: whether to enable atomic link restart - * - * Set the requested flow control mode using set_phy_config. - **/ -enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, - bool atomic_restart) +static noinline_for_stack enum i40e_status_code +i40e_set_fc_status(struct i40e_hw *hw, + struct i40e_aq_get_phy_abilities_resp *abilities, + bool atomic_restart) { - enum i40e_fc_mode fc_mode = hw->fc.requested_mode; - struct i40e_aq_get_phy_abilities_resp abilities; struct i40e_aq_set_phy_config config; - enum i40e_status_code status; + enum i40e_fc_mode fc_mode = hw->fc.requested_mode; u8 pause_mask = 0x0; - *aq_failures = 0x0; - switch (fc_mode) { case I40E_FC_FULL: pause_mask |= I40E_AQ_PHY_FLAG_PAUSE_TX; @@ -1677,6 +1671,48 @@ enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, break; } + memset(&config, 0, sizeof(struct i40e_aq_set_phy_config)); + /* clear the old pause settings */ + config.abilities = abilities->abilities & ~(I40E_AQ_PHY_FLAG_PAUSE_TX) & + ~(I40E_AQ_PHY_FLAG_PAUSE_RX); + /* set the new abilities */ + config.abilities |= pause_mask; + /* If the abilities have changed, then set the new config */ + if (config.abilities == abilities->abilities) + return 0; + + /* Auto restart link so settings take effect */ + if (atomic_restart) + config.abilities |= I40E_AQ_PHY_ENABLE_ATOMIC_LINK; + /* Copy over all the old settings */ + config.phy_type = abilities->phy_type; + config.phy_type_ext = abilities->phy_type_ext; + config.link_speed = abilities->link_speed; + config.eee_capability = abilities->eee_capability; + config.eeer = abilities->eeer_val; + config.low_power_ctrl = abilities->d3_lpan; + config.fec_config = abilities->fec_cfg_curr_mod_ext_info & + I40E_AQ_PHY_FEC_CONFIG_MASK; + + return i40e_aq_set_phy_config(hw, &config, NULL); +} + +/** + * i40e_set_fc + * @hw: pointer to the hw struct + * @aq_failures: buffer to return AdminQ failure information + * @atomic_restart: whether to enable atomic link restart + * + * Set the requested flow control mode using set_phy_config. + **/ +enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, + bool atomic_restart) +{ + struct i40e_aq_get_phy_abilities_resp abilities; + enum i40e_status_code status; + + *aq_failures = 0x0; + /* Get the current phy config */ status = i40e_aq_get_phy_capabilities(hw, false, false, &abilities, NULL); @@ -1685,31 +1721,10 @@ enum i40e_status_code i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures, return status; } - memset(&config, 0, sizeof(struct i40e_aq_set_phy_config)); - /* clear the old pause settings */ - config.abilities = abilities.abilities & ~(I40E_AQ_PHY_FLAG_PAUSE_TX) & - ~(I40E_AQ_PHY_FLAG_PAUSE_RX); - /* set the new abilities */ - config.abilities |= pause_mask; - /* If the abilities have changed, then set the new config */ - if (config.abilities != abilities.abilities) { - /* Auto restart link so settings take effect */ - if (atomic_restart) - config.abilities |= I40E_AQ_PHY_ENABLE_ATOMIC_LINK; - /* Copy over all the old settings */ - config.phy_type = abilities.phy_type; - config.phy_type_ext = abilities.phy_type_ext; - config.link_speed = abilities.link_speed; - config.eee_capability = abilities.eee_capability; - config.eeer = abilities.eeer_val; - config.low_power_ctrl = abilities.d3_lpan; - config.fec_config = abilities.fec_cfg_curr_mod_ext_info & - I40E_AQ_PHY_FEC_CONFIG_MASK; - status = i40e_aq_set_phy_config(hw, &config, NULL); + status = i40e_set_fc_status(hw, &abilities, atomic_restart); + if (status) + *aq_failures |= I40E_SET_FC_AQ_FAIL_SET; - if (status) - *aq_failures |= I40E_SET_FC_AQ_FAIL_SET; - } /* Update the link info */ status = i40e_update_link_info(hw); if (status) { @@ -2537,7 +2552,7 @@ i40e_status i40e_get_link_status(struct i40e_hw *hw, bool *link_up) * i40e_updatelink_status - update status of the HW network link * @hw: pointer to the hw struct **/ -i40e_status i40e_update_link_info(struct i40e_hw *hw) +noinline_for_stack i40e_status i40e_update_link_info(struct i40e_hw *hw) { struct i40e_aq_get_phy_abilities_resp abilities; i40e_status status = 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c index 292eeb3def10..200a1cb3b536 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c @@ -877,7 +877,23 @@ i40e_status i40e_init_dcb(struct i40e_hw *hw, bool enable_mib_change) return I40E_NOT_SUPPORTED; /* Read LLDP NVM area */ - ret = i40e_read_lldp_cfg(hw, &lldp_cfg); + if (hw->flags & I40E_HW_FLAG_FW_LLDP_PERSISTENT) { + u8 offset = 0; + + if (hw->mac.type == I40E_MAC_XL710) + offset = I40E_LLDP_CURRENT_STATUS_XL710_OFFSET; + else if (hw->mac.type == I40E_MAC_X722) + offset = I40E_LLDP_CURRENT_STATUS_X722_OFFSET; + else + return I40E_NOT_SUPPORTED; + + ret = i40e_read_nvm_module_data(hw, + I40E_SR_EMP_SR_SETTINGS_PTR, + offset, 1, + &lldp_cfg.adminstatus); + } else { + ret = i40e_read_lldp_cfg(hw, &lldp_cfg); + } if (ret) return I40E_ERR_NOT_READY; diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h index ddb48ae7cce4..2a80c5daa376 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h @@ -30,6 +30,8 @@ #define I40E_CEE_SUBTYPE_APP_PRI 4 #define I40E_CEE_MAX_FEAT_TYPE 3 +#define I40E_LLDP_CURRENT_STATUS_XL710_OFFSET 0x2B +#define I40E_LLDP_CURRENT_STATUS_X722_OFFSET 0x31 /* Defines for LLDP TLV header */ #define I40E_LLDP_TLV_LEN_SHIFT 0 #define I40E_LLDP_TLV_LEN_MASK (0x01FF << I40E_LLDP_TLV_LEN_SHIFT) diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index 55d20acfcf70..99ea543dd245 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -1125,10 +1125,6 @@ static ssize_t i40e_dbg_command_write(struct file *filp, dev_info(&pf->pdev->dev, "debugfs: forcing GlobR\n"); i40e_do_reset_safe(pf, BIT(__I40E_GLOBAL_RESET_REQUESTED)); - } else if (strncmp(cmd_buf, "empr", 4) == 0) { - dev_info(&pf->pdev->dev, "debugfs: forcing EMPR\n"); - i40e_do_reset_safe(pf, BIT(__I40E_EMP_RESET_REQUESTED)); - } else if (strncmp(cmd_buf, "read", 4) == 0) { u32 address; u32 value; @@ -1732,29 +1728,15 @@ static const struct file_operations i40e_dbg_netdev_ops_fops = { **/ void i40e_dbg_pf_init(struct i40e_pf *pf) { - struct dentry *pfile; const char *name = pci_name(pf->pdev); - const struct device *dev = &pf->pdev->dev; pf->i40e_dbg_pf = debugfs_create_dir(name, i40e_dbg_root); - if (!pf->i40e_dbg_pf) - return; - - pfile = debugfs_create_file("command", 0600, pf->i40e_dbg_pf, pf, - &i40e_dbg_command_fops); - if (!pfile) - goto create_failed; - pfile = debugfs_create_file("netdev_ops", 0600, pf->i40e_dbg_pf, pf, - &i40e_dbg_netdev_ops_fops); - if (!pfile) - goto create_failed; + debugfs_create_file("command", 0600, pf->i40e_dbg_pf, pf, + &i40e_dbg_command_fops); - return; - -create_failed: - dev_info(dev, "debugfs dir/file for %s failed\n", name); - debugfs_remove_recursive(pf->i40e_dbg_pf); + debugfs_create_file("netdev_ops", 0600, pf->i40e_dbg_pf, pf, + &i40e_dbg_netdev_ops_fops); } /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index 527eb52c5401..41e1240acaea 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -711,6 +711,35 @@ static void i40e_phy_type_to_ethtool(struct i40e_pf *pf, } /** + * i40e_get_settings_link_up_fec - Get the FEC mode encoding from mask + * @req_fec_info: mask request FEC info + * @ks: ethtool ksettings to fill in + **/ +static void i40e_get_settings_link_up_fec(u8 req_fec_info, + struct ethtool_link_ksettings *ks) +{ + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); + + if (I40E_AQ_SET_FEC_REQUEST_RS & req_fec_info) { + ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); + } else if (I40E_AQ_SET_FEC_REQUEST_KR & req_fec_info) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_BASER); + } else { + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_NONE); + if (I40E_AQ_SET_FEC_AUTO & req_fec_info) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_RS); + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_BASER); + } + } +} + +/** * i40e_get_settings_link_up - Get the Link settings for when link is up * @hw: hw structure * @ks: ethtool ksettings to fill in @@ -769,13 +798,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 25000baseSR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseSR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); ethtool_link_ksettings_add_link_mode(ks, supported, 10000baseSR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, @@ -892,9 +915,6 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 40000baseKR4_Full); ethtool_link_ksettings_add_link_mode(ks, supported, 25000baseKR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); ethtool_link_ksettings_add_link_mode(ks, supported, 20000baseKR2_Full); ethtool_link_ksettings_add_link_mode(ks, supported, @@ -908,10 +928,7 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 40000baseKR4_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseKR_Full); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); ethtool_link_ksettings_add_link_mode(ks, advertising, 20000baseKR2_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, @@ -929,13 +946,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 25000baseCR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseCR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); + break; case I40E_PHY_TYPE_25GBASE_AOC: case I40E_PHY_TYPE_25GBASE_ACC: @@ -945,13 +957,8 @@ static void i40e_get_settings_link_up(struct i40e_hw *hw, 25000baseCR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, 25000baseCR_Full); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); + i40e_get_settings_link_up_fec(hw_link_info->req_fec_info, ks); + ethtool_link_ksettings_add_link_mode(ks, supported, 10000baseCR_Full); ethtool_link_ksettings_add_link_mode(ks, advertising, @@ -2250,7 +2257,7 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_vsi *vsi = np->vsi; struct i40e_pf *pf = vsi->back; - struct i40e_veb *veb = pf->veb[pf->lan_veb]; + struct i40e_veb *veb = NULL; unsigned int i; bool veb_stats; u64 *p = data; @@ -2273,8 +2280,14 @@ static void i40e_get_ethtool_stats(struct net_device *netdev, goto check_data_pointer; veb_stats = ((pf->lan_veb != I40E_NO_VEB) && + (pf->lan_veb < I40E_MAX_VEB) && (pf->flags & I40E_FLAG_VEB_STATS_ENABLED)); + if (veb_stats) { + veb = pf->veb[pf->lan_veb]; + i40e_update_veb_stats(veb); + } + /* If veb stats aren't enabled, pass NULL instead of the veb so that * we initialize stats to zero and update the data pointer * intelligently @@ -2329,7 +2342,7 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data) } if (vsi != pf->vsi[pf->lan_vsi] || pf->hw.partition_id != 1) - return; + goto check_data_pointer; i40e_add_stat_strings(&data, i40e_gstrings_veb_stats); @@ -2341,6 +2354,7 @@ static void i40e_get_stat_strings(struct net_device *netdev, u8 *data) for (i = 0; i < I40E_MAX_USER_PRIORITY; i++) i40e_add_stat_strings(&data, i40e_gstrings_pfc_stats, i); +check_data_pointer: WARN_ONCE(data - p != i40e_get_stats_count(netdev) * ETH_GSTRING_LEN, "stat strings count mismatch!"); } @@ -5123,6 +5137,12 @@ static int i40e_get_module_info(struct net_device *netdev, /* Module is not SFF-8472 compliant */ modinfo->type = ETH_MODULE_SFF_8079; modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + } else if (!(sff8472_swap & I40E_MODULE_SFF_DDM_IMPLEMENTED)) { + /* Module is SFF-8472 compliant but doesn't implement + * Digital Diagnostic Monitoring (DDM). + */ + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; } else { modinfo->type = ETH_MODULE_SFF_8472; modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_hmc.c index 19ce93d7fd0a..163ee8c6311c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include "i40e.h" #include "i40e_osdep.h" #include "i40e_register.h" #include "i40e_status.h" diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c index 994011c38fb4..be24d42280d8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c @@ -1,6 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 /* Copyright(c) 2013 - 2018 Intel Corporation. */ +#include "i40e.h" #include "i40e_osdep.h" #include "i40e_register.h" #include "i40e_type.h" @@ -963,7 +964,7 @@ static i40e_status i40e_set_hmc_context(u8 *context_bytes, /** * i40e_hmc_get_object_va - retrieves an object's virtual address - * @hmc_info: pointer to i40e_hmc_info struct + * @hw: the hardware struct, from which we obtain the i40e_hmc_info pointer * @object_base: pointer to u64 to get the va * @rsrc_type: the hmc resource type * @obj_idx: hmc object index @@ -972,16 +973,16 @@ static i40e_status i40e_set_hmc_context(u8 *context_bytes, * base pointer. This function is used for LAN Queue contexts. **/ static -i40e_status i40e_hmc_get_object_va(struct i40e_hmc_info *hmc_info, - u8 **object_base, - enum i40e_hmc_lan_rsrc_type rsrc_type, - u32 obj_idx) +i40e_status i40e_hmc_get_object_va(struct i40e_hw *hw, u8 **object_base, + enum i40e_hmc_lan_rsrc_type rsrc_type, + u32 obj_idx) { + struct i40e_hmc_info *hmc_info = &hw->hmc; u32 obj_offset_in_sd, obj_offset_in_pd; - i40e_status ret_code = 0; struct i40e_hmc_sd_entry *sd_entry; struct i40e_hmc_pd_entry *pd_entry; u32 pd_idx, pd_lmt, rel_pd_idx; + i40e_status ret_code = 0; u64 obj_offset_in_fpm; u32 sd_idx, sd_lmt; @@ -1047,7 +1048,7 @@ i40e_status i40e_clear_lan_tx_queue_context(struct i40e_hw *hw, i40e_status err; u8 *context_bytes; - err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes, + err = i40e_hmc_get_object_va(hw, &context_bytes, I40E_HMC_LAN_TX, queue); if (err < 0) return err; @@ -1068,7 +1069,7 @@ i40e_status i40e_set_lan_tx_queue_context(struct i40e_hw *hw, i40e_status err; u8 *context_bytes; - err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes, + err = i40e_hmc_get_object_va(hw, &context_bytes, I40E_HMC_LAN_TX, queue); if (err < 0) return err; @@ -1088,7 +1089,7 @@ i40e_status i40e_clear_lan_rx_queue_context(struct i40e_hw *hw, i40e_status err; u8 *context_bytes; - err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes, + err = i40e_hmc_get_object_va(hw, &context_bytes, I40E_HMC_LAN_RX, queue); if (err < 0) return err; @@ -1109,7 +1110,7 @@ i40e_status i40e_set_lan_rx_queue_context(struct i40e_hw *hw, i40e_status err; u8 *context_bytes; - err = i40e_hmc_get_object_va(&hw->hmc, &context_bytes, + err = i40e_hmc_get_object_va(hw, &context_bytes, I40E_HMC_LAN_RX, queue); if (err < 0) return err; diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 9ebbe3da61bb..6031223eafab 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -73,6 +73,7 @@ static const struct pci_device_id i40e_pci_tbl[] = { {PCI_VDEVICE(INTEL, I40E_DEV_ID_QSFP_C), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T4), 0}, + {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_BASE_T_BC), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_SFP), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_10G_B), 0}, {PCI_VDEVICE(INTEL, I40E_DEV_ID_KX_X722), 0}, @@ -534,6 +535,10 @@ void i40e_pf_reset_stats(struct i40e_pf *pf) sizeof(pf->veb[i]->stats)); memset(&pf->veb[i]->stats_offsets, 0, sizeof(pf->veb[i]->stats_offsets)); + memset(&pf->veb[i]->tc_stats, 0, + sizeof(pf->veb[i]->tc_stats)); + memset(&pf->veb[i]->tc_stats_offsets, 0, + sizeof(pf->veb[i]->tc_stats_offsets)); pf->veb[i]->stat_offsets_loaded = false; } } @@ -677,7 +682,7 @@ void i40e_update_eth_stats(struct i40e_vsi *vsi) * i40e_update_veb_stats - Update Switch component statistics * @veb: the VEB being updated **/ -static void i40e_update_veb_stats(struct i40e_veb *veb) +void i40e_update_veb_stats(struct i40e_veb *veb) { struct i40e_pf *pf = veb->pf; struct i40e_hw *hw = &pf->hw; @@ -2530,6 +2535,10 @@ int i40e_sync_vsi_filters(struct i40e_vsi *vsi) vsi_name, i40e_stat_str(hw, aq_ret), i40e_aq_str(hw, hw->aq.asq_last_status)); + } else { + dev_info(&pf->pdev->dev, "%s is %s allmulti mode.\n", + vsi->netdev->name, + cur_multipromisc ? "entering" : "leaving"); } } @@ -2583,6 +2592,10 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) return; if (!test_and_clear_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state)) return; + if (test_and_set_bit(__I40E_VF_DISABLE, pf->state)) { + set_bit(__I40E_MACVLAN_SYNC_PENDING, pf->state); + return; + } for (v = 0; v < pf->num_alloc_vsi; v++) { if (pf->vsi[v] && @@ -2597,6 +2610,7 @@ static void i40e_sync_filters_subtask(struct i40e_pf *pf) } } } + clear_bit(__I40E_VF_DISABLE, pf->state); } /** @@ -3360,7 +3374,7 @@ static int i40e_vsi_configure_tx(struct i40e_vsi *vsi) for (i = 0; (i < vsi->num_queue_pairs) && !err; i++) err = i40e_configure_tx_ring(vsi->tx_rings[i]); - if (!i40e_enabled_xdp_vsi(vsi)) + if (err || !i40e_enabled_xdp_vsi(vsi)) return err; for (i = 0; (i < vsi->num_queue_pairs) && !err; i++) @@ -6412,50 +6426,6 @@ static int i40e_resume_port_tx(struct i40e_pf *pf) } /** - * i40e_update_dcb_config - * @hw: pointer to the HW struct - * @enable_mib_change: enable MIB change event - * - * Update DCB configuration from the firmware - **/ -static enum i40e_status_code -i40e_update_dcb_config(struct i40e_hw *hw, bool enable_mib_change) -{ - struct i40e_lldp_variables lldp_cfg; - i40e_status ret; - - if (!hw->func_caps.dcb) - return I40E_NOT_SUPPORTED; - - /* Read LLDP NVM area */ - ret = i40e_read_lldp_cfg(hw, &lldp_cfg); - if (ret) - return I40E_ERR_NOT_READY; - - /* Get DCBX status */ - ret = i40e_get_dcbx_status(hw, &hw->dcbx_status); - if (ret) - return ret; - - /* Check the DCBX Status */ - if (hw->dcbx_status == I40E_DCBX_STATUS_DONE || - hw->dcbx_status == I40E_DCBX_STATUS_IN_PROGRESS) { - /* Get current DCBX configuration */ - ret = i40e_get_dcb_config(hw); - if (ret) - return ret; - } else if (hw->dcbx_status == I40E_DCBX_STATUS_DISABLED) { - return I40E_ERR_NOT_READY; - } - - /* Configure the LLDP MIB change event */ - if (enable_mib_change) - ret = i40e_aq_cfg_lldp_mib_change_event(hw, true, NULL); - - return ret; -} - -/** * i40e_init_pf_dcb - Initialize DCB configuration * @pf: PF being configured * @@ -6477,7 +6447,7 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf) goto out; } - err = i40e_update_dcb_config(hw, true); + err = i40e_init_dcb(hw, true); if (!err) { /* Device/Function is not DCBX capable */ if ((!hw->func_caps.dcb) || @@ -6599,19 +6569,19 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) } if (pf->hw.phy.link_info.link_speed == I40E_LINK_SPEED_25GB) { - req_fec = ", Requested FEC: None"; - fec = ", FEC: None"; - an = ", Autoneg: False"; + req_fec = "None"; + fec = "None"; + an = "False"; if (pf->hw.phy.link_info.an_info & I40E_AQ_AN_COMPLETED) - an = ", Autoneg: True"; + an = "True"; if (pf->hw.phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_KR_ENA) - fec = ", FEC: CL74 FC-FEC/BASE-R"; + fec = "CL74 FC-FEC/BASE-R"; else if (pf->hw.phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_RS_ENA) - fec = ", FEC: CL108 RS-FEC"; + fec = "CL108 RS-FEC"; /* 'CL108 RS-FEC' should be displayed when RS is requested, or * both RS and FC are requested @@ -6620,14 +6590,19 @@ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) (I40E_AQ_REQUEST_FEC_KR | I40E_AQ_REQUEST_FEC_RS)) { if (vsi->back->hw.phy.link_info.req_fec_info & I40E_AQ_REQUEST_FEC_RS) - req_fec = ", Requested FEC: CL108 RS-FEC"; + req_fec = "CL108 RS-FEC"; else - req_fec = ", Requested FEC: CL74 FC-FEC/BASE-R"; + req_fec = "CL74 FC-FEC/BASE-R"; } + netdev_info(vsi->netdev, + "NIC Link is Up, %sbps Full Duplex, Requested FEC: %s, Negotiated FEC: %s, Autoneg: %s, Flow Control: %s\n", + speed, req_fec, fec, an, fc); + } else { + netdev_info(vsi->netdev, + "NIC Link is Up, %sbps Full Duplex, Flow Control: %s\n", + speed, fc); } - netdev_info(vsi->netdev, "NIC Link is Up, %sbps Full Duplex%s%s%s, Flow Control: %s\n", - speed, req_fec, fec, an, fc); } /** @@ -8486,6 +8461,11 @@ void i40e_do_reset(struct i40e_pf *pf, u32 reset_flags, bool lock_acquired) dev_dbg(&pf->pdev->dev, "PFR requested\n"); i40e_handle_reset_warning(pf, lock_acquired); + dev_info(&pf->pdev->dev, + pf->flags & I40E_FLAG_DISABLE_FW_LLDP ? + "FW LLDP is disabled\n" : + "FW LLDP is enabled\n"); + } else if (reset_flags & BIT_ULL(__I40E_REINIT_REQUESTED)) { int v; @@ -12561,7 +12541,8 @@ static int i40e_xdp_setup(struct i40e_vsi *vsi, if (need_reset && prog) for (i = 0; i < vsi->num_queue_pairs; i++) if (vsi->xdp_rings[i]->xsk_umem) - (void)i40e_xsk_async_xmit(vsi->netdev, i); + (void)i40e_xsk_wakeup(vsi->netdev, i, + XDP_WAKEUP_RX); return 0; } @@ -12883,7 +12864,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_bridge_setlink = i40e_ndo_bridge_setlink, .ndo_bpf = i40e_xdp, .ndo_xdp_xmit = i40e_xdp_xmit, - .ndo_xsk_async_xmit = i40e_xsk_async_xmit, + .ndo_xsk_wakeup = i40e_xsk_wakeup, .ndo_dfwd_add_station = i40e_fwd_add, .ndo_dfwd_del_station = i40e_fwd_del, }; @@ -14569,9 +14550,20 @@ void i40e_set_fec_in_flags(u8 fec_cfg, u32 *flags) **/ static bool i40e_check_recovery_mode(struct i40e_pf *pf) { - u32 val = rd32(&pf->hw, I40E_GL_FWSTS); - - if (val & I40E_GL_FWSTS_FWS1B_MASK) { + u32 val = rd32(&pf->hw, I40E_GL_FWSTS) & I40E_GL_FWSTS_FWS1B_MASK; + bool is_recovery_mode = false; + + if (pf->hw.mac.type == I40E_MAC_XL710) + is_recovery_mode = + val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK || + val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK || + val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_TRANSITION_MASK || + val == I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_NVM_MASK; + if (pf->hw.mac.type == I40E_MAC_X722) + is_recovery_mode = + val == I40E_X722_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK || + val == I40E_X722_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK; + if (is_recovery_mode) { dev_notice(&pf->pdev->dev, "Firmware recovery mode detected. Limiting functionality.\n"); dev_notice(&pf->pdev->dev, "Refer to the Intel(R) Ethernet Adapters and Devices User Guide for details on firmware recovery mode.\n"); set_bit(__I40E_RECOVERY_MODE, pf->state); @@ -14585,6 +14577,51 @@ static bool i40e_check_recovery_mode(struct i40e_pf *pf) } /** + * i40e_pf_loop_reset - perform reset in a loop. + * @pf: board private structure + * + * This function is useful when a NIC is about to enter recovery mode. + * When a NIC's internal data structures are corrupted the NIC's + * firmware is going to enter recovery mode. + * Right after a POR it takes about 7 minutes for firmware to enter + * recovery mode. Until that time a NIC is in some kind of intermediate + * state. After that time period the NIC almost surely enters + * recovery mode. The only way for a driver to detect intermediate + * state is to issue a series of pf-resets and check a return value. + * If a PF reset returns success then the firmware could be in recovery + * mode so the caller of this code needs to check for recovery mode + * if this function returns success. There is a little chance that + * firmware will hang in intermediate state forever. + * Since waiting 7 minutes is quite a lot of time this function waits + * 10 seconds and then gives up by returning an error. + * + * Return 0 on success, negative on failure. + **/ +static i40e_status i40e_pf_loop_reset(struct i40e_pf *pf) +{ + const unsigned short MAX_CNT = 1000; + const unsigned short MSECS = 10; + struct i40e_hw *hw = &pf->hw; + i40e_status ret; + int cnt; + + for (cnt = 0; cnt < MAX_CNT; ++cnt) { + ret = i40e_pf_reset(hw); + if (!ret) + break; + msleep(MSECS); + } + + if (cnt == MAX_CNT) { + dev_info(&pf->pdev->dev, "PF reset failed: %d\n", ret); + return ret; + } + + pf->pfr_count++; + return ret; +} + +/** * i40e_init_recovery_mode - initialize subsystems needed in recovery mode * @pf: board private structure * @hw: ptr to the hardware info @@ -14812,14 +14849,22 @@ static int i40e_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Reset here to make sure all is clean and to define PF 'n' */ i40e_clear_hw(hw); - if (!i40e_check_recovery_mode(pf)) { - err = i40e_pf_reset(hw); - if (err) { - dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err); - goto err_pf_reset; - } - pf->pfr_count++; + + err = i40e_set_mac_type(hw); + if (err) { + dev_warn(&pdev->dev, "unidentified MAC or BLANK NVM: %d\n", + err); + goto err_pf_reset; } + + err = i40e_pf_loop_reset(pf); + if (err) { + dev_info(&pdev->dev, "Initial pf_reset failed: %d\n", err); + goto err_pf_reset; + } + + i40e_check_recovery_mode(pf); + hw->aq.num_arq_entries = I40E_AQ_LEN; hw->aq.num_asq_entries = I40E_AQ_LEN; hw->aq.arq_buf_size = I40E_MAX_AQ_BUF_SIZE; @@ -15605,8 +15650,7 @@ static void i40e_shutdown(struct pci_dev *pdev) **/ static int __maybe_unused i40e_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct i40e_pf *pf = pci_get_drvdata(pdev); + struct i40e_pf *pf = dev_get_drvdata(dev); struct i40e_hw *hw = &pf->hw; /* If we're already suspended, then there is nothing to do */ @@ -15656,8 +15700,7 @@ static int __maybe_unused i40e_suspend(struct device *dev) **/ static int __maybe_unused i40e_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct i40e_pf *pf = pci_get_drvdata(pdev); + struct i40e_pf *pf = dev_get_drvdata(dev); int err; /* If we're not suspended, then there is nothing to do */ @@ -15674,7 +15717,7 @@ static int __maybe_unused i40e_resume(struct device *dev) */ err = i40e_restore_interrupt_scheme(pf); if (err) { - dev_err(&pdev->dev, "Cannot restore interrupt scheme: %d\n", + dev_err(dev, "Cannot restore interrupt scheme: %d\n", err); } diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index c508b75c3c09..e4d8d20baf3b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -322,6 +322,77 @@ i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, } /** + * i40e_read_nvm_module_data - Reads NVM Buffer to specified memory location + * @hw: pointer to the HW structure + * @module_ptr: Pointer to module in words with respect to NVM beginning + * @offset: offset in words from module start + * @words_data_size: Words to read from NVM + * @data_ptr: Pointer to memory location where resulting buffer will be stored + **/ +i40e_status i40e_read_nvm_module_data(struct i40e_hw *hw, + u8 module_ptr, u16 offset, + u16 words_data_size, + u16 *data_ptr) +{ + i40e_status status; + u16 ptr_value = 0; + u32 flat_offset; + + if (module_ptr != 0) { + status = i40e_read_nvm_word(hw, module_ptr, &ptr_value); + if (status) { + i40e_debug(hw, I40E_DEBUG_ALL, + "Reading nvm word failed.Error code: %d.\n", + status); + return I40E_ERR_NVM; + } + } +#define I40E_NVM_INVALID_PTR_VAL 0x7FFF +#define I40E_NVM_INVALID_VAL 0xFFFF + + /* Pointer not initialized */ + if (ptr_value == I40E_NVM_INVALID_PTR_VAL || + ptr_value == I40E_NVM_INVALID_VAL) + return I40E_ERR_BAD_PTR; + + /* Check whether the module is in SR mapped area or outside */ + if (ptr_value & I40E_PTR_TYPE) { + /* Pointer points outside of the Shared RAM mapped area */ + ptr_value &= ~I40E_PTR_TYPE; + + /* PtrValue in 4kB units, need to convert to words */ + ptr_value /= 2; + flat_offset = ((u32)ptr_value * 0x1000) + (u32)offset; + status = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); + if (!status) { + status = i40e_aq_read_nvm(hw, 0, 2 * flat_offset, + 2 * words_data_size, + data_ptr, true, NULL); + i40e_release_nvm(hw); + if (status) { + i40e_debug(hw, I40E_DEBUG_ALL, + "Reading nvm aq failed.Error code: %d.\n", + status); + return I40E_ERR_NVM; + } + } else { + return I40E_ERR_NVM; + } + } else { + /* Read from the Shadow RAM */ + status = i40e_read_nvm_buffer(hw, ptr_value + offset, + &words_data_size, data_ptr); + if (status) { + i40e_debug(hw, I40E_DEBUG_ALL, + "Reading nvm buffer failed.Error code: %d.\n", + status); + } + } + + return status; +} + +/** * i40e_read_nvm_buffer_srctl - Reads Shadow RAM buffer via SRCTL register * @hw: pointer to the HW structure * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF). @@ -430,6 +501,36 @@ static i40e_status __i40e_read_nvm_buffer(struct i40e_hw *hw, } /** + * i40e_read_nvm_buffer - Reads Shadow RAM buffer and acquire lock if necessary + * @hw: pointer to the HW structure + * @offset: offset of the Shadow RAM word to read (0x000000 - 0x001FFF). + * @words: (in) number of words to read; (out) number of words actually read + * @data: words read from the Shadow RAM + * + * Reads 16 bit words (data buffer) from the SR using the i40e_read_nvm_srrd() + * method. The buffer read is preceded by the NVM ownership take + * and followed by the release. + **/ +i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, + u16 *words, u16 *data) +{ + i40e_status ret_code = 0; + + if (hw->flags & I40E_HW_FLAG_AQ_SRCTL_ACCESS_ENABLE) { + ret_code = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); + if (!ret_code) { + ret_code = i40e_read_nvm_buffer_aq(hw, offset, words, + data); + i40e_release_nvm(hw); + } + } else { + ret_code = i40e_read_nvm_buffer_srctl(hw, offset, words, data); + } + + return ret_code; +} + +/** * i40e_write_nvm_aq - Writes Shadow RAM. * @hw: pointer to the HW structure. * @module_pointer: module pointer location in words from the NVM beginning diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h index a07574bff550..c302ef2524f8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h +++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h @@ -18,7 +18,10 @@ * actual OS primitives */ -#define hw_dbg(hw, S, A...) do {} while (0) +#define hw_dbg(hw, S, A...) \ +do { \ + dev_dbg(&((struct i40e_pf *)hw->back)->pdev->dev, S, ##A); \ +} while (0) #define wr32(a, reg, value) writel((value), ((a)->hw_addr + (reg))) #define rd32(a, reg) readl((a)->hw_addr + (reg)) diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index eac88bcc6c06..5250441bf75b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -315,6 +315,12 @@ i40e_status i40e_acquire_nvm(struct i40e_hw *hw, void i40e_release_nvm(struct i40e_hw *hw); i40e_status i40e_read_nvm_word(struct i40e_hw *hw, u16 offset, u16 *data); +i40e_status i40e_read_nvm_module_data(struct i40e_hw *hw, + u8 module_ptr, u16 offset, + u16 words_data_size, + u16 *data_ptr); +i40e_status i40e_read_nvm_buffer(struct i40e_hw *hw, u16 offset, + u16 *words, u16 *data); i40e_status i40e_update_nvm_checksum(struct i40e_hw *hw); i40e_status i40e_validate_nvm_checksum(struct i40e_hw *hw, u16 *checksum); @@ -326,6 +332,8 @@ void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode, void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw); void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status); +i40e_status i40e_set_mac_type(struct i40e_hw *hw); + extern struct i40e_rx_ptype_decoded i40e_ptype_lookup[]; static inline struct i40e_rx_ptype_decoded decode_rx_desc_ptype(u8 ptype) diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 11394a52e21c..9bf1ad4319f5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -725,7 +725,7 @@ static long i40e_ptp_create_clock(struct i40e_pf *pf) pf->tstamp_config.tx_type = HWTSTAMP_TX_OFF; /* Set the previous "reset" time to the current Kernel clock time */ - pf->ptp_prev_hw_time = ktime_to_timespec64(ktime_get_real()); + ktime_get_real_ts64(&pf->ptp_prev_hw_time); pf->ptp_reset_start = ktime_get(); return 0; diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index 52e3680c57f8..d35d690ca10f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -58,7 +58,7 @@ #define I40E_PF_ARQLEN_ARQCRIT_SHIFT 30 #define I40E_PF_ARQLEN_ARQCRIT_MASK I40E_MASK(0x1, I40E_PF_ARQLEN_ARQCRIT_SHIFT) #define I40E_PF_ARQLEN_ARQENABLE_SHIFT 31 -#define I40E_PF_ARQLEN_ARQENABLE_MASK I40E_MASK(0x1, I40E_PF_ARQLEN_ARQENABLE_SHIFT) +#define I40E_PF_ARQLEN_ARQENABLE_MASK I40E_MASK(0x1u, I40E_PF_ARQLEN_ARQENABLE_SHIFT) #define I40E_PF_ARQT 0x00080480 /* Reset: EMPR */ #define I40E_PF_ARQT_ARQT_SHIFT 0 #define I40E_PF_ARQT_ARQT_MASK I40E_MASK(0x3FF, I40E_PF_ARQT_ARQT_SHIFT) @@ -81,7 +81,7 @@ #define I40E_PF_ATQLEN_ATQCRIT_SHIFT 30 #define I40E_PF_ATQLEN_ATQCRIT_MASK I40E_MASK(0x1, I40E_PF_ATQLEN_ATQCRIT_SHIFT) #define I40E_PF_ATQLEN_ATQENABLE_SHIFT 31 -#define I40E_PF_ATQLEN_ATQENABLE_MASK I40E_MASK(0x1, I40E_PF_ATQLEN_ATQENABLE_SHIFT) +#define I40E_PF_ATQLEN_ATQENABLE_MASK I40E_MASK(0x1u, I40E_PF_ATQLEN_ATQENABLE_SHIFT) #define I40E_PF_ATQT 0x00080400 /* Reset: EMPR */ #define I40E_PF_ATQT_ATQT_SHIFT 0 #define I40E_PF_ATQT_ATQT_MASK I40E_MASK(0x3FF, I40E_PF_ATQT_ATQT_SHIFT) @@ -108,7 +108,7 @@ #define I40E_VF_ARQLEN_ARQCRIT_SHIFT 30 #define I40E_VF_ARQLEN_ARQCRIT_MASK I40E_MASK(0x1, I40E_VF_ARQLEN_ARQCRIT_SHIFT) #define I40E_VF_ARQLEN_ARQENABLE_SHIFT 31 -#define I40E_VF_ARQLEN_ARQENABLE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN_ARQENABLE_SHIFT) +#define I40E_VF_ARQLEN_ARQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ARQLEN_ARQENABLE_SHIFT) #define I40E_VF_ARQT(_VF) (0x00082C00 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */ #define I40E_VF_ARQT_MAX_INDEX 127 #define I40E_VF_ARQT_ARQT_SHIFT 0 @@ -136,7 +136,7 @@ #define I40E_VF_ATQLEN_ATQCRIT_SHIFT 30 #define I40E_VF_ATQLEN_ATQCRIT_MASK I40E_MASK(0x1, I40E_VF_ATQLEN_ATQCRIT_SHIFT) #define I40E_VF_ATQLEN_ATQENABLE_SHIFT 31 -#define I40E_VF_ATQLEN_ATQENABLE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN_ATQENABLE_SHIFT) +#define I40E_VF_ATQLEN_ATQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ATQLEN_ATQENABLE_SHIFT) #define I40E_VF_ATQT(_VF) (0x00082800 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: EMPR */ #define I40E_VF_ATQT_MAX_INDEX 127 #define I40E_VF_ATQT_ATQT_SHIFT 0 @@ -259,7 +259,7 @@ #define I40E_PRTDCB_RETSTCC_UPINTC_MODE_SHIFT 30 #define I40E_PRTDCB_RETSTCC_UPINTC_MODE_MASK I40E_MASK(0x1, I40E_PRTDCB_RETSTCC_UPINTC_MODE_SHIFT) #define I40E_PRTDCB_RETSTCC_ETSTC_SHIFT 31 -#define I40E_PRTDCB_RETSTCC_ETSTC_MASK I40E_MASK(0x1, I40E_PRTDCB_RETSTCC_ETSTC_SHIFT) +#define I40E_PRTDCB_RETSTCC_ETSTC_MASK I40E_MASK(0x1u, I40E_PRTDCB_RETSTCC_ETSTC_SHIFT) #define I40E_PRTDCB_RPPMC 0x001223A0 /* Reset: CORER */ #define I40E_PRTDCB_RPPMC_LANRPPM_SHIFT 0 #define I40E_PRTDCB_RPPMC_LANRPPM_MASK I40E_MASK(0xFF, I40E_PRTDCB_RPPMC_LANRPPM_SHIFT) @@ -363,6 +363,12 @@ #define I40E_GL_FWSTS_FWRI_MASK I40E_MASK(0x1, I40E_GL_FWSTS_FWRI_SHIFT) #define I40E_GL_FWSTS_FWS1B_SHIFT 16 #define I40E_GL_FWSTS_FWS1B_MASK I40E_MASK(0xFF, I40E_GL_FWSTS_FWS1B_SHIFT) +#define I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK I40E_MASK(0x30, I40E_GL_FWSTS_FWS1B_SHIFT) +#define I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK I40E_MASK(0x31, I40E_GL_FWSTS_FWS1B_SHIFT) +#define I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_TRANSITION_MASK I40E_MASK(0x32, I40E_GL_FWSTS_FWS1B_SHIFT) +#define I40E_XL710_GL_FWSTS_FWS1B_REC_MOD_NVM_MASK I40E_MASK(0x33, I40E_GL_FWSTS_FWS1B_SHIFT) +#define I40E_X722_GL_FWSTS_FWS1B_REC_MOD_CORER_MASK I40E_MASK(0xB, I40E_GL_FWSTS_FWS1B_SHIFT) +#define I40E_X722_GL_FWSTS_FWS1B_REC_MOD_GLOBR_MASK I40E_MASK(0xC, I40E_GL_FWSTS_FWS1B_SHIFT) #define I40E_GLGEN_CLKSTAT 0x000B8184 /* Reset: POR */ #define I40E_GLGEN_CLKSTAT_CLKMODE_SHIFT 0 #define I40E_GLGEN_CLKSTAT_CLKMODE_MASK I40E_MASK(0x1, I40E_GLGEN_CLKSTAT_CLKMODE_SHIFT) @@ -503,7 +509,7 @@ #define I40E_GLGEN_MSCA_MDICMD_SHIFT 30 #define I40E_GLGEN_MSCA_MDICMD_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_MDICMD_SHIFT) #define I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT 31 -#define I40E_GLGEN_MSCA_MDIINPROGEN_MASK I40E_MASK(0x1, I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT) +#define I40E_GLGEN_MSCA_MDIINPROGEN_MASK I40E_MASK(0x1u, I40E_GLGEN_MSCA_MDIINPROGEN_SHIFT) #define I40E_GLGEN_MSRWD(_i) (0x0008819C + ((_i) * 4)) /* _i=0...3 */ /* Reset: POR */ #define I40E_GLGEN_MSRWD_MAX_INDEX 3 #define I40E_GLGEN_MSRWD_MDIWRDATA_SHIFT 0 @@ -1242,14 +1248,14 @@ #define I40E_GLLAN_TXPRE_QDIS_SET_QDIS_SHIFT 30 #define I40E_GLLAN_TXPRE_QDIS_SET_QDIS_MASK I40E_MASK(0x1, I40E_GLLAN_TXPRE_QDIS_SET_QDIS_SHIFT) #define I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_SHIFT 31 -#define I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_MASK I40E_MASK(0x1, I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_SHIFT) +#define I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_MASK I40E_MASK(0x1u, I40E_GLLAN_TXPRE_QDIS_CLEAR_QDIS_SHIFT) #define I40E_PFLAN_QALLOC 0x001C0400 /* Reset: CORER */ #define I40E_PFLAN_QALLOC_FIRSTQ_SHIFT 0 #define I40E_PFLAN_QALLOC_FIRSTQ_MASK I40E_MASK(0x7FF, I40E_PFLAN_QALLOC_FIRSTQ_SHIFT) #define I40E_PFLAN_QALLOC_LASTQ_SHIFT 16 #define I40E_PFLAN_QALLOC_LASTQ_MASK I40E_MASK(0x7FF, I40E_PFLAN_QALLOC_LASTQ_SHIFT) #define I40E_PFLAN_QALLOC_VALID_SHIFT 31 -#define I40E_PFLAN_QALLOC_VALID_MASK I40E_MASK(0x1, I40E_PFLAN_QALLOC_VALID_SHIFT) +#define I40E_PFLAN_QALLOC_VALID_MASK I40E_MASK(0x1u, I40E_PFLAN_QALLOC_VALID_SHIFT) #define I40E_QRX_ENA(_Q) (0x00120000 + ((_Q) * 4)) /* _i=0...1535 */ /* Reset: PFR */ #define I40E_QRX_ENA_MAX_INDEX 1535 #define I40E_QRX_ENA_QENA_REQ_SHIFT 0 @@ -1658,7 +1664,7 @@ #define I40E_GLNVM_SRCTL_START_SHIFT 30 #define I40E_GLNVM_SRCTL_START_MASK I40E_MASK(0x1, I40E_GLNVM_SRCTL_START_SHIFT) #define I40E_GLNVM_SRCTL_DONE_SHIFT 31 -#define I40E_GLNVM_SRCTL_DONE_MASK I40E_MASK(0x1, I40E_GLNVM_SRCTL_DONE_SHIFT) +#define I40E_GLNVM_SRCTL_DONE_MASK I40E_MASK(0x1u, I40E_GLNVM_SRCTL_DONE_SHIFT) #define I40E_GLNVM_SRDATA 0x000B6114 /* Reset: POR */ #define I40E_GLNVM_SRDATA_WRDATA_SHIFT 0 #define I40E_GLNVM_SRDATA_WRDATA_MASK I40E_MASK(0xFFFF, I40E_GLNVM_SRDATA_WRDATA_SHIFT) @@ -3025,7 +3031,7 @@ #define I40E_PF_VT_PFALLOC_LASTVF_SHIFT 8 #define I40E_PF_VT_PFALLOC_LASTVF_MASK I40E_MASK(0xFF, I40E_PF_VT_PFALLOC_LASTVF_SHIFT) #define I40E_PF_VT_PFALLOC_VALID_SHIFT 31 -#define I40E_PF_VT_PFALLOC_VALID_MASK I40E_MASK(0x1, I40E_PF_VT_PFALLOC_VALID_SHIFT) +#define I40E_PF_VT_PFALLOC_VALID_MASK I40E_MASK(0x1u, I40E_PF_VT_PFALLOC_VALID_SHIFT) #define I40E_VP_MDET_RX(_VF) (0x0012A000 + ((_VF) * 4)) /* _i=0...127 */ /* Reset: CORER */ #define I40E_VP_MDET_RX_MAX_INDEX 127 #define I40E_VP_MDET_RX_VALID_SHIFT 0 @@ -3161,7 +3167,7 @@ #define I40E_VF_ARQLEN1_ARQCRIT_SHIFT 30 #define I40E_VF_ARQLEN1_ARQCRIT_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQCRIT_SHIFT) #define I40E_VF_ARQLEN1_ARQENABLE_SHIFT 31 -#define I40E_VF_ARQLEN1_ARQENABLE_MASK I40E_MASK(0x1, I40E_VF_ARQLEN1_ARQENABLE_SHIFT) +#define I40E_VF_ARQLEN1_ARQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ARQLEN1_ARQENABLE_SHIFT) #define I40E_VF_ARQT1 0x00007000 /* Reset: EMPR */ #define I40E_VF_ARQT1_ARQT_SHIFT 0 #define I40E_VF_ARQT1_ARQT_MASK I40E_MASK(0x3FF, I40E_VF_ARQT1_ARQT_SHIFT) @@ -3184,7 +3190,7 @@ #define I40E_VF_ATQLEN1_ATQCRIT_SHIFT 30 #define I40E_VF_ATQLEN1_ATQCRIT_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQCRIT_SHIFT) #define I40E_VF_ATQLEN1_ATQENABLE_SHIFT 31 -#define I40E_VF_ATQLEN1_ATQENABLE_MASK I40E_MASK(0x1, I40E_VF_ATQLEN1_ATQENABLE_SHIFT) +#define I40E_VF_ATQLEN1_ATQENABLE_MASK I40E_MASK(0x1u, I40E_VF_ATQLEN1_ATQENABLE_SHIFT) #define I40E_VF_ATQT1 0x00008400 /* Reset: EMPR */ #define I40E_VF_ATQT1_ATQT_SHIFT 0 #define I40E_VF_ATQT1_ATQT_MASK I40E_MASK(0x3FF, I40E_VF_ATQT1_ATQT_SHIFT) diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index 2a2fe3ec7926..e3f29dc8b290 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -3262,7 +3262,7 @@ int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size) **/ bool __i40e_chk_linearize(struct sk_buff *skb) { - const struct skb_frag_struct *frag, *stale; + const skb_frag_t *frag, *stale; int nr_frags, sum; /* no need to check if number of frags is less than 7 */ @@ -3306,7 +3306,7 @@ bool __i40e_chk_linearize(struct sk_buff *skb) * descriptor associated with the fragment. */ if (stale_size > I40E_MAX_DATA_PER_TXD) { - int align_pad = -(stale->page_offset) & + int align_pad = -(skb_frag_off(stale)) & (I40E_MAX_READ_REQ_SIZE - 1); sum -= align_pad; @@ -3349,7 +3349,7 @@ static inline int i40e_tx_map(struct i40e_ring *tx_ring, struct sk_buff *skb, { unsigned int data_len = skb->data_len; unsigned int size = skb_headlen(skb); - struct skb_frag_struct *frag; + skb_frag_t *frag; struct i40e_tx_buffer *tx_bi; struct i40e_tx_desc *tx_desc; u16 i = tx_ring->next_to_use; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 100e92d2982f..36d37f31a287 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -521,7 +521,7 @@ static inline u32 i40e_get_head(struct i40e_ring *tx_ring) **/ static inline int i40e_xmit_descriptor_count(struct sk_buff *skb) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; unsigned int nr_frags = skb_shinfo(skb)->nr_frags; int count = 0, size = skb_headlen(skb); diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index 8f43aa47c263..b43ec94a0f29 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -443,6 +443,7 @@ struct i40e_nvm_access { #define I40E_MODULE_SFF_8472_COMP 0x5E #define I40E_MODULE_SFF_8472_SWAP 0x5C #define I40E_MODULE_SFF_ADDR_MODE 0x04 +#define I40E_MODULE_SFF_DDM_IMPLEMENTED 0x40 #define I40E_MODULE_TYPE_QSFP_PLUS 0x0D #define I40E_MODULE_TYPE_QSFP28 0x11 #define I40E_MODULE_QSFP_MAX_LEN 640 @@ -623,6 +624,7 @@ struct i40e_hw { #define I40E_HW_FLAG_NVM_READ_REQUIRES_LOCK BIT_ULL(3) #define I40E_HW_FLAG_FW_LLDP_STOPPABLE BIT_ULL(4) #define I40E_HW_FLAG_FW_LLDP_PERSISTENT BIT_ULL(5) +#define I40E_HW_FLAG_DROP_MODE BIT_ULL(7) u64 flags; /* Used in set switch config AQ command */ @@ -1316,6 +1318,7 @@ struct i40e_hw_port_stats { #define I40E_SR_VPD_PTR 0x2F #define I40E_SR_PCIE_ALT_AUTO_LOAD_PTR 0x3E #define I40E_SR_SW_CHECKSUM_WORD 0x3F +#define I40E_SR_EMP_SR_SETTINGS_PTR 0x48 /* Auxiliary field, mask and shift definition for Shadow RAM and NVM Flash */ #define I40E_SR_VPD_MODULE_MAX_SIZE 1024 diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 02b09a8ad54c..3d2440838822 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -55,7 +55,12 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf) pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; pfe.severity = PF_EVENT_SEVERITY_INFO; - if (vf->link_forced) { + + /* Always report link is down if the VF queues aren't enabled */ + if (!vf->queues_enabled) { + pfe.event_data.link_event.link_status = false; + pfe.event_data.link_event.link_speed = 0; + } else if (vf->link_forced) { pfe.event_data.link_event.link_status = vf->link_up; pfe.event_data.link_event.link_speed = (vf->link_up ? VIRTCHNL_LINK_SPEED_40GB : 0); @@ -65,6 +70,7 @@ static void i40e_vc_notify_vf_link_state(struct i40e_vf *vf) pfe.event_data.link_event.link_speed = i40e_virtchnl_link_speed(ls->link_speed); } + i40e_aq_send_msg_to_vf(hw, abs_vf_id, VIRTCHNL_OP_EVENT, 0, (u8 *)&pfe, sizeof(pfe), NULL); } @@ -2037,30 +2043,33 @@ static int i40e_vc_config_promiscuous_mode_msg(struct i40e_vf *vf, u8 *msg) alluni = true; aq_ret = i40e_config_vf_promiscuous_mode(vf, info->vsi_id, allmulti, alluni); - if (!aq_ret) { - if (allmulti) { + if (aq_ret) + goto err_out; + + if (allmulti) { + if (!test_and_set_bit(I40E_VF_STATE_MC_PROMISC, + &vf->vf_states)) dev_info(&pf->pdev->dev, "VF %d successfully set multicast promiscuous mode\n", vf->vf_id); - set_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); - } else { - dev_info(&pf->pdev->dev, - "VF %d successfully unset multicast promiscuous mode\n", - vf->vf_id); - clear_bit(I40E_VF_STATE_MC_PROMISC, &vf->vf_states); - } - if (alluni) { + } else if (test_and_clear_bit(I40E_VF_STATE_MC_PROMISC, + &vf->vf_states)) + dev_info(&pf->pdev->dev, + "VF %d successfully unset multicast promiscuous mode\n", + vf->vf_id); + + if (alluni) { + if (!test_and_set_bit(I40E_VF_STATE_UC_PROMISC, + &vf->vf_states)) dev_info(&pf->pdev->dev, "VF %d successfully set unicast promiscuous mode\n", vf->vf_id); - set_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); - } else { - dev_info(&pf->pdev->dev, - "VF %d successfully unset unicast promiscuous mode\n", - vf->vf_id); - clear_bit(I40E_VF_STATE_UC_PROMISC, &vf->vf_states); - } - } + } else if (test_and_clear_bit(I40E_VF_STATE_UC_PROMISC, + &vf->vf_states)) + dev_info(&pf->pdev->dev, + "VF %d successfully unset unicast promiscuous mode\n", + vf->vf_id); + err_out: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, @@ -2153,7 +2162,7 @@ static int i40e_vc_config_queues_msg(struct i40e_vf *vf, u8 *msg) * VF does not know about these additional VSIs and all * it cares is about its own queues. PF configures these queues * to its appropriate VSIs based on TC mapping - **/ + */ if (vf->adq_enabled) { if (idx >= ARRAY_SIZE(vf->ch)) { aq_ret = I40E_ERR_NO_AVAILABLE_VSI; @@ -2364,6 +2373,8 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg) } } + vf->queues_enabled = true; + error_param: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_ENABLE_QUEUES, @@ -2385,6 +2396,9 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg) struct i40e_pf *pf = vf->pf; i40e_status aq_ret = 0; + /* Immediately mark queues as disabled */ + vf->queues_enabled = false; + if (!test_bit(I40E_VF_STATE_ACTIVE, &vf->vf_states)) { aq_ret = I40E_ERR_PARAM; goto error_param; @@ -3953,10 +3967,15 @@ int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac) /* When the VF is resetting wait until it is done. * It can take up to 200 milliseconds, * but wait for up to 300 milliseconds to be safe. + * If the VF is indeed in reset, the vsi pointer has + * to show on the newly loaded vsi under pf->vsi[id]. */ for (i = 0; i < 15; i++) { - if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) + if (test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { + if (i > 0) + vsi = pf->vsi[vf->lan_vsi_idx]; break; + } msleep(20); } if (!test_bit(I40E_VF_STATE_INIT, &vf->vf_states)) { @@ -4244,7 +4263,8 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, if (min_tx_rate) { dev_err(&pf->pdev->dev, "Invalid min tx rate (%d) (greater than 0) specified for VF %d.\n", min_tx_rate, vf_id); - return -EINVAL; + ret = -EINVAL; + goto error; } vf = &pf->vf[vf_id]; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index f65cc0c16550..7164b9bb294f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -99,6 +99,7 @@ struct i40e_vf { unsigned int tx_rate; /* Tx bandwidth limit in Mbps */ bool link_forced; bool link_up; /* only valid if VF link is forced */ + bool queues_enabled; /* true if the VF queues are enabled */ bool spoofchk; u16 num_mac; u16 num_vlan; diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.c b/drivers/net/ethernet/intel/i40e/i40e_xsk.c index 32bad014d76c..b1c3227ae4ab 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.c +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.c @@ -116,7 +116,7 @@ static int i40e_xsk_umem_enable(struct i40e_vsi *vsi, struct xdp_umem *umem, return err; /* Kick start the NAPI context so that receiving will start */ - err = i40e_xsk_async_xmit(vsi->netdev, qid); + err = i40e_xsk_wakeup(vsi->netdev, qid, XDP_WAKEUP_RX); if (err) return err; } @@ -157,6 +157,11 @@ static int i40e_xsk_umem_disable(struct i40e_vsi *vsi, u16 qid) err = i40e_queue_pair_enable(vsi, qid); if (err) return err; + + /* Kick start the NAPI context so that receiving will start */ + err = i40e_xsk_wakeup(vsi->netdev, qid, XDP_WAKEUP_RX); + if (err) + return err; } return 0; @@ -190,9 +195,11 @@ int i40e_xsk_umem_setup(struct i40e_vsi *vsi, struct xdp_umem *umem, **/ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) { + struct xdp_umem *umem = rx_ring->xsk_umem; int err, result = I40E_XDP_PASS; struct i40e_ring *xdp_ring; struct bpf_prog *xdp_prog; + u64 offset; u32 act; rcu_read_lock(); @@ -201,7 +208,10 @@ static int i40e_run_xdp_zc(struct i40e_ring *rx_ring, struct xdp_buff *xdp) */ xdp_prog = READ_ONCE(rx_ring->xdp_prog); act = bpf_prog_run_xdp(xdp_prog, xdp); - xdp->handle += xdp->data - xdp->data_hard_start; + offset = xdp->data - xdp->data_hard_start; + + xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset); + switch (act) { case XDP_PASS: break; @@ -262,7 +272,7 @@ static bool i40e_alloc_buffer_zc(struct i40e_ring *rx_ring, bi->addr = xdp_umem_get_data(umem, handle); bi->addr += hr; - bi->handle = handle + umem->headroom; + bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom); xsk_umem_discard_addr(umem); return true; @@ -299,7 +309,7 @@ static bool i40e_alloc_buffer_slow_zc(struct i40e_ring *rx_ring, bi->addr = xdp_umem_get_data(umem, handle); bi->addr += hr; - bi->handle = handle + umem->headroom; + bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom); xsk_umem_discard_addr_rq(umem); return true; @@ -420,8 +430,6 @@ static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring, struct i40e_rx_buffer *old_bi) { struct i40e_rx_buffer *new_bi = &rx_ring->rx_bi[rx_ring->next_to_alloc]; - unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask; - u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM; u16 nta = rx_ring->next_to_alloc; /* update, and store next to alloc */ @@ -429,14 +437,9 @@ static void i40e_reuse_rx_buffer_zc(struct i40e_ring *rx_ring, rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; /* transfer page from old buffer to new buffer */ - new_bi->dma = old_bi->dma & mask; - new_bi->dma += hr; - - new_bi->addr = (void *)((unsigned long)old_bi->addr & mask); - new_bi->addr += hr; - - new_bi->handle = old_bi->handle & mask; - new_bi->handle += rx_ring->xsk_umem->headroom; + new_bi->dma = old_bi->dma; + new_bi->addr = old_bi->addr; + new_bi->handle = old_bi->handle; old_bi->addr = NULL; } @@ -471,7 +474,8 @@ void i40e_zca_free(struct zero_copy_allocator *alloc, unsigned long handle) bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle); bi->addr += hr; - bi->handle = (u64)handle + rx_ring->xsk_umem->headroom; + bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle, + rx_ring->xsk_umem->headroom); } /** @@ -626,6 +630,15 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget) i40e_finalize_xdp_rx(rx_ring, xdp_xmit); i40e_update_rx_stats(rx_ring, total_rx_bytes, total_rx_packets); + + if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) { + if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) + xsk_set_rx_need_wakeup(rx_ring->xsk_umem); + else + xsk_clear_rx_need_wakeup(rx_ring->xsk_umem); + + return (int)total_rx_packets; + } return failure ? budget : (int)total_rx_packets; } @@ -681,6 +694,8 @@ static bool i40e_xmit_zc(struct i40e_ring *xdp_ring, unsigned int budget) i40e_xdp_ring_update_tail(xdp_ring); xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) + xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); } return !!budget && work_done; @@ -759,19 +774,27 @@ bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, i40e_update_tx_stats(tx_ring, completed_frames, total_bytes); out_xmit: + if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) { + if (tx_ring->next_to_clean == tx_ring->next_to_use) + xsk_set_tx_need_wakeup(tx_ring->xsk_umem); + else + xsk_clear_tx_need_wakeup(tx_ring->xsk_umem); + } + xmit_done = i40e_xmit_zc(tx_ring, budget); return work_done && xmit_done; } /** - * i40e_xsk_async_xmit - Implements the ndo_xsk_async_xmit + * i40e_xsk_wakeup - Implements the ndo_xsk_wakeup * @dev: the netdevice * @queue_id: queue id to wake up + * @flags: ignored in our case since we have Rx and Tx in the same NAPI. * * Returns <0 for errors, 0 otherwise. **/ -int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id) +int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags) { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; diff --git a/drivers/net/ethernet/intel/i40e/i40e_xsk.h b/drivers/net/ethernet/intel/i40e/i40e_xsk.h index 8cc0a2e7d9a2..9ed59c14eb55 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_xsk.h +++ b/drivers/net/ethernet/intel/i40e/i40e_xsk.h @@ -18,6 +18,6 @@ int i40e_clean_rx_irq_zc(struct i40e_ring *rx_ring, int budget); bool i40e_clean_xdp_tx_irq(struct i40e_vsi *vsi, struct i40e_ring *tx_ring, int napi_budget); -int i40e_xsk_async_xmit(struct net_device *dev, u32 queue_id); +int i40e_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); #endif /* _I40E_XSK_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index 9fc635d816d2..29de3ae96ef2 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -253,7 +253,6 @@ struct iavf_adapter { #define IAVF_FLAG_RESET_PENDING BIT(4) #define IAVF_FLAG_RESET_NEEDED BIT(5) #define IAVF_FLAG_WB_ON_ITR_CAPABLE BIT(6) -#define IAVF_FLAG_ADDR_SET_BY_PF BIT(8) #define IAVF_FLAG_SERVICE_CLIENT_REQUESTED BIT(9) #define IAVF_FLAG_CLIENT_NEEDS_OPEN BIT(10) #define IAVF_FLAG_CLIENT_NEEDS_CLOSE BIT(11) diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index 9d2b50964a08..8f310e520b06 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -143,28 +143,6 @@ enum iavf_status iavf_free_virt_mem_d(struct iavf_hw *hw, } /** - * iavf_debug_d - OS dependent version of debug printing - * @hw: pointer to the HW structure - * @mask: debug level mask - * @fmt_str: printf-type format description - **/ -void iavf_debug_d(void *hw, u32 mask, char *fmt_str, ...) -{ - char buf[512]; - va_list argptr; - - if (!(mask & ((struct iavf_hw *)hw)->debug_mask)) - return; - - va_start(argptr, fmt_str); - vsnprintf(buf, sizeof(buf), fmt_str, argptr); - va_end(argptr); - - /* the debug string is already formatted with a newline */ - pr_info("%s", buf); -} - -/** * iavf_schedule_reset - Set the flags and schedule a reset event * @adapter: board private structure **/ @@ -812,9 +790,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p) if (ether_addr_equal(netdev->dev_addr, addr->sa_data)) return 0; - if (adapter->flags & IAVF_FLAG_ADDR_SET_BY_PF) - return -EPERM; - spin_lock_bh(&adapter->mac_vlan_list_lock); f = iavf_find_filter(adapter, hw->mac.addr); @@ -829,7 +804,6 @@ static int iavf_set_mac(struct net_device *netdev, void *p) if (f) { ether_addr_copy(hw->mac.addr, addr->sa_data); - ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); } return (f == NULL) ? -ENOMEM : 0; @@ -1833,7 +1807,6 @@ static int iavf_init_get_resources(struct iavf_adapter *adapter) eth_hw_addr_random(netdev); ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); } else { - adapter->flags |= IAVF_FLAG_ADDR_SET_BY_PF; ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); ether_addr_copy(netdev->perm_addr, adapter->hw.mac.addr); } diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.c b/drivers/net/ethernet/intel/iavf/iavf_txrx.c index 0cca1b589b56..7a30d5d5ef53 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.c +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.c @@ -2161,7 +2161,7 @@ static void iavf_create_tx_ctx(struct iavf_ring *tx_ring, **/ bool __iavf_chk_linearize(struct sk_buff *skb) { - const struct skb_frag_struct *frag, *stale; + const skb_frag_t *frag, *stale; int nr_frags, sum; /* no need to check if number of frags is less than 7 */ @@ -2205,7 +2205,7 @@ bool __iavf_chk_linearize(struct sk_buff *skb) * descriptor associated with the fragment. */ if (stale_size > IAVF_MAX_DATA_PER_TXD) { - int align_pad = -(stale->page_offset) & + int align_pad = -(skb_frag_off(stale)) & (IAVF_MAX_READ_REQ_SIZE - 1); sum -= align_pad; @@ -2269,7 +2269,7 @@ static inline void iavf_tx_map(struct iavf_ring *tx_ring, struct sk_buff *skb, { unsigned int data_len = skb->data_len; unsigned int size = skb_headlen(skb); - struct skb_frag_struct *frag; + skb_frag_t *frag; struct iavf_tx_buffer *tx_bi; struct iavf_tx_desc *tx_desc; u16 i = tx_ring->next_to_use; diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h index 71e7d090f8db..dd3348f9da9d 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h +++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h @@ -462,7 +462,7 @@ bool __iavf_chk_linearize(struct sk_buff *skb); **/ static inline int iavf_xmit_descriptor_count(struct sk_buff *skb) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; unsigned int nr_frags = skb_shinfo(skb)->nr_frags; int count = 0, size = skb_headlen(skb); diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index d49d58a6de80..c46770eba320 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1252,6 +1252,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, case VIRTCHNL_OP_ADD_ETH_ADDR: dev_err(&adapter->pdev->dev, "Failed to add MAC filter, error %s\n", iavf_stat_str(&adapter->hw, v_retval)); + /* restore administratively set MAC address */ + ether_addr_copy(adapter->hw.mac.addr, netdev->dev_addr); break; case VIRTCHNL_OP_DEL_VLAN: dev_err(&adapter->pdev->dev, "Failed to delete VLAN filter, error %s\n", @@ -1319,6 +1321,11 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, } } switch (v_opcode) { + case VIRTCHNL_OP_ADD_ETH_ADDR: { + if (!ether_addr_equal(netdev->dev_addr, adapter->hw.mac.addr)) + ether_addr_copy(netdev->dev_addr, adapter->hw.mac.addr); + } + break; case VIRTCHNL_OP_GET_STATS: { struct iavf_eth_stats *stats = (struct iavf_eth_stats *)msg; diff --git a/drivers/net/ethernet/intel/ice/Makefile b/drivers/net/ethernet/intel/ice/Makefile index 2d140ba83781..9edde960b4f2 100644 --- a/drivers/net/ethernet/intel/ice/Makefile +++ b/drivers/net/ethernet/intel/ice/Makefile @@ -15,6 +15,7 @@ ice-y := ice_main.o \ ice_sched.o \ ice_lib.o \ ice_txrx.o \ + ice_flex_pipe.o \ ice_ethtool.o ice-$(CONFIG_PCI_IOV) += ice_virtchnl_pf.o ice_sriov.o ice-$(CONFIG_DCB) += ice_dcb.o ice_dcb_lib.o diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h index 9ee6b55553c0..45e100666049 100644 --- a/drivers/net/ethernet/intel/ice/ice.h +++ b/drivers/net/ethernet/intel/ice/ice.h @@ -8,6 +8,7 @@ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/module.h> +#include <linux/firmware.h> #include <linux/netdevice.h> #include <linux/compiler.h> #include <linux/etherdevice.h> @@ -29,6 +30,7 @@ #include <linux/sctp.h> #include <linux/ipv6.h> #include <linux/if_bridge.h> +#include <linux/ctype.h> #include <linux/avf/virtchnl.h> #include <net/ipv6.h> #include "ice_devids.h" @@ -47,33 +49,16 @@ extern const char ice_drv_ver[]; #define ICE_MIN_NUM_DESC 64 #define ICE_MAX_NUM_DESC 8160 #define ICE_DFLT_MIN_RX_DESC 512 -/* if the default number of Rx descriptors between ICE_MAX_NUM_DESC and the - * number of descriptors to fill up an entire page is greater than or equal to - * ICE_DFLT_MIN_RX_DESC set it based on page size, otherwise set it to - * ICE_DFLT_MIN_RX_DESC - */ -#define ICE_DFLT_NUM_RX_DESC \ - min_t(u16, ICE_MAX_NUM_DESC, \ - max_t(u16, ALIGN(PAGE_SIZE / sizeof(union ice_32byte_rx_desc), \ - ICE_REQ_DESC_MULTIPLE), \ - ICE_DFLT_MIN_RX_DESC)) -/* set default number of Tx descriptors to the minimum between ICE_MAX_NUM_DESC - * and the number of descriptors to fill up an entire page - */ -#define ICE_DFLT_NUM_TX_DESC min_t(u16, ICE_MAX_NUM_DESC, \ - ALIGN(PAGE_SIZE / \ - sizeof(struct ice_tx_desc), \ - ICE_REQ_DESC_MULTIPLE)) +#define ICE_DFLT_NUM_TX_DESC 256 +#define ICE_DFLT_NUM_RX_DESC 2048 #define ICE_DFLT_TRAFFIC_CLASS BIT(0) #define ICE_INT_NAME_STR_LEN (IFNAMSIZ + 16) -#define ICE_ETHTOOL_FWVER_LEN 32 #define ICE_AQ_LEN 64 -#define ICE_MBXQ_LEN 64 +#define ICE_MBXSQ_LEN 64 +#define ICE_MBXRQ_LEN 512 #define ICE_MIN_MSIX 2 #define ICE_NO_VSI 0xffff -#define ICE_MAX_TXQS 2048 -#define ICE_MAX_RXQS 2048 #define ICE_VSI_MAP_CONTIG 0 #define ICE_VSI_MAP_SCATTER 1 #define ICE_MAX_SCATTER_TXQS 16 @@ -86,16 +71,6 @@ extern const char ice_drv_ver[]; #define ICE_RES_MISC_VEC_ID (ICE_RES_VALID_BIT - 1) #define ICE_INVAL_Q_INDEX 0xffff #define ICE_INVAL_VFID 256 -#define ICE_MAX_VF_COUNT 256 -#define ICE_MAX_QS_PER_VF 256 -#define ICE_MIN_QS_PER_VF 1 -#define ICE_DFLT_QS_PER_VF 4 -#define ICE_NONQ_VECS_VF 1 -#define ICE_MAX_SCATTER_QS_PER_VF 16 -#define ICE_MAX_BASE_QS_PER_VF 16 -#define ICE_MAX_INTR_PER_VF 65 -#define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) -#define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1) #define ICE_MAX_RESET_WAIT 20 @@ -220,6 +195,7 @@ enum ice_state { __ICE_CFG_BUSY, __ICE_SERVICE_SCHED, __ICE_SERVICE_DIS, + __ICE_OICR_INTR_DIS, /* Global OICR interrupt disabled */ __ICE_STATE_NBITS /* must be last */ }; @@ -257,9 +233,6 @@ struct ice_vsi { u16 vsi_num; /* HW (absolute) index of this VSI */ u16 idx; /* software index in pf->vsi[] */ - /* Interrupt thresholds */ - u16 work_lmt; - s16 vf_id; /* VF ID for SR-IOV VSIs */ u16 ethtype; /* Ethernet protocol for pause frame */ @@ -292,8 +265,8 @@ struct ice_vsi { /* queue information */ u8 tx_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ u8 rx_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */ - u16 txq_map[ICE_MAX_TXQS]; /* index in pf->avail_txqs */ - u16 rxq_map[ICE_MAX_RXQS]; /* index in pf->avail_rxqs */ + u16 *txq_map; /* index in pf->avail_txqs */ + u16 *rxq_map; /* index in pf->avail_rxqs */ u16 alloc_txq; /* Allocated Tx queues */ u16 num_txq; /* Used Tx queues */ u16 alloc_rxq; /* Allocated Rx queues */ @@ -329,15 +302,16 @@ struct ice_q_vector { } ____cacheline_internodealigned_in_smp; enum ice_pf_flags { - ICE_FLAG_MSIX_ENA, ICE_FLAG_FLTR_SYNC, ICE_FLAG_RSS_ENA, ICE_FLAG_SRIOV_ENA, ICE_FLAG_SRIOV_CAPABLE, ICE_FLAG_DCB_CAPABLE, ICE_FLAG_DCB_ENA, + ICE_FLAG_ADV_FEATURES, ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA, - ICE_FLAG_ENABLE_FW_LLDP, + ICE_FLAG_NO_MEDIA, + ICE_FLAG_FW_LLDP_AGENT, ICE_FLAG_ETHTOOL_CTXT, /* set when ethtool holds RTNL lock */ ICE_PF_FLAGS_NBITS /* must be last */ }; @@ -363,9 +337,9 @@ struct ice_pf { u16 num_vf_qps; /* num queue pairs per VF */ u16 num_vf_msix; /* num vectors per VF */ DECLARE_BITMAP(state, __ICE_STATE_NBITS); - DECLARE_BITMAP(avail_txqs, ICE_MAX_TXQS); - DECLARE_BITMAP(avail_rxqs, ICE_MAX_RXQS); DECLARE_BITMAP(flags, ICE_PF_FLAGS_NBITS); + unsigned long *avail_txqs; /* bitmap to track PF Tx queue usage */ + unsigned long *avail_rxqs; /* bitmap to track PF Rx queue usage */ unsigned long serv_tmr_period; unsigned long serv_tmr_prev; struct timer_list serv_tmr; @@ -376,11 +350,11 @@ struct ice_pf { u32 hw_csum_rx_error; u32 oicr_idx; /* Other interrupt cause MSIX vector index */ u32 num_avail_sw_msix; /* remaining MSIX SW vectors left unclaimed */ + u16 max_pf_txqs; /* Total Tx queues PF wide */ + u16 max_pf_rxqs; /* Total Rx queues PF wide */ 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 next_vsi; /* Next free slot in pf->vsi[] - 0-based! */ u16 num_alloc_vsi; u16 corer_count; /* Core reset count */ @@ -433,21 +407,26 @@ ice_irq_dynamic_ena(struct ice_hw *hw, struct ice_vsi *vsi, } /** - * ice_find_vsi_by_type - Find and return VSI of a given type - * @pf: PF to search for VSI - * @type: Value indicating type of VSI we are looking for + * ice_netdev_to_pf - Retrieve the PF struct associated with a netdev + * @netdev: pointer to the netdev struct */ -static inline struct ice_vsi * -ice_find_vsi_by_type(struct ice_pf *pf, enum ice_vsi_type type) +static inline struct ice_pf *ice_netdev_to_pf(struct net_device *netdev) { - int i; + struct ice_netdev_priv *np = netdev_priv(netdev); - for (i = 0; i < pf->num_alloc_vsi; i++) { - struct ice_vsi *vsi = pf->vsi[i]; + return np->vsi->back; +} - if (vsi && vsi->type == type) - return vsi; - } +/** + * ice_get_main_vsi - Get the PF VSI + * @pf: PF instance + * + * returns pf->vsi[0], which by definition is the PF VSI + */ +static inline struct ice_vsi *ice_get_main_vsi(struct ice_pf *pf) +{ + if (pf->vsi) + return pf->vsi[0]; return NULL; } @@ -455,6 +434,11 @@ ice_find_vsi_by_type(struct ice_pf *pf, enum ice_vsi_type type) int ice_vsi_setup_tx_rings(struct ice_vsi *vsi); int ice_vsi_setup_rx_rings(struct ice_vsi *vsi); void ice_set_ethtool_ops(struct net_device *netdev); +void ice_set_ethtool_safe_mode_ops(struct net_device *netdev); +u16 ice_get_avail_txq_count(struct ice_pf *pf); +u16 ice_get_avail_rxq_count(struct ice_pf *pf); +void ice_update_vsi_stats(struct ice_vsi *vsi); +void ice_update_pf_stats(struct ice_pf *pf); int ice_up(struct ice_vsi *vsi); int ice_down(struct ice_vsi *vsi); int ice_vsi_cfg(struct ice_vsi *vsi); diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h index 765e3c2ed045..023e3d2fee5f 100644 --- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h +++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h @@ -33,11 +33,22 @@ struct ice_aqc_get_ver { u8 api_patch; }; +/* Send driver version (indirect 0x0002) */ +struct ice_aqc_driver_ver { + u8 major_ver; + u8 minor_ver; + u8 build_ver; + u8 subbuild_ver; + u8 reserved[4]; + __le32 addr_high; + __le32 addr_low; +}; + /* Queue Shutdown (direct 0x0003) */ struct ice_aqc_q_shutdown { - __le32 driver_unloading; + u8 driver_unloading; #define ICE_AQC_DRIVER_UNLOADING BIT(0) - u8 reserved[12]; + u8 reserved[15]; }; /* Request resource ownership (direct 0x0008) @@ -91,6 +102,7 @@ struct ice_aqc_list_caps_elem { #define ICE_AQC_CAPS_SRIOV 0x0012 #define ICE_AQC_CAPS_VF 0x0013 #define ICE_AQC_CAPS_VSI 0x0017 +#define ICE_AQC_CAPS_DCB 0x0018 #define ICE_AQC_CAPS_RSS 0x0040 #define ICE_AQC_CAPS_RXQS 0x0041 #define ICE_AQC_CAPS_TXQS 0x0042 @@ -1518,6 +1530,56 @@ struct ice_aqc_get_clear_fw_log { __le32 addr_low; }; +/* Download Package (indirect 0x0C40) */ +/* Also used for Update Package (indirect 0x0C42) */ +struct ice_aqc_download_pkg { + u8 flags; +#define ICE_AQC_DOWNLOAD_PKG_LAST_BUF 0x01 + u8 reserved[3]; + __le32 reserved1; + __le32 addr_high; + __le32 addr_low; +}; + +struct ice_aqc_download_pkg_resp { + __le32 error_offset; + __le32 error_info; + __le32 addr_high; + __le32 addr_low; +}; + +/* Get Package Info List (indirect 0x0C43) */ +struct ice_aqc_get_pkg_info_list { + __le32 reserved1; + __le32 reserved2; + __le32 addr_high; + __le32 addr_low; +}; + +/* Version format for packages */ +struct ice_pkg_ver { + u8 major; + u8 minor; + u8 update; + u8 draft; +}; + +#define ICE_PKG_NAME_SIZE 32 + +struct ice_aqc_get_pkg_info { + struct ice_pkg_ver ver; + char name[ICE_PKG_NAME_SIZE]; + u8 is_in_nvm; + u8 is_active; + u8 is_active_at_boot; + u8 is_modified; +}; + +/* Get Package Info List response buffer format (0x0C43) */ +struct ice_aqc_get_pkg_info_resp { + __le32 count; + struct ice_aqc_get_pkg_info pkg_info[1]; +}; /** * struct ice_aq_desc - Admin Queue (AQ) descriptor * @flags: ICE_AQ_FLAG_* flags @@ -1546,6 +1608,7 @@ struct ice_aq_desc { u8 raw[16]; struct ice_aqc_generic generic; struct ice_aqc_get_ver get_ver; + struct ice_aqc_driver_ver driver_ver; struct ice_aqc_q_shutdown q_shutdown; struct ice_aqc_req_res res_owner; struct ice_aqc_manage_mac_read mac_read; @@ -1579,6 +1642,7 @@ struct ice_aq_desc { struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res; struct ice_aqc_fw_logging fw_logging; struct ice_aqc_get_clear_fw_log get_clear_fw_log; + struct ice_aqc_download_pkg download_pkg; struct ice_aqc_set_mac_lb set_mac_lb; struct ice_aqc_alloc_free_res_cmd sw_res_ctrl; struct ice_aqc_set_event_mask set_event_mask; @@ -1610,12 +1674,19 @@ enum ice_aq_err { ICE_AQ_RC_EBUSY = 12, /* Device or resource busy */ ICE_AQ_RC_EEXIST = 13, /* Object already exists */ ICE_AQ_RC_ENOSPC = 16, /* No space left or allocation failure */ + ICE_AQ_RC_ENOSYS = 17, /* Function not implemented */ + ICE_AQ_RC_ENOSEC = 24, /* Missing security manifest */ + ICE_AQ_RC_EBADSIG = 25, /* Bad RSA signature */ + ICE_AQ_RC_ESVN = 26, /* SVN number prohibits this package */ + ICE_AQ_RC_EBADMAN = 27, /* Manifest hash mismatch */ + ICE_AQ_RC_EBADBUF = 28, /* Buffer hash mismatches manifest */ }; /* Admin Queue command opcodes */ enum ice_adminq_opc { /* AQ commands */ ice_aqc_opc_get_ver = 0x0001, + ice_aqc_opc_driver_ver = 0x0002, ice_aqc_opc_q_shutdown = 0x0003, /* resource ownership */ @@ -1697,6 +1768,10 @@ enum ice_adminq_opc { ice_aqc_opc_add_txqs = 0x0C30, ice_aqc_opc_dis_txqs = 0x0C31, + /* package commands */ + ice_aqc_opc_download_pkg = 0x0C40, + ice_aqc_opc_get_pkg_info_list = 0x0C43, + /* debug commands */ ice_aqc_opc_fw_logging = 0xFF09, ice_aqc_opc_fw_logging_info = 0xFF10, diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c index 2e0731c1e1a3..3a6b3950eb0e 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.c +++ b/drivers/net/ethernet/intel/ice/ice_common.c @@ -263,21 +263,23 @@ enum ice_status ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, struct ice_link_status *link, struct ice_sq_cd *cd) { - struct ice_link_status *hw_link_info_old, *hw_link_info; struct ice_aqc_get_link_status_data link_data = { 0 }; struct ice_aqc_get_link_status *resp; + struct ice_link_status *li_old, *li; enum ice_media_type *hw_media_type; struct ice_fc_info *hw_fc_info; bool tx_pause, rx_pause; struct ice_aq_desc desc; enum ice_status status; + struct ice_hw *hw; u16 cmd_flags; if (!pi) return ICE_ERR_PARAM; - hw_link_info_old = &pi->phy.link_info_old; + hw = pi->hw; + li_old = &pi->phy.link_info_old; hw_media_type = &pi->phy.media_type; - hw_link_info = &pi->phy.link_info; + li = &pi->phy.link_info; hw_fc_info = &pi->fc; ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_status); @@ -286,27 +288,27 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, resp->cmd_flags = cpu_to_le16(cmd_flags); resp->lport_num = pi->lport; - status = ice_aq_send_cmd(pi->hw, &desc, &link_data, sizeof(link_data), - cd); + status = ice_aq_send_cmd(hw, &desc, &link_data, sizeof(link_data), cd); if (status) return status; /* save off old link status information */ - *hw_link_info_old = *hw_link_info; + *li_old = *li; /* update current link status information */ - hw_link_info->link_speed = le16_to_cpu(link_data.link_speed); - hw_link_info->phy_type_low = le64_to_cpu(link_data.phy_type_low); - hw_link_info->phy_type_high = le64_to_cpu(link_data.phy_type_high); + li->link_speed = le16_to_cpu(link_data.link_speed); + li->phy_type_low = le64_to_cpu(link_data.phy_type_low); + li->phy_type_high = le64_to_cpu(link_data.phy_type_high); *hw_media_type = ice_get_media_type(pi); - hw_link_info->link_info = link_data.link_info; - hw_link_info->an_info = link_data.an_info; - hw_link_info->ext_info = link_data.ext_info; - hw_link_info->max_frame_size = le16_to_cpu(link_data.max_frame_size); - hw_link_info->fec_info = link_data.cfg & ICE_AQ_FEC_MASK; - hw_link_info->topo_media_conflict = link_data.topo_media_conflict; - hw_link_info->pacing = link_data.cfg & ICE_AQ_CFG_PACING_M; + li->link_info = link_data.link_info; + li->an_info = link_data.an_info; + li->ext_info = link_data.ext_info; + li->max_frame_size = le16_to_cpu(link_data.max_frame_size); + li->fec_info = link_data.cfg & ICE_AQ_FEC_MASK; + li->topo_media_conflict = link_data.topo_media_conflict; + li->pacing = link_data.cfg & (ICE_AQ_CFG_PACING_M | + ICE_AQ_CFG_PACING_TYPE_M); /* update fc info */ tx_pause = !!(link_data.an_info & ICE_AQ_LINK_PAUSE_TX); @@ -320,12 +322,24 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse, else hw_fc_info->current_mode = ICE_FC_NONE; - hw_link_info->lse_ena = - !!(resp->cmd_flags & cpu_to_le16(ICE_AQ_LSE_IS_ENABLED)); + li->lse_ena = !!(resp->cmd_flags & cpu_to_le16(ICE_AQ_LSE_IS_ENABLED)); + + ice_debug(hw, ICE_DBG_LINK, "link_speed = 0x%x\n", li->link_speed); + ice_debug(hw, ICE_DBG_LINK, "phy_type_low = 0x%llx\n", + (unsigned long long)li->phy_type_low); + ice_debug(hw, ICE_DBG_LINK, "phy_type_high = 0x%llx\n", + (unsigned long long)li->phy_type_high); + ice_debug(hw, ICE_DBG_LINK, "media_type = 0x%x\n", *hw_media_type); + ice_debug(hw, ICE_DBG_LINK, "link_info = 0x%x\n", li->link_info); + ice_debug(hw, ICE_DBG_LINK, "an_info = 0x%x\n", li->an_info); + ice_debug(hw, ICE_DBG_LINK, "ext_info = 0x%x\n", li->ext_info); + ice_debug(hw, ICE_DBG_LINK, "lse_ena = 0x%x\n", li->lse_ena); + ice_debug(hw, ICE_DBG_LINK, "max_frame = 0x%x\n", li->max_frame_size); + ice_debug(hw, ICE_DBG_LINK, "pacing = 0x%x\n", li->pacing); /* save link status information */ if (link) - *link = *hw_link_info; + *link = *li; /* flag cleared so calling functions don't call AQ again */ pi->phy.get_link_info = false; @@ -715,6 +729,29 @@ static void ice_get_itr_intrl_gran(struct ice_hw *hw) } /** + * ice_get_nvm_version - get cached NVM version data + * @hw: pointer to the hardware structure + * @oem_ver: 8 bit NVM version + * @oem_build: 16 bit NVM build number + * @oem_patch: 8 NVM patch number + * @ver_hi: high 16 bits of the NVM version + * @ver_lo: low 16 bits of the NVM version + */ +void +ice_get_nvm_version(struct ice_hw *hw, u8 *oem_ver, u16 *oem_build, + u8 *oem_patch, u8 *ver_hi, u8 *ver_lo) +{ + struct ice_nvm_info *nvm = &hw->nvm; + + *oem_ver = (u8)((nvm->oem_ver & ICE_OEM_VER_MASK) >> ICE_OEM_VER_SHIFT); + *oem_patch = (u8)(nvm->oem_ver & ICE_OEM_VER_PATCH_MASK); + *oem_build = (u16)((nvm->oem_ver & ICE_OEM_VER_BUILD_MASK) >> + ICE_OEM_VER_BUILD_SHIFT); + *ver_hi = (nvm->ver & ICE_NVM_VER_HI_MASK) >> ICE_NVM_VER_HI_SHIFT; + *ver_lo = (nvm->ver & ICE_NVM_VER_LO_MASK) >> ICE_NVM_VER_LO_SHIFT; +} + +/** * ice_init_hw - main hardware initialization routine * @hw: pointer to the hardware structure */ @@ -740,7 +777,7 @@ enum ice_status ice_init_hw(struct ice_hw *hw) ice_get_itr_intrl_gran(hw); - status = ice_init_all_ctrlq(hw); + status = ice_create_all_ctrlq(hw); if (status) goto err_unroll_cqinit; @@ -845,7 +882,9 @@ enum ice_status ice_init_hw(struct ice_hw *hw) ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC); ice_init_flex_flds(hw, ICE_RXDID_FLEX_NIC_2); - + status = ice_init_hw_tbls(hw); + if (status) + goto err_unroll_fltr_mgmt_struct; return 0; err_unroll_fltr_mgmt_struct: @@ -855,7 +894,7 @@ err_unroll_sched: err_unroll_alloc: devm_kfree(ice_hw_to_dev(hw), hw->port_info); err_unroll_cqinit: - ice_shutdown_all_ctrlq(hw); + ice_destroy_all_ctrlq(hw); return status; } @@ -873,6 +912,8 @@ void ice_deinit_hw(struct ice_hw *hw) ice_sched_cleanup_all(hw); ice_sched_clear_agg(hw); + ice_free_seg(hw); + ice_free_hw_tbls(hw); if (hw->port_info) { devm_kfree(ice_hw_to_dev(hw), hw->port_info); @@ -881,7 +922,7 @@ void ice_deinit_hw(struct ice_hw *hw) /* Attempt to disable FW logging before shutting down control queues */ ice_cfg_fw_log(hw, false); - ice_shutdown_all_ctrlq(hw); + ice_destroy_all_ctrlq(hw); /* Clear VSI contexts if not already cleared */ ice_clear_all_vsi_ctx(hw); @@ -1078,6 +1119,7 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = { ICE_CTX_STORE(ice_rlan_ctx, tphdata_ena, 1, 195), ICE_CTX_STORE(ice_rlan_ctx, tphhead_ena, 1, 196), ICE_CTX_STORE(ice_rlan_ctx, lrxqthresh, 3, 198), + ICE_CTX_STORE(ice_rlan_ctx, prefena, 1, 201), { 0 } }; @@ -1088,7 +1130,8 @@ static const struct ice_ctx_ele ice_rlan_ctx_info[] = { * @rxq_index: the index of the Rx queue * * Converts rxq context from sparse to dense structure and then writes - * it to HW register space + * it to HW register space and enables the hardware to prefetch descriptors + * instead of only fetching them on demand */ enum ice_status ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, @@ -1096,6 +1139,11 @@ ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx, { u8 ctx_buf[ICE_RXQ_CTX_SZ] = { 0 }; + if (!rlan_ctx) + return ICE_ERR_BAD_PTR; + + rlan_ctx->prefena = 1; + ice_set_ctx((u8 *)rlan_ctx, ctx_buf, ice_rlan_ctx_info); return ice_copy_rxq_ctx_to_hw(hw, ctx_buf, rxq_index); } @@ -1111,6 +1159,7 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = { ICE_CTX_STORE(ice_tlan_ctx, vmvf_type, 2, 78), ICE_CTX_STORE(ice_tlan_ctx, src_vsi, 10, 80), ICE_CTX_STORE(ice_tlan_ctx, tsyn_ena, 1, 90), + ICE_CTX_STORE(ice_tlan_ctx, internal_usage_flag, 1, 91), ICE_CTX_STORE(ice_tlan_ctx, alt_vlan, 1, 92), ICE_CTX_STORE(ice_tlan_ctx, cpuid, 8, 93), ICE_CTX_STORE(ice_tlan_ctx, wb_mode, 1, 101), @@ -1129,7 +1178,7 @@ const struct ice_ctx_ele ice_tlan_ctx_info[] = { ICE_CTX_STORE(ice_tlan_ctx, drop_ena, 1, 165), ICE_CTX_STORE(ice_tlan_ctx, cache_prof_idx, 2, 166), ICE_CTX_STORE(ice_tlan_ctx, pkt_shaper_prof_idx, 3, 168), - ICE_CTX_STORE(ice_tlan_ctx, int_q_state, 110, 171), + ICE_CTX_STORE(ice_tlan_ctx, int_q_state, 122, 171), { 0 } }; @@ -1185,6 +1234,12 @@ ice_debug_cq(struct ice_hw *hw, u32 __maybe_unused mask, void *desc, void *buf, /* FW Admin Queue command wrappers */ +/* Software lock/mutex that is meant to be held while the Global Config Lock + * in firmware is acquired by the software to prevent most (but not all) types + * of AQ commands from being sent to FW + */ +DEFINE_MUTEX(ice_global_cfg_lock_sw); + /** * ice_aq_send_cmd - send FW Admin Queue command to FW Admin Queue * @hw: pointer to the HW struct @@ -1199,7 +1254,38 @@ enum ice_status ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, u16 buf_size, struct ice_sq_cd *cd) { - return ice_sq_send_cmd(hw, &hw->adminq, desc, buf, buf_size, cd); + struct ice_aqc_req_res *cmd = &desc->params.res_owner; + bool lock_acquired = false; + enum ice_status status; + + /* When a package download is in process (i.e. when the firmware's + * Global Configuration Lock resource is held), only the Download + * Package, Get Version, Get Package Info List and Release Resource + * (with resource ID set to Global Config Lock) AdminQ commands are + * allowed; all others must block until the package download completes + * and the Global Config Lock is released. See also + * ice_acquire_global_cfg_lock(). + */ + switch (le16_to_cpu(desc->opcode)) { + case ice_aqc_opc_download_pkg: + case ice_aqc_opc_get_pkg_info_list: + case ice_aqc_opc_get_ver: + break; + case ice_aqc_opc_release_res: + if (le16_to_cpu(cmd->res_id) == ICE_AQC_RES_ID_GLBL_LOCK) + break; + /* fall-through */ + default: + mutex_lock(&ice_global_cfg_lock_sw); + lock_acquired = true; + break; + } + + status = ice_sq_send_cmd(hw, &hw->adminq, desc, buf, buf_size, cd); + if (lock_acquired) + mutex_unlock(&ice_global_cfg_lock_sw); + + return status; } /** @@ -1237,6 +1323,43 @@ enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd) } /** + * ice_aq_send_driver_ver + * @hw: pointer to the HW struct + * @dv: driver's major, minor version + * @cd: pointer to command details structure or NULL + * + * Send the driver version (0x0002) to the firmware + */ +enum ice_status +ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv, + struct ice_sq_cd *cd) +{ + struct ice_aqc_driver_ver *cmd; + struct ice_aq_desc desc; + u16 len; + + cmd = &desc.params.driver_ver; + + if (!dv) + return ICE_ERR_PARAM; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_ver); + + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + cmd->major_ver = dv->major_ver; + cmd->minor_ver = dv->minor_ver; + cmd->build_ver = dv->build_ver; + cmd->subbuild_ver = dv->subbuild_ver; + + len = 0; + while (len < sizeof(dv->driver_string) && + isascii(dv->driver_string[len]) && dv->driver_string[len]) + len++; + + return ice_aq_send_cmd(hw, &desc, dv->driver_string, len, cd); +} + +/** * ice_aq_q_shutdown * @hw: pointer to the HW struct * @unloading: is the driver unloading itself @@ -1254,7 +1377,7 @@ enum ice_status ice_aq_q_shutdown(struct ice_hw *hw, bool unloading) ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_q_shutdown); if (unloading) - cmd->driver_unloading = cpu_to_le32(ICE_AQC_DRIVER_UNLOADING); + cmd->driver_unloading = ICE_AQC_DRIVER_UNLOADING; return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL); } @@ -1529,29 +1652,29 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, case ICE_AQC_CAPS_VALID_FUNCTIONS: caps->valid_functions = number; ice_debug(hw, ICE_DBG_INIT, - "%s: valid functions = %d\n", prefix, + "%s: valid_functions (bitmap) = %d\n", prefix, caps->valid_functions); break; case ICE_AQC_CAPS_SRIOV: caps->sr_iov_1_1 = (number == 1); ice_debug(hw, ICE_DBG_INIT, - "%s: SR-IOV = %d\n", prefix, + "%s: sr_iov_1_1 = %d\n", prefix, caps->sr_iov_1_1); break; case ICE_AQC_CAPS_VF: if (dev_p) { dev_p->num_vfs_exposed = number; ice_debug(hw, ICE_DBG_INIT, - "%s: VFs exposed = %d\n", prefix, + "%s: num_vfs_exposed = %d\n", prefix, dev_p->num_vfs_exposed); } else if (func_p) { func_p->num_allocd_vfs = number; func_p->vf_base_id = logical_id; ice_debug(hw, ICE_DBG_INIT, - "%s: VFs allocated = %d\n", prefix, + "%s: num_allocd_vfs = %d\n", prefix, func_p->num_allocd_vfs); ice_debug(hw, ICE_DBG_INIT, - "%s: VF base_id = %d\n", prefix, + "%s: vf_base_id = %d\n", prefix, func_p->vf_base_id); } break; @@ -1559,63 +1682,75 @@ ice_parse_caps(struct ice_hw *hw, void *buf, u32 cap_count, if (dev_p) { dev_p->num_vsi_allocd_to_host = number; ice_debug(hw, ICE_DBG_INIT, - "%s: num VSI alloc to host = %d\n", + "%s: num_vsi_allocd_to_host = %d\n", prefix, dev_p->num_vsi_allocd_to_host); } else if (func_p) { func_p->guar_num_vsi = ice_get_num_per_func(hw, ICE_MAX_VSI); ice_debug(hw, ICE_DBG_INIT, - "%s: num guaranteed VSI (fw) = %d\n", + "%s: guar_num_vsi (fw) = %d\n", prefix, number); ice_debug(hw, ICE_DBG_INIT, - "%s: num guaranteed VSI = %d\n", + "%s: guar_num_vsi = %d\n", prefix, func_p->guar_num_vsi); } break; + case ICE_AQC_CAPS_DCB: + caps->dcb = (number == 1); + caps->active_tc_bitmap = logical_id; + caps->maxtc = phys_id; + ice_debug(hw, ICE_DBG_INIT, + "%s: dcb = %d\n", prefix, caps->dcb); + ice_debug(hw, ICE_DBG_INIT, + "%s: active_tc_bitmap = %d\n", prefix, + caps->active_tc_bitmap); + ice_debug(hw, ICE_DBG_INIT, + "%s: maxtc = %d\n", prefix, caps->maxtc); + break; case ICE_AQC_CAPS_RSS: caps->rss_table_size = number; caps->rss_table_entry_width = logical_id; ice_debug(hw, ICE_DBG_INIT, - "%s: RSS table size = %d\n", prefix, + "%s: rss_table_size = %d\n", prefix, caps->rss_table_size); ice_debug(hw, ICE_DBG_INIT, - "%s: RSS table width = %d\n", prefix, + "%s: rss_table_entry_width = %d\n", prefix, caps->rss_table_entry_width); break; case ICE_AQC_CAPS_RXQS: caps->num_rxq = number; caps->rxq_first_id = phys_id; ice_debug(hw, ICE_DBG_INIT, - "%s: num Rx queues = %d\n", prefix, + "%s: num_rxq = %d\n", prefix, caps->num_rxq); ice_debug(hw, ICE_DBG_INIT, - "%s: Rx first queue ID = %d\n", prefix, + "%s: rxq_first_id = %d\n", prefix, caps->rxq_first_id); break; case ICE_AQC_CAPS_TXQS: caps->num_txq = number; caps->txq_first_id = phys_id; ice_debug(hw, ICE_DBG_INIT, - "%s: num Tx queues = %d\n", prefix, + "%s: num_txq = %d\n", prefix, caps->num_txq); ice_debug(hw, ICE_DBG_INIT, - "%s: Tx first queue ID = %d\n", prefix, + "%s: txq_first_id = %d\n", prefix, caps->txq_first_id); break; case ICE_AQC_CAPS_MSIX: caps->num_msix_vectors = number; caps->msix_vector_first_id = phys_id; ice_debug(hw, ICE_DBG_INIT, - "%s: MSIX vector count = %d\n", prefix, + "%s: num_msix_vectors = %d\n", prefix, caps->num_msix_vectors); ice_debug(hw, ICE_DBG_INIT, - "%s: MSIX first vector index = %d\n", prefix, + "%s: msix_vector_first_id = %d\n", prefix, caps->msix_vector_first_id); break; case ICE_AQC_CAPS_MAX_MTU: caps->max_mtu = number; - ice_debug(hw, ICE_DBG_INIT, "%s: max MTU = %d\n", + ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n", prefix, caps->max_mtu); break; default: @@ -1712,6 +1847,75 @@ ice_discover_caps(struct ice_hw *hw, enum ice_adminq_opc opc) } /** + * ice_set_safe_mode_caps - Override dev/func capabilities when in safe mode + * @hw: pointer to the hardware structure + */ +void ice_set_safe_mode_caps(struct ice_hw *hw) +{ + struct ice_hw_func_caps *func_caps = &hw->func_caps; + struct ice_hw_dev_caps *dev_caps = &hw->dev_caps; + u32 valid_func, rxq_first_id, txq_first_id; + u32 msix_vector_first_id, max_mtu; + u32 num_func = 0; + u8 i; + + /* cache some func_caps values that should be restored after memset */ + valid_func = func_caps->common_cap.valid_functions; + txq_first_id = func_caps->common_cap.txq_first_id; + rxq_first_id = func_caps->common_cap.rxq_first_id; + msix_vector_first_id = func_caps->common_cap.msix_vector_first_id; + max_mtu = func_caps->common_cap.max_mtu; + + /* unset func capabilities */ + memset(func_caps, 0, sizeof(*func_caps)); + + /* restore cached values */ + func_caps->common_cap.valid_functions = valid_func; + func_caps->common_cap.txq_first_id = txq_first_id; + func_caps->common_cap.rxq_first_id = rxq_first_id; + func_caps->common_cap.msix_vector_first_id = msix_vector_first_id; + func_caps->common_cap.max_mtu = max_mtu; + + /* one Tx and one Rx queue in safe mode */ + func_caps->common_cap.num_rxq = 1; + func_caps->common_cap.num_txq = 1; + + /* two MSIX vectors, one for traffic and one for misc causes */ + func_caps->common_cap.num_msix_vectors = 2; + func_caps->guar_num_vsi = 1; + + /* cache some dev_caps values that should be restored after memset */ + valid_func = dev_caps->common_cap.valid_functions; + txq_first_id = dev_caps->common_cap.txq_first_id; + rxq_first_id = dev_caps->common_cap.rxq_first_id; + msix_vector_first_id = dev_caps->common_cap.msix_vector_first_id; + max_mtu = dev_caps->common_cap.max_mtu; + + /* unset dev capabilities */ + memset(dev_caps, 0, sizeof(*dev_caps)); + + /* restore cached values */ + dev_caps->common_cap.valid_functions = valid_func; + dev_caps->common_cap.txq_first_id = txq_first_id; + dev_caps->common_cap.rxq_first_id = rxq_first_id; + dev_caps->common_cap.msix_vector_first_id = msix_vector_first_id; + dev_caps->common_cap.max_mtu = max_mtu; + + /* valid_func is a bitmap. get number of functions */ +#define ICE_MAX_FUNCS 8 + for (i = 0; i < ICE_MAX_FUNCS; i++) + if (valid_func & BIT(i)) + num_func++; + + /* one Tx and one Rx queue per function in safe mode */ + dev_caps->common_cap.num_rxq = num_func; + dev_caps->common_cap.num_txq = num_func; + + /* two MSIX vectors per function */ + dev_caps->common_cap.num_msix_vectors = 2 * num_func; +} + +/** * ice_get_caps - get info about the HW * @hw: pointer to the hardware structure */ @@ -1993,6 +2197,17 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, u8 lport, desc.params.set_phy.lport_num = lport; desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + ice_debug(hw, ICE_DBG_LINK, "phy_type_low = 0x%llx\n", + (unsigned long long)le64_to_cpu(cfg->phy_type_low)); + ice_debug(hw, ICE_DBG_LINK, "phy_type_high = 0x%llx\n", + (unsigned long long)le64_to_cpu(cfg->phy_type_high)); + ice_debug(hw, ICE_DBG_LINK, "caps = 0x%x\n", cfg->caps); + ice_debug(hw, ICE_DBG_LINK, "low_power_ctrl = 0x%x\n", + cfg->low_power_ctrl); + ice_debug(hw, ICE_DBG_LINK, "eee_cap = 0x%x\n", cfg->eee_cap); + ice_debug(hw, ICE_DBG_LINK, "eeer_value = 0x%x\n", cfg->eeer_value); + ice_debug(hw, ICE_DBG_LINK, "link_fec_opt = 0x%x\n", cfg->link_fec_opt); + return ice_aq_send_cmd(hw, &desc, cfg, sizeof(*cfg), cd); } @@ -2024,7 +2239,7 @@ enum ice_status ice_update_link_info(struct ice_port_info *pi) if (!pcaps) return ICE_ERR_NO_MEMORY; - status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_TOPO_CAP, pcaps, NULL); if (!status) memcpy(li->module_type, &pcaps->module_type, @@ -2174,27 +2389,24 @@ ice_cfg_phy_fec(struct ice_aqc_set_phy_cfg_data *cfg, enum ice_fec_mode fec) { switch (fec) { case ICE_FEC_BASER: - /* Clear auto FEC and RS bits, and AND BASE-R ability + /* Clear RS bits, and AND BASE-R ability * bits and OR request bits. */ - cfg->caps &= ~ICE_AQC_PHY_EN_AUTO_FEC; cfg->link_fec_opt &= ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN | ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN; cfg->link_fec_opt |= ICE_AQC_PHY_FEC_10G_KR_40G_KR4_REQ | ICE_AQC_PHY_FEC_25G_KR_REQ; break; case ICE_FEC_RS: - /* Clear auto FEC and BASE-R bits, and AND RS ability + /* Clear BASE-R bits, and AND RS ability * bits and OR request bits. */ - cfg->caps &= ~ICE_AQC_PHY_EN_AUTO_FEC; cfg->link_fec_opt &= ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN; cfg->link_fec_opt |= ICE_AQC_PHY_FEC_25G_RS_528_REQ | ICE_AQC_PHY_FEC_25G_RS_544_REQ; break; case ICE_FEC_NONE: - /* Clear auto FEC and all FEC option bits. */ - cfg->caps &= ~ICE_AQC_PHY_EN_AUTO_FEC; + /* Clear all FEC option bits. */ cfg->link_fec_opt &= ~ICE_AQC_PHY_FEC_MASK; break; case ICE_FEC_AUTO: @@ -3240,40 +3452,44 @@ void ice_replay_post(struct ice_hw *hw) /** * ice_stat_update40 - read 40 bit stat from the chip and update stat values * @hw: ptr to the hardware info - * @hireg: high 32 bit HW register to read from - * @loreg: low 32 bit HW register to read from + * @reg: offset of 64 bit HW register to read from * @prev_stat_loaded: bool to specify if previous stats are loaded * @prev_stat: ptr to previous loaded stat value * @cur_stat: ptr to current stat value */ void -ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg, - bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat) +ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, + u64 *prev_stat, u64 *cur_stat) { - u64 new_data; - - new_data = rd32(hw, loreg); - new_data |= ((u64)(rd32(hw, hireg) & 0xFFFF)) << 32; + u64 new_data = rd64(hw, reg) & (BIT_ULL(40) - 1); /* device stats are not reset at PFR, they likely will not be zeroed - * when the driver starts. So save the first values read and use them as - * offsets to be subtracted from the raw values in order to report stats - * that count from zero. + * when the driver starts. Thus, save the value from the first read + * without adding to the statistic value so that we report stats which + * count up from zero. */ - if (!prev_stat_loaded) + if (!prev_stat_loaded) { *prev_stat = new_data; + return; + } + + /* Calculate the difference between the new and old values, and then + * add it to the software stat value. + */ if (new_data >= *prev_stat) - *cur_stat = new_data - *prev_stat; + *cur_stat += new_data - *prev_stat; else /* to manage the potential roll-over */ - *cur_stat = (new_data + BIT_ULL(40)) - *prev_stat; - *cur_stat &= 0xFFFFFFFFFFULL; + *cur_stat += (new_data + BIT_ULL(40)) - *prev_stat; + + /* Update the previously stored value to prepare for next read */ + *prev_stat = new_data; } /** * ice_stat_update32 - read 32 bit stat from the chip and update stat values * @hw: ptr to the hardware info - * @reg: HW register to read from + * @reg: offset of HW register to read from * @prev_stat_loaded: bool to specify if previous stats are loaded * @prev_stat: ptr to previous loaded stat value * @cur_stat: ptr to current stat value @@ -3287,17 +3503,26 @@ ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, new_data = rd32(hw, reg); /* device stats are not reset at PFR, they likely will not be zeroed - * when the driver starts. So save the first values read and use them as - * offsets to be subtracted from the raw values in order to report stats - * that count from zero. + * when the driver starts. Thus, save the value from the first read + * without adding to the statistic value so that we report stats which + * count up from zero. */ - if (!prev_stat_loaded) + if (!prev_stat_loaded) { *prev_stat = new_data; + return; + } + + /* Calculate the difference between the new and old values, and then + * add it to the software stat value. + */ if (new_data >= *prev_stat) - *cur_stat = new_data - *prev_stat; + *cur_stat += new_data - *prev_stat; else /* to manage the potential roll-over */ - *cur_stat = (new_data + BIT_ULL(32)) - *prev_stat; + *cur_stat += (new_data + BIT_ULL(32)) - *prev_stat; + + /* Update the previously stored value to prepare for next read */ + *prev_stat = new_data; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h index d1f8353fe6bb..c3df92f57777 100644 --- a/drivers/net/ethernet/intel/ice/ice_common.h +++ b/drivers/net/ethernet/intel/ice/ice_common.h @@ -6,6 +6,7 @@ #include "ice.h" #include "ice_type.h" +#include "ice_flex_pipe.h" #include "ice_switch.h" #include <linux/avf/virtchnl.h> @@ -17,8 +18,10 @@ enum ice_status ice_init_hw(struct ice_hw *hw); void ice_deinit_hw(struct ice_hw *hw); enum ice_status ice_check_reset(struct ice_hw *hw); enum ice_status ice_reset(struct ice_hw *hw, enum ice_reset_req req); +enum ice_status ice_create_all_ctrlq(struct ice_hw *hw); enum ice_status ice_init_all_ctrlq(struct ice_hw *hw); void ice_shutdown_all_ctrlq(struct ice_hw *hw); +void ice_destroy_all_ctrlq(struct ice_hw *hw); enum ice_status ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq, struct ice_rq_event_info *e, u16 *pending); @@ -39,6 +42,8 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq, void ice_clear_pxe_mode(struct ice_hw *hw); enum ice_status ice_get_caps(struct ice_hw *hw); +void ice_set_safe_mode_caps(struct ice_hw *hw); + void ice_dev_onetime_setup(struct ice_hw *hw); enum ice_status @@ -64,12 +69,18 @@ void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode); extern const struct ice_ctx_ele ice_tlan_ctx_info[]; enum ice_status ice_set_ctx(u8 *src_ctx, u8 *dest_ctx, const struct ice_ctx_ele *ce_info); + +extern struct mutex ice_global_cfg_lock_sw; + enum ice_status ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf, u16 buf_size, struct ice_sq_cd *cd); enum ice_status ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd); enum ice_status +ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv, + struct ice_sq_cd *cd); +enum ice_status ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode, struct ice_aqc_get_phy_caps_data *caps, struct ice_sq_cd *cd); @@ -123,11 +134,14 @@ enum ice_status ice_replay_vsi(struct ice_hw *hw, u16 vsi_handle); void ice_replay_post(struct ice_hw *hw); void ice_output_fw_log(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf); void -ice_stat_update40(struct ice_hw *hw, u32 hireg, u32 loreg, - bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); +ice_stat_update40(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, + u64 *prev_stat, u64 *cur_stat); void ice_stat_update32(struct ice_hw *hw, u32 reg, bool prev_stat_loaded, u64 *prev_stat, u64 *cur_stat); +void +ice_get_nvm_version(struct ice_hw *hw, u8 *oem_ver, u16 *oem_build, + u8 *oem_patch, u8 *ver_hi, u8 *ver_lo); enum ice_status ice_sched_query_elem(struct ice_hw *hw, u32 node_teid, struct ice_aqc_get_elem *buf); diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c index e91ac4df0242..2353166c654e 100644 --- a/drivers/net/ethernet/intel/ice/ice_controlq.c +++ b/drivers/net/ethernet/intel/ice/ice_controlq.c @@ -310,7 +310,7 @@ ice_cfg_rq_regs(struct ice_hw *hw, struct ice_ctl_q_info *cq) * @cq: pointer to the specific Control queue * * This is the main initialization routine for the Control Send Queue - * Prior to calling this function, drivers *MUST* set the following fields + * Prior to calling this function, the driver *MUST* set the following fields * in the cq->structure: * - cq->num_sq_entries * - cq->sq_buf_size @@ -369,7 +369,7 @@ init_ctrlq_exit: * @cq: pointer to the specific Control queue * * The main initialization routine for the Admin Receive (Event) Queue. - * Prior to calling this function, drivers *MUST* set the following fields + * Prior to calling this function, the driver *MUST* set the following fields * in the cq->structure: * - cq->num_rq_entries * - cq->rq_buf_size @@ -569,14 +569,8 @@ static enum ice_status ice_init_check_adminq(struct ice_hw *hw) return 0; init_ctrlq_free_rq: - if (cq->rq.count) { - ice_shutdown_rq(hw, cq); - mutex_destroy(&cq->rq_lock); - } - if (cq->sq.count) { - ice_shutdown_sq(hw, cq); - mutex_destroy(&cq->sq_lock); - } + ice_shutdown_rq(hw, cq); + ice_shutdown_sq(hw, cq); return status; } @@ -585,12 +579,14 @@ init_ctrlq_free_rq: * @hw: pointer to the hardware structure * @q_type: specific Control queue type * - * Prior to calling this function, drivers *MUST* set the following fields + * Prior to calling this function, the driver *MUST* set the following fields * in the cq->structure: * - cq->num_sq_entries * - cq->num_rq_entries * - cq->rq_buf_size * - cq->sq_buf_size + * + * NOTE: this function does not initialize the controlq locks */ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) { @@ -616,8 +612,6 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) !cq->rq_buf_size || !cq->sq_buf_size) { return ICE_ERR_CFG; } - mutex_init(&cq->sq_lock); - mutex_init(&cq->rq_lock); /* setup SQ command write back timeout */ cq->sq_cmd_timeout = ICE_CTL_Q_SQ_CMD_TIMEOUT; @@ -625,7 +619,7 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) /* allocate the ATQ */ ret_code = ice_init_sq(hw, cq); if (ret_code) - goto init_ctrlq_destroy_locks; + return ret_code; /* allocate the ARQ */ ret_code = ice_init_rq(hw, cq); @@ -637,9 +631,6 @@ static enum ice_status ice_init_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) init_ctrlq_free_sq: ice_shutdown_sq(hw, cq); -init_ctrlq_destroy_locks: - mutex_destroy(&cq->sq_lock); - mutex_destroy(&cq->rq_lock); return ret_code; } @@ -647,12 +638,14 @@ init_ctrlq_destroy_locks: * ice_init_all_ctrlq - main initialization routine for all control queues * @hw: pointer to the hardware structure * - * Prior to calling this function, drivers *MUST* set the following fields + * Prior to calling this function, the driver MUST* set the following fields * in the cq->structure for all control queues: * - cq->num_sq_entries * - cq->num_rq_entries * - cq->rq_buf_size * - cq->sq_buf_size + * + * NOTE: this function does not initialize the controlq locks. */ enum ice_status ice_init_all_ctrlq(struct ice_hw *hw) { @@ -672,9 +665,47 @@ enum ice_status ice_init_all_ctrlq(struct ice_hw *hw) } /** + * ice_init_ctrlq_locks - Initialize locks for a control queue + * @cq: pointer to the control queue + * + * Initializes the send and receive queue locks for a given control queue. + */ +static void ice_init_ctrlq_locks(struct ice_ctl_q_info *cq) +{ + mutex_init(&cq->sq_lock); + mutex_init(&cq->rq_lock); +} + +/** + * ice_create_all_ctrlq - main initialization routine for all control queues + * @hw: pointer to the hardware structure + * + * Prior to calling this function, the driver *MUST* set the following fields + * in the cq->structure for all control queues: + * - cq->num_sq_entries + * - cq->num_rq_entries + * - cq->rq_buf_size + * - cq->sq_buf_size + * + * This function creates all the control queue locks and then calls + * ice_init_all_ctrlq. It should be called once during driver load. If the + * driver needs to re-initialize control queues at run time it should call + * ice_init_all_ctrlq instead. + */ +enum ice_status ice_create_all_ctrlq(struct ice_hw *hw) +{ + ice_init_ctrlq_locks(&hw->adminq); + ice_init_ctrlq_locks(&hw->mailboxq); + + return ice_init_all_ctrlq(hw); +} + +/** * ice_shutdown_ctrlq - shutdown routine for any control queue * @hw: pointer to the hardware structure * @q_type: specific Control queue type + * + * NOTE: this function does not destroy the control queue locks. */ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) { @@ -693,19 +724,17 @@ static void ice_shutdown_ctrlq(struct ice_hw *hw, enum ice_ctl_q q_type) return; } - if (cq->sq.count) { - ice_shutdown_sq(hw, cq); - mutex_destroy(&cq->sq_lock); - } - if (cq->rq.count) { - ice_shutdown_rq(hw, cq); - mutex_destroy(&cq->rq_lock); - } + ice_shutdown_sq(hw, cq); + ice_shutdown_rq(hw, cq); } /** * ice_shutdown_all_ctrlq - shutdown routine for all control queues * @hw: pointer to the hardware structure + * + * NOTE: this function does not destroy the control queue locks. The driver + * may call this at runtime to shutdown and later restart control queues, such + * as in response to a reset event. */ void ice_shutdown_all_ctrlq(struct ice_hw *hw) { @@ -716,6 +745,37 @@ void ice_shutdown_all_ctrlq(struct ice_hw *hw) } /** + * ice_destroy_ctrlq_locks - Destroy locks for a control queue + * @cq: pointer to the control queue + * + * Destroys the send and receive queue locks for a given control queue. + */ +static void +ice_destroy_ctrlq_locks(struct ice_ctl_q_info *cq) +{ + mutex_destroy(&cq->sq_lock); + mutex_destroy(&cq->rq_lock); +} + +/** + * ice_destroy_all_ctrlq - exit routine for all control queues + * @hw: pointer to the hardware structure + * + * This function shuts down all the control queues and then destroys the + * control queue locks. It should be called once during driver unload. The + * driver should call ice_shutdown_all_ctrlq if it needs to shut down and + * reinitialize control queues, such as in response to a reset event. + */ +void ice_destroy_all_ctrlq(struct ice_hw *hw) +{ + /* shut down all the control queues first */ + ice_shutdown_all_ctrlq(hw); + + ice_destroy_ctrlq_locks(&hw->adminq); + ice_destroy_ctrlq_locks(&hw->mailboxq); +} + +/** * ice_clean_sq - cleans Admin send queue (ATQ) * @hw: pointer to the hardware structure * @cq: pointer to the specific Control queue diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c index c2002ded65f6..dd7efff121bd 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb.c @@ -60,7 +60,7 @@ ice_aq_get_lldp_mib(struct ice_hw *hw, u8 bridge_type, u8 mib_type, void *buf, * Enable or Disable posting of an event on ARQ when LLDP MIB * associated with the interface changes (0x0A01) */ -enum ice_status +static enum ice_status ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update, struct ice_sq_cd *cd) { @@ -444,9 +444,15 @@ ice_parse_cee_pgcfg_tlv(struct ice_cee_feat_tlv *tlv, * |pg0|pg1|pg2|pg3|pg4|pg5|pg6|pg7| * --------------------------------- */ - ice_for_each_traffic_class(i) + ice_for_each_traffic_class(i) { etscfg->tcbwtable[i] = buf[offset++]; + if (etscfg->prio_table[i] == ICE_CEE_PGID_STRICT) + dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_STRICT; + else + dcbcfg->etscfg.tsatable[i] = ICE_IEEE_TSA_ETS; + } + /* Number of TCs supported (1 octet) */ etscfg->maxtcs = buf[offset]; } @@ -937,10 +943,11 @@ enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi) /** * ice_init_dcb * @hw: pointer to the HW struct + * @enable_mib_change: enable MIB change event * * Update DCB configuration from the Firmware */ -enum ice_status ice_init_dcb(struct ice_hw *hw) +enum ice_status ice_init_dcb(struct ice_hw *hw, bool enable_mib_change) { struct ice_port_info *pi = hw->port_info; enum ice_status ret = 0; @@ -954,7 +961,8 @@ enum ice_status ice_init_dcb(struct ice_hw *hw) pi->dcbx_status = ice_get_dcbx_status(hw); if (pi->dcbx_status == ICE_DCBX_STATUS_DONE || - pi->dcbx_status == ICE_DCBX_STATUS_IN_PROGRESS) { + pi->dcbx_status == ICE_DCBX_STATUS_IN_PROGRESS || + pi->dcbx_status == ICE_DCBX_STATUS_NOT_STARTED) { /* Get current DCBX configuration */ ret = ice_get_dcb_cfg(pi); pi->is_sw_lldp = (hw->adminq.sq_last_status == ICE_AQ_RC_EPERM); @@ -965,9 +973,39 @@ enum ice_status ice_init_dcb(struct ice_hw *hw) } /* Configure the LLDP MIB change event */ - ret = ice_aq_cfg_lldp_mib_change(hw, true, NULL); + if (enable_mib_change) { + ret = ice_aq_cfg_lldp_mib_change(hw, true, NULL); + if (!ret) + pi->is_sw_lldp = false; + } + + return ret; +} + +/** + * ice_cfg_lldp_mib_change + * @hw: pointer to the HW struct + * @ena_mib: enable/disable MIB change event + * + * Configure (disable/enable) MIB + */ +enum ice_status ice_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_mib) +{ + struct ice_port_info *pi = hw->port_info; + enum ice_status ret; + + if (!hw->func_caps.common_cap.dcb) + return ICE_ERR_NOT_SUPPORTED; + + /* Get DCBX status */ + pi->dcbx_status = ice_get_dcbx_status(hw); + + if (pi->dcbx_status == ICE_DCBX_STATUS_DIS) + return ICE_ERR_NOT_READY; + + ret = ice_aq_cfg_lldp_mib_change(hw, ena_mib, NULL); if (!ret) - pi->is_sw_lldp = false; + pi->is_sw_lldp = !ena_mib; return ret; } diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.h b/drivers/net/ethernet/intel/ice/ice_dcb.h index 522e1452abe2..ee138f9bdc7c 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb.h @@ -125,7 +125,7 @@ ice_aq_get_dcb_cfg(struct ice_hw *hw, u8 mib_type, u8 bridgetype, struct ice_dcbx_cfg *dcbcfg); enum ice_status ice_get_dcb_cfg(struct ice_port_info *pi); enum ice_status ice_set_dcb_cfg(struct ice_port_info *pi); -enum ice_status ice_init_dcb(struct ice_hw *hw); +enum ice_status ice_init_dcb(struct ice_hw *hw, bool enable_mib_change); enum ice_status ice_query_port_ets(struct ice_port_info *pi, struct ice_aqc_port_ets_elem *buf, u16 buf_size, @@ -139,9 +139,7 @@ ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd); enum ice_status ice_aq_start_stop_dcbx(struct ice_hw *hw, bool start_dcbx_agent, bool *dcbx_agent_status, struct ice_sq_cd *cd); -enum ice_status -ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update, - struct ice_sq_cd *cd); +enum ice_status ice_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_mib); #else /* CONFIG_DCB */ static inline enum ice_status ice_aq_stop_lldp(struct ice_hw __always_unused *hw, @@ -172,9 +170,8 @@ ice_aq_start_stop_dcbx(struct ice_hw __always_unused *hw, } static inline enum ice_status -ice_aq_cfg_lldp_mib_change(struct ice_hw __always_unused *hw, - bool __always_unused ena_update, - struct ice_sq_cd __always_unused *cd) +ice_cfg_lldp_mib_change(struct ice_hw __always_unused *hw, + bool __always_unused ena_mib) { return 0; } diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c index fe88b127ca42..dd47869c4ad4 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c @@ -4,6 +4,48 @@ #include "ice_dcb_lib.h" /** + * ice_vsi_cfg_netdev_tc - Setup the netdev TC configuration + * @vsi: the VSI being configured + * @ena_tc: TC map to be enabled + */ +void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc) +{ + struct net_device *netdev = vsi->netdev; + struct ice_pf *pf = vsi->back; + struct ice_dcbx_cfg *dcbcfg; + u8 netdev_tc; + int i; + + if (!netdev) + return; + + if (!ena_tc) { + netdev_reset_tc(netdev); + return; + } + + if (netdev_set_num_tc(netdev, vsi->tc_cfg.numtc)) + return; + + dcbcfg = &pf->hw.port_info->local_dcbx_cfg; + + ice_for_each_traffic_class(i) + if (vsi->tc_cfg.ena_tc & BIT(i)) + netdev_set_tc_queue(netdev, + vsi->tc_cfg.tc_info[i].netdev_tc, + vsi->tc_cfg.tc_info[i].qcount_tx, + vsi->tc_cfg.tc_info[i].qoffset); + + for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) { + u8 ets_tc = dcbcfg->etscfg.prio_table[i]; + + /* Get the mapped netdev TC# for the UP */ + netdev_tc = vsi->tc_cfg.tc_info[ets_tc].netdev_tc; + netdev_set_prio_tc_map(netdev, i, netdev_tc); + } +} + +/** * ice_dcb_get_ena_tc - return bitmap of enabled TCs * @dcbcfg: DCB config to evaluate for enabled TCs */ @@ -204,15 +246,86 @@ out: } /** + * ice_cfg_etsrec_defaults - Set default ETS recommended DCB config + * @pi: port information structure + */ +static void ice_cfg_etsrec_defaults(struct ice_port_info *pi) +{ + struct ice_dcbx_cfg *dcbcfg = &pi->local_dcbx_cfg; + u8 i; + + /* Ensure ETS recommended DCB configuration is not already set */ + if (dcbcfg->etsrec.maxtcs) + return; + + /* In CEE mode, set the default to 1 TC */ + dcbcfg->etsrec.maxtcs = 1; + for (i = 0; i < ICE_MAX_TRAFFIC_CLASS; i++) { + dcbcfg->etsrec.tcbwtable[i] = i ? 0 : 100; + dcbcfg->etsrec.tsatable[i] = i ? ICE_IEEE_TSA_STRICT : + ICE_IEEE_TSA_ETS; + } +} + +/** + * ice_dcb_need_recfg - Check if DCB needs reconfig + * @pf: board private structure + * @old_cfg: current DCB config + * @new_cfg: new DCB config + */ +static bool +ice_dcb_need_recfg(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg, + struct ice_dcbx_cfg *new_cfg) +{ + bool need_reconfig = false; + + /* Check if ETS configuration has changed */ + if (memcmp(&new_cfg->etscfg, &old_cfg->etscfg, + sizeof(new_cfg->etscfg))) { + /* If Priority Table has changed reconfig is needed */ + if (memcmp(&new_cfg->etscfg.prio_table, + &old_cfg->etscfg.prio_table, + sizeof(new_cfg->etscfg.prio_table))) { + need_reconfig = true; + dev_dbg(&pf->pdev->dev, "ETS UP2TC changed.\n"); + } + + if (memcmp(&new_cfg->etscfg.tcbwtable, + &old_cfg->etscfg.tcbwtable, + sizeof(new_cfg->etscfg.tcbwtable))) + dev_dbg(&pf->pdev->dev, "ETS TC BW Table changed.\n"); + + if (memcmp(&new_cfg->etscfg.tsatable, + &old_cfg->etscfg.tsatable, + sizeof(new_cfg->etscfg.tsatable))) + dev_dbg(&pf->pdev->dev, "ETS TSA Table changed.\n"); + } + + /* Check if PFC configuration has changed */ + if (memcmp(&new_cfg->pfc, &old_cfg->pfc, sizeof(new_cfg->pfc))) { + need_reconfig = true; + dev_dbg(&pf->pdev->dev, "PFC config change detected.\n"); + } + + /* Check if APP Table has changed */ + if (memcmp(&new_cfg->app, &old_cfg->app, sizeof(new_cfg->app))) { + need_reconfig = true; + dev_dbg(&pf->pdev->dev, "APP Table change detected.\n"); + } + + dev_dbg(&pf->pdev->dev, "dcb need_reconfig=%d\n", need_reconfig); + return need_reconfig; +} + +/** * ice_dcb_rebuild - rebuild DCB post reset * @pf: physical function instance */ void ice_dcb_rebuild(struct ice_pf *pf) { + struct ice_dcbx_cfg *local_dcbx_cfg, *desired_dcbx_cfg, *prev_cfg; struct ice_aqc_port_ets_elem buf = { 0 }; - struct ice_dcbx_cfg *prev_cfg; enum ice_status ret; - u8 willing; ret = ice_query_port_ets(pf->hw.port_info, &buf, sizeof(buf), NULL); if (ret) { @@ -224,9 +337,15 @@ void ice_dcb_rebuild(struct ice_pf *pf) if (!test_bit(ICE_FLAG_DCB_ENA, pf->flags)) return; + local_dcbx_cfg = &pf->hw.port_info->local_dcbx_cfg; + desired_dcbx_cfg = &pf->hw.port_info->desired_dcbx_cfg; + /* Save current willing state and force FW to unwilling */ - willing = pf->hw.port_info->local_dcbx_cfg.etscfg.willing; - pf->hw.port_info->local_dcbx_cfg.etscfg.willing = 0x0; + local_dcbx_cfg->etscfg.willing = 0x0; + local_dcbx_cfg->pfc.willing = 0x0; + local_dcbx_cfg->app_mode = ICE_DCBX_APPS_NON_WILLING; + + ice_cfg_etsrec_defaults(pf->hw.port_info); ret = ice_set_dcb_cfg(pf->hw.port_info); if (ret) { dev_err(&pf->pdev->dev, "Failed to set DCB to unwilling\n"); @@ -234,31 +353,37 @@ void ice_dcb_rebuild(struct ice_pf *pf) } /* Retrieve DCB config and ensure same as current in SW */ - prev_cfg = devm_kmemdup(&pf->pdev->dev, - &pf->hw.port_info->local_dcbx_cfg, + prev_cfg = devm_kmemdup(&pf->pdev->dev, local_dcbx_cfg, sizeof(*prev_cfg), GFP_KERNEL); if (!prev_cfg) { dev_err(&pf->pdev->dev, "Failed to alloc space for DCB cfg\n"); goto dcb_error; } - ice_init_dcb(&pf->hw); - if (memcmp(prev_cfg, &pf->hw.port_info->local_dcbx_cfg, - sizeof(*prev_cfg))) { + ice_init_dcb(&pf->hw, true); + if (pf->hw.port_info->dcbx_status == ICE_DCBX_STATUS_DIS) + pf->hw.port_info->is_sw_lldp = true; + else + pf->hw.port_info->is_sw_lldp = false; + + if (ice_dcb_need_recfg(pf, prev_cfg, local_dcbx_cfg)) { /* difference in cfg detected - disable DCB till next MIB */ dev_err(&pf->pdev->dev, "Set local MIB not accurate\n"); - devm_kfree(&pf->pdev->dev, prev_cfg); goto dcb_error; } /* fetched config congruent to previous configuration */ devm_kfree(&pf->pdev->dev, prev_cfg); - /* Configuration replayed - reset willing state to previous */ - pf->hw.port_info->local_dcbx_cfg.etscfg.willing = willing; + /* Set the local desired config */ + if (local_dcbx_cfg->dcbx_mode == ICE_DCBX_MODE_CEE) + memcpy(local_dcbx_cfg, desired_dcbx_cfg, + sizeof(*local_dcbx_cfg)); + + ice_cfg_etsrec_defaults(pf->hw.port_info); ret = ice_set_dcb_cfg(pf->hw.port_info); if (ret) { - dev_err(&pf->pdev->dev, "Fail restoring prev willing state\n"); + dev_err(&pf->pdev->dev, "Failed to set desired config\n"); goto dcb_error; } dev_info(&pf->pdev->dev, "DCB restored after reset\n"); @@ -330,7 +455,7 @@ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool locked) memset(&pi->local_dcbx_cfg, 0, sizeof(*dcbcfg)); dcbcfg->etscfg.willing = 1; - dcbcfg->etscfg.maxtcs = 8; + dcbcfg->etscfg.maxtcs = hw->func_caps.common_cap.maxtc; dcbcfg->etscfg.tcbwtable[0] = 100; dcbcfg->etscfg.tsatable[0] = ICE_IEEE_TSA_ETS; @@ -339,7 +464,7 @@ static int ice_dcb_sw_dflt_cfg(struct ice_pf *pf, bool locked) dcbcfg->etsrec.willing = 0; dcbcfg->pfc.willing = 1; - dcbcfg->pfc.pfccap = IEEE_8021QAZ_MAX_TCS; + dcbcfg->pfc.pfccap = hw->func_caps.common_cap.maxtc; dcbcfg->numapps = 1; dcbcfg->app[0].selector = ICE_APP_SEL_ETHTYPE; @@ -364,35 +489,24 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) struct device *dev = &pf->pdev->dev; struct ice_port_info *port_info; struct ice_hw *hw = &pf->hw; - int sw_default = 0; int err; port_info = hw->port_info; - err = ice_init_dcb(hw); - if (err) { - /* FW LLDP is not active, default to SW DCBX/LLDP */ - dev_info(&pf->pdev->dev, "FW LLDP is not active\n"); - hw->port_info->dcbx_status = ICE_DCBX_STATUS_NOT_STARTED; - hw->port_info->is_sw_lldp = true; - } - - if (port_info->dcbx_status == ICE_DCBX_STATUS_DIS) - dev_info(&pf->pdev->dev, "DCBX disabled\n"); - - /* LLDP disabled in FW */ - if (port_info->is_sw_lldp) { - sw_default = 1; - dev_info(&pf->pdev->dev, "DCBx/LLDP in SW mode.\n"); - clear_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags); - } else { - set_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags); + err = ice_init_dcb(hw, false); + if (err && !port_info->is_sw_lldp) { + dev_err(&pf->pdev->dev, "Error initializing DCB %d\n", err); + goto dcb_init_err; } - if (port_info->dcbx_status == ICE_DCBX_STATUS_NOT_STARTED) - dev_info(&pf->pdev->dev, "DCBX not started\n"); - - if (sw_default) { + dev_info(&pf->pdev->dev, + "DCB is enabled in the hardware, max number of TCs supported on this port are %d\n", + pf->hw.func_caps.common_cap.maxtc); + if (err) { + /* FW LLDP is disabled, activate SW DCBX/LLDP mode */ + dev_info(&pf->pdev->dev, + "FW LLDP is disabled, DCBx/LLDP in SW mode.\n"); + clear_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags); err = ice_dcb_sw_dflt_cfg(pf, locked); if (err) { dev_err(&pf->pdev->dev, @@ -402,21 +516,18 @@ int ice_init_pf_dcb(struct ice_pf *pf, bool locked) } pf->dcbx_cap = DCB_CAP_DCBX_HOST | DCB_CAP_DCBX_VER_IEEE; - set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); - set_bit(ICE_FLAG_DCB_ENA, pf->flags); return 0; } + set_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags); + /* DCBX in FW and LLDP enabled in FW */ pf->dcbx_cap = DCB_CAP_DCBX_LLD_MANAGED | DCB_CAP_DCBX_VER_IEEE; - set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); - err = ice_dcb_init_cfg(pf, locked); if (err) goto dcb_init_err; - dev_info(&pf->pdev->dev, "DCBX offload supported\n"); return err; dcb_init_err: @@ -432,30 +543,31 @@ void ice_update_dcb_stats(struct ice_pf *pf) { struct ice_hw_port_stats *prev_ps, *cur_ps; struct ice_hw *hw = &pf->hw; - u8 pf_id = hw->pf_id; + u8 port; int i; + port = hw->port_info->lport; prev_ps = &pf->stats_prev; cur_ps = &pf->stats; for (i = 0; i < 8; i++) { - ice_stat_update32(hw, GLPRT_PXOFFRXC(pf_id, i), + ice_stat_update32(hw, GLPRT_PXOFFRXC(port, i), pf->stat_prev_loaded, &prev_ps->priority_xoff_rx[i], &cur_ps->priority_xoff_rx[i]); - ice_stat_update32(hw, GLPRT_PXONRXC(pf_id, i), + ice_stat_update32(hw, GLPRT_PXONRXC(port, i), pf->stat_prev_loaded, &prev_ps->priority_xon_rx[i], &cur_ps->priority_xon_rx[i]); - ice_stat_update32(hw, GLPRT_PXONTXC(pf_id, i), + ice_stat_update32(hw, GLPRT_PXONTXC(port, i), pf->stat_prev_loaded, &prev_ps->priority_xon_tx[i], &cur_ps->priority_xon_tx[i]); - ice_stat_update32(hw, GLPRT_PXOFFTXC(pf_id, i), + ice_stat_update32(hw, GLPRT_PXOFFTXC(port, i), pf->stat_prev_loaded, &prev_ps->priority_xoff_tx[i], &cur_ps->priority_xoff_tx[i]); - ice_stat_update32(hw, GLPRT_RXON2OFFCNT(pf_id, i), + ice_stat_update32(hw, GLPRT_RXON2OFFCNT(port, i), pf->stat_prev_loaded, &prev_ps->priority_xon_2_xoff[i], &cur_ps->priority_xon_2_xoff[i]); @@ -502,55 +614,6 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring, } /** - * ice_dcb_need_recfg - Check if DCB needs reconfig - * @pf: board private structure - * @old_cfg: current DCB config - * @new_cfg: new DCB config - */ -static bool ice_dcb_need_recfg(struct ice_pf *pf, struct ice_dcbx_cfg *old_cfg, - struct ice_dcbx_cfg *new_cfg) -{ - bool need_reconfig = false; - - /* Check if ETS configuration has changed */ - if (memcmp(&new_cfg->etscfg, &old_cfg->etscfg, - sizeof(new_cfg->etscfg))) { - /* If Priority Table has changed reconfig is needed */ - if (memcmp(&new_cfg->etscfg.prio_table, - &old_cfg->etscfg.prio_table, - sizeof(new_cfg->etscfg.prio_table))) { - need_reconfig = true; - dev_dbg(&pf->pdev->dev, "ETS UP2TC changed.\n"); - } - - if (memcmp(&new_cfg->etscfg.tcbwtable, - &old_cfg->etscfg.tcbwtable, - sizeof(new_cfg->etscfg.tcbwtable))) - dev_dbg(&pf->pdev->dev, "ETS TC BW Table changed.\n"); - - if (memcmp(&new_cfg->etscfg.tsatable, - &old_cfg->etscfg.tsatable, - sizeof(new_cfg->etscfg.tsatable))) - dev_dbg(&pf->pdev->dev, "ETS TSA Table changed.\n"); - } - - /* Check if PFC configuration has changed */ - if (memcmp(&new_cfg->pfc, &old_cfg->pfc, sizeof(new_cfg->pfc))) { - need_reconfig = true; - dev_dbg(&pf->pdev->dev, "PFC config change detected.\n"); - } - - /* Check if APP Table has changed */ - if (memcmp(&new_cfg->app, &old_cfg->app, sizeof(new_cfg->app))) { - need_reconfig = true; - dev_dbg(&pf->pdev->dev, "APP Table change detected.\n"); - } - - dev_dbg(&pf->pdev->dev, "dcb need_reconfig=%d\n", need_reconfig); - return need_reconfig; -} - -/** * ice_dcb_process_lldp_set_mib_change - Process MIB change * @pf: ptr to ice_pf * @event: pointer to the admin queue receive event diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h index 819081053ff5..661a6f7bca64 100644 --- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.h @@ -22,6 +22,7 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_ring *tx_ring, void ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf, struct ice_rq_event_info *event); +void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc); static inline void ice_set_cgd_num(struct ice_tlan_ctx *tlan_ctx, struct ice_ring *ring) { @@ -58,5 +59,6 @@ ice_tx_prepare_vlan_flags_dcb(struct ice_ring __always_unused *tx_ring, #define ice_vsi_cfg_dcb_rings(vsi) do {} while (0) #define ice_dcb_process_lldp_set_mib_change(pf, event) do {} while (0) #define ice_set_cgd_num(tlan_ctx, ring) do {} while (0) +#define ice_vsi_cfg_netdev_tc(vsi, ena_tc) do {} while (0) #endif /* CONFIG_DCB */ #endif /* _ICE_DCB_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 52083a63dee6..7e23034df955 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -155,36 +155,11 @@ struct ice_priv_flag { static const struct ice_priv_flag ice_gstrings_priv_flags[] = { ICE_PRIV_FLAG("link-down-on-close", ICE_FLAG_LINK_DOWN_ON_CLOSE_ENA), - ICE_PRIV_FLAG("enable-fw-lldp", ICE_FLAG_ENABLE_FW_LLDP), + ICE_PRIV_FLAG("fw-lldp-agent", ICE_FLAG_FW_LLDP_AGENT), }; #define ICE_PRIV_FLAG_ARRAY_SIZE ARRAY_SIZE(ice_gstrings_priv_flags) -/** - * ice_nvm_version_str - format the NVM version strings - * @hw: ptr to the hardware info - */ -static char *ice_nvm_version_str(struct ice_hw *hw) -{ - static char buf[ICE_ETHTOOL_FWVER_LEN]; - u8 ver, patch; - u32 full_ver; - u16 build; - - full_ver = hw->nvm.oem_ver; - ver = (u8)((full_ver & ICE_OEM_VER_MASK) >> ICE_OEM_VER_SHIFT); - build = (u16)((full_ver & ICE_OEM_VER_BUILD_MASK) >> - ICE_OEM_VER_BUILD_SHIFT); - patch = (u8)(full_ver & ICE_OEM_VER_PATCH_MASK); - - snprintf(buf, sizeof(buf), "%x.%02x 0x%x %d.%d.%d", - (hw->nvm.ver & ICE_NVM_VER_HI_MASK) >> ICE_NVM_VER_HI_SHIFT, - (hw->nvm.ver & ICE_NVM_VER_LO_MASK) >> ICE_NVM_VER_LO_SHIFT, - hw->nvm.eetrack, ver, build, patch); - - return buf; -} - static void ice_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { @@ -1201,13 +1176,13 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) bitmap_xor(change_flags, pf->flags, orig_flags, ICE_PF_FLAGS_NBITS); - if (test_bit(ICE_FLAG_ENABLE_FW_LLDP, change_flags)) { - if (!test_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags)) { + if (test_bit(ICE_FLAG_FW_LLDP_AGENT, change_flags)) { + if (!test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) { enum ice_status status; /* Disable FW LLDP engine */ - status = ice_aq_cfg_lldp_mib_change(&pf->hw, false, - NULL); + status = ice_cfg_lldp_mib_change(&pf->hw, false); + /* If unregistering for LLDP events fails, this is * not an error state, as there shouldn't be any * events to respond to. @@ -1273,6 +1248,12 @@ static int ice_set_priv_flags(struct net_device *netdev, u32 flags) * The FW LLDP engine will now be consuming them. */ ice_cfg_sw_lldp(vsi, false, false); + + /* Register for MIB change events */ + status = ice_cfg_lldp_mib_change(&pf->hw, true); + if (status) + dev_dbg(&pf->pdev->dev, + "Fail to enable MIB change events\n"); } } clear_bit(ICE_FLAG_ETHTOOL_CTXT, pf->flags); @@ -1319,14 +1300,17 @@ ice_get_ethtool_stats(struct net_device *netdev, struct ice_vsi *vsi = np->vsi; struct ice_pf *pf = vsi->back; struct ice_ring *ring; - unsigned int j = 0; + unsigned int j; int i = 0; char *p; + ice_update_pf_stats(pf); + ice_update_vsi_stats(vsi); + for (j = 0; j < ICE_VSI_STATS_LEN; j++) { p = (char *)vsi + ice_gstrings_vsi_stats[j].stat_offset; data[i++] = (ice_gstrings_vsi_stats[j].sizeof_stat == - sizeof(u64)) ? *(u64 *)p : *(u32 *)p; + sizeof(u64)) ? *(u64 *)p : *(u32 *)p; } /* populate per queue stats */ @@ -1716,6 +1700,7 @@ ice_get_settings_link_up(struct ethtool_link_ksettings *ks, struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_port_info *pi = np->vsi->port_info; struct ethtool_link_ksettings cap_ksettings; struct ice_link_status *link_info; struct ice_vsi *vsi = np->vsi; @@ -2040,6 +2025,33 @@ ice_get_settings_link_up(struct ethtool_link_ksettings *ks, break; } ks->base.duplex = DUPLEX_FULL; + + if (link_info->an_info & ICE_AQ_AN_COMPLETED) + ethtool_link_ksettings_add_link_mode(ks, lp_advertising, + Autoneg); + + /* Set flow control negotiated Rx/Tx pause */ + switch (pi->fc.current_mode) { + case ICE_FC_FULL: + ethtool_link_ksettings_add_link_mode(ks, lp_advertising, Pause); + break; + case ICE_FC_TX_PAUSE: + ethtool_link_ksettings_add_link_mode(ks, lp_advertising, Pause); + ethtool_link_ksettings_add_link_mode(ks, lp_advertising, + Asym_Pause); + break; + case ICE_FC_RX_PAUSE: + ethtool_link_ksettings_add_link_mode(ks, lp_advertising, + Asym_Pause); + break; + case ICE_FC_PFC: + /* fall through */ + default: + ethtool_link_ksettings_del_link_mode(ks, lp_advertising, Pause); + ethtool_link_ksettings_del_link_mode(ks, lp_advertising, + Asym_Pause); + break; + } } /** @@ -2078,9 +2090,12 @@ ice_get_link_ksettings(struct net_device *netdev, struct ice_aqc_get_phy_caps_data *caps; struct ice_link_status *hw_link_info; struct ice_vsi *vsi = np->vsi; + enum ice_status status; + int err = 0; ethtool_link_ksettings_zero_link_mode(ks, supported); ethtool_link_ksettings_zero_link_mode(ks, advertising); + ethtool_link_ksettings_zero_link_mode(ks, lp_advertising); hw_link_info = &vsi->port_info->phy.link_info; /* set speed and duplex */ @@ -2125,48 +2140,36 @@ ice_get_link_ksettings(struct net_device *netdev, /* flow control is symmetric and always supported */ ethtool_link_ksettings_add_link_mode(ks, supported, Pause); - switch (vsi->port_info->fc.req_mode) { - case ICE_FC_FULL: + caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL); + if (!caps) + return -ENOMEM; + + status = ice_aq_get_phy_caps(vsi->port_info, false, + ICE_AQC_REPORT_SW_CFG, caps, NULL); + if (status) { + err = -EIO; + goto done; + } + + /* Set the advertised flow control based on the PHY capability */ + if ((caps->caps & ICE_AQC_PHY_EN_TX_LINK_PAUSE) && + (caps->caps & ICE_AQC_PHY_EN_RX_LINK_PAUSE)) { ethtool_link_ksettings_add_link_mode(ks, advertising, Pause); - break; - case ICE_FC_TX_PAUSE: ethtool_link_ksettings_add_link_mode(ks, advertising, Asym_Pause); - break; - case ICE_FC_RX_PAUSE: + } else if (caps->caps & ICE_AQC_PHY_EN_TX_LINK_PAUSE) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + Asym_Pause); + } else if (caps->caps & ICE_AQC_PHY_EN_RX_LINK_PAUSE) { ethtool_link_ksettings_add_link_mode(ks, advertising, Pause); ethtool_link_ksettings_add_link_mode(ks, advertising, Asym_Pause); - break; - case ICE_FC_PFC: - default: + } else { ethtool_link_ksettings_del_link_mode(ks, advertising, Pause); ethtool_link_ksettings_del_link_mode(ks, advertising, Asym_Pause); - break; } - caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL); - if (!caps) - goto done; - - if (ice_aq_get_phy_caps(vsi->port_info, false, ICE_AQC_REPORT_TOPO_CAP, - caps, NULL)) - netdev_info(netdev, "Get phy capability failed.\n"); - - /* Set supported FEC modes based on PHY capability */ - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); - - if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN || - caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN) - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); - if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN) - ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); - - if (ice_aq_get_phy_caps(vsi->port_info, false, ICE_AQC_REPORT_SW_CFG, - caps, NULL)) - netdev_info(netdev, "Get phy capability failed.\n"); - /* Set advertised FEC modes based on PHY capability */ ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); @@ -2178,9 +2181,25 @@ ice_get_link_ksettings(struct net_device *netdev, caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_544_REQ) ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); + status = ice_aq_get_phy_caps(vsi->port_info, false, + ICE_AQC_REPORT_TOPO_CAP, caps, NULL); + if (status) { + err = -EIO; + goto done; + } + + /* Set supported FEC modes based on PHY capability */ + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_NONE); + + if (caps->link_fec_options & ICE_AQC_PHY_FEC_10G_KR_40G_KR4_EN || + caps->link_fec_options & ICE_AQC_PHY_FEC_25G_KR_CLAUSE74_EN) + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); + if (caps->link_fec_options & ICE_AQC_PHY_FEC_25G_RS_CLAUSE91_EN) + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); + done: devm_kfree(&vsi->back->pdev->dev, caps); - return 0; + return err; } /** @@ -2763,6 +2782,11 @@ static int ice_nway_reset(struct net_device *netdev) * ice_get_pauseparam - Get Flow Control status * @netdev: network interface device structure * @pause: ethernet pause (flow control) parameters + * + * Get requested flow control status from PHY capability. + * If autoneg is true, then ethtool will send the ETHTOOL_GSET ioctl which + * is handled by ice_get_link_ksettings. ice_get_link_ksettings will report + * the negotiated Rx/Tx pause via lp_advertising. */ static void ice_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) @@ -2816,6 +2840,7 @@ static int ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) { struct ice_netdev_priv *np = netdev_priv(netdev); + struct ice_aqc_get_phy_caps_data *pcaps; struct ice_link_status *hw_link_info; struct ice_pf *pf = np->vsi->back; struct ice_dcbx_cfg *dcbx_cfg; @@ -2826,6 +2851,7 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) u8 aq_failures; bool link_up; int err = 0; + u32 is_an; pi = vsi->port_info; hw_link_info = &pi->phy.link_info; @@ -2840,7 +2866,30 @@ ice_set_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) return -EOPNOTSUPP; } - if (pause->autoneg != (hw_link_info->an_info & ICE_AQ_AN_COMPLETED)) { + /* Get pause param reports configured and negotiated flow control pause + * when ETHTOOL_GLINKSETTINGS is defined. Since ETHTOOL_GLINKSETTINGS is + * defined get pause param pause->autoneg reports SW configured setting, + * so compare pause->autoneg with SW configured to prevent the user from + * using set pause param to chance autoneg. + */ + pcaps = kzalloc(sizeof(*pcaps), GFP_KERNEL); + if (!pcaps) + return -ENOMEM; + + /* Get current PHY config */ + status = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps, + NULL); + if (status) { + kfree(pcaps); + return -EIO; + } + + is_an = ((pcaps->caps & ICE_AQC_PHY_AN_MODE) ? + AUTONEG_ENABLE : AUTONEG_DISABLE); + + kfree(pcaps); + + if (pause->autoneg != is_an) { netdev_info(netdev, "To change autoneg please use: ethtool -s <dev> autoneg <on|off>\n"); return -EOPNOTSUPP; } @@ -3146,12 +3195,6 @@ __ice_get_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, if (ice_get_q_coalesce(vsi, ec, q_num)) return -EINVAL; - if (q_num < vsi->num_txq) - ec->tx_max_coalesced_frames_irq = vsi->work_lmt; - - if (q_num < vsi->num_rxq) - ec->rx_max_coalesced_frames_irq = vsi->work_lmt; - return 0; } @@ -3185,25 +3228,25 @@ static int ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, struct ice_ring_container *rc, struct ice_vsi *vsi) { + const char *c_type_str = (c_type == ICE_RX_CONTAINER) ? "rx" : "tx"; + u32 use_adaptive_coalesce, coalesce_usecs; struct ice_pf *pf = vsi->back; u16 itr_setting; if (!rc->ring) return -EINVAL; - itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC; - switch (c_type) { case ICE_RX_CONTAINER: if (ec->rx_coalesce_usecs_high > ICE_MAX_INTRL || (ec->rx_coalesce_usecs_high && ec->rx_coalesce_usecs_high < pf->hw.intrl_gran)) { netdev_info(vsi->netdev, - "Invalid value, rx-usecs-high valid values are 0 (disabled), %d-%d\n", - pf->hw.intrl_gran, ICE_MAX_INTRL); + "Invalid value, %s-usecs-high valid values are 0 (disabled), %d-%d\n", + c_type_str, pf->hw.intrl_gran, + ICE_MAX_INTRL); return -EINVAL; } - if (ec->rx_coalesce_usecs_high != rc->ring->q_vector->intrl) { rc->ring->q_vector->intrl = ec->rx_coalesce_usecs_high; wr32(&pf->hw, GLINT_RATE(rc->ring->q_vector->reg_idx), @@ -3211,60 +3254,60 @@ ice_set_rc_coalesce(enum ice_container_type c_type, struct ethtool_coalesce *ec, pf->hw.intrl_gran)); } - if (ec->rx_coalesce_usecs != itr_setting && - ec->use_adaptive_rx_coalesce) { - netdev_info(vsi->netdev, - "Rx interrupt throttling cannot be changed if adaptive-rx is enabled\n"); - return -EINVAL; - } + use_adaptive_coalesce = ec->use_adaptive_rx_coalesce; + coalesce_usecs = ec->rx_coalesce_usecs; - if (ec->rx_coalesce_usecs > ICE_ITR_MAX) { - netdev_info(vsi->netdev, - "Invalid value, rx-usecs range is 0-%d\n", - ICE_ITR_MAX); - return -EINVAL; - } - - if (ec->use_adaptive_rx_coalesce) { - rc->itr_setting |= ICE_ITR_DYNAMIC; - } else { - rc->itr_setting = ITR_REG_ALIGN(ec->rx_coalesce_usecs); - rc->target_itr = ITR_TO_REG(rc->itr_setting); - } break; case ICE_TX_CONTAINER: if (ec->tx_coalesce_usecs_high) { netdev_info(vsi->netdev, - "setting tx-usecs-high is not supported\n"); + "setting %s-usecs-high is not supported\n", + c_type_str); return -EINVAL; } - if (ec->tx_coalesce_usecs != itr_setting && - ec->use_adaptive_tx_coalesce) { - netdev_info(vsi->netdev, - "Tx interrupt throttling cannot be changed if adaptive-tx is enabled\n"); - return -EINVAL; - } + use_adaptive_coalesce = ec->use_adaptive_tx_coalesce; + coalesce_usecs = ec->tx_coalesce_usecs; - if (ec->tx_coalesce_usecs > ICE_ITR_MAX) { - netdev_info(vsi->netdev, - "Invalid value, tx-usecs range is 0-%d\n", - ICE_ITR_MAX); - return -EINVAL; - } - - if (ec->use_adaptive_tx_coalesce) { - rc->itr_setting |= ICE_ITR_DYNAMIC; - } else { - rc->itr_setting = ITR_REG_ALIGN(ec->tx_coalesce_usecs); - rc->target_itr = ITR_TO_REG(rc->itr_setting); - } break; default: dev_dbg(&pf->pdev->dev, "Invalid container type %d\n", c_type); return -EINVAL; } + itr_setting = rc->itr_setting & ~ICE_ITR_DYNAMIC; + if (coalesce_usecs != itr_setting && use_adaptive_coalesce) { + netdev_info(vsi->netdev, + "%s interrupt throttling cannot be changed if adaptive-%s is enabled\n", + c_type_str, c_type_str); + return -EINVAL; + } + + if (coalesce_usecs > ICE_ITR_MAX) { + netdev_info(vsi->netdev, + "Invalid value, %s-usecs range is 0-%d\n", + c_type_str, ICE_ITR_MAX); + return -EINVAL; + } + + /* hardware only supports an ITR granularity of 2us */ + if (coalesce_usecs % 2 != 0) { + netdev_info(vsi->netdev, + "Invalid value, %s-usecs must be even\n", + c_type_str); + return -EINVAL; + } + + if (use_adaptive_coalesce) { + rc->itr_setting |= ICE_ITR_DYNAMIC; + } else { + /* store user facing value how it was set */ + rc->itr_setting = coalesce_usecs; + /* set to static and convert to value HW understands */ + rc->target_itr = + ITR_TO_REG(ITR_REG_ALIGN(rc->itr_setting)); + } + return 0; } @@ -3331,17 +3374,13 @@ __ice_set_coalesce(struct net_device *netdev, struct ethtool_coalesce *ec, if (ice_set_q_coalesce(vsi, ec, i)) return -EINVAL; } - goto set_work_lmt; + goto set_complete; } if (ice_set_q_coalesce(vsi, ec, q_num)) return -EINVAL; -set_work_lmt: - - if (ec->tx_max_coalesced_frames_irq || ec->rx_max_coalesced_frames_irq) - vsi->work_lmt = max(ec->tx_max_coalesced_frames_irq, - ec->rx_max_coalesced_frames_irq); +set_complete: return 0; } @@ -3396,6 +3435,33 @@ static const struct ethtool_ops ice_ethtool_ops = { .set_fecparam = ice_set_fecparam, }; +static const struct ethtool_ops ice_ethtool_safe_mode_ops = { + .get_link_ksettings = ice_get_link_ksettings, + .set_link_ksettings = ice_set_link_ksettings, + .get_drvinfo = ice_get_drvinfo, + .get_regs_len = ice_get_regs_len, + .get_regs = ice_get_regs, + .get_msglevel = ice_get_msglevel, + .set_msglevel = ice_set_msglevel, + .get_eeprom_len = ice_get_eeprom_len, + .get_eeprom = ice_get_eeprom, + .get_strings = ice_get_strings, + .get_ethtool_stats = ice_get_ethtool_stats, + .get_sset_count = ice_get_sset_count, + .get_ringparam = ice_get_ringparam, + .set_ringparam = ice_set_ringparam, + .nway_reset = ice_nway_reset, +}; + +/** + * ice_set_ethtool_safe_mode_ops - setup safe mode ethtool ops + * @netdev: network interface device structure + */ +void ice_set_ethtool_safe_mode_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &ice_ethtool_safe_mode_ops; +} + /** * ice_set_ethtool_ops - setup netdev ethtool ops * @netdev: network interface device structure diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.c b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c new file mode 100644 index 000000000000..cbd53b586c36 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.c @@ -0,0 +1,1549 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2019, Intel Corporation. */ + +#include "ice_common.h" +#include "ice_flex_pipe.h" + +/** + * ice_pkg_val_buf + * @buf: pointer to the ice buffer + * + * This helper function validates a buffer's header. + */ +static struct ice_buf_hdr *ice_pkg_val_buf(struct ice_buf *buf) +{ + struct ice_buf_hdr *hdr; + u16 section_count; + u16 data_end; + + hdr = (struct ice_buf_hdr *)buf->buf; + /* verify data */ + section_count = le16_to_cpu(hdr->section_count); + if (section_count < ICE_MIN_S_COUNT || section_count > ICE_MAX_S_COUNT) + return NULL; + + data_end = le16_to_cpu(hdr->data_end); + if (data_end < ICE_MIN_S_DATA_END || data_end > ICE_MAX_S_DATA_END) + return NULL; + + return hdr; +} + +/** + * ice_find_buf_table + * @ice_seg: pointer to the ice segment + * + * Returns the address of the buffer table within the ice segment. + */ +static struct ice_buf_table *ice_find_buf_table(struct ice_seg *ice_seg) +{ + struct ice_nvm_table *nvms; + + nvms = (struct ice_nvm_table *) + (ice_seg->device_table + + le32_to_cpu(ice_seg->device_table_count)); + + return (__force struct ice_buf_table *) + (nvms->vers + le32_to_cpu(nvms->table_count)); +} + +/** + * ice_pkg_enum_buf + * @ice_seg: pointer to the ice segment (or NULL on subsequent calls) + * @state: pointer to the enum state + * + * This function will enumerate all the buffers in the ice segment. The first + * call is made with the ice_seg parameter non-NULL; on subsequent calls, + * ice_seg is set to NULL which continues the enumeration. When the function + * returns a NULL pointer, then the end of the buffers has been reached, or an + * unexpected value has been detected (for example an invalid section count or + * an invalid buffer end value). + */ +static struct ice_buf_hdr * +ice_pkg_enum_buf(struct ice_seg *ice_seg, struct ice_pkg_enum *state) +{ + if (ice_seg) { + state->buf_table = ice_find_buf_table(ice_seg); + if (!state->buf_table) + return NULL; + + state->buf_idx = 0; + return ice_pkg_val_buf(state->buf_table->buf_array); + } + + if (++state->buf_idx < le32_to_cpu(state->buf_table->buf_count)) + return ice_pkg_val_buf(state->buf_table->buf_array + + state->buf_idx); + else + return NULL; +} + +/** + * ice_pkg_advance_sect + * @ice_seg: pointer to the ice segment (or NULL on subsequent calls) + * @state: pointer to the enum state + * + * This helper function will advance the section within the ice segment, + * also advancing the buffer if needed. + */ +static bool +ice_pkg_advance_sect(struct ice_seg *ice_seg, struct ice_pkg_enum *state) +{ + if (!ice_seg && !state->buf) + return false; + + if (!ice_seg && state->buf) + if (++state->sect_idx < le16_to_cpu(state->buf->section_count)) + return true; + + state->buf = ice_pkg_enum_buf(ice_seg, state); + if (!state->buf) + return false; + + /* start of new buffer, reset section index */ + state->sect_idx = 0; + return true; +} + +/** + * ice_pkg_enum_section + * @ice_seg: pointer to the ice segment (or NULL on subsequent calls) + * @state: pointer to the enum state + * @sect_type: section type to enumerate + * + * This function will enumerate all the sections of a particular type in the + * ice segment. The first call is made with the ice_seg parameter non-NULL; + * on subsequent calls, ice_seg is set to NULL which continues the enumeration. + * When the function returns a NULL pointer, then the end of the matching + * sections has been reached. + */ +static void * +ice_pkg_enum_section(struct ice_seg *ice_seg, struct ice_pkg_enum *state, + u32 sect_type) +{ + u16 offset, size; + + if (ice_seg) + state->type = sect_type; + + if (!ice_pkg_advance_sect(ice_seg, state)) + return NULL; + + /* scan for next matching section */ + while (state->buf->section_entry[state->sect_idx].type != + cpu_to_le32(state->type)) + if (!ice_pkg_advance_sect(NULL, state)) + return NULL; + + /* validate section */ + offset = le16_to_cpu(state->buf->section_entry[state->sect_idx].offset); + if (offset < ICE_MIN_S_OFF || offset > ICE_MAX_S_OFF) + return NULL; + + size = le16_to_cpu(state->buf->section_entry[state->sect_idx].size); + if (size < ICE_MIN_S_SZ || size > ICE_MAX_S_SZ) + return NULL; + + /* make sure the section fits in the buffer */ + if (offset + size > ICE_PKG_BUF_SIZE) + return NULL; + + state->sect_type = + le32_to_cpu(state->buf->section_entry[state->sect_idx].type); + + /* calc pointer to this section */ + state->sect = ((u8 *)state->buf) + + le16_to_cpu(state->buf->section_entry[state->sect_idx].offset); + + return state->sect; +} + +/** + * ice_acquire_global_cfg_lock + * @hw: pointer to the HW structure + * @access: access type (read or write) + * + * This function will request ownership of the global config lock for reading + * or writing of the package. When attempting to obtain write access, the + * caller must check for the following two return values: + * + * ICE_SUCCESS - Means the caller has acquired the global config lock + * and can perform writing of the package. + * ICE_ERR_AQ_NO_WORK - Indicates another driver has already written the + * package or has found that no update was necessary; in + * this case, the caller can just skip performing any + * update of the package. + */ +static enum ice_status +ice_acquire_global_cfg_lock(struct ice_hw *hw, + enum ice_aq_res_access_type access) +{ + enum ice_status status; + + status = ice_acquire_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID, access, + ICE_GLOBAL_CFG_LOCK_TIMEOUT); + + if (!status) + mutex_lock(&ice_global_cfg_lock_sw); + else if (status == ICE_ERR_AQ_NO_WORK) + ice_debug(hw, ICE_DBG_PKG, + "Global config lock: No work to do\n"); + + return status; +} + +/** + * ice_release_global_cfg_lock + * @hw: pointer to the HW structure + * + * This function will release the global config lock. + */ +static void ice_release_global_cfg_lock(struct ice_hw *hw) +{ + mutex_unlock(&ice_global_cfg_lock_sw); + ice_release_res(hw, ICE_GLOBAL_CFG_LOCK_RES_ID); +} + +/** + * ice_aq_download_pkg + * @hw: pointer to the hardware structure + * @pkg_buf: the package buffer to transfer + * @buf_size: the size of the package buffer + * @last_buf: last buffer indicator + * @error_offset: returns error offset + * @error_info: returns error information + * @cd: pointer to command details structure or NULL + * + * Download Package (0x0C40) + */ +static enum ice_status +ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf, + u16 buf_size, bool last_buf, u32 *error_offset, + u32 *error_info, struct ice_sq_cd *cd) +{ + struct ice_aqc_download_pkg *cmd; + struct ice_aq_desc desc; + enum ice_status status; + + if (error_offset) + *error_offset = 0; + if (error_info) + *error_info = 0; + + cmd = &desc.params.download_pkg; + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg); + desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD); + + if (last_buf) + cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF; + + status = ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd); + if (status == ICE_ERR_AQ_ERROR) { + /* Read error from buffer only when the FW returned an error */ + struct ice_aqc_download_pkg_resp *resp; + + resp = (struct ice_aqc_download_pkg_resp *)pkg_buf; + if (error_offset) + *error_offset = le32_to_cpu(resp->error_offset); + if (error_info) + *error_info = le32_to_cpu(resp->error_info); + } + + return status; +} + +/** + * ice_find_seg_in_pkg + * @hw: pointer to the hardware structure + * @seg_type: the segment type to search for (i.e., SEGMENT_TYPE_CPK) + * @pkg_hdr: pointer to the package header to be searched + * + * This function searches a package file for a particular segment type. On + * success it returns a pointer to the segment header, otherwise it will + * return NULL. + */ +static struct ice_generic_seg_hdr * +ice_find_seg_in_pkg(struct ice_hw *hw, u32 seg_type, + struct ice_pkg_hdr *pkg_hdr) +{ + u32 i; + + ice_debug(hw, ICE_DBG_PKG, "Package format version: %d.%d.%d.%d\n", + pkg_hdr->format_ver.major, pkg_hdr->format_ver.minor, + pkg_hdr->format_ver.update, pkg_hdr->format_ver.draft); + + /* Search all package segments for the requested segment type */ + for (i = 0; i < le32_to_cpu(pkg_hdr->seg_count); i++) { + struct ice_generic_seg_hdr *seg; + + seg = (struct ice_generic_seg_hdr *) + ((u8 *)pkg_hdr + le32_to_cpu(pkg_hdr->seg_offset[i])); + + if (le32_to_cpu(seg->seg_type) == seg_type) + return seg; + } + + return NULL; +} + +/** + * ice_dwnld_cfg_bufs + * @hw: pointer to the hardware structure + * @bufs: pointer to an array of buffers + * @count: the number of buffers in the array + * + * Obtains global config lock and downloads the package configuration buffers + * to the firmware. Metadata buffers are skipped, and the first metadata buffer + * found indicates that the rest of the buffers are all metadata buffers. + */ +static enum ice_status +ice_dwnld_cfg_bufs(struct ice_hw *hw, struct ice_buf *bufs, u32 count) +{ + enum ice_status status; + struct ice_buf_hdr *bh; + u32 offset, info, i; + + if (!bufs || !count) + return ICE_ERR_PARAM; + + /* If the first buffer's first section has its metadata bit set + * then there are no buffers to be downloaded, and the operation is + * considered a success. + */ + bh = (struct ice_buf_hdr *)bufs; + if (le32_to_cpu(bh->section_entry[0].type) & ICE_METADATA_BUF) + return 0; + + /* reset pkg_dwnld_status in case this function is called in the + * reset/rebuild flow + */ + hw->pkg_dwnld_status = ICE_AQ_RC_OK; + + status = ice_acquire_global_cfg_lock(hw, ICE_RES_WRITE); + if (status) { + if (status == ICE_ERR_AQ_NO_WORK) + hw->pkg_dwnld_status = ICE_AQ_RC_EEXIST; + else + hw->pkg_dwnld_status = hw->adminq.sq_last_status; + return status; + } + + for (i = 0; i < count; i++) { + bool last = ((i + 1) == count); + + if (!last) { + /* check next buffer for metadata flag */ + bh = (struct ice_buf_hdr *)(bufs + i + 1); + + /* A set metadata flag in the next buffer will signal + * that the current buffer will be the last buffer + * downloaded + */ + if (le16_to_cpu(bh->section_count)) + if (le32_to_cpu(bh->section_entry[0].type) & + ICE_METADATA_BUF) + last = true; + } + + bh = (struct ice_buf_hdr *)(bufs + i); + + status = ice_aq_download_pkg(hw, bh, ICE_PKG_BUF_SIZE, last, + &offset, &info, NULL); + + /* Save AQ status from download package */ + hw->pkg_dwnld_status = hw->adminq.sq_last_status; + if (status) { + ice_debug(hw, ICE_DBG_PKG, + "Pkg download failed: err %d off %d inf %d\n", + status, offset, info); + + break; + } + + if (last) + break; + } + + ice_release_global_cfg_lock(hw); + + return status; +} + +/** + * ice_aq_get_pkg_info_list + * @hw: pointer to the hardware structure + * @pkg_info: the buffer which will receive the information list + * @buf_size: the size of the pkg_info information buffer + * @cd: pointer to command details structure or NULL + * + * Get Package Info List (0x0C43) + */ +static enum ice_status +ice_aq_get_pkg_info_list(struct ice_hw *hw, + struct ice_aqc_get_pkg_info_resp *pkg_info, + u16 buf_size, struct ice_sq_cd *cd) +{ + struct ice_aq_desc desc; + + ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list); + + return ice_aq_send_cmd(hw, &desc, pkg_info, buf_size, cd); +} + +/** + * ice_download_pkg + * @hw: pointer to the hardware structure + * @ice_seg: pointer to the segment of the package to be downloaded + * + * Handles the download of a complete package. + */ +static enum ice_status +ice_download_pkg(struct ice_hw *hw, struct ice_seg *ice_seg) +{ + struct ice_buf_table *ice_buf_tbl; + + ice_debug(hw, ICE_DBG_PKG, "Segment version: %d.%d.%d.%d\n", + ice_seg->hdr.seg_ver.major, ice_seg->hdr.seg_ver.minor, + ice_seg->hdr.seg_ver.update, ice_seg->hdr.seg_ver.draft); + + ice_debug(hw, ICE_DBG_PKG, "Seg: type 0x%X, size %d, name %s\n", + le32_to_cpu(ice_seg->hdr.seg_type), + le32_to_cpu(ice_seg->hdr.seg_size), ice_seg->hdr.seg_name); + + ice_buf_tbl = ice_find_buf_table(ice_seg); + + ice_debug(hw, ICE_DBG_PKG, "Seg buf count: %d\n", + le32_to_cpu(ice_buf_tbl->buf_count)); + + return ice_dwnld_cfg_bufs(hw, ice_buf_tbl->buf_array, + le32_to_cpu(ice_buf_tbl->buf_count)); +} + +/** + * ice_init_pkg_info + * @hw: pointer to the hardware structure + * @pkg_hdr: pointer to the driver's package hdr + * + * Saves off the package details into the HW structure. + */ +static enum ice_status +ice_init_pkg_info(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr) +{ + struct ice_global_metadata_seg *meta_seg; + struct ice_generic_seg_hdr *seg_hdr; + + if (!pkg_hdr) + return ICE_ERR_PARAM; + + meta_seg = (struct ice_global_metadata_seg *) + ice_find_seg_in_pkg(hw, SEGMENT_TYPE_METADATA, pkg_hdr); + if (meta_seg) { + hw->pkg_ver = meta_seg->pkg_ver; + memcpy(hw->pkg_name, meta_seg->pkg_name, sizeof(hw->pkg_name)); + + ice_debug(hw, ICE_DBG_PKG, "Pkg: %d.%d.%d.%d, %s\n", + meta_seg->pkg_ver.major, meta_seg->pkg_ver.minor, + meta_seg->pkg_ver.update, meta_seg->pkg_ver.draft, + meta_seg->pkg_name); + } else { + ice_debug(hw, ICE_DBG_INIT, + "Did not find metadata segment in driver package\n"); + return ICE_ERR_CFG; + } + + seg_hdr = ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg_hdr); + if (seg_hdr) { + hw->ice_pkg_ver = seg_hdr->seg_ver; + memcpy(hw->ice_pkg_name, seg_hdr->seg_name, + sizeof(hw->ice_pkg_name)); + + ice_debug(hw, ICE_DBG_PKG, "Ice Pkg: %d.%d.%d.%d, %s\n", + seg_hdr->seg_ver.major, seg_hdr->seg_ver.minor, + seg_hdr->seg_ver.update, seg_hdr->seg_ver.draft, + seg_hdr->seg_name); + } else { + ice_debug(hw, ICE_DBG_INIT, + "Did not find ice segment in driver package\n"); + return ICE_ERR_CFG; + } + + return 0; +} + +/** + * ice_get_pkg_info + * @hw: pointer to the hardware structure + * + * Store details of the package currently loaded in HW into the HW structure. + */ +static enum ice_status ice_get_pkg_info(struct ice_hw *hw) +{ + struct ice_aqc_get_pkg_info_resp *pkg_info; + enum ice_status status; + u16 size; + u32 i; + + size = sizeof(*pkg_info) + (sizeof(pkg_info->pkg_info[0]) * + (ICE_PKG_CNT - 1)); + pkg_info = kzalloc(size, GFP_KERNEL); + if (!pkg_info) + return ICE_ERR_NO_MEMORY; + + status = ice_aq_get_pkg_info_list(hw, pkg_info, size, NULL); + if (status) + goto init_pkg_free_alloc; + + for (i = 0; i < le32_to_cpu(pkg_info->count); i++) { +#define ICE_PKG_FLAG_COUNT 4 + char flags[ICE_PKG_FLAG_COUNT + 1] = { 0 }; + u8 place = 0; + + if (pkg_info->pkg_info[i].is_active) { + flags[place++] = 'A'; + hw->active_pkg_ver = pkg_info->pkg_info[i].ver; + memcpy(hw->active_pkg_name, + pkg_info->pkg_info[i].name, + sizeof(hw->active_pkg_name)); + hw->active_pkg_in_nvm = pkg_info->pkg_info[i].is_in_nvm; + } + if (pkg_info->pkg_info[i].is_active_at_boot) + flags[place++] = 'B'; + if (pkg_info->pkg_info[i].is_modified) + flags[place++] = 'M'; + if (pkg_info->pkg_info[i].is_in_nvm) + flags[place++] = 'N'; + + ice_debug(hw, ICE_DBG_PKG, "Pkg[%d]: %d.%d.%d.%d,%s,%s\n", + i, pkg_info->pkg_info[i].ver.major, + pkg_info->pkg_info[i].ver.minor, + pkg_info->pkg_info[i].ver.update, + pkg_info->pkg_info[i].ver.draft, + pkg_info->pkg_info[i].name, flags); + } + +init_pkg_free_alloc: + kfree(pkg_info); + + return status; +} + +/** + * ice_verify_pkg - verify package + * @pkg: pointer to the package buffer + * @len: size of the package buffer + * + * Verifies various attributes of the package file, including length, format + * version, and the requirement of at least one segment. + */ +static enum ice_status ice_verify_pkg(struct ice_pkg_hdr *pkg, u32 len) +{ + u32 seg_count; + u32 i; + + if (len < sizeof(*pkg)) + return ICE_ERR_BUF_TOO_SHORT; + + if (pkg->format_ver.major != ICE_PKG_FMT_VER_MAJ || + pkg->format_ver.minor != ICE_PKG_FMT_VER_MNR || + pkg->format_ver.update != ICE_PKG_FMT_VER_UPD || + pkg->format_ver.draft != ICE_PKG_FMT_VER_DFT) + return ICE_ERR_CFG; + + /* pkg must have at least one segment */ + seg_count = le32_to_cpu(pkg->seg_count); + if (seg_count < 1) + return ICE_ERR_CFG; + + /* make sure segment array fits in package length */ + if (len < sizeof(*pkg) + ((seg_count - 1) * sizeof(pkg->seg_offset))) + return ICE_ERR_BUF_TOO_SHORT; + + /* all segments must fit within length */ + for (i = 0; i < seg_count; i++) { + u32 off = le32_to_cpu(pkg->seg_offset[i]); + struct ice_generic_seg_hdr *seg; + + /* segment header must fit */ + if (len < off + sizeof(*seg)) + return ICE_ERR_BUF_TOO_SHORT; + + seg = (struct ice_generic_seg_hdr *)((u8 *)pkg + off); + + /* segment body must fit */ + if (len < off + le32_to_cpu(seg->seg_size)) + return ICE_ERR_BUF_TOO_SHORT; + } + + return 0; +} + +/** + * ice_free_seg - free package segment pointer + * @hw: pointer to the hardware structure + * + * Frees the package segment pointer in the proper manner, depending on if the + * segment was allocated or just the passed in pointer was stored. + */ +void ice_free_seg(struct ice_hw *hw) +{ + if (hw->pkg_copy) { + devm_kfree(ice_hw_to_dev(hw), hw->pkg_copy); + hw->pkg_copy = NULL; + hw->pkg_size = 0; + } + hw->seg = NULL; +} + +/** + * ice_init_pkg_regs - initialize additional package registers + * @hw: pointer to the hardware structure + */ +static void ice_init_pkg_regs(struct ice_hw *hw) +{ +#define ICE_SW_BLK_INP_MASK_L 0xFFFFFFFF +#define ICE_SW_BLK_INP_MASK_H 0x0000FFFF +#define ICE_SW_BLK_IDX 0 + + /* setup Switch block input mask, which is 48-bits in two parts */ + wr32(hw, GL_PREEXT_L2_PMASK0(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_L); + wr32(hw, GL_PREEXT_L2_PMASK1(ICE_SW_BLK_IDX), ICE_SW_BLK_INP_MASK_H); +} + +/** + * ice_chk_pkg_version - check package version for compatibility with driver + * @pkg_ver: pointer to a version structure to check + * + * Check to make sure that the package about to be downloaded is compatible with + * the driver. To be compatible, the major and minor components of the package + * version must match our ICE_PKG_SUPP_VER_MAJ and ICE_PKG_SUPP_VER_MNR + * definitions. + */ +static enum ice_status ice_chk_pkg_version(struct ice_pkg_ver *pkg_ver) +{ + if (pkg_ver->major != ICE_PKG_SUPP_VER_MAJ || + pkg_ver->minor != ICE_PKG_SUPP_VER_MNR) + return ICE_ERR_NOT_SUPPORTED; + + return 0; +} + +/** + * ice_init_pkg - initialize/download package + * @hw: pointer to the hardware structure + * @buf: pointer to the package buffer + * @len: size of the package buffer + * + * This function initializes a package. The package contains HW tables + * required to do packet processing. First, the function extracts package + * information such as version. Then it finds the ice configuration segment + * within the package; this function then saves a copy of the segment pointer + * within the supplied package buffer. Next, the function will cache any hints + * from the package, followed by downloading the package itself. Note, that if + * a previous PF driver has already downloaded the package successfully, then + * the current driver will not have to download the package again. + * + * The local package contents will be used to query default behavior and to + * update specific sections of the HW's version of the package (e.g. to update + * the parse graph to understand new protocols). + * + * This function stores a pointer to the package buffer memory, and it is + * expected that the supplied buffer will not be freed immediately. If the + * package buffer needs to be freed, such as when read from a file, use + * ice_copy_and_init_pkg() instead of directly calling ice_init_pkg() in this + * case. + */ +enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buf, u32 len) +{ + struct ice_pkg_hdr *pkg; + enum ice_status status; + struct ice_seg *seg; + + if (!buf || !len) + return ICE_ERR_PARAM; + + pkg = (struct ice_pkg_hdr *)buf; + status = ice_verify_pkg(pkg, len); + if (status) { + ice_debug(hw, ICE_DBG_INIT, "failed to verify pkg (err: %d)\n", + status); + return status; + } + + /* initialize package info */ + status = ice_init_pkg_info(hw, pkg); + if (status) + return status; + + /* before downloading the package, check package version for + * compatibility with driver + */ + status = ice_chk_pkg_version(&hw->pkg_ver); + if (status) + return status; + + /* find segment in given package */ + seg = (struct ice_seg *)ice_find_seg_in_pkg(hw, SEGMENT_TYPE_ICE, pkg); + if (!seg) { + ice_debug(hw, ICE_DBG_INIT, "no ice segment in package.\n"); + return ICE_ERR_CFG; + } + + /* download package */ + status = ice_download_pkg(hw, seg); + if (status == ICE_ERR_AQ_NO_WORK) { + ice_debug(hw, ICE_DBG_INIT, + "package previously loaded - no work.\n"); + status = 0; + } + + /* Get information on the package currently loaded in HW, then make sure + * the driver is compatible with this version. + */ + if (!status) { + status = ice_get_pkg_info(hw); + if (!status) + status = ice_chk_pkg_version(&hw->active_pkg_ver); + } + + if (!status) { + hw->seg = seg; + /* on successful package download update other required + * registers to support the package and fill HW tables + * with package content. + */ + ice_init_pkg_regs(hw); + ice_fill_blk_tbls(hw); + } else { + ice_debug(hw, ICE_DBG_INIT, "package load failed, %d\n", + status); + } + + return status; +} + +/** + * ice_copy_and_init_pkg - initialize/download a copy of the package + * @hw: pointer to the hardware structure + * @buf: pointer to the package buffer + * @len: size of the package buffer + * + * This function copies the package buffer, and then calls ice_init_pkg() to + * initialize the copied package contents. + * + * The copying is necessary if the package buffer supplied is constant, or if + * the memory may disappear shortly after calling this function. + * + * If the package buffer resides in the data segment and can be modified, the + * caller is free to use ice_init_pkg() instead of ice_copy_and_init_pkg(). + * + * However, if the package buffer needs to be copied first, such as when being + * read from a file, the caller should use ice_copy_and_init_pkg(). + * + * This function will first copy the package buffer, before calling + * ice_init_pkg(). The caller is free to immediately destroy the original + * package buffer, as the new copy will be managed by this function and + * related routines. + */ +enum ice_status ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len) +{ + enum ice_status status; + u8 *buf_copy; + + if (!buf || !len) + return ICE_ERR_PARAM; + + buf_copy = devm_kmemdup(ice_hw_to_dev(hw), buf, len, GFP_KERNEL); + + status = ice_init_pkg(hw, buf_copy, len); + if (status) { + /* Free the copy, since we failed to initialize the package */ + devm_kfree(ice_hw_to_dev(hw), buf_copy); + } else { + /* Track the copied pkg so we can free it later */ + hw->pkg_copy = buf_copy; + hw->pkg_size = len; + } + + return status; +} + +/* PTG Management */ + +/** + * ice_ptg_find_ptype - Search for packet type group using packet type (ptype) + * @hw: pointer to the hardware structure + * @blk: HW block + * @ptype: the ptype to search for + * @ptg: pointer to variable that receives the PTG + * + * This function will search the PTGs for a particular ptype, returning the + * PTG ID that contains it through the PTG parameter, with the value of + * ICE_DEFAULT_PTG (0) meaning it is part the default PTG. + */ +static enum ice_status +ice_ptg_find_ptype(struct ice_hw *hw, enum ice_block blk, u16 ptype, u8 *ptg) +{ + if (ptype >= ICE_XLT1_CNT || !ptg) + return ICE_ERR_PARAM; + + *ptg = hw->blk[blk].xlt1.ptypes[ptype].ptg; + return 0; +} + +/** + * ice_ptg_alloc_val - Allocates a new packet type group ID by value + * @hw: pointer to the hardware structure + * @blk: HW block + * @ptg: the PTG to allocate + * + * This function allocates a given packet type group ID specified by the PTG + * parameter. + */ +static void ice_ptg_alloc_val(struct ice_hw *hw, enum ice_block blk, u8 ptg) +{ + hw->blk[blk].xlt1.ptg_tbl[ptg].in_use = true; +} + +/** + * ice_ptg_remove_ptype - Removes ptype from a particular packet type group + * @hw: pointer to the hardware structure + * @blk: HW block + * @ptype: the ptype to remove + * @ptg: the PTG to remove the ptype from + * + * This function will remove the ptype from the specific PTG, and move it to + * the default PTG (ICE_DEFAULT_PTG). + */ +static enum ice_status +ice_ptg_remove_ptype(struct ice_hw *hw, enum ice_block blk, u16 ptype, u8 ptg) +{ + struct ice_ptg_ptype **ch; + struct ice_ptg_ptype *p; + + if (ptype > ICE_XLT1_CNT - 1) + return ICE_ERR_PARAM; + + if (!hw->blk[blk].xlt1.ptg_tbl[ptg].in_use) + return ICE_ERR_DOES_NOT_EXIST; + + /* Should not happen if .in_use is set, bad config */ + if (!hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype) + return ICE_ERR_CFG; + + /* find the ptype within this PTG, and bypass the link over it */ + p = hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype; + ch = &hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype; + while (p) { + if (ptype == (p - hw->blk[blk].xlt1.ptypes)) { + *ch = p->next_ptype; + break; + } + + ch = &p->next_ptype; + p = p->next_ptype; + } + + hw->blk[blk].xlt1.ptypes[ptype].ptg = ICE_DEFAULT_PTG; + hw->blk[blk].xlt1.ptypes[ptype].next_ptype = NULL; + + return 0; +} + +/** + * ice_ptg_add_mv_ptype - Adds/moves ptype to a particular packet type group + * @hw: pointer to the hardware structure + * @blk: HW block + * @ptype: the ptype to add or move + * @ptg: the PTG to add or move the ptype to + * + * This function will either add or move a ptype to a particular PTG depending + * on if the ptype is already part of another group. Note that using a + * a destination PTG ID of ICE_DEFAULT_PTG (0) will move the ptype to the + * default PTG. + */ +static enum ice_status +ice_ptg_add_mv_ptype(struct ice_hw *hw, enum ice_block blk, u16 ptype, u8 ptg) +{ + enum ice_status status; + u8 original_ptg; + + if (ptype > ICE_XLT1_CNT - 1) + return ICE_ERR_PARAM; + + if (!hw->blk[blk].xlt1.ptg_tbl[ptg].in_use && ptg != ICE_DEFAULT_PTG) + return ICE_ERR_DOES_NOT_EXIST; + + status = ice_ptg_find_ptype(hw, blk, ptype, &original_ptg); + if (status) + return status; + + /* Is ptype already in the correct PTG? */ + if (original_ptg == ptg) + return 0; + + /* Remove from original PTG and move back to the default PTG */ + if (original_ptg != ICE_DEFAULT_PTG) + ice_ptg_remove_ptype(hw, blk, ptype, original_ptg); + + /* Moving to default PTG? Then we're done with this request */ + if (ptg == ICE_DEFAULT_PTG) + return 0; + + /* Add ptype to PTG at beginning of list */ + hw->blk[blk].xlt1.ptypes[ptype].next_ptype = + hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype; + hw->blk[blk].xlt1.ptg_tbl[ptg].first_ptype = + &hw->blk[blk].xlt1.ptypes[ptype]; + + hw->blk[blk].xlt1.ptypes[ptype].ptg = ptg; + hw->blk[blk].xlt1.t[ptype] = ptg; + + return 0; +} + +/* Block / table size info */ +struct ice_blk_size_details { + u16 xlt1; /* # XLT1 entries */ + u16 xlt2; /* # XLT2 entries */ + u16 prof_tcam; /* # profile ID TCAM entries */ + u16 prof_id; /* # profile IDs */ + u8 prof_cdid_bits; /* # CDID one-hot bits used in key */ + u16 prof_redir; /* # profile redirection entries */ + u16 es; /* # extraction sequence entries */ + u16 fvw; /* # field vector words */ + u8 overwrite; /* overwrite existing entries allowed */ + u8 reverse; /* reverse FV order */ +}; + +static const struct ice_blk_size_details blk_sizes[ICE_BLK_COUNT] = { + /** + * Table Definitions + * XLT1 - Number of entries in XLT1 table + * XLT2 - Number of entries in XLT2 table + * TCAM - Number of entries Profile ID TCAM table + * CDID - Control Domain ID of the hardware block + * PRED - Number of entries in the Profile Redirection Table + * FV - Number of entries in the Field Vector + * FVW - Width (in WORDs) of the Field Vector + * OVR - Overwrite existing table entries + * REV - Reverse FV + */ + /* XLT1 , XLT2 ,TCAM, PID,CDID,PRED, FV, FVW */ + /* Overwrite , Reverse FV */ + /* SW */ { ICE_XLT1_CNT, ICE_XLT2_CNT, 512, 256, 0, 256, 256, 48, + false, false }, + /* ACL */ { ICE_XLT1_CNT, ICE_XLT2_CNT, 512, 128, 0, 128, 128, 32, + false, false }, + /* FD */ { ICE_XLT1_CNT, ICE_XLT2_CNT, 512, 128, 0, 128, 128, 24, + false, true }, + /* RSS */ { ICE_XLT1_CNT, ICE_XLT2_CNT, 512, 128, 0, 128, 128, 24, + true, true }, + /* PE */ { ICE_XLT1_CNT, ICE_XLT2_CNT, 64, 32, 0, 32, 32, 24, + false, false }, +}; + +enum ice_sid_all { + ICE_SID_XLT1_OFF = 0, + ICE_SID_XLT2_OFF, + ICE_SID_PR_OFF, + ICE_SID_PR_REDIR_OFF, + ICE_SID_ES_OFF, + ICE_SID_OFF_COUNT, +}; + +/* VSIG Management */ + +/** + * ice_vsig_find_vsi - find a VSIG that contains a specified VSI + * @hw: pointer to the hardware structure + * @blk: HW block + * @vsi: VSI of interest + * @vsig: pointer to receive the VSI group + * + * This function will lookup the VSI entry in the XLT2 list and return + * the VSI group its associated with. + */ +static enum ice_status +ice_vsig_find_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 *vsig) +{ + if (!vsig || vsi >= ICE_MAX_VSI) + return ICE_ERR_PARAM; + + /* As long as there's a default or valid VSIG associated with the input + * VSI, the functions returns a success. Any handling of VSIG will be + * done by the following add, update or remove functions. + */ + *vsig = hw->blk[blk].xlt2.vsis[vsi].vsig; + + return 0; +} + +/** + * ice_vsig_alloc_val - allocate a new VSIG by value + * @hw: pointer to the hardware structure + * @blk: HW block + * @vsig: the VSIG to allocate + * + * This function will allocate a given VSIG specified by the VSIG parameter. + */ +static u16 ice_vsig_alloc_val(struct ice_hw *hw, enum ice_block blk, u16 vsig) +{ + u16 idx = vsig & ICE_VSIG_IDX_M; + + if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use) { + INIT_LIST_HEAD(&hw->blk[blk].xlt2.vsig_tbl[idx].prop_lst); + hw->blk[blk].xlt2.vsig_tbl[idx].in_use = true; + } + + return ICE_VSIG_VALUE(idx, hw->pf_id); +} + +/** + * ice_vsig_remove_vsi - remove VSI from VSIG + * @hw: pointer to the hardware structure + * @blk: HW block + * @vsi: VSI to remove + * @vsig: VSI group to remove from + * + * The function will remove the input VSI from its VSI group and move it + * to the DEFAULT_VSIG. + */ +static enum ice_status +ice_vsig_remove_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig) +{ + struct ice_vsig_vsi **vsi_head, *vsi_cur, *vsi_tgt; + u16 idx; + + idx = vsig & ICE_VSIG_IDX_M; + + if (vsi >= ICE_MAX_VSI || idx >= ICE_MAX_VSIGS) + return ICE_ERR_PARAM; + + if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use) + return ICE_ERR_DOES_NOT_EXIST; + + /* entry already in default VSIG, don't have to remove */ + if (idx == ICE_DEFAULT_VSIG) + return 0; + + vsi_head = &hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi; + if (!(*vsi_head)) + return ICE_ERR_CFG; + + vsi_tgt = &hw->blk[blk].xlt2.vsis[vsi]; + vsi_cur = (*vsi_head); + + /* iterate the VSI list, skip over the entry to be removed */ + while (vsi_cur) { + if (vsi_tgt == vsi_cur) { + (*vsi_head) = vsi_cur->next_vsi; + break; + } + vsi_head = &vsi_cur->next_vsi; + vsi_cur = vsi_cur->next_vsi; + } + + /* verify if VSI was removed from group list */ + if (!vsi_cur) + return ICE_ERR_DOES_NOT_EXIST; + + vsi_cur->vsig = ICE_DEFAULT_VSIG; + vsi_cur->changed = 1; + vsi_cur->next_vsi = NULL; + + return 0; +} + +/** + * ice_vsig_add_mv_vsi - add or move a VSI to a VSI group + * @hw: pointer to the hardware structure + * @blk: HW block + * @vsi: VSI to move + * @vsig: destination VSI group + * + * This function will move or add the input VSI to the target VSIG. + * The function will find the original VSIG the VSI belongs to and + * move the entry to the DEFAULT_VSIG, update the original VSIG and + * then move entry to the new VSIG. + */ +static enum ice_status +ice_vsig_add_mv_vsi(struct ice_hw *hw, enum ice_block blk, u16 vsi, u16 vsig) +{ + struct ice_vsig_vsi *tmp; + enum ice_status status; + u16 orig_vsig, idx; + + idx = vsig & ICE_VSIG_IDX_M; + + if (vsi >= ICE_MAX_VSI || idx >= ICE_MAX_VSIGS) + return ICE_ERR_PARAM; + + /* if VSIG not in use and VSIG is not default type this VSIG + * doesn't exist. + */ + if (!hw->blk[blk].xlt2.vsig_tbl[idx].in_use && + vsig != ICE_DEFAULT_VSIG) + return ICE_ERR_DOES_NOT_EXIST; + + status = ice_vsig_find_vsi(hw, blk, vsi, &orig_vsig); + if (status) + return status; + + /* no update required if vsigs match */ + if (orig_vsig == vsig) + return 0; + + if (orig_vsig != ICE_DEFAULT_VSIG) { + /* remove entry from orig_vsig and add to default VSIG */ + status = ice_vsig_remove_vsi(hw, blk, vsi, orig_vsig); + if (status) + return status; + } + + if (idx == ICE_DEFAULT_VSIG) + return 0; + + /* Create VSI entry and add VSIG and prop_mask values */ + hw->blk[blk].xlt2.vsis[vsi].vsig = vsig; + hw->blk[blk].xlt2.vsis[vsi].changed = 1; + + /* Add new entry to the head of the VSIG list */ + tmp = hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi; + hw->blk[blk].xlt2.vsig_tbl[idx].first_vsi = + &hw->blk[blk].xlt2.vsis[vsi]; + hw->blk[blk].xlt2.vsis[vsi].next_vsi = tmp; + hw->blk[blk].xlt2.t[vsi] = vsig; + + return 0; +} + +/* Block / table section IDs */ +static const u32 ice_blk_sids[ICE_BLK_COUNT][ICE_SID_OFF_COUNT] = { + /* SWITCH */ + { ICE_SID_XLT1_SW, + ICE_SID_XLT2_SW, + ICE_SID_PROFID_TCAM_SW, + ICE_SID_PROFID_REDIR_SW, + ICE_SID_FLD_VEC_SW + }, + + /* ACL */ + { ICE_SID_XLT1_ACL, + ICE_SID_XLT2_ACL, + ICE_SID_PROFID_TCAM_ACL, + ICE_SID_PROFID_REDIR_ACL, + ICE_SID_FLD_VEC_ACL + }, + + /* FD */ + { ICE_SID_XLT1_FD, + ICE_SID_XLT2_FD, + ICE_SID_PROFID_TCAM_FD, + ICE_SID_PROFID_REDIR_FD, + ICE_SID_FLD_VEC_FD + }, + + /* RSS */ + { ICE_SID_XLT1_RSS, + ICE_SID_XLT2_RSS, + ICE_SID_PROFID_TCAM_RSS, + ICE_SID_PROFID_REDIR_RSS, + ICE_SID_FLD_VEC_RSS + }, + + /* PE */ + { ICE_SID_XLT1_PE, + ICE_SID_XLT2_PE, + ICE_SID_PROFID_TCAM_PE, + ICE_SID_PROFID_REDIR_PE, + ICE_SID_FLD_VEC_PE + } +}; + +/** + * ice_init_sw_xlt1_db - init software XLT1 database from HW tables + * @hw: pointer to the hardware structure + * @blk: the HW block to initialize + */ +static void ice_init_sw_xlt1_db(struct ice_hw *hw, enum ice_block blk) +{ + u16 pt; + + for (pt = 0; pt < hw->blk[blk].xlt1.count; pt++) { + u8 ptg; + + ptg = hw->blk[blk].xlt1.t[pt]; + if (ptg != ICE_DEFAULT_PTG) { + ice_ptg_alloc_val(hw, blk, ptg); + ice_ptg_add_mv_ptype(hw, blk, pt, ptg); + } + } +} + +/** + * ice_init_sw_xlt2_db - init software XLT2 database from HW tables + * @hw: pointer to the hardware structure + * @blk: the HW block to initialize + */ +static void ice_init_sw_xlt2_db(struct ice_hw *hw, enum ice_block blk) +{ + u16 vsi; + + for (vsi = 0; vsi < hw->blk[blk].xlt2.count; vsi++) { + u16 vsig; + + vsig = hw->blk[blk].xlt2.t[vsi]; + if (vsig) { + ice_vsig_alloc_val(hw, blk, vsig); + ice_vsig_add_mv_vsi(hw, blk, vsi, vsig); + /* no changes at this time, since this has been + * initialized from the original package + */ + hw->blk[blk].xlt2.vsis[vsi].changed = 0; + } + } +} + +/** + * ice_init_sw_db - init software database from HW tables + * @hw: pointer to the hardware structure + */ +static void ice_init_sw_db(struct ice_hw *hw) +{ + u16 i; + + for (i = 0; i < ICE_BLK_COUNT; i++) { + ice_init_sw_xlt1_db(hw, (enum ice_block)i); + ice_init_sw_xlt2_db(hw, (enum ice_block)i); + } +} + +/** + * ice_fill_tbl - Reads content of a single table type into database + * @hw: pointer to the hardware structure + * @block_id: Block ID of the table to copy + * @sid: Section ID of the table to copy + * + * Will attempt to read the entire content of a given table of a single block + * into the driver database. We assume that the buffer will always + * be as large or larger than the data contained in the package. If + * this condition is not met, there is most likely an error in the package + * contents. + */ +static void ice_fill_tbl(struct ice_hw *hw, enum ice_block block_id, u32 sid) +{ + u32 dst_len, sect_len, offset = 0; + struct ice_prof_redir_section *pr; + struct ice_prof_id_section *pid; + struct ice_xlt1_section *xlt1; + struct ice_xlt2_section *xlt2; + struct ice_sw_fv_section *es; + struct ice_pkg_enum state; + u8 *src, *dst; + void *sect; + + /* if the HW segment pointer is null then the first iteration of + * ice_pkg_enum_section() will fail. In this case the HW tables will + * not be filled and return success. + */ + if (!hw->seg) { + ice_debug(hw, ICE_DBG_PKG, "hw->seg is NULL, tables are not filled\n"); + return; + } + + memset(&state, 0, sizeof(state)); + + sect = ice_pkg_enum_section(hw->seg, &state, sid); + + while (sect) { + switch (sid) { + case ICE_SID_XLT1_SW: + case ICE_SID_XLT1_FD: + case ICE_SID_XLT1_RSS: + case ICE_SID_XLT1_ACL: + case ICE_SID_XLT1_PE: + xlt1 = (struct ice_xlt1_section *)sect; + src = xlt1->value; + sect_len = le16_to_cpu(xlt1->count) * + sizeof(*hw->blk[block_id].xlt1.t); + dst = hw->blk[block_id].xlt1.t; + dst_len = hw->blk[block_id].xlt1.count * + sizeof(*hw->blk[block_id].xlt1.t); + break; + case ICE_SID_XLT2_SW: + case ICE_SID_XLT2_FD: + case ICE_SID_XLT2_RSS: + case ICE_SID_XLT2_ACL: + case ICE_SID_XLT2_PE: + xlt2 = (struct ice_xlt2_section *)sect; + src = (__force u8 *)xlt2->value; + sect_len = le16_to_cpu(xlt2->count) * + sizeof(*hw->blk[block_id].xlt2.t); + dst = (u8 *)hw->blk[block_id].xlt2.t; + dst_len = hw->blk[block_id].xlt2.count * + sizeof(*hw->blk[block_id].xlt2.t); + break; + case ICE_SID_PROFID_TCAM_SW: + case ICE_SID_PROFID_TCAM_FD: + case ICE_SID_PROFID_TCAM_RSS: + case ICE_SID_PROFID_TCAM_ACL: + case ICE_SID_PROFID_TCAM_PE: + pid = (struct ice_prof_id_section *)sect; + src = (u8 *)pid->entry; + sect_len = le16_to_cpu(pid->count) * + sizeof(*hw->blk[block_id].prof.t); + dst = (u8 *)hw->blk[block_id].prof.t; + dst_len = hw->blk[block_id].prof.count * + sizeof(*hw->blk[block_id].prof.t); + break; + case ICE_SID_PROFID_REDIR_SW: + case ICE_SID_PROFID_REDIR_FD: + case ICE_SID_PROFID_REDIR_RSS: + case ICE_SID_PROFID_REDIR_ACL: + case ICE_SID_PROFID_REDIR_PE: + pr = (struct ice_prof_redir_section *)sect; + src = pr->redir_value; + sect_len = le16_to_cpu(pr->count) * + sizeof(*hw->blk[block_id].prof_redir.t); + dst = hw->blk[block_id].prof_redir.t; + dst_len = hw->blk[block_id].prof_redir.count * + sizeof(*hw->blk[block_id].prof_redir.t); + break; + case ICE_SID_FLD_VEC_SW: + case ICE_SID_FLD_VEC_FD: + case ICE_SID_FLD_VEC_RSS: + case ICE_SID_FLD_VEC_ACL: + case ICE_SID_FLD_VEC_PE: + es = (struct ice_sw_fv_section *)sect; + src = (u8 *)es->fv; + sect_len = (u32)(le16_to_cpu(es->count) * + hw->blk[block_id].es.fvw) * + sizeof(*hw->blk[block_id].es.t); + dst = (u8 *)hw->blk[block_id].es.t; + dst_len = (u32)(hw->blk[block_id].es.count * + hw->blk[block_id].es.fvw) * + sizeof(*hw->blk[block_id].es.t); + break; + default: + return; + } + + /* if the section offset exceeds destination length, terminate + * table fill. + */ + if (offset > dst_len) + return; + + /* if the sum of section size and offset exceed destination size + * then we are out of bounds of the HW table size for that PF. + * Changing section length to fill the remaining table space + * of that PF. + */ + if ((offset + sect_len) > dst_len) + sect_len = dst_len - offset; + + memcpy(dst + offset, src, sect_len); + offset += sect_len; + sect = ice_pkg_enum_section(NULL, &state, sid); + } +} + +/** + * ice_fill_blk_tbls - Read package context for tables + * @hw: pointer to the hardware structure + * + * Reads the current package contents and populates the driver + * database with the data iteratively for all advanced feature + * blocks. Assume that the HW tables have been allocated. + */ +void ice_fill_blk_tbls(struct ice_hw *hw) +{ + u8 i; + + for (i = 0; i < ICE_BLK_COUNT; i++) { + enum ice_block blk_id = (enum ice_block)i; + + ice_fill_tbl(hw, blk_id, hw->blk[blk_id].xlt1.sid); + ice_fill_tbl(hw, blk_id, hw->blk[blk_id].xlt2.sid); + ice_fill_tbl(hw, blk_id, hw->blk[blk_id].prof.sid); + ice_fill_tbl(hw, blk_id, hw->blk[blk_id].prof_redir.sid); + ice_fill_tbl(hw, blk_id, hw->blk[blk_id].es.sid); + } + + ice_init_sw_db(hw); +} + +/** + * ice_free_hw_tbls - free hardware table memory + * @hw: pointer to the hardware structure + */ +void ice_free_hw_tbls(struct ice_hw *hw) +{ + u8 i; + + for (i = 0; i < ICE_BLK_COUNT; i++) { + hw->blk[i].is_list_init = false; + + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt1.ptypes); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt1.ptg_tbl); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt1.t); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt2.t); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt2.vsig_tbl); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].xlt2.vsis); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].prof.t); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].prof_redir.t); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.t); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.ref_count); + devm_kfree(ice_hw_to_dev(hw), hw->blk[i].es.written); + } + + memset(hw->blk, 0, sizeof(hw->blk)); +} + +/** + * ice_clear_hw_tbls - clear HW tables and flow profiles + * @hw: pointer to the hardware structure + */ +void ice_clear_hw_tbls(struct ice_hw *hw) +{ + u8 i; + + for (i = 0; i < ICE_BLK_COUNT; i++) { + struct ice_prof_redir *prof_redir = &hw->blk[i].prof_redir; + struct ice_prof_tcam *prof = &hw->blk[i].prof; + struct ice_xlt1 *xlt1 = &hw->blk[i].xlt1; + struct ice_xlt2 *xlt2 = &hw->blk[i].xlt2; + struct ice_es *es = &hw->blk[i].es; + + memset(xlt1->ptypes, 0, xlt1->count * sizeof(*xlt1->ptypes)); + memset(xlt1->ptg_tbl, 0, + ICE_MAX_PTGS * sizeof(*xlt1->ptg_tbl)); + memset(xlt1->t, 0, xlt1->count * sizeof(*xlt1->t)); + + memset(xlt2->vsis, 0, xlt2->count * sizeof(*xlt2->vsis)); + memset(xlt2->vsig_tbl, 0, + xlt2->count * sizeof(*xlt2->vsig_tbl)); + memset(xlt2->t, 0, xlt2->count * sizeof(*xlt2->t)); + + memset(prof->t, 0, prof->count * sizeof(*prof->t)); + memset(prof_redir->t, 0, + prof_redir->count * sizeof(*prof_redir->t)); + + memset(es->t, 0, es->count * sizeof(*es->t)); + memset(es->ref_count, 0, es->count * sizeof(*es->ref_count)); + memset(es->written, 0, es->count * sizeof(*es->written)); + } +} + +/** + * ice_init_hw_tbls - init hardware table memory + * @hw: pointer to the hardware structure + */ +enum ice_status ice_init_hw_tbls(struct ice_hw *hw) +{ + u8 i; + + for (i = 0; i < ICE_BLK_COUNT; i++) { + struct ice_prof_redir *prof_redir = &hw->blk[i].prof_redir; + struct ice_prof_tcam *prof = &hw->blk[i].prof; + struct ice_xlt1 *xlt1 = &hw->blk[i].xlt1; + struct ice_xlt2 *xlt2 = &hw->blk[i].xlt2; + struct ice_es *es = &hw->blk[i].es; + u16 j; + + if (hw->blk[i].is_list_init) + continue; + + hw->blk[i].is_list_init = true; + + hw->blk[i].overwrite = blk_sizes[i].overwrite; + es->reverse = blk_sizes[i].reverse; + + xlt1->sid = ice_blk_sids[i][ICE_SID_XLT1_OFF]; + xlt1->count = blk_sizes[i].xlt1; + + xlt1->ptypes = devm_kcalloc(ice_hw_to_dev(hw), xlt1->count, + sizeof(*xlt1->ptypes), GFP_KERNEL); + + if (!xlt1->ptypes) + goto err; + + xlt1->ptg_tbl = devm_kcalloc(ice_hw_to_dev(hw), ICE_MAX_PTGS, + sizeof(*xlt1->ptg_tbl), + GFP_KERNEL); + + if (!xlt1->ptg_tbl) + goto err; + + xlt1->t = devm_kcalloc(ice_hw_to_dev(hw), xlt1->count, + sizeof(*xlt1->t), GFP_KERNEL); + if (!xlt1->t) + goto err; + + xlt2->sid = ice_blk_sids[i][ICE_SID_XLT2_OFF]; + xlt2->count = blk_sizes[i].xlt2; + + xlt2->vsis = devm_kcalloc(ice_hw_to_dev(hw), xlt2->count, + sizeof(*xlt2->vsis), GFP_KERNEL); + + if (!xlt2->vsis) + goto err; + + xlt2->vsig_tbl = devm_kcalloc(ice_hw_to_dev(hw), xlt2->count, + sizeof(*xlt2->vsig_tbl), + GFP_KERNEL); + if (!xlt2->vsig_tbl) + goto err; + + for (j = 0; j < xlt2->count; j++) + INIT_LIST_HEAD(&xlt2->vsig_tbl[j].prop_lst); + + xlt2->t = devm_kcalloc(ice_hw_to_dev(hw), xlt2->count, + sizeof(*xlt2->t), GFP_KERNEL); + if (!xlt2->t) + goto err; + + prof->sid = ice_blk_sids[i][ICE_SID_PR_OFF]; + prof->count = blk_sizes[i].prof_tcam; + prof->max_prof_id = blk_sizes[i].prof_id; + prof->cdid_bits = blk_sizes[i].prof_cdid_bits; + prof->t = devm_kcalloc(ice_hw_to_dev(hw), prof->count, + sizeof(*prof->t), GFP_KERNEL); + + if (!prof->t) + goto err; + + prof_redir->sid = ice_blk_sids[i][ICE_SID_PR_REDIR_OFF]; + prof_redir->count = blk_sizes[i].prof_redir; + prof_redir->t = devm_kcalloc(ice_hw_to_dev(hw), + prof_redir->count, + sizeof(*prof_redir->t), + GFP_KERNEL); + + if (!prof_redir->t) + goto err; + + es->sid = ice_blk_sids[i][ICE_SID_ES_OFF]; + es->count = blk_sizes[i].es; + es->fvw = blk_sizes[i].fvw; + es->t = devm_kcalloc(ice_hw_to_dev(hw), + (u32)(es->count * es->fvw), + sizeof(*es->t), GFP_KERNEL); + if (!es->t) + goto err; + + es->ref_count = devm_kcalloc(ice_hw_to_dev(hw), es->count, + sizeof(*es->ref_count), + GFP_KERNEL); + + es->written = devm_kcalloc(ice_hw_to_dev(hw), es->count, + sizeof(*es->written), GFP_KERNEL); + if (!es->ref_count) + goto err; + } + return 0; + +err: + ice_free_hw_tbls(hw); + return ICE_ERR_NO_MEMORY; +} diff --git a/drivers/net/ethernet/intel/ice/ice_flex_pipe.h b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h new file mode 100644 index 000000000000..37eb282742d1 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_flex_pipe.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019, Intel Corporation. */ + +#ifndef _ICE_FLEX_PIPE_H_ +#define _ICE_FLEX_PIPE_H_ + +#include "ice_type.h" + +/* Package minimal version supported */ +#define ICE_PKG_SUPP_VER_MAJ 1 +#define ICE_PKG_SUPP_VER_MNR 3 + +/* Package format version */ +#define ICE_PKG_FMT_VER_MAJ 1 +#define ICE_PKG_FMT_VER_MNR 0 +#define ICE_PKG_FMT_VER_UPD 0 +#define ICE_PKG_FMT_VER_DFT 0 + +#define ICE_PKG_CNT 4 + +enum ice_status ice_init_pkg(struct ice_hw *hw, u8 *buff, u32 len); +enum ice_status +ice_copy_and_init_pkg(struct ice_hw *hw, const u8 *buf, u32 len); +enum ice_status ice_init_hw_tbls(struct ice_hw *hw); +void ice_free_seg(struct ice_hw *hw); +void ice_fill_blk_tbls(struct ice_hw *hw); +void ice_clear_hw_tbls(struct ice_hw *hw); +void ice_free_hw_tbls(struct ice_hw *hw); +#endif /* _ICE_FLEX_PIPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_flex_type.h b/drivers/net/ethernet/intel/ice/ice_flex_type.h new file mode 100644 index 000000000000..5d5a7eaffa30 --- /dev/null +++ b/drivers/net/ethernet/intel/ice/ice_flex_type.h @@ -0,0 +1,374 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019, Intel Corporation. */ + +#ifndef _ICE_FLEX_TYPE_H_ +#define _ICE_FLEX_TYPE_H_ +/* Extraction Sequence (Field Vector) Table */ +struct ice_fv_word { + u8 prot_id; + u16 off; /* Offset within the protocol header */ + u8 resvrd; +} __packed; + +#define ICE_MAX_FV_WORDS 48 +struct ice_fv { + struct ice_fv_word ew[ICE_MAX_FV_WORDS]; +}; + +/* Package and segment headers and tables */ +struct ice_pkg_hdr { + struct ice_pkg_ver format_ver; + __le32 seg_count; + __le32 seg_offset[1]; +}; + +/* generic segment */ +struct ice_generic_seg_hdr { +#define SEGMENT_TYPE_METADATA 0x00000001 +#define SEGMENT_TYPE_ICE 0x00000010 + __le32 seg_type; + struct ice_pkg_ver seg_ver; + __le32 seg_size; + char seg_name[ICE_PKG_NAME_SIZE]; +}; + +/* ice specific segment */ + +union ice_device_id { + struct { + __le16 device_id; + __le16 vendor_id; + } dev_vend_id; + __le32 id; +}; + +struct ice_device_id_entry { + union ice_device_id device; + union ice_device_id sub_device; +}; + +struct ice_seg { + struct ice_generic_seg_hdr hdr; + __le32 device_table_count; + struct ice_device_id_entry device_table[1]; +}; + +struct ice_nvm_table { + __le32 table_count; + __le32 vers[1]; +}; + +struct ice_buf { +#define ICE_PKG_BUF_SIZE 4096 + u8 buf[ICE_PKG_BUF_SIZE]; +}; + +struct ice_buf_table { + __le32 buf_count; + struct ice_buf buf_array[1]; +}; + +/* global metadata specific segment */ +struct ice_global_metadata_seg { + struct ice_generic_seg_hdr hdr; + struct ice_pkg_ver pkg_ver; + __le32 track_id; + char pkg_name[ICE_PKG_NAME_SIZE]; +}; + +#define ICE_MIN_S_OFF 12 +#define ICE_MAX_S_OFF 4095 +#define ICE_MIN_S_SZ 1 +#define ICE_MAX_S_SZ 4084 + +/* section information */ +struct ice_section_entry { + __le32 type; + __le16 offset; + __le16 size; +}; + +#define ICE_MIN_S_COUNT 1 +#define ICE_MAX_S_COUNT 511 +#define ICE_MIN_S_DATA_END 12 +#define ICE_MAX_S_DATA_END 4096 + +#define ICE_METADATA_BUF 0x80000000 + +struct ice_buf_hdr { + __le16 section_count; + __le16 data_end; + struct ice_section_entry section_entry[1]; +}; + +#define ICE_MAX_ENTRIES_IN_BUF(hd_sz, ent_sz) ((ICE_PKG_BUF_SIZE - \ + sizeof(struct ice_buf_hdr) - (hd_sz)) / (ent_sz)) + +/* ice package section IDs */ +#define ICE_SID_XLT1_SW 12 +#define ICE_SID_XLT2_SW 13 +#define ICE_SID_PROFID_TCAM_SW 14 +#define ICE_SID_PROFID_REDIR_SW 15 +#define ICE_SID_FLD_VEC_SW 16 + +#define ICE_SID_XLT1_ACL 22 +#define ICE_SID_XLT2_ACL 23 +#define ICE_SID_PROFID_TCAM_ACL 24 +#define ICE_SID_PROFID_REDIR_ACL 25 +#define ICE_SID_FLD_VEC_ACL 26 + +#define ICE_SID_XLT1_FD 32 +#define ICE_SID_XLT2_FD 33 +#define ICE_SID_PROFID_TCAM_FD 34 +#define ICE_SID_PROFID_REDIR_FD 35 +#define ICE_SID_FLD_VEC_FD 36 + +#define ICE_SID_XLT1_RSS 42 +#define ICE_SID_XLT2_RSS 43 +#define ICE_SID_PROFID_TCAM_RSS 44 +#define ICE_SID_PROFID_REDIR_RSS 45 +#define ICE_SID_FLD_VEC_RSS 46 + +#define ICE_SID_RXPARSER_BOOST_TCAM 56 + +#define ICE_SID_XLT1_PE 82 +#define ICE_SID_XLT2_PE 83 +#define ICE_SID_PROFID_TCAM_PE 84 +#define ICE_SID_PROFID_REDIR_PE 85 +#define ICE_SID_FLD_VEC_PE 86 + +/* Label Metadata section IDs */ +#define ICE_SID_LBL_FIRST 0x80000010 +#define ICE_SID_LBL_RXPARSER_TMEM 0x80000018 +/* The following define MUST be updated to reflect the last label section ID */ +#define ICE_SID_LBL_LAST 0x80000038 + +enum ice_block { + ICE_BLK_SW = 0, + ICE_BLK_ACL, + ICE_BLK_FD, + ICE_BLK_RSS, + ICE_BLK_PE, + ICE_BLK_COUNT +}; + +/* package labels */ +struct ice_label { + __le16 value; +#define ICE_PKG_LABEL_SIZE 64 + char name[ICE_PKG_LABEL_SIZE]; +}; + +struct ice_label_section { + __le16 count; + struct ice_label label[1]; +}; + +#define ICE_MAX_LABELS_IN_BUF ICE_MAX_ENTRIES_IN_BUF( \ + sizeof(struct ice_label_section) - sizeof(struct ice_label), \ + sizeof(struct ice_label)) + +struct ice_sw_fv_section { + __le16 count; + __le16 base_offset; + struct ice_fv fv[1]; +}; + +/* The BOOST TCAM stores the match packet header in reverse order, meaning + * the fields are reversed; in addition, this means that the normally big endian + * fields of the packet are now little endian. + */ +struct ice_boost_key_value { +#define ICE_BOOST_REMAINING_HV_KEY 15 + u8 remaining_hv_key[ICE_BOOST_REMAINING_HV_KEY]; + __le16 hv_dst_port_key; + __le16 hv_src_port_key; + u8 tcam_search_key; +} __packed; + +struct ice_boost_key { + struct ice_boost_key_value key; + struct ice_boost_key_value key2; +}; + +/* package Boost TCAM entry */ +struct ice_boost_tcam_entry { + __le16 addr; + __le16 reserved; + /* break up the 40 bytes of key into different fields */ + struct ice_boost_key key; + u8 boost_hit_index_group; + /* The following contains bitfields which are not on byte boundaries. + * These fields are currently unused by driver software. + */ +#define ICE_BOOST_BIT_FIELDS 43 + u8 bit_fields[ICE_BOOST_BIT_FIELDS]; +}; + +struct ice_boost_tcam_section { + __le16 count; + __le16 reserved; + struct ice_boost_tcam_entry tcam[1]; +}; + +#define ICE_MAX_BST_TCAMS_IN_BUF ICE_MAX_ENTRIES_IN_BUF( \ + sizeof(struct ice_boost_tcam_section) - \ + sizeof(struct ice_boost_tcam_entry), \ + sizeof(struct ice_boost_tcam_entry)) + +struct ice_xlt1_section { + __le16 count; + __le16 offset; + u8 value[1]; +} __packed; + +struct ice_xlt2_section { + __le16 count; + __le16 offset; + __le16 value[1]; +}; + +struct ice_prof_redir_section { + __le16 count; + __le16 offset; + u8 redir_value[1]; +}; + +struct ice_pkg_enum { + struct ice_buf_table *buf_table; + u32 buf_idx; + + u32 type; + struct ice_buf_hdr *buf; + u32 sect_idx; + void *sect; + u32 sect_type; + + u32 entry_idx; + void *(*handler)(u32 sect_type, void *section, u32 index, u32 *offset); +}; + +struct ice_es { + u32 sid; + u16 count; + u16 fvw; + u16 *ref_count; + struct list_head prof_map; + struct ice_fv_word *t; + struct mutex prof_map_lock; /* protect access to profiles list */ + u8 *written; + u8 reverse; /* set to true to reverse FV order */ +}; + +/* PTYPE Group management */ + +/* Note: XLT1 table takes 13-bit as input, and results in an 8-bit packet type + * group (PTG) ID as output. + * + * Note: PTG 0 is the default packet type group and it is assumed that all PTYPE + * are a part of this group until moved to a new PTG. + */ +#define ICE_DEFAULT_PTG 0 + +struct ice_ptg_entry { + struct ice_ptg_ptype *first_ptype; + u8 in_use; +}; + +struct ice_ptg_ptype { + struct ice_ptg_ptype *next_ptype; + u8 ptg; +}; + +struct ice_vsig_entry { + struct list_head prop_lst; + struct ice_vsig_vsi *first_vsi; + u8 in_use; +}; + +struct ice_vsig_vsi { + struct ice_vsig_vsi *next_vsi; + u32 prop_mask; + u16 changed; + u16 vsig; +}; + +#define ICE_XLT1_CNT 1024 +#define ICE_MAX_PTGS 256 + +/* XLT1 Table */ +struct ice_xlt1 { + struct ice_ptg_entry *ptg_tbl; + struct ice_ptg_ptype *ptypes; + u8 *t; + u32 sid; + u16 count; +}; + +#define ICE_XLT2_CNT 768 +#define ICE_MAX_VSIGS 768 + +/* VSIG bit layout: + * [0:12]: incremental VSIG index 1 to ICE_MAX_VSIGS + * [13:15]: PF number of device + */ +#define ICE_VSIG_IDX_M (0x1FFF) +#define ICE_PF_NUM_S 13 +#define ICE_PF_NUM_M (0x07 << ICE_PF_NUM_S) +#define ICE_VSIG_VALUE(vsig, pf_id) \ + (u16)((((u16)(vsig)) & ICE_VSIG_IDX_M) | \ + (((u16)(pf_id) << ICE_PF_NUM_S) & ICE_PF_NUM_M)) +#define ICE_DEFAULT_VSIG 0 + +/* XLT2 Table */ +struct ice_xlt2 { + struct ice_vsig_entry *vsig_tbl; + struct ice_vsig_vsi *vsis; + u16 *t; + u32 sid; + u16 count; +}; + +/* Keys are made up of two values, each one-half the size of the key. + * For TCAM, the entire key is 80 bits wide (or 2, 40-bit wide values) + */ +#define ICE_TCAM_KEY_VAL_SZ 5 +#define ICE_TCAM_KEY_SZ (2 * ICE_TCAM_KEY_VAL_SZ) + +struct ice_prof_tcam_entry { + __le16 addr; + u8 key[ICE_TCAM_KEY_SZ]; + u8 prof_id; +} __packed; + +struct ice_prof_id_section { + __le16 count; + struct ice_prof_tcam_entry entry[1]; +} __packed; + +struct ice_prof_tcam { + u32 sid; + u16 count; + u16 max_prof_id; + struct ice_prof_tcam_entry *t; + u8 cdid_bits; /* # CDID bits to use in key, 0, 2, 4, or 8 */ +}; + +struct ice_prof_redir { + u8 *t; + u32 sid; + u16 count; +}; + +/* Tables per block */ +struct ice_blk_info { + struct ice_xlt1 xlt1; + struct ice_xlt2 xlt2; + struct ice_prof_tcam prof; + struct ice_prof_redir prof_redir; + struct ice_es es; + u8 overwrite; /* set to true to allow overwrite of table entries */ + u8 is_list_init; +}; + +#endif /* _ICE_FLEX_TYPE_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h index 6c5ce05742b1..152fbd556e9b 100644 --- a/drivers/net/ethernet/intel/ice/ice_hw_autogen.h +++ b/drivers/net/ethernet/intel/ice/ice_hw_autogen.h @@ -55,6 +55,8 @@ #define PRTDCB_GENS 0x00083020 #define PRTDCB_GENS_DCBX_STATUS_S 0 #define PRTDCB_GENS_DCBX_STATUS_M ICE_M(0x7, 0) +#define GL_PREEXT_L2_PMASK0(_i) (0x0020F0FC + ((_i) * 4)) +#define GL_PREEXT_L2_PMASK1(_i) (0x0020F108 + ((_i) * 4)) #define GLFLXP_RXDID_FLAGS(_i, _j) (0x0045D000 + ((_i) * 4 + (_j) * 256)) #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_S 0 #define GLFLXP_RXDID_FLAGS_FLEXIFLAG_4N_M ICE_M(0x3F, 0) @@ -127,8 +129,11 @@ #define GLINT_DYN_CTL_CLEARPBA_M BIT(1) #define GLINT_DYN_CTL_SWINT_TRIG_M BIT(2) #define GLINT_DYN_CTL_ITR_INDX_S 3 +#define GLINT_DYN_CTL_ITR_INDX_M ICE_M(0x3, 3) #define GLINT_DYN_CTL_INTERVAL_S 5 +#define GLINT_DYN_CTL_INTERVAL_M ICE_M(0xFFF, 5) #define GLINT_DYN_CTL_SW_ITR_INDX_M ICE_M(0x3, 25) +#define GLINT_DYN_CTL_WB_ON_ITR_M BIT(30) #define GLINT_DYN_CTL_INTENA_MSK_M BIT(31) #define GLINT_ITR(_i, _INT) (0x00154000 + ((_i) * 8192 + (_INT) * 4)) #define GLINT_RATE(_INT) (0x0015A000 + ((_INT) * 4)) @@ -281,14 +286,10 @@ #define GL_PWR_MODE_CTL 0x000B820C #define GL_PWR_MODE_CTL_CAR_MAX_BW_S 30 #define GL_PWR_MODE_CTL_CAR_MAX_BW_M ICE_M(0x3, 30) -#define GLPRT_BPRCH(_i) (0x00381384 + ((_i) * 8)) #define GLPRT_BPRCL(_i) (0x00381380 + ((_i) * 8)) -#define GLPRT_BPTCH(_i) (0x00381244 + ((_i) * 8)) #define GLPRT_BPTCL(_i) (0x00381240 + ((_i) * 8)) #define GLPRT_CRCERRS(_i) (0x00380100 + ((_i) * 8)) -#define GLPRT_GORCH(_i) (0x00380004 + ((_i) * 8)) #define GLPRT_GORCL(_i) (0x00380000 + ((_i) * 8)) -#define GLPRT_GOTCH(_i) (0x00380B44 + ((_i) * 8)) #define GLPRT_GOTCL(_i) (0x00380B40 + ((_i) * 8)) #define GLPRT_ILLERRC(_i) (0x003801C0 + ((_i) * 8)) #define GLPRT_LXOFFRXC(_i) (0x003802C0 + ((_i) * 8)) @@ -296,38 +297,22 @@ #define GLPRT_LXONRXC(_i) (0x00380280 + ((_i) * 8)) #define GLPRT_LXONTXC(_i) (0x00381140 + ((_i) * 8)) #define GLPRT_MLFC(_i) (0x00380040 + ((_i) * 8)) -#define GLPRT_MPRCH(_i) (0x00381344 + ((_i) * 8)) #define GLPRT_MPRCL(_i) (0x00381340 + ((_i) * 8)) -#define GLPRT_MPTCH(_i) (0x00381204 + ((_i) * 8)) #define GLPRT_MPTCL(_i) (0x00381200 + ((_i) * 8)) #define GLPRT_MRFC(_i) (0x00380080 + ((_i) * 8)) -#define GLPRT_PRC1023H(_i) (0x00380A04 + ((_i) * 8)) #define GLPRT_PRC1023L(_i) (0x00380A00 + ((_i) * 8)) -#define GLPRT_PRC127H(_i) (0x00380944 + ((_i) * 8)) #define GLPRT_PRC127L(_i) (0x00380940 + ((_i) * 8)) -#define GLPRT_PRC1522H(_i) (0x00380A44 + ((_i) * 8)) #define GLPRT_PRC1522L(_i) (0x00380A40 + ((_i) * 8)) -#define GLPRT_PRC255H(_i) (0x00380984 + ((_i) * 8)) #define GLPRT_PRC255L(_i) (0x00380980 + ((_i) * 8)) -#define GLPRT_PRC511H(_i) (0x003809C4 + ((_i) * 8)) #define GLPRT_PRC511L(_i) (0x003809C0 + ((_i) * 8)) -#define GLPRT_PRC64H(_i) (0x00380904 + ((_i) * 8)) #define GLPRT_PRC64L(_i) (0x00380900 + ((_i) * 8)) -#define GLPRT_PRC9522H(_i) (0x00380A84 + ((_i) * 8)) #define GLPRT_PRC9522L(_i) (0x00380A80 + ((_i) * 8)) -#define GLPRT_PTC1023H(_i) (0x00380C84 + ((_i) * 8)) #define GLPRT_PTC1023L(_i) (0x00380C80 + ((_i) * 8)) -#define GLPRT_PTC127H(_i) (0x00380BC4 + ((_i) * 8)) #define GLPRT_PTC127L(_i) (0x00380BC0 + ((_i) * 8)) -#define GLPRT_PTC1522H(_i) (0x00380CC4 + ((_i) * 8)) #define GLPRT_PTC1522L(_i) (0x00380CC0 + ((_i) * 8)) -#define GLPRT_PTC255H(_i) (0x00380C04 + ((_i) * 8)) #define GLPRT_PTC255L(_i) (0x00380C00 + ((_i) * 8)) -#define GLPRT_PTC511H(_i) (0x00380C44 + ((_i) * 8)) #define GLPRT_PTC511L(_i) (0x00380C40 + ((_i) * 8)) -#define GLPRT_PTC64H(_i) (0x00380B84 + ((_i) * 8)) #define GLPRT_PTC64L(_i) (0x00380B80 + ((_i) * 8)) -#define GLPRT_PTC9522H(_i) (0x00380D04 + ((_i) * 8)) #define GLPRT_PTC9522L(_i) (0x00380D00 + ((_i) * 8)) #define GLPRT_PXOFFRXC(_i, _j) (0x00380500 + ((_i) * 8 + (_j) * 64)) #define GLPRT_PXOFFTXC(_i, _j) (0x00380F40 + ((_i) * 8 + (_j) * 64)) @@ -340,32 +325,23 @@ #define GLPRT_RUC(_i) (0x00380200 + ((_i) * 8)) #define GLPRT_RXON2OFFCNT(_i, _j) (0x00380700 + ((_i) * 8 + (_j) * 64)) #define GLPRT_TDOLD(_i) (0x00381280 + ((_i) * 8)) -#define GLPRT_UPRCH(_i) (0x00381304 + ((_i) * 8)) #define GLPRT_UPRCL(_i) (0x00381300 + ((_i) * 8)) -#define GLPRT_UPTCH(_i) (0x003811C4 + ((_i) * 8)) #define GLPRT_UPTCL(_i) (0x003811C0 + ((_i) * 8)) -#define GLV_BPRCH(_i) (0x003B6004 + ((_i) * 8)) #define GLV_BPRCL(_i) (0x003B6000 + ((_i) * 8)) -#define GLV_BPTCH(_i) (0x0030E004 + ((_i) * 8)) #define GLV_BPTCL(_i) (0x0030E000 + ((_i) * 8)) -#define GLV_GORCH(_i) (0x003B0004 + ((_i) * 8)) #define GLV_GORCL(_i) (0x003B0000 + ((_i) * 8)) -#define GLV_GOTCH(_i) (0x00300004 + ((_i) * 8)) #define GLV_GOTCL(_i) (0x00300000 + ((_i) * 8)) -#define GLV_MPRCH(_i) (0x003B4004 + ((_i) * 8)) #define GLV_MPRCL(_i) (0x003B4000 + ((_i) * 8)) -#define GLV_MPTCH(_i) (0x0030C004 + ((_i) * 8)) #define GLV_MPTCL(_i) (0x0030C000 + ((_i) * 8)) #define GLV_RDPC(_i) (0x00294C04 + ((_i) * 4)) #define GLV_TEPC(_VSI) (0x00312000 + ((_VSI) * 4)) -#define GLV_UPRCH(_i) (0x003B2004 + ((_i) * 8)) #define GLV_UPRCL(_i) (0x003B2000 + ((_i) * 8)) -#define GLV_UPTCH(_i) (0x0030A004 + ((_i) * 8)) #define GLV_UPTCL(_i) (0x0030A000 + ((_i) * 8)) #define PF_VT_PFALLOC_HIF 0x0009DD80 #define VSIQF_HKEY_MAX_INDEX 12 #define VSIQF_HLUT_MAX_INDEX 15 #define VFINT_DYN_CTLN(_i) (0x00003800 + ((_i) * 4)) #define VFINT_DYN_CTLN_CLEARPBA_M BIT(1) +#define PRTRPB_RDPC 0x000AC260 #endif /* _ICE_HW_AUTOGEN_H_ */ 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 510a8c900e61..2aac8f13daeb 100644 --- a/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h +++ b/drivers/net/ethernet/intel/ice/ice_lan_tx_rx.h @@ -290,6 +290,7 @@ struct ice_rlan_ctx { u8 tphdata_ena; u8 tphhead_ena; u16 lrxqthresh; /* bigger than needed, see above for reason */ + u8 prefena; /* NOTE: normally must be set to 1 at init */ }; struct ice_ctx_ele { @@ -427,6 +428,7 @@ struct ice_tlan_ctx { #define ICE_TLAN_CTX_VMVF_TYPE_PF 2 u16 src_vsi; u8 tsyn_ena; + u8 internal_usage_flag; u8 alt_vlan; u16 cpuid; /* bigger than needed, see above for reason */ u8 wb_mode; diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index a19f5920733b..cc755382df25 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -191,41 +191,58 @@ static int ice_pf_rxq_wait(struct ice_pf *pf, int pf_q, bool ena) } /** - * ice_vsi_ctrl_rx_rings - Start or stop a VSI's Rx rings + * ice_vsi_ctrl_rx_ring - Start or stop a VSI's Rx ring * @vsi: the VSI being configured * @ena: start or stop the Rx rings + * @rxq_idx: Rx queue index */ -static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena) +#ifndef CONFIG_PCI_IOV +static +#endif /* !CONFIG_PCI_IOV */ +int ice_vsi_ctrl_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx) { + int pf_q = vsi->rxq_map[rxq_idx]; struct ice_pf *pf = vsi->back; struct ice_hw *hw = &pf->hw; - int i, ret = 0; + int ret = 0; + u32 rx_reg; - for (i = 0; i < vsi->num_rxq; i++) { - int pf_q = vsi->rxq_map[i]; - u32 rx_reg; + rx_reg = rd32(hw, QRX_CTRL(pf_q)); - rx_reg = rd32(hw, QRX_CTRL(pf_q)); + /* Skip if the queue is already in the requested state */ + if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M)) + return 0; - /* Skip if the queue is already in the requested state */ - if (ena == !!(rx_reg & QRX_CTRL_QENA_STAT_M)) - continue; + /* turn on/off the queue */ + if (ena) + rx_reg |= QRX_CTRL_QENA_REQ_M; + else + rx_reg &= ~QRX_CTRL_QENA_REQ_M; + wr32(hw, QRX_CTRL(pf_q), rx_reg); - /* turn on/off the queue */ - if (ena) - rx_reg |= QRX_CTRL_QENA_REQ_M; - else - rx_reg &= ~QRX_CTRL_QENA_REQ_M; - wr32(hw, QRX_CTRL(pf_q), rx_reg); - - /* wait for the change to finish */ - ret = ice_pf_rxq_wait(pf, pf_q, ena); - if (ret) { - dev_err(&pf->pdev->dev, - "VSI idx %d Rx ring %d %sable timeout\n", - vsi->idx, pf_q, (ena ? "en" : "dis")); + /* wait for the change to finish */ + ret = ice_pf_rxq_wait(pf, pf_q, ena); + if (ret) + dev_err(&pf->pdev->dev, + "VSI idx %d Rx ring %d %sable timeout\n", + vsi->idx, pf_q, (ena ? "en" : "dis")); + + return ret; +} + +/** + * ice_vsi_ctrl_rx_rings - Start or stop a VSI's Rx rings + * @vsi: the VSI being configured + * @ena: start or stop the Rx rings + */ +static int ice_vsi_ctrl_rx_rings(struct ice_vsi *vsi, bool ena) +{ + int i, ret = 0; + + for (i = 0; i < vsi->num_rxq; i++) { + ret = ice_vsi_ctrl_rx_ring(vsi, ena, i); + if (ret) break; - } } return ret; @@ -246,12 +263,24 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) vsi->tx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq, sizeof(*vsi->tx_rings), GFP_KERNEL); if (!vsi->tx_rings) - goto err_txrings; + return -ENOMEM; vsi->rx_rings = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq, sizeof(*vsi->rx_rings), GFP_KERNEL); if (!vsi->rx_rings) - goto err_rxrings; + goto err_rings; + + vsi->txq_map = devm_kcalloc(&pf->pdev->dev, vsi->alloc_txq, + sizeof(*vsi->txq_map), GFP_KERNEL); + + if (!vsi->txq_map) + goto err_txq_map; + + vsi->rxq_map = devm_kcalloc(&pf->pdev->dev, vsi->alloc_rxq, + sizeof(*vsi->rxq_map), GFP_KERNEL); + if (!vsi->rxq_map) + goto err_rxq_map; + /* There is no need to allocate q_vectors for a loopback VSI. */ if (vsi->type == ICE_VSI_LB) @@ -266,10 +295,13 @@ static int ice_vsi_alloc_arrays(struct ice_vsi *vsi) return 0; err_vectors: + devm_kfree(&pf->pdev->dev, vsi->rxq_map); +err_rxq_map: + devm_kfree(&pf->pdev->dev, vsi->txq_map); +err_txq_map: devm_kfree(&pf->pdev->dev, vsi->rx_rings); -err_rxrings: +err_rings: devm_kfree(&pf->pdev->dev, vsi->tx_rings); -err_txrings: return -ENOMEM; } @@ -311,9 +343,21 @@ static void ice_vsi_set_num_qs(struct ice_vsi *vsi, u16 vf_id) switch (vsi->type) { case ICE_VSI_PF: - vsi->alloc_txq = pf->num_lan_tx; - vsi->alloc_rxq = pf->num_lan_rx; - vsi->num_q_vectors = max_t(int, pf->num_lan_rx, pf->num_lan_tx); + vsi->alloc_txq = min_t(int, ice_get_avail_txq_count(pf), + num_online_cpus()); + + pf->num_lan_tx = vsi->alloc_txq; + + /* only 1 Rx queue unless RSS is enabled */ + if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) + vsi->alloc_rxq = 1; + else + vsi->alloc_rxq = min_t(int, ice_get_avail_rxq_count(pf), + num_online_cpus()); + + pf->num_lan_rx = vsi->alloc_rxq; + + vsi->num_q_vectors = max_t(int, vsi->alloc_rxq, vsi->alloc_txq); break; case ICE_VSI_VF: vf = &pf->vf[vsi->vf_id]; @@ -416,6 +460,14 @@ static void ice_vsi_free_arrays(struct ice_vsi *vsi) devm_kfree(&pf->pdev->dev, vsi->rx_rings); vsi->rx_rings = NULL; } + if (vsi->txq_map) { + devm_kfree(&pf->pdev->dev, vsi->txq_map); + vsi->txq_map = NULL; + } + if (vsi->rxq_map) { + devm_kfree(&pf->pdev->dev, vsi->rxq_map); + vsi->rxq_map = NULL; + } } /** @@ -508,8 +560,8 @@ ice_vsi_alloc(struct ice_pf *pf, enum ice_vsi_type type, u16 vf_id) vsi->type = type; vsi->back = pf; set_bit(__ICE_DOWN, vsi->state); + vsi->idx = pf->next_vsi; - vsi->work_lmt = ICE_DFLT_IRQ_WORK; if (type == ICE_VSI_VF) ice_vsi_set_num_qs(vsi, vf_id); @@ -647,7 +699,7 @@ static int ice_vsi_get_qs(struct ice_vsi *vsi) struct ice_qs_cfg tx_qs_cfg = { .qs_mutex = &pf->avail_q_mutex, .pf_map = pf->avail_txqs, - .pf_map_size = ICE_MAX_TXQS, + .pf_map_size = pf->max_pf_txqs, .q_count = vsi->alloc_txq, .scatter_count = ICE_MAX_SCATTER_TXQS, .vsi_map = vsi->txq_map, @@ -657,7 +709,7 @@ static int ice_vsi_get_qs(struct ice_vsi *vsi) struct ice_qs_cfg rx_qs_cfg = { .qs_mutex = &pf->avail_q_mutex, .pf_map = pf->avail_rxqs, - .pf_map_size = ICE_MAX_RXQS, + .pf_map_size = pf->max_pf_rxqs, .q_count = vsi->alloc_rxq, .scatter_count = ICE_MAX_SCATTER_RXQS, .vsi_map = vsi->rxq_map, @@ -701,6 +753,17 @@ void ice_vsi_put_qs(struct ice_vsi *vsi) } /** + * ice_is_safe_mode + * @pf: pointer to the PF struct + * + * returns true if driver is in safe mode, false otherwise + */ +bool ice_is_safe_mode(struct ice_pf *pf) +{ + return !test_bit(ICE_FLAG_ADV_FEATURES, pf->flags); +} + +/** * ice_rss_clean - Delete RSS related VSI structures that hold user inputs * @vsi: the VSI being removed */ @@ -1010,6 +1073,13 @@ static int ice_vsi_init(struct ice_vsi *vsi) ICE_AQ_VSI_SEC_FLAG_ENA_MAC_ANTI_SPOOF; } + /* Allow control frames out of main VSI */ + if (vsi->type == ICE_VSI_PF) { + ctxt->info.sec_flags |= ICE_AQ_VSI_SEC_FLAG_ALLOW_DEST_OVRD; + ctxt->info.valid_sections |= + cpu_to_le16(ICE_AQ_VSI_PROP_SECURITY_VALID); + } + ret = ice_add_vsi(hw, vsi->idx, ctxt, NULL); if (ret) { dev_err(&pf->pdev->dev, @@ -1129,12 +1199,7 @@ static int ice_vsi_alloc_q_vectors(struct ice_vsi *vsi) return -EEXIST; } - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - num_q_vectors = vsi->num_q_vectors; - } else { - err = -EINVAL; - goto err_out; - } + num_q_vectors = vsi->num_q_vectors; for (v_idx = 0; v_idx < num_q_vectors; v_idx++) { err = ice_vsi_alloc_q_vector(vsi, v_idx); @@ -1180,9 +1245,6 @@ static int ice_vsi_setup_vector_base(struct ice_vsi *vsi) return -EEXIST; } - if (!test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - return -ENOENT; - num_q_vectors = vsi->num_q_vectors; /* reserve slots from OS requested IRQs */ vsi->base_vector = ice_get_res(pf, pf->irq_tracker, num_q_vectors, @@ -1477,40 +1539,32 @@ void ice_update_eth_stats(struct ice_vsi *vsi) prev_es = &vsi->eth_stats_prev; cur_es = &vsi->eth_stats; - ice_stat_update40(hw, GLV_GORCH(vsi_num), GLV_GORCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_bytes, - &cur_es->rx_bytes); + ice_stat_update40(hw, GLV_GORCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->rx_bytes, &cur_es->rx_bytes); - ice_stat_update40(hw, GLV_UPRCH(vsi_num), GLV_UPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_unicast, - &cur_es->rx_unicast); + ice_stat_update40(hw, GLV_UPRCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->rx_unicast, &cur_es->rx_unicast); - ice_stat_update40(hw, GLV_MPRCH(vsi_num), GLV_MPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_multicast, - &cur_es->rx_multicast); + ice_stat_update40(hw, GLV_MPRCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->rx_multicast, &cur_es->rx_multicast); - ice_stat_update40(hw, GLV_BPRCH(vsi_num), GLV_BPRCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->rx_broadcast, - &cur_es->rx_broadcast); + ice_stat_update40(hw, GLV_BPRCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->rx_broadcast, &cur_es->rx_broadcast); ice_stat_update32(hw, GLV_RDPC(vsi_num), vsi->stat_offsets_loaded, &prev_es->rx_discards, &cur_es->rx_discards); - ice_stat_update40(hw, GLV_GOTCH(vsi_num), GLV_GOTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_bytes, - &cur_es->tx_bytes); + ice_stat_update40(hw, GLV_GOTCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->tx_bytes, &cur_es->tx_bytes); - ice_stat_update40(hw, GLV_UPTCH(vsi_num), GLV_UPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_unicast, - &cur_es->tx_unicast); + ice_stat_update40(hw, GLV_UPTCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->tx_unicast, &cur_es->tx_unicast); - ice_stat_update40(hw, GLV_MPTCH(vsi_num), GLV_MPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_multicast, - &cur_es->tx_multicast); + ice_stat_update40(hw, GLV_MPTCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->tx_multicast, &cur_es->tx_multicast); - ice_stat_update40(hw, GLV_BPTCH(vsi_num), GLV_BPTCL(vsi_num), - vsi->stat_offsets_loaded, &prev_es->tx_broadcast, - &cur_es->tx_broadcast); + ice_stat_update40(hw, GLV_BPTCL(vsi_num), vsi->stat_offsets_loaded, + &prev_es->tx_broadcast, &cur_es->tx_broadcast); ice_stat_update32(hw, GLV_TEPC(vsi_num), vsi->stat_offsets_loaded, &prev_es->tx_errors, &cur_es->tx_errors); @@ -1658,6 +1712,62 @@ setup_rings: } /** + * ice_vsi_cfg_txq - Configure single Tx queue + * @vsi: the VSI that queue belongs to + * @ring: Tx ring to be configured + * @tc_q_idx: queue index within given TC + * @qg_buf: queue group buffer + * @tc: TC that Tx ring belongs to + */ +static int +ice_vsi_cfg_txq(struct ice_vsi *vsi, struct ice_ring *ring, u16 tc_q_idx, + struct ice_aqc_add_tx_qgrp *qg_buf, u8 tc) +{ + struct ice_tlan_ctx tlan_ctx = { 0 }; + struct ice_aqc_add_txqs_perq *txq; + struct ice_pf *pf = vsi->back; + u8 buf_len = sizeof(*qg_buf); + enum ice_status status; + u16 pf_q; + + pf_q = ring->reg_idx; + ice_setup_tx_ctx(ring, &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. + */ + ring->tail = pf->hw.hw_addr + QTX_COMM_DBELL(pf_q); + + /* Add unique software queue handle of the Tx queue per + * TC into the VSI Tx ring + */ + ring->q_handle = tc_q_idx; + + status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, ring->q_handle, + 1, qg_buf, buf_len, NULL); + if (status) { + dev_err(&pf->pdev->dev, + "Failed to set LAN Tx queue context, error: %d\n", + status); + return -ENODEV; + } + + /* 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)) + ring->txq_teid = le32_to_cpu(txq->q_teid); + + return 0; +} + +/** * ice_vsi_cfg_txqs - Configure the VSI for Tx * @vsi: the VSI being configured * @rings: Tx ring array to be configured @@ -1670,20 +1780,16 @@ static int ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, int offset) { 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; + u16 q_idx = 0, i; + int err = 0; + u8 tc; - buf_len = sizeof(*qg_buf); - qg_buf = devm_kzalloc(&pf->pdev->dev, buf_len, GFP_KERNEL); + qg_buf = devm_kzalloc(&pf->pdev->dev, sizeof(*qg_buf), GFP_KERNEL); if (!qg_buf) return -ENOMEM; qg_buf->num_txqs = 1; - num_q_grps = 1; /* set up and configure the Tx queues for each enabled TC */ ice_for_each_traffic_class(tc) { @@ -1691,39 +1797,10 @@ ice_vsi_cfg_txqs(struct ice_vsi *vsi, struct ice_ring **rings, int offset) break; 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 + offset]; - ice_setup_tx_ctx(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. - */ - rings[q_idx]->tail = - pf->hw.hw_addr + QTX_COMM_DBELL(pf_q); - status = ice_ena_vsi_txq(vsi->port_info, vsi->idx, tc, - i, num_q_grps, qg_buf, - buf_len, NULL); - if (status) { - dev_err(&pf->pdev->dev, - "Failed to set LAN Tx queue context, error: %d\n", - status); - err = -ENODEV; + err = ice_vsi_cfg_txq(vsi, rings[q_idx], i + offset, + qg_buf, tc); + if (err) 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)) - rings[q_idx]->txq_teid = - le32_to_cpu(txq->q_teid); q_idx++; } @@ -2070,45 +2147,112 @@ void ice_trigger_sw_intr(struct ice_hw *hw, struct ice_q_vector *q_vector) } /** - * ice_vsi_stop_tx_rings - Disable Tx rings + * ice_vsi_stop_tx_ring - Disable single Tx ring * @vsi: the VSI being configured * @rst_src: reset source * @rel_vmvf_num: Relative ID of VF/VM - * @rings: Tx ring array to be stopped - * @offset: offset within vsi->txq_map + * @ring: Tx ring to be stopped + * @txq_meta: Meta data of Tx ring to be stopped */ -static int -ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, - u16 rel_vmvf_num, struct ice_ring **rings, int offset) +#ifndef CONFIG_PCI_IOV +static +#endif /* !CONFIG_PCI_IOV */ +int +ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, + u16 rel_vmvf_num, struct ice_ring *ring, + struct ice_txq_meta *txq_meta) { struct ice_pf *pf = vsi->back; + struct ice_q_vector *q_vector; struct ice_hw *hw = &pf->hw; - int tc, q_idx = 0, err = 0; - u16 *q_ids, *q_handles, i; enum ice_status status; - u32 *q_teids, val; + u32 val; - if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS) - return -EINVAL; + /* clear cause_ena bit for disabled queues */ + val = rd32(hw, QINT_TQCTL(ring->reg_idx)); + val &= ~QINT_TQCTL_CAUSE_ENA_M; + wr32(hw, QINT_TQCTL(ring->reg_idx), val); - q_teids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_teids), - GFP_KERNEL); - if (!q_teids) - return -ENOMEM; + /* software is expected to wait for 100 ns */ + ndelay(100); - q_ids = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, sizeof(*q_ids), - GFP_KERNEL); - if (!q_ids) { - err = -ENOMEM; - goto err_alloc_q_ids; + /* trigger a software interrupt for the vector + * associated to the queue to schedule NAPI handler + */ + q_vector = ring->q_vector; + if (q_vector) + ice_trigger_sw_intr(hw, q_vector); + + status = ice_dis_vsi_txq(vsi->port_info, txq_meta->vsi_idx, + txq_meta->tc, 1, &txq_meta->q_handle, + &txq_meta->q_id, &txq_meta->q_teid, rst_src, + rel_vmvf_num, NULL); + + /* if the disable queue command was exercised during an + * active reset flow, ICE_ERR_RESET_ONGOING is returned. + * This is not an error as the reset operation disables + * queues at the hardware level anyway. + */ + if (status == ICE_ERR_RESET_ONGOING) { + dev_dbg(&vsi->back->pdev->dev, + "Reset in progress. LAN Tx queues already disabled\n"); + } else if (status == ICE_ERR_DOES_NOT_EXIST) { + dev_dbg(&vsi->back->pdev->dev, + "LAN Tx queues do not exist, nothing to disable\n"); + } else if (status) { + dev_err(&vsi->back->pdev->dev, + "Failed to disable LAN Tx queues, error: %d\n", status); + return -ENODEV; } - q_handles = devm_kcalloc(&pf->pdev->dev, vsi->num_txq, - sizeof(*q_handles), GFP_KERNEL); - if (!q_handles) { - err = -ENOMEM; - goto err_alloc_q_handles; - } + return 0; +} + +/** + * ice_fill_txq_meta - Prepare the Tx queue's meta data + * @vsi: VSI that ring belongs to + * @ring: ring that txq_meta will be based on + * @txq_meta: a helper struct that wraps Tx queue's information + * + * Set up a helper struct that will contain all the necessary fields that + * are needed for stopping Tx queue + */ +#ifndef CONFIG_PCI_IOV +static +#endif /* !CONFIG_PCI_IOV */ +void +ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_ring *ring, + struct ice_txq_meta *txq_meta) +{ + u8 tc = 0; + +#ifdef CONFIG_DCB + tc = ring->dcb_tc; +#endif /* CONFIG_DCB */ + txq_meta->q_id = ring->reg_idx; + txq_meta->q_teid = ring->txq_teid; + txq_meta->q_handle = ring->q_handle; + txq_meta->vsi_idx = vsi->idx; + txq_meta->tc = tc; +} + +/** + * ice_vsi_stop_tx_rings - Disable Tx rings + * @vsi: the VSI being configured + * @rst_src: reset source + * @rel_vmvf_num: Relative ID of VF/VM + * @rings: Tx ring array to be stopped + */ +static int +ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, + u16 rel_vmvf_num, struct ice_ring **rings) +{ + u16 i, q_idx = 0; + int status; + u8 tc; + + if (vsi->num_txq > ICE_LAN_TXQ_MAX_QDIS) + return -EINVAL; /* set up the Tx queue list to be disabled for each enabled TC */ ice_for_each_traffic_class(tc) { @@ -2116,64 +2260,24 @@ ice_vsi_stop_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, break; for (i = 0; i < vsi->tc_cfg.tc_info[tc].qcount_tx; i++) { - struct ice_q_vector *q_vector; + struct ice_txq_meta txq_meta = { }; - if (!rings || !rings[q_idx]) { - err = -EINVAL; - goto err_out; - } - - q_ids[i] = vsi->txq_map[q_idx + offset]; - q_teids[i] = rings[q_idx]->txq_teid; - q_handles[i] = i; + if (!rings || !rings[q_idx]) + return -EINVAL; - /* clear cause_ena bit for disabled queues */ - val = rd32(hw, QINT_TQCTL(rings[i]->reg_idx)); - val &= ~QINT_TQCTL_CAUSE_ENA_M; - wr32(hw, QINT_TQCTL(rings[i]->reg_idx), val); + ice_fill_txq_meta(vsi, rings[q_idx], &txq_meta); + status = ice_vsi_stop_tx_ring(vsi, rst_src, + rel_vmvf_num, + rings[q_idx], &txq_meta); - /* software is expected to wait for 100 ns */ - ndelay(100); - - /* trigger a software interrupt for the vector - * associated to the queue to schedule NAPI handler - */ - q_vector = rings[i]->q_vector; - if (q_vector) - ice_trigger_sw_intr(hw, q_vector); + if (status) + return status; q_idx++; } - status = ice_dis_vsi_txq(vsi->port_info, vsi->idx, tc, - vsi->num_txq, q_handles, q_ids, - q_teids, rst_src, rel_vmvf_num, NULL); - - /* if the disable queue command was exercised during an active - * reset flow, ICE_ERR_RESET_ONGOING is returned. This is not - * an error as the reset operation disables queues at the - * hardware level anyway. - */ - if (status == ICE_ERR_RESET_ONGOING) { - dev_dbg(&pf->pdev->dev, - "Reset in progress. LAN Tx queues already disabled\n"); - } else if (status) { - dev_err(&pf->pdev->dev, - "Failed to disable LAN Tx queues, error: %d\n", - status); - err = -ENODEV; - } } -err_out: - devm_kfree(&pf->pdev->dev, q_handles); - -err_alloc_q_handles: - devm_kfree(&pf->pdev->dev, q_ids); - -err_alloc_q_ids: - devm_kfree(&pf->pdev->dev, q_teids); - - return err; + return 0; } /** @@ -2186,8 +2290,7 @@ int ice_vsi_stop_lan_tx_rings(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, u16 rel_vmvf_num) { - return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings, - 0); + return ice_vsi_stop_tx_rings(vsi, rst_src, rel_vmvf_num, vsi->tx_rings); } /** @@ -2497,9 +2600,6 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, if (ret) goto unroll_vector_base; - pf->q_left_tx -= vsi->alloc_txq; - pf->q_left_rx -= vsi->alloc_rxq; - /* Do not exit if configuring RSS had an issue, at least * receive traffic on first queue. Hence no need to capture * return value @@ -2519,7 +2619,7 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, /* configure VSI nodes based on number of queues and TC's */ for (i = 0; i < vsi->tc_cfg.numtc; i++) - max_txqs[i] = pf->num_lan_tx; + max_txqs[i] = vsi->alloc_txq; status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, max_txqs); @@ -2540,15 +2640,17 @@ ice_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, * DCB settings in the HW. Also, if the FW DCBX engine is not running * then Rx LLDP packets need to be redirected up the stack. */ - if (vsi->type == ICE_VSI_PF) { - ice_vsi_add_rem_eth_mac(vsi, true); + if (!ice_is_safe_mode(pf)) { + if (vsi->type == ICE_VSI_PF) { + ice_vsi_add_rem_eth_mac(vsi, true); - /* Tx LLDP packets */ - ice_cfg_sw_lldp(vsi, true, true); + /* Tx LLDP packets */ + ice_cfg_sw_lldp(vsi, true, true); - /* Rx LLDP packets */ - if (!test_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags)) - ice_cfg_sw_lldp(vsi, false, true); + /* Rx LLDP packets */ + if (!test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) + ice_cfg_sw_lldp(vsi, false, true); + } } return vsi; @@ -2563,8 +2665,6 @@ unroll_vsi_init: ice_vsi_delete(vsi); unroll_get_qs: ice_vsi_put_qs(vsi); - pf->q_left_tx += vsi->alloc_txq; - pf->q_left_rx += vsi->alloc_rxq; ice_vsi_clear(vsi); return NULL; @@ -2610,39 +2710,36 @@ void ice_vsi_free_irq(struct ice_vsi *vsi) { struct ice_pf *pf = vsi->back; int base = vsi->base_vector; + int i; - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - int i; - - if (!vsi->q_vectors || !vsi->irqs_ready) - return; + if (!vsi->q_vectors || !vsi->irqs_ready) + return; - ice_vsi_release_msix(vsi); - if (vsi->type == ICE_VSI_VF) - return; + ice_vsi_release_msix(vsi); + if (vsi->type == ICE_VSI_VF) + return; - vsi->irqs_ready = false; - ice_for_each_q_vector(vsi, i) { - u16 vector = i + base; - int irq_num; + vsi->irqs_ready = false; + ice_for_each_q_vector(vsi, i) { + u16 vector = i + base; + int irq_num; - irq_num = pf->msix_entries[vector].vector; + irq_num = pf->msix_entries[vector].vector; - /* free only the irqs that were actually requested */ - if (!vsi->q_vectors[i] || - !(vsi->q_vectors[i]->num_ring_tx || - vsi->q_vectors[i]->num_ring_rx)) - continue; + /* free only the irqs that were actually requested */ + if (!vsi->q_vectors[i] || + !(vsi->q_vectors[i]->num_ring_tx || + vsi->q_vectors[i]->num_ring_rx)) + continue; - /* clear the affinity notifier in the IRQ descriptor */ - irq_set_affinity_notifier(irq_num, NULL); + /* clear the affinity notifier in the IRQ descriptor */ + irq_set_affinity_notifier(irq_num, NULL); - /* clear the affinity_mask in the IRQ descriptor */ - irq_set_affinity_hint(irq_num, NULL); - synchronize_irq(irq_num); - devm_free_irq(&pf->pdev->dev, irq_num, - vsi->q_vectors[i]); - } + /* clear the affinity_mask in the IRQ descriptor */ + irq_set_affinity_hint(irq_num, NULL); + synchronize_irq(irq_num); + devm_free_irq(&pf->pdev->dev, irq_num, + vsi->q_vectors[i]); } } @@ -2821,15 +2918,20 @@ void ice_vsi_dis_irq(struct ice_vsi *vsi) } /* disable each interrupt */ - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - ice_for_each_q_vector(vsi, i) - wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0); + ice_for_each_q_vector(vsi, i) { + if (!vsi->q_vectors[i]) + continue; + wr32(hw, GLINT_DYN_CTL(vsi->q_vectors[i]->reg_idx), 0); + } - ice_flush(hw); + ice_flush(hw); - ice_for_each_q_vector(vsi, i) - synchronize_irq(pf->msix_entries[i + base].vector); - } + /* don't call synchronize_irq() for VF's from the host */ + if (vsi->type == ICE_VSI_VF) + return; + + ice_for_each_q_vector(vsi, i) + synchronize_irq(pf->msix_entries[i + base].vector); } /** @@ -2889,14 +2991,16 @@ int ice_vsi_release(struct ice_vsi *vsi) pf->num_avail_sw_msix += vsi->num_q_vectors; } - if (vsi->type == ICE_VSI_PF) { - ice_vsi_add_rem_eth_mac(vsi, false); - ice_cfg_sw_lldp(vsi, true, false); - /* The Rx rule will only exist to remove if the LLDP FW - * engine is currently stopped - */ - if (!test_bit(ICE_FLAG_ENABLE_FW_LLDP, pf->flags)) - ice_cfg_sw_lldp(vsi, false, false); + if (!ice_is_safe_mode(pf)) { + if (vsi->type == ICE_VSI_PF) { + ice_vsi_add_rem_eth_mac(vsi, false); + ice_cfg_sw_lldp(vsi, true, false); + /* The Rx rule will only exist to remove if the LLDP FW + * engine is currently stopped + */ + if (!test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags)) + ice_cfg_sw_lldp(vsi, false, false); + } } ice_remove_vsi_fltr(&pf->hw, vsi->idx); @@ -2913,8 +3017,6 @@ int ice_vsi_release(struct ice_vsi *vsi) ice_vsi_clear_rings(vsi); ice_vsi_put_qs(vsi); - pf->q_left_tx += vsi->alloc_txq; - pf->q_left_rx += vsi->alloc_rxq; /* retain SW VSI data structure since it is needed to unregister and * free VSI netdev when PF is not in reset recovery pending state,\ @@ -2962,6 +3064,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) vsi->base_vector = 0; } + ice_vsi_put_qs(vsi); ice_vsi_clear_rings(vsi); ice_vsi_free_arrays(vsi); ice_dev_onetime_setup(&pf->hw); @@ -2969,6 +3072,12 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) ice_vsi_set_num_qs(vsi, vf->vf_id); else ice_vsi_set_num_qs(vsi, ICE_INVAL_VFID); + + ret = ice_vsi_alloc_arrays(vsi); + if (ret < 0) + goto err_vsi; + + ice_vsi_get_qs(vsi); ice_vsi_set_tc_cfg(vsi); /* Initialize VSI struct elements and create VSI in FW */ @@ -2976,9 +3085,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) if (ret < 0) goto err_vsi; - ret = ice_vsi_alloc_arrays(vsi); - if (ret < 0) - goto err_vsi; switch (vsi->type) { case ICE_VSI_PF: @@ -2986,6 +3092,10 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) if (ret) goto err_rings; + ret = ice_vsi_setup_vector_base(vsi); + if (ret) + goto err_vectors; + ret = ice_vsi_set_q_vectors_reg_idx(vsi); if (ret) goto err_vectors; @@ -3007,10 +3117,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) if (ret) goto err_rings; - ret = ice_vsi_setup_vector_base(vsi); - if (ret) - goto err_vectors; - ret = ice_vsi_set_q_vectors_reg_idx(vsi); if (ret) goto err_vectors; @@ -3019,8 +3125,6 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) if (ret) goto err_vectors; - pf->q_left_tx -= vsi->alloc_txq; - pf->q_left_rx -= vsi->alloc_rxq; break; default: break; @@ -3028,7 +3132,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi) /* configure VSI nodes based on number of queues and TC's */ for (i = 0; i < vsi->tc_cfg.numtc; i++) - max_txqs[i] = pf->num_lan_tx; + max_txqs[i] = vsi->alloc_txq; status = ice_cfg_vsi_lan(vsi->port_info, vsi->idx, vsi->tc_cfg.ena_tc, max_txqs); @@ -3083,48 +3187,6 @@ static void ice_vsi_update_q_map(struct ice_vsi *vsi, struct ice_vsi_ctx *ctx) } /** - * ice_vsi_cfg_netdev_tc - Setup the netdev TC configuration - * @vsi: the VSI being configured - * @ena_tc: TC map to be enabled - */ -static void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc) -{ - struct net_device *netdev = vsi->netdev; - struct ice_pf *pf = vsi->back; - struct ice_dcbx_cfg *dcbcfg; - u8 netdev_tc; - int i; - - if (!netdev) - return; - - if (!ena_tc) { - netdev_reset_tc(netdev); - return; - } - - if (netdev_set_num_tc(netdev, vsi->tc_cfg.numtc)) - return; - - dcbcfg = &pf->hw.port_info->local_dcbx_cfg; - - ice_for_each_traffic_class(i) - if (vsi->tc_cfg.ena_tc & BIT(i)) - netdev_set_tc_queue(netdev, - vsi->tc_cfg.tc_info[i].netdev_tc, - vsi->tc_cfg.tc_info[i].qcount_tx, - vsi->tc_cfg.tc_info[i].qoffset); - - for (i = 0; i < ICE_MAX_USER_PRIORITY; i++) { - u8 ets_tc = dcbcfg->etscfg.prio_table[i]; - - /* Get the mapped netdev TC# for the UP */ - netdev_tc = vsi->tc_cfg.tc_info[ets_tc].netdev_tc; - netdev_set_prio_tc_map(netdev, i, netdev_tc); - } -} - -/** * ice_vsi_cfg_tc - Configure VSI Tx Sched for given TC map * @vsi: VSI to be configured * @ena_tc: TC bitmap @@ -3145,7 +3207,7 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc) if (ena_tc & BIT(i)) num_tc++; /* populate max_txqs per TC */ - max_txqs[i] = pf->num_lan_tx; + max_txqs[i] = vsi->alloc_txq; } vsi->tc_cfg.ena_tc = ena_tc; @@ -3188,3 +3250,52 @@ out: return ret; } #endif /* CONFIG_DCB */ + +/** + * ice_nvm_version_str - format the NVM version strings + * @hw: ptr to the hardware info + */ +char *ice_nvm_version_str(struct ice_hw *hw) +{ + u8 oem_ver, oem_patch, ver_hi, ver_lo; + static char buf[ICE_NVM_VER_LEN]; + u16 oem_build; + + ice_get_nvm_version(hw, &oem_ver, &oem_build, &oem_patch, &ver_hi, + &ver_lo); + + snprintf(buf, sizeof(buf), "%x.%02x 0x%x %d.%d.%d", ver_hi, ver_lo, + hw->nvm.eetrack, oem_ver, oem_build, oem_patch); + + return buf; +} + +/** + * ice_vsi_cfg_mac_fltr - Add or remove a MAC address filter for a VSI + * @vsi: the VSI being configured MAC filter + * @macaddr: the MAC address to be added. + * @set: Add or delete a MAC filter + * + * Adds or removes MAC address filter entry for VF VSI + */ +enum ice_status +ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set) +{ + LIST_HEAD(tmp_add_list); + enum ice_status status; + + /* Update MAC filter list to be added or removed for a VSI */ + if (ice_add_mac_to_list(vsi, &tmp_add_list, macaddr)) { + status = ICE_ERR_NO_MEMORY; + goto cfg_mac_fltr_exit; + } + + if (set) + status = ice_add_mac(&vsi->back->hw, &tmp_add_list); + else + status = ice_remove_mac(&vsi->back->hw, &tmp_add_list); + +cfg_mac_fltr_exit: + ice_free_fltr_list(&vsi->back->pdev->dev, &tmp_add_list); + return status; +} diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h index 6e43ef03bfc3..47bc033fff20 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.h +++ b/drivers/net/ethernet/intel/ice/ice_lib.h @@ -6,8 +6,22 @@ #include "ice.h" -int ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list, - const u8 *macaddr); +struct ice_txq_meta { + /* Tx-scheduler element identifier */ + u32 q_teid; + /* Entry in VSI's txq_map bitmap */ + u16 q_id; + /* Relative index of Tx queue within TC */ + u16 q_handle; + /* VSI index that Tx queue belongs to */ + u16 vsi_idx; + /* TC number that Tx queue belongs to */ + u8 tc; +}; + +int +ice_add_mac_to_list(struct ice_vsi *vsi, struct list_head *add_list, + const u8 *macaddr); void ice_free_fltr_list(struct device *dev, struct list_head *h); @@ -25,6 +39,16 @@ ice_cfg_txq_interrupt(struct ice_vsi *vsi, u16 txq, u16 msix_idx, u16 itr_idx); void ice_cfg_rxq_interrupt(struct ice_vsi *vsi, u16 rxq, u16 msix_idx, u16 itr_idx); + +int +ice_vsi_stop_tx_ring(struct ice_vsi *vsi, enum ice_disq_rst_src rst_src, + u16 rel_vmvf_num, struct ice_ring *ring, + struct ice_txq_meta *txq_meta); + +void ice_fill_txq_meta(struct ice_vsi *vsi, struct ice_ring *ring, + struct ice_txq_meta *txq_meta); + +int ice_vsi_ctrl_rx_ring(struct ice_vsi *vsi, bool ena, u16 rxq_idx); #endif /* CONFIG_PCI_IOV */ int ice_vsi_add_vlan(struct ice_vsi *vsi, u16 vid); @@ -95,4 +119,11 @@ void ice_vsi_free_tx_rings(struct ice_vsi *vsi); int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena); u32 ice_intrl_usec_to_reg(u8 intrl, u8 gran); + +char *ice_nvm_version_str(struct ice_hw *hw); + +enum ice_status +ice_vsi_cfg_mac_fltr(struct ice_vsi *vsi, const u8 *macaddr, bool set); + +bool ice_is_safe_mode(struct ice_pf *pf); #endif /* !_ICE_LIB_H_ */ diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index 63db08d9bafa..214cd6eca405 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -9,16 +9,27 @@ #include "ice_lib.h" #include "ice_dcb_lib.h" -#define DRV_VERSION "0.7.4-k" +#define DRV_VERSION_MAJOR 0 +#define DRV_VERSION_MINOR 8 +#define DRV_VERSION_BUILD 1 + +#define DRV_VERSION __stringify(DRV_VERSION_MAJOR) "." \ + __stringify(DRV_VERSION_MINOR) "." \ + __stringify(DRV_VERSION_BUILD) "-k" #define DRV_SUMMARY "Intel(R) Ethernet Connection E800 Series Linux Driver" const char ice_drv_ver[] = DRV_VERSION; static const char ice_driver_string[] = DRV_SUMMARY; static const char ice_copyright[] = "Copyright (c) 2018, Intel Corporation."; +/* DDP Package file located in firmware search paths (e.g. /lib/firmware/) */ +#define ICE_DDP_PKG_PATH "intel/ice/ddp/" +#define ICE_DDP_PKG_FILE ICE_DDP_PKG_PATH "ice.pkg" + MODULE_AUTHOR("Intel Corporation, <linux.nics@intel.com>"); MODULE_DESCRIPTION(DRV_SUMMARY); MODULE_LICENSE("GPL v2"); MODULE_VERSION(DRV_VERSION); +MODULE_FIRMWARE(ICE_DDP_PKG_FILE); static int debug = -1; module_param(debug, int, 0644); @@ -29,24 +40,23 @@ MODULE_PARM_DESC(debug, "netif level (0=none,...,16=all)"); #endif /* !CONFIG_DYNAMIC_DEBUG */ static struct workqueue_struct *ice_wq; +static const struct net_device_ops ice_netdev_safe_mode_ops; static const struct net_device_ops ice_netdev_ops; -static void ice_rebuild(struct ice_pf *pf); +static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type); static void ice_vsi_release_all(struct ice_pf *pf); -static void ice_update_vsi_stats(struct ice_vsi *vsi); -static void ice_update_pf_stats(struct ice_pf *pf); /** * ice_get_tx_pending - returns number of Tx descriptors not processed * @ring: the ring of descriptors */ -static u32 ice_get_tx_pending(struct ice_ring *ring) +static u16 ice_get_tx_pending(struct ice_ring *ring) { - u32 head, tail; + u16 head, tail; head = ring->next_to_clean; - tail = readl(ring->tail); + tail = ring->next_to_use; if (head != tail) return (head < tail) ? @@ -118,12 +128,11 @@ static void ice_check_for_hang_subtask(struct ice_pf *pf) */ static int ice_init_mac_fltr(struct ice_pf *pf) { - LIST_HEAD(tmp_add_list); + enum ice_status status; u8 broadcast[ETH_ALEN]; struct ice_vsi *vsi; - int status; - vsi = ice_find_vsi_by_type(pf, ICE_VSI_PF); + vsi = ice_get_main_vsi(pf); if (!vsi) return -EINVAL; @@ -132,8 +141,7 @@ static int ice_init_mac_fltr(struct ice_pf *pf) */ /* Add a unicast MAC filter so the VSI can get its packets */ - status = ice_add_mac_to_list(vsi, &tmp_add_list, - vsi->port_info->mac.perm_addr); + status = ice_vsi_cfg_mac_fltr(vsi, vsi->port_info->mac.perm_addr, true); if (status) goto unregister; @@ -141,18 +149,11 @@ static int ice_init_mac_fltr(struct ice_pf *pf) * MAC address to the list as well. */ eth_broadcast_addr(broadcast); - status = ice_add_mac_to_list(vsi, &tmp_add_list, broadcast); - if (status) - goto free_mac_list; - - /* Program MAC filters for entries in tmp_add_list */ - status = ice_add_mac(&pf->hw, &tmp_add_list); + status = ice_vsi_cfg_mac_fltr(vsi, broadcast, true); if (status) - status = -ENOMEM; - -free_mac_list: - ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); + goto unregister; + return 0; unregister: /* We aren't useful with no MAC filters, so unregister if we * had an error @@ -166,7 +167,7 @@ unregister: vsi->netdev = NULL; } - return status; + return -EIO; } /** @@ -447,13 +448,13 @@ static void ice_dis_vsi(struct ice_vsi *vsi, bool locked) if (vsi->type == ICE_VSI_PF && vsi->netdev) { if (netif_running(vsi->netdev)) { - if (!locked) { + if (!locked) rtnl_lock(); - vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); + + ice_stop(vsi->netdev); + + if (!locked) rtnl_unlock(); - } else { - vsi->netdev->netdev_ops->ndo_stop(vsi->netdev); - } } else { ice_vsi_close(vsi); } @@ -488,6 +489,7 @@ static void ice_prepare_for_reset(struct ice_pf *pf) { struct ice_hw *hw = &pf->hw; + int i; /* already prepared for reset */ if (test_bit(__ICE_PREPARED_FOR_RESET, pf->state)) @@ -497,6 +499,12 @@ ice_prepare_for_reset(struct ice_pf *pf) if (ice_check_sq_alive(hw, &hw->mailboxq)) ice_vc_notify_reset(pf); + /* Disable VFs until reset is completed */ + for (i = 0; i < pf->num_alloc_vfs; i++) + ice_set_vf_state_qs_dis(&pf->vf[i]); + + /* clear SW filtering DB */ + ice_clear_hw_tbls(hw); /* disable the VSIs and their queues that are not already DOWN */ ice_pf_dis_all_vsi(pf, false); @@ -542,7 +550,7 @@ static void ice_do_reset(struct ice_pf *pf, enum ice_reset_req reset_type) */ if (reset_type == ICE_RESET_PFR) { pf->pfr_count++; - ice_rebuild(pf); + ice_rebuild(pf, reset_type); clear_bit(__ICE_PREPARED_FOR_RESET, pf->state); clear_bit(__ICE_PFR_REQ, pf->state); ice_reset_all_vfs(pf, true); @@ -573,6 +581,8 @@ static void ice_reset_subtask(struct ice_pf *pf) reset_type = ICE_RESET_CORER; if (test_and_clear_bit(__ICE_GLOBR_RECV, pf->state)) reset_type = ICE_RESET_GLOBR; + if (test_and_clear_bit(__ICE_EMPR_RECV, pf->state)) + reset_type = ICE_RESET_EMPR; /* return if no valid reset type requested */ if (reset_type == ICE_RESET_INVAL) return; @@ -584,7 +594,7 @@ static void ice_reset_subtask(struct ice_pf *pf) } else { /* done with reset. start rebuild */ pf->hw.reset_ongoing = false; - ice_rebuild(pf); + ice_rebuild(pf, reset_type); /* clear bit to resume normal operations, but * ICE_NEEDS_RESTART bit is set in case rebuild failed */ @@ -618,6 +628,22 @@ static void ice_reset_subtask(struct ice_pf *pf) } /** + * ice_print_topo_conflict - print topology conflict message + * @vsi: the VSI whose topology status is being checked + */ +static void ice_print_topo_conflict(struct ice_vsi *vsi) +{ + switch (vsi->port_info->phy.link_info.topo_media_conflict) { + case ICE_AQ_LINK_TOPO_CONFLICT: + case ICE_AQ_LINK_MEDIA_CONFLICT: + netdev_info(vsi->netdev, "Possible mis-configuration of the Ethernet port detected, please use the Intel(R) Ethernet Port Configuration Tool application to address the issue.\n"); + break; + default: + break; + } +} + +/** * ice_print_link_msg - print link up or down message * @vsi: the VSI whose link status is being queried * @isup: boolean for if the link is now up or down @@ -630,6 +656,7 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) const char *speed; const char *fec; const char *fc; + const char *an; if (!vsi) return; @@ -713,6 +740,12 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) break; } + /* check if autoneg completed, might be false due to not supported */ + if (vsi->port_info->phy.link_info.an_info & ICE_AQ_AN_COMPLETED) + an = "True"; + else + an = "False"; + /* Get FEC mode requested based on PHY caps last SW configuration */ caps = devm_kzalloc(&vsi->back->pdev->dev, sizeof(*caps), GFP_KERNEL); if (!caps) { @@ -737,8 +770,9 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup) devm_kfree(&vsi->back->pdev->dev, caps); done: - netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Flow Control: %s\n", - speed, fec_req, fec, fc); + netdev_info(vsi->netdev, "NIC Link is up %sbps, Requested FEC: %s, FEC: %s, Autoneg: %s, Flow Control: %s\n", + speed, fec_req, fec, an, fc); + ice_print_topo_conflict(vsi); } /** @@ -806,10 +840,24 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi, bool link_up, if (link_up == old_link && link_speed == old_link_speed) return result; - vsi = ice_find_vsi_by_type(pf, ICE_VSI_PF); + vsi = ice_get_main_vsi(pf); if (!vsi || !vsi->port_info) return -EINVAL; + /* turn off PHY if media was removed */ + if (!test_bit(ICE_FLAG_NO_MEDIA, pf->flags) && + !(pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE)) { + set_bit(ICE_FLAG_NO_MEDIA, pf->flags); + + result = ice_aq_set_link_restart_an(pi, false, NULL); + if (result) { + dev_dbg(&pf->pdev->dev, + "Failed to set link down, VSI %d error %d\n", + vsi->vsi_num, result); + return result; + } + } + ice_vsi_link_event(vsi, link_up); ice_print_link_msg(vsi, link_up); @@ -1307,14 +1355,134 @@ static void ice_handle_mdd_event(struct ice_pf *pf) if (vf_mdd_detected) { vf->num_mdd_events++; - if (vf->num_mdd_events > 1) - dev_info(&pf->pdev->dev, "VF %d has had %llu MDD events since last boot\n", + if (vf->num_mdd_events && + vf->num_mdd_events <= ICE_MDD_EVENTS_THRESHOLD) + dev_info(&pf->pdev->dev, + "VF %d has had %llu MDD events since last boot, Admin might need to reload AVF driver with this number of events\n", i, vf->num_mdd_events); } } } /** + * ice_force_phys_link_state - Force the physical link state + * @vsi: VSI to force the physical link state to up/down + * @link_up: true/false indicates to set the physical link to up/down + * + * Force the physical link state by getting the current PHY capabilities from + * hardware and setting the PHY config based on the determined capabilities. If + * link changes a link event will be triggered because both the Enable Automatic + * Link Update and LESM Enable bits are set when setting the PHY capabilities. + * + * Returns 0 on success, negative on failure + */ +static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up) +{ + struct ice_aqc_get_phy_caps_data *pcaps; + struct ice_aqc_set_phy_cfg_data *cfg; + struct ice_port_info *pi; + struct device *dev; + int retcode; + + if (!vsi || !vsi->port_info || !vsi->back) + return -EINVAL; + if (vsi->type != ICE_VSI_PF) + return 0; + + dev = &vsi->back->pdev->dev; + + pi = vsi->port_info; + + pcaps = devm_kzalloc(dev, sizeof(*pcaps), GFP_KERNEL); + if (!pcaps) + return -ENOMEM; + + retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps, + NULL); + if (retcode) { + dev_err(dev, + "Failed to get phy capabilities, VSI %d error %d\n", + vsi->vsi_num, retcode); + retcode = -EIO; + goto out; + } + + /* No change in link */ + if (link_up == !!(pcaps->caps & ICE_AQC_PHY_EN_LINK) && + link_up == !!(pi->phy.link_info.link_info & ICE_AQ_LINK_UP)) + goto out; + + cfg = devm_kzalloc(dev, sizeof(*cfg), GFP_KERNEL); + if (!cfg) { + retcode = -ENOMEM; + goto out; + } + + cfg->phy_type_low = pcaps->phy_type_low; + cfg->phy_type_high = pcaps->phy_type_high; + cfg->caps = pcaps->caps | ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; + cfg->low_power_ctrl = pcaps->low_power_ctrl; + cfg->eee_cap = pcaps->eee_cap; + cfg->eeer_value = pcaps->eeer_value; + cfg->link_fec_opt = pcaps->link_fec_options; + if (link_up) + cfg->caps |= ICE_AQ_PHY_ENA_LINK; + else + cfg->caps &= ~ICE_AQ_PHY_ENA_LINK; + + retcode = ice_aq_set_phy_cfg(&vsi->back->hw, pi->lport, cfg, NULL); + if (retcode) { + dev_err(dev, "Failed to set phy config, VSI %d error %d\n", + vsi->vsi_num, retcode); + retcode = -EIO; + } + + devm_kfree(dev, cfg); +out: + devm_kfree(dev, pcaps); + return retcode; +} + +/** + * ice_check_media_subtask - Check for media; bring link up if detected. + * @pf: pointer to PF struct + */ +static void ice_check_media_subtask(struct ice_pf *pf) +{ + struct ice_port_info *pi; + struct ice_vsi *vsi; + int err; + + vsi = ice_get_main_vsi(pf); + if (!vsi) + return; + + /* No need to check for media if it's already present or the interface + * is down + */ + if (!test_bit(ICE_FLAG_NO_MEDIA, pf->flags) || + test_bit(__ICE_DOWN, vsi->state)) + return; + + /* Refresh link info and check if media is present */ + pi = vsi->port_info; + err = ice_update_link_info(pi); + if (err) + return; + + if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { + err = ice_force_phys_link_state(vsi, true); + if (err) + return; + clear_bit(ICE_FLAG_NO_MEDIA, pf->flags); + + /* A Link Status Event will be generated; the event handler + * will complete bringing the interface up + */ + } +} + +/** * ice_service_task - manage and run subtasks * @work: pointer to work_struct contained by the PF struct */ @@ -1336,12 +1504,19 @@ static void ice_service_task(struct work_struct *work) return; } + ice_clean_adminq_subtask(pf); + ice_check_media_subtask(pf); ice_check_for_hang_subtask(pf); ice_sync_fltr_subtask(pf); ice_handle_mdd_event(pf); - ice_process_vflr_event(pf); ice_watchdog_subtask(pf); - ice_clean_adminq_subtask(pf); + + if (ice_is_safe_mode(pf)) { + ice_service_task_complete(pf); + return; + } + + ice_process_vflr_event(pf); ice_clean_mailboxq_subtask(pf); /* Clear __ICE_SERVICE_SCHED flag to allow scheduling next event */ @@ -1369,8 +1544,8 @@ static void ice_set_ctrlq_len(struct ice_hw *hw) hw->adminq.num_sq_entries = ICE_AQ_LEN; hw->adminq.rq_buf_size = ICE_AQ_MAX_BUF_LEN; hw->adminq.sq_buf_size = ICE_AQ_MAX_BUF_LEN; - hw->mailboxq.num_rq_entries = ICE_MBXQ_LEN; - hw->mailboxq.num_sq_entries = ICE_MBXQ_LEN; + hw->mailboxq.num_rq_entries = ICE_MBXRQ_LEN; + hw->mailboxq.num_sq_entries = ICE_MBXSQ_LEN; hw->mailboxq.rq_buf_size = ICE_MBXQ_MAX_BUF_LEN; hw->mailboxq.sq_buf_size = ICE_MBXQ_MAX_BUF_LEN; } @@ -1409,15 +1584,11 @@ static void ice_irq_affinity_release(struct kref __always_unused *ref) {} */ static int ice_vsi_ena_irq(struct ice_vsi *vsi) { - struct ice_pf *pf = vsi->back; - struct ice_hw *hw = &pf->hw; + struct ice_hw *hw = &vsi->back->hw; + int i; - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - int i; - - ice_for_each_q_vector(vsi, i) - ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]); - } + ice_for_each_q_vector(vsi, i) + ice_irq_dynamic_ena(hw, vsi, vsi->q_vectors[i]); ice_flush(hw); return 0; @@ -1665,7 +1836,7 @@ static void ice_free_irq_msix_misc(struct ice_pf *pf) wr32(hw, PFINT_OICR_ENA, 0); ice_flush(hw); - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags) && pf->msix_entries) { + if (pf->msix_entries) { synchronize_irq(pf->msix_entries[pf->oicr_idx].vector); devm_free_irq(&pf->pdev->dev, pf->msix_entries[pf->oicr_idx].vector, pf); @@ -1780,30 +1951,41 @@ static void ice_napi_add(struct ice_vsi *vsi) } /** - * ice_cfg_netdev - Allocate, configure and register a netdev - * @vsi: the VSI associated with the new netdev - * - * Returns 0 on success, negative value on failure + * ice_set_ops - set netdev and ethtools ops for the given netdev + * @netdev: netdev instance */ -static int ice_cfg_netdev(struct ice_vsi *vsi) +static void ice_set_ops(struct net_device *netdev) { + struct ice_pf *pf = ice_netdev_to_pf(netdev); + + if (ice_is_safe_mode(pf)) { + netdev->netdev_ops = &ice_netdev_safe_mode_ops; + ice_set_ethtool_safe_mode_ops(netdev); + return; + } + + netdev->netdev_ops = &ice_netdev_ops; + ice_set_ethtool_ops(netdev); +} + +/** + * ice_set_netdev_features - set features for the given netdev + * @netdev: netdev instance + */ +static void ice_set_netdev_features(struct net_device *netdev) +{ + struct ice_pf *pf = ice_netdev_to_pf(netdev); netdev_features_t csumo_features; netdev_features_t vlano_features; netdev_features_t dflt_features; netdev_features_t tso_features; - struct ice_netdev_priv *np; - struct net_device *netdev; - u8 mac_addr[ETH_ALEN]; - int err; - - netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, - vsi->alloc_rxq); - if (!netdev) - return -ENOMEM; - vsi->netdev = netdev; - np = netdev_priv(netdev); - np->vsi = vsi; + if (ice_is_safe_mode(pf)) { + /* safe mode */ + netdev->features = NETIF_F_SG | NETIF_F_HIGHDMA; + netdev->hw_features = netdev->features; + return; + } dflt_features = NETIF_F_SG | NETIF_F_HIGHDMA | @@ -1831,25 +2013,50 @@ static int ice_cfg_netdev(struct ice_vsi *vsi) tso_features; netdev->vlan_features |= dflt_features | csumo_features | tso_features; +} + +/** + * ice_cfg_netdev - Allocate, configure and register a netdev + * @vsi: the VSI associated with the new netdev + * + * Returns 0 on success, negative value on failure + */ +static int ice_cfg_netdev(struct ice_vsi *vsi) +{ + struct ice_pf *pf = vsi->back; + struct ice_netdev_priv *np; + struct net_device *netdev; + u8 mac_addr[ETH_ALEN]; + int err; + + netdev = alloc_etherdev_mqs(sizeof(*np), vsi->alloc_txq, + vsi->alloc_rxq); + if (!netdev) + return -ENOMEM; + + vsi->netdev = netdev; + np = netdev_priv(netdev); + np->vsi = vsi; + + ice_set_netdev_features(netdev); + + ice_set_ops(netdev); if (vsi->type == ICE_VSI_PF) { - SET_NETDEV_DEV(netdev, &vsi->back->pdev->dev); + SET_NETDEV_DEV(netdev, &pf->pdev->dev); ether_addr_copy(mac_addr, vsi->port_info->mac.perm_addr); - ether_addr_copy(netdev->dev_addr, mac_addr); ether_addr_copy(netdev->perm_addr, mac_addr); } netdev->priv_flags |= IFF_UNICAST_FLT; - /* assign netdev_ops */ - netdev->netdev_ops = &ice_netdev_ops; + /* Setup netdev TC information */ + ice_vsi_cfg_netdev_tc(vsi, vsi->tc_cfg.ena_tc); /* setup watchdog timeout value to be 5 second */ netdev->watchdog_timeo = 5 * HZ; - ice_set_ethtool_ops(netdev); - netdev->min_mtu = ETH_MIN_MTU; netdev->max_mtu = ICE_MAX_MTU; @@ -2041,36 +2248,48 @@ unroll_vsi_setup: ice_vsi_free_q_vectors(vsi); ice_vsi_delete(vsi); ice_vsi_put_qs(vsi); - pf->q_left_tx += vsi->alloc_txq; - pf->q_left_rx += vsi->alloc_rxq; ice_vsi_clear(vsi); } return status; } /** - * ice_determine_q_usage - Calculate queue distribution - * @pf: board private structure - * - * Return -ENOMEM if we don't get enough queues for all ports + * ice_get_avail_q_count - Get count of queues in use + * @pf_qmap: bitmap to get queue use count from + * @lock: pointer to a mutex that protects access to pf_qmap + * @size: size of the bitmap */ -static void ice_determine_q_usage(struct ice_pf *pf) +static u16 +ice_get_avail_q_count(unsigned long *pf_qmap, struct mutex *lock, u16 size) { - u16 q_left_tx, q_left_rx; + u16 count = 0, bit; - q_left_tx = pf->hw.func_caps.common_cap.num_txq; - q_left_rx = pf->hw.func_caps.common_cap.num_rxq; + mutex_lock(lock); + for_each_clear_bit(bit, pf_qmap, size) + count++; + mutex_unlock(lock); - pf->num_lan_tx = min_t(int, q_left_tx, num_online_cpus()); + return count; +} - /* only 1 Rx queue unless RSS is enabled */ - if (!test_bit(ICE_FLAG_RSS_ENA, pf->flags)) - pf->num_lan_rx = 1; - else - pf->num_lan_rx = min_t(int, q_left_rx, num_online_cpus()); +/** + * ice_get_avail_txq_count - Get count of Tx queues in use + * @pf: pointer to an ice_pf instance + */ +u16 ice_get_avail_txq_count(struct ice_pf *pf) +{ + return ice_get_avail_q_count(pf->avail_txqs, &pf->avail_q_mutex, + pf->max_pf_txqs); +} - pf->q_left_tx = q_left_tx - pf->num_lan_tx; - pf->q_left_rx = q_left_rx - pf->num_lan_rx; +/** + * ice_get_avail_rxq_count - Get count of Rx queues in use + * @pf: pointer to an ice_pf instance + */ +u16 ice_get_avail_rxq_count(struct ice_pf *pf) +{ + return ice_get_avail_q_count(pf->avail_rxqs, &pf->avail_q_mutex, + pf->max_pf_rxqs); } /** @@ -2082,43 +2301,74 @@ static void ice_deinit_pf(struct ice_pf *pf) ice_service_task_stop(pf); mutex_destroy(&pf->sw_mutex); mutex_destroy(&pf->avail_q_mutex); + + if (pf->avail_txqs) { + bitmap_free(pf->avail_txqs); + pf->avail_txqs = NULL; + } + + if (pf->avail_rxqs) { + bitmap_free(pf->avail_rxqs); + pf->avail_rxqs = NULL; + } } /** - * ice_init_pf - Initialize general software structures (struct ice_pf) - * @pf: board private structure to initialize + * ice_set_pf_caps - set PFs capability flags + * @pf: pointer to the PF instance */ -static void ice_init_pf(struct ice_pf *pf) +static void ice_set_pf_caps(struct ice_pf *pf) { - bitmap_zero(pf->flags, ICE_PF_FLAGS_NBITS); - set_bit(ICE_FLAG_MSIX_ENA, pf->flags); -#ifdef CONFIG_PCI_IOV - if (pf->hw.func_caps.common_cap.sr_iov_1_1) { - struct ice_hw *hw = &pf->hw; + struct ice_hw_func_caps *func_caps = &pf->hw.func_caps; + clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); + if (func_caps->common_cap.dcb) + set_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); +#ifdef CONFIG_PCI_IOV + clear_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags); + if (func_caps->common_cap.sr_iov_1_1) { set_bit(ICE_FLAG_SRIOV_CAPABLE, pf->flags); - pf->num_vfs_supported = min_t(int, hw->func_caps.num_allocd_vfs, + pf->num_vfs_supported = min_t(int, func_caps->num_allocd_vfs, ICE_MAX_VF_COUNT); } #endif /* CONFIG_PCI_IOV */ + clear_bit(ICE_FLAG_RSS_ENA, pf->flags); + if (func_caps->common_cap.rss_table_size) + set_bit(ICE_FLAG_RSS_ENA, pf->flags); - mutex_init(&pf->sw_mutex); - mutex_init(&pf->avail_q_mutex); + pf->max_pf_txqs = func_caps->common_cap.num_txq; + pf->max_pf_rxqs = func_caps->common_cap.num_rxq; +} - /* Clear avail_[t|r]x_qs bitmaps (set all to avail) */ - mutex_lock(&pf->avail_q_mutex); - bitmap_zero(pf->avail_txqs, ICE_MAX_TXQS); - bitmap_zero(pf->avail_rxqs, ICE_MAX_RXQS); - mutex_unlock(&pf->avail_q_mutex); +/** + * ice_init_pf - Initialize general software structures (struct ice_pf) + * @pf: board private structure to initialize + */ +static int ice_init_pf(struct ice_pf *pf) +{ + ice_set_pf_caps(pf); - if (pf->hw.func_caps.common_cap.rss_table_size) - set_bit(ICE_FLAG_RSS_ENA, pf->flags); + mutex_init(&pf->sw_mutex); /* setup service timer and periodic service task */ timer_setup(&pf->serv_tmr, ice_service_timer, 0); pf->serv_tmr_period = HZ; INIT_WORK(&pf->serv_task, ice_service_task); clear_bit(__ICE_SERVICE_SCHED, pf->state); + + mutex_init(&pf->avail_q_mutex); + pf->avail_txqs = bitmap_zalloc(pf->max_pf_txqs, GFP_KERNEL); + if (!pf->avail_txqs) + return -ENOMEM; + + pf->avail_rxqs = bitmap_zalloc(pf->max_pf_rxqs, GFP_KERNEL); + if (!pf->avail_rxqs) { + devm_kfree(&pf->pdev->dev, pf->avail_txqs); + pf->avail_txqs = NULL; + return -ENOMEM; + } + + return 0; } /** @@ -2137,13 +2387,18 @@ static int ice_ena_msix_range(struct ice_pf *pf) /* reserve one vector for miscellaneous handler */ needed = 1; + if (v_left < needed) + goto no_hw_vecs_left_err; v_budget += needed; v_left -= needed; /* reserve vectors for LAN traffic */ - pf->num_lan_msix = min_t(int, num_online_cpus(), v_left); - v_budget += pf->num_lan_msix; - v_left -= pf->num_lan_msix; + needed = min_t(int, num_online_cpus(), v_left); + if (v_left < needed) + goto no_hw_vecs_left_err; + pf->num_lan_msix = needed; + v_budget += needed; + v_left -= needed; pf->msix_entries = devm_kcalloc(&pf->pdev->dev, v_budget, sizeof(*pf->msix_entries), GFP_KERNEL); @@ -2168,18 +2423,18 @@ static int ice_ena_msix_range(struct ice_pf *pf) if (v_actual < v_budget) { dev_warn(&pf->pdev->dev, - "not enough vectors. requested = %d, obtained = %d\n", + "not enough OS MSI-X vectors. requested = %d, obtained = %d\n", v_budget, v_actual); - if (v_actual >= (pf->num_lan_msix + 1)) { - pf->num_avail_sw_msix = v_actual - - (pf->num_lan_msix + 1); - } else if (v_actual >= 2) { - pf->num_lan_msix = 1; - pf->num_avail_sw_msix = v_actual - 2; - } else { +/* 2 vectors for LAN (traffic + OICR) */ +#define ICE_MIN_LAN_VECS 2 + + if (v_actual < ICE_MIN_LAN_VECS) { + /* error if we can't get minimum vectors */ pci_disable_msix(pf->pdev); err = -ERANGE; goto msix_err; + } else { + pf->num_lan_msix = ICE_MIN_LAN_VECS; } } @@ -2189,9 +2444,13 @@ msix_err: devm_kfree(&pf->pdev->dev, pf->msix_entries); goto exit_err; +no_hw_vecs_left_err: + dev_err(&pf->pdev->dev, + "not enough device MSI-X vectors. requested = %d, available = %d\n", + needed, v_left); + err = -ERANGE; exit_err: pf->num_lan_msix = 0; - clear_bit(ICE_FLAG_MSIX_ENA, pf->flags); return err; } @@ -2204,7 +2463,6 @@ static void ice_dis_msix(struct ice_pf *pf) pci_disable_msix(pf->pdev); devm_kfree(&pf->pdev->dev, pf->msix_entries); pf->msix_entries = NULL; - clear_bit(ICE_FLAG_MSIX_ENA, pf->flags); } /** @@ -2213,8 +2471,7 @@ static void ice_dis_msix(struct ice_pf *pf) */ static void ice_clear_interrupt_scheme(struct ice_pf *pf) { - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - ice_dis_msix(pf); + ice_dis_msix(pf); if (pf->irq_tracker) { devm_kfree(&pf->pdev->dev, pf->irq_tracker); @@ -2230,10 +2487,7 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf) { int vectors; - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - vectors = ice_ena_msix_range(pf); - else - return -ENODEV; + vectors = ice_ena_msix_range(pf); if (vectors < 0) return vectors; @@ -2256,6 +2510,163 @@ static int ice_init_interrupt_scheme(struct ice_pf *pf) } /** + * ice_log_pkg_init - log result of DDP package load + * @hw: pointer to hardware info + * @status: status of package load + */ +static void +ice_log_pkg_init(struct ice_hw *hw, enum ice_status *status) +{ + struct ice_pf *pf = (struct ice_pf *)hw->back; + struct device *dev = &pf->pdev->dev; + + switch (*status) { + case ICE_SUCCESS: + /* The package download AdminQ command returned success because + * this download succeeded or ICE_ERR_AQ_NO_WORK since there is + * already a package loaded on the device. + */ + if (hw->pkg_ver.major == hw->active_pkg_ver.major && + hw->pkg_ver.minor == hw->active_pkg_ver.minor && + hw->pkg_ver.update == hw->active_pkg_ver.update && + hw->pkg_ver.draft == hw->active_pkg_ver.draft && + !memcmp(hw->pkg_name, hw->active_pkg_name, + sizeof(hw->pkg_name))) { + if (hw->pkg_dwnld_status == ICE_AQ_RC_EEXIST) + dev_info(dev, + "DDP package already present on device: %s version %d.%d.%d.%d\n", + hw->active_pkg_name, + hw->active_pkg_ver.major, + hw->active_pkg_ver.minor, + hw->active_pkg_ver.update, + hw->active_pkg_ver.draft); + else + dev_info(dev, + "The DDP package was successfully loaded: %s version %d.%d.%d.%d\n", + hw->active_pkg_name, + hw->active_pkg_ver.major, + hw->active_pkg_ver.minor, + hw->active_pkg_ver.update, + hw->active_pkg_ver.draft); + } else if (hw->active_pkg_ver.major != ICE_PKG_SUPP_VER_MAJ || + hw->active_pkg_ver.minor != ICE_PKG_SUPP_VER_MNR) { + dev_err(dev, + "The device has a DDP package that is not supported by the driver. The device has package '%s' version %d.%d.x.x. The driver requires version %d.%d.x.x. Entering Safe Mode.\n", + hw->active_pkg_name, + hw->active_pkg_ver.major, + hw->active_pkg_ver.minor, + ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR); + *status = ICE_ERR_NOT_SUPPORTED; + } else if (hw->active_pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && + hw->active_pkg_ver.minor == ICE_PKG_SUPP_VER_MNR) { + dev_info(dev, + "The driver could not load the DDP package file because a compatible DDP package is already present on the device. The device has package '%s' version %d.%d.%d.%d. The package file found by the driver: '%s' version %d.%d.%d.%d.\n", + hw->active_pkg_name, + hw->active_pkg_ver.major, + hw->active_pkg_ver.minor, + hw->active_pkg_ver.update, + hw->active_pkg_ver.draft, + hw->pkg_name, + hw->pkg_ver.major, + hw->pkg_ver.minor, + hw->pkg_ver.update, + hw->pkg_ver.draft); + } else { + dev_err(dev, + "An unknown error occurred when loading the DDP package, please reboot the system. If the problem persists, update the NVM. Entering Safe Mode.\n"); + *status = ICE_ERR_NOT_SUPPORTED; + } + break; + case ICE_ERR_BUF_TOO_SHORT: + /* fall-through */ + case ICE_ERR_CFG: + dev_err(dev, + "The DDP package file is invalid. Entering Safe Mode.\n"); + break; + case ICE_ERR_NOT_SUPPORTED: + /* Package File version not supported */ + if (hw->pkg_ver.major > ICE_PKG_SUPP_VER_MAJ || + (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && + hw->pkg_ver.minor > ICE_PKG_SUPP_VER_MNR)) + dev_err(dev, + "The DDP package file version is higher than the driver supports. Please use an updated driver. Entering Safe Mode.\n"); + else if (hw->pkg_ver.major < ICE_PKG_SUPP_VER_MAJ || + (hw->pkg_ver.major == ICE_PKG_SUPP_VER_MAJ && + hw->pkg_ver.minor < ICE_PKG_SUPP_VER_MNR)) + dev_err(dev, + "The DDP package file version is lower than the driver supports. The driver requires version %d.%d.x.x. Please use an updated DDP Package file. Entering Safe Mode.\n", + ICE_PKG_SUPP_VER_MAJ, ICE_PKG_SUPP_VER_MNR); + break; + case ICE_ERR_AQ_ERROR: + switch (hw->adminq.sq_last_status) { + case ICE_AQ_RC_ENOSEC: + case ICE_AQ_RC_EBADSIG: + dev_err(dev, + "The DDP package could not be loaded because its signature is not valid. Please use a valid DDP Package. Entering Safe Mode.\n"); + return; + case ICE_AQ_RC_ESVN: + dev_err(dev, + "The DDP Package could not be loaded because its security revision is too low. Please use an updated DDP Package. Entering Safe Mode.\n"); + return; + case ICE_AQ_RC_EBADMAN: + case ICE_AQ_RC_EBADBUF: + dev_err(dev, + "An error occurred on the device while loading the DDP package. The device will be reset.\n"); + return; + default: + break; + } + /* fall-through */ + default: + dev_err(dev, + "An unknown error (%d) occurred when loading the DDP package. Entering Safe Mode.\n", + *status); + break; + } +} + +/** + * ice_load_pkg - load/reload the DDP Package file + * @firmware: firmware structure when firmware requested or NULL for reload + * @pf: pointer to the PF instance + * + * Called on probe and post CORER/GLOBR rebuild to load DDP Package and + * initialize HW tables. + */ +static void +ice_load_pkg(const struct firmware *firmware, struct ice_pf *pf) +{ + enum ice_status status = ICE_ERR_PARAM; + struct device *dev = &pf->pdev->dev; + struct ice_hw *hw = &pf->hw; + + /* Load DDP Package */ + if (firmware && !hw->pkg_copy) { + status = ice_copy_and_init_pkg(hw, firmware->data, + firmware->size); + ice_log_pkg_init(hw, &status); + } else if (!firmware && hw->pkg_copy) { + /* Reload package during rebuild after CORER/GLOBR reset */ + status = ice_init_pkg(hw, hw->pkg_copy, hw->pkg_size); + ice_log_pkg_init(hw, &status); + } else { + dev_err(dev, + "The DDP package file failed to load. Entering Safe Mode.\n"); + } + + if (status) { + /* Safe Mode */ + clear_bit(ICE_FLAG_ADV_FEATURES, pf->flags); + return; + } + + /* Successful download package is the precondition for advanced + * features, hence setting the ICE_FLAG_ADV_FEATURES flag + */ + set_bit(ICE_FLAG_ADV_FEATURES, pf->flags); +} + +/** * ice_verify_cacheline_size - verify driver's assumption of 64 Byte cache lines * @pf: pointer to the PF structure * @@ -2272,6 +2683,105 @@ static void ice_verify_cacheline_size(struct ice_pf *pf) } /** + * ice_send_version - update firmware with driver version + * @pf: PF struct + * + * Returns ICE_SUCCESS on success, else error code + */ +static enum ice_status ice_send_version(struct ice_pf *pf) +{ + struct ice_driver_ver dv; + + dv.major_ver = DRV_VERSION_MAJOR; + dv.minor_ver = DRV_VERSION_MINOR; + dv.build_ver = DRV_VERSION_BUILD; + dv.subbuild_ver = 0; + strscpy((char *)dv.driver_string, DRV_VERSION, + sizeof(dv.driver_string)); + return ice_aq_send_driver_ver(&pf->hw, &dv, NULL); +} + +/** + * ice_get_opt_fw_name - return optional firmware file name or NULL + * @pf: pointer to the PF instance + */ +static char *ice_get_opt_fw_name(struct ice_pf *pf) +{ + /* Optional firmware name same as default with additional dash + * followed by a EUI-64 identifier (PCIe Device Serial Number) + */ + struct pci_dev *pdev = pf->pdev; + char *opt_fw_filename = NULL; + u32 dword; + u8 dsn[8]; + int pos; + + /* Determine the name of the optional file using the DSN (two + * dwords following the start of the DSN Capability). + */ + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DSN); + if (pos) { + opt_fw_filename = kzalloc(NAME_MAX, GFP_KERNEL); + if (!opt_fw_filename) + return NULL; + + pci_read_config_dword(pdev, pos + 4, &dword); + put_unaligned_le32(dword, &dsn[0]); + pci_read_config_dword(pdev, pos + 8, &dword); + put_unaligned_le32(dword, &dsn[4]); + snprintf(opt_fw_filename, NAME_MAX, + "%sice-%02x%02x%02x%02x%02x%02x%02x%02x.pkg", + ICE_DDP_PKG_PATH, + dsn[7], dsn[6], dsn[5], dsn[4], + dsn[3], dsn[2], dsn[1], dsn[0]); + } + + return opt_fw_filename; +} + +/** + * ice_request_fw - Device initialization routine + * @pf: pointer to the PF instance + */ +static void ice_request_fw(struct ice_pf *pf) +{ + char *opt_fw_filename = ice_get_opt_fw_name(pf); + const struct firmware *firmware = NULL; + struct device *dev = &pf->pdev->dev; + int err = 0; + + /* optional device-specific DDP (if present) overrides the default DDP + * package file. kernel logs a debug message if the file doesn't exist, + * and warning messages for other errors. + */ + if (opt_fw_filename) { + err = firmware_request_nowarn(&firmware, opt_fw_filename, dev); + if (err) { + kfree(opt_fw_filename); + goto dflt_pkg_load; + } + + /* request for firmware was successful. Download to device */ + ice_load_pkg(firmware, pf); + kfree(opt_fw_filename); + release_firmware(firmware); + return; + } + +dflt_pkg_load: + err = request_firmware(&firmware, ICE_DDP_PKG_FILE, dev); + if (err) { + dev_err(dev, + "The DDP package file was not found or could not be read. Entering Safe Mode\n"); + return; + } + + /* request for firmware was successful. Download to device */ + ice_load_pkg(firmware, pf); + release_firmware(firmware); +} + +/** * ice_probe - Device initialization routine * @pdev: PCI device information struct * @ent: entry in ice_pci_tbl @@ -2345,22 +2855,33 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) goto err_exit_unroll; } - dev_info(dev, "firmware %d.%d.%05d api %d.%d\n", - hw->fw_maj_ver, hw->fw_min_ver, hw->fw_build, - hw->api_maj_ver, hw->api_min_ver); + dev_info(dev, "firmware %d.%d.%d api %d.%d.%d nvm %s build 0x%08x\n", + hw->fw_maj_ver, hw->fw_min_ver, hw->fw_patch, + hw->api_maj_ver, hw->api_min_ver, hw->api_patch, + ice_nvm_version_str(hw), hw->fw_build); - ice_init_pf(pf); + ice_request_fw(pf); - err = ice_init_pf_dcb(pf, false); - if (err) { - clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); - clear_bit(ICE_FLAG_DCB_ENA, pf->flags); - - /* do not fail overall init if DCB init fails */ - err = 0; + /* if ice_request_fw fails, ICE_FLAG_ADV_FEATURES bit won't be + * set in pf->state, which will cause ice_is_safe_mode to return + * true + */ + if (ice_is_safe_mode(pf)) { + dev_err(dev, + "Package download failed. Advanced features disabled - Device now in Safe Mode\n"); + /* we already got function/device capabilities but these don't + * reflect what the driver needs to do in safe mode. Instead of + * adding conditional logic everywhere to ignore these + * device/function capabilities, override them. + */ + ice_set_safe_mode_caps(hw); } - ice_determine_q_usage(pf); + err = ice_init_pf(pf); + if (err) { + dev_err(dev, "ice_init_pf failed: %d\n", err); + goto err_init_pf_unroll; + } pf->num_alloc_vsi = hw->func_caps.guar_num_vsi; if (!pf->num_alloc_vsi) { @@ -2390,12 +2911,10 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) * the misc functionality and queue processing is combined in * the same vector and that gets setup at open. */ - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - err = ice_req_irq_msix_misc(pf); - if (err) { - dev_err(dev, "setup of misc vector failed: %d\n", err); - goto err_init_interrupt_unroll; - } + err = ice_req_irq_msix_misc(pf); + if (err) { + dev_err(dev, "setup of misc vector failed: %d\n", err); + goto err_init_interrupt_unroll; } /* create switch struct for the switch element created by FW on boot */ @@ -2423,6 +2942,15 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) clear_bit(__ICE_SERVICE_DIS, pf->state); + /* tell the firmware we are up */ + err = ice_send_version(pf); + if (err) { + dev_err(dev, + "probe failed sending driver version %s. error: %d\n", + ice_drv_ver, err); + goto err_alloc_sw_unroll; + } + /* since everything is good, start the service timer */ mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period)); @@ -2434,6 +2962,20 @@ ice_probe(struct pci_dev *pdev, const struct pci_device_id __always_unused *ent) ice_verify_cacheline_size(pf); + /* If no DDP driven features have to be setup, return here */ + if (ice_is_safe_mode(pf)) + return 0; + + /* initialize DDP driven features */ + + /* Note: DCB init failure is non-fatal to load */ + if (ice_init_pf_dcb(pf, false)) { + clear_bit(ICE_FLAG_DCB_CAPABLE, pf->flags); + clear_bit(ICE_FLAG_DCB_ENA, pf->flags); + } else { + ice_cfg_lldp_mib_change(&pf->hw, true); + } + return 0; err_alloc_sw_unroll: @@ -2483,9 +3025,14 @@ static void ice_remove(struct pci_dev *pdev) continue; ice_vsi_free_q_vectors(pf->vsi[i]); } - ice_clear_interrupt_scheme(pf); ice_deinit_pf(pf); ice_deinit_hw(&pf->hw); + ice_clear_interrupt_scheme(pf); + /* Issue a PFR as part of the prescribed driver unload flow. Do not + * do it via ice_schedule_reset() since there is no need to rebuild + * and the service task is already stopped. + */ + ice_reset(&pf->hw, ICE_RESET_PFR); pci_disable_pcie_error_reporting(pdev); } @@ -2711,10 +3258,8 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) struct ice_hw *hw = &pf->hw; struct sockaddr *addr = pi; enum ice_status status; - LIST_HEAD(a_mac_list); - LIST_HEAD(r_mac_list); u8 flags = 0; - int err; + int err = 0; u8 *mac; mac = (u8 *)addr->sa_data; @@ -2737,42 +3282,23 @@ static int ice_set_mac_address(struct net_device *netdev, void *pi) /* When we change the MAC address we also have to change the MAC address * based filter rules that were created previously for the old MAC * address. So first, we remove the old filter rule using ice_remove_mac - * and then create a new filter rule using ice_add_mac. Note that for - * both these operations, we first need to form a "list" of MAC - * addresses (even though in this case, we have only 1 MAC address to be - * added/removed) and this done using ice_add_mac_to_list. Depending on - * the ensuing operation this "list" of MAC addresses is either to be - * added or removed from the filter. + * and then create a new filter rule using ice_add_mac via + * ice_vsi_cfg_mac_fltr function call for both add and/or remove + * filters. */ - err = ice_add_mac_to_list(vsi, &r_mac_list, netdev->dev_addr); - if (err) { - err = -EADDRNOTAVAIL; - goto free_lists; - } - - status = ice_remove_mac(hw, &r_mac_list); + status = ice_vsi_cfg_mac_fltr(vsi, netdev->dev_addr, false); if (status) { err = -EADDRNOTAVAIL; - goto free_lists; + goto err_update_filters; } - err = ice_add_mac_to_list(vsi, &a_mac_list, mac); - if (err) { - err = -EADDRNOTAVAIL; - goto free_lists; - } - - status = ice_add_mac(hw, &a_mac_list); + status = ice_vsi_cfg_mac_fltr(vsi, mac, true); if (status) { err = -EADDRNOTAVAIL; - goto free_lists; + goto err_update_filters; } -free_lists: - /* free list entries */ - ice_free_fltr_list(&pf->pdev->dev, &r_mac_list); - ice_free_fltr_list(&pf->pdev->dev, &a_mac_list); - +err_update_filters: if (err) { netdev_err(netdev, "can't set MAC %pM. filter update failed\n", mac); @@ -2788,8 +3314,8 @@ free_lists: flags = ICE_AQC_MAN_MAC_UPDATE_LAA_WOL; status = ice_aq_manage_mac_write(hw, mac, flags, NULL); if (status) { - netdev_err(netdev, "can't set MAC %pM. write to firmware failed.\n", - mac); + netdev_err(netdev, "can't set MAC %pM. write to firmware failed error %d\n", + mac, status); } return 0; } @@ -2902,6 +3428,13 @@ ice_set_features(struct net_device *netdev, netdev_features_t features) struct ice_vsi *vsi = np->vsi; int ret = 0; + /* Don't set any netdev advanced features with device in Safe Mode */ + if (ice_is_safe_mode(vsi->back)) { + dev_err(&vsi->back->pdev->dev, + "Device is in Safe Mode - not enabling advanced netdev features\n"); + return ret; + } + /* Multiple features can be changed in one call so keep features in * separate if/else statements to guarantee each feature is checked */ @@ -3008,10 +3541,7 @@ static int ice_up_complete(struct ice_vsi *vsi) struct ice_pf *pf = vsi->back; int err; - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - ice_vsi_cfg_msix(vsi); - else - return -ENOTSUPP; + ice_vsi_cfg_msix(vsi); /* Enable only Rx rings, Tx rings were enabled by the FW when the * Tx queue group list was configured and the context bits were @@ -3132,7 +3662,7 @@ static void ice_update_vsi_ring_stats(struct ice_vsi *vsi) * ice_update_vsi_stats - Update VSI stats counters * @vsi: the VSI to be updated */ -static void ice_update_vsi_stats(struct ice_vsi *vsi) +void ice_update_vsi_stats(struct ice_vsi *vsi) { struct rtnl_link_stats64 *cur_ns = &vsi->net_stats; struct ice_eth_stats *cur_es = &vsi->eth_stats; @@ -3159,6 +3689,8 @@ static void ice_update_vsi_stats(struct ice_vsi *vsi) cur_ns->rx_errors = pf->stats.crc_errors + pf->stats.illegal_bytes; cur_ns->rx_length_errors = pf->stats.rx_len_errors; + /* record drops from the port level */ + cur_ns->rx_missed_errors = pf->stats.eth.rx_discards; } } @@ -3166,149 +3698,139 @@ static void ice_update_vsi_stats(struct ice_vsi *vsi) * ice_update_pf_stats - Update PF port stats counters * @pf: PF whose stats needs to be updated */ -static void ice_update_pf_stats(struct ice_pf *pf) +void ice_update_pf_stats(struct ice_pf *pf) { struct ice_hw_port_stats *prev_ps, *cur_ps; struct ice_hw *hw = &pf->hw; - u8 pf_id; + u8 port; + port = hw->port_info->lport; prev_ps = &pf->stats_prev; cur_ps = &pf->stats; - pf_id = hw->pf_id; - ice_stat_update40(hw, GLPRT_GORCH(pf_id), GLPRT_GORCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.rx_bytes, + ice_stat_update40(hw, GLPRT_GORCL(port), pf->stat_prev_loaded, + &prev_ps->eth.rx_bytes, &cur_ps->eth.rx_bytes); - ice_stat_update40(hw, GLPRT_UPRCH(pf_id), GLPRT_UPRCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.rx_unicast, + ice_stat_update40(hw, GLPRT_UPRCL(port), pf->stat_prev_loaded, + &prev_ps->eth.rx_unicast, &cur_ps->eth.rx_unicast); - ice_stat_update40(hw, GLPRT_MPRCH(pf_id), GLPRT_MPRCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.rx_multicast, + ice_stat_update40(hw, GLPRT_MPRCL(port), pf->stat_prev_loaded, + &prev_ps->eth.rx_multicast, &cur_ps->eth.rx_multicast); - ice_stat_update40(hw, GLPRT_BPRCH(pf_id), GLPRT_BPRCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.rx_broadcast, + ice_stat_update40(hw, GLPRT_BPRCL(port), pf->stat_prev_loaded, + &prev_ps->eth.rx_broadcast, &cur_ps->eth.rx_broadcast); - ice_stat_update40(hw, GLPRT_GOTCH(pf_id), GLPRT_GOTCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.tx_bytes, + ice_stat_update32(hw, PRTRPB_RDPC, pf->stat_prev_loaded, + &prev_ps->eth.rx_discards, + &cur_ps->eth.rx_discards); + + ice_stat_update40(hw, GLPRT_GOTCL(port), pf->stat_prev_loaded, + &prev_ps->eth.tx_bytes, &cur_ps->eth.tx_bytes); - ice_stat_update40(hw, GLPRT_UPTCH(pf_id), GLPRT_UPTCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.tx_unicast, + ice_stat_update40(hw, GLPRT_UPTCL(port), pf->stat_prev_loaded, + &prev_ps->eth.tx_unicast, &cur_ps->eth.tx_unicast); - ice_stat_update40(hw, GLPRT_MPTCH(pf_id), GLPRT_MPTCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.tx_multicast, + ice_stat_update40(hw, GLPRT_MPTCL(port), pf->stat_prev_loaded, + &prev_ps->eth.tx_multicast, &cur_ps->eth.tx_multicast); - ice_stat_update40(hw, GLPRT_BPTCH(pf_id), GLPRT_BPTCL(pf_id), - pf->stat_prev_loaded, &prev_ps->eth.tx_broadcast, + ice_stat_update40(hw, GLPRT_BPTCL(port), pf->stat_prev_loaded, + &prev_ps->eth.tx_broadcast, &cur_ps->eth.tx_broadcast); - ice_stat_update32(hw, GLPRT_TDOLD(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_TDOLD(port), pf->stat_prev_loaded, &prev_ps->tx_dropped_link_down, &cur_ps->tx_dropped_link_down); - ice_stat_update40(hw, GLPRT_PRC64H(pf_id), GLPRT_PRC64L(pf_id), - pf->stat_prev_loaded, &prev_ps->rx_size_64, - &cur_ps->rx_size_64); + ice_stat_update40(hw, GLPRT_PRC64L(port), pf->stat_prev_loaded, + &prev_ps->rx_size_64, &cur_ps->rx_size_64); - ice_stat_update40(hw, GLPRT_PRC127H(pf_id), GLPRT_PRC127L(pf_id), - pf->stat_prev_loaded, &prev_ps->rx_size_127, - &cur_ps->rx_size_127); + ice_stat_update40(hw, GLPRT_PRC127L(port), pf->stat_prev_loaded, + &prev_ps->rx_size_127, &cur_ps->rx_size_127); - ice_stat_update40(hw, GLPRT_PRC255H(pf_id), GLPRT_PRC255L(pf_id), - pf->stat_prev_loaded, &prev_ps->rx_size_255, - &cur_ps->rx_size_255); + ice_stat_update40(hw, GLPRT_PRC255L(port), pf->stat_prev_loaded, + &prev_ps->rx_size_255, &cur_ps->rx_size_255); - ice_stat_update40(hw, GLPRT_PRC511H(pf_id), GLPRT_PRC511L(pf_id), - pf->stat_prev_loaded, &prev_ps->rx_size_511, - &cur_ps->rx_size_511); + ice_stat_update40(hw, GLPRT_PRC511L(port), pf->stat_prev_loaded, + &prev_ps->rx_size_511, &cur_ps->rx_size_511); - ice_stat_update40(hw, GLPRT_PRC1023H(pf_id), - GLPRT_PRC1023L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PRC1023L(port), pf->stat_prev_loaded, &prev_ps->rx_size_1023, &cur_ps->rx_size_1023); - ice_stat_update40(hw, GLPRT_PRC1522H(pf_id), - GLPRT_PRC1522L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PRC1522L(port), pf->stat_prev_loaded, &prev_ps->rx_size_1522, &cur_ps->rx_size_1522); - ice_stat_update40(hw, GLPRT_PRC9522H(pf_id), - GLPRT_PRC9522L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PRC9522L(port), pf->stat_prev_loaded, &prev_ps->rx_size_big, &cur_ps->rx_size_big); - ice_stat_update40(hw, GLPRT_PTC64H(pf_id), GLPRT_PTC64L(pf_id), - pf->stat_prev_loaded, &prev_ps->tx_size_64, - &cur_ps->tx_size_64); + ice_stat_update40(hw, GLPRT_PTC64L(port), pf->stat_prev_loaded, + &prev_ps->tx_size_64, &cur_ps->tx_size_64); - ice_stat_update40(hw, GLPRT_PTC127H(pf_id), GLPRT_PTC127L(pf_id), - pf->stat_prev_loaded, &prev_ps->tx_size_127, - &cur_ps->tx_size_127); + ice_stat_update40(hw, GLPRT_PTC127L(port), pf->stat_prev_loaded, + &prev_ps->tx_size_127, &cur_ps->tx_size_127); - ice_stat_update40(hw, GLPRT_PTC255H(pf_id), GLPRT_PTC255L(pf_id), - pf->stat_prev_loaded, &prev_ps->tx_size_255, - &cur_ps->tx_size_255); + ice_stat_update40(hw, GLPRT_PTC255L(port), pf->stat_prev_loaded, + &prev_ps->tx_size_255, &cur_ps->tx_size_255); - ice_stat_update40(hw, GLPRT_PTC511H(pf_id), GLPRT_PTC511L(pf_id), - pf->stat_prev_loaded, &prev_ps->tx_size_511, - &cur_ps->tx_size_511); + ice_stat_update40(hw, GLPRT_PTC511L(port), pf->stat_prev_loaded, + &prev_ps->tx_size_511, &cur_ps->tx_size_511); - ice_stat_update40(hw, GLPRT_PTC1023H(pf_id), - GLPRT_PTC1023L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PTC1023L(port), pf->stat_prev_loaded, &prev_ps->tx_size_1023, &cur_ps->tx_size_1023); - ice_stat_update40(hw, GLPRT_PTC1522H(pf_id), - GLPRT_PTC1522L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PTC1522L(port), pf->stat_prev_loaded, &prev_ps->tx_size_1522, &cur_ps->tx_size_1522); - ice_stat_update40(hw, GLPRT_PTC9522H(pf_id), - GLPRT_PTC9522L(pf_id), pf->stat_prev_loaded, + ice_stat_update40(hw, GLPRT_PTC9522L(port), pf->stat_prev_loaded, &prev_ps->tx_size_big, &cur_ps->tx_size_big); - ice_stat_update32(hw, GLPRT_LXONRXC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_LXONRXC(port), pf->stat_prev_loaded, &prev_ps->link_xon_rx, &cur_ps->link_xon_rx); - ice_stat_update32(hw, GLPRT_LXOFFRXC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_LXOFFRXC(port), pf->stat_prev_loaded, &prev_ps->link_xoff_rx, &cur_ps->link_xoff_rx); - ice_stat_update32(hw, GLPRT_LXONTXC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_LXONTXC(port), pf->stat_prev_loaded, &prev_ps->link_xon_tx, &cur_ps->link_xon_tx); - ice_stat_update32(hw, GLPRT_LXOFFTXC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_LXOFFTXC(port), pf->stat_prev_loaded, &prev_ps->link_xoff_tx, &cur_ps->link_xoff_tx); ice_update_dcb_stats(pf); - ice_stat_update32(hw, GLPRT_CRCERRS(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_CRCERRS(port), pf->stat_prev_loaded, &prev_ps->crc_errors, &cur_ps->crc_errors); - ice_stat_update32(hw, GLPRT_ILLERRC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_ILLERRC(port), pf->stat_prev_loaded, &prev_ps->illegal_bytes, &cur_ps->illegal_bytes); - ice_stat_update32(hw, GLPRT_MLFC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_MLFC(port), pf->stat_prev_loaded, &prev_ps->mac_local_faults, &cur_ps->mac_local_faults); - ice_stat_update32(hw, GLPRT_MRFC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_MRFC(port), pf->stat_prev_loaded, &prev_ps->mac_remote_faults, &cur_ps->mac_remote_faults); - ice_stat_update32(hw, GLPRT_RLEC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_RLEC(port), pf->stat_prev_loaded, &prev_ps->rx_len_errors, &cur_ps->rx_len_errors); - ice_stat_update32(hw, GLPRT_RUC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_RUC(port), pf->stat_prev_loaded, &prev_ps->rx_undersize, &cur_ps->rx_undersize); - ice_stat_update32(hw, GLPRT_RFC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_RFC(port), pf->stat_prev_loaded, &prev_ps->rx_fragments, &cur_ps->rx_fragments); - ice_stat_update32(hw, GLPRT_ROC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_ROC(port), pf->stat_prev_loaded, &prev_ps->rx_oversize, &cur_ps->rx_oversize); - ice_stat_update32(hw, GLPRT_RJC(pf_id), pf->stat_prev_loaded, + ice_stat_update32(hw, GLPRT_RJC(port), pf->stat_prev_loaded, &prev_ps->rx_jabber, &cur_ps->rx_jabber); pf->stat_prev_loaded = true; @@ -3328,12 +3850,16 @@ void ice_get_stats64(struct net_device *netdev, struct rtnl_link_stats64 *stats) vsi_stats = &vsi->net_stats; - if (test_bit(__ICE_DOWN, vsi->state) || !vsi->num_txq || !vsi->num_rxq) + if (!vsi->num_txq || !vsi->num_rxq) return; + /* netdev packet/byte stats come from ring counter. These are obtained * by summing up ring counters (done by ice_update_vsi_ring_stats). + * But, only call the update routine and read the registers if VSI is + * not down. */ - ice_update_vsi_ring_stats(vsi); + if (!test_bit(__ICE_DOWN, vsi->state)) + ice_update_vsi_ring_stats(vsi); stats->tx_packets = vsi_stats->tx_packets; stats->tx_bytes = vsi_stats->tx_bytes; stats->rx_packets = vsi_stats->rx_packets; @@ -3372,85 +3898,6 @@ static void ice_napi_disable_all(struct ice_vsi *vsi) } /** - * ice_force_phys_link_state - Force the physical link state - * @vsi: VSI to force the physical link state to up/down - * @link_up: true/false indicates to set the physical link to up/down - * - * Force the physical link state by getting the current PHY capabilities from - * hardware and setting the PHY config based on the determined capabilities. If - * link changes a link event will be triggered because both the Enable Automatic - * Link Update and LESM Enable bits are set when setting the PHY capabilities. - * - * Returns 0 on success, negative on failure - */ -static int ice_force_phys_link_state(struct ice_vsi *vsi, bool link_up) -{ - struct ice_aqc_get_phy_caps_data *pcaps; - struct ice_aqc_set_phy_cfg_data *cfg; - struct ice_port_info *pi; - struct device *dev; - int retcode; - - if (!vsi || !vsi->port_info || !vsi->back) - return -EINVAL; - if (vsi->type != ICE_VSI_PF) - return 0; - - dev = &vsi->back->pdev->dev; - - pi = vsi->port_info; - - pcaps = devm_kzalloc(dev, sizeof(*pcaps), GFP_KERNEL); - if (!pcaps) - return -ENOMEM; - - retcode = ice_aq_get_phy_caps(pi, false, ICE_AQC_REPORT_SW_CFG, pcaps, - NULL); - if (retcode) { - dev_err(dev, - "Failed to get phy capabilities, VSI %d error %d\n", - vsi->vsi_num, retcode); - retcode = -EIO; - goto out; - } - - /* No change in link */ - if (link_up == !!(pcaps->caps & ICE_AQC_PHY_EN_LINK) && - link_up == !!(pi->phy.link_info.link_info & ICE_AQ_LINK_UP)) - goto out; - - cfg = devm_kzalloc(dev, sizeof(*cfg), GFP_KERNEL); - if (!cfg) { - retcode = -ENOMEM; - goto out; - } - - cfg->phy_type_low = pcaps->phy_type_low; - cfg->phy_type_high = pcaps->phy_type_high; - cfg->caps = pcaps->caps | ICE_AQ_PHY_ENA_AUTO_LINK_UPDT; - cfg->low_power_ctrl = pcaps->low_power_ctrl; - cfg->eee_cap = pcaps->eee_cap; - cfg->eeer_value = pcaps->eeer_value; - cfg->link_fec_opt = pcaps->link_fec_options; - if (link_up) - cfg->caps |= ICE_AQ_PHY_ENA_LINK; - else - cfg->caps &= ~ICE_AQ_PHY_ENA_LINK; - - retcode = ice_aq_set_phy_cfg(&vsi->back->hw, pi->lport, cfg, NULL); - if (retcode) { - dev_err(dev, "Failed to set phy config, VSI %d error %d\n", - vsi->vsi_num, retcode); - retcode = -EIO; - } - - devm_kfree(dev, cfg); -out: - devm_kfree(dev, pcaps); - return retcode; -} - -/** * ice_down - Shutdown the connection * @vsi: The VSI being stopped */ @@ -3559,24 +4006,6 @@ int ice_vsi_setup_rx_rings(struct ice_vsi *vsi) } /** - * ice_vsi_req_irq - Request IRQ from the OS - * @vsi: The VSI IRQ is being requested for - * @basename: name for the vector - * - * Return 0 on success and a negative value on error - */ -static int ice_vsi_req_irq(struct ice_vsi *vsi, char *basename) -{ - struct ice_pf *pf = vsi->back; - int err = -EINVAL; - - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - err = ice_vsi_req_irq_msix(vsi, basename); - - return err; -} - -/** * ice_vsi_open - Called when a network interface is made active * @vsi: the VSI to open * @@ -3605,7 +4034,7 @@ static int ice_vsi_open(struct ice_vsi *vsi) snprintf(int_name, sizeof(int_name) - 1, "%s-%s", dev_driver_string(&pf->pdev->dev), vsi->netdev->name); - err = ice_vsi_req_irq(vsi, int_name); + err = ice_vsi_req_irq_msix(vsi, int_name); if (err) goto err_setup_rx; @@ -3669,23 +4098,19 @@ static int ice_ena_vsi(struct ice_vsi *vsi, bool locked) int err = 0; if (!test_bit(__ICE_NEEDS_RESTART, vsi->state)) - return err; + return 0; clear_bit(__ICE_NEEDS_RESTART, vsi->state); if (vsi->netdev && vsi->type == ICE_VSI_PF) { - struct net_device *netd = vsi->netdev; - if (netif_running(vsi->netdev)) { - if (locked) { - err = netd->netdev_ops->ndo_open(netd); - } else { + if (!locked) rtnl_lock(); - err = netd->netdev_ops->ndo_open(netd); + + err = ice_open(vsi->netdev); + + if (!locked) rtnl_unlock(); - } - } else { - err = ice_vsi_open(vsi); } } @@ -3699,9 +4124,6 @@ static int ice_ena_vsi(struct ice_vsi *vsi, bool locked) */ #ifdef CONFIG_DCB int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked) -#else -static int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked) -#endif /* CONFIG_DCB */ { int v; @@ -3712,91 +4134,107 @@ static int ice_pf_ena_all_vsi(struct ice_pf *pf, bool locked) return 0; } +#endif /* CONFIG_DCB */ /** - * ice_vsi_rebuild_all - rebuild all VSIs in PF - * @pf: the PF + * ice_vsi_rebuild_by_type - Rebuild VSI of a given type + * @pf: pointer to the PF instance + * @type: VSI type to rebuild + * + * Iterates through the pf->vsi array and rebuilds VSIs of the requested type */ -static int ice_vsi_rebuild_all(struct ice_pf *pf) +static int ice_vsi_rebuild_by_type(struct ice_pf *pf, enum ice_vsi_type type) { - int i; + enum ice_status status; + int i, err; - /* loop through pf->vsi array and reinit the VSI if found */ ice_for_each_vsi(pf, i) { - int err; + struct ice_vsi *vsi = pf->vsi[i]; - if (!pf->vsi[i]) + if (!vsi || vsi->type != type) continue; - err = ice_vsi_rebuild(pf->vsi[i]); + /* rebuild the VSI */ + err = ice_vsi_rebuild(vsi); if (err) { dev_err(&pf->pdev->dev, - "VSI at index %d rebuild failed\n", - pf->vsi[i]->idx); + "rebuild VSI failed, err %d, VSI index %d, type %d\n", + err, vsi->idx, type); return err; } - dev_info(&pf->pdev->dev, - "VSI at index %d rebuilt. vsi_num = 0x%x\n", - pf->vsi[i]->idx, pf->vsi[i]->vsi_num); + /* replay filters for the VSI */ + status = ice_replay_vsi(&pf->hw, vsi->idx); + if (status) { + dev_err(&pf->pdev->dev, + "replay VSI failed, status %d, VSI index %d, type %d\n", + status, vsi->idx, type); + return -EIO; + } + + /* Re-map HW VSI number, using VSI handle that has been + * previously validated in ice_replay_vsi() call above + */ + vsi->vsi_num = ice_get_hw_vsi_num(&pf->hw, vsi->idx); + + /* enable the VSI */ + err = ice_ena_vsi(vsi, false); + if (err) { + dev_err(&pf->pdev->dev, + "enable VSI failed, err %d, VSI index %d, type %d\n", + err, vsi->idx, type); + return err; + } + + dev_info(&pf->pdev->dev, "VSI rebuilt. VSI index %d, type %d\n", + vsi->idx, type); } return 0; } /** - * ice_vsi_replay_all - replay all VSIs configuration in the PF - * @pf: the PF + * ice_update_pf_netdev_link - Update PF netdev link status + * @pf: pointer to the PF instance */ -static int ice_vsi_replay_all(struct ice_pf *pf) +static void ice_update_pf_netdev_link(struct ice_pf *pf) { - struct ice_hw *hw = &pf->hw; - enum ice_status ret; + bool link_up; int i; - /* loop through pf->vsi array and replay the VSI if found */ ice_for_each_vsi(pf, i) { - if (!pf->vsi[i]) - continue; + struct ice_vsi *vsi = pf->vsi[i]; - ret = ice_replay_vsi(hw, pf->vsi[i]->idx); - if (ret) { - dev_err(&pf->pdev->dev, - "VSI at index %d replay failed %d\n", - pf->vsi[i]->idx, ret); - return -EIO; - } - - /* Re-map HW VSI number, using VSI handle that has been - * previously validated in ice_replay_vsi() call above - */ - pf->vsi[i]->vsi_num = ice_get_hw_vsi_num(hw, pf->vsi[i]->idx); + if (!vsi || vsi->type != ICE_VSI_PF) + return; - dev_info(&pf->pdev->dev, - "VSI at index %d filter replayed successfully - vsi_num %i\n", - pf->vsi[i]->idx, pf->vsi[i]->vsi_num); + ice_get_link_status(pf->vsi[i]->port_info, &link_up); + if (link_up) { + netif_carrier_on(pf->vsi[i]->netdev); + netif_tx_wake_all_queues(pf->vsi[i]->netdev); + } else { + netif_carrier_off(pf->vsi[i]->netdev); + netif_tx_stop_all_queues(pf->vsi[i]->netdev); + } } - - /* Clean up replay filter after successful re-configuration */ - ice_replay_post(hw); - return 0; } /** * ice_rebuild - rebuild after reset * @pf: PF to rebuild + * @reset_type: type of reset */ -static void ice_rebuild(struct ice_pf *pf) +static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type) { struct device *dev = &pf->pdev->dev; struct ice_hw *hw = &pf->hw; enum ice_status ret; - int err, i; + int err; if (test_bit(__ICE_DOWN, pf->state)) goto clear_recovery; - dev_dbg(dev, "rebuilding PF\n"); + dev_dbg(dev, "rebuilding PF after reset_type=%d\n", reset_type); ret = ice_init_all_ctrlq(hw); if (ret) { @@ -3804,6 +4242,16 @@ static void ice_rebuild(struct ice_pf *pf) goto err_init_ctrlq; } + /* if DDP was previously loaded successfully */ + if (!ice_is_safe_mode(pf)) { + /* reload the SW DB of filter tables */ + if (reset_type == ICE_RESET_PFR) + ice_fill_blk_tbls(hw); + else + /* Reload DDP Package after CORER/GLOBR reset */ + ice_load_pkg(NULL, pf); + } + ret = ice_clear_pf_cfg(hw); if (ret) { dev_err(dev, "clear PF configuration failed %d\n", ret); @@ -3822,65 +4270,53 @@ static void ice_rebuild(struct ice_pf *pf) if (err) goto err_sched_init_port; - ice_dcb_rebuild(pf); + err = ice_update_link_info(hw->port_info); + if (err) + dev_err(&pf->pdev->dev, "Get link status error %d\n", err); - err = ice_vsi_rebuild_all(pf); + /* start misc vector */ + err = ice_req_irq_msix_misc(pf); if (err) { - dev_err(dev, "ice_vsi_rebuild_all failed\n"); - goto err_vsi_rebuild; + dev_err(dev, "misc vector setup failed: %d\n", err); + goto err_sched_init_port; } - err = ice_update_link_info(hw->port_info); - if (err) - dev_err(&pf->pdev->dev, "Get link status error %d\n", err); + if (test_bit(ICE_FLAG_DCB_ENA, pf->flags)) + ice_dcb_rebuild(pf); - /* Replay all VSIs Configuration, including filters after reset */ - if (ice_vsi_replay_all(pf)) { - dev_err(&pf->pdev->dev, - "error replaying VSI configurations with switch filter rules\n"); + /* rebuild PF VSI */ + err = ice_vsi_rebuild_by_type(pf, ICE_VSI_PF); + if (err) { + dev_err(dev, "PF VSI rebuild failed: %d\n", err); goto err_vsi_rebuild; } - /* start misc vector */ - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) { - err = ice_req_irq_msix_misc(pf); + if (test_bit(ICE_FLAG_SRIOV_ENA, pf->flags)) { + err = ice_vsi_rebuild_by_type(pf, ICE_VSI_VF); if (err) { - dev_err(dev, "misc vector setup failed: %d\n", err); + dev_err(dev, "VF VSI rebuild failed: %d\n", err); goto err_vsi_rebuild; } } - /* restart the VSIs that were rebuilt and running before the reset */ - err = ice_pf_ena_all_vsi(pf, false); - if (err) { - dev_err(&pf->pdev->dev, "error enabling VSIs\n"); - /* no need to disable VSIs in tear down path in ice_rebuild() - * since its already taken care in ice_vsi_open() - */ + ice_update_pf_netdev_link(pf); + + /* tell the firmware we are up */ + ret = ice_send_version(pf); + if (ret) { + dev_err(dev, + "Rebuild failed due to error sending driver version: %d\n", + ret); goto err_vsi_rebuild; } - ice_for_each_vsi(pf, i) { - bool link_up; - - if (!pf->vsi[i] || pf->vsi[i]->type != ICE_VSI_PF) - continue; - ice_get_link_status(pf->vsi[i]->port_info, &link_up); - if (link_up) { - netif_carrier_on(pf->vsi[i]->netdev); - netif_tx_wake_all_queues(pf->vsi[i]->netdev); - } else { - netif_carrier_off(pf->vsi[i]->netdev); - netif_tx_stop_all_queues(pf->vsi[i]->netdev); - } - } + ice_replay_post(hw); /* if we get here, reset flow is successful */ clear_bit(__ICE_RESET_FAILED, pf->state); return; err_vsi_rebuild: - ice_vsi_release_all(pf); err_sched_init_port: ice_sched_cleanup_all(hw); err_init_ctrlq: @@ -4244,9 +4680,7 @@ static void ice_tx_timeout(struct net_device *netdev) 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(hw, - GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); + val = rd32(hw, GLINT_DYN_CTL(tx_ring->q_vector->reg_idx)); 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, @@ -4295,6 +4729,7 @@ int ice_open(struct net_device *netdev) { struct ice_netdev_priv *np = netdev_priv(netdev); struct ice_vsi *vsi = np->vsi; + struct ice_port_info *pi; int err; if (test_bit(__ICE_NEEDS_RESTART, vsi->back->state)) { @@ -4304,13 +4739,33 @@ int ice_open(struct net_device *netdev) netif_carrier_off(netdev); - err = ice_force_phys_link_state(vsi, true); + pi = vsi->port_info; + err = ice_update_link_info(pi); if (err) { - netdev_err(netdev, - "Failed to set physical link up, error %d\n", err); + netdev_err(netdev, "Failed to get link info, error %d\n", + err); return err; } + /* Set PHY if there is media, otherwise, turn off PHY */ + if (pi->phy.link_info.link_info & ICE_AQ_MEDIA_AVAILABLE) { + err = ice_force_phys_link_state(vsi, true); + if (err) { + netdev_err(netdev, + "Failed to set physical link up, error %d\n", + err); + return err; + } + } else { + err = ice_aq_set_link_restart_an(pi, false, NULL); + if (err) { + netdev_err(netdev, "Failed to set PHY state, VSI %d error %d\n", + vsi->vsi_num, err); + return err; + } + set_bit(ICE_FLAG_NO_MEDIA, vsi->back->flags); + } + err = ice_vsi_open(vsi); if (err) netdev_err(netdev, "Failed to open VSI 0x%04X on switch 0x%04X\n", @@ -4388,6 +4843,17 @@ out_rm_features: return features & ~(NETIF_F_CSUM_MASK | NETIF_F_GSO_MASK); } +static const struct net_device_ops ice_netdev_safe_mode_ops = { + .ndo_open = ice_open, + .ndo_stop = ice_stop, + .ndo_start_xmit = ice_start_xmit, + .ndo_set_mac_address = ice_set_mac_address, + .ndo_validate_addr = eth_validate_addr, + .ndo_change_mtu = ice_change_mtu, + .ndo_get_stats64 = ice_get_stats64, + .ndo_tx_timeout = ice_tx_timeout, +}; + static const struct net_device_ops ice_netdev_ops = { .ndo_open = ice_open, .ndo_stop = ice_stop, diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c index 2a232504379d..fc624b73d05d 100644 --- a/drivers/net/ethernet/intel/ice/ice_sched.c +++ b/drivers/net/ethernet/intel/ice/ice_sched.c @@ -260,33 +260,17 @@ ice_sched_remove_elems(struct ice_hw *hw, struct ice_sched_node *parent, /** * ice_sched_get_first_node - get the first node of the given layer - * @hw: pointer to the HW struct + * @pi: port information structure * @parent: pointer the base node of the subtree * @layer: layer number * * This function retrieves the first node of the given layer from the subtree */ static struct ice_sched_node * -ice_sched_get_first_node(struct ice_hw *hw, struct ice_sched_node *parent, - u8 layer) +ice_sched_get_first_node(struct ice_port_info *pi, + struct ice_sched_node *parent, u8 layer) { - u8 i; - - if (layer < hw->sw_entry_point_layer) - return NULL; - for (i = 0; i < parent->num_children; i++) { - struct ice_sched_node *node = parent->children[i]; - - if (node) { - if (node->tx_sched_layer == layer) - return node; - /* this recursion is intentional, and wouldn't - * go more than 9 calls - */ - return ice_sched_get_first_node(hw, node, layer); - } - } - return NULL; + return pi->sib_head[parent->tc_num][layer]; } /** @@ -300,7 +284,7 @@ struct ice_sched_node *ice_sched_get_tc_node(struct ice_port_info *pi, u8 tc) { u8 i; - if (!pi) + if (!pi || !pi->root) return NULL; for (i = 0; i < pi->root->num_children; i++) if (pi->root->children[i]->tc_num == tc) @@ -342,7 +326,7 @@ void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node) parent = node->parent; /* root has no parent */ if (parent) { - struct ice_sched_node *p, *tc_node; + struct ice_sched_node *p; /* update the parent */ for (i = 0; i < parent->num_children; i++) @@ -354,16 +338,7 @@ void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node) break; } - /* search for previous sibling that points to this node and - * remove the reference - */ - tc_node = ice_sched_get_tc_node(pi, node->tc_num); - if (!tc_node) { - ice_debug(hw, ICE_DBG_SCHED, - "Invalid TC number %d\n", node->tc_num); - goto err_exit; - } - p = ice_sched_get_first_node(hw, tc_node, node->tx_sched_layer); + p = ice_sched_get_first_node(pi, node, node->tx_sched_layer); while (p) { if (p->sibling == node) { p->sibling = node->sibling; @@ -371,8 +346,13 @@ void ice_free_sched_node(struct ice_port_info *pi, struct ice_sched_node *node) } p = p->sibling; } + + /* update the sibling head if head is getting removed */ + if (pi->sib_head[node->tc_num][node->tx_sched_layer] == node) + pi->sib_head[node->tc_num][node->tx_sched_layer] = + node->sibling; } -err_exit: + /* leaf nodes have no children */ if (node->children) devm_kfree(ice_hw_to_dev(hw), node->children); @@ -743,13 +723,17 @@ ice_sched_add_elems(struct ice_port_info *pi, struct ice_sched_node *tc_node, /* add it to previous node sibling pointer */ /* Note: siblings are not linked across branches */ - prev = ice_sched_get_first_node(hw, tc_node, layer); + prev = ice_sched_get_first_node(pi, tc_node, layer); if (prev && prev != new_node) { while (prev->sibling) prev = prev->sibling; prev->sibling = new_node; } + /* initialize the sibling head */ + if (!pi->sib_head[tc_node->tc_num][layer]) + pi->sib_head[tc_node->tc_num][layer] = new_node; + if (i == 0) *first_node_teid = teid; } @@ -1160,7 +1144,7 @@ ice_sched_get_free_qparent(struct ice_port_info *pi, u16 vsi_handle, u8 tc, goto lan_q_exit; /* get the first queue group node from VSI sub-tree */ - qgrp_node = ice_sched_get_first_node(pi->hw, vsi_node, qgrp_layer); + qgrp_node = ice_sched_get_first_node(pi, vsi_node, qgrp_layer); while (qgrp_node) { /* make sure the qgroup node is part of the VSI subtree */ if (ice_sched_find_node_in_subtree(pi->hw, vsi_node, qgrp_node)) @@ -1191,7 +1175,7 @@ ice_sched_get_vsi_node(struct ice_hw *hw, struct ice_sched_node *tc_node, u8 vsi_layer; vsi_layer = ice_sched_get_vsi_layer(hw); - node = ice_sched_get_first_node(hw, tc_node, vsi_layer); + node = ice_sched_get_first_node(hw->port_info, tc_node, vsi_layer); /* Check whether it already exists */ while (node) { @@ -1316,7 +1300,8 @@ ice_sched_calc_vsi_support_nodes(struct ice_hw *hw, /* If intermediate nodes are reached max children * then add a new one. */ - node = ice_sched_get_first_node(hw, tc_node, (u8)i); + node = ice_sched_get_first_node(hw->port_info, tc_node, + (u8)i); /* scan all the siblings */ while (node) { if (node->num_children < hw->max_children[i]) diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 8271fd651725..1acdd43a2edd 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -1623,12 +1623,13 @@ ice_remove_rule_internal(struct ice_hw *hw, u8 recp_id, status = ice_aq_sw_rules(hw, s_rule, ICE_SW_RULE_RX_TX_NO_HDR_SIZE, 1, ice_aqc_opc_remove_sw_rules, NULL); - if (status) - goto exit; /* Remove a book keeping from the list */ devm_kfree(ice_hw_to_dev(hw), s_rule); + if (status) + goto exit; + list_del(&list_elem->list_entry); devm_kfree(ice_hw_to_dev(hw), list_elem); } @@ -2137,6 +2138,38 @@ out: } /** + * ice_find_ucast_rule_entry - Search for a unicast MAC filter rule entry + * @hw: pointer to the hardware structure + * @recp_id: lookup type for which the specified rule needs to be searched + * @f_info: rule information + * + * Helper function to search for a unicast rule entry - this is to be used + * to remove unicast MAC filter that is not shared with other VSIs on the + * PF switch. + * + * Returns pointer to entry storing the rule if found + */ +static struct ice_fltr_mgmt_list_entry * +ice_find_ucast_rule_entry(struct ice_hw *hw, u8 recp_id, + struct ice_fltr_info *f_info) +{ + struct ice_switch_info *sw = hw->switch_info; + struct ice_fltr_mgmt_list_entry *list_itr; + struct list_head *list_head; + + list_head = &sw->recp_list[recp_id].filt_rules; + list_for_each_entry(list_itr, list_head, list_entry) { + if (!memcmp(&f_info->l_data, &list_itr->fltr_info.l_data, + sizeof(f_info->l_data)) && + f_info->fwd_id.hw_vsi_id == + list_itr->fltr_info.fwd_id.hw_vsi_id && + f_info->flag == list_itr->fltr_info.flag) + return list_itr; + } + return NULL; +} + +/** * ice_remove_mac - remove a MAC address based filter rule * @hw: pointer to the hardware structure * @m_list: list of MAC addresses and forwarding information @@ -2153,15 +2186,39 @@ enum ice_status ice_remove_mac(struct ice_hw *hw, struct list_head *m_list) { struct ice_fltr_list_entry *list_itr, *tmp; + struct mutex *rule_lock; /* Lock to protect filter rule list */ if (!m_list) return ICE_ERR_PARAM; + rule_lock = &hw->switch_info->recp_list[ICE_SW_LKUP_MAC].filt_rule_lock; list_for_each_entry_safe(list_itr, tmp, m_list, list_entry) { enum ice_sw_lkup_type l_type = list_itr->fltr_info.lkup_type; + u8 *add = &list_itr->fltr_info.l_data.mac.mac_addr[0]; + u16 vsi_handle; if (l_type != ICE_SW_LKUP_MAC) return ICE_ERR_PARAM; + + vsi_handle = list_itr->fltr_info.vsi_handle; + if (!ice_is_vsi_valid(hw, vsi_handle)) + return ICE_ERR_PARAM; + + list_itr->fltr_info.fwd_id.hw_vsi_id = + ice_get_hw_vsi_num(hw, vsi_handle); + if (is_unicast_ether_addr(add) && !hw->ucast_shared) { + /* Don't remove the unicast address that belongs to + * another VSI on the switch, since it is not being + * shared... + */ + mutex_lock(rule_lock); + if (!ice_find_ucast_rule_entry(hw, ICE_SW_LKUP_MAC, + &list_itr->fltr_info)) { + mutex_unlock(rule_lock); + return ICE_ERR_DOES_NOT_EXIST; + } + mutex_unlock(rule_lock); + } list_itr->status = ice_remove_rule_internal(hw, ICE_SW_LKUP_MAC, list_itr); diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c index 3c83230434b6..33dd103035dc 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.c +++ b/drivers/net/ethernet/intel/ice/ice_txrx.c @@ -95,17 +95,16 @@ void ice_free_tx_ring(struct ice_ring *tx_ring) /** * ice_clean_tx_irq - Reclaim resources after transmit completes - * @vsi: the VSI we care about * @tx_ring: Tx ring to clean * @napi_budget: Used to determine if we are in netpoll * * Returns true if there's any budget left (e.g. the clean is finished) */ -static bool -ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring, int napi_budget) +static bool ice_clean_tx_irq(struct ice_ring *tx_ring, int napi_budget) { unsigned int total_bytes = 0, total_pkts = 0; - unsigned int budget = vsi->work_lmt; + unsigned int budget = ICE_DFLT_IRQ_WORK; + struct ice_vsi *vsi = tx_ring->vsi; s16 i = tx_ring->next_to_clean; struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; @@ -114,6 +113,8 @@ ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring, int napi_budget) tx_desc = ICE_TX_DESC(tx_ring, i); i -= tx_ring->count; + prefetch(&vsi->state); + do { struct ice_tx_desc *eop_desc = tx_buf->next_to_watch; @@ -206,7 +207,7 @@ ice_clean_tx_irq(struct ice_vsi *vsi, struct ice_ring *tx_ring, int napi_budget) smp_mb(); if (__netif_subqueue_stopped(tx_ring->netdev, tx_ring->q_index) && - !test_bit(__ICE_DOWN, vsi->state)) { + !test_bit(__ICE_DOWN, vsi->state)) { netif_wake_subqueue(tx_ring->netdev, tx_ring->q_index); ++tx_ring->tx_stats.restart_q; @@ -377,18 +378,28 @@ err: */ static void ice_release_rx_desc(struct ice_ring *rx_ring, u32 val) { + u16 prev_ntu = rx_ring->next_to_use; + rx_ring->next_to_use = val; /* update next to alloc since we have filled the ring */ rx_ring->next_to_alloc = val; - /* 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). + /* QRX_TAIL will be updated with any tail value, but hardware ignores + * the lower 3 bits. This makes it so we only bump tail on meaningful + * boundaries. Also, this allows us to bump tail on intervals of 8 up to + * the budget depending on the current traffic load. */ - wmb(); - writel(val, rx_ring->tail); + val &= ~0x7; + if (prev_ntu != val) { + /* 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). + */ + wmb(); + writel(val, rx_ring->tail); + } } /** @@ -445,7 +456,13 @@ ice_alloc_mapped_page(struct ice_ring *rx_ring, struct ice_rx_buf *bi) * @rx_ring: ring to place buffers on * @cleaned_count: number of buffers to replace * - * Returns false if all allocations were successful, true if any fail + * Returns false if all allocations were successful, true if any fail. Returning + * true signals to the caller that we didn't replace cleaned_count buffers and + * there is more work to do. + * + * First, try to clean "cleaned_count" Rx buffers. Then refill the cleaned Rx + * buffers. Then bump tail at most one time. Grouping like this lets us avoid + * multiple tail writes per call. */ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count) { @@ -462,8 +479,9 @@ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count) bi = &rx_ring->rx_buf[ntu]; do { + /* if we fail here, we have work remaining */ if (!ice_alloc_mapped_page(rx_ring, bi)) - goto no_bufs; + break; /* sync the buffer for use by the device */ dma_sync_single_range_for_device(rx_ring->dev, bi->dma, @@ -494,16 +512,7 @@ bool ice_alloc_rx_bufs(struct ice_ring *rx_ring, u16 cleaned_count) if (rx_ring->next_to_use != ntu) ice_release_rx_desc(rx_ring, ntu); - return false; - -no_bufs: - if (rx_ring->next_to_use != ntu) - ice_release_rx_desc(rx_ring, ntu); - - /* make sure to come back via polling to try again after - * allocation failure - */ - return true; + return !!cleaned_count; } /** @@ -599,6 +608,8 @@ ice_add_rx_frag(struct ice_rx_buf *rx_buf, struct sk_buff *skb, unsigned int truesize = ICE_RXBUF_2048; #endif + if (!size) + return; skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, rx_buf->page, rx_buf->page_offset, size, truesize); @@ -654,6 +665,8 @@ ice_get_rx_buf(struct ice_ring *rx_ring, struct sk_buff **skb, prefetchw(rx_buf->page); *skb = rx_buf->skb; + if (!size) + return rx_buf; /* we are reusing so sync this buffer for CPU use */ dma_sync_single_range_for_cpu(rx_ring->dev, rx_buf->dma, rx_buf->page_offset, size, @@ -737,8 +750,11 @@ ice_construct_skb(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf, */ static void ice_put_rx_buf(struct ice_ring *rx_ring, struct ice_rx_buf *rx_buf) { - /* hand second half of page back to the ring */ + if (!rx_buf) + return; + if (ice_can_reuse_rx_page(rx_buf)) { + /* hand second half of page back to the ring */ ice_reuse_rx_page(rx_ring, rx_buf); rx_ring->rx_stats.page_reuse_count++; } else { @@ -864,7 +880,7 @@ ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, /** * ice_rx_csum - Indicate in skb if checksum is good - * @vsi: the VSI we care about + * @ring: the ring we care about * @skb: skb currently being received and modified * @rx_desc: the receive descriptor * @ptype: the packet type decoded by hardware @@ -872,7 +888,7 @@ ice_rx_hash(struct ice_ring *rx_ring, union ice_32b_rx_flex_desc *rx_desc, * skb->protocol must be set before this function is called */ static void -ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb, +ice_rx_csum(struct ice_ring *ring, struct sk_buff *skb, union ice_32b_rx_flex_desc *rx_desc, u8 ptype) { struct ice_rx_ptype_decoded decoded; @@ -889,7 +905,7 @@ ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb, skb_checksum_none_assert(skb); /* check if Rx checksum is enabled */ - if (!(vsi->netdev->features & NETIF_F_RXCSUM)) + if (!(ring->netdev->features & NETIF_F_RXCSUM)) return; /* check if HW has decoded the packet and checksum */ @@ -929,7 +945,7 @@ ice_rx_csum(struct ice_vsi *vsi, struct sk_buff *skb, return; checksum_fail: - vsi->back->hw_csum_rx_error++; + ring->vsi->back->hw_csum_rx_error++; } /** @@ -953,7 +969,7 @@ ice_process_skb_fields(struct ice_ring *rx_ring, /* modifies the skb - consumes the enet header */ skb->protocol = eth_type_trans(skb, rx_ring->netdev); - ice_rx_csum(rx_ring->vsi, skb, rx_desc, ptype); + ice_rx_csum(rx_ring, skb, rx_desc, ptype); } /** @@ -990,7 +1006,7 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) { unsigned int total_rx_bytes = 0, total_rx_pkts = 0; u16 cleaned_count = ICE_DESC_UNUSED(rx_ring); - bool failure = false; + bool failure; /* start the loop to process Rx packets bounded by 'budget' */ while (likely(total_rx_pkts < (unsigned int)budget)) { @@ -1002,13 +1018,6 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) u16 vlan_tag = 0; u8 rx_ptype; - /* return some buffers to hardware, one at a time is too slow */ - if (cleaned_count >= ICE_RX_BUF_WRITE) { - failure = failure || - ice_alloc_rx_bufs(rx_ring, cleaned_count); - cleaned_count = 0; - } - /* get the Rx desc from Rx ring based on 'next_to_clean' */ rx_desc = ICE_RX_DESC(rx_ring, rx_ring->next_to_clean); @@ -1030,8 +1039,9 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) size = le16_to_cpu(rx_desc->wb.pkt_len) & ICE_RX_FLX_DESC_PKT_LEN_M; + /* retrieve a buffer from the ring */ rx_buf = ice_get_rx_buf(rx_ring, &skb, size); - /* allocate (if needed) and populate skb */ + if (skb) ice_add_rx_frag(rx_buf, skb, size); else @@ -1040,7 +1050,8 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) /* exit if we failed to retrieve a buffer */ if (!skb) { rx_ring->rx_stats.alloc_buf_failed++; - rx_buf->pagecnt_bias++; + if (rx_buf) + rx_buf->pagecnt_bias++; break; } @@ -1057,9 +1068,6 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) continue; } - rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) & - ICE_RX_FLEX_DESC_PTYPE_M; - stat_err_bits = BIT(ICE_RX_FLEX_DESC_STATUS0_L2TAG1P_S); if (ice_test_staterr(rx_desc, stat_err_bits)) vlan_tag = le16_to_cpu(rx_desc->wb.l2tag1); @@ -1076,6 +1084,9 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) total_rx_bytes += skb->len; /* populate checksum, VLAN, and protocol */ + rx_ptype = le16_to_cpu(rx_desc->wb.ptype_flex_flags0) & + ICE_RX_FLEX_DESC_PTYPE_M; + ice_process_skb_fields(rx_ring, rx_desc, skb, rx_ptype); /* send completed skb up the stack */ @@ -1085,6 +1096,9 @@ static int ice_clean_rx_irq(struct ice_ring *rx_ring, int budget) total_rx_pkts++; } + /* return up to cleaned_count buffers to hardware */ + failure = ice_alloc_rx_bufs(rx_ring, cleaned_count); + /* update queue and vector specific stats */ u64_stats_update_begin(&rx_ring->syncp); rx_ring->stats.pkts += total_rx_pkts; @@ -1212,6 +1226,8 @@ ice_update_itr(struct ice_q_vector *q_vector, struct ice_ring_container *rc) if (time_after(next_update, rc->next_update)) goto clear_counts; + prefetch(q_vector->vsi->port_info); + packets = rc->total_pkts; bytes = rc->total_bytes; @@ -1341,16 +1357,32 @@ static u32 ice_buildreg_itr(u16 itr_idx, u16 itr) /** * ice_update_ena_itr - Update ITR and re-enable MSIX interrupt - * @vsi: the VSI associated with the q_vector * @q_vector: q_vector for which ITR is being updated and interrupt enabled */ -static void -ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector) +static void ice_update_ena_itr(struct ice_q_vector *q_vector) { struct ice_ring_container *tx = &q_vector->tx; struct ice_ring_container *rx = &q_vector->rx; + struct ice_vsi *vsi = q_vector->vsi; u32 itr_val; + /* when exiting WB_ON_ITR lets set a low ITR value and trigger + * interrupts to expire right away in case we have more work ready to go + * already + */ + if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE) { + itr_val = ice_buildreg_itr(rx->itr_idx, ICE_WB_ON_ITR_USECS); + wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), itr_val); + /* set target back to last user set value */ + rx->target_itr = rx->itr_setting; + /* set current to what we just wrote and dynamic if needed */ + rx->current_itr = ICE_WB_ON_ITR_USECS | + (rx->itr_setting & ICE_ITR_DYNAMIC); + /* allow normal interrupt flow to start */ + q_vector->itr_countdown = 0; + return; + } + /* This will do nothing if dynamic updates are not enabled */ ice_update_itr(q_vector, tx); ice_update_itr(q_vector, rx); @@ -1389,13 +1421,48 @@ ice_update_ena_itr(struct ice_vsi *vsi, struct ice_q_vector *q_vector) q_vector->itr_countdown--; } - if (!test_bit(__ICE_DOWN, vsi->state)) - wr32(&vsi->back->hw, + if (!test_bit(__ICE_DOWN, q_vector->vsi->state)) + wr32(&q_vector->vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), itr_val); } /** + * ice_set_wb_on_itr - set WB_ON_ITR for this q_vector + * @q_vector: q_vector to set WB_ON_ITR on + * + * We need to tell hardware to write-back completed descriptors even when + * interrupts are disabled. Descriptors will be written back on cache line + * boundaries without WB_ON_ITR enabled, but if we don't enable WB_ON_ITR + * descriptors may not be written back if they don't fill a cache line until the + * next interrupt. + * + * This sets the write-back frequency to 2 microseconds as that is the minimum + * value that's not 0 due to ITR granularity. Also, set the INTENA_MSK bit to + * make sure hardware knows we aren't meddling with the INTENA_M bit. + */ +static void ice_set_wb_on_itr(struct ice_q_vector *q_vector) +{ + struct ice_vsi *vsi = q_vector->vsi; + + /* already in WB_ON_ITR mode no need to change it */ + if (q_vector->itr_countdown == ICE_IN_WB_ON_ITR_MODE) + return; + + if (q_vector->num_ring_rx) + wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), + ICE_GLINT_DYN_CTL_WB_ON_ITR(ICE_WB_ON_ITR_USECS, + ICE_RX_ITR)); + + if (q_vector->num_ring_tx) + wr32(&vsi->back->hw, GLINT_DYN_CTL(q_vector->reg_idx), + ICE_GLINT_DYN_CTL_WB_ON_ITR(ICE_WB_ON_ITR_USECS, + ICE_TX_ITR)); + + q_vector->itr_countdown = ICE_IN_WB_ON_ITR_MODE; +} + +/** * ice_napi_poll - NAPI polling Rx/Tx cleanup routine * @napi: napi struct with our devices info in it * @budget: amount of work driver is allowed to do this pass, in packets @@ -1408,29 +1475,32 @@ int ice_napi_poll(struct napi_struct *napi, int budget) { struct ice_q_vector *q_vector = container_of(napi, struct ice_q_vector, napi); - struct ice_vsi *vsi = q_vector->vsi; - struct ice_pf *pf = vsi->back; bool clean_complete = true; - int budget_per_ring = 0; struct ice_ring *ring; + int budget_per_ring; int work_done = 0; /* Since the actual Tx work is minimal, we can give the Tx a larger * budget and be more aggressive about cleaning up the Tx descriptors. */ ice_for_each_ring(ring, q_vector->tx) - if (!ice_clean_tx_irq(vsi, ring, budget)) + if (!ice_clean_tx_irq(ring, budget)) clean_complete = false; /* Handle case where we are called by netpoll with a budget of 0 */ - if (budget <= 0) + if (unlikely(budget <= 0)) return budget; - /* We attempt to distribute budget to each Rx queue fairly, but don't - * allow the budget to go below 1 because that would exit polling early. - */ - if (q_vector->num_ring_rx) + /* normally we have 1 Rx ring per q_vector */ + if (unlikely(q_vector->num_ring_rx > 1)) + /* We attempt to distribute budget to each Rx queue fairly, but + * don't allow the budget to go below 1 because that would exit + * polling early. + */ budget_per_ring = max(budget / q_vector->num_ring_rx, 1); + else + /* Max of 1 Rx ring in this q_vector so give it the budget */ + budget_per_ring = budget; ice_for_each_ring(ring, q_vector->rx) { int cleaned; @@ -1450,8 +1520,9 @@ int ice_napi_poll(struct napi_struct *napi, int budget) * poll us due to busy-polling */ if (likely(napi_complete_done(napi, work_done))) - if (test_bit(ICE_FLAG_MSIX_ENA, pf->flags)) - ice_update_ena_itr(vsi, q_vector); + ice_update_ena_itr(q_vector); + else + ice_set_wb_on_itr(q_vector); return min_t(int, work_done, budget - 1); } @@ -1521,7 +1592,7 @@ ice_tx_map(struct ice_ring *tx_ring, struct ice_tx_buf *first, { u64 td_offset, td_tag, td_cmd; u16 i = tx_ring->next_to_use; - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned int data_len, size; struct ice_tx_desc *tx_desc; struct ice_tx_buf *tx_buf; @@ -1923,7 +1994,7 @@ static unsigned int ice_txd_use_count(unsigned int size) */ static unsigned int ice_xmit_desc_count(struct sk_buff *skb) { - const struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; unsigned int nr_frags = skb_shinfo(skb)->nr_frags; unsigned int count = 0, size = skb_headlen(skb); @@ -1954,7 +2025,7 @@ static unsigned int ice_xmit_desc_count(struct sk_buff *skb) */ static bool __ice_chk_linearize(struct sk_buff *skb) { - const struct skb_frag_struct *frag, *stale; + const skb_frag_t *frag, *stale; int nr_frags, sum; /* no need to check if number of frags is less than 7 */ @@ -2036,6 +2107,7 @@ static netdev_tx_t ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) { struct ice_tx_offload_params offload = { 0 }; + struct ice_vsi *vsi = tx_ring->vsi; struct ice_tx_buf *first; unsigned int count; int tso, csum; @@ -2083,7 +2155,15 @@ ice_xmit_frame_ring(struct sk_buff *skb, struct ice_ring *tx_ring) if (csum < 0) goto out_drop; - if (tso || offload.cd_tunnel_params) { + /* allow CONTROL frames egress from main VSI if FW LLDP disabled */ + if (unlikely(skb->priority == TC_PRIO_CONTROL && + vsi->type == ICE_VSI_PF && + vsi->port_info->is_sw_lldp)) + offload.cd_qw1 |= (u64)(ICE_TX_DESC_DTYPE_CTX | + ICE_TX_CTX_DESC_SWTCH_UPLINK << + ICE_TXD_CTX_QW1_CMD_S); + + if (offload.cd_qw1 & ICE_TX_DESC_DTYPE_CTX) { struct ice_tx_ctx_desc *cdesc; int i = tx_ring->next_to_use; diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.h b/drivers/net/ethernet/intel/ice/ice_txrx.h index ec76aba347b9..94a9280193e2 100644 --- a/drivers/net/ethernet/intel/ice/ice_txrx.h +++ b/drivers/net/ethernet/intel/ice/ice_txrx.h @@ -144,6 +144,19 @@ enum ice_rx_dtype { #define ICE_DFLT_INTRL 0 #define ICE_MAX_INTRL 236 +#define ICE_WB_ON_ITR_USECS 2 +#define ICE_IN_WB_ON_ITR_MODE 255 +/* Sets WB_ON_ITR and assumes INTENA bit is already cleared, which allows + * setting the MSK_M bit to tell hardware to ignore the INTENA_M bit. Also, + * set the write-back latency to the usecs passed in. + */ +#define ICE_GLINT_DYN_CTL_WB_ON_ITR(usecs, itr_idx) \ + ((((usecs) << (GLINT_DYN_CTL_INTERVAL_S - ICE_ITR_GRAN_S)) & \ + GLINT_DYN_CTL_INTERVAL_M) | \ + (((itr_idx) << GLINT_DYN_CTL_ITR_INDX_S) & \ + GLINT_DYN_CTL_ITR_INDX_M) | GLINT_DYN_CTL_INTENA_MSK_M | \ + GLINT_DYN_CTL_WB_ON_ITR_M) + /* Legacy or Advanced Mode Queue */ #define ICE_TX_ADVANCED 0 #define ICE_TX_LEGACY 1 diff --git a/drivers/net/ethernet/intel/ice/ice_type.h b/drivers/net/ethernet/intel/ice/ice_type.h index 24bbef8bbe69..6667d17a4206 100644 --- a/drivers/net/ethernet/intel/ice/ice_type.h +++ b/drivers/net/ethernet/intel/ice/ice_type.h @@ -4,18 +4,19 @@ #ifndef _ICE_TYPE_H_ #define _ICE_TYPE_H_ +#define ICE_BYTES_PER_WORD 2 +#define ICE_BYTES_PER_DWORD 4 + #include "ice_status.h" #include "ice_hw_autogen.h" #include "ice_osdep.h" #include "ice_controlq.h" #include "ice_lan_tx_rx.h" +#include "ice_flex_type.h" -#define ICE_BYTES_PER_WORD 2 -#define ICE_BYTES_PER_DWORD 4 - -static inline bool ice_is_tc_ena(u8 bitmap, u8 tc) +static inline bool ice_is_tc_ena(unsigned long bitmap, u8 tc) { - return test_bit(tc, (unsigned long *)&bitmap); + return test_bit(tc, &bitmap); } /* Driver always calls main vsi_handle first */ @@ -31,6 +32,7 @@ static inline bool ice_is_tc_ena(u8 bitmap, u8 tc) #define ICE_DBG_LAN BIT_ULL(8) #define ICE_DBG_SW BIT_ULL(13) #define ICE_DBG_SCHED BIT_ULL(14) +#define ICE_DBG_PKG BIT_ULL(16) #define ICE_DBG_RES BIT_ULL(17) #define ICE_DBG_AQ_MSG BIT_ULL(24) #define ICE_DBG_AQ_CMD BIT_ULL(27) @@ -53,6 +55,14 @@ enum ice_aq_res_access_type { ICE_RES_WRITE }; +struct ice_driver_ver { + u8 major_ver; + u8 minor_ver; + u8 build_ver; + u8 subbuild_ver; + u8 driver_string[32]; +}; + enum ice_fc_mode { ICE_FC_NONE = 0, ICE_FC_RX_PAUSE, @@ -139,6 +149,9 @@ struct ice_phy_info { /* Common HW capabilities for SW use */ struct ice_hw_common_caps { u32 valid_functions; + /* DCB capabilities */ + u32 active_tc_bitmap; + u32 maxtc; /* Tx/Rx queues */ u16 num_rxq; /* Number/Total Rx queues */ @@ -219,6 +232,8 @@ struct ice_nvm_info { u8 blank_nvm_mode; /* is NVM empty (no FW present) */ }; +#define ICE_NVM_VER_LEN 32 + /* Max number of port to queue branches w.r.t topology */ #define ICE_MAX_TRAFFIC_CLASS 8 #define ICE_TXSCHED_MAX_BRANCHES ICE_MAX_TRAFFIC_CLASS @@ -347,6 +362,8 @@ struct ice_port_info { struct ice_mac_info mac; struct ice_phy_info phy; struct mutex sched_lock; /* protect access to TXSched tree */ + struct ice_sched_node * + sib_head[ICE_MAX_TRAFFIC_CLASS][ICE_AQC_TOPO_MAX_LEVEL_NUM]; struct ice_dcbx_cfg local_dcbx_cfg; /* Oper/Local Cfg */ /* DCBX info */ struct ice_dcbx_cfg remote_dcbx_cfg; /* Peer Cfg */ @@ -454,6 +471,30 @@ struct ice_hw { u8 ucast_shared; /* true if VSIs can share unicast addr */ + /* Active package version (currently active) */ + struct ice_pkg_ver active_pkg_ver; + u8 active_pkg_name[ICE_PKG_NAME_SIZE]; + u8 active_pkg_in_nvm; + + enum ice_aq_err pkg_dwnld_status; + + /* Driver's package ver - (from the Metadata seg) */ + struct ice_pkg_ver pkg_ver; + u8 pkg_name[ICE_PKG_NAME_SIZE]; + + /* Driver's Ice package version (from the Ice seg) */ + struct ice_pkg_ver ice_pkg_ver; + u8 ice_pkg_name[ICE_PKG_NAME_SIZE]; + + /* Pointer to the ice segment */ + struct ice_seg *seg; + + /* Pointer to allocated copy of pkg memory */ + u8 *pkg_copy; + u32 pkg_size; + + /* HW block tables */ + struct ice_blk_info blk[ICE_BLK_COUNT]; }; /* Statistics collected by each port, VSI, VEB, and S-channel */ diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c index 5d24b539648f..b45797f39b2f 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c @@ -129,7 +129,10 @@ static void ice_vc_notify_vf_link_state(struct ice_vf *vf) pfe.event = VIRTCHNL_EVENT_LINK_CHANGE; pfe.severity = PF_EVENT_SEVERITY_INFO; - if (vf->link_forced) + /* Always report link is down if the VF queues aren't enabled */ + if (!vf->num_qs_ena) + ice_set_pfe_link(vf, &pfe, ICE_AQ_LINK_SPEED_UNKNOWN, false); + else if (vf->link_forced) ice_set_pfe_link_forced(vf, &pfe, vf->link_up); else ice_set_pfe_link(vf, &pfe, ls->link_speed, ls->link_info & @@ -252,6 +255,35 @@ static int ice_sriov_free_msix_res(struct ice_pf *pf) } /** + * ice_set_vf_state_qs_dis - Set VF queues state to disabled + * @vf: pointer to the VF structure + */ +void ice_set_vf_state_qs_dis(struct ice_vf *vf) +{ + /* Clear Rx/Tx enabled queues flag */ + bitmap_zero(vf->txq_ena, ICE_MAX_BASE_QS_PER_VF); + bitmap_zero(vf->rxq_ena, ICE_MAX_BASE_QS_PER_VF); + vf->num_qs_ena = 0; + clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); +} + +/** + * ice_dis_vf_qs - Disable the VF queues + * @vf: pointer to the VF structure + */ +static void ice_dis_vf_qs(struct ice_vf *vf) +{ + struct ice_pf *pf = vf->pf; + struct ice_vsi *vsi; + + vsi = pf->vsi[vf->lan_vsi_idx]; + + ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id); + ice_vsi_stop_rx_rings(vsi); + ice_set_vf_state_qs_dis(vf); +} + +/** * ice_free_vfs - Free all VFs * @pf: pointer to the PF structure */ @@ -267,19 +299,9 @@ void ice_free_vfs(struct ice_pf *pf) usleep_range(1000, 2000); /* Avoid wait time by stopping all VFs at the same time */ - for (i = 0; i < pf->num_alloc_vfs; i++) { - struct ice_vsi *vsi; - - if (!test_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states)) - continue; - - vsi = pf->vsi[pf->vf[i].lan_vsi_idx]; - /* stop rings without wait time */ - ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, i); - ice_vsi_stop_rx_rings(vsi); - - clear_bit(ICE_VF_STATE_ENA, pf->vf[i].vf_states); - } + for (i = 0; i < pf->num_alloc_vfs; i++) + if (test_bit(ICE_VF_STATE_QS_ENA, pf->vf[i].vf_states)) + ice_dis_vf_qs(&pf->vf[i]); /* Disable IOV before freeing resources. This lets any VF drivers * running in the host get themselves cleaned up before we yank @@ -297,13 +319,6 @@ void ice_free_vfs(struct ice_pf *pf) if (test_bit(ICE_VF_STATE_INIT, pf->vf[i].vf_states)) { /* disable VF qp mappings */ ice_dis_vf_mappings(&pf->vf[i]); - - /* Set this state so that assigned VF vectors can be - * reclaimed by PF for reuse in ice_vsi_release(). No - * need to clear this bit since pf->vf array is being - * freed anyways after this for loop - */ - set_bit(ICE_VF_STATE_CFG_INTR, pf->vf[i].vf_states); ice_free_vf_res(&pf->vf[i]); } } @@ -341,12 +356,13 @@ void ice_free_vfs(struct ice_pf *pf) * ice_trigger_vf_reset - Reset a VF on HW * @vf: pointer to the VF structure * @is_vflr: true if VFLR was issued, false if not + * @is_pfr: true if the reset was triggered due to a previous PFR * * Trigger hardware to start a reset for a particular VF. Expects the caller * to wait the proper amount of time to allow hardware to reset the VF before * it cleans up and restores VF functionality. */ -static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr) +static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr, bool is_pfr) { struct ice_pf *pf = vf->pf; u32 reg, reg_idx, bit_idx; @@ -367,10 +383,13 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr) */ clear_bit(ICE_VF_STATE_INIT, vf->vf_states); - /* Clear the VF's ARQLEN register. This is how the VF detects reset, - * since the VFGEN_RSTAT register doesn't stick at 0 after reset. + /* VF_MBX_ARQLEN is cleared by PFR, so the driver needs to clear it + * in the case of VFR. If this is done for PFR, it can mess up VF + * resets because the VF driver may already have started cleanup + * by the time we get here. */ - wr32(hw, VF_MBX_ARQLEN(vf_abs_id), 0); + if (!is_pfr) + wr32(hw, VF_MBX_ARQLEN(vf_abs_id), 0); /* In the case of a VFLR, the HW has already reset the VF and we * just need to clean up, so don't hit the VFRTRIG register. @@ -389,12 +408,15 @@ static void ice_trigger_vf_reset(struct ice_vf *vf, bool is_vflr) wr32(hw, PF_PCI_CIAA, VF_DEVICE_STATUS | (vf_abs_id << PF_PCI_CIAA_VF_NUM_S)); - for (i = 0; i < 100; i++) { + for (i = 0; i < ICE_PCI_CIAD_WAIT_COUNT; i++) { reg = rd32(hw, PF_PCI_CIAD); - if ((reg & VF_TRANS_PENDING_M) != 0) - dev_err(&pf->pdev->dev, - "VF %d PCI transactions stuck\n", vf->vf_id); - udelay(1); + /* no transactions pending so stop polling */ + if ((reg & VF_TRANS_PENDING_M) == 0) + break; + + dev_err(&pf->pdev->dev, + "VF %d PCI transactions stuck\n", vf->vf_id); + udelay(ICE_PCI_CIAD_WAIT_DELAY_US); } } @@ -481,19 +503,20 @@ ice_vf_vsi_setup(struct ice_pf *pf, struct ice_port_info *pi, u16 vf_id) } /** - * ice_calc_vf_first_vector_idx - Calculate absolute MSIX vector index in HW + * ice_calc_vf_first_vector_idx - Calculate MSIX vector index in the PF space * @pf: pointer to PF structure * @vf: pointer to VF that the first MSIX vector index is being calculated for * - * This returns the first MSIX vector index in HW that is used by this VF and - * this will always be the OICR index in the AVF driver so any functionality + * This returns the first MSIX vector index in PF space that is used by this VF. + * This index is used when accessing PF relative registers such as + * GLINT_VECT2FUNC and GLINT_DYN_CTL. + * This will always be the OICR index in the AVF driver so any functionality * using vf->first_vector_idx for queue configuration will have to increment by * 1 to avoid meddling with the OICR index. */ static int ice_calc_vf_first_vector_idx(struct ice_pf *pf, struct ice_vf *vf) { - return pf->hw.func_caps.common_cap.msix_vector_first_id + - pf->sriov_base_vector + vf->vf_id * pf->num_vf_msix; + return pf->sriov_base_vector + vf->vf_id * pf->num_vf_msix; } /** @@ -543,7 +566,10 @@ static int ice_alloc_vsi_res(struct ice_vf *vf) status = ice_add_mac(&pf->hw, &tmp_add_list); if (status) - dev_err(&pf->pdev->dev, "could not add mac filters\n"); + dev_err(&pf->pdev->dev, + "could not add mac filters error %d\n", status); + else + vf->num_mac = 1; /* Clear this bit after VF initialization since we shouldn't reclaim * and reassign interrupts for synchronous or asynchronous VFR events. @@ -551,7 +577,6 @@ static int ice_alloc_vsi_res(struct ice_vf *vf) * expect vector assignment to be changed unless there is a request for * more vectors. */ - clear_bit(ICE_VF_STATE_CFG_INTR, vf->vf_states); ice_alloc_vsi_res_exit: ice_free_fltr_list(&pf->pdev->dev, &tmp_add_list); return status; @@ -567,20 +592,21 @@ static int ice_alloc_vf_res(struct ice_vf *vf) int tx_rx_queue_left; int status; - /* setup VF VSI and necessary resources */ - status = ice_alloc_vsi_res(vf); - if (status) - goto ice_alloc_vf_res_exit; - /* Update number of VF queues, in case VF had requested for queue * changes */ - tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx); + tx_rx_queue_left = min_t(int, ice_get_avail_txq_count(pf), + ice_get_avail_rxq_count(pf)); tx_rx_queue_left += ICE_DFLT_QS_PER_VF; if (vf->num_req_qs && vf->num_req_qs <= tx_rx_queue_left && vf->num_req_qs != vf->num_vf_qs) vf->num_vf_qs = vf->num_req_qs; + /* setup VF VSI and necessary resources */ + status = ice_alloc_vsi_res(vf); + if (status) + goto ice_alloc_vf_res_exit; + if (vf->trusted) set_bit(ICE_VIRTCHNL_VF_CAP_PRIVILEGE, &vf->vf_caps); else @@ -605,27 +631,30 @@ ice_alloc_vf_res_exit: */ static void ice_ena_vf_mappings(struct ice_vf *vf) { + int abs_vf_id, abs_first, abs_last; struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; int first, last, v; struct ice_hw *hw; - int abs_vf_id; u32 reg; hw = &pf->hw; vsi = pf->vsi[vf->lan_vsi_idx]; first = vf->first_vector_idx; last = (first + pf->num_vf_msix) - 1; + abs_first = first + pf->hw.func_caps.common_cap.msix_vector_first_id; + abs_last = (abs_first + pf->num_vf_msix) - 1; abs_vf_id = vf->vf_id + hw->func_caps.vf_base_id; /* VF Vector allocation */ - reg = (((first << VPINT_ALLOC_FIRST_S) & VPINT_ALLOC_FIRST_M) | - ((last << VPINT_ALLOC_LAST_S) & VPINT_ALLOC_LAST_M) | + reg = (((abs_first << VPINT_ALLOC_FIRST_S) & VPINT_ALLOC_FIRST_M) | + ((abs_last << VPINT_ALLOC_LAST_S) & VPINT_ALLOC_LAST_M) | VPINT_ALLOC_VALID_M); wr32(hw, VPINT_ALLOC(vf->vf_id), reg); - reg = (((first << VPINT_ALLOC_PCI_FIRST_S) & VPINT_ALLOC_PCI_FIRST_M) | - ((last << VPINT_ALLOC_PCI_LAST_S) & VPINT_ALLOC_PCI_LAST_M) | + reg = (((abs_first << VPINT_ALLOC_PCI_FIRST_S) + & VPINT_ALLOC_PCI_FIRST_M) | + ((abs_last << VPINT_ALLOC_PCI_LAST_S) & VPINT_ALLOC_PCI_LAST_M) | VPINT_ALLOC_PCI_VALID_M); wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg); /* map the interrupts to its functions */ @@ -870,11 +899,11 @@ static int ice_check_avail_res(struct ice_pf *pf) * at runtime through Virtchnl, that is the reason we start by reserving * few queues. */ - num_txq = ice_determine_res(pf, pf->q_left_tx, ICE_DFLT_QS_PER_VF, - ICE_MIN_QS_PER_VF); + num_txq = ice_determine_res(pf, ice_get_avail_txq_count(pf), + ICE_DFLT_QS_PER_VF, ICE_MIN_QS_PER_VF); - num_rxq = ice_determine_res(pf, pf->q_left_rx, ICE_DFLT_QS_PER_VF, - ICE_MIN_QS_PER_VF); + num_rxq = ice_determine_res(pf, ice_get_avail_rxq_count(pf), + ICE_DFLT_QS_PER_VF, ICE_MIN_QS_PER_VF); if (!num_txq || !num_rxq) return -EIO; @@ -983,6 +1012,47 @@ ice_vf_set_vsi_promisc(struct ice_vf *vf, struct ice_vsi *vsi, u8 promisc_m, } /** + * ice_config_res_vfs - Finalize allocation of VFs resources in one go + * @pf: pointer to the PF structure + * + * This function is being called as last part of resetting all VFs, or when + * configuring VFs for the first time, where there is no resource to be freed + * Returns true if resources were properly allocated for all VFs, and false + * otherwise. + */ +static bool ice_config_res_vfs(struct ice_pf *pf) +{ + struct ice_hw *hw = &pf->hw; + int v; + + if (ice_check_avail_res(pf)) { + dev_err(&pf->pdev->dev, + "Cannot allocate VF resources, try with fewer number of VFs\n"); + return false; + } + + /* rearm global interrupts */ + if (test_and_clear_bit(__ICE_OICR_INTR_DIS, pf->state)) + ice_irq_dynamic_ena(hw, NULL, NULL); + + /* Finish resetting each VF and allocate resources */ + for (v = 0; v < pf->num_alloc_vfs; v++) { + struct ice_vf *vf = &pf->vf[v]; + + vf->num_vf_qs = pf->num_vf_qps; + dev_dbg(&pf->pdev->dev, + "VF-id %d has %d queues configured\n", + vf->vf_id, vf->num_vf_qs); + ice_cleanup_and_realloc_vf(vf); + } + + ice_flush(hw); + clear_bit(__ICE_VF_DIS, pf->state); + + return true; +} + +/** * ice_reset_all_vfs - reset all allocated VFs in one go * @pf: pointer to the PF structure * @is_vflr: true if VFLR was issued, false if not @@ -1010,18 +1080,17 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) /* Begin reset on all VFs at once */ for (v = 0; v < pf->num_alloc_vfs; v++) - ice_trigger_vf_reset(&pf->vf[v], is_vflr); + ice_trigger_vf_reset(&pf->vf[v], is_vflr, true); for (v = 0; v < pf->num_alloc_vfs; v++) { struct ice_vsi *vsi; vf = &pf->vf[v]; vsi = pf->vsi[vf->lan_vsi_idx]; - if (test_bit(ICE_VF_STATE_ENA, vf->vf_states)) { - ice_vsi_stop_lan_tx_rings(vsi, ICE_VF_RESET, vf->vf_id); - ice_vsi_stop_rx_rings(vsi); - clear_bit(ICE_VF_STATE_ENA, vf->vf_states); - } + if (test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) + ice_dis_vf_qs(vf); + ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL, + NULL, ICE_VF_RESET, vf->vf_id, NULL); } /* HW requires some time to make sure it can flush the FIFO for a VF @@ -1031,7 +1100,6 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) * finished resetting. */ for (i = 0, v = 0; i < 10 && v < pf->num_alloc_vfs; i++) { - usleep_range(10000, 20000); /* Check each VF in sequence */ while (v < pf->num_alloc_vfs) { @@ -1039,8 +1107,11 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) vf = &pf->vf[v]; reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id)); - if (!(reg & VPGEN_VFRSTAT_VFRD_M)) + if (!(reg & VPGEN_VFRSTAT_VFRD_M)) { + /* only delay if the check failed */ + usleep_range(10, 20); break; + } /* If the current VF has finished resetting, move on * to the next VF in sequence. @@ -1054,7 +1125,6 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) */ if (v < pf->num_alloc_vfs) dev_warn(&pf->pdev->dev, "VF reset check timeout\n"); - usleep_range(10000, 20000); /* free VF resources to begin resetting the VSI state */ for (v = 0; v < pf->num_alloc_vfs; v++) { @@ -1074,25 +1144,8 @@ bool ice_reset_all_vfs(struct ice_pf *pf, bool is_vflr) dev_err(&pf->pdev->dev, "Failed to free MSIX resources used by SR-IOV\n"); - if (ice_check_avail_res(pf)) { - dev_err(&pf->pdev->dev, - "Cannot allocate VF resources, try with fewer number of VFs\n"); + if (!ice_config_res_vfs(pf)) return false; - } - - /* Finish the reset on each VF */ - for (v = 0; v < pf->num_alloc_vfs; v++) { - vf = &pf->vf[v]; - - vf->num_vf_qs = pf->num_vf_qps; - dev_dbg(&pf->pdev->dev, - "VF-id %d has %d queues configured\n", - vf->vf_id, vf->num_vf_qs); - ice_cleanup_and_realloc_vf(vf); - } - - ice_flush(hw); - clear_bit(__ICE_VF_DIS, pf->state); return true; } @@ -1114,27 +1167,31 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) u32 reg; int i; - /* If the VFs have been disabled, this means something else is - * resetting the VF, so we shouldn't continue. + /* If the PF has been disabled, there is no need resetting VF until + * PF is active again. */ - if (test_and_set_bit(__ICE_VF_DIS, pf->state)) + if (test_bit(__ICE_VF_DIS, pf->state)) return false; - ice_trigger_vf_reset(vf, is_vflr); + /* If the VF has been disabled, this means something else is + * resetting the VF, so we shouldn't continue. Otherwise, set + * disable VF state bit for actual reset, and continue. + */ + if (test_and_set_bit(ICE_VF_STATE_DIS, vf->vf_states)) + return false; + + ice_trigger_vf_reset(vf, is_vflr, false); vsi = pf->vsi[vf->lan_vsi_idx]; - if (test_bit(ICE_VF_STATE_ENA, vf->vf_states)) { - ice_vsi_stop_lan_tx_rings(vsi, ICE_VF_RESET, vf->vf_id); - ice_vsi_stop_rx_rings(vsi); - clear_bit(ICE_VF_STATE_ENA, vf->vf_states); - } else { - /* Call Disable LAN Tx queue AQ call even when queues are not - * enabled. This is needed for successful completiom of VFR - */ - ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL, - NULL, ICE_VF_RESET, vf->vf_id, NULL); - } + if (test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) + ice_dis_vf_qs(vf); + + /* Call Disable LAN Tx queue AQ whether or not queues are + * enabled. This is needed for successful completion of VFR. + */ + ice_dis_vsi_txq(vsi->port_info, vsi->idx, 0, 0, NULL, NULL, + NULL, ICE_VF_RESET, vf->vf_id, NULL); hw = &pf->hw; /* poll VPGEN_VFRSTAT reg to make sure @@ -1145,12 +1202,14 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) * poll the status register to make sure that the reset * completed successfully. */ - usleep_range(10000, 20000); reg = rd32(hw, VPGEN_VFRSTAT(vf->vf_id)); if (reg & VPGEN_VFRSTAT_VFRD_M) { rsd = true; break; } + + /* only sleep if the reset is not done */ + usleep_range(10, 20); } /* Display a warning if VF didn't manage to reset in time, but need to @@ -1160,8 +1219,6 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) dev_warn(&pf->pdev->dev, "VF reset check timeout on VF %d\n", vf->vf_id); - usleep_range(10000, 20000); - /* disable promiscuous modes in case they were enabled * ignore any error if disabling process failed */ @@ -1183,7 +1240,6 @@ static bool ice_reset_vf(struct ice_vf *vf, bool is_vflr) ice_cleanup_and_realloc_vf(vf); ice_flush(hw); - clear_bit(__ICE_VF_DIS, pf->state); return true; } @@ -1257,7 +1313,7 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs) /* Disable global interrupt 0 so we don't try to handle the VFLR. */ wr32(hw, GLINT_DYN_CTL(pf->oicr_idx), ICE_ITR_NONE << GLINT_DYN_CTL_ITR_INDX_S); - + set_bit(__ICE_OICR_INTR_DIS, pf->state); ice_flush(hw); ret = pci_enable_sriov(pf->pdev, num_alloc_vfs); @@ -1283,19 +1339,16 @@ static int ice_alloc_vfs(struct ice_pf *pf, u16 num_alloc_vfs) /* assign default capabilities */ set_bit(ICE_VIRTCHNL_VF_CAP_L2, &vfs[i].vf_caps); vfs[i].spoofchk = true; - - /* Set this state so that PF driver does VF vector assignment */ - set_bit(ICE_VF_STATE_CFG_INTR, vfs[i].vf_states); } pf->num_alloc_vfs = num_alloc_vfs; - /* VF resources get allocated during reset */ - if (!ice_reset_all_vfs(pf, true)) { + /* VF resources get allocated with initialization */ + if (!ice_config_res_vfs(pf)) { ret = -EIO; goto err_unroll_sriov; } - goto err_unroll_intr; + return ret; err_unroll_sriov: pf->vf = NULL; @@ -1307,6 +1360,7 @@ err_pci_disable_sriov: err_unroll_intr: /* rearm interrupts here */ ice_irq_dynamic_ena(hw, NULL, NULL); + clear_bit(__ICE_OICR_INTR_DIS, pf->state); return ret; } @@ -1389,6 +1443,12 @@ int ice_sriov_configure(struct pci_dev *pdev, int num_vfs) { struct ice_pf *pf = pci_get_drvdata(pdev); + if (ice_is_safe_mode(pf)) { + dev_err(&pf->pdev->dev, + "SR-IOV cannot be configured - Device is in Safe Mode\n"); + return -EOPNOTSUPP; + } + if (num_vfs) return ice_pci_sriov_ena(pf, num_vfs); @@ -1490,10 +1550,10 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode, aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval, msg, msglen, NULL); - if (aq_ret) { + if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) { dev_info(&pf->pdev->dev, - "Unable to send the message to VF %d aq_err %d\n", - vf->vf_id, pf->hw.mailboxq.sq_last_status); + "Unable to send the message to VF %d ret %d aq_err %d\n", + vf->vf_id, aq_ret, pf->hw.mailboxq.sq_last_status); return -EIO; } @@ -1688,6 +1748,21 @@ static bool ice_vc_isvalid_q_id(struct ice_vf *vf, u16 vsi_id, u8 qid) } /** + * ice_vc_isvalid_ring_len + * @ring_len: length of ring + * + * check for the valid ring count, should be multiple of ICE_REQ_DESC_MULTIPLE + * or zero + */ +static bool ice_vc_isvalid_ring_len(u16 ring_len) +{ + return ring_len == 0 || + (ring_len >= ICE_MIN_NUM_DESC && + ring_len <= ICE_MAX_NUM_DESC && + !(ring_len % ICE_REQ_DESC_MULTIPLE)); +} + +/** * ice_vc_config_rss_key * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -1712,18 +1787,18 @@ static int ice_vc_config_rss_key(struct ice_vf *vf, u8 *msg) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; - if (!vsi) { + if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) { + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + vsi = pf->vsi[vf->lan_vsi_idx]; + if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1759,18 +1834,18 @@ static int ice_vc_config_rss_lut(struct ice_vf *vf, u8 *msg) goto error_param; } - vsi = pf->vsi[vf->lan_vsi_idx]; - if (!vsi) { + if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) { + if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - if (!test_bit(ICE_FLAG_RSS_ENA, vf->pf->flags)) { + vsi = pf->vsi[vf->lan_vsi_idx]; + if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1839,6 +1914,8 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) (struct virtchnl_queue_select *)msg; struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; + unsigned long q_map; + u16 vf_q_id; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -1855,6 +1932,12 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } + if (vqs->rx_queues > ICE_MAX_BASE_QS_PER_VF || + vqs->tx_queues > ICE_MAX_BASE_QS_PER_VF) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + vsi = pf->vsi[vf->lan_vsi_idx]; if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -1865,12 +1948,48 @@ static int ice_vc_ena_qs_msg(struct ice_vf *vf, u8 *msg) * Tx queue group list was configured and the context bits were * programmed using ice_vsi_cfg_txqs */ - if (ice_vsi_start_rx_rings(vsi)) - v_ret = VIRTCHNL_STATUS_ERR_PARAM; + q_map = vqs->rx_queues; + for_each_set_bit(vf_q_id, &q_map, ICE_MAX_BASE_QS_PER_VF) { + if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Skip queue if enabled */ + if (test_bit(vf_q_id, vf->rxq_ena)) + continue; + + if (ice_vsi_ctrl_rx_ring(vsi, true, vf_q_id)) { + dev_err(&vsi->back->pdev->dev, + "Failed to enable Rx ring %d on VSI %d\n", + vf_q_id, vsi->vsi_num); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + set_bit(vf_q_id, vf->rxq_ena); + vf->num_qs_ena++; + } + + vsi = pf->vsi[vf->lan_vsi_idx]; + q_map = vqs->tx_queues; + for_each_set_bit(vf_q_id, &q_map, ICE_MAX_BASE_QS_PER_VF) { + if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Skip queue if enabled */ + if (test_bit(vf_q_id, vf->txq_ena)) + continue; + + set_bit(vf_q_id, vf->txq_ena); + vf->num_qs_ena++; + } /* Set flag to indicate that queues are enabled */ if (v_ret == VIRTCHNL_STATUS_SUCCESS) - set_bit(ICE_VF_STATE_ENA, vf->vf_states); + set_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); error_param: /* send the response to the VF */ @@ -1893,9 +2012,11 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) (struct virtchnl_queue_select *)msg; struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; + unsigned long q_map; + u16 vf_q_id; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states) && - !test_bit(ICE_VF_STATE_ENA, vf->vf_states)) { + !test_bit(ICE_VF_STATE_QS_ENA, vf->vf_states)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -1910,29 +2031,81 @@ static int ice_vc_dis_qs_msg(struct ice_vf *vf, u8 *msg) goto error_param; } + if (vqs->rx_queues > ICE_MAX_BASE_QS_PER_VF || + vqs->tx_queues > ICE_MAX_BASE_QS_PER_VF) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + vsi = pf->vsi[vf->lan_vsi_idx]; if (!vsi) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } - if (ice_vsi_stop_lan_tx_rings(vsi, ICE_NO_RESET, vf->vf_id)) { - dev_err(&vsi->back->pdev->dev, - "Failed to stop tx rings on VSI %d\n", - vsi->vsi_num); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; + if (vqs->tx_queues) { + q_map = vqs->tx_queues; + + for_each_set_bit(vf_q_id, &q_map, ICE_MAX_BASE_QS_PER_VF) { + struct ice_ring *ring = vsi->tx_rings[vf_q_id]; + struct ice_txq_meta txq_meta = { 0 }; + + if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Skip queue if not enabled */ + if (!test_bit(vf_q_id, vf->txq_ena)) + continue; + + ice_fill_txq_meta(vsi, ring, &txq_meta); + + if (ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, vf->vf_id, + ring, &txq_meta)) { + dev_err(&vsi->back->pdev->dev, + "Failed to stop Tx ring %d on VSI %d\n", + vf_q_id, vsi->vsi_num); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Clear enabled queues flag */ + clear_bit(vf_q_id, vf->txq_ena); + vf->num_qs_ena--; + } } - if (ice_vsi_stop_rx_rings(vsi)) { - dev_err(&vsi->back->pdev->dev, - "Failed to stop rx rings on VSI %d\n", - vsi->vsi_num); - v_ret = VIRTCHNL_STATUS_ERR_PARAM; + if (vqs->rx_queues) { + q_map = vqs->rx_queues; + + for_each_set_bit(vf_q_id, &q_map, ICE_MAX_BASE_QS_PER_VF) { + if (!ice_vc_isvalid_q_id(vf, vqs->vsi_id, vf_q_id)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Skip queue if not enabled */ + if (!test_bit(vf_q_id, vf->rxq_ena)) + continue; + + if (ice_vsi_ctrl_rx_ring(vsi, false, vf_q_id)) { + dev_err(&vsi->back->pdev->dev, + "Failed to stop Rx ring %d on VSI %d\n", + vf_q_id, vsi->vsi_num); + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + + /* Clear enabled queues flag */ + clear_bit(vf_q_id, vf->rxq_ena); + vf->num_qs_ena--; + } } /* Clear enabled queues flag */ - if (v_ret == VIRTCHNL_STATUS_SUCCESS) - clear_bit(ICE_VF_STATE_ENA, vf->vf_states); + if (v_ret == VIRTCHNL_STATUS_SUCCESS && !vf->num_qs_ena) + clear_bit(ICE_VF_STATE_QS_ENA, vf->vf_states); error_param: /* send the response to the VF */ @@ -1962,12 +2135,6 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) irqmap_info = (struct virtchnl_irq_map_info *)msg; num_q_vectors_mapped = irqmap_info->num_vectors; - vsi = pf->vsi[vf->lan_vsi_idx]; - if (!vsi) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; - } - /* Check to make sure number of VF vectors mapped is not greater than * number of VF vectors originally allocated, and check that * there is actually at least a single VF queue vector mapped @@ -1979,6 +2146,12 @@ static int ice_vc_cfg_irq_map_msg(struct ice_vf *vf, u8 *msg) goto error_param; } + vsi = pf->vsi[vf->lan_vsi_idx]; + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + for (i = 0; i < num_q_vectors_mapped; i++) { struct ice_q_vector *q_vector; @@ -2056,6 +2229,7 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) struct virtchnl_vsi_queue_config_info *qci = (struct virtchnl_vsi_queue_config_info *)msg; struct virtchnl_queue_pair_info *qpi; + u16 num_rxq = 0, num_txq = 0; struct ice_pf *pf = vf->pf; struct ice_vsi *vsi; int i; @@ -2071,13 +2245,16 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) } vsi = pf->vsi[vf->lan_vsi_idx]; - if (!vsi) + if (!vsi) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; + } - if (qci->num_queue_pairs > ICE_MAX_BASE_QS_PER_VF) { + if (qci->num_queue_pairs > ICE_MAX_BASE_QS_PER_VF || + qci->num_queue_pairs > min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)) { dev_err(&pf->pdev->dev, "VF-%d requesting more than supported number of queues: %d\n", - vf->vf_id, qci->num_queue_pairs); + vf->vf_id, min_t(u16, vsi->alloc_txq, vsi->alloc_rxq)); v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } @@ -2087,37 +2264,52 @@ static int ice_vc_cfg_qs_msg(struct ice_vf *vf, u8 *msg) if (qpi->txq.vsi_id != qci->vsi_id || qpi->rxq.vsi_id != qci->vsi_id || qpi->rxq.queue_id != qpi->txq.queue_id || + qpi->txq.headwb_enabled || + !ice_vc_isvalid_ring_len(qpi->txq.ring_len) || + !ice_vc_isvalid_ring_len(qpi->rxq.ring_len) || !ice_vc_isvalid_q_id(vf, qci->vsi_id, qpi->txq.queue_id)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; goto error_param; } /* 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 */ - 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)) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; + if (qpi->txq.ring_len > 0) { + num_txq++; + vsi->tx_rings[i]->dma = qpi->txq.dma_ring_addr; + vsi->tx_rings[i]->count = qpi->txq.ring_len; } - vsi->rx_buf_len = qpi->rxq.databuffer_size; - if (qpi->rxq.max_pkt_size >= (16 * 1024) || - qpi->rxq.max_pkt_size < 64) { - v_ret = VIRTCHNL_STATUS_ERR_PARAM; - goto error_param; + + /* copy Rx queue info from VF into VSI */ + if (qpi->rxq.ring_len > 0) { + num_rxq++; + vsi->rx_rings[i]->dma = qpi->rxq.dma_ring_addr; + vsi->rx_rings[i]->count = qpi->rxq.ring_len; + + if (qpi->rxq.databuffer_size != 0 && + (qpi->rxq.databuffer_size > ((16 * 1024) - 128) || + qpi->rxq.databuffer_size < 1024)) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } + vsi->rx_buf_len = qpi->rxq.databuffer_size; + vsi->rx_rings[i]->rx_buf_len = vsi->rx_buf_len; + if (qpi->rxq.max_pkt_size >= (16 * 1024) || + qpi->rxq.max_pkt_size < 64) { + v_ret = VIRTCHNL_STATUS_ERR_PARAM; + goto error_param; + } } + vsi->max_frame = qpi->rxq.max_pkt_size; } /* VF can request to configure less than allocated queues * or default allocated queues. So update the VSI with new number */ - vsi->num_txq = qci->num_queue_pairs; - vsi->num_rxq = qci->num_queue_pairs; + vsi->num_txq = num_txq; + vsi->num_rxq = num_rxq; /* All queues of VF VSI are in TC 0 */ - vsi->tc_cfg.tc_info[0].qcount_tx = qci->num_queue_pairs; - vsi->tc_cfg.tc_info[0].qcount_rx = qci->num_queue_pairs; + vsi->tc_cfg.tc_info[0].qcount_tx = num_txq; + vsi->tc_cfg.tc_info[0].qcount_rx = num_rxq; if (ice_vsi_cfg_lan_txqs(vsi) || ice_vsi_cfg_rxqs(vsi)) v_ret = VIRTCHNL_STATUS_ERR_ADMIN_QUEUE_ERROR; @@ -2171,7 +2363,7 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) (struct virtchnl_ether_addr_list *)msg; struct ice_pf *pf = vf->pf; enum virtchnl_ops vc_op; - LIST_HEAD(mac_list); + enum ice_status status; struct ice_vsi *vsi; int mac_count = 0; int i; @@ -2245,33 +2437,32 @@ ice_vc_handle_mac_addr_msg(struct ice_vf *vf, u8 *msg, bool set) goto handle_mac_exit; } - /* get here if maddr is multicast or if VF can change MAC */ - if (ice_add_mac_to_list(vsi, &mac_list, al->list[i].addr)) { - v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY; + /* program the updated filter list */ + status = ice_vsi_cfg_mac_fltr(vsi, maddr, set); + if (status == ICE_ERR_DOES_NOT_EXIST || + status == ICE_ERR_ALREADY_EXISTS) { + dev_info(&pf->pdev->dev, + "can't %s MAC filters %pM for VF %d, error %d\n", + set ? "add" : "remove", maddr, vf->vf_id, + status); + } else if (status) { + dev_err(&pf->pdev->dev, + "can't %s MAC filters for VF %d, error %d\n", + set ? "add" : "remove", vf->vf_id, status); + v_ret = ice_err_to_virt_err(status); goto handle_mac_exit; } + mac_count++; } - /* program the updated filter list */ + /* Track number of MAC filters programmed for the VF VSI */ if (set) - v_ret = ice_err_to_virt_err(ice_add_mac(&pf->hw, &mac_list)); + vf->num_mac += mac_count; else - v_ret = ice_err_to_virt_err(ice_remove_mac(&pf->hw, &mac_list)); - - if (v_ret) { - dev_err(&pf->pdev->dev, - "can't update MAC filters for VF %d, error %d\n", - vf->vf_id, v_ret); - } else { - if (set) - vf->num_mac += mac_count; - else - vf->num_mac -= mac_count; - } + vf->num_mac -= mac_count; handle_mac_exit: - ice_free_fltr_list(&pf->pdev->dev, &mac_list); /* send the response to the VF */ return ice_vc_send_msg_to_vf(vf, vc_op, v_ret, NULL, 0); } @@ -2315,11 +2506,11 @@ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg) enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS; struct virtchnl_vf_res_request *vfres = (struct virtchnl_vf_res_request *)msg; - int req_queues = vfres->num_queue_pairs; + u16 req_queues = vfres->num_queue_pairs; struct ice_pf *pf = vf->pf; - int max_allowed_vf_queues; - int tx_rx_queue_left; - int cur_queues; + u16 max_allowed_vf_queues; + u16 tx_rx_queue_left; + u16 cur_queues; if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) { v_ret = VIRTCHNL_STATUS_ERR_PARAM; @@ -2327,29 +2518,31 @@ static int ice_vc_request_qs_msg(struct ice_vf *vf, u8 *msg) } cur_queues = vf->num_vf_qs; - tx_rx_queue_left = min_t(int, pf->q_left_tx, pf->q_left_rx); + tx_rx_queue_left = min_t(u16, ice_get_avail_txq_count(pf), + ice_get_avail_rxq_count(pf)); max_allowed_vf_queues = tx_rx_queue_left + cur_queues; - if (req_queues <= 0) { + if (!req_queues) { dev_err(&pf->pdev->dev, - "VF %d tried to request %d queues. Ignoring.\n", - vf->vf_id, req_queues); + "VF %d tried to request 0 queues. Ignoring.\n", + vf->vf_id); } else if (req_queues > ICE_MAX_BASE_QS_PER_VF) { dev_err(&pf->pdev->dev, "VF %d tried to request more than %d queues.\n", vf->vf_id, ICE_MAX_BASE_QS_PER_VF); vfres->num_queue_pairs = ICE_MAX_BASE_QS_PER_VF; - } else if (req_queues - cur_queues > tx_rx_queue_left) { + } else if (req_queues > cur_queues && + req_queues - cur_queues > tx_rx_queue_left) { dev_warn(&pf->pdev->dev, - "VF %d requested %d more queues, but only %d left.\n", + "VF %d requested %u more queues, but only %u left.\n", vf->vf_id, req_queues - cur_queues, tx_rx_queue_left); - vfres->num_queue_pairs = min_t(int, max_allowed_vf_queues, + vfres->num_queue_pairs = min_t(u16, max_allowed_vf_queues, ICE_MAX_BASE_QS_PER_VF); } else { /* request is successful, then reset VF */ vf->num_req_qs = req_queues; ice_vc_dis_vf(vf); dev_info(&pf->pdev->dev, - "VF %d granted request of %d queues.\n", + "VF %d granted request of %u queues.\n", vf->vf_id, req_queues); return 0; } @@ -2589,8 +2782,9 @@ static int ice_vc_process_vlan_msg(struct ice_vf *vf, u8 *msg, bool add_v) } vf->num_vlan--; - /* Disable VLAN pruning when removing VLAN */ - ice_cfg_vlan_pruning(vsi, false, false); + /* Disable VLAN pruning when the last VLAN is removed */ + if (!vf->num_vlan) + ice_cfg_vlan_pruning(vsi, false, false); /* Disable Unicast/Multicast VLAN promiscuous mode */ if (vlan_promisc) { @@ -2731,20 +2925,6 @@ void ice_vc_process_vf_msg(struct ice_pf *pf, struct ice_rq_event_info *event) err = -EPERM; else err = -EINVAL; - goto error_handler; - } - - /* Perform additional checks specific to RSS and Virtchnl */ - if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_KEY) { - struct virtchnl_rss_key *vrk = (struct virtchnl_rss_key *)msg; - - if (vrk->key_len != ICE_VSIQF_HKEY_ARRAY_SIZE) - err = -EINVAL; - } else if (v_opcode == VIRTCHNL_OP_CONFIG_RSS_LUT) { - struct virtchnl_rss_lut *vrl = (struct virtchnl_rss_lut *)msg; - - if (vrl->lut_entries != ICE_VSIQF_HLUT_ARRAY_SIZE) - err = -EINVAL; } error_handler: @@ -2762,6 +2942,7 @@ error_handler: break; case VIRTCHNL_OP_GET_VF_RESOURCES: err = ice_vc_get_vf_res_msg(vf, msg); + ice_vc_notify_vf_link_state(vf); break; case VIRTCHNL_OP_RESET_VF: ice_vc_reset_vf_msg(vf); diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h index c3ca522c245a..0d9880c8bba3 100644 --- a/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_pf.h @@ -15,26 +15,38 @@ #define ICE_MAX_MACADDR_PER_VF 12 /* Malicious Driver Detection */ -#define ICE_DFLT_NUM_MDD_EVENTS_ALLOWED 3 #define ICE_DFLT_NUM_INVAL_MSGS_ALLOWED 10 +#define ICE_MDD_EVENTS_THRESHOLD 30 /* Static VF transaction/status register def */ #define VF_DEVICE_STATUS 0xAA #define VF_TRANS_PENDING_M 0x20 +/* wait defines for polling PF_PCI_CIAD register status */ +#define ICE_PCI_CIAD_WAIT_COUNT 100 +#define ICE_PCI_CIAD_WAIT_DELAY_US 1 + +/* VF resources default values and limitation */ +#define ICE_MAX_VF_COUNT 256 +#define ICE_MAX_QS_PER_VF 256 +#define ICE_MIN_QS_PER_VF 1 +#define ICE_DFLT_QS_PER_VF 4 +#define ICE_NONQ_VECS_VF 1 +#define ICE_MAX_SCATTER_QS_PER_VF 16 +#define ICE_MAX_BASE_QS_PER_VF 16 +#define ICE_MAX_INTR_PER_VF 65 +#define ICE_MAX_POLICY_INTR_PER_VF 33 +#define ICE_MIN_INTR_PER_VF (ICE_MIN_QS_PER_VF + 1) +#define ICE_DFLT_INTR_PER_VF (ICE_DFLT_QS_PER_VF + 1) + /* Specific VF states */ enum ice_vf_states { - ICE_VF_STATE_INIT = 0, - ICE_VF_STATE_ACTIVE, - ICE_VF_STATE_ENA, + ICE_VF_STATE_INIT = 0, /* PF is initializing VF */ + ICE_VF_STATE_ACTIVE, /* VF resources are allocated for use */ + ICE_VF_STATE_QS_ENA, /* VF queue(s) enabled */ ICE_VF_STATE_DIS, ICE_VF_STATE_MC_PROMISC, ICE_VF_STATE_UC_PROMISC, - /* state to indicate if PF needs to do vector assignment for VF. - * This needs to be set during first time VF initialization or later - * when VF asks for more Vectors through virtchnl OP. - */ - ICE_VF_STATE_CFG_INTR, ICE_VF_STATES_NBITS }; @@ -50,11 +62,14 @@ struct ice_vf { s16 vf_id; /* VF ID in the PF space */ u16 lan_vsi_idx; /* index into PF struct */ - int first_vector_idx; /* first vector index of this VF */ + /* first vector index of this VF in the PF space */ + int first_vector_idx; struct ice_sw *vf_sw_id; /* switch ID the VF VSIs connect to */ struct virtchnl_version_info vf_ver; u32 driver_caps; /* reported by VF driver */ struct virtchnl_ether_addr dflt_lan_addr; + DECLARE_BITMAP(txq_ena, ICE_MAX_BASE_QS_PER_VF); + DECLARE_BITMAP(rxq_ena, ICE_MAX_BASE_QS_PER_VF); u16 port_vlan_id; u8 pf_set_mac:1; /* VF MAC address set by VMM admin */ u8 trusted:1; @@ -77,6 +92,7 @@ struct ice_vf { u16 num_mac; u16 num_vlan; u16 num_vf_qs; /* num of queue configured per VF */ + u16 num_qs_ena; /* total num of Tx/Rx queue enabled */ }; #ifdef CONFIG_PCI_IOV @@ -103,12 +119,15 @@ int ice_set_vf_link_state(struct net_device *netdev, int vf_id, int link_state); int ice_set_vf_spoofchk(struct net_device *netdev, int vf_id, bool ena); int ice_calc_vf_reg_idx(struct ice_vf *vf, struct ice_q_vector *q_vector); + +void ice_set_vf_state_qs_dis(struct ice_vf *vf); #else /* CONFIG_PCI_IOV */ #define ice_process_vflr_event(pf) do {} while (0) #define ice_free_vfs(pf) do {} while (0) #define ice_vc_process_vf_msg(pf, event) do {} while (0) #define ice_vc_notify_link_state(pf) do {} while (0) #define ice_vc_notify_reset(pf) do {} while (0) +#define ice_set_vf_state_qs_dis(vf) do {} while (0) static inline bool ice_reset_all_vfs(struct ice_pf __always_unused *pf, diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index b4df3e319467..105b0624081a 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -4731,8 +4731,7 @@ static void igb_clean_rx_ring(struct igb_ring *rx_ring) { u16 i = rx_ring->next_to_clean; - if (rx_ring->skb) - dev_kfree_skb(rx_ring->skb); + dev_kfree_skb(rx_ring->skb); rx_ring->skb = NULL; /* Free all the Rx ring sk_buffs */ @@ -5918,7 +5917,7 @@ static int igb_tx_map(struct igb_ring *tx_ring, struct sk_buff *skb = first->skb; struct igb_tx_buffer *tx_buffer; union e1000_adv_tx_desc *tx_desc; - struct skb_frag_struct *frag; + skb_frag_t *frag; dma_addr_t dma; unsigned int data_len, size; u32 tx_flags = first->tx_flags; @@ -6074,7 +6073,8 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + count += TXD_USE_COUNT(skb_frag_size( + &skb_shinfo(skb)->frags[f])); if (igb_maybe_stop_tx(tx_ring, count + 3)) { /* this is a hard error */ @@ -8879,8 +8879,7 @@ static int __maybe_unused igb_resume(struct device *dev) static int __maybe_unused igb_runtime_idle(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct igb_adapter *adapter = netdev_priv(netdev); if (!igb_has_link(adapter)) diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index 34cd30d7162f..0f2b68f4bb0f 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -2174,7 +2174,7 @@ static inline int igbvf_tx_map_adv(struct igbvf_adapter *adapter, goto dma_error; for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag; count++; i++; diff --git a/drivers/net/ethernet/intel/igc/igc.h b/drivers/net/ethernet/intel/igc/igc.h index 0f5534ce27b0..7e16345d836e 100644 --- a/drivers/net/ethernet/intel/igc/igc.h +++ b/drivers/net/ethernet/intel/igc/igc.h @@ -135,6 +135,9 @@ extern char igc_driver_version[]; /* How many Rx Buffers do we bundle into one write to the hardware ? */ #define IGC_RX_BUFFER_WRITE 16 /* Must be power of 2 */ +/* VLAN info */ +#define IGC_TX_FLAGS_VLAN_MASK 0xffff0000 + /* igc_test_staterr - tests bits within Rx descriptor status and error fields */ static inline __le32 igc_test_staterr(union igc_adv_rx_desc *rx_desc, const u32 stat_err_bits) @@ -254,6 +257,7 @@ struct igc_ring { u16 count; /* number of desc. in the ring */ u8 queue_index; /* logical index of the ring*/ u8 reg_idx; /* physical index of the ring */ + bool launchtime_enable; /* true if LaunchTime is enabled */ /* everything past this point are written often */ u16 next_to_clean; diff --git a/drivers/net/ethernet/intel/igc/igc_base.c b/drivers/net/ethernet/intel/igc/igc_base.c index 59258d791106..db289bcce21d 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.c +++ b/drivers/net/ethernet/intel/igc/igc_base.c @@ -40,7 +40,7 @@ static s32 igc_reset_hw_base(struct igc_hw *hw) ctrl = rd32(IGC_CTRL); hw_dbg("Issuing a global reset to MAC\n"); - wr32(IGC_CTRL, ctrl | IGC_CTRL_RST); + wr32(IGC_CTRL, ctrl | IGC_CTRL_DEV_RST); ret_val = igc_get_auto_rd_done(hw); if (ret_val) { @@ -209,6 +209,9 @@ static s32 igc_get_invariants_base(struct igc_hw *hw) switch (hw->device_id) { case IGC_DEV_ID_I225_LM: case IGC_DEV_ID_I225_V: + case IGC_DEV_ID_I225_I: + case IGC_DEV_ID_I220_V: + case IGC_DEV_ID_I225_K: mac->type = igc_i225; break; default: diff --git a/drivers/net/ethernet/intel/igc/igc_base.h b/drivers/net/ethernet/intel/igc/igc_base.h index 58d1109d7f3f..ea627ce52525 100644 --- a/drivers/net/ethernet/intel/igc/igc_base.h +++ b/drivers/net/ethernet/intel/igc/igc_base.h @@ -22,6 +22,14 @@ union igc_adv_tx_desc { } wb; }; +/* Context descriptors */ +struct igc_adv_tx_context_desc { + __le32 vlan_macip_lens; + __le32 launch_time; + __le32 type_tucmd_mlhl; + __le32 mss_l4len_idx; +}; + /* Adv Transmit Descriptor Config Masks */ #define IGC_ADVTXD_MAC_TSTAMP 0x00080000 /* IEEE1588 Timestamp packet */ #define IGC_ADVTXD_DTYP_CTXT 0x00200000 /* Advanced Context Descriptor */ diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h index fc0ccfe38a20..f3f2325fe567 100644 --- a/drivers/net/ethernet/intel/igc/igc_defines.h +++ b/drivers/net/ethernet/intel/igc/igc_defines.h @@ -10,10 +10,6 @@ #define IGC_CTRL_EXT_DRV_LOAD 0x10000000 /* Drv loaded bit for FW */ -/* PCI Bus Info */ -#define PCIE_DEVICE_CONTROL2 0x28 -#define PCIE_DEVICE_CONTROL2_16ms 0x0005 - /* Physical Func Reset Done Indication */ #define IGC_CTRL_EXT_LINK_MODE_MASK 0x00C00000 @@ -54,7 +50,7 @@ #define IGC_ERR_SWFW_SYNC 13 /* Device Control */ -#define IGC_CTRL_RST 0x04000000 /* Global reset */ +#define IGC_CTRL_DEV_RST 0x20000000 /* Device reset */ #define IGC_CTRL_PHY_RST 0x80000000 /* PHY Reset */ #define IGC_CTRL_SLU 0x00000040 /* Set link up (Force Link) */ @@ -401,4 +397,9 @@ #define IGC_VLAPQF_P_VALID(_n) (0x1 << (3 + (_n) * 4)) #define IGC_VLAPQF_QUEUE_MASK 0x03 +#define IGC_ADVTXD_MACLEN_SHIFT 9 /* Adv ctxt desc mac len shift */ +#define IGC_ADVTXD_TUCMD_IPV4 0x00000400 /* IP Packet Type:1=IPv4 */ +#define IGC_ADVTXD_TUCMD_L4T_TCP 0x00000800 /* L4 Packet Type of TCP */ +#define IGC_ADVTXD_TUCMD_L4T_SCTP 0x00001000 /* L4 packet TYPE of SCTP */ + #endif /* _IGC_DEFINES_H_ */ diff --git a/drivers/net/ethernet/intel/igc/igc_hw.h b/drivers/net/ethernet/intel/igc/igc_hw.h index 1039a224ac80..abb2d72911ff 100644 --- a/drivers/net/ethernet/intel/igc/igc_hw.h +++ b/drivers/net/ethernet/intel/igc/igc_hw.h @@ -18,6 +18,9 @@ #define IGC_DEV_ID_I225_LM 0x15F2 #define IGC_DEV_ID_I225_V 0x15F3 +#define IGC_DEV_ID_I225_I 0x15F8 +#define IGC_DEV_ID_I220_V 0x15F7 +#define IGC_DEV_ID_I225_K 0x3100 #define IGC_FUNC_0 0 @@ -151,16 +154,10 @@ struct igc_phy_info { u16 autoneg_advertised; u16 autoneg_mask; - u16 cable_length; - u16 max_cable_length; - u16 min_cable_length; - u16 pair_length[4]; u8 mdix; - bool disable_polarity_correction; bool is_mdix; - bool polarity_correction; bool reset_disable; bool speed_downgraded; bool autoneg_wait_to_complete; @@ -190,12 +187,7 @@ struct igc_fc_info { }; struct igc_dev_spec_base { - bool global_device_reset; - bool eee_disable; bool clear_semaphore_once; - bool module_plugged; - u8 media_port; - bool mas_capable; }; struct igc_hw { diff --git a/drivers/net/ethernet/intel/igc/igc_mac.c b/drivers/net/ethernet/intel/igc/igc_mac.c index ba4646737288..5eeb4c8caf4a 100644 --- a/drivers/net/ethernet/intel/igc/igc_mac.c +++ b/drivers/net/ethernet/intel/igc/igc_mac.c @@ -7,9 +7,6 @@ #include "igc_mac.h" #include "igc_hw.h" -/* forward declaration */ -static s32 igc_set_fc_watermarks(struct igc_hw *hw); - /** * igc_disable_pcie_master - Disables PCI-express master access * @hw: pointer to the HW structure @@ -75,6 +72,41 @@ void igc_init_rx_addrs(struct igc_hw *hw, u16 rar_count) } /** + * igc_set_fc_watermarks - Set flow control high/low watermarks + * @hw: pointer to the HW structure + * + * Sets the flow control high/low threshold (watermark) registers. If + * flow control XON frame transmission is enabled, then set XON frame + * transmission as well. + */ +static s32 igc_set_fc_watermarks(struct igc_hw *hw) +{ + u32 fcrtl = 0, fcrth = 0; + + /* Set the flow control receive threshold registers. Normally, + * these registers will be set to a default threshold that may be + * adjusted later by the driver's runtime code. However, if the + * ability to transmit pause frames is not enabled, then these + * registers will be set to 0. + */ + if (hw->fc.current_mode & igc_fc_tx_pause) { + /* We need to set up the Receive Threshold high and low water + * marks as well as (optionally) enabling the transmission of + * XON frames. + */ + fcrtl = hw->fc.low_water; + if (hw->fc.send_xon) + fcrtl |= IGC_FCRTL_XONE; + + fcrth = hw->fc.high_water; + } + wr32(IGC_FCRTL, fcrtl); + wr32(IGC_FCRTH, fcrth); + + return 0; +} + +/** * igc_setup_link - Setup flow control and link settings * @hw: pointer to the HW structure * @@ -195,41 +227,6 @@ out: } /** - * igc_set_fc_watermarks - Set flow control high/low watermarks - * @hw: pointer to the HW structure - * - * Sets the flow control high/low threshold (watermark) registers. If - * flow control XON frame transmission is enabled, then set XON frame - * transmission as well. - */ -static s32 igc_set_fc_watermarks(struct igc_hw *hw) -{ - u32 fcrtl = 0, fcrth = 0; - - /* Set the flow control receive threshold registers. Normally, - * these registers will be set to a default threshold that may be - * adjusted later by the driver's runtime code. However, if the - * ability to transmit pause frames is not enabled, then these - * registers will be set to 0. - */ - if (hw->fc.current_mode & igc_fc_tx_pause) { - /* We need to set up the Receive Threshold high and low water - * marks as well as (optionally) enabling the transmission of - * XON frames. - */ - fcrtl = hw->fc.low_water; - if (hw->fc.send_xon) - fcrtl |= IGC_FCRTL_XONE; - - fcrth = hw->fc.high_water; - } - wr32(IGC_FCRTL, fcrtl); - wr32(IGC_FCRTH, fcrth); - - return 0; -} - -/** * igc_clear_hw_cntrs_base - Clear base hardware counters * @hw: pointer to the HW structure * diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index aa9323e55406..63b62d74f961 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -5,6 +5,11 @@ #include <linux/types.h> #include <linux/if_vlan.h> #include <linux/aer.h> +#include <linux/tcp.h> +#include <linux/udp.h> +#include <linux/ip.h> + +#include <net/ipv6.h> #include "igc.h" #include "igc_hw.h" @@ -36,6 +41,9 @@ static const struct igc_info *igc_info_tbl[] = { static const struct pci_device_id igc_pci_tbl[] = { { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_LM), board_base }, { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_V), board_base }, + { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_I), board_base }, + { PCI_VDEVICE(INTEL, IGC_DEV_ID_I220_V), board_base }, + { PCI_VDEVICE(INTEL, IGC_DEV_ID_I225_K), board_base }, /* required last entry */ {0, } }; @@ -349,8 +357,7 @@ static void igc_clean_rx_ring(struct igc_ring *rx_ring) { u16 i = rx_ring->next_to_clean; - if (rx_ring->skb) - dev_kfree_skb(rx_ring->skb); + dev_kfree_skb(rx_ring->skb); rx_ring->skb = NULL; /* Free all the Rx ring sk_buffs */ @@ -788,8 +795,96 @@ static int igc_set_mac(struct net_device *netdev, void *p) return 0; } +static void igc_tx_ctxtdesc(struct igc_ring *tx_ring, + struct igc_tx_buffer *first, + u32 vlan_macip_lens, u32 type_tucmd, + u32 mss_l4len_idx) +{ + struct igc_adv_tx_context_desc *context_desc; + u16 i = tx_ring->next_to_use; + struct timespec64 ts; + + context_desc = IGC_TX_CTXTDESC(tx_ring, i); + + i++; + tx_ring->next_to_use = (i < tx_ring->count) ? i : 0; + + /* set bits to identify this as an advanced context descriptor */ + type_tucmd |= IGC_TXD_CMD_DEXT | IGC_ADVTXD_DTYP_CTXT; + + /* For 82575, context index must be unique per ring. */ + if (test_bit(IGC_RING_FLAG_TX_CTX_IDX, &tx_ring->flags)) + mss_l4len_idx |= tx_ring->reg_idx << 4; + + context_desc->vlan_macip_lens = cpu_to_le32(vlan_macip_lens); + context_desc->type_tucmd_mlhl = cpu_to_le32(type_tucmd); + context_desc->mss_l4len_idx = cpu_to_le32(mss_l4len_idx); + + /* We assume there is always a valid Tx time available. Invalid times + * should have been handled by the upper layers. + */ + if (tx_ring->launchtime_enable) { + ts = ns_to_timespec64(first->skb->tstamp); + first->skb->tstamp = 0; + context_desc->launch_time = cpu_to_le32(ts.tv_nsec / 32); + } else { + context_desc->launch_time = 0; + } +} + +static inline bool igc_ipv6_csum_is_sctp(struct sk_buff *skb) +{ + unsigned int offset = 0; + + ipv6_find_hdr(skb, &offset, IPPROTO_SCTP, NULL, NULL); + + return offset == skb_checksum_start_offset(skb); +} + static void igc_tx_csum(struct igc_ring *tx_ring, struct igc_tx_buffer *first) { + struct sk_buff *skb = first->skb; + u32 vlan_macip_lens = 0; + u32 type_tucmd = 0; + + if (skb->ip_summed != CHECKSUM_PARTIAL) { +csum_failed: + if (!(first->tx_flags & IGC_TX_FLAGS_VLAN) && + !tx_ring->launchtime_enable) + return; + goto no_csum; + } + + switch (skb->csum_offset) { + case offsetof(struct tcphdr, check): + type_tucmd = IGC_ADVTXD_TUCMD_L4T_TCP; + /* fall through */ + case offsetof(struct udphdr, check): + break; + case offsetof(struct sctphdr, checksum): + /* validate that this is actually an SCTP request */ + if ((first->protocol == htons(ETH_P_IP) && + (ip_hdr(skb)->protocol == IPPROTO_SCTP)) || + (first->protocol == htons(ETH_P_IPV6) && + igc_ipv6_csum_is_sctp(skb))) { + type_tucmd = IGC_ADVTXD_TUCMD_L4T_SCTP; + break; + } + /* fall through */ + default: + skb_checksum_help(skb); + goto csum_failed; + } + + /* update TX checksum flag */ + first->tx_flags |= IGC_TX_FLAGS_CSUM; + vlan_macip_lens = skb_checksum_start_offset(skb) - + skb_network_offset(skb); +no_csum: + vlan_macip_lens |= skb_network_offset(skb) << IGC_ADVTXD_MACLEN_SHIFT; + vlan_macip_lens |= first->tx_flags & IGC_TX_FLAGS_VLAN_MASK; + + igc_tx_ctxtdesc(tx_ring, first, vlan_macip_lens, type_tucmd, 0); } static int __igc_maybe_stop_tx(struct igc_ring *tx_ring, const u16 size) @@ -861,7 +956,7 @@ static int igc_tx_map(struct igc_ring *tx_ring, struct igc_tx_buffer *tx_buffer; union igc_adv_tx_desc *tx_desc; u32 tx_flags = first->tx_flags; - struct skb_frag_struct *frag; + skb_frag_t *frag; u16 i = tx_ring->next_to_use; unsigned int data_len, size; dma_addr_t dma; @@ -1015,7 +1110,8 @@ static netdev_tx_t igc_xmit_frame_ring(struct sk_buff *skb, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + count += TXD_USE_COUNT(skb_frag_size( + &skb_shinfo(skb)->frags[f])); if (igc_maybe_stop_tx(tx_ring, count + 3)) { /* this is a hard error */ @@ -4113,6 +4209,9 @@ static int igc_probe(struct pci_dev *pdev, if (err) goto err_sw_init; + /* Add supported features to the features list*/ + netdev->features |= NETIF_F_HW_CSUM; + /* setup the private structure */ err = igc_sw_init(adapter); if (err) @@ -4120,6 +4219,7 @@ static int igc_probe(struct pci_dev *pdev, /* copy netdev features into list of user selectable features */ netdev->hw_features |= NETIF_F_NTUPLE; + netdev->hw_features |= netdev->features; /* MTU range: 68 - 9216 */ netdev->min_mtu = ETH_MIN_MTU; @@ -4130,6 +4230,15 @@ static int igc_probe(struct pci_dev *pdev, */ hw->mac.ops.reset_hw(hw); + if (igc_get_flash_presence_i225(hw)) { + if (hw->nvm.ops.validate(hw) < 0) { + dev_err(&pdev->dev, + "The NVM Checksum Is Not Valid\n"); + err = -EIO; + goto err_eeprom; + } + } + if (eth_platform_get_mac_address(&pdev->dev, hw->mac.addr)) { /* copy the MAC address out of the NVM */ if (hw->mac.ops.read_mac_addr(hw)) diff --git a/drivers/net/ethernet/intel/igc/igc_phy.c b/drivers/net/ethernet/intel/igc/igc_phy.c index 4c8f96a9a148..f4b05af0dd2f 100644 --- a/drivers/net/ethernet/intel/igc/igc_phy.c +++ b/drivers/net/ethernet/intel/igc/igc_phy.c @@ -3,10 +3,6 @@ #include "igc_phy.h" -/* forward declaration */ -static s32 igc_phy_setup_autoneg(struct igc_hw *hw); -static s32 igc_wait_autoneg(struct igc_hw *hw); - /** * igc_check_reset_block - Check if PHY reset is blocked * @hw: pointer to the HW structure @@ -208,100 +204,6 @@ out: } /** - * igc_copper_link_autoneg - Setup/Enable autoneg for copper link - * @hw: pointer to the HW structure - * - * Performs initial bounds checking on autoneg advertisement parameter, then - * configure to advertise the full capability. Setup the PHY to autoneg - * and restart the negotiation process between the link partner. If - * autoneg_wait_to_complete, then wait for autoneg to complete before exiting. - */ -static s32 igc_copper_link_autoneg(struct igc_hw *hw) -{ - struct igc_phy_info *phy = &hw->phy; - u16 phy_ctrl; - s32 ret_val; - - /* Perform some bounds checking on the autoneg advertisement - * parameter. - */ - phy->autoneg_advertised &= phy->autoneg_mask; - - /* If autoneg_advertised is zero, we assume it was not defaulted - * by the calling code so we set to advertise full capability. - */ - if (phy->autoneg_advertised == 0) - phy->autoneg_advertised = phy->autoneg_mask; - - hw_dbg("Reconfiguring auto-neg advertisement params\n"); - ret_val = igc_phy_setup_autoneg(hw); - if (ret_val) { - hw_dbg("Error Setting up Auto-Negotiation\n"); - goto out; - } - hw_dbg("Restarting Auto-Neg\n"); - - /* Restart auto-negotiation by setting the Auto Neg Enable bit and - * the Auto Neg Restart bit in the PHY control register. - */ - ret_val = phy->ops.read_reg(hw, PHY_CONTROL, &phy_ctrl); - if (ret_val) - goto out; - - phy_ctrl |= (MII_CR_AUTO_NEG_EN | MII_CR_RESTART_AUTO_NEG); - ret_val = phy->ops.write_reg(hw, PHY_CONTROL, phy_ctrl); - if (ret_val) - goto out; - - /* Does the user want to wait for Auto-Neg to complete here, or - * check at a later time (for example, callback routine). - */ - if (phy->autoneg_wait_to_complete) { - ret_val = igc_wait_autoneg(hw); - if (ret_val) { - hw_dbg("Error while waiting for autoneg to complete\n"); - goto out; - } - } - - hw->mac.get_link_status = true; - -out: - return ret_val; -} - -/** - * igc_wait_autoneg - Wait for auto-neg completion - * @hw: pointer to the HW structure - * - * Waits for auto-negotiation to complete or for the auto-negotiation time - * limit to expire, which ever happens first. - */ -static s32 igc_wait_autoneg(struct igc_hw *hw) -{ - u16 i, phy_status; - s32 ret_val = 0; - - /* Break after autoneg completes or PHY_AUTO_NEG_LIMIT expires. */ - for (i = PHY_AUTO_NEG_LIMIT; i > 0; i--) { - ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status); - if (ret_val) - break; - ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status); - if (ret_val) - break; - if (phy_status & MII_SR_AUTONEG_COMPLETE) - break; - msleep(100); - } - - /* PHY_AUTO_NEG_TIME expiration doesn't guarantee auto-negotiation - * has completed. - */ - return ret_val; -} - -/** * igc_phy_setup_autoneg - Configure PHY for auto-negotiation * @hw: pointer to the HW structure * @@ -486,6 +388,100 @@ static s32 igc_phy_setup_autoneg(struct igc_hw *hw) } /** + * igc_wait_autoneg - Wait for auto-neg completion + * @hw: pointer to the HW structure + * + * Waits for auto-negotiation to complete or for the auto-negotiation time + * limit to expire, which ever happens first. + */ +static s32 igc_wait_autoneg(struct igc_hw *hw) +{ + u16 i, phy_status; + s32 ret_val = 0; + + /* Break after autoneg completes or PHY_AUTO_NEG_LIMIT expires. */ + for (i = PHY_AUTO_NEG_LIMIT; i > 0; i--) { + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status); + if (ret_val) + break; + ret_val = hw->phy.ops.read_reg(hw, PHY_STATUS, &phy_status); + if (ret_val) + break; + if (phy_status & MII_SR_AUTONEG_COMPLETE) + break; + msleep(100); + } + + /* PHY_AUTO_NEG_TIME expiration doesn't guarantee auto-negotiation + * has completed. + */ + return ret_val; +} + +/** + * igc_copper_link_autoneg - Setup/Enable autoneg for copper link + * @hw: pointer to the HW structure + * + * Performs initial bounds checking on autoneg advertisement parameter, then + * configure to advertise the full capability. Setup the PHY to autoneg + * and restart the negotiation process between the link partner. If + * autoneg_wait_to_complete, then wait for autoneg to complete before exiting. + */ +static s32 igc_copper_link_autoneg(struct igc_hw *hw) +{ + struct igc_phy_info *phy = &hw->phy; + u16 phy_ctrl; + s32 ret_val; + + /* Perform some bounds checking on the autoneg advertisement + * parameter. + */ + phy->autoneg_advertised &= phy->autoneg_mask; + + /* If autoneg_advertised is zero, we assume it was not defaulted + * by the calling code so we set to advertise full capability. + */ + if (phy->autoneg_advertised == 0) + phy->autoneg_advertised = phy->autoneg_mask; + + hw_dbg("Reconfiguring auto-neg advertisement params\n"); + ret_val = igc_phy_setup_autoneg(hw); + if (ret_val) { + hw_dbg("Error Setting up Auto-Negotiation\n"); + goto out; + } + hw_dbg("Restarting Auto-Neg\n"); + + /* Restart auto-negotiation by setting the Auto Neg Enable bit and + * the Auto Neg Restart bit in the PHY control register. + */ + ret_val = phy->ops.read_reg(hw, PHY_CONTROL, &phy_ctrl); + if (ret_val) + goto out; + + phy_ctrl |= (MII_CR_AUTO_NEG_EN | MII_CR_RESTART_AUTO_NEG); + ret_val = phy->ops.write_reg(hw, PHY_CONTROL, phy_ctrl); + if (ret_val) + goto out; + + /* Does the user want to wait for Auto-Neg to complete here, or + * check at a later time (for example, callback routine). + */ + if (phy->autoneg_wait_to_complete) { + ret_val = igc_wait_autoneg(hw); + if (ret_val) { + hw_dbg("Error while waiting for autoneg to complete\n"); + goto out; + } + } + + hw->mac.get_link_status = true; + +out: + return ret_val; +} + +/** * igc_setup_copper_link - Configure copper link settings * @hw: pointer to the HW structure * diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index e5ac2d3fd816..0940a0da16f2 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -1331,9 +1331,7 @@ ixgb_tx_map(struct ixgb_adapter *adapter, struct sk_buff *skb, } for (f = 0; f < nr_frags; f++) { - const struct skb_frag_struct *frag; - - frag = &skb_shinfo(skb)->frags[f]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; len = skb_frag_size(frag); offset = 0; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c index 50dfb02fa34c..171cdc552961 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c @@ -190,22 +190,12 @@ static const struct file_operations ixgbe_dbg_netdev_ops_fops = { void ixgbe_dbg_adapter_init(struct ixgbe_adapter *adapter) { const char *name = pci_name(adapter->pdev); - struct dentry *pfile; + adapter->ixgbe_dbg_adapter = debugfs_create_dir(name, ixgbe_dbg_root); - if (adapter->ixgbe_dbg_adapter) { - pfile = debugfs_create_file("reg_ops", 0600, - adapter->ixgbe_dbg_adapter, adapter, - &ixgbe_dbg_reg_ops_fops); - if (!pfile) - e_dev_err("debugfs reg_ops for %s failed\n", name); - pfile = debugfs_create_file("netdev_ops", 0600, - adapter->ixgbe_dbg_adapter, adapter, - &ixgbe_dbg_netdev_ops_fops); - if (!pfile) - e_dev_err("debugfs netdev_ops for %s failed\n", name); - } else { - e_dev_err("debugfs entry for %s failed\n", name); - } + debugfs_create_file("reg_ops", 0600, adapter->ixgbe_dbg_adapter, + adapter, &ixgbe_dbg_reg_ops_fops); + debugfs_create_file("netdev_ops", 0600, adapter->ixgbe_dbg_adapter, + adapter, &ixgbe_dbg_netdev_ops_fops); } /** @@ -224,8 +214,6 @@ void ixgbe_dbg_adapter_exit(struct ixgbe_adapter *adapter) void ixgbe_dbg_init(void) { ixgbe_dbg_root = debugfs_create_dir(ixgbe_driver_name, NULL); - if (ixgbe_dbg_root == NULL) - pr_err("init of debugfs failed\n"); } /** diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index 31629fc7e820..113f6087c7c9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -960,11 +960,9 @@ int ixgbe_ipsec_vf_add_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) return 0; err_aead: - memset(xs->aead, 0, sizeof(*xs->aead)); - kfree(xs->aead); + kzfree(xs->aead); err_xs: - memset(xs, 0, sizeof(*xs)); - kfree(xs); + kzfree(xs); err_out: msgbuf[1] = err; return err; @@ -1049,8 +1047,7 @@ int ixgbe_ipsec_vf_del_sa(struct ixgbe_adapter *adapter, u32 *msgbuf, u32 vf) ixgbe_ipsec_del_sa(xs); /* remove the xs that was made-up in the add request */ - memset(xs, 0, sizeof(*xs)); - kfree(xs); + kzfree(xs); return 0; } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 51c696b6bf64..1ce2397306b9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1786,7 +1786,7 @@ static bool ixgbe_is_non_eop(struct ixgbe_ring *rx_ring, static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, struct sk_buff *skb) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; unsigned char *va; unsigned int pull_len; @@ -1808,7 +1808,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, /* update all of the pointers */ skb_frag_size_sub(frag, pull_len); - frag->page_offset += pull_len; + skb_frag_off_add(frag, pull_len); skb->data_len -= pull_len; skb->tail += pull_len; } @@ -1826,13 +1826,7 @@ static void ixgbe_pull_tail(struct ixgbe_ring *rx_ring, static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, struct sk_buff *skb) { - /* if the page was released unmap it, else just sync our portion */ - if (unlikely(IXGBE_CB(skb)->page_released)) { - dma_unmap_page_attrs(rx_ring->dev, IXGBE_CB(skb)->dma, - ixgbe_rx_pg_size(rx_ring), - DMA_FROM_DEVICE, - IXGBE_RX_DMA_ATTR); - } else if (ring_uses_build_skb(rx_ring)) { + if (ring_uses_build_skb(rx_ring)) { unsigned long offset = (unsigned long)(skb->data) & ~PAGE_MASK; dma_sync_single_range_for_cpu(rx_ring->dev, @@ -1841,14 +1835,22 @@ static void ixgbe_dma_sync_frag(struct ixgbe_ring *rx_ring, skb_headlen(skb), DMA_FROM_DEVICE); } else { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[0]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[0]; dma_sync_single_range_for_cpu(rx_ring->dev, IXGBE_CB(skb)->dma, - frag->page_offset, + skb_frag_off(frag), skb_frag_size(frag), DMA_FROM_DEVICE); } + + /* If the page was released, just unmap it. */ + if (unlikely(IXGBE_CB(skb)->page_released)) { + dma_unmap_page_attrs(rx_ring->dev, IXGBE_CB(skb)->dma, + ixgbe_rx_pg_size(rx_ring), + DMA_FROM_DEVICE, + IXGBE_RX_DMA_ATTR); + } } /** @@ -8186,7 +8188,7 @@ static int ixgbe_tx_map(struct ixgbe_ring *tx_ring, struct sk_buff *skb = first->skb; struct ixgbe_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; - struct skb_frag_struct *frag; + skb_frag_t *frag; dma_addr_t dma; unsigned int data_len, size; u32 tx_flags = first->tx_flags; @@ -8605,7 +8607,8 @@ netdev_tx_t ixgbe_xmit_frame_ring(struct sk_buff *skb, * otherwise try next time */ for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + count += TXD_USE_COUNT(skb_frag_size( + &skb_shinfo(skb)->frags[f])); if (ixgbe_maybe_stop_tx(tx_ring, count + 3)) { tx_ring->tx_stats.tx_busy++; @@ -8748,7 +8751,7 @@ static netdev_tx_t __ixgbe_xmit_frame(struct sk_buff *skb, if (skb_put_padto(skb, 17)) return NETDEV_TX_OK; - tx_ring = ring ? ring : adapter->tx_ring[skb->queue_mapping]; + tx_ring = ring ? ring : adapter->tx_ring[skb_get_queue_mapping(skb)]; if (unlikely(test_bit(__IXGBE_TX_DISABLED, &tx_ring->state))) return NETDEV_TX_BUSY; @@ -9490,6 +9493,10 @@ static int ixgbe_configure_clsu32(struct ixgbe_adapter *adapter, jump->mat = nexthdr[i].jump; adapter->jump_tables[link_uhtid] = jump; break; + } else { + kfree(mask); + kfree(input); + kfree(jump); } } return 0; @@ -10262,7 +10269,8 @@ static int ixgbe_xdp_setup(struct net_device *dev, struct bpf_prog *prog) if (need_reset && prog) for (i = 0; i < adapter->num_rx_queues; i++) if (adapter->xdp_ring[i]->xsk_umem) - (void)ixgbe_xsk_async_xmit(adapter->netdev, i); + (void)ixgbe_xsk_wakeup(adapter->netdev, i, + XDP_WAKEUP_RX); return 0; } @@ -10381,7 +10389,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_features_check = ixgbe_features_check, .ndo_bpf = ixgbe_xdp, .ndo_xdp_xmit = ixgbe_xdp_xmit, - .ndo_xsk_async_xmit = ixgbe_xsk_async_xmit, + .ndo_xsk_wakeup = ixgbe_xsk_wakeup, }; static void ixgbe_disable_txr_hw(struct ixgbe_adapter *adapter, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h index d93a690aff74..6d01700b46bc 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_txrx_common.h @@ -42,7 +42,7 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, void ixgbe_xsk_clean_rx_ring(struct ixgbe_ring *rx_ring); bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, struct ixgbe_ring *tx_ring, int napi_budget); -int ixgbe_xsk_async_xmit(struct net_device *dev, u32 queue_id); +int ixgbe_xsk_wakeup(struct net_device *dev, u32 queue_id, u32 flags); void ixgbe_xsk_clean_tx_ring(struct ixgbe_ring *tx_ring); #endif /* #define _IXGBE_TXRX_COMMON_H_ */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c index a3b6d8c89127..100ac89b345d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c @@ -100,7 +100,7 @@ static int ixgbe_xsk_umem_enable(struct ixgbe_adapter *adapter, ixgbe_txrx_ring_enable(adapter, qid); /* Kick start the NAPI context so that receiving will start */ - err = ixgbe_xsk_async_xmit(adapter->netdev, qid); + err = ixgbe_xsk_wakeup(adapter->netdev, qid, XDP_WAKEUP_RX); if (err) return err; } @@ -143,15 +143,20 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter, struct ixgbe_ring *rx_ring, struct xdp_buff *xdp) { + struct xdp_umem *umem = rx_ring->xsk_umem; int err, result = IXGBE_XDP_PASS; struct bpf_prog *xdp_prog; struct xdp_frame *xdpf; + u64 offset; u32 act; rcu_read_lock(); xdp_prog = READ_ONCE(rx_ring->xdp_prog); act = bpf_prog_run_xdp(xdp_prog, xdp); - xdp->handle += xdp->data - xdp->data_hard_start; + offset = xdp->data - xdp->data_hard_start; + + xdp->handle = xsk_umem_adjust_offset(umem, xdp->handle, offset); + switch (act) { case XDP_PASS: break; @@ -201,8 +206,6 @@ ixgbe_rx_buffer *ixgbe_get_rx_buffer_zc(struct ixgbe_ring *rx_ring, static void ixgbe_reuse_rx_buffer_zc(struct ixgbe_ring *rx_ring, struct ixgbe_rx_buffer *obi) { - unsigned long mask = (unsigned long)rx_ring->xsk_umem->chunk_mask; - u64 hr = rx_ring->xsk_umem->headroom + XDP_PACKET_HEADROOM; u16 nta = rx_ring->next_to_alloc; struct ixgbe_rx_buffer *nbi; @@ -212,14 +215,9 @@ static void ixgbe_reuse_rx_buffer_zc(struct ixgbe_ring *rx_ring, rx_ring->next_to_alloc = (nta < rx_ring->count) ? nta : 0; /* transfer page from old buffer to new buffer */ - nbi->dma = obi->dma & mask; - nbi->dma += hr; - - nbi->addr = (void *)((unsigned long)obi->addr & mask); - nbi->addr += hr; - - nbi->handle = obi->handle & mask; - nbi->handle += rx_ring->xsk_umem->headroom; + nbi->dma = obi->dma; + nbi->addr = obi->addr; + nbi->handle = obi->handle; obi->addr = NULL; obi->skb = NULL; @@ -250,7 +248,8 @@ void ixgbe_zca_free(struct zero_copy_allocator *alloc, unsigned long handle) bi->addr = xdp_umem_get_data(rx_ring->xsk_umem, handle); bi->addr += hr; - bi->handle = (u64)handle + rx_ring->xsk_umem->headroom; + bi->handle = xsk_umem_adjust_offset(rx_ring->xsk_umem, (u64)handle, + rx_ring->xsk_umem->headroom); } static bool ixgbe_alloc_buffer_zc(struct ixgbe_ring *rx_ring, @@ -276,7 +275,7 @@ static bool ixgbe_alloc_buffer_zc(struct ixgbe_ring *rx_ring, bi->addr = xdp_umem_get_data(umem, handle); bi->addr += hr; - bi->handle = handle + umem->headroom; + bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom); xsk_umem_discard_addr(umem); return true; @@ -303,7 +302,7 @@ static bool ixgbe_alloc_buffer_slow_zc(struct ixgbe_ring *rx_ring, bi->addr = xdp_umem_get_data(umem, handle); bi->addr += hr; - bi->handle = handle + umem->headroom; + bi->handle = xsk_umem_adjust_offset(umem, handle, umem->headroom); xsk_umem_discard_addr_rq(umem); return true; @@ -547,6 +546,14 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector, q_vector->rx.total_packets += total_rx_packets; q_vector->rx.total_bytes += total_rx_bytes; + if (xsk_umem_uses_need_wakeup(rx_ring->xsk_umem)) { + if (failure || rx_ring->next_to_clean == rx_ring->next_to_use) + xsk_set_rx_need_wakeup(rx_ring->xsk_umem); + else + xsk_clear_rx_need_wakeup(rx_ring->xsk_umem); + + return (int)total_rx_packets; + } return failure ? budget : (int)total_rx_packets; } @@ -615,6 +622,8 @@ static bool ixgbe_xmit_zc(struct ixgbe_ring *xdp_ring, unsigned int budget) if (tx_desc) { ixgbe_xdp_ring_update_tail(xdp_ring); xsk_umem_consume_tx_done(xdp_ring->xsk_umem); + if (xsk_umem_uses_need_wakeup(xdp_ring->xsk_umem)) + xsk_clear_tx_need_wakeup(xdp_ring->xsk_umem); } return !!budget && work_done; @@ -682,10 +691,17 @@ bool ixgbe_clean_xdp_tx_irq(struct ixgbe_q_vector *q_vector, if (xsk_frames) xsk_umem_complete_tx(umem, xsk_frames); + if (xsk_umem_uses_need_wakeup(tx_ring->xsk_umem)) { + if (tx_ring->next_to_clean == tx_ring->next_to_use) + xsk_set_tx_need_wakeup(tx_ring->xsk_umem); + else + xsk_clear_tx_need_wakeup(tx_ring->xsk_umem); + } + return ixgbe_xmit_zc(tx_ring, q_vector->tx.work_limit); } -int ixgbe_xsk_async_xmit(struct net_device *dev, u32 qid) +int ixgbe_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_ring *ring; diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 72872d6ca80c..076f2da36f27 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -2262,12 +2262,14 @@ static void ixgbevf_init_last_counter_stats(struct ixgbevf_adapter *adapter) static void ixgbevf_negotiate_api(struct ixgbevf_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - int api[] = { ixgbe_mbox_api_14, - ixgbe_mbox_api_13, - ixgbe_mbox_api_12, - ixgbe_mbox_api_11, - ixgbe_mbox_api_10, - ixgbe_mbox_api_unknown }; + static const int api[] = { + ixgbe_mbox_api_14, + ixgbe_mbox_api_13, + ixgbe_mbox_api_12, + ixgbe_mbox_api_11, + ixgbe_mbox_api_10, + ixgbe_mbox_api_unknown + }; int err, idx = 0; spin_lock_bh(&adapter->mbx_lock); @@ -2518,6 +2520,7 @@ void ixgbevf_reinit_locked(struct ixgbevf_adapter *adapter) msleep(1); ixgbevf_down(adapter); + pci_set_master(adapter->pdev); ixgbevf_up(adapter); clear_bit(__IXGBEVF_RESETTING, &adapter->state); @@ -3950,7 +3953,7 @@ static void ixgbevf_tx_map(struct ixgbevf_ring *tx_ring, struct sk_buff *skb = first->skb; struct ixgbevf_tx_buffer *tx_buffer; union ixgbe_adv_tx_desc *tx_desc; - struct skb_frag_struct *frag; + skb_frag_t *frag; dma_addr_t dma; unsigned int data_len, size; u32 tx_flags = first->tx_flags; @@ -4135,8 +4138,11 @@ static int ixgbevf_xmit_frame_ring(struct sk_buff *skb, * otherwise try next time */ #if PAGE_SIZE > IXGBE_MAX_DATA_PER_TXD - for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) - count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size); + for (f = 0; f < skb_shinfo(skb)->nr_frags; f++) { + skb_frag_t *frag = &skb_shinfo(skb)->frags[f]; + + count += TXD_USE_COUNT(skb_frag_size(frag)); + } #else count += skb_shinfo(skb)->nr_frags; #endif diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c index 0b668357db4d..6d52cf5ce20e 100644 --- a/drivers/net/ethernet/jme.c +++ b/drivers/net/ethernet/jme.c @@ -2030,23 +2030,22 @@ jme_map_tx_skb(struct jme_adapter *jme, struct sk_buff *skb, int idx) bool hidma = jme->dev->features & NETIF_F_HIGHDMA; int i, nr_frags = skb_shinfo(skb)->nr_frags; int mask = jme->tx_ring_mask; - const struct skb_frag_struct *frag; u32 len; int ret = 0; for (i = 0 ; i < nr_frags ; ++i) { - frag = &skb_shinfo(skb)->frags[i]; + const skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; + ctxdesc = txdesc + ((idx + i + 2) & (mask)); ctxbi = txbi + ((idx + i + 2) & (mask)); ret = jme_fill_tx_map(jme->pdev, ctxdesc, ctxbi, - skb_frag_page(frag), - frag->page_offset, skb_frag_size(frag), hidma); + skb_frag_page(frag), skb_frag_off(frag), + skb_frag_size(frag), hidma); if (ret) { jme_drop_tx_map(jme, idx, i); goto out; } - } len = skb_is_nonlinear(skb) ? skb_headlen(skb) : skb->len; @@ -3193,8 +3192,7 @@ jme_shutdown(struct pci_dev *pdev) static int jme_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct jme_adapter *jme = netdev_priv(netdev); if (!netif_running(netdev)) @@ -3236,8 +3234,7 @@ jme_suspend(struct device *dev) static int jme_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct net_device *netdev = pci_get_drvdata(pdev); + struct net_device *netdev = dev_get_drvdata(dev); struct jme_adapter *jme = netdev_priv(netdev); if (!netif_running(netdev)) diff --git a/drivers/net/ethernet/lantiq_xrx200.c b/drivers/net/ethernet/lantiq_xrx200.c index cda641ef89af..900affbdcc0e 100644 --- a/drivers/net/ethernet/lantiq_xrx200.c +++ b/drivers/net/ethernet/lantiq_xrx200.c @@ -458,17 +458,11 @@ static int xrx200_probe(struct platform_device *pdev) } priv->chan_rx.dma.irq = platform_get_irq_byname(pdev, "rx"); - if (priv->chan_rx.dma.irq < 0) { - dev_err(dev, "failed to get RX IRQ, %i\n", - priv->chan_rx.dma.irq); + if (priv->chan_rx.dma.irq < 0) return -ENOENT; - } priv->chan_tx.dma.irq = platform_get_irq_byname(pdev, "tx"); - if (priv->chan_tx.dma.irq < 0) { - dev_err(dev, "failed to get TX IRQ, %i\n", - priv->chan_tx.dma.irq); + if (priv->chan_tx.dma.irq < 0) return -ENOENT; - } /* get the clock */ priv->clk = devm_clk_get(dev, NULL); diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 88ea5ac83c93..82ea55ae5053 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -659,7 +659,7 @@ static inline unsigned int has_tiny_unaligned_frags(struct sk_buff *skb) for (frag = 0; frag < skb_shinfo(skb)->nr_frags; frag++) { const skb_frag_t *fragp = &skb_shinfo(skb)->frags[frag]; - if (skb_frag_size(fragp) <= 8 && fragp->page_offset & 7) + if (skb_frag_size(fragp) <= 8 && skb_frag_off(fragp) & 7) return 1; } diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 895bfed26a8a..e49820675c8c 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -2350,10 +2350,10 @@ static int mvneta_tx_frag_process(struct mvneta_port *pp, struct sk_buff *skb, for (i = 0; i < nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - void *addr = page_address(frag->page.p) + frag->page_offset; + void *addr = skb_frag_address(frag); tx_desc = mvneta_txq_next_desc_get(txq); - tx_desc->data_size = frag->size; + tx_desc->data_size = skb_frag_size(frag); tx_desc->buf_phys_addr = dma_map_single(pp->dev->dev.parent, addr, @@ -4469,7 +4469,6 @@ static int mvneta_port_power_up(struct mvneta_port *pp, int phy_mode) /* Device initialization routine */ static int mvneta_probe(struct platform_device *pdev) { - struct resource *res; struct device_node *dn = pdev->dev.of_node; struct device_node *bm_node; struct mvneta_port *pp; @@ -4553,8 +4552,7 @@ static int mvneta_probe(struct platform_device *pdev) if (!IS_ERR(pp->clk_bus)) clk_prepare_enable(pp->clk_bus); - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - pp->base = devm_ioremap_resource(&pdev->dev, res); + pp->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(pp->base)) { err = PTR_ERR(pp->base); goto err_clk; diff --git a/drivers/net/ethernet/marvell/mvneta_bm.c b/drivers/net/ethernet/marvell/mvneta_bm.c index 82ee2bcca6fd..46c942ef2287 100644 --- a/drivers/net/ethernet/marvell/mvneta_bm.c +++ b/drivers/net/ethernet/marvell/mvneta_bm.c @@ -411,15 +411,13 @@ static int mvneta_bm_probe(struct platform_device *pdev) { struct device_node *dn = pdev->dev.of_node; struct mvneta_bm *priv; - struct resource *res; int err; priv = devm_kzalloc(&pdev->dev, sizeof(struct mvneta_bm), GFP_KERNEL); if (!priv) return -ENOMEM; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - priv->reg_base = devm_ioremap_resource(&pdev->dev, res); + priv->reg_base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(priv->reg_base)) return PTR_ERR(priv->reg_base); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h index 4d9564ba68f6..543a310ec102 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2.h +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2.h @@ -683,6 +683,7 @@ enum mvpp2_prs_l3_cast { #define MVPP2_BM_SHORT_BUF_NUM 2048 #define MVPP2_BM_POOL_SIZE_MAX (16*1024 - MVPP2_BM_POOL_PTR_ALIGN/4) #define MVPP2_BM_POOL_PTR_ALIGN 128 +#define MVPP2_BM_MAX_POOLS 8 /* BM cookie (32 bits) definition */ #define MVPP2_BM_COOKIE_POOL_OFFS 8 @@ -787,6 +788,9 @@ struct mvpp2 { /* Aggregated TXQs */ struct mvpp2_tx_queue *aggr_txqs; + /* Are we using page_pool with per-cpu pools? */ + int percpu_pools; + /* BM pools */ struct mvpp2_bm_pool *bm_pools; @@ -829,9 +833,8 @@ struct mvpp2_pcpu_stats { /* Per-CPU port control */ struct mvpp2_port_pcpu { struct hrtimer tx_done_timer; + struct net_device *dev; bool timer_scheduled; - /* Tasklet for egress finalization */ - struct tasklet_struct tx_done_tasklet; }; struct mvpp2_queue_vector { diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c index 274fb07362cb..4a3baa7e0142 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_debugfs.c @@ -452,8 +452,6 @@ static int mvpp2_dbgfs_flow_port_init(struct dentry *parent, struct dentry *port_dir; port_dir = debugfs_create_dir(port->dev->name, parent); - if (IS_ERR(port_dir)) - return PTR_ERR(port_dir); port_entry = &port->priv->dbgfs_entries->port_flow_entries[port->id]; @@ -480,8 +478,6 @@ static int mvpp2_dbgfs_flow_entry_init(struct dentry *parent, sprintf(flow_entry_name, "%02d", flow); flow_entry_dir = debugfs_create_dir(flow_entry_name, parent); - if (!flow_entry_dir) - return -ENOMEM; entry = &priv->dbgfs_entries->flow_entries[flow]; @@ -514,8 +510,6 @@ static int mvpp2_dbgfs_flow_init(struct dentry *parent, struct mvpp2 *priv) int i, ret; flow_dir = debugfs_create_dir("flows", parent); - if (!flow_dir) - return -ENOMEM; for (i = 0; i < MVPP2_N_PRS_FLOWS; i++) { ret = mvpp2_dbgfs_flow_entry_init(flow_dir, priv, i); @@ -539,8 +533,6 @@ static int mvpp2_dbgfs_prs_entry_init(struct dentry *parent, sprintf(prs_entry_name, "%03d", tid); prs_entry_dir = debugfs_create_dir(prs_entry_name, parent); - if (!prs_entry_dir) - return -ENOMEM; entry = &priv->dbgfs_entries->prs_entries[tid]; @@ -578,8 +570,6 @@ static int mvpp2_dbgfs_prs_init(struct dentry *parent, struct mvpp2 *priv) int i, ret; prs_dir = debugfs_create_dir("parser", parent); - if (!prs_dir) - return -ENOMEM; for (i = 0; i < MVPP2_PRS_TCAM_SRAM_SIZE; i++) { ret = mvpp2_dbgfs_prs_entry_init(prs_dir, priv, i); @@ -688,8 +678,6 @@ static int mvpp2_dbgfs_port_init(struct dentry *parent, struct dentry *port_dir; port_dir = debugfs_create_dir(port->dev->name, parent); - if (IS_ERR(port_dir)) - return PTR_ERR(port_dir); debugfs_create_file("parser_entries", 0444, port_dir, port, &mvpp2_dbgfs_port_parser_fops); @@ -716,15 +704,10 @@ void mvpp2_dbgfs_init(struct mvpp2 *priv, const char *name) int ret, i; mvpp2_root = debugfs_lookup(MVPP2_DRIVER_NAME, NULL); - if (!mvpp2_root) { + if (!mvpp2_root) mvpp2_root = debugfs_create_dir(MVPP2_DRIVER_NAME, NULL); - if (IS_ERR(mvpp2_root)) - return; - } mvpp2_dir = debugfs_create_dir(name, mvpp2_root); - if (IS_ERR(mvpp2_dir)) - return; priv->dbgfs_dir = mvpp2_dir; priv->dbgfs_entries = kzalloc(sizeof(*priv->dbgfs_entries), GFP_KERNEL); diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index ccdd47f3b8fb..111b3b8239e1 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -292,6 +292,26 @@ static void mvpp2_txq_inc_put(struct mvpp2_port *port, txq_pcpu->txq_put_index = 0; } +/* Get number of maximum RXQ */ +static int mvpp2_get_nrxqs(struct mvpp2 *priv) +{ + unsigned int nrxqs; + + if (priv->hw_version == MVPP22 && queue_mode == MVPP2_QDIST_SINGLE_MODE) + return 1; + + /* According to the PPv2.2 datasheet and our experiments on + * PPv2.1, RX queues have an allocation granularity of 4 (when + * more than a single one on PPv2.2). + * Round up to nearest multiple of 4. + */ + nrxqs = (num_possible_cpus() + 3) & ~0x3; + if (nrxqs > MVPP2_PORT_MAX_RXQ) + nrxqs = MVPP2_PORT_MAX_RXQ; + + return nrxqs; +} + /* Get number of physical egress port */ static inline int mvpp2_egress_port(struct mvpp2_port *port) { @@ -323,8 +343,7 @@ static void mvpp2_frag_free(const struct mvpp2_bm_pool *pool, void *data) /* Buffer Manager configuration routines */ /* Create pool */ -static int mvpp2_bm_pool_create(struct platform_device *pdev, - struct mvpp2 *priv, +static int mvpp2_bm_pool_create(struct device *dev, struct mvpp2 *priv, struct mvpp2_bm_pool *bm_pool, int size) { u32 val; @@ -343,7 +362,7 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev, else bm_pool->size_bytes = 2 * sizeof(u64) * size; - bm_pool->virt_addr = dma_alloc_coherent(&pdev->dev, bm_pool->size_bytes, + bm_pool->virt_addr = dma_alloc_coherent(dev, bm_pool->size_bytes, &bm_pool->dma_addr, GFP_KERNEL); if (!bm_pool->virt_addr) @@ -351,9 +370,9 @@ static int mvpp2_bm_pool_create(struct platform_device *pdev, if (!IS_ALIGNED((unsigned long)bm_pool->virt_addr, MVPP2_BM_POOL_PTR_ALIGN)) { - dma_free_coherent(&pdev->dev, bm_pool->size_bytes, + dma_free_coherent(dev, bm_pool->size_bytes, bm_pool->virt_addr, bm_pool->dma_addr); - dev_err(&pdev->dev, "BM pool %d is not %d bytes aligned\n", + dev_err(dev, "BM pool %d is not %d bytes aligned\n", bm_pool->id, MVPP2_BM_POOL_PTR_ALIGN); return -ENOMEM; } @@ -468,15 +487,14 @@ static int mvpp2_check_hw_buf_num(struct mvpp2 *priv, struct mvpp2_bm_pool *bm_p } /* Cleanup pool */ -static int mvpp2_bm_pool_destroy(struct platform_device *pdev, - struct mvpp2 *priv, +static int mvpp2_bm_pool_destroy(struct device *dev, struct mvpp2 *priv, struct mvpp2_bm_pool *bm_pool) { int buf_num; u32 val; buf_num = mvpp2_check_hw_buf_num(priv, bm_pool); - mvpp2_bm_bufs_free(&pdev->dev, priv, bm_pool, buf_num); + mvpp2_bm_bufs_free(dev, priv, bm_pool, buf_num); /* Check buffer counters after free */ buf_num = mvpp2_check_hw_buf_num(priv, bm_pool); @@ -490,24 +508,26 @@ static int mvpp2_bm_pool_destroy(struct platform_device *pdev, val |= MVPP2_BM_STOP_MASK; mvpp2_write(priv, MVPP2_BM_POOL_CTRL_REG(bm_pool->id), val); - dma_free_coherent(&pdev->dev, bm_pool->size_bytes, + dma_free_coherent(dev, bm_pool->size_bytes, bm_pool->virt_addr, bm_pool->dma_addr); return 0; } -static int mvpp2_bm_pools_init(struct platform_device *pdev, - struct mvpp2 *priv) +static int mvpp2_bm_pools_init(struct device *dev, struct mvpp2 *priv) { - int i, err, size; + int i, err, size, poolnum = MVPP2_BM_POOLS_NUM; struct mvpp2_bm_pool *bm_pool; + if (priv->percpu_pools) + poolnum = mvpp2_get_nrxqs(priv) * 2; + /* Create all pools with maximum size */ size = MVPP2_BM_POOL_SIZE_MAX; - for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) { + for (i = 0; i < poolnum; i++) { bm_pool = &priv->bm_pools[i]; bm_pool->id = i; - err = mvpp2_bm_pool_create(pdev, priv, bm_pool, size); + err = mvpp2_bm_pool_create(dev, priv, bm_pool, size); if (err) goto err_unroll_pools; mvpp2_bm_pool_bufsize_set(priv, bm_pool, 0); @@ -515,17 +535,23 @@ static int mvpp2_bm_pools_init(struct platform_device *pdev, return 0; err_unroll_pools: - dev_err(&pdev->dev, "failed to create BM pool %d, size %d\n", i, size); + dev_err(dev, "failed to create BM pool %d, size %d\n", i, size); for (i = i - 1; i >= 0; i--) - mvpp2_bm_pool_destroy(pdev, priv, &priv->bm_pools[i]); + mvpp2_bm_pool_destroy(dev, priv, &priv->bm_pools[i]); return err; } -static int mvpp2_bm_init(struct platform_device *pdev, struct mvpp2 *priv) +static int mvpp2_bm_init(struct device *dev, struct mvpp2 *priv) { - int i, err; + int i, err, poolnum = MVPP2_BM_POOLS_NUM; - for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) { + if (priv->percpu_pools) + poolnum = mvpp2_get_nrxqs(priv) * 2; + + dev_info(dev, "using %d %s buffers\n", poolnum, + priv->percpu_pools ? "per-cpu" : "shared"); + + for (i = 0; i < poolnum; i++) { /* Mask BM all interrupts */ mvpp2_write(priv, MVPP2_BM_INTR_MASK_REG(i), 0); /* Clear BM cause register */ @@ -533,12 +559,12 @@ static int mvpp2_bm_init(struct platform_device *pdev, struct mvpp2 *priv) } /* Allocate and initialize BM pools */ - priv->bm_pools = devm_kcalloc(&pdev->dev, MVPP2_BM_POOLS_NUM, + priv->bm_pools = devm_kcalloc(dev, poolnum, sizeof(*priv->bm_pools), GFP_KERNEL); if (!priv->bm_pools) return -ENOMEM; - err = mvpp2_bm_pools_init(pdev, priv); + err = mvpp2_bm_pools_init(dev, priv); if (err < 0) return err; return 0; @@ -679,6 +705,13 @@ static int mvpp2_bm_bufs_add(struct mvpp2_port *port, phys_addr_t phys_addr; void *buf; + if (port->priv->percpu_pools && + bm_pool->pkt_size > MVPP2_BM_LONG_PKT_SIZE) { + netdev_err(port->dev, + "attempted to use jumbo frames with per-cpu pools"); + return 0; + } + buf_size = MVPP2_RX_BUF_SIZE(bm_pool->pkt_size); total_size = MVPP2_RX_TOTAL_SIZE(buf_size); @@ -722,7 +755,64 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, unsigned pool, int pkt_size) struct mvpp2_bm_pool *new_pool = &port->priv->bm_pools[pool]; int num; - if (pool >= MVPP2_BM_POOLS_NUM) { + if ((port->priv->percpu_pools && pool > mvpp2_get_nrxqs(port->priv) * 2) || + (!port->priv->percpu_pools && pool >= MVPP2_BM_POOLS_NUM)) { + netdev_err(port->dev, "Invalid pool %d\n", pool); + return NULL; + } + + /* Allocate buffers in case BM pool is used as long pool, but packet + * size doesn't match MTU or BM pool hasn't being used yet + */ + if (new_pool->pkt_size == 0) { + int pkts_num; + + /* Set default buffer number or free all the buffers in case + * the pool is not empty + */ + pkts_num = new_pool->buf_num; + if (pkts_num == 0) { + if (port->priv->percpu_pools) { + if (pool < port->nrxqs) + pkts_num = mvpp2_pools[MVPP2_BM_SHORT].buf_num; + else + pkts_num = mvpp2_pools[MVPP2_BM_LONG].buf_num; + } else { + pkts_num = mvpp2_pools[pool].buf_num; + } + } else { + mvpp2_bm_bufs_free(port->dev->dev.parent, + port->priv, new_pool, pkts_num); + } + + new_pool->pkt_size = pkt_size; + new_pool->frag_size = + SKB_DATA_ALIGN(MVPP2_RX_BUF_SIZE(pkt_size)) + + MVPP2_SKB_SHINFO_SIZE; + + /* Allocate buffers for this pool */ + num = mvpp2_bm_bufs_add(port, new_pool, pkts_num); + if (num != pkts_num) { + WARN(1, "pool %d: %d of %d allocated\n", + new_pool->id, num, pkts_num); + return NULL; + } + } + + mvpp2_bm_pool_bufsize_set(port->priv, new_pool, + MVPP2_RX_BUF_SIZE(new_pool->pkt_size)); + + return new_pool; +} + +static struct mvpp2_bm_pool * +mvpp2_bm_pool_use_percpu(struct mvpp2_port *port, int type, + unsigned int pool, int pkt_size) +{ + struct mvpp2_bm_pool *new_pool = &port->priv->bm_pools[pool]; + int num; + + if (pool > port->nrxqs * 2) { netdev_err(port->dev, "Invalid pool %d\n", pool); return NULL; } @@ -738,7 +828,7 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, unsigned pool, int pkt_size) */ pkts_num = new_pool->buf_num; if (pkts_num == 0) - pkts_num = mvpp2_pools[pool].buf_num; + pkts_num = mvpp2_pools[type].buf_num; else mvpp2_bm_bufs_free(port->dev->dev.parent, port->priv, new_pool, pkts_num); @@ -763,11 +853,11 @@ mvpp2_bm_pool_use(struct mvpp2_port *port, unsigned pool, int pkt_size) return new_pool; } -/* Initialize pools for swf */ -static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) +/* Initialize pools for swf, shared buffers variant */ +static int mvpp2_swf_bm_pool_init_shared(struct mvpp2_port *port) { - int rxq; enum mvpp2_bm_pool_log_num long_log_pool, short_log_pool; + int rxq; /* If port pkt_size is higher than 1518B: * HW Long pool - SW Jumbo pool, HW Short pool - SW Long pool @@ -811,6 +901,47 @@ static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) return 0; } +/* Initialize pools for swf, percpu buffers variant */ +static int mvpp2_swf_bm_pool_init_percpu(struct mvpp2_port *port) +{ + struct mvpp2_bm_pool *p; + int i; + + for (i = 0; i < port->nrxqs; i++) { + p = mvpp2_bm_pool_use_percpu(port, MVPP2_BM_SHORT, i, + mvpp2_pools[MVPP2_BM_SHORT].pkt_size); + if (!p) + return -ENOMEM; + + port->priv->bm_pools[i].port_map |= BIT(port->id); + mvpp2_rxq_short_pool_set(port, i, port->priv->bm_pools[i].id); + } + + for (i = 0; i < port->nrxqs; i++) { + p = mvpp2_bm_pool_use_percpu(port, MVPP2_BM_LONG, i + port->nrxqs, + mvpp2_pools[MVPP2_BM_LONG].pkt_size); + if (!p) + return -ENOMEM; + + port->priv->bm_pools[i + port->nrxqs].port_map |= BIT(port->id); + mvpp2_rxq_long_pool_set(port, i, + port->priv->bm_pools[i + port->nrxqs].id); + } + + port->pool_long = NULL; + port->pool_short = NULL; + + return 0; +} + +static int mvpp2_swf_bm_pool_init(struct mvpp2_port *port) +{ + if (port->priv->percpu_pools) + return mvpp2_swf_bm_pool_init_percpu(port); + else + return mvpp2_swf_bm_pool_init_shared(port); +} + static void mvpp2_set_hw_csum(struct mvpp2_port *port, enum mvpp2_bm_pool_log_num new_long_pool) { @@ -837,6 +968,9 @@ static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu) enum mvpp2_bm_pool_log_num new_long_pool; int pkt_size = MVPP2_RX_PKT_SIZE(mtu); + if (port->priv->percpu_pools) + goto out_set; + /* If port MTU is higher than 1518B: * HW Long pool - SW Jumbo pool, HW Short pool - SW Long pool * else: HW Long pool - SW Long pool, HW Short pool - SW Short pool @@ -866,6 +1000,7 @@ static int mvpp2_bm_update_mtu(struct net_device *dev, int mtu) mvpp2_set_hw_csum(port, new_long_pool); } +out_set: dev->mtu = mtu; dev->wanted_features = dev->features; @@ -2651,31 +2786,21 @@ handled: return IRQ_HANDLED; } -static void mvpp2_timer_set(struct mvpp2_port_pcpu *port_pcpu) -{ - ktime_t interval; - - if (!port_pcpu->timer_scheduled) { - port_pcpu->timer_scheduled = true; - interval = MVPP2_TXDONE_HRTIMER_PERIOD_NS; - hrtimer_start(&port_pcpu->tx_done_timer, interval, - HRTIMER_MODE_REL_PINNED); - } -} - -static void mvpp2_tx_proc_cb(unsigned long data) +static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer) { - struct net_device *dev = (struct net_device *)data; - struct mvpp2_port *port = netdev_priv(dev); + struct net_device *dev; + struct mvpp2_port *port; struct mvpp2_port_pcpu *port_pcpu; unsigned int tx_todo, cause; - port_pcpu = per_cpu_ptr(port->pcpu, - mvpp2_cpu_to_thread(port->priv, smp_processor_id())); + port_pcpu = container_of(timer, struct mvpp2_port_pcpu, tx_done_timer); + dev = port_pcpu->dev; if (!netif_running(dev)) - return; + return HRTIMER_NORESTART; + port_pcpu->timer_scheduled = false; + port = netdev_priv(dev); /* Process all the Tx queues */ cause = (1 << port->ntxqs) - 1; @@ -2683,18 +2808,13 @@ static void mvpp2_tx_proc_cb(unsigned long data) mvpp2_cpu_to_thread(port->priv, smp_processor_id())); /* Set the timer in case not all the packets were processed */ - if (tx_todo) - mvpp2_timer_set(port_pcpu); -} - -static enum hrtimer_restart mvpp2_hr_timer_cb(struct hrtimer *timer) -{ - struct mvpp2_port_pcpu *port_pcpu = container_of(timer, - struct mvpp2_port_pcpu, - tx_done_timer); - - tasklet_schedule(&port_pcpu->tx_done_tasklet); + if (tx_todo && !port_pcpu->timer_scheduled) { + port_pcpu->timer_scheduled = true; + hrtimer_forward_now(&port_pcpu->tx_done_timer, + MVPP2_TXDONE_HRTIMER_PERIOD_NS); + return HRTIMER_RESTART; + } return HRTIMER_NORESTART; } @@ -2923,14 +3043,15 @@ static int mvpp2_tx_frag_process(struct mvpp2_port *port, struct sk_buff *skb, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; - void *addr = page_address(frag->page.p) + frag->page_offset; + void *addr = skb_frag_address(frag); tx_desc = mvpp2_txq_next_desc_get(aggr_txq); mvpp2_txdesc_txq_set(port, tx_desc, txq->id); - mvpp2_txdesc_size_set(port, tx_desc, frag->size); + mvpp2_txdesc_size_set(port, tx_desc, skb_frag_size(frag)); buf_dma_addr = dma_map_single(port->dev->dev.parent, addr, - frag->size, DMA_TO_DEVICE); + skb_frag_size(frag), + DMA_TO_DEVICE); if (dma_mapping_error(port->dev->dev.parent, buf_dma_addr)) { mvpp2_txq_desc_put(txq); goto cleanup; @@ -3181,7 +3302,12 @@ out: txq_pcpu->count > 0) { struct mvpp2_port_pcpu *port_pcpu = per_cpu_ptr(port->pcpu, thread); - mvpp2_timer_set(port_pcpu); + if (!port_pcpu->timer_scheduled) { + port_pcpu->timer_scheduled = true; + hrtimer_start(&port_pcpu->tx_done_timer, + MVPP2_TXDONE_HRTIMER_PERIOD_NS, + HRTIMER_MODE_REL_PINNED_SOFT); + } } if (test_bit(thread, &port->priv->lock_map)) @@ -3618,7 +3744,6 @@ static int mvpp2_stop(struct net_device *dev) hrtimer_cancel(&port_pcpu->tx_done_timer); port_pcpu->timer_scheduled = false; - tasklet_kill(&port_pcpu->tx_done_tasklet); } } mvpp2_cleanup_rxqs(port); @@ -3709,10 +3834,48 @@ static int mvpp2_set_mac_address(struct net_device *dev, void *p) return err; } +/* Shut down all the ports, reconfigure the pools as percpu or shared, + * then bring up again all ports. + */ +static int mvpp2_bm_switch_buffers(struct mvpp2 *priv, bool percpu) +{ + int numbufs = MVPP2_BM_POOLS_NUM, i; + struct mvpp2_port *port = NULL; + bool status[MVPP2_MAX_PORTS]; + + for (i = 0; i < priv->port_count; i++) { + port = priv->port_list[i]; + status[i] = netif_running(port->dev); + if (status[i]) + mvpp2_stop(port->dev); + } + + /* nrxqs is the same for all ports */ + if (priv->percpu_pools) + numbufs = port->nrxqs * 2; + + for (i = 0; i < numbufs; i++) + mvpp2_bm_pool_destroy(port->dev->dev.parent, priv, &priv->bm_pools[i]); + + devm_kfree(port->dev->dev.parent, priv->bm_pools); + priv->percpu_pools = percpu; + mvpp2_bm_init(port->dev->dev.parent, priv); + + for (i = 0; i < priv->port_count; i++) { + port = priv->port_list[i]; + mvpp2_swf_bm_pool_init(port); + if (status[i]) + mvpp2_open(port->dev); + } + + return 0; +} + static int mvpp2_change_mtu(struct net_device *dev, int mtu) { struct mvpp2_port *port = netdev_priv(dev); bool running = netif_running(dev); + struct mvpp2 *priv = port->priv; int err; if (!IS_ALIGNED(MVPP2_RX_PKT_SIZE(mtu), 8)) { @@ -3721,6 +3884,31 @@ static int mvpp2_change_mtu(struct net_device *dev, int mtu) mtu = ALIGN(MVPP2_RX_PKT_SIZE(mtu), 8); } + if (MVPP2_RX_PKT_SIZE(mtu) > MVPP2_BM_LONG_PKT_SIZE) { + if (priv->percpu_pools) { + netdev_warn(dev, "mtu %d too high, switching to shared buffers", mtu); + mvpp2_bm_switch_buffers(priv, false); + } + } else { + bool jumbo = false; + int i; + + for (i = 0; i < priv->port_count; i++) + if (priv->port_list[i] != port && + MVPP2_RX_PKT_SIZE(priv->port_list[i]->dev->mtu) > + MVPP2_BM_LONG_PKT_SIZE) { + jumbo = true; + break; + } + + /* No port is using jumbo frames */ + if (!jumbo) { + dev_info(port->dev->dev.parent, + "all ports have a low MTU, switching to per-cpu buffers"); + mvpp2_bm_switch_buffers(priv, true); + } + } + if (running) mvpp2_stop_dev(port); @@ -5010,7 +5198,6 @@ static int mvpp2_port_probe(struct platform_device *pdev, struct device_node *port_node = to_of_node(port_fwnode); netdev_features_t features; struct net_device *dev; - struct resource *res; struct phylink *phylink; char *mac_from = ""; unsigned int ntxqs, nrxqs, thread; @@ -5028,18 +5215,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, } ntxqs = MVPP2_MAX_TXQ; - if (priv->hw_version == MVPP22 && queue_mode == MVPP2_QDIST_SINGLE_MODE) { - nrxqs = 1; - } else { - /* According to the PPv2.2 datasheet and our experiments on - * PPv2.1, RX queues have an allocation granularity of 4 (when - * more than a single one on PPv2.2). - * Round up to nearest multiple of 4. - */ - nrxqs = (num_possible_cpus() + 3) & ~0x3; - if (nrxqs > MVPP2_PORT_MAX_RXQ) - nrxqs = MVPP2_PORT_MAX_RXQ; - } + nrxqs = mvpp2_get_nrxqs(priv); dev = alloc_etherdev_mqs(sizeof(*port), ntxqs, nrxqs); if (!dev) @@ -5114,8 +5290,7 @@ static int mvpp2_port_probe(struct platform_device *pdev, port->comphy = comphy; if (priv->hw_version == MVPP21) { - res = platform_get_resource(pdev, IORESOURCE_MEM, 2 + id); - port->base = devm_ioremap_resource(&pdev->dev, res); + port->base = devm_platform_ioremap_resource(pdev, 2 + id); if (IS_ERR(port->base)) { err = PTR_ERR(port->base); goto err_free_irq; @@ -5184,13 +5359,10 @@ static int mvpp2_port_probe(struct platform_device *pdev, port_pcpu = per_cpu_ptr(port->pcpu, thread); hrtimer_init(&port_pcpu->tx_done_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_REL_PINNED); + HRTIMER_MODE_REL_PINNED_SOFT); port_pcpu->tx_done_timer.function = mvpp2_hr_timer_cb; port_pcpu->timer_scheduled = false; - - tasklet_init(&port_pcpu->tx_done_tasklet, - mvpp2_tx_proc_cb, - (unsigned long)dev); + port_pcpu->dev = dev; } } @@ -5205,7 +5377,8 @@ static int mvpp2_port_probe(struct platform_device *pdev, dev->features |= NETIF_F_NTUPLE; } - mvpp2_set_hw_csum(port, port->pool_long->id); + if (!port->priv->percpu_pools) + mvpp2_set_hw_csum(port, port->pool_long->id); dev->vlan_features |= features; dev->gso_max_segs = MVPP2_MAX_TSO_SEGS; @@ -5497,7 +5670,7 @@ static int mvpp2_init(struct platform_device *pdev, struct mvpp2 *priv) mvpp2_write(priv, MVPP2_TX_SNOOP_REG, 0x1); /* Buffer Manager initialization */ - err = mvpp2_bm_init(pdev, priv); + err = mvpp2_bm_init(&pdev->dev, priv); if (err < 0) return err; @@ -5544,14 +5717,12 @@ static int mvpp2_probe(struct platform_device *pdev) if (priv->hw_version == MVPP21) queue_mode = MVPP2_QDIST_SINGLE_MODE; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - base = devm_ioremap_resource(&pdev->dev, res); + base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) return PTR_ERR(base); if (priv->hw_version == MVPP21) { - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - priv->lms_base = devm_ioremap_resource(&pdev->dev, res); + priv->lms_base = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(priv->lms_base)) return PTR_ERR(priv->lms_base); } else { @@ -5585,6 +5756,10 @@ static int mvpp2_probe(struct platform_device *pdev) priv->sysctrl_base = NULL; } + if (priv->hw_version == MVPP22 && + mvpp2_get_nrxqs(priv) * 2 <= MVPP2_BM_MAX_POOLS) + priv->percpu_pools = 1; + mvpp2_setup_bm_pool(); @@ -5766,7 +5941,7 @@ static int mvpp2_remove(struct platform_device *pdev) for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) { struct mvpp2_bm_pool *bm_pool = &priv->bm_pools[i]; - mvpp2_bm_pool_destroy(pdev, priv, bm_pool); + mvpp2_bm_pool_destroy(&pdev->dev, priv, bm_pool); } for (i = 0; i < MVPP2_MAX_THREADS; i++) { diff --git a/drivers/net/ethernet/marvell/pxa168_eth.c b/drivers/net/ethernet/marvell/pxa168_eth.c index 3aa998797bc1..51b77c2de400 100644 --- a/drivers/net/ethernet/marvell/pxa168_eth.c +++ b/drivers/net/ethernet/marvell/pxa168_eth.c @@ -1425,8 +1425,7 @@ static int pxa168_eth_probe(struct platform_device *pdev) pep->dev = dev; pep->clk = clk; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - pep->base = devm_ioremap_resource(&pdev->dev, res); + pep->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(pep->base)) { err = -ENOMEM; goto err_netdev; diff --git a/drivers/net/ethernet/marvell/skge.c b/drivers/net/ethernet/marvell/skge.c index 9ac854c2b371..0a2ec387a482 100644 --- a/drivers/net/ethernet/marvell/skge.c +++ b/drivers/net/ethernet/marvell/skge.c @@ -3731,7 +3731,6 @@ static int skge_device_event(struct notifier_block *unused, { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct skge_port *skge; - struct dentry *d; if (dev->netdev_ops->ndo_open != &skge_up || !skge_debug) goto done; @@ -3739,33 +3738,20 @@ static int skge_device_event(struct notifier_block *unused, skge = netdev_priv(dev); switch (event) { case NETDEV_CHANGENAME: - if (skge->debugfs) { - d = debugfs_rename(skge_debug, skge->debugfs, - skge_debug, dev->name); - if (d) - skge->debugfs = d; - else { - netdev_info(dev, "rename failed\n"); - debugfs_remove(skge->debugfs); - } - } + if (skge->debugfs) + skge->debugfs = debugfs_rename(skge_debug, + skge->debugfs, + skge_debug, dev->name); break; case NETDEV_GOING_DOWN: - if (skge->debugfs) { - debugfs_remove(skge->debugfs); - skge->debugfs = NULL; - } + debugfs_remove(skge->debugfs); + skge->debugfs = NULL; break; case NETDEV_UP: - d = debugfs_create_file(dev->name, 0444, - skge_debug, dev, - &skge_debug_fops); - if (!d || IS_ERR(d)) - netdev_info(dev, "debugfs create failed\n"); - else - skge->debugfs = d; + skge->debugfs = debugfs_create_file(dev->name, 0444, skge_debug, + dev, &skge_debug_fops); break; } @@ -3780,15 +3766,8 @@ static struct notifier_block skge_notifier = { static __init void skge_debug_init(void) { - struct dentry *ent; + skge_debug = debugfs_create_dir("skge", NULL); - ent = debugfs_create_dir("skge", NULL); - if (!ent || IS_ERR(ent)) { - pr_info("debugfs create directory failed\n"); - return; - } - - skge_debug = ent; register_netdevice_notifier(&skge_notifier); } @@ -4078,8 +4057,7 @@ static void skge_remove(struct pci_dev *pdev) #ifdef CONFIG_PM_SLEEP static int skge_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct skge_hw *hw = pci_get_drvdata(pdev); + struct skge_hw *hw = dev_get_drvdata(dev); int i; if (!hw) @@ -4103,8 +4081,7 @@ static int skge_suspend(struct device *dev) static int skge_resume(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct skge_hw *hw = pci_get_drvdata(pdev); + struct skge_hw *hw = dev_get_drvdata(dev); int i, err; if (!hw) diff --git a/drivers/net/ethernet/marvell/sky2.c b/drivers/net/ethernet/marvell/sky2.c index e0363870f3a5..5f56ee83e3b1 100644 --- a/drivers/net/ethernet/marvell/sky2.c +++ b/drivers/net/ethernet/marvell/sky2.c @@ -5174,8 +5174,7 @@ static void sky2_remove(struct pci_dev *pdev) static int sky2_suspend(struct device *dev) { - struct pci_dev *pdev = to_pci_dev(dev); - struct sky2_hw *hw = pci_get_drvdata(pdev); + struct sky2_hw *hw = dev_get_drvdata(dev); int i; if (!hw) diff --git a/drivers/net/ethernet/mediatek/Kconfig b/drivers/net/ethernet/mediatek/Kconfig index 1f7fff81f24d..4968352ba188 100644 --- a/drivers/net/ethernet/mediatek/Kconfig +++ b/drivers/net/ethernet/mediatek/Kconfig @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only config NET_VENDOR_MEDIATEK bool "MediaTek ethernet driver" - depends on ARCH_MEDIATEK || SOC_MT7621 + depends on ARCH_MEDIATEK || SOC_MT7621 || SOC_MT7620 ---help--- If you have a Mediatek SoC with ethernet, say Y. @@ -9,7 +9,7 @@ if NET_VENDOR_MEDIATEK config NET_MEDIATEK_SOC tristate "MediaTek SoC Gigabit Ethernet support" - select PHYLIB + select PHYLINK ---help--- This driver supports the gigabit ethernet MACs in the MediaTek SoC family. diff --git a/drivers/net/ethernet/mediatek/mtk_eth_path.c b/drivers/net/ethernet/mediatek/mtk_eth_path.c index 7f05880cf9ef..ef11cf3d1ccc 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_path.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_path.c @@ -239,10 +239,9 @@ out: return err; } -static int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id) +int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id) { - unsigned int val = 0; - int sid, err, path; + int err, path; path = (mac_id == 0) ? MTK_ETH_PATH_GMAC1_SGMII : MTK_ETH_PATH_GMAC2_SGMII; @@ -252,33 +251,10 @@ static int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id) if (err) return err; - /* The path GMAC to SGMII will be enabled once the SGMIISYS is being - * setup done. - */ - regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val); - - regmap_update_bits(eth->ethsys, ETHSYS_SYSCFG0, - SYSCFG0_SGMII_MASK, ~(u32)SYSCFG0_SGMII_MASK); - - /* Decide how GMAC and SGMIISYS be mapped */ - sid = (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_SGMII)) ? 0 : mac_id; - - /* Setup SGMIISYS with the determined property */ - if (MTK_HAS_FLAGS(eth->sgmii->flags[sid], MTK_SGMII_PHYSPEED_AN)) - err = mtk_sgmii_setup_mode_an(eth->sgmii, sid); - else - err = mtk_sgmii_setup_mode_force(eth->sgmii, sid); - - if (err) - return err; - - regmap_update_bits(eth->ethsys, ETHSYS_SYSCFG0, - SYSCFG0_SGMII_MASK, val); - return 0; } -static int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id) +int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id) { int err, path = 0; @@ -296,7 +272,7 @@ static int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id) return 0; } -static int mtk_gmac_rgmii_path_setup(struct mtk_eth *eth, int mac_id) +int mtk_gmac_rgmii_path_setup(struct mtk_eth *eth, int mac_id) { int err, path; @@ -311,42 +287,3 @@ static int mtk_gmac_rgmii_path_setup(struct mtk_eth *eth, int mac_id) return 0; } -int mtk_setup_hw_path(struct mtk_eth *eth, int mac_id, int phymode) -{ - int err; - - switch (phymode) { - case PHY_INTERFACE_MODE_TRGMII: - case PHY_INTERFACE_MODE_RGMII_TXID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_ID: - case PHY_INTERFACE_MODE_RGMII: - case PHY_INTERFACE_MODE_MII: - case PHY_INTERFACE_MODE_REVMII: - case PHY_INTERFACE_MODE_RMII: - if (MTK_HAS_CAPS(eth->soc->caps, MTK_RGMII)) { - err = mtk_gmac_rgmii_path_setup(eth, mac_id); - if (err) - return err; - } - break; - case PHY_INTERFACE_MODE_SGMII: - if (MTK_HAS_CAPS(eth->soc->caps, MTK_SGMII)) { - err = mtk_gmac_sgmii_path_setup(eth, mac_id); - if (err) - return err; - } - break; - case PHY_INTERFACE_MODE_GMII: - if (MTK_HAS_CAPS(eth->soc->caps, MTK_GEPHY)) { - err = mtk_gmac_gephy_path_setup(eth, mac_id); - if (err) - return err; - } - break; - default: - break; - } - - return 0; -} diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index c39d7f4ab1d4..c61069340f4f 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -18,6 +18,7 @@ #include <linux/tcp.h> #include <linux/interrupt.h> #include <linux/pinctrl/devinfo.h> +#include <linux/phylink.h> #include "mtk_eth_soc.h" @@ -186,165 +187,339 @@ static void mtk_gmac0_rgmii_adjust(struct mtk_eth *eth, int speed) mtk_w32(eth, val, TRGMII_TCK_CTRL); } -static void mtk_phy_link_adjust(struct net_device *dev) +static void mtk_mac_config(struct phylink_config *config, unsigned int mode, + const struct phylink_link_state *state) { - struct mtk_mac *mac = netdev_priv(dev); - u16 lcl_adv = 0, rmt_adv = 0; - u8 flowctrl; - u32 mcr = MAC_MCR_MAX_RX_1536 | MAC_MCR_IPG_CFG | - MAC_MCR_FORCE_MODE | MAC_MCR_TX_EN | - MAC_MCR_RX_EN | MAC_MCR_BACKOFF_EN | - MAC_MCR_BACKPR_EN; + struct mtk_mac *mac = container_of(config, struct mtk_mac, + phylink_config); + struct mtk_eth *eth = mac->hw; + u32 mcr_cur, mcr_new, sid; + int val, ge_mode, err; + + /* MT76x8 has no hardware settings between for the MAC */ + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628) && + mac->interface != state->interface) { + /* Setup soc pin functions */ + switch (state->interface) { + case PHY_INTERFACE_MODE_TRGMII: + if (mac->id) + goto err_phy; + if (!MTK_HAS_CAPS(mac->hw->soc->caps, + MTK_GMAC1_TRGMII)) + goto err_phy; + /* fall through */ + case PHY_INTERFACE_MODE_RGMII_TXID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_MII: + case PHY_INTERFACE_MODE_REVMII: + case PHY_INTERFACE_MODE_RMII: + if (MTK_HAS_CAPS(eth->soc->caps, MTK_RGMII)) { + err = mtk_gmac_rgmii_path_setup(eth, mac->id); + if (err) + goto init_err; + } + break; + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: + case PHY_INTERFACE_MODE_SGMII: + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SGMII)) { + err = mtk_gmac_sgmii_path_setup(eth, mac->id); + if (err) + goto init_err; + } + break; + case PHY_INTERFACE_MODE_GMII: + if (MTK_HAS_CAPS(eth->soc->caps, MTK_GEPHY)) { + err = mtk_gmac_gephy_path_setup(eth, mac->id); + if (err) + goto init_err; + } + break; + default: + goto err_phy; + } - if (unlikely(test_bit(MTK_RESETTING, &mac->hw->state))) + /* Setup clock for 1st gmac */ + if (!mac->id && state->interface != PHY_INTERFACE_MODE_SGMII && + !phy_interface_mode_is_8023z(state->interface) && + MTK_HAS_CAPS(mac->hw->soc->caps, MTK_GMAC1_TRGMII)) { + if (MTK_HAS_CAPS(mac->hw->soc->caps, + MTK_TRGMII_MT7621_CLK)) { + if (mt7621_gmac0_rgmii_adjust(mac->hw, + state->interface)) + goto err_phy; + } else { + if (state->interface != + PHY_INTERFACE_MODE_TRGMII) + mtk_gmac0_rgmii_adjust(mac->hw, + state->speed); + } + } + + ge_mode = 0; + switch (state->interface) { + case PHY_INTERFACE_MODE_MII: + ge_mode = 1; + break; + case PHY_INTERFACE_MODE_REVMII: + ge_mode = 2; + break; + case PHY_INTERFACE_MODE_RMII: + if (mac->id) + goto err_phy; + ge_mode = 3; + break; + default: + break; + } + + /* put the gmac into the right mode */ + regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val); + val &= ~SYSCFG0_GE_MODE(SYSCFG0_GE_MASK, mac->id); + val |= SYSCFG0_GE_MODE(ge_mode, mac->id); + regmap_write(eth->ethsys, ETHSYS_SYSCFG0, val); + + mac->interface = state->interface; + } + + /* SGMII */ + if (state->interface == PHY_INTERFACE_MODE_SGMII || + phy_interface_mode_is_8023z(state->interface)) { + /* The path GMAC to SGMII will be enabled once the SGMIISYS is + * being setup done. + */ + regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val); + + regmap_update_bits(eth->ethsys, ETHSYS_SYSCFG0, + SYSCFG0_SGMII_MASK, + ~(u32)SYSCFG0_SGMII_MASK); + + /* Decide how GMAC and SGMIISYS be mapped */ + sid = (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_SGMII)) ? + 0 : mac->id; + + /* Setup SGMIISYS with the determined property */ + if (state->interface != PHY_INTERFACE_MODE_SGMII) + err = mtk_sgmii_setup_mode_force(eth->sgmii, sid, + state); + else if (phylink_autoneg_inband(mode)) + err = mtk_sgmii_setup_mode_an(eth->sgmii, sid); + + if (err) + goto init_err; + + regmap_update_bits(eth->ethsys, ETHSYS_SYSCFG0, + SYSCFG0_SGMII_MASK, val); + } else if (phylink_autoneg_inband(mode)) { + dev_err(eth->dev, + "In-band mode not supported in non SGMII mode!\n"); return; + } - switch (dev->phydev->speed) { + /* Setup gmac */ + mcr_cur = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); + mcr_new = mcr_cur; + mcr_new &= ~(MAC_MCR_SPEED_100 | MAC_MCR_SPEED_1000 | + MAC_MCR_FORCE_DPX | MAC_MCR_FORCE_TX_FC | + MAC_MCR_FORCE_RX_FC); + mcr_new |= MAC_MCR_MAX_RX_1536 | MAC_MCR_IPG_CFG | MAC_MCR_FORCE_MODE | + MAC_MCR_BACKOFF_EN | MAC_MCR_BACKPR_EN | MAC_MCR_FORCE_LINK; + + switch (state->speed) { + case SPEED_2500: case SPEED_1000: - mcr |= MAC_MCR_SPEED_1000; + mcr_new |= MAC_MCR_SPEED_1000; break; case SPEED_100: - mcr |= MAC_MCR_SPEED_100; + mcr_new |= MAC_MCR_SPEED_100; break; } - - if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_GMAC1_TRGMII) && !mac->id) { - if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_TRGMII_MT7621_CLK)) { - if (mt7621_gmac0_rgmii_adjust(mac->hw, - dev->phydev->interface)) - return; - } else { - if (!mac->trgmii) - mtk_gmac0_rgmii_adjust(mac->hw, - dev->phydev->speed); - } + if (state->duplex == DUPLEX_FULL) { + mcr_new |= MAC_MCR_FORCE_DPX; + if (state->pause & MLO_PAUSE_TX) + mcr_new |= MAC_MCR_FORCE_TX_FC; + if (state->pause & MLO_PAUSE_RX) + mcr_new |= MAC_MCR_FORCE_RX_FC; } - if (dev->phydev->link) - mcr |= MAC_MCR_FORCE_LINK; + /* Only update control register when needed! */ + if (mcr_new != mcr_cur) + mtk_w32(mac->hw, mcr_new, MTK_MAC_MCR(mac->id)); - if (dev->phydev->duplex) { - mcr |= MAC_MCR_FORCE_DPX; + return; - if (dev->phydev->pause) - rmt_adv = LPA_PAUSE_CAP; - if (dev->phydev->asym_pause) - rmt_adv |= LPA_PAUSE_ASYM; +err_phy: + dev_err(eth->dev, "%s: GMAC%d mode %s not supported!\n", __func__, + mac->id, phy_modes(state->interface)); + return; - lcl_adv = linkmode_adv_to_lcl_adv_t(dev->phydev->advertising); - flowctrl = mii_resolve_flowctrl_fdx(lcl_adv, rmt_adv); +init_err: + dev_err(eth->dev, "%s: GMAC%d mode %s err: %d!\n", __func__, + mac->id, phy_modes(state->interface), err); +} - if (flowctrl & FLOW_CTRL_TX) - mcr |= MAC_MCR_FORCE_TX_FC; - if (flowctrl & FLOW_CTRL_RX) - mcr |= MAC_MCR_FORCE_RX_FC; +static int mtk_mac_link_state(struct phylink_config *config, + struct phylink_link_state *state) +{ + struct mtk_mac *mac = container_of(config, struct mtk_mac, + phylink_config); + u32 pmsr = mtk_r32(mac->hw, MTK_MAC_MSR(mac->id)); - netif_dbg(mac->hw, link, dev, "rx pause %s, tx pause %s\n", - flowctrl & FLOW_CTRL_RX ? "enabled" : "disabled", - flowctrl & FLOW_CTRL_TX ? "enabled" : "disabled"); + state->link = (pmsr & MAC_MSR_LINK); + state->duplex = (pmsr & MAC_MSR_DPX) >> 1; + + switch (pmsr & (MAC_MSR_SPEED_1000 | MAC_MSR_SPEED_100)) { + case 0: + state->speed = SPEED_10; + break; + case MAC_MSR_SPEED_100: + state->speed = SPEED_100; + break; + case MAC_MSR_SPEED_1000: + state->speed = SPEED_1000; + break; + default: + state->speed = SPEED_UNKNOWN; + break; } - mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); + state->pause &= (MLO_PAUSE_RX | MLO_PAUSE_TX); + if (pmsr & MAC_MSR_RX_FC) + state->pause |= MLO_PAUSE_RX; + if (pmsr & MAC_MSR_TX_FC) + state->pause |= MLO_PAUSE_TX; - if (!of_phy_is_fixed_link(mac->of_node)) - phy_print_status(dev->phydev); + return 1; } -static int mtk_phy_connect_node(struct mtk_eth *eth, struct mtk_mac *mac, - struct device_node *phy_node) +static void mtk_mac_an_restart(struct phylink_config *config) { - struct phy_device *phydev; - int phy_mode; - - phy_mode = of_get_phy_mode(phy_node); - if (phy_mode < 0) { - dev_err(eth->dev, "incorrect phy-mode %d\n", phy_mode); - return -EINVAL; - } + struct mtk_mac *mac = container_of(config, struct mtk_mac, + phylink_config); - phydev = of_phy_connect(eth->netdev[mac->id], phy_node, - mtk_phy_link_adjust, 0, phy_mode); - if (!phydev) { - dev_err(eth->dev, "could not connect to PHY\n"); - return -ENODEV; - } + mtk_sgmii_restart_an(mac->hw, mac->id); +} - dev_info(eth->dev, - "connected mac %d to PHY at %s [uid=%08x, driver=%s]\n", - mac->id, phydev_name(phydev), phydev->phy_id, - phydev->drv->name); +static void mtk_mac_link_down(struct phylink_config *config, unsigned int mode, + phy_interface_t interface) +{ + struct mtk_mac *mac = container_of(config, struct mtk_mac, + phylink_config); + u32 mcr = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); - return 0; + mcr &= ~(MAC_MCR_TX_EN | MAC_MCR_RX_EN); + mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); } -static int mtk_phy_connect(struct net_device *dev) +static void mtk_mac_link_up(struct phylink_config *config, unsigned int mode, + phy_interface_t interface, + struct phy_device *phy) { - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth; - struct device_node *np; - u32 val; - int err; + struct mtk_mac *mac = container_of(config, struct mtk_mac, + phylink_config); + u32 mcr = mtk_r32(mac->hw, MTK_MAC_MCR(mac->id)); - eth = mac->hw; - np = of_parse_phandle(mac->of_node, "phy-handle", 0); - if (!np && of_phy_is_fixed_link(mac->of_node)) - if (!of_phy_register_fixed_link(mac->of_node)) - np = of_node_get(mac->of_node); - if (!np) - return -ENODEV; + mcr |= MAC_MCR_TX_EN | MAC_MCR_RX_EN; + mtk_w32(mac->hw, mcr, MTK_MAC_MCR(mac->id)); +} - err = mtk_setup_hw_path(eth, mac->id, of_get_phy_mode(np)); - if (err) - goto err_phy; +static void mtk_validate(struct phylink_config *config, + unsigned long *supported, + struct phylink_link_state *state) +{ + struct mtk_mac *mac = container_of(config, struct mtk_mac, + phylink_config); + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + + if (state->interface != PHY_INTERFACE_MODE_NA && + state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_GMII && + !(MTK_HAS_CAPS(mac->hw->soc->caps, MTK_RGMII) && + phy_interface_mode_is_rgmii(state->interface)) && + !(MTK_HAS_CAPS(mac->hw->soc->caps, MTK_TRGMII) && + !mac->id && state->interface == PHY_INTERFACE_MODE_TRGMII) && + !(MTK_HAS_CAPS(mac->hw->soc->caps, MTK_SGMII) && + (state->interface == PHY_INTERFACE_MODE_SGMII || + phy_interface_mode_is_8023z(state->interface)))) { + linkmode_zero(supported); + return; + } + + phylink_set_port_modes(mask); + phylink_set(mask, Autoneg); - mac->ge_mode = 0; - switch (of_get_phy_mode(np)) { + switch (state->interface) { case PHY_INTERFACE_MODE_TRGMII: - mac->trgmii = true; - case PHY_INTERFACE_MODE_RGMII_TXID: - case PHY_INTERFACE_MODE_RGMII_RXID: - case PHY_INTERFACE_MODE_RGMII_ID: + phylink_set(mask, 1000baseT_Full); + break; + case PHY_INTERFACE_MODE_1000BASEX: + case PHY_INTERFACE_MODE_2500BASEX: + phylink_set(mask, 1000baseX_Full); + phylink_set(mask, 2500baseX_Full); + break; + case PHY_INTERFACE_MODE_GMII: case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_TXID: + phylink_set(mask, 1000baseT_Half); + /* fall through */ case PHY_INTERFACE_MODE_SGMII: - break; + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseX_Full); + /* fall through */ case PHY_INTERFACE_MODE_MII: - case PHY_INTERFACE_MODE_GMII: - mac->ge_mode = 1; - break; - case PHY_INTERFACE_MODE_REVMII: - mac->ge_mode = 2; - break; case PHY_INTERFACE_MODE_RMII: - if (!mac->id) - goto err_phy; - mac->ge_mode = 3; - break; + case PHY_INTERFACE_MODE_REVMII: + case PHY_INTERFACE_MODE_NA: default: - goto err_phy; + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + break; } - /* put the gmac into the right mode */ - regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val); - val &= ~SYSCFG0_GE_MODE(SYSCFG0_GE_MASK, mac->id); - val |= SYSCFG0_GE_MODE(mac->ge_mode, mac->id); - regmap_write(eth->ethsys, ETHSYS_SYSCFG0, val); - - /* couple phydev to net_device */ - if (mtk_phy_connect_node(eth, mac, np)) - goto err_phy; + if (state->interface == PHY_INTERFACE_MODE_NA) { + if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_SGMII)) { + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseX_Full); + phylink_set(mask, 2500baseX_Full); + } + if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_RGMII)) { + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseT_Half); + phylink_set(mask, 1000baseX_Full); + } + if (MTK_HAS_CAPS(mac->hw->soc->caps, MTK_GEPHY)) { + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseT_Half); + } + } - of_node_put(np); + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); - return 0; + linkmode_and(supported, supported, mask); + linkmode_and(state->advertising, state->advertising, mask); -err_phy: - if (of_phy_is_fixed_link(mac->of_node)) - of_phy_deregister_fixed_link(mac->of_node); - of_node_put(np); - dev_err(eth->dev, "%s: invalid phy\n", __func__); - return -EINVAL; + /* We can only operate at 2500BaseX or 1000BaseX. If requested + * to advertise both, only report advertising at 2500BaseX. + */ + phylink_helper_basex_speed(state); } +static const struct phylink_mac_ops mtk_phylink_ops = { + .validate = mtk_validate, + .mac_link_state = mtk_mac_link_state, + .mac_an_restart = mtk_mac_an_restart, + .mac_config = mtk_mac_config, + .mac_link_down = mtk_mac_link_down, + .mac_link_up = mtk_mac_link_up, +}; + static int mtk_mdio_init(struct mtk_eth *eth) { struct device_node *mii_np; @@ -395,8 +570,8 @@ static inline void mtk_tx_irq_disable(struct mtk_eth *eth, u32 mask) u32 val; spin_lock_irqsave(ð->tx_irq_lock, flags); - val = mtk_r32(eth, MTK_QDMA_INT_MASK); - mtk_w32(eth, val & ~mask, MTK_QDMA_INT_MASK); + val = mtk_r32(eth, eth->tx_int_mask_reg); + mtk_w32(eth, val & ~mask, eth->tx_int_mask_reg); spin_unlock_irqrestore(ð->tx_irq_lock, flags); } @@ -406,8 +581,8 @@ static inline void mtk_tx_irq_enable(struct mtk_eth *eth, u32 mask) u32 val; spin_lock_irqsave(ð->tx_irq_lock, flags); - val = mtk_r32(eth, MTK_QDMA_INT_MASK); - mtk_w32(eth, val | mask, MTK_QDMA_INT_MASK); + val = mtk_r32(eth, eth->tx_int_mask_reg); + mtk_w32(eth, val | mask, eth->tx_int_mask_reg); spin_unlock_irqrestore(ð->tx_irq_lock, flags); } @@ -437,6 +612,7 @@ static int mtk_set_mac_address(struct net_device *dev, void *p) { int ret = eth_mac_addr(dev, p); struct mtk_mac *mac = netdev_priv(dev); + struct mtk_eth *eth = mac->hw; const char *macaddr = dev->dev_addr; if (ret) @@ -446,11 +622,19 @@ static int mtk_set_mac_address(struct net_device *dev, void *p) return -EBUSY; spin_lock_bh(&mac->hw->page_lock); - mtk_w32(mac->hw, (macaddr[0] << 8) | macaddr[1], - MTK_GDMA_MAC_ADRH(mac->id)); - mtk_w32(mac->hw, (macaddr[2] << 24) | (macaddr[3] << 16) | - (macaddr[4] << 8) | macaddr[5], - MTK_GDMA_MAC_ADRL(mac->id)); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + mtk_w32(mac->hw, (macaddr[0] << 8) | macaddr[1], + MT7628_SDM_MAC_ADRH); + mtk_w32(mac->hw, (macaddr[2] << 24) | (macaddr[3] << 16) | + (macaddr[4] << 8) | macaddr[5], + MT7628_SDM_MAC_ADRL); + } else { + mtk_w32(mac->hw, (macaddr[0] << 8) | macaddr[1], + MTK_GDMA_MAC_ADRH(mac->id)); + mtk_w32(mac->hw, (macaddr[2] << 24) | (macaddr[3] << 16) | + (macaddr[4] << 8) | macaddr[5], + MTK_GDMA_MAC_ADRL(mac->id)); + } spin_unlock_bh(&mac->hw->page_lock); return 0; @@ -626,19 +810,47 @@ static inline struct mtk_tx_buf *mtk_desc_to_tx_buf(struct mtk_tx_ring *ring, return &ring->buf[idx]; } +static struct mtk_tx_dma *qdma_to_pdma(struct mtk_tx_ring *ring, + struct mtk_tx_dma *dma) +{ + return ring->dma_pdma - ring->dma + dma; +} + +static int txd_to_idx(struct mtk_tx_ring *ring, struct mtk_tx_dma *dma) +{ + return ((void *)dma - (void *)ring->dma) / sizeof(*dma); +} + static void mtk_tx_unmap(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf) { - if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) { - dma_unmap_single(eth->dev, - dma_unmap_addr(tx_buf, dma_addr0), - dma_unmap_len(tx_buf, dma_len0), - DMA_TO_DEVICE); - } else if (tx_buf->flags & MTK_TX_FLAGS_PAGE0) { - dma_unmap_page(eth->dev, - dma_unmap_addr(tx_buf, dma_addr0), - dma_unmap_len(tx_buf, dma_len0), - DMA_TO_DEVICE); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + if (tx_buf->flags & MTK_TX_FLAGS_SINGLE0) { + dma_unmap_single(eth->dev, + dma_unmap_addr(tx_buf, dma_addr0), + dma_unmap_len(tx_buf, dma_len0), + DMA_TO_DEVICE); + } else if (tx_buf->flags & MTK_TX_FLAGS_PAGE0) { + dma_unmap_page(eth->dev, + dma_unmap_addr(tx_buf, dma_addr0), + dma_unmap_len(tx_buf, dma_len0), + DMA_TO_DEVICE); + } + } else { + if (dma_unmap_len(tx_buf, dma_len0)) { + dma_unmap_page(eth->dev, + dma_unmap_addr(tx_buf, dma_addr0), + dma_unmap_len(tx_buf, dma_len0), + DMA_TO_DEVICE); + } + + if (dma_unmap_len(tx_buf, dma_len1)) { + dma_unmap_page(eth->dev, + dma_unmap_addr(tx_buf, dma_addr1), + dma_unmap_len(tx_buf, dma_len1), + DMA_TO_DEVICE); + } } + tx_buf->flags = 0; if (tx_buf->skb && (tx_buf->skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC)) @@ -646,19 +858,45 @@ static void mtk_tx_unmap(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf) tx_buf->skb = NULL; } +static void setup_tx_buf(struct mtk_eth *eth, struct mtk_tx_buf *tx_buf, + struct mtk_tx_dma *txd, dma_addr_t mapped_addr, + size_t size, int idx) +{ + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); + dma_unmap_len_set(tx_buf, dma_len0, size); + } else { + if (idx & 1) { + txd->txd3 = mapped_addr; + txd->txd2 |= TX_DMA_PLEN1(size); + dma_unmap_addr_set(tx_buf, dma_addr1, mapped_addr); + dma_unmap_len_set(tx_buf, dma_len1, size); + } else { + tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC; + txd->txd1 = mapped_addr; + txd->txd2 = TX_DMA_PLEN0(size); + dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); + dma_unmap_len_set(tx_buf, dma_len0, size); + } + } +} + static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, int tx_num, struct mtk_tx_ring *ring, bool gso) { struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; struct mtk_tx_dma *itxd, *txd; + struct mtk_tx_dma *itxd_pdma, *txd_pdma; struct mtk_tx_buf *itx_buf, *tx_buf; dma_addr_t mapped_addr; unsigned int nr_frags; int i, n_desc = 1; u32 txd4 = 0, fport; + int k = 0; itxd = ring->next_free; + itxd_pdma = qdma_to_pdma(ring, itxd); if (itxd == ring->last_free) return -ENOMEM; @@ -689,26 +927,37 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, itx_buf->flags |= MTK_TX_FLAGS_SINGLE0; itx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 : MTK_TX_FLAGS_FPORT1; - dma_unmap_addr_set(itx_buf, dma_addr0, mapped_addr); - dma_unmap_len_set(itx_buf, dma_len0, skb_headlen(skb)); + setup_tx_buf(eth, itx_buf, itxd_pdma, mapped_addr, skb_headlen(skb), + k++); /* TX SG offload */ txd = itxd; + txd_pdma = qdma_to_pdma(ring, txd); nr_frags = skb_shinfo(skb)->nr_frags; + for (i = 0; i < nr_frags; i++) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; unsigned int offset = 0; int frag_size = skb_frag_size(frag); while (frag_size) { bool last_frag = false; unsigned int frag_map_size; + bool new_desc = true; + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA) || + (i & 0x1)) { + txd = mtk_qdma_phys_to_virt(ring, txd->txd2); + txd_pdma = qdma_to_pdma(ring, txd); + if (txd == ring->last_free) + goto err_dma; + + n_desc++; + } else { + new_desc = false; + } - txd = mtk_qdma_phys_to_virt(ring, txd->txd2); - if (txd == ring->last_free) - goto err_dma; - n_desc++; frag_map_size = min(frag_size, MTK_TX_DMA_BUF_LEN); mapped_addr = skb_frag_dma_map(eth->dev, frag, offset, frag_map_size, @@ -727,14 +976,16 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, WRITE_ONCE(txd->txd4, fport); tx_buf = mtk_desc_to_tx_buf(ring, txd); - memset(tx_buf, 0, sizeof(*tx_buf)); + if (new_desc) + memset(tx_buf, 0, sizeof(*tx_buf)); tx_buf->skb = (struct sk_buff *)MTK_DMA_DUMMY_DESC; tx_buf->flags |= MTK_TX_FLAGS_PAGE0; tx_buf->flags |= (!mac->id) ? MTK_TX_FLAGS_FPORT0 : MTK_TX_FLAGS_FPORT1; - dma_unmap_addr_set(tx_buf, dma_addr0, mapped_addr); - dma_unmap_len_set(tx_buf, dma_len0, frag_map_size); + setup_tx_buf(eth, tx_buf, txd_pdma, mapped_addr, + frag_map_size, k++); + frag_size -= frag_map_size; offset += frag_map_size; } @@ -746,6 +997,12 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, WRITE_ONCE(itxd->txd4, txd4); WRITE_ONCE(itxd->txd3, (TX_DMA_SWC | TX_DMA_PLEN0(skb_headlen(skb)) | (!nr_frags * TX_DMA_LS0))); + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + if (k & 0x1) + txd_pdma->txd2 |= TX_DMA_LS0; + else + txd_pdma->txd2 |= TX_DMA_LS1; + } netdev_sent_queue(dev, skb->len); skb_tx_timestamp(skb); @@ -758,9 +1015,15 @@ static int mtk_tx_map(struct sk_buff *skb, struct net_device *dev, */ wmb(); - if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || - !netdev_xmit_more()) - mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + if (netif_xmit_stopped(netdev_get_tx_queue(dev, 0)) || + !netdev_xmit_more()) + mtk_w32(eth, txd->txd2, MTK_QTX_CTX_PTR); + } else { + int next_idx = NEXT_DESP_IDX(txd_to_idx(ring, txd), + ring->dma_size); + mtk_w32(eth, next_idx, MT7628_TX_CTX_IDX0); + } return 0; @@ -772,7 +1035,11 @@ err_dma: mtk_tx_unmap(eth, tx_buf); itxd->txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU; + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + itxd_pdma->txd2 = TX_DMA_DESP2_DEF; + itxd = mtk_qdma_phys_to_virt(ring, itxd->txd2); + itxd_pdma = qdma_to_pdma(ring, itxd); } while (itxd != txd); return -ENOMEM; @@ -781,13 +1048,14 @@ err_dma: static inline int mtk_cal_txd_req(struct sk_buff *skb) { int i, nfrags; - struct skb_frag_struct *frag; + skb_frag_t *frag; nfrags = 1; if (skb_is_gso(skb)) { for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { frag = &skb_shinfo(skb)->frags[i]; - nfrags += DIV_ROUND_UP(frag->size, MTK_TX_DMA_BUF_LEN); + nfrags += DIV_ROUND_UP(skb_frag_size(frag), + MTK_TX_DMA_BUF_LEN); } } else { nfrags += skb_shinfo(skb)->nr_frags; @@ -902,7 +1170,7 @@ static struct mtk_rx_ring *mtk_get_rx_ring(struct mtk_eth *eth) for (i = 0; i < MTK_MAX_RX_RING_NUM; i++) { ring = ð->rx_ring[i]; - idx = NEXT_RX_DESP_IDX(ring->calc_idx, ring->dma_size); + idx = NEXT_DESP_IDX(ring->calc_idx, ring->dma_size); if (ring->dma[idx].rxd2 & RX_DMA_DONE) { ring->calc_idx_update = true; return ring; @@ -945,13 +1213,13 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, struct net_device *netdev; unsigned int pktlen; dma_addr_t dma_addr; - int mac = 0; + int mac; ring = mtk_get_rx_ring(eth); if (unlikely(!ring)) goto rx_done; - idx = NEXT_RX_DESP_IDX(ring->calc_idx, ring->dma_size); + idx = NEXT_DESP_IDX(ring->calc_idx, ring->dma_size); rxd = &ring->dma[idx]; data = ring->data[idx]; @@ -960,9 +1228,13 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, break; /* find out which mac the packet come from. values start at 1 */ - mac = (trxd.rxd4 >> RX_DMA_FPORT_SHIFT) & - RX_DMA_FPORT_MASK; - mac--; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + mac = 0; + } else { + mac = (trxd.rxd4 >> RX_DMA_FPORT_SHIFT) & + RX_DMA_FPORT_MASK; + mac--; + } if (unlikely(mac < 0 || mac >= MTK_MAC_COUNT || !eth->netdev[mac])) @@ -980,7 +1252,8 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, goto release_desc; } dma_addr = dma_map_single(eth->dev, - new_data + NET_SKB_PAD, + new_data + NET_SKB_PAD + + eth->ip_align, ring->buf_size, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(eth->dev, dma_addr))) { @@ -1003,7 +1276,7 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, pktlen = RX_DMA_GET_PLEN0(trxd.rxd2); skb->dev = netdev; skb_put(skb, pktlen); - if (trxd.rxd4 & RX_DMA_L4_VALID) + if (trxd.rxd4 & eth->rx_dma_l4_valid) skb->ip_summed = CHECKSUM_UNNECESSARY; else skb_checksum_none_assert(skb); @@ -1020,7 +1293,10 @@ static int mtk_poll_rx(struct napi_struct *napi, int budget, rxd->rxd1 = (unsigned int)dma_addr; release_desc: - rxd->rxd2 = RX_DMA_PLEN0(ring->buf_size); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) + rxd->rxd2 = RX_DMA_LSO; + else + rxd->rxd2 = RX_DMA_PLEN0(ring->buf_size); ring->calc_idx = idx; @@ -1039,19 +1315,14 @@ rx_done: return done; } -static int mtk_poll_tx(struct mtk_eth *eth, int budget) +static int mtk_poll_tx_qdma(struct mtk_eth *eth, int budget, + unsigned int *done, unsigned int *bytes) { struct mtk_tx_ring *ring = ð->tx_ring; struct mtk_tx_dma *desc; struct sk_buff *skb; struct mtk_tx_buf *tx_buf; - unsigned int done[MTK_MAX_DEVS]; - unsigned int bytes[MTK_MAX_DEVS]; u32 cpu, dma; - int total = 0, i; - - memset(done, 0, sizeof(done)); - memset(bytes, 0, sizeof(bytes)); cpu = mtk_r32(eth, MTK_QTX_CRX_PTR); dma = mtk_r32(eth, MTK_QTX_DRX_PTR); @@ -1089,6 +1360,62 @@ static int mtk_poll_tx(struct mtk_eth *eth, int budget) mtk_w32(eth, cpu, MTK_QTX_CRX_PTR); + return budget; +} + +static int mtk_poll_tx_pdma(struct mtk_eth *eth, int budget, + unsigned int *done, unsigned int *bytes) +{ + struct mtk_tx_ring *ring = ð->tx_ring; + struct mtk_tx_dma *desc; + struct sk_buff *skb; + struct mtk_tx_buf *tx_buf; + u32 cpu, dma; + + cpu = ring->cpu_idx; + dma = mtk_r32(eth, MT7628_TX_DTX_IDX0); + + while ((cpu != dma) && budget) { + tx_buf = &ring->buf[cpu]; + skb = tx_buf->skb; + if (!skb) + break; + + if (skb != (struct sk_buff *)MTK_DMA_DUMMY_DESC) { + bytes[0] += skb->len; + done[0]++; + budget--; + } + + mtk_tx_unmap(eth, tx_buf); + + desc = &ring->dma[cpu]; + ring->last_free = desc; + atomic_inc(&ring->free_count); + + cpu = NEXT_DESP_IDX(cpu, ring->dma_size); + } + + ring->cpu_idx = cpu; + + return budget; +} + +static int mtk_poll_tx(struct mtk_eth *eth, int budget) +{ + struct mtk_tx_ring *ring = ð->tx_ring; + unsigned int done[MTK_MAX_DEVS]; + unsigned int bytes[MTK_MAX_DEVS]; + int total = 0, i; + + memset(done, 0, sizeof(done)); + memset(bytes, 0, sizeof(bytes)); + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + budget = mtk_poll_tx_qdma(eth, budget, done, bytes); + else + budget = mtk_poll_tx_pdma(eth, budget, done, bytes); + for (i = 0; i < MTK_MAC_COUNT; i++) { if (!eth->netdev[i] || !done[i]) continue; @@ -1120,13 +1447,14 @@ static int mtk_napi_tx(struct napi_struct *napi, int budget) u32 status, mask; int tx_done = 0; - mtk_handle_status_irq(eth); - mtk_w32(eth, MTK_TX_DONE_INT, MTK_QMTK_INT_STATUS); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + mtk_handle_status_irq(eth); + mtk_w32(eth, MTK_TX_DONE_INT, eth->tx_int_status_reg); tx_done = mtk_poll_tx(eth, budget); if (unlikely(netif_msg_intr(eth))) { - status = mtk_r32(eth, MTK_QMTK_INT_STATUS); - mask = mtk_r32(eth, MTK_QDMA_INT_MASK); + status = mtk_r32(eth, eth->tx_int_status_reg); + mask = mtk_r32(eth, eth->tx_int_mask_reg); dev_info(eth->dev, "done tx %d, intr 0x%08x/0x%x\n", tx_done, status, mask); @@ -1135,7 +1463,7 @@ static int mtk_napi_tx(struct napi_struct *napi, int budget) if (tx_done == budget) return budget; - status = mtk_r32(eth, MTK_QMTK_INT_STATUS); + status = mtk_r32(eth, eth->tx_int_status_reg); if (status & MTK_TX_DONE_INT) return budget; @@ -1202,6 +1530,24 @@ static int mtk_tx_alloc(struct mtk_eth *eth) ring->dma[i].txd3 = TX_DMA_LS0 | TX_DMA_OWNER_CPU; } + /* On MT7688 (PDMA only) this driver uses the ring->dma structs + * only as the framework. The real HW descriptors are the PDMA + * descriptors in ring->dma_pdma. + */ + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + ring->dma_pdma = dma_alloc_coherent(eth->dev, MTK_DMA_SIZE * sz, + &ring->phys_pdma, + GFP_ATOMIC); + if (!ring->dma_pdma) + goto no_tx_mem; + + for (i = 0; i < MTK_DMA_SIZE; i++) { + ring->dma_pdma[i].txd2 = TX_DMA_DESP2_DEF; + ring->dma_pdma[i].txd4 = 0; + } + } + + ring->dma_size = MTK_DMA_SIZE; atomic_set(&ring->free_count, MTK_DMA_SIZE - 2); ring->next_free = &ring->dma[0]; ring->last_free = &ring->dma[MTK_DMA_SIZE - 1]; @@ -1212,15 +1558,23 @@ static int mtk_tx_alloc(struct mtk_eth *eth) */ wmb(); - mtk_w32(eth, ring->phys, MTK_QTX_CTX_PTR); - mtk_w32(eth, ring->phys, MTK_QTX_DTX_PTR); - mtk_w32(eth, - ring->phys + ((MTK_DMA_SIZE - 1) * sz), - MTK_QTX_CRX_PTR); - mtk_w32(eth, - ring->phys + ((MTK_DMA_SIZE - 1) * sz), - MTK_QTX_DRX_PTR); - mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES, MTK_QTX_CFG(0)); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + mtk_w32(eth, ring->phys, MTK_QTX_CTX_PTR); + mtk_w32(eth, ring->phys, MTK_QTX_DTX_PTR); + mtk_w32(eth, + ring->phys + ((MTK_DMA_SIZE - 1) * sz), + MTK_QTX_CRX_PTR); + mtk_w32(eth, + ring->phys + ((MTK_DMA_SIZE - 1) * sz), + MTK_QTX_DRX_PTR); + mtk_w32(eth, (QDMA_RES_THRES << 8) | QDMA_RES_THRES, + MTK_QTX_CFG(0)); + } else { + mtk_w32(eth, ring->phys_pdma, MT7628_TX_BASE_PTR0); + mtk_w32(eth, MTK_DMA_SIZE, MT7628_TX_MAX_CNT0); + mtk_w32(eth, 0, MT7628_TX_CTX_IDX0); + mtk_w32(eth, MT7628_PST_DTX_IDX0, MTK_PDMA_RST_IDX); + } return 0; @@ -1247,6 +1601,14 @@ static void mtk_tx_clean(struct mtk_eth *eth) ring->phys); ring->dma = NULL; } + + if (ring->dma_pdma) { + dma_free_coherent(eth->dev, + MTK_DMA_SIZE * sizeof(*ring->dma_pdma), + ring->dma_pdma, + ring->phys_pdma); + ring->dma_pdma = NULL; + } } static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) @@ -1294,14 +1656,17 @@ static int mtk_rx_alloc(struct mtk_eth *eth, int ring_no, int rx_flag) for (i = 0; i < rx_dma_size; i++) { dma_addr_t dma_addr = dma_map_single(eth->dev, - ring->data[i] + NET_SKB_PAD, + ring->data[i] + NET_SKB_PAD + eth->ip_align, ring->buf_size, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(eth->dev, dma_addr))) return -ENOMEM; ring->dma[i].rxd1 = (unsigned int)dma_addr; - ring->dma[i].rxd2 = RX_DMA_PLEN0(ring->buf_size); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) + ring->dma[i].rxd2 = RX_DMA_LSO; + else + ring->dma[i].rxd2 = RX_DMA_PLEN0(ring->buf_size); } ring->dma_size = rx_dma_size; ring->calc_idx_update = false; @@ -1617,9 +1982,16 @@ static int mtk_dma_busy_wait(struct mtk_eth *eth) unsigned long t_start = jiffies; while (1) { - if (!(mtk_r32(eth, MTK_QDMA_GLO_CFG) & - (MTK_RX_DMA_BUSY | MTK_TX_DMA_BUSY))) - return 0; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + if (!(mtk_r32(eth, MTK_QDMA_GLO_CFG) & + (MTK_RX_DMA_BUSY | MTK_TX_DMA_BUSY))) + return 0; + } else { + if (!(mtk_r32(eth, MTK_PDMA_GLO_CFG) & + (MTK_RX_DMA_BUSY | MTK_TX_DMA_BUSY))) + return 0; + } + if (time_after(jiffies, t_start + MTK_DMA_BUSY_TIMEOUT)) break; } @@ -1636,20 +2008,24 @@ static int mtk_dma_init(struct mtk_eth *eth) if (mtk_dma_busy_wait(eth)) return -EBUSY; - /* QDMA needs scratch memory for internal reordering of the - * descriptors - */ - err = mtk_init_fq_dma(eth); - if (err) - return err; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + /* QDMA needs scratch memory for internal reordering of the + * descriptors + */ + err = mtk_init_fq_dma(eth); + if (err) + return err; + } err = mtk_tx_alloc(eth); if (err) return err; - err = mtk_rx_alloc(eth, 0, MTK_RX_FLAGS_QDMA); - if (err) - return err; + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + err = mtk_rx_alloc(eth, 0, MTK_RX_FLAGS_QDMA); + if (err) + return err; + } err = mtk_rx_alloc(eth, 0, MTK_RX_FLAGS_NORMAL); if (err) @@ -1666,10 +2042,14 @@ static int mtk_dma_init(struct mtk_eth *eth) return err; } - /* Enable random early drop and set drop threshold automatically */ - mtk_w32(eth, FC_THRES_DROP_MODE | FC_THRES_DROP_EN | FC_THRES_MIN, - MTK_QDMA_FC_THRES); - mtk_w32(eth, 0x0, MTK_QDMA_HRED2); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + /* Enable random early drop and set drop threshold + * automatically + */ + mtk_w32(eth, FC_THRES_DROP_MODE | FC_THRES_DROP_EN | + FC_THRES_MIN, MTK_QDMA_FC_THRES); + mtk_w32(eth, 0x0, MTK_QDMA_HRED2); + } return 0; } @@ -1745,8 +2125,8 @@ static irqreturn_t mtk_handle_irq(int irq, void *_eth) if (mtk_r32(eth, MTK_PDMA_INT_STATUS) & MTK_RX_DONE_INT) mtk_handle_irq_rx(irq, _eth); } - if (mtk_r32(eth, MTK_QDMA_INT_MASK) & MTK_TX_DONE_INT) { - if (mtk_r32(eth, MTK_QMTK_INT_STATUS) & MTK_TX_DONE_INT) + if (mtk_r32(eth, eth->tx_int_mask_reg) & MTK_TX_DONE_INT) { + if (mtk_r32(eth, eth->tx_int_status_reg) & MTK_TX_DONE_INT) mtk_handle_irq_tx(irq, _eth); } @@ -1778,17 +2158,23 @@ static int mtk_start_dma(struct mtk_eth *eth) return err; } - mtk_w32(eth, - MTK_TX_WB_DDONE | MTK_TX_DMA_EN | - MTK_DMA_SIZE_16DWORDS | MTK_NDP_CO_PRO | - MTK_RX_DMA_EN | MTK_RX_2B_OFFSET | - MTK_RX_BT_32DWORDS, - MTK_QDMA_GLO_CFG); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + mtk_w32(eth, + MTK_TX_WB_DDONE | MTK_TX_DMA_EN | + MTK_DMA_SIZE_16DWORDS | MTK_NDP_CO_PRO | + MTK_RX_DMA_EN | MTK_RX_2B_OFFSET | + MTK_RX_BT_32DWORDS, + MTK_QDMA_GLO_CFG); - mtk_w32(eth, - MTK_RX_DMA_EN | rx_2b_offset | - MTK_RX_BT_32DWORDS | MTK_MULTI_EN, - MTK_PDMA_GLO_CFG); + mtk_w32(eth, + MTK_RX_DMA_EN | rx_2b_offset | + MTK_RX_BT_32DWORDS | MTK_MULTI_EN, + MTK_PDMA_GLO_CFG); + } else { + mtk_w32(eth, MTK_TX_WB_DDONE | MTK_TX_DMA_EN | MTK_RX_DMA_EN | + MTK_MULTI_EN | MTK_PDMA_SIZE_8DWORDS, + MTK_PDMA_GLO_CFG); + } return 0; } @@ -1797,6 +2183,14 @@ static int mtk_open(struct net_device *dev) { struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; + int err; + + err = phylink_of_phy_connect(mac->phylink, mac->of_node, 0); + if (err) { + netdev_err(dev, "%s: could not attach PHY: %d\n", __func__, + err); + return err; + } /* we run 2 netdevs on the same dma ring so we only bring it up once */ if (!refcount_read(ð->dma_refcnt)) { @@ -1814,9 +2208,8 @@ static int mtk_open(struct net_device *dev) else refcount_inc(ð->dma_refcnt); - phy_start(dev->phydev); + phylink_start(mac->phylink); netif_start_queue(dev); - return 0; } @@ -1848,8 +2241,11 @@ static int mtk_stop(struct net_device *dev) struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; + phylink_stop(mac->phylink); + netif_tx_disable(dev); - phy_stop(dev->phydev); + + phylink_disconnect_phy(mac->phylink); /* only shutdown DMA if this is the last user */ if (!refcount_dec_and_test(ð->dma_refcnt)) @@ -1860,7 +2256,8 @@ static int mtk_stop(struct net_device *dev) napi_disable(ð->tx_napi); napi_disable(ð->rx_napi); - mtk_stop_dma(eth, MTK_QDMA_GLO_CFG); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) + mtk_stop_dma(eth, MTK_QDMA_GLO_CFG); mtk_stop_dma(eth, MTK_PDMA_GLO_CFG); mtk_dma_free(eth); @@ -1922,17 +2319,26 @@ static int mtk_hw_init(struct mtk_eth *eth) if (ret) goto err_disable_pm; - ethsys_reset(eth, RSTCTRL_FE); - ethsys_reset(eth, RSTCTRL_PPE); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + ret = device_reset(eth->dev); + if (ret) { + dev_err(eth->dev, "MAC reset failed!\n"); + goto err_disable_pm; + } - regmap_read(eth->ethsys, ETHSYS_SYSCFG0, &val); - for (i = 0; i < MTK_MAC_COUNT; i++) { - if (!eth->mac[i]) - continue; - val &= ~SYSCFG0_GE_MODE(SYSCFG0_GE_MASK, eth->mac[i]->id); - val |= SYSCFG0_GE_MODE(eth->mac[i]->ge_mode, eth->mac[i]->id); + /* enable interrupt delay for RX */ + mtk_w32(eth, MTK_PDMA_DELAY_RX_DELAY, MTK_PDMA_DELAY_INT); + + /* disable delay and normal interrupt */ + mtk_tx_irq_disable(eth, ~0); + mtk_rx_irq_disable(eth, ~0); + + return 0; } - regmap_write(eth->ethsys, ETHSYS_SYSCFG0, val); + + /* Non-MT7628 handling... */ + ethsys_reset(eth, RSTCTRL_FE); + ethsys_reset(eth, RSTCTRL_PPE); if (eth->pctl) { /* Set GE2 driving and slew rate */ @@ -1946,11 +2352,11 @@ static int mtk_hw_init(struct mtk_eth *eth) } /* Set linkdown as the default for each GMAC. Its own MCR would be set - * up with the more appropriate value when mtk_phy_link_adjust call is - * being invoked. + * up with the more appropriate value when mtk_mac_config call is being + * invoked. */ for (i = 0; i < MTK_MAC_COUNT; i++) - mtk_w32(eth, 0, MTK_MAC_MCR(i)); + mtk_w32(eth, MAC_MCR_FORCE_LINK_DOWN, MTK_MAC_MCR(i)); /* Indicates CDM to parse the MTK special tag from CPU * which also is working out for untag packets. @@ -1978,7 +2384,7 @@ static int mtk_hw_init(struct mtk_eth *eth) mtk_w32(eth, MTK_RX_DONE_INT, MTK_QDMA_INT_GRP2); mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP); - for (i = 0; i < 2; i++) { + for (i = 0; i < MTK_MAC_COUNT; i++) { u32 val = mtk_r32(eth, MTK_GDMA_FWD_CFG(i)); /* setup the forward port to send frame to PDMA */ @@ -2030,7 +2436,7 @@ static int __init mtk_init(struct net_device *dev) dev->dev_addr); } - return mtk_phy_connect(dev); + return 0; } static void mtk_uninit(struct net_device *dev) @@ -2038,20 +2444,20 @@ static void mtk_uninit(struct net_device *dev) struct mtk_mac *mac = netdev_priv(dev); struct mtk_eth *eth = mac->hw; - phy_disconnect(dev->phydev); - if (of_phy_is_fixed_link(mac->of_node)) - of_phy_deregister_fixed_link(mac->of_node); + phylink_disconnect_phy(mac->phylink); mtk_tx_irq_disable(eth, ~0); mtk_rx_irq_disable(eth, ~0); } static int mtk_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { + struct mtk_mac *mac = netdev_priv(dev); + switch (cmd) { case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: - return phy_mii_ioctl(dev->phydev, ifr, cmd); + return phylink_mii_ioctl(mac->phylink, ifr, cmd); default: break; } @@ -2092,16 +2498,6 @@ static void mtk_pending_work(struct work_struct *work) eth->dev->pins->default_state); mtk_hw_init(eth); - for (i = 0; i < MTK_MAC_COUNT; i++) { - if (!eth->mac[i] || - of_phy_is_fixed_link(eth->mac[i]->of_node)) - continue; - err = phy_init_hw(eth->netdev[i]->phydev); - if (err) - dev_err(eth->dev, "%s: PHY init failed.\n", - eth->netdev[i]->name); - } - /* restart DMA and enable IRQs */ for (i = 0; i < MTK_MAC_COUNT; i++) { if (!test_bit(i, &restart)) @@ -2164,9 +2560,7 @@ static int mtk_get_link_ksettings(struct net_device *ndev, if (unlikely(test_bit(MTK_RESETTING, &mac->hw->state))) return -EBUSY; - phy_ethtool_ksettings_get(ndev->phydev, cmd); - - return 0; + return phylink_ethtool_ksettings_get(mac->phylink, cmd); } static int mtk_set_link_ksettings(struct net_device *ndev, @@ -2177,7 +2571,7 @@ static int mtk_set_link_ksettings(struct net_device *ndev, if (unlikely(test_bit(MTK_RESETTING, &mac->hw->state))) return -EBUSY; - return phy_ethtool_ksettings_set(ndev->phydev, cmd); + return phylink_ethtool_ksettings_set(mac->phylink, cmd); } static void mtk_get_drvinfo(struct net_device *dev, @@ -2211,22 +2605,10 @@ static int mtk_nway_reset(struct net_device *dev) if (unlikely(test_bit(MTK_RESETTING, &mac->hw->state))) return -EBUSY; - return genphy_restart_aneg(dev->phydev); -} + if (!mac->phylink) + return -ENOTSUPP; -static u32 mtk_get_link(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - int err; - - if (unlikely(test_bit(MTK_RESETTING, &mac->hw->state))) - return -EBUSY; - - err = genphy_update_link(dev->phydev); - if (err) - return ethtool_op_get_link(dev); - - return dev->phydev->link; + return phylink_ethtool_nway_reset(mac->phylink); } static void mtk_get_strings(struct net_device *dev, u32 stringset, u8 *data) @@ -2346,7 +2728,7 @@ static const struct ethtool_ops mtk_ethtool_ops = { .get_msglevel = mtk_get_msglevel, .set_msglevel = mtk_set_msglevel, .nway_reset = mtk_nway_reset, - .get_link = mtk_get_link, + .get_link = ethtool_op_get_link, .get_strings = mtk_get_strings, .get_sset_count = mtk_get_sset_count, .get_ethtool_stats = mtk_get_ethtool_stats, @@ -2374,9 +2756,10 @@ static const struct net_device_ops mtk_netdev_ops = { static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) { - struct mtk_mac *mac; const __be32 *_id = of_get_property(np, "reg", NULL); - int id, err; + struct phylink *phylink; + int phy_mode, id, err; + struct mtk_mac *mac; if (!_id) { dev_err(eth->dev, "missing mac id\n"); @@ -2420,18 +2803,44 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) u64_stats_init(&mac->hw_stats->syncp); mac->hw_stats->reg_offset = id * MTK_STAT_OFFSET; + /* phylink create */ + phy_mode = of_get_phy_mode(np); + if (phy_mode < 0) { + dev_err(eth->dev, "incorrect phy-mode\n"); + err = -EINVAL; + goto free_netdev; + } + + /* mac config is not set */ + mac->interface = PHY_INTERFACE_MODE_NA; + mac->mode = MLO_AN_PHY; + mac->speed = SPEED_UNKNOWN; + + mac->phylink_config.dev = ð->netdev[id]->dev; + mac->phylink_config.type = PHYLINK_NETDEV; + + phylink = phylink_create(&mac->phylink_config, + of_fwnode_handle(mac->of_node), + phy_mode, &mtk_phylink_ops); + if (IS_ERR(phylink)) { + err = PTR_ERR(phylink); + goto free_netdev; + } + + mac->phylink = phylink; + SET_NETDEV_DEV(eth->netdev[id], eth->dev); eth->netdev[id]->watchdog_timeo = 5 * HZ; eth->netdev[id]->netdev_ops = &mtk_netdev_ops; eth->netdev[id]->base_addr = (unsigned long)eth->base; - eth->netdev[id]->hw_features = MTK_HW_FEATURES; + eth->netdev[id]->hw_features = eth->soc->hw_features; if (eth->hwlro) eth->netdev[id]->hw_features |= NETIF_F_LRO; - eth->netdev[id]->vlan_features = MTK_HW_FEATURES & + eth->netdev[id]->vlan_features = eth->soc->hw_features & ~(NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX); - eth->netdev[id]->features |= MTK_HW_FEATURES; + eth->netdev[id]->features |= eth->soc->hw_features; eth->netdev[id]->ethtool_ops = &mtk_ethtool_ops; eth->netdev[id]->irq = eth->irq[0]; @@ -2446,11 +2855,9 @@ free_netdev: static int mtk_probe(struct platform_device *pdev) { - struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); struct device_node *mac_np; struct mtk_eth *eth; - int err; - int i; + int err, i; eth = devm_kzalloc(&pdev->dev, sizeof(*eth), GFP_KERNEL); if (!eth) @@ -2459,19 +2866,36 @@ static int mtk_probe(struct platform_device *pdev) eth->soc = of_device_get_match_data(&pdev->dev); eth->dev = &pdev->dev; - eth->base = devm_ioremap_resource(&pdev->dev, res); + eth->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(eth->base)) return PTR_ERR(eth->base); + if (MTK_HAS_CAPS(eth->soc->caps, MTK_QDMA)) { + eth->tx_int_mask_reg = MTK_QDMA_INT_MASK; + eth->tx_int_status_reg = MTK_QDMA_INT_STATUS; + } else { + eth->tx_int_mask_reg = MTK_PDMA_INT_MASK; + eth->tx_int_status_reg = MTK_PDMA_INT_STATUS; + } + + if (MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + eth->rx_dma_l4_valid = RX_DMA_L4_VALID_PDMA; + eth->ip_align = NET_IP_ALIGN; + } else { + eth->rx_dma_l4_valid = RX_DMA_L4_VALID; + } + spin_lock_init(ð->page_lock); spin_lock_init(ð->tx_irq_lock); spin_lock_init(ð->rx_irq_lock); - eth->ethsys = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, - "mediatek,ethsys"); - if (IS_ERR(eth->ethsys)) { - dev_err(&pdev->dev, "no ethsys regmap found\n"); - return PTR_ERR(eth->ethsys); + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + eth->ethsys = syscon_regmap_lookup_by_phandle(pdev->dev.of_node, + "mediatek,ethsys"); + if (IS_ERR(eth->ethsys)) { + dev_err(&pdev->dev, "no ethsys regmap found\n"); + return PTR_ERR(eth->ethsys); + } } if (MTK_HAS_CAPS(eth->soc->caps, MTK_INFRA)) { @@ -2572,9 +2996,12 @@ static int mtk_probe(struct platform_device *pdev) if (err) goto err_free_dev; - err = mtk_mdio_init(eth); - if (err) - goto err_free_dev; + /* No MT7628/88 support yet */ + if (!MTK_HAS_CAPS(eth->soc->caps, MTK_SOC_MT7628)) { + err = mtk_mdio_init(eth); + if (err) + goto err_free_dev; + } for (i = 0; i < MTK_MAX_DEVS; i++) { if (!eth->netdev[i]) @@ -2616,6 +3043,7 @@ err_deinit_hw: static int mtk_remove(struct platform_device *pdev) { struct mtk_eth *eth = platform_get_drvdata(pdev); + struct mtk_mac *mac; int i; /* stop all devices to make sure that dma is properly shut down */ @@ -2623,6 +3051,8 @@ static int mtk_remove(struct platform_device *pdev) if (!eth->netdev[i]) continue; mtk_stop(eth->netdev[i]); + mac = netdev_priv(eth->netdev[i]); + phylink_disconnect_phy(mac->phylink); } mtk_hw_deinit(eth); @@ -2637,12 +3067,14 @@ static int mtk_remove(struct platform_device *pdev) static const struct mtk_soc_data mt2701_data = { .caps = MT7623_CAPS | MTK_HWLRO, + .hw_features = MTK_HW_FEATURES, .required_clks = MT7623_CLKS_BITMAP, .required_pctl = true, }; static const struct mtk_soc_data mt7621_data = { .caps = MT7621_CAPS, + .hw_features = MTK_HW_FEATURES, .required_clks = MT7621_CLKS_BITMAP, .required_pctl = false, }; @@ -2650,12 +3082,14 @@ static const struct mtk_soc_data mt7621_data = { static const struct mtk_soc_data mt7622_data = { .ana_rgc3 = 0x2028, .caps = MT7622_CAPS | MTK_HWLRO, + .hw_features = MTK_HW_FEATURES, .required_clks = MT7622_CLKS_BITMAP, .required_pctl = false, }; static const struct mtk_soc_data mt7623_data = { .caps = MT7623_CAPS | MTK_HWLRO, + .hw_features = MTK_HW_FEATURES, .required_clks = MT7623_CLKS_BITMAP, .required_pctl = true, }; @@ -2663,16 +3097,25 @@ static const struct mtk_soc_data mt7623_data = { static const struct mtk_soc_data mt7629_data = { .ana_rgc3 = 0x128, .caps = MT7629_CAPS | MTK_HWLRO, + .hw_features = MTK_HW_FEATURES, .required_clks = MT7629_CLKS_BITMAP, .required_pctl = false, }; +static const struct mtk_soc_data rt5350_data = { + .caps = MT7628_CAPS, + .hw_features = MTK_HW_FEATURES_MT7628, + .required_clks = MT7628_CLKS_BITMAP, + .required_pctl = false, +}; + const struct of_device_id of_mtk_match[] = { { .compatible = "mediatek,mt2701-eth", .data = &mt2701_data}, { .compatible = "mediatek,mt7621-eth", .data = &mt7621_data}, { .compatible = "mediatek,mt7622-eth", .data = &mt7622_data}, { .compatible = "mediatek,mt7623-eth", .data = &mt7623_data}, { .compatible = "mediatek,mt7629-eth", .data = &mt7629_data}, + { .compatible = "ralink,rt5350-eth", .data = &rt5350_data}, {}, }; MODULE_DEVICE_TABLE(of, of_mtk_match); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.h b/drivers/net/ethernet/mediatek/mtk_eth_soc.h index bab94f763e2c..76bd12cb8150 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.h +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.h @@ -14,6 +14,7 @@ #include <linux/of_net.h> #include <linux/u64_stats_sync.h> #include <linux/refcount.h> +#include <linux/phylink.h> #define MTK_QDMA_PAGE_SIZE 2048 #define MTK_MAX_RX_LENGTH 1536 @@ -39,7 +40,8 @@ NETIF_F_SG | NETIF_F_TSO | \ NETIF_F_TSO6 | \ NETIF_F_IPV6_CSUM) -#define NEXT_RX_DESP_IDX(X, Y) (((X) + 1) & ((Y) - 1)) +#define MTK_HW_FEATURES_MT7628 (NETIF_F_SG | NETIF_F_RXCSUM) +#define NEXT_DESP_IDX(X, Y) (((X) + 1) & ((Y) - 1)) #define MTK_MAX_RX_RING_NUM 4 #define MTK_HW_LRO_DMA_SIZE 8 @@ -118,6 +120,7 @@ /* PDMA Global Configuration Register */ #define MTK_PDMA_GLO_CFG 0xa04 #define MTK_MULTI_EN BIT(10) +#define MTK_PDMA_SIZE_8DWORDS (1 << 4) /* PDMA Reset Index Register */ #define MTK_PDMA_RST_IDX 0xa08 @@ -212,7 +215,7 @@ #define FC_THRES_MIN 0x4444 /* QDMA Interrupt Status Register */ -#define MTK_QMTK_INT_STATUS 0x1A18 +#define MTK_QDMA_INT_STATUS 0x1A18 #define MTK_RX_DONE_DLY BIT(30) #define MTK_RX_DONE_INT3 BIT(19) #define MTK_RX_DONE_INT2 BIT(18) @@ -276,11 +279,18 @@ #define TX_DMA_OWNER_CPU BIT(31) #define TX_DMA_LS0 BIT(30) #define TX_DMA_PLEN0(_x) (((_x) & MTK_TX_DMA_BUF_LEN) << 16) +#define TX_DMA_PLEN1(_x) ((_x) & MTK_TX_DMA_BUF_LEN) #define TX_DMA_SWC BIT(14) #define TX_DMA_SDL(_x) (((_x) & 0x3fff) << 16) +/* PDMA on MT7628 */ +#define TX_DMA_DONE BIT(31) +#define TX_DMA_LS1 BIT(14) +#define TX_DMA_DESP2_DEF (TX_DMA_LS0 | TX_DMA_DONE) + /* QDMA descriptor rxd2 */ #define RX_DMA_DONE BIT(31) +#define RX_DMA_LSO BIT(30) #define RX_DMA_PLEN0(_x) (((_x) & 0x3fff) << 16) #define RX_DMA_GET_PLEN0(_x) (((_x) >> 16) & 0x3fff) @@ -289,6 +299,7 @@ /* QDMA descriptor rxd4 */ #define RX_DMA_L4_VALID BIT(24) +#define RX_DMA_L4_VALID_PDMA BIT(30) /* when PDMA is used */ #define RX_DMA_FPORT_SHIFT 19 #define RX_DMA_FPORT_MASK 0x7 @@ -320,12 +331,19 @@ #define MAC_MCR_SPEED_100 BIT(2) #define MAC_MCR_FORCE_DPX BIT(1) #define MAC_MCR_FORCE_LINK BIT(0) -#define MAC_MCR_FIXED_LINK (MAC_MCR_MAX_RX_1536 | MAC_MCR_IPG_CFG | \ - MAC_MCR_FORCE_MODE | MAC_MCR_TX_EN | \ - MAC_MCR_RX_EN | MAC_MCR_BACKOFF_EN | \ - MAC_MCR_BACKPR_EN | MAC_MCR_FORCE_RX_FC | \ - MAC_MCR_FORCE_TX_FC | MAC_MCR_SPEED_1000 | \ - MAC_MCR_FORCE_DPX | MAC_MCR_FORCE_LINK) +#define MAC_MCR_FORCE_LINK_DOWN (MAC_MCR_FORCE_MODE) + +/* Mac status registers */ +#define MTK_MAC_MSR(x) (0x10108 + (x * 0x100)) +#define MAC_MSR_EEE1G BIT(7) +#define MAC_MSR_EEE100M BIT(6) +#define MAC_MSR_RX_FC BIT(5) +#define MAC_MSR_TX_FC BIT(4) +#define MAC_MSR_SPEED_1000 BIT(3) +#define MAC_MSR_SPEED_100 BIT(2) +#define MAC_MSR_SPEED_MASK (MAC_MSR_SPEED_1000 | MAC_MSR_SPEED_100) +#define MAC_MSR_DPX BIT(1) +#define MAC_MSR_LINK BIT(0) /* TRGMII RXC control register */ #define TRGMII_RCK_CTRL 0x10300 @@ -394,14 +412,38 @@ /* Register to auto-negotiation restart */ #define SGMSYS_PCS_CONTROL_1 0x0 #define SGMII_AN_RESTART BIT(9) +#define SGMII_ISOLATE BIT(10) +#define SGMII_AN_ENABLE BIT(12) +#define SGMII_LINK_STATYS BIT(18) +#define SGMII_AN_ABILITY BIT(19) +#define SGMII_AN_COMPLETE BIT(21) +#define SGMII_PCS_FAULT BIT(23) +#define SGMII_AN_EXPANSION_CLR BIT(30) /* Register to programmable link timer, the unit in 2 * 8ns */ #define SGMSYS_PCS_LINK_TIMER 0x18 #define SGMII_LINK_TIMER_DEFAULT (0x186a0 & GENMASK(19, 0)) /* Register to control remote fault */ -#define SGMSYS_SGMII_MODE 0x20 -#define SGMII_REMOTE_FAULT_DIS BIT(8) +#define SGMSYS_SGMII_MODE 0x20 +#define SGMII_IF_MODE_BIT0 BIT(0) +#define SGMII_SPEED_DUPLEX_AN BIT(1) +#define SGMII_SPEED_10 0x0 +#define SGMII_SPEED_100 BIT(2) +#define SGMII_SPEED_1000 BIT(3) +#define SGMII_DUPLEX_FULL BIT(4) +#define SGMII_IF_MODE_BIT5 BIT(5) +#define SGMII_REMOTE_FAULT_DIS BIT(8) +#define SGMII_CODE_SYNC_SET_VAL BIT(9) +#define SGMII_CODE_SYNC_SET_EN BIT(10) +#define SGMII_SEND_AN_ERROR_EN BIT(11) +#define SGMII_IF_MODE_MASK GENMASK(5, 1) + +/* Register to set SGMII speed, ANA RG_ Control Signals III*/ +#define SGMSYS_ANA_RG_CS3 0x2028 +#define RG_PHY_SPEED_MASK (BIT(2) | BIT(3)) +#define RG_PHY_SPEED_1_25G 0x0 +#define RG_PHY_SPEED_3_125G BIT(2) /* Register to power up QPHY */ #define SGMSYS_QPHY_PWR_STATE_CTRL 0xe8 @@ -412,6 +454,19 @@ #define CO_QPHY_SEL BIT(0) #define GEPHY_MAC_SEL BIT(1) +/* MT7628/88 specific stuff */ +#define MT7628_PDMA_OFFSET 0x0800 +#define MT7628_SDM_OFFSET 0x0c00 + +#define MT7628_TX_BASE_PTR0 (MT7628_PDMA_OFFSET + 0x00) +#define MT7628_TX_MAX_CNT0 (MT7628_PDMA_OFFSET + 0x04) +#define MT7628_TX_CTX_IDX0 (MT7628_PDMA_OFFSET + 0x08) +#define MT7628_TX_DTX_IDX0 (MT7628_PDMA_OFFSET + 0x0c) +#define MT7628_PST_DTX_IDX0 BIT(0) + +#define MT7628_SDM_MAC_ADRL (MT7628_SDM_OFFSET + 0x0c) +#define MT7628_SDM_MAC_ADRH (MT7628_SDM_OFFSET + 0x10) + struct mtk_rx_dma { unsigned int rxd1; unsigned int rxd2; @@ -509,6 +564,7 @@ enum mtk_clks_map { BIT(MTK_CLK_SGMII_CK) | \ BIT(MTK_CLK_ETH2PLL)) #define MT7621_CLKS_BITMAP (0) +#define MT7628_CLKS_BITMAP (0) #define MT7629_CLKS_BITMAP (BIT(MTK_CLK_ETHIF) | BIT(MTK_CLK_ESW) | \ BIT(MTK_CLK_GP0) | BIT(MTK_CLK_GP1) | \ BIT(MTK_CLK_GP2) | BIT(MTK_CLK_FE) | \ @@ -563,6 +619,10 @@ struct mtk_tx_ring { struct mtk_tx_dma *last_free; u16 thresh; atomic_t free_count; + int dma_size; + struct mtk_tx_dma *dma_pdma; /* For MT7628/88 PDMA handling */ + dma_addr_t phys_pdma; + int cpu_idx; }; /* PDMA rx ring mode */ @@ -604,6 +664,8 @@ enum mkt_eth_capabilities { MTK_HWLRO_BIT, MTK_SHARED_INT_BIT, MTK_TRGMII_MT7621_CLK_BIT, + MTK_QDMA_BIT, + MTK_SOC_MT7628_BIT, /* MUX BITS*/ MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT, @@ -634,6 +696,8 @@ enum mkt_eth_capabilities { #define MTK_HWLRO BIT(MTK_HWLRO_BIT) #define MTK_SHARED_INT BIT(MTK_SHARED_INT_BIT) #define MTK_TRGMII_MT7621_CLK BIT(MTK_TRGMII_MT7621_CLK_BIT) +#define MTK_QDMA BIT(MTK_QDMA_BIT) +#define MTK_SOC_MT7628 BIT(MTK_SOC_MT7628_BIT) #define MTK_ETH_MUX_GDM1_TO_GMAC1_ESW \ BIT(MTK_ETH_MUX_GDM1_TO_GMAC1_ESW_BIT) @@ -687,26 +751,31 @@ enum mkt_eth_capabilities { #define MTK_HAS_CAPS(caps, _x) (((caps) & (_x)) == (_x)) #define MT7621_CAPS (MTK_GMAC1_RGMII | MTK_GMAC1_TRGMII | \ - MTK_GMAC2_RGMII | MTK_SHARED_INT | MTK_TRGMII_MT7621_CLK) + MTK_GMAC2_RGMII | MTK_SHARED_INT | \ + MTK_TRGMII_MT7621_CLK | MTK_QDMA) #define MT7622_CAPS (MTK_GMAC1_RGMII | MTK_GMAC1_SGMII | MTK_GMAC2_RGMII | \ MTK_GMAC2_SGMII | MTK_GDM1_ESW | \ MTK_MUX_GDM1_TO_GMAC1_ESW | \ - MTK_MUX_GMAC1_GMAC2_TO_SGMII_RGMII) + MTK_MUX_GMAC1_GMAC2_TO_SGMII_RGMII | MTK_QDMA) -#define MT7623_CAPS (MTK_GMAC1_RGMII | MTK_GMAC1_TRGMII | MTK_GMAC2_RGMII) +#define MT7623_CAPS (MTK_GMAC1_RGMII | MTK_GMAC1_TRGMII | MTK_GMAC2_RGMII | \ + MTK_QDMA) + +#define MT7628_CAPS (MTK_SHARED_INT | MTK_SOC_MT7628) #define MT7629_CAPS (MTK_GMAC1_SGMII | MTK_GMAC2_SGMII | MTK_GMAC2_GEPHY | \ MTK_GDM1_ESW | MTK_MUX_GDM1_TO_GMAC1_ESW | \ MTK_MUX_GMAC2_GMAC0_TO_GEPHY | \ MTK_MUX_U3_GMAC2_TO_QPHY | \ - MTK_MUX_GMAC12_TO_GEPHY_SGMII) + MTK_MUX_GMAC12_TO_GEPHY_SGMII | MTK_QDMA) /* struct mtk_eth_data - This is the structure holding all differences * among various plaforms * @ana_rgc3: The offset for register ANA_RGC3 related to * sgmiisys syscon * @caps Flags shown the extra capability for the SoC + * @hw_features Flags shown HW features * @required_clks Flags shown the bitmap for required clocks on * the target SoC * @required_pctl A bool value to show whether the SoC requires @@ -717,6 +786,7 @@ struct mtk_soc_data { u32 caps; u32 required_clks; bool required_pctl; + netdev_features_t hw_features; }; /* currently no SoC has more than 2 macs */ @@ -810,27 +880,33 @@ struct mtk_eth { unsigned long state; const struct mtk_soc_data *soc; + + u32 tx_int_mask_reg; + u32 tx_int_status_reg; + u32 rx_dma_l4_valid; + int ip_align; }; /* struct mtk_mac - the structure that holds the info about the MACs of the * SoC * @id: The number of the MAC - * @ge_mode: Interface mode kept for setup restoring + * @interface: Interface mode kept for detecting change in hw settings * @of_node: Our devicetree node * @hw: Backpointer to our main datastruture * @hw_stats: Packet statistics counter - * @trgmii Indicate if the MAC uses TRGMII connected to internal - switch */ struct mtk_mac { int id; - int ge_mode; + phy_interface_t interface; + unsigned int mode; + int speed; struct device_node *of_node; + struct phylink *phylink; + struct phylink_config phylink_config; struct mtk_eth *hw; struct mtk_hw_stats *hw_stats; __be32 hwlro_ip[MTK_MAX_LRO_IP_CNT]; int hwlro_ip_cnt; - bool trgmii; }; /* the struct describing the SoC. these are declared in the soc_xyz.c files */ @@ -845,7 +921,12 @@ u32 mtk_r32(struct mtk_eth *eth, unsigned reg); int mtk_sgmii_init(struct mtk_sgmii *ss, struct device_node *np, u32 ana_rgc3); int mtk_sgmii_setup_mode_an(struct mtk_sgmii *ss, int id); -int mtk_sgmii_setup_mode_force(struct mtk_sgmii *ss, int id); -int mtk_setup_hw_path(struct mtk_eth *eth, int mac_id, int phymode); +int mtk_sgmii_setup_mode_force(struct mtk_sgmii *ss, int id, + const struct phylink_link_state *state); +void mtk_sgmii_restart_an(struct mtk_eth *eth, int mac_id); + +int mtk_gmac_sgmii_path_setup(struct mtk_eth *eth, int mac_id); +int mtk_gmac_gephy_path_setup(struct mtk_eth *eth, int mac_id); +int mtk_gmac_rgmii_path_setup(struct mtk_eth *eth, int mac_id); #endif /* MTK_ETH_H */ diff --git a/drivers/net/ethernet/mediatek/mtk_sgmii.c b/drivers/net/ethernet/mediatek/mtk_sgmii.c index ff509d42d818..4db27dfc7ec1 100644 --- a/drivers/net/ethernet/mediatek/mtk_sgmii.c +++ b/drivers/net/ethernet/mediatek/mtk_sgmii.c @@ -16,8 +16,7 @@ int mtk_sgmii_init(struct mtk_sgmii *ss, struct device_node *r, u32 ana_rgc3) { struct device_node *np; - const char *str; - int i, err; + int i; ss->ana_rgc3 = ana_rgc3; @@ -29,19 +28,6 @@ int mtk_sgmii_init(struct mtk_sgmii *ss, struct device_node *r, u32 ana_rgc3) ss->regmap[i] = syscon_node_to_regmap(np); if (IS_ERR(ss->regmap[i])) return PTR_ERR(ss->regmap[i]); - - err = of_property_read_string(np, "mediatek,physpeed", &str); - if (err) - return err; - - if (!strcmp(str, "2500")) - ss->flags[i] |= MTK_SGMII_PHYSPEED_2500; - else if (!strcmp(str, "1000")) - ss->flags[i] |= MTK_SGMII_PHYSPEED_1000; - else if (!strcmp(str, "auto")) - ss->flags[i] |= MTK_SGMII_PHYSPEED_AN; - else - return -EINVAL; } return 0; @@ -73,27 +59,45 @@ int mtk_sgmii_setup_mode_an(struct mtk_sgmii *ss, int id) return 0; } -int mtk_sgmii_setup_mode_force(struct mtk_sgmii *ss, int id) +int mtk_sgmii_setup_mode_force(struct mtk_sgmii *ss, int id, + const struct phylink_link_state *state) { unsigned int val; - int mode; if (!ss->regmap[id]) return -EINVAL; regmap_read(ss->regmap[id], ss->ana_rgc3, &val); - val &= ~GENMASK(3, 2); - mode = ss->flags[id] & MTK_SGMII_PHYSPEED_MASK; - val |= (mode == MTK_SGMII_PHYSPEED_1000) ? 0 : BIT(2); + val &= ~RG_PHY_SPEED_MASK; + if (state->interface == PHY_INTERFACE_MODE_2500BASEX) + val |= RG_PHY_SPEED_3_125G; regmap_write(ss->regmap[id], ss->ana_rgc3, val); /* Disable SGMII AN */ regmap_read(ss->regmap[id], SGMSYS_PCS_CONTROL_1, &val); - val &= ~BIT(12); + val &= ~SGMII_AN_ENABLE; regmap_write(ss->regmap[id], SGMSYS_PCS_CONTROL_1, val); /* SGMII force mode setting */ - val = 0x31120019; + regmap_read(ss->regmap[id], SGMSYS_SGMII_MODE, &val); + val &= ~SGMII_IF_MODE_MASK; + + switch (state->speed) { + case SPEED_10: + val |= SGMII_SPEED_10; + break; + case SPEED_100: + val |= SGMII_SPEED_100; + break; + case SPEED_2500: + case SPEED_1000: + val |= SGMII_SPEED_1000; + break; + }; + + if (state->duplex == DUPLEX_FULL) + val |= SGMII_DUPLEX_FULL; + regmap_write(ss->regmap[id], SGMSYS_SGMII_MODE, val); /* Release PHYA power down state */ @@ -103,3 +107,20 @@ int mtk_sgmii_setup_mode_force(struct mtk_sgmii *ss, int id) return 0; } + +void mtk_sgmii_restart_an(struct mtk_eth *eth, int mac_id) +{ + struct mtk_sgmii *ss = eth->sgmii; + unsigned int val, sid; + + /* Decide how GMAC and SGMIISYS be mapped */ + sid = (MTK_HAS_CAPS(eth->soc->caps, MTK_SHARED_SGMII)) ? + 0 : mac_id; + + if (!ss->regmap[sid]) + return; + + regmap_read(ss->regmap[sid], SGMSYS_PCS_CONTROL_1, &val); + val |= SGMII_AN_RESTART; + regmap_write(ss->regmap[sid], SGMSYS_PCS_CONTROL_1, val); +} diff --git a/drivers/net/ethernet/mellanox/mlx4/catas.c b/drivers/net/ethernet/mellanox/mlx4/catas.c index 87e90b5d4d7d..5b11557f1ae4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/catas.c +++ b/drivers/net/ethernet/mellanox/mlx4/catas.c @@ -210,7 +210,7 @@ static void mlx4_handle_error_state(struct mlx4_dev_persistent *persist) mutex_lock(&persist->interface_state_mutex); if (persist->interface_state & MLX4_INTERFACE_STATE_UP && !(persist->interface_state & MLX4_INTERFACE_STATE_DELETION)) { - err = mlx4_restart_one(persist->pdev, false, NULL); + err = mlx4_restart_one(persist->pdev); mlx4_info(persist->dev, "mlx4_restart_one was ended, ret=%d\n", err); } diff --git a/drivers/net/ethernet/mellanox/mlx4/crdump.c b/drivers/net/ethernet/mellanox/mlx4/crdump.c index 88316c743820..eaf08f7ad128 100644 --- a/drivers/net/ethernet/mellanox/mlx4/crdump.c +++ b/drivers/net/ethernet/mellanox/mlx4/crdump.c @@ -99,8 +99,7 @@ static void mlx4_crdump_collect_crspace(struct mlx4_dev *dev, readl(cr_space + offset); err = devlink_region_snapshot_create(crdump->region_crspace, - cr_res_size, crspace_data, - id, &kvfree); + crspace_data, id, &kvfree); if (err) { kvfree(crspace_data); mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n", @@ -139,9 +138,7 @@ static void mlx4_crdump_collect_fw_health(struct mlx4_dev *dev, readl(health_buf_start + offset); err = devlink_region_snapshot_create(crdump->region_fw_health, - HEALTH_BUFFER_SIZE, - health_data, - id, &kvfree); + health_data, id, &kvfree); if (err) { kvfree(health_data); mlx4_warn(dev, "crdump: devlink create %s snapshot id %d err %d\n", diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 94c59939a8cf..d8313e2ee600 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -639,7 +639,7 @@ static unsigned long *ptys2ethtool_link_mode(struct ptys2ethtool_config *cfg, #define MLX4_BUILD_PTYS2ETHTOOL_CONFIG(reg_, speed_, ...) \ ({ \ struct ptys2ethtool_config *cfg; \ - const unsigned int modes[] = { __VA_ARGS__ }; \ + static const unsigned int modes[] = { __VA_ARGS__ }; \ unsigned int i; \ cfg = &ptys2ethtool_map[reg_]; \ cfg->speed = speed_; \ diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index c1438ae52a11..40ec5acf79c0 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -2645,14 +2645,6 @@ out: en_err(priv, "failed setting L2 tunnel configuration ret %d\n", ret); return; } - - /* set offloads */ - priv->dev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_RXCSUM | - NETIF_F_TSO | NETIF_F_TSO6 | - NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL; } static void mlx4_en_del_vxlan_offloads(struct work_struct *work) @@ -2660,14 +2652,6 @@ static void mlx4_en_del_vxlan_offloads(struct work_struct *work) int ret; struct mlx4_en_priv *priv = container_of(work, struct mlx4_en_priv, vxlan_del_task); - /* unset offloads */ - priv->dev->hw_enc_features &= ~(NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_RXCSUM | - NETIF_F_TSO | NETIF_F_TSO6 | - NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL); - ret = mlx4_SET_PORT_VXLAN(priv->mdev->dev, priv->port, VXLAN_STEER_BY_OUTER_MAC, 0); if (ret) @@ -3415,6 +3399,23 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, if (mdev->LSO_support) dev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6; + if (mdev->dev->caps.tunnel_offload_mode == + MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { + dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_GSO_PARTIAL; + dev->features |= NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_GSO_PARTIAL; + dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; + dev->hw_enc_features = NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM | + NETIF_F_TSO | NETIF_F_TSO6 | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_GSO_UDP_TUNNEL_CSUM | + NETIF_F_GSO_PARTIAL; + } + dev->vlan_features = dev->hw_features; dev->hw_features |= NETIF_F_RXCSUM | NETIF_F_RXHASH; @@ -3483,16 +3484,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, priv->rss_hash_fn = ETH_RSS_HASH_TOP; } - if (mdev->dev->caps.tunnel_offload_mode == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) { - dev->hw_features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL; - dev->features |= NETIF_F_GSO_UDP_TUNNEL | - NETIF_F_GSO_UDP_TUNNEL_CSUM | - NETIF_F_GSO_PARTIAL; - dev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; - } - /* MTU range: 68 - hw-specific max */ dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = priv->max_mtu; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 36a92b19e613..4d5ca302c067 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -772,9 +772,7 @@ static bool mlx4_en_build_dma_wqe(struct mlx4_en_priv *priv, /* Map fragments if any */ for (i_frag = shinfo->nr_frags - 1; i_frag >= 0; i_frag--) { - const struct skb_frag_struct *frag; - - frag = &shinfo->frags[i_frag]; + const skb_frag_t *frag = &shinfo->frags[i_frag]; byte_count = skb_frag_size(frag); dma = skb_frag_dma_map(ddev, frag, 0, byte_count, diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 309470ec0219..fce9b3a24347 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2292,23 +2292,31 @@ static int mlx4_init_fw(struct mlx4_dev *dev) static int mlx4_init_hca(struct mlx4_dev *dev) { struct mlx4_priv *priv = mlx4_priv(dev); + struct mlx4_init_hca_param *init_hca = NULL; + struct mlx4_dev_cap *dev_cap = NULL; struct mlx4_adapter adapter; - struct mlx4_dev_cap dev_cap; struct mlx4_profile profile; - struct mlx4_init_hca_param init_hca; u64 icm_size; struct mlx4_config_dev_params params; int err; if (!mlx4_is_slave(dev)) { - err = mlx4_dev_cap(dev, &dev_cap); + dev_cap = kzalloc(sizeof(*dev_cap), GFP_KERNEL); + init_hca = kzalloc(sizeof(*init_hca), GFP_KERNEL); + + if (!dev_cap || !init_hca) { + err = -ENOMEM; + goto out_free; + } + + err = mlx4_dev_cap(dev, dev_cap); if (err) { mlx4_err(dev, "QUERY_DEV_CAP command failed, aborting\n"); - return err; + goto out_free; } - choose_steering_mode(dev, &dev_cap); - choose_tunnel_offload_mode(dev, &dev_cap); + choose_steering_mode(dev, dev_cap); + choose_tunnel_offload_mode(dev, dev_cap); if (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_STATIC && mlx4_is_master(dev)) @@ -2331,48 +2339,48 @@ static int mlx4_init_hca(struct mlx4_dev *dev) MLX4_STEERING_MODE_DEVICE_MANAGED) profile.num_mcg = MLX4_FS_NUM_MCG; - icm_size = mlx4_make_profile(dev, &profile, &dev_cap, - &init_hca); + icm_size = mlx4_make_profile(dev, &profile, dev_cap, + init_hca); if ((long long) icm_size < 0) { err = icm_size; - return err; + goto out_free; } dev->caps.max_fmr_maps = (1 << (32 - ilog2(dev->caps.num_mpts))) - 1; if (enable_4k_uar || !dev->persist->num_vfs) { - init_hca.log_uar_sz = ilog2(dev->caps.num_uars) + + init_hca->log_uar_sz = ilog2(dev->caps.num_uars) + PAGE_SHIFT - DEFAULT_UAR_PAGE_SHIFT; - init_hca.uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12; + init_hca->uar_page_sz = DEFAULT_UAR_PAGE_SHIFT - 12; } else { - init_hca.log_uar_sz = ilog2(dev->caps.num_uars); - init_hca.uar_page_sz = PAGE_SHIFT - 12; + init_hca->log_uar_sz = ilog2(dev->caps.num_uars); + init_hca->uar_page_sz = PAGE_SHIFT - 12; } - init_hca.mw_enabled = 0; + init_hca->mw_enabled = 0; if (dev->caps.flags & MLX4_DEV_CAP_FLAG_MEM_WINDOW || dev->caps.bmme_flags & MLX4_BMME_FLAG_TYPE_2_WIN) - init_hca.mw_enabled = INIT_HCA_TPT_MW_ENABLE; + init_hca->mw_enabled = INIT_HCA_TPT_MW_ENABLE; - err = mlx4_init_icm(dev, &dev_cap, &init_hca, icm_size); + err = mlx4_init_icm(dev, dev_cap, init_hca, icm_size); if (err) - return err; + goto out_free; - err = mlx4_INIT_HCA(dev, &init_hca); + err = mlx4_INIT_HCA(dev, init_hca); if (err) { mlx4_err(dev, "INIT_HCA command failed, aborting\n"); goto err_free_icm; } - if (dev_cap.flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS) { - err = mlx4_query_func(dev, &dev_cap); + if (dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_SYS_EQS) { + err = mlx4_query_func(dev, dev_cap); if (err < 0) { mlx4_err(dev, "QUERY_FUNC command failed, aborting.\n"); goto err_close; } else if (err & MLX4_QUERY_FUNC_NUM_SYS_EQS) { - dev->caps.num_eqs = dev_cap.max_eqs; - dev->caps.reserved_eqs = dev_cap.reserved_eqs; - dev->caps.reserved_uars = dev_cap.reserved_uars; + dev->caps.num_eqs = dev_cap->max_eqs; + dev->caps.reserved_eqs = dev_cap->reserved_eqs; + dev->caps.reserved_uars = dev_cap->reserved_uars; } } @@ -2381,14 +2389,13 @@ static int mlx4_init_hca(struct mlx4_dev *dev) * read HCA frequency by QUERY_HCA command */ if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_TS) { - memset(&init_hca, 0, sizeof(init_hca)); - err = mlx4_QUERY_HCA(dev, &init_hca); + err = mlx4_QUERY_HCA(dev, init_hca); if (err) { mlx4_err(dev, "QUERY_HCA command failed, disable timestamp\n"); dev->caps.flags2 &= ~MLX4_DEV_CAP_FLAG2_TS; } else { dev->caps.hca_core_clock = - init_hca.hca_core_clock; + init_hca->hca_core_clock; } /* In case we got HCA frequency 0 - disable timestamping @@ -2464,7 +2471,8 @@ static int mlx4_init_hca(struct mlx4_dev *dev) priv->eq_table.inta_pin = adapter.inta_pin; memcpy(dev->board_id, adapter.board_id, sizeof(dev->board_id)); - return 0; + err = 0; + goto out_free; unmap_bf: unmap_internal_clock(dev); @@ -2483,6 +2491,10 @@ err_free_icm: if (!mlx4_is_slave(dev)) mlx4_free_icms(dev); +out_free: + kfree(dev_cap); + kfree(init_hca); + return err; } @@ -3919,26 +3931,43 @@ static void mlx4_devlink_param_load_driverinit_values(struct devlink *devlink) } } -static int mlx4_devlink_reload(struct devlink *devlink, - struct netlink_ext_ack *extack) +static void mlx4_restart_one_down(struct pci_dev *pdev); +static int mlx4_restart_one_up(struct pci_dev *pdev, bool reload, + struct devlink *devlink); + +static int mlx4_devlink_reload_down(struct devlink *devlink, + struct netlink_ext_ack *extack) { struct mlx4_priv *priv = devlink_priv(devlink); struct mlx4_dev *dev = &priv->dev; struct mlx4_dev_persistent *persist = dev->persist; - int err; if (persist->num_vfs) mlx4_warn(persist->dev, "Reload performed on PF, will cause reset on operating Virtual Functions\n"); - err = mlx4_restart_one(persist->pdev, true, devlink); + mlx4_restart_one_down(persist->pdev); + return 0; +} + +static int mlx4_devlink_reload_up(struct devlink *devlink, + struct netlink_ext_ack *extack) +{ + struct mlx4_priv *priv = devlink_priv(devlink); + struct mlx4_dev *dev = &priv->dev; + struct mlx4_dev_persistent *persist = dev->persist; + int err; + + err = mlx4_restart_one_up(persist->pdev, true, devlink); if (err) - mlx4_err(persist->dev, "mlx4_restart_one failed, ret=%d\n", err); + mlx4_err(persist->dev, "mlx4_restart_one_up failed, ret=%d\n", + err); return err; } static const struct devlink_ops mlx4_devlink_ops = { .port_type_set = mlx4_devlink_port_type_set, - .reload = mlx4_devlink_reload, + .reload_down = mlx4_devlink_reload_down, + .reload_up = mlx4_devlink_reload_up, }; static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) @@ -4151,7 +4180,13 @@ static int restore_current_port_types(struct mlx4_dev *dev, return err; } -int mlx4_restart_one(struct pci_dev *pdev, bool reload, struct devlink *devlink) +static void mlx4_restart_one_down(struct pci_dev *pdev) +{ + mlx4_unload_one(pdev); +} + +static int mlx4_restart_one_up(struct pci_dev *pdev, bool reload, + struct devlink *devlink) { struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); struct mlx4_dev *dev = persist->dev; @@ -4163,7 +4198,6 @@ int mlx4_restart_one(struct pci_dev *pdev, bool reload, struct devlink *devlink) total_vfs = dev->persist->num_vfs; memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs)); - mlx4_unload_one(pdev); if (reload) mlx4_devlink_param_load_driverinit_values(devlink); err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv, 1); @@ -4182,6 +4216,12 @@ int mlx4_restart_one(struct pci_dev *pdev, bool reload, struct devlink *devlink) return err; } +int mlx4_restart_one(struct pci_dev *pdev) +{ + mlx4_restart_one_down(pdev); + return mlx4_restart_one_up(pdev, false, NULL); +} + #define MLX_SP(id) { PCI_VDEVICE(MELLANOX, id), MLX4_PCI_DEV_FORCE_SENSE_PORT } #define MLX_VF(id) { PCI_VDEVICE(MELLANOX, id), MLX4_PCI_DEV_IS_VF } #define MLX_GN(id) { PCI_VDEVICE(MELLANOX, id), 0 } diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index 23f1b5b512c2..527b52e48276 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -1043,8 +1043,7 @@ int mlx4_catas_init(struct mlx4_dev *dev); void mlx4_catas_end(struct mlx4_dev *dev); int mlx4_crdump_init(struct mlx4_dev *dev); void mlx4_crdump_end(struct mlx4_dev *dev); -int mlx4_restart_one(struct pci_dev *pdev, bool reload, - struct devlink *devlink); +int mlx4_restart_one(struct pci_dev *pdev); int mlx4_register_device(struct mlx4_dev *dev); void mlx4_unregister_device(struct mlx4_dev *dev); void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_dev_event type, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index 37fef8cd25e3..0dba272a5b2f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -10,6 +10,7 @@ config MLX5_CORE imply PTP_1588_CLOCK imply VXLAN imply MLXFW + imply PCI_HYPERV_INTERFACE default n ---help--- Core driver for low level functionality of the ConnectX-4 and @@ -32,7 +33,6 @@ config MLX5_FPGA config MLX5_CORE_EN bool "Mellanox 5th generation network adapters (ConnectX series) Ethernet support" depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE - depends on IPV6=y || IPV6=n || MLX5_CORE=m select PAGE_POOL select DIMLIB default n @@ -154,3 +154,10 @@ config MLX5_EN_TLS Build support for TLS cryptography-offload accelaration in the NIC. Note: Support for hardware with this capability needs to be selected for this option to become available. + +config MLX5_SW_STEERING + bool "Mellanox Technologies software-managed steering" + depends on MLX5_CORE_EN && MLX5_ESWITCH + default y + help + Build support for software-managed steering in the NIC. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index 57d2cc666fe3..5708fcc079ca 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -15,7 +15,7 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ health.o mcg.o cq.o alloc.o qp.o port.o mr.o pd.o \ transobj.o vport.o sriov.o fs_cmd.o fs_core.o pci_irq.o \ fs_counters.o rl.o lag.o dev.o events.o wq.o lib/gid.o \ - lib/devcom.o lib/pci_vsc.o diag/fs_tracepoint.o \ + lib/devcom.o lib/pci_vsc.o lib/dm.o diag/fs_tracepoint.o \ diag/fw_tracer.o diag/crdump.o devlink.o # @@ -23,8 +23,9 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ # mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en/xdp.o en_stats.o \ - en_selftest.o en/port.o en/monitor_stats.o en/reporter_tx.o \ - en/params.o en/xsk/umem.o en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o + en_selftest.o en/port.o en/monitor_stats.o en/health.o \ + en/reporter_tx.o en/reporter_rx.o en/params.o en/xsk/umem.o \ + en/xsk/setup.o en/xsk/rx.o en/xsk/tx.o # # Netdev extra @@ -34,7 +35,8 @@ mlx5_core-$(CONFIG_MLX5_EN_RXNFC) += en_fs_ethtool.o mlx5_core-$(CONFIG_MLX5_CORE_EN_DCB) += en_dcbnl.o en/port_buffer.o mlx5_core-$(CONFIG_MLX5_ESWITCH) += en_rep.o en_tc.o en/tc_tun.o lib/port_tun.o lag_mp.o \ lib/geneve.o en/tc_tun_vxlan.o en/tc_tun_gre.o \ - en/tc_tun_geneve.o + en/tc_tun_geneve.o diag/en_tc_tracepoint.o +mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += en/hv_vhca_stats.o # # Core extra @@ -44,6 +46,7 @@ mlx5_core-$(CONFIG_MLX5_ESWITCH) += eswitch.o eswitch_offloads.o eswitch_offlo mlx5_core-$(CONFIG_MLX5_MPFS) += lib/mpfs.o mlx5_core-$(CONFIG_VXLAN) += lib/vxlan.o mlx5_core-$(CONFIG_PTP_1588_CLOCK) += lib/clock.o +mlx5_core-$(CONFIG_PCI_HYPERV_INTERFACE) += lib/hv.o lib/hv_vhca.o # # Ipoib netdev @@ -64,3 +67,10 @@ mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \ mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o \ en_accel/ktls.o en_accel/ktls_tx.o + +mlx5_core-$(CONFIG_MLX5_SW_STEERING) += steering/dr_domain.o steering/dr_table.o \ + steering/dr_matcher.o steering/dr_rule.o \ + steering/dr_icm_pool.o steering/dr_crc32.o \ + steering/dr_ste.o steering/dr_send.o \ + steering/dr_cmd.o steering/dr_fw.o \ + steering/dr_action.o steering/fs_dr.o diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 8cdd7e66f8df..ea934cd02448 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -446,6 +446,8 @@ static int mlx5_internal_err_ret_value(struct mlx5_core_dev *dev, u16 op, case MLX5_CMD_OP_CREATE_UMEM: case MLX5_CMD_OP_DESTROY_UMEM: case MLX5_CMD_OP_ALLOC_MEMIC: + case MLX5_CMD_OP_MODIFY_XRQ: + case MLX5_CMD_OP_RELEASE_XRQ_ERROR: *status = MLX5_DRIVER_STATUS_ABORTED; *synd = MLX5_DRIVER_SYND; return -EIO; @@ -637,6 +639,8 @@ const char *mlx5_command_str(int command) MLX5_COMMAND_STR_CASE(DESTROY_UCTX); MLX5_COMMAND_STR_CASE(CREATE_UMEM); MLX5_COMMAND_STR_CASE(DESTROY_UMEM); + MLX5_COMMAND_STR_CASE(RELEASE_XRQ_ERROR); + MLX5_COMMAND_STR_CASE(MODIFY_XRQ); default: return "unknown command opcode"; } } @@ -1368,49 +1372,19 @@ static void clean_debug_files(struct mlx5_core_dev *dev) debugfs_remove_recursive(dbg->dbg_root); } -static int create_debugfs_files(struct mlx5_core_dev *dev) +static void create_debugfs_files(struct mlx5_core_dev *dev) { struct mlx5_cmd_debug *dbg = &dev->cmd.dbg; - int err = -ENOMEM; - - if (!mlx5_debugfs_root) - return 0; dbg->dbg_root = debugfs_create_dir("cmd", dev->priv.dbg_root); - if (!dbg->dbg_root) - return err; - - dbg->dbg_in = debugfs_create_file("in", 0400, dbg->dbg_root, - dev, &dfops); - if (!dbg->dbg_in) - goto err_dbg; - dbg->dbg_out = debugfs_create_file("out", 0200, dbg->dbg_root, - dev, &dfops); - if (!dbg->dbg_out) - goto err_dbg; - - dbg->dbg_outlen = debugfs_create_file("out_len", 0600, dbg->dbg_root, - dev, &olfops); - if (!dbg->dbg_outlen) - goto err_dbg; - - dbg->dbg_status = debugfs_create_u8("status", 0600, dbg->dbg_root, - &dbg->status); - if (!dbg->dbg_status) - goto err_dbg; - - dbg->dbg_run = debugfs_create_file("run", 0200, dbg->dbg_root, dev, &fops); - if (!dbg->dbg_run) - goto err_dbg; + debugfs_create_file("in", 0400, dbg->dbg_root, dev, &dfops); + debugfs_create_file("out", 0200, dbg->dbg_root, dev, &dfops); + debugfs_create_file("out_len", 0600, dbg->dbg_root, dev, &olfops); + debugfs_create_u8("status", 0600, dbg->dbg_root, &dbg->status); + debugfs_create_file("run", 0200, dbg->dbg_root, dev, &fops); mlx5_cmdif_debugfs_init(dev); - - return 0; - -err_dbg: - clean_debug_files(dev); - return err; } static void mlx5_cmd_change_mod(struct mlx5_core_dev *dev, int mode) @@ -2007,17 +1981,10 @@ int mlx5_cmd_init(struct mlx5_core_dev *dev) goto err_cache; } - err = create_debugfs_files(dev); - if (err) { - err = -ENOMEM; - goto err_wq; - } + create_debugfs_files(dev); return 0; -err_wq: - destroy_workqueue(cmd->wq); - err_cache: destroy_msg_cache(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c index a11e22d0b0cc..04854e5fbcd7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/debugfs.c @@ -92,8 +92,6 @@ EXPORT_SYMBOL(mlx5_debugfs_root); void mlx5_register_debugfs(void) { mlx5_debugfs_root = debugfs_create_dir("mlx5", NULL); - if (IS_ERR_OR_NULL(mlx5_debugfs_root)) - mlx5_debugfs_root = NULL; } void mlx5_unregister_debugfs(void) @@ -101,45 +99,25 @@ void mlx5_unregister_debugfs(void) debugfs_remove(mlx5_debugfs_root); } -int mlx5_qp_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_qp_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - atomic_set(&dev->num_qps, 0); dev->priv.qp_debugfs = debugfs_create_dir("QPs", dev->priv.dbg_root); - if (!dev->priv.qp_debugfs) - return -ENOMEM; - - return 0; } void mlx5_qp_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.qp_debugfs); } -int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_eq_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - dev->priv.eq_debugfs = debugfs_create_dir("EQs", dev->priv.dbg_root); - if (!dev->priv.eq_debugfs) - return -ENOMEM; - - return 0; } void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.eq_debugfs); } @@ -183,85 +161,41 @@ static const struct file_operations stats_fops = { .write = average_write, }; -int mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_cmdif_debugfs_init(struct mlx5_core_dev *dev) { struct mlx5_cmd_stats *stats; struct dentry **cmd; const char *namep; - int err; int i; - if (!mlx5_debugfs_root) - return 0; - cmd = &dev->priv.cmdif_debugfs; *cmd = debugfs_create_dir("commands", dev->priv.dbg_root); - if (!*cmd) - return -ENOMEM; for (i = 0; i < ARRAY_SIZE(dev->cmd.stats); i++) { stats = &dev->cmd.stats[i]; namep = mlx5_command_str(i); if (strcmp(namep, "unknown command opcode")) { stats->root = debugfs_create_dir(namep, *cmd); - if (!stats->root) { - mlx5_core_warn(dev, "failed adding command %d\n", - i); - err = -ENOMEM; - goto out; - } - - stats->avg = debugfs_create_file("average", 0400, - stats->root, stats, - &stats_fops); - if (!stats->avg) { - mlx5_core_warn(dev, "failed creating debugfs file\n"); - err = -ENOMEM; - goto out; - } - - stats->count = debugfs_create_u64("n", 0400, - stats->root, - &stats->n); - if (!stats->count) { - mlx5_core_warn(dev, "failed creating debugfs file\n"); - err = -ENOMEM; - goto out; - } + + debugfs_create_file("average", 0400, stats->root, stats, + &stats_fops); + debugfs_create_u64("n", 0400, stats->root, &stats->n); } } - - return 0; -out: - debugfs_remove_recursive(dev->priv.cmdif_debugfs); - return err; } void mlx5_cmdif_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.cmdif_debugfs); } -int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev) +void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return 0; - dev->priv.cq_debugfs = debugfs_create_dir("CQs", dev->priv.dbg_root); - if (!dev->priv.cq_debugfs) - return -ENOMEM; - - return 0; } void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev) { - if (!mlx5_debugfs_root) - return; - debugfs_remove_recursive(dev->priv.cq_debugfs); } @@ -484,7 +418,6 @@ static int add_res_tree(struct mlx5_core_dev *dev, enum dbg_rsc_type type, { struct mlx5_rsc_debug *d; char resn[32]; - int err; int i; d = kzalloc(struct_size(d, fields, nfile), GFP_KERNEL); @@ -496,30 +429,15 @@ static int add_res_tree(struct mlx5_core_dev *dev, enum dbg_rsc_type type, d->type = type; sprintf(resn, "0x%x", rsn); d->root = debugfs_create_dir(resn, root); - if (!d->root) { - err = -ENOMEM; - goto out_free; - } for (i = 0; i < nfile; i++) { d->fields[i].i = i; - d->fields[i].dent = debugfs_create_file(field[i], 0400, - d->root, &d->fields[i], - &fops); - if (!d->fields[i].dent) { - err = -ENOMEM; - goto out_rem; - } + debugfs_create_file(field[i], 0400, d->root, &d->fields[i], + &fops); } *dbg = d; return 0; -out_rem: - debugfs_remove_recursive(d->root); - -out_free: - kfree(d); - return err; } static void rem_res_tree(struct mlx5_rsc_debug *d) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c index a400f4430c28..381925c90d94 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/devlink.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/devlink.c @@ -4,6 +4,7 @@ #include <devlink.h> #include "mlx5_core.h" +#include "fs_core.h" #include "eswitch.h" static int mlx5_devlink_flash_update(struct devlink *devlink, @@ -107,12 +108,121 @@ void mlx5_devlink_free(struct devlink *devlink) devlink_free(devlink); } +static int mlx5_devlink_fs_mode_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + char *value = val.vstr; + int err = 0; + + if (!strcmp(value, "dmfs")) { + return 0; + } else if (!strcmp(value, "smfs")) { + u8 eswitch_mode; + bool smfs_cap; + + eswitch_mode = mlx5_eswitch_mode(dev->priv.eswitch); + smfs_cap = mlx5_fs_dr_is_supported(dev); + + if (!smfs_cap) { + err = -EOPNOTSUPP; + NL_SET_ERR_MSG_MOD(extack, + "Software managed steering is not supported by current device"); + } + + else if (eswitch_mode == MLX5_ESWITCH_OFFLOADS) { + NL_SET_ERR_MSG_MOD(extack, + "Software managed steering is not supported when eswitch offloads enabled."); + err = -EOPNOTSUPP; + } + } else { + NL_SET_ERR_MSG_MOD(extack, + "Bad parameter: supported values are [\"dmfs\", \"smfs\"]"); + err = -EINVAL; + } + + return err; +} + +static int mlx5_devlink_fs_mode_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + enum mlx5_flow_steering_mode mode; + + if (!strcmp(ctx->val.vstr, "smfs")) + mode = MLX5_FLOW_STEERING_MODE_SMFS; + else + mode = MLX5_FLOW_STEERING_MODE_DMFS; + dev->priv.steering->mode = mode; + + return 0; +} + +static int mlx5_devlink_fs_mode_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + + if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_SMFS) + strcpy(ctx->val.vstr, "smfs"); + else + strcpy(ctx->val.vstr, "dmfs"); + return 0; +} + +enum mlx5_devlink_param_id { + MLX5_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX, + MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, +}; + +static const struct devlink_param mlx5_devlink_params[] = { + DEVLINK_PARAM_DRIVER(MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, + "flow_steering_mode", DEVLINK_PARAM_TYPE_STRING, + BIT(DEVLINK_PARAM_CMODE_RUNTIME), + mlx5_devlink_fs_mode_get, mlx5_devlink_fs_mode_set, + mlx5_devlink_fs_mode_validate), +}; + +static void mlx5_devlink_set_params_init_values(struct devlink *devlink) +{ + struct mlx5_core_dev *dev = devlink_priv(devlink); + union devlink_param_value value; + + if (dev->priv.steering->mode == MLX5_FLOW_STEERING_MODE_DMFS) + strcpy(value.vstr, "dmfs"); + else + strcpy(value.vstr, "smfs"); + devlink_param_driverinit_value_set(devlink, + MLX5_DEVLINK_PARAM_FLOW_STEERING_MODE, + value); +} + int mlx5_devlink_register(struct devlink *devlink, struct device *dev) { - return devlink_register(devlink, dev); + int err; + + err = devlink_register(devlink, dev); + if (err) + return err; + + err = devlink_params_register(devlink, mlx5_devlink_params, + ARRAY_SIZE(mlx5_devlink_params)); + if (err) + goto params_reg_err; + mlx5_devlink_set_params_init_values(devlink); + devlink_params_publish(devlink); + return 0; + +params_reg_err: + devlink_unregister(devlink); + return err; } void mlx5_devlink_unregister(struct devlink *devlink) { + devlink_params_unregister(devlink, mlx5_devlink_params, + ARRAY_SIZE(mlx5_devlink_params)); devlink_unregister(devlink); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/en_rep_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/en_rep_tracepoint.h new file mode 100644 index 000000000000..1177860a2ee4 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/en_rep_tracepoint.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_EN_REP_TP_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_EN_REP_TP_ + +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> +#include "en_rep.h" + +TRACE_EVENT(mlx5e_rep_neigh_update, + TP_PROTO(const struct mlx5e_neigh_hash_entry *nhe, const u8 *ha, + bool neigh_connected), + TP_ARGS(nhe, ha, neigh_connected), + TP_STRUCT__entry(__string(devname, nhe->m_neigh.dev->name) + __array(u8, ha, ETH_ALEN) + __array(u8, v4, 4) + __array(u8, v6, 16) + __field(bool, neigh_connected) + ), + TP_fast_assign(const struct mlx5e_neigh *mn = &nhe->m_neigh; + struct in6_addr *pin6; + __be32 *p32; + + __assign_str(devname, mn->dev->name); + __entry->neigh_connected = neigh_connected; + memcpy(__entry->ha, ha, ETH_ALEN); + + p32 = (__be32 *)__entry->v4; + pin6 = (struct in6_addr *)__entry->v6; + if (mn->family == AF_INET) { + *p32 = mn->dst_ip.v4; + ipv6_addr_set_v4mapped(*p32, pin6); + } else if (mn->family == AF_INET6) { + *pin6 = mn->dst_ip.v6; + } + ), + TP_printk("netdev: %s MAC: %pM IPv4: %pI4 IPv6: %pI6c neigh_connected=%d\n", + __get_str(devname), __entry->ha, + __entry->v4, __entry->v6, __entry->neigh_connected + ) +); + +#endif /* _MLX5_EN_REP_TP_ */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ./diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE en_rep_tracepoint +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/en_tc_tracepoint.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/en_tc_tracepoint.c new file mode 100644 index 000000000000..c5dc6c50fa87 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/en_tc_tracepoint.c @@ -0,0 +1,58 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#define CREATE_TRACE_POINTS +#include "en_tc_tracepoint.h" + +void put_ids_to_array(int *ids, + const struct flow_action_entry *entries, + unsigned int num) +{ + unsigned int i; + + for (i = 0; i < num; i++) + ids[i] = entries[i].id; +} + +#define NAME_SIZE 16 + +static const char FLOWACT2STR[NUM_FLOW_ACTIONS][NAME_SIZE] = { + [FLOW_ACTION_ACCEPT] = "ACCEPT", + [FLOW_ACTION_DROP] = "DROP", + [FLOW_ACTION_TRAP] = "TRAP", + [FLOW_ACTION_GOTO] = "GOTO", + [FLOW_ACTION_REDIRECT] = "REDIRECT", + [FLOW_ACTION_MIRRED] = "MIRRED", + [FLOW_ACTION_VLAN_PUSH] = "VLAN_PUSH", + [FLOW_ACTION_VLAN_POP] = "VLAN_POP", + [FLOW_ACTION_VLAN_MANGLE] = "VLAN_MANGLE", + [FLOW_ACTION_TUNNEL_ENCAP] = "TUNNEL_ENCAP", + [FLOW_ACTION_TUNNEL_DECAP] = "TUNNEL_DECAP", + [FLOW_ACTION_MANGLE] = "MANGLE", + [FLOW_ACTION_ADD] = "ADD", + [FLOW_ACTION_CSUM] = "CSUM", + [FLOW_ACTION_MARK] = "MARK", + [FLOW_ACTION_WAKE] = "WAKE", + [FLOW_ACTION_QUEUE] = "QUEUE", + [FLOW_ACTION_SAMPLE] = "SAMPLE", + [FLOW_ACTION_POLICE] = "POLICE", + [FLOW_ACTION_CT] = "CT", +}; + +const char *parse_action(struct trace_seq *p, + int *ids, + unsigned int num) +{ + const char *ret = trace_seq_buffer_ptr(p); + unsigned int i; + + for (i = 0; i < num; i++) { + if (ids[i] < NUM_FLOW_ACTIONS) + trace_seq_printf(p, "%s ", FLOWACT2STR[ids[i]]); + else + trace_seq_printf(p, "UNKNOWN "); + } + + trace_seq_putc(p, 0); + return ret; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/en_tc_tracepoint.h b/drivers/net/ethernet/mellanox/mlx5/core/diag/en_tc_tracepoint.h new file mode 100644 index 000000000000..d4e6cfaaade3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/en_tc_tracepoint.h @@ -0,0 +1,114 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#undef TRACE_SYSTEM +#define TRACE_SYSTEM mlx5 + +#if !defined(_MLX5_TC_TP_) || defined(TRACE_HEADER_MULTI_READ) +#define _MLX5_TC_TP_ + +#include <linux/tracepoint.h> +#include <linux/trace_seq.h> +#include <net/flow_offload.h> +#include "en_rep.h" + +#define __parse_action(ids, num) parse_action(p, ids, num) + +void put_ids_to_array(int *ids, + const struct flow_action_entry *entries, + unsigned int num); + +const char *parse_action(struct trace_seq *p, + int *ids, + unsigned int num); + +DECLARE_EVENT_CLASS(mlx5e_flower_template, + TP_PROTO(const struct flow_cls_offload *f), + TP_ARGS(f), + TP_STRUCT__entry(__field(void *, cookie) + __field(unsigned int, num) + __dynamic_array(int, ids, f->rule ? + f->rule->action.num_entries : 0) + ), + TP_fast_assign(__entry->cookie = (void *)f->cookie; + __entry->num = (f->rule ? + f->rule->action.num_entries : 0); + if (__entry->num) + put_ids_to_array(__get_dynamic_array(ids), + f->rule->action.entries, + f->rule->action.num_entries); + ), + TP_printk("cookie=%p actions= %s\n", + __entry->cookie, __entry->num ? + __parse_action(__get_dynamic_array(ids), + __entry->num) : "NULL" + ) +); + +DEFINE_EVENT(mlx5e_flower_template, mlx5e_configure_flower, + TP_PROTO(const struct flow_cls_offload *f), + TP_ARGS(f) + ); + +DEFINE_EVENT(mlx5e_flower_template, mlx5e_delete_flower, + TP_PROTO(const struct flow_cls_offload *f), + TP_ARGS(f) + ); + +TRACE_EVENT(mlx5e_stats_flower, + TP_PROTO(const struct flow_cls_offload *f), + TP_ARGS(f), + TP_STRUCT__entry(__field(void *, cookie) + __field(u64, bytes) + __field(u64, packets) + __field(u64, lastused) + ), + TP_fast_assign(__entry->cookie = (void *)f->cookie; + __entry->bytes = f->stats.bytes; + __entry->packets = f->stats.pkts; + __entry->lastused = f->stats.lastused; + ), + TP_printk("cookie=%p bytes=%llu packets=%llu lastused=%llu\n", + __entry->cookie, __entry->bytes, + __entry->packets, __entry->lastused + ) +); + +TRACE_EVENT(mlx5e_tc_update_neigh_used_value, + TP_PROTO(const struct mlx5e_neigh_hash_entry *nhe, bool neigh_used), + TP_ARGS(nhe, neigh_used), + TP_STRUCT__entry(__string(devname, nhe->m_neigh.dev->name) + __array(u8, v4, 4) + __array(u8, v6, 16) + __field(bool, neigh_used) + ), + TP_fast_assign(const struct mlx5e_neigh *mn = &nhe->m_neigh; + struct in6_addr *pin6; + __be32 *p32; + + __assign_str(devname, mn->dev->name); + __entry->neigh_used = neigh_used; + + p32 = (__be32 *)__entry->v4; + pin6 = (struct in6_addr *)__entry->v6; + if (mn->family == AF_INET) { + *p32 = mn->dst_ip.v4; + ipv6_addr_set_v4mapped(*p32, pin6); + } else if (mn->family == AF_INET6) { + *pin6 = mn->dst_ip.v6; + } + ), + TP_printk("netdev: %s IPv4: %pI4 IPv6: %pI6c neigh_used=%d\n", + __get_str(devname), __entry->v4, __entry->v6, + __entry->neigh_used + ) +); + +#endif /* _MLX5_TC_TP_ */ + +/* This part must be outside protection */ +#undef TRACE_INCLUDE_PATH +#define TRACE_INCLUDE_PATH ./diag +#undef TRACE_INCLUDE_FILE +#define TRACE_INCLUDE_FILE en_tc_tracepoint +#include <trace/define_trace.h> diff --git a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c index 8a4930c8bf62..94d7b69a95c7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/diag/fw_tracer.c @@ -546,16 +546,17 @@ static void mlx5_fw_tracer_save_trace(struct mlx5_fw_tracer *tracer, trace_data->timestamp = timestamp; trace_data->lost = lost; trace_data->event_id = event_id; - strncpy(trace_data->msg, msg, TRACE_STR_MSG); + strscpy_pad(trace_data->msg, msg, TRACE_STR_MSG); tracer->st_arr.saved_traces_index = (tracer->st_arr.saved_traces_index + 1) & (SAVED_TRACES_NUM - 1); mutex_unlock(&tracer->st_arr.lock); } -static void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt, - struct mlx5_core_dev *dev, - u64 trace_timestamp) +static noinline +void mlx5_tracer_print_trace(struct tracer_string_format *str_frmt, + struct mlx5_core_dev *dev, + u64 trace_timestamp) { char tmp[512]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 65bec19a438f..8d76452cacdc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -54,6 +54,7 @@ #include "mlx5_core.h" #include "en_stats.h" #include "en/fs.h" +#include "lib/hv_vhca.h" extern const struct net_device_ops mlx5e_netdev_ops; struct page_pool; @@ -162,6 +163,14 @@ enum mlx5e_rq_group { #define MLX5E_NUM_RQ_GROUPS(g) (1 + MLX5E_RQ_GROUP_##g) }; +static inline u8 mlx5e_get_num_lag_ports(struct mlx5_core_dev *mdev) +{ + if (mlx5_lag_is_lacp_owner(mdev)) + return 1; + + return clamp_t(u8, MLX5_CAP_GEN(mdev, num_lag_ports), 1, MLX5_MAX_PORTS); +} + static inline u16 mlx5_min_rx_wqes(int wq_type, u32 wq_size) { switch (wq_type) { @@ -300,6 +309,7 @@ struct mlx5e_dcbx_dp { enum { MLX5E_RQ_STATE_ENABLED, + MLX5E_RQ_STATE_RECOVERING, MLX5E_RQ_STATE_AM, MLX5E_RQ_STATE_NO_CSUM_COMPLETE, MLX5E_RQ_STATE_CSUM_FULL, /* cqe_csum_full hw bit is set */ @@ -356,6 +366,7 @@ enum { MLX5E_SQ_STATE_IPSEC, MLX5E_SQ_STATE_AM, MLX5E_SQ_STATE_TLS, + MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, }; struct mlx5e_sq_wqe_info { @@ -480,8 +491,6 @@ struct mlx5e_xdp_mpwqe { struct mlx5e_tx_wqe *wqe; u8 ds_count; u8 pkt_count; - u8 max_ds_count; - u8 complete; u8 inline_on; }; @@ -552,6 +561,8 @@ struct mlx5e_icosq { /* control path */ struct mlx5_wq_ctrl wq_ctrl; struct mlx5e_channel *channel; + + struct work_struct recover_work; } ____cacheline_aligned_in_smp; struct mlx5e_wqe_frag_info { @@ -671,6 +682,8 @@ struct mlx5e_rq { struct zero_copy_allocator zca; struct xdp_umem *umem; + struct work_struct recover_work; + /* control */ struct mlx5_wq_ctrl wq_ctrl; __be32 mkey_be; @@ -700,6 +713,7 @@ struct mlx5e_channel { struct net_device *netdev; __be32 mkey_be; u8 num_tc; + u8 lag_port; /* XDP_REDIRECT */ struct mlx5e_xdpsq xdpsq; @@ -778,6 +792,15 @@ struct mlx5e_modify_sq_param { int rl_index; }; +#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE) +struct mlx5e_hv_vhca_stats_agent { + struct mlx5_hv_vhca_agent *agent; + struct delayed_work work; + u16 delay; + void *buf; +}; +#endif + struct mlx5e_xsk { /* UMEMs are stored separately from channels, because we don't want to * lose them when channels are recreated. The kernel also stores UMEMs, @@ -804,7 +827,7 @@ struct mlx5e_priv { struct mlx5e_rq drop_rq; struct mlx5e_channels channels; - u32 tisn[MLX5E_MAX_NUM_TC]; + u32 tisn[MLX5_MAX_PORTS][MLX5E_MAX_NUM_TC]; struct mlx5e_rqt indir_rqt; struct mlx5e_tir indir_tir[MLX5E_NUM_INDIR_TIRS]; struct mlx5e_tir inner_indir_tir[MLX5E_NUM_INDIR_TIRS]; @@ -847,7 +870,11 @@ struct mlx5e_priv { struct mlx5e_tls *tls; #endif struct devlink_health_reporter *tx_reporter; + struct devlink_health_reporter *rx_reporter; struct mlx5e_xsk xsk; +#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE) + struct mlx5e_hv_vhca_stats_agent stats_agent; +#endif }; struct mlx5e_profile { @@ -888,6 +915,26 @@ bool mlx5e_poll_tx_cq(struct mlx5e_cq *cq, int napi_budget); int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget); void mlx5e_free_txqsq_descs(struct mlx5e_txqsq *sq); +static inline u32 mlx5e_rqwq_get_size(struct mlx5e_rq *rq) +{ + switch (rq->wq_type) { + case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: + return mlx5_wq_ll_get_size(&rq->mpwqe.wq); + default: + return mlx5_wq_cyc_get_size(&rq->wqe.wq); + } +} + +static inline u32 mlx5e_rqwq_get_cur_sz(struct mlx5e_rq *rq) +{ + switch (rq->wq_type) { + case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: + return rq->mpwqe.wq.cur_sz; + default: + return rq->wqe.wq.cur_sz; + } +} + bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev); bool mlx5e_striding_rq_possible(struct mlx5_core_dev *mdev, struct mlx5e_params *params); @@ -1006,18 +1053,18 @@ void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, void mlx5e_set_rq_type(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_init_rq_type_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); +int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state); +void mlx5e_activate_rq(struct mlx5e_rq *rq); +void mlx5e_deactivate_rq(struct mlx5e_rq *rq); +void mlx5e_free_rx_descs(struct mlx5e_rq *rq); +void mlx5e_activate_icosq(struct mlx5e_icosq *icosq); +void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq); int mlx5e_modify_sq(struct mlx5_core_dev *mdev, u32 sqn, struct mlx5e_modify_sq_param *p); void mlx5e_activate_txqsq(struct mlx5e_txqsq *sq); void mlx5e_tx_disable_queue(struct netdev_queue *txq); -static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) -{ - return (MLX5_CAP_ETH(mdev, tunnel_stateless_gre) && - MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version)); -} - static inline bool mlx5_tx_swp_supported(struct mlx5_core_dev *mdev) { return MLX5_CAP_ETH(mdev, swp) && @@ -1063,6 +1110,7 @@ int mlx5e_create_tis(struct mlx5_core_dev *mdev, void *in, u32 *tisn); void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn); int mlx5e_create_tises(struct mlx5e_priv *priv); +void mlx5e_destroy_tises(struct mlx5e_priv *priv); int mlx5e_update_nic_rx(struct mlx5e_priv *priv); void mlx5e_update_carrier(struct mlx5e_priv *priv); int mlx5e_close(struct net_device *netdev); @@ -1135,7 +1183,6 @@ void mlx5e_build_rq_params(struct mlx5_core_dev *mdev, struct mlx5e_params *params); void mlx5e_build_rss_params(struct mlx5e_rss_params *rss_params, u16 num_channels); -u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev); void mlx5e_rx_dim_work(struct work_struct *work); void mlx5e_tx_dim_work(struct work_struct *work); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h index be5961ff24cc..68d593074f6c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/fs.h @@ -10,11 +10,14 @@ enum { }; struct mlx5e_tc_table { + /* protects flow table */ + struct mutex t_lock; struct mlx5_flow_table *t; struct rhashtable ht; - DECLARE_HASHTABLE(mod_hdr_tbl, 8); + struct mod_hdr_tbl mod_hdr; + struct mutex hairpin_tbl_lock; /* protects hairpin_tbl */ DECLARE_HASHTABLE(hairpin_tbl, 8); struct notifier_block netdevice_nb; @@ -92,9 +95,15 @@ struct mlx5e_tirc_config { enum mlx5e_tunnel_types { MLX5E_TT_IPV4_GRE, MLX5E_TT_IPV6_GRE, + MLX5E_TT_IPV4_IPIP, + MLX5E_TT_IPV6_IPIP, + MLX5E_TT_IPV4_IPV6, + MLX5E_TT_IPV6_IPV6, MLX5E_NUM_TUNNEL_TT, }; +bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev); + /* L3/L4 traffic type classifier */ struct mlx5e_ttc_table { struct mlx5e_flow_table ft; @@ -132,12 +141,17 @@ struct mlx5e_ethtool_steering { void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv); void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv); -int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd); -int mlx5e_get_rxnfc(struct net_device *dev, - struct ethtool_rxnfc *info, u32 *rule_locs); +int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd); +int mlx5e_ethtool_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *info, u32 *rule_locs); #else static inline void mlx5e_ethtool_init_steering(struct mlx5e_priv *priv) { } static inline void mlx5e_ethtool_cleanup_steering(struct mlx5e_priv *priv) { } +static inline int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ return -EOPNOTSUPP; } +static inline int mlx5e_ethtool_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *info, u32 *rule_locs) +{ return -EOPNOTSUPP; } #endif /* CONFIG_MLX5_EN_RXNFC */ #ifdef CONFIG_MLX5_EN_ARFS @@ -224,5 +238,8 @@ void mlx5e_disable_cvlan_filter(struct mlx5e_priv *priv); int mlx5e_create_flow_steering(struct mlx5e_priv *priv); void mlx5e_destroy_flow_steering(struct mlx5e_priv *priv); +bool mlx5e_tunnel_proto_supported(struct mlx5_core_dev *mdev, u8 proto_type); +bool mlx5e_any_tunnel_proto_supported(struct mlx5_core_dev *mdev); + #endif /* __MLX5E_FLOW_STEER_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.c b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c new file mode 100644 index 000000000000..1d6b58860da6 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.c @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Mellanox Technologies. + +#include "health.h" +#include "lib/eq.h" + +int mlx5e_reporter_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + return err; + + return 0; +} + +int mlx5e_reporter_named_obj_nest_end(struct devlink_fmsg *fmsg) +{ + int err; + + err = devlink_fmsg_obj_nest_end(fmsg); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} + +int mlx5e_reporter_cq_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg) +{ + struct mlx5e_priv *priv = cq->channel->priv; + u32 out[MLX5_ST_SZ_DW(query_cq_out)] = {}; + u8 hw_status; + void *cqc; + int err; + + err = mlx5_core_query_cq(priv->mdev, &cq->mcq, out, sizeof(out)); + if (err) + return err; + + cqc = MLX5_ADDR_OF(query_cq_out, out, cq_context); + hw_status = MLX5_GET(cqc, cqc, status); + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "CQ"); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "cqn", cq->mcq.cqn); + if (err) + return err; + + err = devlink_fmsg_u8_pair_put(fmsg, "HW status", hw_status); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + return 0; +} + +int mlx5e_reporter_cq_common_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg) +{ + u8 cq_log_stride; + u32 cq_sz; + int err; + + cq_sz = mlx5_cqwq_get_size(&cq->wq); + cq_log_stride = mlx5_cqwq_get_log_stride_size(&cq->wq); + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "CQ"); + if (err) + return err; + + err = devlink_fmsg_u64_pair_put(fmsg, "stride size", BIT(cq_log_stride)); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "size", cq_sz); + if (err) + return err; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + return err; + + return 0; +} + +int mlx5e_health_create_reporters(struct mlx5e_priv *priv) +{ + int err; + + err = mlx5e_reporter_tx_create(priv); + if (err) + return err; + + err = mlx5e_reporter_rx_create(priv); + if (err) + return err; + + return 0; +} + +void mlx5e_health_destroy_reporters(struct mlx5e_priv *priv) +{ + mlx5e_reporter_rx_destroy(priv); + mlx5e_reporter_tx_destroy(priv); +} + +void mlx5e_health_channels_update(struct mlx5e_priv *priv) +{ + if (priv->tx_reporter) + devlink_health_reporter_state_update(priv->tx_reporter, + DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); + if (priv->rx_reporter) + devlink_health_reporter_state_update(priv->rx_reporter, + DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); +} + +int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn) +{ + struct mlx5_core_dev *mdev = channel->mdev; + struct net_device *dev = channel->netdev; + struct mlx5e_modify_sq_param msp = {}; + int err; + + msp.curr_state = MLX5_SQC_STATE_ERR; + msp.next_state = MLX5_SQC_STATE_RST; + + err = mlx5e_modify_sq(mdev, sqn, &msp); + if (err) { + netdev_err(dev, "Failed to move sq 0x%x to reset\n", sqn); + return err; + } + + memset(&msp, 0, sizeof(msp)); + msp.curr_state = MLX5_SQC_STATE_RST; + msp.next_state = MLX5_SQC_STATE_RDY; + + err = mlx5e_modify_sq(mdev, sqn, &msp); + if (err) { + netdev_err(dev, "Failed to move sq 0x%x to ready\n", sqn); + return err; + } + + return 0; +} + +int mlx5e_health_recover_channels(struct mlx5e_priv *priv) +{ + int err = 0; + + rtnl_lock(); + mutex_lock(&priv->state_lock); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto out; + + err = mlx5e_safe_reopen_channels(priv); + +out: + mutex_unlock(&priv->state_lock); + rtnl_unlock(); + + return err; +} + +int mlx5e_health_channel_eq_recover(struct mlx5_eq_comp *eq, struct mlx5e_channel *channel) +{ + u32 eqe_count; + + netdev_err(channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", + eq->core.eqn, eq->core.cons_index, eq->core.irqn); + + eqe_count = mlx5_eq_poll_irq_disabled(eq); + if (!eqe_count) + return -EIO; + + netdev_err(channel->netdev, "Recovered %d eqes on EQ 0x%x\n", + eqe_count, eq->core.eqn); + + channel->stats->eq_rearm++; + return 0; +} + +int mlx5e_health_report(struct mlx5e_priv *priv, + struct devlink_health_reporter *reporter, char *err_str, + struct mlx5e_err_ctx *err_ctx) +{ + if (!reporter) { + netdev_err(priv->netdev, err_str); + return err_ctx->recover(&err_ctx->ctx); + } + return devlink_health_report(reporter, err_str, err_ctx); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/health.h b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h new file mode 100644 index 000000000000..d3693fa547ac --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/health.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5E_EN_HEALTH_H +#define __MLX5E_EN_HEALTH_H + +#include "en.h" + +#define MLX5E_RX_ERR_CQE(cqe) (get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND) + +static inline bool cqe_syndrome_needs_recover(u8 syndrome) +{ + return syndrome == MLX5_CQE_SYNDROME_LOCAL_LENGTH_ERR || + syndrome == MLX5_CQE_SYNDROME_LOCAL_QP_OP_ERR || + syndrome == MLX5_CQE_SYNDROME_LOCAL_PROT_ERR || + syndrome == MLX5_CQE_SYNDROME_WR_FLUSH_ERR; +} + +int mlx5e_reporter_tx_create(struct mlx5e_priv *priv); +void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv); +void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq); +int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq); + +int mlx5e_reporter_cq_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg); +int mlx5e_reporter_cq_common_diagnose(struct mlx5e_cq *cq, struct devlink_fmsg *fmsg); +int mlx5e_reporter_named_obj_nest_start(struct devlink_fmsg *fmsg, char *name); +int mlx5e_reporter_named_obj_nest_end(struct devlink_fmsg *fmsg); + +int mlx5e_reporter_rx_create(struct mlx5e_priv *priv); +void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv); +void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq); +void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq); +void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq); + +#define MLX5E_REPORTER_PER_Q_MAX_LEN 256 + +struct mlx5e_err_ctx { + int (*recover)(void *ctx); + void *ctx; +}; + +int mlx5e_health_sq_to_ready(struct mlx5e_channel *channel, u32 sqn); +int mlx5e_health_channel_eq_recover(struct mlx5_eq_comp *eq, struct mlx5e_channel *channel); +int mlx5e_health_recover_channels(struct mlx5e_priv *priv); +int mlx5e_health_report(struct mlx5e_priv *priv, + struct devlink_health_reporter *reporter, char *err_str, + struct mlx5e_err_ctx *err_ctx); +int mlx5e_health_create_reporters(struct mlx5e_priv *priv); +void mlx5e_health_destroy_reporters(struct mlx5e_priv *priv); +void mlx5e_health_channels_update(struct mlx5e_priv *priv); + + +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c new file mode 100644 index 000000000000..b3a249b2a482 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2018 Mellanox Technologies + +#include "en.h" +#include "en/hv_vhca_stats.h" +#include "lib/hv_vhca.h" +#include "lib/hv.h" + +struct mlx5e_hv_vhca_per_ring_stats { + u64 rx_packets; + u64 rx_bytes; + u64 tx_packets; + u64 tx_bytes; +}; + +static void +mlx5e_hv_vhca_fill_ring_stats(struct mlx5e_priv *priv, int ch, + struct mlx5e_hv_vhca_per_ring_stats *data) +{ + struct mlx5e_channel_stats *stats; + int tc; + + stats = &priv->channel_stats[ch]; + data->rx_packets = stats->rq.packets; + data->rx_bytes = stats->rq.bytes; + + for (tc = 0; tc < priv->max_opened_tc; tc++) { + data->tx_packets += stats->sq[tc].packets; + data->tx_bytes += stats->sq[tc].bytes; + } +} + +static void mlx5e_hv_vhca_fill_stats(struct mlx5e_priv *priv, void *data, + int buf_len) +{ + int ch, i = 0; + + for (ch = 0; ch < priv->max_nch; ch++) { + void *buf = data + i; + + if (WARN_ON_ONCE(buf + + sizeof(struct mlx5e_hv_vhca_per_ring_stats) > + data + buf_len)) + return; + + mlx5e_hv_vhca_fill_ring_stats(priv, ch, buf); + i += sizeof(struct mlx5e_hv_vhca_per_ring_stats); + } +} + +static int mlx5e_hv_vhca_stats_buf_size(struct mlx5e_priv *priv) +{ + return (sizeof(struct mlx5e_hv_vhca_per_ring_stats) * + priv->max_nch); +} + +static void mlx5e_hv_vhca_stats_work(struct work_struct *work) +{ + struct mlx5e_hv_vhca_stats_agent *sagent; + struct mlx5_hv_vhca_agent *agent; + struct delayed_work *dwork; + struct mlx5e_priv *priv; + int buf_len, rc; + void *buf; + + dwork = to_delayed_work(work); + sagent = container_of(dwork, struct mlx5e_hv_vhca_stats_agent, work); + priv = container_of(sagent, struct mlx5e_priv, stats_agent); + buf_len = mlx5e_hv_vhca_stats_buf_size(priv); + agent = sagent->agent; + buf = sagent->buf; + + memset(buf, 0, buf_len); + mlx5e_hv_vhca_fill_stats(priv, buf, buf_len); + + rc = mlx5_hv_vhca_agent_write(agent, buf, buf_len); + if (rc) { + mlx5_core_err(priv->mdev, + "%s: Failed to write stats, err = %d\n", + __func__, rc); + return; + } + + if (sagent->delay) + queue_delayed_work(priv->wq, &sagent->work, sagent->delay); +} + +enum { + MLX5_HV_VHCA_STATS_VERSION = 1, + MLX5_HV_VHCA_STATS_UPDATE_ONCE = 0xFFFF, +}; + +static void mlx5e_hv_vhca_stats_control(struct mlx5_hv_vhca_agent *agent, + struct mlx5_hv_vhca_control_block *block) +{ + struct mlx5e_hv_vhca_stats_agent *sagent; + struct mlx5e_priv *priv; + + priv = mlx5_hv_vhca_agent_priv(agent); + sagent = &priv->stats_agent; + + block->version = MLX5_HV_VHCA_STATS_VERSION; + block->rings = priv->max_nch; + + if (!block->command) { + cancel_delayed_work_sync(&priv->stats_agent.work); + return; + } + + sagent->delay = block->command == MLX5_HV_VHCA_STATS_UPDATE_ONCE ? 0 : + msecs_to_jiffies(block->command * 100); + + queue_delayed_work(priv->wq, &sagent->work, sagent->delay); +} + +static void mlx5e_hv_vhca_stats_cleanup(struct mlx5_hv_vhca_agent *agent) +{ + struct mlx5e_priv *priv = mlx5_hv_vhca_agent_priv(agent); + + cancel_delayed_work_sync(&priv->stats_agent.work); +} + +int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv) +{ + int buf_len = mlx5e_hv_vhca_stats_buf_size(priv); + struct mlx5_hv_vhca_agent *agent; + + priv->stats_agent.buf = kvzalloc(buf_len, GFP_KERNEL); + if (!priv->stats_agent.buf) + return -ENOMEM; + + agent = mlx5_hv_vhca_agent_create(priv->mdev->hv_vhca, + MLX5_HV_VHCA_AGENT_STATS, + mlx5e_hv_vhca_stats_control, NULL, + mlx5e_hv_vhca_stats_cleanup, + priv); + + if (IS_ERR_OR_NULL(agent)) { + if (IS_ERR(agent)) + netdev_warn(priv->netdev, + "Failed to create hv vhca stats agent, err = %ld\n", + PTR_ERR(agent)); + + kfree(priv->stats_agent.buf); + return IS_ERR_OR_NULL(agent); + } + + priv->stats_agent.agent = agent; + INIT_DELAYED_WORK(&priv->stats_agent.work, mlx5e_hv_vhca_stats_work); + + return 0; +} + +void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv) +{ + if (IS_ERR_OR_NULL(priv->stats_agent.agent)) + return; + + mlx5_hv_vhca_agent_destroy(priv->stats_agent.agent); + kfree(priv->stats_agent.buf); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.h new file mode 100644 index 000000000000..664463faf77b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/hv_vhca_stats.h @@ -0,0 +1,25 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __MLX5_EN_STATS_VHCA_H__ +#define __MLX5_EN_STATS_VHCA_H__ +#include "en.h" + +#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE) + +int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv); +void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv); + +#else + +static inline int mlx5e_hv_vhca_stats_create(struct mlx5e_priv *priv) +{ + return 0; +} + +static inline void mlx5e_hv_vhca_stats_destroy(struct mlx5e_priv *priv) +{ +} +#endif + +#endif /* __MLX5_EN_STATS_VHCA_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c index 79301d116667..eb2e1f2138e4 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c @@ -25,18 +25,33 @@ u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params, return headroom; } -u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params, - struct mlx5e_xsk_param *xsk) +u32 mlx5e_rx_get_min_frag_sz(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) { u32 hw_mtu = MLX5E_SW2HW_MTU(params, params->sw_mtu); u16 linear_rq_headroom = mlx5e_get_linear_rq_headroom(params, xsk); - u32 frag_sz = linear_rq_headroom + hw_mtu; + + return linear_rq_headroom + hw_mtu; +} + +u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk) +{ + u32 frag_sz = mlx5e_rx_get_min_frag_sz(params, xsk); /* AF_XDP doesn't build SKBs in place. */ if (!xsk) frag_sz = MLX5_SKB_FRAG_SZ(frag_sz); - /* XDP in mlx5e doesn't support multiple packets per page. */ + /* XDP in mlx5e doesn't support multiple packets per page. AF_XDP is a + * special case. It can run with frames smaller than a page, as it + * doesn't allocate pages dynamically. However, here we pretend that + * fragments are page-sized: it allows to treat XSK frames like pages + * by redirecting alloc and free operations to XSK rings and by using + * the fact there are no multiple packets per "page" (which is a frame). + * The latter is important, because frames may come in a random order, + * and we will have trouble assemblying a real page of multiple frames. + */ if (mlx5e_rx_is_xdp(params, xsk)) frag_sz = max_t(u32, frag_sz, PAGE_SIZE); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h index 3a615d663d84..989d8f429438 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.h @@ -76,6 +76,8 @@ static inline bool mlx5e_qid_validate(const struct mlx5e_profile *profile, u16 mlx5e_get_linear_rq_headroom(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); +u32 mlx5e_rx_get_min_frag_sz(struct mlx5e_params *params, + struct mlx5e_xsk_param *xsk); u32 mlx5e_rx_get_linear_frag_sz(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); u8 mlx5e_mpwqe_log_pkts_per_wqe(struct mlx5e_params *params, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h deleted file mode 100644 index e78e92753d73..000000000000 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter.h +++ /dev/null @@ -1,15 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (c) 2019 Mellanox Technologies. */ - -#ifndef __MLX5E_EN_REPORTER_H -#define __MLX5E_EN_REPORTER_H - -#include <linux/mlx5/driver.h> -#include "en.h" - -int mlx5e_tx_reporter_create(struct mlx5e_priv *priv); -void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv); -void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq); -int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq); - -#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c new file mode 100644 index 000000000000..b860569d4247 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -0,0 +1,404 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2019 Mellanox Technologies. + +#include "health.h" +#include "params.h" + +static int mlx5e_query_rq_state(struct mlx5_core_dev *dev, u32 rqn, u8 *state) +{ + int outlen = MLX5_ST_SZ_BYTES(query_rq_out); + void *out; + void *rqc; + int err; + + out = kvzalloc(outlen, GFP_KERNEL); + if (!out) + return -ENOMEM; + + err = mlx5_core_query_rq(dev, rqn, out); + if (err) + goto out; + + rqc = MLX5_ADDR_OF(query_rq_out, out, rq_context); + *state = MLX5_GET(rqc, rqc, state); + +out: + kvfree(out); + return err; +} + +static int mlx5e_wait_for_icosq_flush(struct mlx5e_icosq *icosq) +{ + unsigned long exp_time = jiffies + msecs_to_jiffies(2000); + + while (time_before(jiffies, exp_time)) { + if (icosq->cc == icosq->pc) + return 0; + + msleep(20); + } + + netdev_err(icosq->channel->netdev, + "Wait for ICOSQ 0x%x flush timeout (cc = 0x%x, pc = 0x%x)\n", + icosq->sqn, icosq->cc, icosq->pc); + + return -ETIMEDOUT; +} + +static void mlx5e_reset_icosq_cc_pc(struct mlx5e_icosq *icosq) +{ + WARN_ONCE(icosq->cc != icosq->pc, "ICOSQ 0x%x: cc (0x%x) != pc (0x%x)\n", + icosq->sqn, icosq->cc, icosq->pc); + icosq->cc = 0; + icosq->pc = 0; +} + +static int mlx5e_rx_reporter_err_icosq_cqe_recover(void *ctx) +{ + struct mlx5_core_dev *mdev; + struct mlx5e_icosq *icosq; + struct net_device *dev; + struct mlx5e_rq *rq; + u8 state; + int err; + + icosq = ctx; + rq = &icosq->channel->rq; + mdev = icosq->channel->mdev; + dev = icosq->channel->netdev; + err = mlx5_core_query_sq_state(mdev, icosq->sqn, &state); + if (err) { + netdev_err(dev, "Failed to query ICOSQ 0x%x state. err = %d\n", + icosq->sqn, err); + goto out; + } + + if (state != MLX5_SQC_STATE_ERR) + goto out; + + mlx5e_deactivate_rq(rq); + err = mlx5e_wait_for_icosq_flush(icosq); + if (err) + goto out; + + mlx5e_deactivate_icosq(icosq); + + /* At this point, both the rq and the icosq are disabled */ + + err = mlx5e_health_sq_to_ready(icosq->channel, icosq->sqn); + if (err) + goto out; + + mlx5e_reset_icosq_cc_pc(icosq); + mlx5e_free_rx_descs(rq); + clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state); + mlx5e_activate_icosq(icosq); + mlx5e_activate_rq(rq); + + rq->stats->recover++; + return 0; +out: + clear_bit(MLX5E_SQ_STATE_RECOVERING, &icosq->state); + return err; +} + +void mlx5e_reporter_icosq_cqe_err(struct mlx5e_icosq *icosq) +{ + struct mlx5e_priv *priv = icosq->channel->priv; + char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_err_ctx err_ctx = {}; + + err_ctx.ctx = icosq; + err_ctx.recover = mlx5e_rx_reporter_err_icosq_cqe_recover; + sprintf(err_str, "ERR CQE on ICOSQ: 0x%x", icosq->sqn); + + mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); +} + +static int mlx5e_rq_to_ready(struct mlx5e_rq *rq, int curr_state) +{ + struct net_device *dev = rq->netdev; + int err; + + err = mlx5e_modify_rq_state(rq, curr_state, MLX5_RQC_STATE_RST); + if (err) { + netdev_err(dev, "Failed to move rq 0x%x to reset\n", rq->rqn); + return err; + } + err = mlx5e_modify_rq_state(rq, MLX5_RQC_STATE_RST, MLX5_RQC_STATE_RDY); + if (err) { + netdev_err(dev, "Failed to move rq 0x%x to ready\n", rq->rqn); + return err; + } + + return 0; +} + +static int mlx5e_rx_reporter_err_rq_cqe_recover(void *ctx) +{ + struct mlx5_core_dev *mdev; + struct net_device *dev; + struct mlx5e_rq *rq; + u8 state; + int err; + + rq = ctx; + mdev = rq->mdev; + dev = rq->netdev; + err = mlx5e_query_rq_state(mdev, rq->rqn, &state); + if (err) { + netdev_err(dev, "Failed to query RQ 0x%x state. err = %d\n", + rq->rqn, err); + goto out; + } + + if (state != MLX5_RQC_STATE_ERR) + goto out; + + mlx5e_deactivate_rq(rq); + mlx5e_free_rx_descs(rq); + + err = mlx5e_rq_to_ready(rq, MLX5_RQC_STATE_ERR); + if (err) + goto out; + + clear_bit(MLX5E_RQ_STATE_RECOVERING, &rq->state); + mlx5e_activate_rq(rq); + rq->stats->recover++; + return 0; +out: + clear_bit(MLX5E_RQ_STATE_RECOVERING, &rq->state); + return err; +} + +void mlx5e_reporter_rq_cqe_err(struct mlx5e_rq *rq) +{ + struct mlx5e_priv *priv = rq->channel->priv; + char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_err_ctx err_ctx = {}; + + err_ctx.ctx = rq; + err_ctx.recover = mlx5e_rx_reporter_err_rq_cqe_recover; + sprintf(err_str, "ERR CQE on RQ: 0x%x", rq->rqn); + + mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); +} + +static int mlx5e_rx_reporter_timeout_recover(void *ctx) +{ + struct mlx5e_icosq *icosq; + struct mlx5_eq_comp *eq; + struct mlx5e_rq *rq; + int err; + + rq = ctx; + icosq = &rq->channel->icosq; + eq = rq->cq.mcq.eq; + err = mlx5e_health_channel_eq_recover(eq, rq->channel); + if (err) + clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state); + + return err; +} + +void mlx5e_reporter_rx_timeout(struct mlx5e_rq *rq) +{ + struct mlx5e_icosq *icosq = &rq->channel->icosq; + struct mlx5e_priv *priv = rq->channel->priv; + char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_err_ctx err_ctx = {}; + + err_ctx.ctx = rq; + err_ctx.recover = mlx5e_rx_reporter_timeout_recover; + sprintf(err_str, "RX timeout on channel: %d, ICOSQ: 0x%x RQ: 0x%x, CQ: 0x%x\n", + icosq->channel->ix, icosq->sqn, rq->rqn, rq->cq.mcq.cqn); + + mlx5e_health_report(priv, priv->rx_reporter, err_str, &err_ctx); +} + +static int mlx5e_rx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx) +{ + return err_ctx->recover(err_ctx->ctx); +} + +static int mlx5e_rx_reporter_recover(struct devlink_health_reporter *reporter, + void *context) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + struct mlx5e_err_ctx *err_ctx = context; + + return err_ctx ? mlx5e_rx_reporter_recover_from_ctx(err_ctx) : + mlx5e_health_recover_channels(priv); +} + +static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq, + struct devlink_fmsg *fmsg) +{ + struct mlx5e_priv *priv = rq->channel->priv; + struct mlx5e_params *params; + struct mlx5e_icosq *icosq; + u8 icosq_hw_state; + int wqes_sz; + u8 hw_state; + u16 wq_head; + int err; + + params = &priv->channels.params; + icosq = &rq->channel->icosq; + err = mlx5e_query_rq_state(priv->mdev, rq->rqn, &hw_state); + if (err) + return err; + + err = mlx5_core_query_sq_state(priv->mdev, icosq->sqn, &icosq_hw_state); + if (err) + return err; + + wqes_sz = mlx5e_rqwq_get_cur_sz(rq); + wq_head = params->rq_wq_type == MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ ? + rq->mpwqe.wq.head : mlx5_wq_cyc_get_head(&rq->wqe.wq); + + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", rq->channel->ix); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "rqn", rq->rqn); + if (err) + return err; + + err = devlink_fmsg_u8_pair_put(fmsg, "HW state", hw_state); + if (err) + return err; + + err = devlink_fmsg_u8_pair_put(fmsg, "SW state", rq->state); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "posted WQEs", wqes_sz); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "cc", wq_head); + if (err) + return err; + + err = devlink_fmsg_u8_pair_put(fmsg, "ICOSQ HW state", icosq_hw_state); + if (err) + return err; + + err = mlx5e_reporter_cq_diagnose(&rq->cq, fmsg); + if (err) + return err; + + err = devlink_fmsg_obj_nest_end(fmsg); + if (err) + return err; + + return 0; +} + +static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter, + struct devlink_fmsg *fmsg) +{ + struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); + struct mlx5e_params *params = &priv->channels.params; + struct mlx5e_rq *generic_rq; + u32 rq_stride, rq_sz; + int i, err = 0; + + mutex_lock(&priv->state_lock); + + if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) + goto unlock; + + generic_rq = &priv->channels.c[0]->rq; + rq_sz = mlx5e_rqwq_get_size(generic_rq); + rq_stride = BIT(mlx5e_mpwqe_get_log_stride_size(priv->mdev, params, NULL)); + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "Common config"); + if (err) + goto unlock; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "RQ"); + if (err) + goto unlock; + + err = devlink_fmsg_u8_pair_put(fmsg, "type", params->rq_wq_type); + if (err) + goto unlock; + + err = devlink_fmsg_u64_pair_put(fmsg, "stride size", rq_stride); + if (err) + goto unlock; + + err = devlink_fmsg_u32_pair_put(fmsg, "size", rq_sz); + if (err) + goto unlock; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + goto unlock; + + err = mlx5e_reporter_cq_common_diagnose(&generic_rq->cq, fmsg); + if (err) + goto unlock; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + goto unlock; + + err = devlink_fmsg_arr_pair_nest_start(fmsg, "RQs"); + if (err) + goto unlock; + + for (i = 0; i < priv->channels.num; i++) { + struct mlx5e_rq *rq = &priv->channels.c[i]->rq; + + err = mlx5e_rx_reporter_build_diagnose_output(rq, fmsg); + if (err) + goto unlock; + } + err = devlink_fmsg_arr_pair_nest_end(fmsg); + if (err) + goto unlock; +unlock: + mutex_unlock(&priv->state_lock); + return err; +} + +static const struct devlink_health_reporter_ops mlx5_rx_reporter_ops = { + .name = "rx", + .recover = mlx5e_rx_reporter_recover, + .diagnose = mlx5e_rx_reporter_diagnose, +}; + +#define MLX5E_REPORTER_RX_GRACEFUL_PERIOD 500 + +int mlx5e_reporter_rx_create(struct mlx5e_priv *priv) +{ + struct devlink *devlink = priv_to_devlink(priv->mdev); + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_create(devlink, + &mlx5_rx_reporter_ops, + MLX5E_REPORTER_RX_GRACEFUL_PERIOD, + true, priv); + if (IS_ERR(reporter)) { + netdev_warn(priv->netdev, "Failed to create rx reporter, err = %ld\n", + PTR_ERR(reporter)); + return PTR_ERR(reporter); + } + priv->rx_reporter = reporter; + return 0; +} + +void mlx5e_reporter_rx_destroy(struct mlx5e_priv *priv) +{ + if (!priv->rx_reporter) + return; + + devlink_health_reporter_destroy(priv->rx_reporter); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index c7f86453c638..bfed558637c2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -1,16 +1,7 @@ /* SPDX-License-Identifier: GPL-2.0 */ /* Copyright (c) 2019 Mellanox Technologies. */ -#include <net/devlink.h> -#include "reporter.h" -#include "lib/eq.h" - -#define MLX5E_TX_REPORTER_PER_SQ_MAX_LEN 256 - -struct mlx5e_tx_err_ctx { - int (*recover)(struct mlx5e_txqsq *sq); - struct mlx5e_txqsq *sq; -}; +#include "health.h" static int mlx5e_wait_for_sq_flush(struct mlx5e_txqsq *sq) { @@ -40,41 +31,20 @@ static void mlx5e_reset_txqsq_cc_pc(struct mlx5e_txqsq *sq) sq->pc = 0; } -static int mlx5e_sq_to_ready(struct mlx5e_txqsq *sq, int curr_state) +static int mlx5e_tx_reporter_err_cqe_recover(void *ctx) { - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - struct mlx5e_modify_sq_param msp = {0}; + struct mlx5_core_dev *mdev; + struct net_device *dev; + struct mlx5e_txqsq *sq; + u8 state; int err; - msp.curr_state = curr_state; - msp.next_state = MLX5_SQC_STATE_RST; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to reset\n", sq->sqn); - return err; - } - - memset(&msp, 0, sizeof(msp)); - msp.curr_state = MLX5_SQC_STATE_RST; - msp.next_state = MLX5_SQC_STATE_RDY; - - err = mlx5e_modify_sq(mdev, sq->sqn, &msp); - if (err) { - netdev_err(dev, "Failed to move sq 0x%x to ready\n", sq->sqn); - return err; - } - - return 0; -} + sq = ctx; + mdev = sq->channel->mdev; + dev = sq->channel->netdev; -static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq) -{ - struct mlx5_core_dev *mdev = sq->channel->mdev; - struct net_device *dev = sq->channel->netdev; - u8 state; - int err; + if (!test_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) + return 0; err = mlx5_core_query_sq_state(mdev, sq->sqn, &state); if (err) { @@ -97,7 +67,7 @@ static int mlx5e_tx_reporter_err_cqe_recover(struct mlx5e_txqsq *sq) * pending WQEs. SQ can safely reset the SQ. */ - err = mlx5e_sq_to_ready(sq, state); + err = mlx5e_health_sq_to_ready(sq->channel, sq->sqn); if (err) goto out; @@ -112,115 +82,98 @@ out: return err; } -static int mlx5_tx_health_report(struct devlink_health_reporter *tx_reporter, - char *err_str, - struct mlx5e_tx_err_ctx *err_ctx) +void mlx5e_reporter_tx_err_cqe(struct mlx5e_txqsq *sq) { - if (IS_ERR_OR_NULL(tx_reporter)) { - netdev_err(err_ctx->sq->channel->netdev, err_str); - return err_ctx->recover(err_ctx->sq); - } - - return devlink_health_report(tx_reporter, err_str, err_ctx); -} + struct mlx5e_priv *priv = sq->channel->priv; + char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_err_ctx err_ctx = {0}; -void mlx5e_tx_reporter_err_cqe(struct mlx5e_txqsq *sq) -{ - char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN]; - struct mlx5e_tx_err_ctx err_ctx = {0}; - - err_ctx.sq = sq; - err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover; + err_ctx.ctx = sq; + err_ctx.recover = mlx5e_tx_reporter_err_cqe_recover; sprintf(err_str, "ERR CQE on SQ: 0x%x", sq->sqn); - mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str, - &err_ctx); + mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx); } -static int mlx5e_tx_reporter_timeout_recover(struct mlx5e_txqsq *sq) +static int mlx5e_tx_reporter_timeout_recover(void *ctx) { - struct mlx5_eq_comp *eq = sq->cq.mcq.eq; - u32 eqe_count; - - netdev_err(sq->channel->netdev, "EQ 0x%x: Cons = 0x%x, irqn = 0x%x\n", - eq->core.eqn, eq->core.cons_index, eq->core.irqn); + struct mlx5_eq_comp *eq; + struct mlx5e_txqsq *sq; + int err; - eqe_count = mlx5_eq_poll_irq_disabled(eq); - if (!eqe_count) { + sq = ctx; + eq = sq->cq.mcq.eq; + err = mlx5e_health_channel_eq_recover(eq, sq->channel); + if (err) clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); - return -EIO; - } - netdev_err(sq->channel->netdev, "Recover %d eqes on EQ 0x%x\n", - eqe_count, eq->core.eqn); - sq->channel->stats->eq_rearm++; - return 0; + return err; } -int mlx5e_tx_reporter_timeout(struct mlx5e_txqsq *sq) +int mlx5e_reporter_tx_timeout(struct mlx5e_txqsq *sq) { - char err_str[MLX5E_TX_REPORTER_PER_SQ_MAX_LEN]; - struct mlx5e_tx_err_ctx err_ctx; + struct mlx5e_priv *priv = sq->channel->priv; + char err_str[MLX5E_REPORTER_PER_Q_MAX_LEN]; + struct mlx5e_err_ctx err_ctx; - err_ctx.sq = sq; - err_ctx.recover = mlx5e_tx_reporter_timeout_recover; + err_ctx.ctx = sq; + err_ctx.recover = mlx5e_tx_reporter_timeout_recover; sprintf(err_str, "TX timeout on queue: %d, SQ: 0x%x, CQ: 0x%x, SQ Cons: 0x%x SQ Prod: 0x%x, usecs since last trans: %u\n", sq->channel->ix, sq->sqn, sq->cq.mcq.cqn, sq->cc, sq->pc, jiffies_to_usecs(jiffies - sq->txq->trans_start)); - return mlx5_tx_health_report(sq->channel->priv->tx_reporter, err_str, - &err_ctx); + return mlx5e_health_report(priv, priv->tx_reporter, err_str, &err_ctx); } /* state lock cannot be grabbed within this function. * It can cause a dead lock or a read-after-free. */ -static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_tx_err_ctx *err_ctx) -{ - return err_ctx->recover(err_ctx->sq); -} - -static int mlx5e_tx_reporter_recover_all(struct mlx5e_priv *priv) +static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx) { - int err = 0; - - rtnl_lock(); - mutex_lock(&priv->state_lock); - - if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) - goto out; - - err = mlx5e_safe_reopen_channels(priv); - -out: - mutex_unlock(&priv->state_lock); - rtnl_unlock(); - - return err; + return err_ctx->recover(err_ctx->ctx); } static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter, void *context) { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); - struct mlx5e_tx_err_ctx *err_ctx = context; + struct mlx5e_err_ctx *err_ctx = context; return err_ctx ? mlx5e_tx_reporter_recover_from_ctx(err_ctx) : - mlx5e_tx_reporter_recover_all(priv); + mlx5e_health_recover_channels(priv); } static int mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, - u32 sqn, u8 state, bool stopped) + struct mlx5e_txqsq *sq, int tc) { + struct mlx5e_priv *priv = sq->channel->priv; + bool stopped = netif_xmit_stopped(sq->txq); + u8 state; int err; + err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state); + if (err) + return err; + err = devlink_fmsg_obj_nest_start(fmsg); if (err) return err; - err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sqn); + err = devlink_fmsg_u32_pair_put(fmsg, "channel ix", sq->ch_ix); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "tc", tc); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "txq ix", sq->txq_ix); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "sqn", sq->sqn); if (err) return err; @@ -232,6 +185,18 @@ mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, if (err) return err; + err = devlink_fmsg_u32_pair_put(fmsg, "cc", sq->cc); + if (err) + return err; + + err = devlink_fmsg_u32_pair_put(fmsg, "pc", sq->pc); + if (err) + return err; + + err = mlx5e_reporter_cq_diagnose(&sq->cq, fmsg); + if (err) + return err; + err = devlink_fmsg_obj_nest_end(fmsg); if (err) return err; @@ -243,31 +208,61 @@ static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, struct devlink_fmsg *fmsg) { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); - int i, err = 0; + struct mlx5e_txqsq *generic_sq = priv->txq2sq[0]; + u32 sq_stride, sq_sz; + + int i, tc, err = 0; mutex_lock(&priv->state_lock); if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) goto unlock; + sq_sz = mlx5_wq_cyc_get_size(&generic_sq->wq); + sq_stride = MLX5_SEND_WQE_BB; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "Common Config"); + if (err) + goto unlock; + + err = mlx5e_reporter_named_obj_nest_start(fmsg, "SQ"); + if (err) + goto unlock; + + err = devlink_fmsg_u64_pair_put(fmsg, "stride size", sq_stride); + if (err) + goto unlock; + + err = devlink_fmsg_u32_pair_put(fmsg, "size", sq_sz); + if (err) + goto unlock; + + err = mlx5e_reporter_cq_common_diagnose(&generic_sq->cq, fmsg); + if (err) + goto unlock; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + goto unlock; + + err = mlx5e_reporter_named_obj_nest_end(fmsg); + if (err) + goto unlock; + err = devlink_fmsg_arr_pair_nest_start(fmsg, "SQs"); if (err) goto unlock; - for (i = 0; i < priv->channels.num * priv->channels.params.num_tc; - i++) { - struct mlx5e_txqsq *sq = priv->txq2sq[i]; - u8 state; + for (i = 0; i < priv->channels.num; i++) { + struct mlx5e_channel *c = priv->channels.c[i]; - err = mlx5_core_query_sq_state(priv->mdev, sq->sqn, &state); - if (err) - goto unlock; + for (tc = 0; tc < priv->channels.params.num_tc; tc++) { + struct mlx5e_txqsq *sq = &c->sq[tc]; - err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq->sqn, - state, - netif_xmit_stopped(sq->txq)); - if (err) - goto unlock; + err = mlx5e_tx_reporter_build_diagnose_output(fmsg, sq, tc); + if (err) + goto unlock; + } } err = devlink_fmsg_arr_pair_nest_end(fmsg); if (err) @@ -286,25 +281,30 @@ static const struct devlink_health_reporter_ops mlx5_tx_reporter_ops = { #define MLX5_REPORTER_TX_GRACEFUL_PERIOD 500 -int mlx5e_tx_reporter_create(struct mlx5e_priv *priv) +int mlx5e_reporter_tx_create(struct mlx5e_priv *priv) { + struct devlink_health_reporter *reporter; struct mlx5_core_dev *mdev = priv->mdev; - struct devlink *devlink = priv_to_devlink(mdev); + struct devlink *devlink; - priv->tx_reporter = + devlink = priv_to_devlink(mdev); + reporter = devlink_health_reporter_create(devlink, &mlx5_tx_reporter_ops, MLX5_REPORTER_TX_GRACEFUL_PERIOD, true, priv); - if (IS_ERR(priv->tx_reporter)) + if (IS_ERR(reporter)) { netdev_warn(priv->netdev, "Failed to create tx reporter, err = %ld\n", - PTR_ERR(priv->tx_reporter)); - return IS_ERR_OR_NULL(priv->tx_reporter); + PTR_ERR(reporter)); + return PTR_ERR(reporter); + } + priv->tx_reporter = reporter; + return 0; } -void mlx5e_tx_reporter_destroy(struct mlx5e_priv *priv) +void mlx5e_reporter_tx_destroy(struct mlx5e_priv *priv) { - if (IS_ERR_OR_NULL(priv->tx_reporter)) + if (!priv->tx_reporter) return; devlink_health_reporter_destroy(priv->tx_reporter); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c index a6a52806be45..f8ee18b4da6f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_tun.c @@ -31,29 +31,36 @@ static int get_route_and_out_devs(struct mlx5e_priv *priv, real_dev = is_vlan_dev(dev) ? vlan_dev_real_dev(dev) : dev; uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); - uplink_upper = netdev_master_upper_dev_get(uplink_dev); + + rcu_read_lock(); + uplink_upper = netdev_master_upper_dev_get_rcu(uplink_dev); + /* mlx5_lag_is_sriov() is a blocking function which can't be called + * while holding rcu read lock. Take the net_device for correctness + * sake. + */ + if (uplink_upper) + dev_hold(uplink_upper); + rcu_read_unlock(); + dst_is_lag_dev = (uplink_upper && netif_is_lag_master(uplink_upper) && real_dev == uplink_upper && mlx5_lag_is_sriov(priv->mdev)); + if (uplink_upper) + dev_put(uplink_upper); /* if the egress device isn't on the same HW e-switch or * it's a LAG device, use the uplink */ + *route_dev = dev; if (!netdev_port_same_parent_id(priv->netdev, real_dev) || - dst_is_lag_dev) { - *route_dev = dev; + dst_is_lag_dev || is_vlan_dev(*route_dev)) *out_dev = uplink_dev; - } else { - *route_dev = dev; - if (is_vlan_dev(*route_dev)) - *out_dev = uplink_dev; - else if (mlx5e_eswitch_rep(dev) && - mlx5e_is_valid_eswitch_fwd_dev(priv, dev)) - *out_dev = *route_dev; - else - return -EOPNOTSUPP; - } + else if (mlx5e_eswitch_rep(dev) && + mlx5e_is_valid_eswitch_fwd_dev(priv, dev)) + *out_dev = *route_dev; + else + return -EOPNOTSUPP; if (!(mlx5e_eswitch_rep(*out_dev) && mlx5e_is_uplink_rep(netdev_priv(*out_dev)))) @@ -284,14 +291,14 @@ int mlx5e_tc_tun_create_header_ipv4(struct mlx5e_priv *priv, */ goto out; } - - err = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv4_encap_size, encap_header, - MLX5_FLOW_NAMESPACE_FDB, - &e->encap_id); - if (err) + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, + e->reformat_type, + ipv4_encap_size, encap_header, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(e->pkt_reformat)) { + err = PTR_ERR(e->pkt_reformat); goto destroy_neigh_entry; + } e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); @@ -400,13 +407,14 @@ int mlx5e_tc_tun_create_header_ipv6(struct mlx5e_priv *priv, goto out; } - err = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - ipv6_encap_size, encap_header, - MLX5_FLOW_NAMESPACE_FDB, - &e->encap_id); - if (err) + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, + e->reformat_type, + ipv6_encap_size, encap_header, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(e->pkt_reformat)) { + err = PTR_ERR(e->pkt_reformat); goto destroy_neigh_entry; + } e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(netdev_priv(out_dev)); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h index ddfe19adb3d9..87be96747902 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h @@ -6,7 +6,7 @@ #include "en.h" -#define MLX5E_SQ_NOPS_ROOM MLX5_SEND_WQE_MAX_WQEBBS +#define MLX5E_SQ_NOPS_ROOM (MLX5_SEND_WQE_MAX_WQEBBS - 1) #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\ MLX5E_SQ_NOPS_ROOM) @@ -117,9 +117,27 @@ mlx5e_notify_hw(struct mlx5_wq_cyc *wq, u16 pc, void __iomem *uar_map, mlx5_write64((__be32 *)ctrl, uar_map); } -static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5e_tx_wqe *wqe) +static inline bool mlx5e_transport_inline_tx_wqe(struct mlx5_wqe_ctrl_seg *cseg) { - return !!wqe->ctrl.tisn; + return cseg && !!cseg->tisn; +} + +static inline u8 +mlx5e_tx_wqe_inline_mode(struct mlx5e_txqsq *sq, struct mlx5_wqe_ctrl_seg *cseg, + struct sk_buff *skb) +{ + u8 mode; + + if (mlx5e_transport_inline_tx_wqe(cseg)) + return MLX5_INLINE_MODE_TCP_UDP; + + mode = sq->min_inline_mode; + + if (skb_vlan_tag_present(skb) && + test_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state)) + mode = max_t(u8, MLX5_INLINE_MODE_L2, mode); + + return mode; } static inline void mlx5e_cq_arm(struct mlx5e_cq *cq) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c index b0b982cf69bb..f049e0ac308a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.c @@ -122,6 +122,7 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, void *va, u16 *rx_headroom, u32 *len, bool xsk) { struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); + struct xdp_umem *umem = rq->umem; struct xdp_buff xdp; u32 act; int err; @@ -138,8 +139,11 @@ bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, xdp.rxq = &rq->xdp_rxq; act = bpf_prog_run_xdp(prog, &xdp); - if (xsk) - xdp.handle += xdp.data - xdp.data_hard_start; + if (xsk) { + u64 off = xdp.data - xdp.data_hard_start; + + xdp.handle = xsk_umem_adjust_offset(umem, xdp.handle, off); + } switch (act) { case XDP_PASS: *rx_headroom = xdp.data - xdp.data_hard_start; @@ -179,33 +183,19 @@ static void mlx5e_xdp_mpwqe_session_start(struct mlx5e_xdpsq *sq) struct mlx5e_xdp_mpwqe *session = &sq->mpwqe; struct mlx5e_xdpsq_stats *stats = sq->stats; struct mlx5_wq_cyc *wq = &sq->wq; - u8 wqebbs; - u16 pi; - - mlx5e_xdpsq_fetch_wqe(sq, &session->wqe); - - prefetchw(session->wqe->data); - session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; - session->pkt_count = 0; - session->complete = 0; + u16 pi, contig_wqebbs; pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + contig_wqebbs = mlx5_wq_cyc_get_contig_wqebbs(wq, pi); -/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS - * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment. - * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a - * full-session WQE be cache-aligned. - */ -#if L1_CACHE_BYTES < 128 -#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1) -#else -#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2) -#endif + if (unlikely(contig_wqebbs < MLX5_SEND_WQE_MAX_WQEBBS)) + mlx5e_fill_xdpsq_frag_edge(sq, wq, pi, contig_wqebbs); - wqebbs = min_t(u16, mlx5_wq_cyc_get_contig_wqebbs(wq, pi), - MLX5E_XDP_MPW_MAX_WQEBBS); + session->wqe = mlx5e_xdpsq_fetch_wqe(sq, &pi); - session->max_ds_count = MLX5_SEND_WQEBB_NUM_DS * wqebbs; + prefetchw(session->wqe->data); + session->ds_count = MLX5E_XDP_TX_EMPTY_DS_COUNT; + session->pkt_count = 0; mlx5e_xdp_update_inline_state(sq); @@ -244,7 +234,7 @@ static int mlx5e_xmit_xdp_frame_check_mpwqe(struct mlx5e_xdpsq *sq) { if (unlikely(!sq->mpwqe.wqe)) { if (unlikely(!mlx5e_wqc_has_room_for(&sq->wq, sq->cc, sq->pc, - MLX5_SEND_WQE_MAX_WQEBBS))) { + MLX5E_XDPSQ_STOP_ROOM))) { /* SQ is full, ring doorbell */ mlx5e_xmit_xdp_doorbell(sq); sq->stats->full++; @@ -285,8 +275,8 @@ static bool mlx5e_xmit_xdp_frame_mpwqe(struct mlx5e_xdpsq *sq, mlx5e_xdp_mpwqe_add_dseg(sq, xdptxd, stats); - if (unlikely(session->complete || - session->ds_count == session->max_ds_count)) + if (unlikely(mlx5e_xdp_no_room_for_inline_pkt(session) || + session->ds_count == MLX5E_XDP_MPW_MAX_NUM_DS)) mlx5e_xdp_mpwqe_complete(sq); mlx5e_xdpi_fifo_push(&sq->db.xdpi_fifo, xdpi); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h index b90923932668..36ac1e3816b9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xdp.h @@ -40,6 +40,26 @@ (sizeof(struct mlx5e_tx_wqe) / MLX5_SEND_WQE_DS) #define MLX5E_XDP_TX_DS_COUNT (MLX5E_XDP_TX_EMPTY_DS_COUNT + 1 /* SG DS */) +#define MLX5E_XDPSQ_STOP_ROOM (MLX5E_SQ_STOP_ROOM) + +#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg)) +#define MLX5E_XDP_INLINE_WQE_MAX_DS_CNT \ + DIV_ROUND_UP(MLX5E_XDP_INLINE_WQE_SZ_THRSD, MLX5_SEND_WQE_DS) + +/* The mult of MLX5_SEND_WQE_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS + * (16 * 4 == 64) does not fit in the 6-bit DS field of Ctrl Segment. + * We use a bound lower that MLX5_SEND_WQE_MAX_WQEBBS to let a + * full-session WQE be cache-aligned. + */ +#if L1_CACHE_BYTES < 128 +#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 1) +#else +#define MLX5E_XDP_MPW_MAX_WQEBBS (MLX5_SEND_WQE_MAX_WQEBBS - 2) +#endif + +#define MLX5E_XDP_MPW_MAX_NUM_DS \ + (MLX5E_XDP_MPW_MAX_WQEBBS * MLX5_SEND_WQEBB_NUM_DS) + struct mlx5e_xsk_param; int mlx5e_xdp_max_mtu(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk); bool mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, @@ -114,6 +134,30 @@ static inline void mlx5e_xdp_update_inline_state(struct mlx5e_xdpsq *sq) session->inline_on = 1; } +static inline bool +mlx5e_xdp_no_room_for_inline_pkt(struct mlx5e_xdp_mpwqe *session) +{ + return session->inline_on && + session->ds_count + MLX5E_XDP_INLINE_WQE_MAX_DS_CNT > MLX5E_XDP_MPW_MAX_NUM_DS; +} + +static inline void +mlx5e_fill_xdpsq_frag_edge(struct mlx5e_xdpsq *sq, struct mlx5_wq_cyc *wq, + u16 pi, u16 nnops) +{ + struct mlx5e_xdp_wqe_info *edge_wi, *wi = &sq->db.wqe_info[pi]; + + edge_wi = wi + nnops; + /* fill sq frag edge with nops to avoid wqe wrapping two pages */ + for (; wi < edge_wi; wi++) { + wi->num_wqebbs = 1; + wi->num_pkts = 0; + mlx5e_post_nop(wq, sq->sqn, &sq->pc); + } + + sq->stats->nops += nnops; +} + static inline void mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, struct mlx5e_xdp_xmit_data *xdptxd, @@ -126,20 +170,12 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, session->pkt_count++; -#define MLX5E_XDP_INLINE_WQE_SZ_THRSD (256 - sizeof(struct mlx5_wqe_inline_seg)) - if (session->inline_on && dma_len <= MLX5E_XDP_INLINE_WQE_SZ_THRSD) { struct mlx5_wqe_inline_seg *inline_dseg = (struct mlx5_wqe_inline_seg *)dseg; u16 ds_len = sizeof(*inline_dseg) + dma_len; u16 ds_cnt = DIV_ROUND_UP(ds_len, MLX5_SEND_WQE_DS); - if (unlikely(session->ds_count + ds_cnt > session->max_ds_count)) { - /* Not enough space for inline wqe, send with memory pointer */ - session->complete = true; - goto no_inline; - } - inline_dseg->byte_count = cpu_to_be32(dma_len | MLX5_INLINE_SEG); memcpy(inline_dseg->data, xdptxd->data, dma_len); @@ -148,21 +184,23 @@ mlx5e_xdp_mpwqe_add_dseg(struct mlx5e_xdpsq *sq, return; } -no_inline: dseg->addr = cpu_to_be64(xdptxd->dma_addr); dseg->byte_count = cpu_to_be32(dma_len); dseg->lkey = sq->mkey_be; session->ds_count++; } -static inline void mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, - struct mlx5e_tx_wqe **wqe) +static inline struct mlx5e_tx_wqe * +mlx5e_xdpsq_fetch_wqe(struct mlx5e_xdpsq *sq, u16 *pi) { struct mlx5_wq_cyc *wq = &sq->wq; - u16 pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + struct mlx5e_tx_wqe *wqe; + + *pi = mlx5_wq_cyc_ctr2ix(wq, sq->pc); + wqe = mlx5_wq_cyc_get_wqe(wq, *pi); + memset(wqe, 0, sizeof(*wqe)); - *wqe = mlx5_wq_cyc_get_wqe(wq, pi); - memset(*wqe, 0, sizeof(**wqe)); + return wqe; } static inline void diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c index 6a55573ec8f2..475b6bd5d29b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.c @@ -24,7 +24,8 @@ int mlx5e_xsk_page_alloc_umem(struct mlx5e_rq *rq, if (!xsk_umem_peek_addr_rq(umem, &handle)) return -ENOMEM; - dma_info->xsk.handle = handle + rq->buff.umem_headroom; + dma_info->xsk.handle = xsk_umem_adjust_offset(umem, handle, + rq->buff.umem_headroom); dma_info->xsk.data = xdp_umem_get_data(umem, dma_info->xsk.handle); /* No need to add headroom to the DMA address. In striding RQ case, we @@ -104,7 +105,7 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_mpwrq_linear(struct mlx5e_rq *rq, /* head_offset is not used in this function, because di->xsk.data and * di->addr point directly to the necessary place. Furthermore, in the - * current implementation, one page = one packet = one frame, so + * current implementation, UMR pages are mapped to XSK frames, so * head_offset should always be 0. */ WARN_ON_ONCE(head_offset); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h index 307b923a1361..cab0e93497ae 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/rx.h @@ -5,6 +5,7 @@ #define __MLX5_EN_XSK_RX_H__ #include "en.h" +#include <net/xdp_sock.h> /* RX data path */ @@ -24,4 +25,17 @@ struct sk_buff *mlx5e_xsk_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5e_wqe_frag_info *wi, u32 cqe_bcnt); +static inline bool mlx5e_xsk_update_rx_wakeup(struct mlx5e_rq *rq, bool alloc_err) +{ + if (!xsk_umem_uses_need_wakeup(rq->umem)) + return alloc_err; + + if (unlikely(alloc_err)) + xsk_set_rx_need_wakeup(rq->umem); + else + xsk_clear_rx_need_wakeup(rq->umem); + + return false; +} + #endif /* __MLX5_EN_XSK_RX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c index 7f78c004d12f..631af8dee517 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/setup.c @@ -4,18 +4,23 @@ #include "setup.h" #include "en/params.h" +/* It matches XDP_UMEM_MIN_CHUNK_SIZE, but as this constant is private and may + * change unexpectedly, and mlx5e has a minimum valid stride size for striding + * RQ, keep this check in the driver. + */ +#define MLX5E_MIN_XSK_CHUNK_SIZE 2048 + bool mlx5e_validate_xsk_param(struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct mlx5_core_dev *mdev) { - /* AF_XDP doesn't support frames larger than PAGE_SIZE, and the current - * mlx5e XDP implementation doesn't support multiple packets per page. - */ - if (xsk->chunk_size != PAGE_SIZE) + /* AF_XDP doesn't support frames larger than PAGE_SIZE. */ + if (xsk->chunk_size > PAGE_SIZE || + xsk->chunk_size < MLX5E_MIN_XSK_CHUNK_SIZE) return false; /* Current MTU and XSK headroom don't allow packets to fit the frames. */ - if (mlx5e_rx_get_linear_frag_sz(params, xsk) > xsk->chunk_size) + if (mlx5e_rx_get_min_frag_sz(params, xsk) > xsk->chunk_size) return false; /* frag_sz is different for regular and XSK RQs, so ensure that linear @@ -60,24 +65,28 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, struct xdp_umem *umem, struct mlx5e_channel *c) { - struct mlx5e_channel_param cparam = {}; + struct mlx5e_channel_param *cparam; struct dim_cq_moder icocq_moder = {}; int err; if (!mlx5e_validate_xsk_param(params, xsk, priv->mdev)) return -EINVAL; - mlx5e_build_xsk_cparam(priv, params, xsk, &cparam); + cparam = kvzalloc(sizeof(*cparam), GFP_KERNEL); + if (!cparam) + return -ENOMEM; + + mlx5e_build_xsk_cparam(priv, params, xsk, cparam); - err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam.rx_cq, &c->xskrq.cq); + err = mlx5e_open_cq(c, params->rx_cq_moderation, &cparam->rx_cq, &c->xskrq.cq); if (unlikely(err)) - return err; + goto err_free_cparam; - err = mlx5e_open_rq(c, params, &cparam.rq, xsk, umem, &c->xskrq); + err = mlx5e_open_rq(c, params, &cparam->rq, xsk, umem, &c->xskrq); if (unlikely(err)) goto err_close_rx_cq; - err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam.tx_cq, &c->xsksq.cq); + err = mlx5e_open_cq(c, params->tx_cq_moderation, &cparam->tx_cq, &c->xsksq.cq); if (unlikely(err)) goto err_close_rq; @@ -87,21 +96,23 @@ int mlx5e_open_xsk(struct mlx5e_priv *priv, struct mlx5e_params *params, * is disabled and then reenabled, but the SQ continues receiving CQEs * from the old UMEM. */ - err = mlx5e_open_xdpsq(c, params, &cparam.xdp_sq, umem, &c->xsksq, true); + err = mlx5e_open_xdpsq(c, params, &cparam->xdp_sq, umem, &c->xsksq, true); if (unlikely(err)) goto err_close_tx_cq; - err = mlx5e_open_cq(c, icocq_moder, &cparam.icosq_cq, &c->xskicosq.cq); + err = mlx5e_open_cq(c, icocq_moder, &cparam->icosq_cq, &c->xskicosq.cq); if (unlikely(err)) goto err_close_sq; /* Create a dedicated SQ for posting NOPs whenever we need an IRQ to be * triggered and NAPI to be called on the correct CPU. */ - err = mlx5e_open_icosq(c, params, &cparam.icosq, &c->xskicosq); + err = mlx5e_open_icosq(c, params, &cparam->icosq, &c->xskicosq); if (unlikely(err)) goto err_close_icocq; + kvfree(cparam); + spin_lock_init(&c->xskicosq_lock); set_bit(MLX5E_CHANNEL_STATE_XSK, c->state); @@ -123,6 +134,9 @@ err_close_rq: err_close_rx_cq: mlx5e_close_cq(&c->xskrq.cq); +err_free_cparam: + kvfree(cparam); + return err; } @@ -141,6 +155,7 @@ void mlx5e_close_xsk(struct mlx5e_channel *c) void mlx5e_activate_xsk(struct mlx5e_channel *c) { + mlx5e_activate_icosq(&c->xskicosq); set_bit(MLX5E_RQ_STATE_ENABLED, &c->xskrq.state); /* TX queue is created active. */ @@ -153,6 +168,7 @@ void mlx5e_deactivate_xsk(struct mlx5e_channel *c) { mlx5e_deactivate_rq(&c->xskrq); /* TX queue is disabled on close. */ + mlx5e_deactivate_icosq(&c->xskicosq); } static int mlx5e_redirect_xsk_rqt(struct mlx5e_priv *priv, u16 ix, u32 rqn) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c index 35e188cf4ea4..87827477d38c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.c @@ -7,7 +7,7 @@ #include "en/params.h" #include <net/xdp_sock.h> -int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid) +int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags) { struct mlx5e_priv *priv = netdev_priv(dev); struct mlx5e_params *params = &priv->channels.params; @@ -26,6 +26,13 @@ int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid) return -ENXIO; if (!napi_if_scheduled_mark_missed(&c->napi)) { + /* To avoid WQE overrun, don't post a NOP if XSKICOSQ is not + * active and not polled by NAPI. Return 0, because the upcoming + * activate will trigger the IRQ for us. + */ + if (unlikely(!test_bit(MLX5E_SQ_STATE_ENABLED, &c->xskicosq.state))) + return 0; + spin_lock(&c->xskicosq_lock); mlx5e_trigger_irq(&c->xskicosq); spin_unlock(&c->xskicosq_lock); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h index 7add18bf78d8..79b487d89757 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/xsk/tx.h @@ -5,11 +5,23 @@ #define __MLX5_EN_XSK_TX_H__ #include "en.h" +#include <net/xdp_sock.h> /* TX data path */ -int mlx5e_xsk_async_xmit(struct net_device *dev, u32 qid); +int mlx5e_xsk_wakeup(struct net_device *dev, u32 qid, u32 flags); bool mlx5e_xsk_tx(struct mlx5e_xdpsq *sq, unsigned int budget); +static inline void mlx5e_xsk_update_tx_wakeup(struct mlx5e_xdpsq *sq) +{ + if (!xsk_umem_uses_need_wakeup(sq->umem)) + return; + + if (sq->pc != sq->cc) + xsk_clear_tx_need_wakeup(sq->umem); + else + xsk_set_tx_need_wakeup(sq->umem); +} + #endif /* __MLX5_EN_XSK_TX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c index 7833ddef0427..d195366461c9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ktls_tx.c @@ -256,8 +256,7 @@ struct mlx5e_dump_wqe { }; static int -tx_post_resync_dump(struct mlx5e_txqsq *sq, struct sk_buff *skb, - skb_frag_t *frag, u32 tisn, bool first) +tx_post_resync_dump(struct mlx5e_txqsq *sq, skb_frag_t *frag, u32 tisn, bool first) { struct mlx5_wqe_ctrl_seg *cseg; struct mlx5_wqe_data_seg *dseg; @@ -371,8 +370,7 @@ mlx5e_ktls_tx_handle_ooo(struct mlx5e_ktls_offload_context_tx *priv_tx, tx_post_resync_params(sq, priv_tx, info.rcd_sn); for (i = 0; i < info.nr_frags; i++) - if (tx_post_resync_dump(sq, skb, info.frags[i], - priv_tx->tisn, !i)) + if (tx_post_resync_dump(sq, info.frags[i], priv_tx->tisn, !i)) goto err_out; /* If no dump WQE was sent, we need to have a fence NOP WQE before the @@ -408,7 +406,7 @@ struct sk_buff *mlx5e_ktls_handle_tx_skb(struct net_device *netdev, goto out; tls_ctx = tls_get_ctx(skb->sk); - if (unlikely(WARN_ON_ONCE(tls_ctx->netdev != netdev))) + if (WARN_ON_ONCE(tls_ctx->netdev != netdev)) goto err_out; priv_tx = mlx5e_get_ktls_tx_priv_ctx(tls_ctx); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c index 1539cf3de5dc..f7890e0ce96c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_common.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_common.c @@ -180,15 +180,3 @@ out: return err; } - -u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev) -{ - u8 min_inline_mode; - - mlx5_query_min_inline(mdev, &min_inline_mode); - if (min_inline_mode == MLX5_INLINE_MODE_NONE && - !MLX5_CAP_ETH(mdev, wqe_vlan_insert)) - min_inline_mode = MLX5_INLINE_MODE_L2; - - return min_inline_mode; -} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c index 8dd31b5c740c..01f2918063af 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dcbnl.c @@ -1101,7 +1101,7 @@ void mlx5e_dcbnl_delete_app(struct mlx5e_priv *priv) static void mlx5e_trust_update_tx_min_inline_mode(struct mlx5e_priv *priv, struct mlx5e_params *params) { - params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(priv->mdev); + mlx5_query_min_inline(priv->mdev, ¶ms->tx_min_inline_mode); if (priv->dcbx_dp.trust_state == MLX5_QPTS_TRUST_DSCP && params->tx_min_inline_mode == MLX5_INLINE_MODE_L2) params->tx_min_inline_mode = MLX5_INLINE_MODE_IP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 20e628c907e5..c5a9c20d7f00 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -1431,7 +1431,7 @@ static __u32 mlx5e_get_wol_supported(struct mlx5_core_dev *mdev) return ret; } -static __u32 mlx5e_refomrat_wol_mode_mlx5_to_linux(u8 mode) +static __u32 mlx5e_reformat_wol_mode_mlx5_to_linux(u8 mode) { __u32 ret = 0; @@ -1459,7 +1459,7 @@ static __u32 mlx5e_refomrat_wol_mode_mlx5_to_linux(u8 mode) return ret; } -static u8 mlx5e_refomrat_wol_mode_linux_to_mlx5(__u32 mode) +static u8 mlx5e_reformat_wol_mode_linux_to_mlx5(__u32 mode) { u8 ret = 0; @@ -1505,7 +1505,7 @@ static void mlx5e_get_wol(struct net_device *netdev, if (err) return; - wol->wolopts = mlx5e_refomrat_wol_mode_mlx5_to_linux(mlx5_wol_mode); + wol->wolopts = mlx5e_reformat_wol_mode_mlx5_to_linux(mlx5_wol_mode); } static int mlx5e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) @@ -1521,7 +1521,7 @@ static int mlx5e_set_wol(struct net_device *netdev, struct ethtool_wolinfo *wol) if (wol->wolopts & ~wol_supported) return -EINVAL; - mlx5_wol_mode = mlx5e_refomrat_wol_mode_linux_to_mlx5(wol->wolopts); + mlx5_wol_mode = mlx5e_reformat_wol_mode_linux_to_mlx5(wol->wolopts); return mlx5_set_port_wol(mdev, mlx5_wol_mode); } @@ -1958,21 +1958,27 @@ static u32 mlx5e_get_priv_flags(struct net_device *netdev) return priv->channels.params.pflags; } -#ifndef CONFIG_MLX5_EN_RXNFC -/* When CONFIG_MLX5_EN_RXNFC=n we only support ETHTOOL_GRXRINGS - * otherwise this function will be defined from en_fs_ethtool.c - */ static int mlx5e_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) { struct mlx5e_priv *priv = netdev_priv(dev); - if (info->cmd != ETHTOOL_GRXRINGS) - return -EOPNOTSUPP; - /* ring_count is needed by ethtool -x */ - info->data = priv->channels.params.num_channels; - return 0; + /* ETHTOOL_GRXRINGS is needed by ethtool -x which is not part + * of rxnfc. We keep this logic out of mlx5e_ethtool_get_rxnfc, + * to avoid breaking "ethtool -x" when mlx5e_ethtool_get_rxnfc + * is compiled out via CONFIG_MLX5_EN_RXNFC=n. + */ + if (info->cmd == ETHTOOL_GRXRINGS) { + info->data = priv->channels.params.num_channels; + return 0; + } + + return mlx5e_ethtool_get_rxnfc(dev, info, rule_locs); +} + +static int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +{ + return mlx5e_ethtool_set_rxnfc(dev, cmd); } -#endif const struct ethtool_ops mlx5e_ethtool_ops = { .get_drvinfo = mlx5e_get_drvinfo, @@ -1993,9 +1999,7 @@ const struct ethtool_ops mlx5e_ethtool_ops = { .get_rxfh = mlx5e_get_rxfh, .set_rxfh = mlx5e_set_rxfh, .get_rxnfc = mlx5e_get_rxnfc, -#ifdef CONFIG_MLX5_EN_RXNFC .set_rxnfc = mlx5e_set_rxnfc, -#endif .get_tunable = mlx5e_get_tunable, .set_tunable = mlx5e_set_tunable, .get_pauseparam = mlx5e_get_pauseparam, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c index 76cc10e44080..15b7f0f1427c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs.c @@ -747,8 +747,55 @@ static struct mlx5e_etype_proto ttc_tunnel_rules[] = { .etype = ETH_P_IPV6, .proto = IPPROTO_GRE, }, + [MLX5E_TT_IPV4_IPIP] = { + .etype = ETH_P_IP, + .proto = IPPROTO_IPIP, + }, + [MLX5E_TT_IPV6_IPIP] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_IPIP, + }, + [MLX5E_TT_IPV4_IPV6] = { + .etype = ETH_P_IP, + .proto = IPPROTO_IPV6, + }, + [MLX5E_TT_IPV6_IPV6] = { + .etype = ETH_P_IPV6, + .proto = IPPROTO_IPV6, + }, + }; +bool mlx5e_tunnel_proto_supported(struct mlx5_core_dev *mdev, u8 proto_type) +{ + switch (proto_type) { + case IPPROTO_GRE: + return MLX5_CAP_ETH(mdev, tunnel_stateless_gre); + case IPPROTO_IPIP: + case IPPROTO_IPV6: + return MLX5_CAP_ETH(mdev, tunnel_stateless_ip_over_ip); + default: + return false; + } +} + +bool mlx5e_any_tunnel_proto_supported(struct mlx5_core_dev *mdev) +{ + int tt; + + for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) { + if (mlx5e_tunnel_proto_supported(mdev, ttc_tunnel_rules[tt].proto)) + return true; + } + return false; +} + +bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) +{ + return (mlx5e_any_tunnel_proto_supported(mdev) && + MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version)); +} + static u8 mlx5e_etype_to_ipv(u16 ethertype) { if (ethertype == ETH_P_IP) @@ -838,6 +885,9 @@ static int mlx5e_generate_ttc_table_rules(struct mlx5e_priv *priv, dest.type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest.ft = params->inner_ttc->ft.t; for (tt = 0; tt < MLX5E_NUM_TUNNEL_TT; tt++) { + if (!mlx5e_tunnel_proto_supported(priv->mdev, + ttc_tunnel_rules[tt].proto)) + continue; rules[tt] = mlx5e_generate_ttc_rule(priv, ft, &dest, ttc_tunnel_rules[tt].etype, ttc_tunnel_rules[tt].proto); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c index 94304abc49e9..eed7101e8bb7 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c @@ -888,10 +888,10 @@ static int mlx5e_get_rss_hash_opt(struct mlx5e_priv *priv, return 0; } -int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) +int mlx5e_ethtool_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) { - int err = 0; struct mlx5e_priv *priv = netdev_priv(dev); + int err = 0; switch (cmd->cmd) { case ETHTOOL_SRXCLSRLINS: @@ -911,16 +911,13 @@ int mlx5e_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *cmd) return err; } -int mlx5e_get_rxnfc(struct net_device *dev, - struct ethtool_rxnfc *info, u32 *rule_locs) +int mlx5e_ethtool_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *info, u32 *rule_locs) { struct mlx5e_priv *priv = netdev_priv(dev); int err = 0; switch (info->cmd) { - case ETHTOOL_GRXRINGS: - info->data = priv->channels.params.num_channels; - break; case ETHTOOL_GRXCLSRLCNT: info->rule_cnt = priv->fs.ethtool.tot_num_rules; break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index 9d5f6e56188f..7569287f8f3c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -56,12 +56,13 @@ #include "en/xdp.h" #include "lib/eq.h" #include "en/monitor_stats.h" -#include "en/reporter.h" +#include "en/health.h" #include "en/params.h" #include "en/xsk/umem.h" #include "en/xsk/setup.h" #include "en/xsk/rx.h" #include "en/xsk/tx.h" +#include "en/hv_vhca_stats.h" bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev) @@ -247,26 +248,6 @@ static inline void mlx5e_build_umr_wqe(struct mlx5e_rq *rq, ucseg->mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE); } -static u32 mlx5e_rqwq_get_size(struct mlx5e_rq *rq) -{ - switch (rq->wq_type) { - case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - return mlx5_wq_ll_get_size(&rq->mpwqe.wq); - default: - return mlx5_wq_cyc_get_size(&rq->wqe.wq); - } -} - -static u32 mlx5e_rqwq_get_cur_sz(struct mlx5e_rq *rq) -{ - switch (rq->wq_type) { - case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: - return rq->mpwqe.wq.cur_sz; - default: - return rq->wqe.wq.cur_sz; - } -} - static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq, struct mlx5e_channel *c) { @@ -382,6 +363,13 @@ static void mlx5e_free_di_list(struct mlx5e_rq *rq) kvfree(rq->wqe.di); } +static void mlx5e_rq_err_cqe_work(struct work_struct *recover_work) +{ + struct mlx5e_rq *rq = container_of(recover_work, struct mlx5e_rq, recover_work); + + mlx5e_reporter_rq_cqe_err(rq); +} + static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5e_params *params, struct mlx5e_xsk_param *xsk, @@ -418,6 +406,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->stats = &c->priv->channel_stats[c->ix].xskrq; else rq->stats = &c->priv->channel_stats[c->ix].rq; + INIT_WORK(&rq->recover_work, mlx5e_rq_err_cqe_work); rq->xdp_prog = params->xdp_prog ? bpf_prog_inc(params->xdp_prog) : NULL; if (IS_ERR(rq->xdp_prog)) { @@ -720,8 +709,7 @@ static int mlx5e_create_rq(struct mlx5e_rq *rq, return err; } -static int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, - int next_state) +int mlx5e_modify_rq_state(struct mlx5e_rq *rq, int curr_state, int next_state) { struct mlx5_core_dev *mdev = rq->mdev; @@ -829,10 +817,11 @@ int mlx5e_wait_for_min_rx_wqes(struct mlx5e_rq *rq, int wait_time) netdev_warn(c->netdev, "Failed to get min RX wqes on Channel[%d] RQN[0x%x] wq cur_sz(%d) min_rx_wqes(%d)\n", c->ix, rq->rqn, mlx5e_rqwq_get_cur_sz(rq), min_wqes); + mlx5e_reporter_rx_timeout(rq); return -ETIMEDOUT; } -static void mlx5e_free_rx_descs(struct mlx5e_rq *rq) +void mlx5e_free_rx_descs(struct mlx5e_rq *rq) { __be16 wqe_ix_be; u16 wqe_ix; @@ -911,7 +900,7 @@ err_free_rq: return err; } -static void mlx5e_activate_rq(struct mlx5e_rq *rq) +void mlx5e_activate_rq(struct mlx5e_rq *rq) { set_bit(MLX5E_RQ_STATE_ENABLED, &rq->state); mlx5e_trigger_irq(&rq->channel->icosq); @@ -926,6 +915,8 @@ void mlx5e_deactivate_rq(struct mlx5e_rq *rq) void mlx5e_close_rq(struct mlx5e_rq *rq) { cancel_work_sync(&rq->dim.work); + cancel_work_sync(&rq->channel->icosq.recover_work); + cancel_work_sync(&rq->recover_work); mlx5e_destroy_rq(rq); mlx5e_free_rx_descs(rq); mlx5e_free_rq(rq); @@ -1042,6 +1033,14 @@ static int mlx5e_alloc_icosq_db(struct mlx5e_icosq *sq, int numa) return 0; } +static void mlx5e_icosq_err_cqe_work(struct work_struct *recover_work) +{ + struct mlx5e_icosq *sq = container_of(recover_work, struct mlx5e_icosq, + recover_work); + + mlx5e_reporter_icosq_cqe_err(sq); +} + static int mlx5e_alloc_icosq(struct mlx5e_channel *c, struct mlx5e_sq_param *param, struct mlx5e_icosq *sq) @@ -1064,6 +1063,8 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c, if (err) goto err_sq_wq_destroy; + INIT_WORK(&sq->recover_work, mlx5e_icosq_err_cqe_work); + return 0; err_sq_wq_destroy: @@ -1130,6 +1131,8 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, sq->stats = &c->priv->channel_stats[c->ix].sq[tc]; sq->stop_room = MLX5E_SQ_STOP_ROOM; INIT_WORK(&sq->recover_work, mlx5e_tx_err_cqe_work); + if (!MLX5_CAP_ETH(mdev, wqe_vlan_insert)) + set_bit(MLX5E_SQ_STATE_VLAN_NEED_L2_INLINE, &sq->state); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); if (mlx5_accel_is_tls_device(c->priv->mdev)) { @@ -1312,7 +1315,6 @@ static int mlx5e_open_txqsq(struct mlx5e_channel *c, return 0; err_free_txqsq: - clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); mlx5e_free_txqsq(sq); return err; @@ -1377,7 +1379,7 @@ static void mlx5e_tx_err_cqe_work(struct work_struct *recover_work) struct mlx5e_txqsq *sq = container_of(recover_work, struct mlx5e_txqsq, recover_work); - mlx5e_tx_reporter_err_cqe(sq); + mlx5e_reporter_tx_err_cqe(sq); } int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params, @@ -1393,7 +1395,6 @@ int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params, csp.cqn = sq->cq.mcq.cqn; csp.wq_ctrl = &sq->wq_ctrl; csp.min_inline_mode = params->tx_min_inline_mode; - set_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); err = mlx5e_create_sq_rdy(c->mdev, param, &csp, &sq->sqn); if (err) goto err_free_icosq; @@ -1401,18 +1402,27 @@ int mlx5e_open_icosq(struct mlx5e_channel *c, struct mlx5e_params *params, return 0; err_free_icosq: - clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); mlx5e_free_icosq(sq); return err; } -void mlx5e_close_icosq(struct mlx5e_icosq *sq) +void mlx5e_activate_icosq(struct mlx5e_icosq *icosq) { - struct mlx5e_channel *c = sq->channel; + set_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state); +} - clear_bit(MLX5E_SQ_STATE_ENABLED, &sq->state); +void mlx5e_deactivate_icosq(struct mlx5e_icosq *icosq) +{ + struct mlx5e_channel *c = icosq->channel; + + clear_bit(MLX5E_SQ_STATE_ENABLED, &icosq->state); napi_synchronize(&c->napi); +} + +void mlx5e_close_icosq(struct mlx5e_icosq *sq) +{ + struct mlx5e_channel *c = sq->channel; mlx5e_destroy_sq(c->mdev, sq->sqn); mlx5e_free_icosq(sq); @@ -1430,7 +1440,7 @@ int mlx5e_open_xdpsq(struct mlx5e_channel *c, struct mlx5e_params *params, return err; csp.tis_lst_sz = 1; - csp.tisn = c->priv->tisn[0]; /* tc = 0 */ + csp.tisn = c->priv->tisn[c->lag_port][0]; /* tc = 0 */ csp.cqn = sq->cq.mcq.cqn; csp.wq_ctrl = &sq->wq_ctrl; csp.min_inline_mode = sq->min_inline_mode; @@ -1680,7 +1690,7 @@ static int mlx5e_open_sqs(struct mlx5e_channel *c, for (tc = 0; tc < params->num_tc; tc++) { int txq_ix = c->ix + tc * priv->max_nch; - err = mlx5e_open_txqsq(c, c->priv->tisn[tc], txq_ix, + err = mlx5e_open_txqsq(c, c->priv->tisn[c->lag_port][tc], txq_ix, params, &cparam->sq, &c->sq[tc], tc); if (err) goto err_close_sqs; @@ -1914,6 +1924,13 @@ static void mlx5e_close_queues(struct mlx5e_channel *c) mlx5e_close_cq(&c->icosq.cq); } +static u8 mlx5e_enumerate_lag_port(struct mlx5_core_dev *mdev, int ix) +{ + u16 port_aff_bias = mlx5_core_is_pf(mdev) ? 0 : MLX5_CAP_GEN(mdev, vhca_id); + + return (ix + port_aff_bias) % mlx5e_get_num_lag_ports(mdev); +} + static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, struct mlx5e_params *params, struct mlx5e_channel_param *cparam, @@ -1948,6 +1965,7 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix, c->xdp = !!params->xdp_prog; c->stats = &priv->channel_stats[ix].ch; c->irq_desc = irq_to_desc(irq); + c->lag_port = mlx5e_enumerate_lag_port(priv->mdev, ix); err = mlx5e_alloc_xps_cpumask(c, params); if (err) @@ -1989,6 +2007,7 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c) for (tc = 0; tc < c->num_tc; tc++) mlx5e_activate_txqsq(&c->sq[tc]); + mlx5e_activate_icosq(&c->icosq); mlx5e_activate_rq(&c->rq); netif_set_xps_queue(c->netdev, c->xps_cpumask, c->ix); @@ -2004,6 +2023,7 @@ static void mlx5e_deactivate_channel(struct mlx5e_channel *c) mlx5e_deactivate_xsk(c); mlx5e_deactivate_rq(&c->rq); + mlx5e_deactivate_icosq(&c->icosq); for (tc = 0; tc < c->num_tc; tc++) mlx5e_deactivate_txqsq(&c->sq[tc]); } @@ -2321,10 +2341,7 @@ int mlx5e_open_channels(struct mlx5e_priv *priv, goto err_close_channels; } - if (!IS_ERR_OR_NULL(priv->tx_reporter)) - devlink_health_reporter_state_update(priv->tx_reporter, - DEVLINK_HEALTH_REPORTER_STATE_HEALTHY); - + mlx5e_health_channels_update(priv); kvfree(cparam); return 0; @@ -3168,40 +3185,58 @@ void mlx5e_destroy_tis(struct mlx5_core_dev *mdev, u32 tisn) mlx5_core_destroy_tis(mdev, tisn); } +void mlx5e_destroy_tises(struct mlx5e_priv *priv) +{ + int tc, i; + + for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++) + for (tc = 0; tc < priv->profile->max_tc; tc++) + mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]); +} + +static bool mlx5e_lag_should_assign_affinity(struct mlx5_core_dev *mdev) +{ + return MLX5_CAP_GEN(mdev, lag_tx_port_affinity) && mlx5e_get_num_lag_ports(mdev) > 1; +} + int mlx5e_create_tises(struct mlx5e_priv *priv) { + int tc, i; int err; - int tc; - for (tc = 0; tc < priv->profile->max_tc; tc++) { - u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {}; - void *tisc; + for (i = 0; i < mlx5e_get_num_lag_ports(priv->mdev); i++) { + for (tc = 0; tc < priv->profile->max_tc; tc++) { + u32 in[MLX5_ST_SZ_DW(create_tis_in)] = {}; + void *tisc; - tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); + tisc = MLX5_ADDR_OF(create_tis_in, in, ctx); - MLX5_SET(tisc, tisc, prio, tc << 1); + MLX5_SET(tisc, tisc, prio, tc << 1); - err = mlx5e_create_tis(priv->mdev, in, &priv->tisn[tc]); - if (err) - goto err_close_tises; + if (mlx5e_lag_should_assign_affinity(priv->mdev)) + MLX5_SET(tisc, tisc, lag_tx_port_affinity, i + 1); + + err = mlx5e_create_tis(priv->mdev, in, &priv->tisn[i][tc]); + if (err) + goto err_close_tises; + } } return 0; err_close_tises: - for (tc--; tc >= 0; tc--) - mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); + for (; i >= 0; i--) { + for (tc--; tc >= 0; tc--) + mlx5e_destroy_tis(priv->mdev, priv->tisn[i][tc]); + tc = priv->profile->max_tc; + } return err; } static void mlx5e_cleanup_nic_tx(struct mlx5e_priv *priv) { - int tc; - - mlx5e_tx_reporter_destroy(priv); - for (tc = 0; tc < priv->profile->max_tc; tc++) - mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); + mlx5e_destroy_tises(priv); } static void mlx5e_build_indir_tir_ctx_common(struct mlx5e_priv *priv, @@ -3422,7 +3457,7 @@ out: #ifdef CONFIG_MLX5_ESWITCH static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv, struct flow_cls_offload *cls_flower, - int flags) + unsigned long flags) { switch (cls_flower->command) { case FLOW_CLS_REPLACE: @@ -3442,12 +3477,12 @@ static int mlx5e_setup_tc_cls_flower(struct mlx5e_priv *priv, static int mlx5e_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { + unsigned long flags = MLX5_TC_FLAG(INGRESS) | MLX5_TC_FLAG(NIC_OFFLOAD); struct mlx5e_priv *priv = cb_priv; switch (type) { case TC_SETUP_CLSFLOWER: - return mlx5e_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS | - MLX5E_TC_NIC_OFFLOAD); + return mlx5e_setup_tc_cls_flower(priv, type_data, flags); default: return -EOPNOTSUPP; } @@ -3463,11 +3498,15 @@ static int mlx5e_setup_tc(struct net_device *dev, enum tc_setup_type type, switch (type) { #ifdef CONFIG_MLX5_ESWITCH - case TC_SETUP_BLOCK: + case TC_SETUP_BLOCK: { + struct flow_block_offload *f = type_data; + + f->unlocked_driver_cb = true; return flow_block_cb_setup_simple(type_data, &mlx5e_block_cb_list, mlx5e_setup_tc_block_cb, priv, priv, true); + } #endif case TC_SETUP_QDISC_MQPRIO: return mlx5e_setup_tc_mqprio(priv, type_data); @@ -3640,7 +3679,7 @@ static int set_feature_tc_num_filters(struct net_device *netdev, bool enable) { struct mlx5e_priv *priv = netdev_priv(netdev); - if (!enable && mlx5e_tc_num_filters(priv, MLX5E_TC_NIC_OFFLOAD)) { + if (!enable && mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD))) { netdev_err(netdev, "Active offloaded tc filters, can't turn hw_tc_offload off\n"); return -EINVAL; @@ -3781,9 +3820,10 @@ static netdev_features_t mlx5e_fix_features(struct net_device *netdev, netdev_warn(netdev, "Dropping C-tag vlan stripping offload due to S-tag vlan\n"); } if (!MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_STRIDING_RQ)) { - features &= ~NETIF_F_LRO; - if (params->lro_en) + if (features & NETIF_F_LRO) { netdev_warn(netdev, "Disabling LRO, not supported in legacy RQ\n"); + features &= ~NETIF_F_LRO; + } } if (MLX5E_GET_PFLAG(params, MLX5E_PFLAG_RX_CQE_COMPRESS)) { @@ -3950,7 +3990,8 @@ int mlx5e_hwstamp_set(struct mlx5e_priv *priv, struct ifreq *ifr) case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: case HWTSTAMP_FILTER_NTP_ALL: /* Disable CQE compression */ - netdev_warn(priv->netdev, "Disabling cqe compression"); + if (MLX5E_GET_PFLAG(&priv->channels.params, MLX5E_PFLAG_RX_CQE_COMPRESS)) + netdev_warn(priv->netdev, "Disabling RX cqe compression\n"); err = mlx5e_modify_rx_cqe_compression_locked(priv, false); if (err) { netdev_err(priv->netdev, "Failed disabling cqe compression err=%d\n", err); @@ -4202,6 +4243,8 @@ static netdev_features_t mlx5e_tunnel_features_check(struct mlx5e_priv *priv, switch (proto) { case IPPROTO_GRE: + case IPPROTO_IPIP: + case IPPROTO_IPV6: return features; case IPPROTO_UDP: udph = udp_hdr(skb); @@ -4267,7 +4310,7 @@ static void mlx5e_tx_timeout_work(struct work_struct *work) if (!netif_xmit_stopped(dev_queue)) continue; - if (mlx5e_tx_reporter_timeout(sq)) + if (mlx5e_reporter_tx_timeout(sq)) report_failed = true; } @@ -4535,7 +4578,7 @@ const struct net_device_ops mlx5e_netdev_ops = { .ndo_tx_timeout = mlx5e_tx_timeout, .ndo_bpf = mlx5e_xdp, .ndo_xdp_xmit = mlx5e_xdp_xmit, - .ndo_xsk_async_xmit = mlx5e_xsk_async_xmit, + .ndo_xsk_wakeup = mlx5e_xsk_wakeup, #ifdef CONFIG_MLX5_EN_ARFS .ndo_rx_flow_steer = mlx5e_rx_flow_steer, #endif @@ -4768,7 +4811,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); /* TX inline */ - params->tx_min_inline_mode = mlx5e_params_calculate_tx_min_inline(mdev); + mlx5_query_min_inline(mdev, ¶ms->tx_min_inline_mode); /* RSS */ mlx5e_build_rss_params(rss_params, params->num_channels); @@ -4838,7 +4881,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->hw_features |= NETIF_F_HW_VLAN_STAG_TX; if (mlx5_vxlan_allowed(mdev->vxlan) || mlx5_geneve_tx_allowed(mdev) || - MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) { + mlx5e_any_tunnel_proto_supported(mdev)) { netdev->hw_enc_features |= NETIF_F_HW_CSUM; netdev->hw_enc_features |= NETIF_F_TSO; netdev->hw_enc_features |= NETIF_F_TSO6; @@ -4853,7 +4896,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) netdev->gso_partial_features = NETIF_F_GSO_UDP_TUNNEL_CSUM; } - if (MLX5_CAP_ETH(mdev, tunnel_stateless_gre)) { + if (mlx5e_tunnel_proto_supported(mdev, IPPROTO_GRE)) { netdev->hw_features |= NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM; netdev->hw_enc_features |= NETIF_F_GSO_GRE | @@ -4862,6 +4905,15 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) NETIF_F_GSO_GRE_CSUM; } + if (mlx5e_tunnel_proto_supported(mdev, IPPROTO_IPIP)) { + netdev->hw_features |= NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6; + netdev->hw_enc_features |= NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6; + netdev->gso_partial_features |= NETIF_F_GSO_IPXIP4 | + NETIF_F_GSO_IPXIP6; + } + netdev->hw_features |= NETIF_F_GSO_PARTIAL; netdev->gso_partial_features |= NETIF_F_GSO_UDP_L4; netdev->hw_features |= NETIF_F_GSO_UDP_L4; @@ -4965,12 +5017,14 @@ static int mlx5e_nic_init(struct mlx5_core_dev *mdev, mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); mlx5e_build_nic_netdev(netdev); mlx5e_build_tc2txq_maps(priv); + mlx5e_health_create_reporters(priv); return 0; } static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) { + mlx5e_health_destroy_reporters(priv); mlx5e_tls_cleanup(priv); mlx5e_ipsec_cleanup(priv); mlx5e_netdev_cleanup(priv->netdev, priv); @@ -5073,7 +5127,6 @@ static int mlx5e_init_nic_tx(struct mlx5e_priv *priv) #ifdef CONFIG_MLX5_CORE_EN_DCB mlx5e_dcbnl_initialize(priv); #endif - mlx5e_tx_reporter_create(priv); return 0; } @@ -5097,6 +5150,7 @@ static void mlx5e_nic_enable(struct mlx5e_priv *priv) if (mlx5e_monitor_counter_supported(priv)) mlx5e_monitor_counter_init(priv); + mlx5e_hv_vhca_stats_create(priv); if (netdev->reg_state != NETREG_REGISTERED) return; #ifdef CONFIG_MLX5_CORE_EN_DCB @@ -5129,6 +5183,7 @@ static void mlx5e_nic_disable(struct mlx5e_priv *priv) queue_work(priv->wq, &priv->set_rx_mode_work); + mlx5e_hv_vhca_stats_destroy(priv); if (mlx5e_monitor_counter_supported(priv)) mlx5e_monitor_counter_cleanup(priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c index d0684fdb69e1..95892a3b63a1 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.c @@ -38,6 +38,7 @@ #include <net/netevent.h> #include <net/arp.h> #include <net/devlink.h> +#include <net/ipv6_stubs.h> #include "eswitch.h" #include "en.h" @@ -46,6 +47,8 @@ #include "en/tc_tun.h" #include "fs_core.h" #include "lib/port_tun.h" +#define CREATE_TRACE_POINTS +#include "diag/en_rep_tracepoint.h" #define MLX5E_REP_PARAMS_DEF_LOG_SQ_SIZE \ max(0x7, MLX5E_PARAMS_MINIMUM_LOG_SQ_SIZE) @@ -389,24 +392,17 @@ static const struct ethtool_ops mlx5e_uplink_rep_ethtool_ops = { .set_pauseparam = mlx5e_uplink_rep_set_pauseparam, }; -static int mlx5e_rep_get_port_parent_id(struct net_device *dev, - struct netdev_phys_item_id *ppid) +static void mlx5e_rep_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) { - struct mlx5_eswitch *esw; struct mlx5e_priv *priv; u64 parent_id; priv = netdev_priv(dev); - esw = priv->mdev->priv.eswitch; - - if (esw->mode == MLX5_ESWITCH_NONE) - return -EOPNOTSUPP; parent_id = mlx5_query_nic_system_image_guid(priv->mdev); ppid->id_len = sizeof(parent_id); memcpy(ppid->id, &parent_id, sizeof(parent_id)); - - return 0; } static void mlx5e_sqs2vport_stop(struct mlx5_eswitch *esw, @@ -504,16 +500,18 @@ void mlx5e_remove_sqs_fwd_rules(struct mlx5e_priv *priv) mlx5e_sqs2vport_stop(esw, rep); } +static unsigned long mlx5e_rep_ipv6_interval(void) +{ + if (IS_ENABLED(CONFIG_IPV6) && ipv6_stub->nd_tbl) + return NEIGH_VAR(&ipv6_stub->nd_tbl->parms, DELAY_PROBE_TIME); + + return ~0UL; +} + static void mlx5e_rep_neigh_update_init_interval(struct mlx5e_rep_priv *rpriv) { -#if IS_ENABLED(CONFIG_IPV6) - unsigned long ipv6_interval = NEIGH_VAR(&nd_tbl.parms, - DELAY_PROBE_TIME); -#else - unsigned long ipv6_interval = ~0UL; -#endif - unsigned long ipv4_interval = NEIGH_VAR(&arp_tbl.parms, - DELAY_PROBE_TIME); + unsigned long ipv4_interval = NEIGH_VAR(&arp_tbl.parms, DELAY_PROBE_TIME); + unsigned long ipv6_interval = mlx5e_rep_ipv6_interval(); struct net_device *netdev = rpriv->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); @@ -531,47 +529,97 @@ void mlx5e_rep_queue_neigh_stats_work(struct mlx5e_priv *priv) neigh_update->min_interval); } +static bool mlx5e_rep_neigh_entry_hold(struct mlx5e_neigh_hash_entry *nhe) +{ + return refcount_inc_not_zero(&nhe->refcnt); +} + +static void mlx5e_rep_neigh_entry_remove(struct mlx5e_neigh_hash_entry *nhe); + +static void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe) +{ + if (refcount_dec_and_test(&nhe->refcnt)) { + mlx5e_rep_neigh_entry_remove(nhe); + kfree_rcu(nhe, rcu); + } +} + +static struct mlx5e_neigh_hash_entry * +mlx5e_get_next_nhe(struct mlx5e_rep_priv *rpriv, + struct mlx5e_neigh_hash_entry *nhe) +{ + struct mlx5e_neigh_hash_entry *next = NULL; + + rcu_read_lock(); + + for (next = nhe ? + list_next_or_null_rcu(&rpriv->neigh_update.neigh_list, + &nhe->neigh_list, + struct mlx5e_neigh_hash_entry, + neigh_list) : + list_first_or_null_rcu(&rpriv->neigh_update.neigh_list, + struct mlx5e_neigh_hash_entry, + neigh_list); + next; + next = list_next_or_null_rcu(&rpriv->neigh_update.neigh_list, + &next->neigh_list, + struct mlx5e_neigh_hash_entry, + neigh_list)) + if (mlx5e_rep_neigh_entry_hold(next)) + break; + + rcu_read_unlock(); + + if (nhe) + mlx5e_rep_neigh_entry_release(nhe); + + return next; +} + static void mlx5e_rep_neigh_stats_work(struct work_struct *work) { struct mlx5e_rep_priv *rpriv = container_of(work, struct mlx5e_rep_priv, neigh_update.neigh_stats_work.work); struct net_device *netdev = rpriv->netdev; struct mlx5e_priv *priv = netdev_priv(netdev); - struct mlx5e_neigh_hash_entry *nhe; + struct mlx5e_neigh_hash_entry *nhe = NULL; rtnl_lock(); if (!list_empty(&rpriv->neigh_update.neigh_list)) mlx5e_rep_queue_neigh_stats_work(priv); - list_for_each_entry(nhe, &rpriv->neigh_update.neigh_list, neigh_list) + while ((nhe = mlx5e_get_next_nhe(rpriv, nhe)) != NULL) mlx5e_tc_update_neigh_used_value(nhe); rtnl_unlock(); } -static void mlx5e_rep_neigh_entry_hold(struct mlx5e_neigh_hash_entry *nhe) -{ - refcount_inc(&nhe->refcnt); -} - -static void mlx5e_rep_neigh_entry_release(struct mlx5e_neigh_hash_entry *nhe) -{ - if (refcount_dec_and_test(&nhe->refcnt)) - kfree(nhe); -} - static void mlx5e_rep_update_flows(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e, bool neigh_connected, unsigned char ha[ETH_ALEN]) { struct ethhdr *eth = (struct ethhdr *)e->encap_header; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + bool encap_connected; + LIST_HEAD(flow_list); ASSERT_RTNL(); + /* wait for encap to be fully initialized */ + wait_for_completion(&e->res_ready); + + mutex_lock(&esw->offloads.encap_tbl_lock); + encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID); + if (e->compl_result || (encap_connected == neigh_connected && + ether_addr_equal(e->h_dest, ha))) + goto unlock; + + mlx5e_take_all_encap_flows(e, &flow_list); + if ((e->flags & MLX5_ENCAP_ENTRY_VALID) && (!neigh_connected || !ether_addr_equal(e->h_dest, ha))) - mlx5e_tc_encap_flows_del(priv, e); + mlx5e_tc_encap_flows_del(priv, e, &flow_list); if (neigh_connected && !(e->flags & MLX5_ENCAP_ENTRY_VALID)) { ether_addr_copy(e->h_dest, ha); @@ -581,8 +629,11 @@ static void mlx5e_rep_update_flows(struct mlx5e_priv *priv, */ ether_addr_copy(eth->h_source, e->route_dev->dev_addr); - mlx5e_tc_encap_flows_add(priv, e); + mlx5e_tc_encap_flows_add(priv, e, &flow_list); } +unlock: + mutex_unlock(&esw->offloads.encap_tbl_lock); + mlx5e_put_encap_flow_list(priv, &flow_list); } static void mlx5e_rep_neigh_update(struct work_struct *work) @@ -594,7 +645,6 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) unsigned char ha[ETH_ALEN]; struct mlx5e_priv *priv; bool neigh_connected; - bool encap_connected; u8 nud_state, dead; rtnl_lock(); @@ -612,13 +662,15 @@ static void mlx5e_rep_neigh_update(struct work_struct *work) neigh_connected = (nud_state & NUD_VALID) && !dead; + trace_mlx5e_rep_neigh_update(nhe, ha, neigh_connected); + list_for_each_entry(e, &nhe->encap_list, encap_list) { - encap_connected = !!(e->flags & MLX5_ENCAP_ENTRY_VALID); - priv = netdev_priv(e->out_dev); + if (!mlx5e_encap_take(e)) + continue; - if (encap_connected != neigh_connected || - !ether_addr_equal(e->h_dest, ha)) - mlx5e_rep_update_flows(priv, e, neigh_connected, ha); + priv = netdev_priv(e->out_dev); + mlx5e_rep_update_flows(priv, e, neigh_connected, ha); + mlx5e_encap_put(priv, e); } mlx5e_rep_neigh_entry_release(nhe); rtnl_unlock(); @@ -659,8 +711,8 @@ mlx5e_rep_indr_offload(struct net_device *netdev, struct flow_cls_offload *flower, struct mlx5e_rep_indr_block_priv *indr_priv) { + unsigned long flags = MLX5_TC_FLAG(EGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD); struct mlx5e_priv *priv = netdev_priv(indr_priv->rpriv->netdev); - int flags = MLX5E_TC_EGRESS | MLX5E_TC_ESW_OFFLOAD; int err = 0; switch (flower->command) { @@ -714,6 +766,7 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev, if (f->binder_type != FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS) return -EOPNOTSUPP; + f->unlocked_driver_cb = true; f->driver_block_list = &mlx5e_block_cb_list; switch (f->command) { @@ -722,10 +775,6 @@ mlx5e_rep_indr_setup_tc_block(struct net_device *netdev, if (indr_priv) return -EEXIST; - if (flow_block_cb_is_busy(mlx5e_rep_indr_setup_block_cb, - indr_priv, &mlx5e_block_cb_list)) - return -EBUSY; - indr_priv = kmalloc(sizeof(*indr_priv), GFP_KERNEL); if (!indr_priv) return -ENOMEM; @@ -785,9 +834,9 @@ static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv, { int err; - err = __tc_indr_block_cb_register(netdev, rpriv, - mlx5e_rep_indr_setup_tc_cb, - rpriv); + err = __flow_indr_block_cb_register(netdev, rpriv, + mlx5e_rep_indr_setup_tc_cb, + rpriv); if (err) { struct mlx5e_priv *priv = netdev_priv(rpriv->netdev); @@ -800,8 +849,8 @@ static int mlx5e_rep_indr_register_block(struct mlx5e_rep_priv *rpriv, static void mlx5e_rep_indr_unregister_block(struct mlx5e_rep_priv *rpriv, struct net_device *netdev) { - __tc_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_tc_cb, - rpriv); + __flow_indr_block_cb_unregister(netdev, mlx5e_rep_indr_setup_tc_cb, + rpriv); } static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb, @@ -827,6 +876,28 @@ static int mlx5e_nic_rep_netdevice_event(struct notifier_block *nb, return NOTIFY_OK; } +static void +mlx5e_rep_queue_neigh_update_work(struct mlx5e_priv *priv, + struct mlx5e_neigh_hash_entry *nhe, + struct neighbour *n) +{ + /* Take a reference to ensure the neighbour and mlx5 encap + * entry won't be destructed until we drop the reference in + * delayed work. + */ + neigh_hold(n); + + /* This assignment is valid as long as the the neigh reference + * is taken + */ + nhe->n = n; + + if (!queue_work(priv->wq, &nhe->neigh_update_work)) { + mlx5e_rep_neigh_entry_release(nhe); + neigh_release(n); + } +} + static struct mlx5e_neigh_hash_entry * mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv, struct mlx5e_neigh *m_neigh); @@ -849,7 +920,7 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb, case NETEVENT_NEIGH_UPDATE: n = ptr; #if IS_ENABLED(CONFIG_IPV6) - if (n->tbl != &nd_tbl && n->tbl != &arp_tbl) + if (n->tbl != ipv6_stub->nd_tbl && n->tbl != &arp_tbl) #else if (n->tbl != &arp_tbl) #endif @@ -859,34 +930,13 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb, m_neigh.family = n->ops->family; memcpy(&m_neigh.dst_ip, n->primary_key, n->tbl->key_len); - /* We are in atomic context and can't take RTNL mutex, so use - * spin_lock_bh to lookup the neigh table. bh is used since - * netevent can be called from a softirq context. - */ - spin_lock_bh(&neigh_update->encap_lock); + rcu_read_lock(); nhe = mlx5e_rep_neigh_entry_lookup(priv, &m_neigh); - if (!nhe) { - spin_unlock_bh(&neigh_update->encap_lock); + rcu_read_unlock(); + if (!nhe) return NOTIFY_DONE; - } - - /* This assignment is valid as long as the the neigh reference - * is taken - */ - nhe->n = n; - - /* Take a reference to ensure the neighbour and mlx5 encap - * entry won't be destructed until we drop the reference in - * delayed work. - */ - neigh_hold(n); - mlx5e_rep_neigh_entry_hold(nhe); - if (!queue_work(priv->wq, &nhe->neigh_update_work)) { - mlx5e_rep_neigh_entry_release(nhe); - neigh_release(n); - } - spin_unlock_bh(&neigh_update->encap_lock); + mlx5e_rep_queue_neigh_update_work(priv, nhe, n); break; case NETEVENT_DELAY_PROBE_TIME_UPDATE: @@ -897,25 +947,21 @@ static int mlx5e_rep_netevent_event(struct notifier_block *nb, * done per device delay prob time parameter. */ #if IS_ENABLED(CONFIG_IPV6) - if (!p->dev || (p->tbl != &nd_tbl && p->tbl != &arp_tbl)) + if (!p->dev || (p->tbl != ipv6_stub->nd_tbl && p->tbl != &arp_tbl)) #else if (!p->dev || p->tbl != &arp_tbl) #endif return NOTIFY_DONE; - /* We are in atomic context and can't take RTNL mutex, - * so use spin_lock_bh to walk the neigh list and look for - * the relevant device. bh is used since netevent can be - * called from a softirq context. - */ - spin_lock_bh(&neigh_update->encap_lock); - list_for_each_entry(nhe, &neigh_update->neigh_list, neigh_list) { + rcu_read_lock(); + list_for_each_entry_rcu(nhe, &neigh_update->neigh_list, + neigh_list) { if (p->dev == nhe->m_neigh.dev) { found = true; break; } } - spin_unlock_bh(&neigh_update->encap_lock); + rcu_read_unlock(); if (!found) return NOTIFY_DONE; @@ -946,7 +992,7 @@ static int mlx5e_rep_neigh_init(struct mlx5e_rep_priv *rpriv) return err; INIT_LIST_HEAD(&neigh_update->neigh_list); - spin_lock_init(&neigh_update->encap_lock); + mutex_init(&neigh_update->encap_lock); INIT_DELAYED_WORK(&neigh_update->neigh_stats_work, mlx5e_rep_neigh_stats_work); mlx5e_rep_neigh_update_init_interval(rpriv); @@ -973,6 +1019,7 @@ static void mlx5e_rep_neigh_cleanup(struct mlx5e_rep_priv *rpriv) cancel_delayed_work_sync(&rpriv->neigh_update.neigh_stats_work); + mutex_destroy(&neigh_update->encap_lock); rhashtable_destroy(&neigh_update->neigh_ht); } @@ -988,28 +1035,27 @@ static int mlx5e_rep_neigh_entry_insert(struct mlx5e_priv *priv, if (err) return err; - list_add(&nhe->neigh_list, &rpriv->neigh_update.neigh_list); + list_add_rcu(&nhe->neigh_list, &rpriv->neigh_update.neigh_list); return err; } -static void mlx5e_rep_neigh_entry_remove(struct mlx5e_priv *priv, - struct mlx5e_neigh_hash_entry *nhe) +static void mlx5e_rep_neigh_entry_remove(struct mlx5e_neigh_hash_entry *nhe) { - struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5e_rep_priv *rpriv = nhe->priv->ppriv; - spin_lock_bh(&rpriv->neigh_update.encap_lock); + mutex_lock(&rpriv->neigh_update.encap_lock); - list_del(&nhe->neigh_list); + list_del_rcu(&nhe->neigh_list); rhashtable_remove_fast(&rpriv->neigh_update.neigh_ht, &nhe->rhash_node, mlx5e_neigh_ht_params); - spin_unlock_bh(&rpriv->neigh_update.encap_lock); + mutex_unlock(&rpriv->neigh_update.encap_lock); } -/* This function must only be called under RTNL lock or under the - * representor's encap_lock in case RTNL mutex can't be held. +/* This function must only be called under the representor's encap_lock or + * inside rcu read lock section. */ static struct mlx5e_neigh_hash_entry * mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv, @@ -1017,9 +1063,11 @@ mlx5e_rep_neigh_entry_lookup(struct mlx5e_priv *priv, { struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5e_neigh_update_table *neigh_update = &rpriv->neigh_update; + struct mlx5e_neigh_hash_entry *nhe; - return rhashtable_lookup_fast(&neigh_update->neigh_ht, m_neigh, - mlx5e_neigh_ht_params); + nhe = rhashtable_lookup_fast(&neigh_update->neigh_ht, m_neigh, + mlx5e_neigh_ht_params); + return nhe && mlx5e_rep_neigh_entry_hold(nhe) ? nhe : NULL; } static int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv, @@ -1032,8 +1080,10 @@ static int mlx5e_rep_neigh_entry_create(struct mlx5e_priv *priv, if (!*nhe) return -ENOMEM; + (*nhe)->priv = priv; memcpy(&(*nhe)->m_neigh, &e->m_neigh, sizeof(e->m_neigh)); INIT_WORK(&(*nhe)->neigh_update_work, mlx5e_rep_neigh_update); + spin_lock_init(&(*nhe)->encap_list_lock); INIT_LIST_HEAD(&(*nhe)->encap_list); refcount_set(&(*nhe)->refcnt, 1); @@ -1047,19 +1097,6 @@ out_free: return err; } -static void mlx5e_rep_neigh_entry_destroy(struct mlx5e_priv *priv, - struct mlx5e_neigh_hash_entry *nhe) -{ - /* The neigh hash entry must be removed from the hash table regardless - * of the reference count value, so it won't be found by the next - * neigh notification call. The neigh hash entry reference count is - * incremented only during creation and neigh notification calls and - * protects from freeing the nhe struct. - */ - mlx5e_rep_neigh_entry_remove(priv, nhe); - mlx5e_rep_neigh_entry_release(nhe); -} - int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) { @@ -1072,16 +1109,26 @@ int mlx5e_rep_encap_entry_attach(struct mlx5e_priv *priv, err = mlx5_tun_entropy_refcount_inc(tun_entropy, e->reformat_type); if (err) return err; + + mutex_lock(&rpriv->neigh_update.encap_lock); nhe = mlx5e_rep_neigh_entry_lookup(priv, &e->m_neigh); if (!nhe) { err = mlx5e_rep_neigh_entry_create(priv, e, &nhe); if (err) { + mutex_unlock(&rpriv->neigh_update.encap_lock); mlx5_tun_entropy_refcount_dec(tun_entropy, e->reformat_type); return err; } } - list_add(&e->encap_list, &nhe->encap_list); + + e->nhe = nhe; + spin_lock(&nhe->encap_list_lock); + list_add_rcu(&e->encap_list, &nhe->encap_list); + spin_unlock(&nhe->encap_list_lock); + + mutex_unlock(&rpriv->neigh_update.encap_lock); + return 0; } @@ -1091,13 +1138,16 @@ void mlx5e_rep_encap_entry_detach(struct mlx5e_priv *priv, struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_rep_uplink_priv *uplink_priv = &rpriv->uplink_priv; struct mlx5_tun_entropy *tun_entropy = &uplink_priv->tun_entropy; - struct mlx5e_neigh_hash_entry *nhe; - list_del(&e->encap_list); - nhe = mlx5e_rep_neigh_entry_lookup(priv, &e->m_neigh); + if (!e->nhe) + return; + + spin_lock(&e->nhe->encap_list_lock); + list_del_rcu(&e->encap_list); + spin_unlock(&e->nhe->encap_list_lock); - if (list_empty(&nhe->encap_list)) - mlx5e_rep_neigh_entry_destroy(priv, nhe); + mlx5e_rep_neigh_entry_release(e->nhe); + e->nhe = NULL; mlx5_tun_entropy_refcount_dec(tun_entropy, e->reformat_type); } @@ -1160,15 +1210,34 @@ mlx5e_rep_setup_tc_cls_flower(struct mlx5e_priv *priv, } } +static +int mlx5e_rep_setup_tc_cls_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + switch (ma->command) { + case TC_CLSMATCHALL_REPLACE: + return mlx5e_tc_configure_matchall(priv, ma); + case TC_CLSMATCHALL_DESTROY: + return mlx5e_tc_delete_matchall(priv, ma); + case TC_CLSMATCHALL_STATS: + mlx5e_tc_stats_matchall(priv, ma); + return 0; + default: + return -EOPNOTSUPP; + } +} + static int mlx5e_rep_setup_tc_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { + unsigned long flags = MLX5_TC_FLAG(INGRESS) | MLX5_TC_FLAG(ESW_OFFLOAD); struct mlx5e_priv *priv = cb_priv; switch (type) { case TC_SETUP_CLSFLOWER: - return mlx5e_rep_setup_tc_cls_flower(priv, type_data, MLX5E_TC_INGRESS | - MLX5E_TC_ESW_OFFLOAD); + return mlx5e_rep_setup_tc_cls_flower(priv, type_data, flags); + case TC_SETUP_CLSMATCHALL: + return mlx5e_rep_setup_tc_cls_matchall(priv, type_data); default: return -EOPNOTSUPP; } @@ -1180,9 +1249,11 @@ static int mlx5e_rep_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { struct mlx5e_priv *priv = netdev_priv(dev); + struct flow_block_offload *f = type_data; switch (type) { case TC_SETUP_BLOCK: + f->unlocked_driver_cb = true; return flow_block_cb_setup_simple(type_data, &mlx5e_rep_block_cb_list, mlx5e_rep_setup_tc_cb, @@ -1553,7 +1624,7 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_rep_uplink_priv *uplink_priv; - int tc, err; + int err; err = mlx5e_create_tises(priv); if (err) { @@ -1564,6 +1635,7 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { uplink_priv = &rpriv->uplink_priv; + mutex_init(&uplink_priv->unready_flows_lock); INIT_LIST_HEAD(&uplink_priv->unready_flows); /* init shared tc flow table */ @@ -1588,18 +1660,15 @@ static int mlx5e_init_rep_tx(struct mlx5e_priv *priv) tc_esw_cleanup: mlx5e_tc_esw_cleanup(&uplink_priv->tc_ht); destroy_tises: - for (tc = 0; tc < priv->profile->max_tc; tc++) - mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); + mlx5e_destroy_tises(priv); return err; } static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) { struct mlx5e_rep_priv *rpriv = priv->ppriv; - int tc; - for (tc = 0; tc < priv->profile->max_tc; tc++) - mlx5e_destroy_tis(priv->mdev, priv->tisn[tc]); + mlx5e_destroy_tises(priv); if (rpriv->rep->vport == MLX5_VPORT_UPLINK) { /* clean indirect TC block notifications */ @@ -1608,6 +1677,7 @@ static void mlx5e_cleanup_rep_tx(struct mlx5e_priv *priv) /* delete shared tc flow table */ mlx5e_tc_esw_cleanup(&rpriv->uplink_priv.tc_ht); + mutex_destroy(&rpriv->uplink_priv.unready_flows_lock); } } @@ -1731,37 +1801,46 @@ is_devlink_port_supported(const struct mlx5_core_dev *dev, mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport); } +static unsigned int +vport_to_devlink_port_index(const struct mlx5_core_dev *dev, u16 vport_num) +{ + return (MLX5_CAP_GEN(dev, vhca_id) << 16) | vport_num; +} + static int register_devlink_port(struct mlx5_core_dev *dev, struct mlx5e_rep_priv *rpriv) { struct devlink *devlink = priv_to_devlink(dev); struct mlx5_eswitch_rep *rep = rpriv->rep; struct netdev_phys_item_id ppid = {}; - int ret; + unsigned int dl_port_index = 0; if (!is_devlink_port_supported(dev, rpriv)) return 0; - ret = mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid); - if (ret) - return ret; + mlx5e_rep_get_port_parent_id(rpriv->netdev, &ppid); - if (rep->vport == MLX5_VPORT_UPLINK) + if (rep->vport == MLX5_VPORT_UPLINK) { devlink_port_attrs_set(&rpriv->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, PCI_FUNC(dev->pdev->devfn), false, 0, &ppid.id[0], ppid.id_len); - else if (rep->vport == MLX5_VPORT_PF) + dl_port_index = vport_to_devlink_port_index(dev, rep->vport); + } else if (rep->vport == MLX5_VPORT_PF) { devlink_port_attrs_pci_pf_set(&rpriv->dl_port, &ppid.id[0], ppid.id_len, dev->pdev->devfn); - else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, rpriv->rep->vport)) + dl_port_index = rep->vport; + } else if (mlx5_eswitch_is_vf_vport(dev->priv.eswitch, + rpriv->rep->vport)) { devlink_port_attrs_pci_vf_set(&rpriv->dl_port, &ppid.id[0], ppid.id_len, dev->pdev->devfn, rep->vport - 1); + dl_port_index = vport_to_devlink_port_index(dev, rep->vport); + } - return devlink_port_register(devlink, &rpriv->dl_port, rep->vport); + return devlink_port_register(devlink, &rpriv->dl_port, dl_port_index); } static void unregister_devlink_port(struct mlx5_core_dev *dev, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h index c56e6ee4350c..31f83c8adcc9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rep.h @@ -35,6 +35,7 @@ #include <net/ip_tunnels.h> #include <linux/rhashtable.h> +#include <linux/mutex.h> #include "eswitch.h" #include "en.h" #include "lib/port_tun.h" @@ -48,7 +49,7 @@ struct mlx5e_neigh_update_table { */ struct list_head neigh_list; /* protect lookup/remove operations */ - spinlock_t encap_lock; + struct mutex encap_lock; struct notifier_block netevent_nb; struct delayed_work neigh_stats_work; unsigned long min_interval; /* jiffies */ @@ -75,6 +76,8 @@ struct mlx5_rep_uplink_priv { struct mlx5_tun_entropy tun_entropy; + /* protects unready_flows */ + struct mutex unready_flows_lock; struct list_head unready_flows; struct work_struct reoffload_flows_work; }; @@ -86,6 +89,7 @@ struct mlx5e_rep_priv { struct mlx5_flow_handle *vport_rx_rule; struct list_head vport_sqs_list; struct mlx5_rep_uplink_priv uplink_priv; /* valid for uplink rep */ + struct rtnl_link_stats64 prev_vf_vport_stats; struct devlink_port dl_port; }; @@ -107,6 +111,7 @@ struct mlx5e_neigh { struct mlx5e_neigh_hash_entry { struct rhash_head rhash_node; struct mlx5e_neigh m_neigh; + struct mlx5e_priv *priv; /* Save the neigh hash entry in a list on the representor in * addition to the hash table. In order to iterate easily over the @@ -114,6 +119,8 @@ struct mlx5e_neigh_hash_entry { */ struct list_head neigh_list; + /* protects encap list */ + spinlock_t encap_list_lock; /* encap list sharing the same neigh */ struct list_head encap_list; @@ -134,6 +141,8 @@ struct mlx5e_neigh_hash_entry { * 'used' value and avoid neigh deleting by the kernel. */ unsigned long reported_lastuse; + + struct rcu_head rcu; }; enum { @@ -142,6 +151,8 @@ enum { }; struct mlx5e_encap_entry { + /* attached neigh hash entry */ + struct mlx5e_neigh_hash_entry *nhe; /* neigh hash entry list of encaps sharing the same neigh */ struct list_head encap_list; struct mlx5e_neigh m_neigh; @@ -150,7 +161,7 @@ struct mlx5e_encap_entry { */ struct hlist_node encap_hlist; struct list_head flows; - u32 encap_id; + struct mlx5_pkt_reformat *pkt_reformat; const struct ip_tunnel_info *tun_info; unsigned char h_dest[ETH_ALEN]; /* destination eth addr */ @@ -161,6 +172,10 @@ struct mlx5e_encap_entry { u8 flags; char *encap_header; int encap_size; + refcount_t refcnt; + struct completion res_ready; + int compl_result; + struct rcu_head rcu; }; struct mlx5e_rep_sq { @@ -168,7 +183,6 @@ struct mlx5e_rep_sq { struct list_head list; }; -void *mlx5e_alloc_nic_rep_priv(struct mlx5_core_dev *mdev); void mlx5e_rep_register_vport_reps(struct mlx5_core_dev *mdev); void mlx5e_rep_unregister_vport_reps(struct mlx5_core_dev *mdev); bool mlx5e_is_uplink_rep(struct mlx5e_priv *priv); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index ac6e586d403d..d6a547238de0 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -48,6 +48,7 @@ #include "lib/clock.h" #include "en/xdp.h" #include "en/xsk/rx.h" +#include "en/health.h" static inline bool mlx5e_rx_hw_stamp(struct hwtstamp_config *config) { @@ -615,6 +616,8 @@ void mlx5e_poll_ico_cq(struct mlx5e_cq *cq) if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_REQ)) { netdev_WARN_ONCE(cq->channel->netdev, "Bad OP in ICOSQ CQE: 0x%x\n", get_cqe_opcode(cqe)); + if (!test_and_set_bit(MLX5E_SQ_STATE_RECOVERING, &sq->state)) + queue_work(cq->channel->priv->wq, &sq->recover_work); break; } do { @@ -692,8 +695,11 @@ bool mlx5e_post_rx_mpwqes(struct mlx5e_rq *rq) rq->mpwqe.umr_in_progress += rq->mpwqe.umr_last_bulk; rq->mpwqe.actual_wq_head = head; - /* If XSK Fill Ring doesn't have enough frames, busy poll by - * rescheduling the NAPI poll. + /* If XSK Fill Ring doesn't have enough frames, report the error, so + * that one of the actions can be performed: + * 1. If need_wakeup is used, signal that the application has to kick + * the driver when it refills the Fill Ring. + * 2. Otherwise, busy poll by rescheduling the NAPI poll. */ if (unlikely(alloc_err == -ENOMEM && rq->umem)) return true; @@ -859,13 +865,24 @@ tail_padding_csum(struct sk_buff *skb, int offset, } static void -mlx5e_skb_padding_csum(struct sk_buff *skb, int network_depth, __be16 proto, - struct mlx5e_rq_stats *stats) +mlx5e_skb_csum_fixup(struct sk_buff *skb, int network_depth, __be16 proto, + struct mlx5e_rq_stats *stats) { struct ipv6hdr *ip6; struct iphdr *ip4; int pkt_len; + /* Fixup vlan headers, if any */ + if (network_depth > ETH_HLEN) + /* CQE csum is calculated from the IP header and does + * not cover VLAN headers (if present). This will add + * the checksum manually. + */ + skb->csum = csum_partial(skb->data + ETH_HLEN, + network_depth - ETH_HLEN, + skb->csum); + + /* Fixup tail padding, if any */ switch (proto) { case htons(ETH_P_IP): ip4 = (struct iphdr *)(skb->data + network_depth); @@ -931,16 +948,7 @@ static inline void mlx5e_handle_csum(struct net_device *netdev, return; /* CQE csum covers all received bytes */ /* csum might need some fixups ...*/ - if (network_depth > ETH_HLEN) - /* CQE csum is calculated from the IP header and does - * not cover VLAN headers (if present). This will add - * the checksum manually. - */ - skb->csum = csum_partial(skb->data + ETH_HLEN, - network_depth - ETH_HLEN, - skb->csum); - - mlx5e_skb_padding_csum(skb, network_depth, proto, stats); + mlx5e_skb_csum_fixup(skb, network_depth, proto, stats); return; } @@ -1065,11 +1073,6 @@ mlx5e_skb_from_cqe_linear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, prefetchw(va); /* xdp_frame data area */ prefetch(data); - if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) { - rq->stats->wqe_err++; - return NULL; - } - rcu_read_lock(); consumed = mlx5e_xdp_handle(rq, di, va, &rx_headroom, &cqe_bcnt, false); rcu_read_unlock(); @@ -1097,11 +1100,6 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, u16 byte_cnt = cqe_bcnt - headlen; struct sk_buff *skb; - if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) { - rq->stats->wqe_err++; - return NULL; - } - /* XDP is not supported in this configuration, as incoming packets * might spread among multiple pages. */ @@ -1135,6 +1133,15 @@ mlx5e_skb_from_cqe_nonlinear(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, return skb; } +static void trigger_report(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) +{ + struct mlx5_err_cqe *err_cqe = (struct mlx5_err_cqe *)cqe; + + if (cqe_syndrome_needs_recover(err_cqe->syndrome) && + !test_and_set_bit(MLX5E_RQ_STATE_RECOVERING, &rq->state)) + queue_work(rq->channel->priv->wq, &rq->recover_work); +} + void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) { struct mlx5_wq_cyc *wq = &rq->wqe.wq; @@ -1147,6 +1154,12 @@ void mlx5e_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) wi = get_frag(rq, ci); cqe_bcnt = be32_to_cpu(cqe->byte_cnt); + if (unlikely(MLX5E_RX_ERR_CQE(cqe))) { + trigger_report(rq, cqe); + rq->stats->wqe_err++; + goto free_wqe; + } + skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe, mlx5e_skb_from_cqe_linear, mlx5e_skb_from_cqe_nonlinear, @@ -1188,6 +1201,11 @@ void mlx5e_handle_rx_cqe_rep(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) wi = get_frag(rq, ci); cqe_bcnt = be32_to_cpu(cqe->byte_cnt); + if (unlikely(MLX5E_RX_ERR_CQE(cqe))) { + rq->stats->wqe_err++; + goto free_wqe; + } + skb = rq->wqe.skb_from_cqe(rq, cqe, wi, cqe_bcnt); if (!skb) { /* probably for XDP */ @@ -1322,7 +1340,8 @@ void mlx5e_handle_rx_cqe_mpwrq(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) wi->consumed_strides += cstrides; - if (unlikely(get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)) { + if (unlikely(MLX5E_RX_ERR_CQE(cqe))) { + trigger_report(rq, cqe); rq->stats->wqe_err++; goto mpwrq_cqe_out; } @@ -1498,6 +1517,11 @@ void mlx5i_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) wi = get_frag(rq, ci); cqe_bcnt = be32_to_cpu(cqe->byte_cnt); + if (unlikely(MLX5E_RX_ERR_CQE(cqe))) { + rq->stats->wqe_err++; + goto wq_free_wqe; + } + skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe, mlx5e_skb_from_cqe_linear, mlx5e_skb_from_cqe_nonlinear, @@ -1533,26 +1557,27 @@ void mlx5e_ipsec_handle_rx_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe) wi = get_frag(rq, ci); cqe_bcnt = be32_to_cpu(cqe->byte_cnt); + if (unlikely(MLX5E_RX_ERR_CQE(cqe))) { + rq->stats->wqe_err++; + goto wq_free_wqe; + } + skb = INDIRECT_CALL_2(rq->wqe.skb_from_cqe, mlx5e_skb_from_cqe_linear, mlx5e_skb_from_cqe_nonlinear, rq, cqe, wi, cqe_bcnt); - if (unlikely(!skb)) { - /* a DROP, save the page-reuse checks */ - mlx5e_free_rx_wqe(rq, wi, true); - goto wq_cyc_pop; - } + if (unlikely(!skb)) /* a DROP, save the page-reuse checks */ + goto wq_free_wqe; + skb = mlx5e_ipsec_handle_rx_skb(rq->netdev, skb, &cqe_bcnt); - if (unlikely(!skb)) { - mlx5e_free_rx_wqe(rq, wi, true); - goto wq_cyc_pop; - } + if (unlikely(!skb)) + goto wq_free_wqe; mlx5e_complete_rx_cqe(rq, cqe, cqe_bcnt, skb); napi_gro_receive(rq->cq.napi, skb); +wq_free_wqe: mlx5e_free_rx_wqe(rq, wi, true); -wq_cyc_pop: mlx5_wq_cyc_pop(wq); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index 57f9f346d213..ac6fdcda7019 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -74,6 +74,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_mpwqe) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_inlnw) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_nops) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_xdp_tx_cqe) }, @@ -90,6 +91,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_xmit) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_mpwqe) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_inlnw) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_nops) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_full) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_err) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_xdp_cqes) }, @@ -107,6 +109,7 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_cache_waive) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_congst_umr) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_arfs_err) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_recover) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_events) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_poll) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, ch_arm) }, @@ -200,6 +203,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_xdp_tx_xmit += xdpsq_stats->xmit; s->rx_xdp_tx_mpwqe += xdpsq_stats->mpwqe; s->rx_xdp_tx_inlnw += xdpsq_stats->inlnw; + s->rx_xdp_tx_nops += xdpsq_stats->nops; s->rx_xdp_tx_full += xdpsq_stats->full; s->rx_xdp_tx_err += xdpsq_stats->err; s->rx_xdp_tx_cqe += xdpsq_stats->cqes; @@ -217,6 +221,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->rx_cache_waive += rq_stats->cache_waive; s->rx_congst_umr += rq_stats->congst_umr; s->rx_arfs_err += rq_stats->arfs_err; + s->rx_recover += rq_stats->recover; s->ch_events += ch_stats->events; s->ch_poll += ch_stats->poll; s->ch_arm += ch_stats->arm; @@ -227,6 +232,7 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->tx_xdp_xmit += xdpsq_red_stats->xmit; s->tx_xdp_mpwqe += xdpsq_red_stats->mpwqe; s->tx_xdp_inlnw += xdpsq_red_stats->inlnw; + s->tx_xdp_nops += xdpsq_red_stats->nops; s->tx_xdp_full += xdpsq_red_stats->full; s->tx_xdp_err += xdpsq_red_stats->err; s->tx_xdp_cqes += xdpsq_red_stats->cqes; @@ -363,17 +369,27 @@ static void mlx5e_grp_q_update_stats(struct mlx5e_priv *priv) } #define VNIC_ENV_OFF(c) MLX5_BYTE_OFF(query_vnic_env_out, c) -static const struct counter_desc vnic_env_stats_desc[] = { +static const struct counter_desc vnic_env_stats_steer_desc[] = { { "rx_steer_missed_packets", VNIC_ENV_OFF(vport_env.nic_receive_steering_discard) }, }; -#define NUM_VNIC_ENV_COUNTERS ARRAY_SIZE(vnic_env_stats_desc) +static const struct counter_desc vnic_env_stats_dev_oob_desc[] = { + { "dev_internal_queue_oob", + VNIC_ENV_OFF(vport_env.internal_rq_out_of_buffer) }, +}; + +#define NUM_VNIC_ENV_STEER_COUNTERS(dev) \ + (MLX5_CAP_GEN(dev, nic_receive_steering_discard) ? \ + ARRAY_SIZE(vnic_env_stats_steer_desc) : 0) +#define NUM_VNIC_ENV_DEV_OOB_COUNTERS(dev) \ + (MLX5_CAP_GEN(dev, vnic_env_int_rq_oob) ? \ + ARRAY_SIZE(vnic_env_stats_dev_oob_desc) : 0) static int mlx5e_grp_vnic_env_get_num_stats(struct mlx5e_priv *priv) { - return MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard) ? - NUM_VNIC_ENV_COUNTERS : 0; + return NUM_VNIC_ENV_STEER_COUNTERS(priv->mdev) + + NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev); } static int mlx5e_grp_vnic_env_fill_strings(struct mlx5e_priv *priv, u8 *data, @@ -381,12 +397,13 @@ static int mlx5e_grp_vnic_env_fill_strings(struct mlx5e_priv *priv, u8 *data, { int i; - if (!MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard)) - return idx; + for (i = 0; i < NUM_VNIC_ENV_STEER_COUNTERS(priv->mdev); i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + vnic_env_stats_steer_desc[i].format); - for (i = 0; i < NUM_VNIC_ENV_COUNTERS; i++) + for (i = 0; i < NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev); i++) strcpy(data + (idx++) * ETH_GSTRING_LEN, - vnic_env_stats_desc[i].format); + vnic_env_stats_dev_oob_desc[i].format); return idx; } @@ -395,12 +412,13 @@ static int mlx5e_grp_vnic_env_fill_stats(struct mlx5e_priv *priv, u64 *data, { int i; - if (!MLX5_CAP_GEN(priv->mdev, nic_receive_steering_discard)) - return idx; - - for (i = 0; i < NUM_VNIC_ENV_COUNTERS; i++) + for (i = 0; i < NUM_VNIC_ENV_STEER_COUNTERS(priv->mdev); i++) data[idx++] = MLX5E_READ_CTR64_BE(priv->stats.vnic.query_vnic_env_out, - vnic_env_stats_desc, i); + vnic_env_stats_steer_desc, i); + + for (i = 0; i < NUM_VNIC_ENV_DEV_OOB_COUNTERS(priv->mdev); i++) + data[idx++] = MLX5E_READ_CTR32_BE(priv->stats.vnic.query_vnic_env_out, + vnic_env_stats_dev_oob_desc, i); return idx; } @@ -963,6 +981,147 @@ static void mlx5e_grp_pcie_update_stats(struct mlx5e_priv *priv) mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_MPCNT, 0, 0); } +#define PPORT_PER_TC_PRIO_OFF(c) \ + MLX5_BYTE_OFF(ppcnt_reg, \ + counter_set.eth_per_tc_prio_grp_data_layout.c##_high) + +static const struct counter_desc pport_per_tc_prio_stats_desc[] = { + { "rx_prio%d_buf_discard", PPORT_PER_TC_PRIO_OFF(no_buffer_discard_uc) }, +}; + +#define NUM_PPORT_PER_TC_PRIO_COUNTERS ARRAY_SIZE(pport_per_tc_prio_stats_desc) + +#define PPORT_PER_TC_CONGEST_PRIO_OFF(c) \ + MLX5_BYTE_OFF(ppcnt_reg, \ + counter_set.eth_per_tc_congest_prio_grp_data_layout.c##_high) + +static const struct counter_desc pport_per_tc_congest_prio_stats_desc[] = { + { "rx_prio%d_cong_discard", PPORT_PER_TC_CONGEST_PRIO_OFF(wred_discard) }, + { "rx_prio%d_marked", PPORT_PER_TC_CONGEST_PRIO_OFF(ecn_marked_tc) }, +}; + +#define NUM_PPORT_PER_TC_CONGEST_PRIO_COUNTERS \ + ARRAY_SIZE(pport_per_tc_congest_prio_stats_desc) + +static int mlx5e_grp_per_tc_prio_get_num_stats(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + + if (!MLX5_CAP_GEN(mdev, sbcam_reg)) + return 0; + + return NUM_PPORT_PER_TC_PRIO_COUNTERS * NUM_PPORT_PRIO; +} + +static int mlx5e_grp_per_port_buffer_congest_fill_strings(struct mlx5e_priv *priv, + u8 *data, int idx) +{ + struct mlx5_core_dev *mdev = priv->mdev; + int i, prio; + + if (!MLX5_CAP_GEN(mdev, sbcam_reg)) + return idx; + + for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { + for (i = 0; i < NUM_PPORT_PER_TC_PRIO_COUNTERS; i++) + sprintf(data + (idx++) * ETH_GSTRING_LEN, + pport_per_tc_prio_stats_desc[i].format, prio); + for (i = 0; i < NUM_PPORT_PER_TC_CONGEST_PRIO_COUNTERS; i++) + sprintf(data + (idx++) * ETH_GSTRING_LEN, + pport_per_tc_congest_prio_stats_desc[i].format, prio); + } + + return idx; +} + +static int mlx5e_grp_per_port_buffer_congest_fill_stats(struct mlx5e_priv *priv, + u64 *data, int idx) +{ + struct mlx5e_pport_stats *pport = &priv->stats.pport; + struct mlx5_core_dev *mdev = priv->mdev; + int i, prio; + + if (!MLX5_CAP_GEN(mdev, sbcam_reg)) + return idx; + + for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { + for (i = 0; i < NUM_PPORT_PER_TC_PRIO_COUNTERS; i++) + data[idx++] = + MLX5E_READ_CTR64_BE(&pport->per_tc_prio_counters[prio], + pport_per_tc_prio_stats_desc, i); + for (i = 0; i < NUM_PPORT_PER_TC_CONGEST_PRIO_COUNTERS ; i++) + data[idx++] = + MLX5E_READ_CTR64_BE(&pport->per_tc_congest_prio_counters[prio], + pport_per_tc_congest_prio_stats_desc, i); + } + + return idx; +} + +static void mlx5e_grp_per_tc_prio_update_stats(struct mlx5e_priv *priv) +{ + struct mlx5e_pport_stats *pstats = &priv->stats.pport; + struct mlx5_core_dev *mdev = priv->mdev; + u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {}; + int sz = MLX5_ST_SZ_BYTES(ppcnt_reg); + void *out; + int prio; + + if (!MLX5_CAP_GEN(mdev, sbcam_reg)) + return; + + MLX5_SET(ppcnt_reg, in, pnat, 2); + MLX5_SET(ppcnt_reg, in, grp, MLX5_PER_TRAFFIC_CLASS_COUNTERS_GROUP); + for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { + out = pstats->per_tc_prio_counters[prio]; + MLX5_SET(ppcnt_reg, in, prio_tc, prio); + mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0); + } +} + +static int mlx5e_grp_per_tc_congest_prio_get_num_stats(struct mlx5e_priv *priv) +{ + struct mlx5_core_dev *mdev = priv->mdev; + + if (!MLX5_CAP_GEN(mdev, sbcam_reg)) + return 0; + + return NUM_PPORT_PER_TC_CONGEST_PRIO_COUNTERS * NUM_PPORT_PRIO; +} + +static void mlx5e_grp_per_tc_congest_prio_update_stats(struct mlx5e_priv *priv) +{ + struct mlx5e_pport_stats *pstats = &priv->stats.pport; + struct mlx5_core_dev *mdev = priv->mdev; + u32 in[MLX5_ST_SZ_DW(ppcnt_reg)] = {}; + int sz = MLX5_ST_SZ_BYTES(ppcnt_reg); + void *out; + int prio; + + if (!MLX5_CAP_GEN(mdev, sbcam_reg)) + return; + + MLX5_SET(ppcnt_reg, in, pnat, 2); + MLX5_SET(ppcnt_reg, in, grp, MLX5_PER_TRAFFIC_CLASS_CONGESTION_GROUP); + for (prio = 0; prio < NUM_PPORT_PRIO; prio++) { + out = pstats->per_tc_congest_prio_counters[prio]; + MLX5_SET(ppcnt_reg, in, prio_tc, prio); + mlx5_core_access_reg(mdev, in, sz, out, sz, MLX5_REG_PPCNT, 0, 0); + } +} + +static int mlx5e_grp_per_port_buffer_congest_get_num_stats(struct mlx5e_priv *priv) +{ + return mlx5e_grp_per_tc_prio_get_num_stats(priv) + + mlx5e_grp_per_tc_congest_prio_get_num_stats(priv); +} + +static void mlx5e_grp_per_port_buffer_congest_update_stats(struct mlx5e_priv *priv) +{ + mlx5e_grp_per_tc_prio_update_stats(priv); + mlx5e_grp_per_tc_congest_prio_update_stats(priv); +} + #define PPORT_PER_PRIO_OFF(c) \ MLX5_BYTE_OFF(ppcnt_reg, \ counter_set.eth_per_prio_grp_data_layout.c##_high) @@ -1294,6 +1453,7 @@ static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, cache_waive) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, congst_umr) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, arfs_err) }, + { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, recover) }, }; static const struct counter_desc sq_stats_desc[] = { @@ -1331,6 +1491,7 @@ static const struct counter_desc rq_xdpsq_stats_desc[] = { { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) }, + { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, { MLX5E_DECLARE_RQ_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, @@ -1340,6 +1501,7 @@ static const struct counter_desc xdpsq_stats_desc[] = { { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, xmit) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, mpwqe) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, inlnw) }, + { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, nops) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, full) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, err) }, { MLX5E_DECLARE_XDPSQ_STAT(struct mlx5e_xdpsq_stats, cqes) }, @@ -1589,7 +1751,13 @@ const struct mlx5e_stats_grp mlx5e_stats_grps[] = { .get_num_stats = mlx5e_grp_channels_get_num_stats, .fill_strings = mlx5e_grp_channels_fill_strings, .fill_stats = mlx5e_grp_channels_fill_stats, - } + }, + { + .get_num_stats = mlx5e_grp_per_port_buffer_congest_get_num_stats, + .fill_strings = mlx5e_grp_per_port_buffer_congest_fill_strings, + .fill_stats = mlx5e_grp_per_port_buffer_congest_fill_stats, + .update_stats = mlx5e_grp_per_port_buffer_congest_update_stats, + }, }; const int mlx5e_num_stats_grps = ARRAY_SIZE(mlx5e_stats_grps); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 76ac111e14d0..79f261bf86ac 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -81,6 +81,7 @@ struct mlx5e_sw_stats { u64 rx_xdp_tx_xmit; u64 rx_xdp_tx_mpwqe; u64 rx_xdp_tx_inlnw; + u64 rx_xdp_tx_nops; u64 rx_xdp_tx_full; u64 rx_xdp_tx_err; u64 rx_xdp_tx_cqe; @@ -97,6 +98,7 @@ struct mlx5e_sw_stats { u64 tx_xdp_xmit; u64 tx_xdp_mpwqe; u64 tx_xdp_inlnw; + u64 tx_xdp_nops; u64 tx_xdp_full; u64 tx_xdp_err; u64 tx_xdp_cqes; @@ -114,6 +116,7 @@ struct mlx5e_sw_stats { u64 rx_cache_waive; u64 rx_congst_umr; u64 rx_arfs_err; + u64 rx_recover; u64 ch_events; u64 ch_poll; u64 ch_arm; @@ -204,6 +207,8 @@ struct mlx5e_pport_stats { __be64 phy_counters[MLX5_ST_SZ_QW(ppcnt_reg)]; __be64 phy_statistical_counters[MLX5_ST_SZ_QW(ppcnt_reg)]; __be64 eth_ext_counters[MLX5_ST_SZ_QW(ppcnt_reg)]; + __be64 per_tc_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)]; + __be64 per_tc_congest_prio_counters[NUM_PPORT_PRIO][MLX5_ST_SZ_QW(ppcnt_reg)]; }; #define PCIE_PERF_GET(pcie_stats, c) \ @@ -247,6 +252,7 @@ struct mlx5e_rq_stats { u64 cache_waive; u64 congst_umr; u64 arfs_err; + u64 recover; }; struct mlx5e_sq_stats { @@ -288,6 +294,7 @@ struct mlx5e_xdpsq_stats { u64 xmit; u64 mpwqe; u64 inlnw; + u64 nops; u64 full; u64 err; /* dirtied @completion */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 00b2d4a86159..da7555fdb4d5 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -38,6 +38,8 @@ #include <linux/mlx5/fs.h> #include <linux/mlx5/device.h> #include <linux/rhashtable.h> +#include <linux/refcount.h> +#include <linux/completion.h> #include <net/tc_act/tc_mirred.h> #include <net/tc_act/tc_vlan.h> #include <net/tc_act/tc_tunnel_key.h> @@ -54,30 +56,32 @@ #include "en/tc_tun.h" #include "lib/devcom.h" #include "lib/geneve.h" +#include "diag/en_tc_tracepoint.h" struct mlx5_nic_flow_attr { u32 action; u32 flow_tag; - u32 mod_hdr_id; + struct mlx5_modify_hdr *modify_hdr; u32 hairpin_tirn; u8 match_level; struct mlx5_flow_table *hairpin_ft; struct mlx5_fc *counter; }; -#define MLX5E_TC_FLOW_BASE (MLX5E_TC_LAST_EXPORTED_BIT + 1) +#define MLX5E_TC_FLOW_BASE (MLX5E_TC_FLAG_LAST_EXPORTED_BIT + 1) enum { - MLX5E_TC_FLOW_INGRESS = MLX5E_TC_INGRESS, - MLX5E_TC_FLOW_EGRESS = MLX5E_TC_EGRESS, - MLX5E_TC_FLOW_ESWITCH = MLX5E_TC_ESW_OFFLOAD, - MLX5E_TC_FLOW_NIC = MLX5E_TC_NIC_OFFLOAD, - MLX5E_TC_FLOW_OFFLOADED = BIT(MLX5E_TC_FLOW_BASE), - MLX5E_TC_FLOW_HAIRPIN = BIT(MLX5E_TC_FLOW_BASE + 1), - MLX5E_TC_FLOW_HAIRPIN_RSS = BIT(MLX5E_TC_FLOW_BASE + 2), - MLX5E_TC_FLOW_SLOW = BIT(MLX5E_TC_FLOW_BASE + 3), - MLX5E_TC_FLOW_DUP = BIT(MLX5E_TC_FLOW_BASE + 4), - MLX5E_TC_FLOW_NOT_READY = BIT(MLX5E_TC_FLOW_BASE + 5), + MLX5E_TC_FLOW_FLAG_INGRESS = MLX5E_TC_FLAG_INGRESS_BIT, + MLX5E_TC_FLOW_FLAG_EGRESS = MLX5E_TC_FLAG_EGRESS_BIT, + MLX5E_TC_FLOW_FLAG_ESWITCH = MLX5E_TC_FLAG_ESW_OFFLOAD_BIT, + MLX5E_TC_FLOW_FLAG_NIC = MLX5E_TC_FLAG_NIC_OFFLOAD_BIT, + MLX5E_TC_FLOW_FLAG_OFFLOADED = MLX5E_TC_FLOW_BASE, + MLX5E_TC_FLOW_FLAG_HAIRPIN = MLX5E_TC_FLOW_BASE + 1, + MLX5E_TC_FLOW_FLAG_HAIRPIN_RSS = MLX5E_TC_FLOW_BASE + 2, + MLX5E_TC_FLOW_FLAG_SLOW = MLX5E_TC_FLOW_BASE + 3, + MLX5E_TC_FLOW_FLAG_DUP = MLX5E_TC_FLOW_BASE + 4, + MLX5E_TC_FLOW_FLAG_NOT_READY = MLX5E_TC_FLOW_BASE + 5, + MLX5E_TC_FLOW_FLAG_DELETED = MLX5E_TC_FLOW_BASE + 6, }; #define MLX5E_TC_MAX_SPLITS 1 @@ -100,6 +104,7 @@ enum { * container_of(helper item, containing struct type, helper field[index]) */ struct encap_flow_item { + struct mlx5e_encap_entry *e; /* attached encap instance */ struct list_head list; int index; }; @@ -108,7 +113,7 @@ struct mlx5e_tc_flow { struct rhash_head node; struct mlx5e_priv *priv; u64 cookie; - u16 flags; + unsigned long flags; struct mlx5_flow_handle *rule[MLX5E_TC_MAX_SPLITS + 1]; /* Flow can be associated with multiple encap IDs. * The number of encaps is bounded by the number of supported @@ -116,10 +121,17 @@ struct mlx5e_tc_flow { */ struct encap_flow_item encaps[MLX5_MAX_FLOW_FWD_VPORTS]; struct mlx5e_tc_flow *peer_flow; + struct mlx5e_mod_hdr_entry *mh; /* attached mod header instance */ struct list_head mod_hdr; /* flows sharing the same mod hdr ID */ + struct mlx5e_hairpin_entry *hpe; /* attached hairpin instance */ struct list_head hairpin; /* flows sharing the same hairpin */ struct list_head peer; /* flows with peer flow */ struct list_head unready; /* flows not ready to be offloaded (e.g due to missing route) */ + int tmp_efi_index; + struct list_head tmp_list; /* temporary flow list used by neigh update */ + refcount_t refcnt; + struct rcu_head rcu_head; + struct completion init_done; union { struct mlx5_esw_flow_attr esw_attr[0]; struct mlx5_nic_flow_attr nic_attr[0]; @@ -157,12 +169,20 @@ struct mlx5e_hairpin_entry { /* a node of a hash table which keeps all the hairpin entries */ struct hlist_node hairpin_hlist; + /* protects flows list */ + spinlock_t flows_lock; /* flows sharing the same hairpin */ struct list_head flows; + /* hpe's that were not fully initialized when dead peer update event + * function traversed them. + */ + struct list_head dead_peer_wait_list; u16 peer_vhca_id; u8 prio; struct mlx5e_hairpin *hp; + refcount_t refcnt; + struct completion res_ready; }; struct mod_hdr_key { @@ -174,16 +194,93 @@ struct mlx5e_mod_hdr_entry { /* a node of a hash table which keeps all the mod_hdr entries */ struct hlist_node mod_hdr_hlist; + /* protects flows list */ + spinlock_t flows_lock; /* flows sharing the same mod_hdr entry */ struct list_head flows; struct mod_hdr_key key; - u32 mod_hdr_id; + struct mlx5_modify_hdr *modify_hdr; + + refcount_t refcnt; + struct completion res_ready; + int compl_result; }; #define MLX5_MH_ACT_SZ MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) +static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow); + +static struct mlx5e_tc_flow *mlx5e_flow_get(struct mlx5e_tc_flow *flow) +{ + if (!flow || !refcount_inc_not_zero(&flow->refcnt)) + return ERR_PTR(-EINVAL); + return flow; +} + +static void mlx5e_flow_put(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow) +{ + if (refcount_dec_and_test(&flow->refcnt)) { + mlx5e_tc_del_flow(priv, flow); + kfree_rcu(flow, rcu_head); + } +} + +static void __flow_flag_set(struct mlx5e_tc_flow *flow, unsigned long flag) +{ + /* Complete all memory stores before setting bit. */ + smp_mb__before_atomic(); + set_bit(flag, &flow->flags); +} + +#define flow_flag_set(flow, flag) __flow_flag_set(flow, MLX5E_TC_FLOW_FLAG_##flag) + +static bool __flow_flag_test_and_set(struct mlx5e_tc_flow *flow, + unsigned long flag) +{ + /* test_and_set_bit() provides all necessary barriers */ + return test_and_set_bit(flag, &flow->flags); +} + +#define flow_flag_test_and_set(flow, flag) \ + __flow_flag_test_and_set(flow, \ + MLX5E_TC_FLOW_FLAG_##flag) + +static void __flow_flag_clear(struct mlx5e_tc_flow *flow, unsigned long flag) +{ + /* Complete all memory stores before clearing bit. */ + smp_mb__before_atomic(); + clear_bit(flag, &flow->flags); +} + +#define flow_flag_clear(flow, flag) __flow_flag_clear(flow, \ + MLX5E_TC_FLOW_FLAG_##flag) + +static bool __flow_flag_test(struct mlx5e_tc_flow *flow, unsigned long flag) +{ + bool ret = test_bit(flag, &flow->flags); + + /* Read fields of flow structure only after checking flags. */ + smp_mb__after_atomic(); + return ret; +} + +#define flow_flag_test(flow, flag) __flow_flag_test(flow, \ + MLX5E_TC_FLOW_FLAG_##flag) + +static bool mlx5e_is_eswitch_flow(struct mlx5e_tc_flow *flow) +{ + return flow_flag_test(flow, ESWITCH); +} + +static bool mlx5e_is_offloaded_flow(struct mlx5e_tc_flow *flow) +{ + return flow_flag_test(flow, OFFLOADED); +} + static inline u32 hash_mod_hdr_info(struct mod_hdr_key *key) { return jhash(key->actions, @@ -199,15 +296,62 @@ static inline int cmp_mod_hdr_info(struct mod_hdr_key *a, return memcmp(a->actions, b->actions, a->num_actions * MLX5_MH_ACT_SZ); } +static struct mod_hdr_tbl * +get_mod_hdr_table(struct mlx5e_priv *priv, int namespace) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + return namespace == MLX5_FLOW_NAMESPACE_FDB ? &esw->offloads.mod_hdr : + &priv->fs.tc.mod_hdr; +} + +static struct mlx5e_mod_hdr_entry * +mlx5e_mod_hdr_get(struct mod_hdr_tbl *tbl, struct mod_hdr_key *key, u32 hash_key) +{ + struct mlx5e_mod_hdr_entry *mh, *found = NULL; + + hash_for_each_possible(tbl->hlist, mh, mod_hdr_hlist, hash_key) { + if (!cmp_mod_hdr_info(&mh->key, key)) { + refcount_inc(&mh->refcnt); + found = mh; + break; + } + } + + return found; +} + +static void mlx5e_mod_hdr_put(struct mlx5e_priv *priv, + struct mlx5e_mod_hdr_entry *mh, + int namespace) +{ + struct mod_hdr_tbl *tbl = get_mod_hdr_table(priv, namespace); + + if (!refcount_dec_and_mutex_lock(&mh->refcnt, &tbl->lock)) + return; + hash_del(&mh->mod_hdr_hlist); + mutex_unlock(&tbl->lock); + + WARN_ON(!list_empty(&mh->flows)); + if (mh->compl_result > 0) + mlx5_modify_header_dealloc(priv->mdev, mh->modify_hdr); + + kfree(mh); +} + +static int get_flow_name_space(struct mlx5e_tc_flow *flow) +{ + return mlx5e_is_eswitch_flow(flow) ? + MLX5_FLOW_NAMESPACE_FDB : MLX5_FLOW_NAMESPACE_KERNEL; +} static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct mlx5e_tc_flow_parse_attr *parse_attr) { - struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; int num_actions, actions_size, namespace, err; struct mlx5e_mod_hdr_entry *mh; + struct mod_hdr_tbl *tbl; struct mod_hdr_key key; - bool found = false; u32 hash_key; num_actions = parse_attr->num_mod_hdr_actions; @@ -218,80 +362,82 @@ static int mlx5e_attach_mod_hdr(struct mlx5e_priv *priv, hash_key = hash_mod_hdr_info(&key); - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { - namespace = MLX5_FLOW_NAMESPACE_FDB; - hash_for_each_possible(esw->offloads.mod_hdr_tbl, mh, - mod_hdr_hlist, hash_key) { - if (!cmp_mod_hdr_info(&mh->key, &key)) { - found = true; - break; - } - } - } else { - namespace = MLX5_FLOW_NAMESPACE_KERNEL; - hash_for_each_possible(priv->fs.tc.mod_hdr_tbl, mh, - mod_hdr_hlist, hash_key) { - if (!cmp_mod_hdr_info(&mh->key, &key)) { - found = true; - break; - } - } - } + namespace = get_flow_name_space(flow); + tbl = get_mod_hdr_table(priv, namespace); + + mutex_lock(&tbl->lock); + mh = mlx5e_mod_hdr_get(tbl, &key, hash_key); + if (mh) { + mutex_unlock(&tbl->lock); + wait_for_completion(&mh->res_ready); - if (found) + if (mh->compl_result < 0) { + err = -EREMOTEIO; + goto attach_header_err; + } goto attach_flow; + } mh = kzalloc(sizeof(*mh) + actions_size, GFP_KERNEL); - if (!mh) + if (!mh) { + mutex_unlock(&tbl->lock); return -ENOMEM; + } mh->key.actions = (void *)mh + sizeof(*mh); memcpy(mh->key.actions, key.actions, actions_size); mh->key.num_actions = num_actions; + spin_lock_init(&mh->flows_lock); INIT_LIST_HEAD(&mh->flows); - - err = mlx5_modify_header_alloc(priv->mdev, namespace, - mh->key.num_actions, - mh->key.actions, - &mh->mod_hdr_id); - if (err) - goto out_err; - - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) - hash_add(esw->offloads.mod_hdr_tbl, &mh->mod_hdr_hlist, hash_key); - else - hash_add(priv->fs.tc.mod_hdr_tbl, &mh->mod_hdr_hlist, hash_key); + refcount_set(&mh->refcnt, 1); + init_completion(&mh->res_ready); + + hash_add(tbl->hlist, &mh->mod_hdr_hlist, hash_key); + mutex_unlock(&tbl->lock); + + mh->modify_hdr = mlx5_modify_header_alloc(priv->mdev, namespace, + mh->key.num_actions, + mh->key.actions); + if (IS_ERR(mh->modify_hdr)) { + err = PTR_ERR(mh->modify_hdr); + mh->compl_result = err; + goto alloc_header_err; + } + mh->compl_result = 1; + complete_all(&mh->res_ready); attach_flow: + flow->mh = mh; + spin_lock(&mh->flows_lock); list_add(&flow->mod_hdr, &mh->flows); - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) - flow->esw_attr->mod_hdr_id = mh->mod_hdr_id; + spin_unlock(&mh->flows_lock); + if (mlx5e_is_eswitch_flow(flow)) + flow->esw_attr->modify_hdr = mh->modify_hdr; else - flow->nic_attr->mod_hdr_id = mh->mod_hdr_id; + flow->nic_attr->modify_hdr = mh->modify_hdr; return 0; -out_err: - kfree(mh); +alloc_header_err: + complete_all(&mh->res_ready); +attach_header_err: + mlx5e_mod_hdr_put(priv, mh, namespace); return err; } static void mlx5e_detach_mod_hdr(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { - struct list_head *next = flow->mod_hdr.next; + /* flow wasn't fully initialized */ + if (!flow->mh) + return; + spin_lock(&flow->mh->flows_lock); list_del(&flow->mod_hdr); + spin_unlock(&flow->mh->flows_lock); - if (list_empty(next)) { - struct mlx5e_mod_hdr_entry *mh; - - mh = list_entry(next, struct mlx5e_mod_hdr_entry, flows); - - mlx5_modify_header_dealloc(priv->mdev, mh->mod_hdr_id); - hash_del(&mh->mod_hdr_hlist); - kfree(mh); - } + mlx5e_mod_hdr_put(priv, flow->mh, get_flow_name_space(flow)); + flow->mh = NULL; } static @@ -555,13 +701,35 @@ static struct mlx5e_hairpin_entry *mlx5e_hairpin_get(struct mlx5e_priv *priv, hash_for_each_possible(priv->fs.tc.hairpin_tbl, hpe, hairpin_hlist, hash_key) { - if (hpe->peer_vhca_id == peer_vhca_id && hpe->prio == prio) + if (hpe->peer_vhca_id == peer_vhca_id && hpe->prio == prio) { + refcount_inc(&hpe->refcnt); return hpe; + } } return NULL; } +static void mlx5e_hairpin_put(struct mlx5e_priv *priv, + struct mlx5e_hairpin_entry *hpe) +{ + /* no more hairpin flows for us, release the hairpin pair */ + if (!refcount_dec_and_mutex_lock(&hpe->refcnt, &priv->fs.tc.hairpin_tbl_lock)) + return; + hash_del(&hpe->hairpin_hlist); + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); + + if (!IS_ERR_OR_NULL(hpe->hp)) { + netdev_dbg(priv->netdev, "del hairpin: peer %s\n", + dev_name(hpe->hp->pair->peer_mdev->device)); + + mlx5e_hairpin_destroy(hpe->hp); + } + + WARN_ON(!list_empty(&hpe->flows)); + kfree(hpe); +} + #define UNKNOWN_MATCH_PRIO 8 static int mlx5e_hairpin_get_prio(struct mlx5e_priv *priv, @@ -627,17 +795,37 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, extack); if (err) return err; + + mutex_lock(&priv->fs.tc.hairpin_tbl_lock); hpe = mlx5e_hairpin_get(priv, peer_id, match_prio); - if (hpe) + if (hpe) { + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); + wait_for_completion(&hpe->res_ready); + + if (IS_ERR(hpe->hp)) { + err = -EREMOTEIO; + goto out_err; + } goto attach_flow; + } hpe = kzalloc(sizeof(*hpe), GFP_KERNEL); - if (!hpe) + if (!hpe) { + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); return -ENOMEM; + } + spin_lock_init(&hpe->flows_lock); INIT_LIST_HEAD(&hpe->flows); + INIT_LIST_HEAD(&hpe->dead_peer_wait_list); hpe->peer_vhca_id = peer_id; hpe->prio = match_prio; + refcount_set(&hpe->refcnt, 1); + init_completion(&hpe->res_ready); + + hash_add(priv->fs.tc.hairpin_tbl, &hpe->hairpin_hlist, + hash_hairpin_info(peer_id, match_prio)); + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); params.log_data_size = 15; params.log_data_size = min_t(u8, params.log_data_size, @@ -659,9 +847,11 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, params.num_channels = link_speed64; hp = mlx5e_hairpin_create(priv, ¶ms, peer_ifindex); + hpe->hp = hp; + complete_all(&hpe->res_ready); if (IS_ERR(hp)) { err = PTR_ERR(hp); - goto create_hairpin_err; + goto out_err; } netdev_dbg(priv->netdev, "add hairpin: tirn %x rqn %x peer %s sqn %x prio %d (log) data %d packets %d\n", @@ -669,46 +859,39 @@ static int mlx5e_hairpin_flow_add(struct mlx5e_priv *priv, dev_name(hp->pair->peer_mdev->device), hp->pair->sqn[0], match_prio, params.log_data_size, params.log_num_packets); - hpe->hp = hp; - hash_add(priv->fs.tc.hairpin_tbl, &hpe->hairpin_hlist, - hash_hairpin_info(peer_id, match_prio)); - attach_flow: if (hpe->hp->num_channels > 1) { - flow->flags |= MLX5E_TC_FLOW_HAIRPIN_RSS; + flow_flag_set(flow, HAIRPIN_RSS); flow->nic_attr->hairpin_ft = hpe->hp->ttc.ft.t; } else { flow->nic_attr->hairpin_tirn = hpe->hp->tirn; } + + flow->hpe = hpe; + spin_lock(&hpe->flows_lock); list_add(&flow->hairpin, &hpe->flows); + spin_unlock(&hpe->flows_lock); return 0; -create_hairpin_err: - kfree(hpe); +out_err: + mlx5e_hairpin_put(priv, hpe); return err; } static void mlx5e_hairpin_flow_del(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { - struct list_head *next = flow->hairpin.next; + /* flow wasn't fully initialized */ + if (!flow->hpe) + return; + spin_lock(&flow->hpe->flows_lock); list_del(&flow->hairpin); + spin_unlock(&flow->hpe->flows_lock); - /* no more hairpin flows for us, release the hairpin pair */ - if (list_empty(next)) { - struct mlx5e_hairpin_entry *hpe; - - hpe = list_entry(next, struct mlx5e_hairpin_entry, flows); - - netdev_dbg(priv->netdev, "del hairpin: peer %s\n", - dev_name(hpe->hp->pair->peer_mdev->device)); - - mlx5e_hairpin_destroy(hpe->hp); - hash_del(&hpe->hairpin_hlist); - kfree(hpe); - } + mlx5e_hairpin_put(priv, flow->hpe); + flow->hpe = NULL; } static int @@ -723,22 +906,20 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, struct mlx5_flow_destination dest[2] = {}; struct mlx5_flow_act flow_act = { .action = attr->action, - .reformat_id = 0, .flags = FLOW_ACT_NO_APPEND, }; struct mlx5_fc *counter = NULL; - bool table_created = false; int err, dest_ix = 0; flow_context->flags |= FLOW_CONTEXT_HAS_TAG; flow_context->flow_tag = attr->flow_tag; - if (flow->flags & MLX5E_TC_FLOW_HAIRPIN) { + if (flow_flag_test(flow, HAIRPIN)) { err = mlx5e_hairpin_flow_add(priv, flow, parse_attr, extack); - if (err) { - goto err_add_hairpin_flow; - } - if (flow->flags & MLX5E_TC_FLOW_HAIRPIN_RSS) { + if (err) + return err; + + if (flow_flag_test(flow, HAIRPIN_RSS)) { dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; dest[dest_ix].ft = attr->hairpin_ft; } else { @@ -754,10 +935,9 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { counter = mlx5_fc_create(dev, true); - if (IS_ERR(counter)) { - err = PTR_ERR(counter); - goto err_fc_create; - } + if (IS_ERR(counter)) + return PTR_ERR(counter); + dest[dest_ix].type = MLX5_FLOW_DESTINATION_TYPE_COUNTER; dest[dest_ix].counter_id = mlx5_fc_id(counter); dest_ix++; @@ -766,12 +946,13 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); - flow_act.modify_id = attr->mod_hdr_id; + flow_act.modify_hdr = attr->modify_hdr; kfree(parse_attr->mod_hdr_actions); if (err) - goto err_create_mod_hdr_id; + return err; } + mutex_lock(&priv->fs.tc.t_lock); if (IS_ERR_OR_NULL(priv->fs.tc.t)) { int tc_grp_size, tc_tbl_size; u32 max_flow_counter; @@ -791,15 +972,13 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, MLX5E_TC_TABLE_NUM_GROUPS, MLX5E_TC_FT_LEVEL, 0); if (IS_ERR(priv->fs.tc.t)) { + mutex_unlock(&priv->fs.tc.t_lock); NL_SET_ERR_MSG_MOD(extack, "Failed to create tc offload table\n"); netdev_err(priv->netdev, "Failed to create tc offload table\n"); - err = PTR_ERR(priv->fs.tc.t); - goto err_create_ft; + return PTR_ERR(priv->fs.tc.t); } - - table_created = true; } if (attr->match_level != MLX5_MATCH_NONE) @@ -807,29 +986,9 @@ mlx5e_tc_add_nic_flow(struct mlx5e_priv *priv, flow->rule[0] = mlx5_add_flow_rules(priv->fs.tc.t, &parse_attr->spec, &flow_act, dest, dest_ix); + mutex_unlock(&priv->fs.tc.t_lock); - if (IS_ERR(flow->rule[0])) { - err = PTR_ERR(flow->rule[0]); - goto err_add_rule; - } - - return 0; - -err_add_rule: - if (table_created) { - mlx5_destroy_flow_table(priv->fs.tc.t); - priv->fs.tc.t = NULL; - } -err_create_ft: - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - mlx5e_detach_mod_hdr(priv, flow); -err_create_mod_hdr_id: - mlx5_fc_destroy(dev, counter); -err_fc_create: - if (flow->flags & MLX5E_TC_FLOW_HAIRPIN) - mlx5e_hairpin_flow_del(priv, flow); -err_add_hairpin_flow: - return err; + return PTR_ERR_OR_ZERO(flow->rule[0]); } static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, @@ -839,18 +998,21 @@ static void mlx5e_tc_del_nic_flow(struct mlx5e_priv *priv, struct mlx5_fc *counter = NULL; counter = attr->counter; - mlx5_del_flow_rules(flow->rule[0]); + if (!IS_ERR_OR_NULL(flow->rule[0])) + mlx5_del_flow_rules(flow->rule[0]); mlx5_fc_destroy(priv->mdev, counter); - if (!mlx5e_tc_num_filters(priv, MLX5E_TC_NIC_OFFLOAD) && priv->fs.tc.t) { + mutex_lock(&priv->fs.tc.t_lock); + if (!mlx5e_tc_num_filters(priv, MLX5_TC_FLAG(NIC_OFFLOAD)) && priv->fs.tc.t) { mlx5_destroy_flow_table(priv->fs.tc.t); priv->fs.tc.t = NULL; } + mutex_unlock(&priv->fs.tc.t_lock); if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) mlx5e_detach_mod_hdr(priv, flow); - if (flow->flags & MLX5E_TC_FLOW_HAIRPIN) + if (flow_flag_test(flow, HAIRPIN)) mlx5e_hairpin_flow_del(priv, flow); } @@ -885,7 +1047,6 @@ mlx5e_tc_offload_fdb_rules(struct mlx5_eswitch *esw, } } - flow->flags |= MLX5E_TC_FLOW_OFFLOADED; return rule; } @@ -894,7 +1055,7 @@ mlx5e_tc_unoffload_fdb_rules(struct mlx5_eswitch *esw, struct mlx5e_tc_flow *flow, struct mlx5_esw_flow_attr *attr) { - flow->flags &= ~MLX5E_TC_FLOW_OFFLOADED; + flow_flag_clear(flow, OFFLOADED); if (attr->split_count) mlx5_eswitch_del_fwd_rule(esw, flow->rule[1], attr); @@ -917,7 +1078,7 @@ mlx5e_tc_offload_to_slow_path(struct mlx5_eswitch *esw, rule = mlx5e_tc_offload_fdb_rules(esw, flow, spec, slow_attr); if (!IS_ERR(rule)) - flow->flags |= MLX5E_TC_FLOW_SLOW; + flow_flag_set(flow, SLOW); return rule; } @@ -932,7 +1093,26 @@ mlx5e_tc_unoffload_from_slow_path(struct mlx5_eswitch *esw, slow_attr->split_count = 0; slow_attr->dest_chain = FDB_SLOW_PATH_CHAIN; mlx5e_tc_unoffload_fdb_rules(esw, flow, slow_attr); - flow->flags &= ~MLX5E_TC_FLOW_SLOW; + flow_flag_clear(flow, SLOW); +} + +/* Caller must obtain uplink_priv->unready_flows_lock mutex before calling this + * function. + */ +static void unready_flow_add(struct mlx5e_tc_flow *flow, + struct list_head *unready_flows) +{ + flow_flag_set(flow, NOT_READY); + list_add_tail(&flow->unready, unready_flows); +} + +/* Caller must obtain uplink_priv->unready_flows_lock mutex before calling this + * function. + */ +static void unready_flow_del(struct mlx5e_tc_flow *flow) +{ + list_del(&flow->unready); + flow_flag_clear(flow, NOT_READY); } static void add_unready_flow(struct mlx5e_tc_flow *flow) @@ -945,14 +1125,24 @@ static void add_unready_flow(struct mlx5e_tc_flow *flow) rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); uplink_priv = &rpriv->uplink_priv; - flow->flags |= MLX5E_TC_FLOW_NOT_READY; - list_add_tail(&flow->unready, &uplink_priv->unready_flows); + mutex_lock(&uplink_priv->unready_flows_lock); + unready_flow_add(flow, &uplink_priv->unready_flows); + mutex_unlock(&uplink_priv->unready_flows_lock); } static void remove_unready_flow(struct mlx5e_tc_flow *flow) { - list_del(&flow->unready); - flow->flags &= ~MLX5E_TC_FLOW_NOT_READY; + struct mlx5_rep_uplink_priv *uplink_priv; + struct mlx5e_rep_priv *rpriv; + struct mlx5_eswitch *esw; + + esw = flow->priv->mdev->priv.eswitch; + rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); + uplink_priv = &rpriv->uplink_priv; + + mutex_lock(&uplink_priv->unready_flows_lock); + unready_flow_del(flow); + mutex_unlock(&uplink_priv->unready_flows_lock); } static int @@ -980,14 +1170,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, if (attr->chain > max_chain) { NL_SET_ERR_MSG(extack, "Requested chain is out of supported range"); - err = -EOPNOTSUPP; - goto err_max_prio_chain; + return -EOPNOTSUPP; } if (attr->prio > max_prio) { NL_SET_ERR_MSG(extack, "Requested priority is out of supported range"); - err = -EOPNOTSUPP; - goto err_max_prio_chain; + return -EOPNOTSUPP; } for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) { @@ -1002,7 +1190,7 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, err = mlx5e_attach_encap(priv, flow, out_dev, out_index, extack, &encap_dev, &encap_valid); if (err) - goto err_attach_encap; + return err; out_priv = netdev_priv(encap_dev); rpriv = out_priv->ppriv; @@ -1012,21 +1200,19 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, err = mlx5_eswitch_add_vlan_action(esw, attr); if (err) - goto err_add_vlan; + return err; if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) { err = mlx5e_attach_mod_hdr(priv, flow, parse_attr); kfree(parse_attr->mod_hdr_actions); if (err) - goto err_mod_hdr; + return err; } if (attr->action & MLX5_FLOW_CONTEXT_ACTION_COUNT) { counter = mlx5_fc_create(attr->counter_dev, true); - if (IS_ERR(counter)) { - err = PTR_ERR(counter); - goto err_create_counter; - } + if (IS_ERR(counter)) + return PTR_ERR(counter); attr->counter = counter; } @@ -1044,27 +1230,12 @@ mlx5e_tc_add_fdb_flow(struct mlx5e_priv *priv, flow->rule[0] = mlx5e_tc_offload_fdb_rules(esw, flow, &parse_attr->spec, attr); } - if (IS_ERR(flow->rule[0])) { - err = PTR_ERR(flow->rule[0]); - goto err_add_rule; - } + if (IS_ERR(flow->rule[0])) + return PTR_ERR(flow->rule[0]); + else + flow_flag_set(flow, OFFLOADED); return 0; - -err_add_rule: - mlx5_fc_destroy(attr->counter_dev, counter); -err_create_counter: - if (attr->action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - mlx5e_detach_mod_hdr(priv, flow); -err_mod_hdr: - mlx5_eswitch_del_vlan_action(esw, attr); -err_add_vlan: - for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) - if (attr->dests[out_index].flags & MLX5_ESW_DEST_ENCAP) - mlx5e_detach_encap(priv, flow, out_index); -err_attach_encap: -err_max_prio_chain: - return err; } static bool mlx5_flow_has_geneve_opt(struct mlx5e_tc_flow *flow) @@ -1088,14 +1259,14 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr slow_attr; int out_index; - if (flow->flags & MLX5E_TC_FLOW_NOT_READY) { + if (flow_flag_test(flow, NOT_READY)) { remove_unready_flow(flow); kvfree(attr->parse_attr); return; } - if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { - if (flow->flags & MLX5E_TC_FLOW_SLOW) + if (mlx5e_is_offloaded_flow(flow)) { + if (flow_flag_test(flow, SLOW)) mlx5e_tc_unoffload_from_slow_path(esw, flow, &slow_attr); else mlx5e_tc_unoffload_fdb_rules(esw, flow, attr); @@ -1119,39 +1290,39 @@ static void mlx5e_tc_del_fdb_flow(struct mlx5e_priv *priv, } void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, - struct mlx5e_encap_entry *e) + struct mlx5e_encap_entry *e, + struct list_head *flow_list) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr slow_attr, *esw_attr; struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; - struct encap_flow_item *efi; struct mlx5e_tc_flow *flow; int err; - err = mlx5_packet_reformat_alloc(priv->mdev, - e->reformat_type, - e->encap_size, e->encap_header, - MLX5_FLOW_NAMESPACE_FDB, - &e->encap_id); - if (err) { - mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %d\n", - err); + e->pkt_reformat = mlx5_packet_reformat_alloc(priv->mdev, + e->reformat_type, + e->encap_size, e->encap_header, + MLX5_FLOW_NAMESPACE_FDB); + if (IS_ERR(e->pkt_reformat)) { + mlx5_core_warn(priv->mdev, "Failed to offload cached encapsulation header, %lu\n", + PTR_ERR(e->pkt_reformat)); return; } e->flags |= MLX5_ENCAP_ENTRY_VALID; mlx5e_rep_queue_neigh_stats_work(priv); - list_for_each_entry(efi, &e->flows, list) { + list_for_each_entry(flow, flow_list, tmp_list) { bool all_flow_encaps_valid = true; int i; - flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]); + if (!mlx5e_is_offloaded_flow(flow)) + continue; esw_attr = flow->esw_attr; spec = &esw_attr->parse_attr->spec; - esw_attr->dests[efi->index].encap_id = e->encap_id; - esw_attr->dests[efi->index].flags |= MLX5_ESW_DEST_ENCAP_VALID; + esw_attr->dests[flow->tmp_efi_index].pkt_reformat = e->pkt_reformat; + esw_attr->dests[flow->tmp_efi_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; /* Flow can be associated with multiple encap entries. * Before offloading the flow verify that all of them have * a valid neighbour. @@ -1177,30 +1348,32 @@ void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, } mlx5e_tc_unoffload_from_slow_path(esw, flow, &slow_attr); - flow->flags |= MLX5E_TC_FLOW_OFFLOADED; /* was unset when slow path rule removed */ flow->rule[0] = rule; + /* was unset when slow path rule removed */ + flow_flag_set(flow, OFFLOADED); } } void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, - struct mlx5e_encap_entry *e) + struct mlx5e_encap_entry *e, + struct list_head *flow_list) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5_esw_flow_attr slow_attr; struct mlx5_flow_handle *rule; struct mlx5_flow_spec *spec; - struct encap_flow_item *efi; struct mlx5e_tc_flow *flow; int err; - list_for_each_entry(efi, &e->flows, list) { - flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]); + list_for_each_entry(flow, flow_list, tmp_list) { + if (!mlx5e_is_offloaded_flow(flow)) + continue; spec = &flow->esw_attr->parse_attr->spec; /* update from encap rule to slow path rule */ rule = mlx5e_tc_offload_to_slow_path(esw, flow, spec, &slow_attr); /* mark the flow's encap dest as non-valid */ - flow->esw_attr->dests[efi->index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID; + flow->esw_attr->dests[flow->tmp_efi_index].flags &= ~MLX5_ESW_DEST_ENCAP_VALID; if (IS_ERR(rule)) { err = PTR_ERR(rule); @@ -1210,28 +1383,102 @@ void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, } mlx5e_tc_unoffload_fdb_rules(esw, flow, flow->esw_attr); - flow->flags |= MLX5E_TC_FLOW_OFFLOADED; /* was unset when fast path rule removed */ flow->rule[0] = rule; + /* was unset when fast path rule removed */ + flow_flag_set(flow, OFFLOADED); } /* we know that the encap is valid */ e->flags &= ~MLX5_ENCAP_ENTRY_VALID; - mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); + mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); } static struct mlx5_fc *mlx5e_tc_get_counter(struct mlx5e_tc_flow *flow) { - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + if (mlx5e_is_eswitch_flow(flow)) return flow->esw_attr->counter; else return flow->nic_attr->counter; } +/* Takes reference to all flows attached to encap and adds the flows to + * flow_list using 'tmp_list' list_head in mlx5e_tc_flow. + */ +void mlx5e_take_all_encap_flows(struct mlx5e_encap_entry *e, struct list_head *flow_list) +{ + struct encap_flow_item *efi; + struct mlx5e_tc_flow *flow; + + list_for_each_entry(efi, &e->flows, list) { + flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]); + if (IS_ERR(mlx5e_flow_get(flow))) + continue; + wait_for_completion(&flow->init_done); + + flow->tmp_efi_index = efi->index; + list_add(&flow->tmp_list, flow_list); + } +} + +/* Iterate over tmp_list of flows attached to flow_list head. */ +void mlx5e_put_encap_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list) +{ + struct mlx5e_tc_flow *flow, *tmp; + + list_for_each_entry_safe(flow, tmp, flow_list, tmp_list) + mlx5e_flow_put(priv, flow); +} + +static struct mlx5e_encap_entry * +mlx5e_get_next_valid_encap(struct mlx5e_neigh_hash_entry *nhe, + struct mlx5e_encap_entry *e) +{ + struct mlx5e_encap_entry *next = NULL; + +retry: + rcu_read_lock(); + + /* find encap with non-zero reference counter value */ + for (next = e ? + list_next_or_null_rcu(&nhe->encap_list, + &e->encap_list, + struct mlx5e_encap_entry, + encap_list) : + list_first_or_null_rcu(&nhe->encap_list, + struct mlx5e_encap_entry, + encap_list); + next; + next = list_next_or_null_rcu(&nhe->encap_list, + &next->encap_list, + struct mlx5e_encap_entry, + encap_list)) + if (mlx5e_encap_take(next)) + break; + + rcu_read_unlock(); + + /* release starting encap */ + if (e) + mlx5e_encap_put(netdev_priv(e->out_dev), e); + if (!next) + return next; + + /* wait for encap to be fully initialized */ + wait_for_completion(&next->res_ready); + /* continue searching if encap entry is not in valid state after completion */ + if (!(next->flags & MLX5_ENCAP_ENTRY_VALID)) { + e = next; + goto retry; + } + + return next; +} + void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) { struct mlx5e_neigh *m_neigh = &nhe->m_neigh; + struct mlx5e_encap_entry *e = NULL; struct mlx5e_tc_flow *flow; - struct mlx5e_encap_entry *e; struct mlx5_fc *counter; struct neigh_table *tbl; bool neigh_used = false; @@ -1242,19 +1489,30 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) tbl = &arp_tbl; #if IS_ENABLED(CONFIG_IPV6) else if (m_neigh->family == AF_INET6) - tbl = &nd_tbl; + tbl = ipv6_stub->nd_tbl; #endif else return; - list_for_each_entry(e, &nhe->encap_list, encap_list) { - struct encap_flow_item *efi; - if (!(e->flags & MLX5_ENCAP_ENTRY_VALID)) - continue; - list_for_each_entry(efi, &e->flows, list) { + /* mlx5e_get_next_valid_encap() releases previous encap before returning + * next one. + */ + while ((e = mlx5e_get_next_valid_encap(nhe, e)) != NULL) { + struct mlx5e_priv *priv = netdev_priv(e->out_dev); + struct encap_flow_item *efi, *tmp; + struct mlx5_eswitch *esw; + LIST_HEAD(flow_list); + + esw = priv->mdev->priv.eswitch; + mutex_lock(&esw->offloads.encap_tbl_lock); + list_for_each_entry_safe(efi, tmp, &e->flows, list) { flow = container_of(efi, struct mlx5e_tc_flow, encaps[efi->index]); - if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { + if (IS_ERR(mlx5e_flow_get(flow))) + continue; + list_add(&flow->tmp_list, &flow_list); + + if (mlx5e_is_offloaded_flow(flow)) { counter = mlx5e_tc_get_counter(flow); lastuse = mlx5_fc_query_lastuse(counter); if (time_after((unsigned long)lastuse, nhe->reported_lastuse)) { @@ -1263,10 +1521,18 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) } } } - if (neigh_used) + mutex_unlock(&esw->offloads.encap_tbl_lock); + + mlx5e_put_encap_flow_list(priv, &flow_list); + if (neigh_used) { + /* release current encap before breaking the loop */ + mlx5e_encap_put(priv, e); break; + } } + trace_mlx5e_tc_update_neigh_used_value(nhe, neigh_used); + if (neigh_used) { nhe->reported_lastuse = jiffies; @@ -1282,40 +1548,69 @@ void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe) } } -static void mlx5e_detach_encap(struct mlx5e_priv *priv, - struct mlx5e_tc_flow *flow, int out_index) +static void mlx5e_encap_dealloc(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) { - struct list_head *next = flow->encaps[out_index].list.next; + WARN_ON(!list_empty(&e->flows)); - list_del(&flow->encaps[out_index].list); - if (list_empty(next)) { - struct mlx5e_encap_entry *e; - - e = list_entry(next, struct mlx5e_encap_entry, flows); + if (e->compl_result > 0) { mlx5e_rep_encap_entry_detach(netdev_priv(e->out_dev), e); if (e->flags & MLX5_ENCAP_ENTRY_VALID) - mlx5_packet_reformat_dealloc(priv->mdev, e->encap_id); + mlx5_packet_reformat_dealloc(priv->mdev, e->pkt_reformat); + } - hash_del_rcu(&e->encap_hlist); - kfree(e->encap_header); - kfree(e); + kfree(e->encap_header); + kfree_rcu(e, rcu); +} + +void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + if (!refcount_dec_and_mutex_lock(&e->refcnt, &esw->offloads.encap_tbl_lock)) + return; + hash_del_rcu(&e->encap_hlist); + mutex_unlock(&esw->offloads.encap_tbl_lock); + + mlx5e_encap_dealloc(priv, e); +} + +static void mlx5e_detach_encap(struct mlx5e_priv *priv, + struct mlx5e_tc_flow *flow, int out_index) +{ + struct mlx5e_encap_entry *e = flow->encaps[out_index].e; + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + + /* flow wasn't fully initialized */ + if (!e) + return; + + mutex_lock(&esw->offloads.encap_tbl_lock); + list_del(&flow->encaps[out_index].list); + flow->encaps[out_index].e = NULL; + if (!refcount_dec_and_test(&e->refcnt)) { + mutex_unlock(&esw->offloads.encap_tbl_lock); + return; } + hash_del_rcu(&e->encap_hlist); + mutex_unlock(&esw->offloads.encap_tbl_lock); + + mlx5e_encap_dealloc(priv, e); } static void __mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow) { struct mlx5_eswitch *esw = flow->priv->mdev->priv.eswitch; - if (!(flow->flags & MLX5E_TC_FLOW_ESWITCH) || - !(flow->flags & MLX5E_TC_FLOW_DUP)) + if (!flow_flag_test(flow, ESWITCH) || + !flow_flag_test(flow, DUP)) return; mutex_lock(&esw->offloads.peer_mutex); list_del(&flow->peer); mutex_unlock(&esw->offloads.peer_mutex); - flow->flags &= ~MLX5E_TC_FLOW_DUP; + flow_flag_clear(flow, DUP); mlx5e_tc_del_fdb_flow(flow->peer_flow->priv, flow->peer_flow); kvfree(flow->peer_flow); @@ -1339,7 +1634,7 @@ static void mlx5e_tc_del_fdb_peer_flow(struct mlx5e_tc_flow *flow) static void mlx5e_tc_del_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow) { - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { + if (mlx5e_is_eswitch_flow(flow)) { mlx5e_tc_del_fdb_peer_flow(flow); mlx5e_tc_del_fdb_flow(priv, flow); } else { @@ -1596,7 +1891,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, *match_level = MLX5_MATCH_L2; } } else if (*match_level != MLX5_MATCH_NONE) { - MLX5_SET(fte_match_set_lyr_2_4, headers_c, svlan_tag, 1); + /* cvlan_tag enabled in match criteria and + * disabled in match value means both S & C tags + * don't exist (untagged of both) + */ MLX5_SET(fte_match_set_lyr_2_4, headers_c, cvlan_tag, 1); *match_level = MLX5_MATCH_L2; } @@ -1840,6 +2138,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, struct mlx5_eswitch *esw = dev->priv.eswitch; struct mlx5e_rep_priv *rpriv = priv->ppriv; struct mlx5_eswitch_rep *rep; + bool is_eswitch_flow; int err; inner_match_level = MLX5_MATCH_NONE; @@ -1850,7 +2149,8 @@ static int parse_cls_flower(struct mlx5e_priv *priv, non_tunnel_match_level = (inner_match_level == MLX5_MATCH_NONE) ? outer_match_level : inner_match_level; - if (!err && (flow->flags & MLX5E_TC_FLOW_ESWITCH)) { + is_eswitch_flow = mlx5e_is_eswitch_flow(flow); + if (!err && is_eswitch_flow) { rep = rpriv->rep; if (rep->vport != MLX5_VPORT_UPLINK && (esw->offloads.inline_mode != MLX5_INLINE_MODE_NONE && @@ -1864,7 +2164,7 @@ static int parse_cls_flower(struct mlx5e_priv *priv, } } - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) { + if (is_eswitch_flow) { flow->esw_attr->inner_match_level = inner_match_level; flow->esw_attr->outer_match_level = outer_match_level; } else { @@ -2385,14 +2685,15 @@ static bool actions_match_supported(struct mlx5e_priv *priv, { u32 actions; - if (flow->flags & MLX5E_TC_FLOW_ESWITCH) + if (mlx5e_is_eswitch_flow(flow)) actions = flow->esw_attr->action; else actions = flow->nic_attr->action; - if (flow->flags & MLX5E_TC_FLOW_EGRESS && + if (flow_flag_test(flow, EGRESS) && !((actions & MLX5_FLOW_CONTEXT_ACTION_DECAP) || - (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP))) + (actions & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) || + (actions & MLX5_FLOW_CONTEXT_ACTION_DROP))) return false; if (actions & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) @@ -2542,7 +2843,7 @@ static int parse_tc_nic_actions(struct mlx5e_priv *priv, if (priv->netdev->netdev_ops == peer_dev->netdev_ops && same_hw_devs(priv, netdev_priv(peer_dev))) { parse_attr->mirred_ifindex[0] = peer_dev->ifindex; - flow->flags |= MLX5E_TC_FLOW_HAIRPIN; + flow_flag_set(flow, HAIRPIN); action |= MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | MLX5_FLOW_CONTEXT_ACTION_COUNT; } else { @@ -2629,6 +2930,31 @@ static bool is_merged_eswitch_dev(struct mlx5e_priv *priv, +bool mlx5e_encap_take(struct mlx5e_encap_entry *e) +{ + return refcount_inc_not_zero(&e->refcnt); +} + +static struct mlx5e_encap_entry * +mlx5e_encap_get(struct mlx5e_priv *priv, struct encap_key *key, + uintptr_t hash_key) +{ + struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; + struct mlx5e_encap_entry *e; + struct encap_key e_key; + + hash_for_each_possible_rcu(esw->offloads.encap_tbl, e, + encap_hlist, hash_key) { + e_key.ip_tun_key = &e->tun_info->key; + e_key.tc_tunnel = e->tunnel; + if (!cmp_encap_info(&e_key, key) && + mlx5e_encap_take(e)) + return e; + } + + return NULL; +} + static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow, struct net_device *mirred_dev, @@ -2641,11 +2967,10 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, struct mlx5_esw_flow_attr *attr = flow->esw_attr; struct mlx5e_tc_flow_parse_attr *parse_attr; const struct ip_tunnel_info *tun_info; - struct encap_key key, e_key; + struct encap_key key; struct mlx5e_encap_entry *e; unsigned short family; uintptr_t hash_key; - bool found = false; int err = 0; parse_attr = attr->parse_attr; @@ -2660,57 +2985,78 @@ static int mlx5e_attach_encap(struct mlx5e_priv *priv, hash_key = hash_encap_info(&key); - hash_for_each_possible_rcu(esw->offloads.encap_tbl, e, - encap_hlist, hash_key) { - e_key.ip_tun_key = &e->tun_info->key; - e_key.tc_tunnel = e->tunnel; - if (!cmp_encap_info(&e_key, &key)) { - found = true; - break; - } - } + mutex_lock(&esw->offloads.encap_tbl_lock); + e = mlx5e_encap_get(priv, &key, hash_key); /* must verify if encap is valid or not */ - if (found) + if (e) { + mutex_unlock(&esw->offloads.encap_tbl_lock); + wait_for_completion(&e->res_ready); + + /* Protect against concurrent neigh update. */ + mutex_lock(&esw->offloads.encap_tbl_lock); + if (e->compl_result < 0) { + err = -EREMOTEIO; + goto out_err; + } goto attach_flow; + } e = kzalloc(sizeof(*e), GFP_KERNEL); - if (!e) - return -ENOMEM; + if (!e) { + err = -ENOMEM; + goto out_err; + } + + refcount_set(&e->refcnt, 1); + init_completion(&e->res_ready); e->tun_info = tun_info; err = mlx5e_tc_tun_init_encap_attr(mirred_dev, priv, e, extack); - if (err) + if (err) { + kfree(e); + e = NULL; goto out_err; + } INIT_LIST_HEAD(&e->flows); + hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); + mutex_unlock(&esw->offloads.encap_tbl_lock); if (family == AF_INET) err = mlx5e_tc_tun_create_header_ipv4(priv, mirred_dev, e); else if (family == AF_INET6) err = mlx5e_tc_tun_create_header_ipv6(priv, mirred_dev, e); - if (err) + /* Protect against concurrent neigh update. */ + mutex_lock(&esw->offloads.encap_tbl_lock); + complete_all(&e->res_ready); + if (err) { + e->compl_result = err; goto out_err; - - hash_add_rcu(esw->offloads.encap_tbl, &e->encap_hlist, hash_key); + } + e->compl_result = 1; attach_flow: + flow->encaps[out_index].e = e; list_add(&flow->encaps[out_index].list, &e->flows); flow->encaps[out_index].index = out_index; *encap_dev = e->out_dev; if (e->flags & MLX5_ENCAP_ENTRY_VALID) { - attr->dests[out_index].encap_id = e->encap_id; + attr->dests[out_index].pkt_reformat = e->pkt_reformat; attr->dests[out_index].flags |= MLX5_ESW_DEST_ENCAP_VALID; *encap_valid = true; } else { *encap_valid = false; } + mutex_unlock(&esw->offloads.encap_tbl_lock); return err; out_err: - kfree(e); + mutex_unlock(&esw->offloads.encap_tbl_lock); + if (e) + mlx5e_encap_put(priv, e); return err; } @@ -2890,12 +3236,16 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, if (netdev_port_same_parent_id(priv->netdev, out_dev)) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct net_device *uplink_dev = mlx5_eswitch_uplink_get_proto_dev(esw, REP_ETH); - struct net_device *uplink_upper = netdev_master_upper_dev_get(uplink_dev); + struct net_device *uplink_upper; + rcu_read_lock(); + uplink_upper = + netdev_master_upper_dev_get_rcu(uplink_dev); if (uplink_upper && netif_is_lag_master(uplink_upper) && uplink_upper == out_dev) out_dev = uplink_dev; + rcu_read_unlock(); if (is_vlan_dev(out_dev)) { err = add_vlan_push_action(priv, attr, @@ -3066,19 +3416,19 @@ static int parse_tc_fdb_actions(struct mlx5e_priv *priv, return 0; } -static void get_flags(int flags, u16 *flow_flags) +static void get_flags(int flags, unsigned long *flow_flags) { - u16 __flow_flags = 0; + unsigned long __flow_flags = 0; - if (flags & MLX5E_TC_INGRESS) - __flow_flags |= MLX5E_TC_FLOW_INGRESS; - if (flags & MLX5E_TC_EGRESS) - __flow_flags |= MLX5E_TC_FLOW_EGRESS; + if (flags & MLX5_TC_FLAG(INGRESS)) + __flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_INGRESS); + if (flags & MLX5_TC_FLAG(EGRESS)) + __flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_EGRESS); - if (flags & MLX5E_TC_ESW_OFFLOAD) - __flow_flags |= MLX5E_TC_FLOW_ESWITCH; - if (flags & MLX5E_TC_NIC_OFFLOAD) - __flow_flags |= MLX5E_TC_FLOW_NIC; + if (flags & MLX5_TC_FLAG(ESW_OFFLOAD)) + __flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_ESWITCH); + if (flags & MLX5_TC_FLAG(NIC_OFFLOAD)) + __flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_NIC); *flow_flags = __flow_flags; } @@ -3090,12 +3440,13 @@ static const struct rhashtable_params tc_ht_params = { .automatic_shrinking = true, }; -static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv, int flags) +static struct rhashtable *get_tc_ht(struct mlx5e_priv *priv, + unsigned long flags) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; struct mlx5e_rep_priv *uplink_rpriv; - if (flags & MLX5E_TC_ESW_OFFLOAD) { + if (flags & MLX5_TC_FLAG(ESW_OFFLOAD)) { uplink_rpriv = mlx5_eswitch_get_uplink_priv(esw, REP_ETH); return &uplink_rpriv->uplink_priv.tc_ht; } else /* NIC offload */ @@ -3106,7 +3457,7 @@ static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow) { struct mlx5_esw_flow_attr *attr = flow->esw_attr; bool is_rep_ingress = attr->in_rep->vport != MLX5_VPORT_UPLINK && - flow->flags & MLX5E_TC_FLOW_INGRESS; + flow_flag_test(flow, INGRESS); bool act_is_encap = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT); bool esw_paired = mlx5_devcom_is_paired(attr->in_mdev->priv.devcom, @@ -3125,13 +3476,13 @@ static bool is_peer_flow_needed(struct mlx5e_tc_flow *flow) static int mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, - struct flow_cls_offload *f, u16 flow_flags, + struct flow_cls_offload *f, unsigned long flow_flags, struct mlx5e_tc_flow_parse_attr **__parse_attr, struct mlx5e_tc_flow **__flow) { struct mlx5e_tc_flow_parse_attr *parse_attr; struct mlx5e_tc_flow *flow; - int err; + int out_index, err; flow = kzalloc(sizeof(*flow) + attr_size, GFP_KERNEL); parse_attr = kvzalloc(sizeof(*parse_attr), GFP_KERNEL); @@ -3143,6 +3494,12 @@ mlx5e_alloc_flow(struct mlx5e_priv *priv, int attr_size, flow->cookie = f->cookie; flow->flags = flow_flags; flow->priv = priv; + for (out_index = 0; out_index < MLX5_MAX_FLOW_FWD_VPORTS; out_index++) + INIT_LIST_HEAD(&flow->encaps[out_index].list); + INIT_LIST_HEAD(&flow->mod_hdr); + INIT_LIST_HEAD(&flow->hairpin); + refcount_set(&flow->refcnt, 1); + init_completion(&flow->init_done); *__flow = flow; *__parse_attr = parse_attr; @@ -3182,7 +3539,7 @@ mlx5e_flow_esw_attr_init(struct mlx5_esw_flow_attr *esw_attr, static struct mlx5e_tc_flow * __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, struct flow_cls_offload *f, - u16 flow_flags, + unsigned long flow_flags, struct net_device *filter_dev, struct mlx5_eswitch_rep *in_rep, struct mlx5_core_dev *in_mdev) @@ -3193,7 +3550,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, struct mlx5e_tc_flow *flow; int attr_size, err; - flow_flags |= MLX5E_TC_FLOW_ESWITCH; + flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_ESWITCH); attr_size = sizeof(struct mlx5_esw_flow_attr); err = mlx5e_alloc_flow(priv, attr_size, f, flow_flags, &parse_attr, &flow); @@ -3215,6 +3572,7 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, goto err_free; err = mlx5e_tc_add_fdb_flow(priv, flow, extack); + complete_all(&flow->init_done); if (err) { if (!(err == -ENETUNREACH && mlx5_lag_is_multipath(in_mdev))) goto err_free; @@ -3225,15 +3583,14 @@ __mlx5e_add_fdb_flow(struct mlx5e_priv *priv, return flow; err_free: - kfree(flow); - kvfree(parse_attr); + mlx5e_flow_put(priv, flow); out: return ERR_PTR(err); } static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f, struct mlx5e_tc_flow *flow, - u16 flow_flags) + unsigned long flow_flags) { struct mlx5e_priv *priv = flow->priv, *peer_priv; struct mlx5_eswitch *esw = priv->mdev->priv.eswitch, *peer_esw; @@ -3271,7 +3628,7 @@ static int mlx5e_tc_add_fdb_peer_flow(struct flow_cls_offload *f, } flow->peer_flow = peer_flow; - flow->flags |= MLX5E_TC_FLOW_DUP; + flow_flag_set(flow, DUP); mutex_lock(&esw->offloads.peer_mutex); list_add_tail(&flow->peer, &esw->offloads.peer_flows); mutex_unlock(&esw->offloads.peer_mutex); @@ -3284,7 +3641,7 @@ out: static int mlx5e_add_fdb_flow(struct mlx5e_priv *priv, struct flow_cls_offload *f, - u16 flow_flags, + unsigned long flow_flags, struct net_device *filter_dev, struct mlx5e_tc_flow **__flow) { @@ -3318,7 +3675,7 @@ out: static int mlx5e_add_nic_flow(struct mlx5e_priv *priv, struct flow_cls_offload *f, - u16 flow_flags, + unsigned long flow_flags, struct net_device *filter_dev, struct mlx5e_tc_flow **__flow) { @@ -3332,7 +3689,7 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, if (!tc_cls_can_offload_and_chain0(priv->netdev, &f->common)) return -EOPNOTSUPP; - flow_flags |= MLX5E_TC_FLOW_NIC; + flow_flags |= BIT(MLX5E_TC_FLOW_FLAG_NIC); attr_size = sizeof(struct mlx5_nic_flow_attr); err = mlx5e_alloc_flow(priv, attr_size, f, flow_flags, &parse_attr, &flow); @@ -3353,14 +3710,14 @@ mlx5e_add_nic_flow(struct mlx5e_priv *priv, if (err) goto err_free; - flow->flags |= MLX5E_TC_FLOW_OFFLOADED; + flow_flag_set(flow, OFFLOADED); kvfree(parse_attr); *__flow = flow; return 0; err_free: - kfree(flow); + mlx5e_flow_put(priv, flow); kvfree(parse_attr); out: return err; @@ -3369,12 +3726,12 @@ out: static int mlx5e_tc_add_flow(struct mlx5e_priv *priv, struct flow_cls_offload *f, - int flags, + unsigned long flags, struct net_device *filter_dev, struct mlx5e_tc_flow **flow) { struct mlx5_eswitch *esw = priv->mdev->priv.eswitch; - u16 flow_flags; + unsigned long flow_flags; int err; get_flags(flags, &flow_flags); @@ -3393,14 +3750,16 @@ mlx5e_tc_add_flow(struct mlx5e_priv *priv, } int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags) + struct flow_cls_offload *f, unsigned long flags) { struct netlink_ext_ack *extack = f->common.extack; struct rhashtable *tc_ht = get_tc_ht(priv, flags); struct mlx5e_tc_flow *flow; int err = 0; - flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); + rcu_read_lock(); + flow = rhashtable_lookup(tc_ht, &f->cookie, tc_ht_params); + rcu_read_unlock(); if (flow) { NL_SET_ERR_MSG_MOD(extack, "flow cookie already exists, ignoring"); @@ -3411,55 +3770,68 @@ int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, goto out; } + trace_mlx5e_configure_flower(f); err = mlx5e_tc_add_flow(priv, f, flags, dev, &flow); if (err) goto out; - err = rhashtable_insert_fast(tc_ht, &flow->node, tc_ht_params); + err = rhashtable_lookup_insert_fast(tc_ht, &flow->node, tc_ht_params); if (err) goto err_free; return 0; err_free: - mlx5e_tc_del_flow(priv, flow); - kfree(flow); + mlx5e_flow_put(priv, flow); out: return err; } -#define DIRECTION_MASK (MLX5E_TC_INGRESS | MLX5E_TC_EGRESS) -#define FLOW_DIRECTION_MASK (MLX5E_TC_FLOW_INGRESS | MLX5E_TC_FLOW_EGRESS) - static bool same_flow_direction(struct mlx5e_tc_flow *flow, int flags) { - if ((flow->flags & FLOW_DIRECTION_MASK) == (flags & DIRECTION_MASK)) - return true; + bool dir_ingress = !!(flags & MLX5_TC_FLAG(INGRESS)); + bool dir_egress = !!(flags & MLX5_TC_FLAG(EGRESS)); - return false; + return flow_flag_test(flow, INGRESS) == dir_ingress && + flow_flag_test(flow, EGRESS) == dir_egress; } int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags) + struct flow_cls_offload *f, unsigned long flags) { struct rhashtable *tc_ht = get_tc_ht(priv, flags); struct mlx5e_tc_flow *flow; + int err; + rcu_read_lock(); flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); - if (!flow || !same_flow_direction(flow, flags)) - return -EINVAL; + if (!flow || !same_flow_direction(flow, flags)) { + err = -EINVAL; + goto errout; + } + /* Only delete the flow if it doesn't have MLX5E_TC_FLOW_DELETED flag + * set. + */ + if (flow_flag_test_and_set(flow, DELETED)) { + err = -EINVAL; + goto errout; + } rhashtable_remove_fast(tc_ht, &flow->node, tc_ht_params); + rcu_read_unlock(); - mlx5e_tc_del_flow(priv, flow); - - kfree(flow); + trace_mlx5e_delete_flower(f); + mlx5e_flow_put(priv, flow); return 0; + +errout: + rcu_read_unlock(); + return err; } int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags) + struct flow_cls_offload *f, unsigned long flags) { struct mlx5_devcom *devcom = priv->mdev->priv.devcom; struct rhashtable *tc_ht = get_tc_ht(priv, flags); @@ -3469,15 +3841,24 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, u64 lastuse = 0; u64 packets = 0; u64 bytes = 0; + int err = 0; - flow = rhashtable_lookup_fast(tc_ht, &f->cookie, tc_ht_params); - if (!flow || !same_flow_direction(flow, flags)) - return -EINVAL; + rcu_read_lock(); + flow = mlx5e_flow_get(rhashtable_lookup(tc_ht, &f->cookie, + tc_ht_params)); + rcu_read_unlock(); + if (IS_ERR(flow)) + return PTR_ERR(flow); - if (flow->flags & MLX5E_TC_FLOW_OFFLOADED) { + if (!same_flow_direction(flow, flags)) { + err = -EINVAL; + goto errout; + } + + if (mlx5e_is_offloaded_flow(flow)) { counter = mlx5e_tc_get_counter(flow); if (!counter) - return 0; + goto errout; mlx5_fc_query_cached(counter, &bytes, &packets, &lastuse); } @@ -3489,8 +3870,8 @@ int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, if (!peer_esw) goto out; - if ((flow->flags & MLX5E_TC_FLOW_DUP) && - (flow->peer_flow->flags & MLX5E_TC_FLOW_OFFLOADED)) { + if (flow_flag_test(flow, DUP) && + flow_flag_test(flow->peer_flow, OFFLOADED)) { u64 bytes2; u64 packets2; u64 lastuse2; @@ -3509,15 +3890,118 @@ no_peer_counter: mlx5_devcom_release_peer_data(devcom, MLX5_DEVCOM_ESW_OFFLOADS); out: flow_stats_update(&f->stats, bytes, packets, lastuse); + trace_mlx5e_stats_flower(f); +errout: + mlx5e_flow_put(priv, flow); + return err; +} + +static int apply_police_params(struct mlx5e_priv *priv, u32 rate, + struct netlink_ext_ack *extack) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct mlx5_eswitch *esw; + u16 vport_num; + u32 rate_mbps; + int err; + + esw = priv->mdev->priv.eswitch; + /* rate is given in bytes/sec. + * First convert to bits/sec and then round to the nearest mbit/secs. + * mbit means million bits. + * Moreover, if rate is non zero we choose to configure to a minimum of + * 1 mbit/sec. + */ + rate_mbps = rate ? max_t(u32, (rate * 8 + 500000) / 1000000, 1) : 0; + vport_num = rpriv->rep->vport; + + err = mlx5_esw_modify_vport_rate(esw, vport_num, rate_mbps); + if (err) + NL_SET_ERR_MSG_MOD(extack, "failed applying action to hardware"); + + return err; +} + +static int scan_tc_matchall_fdb_actions(struct mlx5e_priv *priv, + struct flow_action *flow_action, + struct netlink_ext_ack *extack) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + const struct flow_action_entry *act; + int err; + int i; + + if (!flow_action_has_entries(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "matchall called with no action"); + return -EINVAL; + } + + if (!flow_offload_has_one_action(flow_action)) { + NL_SET_ERR_MSG_MOD(extack, "matchall policing support only a single action"); + return -EOPNOTSUPP; + } + + flow_action_for_each(i, act, flow_action) { + switch (act->id) { + case FLOW_ACTION_POLICE: + err = apply_police_params(priv, act->police.rate_bytes_ps, extack); + if (err) + return err; + + rpriv->prev_vf_vport_stats = priv->stats.vf_vport; + break; + default: + NL_SET_ERR_MSG_MOD(extack, "mlx5 supports only police action for matchall"); + return -EOPNOTSUPP; + } + } return 0; } +int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct netlink_ext_ack *extack = ma->common.extack; + int prio = TC_H_MAJ(ma->common.prio) >> 16; + + if (prio != 1) { + NL_SET_ERR_MSG_MOD(extack, "only priority 1 is supported"); + return -EINVAL; + } + + return scan_tc_matchall_fdb_actions(priv, &ma->rule->action, extack); +} + +int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct netlink_ext_ack *extack = ma->common.extack; + + return apply_police_params(priv, 0, extack); +} + +void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma) +{ + struct mlx5e_rep_priv *rpriv = priv->ppriv; + struct rtnl_link_stats64 cur_stats; + u64 dbytes; + u64 dpkts; + + cur_stats = priv->stats.vf_vport; + dpkts = cur_stats.rx_packets - rpriv->prev_vf_vport_stats.rx_packets; + dbytes = cur_stats.rx_bytes - rpriv->prev_vf_vport_stats.rx_bytes; + rpriv->prev_vf_vport_stats = cur_stats; + flow_stats_update(&ma->stats, dpkts, dbytes, jiffies); +} + static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, struct mlx5e_priv *peer_priv) { struct mlx5_core_dev *peer_mdev = peer_priv->mdev; - struct mlx5e_hairpin_entry *hpe; + struct mlx5e_hairpin_entry *hpe, *tmp; + LIST_HEAD(init_wait_list); u16 peer_vhca_id; int bkt; @@ -3526,9 +4010,18 @@ static void mlx5e_tc_hairpin_update_dead_peer(struct mlx5e_priv *priv, peer_vhca_id = MLX5_CAP_GEN(peer_mdev, vhca_id); - hash_for_each(priv->fs.tc.hairpin_tbl, bkt, hpe, hairpin_hlist) { - if (hpe->peer_vhca_id == peer_vhca_id) + mutex_lock(&priv->fs.tc.hairpin_tbl_lock); + hash_for_each(priv->fs.tc.hairpin_tbl, bkt, hpe, hairpin_hlist) + if (refcount_inc_not_zero(&hpe->refcnt)) + list_add(&hpe->dead_peer_wait_list, &init_wait_list); + mutex_unlock(&priv->fs.tc.hairpin_tbl_lock); + + list_for_each_entry_safe(hpe, tmp, &init_wait_list, dead_peer_wait_list) { + wait_for_completion(&hpe->res_ready); + if (!IS_ERR_OR_NULL(hpe->hp) && hpe->peer_vhca_id == peer_vhca_id) hpe->hp->pair->peer_gone = true; + + mlx5e_hairpin_put(priv, hpe); } } @@ -3564,7 +4057,10 @@ int mlx5e_tc_nic_init(struct mlx5e_priv *priv) struct mlx5e_tc_table *tc = &priv->fs.tc; int err; - hash_init(tc->mod_hdr_tbl); + mutex_init(&tc->t_lock); + mutex_init(&tc->mod_hdr.lock); + hash_init(tc->mod_hdr.hlist); + mutex_init(&tc->hairpin_tbl_lock); hash_init(tc->hairpin_tbl); err = rhashtable_init(&tc->ht, &tc_ht_params); @@ -3596,12 +4092,16 @@ void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) if (tc->netdevice_nb.notifier_call) unregister_netdevice_notifier(&tc->netdevice_nb); + mutex_destroy(&tc->mod_hdr.lock); + mutex_destroy(&tc->hairpin_tbl_lock); + rhashtable_destroy(&tc->ht); if (!IS_ERR_OR_NULL(tc->t)) { mlx5_destroy_flow_table(tc->t); tc->t = NULL; } + mutex_destroy(&tc->t_lock); } int mlx5e_tc_esw_init(struct rhashtable *tc_ht) @@ -3614,7 +4114,7 @@ void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht) rhashtable_free_and_destroy(tc_ht, _mlx5e_tc_del_flow, NULL); } -int mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags) +int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags) { struct rhashtable *tc_ht = get_tc_ht(priv, flags); @@ -3636,10 +4136,10 @@ void mlx5e_tc_reoffload_flows_work(struct work_struct *work) reoffload_flows_work); struct mlx5e_tc_flow *flow, *tmp; - rtnl_lock(); + mutex_lock(&rpriv->unready_flows_lock); list_for_each_entry_safe(flow, tmp, &rpriv->unready_flows, unready) { if (!mlx5e_tc_add_fdb_flow(flow->priv, flow, NULL)) - remove_unready_flow(flow); + unready_flow_del(flow); } - rtnl_unlock(); + mutex_unlock(&rpriv->unready_flows_lock); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h index 3ab39275ca7d..924c6ef86a14 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.h @@ -40,13 +40,15 @@ #ifdef CONFIG_MLX5_ESWITCH enum { - MLX5E_TC_INGRESS = BIT(0), - MLX5E_TC_EGRESS = BIT(1), - MLX5E_TC_NIC_OFFLOAD = BIT(2), - MLX5E_TC_ESW_OFFLOAD = BIT(3), - MLX5E_TC_LAST_EXPORTED_BIT = 3, + MLX5E_TC_FLAG_INGRESS_BIT, + MLX5E_TC_FLAG_EGRESS_BIT, + MLX5E_TC_FLAG_NIC_OFFLOAD_BIT, + MLX5E_TC_FLAG_ESW_OFFLOAD_BIT, + MLX5E_TC_FLAG_LAST_EXPORTED_BIT = MLX5E_TC_FLAG_ESW_OFFLOAD_BIT, }; +#define MLX5_TC_FLAG(flag) BIT(MLX5E_TC_FLAG_##flag##_BIT) + int mlx5e_tc_nic_init(struct mlx5e_priv *priv); void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv); @@ -54,23 +56,37 @@ int mlx5e_tc_esw_init(struct rhashtable *tc_ht); void mlx5e_tc_esw_cleanup(struct rhashtable *tc_ht); int mlx5e_configure_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags); + struct flow_cls_offload *f, unsigned long flags); int mlx5e_delete_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags); + struct flow_cls_offload *f, unsigned long flags); int mlx5e_stats_flower(struct net_device *dev, struct mlx5e_priv *priv, - struct flow_cls_offload *f, int flags); + struct flow_cls_offload *f, unsigned long flags); + +int mlx5e_tc_configure_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *f); +int mlx5e_tc_delete_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *f); +void mlx5e_tc_stats_matchall(struct mlx5e_priv *priv, + struct tc_cls_matchall_offload *ma); struct mlx5e_encap_entry; void mlx5e_tc_encap_flows_add(struct mlx5e_priv *priv, - struct mlx5e_encap_entry *e); + struct mlx5e_encap_entry *e, + struct list_head *flow_list); void mlx5e_tc_encap_flows_del(struct mlx5e_priv *priv, - struct mlx5e_encap_entry *e); + struct mlx5e_encap_entry *e, + struct list_head *flow_list); +bool mlx5e_encap_take(struct mlx5e_encap_entry *e); +void mlx5e_encap_put(struct mlx5e_priv *priv, struct mlx5e_encap_entry *e); + +void mlx5e_take_all_encap_flows(struct mlx5e_encap_entry *e, struct list_head *flow_list); +void mlx5e_put_encap_flow_list(struct mlx5e_priv *priv, struct list_head *flow_list); struct mlx5e_neigh_hash_entry; void mlx5e_tc_update_neigh_used_value(struct mlx5e_neigh_hash_entry *nhe); -int mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags); +int mlx5e_tc_num_filters(struct mlx5e_priv *priv, unsigned long flags); void mlx5e_tc_reoffload_flows_work(struct work_struct *work); @@ -80,7 +96,11 @@ bool mlx5e_is_valid_eswitch_fwd_dev(struct mlx5e_priv *priv, #else /* CONFIG_MLX5_ESWITCH */ static inline int mlx5e_tc_nic_init(struct mlx5e_priv *priv) { return 0; } static inline void mlx5e_tc_nic_cleanup(struct mlx5e_priv *priv) {} -static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv, int flags) { return 0; } +static inline int mlx5e_tc_num_filters(struct mlx5e_priv *priv, + unsigned long flags) +{ + return 0; +} #endif #endif /* __MLX5_EN_TC_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 600e92cb629a..d3a67a9b4eba 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -210,7 +210,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb, } for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { - struct skb_frag_struct *frag = &skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; int fsz = skb_frag_size(frag); dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz, @@ -292,8 +292,7 @@ netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; stats->packets += skb_shinfo(skb)->gso_segs; } else { - u8 mode = mlx5e_transport_inline_tx_wqe(wqe) ? - MLX5_INLINE_MODE_TCP_UDP : sq->min_inline_mode; + u8 mode = mlx5e_tx_wqe_inline_mode(sq, &wqe->ctrl, skb); opcode = MLX5_OPCODE_SEND; mss = 0; @@ -608,9 +607,11 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_bytes = skb->len + (skb_shinfo(skb)->gso_segs - 1) * ihs; stats->packets += skb_shinfo(skb)->gso_segs; } else { + u8 mode = mlx5e_tx_wqe_inline_mode(sq, NULL, skb); + opcode = MLX5_OPCODE_SEND; mss = 0; - ihs = mlx5e_calc_min_inline(sq->min_inline_mode, skb); + ihs = mlx5e_calc_min_inline(mode, skb); num_bytes = max_t(unsigned int, skb->len, ETH_ZLEN); stats->packets++; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index 49b06b256c92..257a7c9f7a14 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -33,6 +33,7 @@ #include <linux/irq.h> #include "en.h" #include "en/xdp.h" +#include "en/xsk/rx.h" #include "en/xsk/tx.h" static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c) @@ -81,6 +82,29 @@ void mlx5e_trigger_irq(struct mlx5e_icosq *sq) mlx5e_notify_hw(wq, sq->pc, sq->uar_map, &nopwqe->ctrl); } +static bool mlx5e_napi_xsk_post(struct mlx5e_xdpsq *xsksq, struct mlx5e_rq *xskrq) +{ + bool busy_xsk = false, xsk_rx_alloc_err; + + /* Handle the race between the application querying need_wakeup and the + * driver setting it: + * 1. Update need_wakeup both before and after the TX. If it goes to + * "yes", it can only happen with the first update. + * 2. If the application queried need_wakeup before we set it, the + * packets will be transmitted anyway, even w/o a wakeup. + * 3. Give a chance to clear need_wakeup after new packets were queued + * for TX. + */ + mlx5e_xsk_update_tx_wakeup(xsksq); + busy_xsk |= mlx5e_xsk_tx(xsksq, MLX5E_TX_XSK_POLL_BUDGET); + mlx5e_xsk_update_tx_wakeup(xsksq); + + xsk_rx_alloc_err = xskrq->post_wqes(xskrq); + busy_xsk |= mlx5e_xsk_update_rx_wakeup(xskrq, xsk_rx_alloc_err); + + return busy_xsk; +} + int mlx5e_napi_poll(struct napi_struct *napi, int budget) { struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel, @@ -122,8 +146,7 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) if (xsk_open) { mlx5e_poll_ico_cq(&c->xskicosq.cq); busy |= mlx5e_poll_xdpsq_cq(&xsksq->cq); - busy_xsk |= mlx5e_xsk_tx(xsksq, MLX5E_TX_XSK_POLL_BUDGET); - busy_xsk |= xskrq->post_wqes(xskrq); + busy_xsk |= mlx5e_napi_xsk_post(xsksq, xskrq); } busy |= busy_xsk; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index 41f25ea2e8d9..580c71cb9dfa 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -215,11 +215,7 @@ static int mlx5_eq_async_int(struct notifier_block *nb, */ dma_rmb(); - if (likely(eqe->type < MLX5_EVENT_TYPE_MAX)) - atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe); - else - mlx5_core_warn_once(dev, "notifier_call_chain is not setup for eqe: %d\n", eqe->type); - + atomic_notifier_call_chain(&eqt->nh[eqe->type], eqe->type, eqe); atomic_notifier_call_chain(&eqt->nh[MLX5_EVENT_TYPE_NOTIFY_ANY], eqe->type, eqe); ++eq->cons_index; @@ -328,10 +324,13 @@ err_buf: /** * mlx5_eq_enable - Enable EQ for receiving EQEs - * @dev - Device which owns the eq - * @eq - EQ to enable - * @nb - notifier call block - * mlx5_eq_enable - must be called after EQ is created in device. + * @dev : Device which owns the eq + * @eq : EQ to enable + * @nb : Notifier call block + * + * Must be called after EQ is created in device. + * + * @return: 0 if no error */ int mlx5_eq_enable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, struct notifier_block *nb) @@ -348,11 +347,12 @@ int mlx5_eq_enable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, EXPORT_SYMBOL(mlx5_eq_enable); /** - * mlx5_eq_disable - Enable EQ for receiving EQEs - * @dev - Device which owns the eq - * @eq - EQ to disable - * @nb - notifier call block - * mlx5_eq_disable - must be called before EQ is destroyed. + * mlx5_eq_disable - Disable EQ for receiving EQEs + * @dev : Device which owns the eq + * @eq : EQ to disable + * @nb : Notifier call block + * + * Must be called before EQ is destroyed. */ void mlx5_eq_disable(struct mlx5_core_dev *dev, struct mlx5_eq *eq, struct notifier_block *nb) @@ -415,7 +415,7 @@ void mlx5_eq_del_cq(struct mlx5_eq *eq, struct mlx5_core_cq *cq) int mlx5_eq_table_init(struct mlx5_core_dev *dev) { struct mlx5_eq_table *eq_table; - int i, err; + int i; eq_table = kvzalloc(sizeof(*eq_table), GFP_KERNEL); if (!eq_table) @@ -423,9 +423,7 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev) dev->priv.eq_table = eq_table; - err = mlx5_eq_debugfs_init(dev); - if (err) - goto kvfree_eq_table; + mlx5_eq_debugfs_init(dev); mutex_init(&eq_table->lock); for (i = 0; i < MLX5_EVENT_TYPE_MAX; i++) @@ -433,11 +431,6 @@ int mlx5_eq_table_init(struct mlx5_core_dev *dev) eq_table->irq_table = dev->priv.irq_table; return 0; - -kvfree_eq_table: - kvfree(eq_table); - dev->priv.eq_table = NULL; - return err; } void mlx5_eq_table_cleanup(struct mlx5_core_dev *dev) @@ -945,9 +938,6 @@ int mlx5_eq_notifier_register(struct mlx5_core_dev *dev, struct mlx5_nb *nb) { struct mlx5_eq_table *eqt = dev->priv.eq_table; - if (nb->event_type >= MLX5_EVENT_TYPE_MAX) - return -EINVAL; - return atomic_notifier_chain_register(&eqt->nh[nb->event_type], &nb->nb); } EXPORT_SYMBOL(mlx5_eq_notifier_register); @@ -956,9 +946,6 @@ int mlx5_eq_notifier_unregister(struct mlx5_core_dev *dev, struct mlx5_nb *nb) { struct mlx5_eq_table *eqt = dev->priv.eq_table; - if (nb->event_type >= MLX5_EVENT_TYPE_MAX) - return -EINVAL; - return atomic_notifier_chain_unregister(&eqt->nh[nb->event_type], &nb->nb); } EXPORT_SYMBOL(mlx5_eq_notifier_unregister); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index 1f3891fde2eb..30aae76b6a1d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -58,20 +58,9 @@ struct vport_addr { bool mc_promisc; }; -enum { - UC_ADDR_CHANGE = BIT(0), - MC_ADDR_CHANGE = BIT(1), - PROMISC_CHANGE = BIT(3), -}; - static void esw_destroy_legacy_fdb_table(struct mlx5_eswitch *esw); static void esw_cleanup_vepa_rules(struct mlx5_eswitch *esw); -/* Vport context events */ -#define SRIOV_VPORT_EVENTS (UC_ADDR_CHANGE | \ - MC_ADDR_CHANGE | \ - PROMISC_CHANGE) - struct mlx5_vport *__must_check mlx5_eswitch_get_vport(struct mlx5_eswitch *esw, u16 vport_num) { @@ -108,13 +97,13 @@ static int arm_vport_context_events_cmd(struct mlx5_core_dev *dev, u16 vport, MLX5_SET(nic_vport_context, nic_vport_ctx, arm_change_event, 1); - if (events_mask & UC_ADDR_CHANGE) + if (events_mask & MLX5_VPORT_UC_ADDR_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_uc_address_change, 1); - if (events_mask & MC_ADDR_CHANGE) + if (events_mask & MLX5_VPORT_MC_ADDR_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_mc_address_change, 1); - if (events_mask & PROMISC_CHANGE) + if (events_mask & MLX5_VPORT_PROMISC_CHANGE) MLX5_SET(nic_vport_context, nic_vport_ctx, event_on_promisc_change, 1); @@ -463,6 +452,22 @@ static int esw_create_legacy_table(struct mlx5_eswitch *esw) return err; } +#define MLX5_LEGACY_SRIOV_VPORT_EVENTS (MLX5_VPORT_UC_ADDR_CHANGE | \ + MLX5_VPORT_MC_ADDR_CHANGE | \ + MLX5_VPORT_PROMISC_CHANGE) + +static int esw_legacy_enable(struct mlx5_eswitch *esw) +{ + int ret; + + ret = esw_create_legacy_table(esw); + if (ret) + return ret; + + mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_LEGACY_SRIOV_VPORT_EVENTS); + return 0; +} + static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) { esw_cleanup_vepa_rules(esw); @@ -470,6 +475,19 @@ static void esw_destroy_legacy_table(struct mlx5_eswitch *esw) esw_destroy_legacy_vepa_table(esw); } +static void esw_legacy_disable(struct mlx5_eswitch *esw) +{ + struct esw_mc_addr *mc_promisc; + + mlx5_eswitch_disable_pf_vf_vports(esw); + + mc_promisc = &esw->mc_promisc; + if (mc_promisc->uplink_rule) + mlx5_del_flow_rules(mc_promisc->uplink_rule); + + esw_destroy_legacy_table(esw); +} + /* E-Switch vport UC/MC lists management */ typedef int (*vport_addr_action)(struct mlx5_eswitch *esw, struct vport_addr *vaddr); @@ -901,21 +919,21 @@ static void esw_vport_change_handle_locked(struct mlx5_vport *vport) esw_debug(dev, "vport[%d] Context Changed: perm mac: %pM\n", vport->vport, mac); - if (vport->enabled_events & UC_ADDR_CHANGE) { + if (vport->enabled_events & MLX5_VPORT_UC_ADDR_CHANGE) { esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC); esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_UC); } - if (vport->enabled_events & MC_ADDR_CHANGE) + if (vport->enabled_events & MLX5_VPORT_MC_ADDR_CHANGE) esw_update_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC); - if (vport->enabled_events & PROMISC_CHANGE) { + if (vport->enabled_events & MLX5_VPORT_PROMISC_CHANGE) { esw_update_vport_rx_mode(esw, vport); if (!IS_ERR_OR_NULL(vport->allmulti_rule)) esw_update_vport_mc_promisc(esw, vport); } - if (vport->enabled_events & (PROMISC_CHANGE | MC_ADDR_CHANGE)) + if (vport->enabled_events & (MLX5_VPORT_PROMISC_CHANGE | MLX5_VPORT_MC_ADDR_CHANGE)) esw_apply_vport_addr_list(esw, vport, MLX5_NVPRT_LIST_TYPE_MC); esw_debug(esw->dev, "vport[%d] Context Changed: Done\n", vport->vport); @@ -1393,18 +1411,49 @@ out: return err; } +static bool element_type_supported(struct mlx5_eswitch *esw, int type) +{ + const struct mlx5_core_dev *dev = esw->dev; + + switch (type) { + case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_TASR; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_VPORT_TC; + case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC: + return MLX5_CAP_QOS(dev, esw_element_type) & + ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC; + } + return false; +} + /* Vport QoS management */ -static int esw_create_tsar(struct mlx5_eswitch *esw) +static void esw_create_tsar(struct mlx5_eswitch *esw) { u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0}; struct mlx5_core_dev *dev = esw->dev; + __be32 *attr; int err; if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling)) - return 0; + return; + + if (!element_type_supported(esw, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR)) + return; if (esw->qos.enabled) - return -EEXIST; + return; + + MLX5_SET(scheduling_context, tsar_ctx, element_type, + SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR); + + attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes); + *attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16); err = mlx5_create_scheduling_element_cmd(dev, SCHEDULING_HIERARCHY_E_SWITCH, @@ -1412,11 +1461,10 @@ static int esw_create_tsar(struct mlx5_eswitch *esw) &esw->qos.root_tsar_id); if (err) { esw_warn(esw->dev, "E-Switch create TSAR failed (%d)\n", err); - return err; + return; } esw->qos.enabled = true; - return 0; } static void esw_destroy_tsar(struct mlx5_eswitch *esw) @@ -1537,6 +1585,22 @@ static int esw_vport_qos_config(struct mlx5_eswitch *esw, return 0; } +int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, + u32 rate_mbps) +{ + u32 ctx[MLX5_ST_SZ_DW(scheduling_context)] = {}; + struct mlx5_vport *vport; + + vport = mlx5_eswitch_get_vport(esw, vport_num); + MLX5_SET(scheduling_context, ctx, max_average_bw, rate_mbps); + + return mlx5_modify_scheduling_element_cmd(esw->dev, + SCHEDULING_HIERARCHY_E_SWITCH, + ctx, + vport->qos.esw_tsar_ix, + MODIFY_SCHEDULING_ELEMENT_IN_MODIFY_BITMASK_MAX_AVERAGE_BW); +} + static void node_guid_gen_from_mac(u64 *node_guid, u8 mac[ETH_ALEN]) { ((u8 *)node_guid)[7] = mac[0]; @@ -1619,7 +1683,7 @@ static void esw_vport_destroy_drop_counters(struct mlx5_vport *vport) } static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, - int enable_events) + enum mlx5_eswitch_vport_event enabled_events) { u16 vport_num = vport->vport; @@ -1641,7 +1705,7 @@ static void esw_enable_vport(struct mlx5_eswitch *esw, struct mlx5_vport *vport, esw_warn(esw->dev, "Failed to attach vport %d to eswitch rate limiter", vport_num); /* Sync with current vport context */ - vport->enabled_events = enable_events; + vport->enabled_events = enabled_events; vport->enabled = true; /* Esw manager is trusted by default. Host PF (vport 0) is trusted as well @@ -1770,11 +1834,46 @@ static void mlx5_eswitch_event_handlers_unregister(struct mlx5_eswitch *esw) /* Public E-Switch API */ #define ESW_ALLOWED(esw) ((esw) && MLX5_ESWITCH_MANAGER((esw)->dev)) -int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) +/* mlx5_eswitch_enable_pf_vf_vports() enables vports of PF, ECPF and VFs + * whichever are present on the eswitch. + */ +void +mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, + enum mlx5_eswitch_vport_event enabled_events) { struct mlx5_vport *vport; + int i; + + /* Enable PF vport */ + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); + esw_enable_vport(esw, vport, enabled_events); + + /* Enable ECPF vports */ + if (mlx5_ecpf_vport_exists(esw->dev)) { + vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); + esw_enable_vport(esw, vport, enabled_events); + } + + /* Enable VF vports */ + mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) + esw_enable_vport(esw, vport, enabled_events); +} + +/* mlx5_eswitch_disable_pf_vf_vports() disables vports of PF, ECPF and VFs + * whichever are previously enabled on the eswitch. + */ +void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw) +{ + struct mlx5_vport *vport; + int i; + + mlx5_esw_for_all_vports_reverse(esw, i, vport) + esw_disable_vport(esw, vport); +} + +int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) +{ int err; - int i, enabled_events; if (!ESW_ALLOWED(esw) || !MLX5_CAP_ESW_FLOWTABLE_FDB(esw->dev, ft_support)) { @@ -1788,44 +1887,23 @@ int mlx5_eswitch_enable(struct mlx5_eswitch *esw, int mode) if (!MLX5_CAP_ESW_EGRESS_ACL(esw->dev, ft_support)) esw_warn(esw->dev, "engress ACL is not supported by FW\n"); + esw_create_tsar(esw); + esw->mode = mode; mlx5_lag_update(esw->dev); if (mode == MLX5_ESWITCH_LEGACY) { - err = esw_create_legacy_table(esw); - if (err) - goto abort; + err = esw_legacy_enable(esw); } else { mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_ETH); mlx5_reload_interface(esw->dev, MLX5_INTERFACE_PROTOCOL_IB); - err = esw_offloads_init(esw); + err = esw_offloads_enable(esw); } if (err) goto abort; - err = esw_create_tsar(esw); - if (err) - esw_warn(esw->dev, "Failed to create eswitch TSAR"); - - enabled_events = (mode == MLX5_ESWITCH_LEGACY) ? SRIOV_VPORT_EVENTS : - UC_ADDR_CHANGE; - - /* Enable PF vport */ - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_PF); - esw_enable_vport(esw, vport, enabled_events); - - /* Enable ECPF vports */ - if (mlx5_ecpf_vport_exists(esw->dev)) { - vport = mlx5_eswitch_get_vport(esw, MLX5_VPORT_ECPF); - esw_enable_vport(esw, vport, enabled_events); - } - - /* Enable VF vports */ - mlx5_esw_for_each_vf_vport(esw, i, vport, esw->esw_funcs.num_vfs) - esw_enable_vport(esw, vport, enabled_events); - mlx5_eswitch_event_handlers_register(esw); esw_info(esw->dev, "Enable: mode(%s), nvfs(%d), active vports(%d)\n", @@ -1847,10 +1925,7 @@ abort: void mlx5_eswitch_disable(struct mlx5_eswitch *esw) { - struct esw_mc_addr *mc_promisc; - struct mlx5_vport *vport; int old_mode; - int i; if (!ESW_ALLOWED(esw) || esw->mode == MLX5_ESWITCH_NONE) return; @@ -1859,21 +1934,14 @@ void mlx5_eswitch_disable(struct mlx5_eswitch *esw) esw->mode == MLX5_ESWITCH_LEGACY ? "LEGACY" : "OFFLOADS", esw->esw_funcs.num_vfs, esw->enabled_vports); - mc_promisc = &esw->mc_promisc; mlx5_eswitch_event_handlers_unregister(esw); - mlx5_esw_for_all_vports(esw, i, vport) - esw_disable_vport(esw, vport); - - if (mc_promisc && mc_promisc->uplink_rule) - mlx5_del_flow_rules(mc_promisc->uplink_rule); - - esw_destroy_tsar(esw); - if (esw->mode == MLX5_ESWITCH_LEGACY) - esw_destroy_legacy_table(esw); + esw_legacy_disable(esw); else if (esw->mode == MLX5_ESWITCH_OFFLOADS) - esw_offloads_cleanup(esw); + esw_offloads_disable(esw); + + esw_destroy_tsar(esw); old_mode = esw->mode; esw->mode = MLX5_ESWITCH_NONE; @@ -1931,8 +1999,11 @@ int mlx5_eswitch_init(struct mlx5_core_dev *dev) if (err) goto abort; + mutex_init(&esw->offloads.encap_tbl_lock); hash_init(esw->offloads.encap_tbl); - hash_init(esw->offloads.mod_hdr_tbl); + mutex_init(&esw->offloads.mod_hdr.lock); + hash_init(esw->offloads.mod_hdr.hlist); + atomic64_set(&esw->offloads.num_flows, 0); mutex_init(&esw->state_lock); mlx5_esw_for_all_vports(esw, i, vport) { @@ -1968,6 +2039,8 @@ void mlx5_eswitch_cleanup(struct mlx5_eswitch *esw) esw->dev->priv.eswitch = NULL; destroy_workqueue(esw->work_queue); esw_offloads_cleanup_reps(esw); + mutex_destroy(&esw->offloads.mod_hdr.lock); + mutex_destroy(&esw->offloads.encap_tbl_lock); kfree(esw->vports); kfree(esw); } @@ -2085,23 +2158,19 @@ int __mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, if (vlan > 4095 || qos > 7) return -EINVAL; - mutex_lock(&esw->state_lock); - err = modify_esw_vport_cvlan(esw->dev, vport, vlan, qos, set_flags); if (err) - goto unlock; + return err; evport->info.vlan = vlan; evport->info.qos = qos; if (evport->enabled && esw->mode == MLX5_ESWITCH_LEGACY) { err = esw_vport_ingress_config(esw, evport); if (err) - goto unlock; + return err; err = esw_vport_egress_config(esw, evport); } -unlock: - mutex_unlock(&esw->state_lock); return err; } @@ -2109,11 +2178,16 @@ int mlx5_eswitch_set_vport_vlan(struct mlx5_eswitch *esw, u16 vport, u16 vlan, u8 qos) { u8 set_flags = 0; + int err; if (vlan || qos) set_flags = SET_VLAN_STRIP | SET_VLAN_INSERT; - return __mlx5_eswitch_set_vport_vlan(esw, vport, vlan, qos, set_flags); + mutex_lock(&esw->state_lock); + err = __mlx5_eswitch_set_vport_vlan(esw, vport, vlan, qos, set_flags); + mutex_unlock(&esw->state_lock); + + return err; } int mlx5_eswitch_set_vport_spoofchk(struct mlx5_eswitch *esw, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h index 04685dbb280c..6bd6f5895244 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.h @@ -35,6 +35,7 @@ #include <linux/if_ether.h> #include <linux/if_link.h> +#include <linux/atomic.h> #include <net/devlink.h> #include <linux/mlx5/device.h> #include <linux/mlx5/eswitch.h> @@ -68,7 +69,7 @@ struct vport_ingress { struct mlx5_flow_group *allow_spoofchk_only_grp; struct mlx5_flow_group *allow_untagged_only_grp; struct mlx5_flow_group *drop_grp; - int modify_metadata_id; + struct mlx5_modify_hdr *modify_metadata; struct mlx5_flow_handle *modify_metadata_rule; struct mlx5_flow_handle *allow_rule; struct mlx5_flow_handle *drop_rule; @@ -101,6 +102,13 @@ struct mlx5_vport_info { bool trusted; }; +/* Vport context events */ +enum mlx5_eswitch_vport_event { + MLX5_VPORT_UC_ADDR_CHANGE = BIT(0), + MLX5_VPORT_MC_ADDR_CHANGE = BIT(1), + MLX5_VPORT_PROMISC_CHANGE = BIT(3), +}; + struct mlx5_vport { struct mlx5_core_dev *dev; int vport; @@ -122,7 +130,7 @@ struct mlx5_vport { } qos; bool enabled; - u16 enabled_events; + enum mlx5_eswitch_vport_event enabled_events; }; enum offloads_fdb_flags { @@ -145,6 +153,7 @@ struct mlx5_eswitch_fdb { } legacy; struct offloads_fdb { + struct mlx5_flow_namespace *ns; struct mlx5_flow_table *slow_fdb; struct mlx5_flow_group *send_to_vport_grp; struct mlx5_flow_group *peer_miss_grp; @@ -173,13 +182,14 @@ struct mlx5_esw_offload { struct mlx5_eswitch_rep *vport_reps; struct list_head peer_flows; struct mutex peer_mutex; + struct mutex encap_tbl_lock; /* protects encap_tbl */ DECLARE_HASHTABLE(encap_tbl, 8); - DECLARE_HASHTABLE(mod_hdr_tbl, 8); + struct mod_hdr_tbl mod_hdr; DECLARE_HASHTABLE(termtbl_tbl, 8); struct mutex termtbl_mutex; /* protects termtbl hash */ const struct mlx5_eswitch_rep_ops *rep_ops[NUM_REP_TYPES]; u8 inline_mode; - u64 num_flows; + atomic64_t num_flows; enum devlink_eswitch_encap_mode encap; }; @@ -207,8 +217,11 @@ enum { struct mlx5_eswitch { struct mlx5_core_dev *dev; struct mlx5_nb nb; + /* legacy data structures */ struct mlx5_eswitch_fdb fdb_table; struct hlist_head mc_table[MLX5_L2_ADDR_HASH_SIZE]; + struct esw_mc_addr mc_promisc; + /* end of legacy */ struct workqueue_struct *work_queue; struct mlx5_vport *vports; u32 flags; @@ -218,7 +231,6 @@ struct mlx5_eswitch { * and async SRIOV admin state changes */ struct mutex state_lock; - struct esw_mc_addr mc_promisc; struct { bool enabled; @@ -233,8 +245,8 @@ struct mlx5_eswitch { struct mlx5_esw_functions esw_funcs; }; -void esw_offloads_cleanup(struct mlx5_eswitch *esw); -int esw_offloads_init(struct mlx5_eswitch *esw); +void esw_offloads_disable(struct mlx5_eswitch *esw); +int esw_offloads_enable(struct mlx5_eswitch *esw); void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw); int esw_offloads_init_reps(struct mlx5_eswitch *esw); void esw_vport_cleanup_ingress_rules(struct mlx5_eswitch *esw, @@ -251,6 +263,8 @@ void esw_vport_disable_ingress_acl(struct mlx5_eswitch *esw, struct mlx5_vport *vport); void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, struct mlx5_vport *vport); +int mlx5_esw_modify_vport_rate(struct mlx5_eswitch *esw, u16 vport_num, + u32 rate_mbps); /* E-Switch API */ int mlx5_eswitch_init(struct mlx5_core_dev *dev); @@ -372,11 +386,11 @@ struct mlx5_esw_flow_attr { struct { u32 flags; struct mlx5_eswitch_rep *rep; + struct mlx5_pkt_reformat *pkt_reformat; struct mlx5_core_dev *mdev; - u32 encap_id; struct mlx5_termtbl_handle *termtbl; } dests[MLX5_MAX_FLOW_FWD_VPORTS]; - u32 mod_hdr_id; + struct mlx5_modify_hdr *modify_hdr; u8 inner_match_level; u8 outer_match_level; struct mlx5_fc *counter; @@ -513,6 +527,11 @@ void mlx5e_tc_clean_fdb_peer_flows(struct mlx5_eswitch *esw); (vport) = &(esw)->vports[i], \ (i) < (esw)->total_vports; (i)++) +#define mlx5_esw_for_all_vports_reverse(esw, i, vport) \ + for ((i) = (esw)->total_vports - 1; \ + (vport) = &(esw)->vports[i], \ + (i) >= MLX5_VPORT_PF; (i)--) + #define mlx5_esw_for_each_vf_vport(esw, i, vport, nvfs) \ for ((i) = MLX5_VPORT_FIRST_VF; \ (vport) = &(esw)->vports[(i)], \ @@ -574,6 +593,11 @@ bool mlx5_eswitch_is_vf_vport(const struct mlx5_eswitch *esw, u16 vport_num); void mlx5_eswitch_update_num_of_vfs(struct mlx5_eswitch *esw, const int num_vfs); int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type, void *data); +void +mlx5_eswitch_enable_pf_vf_vports(struct mlx5_eswitch *esw, + enum mlx5_eswitch_vport_event enabled_events); +void mlx5_eswitch_disable_pf_vf_vports(struct mlx5_eswitch *esw); + #else /* CONFIG_MLX5_ESWITCH */ /* eswitch API stubs */ static inline int mlx5_eswitch_init(struct mlx5_core_dev *dev) { return 0; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c index 0323fd078271..00d71db15f22 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch_offloads.c @@ -190,10 +190,10 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, MLX5_FLOW_DEST_VPORT_VHCA_ID; if (attr->dests[j].flags & MLX5_ESW_DEST_ENCAP) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT; - flow_act.reformat_id = attr->dests[j].encap_id; + flow_act.pkt_reformat = attr->dests[j].pkt_reformat; dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID; - dest[i].vport.reformat_id = - attr->dests[j].encap_id; + dest[i].vport.pkt_reformat = + attr->dests[j].pkt_reformat; } i++; } @@ -213,7 +213,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, spec->match_criteria_enable |= MLX5_MATCH_INNER_HEADERS; if (flow_act.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) - flow_act.modify_id = attr->mod_hdr_id; + flow_act.modify_hdr = attr->modify_hdr; fdb = esw_get_prio_table(esw, attr->chain, attr->prio, !!split); if (IS_ERR(fdb)) { @@ -229,7 +229,7 @@ mlx5_eswitch_add_offloaded_rule(struct mlx5_eswitch *esw, if (IS_ERR(rule)) goto err_add_rule; else - esw->offloads.num_flows++; + atomic64_inc(&esw->offloads.num_flows); return rule; @@ -276,7 +276,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_VHCA_ID; if (attr->dests[i].flags & MLX5_ESW_DEST_ENCAP) { dest[i].vport.flags |= MLX5_FLOW_DEST_VPORT_REFORMAT_ID; - dest[i].vport.reformat_id = attr->dests[i].encap_id; + dest[i].vport.pkt_reformat = attr->dests[i].pkt_reformat; } } dest[i].type = MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE; @@ -294,7 +294,7 @@ mlx5_eswitch_add_fwd_rule(struct mlx5_eswitch *esw, if (IS_ERR(rule)) goto add_err; - esw->offloads.num_flows++; + atomic64_inc(&esw->offloads.num_flows); return rule; add_err: @@ -322,7 +322,7 @@ __mlx5_eswitch_del_rule(struct mlx5_eswitch *esw, mlx5_eswitch_termtbl_put(esw, attr->dests[i].termtbl); } - esw->offloads.num_flows--; + atomic64_dec(&esw->offloads.num_flows); if (fwd_rule) { esw_put_prio_table(esw, attr->chain, attr->prio, 1); @@ -438,9 +438,11 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, fwd = !!((attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) && !attr->dest_chain); + mutex_lock(&esw->state_lock); + err = esw_add_vlan_action_check(attr, push, pop, fwd); if (err) - return err; + goto unlock; attr->vlan_handled = false; @@ -453,11 +455,11 @@ int mlx5_eswitch_add_vlan_action(struct mlx5_eswitch *esw, attr->vlan_handled = true; } - return 0; + goto unlock; } if (!push && !pop) - return 0; + goto unlock; if (!(offloads->vlan_push_pop_refcount)) { /* it's the 1st vlan rule, apply global vlan pop policy */ @@ -482,6 +484,8 @@ skip_set_push: out: if (!err) attr->vlan_handled = true; +unlock: + mutex_unlock(&esw->state_lock); return err; } @@ -504,6 +508,8 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, pop = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP); fwd = !!(attr->action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST); + mutex_lock(&esw->state_lock); + vport = esw_vlan_action_get_vport(attr, push, pop); if (!push && !pop && fwd) { @@ -511,7 +517,7 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, if (attr->dests[0].rep->vport == MLX5_VPORT_UPLINK) vport->vlan_refcount--; - return 0; + goto out; } if (push) { @@ -529,12 +535,13 @@ int mlx5_eswitch_del_vlan_action(struct mlx5_eswitch *esw, skip_unset_push: offloads->vlan_push_pop_refcount--; if (offloads->vlan_push_pop_refcount) - return 0; + goto out; /* no more vlan rules, stop global vlan pop policy */ err = esw_set_global_vlan_pop(esw, 0); out: + mutex_unlock(&esw->state_lock); return err; } @@ -583,38 +590,15 @@ void mlx5_eswitch_del_send_to_vport_rule(struct mlx5_flow_handle *rule) mlx5_del_flow_rules(rule); } -static int mlx5_eswitch_enable_passing_vport_metadata(struct mlx5_eswitch *esw) +static int esw_set_passing_vport_metadata(struct mlx5_eswitch *esw, bool enable) { u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {}; u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {}; u8 fdb_to_vport_reg_c_id; int err; - err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport, - out, sizeof(out)); - if (err) - return err; - - fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out, - esw_vport_context.fdb_to_vport_reg_c_id); - - fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0; - MLX5_SET(modify_esw_vport_context_in, in, - esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id); - - MLX5_SET(modify_esw_vport_context_in, in, - field_select.fdb_to_vport_reg_c_id, 1); - - return mlx5_eswitch_modify_esw_vport_context(esw, esw->manager_vport, - in, sizeof(in)); -} - -static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw) -{ - u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {}; - u32 in[MLX5_ST_SZ_DW(modify_esw_vport_context_in)] = {}; - u8 fdb_to_vport_reg_c_id; - int err; + if (!mlx5_eswitch_vport_match_metadata_enabled(esw)) + return 0; err = mlx5_eswitch_query_esw_vport_context(esw, esw->manager_vport, out, sizeof(out)); @@ -624,7 +608,10 @@ static int mlx5_eswitch_disable_passing_vport_metadata(struct mlx5_eswitch *esw) fdb_to_vport_reg_c_id = MLX5_GET(query_esw_vport_context_out, out, esw_vport_context.fdb_to_vport_reg_c_id); - fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0; + if (enable) + fdb_to_vport_reg_c_id |= MLX5_FDB_TO_VPORT_REG_C_0; + else + fdb_to_vport_reg_c_id &= ~MLX5_FDB_TO_VPORT_REG_C_0; MLX5_SET(modify_esw_vport_context_in, in, esw_vport_context.fdb_to_vport_reg_c_id, fdb_to_vport_reg_c_id); @@ -1081,6 +1068,13 @@ static int esw_create_offloads_fdb_tables(struct mlx5_eswitch *esw, int nvports) err = -EOPNOTSUPP; goto ns_err; } + esw->fdb_table.offloads.ns = root_ns; + err = mlx5_flow_namespace_set_mode(root_ns, + esw->dev->priv.steering->mode); + if (err) { + esw_warn(dev, "Failed to set FDB namespace steering mode\n"); + goto ns_err; + } max_flow_counter = (MLX5_CAP_GEN(dev, max_flow_counter_31_16) << 16) | MLX5_CAP_GEN(dev, max_flow_counter_15_0); @@ -1220,6 +1214,8 @@ send_vport_err: esw_destroy_offloads_fast_fdb_tables(esw); mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); slow_fdb_err: + /* Holds true only as long as DMFS is the default */ + mlx5_flow_namespace_set_mode(root_ns, MLX5_FLOW_STEERING_MODE_DMFS); ns_err: kvfree(flow_group_in); return err; @@ -1239,6 +1235,9 @@ static void esw_destroy_offloads_fdb_tables(struct mlx5_eswitch *esw) mlx5_destroy_flow_table(esw->fdb_table.offloads.slow_fdb); esw_destroy_offloads_fast_fdb_tables(esw); + /* Holds true only as long as DMFS is the default */ + mlx5_flow_namespace_set_mode(esw->fdb_table.offloads.ns, + MLX5_FLOW_STEERING_MODE_DMFS); } static int esw_create_offloads_table(struct mlx5_eswitch *esw, int nvports) @@ -1402,10 +1401,9 @@ void esw_offloads_cleanup_reps(struct mlx5_eswitch *esw) int esw_offloads_init_reps(struct mlx5_eswitch *esw) { int total_vports = esw->total_vports; - struct mlx5_core_dev *dev = esw->dev; struct mlx5_eswitch_rep *rep; - u8 hw_id[ETH_ALEN], rep_type; int vport_index; + u8 rep_type; esw->offloads.vport_reps = kcalloc(total_vports, sizeof(struct mlx5_eswitch_rep), @@ -1413,12 +1411,9 @@ int esw_offloads_init_reps(struct mlx5_eswitch *esw) if (!esw->offloads.vport_reps) return -ENOMEM; - mlx5_query_mac_address(dev, hw_id); - mlx5_esw_for_all_reps(esw, vport_index, rep) { rep->vport = mlx5_eswitch_index_to_vport_num(esw, vport_index); rep->vport_index = vport_index; - ether_addr_copy(rep->hw_id, hw_id); for (rep_type = 0; rep_type < NUM_REP_TYPES; rep_type++) atomic_set(&rep->rep_data[rep_type].state, @@ -1640,13 +1635,42 @@ static void mlx5_esw_offloads_unpair(struct mlx5_eswitch *esw) esw_del_fdb_peer_miss_rules(esw); } +static int mlx5_esw_offloads_set_ns_peer(struct mlx5_eswitch *esw, + struct mlx5_eswitch *peer_esw, + bool pair) +{ + struct mlx5_flow_root_namespace *peer_ns; + struct mlx5_flow_root_namespace *ns; + int err; + + peer_ns = peer_esw->dev->priv.steering->fdb_root_ns; + ns = esw->dev->priv.steering->fdb_root_ns; + + if (pair) { + err = mlx5_flow_namespace_set_peer(ns, peer_ns); + if (err) + return err; + + err = mlx5_flow_namespace_set_peer(peer_ns, ns); + if (err) { + mlx5_flow_namespace_set_peer(ns, NULL); + return err; + } + } else { + mlx5_flow_namespace_set_peer(ns, NULL); + mlx5_flow_namespace_set_peer(peer_ns, NULL); + } + + return 0; +} + static int mlx5_esw_offloads_devcom_event(int event, void *my_data, void *event_data) { struct mlx5_eswitch *esw = my_data; - struct mlx5_eswitch *peer_esw = event_data; struct mlx5_devcom *devcom = esw->dev->priv.devcom; + struct mlx5_eswitch *peer_esw = event_data; int err; switch (event) { @@ -1655,9 +1679,12 @@ static int mlx5_esw_offloads_devcom_event(int event, mlx5_eswitch_vport_match_metadata_enabled(peer_esw)) break; - err = mlx5_esw_offloads_pair(esw, peer_esw); + err = mlx5_esw_offloads_set_ns_peer(esw, peer_esw, true); if (err) goto err_out; + err = mlx5_esw_offloads_pair(esw, peer_esw); + if (err) + goto err_peer; err = mlx5_esw_offloads_pair(peer_esw, esw); if (err) @@ -1673,6 +1700,7 @@ static int mlx5_esw_offloads_devcom_event(int event, mlx5_devcom_set_paired(devcom, MLX5_DEVCOM_ESW_OFFLOADS, false); mlx5_esw_offloads_unpair(peer_esw); mlx5_esw_offloads_unpair(esw); + mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false); break; } @@ -1680,7 +1708,8 @@ static int mlx5_esw_offloads_devcom_event(int event, err_pair: mlx5_esw_offloads_unpair(esw); - +err_peer: + mlx5_esw_offloads_set_ns_peer(esw, peer_esw, false); err_out: mlx5_core_err(esw->dev, "esw offloads devcom event failure, event %u err %d", event, err); @@ -1751,7 +1780,7 @@ static int esw_vport_ingress_prio_tag_config(struct mlx5_eswitch *esw, if (vport->ingress.modify_metadata_rule) { flow_act.action |= MLX5_FLOW_CONTEXT_ACTION_MOD_HDR; - flow_act.modify_id = vport->ingress.modify_metadata_id; + flow_act.modify_hdr = vport->ingress.modify_metadata; } vport->ingress.allow_rule = @@ -1787,9 +1816,11 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, MLX5_SET(set_action_in, action, data, mlx5_eswitch_get_vport_metadata_for_match(esw, vport->vport)); - err = mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS, - 1, action, &vport->ingress.modify_metadata_id); - if (err) { + vport->ingress.modify_metadata = + mlx5_modify_header_alloc(esw->dev, MLX5_FLOW_NAMESPACE_ESW_INGRESS, + 1, action); + if (IS_ERR(vport->ingress.modify_metadata)) { + err = PTR_ERR(vport->ingress.modify_metadata); esw_warn(esw->dev, "failed to alloc modify header for vport %d ingress acl (%d)\n", vport->vport, err); @@ -1797,7 +1828,7 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, } flow_act.action = MLX5_FLOW_CONTEXT_ACTION_MOD_HDR | MLX5_FLOW_CONTEXT_ACTION_ALLOW; - flow_act.modify_id = vport->ingress.modify_metadata_id; + flow_act.modify_hdr = vport->ingress.modify_metadata; vport->ingress.modify_metadata_rule = mlx5_add_flow_rules(vport->ingress.acl, &spec, &flow_act, NULL, 0); if (IS_ERR(vport->ingress.modify_metadata_rule)) { @@ -1811,7 +1842,7 @@ static int esw_vport_add_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, out: if (err) - mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id); + mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata); return err; } @@ -1820,7 +1851,7 @@ void esw_vport_del_ingress_acl_modify_metadata(struct mlx5_eswitch *esw, { if (vport->ingress.modify_metadata_rule) { mlx5_del_flow_rules(vport->ingress.modify_metadata_rule); - mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata_id); + mlx5_modify_header_dealloc(esw->dev, vport->ingress.modify_metadata); vport->ingress.modify_metadata_rule = NULL; } @@ -2120,7 +2151,7 @@ int mlx5_esw_funcs_changed_handler(struct notifier_block *nb, unsigned long type return NOTIFY_OK; } -int esw_offloads_init(struct mlx5_eswitch *esw) +int esw_offloads_enable(struct mlx5_eswitch *esw) { int err; @@ -2130,15 +2161,16 @@ int esw_offloads_init(struct mlx5_eswitch *esw) else esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; + mlx5_rdma_enable_roce(esw->dev); err = esw_offloads_steering_init(esw); if (err) - return err; + goto err_steering_init; - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) { - err = mlx5_eswitch_enable_passing_vport_metadata(esw); - if (err) - goto err_vport_metadata; - } + err = esw_set_passing_vport_metadata(esw, true); + if (err) + goto err_vport_metadata; + + mlx5_eswitch_enable_pf_vf_vports(esw, MLX5_VPORT_UC_ADDR_CHANGE); err = esw_offloads_load_all_reps(esw); if (err) @@ -2147,15 +2179,15 @@ int esw_offloads_init(struct mlx5_eswitch *esw) esw_offloads_devcom_init(esw); mutex_init(&esw->offloads.termtbl_mutex); - mlx5_rdma_enable_roce(esw->dev); - return 0; err_reps: - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) - mlx5_eswitch_disable_passing_vport_metadata(esw); + mlx5_eswitch_disable_pf_vf_vports(esw); + esw_set_passing_vport_metadata(esw, false); err_vport_metadata: esw_offloads_steering_cleanup(esw); +err_steering_init: + mlx5_rdma_disable_roce(esw->dev); return err; } @@ -2178,14 +2210,14 @@ static int esw_offloads_stop(struct mlx5_eswitch *esw, return err; } -void esw_offloads_cleanup(struct mlx5_eswitch *esw) +void esw_offloads_disable(struct mlx5_eswitch *esw) { - mlx5_rdma_disable_roce(esw->dev); esw_offloads_devcom_cleanup(esw); esw_offloads_unload_all_reps(esw); - if (mlx5_eswitch_vport_match_metadata_enabled(esw)) - mlx5_eswitch_disable_passing_vport_metadata(esw); + mlx5_eswitch_disable_pf_vf_vports(esw); + esw_set_passing_vport_metadata(esw, false); esw_offloads_steering_cleanup(esw); + mlx5_rdma_disable_roce(esw->dev); esw->offloads.encap = DEVLINK_ESWITCH_ENCAP_MODE_NONE; } @@ -2345,7 +2377,7 @@ int mlx5_devlink_eswitch_inline_mode_set(struct devlink *devlink, u8 mode, break; } - if (esw->offloads.num_flows > 0) { + if (atomic64_read(&esw->offloads.num_flows) > 0) { NL_SET_ERR_MSG_MOD(extack, "Can't set inline mode when flows are configured"); return -EOPNOTSUPP; @@ -2455,7 +2487,7 @@ int mlx5_devlink_eswitch_encap_mode_set(struct devlink *devlink, if (esw->offloads.encap == encap) return 0; - if (esw->offloads.num_flows > 0) { + if (atomic64_read(&esw->offloads.num_flows) > 0) { NL_SET_ERR_MSG_MOD(extack, "Can't set encapsulation when flows are configured"); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c index 7ac1249eadc3..579c306caa7b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.c @@ -107,6 +107,50 @@ static int mlx5_cmd_stub_delete_fte(struct mlx5_flow_root_namespace *ns, return 0; } +static int mlx5_cmd_stub_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat) +{ + return 0; +} + +static void mlx5_cmd_stub_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat) +{ +} + +static int mlx5_cmd_stub_modify_header_alloc(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr) +{ + return 0; +} + +static void mlx5_cmd_stub_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr) +{ +} + +static int mlx5_cmd_stub_set_peer(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns) +{ + return 0; +} + +static int mlx5_cmd_stub_create_ns(struct mlx5_flow_root_namespace *ns) +{ + return 0; +} + +static int mlx5_cmd_stub_destroy_ns(struct mlx5_flow_root_namespace *ns) +{ + return 0; +} + static int mlx5_cmd_update_root_ft(struct mlx5_flow_root_namespace *ns, struct mlx5_flow_table *ft, u32 underlay_qpn, bool disconnect) @@ -182,7 +226,7 @@ static int mlx5_cmd_create_flow_table(struct mlx5_flow_root_namespace *ns, } else { MLX5_SET(create_flow_table_in, in, flow_table_context.table_miss_action, - ns->def_miss_action); + ft->def_miss_action); } break; @@ -262,7 +306,7 @@ static int mlx5_cmd_modify_flow_table(struct mlx5_flow_root_namespace *ns, } else { MLX5_SET(modify_flow_table_in, in, flow_table_context.table_miss_action, - ns->def_miss_action); + ft->def_miss_action); } } @@ -412,11 +456,13 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, } else { MLX5_SET(flow_context, in_flow_context, action, fte->action.action); - MLX5_SET(flow_context, in_flow_context, packet_reformat_id, - fte->action.reformat_id); + if (fte->action.pkt_reformat) + MLX5_SET(flow_context, in_flow_context, packet_reformat_id, + fte->action.pkt_reformat->id); } - MLX5_SET(flow_context, in_flow_context, modify_header_id, - fte->action.modify_id); + if (fte->action.modify_hdr) + MLX5_SET(flow_context, in_flow_context, modify_header_id, + fte->action.modify_hdr->id); vlan = MLX5_ADDR_OF(flow_context, in_flow_context, push_vlan); @@ -468,7 +514,7 @@ static int mlx5_cmd_set_fte(struct mlx5_core_dev *dev, MLX5_FLOW_DEST_VPORT_REFORMAT_ID)); MLX5_SET(extended_dest_format, in_dests, packet_reformat_id, - dst->dest_attr.vport.reformat_id); + dst->dest_attr.vport.pkt_reformat->id); } break; default: @@ -566,7 +612,9 @@ static int mlx5_cmd_delete_fte(struct mlx5_flow_root_namespace *ns, return mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) +int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask, + u32 *id) { u32 in[MLX5_ST_SZ_DW(alloc_flow_counter_in)] = {0}; u32 out[MLX5_ST_SZ_DW(alloc_flow_counter_out)] = {0}; @@ -574,6 +622,7 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) MLX5_SET(alloc_flow_counter_in, in, opcode, MLX5_CMD_OP_ALLOC_FLOW_COUNTER); + MLX5_SET(alloc_flow_counter_in, in, flow_counter_bulk, alloc_bitmask); err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); if (!err) @@ -581,6 +630,11 @@ int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) return err; } +int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id) +{ + return mlx5_cmd_fc_bulk_alloc(dev, 0, id); +} + int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id) { u32 in[MLX5_ST_SZ_DW(dealloc_flow_counter_in)] = {0}; @@ -615,77 +669,35 @@ int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, return 0; } -struct mlx5_cmd_fc_bulk { - u32 id; - int num; - int outlen; - u32 out[0]; -}; - -struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num) -{ - struct mlx5_cmd_fc_bulk *b; - int outlen = - MLX5_ST_SZ_BYTES(query_flow_counter_out) + - MLX5_ST_SZ_BYTES(traffic_counter) * num; - - b = kzalloc(sizeof(*b) + outlen, GFP_KERNEL); - if (!b) - return NULL; - - b->id = id; - b->num = num; - b->outlen = outlen; - - return b; -} - -void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b) +int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len) { - kfree(b); + return MLX5_ST_SZ_BYTES(query_flow_counter_out) + + MLX5_ST_SZ_BYTES(traffic_counter) * bulk_len; } -int -mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b) +int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, + u32 *out) { + int outlen = mlx5_cmd_fc_get_bulk_query_out_len(bulk_len); u32 in[MLX5_ST_SZ_DW(query_flow_counter_in)] = {0}; MLX5_SET(query_flow_counter_in, in, opcode, MLX5_CMD_OP_QUERY_FLOW_COUNTER); MLX5_SET(query_flow_counter_in, in, op_mod, 0); - MLX5_SET(query_flow_counter_in, in, flow_counter_id, b->id); - MLX5_SET(query_flow_counter_in, in, num_of_counters, b->num); - return mlx5_cmd_exec(dev, in, sizeof(in), b->out, b->outlen); + MLX5_SET(query_flow_counter_in, in, flow_counter_id, base_id); + MLX5_SET(query_flow_counter_in, in, num_of_counters, bulk_len); + return mlx5_cmd_exec(dev, in, sizeof(in), out, outlen); } -void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u32 id, - u64 *packets, u64 *bytes) -{ - int index = id - b->id; - void *stats; - - if (index < 0 || index >= b->num) { - mlx5_core_warn(dev, "Flow counter id (0x%x) out of range (0x%x..0x%x). Counter ignored.\n", - id, b->id, b->id + b->num - 1); - return; - } - - stats = MLX5_ADDR_OF(query_flow_counter_out, b->out, - flow_statistics[index]); - *packets = MLX5_GET64(traffic_counter, stats, packets); - *bytes = MLX5_GET64(traffic_counter, stats, octets); -} - -int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, - int reformat_type, - size_t size, - void *reformat_data, - enum mlx5_flow_namespace_type namespace, - u32 *packet_reformat_id) +static int mlx5_cmd_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat) { u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)]; + struct mlx5_core_dev *dev = ns->dev; void *packet_reformat_context_in; int max_encap_size; void *reformat; @@ -728,35 +740,36 @@ int mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, memset(out, 0, sizeof(out)); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); - *packet_reformat_id = MLX5_GET(alloc_packet_reformat_context_out, - out, packet_reformat_id); + pkt_reformat->id = MLX5_GET(alloc_packet_reformat_context_out, + out, packet_reformat_id); kfree(in); return err; } -EXPORT_SYMBOL(mlx5_packet_reformat_alloc); -void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, - u32 packet_reformat_id) +static void mlx5_cmd_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat) { u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)]; u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)]; + struct mlx5_core_dev *dev = ns->dev; memset(in, 0, sizeof(in)); MLX5_SET(dealloc_packet_reformat_context_in, in, opcode, MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT); MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id, - packet_reformat_id); + pkt_reformat->id); mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -EXPORT_SYMBOL(mlx5_packet_reformat_dealloc); -int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, - u8 namespace, u8 num_actions, - void *modify_actions, u32 *modify_header_id) +static int mlx5_cmd_modify_header_alloc(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr) { u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)]; int max_actions, actions_size, inlen, err; + struct mlx5_core_dev *dev = ns->dev; void *actions_in; u8 table_type; u32 *in; @@ -807,26 +820,26 @@ int mlx5_modify_header_alloc(struct mlx5_core_dev *dev, memset(out, 0, sizeof(out)); err = mlx5_cmd_exec(dev, in, inlen, out, sizeof(out)); - *modify_header_id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id); + modify_hdr->id = MLX5_GET(alloc_modify_header_context_out, out, modify_header_id); kfree(in); return err; } -EXPORT_SYMBOL(mlx5_modify_header_alloc); -void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, u32 modify_header_id) +static void mlx5_cmd_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr) { u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)]; u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)]; + struct mlx5_core_dev *dev = ns->dev; memset(in, 0, sizeof(in)); MLX5_SET(dealloc_modify_header_context_in, in, opcode, MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT); MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id, - modify_header_id); + modify_hdr->id); mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); } -EXPORT_SYMBOL(mlx5_modify_header_dealloc); static const struct mlx5_flow_cmds mlx5_flow_cmds = { .create_flow_table = mlx5_cmd_create_flow_table, @@ -838,6 +851,13 @@ static const struct mlx5_flow_cmds mlx5_flow_cmds = { .update_fte = mlx5_cmd_update_fte, .delete_fte = mlx5_cmd_delete_fte, .update_root_ft = mlx5_cmd_update_root_ft, + .packet_reformat_alloc = mlx5_cmd_packet_reformat_alloc, + .packet_reformat_dealloc = mlx5_cmd_packet_reformat_dealloc, + .modify_header_alloc = mlx5_cmd_modify_header_alloc, + .modify_header_dealloc = mlx5_cmd_modify_header_dealloc, + .set_peer = mlx5_cmd_stub_set_peer, + .create_ns = mlx5_cmd_stub_create_ns, + .destroy_ns = mlx5_cmd_stub_destroy_ns, }; static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { @@ -850,9 +870,16 @@ static const struct mlx5_flow_cmds mlx5_flow_cmd_stubs = { .update_fte = mlx5_cmd_stub_update_fte, .delete_fte = mlx5_cmd_stub_delete_fte, .update_root_ft = mlx5_cmd_stub_update_root_ft, + .packet_reformat_alloc = mlx5_cmd_stub_packet_reformat_alloc, + .packet_reformat_dealloc = mlx5_cmd_stub_packet_reformat_dealloc, + .modify_header_alloc = mlx5_cmd_stub_modify_header_alloc, + .modify_header_dealloc = mlx5_cmd_stub_modify_header_dealloc, + .set_peer = mlx5_cmd_stub_set_peer, + .create_ns = mlx5_cmd_stub_create_ns, + .destroy_ns = mlx5_cmd_stub_destroy_ns, }; -static const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void) +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void) { return &mlx5_flow_cmds; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h index e340f9af2f5a..d62de642eca9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_cmd.h @@ -75,24 +75,45 @@ struct mlx5_flow_cmds { struct mlx5_flow_table *ft, u32 underlay_qpn, bool disconnect); + + int (*packet_reformat_alloc)(struct mlx5_flow_root_namespace *ns, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat); + + void (*packet_reformat_dealloc)(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat); + + int (*modify_header_alloc)(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr); + + void (*modify_header_dealloc)(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr); + + int (*set_peer)(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns); + + int (*create_ns)(struct mlx5_flow_root_namespace *ns); + int (*destroy_ns)(struct mlx5_flow_root_namespace *ns); }; int mlx5_cmd_fc_alloc(struct mlx5_core_dev *dev, u32 *id); +int mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask, + u32 *id); int mlx5_cmd_fc_free(struct mlx5_core_dev *dev, u32 id); int mlx5_cmd_fc_query(struct mlx5_core_dev *dev, u32 id, u64 *packets, u64 *bytes); -struct mlx5_cmd_fc_bulk; - -struct mlx5_cmd_fc_bulk * -mlx5_cmd_fc_bulk_alloc(struct mlx5_core_dev *dev, u32 id, int num); -void mlx5_cmd_fc_bulk_free(struct mlx5_cmd_fc_bulk *b); -int -mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, struct mlx5_cmd_fc_bulk *b); -void mlx5_cmd_fc_bulk_get(struct mlx5_core_dev *dev, - struct mlx5_cmd_fc_bulk *b, u32 id, - u64 *packets, u64 *bytes); +int mlx5_cmd_fc_get_bulk_query_out_len(int bulk_len); +int mlx5_cmd_fc_bulk_query(struct mlx5_core_dev *dev, u32 base_id, int bulk_len, + u32 *out); const struct mlx5_flow_cmds *mlx5_fs_cmd_get_default(enum fs_flow_table_type type); +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void); #endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 3e99799bdb40..3bbb49354829 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -60,7 +60,8 @@ ADD_PRIO(num_prios_val, 0, num_levels_val, {},\ __VA_ARGS__)\ -#define ADD_NS(...) {.type = FS_TYPE_NAMESPACE,\ +#define ADD_NS(def_miss_act, ...) {.type = FS_TYPE_NAMESPACE, \ + .def_miss_action = def_miss_act,\ .children = (struct init_tree_node[]) {__VA_ARGS__},\ .ar_size = INIT_TREE_NODE_ARRAY_SIZE(__VA_ARGS__) \ } @@ -131,33 +132,41 @@ static struct init_tree_node { int num_leaf_prios; int prio; int num_levels; + enum mlx5_flow_table_miss_action def_miss_action; } root_fs = { .type = FS_TYPE_NAMESPACE, .ar_size = 7, - .children = (struct init_tree_node[]) { - ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, - FS_CHAINING_CAPS, - ADD_NS(ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS, - BY_PASS_PRIO_NUM_LEVELS))), - ADD_PRIO(0, LAG_MIN_LEVEL, 0, - FS_CHAINING_CAPS, - ADD_NS(ADD_MULTIPLE_PRIO(LAG_NUM_PRIOS, - LAG_PRIO_NUM_LEVELS))), - ADD_PRIO(0, OFFLOADS_MIN_LEVEL, 0, {}, - ADD_NS(ADD_MULTIPLE_PRIO(OFFLOADS_NUM_PRIOS, OFFLOADS_MAX_FT))), - ADD_PRIO(0, ETHTOOL_MIN_LEVEL, 0, - FS_CHAINING_CAPS, - ADD_NS(ADD_MULTIPLE_PRIO(ETHTOOL_NUM_PRIOS, - ETHTOOL_PRIO_NUM_LEVELS))), - ADD_PRIO(0, KERNEL_MIN_LEVEL, 0, {}, - ADD_NS(ADD_MULTIPLE_PRIO(KERNEL_NIC_TC_NUM_PRIOS, KERNEL_NIC_TC_NUM_LEVELS), - ADD_MULTIPLE_PRIO(KERNEL_NIC_NUM_PRIOS, - KERNEL_NIC_PRIO_NUM_LEVELS))), - ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, - FS_CHAINING_CAPS, - ADD_NS(ADD_MULTIPLE_PRIO(LEFTOVERS_NUM_PRIOS, LEFTOVERS_NUM_LEVELS))), - ADD_PRIO(0, ANCHOR_MIN_LEVEL, 0, {}, - ADD_NS(ADD_MULTIPLE_PRIO(ANCHOR_NUM_PRIOS, ANCHOR_NUM_LEVELS))), + .children = (struct init_tree_node[]){ + ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS, + BY_PASS_PRIO_NUM_LEVELS))), + ADD_PRIO(0, LAG_MIN_LEVEL, 0, FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(LAG_NUM_PRIOS, + LAG_PRIO_NUM_LEVELS))), + ADD_PRIO(0, OFFLOADS_MIN_LEVEL, 0, {}, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(OFFLOADS_NUM_PRIOS, + OFFLOADS_MAX_FT))), + ADD_PRIO(0, ETHTOOL_MIN_LEVEL, 0, FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(ETHTOOL_NUM_PRIOS, + ETHTOOL_PRIO_NUM_LEVELS))), + ADD_PRIO(0, KERNEL_MIN_LEVEL, 0, {}, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(KERNEL_NIC_TC_NUM_PRIOS, + KERNEL_NIC_TC_NUM_LEVELS), + ADD_MULTIPLE_PRIO(KERNEL_NIC_NUM_PRIOS, + KERNEL_NIC_PRIO_NUM_LEVELS))), + ADD_PRIO(0, BY_PASS_MIN_LEVEL, 0, FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(LEFTOVERS_NUM_PRIOS, + LEFTOVERS_NUM_LEVELS))), + ADD_PRIO(0, ANCHOR_MIN_LEVEL, 0, {}, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(ANCHOR_NUM_PRIOS, + ANCHOR_NUM_LEVELS))), } }; @@ -167,8 +176,29 @@ static struct init_tree_node egress_root_fs = { .children = (struct init_tree_node[]) { ADD_PRIO(0, MLX5_BY_PASS_NUM_PRIOS, 0, FS_CHAINING_CAPS_EGRESS, - ADD_NS(ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_PRIOS, + BY_PASS_PRIO_NUM_LEVELS))), + } +}; + +#define RDMA_RX_BYPASS_PRIO 0 +#define RDMA_RX_KERNEL_PRIO 1 +static struct init_tree_node rdma_rx_root_fs = { + .type = FS_TYPE_NAMESPACE, + .ar_size = 2, + .children = (struct init_tree_node[]) { + [RDMA_RX_BYPASS_PRIO] = + ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_DEF, + ADD_MULTIPLE_PRIO(MLX5_BY_PASS_NUM_REGULAR_PRIOS, BY_PASS_PRIO_NUM_LEVELS))), + [RDMA_RX_KERNEL_PRIO] = + ADD_PRIO(0, MLX5_BY_PASS_NUM_REGULAR_PRIOS + 1, 0, + FS_CHAINING_CAPS, + ADD_NS(MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN, + ADD_MULTIPLE_PRIO(1, 1))), } }; @@ -1014,6 +1044,7 @@ static struct mlx5_flow_table *__mlx5_create_flow_table(struct mlx5_flow_namespa tree_init_node(&ft->node, del_hw_flow_table, del_sw_flow_table); log_table_sz = ft->max_fte ? ilog2(ft->max_fte) : 0; next_ft = find_next_chained_ft(fs_prio); + ft->def_miss_action = ns->def_miss_action; err = root->cmds->create_flow_table(root, ft, log_table_sz, next_ft); if (err) goto free_ft; @@ -1384,7 +1415,8 @@ static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_VHCA_ID) ? (d1->vport.vhca_id == d2->vport.vhca_id) : true) && ((d1->vport.flags & MLX5_FLOW_DEST_VPORT_REFORMAT_ID) ? - (d1->vport.reformat_id == d2->vport.reformat_id) : true)) || + (d1->vport.pkt_reformat->id == + d2->vport.pkt_reformat->id) : true)) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE && d1->ft == d2->ft) || (d1->type == MLX5_FLOW_DESTINATION_TYPE_TIR && @@ -2056,16 +2088,18 @@ struct mlx5_flow_namespace *mlx5_get_flow_namespace(struct mlx5_core_dev *dev, if (steering->sniffer_tx_root_ns) return &steering->sniffer_tx_root_ns->ns; return NULL; - case MLX5_FLOW_NAMESPACE_RDMA_RX: - if (steering->rdma_rx_root_ns) - return &steering->rdma_rx_root_ns->ns; - return NULL; default: break; } if (type == MLX5_FLOW_NAMESPACE_EGRESS) { root_ns = steering->egress_root_ns; + } else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX) { + root_ns = steering->rdma_rx_root_ns; + prio = RDMA_RX_BYPASS_PRIO; + } else if (type == MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL) { + root_ns = steering->rdma_rx_root_ns; + prio = RDMA_RX_KERNEL_PRIO; } else { /* Must be NIC RX */ root_ns = steering->root_ns; prio = type; @@ -2155,7 +2189,8 @@ static struct mlx5_flow_namespace *fs_init_namespace(struct mlx5_flow_namespace return ns; } -static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) +static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio, + int def_miss_act) { struct mlx5_flow_namespace *ns; @@ -2164,6 +2199,7 @@ static struct mlx5_flow_namespace *fs_create_namespace(struct fs_prio *prio) return ERR_PTR(-ENOMEM); fs_init_namespace(ns); + ns->def_miss_action = def_miss_act; tree_init_node(&ns->node, NULL, del_sw_ns); tree_add_node(&ns->node, &prio->node); list_add_tail(&ns->node.list, &prio->node.children); @@ -2230,7 +2266,7 @@ static int init_root_tree_recursive(struct mlx5_flow_steering *steering, base = &fs_prio->node; } else if (init_node->type == FS_TYPE_NAMESPACE) { fs_get_obj(fs_prio, fs_parent_node); - fs_ns = fs_create_namespace(fs_prio); + fs_ns = fs_create_namespace(fs_prio, init_node->def_miss_action); if (IS_ERR(fs_ns)) return PTR_ERR(fs_ns); base = &fs_ns->node; @@ -2494,18 +2530,25 @@ static int init_sniffer_rx_root_ns(struct mlx5_flow_steering *steering) static int init_rdma_rx_root_ns(struct mlx5_flow_steering *steering) { - struct fs_prio *prio; + int err; steering->rdma_rx_root_ns = create_root_ns(steering, FS_FT_RDMA_RX); if (!steering->rdma_rx_root_ns) return -ENOMEM; - steering->rdma_rx_root_ns->def_miss_action = - MLX5_FLOW_TABLE_MISS_ACTION_SWITCH_DOMAIN; + err = init_root_tree(steering, &rdma_rx_root_fs, + &steering->rdma_rx_root_ns->ns.node); + if (err) + goto out_err; - /* Create single prio */ - prio = fs_create_prio(&steering->rdma_rx_root_ns->ns, 0, 1); - return PTR_ERR_OR_ZERO(prio); + set_prio_attrs(steering->rdma_rx_root_ns); + + return 0; + +out_err: + cleanup_root_ns(steering->rdma_rx_root_ns); + steering->rdma_rx_root_ns = NULL; + return err; } static int init_fdb_root_ns(struct mlx5_flow_steering *steering) { @@ -2543,7 +2586,7 @@ static int init_fdb_root_ns(struct mlx5_flow_steering *steering) } for (chain = 0; chain <= FDB_MAX_CHAIN; chain++) { - ns = fs_create_namespace(maj_prio); + ns = fs_create_namespace(maj_prio, MLX5_FLOW_TABLE_MISS_ACTION_DEF); if (IS_ERR(ns)) { err = PTR_ERR(ns); goto out_err; @@ -2846,3 +2889,160 @@ out: return err; } EXPORT_SYMBOL(mlx5_fs_remove_rx_underlay_qpn); + +static struct mlx5_flow_root_namespace +*get_root_namespace(struct mlx5_core_dev *dev, enum mlx5_flow_namespace_type ns_type) +{ + struct mlx5_flow_namespace *ns; + + if (ns_type == MLX5_FLOW_NAMESPACE_ESW_EGRESS || + ns_type == MLX5_FLOW_NAMESPACE_ESW_INGRESS) + ns = mlx5_get_flow_vport_acl_namespace(dev, ns_type, 0); + else + ns = mlx5_get_flow_namespace(dev, ns_type); + if (!ns) + return NULL; + + return find_root(&ns->node); +} + +struct mlx5_modify_hdr *mlx5_modify_header_alloc(struct mlx5_core_dev *dev, + u8 ns_type, u8 num_actions, + void *modify_actions) +{ + struct mlx5_flow_root_namespace *root; + struct mlx5_modify_hdr *modify_hdr; + int err; + + root = get_root_namespace(dev, ns_type); + if (!root) + return ERR_PTR(-EOPNOTSUPP); + + modify_hdr = kzalloc(sizeof(*modify_hdr), GFP_KERNEL); + if (!modify_hdr) + return ERR_PTR(-ENOMEM); + + modify_hdr->ns_type = ns_type; + err = root->cmds->modify_header_alloc(root, ns_type, num_actions, + modify_actions, modify_hdr); + if (err) { + kfree(modify_hdr); + return ERR_PTR(err); + } + + return modify_hdr; +} +EXPORT_SYMBOL(mlx5_modify_header_alloc); + +void mlx5_modify_header_dealloc(struct mlx5_core_dev *dev, + struct mlx5_modify_hdr *modify_hdr) +{ + struct mlx5_flow_root_namespace *root; + + root = get_root_namespace(dev, modify_hdr->ns_type); + if (WARN_ON(!root)) + return; + root->cmds->modify_header_dealloc(root, modify_hdr); + kfree(modify_hdr); +} +EXPORT_SYMBOL(mlx5_modify_header_dealloc); + +struct mlx5_pkt_reformat *mlx5_packet_reformat_alloc(struct mlx5_core_dev *dev, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type ns_type) +{ + struct mlx5_pkt_reformat *pkt_reformat; + struct mlx5_flow_root_namespace *root; + int err; + + root = get_root_namespace(dev, ns_type); + if (!root) + return ERR_PTR(-EOPNOTSUPP); + + pkt_reformat = kzalloc(sizeof(*pkt_reformat), GFP_KERNEL); + if (!pkt_reformat) + return ERR_PTR(-ENOMEM); + + pkt_reformat->ns_type = ns_type; + pkt_reformat->reformat_type = reformat_type; + err = root->cmds->packet_reformat_alloc(root, reformat_type, size, + reformat_data, ns_type, + pkt_reformat); + if (err) { + kfree(pkt_reformat); + return ERR_PTR(err); + } + + return pkt_reformat; +} +EXPORT_SYMBOL(mlx5_packet_reformat_alloc); + +void mlx5_packet_reformat_dealloc(struct mlx5_core_dev *dev, + struct mlx5_pkt_reformat *pkt_reformat) +{ + struct mlx5_flow_root_namespace *root; + + root = get_root_namespace(dev, pkt_reformat->ns_type); + if (WARN_ON(!root)) + return; + root->cmds->packet_reformat_dealloc(root, pkt_reformat); + kfree(pkt_reformat); +} +EXPORT_SYMBOL(mlx5_packet_reformat_dealloc); + +int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns) +{ + if (peer_ns && ns->mode != peer_ns->mode) { + mlx5_core_err(ns->dev, + "Can't peer namespace of different steering mode\n"); + return -EINVAL; + } + + return ns->cmds->set_peer(ns, peer_ns); +} + +/* This function should be called only at init stage of the namespace. + * It is not safe to call this function while steering operations + * are executed in the namespace. + */ +int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, + enum mlx5_flow_steering_mode mode) +{ + struct mlx5_flow_root_namespace *root; + const struct mlx5_flow_cmds *cmds; + int err; + + root = find_root(&ns->node); + if (&root->ns != ns) + /* Can't set cmds to non root namespace */ + return -EINVAL; + + if (root->table_type != FS_FT_FDB) + return -EOPNOTSUPP; + + if (root->mode == mode) + return 0; + + if (mode == MLX5_FLOW_STEERING_MODE_SMFS) + cmds = mlx5_fs_cmd_get_dr_cmds(); + else + cmds = mlx5_fs_cmd_get_fw_cmds(); + if (!cmds) + return -EOPNOTSUPP; + + err = cmds->create_ns(root); + if (err) { + mlx5_core_err(root->dev, "Failed to create flow namespace (%d)\n", + err); + return err; + } + + root->cmds->destroy_ns(root); + root->cmds = cmds; + root->mode = mode; + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h index c1252d6be0ef..00717eba2256 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.h @@ -37,6 +37,24 @@ #include <linux/mlx5/fs.h> #include <linux/rhashtable.h> #include <linux/llist.h> +#include <steering/fs_dr.h> + +struct mlx5_modify_hdr { + enum mlx5_flow_namespace_type ns_type; + union { + struct mlx5_fs_dr_action action; + u32 id; + }; +}; + +struct mlx5_pkt_reformat { + enum mlx5_flow_namespace_type ns_type; + int reformat_type; /* from mlx5_ifc */ + union { + struct mlx5_fs_dr_action action; + u32 id; + }; +}; /* FS_TYPE_PRIO_CHAINS is a PRIO that will have namespaces only, * and those are in parallel to one another when going over them to connect @@ -80,9 +98,15 @@ enum fs_fte_status { FS_FTE_STATUS_EXISTING = 1UL << 0, }; +enum mlx5_flow_steering_mode { + MLX5_FLOW_STEERING_MODE_DMFS, + MLX5_FLOW_STEERING_MODE_SMFS +}; + struct mlx5_flow_steering { struct mlx5_core_dev *dev; - struct kmem_cache *fgs_cache; + enum mlx5_flow_steering_mode mode; + struct kmem_cache *fgs_cache; struct kmem_cache *ftes_cache; struct mlx5_flow_root_namespace *root_ns; struct mlx5_flow_root_namespace *fdb_root_ns; @@ -128,6 +152,7 @@ struct mlx5_flow_handle { /* Type of children is mlx5_flow_group */ struct mlx5_flow_table { struct fs_node node; + struct mlx5_fs_dr_table fs_dr_table; u32 id; u16 vport; unsigned int max_fte; @@ -145,6 +170,7 @@ struct mlx5_flow_table { struct list_head fwd_rules; u32 flags; struct rhltable fgs_hash; + enum mlx5_flow_table_miss_action def_miss_action; }; struct mlx5_ft_underlay_qp { @@ -167,6 +193,7 @@ struct mlx5_ft_underlay_qp { /* Type of children is mlx5_flow_rule */ struct fs_fte { struct fs_node node; + struct mlx5_fs_dr_rule fs_dr_rule; u32 val[MLX5_ST_SZ_DW_MATCH_PARAM]; u32 dests_size; u32 index; @@ -191,6 +218,7 @@ struct fs_prio { struct mlx5_flow_namespace { /* parent == NULL => root ns */ struct fs_node node; + enum mlx5_flow_table_miss_action def_miss_action; }; struct mlx5_flow_group_mask { @@ -201,6 +229,7 @@ struct mlx5_flow_group_mask { /* Type of children is fs_fte */ struct mlx5_flow_group { struct fs_node node; + struct mlx5_fs_dr_matcher fs_dr_matcher; struct mlx5_flow_group_mask mask; u32 start_index; u32 max_ftes; @@ -212,6 +241,8 @@ struct mlx5_flow_group { struct mlx5_flow_root_namespace { struct mlx5_flow_namespace ns; + enum mlx5_flow_steering_mode mode; + struct mlx5_fs_dr_domain fs_dr_domain; enum fs_flow_table_type table_type; struct mlx5_core_dev *dev; struct mlx5_flow_table *root_ft; @@ -219,7 +250,6 @@ struct mlx5_flow_root_namespace { struct mutex chain_lock; struct list_head underlay_qpns; const struct mlx5_flow_cmds *cmds; - enum mlx5_flow_table_miss_action def_miss_action; }; int mlx5_init_fc_stats(struct mlx5_core_dev *dev); @@ -230,6 +260,14 @@ void mlx5_fc_queue_stats_work(struct mlx5_core_dev *dev, void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev, unsigned long interval); +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_fw_cmds(void); + +int mlx5_flow_namespace_set_peer(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns); + +int mlx5_flow_namespace_set_mode(struct mlx5_flow_namespace *ns, + enum mlx5_flow_steering_mode mode); + int mlx5_init_fs(struct mlx5_core_dev *dev); void mlx5_cleanup_fs(struct mlx5_core_dev *dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c index 1834d9f3aa1c..ab69effb056d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_counters.c @@ -40,6 +40,8 @@ #define MLX5_FC_STATS_PERIOD msecs_to_jiffies(1000) /* Max number of counters to query in bulk read is 32K */ #define MLX5_SW_MAX_COUNTERS_BULK BIT(15) +#define MLX5_FC_POOL_MAX_THRESHOLD BIT(18) +#define MLX5_FC_POOL_USED_BUFF_RATIO 10 struct mlx5_fc_cache { u64 packets; @@ -58,12 +60,18 @@ struct mlx5_fc { u64 lastpackets; u64 lastbytes; + struct mlx5_fc_bulk *bulk; u32 id; bool aging; struct mlx5_fc_cache cache ____cacheline_aligned_in_smp; }; +static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev); +static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool); +static struct mlx5_fc *mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool); +static void mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc); + /* locking scheme: * * It is the responsibility of the user to prevent concurrent calls or bad @@ -75,7 +83,7 @@ struct mlx5_fc { * access to counter list: * - create (user context) * - mlx5_fc_create() only adds to an addlist to be used by - * mlx5_fc_stats_query_work(). addlist is a lockless single linked list + * mlx5_fc_stats_work(). addlist is a lockless single linked list * that doesn't require any additional synchronization when adding single * node. * - spawn thread to do the actual destroy @@ -136,81 +144,87 @@ static void mlx5_fc_stats_remove(struct mlx5_core_dev *dev, spin_unlock(&fc_stats->counters_idr_lock); } -/* The function returns the last counter that was queried so the caller - * function can continue calling it till all counters are queried. - */ -static struct mlx5_fc *mlx5_fc_stats_query(struct mlx5_core_dev *dev, - struct mlx5_fc *first, - u32 last_id) +static int get_max_bulk_query_len(struct mlx5_core_dev *dev) { - struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; - struct mlx5_fc *counter = NULL; - struct mlx5_cmd_fc_bulk *b; - bool more = false; - u32 afirst_id; - int num; - int err; + return min_t(int, MLX5_SW_MAX_COUNTERS_BULK, + (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); +} - int max_bulk = min_t(int, MLX5_SW_MAX_COUNTERS_BULK, - (1 << MLX5_CAP_GEN(dev, log_max_flow_counter_bulk))); +static void update_counter_cache(int index, u32 *bulk_raw_data, + struct mlx5_fc_cache *cache) +{ + void *stats = MLX5_ADDR_OF(query_flow_counter_out, bulk_raw_data, + flow_statistics[index]); + u64 packets = MLX5_GET64(traffic_counter, stats, packets); + u64 bytes = MLX5_GET64(traffic_counter, stats, octets); - /* first id must be aligned to 4 when using bulk query */ - afirst_id = first->id & ~0x3; + if (cache->packets == packets) + return; - /* number of counters to query inc. the last counter */ - num = ALIGN(last_id - afirst_id + 1, 4); - if (num > max_bulk) { - num = max_bulk; - last_id = afirst_id + num - 1; - } + cache->packets = packets; + cache->bytes = bytes; + cache->lastuse = jiffies; +} - b = mlx5_cmd_fc_bulk_alloc(dev, afirst_id, num); - if (!b) { - mlx5_core_err(dev, "Error allocating resources for bulk query\n"); - return NULL; - } +static void mlx5_fc_stats_query_counter_range(struct mlx5_core_dev *dev, + struct mlx5_fc *first, + u32 last_id) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + bool query_more_counters = (first->id <= last_id); + int max_bulk_len = get_max_bulk_query_len(dev); + u32 *data = fc_stats->bulk_query_out; + struct mlx5_fc *counter = first; + u32 bulk_base_id; + int bulk_len; + int err; - err = mlx5_cmd_fc_bulk_query(dev, b); - if (err) { - mlx5_core_err(dev, "Error doing bulk query: %d\n", err); - goto out; - } + while (query_more_counters) { + /* first id must be aligned to 4 when using bulk query */ + bulk_base_id = counter->id & ~0x3; - counter = first; - list_for_each_entry_from(counter, &fc_stats->counters, list) { - struct mlx5_fc_cache *c = &counter->cache; - u64 packets; - u64 bytes; + /* number of counters to query inc. the last counter */ + bulk_len = min_t(int, max_bulk_len, + ALIGN(last_id - bulk_base_id + 1, 4)); - if (counter->id > last_id) { - more = true; - break; + err = mlx5_cmd_fc_bulk_query(dev, bulk_base_id, bulk_len, + data); + if (err) { + mlx5_core_err(dev, "Error doing bulk query: %d\n", err); + return; } + query_more_counters = false; - mlx5_cmd_fc_bulk_get(dev, b, - counter->id, &packets, &bytes); + list_for_each_entry_from(counter, &fc_stats->counters, list) { + int counter_index = counter->id - bulk_base_id; + struct mlx5_fc_cache *cache = &counter->cache; - if (c->packets == packets) - continue; + if (counter->id >= bulk_base_id + bulk_len) { + query_more_counters = true; + break; + } - c->packets = packets; - c->bytes = bytes; - c->lastuse = jiffies; + update_counter_cache(counter_index, data, cache); + } } - -out: - mlx5_cmd_fc_bulk_free(b); - - return more ? counter : NULL; } -static void mlx5_free_fc(struct mlx5_core_dev *dev, - struct mlx5_fc *counter) +static void mlx5_fc_free(struct mlx5_core_dev *dev, struct mlx5_fc *counter) { mlx5_cmd_fc_free(dev, counter->id); kfree(counter); } +static void mlx5_fc_release(struct mlx5_core_dev *dev, struct mlx5_fc *counter) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + + if (counter->bulk) + mlx5_fc_pool_release_counter(&fc_stats->fc_pool, counter); + else + mlx5_fc_free(dev, counter); +} + static void mlx5_fc_stats_work(struct work_struct *work) { struct mlx5_core_dev *dev = container_of(work, struct mlx5_core_dev, @@ -234,7 +248,7 @@ static void mlx5_fc_stats_work(struct work_struct *work) llist_for_each_entry_safe(counter, tmp, dellist, dellist) { mlx5_fc_stats_remove(dev, counter); - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } if (time_before(now, fc_stats->next_query) || @@ -244,32 +258,62 @@ static void mlx5_fc_stats_work(struct work_struct *work) counter = list_first_entry(&fc_stats->counters, struct mlx5_fc, list); - while (counter) - counter = mlx5_fc_stats_query(dev, counter, last->id); + if (counter) + mlx5_fc_stats_query_counter_range(dev, counter, last->id); fc_stats->next_query = now + fc_stats->sampling_interval; } -struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +static struct mlx5_fc *mlx5_fc_single_alloc(struct mlx5_core_dev *dev) { - struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; struct mlx5_fc *counter; int err; counter = kzalloc(sizeof(*counter), GFP_KERNEL); if (!counter) return ERR_PTR(-ENOMEM); - INIT_LIST_HEAD(&counter->list); err = mlx5_cmd_fc_alloc(dev, &counter->id); - if (err) - goto err_out; + if (err) { + kfree(counter); + return ERR_PTR(err); + } + + return counter; +} + +static struct mlx5_fc *mlx5_fc_acquire(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + struct mlx5_fc *counter; + + if (aging && MLX5_CAP_GEN(dev, flow_counter_bulk_alloc) != 0) { + counter = mlx5_fc_pool_acquire_counter(&fc_stats->fc_pool); + if (!IS_ERR(counter)) + return counter; + } + + return mlx5_fc_single_alloc(dev); +} + +struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) +{ + struct mlx5_fc *counter = mlx5_fc_acquire(dev, aging); + struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + int err; + + if (IS_ERR(counter)) + return counter; + + INIT_LIST_HEAD(&counter->list); + counter->aging = aging; if (aging) { u32 id = counter->id; counter->cache.lastuse = jiffies; - counter->aging = true; + counter->lastbytes = counter->cache.bytes; + counter->lastpackets = counter->cache.packets; idr_preload(GFP_KERNEL); spin_lock(&fc_stats->counters_idr_lock); @@ -290,10 +334,7 @@ struct mlx5_fc *mlx5_fc_create(struct mlx5_core_dev *dev, bool aging) return counter; err_out_alloc: - mlx5_cmd_fc_free(dev, counter->id); -err_out: - kfree(counter); - + mlx5_fc_release(dev, counter); return ERR_PTR(err); } EXPORT_SYMBOL(mlx5_fc_create); @@ -317,13 +358,15 @@ void mlx5_fc_destroy(struct mlx5_core_dev *dev, struct mlx5_fc *counter) return; } - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); } EXPORT_SYMBOL(mlx5_fc_destroy); int mlx5_init_fc_stats(struct mlx5_core_dev *dev) { struct mlx5_fc_stats *fc_stats = &dev->priv.fc_stats; + int max_bulk_len; + int max_out_len; spin_lock_init(&fc_stats->counters_idr_lock); idr_init(&fc_stats->counters_idr); @@ -331,14 +374,25 @@ int mlx5_init_fc_stats(struct mlx5_core_dev *dev) init_llist_head(&fc_stats->addlist); init_llist_head(&fc_stats->dellist); + max_bulk_len = get_max_bulk_query_len(dev); + max_out_len = mlx5_cmd_fc_get_bulk_query_out_len(max_bulk_len); + fc_stats->bulk_query_out = kzalloc(max_out_len, GFP_KERNEL); + if (!fc_stats->bulk_query_out) + return -ENOMEM; + fc_stats->wq = create_singlethread_workqueue("mlx5_fc"); if (!fc_stats->wq) - return -ENOMEM; + goto err_wq_create; fc_stats->sampling_interval = MLX5_FC_STATS_PERIOD; INIT_DELAYED_WORK(&fc_stats->work, mlx5_fc_stats_work); + mlx5_fc_pool_init(&fc_stats->fc_pool, dev); return 0; + +err_wq_create: + kfree(fc_stats->bulk_query_out); + return -ENOMEM; } void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) @@ -352,14 +406,16 @@ void mlx5_cleanup_fc_stats(struct mlx5_core_dev *dev) destroy_workqueue(dev->priv.fc_stats.wq); dev->priv.fc_stats.wq = NULL; - idr_destroy(&fc_stats->counters_idr); - tmplist = llist_del_all(&fc_stats->addlist); llist_for_each_entry_safe(counter, tmp, tmplist, addlist) - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); list_for_each_entry_safe(counter, tmp, &fc_stats->counters, list) - mlx5_free_fc(dev, counter); + mlx5_fc_release(dev, counter); + + mlx5_fc_pool_cleanup(&fc_stats->fc_pool); + idr_destroy(&fc_stats->counters_idr); + kfree(fc_stats->bulk_query_out); } int mlx5_fc_query(struct mlx5_core_dev *dev, struct mlx5_fc *counter, @@ -406,3 +462,243 @@ void mlx5_fc_update_sampling_interval(struct mlx5_core_dev *dev, fc_stats->sampling_interval = min_t(unsigned long, interval, fc_stats->sampling_interval); } + +/* Flow counter bluks */ + +struct mlx5_fc_bulk { + struct list_head pool_list; + u32 base_id; + int bulk_len; + unsigned long *bitmask; + struct mlx5_fc fcs[0]; +}; + +static void mlx5_fc_init(struct mlx5_fc *counter, struct mlx5_fc_bulk *bulk, + u32 id) +{ + counter->bulk = bulk; + counter->id = id; +} + +static int mlx5_fc_bulk_get_free_fcs_amount(struct mlx5_fc_bulk *bulk) +{ + return bitmap_weight(bulk->bitmask, bulk->bulk_len); +} + +static struct mlx5_fc_bulk *mlx5_fc_bulk_create(struct mlx5_core_dev *dev) +{ + enum mlx5_fc_bulk_alloc_bitmask alloc_bitmask; + struct mlx5_fc_bulk *bulk; + int err = -ENOMEM; + int bulk_len; + u32 base_id; + int i; + + alloc_bitmask = MLX5_CAP_GEN(dev, flow_counter_bulk_alloc); + bulk_len = alloc_bitmask > 0 ? MLX5_FC_BULK_NUM_FCS(alloc_bitmask) : 1; + + bulk = kzalloc(sizeof(*bulk) + bulk_len * sizeof(struct mlx5_fc), + GFP_KERNEL); + if (!bulk) + goto err_alloc_bulk; + + bulk->bitmask = kcalloc(BITS_TO_LONGS(bulk_len), sizeof(unsigned long), + GFP_KERNEL); + if (!bulk->bitmask) + goto err_alloc_bitmask; + + err = mlx5_cmd_fc_bulk_alloc(dev, alloc_bitmask, &base_id); + if (err) + goto err_mlx5_cmd_bulk_alloc; + + bulk->base_id = base_id; + bulk->bulk_len = bulk_len; + for (i = 0; i < bulk_len; i++) { + mlx5_fc_init(&bulk->fcs[i], bulk, base_id + i); + set_bit(i, bulk->bitmask); + } + + return bulk; + +err_mlx5_cmd_bulk_alloc: + kfree(bulk->bitmask); +err_alloc_bitmask: + kfree(bulk); +err_alloc_bulk: + return ERR_PTR(err); +} + +static int +mlx5_fc_bulk_destroy(struct mlx5_core_dev *dev, struct mlx5_fc_bulk *bulk) +{ + if (mlx5_fc_bulk_get_free_fcs_amount(bulk) < bulk->bulk_len) { + mlx5_core_err(dev, "Freeing bulk before all counters were released\n"); + return -EBUSY; + } + + mlx5_cmd_fc_free(dev, bulk->base_id); + kfree(bulk->bitmask); + kfree(bulk); + + return 0; +} + +static struct mlx5_fc *mlx5_fc_bulk_acquire_fc(struct mlx5_fc_bulk *bulk) +{ + int free_fc_index = find_first_bit(bulk->bitmask, bulk->bulk_len); + + if (free_fc_index >= bulk->bulk_len) + return ERR_PTR(-ENOSPC); + + clear_bit(free_fc_index, bulk->bitmask); + return &bulk->fcs[free_fc_index]; +} + +static int mlx5_fc_bulk_release_fc(struct mlx5_fc_bulk *bulk, struct mlx5_fc *fc) +{ + int fc_index = fc->id - bulk->base_id; + + if (test_bit(fc_index, bulk->bitmask)) + return -EINVAL; + + set_bit(fc_index, bulk->bitmask); + return 0; +} + +/* Flow counters pool API */ + +static void mlx5_fc_pool_init(struct mlx5_fc_pool *fc_pool, struct mlx5_core_dev *dev) +{ + fc_pool->dev = dev; + mutex_init(&fc_pool->pool_lock); + INIT_LIST_HEAD(&fc_pool->fully_used); + INIT_LIST_HEAD(&fc_pool->partially_used); + INIT_LIST_HEAD(&fc_pool->unused); + fc_pool->available_fcs = 0; + fc_pool->used_fcs = 0; + fc_pool->threshold = 0; +} + +static void mlx5_fc_pool_cleanup(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *bulk; + struct mlx5_fc_bulk *tmp; + + list_for_each_entry_safe(bulk, tmp, &fc_pool->fully_used, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &fc_pool->partially_used, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); + list_for_each_entry_safe(bulk, tmp, &fc_pool->unused, pool_list) + mlx5_fc_bulk_destroy(dev, bulk); +} + +static void mlx5_fc_pool_update_threshold(struct mlx5_fc_pool *fc_pool) +{ + fc_pool->threshold = min_t(int, MLX5_FC_POOL_MAX_THRESHOLD, + fc_pool->used_fcs / MLX5_FC_POOL_USED_BUFF_RATIO); +} + +static struct mlx5_fc_bulk * +mlx5_fc_pool_alloc_new_bulk(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *new_bulk; + + new_bulk = mlx5_fc_bulk_create(dev); + if (!IS_ERR(new_bulk)) + fc_pool->available_fcs += new_bulk->bulk_len; + mlx5_fc_pool_update_threshold(fc_pool); + return new_bulk; +} + +static void +mlx5_fc_pool_free_bulk(struct mlx5_fc_pool *fc_pool, struct mlx5_fc_bulk *bulk) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + + fc_pool->available_fcs -= bulk->bulk_len; + mlx5_fc_bulk_destroy(dev, bulk); + mlx5_fc_pool_update_threshold(fc_pool); +} + +static struct mlx5_fc * +mlx5_fc_pool_acquire_from_list(struct list_head *src_list, + struct list_head *next_list, + bool move_non_full_bulk) +{ + struct mlx5_fc_bulk *bulk; + struct mlx5_fc *fc; + + if (list_empty(src_list)) + return ERR_PTR(-ENODATA); + + bulk = list_first_entry(src_list, struct mlx5_fc_bulk, pool_list); + fc = mlx5_fc_bulk_acquire_fc(bulk); + if (move_non_full_bulk || mlx5_fc_bulk_get_free_fcs_amount(bulk) == 0) + list_move(&bulk->pool_list, next_list); + return fc; +} + +static struct mlx5_fc * +mlx5_fc_pool_acquire_counter(struct mlx5_fc_pool *fc_pool) +{ + struct mlx5_fc_bulk *new_bulk; + struct mlx5_fc *fc; + + mutex_lock(&fc_pool->pool_lock); + + fc = mlx5_fc_pool_acquire_from_list(&fc_pool->partially_used, + &fc_pool->fully_used, false); + if (IS_ERR(fc)) + fc = mlx5_fc_pool_acquire_from_list(&fc_pool->unused, + &fc_pool->partially_used, + true); + if (IS_ERR(fc)) { + new_bulk = mlx5_fc_pool_alloc_new_bulk(fc_pool); + if (IS_ERR(new_bulk)) { + fc = ERR_CAST(new_bulk); + goto out; + } + fc = mlx5_fc_bulk_acquire_fc(new_bulk); + list_add(&new_bulk->pool_list, &fc_pool->partially_used); + } + fc_pool->available_fcs--; + fc_pool->used_fcs++; + +out: + mutex_unlock(&fc_pool->pool_lock); + return fc; +} + +static void +mlx5_fc_pool_release_counter(struct mlx5_fc_pool *fc_pool, struct mlx5_fc *fc) +{ + struct mlx5_core_dev *dev = fc_pool->dev; + struct mlx5_fc_bulk *bulk = fc->bulk; + int bulk_free_fcs_amount; + + mutex_lock(&fc_pool->pool_lock); + + if (mlx5_fc_bulk_release_fc(bulk, fc)) { + mlx5_core_warn(dev, "Attempted to release a counter which is not acquired\n"); + goto unlock; + } + + fc_pool->available_fcs++; + fc_pool->used_fcs--; + + bulk_free_fcs_amount = mlx5_fc_bulk_get_free_fcs_amount(bulk); + if (bulk_free_fcs_amount == 1) + list_move_tail(&bulk->pool_list, &fc_pool->partially_used); + if (bulk_free_fcs_amount == bulk->bulk_len) { + list_del(&bulk->pool_list); + if (fc_pool->available_fcs > fc_pool->threshold) + mlx5_fc_pool_free_bulk(fc_pool, bulk); + else + list_add(&bulk->pool_list, &fc_pool->unused); + } + +unlock: + mutex_unlock(&fc_pool->pool_lock); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c index 1a2560e3bf7c..3ed8ab2d703d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib.c @@ -279,7 +279,7 @@ static int mlx5i_init_tx(struct mlx5e_priv *priv) return err; } - err = mlx5i_create_tis(priv->mdev, ipriv->qp.qpn, &priv->tisn[0]); + err = mlx5i_create_tis(priv->mdev, ipriv->qp.qpn, &priv->tisn[0][0]); if (err) { mlx5_core_warn(priv->mdev, "create tis failed, %d\n", err); goto err_destroy_underlay_qp; @@ -296,7 +296,7 @@ static void mlx5i_cleanup_tx(struct mlx5e_priv *priv) { struct mlx5i_priv *ipriv = priv->ppriv; - mlx5e_destroy_tis(priv->mdev, priv->tisn[0]); + mlx5e_destroy_tis(priv->mdev, priv->tisn[0][0]); mlx5i_destroy_underlay_qp(priv->mdev, &ipriv->qp); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c index c5a491e22e55..96e64187c089 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/ipoib/ipoib_vlan.c @@ -210,7 +210,7 @@ static int mlx5i_pkey_open(struct net_device *netdev) goto err_unint_underlay_qp; } - err = mlx5i_create_tis(mdev, ipriv->qp.qpn, &epriv->tisn[0]); + err = mlx5i_create_tis(mdev, ipriv->qp.qpn, &epriv->tisn[0][0]); if (err) { mlx5_core_warn(mdev, "create child tis failed, %d\n", err); goto err_remove_rx_uderlay_qp; @@ -228,7 +228,7 @@ static int mlx5i_pkey_open(struct net_device *netdev) return 0; err_clear_state_opened_flag: - mlx5e_destroy_tis(mdev, epriv->tisn[0]); + mlx5e_destroy_tis(mdev, epriv->tisn[0][0]); err_remove_rx_uderlay_qp: mlx5_fs_remove_rx_underlay_qpn(mdev, ipriv->qp.qpn); err_unint_underlay_qp: @@ -257,7 +257,7 @@ static int mlx5i_pkey_close(struct net_device *netdev) mlx5i_uninit_underlay_qp(priv); mlx5e_deactivate_priv_channels(priv); mlx5e_close_channels(&priv->channels); - mlx5e_destroy_tis(mdev, priv->tisn[0]); + mlx5e_destroy_tis(mdev, priv->tisn[0][0]); unlock: mutex_unlock(&priv->state_lock); return 0; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c index e69766393990..5d20d615663e 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lag_mp.c @@ -248,6 +248,9 @@ static int mlx5_lag_fib_event(struct notifier_block *nb, struct net_device *fib_dev; struct fib_info *fi; + if (!net_eq(info->net, &init_net)) + return NOTIFY_DONE; + if (info->family != AF_INET) return NOTIFY_DONE; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c index ea1d4d26ece0..3fc575d1c3ec 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/crypto.c @@ -2,6 +2,7 @@ // Copyright (c) 2019 Mellanox Technologies. #include "mlx5_core.h" +#include "lib/mlx5.h" int mlx5_create_encryption_key(struct mlx5_core_dev *mdev, void *key, u32 sz_bytes, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c new file mode 100644 index 000000000000..e065c2f68f5a --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/dm.c @@ -0,0 +1,223 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2019 Mellanox Technologies + +#include <linux/mlx5/driver.h> +#include <linux/mlx5/device.h> + +#include "mlx5_core.h" +#include "lib/mlx5.h" + +struct mlx5_dm { + /* protect access to icm bitmask */ + spinlock_t lock; + unsigned long *steering_sw_icm_alloc_blocks; + unsigned long *header_modify_sw_icm_alloc_blocks; +}; + +struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev) +{ + u64 header_modify_icm_blocks = 0; + u64 steering_icm_blocks = 0; + struct mlx5_dm *dm; + + if (!(MLX5_CAP_GEN_64(dev, general_obj_types) & MLX5_GENERAL_OBJ_TYPES_CAP_SW_ICM)) + return 0; + + dm = kzalloc(sizeof(*dm), GFP_KERNEL); + if (!dm) + return ERR_PTR(-ENOMEM); + + spin_lock_init(&dm->lock); + + if (MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address)) { + steering_icm_blocks = + BIT(MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); + + dm->steering_sw_icm_alloc_blocks = + kcalloc(BITS_TO_LONGS(steering_icm_blocks), + sizeof(unsigned long), GFP_KERNEL); + if (!dm->steering_sw_icm_alloc_blocks) + goto err_steering; + } + + if (MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address)) { + header_modify_icm_blocks = + BIT(MLX5_CAP_DEV_MEM(dev, log_header_modify_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); + + dm->header_modify_sw_icm_alloc_blocks = + kcalloc(BITS_TO_LONGS(header_modify_icm_blocks), + sizeof(unsigned long), GFP_KERNEL); + if (!dm->header_modify_sw_icm_alloc_blocks) + goto err_modify_hdr; + } + + return dm; + +err_modify_hdr: + kfree(dm->steering_sw_icm_alloc_blocks); + +err_steering: + kfree(dm); + + return ERR_PTR(-ENOMEM); +} + +void mlx5_dm_cleanup(struct mlx5_core_dev *dev) +{ + struct mlx5_dm *dm = dev->dm; + + if (!dev->dm) + return; + + if (dm->steering_sw_icm_alloc_blocks) { + WARN_ON(!bitmap_empty(dm->steering_sw_icm_alloc_blocks, + BIT(MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)))); + kfree(dm->steering_sw_icm_alloc_blocks); + } + + if (dm->header_modify_sw_icm_alloc_blocks) { + WARN_ON(!bitmap_empty(dm->header_modify_sw_icm_alloc_blocks, + BIT(MLX5_CAP_DEV_MEM(dev, + log_header_modify_sw_icm_size) - + MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)))); + kfree(dm->header_modify_sw_icm_alloc_blocks); + } + + kfree(dm); +} + +int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, + u64 length, u16 uid, phys_addr_t *addr, u32 *obj_id) +{ + u32 num_blocks = DIV_ROUND_UP_ULL(length, MLX5_SW_ICM_BLOCK_SIZE(dev)); + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {}; + u32 in[MLX5_ST_SZ_DW(create_sw_icm_in)] = {}; + struct mlx5_dm *dm = dev->dm; + unsigned long *block_map; + u64 icm_start_addr; + u32 log_icm_size; + u32 max_blocks; + u64 block_idx; + void *sw_icm; + int ret; + + if (!dev->dm) + return -EOPNOTSUPP; + + if (!length || (length & (length - 1)) || + length & (MLX5_SW_ICM_BLOCK_SIZE(dev) - 1)) + return -EINVAL; + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_CREATE_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM); + MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid); + + switch (type) { + case MLX5_SW_ICM_TYPE_STEERING: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address); + log_icm_size = MLX5_CAP_DEV_MEM(dev, log_steering_sw_icm_size); + block_map = dm->steering_sw_icm_alloc_blocks; + break; + case MLX5_SW_ICM_TYPE_HEADER_MODIFY: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address); + log_icm_size = MLX5_CAP_DEV_MEM(dev, + log_header_modify_sw_icm_size); + block_map = dm->header_modify_sw_icm_alloc_blocks; + break; + default: + return -EINVAL; + } + + if (!block_map) + return -EOPNOTSUPP; + + max_blocks = BIT(log_icm_size - MLX5_LOG_SW_ICM_BLOCK_SIZE(dev)); + spin_lock(&dm->lock); + block_idx = bitmap_find_next_zero_area(block_map, + max_blocks, + 0, + num_blocks, 0); + + if (block_idx < max_blocks) + bitmap_set(block_map, + block_idx, num_blocks); + + spin_unlock(&dm->lock); + + if (block_idx >= max_blocks) + return -ENOMEM; + + sw_icm = MLX5_ADDR_OF(create_sw_icm_in, in, sw_icm); + icm_start_addr += block_idx << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); + MLX5_SET64(sw_icm, sw_icm, sw_icm_start_addr, + icm_start_addr); + MLX5_SET(sw_icm, sw_icm, log_sw_icm_size, ilog2(length)); + + ret = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (ret) { + spin_lock(&dm->lock); + bitmap_clear(block_map, + block_idx, num_blocks); + spin_unlock(&dm->lock); + + return ret; + } + + *addr = icm_start_addr; + *obj_id = MLX5_GET(general_obj_out_cmd_hdr, out, obj_id); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_dm_sw_icm_alloc); + +int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type, + u64 length, u16 uid, phys_addr_t addr, u32 obj_id) +{ + u32 num_blocks = DIV_ROUND_UP_ULL(length, MLX5_SW_ICM_BLOCK_SIZE(dev)); + u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)] = {}; + u32 in[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)] = {}; + struct mlx5_dm *dm = dev->dm; + unsigned long *block_map; + u64 icm_start_addr; + u64 start_idx; + int err; + + if (!dev->dm) + return -EOPNOTSUPP; + + switch (type) { + case MLX5_SW_ICM_TYPE_STEERING: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, steering_sw_icm_start_address); + block_map = dm->steering_sw_icm_alloc_blocks; + break; + case MLX5_SW_ICM_TYPE_HEADER_MODIFY: + icm_start_addr = MLX5_CAP64_DEV_MEM(dev, header_modify_sw_icm_start_address); + block_map = dm->header_modify_sw_icm_alloc_blocks; + break; + default: + return -EINVAL; + } + + MLX5_SET(general_obj_in_cmd_hdr, in, opcode, + MLX5_CMD_OP_DESTROY_GENERAL_OBJECT); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_type, MLX5_OBJ_TYPE_SW_ICM); + MLX5_SET(general_obj_in_cmd_hdr, in, obj_id, obj_id); + MLX5_SET(general_obj_in_cmd_hdr, in, uid, uid); + + err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + start_idx = (addr - icm_start_addr) >> MLX5_LOG_SW_ICM_BLOCK_SIZE(dev); + spin_lock(&dm->lock); + bitmap_clear(block_map, + start_idx, num_blocks); + spin_unlock(&dm->lock); + + return 0; +} +EXPORT_SYMBOL_GPL(mlx5_dm_sw_icm_dealloc); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h index 3dfab91ae5f2..4be4d2d36218 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/eq.h @@ -87,7 +87,7 @@ void mlx5_eq_synchronize_cmd_irq(struct mlx5_core_dev *dev); int mlx5_debug_eq_add(struct mlx5_core_dev *dev, struct mlx5_eq *eq); void mlx5_debug_eq_remove(struct mlx5_core_dev *dev, struct mlx5_eq *eq); -int mlx5_eq_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_eq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_eq_debugfs_cleanup(struct mlx5_core_dev *dev); /* This function should only be called after mlx5_cmd_force_teardown_hca */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c new file mode 100644 index 000000000000..583dc7e2aca8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.c @@ -0,0 +1,64 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2018 Mellanox Technologies + +#include <linux/hyperv.h> +#include "mlx5_core.h" +#include "lib/hv.h" + +static int mlx5_hv_config_common(struct mlx5_core_dev *dev, void *buf, int len, + int offset, bool read) +{ + int rc = -EOPNOTSUPP; + int bytes_returned; + int block_id; + + if (offset % HV_CONFIG_BLOCK_SIZE_MAX || len != HV_CONFIG_BLOCK_SIZE_MAX) + return -EINVAL; + + block_id = offset / HV_CONFIG_BLOCK_SIZE_MAX; + + rc = read ? + hyperv_read_cfg_blk(dev->pdev, buf, + HV_CONFIG_BLOCK_SIZE_MAX, block_id, + &bytes_returned) : + hyperv_write_cfg_blk(dev->pdev, buf, + HV_CONFIG_BLOCK_SIZE_MAX, block_id); + + /* Make sure len bytes were read successfully */ + if (read && !rc && len != bytes_returned) + rc = -EIO; + + if (rc) { + mlx5_core_err(dev, "Failed to %s hv config, err = %d, len = %d, offset = %d\n", + read ? "read" : "write", rc, len, + offset); + return rc; + } + + return 0; +} + +int mlx5_hv_read_config(struct mlx5_core_dev *dev, void *buf, int len, + int offset) +{ + return mlx5_hv_config_common(dev, buf, len, offset, true); +} + +int mlx5_hv_write_config(struct mlx5_core_dev *dev, void *buf, int len, + int offset) +{ + return mlx5_hv_config_common(dev, buf, len, offset, false); +} + +int mlx5_hv_register_invalidate(struct mlx5_core_dev *dev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)) +{ + return hyperv_reg_block_invalidate(dev->pdev, context, + block_invalidate); +} + +void mlx5_hv_unregister_invalidate(struct mlx5_core_dev *dev) +{ + hyperv_reg_block_invalidate(dev->pdev, NULL, NULL); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.h new file mode 100644 index 000000000000..f9a45573f459 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __LIB_HV_H__ +#define __LIB_HV_H__ + +#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE) + +#include <linux/hyperv.h> +#include <linux/mlx5/driver.h> + +int mlx5_hv_read_config(struct mlx5_core_dev *dev, void *buf, int len, + int offset); +int mlx5_hv_write_config(struct mlx5_core_dev *dev, void *buf, int len, + int offset); +int mlx5_hv_register_invalidate(struct mlx5_core_dev *dev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)); +void mlx5_hv_unregister_invalidate(struct mlx5_core_dev *dev); +#endif + +#endif /* __LIB_HV_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c new file mode 100644 index 000000000000..4047629a876b --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.c @@ -0,0 +1,371 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +// Copyright (c) 2018 Mellanox Technologies + +#include <linux/hyperv.h> +#include "mlx5_core.h" +#include "lib/hv.h" +#include "lib/hv_vhca.h" + +struct mlx5_hv_vhca { + struct mlx5_core_dev *dev; + struct workqueue_struct *work_queue; + struct mlx5_hv_vhca_agent *agents[MLX5_HV_VHCA_AGENT_MAX]; + struct mutex agents_lock; /* Protect agents array */ +}; + +struct mlx5_hv_vhca_work { + struct work_struct invalidate_work; + struct mlx5_hv_vhca *hv_vhca; + u64 block_mask; +}; + +struct mlx5_hv_vhca_data_block { + u16 sequence; + u16 offset; + u8 reserved[4]; + u64 data[15]; +}; + +struct mlx5_hv_vhca_agent { + enum mlx5_hv_vhca_agent_type type; + struct mlx5_hv_vhca *hv_vhca; + void *priv; + u16 seq; + void (*control)(struct mlx5_hv_vhca_agent *agent, + struct mlx5_hv_vhca_control_block *block); + void (*invalidate)(struct mlx5_hv_vhca_agent *agent, + u64 block_mask); + void (*cleanup)(struct mlx5_hv_vhca_agent *agent); +}; + +struct mlx5_hv_vhca *mlx5_hv_vhca_create(struct mlx5_core_dev *dev) +{ + struct mlx5_hv_vhca *hv_vhca = NULL; + + hv_vhca = kzalloc(sizeof(*hv_vhca), GFP_KERNEL); + if (!hv_vhca) + return ERR_PTR(-ENOMEM); + + hv_vhca->work_queue = create_singlethread_workqueue("mlx5_hv_vhca"); + if (!hv_vhca->work_queue) { + kfree(hv_vhca); + return ERR_PTR(-ENOMEM); + } + + hv_vhca->dev = dev; + mutex_init(&hv_vhca->agents_lock); + + return hv_vhca; +} + +void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca) +{ + if (IS_ERR_OR_NULL(hv_vhca)) + return; + + destroy_workqueue(hv_vhca->work_queue); + kfree(hv_vhca); +} + +static void mlx5_hv_vhca_invalidate_work(struct work_struct *work) +{ + struct mlx5_hv_vhca_work *hwork; + struct mlx5_hv_vhca *hv_vhca; + int i; + + hwork = container_of(work, struct mlx5_hv_vhca_work, invalidate_work); + hv_vhca = hwork->hv_vhca; + + mutex_lock(&hv_vhca->agents_lock); + for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) { + struct mlx5_hv_vhca_agent *agent = hv_vhca->agents[i]; + + if (!agent || !agent->invalidate) + continue; + + if (!(BIT(agent->type) & hwork->block_mask)) + continue; + + agent->invalidate(agent, hwork->block_mask); + } + mutex_unlock(&hv_vhca->agents_lock); + + kfree(hwork); +} + +void mlx5_hv_vhca_invalidate(void *context, u64 block_mask) +{ + struct mlx5_hv_vhca *hv_vhca = (struct mlx5_hv_vhca *)context; + struct mlx5_hv_vhca_work *work; + + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return; + + INIT_WORK(&work->invalidate_work, mlx5_hv_vhca_invalidate_work); + work->hv_vhca = hv_vhca; + work->block_mask = block_mask; + + queue_work(hv_vhca->work_queue, &work->invalidate_work); +} + +#define AGENT_MASK(type) (type ? BIT(type - 1) : 0 /* control */) + +static void mlx5_hv_vhca_agents_control(struct mlx5_hv_vhca *hv_vhca, + struct mlx5_hv_vhca_control_block *block) +{ + int i; + + for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) { + struct mlx5_hv_vhca_agent *agent = hv_vhca->agents[i]; + + if (!agent || !agent->control) + continue; + + if (!(AGENT_MASK(agent->type) & block->control)) + continue; + + agent->control(agent, block); + } +} + +static void mlx5_hv_vhca_capabilities(struct mlx5_hv_vhca *hv_vhca, + u32 *capabilities) +{ + int i; + + for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) { + struct mlx5_hv_vhca_agent *agent = hv_vhca->agents[i]; + + if (agent) + *capabilities |= AGENT_MASK(agent->type); + } +} + +static void +mlx5_hv_vhca_control_agent_invalidate(struct mlx5_hv_vhca_agent *agent, + u64 block_mask) +{ + struct mlx5_hv_vhca *hv_vhca = agent->hv_vhca; + struct mlx5_core_dev *dev = hv_vhca->dev; + struct mlx5_hv_vhca_control_block *block; + u32 capabilities = 0; + int err; + + block = kzalloc(sizeof(*block), GFP_KERNEL); + if (!block) + return; + + err = mlx5_hv_read_config(dev, block, sizeof(*block), 0); + if (err) + goto free_block; + + mlx5_hv_vhca_capabilities(hv_vhca, &capabilities); + + /* In case no capabilities, send empty block in return */ + if (!capabilities) { + memset(block, 0, sizeof(*block)); + goto write; + } + + if (block->capabilities != capabilities) + block->capabilities = capabilities; + + if (block->control & ~capabilities) + goto free_block; + + mlx5_hv_vhca_agents_control(hv_vhca, block); + block->command_ack = block->command; + +write: + mlx5_hv_write_config(dev, block, sizeof(*block), 0); + +free_block: + kfree(block); +} + +static struct mlx5_hv_vhca_agent * +mlx5_hv_vhca_control_agent_create(struct mlx5_hv_vhca *hv_vhca) +{ + return mlx5_hv_vhca_agent_create(hv_vhca, MLX5_HV_VHCA_AGENT_CONTROL, + NULL, + mlx5_hv_vhca_control_agent_invalidate, + NULL, NULL); +} + +static void mlx5_hv_vhca_control_agent_destroy(struct mlx5_hv_vhca_agent *agent) +{ + mlx5_hv_vhca_agent_destroy(agent); +} + +int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca) +{ + struct mlx5_hv_vhca_agent *agent; + int err; + + if (IS_ERR_OR_NULL(hv_vhca)) + return IS_ERR_OR_NULL(hv_vhca); + + err = mlx5_hv_register_invalidate(hv_vhca->dev, hv_vhca, + mlx5_hv_vhca_invalidate); + if (err) + return err; + + agent = mlx5_hv_vhca_control_agent_create(hv_vhca); + if (IS_ERR_OR_NULL(agent)) { + mlx5_hv_unregister_invalidate(hv_vhca->dev); + return IS_ERR_OR_NULL(agent); + } + + hv_vhca->agents[MLX5_HV_VHCA_AGENT_CONTROL] = agent; + + return 0; +} + +void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca) +{ + struct mlx5_hv_vhca_agent *agent; + int i; + + if (IS_ERR_OR_NULL(hv_vhca)) + return; + + agent = hv_vhca->agents[MLX5_HV_VHCA_AGENT_CONTROL]; + if (agent) + mlx5_hv_vhca_control_agent_destroy(agent); + + mutex_lock(&hv_vhca->agents_lock); + for (i = 0; i < MLX5_HV_VHCA_AGENT_MAX; i++) + WARN_ON(hv_vhca->agents[i]); + + mutex_unlock(&hv_vhca->agents_lock); + + mlx5_hv_unregister_invalidate(hv_vhca->dev); +} + +static void mlx5_hv_vhca_agents_update(struct mlx5_hv_vhca *hv_vhca) +{ + mlx5_hv_vhca_invalidate(hv_vhca, BIT(MLX5_HV_VHCA_AGENT_CONTROL)); +} + +struct mlx5_hv_vhca_agent * +mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, + enum mlx5_hv_vhca_agent_type type, + void (*control)(struct mlx5_hv_vhca_agent*, + struct mlx5_hv_vhca_control_block *block), + void (*invalidate)(struct mlx5_hv_vhca_agent*, + u64 block_mask), + void (*cleaup)(struct mlx5_hv_vhca_agent *agent), + void *priv) +{ + struct mlx5_hv_vhca_agent *agent; + + if (IS_ERR_OR_NULL(hv_vhca)) + return ERR_PTR(-ENOMEM); + + if (type >= MLX5_HV_VHCA_AGENT_MAX) + return ERR_PTR(-EINVAL); + + mutex_lock(&hv_vhca->agents_lock); + if (hv_vhca->agents[type]) { + mutex_unlock(&hv_vhca->agents_lock); + return ERR_PTR(-EINVAL); + } + mutex_unlock(&hv_vhca->agents_lock); + + agent = kzalloc(sizeof(*agent), GFP_KERNEL); + if (!agent) + return ERR_PTR(-ENOMEM); + + agent->type = type; + agent->hv_vhca = hv_vhca; + agent->priv = priv; + agent->control = control; + agent->invalidate = invalidate; + agent->cleanup = cleaup; + + mutex_lock(&hv_vhca->agents_lock); + hv_vhca->agents[type] = agent; + mutex_unlock(&hv_vhca->agents_lock); + + mlx5_hv_vhca_agents_update(hv_vhca); + + return agent; +} + +void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent) +{ + struct mlx5_hv_vhca *hv_vhca = agent->hv_vhca; + + mutex_lock(&hv_vhca->agents_lock); + + if (WARN_ON(agent != hv_vhca->agents[agent->type])) { + mutex_unlock(&hv_vhca->agents_lock); + return; + } + + hv_vhca->agents[agent->type] = NULL; + mutex_unlock(&hv_vhca->agents_lock); + + if (agent->cleanup) + agent->cleanup(agent); + + kfree(agent); + + mlx5_hv_vhca_agents_update(hv_vhca); +} + +static int mlx5_hv_vhca_data_block_prepare(struct mlx5_hv_vhca_agent *agent, + struct mlx5_hv_vhca_data_block *data_block, + void *src, int len, int *offset) +{ + int bytes = min_t(int, (int)sizeof(data_block->data), len); + + data_block->sequence = agent->seq; + data_block->offset = (*offset)++; + memcpy(data_block->data, src, bytes); + + return bytes; +} + +static void mlx5_hv_vhca_agent_seq_update(struct mlx5_hv_vhca_agent *agent) +{ + agent->seq++; +} + +int mlx5_hv_vhca_agent_write(struct mlx5_hv_vhca_agent *agent, + void *buf, int len) +{ + int offset = agent->type * HV_CONFIG_BLOCK_SIZE_MAX; + int block_offset = 0; + int total = 0; + int err; + + while (len) { + struct mlx5_hv_vhca_data_block data_block = {0}; + int bytes; + + bytes = mlx5_hv_vhca_data_block_prepare(agent, &data_block, + buf + total, + len, &block_offset); + if (!bytes) + return -ENOMEM; + + err = mlx5_hv_write_config(agent->hv_vhca->dev, &data_block, + sizeof(data_block), offset); + if (err) + return err; + + total += bytes; + len -= bytes; + } + + mlx5_hv_vhca_agent_seq_update(agent); + + return 0; +} + +void *mlx5_hv_vhca_agent_priv(struct mlx5_hv_vhca_agent *agent) +{ + return agent->priv; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h new file mode 100644 index 000000000000..4bad6a5fde56 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/hv_vhca.h @@ -0,0 +1,104 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019 Mellanox Technologies. */ + +#ifndef __LIB_HV_VHCA_H__ +#define __LIB_HV_VHCA_H__ + +#include "en.h" +#include "lib/hv.h" + +struct mlx5_hv_vhca_agent; +struct mlx5_hv_vhca; +struct mlx5_hv_vhca_control_block; + +enum mlx5_hv_vhca_agent_type { + MLX5_HV_VHCA_AGENT_CONTROL = 0, + MLX5_HV_VHCA_AGENT_STATS = 1, + MLX5_HV_VHCA_AGENT_MAX = 32, +}; + +#if IS_ENABLED(CONFIG_PCI_HYPERV_INTERFACE) + +struct mlx5_hv_vhca_control_block { + u32 capabilities; + u32 control; + u16 command; + u16 command_ack; + u16 version; + u16 rings; + u32 reserved1[28]; +}; + +struct mlx5_hv_vhca *mlx5_hv_vhca_create(struct mlx5_core_dev *dev); +void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca); +int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca); +void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca); +void mlx5_hv_vhca_invalidate(void *context, u64 block_mask); + +struct mlx5_hv_vhca_agent * +mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, + enum mlx5_hv_vhca_agent_type type, + void (*control)(struct mlx5_hv_vhca_agent*, + struct mlx5_hv_vhca_control_block *block), + void (*invalidate)(struct mlx5_hv_vhca_agent*, + u64 block_mask), + void (*cleanup)(struct mlx5_hv_vhca_agent *agent), + void *context); + +void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent); +int mlx5_hv_vhca_agent_write(struct mlx5_hv_vhca_agent *agent, + void *buf, int len); +void *mlx5_hv_vhca_agent_priv(struct mlx5_hv_vhca_agent *agent); + +#else + +static inline struct mlx5_hv_vhca * +mlx5_hv_vhca_create(struct mlx5_core_dev *dev) +{ + return NULL; +} + +static inline void mlx5_hv_vhca_destroy(struct mlx5_hv_vhca *hv_vhca) +{ +} + +static inline int mlx5_hv_vhca_init(struct mlx5_hv_vhca *hv_vhca) +{ + return 0; +} + +static inline void mlx5_hv_vhca_cleanup(struct mlx5_hv_vhca *hv_vhca) +{ +} + +static inline void mlx5_hv_vhca_invalidate(void *context, + u64 block_mask) +{ +} + +static inline struct mlx5_hv_vhca_agent * +mlx5_hv_vhca_agent_create(struct mlx5_hv_vhca *hv_vhca, + enum mlx5_hv_vhca_agent_type type, + void (*control)(struct mlx5_hv_vhca_agent*, + struct mlx5_hv_vhca_control_block *block), + void (*invalidate)(struct mlx5_hv_vhca_agent*, + u64 block_mask), + void (*cleanup)(struct mlx5_hv_vhca_agent *agent), + void *context) +{ + return NULL; +} + +static inline void mlx5_hv_vhca_agent_destroy(struct mlx5_hv_vhca_agent *agent) +{ +} + +static inline int +mlx5_hv_vhca_write_agent(struct mlx5_hv_vhca_agent *agent, + void *buf, int len) +{ + return 0; +} +#endif + +#endif /* __LIB_HV_VHCA_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c index b9d4f4e19ff9..148b55c3db7a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/vxlan.c @@ -32,6 +32,7 @@ #include <linux/kernel.h> #include <linux/module.h> +#include <linux/refcount.h> #include <linux/mlx5/driver.h> #include <net/vxlan.h> #include "mlx5_core.h" @@ -48,7 +49,7 @@ struct mlx5_vxlan { struct mlx5_vxlan_port { struct hlist_node hlist; - atomic_t refcount; + refcount_t refcount; u16 udp_port; }; @@ -113,7 +114,7 @@ int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) vxlanp = mlx5_vxlan_lookup_port(vxlan, port); if (vxlanp) { - atomic_inc(&vxlanp->refcount); + refcount_inc(&vxlanp->refcount); return 0; } @@ -137,7 +138,7 @@ int mlx5_vxlan_add_port(struct mlx5_vxlan *vxlan, u16 port) } vxlanp->udp_port = port; - atomic_set(&vxlanp->refcount, 1); + refcount_set(&vxlanp->refcount, 1); spin_lock_bh(&vxlan->lock); hash_add(vxlan->htable, &vxlanp->hlist, port); @@ -170,7 +171,7 @@ int mlx5_vxlan_del_port(struct mlx5_vxlan *vxlan, u16 port) goto out_unlock; } - if (atomic_dec_and_test(&vxlanp->refcount)) { + if (refcount_dec_and_test(&vxlanp->refcount)) { hash_del(&vxlanp->hlist); remove = true; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index b15b27a497fc..9648c2297803 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -69,6 +69,7 @@ #include "lib/pci_vsc.h" #include "diag/fw_tracer.h" #include "ecpf.h" +#include "lib/hv_vhca.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); MODULE_DESCRIPTION("Mellanox 5th generation network adapters (ConnectX series) core driver"); @@ -495,6 +496,12 @@ static int handle_hca_cap_odp(struct mlx5_core_dev *dev) ODP_CAP_SET_MAX(dev, xrc_odp_caps.write); ODP_CAP_SET_MAX(dev, xrc_odp_caps.read); ODP_CAP_SET_MAX(dev, xrc_odp_caps.atomic); + ODP_CAP_SET_MAX(dev, dc_odp_caps.srq_receive); + ODP_CAP_SET_MAX(dev, dc_odp_caps.send); + ODP_CAP_SET_MAX(dev, dc_odp_caps.receive); + ODP_CAP_SET_MAX(dev, dc_odp_caps.write); + ODP_CAP_SET_MAX(dev, dc_odp_caps.read); + ODP_CAP_SET_MAX(dev, dc_odp_caps.atomic); if (do_set) err = set_caps(dev, set_ctx, set_sz, @@ -826,11 +833,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_eq_cleanup; } - err = mlx5_cq_debugfs_init(dev); - if (err) { - mlx5_core_err(dev, "failed to initialize cq debugfs\n"); - goto err_events_cleanup; - } + mlx5_cq_debugfs_init(dev); mlx5_init_qp_table(dev); @@ -873,7 +876,12 @@ static int mlx5_init_once(struct mlx5_core_dev *dev) goto err_eswitch_cleanup; } + dev->dm = mlx5_dm_create(dev); + if (IS_ERR(dev->dm)) + mlx5_core_warn(dev, "Failed to init device memory%d\n", err); + dev->tracer = mlx5_fw_tracer_create(dev); + dev->hv_vhca = mlx5_hv_vhca_create(dev); return 0; @@ -891,7 +899,6 @@ err_tables_cleanup: mlx5_cleanup_mkey_table(dev); mlx5_cleanup_qp_table(dev); mlx5_cq_debugfs_cleanup(dev); -err_events_cleanup: mlx5_events_cleanup(dev); err_eq_cleanup: mlx5_eq_table_cleanup(dev); @@ -905,7 +912,9 @@ err_devcom: static void mlx5_cleanup_once(struct mlx5_core_dev *dev) { + mlx5_hv_vhca_destroy(dev->hv_vhca); mlx5_fw_tracer_destroy(dev->tracer); + mlx5_dm_cleanup(dev); mlx5_fpga_cleanup(dev); mlx5_eswitch_cleanup(dev->priv.eswitch); mlx5_sriov_cleanup(dev); @@ -1072,6 +1081,8 @@ static int mlx5_load(struct mlx5_core_dev *dev) goto err_fw_tracer; } + mlx5_hv_vhca_init(dev->hv_vhca); + err = mlx5_fpga_device_start(dev); if (err) { mlx5_core_err(dev, "fpga device start failed %d\n", err); @@ -1127,6 +1138,7 @@ err_tls_start: err_ipsec_start: mlx5_fpga_device_stop(dev); err_fpga_start: + mlx5_hv_vhca_cleanup(dev->hv_vhca); mlx5_fw_tracer_cleanup(dev->tracer); err_fw_tracer: mlx5_eq_table_destroy(dev); @@ -1147,6 +1159,7 @@ static void mlx5_unload(struct mlx5_core_dev *dev) mlx5_accel_ipsec_cleanup(dev); mlx5_accel_tls_cleanup(dev); mlx5_fpga_device_stop(dev); + mlx5_hv_vhca_cleanup(dev->hv_vhca); mlx5_fw_tracer_cleanup(dev->tracer); mlx5_eq_table_destroy(dev); mlx5_irq_table_destroy(dev); @@ -1217,8 +1230,10 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, bool cleanup) { int err = 0; - if (cleanup) + if (cleanup) { + mlx5_unregister_device(dev); mlx5_drain_health_wq(dev); + } mutex_lock(&dev->intf_state_mutex); if (!test_bit(MLX5_INTERFACE_STATE_UP, &dev->intf_state)) { @@ -1369,7 +1384,6 @@ static void remove_one(struct pci_dev *pdev) mlx5_crdump_disable(dev); mlx5_devlink_unregister(devlink); - mlx5_unregister_device(dev); if (mlx5_unload_one(dev, true)) { mlx5_core_err(dev, "mlx5_unload_one failed\n"); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h index 471bbc48bc1f..b100489dc85c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h @@ -146,7 +146,7 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev, void mlx5_cmd_trigger_completions(struct mlx5_core_dev *dev); void mlx5_cmd_flush(struct mlx5_core_dev *dev); -int mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); +void mlx5_cq_debugfs_init(struct mlx5_core_dev *dev); void mlx5_cq_debugfs_cleanup(struct mlx5_core_dev *dev); int mlx5_query_pcam_reg(struct mlx5_core_dev *dev, u32 *pcam, u8 feature_group, @@ -198,6 +198,9 @@ int mlx5_set_mtpps(struct mlx5_core_dev *mdev, u32 *mtpps, u32 mtpps_size); int mlx5_query_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 *arm, u8 *mode); int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode); +struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev); +void mlx5_dm_cleanup(struct mlx5_core_dev *dev); + #define MLX5_PPS_CAP(mdev) (MLX5_CAP_GEN((mdev), pps) && \ MLX5_CAP_GEN((mdev), pps_modify) && \ MLX5_CAP_MCAM_FEATURE((mdev), mtpps_fs) && \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index b8ba74de9555..c3aea4cc2fff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -53,7 +53,7 @@ mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn) common = radix_tree_lookup(&table->tree, rsn); if (common) - atomic_inc(&common->refcount); + refcount_inc(&common->refcount); spin_unlock_irqrestore(&table->lock, flags); @@ -62,7 +62,7 @@ mlx5_get_rsc(struct mlx5_qp_table *table, u32 rsn) void mlx5_core_put_rsc(struct mlx5_core_rsc_common *common) { - if (atomic_dec_and_test(&common->refcount)) + if (refcount_dec_and_test(&common->refcount)) complete(&common->free); } @@ -162,7 +162,7 @@ static int rsc_event_notifier(struct notifier_block *nb, common = mlx5_get_rsc(table, rsn); if (!common) { - mlx5_core_warn(dev, "Async event for bogus resource 0x%x\n", rsn); + mlx5_core_dbg(dev, "Async event for unknown resource 0x%x\n", rsn); return NOTIFY_OK; } @@ -209,7 +209,7 @@ static int create_resource_common(struct mlx5_core_dev *dev, if (err) return err; - atomic_set(&qp->common.refcount, 1); + refcount_set(&qp->common.refcount, 1); init_completion(&qp->common.free); qp->pid = current->pid; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c index 17ce9dd56b13..0fc7de4aa572 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/rdma.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/rdma.c @@ -14,9 +14,6 @@ static void mlx5_rdma_disable_roce_steering(struct mlx5_core_dev *dev) { struct mlx5_core_roce *roce = &dev->priv.roce; - if (!roce->ft) - return; - mlx5_del_flow_rules(roce->allow_rule); mlx5_destroy_flow_group(roce->fg); mlx5_destroy_flow_table(roce->ft); @@ -51,7 +48,7 @@ static int mlx5_rdma_enable_roce_steering(struct mlx5_core_dev *dev) return -ENOMEM; } - ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_RDMA_RX); + ns = mlx5_get_flow_namespace(dev, MLX5_FLOW_NAMESPACE_RDMA_RX_KERNEL); if (!ns) { mlx5_core_err(dev, "Failed to get RDMA RX namespace"); err = -EOPNOTSUPP; @@ -145,6 +142,11 @@ static int mlx5_rdma_add_roce_addr(struct mlx5_core_dev *dev) void mlx5_rdma_disable_roce(struct mlx5_core_dev *dev) { + struct mlx5_core_roce *roce = &dev->priv.roce; + + if (!roce->ft) + return; + mlx5_rdma_disable_roce_steering(dev); mlx5_rdma_del_roce_addr(dev); mlx5_nic_vport_disable_roce(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile new file mode 100644 index 000000000000..c78512eed8d7 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/Makefile @@ -0,0 +1,2 @@ +# SPDX-License-Identifier: GPL-2.0-only +subdir-ccflags-y += -I$(src)/.. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c new file mode 100644 index 000000000000..7d81a7735de5 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_action.c @@ -0,0 +1,1588 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +enum dr_action_domain { + DR_ACTION_DOMAIN_NIC_INGRESS, + DR_ACTION_DOMAIN_NIC_EGRESS, + DR_ACTION_DOMAIN_FDB_INGRESS, + DR_ACTION_DOMAIN_FDB_EGRESS, + DR_ACTION_DOMAIN_MAX, +}; + +enum dr_action_valid_state { + DR_ACTION_STATE_ERR, + DR_ACTION_STATE_NO_ACTION, + DR_ACTION_STATE_REFORMAT, + DR_ACTION_STATE_MODIFY_HDR, + DR_ACTION_STATE_MODIFY_VLAN, + DR_ACTION_STATE_NON_TERM, + DR_ACTION_STATE_TERM, + DR_ACTION_STATE_MAX, +}; + +static const enum dr_action_valid_state +next_action_state[DR_ACTION_DOMAIN_MAX][DR_ACTION_STATE_MAX][DR_ACTION_TYP_MAX] = { + [DR_ACTION_DOMAIN_NIC_INGRESS] = { + [DR_ACTION_STATE_NO_ACTION] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_MODIFY_HDR] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, + }, + [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + }, + [DR_ACTION_STATE_NON_TERM] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_QP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_TAG] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_TERM] = { + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM, + }, + }, + [DR_ACTION_DOMAIN_NIC_EGRESS] = { + [DR_ACTION_STATE_NO_ACTION] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + }, + [DR_ACTION_STATE_MODIFY_HDR] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + }, + [DR_ACTION_STATE_NON_TERM] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + }, + [DR_ACTION_STATE_TERM] = { + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM, + }, + }, + [DR_ACTION_DOMAIN_FDB_INGRESS] = { + [DR_ACTION_STATE_NO_ACTION] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_MODIFY_HDR] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + }, + [DR_ACTION_STATE_NON_TERM] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_TNL_L2_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_TNL_L3_TO_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_POP_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_TERM] = { + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM, + }, + }, + [DR_ACTION_DOMAIN_FDB_EGRESS] = { + [DR_ACTION_STATE_NO_ACTION] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_REFORMAT] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_MODIFY_HDR] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_MODIFY_VLAN] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_NON_TERM] = { + [DR_ACTION_TYP_DROP] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_FT] = DR_ACTION_STATE_TERM, + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_NON_TERM, + [DR_ACTION_TYP_MODIFY_HDR] = DR_ACTION_STATE_MODIFY_HDR, + [DR_ACTION_TYP_L2_TO_TNL_L2] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_L2_TO_TNL_L3] = DR_ACTION_STATE_REFORMAT, + [DR_ACTION_TYP_PUSH_VLAN] = DR_ACTION_STATE_MODIFY_VLAN, + [DR_ACTION_TYP_VPORT] = DR_ACTION_STATE_TERM, + }, + [DR_ACTION_STATE_TERM] = { + [DR_ACTION_TYP_CTR] = DR_ACTION_STATE_TERM, + }, + }, +}; + +struct dr_action_modify_field_conv { + u16 hw_field; + u8 start; + u8 end; + u8 l3_type; + u8 l4_type; +}; + +static const struct dr_action_modify_field_conv dr_action_conv_arr[] = { + [MLX5_ACTION_IN_FIELD_OUT_SMAC_47_16] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_1, .start = 16, .end = 47, + }, + [MLX5_ACTION_IN_FIELD_OUT_SMAC_15_0] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_1, .start = 0, .end = 15, + }, + [MLX5_ACTION_IN_FIELD_OUT_ETHERTYPE] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_2, .start = 32, .end = 47, + }, + [MLX5_ACTION_IN_FIELD_OUT_DMAC_47_16] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_0, .start = 16, .end = 47, + }, + [MLX5_ACTION_IN_FIELD_OUT_DMAC_15_0] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_0, .start = 0, .end = 15, + }, + [MLX5_ACTION_IN_FIELD_OUT_IP_DSCP] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_1, .start = 0, .end = 5, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_FLAGS] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 48, .end = 56, + .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_SPORT] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 0, .end = 15, + .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_DPORT] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 16, .end = 31, + .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP, + }, + [MLX5_ACTION_IN_FIELD_OUT_IP_TTL] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_1, .start = 8, .end = 15, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_1, .start = 8, .end = 15, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_UDP_SPORT] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 0, .end = 15, + .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_UDP, + }, + [MLX5_ACTION_IN_FIELD_OUT_UDP_DPORT] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_0, .start = 16, .end = 31, + .l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_UDP, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_127_96] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_3, .start = 32, .end = 63, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_95_64] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_3, .start = 0, .end = 31, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_63_32] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_4, .start = 32, .end = 63, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV6_31_0] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_4, .start = 0, .end = 31, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_127_96] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 32, .end = 63, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_95_64] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 0, .end = 31, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_63_32] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_2, .start = 32, .end = 63, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV6_31_0] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_2, .start = 0, .end = 31, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6, + }, + [MLX5_ACTION_IN_FIELD_OUT_SIPV4] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 0, .end = 31, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_OUT_DIPV4] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L3_0, .start = 32, .end = 63, + .l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_A] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_METADATA, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_B] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_METADATA, .start = 32, .end = 63, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_0] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_0, .start = 32, .end = 63, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_1] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_0, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_2] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_1, .start = 32, .end = 63, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_3] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_4] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_2, .start = 32, .end = 63, + }, + [MLX5_ACTION_IN_FIELD_METADATA_REG_C_5] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_REG_2, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_1, .start = 32, .end = 63, + }, + [MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L4_1, .start = 0, .end = 31, + }, + [MLX5_ACTION_IN_FIELD_OUT_FIRST_VID] = { + .hw_field = MLX5DR_ACTION_MDFY_HW_FLD_L2_2, .start = 0, .end = 15, + }, +}; + +#define MAX_VLANS 2 +struct dr_action_vlan_info { + int count; + u32 headers[MAX_VLANS]; +}; + +struct dr_action_apply_attr { + u32 modify_index; + u16 modify_actions; + u32 decap_index; + u16 decap_actions; + u8 decap_with_vlan:1; + u64 final_icm_addr; + u32 flow_tag; + u32 ctr_id; + u16 gvmi; + u16 hit_gvmi; + u32 reformat_id; + u32 reformat_size; + struct dr_action_vlan_info vlans; +}; + +static int +dr_action_reformat_to_action_type(enum mlx5dr_action_reformat_type reformat_type, + enum mlx5dr_action_type *action_type) +{ + switch (reformat_type) { + case DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2: + *action_type = DR_ACTION_TYP_TNL_L2_TO_L2; + break; + case DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2: + *action_type = DR_ACTION_TYP_L2_TO_TNL_L2; + break; + case DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2: + *action_type = DR_ACTION_TYP_TNL_L3_TO_L2; + break; + case DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3: + *action_type = DR_ACTION_TYP_L2_TO_TNL_L3; + break; + default: + return -EINVAL; + } + + return 0; +} + +static void dr_actions_init_next_ste(u8 **last_ste, + u32 *added_stes, + enum mlx5dr_ste_entry_type entry_type, + u16 gvmi) +{ + (*added_stes)++; + *last_ste += DR_STE_SIZE; + mlx5dr_ste_init(*last_ste, MLX5DR_STE_LU_TYPE_DONT_CARE, entry_type, gvmi); +} + +static void dr_actions_apply_tx(struct mlx5dr_domain *dmn, + u8 *action_type_set, + u8 *last_ste, + struct dr_action_apply_attr *attr, + u32 *added_stes) +{ + bool encap = action_type_set[DR_ACTION_TYP_L2_TO_TNL_L2] || + action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]; + + /* We want to make sure the modify header comes before L2 + * encapsulation. The reason for that is that we support + * modify headers for outer headers only + */ + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + mlx5dr_ste_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT); + mlx5dr_ste_set_rewrite_actions(last_ste, + attr->modify_actions, + attr->modify_index); + } + + if (action_type_set[DR_ACTION_TYP_PUSH_VLAN]) { + int i; + + for (i = 0; i < attr->vlans.count; i++) { + if (i || action_type_set[DR_ACTION_TYP_MODIFY_HDR]) + dr_actions_init_next_ste(&last_ste, + added_stes, + MLX5DR_STE_TYPE_TX, + attr->gvmi); + + mlx5dr_ste_set_tx_push_vlan(last_ste, + attr->vlans.headers[i], + encap); + } + } + + if (encap) { + /* Modify header and encapsulation require a different STEs. + * Since modify header STE format doesn't support encapsulation + * tunneling_action. + */ + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR] || + action_type_set[DR_ACTION_TYP_PUSH_VLAN]) + dr_actions_init_next_ste(&last_ste, + added_stes, + MLX5DR_STE_TYPE_TX, + attr->gvmi); + + mlx5dr_ste_set_tx_encap(last_ste, + attr->reformat_id, + attr->reformat_size, + action_type_set[DR_ACTION_TYP_L2_TO_TNL_L3]); + /* Whenever prio_tag_required enabled, we can be sure that the + * previous table (ACL) already push vlan to our packet, + * And due to HW limitation we need to set this bit, otherwise + * push vlan + reformat will not work. + */ + if (MLX5_CAP_GEN(dmn->mdev, prio_tag_required)) + mlx5dr_ste_set_go_back_bit(last_ste); + } + + if (action_type_set[DR_ACTION_TYP_CTR]) + mlx5dr_ste_set_counter_id(last_ste, attr->ctr_id); +} + +static void dr_actions_apply_rx(u8 *action_type_set, + u8 *last_ste, + struct dr_action_apply_attr *attr, + u32 *added_stes) +{ + if (action_type_set[DR_ACTION_TYP_CTR]) + mlx5dr_ste_set_counter_id(last_ste, attr->ctr_id); + + if (action_type_set[DR_ACTION_TYP_TNL_L3_TO_L2]) { + mlx5dr_ste_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT); + mlx5dr_ste_set_rx_decap_l3(last_ste, attr->decap_with_vlan); + mlx5dr_ste_set_rewrite_actions(last_ste, + attr->decap_actions, + attr->decap_index); + } + + if (action_type_set[DR_ACTION_TYP_TNL_L2_TO_L2]) + mlx5dr_ste_set_rx_decap(last_ste); + + if (action_type_set[DR_ACTION_TYP_POP_VLAN]) { + int i; + + for (i = 0; i < attr->vlans.count; i++) { + if (i || + action_type_set[DR_ACTION_TYP_TNL_L2_TO_L2] || + action_type_set[DR_ACTION_TYP_TNL_L3_TO_L2]) + dr_actions_init_next_ste(&last_ste, + added_stes, + MLX5DR_STE_TYPE_RX, + attr->gvmi); + + mlx5dr_ste_set_rx_pop_vlan(last_ste); + } + } + + if (action_type_set[DR_ACTION_TYP_MODIFY_HDR]) { + if (mlx5dr_ste_get_entry_type(last_ste) == MLX5DR_STE_TYPE_MODIFY_PKT) + dr_actions_init_next_ste(&last_ste, + added_stes, + MLX5DR_STE_TYPE_MODIFY_PKT, + attr->gvmi); + else + mlx5dr_ste_set_entry_type(last_ste, MLX5DR_STE_TYPE_MODIFY_PKT); + + mlx5dr_ste_set_rewrite_actions(last_ste, + attr->modify_actions, + attr->modify_index); + } + + if (action_type_set[DR_ACTION_TYP_TAG]) { + if (mlx5dr_ste_get_entry_type(last_ste) == MLX5DR_STE_TYPE_MODIFY_PKT) + dr_actions_init_next_ste(&last_ste, + added_stes, + MLX5DR_STE_TYPE_RX, + attr->gvmi); + + mlx5dr_ste_rx_set_flow_tag(last_ste, attr->flow_tag); + } +} + +/* Apply the actions on the rule STE array starting from the last_ste. + * Actions might require more than one STE, new_num_stes will return + * the new size of the STEs array, rule with actions. + */ +static void dr_actions_apply(struct mlx5dr_domain *dmn, + enum mlx5dr_ste_entry_type ste_type, + u8 *action_type_set, + u8 *last_ste, + struct dr_action_apply_attr *attr, + u32 *new_num_stes) +{ + u32 added_stes = 0; + + if (ste_type == MLX5DR_STE_TYPE_RX) + dr_actions_apply_rx(action_type_set, last_ste, attr, &added_stes); + else + dr_actions_apply_tx(dmn, action_type_set, last_ste, attr, &added_stes); + + last_ste += added_stes * DR_STE_SIZE; + *new_num_stes += added_stes; + + mlx5dr_ste_set_hit_gvmi(last_ste, attr->hit_gvmi); + mlx5dr_ste_set_hit_addr(last_ste, attr->final_icm_addr, 1); +} + +static enum dr_action_domain +dr_action_get_action_domain(enum mlx5dr_domain_type domain, + enum mlx5dr_ste_entry_type ste_type) +{ + switch (domain) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + return DR_ACTION_DOMAIN_NIC_INGRESS; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + return DR_ACTION_DOMAIN_NIC_EGRESS; + case MLX5DR_DOMAIN_TYPE_FDB: + if (ste_type == MLX5DR_STE_TYPE_RX) + return DR_ACTION_DOMAIN_FDB_INGRESS; + return DR_ACTION_DOMAIN_FDB_EGRESS; + default: + WARN_ON(true); + return DR_ACTION_DOMAIN_MAX; + } +} + +static +int dr_action_validate_and_get_next_state(enum dr_action_domain action_domain, + u32 action_type, + u32 *state) +{ + u32 cur_state = *state; + + /* Check action state machine is valid */ + *state = next_action_state[action_domain][cur_state][action_type]; + + if (*state == DR_ACTION_STATE_ERR) + return -EOPNOTSUPP; + + return 0; +} + +static int dr_action_handle_cs_recalc(struct mlx5dr_domain *dmn, + struct mlx5dr_action *dest_action, + u64 *final_icm_addr) +{ + int ret; + + switch (dest_action->action_type) { + case DR_ACTION_TYP_FT: + /* Allow destination flow table only if table is a terminating + * table, since there is an *assumption* that in such case FW + * will recalculate the CS. + */ + if (dest_action->dest_tbl.is_fw_tbl) { + *final_icm_addr = dest_action->dest_tbl.fw_tbl.rx_icm_addr; + } else { + mlx5dr_dbg(dmn, + "Destination FT should be terminating when modify TTL is used\n"); + return -EINVAL; + } + break; + + case DR_ACTION_TYP_VPORT: + /* If destination is vport we will get the FW flow table + * that recalculates the CS and forwards to the vport. + */ + ret = mlx5dr_domain_cache_get_recalc_cs_ft_addr(dest_action->vport.dmn, + dest_action->vport.num, + final_icm_addr); + if (ret) { + mlx5dr_err(dmn, "Failed to get FW cs recalc flow table\n"); + return ret; + } + break; + + default: + break; + } + + return 0; +} + +#define WITH_VLAN_NUM_HW_ACTIONS 6 + +int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_action *actions[], + u32 num_actions, + u8 *ste_arr, + u32 *new_hw_ste_arr_sz) +{ + struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn; + bool rx_rule = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + u8 action_type_set[DR_ACTION_TYP_MAX] = {}; + struct mlx5dr_action *dest_action = NULL; + u32 state = DR_ACTION_STATE_NO_ACTION; + struct dr_action_apply_attr attr = {}; + enum dr_action_domain action_domain; + bool recalc_cs_required = false; + u8 *last_ste; + int i, ret; + + attr.gvmi = dmn->info.caps.gvmi; + attr.hit_gvmi = dmn->info.caps.gvmi; + attr.final_icm_addr = nic_dmn->default_icm_addr; + action_domain = dr_action_get_action_domain(dmn->type, nic_dmn->ste_type); + + for (i = 0; i < num_actions; i++) { + struct mlx5dr_action *action; + int max_actions_type = 1; + u32 action_type; + + action = actions[i]; + action_type = action->action_type; + + switch (action_type) { + case DR_ACTION_TYP_DROP: + attr.final_icm_addr = nic_dmn->drop_icm_addr; + break; + case DR_ACTION_TYP_FT: + dest_action = action; + if (!action->dest_tbl.is_fw_tbl) { + if (action->dest_tbl.tbl->dmn != dmn) { + mlx5dr_dbg(dmn, + "Destination table belongs to a different domain\n"); + goto out_invalid_arg; + } + if (action->dest_tbl.tbl->level <= matcher->tbl->level) { + mlx5dr_dbg(dmn, + "Destination table level should be higher than source table\n"); + goto out_invalid_arg; + } + attr.final_icm_addr = rx_rule ? + action->dest_tbl.tbl->rx.s_anchor->chunk->icm_addr : + action->dest_tbl.tbl->tx.s_anchor->chunk->icm_addr; + } else { + struct mlx5dr_cmd_query_flow_table_details output; + int ret; + + /* get the relevant addresses */ + if (!action->dest_tbl.fw_tbl.rx_icm_addr) { + ret = mlx5dr_cmd_query_flow_table(action->dest_tbl.fw_tbl.mdev, + action->dest_tbl.fw_tbl.ft->type, + action->dest_tbl.fw_tbl.ft->id, + &output); + if (!ret) { + action->dest_tbl.fw_tbl.tx_icm_addr = + output.sw_owner_icm_root_1; + action->dest_tbl.fw_tbl.rx_icm_addr = + output.sw_owner_icm_root_0; + } else { + mlx5dr_dbg(dmn, + "Failed mlx5_cmd_query_flow_table ret: %d\n", + ret); + return ret; + } + } + attr.final_icm_addr = rx_rule ? + action->dest_tbl.fw_tbl.rx_icm_addr : + action->dest_tbl.fw_tbl.tx_icm_addr; + } + break; + case DR_ACTION_TYP_QP: + mlx5dr_info(dmn, "Domain doesn't support QP\n"); + goto out_invalid_arg; + case DR_ACTION_TYP_CTR: + attr.ctr_id = action->ctr.ctr_id + + action->ctr.offeset; + break; + case DR_ACTION_TYP_TAG: + attr.flow_tag = action->flow_tag; + break; + case DR_ACTION_TYP_TNL_L2_TO_L2: + break; + case DR_ACTION_TYP_TNL_L3_TO_L2: + attr.decap_index = action->rewrite.index; + attr.decap_actions = action->rewrite.num_of_actions; + attr.decap_with_vlan = + attr.decap_actions == WITH_VLAN_NUM_HW_ACTIONS; + break; + case DR_ACTION_TYP_MODIFY_HDR: + attr.modify_index = action->rewrite.index; + attr.modify_actions = action->rewrite.num_of_actions; + recalc_cs_required = action->rewrite.modify_ttl; + break; + case DR_ACTION_TYP_L2_TO_TNL_L2: + case DR_ACTION_TYP_L2_TO_TNL_L3: + attr.reformat_size = action->reformat.reformat_size; + attr.reformat_id = action->reformat.reformat_id; + break; + case DR_ACTION_TYP_VPORT: + attr.hit_gvmi = action->vport.caps->vhca_gvmi; + dest_action = action; + if (rx_rule) { + /* Loopback on WIRE vport is not supported */ + if (action->vport.num == WIRE_PORT) + goto out_invalid_arg; + + attr.final_icm_addr = action->vport.caps->icm_address_rx; + } else { + attr.final_icm_addr = action->vport.caps->icm_address_tx; + } + break; + case DR_ACTION_TYP_POP_VLAN: + max_actions_type = MAX_VLANS; + attr.vlans.count++; + break; + case DR_ACTION_TYP_PUSH_VLAN: + max_actions_type = MAX_VLANS; + if (attr.vlans.count == MAX_VLANS) + return -EINVAL; + + attr.vlans.headers[attr.vlans.count++] = action->push_vlan.vlan_hdr; + break; + default: + goto out_invalid_arg; + } + + /* Check action duplication */ + if (++action_type_set[action_type] > max_actions_type) { + mlx5dr_dbg(dmn, "Action type %d supports only max %d time(s)\n", + action_type, max_actions_type); + goto out_invalid_arg; + } + + /* Check action state machine is valid */ + if (dr_action_validate_and_get_next_state(action_domain, + action_type, + &state)) { + mlx5dr_dbg(dmn, "Invalid action sequence provided\n"); + return -EOPNOTSUPP; + } + } + + *new_hw_ste_arr_sz = nic_matcher->num_of_builders; + last_ste = ste_arr + DR_STE_SIZE * (nic_matcher->num_of_builders - 1); + + /* Due to a HW bug, modifying TTL on RX flows will cause an incorrect + * checksum calculation. In this case we will use a FW table to + * recalculate. + */ + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB && + rx_rule && recalc_cs_required && dest_action) { + ret = dr_action_handle_cs_recalc(dmn, dest_action, &attr.final_icm_addr); + if (ret) { + mlx5dr_dbg(dmn, + "Failed to handle checksum recalculation err %d\n", + ret); + return ret; + } + } + + dr_actions_apply(dmn, + nic_dmn->ste_type, + action_type_set, + last_ste, + &attr, + new_hw_ste_arr_sz); + + return 0; + +out_invalid_arg: + return -EINVAL; +} + +#define CVLAN_ETHERTYPE 0x8100 +#define SVLAN_ETHERTYPE 0x88a8 +#define HDR_LEN_L2_ONLY 14 +#define HDR_LEN_L2_VLAN 18 +#define REWRITE_HW_ACTION_NUM 6 + +static int dr_actions_l2_rewrite(struct mlx5dr_domain *dmn, + struct mlx5dr_action *action, + void *data, size_t data_sz) +{ + struct mlx5_ifc_l2_hdr_bits *l2_hdr = data; + u64 ops[REWRITE_HW_ACTION_NUM] = {}; + u32 hdr_fld_4b; + u16 hdr_fld_2b; + u16 vlan_type; + bool vlan; + int i = 0; + int ret; + + vlan = (data_sz != HDR_LEN_L2_ONLY); + + /* dmac_47_16 */ + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + MLX5_SET(dr_action_hw_set, ops + i, + destination_length, 0); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_0); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 16); + hdr_fld_4b = MLX5_GET(l2_hdr, l2_hdr, dmac_47_16); + MLX5_SET(dr_action_hw_set, ops + i, + inline_data, hdr_fld_4b); + i++; + + /* smac_47_16 */ + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + MLX5_SET(dr_action_hw_set, ops + i, + destination_length, 0); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_1); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 16); + hdr_fld_4b = (MLX5_GET(l2_hdr, l2_hdr, smac_31_0) >> 16 | + MLX5_GET(l2_hdr, l2_hdr, smac_47_32) << 16); + MLX5_SET(dr_action_hw_set, ops + i, + inline_data, hdr_fld_4b); + i++; + + /* dmac_15_0 */ + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + MLX5_SET(dr_action_hw_set, ops + i, + destination_length, 16); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_0); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 0); + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, dmac_15_0); + MLX5_SET(dr_action_hw_set, ops + i, + inline_data, hdr_fld_2b); + i++; + + /* ethertype + (optional) vlan */ + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_2); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 32); + if (!vlan) { + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, ethertype); + MLX5_SET(dr_action_hw_set, ops + i, inline_data, hdr_fld_2b); + MLX5_SET(dr_action_hw_set, ops + i, destination_length, 16); + } else { + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, ethertype); + vlan_type = hdr_fld_2b == SVLAN_ETHERTYPE ? DR_STE_SVLAN : DR_STE_CVLAN; + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, vlan); + hdr_fld_4b = (vlan_type << 16) | hdr_fld_2b; + MLX5_SET(dr_action_hw_set, ops + i, inline_data, hdr_fld_4b); + MLX5_SET(dr_action_hw_set, ops + i, destination_length, 18); + } + i++; + + /* smac_15_0 */ + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + MLX5_SET(dr_action_hw_set, ops + i, + destination_length, 16); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_1); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 0); + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, smac_31_0); + MLX5_SET(dr_action_hw_set, ops + i, + inline_data, hdr_fld_2b); + i++; + + if (vlan) { + MLX5_SET(dr_action_hw_set, ops + i, + opcode, MLX5DR_ACTION_MDFY_HW_OP_SET); + hdr_fld_2b = MLX5_GET(l2_hdr, l2_hdr, vlan_type); + MLX5_SET(dr_action_hw_set, ops + i, + inline_data, hdr_fld_2b); + MLX5_SET(dr_action_hw_set, ops + i, + destination_length, 16); + MLX5_SET(dr_action_hw_set, ops + i, + destination_field_code, MLX5DR_ACTION_MDFY_HW_FLD_L2_2); + MLX5_SET(dr_action_hw_set, ops + i, + destination_left_shifter, 0); + i++; + } + + action->rewrite.data = (void *)ops; + action->rewrite.num_of_actions = i; + action->rewrite.chunk->byte_size = i * sizeof(*ops); + + ret = mlx5dr_send_postsend_action(dmn, action); + if (ret) { + mlx5dr_dbg(dmn, "Writing encapsulation action to ICM failed\n"); + return ret; + } + + return 0; +} + +static struct mlx5dr_action * +dr_action_create_generic(enum mlx5dr_action_type action_type) +{ + struct mlx5dr_action *action; + + action = kzalloc(sizeof(*action), GFP_KERNEL); + if (!action) + return NULL; + + action->action_type = action_type; + refcount_set(&action->refcount, 1); + + return action; +} + +struct mlx5dr_action *mlx5dr_action_create_drop(void) +{ + return dr_action_create_generic(DR_ACTION_TYP_DROP); +} + +struct mlx5dr_action * +mlx5dr_action_create_dest_table(struct mlx5dr_table *tbl) +{ + struct mlx5dr_action *action; + + refcount_inc(&tbl->refcount); + + action = dr_action_create_generic(DR_ACTION_TYP_FT); + if (!action) + goto dec_ref; + + action->dest_tbl.tbl = tbl; + + return action; + +dec_ref: + refcount_dec(&tbl->refcount); + return NULL; +} + +struct mlx5dr_action * +mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft, + struct mlx5_core_dev *mdev) +{ + struct mlx5dr_action *action; + + action = dr_action_create_generic(DR_ACTION_TYP_FT); + if (!action) + return NULL; + + action->dest_tbl.is_fw_tbl = 1; + action->dest_tbl.fw_tbl.ft = ft; + action->dest_tbl.fw_tbl.mdev = mdev; + + return action; +} + +struct mlx5dr_action * +mlx5dr_action_create_flow_counter(u32 counter_id) +{ + struct mlx5dr_action *action; + + action = dr_action_create_generic(DR_ACTION_TYP_CTR); + if (!action) + return NULL; + + action->ctr.ctr_id = counter_id; + + return action; +} + +struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value) +{ + struct mlx5dr_action *action; + + action = dr_action_create_generic(DR_ACTION_TYP_TAG); + if (!action) + return NULL; + + action->flow_tag = tag_value & 0xffffff; + + return action; +} + +static int +dr_action_verify_reformat_params(enum mlx5dr_action_type reformat_type, + struct mlx5dr_domain *dmn, + size_t data_sz, + void *data) +{ + if ((!data && data_sz) || (data && !data_sz) || reformat_type > + DR_ACTION_TYP_L2_TO_TNL_L3) { + mlx5dr_dbg(dmn, "Invalid reformat parameter!\n"); + goto out_err; + } + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB) + return 0; + + if (dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) { + if (reformat_type != DR_ACTION_TYP_TNL_L2_TO_L2 && + reformat_type != DR_ACTION_TYP_TNL_L3_TO_L2) { + mlx5dr_dbg(dmn, "Action reformat type not support on RX domain\n"); + goto out_err; + } + } else if (dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) { + if (reformat_type != DR_ACTION_TYP_L2_TO_TNL_L2 && + reformat_type != DR_ACTION_TYP_L2_TO_TNL_L3) { + mlx5dr_dbg(dmn, "Action reformat type not support on TX domain\n"); + goto out_err; + } + } + + return 0; + +out_err: + return -EINVAL; +} + +#define ACTION_CACHE_LINE_SIZE 64 + +static int +dr_action_create_reformat_action(struct mlx5dr_domain *dmn, + size_t data_sz, void *data, + struct mlx5dr_action *action) +{ + u32 reformat_id; + int ret; + + switch (action->action_type) { + case DR_ACTION_TYP_L2_TO_TNL_L2: + case DR_ACTION_TYP_L2_TO_TNL_L3: + { + enum mlx5_reformat_ctx_type rt; + + if (action->action_type == DR_ACTION_TYP_L2_TO_TNL_L2) + rt = MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL; + else + rt = MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL; + + ret = mlx5dr_cmd_create_reformat_ctx(dmn->mdev, rt, data_sz, data, + &reformat_id); + if (ret) + return ret; + + action->reformat.reformat_id = reformat_id; + action->reformat.reformat_size = data_sz; + return 0; + } + case DR_ACTION_TYP_TNL_L2_TO_L2: + { + return 0; + } + case DR_ACTION_TYP_TNL_L3_TO_L2: + { + /* Only Ethernet frame is supported, with VLAN (18) or without (14) */ + if (data_sz != HDR_LEN_L2_ONLY && data_sz != HDR_LEN_L2_VLAN) + return -EINVAL; + + action->rewrite.chunk = mlx5dr_icm_alloc_chunk(dmn->action_icm_pool, + DR_CHUNK_SIZE_8); + if (!action->rewrite.chunk) + return -ENOMEM; + + action->rewrite.index = (action->rewrite.chunk->icm_addr - + dmn->info.caps.hdr_modify_icm_addr) / + ACTION_CACHE_LINE_SIZE; + + ret = dr_actions_l2_rewrite(dmn, action, data, data_sz); + if (ret) { + mlx5dr_icm_free_chunk(action->rewrite.chunk); + return ret; + } + return 0; + } + default: + mlx5dr_info(dmn, "Reformat type is not supported %d\n", action->action_type); + return -EINVAL; + } +} + +struct mlx5dr_action *mlx5dr_action_create_pop_vlan(void) +{ + return dr_action_create_generic(DR_ACTION_TYP_POP_VLAN); +} + +struct mlx5dr_action *mlx5dr_action_create_push_vlan(struct mlx5dr_domain *dmn, + __be32 vlan_hdr) +{ + u32 vlan_hdr_h = ntohl(vlan_hdr); + u16 ethertype = vlan_hdr_h >> 16; + struct mlx5dr_action *action; + + if (ethertype != SVLAN_ETHERTYPE && ethertype != CVLAN_ETHERTYPE) { + mlx5dr_dbg(dmn, "Invalid vlan ethertype\n"); + return NULL; + } + + action = dr_action_create_generic(DR_ACTION_TYP_PUSH_VLAN); + if (!action) + return NULL; + + action->push_vlan.vlan_hdr = vlan_hdr_h; + return action; +} + +struct mlx5dr_action * +mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, + enum mlx5dr_action_reformat_type reformat_type, + size_t data_sz, + void *data) +{ + enum mlx5dr_action_type action_type; + struct mlx5dr_action *action; + int ret; + + refcount_inc(&dmn->refcount); + + /* General checks */ + ret = dr_action_reformat_to_action_type(reformat_type, &action_type); + if (ret) { + mlx5dr_dbg(dmn, "Invalid reformat_type provided\n"); + goto dec_ref; + } + + ret = dr_action_verify_reformat_params(action_type, dmn, data_sz, data); + if (ret) + goto dec_ref; + + action = dr_action_create_generic(action_type); + if (!action) + goto dec_ref; + + action->reformat.dmn = dmn; + + ret = dr_action_create_reformat_action(dmn, + data_sz, + data, + action); + if (ret) { + mlx5dr_dbg(dmn, "Failed creating reformat action %d\n", ret); + goto free_action; + } + + return action; + +free_action: + kfree(action); +dec_ref: + refcount_dec(&dmn->refcount); + return NULL; +} + +static const struct dr_action_modify_field_conv * +dr_action_modify_get_hw_info(u16 sw_field) +{ + const struct dr_action_modify_field_conv *hw_action_info; + + if (sw_field >= ARRAY_SIZE(dr_action_conv_arr)) + goto not_found; + + hw_action_info = &dr_action_conv_arr[sw_field]; + if (!hw_action_info->end && !hw_action_info->start) + goto not_found; + + return hw_action_info; + +not_found: + return NULL; +} + +static int +dr_action_modify_sw_to_hw(struct mlx5dr_domain *dmn, + __be64 *sw_action, + __be64 *hw_action, + const struct dr_action_modify_field_conv **ret_hw_info) +{ + const struct dr_action_modify_field_conv *hw_action_info; + u8 offset, length, max_length, action; + u16 sw_field; + u8 hw_opcode; + u32 data; + + /* Get SW modify action data */ + action = MLX5_GET(set_action_in, sw_action, action_type); + length = MLX5_GET(set_action_in, sw_action, length); + offset = MLX5_GET(set_action_in, sw_action, offset); + sw_field = MLX5_GET(set_action_in, sw_action, field); + data = MLX5_GET(set_action_in, sw_action, data); + + /* Convert SW data to HW modify action format */ + hw_action_info = dr_action_modify_get_hw_info(sw_field); + if (!hw_action_info) { + mlx5dr_dbg(dmn, "Modify action invalid field given\n"); + return -EINVAL; + } + + max_length = hw_action_info->end - hw_action_info->start + 1; + + switch (action) { + case MLX5_ACTION_TYPE_SET: + hw_opcode = MLX5DR_ACTION_MDFY_HW_OP_SET; + /* PRM defines that length zero specific length of 32bits */ + if (!length) + length = 32; + + if (length + offset > max_length) { + mlx5dr_dbg(dmn, "Modify action length + offset exceeds limit\n"); + return -EINVAL; + } + break; + + case MLX5_ACTION_TYPE_ADD: + hw_opcode = MLX5DR_ACTION_MDFY_HW_OP_ADD; + offset = 0; + length = max_length; + break; + + default: + mlx5dr_info(dmn, "Unsupported action_type for modify action\n"); + return -EOPNOTSUPP; + } + + MLX5_SET(dr_action_hw_set, hw_action, opcode, hw_opcode); + + MLX5_SET(dr_action_hw_set, hw_action, destination_field_code, + hw_action_info->hw_field); + + MLX5_SET(dr_action_hw_set, hw_action, destination_left_shifter, + hw_action_info->start + offset); + + MLX5_SET(dr_action_hw_set, hw_action, destination_length, + length == 32 ? 0 : length); + + MLX5_SET(dr_action_hw_set, hw_action, inline_data, data); + + *ret_hw_info = hw_action_info; + + return 0; +} + +static int +dr_action_modify_check_field_limitation(struct mlx5dr_domain *dmn, + const __be64 *sw_action) +{ + u16 sw_field; + u8 action; + + sw_field = MLX5_GET(set_action_in, sw_action, field); + action = MLX5_GET(set_action_in, sw_action, action_type); + + /* Check if SW field is supported in current domain (RX/TX) */ + if (action == MLX5_ACTION_TYPE_SET) { + if (sw_field == MLX5_ACTION_IN_FIELD_METADATA_REG_A) { + if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_TX) { + mlx5dr_dbg(dmn, "Unsupported field %d for RX/FDB set action\n", + sw_field); + return -EINVAL; + } + } + + if (sw_field == MLX5_ACTION_IN_FIELD_METADATA_REG_B) { + if (dmn->type != MLX5DR_DOMAIN_TYPE_NIC_RX) { + mlx5dr_dbg(dmn, "Unsupported field %d for TX/FDB set action\n", + sw_field); + return -EINVAL; + } + } + } else if (action == MLX5_ACTION_TYPE_ADD) { + if (sw_field != MLX5_ACTION_IN_FIELD_OUT_IP_TTL && + sw_field != MLX5_ACTION_IN_FIELD_OUT_IPV6_HOPLIMIT && + sw_field != MLX5_ACTION_IN_FIELD_OUT_TCP_SEQ_NUM && + sw_field != MLX5_ACTION_IN_FIELD_OUT_TCP_ACK_NUM) { + mlx5dr_dbg(dmn, "Unsupported field %d for add action\n", sw_field); + return -EINVAL; + } + } else { + mlx5dr_info(dmn, "Unsupported action %d modify action\n", action); + return -EOPNOTSUPP; + } + + return 0; +} + +static bool +dr_action_modify_check_is_ttl_modify(const u64 *sw_action) +{ + u16 sw_field = MLX5_GET(set_action_in, sw_action, field); + + return sw_field == MLX5_ACTION_IN_FIELD_OUT_IP_TTL; +} + +static int dr_actions_convert_modify_header(struct mlx5dr_domain *dmn, + u32 max_hw_actions, + u32 num_sw_actions, + __be64 sw_actions[], + __be64 hw_actions[], + u32 *num_hw_actions, + bool *modify_ttl) +{ + const struct dr_action_modify_field_conv *hw_action_info; + u16 hw_field = MLX5DR_ACTION_MDFY_HW_FLD_RESERVED; + u32 l3_type = MLX5DR_ACTION_MDFY_HW_HDR_L3_NONE; + u32 l4_type = MLX5DR_ACTION_MDFY_HW_HDR_L4_NONE; + int ret, i, hw_idx = 0; + __be64 *sw_action; + __be64 hw_action; + + *modify_ttl = false; + + for (i = 0; i < num_sw_actions; i++) { + sw_action = &sw_actions[i]; + + ret = dr_action_modify_check_field_limitation(dmn, sw_action); + if (ret) + return ret; + + if (!(*modify_ttl)) + *modify_ttl = dr_action_modify_check_is_ttl_modify(sw_action); + + /* Convert SW action to HW action */ + ret = dr_action_modify_sw_to_hw(dmn, + sw_action, + &hw_action, + &hw_action_info); + if (ret) + return ret; + + /* Due to a HW limitation we cannot modify 2 different L3 types */ + if (l3_type && hw_action_info->l3_type && + hw_action_info->l3_type != l3_type) { + mlx5dr_dbg(dmn, "Action list can't support two different L3 types\n"); + return -EINVAL; + } + if (hw_action_info->l3_type) + l3_type = hw_action_info->l3_type; + + /* Due to a HW limitation we cannot modify two different L4 types */ + if (l4_type && hw_action_info->l4_type && + hw_action_info->l4_type != l4_type) { + mlx5dr_dbg(dmn, "Action list can't support two different L4 types\n"); + return -EINVAL; + } + if (hw_action_info->l4_type) + l4_type = hw_action_info->l4_type; + + /* HW reads and executes two actions at once this means we + * need to create a gap if two actions access the same field + */ + if ((hw_idx % 2) && hw_field == hw_action_info->hw_field) { + /* Check if after gap insertion the total number of HW + * modify actions doesn't exceeds the limit + */ + hw_idx++; + if ((num_sw_actions + hw_idx - i) >= max_hw_actions) { + mlx5dr_dbg(dmn, "Modify header action number exceeds HW limit\n"); + return -EINVAL; + } + } + hw_field = hw_action_info->hw_field; + + hw_actions[hw_idx] = hw_action; + hw_idx++; + } + + *num_hw_actions = hw_idx; + + return 0; +} + +static int dr_action_create_modify_action(struct mlx5dr_domain *dmn, + size_t actions_sz, + __be64 actions[], + struct mlx5dr_action *action) +{ + struct mlx5dr_icm_chunk *chunk; + u32 max_hw_actions; + u32 num_hw_actions; + u32 num_sw_actions; + __be64 *hw_actions; + bool modify_ttl; + int ret; + + num_sw_actions = actions_sz / DR_MODIFY_ACTION_SIZE; + max_hw_actions = mlx5dr_icm_pool_chunk_size_to_entries(DR_CHUNK_SIZE_16); + + if (num_sw_actions > max_hw_actions) { + mlx5dr_dbg(dmn, "Max number of actions %d exceeds limit %d\n", + num_sw_actions, max_hw_actions); + return -EINVAL; + } + + chunk = mlx5dr_icm_alloc_chunk(dmn->action_icm_pool, DR_CHUNK_SIZE_16); + if (!chunk) + return -ENOMEM; + + hw_actions = kcalloc(1, max_hw_actions * DR_MODIFY_ACTION_SIZE, GFP_KERNEL); + if (!hw_actions) { + ret = -ENOMEM; + goto free_chunk; + } + + ret = dr_actions_convert_modify_header(dmn, + max_hw_actions, + num_sw_actions, + actions, + hw_actions, + &num_hw_actions, + &modify_ttl); + if (ret) + goto free_hw_actions; + + action->rewrite.chunk = chunk; + action->rewrite.modify_ttl = modify_ttl; + action->rewrite.data = (u8 *)hw_actions; + action->rewrite.num_of_actions = num_hw_actions; + action->rewrite.index = (chunk->icm_addr - + dmn->info.caps.hdr_modify_icm_addr) / + ACTION_CACHE_LINE_SIZE; + + ret = mlx5dr_send_postsend_action(dmn, action); + if (ret) + goto free_hw_actions; + + return 0; + +free_hw_actions: + kfree(hw_actions); +free_chunk: + mlx5dr_icm_free_chunk(chunk); + return ret; +} + +struct mlx5dr_action * +mlx5dr_action_create_modify_header(struct mlx5dr_domain *dmn, + u32 flags, + size_t actions_sz, + __be64 actions[]) +{ + struct mlx5dr_action *action; + int ret = 0; + + refcount_inc(&dmn->refcount); + + if (actions_sz % DR_MODIFY_ACTION_SIZE) { + mlx5dr_dbg(dmn, "Invalid modify actions size provided\n"); + goto dec_ref; + } + + action = dr_action_create_generic(DR_ACTION_TYP_MODIFY_HDR); + if (!action) + goto dec_ref; + + action->rewrite.dmn = dmn; + + ret = dr_action_create_modify_action(dmn, + actions_sz, + actions, + action); + if (ret) { + mlx5dr_dbg(dmn, "Failed creating modify header action %d\n", ret); + goto free_action; + } + + return action; + +free_action: + kfree(action); +dec_ref: + refcount_dec(&dmn->refcount); + return NULL; +} + +struct mlx5dr_action * +mlx5dr_action_create_dest_vport(struct mlx5dr_domain *dmn, + u32 vport, u8 vhca_id_valid, + u16 vhca_id) +{ + struct mlx5dr_cmd_vport_cap *vport_cap; + struct mlx5dr_domain *vport_dmn; + struct mlx5dr_action *action; + u8 peer_vport; + + peer_vport = vhca_id_valid && (vhca_id != dmn->info.caps.gvmi); + vport_dmn = peer_vport ? dmn->peer_dmn : dmn; + if (!vport_dmn) { + mlx5dr_dbg(dmn, "No peer vport domain for given vhca_id\n"); + return NULL; + } + + if (vport_dmn->type != MLX5DR_DOMAIN_TYPE_FDB) { + mlx5dr_dbg(dmn, "Domain doesn't support vport actions\n"); + return NULL; + } + + vport_cap = mlx5dr_get_vport_cap(&vport_dmn->info.caps, vport); + if (!vport_cap) { + mlx5dr_dbg(dmn, "Failed to get vport %d caps\n", vport); + return NULL; + } + + action = dr_action_create_generic(DR_ACTION_TYP_VPORT); + if (!action) + return NULL; + + action->vport.dmn = vport_dmn; + action->vport.caps = vport_cap; + + return action; +} + +int mlx5dr_action_destroy(struct mlx5dr_action *action) +{ + if (refcount_read(&action->refcount) > 1) + return -EBUSY; + + switch (action->action_type) { + case DR_ACTION_TYP_FT: + if (!action->dest_tbl.is_fw_tbl) + refcount_dec(&action->dest_tbl.tbl->refcount); + break; + case DR_ACTION_TYP_TNL_L2_TO_L2: + refcount_dec(&action->reformat.dmn->refcount); + break; + case DR_ACTION_TYP_TNL_L3_TO_L2: + mlx5dr_icm_free_chunk(action->rewrite.chunk); + refcount_dec(&action->reformat.dmn->refcount); + break; + case DR_ACTION_TYP_L2_TO_TNL_L2: + case DR_ACTION_TYP_L2_TO_TNL_L3: + mlx5dr_cmd_destroy_reformat_ctx((action->reformat.dmn)->mdev, + action->reformat.reformat_id); + refcount_dec(&action->reformat.dmn->refcount); + break; + case DR_ACTION_TYP_MODIFY_HDR: + mlx5dr_icm_free_chunk(action->rewrite.chunk); + refcount_dec(&action->rewrite.dmn->refcount); + break; + default: + break; + } + + kfree(action); + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c new file mode 100644 index 000000000000..41662c4e2664 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_cmd.c @@ -0,0 +1,480 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +int mlx5dr_cmd_query_esw_vport_context(struct mlx5_core_dev *mdev, + bool other_vport, + u16 vport_number, + u64 *icm_address_rx, + u64 *icm_address_tx) +{ + u32 out[MLX5_ST_SZ_DW(query_esw_vport_context_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_esw_vport_context_in)] = {}; + int err; + + MLX5_SET(query_esw_vport_context_in, in, opcode, + MLX5_CMD_OP_QUERY_ESW_VPORT_CONTEXT); + MLX5_SET(query_esw_vport_context_in, in, other_vport, other_vport); + MLX5_SET(query_esw_vport_context_in, in, vport_number, vport_number); + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + *icm_address_rx = + MLX5_GET64(query_esw_vport_context_out, out, + esw_vport_context.sw_steering_vport_icm_address_rx); + *icm_address_tx = + MLX5_GET64(query_esw_vport_context_out, out, + esw_vport_context.sw_steering_vport_icm_address_tx); + return 0; +} + +int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, bool other_vport, + u16 vport_number, u16 *gvmi) +{ + u32 in[MLX5_ST_SZ_DW(query_hca_cap_in)] = {}; + int out_size; + void *out; + int err; + + out_size = MLX5_ST_SZ_BYTES(query_hca_cap_out); + out = kzalloc(out_size, GFP_KERNEL); + if (!out) + return -ENOMEM; + + MLX5_SET(query_hca_cap_in, in, opcode, MLX5_CMD_OP_QUERY_HCA_CAP); + MLX5_SET(query_hca_cap_in, in, other_function, other_vport); + MLX5_SET(query_hca_cap_in, in, function_id, vport_number); + MLX5_SET(query_hca_cap_in, in, op_mod, + MLX5_SET_HCA_CAP_OP_MOD_GENERAL_DEVICE << 1 | + HCA_CAP_OPMOD_GET_CUR); + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, out_size); + if (err) { + kfree(out); + return err; + } + + *gvmi = MLX5_GET(query_hca_cap_out, out, capability.cmd_hca_cap.vhca_id); + + kfree(out); + return 0; +} + +int mlx5dr_cmd_query_esw_caps(struct mlx5_core_dev *mdev, + struct mlx5dr_esw_caps *caps) +{ + caps->drop_icm_address_rx = + MLX5_CAP64_ESW_FLOWTABLE(mdev, + sw_steering_fdb_action_drop_icm_address_rx); + caps->drop_icm_address_tx = + MLX5_CAP64_ESW_FLOWTABLE(mdev, + sw_steering_fdb_action_drop_icm_address_tx); + caps->uplink_icm_address_rx = + MLX5_CAP64_ESW_FLOWTABLE(mdev, + sw_steering_uplink_icm_address_rx); + caps->uplink_icm_address_tx = + MLX5_CAP64_ESW_FLOWTABLE(mdev, + sw_steering_uplink_icm_address_tx); + caps->sw_owner = + MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, + sw_owner); + + return 0; +} + +int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, + struct mlx5dr_cmd_caps *caps) +{ + caps->prio_tag_required = MLX5_CAP_GEN(mdev, prio_tag_required); + caps->eswitch_manager = MLX5_CAP_GEN(mdev, eswitch_manager); + caps->gvmi = MLX5_CAP_GEN(mdev, vhca_id); + caps->flex_protocols = MLX5_CAP_GEN(mdev, flex_parser_protocols); + + if (mlx5dr_matcher_supp_flex_parser_icmp_v4(caps)) { + caps->flex_parser_id_icmp_dw0 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw0); + caps->flex_parser_id_icmp_dw1 = MLX5_CAP_GEN(mdev, flex_parser_id_icmp_dw1); + } + + if (mlx5dr_matcher_supp_flex_parser_icmp_v6(caps)) { + caps->flex_parser_id_icmpv6_dw0 = + MLX5_CAP_GEN(mdev, flex_parser_id_icmpv6_dw0); + caps->flex_parser_id_icmpv6_dw1 = + MLX5_CAP_GEN(mdev, flex_parser_id_icmpv6_dw1); + } + + caps->nic_rx_drop_address = + MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_rx_action_drop_icm_address); + caps->nic_tx_drop_address = + MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_tx_action_drop_icm_address); + caps->nic_tx_allow_address = + MLX5_CAP64_FLOWTABLE(mdev, sw_steering_nic_tx_action_allow_icm_address); + + caps->rx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, sw_owner); + caps->max_ft_level = MLX5_CAP_FLOWTABLE_NIC_RX(mdev, max_ft_level); + + caps->tx_sw_owner = MLX5_CAP_FLOWTABLE_NIC_TX(mdev, sw_owner); + + caps->log_icm_size = MLX5_CAP_DEV_MEM(mdev, log_steering_sw_icm_size); + caps->hdr_modify_icm_addr = + MLX5_CAP64_DEV_MEM(mdev, header_modify_sw_icm_start_address); + + caps->roce_min_src_udp = MLX5_CAP_ROCE(mdev, r_roce_min_src_udp_port); + + return 0; +} + +int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev, + enum fs_flow_table_type type, + u32 table_id, + struct mlx5dr_cmd_query_flow_table_details *output) +{ + u32 out[MLX5_ST_SZ_DW(query_flow_table_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_flow_table_in)] = {}; + int err; + + MLX5_SET(query_flow_table_in, in, opcode, + MLX5_CMD_OP_QUERY_FLOW_TABLE); + + MLX5_SET(query_flow_table_in, in, table_type, type); + MLX5_SET(query_flow_table_in, in, table_id, table_id); + + err = mlx5_cmd_exec(dev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + output->status = MLX5_GET(query_flow_table_out, out, status); + output->level = MLX5_GET(query_flow_table_out, out, flow_table_context.level); + + output->sw_owner_icm_root_1 = MLX5_GET64(query_flow_table_out, out, + flow_table_context.sw_owner_icm_root_1); + output->sw_owner_icm_root_0 = MLX5_GET64(query_flow_table_out, out, + flow_table_context.sw_owner_icm_root_0); + + return 0; +} + +int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev) +{ + u32 out[MLX5_ST_SZ_DW(sync_steering_out)] = {}; + u32 in[MLX5_ST_SZ_DW(sync_steering_in)] = {}; + + MLX5_SET(sync_steering_in, in, opcode, MLX5_CMD_OP_SYNC_STEERING); + + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 group_id, + u32 modify_header_id, + u32 vport_id) +{ + u32 out[MLX5_ST_SZ_DW(set_fte_out)] = {}; + void *in_flow_context; + unsigned int inlen; + void *in_dests; + u32 *in; + int err; + + inlen = MLX5_ST_SZ_BYTES(set_fte_in) + + 1 * MLX5_ST_SZ_BYTES(dest_format_struct); /* One destination only */ + + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(set_fte_in, in, opcode, MLX5_CMD_OP_SET_FLOW_TABLE_ENTRY); + MLX5_SET(set_fte_in, in, table_type, table_type); + MLX5_SET(set_fte_in, in, table_id, table_id); + + in_flow_context = MLX5_ADDR_OF(set_fte_in, in, flow_context); + MLX5_SET(flow_context, in_flow_context, group_id, group_id); + MLX5_SET(flow_context, in_flow_context, modify_header_id, modify_header_id); + MLX5_SET(flow_context, in_flow_context, destination_list_size, 1); + MLX5_SET(flow_context, in_flow_context, action, + MLX5_FLOW_CONTEXT_ACTION_FWD_DEST | + MLX5_FLOW_CONTEXT_ACTION_MOD_HDR); + + in_dests = MLX5_ADDR_OF(flow_context, in_flow_context, destination); + MLX5_SET(dest_format_struct, in_dests, destination_type, + MLX5_FLOW_DESTINATION_TYPE_VPORT); + MLX5_SET(dest_format_struct, in_dests, destination_id, vport_id); + + err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); + kvfree(in); + + return err; +} + +int mlx5dr_cmd_del_flow_table_entry(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id) +{ + u32 out[MLX5_ST_SZ_DW(delete_fte_out)] = {}; + u32 in[MLX5_ST_SZ_DW(delete_fte_in)] = {}; + + MLX5_SET(delete_fte_in, in, opcode, MLX5_CMD_OP_DELETE_FLOW_TABLE_ENTRY); + MLX5_SET(delete_fte_in, in, table_type, table_type); + MLX5_SET(delete_fte_in, in, table_id, table_id); + + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_alloc_modify_header(struct mlx5_core_dev *mdev, + u32 table_type, + u8 num_of_actions, + u64 *actions, + u32 *modify_header_id) +{ + u32 out[MLX5_ST_SZ_DW(alloc_modify_header_context_out)] = {}; + void *p_actions; + u32 inlen; + u32 *in; + int err; + + inlen = MLX5_ST_SZ_BYTES(alloc_modify_header_context_in) + + num_of_actions * sizeof(u64); + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(alloc_modify_header_context_in, in, opcode, + MLX5_CMD_OP_ALLOC_MODIFY_HEADER_CONTEXT); + MLX5_SET(alloc_modify_header_context_in, in, table_type, table_type); + MLX5_SET(alloc_modify_header_context_in, in, num_of_actions, num_of_actions); + p_actions = MLX5_ADDR_OF(alloc_modify_header_context_in, in, actions); + memcpy(p_actions, actions, num_of_actions * sizeof(u64)); + + err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); + if (err) + goto out; + + *modify_header_id = MLX5_GET(alloc_modify_header_context_out, out, + modify_header_id); +out: + kvfree(in); + return err; +} + +int mlx5dr_cmd_dealloc_modify_header(struct mlx5_core_dev *mdev, + u32 modify_header_id) +{ + u32 out[MLX5_ST_SZ_DW(dealloc_modify_header_context_out)] = {}; + u32 in[MLX5_ST_SZ_DW(dealloc_modify_header_context_in)] = {}; + + MLX5_SET(dealloc_modify_header_context_in, in, opcode, + MLX5_CMD_OP_DEALLOC_MODIFY_HEADER_CONTEXT); + MLX5_SET(dealloc_modify_header_context_in, in, modify_header_id, + modify_header_id); + + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_create_empty_flow_group(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 *group_id) +{ + u32 out[MLX5_ST_SZ_DW(create_flow_group_out)] = {}; + int inlen = MLX5_ST_SZ_BYTES(create_flow_group_in); + u32 *in; + int err; + + in = kzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(create_flow_group_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_GROUP); + MLX5_SET(create_flow_group_in, in, table_type, table_type); + MLX5_SET(create_flow_group_in, in, table_id, table_id); + + err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); + if (err) + goto out; + + *group_id = MLX5_GET(create_flow_group_out, out, group_id); + +out: + kfree(in); + return err; +} + +int mlx5dr_cmd_destroy_flow_group(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 group_id) +{ + u32 in[MLX5_ST_SZ_DW(destroy_flow_group_in)] = {}; + u32 out[MLX5_ST_SZ_DW(destroy_flow_group_out)] = {}; + + MLX5_SET(create_flow_group_in, in, opcode, MLX5_CMD_OP_DESTROY_FLOW_GROUP); + MLX5_SET(destroy_flow_group_in, in, table_type, table_type); + MLX5_SET(destroy_flow_group_in, in, table_id, table_id); + MLX5_SET(destroy_flow_group_in, in, group_id, group_id); + + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev, + u32 table_type, + u64 icm_addr_rx, + u64 icm_addr_tx, + u8 level, + bool sw_owner, + bool term_tbl, + u64 *fdb_rx_icm_addr, + u32 *table_id) +{ + u32 out[MLX5_ST_SZ_DW(create_flow_table_out)] = {}; + u32 in[MLX5_ST_SZ_DW(create_flow_table_in)] = {}; + void *ft_mdev; + int err; + + MLX5_SET(create_flow_table_in, in, opcode, MLX5_CMD_OP_CREATE_FLOW_TABLE); + MLX5_SET(create_flow_table_in, in, table_type, table_type); + + ft_mdev = MLX5_ADDR_OF(create_flow_table_in, in, flow_table_context); + MLX5_SET(flow_table_context, ft_mdev, termination_table, term_tbl); + MLX5_SET(flow_table_context, ft_mdev, sw_owner, sw_owner); + MLX5_SET(flow_table_context, ft_mdev, level, level); + + if (sw_owner) { + /* icm_addr_0 used for FDB RX / NIC TX / NIC_RX + * icm_addr_1 used for FDB TX + */ + if (table_type == MLX5_FLOW_TABLE_TYPE_NIC_RX) { + MLX5_SET64(flow_table_context, ft_mdev, + sw_owner_icm_root_0, icm_addr_rx); + } else if (table_type == MLX5_FLOW_TABLE_TYPE_NIC_TX) { + MLX5_SET64(flow_table_context, ft_mdev, + sw_owner_icm_root_0, icm_addr_tx); + } else if (table_type == MLX5_FLOW_TABLE_TYPE_FDB) { + MLX5_SET64(flow_table_context, ft_mdev, + sw_owner_icm_root_0, icm_addr_rx); + MLX5_SET64(flow_table_context, ft_mdev, + sw_owner_icm_root_1, icm_addr_tx); + } + } + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + *table_id = MLX5_GET(create_flow_table_out, out, table_id); + if (!sw_owner && table_type == MLX5_FLOW_TABLE_TYPE_FDB) + *fdb_rx_icm_addr = + (u64)MLX5_GET(create_flow_table_out, out, icm_address_31_0) | + (u64)MLX5_GET(create_flow_table_out, out, icm_address_39_32) << 32 | + (u64)MLX5_GET(create_flow_table_out, out, icm_address_63_40) << 40; + + return 0; +} + +int mlx5dr_cmd_destroy_flow_table(struct mlx5_core_dev *mdev, + u32 table_id, + u32 table_type) +{ + u32 out[MLX5_ST_SZ_DW(destroy_flow_table_out)] = {}; + u32 in[MLX5_ST_SZ_DW(destroy_flow_table_in)] = {}; + + MLX5_SET(destroy_flow_table_in, in, opcode, + MLX5_CMD_OP_DESTROY_FLOW_TABLE); + MLX5_SET(destroy_flow_table_in, in, table_type, table_type); + MLX5_SET(destroy_flow_table_in, in, table_id, table_id); + + return mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, + enum mlx5_reformat_ctx_type rt, + size_t reformat_size, + void *reformat_data, + u32 *reformat_id) +{ + u32 out[MLX5_ST_SZ_DW(alloc_packet_reformat_context_out)] = {}; + size_t inlen, cmd_data_sz, cmd_total_sz; + void *prctx; + void *pdata; + void *in; + int err; + + cmd_total_sz = MLX5_ST_SZ_BYTES(alloc_packet_reformat_context_in); + cmd_data_sz = MLX5_FLD_SZ_BYTES(alloc_packet_reformat_context_in, + packet_reformat_context.reformat_data); + inlen = ALIGN(cmd_total_sz + reformat_size - cmd_data_sz, 4); + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + return -ENOMEM; + + MLX5_SET(alloc_packet_reformat_context_in, in, opcode, + MLX5_CMD_OP_ALLOC_PACKET_REFORMAT_CONTEXT); + + prctx = MLX5_ADDR_OF(alloc_packet_reformat_context_in, in, packet_reformat_context); + pdata = MLX5_ADDR_OF(packet_reformat_context_in, prctx, reformat_data); + + MLX5_SET(packet_reformat_context_in, prctx, reformat_type, rt); + MLX5_SET(packet_reformat_context_in, prctx, reformat_data_size, reformat_size); + memcpy(pdata, reformat_data, reformat_size); + + err = mlx5_cmd_exec(mdev, in, inlen, out, sizeof(out)); + if (err) + return err; + + *reformat_id = MLX5_GET(alloc_packet_reformat_context_out, out, packet_reformat_id); + kvfree(in); + + return err; +} + +void mlx5dr_cmd_destroy_reformat_ctx(struct mlx5_core_dev *mdev, + u32 reformat_id) +{ + u32 out[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_out)] = {}; + u32 in[MLX5_ST_SZ_DW(dealloc_packet_reformat_context_in)] = {}; + + MLX5_SET(dealloc_packet_reformat_context_in, in, opcode, + MLX5_CMD_OP_DEALLOC_PACKET_REFORMAT_CONTEXT); + MLX5_SET(dealloc_packet_reformat_context_in, in, packet_reformat_id, + reformat_id); + + mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); +} + +int mlx5dr_cmd_query_gid(struct mlx5_core_dev *mdev, u8 vhca_port_num, + u16 index, struct mlx5dr_cmd_gid_attr *attr) +{ + u32 out[MLX5_ST_SZ_DW(query_roce_address_out)] = {}; + u32 in[MLX5_ST_SZ_DW(query_roce_address_in)] = {}; + int err; + + MLX5_SET(query_roce_address_in, in, opcode, + MLX5_CMD_OP_QUERY_ROCE_ADDRESS); + + MLX5_SET(query_roce_address_in, in, roce_address_index, index); + MLX5_SET(query_roce_address_in, in, vhca_port_num, vhca_port_num); + + err = mlx5_cmd_exec(mdev, in, sizeof(in), out, sizeof(out)); + if (err) + return err; + + memcpy(&attr->gid, + MLX5_ADDR_OF(query_roce_address_out, + out, roce_address.source_l3_address), + sizeof(attr->gid)); + memcpy(attr->mac, + MLX5_ADDR_OF(query_roce_address_out, out, + roce_address.source_mac_47_32), + sizeof(attr->mac)); + + if (MLX5_GET(query_roce_address_out, out, + roce_address.roce_version) == MLX5_ROCE_VERSION_2) + attr->roce_ver = MLX5_ROCE_VERSION_2; + else + attr->roce_ver = MLX5_ROCE_VERSION_1; + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c new file mode 100644 index 000000000000..9e2eccbb1eb8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_crc32.c @@ -0,0 +1,98 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +/* Copyright (c) 2011-2015 Stephan Brumme. All rights reserved. + * Slicing-by-16 contributed by Bulat Ziganshin + * + * This software is provided 'as-is', without any express or implied warranty. + * In no event will the author be held liable for any damages arising from the + * of this software. + * + * Permission is granted to anyone to use this software for any purpose, + * including commercial applications, and to alter it and redistribute it + * freely, subject to the following restrictions: + * + * 1. The origin of this software must not be misrepresented; you must not + * claim that you wrote the original software. + * 2. If you use this software in a product, an acknowledgment in the product + * documentation would be appreciated but is not required. + * 3. Altered source versions must be plainly marked as such, and must not be + * misrepresented as being the original software. + * + * Taken from http://create.stephan-brumme.com/crc32/ and adapted. + */ + +#include "dr_types.h" + +#define DR_STE_CRC_POLY 0xEDB88320L + +static u32 dr_ste_crc_tab32[8][256]; + +static void dr_crc32_calc_lookup_entry(u32 (*tbl)[256], u8 i, u8 j) +{ + tbl[i][j] = (tbl[i - 1][j] >> 8) ^ tbl[0][tbl[i - 1][j] & 0xff]; +} + +void mlx5dr_crc32_init_table(void) +{ + u32 crc, i, j; + + for (i = 0; i < 256; i++) { + crc = i; + for (j = 0; j < 8; j++) { + if (crc & 0x00000001L) + crc = (crc >> 1) ^ DR_STE_CRC_POLY; + else + crc = crc >> 1; + } + dr_ste_crc_tab32[0][i] = crc; + } + + /* Init CRC lookup tables according to crc_slice_8 algorithm */ + for (i = 0; i < 256; i++) { + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 1, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 2, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 3, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 4, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 5, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 6, i); + dr_crc32_calc_lookup_entry(dr_ste_crc_tab32, 7, i); + } +} + +/* Compute CRC32 (Slicing-by-8 algorithm) */ +u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length) +{ + const u32 *curr = (const u32 *)input_data; + const u8 *curr_char; + u32 crc = 0, one, two; + + if (!input_data) + return 0; + + /* Process eight bytes at once (Slicing-by-8) */ + while (length >= 8) { + one = *curr++ ^ crc; + two = *curr++; + + crc = dr_ste_crc_tab32[0][(two >> 24) & 0xff] + ^ dr_ste_crc_tab32[1][(two >> 16) & 0xff] + ^ dr_ste_crc_tab32[2][(two >> 8) & 0xff] + ^ dr_ste_crc_tab32[3][two & 0xff] + ^ dr_ste_crc_tab32[4][(one >> 24) & 0xff] + ^ dr_ste_crc_tab32[5][(one >> 16) & 0xff] + ^ dr_ste_crc_tab32[6][(one >> 8) & 0xff] + ^ dr_ste_crc_tab32[7][one & 0xff]; + + length -= 8; + } + + curr_char = (const u8 *)curr; + /* Remaining 1 to 7 bytes (standard algorithm) */ + while (length-- != 0) + crc = (crc >> 8) ^ dr_ste_crc_tab32[0][(crc & 0xff) + ^ *curr_char++]; + + return ((crc >> 24) & 0xff) | ((crc << 8) & 0xff0000) | + ((crc >> 8) & 0xff00) | ((crc << 24) & 0xff000000); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c new file mode 100644 index 000000000000..5b24732b18c0 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_domain.c @@ -0,0 +1,393 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include <linux/mlx5/eswitch.h> +#include "dr_types.h" + +static int dr_domain_init_cache(struct mlx5dr_domain *dmn) +{ + /* Per vport cached FW FT for checksum recalculation, this + * recalculation is needed due to a HW bug. + */ + dmn->cache.recalc_cs_ft = kcalloc(dmn->info.caps.num_vports, + sizeof(dmn->cache.recalc_cs_ft[0]), + GFP_KERNEL); + if (!dmn->cache.recalc_cs_ft) + return -ENOMEM; + + return 0; +} + +static void dr_domain_uninit_cache(struct mlx5dr_domain *dmn) +{ + int i; + + for (i = 0; i < dmn->info.caps.num_vports; i++) { + if (!dmn->cache.recalc_cs_ft[i]) + continue; + + mlx5dr_fw_destroy_recalc_cs_ft(dmn, dmn->cache.recalc_cs_ft[i]); + } + + kfree(dmn->cache.recalc_cs_ft); +} + +int mlx5dr_domain_cache_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn, + u32 vport_num, + u64 *rx_icm_addr) +{ + struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft; + + recalc_cs_ft = dmn->cache.recalc_cs_ft[vport_num]; + if (!recalc_cs_ft) { + /* Table not in cache, need to allocate a new one */ + recalc_cs_ft = mlx5dr_fw_create_recalc_cs_ft(dmn, vport_num); + if (!recalc_cs_ft) + return -EINVAL; + + dmn->cache.recalc_cs_ft[vport_num] = recalc_cs_ft; + } + + *rx_icm_addr = recalc_cs_ft->rx_icm_addr; + + return 0; +} + +static int dr_domain_init_resources(struct mlx5dr_domain *dmn) +{ + int ret; + + ret = mlx5_core_alloc_pd(dmn->mdev, &dmn->pdn); + if (ret) { + mlx5dr_dbg(dmn, "Couldn't allocate PD\n"); + return ret; + } + + dmn->uar = mlx5_get_uars_page(dmn->mdev); + if (!dmn->uar) { + mlx5dr_err(dmn, "Couldn't allocate UAR\n"); + ret = -ENOMEM; + goto clean_pd; + } + + dmn->ste_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_STE); + if (!dmn->ste_icm_pool) { + mlx5dr_err(dmn, "Couldn't get icm memory\n"); + ret = -ENOMEM; + goto clean_uar; + } + + dmn->action_icm_pool = mlx5dr_icm_pool_create(dmn, DR_ICM_TYPE_MODIFY_ACTION); + if (!dmn->action_icm_pool) { + mlx5dr_err(dmn, "Couldn't get action icm memory\n"); + ret = -ENOMEM; + goto free_ste_icm_pool; + } + + ret = mlx5dr_send_ring_alloc(dmn); + if (ret) { + mlx5dr_err(dmn, "Couldn't create send-ring\n"); + goto free_action_icm_pool; + } + + return 0; + +free_action_icm_pool: + mlx5dr_icm_pool_destroy(dmn->action_icm_pool); +free_ste_icm_pool: + mlx5dr_icm_pool_destroy(dmn->ste_icm_pool); +clean_uar: + mlx5_put_uars_page(dmn->mdev, dmn->uar); +clean_pd: + mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn); + + return ret; +} + +static void dr_domain_uninit_resources(struct mlx5dr_domain *dmn) +{ + mlx5dr_send_ring_free(dmn, dmn->send_ring); + mlx5dr_icm_pool_destroy(dmn->action_icm_pool); + mlx5dr_icm_pool_destroy(dmn->ste_icm_pool); + mlx5_put_uars_page(dmn->mdev, dmn->uar); + mlx5_core_dealloc_pd(dmn->mdev, dmn->pdn); +} + +static int dr_domain_query_vport(struct mlx5dr_domain *dmn, + bool other_vport, + u16 vport_number) +{ + struct mlx5dr_cmd_vport_cap *vport_caps; + int ret; + + vport_caps = &dmn->info.caps.vports_caps[vport_number]; + + ret = mlx5dr_cmd_query_esw_vport_context(dmn->mdev, + other_vport, + vport_number, + &vport_caps->icm_address_rx, + &vport_caps->icm_address_tx); + if (ret) + return ret; + + ret = mlx5dr_cmd_query_gvmi(dmn->mdev, + other_vport, + vport_number, + &vport_caps->vport_gvmi); + if (ret) + return ret; + + vport_caps->num = vport_number; + vport_caps->vhca_gvmi = dmn->info.caps.gvmi; + + return 0; +} + +static int dr_domain_query_vports(struct mlx5dr_domain *dmn) +{ + struct mlx5dr_esw_caps *esw_caps = &dmn->info.caps.esw_caps; + struct mlx5dr_cmd_vport_cap *wire_vport; + int vport; + int ret; + + /* Query vports (except wire vport) */ + for (vport = 0; vport < dmn->info.caps.num_esw_ports - 1; vport++) { + ret = dr_domain_query_vport(dmn, !!vport, vport); + if (ret) + return ret; + } + + /* Last vport is the wire port */ + wire_vport = &dmn->info.caps.vports_caps[vport]; + wire_vport->num = WIRE_PORT; + wire_vport->icm_address_rx = esw_caps->uplink_icm_address_rx; + wire_vport->icm_address_tx = esw_caps->uplink_icm_address_tx; + wire_vport->vport_gvmi = 0; + wire_vport->vhca_gvmi = dmn->info.caps.gvmi; + + return 0; +} + +static int dr_domain_query_fdb_caps(struct mlx5_core_dev *mdev, + struct mlx5dr_domain *dmn) +{ + int ret; + + if (!dmn->info.caps.eswitch_manager) + return -EOPNOTSUPP; + + ret = mlx5dr_cmd_query_esw_caps(mdev, &dmn->info.caps.esw_caps); + if (ret) + return ret; + + dmn->info.caps.fdb_sw_owner = dmn->info.caps.esw_caps.sw_owner; + dmn->info.caps.esw_rx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_rx; + dmn->info.caps.esw_tx_drop_address = dmn->info.caps.esw_caps.drop_icm_address_tx; + + dmn->info.caps.vports_caps = kcalloc(dmn->info.caps.num_esw_ports, + sizeof(dmn->info.caps.vports_caps[0]), + GFP_KERNEL); + if (!dmn->info.caps.vports_caps) + return -ENOMEM; + + ret = dr_domain_query_vports(dmn); + if (ret) { + mlx5dr_dbg(dmn, "Failed to query vports caps\n"); + goto free_vports_caps; + } + + dmn->info.caps.num_vports = dmn->info.caps.num_esw_ports - 1; + + return 0; + +free_vports_caps: + kfree(dmn->info.caps.vports_caps); + dmn->info.caps.vports_caps = NULL; + return ret; +} + +static int dr_domain_caps_init(struct mlx5_core_dev *mdev, + struct mlx5dr_domain *dmn) +{ + struct mlx5dr_cmd_vport_cap *vport_cap; + int ret; + + if (MLX5_CAP_GEN(mdev, port_type) != MLX5_CAP_PORT_TYPE_ETH) { + mlx5dr_dbg(dmn, "Failed to allocate domain, bad link type\n"); + return -EOPNOTSUPP; + } + + dmn->info.caps.num_esw_ports = mlx5_eswitch_get_total_vports(mdev); + + ret = mlx5dr_cmd_query_device(mdev, &dmn->info.caps); + if (ret) + return ret; + + ret = dr_domain_query_fdb_caps(mdev, dmn); + if (ret) + return ret; + + switch (dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + if (!dmn->info.caps.rx_sw_owner) + return -ENOTSUPP; + + dmn->info.supp_sw_steering = true; + dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX; + dmn->info.rx.default_icm_addr = dmn->info.caps.nic_rx_drop_address; + dmn->info.rx.drop_icm_addr = dmn->info.caps.nic_rx_drop_address; + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + if (!dmn->info.caps.tx_sw_owner) + return -ENOTSUPP; + + dmn->info.supp_sw_steering = true; + dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX; + dmn->info.tx.default_icm_addr = dmn->info.caps.nic_tx_allow_address; + dmn->info.tx.drop_icm_addr = dmn->info.caps.nic_tx_drop_address; + break; + case MLX5DR_DOMAIN_TYPE_FDB: + if (!dmn->info.caps.eswitch_manager) + return -ENOTSUPP; + + if (!dmn->info.caps.fdb_sw_owner) + return -ENOTSUPP; + + dmn->info.rx.ste_type = MLX5DR_STE_TYPE_RX; + dmn->info.tx.ste_type = MLX5DR_STE_TYPE_TX; + vport_cap = mlx5dr_get_vport_cap(&dmn->info.caps, 0); + if (!vport_cap) { + mlx5dr_dbg(dmn, "Failed to get esw manager vport\n"); + return -ENOENT; + } + + dmn->info.supp_sw_steering = true; + dmn->info.tx.default_icm_addr = vport_cap->icm_address_tx; + dmn->info.rx.default_icm_addr = vport_cap->icm_address_rx; + dmn->info.rx.drop_icm_addr = dmn->info.caps.esw_rx_drop_address; + dmn->info.tx.drop_icm_addr = dmn->info.caps.esw_tx_drop_address; + break; + default: + mlx5dr_dbg(dmn, "Invalid domain\n"); + ret = -EINVAL; + break; + } + + return ret; +} + +static void dr_domain_caps_uninit(struct mlx5dr_domain *dmn) +{ + kfree(dmn->info.caps.vports_caps); +} + +struct mlx5dr_domain * +mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) +{ + struct mlx5dr_domain *dmn; + int ret; + + if (type > MLX5DR_DOMAIN_TYPE_FDB) + return NULL; + + dmn = kzalloc(sizeof(*dmn), GFP_KERNEL); + if (!dmn) + return NULL; + + dmn->mdev = mdev; + dmn->type = type; + refcount_set(&dmn->refcount, 1); + mutex_init(&dmn->mutex); + + if (dr_domain_caps_init(mdev, dmn)) { + mlx5dr_dbg(dmn, "Failed init domain, no caps\n"); + goto free_domain; + } + + dmn->info.max_log_action_icm_sz = DR_CHUNK_SIZE_4K; + dmn->info.max_log_sw_icm_sz = min_t(u32, DR_CHUNK_SIZE_1024K, + dmn->info.caps.log_icm_size); + + if (!dmn->info.supp_sw_steering) { + mlx5dr_err(dmn, "SW steering is not supported\n"); + goto uninit_caps; + } + + /* Allocate resources */ + ret = dr_domain_init_resources(dmn); + if (ret) { + mlx5dr_err(dmn, "Failed init domain resources\n"); + goto uninit_caps; + } + + ret = dr_domain_init_cache(dmn); + if (ret) { + mlx5dr_err(dmn, "Failed initialize domain cache\n"); + goto uninit_resourses; + } + + /* Init CRC table for htbl CRC calculation */ + mlx5dr_crc32_init_table(); + + return dmn; + +uninit_resourses: + dr_domain_uninit_resources(dmn); +uninit_caps: + dr_domain_caps_uninit(dmn); +free_domain: + kfree(dmn); + return NULL; +} + +/* Assure synchronization of the device steering tables with updates made by SW + * insertion. + */ +int mlx5dr_domain_sync(struct mlx5dr_domain *dmn, u32 flags) +{ + int ret = 0; + + if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_SW) { + mutex_lock(&dmn->mutex); + ret = mlx5dr_send_ring_force_drain(dmn); + mutex_unlock(&dmn->mutex); + if (ret) + return ret; + } + + if (flags & MLX5DR_DOMAIN_SYNC_FLAGS_HW) + ret = mlx5dr_cmd_sync_steering(dmn->mdev); + + return ret; +} + +int mlx5dr_domain_destroy(struct mlx5dr_domain *dmn) +{ + if (refcount_read(&dmn->refcount) > 1) + return -EBUSY; + + /* make sure resources are not used by the hardware */ + mlx5dr_cmd_sync_steering(dmn->mdev); + dr_domain_uninit_cache(dmn); + dr_domain_uninit_resources(dmn); + dr_domain_caps_uninit(dmn); + mutex_destroy(&dmn->mutex); + kfree(dmn); + return 0; +} + +void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, + struct mlx5dr_domain *peer_dmn) +{ + mutex_lock(&dmn->mutex); + + if (dmn->peer_dmn) + refcount_dec(&dmn->peer_dmn->refcount); + + dmn->peer_dmn = peer_dmn; + + if (dmn->peer_dmn) + refcount_inc(&dmn->peer_dmn->refcount); + + mutex_unlock(&dmn->mutex); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c new file mode 100644 index 000000000000..60ef6e6171e3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_fw.c @@ -0,0 +1,93 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include <linux/types.h> +#include "dr_types.h" + +struct mlx5dr_fw_recalc_cs_ft * +mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u32 vport_num) +{ + struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft; + u32 table_id, group_id, modify_hdr_id; + u64 rx_icm_addr, modify_ttl_action; + int ret; + + recalc_cs_ft = kzalloc(sizeof(*recalc_cs_ft), GFP_KERNEL); + if (!recalc_cs_ft) + return NULL; + + ret = mlx5dr_cmd_create_flow_table(dmn->mdev, MLX5_FLOW_TABLE_TYPE_FDB, + 0, 0, dmn->info.caps.max_ft_level - 1, + false, true, &rx_icm_addr, &table_id); + if (ret) { + mlx5dr_err(dmn, "Failed creating TTL W/A FW flow table %d\n", ret); + goto free_ttl_tbl; + } + + ret = mlx5dr_cmd_create_empty_flow_group(dmn->mdev, + MLX5_FLOW_TABLE_TYPE_FDB, + table_id, &group_id); + if (ret) { + mlx5dr_err(dmn, "Failed creating TTL W/A FW flow group %d\n", ret); + goto destroy_flow_table; + } + + /* Modify TTL action by adding zero to trigger CS recalculation */ + modify_ttl_action = 0; + MLX5_SET(set_action_in, &modify_ttl_action, action_type, MLX5_ACTION_TYPE_ADD); + MLX5_SET(set_action_in, &modify_ttl_action, field, MLX5_ACTION_IN_FIELD_OUT_IP_TTL); + + ret = mlx5dr_cmd_alloc_modify_header(dmn->mdev, MLX5_FLOW_TABLE_TYPE_FDB, 1, + &modify_ttl_action, + &modify_hdr_id); + if (ret) { + mlx5dr_err(dmn, "Failed modify header TTL %d\n", ret); + goto destroy_flow_group; + } + + ret = mlx5dr_cmd_set_fte_modify_and_vport(dmn->mdev, + MLX5_FLOW_TABLE_TYPE_FDB, + table_id, group_id, modify_hdr_id, + vport_num); + if (ret) { + mlx5dr_err(dmn, "Failed setting TTL W/A flow table entry %d\n", ret); + goto dealloc_modify_header; + } + + recalc_cs_ft->modify_hdr_id = modify_hdr_id; + recalc_cs_ft->rx_icm_addr = rx_icm_addr; + recalc_cs_ft->table_id = table_id; + recalc_cs_ft->group_id = group_id; + + return recalc_cs_ft; + +dealloc_modify_header: + mlx5dr_cmd_dealloc_modify_header(dmn->mdev, modify_hdr_id); +destroy_flow_group: + mlx5dr_cmd_destroy_flow_group(dmn->mdev, + MLX5_FLOW_TABLE_TYPE_FDB, + table_id, group_id); +destroy_flow_table: + mlx5dr_cmd_destroy_flow_table(dmn->mdev, table_id, MLX5_FLOW_TABLE_TYPE_FDB); +free_ttl_tbl: + kfree(recalc_cs_ft); + return NULL; +} + +void mlx5dr_fw_destroy_recalc_cs_ft(struct mlx5dr_domain *dmn, + struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft) +{ + mlx5dr_cmd_del_flow_table_entry(dmn->mdev, + MLX5_FLOW_TABLE_TYPE_FDB, + recalc_cs_ft->table_id); + mlx5dr_cmd_dealloc_modify_header(dmn->mdev, recalc_cs_ft->modify_hdr_id); + mlx5dr_cmd_destroy_flow_group(dmn->mdev, + MLX5_FLOW_TABLE_TYPE_FDB, + recalc_cs_ft->table_id, + recalc_cs_ft->group_id); + mlx5dr_cmd_destroy_flow_table(dmn->mdev, + recalc_cs_ft->table_id, + MLX5_FLOW_TABLE_TYPE_FDB); + + kfree(recalc_cs_ft); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c new file mode 100644 index 000000000000..913f1e5aaaf2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_icm_pool.c @@ -0,0 +1,570 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +#define DR_ICM_MODIFY_HDR_ALIGN_BASE 64 +#define DR_ICM_SYNC_THRESHOLD (64 * 1024 * 1024) + +struct mlx5dr_icm_pool; + +struct mlx5dr_icm_bucket { + struct mlx5dr_icm_pool *pool; + + /* Chunks that aren't visible to HW not directly and not in cache */ + struct list_head free_list; + unsigned int free_list_count; + + /* Used chunks, HW may be accessing this memory */ + struct list_head used_list; + unsigned int used_list_count; + + /* HW may be accessing this memory but at some future, + * undetermined time, it might cease to do so. Before deciding to call + * sync_ste, this list is moved to sync_list + */ + struct list_head hot_list; + unsigned int hot_list_count; + + /* Pending sync list, entries from the hot list are moved to this list. + * sync_ste is executed and then sync_list is concatenated to the free list + */ + struct list_head sync_list; + unsigned int sync_list_count; + + u32 total_chunks; + u32 num_of_entries; + u32 entry_size; + /* protect the ICM bucket */ + struct mutex mutex; +}; + +struct mlx5dr_icm_pool { + struct mlx5dr_icm_bucket *buckets; + enum mlx5dr_icm_type icm_type; + enum mlx5dr_icm_chunk_size max_log_chunk_sz; + enum mlx5dr_icm_chunk_size num_of_buckets; + struct list_head icm_mr_list; + /* protect the ICM MR list */ + struct mutex mr_mutex; + struct mlx5dr_domain *dmn; +}; + +struct mlx5dr_icm_dm { + u32 obj_id; + enum mlx5_sw_icm_type type; + phys_addr_t addr; + size_t length; +}; + +struct mlx5dr_icm_mr { + struct mlx5dr_icm_pool *pool; + struct mlx5_core_mkey mkey; + struct mlx5dr_icm_dm dm; + size_t used_length; + size_t length; + u64 icm_start_addr; + struct list_head mr_list; +}; + +static int dr_icm_create_dm_mkey(struct mlx5_core_dev *mdev, + u32 pd, u64 length, u64 start_addr, int mode, + struct mlx5_core_mkey *mkey) +{ + u32 inlen = MLX5_ST_SZ_BYTES(create_mkey_in); + u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {}; + void *mkc; + + mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + + MLX5_SET(mkc, mkc, access_mode_1_0, mode); + MLX5_SET(mkc, mkc, access_mode_4_2, (mode >> 2) & 0x7); + MLX5_SET(mkc, mkc, lw, 1); + MLX5_SET(mkc, mkc, lr, 1); + if (mode == MLX5_MKC_ACCESS_MODE_SW_ICM) { + MLX5_SET(mkc, mkc, rw, 1); + MLX5_SET(mkc, mkc, rr, 1); + } + + MLX5_SET64(mkc, mkc, len, length); + MLX5_SET(mkc, mkc, pd, pd); + MLX5_SET(mkc, mkc, qpn, 0xffffff); + MLX5_SET64(mkc, mkc, start_addr, start_addr); + + return mlx5_core_create_mkey(mdev, mkey, in, inlen); +} + +static struct mlx5dr_icm_mr * +dr_icm_pool_mr_create(struct mlx5dr_icm_pool *pool, + enum mlx5_sw_icm_type type, + size_t align_base) +{ + struct mlx5_core_dev *mdev = pool->dmn->mdev; + struct mlx5dr_icm_mr *icm_mr; + size_t align_diff; + int err; + + icm_mr = kvzalloc(sizeof(*icm_mr), GFP_KERNEL); + if (!icm_mr) + return NULL; + + icm_mr->pool = pool; + INIT_LIST_HEAD(&icm_mr->mr_list); + + icm_mr->dm.type = type; + + /* 2^log_biggest_table * entry-size * double-for-alignment */ + icm_mr->dm.length = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, + pool->icm_type) * 2; + + err = mlx5_dm_sw_icm_alloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0, + &icm_mr->dm.addr, &icm_mr->dm.obj_id); + if (err) { + mlx5dr_err(pool->dmn, "Failed to allocate SW ICM memory, err (%d)\n", err); + goto free_icm_mr; + } + + /* Register device memory */ + err = dr_icm_create_dm_mkey(mdev, pool->dmn->pdn, + icm_mr->dm.length, + icm_mr->dm.addr, + MLX5_MKC_ACCESS_MODE_SW_ICM, + &icm_mr->mkey); + if (err) { + mlx5dr_err(pool->dmn, "Failed to create SW ICM MKEY, err (%d)\n", err); + goto free_dm; + } + + icm_mr->icm_start_addr = icm_mr->dm.addr; + + align_diff = icm_mr->icm_start_addr % align_base; + if (align_diff) + icm_mr->used_length = align_base - align_diff; + + list_add_tail(&icm_mr->mr_list, &pool->icm_mr_list); + + return icm_mr; + +free_dm: + mlx5_dm_sw_icm_dealloc(mdev, icm_mr->dm.type, icm_mr->dm.length, 0, + icm_mr->dm.addr, icm_mr->dm.obj_id); +free_icm_mr: + kvfree(icm_mr); + return NULL; +} + +static void dr_icm_pool_mr_destroy(struct mlx5dr_icm_mr *icm_mr) +{ + struct mlx5_core_dev *mdev = icm_mr->pool->dmn->mdev; + struct mlx5dr_icm_dm *dm = &icm_mr->dm; + + list_del(&icm_mr->mr_list); + mlx5_core_destroy_mkey(mdev, &icm_mr->mkey); + mlx5_dm_sw_icm_dealloc(mdev, dm->type, dm->length, 0, + dm->addr, dm->obj_id); + kvfree(icm_mr); +} + +static int dr_icm_chunk_ste_init(struct mlx5dr_icm_chunk *chunk) +{ + struct mlx5dr_icm_bucket *bucket = chunk->bucket; + + chunk->ste_arr = kvzalloc(bucket->num_of_entries * + sizeof(chunk->ste_arr[0]), GFP_KERNEL); + if (!chunk->ste_arr) + return -ENOMEM; + + chunk->hw_ste_arr = kvzalloc(bucket->num_of_entries * + DR_STE_SIZE_REDUCED, GFP_KERNEL); + if (!chunk->hw_ste_arr) + goto out_free_ste_arr; + + chunk->miss_list = kvmalloc(bucket->num_of_entries * + sizeof(chunk->miss_list[0]), GFP_KERNEL); + if (!chunk->miss_list) + goto out_free_hw_ste_arr; + + return 0; + +out_free_hw_ste_arr: + kvfree(chunk->hw_ste_arr); +out_free_ste_arr: + kvfree(chunk->ste_arr); + return -ENOMEM; +} + +static int dr_icm_chunks_create(struct mlx5dr_icm_bucket *bucket) +{ + size_t mr_free_size, mr_req_size, mr_row_size; + struct mlx5dr_icm_pool *pool = bucket->pool; + struct mlx5dr_icm_mr *icm_mr = NULL; + struct mlx5dr_icm_chunk *chunk; + enum mlx5_sw_icm_type dm_type; + size_t align_base; + int i, err = 0; + + mr_req_size = bucket->num_of_entries * bucket->entry_size; + mr_row_size = mlx5dr_icm_pool_chunk_size_to_byte(pool->max_log_chunk_sz, + pool->icm_type); + + if (pool->icm_type == DR_ICM_TYPE_STE) { + dm_type = MLX5_SW_ICM_TYPE_STEERING; + /* Align base is the biggest chunk size / row size */ + align_base = mr_row_size; + } else { + dm_type = MLX5_SW_ICM_TYPE_HEADER_MODIFY; + /* Align base is 64B */ + align_base = DR_ICM_MODIFY_HDR_ALIGN_BASE; + } + + mutex_lock(&pool->mr_mutex); + if (!list_empty(&pool->icm_mr_list)) { + icm_mr = list_last_entry(&pool->icm_mr_list, + struct mlx5dr_icm_mr, mr_list); + + if (icm_mr) + mr_free_size = icm_mr->dm.length - icm_mr->used_length; + } + + if (!icm_mr || mr_free_size < mr_row_size) { + icm_mr = dr_icm_pool_mr_create(pool, dm_type, align_base); + if (!icm_mr) { + err = -ENOMEM; + goto out_err; + } + } + + /* Create memory aligned chunks */ + for (i = 0; i < mr_row_size / mr_req_size; i++) { + chunk = kvzalloc(sizeof(*chunk), GFP_KERNEL); + if (!chunk) { + err = -ENOMEM; + goto out_err; + } + + chunk->bucket = bucket; + chunk->rkey = icm_mr->mkey.key; + /* mr start addr is zero based */ + chunk->mr_addr = icm_mr->used_length; + chunk->icm_addr = (uintptr_t)icm_mr->icm_start_addr + icm_mr->used_length; + icm_mr->used_length += mr_req_size; + chunk->num_of_entries = bucket->num_of_entries; + chunk->byte_size = chunk->num_of_entries * bucket->entry_size; + + if (pool->icm_type == DR_ICM_TYPE_STE) { + err = dr_icm_chunk_ste_init(chunk); + if (err) + goto out_free_chunk; + } + + INIT_LIST_HEAD(&chunk->chunk_list); + list_add(&chunk->chunk_list, &bucket->free_list); + bucket->free_list_count++; + bucket->total_chunks++; + } + mutex_unlock(&pool->mr_mutex); + return 0; + +out_free_chunk: + kvfree(chunk); +out_err: + mutex_unlock(&pool->mr_mutex); + return err; +} + +static void dr_icm_chunk_ste_cleanup(struct mlx5dr_icm_chunk *chunk) +{ + kvfree(chunk->miss_list); + kvfree(chunk->hw_ste_arr); + kvfree(chunk->ste_arr); +} + +static void dr_icm_chunk_destroy(struct mlx5dr_icm_chunk *chunk) +{ + struct mlx5dr_icm_bucket *bucket = chunk->bucket; + + list_del(&chunk->chunk_list); + bucket->total_chunks--; + + if (bucket->pool->icm_type == DR_ICM_TYPE_STE) + dr_icm_chunk_ste_cleanup(chunk); + + kvfree(chunk); +} + +static void dr_icm_bucket_init(struct mlx5dr_icm_pool *pool, + struct mlx5dr_icm_bucket *bucket, + enum mlx5dr_icm_chunk_size chunk_size) +{ + if (pool->icm_type == DR_ICM_TYPE_STE) + bucket->entry_size = DR_STE_SIZE; + else + bucket->entry_size = DR_MODIFY_ACTION_SIZE; + + bucket->num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size); + bucket->pool = pool; + mutex_init(&bucket->mutex); + INIT_LIST_HEAD(&bucket->free_list); + INIT_LIST_HEAD(&bucket->used_list); + INIT_LIST_HEAD(&bucket->hot_list); + INIT_LIST_HEAD(&bucket->sync_list); +} + +static void dr_icm_bucket_cleanup(struct mlx5dr_icm_bucket *bucket) +{ + struct mlx5dr_icm_chunk *chunk, *next; + + mutex_destroy(&bucket->mutex); + list_splice_tail_init(&bucket->sync_list, &bucket->free_list); + list_splice_tail_init(&bucket->hot_list, &bucket->free_list); + + list_for_each_entry_safe(chunk, next, &bucket->free_list, chunk_list) + dr_icm_chunk_destroy(chunk); + + WARN_ON(bucket->total_chunks != 0); + + /* Cleanup of unreturned chunks */ + list_for_each_entry_safe(chunk, next, &bucket->used_list, chunk_list) + dr_icm_chunk_destroy(chunk); +} + +static u64 dr_icm_hot_mem_size(struct mlx5dr_icm_pool *pool) +{ + u64 hot_size = 0; + int chunk_order; + + for (chunk_order = 0; chunk_order < pool->num_of_buckets; chunk_order++) + hot_size += pool->buckets[chunk_order].hot_list_count * + mlx5dr_icm_pool_chunk_size_to_byte(chunk_order, pool->icm_type); + + return hot_size; +} + +static bool dr_icm_reuse_hot_entries(struct mlx5dr_icm_pool *pool, + struct mlx5dr_icm_bucket *bucket) +{ + u64 bytes_for_sync; + + bytes_for_sync = dr_icm_hot_mem_size(pool); + if (bytes_for_sync < DR_ICM_SYNC_THRESHOLD || !bucket->hot_list_count) + return false; + + return true; +} + +static void dr_icm_chill_bucket_start(struct mlx5dr_icm_bucket *bucket) +{ + list_splice_tail_init(&bucket->hot_list, &bucket->sync_list); + bucket->sync_list_count += bucket->hot_list_count; + bucket->hot_list_count = 0; +} + +static void dr_icm_chill_bucket_end(struct mlx5dr_icm_bucket *bucket) +{ + list_splice_tail_init(&bucket->sync_list, &bucket->free_list); + bucket->free_list_count += bucket->sync_list_count; + bucket->sync_list_count = 0; +} + +static void dr_icm_chill_bucket_abort(struct mlx5dr_icm_bucket *bucket) +{ + list_splice_tail_init(&bucket->sync_list, &bucket->hot_list); + bucket->hot_list_count += bucket->sync_list_count; + bucket->sync_list_count = 0; +} + +static void dr_icm_chill_buckets_start(struct mlx5dr_icm_pool *pool, + struct mlx5dr_icm_bucket *cb, + bool buckets[DR_CHUNK_SIZE_MAX]) +{ + struct mlx5dr_icm_bucket *bucket; + int i; + + for (i = 0; i < pool->num_of_buckets; i++) { + bucket = &pool->buckets[i]; + if (bucket == cb) { + dr_icm_chill_bucket_start(bucket); + continue; + } + + /* Freeing the mutex is done at the end of that process, after + * sync_ste was executed at dr_icm_chill_buckets_end func. + */ + if (mutex_trylock(&bucket->mutex)) { + dr_icm_chill_bucket_start(bucket); + buckets[i] = true; + } + } +} + +static void dr_icm_chill_buckets_end(struct mlx5dr_icm_pool *pool, + struct mlx5dr_icm_bucket *cb, + bool buckets[DR_CHUNK_SIZE_MAX]) +{ + struct mlx5dr_icm_bucket *bucket; + int i; + + for (i = 0; i < pool->num_of_buckets; i++) { + bucket = &pool->buckets[i]; + if (bucket == cb) { + dr_icm_chill_bucket_end(bucket); + continue; + } + + if (!buckets[i]) + continue; + + dr_icm_chill_bucket_end(bucket); + mutex_unlock(&bucket->mutex); + } +} + +static void dr_icm_chill_buckets_abort(struct mlx5dr_icm_pool *pool, + struct mlx5dr_icm_bucket *cb, + bool buckets[DR_CHUNK_SIZE_MAX]) +{ + struct mlx5dr_icm_bucket *bucket; + int i; + + for (i = 0; i < pool->num_of_buckets; i++) { + bucket = &pool->buckets[i]; + if (bucket == cb) { + dr_icm_chill_bucket_abort(bucket); + continue; + } + + if (!buckets[i]) + continue; + + dr_icm_chill_bucket_abort(bucket); + mutex_unlock(&bucket->mutex); + } +} + +/* Allocate an ICM chunk, each chunk holds a piece of ICM memory and + * also memory used for HW STE management for optimizations. + */ +struct mlx5dr_icm_chunk * +mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size) +{ + struct mlx5dr_icm_chunk *chunk = NULL; /* Fix compilation warning */ + bool buckets[DR_CHUNK_SIZE_MAX] = {}; + struct mlx5dr_icm_bucket *bucket; + int err; + + if (chunk_size > pool->max_log_chunk_sz) + return NULL; + + bucket = &pool->buckets[chunk_size]; + + mutex_lock(&bucket->mutex); + + /* Take chunk from pool if available, otherwise allocate new chunks */ + if (list_empty(&bucket->free_list)) { + if (dr_icm_reuse_hot_entries(pool, bucket)) { + dr_icm_chill_buckets_start(pool, bucket, buckets); + err = mlx5dr_cmd_sync_steering(pool->dmn->mdev); + if (err) { + dr_icm_chill_buckets_abort(pool, bucket, buckets); + mlx5dr_dbg(pool->dmn, "Sync_steering failed\n"); + chunk = NULL; + goto out; + } + dr_icm_chill_buckets_end(pool, bucket, buckets); + } else { + dr_icm_chunks_create(bucket); + } + } + + if (!list_empty(&bucket->free_list)) { + chunk = list_last_entry(&bucket->free_list, + struct mlx5dr_icm_chunk, + chunk_list); + if (chunk) { + list_del_init(&chunk->chunk_list); + list_add_tail(&chunk->chunk_list, &bucket->used_list); + bucket->free_list_count--; + bucket->used_list_count++; + } + } +out: + mutex_unlock(&bucket->mutex); + return chunk; +} + +void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk) +{ + struct mlx5dr_icm_bucket *bucket = chunk->bucket; + + if (bucket->pool->icm_type == DR_ICM_TYPE_STE) { + memset(chunk->ste_arr, 0, + bucket->num_of_entries * sizeof(chunk->ste_arr[0])); + memset(chunk->hw_ste_arr, 0, + bucket->num_of_entries * DR_STE_SIZE_REDUCED); + } + + mutex_lock(&bucket->mutex); + list_del_init(&chunk->chunk_list); + list_add_tail(&chunk->chunk_list, &bucket->hot_list); + bucket->hot_list_count++; + bucket->used_list_count--; + mutex_unlock(&bucket->mutex); +} + +struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, + enum mlx5dr_icm_type icm_type) +{ + enum mlx5dr_icm_chunk_size max_log_chunk_sz; + struct mlx5dr_icm_pool *pool; + int i; + + if (icm_type == DR_ICM_TYPE_STE) + max_log_chunk_sz = dmn->info.max_log_sw_icm_sz; + else + max_log_chunk_sz = dmn->info.max_log_action_icm_sz; + + pool = kvzalloc(sizeof(*pool), GFP_KERNEL); + if (!pool) + return NULL; + + pool->buckets = kcalloc(max_log_chunk_sz + 1, + sizeof(pool->buckets[0]), + GFP_KERNEL); + if (!pool->buckets) + goto free_pool; + + pool->dmn = dmn; + pool->icm_type = icm_type; + pool->max_log_chunk_sz = max_log_chunk_sz; + pool->num_of_buckets = max_log_chunk_sz + 1; + INIT_LIST_HEAD(&pool->icm_mr_list); + + for (i = 0; i < pool->num_of_buckets; i++) + dr_icm_bucket_init(pool, &pool->buckets[i], i); + + mutex_init(&pool->mr_mutex); + + return pool; + +free_pool: + kvfree(pool); + return NULL; +} + +void mlx5dr_icm_pool_destroy(struct mlx5dr_icm_pool *pool) +{ + struct mlx5dr_icm_mr *icm_mr, *next; + int i; + + mutex_destroy(&pool->mr_mutex); + + list_for_each_entry_safe(icm_mr, next, &pool->icm_mr_list, mr_list) + dr_icm_pool_mr_destroy(icm_mr); + + for (i = 0; i < pool->num_of_buckets; i++) + dr_icm_bucket_cleanup(&pool->buckets[i]); + + kfree(pool->buckets); + kvfree(pool); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c new file mode 100644 index 000000000000..01008cd66f75 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_matcher.c @@ -0,0 +1,770 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +static bool dr_mask_is_smac_set(struct mlx5dr_match_spec *spec) +{ + return (spec->smac_47_16 || spec->smac_15_0); +} + +static bool dr_mask_is_dmac_set(struct mlx5dr_match_spec *spec) +{ + return (spec->dmac_47_16 || spec->dmac_15_0); +} + +static bool dr_mask_is_src_addr_set(struct mlx5dr_match_spec *spec) +{ + return (spec->src_ip_127_96 || spec->src_ip_95_64 || + spec->src_ip_63_32 || spec->src_ip_31_0); +} + +static bool dr_mask_is_dst_addr_set(struct mlx5dr_match_spec *spec) +{ + return (spec->dst_ip_127_96 || spec->dst_ip_95_64 || + spec->dst_ip_63_32 || spec->dst_ip_31_0); +} + +static bool dr_mask_is_l3_base_set(struct mlx5dr_match_spec *spec) +{ + return (spec->ip_protocol || spec->frag || spec->tcp_flags || + spec->ip_ecn || spec->ip_dscp); +} + +static bool dr_mask_is_tcp_udp_base_set(struct mlx5dr_match_spec *spec) +{ + return (spec->tcp_sport || spec->tcp_dport || + spec->udp_sport || spec->udp_dport); +} + +static bool dr_mask_is_ipv4_set(struct mlx5dr_match_spec *spec) +{ + return (spec->dst_ip_31_0 || spec->src_ip_31_0); +} + +static bool dr_mask_is_ipv4_5_tuple_set(struct mlx5dr_match_spec *spec) +{ + return (dr_mask_is_l3_base_set(spec) || + dr_mask_is_tcp_udp_base_set(spec) || + dr_mask_is_ipv4_set(spec)); +} + +static bool dr_mask_is_eth_l2_tnl_set(struct mlx5dr_match_misc *misc) +{ + return misc->vxlan_vni; +} + +static bool dr_mask_is_ttl_set(struct mlx5dr_match_spec *spec) +{ + return spec->ttl_hoplimit; +} + +#define DR_MASK_IS_L2_DST(_spec, _misc, _inner_outer) (_spec.first_vid || \ + (_spec).first_cfi || (_spec).first_prio || (_spec).cvlan_tag || \ + (_spec).svlan_tag || (_spec).dmac_47_16 || (_spec).dmac_15_0 || \ + (_spec).ethertype || (_spec).ip_version || \ + (_misc)._inner_outer##_second_vid || \ + (_misc)._inner_outer##_second_cfi || \ + (_misc)._inner_outer##_second_prio || \ + (_misc)._inner_outer##_second_cvlan_tag || \ + (_misc)._inner_outer##_second_svlan_tag) + +#define DR_MASK_IS_ETH_L4_SET(_spec, _misc, _inner_outer) ( \ + dr_mask_is_l3_base_set(&(_spec)) || \ + dr_mask_is_tcp_udp_base_set(&(_spec)) || \ + dr_mask_is_ttl_set(&(_spec)) || \ + (_misc)._inner_outer##_ipv6_flow_label) + +#define DR_MASK_IS_ETH_L4_MISC_SET(_misc3, _inner_outer) ( \ + (_misc3)._inner_outer##_tcp_seq_num || \ + (_misc3)._inner_outer##_tcp_ack_num) + +#define DR_MASK_IS_FIRST_MPLS_SET(_misc2, _inner_outer) ( \ + (_misc2)._inner_outer##_first_mpls_label || \ + (_misc2)._inner_outer##_first_mpls_exp || \ + (_misc2)._inner_outer##_first_mpls_s_bos || \ + (_misc2)._inner_outer##_first_mpls_ttl) + +static bool dr_mask_is_gre_set(struct mlx5dr_match_misc *misc) +{ + return (misc->gre_key_h || misc->gre_key_l || + misc->gre_protocol || misc->gre_c_present || + misc->gre_k_present || misc->gre_s_present); +} + +#define DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET(_misc2, gre_udp) ( \ + (_misc2).outer_first_mpls_over_##gre_udp##_label || \ + (_misc2).outer_first_mpls_over_##gre_udp##_exp || \ + (_misc2).outer_first_mpls_over_##gre_udp##_s_bos || \ + (_misc2).outer_first_mpls_over_##gre_udp##_ttl) + +#define DR_MASK_IS_FLEX_PARSER_0_SET(_misc2) ( \ + DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), gre) || \ + DR_MASK_IS_OUTER_MPLS_OVER_GRE_UDP_SET((_misc2), udp)) + +static bool dr_mask_is_flex_parser_tnl_set(struct mlx5dr_match_misc3 *misc3) +{ + return (misc3->outer_vxlan_gpe_vni || + misc3->outer_vxlan_gpe_next_protocol || + misc3->outer_vxlan_gpe_flags); +} + +static bool dr_mask_is_flex_parser_icmpv6_set(struct mlx5dr_match_misc3 *misc3) +{ + return (misc3->icmpv6_type || misc3->icmpv6_code || + misc3->icmpv6_header_data); +} + +static bool dr_mask_is_wqe_metadata_set(struct mlx5dr_match_misc2 *misc2) +{ + return misc2->metadata_reg_a; +} + +static bool dr_mask_is_reg_c_0_3_set(struct mlx5dr_match_misc2 *misc2) +{ + return (misc2->metadata_reg_c_0 || misc2->metadata_reg_c_1 || + misc2->metadata_reg_c_2 || misc2->metadata_reg_c_3); +} + +static bool dr_mask_is_reg_c_4_7_set(struct mlx5dr_match_misc2 *misc2) +{ + return (misc2->metadata_reg_c_4 || misc2->metadata_reg_c_5 || + misc2->metadata_reg_c_6 || misc2->metadata_reg_c_7); +} + +static bool dr_mask_is_gvmi_or_qpn_set(struct mlx5dr_match_misc *misc) +{ + return (misc->source_sqn || misc->source_port); +} + +static bool +dr_matcher_supp_flex_parser_vxlan_gpe(struct mlx5dr_domain *dmn) +{ + return dmn->info.caps.flex_protocols & + MLX5_FLEX_PARSER_VXLAN_GPE_ENABLED; +} + +int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + bool ipv6) +{ + if (ipv6) { + nic_matcher->ste_builder = nic_matcher->ste_builder6; + nic_matcher->num_of_builders = nic_matcher->num_of_builders6; + } else { + nic_matcher->ste_builder = nic_matcher->ste_builder4; + nic_matcher->num_of_builders = nic_matcher->num_of_builders4; + } + + if (!nic_matcher->num_of_builders) { + mlx5dr_dbg(matcher->tbl->dmn, + "Rule not supported on this matcher due to IP related fields\n"); + return -EINVAL; + } + + return 0; +} + +static int dr_matcher_set_ste_builders(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + bool ipv6) +{ + struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_match_param mask = {}; + struct mlx5dr_match_misc3 *misc3; + struct mlx5dr_ste_build *sb; + u8 *num_of_builders; + bool inner, rx; + int idx = 0; + int ret, i; + + if (ipv6) { + sb = nic_matcher->ste_builder6; + num_of_builders = &nic_matcher->num_of_builders6; + } else { + sb = nic_matcher->ste_builder4; + num_of_builders = &nic_matcher->num_of_builders4; + } + + rx = nic_dmn->ste_type == MLX5DR_STE_TYPE_RX; + + /* Create a temporary mask to track and clear used mask fields */ + if (matcher->match_criteria & DR_MATCHER_CRITERIA_OUTER) + mask.outer = matcher->mask.outer; + + if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC) + mask.misc = matcher->mask.misc; + + if (matcher->match_criteria & DR_MATCHER_CRITERIA_INNER) + mask.inner = matcher->mask.inner; + + if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC2) + mask.misc2 = matcher->mask.misc2; + + if (matcher->match_criteria & DR_MATCHER_CRITERIA_MISC3) + mask.misc3 = matcher->mask.misc3; + + ret = mlx5dr_ste_build_pre_check(dmn, matcher->match_criteria, + &matcher->mask, NULL); + if (ret) + return ret; + + /* Outer */ + if (matcher->match_criteria & (DR_MATCHER_CRITERIA_OUTER | + DR_MATCHER_CRITERIA_MISC | + DR_MATCHER_CRITERIA_MISC2 | + DR_MATCHER_CRITERIA_MISC3)) { + inner = false; + + if (dr_mask_is_wqe_metadata_set(&mask.misc2)) + mlx5dr_ste_build_general_purpose(&sb[idx++], &mask, inner, rx); + + if (dr_mask_is_reg_c_0_3_set(&mask.misc2)) + mlx5dr_ste_build_register_0(&sb[idx++], &mask, inner, rx); + + if (dr_mask_is_reg_c_4_7_set(&mask.misc2)) + mlx5dr_ste_build_register_1(&sb[idx++], &mask, inner, rx); + + if (dr_mask_is_gvmi_or_qpn_set(&mask.misc) && + (dmn->type == MLX5DR_DOMAIN_TYPE_FDB || + dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX)) { + ret = mlx5dr_ste_build_src_gvmi_qpn(&sb[idx++], &mask, + &dmn->info.caps, + inner, rx); + if (ret) + return ret; + } + + if (dr_mask_is_smac_set(&mask.outer) && + dr_mask_is_dmac_set(&mask.outer)) { + ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], &mask, + inner, rx); + if (ret) + return ret; + } + + if (dr_mask_is_smac_set(&mask.outer)) + mlx5dr_ste_build_eth_l2_src(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_L2_DST(mask.outer, mask.misc, outer)) + mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx); + + if (ipv6) { + if (dr_mask_is_dst_addr_set(&mask.outer)) + mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask, + inner, rx); + + if (dr_mask_is_src_addr_set(&mask.outer)) + mlx5dr_ste_build_eth_l3_ipv6_src(&sb[idx++], &mask, + inner, rx); + + if (DR_MASK_IS_ETH_L4_SET(mask.outer, mask.misc, outer)) + mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask, + inner, rx); + } else { + if (dr_mask_is_ipv4_5_tuple_set(&mask.outer)) + mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask, + inner, rx); + + if (dr_mask_is_ttl_set(&mask.outer)) + mlx5dr_ste_build_eth_l3_ipv4_misc(&sb[idx++], &mask, + inner, rx); + } + + if (dr_mask_is_flex_parser_tnl_set(&mask.misc3) && + dr_matcher_supp_flex_parser_vxlan_gpe(dmn)) + mlx5dr_ste_build_flex_parser_tnl(&sb[idx++], &mask, + inner, rx); + + if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, outer)) + mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, outer)) + mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2)) + mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, + inner, rx); + + misc3 = &mask.misc3; + if ((DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc3) && + mlx5dr_matcher_supp_flex_parser_icmp_v4(&dmn->info.caps)) || + (dr_mask_is_flex_parser_icmpv6_set(&mask.misc3) && + mlx5dr_matcher_supp_flex_parser_icmp_v6(&dmn->info.caps))) { + ret = mlx5dr_ste_build_flex_parser_1(&sb[idx++], + &mask, &dmn->info.caps, + inner, rx); + if (ret) + return ret; + } + if (dr_mask_is_gre_set(&mask.misc)) + mlx5dr_ste_build_gre(&sb[idx++], &mask, inner, rx); + } + + /* Inner */ + if (matcher->match_criteria & (DR_MATCHER_CRITERIA_INNER | + DR_MATCHER_CRITERIA_MISC | + DR_MATCHER_CRITERIA_MISC2 | + DR_MATCHER_CRITERIA_MISC3)) { + inner = true; + + if (dr_mask_is_eth_l2_tnl_set(&mask.misc)) + mlx5dr_ste_build_eth_l2_tnl(&sb[idx++], &mask, inner, rx); + + if (dr_mask_is_smac_set(&mask.inner) && + dr_mask_is_dmac_set(&mask.inner)) { + ret = mlx5dr_ste_build_eth_l2_src_des(&sb[idx++], + &mask, inner, rx); + if (ret) + return ret; + } + + if (dr_mask_is_smac_set(&mask.inner)) + mlx5dr_ste_build_eth_l2_src(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_L2_DST(mask.inner, mask.misc, inner)) + mlx5dr_ste_build_eth_l2_dst(&sb[idx++], &mask, inner, rx); + + if (ipv6) { + if (dr_mask_is_dst_addr_set(&mask.inner)) + mlx5dr_ste_build_eth_l3_ipv6_dst(&sb[idx++], &mask, + inner, rx); + + if (dr_mask_is_src_addr_set(&mask.inner)) + mlx5dr_ste_build_eth_l3_ipv6_src(&sb[idx++], &mask, + inner, rx); + + if (DR_MASK_IS_ETH_L4_SET(mask.inner, mask.misc, inner)) + mlx5dr_ste_build_ipv6_l3_l4(&sb[idx++], &mask, + inner, rx); + } else { + if (dr_mask_is_ipv4_5_tuple_set(&mask.inner)) + mlx5dr_ste_build_eth_l3_ipv4_5_tuple(&sb[idx++], &mask, + inner, rx); + + if (dr_mask_is_ttl_set(&mask.inner)) + mlx5dr_ste_build_eth_l3_ipv4_misc(&sb[idx++], &mask, + inner, rx); + } + + if (DR_MASK_IS_ETH_L4_MISC_SET(mask.misc3, inner)) + mlx5dr_ste_build_eth_l4_misc(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_FIRST_MPLS_SET(mask.misc2, inner)) + mlx5dr_ste_build_mpls(&sb[idx++], &mask, inner, rx); + + if (DR_MASK_IS_FLEX_PARSER_0_SET(mask.misc2)) + mlx5dr_ste_build_flex_parser_0(&sb[idx++], &mask, inner, rx); + } + /* Empty matcher, takes all */ + if (matcher->match_criteria == DR_MATCHER_CRITERIA_EMPTY) + mlx5dr_ste_build_empty_always_hit(&sb[idx++], rx); + + if (idx == 0) { + mlx5dr_dbg(dmn, "Cannot generate any valid rules from mask\n"); + return -EINVAL; + } + + /* Check that all mask fields were consumed */ + for (i = 0; i < sizeof(struct mlx5dr_match_param); i++) { + if (((u8 *)&mask)[i] != 0) { + mlx5dr_info(dmn, "Mask contains unsupported parameters\n"); + return -EOPNOTSUPP; + } + } + + *num_of_builders = idx; + + return 0; +} + +static int dr_matcher_connect(struct mlx5dr_domain *dmn, + struct mlx5dr_matcher_rx_tx *curr_nic_matcher, + struct mlx5dr_matcher_rx_tx *next_nic_matcher, + struct mlx5dr_matcher_rx_tx *prev_nic_matcher) +{ + struct mlx5dr_table_rx_tx *nic_tbl = curr_nic_matcher->nic_tbl; + struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn; + struct mlx5dr_htbl_connect_info info; + struct mlx5dr_ste_htbl *prev_htbl; + int ret; + + /* Connect end anchor hash table to next_htbl or to the default address */ + if (next_nic_matcher) { + info.type = CONNECT_HIT; + info.hit_next_htbl = next_nic_matcher->s_htbl; + } else { + info.type = CONNECT_MISS; + info.miss_icm_addr = nic_tbl->default_icm_addr; + } + ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, + curr_nic_matcher->e_anchor, + &info, info.type == CONNECT_HIT); + if (ret) + return ret; + + /* Connect start hash table to end anchor */ + info.type = CONNECT_MISS; + info.miss_icm_addr = curr_nic_matcher->e_anchor->chunk->icm_addr; + ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, + curr_nic_matcher->s_htbl, + &info, false); + if (ret) + return ret; + + /* Connect previous hash table to matcher start hash table */ + if (prev_nic_matcher) + prev_htbl = prev_nic_matcher->e_anchor; + else + prev_htbl = nic_tbl->s_anchor; + + info.type = CONNECT_HIT; + info.hit_next_htbl = curr_nic_matcher->s_htbl; + ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, prev_htbl, + &info, true); + if (ret) + return ret; + + /* Update the pointing ste and next hash table */ + curr_nic_matcher->s_htbl->pointing_ste = prev_htbl->ste_arr; + prev_htbl->ste_arr[0].next_htbl = curr_nic_matcher->s_htbl; + + if (next_nic_matcher) { + next_nic_matcher->s_htbl->pointing_ste = curr_nic_matcher->e_anchor->ste_arr; + curr_nic_matcher->e_anchor->ste_arr[0].next_htbl = next_nic_matcher->s_htbl; + } + + return 0; +} + +static int dr_matcher_add_to_tbl(struct mlx5dr_matcher *matcher) +{ + struct mlx5dr_matcher *next_matcher, *prev_matcher, *tmp_matcher; + struct mlx5dr_table *tbl = matcher->tbl; + struct mlx5dr_domain *dmn = tbl->dmn; + bool first = true; + int ret; + + next_matcher = NULL; + if (!list_empty(&tbl->matcher_list)) + list_for_each_entry(tmp_matcher, &tbl->matcher_list, matcher_list) { + if (tmp_matcher->prio >= matcher->prio) { + next_matcher = tmp_matcher; + break; + } + first = false; + } + + prev_matcher = NULL; + if (next_matcher && !first) + prev_matcher = list_entry(next_matcher->matcher_list.prev, + struct mlx5dr_matcher, + matcher_list); + else if (!first) + prev_matcher = list_entry(tbl->matcher_list.prev, + struct mlx5dr_matcher, + matcher_list); + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB || + dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) { + ret = dr_matcher_connect(dmn, &matcher->rx, + next_matcher ? &next_matcher->rx : NULL, + prev_matcher ? &prev_matcher->rx : NULL); + if (ret) + return ret; + } + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB || + dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) { + ret = dr_matcher_connect(dmn, &matcher->tx, + next_matcher ? &next_matcher->tx : NULL, + prev_matcher ? &prev_matcher->tx : NULL); + if (ret) + return ret; + } + + if (prev_matcher) + list_add(&matcher->matcher_list, &prev_matcher->matcher_list); + else if (next_matcher) + list_add_tail(&matcher->matcher_list, + &next_matcher->matcher_list); + else + list_add(&matcher->matcher_list, &tbl->matcher_list); + + return 0; +} + +static void dr_matcher_uninit_nic(struct mlx5dr_matcher_rx_tx *nic_matcher) +{ + mlx5dr_htbl_put(nic_matcher->s_htbl); + mlx5dr_htbl_put(nic_matcher->e_anchor); +} + +static void dr_matcher_uninit_fdb(struct mlx5dr_matcher *matcher) +{ + dr_matcher_uninit_nic(&matcher->rx); + dr_matcher_uninit_nic(&matcher->tx); +} + +static void dr_matcher_uninit(struct mlx5dr_matcher *matcher) +{ + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + + switch (dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + dr_matcher_uninit_nic(&matcher->rx); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + dr_matcher_uninit_nic(&matcher->tx); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + dr_matcher_uninit_fdb(matcher); + break; + default: + WARN_ON(true); + break; + } +} + +static int dr_matcher_init_nic(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher) +{ + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + int ret, ret_v4, ret_v6; + + ret_v4 = dr_matcher_set_ste_builders(matcher, nic_matcher, false); + ret_v6 = dr_matcher_set_ste_builders(matcher, nic_matcher, true); + + if (ret_v4 && ret_v6) { + mlx5dr_dbg(dmn, "Cannot generate IPv4 or IPv6 rules with given mask\n"); + return -EINVAL; + } + + if (!ret_v4) + nic_matcher->ste_builder = nic_matcher->ste_builder4; + else + nic_matcher->ste_builder = nic_matcher->ste_builder6; + + nic_matcher->e_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + DR_CHUNK_SIZE_1, + MLX5DR_STE_LU_TYPE_DONT_CARE, + 0); + if (!nic_matcher->e_anchor) + return -ENOMEM; + + nic_matcher->s_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + DR_CHUNK_SIZE_1, + nic_matcher->ste_builder[0].lu_type, + nic_matcher->ste_builder[0].byte_mask); + if (!nic_matcher->s_htbl) { + ret = -ENOMEM; + goto free_e_htbl; + } + + /* make sure the tables exist while empty */ + mlx5dr_htbl_get(nic_matcher->s_htbl); + mlx5dr_htbl_get(nic_matcher->e_anchor); + + return 0; + +free_e_htbl: + mlx5dr_ste_htbl_free(nic_matcher->e_anchor); + return ret; +} + +static int dr_matcher_init_fdb(struct mlx5dr_matcher *matcher) +{ + int ret; + + ret = dr_matcher_init_nic(matcher, &matcher->rx); + if (ret) + return ret; + + ret = dr_matcher_init_nic(matcher, &matcher->tx); + if (ret) + goto uninit_nic_rx; + + return 0; + +uninit_nic_rx: + dr_matcher_uninit_nic(&matcher->rx); + return ret; +} + +static int dr_matcher_init(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *mask) +{ + struct mlx5dr_table *tbl = matcher->tbl; + struct mlx5dr_domain *dmn = tbl->dmn; + int ret; + + if (matcher->match_criteria >= DR_MATCHER_CRITERIA_MAX) { + mlx5dr_info(dmn, "Invalid match criteria attribute\n"); + return -EINVAL; + } + + if (mask) { + if (mask->match_sz > sizeof(struct mlx5dr_match_param)) { + mlx5dr_info(dmn, "Invalid match size attribute\n"); + return -EINVAL; + } + mlx5dr_ste_copy_param(matcher->match_criteria, + &matcher->mask, mask); + } + + switch (dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + matcher->rx.nic_tbl = &tbl->rx; + ret = dr_matcher_init_nic(matcher, &matcher->rx); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + matcher->tx.nic_tbl = &tbl->tx; + ret = dr_matcher_init_nic(matcher, &matcher->tx); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + matcher->rx.nic_tbl = &tbl->rx; + matcher->tx.nic_tbl = &tbl->tx; + ret = dr_matcher_init_fdb(matcher); + break; + default: + WARN_ON(true); + return -EINVAL; + } + + return ret; +} + +struct mlx5dr_matcher * +mlx5dr_matcher_create(struct mlx5dr_table *tbl, + u16 priority, + u8 match_criteria_enable, + struct mlx5dr_match_parameters *mask) +{ + struct mlx5dr_matcher *matcher; + int ret; + + refcount_inc(&tbl->refcount); + + matcher = kzalloc(sizeof(*matcher), GFP_KERNEL); + if (!matcher) + goto dec_ref; + + matcher->tbl = tbl; + matcher->prio = priority; + matcher->match_criteria = match_criteria_enable; + refcount_set(&matcher->refcount, 1); + INIT_LIST_HEAD(&matcher->matcher_list); + + mutex_lock(&tbl->dmn->mutex); + + ret = dr_matcher_init(matcher, mask); + if (ret) + goto free_matcher; + + ret = dr_matcher_add_to_tbl(matcher); + if (ret) + goto matcher_uninit; + + mutex_unlock(&tbl->dmn->mutex); + + return matcher; + +matcher_uninit: + dr_matcher_uninit(matcher); +free_matcher: + mutex_unlock(&tbl->dmn->mutex); + kfree(matcher); +dec_ref: + refcount_dec(&tbl->refcount); + return NULL; +} + +static int dr_matcher_disconnect(struct mlx5dr_domain *dmn, + struct mlx5dr_table_rx_tx *nic_tbl, + struct mlx5dr_matcher_rx_tx *next_nic_matcher, + struct mlx5dr_matcher_rx_tx *prev_nic_matcher) +{ + struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn; + struct mlx5dr_htbl_connect_info info; + struct mlx5dr_ste_htbl *prev_anchor; + + if (prev_nic_matcher) + prev_anchor = prev_nic_matcher->e_anchor; + else + prev_anchor = nic_tbl->s_anchor; + + /* Connect previous anchor hash table to next matcher or to the default address */ + if (next_nic_matcher) { + info.type = CONNECT_HIT; + info.hit_next_htbl = next_nic_matcher->s_htbl; + next_nic_matcher->s_htbl->pointing_ste = prev_anchor->ste_arr; + prev_anchor->ste_arr[0].next_htbl = next_nic_matcher->s_htbl; + } else { + info.type = CONNECT_MISS; + info.miss_icm_addr = nic_tbl->default_icm_addr; + prev_anchor->ste_arr[0].next_htbl = NULL; + } + + return mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, prev_anchor, + &info, true); +} + +static int dr_matcher_remove_from_tbl(struct mlx5dr_matcher *matcher) +{ + struct mlx5dr_matcher *prev_matcher, *next_matcher; + struct mlx5dr_table *tbl = matcher->tbl; + struct mlx5dr_domain *dmn = tbl->dmn; + int ret = 0; + + if (list_is_last(&matcher->matcher_list, &tbl->matcher_list)) + next_matcher = NULL; + else + next_matcher = list_next_entry(matcher, matcher_list); + + if (matcher->matcher_list.prev == &tbl->matcher_list) + prev_matcher = NULL; + else + prev_matcher = list_prev_entry(matcher, matcher_list); + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB || + dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX) { + ret = dr_matcher_disconnect(dmn, &tbl->rx, + next_matcher ? &next_matcher->rx : NULL, + prev_matcher ? &prev_matcher->rx : NULL); + if (ret) + return ret; + } + + if (dmn->type == MLX5DR_DOMAIN_TYPE_FDB || + dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX) { + ret = dr_matcher_disconnect(dmn, &tbl->tx, + next_matcher ? &next_matcher->tx : NULL, + prev_matcher ? &prev_matcher->tx : NULL); + if (ret) + return ret; + } + + list_del(&matcher->matcher_list); + + return 0; +} + +int mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher) +{ + struct mlx5dr_table *tbl = matcher->tbl; + + if (refcount_read(&matcher->refcount) > 1) + return -EBUSY; + + mutex_lock(&tbl->dmn->mutex); + + dr_matcher_remove_from_tbl(matcher); + dr_matcher_uninit(matcher); + refcount_dec(&matcher->tbl->refcount); + + mutex_unlock(&tbl->dmn->mutex); + kfree(matcher); + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c new file mode 100644 index 000000000000..3bc3f66b8fa8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c @@ -0,0 +1,1243 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +#define DR_RULE_MAX_STE_CHAIN (DR_RULE_MAX_STES + DR_ACTION_MAX_STES) + +struct mlx5dr_rule_action_member { + struct mlx5dr_action *action; + struct list_head list; +}; + +static int dr_rule_append_to_miss_list(struct mlx5dr_ste *new_last_ste, + struct list_head *miss_list, + struct list_head *send_list) +{ + struct mlx5dr_ste_send_info *ste_info_last; + struct mlx5dr_ste *last_ste; + + /* The new entry will be inserted after the last */ + last_ste = list_entry(miss_list->prev, struct mlx5dr_ste, miss_list_node); + WARN_ON(!last_ste); + + ste_info_last = kzalloc(sizeof(*ste_info_last), GFP_KERNEL); + if (!ste_info_last) + return -ENOMEM; + + mlx5dr_ste_set_miss_addr(last_ste->hw_ste, + mlx5dr_ste_get_icm_addr(new_last_ste)); + list_add_tail(&new_last_ste->miss_list_node, miss_list); + + mlx5dr_send_fill_and_append_ste_send_info(last_ste, DR_STE_SIZE_REDUCED, + 0, last_ste->hw_ste, + ste_info_last, send_list, true); + + return 0; +} + +static struct mlx5dr_ste * +dr_rule_create_collision_htbl(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + u8 *hw_ste) +{ + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_ste_htbl *new_htbl; + struct mlx5dr_ste *ste; + + /* Create new table for miss entry */ + new_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + DR_CHUNK_SIZE_1, + MLX5DR_STE_LU_TYPE_DONT_CARE, + 0); + if (!new_htbl) { + mlx5dr_dbg(dmn, "Failed allocating collision table\n"); + return NULL; + } + + /* One and only entry, never grows */ + ste = new_htbl->ste_arr; + mlx5dr_ste_set_miss_addr(hw_ste, nic_matcher->e_anchor->chunk->icm_addr); + mlx5dr_htbl_get(new_htbl); + + return ste; +} + +static struct mlx5dr_ste * +dr_rule_create_collision_entry(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + u8 *hw_ste, + struct mlx5dr_ste *orig_ste) +{ + struct mlx5dr_ste *ste; + + ste = dr_rule_create_collision_htbl(matcher, nic_matcher, hw_ste); + if (!ste) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed creating collision entry\n"); + return NULL; + } + + ste->ste_chain_location = orig_ste->ste_chain_location; + + /* In collision entry, all members share the same miss_list_head */ + ste->htbl->miss_list = mlx5dr_ste_get_miss_list(orig_ste); + + /* Next table */ + if (mlx5dr_ste_create_next_htbl(matcher, nic_matcher, ste, hw_ste, + DR_CHUNK_SIZE_1)) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed allocating table\n"); + goto free_tbl; + } + + return ste; + +free_tbl: + mlx5dr_ste_free(ste, matcher, nic_matcher); + return NULL; +} + +static int +dr_rule_handle_one_ste_in_update_list(struct mlx5dr_ste_send_info *ste_info, + struct mlx5dr_domain *dmn) +{ + int ret; + + list_del(&ste_info->send_list); + ret = mlx5dr_send_postsend_ste(dmn, ste_info->ste, ste_info->data, + ste_info->size, ste_info->offset); + if (ret) + goto out; + /* Copy data to ste, only reduced size, the last 16B (mask) + * is already written to the hw. + */ + memcpy(ste_info->ste->hw_ste, ste_info->data, DR_STE_SIZE_REDUCED); + +out: + kfree(ste_info); + return ret; +} + +static int dr_rule_send_update_list(struct list_head *send_ste_list, + struct mlx5dr_domain *dmn, + bool is_reverse) +{ + struct mlx5dr_ste_send_info *ste_info, *tmp_ste_info; + int ret; + + if (is_reverse) { + list_for_each_entry_safe_reverse(ste_info, tmp_ste_info, + send_ste_list, send_list) { + ret = dr_rule_handle_one_ste_in_update_list(ste_info, + dmn); + if (ret) + return ret; + } + } else { + list_for_each_entry_safe(ste_info, tmp_ste_info, + send_ste_list, send_list) { + ret = dr_rule_handle_one_ste_in_update_list(ste_info, + dmn); + if (ret) + return ret; + } + } + + return 0; +} + +static struct mlx5dr_ste * +dr_rule_find_ste_in_miss_list(struct list_head *miss_list, u8 *hw_ste) +{ + struct mlx5dr_ste *ste; + + if (list_empty(miss_list)) + return NULL; + + /* Check if hw_ste is present in the list */ + list_for_each_entry(ste, miss_list, miss_list_node) { + if (mlx5dr_ste_equal_tag(ste->hw_ste, hw_ste)) + return ste; + } + + return NULL; +} + +static struct mlx5dr_ste * +dr_rule_rehash_handle_collision(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct list_head *update_list, + struct mlx5dr_ste *col_ste, + u8 *hw_ste) +{ + struct mlx5dr_ste *new_ste; + int ret; + + new_ste = dr_rule_create_collision_htbl(matcher, nic_matcher, hw_ste); + if (!new_ste) + return NULL; + + /* In collision entry, all members share the same miss_list_head */ + new_ste->htbl->miss_list = mlx5dr_ste_get_miss_list(col_ste); + + /* Update the previous from the list */ + ret = dr_rule_append_to_miss_list(new_ste, + mlx5dr_ste_get_miss_list(col_ste), + update_list); + if (ret) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed update dup entry\n"); + goto err_exit; + } + + return new_ste; + +err_exit: + mlx5dr_ste_free(new_ste, matcher, nic_matcher); + return NULL; +} + +static void dr_rule_rehash_copy_ste_ctrl(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste *cur_ste, + struct mlx5dr_ste *new_ste) +{ + new_ste->next_htbl = cur_ste->next_htbl; + new_ste->ste_chain_location = cur_ste->ste_chain_location; + + if (!mlx5dr_ste_is_last_in_rule(nic_matcher, new_ste->ste_chain_location)) + new_ste->next_htbl->pointing_ste = new_ste; + + /* We need to copy the refcount since this ste + * may have been traversed several times + */ + refcount_set(&new_ste->refcount, refcount_read(&cur_ste->refcount)); + + /* Link old STEs rule_mem list to the new ste */ + mlx5dr_rule_update_rule_member(cur_ste, new_ste); + INIT_LIST_HEAD(&new_ste->rule_list); + list_splice_tail_init(&cur_ste->rule_list, &new_ste->rule_list); +} + +static struct mlx5dr_ste * +dr_rule_rehash_copy_ste(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste *cur_ste, + struct mlx5dr_ste_htbl *new_htbl, + struct list_head *update_list) +{ + struct mlx5dr_ste_send_info *ste_info; + bool use_update_list = false; + u8 hw_ste[DR_STE_SIZE] = {}; + struct mlx5dr_ste *new_ste; + int new_idx; + u8 sb_idx; + + /* Copy STE mask from the matcher */ + sb_idx = cur_ste->ste_chain_location - 1; + mlx5dr_ste_set_bit_mask(hw_ste, nic_matcher->ste_builder[sb_idx].bit_mask); + + /* Copy STE control and tag */ + memcpy(hw_ste, cur_ste->hw_ste, DR_STE_SIZE_REDUCED); + mlx5dr_ste_set_miss_addr(hw_ste, nic_matcher->e_anchor->chunk->icm_addr); + + new_idx = mlx5dr_ste_calc_hash_index(hw_ste, new_htbl); + new_ste = &new_htbl->ste_arr[new_idx]; + + if (mlx5dr_ste_not_used_ste(new_ste)) { + mlx5dr_htbl_get(new_htbl); + list_add_tail(&new_ste->miss_list_node, + mlx5dr_ste_get_miss_list(new_ste)); + } else { + new_ste = dr_rule_rehash_handle_collision(matcher, + nic_matcher, + update_list, + new_ste, + hw_ste); + if (!new_ste) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed adding collision entry, index: %d\n", + new_idx); + return NULL; + } + new_htbl->ctrl.num_of_collisions++; + use_update_list = true; + } + + memcpy(new_ste->hw_ste, hw_ste, DR_STE_SIZE_REDUCED); + + new_htbl->ctrl.num_of_valid_entries++; + + if (use_update_list) { + ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + if (!ste_info) + goto err_exit; + + mlx5dr_send_fill_and_append_ste_send_info(new_ste, DR_STE_SIZE, 0, + hw_ste, ste_info, + update_list, true); + } + + dr_rule_rehash_copy_ste_ctrl(matcher, nic_matcher, cur_ste, new_ste); + + return new_ste; + +err_exit: + mlx5dr_ste_free(new_ste, matcher, nic_matcher); + return NULL; +} + +static int dr_rule_rehash_copy_miss_list(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct list_head *cur_miss_list, + struct mlx5dr_ste_htbl *new_htbl, + struct list_head *update_list) +{ + struct mlx5dr_ste *tmp_ste, *cur_ste, *new_ste; + + if (list_empty(cur_miss_list)) + return 0; + + list_for_each_entry_safe(cur_ste, tmp_ste, cur_miss_list, miss_list_node) { + new_ste = dr_rule_rehash_copy_ste(matcher, + nic_matcher, + cur_ste, + new_htbl, + update_list); + if (!new_ste) + goto err_insert; + + list_del(&cur_ste->miss_list_node); + mlx5dr_htbl_put(cur_ste->htbl); + } + return 0; + +err_insert: + mlx5dr_err(matcher->tbl->dmn, "Fatal error during resize\n"); + WARN_ON(true); + return -EINVAL; +} + +static int dr_rule_rehash_copy_htbl(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste_htbl *cur_htbl, + struct mlx5dr_ste_htbl *new_htbl, + struct list_head *update_list) +{ + struct mlx5dr_ste *cur_ste; + int cur_entries; + int err = 0; + int i; + + cur_entries = mlx5dr_icm_pool_chunk_size_to_entries(cur_htbl->chunk_size); + + if (cur_entries < 1) { + mlx5dr_dbg(matcher->tbl->dmn, "Invalid number of entries\n"); + return -EINVAL; + } + + for (i = 0; i < cur_entries; i++) { + cur_ste = &cur_htbl->ste_arr[i]; + if (mlx5dr_ste_not_used_ste(cur_ste)) /* Empty, nothing to copy */ + continue; + + err = dr_rule_rehash_copy_miss_list(matcher, + nic_matcher, + mlx5dr_ste_get_miss_list(cur_ste), + new_htbl, + update_list); + if (err) + goto clean_copy; + } + +clean_copy: + return err; +} + +static struct mlx5dr_ste_htbl * +dr_rule_rehash_htbl(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule, + struct mlx5dr_ste_htbl *cur_htbl, + u8 ste_location, + struct list_head *update_list, + enum mlx5dr_icm_chunk_size new_size) +{ + struct mlx5dr_ste_send_info *del_ste_info, *tmp_ste_info; + struct mlx5dr_matcher *matcher = rule->matcher; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_matcher_rx_tx *nic_matcher; + struct mlx5dr_ste_send_info *ste_info; + struct mlx5dr_htbl_connect_info info; + struct mlx5dr_domain_rx_tx *nic_dmn; + u8 formatted_ste[DR_STE_SIZE] = {}; + LIST_HEAD(rehash_table_send_list); + struct mlx5dr_ste *ste_to_update; + struct mlx5dr_ste_htbl *new_htbl; + int err; + + nic_matcher = nic_rule->nic_matcher; + nic_dmn = nic_matcher->nic_tbl->nic_dmn; + + ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + if (!ste_info) + return NULL; + + new_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + new_size, + cur_htbl->lu_type, + cur_htbl->byte_mask); + if (!new_htbl) { + mlx5dr_err(dmn, "Failed to allocate new hash table\n"); + goto free_ste_info; + } + + /* Write new table to HW */ + info.type = CONNECT_MISS; + info.miss_icm_addr = nic_matcher->e_anchor->chunk->icm_addr; + mlx5dr_ste_set_formatted_ste(dmn->info.caps.gvmi, + nic_dmn, + new_htbl, + formatted_ste, + &info); + + new_htbl->pointing_ste = cur_htbl->pointing_ste; + new_htbl->pointing_ste->next_htbl = new_htbl; + err = dr_rule_rehash_copy_htbl(matcher, + nic_matcher, + cur_htbl, + new_htbl, + &rehash_table_send_list); + if (err) + goto free_new_htbl; + + if (mlx5dr_send_postsend_htbl(dmn, new_htbl, formatted_ste, + nic_matcher->ste_builder[ste_location - 1].bit_mask)) { + mlx5dr_err(dmn, "Failed writing table to HW\n"); + goto free_new_htbl; + } + + /* Writing to the hw is done in regular order of rehash_table_send_list, + * in order to have the origin data written before the miss address of + * collision entries, if exists. + */ + if (dr_rule_send_update_list(&rehash_table_send_list, dmn, false)) { + mlx5dr_err(dmn, "Failed updating table to HW\n"); + goto free_ste_list; + } + + /* Connect previous hash table to current */ + if (ste_location == 1) { + /* The previous table is an anchor, anchors size is always one STE */ + struct mlx5dr_ste_htbl *prev_htbl = cur_htbl->pointing_ste->htbl; + + /* On matcher s_anchor we keep an extra refcount */ + mlx5dr_htbl_get(new_htbl); + mlx5dr_htbl_put(cur_htbl); + + nic_matcher->s_htbl = new_htbl; + + /* It is safe to operate dr_ste_set_hit_addr on the hw_ste here + * (48B len) which works only on first 32B + */ + mlx5dr_ste_set_hit_addr(prev_htbl->ste_arr[0].hw_ste, + new_htbl->chunk->icm_addr, + new_htbl->chunk->num_of_entries); + + ste_to_update = &prev_htbl->ste_arr[0]; + } else { + mlx5dr_ste_set_hit_addr_by_next_htbl(cur_htbl->pointing_ste->hw_ste, + new_htbl); + ste_to_update = cur_htbl->pointing_ste; + } + + mlx5dr_send_fill_and_append_ste_send_info(ste_to_update, DR_STE_SIZE_REDUCED, + 0, ste_to_update->hw_ste, ste_info, + update_list, false); + + return new_htbl; + +free_ste_list: + /* Clean all ste_info's from the new table */ + list_for_each_entry_safe(del_ste_info, tmp_ste_info, + &rehash_table_send_list, send_list) { + list_del(&del_ste_info->send_list); + kfree(del_ste_info); + } + +free_new_htbl: + mlx5dr_ste_htbl_free(new_htbl); +free_ste_info: + kfree(ste_info); + mlx5dr_info(dmn, "Failed creating rehash table\n"); + return NULL; +} + +static struct mlx5dr_ste_htbl *dr_rule_rehash(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule, + struct mlx5dr_ste_htbl *cur_htbl, + u8 ste_location, + struct list_head *update_list) +{ + struct mlx5dr_domain *dmn = rule->matcher->tbl->dmn; + enum mlx5dr_icm_chunk_size new_size; + + new_size = mlx5dr_icm_next_higher_chunk(cur_htbl->chunk_size); + new_size = min_t(u32, new_size, dmn->info.max_log_sw_icm_sz); + + if (new_size == cur_htbl->chunk_size) + return NULL; /* Skip rehash, we already at the max size */ + + return dr_rule_rehash_htbl(rule, nic_rule, cur_htbl, ste_location, + update_list, new_size); +} + +static struct mlx5dr_ste * +dr_rule_handle_collision(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste *ste, + u8 *hw_ste, + struct list_head *miss_list, + struct list_head *send_list) +{ + struct mlx5dr_ste_send_info *ste_info; + struct mlx5dr_ste *new_ste; + + ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + if (!ste_info) + return NULL; + + new_ste = dr_rule_create_collision_entry(matcher, nic_matcher, hw_ste, ste); + if (!new_ste) + goto free_send_info; + + if (dr_rule_append_to_miss_list(new_ste, miss_list, send_list)) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed to update prev miss_list\n"); + goto err_exit; + } + + mlx5dr_send_fill_and_append_ste_send_info(new_ste, DR_STE_SIZE, 0, hw_ste, + ste_info, send_list, false); + + ste->htbl->ctrl.num_of_collisions++; + ste->htbl->ctrl.num_of_valid_entries++; + + return new_ste; + +err_exit: + mlx5dr_ste_free(new_ste, matcher, nic_matcher); +free_send_info: + kfree(ste_info); + return NULL; +} + +static void dr_rule_remove_action_members(struct mlx5dr_rule *rule) +{ + struct mlx5dr_rule_action_member *action_mem; + struct mlx5dr_rule_action_member *tmp; + + list_for_each_entry_safe(action_mem, tmp, &rule->rule_actions_list, list) { + list_del(&action_mem->list); + refcount_dec(&action_mem->action->refcount); + kvfree(action_mem); + } +} + +static int dr_rule_add_action_members(struct mlx5dr_rule *rule, + size_t num_actions, + struct mlx5dr_action *actions[]) +{ + struct mlx5dr_rule_action_member *action_mem; + int i; + + for (i = 0; i < num_actions; i++) { + action_mem = kvzalloc(sizeof(*action_mem), GFP_KERNEL); + if (!action_mem) + goto free_action_members; + + action_mem->action = actions[i]; + INIT_LIST_HEAD(&action_mem->list); + list_add_tail(&action_mem->list, &rule->rule_actions_list); + refcount_inc(&action_mem->action->refcount); + } + + return 0; + +free_action_members: + dr_rule_remove_action_members(rule); + return -ENOMEM; +} + +/* While the pointer of ste is no longer valid, like while moving ste to be + * the first in the miss_list, and to be in the origin table, + * all rule-members that are attached to this ste should update their ste member + * to the new pointer + */ +void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *ste, + struct mlx5dr_ste *new_ste) +{ + struct mlx5dr_rule_member *rule_mem; + + if (!list_empty(&ste->rule_list)) + list_for_each_entry(rule_mem, &ste->rule_list, use_ste_list) + rule_mem->ste = new_ste; +} + +static void dr_rule_clean_rule_members(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule) +{ + struct mlx5dr_rule_member *rule_mem; + struct mlx5dr_rule_member *tmp_mem; + + if (list_empty(&nic_rule->rule_members_list)) + return; + list_for_each_entry_safe(rule_mem, tmp_mem, &nic_rule->rule_members_list, list) { + list_del(&rule_mem->list); + list_del(&rule_mem->use_ste_list); + mlx5dr_ste_put(rule_mem->ste, rule->matcher, nic_rule->nic_matcher); + kvfree(rule_mem); + } +} + +static bool dr_rule_need_enlarge_hash(struct mlx5dr_ste_htbl *htbl, + struct mlx5dr_domain *dmn, + struct mlx5dr_domain_rx_tx *nic_dmn) +{ + struct mlx5dr_ste_htbl_ctrl *ctrl = &htbl->ctrl; + + if (dmn->info.max_log_sw_icm_sz <= htbl->chunk_size) + return false; + + if (!ctrl->may_grow) + return false; + + if (ctrl->num_of_collisions >= ctrl->increase_threshold && + (ctrl->num_of_valid_entries - ctrl->num_of_collisions) >= ctrl->increase_threshold) + return true; + + return false; +} + +static int dr_rule_add_member(struct mlx5dr_rule_rx_tx *nic_rule, + struct mlx5dr_ste *ste) +{ + struct mlx5dr_rule_member *rule_mem; + + rule_mem = kvzalloc(sizeof(*rule_mem), GFP_KERNEL); + if (!rule_mem) + return -ENOMEM; + + rule_mem->ste = ste; + list_add_tail(&rule_mem->list, &nic_rule->rule_members_list); + + list_add_tail(&rule_mem->use_ste_list, &ste->rule_list); + + return 0; +} + +static int dr_rule_handle_action_stes(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule, + struct list_head *send_ste_list, + struct mlx5dr_ste *last_ste, + u8 *hw_ste_arr, + u32 new_hw_ste_arr_sz) +{ + struct mlx5dr_matcher_rx_tx *nic_matcher = nic_rule->nic_matcher; + struct mlx5dr_ste_send_info *ste_info_arr[DR_ACTION_MAX_STES]; + u8 num_of_builders = nic_matcher->num_of_builders; + struct mlx5dr_matcher *matcher = rule->matcher; + u8 *curr_hw_ste, *prev_hw_ste; + struct mlx5dr_ste *action_ste; + int i, k, ret; + + /* Two cases: + * 1. num_of_builders is equal to new_hw_ste_arr_sz, the action in the ste + * 2. num_of_builders is less then new_hw_ste_arr_sz, new ste was added + * to support the action. + */ + if (num_of_builders == new_hw_ste_arr_sz) + return 0; + + for (i = num_of_builders, k = 0; i < new_hw_ste_arr_sz; i++, k++) { + curr_hw_ste = hw_ste_arr + i * DR_STE_SIZE; + prev_hw_ste = (i == 0) ? curr_hw_ste : hw_ste_arr + ((i - 1) * DR_STE_SIZE); + action_ste = dr_rule_create_collision_htbl(matcher, + nic_matcher, + curr_hw_ste); + if (!action_ste) + return -ENOMEM; + + mlx5dr_ste_get(action_ste); + + /* While free ste we go over the miss list, so add this ste to the list */ + list_add_tail(&action_ste->miss_list_node, + mlx5dr_ste_get_miss_list(action_ste)); + + ste_info_arr[k] = kzalloc(sizeof(*ste_info_arr[k]), + GFP_KERNEL); + if (!ste_info_arr[k]) + goto err_exit; + + /* Point current ste to the new action */ + mlx5dr_ste_set_hit_addr_by_next_htbl(prev_hw_ste, action_ste->htbl); + ret = dr_rule_add_member(nic_rule, action_ste); + if (ret) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed adding rule member\n"); + goto free_ste_info; + } + mlx5dr_send_fill_and_append_ste_send_info(action_ste, DR_STE_SIZE, 0, + curr_hw_ste, + ste_info_arr[k], + send_ste_list, false); + } + + return 0; + +free_ste_info: + kfree(ste_info_arr[k]); +err_exit: + mlx5dr_ste_put(action_ste, matcher, nic_matcher); + return -ENOMEM; +} + +static int dr_rule_handle_empty_entry(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste_htbl *cur_htbl, + struct mlx5dr_ste *ste, + u8 ste_location, + u8 *hw_ste, + struct list_head *miss_list, + struct list_head *send_list) +{ + struct mlx5dr_ste_send_info *ste_info; + + /* Take ref on table, only on first time this ste is used */ + mlx5dr_htbl_get(cur_htbl); + + /* new entry -> new branch */ + list_add_tail(&ste->miss_list_node, miss_list); + + mlx5dr_ste_set_miss_addr(hw_ste, nic_matcher->e_anchor->chunk->icm_addr); + + ste->ste_chain_location = ste_location; + + ste_info = kzalloc(sizeof(*ste_info), GFP_KERNEL); + if (!ste_info) + goto clean_ste_setting; + + if (mlx5dr_ste_create_next_htbl(matcher, + nic_matcher, + ste, + hw_ste, + DR_CHUNK_SIZE_1)) { + mlx5dr_dbg(matcher->tbl->dmn, "Failed allocating table\n"); + goto clean_ste_info; + } + + cur_htbl->ctrl.num_of_valid_entries++; + + mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE, 0, hw_ste, + ste_info, send_list, false); + + return 0; + +clean_ste_info: + kfree(ste_info); +clean_ste_setting: + list_del_init(&ste->miss_list_node); + mlx5dr_htbl_put(cur_htbl); + + return -ENOMEM; +} + +static struct mlx5dr_ste * +dr_rule_handle_ste_branch(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule, + struct list_head *send_ste_list, + struct mlx5dr_ste_htbl *cur_htbl, + u8 *hw_ste, + u8 ste_location, + struct mlx5dr_ste_htbl **put_htbl) +{ + struct mlx5dr_matcher *matcher = rule->matcher; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_matcher_rx_tx *nic_matcher; + struct mlx5dr_domain_rx_tx *nic_dmn; + struct mlx5dr_ste_htbl *new_htbl; + struct mlx5dr_ste *matched_ste; + struct list_head *miss_list; + bool skip_rehash = false; + struct mlx5dr_ste *ste; + int index; + + nic_matcher = nic_rule->nic_matcher; + nic_dmn = nic_matcher->nic_tbl->nic_dmn; + +again: + index = mlx5dr_ste_calc_hash_index(hw_ste, cur_htbl); + miss_list = &cur_htbl->chunk->miss_list[index]; + ste = &cur_htbl->ste_arr[index]; + + if (mlx5dr_ste_not_used_ste(ste)) { + if (dr_rule_handle_empty_entry(matcher, nic_matcher, cur_htbl, + ste, ste_location, + hw_ste, miss_list, + send_ste_list)) + return NULL; + } else { + /* Hash table index in use, check if this ste is in the miss list */ + matched_ste = dr_rule_find_ste_in_miss_list(miss_list, hw_ste); + if (matched_ste) { + /* If it is last STE in the chain, and has the same tag + * it means that all the previous stes are the same, + * if so, this rule is duplicated. + */ + if (mlx5dr_ste_is_last_in_rule(nic_matcher, + matched_ste->ste_chain_location)) { + mlx5dr_info(dmn, "Duplicate rule inserted, aborting!!\n"); + return NULL; + } + return matched_ste; + } + + if (!skip_rehash && dr_rule_need_enlarge_hash(cur_htbl, dmn, nic_dmn)) { + /* Hash table index in use, try to resize of the hash */ + skip_rehash = true; + + /* Hold the table till we update. + * Release in dr_rule_create_rule() + */ + *put_htbl = cur_htbl; + mlx5dr_htbl_get(cur_htbl); + + new_htbl = dr_rule_rehash(rule, nic_rule, cur_htbl, + ste_location, send_ste_list); + if (!new_htbl) { + mlx5dr_htbl_put(cur_htbl); + mlx5dr_info(dmn, "failed creating rehash table, htbl-log_size: %d\n", + cur_htbl->chunk_size); + } else { + cur_htbl = new_htbl; + } + goto again; + } else { + /* Hash table index in use, add another collision (miss) */ + ste = dr_rule_handle_collision(matcher, + nic_matcher, + ste, + hw_ste, + miss_list, + send_ste_list); + if (!ste) { + mlx5dr_dbg(dmn, "failed adding collision entry, index: %d\n", + index); + return NULL; + } + } + } + return ste; +} + +static bool dr_rule_cmp_value_to_mask(u8 *mask, u8 *value, + u32 s_idx, u32 e_idx) +{ + u32 i; + + for (i = s_idx; i < e_idx; i++) { + if (value[i] & ~mask[i]) { + pr_info("Rule parameters contains a value not specified by mask\n"); + return false; + } + } + return true; +} + +static bool dr_rule_verify(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *value, + struct mlx5dr_match_param *param) +{ + u8 match_criteria = matcher->match_criteria; + size_t value_size = value->match_sz; + u8 *mask_p = (u8 *)&matcher->mask; + u8 *param_p = (u8 *)param; + u32 s_idx, e_idx; + + if (!value_size || + (value_size > sizeof(struct mlx5dr_match_param) || + (value_size % sizeof(u32)))) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule parameters length is incorrect\n"); + return false; + } + + mlx5dr_ste_copy_param(matcher->match_criteria, param, value); + + if (match_criteria & DR_MATCHER_CRITERIA_OUTER) { + s_idx = offsetof(struct mlx5dr_match_param, outer); + e_idx = min(s_idx + sizeof(param->outer), value_size); + + if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule outer parameters contains a value not specified by mask\n"); + return false; + } + } + + if (match_criteria & DR_MATCHER_CRITERIA_MISC) { + s_idx = offsetof(struct mlx5dr_match_param, misc); + e_idx = min(s_idx + sizeof(param->misc), value_size); + + if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule misc parameters contains a value not specified by mask\n"); + return false; + } + } + + if (match_criteria & DR_MATCHER_CRITERIA_INNER) { + s_idx = offsetof(struct mlx5dr_match_param, inner); + e_idx = min(s_idx + sizeof(param->inner), value_size); + + if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule inner parameters contains a value not specified by mask\n"); + return false; + } + } + + if (match_criteria & DR_MATCHER_CRITERIA_MISC2) { + s_idx = offsetof(struct mlx5dr_match_param, misc2); + e_idx = min(s_idx + sizeof(param->misc2), value_size); + + if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule misc2 parameters contains a value not specified by mask\n"); + return false; + } + } + + if (match_criteria & DR_MATCHER_CRITERIA_MISC3) { + s_idx = offsetof(struct mlx5dr_match_param, misc3); + e_idx = min(s_idx + sizeof(param->misc3), value_size); + + if (!dr_rule_cmp_value_to_mask(mask_p, param_p, s_idx, e_idx)) { + mlx5dr_dbg(matcher->tbl->dmn, "Rule misc3 parameters contains a value not specified by mask\n"); + return false; + } + } + return true; +} + +static int dr_rule_destroy_rule_nic(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule) +{ + dr_rule_clean_rule_members(rule, nic_rule); + return 0; +} + +static int dr_rule_destroy_rule_fdb(struct mlx5dr_rule *rule) +{ + dr_rule_destroy_rule_nic(rule, &rule->rx); + dr_rule_destroy_rule_nic(rule, &rule->tx); + return 0; +} + +static int dr_rule_destroy_rule(struct mlx5dr_rule *rule) +{ + struct mlx5dr_domain *dmn = rule->matcher->tbl->dmn; + + switch (dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + dr_rule_destroy_rule_nic(rule, &rule->rx); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + dr_rule_destroy_rule_nic(rule, &rule->tx); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + dr_rule_destroy_rule_fdb(rule); + break; + default: + return -EINVAL; + } + + dr_rule_remove_action_members(rule); + kfree(rule); + return 0; +} + +static bool dr_rule_is_ipv6(struct mlx5dr_match_param *param) +{ + return (param->outer.ip_version == 6 || + param->inner.ip_version == 6 || + param->outer.ethertype == ETH_P_IPV6 || + param->inner.ethertype == ETH_P_IPV6); +} + +static bool dr_rule_skip(enum mlx5dr_domain_type domain, + enum mlx5dr_ste_entry_type ste_type, + struct mlx5dr_match_param *mask, + struct mlx5dr_match_param *value) +{ + if (domain != MLX5DR_DOMAIN_TYPE_FDB) + return false; + + if (mask->misc.source_port) { + if (ste_type == MLX5DR_STE_TYPE_RX) + if (value->misc.source_port != WIRE_PORT) + return true; + + if (ste_type == MLX5DR_STE_TYPE_TX) + if (value->misc.source_port == WIRE_PORT) + return true; + } + + /* Metadata C can be used to describe the source vport */ + if (mask->misc2.metadata_reg_c_0) { + if (ste_type == MLX5DR_STE_TYPE_RX) + if ((value->misc2.metadata_reg_c_0 & WIRE_PORT) != WIRE_PORT) + return true; + + if (ste_type == MLX5DR_STE_TYPE_TX) + if ((value->misc2.metadata_reg_c_0 & WIRE_PORT) == WIRE_PORT) + return true; + } + return false; +} + +static int +dr_rule_create_rule_nic(struct mlx5dr_rule *rule, + struct mlx5dr_rule_rx_tx *nic_rule, + struct mlx5dr_match_param *param, + size_t num_actions, + struct mlx5dr_action *actions[]) +{ + struct mlx5dr_ste_send_info *ste_info, *tmp_ste_info; + struct mlx5dr_matcher *matcher = rule->matcher; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_matcher_rx_tx *nic_matcher; + struct mlx5dr_domain_rx_tx *nic_dmn; + struct mlx5dr_ste_htbl *htbl = NULL; + struct mlx5dr_ste_htbl *cur_htbl; + struct mlx5dr_ste *ste = NULL; + LIST_HEAD(send_ste_list); + u8 *hw_ste_arr = NULL; + u32 new_hw_ste_arr_sz; + int ret, i; + + nic_matcher = nic_rule->nic_matcher; + nic_dmn = nic_matcher->nic_tbl->nic_dmn; + + INIT_LIST_HEAD(&nic_rule->rule_members_list); + + if (dr_rule_skip(dmn->type, nic_dmn->ste_type, &matcher->mask, param)) + return 0; + + ret = mlx5dr_matcher_select_builders(matcher, + nic_matcher, + dr_rule_is_ipv6(param)); + if (ret) + goto out_err; + + hw_ste_arr = kzalloc(DR_RULE_MAX_STE_CHAIN * DR_STE_SIZE, GFP_KERNEL); + if (!hw_ste_arr) { + ret = -ENOMEM; + goto out_err; + } + + /* Set the tag values inside the ste array */ + ret = mlx5dr_ste_build_ste_arr(matcher, nic_matcher, param, hw_ste_arr); + if (ret) + goto free_hw_ste; + + /* Set the actions values/addresses inside the ste array */ + ret = mlx5dr_actions_build_ste_arr(matcher, nic_matcher, actions, + num_actions, hw_ste_arr, + &new_hw_ste_arr_sz); + if (ret) + goto free_hw_ste; + + cur_htbl = nic_matcher->s_htbl; + + /* Go over the array of STEs, and build dr_ste accordingly. + * The loop is over only the builders which are equal or less to the + * number of stes, in case we have actions that lives in other stes. + */ + for (i = 0; i < nic_matcher->num_of_builders; i++) { + /* Calculate CRC and keep new ste entry */ + u8 *cur_hw_ste_ent = hw_ste_arr + (i * DR_STE_SIZE); + + ste = dr_rule_handle_ste_branch(rule, + nic_rule, + &send_ste_list, + cur_htbl, + cur_hw_ste_ent, + i + 1, + &htbl); + if (!ste) { + mlx5dr_err(dmn, "Failed creating next branch\n"); + ret = -ENOENT; + goto free_rule; + } + + cur_htbl = ste->next_htbl; + + /* Keep all STEs in the rule struct */ + ret = dr_rule_add_member(nic_rule, ste); + if (ret) { + mlx5dr_dbg(dmn, "Failed adding rule member index %d\n", i); + goto free_ste; + } + + mlx5dr_ste_get(ste); + } + + /* Connect actions */ + ret = dr_rule_handle_action_stes(rule, nic_rule, &send_ste_list, + ste, hw_ste_arr, new_hw_ste_arr_sz); + if (ret) { + mlx5dr_dbg(dmn, "Failed apply actions\n"); + goto free_rule; + } + ret = dr_rule_send_update_list(&send_ste_list, dmn, true); + if (ret) { + mlx5dr_err(dmn, "Failed sending ste!\n"); + goto free_rule; + } + + if (htbl) + mlx5dr_htbl_put(htbl); + + return 0; + +free_ste: + mlx5dr_ste_put(ste, matcher, nic_matcher); +free_rule: + dr_rule_clean_rule_members(rule, nic_rule); + /* Clean all ste_info's */ + list_for_each_entry_safe(ste_info, tmp_ste_info, &send_ste_list, send_list) { + list_del(&ste_info->send_list); + kfree(ste_info); + } +free_hw_ste: + kfree(hw_ste_arr); +out_err: + return ret; +} + +static int +dr_rule_create_rule_fdb(struct mlx5dr_rule *rule, + struct mlx5dr_match_param *param, + size_t num_actions, + struct mlx5dr_action *actions[]) +{ + struct mlx5dr_match_param copy_param = {}; + int ret; + + /* Copy match_param since they will be consumed during the first + * nic_rule insertion. + */ + memcpy(©_param, param, sizeof(struct mlx5dr_match_param)); + + ret = dr_rule_create_rule_nic(rule, &rule->rx, param, + num_actions, actions); + if (ret) + return ret; + + ret = dr_rule_create_rule_nic(rule, &rule->tx, ©_param, + num_actions, actions); + if (ret) + goto destroy_rule_nic_rx; + + return 0; + +destroy_rule_nic_rx: + dr_rule_destroy_rule_nic(rule, &rule->rx); + return ret; +} + +static struct mlx5dr_rule * +dr_rule_create_rule(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *value, + size_t num_actions, + struct mlx5dr_action *actions[]) +{ + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_match_param param = {}; + struct mlx5dr_rule *rule; + int ret; + + if (!dr_rule_verify(matcher, value, ¶m)) + return NULL; + + rule = kzalloc(sizeof(*rule), GFP_KERNEL); + if (!rule) + return NULL; + + rule->matcher = matcher; + INIT_LIST_HEAD(&rule->rule_actions_list); + + ret = dr_rule_add_action_members(rule, num_actions, actions); + if (ret) + goto free_rule; + + switch (dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + rule->rx.nic_matcher = &matcher->rx; + ret = dr_rule_create_rule_nic(rule, &rule->rx, ¶m, + num_actions, actions); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + rule->tx.nic_matcher = &matcher->tx; + ret = dr_rule_create_rule_nic(rule, &rule->tx, ¶m, + num_actions, actions); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + rule->rx.nic_matcher = &matcher->rx; + rule->tx.nic_matcher = &matcher->tx; + ret = dr_rule_create_rule_fdb(rule, ¶m, + num_actions, actions); + break; + default: + ret = -EINVAL; + break; + } + + if (ret) + goto remove_action_members; + + return rule; + +remove_action_members: + dr_rule_remove_action_members(rule); +free_rule: + kfree(rule); + mlx5dr_info(dmn, "Failed creating rule\n"); + return NULL; +} + +struct mlx5dr_rule *mlx5dr_rule_create(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *value, + size_t num_actions, + struct mlx5dr_action *actions[]) +{ + struct mlx5dr_rule *rule; + + mutex_lock(&matcher->tbl->dmn->mutex); + refcount_inc(&matcher->refcount); + + rule = dr_rule_create_rule(matcher, value, num_actions, actions); + if (!rule) + refcount_dec(&matcher->refcount); + + mutex_unlock(&matcher->tbl->dmn->mutex); + + return rule; +} + +int mlx5dr_rule_destroy(struct mlx5dr_rule *rule) +{ + struct mlx5dr_matcher *matcher = rule->matcher; + struct mlx5dr_table *tbl = rule->matcher->tbl; + int ret; + + mutex_lock(&tbl->dmn->mutex); + + ret = dr_rule_destroy_rule(rule); + + mutex_unlock(&tbl->dmn->mutex); + + if (!ret) + refcount_dec(&matcher->refcount); + return ret; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c new file mode 100644 index 000000000000..5df8436b2ae3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_send.c @@ -0,0 +1,975 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +#define QUEUE_SIZE 128 +#define SIGNAL_PER_DIV_QUEUE 16 +#define TH_NUMS_TO_DRAIN 2 + +enum { CQ_OK = 0, CQ_EMPTY = -1, CQ_POLL_ERR = -2 }; + +struct dr_data_seg { + u64 addr; + u32 length; + u32 lkey; + unsigned int send_flags; +}; + +struct postsend_info { + struct dr_data_seg write; + struct dr_data_seg read; + u64 remote_addr; + u32 rkey; +}; + +struct dr_qp_rtr_attr { + struct mlx5dr_cmd_gid_attr dgid_attr; + enum ib_mtu mtu; + u32 qp_num; + u16 port_num; + u8 min_rnr_timer; + u8 sgid_index; + u16 udp_src_port; +}; + +struct dr_qp_rts_attr { + u8 timeout; + u8 retry_cnt; + u8 rnr_retry; +}; + +struct dr_qp_init_attr { + u32 cqn; + u32 pdn; + u32 max_send_wr; + struct mlx5_uars_page *uar; +}; + +static int dr_parse_cqe(struct mlx5dr_cq *dr_cq, struct mlx5_cqe64 *cqe64) +{ + unsigned int idx; + u8 opcode; + + opcode = get_cqe_opcode(cqe64); + if (opcode == MLX5_CQE_REQ_ERR) { + idx = be16_to_cpu(cqe64->wqe_counter) & + (dr_cq->qp->sq.wqe_cnt - 1); + dr_cq->qp->sq.cc = dr_cq->qp->sq.wqe_head[idx] + 1; + } else if (opcode == MLX5_CQE_RESP_ERR) { + ++dr_cq->qp->sq.cc; + } else { + idx = be16_to_cpu(cqe64->wqe_counter) & + (dr_cq->qp->sq.wqe_cnt - 1); + dr_cq->qp->sq.cc = dr_cq->qp->sq.wqe_head[idx] + 1; + + return CQ_OK; + } + + return CQ_POLL_ERR; +} + +static int dr_cq_poll_one(struct mlx5dr_cq *dr_cq) +{ + struct mlx5_cqe64 *cqe64; + int err; + + cqe64 = mlx5_cqwq_get_cqe(&dr_cq->wq); + if (!cqe64) + return CQ_EMPTY; + + mlx5_cqwq_pop(&dr_cq->wq); + err = dr_parse_cqe(dr_cq, cqe64); + mlx5_cqwq_update_db_record(&dr_cq->wq); + + return err; +} + +static int dr_poll_cq(struct mlx5dr_cq *dr_cq, int ne) +{ + int npolled; + int err = 0; + + for (npolled = 0; npolled < ne; ++npolled) { + err = dr_cq_poll_one(dr_cq); + if (err != CQ_OK) + break; + } + + return err == CQ_POLL_ERR ? err : npolled; +} + +static void dr_qp_event(struct mlx5_core_qp *mqp, int event) +{ + pr_info("DR QP event %u on QP #%u\n", event, mqp->qpn); +} + +static struct mlx5dr_qp *dr_create_rc_qp(struct mlx5_core_dev *mdev, + struct dr_qp_init_attr *attr) +{ + u32 temp_qpc[MLX5_ST_SZ_DW(qpc)] = {}; + struct mlx5_wq_param wqp; + struct mlx5dr_qp *dr_qp; + int inlen; + void *qpc; + void *in; + int err; + + dr_qp = kzalloc(sizeof(*dr_qp), GFP_KERNEL); + if (!dr_qp) + return NULL; + + wqp.buf_numa_node = mdev->priv.numa_node; + wqp.db_numa_node = mdev->priv.numa_node; + + dr_qp->rq.pc = 0; + dr_qp->rq.cc = 0; + dr_qp->rq.wqe_cnt = 4; + dr_qp->sq.pc = 0; + dr_qp->sq.cc = 0; + dr_qp->sq.wqe_cnt = roundup_pow_of_two(attr->max_send_wr); + + MLX5_SET(qpc, temp_qpc, log_rq_stride, ilog2(MLX5_SEND_WQE_DS) - 4); + MLX5_SET(qpc, temp_qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt)); + MLX5_SET(qpc, temp_qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt)); + err = mlx5_wq_qp_create(mdev, &wqp, temp_qpc, &dr_qp->wq, + &dr_qp->wq_ctrl); + if (err) { + mlx5_core_info(mdev, "Can't create QP WQ\n"); + goto err_wq; + } + + dr_qp->sq.wqe_head = kcalloc(dr_qp->sq.wqe_cnt, + sizeof(dr_qp->sq.wqe_head[0]), + GFP_KERNEL); + + if (!dr_qp->sq.wqe_head) { + mlx5_core_warn(mdev, "Can't allocate wqe head\n"); + goto err_wqe_head; + } + + inlen = MLX5_ST_SZ_BYTES(create_qp_in) + + MLX5_FLD_SZ_BYTES(create_qp_in, pas[0]) * + dr_qp->wq_ctrl.buf.npages; + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) { + err = -ENOMEM; + goto err_in; + } + + qpc = MLX5_ADDR_OF(create_qp_in, in, qpc); + MLX5_SET(qpc, qpc, st, MLX5_QP_ST_RC); + MLX5_SET(qpc, qpc, pm_state, MLX5_QP_PM_MIGRATED); + MLX5_SET(qpc, qpc, pd, attr->pdn); + MLX5_SET(qpc, qpc, uar_page, attr->uar->index); + MLX5_SET(qpc, qpc, log_page_size, + dr_qp->wq_ctrl.buf.page_shift - MLX5_ADAPTER_PAGE_SHIFT); + MLX5_SET(qpc, qpc, fre, 1); + MLX5_SET(qpc, qpc, rlky, 1); + MLX5_SET(qpc, qpc, cqn_snd, attr->cqn); + MLX5_SET(qpc, qpc, cqn_rcv, attr->cqn); + MLX5_SET(qpc, qpc, log_rq_stride, ilog2(MLX5_SEND_WQE_DS) - 4); + MLX5_SET(qpc, qpc, log_rq_size, ilog2(dr_qp->rq.wqe_cnt)); + MLX5_SET(qpc, qpc, rq_type, MLX5_NON_ZERO_RQ); + MLX5_SET(qpc, qpc, log_sq_size, ilog2(dr_qp->sq.wqe_cnt)); + MLX5_SET64(qpc, qpc, dbr_addr, dr_qp->wq_ctrl.db.dma); + if (MLX5_CAP_GEN(mdev, cqe_version) == 1) + MLX5_SET(qpc, qpc, user_index, 0xFFFFFF); + mlx5_fill_page_frag_array(&dr_qp->wq_ctrl.buf, + (__be64 *)MLX5_ADDR_OF(create_qp_in, + in, pas)); + + err = mlx5_core_create_qp(mdev, &dr_qp->mqp, in, inlen); + kfree(in); + + if (err) { + mlx5_core_warn(mdev, " Can't create QP\n"); + goto err_in; + } + dr_qp->mqp.event = dr_qp_event; + dr_qp->uar = attr->uar; + + return dr_qp; + +err_in: + kfree(dr_qp->sq.wqe_head); +err_wqe_head: + mlx5_wq_destroy(&dr_qp->wq_ctrl); +err_wq: + kfree(dr_qp); + return NULL; +} + +static void dr_destroy_qp(struct mlx5_core_dev *mdev, + struct mlx5dr_qp *dr_qp) +{ + mlx5_core_destroy_qp(mdev, &dr_qp->mqp); + kfree(dr_qp->sq.wqe_head); + mlx5_wq_destroy(&dr_qp->wq_ctrl); + kfree(dr_qp); +} + +static void dr_cmd_notify_hw(struct mlx5dr_qp *dr_qp, void *ctrl) +{ + dma_wmb(); + *dr_qp->wq.sq.db = cpu_to_be32(dr_qp->sq.pc & 0xfffff); + + /* After wmb() the hw aware of new work */ + wmb(); + + mlx5_write64(ctrl, dr_qp->uar->map + MLX5_BF_OFFSET); +} + +static void dr_rdma_segments(struct mlx5dr_qp *dr_qp, u64 remote_addr, + u32 rkey, struct dr_data_seg *data_seg, + u32 opcode, int nreq) +{ + struct mlx5_wqe_raddr_seg *wq_raddr; + struct mlx5_wqe_ctrl_seg *wq_ctrl; + struct mlx5_wqe_data_seg *wq_dseg; + unsigned int size; + unsigned int idx; + + size = sizeof(*wq_ctrl) / 16 + sizeof(*wq_dseg) / 16 + + sizeof(*wq_raddr) / 16; + + idx = dr_qp->sq.pc & (dr_qp->sq.wqe_cnt - 1); + + wq_ctrl = mlx5_wq_cyc_get_wqe(&dr_qp->wq.sq, idx); + wq_ctrl->imm = 0; + wq_ctrl->fm_ce_se = (data_seg->send_flags) ? + MLX5_WQE_CTRL_CQ_UPDATE : 0; + wq_ctrl->opmod_idx_opcode = cpu_to_be32(((dr_qp->sq.pc & 0xffff) << 8) | + opcode); + wq_ctrl->qpn_ds = cpu_to_be32(size | dr_qp->mqp.qpn << 8); + wq_raddr = (void *)(wq_ctrl + 1); + wq_raddr->raddr = cpu_to_be64(remote_addr); + wq_raddr->rkey = cpu_to_be32(rkey); + wq_raddr->reserved = 0; + + wq_dseg = (void *)(wq_raddr + 1); + wq_dseg->byte_count = cpu_to_be32(data_seg->length); + wq_dseg->lkey = cpu_to_be32(data_seg->lkey); + wq_dseg->addr = cpu_to_be64(data_seg->addr); + + dr_qp->sq.wqe_head[idx] = dr_qp->sq.pc++; + + if (nreq) + dr_cmd_notify_hw(dr_qp, wq_ctrl); +} + +static void dr_post_send(struct mlx5dr_qp *dr_qp, struct postsend_info *send_info) +{ + dr_rdma_segments(dr_qp, send_info->remote_addr, send_info->rkey, + &send_info->write, MLX5_OPCODE_RDMA_WRITE, 0); + dr_rdma_segments(dr_qp, send_info->remote_addr, send_info->rkey, + &send_info->read, MLX5_OPCODE_RDMA_READ, 1); +} + +/** + * mlx5dr_send_fill_and_append_ste_send_info: Add data to be sent + * with send_list parameters: + * + * @ste: The data that attached to this specific ste + * @size: of data to write + * @offset: of the data from start of the hw_ste entry + * @data: data + * @ste_info: ste to be sent with send_list + * @send_list: to append into it + * @copy_data: if true indicates that the data should be kept because + * it's not backuped any where (like in re-hash). + * if false, it lets the data to be updated after + * it was added to the list. + */ +void mlx5dr_send_fill_and_append_ste_send_info(struct mlx5dr_ste *ste, u16 size, + u16 offset, u8 *data, + struct mlx5dr_ste_send_info *ste_info, + struct list_head *send_list, + bool copy_data) +{ + ste_info->size = size; + ste_info->ste = ste; + ste_info->offset = offset; + + if (copy_data) { + memcpy(ste_info->data_cont, data, size); + ste_info->data = ste_info->data_cont; + } else { + ste_info->data = data; + } + + list_add_tail(&ste_info->send_list, send_list); +} + +/* The function tries to consume one wc each time, unless the queue is full, in + * that case, which means that the hw is behind the sw in a full queue len + * the function will drain the cq till it empty. + */ +static int dr_handle_pending_wc(struct mlx5dr_domain *dmn, + struct mlx5dr_send_ring *send_ring) +{ + bool is_drain = false; + int ne; + + if (send_ring->pending_wqe < send_ring->signal_th) + return 0; + + /* Queue is full start drain it */ + if (send_ring->pending_wqe >= + dmn->send_ring->signal_th * TH_NUMS_TO_DRAIN) + is_drain = true; + + do { + ne = dr_poll_cq(send_ring->cq, 1); + if (ne < 0) + return ne; + else if (ne == 1) + send_ring->pending_wqe -= send_ring->signal_th; + } while (is_drain && send_ring->pending_wqe); + + return 0; +} + +static void dr_fill_data_segs(struct mlx5dr_send_ring *send_ring, + struct postsend_info *send_info) +{ + send_ring->pending_wqe++; + + if (send_ring->pending_wqe % send_ring->signal_th == 0) + send_info->write.send_flags |= IB_SEND_SIGNALED; + + send_ring->pending_wqe++; + send_info->read.length = send_info->write.length; + /* Read into the same write area */ + send_info->read.addr = (uintptr_t)send_info->write.addr; + send_info->read.lkey = send_ring->mr->mkey.key; + + if (send_ring->pending_wqe % send_ring->signal_th == 0) + send_info->read.send_flags = IB_SEND_SIGNALED; + else + send_info->read.send_flags = 0; +} + +static int dr_postsend_icm_data(struct mlx5dr_domain *dmn, + struct postsend_info *send_info) +{ + struct mlx5dr_send_ring *send_ring = dmn->send_ring; + u32 buff_offset; + int ret; + + ret = dr_handle_pending_wc(dmn, send_ring); + if (ret) + return ret; + + if (send_info->write.length > dmn->info.max_inline_size) { + buff_offset = (send_ring->tx_head & + (dmn->send_ring->signal_th - 1)) * + send_ring->max_post_send_size; + /* Copy to ring mr */ + memcpy(send_ring->buf + buff_offset, + (void *)(uintptr_t)send_info->write.addr, + send_info->write.length); + send_info->write.addr = (uintptr_t)send_ring->mr->dma_addr + buff_offset; + send_info->write.lkey = send_ring->mr->mkey.key; + } + + send_ring->tx_head++; + dr_fill_data_segs(send_ring, send_info); + dr_post_send(send_ring->qp, send_info); + + return 0; +} + +static int dr_get_tbl_copy_details(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_htbl *htbl, + u8 **data, + u32 *byte_size, + int *iterations, + int *num_stes) +{ + int alloc_size; + + if (htbl->chunk->byte_size > dmn->send_ring->max_post_send_size) { + *iterations = htbl->chunk->byte_size / + dmn->send_ring->max_post_send_size; + *byte_size = dmn->send_ring->max_post_send_size; + alloc_size = *byte_size; + *num_stes = *byte_size / DR_STE_SIZE; + } else { + *iterations = 1; + *num_stes = htbl->chunk->num_of_entries; + alloc_size = *num_stes * DR_STE_SIZE; + } + + *data = kzalloc(alloc_size, GFP_KERNEL); + if (!*data) + return -ENOMEM; + + return 0; +} + +/** + * mlx5dr_send_postsend_ste: write size bytes into offset from the hw cm. + * + * @dmn: Domain + * @ste: The ste struct that contains the data (at + * least part of it) + * @data: The real data to send size data + * @size: for writing. + * @offset: The offset from the icm mapped data to + * start write to this for write only part of the + * buffer. + * + * Return: 0 on success. + */ +int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn, struct mlx5dr_ste *ste, + u8 *data, u16 size, u16 offset) +{ + struct postsend_info send_info = {}; + + send_info.write.addr = (uintptr_t)data; + send_info.write.length = size; + send_info.write.lkey = 0; + send_info.remote_addr = mlx5dr_ste_get_mr_addr(ste) + offset; + send_info.rkey = ste->htbl->chunk->rkey; + + return dr_postsend_icm_data(dmn, &send_info); +} + +int mlx5dr_send_postsend_htbl(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *formatted_ste, u8 *mask) +{ + u32 byte_size = htbl->chunk->byte_size; + int num_stes_per_iter; + int iterations; + u8 *data; + int ret; + int i; + int j; + + ret = dr_get_tbl_copy_details(dmn, htbl, &data, &byte_size, + &iterations, &num_stes_per_iter); + if (ret) + return ret; + + /* Send the data iteration times */ + for (i = 0; i < iterations; i++) { + u32 ste_index = i * (byte_size / DR_STE_SIZE); + struct postsend_info send_info = {}; + + /* Copy all ste's on the data buffer + * need to add the bit_mask + */ + for (j = 0; j < num_stes_per_iter; j++) { + u8 *hw_ste = htbl->ste_arr[ste_index + j].hw_ste; + u32 ste_off = j * DR_STE_SIZE; + + if (mlx5dr_ste_is_not_valid_entry(hw_ste)) { + memcpy(data + ste_off, + formatted_ste, DR_STE_SIZE); + } else { + /* Copy data */ + memcpy(data + ste_off, + htbl->ste_arr[ste_index + j].hw_ste, + DR_STE_SIZE_REDUCED); + /* Copy bit_mask */ + memcpy(data + ste_off + DR_STE_SIZE_REDUCED, + mask, DR_STE_SIZE_MASK); + } + } + + send_info.write.addr = (uintptr_t)data; + send_info.write.length = byte_size; + send_info.write.lkey = 0; + send_info.remote_addr = + mlx5dr_ste_get_mr_addr(htbl->ste_arr + ste_index); + send_info.rkey = htbl->chunk->rkey; + + ret = dr_postsend_icm_data(dmn, &send_info); + if (ret) + goto out_free; + } + +out_free: + kfree(data); + return ret; +} + +/* Initialize htble with default STEs */ +int mlx5dr_send_postsend_formatted_htbl(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *ste_init_data, + bool update_hw_ste) +{ + u32 byte_size = htbl->chunk->byte_size; + int iterations; + int num_stes; + u8 *data; + int ret; + int i; + + ret = dr_get_tbl_copy_details(dmn, htbl, &data, &byte_size, + &iterations, &num_stes); + if (ret) + return ret; + + for (i = 0; i < num_stes; i++) { + u8 *copy_dst; + + /* Copy the same ste on the data buffer */ + copy_dst = data + i * DR_STE_SIZE; + memcpy(copy_dst, ste_init_data, DR_STE_SIZE); + + if (update_hw_ste) { + /* Copy the reduced ste to hash table ste_arr */ + copy_dst = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED; + memcpy(copy_dst, ste_init_data, DR_STE_SIZE_REDUCED); + } + } + + /* Send the data iteration times */ + for (i = 0; i < iterations; i++) { + u8 ste_index = i * (byte_size / DR_STE_SIZE); + struct postsend_info send_info = {}; + + send_info.write.addr = (uintptr_t)data; + send_info.write.length = byte_size; + send_info.write.lkey = 0; + send_info.remote_addr = + mlx5dr_ste_get_mr_addr(htbl->ste_arr + ste_index); + send_info.rkey = htbl->chunk->rkey; + + ret = dr_postsend_icm_data(dmn, &send_info); + if (ret) + goto out_free; + } + +out_free: + kfree(data); + return ret; +} + +int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn, + struct mlx5dr_action *action) +{ + struct postsend_info send_info = {}; + int ret; + + send_info.write.addr = (uintptr_t)action->rewrite.data; + send_info.write.length = action->rewrite.chunk->byte_size; + send_info.write.lkey = 0; + send_info.remote_addr = action->rewrite.chunk->mr_addr; + send_info.rkey = action->rewrite.chunk->rkey; + + mutex_lock(&dmn->mutex); + ret = dr_postsend_icm_data(dmn, &send_info); + mutex_unlock(&dmn->mutex); + + return ret; +} + +static int dr_modify_qp_rst2init(struct mlx5_core_dev *mdev, + struct mlx5dr_qp *dr_qp, + int port) +{ + u32 in[MLX5_ST_SZ_DW(rst2init_qp_in)] = {}; + void *qpc; + + qpc = MLX5_ADDR_OF(rst2init_qp_in, in, qpc); + + MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, port); + MLX5_SET(qpc, qpc, pm_state, MLX5_QPC_PM_STATE_MIGRATED); + MLX5_SET(qpc, qpc, rre, 1); + MLX5_SET(qpc, qpc, rwe, 1); + + return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RST2INIT_QP, 0, qpc, + &dr_qp->mqp); +} + +static int dr_cmd_modify_qp_rtr2rts(struct mlx5_core_dev *mdev, + struct mlx5dr_qp *dr_qp, + struct dr_qp_rts_attr *attr) +{ + u32 in[MLX5_ST_SZ_DW(rtr2rts_qp_in)] = {}; + void *qpc; + + qpc = MLX5_ADDR_OF(rtr2rts_qp_in, in, qpc); + + MLX5_SET(rtr2rts_qp_in, in, qpn, dr_qp->mqp.qpn); + + MLX5_SET(qpc, qpc, log_ack_req_freq, 0); + MLX5_SET(qpc, qpc, retry_count, attr->retry_cnt); + MLX5_SET(qpc, qpc, rnr_retry, attr->rnr_retry); + + return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_RTR2RTS_QP, 0, qpc, + &dr_qp->mqp); +} + +static int dr_cmd_modify_qp_init2rtr(struct mlx5_core_dev *mdev, + struct mlx5dr_qp *dr_qp, + struct dr_qp_rtr_attr *attr) +{ + u32 in[MLX5_ST_SZ_DW(init2rtr_qp_in)] = {}; + void *qpc; + + qpc = MLX5_ADDR_OF(init2rtr_qp_in, in, qpc); + + MLX5_SET(init2rtr_qp_in, in, qpn, dr_qp->mqp.qpn); + + MLX5_SET(qpc, qpc, mtu, attr->mtu); + MLX5_SET(qpc, qpc, log_msg_max, DR_CHUNK_SIZE_MAX - 1); + MLX5_SET(qpc, qpc, remote_qpn, attr->qp_num); + memcpy(MLX5_ADDR_OF(qpc, qpc, primary_address_path.rmac_47_32), + attr->dgid_attr.mac, sizeof(attr->dgid_attr.mac)); + memcpy(MLX5_ADDR_OF(qpc, qpc, primary_address_path.rgid_rip), + attr->dgid_attr.gid, sizeof(attr->dgid_attr.gid)); + MLX5_SET(qpc, qpc, primary_address_path.src_addr_index, + attr->sgid_index); + + if (attr->dgid_attr.roce_ver == MLX5_ROCE_VERSION_2) + MLX5_SET(qpc, qpc, primary_address_path.udp_sport, + attr->udp_src_port); + + MLX5_SET(qpc, qpc, primary_address_path.vhca_port_num, attr->port_num); + MLX5_SET(qpc, qpc, min_rnr_nak, 1); + + return mlx5_core_qp_modify(mdev, MLX5_CMD_OP_INIT2RTR_QP, 0, qpc, + &dr_qp->mqp); +} + +static int dr_prepare_qp_to_rts(struct mlx5dr_domain *dmn) +{ + struct mlx5dr_qp *dr_qp = dmn->send_ring->qp; + struct dr_qp_rts_attr rts_attr = {}; + struct dr_qp_rtr_attr rtr_attr = {}; + enum ib_mtu mtu = IB_MTU_1024; + u16 gid_index = 0; + int port = 1; + int ret; + + /* Init */ + ret = dr_modify_qp_rst2init(dmn->mdev, dr_qp, port); + if (ret) + return ret; + + /* RTR */ + ret = mlx5dr_cmd_query_gid(dmn->mdev, port, gid_index, &rtr_attr.dgid_attr); + if (ret) + return ret; + + rtr_attr.mtu = mtu; + rtr_attr.qp_num = dr_qp->mqp.qpn; + rtr_attr.min_rnr_timer = 12; + rtr_attr.port_num = port; + rtr_attr.sgid_index = gid_index; + rtr_attr.udp_src_port = dmn->info.caps.roce_min_src_udp; + + ret = dr_cmd_modify_qp_init2rtr(dmn->mdev, dr_qp, &rtr_attr); + if (ret) + return ret; + + /* RTS */ + rts_attr.timeout = 14; + rts_attr.retry_cnt = 7; + rts_attr.rnr_retry = 7; + + ret = dr_cmd_modify_qp_rtr2rts(dmn->mdev, dr_qp, &rts_attr); + if (ret) + return ret; + + return 0; +} + +static void dr_cq_event(struct mlx5_core_cq *mcq, + enum mlx5_event event) +{ + pr_info("CQ event %u on CQ #%u\n", event, mcq->cqn); +} + +static struct mlx5dr_cq *dr_create_cq(struct mlx5_core_dev *mdev, + struct mlx5_uars_page *uar, + size_t ncqe) +{ + u32 temp_cqc[MLX5_ST_SZ_DW(cqc)] = {}; + u32 out[MLX5_ST_SZ_DW(create_cq_out)]; + struct mlx5_wq_param wqp; + struct mlx5_cqe64 *cqe; + struct mlx5dr_cq *cq; + int inlen, err, eqn; + unsigned int irqn; + void *cqc, *in; + __be64 *pas; + u32 i; + + cq = kzalloc(sizeof(*cq), GFP_KERNEL); + if (!cq) + return NULL; + + ncqe = roundup_pow_of_two(ncqe); + MLX5_SET(cqc, temp_cqc, log_cq_size, ilog2(ncqe)); + + wqp.buf_numa_node = mdev->priv.numa_node; + wqp.db_numa_node = mdev->priv.numa_node; + + err = mlx5_cqwq_create(mdev, &wqp, temp_cqc, &cq->wq, + &cq->wq_ctrl); + if (err) + goto out; + + for (i = 0; i < mlx5_cqwq_get_size(&cq->wq); i++) { + cqe = mlx5_cqwq_get_wqe(&cq->wq, i); + cqe->op_own = MLX5_CQE_INVALID << 4 | MLX5_CQE_OWNER_MASK; + } + + inlen = MLX5_ST_SZ_BYTES(create_cq_in) + + sizeof(u64) * cq->wq_ctrl.buf.npages; + in = kvzalloc(inlen, GFP_KERNEL); + if (!in) + goto err_cqwq; + + err = mlx5_vector2eqn(mdev, smp_processor_id(), &eqn, &irqn); + if (err) { + kvfree(in); + goto err_cqwq; + } + + cqc = MLX5_ADDR_OF(create_cq_in, in, cq_context); + MLX5_SET(cqc, cqc, log_cq_size, ilog2(ncqe)); + MLX5_SET(cqc, cqc, c_eqn, eqn); + MLX5_SET(cqc, cqc, uar_page, uar->index); + MLX5_SET(cqc, cqc, log_page_size, cq->wq_ctrl.buf.page_shift - + MLX5_ADAPTER_PAGE_SHIFT); + MLX5_SET64(cqc, cqc, dbr_addr, cq->wq_ctrl.db.dma); + + pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, in, pas); + mlx5_fill_page_frag_array(&cq->wq_ctrl.buf, pas); + + cq->mcq.event = dr_cq_event; + + err = mlx5_core_create_cq(mdev, &cq->mcq, in, inlen, out, sizeof(out)); + kvfree(in); + + if (err) + goto err_cqwq; + + cq->mcq.cqe_sz = 64; + cq->mcq.set_ci_db = cq->wq_ctrl.db.db; + cq->mcq.arm_db = cq->wq_ctrl.db.db + 1; + *cq->mcq.set_ci_db = 0; + *cq->mcq.arm_db = 0; + cq->mcq.vector = 0; + cq->mcq.irqn = irqn; + cq->mcq.uar = uar; + + return cq; + +err_cqwq: + mlx5_wq_destroy(&cq->wq_ctrl); +out: + kfree(cq); + return NULL; +} + +static void dr_destroy_cq(struct mlx5_core_dev *mdev, struct mlx5dr_cq *cq) +{ + mlx5_core_destroy_cq(mdev, &cq->mcq); + mlx5_wq_destroy(&cq->wq_ctrl); + kfree(cq); +} + +static int +dr_create_mkey(struct mlx5_core_dev *mdev, u32 pdn, struct mlx5_core_mkey *mkey) +{ + u32 in[MLX5_ST_SZ_DW(create_mkey_in)] = {}; + void *mkc; + + mkc = MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); + MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_PA); + MLX5_SET(mkc, mkc, a, 1); + MLX5_SET(mkc, mkc, rw, 1); + MLX5_SET(mkc, mkc, rr, 1); + MLX5_SET(mkc, mkc, lw, 1); + MLX5_SET(mkc, mkc, lr, 1); + + MLX5_SET(mkc, mkc, pd, pdn); + MLX5_SET(mkc, mkc, length64, 1); + MLX5_SET(mkc, mkc, qpn, 0xffffff); + + return mlx5_core_create_mkey(mdev, mkey, in, sizeof(in)); +} + +static struct mlx5dr_mr *dr_reg_mr(struct mlx5_core_dev *mdev, + u32 pdn, void *buf, size_t size) +{ + struct mlx5dr_mr *mr = kzalloc(sizeof(*mr), GFP_KERNEL); + struct device *dma_device; + dma_addr_t dma_addr; + int err; + + if (!mr) + return NULL; + + dma_device = &mdev->pdev->dev; + dma_addr = dma_map_single(dma_device, buf, size, + DMA_BIDIRECTIONAL); + err = dma_mapping_error(dma_device, dma_addr); + if (err) { + mlx5_core_warn(mdev, "Can't dma buf\n"); + kfree(mr); + return NULL; + } + + err = dr_create_mkey(mdev, pdn, &mr->mkey); + if (err) { + mlx5_core_warn(mdev, "Can't create mkey\n"); + dma_unmap_single(dma_device, dma_addr, size, + DMA_BIDIRECTIONAL); + kfree(mr); + return NULL; + } + + mr->dma_addr = dma_addr; + mr->size = size; + mr->addr = buf; + + return mr; +} + +static void dr_dereg_mr(struct mlx5_core_dev *mdev, struct mlx5dr_mr *mr) +{ + mlx5_core_destroy_mkey(mdev, &mr->mkey); + dma_unmap_single(&mdev->pdev->dev, mr->dma_addr, mr->size, + DMA_BIDIRECTIONAL); + kfree(mr); +} + +int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn) +{ + struct dr_qp_init_attr init_attr = {}; + int cq_size; + int size; + int ret; + + dmn->send_ring = kzalloc(sizeof(*dmn->send_ring), GFP_KERNEL); + if (!dmn->send_ring) + return -ENOMEM; + + cq_size = QUEUE_SIZE + 1; + dmn->send_ring->cq = dr_create_cq(dmn->mdev, dmn->uar, cq_size); + if (!dmn->send_ring->cq) { + ret = -ENOMEM; + goto free_send_ring; + } + + init_attr.cqn = dmn->send_ring->cq->mcq.cqn; + init_attr.pdn = dmn->pdn; + init_attr.uar = dmn->uar; + init_attr.max_send_wr = QUEUE_SIZE; + + dmn->send_ring->qp = dr_create_rc_qp(dmn->mdev, &init_attr); + if (!dmn->send_ring->qp) { + ret = -ENOMEM; + goto clean_cq; + } + + dmn->send_ring->cq->qp = dmn->send_ring->qp; + + dmn->info.max_send_wr = QUEUE_SIZE; + dmn->info.max_inline_size = min(dmn->send_ring->qp->max_inline_data, + DR_STE_SIZE); + + dmn->send_ring->signal_th = dmn->info.max_send_wr / + SIGNAL_PER_DIV_QUEUE; + + /* Prepare qp to be used */ + ret = dr_prepare_qp_to_rts(dmn); + if (ret) + goto clean_qp; + + dmn->send_ring->max_post_send_size = + mlx5dr_icm_pool_chunk_size_to_byte(DR_CHUNK_SIZE_1K, + DR_ICM_TYPE_STE); + + /* Allocating the max size as a buffer for writing */ + size = dmn->send_ring->signal_th * dmn->send_ring->max_post_send_size; + dmn->send_ring->buf = kzalloc(size, GFP_KERNEL); + if (!dmn->send_ring->buf) { + ret = -ENOMEM; + goto clean_qp; + } + + dmn->send_ring->buf_size = size; + + dmn->send_ring->mr = dr_reg_mr(dmn->mdev, + dmn->pdn, dmn->send_ring->buf, size); + if (!dmn->send_ring->mr) { + ret = -ENOMEM; + goto free_mem; + } + + dmn->send_ring->sync_mr = dr_reg_mr(dmn->mdev, + dmn->pdn, dmn->send_ring->sync_buff, + MIN_READ_SYNC); + if (!dmn->send_ring->sync_mr) { + ret = -ENOMEM; + goto clean_mr; + } + + return 0; + +clean_mr: + dr_dereg_mr(dmn->mdev, dmn->send_ring->mr); +free_mem: + kfree(dmn->send_ring->buf); +clean_qp: + dr_destroy_qp(dmn->mdev, dmn->send_ring->qp); +clean_cq: + dr_destroy_cq(dmn->mdev, dmn->send_ring->cq); +free_send_ring: + kfree(dmn->send_ring); + + return ret; +} + +void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn, + struct mlx5dr_send_ring *send_ring) +{ + dr_destroy_qp(dmn->mdev, send_ring->qp); + dr_destroy_cq(dmn->mdev, send_ring->cq); + dr_dereg_mr(dmn->mdev, send_ring->sync_mr); + dr_dereg_mr(dmn->mdev, send_ring->mr); + kfree(send_ring->buf); + kfree(send_ring); +} + +int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn) +{ + struct mlx5dr_send_ring *send_ring = dmn->send_ring; + struct postsend_info send_info = {}; + u8 data[DR_STE_SIZE]; + int num_of_sends_req; + int ret; + int i; + + /* Sending this amount of requests makes sure we will get drain */ + num_of_sends_req = send_ring->signal_th * TH_NUMS_TO_DRAIN / 2; + + /* Send fake requests forcing the last to be signaled */ + send_info.write.addr = (uintptr_t)data; + send_info.write.length = DR_STE_SIZE; + send_info.write.lkey = 0; + /* Using the sync_mr in order to write/read */ + send_info.remote_addr = (uintptr_t)send_ring->sync_mr->addr; + send_info.rkey = send_ring->sync_mr->mkey.key; + + for (i = 0; i < num_of_sends_req; i++) { + ret = dr_postsend_icm_data(dmn, &send_info); + if (ret) + return ret; + } + + ret = dr_handle_pending_wc(dmn, send_ring); + + return ret; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c new file mode 100644 index 000000000000..6b0af64536d8 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_ste.c @@ -0,0 +1,2308 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include <linux/types.h> +#include "dr_types.h" + +#define DR_STE_CRC_POLY 0xEDB88320L +#define STE_IPV4 0x1 +#define STE_IPV6 0x2 +#define STE_TCP 0x1 +#define STE_UDP 0x2 +#define STE_SPI 0x3 +#define IP_VERSION_IPV4 0x4 +#define IP_VERSION_IPV6 0x6 +#define STE_SVLAN 0x1 +#define STE_CVLAN 0x2 + +#define DR_STE_ENABLE_FLOW_TAG BIT(31) + +/* Set to STE a specific value using DR_STE_SET */ +#define DR_STE_SET_VAL(lookup_type, tag, t_fname, spec, s_fname, value) do { \ + if ((spec)->s_fname) { \ + MLX5_SET(ste_##lookup_type, tag, t_fname, value); \ + (spec)->s_fname = 0; \ + } \ +} while (0) + +/* Set to STE spec->s_fname to tag->t_fname */ +#define DR_STE_SET_TAG(lookup_type, tag, t_fname, spec, s_fname) \ + DR_STE_SET_VAL(lookup_type, tag, t_fname, spec, s_fname, spec->s_fname) + +/* Set to STE -1 to bit_mask->bm_fname and set spec->s_fname as used */ +#define DR_STE_SET_MASK(lookup_type, bit_mask, bm_fname, spec, s_fname) \ + DR_STE_SET_VAL(lookup_type, bit_mask, bm_fname, spec, s_fname, -1) + +/* Set to STE spec->s_fname to bit_mask->bm_fname and set spec->s_fname as used */ +#define DR_STE_SET_MASK_V(lookup_type, bit_mask, bm_fname, spec, s_fname) \ + DR_STE_SET_VAL(lookup_type, bit_mask, bm_fname, spec, s_fname, (spec)->s_fname) + +#define DR_STE_SET_TCP_FLAGS(lookup_type, tag, spec) do { \ + MLX5_SET(ste_##lookup_type, tag, tcp_ns, !!((spec)->tcp_flags & (1 << 8))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_cwr, !!((spec)->tcp_flags & (1 << 7))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_ece, !!((spec)->tcp_flags & (1 << 6))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_urg, !!((spec)->tcp_flags & (1 << 5))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_ack, !!((spec)->tcp_flags & (1 << 4))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_psh, !!((spec)->tcp_flags & (1 << 3))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_rst, !!((spec)->tcp_flags & (1 << 2))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_syn, !!((spec)->tcp_flags & (1 << 1))); \ + MLX5_SET(ste_##lookup_type, tag, tcp_fin, !!((spec)->tcp_flags & (1 << 0))); \ +} while (0) + +#define DR_STE_SET_MPLS_MASK(lookup_type, mask, in_out, bit_mask) do { \ + DR_STE_SET_MASK_V(lookup_type, mask, mpls0_label, mask, \ + in_out##_first_mpls_label);\ + DR_STE_SET_MASK_V(lookup_type, mask, mpls0_s_bos, mask, \ + in_out##_first_mpls_s_bos); \ + DR_STE_SET_MASK_V(lookup_type, mask, mpls0_exp, mask, \ + in_out##_first_mpls_exp); \ + DR_STE_SET_MASK_V(lookup_type, mask, mpls0_ttl, mask, \ + in_out##_first_mpls_ttl); \ +} while (0) + +#define DR_STE_SET_MPLS_TAG(lookup_type, mask, in_out, tag) do { \ + DR_STE_SET_TAG(lookup_type, tag, mpls0_label, mask, \ + in_out##_first_mpls_label);\ + DR_STE_SET_TAG(lookup_type, tag, mpls0_s_bos, mask, \ + in_out##_first_mpls_s_bos); \ + DR_STE_SET_TAG(lookup_type, tag, mpls0_exp, mask, \ + in_out##_first_mpls_exp); \ + DR_STE_SET_TAG(lookup_type, tag, mpls0_ttl, mask, \ + in_out##_first_mpls_ttl); \ +} while (0) + +#define DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(_misc) (\ + (_misc)->outer_first_mpls_over_gre_label || \ + (_misc)->outer_first_mpls_over_gre_exp || \ + (_misc)->outer_first_mpls_over_gre_s_bos || \ + (_misc)->outer_first_mpls_over_gre_ttl) +#define DR_STE_IS_OUTER_MPLS_OVER_UDP_SET(_misc) (\ + (_misc)->outer_first_mpls_over_udp_label || \ + (_misc)->outer_first_mpls_over_udp_exp || \ + (_misc)->outer_first_mpls_over_udp_s_bos || \ + (_misc)->outer_first_mpls_over_udp_ttl) + +#define DR_STE_CALC_LU_TYPE(lookup_type, rx, inner) \ + ((inner) ? MLX5DR_STE_LU_TYPE_##lookup_type##_I : \ + (rx) ? MLX5DR_STE_LU_TYPE_##lookup_type##_D : \ + MLX5DR_STE_LU_TYPE_##lookup_type##_O) + +enum dr_ste_tunl_action { + DR_STE_TUNL_ACTION_NONE = 0, + DR_STE_TUNL_ACTION_ENABLE = 1, + DR_STE_TUNL_ACTION_DECAP = 2, + DR_STE_TUNL_ACTION_L3_DECAP = 3, + DR_STE_TUNL_ACTION_POP_VLAN = 4, +}; + +enum dr_ste_action_type { + DR_STE_ACTION_TYPE_PUSH_VLAN = 1, + DR_STE_ACTION_TYPE_ENCAP_L3 = 3, + DR_STE_ACTION_TYPE_ENCAP = 4, +}; + +struct dr_hw_ste_format { + u8 ctrl[DR_STE_SIZE_CTRL]; + u8 tag[DR_STE_SIZE_TAG]; + u8 mask[DR_STE_SIZE_MASK]; +}; + +u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + u8 masked[DR_STE_SIZE_TAG] = {}; + u32 crc32, index; + u16 bit; + int i; + + /* Don't calculate CRC if the result is predicted */ + if (htbl->chunk->num_of_entries == 1 || htbl->byte_mask == 0) + return 0; + + /* Mask tag using byte mask, bit per byte */ + bit = 1 << (DR_STE_SIZE_TAG - 1); + for (i = 0; i < DR_STE_SIZE_TAG; i++) { + if (htbl->byte_mask & bit) + masked[i] = hw_ste->tag[i]; + + bit = bit >> 1; + } + + crc32 = mlx5dr_crc32_slice8_calc(masked, DR_STE_SIZE_TAG); + index = crc32 & (htbl->chunk->num_of_entries - 1); + + return index; +} + +static u16 dr_ste_conv_bit_to_byte_mask(u8 *bit_mask) +{ + u16 byte_mask = 0; + int i; + + for (i = 0; i < DR_STE_SIZE_MASK; i++) { + byte_mask = byte_mask << 1; + if (bit_mask[i] == 0xff) + byte_mask |= 1; + } + return byte_mask; +} + +void mlx5dr_ste_set_bit_mask(u8 *hw_ste_p, u8 *bit_mask) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + + memcpy(hw_ste->mask, bit_mask, DR_STE_SIZE_MASK); +} + +void mlx5dr_ste_rx_set_flow_tag(u8 *hw_ste_p, u32 flow_tag) +{ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, qp_list_pointer, + DR_STE_ENABLE_FLOW_TAG | flow_tag); +} + +void mlx5dr_ste_set_counter_id(u8 *hw_ste_p, u32 ctr_id) +{ + /* This can be used for both rx_steering_mult and for sx_transmit */ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, counter_trigger_15_0, ctr_id); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, counter_trigger_23_16, ctr_id >> 16); +} + +void mlx5dr_ste_set_go_back_bit(u8 *hw_ste_p) +{ + MLX5_SET(ste_sx_transmit, hw_ste_p, go_back, 1); +} + +void mlx5dr_ste_set_tx_push_vlan(u8 *hw_ste_p, u32 vlan_hdr, + bool go_back) +{ + MLX5_SET(ste_sx_transmit, hw_ste_p, action_type, + DR_STE_ACTION_TYPE_PUSH_VLAN); + MLX5_SET(ste_sx_transmit, hw_ste_p, encap_pointer_vlan_data, vlan_hdr); + /* Due to HW limitation we need to set this bit, otherwise reforamt + + * push vlan will not work. + */ + if (go_back) + mlx5dr_ste_set_go_back_bit(hw_ste_p); +} + +void mlx5dr_ste_set_tx_encap(void *hw_ste_p, u32 reformat_id, int size, bool encap_l3) +{ + MLX5_SET(ste_sx_transmit, hw_ste_p, action_type, + encap_l3 ? DR_STE_ACTION_TYPE_ENCAP_L3 : DR_STE_ACTION_TYPE_ENCAP); + /* The hardware expects here size in words (2 byte) */ + MLX5_SET(ste_sx_transmit, hw_ste_p, action_description, size / 2); + MLX5_SET(ste_sx_transmit, hw_ste_p, encap_pointer_vlan_data, reformat_id); +} + +void mlx5dr_ste_set_rx_decap(u8 *hw_ste_p) +{ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action, + DR_STE_TUNL_ACTION_DECAP); +} + +void mlx5dr_ste_set_rx_pop_vlan(u8 *hw_ste_p) +{ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action, + DR_STE_TUNL_ACTION_POP_VLAN); +} + +void mlx5dr_ste_set_rx_decap_l3(u8 *hw_ste_p, bool vlan) +{ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, tunneling_action, + DR_STE_TUNL_ACTION_L3_DECAP); + MLX5_SET(ste_modify_packet, hw_ste_p, action_description, vlan ? 1 : 0); +} + +void mlx5dr_ste_set_entry_type(u8 *hw_ste_p, u8 entry_type) +{ + MLX5_SET(ste_general, hw_ste_p, entry_type, entry_type); +} + +u8 mlx5dr_ste_get_entry_type(u8 *hw_ste_p) +{ + return MLX5_GET(ste_general, hw_ste_p, entry_type); +} + +void mlx5dr_ste_set_rewrite_actions(u8 *hw_ste_p, u16 num_of_actions, + u32 re_write_index) +{ + MLX5_SET(ste_modify_packet, hw_ste_p, number_of_re_write_actions, + num_of_actions); + MLX5_SET(ste_modify_packet, hw_ste_p, header_re_write_actions_pointer, + re_write_index); +} + +void mlx5dr_ste_set_hit_gvmi(u8 *hw_ste_p, u16 gvmi) +{ + MLX5_SET(ste_general, hw_ste_p, next_table_base_63_48, gvmi); +} + +void mlx5dr_ste_init(u8 *hw_ste_p, u8 lu_type, u8 entry_type, + u16 gvmi) +{ + MLX5_SET(ste_general, hw_ste_p, entry_type, entry_type); + MLX5_SET(ste_general, hw_ste_p, entry_sub_type, lu_type); + MLX5_SET(ste_general, hw_ste_p, next_lu_type, MLX5DR_STE_LU_TYPE_DONT_CARE); + + /* Set GVMI once, this is the same for RX/TX + * bits 63_48 of next table base / miss address encode the next GVMI + */ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, gvmi, gvmi); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, next_table_base_63_48, gvmi); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_63_48, gvmi); +} + +static void dr_ste_set_always_hit(struct dr_hw_ste_format *hw_ste) +{ + memset(&hw_ste->tag, 0, sizeof(hw_ste->tag)); + memset(&hw_ste->mask, 0, sizeof(hw_ste->mask)); +} + +static void dr_ste_set_always_miss(struct dr_hw_ste_format *hw_ste) +{ + hw_ste->tag[0] = 0xdc; + hw_ste->mask[0] = 0; +} + +u64 mlx5dr_ste_get_miss_addr(u8 *hw_ste) +{ + u64 index = + (MLX5_GET(ste_rx_steering_mult, hw_ste, miss_address_31_6) | + MLX5_GET(ste_rx_steering_mult, hw_ste, miss_address_39_32) << 26); + + return index << 6; +} + +void mlx5dr_ste_set_hit_addr(u8 *hw_ste, u64 icm_addr, u32 ht_size) +{ + u64 index = (icm_addr >> 5) | ht_size; + + MLX5_SET(ste_general, hw_ste, next_table_base_39_32_size, index >> 27); + MLX5_SET(ste_general, hw_ste, next_table_base_31_5_size, index); +} + +u64 mlx5dr_ste_get_icm_addr(struct mlx5dr_ste *ste) +{ + u32 index = ste - ste->htbl->ste_arr; + + return ste->htbl->chunk->icm_addr + DR_STE_SIZE * index; +} + +u64 mlx5dr_ste_get_mr_addr(struct mlx5dr_ste *ste) +{ + u32 index = ste - ste->htbl->ste_arr; + + return ste->htbl->chunk->mr_addr + DR_STE_SIZE * index; +} + +struct list_head *mlx5dr_ste_get_miss_list(struct mlx5dr_ste *ste) +{ + u32 index = ste - ste->htbl->ste_arr; + + return &ste->htbl->miss_list[index]; +} + +static void dr_ste_always_hit_htbl(struct mlx5dr_ste *ste, + struct mlx5dr_ste_htbl *next_htbl) +{ + struct mlx5dr_icm_chunk *chunk = next_htbl->chunk; + u8 *hw_ste = ste->hw_ste; + + MLX5_SET(ste_general, hw_ste, byte_mask, next_htbl->byte_mask); + MLX5_SET(ste_general, hw_ste, next_lu_type, next_htbl->lu_type); + mlx5dr_ste_set_hit_addr(hw_ste, chunk->icm_addr, chunk->num_of_entries); + + dr_ste_set_always_hit((struct dr_hw_ste_format *)ste->hw_ste); +} + +bool mlx5dr_ste_is_last_in_rule(struct mlx5dr_matcher_rx_tx *nic_matcher, + u8 ste_location) +{ + return ste_location == nic_matcher->num_of_builders; +} + +/* Replace relevant fields, except of: + * htbl - keep the origin htbl + * miss_list + list - already took the src from the list. + * icm_addr/mr_addr - depends on the hosting table. + * + * Before: + * | a | -> | b | -> | c | -> + * + * After: + * | a | -> | c | -> + * While the data that was in b copied to a. + */ +static void dr_ste_replace(struct mlx5dr_ste *dst, struct mlx5dr_ste *src) +{ + memcpy(dst->hw_ste, src->hw_ste, DR_STE_SIZE_REDUCED); + dst->next_htbl = src->next_htbl; + if (dst->next_htbl) + dst->next_htbl->pointing_ste = dst; + + refcount_set(&dst->refcount, refcount_read(&src->refcount)); + + INIT_LIST_HEAD(&dst->rule_list); + list_splice_tail_init(&src->rule_list, &dst->rule_list); +} + +/* Free ste which is the head and the only one in miss_list */ +static void +dr_ste_remove_head_ste(struct mlx5dr_ste *ste, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste_send_info *ste_info_head, + struct list_head *send_ste_list, + struct mlx5dr_ste_htbl *stats_tbl) +{ + u8 tmp_data_ste[DR_STE_SIZE] = {}; + struct mlx5dr_ste tmp_ste = {}; + u64 miss_addr; + + tmp_ste.hw_ste = tmp_data_ste; + + /* Use temp ste because dr_ste_always_miss_addr + * touches bit_mask area which doesn't exist at ste->hw_ste. + */ + memcpy(tmp_ste.hw_ste, ste->hw_ste, DR_STE_SIZE_REDUCED); + miss_addr = nic_matcher->e_anchor->chunk->icm_addr; + mlx5dr_ste_always_miss_addr(&tmp_ste, miss_addr); + memcpy(ste->hw_ste, tmp_ste.hw_ste, DR_STE_SIZE_REDUCED); + + list_del_init(&ste->miss_list_node); + + /* Write full STE size in order to have "always_miss" */ + mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE, + 0, tmp_data_ste, + ste_info_head, + send_ste_list, + true /* Copy data */); + + stats_tbl->ctrl.num_of_valid_entries--; +} + +/* Free ste which is the head but NOT the only one in miss_list: + * |_ste_| --> |_next_ste_| -->|__| -->|__| -->/0 + */ +static void +dr_ste_replace_head_ste(struct mlx5dr_ste *ste, struct mlx5dr_ste *next_ste, + struct mlx5dr_ste_send_info *ste_info_head, + struct list_head *send_ste_list, + struct mlx5dr_ste_htbl *stats_tbl) + +{ + struct mlx5dr_ste_htbl *next_miss_htbl; + + next_miss_htbl = next_ste->htbl; + + /* Remove from the miss_list the next_ste before copy */ + list_del_init(&next_ste->miss_list_node); + + /* All rule-members that use next_ste should know about that */ + mlx5dr_rule_update_rule_member(next_ste, ste); + + /* Move data from next into ste */ + dr_ste_replace(ste, next_ste); + + /* Del the htbl that contains the next_ste. + * The origin htbl stay with the same number of entries. + */ + mlx5dr_htbl_put(next_miss_htbl); + + mlx5dr_send_fill_and_append_ste_send_info(ste, DR_STE_SIZE_REDUCED, + 0, ste->hw_ste, + ste_info_head, + send_ste_list, + true /* Copy data */); + + stats_tbl->ctrl.num_of_collisions--; + stats_tbl->ctrl.num_of_valid_entries--; +} + +/* Free ste that is located in the middle of the miss list: + * |__| -->|_prev_ste_|->|_ste_|-->|_next_ste_| + */ +static void dr_ste_remove_middle_ste(struct mlx5dr_ste *ste, + struct mlx5dr_ste_send_info *ste_info, + struct list_head *send_ste_list, + struct mlx5dr_ste_htbl *stats_tbl) +{ + struct mlx5dr_ste *prev_ste; + u64 miss_addr; + + prev_ste = list_entry(mlx5dr_ste_get_miss_list(ste)->prev, struct mlx5dr_ste, + miss_list_node); + if (!prev_ste) { + WARN_ON(true); + return; + } + + miss_addr = mlx5dr_ste_get_miss_addr(ste->hw_ste); + mlx5dr_ste_set_miss_addr(prev_ste->hw_ste, miss_addr); + + mlx5dr_send_fill_and_append_ste_send_info(prev_ste, DR_STE_SIZE_REDUCED, 0, + prev_ste->hw_ste, ste_info, + send_ste_list, true /* Copy data*/); + + list_del_init(&ste->miss_list_node); + + stats_tbl->ctrl.num_of_valid_entries--; + stats_tbl->ctrl.num_of_collisions--; +} + +void mlx5dr_ste_free(struct mlx5dr_ste *ste, + struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher) +{ + struct mlx5dr_ste_send_info *cur_ste_info, *tmp_ste_info; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_ste_send_info ste_info_head; + struct mlx5dr_ste *next_ste, *first_ste; + bool put_on_origin_table = true; + struct mlx5dr_ste_htbl *stats_tbl; + LIST_HEAD(send_ste_list); + + first_ste = list_entry(mlx5dr_ste_get_miss_list(ste)->next, + struct mlx5dr_ste, miss_list_node); + stats_tbl = first_ste->htbl; + + /* Two options: + * 1. ste is head: + * a. head ste is the only ste in the miss list + * b. head ste is not the only ste in the miss-list + * 2. ste is not head + */ + if (first_ste == ste) { /* Ste is the head */ + struct mlx5dr_ste *last_ste; + + last_ste = list_last_entry(mlx5dr_ste_get_miss_list(ste), + struct mlx5dr_ste, miss_list_node); + if (last_ste == first_ste) + next_ste = NULL; + else + next_ste = list_entry(ste->miss_list_node.next, + struct mlx5dr_ste, miss_list_node); + + if (!next_ste) { + /* One and only entry in the list */ + dr_ste_remove_head_ste(ste, nic_matcher, + &ste_info_head, + &send_ste_list, + stats_tbl); + } else { + /* First but not only entry in the list */ + dr_ste_replace_head_ste(ste, next_ste, &ste_info_head, + &send_ste_list, stats_tbl); + put_on_origin_table = false; + } + } else { /* Ste in the middle of the list */ + dr_ste_remove_middle_ste(ste, &ste_info_head, &send_ste_list, stats_tbl); + } + + /* Update HW */ + list_for_each_entry_safe(cur_ste_info, tmp_ste_info, + &send_ste_list, send_list) { + list_del(&cur_ste_info->send_list); + mlx5dr_send_postsend_ste(dmn, cur_ste_info->ste, + cur_ste_info->data, cur_ste_info->size, + cur_ste_info->offset); + } + + if (put_on_origin_table) + mlx5dr_htbl_put(ste->htbl); +} + +bool mlx5dr_ste_equal_tag(void *src, void *dst) +{ + struct dr_hw_ste_format *s_hw_ste = (struct dr_hw_ste_format *)src; + struct dr_hw_ste_format *d_hw_ste = (struct dr_hw_ste_format *)dst; + + return !memcmp(s_hw_ste->tag, d_hw_ste->tag, DR_STE_SIZE_TAG); +} + +void mlx5dr_ste_set_hit_addr_by_next_htbl(u8 *hw_ste, + struct mlx5dr_ste_htbl *next_htbl) +{ + struct mlx5dr_icm_chunk *chunk = next_htbl->chunk; + + mlx5dr_ste_set_hit_addr(hw_ste, chunk->icm_addr, chunk->num_of_entries); +} + +void mlx5dr_ste_set_miss_addr(u8 *hw_ste_p, u64 miss_addr) +{ + u64 index = miss_addr >> 6; + + /* Miss address for TX and RX STEs located in the same offsets */ + MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_39_32, index >> 26); + MLX5_SET(ste_rx_steering_mult, hw_ste_p, miss_address_31_6, index); +} + +void mlx5dr_ste_always_miss_addr(struct mlx5dr_ste *ste, u64 miss_addr) +{ + u8 *hw_ste = ste->hw_ste; + + MLX5_SET(ste_rx_steering_mult, hw_ste, next_lu_type, MLX5DR_STE_LU_TYPE_DONT_CARE); + mlx5dr_ste_set_miss_addr(hw_ste, miss_addr); + dr_ste_set_always_miss((struct dr_hw_ste_format *)ste->hw_ste); +} + +/* The assumption here is that we don't update the ste->hw_ste if it is not + * used ste, so it will be all zero, checking the next_lu_type. + */ +bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)p_hw_ste; + + if (MLX5_GET(ste_general, hw_ste, next_lu_type) == + MLX5DR_STE_LU_TYPE_NOP) + return true; + + return false; +} + +bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste) +{ + return !refcount_read(&ste->refcount); +} + +static u16 get_bits_per_mask(u16 byte_mask) +{ + u16 bits = 0; + + while (byte_mask) { + byte_mask = byte_mask & (byte_mask - 1); + bits++; + } + + return bits; +} + +/* Init one ste as a pattern for ste data array */ +void mlx5dr_ste_set_formatted_ste(u16 gvmi, + struct mlx5dr_domain_rx_tx *nic_dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *formatted_ste, + struct mlx5dr_htbl_connect_info *connect_info) +{ + struct mlx5dr_ste ste = {}; + + mlx5dr_ste_init(formatted_ste, htbl->lu_type, nic_dmn->ste_type, gvmi); + ste.hw_ste = formatted_ste; + + if (connect_info->type == CONNECT_HIT) + dr_ste_always_hit_htbl(&ste, connect_info->hit_next_htbl); + else + mlx5dr_ste_always_miss_addr(&ste, connect_info->miss_icm_addr); +} + +int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn, + struct mlx5dr_domain_rx_tx *nic_dmn, + struct mlx5dr_ste_htbl *htbl, + struct mlx5dr_htbl_connect_info *connect_info, + bool update_hw_ste) +{ + u8 formatted_ste[DR_STE_SIZE] = {}; + + mlx5dr_ste_set_formatted_ste(dmn->info.caps.gvmi, + nic_dmn, + htbl, + formatted_ste, + connect_info); + + return mlx5dr_send_postsend_formatted_htbl(dmn, htbl, formatted_ste, update_hw_ste); +} + +int mlx5dr_ste_create_next_htbl(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste *ste, + u8 *cur_hw_ste, + enum mlx5dr_icm_chunk_size log_table_size) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)cur_hw_ste; + struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_htbl_connect_info info; + struct mlx5dr_ste_htbl *next_htbl; + + if (!mlx5dr_ste_is_last_in_rule(nic_matcher, ste->ste_chain_location)) { + u32 bits_in_mask; + u8 next_lu_type; + u16 byte_mask; + + next_lu_type = MLX5_GET(ste_general, hw_ste, next_lu_type); + byte_mask = MLX5_GET(ste_general, hw_ste, byte_mask); + + /* Don't allocate table more than required, + * the size of the table defined via the byte_mask, so no need + * to allocate more than that. + */ + bits_in_mask = get_bits_per_mask(byte_mask) * BITS_PER_BYTE; + log_table_size = min(log_table_size, bits_in_mask); + + next_htbl = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + log_table_size, + next_lu_type, + byte_mask); + if (!next_htbl) { + mlx5dr_dbg(dmn, "Failed allocating table\n"); + return -ENOMEM; + } + + /* Write new table to HW */ + info.type = CONNECT_MISS; + info.miss_icm_addr = nic_matcher->e_anchor->chunk->icm_addr; + if (mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, next_htbl, + &info, false)) { + mlx5dr_info(dmn, "Failed writing table to HW\n"); + goto free_table; + } + + mlx5dr_ste_set_hit_addr_by_next_htbl(cur_hw_ste, next_htbl); + ste->next_htbl = next_htbl; + next_htbl->pointing_ste = ste; + } + + return 0; + +free_table: + mlx5dr_ste_htbl_free(next_htbl); + return -ENOENT; +} + +static void dr_ste_set_ctrl(struct mlx5dr_ste_htbl *htbl) +{ + struct mlx5dr_ste_htbl_ctrl *ctrl = &htbl->ctrl; + int num_of_entries; + + htbl->ctrl.may_grow = true; + + if (htbl->chunk_size == DR_CHUNK_SIZE_MAX - 1) + htbl->ctrl.may_grow = false; + + /* Threshold is 50%, one is added to table of size 1 */ + num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(htbl->chunk_size); + ctrl->increase_threshold = (num_of_entries + 1) / 2; +} + +struct mlx5dr_ste_htbl *mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size, + u8 lu_type, u16 byte_mask) +{ + struct mlx5dr_icm_chunk *chunk; + struct mlx5dr_ste_htbl *htbl; + int i; + + htbl = kzalloc(sizeof(*htbl), GFP_KERNEL); + if (!htbl) + return NULL; + + chunk = mlx5dr_icm_alloc_chunk(pool, chunk_size); + if (!chunk) + goto out_free_htbl; + + htbl->chunk = chunk; + htbl->lu_type = lu_type; + htbl->byte_mask = byte_mask; + htbl->ste_arr = chunk->ste_arr; + htbl->hw_ste_arr = chunk->hw_ste_arr; + htbl->miss_list = chunk->miss_list; + refcount_set(&htbl->refcount, 0); + + for (i = 0; i < chunk->num_of_entries; i++) { + struct mlx5dr_ste *ste = &htbl->ste_arr[i]; + + ste->hw_ste = htbl->hw_ste_arr + i * DR_STE_SIZE_REDUCED; + ste->htbl = htbl; + refcount_set(&ste->refcount, 0); + INIT_LIST_HEAD(&ste->miss_list_node); + INIT_LIST_HEAD(&htbl->miss_list[i]); + INIT_LIST_HEAD(&ste->rule_list); + } + + htbl->chunk_size = chunk_size; + dr_ste_set_ctrl(htbl); + return htbl; + +out_free_htbl: + kfree(htbl); + return NULL; +} + +int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl) +{ + if (refcount_read(&htbl->refcount)) + return -EBUSY; + + mlx5dr_icm_free_chunk(htbl->chunk); + kfree(htbl); + return 0; +} + +int mlx5dr_ste_build_pre_check(struct mlx5dr_domain *dmn, + u8 match_criteria, + struct mlx5dr_match_param *mask, + struct mlx5dr_match_param *value) +{ + if (!value && (match_criteria & DR_MATCHER_CRITERIA_MISC)) { + if (mask->misc.source_port && mask->misc.source_port != 0xffff) { + mlx5dr_dbg(dmn, "Partial mask source_port is not supported\n"); + return -EINVAL; + } + } + + return 0; +} + +int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_match_param *value, + u8 *ste_arr) +{ + struct mlx5dr_domain_rx_tx *nic_dmn = nic_matcher->nic_tbl->nic_dmn; + struct mlx5dr_domain *dmn = matcher->tbl->dmn; + struct mlx5dr_ste_build *sb; + int ret, i; + + ret = mlx5dr_ste_build_pre_check(dmn, matcher->match_criteria, + &matcher->mask, value); + if (ret) + return ret; + + sb = nic_matcher->ste_builder; + for (i = 0; i < nic_matcher->num_of_builders; i++) { + mlx5dr_ste_init(ste_arr, + sb->lu_type, + nic_dmn->ste_type, + dmn->info.caps.gvmi); + + mlx5dr_ste_set_bit_mask(ste_arr, sb->bit_mask); + + ret = sb->ste_build_tag_func(value, sb, ste_arr); + if (ret) + return ret; + + /* Connect the STEs */ + if (i < (nic_matcher->num_of_builders - 1)) { + /* Need the next builder for these fields, + * not relevant for the last ste in the chain. + */ + sb++; + MLX5_SET(ste_general, ste_arr, next_lu_type, sb->lu_type); + MLX5_SET(ste_general, ste_arr, byte_mask, sb->byte_mask); + } + ste_arr += DR_STE_SIZE; + } + return 0; +} + +static int dr_ste_build_eth_l2_src_des_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, dmac_47_16, mask, dmac_47_16); + DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, dmac_15_0, mask, dmac_15_0); + + if (mask->smac_47_16 || mask->smac_15_0) { + MLX5_SET(ste_eth_l2_src_dst, bit_mask, smac_47_32, + mask->smac_47_16 >> 16); + MLX5_SET(ste_eth_l2_src_dst, bit_mask, smac_31_0, + mask->smac_47_16 << 16 | mask->smac_15_0); + mask->smac_47_16 = 0; + mask->smac_15_0 = 0; + } + + DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_vlan_id, mask, first_vid); + DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_cfi, mask, first_cfi); + DR_STE_SET_MASK_V(eth_l2_src_dst, bit_mask, first_priority, mask, first_prio); + DR_STE_SET_MASK(eth_l2_src_dst, bit_mask, l3_type, mask, ip_version); + + if (mask->cvlan_tag) { + MLX5_SET(ste_eth_l2_src_dst, bit_mask, first_vlan_qualifier, -1); + mask->cvlan_tag = 0; + } else if (mask->svlan_tag) { + MLX5_SET(ste_eth_l2_src_dst, bit_mask, first_vlan_qualifier, -1); + mask->svlan_tag = 0; + } + + if (mask->cvlan_tag || mask->svlan_tag) { + pr_info("Invalid c/svlan mask configuration\n"); + return -EINVAL; + } + + return 0; +} + +static void dr_ste_copy_mask_misc(char *mask, struct mlx5dr_match_misc *spec) +{ + spec->gre_c_present = MLX5_GET(fte_match_set_misc, mask, gre_c_present); + spec->gre_k_present = MLX5_GET(fte_match_set_misc, mask, gre_k_present); + spec->gre_s_present = MLX5_GET(fte_match_set_misc, mask, gre_s_present); + spec->source_vhca_port = MLX5_GET(fte_match_set_misc, mask, source_vhca_port); + spec->source_sqn = MLX5_GET(fte_match_set_misc, mask, source_sqn); + + spec->source_port = MLX5_GET(fte_match_set_misc, mask, source_port); + + spec->outer_second_prio = MLX5_GET(fte_match_set_misc, mask, outer_second_prio); + spec->outer_second_cfi = MLX5_GET(fte_match_set_misc, mask, outer_second_cfi); + spec->outer_second_vid = MLX5_GET(fte_match_set_misc, mask, outer_second_vid); + spec->inner_second_prio = MLX5_GET(fte_match_set_misc, mask, inner_second_prio); + spec->inner_second_cfi = MLX5_GET(fte_match_set_misc, mask, inner_second_cfi); + spec->inner_second_vid = MLX5_GET(fte_match_set_misc, mask, inner_second_vid); + + spec->outer_second_cvlan_tag = + MLX5_GET(fte_match_set_misc, mask, outer_second_cvlan_tag); + spec->inner_second_cvlan_tag = + MLX5_GET(fte_match_set_misc, mask, inner_second_cvlan_tag); + spec->outer_second_svlan_tag = + MLX5_GET(fte_match_set_misc, mask, outer_second_svlan_tag); + spec->inner_second_svlan_tag = + MLX5_GET(fte_match_set_misc, mask, inner_second_svlan_tag); + + spec->gre_protocol = MLX5_GET(fte_match_set_misc, mask, gre_protocol); + + spec->gre_key_h = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.hi); + spec->gre_key_l = MLX5_GET(fte_match_set_misc, mask, gre_key.nvgre.lo); + + spec->vxlan_vni = MLX5_GET(fte_match_set_misc, mask, vxlan_vni); + + spec->geneve_vni = MLX5_GET(fte_match_set_misc, mask, geneve_vni); + spec->geneve_oam = MLX5_GET(fte_match_set_misc, mask, geneve_oam); + + spec->outer_ipv6_flow_label = + MLX5_GET(fte_match_set_misc, mask, outer_ipv6_flow_label); + + spec->inner_ipv6_flow_label = + MLX5_GET(fte_match_set_misc, mask, inner_ipv6_flow_label); + + spec->geneve_opt_len = MLX5_GET(fte_match_set_misc, mask, geneve_opt_len); + spec->geneve_protocol_type = + MLX5_GET(fte_match_set_misc, mask, geneve_protocol_type); + + spec->bth_dst_qp = MLX5_GET(fte_match_set_misc, mask, bth_dst_qp); +} + +static void dr_ste_copy_mask_spec(char *mask, struct mlx5dr_match_spec *spec) +{ + u32 raw_ip[4]; + + spec->smac_47_16 = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_47_16); + + spec->smac_15_0 = MLX5_GET(fte_match_set_lyr_2_4, mask, smac_15_0); + spec->ethertype = MLX5_GET(fte_match_set_lyr_2_4, mask, ethertype); + + spec->dmac_47_16 = MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_47_16); + + spec->dmac_15_0 = MLX5_GET(fte_match_set_lyr_2_4, mask, dmac_15_0); + spec->first_prio = MLX5_GET(fte_match_set_lyr_2_4, mask, first_prio); + spec->first_cfi = MLX5_GET(fte_match_set_lyr_2_4, mask, first_cfi); + spec->first_vid = MLX5_GET(fte_match_set_lyr_2_4, mask, first_vid); + + spec->ip_protocol = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_protocol); + spec->ip_dscp = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_dscp); + spec->ip_ecn = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_ecn); + spec->cvlan_tag = MLX5_GET(fte_match_set_lyr_2_4, mask, cvlan_tag); + spec->svlan_tag = MLX5_GET(fte_match_set_lyr_2_4, mask, svlan_tag); + spec->frag = MLX5_GET(fte_match_set_lyr_2_4, mask, frag); + spec->ip_version = MLX5_GET(fte_match_set_lyr_2_4, mask, ip_version); + spec->tcp_flags = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_flags); + spec->tcp_sport = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_sport); + spec->tcp_dport = MLX5_GET(fte_match_set_lyr_2_4, mask, tcp_dport); + + spec->ttl_hoplimit = MLX5_GET(fte_match_set_lyr_2_4, mask, ttl_hoplimit); + + spec->udp_sport = MLX5_GET(fte_match_set_lyr_2_4, mask, udp_sport); + spec->udp_dport = MLX5_GET(fte_match_set_lyr_2_4, mask, udp_dport); + + memcpy(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask, + src_ipv4_src_ipv6.ipv6_layout.ipv6), + sizeof(raw_ip)); + + spec->src_ip_127_96 = be32_to_cpu(raw_ip[0]); + spec->src_ip_95_64 = be32_to_cpu(raw_ip[1]); + spec->src_ip_63_32 = be32_to_cpu(raw_ip[2]); + spec->src_ip_31_0 = be32_to_cpu(raw_ip[3]); + + memcpy(raw_ip, MLX5_ADDR_OF(fte_match_set_lyr_2_4, mask, + dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + sizeof(raw_ip)); + + spec->dst_ip_127_96 = be32_to_cpu(raw_ip[0]); + spec->dst_ip_95_64 = be32_to_cpu(raw_ip[1]); + spec->dst_ip_63_32 = be32_to_cpu(raw_ip[2]); + spec->dst_ip_31_0 = be32_to_cpu(raw_ip[3]); +} + +static void dr_ste_copy_mask_misc2(char *mask, struct mlx5dr_match_misc2 *spec) +{ + spec->outer_first_mpls_label = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_label); + spec->outer_first_mpls_exp = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_exp); + spec->outer_first_mpls_s_bos = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_s_bos); + spec->outer_first_mpls_ttl = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls.mpls_ttl); + spec->inner_first_mpls_label = + MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_label); + spec->inner_first_mpls_exp = + MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_exp); + spec->inner_first_mpls_s_bos = + MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_s_bos); + spec->inner_first_mpls_ttl = + MLX5_GET(fte_match_set_misc2, mask, inner_first_mpls.mpls_ttl); + spec->outer_first_mpls_over_gre_label = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_label); + spec->outer_first_mpls_over_gre_exp = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_exp); + spec->outer_first_mpls_over_gre_s_bos = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_s_bos); + spec->outer_first_mpls_over_gre_ttl = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_gre.mpls_ttl); + spec->outer_first_mpls_over_udp_label = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_label); + spec->outer_first_mpls_over_udp_exp = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_exp); + spec->outer_first_mpls_over_udp_s_bos = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_s_bos); + spec->outer_first_mpls_over_udp_ttl = + MLX5_GET(fte_match_set_misc2, mask, outer_first_mpls_over_udp.mpls_ttl); + spec->metadata_reg_c_7 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_7); + spec->metadata_reg_c_6 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_6); + spec->metadata_reg_c_5 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_5); + spec->metadata_reg_c_4 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_4); + spec->metadata_reg_c_3 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_3); + spec->metadata_reg_c_2 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_2); + spec->metadata_reg_c_1 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_1); + spec->metadata_reg_c_0 = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_c_0); + spec->metadata_reg_a = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_a); + spec->metadata_reg_b = MLX5_GET(fte_match_set_misc2, mask, metadata_reg_b); +} + +static void dr_ste_copy_mask_misc3(char *mask, struct mlx5dr_match_misc3 *spec) +{ + spec->inner_tcp_seq_num = MLX5_GET(fte_match_set_misc3, mask, inner_tcp_seq_num); + spec->outer_tcp_seq_num = MLX5_GET(fte_match_set_misc3, mask, outer_tcp_seq_num); + spec->inner_tcp_ack_num = MLX5_GET(fte_match_set_misc3, mask, inner_tcp_ack_num); + spec->outer_tcp_ack_num = MLX5_GET(fte_match_set_misc3, mask, outer_tcp_ack_num); + spec->outer_vxlan_gpe_vni = + MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_vni); + spec->outer_vxlan_gpe_next_protocol = + MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_next_protocol); + spec->outer_vxlan_gpe_flags = + MLX5_GET(fte_match_set_misc3, mask, outer_vxlan_gpe_flags); + spec->icmpv4_header_data = MLX5_GET(fte_match_set_misc3, mask, icmp_header_data); + spec->icmpv6_header_data = + MLX5_GET(fte_match_set_misc3, mask, icmpv6_header_data); + spec->icmpv4_type = MLX5_GET(fte_match_set_misc3, mask, icmp_type); + spec->icmpv4_code = MLX5_GET(fte_match_set_misc3, mask, icmp_code); + spec->icmpv6_type = MLX5_GET(fte_match_set_misc3, mask, icmpv6_type); + spec->icmpv6_code = MLX5_GET(fte_match_set_misc3, mask, icmpv6_code); +} + +void mlx5dr_ste_copy_param(u8 match_criteria, + struct mlx5dr_match_param *set_param, + struct mlx5dr_match_parameters *mask) +{ + u8 tail_param[MLX5_ST_SZ_BYTES(fte_match_set_lyr_2_4)] = {}; + u8 *data = (u8 *)mask->match_buf; + size_t param_location; + void *buff; + + if (match_criteria & DR_MATCHER_CRITERIA_OUTER) { + if (mask->match_sz < sizeof(struct mlx5dr_match_spec)) { + memcpy(tail_param, data, mask->match_sz); + buff = tail_param; + } else { + buff = mask->match_buf; + } + dr_ste_copy_mask_spec(buff, &set_param->outer); + } + param_location = sizeof(struct mlx5dr_match_spec); + + if (match_criteria & DR_MATCHER_CRITERIA_MISC) { + if (mask->match_sz < param_location + + sizeof(struct mlx5dr_match_misc)) { + memcpy(tail_param, data + param_location, + mask->match_sz - param_location); + buff = tail_param; + } else { + buff = data + param_location; + } + dr_ste_copy_mask_misc(buff, &set_param->misc); + } + param_location += sizeof(struct mlx5dr_match_misc); + + if (match_criteria & DR_MATCHER_CRITERIA_INNER) { + if (mask->match_sz < param_location + + sizeof(struct mlx5dr_match_spec)) { + memcpy(tail_param, data + param_location, + mask->match_sz - param_location); + buff = tail_param; + } else { + buff = data + param_location; + } + dr_ste_copy_mask_spec(buff, &set_param->inner); + } + param_location += sizeof(struct mlx5dr_match_spec); + + if (match_criteria & DR_MATCHER_CRITERIA_MISC2) { + if (mask->match_sz < param_location + + sizeof(struct mlx5dr_match_misc2)) { + memcpy(tail_param, data + param_location, + mask->match_sz - param_location); + buff = tail_param; + } else { + buff = data + param_location; + } + dr_ste_copy_mask_misc2(buff, &set_param->misc2); + } + + param_location += sizeof(struct mlx5dr_match_misc2); + + if (match_criteria & DR_MATCHER_CRITERIA_MISC3) { + if (mask->match_sz < param_location + + sizeof(struct mlx5dr_match_misc3)) { + memcpy(tail_param, data + param_location, + mask->match_sz - param_location); + buff = tail_param; + } else { + buff = data + param_location; + } + dr_ste_copy_mask_misc3(buff, &set_param->misc3); + } +} + +static int dr_ste_build_eth_l2_src_des_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l2_src_dst, tag, dmac_47_16, spec, dmac_47_16); + DR_STE_SET_TAG(eth_l2_src_dst, tag, dmac_15_0, spec, dmac_15_0); + + if (spec->smac_47_16 || spec->smac_15_0) { + MLX5_SET(ste_eth_l2_src_dst, tag, smac_47_32, + spec->smac_47_16 >> 16); + MLX5_SET(ste_eth_l2_src_dst, tag, smac_31_0, + spec->smac_47_16 << 16 | spec->smac_15_0); + spec->smac_47_16 = 0; + spec->smac_15_0 = 0; + } + + if (spec->ip_version) { + if (spec->ip_version == IP_VERSION_IPV4) { + MLX5_SET(ste_eth_l2_src_dst, tag, l3_type, STE_IPV4); + spec->ip_version = 0; + } else if (spec->ip_version == IP_VERSION_IPV6) { + MLX5_SET(ste_eth_l2_src_dst, tag, l3_type, STE_IPV6); + spec->ip_version = 0; + } else { + pr_info("Unsupported ip_version value\n"); + return -EINVAL; + } + } + + DR_STE_SET_TAG(eth_l2_src_dst, tag, first_vlan_id, spec, first_vid); + DR_STE_SET_TAG(eth_l2_src_dst, tag, first_cfi, spec, first_cfi); + DR_STE_SET_TAG(eth_l2_src_dst, tag, first_priority, spec, first_prio); + + if (spec->cvlan_tag) { + MLX5_SET(ste_eth_l2_src_dst, tag, first_vlan_qualifier, DR_STE_CVLAN); + spec->cvlan_tag = 0; + } else if (spec->svlan_tag) { + MLX5_SET(ste_eth_l2_src_dst, tag, first_vlan_qualifier, DR_STE_SVLAN); + spec->svlan_tag = 0; + } + return 0; +} + +int mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + int ret; + + ret = dr_ste_build_eth_l2_src_des_bit_mask(mask, inner, sb->bit_mask); + if (ret) + return ret; + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_SRC_DST, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l2_src_des_tag; + + return 0; +} + +static void dr_ste_build_eth_l3_ipv6_dst_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_127_96, mask, dst_ip_127_96); + DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_95_64, mask, dst_ip_95_64); + DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_63_32, mask, dst_ip_63_32); + DR_STE_SET_MASK_V(eth_l3_ipv6_dst, bit_mask, dst_ip_31_0, mask, dst_ip_31_0); +} + +static int dr_ste_build_eth_l3_ipv6_dst_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_127_96, spec, dst_ip_127_96); + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_95_64, spec, dst_ip_95_64); + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_63_32, spec, dst_ip_63_32); + DR_STE_SET_TAG(eth_l3_ipv6_dst, tag, dst_ip_31_0, spec, dst_ip_31_0); + + return 0; +} + +void mlx5dr_ste_build_eth_l3_ipv6_dst(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l3_ipv6_dst_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV6_DST, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv6_dst_tag; +} + +static void dr_ste_build_eth_l3_ipv6_src_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_127_96, mask, src_ip_127_96); + DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_95_64, mask, src_ip_95_64); + DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_63_32, mask, src_ip_63_32); + DR_STE_SET_MASK_V(eth_l3_ipv6_src, bit_mask, src_ip_31_0, mask, src_ip_31_0); +} + +static int dr_ste_build_eth_l3_ipv6_src_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_127_96, spec, src_ip_127_96); + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_95_64, spec, src_ip_95_64); + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_63_32, spec, src_ip_63_32); + DR_STE_SET_TAG(eth_l3_ipv6_src, tag, src_ip_31_0, spec, src_ip_31_0); + + return 0; +} + +void mlx5dr_ste_build_eth_l3_ipv6_src(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l3_ipv6_src_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV6_SRC, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv6_src_tag; +} + +static void dr_ste_build_eth_l3_ipv4_5_tuple_bit_mask(struct mlx5dr_match_param *value, + bool inner, + u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + destination_address, mask, dst_ip_31_0); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + source_address, mask, src_ip_31_0); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + destination_port, mask, tcp_dport); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + destination_port, mask, udp_dport); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + source_port, mask, tcp_sport); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + source_port, mask, udp_sport); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + protocol, mask, ip_protocol); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + fragmented, mask, frag); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + dscp, mask, ip_dscp); + DR_STE_SET_MASK_V(eth_l3_ipv4_5_tuple, bit_mask, + ecn, mask, ip_ecn); + + if (mask->tcp_flags) { + DR_STE_SET_TCP_FLAGS(eth_l3_ipv4_5_tuple, bit_mask, mask); + mask->tcp_flags = 0; + } +} + +static int dr_ste_build_eth_l3_ipv4_5_tuple_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_address, spec, dst_ip_31_0); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_address, spec, src_ip_31_0); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_port, spec, tcp_dport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, destination_port, spec, udp_dport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_port, spec, tcp_sport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, source_port, spec, udp_sport); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, protocol, spec, ip_protocol); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, fragmented, spec, frag); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, dscp, spec, ip_dscp); + DR_STE_SET_TAG(eth_l3_ipv4_5_tuple, tag, ecn, spec, ip_ecn); + + if (spec->tcp_flags) { + DR_STE_SET_TCP_FLAGS(eth_l3_ipv4_5_tuple, tag, spec); + spec->tcp_flags = 0; + } + + return 0; +} + +void mlx5dr_ste_build_eth_l3_ipv4_5_tuple(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l3_ipv4_5_tuple_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV4_5_TUPLE, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv4_5_tuple_tag; +} + +static void +dr_ste_build_eth_l2_src_or_dst_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc_mask = &value->misc; + + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_vlan_id, mask, first_vid); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_cfi, mask, first_cfi); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, first_priority, mask, first_prio); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, ip_fragmented, mask, frag); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, l3_ethertype, mask, ethertype); + DR_STE_SET_MASK(eth_l2_src, bit_mask, l3_type, mask, ip_version); + + if (mask->svlan_tag || mask->cvlan_tag) { + MLX5_SET(ste_eth_l2_src, bit_mask, first_vlan_qualifier, -1); + mask->cvlan_tag = 0; + mask->svlan_tag = 0; + } + + if (inner) { + if (misc_mask->inner_second_cvlan_tag || + misc_mask->inner_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src, bit_mask, second_vlan_qualifier, -1); + misc_mask->inner_second_cvlan_tag = 0; + misc_mask->inner_second_svlan_tag = 0; + } + + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_vlan_id, misc_mask, inner_second_vid); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_cfi, misc_mask, inner_second_cfi); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_priority, misc_mask, inner_second_prio); + } else { + if (misc_mask->outer_second_cvlan_tag || + misc_mask->outer_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src, bit_mask, second_vlan_qualifier, -1); + misc_mask->outer_second_cvlan_tag = 0; + misc_mask->outer_second_svlan_tag = 0; + } + + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_vlan_id, misc_mask, outer_second_vid); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_cfi, misc_mask, outer_second_cfi); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, + second_priority, misc_mask, outer_second_prio); + } +} + +static int dr_ste_build_eth_l2_src_or_dst_tag(struct mlx5dr_match_param *value, + bool inner, u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc_spec = &value->misc; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l2_src, tag, first_vlan_id, spec, first_vid); + DR_STE_SET_TAG(eth_l2_src, tag, first_cfi, spec, first_cfi); + DR_STE_SET_TAG(eth_l2_src, tag, first_priority, spec, first_prio); + DR_STE_SET_TAG(eth_l2_src, tag, ip_fragmented, spec, frag); + DR_STE_SET_TAG(eth_l2_src, tag, l3_ethertype, spec, ethertype); + + if (spec->ip_version) { + if (spec->ip_version == IP_VERSION_IPV4) { + MLX5_SET(ste_eth_l2_src, tag, l3_type, STE_IPV4); + spec->ip_version = 0; + } else if (spec->ip_version == IP_VERSION_IPV6) { + MLX5_SET(ste_eth_l2_src, tag, l3_type, STE_IPV6); + spec->ip_version = 0; + } else { + pr_info("Unsupported ip_version value\n"); + return -EINVAL; + } + } + + if (spec->cvlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, first_vlan_qualifier, DR_STE_CVLAN); + spec->cvlan_tag = 0; + } else if (spec->svlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, first_vlan_qualifier, DR_STE_SVLAN); + spec->svlan_tag = 0; + } + + if (inner) { + if (misc_spec->inner_second_cvlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_CVLAN); + misc_spec->inner_second_cvlan_tag = 0; + } else if (misc_spec->inner_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_SVLAN); + misc_spec->inner_second_svlan_tag = 0; + } + + DR_STE_SET_TAG(eth_l2_src, tag, second_vlan_id, misc_spec, inner_second_vid); + DR_STE_SET_TAG(eth_l2_src, tag, second_cfi, misc_spec, inner_second_cfi); + DR_STE_SET_TAG(eth_l2_src, tag, second_priority, misc_spec, inner_second_prio); + } else { + if (misc_spec->outer_second_cvlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_CVLAN); + misc_spec->outer_second_cvlan_tag = 0; + } else if (misc_spec->outer_second_svlan_tag) { + MLX5_SET(ste_eth_l2_src, tag, second_vlan_qualifier, DR_STE_SVLAN); + misc_spec->outer_second_svlan_tag = 0; + } + DR_STE_SET_TAG(eth_l2_src, tag, second_vlan_id, misc_spec, outer_second_vid); + DR_STE_SET_TAG(eth_l2_src, tag, second_cfi, misc_spec, outer_second_cfi); + DR_STE_SET_TAG(eth_l2_src, tag, second_priority, misc_spec, outer_second_prio); + } + + return 0; +} + +static void dr_ste_build_eth_l2_src_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, smac_47_16, mask, smac_47_16); + DR_STE_SET_MASK_V(eth_l2_src, bit_mask, smac_15_0, mask, smac_15_0); + + dr_ste_build_eth_l2_src_or_dst_bit_mask(value, inner, bit_mask); +} + +static int dr_ste_build_eth_l2_src_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l2_src, tag, smac_47_16, spec, smac_47_16); + DR_STE_SET_TAG(eth_l2_src, tag, smac_15_0, spec, smac_15_0); + + return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, hw_ste_p); +} + +void mlx5dr_ste_build_eth_l2_src(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l2_src_bit_mask(mask, inner, sb->bit_mask); + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_SRC, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l2_src_tag; +} + +static void dr_ste_build_eth_l2_dst_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l2_dst, bit_mask, dmac_47_16, mask, dmac_47_16); + DR_STE_SET_MASK_V(eth_l2_dst, bit_mask, dmac_15_0, mask, dmac_15_0); + + dr_ste_build_eth_l2_src_or_dst_bit_mask(value, inner, bit_mask); +} + +static int dr_ste_build_eth_l2_dst_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l2_dst, tag, dmac_47_16, spec, dmac_47_16); + DR_STE_SET_TAG(eth_l2_dst, tag, dmac_15_0, spec, dmac_15_0); + + return dr_ste_build_eth_l2_src_or_dst_tag(value, sb->inner, hw_ste_p); +} + +void mlx5dr_ste_build_eth_l2_dst(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l2_dst_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL2_DST, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l2_dst_tag; +} + +static void dr_ste_build_eth_l2_tnl_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + struct mlx5dr_match_misc *misc = &value->misc; + + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, dmac_47_16, mask, dmac_47_16); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, dmac_15_0, mask, dmac_15_0); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_vlan_id, mask, first_vid); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_cfi, mask, first_cfi); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, first_priority, mask, first_prio); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, ip_fragmented, mask, frag); + DR_STE_SET_MASK_V(eth_l2_tnl, bit_mask, l3_ethertype, mask, ethertype); + DR_STE_SET_MASK(eth_l2_tnl, bit_mask, l3_type, mask, ip_version); + + if (misc->vxlan_vni) { + MLX5_SET(ste_eth_l2_tnl, bit_mask, + l2_tunneling_network_id, (misc->vxlan_vni << 8)); + misc->vxlan_vni = 0; + } + + if (mask->svlan_tag || mask->cvlan_tag) { + MLX5_SET(ste_eth_l2_tnl, bit_mask, first_vlan_qualifier, -1); + mask->cvlan_tag = 0; + mask->svlan_tag = 0; + } +} + +static int dr_ste_build_eth_l2_tnl_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc *misc = &value->misc; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l2_tnl, tag, dmac_47_16, spec, dmac_47_16); + DR_STE_SET_TAG(eth_l2_tnl, tag, dmac_15_0, spec, dmac_15_0); + DR_STE_SET_TAG(eth_l2_tnl, tag, first_vlan_id, spec, first_vid); + DR_STE_SET_TAG(eth_l2_tnl, tag, first_cfi, spec, first_cfi); + DR_STE_SET_TAG(eth_l2_tnl, tag, ip_fragmented, spec, frag); + DR_STE_SET_TAG(eth_l2_tnl, tag, first_priority, spec, first_prio); + DR_STE_SET_TAG(eth_l2_tnl, tag, l3_ethertype, spec, ethertype); + + if (misc->vxlan_vni) { + MLX5_SET(ste_eth_l2_tnl, tag, l2_tunneling_network_id, + (misc->vxlan_vni << 8)); + misc->vxlan_vni = 0; + } + + if (spec->cvlan_tag) { + MLX5_SET(ste_eth_l2_tnl, tag, first_vlan_qualifier, DR_STE_CVLAN); + spec->cvlan_tag = 0; + } else if (spec->svlan_tag) { + MLX5_SET(ste_eth_l2_tnl, tag, first_vlan_qualifier, DR_STE_SVLAN); + spec->svlan_tag = 0; + } + + if (spec->ip_version) { + if (spec->ip_version == IP_VERSION_IPV4) { + MLX5_SET(ste_eth_l2_tnl, tag, l3_type, STE_IPV4); + spec->ip_version = 0; + } else if (spec->ip_version == IP_VERSION_IPV6) { + MLX5_SET(ste_eth_l2_tnl, tag, l3_type, STE_IPV6); + spec->ip_version = 0; + } else { + return -EINVAL; + } + } + + return 0; +} + +void mlx5dr_ste_build_eth_l2_tnl(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, bool inner, bool rx) +{ + dr_ste_build_eth_l2_tnl_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_ETHL2_TUNNELING_I; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l2_tnl_tag; +} + +static void dr_ste_build_eth_l3_ipv4_misc_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l3_ipv4_misc, bit_mask, time_to_live, mask, ttl_hoplimit); +} + +static int dr_ste_build_eth_l3_ipv4_misc_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l3_ipv4_misc, tag, time_to_live, spec, ttl_hoplimit); + + return 0; +} + +void mlx5dr_ste_build_eth_l3_ipv4_misc(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l3_ipv4_misc_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL3_IPV4_MISC, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l3_ipv4_misc_tag; +} + +static void dr_ste_build_ipv6_l3_l4_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_spec *mask = inner ? &value->inner : &value->outer; + + DR_STE_SET_MASK_V(eth_l4, bit_mask, dst_port, mask, tcp_dport); + DR_STE_SET_MASK_V(eth_l4, bit_mask, src_port, mask, tcp_sport); + DR_STE_SET_MASK_V(eth_l4, bit_mask, dst_port, mask, udp_dport); + DR_STE_SET_MASK_V(eth_l4, bit_mask, src_port, mask, udp_sport); + DR_STE_SET_MASK_V(eth_l4, bit_mask, protocol, mask, ip_protocol); + DR_STE_SET_MASK_V(eth_l4, bit_mask, fragmented, mask, frag); + DR_STE_SET_MASK_V(eth_l4, bit_mask, dscp, mask, ip_dscp); + DR_STE_SET_MASK_V(eth_l4, bit_mask, ecn, mask, ip_ecn); + DR_STE_SET_MASK_V(eth_l4, bit_mask, ipv6_hop_limit, mask, ttl_hoplimit); + + if (mask->tcp_flags) { + DR_STE_SET_TCP_FLAGS(eth_l4, bit_mask, mask); + mask->tcp_flags = 0; + } +} + +static int dr_ste_build_ipv6_l3_l4_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct mlx5dr_match_spec *spec = sb->inner ? &value->inner : &value->outer; + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(eth_l4, tag, dst_port, spec, tcp_dport); + DR_STE_SET_TAG(eth_l4, tag, src_port, spec, tcp_sport); + DR_STE_SET_TAG(eth_l4, tag, dst_port, spec, udp_dport); + DR_STE_SET_TAG(eth_l4, tag, src_port, spec, udp_sport); + DR_STE_SET_TAG(eth_l4, tag, protocol, spec, ip_protocol); + DR_STE_SET_TAG(eth_l4, tag, fragmented, spec, frag); + DR_STE_SET_TAG(eth_l4, tag, dscp, spec, ip_dscp); + DR_STE_SET_TAG(eth_l4, tag, ecn, spec, ip_ecn); + DR_STE_SET_TAG(eth_l4, tag, ipv6_hop_limit, spec, ttl_hoplimit); + + if (spec->tcp_flags) { + DR_STE_SET_TCP_FLAGS(eth_l4, tag, spec); + spec->tcp_flags = 0; + } + + return 0; +} + +void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_ipv6_l3_l4_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL4, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_ipv6_l3_l4_tag; +} + +static int dr_ste_build_empty_always_hit_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + return 0; +} + +void mlx5dr_ste_build_empty_always_hit(struct mlx5dr_ste_build *sb, bool rx) +{ + sb->rx = rx; + sb->lu_type = MLX5DR_STE_LU_TYPE_DONT_CARE; + sb->byte_mask = 0; + sb->ste_build_tag_func = &dr_ste_build_empty_always_hit_tag; +} + +static void dr_ste_build_mpls_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc2 *misc2_mask = &value->misc2; + + if (inner) + DR_STE_SET_MPLS_MASK(mpls, misc2_mask, inner, bit_mask); + else + DR_STE_SET_MPLS_MASK(mpls, misc2_mask, outer, bit_mask); +} + +static int dr_ste_build_mpls_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc2 *misc2_mask = &value->misc2; + u8 *tag = hw_ste->tag; + + if (sb->inner) + DR_STE_SET_MPLS_TAG(mpls, misc2_mask, inner, tag); + else + DR_STE_SET_MPLS_TAG(mpls, misc2_mask, outer, tag); + + return 0; +} + +void mlx5dr_ste_build_mpls(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_mpls_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(MPLS_FIRST, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_mpls_tag; +} + +static void dr_ste_build_gre_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc *misc_mask = &value->misc; + + DR_STE_SET_MASK_V(gre, bit_mask, gre_protocol, misc_mask, gre_protocol); + DR_STE_SET_MASK_V(gre, bit_mask, gre_k_present, misc_mask, gre_k_present); + DR_STE_SET_MASK_V(gre, bit_mask, gre_key_h, misc_mask, gre_key_h); + DR_STE_SET_MASK_V(gre, bit_mask, gre_key_l, misc_mask, gre_key_l); + + DR_STE_SET_MASK_V(gre, bit_mask, gre_c_present, misc_mask, gre_c_present); + DR_STE_SET_MASK_V(gre, bit_mask, gre_s_present, misc_mask, gre_s_present); +} + +static int dr_ste_build_gre_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc *misc = &value->misc; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(gre, tag, gre_protocol, misc, gre_protocol); + + DR_STE_SET_TAG(gre, tag, gre_k_present, misc, gre_k_present); + DR_STE_SET_TAG(gre, tag, gre_key_h, misc, gre_key_h); + DR_STE_SET_TAG(gre, tag, gre_key_l, misc, gre_key_l); + + DR_STE_SET_TAG(gre, tag, gre_c_present, misc, gre_c_present); + + DR_STE_SET_TAG(gre, tag, gre_s_present, misc, gre_s_present); + + return 0; +} + +void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, bool inner, bool rx) +{ + dr_ste_build_gre_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_GRE; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_gre_tag; +} + +static void dr_ste_build_flex_parser_0_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + + if (DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(misc_2_mask)) { + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_label, + misc_2_mask, outer_first_mpls_over_gre_label); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_exp, + misc_2_mask, outer_first_mpls_over_gre_exp); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_s_bos, + misc_2_mask, outer_first_mpls_over_gre_s_bos); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_ttl, + misc_2_mask, outer_first_mpls_over_gre_ttl); + } else { + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_label, + misc_2_mask, outer_first_mpls_over_udp_label); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_exp, + misc_2_mask, outer_first_mpls_over_udp_exp); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_s_bos, + misc_2_mask, outer_first_mpls_over_udp_s_bos); + + DR_STE_SET_MASK_V(flex_parser_0, bit_mask, parser_3_ttl, + misc_2_mask, outer_first_mpls_over_udp_ttl); + } +} + +static int dr_ste_build_flex_parser_0_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + u8 *tag = hw_ste->tag; + + if (DR_STE_IS_OUTER_MPLS_OVER_GRE_SET(misc_2_mask)) { + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_label, + misc_2_mask, outer_first_mpls_over_gre_label); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_exp, + misc_2_mask, outer_first_mpls_over_gre_exp); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_s_bos, + misc_2_mask, outer_first_mpls_over_gre_s_bos); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_ttl, + misc_2_mask, outer_first_mpls_over_gre_ttl); + } else { + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_label, + misc_2_mask, outer_first_mpls_over_udp_label); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_exp, + misc_2_mask, outer_first_mpls_over_udp_exp); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_s_bos, + misc_2_mask, outer_first_mpls_over_udp_s_bos); + + DR_STE_SET_TAG(flex_parser_0, tag, parser_3_ttl, + misc_2_mask, outer_first_mpls_over_udp_ttl); + } + return 0; +} + +void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_flex_parser_0_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_0; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_flex_parser_0_tag; +} + +#define ICMP_TYPE_OFFSET_FIRST_DW 24 +#define ICMP_CODE_OFFSET_FIRST_DW 16 +#define ICMP_HEADER_DATA_OFFSET_SECOND_DW 0 + +static int dr_ste_build_flex_parser_1_bit_mask(struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + u8 *bit_mask) +{ + struct mlx5dr_match_misc3 *misc_3_mask = &mask->misc3; + bool is_ipv4_mask = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3_mask); + u32 icmp_header_data_mask; + u32 icmp_type_mask; + u32 icmp_code_mask; + int dw0_location; + int dw1_location; + + if (is_ipv4_mask) { + icmp_header_data_mask = misc_3_mask->icmpv4_header_data; + icmp_type_mask = misc_3_mask->icmpv4_type; + icmp_code_mask = misc_3_mask->icmpv4_code; + dw0_location = caps->flex_parser_id_icmp_dw0; + dw1_location = caps->flex_parser_id_icmp_dw1; + } else { + icmp_header_data_mask = misc_3_mask->icmpv6_header_data; + icmp_type_mask = misc_3_mask->icmpv6_type; + icmp_code_mask = misc_3_mask->icmpv6_code; + dw0_location = caps->flex_parser_id_icmpv6_dw0; + dw1_location = caps->flex_parser_id_icmpv6_dw1; + } + + switch (dw0_location) { + case 4: + if (icmp_type_mask) { + MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_4, + (icmp_type_mask << ICMP_TYPE_OFFSET_FIRST_DW)); + if (is_ipv4_mask) + misc_3_mask->icmpv4_type = 0; + else + misc_3_mask->icmpv6_type = 0; + } + if (icmp_code_mask) { + u32 cur_val = MLX5_GET(ste_flex_parser_1, bit_mask, + flex_parser_4); + MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_4, + cur_val | (icmp_code_mask << ICMP_CODE_OFFSET_FIRST_DW)); + if (is_ipv4_mask) + misc_3_mask->icmpv4_code = 0; + else + misc_3_mask->icmpv6_code = 0; + } + break; + default: + return -EINVAL; + } + + switch (dw1_location) { + case 5: + if (icmp_header_data_mask) { + MLX5_SET(ste_flex_parser_1, bit_mask, flex_parser_5, + (icmp_header_data_mask << ICMP_HEADER_DATA_OFFSET_SECOND_DW)); + if (is_ipv4_mask) + misc_3_mask->icmpv4_header_data = 0; + else + misc_3_mask->icmpv6_header_data = 0; + } + break; + default: + return -EINVAL; + } + + return 0; +} + +static int dr_ste_build_flex_parser_1_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc3 *misc_3 = &value->misc3; + u8 *tag = hw_ste->tag; + u32 icmp_header_data; + int dw0_location; + int dw1_location; + u32 icmp_type; + u32 icmp_code; + bool is_ipv4; + + is_ipv4 = DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(misc_3); + if (is_ipv4) { + icmp_header_data = misc_3->icmpv4_header_data; + icmp_type = misc_3->icmpv4_type; + icmp_code = misc_3->icmpv4_code; + dw0_location = sb->caps->flex_parser_id_icmp_dw0; + dw1_location = sb->caps->flex_parser_id_icmp_dw1; + } else { + icmp_header_data = misc_3->icmpv6_header_data; + icmp_type = misc_3->icmpv6_type; + icmp_code = misc_3->icmpv6_code; + dw0_location = sb->caps->flex_parser_id_icmpv6_dw0; + dw1_location = sb->caps->flex_parser_id_icmpv6_dw1; + } + + switch (dw0_location) { + case 4: + if (icmp_type) { + MLX5_SET(ste_flex_parser_1, tag, flex_parser_4, + (icmp_type << ICMP_TYPE_OFFSET_FIRST_DW)); + if (is_ipv4) + misc_3->icmpv4_type = 0; + else + misc_3->icmpv6_type = 0; + } + + if (icmp_code) { + u32 cur_val = MLX5_GET(ste_flex_parser_1, tag, + flex_parser_4); + MLX5_SET(ste_flex_parser_1, tag, flex_parser_4, + cur_val | (icmp_code << ICMP_CODE_OFFSET_FIRST_DW)); + if (is_ipv4) + misc_3->icmpv4_code = 0; + else + misc_3->icmpv6_code = 0; + } + break; + default: + return -EINVAL; + } + + switch (dw1_location) { + case 5: + if (icmp_header_data) { + MLX5_SET(ste_flex_parser_1, tag, flex_parser_5, + (icmp_header_data << ICMP_HEADER_DATA_OFFSET_SECOND_DW)); + if (is_ipv4) + misc_3->icmpv4_header_data = 0; + else + misc_3->icmpv6_header_data = 0; + } + break; + default: + return -EINVAL; + } + + return 0; +} + +int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx) +{ + int ret; + + ret = dr_ste_build_flex_parser_1_bit_mask(mask, caps, sb->bit_mask); + if (ret) + return ret; + + sb->rx = rx; + sb->inner = inner; + sb->caps = caps; + sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_1; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_flex_parser_1_tag; + + return 0; +} + +static void dr_ste_build_general_purpose_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + + DR_STE_SET_MASK_V(general_purpose, bit_mask, + general_purpose_lookup_field, misc_2_mask, + metadata_reg_a); +} + +static int dr_ste_build_general_purpose_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(general_purpose, tag, general_purpose_lookup_field, + misc_2_mask, metadata_reg_a); + + return 0; +} + +void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_general_purpose_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_GENERAL_PURPOSE; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_general_purpose_tag; +} + +static void dr_ste_build_eth_l4_misc_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc3 *misc_3_mask = &value->misc3; + + if (inner) { + DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, seq_num, misc_3_mask, + inner_tcp_seq_num); + DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, ack_num, misc_3_mask, + inner_tcp_ack_num); + } else { + DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, seq_num, misc_3_mask, + outer_tcp_seq_num); + DR_STE_SET_MASK_V(eth_l4_misc, bit_mask, ack_num, misc_3_mask, + outer_tcp_ack_num); + } +} + +static int dr_ste_build_eth_l4_misc_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc3 *misc3 = &value->misc3; + u8 *tag = hw_ste->tag; + + if (sb->inner) { + DR_STE_SET_TAG(eth_l4_misc, tag, seq_num, misc3, inner_tcp_seq_num); + DR_STE_SET_TAG(eth_l4_misc, tag, ack_num, misc3, inner_tcp_ack_num); + } else { + DR_STE_SET_TAG(eth_l4_misc, tag, seq_num, misc3, outer_tcp_seq_num); + DR_STE_SET_TAG(eth_l4_misc, tag, ack_num, misc3, outer_tcp_ack_num); + } + + return 0; +} + +void mlx5dr_ste_build_eth_l4_misc(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_eth_l4_misc_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = DR_STE_CALC_LU_TYPE(ETHL4_MISC, rx, inner); + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_eth_l4_misc_tag; +} + +static void dr_ste_build_flex_parser_tnl_bit_mask(struct mlx5dr_match_param *value, + bool inner, u8 *bit_mask) +{ + struct mlx5dr_match_misc3 *misc_3_mask = &value->misc3; + + if (misc_3_mask->outer_vxlan_gpe_flags || + misc_3_mask->outer_vxlan_gpe_next_protocol) { + MLX5_SET(ste_flex_parser_tnl, bit_mask, + flex_parser_tunneling_header_63_32, + (misc_3_mask->outer_vxlan_gpe_flags << 24) | + (misc_3_mask->outer_vxlan_gpe_next_protocol)); + misc_3_mask->outer_vxlan_gpe_flags = 0; + misc_3_mask->outer_vxlan_gpe_next_protocol = 0; + } + + if (misc_3_mask->outer_vxlan_gpe_vni) { + MLX5_SET(ste_flex_parser_tnl, bit_mask, + flex_parser_tunneling_header_31_0, + misc_3_mask->outer_vxlan_gpe_vni << 8); + misc_3_mask->outer_vxlan_gpe_vni = 0; + } +} + +static int dr_ste_build_flex_parser_tnl_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc3 *misc3 = &value->misc3; + u8 *tag = hw_ste->tag; + + if (misc3->outer_vxlan_gpe_flags || + misc3->outer_vxlan_gpe_next_protocol) { + MLX5_SET(ste_flex_parser_tnl, tag, + flex_parser_tunneling_header_63_32, + (misc3->outer_vxlan_gpe_flags << 24) | + (misc3->outer_vxlan_gpe_next_protocol)); + misc3->outer_vxlan_gpe_flags = 0; + misc3->outer_vxlan_gpe_next_protocol = 0; + } + + if (misc3->outer_vxlan_gpe_vni) { + MLX5_SET(ste_flex_parser_tnl, tag, + flex_parser_tunneling_header_31_0, + misc3->outer_vxlan_gpe_vni << 8); + misc3->outer_vxlan_gpe_vni = 0; + } + + return 0; +} + +void mlx5dr_ste_build_flex_parser_tnl(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_flex_parser_tnl_bit_mask(mask, inner, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_flex_parser_tnl_tag; +} + +static void dr_ste_build_register_0_bit_mask(struct mlx5dr_match_param *value, + u8 *bit_mask) +{ + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + + DR_STE_SET_MASK_V(register_0, bit_mask, register_0_h, + misc_2_mask, metadata_reg_c_0); + DR_STE_SET_MASK_V(register_0, bit_mask, register_0_l, + misc_2_mask, metadata_reg_c_1); + DR_STE_SET_MASK_V(register_0, bit_mask, register_1_h, + misc_2_mask, metadata_reg_c_2); + DR_STE_SET_MASK_V(register_0, bit_mask, register_1_l, + misc_2_mask, metadata_reg_c_3); +} + +static int dr_ste_build_register_0_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc2 *misc2 = &value->misc2; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(register_0, tag, register_0_h, misc2, metadata_reg_c_0); + DR_STE_SET_TAG(register_0, tag, register_0_l, misc2, metadata_reg_c_1); + DR_STE_SET_TAG(register_0, tag, register_1_h, misc2, metadata_reg_c_2); + DR_STE_SET_TAG(register_0, tag, register_1_l, misc2, metadata_reg_c_3); + + return 0; +} + +void mlx5dr_ste_build_register_0(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_register_0_bit_mask(mask, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_0; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_register_0_tag; +} + +static void dr_ste_build_register_1_bit_mask(struct mlx5dr_match_param *value, + u8 *bit_mask) +{ + struct mlx5dr_match_misc2 *misc_2_mask = &value->misc2; + + DR_STE_SET_MASK_V(register_1, bit_mask, register_2_h, + misc_2_mask, metadata_reg_c_4); + DR_STE_SET_MASK_V(register_1, bit_mask, register_2_l, + misc_2_mask, metadata_reg_c_5); + DR_STE_SET_MASK_V(register_1, bit_mask, register_3_h, + misc_2_mask, metadata_reg_c_6); + DR_STE_SET_MASK_V(register_1, bit_mask, register_3_l, + misc_2_mask, metadata_reg_c_7); +} + +static int dr_ste_build_register_1_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc2 *misc2 = &value->misc2; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(register_1, tag, register_2_h, misc2, metadata_reg_c_4); + DR_STE_SET_TAG(register_1, tag, register_2_l, misc2, metadata_reg_c_5); + DR_STE_SET_TAG(register_1, tag, register_3_h, misc2, metadata_reg_c_6); + DR_STE_SET_TAG(register_1, tag, register_3_l, misc2, metadata_reg_c_7); + + return 0; +} + +void mlx5dr_ste_build_register_1(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx) +{ + dr_ste_build_register_1_bit_mask(mask, sb->bit_mask); + + sb->rx = rx; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_1; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_register_1_tag; +} + +static int dr_ste_build_src_gvmi_qpn_bit_mask(struct mlx5dr_match_param *value, + u8 *bit_mask) +{ + struct mlx5dr_match_misc *misc_mask = &value->misc; + + if (misc_mask->source_port != 0xffff) + return -EINVAL; + + DR_STE_SET_MASK(src_gvmi_qp, bit_mask, source_gvmi, misc_mask, source_port); + DR_STE_SET_MASK(src_gvmi_qp, bit_mask, source_qp, misc_mask, source_sqn); + + return 0; +} + +static int dr_ste_build_src_gvmi_qpn_tag(struct mlx5dr_match_param *value, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p) +{ + struct dr_hw_ste_format *hw_ste = (struct dr_hw_ste_format *)hw_ste_p; + struct mlx5dr_match_misc *misc = &value->misc; + struct mlx5dr_cmd_vport_cap *vport_cap; + u8 *tag = hw_ste->tag; + + DR_STE_SET_TAG(src_gvmi_qp, tag, source_qp, misc, source_sqn); + + vport_cap = mlx5dr_get_vport_cap(sb->caps, misc->source_port); + if (!vport_cap) + return -EINVAL; + + if (vport_cap->vport_gvmi) + MLX5_SET(ste_src_gvmi_qp, tag, source_gvmi, vport_cap->vport_gvmi); + + misc->source_port = 0; + + return 0; +} + +int mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx) +{ + int ret; + + ret = dr_ste_build_src_gvmi_qpn_bit_mask(mask, sb->bit_mask); + if (ret) + return ret; + + sb->rx = rx; + sb->caps = caps; + sb->inner = inner; + sb->lu_type = MLX5DR_STE_LU_TYPE_SRC_GVMI_AND_QP; + sb->byte_mask = dr_ste_conv_bit_to_byte_mask(sb->bit_mask); + sb->ste_build_tag_func = &dr_ste_build_src_gvmi_qpn_tag; + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c new file mode 100644 index 000000000000..e178d8d3dbc9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_table.c @@ -0,0 +1,294 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies. */ + +#include "dr_types.h" + +int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl, + struct mlx5dr_action *action) +{ + struct mlx5dr_matcher *last_matcher = NULL; + struct mlx5dr_htbl_connect_info info; + struct mlx5dr_ste_htbl *last_htbl; + int ret; + + if (action && action->action_type != DR_ACTION_TYP_FT) + return -EOPNOTSUPP; + + mutex_lock(&tbl->dmn->mutex); + + if (!list_empty(&tbl->matcher_list)) + last_matcher = list_last_entry(&tbl->matcher_list, + struct mlx5dr_matcher, + matcher_list); + + if (tbl->dmn->type == MLX5DR_DOMAIN_TYPE_NIC_RX || + tbl->dmn->type == MLX5DR_DOMAIN_TYPE_FDB) { + if (last_matcher) + last_htbl = last_matcher->rx.e_anchor; + else + last_htbl = tbl->rx.s_anchor; + + tbl->rx.default_icm_addr = action ? + action->dest_tbl.tbl->rx.s_anchor->chunk->icm_addr : + tbl->rx.nic_dmn->default_icm_addr; + + info.type = CONNECT_MISS; + info.miss_icm_addr = tbl->rx.default_icm_addr; + + ret = mlx5dr_ste_htbl_init_and_postsend(tbl->dmn, + tbl->rx.nic_dmn, + last_htbl, + &info, true); + if (ret) { + mlx5dr_dbg(tbl->dmn, "Failed to set RX miss action, ret %d\n", ret); + goto out; + } + } + + if (tbl->dmn->type == MLX5DR_DOMAIN_TYPE_NIC_TX || + tbl->dmn->type == MLX5DR_DOMAIN_TYPE_FDB) { + if (last_matcher) + last_htbl = last_matcher->tx.e_anchor; + else + last_htbl = tbl->tx.s_anchor; + + tbl->tx.default_icm_addr = action ? + action->dest_tbl.tbl->tx.s_anchor->chunk->icm_addr : + tbl->tx.nic_dmn->default_icm_addr; + + info.type = CONNECT_MISS; + info.miss_icm_addr = tbl->tx.default_icm_addr; + + ret = mlx5dr_ste_htbl_init_and_postsend(tbl->dmn, + tbl->tx.nic_dmn, + last_htbl, &info, true); + if (ret) { + mlx5dr_dbg(tbl->dmn, "Failed to set TX miss action, ret %d\n", ret); + goto out; + } + } + + /* Release old action */ + if (tbl->miss_action) + refcount_dec(&tbl->miss_action->refcount); + + /* Set new miss action */ + tbl->miss_action = action; + if (tbl->miss_action) + refcount_inc(&action->refcount); + +out: + mutex_unlock(&tbl->dmn->mutex); + return ret; +} + +static void dr_table_uninit_nic(struct mlx5dr_table_rx_tx *nic_tbl) +{ + mlx5dr_htbl_put(nic_tbl->s_anchor); +} + +static void dr_table_uninit_fdb(struct mlx5dr_table *tbl) +{ + dr_table_uninit_nic(&tbl->rx); + dr_table_uninit_nic(&tbl->tx); +} + +static void dr_table_uninit(struct mlx5dr_table *tbl) +{ + mutex_lock(&tbl->dmn->mutex); + + switch (tbl->dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + dr_table_uninit_nic(&tbl->rx); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + dr_table_uninit_nic(&tbl->tx); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + dr_table_uninit_fdb(tbl); + break; + default: + WARN_ON(true); + break; + } + + mutex_unlock(&tbl->dmn->mutex); +} + +static int dr_table_init_nic(struct mlx5dr_domain *dmn, + struct mlx5dr_table_rx_tx *nic_tbl) +{ + struct mlx5dr_domain_rx_tx *nic_dmn = nic_tbl->nic_dmn; + struct mlx5dr_htbl_connect_info info; + int ret; + + nic_tbl->default_icm_addr = nic_dmn->default_icm_addr; + + nic_tbl->s_anchor = mlx5dr_ste_htbl_alloc(dmn->ste_icm_pool, + DR_CHUNK_SIZE_1, + MLX5DR_STE_LU_TYPE_DONT_CARE, + 0); + if (!nic_tbl->s_anchor) + return -ENOMEM; + + info.type = CONNECT_MISS; + info.miss_icm_addr = nic_dmn->default_icm_addr; + ret = mlx5dr_ste_htbl_init_and_postsend(dmn, nic_dmn, + nic_tbl->s_anchor, + &info, true); + if (ret) + goto free_s_anchor; + + mlx5dr_htbl_get(nic_tbl->s_anchor); + + return 0; + +free_s_anchor: + mlx5dr_ste_htbl_free(nic_tbl->s_anchor); + return ret; +} + +static int dr_table_init_fdb(struct mlx5dr_table *tbl) +{ + int ret; + + ret = dr_table_init_nic(tbl->dmn, &tbl->rx); + if (ret) + return ret; + + ret = dr_table_init_nic(tbl->dmn, &tbl->tx); + if (ret) + goto destroy_rx; + + return 0; + +destroy_rx: + dr_table_uninit_nic(&tbl->rx); + return ret; +} + +static int dr_table_init(struct mlx5dr_table *tbl) +{ + int ret = 0; + + INIT_LIST_HEAD(&tbl->matcher_list); + + mutex_lock(&tbl->dmn->mutex); + + switch (tbl->dmn->type) { + case MLX5DR_DOMAIN_TYPE_NIC_RX: + tbl->table_type = MLX5_FLOW_TABLE_TYPE_NIC_RX; + tbl->rx.nic_dmn = &tbl->dmn->info.rx; + ret = dr_table_init_nic(tbl->dmn, &tbl->rx); + break; + case MLX5DR_DOMAIN_TYPE_NIC_TX: + tbl->table_type = MLX5_FLOW_TABLE_TYPE_NIC_TX; + tbl->tx.nic_dmn = &tbl->dmn->info.tx; + ret = dr_table_init_nic(tbl->dmn, &tbl->tx); + break; + case MLX5DR_DOMAIN_TYPE_FDB: + tbl->table_type = MLX5_FLOW_TABLE_TYPE_FDB; + tbl->rx.nic_dmn = &tbl->dmn->info.rx; + tbl->tx.nic_dmn = &tbl->dmn->info.tx; + ret = dr_table_init_fdb(tbl); + break; + default: + WARN_ON(true); + break; + } + + mutex_unlock(&tbl->dmn->mutex); + + return ret; +} + +static int dr_table_destroy_sw_owned_tbl(struct mlx5dr_table *tbl) +{ + return mlx5dr_cmd_destroy_flow_table(tbl->dmn->mdev, + tbl->table_id, + tbl->table_type); +} + +static int dr_table_create_sw_owned_tbl(struct mlx5dr_table *tbl) +{ + u64 icm_addr_rx = 0; + u64 icm_addr_tx = 0; + int ret; + + if (tbl->rx.s_anchor) + icm_addr_rx = tbl->rx.s_anchor->chunk->icm_addr; + + if (tbl->tx.s_anchor) + icm_addr_tx = tbl->tx.s_anchor->chunk->icm_addr; + + ret = mlx5dr_cmd_create_flow_table(tbl->dmn->mdev, + tbl->table_type, + icm_addr_rx, + icm_addr_tx, + tbl->dmn->info.caps.max_ft_level - 1, + true, false, NULL, + &tbl->table_id); + + return ret; +} + +struct mlx5dr_table *mlx5dr_table_create(struct mlx5dr_domain *dmn, u32 level) +{ + struct mlx5dr_table *tbl; + int ret; + + refcount_inc(&dmn->refcount); + + tbl = kzalloc(sizeof(*tbl), GFP_KERNEL); + if (!tbl) + goto dec_ref; + + tbl->dmn = dmn; + tbl->level = level; + refcount_set(&tbl->refcount, 1); + + ret = dr_table_init(tbl); + if (ret) + goto free_tbl; + + ret = dr_table_create_sw_owned_tbl(tbl); + if (ret) + goto uninit_tbl; + + return tbl; + +uninit_tbl: + dr_table_uninit(tbl); +free_tbl: + kfree(tbl); +dec_ref: + refcount_dec(&dmn->refcount); + return NULL; +} + +int mlx5dr_table_destroy(struct mlx5dr_table *tbl) +{ + int ret; + + if (refcount_read(&tbl->refcount) > 1) + return -EBUSY; + + ret = dr_table_destroy_sw_owned_tbl(tbl); + if (ret) + return ret; + + dr_table_uninit(tbl); + + if (tbl->miss_action) + refcount_dec(&tbl->miss_action->refcount); + + refcount_dec(&tbl->dmn->refcount); + kfree(tbl); + + return ret; +} + +u32 mlx5dr_table_get_id(struct mlx5dr_table *tbl) +{ + return tbl->table_id; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h new file mode 100644 index 000000000000..a37ee6359be2 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_types.h @@ -0,0 +1,1060 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019, Mellanox Technologies */ + +#ifndef _DR_TYPES_ +#define _DR_TYPES_ + +#include <linux/mlx5/driver.h> +#include <linux/refcount.h> +#include "fs_core.h" +#include "wq.h" +#include "lib/mlx5.h" +#include "mlx5_ifc_dr.h" +#include "mlx5dr.h" + +#define DR_RULE_MAX_STES 17 +#define DR_ACTION_MAX_STES 5 +#define WIRE_PORT 0xFFFF +#define DR_STE_SVLAN 0x1 +#define DR_STE_CVLAN 0x2 + +#define mlx5dr_err(dmn, arg...) mlx5_core_err((dmn)->mdev, ##arg) +#define mlx5dr_info(dmn, arg...) mlx5_core_info((dmn)->mdev, ##arg) +#define mlx5dr_dbg(dmn, arg...) mlx5_core_dbg((dmn)->mdev, ##arg) + +enum mlx5dr_icm_chunk_size { + DR_CHUNK_SIZE_1, + DR_CHUNK_SIZE_MIN = DR_CHUNK_SIZE_1, /* keep updated when changing */ + DR_CHUNK_SIZE_2, + DR_CHUNK_SIZE_4, + DR_CHUNK_SIZE_8, + DR_CHUNK_SIZE_16, + DR_CHUNK_SIZE_32, + DR_CHUNK_SIZE_64, + DR_CHUNK_SIZE_128, + DR_CHUNK_SIZE_256, + DR_CHUNK_SIZE_512, + DR_CHUNK_SIZE_1K, + DR_CHUNK_SIZE_2K, + DR_CHUNK_SIZE_4K, + DR_CHUNK_SIZE_8K, + DR_CHUNK_SIZE_16K, + DR_CHUNK_SIZE_32K, + DR_CHUNK_SIZE_64K, + DR_CHUNK_SIZE_128K, + DR_CHUNK_SIZE_256K, + DR_CHUNK_SIZE_512K, + DR_CHUNK_SIZE_1024K, + DR_CHUNK_SIZE_2048K, + DR_CHUNK_SIZE_MAX, +}; + +enum mlx5dr_icm_type { + DR_ICM_TYPE_STE, + DR_ICM_TYPE_MODIFY_ACTION, +}; + +static inline enum mlx5dr_icm_chunk_size +mlx5dr_icm_next_higher_chunk(enum mlx5dr_icm_chunk_size chunk) +{ + chunk += 2; + if (chunk < DR_CHUNK_SIZE_MAX) + return chunk; + + return DR_CHUNK_SIZE_MAX; +} + +enum { + DR_STE_SIZE = 64, + DR_STE_SIZE_CTRL = 32, + DR_STE_SIZE_TAG = 16, + DR_STE_SIZE_MASK = 16, +}; + +enum { + DR_STE_SIZE_REDUCED = DR_STE_SIZE - DR_STE_SIZE_MASK, +}; + +enum { + DR_MODIFY_ACTION_SIZE = 8, +}; + +enum mlx5dr_matcher_criteria { + DR_MATCHER_CRITERIA_EMPTY = 0, + DR_MATCHER_CRITERIA_OUTER = 1 << 0, + DR_MATCHER_CRITERIA_MISC = 1 << 1, + DR_MATCHER_CRITERIA_INNER = 1 << 2, + DR_MATCHER_CRITERIA_MISC2 = 1 << 3, + DR_MATCHER_CRITERIA_MISC3 = 1 << 4, + DR_MATCHER_CRITERIA_MAX = 1 << 5, +}; + +enum mlx5dr_action_type { + DR_ACTION_TYP_TNL_L2_TO_L2, + DR_ACTION_TYP_L2_TO_TNL_L2, + DR_ACTION_TYP_TNL_L3_TO_L2, + DR_ACTION_TYP_L2_TO_TNL_L3, + DR_ACTION_TYP_DROP, + DR_ACTION_TYP_QP, + DR_ACTION_TYP_FT, + DR_ACTION_TYP_CTR, + DR_ACTION_TYP_TAG, + DR_ACTION_TYP_MODIFY_HDR, + DR_ACTION_TYP_VPORT, + DR_ACTION_TYP_POP_VLAN, + DR_ACTION_TYP_PUSH_VLAN, + DR_ACTION_TYP_MAX, +}; + +struct mlx5dr_icm_pool; +struct mlx5dr_icm_chunk; +struct mlx5dr_icm_bucket; +struct mlx5dr_ste_htbl; +struct mlx5dr_match_param; +struct mlx5dr_cmd_caps; +struct mlx5dr_matcher_rx_tx; + +struct mlx5dr_ste { + u8 *hw_ste; + /* refcount: indicates the num of rules that using this ste */ + refcount_t refcount; + + /* attached to the miss_list head at each htbl entry */ + struct list_head miss_list_node; + + /* each rule member that uses this ste attached here */ + struct list_head rule_list; + + /* this ste is member of htbl */ + struct mlx5dr_ste_htbl *htbl; + + struct mlx5dr_ste_htbl *next_htbl; + + /* this ste is part of a rule, located in ste's chain */ + u8 ste_chain_location; +}; + +struct mlx5dr_ste_htbl_ctrl { + /* total number of valid entries belonging to this hash table. This + * includes the non collision and collision entries + */ + unsigned int num_of_valid_entries; + + /* total number of collisions entries attached to this table */ + unsigned int num_of_collisions; + unsigned int increase_threshold; + u8 may_grow:1; +}; + +struct mlx5dr_ste_htbl { + u8 lu_type; + u16 byte_mask; + refcount_t refcount; + struct mlx5dr_icm_chunk *chunk; + struct mlx5dr_ste *ste_arr; + u8 *hw_ste_arr; + + struct list_head *miss_list; + + enum mlx5dr_icm_chunk_size chunk_size; + struct mlx5dr_ste *pointing_ste; + + struct mlx5dr_ste_htbl_ctrl ctrl; +}; + +struct mlx5dr_ste_send_info { + struct mlx5dr_ste *ste; + struct list_head send_list; + u16 size; + u16 offset; + u8 data_cont[DR_STE_SIZE]; + u8 *data; +}; + +void mlx5dr_send_fill_and_append_ste_send_info(struct mlx5dr_ste *ste, u16 size, + u16 offset, u8 *data, + struct mlx5dr_ste_send_info *ste_info, + struct list_head *send_list, + bool copy_data); + +struct mlx5dr_ste_build { + u8 inner:1; + u8 rx:1; + struct mlx5dr_cmd_caps *caps; + u8 lu_type; + u16 byte_mask; + u8 bit_mask[DR_STE_SIZE_MASK]; + int (*ste_build_tag_func)(struct mlx5dr_match_param *spec, + struct mlx5dr_ste_build *sb, + u8 *hw_ste_p); +}; + +struct mlx5dr_ste_htbl * +mlx5dr_ste_htbl_alloc(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size, + u8 lu_type, u16 byte_mask); + +int mlx5dr_ste_htbl_free(struct mlx5dr_ste_htbl *htbl); + +static inline void mlx5dr_htbl_put(struct mlx5dr_ste_htbl *htbl) +{ + if (refcount_dec_and_test(&htbl->refcount)) + mlx5dr_ste_htbl_free(htbl); +} + +static inline void mlx5dr_htbl_get(struct mlx5dr_ste_htbl *htbl) +{ + refcount_inc(&htbl->refcount); +} + +/* STE utils */ +u32 mlx5dr_ste_calc_hash_index(u8 *hw_ste_p, struct mlx5dr_ste_htbl *htbl); +void mlx5dr_ste_init(u8 *hw_ste_p, u8 lu_type, u8 entry_type, u16 gvmi); +void mlx5dr_ste_always_hit_htbl(struct mlx5dr_ste *ste, + struct mlx5dr_ste_htbl *next_htbl); +void mlx5dr_ste_set_miss_addr(u8 *hw_ste, u64 miss_addr); +u64 mlx5dr_ste_get_miss_addr(u8 *hw_ste); +void mlx5dr_ste_set_hit_gvmi(u8 *hw_ste_p, u16 gvmi); +void mlx5dr_ste_set_hit_addr(u8 *hw_ste, u64 icm_addr, u32 ht_size); +void mlx5dr_ste_always_miss_addr(struct mlx5dr_ste *ste, u64 miss_addr); +void mlx5dr_ste_set_bit_mask(u8 *hw_ste_p, u8 *bit_mask); +bool mlx5dr_ste_not_used_ste(struct mlx5dr_ste *ste); +bool mlx5dr_ste_is_last_in_rule(struct mlx5dr_matcher_rx_tx *nic_matcher, + u8 ste_location); +void mlx5dr_ste_rx_set_flow_tag(u8 *hw_ste_p, u32 flow_tag); +void mlx5dr_ste_set_counter_id(u8 *hw_ste_p, u32 ctr_id); +void mlx5dr_ste_set_tx_encap(void *hw_ste_p, u32 reformat_id, + int size, bool encap_l3); +void mlx5dr_ste_set_rx_decap(u8 *hw_ste_p); +void mlx5dr_ste_set_rx_decap_l3(u8 *hw_ste_p, bool vlan); +void mlx5dr_ste_set_rx_pop_vlan(u8 *hw_ste_p); +void mlx5dr_ste_set_tx_push_vlan(u8 *hw_ste_p, u32 vlan_tpid_pcp_dei_vid, + bool go_back); +void mlx5dr_ste_set_entry_type(u8 *hw_ste_p, u8 entry_type); +u8 mlx5dr_ste_get_entry_type(u8 *hw_ste_p); +void mlx5dr_ste_set_rewrite_actions(u8 *hw_ste_p, u16 num_of_actions, + u32 re_write_index); +void mlx5dr_ste_set_go_back_bit(u8 *hw_ste_p); +u64 mlx5dr_ste_get_icm_addr(struct mlx5dr_ste *ste); +u64 mlx5dr_ste_get_mr_addr(struct mlx5dr_ste *ste); +struct list_head *mlx5dr_ste_get_miss_list(struct mlx5dr_ste *ste); + +void mlx5dr_ste_free(struct mlx5dr_ste *ste, + struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher); +static inline void mlx5dr_ste_put(struct mlx5dr_ste *ste, + struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher) +{ + if (refcount_dec_and_test(&ste->refcount)) + mlx5dr_ste_free(ste, matcher, nic_matcher); +} + +/* initial as 0, increased only when ste appears in a new rule */ +static inline void mlx5dr_ste_get(struct mlx5dr_ste *ste) +{ + refcount_inc(&ste->refcount); +} + +void mlx5dr_ste_set_hit_addr_by_next_htbl(u8 *hw_ste, + struct mlx5dr_ste_htbl *next_htbl); +bool mlx5dr_ste_equal_tag(void *src, void *dst); +int mlx5dr_ste_create_next_htbl(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_ste *ste, + u8 *cur_hw_ste, + enum mlx5dr_icm_chunk_size log_table_size); + +/* STE build functions */ +int mlx5dr_ste_build_pre_check(struct mlx5dr_domain *dmn, + u8 match_criteria, + struct mlx5dr_match_param *mask, + struct mlx5dr_match_param *value); +int mlx5dr_ste_build_ste_arr(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_match_param *value, + u8 *ste_arr); +int mlx5dr_ste_build_eth_l2_src_des(struct mlx5dr_ste_build *builder, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l3_ipv4_5_tuple(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l3_ipv4_misc(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l3_ipv6_dst(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l3_ipv6_src(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l2_src(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l2_dst(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l2_tnl(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_ipv6_l3_l4(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_eth_l4_misc(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_gre(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_mpls(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_flex_parser_0(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +int mlx5dr_ste_build_flex_parser_1(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx); +void mlx5dr_ste_build_flex_parser_tnl(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_general_purpose(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_register_0(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +void mlx5dr_ste_build_register_1(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + bool inner, bool rx); +int mlx5dr_ste_build_src_gvmi_qpn(struct mlx5dr_ste_build *sb, + struct mlx5dr_match_param *mask, + struct mlx5dr_cmd_caps *caps, + bool inner, bool rx); +void mlx5dr_ste_build_empty_always_hit(struct mlx5dr_ste_build *sb, bool rx); + +/* Actions utils */ +int mlx5dr_actions_build_ste_arr(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + struct mlx5dr_action *actions[], + u32 num_actions, + u8 *ste_arr, + u32 *new_hw_ste_arr_sz); + +struct mlx5dr_match_spec { + u32 smac_47_16; /* Source MAC address of incoming packet */ + /* Incoming packet Ethertype - this is the Ethertype + * following the last VLAN tag of the packet + */ + u32 ethertype:16; + u32 smac_15_0:16; /* Source MAC address of incoming packet */ + u32 dmac_47_16; /* Destination MAC address of incoming packet */ + /* VLAN ID of first VLAN tag in the incoming packet. + * Valid only when cvlan_tag==1 or svlan_tag==1 + */ + u32 first_vid:12; + /* CFI bit of first VLAN tag in the incoming packet. + * Valid only when cvlan_tag==1 or svlan_tag==1 + */ + u32 first_cfi:1; + /* Priority of first VLAN tag in the incoming packet. + * Valid only when cvlan_tag==1 or svlan_tag==1 + */ + u32 first_prio:3; + u32 dmac_15_0:16; /* Destination MAC address of incoming packet */ + /* TCP flags. ;Bit 0: FIN;Bit 1: SYN;Bit 2: RST;Bit 3: PSH;Bit 4: ACK; + * Bit 5: URG;Bit 6: ECE;Bit 7: CWR;Bit 8: NS + */ + u32 tcp_flags:9; + u32 ip_version:4; /* IP version */ + u32 frag:1; /* Packet is an IP fragment */ + /* The first vlan in the packet is s-vlan (0x8a88). + * cvlan_tag and svlan_tag cannot be set together + */ + u32 svlan_tag:1; + /* The first vlan in the packet is c-vlan (0x8100). + * cvlan_tag and svlan_tag cannot be set together + */ + u32 cvlan_tag:1; + /* Explicit Congestion Notification derived from + * Traffic Class/TOS field of IPv6/v4 + */ + u32 ip_ecn:2; + /* Differentiated Services Code Point derived from + * Traffic Class/TOS field of IPv6/v4 + */ + u32 ip_dscp:6; + u32 ip_protocol:8; /* IP protocol */ + /* TCP destination port. + * tcp and udp sport/dport are mutually exclusive + */ + u32 tcp_dport:16; + /* TCP source port.;tcp and udp sport/dport are mutually exclusive */ + u32 tcp_sport:16; + u32 ttl_hoplimit:8; + u32 reserved:24; + /* UDP destination port.;tcp and udp sport/dport are mutually exclusive */ + u32 udp_dport:16; + /* UDP source port.;tcp and udp sport/dport are mutually exclusive */ + u32 udp_sport:16; + /* IPv6 source address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 src_ip_127_96; + /* IPv6 source address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 src_ip_95_64; + /* IPv6 source address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 src_ip_63_32; + /* IPv6 source address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 src_ip_31_0; + /* IPv6 destination address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 dst_ip_127_96; + /* IPv6 destination address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 dst_ip_95_64; + /* IPv6 destination address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 dst_ip_63_32; + /* IPv6 destination address of incoming packets + * For IPv4 address use bits 31:0 (rest of the bits are reserved) + * This field should be qualified by an appropriate ethertype + */ + u32 dst_ip_31_0; +}; + +struct mlx5dr_match_misc { + u32 source_sqn:24; /* Source SQN */ + u32 source_vhca_port:4; + /* used with GRE, sequence number exist when gre_s_present == 1 */ + u32 gre_s_present:1; + /* used with GRE, key exist when gre_k_present == 1 */ + u32 gre_k_present:1; + u32 reserved_auto1:1; + /* used with GRE, checksum exist when gre_c_present == 1 */ + u32 gre_c_present:1; + /* Source port.;0xffff determines wire port */ + u32 source_port:16; + u32 reserved_auto2:16; + /* VLAN ID of first VLAN tag the inner header of the incoming packet. + * Valid only when inner_second_cvlan_tag ==1 or inner_second_svlan_tag ==1 + */ + u32 inner_second_vid:12; + /* CFI bit of first VLAN tag in the inner header of the incoming packet. + * Valid only when inner_second_cvlan_tag ==1 or inner_second_svlan_tag ==1 + */ + u32 inner_second_cfi:1; + /* Priority of second VLAN tag in the inner header of the incoming packet. + * Valid only when inner_second_cvlan_tag ==1 or inner_second_svlan_tag ==1 + */ + u32 inner_second_prio:3; + /* VLAN ID of first VLAN tag the outer header of the incoming packet. + * Valid only when outer_second_cvlan_tag ==1 or outer_second_svlan_tag ==1 + */ + u32 outer_second_vid:12; + /* CFI bit of first VLAN tag in the outer header of the incoming packet. + * Valid only when outer_second_cvlan_tag ==1 or outer_second_svlan_tag ==1 + */ + u32 outer_second_cfi:1; + /* Priority of second VLAN tag in the outer header of the incoming packet. + * Valid only when outer_second_cvlan_tag ==1 or outer_second_svlan_tag ==1 + */ + u32 outer_second_prio:3; + u32 gre_protocol:16; /* GRE Protocol (outer) */ + u32 reserved_auto3:12; + /* The second vlan in the inner header of the packet is s-vlan (0x8a88). + * inner_second_cvlan_tag and inner_second_svlan_tag cannot be set together + */ + u32 inner_second_svlan_tag:1; + /* The second vlan in the outer header of the packet is s-vlan (0x8a88). + * outer_second_cvlan_tag and outer_second_svlan_tag cannot be set together + */ + u32 outer_second_svlan_tag:1; + /* The second vlan in the inner header of the packet is c-vlan (0x8100). + * inner_second_cvlan_tag and inner_second_svlan_tag cannot be set together + */ + u32 inner_second_cvlan_tag:1; + /* The second vlan in the outer header of the packet is c-vlan (0x8100). + * outer_second_cvlan_tag and outer_second_svlan_tag cannot be set together + */ + u32 outer_second_cvlan_tag:1; + u32 gre_key_l:8; /* GRE Key [7:0] (outer) */ + u32 gre_key_h:24; /* GRE Key[31:8] (outer) */ + u32 reserved_auto4:8; + u32 vxlan_vni:24; /* VXLAN VNI (outer) */ + u32 geneve_oam:1; /* GENEVE OAM field (outer) */ + u32 reserved_auto5:7; + u32 geneve_vni:24; /* GENEVE VNI field (outer) */ + u32 outer_ipv6_flow_label:20; /* Flow label of incoming IPv6 packet (outer) */ + u32 reserved_auto6:12; + u32 inner_ipv6_flow_label:20; /* Flow label of incoming IPv6 packet (inner) */ + u32 reserved_auto7:12; + u32 geneve_protocol_type:16; /* GENEVE protocol type (outer) */ + u32 geneve_opt_len:6; /* GENEVE OptLen (outer) */ + u32 reserved_auto8:10; + u32 bth_dst_qp:24; /* Destination QP in BTH header */ + u32 reserved_auto9:8; + u8 reserved_auto10[20]; +}; + +struct mlx5dr_match_misc2 { + u32 outer_first_mpls_ttl:8; /* First MPLS TTL (outer) */ + u32 outer_first_mpls_s_bos:1; /* First MPLS S_BOS (outer) */ + u32 outer_first_mpls_exp:3; /* First MPLS EXP (outer) */ + u32 outer_first_mpls_label:20; /* First MPLS LABEL (outer) */ + u32 inner_first_mpls_ttl:8; /* First MPLS TTL (inner) */ + u32 inner_first_mpls_s_bos:1; /* First MPLS S_BOS (inner) */ + u32 inner_first_mpls_exp:3; /* First MPLS EXP (inner) */ + u32 inner_first_mpls_label:20; /* First MPLS LABEL (inner) */ + u32 outer_first_mpls_over_gre_ttl:8; /* last MPLS TTL (outer) */ + u32 outer_first_mpls_over_gre_s_bos:1; /* last MPLS S_BOS (outer) */ + u32 outer_first_mpls_over_gre_exp:3; /* last MPLS EXP (outer) */ + u32 outer_first_mpls_over_gre_label:20; /* last MPLS LABEL (outer) */ + u32 outer_first_mpls_over_udp_ttl:8; /* last MPLS TTL (outer) */ + u32 outer_first_mpls_over_udp_s_bos:1; /* last MPLS S_BOS (outer) */ + u32 outer_first_mpls_over_udp_exp:3; /* last MPLS EXP (outer) */ + u32 outer_first_mpls_over_udp_label:20; /* last MPLS LABEL (outer) */ + u32 metadata_reg_c_7; /* metadata_reg_c_7 */ + u32 metadata_reg_c_6; /* metadata_reg_c_6 */ + u32 metadata_reg_c_5; /* metadata_reg_c_5 */ + u32 metadata_reg_c_4; /* metadata_reg_c_4 */ + u32 metadata_reg_c_3; /* metadata_reg_c_3 */ + u32 metadata_reg_c_2; /* metadata_reg_c_2 */ + u32 metadata_reg_c_1; /* metadata_reg_c_1 */ + u32 metadata_reg_c_0; /* metadata_reg_c_0 */ + u32 metadata_reg_a; /* metadata_reg_a */ + u32 metadata_reg_b; /* metadata_reg_b */ + u8 reserved_auto2[8]; +}; + +struct mlx5dr_match_misc3 { + u32 inner_tcp_seq_num; + u32 outer_tcp_seq_num; + u32 inner_tcp_ack_num; + u32 outer_tcp_ack_num; + u32 outer_vxlan_gpe_vni:24; + u32 reserved_auto1:8; + u32 reserved_auto2:16; + u32 outer_vxlan_gpe_flags:8; + u32 outer_vxlan_gpe_next_protocol:8; + u32 icmpv4_header_data; + u32 icmpv6_header_data; + u32 icmpv6_code:8; + u32 icmpv6_type:8; + u32 icmpv4_code:8; + u32 icmpv4_type:8; + u8 reserved_auto3[0x1c]; +}; + +struct mlx5dr_match_param { + struct mlx5dr_match_spec outer; + struct mlx5dr_match_misc misc; + struct mlx5dr_match_spec inner; + struct mlx5dr_match_misc2 misc2; + struct mlx5dr_match_misc3 misc3; +}; + +#define DR_MASK_IS_FLEX_PARSER_ICMPV4_SET(_misc3) ((_misc3)->icmpv4_type || \ + (_misc3)->icmpv4_code || \ + (_misc3)->icmpv4_header_data) + +struct mlx5dr_esw_caps { + u64 drop_icm_address_rx; + u64 drop_icm_address_tx; + u64 uplink_icm_address_rx; + u64 uplink_icm_address_tx; + bool sw_owner; +}; + +struct mlx5dr_cmd_vport_cap { + u16 vport_gvmi; + u16 vhca_gvmi; + u64 icm_address_rx; + u64 icm_address_tx; + u32 num; +}; + +struct mlx5dr_cmd_caps { + u16 gvmi; + u64 nic_rx_drop_address; + u64 nic_tx_drop_address; + u64 nic_tx_allow_address; + u64 esw_rx_drop_address; + u64 esw_tx_drop_address; + u32 log_icm_size; + u64 hdr_modify_icm_addr; + u32 flex_protocols; + u8 flex_parser_id_icmp_dw0; + u8 flex_parser_id_icmp_dw1; + u8 flex_parser_id_icmpv6_dw0; + u8 flex_parser_id_icmpv6_dw1; + u8 max_ft_level; + u16 roce_min_src_udp; + u8 num_esw_ports; + bool eswitch_manager; + bool rx_sw_owner; + bool tx_sw_owner; + bool fdb_sw_owner; + u32 num_vports; + struct mlx5dr_esw_caps esw_caps; + struct mlx5dr_cmd_vport_cap *vports_caps; + bool prio_tag_required; +}; + +struct mlx5dr_domain_rx_tx { + u64 drop_icm_addr; + u64 default_icm_addr; + enum mlx5dr_ste_entry_type ste_type; +}; + +struct mlx5dr_domain_info { + bool supp_sw_steering; + u32 max_inline_size; + u32 max_send_wr; + u32 max_log_sw_icm_sz; + u32 max_log_action_icm_sz; + struct mlx5dr_domain_rx_tx rx; + struct mlx5dr_domain_rx_tx tx; + struct mlx5dr_cmd_caps caps; +}; + +struct mlx5dr_domain_cache { + struct mlx5dr_fw_recalc_cs_ft **recalc_cs_ft; +}; + +struct mlx5dr_domain { + struct mlx5dr_domain *peer_dmn; + struct mlx5_core_dev *mdev; + u32 pdn; + struct mlx5_uars_page *uar; + enum mlx5dr_domain_type type; + refcount_t refcount; + struct mutex mutex; /* protect domain */ + struct mlx5dr_icm_pool *ste_icm_pool; + struct mlx5dr_icm_pool *action_icm_pool; + struct mlx5dr_send_ring *send_ring; + struct mlx5dr_domain_info info; + struct mlx5dr_domain_cache cache; +}; + +struct mlx5dr_table_rx_tx { + struct mlx5dr_ste_htbl *s_anchor; + struct mlx5dr_domain_rx_tx *nic_dmn; + u64 default_icm_addr; +}; + +struct mlx5dr_table { + struct mlx5dr_domain *dmn; + struct mlx5dr_table_rx_tx rx; + struct mlx5dr_table_rx_tx tx; + u32 level; + u32 table_type; + u32 table_id; + struct list_head matcher_list; + struct mlx5dr_action *miss_action; + refcount_t refcount; +}; + +struct mlx5dr_matcher_rx_tx { + struct mlx5dr_ste_htbl *s_htbl; + struct mlx5dr_ste_htbl *e_anchor; + struct mlx5dr_ste_build *ste_builder; + struct mlx5dr_ste_build ste_builder4[DR_RULE_MAX_STES]; + struct mlx5dr_ste_build ste_builder6[DR_RULE_MAX_STES]; + u8 num_of_builders; + u8 num_of_builders4; + u8 num_of_builders6; + u64 default_icm_addr; + struct mlx5dr_table_rx_tx *nic_tbl; +}; + +struct mlx5dr_matcher { + struct mlx5dr_table *tbl; + struct mlx5dr_matcher_rx_tx rx; + struct mlx5dr_matcher_rx_tx tx; + struct list_head matcher_list; + u16 prio; + struct mlx5dr_match_param mask; + u8 match_criteria; + refcount_t refcount; + struct mlx5dv_flow_matcher *dv_matcher; +}; + +struct mlx5dr_rule_member { + struct mlx5dr_ste *ste; + /* attached to mlx5dr_rule via this */ + struct list_head list; + /* attached to mlx5dr_ste via this */ + struct list_head use_ste_list; +}; + +struct mlx5dr_action { + enum mlx5dr_action_type action_type; + refcount_t refcount; + union { + struct { + struct mlx5dr_domain *dmn; + struct mlx5dr_icm_chunk *chunk; + u8 *data; + u32 data_size; + u16 num_of_actions; + u32 index; + u8 allow_rx:1; + u8 allow_tx:1; + u8 modify_ttl:1; + } rewrite; + struct { + struct mlx5dr_domain *dmn; + u32 reformat_id; + u32 reformat_size; + } reformat; + struct { + u8 is_fw_tbl:1; + union { + struct mlx5dr_table *tbl; + struct { + struct mlx5_flow_table *ft; + u64 rx_icm_addr; + u64 tx_icm_addr; + struct mlx5_core_dev *mdev; + } fw_tbl; + }; + } dest_tbl; + struct { + u32 ctr_id; + u32 offeset; + } ctr; + struct { + struct mlx5dr_domain *dmn; + struct mlx5dr_cmd_vport_cap *caps; + u32 num; + } vport; + struct { + u32 vlan_hdr; /* tpid_pcp_dei_vid */ + } push_vlan; + u32 flow_tag; + }; +}; + +enum mlx5dr_connect_type { + CONNECT_HIT = 1, + CONNECT_MISS = 2, +}; + +struct mlx5dr_htbl_connect_info { + enum mlx5dr_connect_type type; + union { + struct mlx5dr_ste_htbl *hit_next_htbl; + u64 miss_icm_addr; + }; +}; + +struct mlx5dr_rule_rx_tx { + struct list_head rule_members_list; + struct mlx5dr_matcher_rx_tx *nic_matcher; +}; + +struct mlx5dr_rule { + struct mlx5dr_matcher *matcher; + struct mlx5dr_rule_rx_tx rx; + struct mlx5dr_rule_rx_tx tx; + struct list_head rule_actions_list; +}; + +void mlx5dr_rule_update_rule_member(struct mlx5dr_ste *new_ste, + struct mlx5dr_ste *ste); + +struct mlx5dr_icm_chunk { + struct mlx5dr_icm_bucket *bucket; + struct list_head chunk_list; + u32 rkey; + u32 num_of_entries; + u32 byte_size; + u64 icm_addr; + u64 mr_addr; + + /* Memory optimisation */ + struct mlx5dr_ste *ste_arr; + u8 *hw_ste_arr; + struct list_head *miss_list; +}; + +static inline int +mlx5dr_matcher_supp_flex_parser_icmp_v4(struct mlx5dr_cmd_caps *caps) +{ + return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V4_ENABLED; +} + +static inline int +mlx5dr_matcher_supp_flex_parser_icmp_v6(struct mlx5dr_cmd_caps *caps) +{ + return caps->flex_protocols & MLX5_FLEX_PARSER_ICMP_V6_ENABLED; +} + +int mlx5dr_matcher_select_builders(struct mlx5dr_matcher *matcher, + struct mlx5dr_matcher_rx_tx *nic_matcher, + bool ipv6); + +static inline u32 +mlx5dr_icm_pool_chunk_size_to_entries(enum mlx5dr_icm_chunk_size chunk_size) +{ + return 1 << chunk_size; +} + +static inline int +mlx5dr_icm_pool_chunk_size_to_byte(enum mlx5dr_icm_chunk_size chunk_size, + enum mlx5dr_icm_type icm_type) +{ + int num_of_entries; + int entry_size; + + if (icm_type == DR_ICM_TYPE_STE) + entry_size = DR_STE_SIZE; + else + entry_size = DR_MODIFY_ACTION_SIZE; + + num_of_entries = mlx5dr_icm_pool_chunk_size_to_entries(chunk_size); + + return entry_size * num_of_entries; +} + +static inline struct mlx5dr_cmd_vport_cap * +mlx5dr_get_vport_cap(struct mlx5dr_cmd_caps *caps, u32 vport) +{ + if (!caps->vports_caps || + (vport >= caps->num_vports && vport != WIRE_PORT)) + return NULL; + + if (vport == WIRE_PORT) + vport = caps->num_vports; + + return &caps->vports_caps[vport]; +} + +struct mlx5dr_cmd_query_flow_table_details { + u8 status; + u8 level; + u64 sw_owner_icm_root_1; + u64 sw_owner_icm_root_0; +}; + +/* internal API functions */ +int mlx5dr_cmd_query_device(struct mlx5_core_dev *mdev, + struct mlx5dr_cmd_caps *caps); +int mlx5dr_cmd_query_esw_vport_context(struct mlx5_core_dev *mdev, + bool other_vport, u16 vport_number, + u64 *icm_address_rx, + u64 *icm_address_tx); +int mlx5dr_cmd_query_gvmi(struct mlx5_core_dev *mdev, + bool other_vport, u16 vport_number, u16 *gvmi); +int mlx5dr_cmd_query_esw_caps(struct mlx5_core_dev *mdev, + struct mlx5dr_esw_caps *caps); +int mlx5dr_cmd_sync_steering(struct mlx5_core_dev *mdev); +int mlx5dr_cmd_set_fte_modify_and_vport(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 group_id, + u32 modify_header_id, + u32 vport_id); +int mlx5dr_cmd_del_flow_table_entry(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id); +int mlx5dr_cmd_alloc_modify_header(struct mlx5_core_dev *mdev, + u32 table_type, + u8 num_of_actions, + u64 *actions, + u32 *modify_header_id); +int mlx5dr_cmd_dealloc_modify_header(struct mlx5_core_dev *mdev, + u32 modify_header_id); +int mlx5dr_cmd_create_empty_flow_group(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 *group_id); +int mlx5dr_cmd_destroy_flow_group(struct mlx5_core_dev *mdev, + u32 table_type, + u32 table_id, + u32 group_id); +int mlx5dr_cmd_create_flow_table(struct mlx5_core_dev *mdev, + u32 table_type, + u64 icm_addr_rx, + u64 icm_addr_tx, + u8 level, + bool sw_owner, + bool term_tbl, + u64 *fdb_rx_icm_addr, + u32 *table_id); +int mlx5dr_cmd_destroy_flow_table(struct mlx5_core_dev *mdev, + u32 table_id, + u32 table_type); +int mlx5dr_cmd_query_flow_table(struct mlx5_core_dev *dev, + enum fs_flow_table_type type, + u32 table_id, + struct mlx5dr_cmd_query_flow_table_details *output); +int mlx5dr_cmd_create_reformat_ctx(struct mlx5_core_dev *mdev, + enum mlx5_reformat_ctx_type rt, + size_t reformat_size, + void *reformat_data, + u32 *reformat_id); +void mlx5dr_cmd_destroy_reformat_ctx(struct mlx5_core_dev *mdev, + u32 reformat_id); + +struct mlx5dr_cmd_gid_attr { + u8 gid[16]; + u8 mac[6]; + u32 roce_ver; +}; + +struct mlx5dr_cmd_qp_create_attr { + u32 page_id; + u32 pdn; + u32 cqn; + u32 pm_state; + u32 service_type; + u32 buff_umem_id; + u32 db_umem_id; + u32 sq_wqe_cnt; + u32 rq_wqe_cnt; + u32 rq_wqe_shift; +}; + +int mlx5dr_cmd_query_gid(struct mlx5_core_dev *mdev, u8 vhca_port_num, + u16 index, struct mlx5dr_cmd_gid_attr *attr); + +struct mlx5dr_icm_pool *mlx5dr_icm_pool_create(struct mlx5dr_domain *dmn, + enum mlx5dr_icm_type icm_type); +void mlx5dr_icm_pool_destroy(struct mlx5dr_icm_pool *pool); + +struct mlx5dr_icm_chunk * +mlx5dr_icm_alloc_chunk(struct mlx5dr_icm_pool *pool, + enum mlx5dr_icm_chunk_size chunk_size); +void mlx5dr_icm_free_chunk(struct mlx5dr_icm_chunk *chunk); +bool mlx5dr_ste_is_not_valid_entry(u8 *p_hw_ste); +int mlx5dr_ste_htbl_init_and_postsend(struct mlx5dr_domain *dmn, + struct mlx5dr_domain_rx_tx *nic_dmn, + struct mlx5dr_ste_htbl *htbl, + struct mlx5dr_htbl_connect_info *connect_info, + bool update_hw_ste); +void mlx5dr_ste_set_formatted_ste(u16 gvmi, + struct mlx5dr_domain_rx_tx *nic_dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *formatted_ste, + struct mlx5dr_htbl_connect_info *connect_info); +void mlx5dr_ste_copy_param(u8 match_criteria, + struct mlx5dr_match_param *set_param, + struct mlx5dr_match_parameters *mask); + +void mlx5dr_crc32_init_table(void); +u32 mlx5dr_crc32_slice8_calc(const void *input_data, size_t length); + +struct mlx5dr_qp { + struct mlx5_core_dev *mdev; + struct mlx5_wq_qp wq; + struct mlx5_uars_page *uar; + struct mlx5_wq_ctrl wq_ctrl; + struct mlx5_core_qp mqp; + struct { + unsigned int pc; + unsigned int cc; + unsigned int size; + unsigned int *wqe_head; + unsigned int wqe_cnt; + } sq; + struct { + unsigned int pc; + unsigned int cc; + unsigned int size; + unsigned int wqe_cnt; + } rq; + int max_inline_data; +}; + +struct mlx5dr_cq { + struct mlx5_core_dev *mdev; + struct mlx5_cqwq wq; + struct mlx5_wq_ctrl wq_ctrl; + struct mlx5_core_cq mcq; + struct mlx5dr_qp *qp; +}; + +struct mlx5dr_mr { + struct mlx5_core_dev *mdev; + struct mlx5_core_mkey mkey; + dma_addr_t dma_addr; + void *addr; + size_t size; +}; + +#define MAX_SEND_CQE 64 +#define MIN_READ_SYNC 64 + +struct mlx5dr_send_ring { + struct mlx5dr_cq *cq; + struct mlx5dr_qp *qp; + struct mlx5dr_mr *mr; + /* How much wqes are waiting for completion */ + u32 pending_wqe; + /* Signal request per this trash hold value */ + u16 signal_th; + /* Each post_send_size less than max_post_send_size */ + u32 max_post_send_size; + /* manage the send queue */ + u32 tx_head; + void *buf; + u32 buf_size; + struct ib_wc wc[MAX_SEND_CQE]; + u8 sync_buff[MIN_READ_SYNC]; + struct mlx5dr_mr *sync_mr; +}; + +int mlx5dr_send_ring_alloc(struct mlx5dr_domain *dmn); +void mlx5dr_send_ring_free(struct mlx5dr_domain *dmn, + struct mlx5dr_send_ring *send_ring); +int mlx5dr_send_ring_force_drain(struct mlx5dr_domain *dmn); +int mlx5dr_send_postsend_ste(struct mlx5dr_domain *dmn, + struct mlx5dr_ste *ste, + u8 *data, + u16 size, + u16 offset); +int mlx5dr_send_postsend_htbl(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *formatted_ste, u8 *mask); +int mlx5dr_send_postsend_formatted_htbl(struct mlx5dr_domain *dmn, + struct mlx5dr_ste_htbl *htbl, + u8 *ste_init_data, + bool update_hw_ste); +int mlx5dr_send_postsend_action(struct mlx5dr_domain *dmn, + struct mlx5dr_action *action); + +struct mlx5dr_fw_recalc_cs_ft { + u64 rx_icm_addr; + u32 table_id; + u32 group_id; + u32 modify_hdr_id; +}; + +struct mlx5dr_fw_recalc_cs_ft * +mlx5dr_fw_create_recalc_cs_ft(struct mlx5dr_domain *dmn, u32 vport_num); +void mlx5dr_fw_destroy_recalc_cs_ft(struct mlx5dr_domain *dmn, + struct mlx5dr_fw_recalc_cs_ft *recalc_cs_ft); +int mlx5dr_domain_cache_get_recalc_cs_ft_addr(struct mlx5dr_domain *dmn, + u32 vport_num, + u64 *rx_icm_addr); +#endif /* _DR_TYPES_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c new file mode 100644 index 000000000000..3d587d0bdbbe --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.c @@ -0,0 +1,600 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* Copyright (c) 2019 Mellanox Technologies */ + +#include "mlx5_core.h" +#include "fs_core.h" +#include "fs_cmd.h" +#include "mlx5dr.h" +#include "fs_dr.h" + +static bool mlx5_dr_is_fw_table(u32 flags) +{ + if (flags & MLX5_FLOW_TABLE_TERMINATION) + return true; + + return false; +} + +static int mlx5_cmd_dr_update_root_ft(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + u32 underlay_qpn, + bool disconnect) +{ + return mlx5_fs_cmd_get_fw_cmds()->update_root_ft(ns, ft, underlay_qpn, + disconnect); +} + +static int set_miss_action(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_table *next_ft) +{ + struct mlx5dr_action *old_miss_action; + struct mlx5dr_action *action = NULL; + struct mlx5dr_table *next_tbl; + int err; + + next_tbl = next_ft ? next_ft->fs_dr_table.dr_table : NULL; + if (next_tbl) { + action = mlx5dr_action_create_dest_table(next_tbl); + if (!action) + return -EINVAL; + } + old_miss_action = ft->fs_dr_table.miss_action; + err = mlx5dr_table_set_miss_action(ft->fs_dr_table.dr_table, action); + if (err && action) { + err = mlx5dr_action_destroy(action); + if (err) { + action = NULL; + mlx5_core_err(ns->dev, "Failed to destroy action (%d)\n", + err); + } + } + ft->fs_dr_table.miss_action = action; + if (old_miss_action) { + err = mlx5dr_action_destroy(old_miss_action); + if (err) + mlx5_core_err(ns->dev, "Failed to destroy action (%d)\n", + err); + } + + return err; +} + +static int mlx5_cmd_dr_create_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + unsigned int log_size, + struct mlx5_flow_table *next_ft) +{ + struct mlx5dr_table *tbl; + int err; + + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->create_flow_table(ns, ft, + log_size, + next_ft); + + tbl = mlx5dr_table_create(ns->fs_dr_domain.dr_domain, + ft->level); + if (!tbl) { + mlx5_core_err(ns->dev, "Failed creating dr flow_table\n"); + return -EINVAL; + } + + ft->fs_dr_table.dr_table = tbl; + ft->id = mlx5dr_table_get_id(tbl); + + if (next_ft) { + err = set_miss_action(ns, ft, next_ft); + if (err) { + mlx5dr_table_destroy(tbl); + ft->fs_dr_table.dr_table = NULL; + return err; + } + } + + return 0; +} + +static int mlx5_cmd_dr_destroy_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft) +{ + struct mlx5dr_action *action = ft->fs_dr_table.miss_action; + int err; + + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_table(ns, ft); + + err = mlx5dr_table_destroy(ft->fs_dr_table.dr_table); + if (err) { + mlx5_core_err(ns->dev, "Failed to destroy flow_table (%d)\n", + err); + return err; + } + if (action) { + err = mlx5dr_action_destroy(action); + if (err) { + mlx5_core_err(ns->dev, "Failed to destroy action(%d)\n", + err); + return err; + } + } + + return err; +} + +static int mlx5_cmd_dr_modify_flow_table(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_table *next_ft) +{ + return set_miss_action(ns, ft, next_ft); +} + +static int mlx5_cmd_dr_create_flow_group(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + u32 *in, + struct mlx5_flow_group *fg) +{ + struct mlx5dr_matcher *matcher; + u16 priority = MLX5_GET(create_flow_group_in, in, + start_flow_index); + u8 match_criteria_enable = MLX5_GET(create_flow_group_in, + in, + match_criteria_enable); + struct mlx5dr_match_parameters mask; + + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->create_flow_group(ns, ft, in, + fg); + + mask.match_buf = MLX5_ADDR_OF(create_flow_group_in, + in, match_criteria); + mask.match_sz = sizeof(fg->mask.match_criteria); + + matcher = mlx5dr_matcher_create(ft->fs_dr_table.dr_table, + priority, + match_criteria_enable, + &mask); + if (!matcher) { + mlx5_core_err(ns->dev, "Failed creating matcher\n"); + return -EINVAL; + } + + fg->fs_dr_matcher.dr_matcher = matcher; + return 0; +} + +static int mlx5_cmd_dr_destroy_flow_group(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *fg) +{ + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->destroy_flow_group(ns, ft, fg); + + return mlx5dr_matcher_destroy(fg->fs_dr_matcher.dr_matcher); +} + +static struct mlx5dr_action *create_vport_action(struct mlx5dr_domain *domain, + struct mlx5_flow_rule *dst) +{ + struct mlx5_flow_destination *dest_attr = &dst->dest_attr; + + return mlx5dr_action_create_dest_vport(domain, dest_attr->vport.num, + dest_attr->vport.flags & + MLX5_FLOW_DEST_VPORT_VHCA_ID, + dest_attr->vport.vhca_id); +} + +static struct mlx5dr_action *create_ft_action(struct mlx5_core_dev *dev, + struct mlx5_flow_rule *dst) +{ + struct mlx5_flow_table *dest_ft = dst->dest_attr.ft; + + if (mlx5_dr_is_fw_table(dest_ft->flags)) + return mlx5dr_create_action_dest_flow_fw_table(dest_ft, dev); + return mlx5dr_action_create_dest_table(dest_ft->fs_dr_table.dr_table); +} + +static struct mlx5dr_action *create_action_push_vlan(struct mlx5dr_domain *domain, + struct mlx5_fs_vlan *vlan) +{ + u16 n_ethtype = vlan->ethtype; + u8 prio = vlan->prio; + u16 vid = vlan->vid; + u32 vlan_hdr; + + vlan_hdr = (u32)n_ethtype << 16 | (u32)(prio) << 12 | (u32)vid; + return mlx5dr_action_create_push_vlan(domain, htonl(vlan_hdr)); +} + +#define MLX5_FLOW_CONTEXT_ACTION_MAX 20 +static int mlx5_cmd_dr_create_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *group, + struct fs_fte *fte) +{ + struct mlx5dr_domain *domain = ns->fs_dr_domain.dr_domain; + struct mlx5dr_action *term_action = NULL; + struct mlx5dr_match_parameters params; + struct mlx5_core_dev *dev = ns->dev; + struct mlx5dr_action **fs_dr_actions; + struct mlx5dr_action *tmp_action; + struct mlx5dr_action **actions; + bool delay_encap_set = false; + struct mlx5dr_rule *rule; + struct mlx5_flow_rule *dst; + int fs_dr_num_actions = 0; + int num_actions = 0; + size_t match_sz; + int err = 0; + int i; + + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->create_fte(ns, ft, group, fte); + + actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, sizeof(*actions), + GFP_KERNEL); + if (!actions) + return -ENOMEM; + + fs_dr_actions = kcalloc(MLX5_FLOW_CONTEXT_ACTION_MAX, + sizeof(*fs_dr_actions), GFP_KERNEL); + if (!fs_dr_actions) { + kfree(actions); + return -ENOMEM; + } + + match_sz = sizeof(fte->val); + + /* The order of the actions are must to be keep, only the following + * order is supported by SW steering: + * TX: push vlan -> modify header -> encap + * RX: decap -> pop vlan -> modify header + */ + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH) { + tmp_action = create_action_push_vlan(domain, &fte->action.vlan[0]); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_PUSH_2) { + tmp_action = create_action_push_vlan(domain, &fte->action.vlan[1]); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_DECAP) { + enum mlx5dr_action_reformat_type decap_type = + DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2; + + tmp_action = mlx5dr_action_create_packet_reformat(domain, + decap_type, 0, + NULL); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_PACKET_REFORMAT) { + bool is_decap = fte->action.pkt_reformat->reformat_type == + MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2; + + if (is_decap) + actions[num_actions++] = + fte->action.pkt_reformat->action.dr_action; + else + delay_encap_set = true; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP) { + tmp_action = + mlx5dr_action_create_pop_vlan(); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_VLAN_POP_2) { + tmp_action = + mlx5dr_action_create_pop_vlan(); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_MOD_HDR) + actions[num_actions++] = + fte->action.modify_hdr->action.dr_action; + + if (delay_encap_set) + actions[num_actions++] = + fte->action.pkt_reformat->action.dr_action; + + /* The order of the actions below is not important */ + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_DROP) { + tmp_action = mlx5dr_action_create_drop(); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + term_action = tmp_action; + } + + if (fte->flow_context.flow_tag) { + tmp_action = + mlx5dr_action_create_tag(fte->flow_context.flow_tag); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + } + + if (fte->action.action & MLX5_FLOW_CONTEXT_ACTION_FWD_DEST) { + list_for_each_entry(dst, &fte->node.children, node.list) { + enum mlx5_flow_destination_type type = dst->dest_attr.type; + u32 id; + + if (num_actions == MLX5_FLOW_CONTEXT_ACTION_MAX) { + err = -ENOSPC; + goto free_actions; + } + + switch (type) { + case MLX5_FLOW_DESTINATION_TYPE_COUNTER: + id = dst->dest_attr.counter_id; + + tmp_action = + mlx5dr_action_create_flow_counter(id); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + actions[num_actions++] = tmp_action; + break; + case MLX5_FLOW_DESTINATION_TYPE_FLOW_TABLE: + tmp_action = create_ft_action(dev, dst); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + term_action = tmp_action; + break; + case MLX5_FLOW_DESTINATION_TYPE_VPORT: + tmp_action = create_vport_action(domain, dst); + if (!tmp_action) { + err = -ENOMEM; + goto free_actions; + } + fs_dr_actions[fs_dr_num_actions++] = tmp_action; + term_action = tmp_action; + break; + default: + err = -EOPNOTSUPP; + goto free_actions; + } + } + } + + params.match_sz = match_sz; + params.match_buf = (u64 *)fte->val; + + if (term_action) + actions[num_actions++] = term_action; + + rule = mlx5dr_rule_create(group->fs_dr_matcher.dr_matcher, + ¶ms, + num_actions, + actions); + if (!rule) { + err = -EINVAL; + goto free_actions; + } + + kfree(actions); + fte->fs_dr_rule.dr_rule = rule; + fte->fs_dr_rule.num_actions = fs_dr_num_actions; + fte->fs_dr_rule.dr_actions = fs_dr_actions; + + return 0; + +free_actions: + for (i = 0; i < fs_dr_num_actions; i++) + if (!IS_ERR_OR_NULL(fs_dr_actions[i])) + mlx5dr_action_destroy(fs_dr_actions[i]); + + mlx5_core_err(dev, "Failed to create dr rule err(%d)\n", err); + kfree(actions); + kfree(fs_dr_actions); + return err; +} + +static int mlx5_cmd_dr_packet_reformat_alloc(struct mlx5_flow_root_namespace *ns, + int reformat_type, + size_t size, + void *reformat_data, + enum mlx5_flow_namespace_type namespace, + struct mlx5_pkt_reformat *pkt_reformat) +{ + struct mlx5dr_domain *dr_domain = ns->fs_dr_domain.dr_domain; + struct mlx5dr_action *action; + int dr_reformat; + + switch (reformat_type) { + case MLX5_REFORMAT_TYPE_L2_TO_VXLAN: + case MLX5_REFORMAT_TYPE_L2_TO_NVGRE: + case MLX5_REFORMAT_TYPE_L2_TO_L2_TUNNEL: + dr_reformat = DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2; + break; + case MLX5_REFORMAT_TYPE_L3_TUNNEL_TO_L2: + dr_reformat = DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2; + break; + case MLX5_REFORMAT_TYPE_L2_TO_L3_TUNNEL: + dr_reformat = DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3; + break; + default: + mlx5_core_err(ns->dev, "Packet-reformat not supported(%d)\n", + reformat_type); + return -EOPNOTSUPP; + } + + action = mlx5dr_action_create_packet_reformat(dr_domain, + dr_reformat, + size, + reformat_data); + if (!action) { + mlx5_core_err(ns->dev, "Failed allocating packet-reformat action\n"); + return -EINVAL; + } + + pkt_reformat->action.dr_action = action; + + return 0; +} + +static void mlx5_cmd_dr_packet_reformat_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_pkt_reformat *pkt_reformat) +{ + mlx5dr_action_destroy(pkt_reformat->action.dr_action); +} + +static int mlx5_cmd_dr_modify_header_alloc(struct mlx5_flow_root_namespace *ns, + u8 namespace, u8 num_actions, + void *modify_actions, + struct mlx5_modify_hdr *modify_hdr) +{ + struct mlx5dr_domain *dr_domain = ns->fs_dr_domain.dr_domain; + struct mlx5dr_action *action; + size_t actions_sz; + + actions_sz = MLX5_UN_SZ_BYTES(set_action_in_add_action_in_auto) * + num_actions; + action = mlx5dr_action_create_modify_header(dr_domain, 0, + actions_sz, + modify_actions); + if (!action) { + mlx5_core_err(ns->dev, "Failed allocating modify-header action\n"); + return -EINVAL; + } + + modify_hdr->action.dr_action = action; + + return 0; +} + +static void mlx5_cmd_dr_modify_header_dealloc(struct mlx5_flow_root_namespace *ns, + struct mlx5_modify_hdr *modify_hdr) +{ + mlx5dr_action_destroy(modify_hdr->action.dr_action); +} + +static int mlx5_cmd_dr_update_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct mlx5_flow_group *group, + int modify_mask, + struct fs_fte *fte) +{ + return -EOPNOTSUPP; +} + +static int mlx5_cmd_dr_delete_fte(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_table *ft, + struct fs_fte *fte) +{ + struct mlx5_fs_dr_rule *rule = &fte->fs_dr_rule; + int err; + int i; + + if (mlx5_dr_is_fw_table(ft->flags)) + return mlx5_fs_cmd_get_fw_cmds()->delete_fte(ns, ft, fte); + + err = mlx5dr_rule_destroy(rule->dr_rule); + if (err) + return err; + + for (i = 0; i < rule->num_actions; i++) + if (!IS_ERR_OR_NULL(rule->dr_actions[i])) + mlx5dr_action_destroy(rule->dr_actions[i]); + + kfree(rule->dr_actions); + return 0; +} + +static int mlx5_cmd_dr_set_peer(struct mlx5_flow_root_namespace *ns, + struct mlx5_flow_root_namespace *peer_ns) +{ + struct mlx5dr_domain *peer_domain = NULL; + + if (peer_ns) + peer_domain = peer_ns->fs_dr_domain.dr_domain; + mlx5dr_domain_set_peer(ns->fs_dr_domain.dr_domain, + peer_domain); + return 0; +} + +static int mlx5_cmd_dr_create_ns(struct mlx5_flow_root_namespace *ns) +{ + ns->fs_dr_domain.dr_domain = + mlx5dr_domain_create(ns->dev, + MLX5DR_DOMAIN_TYPE_FDB); + if (!ns->fs_dr_domain.dr_domain) { + mlx5_core_err(ns->dev, "Failed to create dr flow namespace\n"); + return -EOPNOTSUPP; + } + return 0; +} + +static int mlx5_cmd_dr_destroy_ns(struct mlx5_flow_root_namespace *ns) +{ + return mlx5dr_domain_destroy(ns->fs_dr_domain.dr_domain); +} + +bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev) +{ + return mlx5dr_is_supported(dev); +} + +static const struct mlx5_flow_cmds mlx5_flow_cmds_dr = { + .create_flow_table = mlx5_cmd_dr_create_flow_table, + .destroy_flow_table = mlx5_cmd_dr_destroy_flow_table, + .modify_flow_table = mlx5_cmd_dr_modify_flow_table, + .create_flow_group = mlx5_cmd_dr_create_flow_group, + .destroy_flow_group = mlx5_cmd_dr_destroy_flow_group, + .create_fte = mlx5_cmd_dr_create_fte, + .update_fte = mlx5_cmd_dr_update_fte, + .delete_fte = mlx5_cmd_dr_delete_fte, + .update_root_ft = mlx5_cmd_dr_update_root_ft, + .packet_reformat_alloc = mlx5_cmd_dr_packet_reformat_alloc, + .packet_reformat_dealloc = mlx5_cmd_dr_packet_reformat_dealloc, + .modify_header_alloc = mlx5_cmd_dr_modify_header_alloc, + .modify_header_dealloc = mlx5_cmd_dr_modify_header_dealloc, + .set_peer = mlx5_cmd_dr_set_peer, + .create_ns = mlx5_cmd_dr_create_ns, + .destroy_ns = mlx5_cmd_dr_destroy_ns, +}; + +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void) +{ + return &mlx5_flow_cmds_dr; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h new file mode 100644 index 000000000000..1fb185d6ac7f --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/fs_dr.h @@ -0,0 +1,60 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB + * Copyright (c) 2019 Mellanox Technologies + */ + +#ifndef _MLX5_FS_DR_ +#define _MLX5_FS_DR_ + +#include "mlx5dr.h" + +struct mlx5_flow_root_namespace; +struct fs_fte; + +struct mlx5_fs_dr_action { + struct mlx5dr_action *dr_action; +}; + +struct mlx5_fs_dr_ns { + struct mlx5_dr_ns *dr_ns; +}; + +struct mlx5_fs_dr_rule { + struct mlx5dr_rule *dr_rule; + /* Only actions created by fs_dr */ + struct mlx5dr_action **dr_actions; + int num_actions; +}; + +struct mlx5_fs_dr_domain { + struct mlx5dr_domain *dr_domain; +}; + +struct mlx5_fs_dr_matcher { + struct mlx5dr_matcher *dr_matcher; +}; + +struct mlx5_fs_dr_table { + struct mlx5dr_table *dr_table; + struct mlx5dr_action *miss_action; +}; + +#ifdef CONFIG_MLX5_SW_STEERING + +bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev); + +const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void); + +#else + +static inline const struct mlx5_flow_cmds *mlx5_fs_cmd_get_dr_cmds(void) +{ + return NULL; +} + +static inline bool mlx5_fs_dr_is_supported(struct mlx5_core_dev *dev) +{ + return false; +} + +#endif /* CONFIG_MLX5_SW_STEERING */ +#endif diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h new file mode 100644 index 000000000000..596c927220d9 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5_ifc_dr.h @@ -0,0 +1,604 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019, Mellanox Technologies */ + +#ifndef MLX5_IFC_DR_H +#define MLX5_IFC_DR_H + +enum { + MLX5DR_ACTION_MDFY_HW_FLD_L2_0 = 0, + MLX5DR_ACTION_MDFY_HW_FLD_L2_1 = 1, + MLX5DR_ACTION_MDFY_HW_FLD_L2_2 = 2, + MLX5DR_ACTION_MDFY_HW_FLD_L3_0 = 3, + MLX5DR_ACTION_MDFY_HW_FLD_L3_1 = 4, + MLX5DR_ACTION_MDFY_HW_FLD_L3_2 = 5, + MLX5DR_ACTION_MDFY_HW_FLD_L3_3 = 6, + MLX5DR_ACTION_MDFY_HW_FLD_L3_4 = 7, + MLX5DR_ACTION_MDFY_HW_FLD_L4_0 = 8, + MLX5DR_ACTION_MDFY_HW_FLD_L4_1 = 9, + MLX5DR_ACTION_MDFY_HW_FLD_MPLS = 10, + MLX5DR_ACTION_MDFY_HW_FLD_L2_TNL_0 = 11, + MLX5DR_ACTION_MDFY_HW_FLD_REG_0 = 12, + MLX5DR_ACTION_MDFY_HW_FLD_REG_1 = 13, + MLX5DR_ACTION_MDFY_HW_FLD_REG_2 = 14, + MLX5DR_ACTION_MDFY_HW_FLD_REG_3 = 15, + MLX5DR_ACTION_MDFY_HW_FLD_L4_2 = 16, + MLX5DR_ACTION_MDFY_HW_FLD_FLEX_0 = 17, + MLX5DR_ACTION_MDFY_HW_FLD_FLEX_1 = 18, + MLX5DR_ACTION_MDFY_HW_FLD_FLEX_2 = 19, + MLX5DR_ACTION_MDFY_HW_FLD_FLEX_3 = 20, + MLX5DR_ACTION_MDFY_HW_FLD_L2_TNL_1 = 21, + MLX5DR_ACTION_MDFY_HW_FLD_METADATA = 22, + MLX5DR_ACTION_MDFY_HW_FLD_RESERVED = 23, +}; + +enum { + MLX5DR_ACTION_MDFY_HW_OP_SET = 0x2, + MLX5DR_ACTION_MDFY_HW_OP_ADD = 0x3, +}; + +enum { + MLX5DR_ACTION_MDFY_HW_HDR_L3_NONE = 0x0, + MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV4 = 0x1, + MLX5DR_ACTION_MDFY_HW_HDR_L3_IPV6 = 0x2, +}; + +enum { + MLX5DR_ACTION_MDFY_HW_HDR_L4_NONE = 0x0, + MLX5DR_ACTION_MDFY_HW_HDR_L4_TCP = 0x1, + MLX5DR_ACTION_MDFY_HW_HDR_L4_UDP = 0x2, +}; + +enum { + MLX5DR_STE_LU_TYPE_NOP = 0x00, + MLX5DR_STE_LU_TYPE_SRC_GVMI_AND_QP = 0x05, + MLX5DR_STE_LU_TYPE_ETHL2_TUNNELING_I = 0x0a, + MLX5DR_STE_LU_TYPE_ETHL2_DST_O = 0x06, + MLX5DR_STE_LU_TYPE_ETHL2_DST_I = 0x07, + MLX5DR_STE_LU_TYPE_ETHL2_DST_D = 0x1b, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_O = 0x08, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_I = 0x09, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_D = 0x1c, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_O = 0x36, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_I = 0x37, + MLX5DR_STE_LU_TYPE_ETHL2_SRC_DST_D = 0x38, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_O = 0x0d, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_I = 0x0e, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_DST_D = 0x1e, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_O = 0x0f, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_I = 0x10, + MLX5DR_STE_LU_TYPE_ETHL3_IPV6_SRC_D = 0x1f, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_O = 0x11, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_I = 0x12, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_5_TUPLE_D = 0x20, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_O = 0x29, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_I = 0x2a, + MLX5DR_STE_LU_TYPE_ETHL3_IPV4_MISC_D = 0x2b, + MLX5DR_STE_LU_TYPE_ETHL4_O = 0x13, + MLX5DR_STE_LU_TYPE_ETHL4_I = 0x14, + MLX5DR_STE_LU_TYPE_ETHL4_D = 0x21, + MLX5DR_STE_LU_TYPE_ETHL4_MISC_O = 0x2c, + MLX5DR_STE_LU_TYPE_ETHL4_MISC_I = 0x2d, + MLX5DR_STE_LU_TYPE_ETHL4_MISC_D = 0x2e, + MLX5DR_STE_LU_TYPE_MPLS_FIRST_O = 0x15, + MLX5DR_STE_LU_TYPE_MPLS_FIRST_I = 0x24, + MLX5DR_STE_LU_TYPE_MPLS_FIRST_D = 0x25, + MLX5DR_STE_LU_TYPE_GRE = 0x16, + MLX5DR_STE_LU_TYPE_FLEX_PARSER_0 = 0x22, + MLX5DR_STE_LU_TYPE_FLEX_PARSER_1 = 0x23, + MLX5DR_STE_LU_TYPE_FLEX_PARSER_TNL_HEADER = 0x19, + MLX5DR_STE_LU_TYPE_GENERAL_PURPOSE = 0x18, + MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_0 = 0x2f, + MLX5DR_STE_LU_TYPE_STEERING_REGISTERS_1 = 0x30, + MLX5DR_STE_LU_TYPE_DONT_CARE = 0x0f, +}; + +enum mlx5dr_ste_entry_type { + MLX5DR_STE_TYPE_TX = 1, + MLX5DR_STE_TYPE_RX = 2, + MLX5DR_STE_TYPE_MODIFY_PKT = 6, +}; + +struct mlx5_ifc_ste_general_bits { + u8 entry_type[0x4]; + u8 reserved_at_4[0x4]; + u8 entry_sub_type[0x8]; + u8 byte_mask[0x10]; + + u8 next_table_base_63_48[0x10]; + u8 next_lu_type[0x8]; + u8 next_table_base_39_32_size[0x8]; + + u8 next_table_base_31_5_size[0x1b]; + u8 linear_hash_enable[0x1]; + u8 reserved_at_5c[0x2]; + u8 next_table_rank[0x2]; + + u8 reserved_at_60[0xa0]; + u8 tag_value[0x60]; + u8 bit_mask[0x60]; +}; + +struct mlx5_ifc_ste_sx_transmit_bits { + u8 entry_type[0x4]; + u8 reserved_at_4[0x4]; + u8 entry_sub_type[0x8]; + u8 byte_mask[0x10]; + + u8 next_table_base_63_48[0x10]; + u8 next_lu_type[0x8]; + u8 next_table_base_39_32_size[0x8]; + + u8 next_table_base_31_5_size[0x1b]; + u8 linear_hash_enable[0x1]; + u8 reserved_at_5c[0x2]; + u8 next_table_rank[0x2]; + + u8 sx_wire[0x1]; + u8 sx_func_lb[0x1]; + u8 sx_sniffer[0x1]; + u8 sx_wire_enable[0x1]; + u8 sx_func_lb_enable[0x1]; + u8 sx_sniffer_enable[0x1]; + u8 action_type[0x3]; + u8 reserved_at_69[0x1]; + u8 action_description[0x6]; + u8 gvmi[0x10]; + + u8 encap_pointer_vlan_data[0x20]; + + u8 loopback_syndome_en[0x8]; + u8 loopback_syndome[0x8]; + u8 counter_trigger[0x10]; + + u8 miss_address_63_48[0x10]; + u8 counter_trigger_23_16[0x8]; + u8 miss_address_39_32[0x8]; + + u8 miss_address_31_6[0x1a]; + u8 learning_point[0x1]; + u8 go_back[0x1]; + u8 match_polarity[0x1]; + u8 mask_mode[0x1]; + u8 miss_rank[0x2]; +}; + +struct mlx5_ifc_ste_rx_steering_mult_bits { + u8 entry_type[0x4]; + u8 reserved_at_4[0x4]; + u8 entry_sub_type[0x8]; + u8 byte_mask[0x10]; + + u8 next_table_base_63_48[0x10]; + u8 next_lu_type[0x8]; + u8 next_table_base_39_32_size[0x8]; + + u8 next_table_base_31_5_size[0x1b]; + u8 linear_hash_enable[0x1]; + u8 reserved_at_[0x2]; + u8 next_table_rank[0x2]; + + u8 member_count[0x10]; + u8 gvmi[0x10]; + + u8 qp_list_pointer[0x20]; + + u8 reserved_at_a0[0x1]; + u8 tunneling_action[0x3]; + u8 action_description[0x4]; + u8 reserved_at_a8[0x8]; + u8 counter_trigger_15_0[0x10]; + + u8 miss_address_63_48[0x10]; + u8 counter_trigger_23_16[0x08]; + u8 miss_address_39_32[0x8]; + + u8 miss_address_31_6[0x1a]; + u8 learning_point[0x1]; + u8 fail_on_error[0x1]; + u8 match_polarity[0x1]; + u8 mask_mode[0x1]; + u8 miss_rank[0x2]; +}; + +struct mlx5_ifc_ste_modify_packet_bits { + u8 entry_type[0x4]; + u8 reserved_at_4[0x4]; + u8 entry_sub_type[0x8]; + u8 byte_mask[0x10]; + + u8 next_table_base_63_48[0x10]; + u8 next_lu_type[0x8]; + u8 next_table_base_39_32_size[0x8]; + + u8 next_table_base_31_5_size[0x1b]; + u8 linear_hash_enable[0x1]; + u8 reserved_at_[0x2]; + u8 next_table_rank[0x2]; + + u8 number_of_re_write_actions[0x10]; + u8 gvmi[0x10]; + + u8 header_re_write_actions_pointer[0x20]; + + u8 reserved_at_a0[0x1]; + u8 tunneling_action[0x3]; + u8 action_description[0x4]; + u8 reserved_at_a8[0x8]; + u8 counter_trigger_15_0[0x10]; + + u8 miss_address_63_48[0x10]; + u8 counter_trigger_23_16[0x08]; + u8 miss_address_39_32[0x8]; + + u8 miss_address_31_6[0x1a]; + u8 learning_point[0x1]; + u8 fail_on_error[0x1]; + u8 match_polarity[0x1]; + u8 mask_mode[0x1]; + u8 miss_rank[0x2]; +}; + +struct mlx5_ifc_ste_eth_l2_src_bits { + u8 smac_47_16[0x20]; + + u8 smac_15_0[0x10]; + u8 l3_ethertype[0x10]; + + u8 qp_type[0x2]; + u8 ethertype_filter[0x1]; + u8 reserved_at_43[0x1]; + u8 sx_sniffer[0x1]; + u8 force_lb[0x1]; + u8 functional_lb[0x1]; + u8 port[0x1]; + u8 reserved_at_48[0x4]; + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 first_vlan_qualifier[0x2]; + u8 reserved_at_52[0x2]; + u8 first_vlan_id[0xc]; + + u8 ip_fragmented[0x1]; + u8 tcp_syn[0x1]; + u8 encp_type[0x2]; + u8 l3_type[0x2]; + u8 l4_type[0x2]; + u8 reserved_at_68[0x4]; + u8 second_priority[0x3]; + u8 second_cfi[0x1]; + u8 second_vlan_qualifier[0x2]; + u8 reserved_at_72[0x2]; + u8 second_vlan_id[0xc]; +}; + +struct mlx5_ifc_ste_eth_l2_dst_bits { + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 l3_ethertype[0x10]; + + u8 qp_type[0x2]; + u8 ethertype_filter[0x1]; + u8 reserved_at_43[0x1]; + u8 sx_sniffer[0x1]; + u8 force_lb[0x1]; + u8 functional_lb[0x1]; + u8 port[0x1]; + u8 reserved_at_48[0x4]; + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 first_vlan_qualifier[0x2]; + u8 reserved_at_52[0x2]; + u8 first_vlan_id[0xc]; + + u8 ip_fragmented[0x1]; + u8 tcp_syn[0x1]; + u8 encp_type[0x2]; + u8 l3_type[0x2]; + u8 l4_type[0x2]; + u8 reserved_at_68[0x4]; + u8 second_priority[0x3]; + u8 second_cfi[0x1]; + u8 second_vlan_qualifier[0x2]; + u8 reserved_at_72[0x2]; + u8 second_vlan_id[0xc]; +}; + +struct mlx5_ifc_ste_eth_l2_src_dst_bits { + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 smac_47_32[0x10]; + + u8 smac_31_0[0x20]; + + u8 sx_sniffer[0x1]; + u8 force_lb[0x1]; + u8 functional_lb[0x1]; + u8 port[0x1]; + u8 l3_type[0x2]; + u8 reserved_at_66[0x6]; + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 first_vlan_qualifier[0x2]; + u8 reserved_at_72[0x2]; + u8 first_vlan_id[0xc]; +}; + +struct mlx5_ifc_ste_eth_l3_ipv4_5_tuple_bits { + u8 destination_address[0x20]; + + u8 source_address[0x20]; + + u8 source_port[0x10]; + u8 destination_port[0x10]; + + u8 fragmented[0x1]; + u8 first_fragment[0x1]; + u8 reserved_at_62[0x2]; + u8 reserved_at_64[0x1]; + u8 ecn[0x2]; + u8 tcp_ns[0x1]; + u8 tcp_cwr[0x1]; + u8 tcp_ece[0x1]; + u8 tcp_urg[0x1]; + u8 tcp_ack[0x1]; + u8 tcp_psh[0x1]; + u8 tcp_rst[0x1]; + u8 tcp_syn[0x1]; + u8 tcp_fin[0x1]; + u8 dscp[0x6]; + u8 reserved_at_76[0x2]; + u8 protocol[0x8]; +}; + +struct mlx5_ifc_ste_eth_l3_ipv6_dst_bits { + u8 dst_ip_127_96[0x20]; + + u8 dst_ip_95_64[0x20]; + + u8 dst_ip_63_32[0x20]; + + u8 dst_ip_31_0[0x20]; +}; + +struct mlx5_ifc_ste_eth_l2_tnl_bits { + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 l3_ethertype[0x10]; + + u8 l2_tunneling_network_id[0x20]; + + u8 ip_fragmented[0x1]; + u8 tcp_syn[0x1]; + u8 encp_type[0x2]; + u8 l3_type[0x2]; + u8 l4_type[0x2]; + u8 first_priority[0x3]; + u8 first_cfi[0x1]; + u8 reserved_at_6c[0x3]; + u8 gre_key_flag[0x1]; + u8 first_vlan_qualifier[0x2]; + u8 reserved_at_72[0x2]; + u8 first_vlan_id[0xc]; +}; + +struct mlx5_ifc_ste_eth_l3_ipv6_src_bits { + u8 src_ip_127_96[0x20]; + + u8 src_ip_95_64[0x20]; + + u8 src_ip_63_32[0x20]; + + u8 src_ip_31_0[0x20]; +}; + +struct mlx5_ifc_ste_eth_l3_ipv4_misc_bits { + u8 version[0x4]; + u8 ihl[0x4]; + u8 reserved_at_8[0x8]; + u8 total_length[0x10]; + + u8 identification[0x10]; + u8 flags[0x3]; + u8 fragment_offset[0xd]; + + u8 time_to_live[0x8]; + u8 reserved_at_48[0x8]; + u8 checksum[0x10]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_ste_eth_l4_bits { + u8 fragmented[0x1]; + u8 first_fragment[0x1]; + u8 reserved_at_2[0x6]; + u8 protocol[0x8]; + u8 dst_port[0x10]; + + u8 ipv6_version[0x4]; + u8 reserved_at_24[0x1]; + u8 ecn[0x2]; + u8 tcp_ns[0x1]; + u8 tcp_cwr[0x1]; + u8 tcp_ece[0x1]; + u8 tcp_urg[0x1]; + u8 tcp_ack[0x1]; + u8 tcp_psh[0x1]; + u8 tcp_rst[0x1]; + u8 tcp_syn[0x1]; + u8 tcp_fin[0x1]; + u8 src_port[0x10]; + + u8 ipv6_payload_length[0x10]; + u8 ipv6_hop_limit[0x8]; + u8 dscp[0x6]; + u8 reserved_at_5e[0x2]; + + u8 tcp_data_offset[0x4]; + u8 reserved_at_64[0x8]; + u8 flow_label[0x14]; +}; + +struct mlx5_ifc_ste_eth_l4_misc_bits { + u8 checksum[0x10]; + u8 length[0x10]; + + u8 seq_num[0x20]; + + u8 ack_num[0x20]; + + u8 urgent_pointer[0x10]; + u8 window_size[0x10]; +}; + +struct mlx5_ifc_ste_mpls_bits { + u8 mpls0_label[0x14]; + u8 mpls0_exp[0x3]; + u8 mpls0_s_bos[0x1]; + u8 mpls0_ttl[0x8]; + + u8 mpls1_label[0x20]; + + u8 mpls2_label[0x20]; + + u8 reserved_at_60[0x16]; + u8 mpls4_s_bit[0x1]; + u8 mpls4_qualifier[0x1]; + u8 mpls3_s_bit[0x1]; + u8 mpls3_qualifier[0x1]; + u8 mpls2_s_bit[0x1]; + u8 mpls2_qualifier[0x1]; + u8 mpls1_s_bit[0x1]; + u8 mpls1_qualifier[0x1]; + u8 mpls0_s_bit[0x1]; + u8 mpls0_qualifier[0x1]; +}; + +struct mlx5_ifc_ste_register_0_bits { + u8 register_0_h[0x20]; + + u8 register_0_l[0x20]; + + u8 register_1_h[0x20]; + + u8 register_1_l[0x20]; +}; + +struct mlx5_ifc_ste_register_1_bits { + u8 register_2_h[0x20]; + + u8 register_2_l[0x20]; + + u8 register_3_h[0x20]; + + u8 register_3_l[0x20]; +}; + +struct mlx5_ifc_ste_gre_bits { + u8 gre_c_present[0x1]; + u8 reserved_at_30[0x1]; + u8 gre_k_present[0x1]; + u8 gre_s_present[0x1]; + u8 strict_src_route[0x1]; + u8 recur[0x3]; + u8 flags[0x5]; + u8 version[0x3]; + u8 gre_protocol[0x10]; + + u8 checksum[0x10]; + u8 offset[0x10]; + + u8 gre_key_h[0x18]; + u8 gre_key_l[0x8]; + + u8 seq_num[0x20]; +}; + +struct mlx5_ifc_ste_flex_parser_0_bits { + u8 parser_3_label[0x14]; + u8 parser_3_exp[0x3]; + u8 parser_3_s_bos[0x1]; + u8 parser_3_ttl[0x8]; + + u8 flex_parser_2[0x20]; + + u8 flex_parser_1[0x20]; + + u8 flex_parser_0[0x20]; +}; + +struct mlx5_ifc_ste_flex_parser_1_bits { + u8 flex_parser_7[0x20]; + + u8 flex_parser_6[0x20]; + + u8 flex_parser_5[0x20]; + + u8 flex_parser_4[0x20]; +}; + +struct mlx5_ifc_ste_flex_parser_tnl_bits { + u8 flex_parser_tunneling_header_63_32[0x20]; + + u8 flex_parser_tunneling_header_31_0[0x20]; + + u8 reserved_at_40[0x40]; +}; + +struct mlx5_ifc_ste_general_purpose_bits { + u8 general_purpose_lookup_field[0x20]; + + u8 reserved_at_20[0x20]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_ste_src_gvmi_qp_bits { + u8 loopback_syndrome[0x8]; + u8 reserved_at_8[0x8]; + u8 source_gvmi[0x10]; + + u8 reserved_at_20[0x5]; + u8 force_lb[0x1]; + u8 functional_lb[0x1]; + u8 source_is_requestor[0x1]; + u8 source_qp[0x18]; + + u8 reserved_at_40[0x20]; + + u8 reserved_at_60[0x20]; +}; + +struct mlx5_ifc_l2_hdr_bits { + u8 dmac_47_16[0x20]; + + u8 dmac_15_0[0x10]; + u8 smac_47_32[0x10]; + + u8 smac_31_0[0x20]; + + u8 ethertype[0x10]; + u8 vlan_type[0x10]; + + u8 vlan[0x10]; + u8 reserved_at_90[0x10]; +}; + +/* Both HW set and HW add share the same HW format with different opcodes */ +struct mlx5_ifc_dr_action_hw_set_bits { + u8 opcode[0x8]; + u8 destination_field_code[0x8]; + u8 reserved_at_10[0x2]; + u8 destination_left_shifter[0x6]; + u8 reserved_at_18[0x3]; + u8 destination_length[0x5]; + + u8 inline_data[0x20]; +}; + +#endif /* MLX5_IFC_DR_H */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h new file mode 100644 index 000000000000..adda9cbfba45 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/mlx5dr.h @@ -0,0 +1,212 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB */ +/* Copyright (c) 2019, Mellanox Technologies */ + +#ifndef _MLX5DR_H_ +#define _MLX5DR_H_ + +struct mlx5dr_domain; +struct mlx5dr_table; +struct mlx5dr_matcher; +struct mlx5dr_rule; +struct mlx5dr_action; + +enum mlx5dr_domain_type { + MLX5DR_DOMAIN_TYPE_NIC_RX, + MLX5DR_DOMAIN_TYPE_NIC_TX, + MLX5DR_DOMAIN_TYPE_FDB, +}; + +enum mlx5dr_domain_sync_flags { + MLX5DR_DOMAIN_SYNC_FLAGS_SW = 1 << 0, + MLX5DR_DOMAIN_SYNC_FLAGS_HW = 1 << 1, +}; + +enum mlx5dr_action_reformat_type { + DR_ACTION_REFORMAT_TYP_TNL_L2_TO_L2, + DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L2, + DR_ACTION_REFORMAT_TYP_TNL_L3_TO_L2, + DR_ACTION_REFORMAT_TYP_L2_TO_TNL_L3, +}; + +struct mlx5dr_match_parameters { + size_t match_sz; + u64 *match_buf; /* Device spec format */ +}; + +#ifdef CONFIG_MLX5_SW_STEERING + +struct mlx5dr_domain * +mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type); + +int mlx5dr_domain_destroy(struct mlx5dr_domain *domain); + +int mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags); + +void mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, + struct mlx5dr_domain *peer_dmn); + +struct mlx5dr_table * +mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level); + +int mlx5dr_table_destroy(struct mlx5dr_table *table); + +u32 mlx5dr_table_get_id(struct mlx5dr_table *table); + +struct mlx5dr_matcher * +mlx5dr_matcher_create(struct mlx5dr_table *table, + u16 priority, + u8 match_criteria_enable, + struct mlx5dr_match_parameters *mask); + +int mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher); + +struct mlx5dr_rule * +mlx5dr_rule_create(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *value, + size_t num_actions, + struct mlx5dr_action *actions[]); + +int mlx5dr_rule_destroy(struct mlx5dr_rule *rule); + +int mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl, + struct mlx5dr_action *action); + +struct mlx5dr_action * +mlx5dr_action_create_dest_table(struct mlx5dr_table *table); + +struct mlx5dr_action * +mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft, + struct mlx5_core_dev *mdev); + +struct mlx5dr_action * +mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain, + u32 vport, u8 vhca_id_valid, + u16 vhca_id); + +struct mlx5dr_action *mlx5dr_action_create_drop(void); + +struct mlx5dr_action *mlx5dr_action_create_tag(u32 tag_value); + +struct mlx5dr_action * +mlx5dr_action_create_flow_counter(u32 counter_id); + +struct mlx5dr_action * +mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, + enum mlx5dr_action_reformat_type reformat_type, + size_t data_sz, + void *data); + +struct mlx5dr_action * +mlx5dr_action_create_modify_header(struct mlx5dr_domain *domain, + u32 flags, + size_t actions_sz, + __be64 actions[]); + +struct mlx5dr_action *mlx5dr_action_create_pop_vlan(void); + +struct mlx5dr_action * +mlx5dr_action_create_push_vlan(struct mlx5dr_domain *domain, __be32 vlan_hdr); + +int mlx5dr_action_destroy(struct mlx5dr_action *action); + +static inline bool +mlx5dr_is_supported(struct mlx5_core_dev *dev) +{ + return MLX5_CAP_ESW_FLOWTABLE_FDB(dev, sw_owner); +} + +#else /* CONFIG_MLX5_SW_STEERING */ + +static inline struct mlx5dr_domain * +mlx5dr_domain_create(struct mlx5_core_dev *mdev, enum mlx5dr_domain_type type) { return NULL; } + +static inline int +mlx5dr_domain_destroy(struct mlx5dr_domain *domain) { return 0; } + +static inline int +mlx5dr_domain_sync(struct mlx5dr_domain *domain, u32 flags) { return 0; } + +static inline void +mlx5dr_domain_set_peer(struct mlx5dr_domain *dmn, + struct mlx5dr_domain *peer_dmn) { } + +static inline struct mlx5dr_table * +mlx5dr_table_create(struct mlx5dr_domain *domain, u32 level) { return NULL; } + +static inline int +mlx5dr_table_destroy(struct mlx5dr_table *table) { return 0; } + +static inline u32 +mlx5dr_table_get_id(struct mlx5dr_table *table) { return 0; } + +static inline struct mlx5dr_matcher * +mlx5dr_matcher_create(struct mlx5dr_table *table, + u16 priority, + u8 match_criteria_enable, + struct mlx5dr_match_parameters *mask) { return NULL; } + +static inline int +mlx5dr_matcher_destroy(struct mlx5dr_matcher *matcher) { return 0; } + +static inline struct mlx5dr_rule * +mlx5dr_rule_create(struct mlx5dr_matcher *matcher, + struct mlx5dr_match_parameters *value, + size_t num_actions, + struct mlx5dr_action *actions[]) { return NULL; } + +static inline int +mlx5dr_rule_destroy(struct mlx5dr_rule *rule) { return 0; } + +static inline int +mlx5dr_table_set_miss_action(struct mlx5dr_table *tbl, + struct mlx5dr_action *action) { return 0; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_dest_table(struct mlx5dr_table *table) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_create_action_dest_flow_fw_table(struct mlx5_flow_table *ft, + struct mlx5_core_dev *mdev) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_dest_vport(struct mlx5dr_domain *domain, + u32 vport, u8 vhca_id_valid, + u16 vhca_id) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_drop(void) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_tag(u32 tag_value) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_flow_counter(u32 counter_id) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_packet_reformat(struct mlx5dr_domain *dmn, + enum mlx5dr_action_reformat_type reformat_type, + size_t data_sz, + void *data) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_modify_header(struct mlx5dr_domain *domain, + u32 flags, + size_t actions_sz, + __be64 actions[]) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_pop_vlan(void) { return NULL; } + +static inline struct mlx5dr_action * +mlx5dr_action_create_push_vlan(struct mlx5dr_domain *domain, + __be32 vlan_hdr) { return NULL; } + +static inline int +mlx5dr_action_destroy(struct mlx5dr_action *action) { return 0; } + +static inline bool +mlx5dr_is_supported(struct mlx5_core_dev *dev) { return false; } + +#endif /* CONFIG_MLX5_SW_STEERING */ + +#endif /* _MLX5DR_H_ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/vport.c b/drivers/net/ethernet/mellanox/mlx5/core/vport.c index c912d82ca64b..30f7848a6f88 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/vport.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/vport.c @@ -122,12 +122,13 @@ void mlx5_query_min_inline(struct mlx5_core_dev *mdev, u8 *min_inline_mode) { switch (MLX5_CAP_ETH(mdev, wqe_inline_mode)) { + case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: + if (!mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode)) + break; + /* fall through */ case MLX5_CAP_INLINE_MODE_L2: *min_inline_mode = MLX5_INLINE_MODE_L2; break; - case MLX5_CAP_INLINE_MODE_VPORT_CONTEXT: - mlx5_query_nic_vport_min_inline(mdev, 0, min_inline_mode); - break; case MLX5_CAP_INLINE_MODE_NOT_REQUIRED: *min_inline_mode = MLX5_INLINE_MODE_NONE; break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.c b/drivers/net/ethernet/mellanox/mlx5/core/wq.c index 953cc8efba69..dd2315ce4441 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.c @@ -44,6 +44,11 @@ u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq) return wq->fbc.sz_m1 + 1; } +u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq) +{ + return wq->fbc.log_stride; +} + u32 mlx5_wq_ll_get_size(struct mlx5_wq_ll *wq) { return (u32)wq->fbc.sz_m1 + 1; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index f1ec58c9e9e3..55791f71a778 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -89,6 +89,7 @@ int mlx5_cqwq_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *cqc, struct mlx5_cqwq *wq, struct mlx5_wq_ctrl *wq_ctrl); u32 mlx5_cqwq_get_size(struct mlx5_cqwq *wq); +u8 mlx5_cqwq_get_log_stride_size(struct mlx5_cqwq *wq); int mlx5_wq_ll_create(struct mlx5_core_dev *mdev, struct mlx5_wq_param *param, void *wqc, struct mlx5_wq_ll *wq, diff --git a/drivers/net/ethernet/mellanox/mlxsw/Kconfig b/drivers/net/ethernet/mellanox/mlxsw/Kconfig index 06c80343d9ed..f458fd1ce9f8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Kconfig +++ b/drivers/net/ethernet/mellanox/mlxsw/Kconfig @@ -71,7 +71,7 @@ config MLXSW_SWITCHX2 module will be called mlxsw_switchx2. config MLXSW_SPECTRUM - tristate "Mellanox Technologies Spectrum support" + tristate "Mellanox Technologies Spectrum family support" depends on MLXSW_CORE && MLXSW_PCI && NET_SWITCHDEV && VLAN_8021Q depends on PSAMPLE || PSAMPLE=n depends on BRIDGE || BRIDGE=n @@ -87,8 +87,8 @@ config MLXSW_SPECTRUM select NET_PTP_CLASSIFY if PTP_1588_CLOCK default m ---help--- - This driver supports Mellanox Technologies Spectrum Ethernet - Switch ASICs. + This driver supports Mellanox Technologies + Spectrum/Spectrum-2/Spectrum-3 Ethernet Switch ASICs. To compile this driver as a module, choose M here: the module will be called mlxsw_spectrum. diff --git a/drivers/net/ethernet/mellanox/mlxsw/Makefile b/drivers/net/ethernet/mellanox/mlxsw/Makefile index 171b36bd8a4e..0e86a581d45b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/Makefile +++ b/drivers/net/ethernet/mellanox/mlxsw/Makefile @@ -29,7 +29,7 @@ mlxsw_spectrum-objs := spectrum.o spectrum_buffers.o \ spectrum_mr_tcam.o spectrum_mr.o \ spectrum_qdisc.o spectrum_span.o \ spectrum_nve.o spectrum_nve_vxlan.o \ - spectrum_dpipe.o + spectrum_dpipe.o spectrum_trap.o mlxsw_spectrum-$(CONFIG_MLXSW_SPECTRUM_DCB) += spectrum_dcb.o mlxsw_spectrum-$(CONFIG_PTP_1588_CLOCK) += spectrum_ptp.o obj-$(CONFIG_MLXSW_MINIMAL) += mlxsw_minimal.o diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 17ceac7505e5..14dcc786926d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -80,7 +80,6 @@ struct mlxsw_core { struct mlxsw_thermal *thermal; struct mlxsw_core_port *ports; unsigned int max_ports; - bool reload_fail; bool fw_flash_in_progress; unsigned long driver_priv[0]; /* driver_priv has to be always the last item */ @@ -984,23 +983,29 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, return 0; } -static int mlxsw_devlink_core_bus_device_reload(struct devlink *devlink, - struct netlink_ext_ack *extack) +static int +mlxsw_devlink_core_bus_device_reload_down(struct devlink *devlink, + struct netlink_ext_ack *extack) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - int err; if (!(mlxsw_core->bus->features & MLXSW_BUS_F_RESET)) return -EOPNOTSUPP; mlxsw_core_bus_device_unregister(mlxsw_core, true); - err = mlxsw_core_bus_device_register(mlxsw_core->bus_info, - mlxsw_core->bus, - mlxsw_core->bus_priv, true, - devlink); - mlxsw_core->reload_fail = !!err; + return 0; +} - return err; +static int +mlxsw_devlink_core_bus_device_reload_up(struct devlink *devlink, + struct netlink_ext_ack *extack) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + + return mlxsw_core_bus_device_register(mlxsw_core->bus_info, + mlxsw_core->bus, + mlxsw_core->bus_priv, true, + devlink); } static int mlxsw_devlink_flash_update(struct devlink *devlink, @@ -1017,8 +1022,57 @@ static int mlxsw_devlink_flash_update(struct devlink *devlink, component, extack); } +static int mlxsw_devlink_trap_init(struct devlink *devlink, + const struct devlink_trap *trap, + void *trap_ctx) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver; + + if (!mlxsw_driver->trap_init) + return -EOPNOTSUPP; + return mlxsw_driver->trap_init(mlxsw_core, trap, trap_ctx); +} + +static void mlxsw_devlink_trap_fini(struct devlink *devlink, + const struct devlink_trap *trap, + void *trap_ctx) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver; + + if (!mlxsw_driver->trap_fini) + return; + mlxsw_driver->trap_fini(mlxsw_core, trap, trap_ctx); +} + +static int mlxsw_devlink_trap_action_set(struct devlink *devlink, + const struct devlink_trap *trap, + enum devlink_trap_action action) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver; + + if (!mlxsw_driver->trap_action_set) + return -EOPNOTSUPP; + return mlxsw_driver->trap_action_set(mlxsw_core, trap, action); +} + +static int +mlxsw_devlink_trap_group_init(struct devlink *devlink, + const struct devlink_trap_group *group) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + struct mlxsw_driver *mlxsw_driver = mlxsw_core->driver; + + if (!mlxsw_driver->trap_group_init) + return -EOPNOTSUPP; + return mlxsw_driver->trap_group_init(mlxsw_core, group); +} + static const struct devlink_ops mlxsw_devlink_ops = { - .reload = mlxsw_devlink_core_bus_device_reload, + .reload_down = mlxsw_devlink_core_bus_device_reload_down, + .reload_up = mlxsw_devlink_core_bus_device_reload_up, .port_type_set = mlxsw_devlink_port_type_set, .port_split = mlxsw_devlink_port_split, .port_unsplit = mlxsw_devlink_port_unsplit, @@ -1034,6 +1088,10 @@ static const struct devlink_ops mlxsw_devlink_ops = { .sb_occ_tc_port_bind_get = mlxsw_devlink_sb_occ_tc_port_bind_get, .info_get = mlxsw_devlink_info_get, .flash_update = mlxsw_devlink_flash_update, + .trap_init = mlxsw_devlink_trap_init, + .trap_fini = mlxsw_devlink_trap_fini, + .trap_action_set = mlxsw_devlink_trap_action_set, + .trap_group_init = mlxsw_devlink_trap_group_init, }; static int @@ -1191,7 +1249,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); - if (mlxsw_core->reload_fail) { + if (devlink_is_reload_failed(devlink)) { if (!reload) /* Only the parts that were not de-initialized in the * failed reload attempt need to be de-initialized. @@ -1477,6 +1535,18 @@ void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_trap_unregister); +int mlxsw_core_trap_action_set(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listener, + enum mlxsw_reg_hpkt_action action) +{ + char hpkt_pl[MLXSW_REG_HPKT_LEN]; + + mlxsw_reg_hpkt_pack(hpkt_pl, action, listener->trap_id, + listener->trap_group, listener->is_ctrl); + return mlxsw_reg_write(mlxsw_core, MLXSW_REG(hpkt), hpkt_pl); +} +EXPORT_SYMBOL(mlxsw_core_trap_action_set); + static u64 mlxsw_core_tid_get(struct mlxsw_core *mlxsw_core) { return atomic64_inc_return(&mlxsw_core->emad.tid); @@ -1794,11 +1864,12 @@ u64 mlxsw_core_res_get(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_res_get); -int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port, - u32 port_number, bool split, - u32 split_port_subnumber, - const unsigned char *switch_id, - unsigned char switch_id_len) +static int __mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port, + enum devlink_port_flavour flavour, + u32 port_number, bool split, + u32 split_port_subnumber, + const unsigned char *switch_id, + unsigned char switch_id_len) { struct devlink *devlink = priv_to_devlink(mlxsw_core); struct mlxsw_core_port *mlxsw_core_port = @@ -1807,17 +1878,16 @@ int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port, int err; mlxsw_core_port->local_port = local_port; - devlink_port_attrs_set(devlink_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, - port_number, split, split_port_subnumber, + devlink_port_attrs_set(devlink_port, flavour, port_number, + split, split_port_subnumber, switch_id, switch_id_len); err = devlink_port_register(devlink, devlink_port, local_port); if (err) memset(mlxsw_core_port, 0, sizeof(*mlxsw_core_port)); return err; } -EXPORT_SYMBOL(mlxsw_core_port_init); -void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port) +static void __mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port) { struct mlxsw_core_port *mlxsw_core_port = &mlxsw_core->ports[local_port]; @@ -1826,8 +1896,53 @@ void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port) devlink_port_unregister(devlink_port); memset(mlxsw_core_port, 0, sizeof(*mlxsw_core_port)); } + +int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port, + u32 port_number, bool split, + u32 split_port_subnumber, + const unsigned char *switch_id, + unsigned char switch_id_len) +{ + return __mlxsw_core_port_init(mlxsw_core, local_port, + DEVLINK_PORT_FLAVOUR_PHYSICAL, + port_number, split, split_port_subnumber, + switch_id, switch_id_len); +} +EXPORT_SYMBOL(mlxsw_core_port_init); + +void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port) +{ + __mlxsw_core_port_fini(mlxsw_core, local_port); +} EXPORT_SYMBOL(mlxsw_core_port_fini); +int mlxsw_core_cpu_port_init(struct mlxsw_core *mlxsw_core, + void *port_driver_priv, + const unsigned char *switch_id, + unsigned char switch_id_len) +{ + struct mlxsw_core_port *mlxsw_core_port = + &mlxsw_core->ports[MLXSW_PORT_CPU_PORT]; + int err; + + err = __mlxsw_core_port_init(mlxsw_core, MLXSW_PORT_CPU_PORT, + DEVLINK_PORT_FLAVOUR_CPU, + 0, false, 0, + switch_id, switch_id_len); + if (err) + return err; + + mlxsw_core_port->port_driver_priv = port_driver_priv; + return 0; +} +EXPORT_SYMBOL(mlxsw_core_cpu_port_init); + +void mlxsw_core_cpu_port_fini(struct mlxsw_core *mlxsw_core) +{ + __mlxsw_core_port_fini(mlxsw_core, MLXSW_PORT_CPU_PORT); +} +EXPORT_SYMBOL(mlxsw_core_cpu_port_fini); + void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u8 local_port, void *port_driver_priv, struct net_device *dev) { diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index 8efcff4b59cb..5d7d2ab6d155 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -128,6 +128,9 @@ int mlxsw_core_trap_register(struct mlxsw_core *mlxsw_core, void mlxsw_core_trap_unregister(struct mlxsw_core *mlxsw_core, const struct mlxsw_listener *listener, void *priv); +int mlxsw_core_trap_action_set(struct mlxsw_core *mlxsw_core, + const struct mlxsw_listener *listener, + enum mlxsw_reg_hpkt_action action); typedef void mlxsw_reg_trans_cb_t(struct mlxsw_core *mlxsw_core, char *payload, size_t payload_len, unsigned long cb_priv); @@ -174,6 +177,11 @@ int mlxsw_core_port_init(struct mlxsw_core *mlxsw_core, u8 local_port, const unsigned char *switch_id, unsigned char switch_id_len); void mlxsw_core_port_fini(struct mlxsw_core *mlxsw_core, u8 local_port); +int mlxsw_core_cpu_port_init(struct mlxsw_core *mlxsw_core, + void *port_driver_priv, + const unsigned char *switch_id, + unsigned char switch_id_len); +void mlxsw_core_cpu_port_fini(struct mlxsw_core *mlxsw_core); void mlxsw_core_port_eth_set(struct mlxsw_core *mlxsw_core, u8 local_port, void *port_driver_priv, struct net_device *dev); void mlxsw_core_port_ib_set(struct mlxsw_core *mlxsw_core, u8 local_port, @@ -289,6 +297,15 @@ struct mlxsw_driver { int (*flash_update)(struct mlxsw_core *mlxsw_core, const char *file_name, const char *component, struct netlink_ext_ack *extack); + int (*trap_init)(struct mlxsw_core *mlxsw_core, + const struct devlink_trap *trap, void *trap_ctx); + void (*trap_fini)(struct mlxsw_core *mlxsw_core, + const struct devlink_trap *trap, void *trap_ctx); + int (*trap_action_set)(struct mlxsw_core *mlxsw_core, + const struct devlink_trap *trap, + enum devlink_trap_action action); + int (*trap_group_init)(struct mlxsw_core *mlxsw_core, + const struct devlink_trap_group *group); void (*txhdr_construct)(struct sk_buff *skb, const struct mlxsw_tx_info *tx_info); int (*resources_register)(struct mlxsw_core *mlxsw_core); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.h b/drivers/net/ethernet/mellanox/mlxsw/pci.h index 946339e13eb9..5b1323645a5d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.h @@ -9,6 +9,7 @@ #define PCI_DEVICE_ID_MELLANOX_SWITCHX2 0xc738 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM 0xcb84 #define PCI_DEVICE_ID_MELLANOX_SPECTRUM2 0xcf6c +#define PCI_DEVICE_ID_MELLANOX_SPECTRUM3 0xcf70 #define PCI_DEVICE_ID_MELLANOX_SWITCHIB 0xcb20 #define PCI_DEVICE_ID_MELLANOX_SWITCHIB2 0xcf08 diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index ead36702549a..5494cf93f34c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -4126,7 +4126,6 @@ MLXSW_ITEM32(reg, ptys, ext_eth_proto_cap, 0x08, 0, 32); #define MLXSW_REG_PTYS_ETH_SPEED_20GBASE_KR2 BIT(5) #define MLXSW_REG_PTYS_ETH_SPEED_40GBASE_CR4 BIT(6) #define MLXSW_REG_PTYS_ETH_SPEED_40GBASE_KR4 BIT(7) -#define MLXSW_REG_PTYS_ETH_SPEED_56GBASE_R4 BIT(8) #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_CR BIT(12) #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_SR BIT(13) #define MLXSW_REG_PTYS_ETH_SPEED_10GBASE_ER_LR BIT(14) @@ -5422,6 +5421,14 @@ enum mlxsw_reg_htgt_trap_group { MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR, MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0, MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1, + + __MLXSW_REG_HTGT_TRAP_GROUP_MAX, + MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1 +}; + +enum mlxsw_reg_htgt_discard_trap_group { + MLXSW_REG_HTGT_DISCARD_TRAP_GROUP_BASE = MLXSW_REG_HTGT_TRAP_GROUP_MAX, + MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS, }; /* reg_htgt_trap_group @@ -5559,6 +5566,8 @@ enum mlxsw_reg_hpkt_action { MLXSW_REG_HPKT_ACTION_DISCARD, MLXSW_REG_HPKT_ACTION_SOFT_DISCARD, MLXSW_REG_HPKT_ACTION_TRAP_AND_SOFT_DISCARD, + MLXSW_REG_HPKT_ACTION_TRAP_EXCEPTION_TO_CPU, + MLXSW_REG_HPKT_ACTION_SET_FW_DEFAULT = 15, }; /* reg_hpkt_action @@ -5569,6 +5578,8 @@ enum mlxsw_reg_hpkt_action { * 3 - Discard. * 4 - Soft discard (allow other traps to act on the packet). * 5 - Trap and soft discard (allow other traps to overwrite this trap). + * 6 - Trap to CPU (CPU receives sole copy) and count it as error. + * 15 - Restore the firmware's default action. * Access: RW * * Note: Must be set to 0 (forward) for event trap IDs, as they are already diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index eda9c23e87b2..dd234cf7b39d 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -48,7 +48,7 @@ #define MLXSW_SP1_FWREV_MAJOR 13 #define MLXSW_SP1_FWREV_MINOR 2000 -#define MLXSW_SP1_FWREV_SUBMINOR 1122 +#define MLXSW_SP1_FWREV_SUBMINOR 1886 #define MLXSW_SP1_FWREV_CAN_RESET_MINOR 1702 static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { @@ -65,6 +65,7 @@ static const struct mlxsw_fw_rev mlxsw_sp1_fw_rev = { static const char mlxsw_sp1_driver_name[] = "mlxsw_spectrum"; static const char mlxsw_sp2_driver_name[] = "mlxsw_spectrum2"; +static const char mlxsw_sp3_driver_name[] = "mlxsw_spectrum3"; static const char mlxsw_sp_driver_version[] = "1.0"; static const unsigned char mlxsw_sp1_mac_mask[ETH_ALEN] = { @@ -174,6 +175,10 @@ struct mlxsw_sp_ptp_ops { void (*shaper_work)(struct work_struct *work); int (*get_ts_info)(struct mlxsw_sp *mlxsw_sp, struct ethtool_ts_info *info); + int (*get_stats_count)(void); + void (*get_stats_strings)(u8 **p); + void (*get_stats)(struct mlxsw_sp_port *mlxsw_sp_port, + u64 *data, int data_index); }; static int mlxsw_sp_component_query(struct mlxfw_dev *mlxfw_dev, @@ -1625,7 +1630,7 @@ mlxsw_sp_setup_tc_block_flower_bind(struct mlxsw_sp_port *mlxsw_sp_port, } flow_block_cb_incref(block_cb); err = mlxsw_sp_acl_block_bind(mlxsw_sp, acl_block, - mlxsw_sp_port, ingress); + mlxsw_sp_port, ingress, f->extack); if (err) goto err_block_bind; @@ -2328,6 +2333,7 @@ static void mlxsw_sp_port_get_tc_strings(u8 **p, int tc) static void mlxsw_sp_port_get_strings(struct net_device *dev, u32 stringset, u8 *data) { + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); u8 *p = data; int i; @@ -2369,6 +2375,7 @@ static void mlxsw_sp_port_get_strings(struct net_device *dev, for (i = 0; i < TC_MAX_QUEUE; i++) mlxsw_sp_port_get_tc_strings(&p, i); + mlxsw_sp_port->mlxsw_sp->ptp_ops->get_stats_strings(&p); break; } } @@ -2463,6 +2470,7 @@ static void __mlxsw_sp_port_get_stats(struct net_device *dev, static void mlxsw_sp_port_get_stats(struct net_device *dev, struct ethtool_stats *stats, u64 *data) { + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); int i, data_index = 0; /* IEEE 802.3 Counters */ @@ -2503,13 +2511,21 @@ static void mlxsw_sp_port_get_stats(struct net_device *dev, data, data_index); data_index += MLXSW_SP_PORT_HW_TC_STATS_LEN; } + + /* PTP counters */ + mlxsw_sp_port->mlxsw_sp->ptp_ops->get_stats(mlxsw_sp_port, + data, data_index); + data_index += mlxsw_sp_port->mlxsw_sp->ptp_ops->get_stats_count(); } static int mlxsw_sp_port_get_sset_count(struct net_device *dev, int sset) { + struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + switch (sset) { case ETH_SS_STATS: - return MLXSW_SP_PORT_ETHTOOL_STATS_LEN; + return MLXSW_SP_PORT_ETHTOOL_STATS_LEN + + mlxsw_sp_port->mlxsw_sp->ptp_ops->get_stats_count(); default: return -EOPNOTSUPP; } @@ -2608,26 +2624,6 @@ static const struct mlxsw_sp1_port_link_mode mlxsw_sp1_port_link_mode[] = { .speed = SPEED_50000, }, { - .mask = MLXSW_REG_PTYS_ETH_SPEED_56GBASE_R4, - .mask_ethtool = ETHTOOL_LINK_MODE_56000baseKR4_Full_BIT, - .speed = SPEED_56000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_56GBASE_R4, - .mask_ethtool = ETHTOOL_LINK_MODE_56000baseCR4_Full_BIT, - .speed = SPEED_56000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_56GBASE_R4, - .mask_ethtool = ETHTOOL_LINK_MODE_56000baseSR4_Full_BIT, - .speed = SPEED_56000, - }, - { - .mask = MLXSW_REG_PTYS_ETH_SPEED_56GBASE_R4, - .mask_ethtool = ETHTOOL_LINK_MODE_56000baseLR4_Full_BIT, - .speed = SPEED_56000, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4, .mask_ethtool = ETHTOOL_LINK_MODE_100000baseCR4_Full_BIT, .speed = SPEED_100000, @@ -2674,7 +2670,7 @@ mlxsw_sp1_from_ptys_supported_port(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp1_from_ptys_link(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto, - unsigned long *mode) + u8 width, unsigned long *mode) { int i; @@ -2715,7 +2711,7 @@ mlxsw_sp1_from_ptys_speed_duplex(struct mlxsw_sp *mlxsw_sp, bool carrier_ok, } static u32 -mlxsw_sp1_to_ptys_advert_link(struct mlxsw_sp *mlxsw_sp, +mlxsw_sp1_to_ptys_advert_link(struct mlxsw_sp *mlxsw_sp, u8 width, const struct ethtool_link_ksettings *cmd) { u32 ptys_proto = 0; @@ -2729,7 +2725,8 @@ mlxsw_sp1_to_ptys_advert_link(struct mlxsw_sp *mlxsw_sp, return ptys_proto; } -static u32 mlxsw_sp1_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, u32 speed) +static u32 mlxsw_sp1_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, u8 width, + u32 speed) { u32 ptys_proto = 0; int i; @@ -2917,11 +2914,31 @@ mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4[] = { #define MLXSW_SP2_MASK_ETHTOOL_200GAUI_4_200GBASE_CR4_KR4_LEN \ ARRAY_SIZE(mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4) +#define MLXSW_SP_PORT_MASK_WIDTH_1X BIT(0) +#define MLXSW_SP_PORT_MASK_WIDTH_2X BIT(1) +#define MLXSW_SP_PORT_MASK_WIDTH_4X BIT(2) + +static u8 mlxsw_sp_port_mask_width_get(u8 width) +{ + switch (width) { + case 1: + return MLXSW_SP_PORT_MASK_WIDTH_1X; + case 2: + return MLXSW_SP_PORT_MASK_WIDTH_2X; + case 4: + return MLXSW_SP_PORT_MASK_WIDTH_4X; + default: + WARN_ON_ONCE(1); + return 0; + } +} + struct mlxsw_sp2_port_link_mode { const enum ethtool_link_mode_bit_indices *mask_ethtool; int m_ethtool_len; u32 mask; u32 speed; + u8 mask_width; }; static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { @@ -2929,72 +2946,97 @@ static const struct mlxsw_sp2_port_link_mode mlxsw_sp2_port_link_mode[] = { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_SGMII_100M, .mask_ethtool = mlxsw_sp2_mask_ethtool_sgmii_100m, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_SGMII_100M_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | + MLXSW_SP_PORT_MASK_WIDTH_2X | + MLXSW_SP_PORT_MASK_WIDTH_4X, .speed = SPEED_100, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_1000BASE_X_SGMII, .mask_ethtool = mlxsw_sp2_mask_ethtool_1000base_x_sgmii, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_1000BASE_X_SGMII_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | + MLXSW_SP_PORT_MASK_WIDTH_2X | + MLXSW_SP_PORT_MASK_WIDTH_4X, .speed = SPEED_1000, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_2_5GBASE_X_2_5GMII, .mask_ethtool = mlxsw_sp2_mask_ethtool_2_5gbase_x_2_5gmii, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_2_5GBASE_X_2_5GMII_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | + MLXSW_SP_PORT_MASK_WIDTH_2X | + MLXSW_SP_PORT_MASK_WIDTH_4X, .speed = SPEED_2500, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_5GBASE_R, .mask_ethtool = mlxsw_sp2_mask_ethtool_5gbase_r, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_5GBASE_R_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | + MLXSW_SP_PORT_MASK_WIDTH_2X | + MLXSW_SP_PORT_MASK_WIDTH_4X, .speed = SPEED_5000, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_XFI_XAUI_1_10G, .mask_ethtool = mlxsw_sp2_mask_ethtool_xfi_xaui_1_10g, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_XFI_XAUI_1_10G_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | + MLXSW_SP_PORT_MASK_WIDTH_2X | + MLXSW_SP_PORT_MASK_WIDTH_4X, .speed = SPEED_10000, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_XLAUI_4_XLPPI_4_40G, .mask_ethtool = mlxsw_sp2_mask_ethtool_xlaui_4_xlppi_4_40g, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_XLAUI_4_XLPPI_4_40G_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_4X, .speed = SPEED_40000, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_25GAUI_1_25GBASE_CR_KR, .mask_ethtool = mlxsw_sp2_mask_ethtool_25gaui_1_25gbase_cr_kr, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_25GAUI_1_25GBASE_CR_KR_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X | + MLXSW_SP_PORT_MASK_WIDTH_2X | + MLXSW_SP_PORT_MASK_WIDTH_4X, .speed = SPEED_25000, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_2_LAUI_2_50GBASE_CR2_KR2, .mask_ethtool = mlxsw_sp2_mask_ethtool_50gaui_2_laui_2_50gbase_cr2_kr2, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_50GAUI_2_LAUI_2_50GBASE_CR2_KR2_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_2X | + MLXSW_SP_PORT_MASK_WIDTH_4X, .speed = SPEED_50000, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_50GAUI_1_LAUI_1_50GBASE_CR_KR, .mask_ethtool = mlxsw_sp2_mask_ethtool_50gaui_1_laui_1_50gbase_cr_kr, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_50GAUI_1_LAUI_1_50GBASE_CR_KR_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_1X, .speed = SPEED_50000, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_CAUI_4_100GBASE_CR4_KR4, .mask_ethtool = mlxsw_sp2_mask_ethtool_caui_4_100gbase_cr4_kr4, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_CAUI_4_100GBASE_CR4_KR4_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_4X, .speed = SPEED_100000, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_100GAUI_2_100GBASE_CR2_KR2, .mask_ethtool = mlxsw_sp2_mask_ethtool_100gaui_2_100gbase_cr2_kr2, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_100GAUI_2_100GBASE_CR2_KR2_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_2X, .speed = SPEED_100000, }, { .mask = MLXSW_REG_PTYS_EXT_ETH_SPEED_200GAUI_4_200GBASE_CR4_KR4, .mask_ethtool = mlxsw_sp2_mask_ethtool_200gaui_4_200gbase_cr4_kr4, .m_ethtool_len = MLXSW_SP2_MASK_ETHTOOL_200GAUI_4_200GBASE_CR4_KR4_LEN, + .mask_width = MLXSW_SP_PORT_MASK_WIDTH_4X, .speed = SPEED_200000, }, }; @@ -3022,12 +3064,14 @@ mlxsw_sp2_set_bit_ethtool(const struct mlxsw_sp2_port_link_mode *link_mode, static void mlxsw_sp2_from_ptys_link(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto, - unsigned long *mode) + u8 width, unsigned long *mode) { + u8 mask_width = mlxsw_sp_port_mask_width_get(width); int i; for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) { - if (ptys_eth_proto & mlxsw_sp2_port_link_mode[i].mask) + if ((ptys_eth_proto & mlxsw_sp2_port_link_mode[i].mask) && + (mask_width & mlxsw_sp2_port_link_mode[i].mask_width)) mlxsw_sp2_set_bit_ethtool(&mlxsw_sp2_port_link_mode[i], mode); } @@ -3078,27 +3122,32 @@ mlxsw_sp2_test_bit_ethtool(const struct mlxsw_sp2_port_link_mode *link_mode, } static u32 -mlxsw_sp2_to_ptys_advert_link(struct mlxsw_sp *mlxsw_sp, +mlxsw_sp2_to_ptys_advert_link(struct mlxsw_sp *mlxsw_sp, u8 width, const struct ethtool_link_ksettings *cmd) { + u8 mask_width = mlxsw_sp_port_mask_width_get(width); u32 ptys_proto = 0; int i; for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) { - if (mlxsw_sp2_test_bit_ethtool(&mlxsw_sp2_port_link_mode[i], + if ((mask_width & mlxsw_sp2_port_link_mode[i].mask_width) && + mlxsw_sp2_test_bit_ethtool(&mlxsw_sp2_port_link_mode[i], cmd->link_modes.advertising)) ptys_proto |= mlxsw_sp2_port_link_mode[i].mask; } return ptys_proto; } -static u32 mlxsw_sp2_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, u32 speed) +static u32 mlxsw_sp2_to_ptys_speed(struct mlxsw_sp *mlxsw_sp, + u8 width, u32 speed) { + u8 mask_width = mlxsw_sp_port_mask_width_get(width); u32 ptys_proto = 0; int i; for (i = 0; i < MLXSW_SP2_PORT_LINK_MODE_LEN; i++) { - if (speed == mlxsw_sp2_port_link_mode[i].speed) + if ((speed == mlxsw_sp2_port_link_mode[i].speed) && + (mask_width & mlxsw_sp2_port_link_mode[i].mask_width)) ptys_proto |= mlxsw_sp2_port_link_mode[i].mask; } return ptys_proto; @@ -3182,7 +3231,7 @@ mlxsw_sp2_port_type_speed_ops = { static void mlxsw_sp_port_get_link_supported(struct mlxsw_sp *mlxsw_sp, u32 eth_proto_cap, - struct ethtool_link_ksettings *cmd) + u8 width, struct ethtool_link_ksettings *cmd) { const struct mlxsw_sp_port_type_speed_ops *ops; @@ -3193,12 +3242,13 @@ mlxsw_sp_port_get_link_supported(struct mlxsw_sp *mlxsw_sp, u32 eth_proto_cap, ethtool_link_ksettings_add_link_mode(cmd, supported, Pause); ops->from_ptys_supported_port(mlxsw_sp, eth_proto_cap, cmd); - ops->from_ptys_link(mlxsw_sp, eth_proto_cap, cmd->link_modes.supported); + ops->from_ptys_link(mlxsw_sp, eth_proto_cap, width, + cmd->link_modes.supported); } static void mlxsw_sp_port_get_link_advertise(struct mlxsw_sp *mlxsw_sp, - u32 eth_proto_admin, bool autoneg, + u32 eth_proto_admin, bool autoneg, u8 width, struct ethtool_link_ksettings *cmd) { const struct mlxsw_sp_port_type_speed_ops *ops; @@ -3209,7 +3259,7 @@ mlxsw_sp_port_get_link_advertise(struct mlxsw_sp *mlxsw_sp, return; ethtool_link_ksettings_add_link_mode(cmd, advertising, Autoneg); - ops->from_ptys_link(mlxsw_sp, eth_proto_admin, + ops->from_ptys_link(mlxsw_sp, eth_proto_admin, width, cmd->link_modes.advertising); } @@ -3264,10 +3314,11 @@ static int mlxsw_sp_port_get_link_ksettings(struct net_device *dev, ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, ð_proto_cap, ð_proto_admin, ð_proto_oper); - mlxsw_sp_port_get_link_supported(mlxsw_sp, eth_proto_cap, cmd); + mlxsw_sp_port_get_link_supported(mlxsw_sp, eth_proto_cap, + mlxsw_sp_port->mapping.width, cmd); mlxsw_sp_port_get_link_advertise(mlxsw_sp, eth_proto_admin, autoneg, - cmd); + mlxsw_sp_port->mapping.width, cmd); cmd->base.autoneg = autoneg ? AUTONEG_ENABLE : AUTONEG_DISABLE; connector_type = mlxsw_reg_ptys_connector_type_get(ptys_pl); @@ -3300,13 +3351,11 @@ mlxsw_sp_port_set_link_ksettings(struct net_device *dev, ops->reg_ptys_eth_unpack(mlxsw_sp, ptys_pl, ð_proto_cap, NULL, NULL); autoneg = cmd->base.autoneg == AUTONEG_ENABLE; - if (!autoneg && cmd->base.speed == SPEED_56000) { - netdev_err(dev, "56G not supported with autoneg off\n"); - return -EINVAL; - } eth_proto_new = autoneg ? - ops->to_ptys_advert_link(mlxsw_sp, cmd) : - ops->to_ptys_speed(mlxsw_sp, cmd->base.speed); + ops->to_ptys_advert_link(mlxsw_sp, mlxsw_sp_port->mapping.width, + cmd) : + ops->to_ptys_speed(mlxsw_sp, mlxsw_sp_port->mapping.width, + cmd->base.speed); eth_proto_new = eth_proto_new & eth_proto_cap; if (!eth_proto_new) { @@ -3823,6 +3872,45 @@ static void mlxsw_sp_port_remove(struct mlxsw_sp *mlxsw_sp, u8 local_port) mlxsw_core_port_fini(mlxsw_sp->core, local_port); } +static int mlxsw_sp_cpu_port_create(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_port *mlxsw_sp_port; + int err; + + mlxsw_sp_port = kzalloc(sizeof(*mlxsw_sp_port), GFP_KERNEL); + if (!mlxsw_sp_port) + return -ENOMEM; + + mlxsw_sp_port->mlxsw_sp = mlxsw_sp; + mlxsw_sp_port->local_port = MLXSW_PORT_CPU_PORT; + + err = mlxsw_core_cpu_port_init(mlxsw_sp->core, + mlxsw_sp_port, + mlxsw_sp->base_mac, + sizeof(mlxsw_sp->base_mac)); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize core CPU port\n"); + goto err_core_cpu_port_init; + } + + mlxsw_sp->ports[MLXSW_PORT_CPU_PORT] = mlxsw_sp_port; + return 0; + +err_core_cpu_port_init: + kfree(mlxsw_sp_port); + return err; +} + +static void mlxsw_sp_cpu_port_remove(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_port *mlxsw_sp_port = + mlxsw_sp->ports[MLXSW_PORT_CPU_PORT]; + + mlxsw_core_cpu_port_fini(mlxsw_sp->core); + mlxsw_sp->ports[MLXSW_PORT_CPU_PORT] = NULL; + kfree(mlxsw_sp_port); +} + static bool mlxsw_sp_port_created(struct mlxsw_sp *mlxsw_sp, u8 local_port) { return mlxsw_sp->ports[local_port] != NULL; @@ -3835,6 +3923,7 @@ static void mlxsw_sp_ports_remove(struct mlxsw_sp *mlxsw_sp) for (i = 1; i < mlxsw_core_max_ports(mlxsw_sp->core); i++) if (mlxsw_sp_port_created(mlxsw_sp, i)) mlxsw_sp_port_remove(mlxsw_sp, i); + mlxsw_sp_cpu_port_remove(mlxsw_sp); kfree(mlxsw_sp->port_to_module); kfree(mlxsw_sp->ports); } @@ -3859,6 +3948,10 @@ static int mlxsw_sp_ports_create(struct mlxsw_sp *mlxsw_sp) goto err_port_to_module_alloc; } + err = mlxsw_sp_cpu_port_create(mlxsw_sp); + if (err) + goto err_cpu_port_create; + for (i = 1; i < max_ports; i++) { /* Mark as invalid */ mlxsw_sp->port_to_module[i] = -1; @@ -3882,6 +3975,8 @@ err_port_module_info_get: for (i--; i >= 1; i--) if (mlxsw_sp_port_created(mlxsw_sp, i)) mlxsw_sp_port_remove(mlxsw_sp, i); + mlxsw_sp_cpu_port_remove(mlxsw_sp); +err_cpu_port_create: kfree(mlxsw_sp->port_to_module); err_port_to_module_alloc: kfree(mlxsw_sp->ports); @@ -4609,6 +4704,9 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp1_ptp_ops = { .hwtstamp_set = mlxsw_sp1_ptp_hwtstamp_set, .shaper_work = mlxsw_sp1_ptp_shaper_work, .get_ts_info = mlxsw_sp1_ptp_get_ts_info, + .get_stats_count = mlxsw_sp1_get_stats_count, + .get_stats_strings = mlxsw_sp1_get_stats_strings, + .get_stats = mlxsw_sp1_get_stats, }; static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = { @@ -4622,6 +4720,9 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = { .hwtstamp_set = mlxsw_sp2_ptp_hwtstamp_set, .shaper_work = mlxsw_sp2_ptp_shaper_work, .get_ts_info = mlxsw_sp2_ptp_get_ts_info, + .get_stats_count = mlxsw_sp2_get_stats_count, + .get_stats_strings = mlxsw_sp2_get_stats_strings, + .get_stats = mlxsw_sp2_get_stats, }; static int mlxsw_sp_netdevice_event(struct notifier_block *unused, @@ -4664,6 +4765,12 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_traps_init; } + err = mlxsw_sp_devlink_traps_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize devlink traps\n"); + goto err_devlink_traps_init; + } + err = mlxsw_sp_buffers_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize buffers\n"); @@ -4797,6 +4904,8 @@ err_span_init: err_lag_init: mlxsw_sp_buffers_fini(mlxsw_sp); err_buffers_init: + mlxsw_sp_devlink_traps_fini(mlxsw_sp); +err_devlink_traps_init: mlxsw_sp_traps_fini(mlxsw_sp); err_traps_init: mlxsw_sp_fids_fini(mlxsw_sp); @@ -4869,6 +4978,7 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_span_fini(mlxsw_sp); mlxsw_sp_lag_fini(mlxsw_sp); mlxsw_sp_buffers_fini(mlxsw_sp); + mlxsw_sp_devlink_traps_fini(mlxsw_sp); mlxsw_sp_traps_fini(mlxsw_sp); mlxsw_sp_fids_fini(mlxsw_sp); mlxsw_sp_kvdl_fini(mlxsw_sp); @@ -5026,6 +5136,26 @@ static int mlxsw_sp1_resources_kvd_register(struct mlxsw_core *mlxsw_core) return 0; } +static int mlxsw_sp2_resources_kvd_register(struct mlxsw_core *mlxsw_core) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_core); + struct devlink_resource_size_params kvd_size_params; + u32 kvd_size; + + if (!MLXSW_CORE_RES_VALID(mlxsw_core, KVD_SIZE)) + return -EIO; + + kvd_size = MLXSW_CORE_RES_GET(mlxsw_core, KVD_SIZE); + devlink_resource_size_params_init(&kvd_size_params, kvd_size, kvd_size, + MLXSW_SP_KVD_GRANULARITY, + DEVLINK_RESOURCE_UNIT_ENTRY); + + return devlink_resource_register(devlink, MLXSW_SP_RESOURCE_NAME_KVD, + kvd_size, MLXSW_SP_RESOURCE_KVD, + DEVLINK_RESOURCE_ID_PARENT_TOP, + &kvd_size_params); +} + static int mlxsw_sp1_resources_register(struct mlxsw_core *mlxsw_core) { return mlxsw_sp1_resources_kvd_register(mlxsw_core); @@ -5033,7 +5163,7 @@ static int mlxsw_sp1_resources_register(struct mlxsw_core *mlxsw_core) static int mlxsw_sp2_resources_register(struct mlxsw_core *mlxsw_core) { - return 0; + return mlxsw_sp2_resources_kvd_register(mlxsw_core); } static int mlxsw_sp_kvd_sizes_get(struct mlxsw_core *mlxsw_core, @@ -5230,6 +5360,10 @@ static struct mlxsw_driver mlxsw_sp1_driver = { .sb_occ_port_pool_get = mlxsw_sp_sb_occ_port_pool_get, .sb_occ_tc_port_bind_get = mlxsw_sp_sb_occ_tc_port_bind_get, .flash_update = mlxsw_sp_flash_update, + .trap_init = mlxsw_sp_trap_init, + .trap_fini = mlxsw_sp_trap_fini, + .trap_action_set = mlxsw_sp_trap_action_set, + .trap_group_init = mlxsw_sp_trap_group_init, .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp1_resources_register, .kvd_sizes_get = mlxsw_sp_kvd_sizes_get, @@ -5260,6 +5394,43 @@ static struct mlxsw_driver mlxsw_sp2_driver = { .sb_occ_port_pool_get = mlxsw_sp_sb_occ_port_pool_get, .sb_occ_tc_port_bind_get = mlxsw_sp_sb_occ_tc_port_bind_get, .flash_update = mlxsw_sp_flash_update, + .trap_init = mlxsw_sp_trap_init, + .trap_fini = mlxsw_sp_trap_fini, + .trap_action_set = mlxsw_sp_trap_action_set, + .trap_group_init = mlxsw_sp_trap_group_init, + .txhdr_construct = mlxsw_sp_txhdr_construct, + .resources_register = mlxsw_sp2_resources_register, + .params_register = mlxsw_sp2_params_register, + .params_unregister = mlxsw_sp2_params_unregister, + .ptp_transmitted = mlxsw_sp_ptp_transmitted, + .txhdr_len = MLXSW_TXHDR_LEN, + .profile = &mlxsw_sp2_config_profile, + .res_query_enabled = true, +}; + +static struct mlxsw_driver mlxsw_sp3_driver = { + .kind = mlxsw_sp3_driver_name, + .priv_size = sizeof(struct mlxsw_sp), + .init = mlxsw_sp2_init, + .fini = mlxsw_sp_fini, + .basic_trap_groups_set = mlxsw_sp_basic_trap_groups_set, + .port_split = mlxsw_sp_port_split, + .port_unsplit = mlxsw_sp_port_unsplit, + .sb_pool_get = mlxsw_sp_sb_pool_get, + .sb_pool_set = mlxsw_sp_sb_pool_set, + .sb_port_pool_get = mlxsw_sp_sb_port_pool_get, + .sb_port_pool_set = mlxsw_sp_sb_port_pool_set, + .sb_tc_pool_bind_get = mlxsw_sp_sb_tc_pool_bind_get, + .sb_tc_pool_bind_set = mlxsw_sp_sb_tc_pool_bind_set, + .sb_occ_snapshot = mlxsw_sp_sb_occ_snapshot, + .sb_occ_max_clear = mlxsw_sp_sb_occ_max_clear, + .sb_occ_port_pool_get = mlxsw_sp_sb_occ_port_pool_get, + .sb_occ_tc_port_bind_get = mlxsw_sp_sb_occ_tc_port_bind_get, + .flash_update = mlxsw_sp_flash_update, + .trap_init = mlxsw_sp_trap_init, + .trap_fini = mlxsw_sp_trap_fini, + .trap_action_set = mlxsw_sp_trap_action_set, + .trap_group_init = mlxsw_sp_trap_group_init, .txhdr_construct = mlxsw_sp_txhdr_construct, .resources_register = mlxsw_sp2_resources_register, .params_register = mlxsw_sp2_params_register, @@ -6304,6 +6475,16 @@ static struct pci_driver mlxsw_sp2_pci_driver = { .id_table = mlxsw_sp2_pci_id_table, }; +static const struct pci_device_id mlxsw_sp3_pci_id_table[] = { + {PCI_VDEVICE(MELLANOX, PCI_DEVICE_ID_MELLANOX_SPECTRUM3), 0}, + {0, }, +}; + +static struct pci_driver mlxsw_sp3_pci_driver = { + .name = mlxsw_sp3_driver_name, + .id_table = mlxsw_sp3_pci_id_table, +}; + static int __init mlxsw_sp_module_init(void) { int err; @@ -6319,6 +6500,10 @@ static int __init mlxsw_sp_module_init(void) if (err) goto err_sp2_core_driver_register; + err = mlxsw_core_driver_register(&mlxsw_sp3_driver); + if (err) + goto err_sp3_core_driver_register; + err = mlxsw_pci_driver_register(&mlxsw_sp1_pci_driver); if (err) goto err_sp1_pci_driver_register; @@ -6327,11 +6512,19 @@ static int __init mlxsw_sp_module_init(void) if (err) goto err_sp2_pci_driver_register; + err = mlxsw_pci_driver_register(&mlxsw_sp3_pci_driver); + if (err) + goto err_sp3_pci_driver_register; + return 0; +err_sp3_pci_driver_register: + mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver); err_sp2_pci_driver_register: mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver); err_sp1_pci_driver_register: + mlxsw_core_driver_unregister(&mlxsw_sp3_driver); +err_sp3_core_driver_register: mlxsw_core_driver_unregister(&mlxsw_sp2_driver); err_sp2_core_driver_register: mlxsw_core_driver_unregister(&mlxsw_sp1_driver); @@ -6343,8 +6536,10 @@ err_sp1_core_driver_register: static void __exit mlxsw_sp_module_exit(void) { + mlxsw_pci_driver_unregister(&mlxsw_sp3_pci_driver); mlxsw_pci_driver_unregister(&mlxsw_sp2_pci_driver); mlxsw_pci_driver_unregister(&mlxsw_sp1_pci_driver); + mlxsw_core_driver_unregister(&mlxsw_sp3_driver); mlxsw_core_driver_unregister(&mlxsw_sp2_driver); mlxsw_core_driver_unregister(&mlxsw_sp1_driver); unregister_inet6addr_validator_notifier(&mlxsw_sp_inet6addr_valid_nb); @@ -6359,4 +6554,5 @@ MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>"); MODULE_DESCRIPTION("Mellanox Spectrum driver"); MODULE_DEVICE_TABLE(pci, mlxsw_sp1_pci_id_table); MODULE_DEVICE_TABLE(pci, mlxsw_sp2_pci_id_table); +MODULE_DEVICE_TABLE(pci, mlxsw_sp3_pci_id_table); MODULE_FIRMWARE(MLXSW_SP1_FW_FILENAME); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 6664119fb0c8..b2a0028b1694 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -225,6 +225,16 @@ struct mlxsw_sp_port_xstats { u64 tx_packets[IEEE_8021QAZ_MAX_TCS]; }; +struct mlxsw_sp_ptp_port_dir_stats { + u64 packets; + u64 timestamps; +}; + +struct mlxsw_sp_ptp_port_stats { + struct mlxsw_sp_ptp_port_dir_stats rx_gcd; + struct mlxsw_sp_ptp_port_dir_stats tx_gcd; +}; + struct mlxsw_sp_port { struct net_device *dev; struct mlxsw_sp_port_pcpu_stats __percpu *pcpu_stats; @@ -271,6 +281,7 @@ struct mlxsw_sp_port { struct hwtstamp_config hwtstamp_config; u16 ing_types; u16 egr_types; + struct mlxsw_sp_ptp_port_stats stats; } ptp; }; @@ -279,14 +290,14 @@ struct mlxsw_sp_port_type_speed_ops { u32 ptys_eth_proto, struct ethtool_link_ksettings *cmd); void (*from_ptys_link)(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto, - unsigned long *mode); + u8 width, unsigned long *mode); u32 (*from_ptys_speed)(struct mlxsw_sp *mlxsw_sp, u32 ptys_eth_proto); void (*from_ptys_speed_duplex)(struct mlxsw_sp *mlxsw_sp, bool carrier_ok, u32 ptys_eth_proto, struct ethtool_link_ksettings *cmd); - u32 (*to_ptys_advert_link)(struct mlxsw_sp *mlxsw_sp, + u32 (*to_ptys_advert_link)(struct mlxsw_sp *mlxsw_sp, u8 width, const struct ethtool_link_ksettings *cmd); - u32 (*to_ptys_speed)(struct mlxsw_sp *mlxsw_sp, u32 speed); + u32 (*to_ptys_speed)(struct mlxsw_sp *mlxsw_sp, u8 width, u32 speed); u32 (*to_ptys_upper_speed)(struct mlxsw_sp *mlxsw_sp, u32 upper_speed); int (*port_speed_base)(struct mlxsw_sp *mlxsw_sp, u8 local_port, u32 *base_speed); @@ -623,7 +634,8 @@ struct mlxsw_sp_acl_rule_info { unsigned int priority; struct mlxsw_afk_element_values values; struct mlxsw_afa_block *act_block; - u8 action_created:1; + u8 action_created:1, + egress_bind_blocker:1; unsigned int counter_index; }; @@ -642,6 +654,7 @@ struct mlxsw_sp_acl_block { struct mlxsw_sp *mlxsw_sp; unsigned int rule_count; unsigned int disable_count; + unsigned int egress_blocker_rule_count; struct net *net; }; @@ -657,7 +670,8 @@ void mlxsw_sp_acl_block_destroy(struct mlxsw_sp_acl_block *block); int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, struct mlxsw_sp_port *mlxsw_sp_port, - bool ingress); + bool ingress, + struct netlink_ext_ack *extack); int mlxsw_sp_acl_block_unbind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, struct mlxsw_sp_port *mlxsw_sp_port, @@ -955,4 +969,17 @@ void mlxsw_sp_nve_fini(struct mlxsw_sp *mlxsw_sp); int mlxsw_sp_nve_inc_parsing_depth_get(struct mlxsw_sp *mlxsw_sp); void mlxsw_sp_nve_inc_parsing_depth_put(struct mlxsw_sp *mlxsw_sp); +/* spectrum_trap.c */ +int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp); +void mlxsw_sp_devlink_traps_fini(struct mlxsw_sp *mlxsw_sp); +int mlxsw_sp_trap_init(struct mlxsw_core *mlxsw_core, + const struct devlink_trap *trap, void *trap_ctx); +void mlxsw_sp_trap_fini(struct mlxsw_core *mlxsw_core, + const struct devlink_trap *trap, void *trap_ctx); +int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core, + const struct devlink_trap *trap, + enum devlink_trap_action action); +int mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core, + const struct devlink_trap_group *group); + #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c index 84a87d059333..150b3a144b83 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl.c @@ -239,7 +239,8 @@ mlxsw_sp_acl_block_lookup(struct mlxsw_sp_acl_block *block, int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_acl_block *block, struct mlxsw_sp_port *mlxsw_sp_port, - bool ingress) + bool ingress, + struct netlink_ext_ack *extack) { struct mlxsw_sp_acl_block_binding *binding; int err; @@ -247,6 +248,11 @@ int mlxsw_sp_acl_block_bind(struct mlxsw_sp *mlxsw_sp, if (WARN_ON(mlxsw_sp_acl_block_lookup(block, mlxsw_sp_port, ingress))) return -EEXIST; + if (!ingress && block->egress_blocker_rule_count) { + NL_SET_ERR_MSG_MOD(extack, "Block cannot be bound to egress because it contains unsupported rules"); + return -EOPNOTSUPP; + } + binding = kzalloc(sizeof(*binding), GFP_KERNEL); if (!binding) return -ENOMEM; @@ -672,6 +678,7 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset; const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; + struct mlxsw_sp_acl_block *block = ruleset->ht_key.block; int err; err = ops->rule_add(mlxsw_sp, ruleset->priv, rule->priv, rule->rulei); @@ -689,14 +696,14 @@ int mlxsw_sp_acl_rule_add(struct mlxsw_sp *mlxsw_sp, * one, to be directly bound to device. The rest of the * rulesets are bound by "Goto action set". */ - err = mlxsw_sp_acl_ruleset_block_bind(mlxsw_sp, ruleset, - ruleset->ht_key.block); + err = mlxsw_sp_acl_ruleset_block_bind(mlxsw_sp, ruleset, block); if (err) goto err_ruleset_block_bind; } list_add_tail(&rule->list, &mlxsw_sp->acl->rules); - ruleset->ht_key.block->rule_count++; + block->rule_count++; + block->egress_blocker_rule_count += rule->rulei->egress_bind_blocker; return 0; err_ruleset_block_bind: @@ -712,7 +719,9 @@ void mlxsw_sp_acl_rule_del(struct mlxsw_sp *mlxsw_sp, { struct mlxsw_sp_acl_ruleset *ruleset = rule->ruleset; const struct mlxsw_sp_acl_profile_ops *ops = ruleset->ht_key.ops; + struct mlxsw_sp_acl_block *block = ruleset->ht_key.block; + block->egress_blocker_rule_count -= rule->rulei->egress_bind_blocker; ruleset->ht_key.block->rule_count--; list_del(&rule->list); if (!ruleset->ht_key.chain_index && diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c index 888ba4300bcc..b9eeae37a4dc 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_buffers.c @@ -250,6 +250,10 @@ static int mlxsw_sp_sb_pm_occ_clear(struct mlxsw_sp *mlxsw_sp, u8 local_port, &mlxsw_sp->sb_vals->pool_dess[pool_index]; char sbpm_pl[MLXSW_REG_SBPM_LEN]; + if (local_port == MLXSW_PORT_CPU_PORT && + des->dir == MLXSW_REG_SBXX_DIR_INGRESS) + return 0; + mlxsw_reg_sbpm_pack(sbpm_pl, local_port, des->pool, des->dir, true, 0, 0); return mlxsw_reg_trans_query(mlxsw_sp->core, MLXSW_REG(sbpm), sbpm_pl, @@ -273,6 +277,10 @@ static int mlxsw_sp_sb_pm_occ_query(struct mlxsw_sp *mlxsw_sp, u8 local_port, char sbpm_pl[MLXSW_REG_SBPM_LEN]; struct mlxsw_sp_sb_pm *pm; + if (local_port == MLXSW_PORT_CPU_PORT && + des->dir == MLXSW_REG_SBXX_DIR_INGRESS) + return 0; + pm = mlxsw_sp_sb_pm_get(mlxsw_sp, local_port, pool_index); mlxsw_reg_sbpm_pack(sbpm_pl, local_port, des->pool, des->dir, false, 0, 0); @@ -1085,6 +1093,11 @@ int mlxsw_sp_sb_port_pool_set(struct mlxsw_core_port *mlxsw_core_port, u32 max_buff; int err; + if (local_port == MLXSW_PORT_CPU_PORT) { + NL_SET_ERR_MSG_MOD(extack, "Changing CPU port's threshold is forbidden"); + return -EINVAL; + } + err = mlxsw_sp_sb_threshold_in(mlxsw_sp, pool_index, threshold, &max_buff, extack); if (err) @@ -1130,6 +1143,11 @@ int mlxsw_sp_sb_tc_pool_bind_set(struct mlxsw_core_port *mlxsw_core_port, u32 max_buff; int err; + if (local_port == MLXSW_PORT_CPU_PORT) { + NL_SET_ERR_MSG_MOD(extack, "Changing CPU port's binding is forbidden"); + return -EINVAL; + } + if (dir != mlxsw_sp->sb_vals->pool_dess[pool_index].dir) { NL_SET_ERR_MSG_MOD(extack, "Binding egress TC to ingress pool and vice versa is forbidden"); return -EINVAL; @@ -1187,6 +1205,11 @@ static void mlxsw_sp_sb_sr_occ_query_cb(struct mlxsw_core *mlxsw_core, local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) { if (!mlxsw_sp->ports[local_port]) continue; + if (local_port == MLXSW_PORT_CPU_PORT) { + /* Ingress quotas are not supported for the CPU port */ + masked_count++; + continue; + } for (i = 0; i < MLXSW_SP_SB_ING_TC_COUNT; i++) { cm = mlxsw_sp_sb_cm_get(mlxsw_sp, local_port, i, MLXSW_REG_SBXX_DIR_INGRESS); @@ -1222,7 +1245,7 @@ int mlxsw_sp_sb_occ_snapshot(struct mlxsw_core *mlxsw_core, char *sbsr_pl; u8 masked_count; u8 local_port_1; - u8 local_port = 0; + u8 local_port; int i; int err; int err2; @@ -1231,8 +1254,8 @@ int mlxsw_sp_sb_occ_snapshot(struct mlxsw_core *mlxsw_core, if (!sbsr_pl) return -ENOMEM; + local_port = MLXSW_PORT_CPU_PORT; next_batch: - local_port++; local_port_1 = local_port; masked_count = 0; mlxsw_reg_sbsr_pack(sbsr_pl, false); @@ -1243,7 +1266,11 @@ next_batch: for (; local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) { if (!mlxsw_sp->ports[local_port]) continue; - mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1); + if (local_port != MLXSW_PORT_CPU_PORT) { + /* Ingress quotas are not supported for the CPU port */ + mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, + local_port, 1); + } mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1); for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) { err = mlxsw_sp_sb_pm_occ_query(mlxsw_sp, local_port, i, @@ -1264,8 +1291,10 @@ do_query: cb_priv); if (err) goto out; - if (local_port < mlxsw_core_max_ports(mlxsw_core)) + if (local_port < mlxsw_core_max_ports(mlxsw_core)) { + local_port++; goto next_batch; + } out: err2 = mlxsw_reg_trans_bulk_wait(&bulk_list); @@ -1282,7 +1311,7 @@ int mlxsw_sp_sb_occ_max_clear(struct mlxsw_core *mlxsw_core, LIST_HEAD(bulk_list); char *sbsr_pl; unsigned int masked_count; - u8 local_port = 0; + u8 local_port; int i; int err; int err2; @@ -1291,8 +1320,8 @@ int mlxsw_sp_sb_occ_max_clear(struct mlxsw_core *mlxsw_core, if (!sbsr_pl) return -ENOMEM; + local_port = MLXSW_PORT_CPU_PORT; next_batch: - local_port++; masked_count = 0; mlxsw_reg_sbsr_pack(sbsr_pl, true); for (i = 0; i < MLXSW_SP_SB_ING_TC_COUNT; i++) @@ -1302,7 +1331,11 @@ next_batch: for (; local_port < mlxsw_core_max_ports(mlxsw_core); local_port++) { if (!mlxsw_sp->ports[local_port]) continue; - mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, local_port, 1); + if (local_port != MLXSW_PORT_CPU_PORT) { + /* Ingress quotas are not supported for the CPU port */ + mlxsw_reg_sbsr_ingress_port_mask_set(sbsr_pl, + local_port, 1); + } mlxsw_reg_sbsr_egress_port_mask_set(sbsr_pl, local_port, 1); for (i = 0; i < mlxsw_sp->sb_vals->pool_count; i++) { err = mlxsw_sp_sb_pm_occ_clear(mlxsw_sp, local_port, i, @@ -1319,8 +1352,10 @@ do_query: &bulk_list, NULL, 0); if (err) goto out; - if (local_port < mlxsw_core_max_ports(mlxsw_core)) + if (local_port < mlxsw_core_max_ports(mlxsw_core)) { + local_port++; goto next_batch; + } out: err2 = mlxsw_reg_trans_bulk_wait(&bulk_list); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c index 202e9a246019..0ad1a24abfc6 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_flower.c @@ -78,6 +78,16 @@ static int mlxsw_sp_flower_parse_actions(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fid *fid; u16 fid_index; + if (mlxsw_sp_acl_block_is_egress_bound(block)) { + NL_SET_ERR_MSG_MOD(extack, "Redirect action is not supported on egress"); + return -EOPNOTSUPP; + } + + /* Forbid block with this rulei to be bound + * to egress in future. + */ + rulei->egress_bind_blocker = 1; + fid = mlxsw_sp_acl_dummy_fid(mlxsw_sp); fid_index = mlxsw_sp_fid_index(fid); err = mlxsw_sp_acl_rulei_act_fid_set(mlxsw_sp, rulei, @@ -257,6 +267,12 @@ static int mlxsw_sp_flower_parse_tcp(struct mlxsw_sp *mlxsw_sp, flow_rule_match_tcp(rule, &match); + if (match.mask->flags & htons(0x0E00)) { + NL_SET_ERR_MSG_MOD(f->common.extack, "TCP flags match not supported on reserved bits"); + dev_err(mlxsw_sp->bus_info->dev, "TCP flags match not supported on reserved bits\n"); + return -EINVAL; + } + mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_TCP_FLAGS, ntohs(match.key->flags), ntohs(match.mask->flags)); @@ -390,6 +406,12 @@ static int mlxsw_sp_flower_parse(struct mlxsw_sp *mlxsw_sp, NL_SET_ERR_MSG_MOD(f->common.extack, "vlan_id key is not supported on egress"); return -EOPNOTSUPP; } + + /* Forbid block with this rulei to be bound + * to egress in future. + */ + rulei->egress_bind_blocker = 1; + if (match.mask->vlan_id != 0) mlxsw_sp_acl_rulei_keymask_u32(rulei, MLXSW_AFK_ELEMENT_VID, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c index 38bb1cfe4e8c..ec2ff3d7f41c 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c @@ -630,6 +630,8 @@ static void mlxsw_sp1_ptp_ht_gc_collect(struct mlxsw_sp_ptp_state *ptp_state, struct mlxsw_sp1_ptp_unmatched *unmatched) { + struct mlxsw_sp_ptp_port_dir_stats *stats; + struct mlxsw_sp_port *mlxsw_sp_port; int err; /* If an unmatched entry has an SKB, it has to be handed over to the @@ -650,6 +652,17 @@ mlxsw_sp1_ptp_ht_gc_collect(struct mlxsw_sp_ptp_state *ptp_state, /* The packet was matched with timestamp during the walk. */ goto out; + mlxsw_sp_port = ptp_state->mlxsw_sp->ports[unmatched->key.local_port]; + if (mlxsw_sp_port) { + stats = unmatched->key.ingress ? + &mlxsw_sp_port->ptp.stats.rx_gcd : + &mlxsw_sp_port->ptp.stats.tx_gcd; + if (unmatched->skb) + stats->packets++; + else + stats->timestamps++; + } + /* mlxsw_sp1_ptp_unmatched_finish() invokes netif_receive_skb(). While * the comment at that function states that it can only be called in * soft IRQ context, this pattern of local_bh_disable() + @@ -1098,3 +1111,57 @@ int mlxsw_sp1_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp, return 0; } + +struct mlxsw_sp_ptp_port_stat { + char str[ETH_GSTRING_LEN]; + ptrdiff_t offset; +}; + +#define MLXSW_SP_PTP_PORT_STAT(NAME, FIELD) \ + { \ + .str = NAME, \ + .offset = offsetof(struct mlxsw_sp_ptp_port_stats, \ + FIELD), \ + } + +static const struct mlxsw_sp_ptp_port_stat mlxsw_sp_ptp_port_stats[] = { + MLXSW_SP_PTP_PORT_STAT("ptp_rx_gcd_packets", rx_gcd.packets), + MLXSW_SP_PTP_PORT_STAT("ptp_rx_gcd_timestamps", rx_gcd.timestamps), + MLXSW_SP_PTP_PORT_STAT("ptp_tx_gcd_packets", tx_gcd.packets), + MLXSW_SP_PTP_PORT_STAT("ptp_tx_gcd_timestamps", tx_gcd.timestamps), +}; + +#undef MLXSW_SP_PTP_PORT_STAT + +#define MLXSW_SP_PTP_PORT_STATS_LEN \ + ARRAY_SIZE(mlxsw_sp_ptp_port_stats) + +int mlxsw_sp1_get_stats_count(void) +{ + return MLXSW_SP_PTP_PORT_STATS_LEN; +} + +void mlxsw_sp1_get_stats_strings(u8 **p) +{ + int i; + + for (i = 0; i < MLXSW_SP_PTP_PORT_STATS_LEN; i++) { + memcpy(*p, mlxsw_sp_ptp_port_stats[i].str, + ETH_GSTRING_LEN); + *p += ETH_GSTRING_LEN; + } +} + +void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port, + u64 *data, int data_index) +{ + void *stats = &mlxsw_sp_port->ptp.stats; + ptrdiff_t offset; + int i; + + data += data_index; + for (i = 0; i < MLXSW_SP_PTP_PORT_STATS_LEN; i++) { + offset = mlxsw_sp_ptp_port_stats[i].offset; + *data++ = *(u64 *)(stats + offset); + } +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h index 72e55f6926b9..8c386571afce 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.h @@ -59,6 +59,11 @@ void mlxsw_sp1_ptp_shaper_work(struct work_struct *work); int mlxsw_sp1_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp, struct ethtool_ts_info *info); +int mlxsw_sp1_get_stats_count(void); +void mlxsw_sp1_get_stats_strings(u8 **p); +void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port, + u64 *data, int data_index); + #else static inline struct mlxsw_sp_ptp_clock * @@ -125,6 +130,19 @@ static inline int mlxsw_sp1_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_ptp_get_ts_info_noptp(info); } +static inline int mlxsw_sp1_get_stats_count(void) +{ + return 0; +} + +static inline void mlxsw_sp1_get_stats_strings(u8 **p) +{ +} + +static inline void mlxsw_sp1_get_stats(struct mlxsw_sp_port *mlxsw_sp_port, + u64 *data, int data_index) +{ +} #endif static inline struct mlxsw_sp_ptp_clock * @@ -183,4 +201,18 @@ static inline int mlxsw_sp2_ptp_get_ts_info(struct mlxsw_sp *mlxsw_sp, return mlxsw_sp_ptp_get_ts_info_noptp(info); } +static inline int mlxsw_sp2_get_stats_count(void) +{ + return 0; +} + +static inline void mlxsw_sp2_get_stats_strings(u8 **p) +{ +} + +static inline void mlxsw_sp2_get_stats(struct mlxsw_sp_port *mlxsw_sp_port, + u64 *data, int data_index) +{ +} + #endif diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index e618be7ce6c6..a330b369e899 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -2943,7 +2943,7 @@ static u32 mlxsw_sp_nexthop_group_hash_obj(const void *data, u32 len, u32 seed) val = nh_grp->count; for (i = 0; i < nh_grp->count; i++) { nh = &nh_grp->nexthops[i]; - val ^= nh->ifindex; + val ^= jhash(&nh->ifindex, sizeof(nh->ifindex), seed); } return jhash(&val, sizeof(val), seed); default: @@ -2961,7 +2961,7 @@ mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed) list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { dev = mlxsw_sp_rt6->rt->fib6_nh->fib_nh_dev; - val ^= dev->ifindex; + val ^= jhash(&dev->ifindex, sizeof(dev->ifindex), seed); } return jhash(&val, sizeof(val), seed); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c new file mode 100644 index 000000000000..899450b28621 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_trap.c @@ -0,0 +1,267 @@ +// SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 +/* Copyright (c) 2019 Mellanox Technologies. All rights reserved */ + +#include <linux/kernel.h> +#include <net/devlink.h> +#include <uapi/linux/devlink.h> + +#include "core.h" +#include "reg.h" +#include "spectrum.h" + +#define MLXSW_SP_TRAP_METADATA DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT + +static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port, + void *priv); + +#define MLXSW_SP_TRAP_DROP(_id, _group_id) \ + DEVLINK_TRAP_GENERIC(DROP, DROP, _id, \ + DEVLINK_TRAP_GROUP_GENERIC(_group_id), \ + MLXSW_SP_TRAP_METADATA) + +#define MLXSW_SP_RXL_DISCARD(_id, _group_id) \ + MLXSW_RXL(mlxsw_sp_rx_drop_listener, DISCARD_##_id, SET_FW_DEFAULT, \ + false, SP_##_group_id, DISCARD) + +static struct devlink_trap mlxsw_sp_traps_arr[] = { + MLXSW_SP_TRAP_DROP(SMAC_MC, L2_DROPS), + MLXSW_SP_TRAP_DROP(VLAN_TAG_MISMATCH, L2_DROPS), + MLXSW_SP_TRAP_DROP(INGRESS_VLAN_FILTER, L2_DROPS), + MLXSW_SP_TRAP_DROP(INGRESS_STP_FILTER, L2_DROPS), + MLXSW_SP_TRAP_DROP(EMPTY_TX_LIST, L2_DROPS), + MLXSW_SP_TRAP_DROP(PORT_LOOPBACK_FILTER, L2_DROPS), +}; + +static struct mlxsw_listener mlxsw_sp_listeners_arr[] = { + MLXSW_SP_RXL_DISCARD(ING_PACKET_SMAC_MC, L2_DISCARDS), + MLXSW_SP_RXL_DISCARD(ING_SWITCH_VTAG_ALLOW, L2_DISCARDS), + MLXSW_SP_RXL_DISCARD(ING_SWITCH_VLAN, L2_DISCARDS), + MLXSW_SP_RXL_DISCARD(ING_SWITCH_STP, L2_DISCARDS), + MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_UC, L2_DISCARDS), + MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_MC_NULL, L2_DISCARDS), + MLXSW_SP_RXL_DISCARD(LOOKUP_SWITCH_LB, L2_DISCARDS), +}; + +/* Mapping between hardware trap and devlink trap. Multiple hardware traps can + * be mapped to the same devlink trap. Order is according to + * 'mlxsw_sp_listeners_arr'. + */ +static u16 mlxsw_sp_listener_devlink_map[] = { + DEVLINK_TRAP_GENERIC_ID_SMAC_MC, + DEVLINK_TRAP_GENERIC_ID_VLAN_TAG_MISMATCH, + DEVLINK_TRAP_GENERIC_ID_INGRESS_VLAN_FILTER, + DEVLINK_TRAP_GENERIC_ID_INGRESS_STP_FILTER, + DEVLINK_TRAP_GENERIC_ID_EMPTY_TX_LIST, + DEVLINK_TRAP_GENERIC_ID_EMPTY_TX_LIST, + DEVLINK_TRAP_GENERIC_ID_PORT_LOOPBACK_FILTER, +}; + +static int mlxsw_sp_rx_listener(struct mlxsw_sp *mlxsw_sp, struct sk_buff *skb, + u8 local_port, + struct mlxsw_sp_port *mlxsw_sp_port) +{ + struct mlxsw_sp_port_pcpu_stats *pcpu_stats; + + if (unlikely(!mlxsw_sp_port)) { + dev_warn_ratelimited(mlxsw_sp->bus_info->dev, "Port %d: skb received for non-existent port\n", + local_port); + kfree_skb(skb); + return -EINVAL; + } + + skb->dev = mlxsw_sp_port->dev; + + pcpu_stats = this_cpu_ptr(mlxsw_sp_port->pcpu_stats); + u64_stats_update_begin(&pcpu_stats->syncp); + pcpu_stats->rx_packets++; + pcpu_stats->rx_bytes += skb->len; + u64_stats_update_end(&pcpu_stats->syncp); + + skb->protocol = eth_type_trans(skb, skb->dev); + + return 0; +} + +static void mlxsw_sp_rx_drop_listener(struct sk_buff *skb, u8 local_port, + void *trap_ctx) +{ + struct devlink_port *in_devlink_port; + struct mlxsw_sp_port *mlxsw_sp_port; + struct mlxsw_sp *mlxsw_sp; + struct devlink *devlink; + + mlxsw_sp = devlink_trap_ctx_priv(trap_ctx); + mlxsw_sp_port = mlxsw_sp->ports[local_port]; + + if (mlxsw_sp_rx_listener(mlxsw_sp, skb, local_port, mlxsw_sp_port)) + return; + + devlink = priv_to_devlink(mlxsw_sp->core); + in_devlink_port = mlxsw_core_port_devlink_port_get(mlxsw_sp->core, + local_port); + devlink_trap_report(devlink, skb, trap_ctx, in_devlink_port); + consume_skb(skb); +} + +int mlxsw_sp_devlink_traps_init(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + if (WARN_ON(ARRAY_SIZE(mlxsw_sp_listener_devlink_map) != + ARRAY_SIZE(mlxsw_sp_listeners_arr))) + return -EINVAL; + + return devlink_traps_register(devlink, mlxsw_sp_traps_arr, + ARRAY_SIZE(mlxsw_sp_traps_arr), + mlxsw_sp); +} + +void mlxsw_sp_devlink_traps_fini(struct mlxsw_sp *mlxsw_sp) +{ + struct devlink *devlink = priv_to_devlink(mlxsw_sp->core); + + devlink_traps_unregister(devlink, mlxsw_sp_traps_arr, + ARRAY_SIZE(mlxsw_sp_traps_arr)); +} + +int mlxsw_sp_trap_init(struct mlxsw_core *mlxsw_core, + const struct devlink_trap *trap, void *trap_ctx) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) { + struct mlxsw_listener *listener; + int err; + + if (mlxsw_sp_listener_devlink_map[i] != trap->id) + continue; + listener = &mlxsw_sp_listeners_arr[i]; + + err = mlxsw_core_trap_register(mlxsw_core, listener, trap_ctx); + if (err) + return err; + } + + return 0; +} + +void mlxsw_sp_trap_fini(struct mlxsw_core *mlxsw_core, + const struct devlink_trap *trap, void *trap_ctx) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) { + struct mlxsw_listener *listener; + + if (mlxsw_sp_listener_devlink_map[i] != trap->id) + continue; + listener = &mlxsw_sp_listeners_arr[i]; + + mlxsw_core_trap_unregister(mlxsw_core, listener, trap_ctx); + } +} + +int mlxsw_sp_trap_action_set(struct mlxsw_core *mlxsw_core, + const struct devlink_trap *trap, + enum devlink_trap_action action) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mlxsw_sp_listener_devlink_map); i++) { + enum mlxsw_reg_hpkt_action hw_action; + struct mlxsw_listener *listener; + int err; + + if (mlxsw_sp_listener_devlink_map[i] != trap->id) + continue; + listener = &mlxsw_sp_listeners_arr[i]; + + switch (action) { + case DEVLINK_TRAP_ACTION_DROP: + hw_action = MLXSW_REG_HPKT_ACTION_SET_FW_DEFAULT; + break; + case DEVLINK_TRAP_ACTION_TRAP: + hw_action = MLXSW_REG_HPKT_ACTION_TRAP_EXCEPTION_TO_CPU; + break; + default: + return -EINVAL; + } + + err = mlxsw_core_trap_action_set(mlxsw_core, listener, + hw_action); + if (err) + return err; + } + + return 0; +} + +#define MLXSW_SP_DISCARD_POLICER_ID (MLXSW_REG_HTGT_TRAP_GROUP_MAX + 1) + +static int +mlxsw_sp_trap_group_policer_init(struct mlxsw_sp *mlxsw_sp, + const struct devlink_trap_group *group) +{ + enum mlxsw_reg_qpcr_ir_units ir_units; + char qpcr_pl[MLXSW_REG_QPCR_LEN]; + u16 policer_id; + u8 burst_size; + bool is_bytes; + u32 rate; + + switch (group->id) { + case DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS: + policer_id = MLXSW_SP_DISCARD_POLICER_ID; + ir_units = MLXSW_REG_QPCR_IR_UNITS_M; + is_bytes = false; + rate = 10 * 1024; /* 10Kpps */ + burst_size = 7; + break; + default: + return -EINVAL; + } + + mlxsw_reg_qpcr_pack(qpcr_pl, policer_id, ir_units, is_bytes, rate, + burst_size); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(qpcr), qpcr_pl); +} + +static int +__mlxsw_sp_trap_group_init(struct mlxsw_sp *mlxsw_sp, + const struct devlink_trap_group *group) +{ + char htgt_pl[MLXSW_REG_HTGT_LEN]; + u8 priority, tc, group_id; + u16 policer_id; + + switch (group->id) { + case DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS: + group_id = MLXSW_REG_HTGT_TRAP_GROUP_SP_L2_DISCARDS; + policer_id = MLXSW_SP_DISCARD_POLICER_ID; + priority = 0; + tc = 1; + break; + default: + return -EINVAL; + } + + mlxsw_reg_htgt_pack(htgt_pl, group_id, policer_id, priority, tc); + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(htgt), htgt_pl); +} + +int mlxsw_sp_trap_group_init(struct mlxsw_core *mlxsw_core, + const struct devlink_trap_group *group) +{ + struct mlxsw_sp *mlxsw_sp = mlxsw_core_driver_priv(mlxsw_core); + int err; + + err = mlxsw_sp_trap_group_policer_init(mlxsw_sp, group); + if (err) + return err; + + err = __mlxsw_sp_trap_group_init(mlxsw_sp, group); + if (err) + return err; + + return 0; +} diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index bdab96f5bc70..1c14c051ee52 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -637,12 +637,6 @@ static const struct mlxsw_sx_port_link_mode mlxsw_sx_port_link_mode[] = { .speed = 50000, }, { - .mask = MLXSW_REG_PTYS_ETH_SPEED_56GBASE_R4, - .supported = SUPPORTED_56000baseKR4_Full, - .advertised = ADVERTISED_56000baseKR4_Full, - .speed = 56000, - }, - { .mask = MLXSW_REG_PTYS_ETH_SPEED_100GBASE_CR4 | MLXSW_REG_PTYS_ETH_SPEED_100GBASE_SR4 | MLXSW_REG_PTYS_ETH_SPEED_100GBASE_KR4 | diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 19202bdb5105..7618f084cae9 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -66,6 +66,13 @@ enum { MLXSW_TRAP_ID_NVE_ENCAP_ARP = 0xBD, MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6, MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7, + MLXSW_TRAP_ID_DISCARD_ING_PACKET_SMAC_MC = 0x140, + MLXSW_TRAP_ID_DISCARD_ING_SWITCH_VTAG_ALLOW = 0x148, + MLXSW_TRAP_ID_DISCARD_ING_SWITCH_VLAN = 0x149, + MLXSW_TRAP_ID_DISCARD_ING_SWITCH_STP = 0x14A, + MLXSW_TRAP_ID_DISCARD_LOOKUP_SWITCH_UC = 0x150, + MLXSW_TRAP_ID_DISCARD_LOOKUP_SWITCH_MC_NULL = 0x151, + MLXSW_TRAP_ID_DISCARD_LOOKUP_SWITCH_LB = 0x152, MLXSW_TRAP_ID_ACL0 = 0x1C0, /* Multicast trap used for routes with trap action */ MLXSW_TRAP_ID_ACL1 = 0x1C1, diff --git a/drivers/net/ethernet/micrel/ks8842.c b/drivers/net/ethernet/micrel/ks8842.c index ccd06702cc56..da329ca115cc 100644 --- a/drivers/net/ethernet/micrel/ks8842.c +++ b/drivers/net/ethernet/micrel/ks8842.c @@ -580,9 +580,7 @@ out: dma_unmap_single(adapter->dev, sg_dma_address(sg), DMA_BUFFER_SIZE, DMA_FROM_DEVICE); sg_dma_address(sg) = 0; - if (ctl->skb) - dev_kfree_skb(ctl->skb); - + dev_kfree_skb(ctl->skb); ctl->skb = NULL; printk(KERN_ERR DRV_NAME": Failed to start RX DMA: %d\n", err); diff --git a/drivers/net/ethernet/micrel/ks8851_mll.c b/drivers/net/ethernet/micrel/ks8851_mll.c index e52b015e31a9..a41a90c589db 100644 --- a/drivers/net/ethernet/micrel/ks8851_mll.c +++ b/drivers/net/ethernet/micrel/ks8851_mll.c @@ -1225,7 +1225,6 @@ MODULE_DEVICE_TABLE(of, ks8851_ml_dt_ids); static int ks8851_probe(struct platform_device *pdev) { int err; - struct resource *io_d, *io_c; struct net_device *netdev; struct ks_net *ks; u16 id, data; @@ -1240,15 +1239,13 @@ static int ks8851_probe(struct platform_device *pdev) ks = netdev_priv(netdev); ks->netdev = netdev; - io_d = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ks->hw_addr = devm_ioremap_resource(&pdev->dev, io_d); + ks->hw_addr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ks->hw_addr)) { err = PTR_ERR(ks->hw_addr); goto err_free; } - io_c = platform_get_resource(pdev, IORESOURCE_MEM, 1); - ks->hw_addr_cmd = devm_ioremap_resource(&pdev->dev, io_c); + ks->hw_addr_cmd = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(ks->hw_addr_cmd)) { err = PTR_ERR(ks->hw_addr_cmd); goto err_free; diff --git a/drivers/net/ethernet/micrel/ksz884x.c b/drivers/net/ethernet/micrel/ksz884x.c index 3103446f018c..e102e1560ac7 100644 --- a/drivers/net/ethernet/micrel/ksz884x.c +++ b/drivers/net/ethernet/micrel/ksz884x.c @@ -2166,7 +2166,7 @@ static void sw_get_broad_storm(struct ksz_hw *hw, u8 *percent) num = (data & BROADCAST_STORM_RATE_HI); num <<= 8; num |= (data & BROADCAST_STORM_RATE_LO) >> 8; - num = (num * 100 + BROADCAST_STORM_VALUE / 2) / BROADCAST_STORM_VALUE; + num = DIV_ROUND_CLOSEST(num * 100, BROADCAST_STORM_VALUE); *percent = (u8) num; } diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index 13e6bf13ac4d..a43140f7b5eb 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -1434,7 +1434,7 @@ static void lan743x_tx_frame_add_lso(struct lan743x_tx *tx, } static int lan743x_tx_frame_add_fragment(struct lan743x_tx *tx, - const struct skb_frag_struct *fragment, + const skb_frag_t *fragment, unsigned int frame_length) { /* called only from within lan743x_tx_xmit_frame @@ -1607,9 +1607,8 @@ static netdev_tx_t lan743x_tx_xmit_frame(struct lan743x_tx *tx, goto finish; for (j = 0; j < nr_frags; j++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag = &(skb_shinfo(skb)->frags[j]); - frag = &(skb_shinfo(skb)->frags[j]); if (lan743x_tx_frame_add_fragment(tx, frag, frame_length)) { /* upon error no need to call * lan743x_tx_frame_end @@ -2173,9 +2172,8 @@ static int lan743x_rx_napi_poll(struct napi_struct *napi, int weight) } count = 0; while (count < weight) { - int rx_process_result = -1; + int rx_process_result = lan743x_rx_process_packet(rx); - rx_process_result = lan743x_rx_process_packet(rx); if (rx_process_result == RX_PROCESS_RESULT_PACKET_RECEIVED) { count++; } else if (rx_process_result == diff --git a/drivers/net/ethernet/microchip/lan743x_ptp.c b/drivers/net/ethernet/microchip/lan743x_ptp.c index b2109eca81fd..57b26c2acf87 100644 --- a/drivers/net/ethernet/microchip/lan743x_ptp.c +++ b/drivers/net/ethernet/microchip/lan743x_ptp.c @@ -963,8 +963,7 @@ void lan743x_ptp_close(struct lan743x_adapter *adapter) index++) { struct sk_buff *skb = ptp->tx_ts_skb_queue[index]; - if (skb) - dev_kfree_skb(skb); + dev_kfree_skb(skb); ptp->tx_ts_skb_queue[index] = NULL; ptp->tx_ts_seconds_queue[index] = 0; ptp->tx_ts_nseconds_queue[index] = 0; diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c index 6932e615d4b0..4d1bce4389c7 100644 --- a/drivers/net/ethernet/mscc/ocelot.c +++ b/drivers/net/ethernet/mscc/ocelot.c @@ -14,6 +14,7 @@ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/phy.h> +#include <linux/ptp_clock_kernel.h> #include <linux/skbuff.h> #include <linux/iopoll.h> #include <net/arp.h> @@ -538,7 +539,7 @@ static int ocelot_port_stop(struct net_device *dev) */ static int ocelot_gen_ifh(u32 *ifh, struct frame_info *info) { - ifh[0] = IFH_INJ_BYPASS; + ifh[0] = IFH_INJ_BYPASS | ((0x1ff & info->rew_op) << 21); ifh[1] = (0xf00 & info->port) >> 8; ifh[2] = (0xff & info->port) << 24; ifh[3] = (info->tag_type << 16) | info->vid; @@ -548,6 +549,7 @@ static int ocelot_gen_ifh(u32 *ifh, struct frame_info *info) static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) { + struct skb_shared_info *shinfo = skb_shinfo(skb); struct ocelot_port *port = netdev_priv(dev); struct ocelot *ocelot = port->ocelot; u32 val, ifh[IFH_LEN]; @@ -566,6 +568,14 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) info.port = BIT(port->chip_port); info.tag_type = IFH_TAG_TYPE_C; info.vid = skb_vlan_tag_get(skb); + + /* Check if timestamping is needed */ + if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP) { + info.rew_op = port->ptp_cmd; + if (port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) + info.rew_op |= (port->ts_id % 4) << 3; + } + ocelot_gen_ifh(ifh, &info); for (i = 0; i < IFH_LEN; i++) @@ -596,11 +606,58 @@ static int ocelot_port_xmit(struct sk_buff *skb, struct net_device *dev) dev->stats.tx_packets++; dev->stats.tx_bytes += skb->len; - dev_kfree_skb_any(skb); + if (ocelot->ptp && shinfo->tx_flags & SKBTX_HW_TSTAMP && + port->ptp_cmd == IFH_REW_OP_TWO_STEP_PTP) { + struct ocelot_skb *oskb = + kzalloc(sizeof(struct ocelot_skb), GFP_ATOMIC); + + if (unlikely(!oskb)) + goto out; + + skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; + + oskb->skb = skb; + oskb->id = port->ts_id % 4; + port->ts_id++; + + list_add_tail(&oskb->head, &port->skbs); + + return NETDEV_TX_OK; + } + +out: + dev_kfree_skb_any(skb); return NETDEV_TX_OK; } +void ocelot_get_hwtimestamp(struct ocelot *ocelot, struct timespec64 *ts) +{ + unsigned long flags; + u32 val; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + /* Read current PTP time to get seconds */ + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_SAVE); + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + ts->tv_sec = ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN); + + /* Read packet HW timestamp from FIFO */ + val = ocelot_read(ocelot, SYS_PTP_TXSTAMP); + ts->tv_nsec = SYS_PTP_TXSTAMP_PTP_TXSTAMP(val); + + /* Sec has incremented since the ts was registered */ + if ((ts->tv_sec & 0x1) != !!(val & SYS_PTP_TXSTAMP_PTP_TXSTAMP_SEC)) + ts->tv_sec--; + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); +} +EXPORT_SYMBOL(ocelot_get_hwtimestamp); + static int ocelot_mc_unsync(struct net_device *dev, const unsigned char *addr) { struct ocelot_port *port = netdev_priv(dev); @@ -917,6 +974,97 @@ static int ocelot_get_port_parent_id(struct net_device *dev, return 0; } +static int ocelot_hwstamp_get(struct ocelot_port *port, struct ifreq *ifr) +{ + struct ocelot *ocelot = port->ocelot; + + return copy_to_user(ifr->ifr_data, &ocelot->hwtstamp_config, + sizeof(ocelot->hwtstamp_config)) ? -EFAULT : 0; +} + +static int ocelot_hwstamp_set(struct ocelot_port *port, struct ifreq *ifr) +{ + struct ocelot *ocelot = port->ocelot; + struct hwtstamp_config cfg; + + if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg))) + return -EFAULT; + + /* reserved for future extensions */ + if (cfg.flags) + return -EINVAL; + + /* Tx type sanity check */ + switch (cfg.tx_type) { + case HWTSTAMP_TX_ON: + port->ptp_cmd = IFH_REW_OP_TWO_STEP_PTP; + break; + case HWTSTAMP_TX_ONESTEP_SYNC: + /* IFH_REW_OP_ONE_STEP_PTP updates the correctional field, we + * need to update the origin time. + */ + port->ptp_cmd = IFH_REW_OP_ORIGIN_PTP; + break; + case HWTSTAMP_TX_OFF: + port->ptp_cmd = 0; + break; + default: + return -ERANGE; + } + + mutex_lock(&ocelot->ptp_lock); + + switch (cfg.rx_filter) { + case HWTSTAMP_FILTER_NONE: + break; + case HWTSTAMP_FILTER_ALL: + case HWTSTAMP_FILTER_SOME: + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + case HWTSTAMP_FILTER_NTP_ALL: + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: + case HWTSTAMP_FILTER_PTP_V2_EVENT: + case HWTSTAMP_FILTER_PTP_V2_SYNC: + case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: + cfg.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + break; + default: + mutex_unlock(&ocelot->ptp_lock); + return -ERANGE; + } + + /* Commit back the result & save it */ + memcpy(&ocelot->hwtstamp_config, &cfg, sizeof(cfg)); + mutex_unlock(&ocelot->ptp_lock); + + return copy_to_user(ifr->ifr_data, &cfg, sizeof(cfg)) ? -EFAULT : 0; +} + +static int ocelot_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) +{ + struct ocelot_port *port = netdev_priv(dev); + struct ocelot *ocelot = port->ocelot; + + /* The function is only used for PTP operations for now */ + if (!ocelot->ptp) + return -EOPNOTSUPP; + + switch (cmd) { + case SIOCSHWTSTAMP: + return ocelot_hwstamp_set(port, ifr); + case SIOCGHWTSTAMP: + return ocelot_hwstamp_get(port, ifr); + default: + return -EOPNOTSUPP; + } +} + static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_open = ocelot_port_open, .ndo_stop = ocelot_port_stop, @@ -933,6 +1081,7 @@ static const struct net_device_ops ocelot_port_netdev_ops = { .ndo_set_features = ocelot_set_features, .ndo_get_port_parent_id = ocelot_get_port_parent_id, .ndo_setup_tc = ocelot_setup_tc, + .ndo_do_ioctl = ocelot_ioctl, }; static void ocelot_get_strings(struct net_device *netdev, u32 sset, u8 *data) @@ -1014,12 +1163,37 @@ static int ocelot_get_sset_count(struct net_device *dev, int sset) return ocelot->num_stats; } +static int ocelot_get_ts_info(struct net_device *dev, + struct ethtool_ts_info *info) +{ + struct ocelot_port *ocelot_port = netdev_priv(dev); + struct ocelot *ocelot = ocelot_port->ocelot; + + if (!ocelot->ptp) + return ethtool_op_get_ts_info(dev, info); + + info->phc_index = ocelot->ptp_clock ? + ptp_clock_index(ocelot->ptp_clock) : -1; + info->so_timestamping |= SOF_TIMESTAMPING_TX_SOFTWARE | + SOF_TIMESTAMPING_RX_SOFTWARE | + SOF_TIMESTAMPING_SOFTWARE | + SOF_TIMESTAMPING_TX_HARDWARE | + SOF_TIMESTAMPING_RX_HARDWARE | + SOF_TIMESTAMPING_RAW_HARDWARE; + info->tx_types = BIT(HWTSTAMP_TX_OFF) | BIT(HWTSTAMP_TX_ON) | + BIT(HWTSTAMP_TX_ONESTEP_SYNC); + info->rx_filters = BIT(HWTSTAMP_FILTER_NONE) | BIT(HWTSTAMP_FILTER_ALL); + + return 0; +} + static const struct ethtool_ops ocelot_ethtool_ops = { .get_strings = ocelot_get_strings, .get_ethtool_stats = ocelot_get_ethtool_stats, .get_sset_count = ocelot_get_sset_count, .get_link_ksettings = phy_ethtool_get_link_ksettings, .set_link_ksettings = phy_ethtool_set_link_ksettings, + .get_ts_info = ocelot_get_ts_info, }; static int ocelot_port_attr_stp_state_set(struct ocelot_port *ocelot_port, @@ -1629,6 +1803,196 @@ struct notifier_block ocelot_switchdev_blocking_nb __read_mostly = { }; EXPORT_SYMBOL(ocelot_switchdev_blocking_nb); +int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts) +{ + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + unsigned long flags; + time64_t s; + u32 val; + s64 ns; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_SAVE); + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + s = ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN) & 0xffff; + s <<= 32; + s += ocelot_read_rix(ocelot, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN); + ns = ocelot_read_rix(ocelot, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + + /* Deal with negative values */ + if (ns >= 0x3ffffff0 && ns <= 0x3fffffff) { + s--; + ns &= 0xf; + ns += 999999984; + } + + set_normalized_timespec64(ts, s, ns); + return 0; +} +EXPORT_SYMBOL(ocelot_ptp_gettime64); + +static int ocelot_ptp_settime64(struct ptp_clock_info *ptp, + const struct timespec64 *ts) +{ + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + unsigned long flags; + u32 val; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + ocelot_write_rix(ocelot, lower_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_LSB, + TOD_ACC_PIN); + ocelot_write_rix(ocelot, upper_32_bits(ts->tv_sec), PTP_PIN_TOD_SEC_MSB, + TOD_ACC_PIN); + ocelot_write_rix(ocelot, ts->tv_nsec, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_LOAD); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + return 0; +} + +static int ocelot_ptp_adjtime(struct ptp_clock_info *ptp, s64 delta) +{ + if (delta > -(NSEC_PER_SEC / 2) && delta < (NSEC_PER_SEC / 2)) { + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + unsigned long flags; + u32 val; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_IDLE); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_LSB, TOD_ACC_PIN); + ocelot_write_rix(ocelot, 0, PTP_PIN_TOD_SEC_MSB, TOD_ACC_PIN); + ocelot_write_rix(ocelot, delta, PTP_PIN_TOD_NSEC, TOD_ACC_PIN); + + val = ocelot_read_rix(ocelot, PTP_PIN_CFG, TOD_ACC_PIN); + val &= ~(PTP_PIN_CFG_SYNC | PTP_PIN_CFG_ACTION_MASK | PTP_PIN_CFG_DOM); + val |= PTP_PIN_CFG_ACTION(PTP_PIN_ACTION_DELTA); + + ocelot_write_rix(ocelot, val, PTP_PIN_CFG, TOD_ACC_PIN); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + } else { + /* Fall back using ocelot_ptp_settime64 which is not exact. */ + struct timespec64 ts; + u64 now; + + ocelot_ptp_gettime64(ptp, &ts); + + now = ktime_to_ns(timespec64_to_ktime(ts)); + ts = ns_to_timespec64(now + delta); + + ocelot_ptp_settime64(ptp, &ts); + } + return 0; +} + +static int ocelot_ptp_adjfine(struct ptp_clock_info *ptp, long scaled_ppm) +{ + struct ocelot *ocelot = container_of(ptp, struct ocelot, ptp_info); + u32 unit = 0, direction = 0; + unsigned long flags; + u64 adj = 0; + + spin_lock_irqsave(&ocelot->ptp_clock_lock, flags); + + if (!scaled_ppm) + goto disable_adj; + + if (scaled_ppm < 0) { + direction = PTP_CFG_CLK_ADJ_CFG_DIR; + scaled_ppm = -scaled_ppm; + } + + adj = PSEC_PER_SEC << 16; + do_div(adj, scaled_ppm); + do_div(adj, 1000); + + /* If the adjustment value is too large, use ns instead */ + if (adj >= (1L << 30)) { + unit = PTP_CFG_CLK_ADJ_FREQ_NS; + do_div(adj, 1000); + } + + /* Still too big */ + if (adj >= (1L << 30)) + goto disable_adj; + + ocelot_write(ocelot, unit | adj, PTP_CLK_CFG_ADJ_FREQ); + ocelot_write(ocelot, PTP_CFG_CLK_ADJ_CFG_ENA | direction, + PTP_CLK_CFG_ADJ_CFG); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + return 0; + +disable_adj: + ocelot_write(ocelot, 0, PTP_CLK_CFG_ADJ_CFG); + + spin_unlock_irqrestore(&ocelot->ptp_clock_lock, flags); + return 0; +} + +static struct ptp_clock_info ocelot_ptp_clock_info = { + .owner = THIS_MODULE, + .name = "ocelot ptp", + .max_adj = 0x7fffffff, + .n_alarm = 0, + .n_ext_ts = 0, + .n_per_out = 0, + .n_pins = 0, + .pps = 0, + .gettime64 = ocelot_ptp_gettime64, + .settime64 = ocelot_ptp_settime64, + .adjtime = ocelot_ptp_adjtime, + .adjfine = ocelot_ptp_adjfine, +}; + +static int ocelot_init_timestamp(struct ocelot *ocelot) +{ + ocelot->ptp_info = ocelot_ptp_clock_info; + ocelot->ptp_clock = ptp_clock_register(&ocelot->ptp_info, ocelot->dev); + if (IS_ERR(ocelot->ptp_clock)) + return PTR_ERR(ocelot->ptp_clock); + /* Check if PHC support is missing at the configuration level */ + if (!ocelot->ptp_clock) + return 0; + + ocelot_write(ocelot, SYS_PTP_CFG_PTP_STAMP_WID(30), SYS_PTP_CFG); + ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_LOW); + ocelot_write(ocelot, 0xffffffff, ANA_TABLES_PTP_ID_HIGH); + + ocelot_write(ocelot, PTP_CFG_MISC_PTP_EN, PTP_CFG_MISC); + + /* There is no device reconfiguration, PTP Rx stamping is always + * enabled. + */ + ocelot->hwtstamp_config.rx_filter = HWTSTAMP_FILTER_PTP_V2_EVENT; + + return 0; +} + int ocelot_probe_port(struct ocelot *ocelot, u8 port, void __iomem *regs, struct phy_device *phy) @@ -1661,6 +2025,8 @@ int ocelot_probe_port(struct ocelot *ocelot, u8 port, ocelot_mact_learn(ocelot, PGID_CPU, dev->dev_addr, ocelot_port->pvid, ENTRYTYPE_LOCKED); + INIT_LIST_HEAD(&ocelot_port->skbs); + err = register_netdev(dev); if (err) { dev_err(ocelot->dev, "register_netdev failed\n"); @@ -1684,7 +2050,7 @@ EXPORT_SYMBOL(ocelot_probe_port); int ocelot_init(struct ocelot *ocelot) { u32 port; - int i, cpu = ocelot->num_phys_ports; + int i, ret, cpu = ocelot->num_phys_ports; char queue_name[32]; ocelot->lags = devm_kcalloc(ocelot->dev, ocelot->num_phys_ports, @@ -1699,6 +2065,8 @@ int ocelot_init(struct ocelot *ocelot) return -ENOMEM; mutex_init(&ocelot->stats_lock); + mutex_init(&ocelot->ptp_lock); + spin_lock_init(&ocelot->ptp_clock_lock); snprintf(queue_name, sizeof(queue_name), "%s-stats", dev_name(ocelot->dev)); ocelot->stats_queue = create_singlethread_workqueue(queue_name); @@ -1812,16 +2180,43 @@ int ocelot_init(struct ocelot *ocelot) INIT_DELAYED_WORK(&ocelot->stats_work, ocelot_check_stats_work); queue_delayed_work(ocelot->stats_queue, &ocelot->stats_work, OCELOT_STATS_CHECK_DELAY); + + if (ocelot->ptp) { + ret = ocelot_init_timestamp(ocelot); + if (ret) { + dev_err(ocelot->dev, + "Timestamp initialization failed\n"); + return ret; + } + } + return 0; } EXPORT_SYMBOL(ocelot_init); void ocelot_deinit(struct ocelot *ocelot) { + struct list_head *pos, *tmp; + struct ocelot_port *port; + struct ocelot_skb *entry; + int i; + cancel_delayed_work(&ocelot->stats_work); destroy_workqueue(ocelot->stats_queue); mutex_destroy(&ocelot->stats_lock); ocelot_ace_deinit(); + + for (i = 0; i < ocelot->num_phys_ports; i++) { + port = ocelot->ports[i]; + + list_for_each_safe(pos, tmp, &port->skbs) { + entry = list_entry(pos, struct ocelot_skb, head); + + list_del(pos); + dev_kfree_skb_any(entry->skb); + kfree(entry); + } + } } EXPORT_SYMBOL(ocelot_deinit); diff --git a/drivers/net/ethernet/mscc/ocelot.h b/drivers/net/ethernet/mscc/ocelot.h index f7eeb4806897..e40773c01a44 100644 --- a/drivers/net/ethernet/mscc/ocelot.h +++ b/drivers/net/ethernet/mscc/ocelot.h @@ -11,9 +11,11 @@ #include <linux/bitops.h> #include <linux/etherdevice.h> #include <linux/if_vlan.h> +#include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/phy/phy.h> #include <linux/platform_device.h> +#include <linux/ptp_clock_kernel.h> #include <linux/regmap.h> #include "ocelot_ana.h" @@ -23,6 +25,7 @@ #include "ocelot_sys.h" #include "ocelot_qs.h" #include "ocelot_tc.h" +#include "ocelot_ptp.h" #define PGID_AGGR 64 #define PGID_SRC 80 @@ -38,14 +41,17 @@ #define OCELOT_STATS_CHECK_DELAY (2 * HZ) +#define OCELOT_PTP_QUEUE_SZ 128 + #define IFH_LEN 4 struct frame_info { u32 len; u16 port; u16 vid; - u8 cpuq; u8 tag_type; + u16 rew_op; + u32 timestamp; /* rew_val */ }; #define IFH_INJ_BYPASS BIT(31) @@ -54,6 +60,12 @@ struct frame_info { #define IFH_TAG_TYPE_C 0 #define IFH_TAG_TYPE_S 1 +#define IFH_REW_OP_NOOP 0x0 +#define IFH_REW_OP_DSCP 0x1 +#define IFH_REW_OP_ONE_STEP_PTP 0x2 +#define IFH_REW_OP_TWO_STEP_PTP 0x3 +#define IFH_REW_OP_ORIGIN_PTP 0x5 + #define OCELOT_SPEED_2500 0 #define OCELOT_SPEED_1000 1 #define OCELOT_SPEED_100 2 @@ -71,6 +83,7 @@ enum ocelot_target { SYS, S2, HSIO, + PTP, TARGET_MAX, }; @@ -343,6 +356,13 @@ enum ocelot_reg { S2_CACHE_ACTION_DAT, S2_CACHE_CNT_DAT, S2_CACHE_TG_DAT, + PTP_PIN_CFG = PTP << TARGET_OFFSET, + PTP_PIN_TOD_SEC_MSB, + PTP_PIN_TOD_SEC_LSB, + PTP_PIN_TOD_NSEC, + PTP_CFG_MISC, + PTP_CLK_CFG_ADJ_CFG, + PTP_CLK_CFG_ADJ_FREQ, }; enum ocelot_regfield { @@ -393,6 +413,13 @@ enum ocelot_regfield { REGFIELD_MAX }; +enum ocelot_clk_pins { + ALT_PPS_PIN = 1, + EXT_CLK_PIN, + ALT_LDST_PIN, + TOD_ACC_PIN +}; + struct ocelot_multicast { struct list_head list; unsigned char addr[ETH_ALEN]; @@ -442,6 +469,13 @@ struct ocelot { u64 *stats; struct delayed_work stats_work; struct workqueue_struct *stats_queue; + + u8 ptp:1; + struct ptp_clock *ptp_clock; + struct ptp_clock_info ptp_info; + struct hwtstamp_config hwtstamp_config; + struct mutex ptp_lock; /* Protects the PTP interface state */ + spinlock_t ptp_clock_lock; /* Protects the PTP clock */ }; struct ocelot_port { @@ -465,6 +499,16 @@ struct ocelot_port { struct phy *serdes; struct ocelot_port_tc tc; + + u8 ptp_cmd; + struct list_head skbs; + u8 ts_id; +}; + +struct ocelot_skb { + struct list_head head; + struct sk_buff *skb; + u8 id; }; u32 __ocelot_read_ix(struct ocelot *ocelot, u32 reg, u32 offset); @@ -509,4 +553,7 @@ extern struct notifier_block ocelot_netdevice_nb; extern struct notifier_block ocelot_switchdev_nb; extern struct notifier_block ocelot_switchdev_blocking_nb; +int ocelot_ptp_gettime64(struct ptp_clock_info *ptp, struct timespec64 *ts); +void ocelot_get_hwtimestamp(struct ocelot *ocelot, struct timespec64 *ts); + #endif diff --git a/drivers/net/ethernet/mscc/ocelot_board.c b/drivers/net/ethernet/mscc/ocelot_board.c index 2451d4a96490..b063eb78fa0c 100644 --- a/drivers/net/ethernet/mscc/ocelot_board.c +++ b/drivers/net/ethernet/mscc/ocelot_board.c @@ -16,24 +16,27 @@ #include "ocelot.h" -static int ocelot_parse_ifh(u32 *ifh, struct frame_info *info) +#define IFH_EXTRACT_BITFIELD64(x, o, w) (((x) >> (o)) & GENMASK_ULL((w) - 1, 0)) + +static int ocelot_parse_ifh(u32 *_ifh, struct frame_info *info) { - int i; u8 llen, wlen; + u64 ifh[2]; + + ifh[0] = be64_to_cpu(((__force __be64 *)_ifh)[0]); + ifh[1] = be64_to_cpu(((__force __be64 *)_ifh)[1]); - /* The IFH is in network order, switch to CPU order */ - for (i = 0; i < IFH_LEN; i++) - ifh[i] = ntohl((__force __be32)ifh[i]); + wlen = IFH_EXTRACT_BITFIELD64(ifh[0], 7, 8); + llen = IFH_EXTRACT_BITFIELD64(ifh[0], 15, 6); - wlen = (ifh[1] >> 7) & 0xff; - llen = (ifh[1] >> 15) & 0x3f; info->len = OCELOT_BUFFER_CELL_SZ * wlen + llen - 80; - info->port = (ifh[2] & GENMASK(14, 11)) >> 11; + info->timestamp = IFH_EXTRACT_BITFIELD64(ifh[0], 21, 32); + + info->port = IFH_EXTRACT_BITFIELD64(ifh[1], 43, 4); - info->cpuq = (ifh[3] & GENMASK(27, 20)) >> 20; - info->tag_type = (ifh[3] & BIT(16)) >> 16; - info->vid = ifh[3] & GENMASK(11, 0); + info->tag_type = IFH_EXTRACT_BITFIELD64(ifh[1], 16, 1); + info->vid = IFH_EXTRACT_BITFIELD64(ifh[1], 0, 12); return 0; } @@ -91,13 +94,14 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) return IRQ_NONE; do { - struct sk_buff *skb; + struct skb_shared_hwtstamps *shhwtstamps; + u64 tod_in_ns, full_ts_in_ns; + struct frame_info info = {}; struct net_device *dev; - u32 *buf; + u32 ifh[4], val, *buf; + struct timespec64 ts; int sz, len, buf_len; - u32 ifh[4]; - u32 val; - struct frame_info info; + struct sk_buff *skb; for (i = 0; i < IFH_LEN; i++) { err = ocelot_rx_frame_word(ocelot, grp, true, &ifh[i]); @@ -144,6 +148,22 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) break; } + if (ocelot->ptp) { + ocelot_ptp_gettime64(&ocelot->ptp_info, &ts); + + tod_in_ns = ktime_set(ts.tv_sec, ts.tv_nsec); + if ((tod_in_ns & 0xffffffff) < info.timestamp) + full_ts_in_ns = (((tod_in_ns >> 32) - 1) << 32) | + info.timestamp; + else + full_ts_in_ns = (tod_in_ns & GENMASK_ULL(63, 32)) | + info.timestamp; + + shhwtstamps = skb_hwtstamps(skb); + memset(shhwtstamps, 0, sizeof(struct skb_shared_hwtstamps)); + shhwtstamps->hwtstamp = full_ts_in_ns; + } + /* Everything we see on an interface that is in the HW bridge * has already been forwarded. */ @@ -163,6 +183,66 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg) return IRQ_HANDLED; } +static irqreturn_t ocelot_ptp_rdy_irq_handler(int irq, void *arg) +{ + int budget = OCELOT_PTP_QUEUE_SZ; + struct ocelot *ocelot = arg; + + while (budget--) { + struct skb_shared_hwtstamps shhwtstamps; + struct list_head *pos, *tmp; + struct sk_buff *skb = NULL; + struct ocelot_skb *entry; + struct ocelot_port *port; + struct timespec64 ts; + u32 val, id, txport; + + val = ocelot_read(ocelot, SYS_PTP_STATUS); + + /* Check if a timestamp can be retrieved */ + if (!(val & SYS_PTP_STATUS_PTP_MESS_VLD)) + break; + + WARN_ON(val & SYS_PTP_STATUS_PTP_OVFL); + + /* Retrieve the ts ID and Tx port */ + id = SYS_PTP_STATUS_PTP_MESS_ID_X(val); + txport = SYS_PTP_STATUS_PTP_MESS_TXPORT_X(val); + + /* Retrieve its associated skb */ + port = ocelot->ports[txport]; + + list_for_each_safe(pos, tmp, &port->skbs) { + entry = list_entry(pos, struct ocelot_skb, head); + if (entry->id != id) + continue; + + skb = entry->skb; + + list_del(pos); + kfree(entry); + } + + /* Next ts */ + ocelot_write(ocelot, SYS_PTP_NXT_PTP_NXT, SYS_PTP_NXT); + + if (unlikely(!skb)) + continue; + + /* Get the h/w timestamp */ + ocelot_get_hwtimestamp(ocelot, &ts); + + /* Set the timestamp into the skb */ + memset(&shhwtstamps, 0, sizeof(shhwtstamps)); + shhwtstamps.hwtstamp = ktime_set(ts.tv_sec, ts.tv_nsec); + skb_tstamp_tx(skb, &shhwtstamps); + + dev_kfree_skb_any(skb); + } + + return IRQ_HANDLED; +} + static const struct of_device_id mscc_ocelot_match[] = { { .compatible = "mscc,vsc7514-switch" }, { } @@ -171,17 +251,18 @@ MODULE_DEVICE_TABLE(of, mscc_ocelot_match); static int mscc_ocelot_probe(struct platform_device *pdev) { - int err, irq; - unsigned int i; struct device_node *np = pdev->dev.of_node; struct device_node *ports, *portnp; + int err, irq_xtr, irq_ptp_rdy; struct ocelot *ocelot; struct regmap *hsio; + unsigned int i; u32 val; struct { enum ocelot_target id; char *name; + u8 optional:1; } res[] = { { SYS, "sys" }, { REW, "rew" }, @@ -189,6 +270,7 @@ static int mscc_ocelot_probe(struct platform_device *pdev) { ANA, "ana" }, { QS, "qs" }, { S2, "s2" }, + { PTP, "ptp", 1 }, }; if (!np && !pdev->dev.platform_data) @@ -205,8 +287,14 @@ static int mscc_ocelot_probe(struct platform_device *pdev) struct regmap *target; target = ocelot_io_platform_init(ocelot, pdev, res[i].name); - if (IS_ERR(target)) + if (IS_ERR(target)) { + if (res[i].optional) { + ocelot->targets[res[i].id] = NULL; + continue; + } + return PTR_ERR(target); + } ocelot->targets[res[i].id] = target; } @@ -223,16 +311,29 @@ static int mscc_ocelot_probe(struct platform_device *pdev) if (err) return err; - irq = platform_get_irq_byname(pdev, "xtr"); - if (irq < 0) + irq_xtr = platform_get_irq_byname(pdev, "xtr"); + if (irq_xtr < 0) return -ENODEV; - err = devm_request_threaded_irq(&pdev->dev, irq, NULL, + err = devm_request_threaded_irq(&pdev->dev, irq_xtr, NULL, ocelot_xtr_irq_handler, IRQF_ONESHOT, "frame extraction", ocelot); if (err) return err; + irq_ptp_rdy = platform_get_irq_byname(pdev, "ptp_rdy"); + if (irq_ptp_rdy > 0 && ocelot->targets[PTP]) { + err = devm_request_threaded_irq(&pdev->dev, irq_ptp_rdy, NULL, + ocelot_ptp_rdy_irq_handler, + IRQF_ONESHOT, "ptp ready", + ocelot); + if (err) + return err; + + /* Both the PTP interrupt and the PTP bank are available */ + ocelot->ptp = 1; + } + regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_INIT], 1); regmap_field_write(ocelot->regfields[SYS_RESET_CFG_MEM_ENA], 1); diff --git a/drivers/net/ethernet/mscc/ocelot_ptp.h b/drivers/net/ethernet/mscc/ocelot_ptp.h new file mode 100644 index 000000000000..9ede14a12573 --- /dev/null +++ b/drivers/net/ethernet/mscc/ocelot_ptp.h @@ -0,0 +1,41 @@ +/* SPDX-License-Identifier: (GPL-2.0 OR MIT) */ +/* + * Microsemi Ocelot Switch driver + * + * License: Dual MIT/GPL + * Copyright (c) 2017 Microsemi Corporation + */ + +#ifndef _MSCC_OCELOT_PTP_H_ +#define _MSCC_OCELOT_PTP_H_ + +#define PTP_PIN_CFG_RSZ 0x20 +#define PTP_PIN_TOD_SEC_MSB_RSZ PTP_PIN_CFG_RSZ +#define PTP_PIN_TOD_SEC_LSB_RSZ PTP_PIN_CFG_RSZ +#define PTP_PIN_TOD_NSEC_RSZ PTP_PIN_CFG_RSZ + +#define PTP_PIN_CFG_DOM BIT(0) +#define PTP_PIN_CFG_SYNC BIT(2) +#define PTP_PIN_CFG_ACTION(x) ((x) << 3) +#define PTP_PIN_CFG_ACTION_MASK PTP_PIN_CFG_ACTION(0x7) + +enum { + PTP_PIN_ACTION_IDLE = 0, + PTP_PIN_ACTION_LOAD, + PTP_PIN_ACTION_SAVE, + PTP_PIN_ACTION_CLOCK, + PTP_PIN_ACTION_DELTA, + PTP_PIN_ACTION_NOSYNC, + PTP_PIN_ACTION_SYNC, +}; + +#define PTP_CFG_MISC_PTP_EN BIT(2) + +#define PSEC_PER_SEC 1000000000000LL + +#define PTP_CFG_CLK_ADJ_CFG_ENA BIT(0) +#define PTP_CFG_CLK_ADJ_CFG_DIR BIT(1) + +#define PTP_CFG_CLK_ADJ_FREQ_NS BIT(30) + +#endif diff --git a/drivers/net/ethernet/mscc/ocelot_regs.c b/drivers/net/ethernet/mscc/ocelot_regs.c index 6c387f994ec5..e59977d20400 100644 --- a/drivers/net/ethernet/mscc/ocelot_regs.c +++ b/drivers/net/ethernet/mscc/ocelot_regs.c @@ -234,6 +234,16 @@ static const u32 ocelot_s2_regmap[] = { REG(S2_CACHE_TG_DAT, 0x000388), }; +static const u32 ocelot_ptp_regmap[] = { + REG(PTP_PIN_CFG, 0x000000), + REG(PTP_PIN_TOD_SEC_MSB, 0x000004), + REG(PTP_PIN_TOD_SEC_LSB, 0x000008), + REG(PTP_PIN_TOD_NSEC, 0x00000c), + REG(PTP_CFG_MISC, 0x0000a0), + REG(PTP_CLK_CFG_ADJ_CFG, 0x0000a4), + REG(PTP_CLK_CFG_ADJ_FREQ, 0x0000a8), +}; + static const u32 *ocelot_regmap[] = { [ANA] = ocelot_ana_regmap, [QS] = ocelot_qs_regmap, @@ -241,6 +251,7 @@ static const u32 *ocelot_regmap[] = { [REW] = ocelot_rew_regmap, [SYS] = ocelot_sys_regmap, [S2] = ocelot_s2_regmap, + [PTP] = ocelot_ptp_regmap, }; static const struct reg_field ocelot_regfields[] = { diff --git a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c index 337b0cbfd153..c979f38a2e0c 100644 --- a/drivers/net/ethernet/myricom/myri10ge/myri10ge.c +++ b/drivers/net/ethernet/myricom/myri10ge/myri10ge.c @@ -1286,7 +1286,7 @@ myri10ge_vlan_rx(struct net_device *dev, void *addr, struct sk_buff *skb) { u8 *va; struct vlan_ethhdr *veh; - struct skb_frag_struct *frag; + skb_frag_t *frag; __wsum vsum; va = addr; @@ -1306,8 +1306,8 @@ myri10ge_vlan_rx(struct net_device *dev, void *addr, struct sk_buff *skb) skb->len -= VLAN_HLEN; skb->data_len -= VLAN_HLEN; frag = skb_shinfo(skb)->frags; - frag->page_offset += VLAN_HLEN; - skb_frag_size_set(frag, skb_frag_size(frag) - VLAN_HLEN); + skb_frag_off_add(frag, VLAN_HLEN); + skb_frag_size_sub(frag, VLAN_HLEN); } } @@ -1318,7 +1318,7 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum) { struct myri10ge_priv *mgp = ss->mgp; struct sk_buff *skb; - struct skb_frag_struct *rx_frags; + skb_frag_t *rx_frags; struct myri10ge_rx_buf *rx; int i, idx, remainder, bytes; struct pci_dev *pdev = mgp->pdev; @@ -1351,7 +1351,7 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum) return 0; } rx_frags = skb_shinfo(skb)->frags; - /* Fill skb_frag_struct(s) with data from our receive */ + /* Fill skb_frag_t(s) with data from our receive */ for (i = 0, remainder = len; remainder > 0; i++) { myri10ge_unmap_rx_page(pdev, &rx->info[idx], bytes); skb_fill_page_desc(skb, i, rx->info[idx].page, @@ -1364,8 +1364,8 @@ myri10ge_rx_done(struct myri10ge_slice_state *ss, int len, __wsum csum) } /* remove padding */ - rx_frags[0].page_offset += MXGEFW_PAD; - rx_frags[0].size -= MXGEFW_PAD; + skb_frag_off_add(&rx_frags[0], MXGEFW_PAD); + skb_frag_size_sub(&rx_frags[0], MXGEFW_PAD); len -= MXGEFW_PAD; skb->len = len; @@ -2628,7 +2628,7 @@ static netdev_tx_t myri10ge_xmit(struct sk_buff *skb, struct myri10ge_slice_state *ss; struct mcp_kreq_ether_send *req; struct myri10ge_tx_buf *tx; - struct skb_frag_struct *frag; + skb_frag_t *frag; struct netdev_queue *netdev_queue; dma_addr_t bus; u32 low; @@ -3037,7 +3037,6 @@ static int myri10ge_set_mac_address(struct net_device *dev, void *addr) static int myri10ge_change_mtu(struct net_device *dev, int new_mtu) { struct myri10ge_priv *mgp = netdev_priv(dev); - int error = 0; netdev_info(dev, "changing mtu from %d to %d\n", dev->mtu, new_mtu); if (mgp->running) { @@ -3049,7 +3048,7 @@ static int myri10ge_change_mtu(struct net_device *dev, int new_mtu) } else dev->mtu = new_mtu; - return error; + return 0; } /* diff --git a/drivers/net/ethernet/netronome/nfp/Makefile b/drivers/net/ethernet/netronome/nfp/Makefile index 2805641965f3..d31772ae511d 100644 --- a/drivers/net/ethernet/netronome/nfp/Makefile +++ b/drivers/net/ethernet/netronome/nfp/Makefile @@ -17,6 +17,7 @@ nfp-objs := \ nfpcore/nfp_target.o \ ccm.o \ ccm_mbox.o \ + devlink_param.o \ nfp_asm.o \ nfp_app.o \ nfp_app_nic.o \ diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c index bc9850e4ec5e..0e2db6ea79e9 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c @@ -6,6 +6,7 @@ #include <linux/bug.h> #include <linux/jiffies.h> #include <linux/skbuff.h> +#include <linux/timekeeping.h> #include "../ccm.h" #include "../nfp_app.h" @@ -175,29 +176,151 @@ nfp_bpf_ctrl_reply_val(struct nfp_app_bpf *bpf, struct cmsg_reply_map_op *reply, return &reply->data[bpf->cmsg_key_sz * (n + 1) + bpf->cmsg_val_sz * n]; } +static bool nfp_bpf_ctrl_op_cache_invalidate(enum nfp_ccm_type op) +{ + return op == NFP_CCM_TYPE_BPF_MAP_UPDATE || + op == NFP_CCM_TYPE_BPF_MAP_DELETE; +} + +static bool nfp_bpf_ctrl_op_cache_capable(enum nfp_ccm_type op) +{ + return op == NFP_CCM_TYPE_BPF_MAP_LOOKUP || + op == NFP_CCM_TYPE_BPF_MAP_GETNEXT; +} + +static bool nfp_bpf_ctrl_op_cache_fill(enum nfp_ccm_type op) +{ + return op == NFP_CCM_TYPE_BPF_MAP_GETFIRST || + op == NFP_CCM_TYPE_BPF_MAP_GETNEXT; +} + +static unsigned int +nfp_bpf_ctrl_op_cache_get(struct nfp_bpf_map *nfp_map, enum nfp_ccm_type op, + const u8 *key, u8 *out_key, u8 *out_value, + u32 *cache_gen) +{ + struct bpf_map *map = &nfp_map->offmap->map; + struct nfp_app_bpf *bpf = nfp_map->bpf; + unsigned int i, count, n_entries; + struct cmsg_reply_map_op *reply; + + n_entries = nfp_bpf_ctrl_op_cache_fill(op) ? bpf->cmsg_cache_cnt : 1; + + spin_lock(&nfp_map->cache_lock); + *cache_gen = nfp_map->cache_gen; + if (nfp_map->cache_blockers) + n_entries = 1; + + if (nfp_bpf_ctrl_op_cache_invalidate(op)) + goto exit_block; + if (!nfp_bpf_ctrl_op_cache_capable(op)) + goto exit_unlock; + + if (!nfp_map->cache) + goto exit_unlock; + if (nfp_map->cache_to < ktime_get_ns()) + goto exit_invalidate; + + reply = (void *)nfp_map->cache->data; + count = be32_to_cpu(reply->count); + + for (i = 0; i < count; i++) { + void *cached_key; + + cached_key = nfp_bpf_ctrl_reply_key(bpf, reply, i); + if (memcmp(cached_key, key, map->key_size)) + continue; + + if (op == NFP_CCM_TYPE_BPF_MAP_LOOKUP) + memcpy(out_value, nfp_bpf_ctrl_reply_val(bpf, reply, i), + map->value_size); + if (op == NFP_CCM_TYPE_BPF_MAP_GETNEXT) { + if (i + 1 == count) + break; + + memcpy(out_key, + nfp_bpf_ctrl_reply_key(bpf, reply, i + 1), + map->key_size); + } + + n_entries = 0; + goto exit_unlock; + } + goto exit_unlock; + +exit_block: + nfp_map->cache_blockers++; +exit_invalidate: + dev_consume_skb_any(nfp_map->cache); + nfp_map->cache = NULL; +exit_unlock: + spin_unlock(&nfp_map->cache_lock); + return n_entries; +} + +static void +nfp_bpf_ctrl_op_cache_put(struct nfp_bpf_map *nfp_map, enum nfp_ccm_type op, + struct sk_buff *skb, u32 cache_gen) +{ + bool blocker, filler; + + blocker = nfp_bpf_ctrl_op_cache_invalidate(op); + filler = nfp_bpf_ctrl_op_cache_fill(op); + if (blocker || filler) { + u64 to = 0; + + if (filler) + to = ktime_get_ns() + NFP_BPF_MAP_CACHE_TIME_NS; + + spin_lock(&nfp_map->cache_lock); + if (blocker) { + nfp_map->cache_blockers--; + nfp_map->cache_gen++; + } + if (filler && !nfp_map->cache_blockers && + nfp_map->cache_gen == cache_gen) { + nfp_map->cache_to = to; + swap(nfp_map->cache, skb); + } + spin_unlock(&nfp_map->cache_lock); + } + + dev_consume_skb_any(skb); +} + static int nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap, enum nfp_ccm_type op, u8 *key, u8 *value, u64 flags, u8 *out_key, u8 *out_value) { struct nfp_bpf_map *nfp_map = offmap->dev_priv; + unsigned int n_entries, reply_entries, count; struct nfp_app_bpf *bpf = nfp_map->bpf; struct bpf_map *map = &offmap->map; struct cmsg_reply_map_op *reply; struct cmsg_req_map_op *req; struct sk_buff *skb; + u32 cache_gen; int err; /* FW messages have no space for more than 32 bits of flags */ if (flags >> 32) return -EOPNOTSUPP; + /* Handle op cache */ + n_entries = nfp_bpf_ctrl_op_cache_get(nfp_map, op, key, out_key, + out_value, &cache_gen); + if (!n_entries) + return 0; + skb = nfp_bpf_cmsg_map_req_alloc(bpf, 1); - if (!skb) - return -ENOMEM; + if (!skb) { + err = -ENOMEM; + goto err_cache_put; + } req = (void *)skb->data; req->tid = cpu_to_be32(nfp_map->tid); - req->count = cpu_to_be32(1); + req->count = cpu_to_be32(n_entries); req->flags = cpu_to_be32(flags); /* Copy inputs */ @@ -207,16 +330,38 @@ nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap, enum nfp_ccm_type op, memcpy(nfp_bpf_ctrl_req_val(bpf, req, 0), value, map->value_size); - skb = nfp_ccm_communicate(&bpf->ccm, skb, op, - nfp_bpf_cmsg_map_reply_size(bpf, 1)); - if (IS_ERR(skb)) - return PTR_ERR(skb); + skb = nfp_ccm_communicate(&bpf->ccm, skb, op, 0); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + goto err_cache_put; + } + + if (skb->len < sizeof(*reply)) { + cmsg_warn(bpf, "cmsg drop - type 0x%02x too short %d!\n", + op, skb->len); + err = -EIO; + goto err_free; + } reply = (void *)skb->data; + count = be32_to_cpu(reply->count); err = nfp_bpf_ctrl_rc_to_errno(bpf, &reply->reply_hdr); + /* FW responds with message sized to hold the good entries, + * plus one extra entry if there was an error. + */ + reply_entries = count + !!err; + if (n_entries > 1 && count) + err = 0; if (err) goto err_free; + if (skb->len != nfp_bpf_cmsg_map_reply_size(bpf, reply_entries)) { + cmsg_warn(bpf, "cmsg drop - type 0x%02x too short %d for %d entries!\n", + op, skb->len, reply_entries); + err = -EIO; + goto err_free; + } + /* Copy outputs */ if (out_key) memcpy(out_key, nfp_bpf_ctrl_reply_key(bpf, reply, 0), @@ -225,11 +370,13 @@ nfp_bpf_ctrl_entry_op(struct bpf_offloaded_map *offmap, enum nfp_ccm_type op, memcpy(out_value, nfp_bpf_ctrl_reply_val(bpf, reply, 0), map->value_size); - dev_consume_skb_any(skb); + nfp_bpf_ctrl_op_cache_put(nfp_map, op, skb, cache_gen); return 0; err_free: dev_kfree_skb_any(skb); +err_cache_put: + nfp_bpf_ctrl_op_cache_put(nfp_map, op, NULL, cache_gen); return err; } @@ -267,11 +414,29 @@ int nfp_bpf_ctrl_getnext_entry(struct bpf_offloaded_map *offmap, key, NULL, 0, next_key, NULL); } +unsigned int nfp_bpf_ctrl_cmsg_min_mtu(struct nfp_app_bpf *bpf) +{ + return max(nfp_bpf_cmsg_map_req_size(bpf, 1), + nfp_bpf_cmsg_map_reply_size(bpf, 1)); +} + unsigned int nfp_bpf_ctrl_cmsg_mtu(struct nfp_app_bpf *bpf) { - return max3((unsigned int)NFP_NET_DEFAULT_MTU, - nfp_bpf_cmsg_map_req_size(bpf, 1), - nfp_bpf_cmsg_map_reply_size(bpf, 1)); + return max3(NFP_NET_DEFAULT_MTU, + nfp_bpf_cmsg_map_req_size(bpf, NFP_BPF_MAP_CACHE_CNT), + nfp_bpf_cmsg_map_reply_size(bpf, NFP_BPF_MAP_CACHE_CNT)); +} + +unsigned int nfp_bpf_ctrl_cmsg_cache_cnt(struct nfp_app_bpf *bpf) +{ + unsigned int mtu, req_max, reply_max, entry_sz; + + mtu = bpf->app->ctrl->dp.mtu; + entry_sz = bpf->cmsg_key_sz + bpf->cmsg_val_sz; + req_max = (mtu - sizeof(struct cmsg_req_map_op)) / entry_sz; + reply_max = (mtu - sizeof(struct cmsg_reply_map_op)) / entry_sz; + + return min3(req_max, reply_max, NFP_BPF_MAP_CACHE_CNT); } void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/fw.h b/drivers/net/ethernet/netronome/nfp/bpf/fw.h index 06c4286bd79e..a83a0ad5e27d 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/fw.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/fw.h @@ -24,6 +24,7 @@ enum bpf_cap_tlv_type { NFP_BPF_CAP_TYPE_QUEUE_SELECT = 5, NFP_BPF_CAP_TYPE_ADJUST_TAIL = 6, NFP_BPF_CAP_TYPE_ABI_VERSION = 7, + NFP_BPF_CAP_TYPE_CMSG_MULTI_ENT = 8, }; struct nfp_bpf_cap_tlv_func { diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 1c9fb11470df..8f732771d3fa 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -300,6 +300,14 @@ nfp_bpf_parse_cap_adjust_tail(struct nfp_app_bpf *bpf, void __iomem *value, } static int +nfp_bpf_parse_cap_cmsg_multi_ent(struct nfp_app_bpf *bpf, void __iomem *value, + u32 length) +{ + bpf->cmsg_multi_ent = true; + return 0; +} + +static int nfp_bpf_parse_cap_abi_version(struct nfp_app_bpf *bpf, void __iomem *value, u32 length) { @@ -375,6 +383,11 @@ static int nfp_bpf_parse_capabilities(struct nfp_app *app) length)) goto err_release_free; break; + case NFP_BPF_CAP_TYPE_CMSG_MULTI_ENT: + if (nfp_bpf_parse_cap_cmsg_multi_ent(app->priv, value, + length)) + goto err_release_free; + break; default: nfp_dbg(cpp, "unknown BPF capability: %d\n", type); break; @@ -415,6 +428,25 @@ static void nfp_bpf_ndo_uninit(struct nfp_app *app, struct net_device *netdev) bpf_offload_dev_netdev_unregister(bpf->bpf_dev, netdev); } +static int nfp_bpf_start(struct nfp_app *app) +{ + struct nfp_app_bpf *bpf = app->priv; + + if (app->ctrl->dp.mtu < nfp_bpf_ctrl_cmsg_min_mtu(bpf)) { + nfp_err(bpf->app->cpp, + "ctrl channel MTU below min required %u < %u\n", + app->ctrl->dp.mtu, nfp_bpf_ctrl_cmsg_min_mtu(bpf)); + return -EINVAL; + } + + if (bpf->cmsg_multi_ent) + bpf->cmsg_cache_cnt = nfp_bpf_ctrl_cmsg_cache_cnt(bpf); + else + bpf->cmsg_cache_cnt = 1; + + return 0; +} + static int nfp_bpf_init(struct nfp_app *app) { struct nfp_app_bpf *bpf; @@ -488,6 +520,7 @@ const struct nfp_app_type app_bpf = { .init = nfp_bpf_init, .clean = nfp_bpf_clean, + .start = nfp_bpf_start, .check_mtu = nfp_bpf_check_mtu, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index 57d6ff51e980..fac9c6f9e197 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -99,6 +99,7 @@ enum pkt_vec { * @maps_neutral: hash table of offload-neutral maps (on pointer) * * @abi_version: global BPF ABI version + * @cmsg_cache_cnt: number of entries to read for caching * * @adjust_head: adjust head capability * @adjust_head.flags: extra flags for adjust head @@ -124,6 +125,7 @@ enum pkt_vec { * @pseudo_random: FW initialized the pseudo-random machinery (CSRs) * @queue_select: BPF can set the RX queue ID in packet vector * @adjust_tail: BPF can simply trunc packet size for adjust tail + * @cmsg_multi_ent: FW can pack multiple map entries in a single cmsg */ struct nfp_app_bpf { struct nfp_app *app; @@ -134,6 +136,8 @@ struct nfp_app_bpf { unsigned int cmsg_key_sz; unsigned int cmsg_val_sz; + unsigned int cmsg_cache_cnt; + struct list_head map_list; unsigned int maps_in_use; unsigned int map_elems_in_use; @@ -169,6 +173,7 @@ struct nfp_app_bpf { bool pseudo_random; bool queue_select; bool adjust_tail; + bool cmsg_multi_ent; }; enum nfp_bpf_map_use { @@ -183,11 +188,21 @@ struct nfp_bpf_map_word { unsigned char non_zero_update :1; }; +#define NFP_BPF_MAP_CACHE_CNT 4U +#define NFP_BPF_MAP_CACHE_TIME_NS (250 * 1000) + /** * struct nfp_bpf_map - private per-map data attached to BPF maps for offload * @offmap: pointer to the offloaded BPF map * @bpf: back pointer to bpf app private structure * @tid: table id identifying map on datapath + * + * @cache_lock: protects @cache_blockers, @cache_to, @cache + * @cache_blockers: number of ops in flight which block caching + * @cache_gen: counter incremented by every blocker on exit + * @cache_to: time when cache will no longer be valid (ns) + * @cache: skb with cached response + * * @l: link on the nfp_app_bpf->map_list list * @use_map: map of how the value is used (in 4B chunks) */ @@ -195,6 +210,13 @@ struct nfp_bpf_map { struct bpf_offloaded_map *offmap; struct nfp_app_bpf *bpf; u32 tid; + + spinlock_t cache_lock; + u32 cache_blockers; + u32 cache_gen; + u64 cache_to; + struct sk_buff *cache; + struct list_head l; struct nfp_bpf_map_word use_map[]; }; @@ -564,7 +586,9 @@ nfp_bpf_goto_meta(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv); +unsigned int nfp_bpf_ctrl_cmsg_min_mtu(struct nfp_app_bpf *bpf); unsigned int nfp_bpf_ctrl_cmsg_mtu(struct nfp_app_bpf *bpf); +unsigned int nfp_bpf_ctrl_cmsg_cache_cnt(struct nfp_app_bpf *bpf); long long int nfp_bpf_ctrl_alloc_map(struct nfp_app_bpf *bpf, struct bpf_map *map); void diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 39c9fec222b4..88fab6a82acf 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -385,6 +385,7 @@ nfp_bpf_map_alloc(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap) offmap->dev_priv = nfp_map; nfp_map->offmap = offmap; nfp_map->bpf = bpf; + spin_lock_init(&nfp_map->cache_lock); res = nfp_bpf_ctrl_alloc_map(bpf, &offmap->map); if (res < 0) { @@ -407,6 +408,8 @@ nfp_bpf_map_free(struct nfp_app_bpf *bpf, struct bpf_offloaded_map *offmap) struct nfp_bpf_map *nfp_map = offmap->dev_priv; nfp_bpf_ctrl_free_map(bpf, nfp_map); + dev_consume_skb_any(nfp_map->cache); + WARN_ON_ONCE(nfp_map->cache_blockers); list_del_init(&nfp_map->l); bpf->map_elems_in_use -= offmap->map.max_entries; bpf->maps_in_use--; diff --git a/drivers/net/ethernet/netronome/nfp/devlink_param.c b/drivers/net/ethernet/netronome/nfp/devlink_param.c new file mode 100644 index 000000000000..36491835ac65 --- /dev/null +++ b/drivers/net/ethernet/netronome/nfp/devlink_param.c @@ -0,0 +1,255 @@ +// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) +/* Copyright (C) 2019 Netronome Systems, Inc. */ + +#include <net/devlink.h> + +#include "nfpcore/nfp.h" +#include "nfpcore/nfp_nsp.h" +#include "nfp_main.h" + +/** + * struct nfp_devlink_param_u8_arg - Devlink u8 parameter get/set arguments + * @hwinfo_name: HWinfo key name + * @default_hi_val: Default HWinfo value if HWinfo doesn't exist + * @invalid_dl_val: Devlink value to use if HWinfo is unknown/invalid. + * -errno if there is no unknown/invalid value available + * @hi_to_dl: HWinfo to devlink value mapping + * @dl_to_hi: Devlink to hwinfo value mapping + * @max_dl_val: Maximum devlink value supported, for validation only + * @max_hi_val: Maximum HWinfo value supported, for validation only + */ +struct nfp_devlink_param_u8_arg { + const char *hwinfo_name; + const char *default_hi_val; + int invalid_dl_val; + u8 hi_to_dl[4]; + u8 dl_to_hi[4]; + u8 max_dl_val; + u8 max_hi_val; +}; + +static const struct nfp_devlink_param_u8_arg nfp_devlink_u8_args[] = { + [DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY] = { + .hwinfo_name = "app_fw_from_flash", + .default_hi_val = NFP_NSP_APP_FW_LOAD_DEFAULT, + .invalid_dl_val = + DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_UNKNOWN, + .hi_to_dl = { + [NFP_NSP_APP_FW_LOAD_DISK] = + DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DISK, + [NFP_NSP_APP_FW_LOAD_FLASH] = + DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH, + [NFP_NSP_APP_FW_LOAD_PREF] = + DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER, + }, + .dl_to_hi = { + [DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DRIVER] = + NFP_NSP_APP_FW_LOAD_PREF, + [DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH] = + NFP_NSP_APP_FW_LOAD_FLASH, + [DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DISK] = + NFP_NSP_APP_FW_LOAD_DISK, + }, + .max_dl_val = DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DISK, + .max_hi_val = NFP_NSP_APP_FW_LOAD_PREF, + }, + [DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE] = { + .hwinfo_name = "abi_drv_reset", + .default_hi_val = NFP_NSP_DRV_RESET_DEFAULT, + .invalid_dl_val = + DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_UNKNOWN, + .hi_to_dl = { + [NFP_NSP_DRV_RESET_ALWAYS] = + DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_ALWAYS, + [NFP_NSP_DRV_RESET_NEVER] = + DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_NEVER, + [NFP_NSP_DRV_RESET_DISK] = + DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_DISK, + }, + .dl_to_hi = { + [DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_ALWAYS] = + NFP_NSP_DRV_RESET_ALWAYS, + [DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_NEVER] = + NFP_NSP_DRV_RESET_NEVER, + [DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_DISK] = + NFP_NSP_DRV_RESET_DISK, + }, + .max_dl_val = DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_DISK, + .max_hi_val = NFP_NSP_DRV_RESET_NEVER, + } +}; + +static int +nfp_devlink_param_u8_get(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + const struct nfp_devlink_param_u8_arg *arg; + struct nfp_pf *pf = devlink_priv(devlink); + struct nfp_nsp *nsp; + char hwinfo[32]; + long value; + int err; + + if (id >= ARRAY_SIZE(nfp_devlink_u8_args)) + return -EOPNOTSUPP; + + arg = &nfp_devlink_u8_args[id]; + + nsp = nfp_nsp_open(pf->cpp); + if (IS_ERR(nsp)) { + err = PTR_ERR(nsp); + nfp_warn(pf->cpp, "can't access NSP: %d\n", err); + return err; + } + + snprintf(hwinfo, sizeof(hwinfo), arg->hwinfo_name); + err = nfp_nsp_hwinfo_lookup_optional(nsp, hwinfo, sizeof(hwinfo), + arg->default_hi_val); + if (err) { + nfp_warn(pf->cpp, "HWinfo lookup failed: %d\n", err); + goto exit_close_nsp; + } + + err = kstrtol(hwinfo, 0, &value); + if (err || value < 0 || value > arg->max_hi_val) { + nfp_warn(pf->cpp, "HWinfo '%s' value %li invalid\n", + arg->hwinfo_name, value); + + if (arg->invalid_dl_val >= 0) + ctx->val.vu8 = arg->invalid_dl_val; + else + err = arg->invalid_dl_val; + + goto exit_close_nsp; + } + + ctx->val.vu8 = arg->hi_to_dl[value]; + +exit_close_nsp: + nfp_nsp_close(nsp); + return err; +} + +static int +nfp_devlink_param_u8_set(struct devlink *devlink, u32 id, + struct devlink_param_gset_ctx *ctx) +{ + const struct nfp_devlink_param_u8_arg *arg; + struct nfp_pf *pf = devlink_priv(devlink); + struct nfp_nsp *nsp; + char hwinfo[32]; + int err; + + if (id >= ARRAY_SIZE(nfp_devlink_u8_args)) + return -EOPNOTSUPP; + + arg = &nfp_devlink_u8_args[id]; + + nsp = nfp_nsp_open(pf->cpp); + if (IS_ERR(nsp)) { + err = PTR_ERR(nsp); + nfp_warn(pf->cpp, "can't access NSP: %d\n", err); + return err; + } + + /* Note the value has already been validated. */ + snprintf(hwinfo, sizeof(hwinfo), "%s=%u", + arg->hwinfo_name, arg->dl_to_hi[ctx->val.vu8]); + err = nfp_nsp_hwinfo_set(nsp, hwinfo, sizeof(hwinfo)); + if (err) { + nfp_warn(pf->cpp, "HWinfo set failed: %d\n", err); + goto exit_close_nsp; + } + +exit_close_nsp: + nfp_nsp_close(nsp); + return err; +} + +static int +nfp_devlink_param_u8_validate(struct devlink *devlink, u32 id, + union devlink_param_value val, + struct netlink_ext_ack *extack) +{ + const struct nfp_devlink_param_u8_arg *arg; + + if (id >= ARRAY_SIZE(nfp_devlink_u8_args)) + return -EOPNOTSUPP; + + arg = &nfp_devlink_u8_args[id]; + + if (val.vu8 > arg->max_dl_val) { + NL_SET_ERR_MSG_MOD(extack, "parameter out of range"); + return -EINVAL; + } + + if (val.vu8 == arg->invalid_dl_val) { + NL_SET_ERR_MSG_MOD(extack, "unknown/invalid value specified"); + return -EINVAL; + } + + return 0; +} + +static const struct devlink_param nfp_devlink_params[] = { + DEVLINK_PARAM_GENERIC(FW_LOAD_POLICY, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + nfp_devlink_param_u8_get, + nfp_devlink_param_u8_set, + nfp_devlink_param_u8_validate), + DEVLINK_PARAM_GENERIC(RESET_DEV_ON_DRV_PROBE, + BIT(DEVLINK_PARAM_CMODE_PERMANENT), + nfp_devlink_param_u8_get, + nfp_devlink_param_u8_set, + nfp_devlink_param_u8_validate), +}; + +static int nfp_devlink_supports_params(struct nfp_pf *pf) +{ + struct nfp_nsp *nsp; + bool supported; + int err; + + nsp = nfp_nsp_open(pf->cpp); + if (IS_ERR(nsp)) { + err = PTR_ERR(nsp); + dev_err(&pf->pdev->dev, "Failed to access the NSP: %d\n", err); + return err; + } + + supported = nfp_nsp_has_hwinfo_lookup(nsp) && + nfp_nsp_has_hwinfo_set(nsp); + + nfp_nsp_close(nsp); + return supported; +} + +int nfp_devlink_params_register(struct nfp_pf *pf) +{ + struct devlink *devlink = priv_to_devlink(pf); + int err; + + err = nfp_devlink_supports_params(pf); + if (err <= 0) + return err; + + err = devlink_params_register(devlink, nfp_devlink_params, + ARRAY_SIZE(nfp_devlink_params)); + if (err) + return err; + + devlink_params_publish(devlink); + return 0; +} + +void nfp_devlink_params_unregister(struct nfp_pf *pf) +{ + int err; + + err = nfp_devlink_supports_params(pf); + if (err <= 0) + return; + + devlink_params_unregister(priv_to_devlink(pf), nfp_devlink_params, + ARRAY_SIZE(nfp_devlink_params)); +} diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c index 5a54fe848de4..1b019fdfcd97 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/action.c +++ b/drivers/net/ethernet/netronome/nfp/flower/action.c @@ -2,10 +2,12 @@ /* Copyright (C) 2017-2018 Netronome Systems, Inc. */ #include <linux/bitfield.h> +#include <linux/mpls.h> #include <net/pkt_cls.h> #include <net/tc_act/tc_csum.h> #include <net/tc_act/tc_gact.h> #include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_mpls.h> #include <net/tc_act/tc_pedit.h> #include <net/tc_act/tc_vlan.h> #include <net/tc_act/tc_tunnel_key.h> @@ -25,6 +27,80 @@ NFP_FL_TUNNEL_KEY | \ NFP_FL_TUNNEL_GENEVE_OPT) +static int +nfp_fl_push_mpls(struct nfp_fl_push_mpls *push_mpls, + const struct flow_action_entry *act, + struct netlink_ext_ack *extack) +{ + size_t act_size = sizeof(struct nfp_fl_push_mpls); + u32 mpls_lse = 0; + + push_mpls->head.jump_id = NFP_FL_ACTION_OPCODE_PUSH_MPLS; + push_mpls->head.len_lw = act_size >> NFP_FL_LW_SIZ; + + /* BOS is optional in the TC action but required for offload. */ + if (act->mpls_push.bos != ACT_MPLS_BOS_NOT_SET) { + mpls_lse |= act->mpls_push.bos << MPLS_LS_S_SHIFT; + } else { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: BOS field must explicitly be set for MPLS push"); + return -EOPNOTSUPP; + } + + /* Leave MPLS TC as a default value of 0 if not explicitly set. */ + if (act->mpls_push.tc != ACT_MPLS_TC_NOT_SET) + mpls_lse |= act->mpls_push.tc << MPLS_LS_TC_SHIFT; + + /* Proto, label and TTL are enforced and verified for MPLS push. */ + mpls_lse |= act->mpls_push.label << MPLS_LS_LABEL_SHIFT; + mpls_lse |= act->mpls_push.ttl << MPLS_LS_TTL_SHIFT; + push_mpls->ethtype = act->mpls_push.proto; + push_mpls->lse = cpu_to_be32(mpls_lse); + + return 0; +} + +static void +nfp_fl_pop_mpls(struct nfp_fl_pop_mpls *pop_mpls, + const struct flow_action_entry *act) +{ + size_t act_size = sizeof(struct nfp_fl_pop_mpls); + + pop_mpls->head.jump_id = NFP_FL_ACTION_OPCODE_POP_MPLS; + pop_mpls->head.len_lw = act_size >> NFP_FL_LW_SIZ; + pop_mpls->ethtype = act->mpls_pop.proto; +} + +static void +nfp_fl_set_mpls(struct nfp_fl_set_mpls *set_mpls, + const struct flow_action_entry *act) +{ + size_t act_size = sizeof(struct nfp_fl_set_mpls); + u32 mpls_lse = 0, mpls_mask = 0; + + set_mpls->head.jump_id = NFP_FL_ACTION_OPCODE_SET_MPLS; + set_mpls->head.len_lw = act_size >> NFP_FL_LW_SIZ; + + if (act->mpls_mangle.label != ACT_MPLS_LABEL_NOT_SET) { + mpls_lse |= act->mpls_mangle.label << MPLS_LS_LABEL_SHIFT; + mpls_mask |= MPLS_LS_LABEL_MASK; + } + if (act->mpls_mangle.tc != ACT_MPLS_TC_NOT_SET) { + mpls_lse |= act->mpls_mangle.tc << MPLS_LS_TC_SHIFT; + mpls_mask |= MPLS_LS_TC_MASK; + } + if (act->mpls_mangle.bos != ACT_MPLS_BOS_NOT_SET) { + mpls_lse |= act->mpls_mangle.bos << MPLS_LS_S_SHIFT; + mpls_mask |= MPLS_LS_S_MASK; + } + if (act->mpls_mangle.ttl) { + mpls_lse |= act->mpls_mangle.ttl << MPLS_LS_TTL_SHIFT; + mpls_mask |= MPLS_LS_TTL_MASK; + } + + set_mpls->lse = cpu_to_be32(mpls_lse); + set_mpls->lse_mask = cpu_to_be32(mpls_mask); +} + static void nfp_fl_pop_vlan(struct nfp_fl_pop_vlan *pop_vlan) { size_t act_size = sizeof(struct nfp_fl_pop_vlan); @@ -97,7 +173,7 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, struct nfp_fl_payload *nfp_flow, bool last, struct net_device *in_dev, enum nfp_flower_tun_type tun_type, int *tun_out_cnt, - struct netlink_ext_ack *extack) + bool pkt_host, struct netlink_ext_ack *extack) { size_t act_size = sizeof(struct nfp_fl_output); struct nfp_flower_priv *priv = app->priv; @@ -142,6 +218,20 @@ nfp_fl_output(struct nfp_app *app, struct nfp_fl_output *output, return gid; } output->port = cpu_to_be32(NFP_FL_LAG_OUT | gid); + } else if (nfp_flower_internal_port_can_offload(app, out_dev)) { + if (!(priv->flower_ext_feats & NFP_FL_FEATS_PRE_TUN_RULES)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pre-tunnel rules not supported in loaded firmware"); + return -EOPNOTSUPP; + } + + if (nfp_flow->pre_tun_rule.dev || !pkt_host) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: pre-tunnel rules require single egress dev and ptype HOST action"); + return -EOPNOTSUPP; + } + + nfp_flow->pre_tun_rule.dev = out_dev; + + return 0; } else { /* Set action output parameters. */ output->flags = cpu_to_be16(tmp_flags); @@ -809,7 +899,7 @@ nfp_flower_output_action(struct nfp_app *app, struct nfp_fl_payload *nfp_fl, int *a_len, struct net_device *netdev, bool last, enum nfp_flower_tun_type *tun_type, int *tun_out_cnt, - int *out_cnt, u32 *csum_updated, + int *out_cnt, u32 *csum_updated, bool pkt_host, struct netlink_ext_ack *extack) { struct nfp_flower_priv *priv = app->priv; @@ -831,7 +921,7 @@ nfp_flower_output_action(struct nfp_app *app, output = (struct nfp_fl_output *)&nfp_fl->action_data[*a_len]; err = nfp_fl_output(app, output, act, nfp_fl, last, netdev, *tun_type, - tun_out_cnt, extack); + tun_out_cnt, pkt_host, extack); if (err) return err; @@ -863,30 +953,37 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act, struct net_device *netdev, enum nfp_flower_tun_type *tun_type, int *tun_out_cnt, int *out_cnt, u32 *csum_updated, - struct nfp_flower_pedit_acts *set_act, + struct nfp_flower_pedit_acts *set_act, bool *pkt_host, struct netlink_ext_ack *extack, int act_idx) { struct nfp_fl_set_ipv4_tun *set_tun; struct nfp_fl_pre_tunnel *pre_tun; struct nfp_fl_push_vlan *psh_v; + struct nfp_fl_push_mpls *psh_m; struct nfp_fl_pop_vlan *pop_v; + struct nfp_fl_pop_mpls *pop_m; + struct nfp_fl_set_mpls *set_m; int err; switch (act->id) { case FLOW_ACTION_DROP: nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_DROP); break; + case FLOW_ACTION_REDIRECT_INGRESS: case FLOW_ACTION_REDIRECT: err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev, true, tun_type, tun_out_cnt, - out_cnt, csum_updated, extack); + out_cnt, csum_updated, *pkt_host, + extack); if (err) return err; break; + case FLOW_ACTION_MIRRED_INGRESS: case FLOW_ACTION_MIRRED: err = nfp_flower_output_action(app, act, nfp_fl, a_len, netdev, false, tun_type, tun_out_cnt, - out_cnt, csum_updated, extack); + out_cnt, csum_updated, *pkt_host, + extack); if (err) return err; break; @@ -975,6 +1072,54 @@ nfp_flower_loop_action(struct nfp_app *app, const struct flow_action_entry *act, */ *csum_updated &= ~act->csum_flags; break; + case FLOW_ACTION_MPLS_PUSH: + if (*a_len + + sizeof(struct nfp_fl_push_mpls) > NFP_FL_MAX_A_SIZ) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at push MPLS"); + return -EOPNOTSUPP; + } + + psh_m = (struct nfp_fl_push_mpls *)&nfp_fl->action_data[*a_len]; + nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL); + + err = nfp_fl_push_mpls(psh_m, act, extack); + if (err) + return err; + *a_len += sizeof(struct nfp_fl_push_mpls); + break; + case FLOW_ACTION_MPLS_POP: + if (*a_len + + sizeof(struct nfp_fl_pop_mpls) > NFP_FL_MAX_A_SIZ) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at pop MPLS"); + return -EOPNOTSUPP; + } + + pop_m = (struct nfp_fl_pop_mpls *)&nfp_fl->action_data[*a_len]; + nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL); + + nfp_fl_pop_mpls(pop_m, act); + *a_len += sizeof(struct nfp_fl_pop_mpls); + break; + case FLOW_ACTION_MPLS_MANGLE: + if (*a_len + + sizeof(struct nfp_fl_set_mpls) > NFP_FL_MAX_A_SIZ) { + NL_SET_ERR_MSG_MOD(extack, "unsupported offload: maximum allowed action list size exceeded at set MPLS"); + return -EOPNOTSUPP; + } + + set_m = (struct nfp_fl_set_mpls *)&nfp_fl->action_data[*a_len]; + nfp_fl->meta.shortcut = cpu_to_be32(NFP_FL_SC_ACT_NULL); + + nfp_fl_set_mpls(set_m, act); + *a_len += sizeof(struct nfp_fl_set_mpls); + break; + case FLOW_ACTION_PTYPE: + /* TC ptype skbedit sets PACKET_HOST for ingress redirect. */ + if (act->ptype != PACKET_HOST) + return -EOPNOTSUPP; + + *pkt_host = true; + break; default: /* Currently we do not handle any other actions. */ NL_SET_ERR_MSG_MOD(extack, "unsupported offload: unsupported action in action list"); @@ -1030,6 +1175,7 @@ int nfp_flower_compile_action(struct nfp_app *app, struct nfp_flower_pedit_acts set_act; enum nfp_flower_tun_type tun_type; struct flow_action_entry *act; + bool pkt_host = false; u32 csum_updated = 0; memset(nfp_flow->action_data, 0, NFP_FL_MAX_A_SIZ); @@ -1046,7 +1192,7 @@ int nfp_flower_compile_action(struct nfp_app *app, err = nfp_flower_loop_action(app, act, flow, nfp_flow, &act_len, netdev, &tun_type, &tun_out_cnt, &out_cnt, &csum_updated, - &set_act, extack, i); + &set_act, &pkt_host, extack, i); if (err) return err; act_cnt++; diff --git a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h index 0f1706ae5bfc..7eb2ec8969c3 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/cmsg.h +++ b/drivers/net/ethernet/netronome/nfp/flower/cmsg.h @@ -68,8 +68,11 @@ #define NFP_FL_ACTION_OPCODE_OUTPUT 0 #define NFP_FL_ACTION_OPCODE_PUSH_VLAN 1 #define NFP_FL_ACTION_OPCODE_POP_VLAN 2 +#define NFP_FL_ACTION_OPCODE_PUSH_MPLS 3 +#define NFP_FL_ACTION_OPCODE_POP_MPLS 4 #define NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL 6 #define NFP_FL_ACTION_OPCODE_SET_ETHERNET 7 +#define NFP_FL_ACTION_OPCODE_SET_MPLS 8 #define NFP_FL_ACTION_OPCODE_SET_IPV4_ADDRS 9 #define NFP_FL_ACTION_OPCODE_SET_IPV4_TTL_TOS 10 #define NFP_FL_ACTION_OPCODE_SET_IPV6_SRC 11 @@ -217,7 +220,8 @@ struct nfp_fl_set_ipv4_tun { __be16 tun_flags; u8 ttl; u8 tos; - __be32 extra; + __be16 outer_vlan_tpid; + __be16 outer_vlan_tci; u8 tun_len; u8 res2; __be16 tun_proto; @@ -232,6 +236,24 @@ struct nfp_fl_push_geneve { u8 opt_data[]; }; +struct nfp_fl_push_mpls { + struct nfp_fl_act_head head; + __be16 ethtype; + __be32 lse; +}; + +struct nfp_fl_pop_mpls { + struct nfp_fl_act_head head; + __be16 ethtype; +}; + +struct nfp_fl_set_mpls { + struct nfp_fl_act_head head; + __be16 reserved; + __be32 lse_mask; + __be32 lse; +}; + /* Metadata with L2 (1W/4B) * ---------------------------------------------------------------- * 3 2 1 @@ -462,6 +484,7 @@ enum nfp_flower_cmsg_type_port { NFP_FLOWER_CMSG_TYPE_QOS_MOD = 18, NFP_FLOWER_CMSG_TYPE_QOS_DEL = 19, NFP_FLOWER_CMSG_TYPE_QOS_STATS = 20, + NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE = 21, NFP_FLOWER_CMSG_TYPE_MAX = 32, }; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.c b/drivers/net/ethernet/netronome/nfp/flower/main.c index eb846133943b..7a20447cca19 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.c +++ b/drivers/net/ethernet/netronome/nfp/flower/main.c @@ -781,6 +781,7 @@ static int nfp_flower_init(struct nfp_app *app) INIT_LIST_HEAD(&app_priv->indr_block_cb_priv); INIT_LIST_HEAD(&app_priv->non_repr_priv); + app_priv->pre_tun_rule_cnt = 0; return 0; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index af9441d5787f..31d94592a7c0 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -42,6 +42,7 @@ struct nfp_app; #define NFP_FL_FEATS_VLAN_PCP BIT(3) #define NFP_FL_FEATS_VF_RLIM BIT(4) #define NFP_FL_FEATS_FLOW_MOD BIT(5) +#define NFP_FL_FEATS_PRE_TUN_RULES BIT(6) #define NFP_FL_FEATS_FLOW_MERGE BIT(30) #define NFP_FL_FEATS_LAG BIT(31) @@ -162,6 +163,7 @@ struct nfp_fl_internal_ports { * @qos_stats_work: Workqueue for qos stats processing * @qos_rate_limiters: Current active qos rate limiters * @qos_stats_lock: Lock on qos stats updates + * @pre_tun_rule_cnt: Number of pre-tunnel rules offloaded */ struct nfp_flower_priv { struct nfp_app *app; @@ -193,6 +195,7 @@ struct nfp_flower_priv { struct delayed_work qos_stats_work; unsigned int qos_rate_limiters; spinlock_t qos_stats_lock; /* Protect the qos stats */ + int pre_tun_rule_cnt; }; /** @@ -218,6 +221,7 @@ struct nfp_fl_qos { * @block_shared: Flag indicating if offload applies to shared blocks * @mac_list: List entry of reprs that share the same offloaded MAC * @qos_table: Stored info on filters implementing qos + * @on_bridge: Indicates if the repr is attached to a bridge */ struct nfp_flower_repr_priv { struct nfp_repr *nfp_repr; @@ -227,6 +231,7 @@ struct nfp_flower_repr_priv { bool block_shared; struct list_head mac_list; struct nfp_fl_qos qos_table; + bool on_bridge; }; /** @@ -280,6 +285,11 @@ struct nfp_fl_payload { char *action_data; struct list_head linked_flows; bool in_hw; + struct { + struct net_device *dev; + __be16 vlan_tci; + __be16 port_idx; + } pre_tun_rule; }; struct nfp_fl_payload_link { @@ -333,6 +343,11 @@ static inline bool nfp_flower_is_merge_flow(struct nfp_fl_payload *flow_pay) return flow_pay->tc_flower_cookie == (unsigned long)flow_pay; } +static inline bool nfp_flower_is_supported_bridge(struct net_device *netdev) +{ + return netif_is_ovs_master(netdev); +} + int nfp_flower_metadata_init(struct nfp_app *app, u64 host_ctx_count, unsigned int host_ctx_split); void nfp_flower_metadata_cleanup(struct nfp_app *app); @@ -415,4 +430,8 @@ void nfp_flower_non_repr_priv_put(struct nfp_app *app, struct net_device *netdev); u32 nfp_flower_get_port_id_from_netdev(struct nfp_app *app, struct net_device *netdev); +int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, + struct nfp_fl_payload *flow); +int nfp_flower_xmit_pre_tun_del_flow(struct nfp_app *app, + struct nfp_fl_payload *flow); #endif diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 457bdc60f3ee..987ae221f6be 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -61,6 +61,11 @@ NFP_FLOWER_LAYER_IPV4 | \ NFP_FLOWER_LAYER_IPV6) +#define NFP_FLOWER_PRE_TUN_RULE_FIELDS \ + (NFP_FLOWER_LAYER_PORT | \ + NFP_FLOWER_LAYER_MAC | \ + NFP_FLOWER_LAYER_IPV4) + struct nfp_flower_merge_check { union { struct { @@ -489,6 +494,7 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer) flow_pay->meta.flags = 0; INIT_LIST_HEAD(&flow_pay->linked_flows); flow_pay->in_hw = false; + flow_pay->pre_tun_rule.dev = NULL; return flow_pay; @@ -732,28 +738,62 @@ nfp_flower_copy_pre_actions(char *act_dst, char *act_src, int len, return act_off; } -static int nfp_fl_verify_post_tun_acts(char *acts, int len) +static int +nfp_fl_verify_post_tun_acts(char *acts, int len, struct nfp_fl_push_vlan **vlan) { struct nfp_fl_act_head *a; unsigned int act_off = 0; while (act_off < len) { a = (struct nfp_fl_act_head *)&acts[act_off]; - if (a->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) + + if (a->jump_id == NFP_FL_ACTION_OPCODE_PUSH_VLAN && !act_off) + *vlan = (struct nfp_fl_push_vlan *)a; + else if (a->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) return -EOPNOTSUPP; act_off += a->len_lw << NFP_FL_LW_SIZ; } + /* Ensure any VLAN push also has an egress action. */ + if (*vlan && act_off <= sizeof(struct nfp_fl_push_vlan)) + return -EOPNOTSUPP; + return 0; } static int +nfp_fl_push_vlan_after_tun(char *acts, int len, struct nfp_fl_push_vlan *vlan) +{ + struct nfp_fl_set_ipv4_tun *tun; + struct nfp_fl_act_head *a; + unsigned int act_off = 0; + + while (act_off < len) { + a = (struct nfp_fl_act_head *)&acts[act_off]; + + if (a->jump_id == NFP_FL_ACTION_OPCODE_SET_IPV4_TUNNEL) { + tun = (struct nfp_fl_set_ipv4_tun *)a; + tun->outer_vlan_tpid = vlan->vlan_tpid; + tun->outer_vlan_tci = vlan->vlan_tci; + + return 0; + } + + act_off += a->len_lw << NFP_FL_LW_SIZ; + } + + /* Return error if no tunnel action is found. */ + return -EOPNOTSUPP; +} + +static int nfp_flower_merge_action(struct nfp_fl_payload *sub_flow1, struct nfp_fl_payload *sub_flow2, struct nfp_fl_payload *merge_flow) { unsigned int sub1_act_len, sub2_act_len, pre_off1, pre_off2; + struct nfp_fl_push_vlan *post_tun_push_vlan = NULL; bool tunnel_act = false; char *merge_act; int err; @@ -790,18 +830,36 @@ nfp_flower_merge_action(struct nfp_fl_payload *sub_flow1, sub2_act_len -= pre_off2; /* FW does a tunnel push when egressing, therefore, if sub_flow 1 pushes - * a tunnel, sub_flow 2 can only have output actions for a valid merge. + * a tunnel, there are restrictions on what sub_flow 2 actions lead to a + * valid merge. */ if (tunnel_act) { char *post_tun_acts = &sub_flow2->action_data[pre_off2]; - err = nfp_fl_verify_post_tun_acts(post_tun_acts, sub2_act_len); + err = nfp_fl_verify_post_tun_acts(post_tun_acts, sub2_act_len, + &post_tun_push_vlan); if (err) return err; + + if (post_tun_push_vlan) { + pre_off2 += sizeof(*post_tun_push_vlan); + sub2_act_len -= sizeof(*post_tun_push_vlan); + } } /* Copy remaining actions from sub_flows 1 and 2. */ memcpy(merge_act, sub_flow1->action_data + pre_off1, sub1_act_len); + + if (post_tun_push_vlan) { + /* Update tunnel action in merge to include VLAN push. */ + err = nfp_fl_push_vlan_after_tun(merge_act, sub1_act_len, + post_tun_push_vlan); + if (err) + return err; + + merge_flow->meta.act_len -= sizeof(*post_tun_push_vlan); + } + merge_act += sub1_act_len; memcpy(merge_act, sub_flow2->action_data + pre_off2, sub2_act_len); @@ -945,6 +1003,106 @@ err_destroy_merge_flow: } /** + * nfp_flower_validate_pre_tun_rule() + * @app: Pointer to the APP handle + * @flow: Pointer to NFP flow representation of rule + * @extack: Netlink extended ACK report + * + * Verifies the flow as a pre-tunnel rule. + * + * Return: negative value on error, 0 if verified. + */ +static int +nfp_flower_validate_pre_tun_rule(struct nfp_app *app, + struct nfp_fl_payload *flow, + struct netlink_ext_ack *extack) +{ + struct nfp_flower_meta_tci *meta_tci; + struct nfp_flower_mac_mpls *mac; + struct nfp_fl_act_head *act; + u8 *mask = flow->mask_data; + bool vlan = false; + int act_offset; + u8 key_layer; + + meta_tci = (struct nfp_flower_meta_tci *)flow->unmasked_data; + if (meta_tci->tci & cpu_to_be16(NFP_FLOWER_MASK_VLAN_PRESENT)) { + u16 vlan_tci = be16_to_cpu(meta_tci->tci); + + vlan_tci &= ~NFP_FLOWER_MASK_VLAN_PRESENT; + flow->pre_tun_rule.vlan_tci = cpu_to_be16(vlan_tci); + vlan = true; + } else { + flow->pre_tun_rule.vlan_tci = cpu_to_be16(0xffff); + } + + key_layer = meta_tci->nfp_flow_key_layer; + if (key_layer & ~NFP_FLOWER_PRE_TUN_RULE_FIELDS) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: too many match fields"); + return -EOPNOTSUPP; + } + + if (!(key_layer & NFP_FLOWER_LAYER_MAC)) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: MAC fields match required"); + return -EOPNOTSUPP; + } + + /* Skip fields known to exist. */ + mask += sizeof(struct nfp_flower_meta_tci); + mask += sizeof(struct nfp_flower_in_port); + + /* Ensure destination MAC address is fully matched. */ + mac = (struct nfp_flower_mac_mpls *)mask; + if (!is_broadcast_ether_addr(&mac->mac_dst[0])) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: dest MAC field must not be masked"); + return -EOPNOTSUPP; + } + + if (key_layer & NFP_FLOWER_LAYER_IPV4) { + int ip_flags = offsetof(struct nfp_flower_ipv4, ip_ext.flags); + int ip_proto = offsetof(struct nfp_flower_ipv4, ip_ext.proto); + int i; + + mask += sizeof(struct nfp_flower_mac_mpls); + + /* Ensure proto and flags are the only IP layer fields. */ + for (i = 0; i < sizeof(struct nfp_flower_ipv4); i++) + if (mask[i] && i != ip_flags && i != ip_proto) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: only flags and proto can be matched in ip header"); + return -EOPNOTSUPP; + } + } + + /* Action must be a single egress or pop_vlan and egress. */ + act_offset = 0; + act = (struct nfp_fl_act_head *)&flow->action_data[act_offset]; + if (vlan) { + if (act->jump_id != NFP_FL_ACTION_OPCODE_POP_VLAN) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: match on VLAN must have VLAN pop as first action"); + return -EOPNOTSUPP; + } + + act_offset += act->len_lw << NFP_FL_LW_SIZ; + act = (struct nfp_fl_act_head *)&flow->action_data[act_offset]; + } + + if (act->jump_id != NFP_FL_ACTION_OPCODE_OUTPUT) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: non egress action detected where egress was expected"); + return -EOPNOTSUPP; + } + + act_offset += act->len_lw << NFP_FL_LW_SIZ; + + /* Ensure there are no more actions after egress. */ + if (act_offset != flow->meta.act_len) { + NL_SET_ERR_MSG_MOD(extack, "unsupported pre-tunnel rule: egress is not the last action"); + return -EOPNOTSUPP; + } + + return 0; +} + +/** * nfp_flower_add_offload() - Adds a new flow to hardware. * @app: Pointer to the APP handle * @netdev: netdev structure. @@ -994,6 +1152,12 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, if (err) goto err_destroy_flow; + if (flow_pay->pre_tun_rule.dev) { + err = nfp_flower_validate_pre_tun_rule(app, flow_pay, extack); + if (err) + goto err_destroy_flow; + } + err = nfp_compile_flow_metadata(app, flow, flow_pay, netdev, extack); if (err) goto err_destroy_flow; @@ -1006,8 +1170,11 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, goto err_release_metadata; } - err = nfp_flower_xmit_flow(app, flow_pay, - NFP_FLOWER_CMSG_TYPE_FLOW_ADD); + if (flow_pay->pre_tun_rule.dev) + err = nfp_flower_xmit_pre_tun_flow(app, flow_pay); + else + err = nfp_flower_xmit_flow(app, flow_pay, + NFP_FLOWER_CMSG_TYPE_FLOW_ADD); if (err) goto err_remove_rhash; @@ -1149,8 +1316,11 @@ nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev, goto err_free_merge_flow; } - err = nfp_flower_xmit_flow(app, nfp_flow, - NFP_FLOWER_CMSG_TYPE_FLOW_DEL); + if (nfp_flow->pre_tun_rule.dev) + err = nfp_flower_xmit_pre_tun_del_flow(app, nfp_flow); + else + err = nfp_flower_xmit_flow(app, nfp_flow, + NFP_FLOWER_CMSG_TYPE_FLOW_DEL); /* Fall through on error. */ err_free_merge_flow: @@ -1487,16 +1657,17 @@ int nfp_flower_reg_indir_block_handler(struct nfp_app *app, return NOTIFY_OK; if (event == NETDEV_REGISTER) { - err = __tc_indr_block_cb_register(netdev, app, - nfp_flower_indr_setup_tc_cb, - app); + err = __flow_indr_block_cb_register(netdev, app, + nfp_flower_indr_setup_tc_cb, + app); if (err) nfp_flower_cmsg_warn(app, "Indirect block reg failed - %s\n", netdev->name); } else if (event == NETDEV_UNREGISTER) { - __tc_indr_block_cb_unregister(netdev, - nfp_flower_indr_setup_tc_cb, app); + __flow_indr_block_cb_unregister(netdev, + nfp_flower_indr_setup_tc_cb, + app); } return NOTIFY_OK; diff --git a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c index f0ee982eb1b5..2600ce476d6b 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c +++ b/drivers/net/ethernet/netronome/nfp/flower/tunnel_conf.c @@ -15,6 +15,24 @@ #define NFP_FL_MAX_ROUTES 32 +#define NFP_TUN_PRE_TUN_RULE_LIMIT 32 +#define NFP_TUN_PRE_TUN_RULE_DEL 0x1 +#define NFP_TUN_PRE_TUN_IDX_BIT 0x8 + +/** + * struct nfp_tun_pre_run_rule - rule matched before decap + * @flags: options for the rule offset + * @port_idx: index of destination MAC address for the rule + * @vlan_tci: VLAN info associated with MAC + * @host_ctx_id: stats context of rule to update + */ +struct nfp_tun_pre_tun_rule { + __be32 flags; + __be16 port_idx; + __be16 vlan_tci; + __be32 host_ctx_id; +}; + /** * struct nfp_tun_active_tuns - periodic message of active tunnels * @seq: sequence number of the message @@ -124,11 +142,12 @@ enum nfp_flower_mac_offload_cmd { /** * struct nfp_tun_offloaded_mac - hashtable entry for an offloaded MAC - * @ht_node: Hashtable entry - * @addr: Offloaded MAC address - * @index: Offloaded index for given MAC address - * @ref_count: Number of devs using this MAC address - * @repr_list: List of reprs sharing this MAC address + * @ht_node: Hashtable entry + * @addr: Offloaded MAC address + * @index: Offloaded index for given MAC address + * @ref_count: Number of devs using this MAC address + * @repr_list: List of reprs sharing this MAC address + * @bridge_count: Number of bridge/internal devs with MAC */ struct nfp_tun_offloaded_mac { struct rhash_head ht_node; @@ -136,6 +155,7 @@ struct nfp_tun_offloaded_mac { u16 index; int ref_count; struct list_head repr_list; + int bridge_count; }; static const struct rhashtable_params offloaded_macs_params = { @@ -556,6 +576,8 @@ nfp_tunnel_offloaded_macs_inc_ref_and_link(struct nfp_tun_offloaded_mac *entry, list_del(&repr_priv->mac_list); list_add_tail(&repr_priv->mac_list, &entry->repr_list); + } else if (nfp_flower_is_supported_bridge(netdev)) { + entry->bridge_count++; } entry->ref_count++; @@ -572,20 +594,35 @@ nfp_tunnel_add_shared_mac(struct nfp_app *app, struct net_device *netdev, entry = nfp_tunnel_lookup_offloaded_macs(app, netdev->dev_addr); if (entry && nfp_tunnel_is_mac_idx_global(entry->index)) { - nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, netdev, mod); - return 0; + if (entry->bridge_count || + !nfp_flower_is_supported_bridge(netdev)) { + nfp_tunnel_offloaded_macs_inc_ref_and_link(entry, + netdev, mod); + return 0; + } + + /* MAC is global but matches need to go to pre_tun table. */ + nfp_mac_idx = entry->index | NFP_TUN_PRE_TUN_IDX_BIT; } - /* Assign a global index if non-repr or MAC address is now shared. */ - if (entry || !port) { - ida_idx = ida_simple_get(&priv->tun.mac_off_ids, 0, - NFP_MAX_MAC_INDEX, GFP_KERNEL); - if (ida_idx < 0) - return ida_idx; + if (!nfp_mac_idx) { + /* Assign a global index if non-repr or MAC is now shared. */ + if (entry || !port) { + ida_idx = ida_simple_get(&priv->tun.mac_off_ids, 0, + NFP_MAX_MAC_INDEX, GFP_KERNEL); + if (ida_idx < 0) + return ida_idx; - nfp_mac_idx = nfp_tunnel_get_global_mac_idx_from_ida(ida_idx); - } else { - nfp_mac_idx = nfp_tunnel_get_mac_idx_from_phy_port_id(port); + nfp_mac_idx = + nfp_tunnel_get_global_mac_idx_from_ida(ida_idx); + + if (nfp_flower_is_supported_bridge(netdev)) + nfp_mac_idx |= NFP_TUN_PRE_TUN_IDX_BIT; + + } else { + nfp_mac_idx = + nfp_tunnel_get_mac_idx_from_phy_port_id(port); + } } if (!entry) { @@ -654,6 +691,25 @@ nfp_tunnel_del_shared_mac(struct nfp_app *app, struct net_device *netdev, list_del(&repr_priv->mac_list); } + if (nfp_flower_is_supported_bridge(netdev)) { + entry->bridge_count--; + + if (!entry->bridge_count && entry->ref_count) { + u16 nfp_mac_idx; + + nfp_mac_idx = entry->index & ~NFP_TUN_PRE_TUN_IDX_BIT; + if (__nfp_tunnel_offload_mac(app, mac, nfp_mac_idx, + false)) { + nfp_flower_cmsg_warn(app, "MAC offload index revert failed on %s.\n", + netdev_name(netdev)); + return 0; + } + + entry->index = nfp_mac_idx; + return 0; + } + } + /* If MAC is now used by 1 repr set the offloaded MAC index to port. */ if (entry->ref_count == 1 && list_is_singular(&entry->repr_list)) { u16 nfp_mac_idx; @@ -713,6 +769,9 @@ nfp_tunnel_offload_mac(struct nfp_app *app, struct net_device *netdev, return 0; repr_priv = repr->app_priv; + if (repr_priv->on_bridge) + return 0; + mac_offloaded = &repr_priv->mac_offloaded; off_mac = &repr_priv->offloaded_mac_addr[0]; port = nfp_repr_get_port_id(netdev); @@ -828,10 +887,119 @@ int nfp_tunnel_mac_event_handler(struct nfp_app *app, if (err) nfp_flower_cmsg_warn(app, "Failed to offload MAC change on %s.\n", netdev_name(netdev)); + } else if (event == NETDEV_CHANGEUPPER) { + /* If a repr is attached to a bridge then tunnel packets + * entering the physical port are directed through the bridge + * datapath and cannot be directly detunneled. Therefore, + * associated offloaded MACs and indexes should not be used + * by fw for detunneling. + */ + struct netdev_notifier_changeupper_info *info = ptr; + struct net_device *upper = info->upper_dev; + struct nfp_flower_repr_priv *repr_priv; + struct nfp_repr *repr; + + if (!nfp_netdev_is_nfp_repr(netdev) || + !nfp_flower_is_supported_bridge(upper)) + return NOTIFY_OK; + + repr = netdev_priv(netdev); + if (repr->app != app) + return NOTIFY_OK; + + repr_priv = repr->app_priv; + + if (info->linking) { + if (nfp_tunnel_offload_mac(app, netdev, + NFP_TUNNEL_MAC_OFFLOAD_DEL)) + nfp_flower_cmsg_warn(app, "Failed to delete offloaded MAC on %s.\n", + netdev_name(netdev)); + repr_priv->on_bridge = true; + } else { + repr_priv->on_bridge = false; + + if (!(netdev->flags & IFF_UP)) + return NOTIFY_OK; + + if (nfp_tunnel_offload_mac(app, netdev, + NFP_TUNNEL_MAC_OFFLOAD_ADD)) + nfp_flower_cmsg_warn(app, "Failed to offload MAC on %s.\n", + netdev_name(netdev)); + } } return NOTIFY_OK; } +int nfp_flower_xmit_pre_tun_flow(struct nfp_app *app, + struct nfp_fl_payload *flow) +{ + struct nfp_flower_priv *app_priv = app->priv; + struct nfp_tun_offloaded_mac *mac_entry; + struct nfp_tun_pre_tun_rule payload; + struct net_device *internal_dev; + int err; + + if (app_priv->pre_tun_rule_cnt == NFP_TUN_PRE_TUN_RULE_LIMIT) + return -ENOSPC; + + memset(&payload, 0, sizeof(struct nfp_tun_pre_tun_rule)); + + internal_dev = flow->pre_tun_rule.dev; + payload.vlan_tci = flow->pre_tun_rule.vlan_tci; + payload.host_ctx_id = flow->meta.host_ctx_id; + + /* Lookup MAC index for the pre-tunnel rule egress device. + * Note that because the device is always an internal port, it will + * have a constant global index so does not need to be tracked. + */ + mac_entry = nfp_tunnel_lookup_offloaded_macs(app, + internal_dev->dev_addr); + if (!mac_entry) + return -ENOENT; + + payload.port_idx = cpu_to_be16(mac_entry->index); + + /* Copy mac id and vlan to flow - dev may not exist at delete time. */ + flow->pre_tun_rule.vlan_tci = payload.vlan_tci; + flow->pre_tun_rule.port_idx = payload.port_idx; + + err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE, + sizeof(struct nfp_tun_pre_tun_rule), + (unsigned char *)&payload, GFP_KERNEL); + if (err) + return err; + + app_priv->pre_tun_rule_cnt++; + + return 0; +} + +int nfp_flower_xmit_pre_tun_del_flow(struct nfp_app *app, + struct nfp_fl_payload *flow) +{ + struct nfp_flower_priv *app_priv = app->priv; + struct nfp_tun_pre_tun_rule payload; + u32 tmp_flags = 0; + int err; + + memset(&payload, 0, sizeof(struct nfp_tun_pre_tun_rule)); + + tmp_flags |= NFP_TUN_PRE_TUN_RULE_DEL; + payload.flags = cpu_to_be32(tmp_flags); + payload.vlan_tci = flow->pre_tun_rule.vlan_tci; + payload.port_idx = flow->pre_tun_rule.port_idx; + + err = nfp_flower_xmit_tun_conf(app, NFP_FLOWER_CMSG_TYPE_PRE_TUN_RULE, + sizeof(struct nfp_tun_pre_tun_rule), + (unsigned char *)&payload, GFP_KERNEL); + if (err) + return err; + + app_priv->pre_tun_rule_cnt--; + + return 0; +} + int nfp_tunnel_config_start(struct nfp_app *app) { struct nfp_flower_priv *priv = app->priv; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index 60e57f08de80..4d282fc56009 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -352,7 +352,7 @@ nfp_net_fw_request(struct pci_dev *pdev, struct nfp_pf *pf, const char *name) err = request_firmware_direct(&fw, name, &pdev->dev); nfp_info(pf->cpp, " %s: %s\n", - name, err ? "not found" : "found, loading..."); + name, err ? "not found" : "found"); if (err) return NULL; @@ -430,8 +430,35 @@ nfp_net_fw_find(struct pci_dev *pdev, struct nfp_pf *pf) return nfp_net_fw_request(pdev, pf, fw_name); } +static int +nfp_get_fw_policy_value(struct pci_dev *pdev, struct nfp_nsp *nsp, + const char *key, const char *default_val, int max_val, + int *value) +{ + char hwinfo[64]; + long hi_val; + int err; + + snprintf(hwinfo, sizeof(hwinfo), key); + err = nfp_nsp_hwinfo_lookup_optional(nsp, hwinfo, sizeof(hwinfo), + default_val); + if (err) + return err; + + err = kstrtol(hwinfo, 0, &hi_val); + if (err || hi_val < 0 || hi_val > max_val) { + dev_warn(&pdev->dev, + "Invalid value '%s' from '%s', ignoring\n", + hwinfo, key); + err = kstrtol(default_val, 0, &hi_val); + } + + *value = hi_val; + return err; +} + /** - * nfp_net_fw_load() - Load the firmware image + * nfp_fw_load() - Load the firmware image * @pdev: PCI Device structure * @pf: NFP PF Device structure * @nsp: NFP SP handle @@ -441,44 +468,107 @@ nfp_net_fw_find(struct pci_dev *pdev, struct nfp_pf *pf) static int nfp_fw_load(struct pci_dev *pdev, struct nfp_pf *pf, struct nfp_nsp *nsp) { - const struct firmware *fw; + bool do_reset, fw_loaded = false; + const struct firmware *fw = NULL; + int err, reset, policy, ifcs = 0; + char *token, *ptr; + char hwinfo[64]; u16 interface; - int err; + + snprintf(hwinfo, sizeof(hwinfo), "abi_drv_load_ifc"); + err = nfp_nsp_hwinfo_lookup_optional(nsp, hwinfo, sizeof(hwinfo), + NFP_NSP_DRV_LOAD_IFC_DEFAULT); + if (err) + return err; interface = nfp_cpp_interface(pf->cpp); - if (NFP_CPP_INTERFACE_UNIT_of(interface) != 0) { - /* Only Unit 0 should reset or load firmware */ + ptr = hwinfo; + while ((token = strsep(&ptr, ","))) { + unsigned long interface_hi; + + err = kstrtoul(token, 0, &interface_hi); + if (err) { + dev_err(&pdev->dev, + "Failed to parse interface '%s': %d\n", + token, err); + return err; + } + + ifcs++; + if (interface == interface_hi) + break; + } + + if (!token) { dev_info(&pdev->dev, "Firmware will be loaded by partner\n"); return 0; } + err = nfp_get_fw_policy_value(pdev, nsp, "abi_drv_reset", + NFP_NSP_DRV_RESET_DEFAULT, + NFP_NSP_DRV_RESET_NEVER, &reset); + if (err) + return err; + + err = nfp_get_fw_policy_value(pdev, nsp, "app_fw_from_flash", + NFP_NSP_APP_FW_LOAD_DEFAULT, + NFP_NSP_APP_FW_LOAD_PREF, &policy); + if (err) + return err; + fw = nfp_net_fw_find(pdev, pf); - if (!fw) { - if (nfp_nsp_has_stored_fw_load(nsp)) - nfp_nsp_load_stored_fw(nsp); - return 0; + do_reset = reset == NFP_NSP_DRV_RESET_ALWAYS || + (fw && reset == NFP_NSP_DRV_RESET_DISK); + + if (do_reset) { + dev_info(&pdev->dev, "Soft-resetting the NFP\n"); + err = nfp_nsp_device_soft_reset(nsp); + if (err < 0) { + dev_err(&pdev->dev, + "Failed to soft reset the NFP: %d\n", err); + goto exit_release_fw; + } } - dev_info(&pdev->dev, "Soft-reset, loading FW image\n"); - err = nfp_nsp_device_soft_reset(nsp); - if (err < 0) { - dev_err(&pdev->dev, "Failed to soft reset the NFP: %d\n", - err); - goto exit_release_fw; - } + if (fw && policy != NFP_NSP_APP_FW_LOAD_FLASH) { + if (nfp_nsp_has_fw_loaded(nsp) && nfp_nsp_fw_loaded(nsp)) + goto exit_release_fw; - err = nfp_nsp_load_fw(nsp, fw); - if (err < 0) { - dev_err(&pdev->dev, "FW loading failed: %d\n", err); - goto exit_release_fw; + err = nfp_nsp_load_fw(nsp, fw); + if (err < 0) { + dev_err(&pdev->dev, "FW loading failed: %d\n", + err); + goto exit_release_fw; + } + dev_info(&pdev->dev, "Finished loading FW image\n"); + fw_loaded = true; + } else if (policy != NFP_NSP_APP_FW_LOAD_DISK && + nfp_nsp_has_stored_fw_load(nsp)) { + + /* Don't propagate this error to stick with legacy driver + * behavior, failure will be detected later during init. + */ + if (!nfp_nsp_load_stored_fw(nsp)) + dev_info(&pdev->dev, "Finished loading stored FW image\n"); + + /* Don't flag the fw_loaded in this case since other devices + * may reuse the firmware when configured this way + */ + } else { + dev_warn(&pdev->dev, "Didn't load firmware, please update flash or reconfigure card\n"); } - dev_info(&pdev->dev, "Finished loading FW image\n"); - exit_release_fw: release_firmware(fw); - return err < 0 ? err : 1; + /* We don't want to unload firmware when other devices may still be + * dependent on it, which could be the case if there are multiple + * devices that could load firmware. + */ + if (fw_loaded && ifcs == 1) + pf->unload_fw_on_remove = true; + + return err < 0 ? err : fw_loaded; } static void @@ -704,7 +794,7 @@ err_net_remove: err_fw_unload: kfree(pf->rtbl); nfp_mip_close(pf->mip); - if (pf->fw_loaded) + if (pf->unload_fw_on_remove) nfp_fw_unload(pf); kfree(pf->eth_tbl); kfree(pf->nspi); @@ -744,7 +834,7 @@ static void __nfp_pci_shutdown(struct pci_dev *pdev, bool unload_fw) vfree(pf->dumpspec); kfree(pf->rtbl); nfp_mip_close(pf->mip); - if (unload_fw && pf->fw_loaded) + if (unload_fw && pf->unload_fw_on_remove) nfp_fw_unload(pf); destroy_workqueue(pf->wq); @@ -815,6 +905,8 @@ static void __exit nfp_main_exit(void) module_init(nfp_main_init); module_exit(nfp_main_exit); +MODULE_FIRMWARE("netronome/nic_AMDA0058-0011_2x40.nffw"); +MODULE_FIRMWARE("netronome/nic_AMDA0058-0012_2x40.nffw"); MODULE_FIRMWARE("netronome/nic_AMDA0081-0001_1x40.nffw"); MODULE_FIRMWARE("netronome/nic_AMDA0081-0001_4x10.nffw"); MODULE_FIRMWARE("netronome/nic_AMDA0096-0001_2x10.nffw"); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.h b/drivers/net/ethernet/netronome/nfp/nfp_main.h index b7211f200d22..5d5812fd9317 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.h @@ -64,6 +64,7 @@ struct nfp_dumpspec { * @limit_vfs: Number of VFs supported by firmware (~0 for PCI limit) * @num_vfs: Number of SR-IOV VFs enabled * @fw_loaded: Is the firmware loaded? + * @unload_fw_on_remove:Do we need to unload firmware on driver removal? * @ctrl_vnic: Pointer to the control vNIC if available * @mip: MIP handle * @rtbl: RTsym table @@ -110,6 +111,7 @@ struct nfp_pf { unsigned int num_vfs; bool fw_loaded; + bool unload_fw_on_remove; struct nfp_net *ctrl_vnic; @@ -185,4 +187,7 @@ int nfp_shared_buf_pool_get(struct nfp_pf *pf, unsigned int sb, u16 pool_index, int nfp_shared_buf_pool_set(struct nfp_pf *pf, unsigned int sb, u16 pool_index, u32 size, enum devlink_sb_threshold_type threshold_type); + +int nfp_devlink_params_register(struct nfp_pf *pf); +void nfp_devlink_params_unregister(struct nfp_pf *pf); #endif /* NFP_MAIN_H */ diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net.h b/drivers/net/ethernet/netronome/nfp/nfp_net.h index 5d6c3738b494..250f510b1d21 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_net.h @@ -66,7 +66,7 @@ #define NFP_NET_MAX_DMA_BITS 40 /* Default size for MTU and freelist buffer sizes */ -#define NFP_NET_DEFAULT_MTU 1500 +#define NFP_NET_DEFAULT_MTU 1500U /* Maximum number of bytes prepended to a packet */ #define NFP_NET_MAX_PREPEND 64 diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 9903805717da..61aabffc8888 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -975,7 +975,7 @@ static int nfp_net_prep_tx_meta(struct sk_buff *skb, u64 tls_handle) static int nfp_net_tx(struct sk_buff *skb, struct net_device *netdev) { struct nfp_net *nn = netdev_priv(netdev); - const struct skb_frag_struct *frag; + const skb_frag_t *frag; int f, nr_frags, wr_idx, md_bytes; struct nfp_net_tx_ring *tx_ring; struct nfp_net_r_vector *r_vec; @@ -1155,7 +1155,7 @@ static void nfp_net_tx_complete(struct nfp_net_tx_ring *tx_ring, int budget) todo = D_IDX(tx_ring, qcp_rd_p - tx_ring->qcp_rd_p); while (todo--) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag; struct nfp_net_tx_buf *tx_buf; struct sk_buff *skb; int fidx, nr_frags; @@ -1270,7 +1270,7 @@ static bool nfp_net_xdp_complete(struct nfp_net_tx_ring *tx_ring) static void nfp_net_tx_ring_reset(struct nfp_net_dp *dp, struct nfp_net_tx_ring *tx_ring) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag; struct netdev_queue *nd_q; while (!tx_ring->is_xdp && tx_ring->rd_p != tx_ring->wr_p) { @@ -4116,14 +4116,7 @@ int nfp_net_init(struct nfp_net *nn) /* Set default MTU and Freelist buffer size */ if (!nfp_net_is_data_vnic(nn) && nn->app->ctrl_mtu) { - if (nn->app->ctrl_mtu <= nn->max_mtu) { - nn->dp.mtu = nn->app->ctrl_mtu; - } else { - if (nn->app->ctrl_mtu != NFP_APP_CTRL_MTU_MAX) - nn_warn(nn, "app requested MTU above max supported %u > %u\n", - nn->app->ctrl_mtu, nn->max_mtu); - nn->dp.mtu = nn->max_mtu; - } + nn->dp.mtu = min(nn->app->ctrl_mtu, nn->max_mtu); } else if (nn->max_mtu < NFP_NET_DEFAULT_MTU) { nn->dp.mtu = nn->max_mtu; } else { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c index ab7f2498e1c4..553c708694e8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_debugfs.c @@ -159,19 +159,13 @@ void nfp_net_debugfs_vnic_add(struct nfp_net *nn, struct dentry *ddir) else strcpy(name, "ctrl-vnic"); nn->debugfs_dir = debugfs_create_dir(name, ddir); - if (IS_ERR_OR_NULL(nn->debugfs_dir)) - return; /* Create queue debugging sub-tree */ queues = debugfs_create_dir("queue", nn->debugfs_dir); - if (IS_ERR_OR_NULL(queues)) - return; rx = debugfs_create_dir("rx", queues); tx = debugfs_create_dir("tx", queues); xdp = debugfs_create_dir("xdp", queues); - if (IS_ERR_OR_NULL(rx) || IS_ERR_OR_NULL(tx) || IS_ERR_OR_NULL(xdp)) - return; for (i = 0; i < min(nn->max_rx_rings, nn->max_r_vecs); i++) { sprintf(name, "%d", i); @@ -190,16 +184,7 @@ void nfp_net_debugfs_vnic_add(struct nfp_net *nn, struct dentry *ddir) struct dentry *nfp_net_debugfs_device_add(struct pci_dev *pdev) { - struct dentry *dev_dir; - - if (IS_ERR_OR_NULL(nfp_dir)) - return NULL; - - dev_dir = debugfs_create_dir(pci_name(pdev), nfp_dir); - if (IS_ERR_OR_NULL(dev_dir)) - return NULL; - - return dev_dir; + return debugfs_create_dir(pci_name(pdev), nfp_dir); } void nfp_net_debugfs_dir_clean(struct dentry **dir) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c index 986464d4a206..921db40047d7 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_main.c @@ -205,10 +205,8 @@ nfp_net_pf_alloc_vnics(struct nfp_pf *pf, void __iomem *ctrl_bar, ctrl_bar += NFP_PF_CSR_SLICE_SIZE; /* Kill the vNIC if app init marked it as invalid */ - if (nn->port && nn->port->type == NFP_PORT_INVALID) { + if (nn->port && nn->port->type == NFP_PORT_INVALID) nfp_net_pf_free_vnic(pf, nn); - continue; - } } if (list_empty(&pf->vnics)) @@ -711,6 +709,10 @@ int nfp_net_pci_probe(struct nfp_pf *pf) if (err) goto err_devlink_unreg; + err = nfp_devlink_params_register(pf); + if (err) + goto err_shared_buf_unreg; + mutex_lock(&pf->lock); pf->ddir = nfp_net_debugfs_device_add(pf->pdev); @@ -744,6 +746,8 @@ err_free_vnics: err_clean_ddir: nfp_net_debugfs_dir_clean(&pf->ddir); mutex_unlock(&pf->lock); + nfp_devlink_params_unregister(pf); +err_shared_buf_unreg: nfp_shared_buf_unregister(pf); err_devlink_unreg: cancel_work_sync(&pf->port_refresh_work); @@ -773,6 +777,7 @@ void nfp_net_pci_remove(struct nfp_pf *pf) mutex_unlock(&pf->lock); + nfp_devlink_params_unregister(pf); nfp_shared_buf_unregister(pf); devlink_unregister(priv_to_devlink(pf)); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c index 3cfecf105bde..85734c6badf5 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpplib.c @@ -24,8 +24,9 @@ /* NFP6000 PL */ #define NFP_PL_DEVICE_ID 0x00000004 #define NFP_PL_DEVICE_ID_MASK GENMASK(7, 0) - -#define NFP6000_ARM_GCSR_SOFTMODEL0 0x00400144 +#define NFP_PL_DEVICE_PART_MASK GENMASK(31, 16) +#define NFP_PL_DEVICE_MODEL_MASK (NFP_PL_DEVICE_PART_MASK | \ + NFP_PL_DEVICE_ID_MASK) /** * nfp_cpp_readl() - Read a u32 word from a CPP location @@ -120,22 +121,17 @@ int nfp_cpp_writeq(struct nfp_cpp *cpp, u32 cpp_id, */ int nfp_cpp_model_autodetect(struct nfp_cpp *cpp, u32 *model) { - const u32 arm_id = NFP_CPP_ID(NFP_CPP_TARGET_ARM, 0, 0); u32 reg; int err; - err = nfp_cpp_readl(cpp, arm_id, NFP6000_ARM_GCSR_SOFTMODEL0, model); - if (err < 0) - return err; - - /* The PL's PluDeviceID revision code is authoratative */ - *model &= ~0xff; err = nfp_xpb_readl(cpp, NFP_XPB_DEVICE(1, 1, 16) + NFP_PL_DEVICE_ID, ®); if (err < 0) return err; - *model |= (NFP_PL_DEVICE_ID_MASK & reg) - 0x10; + *model = reg & NFP_PL_DEVICE_MODEL_MASK; + if (*model & NFP_PL_DEVICE_ID_MASK) + *model -= 0x10; return 0; } diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c index 9a08623c325d..f18e787fa9ad 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.c @@ -96,6 +96,8 @@ enum nfp_nsp_cmd { SPCODE_NSP_IDENTIFY = 13, /* Read NSP version */ SPCODE_FW_STORED = 16, /* If no FW loaded, load flash app FW */ SPCODE_HWINFO_LOOKUP = 17, /* Lookup HWinfo with overwrites etc. */ + SPCODE_HWINFO_SET = 18, /* Set HWinfo entry */ + SPCODE_FW_LOADED = 19, /* Is application firmware loaded */ SPCODE_VERSIONS = 21, /* Report FW versions */ SPCODE_READ_SFF_EEPROM = 22, /* Read module EEPROM */ }; @@ -143,6 +145,8 @@ struct nfp_nsp { * @option: NFP SP Command Argument * @buf: NFP SP Buffer Address * @error_cb: Callback for interpreting option if error occurred + * @error_quiet:Don't print command error/warning. Protocol errors are still + * logged. */ struct nfp_nsp_command_arg { u16 code; @@ -151,6 +155,7 @@ struct nfp_nsp_command_arg { u32 option; u64 buf; void (*error_cb)(struct nfp_nsp *state, u32 ret_val); + bool error_quiet; }; /** @@ -405,8 +410,10 @@ __nfp_nsp_command(struct nfp_nsp *state, const struct nfp_nsp_command_arg *arg) err = FIELD_GET(NSP_STATUS_RESULT, reg); if (err) { - nfp_warn(cpp, "Result (error) code set: %d (%d) command: %d\n", - -err, (int)ret_val, arg->code); + if (!arg->error_quiet) + nfp_warn(cpp, "Result (error) code set: %d (%d) command: %d\n", + -err, (int)ret_val, arg->code); + if (arg->error_cb) arg->error_cb(state, ret_val); else @@ -891,12 +898,14 @@ int nfp_nsp_load_stored_fw(struct nfp_nsp *state) } static int -__nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size) +__nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size, + bool optional) { struct nfp_nsp_command_buf_arg hwinfo_lookup = { { .code = SPCODE_HWINFO_LOOKUP, .option = size, + .error_quiet = optional, }, .in_buf = buf, .in_size = size, @@ -913,7 +922,7 @@ int nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size) size = min_t(u32, size, NFP_HWINFO_LOOKUP_SIZE); - err = __nfp_nsp_hwinfo_lookup(state, buf, size); + err = __nfp_nsp_hwinfo_lookup(state, buf, size, false); if (err) return err; @@ -925,6 +934,66 @@ int nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size) return 0; } +int nfp_nsp_hwinfo_lookup_optional(struct nfp_nsp *state, void *buf, + unsigned int size, const char *default_val) +{ + int err; + + /* Ensure that the default value is usable irrespective of whether + * it is actually going to be used. + */ + if (strnlen(default_val, size) == size) + return -EINVAL; + + if (!nfp_nsp_has_hwinfo_lookup(state)) { + strcpy(buf, default_val); + return 0; + } + + size = min_t(u32, size, NFP_HWINFO_LOOKUP_SIZE); + + err = __nfp_nsp_hwinfo_lookup(state, buf, size, true); + if (err) { + if (err == -ENOENT) { + strcpy(buf, default_val); + return 0; + } + + nfp_err(state->cpp, "NSP HWinfo lookup failed: %d\n", err); + return err; + } + + if (strnlen(buf, size) == size) { + nfp_err(state->cpp, "NSP HWinfo value not NULL-terminated\n"); + return -EINVAL; + } + + return 0; +} + +int nfp_nsp_hwinfo_set(struct nfp_nsp *state, void *buf, unsigned int size) +{ + struct nfp_nsp_command_buf_arg hwinfo_set = { + { + .code = SPCODE_HWINFO_SET, + .option = size, + }, + .in_buf = buf, + .in_size = size, + }; + + return nfp_nsp_command_buf(state, &hwinfo_set); +} + +int nfp_nsp_fw_loaded(struct nfp_nsp *state) +{ + const struct nfp_nsp_command_arg arg = { + .code = SPCODE_FW_LOADED, + }; + + return __nfp_nsp_command(state, &arg); +} + int nfp_nsp_versions(struct nfp_nsp *state, void *buf, unsigned int size) { struct nfp_nsp_command_buf_arg versions = { diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h index 22ee6985ee1c..1531c1870020 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_nsp.h @@ -22,6 +22,10 @@ int nfp_nsp_write_flash(struct nfp_nsp *state, const struct firmware *fw); int nfp_nsp_mac_reinit(struct nfp_nsp *state); int nfp_nsp_load_stored_fw(struct nfp_nsp *state); int nfp_nsp_hwinfo_lookup(struct nfp_nsp *state, void *buf, unsigned int size); +int nfp_nsp_hwinfo_lookup_optional(struct nfp_nsp *state, void *buf, + unsigned int size, const char *default_val); +int nfp_nsp_hwinfo_set(struct nfp_nsp *state, void *buf, unsigned int size); +int nfp_nsp_fw_loaded(struct nfp_nsp *state); int nfp_nsp_read_module_eeprom(struct nfp_nsp *state, int eth_index, unsigned int offset, void *data, unsigned int len, unsigned int *read_len); @@ -41,6 +45,16 @@ static inline bool nfp_nsp_has_hwinfo_lookup(struct nfp_nsp *state) return nfp_nsp_get_abi_ver_minor(state) > 24; } +static inline bool nfp_nsp_has_hwinfo_set(struct nfp_nsp *state) +{ + return nfp_nsp_get_abi_ver_minor(state) > 25; +} + +static inline bool nfp_nsp_has_fw_loaded(struct nfp_nsp *state) +{ + return nfp_nsp_get_abi_ver_minor(state) > 25; +} + static inline bool nfp_nsp_has_versions(struct nfp_nsp *state) { return nfp_nsp_get_abi_ver_minor(state) > 27; @@ -88,6 +102,21 @@ enum nfp_eth_fec { #define NFP_FEC_REED_SOLOMON BIT(NFP_FEC_REED_SOLOMON_BIT) #define NFP_FEC_DISABLED BIT(NFP_FEC_DISABLED_BIT) +/* Defines the valid values of the 'abi_drv_reset' hwinfo key */ +#define NFP_NSP_DRV_RESET_DISK 0 +#define NFP_NSP_DRV_RESET_ALWAYS 1 +#define NFP_NSP_DRV_RESET_NEVER 2 +#define NFP_NSP_DRV_RESET_DEFAULT "0" + +/* Defines the valid values of the 'app_fw_from_flash' hwinfo key */ +#define NFP_NSP_APP_FW_LOAD_DISK 0 +#define NFP_NSP_APP_FW_LOAD_FLASH 1 +#define NFP_NSP_APP_FW_LOAD_PREF 2 +#define NFP_NSP_APP_FW_LOAD_DEFAULT "2" + +/* Define the default value for the 'abi_drv_load_ifc' key */ +#define NFP_NSP_DRV_LOAD_IFC_DEFAULT "0x10ff" + /** * struct nfp_eth_table - ETH table information * @count: number of table entries diff --git a/drivers/net/ethernet/nvidia/forcedeth.c b/drivers/net/ethernet/nvidia/forcedeth.c index a6b4bfae4684..05d2b478c99b 100644 --- a/drivers/net/ethernet/nvidia/forcedeth.c +++ b/drivers/net/ethernet/nvidia/forcedeth.c @@ -6181,8 +6181,7 @@ static void nv_remove(struct pci_dev *pci_dev) #ifdef CONFIG_PM_SLEEP static int nv_suspend(struct device *device) { - struct pci_dev *pdev = to_pci_dev(device); - struct net_device *dev = pci_get_drvdata(pdev); + struct net_device *dev = dev_get_drvdata(device); struct fe_priv *np = netdev_priv(dev); u8 __iomem *base = get_hwbase(dev); int i; diff --git a/drivers/net/ethernet/packetengines/yellowfin.c b/drivers/net/ethernet/packetengines/yellowfin.c index 6f8d6584f809..5113ee647090 100644 --- a/drivers/net/ethernet/packetengines/yellowfin.c +++ b/drivers/net/ethernet/packetengines/yellowfin.c @@ -1258,8 +1258,7 @@ static int yellowfin_close(struct net_device *dev) yp->rx_skbuff[i] = NULL; } for (i = 0; i < TX_RING_SIZE; i++) { - if (yp->tx_skbuff[i]) - dev_kfree_skb(yp->tx_skbuff[i]); + dev_kfree_skb(yp->tx_skbuff[i]); yp->tx_skbuff[i] = NULL; } diff --git a/drivers/net/ethernet/pensando/Kconfig b/drivers/net/ethernet/pensando/Kconfig new file mode 100644 index 000000000000..5ea570be8379 --- /dev/null +++ b/drivers/net/ethernet/pensando/Kconfig @@ -0,0 +1,32 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright (c) 2019 Pensando Systems, Inc +# +# Pensando device configuration +# + +config NET_VENDOR_PENSANDO + bool "Pensando devices" + default y + help + If you have a network (Ethernet) card belonging to this class, say Y. + + Note that the answer to this question doesn't directly affect the + kernel: saying N will just cause the configurator to skip all + the questions about Pensando cards. If you say Y, you will be asked + for your specific card in the following questions. + +if NET_VENDOR_PENSANDO + +config IONIC + tristate "Pensando Ethernet IONIC Support" + depends on 64BIT && PCI + help + This enables the support for the Pensando family of Ethernet + adapters. More specific information on this driver can be + found in + <file:Documentation/networking/device_drivers/pensando/ionic.rst>. + + To compile this driver as a module, choose M here. The module + will be called ionic. + +endif # NET_VENDOR_PENSANDO diff --git a/drivers/net/ethernet/pensando/Makefile b/drivers/net/ethernet/pensando/Makefile new file mode 100644 index 000000000000..21ce7499c122 --- /dev/null +++ b/drivers/net/ethernet/pensando/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Makefile for the Pensando network device drivers. +# + +obj-$(CONFIG_IONIC) += ionic/ diff --git a/drivers/net/ethernet/pensando/ionic/Makefile b/drivers/net/ethernet/pensando/ionic/Makefile new file mode 100644 index 000000000000..29f304d75261 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0 +# Copyright(c) 2017 - 2019 Pensando Systems, Inc + +obj-$(CONFIG_IONIC) := ionic.o + +ionic-y := ionic_main.o ionic_bus_pci.o ionic_devlink.o ionic_dev.o \ + ionic_debugfs.o ionic_lif.o ionic_rx_filter.o ionic_ethtool.o \ + ionic_txrx.o ionic_stats.o diff --git a/drivers/net/ethernet/pensando/ionic/ionic.h b/drivers/net/ethernet/pensando/ionic/ionic.h new file mode 100644 index 000000000000..7a7060677f15 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic.h @@ -0,0 +1,73 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_H_ +#define _IONIC_H_ + +struct ionic_lif; + +#include "ionic_if.h" +#include "ionic_dev.h" +#include "ionic_devlink.h" + +#define IONIC_DRV_NAME "ionic" +#define IONIC_DRV_DESCRIPTION "Pensando Ethernet NIC Driver" +#define IONIC_DRV_VERSION "0.15.0-k" + +#define PCI_VENDOR_ID_PENSANDO 0x1dd8 + +#define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_PF 0x1002 +#define PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF 0x1003 + +#define IONIC_SUBDEV_ID_NAPLES_25 0x4000 +#define IONIC_SUBDEV_ID_NAPLES_100_4 0x4001 +#define IONIC_SUBDEV_ID_NAPLES_100_8 0x4002 + +#define DEVCMD_TIMEOUT 10 + +struct ionic { + struct pci_dev *pdev; + struct device *dev; + struct devlink_port dl_port; + struct ionic_dev idev; + struct mutex dev_cmd_lock; /* lock for dev_cmd operations */ + struct dentry *dentry; + struct ionic_dev_bar bars[IONIC_BARS_MAX]; + unsigned int num_bars; + struct ionic_identity ident; + struct list_head lifs; + struct ionic_lif *master_lif; + unsigned int nnqs_per_lif; + unsigned int neqs_per_lif; + unsigned int ntxqs_per_lif; + unsigned int nrxqs_per_lif; + DECLARE_BITMAP(lifbits, IONIC_LIFS_MAX); + unsigned int nintrs; + DECLARE_BITMAP(intrs, IONIC_INTR_CTRL_REGS_MAX); + struct work_struct nb_work; + struct notifier_block nb; +}; + +struct ionic_admin_ctx { + struct completion work; + union ionic_adminq_cmd cmd; + union ionic_adminq_comp comp; +}; + +int ionic_napi(struct napi_struct *napi, int budget, ionic_cq_cb cb, + ionic_cq_done_cb done_cb, void *done_arg); + +int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx); +int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_wait); +int ionic_set_dma_mask(struct ionic *ionic); +int ionic_setup(struct ionic *ionic); + +int ionic_identify(struct ionic *ionic); +int ionic_init(struct ionic *ionic); +int ionic_reset(struct ionic *ionic); + +int ionic_port_identify(struct ionic *ionic); +int ionic_port_init(struct ionic *ionic); +int ionic_port_reset(struct ionic *ionic); + +#endif /* _IONIC_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus.h b/drivers/net/ethernet/pensando/ionic/ionic_bus.h new file mode 100644 index 000000000000..2f4d08c64910 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_BUS_H_ +#define _IONIC_BUS_H_ + +int ionic_bus_get_irq(struct ionic *ionic, unsigned int num); +const char *ionic_bus_info(struct ionic *ionic); +int ionic_bus_alloc_irq_vectors(struct ionic *ionic, unsigned int nintrs); +void ionic_bus_free_irq_vectors(struct ionic *ionic); +int ionic_bus_register_driver(void); +void ionic_bus_unregister_driver(void); +void __iomem *ionic_bus_map_dbpage(struct ionic *ionic, int page_num); +void ionic_bus_unmap_dbpage(struct ionic *ionic, void __iomem *page); + +#endif /* _IONIC_BUS_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c new file mode 100644 index 000000000000..9a9ab8cb2cb3 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -0,0 +1,292 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/pci.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_debugfs.h" + +/* Supported devices */ +static const struct pci_device_id ionic_id_table[] = { + { PCI_VDEVICE(PENSANDO, PCI_DEVICE_ID_PENSANDO_IONIC_ETH_PF) }, + { PCI_VDEVICE(PENSANDO, PCI_DEVICE_ID_PENSANDO_IONIC_ETH_VF) }, + { 0, } /* end of table */ +}; +MODULE_DEVICE_TABLE(pci, ionic_id_table); + +int ionic_bus_get_irq(struct ionic *ionic, unsigned int num) +{ + return pci_irq_vector(ionic->pdev, num); +} + +const char *ionic_bus_info(struct ionic *ionic) +{ + return pci_name(ionic->pdev); +} + +int ionic_bus_alloc_irq_vectors(struct ionic *ionic, unsigned int nintrs) +{ + return pci_alloc_irq_vectors(ionic->pdev, nintrs, nintrs, + PCI_IRQ_MSIX); +} + +void ionic_bus_free_irq_vectors(struct ionic *ionic) +{ + pci_free_irq_vectors(ionic->pdev); +} + +static int ionic_map_bars(struct ionic *ionic) +{ + struct pci_dev *pdev = ionic->pdev; + struct device *dev = ionic->dev; + struct ionic_dev_bar *bars; + unsigned int i, j; + + bars = ionic->bars; + ionic->num_bars = 0; + + for (i = 0, j = 0; i < IONIC_BARS_MAX; i++) { + if (!(pci_resource_flags(pdev, i) & IORESOURCE_MEM)) + continue; + bars[j].len = pci_resource_len(pdev, i); + + /* only map the whole bar 0 */ + if (j > 0) { + bars[j].vaddr = NULL; + } else { + bars[j].vaddr = pci_iomap(pdev, i, bars[j].len); + if (!bars[j].vaddr) { + dev_err(dev, + "Cannot memory-map BAR %d, aborting\n", + i); + return -ENODEV; + } + } + + bars[j].bus_addr = pci_resource_start(pdev, i); + bars[j].res_index = i; + ionic->num_bars++; + j++; + } + + return 0; +} + +static void ionic_unmap_bars(struct ionic *ionic) +{ + struct ionic_dev_bar *bars = ionic->bars; + unsigned int i; + + for (i = 0; i < IONIC_BARS_MAX; i++) { + if (bars[i].vaddr) { + iounmap(bars[i].vaddr); + bars[i].bus_addr = 0; + bars[i].vaddr = NULL; + bars[i].len = 0; + } + } +} + +void __iomem *ionic_bus_map_dbpage(struct ionic *ionic, int page_num) +{ + return pci_iomap_range(ionic->pdev, + ionic->bars[IONIC_PCI_BAR_DBELL].res_index, + (u64)page_num << PAGE_SHIFT, PAGE_SIZE); +} + +void ionic_bus_unmap_dbpage(struct ionic *ionic, void __iomem *page) +{ + iounmap(page); +} + +static int ionic_probe(struct pci_dev *pdev, const struct pci_device_id *ent) +{ + struct device *dev = &pdev->dev; + struct ionic *ionic; + int err; + + ionic = ionic_devlink_alloc(dev); + if (!ionic) + return -ENOMEM; + + ionic->pdev = pdev; + ionic->dev = dev; + pci_set_drvdata(pdev, ionic); + mutex_init(&ionic->dev_cmd_lock); + + /* Query system for DMA addressing limitation for the device. */ + err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(IONIC_ADDR_LEN)); + if (err) { + dev_err(dev, "Unable to obtain 64-bit DMA for consistent allocations, aborting. err=%d\n", + err); + goto err_out_clear_drvdata; + } + + ionic_debugfs_add_dev(ionic); + + /* Setup PCI device */ + err = pci_enable_device_mem(pdev); + if (err) { + dev_err(dev, "Cannot enable PCI device: %d, aborting\n", err); + goto err_out_debugfs_del_dev; + } + + err = pci_request_regions(pdev, IONIC_DRV_NAME); + if (err) { + dev_err(dev, "Cannot request PCI regions: %d, aborting\n", err); + goto err_out_pci_disable_device; + } + + pci_set_master(pdev); + + err = ionic_map_bars(ionic); + if (err) + goto err_out_pci_clear_master; + + /* Configure the device */ + err = ionic_setup(ionic); + if (err) { + dev_err(dev, "Cannot setup device: %d, aborting\n", err); + goto err_out_unmap_bars; + } + + err = ionic_identify(ionic); + if (err) { + dev_err(dev, "Cannot identify device: %d, aborting\n", err); + goto err_out_teardown; + } + + err = ionic_init(ionic); + if (err) { + dev_err(dev, "Cannot init device: %d, aborting\n", err); + goto err_out_teardown; + } + + /* Configure the ports */ + err = ionic_port_identify(ionic); + if (err) { + dev_err(dev, "Cannot identify port: %d, aborting\n", err); + goto err_out_reset; + } + + err = ionic_port_init(ionic); + if (err) { + dev_err(dev, "Cannot init port: %d, aborting\n", err); + goto err_out_reset; + } + + /* Configure LIFs */ + err = ionic_lif_identify(ionic, IONIC_LIF_TYPE_CLASSIC, + &ionic->ident.lif); + if (err) { + dev_err(dev, "Cannot identify LIFs: %d, aborting\n", err); + goto err_out_port_reset; + } + + err = ionic_lifs_size(ionic); + if (err) { + dev_err(dev, "Cannot size LIFs: %d, aborting\n", err); + goto err_out_port_reset; + } + + err = ionic_lifs_alloc(ionic); + if (err) { + dev_err(dev, "Cannot allocate LIFs: %d, aborting\n", err); + goto err_out_free_irqs; + } + + err = ionic_lifs_init(ionic); + if (err) { + dev_err(dev, "Cannot init LIFs: %d, aborting\n", err); + goto err_out_free_lifs; + } + + err = ionic_lifs_register(ionic); + if (err) { + dev_err(dev, "Cannot register LIFs: %d, aborting\n", err); + goto err_out_deinit_lifs; + } + + err = ionic_devlink_register(ionic); + if (err) { + dev_err(dev, "Cannot register devlink: %d\n", err); + goto err_out_deregister_lifs; + } + + return 0; + +err_out_deregister_lifs: + ionic_lifs_unregister(ionic); +err_out_deinit_lifs: + ionic_lifs_deinit(ionic); +err_out_free_lifs: + ionic_lifs_free(ionic); +err_out_free_irqs: + ionic_bus_free_irq_vectors(ionic); +err_out_port_reset: + ionic_port_reset(ionic); +err_out_reset: + ionic_reset(ionic); +err_out_teardown: + ionic_dev_teardown(ionic); +err_out_unmap_bars: + ionic_unmap_bars(ionic); + pci_release_regions(pdev); +err_out_pci_clear_master: + pci_clear_master(pdev); +err_out_pci_disable_device: + pci_disable_device(pdev); +err_out_debugfs_del_dev: + ionic_debugfs_del_dev(ionic); +err_out_clear_drvdata: + mutex_destroy(&ionic->dev_cmd_lock); + ionic_devlink_free(ionic); + + return err; +} + +static void ionic_remove(struct pci_dev *pdev) +{ + struct ionic *ionic = pci_get_drvdata(pdev); + + if (!ionic) + return; + + ionic_devlink_unregister(ionic); + ionic_lifs_unregister(ionic); + ionic_lifs_deinit(ionic); + ionic_lifs_free(ionic); + ionic_bus_free_irq_vectors(ionic); + ionic_port_reset(ionic); + ionic_reset(ionic); + ionic_dev_teardown(ionic); + ionic_unmap_bars(ionic); + pci_release_regions(pdev); + pci_clear_master(pdev); + pci_disable_device(pdev); + ionic_debugfs_del_dev(ionic); + mutex_destroy(&ionic->dev_cmd_lock); + ionic_devlink_free(ionic); +} + +static struct pci_driver ionic_driver = { + .name = IONIC_DRV_NAME, + .id_table = ionic_id_table, + .probe = ionic_probe, + .remove = ionic_remove, +}; + +int ionic_bus_register_driver(void) +{ + return pci_register_driver(&ionic_driver); +} + +void ionic_bus_unregister_driver(void) +{ + pci_unregister_driver(&ionic_driver); +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c new file mode 100644 index 000000000000..7afc4a365b75 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.c @@ -0,0 +1,248 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/pci.h> +#include <linux/netdevice.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_debugfs.h" + +#ifdef CONFIG_DEBUG_FS + +static struct dentry *ionic_dir; + +void ionic_debugfs_create(void) +{ + ionic_dir = debugfs_create_dir(IONIC_DRV_NAME, NULL); +} + +void ionic_debugfs_destroy(void) +{ + debugfs_remove_recursive(ionic_dir); +} + +void ionic_debugfs_add_dev(struct ionic *ionic) +{ + ionic->dentry = debugfs_create_dir(ionic_bus_info(ionic), ionic_dir); +} + +void ionic_debugfs_del_dev(struct ionic *ionic) +{ + debugfs_remove_recursive(ionic->dentry); + ionic->dentry = NULL; +} + +static int identity_show(struct seq_file *seq, void *v) +{ + struct ionic *ionic = seq->private; + struct ionic_identity *ident; + + ident = &ionic->ident; + + seq_printf(seq, "nlifs: %d\n", ident->dev.nlifs); + seq_printf(seq, "nintrs: %d\n", ident->dev.nintrs); + seq_printf(seq, "ndbpgs_per_lif: %d\n", ident->dev.ndbpgs_per_lif); + seq_printf(seq, "intr_coal_mult: %d\n", ident->dev.intr_coal_mult); + seq_printf(seq, "intr_coal_div: %d\n", ident->dev.intr_coal_div); + + seq_printf(seq, "max_ucast_filters: %d\n", ident->lif.eth.max_ucast_filters); + seq_printf(seq, "max_mcast_filters: %d\n", ident->lif.eth.max_mcast_filters); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(identity); + +void ionic_debugfs_add_ident(struct ionic *ionic) +{ + debugfs_create_file("identity", 0400, ionic->dentry, + ionic, &identity_fops) ? 0 : -EOPNOTSUPP; +} + +void ionic_debugfs_add_sizes(struct ionic *ionic) +{ + debugfs_create_u32("nlifs", 0400, ionic->dentry, + (u32 *)&ionic->ident.dev.nlifs); + debugfs_create_u32("nintrs", 0400, ionic->dentry, &ionic->nintrs); + + debugfs_create_u32("ntxqs_per_lif", 0400, ionic->dentry, + (u32 *)&ionic->ident.lif.eth.config.queue_count[IONIC_QTYPE_TXQ]); + debugfs_create_u32("nrxqs_per_lif", 0400, ionic->dentry, + (u32 *)&ionic->ident.lif.eth.config.queue_count[IONIC_QTYPE_RXQ]); +} + +static int q_tail_show(struct seq_file *seq, void *v) +{ + struct ionic_queue *q = seq->private; + + seq_printf(seq, "%d\n", q->tail->index); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(q_tail); + +static int q_head_show(struct seq_file *seq, void *v) +{ + struct ionic_queue *q = seq->private; + + seq_printf(seq, "%d\n", q->head->index); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(q_head); + +static int cq_tail_show(struct seq_file *seq, void *v) +{ + struct ionic_cq *cq = seq->private; + + seq_printf(seq, "%d\n", cq->tail->index); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(cq_tail); + +static const struct debugfs_reg32 intr_ctrl_regs[] = { + { .name = "coal_init", .offset = 0, }, + { .name = "mask", .offset = 4, }, + { .name = "credits", .offset = 8, }, + { .name = "mask_on_assert", .offset = 12, }, + { .name = "coal_timer", .offset = 16, }, +}; + +void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct dentry *q_dentry, *cq_dentry, *intr_dentry, *stats_dentry; + struct ionic_dev *idev = &lif->ionic->idev; + struct debugfs_regset32 *intr_ctrl_regset; + struct ionic_intr_info *intr = &qcq->intr; + struct debugfs_blob_wrapper *desc_blob; + struct device *dev = lif->ionic->dev; + struct ionic_queue *q = &qcq->q; + struct ionic_cq *cq = &qcq->cq; + + qcq->dentry = debugfs_create_dir(q->name, lif->dentry); + + debugfs_create_x32("total_size", 0400, qcq->dentry, &qcq->total_size); + debugfs_create_x64("base_pa", 0400, qcq->dentry, &qcq->base_pa); + + q_dentry = debugfs_create_dir("q", qcq->dentry); + + debugfs_create_u32("index", 0400, q_dentry, &q->index); + debugfs_create_x64("base_pa", 0400, q_dentry, &q->base_pa); + if (qcq->flags & IONIC_QCQ_F_SG) { + debugfs_create_x64("sg_base_pa", 0400, q_dentry, + &q->sg_base_pa); + debugfs_create_u32("sg_desc_size", 0400, q_dentry, + &q->sg_desc_size); + } + debugfs_create_u32("num_descs", 0400, q_dentry, &q->num_descs); + debugfs_create_u32("desc_size", 0400, q_dentry, &q->desc_size); + debugfs_create_u32("pid", 0400, q_dentry, &q->pid); + debugfs_create_u32("qid", 0400, q_dentry, &q->hw_index); + debugfs_create_u32("qtype", 0400, q_dentry, &q->hw_type); + debugfs_create_u64("drop", 0400, q_dentry, &q->drop); + debugfs_create_u64("stop", 0400, q_dentry, &q->stop); + debugfs_create_u64("wake", 0400, q_dentry, &q->wake); + + debugfs_create_file("tail", 0400, q_dentry, q, &q_tail_fops); + debugfs_create_file("head", 0400, q_dentry, q, &q_head_fops); + + desc_blob = devm_kzalloc(dev, sizeof(*desc_blob), GFP_KERNEL); + if (!desc_blob) + return; + desc_blob->data = q->base; + desc_blob->size = (unsigned long)q->num_descs * q->desc_size; + debugfs_create_blob("desc_blob", 0400, q_dentry, desc_blob); + + if (qcq->flags & IONIC_QCQ_F_SG) { + desc_blob = devm_kzalloc(dev, sizeof(*desc_blob), GFP_KERNEL); + if (!desc_blob) + return; + desc_blob->data = q->sg_base; + desc_blob->size = (unsigned long)q->num_descs * q->sg_desc_size; + debugfs_create_blob("sg_desc_blob", 0400, q_dentry, + desc_blob); + } + + cq_dentry = debugfs_create_dir("cq", qcq->dentry); + + debugfs_create_x64("base_pa", 0400, cq_dentry, &cq->base_pa); + debugfs_create_u32("num_descs", 0400, cq_dentry, &cq->num_descs); + debugfs_create_u32("desc_size", 0400, cq_dentry, &cq->desc_size); + debugfs_create_u8("done_color", 0400, cq_dentry, + (u8 *)&cq->done_color); + + debugfs_create_file("tail", 0400, cq_dentry, cq, &cq_tail_fops); + + desc_blob = devm_kzalloc(dev, sizeof(*desc_blob), GFP_KERNEL); + if (!desc_blob) + return; + desc_blob->data = cq->base; + desc_blob->size = (unsigned long)cq->num_descs * cq->desc_size; + debugfs_create_blob("desc_blob", 0400, cq_dentry, desc_blob); + + if (qcq->flags & IONIC_QCQ_F_INTR) { + intr_dentry = debugfs_create_dir("intr", qcq->dentry); + + debugfs_create_u32("index", 0400, intr_dentry, + &intr->index); + debugfs_create_u32("vector", 0400, intr_dentry, + &intr->vector); + + intr_ctrl_regset = devm_kzalloc(dev, sizeof(*intr_ctrl_regset), + GFP_KERNEL); + if (!intr_ctrl_regset) + return; + intr_ctrl_regset->regs = intr_ctrl_regs; + intr_ctrl_regset->nregs = ARRAY_SIZE(intr_ctrl_regs); + intr_ctrl_regset->base = &idev->intr_ctrl[intr->index]; + + debugfs_create_regset32("intr_ctrl", 0400, intr_dentry, + intr_ctrl_regset); + } + + if (qcq->flags & IONIC_QCQ_F_NOTIFYQ) { + stats_dentry = debugfs_create_dir("notifyblock", qcq->dentry); + + debugfs_create_u64("eid", 0400, stats_dentry, + (u64 *)&lif->info->status.eid); + debugfs_create_u16("link_status", 0400, stats_dentry, + (u16 *)&lif->info->status.link_status); + debugfs_create_u32("link_speed", 0400, stats_dentry, + (u32 *)&lif->info->status.link_speed); + debugfs_create_u16("link_down_count", 0400, stats_dentry, + (u16 *)&lif->info->status.link_down_count); + } +} + +static int netdev_show(struct seq_file *seq, void *v) +{ + struct net_device *netdev = seq->private; + + seq_printf(seq, "%s\n", netdev->name); + + return 0; +} +DEFINE_SHOW_ATTRIBUTE(netdev); + +void ionic_debugfs_add_lif(struct ionic_lif *lif) +{ + lif->dentry = debugfs_create_dir(lif->name, lif->ionic->dentry); + debugfs_create_file("netdev", 0400, lif->dentry, + lif->netdev, &netdev_fops); +} + +void ionic_debugfs_del_lif(struct ionic_lif *lif) +{ + debugfs_remove_recursive(lif->dentry); + lif->dentry = NULL; +} + +void ionic_debugfs_del_qcq(struct ionic_qcq *qcq) +{ + debugfs_remove_recursive(qcq->dentry); + qcq->dentry = NULL; +} + +#endif diff --git a/drivers/net/ethernet/pensando/ionic/ionic_debugfs.h b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.h new file mode 100644 index 000000000000..c44ebde170b6 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_debugfs.h @@ -0,0 +1,34 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_DEBUGFS_H_ +#define _IONIC_DEBUGFS_H_ + +#include <linux/debugfs.h> + +#ifdef CONFIG_DEBUG_FS + +void ionic_debugfs_create(void); +void ionic_debugfs_destroy(void); +void ionic_debugfs_add_dev(struct ionic *ionic); +void ionic_debugfs_del_dev(struct ionic *ionic); +void ionic_debugfs_add_ident(struct ionic *ionic); +void ionic_debugfs_add_sizes(struct ionic *ionic); +void ionic_debugfs_add_lif(struct ionic_lif *lif); +void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq); +void ionic_debugfs_del_lif(struct ionic_lif *lif); +void ionic_debugfs_del_qcq(struct ionic_qcq *qcq); +#else +static inline void ionic_debugfs_create(void) { } +static inline void ionic_debugfs_destroy(void) { } +static inline void ionic_debugfs_add_dev(struct ionic *ionic) { } +static inline void ionic_debugfs_del_dev(struct ionic *ionic) { } +static inline void ionic_debugfs_add_ident(struct ionic *ionic) { } +static inline void ionic_debugfs_add_sizes(struct ionic *ionic) { } +static inline void ionic_debugfs_add_lif(struct ionic_lif *lif) { } +static inline void ionic_debugfs_add_qcq(struct ionic_lif *lif, struct ionic_qcq *qcq) { } +static inline void ionic_debugfs_del_lif(struct ionic_lif *lif) { } +static inline void ionic_debugfs_del_qcq(struct ionic_qcq *qcq) { } +#endif + +#endif /* _IONIC_DEBUGFS_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.c b/drivers/net/ethernet/pensando/ionic/ionic_dev.c new file mode 100644 index 000000000000..d168a6435322 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.c @@ -0,0 +1,500 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/kernel.h> +#include <linux/types.h> +#include <linux/errno.h> +#include <linux/io.h> +#include <linux/slab.h> +#include <linux/etherdevice.h> +#include "ionic.h" +#include "ionic_dev.h" +#include "ionic_lif.h" + +void ionic_init_devinfo(struct ionic *ionic) +{ + struct ionic_dev *idev = &ionic->idev; + + idev->dev_info.asic_type = ioread8(&idev->dev_info_regs->asic_type); + idev->dev_info.asic_rev = ioread8(&idev->dev_info_regs->asic_rev); + + memcpy_fromio(idev->dev_info.fw_version, + idev->dev_info_regs->fw_version, + IONIC_DEVINFO_FWVERS_BUFLEN); + + memcpy_fromio(idev->dev_info.serial_num, + idev->dev_info_regs->serial_num, + IONIC_DEVINFO_SERIAL_BUFLEN); + + idev->dev_info.fw_version[IONIC_DEVINFO_FWVERS_BUFLEN] = 0; + idev->dev_info.serial_num[IONIC_DEVINFO_SERIAL_BUFLEN] = 0; + + dev_dbg(ionic->dev, "fw_version %s\n", idev->dev_info.fw_version); +} + +int ionic_dev_setup(struct ionic *ionic) +{ + struct ionic_dev_bar *bar = ionic->bars; + unsigned int num_bars = ionic->num_bars; + struct ionic_dev *idev = &ionic->idev; + struct device *dev = ionic->dev; + u32 sig; + + /* BAR0: dev_cmd and interrupts */ + if (num_bars < 1) { + dev_err(dev, "No bars found, aborting\n"); + return -EFAULT; + } + + if (bar->len < IONIC_BAR0_SIZE) { + dev_err(dev, "Resource bar size %lu too small, aborting\n", + bar->len); + return -EFAULT; + } + + idev->dev_info_regs = bar->vaddr + IONIC_BAR0_DEV_INFO_REGS_OFFSET; + idev->dev_cmd_regs = bar->vaddr + IONIC_BAR0_DEV_CMD_REGS_OFFSET; + idev->intr_status = bar->vaddr + IONIC_BAR0_INTR_STATUS_OFFSET; + idev->intr_ctrl = bar->vaddr + IONIC_BAR0_INTR_CTRL_OFFSET; + + sig = ioread32(&idev->dev_info_regs->signature); + if (sig != IONIC_DEV_INFO_SIGNATURE) { + dev_err(dev, "Incompatible firmware signature %x", sig); + return -EFAULT; + } + + ionic_init_devinfo(ionic); + + /* BAR1: doorbells */ + bar++; + if (num_bars < 2) { + dev_err(dev, "Doorbell bar missing, aborting\n"); + return -EFAULT; + } + + idev->db_pages = bar->vaddr; + idev->phy_db_pages = bar->bus_addr; + + return 0; +} + +void ionic_dev_teardown(struct ionic *ionic) +{ + /* place holder */ +} + +/* Devcmd Interface */ +u8 ionic_dev_cmd_status(struct ionic_dev *idev) +{ + return ioread8(&idev->dev_cmd_regs->comp.comp.status); +} + +bool ionic_dev_cmd_done(struct ionic_dev *idev) +{ + return ioread32(&idev->dev_cmd_regs->done) & IONIC_DEV_CMD_DONE; +} + +void ionic_dev_cmd_comp(struct ionic_dev *idev, union ionic_dev_cmd_comp *comp) +{ + memcpy_fromio(comp, &idev->dev_cmd_regs->comp, sizeof(*comp)); +} + +void ionic_dev_cmd_go(struct ionic_dev *idev, union ionic_dev_cmd *cmd) +{ + memcpy_toio(&idev->dev_cmd_regs->cmd, cmd, sizeof(*cmd)); + iowrite32(0, &idev->dev_cmd_regs->done); + iowrite32(1, &idev->dev_cmd_regs->doorbell); +} + +/* Device commands */ +void ionic_dev_cmd_identify(struct ionic_dev *idev, u8 ver) +{ + union ionic_dev_cmd cmd = { + .identify.opcode = IONIC_CMD_IDENTIFY, + .identify.ver = ver, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_init(struct ionic_dev *idev) +{ + union ionic_dev_cmd cmd = { + .init.opcode = IONIC_CMD_INIT, + .init.type = 0, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_reset(struct ionic_dev *idev) +{ + union ionic_dev_cmd cmd = { + .reset.opcode = IONIC_CMD_RESET, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +/* Port commands */ +void ionic_dev_cmd_port_identify(struct ionic_dev *idev) +{ + union ionic_dev_cmd cmd = { + .port_init.opcode = IONIC_CMD_PORT_IDENTIFY, + .port_init.index = 0, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_init(struct ionic_dev *idev) +{ + union ionic_dev_cmd cmd = { + .port_init.opcode = IONIC_CMD_PORT_INIT, + .port_init.index = 0, + .port_init.info_pa = cpu_to_le64(idev->port_info_pa), + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_reset(struct ionic_dev *idev) +{ + union ionic_dev_cmd cmd = { + .port_reset.opcode = IONIC_CMD_PORT_RESET, + .port_reset.index = 0, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_state(struct ionic_dev *idev, u8 state) +{ + union ionic_dev_cmd cmd = { + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR, + .port_setattr.index = 0, + .port_setattr.attr = IONIC_PORT_ATTR_STATE, + .port_setattr.state = state, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_speed(struct ionic_dev *idev, u32 speed) +{ + union ionic_dev_cmd cmd = { + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR, + .port_setattr.index = 0, + .port_setattr.attr = IONIC_PORT_ATTR_SPEED, + .port_setattr.speed = cpu_to_le32(speed), + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_autoneg(struct ionic_dev *idev, u8 an_enable) +{ + union ionic_dev_cmd cmd = { + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR, + .port_setattr.index = 0, + .port_setattr.attr = IONIC_PORT_ATTR_AUTONEG, + .port_setattr.an_enable = an_enable, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_fec(struct ionic_dev *idev, u8 fec_type) +{ + union ionic_dev_cmd cmd = { + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR, + .port_setattr.index = 0, + .port_setattr.attr = IONIC_PORT_ATTR_FEC, + .port_setattr.fec_type = fec_type, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type) +{ + union ionic_dev_cmd cmd = { + .port_setattr.opcode = IONIC_CMD_PORT_SETATTR, + .port_setattr.index = 0, + .port_setattr.attr = IONIC_PORT_ATTR_PAUSE, + .port_setattr.pause_type = pause_type, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +/* LIF commands */ +void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver) +{ + union ionic_dev_cmd cmd = { + .lif_identify.opcode = IONIC_CMD_LIF_IDENTIFY, + .lif_identify.type = type, + .lif_identify.ver = ver, + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_lif_init(struct ionic_dev *idev, u16 lif_index, + dma_addr_t info_pa) +{ + union ionic_dev_cmd cmd = { + .lif_init.opcode = IONIC_CMD_LIF_INIT, + .lif_init.index = cpu_to_le16(lif_index), + .lif_init.info_pa = cpu_to_le64(info_pa), + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_lif_reset(struct ionic_dev *idev, u16 lif_index) +{ + union ionic_dev_cmd cmd = { + .lif_init.opcode = IONIC_CMD_LIF_RESET, + .lif_init.index = cpu_to_le16(lif_index), + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +void ionic_dev_cmd_adminq_init(struct ionic_dev *idev, struct ionic_qcq *qcq, + u16 lif_index, u16 intr_index) +{ + struct ionic_queue *q = &qcq->q; + struct ionic_cq *cq = &qcq->cq; + + union ionic_dev_cmd cmd = { + .q_init.opcode = IONIC_CMD_Q_INIT, + .q_init.lif_index = cpu_to_le16(lif_index), + .q_init.type = q->type, + .q_init.index = cpu_to_le32(q->index), + .q_init.flags = cpu_to_le16(IONIC_QINIT_F_IRQ | + IONIC_QINIT_F_ENA), + .q_init.pid = cpu_to_le16(q->pid), + .q_init.intr_index = cpu_to_le16(intr_index), + .q_init.ring_size = ilog2(q->num_descs), + .q_init.ring_base = cpu_to_le64(q->base_pa), + .q_init.cq_ring_base = cpu_to_le64(cq->base_pa), + }; + + ionic_dev_cmd_go(idev, &cmd); +} + +int ionic_db_page_num(struct ionic_lif *lif, int pid) +{ + return (lif->hw_index * lif->dbid_count) + pid; +} + +int ionic_cq_init(struct ionic_lif *lif, struct ionic_cq *cq, + struct ionic_intr_info *intr, + unsigned int num_descs, size_t desc_size) +{ + struct ionic_cq_info *cur; + unsigned int ring_size; + unsigned int i; + + if (desc_size == 0 || !is_power_of_2(num_descs)) + return -EINVAL; + + ring_size = ilog2(num_descs); + if (ring_size < 2 || ring_size > 16) + return -EINVAL; + + cq->lif = lif; + cq->bound_intr = intr; + cq->num_descs = num_descs; + cq->desc_size = desc_size; + cq->tail = cq->info; + cq->done_color = 1; + + cur = cq->info; + + for (i = 0; i < num_descs; i++) { + if (i + 1 == num_descs) { + cur->next = cq->info; + cur->last = true; + } else { + cur->next = cur + 1; + } + cur->index = i; + cur++; + } + + return 0; +} + +void ionic_cq_map(struct ionic_cq *cq, void *base, dma_addr_t base_pa) +{ + struct ionic_cq_info *cur; + unsigned int i; + + cq->base = base; + cq->base_pa = base_pa; + + for (i = 0, cur = cq->info; i < cq->num_descs; i++, cur++) + cur->cq_desc = base + (i * cq->desc_size); +} + +void ionic_cq_bind(struct ionic_cq *cq, struct ionic_queue *q) +{ + cq->bound_q = q; +} + +unsigned int ionic_cq_service(struct ionic_cq *cq, unsigned int work_to_do, + ionic_cq_cb cb, ionic_cq_done_cb done_cb, + void *done_arg) +{ + unsigned int work_done = 0; + + if (work_to_do == 0) + return 0; + + while (cb(cq, cq->tail)) { + if (cq->tail->last) + cq->done_color = !cq->done_color; + cq->tail = cq->tail->next; + DEBUG_STATS_CQE_CNT(cq); + + if (++work_done >= work_to_do) + break; + } + + if (work_done && done_cb) + done_cb(done_arg); + + return work_done; +} + +int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev, + struct ionic_queue *q, unsigned int index, const char *name, + unsigned int num_descs, size_t desc_size, + size_t sg_desc_size, unsigned int pid) +{ + struct ionic_desc_info *cur; + unsigned int ring_size; + unsigned int i; + + if (desc_size == 0 || !is_power_of_2(num_descs)) + return -EINVAL; + + ring_size = ilog2(num_descs); + if (ring_size < 2 || ring_size > 16) + return -EINVAL; + + q->lif = lif; + q->idev = idev; + q->index = index; + q->num_descs = num_descs; + q->desc_size = desc_size; + q->sg_desc_size = sg_desc_size; + q->tail = q->info; + q->head = q->tail; + q->pid = pid; + + snprintf(q->name, sizeof(q->name), "L%d-%s%u", lif->index, name, index); + + cur = q->info; + + for (i = 0; i < num_descs; i++) { + if (i + 1 == num_descs) + cur->next = q->info; + else + cur->next = cur + 1; + cur->index = i; + cur->left = num_descs - i; + cur++; + } + + return 0; +} + +void ionic_q_map(struct ionic_queue *q, void *base, dma_addr_t base_pa) +{ + struct ionic_desc_info *cur; + unsigned int i; + + q->base = base; + q->base_pa = base_pa; + + for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) + cur->desc = base + (i * q->desc_size); +} + +void ionic_q_sg_map(struct ionic_queue *q, void *base, dma_addr_t base_pa) +{ + struct ionic_desc_info *cur; + unsigned int i; + + q->sg_base = base; + q->sg_base_pa = base_pa; + + for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) + cur->sg_desc = base + (i * q->sg_desc_size); +} + +void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, + void *cb_arg) +{ + struct device *dev = q->lif->ionic->dev; + struct ionic_lif *lif = q->lif; + + q->head->cb = cb; + q->head->cb_arg = cb_arg; + q->head = q->head->next; + + dev_dbg(dev, "lif=%d qname=%s qid=%d qtype=%d p_index=%d ringdb=%d\n", + q->lif->index, q->name, q->hw_type, q->hw_index, + q->head->index, ring_doorbell); + + if (ring_doorbell) + ionic_dbell_ring(lif->kern_dbpage, q->hw_type, + q->dbval | q->head->index); +} + +static bool ionic_q_is_posted(struct ionic_queue *q, unsigned int pos) +{ + unsigned int mask, tail, head; + + mask = q->num_descs - 1; + tail = q->tail->index; + head = q->head->index; + + return ((pos - tail) & mask) < ((head - tail) & mask); +} + +void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, + unsigned int stop_index) +{ + struct ionic_desc_info *desc_info; + ionic_desc_cb cb; + void *cb_arg; + + /* check for empty queue */ + if (q->tail->index == q->head->index) + return; + + /* stop index must be for a descriptor that is not yet completed */ + if (unlikely(!ionic_q_is_posted(q, stop_index))) + dev_err(q->lif->ionic->dev, + "ionic stop is not posted %s stop %u tail %u head %u\n", + q->name, stop_index, q->tail->index, q->head->index); + + do { + desc_info = q->tail; + q->tail = desc_info->next; + + cb = desc_info->cb; + cb_arg = desc_info->cb_arg; + + desc_info->cb = NULL; + desc_info->cb_arg = NULL; + + if (cb) + cb(q, desc_info, cq_info, cb_arg); + } while (desc_info->index != stop_index); +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_dev.h b/drivers/net/ethernet/pensando/ionic/ionic_dev.h new file mode 100644 index 000000000000..9610aeb7d5f4 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_dev.h @@ -0,0 +1,299 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_DEV_H_ +#define _IONIC_DEV_H_ + +#include <linux/mutex.h> +#include <linux/workqueue.h> + +#include "ionic_if.h" +#include "ionic_regs.h" + +#define IONIC_MIN_MTU ETH_MIN_MTU +#define IONIC_MAX_MTU 9194 +#define IONIC_MAX_TXRX_DESC 16384 +#define IONIC_MIN_TXRX_DESC 16 +#define IONIC_DEF_TXRX_DESC 4096 +#define IONIC_LIFS_MAX 1024 +#define IONIC_ITR_COAL_USEC_DEFAULT 64 + +#define IONIC_DEV_CMD_REG_VERSION 1 +#define IONIC_DEV_INFO_REG_COUNT 32 +#define IONIC_DEV_CMD_REG_COUNT 32 + +struct ionic_dev_bar { + void __iomem *vaddr; + phys_addr_t bus_addr; + unsigned long len; + int res_index; +}; + +/* Registers */ +static_assert(sizeof(struct ionic_intr) == 32); + +static_assert(sizeof(struct ionic_doorbell) == 8); +static_assert(sizeof(struct ionic_intr_status) == 8); +static_assert(sizeof(union ionic_dev_regs) == 4096); +static_assert(sizeof(union ionic_dev_info_regs) == 2048); +static_assert(sizeof(union ionic_dev_cmd_regs) == 2048); +static_assert(sizeof(struct ionic_lif_stats) == 1024); + +static_assert(sizeof(struct ionic_admin_cmd) == 64); +static_assert(sizeof(struct ionic_admin_comp) == 16); +static_assert(sizeof(struct ionic_nop_cmd) == 64); +static_assert(sizeof(struct ionic_nop_comp) == 16); + +/* Device commands */ +static_assert(sizeof(struct ionic_dev_identify_cmd) == 64); +static_assert(sizeof(struct ionic_dev_identify_comp) == 16); +static_assert(sizeof(struct ionic_dev_init_cmd) == 64); +static_assert(sizeof(struct ionic_dev_init_comp) == 16); +static_assert(sizeof(struct ionic_dev_reset_cmd) == 64); +static_assert(sizeof(struct ionic_dev_reset_comp) == 16); +static_assert(sizeof(struct ionic_dev_getattr_cmd) == 64); +static_assert(sizeof(struct ionic_dev_getattr_comp) == 16); +static_assert(sizeof(struct ionic_dev_setattr_cmd) == 64); +static_assert(sizeof(struct ionic_dev_setattr_comp) == 16); + +/* Port commands */ +static_assert(sizeof(struct ionic_port_identify_cmd) == 64); +static_assert(sizeof(struct ionic_port_identify_comp) == 16); +static_assert(sizeof(struct ionic_port_init_cmd) == 64); +static_assert(sizeof(struct ionic_port_init_comp) == 16); +static_assert(sizeof(struct ionic_port_reset_cmd) == 64); +static_assert(sizeof(struct ionic_port_reset_comp) == 16); +static_assert(sizeof(struct ionic_port_getattr_cmd) == 64); +static_assert(sizeof(struct ionic_port_getattr_comp) == 16); +static_assert(sizeof(struct ionic_port_setattr_cmd) == 64); +static_assert(sizeof(struct ionic_port_setattr_comp) == 16); + +/* LIF commands */ +static_assert(sizeof(struct ionic_lif_init_cmd) == 64); +static_assert(sizeof(struct ionic_lif_init_comp) == 16); +static_assert(sizeof(struct ionic_lif_reset_cmd) == 64); +static_assert(sizeof(ionic_lif_reset_comp) == 16); +static_assert(sizeof(struct ionic_lif_getattr_cmd) == 64); +static_assert(sizeof(struct ionic_lif_getattr_comp) == 16); +static_assert(sizeof(struct ionic_lif_setattr_cmd) == 64); +static_assert(sizeof(struct ionic_lif_setattr_comp) == 16); + +static_assert(sizeof(struct ionic_q_init_cmd) == 64); +static_assert(sizeof(struct ionic_q_init_comp) == 16); +static_assert(sizeof(struct ionic_q_control_cmd) == 64); +static_assert(sizeof(ionic_q_control_comp) == 16); + +static_assert(sizeof(struct ionic_rx_mode_set_cmd) == 64); +static_assert(sizeof(ionic_rx_mode_set_comp) == 16); +static_assert(sizeof(struct ionic_rx_filter_add_cmd) == 64); +static_assert(sizeof(struct ionic_rx_filter_add_comp) == 16); +static_assert(sizeof(struct ionic_rx_filter_del_cmd) == 64); +static_assert(sizeof(ionic_rx_filter_del_comp) == 16); + +/* RDMA commands */ +static_assert(sizeof(struct ionic_rdma_reset_cmd) == 64); +static_assert(sizeof(struct ionic_rdma_queue_cmd) == 64); + +/* Events */ +static_assert(sizeof(struct ionic_notifyq_cmd) == 4); +static_assert(sizeof(union ionic_notifyq_comp) == 64); +static_assert(sizeof(struct ionic_notifyq_event) == 64); +static_assert(sizeof(struct ionic_link_change_event) == 64); +static_assert(sizeof(struct ionic_reset_event) == 64); +static_assert(sizeof(struct ionic_heartbeat_event) == 64); +static_assert(sizeof(struct ionic_log_event) == 64); + +/* I/O */ +static_assert(sizeof(struct ionic_txq_desc) == 16); +static_assert(sizeof(struct ionic_txq_sg_desc) == 128); +static_assert(sizeof(struct ionic_txq_comp) == 16); + +static_assert(sizeof(struct ionic_rxq_desc) == 16); +static_assert(sizeof(struct ionic_rxq_sg_desc) == 128); +static_assert(sizeof(struct ionic_rxq_comp) == 16); + +struct ionic_devinfo { + u8 asic_type; + u8 asic_rev; + char fw_version[IONIC_DEVINFO_FWVERS_BUFLEN + 1]; + char serial_num[IONIC_DEVINFO_SERIAL_BUFLEN + 1]; +}; + +struct ionic_dev { + union ionic_dev_info_regs __iomem *dev_info_regs; + union ionic_dev_cmd_regs __iomem *dev_cmd_regs; + + u64 __iomem *db_pages; + dma_addr_t phy_db_pages; + + struct ionic_intr __iomem *intr_ctrl; + u64 __iomem *intr_status; + + u32 port_info_sz; + struct ionic_port_info *port_info; + dma_addr_t port_info_pa; + + struct ionic_devinfo dev_info; +}; + +struct ionic_cq_info { + void *cq_desc; + struct ionic_cq_info *next; + unsigned int index; + bool last; +}; + +struct ionic_queue; +struct ionic_qcq; +struct ionic_desc_info; + +typedef void (*ionic_desc_cb)(struct ionic_queue *q, + struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, void *cb_arg); + +struct ionic_desc_info { + void *desc; + void *sg_desc; + struct ionic_desc_info *next; + unsigned int index; + unsigned int left; + ionic_desc_cb cb; + void *cb_arg; +}; + +#define QUEUE_NAME_MAX_SZ 32 + +struct ionic_queue { + u64 dbell_count; + u64 drop; + u64 stop; + u64 wake; + struct ionic_lif *lif; + struct ionic_desc_info *info; + struct ionic_desc_info *tail; + struct ionic_desc_info *head; + struct ionic_dev *idev; + unsigned int index; + unsigned int type; + unsigned int hw_index; + unsigned int hw_type; + u64 dbval; + void *base; + void *sg_base; + dma_addr_t base_pa; + dma_addr_t sg_base_pa; + unsigned int num_descs; + unsigned int desc_size; + unsigned int sg_desc_size; + unsigned int pid; + char name[QUEUE_NAME_MAX_SZ]; +}; + +#define INTR_INDEX_NOT_ASSIGNED -1 +#define INTR_NAME_MAX_SZ 32 + +struct ionic_intr_info { + char name[INTR_NAME_MAX_SZ]; + unsigned int index; + unsigned int vector; + u64 rearm_count; + unsigned int cpu; + cpumask_t affinity_mask; +}; + +struct ionic_cq { + void *base; + dma_addr_t base_pa; + struct ionic_lif *lif; + struct ionic_cq_info *info; + struct ionic_cq_info *tail; + struct ionic_queue *bound_q; + struct ionic_intr_info *bound_intr; + bool done_color; + unsigned int num_descs; + u64 compl_count; + unsigned int desc_size; +}; + +struct ionic; + +static inline void ionic_intr_init(struct ionic_dev *idev, + struct ionic_intr_info *intr, + unsigned long index) +{ + ionic_intr_clean(idev->intr_ctrl, index); + intr->index = index; +} + +static inline unsigned int ionic_q_space_avail(struct ionic_queue *q) +{ + unsigned int avail = q->tail->index; + + if (q->head->index >= avail) + avail += q->head->left - 1; + else + avail -= q->head->index + 1; + + return avail; +} + +static inline bool ionic_q_has_space(struct ionic_queue *q, unsigned int want) +{ + return ionic_q_space_avail(q) >= want; +} + +void ionic_init_devinfo(struct ionic *ionic); +int ionic_dev_setup(struct ionic *ionic); +void ionic_dev_teardown(struct ionic *ionic); + +void ionic_dev_cmd_go(struct ionic_dev *idev, union ionic_dev_cmd *cmd); +u8 ionic_dev_cmd_status(struct ionic_dev *idev); +bool ionic_dev_cmd_done(struct ionic_dev *idev); +void ionic_dev_cmd_comp(struct ionic_dev *idev, union ionic_dev_cmd_comp *comp); + +void ionic_dev_cmd_identify(struct ionic_dev *idev, u8 ver); +void ionic_dev_cmd_init(struct ionic_dev *idev); +void ionic_dev_cmd_reset(struct ionic_dev *idev); + +void ionic_dev_cmd_port_identify(struct ionic_dev *idev); +void ionic_dev_cmd_port_init(struct ionic_dev *idev); +void ionic_dev_cmd_port_reset(struct ionic_dev *idev); +void ionic_dev_cmd_port_state(struct ionic_dev *idev, u8 state); +void ionic_dev_cmd_port_speed(struct ionic_dev *idev, u32 speed); +void ionic_dev_cmd_port_autoneg(struct ionic_dev *idev, u8 an_enable); +void ionic_dev_cmd_port_fec(struct ionic_dev *idev, u8 fec_type); +void ionic_dev_cmd_port_pause(struct ionic_dev *idev, u8 pause_type); + +void ionic_dev_cmd_lif_identify(struct ionic_dev *idev, u8 type, u8 ver); +void ionic_dev_cmd_lif_init(struct ionic_dev *idev, u16 lif_index, + dma_addr_t addr); +void ionic_dev_cmd_lif_reset(struct ionic_dev *idev, u16 lif_index); +void ionic_dev_cmd_adminq_init(struct ionic_dev *idev, struct ionic_qcq *qcq, + u16 lif_index, u16 intr_index); + +int ionic_db_page_num(struct ionic_lif *lif, int pid); + +int ionic_cq_init(struct ionic_lif *lif, struct ionic_cq *cq, + struct ionic_intr_info *intr, + unsigned int num_descs, size_t desc_size); +void ionic_cq_map(struct ionic_cq *cq, void *base, dma_addr_t base_pa); +void ionic_cq_bind(struct ionic_cq *cq, struct ionic_queue *q); +typedef bool (*ionic_cq_cb)(struct ionic_cq *cq, struct ionic_cq_info *cq_info); +typedef void (*ionic_cq_done_cb)(void *done_arg); +unsigned int ionic_cq_service(struct ionic_cq *cq, unsigned int work_to_do, + ionic_cq_cb cb, ionic_cq_done_cb done_cb, + void *done_arg); + +int ionic_q_init(struct ionic_lif *lif, struct ionic_dev *idev, + struct ionic_queue *q, unsigned int index, const char *name, + unsigned int num_descs, size_t desc_size, + size_t sg_desc_size, unsigned int pid); +void ionic_q_map(struct ionic_queue *q, void *base, dma_addr_t base_pa); +void ionic_q_sg_map(struct ionic_queue *q, void *base, dma_addr_t base_pa); +void ionic_q_post(struct ionic_queue *q, bool ring_doorbell, ionic_desc_cb cb, + void *cb_arg); +void ionic_q_rewind(struct ionic_queue *q, struct ionic_desc_info *start); +void ionic_q_service(struct ionic_queue *q, struct ionic_cq_info *cq_info, + unsigned int stop_index); + +#endif /* _IONIC_DEV_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.c b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c new file mode 100644 index 000000000000..af1647afa4e8 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.c @@ -0,0 +1,99 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/module.h> +#include <linux/netdevice.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_devlink.h" + +static int ionic_dl_info_get(struct devlink *dl, struct devlink_info_req *req, + struct netlink_ext_ack *extack) +{ + struct ionic *ionic = devlink_priv(dl); + struct ionic_dev *idev = &ionic->idev; + char buf[16]; + int err = 0; + + err = devlink_info_driver_name_put(req, IONIC_DRV_NAME); + if (err) + goto info_out; + + err = devlink_info_version_running_put(req, + DEVLINK_INFO_VERSION_GENERIC_FW, + idev->dev_info.fw_version); + if (err) + goto info_out; + + snprintf(buf, sizeof(buf), "0x%x", idev->dev_info.asic_type); + err = devlink_info_version_fixed_put(req, + DEVLINK_INFO_VERSION_GENERIC_ASIC_ID, + buf); + if (err) + goto info_out; + + snprintf(buf, sizeof(buf), "0x%x", idev->dev_info.asic_rev); + err = devlink_info_version_fixed_put(req, + DEVLINK_INFO_VERSION_GENERIC_ASIC_REV, + buf); + if (err) + goto info_out; + + err = devlink_info_serial_number_put(req, idev->dev_info.serial_num); + +info_out: + return err; +} + +static const struct devlink_ops ionic_dl_ops = { + .info_get = ionic_dl_info_get, +}; + +struct ionic *ionic_devlink_alloc(struct device *dev) +{ + struct devlink *dl; + + dl = devlink_alloc(&ionic_dl_ops, sizeof(struct ionic)); + + return devlink_priv(dl); +} + +void ionic_devlink_free(struct ionic *ionic) +{ + struct devlink *dl = priv_to_devlink(ionic); + + devlink_free(dl); +} + +int ionic_devlink_register(struct ionic *ionic) +{ + struct devlink *dl = priv_to_devlink(ionic); + int err; + + err = devlink_register(dl, ionic->dev); + if (err) { + dev_warn(ionic->dev, "devlink_register failed: %d\n", err); + return err; + } + + devlink_port_attrs_set(&ionic->dl_port, DEVLINK_PORT_FLAVOUR_PHYSICAL, + 0, false, 0, NULL, 0); + err = devlink_port_register(dl, &ionic->dl_port, 0); + if (err) + dev_err(ionic->dev, "devlink_port_register failed: %d\n", err); + else + devlink_port_type_eth_set(&ionic->dl_port, + ionic->master_lif->netdev); + + return err; +} + +void ionic_devlink_unregister(struct ionic *ionic) +{ + struct devlink *dl = priv_to_devlink(ionic); + + devlink_port_unregister(&ionic->dl_port); + devlink_unregister(dl); +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_devlink.h b/drivers/net/ethernet/pensando/ionic/ionic_devlink.h new file mode 100644 index 000000000000..0690172fc57a --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_devlink.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_DEVLINK_H_ +#define _IONIC_DEVLINK_H_ + +#include <net/devlink.h> + +struct ionic *ionic_devlink_alloc(struct device *dev); +void ionic_devlink_free(struct ionic *ionic); +int ionic_devlink_register(struct ionic *ionic); +void ionic_devlink_unregister(struct ionic *ionic); + +#endif /* _IONIC_DEVLINK_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c new file mode 100644 index 000000000000..7d10265f782a --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.c @@ -0,0 +1,779 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/module.h> +#include <linux/netdevice.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_ethtool.h" +#include "ionic_stats.h" + +static const char ionic_priv_flags_strings[][ETH_GSTRING_LEN] = { +#define PRIV_F_SW_DBG_STATS BIT(0) + "sw-dbg-stats", +}; +#define PRIV_FLAGS_COUNT ARRAY_SIZE(ionic_priv_flags_strings) + +static void ionic_get_stats_strings(struct ionic_lif *lif, u8 *buf) +{ + u32 i; + + for (i = 0; i < ionic_num_stats_grps; i++) + ionic_stats_groups[i].get_strings(lif, &buf); +} + +static void ionic_get_stats(struct net_device *netdev, + struct ethtool_stats *stats, u64 *buf) +{ + struct ionic_lif *lif; + u32 i; + + lif = netdev_priv(netdev); + + memset(buf, 0, stats->n_stats * sizeof(*buf)); + for (i = 0; i < ionic_num_stats_grps; i++) + ionic_stats_groups[i].get_values(lif, &buf); +} + +static int ionic_get_stats_count(struct ionic_lif *lif) +{ + int i, num_stats = 0; + + for (i = 0; i < ionic_num_stats_grps; i++) + num_stats += ionic_stats_groups[i].get_count(lif); + + return num_stats; +} + +static int ionic_get_sset_count(struct net_device *netdev, int sset) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int count = 0; + + switch (sset) { + case ETH_SS_STATS: + count = ionic_get_stats_count(lif); + break; + case ETH_SS_PRIV_FLAGS: + count = PRIV_FLAGS_COUNT; + break; + } + return count; +} + +static void ionic_get_strings(struct net_device *netdev, + u32 sset, u8 *buf) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + switch (sset) { + case ETH_SS_STATS: + ionic_get_stats_strings(lif, buf); + break; + case ETH_SS_PRIV_FLAGS: + memcpy(buf, ionic_priv_flags_strings, + PRIV_FLAGS_COUNT * ETH_GSTRING_LEN); + break; + } +} + +static void ionic_get_drvinfo(struct net_device *netdev, + struct ethtool_drvinfo *drvinfo) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic *ionic = lif->ionic; + + strlcpy(drvinfo->driver, IONIC_DRV_NAME, sizeof(drvinfo->driver)); + strlcpy(drvinfo->version, IONIC_DRV_VERSION, sizeof(drvinfo->version)); + strlcpy(drvinfo->fw_version, ionic->idev.dev_info.fw_version, + sizeof(drvinfo->fw_version)); + strlcpy(drvinfo->bus_info, ionic_bus_info(ionic), + sizeof(drvinfo->bus_info)); +} + +static int ionic_get_regs_len(struct net_device *netdev) +{ + return (IONIC_DEV_INFO_REG_COUNT + IONIC_DEV_CMD_REG_COUNT) * sizeof(u32); +} + +static void ionic_get_regs(struct net_device *netdev, struct ethtool_regs *regs, + void *p) +{ + struct ionic_lif *lif = netdev_priv(netdev); + unsigned int size; + + regs->version = IONIC_DEV_CMD_REG_VERSION; + + size = IONIC_DEV_INFO_REG_COUNT * sizeof(u32); + memcpy_fromio(p, lif->ionic->idev.dev_info_regs->words, size); + + size = IONIC_DEV_CMD_REG_COUNT * sizeof(u32); + memcpy_fromio(p, lif->ionic->idev.dev_cmd_regs->words, size); +} + +static int ionic_get_link_ksettings(struct net_device *netdev, + struct ethtool_link_ksettings *ks) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_dev *idev = &lif->ionic->idev; + int copper_seen = 0; + + ethtool_link_ksettings_zero_link_mode(ks, supported); + + /* The port_info data is found in a DMA space that the NIC keeps + * up-to-date, so there's no need to request the data from the + * NIC, we already have it in our memory space. + */ + + switch (le16_to_cpu(idev->port_info->status.xcvr.pid)) { + /* Copper */ + case IONIC_XCVR_PID_QSFP_100G_CR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 100000baseCR4_Full); + copper_seen++; + break; + case IONIC_XCVR_PID_QSFP_40GBASE_CR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseCR4_Full); + copper_seen++; + break; + case IONIC_XCVR_PID_SFP_25GBASE_CR_S: + case IONIC_XCVR_PID_SFP_25GBASE_CR_L: + case IONIC_XCVR_PID_SFP_25GBASE_CR_N: + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseCR_Full); + copper_seen++; + break; + case IONIC_XCVR_PID_SFP_10GBASE_AOC: + case IONIC_XCVR_PID_SFP_10GBASE_CU: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseCR_Full); + copper_seen++; + break; + + /* Fibre */ + case IONIC_XCVR_PID_QSFP_100G_SR4: + case IONIC_XCVR_PID_QSFP_100G_AOC: + ethtool_link_ksettings_add_link_mode(ks, supported, + 100000baseSR4_Full); + break; + case IONIC_XCVR_PID_QSFP_100G_LR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 100000baseLR4_ER4_Full); + break; + case IONIC_XCVR_PID_QSFP_100G_ER4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 100000baseLR4_ER4_Full); + break; + case IONIC_XCVR_PID_QSFP_40GBASE_SR4: + case IONIC_XCVR_PID_QSFP_40GBASE_AOC: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseSR4_Full); + break; + case IONIC_XCVR_PID_QSFP_40GBASE_LR4: + ethtool_link_ksettings_add_link_mode(ks, supported, + 40000baseLR4_Full); + break; + case IONIC_XCVR_PID_SFP_25GBASE_SR: + case IONIC_XCVR_PID_SFP_25GBASE_AOC: + ethtool_link_ksettings_add_link_mode(ks, supported, + 25000baseSR_Full); + break; + case IONIC_XCVR_PID_SFP_10GBASE_SR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseSR_Full); + break; + case IONIC_XCVR_PID_SFP_10GBASE_LR: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLR_Full); + break; + case IONIC_XCVR_PID_SFP_10GBASE_LRM: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseLRM_Full); + break; + case IONIC_XCVR_PID_SFP_10GBASE_ER: + ethtool_link_ksettings_add_link_mode(ks, supported, + 10000baseER_Full); + break; + case IONIC_XCVR_PID_UNKNOWN: + /* This means there's no module plugged in */ + break; + default: + dev_info(lif->ionic->dev, "unknown xcvr type pid=%d / 0x%x\n", + idev->port_info->status.xcvr.pid, + idev->port_info->status.xcvr.pid); + break; + } + + bitmap_copy(ks->link_modes.advertising, ks->link_modes.supported, + __ETHTOOL_LINK_MODE_MASK_NBITS); + + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER); + ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); + if (idev->port_info->config.fec_type == IONIC_PORT_FEC_TYPE_FC) + ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_BASER); + else if (idev->port_info->config.fec_type == IONIC_PORT_FEC_TYPE_RS) + ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); + + ethtool_link_ksettings_add_link_mode(ks, supported, FIBRE); + ethtool_link_ksettings_add_link_mode(ks, supported, Pause); + + if (idev->port_info->status.xcvr.phy == IONIC_PHY_TYPE_COPPER || + copper_seen) + ks->base.port = PORT_DA; + else if (idev->port_info->status.xcvr.phy == IONIC_PHY_TYPE_FIBER) + ks->base.port = PORT_FIBRE; + else + ks->base.port = PORT_NONE; + + if (ks->base.port != PORT_NONE) { + ks->base.speed = le32_to_cpu(lif->info->status.link_speed); + + if (le16_to_cpu(lif->info->status.link_status)) + ks->base.duplex = DUPLEX_FULL; + else + ks->base.duplex = DUPLEX_UNKNOWN; + + ethtool_link_ksettings_add_link_mode(ks, supported, Autoneg); + + if (idev->port_info->config.an_enable) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + Autoneg); + ks->base.autoneg = AUTONEG_ENABLE; + } + } + + return 0; +} + +static int ionic_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *ks) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic *ionic = lif->ionic; + struct ionic_dev *idev; + u32 req_rs, req_fc; + u8 fec_type; + int err = 0; + + idev = &lif->ionic->idev; + fec_type = IONIC_PORT_FEC_TYPE_NONE; + + /* set autoneg */ + if (ks->base.autoneg != idev->port_info->config.an_enable) { + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_autoneg(idev, ks->base.autoneg); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + if (err) + return err; + } + + /* set speed */ + if (ks->base.speed != le32_to_cpu(idev->port_info->config.speed)) { + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_speed(idev, ks->base.speed); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + if (err) + return err; + } + + /* set FEC */ + req_rs = ethtool_link_ksettings_test_link_mode(ks, advertising, FEC_RS); + req_fc = ethtool_link_ksettings_test_link_mode(ks, advertising, FEC_BASER); + if (req_rs && req_fc) { + netdev_info(netdev, "Only select one FEC mode at a time\n"); + return -EINVAL; + } else if (req_fc) { + fec_type = IONIC_PORT_FEC_TYPE_FC; + } else if (req_rs) { + fec_type = IONIC_PORT_FEC_TYPE_RS; + } else if (!(req_rs | req_fc)) { + fec_type = IONIC_PORT_FEC_TYPE_NONE; + } + + if (fec_type != idev->port_info->config.fec_type) { + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_fec(idev, fec_type); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + if (err) + return err; + } + + return 0; +} + +static void ionic_get_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct ionic_lif *lif = netdev_priv(netdev); + u8 pause_type; + + pause->autoneg = 0; + + pause_type = lif->ionic->idev.port_info->config.pause_type; + if (pause_type) { + pause->rx_pause = pause_type & IONIC_PAUSE_F_RX ? 1 : 0; + pause->tx_pause = pause_type & IONIC_PAUSE_F_TX ? 1 : 0; + } +} + +static int ionic_set_pauseparam(struct net_device *netdev, + struct ethtool_pauseparam *pause) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic *ionic = lif->ionic; + u32 requested_pause; + int err; + + if (pause->autoneg) + return -EOPNOTSUPP; + + /* change both at the same time */ + requested_pause = IONIC_PORT_PAUSE_TYPE_LINK; + if (pause->rx_pause) + requested_pause |= IONIC_PAUSE_F_RX; + if (pause->tx_pause) + requested_pause |= IONIC_PAUSE_F_TX; + + if (requested_pause == lif->ionic->idev.port_info->config.pause_type) + return 0; + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_pause(&lif->ionic->idev, requested_pause); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + if (err) + return err; + + return 0; +} + +static int ionic_get_coalesce(struct net_device *netdev, + struct ethtool_coalesce *coalesce) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + /* Tx uses Rx interrupt */ + coalesce->tx_coalesce_usecs = lif->rx_coalesce_usecs; + coalesce->rx_coalesce_usecs = lif->rx_coalesce_usecs; + + return 0; +} + +static int ionic_set_coalesce(struct net_device *netdev, + struct ethtool_coalesce *coalesce) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_identity *ident; + struct ionic_qcq *qcq; + unsigned int i; + u32 usecs; + u32 coal; + + if (coalesce->rx_max_coalesced_frames || + coalesce->rx_coalesce_usecs_irq || + coalesce->rx_max_coalesced_frames_irq || + coalesce->tx_max_coalesced_frames || + coalesce->tx_coalesce_usecs_irq || + coalesce->tx_max_coalesced_frames_irq || + coalesce->stats_block_coalesce_usecs || + coalesce->use_adaptive_rx_coalesce || + coalesce->use_adaptive_tx_coalesce || + coalesce->pkt_rate_low || + coalesce->rx_coalesce_usecs_low || + coalesce->rx_max_coalesced_frames_low || + coalesce->tx_coalesce_usecs_low || + coalesce->tx_max_coalesced_frames_low || + coalesce->pkt_rate_high || + coalesce->rx_coalesce_usecs_high || + coalesce->rx_max_coalesced_frames_high || + coalesce->tx_coalesce_usecs_high || + coalesce->tx_max_coalesced_frames_high || + coalesce->rate_sample_interval) + return -EINVAL; + + ident = &lif->ionic->ident; + if (ident->dev.intr_coal_div == 0) { + netdev_warn(netdev, "bad HW value in dev.intr_coal_div = %d\n", + ident->dev.intr_coal_div); + return -EIO; + } + + /* Tx uses Rx interrupt, so only change Rx */ + if (coalesce->tx_coalesce_usecs != lif->rx_coalesce_usecs) { + netdev_warn(netdev, "only the rx-usecs can be changed\n"); + return -EINVAL; + } + + coal = ionic_coal_usec_to_hw(lif->ionic, coalesce->rx_coalesce_usecs); + + if (coal > IONIC_INTR_CTRL_COAL_MAX) + return -ERANGE; + + /* If they asked for non-zero and it resolved to zero, bump it up */ + if (!coal && coalesce->rx_coalesce_usecs) + coal = 1; + + /* Convert it back to get device resolution */ + usecs = ionic_coal_hw_to_usec(lif->ionic, coal); + + if (usecs != lif->rx_coalesce_usecs) { + lif->rx_coalesce_usecs = usecs; + + if (test_bit(IONIC_LIF_UP, lif->state)) { + for (i = 0; i < lif->nxqs; i++) { + qcq = lif->rxqcqs[i].qcq; + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + qcq->intr.index, coal); + } + } + } + + return 0; +} + +static void ionic_get_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + ring->tx_max_pending = IONIC_MAX_TXRX_DESC; + ring->tx_pending = lif->ntxq_descs; + ring->rx_max_pending = IONIC_MAX_TXRX_DESC; + ring->rx_pending = lif->nrxq_descs; +} + +static int ionic_set_ringparam(struct net_device *netdev, + struct ethtool_ringparam *ring) +{ + struct ionic_lif *lif = netdev_priv(netdev); + bool running; + + if (ring->rx_mini_pending || ring->rx_jumbo_pending) { + netdev_info(netdev, "Changing jumbo or mini descriptors not supported\n"); + return -EINVAL; + } + + if (!is_power_of_2(ring->tx_pending) || + !is_power_of_2(ring->rx_pending)) { + netdev_info(netdev, "Descriptor count must be a power of 2\n"); + return -EINVAL; + } + + /* if nothing to do return success */ + if (ring->tx_pending == lif->ntxq_descs && + ring->rx_pending == lif->nrxq_descs) + return 0; + + if (!ionic_wait_for_bit(lif, IONIC_LIF_QUEUE_RESET)) + return -EBUSY; + + running = test_bit(IONIC_LIF_UP, lif->state); + if (running) + ionic_stop(netdev); + + lif->ntxq_descs = ring->tx_pending; + lif->nrxq_descs = ring->rx_pending; + + if (running) + ionic_open(netdev); + clear_bit(IONIC_LIF_QUEUE_RESET, lif->state); + + return 0; +} + +static void ionic_get_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + /* report maximum channels */ + ch->max_combined = lif->ionic->ntxqs_per_lif; + + /* report current channels */ + ch->combined_count = lif->nxqs; +} + +static int ionic_set_channels(struct net_device *netdev, + struct ethtool_channels *ch) +{ + struct ionic_lif *lif = netdev_priv(netdev); + bool running; + + if (!ch->combined_count || ch->other_count || + ch->rx_count || ch->tx_count) + return -EINVAL; + + if (ch->combined_count == lif->nxqs) + return 0; + + if (!ionic_wait_for_bit(lif, IONIC_LIF_QUEUE_RESET)) + return -EBUSY; + + running = test_bit(IONIC_LIF_UP, lif->state); + if (running) + ionic_stop(netdev); + + lif->nxqs = ch->combined_count; + + if (running) + ionic_open(netdev); + clear_bit(IONIC_LIF_QUEUE_RESET, lif->state); + + return 0; +} + +static u32 ionic_get_priv_flags(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + u32 priv_flags = 0; + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) + priv_flags |= PRIV_F_SW_DBG_STATS; + + return priv_flags; +} + +static int ionic_set_priv_flags(struct net_device *netdev, u32 priv_flags) +{ + struct ionic_lif *lif = netdev_priv(netdev); + u32 flags = lif->flags; + + clear_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state); + if (priv_flags & PRIV_F_SW_DBG_STATS) + set_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state); + + if (flags != lif->flags) + lif->flags = flags; + + return 0; +} + +static int ionic_get_rxnfc(struct net_device *netdev, + struct ethtool_rxnfc *info, u32 *rules) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int err = 0; + + switch (info->cmd) { + case ETHTOOL_GRXRINGS: + info->data = lif->nxqs; + break; + default: + netdev_err(netdev, "Command parameter %d is not supported\n", + info->cmd); + err = -EOPNOTSUPP; + } + + return err; +} + +static u32 ionic_get_rxfh_indir_size(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + return le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); +} + +static u32 ionic_get_rxfh_key_size(struct net_device *netdev) +{ + return IONIC_RSS_HASH_KEY_SIZE; +} + +static int ionic_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct ionic_lif *lif = netdev_priv(netdev); + unsigned int i, tbl_sz; + + if (indir) { + tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); + for (i = 0; i < tbl_sz; i++) + indir[i] = lif->rss_ind_tbl[i]; + } + + if (key) + memcpy(key, lif->rss_hash_key, IONIC_RSS_HASH_KEY_SIZE); + + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; + + return 0; +} + +static int ionic_set_rxfh(struct net_device *netdev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int err; + + if (hfunc != ETH_RSS_HASH_NO_CHANGE && hfunc != ETH_RSS_HASH_TOP) + return -EOPNOTSUPP; + + err = ionic_lif_rss_config(lif, lif->rss_types, key, indir); + if (err) + return err; + + return 0; +} + +static int ionic_set_tunable(struct net_device *dev, + const struct ethtool_tunable *tuna, + const void *data) +{ + struct ionic_lif *lif = netdev_priv(dev); + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + lif->rx_copybreak = *(u32 *)data; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int ionic_get_tunable(struct net_device *netdev, + const struct ethtool_tunable *tuna, void *data) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + switch (tuna->id) { + case ETHTOOL_RX_COPYBREAK: + *(u32 *)data = lif->rx_copybreak; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static int ionic_get_module_info(struct net_device *netdev, + struct ethtool_modinfo *modinfo) + +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_dev *idev = &lif->ionic->idev; + struct ionic_xcvr_status *xcvr; + + xcvr = &idev->port_info->status.xcvr; + + /* report the module data type and length */ + switch (xcvr->sprom[0]) { + case 0x03: /* SFP */ + modinfo->type = ETH_MODULE_SFF_8079; + modinfo->eeprom_len = ETH_MODULE_SFF_8079_LEN; + break; + case 0x0D: /* QSFP */ + case 0x11: /* QSFP28 */ + modinfo->type = ETH_MODULE_SFF_8436; + modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; + break; + default: + netdev_info(netdev, "unknown xcvr type 0x%02x\n", + xcvr->sprom[0]); + break; + } + + return 0; +} + +static int ionic_get_module_eeprom(struct net_device *netdev, + struct ethtool_eeprom *ee, + u8 *data) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_dev *idev = &lif->ionic->idev; + struct ionic_xcvr_status *xcvr; + char tbuf[sizeof(xcvr->sprom)]; + int count = 10; + u32 len; + + /* The NIC keeps the module prom up-to-date in the DMA space + * so we can simply copy the module bytes into the data buffer. + */ + xcvr = &idev->port_info->status.xcvr; + len = min_t(u32, sizeof(xcvr->sprom), ee->len); + + do { + memcpy(data, xcvr->sprom, len); + memcpy(tbuf, xcvr->sprom, len); + + /* Let's make sure we got a consistent copy */ + if (!memcmp(data, tbuf, len)) + break; + + } while (--count); + + if (!count) + return -ETIMEDOUT; + + return 0; +} + +static int ionic_nway_reset(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic *ionic = lif->ionic; + int err = 0; + + /* flap the link to force auto-negotiation */ + + mutex_lock(&ionic->dev_cmd_lock); + + ionic_dev_cmd_port_state(&ionic->idev, IONIC_PORT_ADMIN_STATE_DOWN); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + + if (!err) { + ionic_dev_cmd_port_state(&ionic->idev, IONIC_PORT_ADMIN_STATE_UP); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + } + + mutex_unlock(&ionic->dev_cmd_lock); + + return err; +} + +static const struct ethtool_ops ionic_ethtool_ops = { + .get_drvinfo = ionic_get_drvinfo, + .get_regs_len = ionic_get_regs_len, + .get_regs = ionic_get_regs, + .get_link = ethtool_op_get_link, + .get_link_ksettings = ionic_get_link_ksettings, + .get_coalesce = ionic_get_coalesce, + .set_coalesce = ionic_set_coalesce, + .get_ringparam = ionic_get_ringparam, + .set_ringparam = ionic_set_ringparam, + .get_channels = ionic_get_channels, + .set_channels = ionic_set_channels, + .get_strings = ionic_get_strings, + .get_ethtool_stats = ionic_get_stats, + .get_sset_count = ionic_get_sset_count, + .get_priv_flags = ionic_get_priv_flags, + .set_priv_flags = ionic_set_priv_flags, + .get_rxnfc = ionic_get_rxnfc, + .get_rxfh_indir_size = ionic_get_rxfh_indir_size, + .get_rxfh_key_size = ionic_get_rxfh_key_size, + .get_rxfh = ionic_get_rxfh, + .set_rxfh = ionic_set_rxfh, + .get_tunable = ionic_get_tunable, + .set_tunable = ionic_set_tunable, + .get_module_info = ionic_get_module_info, + .get_module_eeprom = ionic_get_module_eeprom, + .get_pauseparam = ionic_get_pauseparam, + .set_pauseparam = ionic_set_pauseparam, + .set_link_ksettings = ionic_set_link_ksettings, + .nway_reset = ionic_nway_reset, +}; + +void ionic_ethtool_set_ops(struct net_device *netdev) +{ + netdev->ethtool_ops = &ionic_ethtool_ops; +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_ethtool.h b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.h new file mode 100644 index 000000000000..38b91b1d70ae --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_ethtool.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_ETHTOOL_H_ +#define _IONIC_ETHTOOL_H_ + +void ionic_ethtool_set_ops(struct net_device *netdev); + +#endif /* _IONIC_ETHTOOL_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_if.h b/drivers/net/ethernet/pensando/ionic/ionic_if.h new file mode 100644 index 000000000000..5bfdda19f64d --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_if.h @@ -0,0 +1,2482 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB OR BSD-2-Clause */ +/* Copyright (c) 2017-2019 Pensando Systems, Inc. All rights reserved. */ + +#ifndef _IONIC_IF_H_ +#define _IONIC_IF_H_ + +#pragma pack(push, 1) + +#define IONIC_DEV_INFO_SIGNATURE 0x44455649 /* 'DEVI' */ +#define IONIC_DEV_INFO_VERSION 1 +#define IONIC_IFNAMSIZ 16 + +/** + * Commands + */ +enum ionic_cmd_opcode { + IONIC_CMD_NOP = 0, + + /* Device commands */ + IONIC_CMD_IDENTIFY = 1, + IONIC_CMD_INIT = 2, + IONIC_CMD_RESET = 3, + IONIC_CMD_GETATTR = 4, + IONIC_CMD_SETATTR = 5, + + /* Port commands */ + IONIC_CMD_PORT_IDENTIFY = 10, + IONIC_CMD_PORT_INIT = 11, + IONIC_CMD_PORT_RESET = 12, + IONIC_CMD_PORT_GETATTR = 13, + IONIC_CMD_PORT_SETATTR = 14, + + /* LIF commands */ + IONIC_CMD_LIF_IDENTIFY = 20, + IONIC_CMD_LIF_INIT = 21, + IONIC_CMD_LIF_RESET = 22, + IONIC_CMD_LIF_GETATTR = 23, + IONIC_CMD_LIF_SETATTR = 24, + + IONIC_CMD_RX_MODE_SET = 30, + IONIC_CMD_RX_FILTER_ADD = 31, + IONIC_CMD_RX_FILTER_DEL = 32, + + /* Queue commands */ + IONIC_CMD_Q_INIT = 40, + IONIC_CMD_Q_CONTROL = 41, + + /* RDMA commands */ + IONIC_CMD_RDMA_RESET_LIF = 50, + IONIC_CMD_RDMA_CREATE_EQ = 51, + IONIC_CMD_RDMA_CREATE_CQ = 52, + IONIC_CMD_RDMA_CREATE_ADMINQ = 53, + + /* QoS commands */ + IONIC_CMD_QOS_CLASS_IDENTIFY = 240, + IONIC_CMD_QOS_CLASS_INIT = 241, + IONIC_CMD_QOS_CLASS_RESET = 242, + + /* Firmware commands */ + IONIC_CMD_FW_DOWNLOAD = 254, + IONIC_CMD_FW_CONTROL = 255, +}; + +/** + * Command Return codes + */ +enum ionic_status_code { + IONIC_RC_SUCCESS = 0, /* Success */ + IONIC_RC_EVERSION = 1, /* Incorrect version for request */ + IONIC_RC_EOPCODE = 2, /* Invalid cmd opcode */ + IONIC_RC_EIO = 3, /* I/O error */ + IONIC_RC_EPERM = 4, /* Permission denied */ + IONIC_RC_EQID = 5, /* Bad qid */ + IONIC_RC_EQTYPE = 6, /* Bad qtype */ + IONIC_RC_ENOENT = 7, /* No such element */ + IONIC_RC_EINTR = 8, /* operation interrupted */ + IONIC_RC_EAGAIN = 9, /* Try again */ + IONIC_RC_ENOMEM = 10, /* Out of memory */ + IONIC_RC_EFAULT = 11, /* Bad address */ + IONIC_RC_EBUSY = 12, /* Device or resource busy */ + IONIC_RC_EEXIST = 13, /* object already exists */ + IONIC_RC_EINVAL = 14, /* Invalid argument */ + IONIC_RC_ENOSPC = 15, /* No space left or alloc failure */ + IONIC_RC_ERANGE = 16, /* Parameter out of range */ + IONIC_RC_BAD_ADDR = 17, /* Descriptor contains a bad ptr */ + IONIC_RC_DEV_CMD = 18, /* Device cmd attempted on AdminQ */ + IONIC_RC_ENOSUPP = 19, /* Operation not supported */ + IONIC_RC_ERROR = 29, /* Generic error */ + + IONIC_RC_ERDMA = 30, /* Generic RDMA error */ +}; + +enum ionic_notifyq_opcode { + IONIC_EVENT_LINK_CHANGE = 1, + IONIC_EVENT_RESET = 2, + IONIC_EVENT_HEARTBEAT = 3, + IONIC_EVENT_LOG = 4, +}; + +/** + * struct cmd - General admin command format + * @opcode: Opcode for the command + * @lif_index: LIF index + * @cmd_data: Opcode-specific command bytes + */ +struct ionic_admin_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + u8 cmd_data[60]; +}; + +/** + * struct admin_comp - General admin command completion format + * @status: The status of the command (enum status_code) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @cmd_data: Command-specific bytes. + * @color: Color bit. (Always 0 for commands issued to the + * Device Cmd Registers.) + */ +struct ionic_admin_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + u8 cmd_data[11]; + u8 color; +#define IONIC_COMP_COLOR_MASK 0x80 +}; + +static inline u8 color_match(u8 color, u8 done_color) +{ + return (!!(color & IONIC_COMP_COLOR_MASK)) == done_color; +} + +/** + * struct nop_cmd - NOP command + * @opcode: opcode + */ +struct ionic_nop_cmd { + u8 opcode; + u8 rsvd[63]; +}; + +/** + * struct nop_comp - NOP command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_nop_comp { + u8 status; + u8 rsvd[15]; +}; + +/** + * struct dev_init_cmd - Device init command + * @opcode: opcode + * @type: device type + */ +struct ionic_dev_init_cmd { + u8 opcode; + u8 type; + u8 rsvd[62]; +}; + +/** + * struct init_comp - Device init command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_dev_init_comp { + u8 status; + u8 rsvd[15]; +}; + +/** + * struct dev_reset_cmd - Device reset command + * @opcode: opcode + */ +struct ionic_dev_reset_cmd { + u8 opcode; + u8 rsvd[63]; +}; + +/** + * struct reset_comp - Reset command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_dev_reset_comp { + u8 status; + u8 rsvd[15]; +}; + +#define IONIC_IDENTITY_VERSION_1 1 + +/** + * struct dev_identify_cmd - Driver/device identify command + * @opcode: opcode + * @ver: Highest version of identify supported by driver + */ +struct ionic_dev_identify_cmd { + u8 opcode; + u8 ver; + u8 rsvd[62]; +}; + +/** + * struct dev_identify_comp - Driver/device identify command completion + * @status: The status of the command (enum status_code) + * @ver: Version of identify returned by device + */ +struct ionic_dev_identify_comp { + u8 status; + u8 ver; + u8 rsvd[14]; +}; + +enum ionic_os_type { + IONIC_OS_TYPE_LINUX = 1, + IONIC_OS_TYPE_WIN = 2, + IONIC_OS_TYPE_DPDK = 3, + IONIC_OS_TYPE_FREEBSD = 4, + IONIC_OS_TYPE_IPXE = 5, + IONIC_OS_TYPE_ESXI = 6, +}; + +/** + * union drv_identity - driver identity information + * @os_type: OS type (see enum os_type) + * @os_dist: OS distribution, numeric format + * @os_dist_str: OS distribution, string format + * @kernel_ver: Kernel version, numeric format + * @kernel_ver_str: Kernel version, string format + * @driver_ver_str: Driver version, string format + */ +union ionic_drv_identity { + struct { + __le32 os_type; + __le32 os_dist; + char os_dist_str[128]; + __le32 kernel_ver; + char kernel_ver_str[32]; + char driver_ver_str[32]; + }; + __le32 words[512]; +}; + +/** + * union dev_identity - device identity information + * @version: Version of device identify + * @type: Identify type (0 for now) + * @nports: Number of ports provisioned + * @nlifs: Number of LIFs provisioned + * @nintrs: Number of interrupts provisioned + * @ndbpgs_per_lif: Number of doorbell pages per LIF + * @intr_coal_mult: Interrupt coalescing multiplication factor. + * Scale user-supplied interrupt coalescing + * value in usecs to device units using: + * device units = usecs * mult / div + * @intr_coal_div: Interrupt coalescing division factor. + * Scale user-supplied interrupt coalescing + * value in usecs to device units using: + * device units = usecs * mult / div + * + */ +union ionic_dev_identity { + struct { + u8 version; + u8 type; + u8 rsvd[2]; + u8 nports; + u8 rsvd2[3]; + __le32 nlifs; + __le32 nintrs; + __le32 ndbpgs_per_lif; + __le32 intr_coal_mult; + __le32 intr_coal_div; + }; + __le32 words[512]; +}; + +enum ionic_lif_type { + IONIC_LIF_TYPE_CLASSIC = 0, + IONIC_LIF_TYPE_MACVLAN = 1, + IONIC_LIF_TYPE_NETQUEUE = 2, +}; + +/** + * struct lif_identify_cmd - lif identify command + * @opcode: opcode + * @type: lif type (enum lif_type) + * @ver: version of identify returned by device + */ +struct ionic_lif_identify_cmd { + u8 opcode; + u8 type; + u8 ver; + u8 rsvd[61]; +}; + +/** + * struct lif_identify_comp - lif identify command completion + * @status: status of the command (enum status_code) + * @ver: version of identify returned by device + */ +struct ionic_lif_identify_comp { + u8 status; + u8 ver; + u8 rsvd2[14]; +}; + +enum ionic_lif_capability { + IONIC_LIF_CAP_ETH = BIT(0), + IONIC_LIF_CAP_RDMA = BIT(1), +}; + +/** + * Logical Queue Types + */ +enum ionic_logical_qtype { + IONIC_QTYPE_ADMINQ = 0, + IONIC_QTYPE_NOTIFYQ = 1, + IONIC_QTYPE_RXQ = 2, + IONIC_QTYPE_TXQ = 3, + IONIC_QTYPE_EQ = 4, + IONIC_QTYPE_MAX = 16, +}; + +/** + * struct lif_logical_qtype - Descriptor of logical to hardware queue type. + * @qtype: Hardware Queue Type. + * @qid_count: Number of Queue IDs of the logical type. + * @qid_base: Minimum Queue ID of the logical type. + */ +struct ionic_lif_logical_qtype { + u8 qtype; + u8 rsvd[3]; + __le32 qid_count; + __le32 qid_base; +}; + +enum ionic_lif_state { + IONIC_LIF_DISABLE = 0, + IONIC_LIF_ENABLE = 1, + IONIC_LIF_HANG_RESET = 2, +}; + +/** + * LIF configuration + * @state: lif state (enum lif_state) + * @name: lif name + * @mtu: mtu + * @mac: station mac address + * @features: features (enum eth_hw_features) + * @queue_count: queue counts per queue-type + */ +union ionic_lif_config { + struct { + u8 state; + u8 rsvd[3]; + char name[IONIC_IFNAMSIZ]; + __le32 mtu; + u8 mac[6]; + u8 rsvd2[2]; + __le64 features; + __le32 queue_count[IONIC_QTYPE_MAX]; + }; + __le32 words[64]; +}; + +/** + * struct lif_identity - lif identity information (type-specific) + * + * @capabilities LIF capabilities + * + * Ethernet: + * @version: Ethernet identify structure version. + * @features: Ethernet features supported on this lif type. + * @max_ucast_filters: Number of perfect unicast addresses supported. + * @max_mcast_filters: Number of perfect multicast addresses supported. + * @min_frame_size: Minimum size of frames to be sent + * @max_frame_size: Maximim size of frames to be sent + * @config: LIF config struct with features, mtu, mac, q counts + * + * RDMA: + * @version: RDMA version of opcodes and queue descriptors. + * @qp_opcodes: Number of rdma queue pair opcodes supported. + * @admin_opcodes: Number of rdma admin opcodes supported. + * @npts_per_lif: Page table size per lif + * @nmrs_per_lif: Number of memory regions per lif + * @nahs_per_lif: Number of address handles per lif + * @max_stride: Max work request stride. + * @cl_stride: Cache line stride. + * @pte_stride: Page table entry stride. + * @rrq_stride: Remote RQ work request stride. + * @rsq_stride: Remote SQ work request stride. + * @dcqcn_profiles: Number of DCQCN profiles + * @aq_qtype: RDMA Admin Qtype. + * @sq_qtype: RDMA Send Qtype. + * @rq_qtype: RDMA Receive Qtype. + * @cq_qtype: RDMA Completion Qtype. + * @eq_qtype: RDMA Event Qtype. + */ +union ionic_lif_identity { + struct { + __le64 capabilities; + + struct { + u8 version; + u8 rsvd[3]; + __le32 max_ucast_filters; + __le32 max_mcast_filters; + __le16 rss_ind_tbl_sz; + __le32 min_frame_size; + __le32 max_frame_size; + u8 rsvd2[106]; + union ionic_lif_config config; + } eth; + + struct { + u8 version; + u8 qp_opcodes; + u8 admin_opcodes; + u8 rsvd; + __le32 npts_per_lif; + __le32 nmrs_per_lif; + __le32 nahs_per_lif; + u8 max_stride; + u8 cl_stride; + u8 pte_stride; + u8 rrq_stride; + u8 rsq_stride; + u8 dcqcn_profiles; + u8 rsvd_dimensions[10]; + struct ionic_lif_logical_qtype aq_qtype; + struct ionic_lif_logical_qtype sq_qtype; + struct ionic_lif_logical_qtype rq_qtype; + struct ionic_lif_logical_qtype cq_qtype; + struct ionic_lif_logical_qtype eq_qtype; + } rdma; + }; + __le32 words[512]; +}; + +/** + * struct lif_init_cmd - LIF init command + * @opcode: opcode + * @type: LIF type (enum lif_type) + * @index: LIF index + * @info_pa: destination address for lif info (struct lif_info) + */ +struct ionic_lif_init_cmd { + u8 opcode; + u8 type; + __le16 index; + __le32 rsvd; + __le64 info_pa; + u8 rsvd2[48]; +}; + +/** + * struct lif_init_comp - LIF init command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_lif_init_comp { + u8 status; + u8 rsvd; + __le16 hw_index; + u8 rsvd2[12]; +}; + +/** + * struct q_init_cmd - Queue init command + * @opcode: opcode + * @type: Logical queue type + * @ver: Queue version (defines opcode/descriptor scope) + * @lif_index: LIF index + * @index: (lif, qtype) relative admin queue index + * @intr_index: Interrupt control register index + * @pid: Process ID + * @flags: + * IRQ: Interrupt requested on completion + * ENA: Enable the queue. If ENA=0 the queue is initialized + * but remains disabled, to be later enabled with the + * Queue Enable command. If ENA=1, then queue is + * initialized and then enabled. + * SG: Enable Scatter-Gather on the queue. + * in number of descs. The actual ring size is + * (1 << ring_size). For example, to + * select a ring size of 64 descriptors write + * ring_size = 6. The minimum ring_size value is 2 + * for a ring size of 4 descriptors. The maximum + * ring_size value is 16 for a ring size of 64k + * descriptors. Values of ring_size <2 and >16 are + * reserved. + * EQ: Enable the Event Queue + * @cos: Class of service for this queue. + * @ring_size: Queue ring size, encoded as a log2(size) + * @ring_base: Queue ring base address + * @cq_ring_base: Completion queue ring base address + * @sg_ring_base: Scatter/Gather ring base address + * @eq_index: Event queue index + */ +struct ionic_q_init_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + u8 type; + u8 ver; + u8 rsvd1[2]; + __le32 index; + __le16 pid; + __le16 intr_index; + __le16 flags; +#define IONIC_QINIT_F_IRQ 0x01 /* Request interrupt on completion */ +#define IONIC_QINIT_F_ENA 0x02 /* Enable the queue */ +#define IONIC_QINIT_F_SG 0x04 /* Enable scatter/gather on the queue */ +#define IONIC_QINIT_F_EQ 0x08 /* Enable event queue */ +#define IONIC_QINIT_F_DEBUG 0x80 /* Enable queue debugging */ + u8 cos; + u8 ring_size; + __le64 ring_base; + __le64 cq_ring_base; + __le64 sg_ring_base; + __le32 eq_index; + u8 rsvd2[16]; +}; + +/** + * struct q_init_comp - Queue init command completion + * @status: The status of the command (enum status_code) + * @ver: Queue version (defines opcode/descriptor scope) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @hw_index: Hardware Queue ID + * @hw_type: Hardware Queue type + * @color: Color + */ +struct ionic_q_init_comp { + u8 status; + u8 ver; + __le16 comp_index; + __le32 hw_index; + u8 hw_type; + u8 rsvd2[6]; + u8 color; +}; + +/* the device's internal addressing uses up to 52 bits */ +#define IONIC_ADDR_LEN 52 +#define IONIC_ADDR_MASK (BIT_ULL(IONIC_ADDR_LEN) - 1) + +enum ionic_txq_desc_opcode { + IONIC_TXQ_DESC_OPCODE_CSUM_NONE = 0, + IONIC_TXQ_DESC_OPCODE_CSUM_PARTIAL = 1, + IONIC_TXQ_DESC_OPCODE_CSUM_HW = 2, + IONIC_TXQ_DESC_OPCODE_TSO = 3, +}; + +/** + * struct txq_desc - Ethernet Tx queue descriptor format + * @opcode: Tx operation, see TXQ_DESC_OPCODE_*: + * + * IONIC_TXQ_DESC_OPCODE_CSUM_NONE: + * + * Non-offload send. No segmentation, + * fragmentation or checksum calc/insertion is + * performed by device; packet is prepared + * to send by software stack and requires + * no further manipulation from device. + * + * IONIC_TXQ_DESC_OPCODE_CSUM_PARTIAL: + * + * Offload 16-bit L4 checksum + * calculation/insertion. The device will + * calculate the L4 checksum value and + * insert the result in the packet's L4 + * header checksum field. The L4 checksum + * is calculated starting at @csum_start bytes + * into the packet to the end of the packet. + * The checksum insertion position is given + * in @csum_offset. This feature is only + * applicable to protocols such as TCP, UDP + * and ICMP where a standard (i.e. the + * 'IP-style' checksum) one's complement + * 16-bit checksum is used, using an IP + * pseudo-header to seed the calculation. + * Software will preload the L4 checksum + * field with the IP pseudo-header checksum. + * + * For tunnel encapsulation, @csum_start and + * @csum_offset refer to the inner L4 + * header. Supported tunnels encapsulations + * are: IPIP, GRE, and UDP. If the @encap + * is clear, no further processing by the + * device is required; software will + * calculate the outer header checksums. If + * the @encap is set, the device will + * offload the outer header checksums using + * LCO (local checksum offload) (see + * Documentation/networking/checksum- + * offloads.txt for more info). + * + * IONIC_TXQ_DESC_OPCODE_CSUM_HW: + * + * Offload 16-bit checksum computation to hardware. + * If @csum_l3 is set then the packet's L3 checksum is + * updated. Similarly, if @csum_l4 is set the the L4 + * checksum is updated. If @encap is set then encap header + * checksums are also updated. + * + * IONIC_TXQ_DESC_OPCODE_TSO: + * + * Device preforms TCP segmentation offload + * (TSO). @hdr_len is the number of bytes + * to the end of TCP header (the offset to + * the TCP payload). @mss is the desired + * MSS, the TCP payload length for each + * segment. The device will calculate/ + * insert IP (IPv4 only) and TCP checksums + * for each segment. In the first data + * buffer containing the header template, + * the driver will set IPv4 checksum to 0 + * and preload TCP checksum with the IP + * pseudo header calculated with IP length = 0. + * + * Supported tunnel encapsulations are IPIP, + * layer-3 GRE, and UDP. @hdr_len includes + * both outer and inner headers. The driver + * will set IPv4 checksum to zero and + * preload TCP checksum with IP pseudo + * header on the inner header. + * + * TCP ECN offload is supported. The device + * will set CWR flag in the first segment if + * CWR is set in the template header, and + * clear CWR in remaining segments. + * @flags: + * vlan: + * Insert an L2 VLAN header using @vlan_tci. + * encap: + * Calculate encap header checksum. + * csum_l3: + * Compute L3 header checksum. + * csum_l4: + * Compute L4 header checksum. + * tso_sot: + * TSO start + * tso_eot: + * TSO end + * @num_sg_elems: Number of scatter-gather elements in SG + * descriptor + * @addr: First data buffer's DMA address. + * (Subsequent data buffers are on txq_sg_desc). + * @len: First data buffer's length, in bytes + * @vlan_tci: VLAN tag to insert in the packet (if requested + * by @V-bit). Includes .1p and .1q tags + * @hdr_len: Length of packet headers, including + * encapsulating outer header, if applicable. + * Valid for opcodes TXQ_DESC_OPCODE_CALC_CSUM and + * TXQ_DESC_OPCODE_TSO. Should be set to zero for + * all other modes. For + * TXQ_DESC_OPCODE_CALC_CSUM, @hdr_len is length + * of headers up to inner-most L4 header. For + * TXQ_DESC_OPCODE_TSO, @hdr_len is up to + * inner-most L4 payload, so inclusive of + * inner-most L4 header. + * @mss: Desired MSS value for TSO. Only applicable for + * TXQ_DESC_OPCODE_TSO. + * @csum_start: Offset into inner-most L3 header of checksum + * @csum_offset: Offset into inner-most L4 header of checksum + */ + +#define IONIC_TXQ_DESC_OPCODE_MASK 0xf +#define IONIC_TXQ_DESC_OPCODE_SHIFT 4 +#define IONIC_TXQ_DESC_FLAGS_MASK 0xf +#define IONIC_TXQ_DESC_FLAGS_SHIFT 0 +#define IONIC_TXQ_DESC_NSGE_MASK 0xf +#define IONIC_TXQ_DESC_NSGE_SHIFT 8 +#define IONIC_TXQ_DESC_ADDR_MASK (BIT_ULL(IONIC_ADDR_LEN) - 1) +#define IONIC_TXQ_DESC_ADDR_SHIFT 12 + +/* common flags */ +#define IONIC_TXQ_DESC_FLAG_VLAN 0x1 +#define IONIC_TXQ_DESC_FLAG_ENCAP 0x2 + +/* flags for csum_hw opcode */ +#define IONIC_TXQ_DESC_FLAG_CSUM_L3 0x4 +#define IONIC_TXQ_DESC_FLAG_CSUM_L4 0x8 + +/* flags for tso opcode */ +#define IONIC_TXQ_DESC_FLAG_TSO_SOT 0x4 +#define IONIC_TXQ_DESC_FLAG_TSO_EOT 0x8 + +struct ionic_txq_desc { + __le64 cmd; + __le16 len; + union { + __le16 vlan_tci; + __le16 hword0; + }; + union { + __le16 csum_start; + __le16 hdr_len; + __le16 hword1; + }; + union { + __le16 csum_offset; + __le16 mss; + __le16 hword2; + }; +}; + +static inline u64 encode_txq_desc_cmd(u8 opcode, u8 flags, + u8 nsge, u64 addr) +{ + u64 cmd; + + cmd = (opcode & IONIC_TXQ_DESC_OPCODE_MASK) << IONIC_TXQ_DESC_OPCODE_SHIFT; + cmd |= (flags & IONIC_TXQ_DESC_FLAGS_MASK) << IONIC_TXQ_DESC_FLAGS_SHIFT; + cmd |= (nsge & IONIC_TXQ_DESC_NSGE_MASK) << IONIC_TXQ_DESC_NSGE_SHIFT; + cmd |= (addr & IONIC_TXQ_DESC_ADDR_MASK) << IONIC_TXQ_DESC_ADDR_SHIFT; + + return cmd; +}; + +static inline void decode_txq_desc_cmd(u64 cmd, u8 *opcode, u8 *flags, + u8 *nsge, u64 *addr) +{ + *opcode = (cmd >> IONIC_TXQ_DESC_OPCODE_SHIFT) & IONIC_TXQ_DESC_OPCODE_MASK; + *flags = (cmd >> IONIC_TXQ_DESC_FLAGS_SHIFT) & IONIC_TXQ_DESC_FLAGS_MASK; + *nsge = (cmd >> IONIC_TXQ_DESC_NSGE_SHIFT) & IONIC_TXQ_DESC_NSGE_MASK; + *addr = (cmd >> IONIC_TXQ_DESC_ADDR_SHIFT) & IONIC_TXQ_DESC_ADDR_MASK; +}; + +#define IONIC_TX_MAX_SG_ELEMS 8 +#define IONIC_RX_MAX_SG_ELEMS 8 + +/** + * struct txq_sg_desc - Transmit scatter-gather (SG) list + * @addr: DMA address of SG element data buffer + * @len: Length of SG element data buffer, in bytes + */ +struct ionic_txq_sg_desc { + struct ionic_txq_sg_elem { + __le64 addr; + __le16 len; + __le16 rsvd[3]; + } elems[IONIC_TX_MAX_SG_ELEMS]; +}; + +/** + * struct txq_comp - Ethernet transmit queue completion descriptor + * @status: The status of the command (enum status_code) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @color: Color bit. + */ +struct ionic_txq_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + u8 rsvd2[11]; + u8 color; +}; + +enum ionic_rxq_desc_opcode { + IONIC_RXQ_DESC_OPCODE_SIMPLE = 0, + IONIC_RXQ_DESC_OPCODE_SG = 1, +}; + +/** + * struct rxq_desc - Ethernet Rx queue descriptor format + * @opcode: Rx operation, see RXQ_DESC_OPCODE_*: + * + * RXQ_DESC_OPCODE_SIMPLE: + * + * Receive full packet into data buffer + * starting at @addr. Results of + * receive, including actual bytes received, + * are recorded in Rx completion descriptor. + * + * @len: Data buffer's length, in bytes. + * @addr: Data buffer's DMA address + */ +struct ionic_rxq_desc { + u8 opcode; + u8 rsvd[5]; + __le16 len; + __le64 addr; +}; + +/** + * struct rxq_sg_desc - Receive scatter-gather (SG) list + * @addr: DMA address of SG element data buffer + * @len: Length of SG element data buffer, in bytes + */ +struct ionic_rxq_sg_desc { + struct ionic_rxq_sg_elem { + __le64 addr; + __le16 len; + __le16 rsvd[3]; + } elems[IONIC_RX_MAX_SG_ELEMS]; +}; + +/** + * struct rxq_comp - Ethernet receive queue completion descriptor + * @status: The status of the command (enum status_code) + * @num_sg_elems: Number of SG elements used by this descriptor + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @rss_hash: 32-bit RSS hash + * @csum: 16-bit sum of the packet's L2 payload. + * If the packet's L2 payload is odd length, an extra + * zero-value byte is included in the @csum calculation but + * not included in @len. + * @vlan_tci: VLAN tag stripped from the packet. Valid if @VLAN is + * set. Includes .1p and .1q tags. + * @len: Received packet length, in bytes. Excludes FCS. + * @csum_calc L2 payload checksum is computed or not + * @csum_tcp_ok: The TCP checksum calculated by the device + * matched the checksum in the receive packet's + * TCP header + * @csum_tcp_bad: The TCP checksum calculated by the device did + * not match the checksum in the receive packet's + * TCP header. + * @csum_udp_ok: The UDP checksum calculated by the device + * matched the checksum in the receive packet's + * UDP header + * @csum_udp_bad: The UDP checksum calculated by the device did + * not match the checksum in the receive packet's + * UDP header. + * @csum_ip_ok: The IPv4 checksum calculated by the device + * matched the checksum in the receive packet's + * first IPv4 header. If the receive packet + * contains both a tunnel IPv4 header and a + * transport IPv4 header, the device validates the + * checksum for the both IPv4 headers. + * @csum_ip_bad: The IPv4 checksum calculated by the device did + * not match the checksum in the receive packet's + * first IPv4 header. If the receive packet + * contains both a tunnel IPv4 header and a + * transport IPv4 header, the device validates the + * checksum for both IP headers. + * @VLAN: VLAN header was stripped and placed in @vlan_tci. + * @pkt_type: Packet type + * @color: Color bit. + */ +struct ionic_rxq_comp { + u8 status; + u8 num_sg_elems; + __le16 comp_index; + __le32 rss_hash; + __le16 csum; + __le16 vlan_tci; + __le16 len; + u8 csum_flags; +#define IONIC_RXQ_COMP_CSUM_F_TCP_OK 0x01 +#define IONIC_RXQ_COMP_CSUM_F_TCP_BAD 0x02 +#define IONIC_RXQ_COMP_CSUM_F_UDP_OK 0x04 +#define IONIC_RXQ_COMP_CSUM_F_UDP_BAD 0x08 +#define IONIC_RXQ_COMP_CSUM_F_IP_OK 0x10 +#define IONIC_RXQ_COMP_CSUM_F_IP_BAD 0x20 +#define IONIC_RXQ_COMP_CSUM_F_VLAN 0x40 +#define IONIC_RXQ_COMP_CSUM_F_CALC 0x80 + u8 pkt_type_color; +#define IONIC_RXQ_COMP_PKT_TYPE_MASK 0x0f +}; + +enum ionic_pkt_type { + IONIC_PKT_TYPE_NON_IP = 0x000, + IONIC_PKT_TYPE_IPV4 = 0x001, + IONIC_PKT_TYPE_IPV4_TCP = 0x003, + IONIC_PKT_TYPE_IPV4_UDP = 0x005, + IONIC_PKT_TYPE_IPV6 = 0x008, + IONIC_PKT_TYPE_IPV6_TCP = 0x018, + IONIC_PKT_TYPE_IPV6_UDP = 0x028, +}; + +enum ionic_eth_hw_features { + IONIC_ETH_HW_VLAN_TX_TAG = BIT(0), + IONIC_ETH_HW_VLAN_RX_STRIP = BIT(1), + IONIC_ETH_HW_VLAN_RX_FILTER = BIT(2), + IONIC_ETH_HW_RX_HASH = BIT(3), + IONIC_ETH_HW_RX_CSUM = BIT(4), + IONIC_ETH_HW_TX_SG = BIT(5), + IONIC_ETH_HW_RX_SG = BIT(6), + IONIC_ETH_HW_TX_CSUM = BIT(7), + IONIC_ETH_HW_TSO = BIT(8), + IONIC_ETH_HW_TSO_IPV6 = BIT(9), + IONIC_ETH_HW_TSO_ECN = BIT(10), + IONIC_ETH_HW_TSO_GRE = BIT(11), + IONIC_ETH_HW_TSO_GRE_CSUM = BIT(12), + IONIC_ETH_HW_TSO_IPXIP4 = BIT(13), + IONIC_ETH_HW_TSO_IPXIP6 = BIT(14), + IONIC_ETH_HW_TSO_UDP = BIT(15), + IONIC_ETH_HW_TSO_UDP_CSUM = BIT(16), +}; + +/** + * struct q_control_cmd - Queue control command + * @opcode: opcode + * @type: Queue type + * @lif_index: LIF index + * @index: Queue index + * @oper: Operation (enum q_control_oper) + */ +struct ionic_q_control_cmd { + u8 opcode; + u8 type; + __le16 lif_index; + __le32 index; + u8 oper; + u8 rsvd[55]; +}; + +typedef struct ionic_admin_comp ionic_q_control_comp; + +enum q_control_oper { + IONIC_Q_DISABLE = 0, + IONIC_Q_ENABLE = 1, + IONIC_Q_HANG_RESET = 2, +}; + +/** + * Physical connection type + */ +enum ionic_phy_type { + IONIC_PHY_TYPE_NONE = 0, + IONIC_PHY_TYPE_COPPER = 1, + IONIC_PHY_TYPE_FIBER = 2, +}; + +/** + * Transceiver status + */ +enum ionic_xcvr_state { + IONIC_XCVR_STATE_REMOVED = 0, + IONIC_XCVR_STATE_INSERTED = 1, + IONIC_XCVR_STATE_PENDING = 2, + IONIC_XCVR_STATE_SPROM_READ = 3, + IONIC_XCVR_STATE_SPROM_READ_ERR = 4, +}; + +/** + * Supported link modes + */ +enum ionic_xcvr_pid { + IONIC_XCVR_PID_UNKNOWN = 0, + + /* CU */ + IONIC_XCVR_PID_QSFP_100G_CR4 = 1, + IONIC_XCVR_PID_QSFP_40GBASE_CR4 = 2, + IONIC_XCVR_PID_SFP_25GBASE_CR_S = 3, + IONIC_XCVR_PID_SFP_25GBASE_CR_L = 4, + IONIC_XCVR_PID_SFP_25GBASE_CR_N = 5, + + /* Fiber */ + IONIC_XCVR_PID_QSFP_100G_AOC = 50, + IONIC_XCVR_PID_QSFP_100G_ACC = 51, + IONIC_XCVR_PID_QSFP_100G_SR4 = 52, + IONIC_XCVR_PID_QSFP_100G_LR4 = 53, + IONIC_XCVR_PID_QSFP_100G_ER4 = 54, + IONIC_XCVR_PID_QSFP_40GBASE_ER4 = 55, + IONIC_XCVR_PID_QSFP_40GBASE_SR4 = 56, + IONIC_XCVR_PID_QSFP_40GBASE_LR4 = 57, + IONIC_XCVR_PID_QSFP_40GBASE_AOC = 58, + IONIC_XCVR_PID_SFP_25GBASE_SR = 59, + IONIC_XCVR_PID_SFP_25GBASE_LR = 60, + IONIC_XCVR_PID_SFP_25GBASE_ER = 61, + IONIC_XCVR_PID_SFP_25GBASE_AOC = 62, + IONIC_XCVR_PID_SFP_10GBASE_SR = 63, + IONIC_XCVR_PID_SFP_10GBASE_LR = 64, + IONIC_XCVR_PID_SFP_10GBASE_LRM = 65, + IONIC_XCVR_PID_SFP_10GBASE_ER = 66, + IONIC_XCVR_PID_SFP_10GBASE_AOC = 67, + IONIC_XCVR_PID_SFP_10GBASE_CU = 68, + IONIC_XCVR_PID_QSFP_100G_CWDM4 = 69, + IONIC_XCVR_PID_QSFP_100G_PSM4 = 70, +}; + +/** + * Port types + */ +enum ionic_port_type { + IONIC_PORT_TYPE_NONE = 0, /* port type not configured */ + IONIC_PORT_TYPE_ETH = 1, /* port carries ethernet traffic (inband) */ + IONIC_PORT_TYPE_MGMT = 2, /* port carries mgmt traffic (out-of-band) */ +}; + +/** + * Port config state + */ +enum ionic_port_admin_state { + IONIC_PORT_ADMIN_STATE_NONE = 0, /* port admin state not configured */ + IONIC_PORT_ADMIN_STATE_DOWN = 1, /* port is admin disabled */ + IONIC_PORT_ADMIN_STATE_UP = 2, /* port is admin enabled */ +}; + +/** + * Port operational status + */ +enum ionic_port_oper_status { + IONIC_PORT_OPER_STATUS_NONE = 0, /* port is disabled */ + IONIC_PORT_OPER_STATUS_UP = 1, /* port is linked up */ + IONIC_PORT_OPER_STATUS_DOWN = 2, /* port link status is down */ +}; + +/** + * Ethernet Forward error correction (fec) modes + */ +enum ionic_port_fec_type { + IONIC_PORT_FEC_TYPE_NONE = 0, /* Disabled */ + IONIC_PORT_FEC_TYPE_FC = 1, /* FireCode */ + IONIC_PORT_FEC_TYPE_RS = 2, /* ReedSolomon */ +}; + +/** + * Ethernet pause (flow control) modes + */ +enum ionic_port_pause_type { + IONIC_PORT_PAUSE_TYPE_NONE = 0, /* Disable Pause */ + IONIC_PORT_PAUSE_TYPE_LINK = 1, /* Link level pause */ + IONIC_PORT_PAUSE_TYPE_PFC = 2, /* Priority-Flow control */ +}; + +/** + * Loopback modes + */ +enum ionic_port_loopback_mode { + IONIC_PORT_LOOPBACK_MODE_NONE = 0, /* Disable loopback */ + IONIC_PORT_LOOPBACK_MODE_MAC = 1, /* MAC loopback */ + IONIC_PORT_LOOPBACK_MODE_PHY = 2, /* PHY/Serdes loopback */ +}; + +/** + * Transceiver Status information + * @state: Transceiver status (enum xcvr_state) + * @phy: Physical connection type (enum phy_type) + * @pid: Transceiver link mode (enum pid) + * @sprom: Transceiver sprom contents + */ +struct ionic_xcvr_status { + u8 state; + u8 phy; + __le16 pid; + u8 sprom[256]; +}; + +/** + * Port configuration + * @speed: port speed (in Mbps) + * @mtu: mtu + * @state: port admin state (enum port_admin_state) + * @an_enable: autoneg enable + * @fec_type: fec type (enum port_fec_type) + * @pause_type: pause type (enum port_pause_type) + * @loopback_mode: loopback mode (enum port_loopback_mode) + */ +union ionic_port_config { + struct { +#define IONIC_SPEED_100G 100000 /* 100G in Mbps */ +#define IONIC_SPEED_50G 50000 /* 50G in Mbps */ +#define IONIC_SPEED_40G 40000 /* 40G in Mbps */ +#define IONIC_SPEED_25G 25000 /* 25G in Mbps */ +#define IONIC_SPEED_10G 10000 /* 10G in Mbps */ +#define IONIC_SPEED_1G 1000 /* 1G in Mbps */ + __le32 speed; + __le32 mtu; + u8 state; + u8 an_enable; + u8 fec_type; +#define IONIC_PAUSE_TYPE_MASK 0x0f +#define IONIC_PAUSE_FLAGS_MASK 0xf0 +#define IONIC_PAUSE_F_TX 0x10 +#define IONIC_PAUSE_F_RX 0x20 + u8 pause_type; + u8 loopback_mode; + }; + __le32 words[64]; +}; + +/** + * Port Status information + * @status: link status (enum port_oper_status) + * @id: port id + * @speed: link speed (in Mbps) + * @xcvr: tranceiver status + */ +struct ionic_port_status { + __le32 id; + __le32 speed; + u8 status; + u8 rsvd[51]; + struct ionic_xcvr_status xcvr; +}; + +/** + * struct port_identify_cmd - Port identify command + * @opcode: opcode + * @index: port index + * @ver: Highest version of identify supported by driver + */ +struct ionic_port_identify_cmd { + u8 opcode; + u8 index; + u8 ver; + u8 rsvd[61]; +}; + +/** + * struct port_identify_comp - Port identify command completion + * @status: The status of the command (enum status_code) + * @ver: Version of identify returned by device + */ +struct ionic_port_identify_comp { + u8 status; + u8 ver; + u8 rsvd[14]; +}; + +/** + * struct port_init_cmd - Port initialization command + * @opcode: opcode + * @index: port index + * @info_pa: destination address for port info (struct port_info) + */ +struct ionic_port_init_cmd { + u8 opcode; + u8 index; + u8 rsvd[6]; + __le64 info_pa; + u8 rsvd2[48]; +}; + +/** + * struct port_init_comp - Port initialization command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_port_init_comp { + u8 status; + u8 rsvd[15]; +}; + +/** + * struct port_reset_cmd - Port reset command + * @opcode: opcode + * @index: port index + */ +struct ionic_port_reset_cmd { + u8 opcode; + u8 index; + u8 rsvd[62]; +}; + +/** + * struct port_reset_comp - Port reset command completion + * @status: The status of the command (enum status_code) + */ +struct ionic_port_reset_comp { + u8 status; + u8 rsvd[15]; +}; + +/** + * enum stats_ctl_cmd - List of commands for stats control + */ +enum ionic_stats_ctl_cmd { + IONIC_STATS_CTL_RESET = 0, +}; + + +/** + * enum ionic_port_attr - List of device attributes + */ +enum ionic_port_attr { + IONIC_PORT_ATTR_STATE = 0, + IONIC_PORT_ATTR_SPEED = 1, + IONIC_PORT_ATTR_MTU = 2, + IONIC_PORT_ATTR_AUTONEG = 3, + IONIC_PORT_ATTR_FEC = 4, + IONIC_PORT_ATTR_PAUSE = 5, + IONIC_PORT_ATTR_LOOPBACK = 6, + IONIC_PORT_ATTR_STATS_CTRL = 7, +}; + +/** + * struct port_setattr_cmd - Set port attributes on the NIC + * @opcode: Opcode + * @index: port index + * @attr: Attribute type (enum ionic_port_attr) + */ +struct ionic_port_setattr_cmd { + u8 opcode; + u8 index; + u8 attr; + u8 rsvd; + union { + u8 state; + __le32 speed; + __le32 mtu; + u8 an_enable; + u8 fec_type; + u8 pause_type; + u8 loopback_mode; + u8 stats_ctl; + u8 rsvd2[60]; + }; +}; + +/** + * struct port_setattr_comp - Port set attr command completion + * @status: The status of the command (enum status_code) + * @color: Color bit + */ +struct ionic_port_setattr_comp { + u8 status; + u8 rsvd[14]; + u8 color; +}; + +/** + * struct port_getattr_cmd - Get port attributes from the NIC + * @opcode: Opcode + * @index: port index + * @attr: Attribute type (enum ionic_port_attr) + */ +struct ionic_port_getattr_cmd { + u8 opcode; + u8 index; + u8 attr; + u8 rsvd[61]; +}; + +/** + * struct port_getattr_comp - Port get attr command completion + * @status: The status of the command (enum status_code) + * @color: Color bit + */ +struct ionic_port_getattr_comp { + u8 status; + u8 rsvd[3]; + union { + u8 state; + __le32 speed; + __le32 mtu; + u8 an_enable; + u8 fec_type; + u8 pause_type; + u8 loopback_mode; + u8 rsvd2[11]; + }; + u8 color; +}; + +/** + * struct lif_status - Lif status register + * @eid: most recent NotifyQ event id + * @port_num: port the lif is connected to + * @link_status: port status (enum port_oper_status) + * @link_speed: speed of link in Mbps + * @link_down_count: number of times link status changes + */ +struct ionic_lif_status { + __le64 eid; + u8 port_num; + u8 rsvd; + __le16 link_status; + __le32 link_speed; /* units of 1Mbps: eg 10000 = 10Gbps */ + __le16 link_down_count; + u8 rsvd2[46]; +}; + +/** + * struct lif_reset_cmd - LIF reset command + * @opcode: opcode + * @index: LIF index + */ +struct ionic_lif_reset_cmd { + u8 opcode; + u8 rsvd; + __le16 index; + __le32 rsvd2[15]; +}; + +typedef struct ionic_admin_comp ionic_lif_reset_comp; + +enum ionic_dev_state { + IONIC_DEV_DISABLE = 0, + IONIC_DEV_ENABLE = 1, + IONIC_DEV_HANG_RESET = 2, +}; + +/** + * enum dev_attr - List of device attributes + */ +enum ionic_dev_attr { + IONIC_DEV_ATTR_STATE = 0, + IONIC_DEV_ATTR_NAME = 1, + IONIC_DEV_ATTR_FEATURES = 2, +}; + +/** + * struct dev_setattr_cmd - Set Device attributes on the NIC + * @opcode: Opcode + * @attr: Attribute type (enum dev_attr) + * @state: Device state (enum dev_state) + * @name: The bus info, e.g. PCI slot-device-function, 0 terminated + * @features: Device features + */ +struct ionic_dev_setattr_cmd { + u8 opcode; + u8 attr; + __le16 rsvd; + union { + u8 state; + char name[IONIC_IFNAMSIZ]; + __le64 features; + u8 rsvd2[60]; + }; +}; + +/** + * struct dev_setattr_comp - Device set attr command completion + * @status: The status of the command (enum status_code) + * @features: Device features + * @color: Color bit + */ +struct ionic_dev_setattr_comp { + u8 status; + u8 rsvd[3]; + union { + __le64 features; + u8 rsvd2[11]; + }; + u8 color; +}; + +/** + * struct dev_getattr_cmd - Get Device attributes from the NIC + * @opcode: opcode + * @attr: Attribute type (enum dev_attr) + */ +struct ionic_dev_getattr_cmd { + u8 opcode; + u8 attr; + u8 rsvd[62]; +}; + +/** + * struct dev_setattr_comp - Device set attr command completion + * @status: The status of the command (enum status_code) + * @features: Device features + * @color: Color bit + */ +struct ionic_dev_getattr_comp { + u8 status; + u8 rsvd[3]; + union { + __le64 features; + u8 rsvd2[11]; + }; + u8 color; +}; + +/** + * RSS parameters + */ +#define IONIC_RSS_HASH_KEY_SIZE 40 + +enum ionic_rss_hash_types { + IONIC_RSS_TYPE_IPV4 = BIT(0), + IONIC_RSS_TYPE_IPV4_TCP = BIT(1), + IONIC_RSS_TYPE_IPV4_UDP = BIT(2), + IONIC_RSS_TYPE_IPV6 = BIT(3), + IONIC_RSS_TYPE_IPV6_TCP = BIT(4), + IONIC_RSS_TYPE_IPV6_UDP = BIT(5), +}; + +/** + * enum lif_attr - List of LIF attributes + */ +enum ionic_lif_attr { + IONIC_LIF_ATTR_STATE = 0, + IONIC_LIF_ATTR_NAME = 1, + IONIC_LIF_ATTR_MTU = 2, + IONIC_LIF_ATTR_MAC = 3, + IONIC_LIF_ATTR_FEATURES = 4, + IONIC_LIF_ATTR_RSS = 5, + IONIC_LIF_ATTR_STATS_CTRL = 6, +}; + +/** + * struct lif_setattr_cmd - Set LIF attributes on the NIC + * @opcode: Opcode + * @type: Attribute type (enum lif_attr) + * @index: LIF index + * @state: lif state (enum lif_state) + * @name: The netdev name string, 0 terminated + * @mtu: Mtu + * @mac: Station mac + * @features: Features (enum eth_hw_features) + * @rss: RSS properties + * @types: The hash types to enable (see rss_hash_types). + * @key: The hash secret key. + * @addr: Address for the indirection table shared memory. + * @stats_ctl: stats control commands (enum stats_ctl_cmd) + */ +struct ionic_lif_setattr_cmd { + u8 opcode; + u8 attr; + __le16 index; + union { + u8 state; + char name[IONIC_IFNAMSIZ]; + __le32 mtu; + u8 mac[6]; + __le64 features; + struct { + __le16 types; + u8 key[IONIC_RSS_HASH_KEY_SIZE]; + u8 rsvd[6]; + __le64 addr; + } rss; + u8 stats_ctl; + u8 rsvd[60]; + }; +}; + +/** + * struct lif_setattr_comp - LIF set attr command completion + * @status: The status of the command (enum status_code) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @features: features (enum eth_hw_features) + * @color: Color bit + */ +struct ionic_lif_setattr_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + union { + __le64 features; + u8 rsvd2[11]; + }; + u8 color; +}; + +/** + * struct lif_getattr_cmd - Get LIF attributes from the NIC + * @opcode: Opcode + * @attr: Attribute type (enum lif_attr) + * @index: LIF index + */ +struct ionic_lif_getattr_cmd { + u8 opcode; + u8 attr; + __le16 index; + u8 rsvd[60]; +}; + +/** + * struct lif_getattr_comp - LIF get attr command completion + * @status: The status of the command (enum status_code) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @state: lif state (enum lif_state) + * @name: The netdev name string, 0 terminated + * @mtu: Mtu + * @mac: Station mac + * @features: Features (enum eth_hw_features) + * @color: Color bit + */ +struct ionic_lif_getattr_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + union { + u8 state; + __le32 mtu; + u8 mac[6]; + __le64 features; + u8 rsvd2[11]; + }; + u8 color; +}; + +enum ionic_rx_mode { + IONIC_RX_MODE_F_UNICAST = BIT(0), + IONIC_RX_MODE_F_MULTICAST = BIT(1), + IONIC_RX_MODE_F_BROADCAST = BIT(2), + IONIC_RX_MODE_F_PROMISC = BIT(3), + IONIC_RX_MODE_F_ALLMULTI = BIT(4), +}; + +/** + * struct rx_mode_set_cmd - Set LIF's Rx mode command + * @opcode: opcode + * @lif_index: LIF index + * @rx_mode: Rx mode flags: + * IONIC_RX_MODE_F_UNICAST: Accept known unicast packets. + * IONIC_RX_MODE_F_MULTICAST: Accept known multicast packets. + * IONIC_RX_MODE_F_BROADCAST: Accept broadcast packets. + * IONIC_RX_MODE_F_PROMISC: Accept any packets. + * IONIC_RX_MODE_F_ALLMULTI: Accept any multicast packets. + */ +struct ionic_rx_mode_set_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + __le16 rx_mode; + __le16 rsvd2[29]; +}; + +typedef struct ionic_admin_comp ionic_rx_mode_set_comp; + +enum ionic_rx_filter_match_type { + IONIC_RX_FILTER_MATCH_VLAN = 0, + IONIC_RX_FILTER_MATCH_MAC, + IONIC_RX_FILTER_MATCH_MAC_VLAN, +}; + +/** + * struct rx_filter_add_cmd - Add LIF Rx filter command + * @opcode: opcode + * @qtype: Queue type + * @lif_index: LIF index + * @qid: Queue ID + * @match: Rx filter match type. (See IONIC_RX_FILTER_MATCH_xxx) + * @vlan: VLAN ID + * @addr: MAC address (network-byte order) + */ +struct ionic_rx_filter_add_cmd { + u8 opcode; + u8 qtype; + __le16 lif_index; + __le32 qid; + __le16 match; + union { + struct { + __le16 vlan; + } vlan; + struct { + u8 addr[6]; + } mac; + struct { + __le16 vlan; + u8 addr[6]; + } mac_vlan; + u8 rsvd[54]; + }; +}; + +/** + * struct rx_filter_add_comp - Add LIF Rx filter command completion + * @status: The status of the command (enum status_code) + * @comp_index: The index in the descriptor ring for which this + * is the completion. + * @filter_id: Filter ID + * @color: Color bit. + */ +struct ionic_rx_filter_add_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + __le32 filter_id; + u8 rsvd2[7]; + u8 color; +}; + +/** + * struct rx_filter_del_cmd - Delete LIF Rx filter command + * @opcode: opcode + * @lif_index: LIF index + * @filter_id: Filter ID + */ +struct ionic_rx_filter_del_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + __le32 filter_id; + u8 rsvd2[56]; +}; + +typedef struct ionic_admin_comp ionic_rx_filter_del_comp; + +/** + * struct qos_identify_cmd - QoS identify command + * @opcode: opcode + * @ver: Highest version of identify supported by driver + * + */ +struct ionic_qos_identify_cmd { + u8 opcode; + u8 ver; + u8 rsvd[62]; +}; + +/** + * struct qos_identify_comp - QoS identify command completion + * @status: The status of the command (enum status_code) + * @ver: Version of identify returned by device + */ +struct ionic_qos_identify_comp { + u8 status; + u8 ver; + u8 rsvd[14]; +}; + +#define IONIC_QOS_CLASS_MAX 7 +#define IONIC_QOS_CLASS_NAME_SZ 32 +#define IONIC_QOS_DSCP_MAX_VALUES 64 + +/** + * enum qos_class + */ +enum ionic_qos_class { + IONIC_QOS_CLASS_DEFAULT = 0, + IONIC_QOS_CLASS_USER_DEFINED_1 = 1, + IONIC_QOS_CLASS_USER_DEFINED_2 = 2, + IONIC_QOS_CLASS_USER_DEFINED_3 = 3, + IONIC_QOS_CLASS_USER_DEFINED_4 = 4, + IONIC_QOS_CLASS_USER_DEFINED_5 = 5, + IONIC_QOS_CLASS_USER_DEFINED_6 = 6, +}; + +/** + * enum qos_class_type - Traffic classification criteria + */ +enum ionic_qos_class_type { + IONIC_QOS_CLASS_TYPE_NONE = 0, + IONIC_QOS_CLASS_TYPE_PCP = 1, /* Dot1Q pcp */ + IONIC_QOS_CLASS_TYPE_DSCP = 2, /* IP dscp */ +}; + +/** + * enum qos_sched_type - Qos class scheduling type + */ +enum ionic_qos_sched_type { + IONIC_QOS_SCHED_TYPE_STRICT = 0, /* Strict priority */ + IONIC_QOS_SCHED_TYPE_DWRR = 1, /* Deficit weighted round-robin */ +}; + +/** + * union qos_config - Qos configuration structure + * @flags: Configuration flags + * IONIC_QOS_CONFIG_F_ENABLE enable + * IONIC_QOS_CONFIG_F_DROP drop/nodrop + * IONIC_QOS_CONFIG_F_RW_DOT1Q_PCP enable dot1q pcp rewrite + * IONIC_QOS_CONFIG_F_RW_IP_DSCP enable ip dscp rewrite + * @sched_type: Qos class scheduling type (enum qos_sched_type) + * @class_type: Qos class type (enum qos_class_type) + * @pause_type: Qos pause type (enum qos_pause_type) + * @name: Qos class name + * @mtu: MTU of the class + * @pfc_dot1q_pcp: Pcp value for pause frames (valid iff F_NODROP) + * @dwrr_weight: Qos class scheduling weight + * @strict_rlmt: Rate limit for strict priority scheduling + * @rw_dot1q_pcp: Rewrite dot1q pcp to this value (valid iff F_RW_DOT1Q_PCP) + * @rw_ip_dscp: Rewrite ip dscp to this value (valid iff F_RW_IP_DSCP) + * @dot1q_pcp: Dot1q pcp value + * @ndscp: Number of valid dscp values in the ip_dscp field + * @ip_dscp: IP dscp values + */ +union ionic_qos_config { + struct { +#define IONIC_QOS_CONFIG_F_ENABLE BIT(0) +#define IONIC_QOS_CONFIG_F_DROP BIT(1) +#define IONIC_QOS_CONFIG_F_RW_DOT1Q_PCP BIT(2) +#define IONIC_QOS_CONFIG_F_RW_IP_DSCP BIT(3) + u8 flags; + u8 sched_type; + u8 class_type; + u8 pause_type; + char name[IONIC_QOS_CLASS_NAME_SZ]; + __le32 mtu; + /* flow control */ + u8 pfc_cos; + /* scheduler */ + union { + u8 dwrr_weight; + __le64 strict_rlmt; + }; + /* marking */ + union { + u8 rw_dot1q_pcp; + u8 rw_ip_dscp; + }; + /* classification */ + union { + u8 dot1q_pcp; + struct { + u8 ndscp; + u8 ip_dscp[IONIC_QOS_DSCP_MAX_VALUES]; + }; + }; + }; + __le32 words[64]; +}; + +/** + * union qos_identity - QoS identity structure + * @version: Version of the identify structure + * @type: QoS system type + * @nclasses: Number of usable QoS classes + * @config: Current configuration of classes + */ +union ionic_qos_identity { + struct { + u8 version; + u8 type; + u8 rsvd[62]; + union ionic_qos_config config[IONIC_QOS_CLASS_MAX]; + }; + __le32 words[512]; +}; + +/** + * struct qos_init_cmd - QoS config init command + * @opcode: Opcode + * @group: Qos class id + * @info_pa: destination address for qos info + */ +struct ionic_qos_init_cmd { + u8 opcode; + u8 group; + u8 rsvd[6]; + __le64 info_pa; + u8 rsvd1[48]; +}; + +typedef struct ionic_admin_comp ionic_qos_init_comp; + +/** + * struct qos_reset_cmd - Qos config reset command + * @opcode: Opcode + */ +struct ionic_qos_reset_cmd { + u8 opcode; + u8 group; + u8 rsvd[62]; +}; + +typedef struct ionic_admin_comp ionic_qos_reset_comp; + +/** + * struct fw_download_cmd - Firmware download command + * @opcode: opcode + * @addr: dma address of the firmware buffer + * @offset: offset of the firmware buffer within the full image + * @length: number of valid bytes in the firmware buffer + */ +struct ionic_fw_download_cmd { + u8 opcode; + u8 rsvd[3]; + __le32 offset; + __le64 addr; + __le32 length; +}; + +typedef struct ionic_admin_comp ionic_fw_download_comp; + +enum ionic_fw_control_oper { + IONIC_FW_RESET = 0, /* Reset firmware */ + IONIC_FW_INSTALL = 1, /* Install firmware */ + IONIC_FW_ACTIVATE = 2, /* Activate firmware */ +}; + +/** + * struct fw_control_cmd - Firmware control command + * @opcode: opcode + * @oper: firmware control operation (enum fw_control_oper) + * @slot: slot to activate + */ +struct ionic_fw_control_cmd { + u8 opcode; + u8 rsvd[3]; + u8 oper; + u8 slot; + u8 rsvd1[58]; +}; + +/** + * struct fw_control_comp - Firmware control copletion + * @opcode: opcode + * @slot: slot where the firmware was installed + */ +struct ionic_fw_control_comp { + u8 status; + u8 rsvd; + __le16 comp_index; + u8 slot; + u8 rsvd1[10]; + u8 color; +}; + +/****************************************************************** + ******************* RDMA Commands ******************************** + ******************************************************************/ + +/** + * struct rdma_reset_cmd - Reset RDMA LIF cmd + * @opcode: opcode + * @lif_index: lif index + * + * There is no rdma specific dev command completion struct. Completion uses + * the common struct admin_comp. Only the status is indicated. Nonzero status + * means the LIF does not support rdma. + **/ +struct ionic_rdma_reset_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + u8 rsvd2[60]; +}; + +/** + * struct rdma_queue_cmd - Create RDMA Queue command + * @opcode: opcode, 52, 53 + * @lif_index lif index + * @qid_ver: (qid | (rdma version << 24)) + * @cid: intr, eq_id, or cq_id + * @dbid: doorbell page id + * @depth_log2: log base two of queue depth + * @stride_log2: log base two of queue stride + * @dma_addr: address of the queue memory + * @xxx_table_index: temporary, but should not need pgtbl for contig. queues. + * + * The same command struct is used to create an rdma event queue, completion + * queue, or rdma admin queue. The cid is an interrupt number for an event + * queue, an event queue id for a completion queue, or a completion queue id + * for an rdma admin queue. + * + * The queue created via a dev command must be contiguous in dma space. + * + * The dev commands are intended only to be used during driver initialization, + * to create queues supporting the rdma admin queue. Other queues, and other + * types of rdma resources like memory regions, will be created and registered + * via the rdma admin queue, and will support a more complete interface + * providing scatter gather lists for larger, scattered queue buffers and + * memory registration. + * + * There is no rdma specific dev command completion struct. Completion uses + * the common struct admin_comp. Only the status is indicated. + **/ +struct ionic_rdma_queue_cmd { + u8 opcode; + u8 rsvd; + __le16 lif_index; + __le32 qid_ver; + __le32 cid; + __le16 dbid; + u8 depth_log2; + u8 stride_log2; + __le64 dma_addr; + u8 rsvd2[36]; + __le32 xxx_table_index; +}; + +/****************************************************************** + ******************* Notify Events ******************************** + ******************************************************************/ + +/** + * struct notifyq_event + * @eid: event number + * @ecode: event code + * @data: unspecified data about the event + * + * This is the generic event report struct from which the other + * actual events will be formed. + */ +struct ionic_notifyq_event { + __le64 eid; + __le16 ecode; + u8 data[54]; +}; + +/** + * struct link_change_event + * @eid: event number + * @ecode: event code = EVENT_OPCODE_LINK_CHANGE + * @link_status: link up or down, with error bits (enum port_status) + * @link_speed: speed of the network link + * + * Sent when the network link state changes between UP and DOWN + */ +struct ionic_link_change_event { + __le64 eid; + __le16 ecode; + __le16 link_status; + __le32 link_speed; /* units of 1Mbps: e.g. 10000 = 10Gbps */ + u8 rsvd[48]; +}; + +/** + * struct reset_event + * @eid: event number + * @ecode: event code = EVENT_OPCODE_RESET + * @reset_code: reset type + * @state: 0=pending, 1=complete, 2=error + * + * Sent when the NIC or some subsystem is going to be or + * has been reset. + */ +struct ionic_reset_event { + __le64 eid; + __le16 ecode; + u8 reset_code; + u8 state; + u8 rsvd[52]; +}; + +/** + * struct heartbeat_event + * @eid: event number + * @ecode: event code = EVENT_OPCODE_HEARTBEAT + * + * Sent periodically by the NIC to indicate continued health + */ +struct ionic_heartbeat_event { + __le64 eid; + __le16 ecode; + u8 rsvd[54]; +}; + +/** + * struct log_event + * @eid: event number + * @ecode: event code = EVENT_OPCODE_LOG + * @data: log data + * + * Sent to notify the driver of an internal error. + */ +struct ionic_log_event { + __le64 eid; + __le16 ecode; + u8 data[54]; +}; + +/** + * struct port_stats + */ +struct ionic_port_stats { + __le64 frames_rx_ok; + __le64 frames_rx_all; + __le64 frames_rx_bad_fcs; + __le64 frames_rx_bad_all; + __le64 octets_rx_ok; + __le64 octets_rx_all; + __le64 frames_rx_unicast; + __le64 frames_rx_multicast; + __le64 frames_rx_broadcast; + __le64 frames_rx_pause; + __le64 frames_rx_bad_length; + __le64 frames_rx_undersized; + __le64 frames_rx_oversized; + __le64 frames_rx_fragments; + __le64 frames_rx_jabber; + __le64 frames_rx_pripause; + __le64 frames_rx_stomped_crc; + __le64 frames_rx_too_long; + __le64 frames_rx_vlan_good; + __le64 frames_rx_dropped; + __le64 frames_rx_less_than_64b; + __le64 frames_rx_64b; + __le64 frames_rx_65b_127b; + __le64 frames_rx_128b_255b; + __le64 frames_rx_256b_511b; + __le64 frames_rx_512b_1023b; + __le64 frames_rx_1024b_1518b; + __le64 frames_rx_1519b_2047b; + __le64 frames_rx_2048b_4095b; + __le64 frames_rx_4096b_8191b; + __le64 frames_rx_8192b_9215b; + __le64 frames_rx_other; + __le64 frames_tx_ok; + __le64 frames_tx_all; + __le64 frames_tx_bad; + __le64 octets_tx_ok; + __le64 octets_tx_total; + __le64 frames_tx_unicast; + __le64 frames_tx_multicast; + __le64 frames_tx_broadcast; + __le64 frames_tx_pause; + __le64 frames_tx_pripause; + __le64 frames_tx_vlan; + __le64 frames_tx_less_than_64b; + __le64 frames_tx_64b; + __le64 frames_tx_65b_127b; + __le64 frames_tx_128b_255b; + __le64 frames_tx_256b_511b; + __le64 frames_tx_512b_1023b; + __le64 frames_tx_1024b_1518b; + __le64 frames_tx_1519b_2047b; + __le64 frames_tx_2048b_4095b; + __le64 frames_tx_4096b_8191b; + __le64 frames_tx_8192b_9215b; + __le64 frames_tx_other; + __le64 frames_tx_pri_0; + __le64 frames_tx_pri_1; + __le64 frames_tx_pri_2; + __le64 frames_tx_pri_3; + __le64 frames_tx_pri_4; + __le64 frames_tx_pri_5; + __le64 frames_tx_pri_6; + __le64 frames_tx_pri_7; + __le64 frames_rx_pri_0; + __le64 frames_rx_pri_1; + __le64 frames_rx_pri_2; + __le64 frames_rx_pri_3; + __le64 frames_rx_pri_4; + __le64 frames_rx_pri_5; + __le64 frames_rx_pri_6; + __le64 frames_rx_pri_7; + __le64 tx_pripause_0_1us_count; + __le64 tx_pripause_1_1us_count; + __le64 tx_pripause_2_1us_count; + __le64 tx_pripause_3_1us_count; + __le64 tx_pripause_4_1us_count; + __le64 tx_pripause_5_1us_count; + __le64 tx_pripause_6_1us_count; + __le64 tx_pripause_7_1us_count; + __le64 rx_pripause_0_1us_count; + __le64 rx_pripause_1_1us_count; + __le64 rx_pripause_2_1us_count; + __le64 rx_pripause_3_1us_count; + __le64 rx_pripause_4_1us_count; + __le64 rx_pripause_5_1us_count; + __le64 rx_pripause_6_1us_count; + __le64 rx_pripause_7_1us_count; + __le64 rx_pause_1us_count; + __le64 frames_tx_truncated; +}; + +struct ionic_mgmt_port_stats { + __le64 frames_rx_ok; + __le64 frames_rx_all; + __le64 frames_rx_bad_fcs; + __le64 frames_rx_bad_all; + __le64 octets_rx_ok; + __le64 octets_rx_all; + __le64 frames_rx_unicast; + __le64 frames_rx_multicast; + __le64 frames_rx_broadcast; + __le64 frames_rx_pause; + __le64 frames_rx_bad_length0; + __le64 frames_rx_undersized1; + __le64 frames_rx_oversized2; + __le64 frames_rx_fragments3; + __le64 frames_rx_jabber4; + __le64 frames_rx_64b5; + __le64 frames_rx_65b_127b6; + __le64 frames_rx_128b_255b7; + __le64 frames_rx_256b_511b8; + __le64 frames_rx_512b_1023b9; + __le64 frames_rx_1024b_1518b0; + __le64 frames_rx_gt_1518b1; + __le64 frames_rx_fifo_full2; + __le64 frames_tx_ok3; + __le64 frames_tx_all4; + __le64 frames_tx_bad5; + __le64 octets_tx_ok6; + __le64 octets_tx_total7; + __le64 frames_tx_unicast8; + __le64 frames_tx_multicast9; + __le64 frames_tx_broadcast0; + __le64 frames_tx_pause1; +}; + +/** + * struct port_identity - port identity structure + * @version: identity structure version + * @type: type of port (enum port_type) + * @num_lanes: number of lanes for the port + * @autoneg: autoneg supported + * @min_frame_size: minimum frame size supported + * @max_frame_size: maximum frame size supported + * @fec_type: supported fec types + * @pause_type: supported pause types + * @loopback_mode: supported loopback mode + * @speeds: supported speeds + * @config: current port configuration + */ +union ionic_port_identity { + struct { + u8 version; + u8 type; + u8 num_lanes; + u8 autoneg; + __le32 min_frame_size; + __le32 max_frame_size; + u8 fec_type[4]; + u8 pause_type[2]; + u8 loopback_mode[2]; + __le32 speeds[16]; + u8 rsvd2[44]; + union ionic_port_config config; + }; + __le32 words[512]; +}; + +/** + * struct port_info - port info structure + * @port_status: port status + * @port_stats: port stats + */ +struct ionic_port_info { + union ionic_port_config config; + struct ionic_port_status status; + struct ionic_port_stats stats; +}; + +/** + * struct lif_stats + */ +struct ionic_lif_stats { + /* RX */ + __le64 rx_ucast_bytes; + __le64 rx_ucast_packets; + __le64 rx_mcast_bytes; + __le64 rx_mcast_packets; + __le64 rx_bcast_bytes; + __le64 rx_bcast_packets; + __le64 rsvd0; + __le64 rsvd1; + /* RX drops */ + __le64 rx_ucast_drop_bytes; + __le64 rx_ucast_drop_packets; + __le64 rx_mcast_drop_bytes; + __le64 rx_mcast_drop_packets; + __le64 rx_bcast_drop_bytes; + __le64 rx_bcast_drop_packets; + __le64 rx_dma_error; + __le64 rsvd2; + /* TX */ + __le64 tx_ucast_bytes; + __le64 tx_ucast_packets; + __le64 tx_mcast_bytes; + __le64 tx_mcast_packets; + __le64 tx_bcast_bytes; + __le64 tx_bcast_packets; + __le64 rsvd3; + __le64 rsvd4; + /* TX drops */ + __le64 tx_ucast_drop_bytes; + __le64 tx_ucast_drop_packets; + __le64 tx_mcast_drop_bytes; + __le64 tx_mcast_drop_packets; + __le64 tx_bcast_drop_bytes; + __le64 tx_bcast_drop_packets; + __le64 tx_dma_error; + __le64 rsvd5; + /* Rx Queue/Ring drops */ + __le64 rx_queue_disabled; + __le64 rx_queue_empty; + __le64 rx_queue_error; + __le64 rx_desc_fetch_error; + __le64 rx_desc_data_error; + __le64 rsvd6; + __le64 rsvd7; + __le64 rsvd8; + /* Tx Queue/Ring drops */ + __le64 tx_queue_disabled; + __le64 tx_queue_error; + __le64 tx_desc_fetch_error; + __le64 tx_desc_data_error; + __le64 rsvd9; + __le64 rsvd10; + __le64 rsvd11; + __le64 rsvd12; + + /* RDMA/ROCE TX */ + __le64 tx_rdma_ucast_bytes; + __le64 tx_rdma_ucast_packets; + __le64 tx_rdma_mcast_bytes; + __le64 tx_rdma_mcast_packets; + __le64 tx_rdma_cnp_packets; + __le64 rsvd13; + __le64 rsvd14; + __le64 rsvd15; + + /* RDMA/ROCE RX */ + __le64 rx_rdma_ucast_bytes; + __le64 rx_rdma_ucast_packets; + __le64 rx_rdma_mcast_bytes; + __le64 rx_rdma_mcast_packets; + __le64 rx_rdma_cnp_packets; + __le64 rx_rdma_ecn_packets; + __le64 rsvd16; + __le64 rsvd17; + + __le64 rsvd18; + __le64 rsvd19; + __le64 rsvd20; + __le64 rsvd21; + __le64 rsvd22; + __le64 rsvd23; + __le64 rsvd24; + __le64 rsvd25; + + __le64 rsvd26; + __le64 rsvd27; + __le64 rsvd28; + __le64 rsvd29; + __le64 rsvd30; + __le64 rsvd31; + __le64 rsvd32; + __le64 rsvd33; + + __le64 rsvd34; + __le64 rsvd35; + __le64 rsvd36; + __le64 rsvd37; + __le64 rsvd38; + __le64 rsvd39; + __le64 rsvd40; + __le64 rsvd41; + + __le64 rsvd42; + __le64 rsvd43; + __le64 rsvd44; + __le64 rsvd45; + __le64 rsvd46; + __le64 rsvd47; + __le64 rsvd48; + __le64 rsvd49; + + /* RDMA/ROCE REQ Error/Debugs (768 - 895) */ + __le64 rdma_req_rx_pkt_seq_err; + __le64 rdma_req_rx_rnr_retry_err; + __le64 rdma_req_rx_remote_access_err; + __le64 rdma_req_rx_remote_inv_req_err; + __le64 rdma_req_rx_remote_oper_err; + __le64 rdma_req_rx_implied_nak_seq_err; + __le64 rdma_req_rx_cqe_err; + __le64 rdma_req_rx_cqe_flush_err; + + __le64 rdma_req_rx_dup_responses; + __le64 rdma_req_rx_invalid_packets; + __le64 rdma_req_tx_local_access_err; + __le64 rdma_req_tx_local_oper_err; + __le64 rdma_req_tx_memory_mgmt_err; + __le64 rsvd52; + __le64 rsvd53; + __le64 rsvd54; + + /* RDMA/ROCE RESP Error/Debugs (896 - 1023) */ + __le64 rdma_resp_rx_dup_requests; + __le64 rdma_resp_rx_out_of_buffer; + __le64 rdma_resp_rx_out_of_seq_pkts; + __le64 rdma_resp_rx_cqe_err; + __le64 rdma_resp_rx_cqe_flush_err; + __le64 rdma_resp_rx_local_len_err; + __le64 rdma_resp_rx_inv_request_err; + __le64 rdma_resp_rx_local_qp_oper_err; + + __le64 rdma_resp_rx_out_of_atomic_resource; + __le64 rdma_resp_tx_pkt_seq_err; + __le64 rdma_resp_tx_remote_inv_req_err; + __le64 rdma_resp_tx_remote_access_err; + __le64 rdma_resp_tx_remote_oper_err; + __le64 rdma_resp_tx_rnr_retry_err; + __le64 rsvd57; + __le64 rsvd58; +}; + +/** + * struct lif_info - lif info structure + */ +struct ionic_lif_info { + union ionic_lif_config config; + struct ionic_lif_status status; + struct ionic_lif_stats stats; +}; + +union ionic_dev_cmd { + u32 words[16]; + struct ionic_admin_cmd cmd; + struct ionic_nop_cmd nop; + + struct ionic_dev_identify_cmd identify; + struct ionic_dev_init_cmd init; + struct ionic_dev_reset_cmd reset; + struct ionic_dev_getattr_cmd getattr; + struct ionic_dev_setattr_cmd setattr; + + struct ionic_port_identify_cmd port_identify; + struct ionic_port_init_cmd port_init; + struct ionic_port_reset_cmd port_reset; + struct ionic_port_getattr_cmd port_getattr; + struct ionic_port_setattr_cmd port_setattr; + + struct ionic_lif_identify_cmd lif_identify; + struct ionic_lif_init_cmd lif_init; + struct ionic_lif_reset_cmd lif_reset; + + struct ionic_qos_identify_cmd qos_identify; + struct ionic_qos_init_cmd qos_init; + struct ionic_qos_reset_cmd qos_reset; + + struct ionic_q_init_cmd q_init; +}; + +union ionic_dev_cmd_comp { + u32 words[4]; + u8 status; + struct ionic_admin_comp comp; + struct ionic_nop_comp nop; + + struct ionic_dev_identify_comp identify; + struct ionic_dev_init_comp init; + struct ionic_dev_reset_comp reset; + struct ionic_dev_getattr_comp getattr; + struct ionic_dev_setattr_comp setattr; + + struct ionic_port_identify_comp port_identify; + struct ionic_port_init_comp port_init; + struct ionic_port_reset_comp port_reset; + struct ionic_port_getattr_comp port_getattr; + struct ionic_port_setattr_comp port_setattr; + + struct ionic_lif_identify_comp lif_identify; + struct ionic_lif_init_comp lif_init; + ionic_lif_reset_comp lif_reset; + + struct ionic_qos_identify_comp qos_identify; + ionic_qos_init_comp qos_init; + ionic_qos_reset_comp qos_reset; + + struct ionic_q_init_comp q_init; +}; + +/** + * union dev_info - Device info register format (read-only) + * @signature: Signature value of 0x44455649 ('DEVI'). + * @version: Current version of info. + * @asic_type: Asic type. + * @asic_rev: Asic revision. + * @fw_status: Firmware status. + * @fw_heartbeat: Firmware heartbeat counter. + * @serial_num: Serial number. + * @fw_version: Firmware version. + */ +union ionic_dev_info_regs { +#define IONIC_DEVINFO_FWVERS_BUFLEN 32 +#define IONIC_DEVINFO_SERIAL_BUFLEN 32 + struct { + u32 signature; + u8 version; + u8 asic_type; + u8 asic_rev; + u8 fw_status; + u32 fw_heartbeat; + char fw_version[IONIC_DEVINFO_FWVERS_BUFLEN]; + char serial_num[IONIC_DEVINFO_SERIAL_BUFLEN]; + }; + u32 words[512]; +}; + +/** + * union dev_cmd_regs - Device command register format (read-write) + * @doorbell: Device Cmd Doorbell, write-only. + * Write a 1 to signal device to process cmd, + * poll done for completion. + * @done: Done indicator, bit 0 == 1 when command is complete. + * @cmd: Opcode-specific command bytes + * @comp: Opcode-specific response bytes + * @data: Opcode-specific side-data + */ +union ionic_dev_cmd_regs { + struct { + u32 doorbell; + u32 done; + union ionic_dev_cmd cmd; + union ionic_dev_cmd_comp comp; + u8 rsvd[48]; + u32 data[478]; + }; + u32 words[512]; +}; + +/** + * union dev_regs - Device register format in for bar 0 page 0 + * @info: Device info registers + * @devcmd: Device command registers + */ +union ionic_dev_regs { + struct { + union ionic_dev_info_regs info; + union ionic_dev_cmd_regs devcmd; + }; + __le32 words[1024]; +}; + +union ionic_adminq_cmd { + struct ionic_admin_cmd cmd; + struct ionic_nop_cmd nop; + struct ionic_q_init_cmd q_init; + struct ionic_q_control_cmd q_control; + struct ionic_lif_setattr_cmd lif_setattr; + struct ionic_lif_getattr_cmd lif_getattr; + struct ionic_rx_mode_set_cmd rx_mode_set; + struct ionic_rx_filter_add_cmd rx_filter_add; + struct ionic_rx_filter_del_cmd rx_filter_del; + struct ionic_rdma_reset_cmd rdma_reset; + struct ionic_rdma_queue_cmd rdma_queue; + struct ionic_fw_download_cmd fw_download; + struct ionic_fw_control_cmd fw_control; +}; + +union ionic_adminq_comp { + struct ionic_admin_comp comp; + struct ionic_nop_comp nop; + struct ionic_q_init_comp q_init; + struct ionic_lif_setattr_comp lif_setattr; + struct ionic_lif_getattr_comp lif_getattr; + struct ionic_rx_filter_add_comp rx_filter_add; + struct ionic_fw_control_comp fw_control; +}; + +#define IONIC_BARS_MAX 6 +#define IONIC_PCI_BAR_DBELL 1 + +/* BAR0 */ +#define IONIC_BAR0_SIZE 0x8000 + +#define IONIC_BAR0_DEV_INFO_REGS_OFFSET 0x0000 +#define IONIC_BAR0_DEV_CMD_REGS_OFFSET 0x0800 +#define IONIC_BAR0_DEV_CMD_DATA_REGS_OFFSET 0x0c00 +#define IONIC_BAR0_INTR_STATUS_OFFSET 0x1000 +#define IONIC_BAR0_INTR_CTRL_OFFSET 0x2000 +#define IONIC_DEV_CMD_DONE 0x00000001 + +#define IONIC_ASIC_TYPE_CAPRI 0 + +/** + * struct doorbell - Doorbell register layout + * @p_index: Producer index + * @ring: Selects the specific ring of the queue to update. + * Type-specific meaning: + * ring=0: Default producer/consumer queue. + * ring=1: (CQ, EQ) Re-Arm queue. RDMA CQs + * send events to EQs when armed. EQs send + * interrupts when armed. + * @qid: The queue id selects the queue destination for the + * producer index and flags. + */ +struct ionic_doorbell { + __le16 p_index; + u8 ring; + u8 qid_lo; + __le16 qid_hi; + u16 rsvd2; +}; + +struct ionic_intr_status { + u32 status[2]; +}; + +struct ionic_notifyq_cmd { + __le32 data; /* Not used but needed for qcq structure */ +}; + +union ionic_notifyq_comp { + struct ionic_notifyq_event event; + struct ionic_link_change_event link_change; + struct ionic_reset_event reset; + struct ionic_heartbeat_event heartbeat; + struct ionic_log_event log; +}; + +/* Deprecate */ +struct ionic_identity { + union ionic_drv_identity drv; + union ionic_dev_identity dev; + union ionic_lif_identity lif; + union ionic_port_identity port; + union ionic_qos_identity qos; +}; + +#pragma pack(pop) + +#endif /* _IONIC_IF_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c new file mode 100644 index 000000000000..db7c82742828 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c @@ -0,0 +1,2274 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/netdevice.h> +#include <linux/etherdevice.h> +#include <linux/rtnetlink.h> +#include <linux/interrupt.h> +#include <linux/pci.h> +#include <linux/cpumask.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_txrx.h" +#include "ionic_ethtool.h" +#include "ionic_debugfs.h" + +static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode); +static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr); +static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr); +static void ionic_link_status_check(struct ionic_lif *lif); + +static void ionic_lif_deferred_work(struct work_struct *work) +{ + struct ionic_lif *lif = container_of(work, struct ionic_lif, deferred.work); + struct ionic_deferred *def = &lif->deferred; + struct ionic_deferred_work *w = NULL; + + spin_lock_bh(&def->lock); + if (!list_empty(&def->list)) { + w = list_first_entry(&def->list, + struct ionic_deferred_work, list); + list_del(&w->list); + } + spin_unlock_bh(&def->lock); + + if (w) { + switch (w->type) { + case IONIC_DW_TYPE_RX_MODE: + ionic_lif_rx_mode(lif, w->rx_mode); + break; + case IONIC_DW_TYPE_RX_ADDR_ADD: + ionic_lif_addr_add(lif, w->addr); + break; + case IONIC_DW_TYPE_RX_ADDR_DEL: + ionic_lif_addr_del(lif, w->addr); + break; + case IONIC_DW_TYPE_LINK_STATUS: + ionic_link_status_check(lif); + break; + default: + break; + } + kfree(w); + schedule_work(&def->work); + } +} + +static void ionic_lif_deferred_enqueue(struct ionic_deferred *def, + struct ionic_deferred_work *work) +{ + spin_lock_bh(&def->lock); + list_add_tail(&work->list, &def->list); + spin_unlock_bh(&def->lock); + schedule_work(&def->work); +} + +static void ionic_link_status_check(struct ionic_lif *lif) +{ + struct net_device *netdev = lif->netdev; + u16 link_status; + bool link_up; + + link_status = le16_to_cpu(lif->info->status.link_status); + link_up = link_status == IONIC_PORT_OPER_STATUS_UP; + + /* filter out the no-change cases */ + if (link_up == netif_carrier_ok(netdev)) + goto link_out; + + if (link_up) { + netdev_info(netdev, "Link up - %d Gbps\n", + le32_to_cpu(lif->info->status.link_speed) / 1000); + + if (test_bit(IONIC_LIF_UP, lif->state)) { + netif_tx_wake_all_queues(lif->netdev); + netif_carrier_on(netdev); + } + } else { + netdev_info(netdev, "Link down\n"); + + /* carrier off first to avoid watchdog timeout */ + netif_carrier_off(netdev); + if (test_bit(IONIC_LIF_UP, lif->state)) + netif_tx_stop_all_queues(netdev); + } + +link_out: + clear_bit(IONIC_LIF_LINK_CHECK_REQUESTED, lif->state); +} + +static void ionic_link_status_check_request(struct ionic_lif *lif) +{ + struct ionic_deferred_work *work; + + /* we only need one request outstanding at a time */ + if (test_and_set_bit(IONIC_LIF_LINK_CHECK_REQUESTED, lif->state)) + return; + + if (in_interrupt()) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) + return; + + work->type = IONIC_DW_TYPE_LINK_STATUS; + ionic_lif_deferred_enqueue(&lif->deferred, work); + } else { + ionic_link_status_check(lif); + } +} + +static irqreturn_t ionic_isr(int irq, void *data) +{ + struct napi_struct *napi = data; + + napi_schedule_irqoff(napi); + + return IRQ_HANDLED; +} + +static int ionic_request_irq(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct ionic_intr_info *intr = &qcq->intr; + struct device *dev = lif->ionic->dev; + struct ionic_queue *q = &qcq->q; + const char *name; + + if (lif->registered) + name = lif->netdev->name; + else + name = dev_name(dev); + + snprintf(intr->name, sizeof(intr->name), + "%s-%s-%s", IONIC_DRV_NAME, name, q->name); + + return devm_request_irq(dev, intr->vector, ionic_isr, + 0, intr->name, &qcq->napi); +} + +static int ionic_intr_alloc(struct ionic_lif *lif, struct ionic_intr_info *intr) +{ + struct ionic *ionic = lif->ionic; + int index; + + index = find_first_zero_bit(ionic->intrs, ionic->nintrs); + if (index == ionic->nintrs) { + netdev_warn(lif->netdev, "%s: no intr, index=%d nintrs=%d\n", + __func__, index, ionic->nintrs); + return -ENOSPC; + } + + set_bit(index, ionic->intrs); + ionic_intr_init(&ionic->idev, intr, index); + + return 0; +} + +static void ionic_intr_free(struct ionic_lif *lif, int index) +{ + if (index != INTR_INDEX_NOT_ASSIGNED && index < lif->ionic->nintrs) + clear_bit(index, lif->ionic->intrs); +} + +static int ionic_qcq_enable(struct ionic_qcq *qcq) +{ + struct ionic_queue *q = &qcq->q; + struct ionic_lif *lif = q->lif; + struct ionic_dev *idev; + struct device *dev; + + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.q_control = { + .opcode = IONIC_CMD_Q_CONTROL, + .lif_index = cpu_to_le16(lif->index), + .type = q->type, + .index = cpu_to_le32(q->index), + .oper = IONIC_Q_ENABLE, + }, + }; + + idev = &lif->ionic->idev; + dev = lif->ionic->dev; + + dev_dbg(dev, "q_enable.index %d q_enable.qtype %d\n", + ctx.cmd.q_control.index, ctx.cmd.q_control.type); + + if (qcq->flags & IONIC_QCQ_F_INTR) { + irq_set_affinity_hint(qcq->intr.vector, + &qcq->intr.affinity_mask); + napi_enable(&qcq->napi); + ionic_intr_clean(idev->intr_ctrl, qcq->intr.index); + ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, + IONIC_INTR_MASK_CLEAR); + } + + return ionic_adminq_post_wait(lif, &ctx); +} + +static int ionic_qcq_disable(struct ionic_qcq *qcq) +{ + struct ionic_queue *q = &qcq->q; + struct ionic_lif *lif = q->lif; + struct ionic_dev *idev; + struct device *dev; + + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.q_control = { + .opcode = IONIC_CMD_Q_CONTROL, + .lif_index = cpu_to_le16(lif->index), + .type = q->type, + .index = cpu_to_le32(q->index), + .oper = IONIC_Q_DISABLE, + }, + }; + + idev = &lif->ionic->idev; + dev = lif->ionic->dev; + + dev_dbg(dev, "q_disable.index %d q_disable.qtype %d\n", + ctx.cmd.q_control.index, ctx.cmd.q_control.type); + + if (qcq->flags & IONIC_QCQ_F_INTR) { + ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, + IONIC_INTR_MASK_SET); + synchronize_irq(qcq->intr.vector); + irq_set_affinity_hint(qcq->intr.vector, NULL); + napi_disable(&qcq->napi); + } + + return ionic_adminq_post_wait(lif, &ctx); +} + +static void ionic_lif_qcq_deinit(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct ionic_dev *idev = &lif->ionic->idev; + struct device *dev = lif->ionic->dev; + + if (!qcq) + return; + + ionic_debugfs_del_qcq(qcq); + + if (!(qcq->flags & IONIC_QCQ_F_INITED)) + return; + + if (qcq->flags & IONIC_QCQ_F_INTR) { + ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, + IONIC_INTR_MASK_SET); + devm_free_irq(dev, qcq->intr.vector, &qcq->napi); + netif_napi_del(&qcq->napi); + } + + qcq->flags &= ~IONIC_QCQ_F_INITED; +} + +static void ionic_qcq_free(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct device *dev = lif->ionic->dev; + + if (!qcq) + return; + + dma_free_coherent(dev, qcq->total_size, qcq->base, qcq->base_pa); + qcq->base = NULL; + qcq->base_pa = 0; + + if (qcq->flags & IONIC_QCQ_F_INTR) + ionic_intr_free(lif, qcq->intr.index); + + devm_kfree(dev, qcq->cq.info); + qcq->cq.info = NULL; + devm_kfree(dev, qcq->q.info); + qcq->q.info = NULL; + devm_kfree(dev, qcq); +} + +static void ionic_qcqs_free(struct ionic_lif *lif) +{ + struct device *dev = lif->ionic->dev; + unsigned int i; + + if (lif->notifyqcq) { + ionic_qcq_free(lif, lif->notifyqcq); + lif->notifyqcq = NULL; + } + + if (lif->adminqcq) { + ionic_qcq_free(lif, lif->adminqcq); + lif->adminqcq = NULL; + } + + for (i = 0; i < lif->nxqs; i++) + if (lif->rxqcqs[i].stats) + devm_kfree(dev, lif->rxqcqs[i].stats); + + devm_kfree(dev, lif->rxqcqs); + lif->rxqcqs = NULL; + + for (i = 0; i < lif->nxqs; i++) + if (lif->txqcqs[i].stats) + devm_kfree(dev, lif->txqcqs[i].stats); + + devm_kfree(dev, lif->txqcqs); + lif->txqcqs = NULL; +} + +static void ionic_link_qcq_interrupts(struct ionic_qcq *src_qcq, + struct ionic_qcq *n_qcq) +{ + if (WARN_ON(n_qcq->flags & IONIC_QCQ_F_INTR)) { + ionic_intr_free(n_qcq->cq.lif, n_qcq->intr.index); + n_qcq->flags &= ~IONIC_QCQ_F_INTR; + } + + n_qcq->intr.vector = src_qcq->intr.vector; + n_qcq->intr.index = src_qcq->intr.index; +} + +static int ionic_qcq_alloc(struct ionic_lif *lif, unsigned int type, + unsigned int index, + const char *name, unsigned int flags, + unsigned int num_descs, unsigned int desc_size, + unsigned int cq_desc_size, + unsigned int sg_desc_size, + unsigned int pid, struct ionic_qcq **qcq) +{ + struct ionic_dev *idev = &lif->ionic->idev; + u32 q_size, cq_size, sg_size, total_size; + struct device *dev = lif->ionic->dev; + void *q_base, *cq_base, *sg_base; + dma_addr_t cq_base_pa = 0; + dma_addr_t sg_base_pa = 0; + dma_addr_t q_base_pa = 0; + struct ionic_qcq *new; + int err; + + *qcq = NULL; + + q_size = num_descs * desc_size; + cq_size = num_descs * cq_desc_size; + sg_size = num_descs * sg_desc_size; + + total_size = ALIGN(q_size, PAGE_SIZE) + ALIGN(cq_size, PAGE_SIZE); + /* Note: aligning q_size/cq_size is not enough due to cq_base + * address aligning as q_base could be not aligned to the page. + * Adding PAGE_SIZE. + */ + total_size += PAGE_SIZE; + if (flags & IONIC_QCQ_F_SG) { + total_size += ALIGN(sg_size, PAGE_SIZE); + total_size += PAGE_SIZE; + } + + new = devm_kzalloc(dev, sizeof(*new), GFP_KERNEL); + if (!new) { + netdev_err(lif->netdev, "Cannot allocate queue structure\n"); + err = -ENOMEM; + goto err_out; + } + + new->flags = flags; + + new->q.info = devm_kzalloc(dev, sizeof(*new->q.info) * num_descs, + GFP_KERNEL); + if (!new->q.info) { + netdev_err(lif->netdev, "Cannot allocate queue info\n"); + err = -ENOMEM; + goto err_out; + } + + new->q.type = type; + + err = ionic_q_init(lif, idev, &new->q, index, name, num_descs, + desc_size, sg_desc_size, pid); + if (err) { + netdev_err(lif->netdev, "Cannot initialize queue\n"); + goto err_out; + } + + if (flags & IONIC_QCQ_F_INTR) { + err = ionic_intr_alloc(lif, &new->intr); + if (err) { + netdev_warn(lif->netdev, "no intr for %s: %d\n", + name, err); + goto err_out; + } + + err = ionic_bus_get_irq(lif->ionic, new->intr.index); + if (err < 0) { + netdev_warn(lif->netdev, "no vector for %s: %d\n", + name, err); + goto err_out_free_intr; + } + new->intr.vector = err; + ionic_intr_mask_assert(idev->intr_ctrl, new->intr.index, + IONIC_INTR_MASK_SET); + + new->intr.cpu = new->intr.index % num_online_cpus(); + if (cpu_online(new->intr.cpu)) + cpumask_set_cpu(new->intr.cpu, + &new->intr.affinity_mask); + } else { + new->intr.index = INTR_INDEX_NOT_ASSIGNED; + } + + new->cq.info = devm_kzalloc(dev, sizeof(*new->cq.info) * num_descs, + GFP_KERNEL); + if (!new->cq.info) { + netdev_err(lif->netdev, "Cannot allocate completion queue info\n"); + err = -ENOMEM; + goto err_out_free_intr; + } + + err = ionic_cq_init(lif, &new->cq, &new->intr, num_descs, cq_desc_size); + if (err) { + netdev_err(lif->netdev, "Cannot initialize completion queue\n"); + goto err_out_free_intr; + } + + new->base = dma_alloc_coherent(dev, total_size, &new->base_pa, + GFP_KERNEL); + if (!new->base) { + netdev_err(lif->netdev, "Cannot allocate queue DMA memory\n"); + err = -ENOMEM; + goto err_out_free_intr; + } + + new->total_size = total_size; + + q_base = new->base; + q_base_pa = new->base_pa; + + cq_base = (void *)ALIGN((uintptr_t)q_base + q_size, PAGE_SIZE); + cq_base_pa = ALIGN(q_base_pa + q_size, PAGE_SIZE); + + if (flags & IONIC_QCQ_F_SG) { + sg_base = (void *)ALIGN((uintptr_t)cq_base + cq_size, + PAGE_SIZE); + sg_base_pa = ALIGN(cq_base_pa + cq_size, PAGE_SIZE); + ionic_q_sg_map(&new->q, sg_base, sg_base_pa); + } + + ionic_q_map(&new->q, q_base, q_base_pa); + ionic_cq_map(&new->cq, cq_base, cq_base_pa); + ionic_cq_bind(&new->cq, &new->q); + + *qcq = new; + + return 0; + +err_out_free_intr: + ionic_intr_free(lif, new->intr.index); +err_out: + dev_err(dev, "qcq alloc of %s%d failed %d\n", name, index, err); + return err; +} + +static int ionic_qcqs_alloc(struct ionic_lif *lif) +{ + struct device *dev = lif->ionic->dev; + unsigned int q_list_size; + unsigned int flags; + int err; + int i; + + flags = IONIC_QCQ_F_INTR; + err = ionic_qcq_alloc(lif, IONIC_QTYPE_ADMINQ, 0, "admin", flags, + IONIC_ADMINQ_LENGTH, + sizeof(struct ionic_admin_cmd), + sizeof(struct ionic_admin_comp), + 0, lif->kern_pid, &lif->adminqcq); + if (err) + return err; + + if (lif->ionic->nnqs_per_lif) { + flags = IONIC_QCQ_F_NOTIFYQ; + err = ionic_qcq_alloc(lif, IONIC_QTYPE_NOTIFYQ, 0, "notifyq", + flags, IONIC_NOTIFYQ_LENGTH, + sizeof(struct ionic_notifyq_cmd), + sizeof(union ionic_notifyq_comp), + 0, lif->kern_pid, &lif->notifyqcq); + if (err) + goto err_out_free_adminqcq; + + /* Let the notifyq ride on the adminq interrupt */ + ionic_link_qcq_interrupts(lif->adminqcq, lif->notifyqcq); + } + + q_list_size = sizeof(*lif->txqcqs) * lif->nxqs; + err = -ENOMEM; + lif->txqcqs = devm_kzalloc(dev, q_list_size, GFP_KERNEL); + if (!lif->txqcqs) + goto err_out_free_notifyqcq; + for (i = 0; i < lif->nxqs; i++) { + lif->txqcqs[i].stats = devm_kzalloc(dev, + sizeof(struct ionic_q_stats), + GFP_KERNEL); + if (!lif->txqcqs[i].stats) + goto err_out_free_tx_stats; + } + + lif->rxqcqs = devm_kzalloc(dev, q_list_size, GFP_KERNEL); + if (!lif->rxqcqs) + goto err_out_free_tx_stats; + for (i = 0; i < lif->nxqs; i++) { + lif->rxqcqs[i].stats = devm_kzalloc(dev, + sizeof(struct ionic_q_stats), + GFP_KERNEL); + if (!lif->rxqcqs[i].stats) + goto err_out_free_rx_stats; + } + + return 0; + +err_out_free_rx_stats: + for (i = 0; i < lif->nxqs; i++) + if (lif->rxqcqs[i].stats) + devm_kfree(dev, lif->rxqcqs[i].stats); + devm_kfree(dev, lif->rxqcqs); + lif->rxqcqs = NULL; +err_out_free_tx_stats: + for (i = 0; i < lif->nxqs; i++) + if (lif->txqcqs[i].stats) + devm_kfree(dev, lif->txqcqs[i].stats); + devm_kfree(dev, lif->txqcqs); + lif->txqcqs = NULL; +err_out_free_notifyqcq: + if (lif->notifyqcq) { + ionic_qcq_free(lif, lif->notifyqcq); + lif->notifyqcq = NULL; + } +err_out_free_adminqcq: + ionic_qcq_free(lif, lif->adminqcq); + lif->adminqcq = NULL; + + return err; +} + +static int ionic_lif_txq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct device *dev = lif->ionic->dev; + struct ionic_queue *q = &qcq->q; + struct ionic_cq *cq = &qcq->cq; + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.q_init = { + .opcode = IONIC_CMD_Q_INIT, + .lif_index = cpu_to_le16(lif->index), + .type = q->type, + .index = cpu_to_le32(q->index), + .flags = cpu_to_le16(IONIC_QINIT_F_IRQ | + IONIC_QINIT_F_SG), + .intr_index = cpu_to_le16(lif->rxqcqs[q->index].qcq->intr.index), + .pid = cpu_to_le16(q->pid), + .ring_size = ilog2(q->num_descs), + .ring_base = cpu_to_le64(q->base_pa), + .cq_ring_base = cpu_to_le64(cq->base_pa), + .sg_ring_base = cpu_to_le64(q->sg_base_pa), + }, + }; + int err; + + dev_dbg(dev, "txq_init.pid %d\n", ctx.cmd.q_init.pid); + dev_dbg(dev, "txq_init.index %d\n", ctx.cmd.q_init.index); + dev_dbg(dev, "txq_init.ring_base 0x%llx\n", ctx.cmd.q_init.ring_base); + dev_dbg(dev, "txq_init.ring_size %d\n", ctx.cmd.q_init.ring_size); + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + q->hw_type = ctx.comp.q_init.hw_type; + q->hw_index = le32_to_cpu(ctx.comp.q_init.hw_index); + q->dbval = IONIC_DBELL_QID(q->hw_index); + + dev_dbg(dev, "txq->hw_type %d\n", q->hw_type); + dev_dbg(dev, "txq->hw_index %d\n", q->hw_index); + + qcq->flags |= IONIC_QCQ_F_INITED; + + ionic_debugfs_add_qcq(lif, qcq); + + return 0; +} + +static int ionic_lif_rxq_init(struct ionic_lif *lif, struct ionic_qcq *qcq) +{ + struct device *dev = lif->ionic->dev; + struct ionic_queue *q = &qcq->q; + struct ionic_cq *cq = &qcq->cq; + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.q_init = { + .opcode = IONIC_CMD_Q_INIT, + .lif_index = cpu_to_le16(lif->index), + .type = q->type, + .index = cpu_to_le32(q->index), + .flags = cpu_to_le16(IONIC_QINIT_F_IRQ), + .intr_index = cpu_to_le16(cq->bound_intr->index), + .pid = cpu_to_le16(q->pid), + .ring_size = ilog2(q->num_descs), + .ring_base = cpu_to_le64(q->base_pa), + .cq_ring_base = cpu_to_le64(cq->base_pa), + }, + }; + int err; + + dev_dbg(dev, "rxq_init.pid %d\n", ctx.cmd.q_init.pid); + dev_dbg(dev, "rxq_init.index %d\n", ctx.cmd.q_init.index); + dev_dbg(dev, "rxq_init.ring_base 0x%llx\n", ctx.cmd.q_init.ring_base); + dev_dbg(dev, "rxq_init.ring_size %d\n", ctx.cmd.q_init.ring_size); + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + q->hw_type = ctx.comp.q_init.hw_type; + q->hw_index = le32_to_cpu(ctx.comp.q_init.hw_index); + q->dbval = IONIC_DBELL_QID(q->hw_index); + + dev_dbg(dev, "rxq->hw_type %d\n", q->hw_type); + dev_dbg(dev, "rxq->hw_index %d\n", q->hw_index); + + netif_napi_add(lif->netdev, &qcq->napi, ionic_rx_napi, + NAPI_POLL_WEIGHT); + + err = ionic_request_irq(lif, qcq); + if (err) { + netif_napi_del(&qcq->napi); + return err; + } + + qcq->flags |= IONIC_QCQ_F_INITED; + + ionic_debugfs_add_qcq(lif, qcq); + + return 0; +} + +static bool ionic_notifyq_service(struct ionic_cq *cq, + struct ionic_cq_info *cq_info) +{ + union ionic_notifyq_comp *comp = cq_info->cq_desc; + struct net_device *netdev; + struct ionic_queue *q; + struct ionic_lif *lif; + u64 eid; + + q = cq->bound_q; + lif = q->info[0].cb_arg; + netdev = lif->netdev; + eid = le64_to_cpu(comp->event.eid); + + /* Have we run out of new completions to process? */ + if (eid <= lif->last_eid) + return false; + + lif->last_eid = eid; + + dev_dbg(lif->ionic->dev, "notifyq event:\n"); + dynamic_hex_dump("event ", DUMP_PREFIX_OFFSET, 16, 1, + comp, sizeof(*comp), true); + + switch (le16_to_cpu(comp->event.ecode)) { + case IONIC_EVENT_LINK_CHANGE: + ionic_link_status_check_request(lif); + break; + case IONIC_EVENT_RESET: + netdev_info(netdev, "Notifyq IONIC_EVENT_RESET eid=%lld\n", + eid); + netdev_info(netdev, " reset_code=%d state=%d\n", + comp->reset.reset_code, + comp->reset.state); + break; + default: + netdev_warn(netdev, "Notifyq unknown event ecode=%d eid=%lld\n", + comp->event.ecode, eid); + break; + } + + return true; +} + +static int ionic_notifyq_clean(struct ionic_lif *lif, int budget) +{ + struct ionic_dev *idev = &lif->ionic->idev; + struct ionic_cq *cq = &lif->notifyqcq->cq; + u32 work_done; + + work_done = ionic_cq_service(cq, budget, ionic_notifyq_service, + NULL, NULL); + if (work_done) + ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index, + work_done, IONIC_INTR_CRED_RESET_COALESCE); + + return work_done; +} + +static bool ionic_adminq_service(struct ionic_cq *cq, + struct ionic_cq_info *cq_info) +{ + struct ionic_admin_comp *comp = cq_info->cq_desc; + + if (!color_match(comp->color, cq->done_color)) + return false; + + ionic_q_service(cq->bound_q, cq_info, le16_to_cpu(comp->comp_index)); + + return true; +} + +static int ionic_adminq_napi(struct napi_struct *napi, int budget) +{ + struct ionic_lif *lif = napi_to_cq(napi)->lif; + int n_work = 0; + int a_work = 0; + + if (likely(lif->notifyqcq && lif->notifyqcq->flags & IONIC_QCQ_F_INITED)) + n_work = ionic_notifyq_clean(lif, budget); + a_work = ionic_napi(napi, budget, ionic_adminq_service, NULL, NULL); + + return max(n_work, a_work); +} + +static void ionic_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *ns) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_lif_stats *ls; + + memset(ns, 0, sizeof(*ns)); + ls = &lif->info->stats; + + ns->rx_packets = le64_to_cpu(ls->rx_ucast_packets) + + le64_to_cpu(ls->rx_mcast_packets) + + le64_to_cpu(ls->rx_bcast_packets); + + ns->tx_packets = le64_to_cpu(ls->tx_ucast_packets) + + le64_to_cpu(ls->tx_mcast_packets) + + le64_to_cpu(ls->tx_bcast_packets); + + ns->rx_bytes = le64_to_cpu(ls->rx_ucast_bytes) + + le64_to_cpu(ls->rx_mcast_bytes) + + le64_to_cpu(ls->rx_bcast_bytes); + + ns->tx_bytes = le64_to_cpu(ls->tx_ucast_bytes) + + le64_to_cpu(ls->tx_mcast_bytes) + + le64_to_cpu(ls->tx_bcast_bytes); + + ns->rx_dropped = le64_to_cpu(ls->rx_ucast_drop_packets) + + le64_to_cpu(ls->rx_mcast_drop_packets) + + le64_to_cpu(ls->rx_bcast_drop_packets); + + ns->tx_dropped = le64_to_cpu(ls->tx_ucast_drop_packets) + + le64_to_cpu(ls->tx_mcast_drop_packets) + + le64_to_cpu(ls->tx_bcast_drop_packets); + + ns->multicast = le64_to_cpu(ls->rx_mcast_packets); + + ns->rx_over_errors = le64_to_cpu(ls->rx_queue_empty); + + ns->rx_missed_errors = le64_to_cpu(ls->rx_dma_error) + + le64_to_cpu(ls->rx_queue_disabled) + + le64_to_cpu(ls->rx_desc_fetch_error) + + le64_to_cpu(ls->rx_desc_data_error); + + ns->tx_aborted_errors = le64_to_cpu(ls->tx_dma_error) + + le64_to_cpu(ls->tx_queue_disabled) + + le64_to_cpu(ls->tx_desc_fetch_error) + + le64_to_cpu(ls->tx_desc_data_error); + + ns->rx_errors = ns->rx_over_errors + + ns->rx_missed_errors; + + ns->tx_errors = ns->tx_aborted_errors; +} + +static int ionic_lif_addr_add(struct ionic_lif *lif, const u8 *addr) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_add = { + .opcode = IONIC_CMD_RX_FILTER_ADD, + .lif_index = cpu_to_le16(lif->index), + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_MAC), + }, + }; + struct ionic_rx_filter *f; + int err; + + /* don't bother if we already have it */ + spin_lock_bh(&lif->rx_filters.lock); + f = ionic_rx_filter_by_addr(lif, addr); + spin_unlock_bh(&lif->rx_filters.lock); + if (f) + return 0; + + netdev_dbg(lif->netdev, "rx_filter add ADDR %pM (id %d)\n", addr, + ctx.comp.rx_filter_add.filter_id); + + memcpy(ctx.cmd.rx_filter_add.mac.addr, addr, ETH_ALEN); + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + return ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx); +} + +static int ionic_lif_addr_del(struct ionic_lif *lif, const u8 *addr) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_del = { + .opcode = IONIC_CMD_RX_FILTER_DEL, + .lif_index = cpu_to_le16(lif->index), + }, + }; + struct ionic_rx_filter *f; + int err; + + spin_lock_bh(&lif->rx_filters.lock); + f = ionic_rx_filter_by_addr(lif, addr); + if (!f) { + spin_unlock_bh(&lif->rx_filters.lock); + return -ENOENT; + } + + ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); + ionic_rx_filter_free(lif, f); + spin_unlock_bh(&lif->rx_filters.lock); + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + netdev_dbg(lif->netdev, "rx_filter del ADDR %pM (id %d)\n", addr, + ctx.cmd.rx_filter_del.filter_id); + + return 0; +} + +static int ionic_lif_addr(struct ionic_lif *lif, const u8 *addr, bool add) +{ + struct ionic *ionic = lif->ionic; + struct ionic_deferred_work *work; + unsigned int nmfilters; + unsigned int nufilters; + + if (add) { + /* Do we have space for this filter? We test the counters + * here before checking the need for deferral so that we + * can return an overflow error to the stack. + */ + nmfilters = le32_to_cpu(ionic->ident.lif.eth.max_mcast_filters); + nufilters = le32_to_cpu(ionic->ident.lif.eth.max_ucast_filters); + + if ((is_multicast_ether_addr(addr) && lif->nmcast < nmfilters)) + lif->nmcast++; + else if (!is_multicast_ether_addr(addr) && + lif->nucast < nufilters) + lif->nucast++; + else + return -ENOSPC; + } else { + if (is_multicast_ether_addr(addr) && lif->nmcast) + lif->nmcast--; + else if (!is_multicast_ether_addr(addr) && lif->nucast) + lif->nucast--; + } + + if (in_interrupt()) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) { + netdev_err(lif->netdev, "%s OOM\n", __func__); + return -ENOMEM; + } + work->type = add ? IONIC_DW_TYPE_RX_ADDR_ADD : + IONIC_DW_TYPE_RX_ADDR_DEL; + memcpy(work->addr, addr, ETH_ALEN); + netdev_dbg(lif->netdev, "deferred: rx_filter %s %pM\n", + add ? "add" : "del", addr); + ionic_lif_deferred_enqueue(&lif->deferred, work); + } else { + netdev_dbg(lif->netdev, "rx_filter %s %pM\n", + add ? "add" : "del", addr); + if (add) + return ionic_lif_addr_add(lif, addr); + else + return ionic_lif_addr_del(lif, addr); + } + + return 0; +} + +static int ionic_addr_add(struct net_device *netdev, const u8 *addr) +{ + return ionic_lif_addr(netdev_priv(netdev), addr, true); +} + +static int ionic_addr_del(struct net_device *netdev, const u8 *addr) +{ + return ionic_lif_addr(netdev_priv(netdev), addr, false); +} + +static void ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_mode_set = { + .opcode = IONIC_CMD_RX_MODE_SET, + .lif_index = cpu_to_le16(lif->index), + .rx_mode = cpu_to_le16(rx_mode), + }, + }; + char buf[128]; + int err; + int i; +#define REMAIN(__x) (sizeof(buf) - (__x)) + + i = snprintf(buf, sizeof(buf), "rx_mode 0x%04x -> 0x%04x:", + lif->rx_mode, rx_mode); + if (rx_mode & IONIC_RX_MODE_F_UNICAST) + i += snprintf(&buf[i], REMAIN(i), " RX_MODE_F_UNICAST"); + if (rx_mode & IONIC_RX_MODE_F_MULTICAST) + i += snprintf(&buf[i], REMAIN(i), " RX_MODE_F_MULTICAST"); + if (rx_mode & IONIC_RX_MODE_F_BROADCAST) + i += snprintf(&buf[i], REMAIN(i), " RX_MODE_F_BROADCAST"); + if (rx_mode & IONIC_RX_MODE_F_PROMISC) + i += snprintf(&buf[i], REMAIN(i), " RX_MODE_F_PROMISC"); + if (rx_mode & IONIC_RX_MODE_F_ALLMULTI) + i += snprintf(&buf[i], REMAIN(i), " RX_MODE_F_ALLMULTI"); + netdev_dbg(lif->netdev, "lif%d %s\n", lif->index, buf); + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + netdev_warn(lif->netdev, "set rx_mode 0x%04x failed: %d\n", + rx_mode, err); + else + lif->rx_mode = rx_mode; +} + +static void _ionic_lif_rx_mode(struct ionic_lif *lif, unsigned int rx_mode) +{ + struct ionic_deferred_work *work; + + if (in_interrupt()) { + work = kzalloc(sizeof(*work), GFP_ATOMIC); + if (!work) { + netdev_err(lif->netdev, "%s OOM\n", __func__); + return; + } + work->type = IONIC_DW_TYPE_RX_MODE; + work->rx_mode = rx_mode; + netdev_dbg(lif->netdev, "deferred: rx_mode\n"); + ionic_lif_deferred_enqueue(&lif->deferred, work); + } else { + ionic_lif_rx_mode(lif, rx_mode); + } +} + +static void ionic_set_rx_mode(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_identity *ident; + unsigned int nfilters; + unsigned int rx_mode; + + ident = &lif->ionic->ident; + + rx_mode = IONIC_RX_MODE_F_UNICAST; + rx_mode |= (netdev->flags & IFF_MULTICAST) ? IONIC_RX_MODE_F_MULTICAST : 0; + rx_mode |= (netdev->flags & IFF_BROADCAST) ? IONIC_RX_MODE_F_BROADCAST : 0; + rx_mode |= (netdev->flags & IFF_PROMISC) ? IONIC_RX_MODE_F_PROMISC : 0; + rx_mode |= (netdev->flags & IFF_ALLMULTI) ? IONIC_RX_MODE_F_ALLMULTI : 0; + + /* sync unicast addresses + * next check to see if we're in an overflow state + * if so, we track that we overflowed and enable NIC PROMISC + * else if the overflow is set and not needed + * we remove our overflow flag and check the netdev flags + * to see if we can disable NIC PROMISC + */ + __dev_uc_sync(netdev, ionic_addr_add, ionic_addr_del); + nfilters = le32_to_cpu(ident->lif.eth.max_ucast_filters); + if (netdev_uc_count(netdev) + 1 > nfilters) { + rx_mode |= IONIC_RX_MODE_F_PROMISC; + lif->uc_overflow = true; + } else if (lif->uc_overflow) { + lif->uc_overflow = false; + if (!(netdev->flags & IFF_PROMISC)) + rx_mode &= ~IONIC_RX_MODE_F_PROMISC; + } + + /* same for multicast */ + __dev_mc_sync(netdev, ionic_addr_add, ionic_addr_del); + nfilters = le32_to_cpu(ident->lif.eth.max_mcast_filters); + if (netdev_mc_count(netdev) > nfilters) { + rx_mode |= IONIC_RX_MODE_F_ALLMULTI; + lif->mc_overflow = true; + } else if (lif->mc_overflow) { + lif->mc_overflow = false; + if (!(netdev->flags & IFF_ALLMULTI)) + rx_mode &= ~IONIC_RX_MODE_F_ALLMULTI; + } + + if (lif->rx_mode != rx_mode) + _ionic_lif_rx_mode(lif, rx_mode); +} + +static __le64 ionic_netdev_features_to_nic(netdev_features_t features) +{ + u64 wanted = 0; + + if (features & NETIF_F_HW_VLAN_CTAG_TX) + wanted |= IONIC_ETH_HW_VLAN_TX_TAG; + if (features & NETIF_F_HW_VLAN_CTAG_RX) + wanted |= IONIC_ETH_HW_VLAN_RX_STRIP; + if (features & NETIF_F_HW_VLAN_CTAG_FILTER) + wanted |= IONIC_ETH_HW_VLAN_RX_FILTER; + if (features & NETIF_F_RXHASH) + wanted |= IONIC_ETH_HW_RX_HASH; + if (features & NETIF_F_RXCSUM) + wanted |= IONIC_ETH_HW_RX_CSUM; + if (features & NETIF_F_SG) + wanted |= IONIC_ETH_HW_TX_SG; + if (features & NETIF_F_HW_CSUM) + wanted |= IONIC_ETH_HW_TX_CSUM; + if (features & NETIF_F_TSO) + wanted |= IONIC_ETH_HW_TSO; + if (features & NETIF_F_TSO6) + wanted |= IONIC_ETH_HW_TSO_IPV6; + if (features & NETIF_F_TSO_ECN) + wanted |= IONIC_ETH_HW_TSO_ECN; + if (features & NETIF_F_GSO_GRE) + wanted |= IONIC_ETH_HW_TSO_GRE; + if (features & NETIF_F_GSO_GRE_CSUM) + wanted |= IONIC_ETH_HW_TSO_GRE_CSUM; + if (features & NETIF_F_GSO_IPXIP4) + wanted |= IONIC_ETH_HW_TSO_IPXIP4; + if (features & NETIF_F_GSO_IPXIP6) + wanted |= IONIC_ETH_HW_TSO_IPXIP6; + if (features & NETIF_F_GSO_UDP_TUNNEL) + wanted |= IONIC_ETH_HW_TSO_UDP; + if (features & NETIF_F_GSO_UDP_TUNNEL_CSUM) + wanted |= IONIC_ETH_HW_TSO_UDP_CSUM; + + return cpu_to_le64(wanted); +} + +static int ionic_set_nic_features(struct ionic_lif *lif, + netdev_features_t features) +{ + struct device *dev = lif->ionic->dev; + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_setattr = { + .opcode = IONIC_CMD_LIF_SETATTR, + .index = cpu_to_le16(lif->index), + .attr = IONIC_LIF_ATTR_FEATURES, + }, + }; + u64 vlan_flags = IONIC_ETH_HW_VLAN_TX_TAG | + IONIC_ETH_HW_VLAN_RX_STRIP | + IONIC_ETH_HW_VLAN_RX_FILTER; + int err; + + ctx.cmd.lif_setattr.features = ionic_netdev_features_to_nic(features); + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + lif->hw_features = le64_to_cpu(ctx.cmd.lif_setattr.features & + ctx.comp.lif_setattr.features); + + if ((vlan_flags & features) && + !(vlan_flags & le64_to_cpu(ctx.comp.lif_setattr.features))) + dev_info_once(lif->ionic->dev, "NIC is not supporting vlan offload, likely in SmartNIC mode\n"); + + if (lif->hw_features & IONIC_ETH_HW_VLAN_TX_TAG) + dev_dbg(dev, "feature ETH_HW_VLAN_TX_TAG\n"); + if (lif->hw_features & IONIC_ETH_HW_VLAN_RX_STRIP) + dev_dbg(dev, "feature ETH_HW_VLAN_RX_STRIP\n"); + if (lif->hw_features & IONIC_ETH_HW_VLAN_RX_FILTER) + dev_dbg(dev, "feature ETH_HW_VLAN_RX_FILTER\n"); + if (lif->hw_features & IONIC_ETH_HW_RX_HASH) + dev_dbg(dev, "feature ETH_HW_RX_HASH\n"); + if (lif->hw_features & IONIC_ETH_HW_TX_SG) + dev_dbg(dev, "feature ETH_HW_TX_SG\n"); + if (lif->hw_features & IONIC_ETH_HW_TX_CSUM) + dev_dbg(dev, "feature ETH_HW_TX_CSUM\n"); + if (lif->hw_features & IONIC_ETH_HW_RX_CSUM) + dev_dbg(dev, "feature ETH_HW_RX_CSUM\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO) + dev_dbg(dev, "feature ETH_HW_TSO\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_IPV6) + dev_dbg(dev, "feature ETH_HW_TSO_IPV6\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_ECN) + dev_dbg(dev, "feature ETH_HW_TSO_ECN\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_GRE) + dev_dbg(dev, "feature ETH_HW_TSO_GRE\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_GRE_CSUM) + dev_dbg(dev, "feature ETH_HW_TSO_GRE_CSUM\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_IPXIP4) + dev_dbg(dev, "feature ETH_HW_TSO_IPXIP4\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_IPXIP6) + dev_dbg(dev, "feature ETH_HW_TSO_IPXIP6\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_UDP) + dev_dbg(dev, "feature ETH_HW_TSO_UDP\n"); + if (lif->hw_features & IONIC_ETH_HW_TSO_UDP_CSUM) + dev_dbg(dev, "feature ETH_HW_TSO_UDP_CSUM\n"); + + return 0; +} + +static int ionic_init_nic_features(struct ionic_lif *lif) +{ + struct net_device *netdev = lif->netdev; + netdev_features_t features; + int err; + + /* set up what we expect to support by default */ + features = NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX | + NETIF_F_HW_VLAN_CTAG_FILTER | + NETIF_F_RXHASH | + NETIF_F_SG | + NETIF_F_HW_CSUM | + NETIF_F_RXCSUM | + NETIF_F_TSO | + NETIF_F_TSO6 | + NETIF_F_TSO_ECN; + + err = ionic_set_nic_features(lif, features); + if (err) + return err; + + /* tell the netdev what we actually can support */ + netdev->features |= NETIF_F_HIGHDMA; + + if (lif->hw_features & IONIC_ETH_HW_VLAN_TX_TAG) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_TX; + if (lif->hw_features & IONIC_ETH_HW_VLAN_RX_STRIP) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_RX; + if (lif->hw_features & IONIC_ETH_HW_VLAN_RX_FILTER) + netdev->hw_features |= NETIF_F_HW_VLAN_CTAG_FILTER; + if (lif->hw_features & IONIC_ETH_HW_RX_HASH) + netdev->hw_features |= NETIF_F_RXHASH; + if (lif->hw_features & IONIC_ETH_HW_TX_SG) + netdev->hw_features |= NETIF_F_SG; + + if (lif->hw_features & IONIC_ETH_HW_TX_CSUM) + netdev->hw_enc_features |= NETIF_F_HW_CSUM; + if (lif->hw_features & IONIC_ETH_HW_RX_CSUM) + netdev->hw_enc_features |= NETIF_F_RXCSUM; + if (lif->hw_features & IONIC_ETH_HW_TSO) + netdev->hw_enc_features |= NETIF_F_TSO; + if (lif->hw_features & IONIC_ETH_HW_TSO_IPV6) + netdev->hw_enc_features |= NETIF_F_TSO6; + if (lif->hw_features & IONIC_ETH_HW_TSO_ECN) + netdev->hw_enc_features |= NETIF_F_TSO_ECN; + if (lif->hw_features & IONIC_ETH_HW_TSO_GRE) + netdev->hw_enc_features |= NETIF_F_GSO_GRE; + if (lif->hw_features & IONIC_ETH_HW_TSO_GRE_CSUM) + netdev->hw_enc_features |= NETIF_F_GSO_GRE_CSUM; + if (lif->hw_features & IONIC_ETH_HW_TSO_IPXIP4) + netdev->hw_enc_features |= NETIF_F_GSO_IPXIP4; + if (lif->hw_features & IONIC_ETH_HW_TSO_IPXIP6) + netdev->hw_enc_features |= NETIF_F_GSO_IPXIP6; + if (lif->hw_features & IONIC_ETH_HW_TSO_UDP) + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL; + if (lif->hw_features & IONIC_ETH_HW_TSO_UDP_CSUM) + netdev->hw_enc_features |= NETIF_F_GSO_UDP_TUNNEL_CSUM; + + netdev->hw_features |= netdev->hw_enc_features; + netdev->features |= netdev->hw_features; + + netdev->priv_flags |= IFF_UNICAST_FLT; + + return 0; +} + +static int ionic_set_features(struct net_device *netdev, + netdev_features_t features) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int err; + + netdev_dbg(netdev, "%s: lif->features=0x%08llx new_features=0x%08llx\n", + __func__, (u64)lif->netdev->features, (u64)features); + + err = ionic_set_nic_features(lif, features); + + return err; +} + +static int ionic_set_mac_address(struct net_device *netdev, void *sa) +{ + struct sockaddr *addr = sa; + u8 *mac; + int err; + + mac = (u8 *)addr->sa_data; + if (ether_addr_equal(netdev->dev_addr, mac)) + return 0; + + err = eth_prepare_mac_addr_change(netdev, addr); + if (err) + return err; + + if (!is_zero_ether_addr(netdev->dev_addr)) { + netdev_info(netdev, "deleting mac addr %pM\n", + netdev->dev_addr); + ionic_addr_del(netdev, netdev->dev_addr); + } + + eth_commit_mac_addr_change(netdev, addr); + netdev_info(netdev, "updating mac addr %pM\n", mac); + + return ionic_addr_add(netdev, mac); +} + +static int ionic_change_mtu(struct net_device *netdev, int new_mtu) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_setattr = { + .opcode = IONIC_CMD_LIF_SETATTR, + .index = cpu_to_le16(lif->index), + .attr = IONIC_LIF_ATTR_MTU, + .mtu = cpu_to_le32(new_mtu), + }, + }; + int err; + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + netdev->mtu = new_mtu; + err = ionic_reset_queues(lif); + + return err; +} + +static void ionic_tx_timeout_work(struct work_struct *ws) +{ + struct ionic_lif *lif = container_of(ws, struct ionic_lif, tx_timeout_work); + + netdev_info(lif->netdev, "Tx Timeout recovery\n"); + + rtnl_lock(); + ionic_reset_queues(lif); + rtnl_unlock(); +} + +static void ionic_tx_timeout(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + + schedule_work(&lif->tx_timeout_work); +} + +static int ionic_vlan_rx_add_vid(struct net_device *netdev, __be16 proto, + u16 vid) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_add = { + .opcode = IONIC_CMD_RX_FILTER_ADD, + .lif_index = cpu_to_le16(lif->index), + .match = cpu_to_le16(IONIC_RX_FILTER_MATCH_VLAN), + .vlan.vlan = cpu_to_le16(vid), + }, + }; + int err; + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + netdev_dbg(netdev, "rx_filter add VLAN %d (id %d)\n", vid, + ctx.comp.rx_filter_add.filter_id); + + return ionic_rx_filter_save(lif, 0, IONIC_RXQ_INDEX_ANY, 0, &ctx); +} + +static int ionic_vlan_rx_kill_vid(struct net_device *netdev, __be16 proto, + u16 vid) +{ + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_del = { + .opcode = IONIC_CMD_RX_FILTER_DEL, + .lif_index = cpu_to_le16(lif->index), + }, + }; + struct ionic_rx_filter *f; + + spin_lock_bh(&lif->rx_filters.lock); + + f = ionic_rx_filter_by_vlan(lif, vid); + if (!f) { + spin_unlock_bh(&lif->rx_filters.lock); + return -ENOENT; + } + + netdev_dbg(netdev, "rx_filter del VLAN %d (id %d)\n", vid, + le32_to_cpu(ctx.cmd.rx_filter_del.filter_id)); + + ctx.cmd.rx_filter_del.filter_id = cpu_to_le32(f->filter_id); + ionic_rx_filter_free(lif, f); + spin_unlock_bh(&lif->rx_filters.lock); + + return ionic_adminq_post_wait(lif, &ctx); +} + +int ionic_lif_rss_config(struct ionic_lif *lif, const u16 types, + const u8 *key, const u32 *indir) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_setattr = { + .opcode = IONIC_CMD_LIF_SETATTR, + .attr = IONIC_LIF_ATTR_RSS, + .rss.types = cpu_to_le16(types), + .rss.addr = cpu_to_le64(lif->rss_ind_tbl_pa), + }, + }; + unsigned int i, tbl_sz; + + lif->rss_types = types; + + if (key) + memcpy(lif->rss_hash_key, key, IONIC_RSS_HASH_KEY_SIZE); + + if (indir) { + tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); + for (i = 0; i < tbl_sz; i++) + lif->rss_ind_tbl[i] = indir[i]; + } + + memcpy(ctx.cmd.lif_setattr.rss.key, lif->rss_hash_key, + IONIC_RSS_HASH_KEY_SIZE); + + return ionic_adminq_post_wait(lif, &ctx); +} + +static int ionic_lif_rss_init(struct ionic_lif *lif) +{ + u8 rss_key[IONIC_RSS_HASH_KEY_SIZE]; + unsigned int tbl_sz; + unsigned int i; + + netdev_rss_key_fill(rss_key, IONIC_RSS_HASH_KEY_SIZE); + + lif->rss_types = IONIC_RSS_TYPE_IPV4 | + IONIC_RSS_TYPE_IPV4_TCP | + IONIC_RSS_TYPE_IPV4_UDP | + IONIC_RSS_TYPE_IPV6 | + IONIC_RSS_TYPE_IPV6_TCP | + IONIC_RSS_TYPE_IPV6_UDP; + + /* Fill indirection table with 'default' values */ + tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); + for (i = 0; i < tbl_sz; i++) + lif->rss_ind_tbl[i] = ethtool_rxfh_indir_default(i, lif->nxqs); + + return ionic_lif_rss_config(lif, lif->rss_types, rss_key, NULL); +} + +static int ionic_lif_rss_deinit(struct ionic_lif *lif) +{ + return ionic_lif_rss_config(lif, 0x0, NULL, NULL); +} + +static void ionic_txrx_disable(struct ionic_lif *lif) +{ + unsigned int i; + + for (i = 0; i < lif->nxqs; i++) { + ionic_qcq_disable(lif->txqcqs[i].qcq); + ionic_qcq_disable(lif->rxqcqs[i].qcq); + } +} + +static void ionic_txrx_deinit(struct ionic_lif *lif) +{ + unsigned int i; + + for (i = 0; i < lif->nxqs; i++) { + ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); + ionic_tx_flush(&lif->txqcqs[i].qcq->cq); + + ionic_lif_qcq_deinit(lif, lif->rxqcqs[i].qcq); + ionic_rx_flush(&lif->rxqcqs[i].qcq->cq); + ionic_rx_empty(&lif->rxqcqs[i].qcq->q); + } +} + +static void ionic_txrx_free(struct ionic_lif *lif) +{ + unsigned int i; + + for (i = 0; i < lif->nxqs; i++) { + ionic_qcq_free(lif, lif->txqcqs[i].qcq); + lif->txqcqs[i].qcq = NULL; + + ionic_qcq_free(lif, lif->rxqcqs[i].qcq); + lif->rxqcqs[i].qcq = NULL; + } +} + +static int ionic_txrx_alloc(struct ionic_lif *lif) +{ + unsigned int flags; + unsigned int i; + int err = 0; + u32 coal; + + flags = IONIC_QCQ_F_TX_STATS | IONIC_QCQ_F_SG; + for (i = 0; i < lif->nxqs; i++) { + err = ionic_qcq_alloc(lif, IONIC_QTYPE_TXQ, i, "tx", flags, + lif->ntxq_descs, + sizeof(struct ionic_txq_desc), + sizeof(struct ionic_txq_comp), + sizeof(struct ionic_txq_sg_desc), + lif->kern_pid, &lif->txqcqs[i].qcq); + if (err) + goto err_out; + + lif->txqcqs[i].qcq->stats = lif->txqcqs[i].stats; + } + + flags = IONIC_QCQ_F_RX_STATS | IONIC_QCQ_F_INTR; + coal = ionic_coal_usec_to_hw(lif->ionic, lif->rx_coalesce_usecs); + for (i = 0; i < lif->nxqs; i++) { + err = ionic_qcq_alloc(lif, IONIC_QTYPE_RXQ, i, "rx", flags, + lif->nrxq_descs, + sizeof(struct ionic_rxq_desc), + sizeof(struct ionic_rxq_comp), + 0, lif->kern_pid, &lif->rxqcqs[i].qcq); + if (err) + goto err_out; + + lif->rxqcqs[i].qcq->stats = lif->rxqcqs[i].stats; + + ionic_intr_coal_init(lif->ionic->idev.intr_ctrl, + lif->rxqcqs[i].qcq->intr.index, coal); + ionic_link_qcq_interrupts(lif->rxqcqs[i].qcq, + lif->txqcqs[i].qcq); + } + + return 0; + +err_out: + ionic_txrx_free(lif); + + return err; +} + +static int ionic_txrx_init(struct ionic_lif *lif) +{ + unsigned int i; + int err; + + for (i = 0; i < lif->nxqs; i++) { + err = ionic_lif_txq_init(lif, lif->txqcqs[i].qcq); + if (err) + goto err_out; + + err = ionic_lif_rxq_init(lif, lif->rxqcqs[i].qcq); + if (err) { + ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); + goto err_out; + } + } + + if (lif->netdev->features & NETIF_F_RXHASH) + ionic_lif_rss_init(lif); + + ionic_set_rx_mode(lif->netdev); + + return 0; + +err_out: + while (i--) { + ionic_lif_qcq_deinit(lif, lif->txqcqs[i].qcq); + ionic_lif_qcq_deinit(lif, lif->rxqcqs[i].qcq); + } + + return err; +} + +static int ionic_txrx_enable(struct ionic_lif *lif) +{ + int i, err; + + for (i = 0; i < lif->nxqs; i++) { + err = ionic_qcq_enable(lif->txqcqs[i].qcq); + if (err) + goto err_out; + + ionic_rx_fill(&lif->rxqcqs[i].qcq->q); + err = ionic_qcq_enable(lif->rxqcqs[i].qcq); + if (err) { + ionic_qcq_disable(lif->txqcqs[i].qcq); + goto err_out; + } + } + + return 0; + +err_out: + while (i--) { + ionic_qcq_disable(lif->rxqcqs[i].qcq); + ionic_qcq_disable(lif->txqcqs[i].qcq); + } + + return err; +} + +int ionic_open(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int err; + + netif_carrier_off(netdev); + + err = ionic_txrx_alloc(lif); + if (err) + return err; + + err = ionic_txrx_init(lif); + if (err) + goto err_txrx_free; + + err = ionic_txrx_enable(lif); + if (err) + goto err_txrx_deinit; + + netif_set_real_num_tx_queues(netdev, lif->nxqs); + netif_set_real_num_rx_queues(netdev, lif->nxqs); + + set_bit(IONIC_LIF_UP, lif->state); + + ionic_link_status_check_request(lif); + if (netif_carrier_ok(netdev)) + netif_tx_wake_all_queues(netdev); + + return 0; + +err_txrx_deinit: + ionic_txrx_deinit(lif); +err_txrx_free: + ionic_txrx_free(lif); + return err; +} + +int ionic_stop(struct net_device *netdev) +{ + struct ionic_lif *lif = netdev_priv(netdev); + int err = 0; + + if (!test_bit(IONIC_LIF_UP, lif->state)) { + dev_dbg(lif->ionic->dev, "%s: %s state=DOWN\n", + __func__, lif->name); + return 0; + } + dev_dbg(lif->ionic->dev, "%s: %s state=UP\n", __func__, lif->name); + clear_bit(IONIC_LIF_UP, lif->state); + + /* carrier off before disabling queues to avoid watchdog timeout */ + netif_carrier_off(netdev); + netif_tx_stop_all_queues(netdev); + netif_tx_disable(netdev); + + ionic_txrx_disable(lif); + ionic_txrx_deinit(lif); + ionic_txrx_free(lif); + + return err; +} + +static const struct net_device_ops ionic_netdev_ops = { + .ndo_open = ionic_open, + .ndo_stop = ionic_stop, + .ndo_start_xmit = ionic_start_xmit, + .ndo_get_stats64 = ionic_get_stats64, + .ndo_set_rx_mode = ionic_set_rx_mode, + .ndo_set_features = ionic_set_features, + .ndo_set_mac_address = ionic_set_mac_address, + .ndo_validate_addr = eth_validate_addr, + .ndo_tx_timeout = ionic_tx_timeout, + .ndo_change_mtu = ionic_change_mtu, + .ndo_vlan_rx_add_vid = ionic_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = ionic_vlan_rx_kill_vid, +}; + +int ionic_reset_queues(struct ionic_lif *lif) +{ + bool running; + int err = 0; + + /* Put off the next watchdog timeout */ + netif_trans_update(lif->netdev); + + if (!ionic_wait_for_bit(lif, IONIC_LIF_QUEUE_RESET)) + return -EBUSY; + + running = netif_running(lif->netdev); + if (running) + err = ionic_stop(lif->netdev); + if (!err && running) + ionic_open(lif->netdev); + + clear_bit(IONIC_LIF_QUEUE_RESET, lif->state); + + return err; +} + +static struct ionic_lif *ionic_lif_alloc(struct ionic *ionic, unsigned int index) +{ + struct device *dev = ionic->dev; + struct net_device *netdev; + struct ionic_lif *lif; + int tbl_sz; + u32 coal; + int err; + + netdev = alloc_etherdev_mqs(sizeof(*lif), + ionic->ntxqs_per_lif, ionic->ntxqs_per_lif); + if (!netdev) { + dev_err(dev, "Cannot allocate netdev, aborting\n"); + return ERR_PTR(-ENOMEM); + } + + SET_NETDEV_DEV(netdev, dev); + + lif = netdev_priv(netdev); + lif->netdev = netdev; + ionic->master_lif = lif; + netdev->netdev_ops = &ionic_netdev_ops; + ionic_ethtool_set_ops(netdev); + + netdev->watchdog_timeo = 2 * HZ; + netdev->min_mtu = IONIC_MIN_MTU; + netdev->max_mtu = IONIC_MAX_MTU; + + lif->neqs = ionic->neqs_per_lif; + lif->nxqs = ionic->ntxqs_per_lif; + + lif->ionic = ionic; + lif->index = index; + lif->ntxq_descs = IONIC_DEF_TXRX_DESC; + lif->nrxq_descs = IONIC_DEF_TXRX_DESC; + + /* Convert the default coalesce value to actual hw resolution */ + coal = ionic_coal_usec_to_hw(lif->ionic, IONIC_ITR_COAL_USEC_DEFAULT); + lif->rx_coalesce_usecs = ionic_coal_hw_to_usec(lif->ionic, coal); + + snprintf(lif->name, sizeof(lif->name), "lif%u", index); + + spin_lock_init(&lif->adminq_lock); + + spin_lock_init(&lif->deferred.lock); + INIT_LIST_HEAD(&lif->deferred.list); + INIT_WORK(&lif->deferred.work, ionic_lif_deferred_work); + + /* allocate lif info */ + lif->info_sz = ALIGN(sizeof(*lif->info), PAGE_SIZE); + lif->info = dma_alloc_coherent(dev, lif->info_sz, + &lif->info_pa, GFP_KERNEL); + if (!lif->info) { + dev_err(dev, "Failed to allocate lif info, aborting\n"); + err = -ENOMEM; + goto err_out_free_netdev; + } + + /* allocate queues */ + err = ionic_qcqs_alloc(lif); + if (err) + goto err_out_free_lif_info; + + /* allocate rss indirection table */ + tbl_sz = le16_to_cpu(lif->ionic->ident.lif.eth.rss_ind_tbl_sz); + lif->rss_ind_tbl_sz = sizeof(*lif->rss_ind_tbl) * tbl_sz; + lif->rss_ind_tbl = dma_alloc_coherent(dev, lif->rss_ind_tbl_sz, + &lif->rss_ind_tbl_pa, + GFP_KERNEL); + + if (!lif->rss_ind_tbl) { + dev_err(dev, "Failed to allocate rss indirection table, aborting\n"); + goto err_out_free_qcqs; + } + + list_add_tail(&lif->list, &ionic->lifs); + + return lif; + +err_out_free_qcqs: + ionic_qcqs_free(lif); +err_out_free_lif_info: + dma_free_coherent(dev, lif->info_sz, lif->info, lif->info_pa); + lif->info = NULL; + lif->info_pa = 0; +err_out_free_netdev: + free_netdev(lif->netdev); + lif = NULL; + + return ERR_PTR(err); +} + +int ionic_lifs_alloc(struct ionic *ionic) +{ + struct ionic_lif *lif; + + INIT_LIST_HEAD(&ionic->lifs); + + /* only build the first lif, others are for later features */ + set_bit(0, ionic->lifbits); + lif = ionic_lif_alloc(ionic, 0); + + return PTR_ERR_OR_ZERO(lif); +} + +static void ionic_lif_reset(struct ionic_lif *lif) +{ + struct ionic_dev *idev = &lif->ionic->idev; + + mutex_lock(&lif->ionic->dev_cmd_lock); + ionic_dev_cmd_lif_reset(idev, lif->index); + ionic_dev_cmd_wait(lif->ionic, DEVCMD_TIMEOUT); + mutex_unlock(&lif->ionic->dev_cmd_lock); +} + +static void ionic_lif_free(struct ionic_lif *lif) +{ + struct device *dev = lif->ionic->dev; + + /* free rss indirection table */ + dma_free_coherent(dev, lif->rss_ind_tbl_sz, lif->rss_ind_tbl, + lif->rss_ind_tbl_pa); + lif->rss_ind_tbl = NULL; + lif->rss_ind_tbl_pa = 0; + + /* free queues */ + ionic_qcqs_free(lif); + ionic_lif_reset(lif); + + /* free lif info */ + dma_free_coherent(dev, lif->info_sz, lif->info, lif->info_pa); + lif->info = NULL; + lif->info_pa = 0; + + /* unmap doorbell page */ + ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage); + lif->kern_dbpage = NULL; + kfree(lif->dbid_inuse); + lif->dbid_inuse = NULL; + + /* free netdev & lif */ + ionic_debugfs_del_lif(lif); + list_del(&lif->list); + free_netdev(lif->netdev); +} + +void ionic_lifs_free(struct ionic *ionic) +{ + struct list_head *cur, *tmp; + struct ionic_lif *lif; + + list_for_each_safe(cur, tmp, &ionic->lifs) { + lif = list_entry(cur, struct ionic_lif, list); + + ionic_lif_free(lif); + } +} + +static void ionic_lif_deinit(struct ionic_lif *lif) +{ + if (!test_bit(IONIC_LIF_INITED, lif->state)) + return; + + clear_bit(IONIC_LIF_INITED, lif->state); + + ionic_rx_filters_deinit(lif); + ionic_lif_rss_deinit(lif); + + napi_disable(&lif->adminqcq->napi); + ionic_lif_qcq_deinit(lif, lif->notifyqcq); + ionic_lif_qcq_deinit(lif, lif->adminqcq); + + ionic_lif_reset(lif); +} + +void ionic_lifs_deinit(struct ionic *ionic) +{ + struct list_head *cur, *tmp; + struct ionic_lif *lif; + + list_for_each_safe(cur, tmp, &ionic->lifs) { + lif = list_entry(cur, struct ionic_lif, list); + ionic_lif_deinit(lif); + } +} + +static int ionic_lif_adminq_init(struct ionic_lif *lif) +{ + struct device *dev = lif->ionic->dev; + struct ionic_q_init_comp comp; + struct ionic_dev *idev; + struct ionic_qcq *qcq; + struct ionic_queue *q; + int err; + + idev = &lif->ionic->idev; + qcq = lif->adminqcq; + q = &qcq->q; + + mutex_lock(&lif->ionic->dev_cmd_lock); + ionic_dev_cmd_adminq_init(idev, qcq, lif->index, qcq->intr.index); + err = ionic_dev_cmd_wait(lif->ionic, DEVCMD_TIMEOUT); + ionic_dev_cmd_comp(idev, (union ionic_dev_cmd_comp *)&comp); + mutex_unlock(&lif->ionic->dev_cmd_lock); + if (err) { + netdev_err(lif->netdev, "adminq init failed %d\n", err); + return err; + } + + q->hw_type = comp.hw_type; + q->hw_index = le32_to_cpu(comp.hw_index); + q->dbval = IONIC_DBELL_QID(q->hw_index); + + dev_dbg(dev, "adminq->hw_type %d\n", q->hw_type); + dev_dbg(dev, "adminq->hw_index %d\n", q->hw_index); + + netif_napi_add(lif->netdev, &qcq->napi, ionic_adminq_napi, + NAPI_POLL_WEIGHT); + + err = ionic_request_irq(lif, qcq); + if (err) { + netdev_warn(lif->netdev, "adminq irq request failed %d\n", err); + netif_napi_del(&qcq->napi); + return err; + } + + napi_enable(&qcq->napi); + + if (qcq->flags & IONIC_QCQ_F_INTR) + ionic_intr_mask(idev->intr_ctrl, qcq->intr.index, + IONIC_INTR_MASK_CLEAR); + + qcq->flags |= IONIC_QCQ_F_INITED; + + ionic_debugfs_add_qcq(lif, qcq); + + return 0; +} + +static int ionic_lif_notifyq_init(struct ionic_lif *lif) +{ + struct ionic_qcq *qcq = lif->notifyqcq; + struct device *dev = lif->ionic->dev; + struct ionic_queue *q = &qcq->q; + int err; + + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.q_init = { + .opcode = IONIC_CMD_Q_INIT, + .lif_index = cpu_to_le16(lif->index), + .type = q->type, + .index = cpu_to_le32(q->index), + .flags = cpu_to_le16(IONIC_QINIT_F_IRQ | + IONIC_QINIT_F_ENA), + .intr_index = cpu_to_le16(lif->adminqcq->intr.index), + .pid = cpu_to_le16(q->pid), + .ring_size = ilog2(q->num_descs), + .ring_base = cpu_to_le64(q->base_pa), + } + }; + + dev_dbg(dev, "notifyq_init.pid %d\n", ctx.cmd.q_init.pid); + dev_dbg(dev, "notifyq_init.index %d\n", ctx.cmd.q_init.index); + dev_dbg(dev, "notifyq_init.ring_base 0x%llx\n", ctx.cmd.q_init.ring_base); + dev_dbg(dev, "notifyq_init.ring_size %d\n", ctx.cmd.q_init.ring_size); + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + q->hw_type = ctx.comp.q_init.hw_type; + q->hw_index = le32_to_cpu(ctx.comp.q_init.hw_index); + q->dbval = IONIC_DBELL_QID(q->hw_index); + + dev_dbg(dev, "notifyq->hw_type %d\n", q->hw_type); + dev_dbg(dev, "notifyq->hw_index %d\n", q->hw_index); + + /* preset the callback info */ + q->info[0].cb_arg = lif; + + qcq->flags |= IONIC_QCQ_F_INITED; + + ionic_debugfs_add_qcq(lif, qcq); + + return 0; +} + +static int ionic_station_set(struct ionic_lif *lif) +{ + struct net_device *netdev = lif->netdev; + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_getattr = { + .opcode = IONIC_CMD_LIF_GETATTR, + .index = cpu_to_le16(lif->index), + .attr = IONIC_LIF_ATTR_MAC, + }, + }; + struct sockaddr addr; + int err; + + err = ionic_adminq_post_wait(lif, &ctx); + if (err) + return err; + + memcpy(addr.sa_data, ctx.comp.lif_getattr.mac, netdev->addr_len); + addr.sa_family = AF_INET; + err = eth_prepare_mac_addr_change(netdev, &addr); + if (err) + return err; + + if (!is_zero_ether_addr(netdev->dev_addr)) { + netdev_dbg(lif->netdev, "deleting station MAC addr %pM\n", + netdev->dev_addr); + ionic_lif_addr(lif, netdev->dev_addr, false); + } + + eth_commit_mac_addr_change(netdev, &addr); + netdev_dbg(lif->netdev, "adding station MAC addr %pM\n", + netdev->dev_addr); + ionic_lif_addr(lif, netdev->dev_addr, true); + + return 0; +} + +static int ionic_lif_init(struct ionic_lif *lif) +{ + struct ionic_dev *idev = &lif->ionic->idev; + struct device *dev = lif->ionic->dev; + struct ionic_lif_init_comp comp; + int dbpage_num; + int err; + + ionic_debugfs_add_lif(lif); + + mutex_lock(&lif->ionic->dev_cmd_lock); + ionic_dev_cmd_lif_init(idev, lif->index, lif->info_pa); + err = ionic_dev_cmd_wait(lif->ionic, DEVCMD_TIMEOUT); + ionic_dev_cmd_comp(idev, (union ionic_dev_cmd_comp *)&comp); + mutex_unlock(&lif->ionic->dev_cmd_lock); + if (err) + return err; + + lif->hw_index = le16_to_cpu(comp.hw_index); + + /* now that we have the hw_index we can figure out our doorbell page */ + lif->dbid_count = le32_to_cpu(lif->ionic->ident.dev.ndbpgs_per_lif); + if (!lif->dbid_count) { + dev_err(dev, "No doorbell pages, aborting\n"); + return -EINVAL; + } + + lif->dbid_inuse = bitmap_alloc(lif->dbid_count, GFP_KERNEL); + if (!lif->dbid_inuse) { + dev_err(dev, "Failed alloc doorbell id bitmap, aborting\n"); + return -ENOMEM; + } + + /* first doorbell id reserved for kernel (dbid aka pid == zero) */ + set_bit(0, lif->dbid_inuse); + lif->kern_pid = 0; + + dbpage_num = ionic_db_page_num(lif, lif->kern_pid); + lif->kern_dbpage = ionic_bus_map_dbpage(lif->ionic, dbpage_num); + if (!lif->kern_dbpage) { + dev_err(dev, "Cannot map dbpage, aborting\n"); + err = -ENOMEM; + goto err_out_free_dbid; + } + + err = ionic_lif_adminq_init(lif); + if (err) + goto err_out_adminq_deinit; + + if (lif->ionic->nnqs_per_lif) { + err = ionic_lif_notifyq_init(lif); + if (err) + goto err_out_notifyq_deinit; + } + + err = ionic_init_nic_features(lif); + if (err) + goto err_out_notifyq_deinit; + + err = ionic_rx_filters_init(lif); + if (err) + goto err_out_notifyq_deinit; + + err = ionic_station_set(lif); + if (err) + goto err_out_notifyq_deinit; + + lif->rx_copybreak = IONIC_RX_COPYBREAK_DEFAULT; + + set_bit(IONIC_LIF_INITED, lif->state); + + INIT_WORK(&lif->tx_timeout_work, ionic_tx_timeout_work); + + return 0; + +err_out_notifyq_deinit: + ionic_lif_qcq_deinit(lif, lif->notifyqcq); +err_out_adminq_deinit: + ionic_lif_qcq_deinit(lif, lif->adminqcq); + ionic_lif_reset(lif); + ionic_bus_unmap_dbpage(lif->ionic, lif->kern_dbpage); + lif->kern_dbpage = NULL; +err_out_free_dbid: + kfree(lif->dbid_inuse); + lif->dbid_inuse = NULL; + + return err; +} + +int ionic_lifs_init(struct ionic *ionic) +{ + struct list_head *cur, *tmp; + struct ionic_lif *lif; + int err; + + list_for_each_safe(cur, tmp, &ionic->lifs) { + lif = list_entry(cur, struct ionic_lif, list); + err = ionic_lif_init(lif); + if (err) + return err; + } + + return 0; +} + +static void ionic_lif_notify_work(struct work_struct *ws) +{ +} + +static void ionic_lif_set_netdev_info(struct ionic_lif *lif) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.lif_setattr = { + .opcode = IONIC_CMD_LIF_SETATTR, + .index = cpu_to_le16(lif->index), + .attr = IONIC_LIF_ATTR_NAME, + }, + }; + + strlcpy(ctx.cmd.lif_setattr.name, lif->netdev->name, + sizeof(ctx.cmd.lif_setattr.name)); + + ionic_adminq_post_wait(lif, &ctx); +} + +static struct ionic_lif *ionic_netdev_lif(struct net_device *netdev) +{ + if (!netdev || netdev->netdev_ops->ndo_start_xmit != ionic_start_xmit) + return NULL; + + return netdev_priv(netdev); +} + +static int ionic_lif_notify(struct notifier_block *nb, + unsigned long event, void *info) +{ + struct net_device *ndev = netdev_notifier_info_to_dev(info); + struct ionic *ionic = container_of(nb, struct ionic, nb); + struct ionic_lif *lif = ionic_netdev_lif(ndev); + + if (!lif || lif->ionic != ionic) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_CHANGENAME: + ionic_lif_set_netdev_info(lif); + break; + } + + return NOTIFY_DONE; +} + +int ionic_lifs_register(struct ionic *ionic) +{ + int err; + + INIT_WORK(&ionic->nb_work, ionic_lif_notify_work); + + ionic->nb.notifier_call = ionic_lif_notify; + + err = register_netdevice_notifier(&ionic->nb); + if (err) + ionic->nb.notifier_call = NULL; + + /* only register LIF0 for now */ + err = register_netdev(ionic->master_lif->netdev); + if (err) { + dev_err(ionic->dev, "Cannot register net device, aborting\n"); + return err; + } + + ionic_link_status_check_request(ionic->master_lif); + ionic->master_lif->registered = true; + + return 0; +} + +void ionic_lifs_unregister(struct ionic *ionic) +{ + if (ionic->nb.notifier_call) { + unregister_netdevice_notifier(&ionic->nb); + cancel_work_sync(&ionic->nb_work); + ionic->nb.notifier_call = NULL; + } + + /* There is only one lif ever registered in the + * current model, so don't bother searching the + * ionic->lif for candidates to unregister + */ + cancel_work_sync(&ionic->master_lif->deferred.work); + cancel_work_sync(&ionic->master_lif->tx_timeout_work); + if (ionic->master_lif->netdev->reg_state == NETREG_REGISTERED) + unregister_netdev(ionic->master_lif->netdev); +} + +int ionic_lif_identify(struct ionic *ionic, u8 lif_type, + union ionic_lif_identity *lid) +{ + struct ionic_dev *idev = &ionic->idev; + size_t sz; + int err; + + sz = min(sizeof(*lid), sizeof(idev->dev_cmd_regs->data)); + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_lif_identify(idev, lif_type, IONIC_IDENTITY_VERSION_1); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + memcpy_fromio(lid, &idev->dev_cmd_regs->data, sz); + mutex_unlock(&ionic->dev_cmd_lock); + if (err) + return (err); + + dev_dbg(ionic->dev, "capabilities 0x%llx\n", + le64_to_cpu(lid->capabilities)); + + dev_dbg(ionic->dev, "eth.max_ucast_filters %d\n", + le32_to_cpu(lid->eth.max_ucast_filters)); + dev_dbg(ionic->dev, "eth.max_mcast_filters %d\n", + le32_to_cpu(lid->eth.max_mcast_filters)); + dev_dbg(ionic->dev, "eth.features 0x%llx\n", + le64_to_cpu(lid->eth.config.features)); + dev_dbg(ionic->dev, "eth.queue_count[IONIC_QTYPE_ADMINQ] %d\n", + le32_to_cpu(lid->eth.config.queue_count[IONIC_QTYPE_ADMINQ])); + dev_dbg(ionic->dev, "eth.queue_count[IONIC_QTYPE_NOTIFYQ] %d\n", + le32_to_cpu(lid->eth.config.queue_count[IONIC_QTYPE_NOTIFYQ])); + dev_dbg(ionic->dev, "eth.queue_count[IONIC_QTYPE_RXQ] %d\n", + le32_to_cpu(lid->eth.config.queue_count[IONIC_QTYPE_RXQ])); + dev_dbg(ionic->dev, "eth.queue_count[IONIC_QTYPE_TXQ] %d\n", + le32_to_cpu(lid->eth.config.queue_count[IONIC_QTYPE_TXQ])); + dev_dbg(ionic->dev, "eth.config.name %s\n", lid->eth.config.name); + dev_dbg(ionic->dev, "eth.config.mac %pM\n", lid->eth.config.mac); + dev_dbg(ionic->dev, "eth.config.mtu %d\n", + le32_to_cpu(lid->eth.config.mtu)); + + return 0; +} + +int ionic_lifs_size(struct ionic *ionic) +{ + struct ionic_identity *ident = &ionic->ident; + unsigned int nintrs, dev_nintrs; + union ionic_lif_config *lc; + unsigned int ntxqs_per_lif; + unsigned int nrxqs_per_lif; + unsigned int neqs_per_lif; + unsigned int nnqs_per_lif; + unsigned int nxqs, neqs; + unsigned int min_intrs; + int err; + + lc = &ident->lif.eth.config; + dev_nintrs = le32_to_cpu(ident->dev.nintrs); + neqs_per_lif = le32_to_cpu(ident->lif.rdma.eq_qtype.qid_count); + nnqs_per_lif = le32_to_cpu(lc->queue_count[IONIC_QTYPE_NOTIFYQ]); + ntxqs_per_lif = le32_to_cpu(lc->queue_count[IONIC_QTYPE_TXQ]); + nrxqs_per_lif = le32_to_cpu(lc->queue_count[IONIC_QTYPE_RXQ]); + + nxqs = min(ntxqs_per_lif, nrxqs_per_lif); + nxqs = min(nxqs, num_online_cpus()); + neqs = min(neqs_per_lif, num_online_cpus()); + +try_again: + /* interrupt usage: + * 1 for master lif adminq/notifyq + * 1 for each CPU for master lif TxRx queue pairs + * whatever's left is for RDMA queues + */ + nintrs = 1 + nxqs + neqs; + min_intrs = 2; /* adminq + 1 TxRx queue pair */ + + if (nintrs > dev_nintrs) + goto try_fewer; + + err = ionic_bus_alloc_irq_vectors(ionic, nintrs); + if (err < 0 && err != -ENOSPC) { + dev_err(ionic->dev, "Can't get intrs from OS: %d\n", err); + return err; + } + if (err == -ENOSPC) + goto try_fewer; + + if (err != nintrs) { + ionic_bus_free_irq_vectors(ionic); + goto try_fewer; + } + + ionic->nnqs_per_lif = nnqs_per_lif; + ionic->neqs_per_lif = neqs; + ionic->ntxqs_per_lif = nxqs; + ionic->nrxqs_per_lif = nxqs; + ionic->nintrs = nintrs; + + ionic_debugfs_add_sizes(ionic); + + return 0; + +try_fewer: + if (nnqs_per_lif > 1) { + nnqs_per_lif >>= 1; + goto try_again; + } + if (neqs > 1) { + neqs >>= 1; + goto try_again; + } + if (nxqs > 1) { + nxqs >>= 1; + goto try_again; + } + dev_err(ionic->dev, "Can't get minimum %d intrs from OS\n", min_intrs); + return -ENOSPC; +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.h b/drivers/net/ethernet/pensando/ionic/ionic_lif.h new file mode 100644 index 000000000000..812190e729c2 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.h @@ -0,0 +1,277 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_LIF_H_ +#define _IONIC_LIF_H_ + +#include <linux/pci.h> +#include "ionic_rx_filter.h" + +#define IONIC_ADMINQ_LENGTH 16 /* must be a power of two */ +#define IONIC_NOTIFYQ_LENGTH 64 /* must be a power of two */ + +#define IONIC_MAX_NUM_NAPI_CNTR (NAPI_POLL_WEIGHT + 1) +#define IONIC_MAX_NUM_SG_CNTR (IONIC_TX_MAX_SG_ELEMS + 1) +#define IONIC_RX_COPYBREAK_DEFAULT 256 + +struct ionic_tx_stats { + u64 dma_map_err; + u64 pkts; + u64 bytes; + u64 clean; + u64 linearize; + u64 no_csum; + u64 csum; + u64 crc32_csum; + u64 tso; + u64 frags; + u64 sg_cntr[IONIC_MAX_NUM_SG_CNTR]; +}; + +struct ionic_rx_stats { + u64 dma_map_err; + u64 alloc_err; + u64 pkts; + u64 bytes; + u64 csum_none; + u64 csum_complete; + u64 csum_error; + u64 buffers_posted; +}; + +#define IONIC_QCQ_F_INITED BIT(0) +#define IONIC_QCQ_F_SG BIT(1) +#define IONIC_QCQ_F_INTR BIT(2) +#define IONIC_QCQ_F_TX_STATS BIT(3) +#define IONIC_QCQ_F_RX_STATS BIT(4) +#define IONIC_QCQ_F_NOTIFYQ BIT(5) + +struct ionic_napi_stats { + u64 poll_count; + u64 work_done_cntr[IONIC_MAX_NUM_NAPI_CNTR]; +}; + +struct ionic_q_stats { + union { + struct ionic_tx_stats tx; + struct ionic_rx_stats rx; + }; +}; + +struct ionic_qcq { + void *base; + dma_addr_t base_pa; + unsigned int total_size; + struct ionic_queue q; + struct ionic_cq cq; + struct ionic_intr_info intr; + struct napi_struct napi; + struct ionic_napi_stats napi_stats; + struct ionic_q_stats *stats; + unsigned int flags; + struct dentry *dentry; +}; + +struct ionic_qcqst { + struct ionic_qcq *qcq; + struct ionic_q_stats *stats; +}; + +#define q_to_qcq(q) container_of(q, struct ionic_qcq, q) +#define q_to_tx_stats(q) (&q_to_qcq(q)->stats->tx) +#define q_to_rx_stats(q) (&q_to_qcq(q)->stats->rx) +#define napi_to_qcq(napi) container_of(napi, struct ionic_qcq, napi) +#define napi_to_cq(napi) (&napi_to_qcq(napi)->cq) + +enum ionic_deferred_work_type { + IONIC_DW_TYPE_RX_MODE, + IONIC_DW_TYPE_RX_ADDR_ADD, + IONIC_DW_TYPE_RX_ADDR_DEL, + IONIC_DW_TYPE_LINK_STATUS, + IONIC_DW_TYPE_LIF_RESET, +}; + +struct ionic_deferred_work { + struct list_head list; + enum ionic_deferred_work_type type; + union { + unsigned int rx_mode; + u8 addr[ETH_ALEN]; + }; +}; + +struct ionic_deferred { + spinlock_t lock; /* lock for deferred work list */ + struct list_head list; + struct work_struct work; +}; + +struct ionic_lif_sw_stats { + u64 tx_packets; + u64 tx_bytes; + u64 rx_packets; + u64 rx_bytes; + u64 tx_tso; + u64 tx_no_csum; + u64 tx_csum; + u64 rx_csum_none; + u64 rx_csum_complete; + u64 rx_csum_error; +}; + +enum ionic_lif_state_flags { + IONIC_LIF_INITED, + IONIC_LIF_SW_DEBUG_STATS, + IONIC_LIF_UP, + IONIC_LIF_LINK_CHECK_REQUESTED, + IONIC_LIF_QUEUE_RESET, + + /* leave this as last */ + IONIC_LIF_STATE_SIZE +}; + +#define IONIC_LIF_NAME_MAX_SZ 32 +struct ionic_lif { + char name[IONIC_LIF_NAME_MAX_SZ]; + struct list_head list; + struct net_device *netdev; + DECLARE_BITMAP(state, IONIC_LIF_STATE_SIZE); + struct ionic *ionic; + bool registered; + unsigned int index; + unsigned int hw_index; + unsigned int kern_pid; + u64 __iomem *kern_dbpage; + spinlock_t adminq_lock; /* lock for AdminQ operations */ + struct ionic_qcq *adminqcq; + struct ionic_qcq *notifyqcq; + struct ionic_qcqst *txqcqs; + struct ionic_qcqst *rxqcqs; + u64 last_eid; + unsigned int neqs; + unsigned int nxqs; + unsigned int ntxq_descs; + unsigned int nrxq_descs; + u32 rx_copybreak; + unsigned int rx_mode; + u64 hw_features; + bool mc_overflow; + unsigned int nmcast; + bool uc_overflow; + unsigned int nucast; + + struct ionic_lif_info *info; + dma_addr_t info_pa; + u32 info_sz; + + u16 rss_types; + u8 rss_hash_key[IONIC_RSS_HASH_KEY_SIZE]; + u8 *rss_ind_tbl; + dma_addr_t rss_ind_tbl_pa; + u32 rss_ind_tbl_sz; + + struct ionic_rx_filters rx_filters; + struct ionic_deferred deferred; + unsigned long *dbid_inuse; + unsigned int dbid_count; + struct dentry *dentry; + u32 rx_coalesce_usecs; + u32 flags; + struct work_struct tx_timeout_work; +}; + +#define lif_to_txqcq(lif, i) ((lif)->txqcqs[i].qcq) +#define lif_to_rxqcq(lif, i) ((lif)->rxqcqs[i].qcq) +#define lif_to_txq(lif, i) (&lif_to_txqcq((lif), i)->q) +#define lif_to_rxq(lif, i) (&lif_to_txqcq((lif), i)->q) + +static inline int ionic_wait_for_bit(struct ionic_lif *lif, int bitname) +{ + unsigned long tlimit = jiffies + HZ; + + while (test_and_set_bit(bitname, lif->state) && + time_before(jiffies, tlimit)) + usleep_range(100, 200); + + return test_bit(bitname, lif->state); +} + +static inline u32 ionic_coal_usec_to_hw(struct ionic *ionic, u32 usecs) +{ + u32 mult = le32_to_cpu(ionic->ident.dev.intr_coal_mult); + u32 div = le32_to_cpu(ionic->ident.dev.intr_coal_div); + + /* Div-by-zero should never be an issue, but check anyway */ + if (!div || !mult) + return 0; + + /* Round up in case usecs is close to the next hw unit */ + usecs += (div / mult) >> 1; + + /* Convert from usecs to device units */ + return (usecs * mult) / div; +} + +static inline u32 ionic_coal_hw_to_usec(struct ionic *ionic, u32 units) +{ + u32 mult = le32_to_cpu(ionic->ident.dev.intr_coal_mult); + u32 div = le32_to_cpu(ionic->ident.dev.intr_coal_div); + + /* Div-by-zero should never be an issue, but check anyway */ + if (!div || !mult) + return 0; + + /* Convert from device units to usec */ + return (units * div) / mult; +} + +int ionic_lifs_alloc(struct ionic *ionic); +void ionic_lifs_free(struct ionic *ionic); +void ionic_lifs_deinit(struct ionic *ionic); +int ionic_lifs_init(struct ionic *ionic); +int ionic_lifs_register(struct ionic *ionic); +void ionic_lifs_unregister(struct ionic *ionic); +int ionic_lif_identify(struct ionic *ionic, u8 lif_type, + union ionic_lif_identity *lif_ident); +int ionic_lifs_size(struct ionic *ionic); +int ionic_lif_rss_config(struct ionic_lif *lif, u16 types, + const u8 *key, const u32 *indir); + +int ionic_open(struct net_device *netdev); +int ionic_stop(struct net_device *netdev); +int ionic_reset_queues(struct ionic_lif *lif); + +static inline void debug_stats_txq_post(struct ionic_qcq *qcq, + struct ionic_txq_desc *desc, bool dbell) +{ + u8 num_sg_elems = ((le64_to_cpu(desc->cmd) >> IONIC_TXQ_DESC_NSGE_SHIFT) + & IONIC_TXQ_DESC_NSGE_MASK); + + qcq->q.dbell_count += dbell; + + if (num_sg_elems > (IONIC_MAX_NUM_SG_CNTR - 1)) + num_sg_elems = IONIC_MAX_NUM_SG_CNTR - 1; + + qcq->stats->tx.sg_cntr[num_sg_elems]++; +} + +static inline void debug_stats_napi_poll(struct ionic_qcq *qcq, + unsigned int work_done) +{ + qcq->napi_stats.poll_count++; + + if (work_done > (IONIC_MAX_NUM_NAPI_CNTR - 1)) + work_done = IONIC_MAX_NUM_NAPI_CNTR - 1; + + qcq->napi_stats.work_done_cntr[work_done]++; +} + +#define DEBUG_STATS_CQE_CNT(cq) ((cq)->compl_count++) +#define DEBUG_STATS_RX_BUFF_CNT(qcq) ((qcq)->stats->rx.buffers_posted++) +#define DEBUG_STATS_INTR_REARM(intr) ((intr)->rearm_count++) +#define DEBUG_STATS_TXQ_POST(qcq, txdesc, dbell) \ + debug_stats_txq_post(qcq, txdesc, dbell) +#define DEBUG_STATS_NAPI_POLL(qcq, work_done) \ + debug_stats_napi_poll(qcq, work_done) + +#endif /* _IONIC_LIF_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_main.c b/drivers/net/ethernet/pensando/ionic/ionic_main.c new file mode 100644 index 000000000000..15e432386b35 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_main.c @@ -0,0 +1,548 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/utsname.h> + +#include "ionic.h" +#include "ionic_bus.h" +#include "ionic_lif.h" +#include "ionic_debugfs.h" + +MODULE_DESCRIPTION(IONIC_DRV_DESCRIPTION); +MODULE_AUTHOR("Pensando Systems, Inc"); +MODULE_LICENSE("GPL"); +MODULE_VERSION(IONIC_DRV_VERSION); + +static const char *ionic_error_to_str(enum ionic_status_code code) +{ + switch (code) { + case IONIC_RC_SUCCESS: + return "IONIC_RC_SUCCESS"; + case IONIC_RC_EVERSION: + return "IONIC_RC_EVERSION"; + case IONIC_RC_EOPCODE: + return "IONIC_RC_EOPCODE"; + case IONIC_RC_EIO: + return "IONIC_RC_EIO"; + case IONIC_RC_EPERM: + return "IONIC_RC_EPERM"; + case IONIC_RC_EQID: + return "IONIC_RC_EQID"; + case IONIC_RC_EQTYPE: + return "IONIC_RC_EQTYPE"; + case IONIC_RC_ENOENT: + return "IONIC_RC_ENOENT"; + case IONIC_RC_EINTR: + return "IONIC_RC_EINTR"; + case IONIC_RC_EAGAIN: + return "IONIC_RC_EAGAIN"; + case IONIC_RC_ENOMEM: + return "IONIC_RC_ENOMEM"; + case IONIC_RC_EFAULT: + return "IONIC_RC_EFAULT"; + case IONIC_RC_EBUSY: + return "IONIC_RC_EBUSY"; + case IONIC_RC_EEXIST: + return "IONIC_RC_EEXIST"; + case IONIC_RC_EINVAL: + return "IONIC_RC_EINVAL"; + case IONIC_RC_ENOSPC: + return "IONIC_RC_ENOSPC"; + case IONIC_RC_ERANGE: + return "IONIC_RC_ERANGE"; + case IONIC_RC_BAD_ADDR: + return "IONIC_RC_BAD_ADDR"; + case IONIC_RC_DEV_CMD: + return "IONIC_RC_DEV_CMD"; + case IONIC_RC_ERROR: + return "IONIC_RC_ERROR"; + case IONIC_RC_ERDMA: + return "IONIC_RC_ERDMA"; + default: + return "IONIC_RC_UNKNOWN"; + } +} + +static int ionic_error_to_errno(enum ionic_status_code code) +{ + switch (code) { + case IONIC_RC_SUCCESS: + return 0; + case IONIC_RC_EVERSION: + case IONIC_RC_EQTYPE: + case IONIC_RC_EQID: + case IONIC_RC_EINVAL: + return -EINVAL; + case IONIC_RC_EPERM: + return -EPERM; + case IONIC_RC_ENOENT: + return -ENOENT; + case IONIC_RC_EAGAIN: + return -EAGAIN; + case IONIC_RC_ENOMEM: + return -ENOMEM; + case IONIC_RC_EFAULT: + return -EFAULT; + case IONIC_RC_EBUSY: + return -EBUSY; + case IONIC_RC_EEXIST: + return -EEXIST; + case IONIC_RC_ENOSPC: + return -ENOSPC; + case IONIC_RC_ERANGE: + return -ERANGE; + case IONIC_RC_BAD_ADDR: + return -EFAULT; + case IONIC_RC_EOPCODE: + case IONIC_RC_EINTR: + case IONIC_RC_DEV_CMD: + case IONIC_RC_ERROR: + case IONIC_RC_ERDMA: + case IONIC_RC_EIO: + default: + return -EIO; + } +} + +static const char *ionic_opcode_to_str(enum ionic_cmd_opcode opcode) +{ + switch (opcode) { + case IONIC_CMD_NOP: + return "IONIC_CMD_NOP"; + case IONIC_CMD_INIT: + return "IONIC_CMD_INIT"; + case IONIC_CMD_RESET: + return "IONIC_CMD_RESET"; + case IONIC_CMD_IDENTIFY: + return "IONIC_CMD_IDENTIFY"; + case IONIC_CMD_GETATTR: + return "IONIC_CMD_GETATTR"; + case IONIC_CMD_SETATTR: + return "IONIC_CMD_SETATTR"; + case IONIC_CMD_PORT_IDENTIFY: + return "IONIC_CMD_PORT_IDENTIFY"; + case IONIC_CMD_PORT_INIT: + return "IONIC_CMD_PORT_INIT"; + case IONIC_CMD_PORT_RESET: + return "IONIC_CMD_PORT_RESET"; + case IONIC_CMD_PORT_GETATTR: + return "IONIC_CMD_PORT_GETATTR"; + case IONIC_CMD_PORT_SETATTR: + return "IONIC_CMD_PORT_SETATTR"; + case IONIC_CMD_LIF_INIT: + return "IONIC_CMD_LIF_INIT"; + case IONIC_CMD_LIF_RESET: + return "IONIC_CMD_LIF_RESET"; + case IONIC_CMD_LIF_IDENTIFY: + return "IONIC_CMD_LIF_IDENTIFY"; + case IONIC_CMD_LIF_SETATTR: + return "IONIC_CMD_LIF_SETATTR"; + case IONIC_CMD_LIF_GETATTR: + return "IONIC_CMD_LIF_GETATTR"; + case IONIC_CMD_RX_MODE_SET: + return "IONIC_CMD_RX_MODE_SET"; + case IONIC_CMD_RX_FILTER_ADD: + return "IONIC_CMD_RX_FILTER_ADD"; + case IONIC_CMD_RX_FILTER_DEL: + return "IONIC_CMD_RX_FILTER_DEL"; + case IONIC_CMD_Q_INIT: + return "IONIC_CMD_Q_INIT"; + case IONIC_CMD_Q_CONTROL: + return "IONIC_CMD_Q_CONTROL"; + case IONIC_CMD_RDMA_RESET_LIF: + return "IONIC_CMD_RDMA_RESET_LIF"; + case IONIC_CMD_RDMA_CREATE_EQ: + return "IONIC_CMD_RDMA_CREATE_EQ"; + case IONIC_CMD_RDMA_CREATE_CQ: + return "IONIC_CMD_RDMA_CREATE_CQ"; + case IONIC_CMD_RDMA_CREATE_ADMINQ: + return "IONIC_CMD_RDMA_CREATE_ADMINQ"; + case IONIC_CMD_FW_DOWNLOAD: + return "IONIC_CMD_FW_DOWNLOAD"; + case IONIC_CMD_FW_CONTROL: + return "IONIC_CMD_FW_CONTROL"; + default: + return "DEVCMD_UNKNOWN"; + } +} + +static void ionic_adminq_flush(struct ionic_lif *lif) +{ + struct ionic_queue *adminq = &lif->adminqcq->q; + + spin_lock(&lif->adminq_lock); + + while (adminq->tail != adminq->head) { + memset(adminq->tail->desc, 0, sizeof(union ionic_adminq_cmd)); + adminq->tail->cb = NULL; + adminq->tail->cb_arg = NULL; + adminq->tail = adminq->tail->next; + } + spin_unlock(&lif->adminq_lock); +} + +static int ionic_adminq_check_err(struct ionic_lif *lif, + struct ionic_admin_ctx *ctx, + bool timeout) +{ + struct net_device *netdev = lif->netdev; + const char *opcode_str; + const char *status_str; + int err = 0; + + if (ctx->comp.comp.status || timeout) { + opcode_str = ionic_opcode_to_str(ctx->cmd.cmd.opcode); + status_str = ionic_error_to_str(ctx->comp.comp.status); + err = timeout ? -ETIMEDOUT : + ionic_error_to_errno(ctx->comp.comp.status); + + netdev_err(netdev, "%s (%d) failed: %s (%d)\n", + opcode_str, ctx->cmd.cmd.opcode, + timeout ? "TIMEOUT" : status_str, err); + + if (timeout) + ionic_adminq_flush(lif); + } + + return err; +} + +static void ionic_adminq_cb(struct ionic_queue *q, + struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, void *cb_arg) +{ + struct ionic_admin_ctx *ctx = cb_arg; + struct ionic_admin_comp *comp; + struct device *dev; + + if (!ctx) + return; + + comp = cq_info->cq_desc; + dev = &q->lif->netdev->dev; + + memcpy(&ctx->comp, comp, sizeof(*comp)); + + dev_dbg(dev, "comp admin queue command:\n"); + dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1, + &ctx->comp, sizeof(ctx->comp), true); + + complete_all(&ctx->work); +} + +static int ionic_adminq_post(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) +{ + struct ionic_queue *adminq = &lif->adminqcq->q; + int err = 0; + + WARN_ON(in_interrupt()); + + spin_lock(&lif->adminq_lock); + if (!ionic_q_has_space(adminq, 1)) { + err = -ENOSPC; + goto err_out; + } + + memcpy(adminq->head->desc, &ctx->cmd, sizeof(ctx->cmd)); + + dev_dbg(&lif->netdev->dev, "post admin queue command:\n"); + dynamic_hex_dump("cmd ", DUMP_PREFIX_OFFSET, 16, 1, + &ctx->cmd, sizeof(ctx->cmd), true); + + ionic_q_post(adminq, true, ionic_adminq_cb, ctx); + +err_out: + spin_unlock(&lif->adminq_lock); + + return err; +} + +int ionic_adminq_post_wait(struct ionic_lif *lif, struct ionic_admin_ctx *ctx) +{ + struct net_device *netdev = lif->netdev; + unsigned long remaining; + const char *name; + int err; + + err = ionic_adminq_post(lif, ctx); + if (err) { + name = ionic_opcode_to_str(ctx->cmd.cmd.opcode); + netdev_err(netdev, "Posting of %s (%d) failed: %d\n", + name, ctx->cmd.cmd.opcode, err); + return err; + } + + remaining = wait_for_completion_timeout(&ctx->work, + HZ * (ulong)DEVCMD_TIMEOUT); + return ionic_adminq_check_err(lif, ctx, (remaining == 0)); +} + +int ionic_napi(struct napi_struct *napi, int budget, ionic_cq_cb cb, + ionic_cq_done_cb done_cb, void *done_arg) +{ + struct ionic_qcq *qcq = napi_to_qcq(napi); + struct ionic_cq *cq = &qcq->cq; + u32 work_done, flags = 0; + + work_done = ionic_cq_service(cq, budget, cb, done_cb, done_arg); + + if (work_done < budget && napi_complete_done(napi, work_done)) { + flags |= IONIC_INTR_CRED_UNMASK; + DEBUG_STATS_INTR_REARM(cq->bound_intr); + } + + if (work_done || flags) { + flags |= IONIC_INTR_CRED_RESET_COALESCE; + ionic_intr_credits(cq->lif->ionic->idev.intr_ctrl, + cq->bound_intr->index, + work_done, flags); + } + + DEBUG_STATS_NAPI_POLL(qcq, work_done); + + return work_done; +} + +int ionic_dev_cmd_wait(struct ionic *ionic, unsigned long max_seconds) +{ + struct ionic_dev *idev = &ionic->idev; + unsigned long start_time; + unsigned long max_wait; + unsigned long duration; + int opcode; + int done; + int err; + + WARN_ON(in_interrupt()); + + /* Wait for dev cmd to complete, retrying if we get EAGAIN, + * but don't wait any longer than max_seconds. + */ + max_wait = jiffies + (max_seconds * HZ); +try_again: + start_time = jiffies; + do { + done = ionic_dev_cmd_done(idev); + if (done) + break; + msleep(20); + } while (!done && time_before(jiffies, max_wait)); + duration = jiffies - start_time; + + opcode = idev->dev_cmd_regs->cmd.cmd.opcode; + dev_dbg(ionic->dev, "DEVCMD %s (%d) done=%d took %ld secs (%ld jiffies)\n", + ionic_opcode_to_str(opcode), opcode, + done, duration / HZ, duration); + + if (!done && !time_before(jiffies, max_wait)) { + dev_warn(ionic->dev, "DEVCMD %s (%d) timeout after %ld secs\n", + ionic_opcode_to_str(opcode), opcode, max_seconds); + return -ETIMEDOUT; + } + + err = ionic_dev_cmd_status(&ionic->idev); + if (err) { + if (err == IONIC_RC_EAGAIN && !time_after(jiffies, max_wait)) { + dev_err(ionic->dev, "DEV_CMD %s (%d) error, %s (%d) retrying...\n", + ionic_opcode_to_str(opcode), opcode, + ionic_error_to_str(err), err); + + msleep(1000); + iowrite32(0, &idev->dev_cmd_regs->done); + iowrite32(1, &idev->dev_cmd_regs->doorbell); + goto try_again; + } + + dev_err(ionic->dev, "DEV_CMD %s (%d) error, %s (%d) failed\n", + ionic_opcode_to_str(opcode), opcode, + ionic_error_to_str(err), err); + + return ionic_error_to_errno(err); + } + + return 0; +} + +int ionic_setup(struct ionic *ionic) +{ + int err; + + err = ionic_dev_setup(ionic); + if (err) + return err; + + return 0; +} + +int ionic_identify(struct ionic *ionic) +{ + struct ionic_identity *ident = &ionic->ident; + struct ionic_dev *idev = &ionic->idev; + size_t sz; + int err; + + memset(ident, 0, sizeof(*ident)); + + ident->drv.os_type = cpu_to_le32(IONIC_OS_TYPE_LINUX); + strncpy(ident->drv.driver_ver_str, IONIC_DRV_VERSION, + sizeof(ident->drv.driver_ver_str) - 1); + + mutex_lock(&ionic->dev_cmd_lock); + + sz = min(sizeof(ident->drv), sizeof(idev->dev_cmd_regs->data)); + memcpy_toio(&idev->dev_cmd_regs->data, &ident->drv, sz); + + ionic_dev_cmd_identify(idev, IONIC_IDENTITY_VERSION_1); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + if (!err) { + sz = min(sizeof(ident->dev), sizeof(idev->dev_cmd_regs->data)); + memcpy_fromio(&ident->dev, &idev->dev_cmd_regs->data, sz); + } + + mutex_unlock(&ionic->dev_cmd_lock); + + if (err) + goto err_out_unmap; + + ionic_debugfs_add_ident(ionic); + + return 0; + +err_out_unmap: + return err; +} + +int ionic_init(struct ionic *ionic) +{ + struct ionic_dev *idev = &ionic->idev; + int err; + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_init(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + + return err; +} + +int ionic_reset(struct ionic *ionic) +{ + struct ionic_dev *idev = &ionic->idev; + int err; + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_reset(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + + return err; +} + +int ionic_port_identify(struct ionic *ionic) +{ + struct ionic_identity *ident = &ionic->ident; + struct ionic_dev *idev = &ionic->idev; + size_t sz; + int err; + + mutex_lock(&ionic->dev_cmd_lock); + + ionic_dev_cmd_port_identify(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + if (!err) { + sz = min(sizeof(ident->port), sizeof(idev->dev_cmd_regs->data)); + memcpy_fromio(&ident->port, &idev->dev_cmd_regs->data, sz); + } + + mutex_unlock(&ionic->dev_cmd_lock); + + return err; +} + +int ionic_port_init(struct ionic *ionic) +{ + struct ionic_identity *ident = &ionic->ident; + struct ionic_dev *idev = &ionic->idev; + size_t sz; + int err; + + if (idev->port_info) + return 0; + + idev->port_info_sz = ALIGN(sizeof(*idev->port_info), PAGE_SIZE); + idev->port_info = dma_alloc_coherent(ionic->dev, idev->port_info_sz, + &idev->port_info_pa, + GFP_KERNEL); + if (!idev->port_info) { + dev_err(ionic->dev, "Failed to allocate port info, aborting\n"); + return -ENOMEM; + } + + sz = min(sizeof(ident->port.config), sizeof(idev->dev_cmd_regs->data)); + + mutex_lock(&ionic->dev_cmd_lock); + + memcpy_toio(&idev->dev_cmd_regs->data, &ident->port.config, sz); + ionic_dev_cmd_port_init(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + + ionic_dev_cmd_port_state(&ionic->idev, IONIC_PORT_ADMIN_STATE_UP); + (void)ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + + mutex_unlock(&ionic->dev_cmd_lock); + if (err) { + dev_err(ionic->dev, "Failed to init port\n"); + dma_free_coherent(ionic->dev, idev->port_info_sz, + idev->port_info, idev->port_info_pa); + idev->port_info = NULL; + idev->port_info_pa = 0; + } + + return err; +} + +int ionic_port_reset(struct ionic *ionic) +{ + struct ionic_dev *idev = &ionic->idev; + int err; + + if (!idev->port_info) + return 0; + + mutex_lock(&ionic->dev_cmd_lock); + ionic_dev_cmd_port_reset(idev); + err = ionic_dev_cmd_wait(ionic, DEVCMD_TIMEOUT); + mutex_unlock(&ionic->dev_cmd_lock); + + dma_free_coherent(ionic->dev, idev->port_info_sz, + idev->port_info, idev->port_info_pa); + + idev->port_info = NULL; + idev->port_info_pa = 0; + + if (err) + dev_err(ionic->dev, "Failed to reset port\n"); + + return err; +} + +static int __init ionic_init_module(void) +{ + pr_info("%s %s, ver %s\n", + IONIC_DRV_NAME, IONIC_DRV_DESCRIPTION, IONIC_DRV_VERSION); + ionic_debugfs_create(); + return ionic_bus_register_driver(); +} + +static void __exit ionic_cleanup_module(void) +{ + ionic_bus_unregister_driver(); + ionic_debugfs_destroy(); + + pr_info("%s removed\n", IONIC_DRV_NAME); +} + +module_init(ionic_init_module); +module_exit(ionic_cleanup_module); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_regs.h b/drivers/net/ethernet/pensando/ionic/ionic_regs.h new file mode 100644 index 000000000000..03ee5a36472b --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_regs.h @@ -0,0 +1,136 @@ +/* SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB OR BSD-2-Clause */ +/* Copyright (c) 2018-2019 Pensando Systems, Inc. All rights reserved. */ + +#ifndef IONIC_REGS_H +#define IONIC_REGS_H + +#include <linux/io.h> + +/** struct ionic_intr - interrupt control register set. + * @coal_init: coalesce timer initial value. + * @mask: interrupt mask value. + * @credits: interrupt credit count and return. + * @mask_assert: interrupt mask value on assert. + * @coal: coalesce timer time remaining. + */ +struct ionic_intr { + u32 coal_init; + u32 mask; + u32 credits; + u32 mask_assert; + u32 coal; + u32 rsvd[3]; +}; + +#define IONIC_INTR_CTRL_REGS_MAX 2048 +#define IONIC_INTR_CTRL_COAL_MAX 0x3F + +/** enum ionic_intr_mask_vals - valid values for mask and mask_assert. + * @IONIC_INTR_MASK_CLEAR: unmask interrupt. + * @IONIC_INTR_MASK_SET: mask interrupt. + */ +enum ionic_intr_mask_vals { + IONIC_INTR_MASK_CLEAR = 0, + IONIC_INTR_MASK_SET = 1, +}; + +/** enum ionic_intr_credits_bits - bitwise composition of credits values. + * @IONIC_INTR_CRED_COUNT: bit mask of credit count, no shift needed. + * @IONIC_INTR_CRED_COUNT_SIGNED: bit mask of credit count, including sign bit. + * @IONIC_INTR_CRED_UNMASK: unmask the interrupt. + * @IONIC_INTR_CRED_RESET_COALESCE: reset the coalesce timer. + * @IONIC_INTR_CRED_REARM: unmask the and reset the timer. + */ +enum ionic_intr_credits_bits { + IONIC_INTR_CRED_COUNT = 0x7fffu, + IONIC_INTR_CRED_COUNT_SIGNED = 0xffffu, + IONIC_INTR_CRED_UNMASK = 0x10000u, + IONIC_INTR_CRED_RESET_COALESCE = 0x20000u, + IONIC_INTR_CRED_REARM = (IONIC_INTR_CRED_UNMASK | + IONIC_INTR_CRED_RESET_COALESCE), +}; + +static inline void ionic_intr_coal_init(struct ionic_intr __iomem *intr_ctrl, + int intr_idx, u32 coal) +{ + iowrite32(coal, &intr_ctrl[intr_idx].coal_init); +} + +static inline void ionic_intr_mask(struct ionic_intr __iomem *intr_ctrl, + int intr_idx, u32 mask) +{ + iowrite32(mask, &intr_ctrl[intr_idx].mask); +} + +static inline void ionic_intr_credits(struct ionic_intr __iomem *intr_ctrl, + int intr_idx, u32 cred, u32 flags) +{ + if (WARN_ON_ONCE(cred > IONIC_INTR_CRED_COUNT)) { + cred = ioread32(&intr_ctrl[intr_idx].credits); + cred &= IONIC_INTR_CRED_COUNT_SIGNED; + } + + iowrite32(cred | flags, &intr_ctrl[intr_idx].credits); +} + +static inline void ionic_intr_clean(struct ionic_intr __iomem *intr_ctrl, + int intr_idx) +{ + u32 cred; + + cred = ioread32(&intr_ctrl[intr_idx].credits); + cred &= IONIC_INTR_CRED_COUNT_SIGNED; + cred |= IONIC_INTR_CRED_RESET_COALESCE; + iowrite32(cred, &intr_ctrl[intr_idx].credits); +} + +static inline void ionic_intr_mask_assert(struct ionic_intr __iomem *intr_ctrl, + int intr_idx, u32 mask) +{ + iowrite32(mask, &intr_ctrl[intr_idx].mask_assert); +} + +/** enum ionic_dbell_bits - bitwise composition of dbell values. + * + * @IONIC_DBELL_QID_MASK: unshifted mask of valid queue id bits. + * @IONIC_DBELL_QID_SHIFT: queue id shift amount in dbell value. + * @IONIC_DBELL_QID: macro to build QID component of dbell value. + * + * @IONIC_DBELL_RING_MASK: unshifted mask of valid ring bits. + * @IONIC_DBELL_RING_SHIFT: ring shift amount in dbell value. + * @IONIC_DBELL_RING: macro to build ring component of dbell value. + * + * @IONIC_DBELL_RING_0: ring zero dbell component value. + * @IONIC_DBELL_RING_1: ring one dbell component value. + * @IONIC_DBELL_RING_2: ring two dbell component value. + * @IONIC_DBELL_RING_3: ring three dbell component value. + * + * @IONIC_DBELL_INDEX_MASK: bit mask of valid index bits, no shift needed. + */ +enum ionic_dbell_bits { + IONIC_DBELL_QID_MASK = 0xffffff, + IONIC_DBELL_QID_SHIFT = 24, + +#define IONIC_DBELL_QID(n) \ + (((u64)(n) & IONIC_DBELL_QID_MASK) << IONIC_DBELL_QID_SHIFT) + + IONIC_DBELL_RING_MASK = 0x7, + IONIC_DBELL_RING_SHIFT = 16, + +#define IONIC_DBELL_RING(n) \ + (((u64)(n) & IONIC_DBELL_RING_MASK) << IONIC_DBELL_RING_SHIFT) + + IONIC_DBELL_RING_0 = 0, + IONIC_DBELL_RING_1 = IONIC_DBELL_RING(1), + IONIC_DBELL_RING_2 = IONIC_DBELL_RING(2), + IONIC_DBELL_RING_3 = IONIC_DBELL_RING(3), + + IONIC_DBELL_INDEX_MASK = 0xffff, +}; + +static inline void ionic_dbell_ring(u64 __iomem *db_page, int qtype, u64 val) +{ + writeq(val, &db_page[qtype]); +} + +#endif /* IONIC_REGS_H */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c new file mode 100644 index 000000000000..7a093f148ee5 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.c @@ -0,0 +1,150 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/netdevice.h> +#include <linux/etherdevice.h> + +#include "ionic.h" +#include "ionic_lif.h" +#include "ionic_rx_filter.h" + +void ionic_rx_filter_free(struct ionic_lif *lif, struct ionic_rx_filter *f) +{ + struct device *dev = lif->ionic->dev; + + hlist_del(&f->by_id); + hlist_del(&f->by_hash); + devm_kfree(dev, f); +} + +int ionic_rx_filter_del(struct ionic_lif *lif, struct ionic_rx_filter *f) +{ + struct ionic_admin_ctx ctx = { + .work = COMPLETION_INITIALIZER_ONSTACK(ctx.work), + .cmd.rx_filter_del = { + .opcode = IONIC_CMD_RX_FILTER_DEL, + .filter_id = cpu_to_le32(f->filter_id), + }, + }; + + return ionic_adminq_post_wait(lif, &ctx); +} + +int ionic_rx_filters_init(struct ionic_lif *lif) +{ + unsigned int i; + + spin_lock_init(&lif->rx_filters.lock); + + for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) { + INIT_HLIST_HEAD(&lif->rx_filters.by_hash[i]); + INIT_HLIST_HEAD(&lif->rx_filters.by_id[i]); + } + + return 0; +} + +void ionic_rx_filters_deinit(struct ionic_lif *lif) +{ + struct ionic_rx_filter *f; + struct hlist_head *head; + struct hlist_node *tmp; + unsigned int i; + + for (i = 0; i < IONIC_RX_FILTER_HLISTS; i++) { + head = &lif->rx_filters.by_id[i]; + hlist_for_each_entry_safe(f, tmp, head, by_id) + ionic_rx_filter_free(lif, f); + } +} + +int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index, + u32 hash, struct ionic_admin_ctx *ctx) +{ + struct device *dev = lif->ionic->dev; + struct ionic_rx_filter_add_cmd *ac; + struct ionic_rx_filter *f; + struct hlist_head *head; + unsigned int key; + + ac = &ctx->cmd.rx_filter_add; + + switch (le16_to_cpu(ac->match)) { + case IONIC_RX_FILTER_MATCH_VLAN: + key = le16_to_cpu(ac->vlan.vlan); + break; + case IONIC_RX_FILTER_MATCH_MAC: + key = *(u32 *)ac->mac.addr; + break; + case IONIC_RX_FILTER_MATCH_MAC_VLAN: + key = le16_to_cpu(ac->mac_vlan.vlan); + break; + default: + return -EINVAL; + } + + f = devm_kzalloc(dev, sizeof(*f), GFP_KERNEL); + if (!f) + return -ENOMEM; + + f->flow_id = flow_id; + f->filter_id = le32_to_cpu(ctx->comp.rx_filter_add.filter_id); + f->rxq_index = rxq_index; + memcpy(&f->cmd, ac, sizeof(f->cmd)); + + INIT_HLIST_NODE(&f->by_hash); + INIT_HLIST_NODE(&f->by_id); + + spin_lock_bh(&lif->rx_filters.lock); + + key = hash_32(key, IONIC_RX_FILTER_HASH_BITS); + head = &lif->rx_filters.by_hash[key]; + hlist_add_head(&f->by_hash, head); + + key = f->filter_id & IONIC_RX_FILTER_HLISTS_MASK; + head = &lif->rx_filters.by_id[key]; + hlist_add_head(&f->by_id, head); + + spin_unlock_bh(&lif->rx_filters.lock); + + return 0; +} + +struct ionic_rx_filter *ionic_rx_filter_by_vlan(struct ionic_lif *lif, u16 vid) +{ + struct ionic_rx_filter *f; + struct hlist_head *head; + unsigned int key; + + key = hash_32(vid, IONIC_RX_FILTER_HASH_BITS); + head = &lif->rx_filters.by_hash[key]; + + hlist_for_each_entry(f, head, by_hash) { + if (le16_to_cpu(f->cmd.match) != IONIC_RX_FILTER_MATCH_VLAN) + continue; + if (le16_to_cpu(f->cmd.vlan.vlan) == vid) + return f; + } + + return NULL; +} + +struct ionic_rx_filter *ionic_rx_filter_by_addr(struct ionic_lif *lif, + const u8 *addr) +{ + struct ionic_rx_filter *f; + struct hlist_head *head; + unsigned int key; + + key = hash_32(*(u32 *)addr, IONIC_RX_FILTER_HASH_BITS); + head = &lif->rx_filters.by_hash[key]; + + hlist_for_each_entry(f, head, by_hash) { + if (le16_to_cpu(f->cmd.match) != IONIC_RX_FILTER_MATCH_MAC) + continue; + if (memcmp(addr, f->cmd.mac.addr, ETH_ALEN) == 0) + return f; + } + + return NULL; +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h new file mode 100644 index 000000000000..b6aec9c19918 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_rx_filter.h @@ -0,0 +1,35 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_RX_FILTER_H_ +#define _IONIC_RX_FILTER_H_ + +#define IONIC_RXQ_INDEX_ANY (0xFFFF) +struct ionic_rx_filter { + u32 flow_id; + u32 filter_id; + u16 rxq_index; + struct ionic_rx_filter_add_cmd cmd; + struct hlist_node by_hash; + struct hlist_node by_id; +}; + +#define IONIC_RX_FILTER_HASH_BITS 10 +#define IONIC_RX_FILTER_HLISTS BIT(IONIC_RX_FILTER_HASH_BITS) +#define IONIC_RX_FILTER_HLISTS_MASK (IONIC_RX_FILTER_HLISTS - 1) +struct ionic_rx_filters { + spinlock_t lock; /* filter list lock */ + struct hlist_head by_hash[IONIC_RX_FILTER_HLISTS]; /* by skb hash */ + struct hlist_head by_id[IONIC_RX_FILTER_HLISTS]; /* by filter_id */ +}; + +void ionic_rx_filter_free(struct ionic_lif *lif, struct ionic_rx_filter *f); +int ionic_rx_filter_del(struct ionic_lif *lif, struct ionic_rx_filter *f); +int ionic_rx_filters_init(struct ionic_lif *lif); +void ionic_rx_filters_deinit(struct ionic_lif *lif); +int ionic_rx_filter_save(struct ionic_lif *lif, u32 flow_id, u16 rxq_index, + u32 hash, struct ionic_admin_ctx *ctx); +struct ionic_rx_filter *ionic_rx_filter_by_vlan(struct ionic_lif *lif, u16 vid); +struct ionic_rx_filter *ionic_rx_filter_by_addr(struct ionic_lif *lif, const u8 *addr); + +#endif /* _IONIC_RX_FILTER_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.c b/drivers/net/ethernet/pensando/ionic/ionic_stats.c new file mode 100644 index 000000000000..e2907884f843 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.c @@ -0,0 +1,310 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/kernel.h> +#include <linux/mutex.h> +#include <linux/netdevice.h> + +#include "ionic.h" +#include "ionic_lif.h" +#include "ionic_stats.h" + +static const struct ionic_stat_desc ionic_lif_stats_desc[] = { + IONIC_LIF_STAT_DESC(tx_packets), + IONIC_LIF_STAT_DESC(tx_bytes), + IONIC_LIF_STAT_DESC(rx_packets), + IONIC_LIF_STAT_DESC(rx_bytes), + IONIC_LIF_STAT_DESC(tx_tso), + IONIC_LIF_STAT_DESC(tx_no_csum), + IONIC_LIF_STAT_DESC(tx_csum), + IONIC_LIF_STAT_DESC(rx_csum_none), + IONIC_LIF_STAT_DESC(rx_csum_complete), + IONIC_LIF_STAT_DESC(rx_csum_error), +}; + +static const struct ionic_stat_desc ionic_tx_stats_desc[] = { + IONIC_TX_STAT_DESC(pkts), + IONIC_TX_STAT_DESC(bytes), + IONIC_TX_STAT_DESC(clean), + IONIC_TX_STAT_DESC(dma_map_err), + IONIC_TX_STAT_DESC(linearize), + IONIC_TX_STAT_DESC(frags), +}; + +static const struct ionic_stat_desc ionic_rx_stats_desc[] = { + IONIC_RX_STAT_DESC(pkts), + IONIC_RX_STAT_DESC(bytes), + IONIC_RX_STAT_DESC(dma_map_err), + IONIC_RX_STAT_DESC(alloc_err), + IONIC_RX_STAT_DESC(csum_none), + IONIC_RX_STAT_DESC(csum_complete), + IONIC_RX_STAT_DESC(csum_error), +}; + +static const struct ionic_stat_desc ionic_txq_stats_desc[] = { + IONIC_TX_Q_STAT_DESC(stop), + IONIC_TX_Q_STAT_DESC(wake), + IONIC_TX_Q_STAT_DESC(drop), + IONIC_TX_Q_STAT_DESC(dbell_count), +}; + +static const struct ionic_stat_desc ionic_dbg_cq_stats_desc[] = { + IONIC_CQ_STAT_DESC(compl_count), +}; + +static const struct ionic_stat_desc ionic_dbg_intr_stats_desc[] = { + IONIC_INTR_STAT_DESC(rearm_count), +}; + +static const struct ionic_stat_desc ionic_dbg_napi_stats_desc[] = { + IONIC_NAPI_STAT_DESC(poll_count), +}; + +#define IONIC_NUM_LIF_STATS ARRAY_SIZE(ionic_lif_stats_desc) +#define IONIC_NUM_TX_STATS ARRAY_SIZE(ionic_tx_stats_desc) +#define IONIC_NUM_RX_STATS ARRAY_SIZE(ionic_rx_stats_desc) +#define IONIC_NUM_TX_Q_STATS ARRAY_SIZE(ionic_txq_stats_desc) +#define IONIC_NUM_DBG_CQ_STATS ARRAY_SIZE(ionic_dbg_cq_stats_desc) +#define IONIC_NUM_DBG_INTR_STATS ARRAY_SIZE(ionic_dbg_intr_stats_desc) +#define IONIC_NUM_DBG_NAPI_STATS ARRAY_SIZE(ionic_dbg_napi_stats_desc) + +#define MAX_Q(lif) ((lif)->netdev->real_num_tx_queues) + +static void ionic_get_lif_stats(struct ionic_lif *lif, + struct ionic_lif_sw_stats *stats) +{ + struct ionic_tx_stats *tstats; + struct ionic_rx_stats *rstats; + struct ionic_qcq *txqcq; + struct ionic_qcq *rxqcq; + int q_num; + + memset(stats, 0, sizeof(*stats)); + + for (q_num = 0; q_num < MAX_Q(lif); q_num++) { + txqcq = lif_to_txqcq(lif, q_num); + if (txqcq && txqcq->stats) { + tstats = &txqcq->stats->tx; + stats->tx_packets += tstats->pkts; + stats->tx_bytes += tstats->bytes; + stats->tx_tso += tstats->tso; + stats->tx_no_csum += tstats->no_csum; + stats->tx_csum += tstats->csum; + } + + rxqcq = lif_to_rxqcq(lif, q_num); + if (rxqcq && rxqcq->stats) { + rstats = &rxqcq->stats->rx; + stats->rx_packets += rstats->pkts; + stats->rx_bytes += rstats->bytes; + stats->rx_csum_none += rstats->csum_none; + stats->rx_csum_complete += rstats->csum_complete; + stats->rx_csum_error += rstats->csum_error; + } + } +} + +static u64 ionic_sw_stats_get_count(struct ionic_lif *lif) +{ + u64 total = 0; + + /* lif stats */ + total += IONIC_NUM_LIF_STATS; + + /* tx stats */ + total += MAX_Q(lif) * IONIC_NUM_TX_STATS; + + /* rx stats */ + total += MAX_Q(lif) * IONIC_NUM_RX_STATS; + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + /* tx debug stats */ + total += MAX_Q(lif) * (IONIC_NUM_DBG_CQ_STATS + + IONIC_NUM_TX_Q_STATS + + IONIC_NUM_DBG_INTR_STATS + + IONIC_MAX_NUM_SG_CNTR); + + /* rx debug stats */ + total += MAX_Q(lif) * (IONIC_NUM_DBG_CQ_STATS + + IONIC_NUM_DBG_INTR_STATS + + IONIC_NUM_DBG_NAPI_STATS + + IONIC_MAX_NUM_NAPI_CNTR); + } + + return total; +} + +static void ionic_sw_stats_get_strings(struct ionic_lif *lif, u8 **buf) +{ + int i, q_num; + + for (i = 0; i < IONIC_NUM_LIF_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, ionic_lif_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (q_num = 0; q_num < MAX_Q(lif); q_num++) { + for (i = 0; i < IONIC_NUM_TX_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, "tx_%d_%s", + q_num, ionic_tx_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "txq_%d_%s", + q_num, + ionic_txq_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "txq_%d_cq_%s", + q_num, + ionic_dbg_cq_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_NUM_DBG_INTR_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "txq_%d_intr_%s", + q_num, + ionic_dbg_intr_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_MAX_NUM_SG_CNTR; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "txq_%d_sg_cntr_%d", + q_num, i); + *buf += ETH_GSTRING_LEN; + } + } + } + for (q_num = 0; q_num < MAX_Q(lif); q_num++) { + for (i = 0; i < IONIC_NUM_RX_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "rx_%d_%s", + q_num, ionic_rx_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "rxq_%d_cq_%s", + q_num, + ionic_dbg_cq_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_NUM_DBG_INTR_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "rxq_%d_intr_%s", + q_num, + ionic_dbg_intr_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_NUM_DBG_NAPI_STATS; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "rxq_%d_napi_%s", + q_num, + ionic_dbg_napi_stats_desc[i].name); + *buf += ETH_GSTRING_LEN; + } + for (i = 0; i < IONIC_MAX_NUM_NAPI_CNTR; i++) { + snprintf(*buf, ETH_GSTRING_LEN, + "rxq_%d_napi_work_done_%d", + q_num, i); + *buf += ETH_GSTRING_LEN; + } + } + } +} + +static void ionic_sw_stats_get_values(struct ionic_lif *lif, u64 **buf) +{ + struct ionic_lif_sw_stats lif_stats; + struct ionic_qcq *txqcq, *rxqcq; + int i, q_num; + + ionic_get_lif_stats(lif, &lif_stats); + + for (i = 0; i < IONIC_NUM_LIF_STATS; i++) { + **buf = IONIC_READ_STAT64(&lif_stats, &ionic_lif_stats_desc[i]); + (*buf)++; + } + + for (q_num = 0; q_num < MAX_Q(lif); q_num++) { + txqcq = lif_to_txqcq(lif, q_num); + + for (i = 0; i < IONIC_NUM_TX_STATS; i++) { + **buf = IONIC_READ_STAT64(&txqcq->stats->tx, + &ionic_tx_stats_desc[i]); + (*buf)++; + } + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + for (i = 0; i < IONIC_NUM_TX_Q_STATS; i++) { + **buf = IONIC_READ_STAT64(&txqcq->q, + &ionic_txq_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { + **buf = IONIC_READ_STAT64(&txqcq->cq, + &ionic_dbg_cq_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_NUM_DBG_INTR_STATS; i++) { + **buf = IONIC_READ_STAT64(&txqcq->intr, + &ionic_dbg_intr_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_MAX_NUM_SG_CNTR; i++) { + **buf = txqcq->stats->tx.sg_cntr[i]; + (*buf)++; + } + } + } + + for (q_num = 0; q_num < MAX_Q(lif); q_num++) { + rxqcq = lif_to_rxqcq(lif, q_num); + + for (i = 0; i < IONIC_NUM_RX_STATS; i++) { + **buf = IONIC_READ_STAT64(&rxqcq->stats->rx, + &ionic_rx_stats_desc[i]); + (*buf)++; + } + + if (test_bit(IONIC_LIF_SW_DEBUG_STATS, lif->state)) { + for (i = 0; i < IONIC_NUM_DBG_CQ_STATS; i++) { + **buf = IONIC_READ_STAT64(&rxqcq->cq, + &ionic_dbg_cq_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_NUM_DBG_INTR_STATS; i++) { + **buf = IONIC_READ_STAT64(&rxqcq->intr, + &ionic_dbg_intr_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_NUM_DBG_NAPI_STATS; i++) { + **buf = IONIC_READ_STAT64(&rxqcq->napi_stats, + &ionic_dbg_napi_stats_desc[i]); + (*buf)++; + } + for (i = 0; i < IONIC_MAX_NUM_NAPI_CNTR; i++) { + **buf = rxqcq->napi_stats.work_done_cntr[i]; + (*buf)++; + } + } + } +} + +const struct ionic_stats_group_intf ionic_stats_groups[] = { + /* SW Stats group */ + { + .get_strings = ionic_sw_stats_get_strings, + .get_values = ionic_sw_stats_get_values, + .get_count = ionic_sw_stats_get_count, + }, + /* Add more stat groups here */ +}; + +const int ionic_num_stats_grps = ARRAY_SIZE(ionic_stats_groups); diff --git a/drivers/net/ethernet/pensando/ionic/ionic_stats.h b/drivers/net/ethernet/pensando/ionic/ionic_stats.h new file mode 100644 index 000000000000..d2c1122a2c6e --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_stats.h @@ -0,0 +1,53 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_STATS_H_ +#define _IONIC_STATS_H_ + +#define IONIC_STAT_TO_OFFSET(type, stat_name) (offsetof(type, stat_name)) + +#define IONIC_STAT_DESC(type, stat_name) { \ + .name = #stat_name, \ + .offset = IONIC_STAT_TO_OFFSET(type, stat_name) \ +} + +#define IONIC_LIF_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_lif_sw_stats, stat_name) + +#define IONIC_TX_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_tx_stats, stat_name) + +#define IONIC_RX_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_rx_stats, stat_name) + +#define IONIC_TX_Q_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_queue, stat_name) + +#define IONIC_CQ_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_cq, stat_name) + +#define IONIC_INTR_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_intr_info, stat_name) + +#define IONIC_NAPI_STAT_DESC(stat_name) \ + IONIC_STAT_DESC(struct ionic_napi_stats, stat_name) + +/* Interface structure for a particalar stats group */ +struct ionic_stats_group_intf { + void (*get_strings)(struct ionic_lif *lif, u8 **buf); + void (*get_values)(struct ionic_lif *lif, u64 **buf); + u64 (*get_count)(struct ionic_lif *lif); +}; + +extern const struct ionic_stats_group_intf ionic_stats_groups[]; +extern const int ionic_num_stats_grps; + +#define IONIC_READ_STAT64(base_ptr, desc_ptr) \ + (*((u64 *)(((u8 *)(base_ptr)) + (desc_ptr)->offset))) + +struct ionic_stat_desc { + char name[ETH_GSTRING_LEN]; + u64 offset; +}; + +#endif /* _IONIC_STATS_H_ */ diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.c b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c new file mode 100644 index 000000000000..ab6663d94f42 --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.c @@ -0,0 +1,925 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/if_vlan.h> +#include <net/ip6_checksum.h> + +#include "ionic.h" +#include "ionic_lif.h" +#include "ionic_txrx.h" + +static void ionic_rx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, void *cb_arg); + +static inline void ionic_txq_post(struct ionic_queue *q, bool ring_dbell, + ionic_desc_cb cb_func, void *cb_arg) +{ + DEBUG_STATS_TXQ_POST(q_to_qcq(q), q->head->desc, ring_dbell); + + ionic_q_post(q, ring_dbell, cb_func, cb_arg); +} + +static inline void ionic_rxq_post(struct ionic_queue *q, bool ring_dbell, + ionic_desc_cb cb_func, void *cb_arg) +{ + ionic_q_post(q, ring_dbell, cb_func, cb_arg); + + DEBUG_STATS_RX_BUFF_CNT(q_to_qcq(q)); +} + +static inline struct netdev_queue *q_to_ndq(struct ionic_queue *q) +{ + return netdev_get_tx_queue(q->lif->netdev, q->index); +} + +static void ionic_rx_recycle(struct ionic_queue *q, struct ionic_desc_info *desc_info, + struct sk_buff *skb) +{ + struct ionic_rxq_desc *old = desc_info->desc; + struct ionic_rxq_desc *new = q->head->desc; + + new->addr = old->addr; + new->len = old->len; + + ionic_rxq_post(q, true, ionic_rx_clean, skb); +} + +static bool ionic_rx_copybreak(struct ionic_queue *q, struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, struct sk_buff **skb) +{ + struct ionic_rxq_comp *comp = cq_info->cq_desc; + struct ionic_rxq_desc *desc = desc_info->desc; + struct net_device *netdev = q->lif->netdev; + struct device *dev = q->lif->ionic->dev; + struct sk_buff *new_skb; + u16 clen, dlen; + + clen = le16_to_cpu(comp->len); + dlen = le16_to_cpu(desc->len); + if (clen > q->lif->rx_copybreak) { + dma_unmap_single(dev, (dma_addr_t)le64_to_cpu(desc->addr), + dlen, DMA_FROM_DEVICE); + return false; + } + + new_skb = netdev_alloc_skb_ip_align(netdev, clen); + if (!new_skb) { + dma_unmap_single(dev, (dma_addr_t)le64_to_cpu(desc->addr), + dlen, DMA_FROM_DEVICE); + return false; + } + + dma_sync_single_for_cpu(dev, (dma_addr_t)le64_to_cpu(desc->addr), + clen, DMA_FROM_DEVICE); + + memcpy(new_skb->data, (*skb)->data, clen); + + ionic_rx_recycle(q, desc_info, *skb); + *skb = new_skb; + + return true; +} + +static void ionic_rx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, void *cb_arg) +{ + struct ionic_rxq_comp *comp = cq_info->cq_desc; + struct ionic_qcq *qcq = q_to_qcq(q); + struct sk_buff *skb = cb_arg; + struct ionic_rx_stats *stats; + struct net_device *netdev; + + stats = q_to_rx_stats(q); + netdev = q->lif->netdev; + + if (comp->status) { + ionic_rx_recycle(q, desc_info, skb); + return; + } + + if (unlikely(test_bit(IONIC_LIF_QUEUE_RESET, q->lif->state))) { + /* no packet processing while resetting */ + ionic_rx_recycle(q, desc_info, skb); + return; + } + + stats->pkts++; + stats->bytes += le16_to_cpu(comp->len); + + ionic_rx_copybreak(q, desc_info, cq_info, &skb); + + skb_put(skb, le16_to_cpu(comp->len)); + skb->protocol = eth_type_trans(skb, netdev); + + skb_record_rx_queue(skb, q->index); + + if (netdev->features & NETIF_F_RXHASH) { + switch (comp->pkt_type_color & IONIC_RXQ_COMP_PKT_TYPE_MASK) { + case IONIC_PKT_TYPE_IPV4: + case IONIC_PKT_TYPE_IPV6: + skb_set_hash(skb, le32_to_cpu(comp->rss_hash), + PKT_HASH_TYPE_L3); + break; + case IONIC_PKT_TYPE_IPV4_TCP: + case IONIC_PKT_TYPE_IPV6_TCP: + case IONIC_PKT_TYPE_IPV4_UDP: + case IONIC_PKT_TYPE_IPV6_UDP: + skb_set_hash(skb, le32_to_cpu(comp->rss_hash), + PKT_HASH_TYPE_L4); + break; + } + } + + if (netdev->features & NETIF_F_RXCSUM) { + if (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_CALC) { + skb->ip_summed = CHECKSUM_COMPLETE; + skb->csum = (__wsum)le16_to_cpu(comp->csum); + stats->csum_complete++; + } + } else { + stats->csum_none++; + } + + if ((comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_TCP_BAD) || + (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_UDP_BAD) || + (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_IP_BAD)) + stats->csum_error++; + + if (netdev->features & NETIF_F_HW_VLAN_CTAG_RX) { + if (comp->csum_flags & IONIC_RXQ_COMP_CSUM_F_VLAN) + __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), + le16_to_cpu(comp->vlan_tci)); + } + + napi_gro_receive(&qcq->napi, skb); +} + +static bool ionic_rx_service(struct ionic_cq *cq, struct ionic_cq_info *cq_info) +{ + struct ionic_rxq_comp *comp = cq_info->cq_desc; + struct ionic_queue *q = cq->bound_q; + struct ionic_desc_info *desc_info; + + if (!color_match(comp->pkt_type_color, cq->done_color)) + return false; + + /* check for empty queue */ + if (q->tail->index == q->head->index) + return false; + + desc_info = q->tail; + if (desc_info->index != le16_to_cpu(comp->comp_index)) + return false; + + q->tail = desc_info->next; + + /* clean the related q entry, only one per qc completion */ + ionic_rx_clean(q, desc_info, cq_info, desc_info->cb_arg); + + desc_info->cb = NULL; + desc_info->cb_arg = NULL; + + return true; +} + +static u32 ionic_rx_walk_cq(struct ionic_cq *rxcq, u32 limit) +{ + u32 work_done = 0; + + while (ionic_rx_service(rxcq, rxcq->tail)) { + if (rxcq->tail->last) + rxcq->done_color = !rxcq->done_color; + rxcq->tail = rxcq->tail->next; + DEBUG_STATS_CQE_CNT(rxcq); + + if (++work_done >= limit) + break; + } + + return work_done; +} + +void ionic_rx_flush(struct ionic_cq *cq) +{ + struct ionic_dev *idev = &cq->lif->ionic->idev; + u32 work_done; + + work_done = ionic_rx_walk_cq(cq, cq->num_descs); + + if (work_done) + ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index, + work_done, IONIC_INTR_CRED_RESET_COALESCE); +} + +static struct sk_buff *ionic_rx_skb_alloc(struct ionic_queue *q, unsigned int len, + dma_addr_t *dma_addr) +{ + struct ionic_lif *lif = q->lif; + struct ionic_rx_stats *stats; + struct net_device *netdev; + struct sk_buff *skb; + struct device *dev; + + netdev = lif->netdev; + dev = lif->ionic->dev; + stats = q_to_rx_stats(q); + skb = netdev_alloc_skb_ip_align(netdev, len); + if (!skb) { + net_warn_ratelimited("%s: SKB alloc failed on %s!\n", + netdev->name, q->name); + stats->alloc_err++; + return NULL; + } + + *dma_addr = dma_map_single(dev, skb->data, len, DMA_FROM_DEVICE); + if (dma_mapping_error(dev, *dma_addr)) { + dev_kfree_skb(skb); + net_warn_ratelimited("%s: DMA single map failed on %s!\n", + netdev->name, q->name); + stats->dma_map_err++; + return NULL; + } + + return skb; +} + +#define IONIC_RX_RING_DOORBELL_STRIDE ((1 << 2) - 1) + +void ionic_rx_fill(struct ionic_queue *q) +{ + struct net_device *netdev = q->lif->netdev; + struct ionic_rxq_desc *desc; + struct sk_buff *skb; + dma_addr_t dma_addr; + bool ring_doorbell; + unsigned int len; + unsigned int i; + + len = netdev->mtu + ETH_HLEN; + + for (i = ionic_q_space_avail(q); i; i--) { + skb = ionic_rx_skb_alloc(q, len, &dma_addr); + if (!skb) + return; + + desc = q->head->desc; + desc->addr = cpu_to_le64(dma_addr); + desc->len = cpu_to_le16(len); + desc->opcode = IONIC_RXQ_DESC_OPCODE_SIMPLE; + + ring_doorbell = ((q->head->index + 1) & + IONIC_RX_RING_DOORBELL_STRIDE) == 0; + + ionic_rxq_post(q, ring_doorbell, ionic_rx_clean, skb); + } +} + +static void ionic_rx_fill_cb(void *arg) +{ + ionic_rx_fill(arg); +} + +void ionic_rx_empty(struct ionic_queue *q) +{ + struct device *dev = q->lif->ionic->dev; + struct ionic_desc_info *cur; + struct ionic_rxq_desc *desc; + + for (cur = q->tail; cur != q->head; cur = cur->next) { + desc = cur->desc; + dma_unmap_single(dev, le64_to_cpu(desc->addr), + le16_to_cpu(desc->len), DMA_FROM_DEVICE); + dev_kfree_skb(cur->cb_arg); + cur->cb_arg = NULL; + } +} + +int ionic_rx_napi(struct napi_struct *napi, int budget) +{ + struct ionic_qcq *qcq = napi_to_qcq(napi); + struct ionic_cq *rxcq = napi_to_cq(napi); + unsigned int qi = rxcq->bound_q->index; + struct ionic_dev *idev; + struct ionic_lif *lif; + struct ionic_cq *txcq; + u32 work_done = 0; + u32 flags = 0; + + lif = rxcq->bound_q->lif; + idev = &lif->ionic->idev; + txcq = &lif->txqcqs[qi].qcq->cq; + + ionic_tx_flush(txcq); + + work_done = ionic_rx_walk_cq(rxcq, budget); + + if (work_done) + ionic_rx_fill_cb(rxcq->bound_q); + + if (work_done < budget && napi_complete_done(napi, work_done)) { + flags |= IONIC_INTR_CRED_UNMASK; + DEBUG_STATS_INTR_REARM(rxcq->bound_intr); + } + + if (work_done || flags) { + flags |= IONIC_INTR_CRED_RESET_COALESCE; + ionic_intr_credits(idev->intr_ctrl, rxcq->bound_intr->index, + work_done, flags); + } + + DEBUG_STATS_NAPI_POLL(qcq, work_done); + + return work_done; +} + +static dma_addr_t ionic_tx_map_single(struct ionic_queue *q, void *data, size_t len) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct device *dev = q->lif->ionic->dev; + dma_addr_t dma_addr; + + dma_addr = dma_map_single(dev, data, len, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma_addr)) { + net_warn_ratelimited("%s: DMA single map failed on %s!\n", + q->lif->netdev->name, q->name); + stats->dma_map_err++; + return 0; + } + return dma_addr; +} + +static dma_addr_t ionic_tx_map_frag(struct ionic_queue *q, const skb_frag_t *frag, + size_t offset, size_t len) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct device *dev = q->lif->ionic->dev; + dma_addr_t dma_addr; + + dma_addr = skb_frag_dma_map(dev, frag, offset, len, DMA_TO_DEVICE); + if (dma_mapping_error(dev, dma_addr)) { + net_warn_ratelimited("%s: DMA frag map failed on %s!\n", + q->lif->netdev->name, q->name); + stats->dma_map_err++; + } + return dma_addr; +} + +static void ionic_tx_clean(struct ionic_queue *q, struct ionic_desc_info *desc_info, + struct ionic_cq_info *cq_info, void *cb_arg) +{ + struct ionic_txq_sg_desc *sg_desc = desc_info->sg_desc; + struct ionic_txq_sg_elem *elem = sg_desc->elems; + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct ionic_txq_desc *desc = desc_info->desc; + struct device *dev = q->lif->ionic->dev; + u8 opcode, flags, nsge; + u16 queue_index; + unsigned int i; + u64 addr; + + decode_txq_desc_cmd(le64_to_cpu(desc->cmd), + &opcode, &flags, &nsge, &addr); + + /* use unmap_single only if either this is not TSO, + * or this is first descriptor of a TSO + */ + if (opcode != IONIC_TXQ_DESC_OPCODE_TSO || + flags & IONIC_TXQ_DESC_FLAG_TSO_SOT) + dma_unmap_single(dev, (dma_addr_t)addr, + le16_to_cpu(desc->len), DMA_TO_DEVICE); + else + dma_unmap_page(dev, (dma_addr_t)addr, + le16_to_cpu(desc->len), DMA_TO_DEVICE); + + for (i = 0; i < nsge; i++, elem++) + dma_unmap_page(dev, (dma_addr_t)le64_to_cpu(elem->addr), + le16_to_cpu(elem->len), DMA_TO_DEVICE); + + if (cb_arg) { + struct sk_buff *skb = cb_arg; + u32 len = skb->len; + + queue_index = skb_get_queue_mapping(skb); + if (unlikely(__netif_subqueue_stopped(q->lif->netdev, + queue_index))) { + netif_wake_subqueue(q->lif->netdev, queue_index); + q->wake++; + } + dev_kfree_skb_any(skb); + stats->clean++; + netdev_tx_completed_queue(q_to_ndq(q), 1, len); + } +} + +void ionic_tx_flush(struct ionic_cq *cq) +{ + struct ionic_txq_comp *comp = cq->tail->cq_desc; + struct ionic_dev *idev = &cq->lif->ionic->idev; + struct ionic_queue *q = cq->bound_q; + struct ionic_desc_info *desc_info; + unsigned int work_done = 0; + + /* walk the completed cq entries */ + while (work_done < cq->num_descs && + color_match(comp->color, cq->done_color)) { + + /* clean the related q entries, there could be + * several q entries completed for each cq completion + */ + do { + desc_info = q->tail; + q->tail = desc_info->next; + ionic_tx_clean(q, desc_info, cq->tail, + desc_info->cb_arg); + desc_info->cb = NULL; + desc_info->cb_arg = NULL; + } while (desc_info->index != le16_to_cpu(comp->comp_index)); + + if (cq->tail->last) + cq->done_color = !cq->done_color; + + cq->tail = cq->tail->next; + comp = cq->tail->cq_desc; + DEBUG_STATS_CQE_CNT(cq); + + work_done++; + } + + if (work_done) + ionic_intr_credits(idev->intr_ctrl, cq->bound_intr->index, + work_done, 0); +} + +static int ionic_tx_tcp_inner_pseudo_csum(struct sk_buff *skb) +{ + int err; + + err = skb_cow_head(skb, 0); + if (err) + return err; + + if (skb->protocol == cpu_to_be16(ETH_P_IP)) { + inner_ip_hdr(skb)->check = 0; + inner_tcp_hdr(skb)->check = + ~csum_tcpudp_magic(inner_ip_hdr(skb)->saddr, + inner_ip_hdr(skb)->daddr, + 0, IPPROTO_TCP, 0); + } else if (skb->protocol == cpu_to_be16(ETH_P_IPV6)) { + inner_tcp_hdr(skb)->check = + ~csum_ipv6_magic(&inner_ipv6_hdr(skb)->saddr, + &inner_ipv6_hdr(skb)->daddr, + 0, IPPROTO_TCP, 0); + } + + return 0; +} + +static int ionic_tx_tcp_pseudo_csum(struct sk_buff *skb) +{ + int err; + + err = skb_cow_head(skb, 0); + if (err) + return err; + + if (skb->protocol == cpu_to_be16(ETH_P_IP)) { + ip_hdr(skb)->check = 0; + tcp_hdr(skb)->check = + ~csum_tcpudp_magic(ip_hdr(skb)->saddr, + ip_hdr(skb)->daddr, + 0, IPPROTO_TCP, 0); + } else if (skb->protocol == cpu_to_be16(ETH_P_IPV6)) { + tcp_hdr(skb)->check = + ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, + &ipv6_hdr(skb)->daddr, + 0, IPPROTO_TCP, 0); + } + + return 0; +} + +static void ionic_tx_tso_post(struct ionic_queue *q, struct ionic_txq_desc *desc, + struct sk_buff *skb, + dma_addr_t addr, u8 nsge, u16 len, + unsigned int hdrlen, unsigned int mss, + bool outer_csum, + u16 vlan_tci, bool has_vlan, + bool start, bool done) +{ + u8 flags = 0; + u64 cmd; + + flags |= has_vlan ? IONIC_TXQ_DESC_FLAG_VLAN : 0; + flags |= outer_csum ? IONIC_TXQ_DESC_FLAG_ENCAP : 0; + flags |= start ? IONIC_TXQ_DESC_FLAG_TSO_SOT : 0; + flags |= done ? IONIC_TXQ_DESC_FLAG_TSO_EOT : 0; + + cmd = encode_txq_desc_cmd(IONIC_TXQ_DESC_OPCODE_TSO, flags, nsge, addr); + desc->cmd = cpu_to_le64(cmd); + desc->len = cpu_to_le16(len); + desc->vlan_tci = cpu_to_le16(vlan_tci); + desc->hdr_len = cpu_to_le16(hdrlen); + desc->mss = cpu_to_le16(mss); + + if (done) { + skb_tx_timestamp(skb); + netdev_tx_sent_queue(q_to_ndq(q), skb->len); + ionic_txq_post(q, !netdev_xmit_more(), ionic_tx_clean, skb); + } else { + ionic_txq_post(q, false, ionic_tx_clean, NULL); + } +} + +static struct ionic_txq_desc *ionic_tx_tso_next(struct ionic_queue *q, + struct ionic_txq_sg_elem **elem) +{ + struct ionic_txq_sg_desc *sg_desc = q->head->sg_desc; + struct ionic_txq_desc *desc = q->head->desc; + + *elem = sg_desc->elems; + return desc; +} + +static int ionic_tx_tso(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct ionic_desc_info *abort = q->head; + struct device *dev = q->lif->ionic->dev; + struct ionic_desc_info *rewind = abort; + struct ionic_txq_sg_elem *elem; + struct ionic_txq_desc *desc; + unsigned int frag_left = 0; + unsigned int offset = 0; + unsigned int len_left; + dma_addr_t desc_addr; + unsigned int hdrlen; + unsigned int nfrags; + unsigned int seglen; + u64 total_bytes = 0; + u64 total_pkts = 0; + unsigned int left; + unsigned int len; + unsigned int mss; + skb_frag_t *frag; + bool start, done; + bool outer_csum; + bool has_vlan; + u16 desc_len; + u8 desc_nsge; + u16 vlan_tci; + bool encap; + int err; + + mss = skb_shinfo(skb)->gso_size; + nfrags = skb_shinfo(skb)->nr_frags; + len_left = skb->len - skb_headlen(skb); + outer_csum = (skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM) || + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); + has_vlan = !!skb_vlan_tag_present(skb); + vlan_tci = skb_vlan_tag_get(skb); + encap = skb->encapsulation; + + /* Preload inner-most TCP csum field with IP pseudo hdr + * calculated with IP length set to zero. HW will later + * add in length to each TCP segment resulting from the TSO. + */ + + if (encap) + err = ionic_tx_tcp_inner_pseudo_csum(skb); + else + err = ionic_tx_tcp_pseudo_csum(skb); + if (err) + return err; + + if (encap) + hdrlen = skb_inner_transport_header(skb) - skb->data + + inner_tcp_hdrlen(skb); + else + hdrlen = skb_transport_offset(skb) + tcp_hdrlen(skb); + + seglen = hdrlen + mss; + left = skb_headlen(skb); + + desc = ionic_tx_tso_next(q, &elem); + start = true; + + /* Chop skb->data up into desc segments */ + + while (left > 0) { + len = min(seglen, left); + frag_left = seglen - len; + desc_addr = ionic_tx_map_single(q, skb->data + offset, len); + if (dma_mapping_error(dev, desc_addr)) + goto err_out_abort; + desc_len = len; + desc_nsge = 0; + left -= len; + offset += len; + if (nfrags > 0 && frag_left > 0) + continue; + done = (nfrags == 0 && left == 0); + ionic_tx_tso_post(q, desc, skb, + desc_addr, desc_nsge, desc_len, + hdrlen, mss, + outer_csum, + vlan_tci, has_vlan, + start, done); + total_pkts++; + total_bytes += start ? len : len + hdrlen; + desc = ionic_tx_tso_next(q, &elem); + start = false; + seglen = mss; + } + + /* Chop skb frags into desc segments */ + + for (frag = skb_shinfo(skb)->frags; len_left; frag++) { + offset = 0; + left = skb_frag_size(frag); + len_left -= left; + nfrags--; + stats->frags++; + + while (left > 0) { + if (frag_left > 0) { + len = min(frag_left, left); + frag_left -= len; + elem->addr = + cpu_to_le64(ionic_tx_map_frag(q, frag, + offset, len)); + if (dma_mapping_error(dev, elem->addr)) + goto err_out_abort; + elem->len = cpu_to_le16(len); + elem++; + desc_nsge++; + left -= len; + offset += len; + if (nfrags > 0 && frag_left > 0) + continue; + done = (nfrags == 0 && left == 0); + ionic_tx_tso_post(q, desc, skb, desc_addr, + desc_nsge, desc_len, + hdrlen, mss, outer_csum, + vlan_tci, has_vlan, + start, done); + total_pkts++; + total_bytes += start ? len : len + hdrlen; + desc = ionic_tx_tso_next(q, &elem); + start = false; + } else { + len = min(mss, left); + frag_left = mss - len; + desc_addr = ionic_tx_map_frag(q, frag, + offset, len); + if (dma_mapping_error(dev, desc_addr)) + goto err_out_abort; + desc_len = len; + desc_nsge = 0; + left -= len; + offset += len; + if (nfrags > 0 && frag_left > 0) + continue; + done = (nfrags == 0 && left == 0); + ionic_tx_tso_post(q, desc, skb, desc_addr, + desc_nsge, desc_len, + hdrlen, mss, outer_csum, + vlan_tci, has_vlan, + start, done); + total_pkts++; + total_bytes += start ? len : len + hdrlen; + desc = ionic_tx_tso_next(q, &elem); + start = false; + } + } + } + + stats->pkts += total_pkts; + stats->bytes += total_bytes; + stats->tso++; + + return 0; + +err_out_abort: + while (rewind->desc != q->head->desc) { + ionic_tx_clean(q, rewind, NULL, NULL); + rewind = rewind->next; + } + q->head = abort; + + return -ENOMEM; +} + +static int ionic_tx_calc_csum(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct ionic_txq_desc *desc = q->head->desc; + struct device *dev = q->lif->ionic->dev; + dma_addr_t dma_addr; + bool has_vlan; + u8 flags = 0; + bool encap; + u64 cmd; + + has_vlan = !!skb_vlan_tag_present(skb); + encap = skb->encapsulation; + + dma_addr = ionic_tx_map_single(q, skb->data, skb_headlen(skb)); + if (dma_mapping_error(dev, dma_addr)) + return -ENOMEM; + + flags |= has_vlan ? IONIC_TXQ_DESC_FLAG_VLAN : 0; + flags |= encap ? IONIC_TXQ_DESC_FLAG_ENCAP : 0; + + cmd = encode_txq_desc_cmd(IONIC_TXQ_DESC_OPCODE_CSUM_PARTIAL, + flags, skb_shinfo(skb)->nr_frags, dma_addr); + desc->cmd = cpu_to_le64(cmd); + desc->len = cpu_to_le16(skb_headlen(skb)); + desc->vlan_tci = cpu_to_le16(skb_vlan_tag_get(skb)); + desc->csum_start = cpu_to_le16(skb_checksum_start_offset(skb)); + desc->csum_offset = cpu_to_le16(skb->csum_offset); + + if (skb->csum_not_inet) + stats->crc32_csum++; + else + stats->csum++; + + return 0; +} + +static int ionic_tx_calc_no_csum(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct ionic_txq_desc *desc = q->head->desc; + struct device *dev = q->lif->ionic->dev; + dma_addr_t dma_addr; + bool has_vlan; + u8 flags = 0; + bool encap; + u64 cmd; + + has_vlan = !!skb_vlan_tag_present(skb); + encap = skb->encapsulation; + + dma_addr = ionic_tx_map_single(q, skb->data, skb_headlen(skb)); + if (dma_mapping_error(dev, dma_addr)) + return -ENOMEM; + + flags |= has_vlan ? IONIC_TXQ_DESC_FLAG_VLAN : 0; + flags |= encap ? IONIC_TXQ_DESC_FLAG_ENCAP : 0; + + cmd = encode_txq_desc_cmd(IONIC_TXQ_DESC_OPCODE_CSUM_NONE, + flags, skb_shinfo(skb)->nr_frags, dma_addr); + desc->cmd = cpu_to_le64(cmd); + desc->len = cpu_to_le16(skb_headlen(skb)); + desc->vlan_tci = cpu_to_le16(skb_vlan_tag_get(skb)); + + stats->no_csum++; + + return 0; +} + +static int ionic_tx_skb_frags(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_txq_sg_desc *sg_desc = q->head->sg_desc; + unsigned int len_left = skb->len - skb_headlen(skb); + struct ionic_txq_sg_elem *elem = sg_desc->elems; + struct ionic_tx_stats *stats = q_to_tx_stats(q); + struct device *dev = q->lif->ionic->dev; + dma_addr_t dma_addr; + skb_frag_t *frag; + u16 len; + + for (frag = skb_shinfo(skb)->frags; len_left; frag++, elem++) { + len = skb_frag_size(frag); + elem->len = cpu_to_le16(len); + dma_addr = ionic_tx_map_frag(q, frag, 0, len); + if (dma_mapping_error(dev, dma_addr)) + return -ENOMEM; + elem->addr = cpu_to_le64(dma_addr); + len_left -= len; + stats->frags++; + } + + return 0; +} + +static int ionic_tx(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + int err; + + /* set up the initial descriptor */ + if (skb->ip_summed == CHECKSUM_PARTIAL) + err = ionic_tx_calc_csum(q, skb); + else + err = ionic_tx_calc_no_csum(q, skb); + if (err) + return err; + + /* add frags */ + err = ionic_tx_skb_frags(q, skb); + if (err) + return err; + + skb_tx_timestamp(skb); + stats->pkts++; + stats->bytes += skb->len; + + netdev_tx_sent_queue(q_to_ndq(q), skb->len); + ionic_txq_post(q, !netdev_xmit_more(), ionic_tx_clean, skb); + + return 0; +} + +static int ionic_tx_descs_needed(struct ionic_queue *q, struct sk_buff *skb) +{ + struct ionic_tx_stats *stats = q_to_tx_stats(q); + int err; + + /* If TSO, need roundup(skb->len/mss) descs */ + if (skb_is_gso(skb)) + return (skb->len / skb_shinfo(skb)->gso_size) + 1; + + /* If non-TSO, just need 1 desc and nr_frags sg elems */ + if (skb_shinfo(skb)->nr_frags <= IONIC_TX_MAX_SG_ELEMS) + return 1; + + /* Too many frags, so linearize */ + err = skb_linearize(skb); + if (err) + return err; + + stats->linearize++; + + /* Need 1 desc and zero sg elems */ + return 1; +} + +static int ionic_maybe_stop_tx(struct ionic_queue *q, int ndescs) +{ + int stopped = 0; + + if (unlikely(!ionic_q_has_space(q, ndescs))) { + netif_stop_subqueue(q->lif->netdev, q->index); + q->stop++; + stopped = 1; + + /* Might race with ionic_tx_clean, check again */ + smp_rmb(); + if (ionic_q_has_space(q, ndescs)) { + netif_wake_subqueue(q->lif->netdev, q->index); + stopped = 0; + } + } + + return stopped; +} + +netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev) +{ + u16 queue_index = skb_get_queue_mapping(skb); + struct ionic_lif *lif = netdev_priv(netdev); + struct ionic_queue *q; + int ndescs; + int err; + + if (unlikely(!test_bit(IONIC_LIF_UP, lif->state))) { + dev_kfree_skb(skb); + return NETDEV_TX_OK; + } + + if (unlikely(!lif_to_txqcq(lif, queue_index))) + queue_index = 0; + q = lif_to_txq(lif, queue_index); + + ndescs = ionic_tx_descs_needed(q, skb); + if (ndescs < 0) + goto err_out_drop; + + if (unlikely(ionic_maybe_stop_tx(q, ndescs))) + return NETDEV_TX_BUSY; + + if (skb_is_gso(skb)) + err = ionic_tx_tso(q, skb); + else + err = ionic_tx(q, skb); + + if (err) + goto err_out_drop; + + /* Stop the queue if there aren't descriptors for the next packet. + * Since our SG lists per descriptor take care of most of the possible + * fragmentation, we don't need to have many descriptors available. + */ + ionic_maybe_stop_tx(q, 4); + + return NETDEV_TX_OK; + +err_out_drop: + q->stop++; + q->drop++; + dev_kfree_skb(skb); + return NETDEV_TX_OK; +} diff --git a/drivers/net/ethernet/pensando/ionic/ionic_txrx.h b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h new file mode 100644 index 000000000000..53775c62c85a --- /dev/null +++ b/drivers/net/ethernet/pensando/ionic/ionic_txrx.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2017 - 2019 Pensando Systems, Inc */ + +#ifndef _IONIC_TXRX_H_ +#define _IONIC_TXRX_H_ + +void ionic_rx_flush(struct ionic_cq *cq); +void ionic_tx_flush(struct ionic_cq *cq); + +void ionic_rx_fill(struct ionic_queue *q); +void ionic_rx_empty(struct ionic_queue *q); +int ionic_rx_napi(struct napi_struct *napi, int budget); +netdev_tx_t ionic_start_xmit(struct sk_buff *skb, struct net_device *netdev); + +#endif /* _IONIC_TXRX_H_ */ diff --git a/drivers/net/ethernet/qlogic/Kconfig b/drivers/net/ethernet/qlogic/Kconfig index a391cf6ee4b2..55a29ec76680 100644 --- a/drivers/net/ethernet/qlogic/Kconfig +++ b/drivers/net/ethernet/qlogic/Kconfig @@ -66,15 +66,6 @@ config QLCNIC_HWMON This data is available via the hwmon sysfs interface. -config QLGE - tristate "QLogic QLGE 10Gb Ethernet Driver Support" - depends on PCI - ---help--- - This driver supports QLogic ISP8XXX 10Gb Ethernet cards. - - To compile this driver as a module, choose M here: the module - will be called qlge. - config NETXEN_NIC tristate "NetXen Multi port (1/10) Gigabit Ethernet NIC" depends on PCI diff --git a/drivers/net/ethernet/qlogic/Makefile b/drivers/net/ethernet/qlogic/Makefile index 6cd2e333a5fc..1ae4a0743bd5 100644 --- a/drivers/net/ethernet/qlogic/Makefile +++ b/drivers/net/ethernet/qlogic/Makefile @@ -5,7 +5,6 @@ obj-$(CONFIG_QLA3XXX) += qla3xxx.o obj-$(CONFIG_QLCNIC) += qlcnic/ -obj-$(CONFIG_QLGE) += qlge/ obj-$(CONFIG_NETXEN_NIC) += netxen/ obj-$(CONFIG_QED) += qed/ obj-$(CONFIG_QEDE)+= qede/ diff --git a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c index 58e2eaf77014..c692a41e4548 100644 --- a/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c +++ b/drivers/net/ethernet/qlogic/netxen/netxen_nic_main.c @@ -1980,7 +1980,7 @@ netxen_map_tx_skb(struct pci_dev *pdev, struct sk_buff *skb, struct netxen_cmd_buffer *pbuf) { struct netxen_skb_frag *nf; - struct skb_frag_struct *frag; + skb_frag_t *frag; int i, nr_frags; dma_addr_t map; @@ -2043,7 +2043,7 @@ netxen_nic_xmit_frame(struct sk_buff *skb, struct net_device *netdev) struct pci_dev *pdev; int i, k; int delta = 0; - struct skb_frag_struct *frag; + skb_frag_t *frag; u32 producer; int frag_count; diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 5ea6c4fc6050..859caa6c1a1f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -1756,6 +1756,15 @@ static u32 qed_read_unaligned_dword(u8 *buf) return dword; } +/* Sets the value of the specified GRC param */ +static void qed_grc_set_param(struct qed_hwfn *p_hwfn, + enum dbg_grc_params grc_param, u32 val) +{ + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + + dev_data->grc.param_val[grc_param] = val; +} + /* Returns the value of the specified GRC param */ static u32 qed_grc_get_param(struct qed_hwfn *p_hwfn, enum dbg_grc_params grc_param) @@ -5119,6 +5128,69 @@ bool qed_read_fw_info(struct qed_hwfn *p_hwfn, return false; } +enum dbg_status qed_dbg_grc_config(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + enum dbg_grc_params grc_param, u32 val) +{ + enum dbg_status status; + int i; + + DP_VERBOSE(p_hwfn, QED_MSG_DEBUG, + "dbg_grc_config: paramId = %d, val = %d\n", grc_param, val); + + status = qed_dbg_dev_init(p_hwfn, p_ptt); + if (status != DBG_STATUS_OK) + return status; + + /* Initializes the GRC parameters (if not initialized). Needed in order + * to set the default parameter values for the first time. + */ + qed_dbg_grc_init_params(p_hwfn); + + if (grc_param >= MAX_DBG_GRC_PARAMS) + return DBG_STATUS_INVALID_ARGS; + if (val < s_grc_param_defs[grc_param].min || + val > s_grc_param_defs[grc_param].max) + return DBG_STATUS_INVALID_ARGS; + + if (s_grc_param_defs[grc_param].is_preset) { + /* Preset param */ + + /* Disabling a preset is not allowed. Call + * dbg_grc_set_params_default instead. + */ + if (!val) + return DBG_STATUS_INVALID_ARGS; + + /* Update all params with the preset values */ + for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) { + u32 preset_val; + + /* Skip persistent params */ + if (s_grc_param_defs[i].is_persistent) + continue; + + /* Find preset value */ + if (grc_param == DBG_GRC_PARAM_EXCLUDE_ALL) + preset_val = + s_grc_param_defs[i].exclude_all_preset_val; + else if (grc_param == DBG_GRC_PARAM_CRASH) + preset_val = + s_grc_param_defs[i].crash_preset_val; + else + return DBG_STATUS_INVALID_ARGS; + + qed_grc_set_param(p_hwfn, + (enum dbg_grc_params)i, preset_val); + } + } else { + /* Regular param - set its value */ + qed_grc_set_param(p_hwfn, grc_param, val); + } + + return DBG_STATUS_OK; +} + /* Assign default GRC param values */ void qed_dbg_grc_set_params_default(struct qed_hwfn *p_hwfn) { @@ -7997,9 +8069,16 @@ static u32 qed_calc_regdump_header(enum debug_print_features feature, int qed_dbg_all_data(struct qed_dev *cdev, void *buffer) { u8 cur_engine, omit_engine = 0, org_engine; + struct qed_hwfn *p_hwfn = + &cdev->hwfns[cdev->dbg_params.engine_for_debug]; + struct dbg_tools_data *dev_data = &p_hwfn->dbg_info; + int grc_params[MAX_DBG_GRC_PARAMS], i; u32 offset = 0, feature_size; int rc; + for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) + grc_params[i] = dev_data->grc.param_val[i]; + if (cdev->num_hwfns == 1) omit_engine = 1; @@ -8087,6 +8166,9 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer) rc); } + for (i = 0; i < MAX_DBG_GRC_PARAMS; i++) + dev_data->grc.param_val[i] = grc_params[i]; + /* GRC dump - must be last because when mcp stuck it will * clutter idle_chk, reg_fifo, ... */ diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index e054f6c69e3a..cf3ceb62e397 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -3024,6 +3024,21 @@ void qed_read_regs(struct qed_hwfn *p_hwfn, */ bool qed_read_fw_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct fw_info *fw_info); +/** + * @brief qed_dbg_grc_config - Sets the value of a GRC parameter. + * + * @param p_hwfn - HW device data + * @param grc_param - GRC parameter + * @param val - Value to set. + * + * @return error if one of the following holds: + * - the version wasn't set + * - grc_param is invalid + * - val is outside the allowed boundaries + */ +enum dbg_status qed_dbg_grc_config(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + enum dbg_grc_params grc_param, u32 val); /** * @brief qed_dbg_grc_set_params_default - Reverts all GRC parameters to their @@ -12580,6 +12595,8 @@ struct public_drv_mb { #define DRV_MSG_CODE_BW_UPDATE_ACK 0x32000000 #define DRV_MSG_CODE_NIG_DRAIN 0x30000000 #define DRV_MSG_CODE_S_TAG_UPDATE_ACK 0x3b000000 +#define DRV_MSG_CODE_GET_NVM_CFG_OPTION 0x003e0000 +#define DRV_MSG_CODE_SET_NVM_CFG_OPTION 0x003f0000 #define DRV_MSG_CODE_INITIATE_PF_FLR 0x02010000 #define DRV_MSG_CODE_VF_DISABLED_DONE 0xc0000000 #define DRV_MSG_CODE_CFG_VF_MSIX 0xc0010000 @@ -12748,6 +12765,21 @@ struct public_drv_mb { #define DRV_MB_PARAM_FEATURE_SUPPORT_PORT_EEE 0x00000002 #define DRV_MB_PARAM_FEATURE_SUPPORT_FUNC_VLINK 0x00010000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ID_SHIFT 0 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ID_MASK 0x0000FFFF +#define DRV_MB_PARAM_NVM_CFG_OPTION_ALL_SHIFT 16 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ALL_MASK 0x00010000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_INIT_SHIFT 17 +#define DRV_MB_PARAM_NVM_CFG_OPTION_INIT_MASK 0x00020000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_COMMIT_SHIFT 18 +#define DRV_MB_PARAM_NVM_CFG_OPTION_COMMIT_MASK 0x00040000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_FREE_SHIFT 19 +#define DRV_MB_PARAM_NVM_CFG_OPTION_FREE_MASK 0x00080000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_SEL_SHIFT 20 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_SEL_MASK 0x00100000 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_ID_SHIFT 24 +#define DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_ID_MASK 0x0f000000 + u32 fw_mb_header; #define FW_MSG_CODE_MASK 0xffff0000 #define FW_MSG_CODE_UNSUPPORTED 0x00000000 diff --git a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c index f380fae8799d..65ec16a31658 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_iwarp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_iwarp.c @@ -382,7 +382,7 @@ qed_iwarp2roce_state(enum qed_iwarp_qp_state state) } } -const static char *iwarp_state_names[] = { +static const char * const iwarp_state_names[] = { "IDLE", "RTS", "TERMINATE", diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 9f36e7948222..1a5fc2ae351c 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -1631,10 +1631,9 @@ static void __qed_get_vport_pstats_addrlen(struct qed_hwfn *p_hwfn, } } -static void __qed_get_vport_pstats(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - struct qed_eth_stats *p_stats, - u16 statistics_bin) +static noinline_for_stack void +__qed_get_vport_pstats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_eth_stats *p_stats, u16 statistics_bin) { struct eth_pstorm_per_queue_stat pstats; u32 pstats_addr = 0, pstats_len = 0; @@ -1661,10 +1660,9 @@ static void __qed_get_vport_pstats(struct qed_hwfn *p_hwfn, HILO_64_REGPAIR(pstats.error_drop_pkts); } -static void __qed_get_vport_tstats(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - struct qed_eth_stats *p_stats, - u16 statistics_bin) +static noinline_for_stack void +__qed_get_vport_tstats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_eth_stats *p_stats, u16 statistics_bin) { struct tstorm_per_port_stat tstats; u32 tstats_addr, tstats_len; @@ -1709,10 +1707,9 @@ static void __qed_get_vport_ustats_addrlen(struct qed_hwfn *p_hwfn, } } -static void __qed_get_vport_ustats(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - struct qed_eth_stats *p_stats, - u16 statistics_bin) +static noinline_for_stack +void __qed_get_vport_ustats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_eth_stats *p_stats, u16 statistics_bin) { struct eth_ustorm_per_queue_stat ustats; u32 ustats_addr = 0, ustats_len = 0; @@ -1751,10 +1748,9 @@ static void __qed_get_vport_mstats_addrlen(struct qed_hwfn *p_hwfn, } } -static void __qed_get_vport_mstats(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - struct qed_eth_stats *p_stats, - u16 statistics_bin) +static noinline_for_stack void +__qed_get_vport_mstats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_eth_stats *p_stats, u16 statistics_bin) { struct eth_mstorm_per_queue_stat mstats; u32 mstats_addr = 0, mstats_len = 0; @@ -1780,9 +1776,9 @@ static void __qed_get_vport_mstats(struct qed_hwfn *p_hwfn, HILO_64_REGPAIR(mstats.tpa_coalesced_bytes); } -static void __qed_get_vport_port_stats(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, - struct qed_eth_stats *p_stats) +static noinline_for_stack void +__qed_get_vport_port_stats(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + struct qed_eth_stats *p_stats) { struct qed_eth_stats_common *p_common = &p_stats->common; struct port_stats port_stats; diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 1efff7f68ef6..2ce70097d018 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -67,6 +67,10 @@ #define QED_ROCE_QPS (8192) #define QED_ROCE_DPIS (8) #define QED_RDMA_SRQS QED_ROCE_QPS +#define QED_NVM_CFG_SET_FLAGS 0xE +#define QED_NVM_CFG_SET_PF_FLAGS 0x1E +#define QED_NVM_CFG_GET_FLAGS 0xA +#define QED_NVM_CFG_GET_PF_FLAGS 0x1A static char version[] = "QLogic FastLinQ 4xxxx Core Module qed " DRV_MODULE_VERSION "\n"; @@ -1690,6 +1694,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, switch (media_type) { case MEDIA_DA_TWINAX: + *if_capability |= QED_LM_FIBRE_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) *if_capability |= QED_LM_20000baseKR2_Full_BIT; /* For DAC media multiple speed capabilities are supported*/ @@ -1709,6 +1714,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, *if_capability |= QED_LM_100000baseCR4_Full_BIT; break; case MEDIA_BASE_T: + *if_capability |= QED_LM_TP_BIT; if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_EXT_PHY) { if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) { @@ -1720,6 +1726,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, } } if (board_cfg & NVM_CFG1_PORT_PORT_TYPE_MODULE) { + *if_capability |= QED_LM_FIBRE_BIT; if (tcvr_type == ETH_TRANSCEIVER_TYPE_1000BASET) *if_capability |= QED_LM_1000baseT_Full_BIT; if (tcvr_type == ETH_TRANSCEIVER_TYPE_10G_BASET) @@ -1730,6 +1737,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, case MEDIA_SFPP_10G_FIBER: case MEDIA_XFP_FIBER: case MEDIA_MODULE_FIBER: + *if_capability |= QED_LM_FIBRE_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_1G) { if ((tcvr_type == ETH_TRANSCEIVER_TYPE_1G_LX) || @@ -1772,6 +1780,7 @@ static void qed_fill_link_capability(struct qed_hwfn *hwfn, break; case MEDIA_KR: + *if_capability |= QED_LM_Backplane_BIT; if (capability & NVM_CFG1_PORT_DRV_SPEED_CAPABILITY_MASK_20G) *if_capability |= QED_LM_20000baseKR2_Full_BIT; if (capability & @@ -1823,7 +1832,6 @@ static void qed_fill_link(struct qed_hwfn *hwfn, if_link->link_up = true; /* TODO - at the moment assume supported and advertised speed equal */ - if_link->supported_caps = QED_LM_FIBRE_BIT; if (link_caps.default_speed_autoneg) if_link->supported_caps |= QED_LM_Autoneg_BIT; if (params.pause.autoneg || @@ -2229,6 +2237,119 @@ static int qed_nvm_flash_image_validate(struct qed_dev *cdev, return 0; } +/* Binary file format - + * /----------------------------------------------------------------------\ + * 0B | 0x5 [command index] | + * 4B | Number of config attributes | Reserved | + * 4B | Config ID | Entity ID | Length | + * 4B | Value | + * | | + * \----------------------------------------------------------------------/ + * There can be several cfg_id-entity_id-Length-Value sets as specified by + * 'Number of config attributes'. + * + * The API parses config attributes from the user provided buffer and flashes + * them to the respective NVM path using Management FW inerface. + */ +static int qed_nvm_flash_cfg_write(struct qed_dev *cdev, const u8 **data) +{ + struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); + u8 entity_id, len, buf[32]; + struct qed_ptt *ptt; + u16 cfg_id, count; + int rc = 0, i; + u32 flags; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) + return -EAGAIN; + + /* NVM CFG ID attribute header */ + *data += 4; + count = *((u16 *)*data); + *data += 4; + + DP_VERBOSE(cdev, NETIF_MSG_DRV, + "Read config ids: num_attrs = %0d\n", count); + /* NVM CFG ID attributes */ + for (i = 0; i < count; i++) { + cfg_id = *((u16 *)*data); + *data += 2; + entity_id = **data; + (*data)++; + len = **data; + (*data)++; + memcpy(buf, *data, len); + *data += len; + + flags = entity_id ? QED_NVM_CFG_SET_PF_FLAGS : + QED_NVM_CFG_SET_FLAGS; + + DP_VERBOSE(cdev, NETIF_MSG_DRV, + "cfg_id = %d entity = %d len = %d\n", cfg_id, + entity_id, len); + rc = qed_mcp_nvm_set_cfg(hwfn, ptt, cfg_id, entity_id, flags, + buf, len); + if (rc) { + DP_ERR(cdev, "Error %d configuring %d\n", rc, cfg_id); + break; + } + } + + qed_ptt_release(hwfn, ptt); + + return rc; +} + +#define QED_MAX_NVM_BUF_LEN 32 +static int qed_nvm_flash_cfg_len(struct qed_dev *cdev, u32 cmd) +{ + struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); + u8 buf[QED_MAX_NVM_BUF_LEN]; + struct qed_ptt *ptt; + u32 len; + int rc; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) + return QED_MAX_NVM_BUF_LEN; + + rc = qed_mcp_nvm_get_cfg(hwfn, ptt, cmd, 0, QED_NVM_CFG_GET_FLAGS, buf, + &len); + if (rc || !len) { + DP_ERR(cdev, "Error %d reading %d\n", rc, cmd); + len = QED_MAX_NVM_BUF_LEN; + } + + qed_ptt_release(hwfn, ptt); + + return len; +} + +static int qed_nvm_flash_cfg_read(struct qed_dev *cdev, u8 **data, + u32 cmd, u32 entity_id) +{ + struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); + struct qed_ptt *ptt; + u32 flags, len; + int rc = 0; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) + return -EAGAIN; + + DP_VERBOSE(cdev, NETIF_MSG_DRV, + "Read config cmd = %d entity id %d\n", cmd, entity_id); + flags = entity_id ? QED_NVM_CFG_GET_PF_FLAGS : QED_NVM_CFG_GET_FLAGS; + rc = qed_mcp_nvm_get_cfg(hwfn, ptt, cmd, entity_id, flags, *data, &len); + if (rc) + DP_ERR(cdev, "Error %d reading %d\n", rc, cmd); + + qed_ptt_release(hwfn, ptt); + + return rc; +} + static int qed_nvm_flash(struct qed_dev *cdev, const char *name) { const struct firmware *image; @@ -2270,6 +2391,9 @@ static int qed_nvm_flash(struct qed_dev *cdev, const char *name) rc = qed_nvm_flash_image_access(cdev, &data, &check_resp); break; + case QED_NVM_FLASH_CMD_NVM_CFG_ID: + rc = qed_nvm_flash_cfg_write(cdev, &data); + break; default: DP_ERR(cdev, "Unknown command %08x\n", cmd_type); rc = -EINVAL; @@ -2485,6 +2609,26 @@ static int qed_read_module_eeprom(struct qed_dev *cdev, char *buf, return rc; } +static int qed_set_grc_config(struct qed_dev *cdev, u32 cfg_id, u32 val) +{ + struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); + struct qed_ptt *ptt; + int rc = 0; + + if (IS_VF(cdev)) + return 0; + + ptt = qed_ptt_acquire(hwfn); + if (!ptt) + return -EAGAIN; + + rc = qed_dbg_grc_config(hwfn, ptt, cfg_id, val); + + qed_ptt_release(hwfn, ptt); + + return rc; +} + static u8 qed_get_affin_hwfn_idx(struct qed_dev *cdev) { return QED_AFFIN_HWFN_IDX(cdev); @@ -2538,6 +2682,9 @@ const struct qed_common_ops qed_common_ops_pass = { .db_recovery_del = &qed_db_recovery_del, .read_module_eeprom = &qed_read_module_eeprom, .get_affin_hwfn_idx = &qed_get_affin_hwfn_idx, + .read_nvm_cfg = &qed_nvm_flash_cfg_read, + .read_nvm_cfg_len = &qed_nvm_flash_cfg_len, + .set_grc_config = &qed_set_grc_config, }; void qed_get_protocol_stats(struct qed_dev *cdev, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index 758702c1ce9c..36ddb89856a8 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -3750,3 +3750,64 @@ int qed_mcp_get_ppfid_bitmap(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) return 0; } + +int qed_mcp_nvm_get_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, + u32 *p_len) +{ + u32 mb_param = 0, resp, param; + int rc; + + QED_MFW_SET_FIELD(mb_param, DRV_MB_PARAM_NVM_CFG_OPTION_ID, option_id); + if (flags & QED_NVM_CFG_OPTION_INIT) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_INIT, 1); + if (flags & QED_NVM_CFG_OPTION_FREE) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_FREE, 1); + if (flags & QED_NVM_CFG_OPTION_ENTITY_SEL) { + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_SEL, 1); + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_ID, + entity_id); + } + + rc = qed_mcp_nvm_rd_cmd(p_hwfn, p_ptt, + DRV_MSG_CODE_GET_NVM_CFG_OPTION, + mb_param, &resp, ¶m, p_len, (u32 *)p_buf); + + return rc; +} + +int qed_mcp_nvm_set_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, + u32 len) +{ + u32 mb_param = 0, resp, param; + + QED_MFW_SET_FIELD(mb_param, DRV_MB_PARAM_NVM_CFG_OPTION_ID, option_id); + if (flags & QED_NVM_CFG_OPTION_ALL) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_ALL, 1); + if (flags & QED_NVM_CFG_OPTION_INIT) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_INIT, 1); + if (flags & QED_NVM_CFG_OPTION_COMMIT) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_COMMIT, 1); + if (flags & QED_NVM_CFG_OPTION_FREE) + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_FREE, 1); + if (flags & QED_NVM_CFG_OPTION_ENTITY_SEL) { + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_SEL, 1); + QED_MFW_SET_FIELD(mb_param, + DRV_MB_PARAM_NVM_CFG_OPTION_ENTITY_ID, + entity_id); + } + + return qed_mcp_nvm_wr_cmd(p_hwfn, p_ptt, + DRV_MSG_CODE_SET_NVM_CFG_OPTION, + mb_param, &resp, ¶m, len, (u32 *)p_buf); +} diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index e4f8fe4bd062..9c4c2763de8d 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -251,6 +251,12 @@ union qed_mfw_tlv_data { struct qed_mfw_tlv_iscsi iscsi; }; +#define QED_NVM_CFG_OPTION_ALL BIT(0) +#define QED_NVM_CFG_OPTION_INIT BIT(1) +#define QED_NVM_CFG_OPTION_COMMIT BIT(2) +#define QED_NVM_CFG_OPTION_FREE BIT(3) +#define QED_NVM_CFG_OPTION_ENTITY_SEL BIT(4) + /** * @brief - returns the link params of the hw function * @@ -1202,4 +1208,33 @@ int qed_mcp_get_engine_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); */ int qed_mcp_get_ppfid_bitmap(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); +/** + * @brief Get NVM config attribute value. + * + * @param p_hwfn + * @param p_ptt + * @param option_id + * @param entity_id + * @param flags + * @param p_buf + * @param p_len + */ +int qed_mcp_nvm_get_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, + u32 *p_len); + +/** + * @brief Set NVM config attribute value. + * + * @param p_hwfn + * @param p_ptt + * @param option_id + * @param entity_id + * @param flags + * @param p_buf + * @param len + */ +int qed_mcp_nvm_set_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, + u16 option_id, u8 entity_id, u16 flags, u8 *p_buf, + u32 len); #endif diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 5dda547772c1..856051f50eb7 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -231,7 +231,7 @@ static void qed_vf_pf_acquire_reduce_resc(struct qed_hwfn *p_hwfn, { DP_VERBOSE(p_hwfn, QED_MSG_IOV, - "PF unwilling to fullill resource request: rxq [%02x/%02x] txq [%02x/%02x] sbs [%02x/%02x] mac [%02x/%02x] vlan [%02x/%02x] mc [%02x/%02x] cids [%02x/%02x]. Try PF recommended amount\n", + "PF unwilling to fulfill resource request: rxq [%02x/%02x] txq [%02x/%02x] sbs [%02x/%02x] mac [%02x/%02x] vlan [%02x/%02x] mc [%02x/%02x] cids [%02x/%02x]. Try PF recommended amount\n", p_req->num_rxqs, p_resp->num_rxqs, p_req->num_rxqs, diff --git a/drivers/net/ethernet/qlogic/qede/qede.h b/drivers/net/ethernet/qlogic/qede/qede.h index 0e931c04fecf..c303a92d5b06 100644 --- a/drivers/net/ethernet/qlogic/qede/qede.h +++ b/drivers/net/ethernet/qlogic/qede/qede.h @@ -177,6 +177,20 @@ enum qede_flags_bit { QEDE_FLAGS_TX_TIMESTAMPING_EN }; +#define QEDE_DUMP_MAX_ARGS 4 +enum qede_dump_cmd { + QEDE_DUMP_CMD_NONE = 0, + QEDE_DUMP_CMD_NVM_CFG, + QEDE_DUMP_CMD_GRCDUMP, + QEDE_DUMP_CMD_MAX +}; + +struct qede_dump_info { + enum qede_dump_cmd cmd; + u8 num_args; + u32 args[QEDE_DUMP_MAX_ARGS]; +}; + struct qede_dev { struct qed_dev *cdev; struct net_device *ndev; @@ -262,6 +276,7 @@ struct qede_dev { struct qede_rdma_dev rdma_info; struct bpf_prog *xdp_prog; + struct qede_dump_info dump_info; }; enum QEDE_STATE { diff --git a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c index e85f9fef930c..8a426afb6a55 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_ethtool.c +++ b/drivers/net/ethernet/qlogic/qede/qede_ethtool.c @@ -48,6 +48,8 @@ {QEDE_RQSTAT_OFFSET(stat_name), QEDE_RQSTAT_STRING(stat_name)} #define QEDE_SELFTEST_POLL_COUNT 100 +#define QEDE_DUMP_VERSION 0x1 +#define QEDE_DUMP_NVM_ARG_COUNT 2 static const struct { u64 offset; @@ -424,12 +426,13 @@ struct qede_link_mode_mapping { }; static const struct qede_link_mode_mapping qed_lm_map[] = { + {QED_LM_FIBRE_BIT, ETHTOOL_LINK_MODE_FIBRE_BIT}, {QED_LM_Autoneg_BIT, ETHTOOL_LINK_MODE_Autoneg_BIT}, {QED_LM_Asym_Pause_BIT, ETHTOOL_LINK_MODE_Asym_Pause_BIT}, {QED_LM_Pause_BIT, ETHTOOL_LINK_MODE_Pause_BIT}, {QED_LM_1000baseT_Full_BIT, ETHTOOL_LINK_MODE_1000baseT_Full_BIT}, {QED_LM_10000baseT_Full_BIT, ETHTOOL_LINK_MODE_10000baseT_Full_BIT}, - {QED_LM_2500baseX_Full_BIT, ETHTOOL_LINK_MODE_2500baseX_Full_BIT}, + {QED_LM_TP_BIT, ETHTOOL_LINK_MODE_TP_BIT}, {QED_LM_Backplane_BIT, ETHTOOL_LINK_MODE_Backplane_BIT}, {QED_LM_1000baseKX_Full_BIT, ETHTOOL_LINK_MODE_1000baseKX_Full_BIT}, {QED_LM_10000baseKX4_Full_BIT, ETHTOOL_LINK_MODE_10000baseKX4_Full_BIT}, @@ -1972,6 +1975,117 @@ static int qede_get_module_eeprom(struct net_device *dev, return rc; } +static int qede_set_dump(struct net_device *dev, struct ethtool_dump *val) +{ + struct qede_dev *edev = netdev_priv(dev); + int rc = 0; + + if (edev->dump_info.cmd == QEDE_DUMP_CMD_NONE) { + if (val->flag > QEDE_DUMP_CMD_MAX) { + DP_ERR(edev, "Invalid command %d\n", val->flag); + return -EINVAL; + } + edev->dump_info.cmd = val->flag; + edev->dump_info.num_args = 0; + return 0; + } + + if (edev->dump_info.num_args == QEDE_DUMP_MAX_ARGS) { + DP_ERR(edev, "Arg count = %d\n", edev->dump_info.num_args); + return -EINVAL; + } + + switch (edev->dump_info.cmd) { + case QEDE_DUMP_CMD_NVM_CFG: + edev->dump_info.args[edev->dump_info.num_args] = val->flag; + edev->dump_info.num_args++; + break; + case QEDE_DUMP_CMD_GRCDUMP: + rc = edev->ops->common->set_grc_config(edev->cdev, + val->flag, 1); + break; + default: + break; + } + + return rc; +} + +static int qede_get_dump_flag(struct net_device *dev, + struct ethtool_dump *dump) +{ + struct qede_dev *edev = netdev_priv(dev); + + if (!edev->ops || !edev->ops->common) { + DP_ERR(edev, "Edev ops not populated\n"); + return -EINVAL; + } + + dump->version = QEDE_DUMP_VERSION; + switch (edev->dump_info.cmd) { + case QEDE_DUMP_CMD_NVM_CFG: + dump->flag = QEDE_DUMP_CMD_NVM_CFG; + dump->len = edev->ops->common->read_nvm_cfg_len(edev->cdev, + edev->dump_info.args[0]); + break; + case QEDE_DUMP_CMD_GRCDUMP: + dump->flag = QEDE_DUMP_CMD_GRCDUMP; + dump->len = edev->ops->common->dbg_all_data_size(edev->cdev); + break; + default: + DP_ERR(edev, "Invalid cmd = %d\n", edev->dump_info.cmd); + return -EINVAL; + } + + DP_VERBOSE(edev, QED_MSG_DEBUG, + "dump->version = 0x%x dump->flag = %d dump->len = %d\n", + dump->version, dump->flag, dump->len); + return 0; +} + +static int qede_get_dump_data(struct net_device *dev, + struct ethtool_dump *dump, void *buf) +{ + struct qede_dev *edev = netdev_priv(dev); + int rc = 0; + + if (!edev->ops || !edev->ops->common) { + DP_ERR(edev, "Edev ops not populated\n"); + rc = -EINVAL; + goto err; + } + + switch (edev->dump_info.cmd) { + case QEDE_DUMP_CMD_NVM_CFG: + if (edev->dump_info.num_args != QEDE_DUMP_NVM_ARG_COUNT) { + DP_ERR(edev, "Arg count = %d required = %d\n", + edev->dump_info.num_args, + QEDE_DUMP_NVM_ARG_COUNT); + rc = -EINVAL; + goto err; + } + rc = edev->ops->common->read_nvm_cfg(edev->cdev, (u8 **)&buf, + edev->dump_info.args[0], + edev->dump_info.args[1]); + break; + case QEDE_DUMP_CMD_GRCDUMP: + memset(buf, 0, dump->len); + rc = edev->ops->common->dbg_all_data(edev->cdev, buf); + break; + default: + DP_ERR(edev, "Invalid cmd = %d\n", edev->dump_info.cmd); + rc = -EINVAL; + break; + } + +err: + edev->dump_info.cmd = QEDE_DUMP_CMD_NONE; + edev->dump_info.num_args = 0; + memset(edev->dump_info.args, 0, sizeof(edev->dump_info.args)); + + return rc; +} + static const struct ethtool_ops qede_ethtool_ops = { .get_link_ksettings = qede_get_link_ksettings, .set_link_ksettings = qede_set_link_ksettings, @@ -2013,6 +2127,9 @@ static const struct ethtool_ops qede_ethtool_ops = { .get_tunable = qede_get_tunable, .set_tunable = qede_set_tunable, .flash_device = qede_flash_device, + .get_dump_flag = qede_get_dump_flag, + .get_dump_data = qede_get_dump_data, + .set_dump = qede_set_dump, }; static const struct ethtool_ops qede_vf_ethtool_ops = { diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c index 14f26bf3b388..ac61f614de37 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_io.c @@ -581,7 +581,7 @@ static int qlcnic_map_tx_skb(struct pci_dev *pdev, struct sk_buff *skb, struct qlcnic_cmd_buffer *pbuf) { struct qlcnic_skb_frag *nf; - struct skb_frag_struct *frag; + skb_frag_t *frag; int i, nr_frags; dma_addr_t map; diff --git a/drivers/net/ethernet/qlogic/qlge/Makefile b/drivers/net/ethernet/qlogic/qlge/Makefile deleted file mode 100644 index 1dc2568e820c..000000000000 --- a/drivers/net/ethernet/qlogic/qlge/Makefile +++ /dev/null @@ -1,8 +0,0 @@ -# SPDX-License-Identifier: GPL-2.0-only -# -# Makefile for the Qlogic 10GbE PCI Express ethernet driver -# - -obj-$(CONFIG_QLGE) += qlge.o - -qlge-objs := qlge_main.o qlge_dbg.o qlge_mpi.o qlge_ethtool.o diff --git a/drivers/net/ethernet/qlogic/qlge/qlge.h b/drivers/net/ethernet/qlogic/qlge/qlge.h deleted file mode 100644 index ad7c5eb8a3b6..000000000000 --- a/drivers/net/ethernet/qlogic/qlge/qlge.h +++ /dev/null @@ -1,2353 +0,0 @@ -/* - * QLogic QLA41xx NIC HBA Driver - * Copyright (c) 2003-2006 QLogic Corporation - * - * See LICENSE.qlge for copyright and licensing details. - */ -#ifndef _QLGE_H_ -#define _QLGE_H_ - -#include <linux/interrupt.h> -#include <linux/pci.h> -#include <linux/netdevice.h> -#include <linux/rtnetlink.h> -#include <linux/if_vlan.h> - -/* - * General definitions... - */ -#define DRV_NAME "qlge" -#define DRV_STRING "QLogic 10 Gigabit PCI-E Ethernet Driver " -#define DRV_VERSION "1.00.00.35" - -#define WQ_ADDR_ALIGN 0x3 /* 4 byte alignment */ - -#define QLGE_VENDOR_ID 0x1077 -#define QLGE_DEVICE_ID_8012 0x8012 -#define QLGE_DEVICE_ID_8000 0x8000 -#define QLGE_MEZZ_SSYS_ID_068 0x0068 -#define QLGE_MEZZ_SSYS_ID_180 0x0180 -#define MAX_CPUS 8 -#define MAX_TX_RINGS MAX_CPUS -#define MAX_RX_RINGS ((MAX_CPUS * 2) + 1) - -#define NUM_TX_RING_ENTRIES 256 -#define NUM_RX_RING_ENTRIES 256 - -#define NUM_SMALL_BUFFERS 512 -#define NUM_LARGE_BUFFERS 512 -#define DB_PAGE_SIZE 4096 - -/* Calculate the number of (4k) pages required to - * contain a buffer queue of the given length. - */ -#define MAX_DB_PAGES_PER_BQ(x) \ - (((x * sizeof(u64)) / DB_PAGE_SIZE) + \ - (((x * sizeof(u64)) % DB_PAGE_SIZE) ? 1 : 0)) - -#define RX_RING_SHADOW_SPACE (sizeof(u64) + \ - MAX_DB_PAGES_PER_BQ(NUM_SMALL_BUFFERS) * sizeof(u64) + \ - MAX_DB_PAGES_PER_BQ(NUM_LARGE_BUFFERS) * sizeof(u64)) -#define LARGE_BUFFER_MAX_SIZE 8192 -#define LARGE_BUFFER_MIN_SIZE 2048 - -#define MAX_CQ 128 -#define DFLT_COALESCE_WAIT 100 /* 100 usec wait for coalescing */ -#define MAX_INTER_FRAME_WAIT 10 /* 10 usec max interframe-wait for coalescing */ -#define DFLT_INTER_FRAME_WAIT (MAX_INTER_FRAME_WAIT/2) -#define UDELAY_COUNT 3 -#define UDELAY_DELAY 100 - - -#define TX_DESC_PER_IOCB 8 - -#if ((MAX_SKB_FRAGS - TX_DESC_PER_IOCB) + 2) > 0 -#define TX_DESC_PER_OAL ((MAX_SKB_FRAGS - TX_DESC_PER_IOCB) + 2) -#else /* all other page sizes */ -#define TX_DESC_PER_OAL 0 -#endif - -/* Word shifting for converting 64-bit - * address to a series of 16-bit words. - * This is used for some MPI firmware - * mailbox commands. - */ -#define LSW(x) ((u16)(x)) -#define MSW(x) ((u16)((u32)(x) >> 16)) -#define LSD(x) ((u32)((u64)(x))) -#define MSD(x) ((u32)((((u64)(x)) >> 32))) - -/* MPI test register definitions. This register - * is used for determining alternate NIC function's - * PCI->func number. - */ -enum { - MPI_TEST_FUNC_PORT_CFG = 0x1002, - MPI_TEST_FUNC_PRB_CTL = 0x100e, - MPI_TEST_FUNC_PRB_EN = 0x18a20000, - MPI_TEST_FUNC_RST_STS = 0x100a, - MPI_TEST_FUNC_RST_FRC = 0x00000003, - MPI_TEST_NIC_FUNC_MASK = 0x00000007, - MPI_TEST_NIC1_FUNCTION_ENABLE = (1 << 0), - MPI_TEST_NIC1_FUNCTION_MASK = 0x0000000e, - MPI_TEST_NIC1_FUNC_SHIFT = 1, - MPI_TEST_NIC2_FUNCTION_ENABLE = (1 << 4), - MPI_TEST_NIC2_FUNCTION_MASK = 0x000000e0, - MPI_TEST_NIC2_FUNC_SHIFT = 5, - MPI_TEST_FC1_FUNCTION_ENABLE = (1 << 8), - MPI_TEST_FC1_FUNCTION_MASK = 0x00000e00, - MPI_TEST_FC1_FUNCTION_SHIFT = 9, - MPI_TEST_FC2_FUNCTION_ENABLE = (1 << 12), - MPI_TEST_FC2_FUNCTION_MASK = 0x0000e000, - MPI_TEST_FC2_FUNCTION_SHIFT = 13, - - MPI_NIC_READ = 0x00000000, - MPI_NIC_REG_BLOCK = 0x00020000, - MPI_NIC_FUNCTION_SHIFT = 6, -}; - -/* - * Processor Address Register (PROC_ADDR) bit definitions. - */ -enum { - - /* Misc. stuff */ - MAILBOX_COUNT = 16, - MAILBOX_TIMEOUT = 5, - - PROC_ADDR_RDY = (1 << 31), - PROC_ADDR_R = (1 << 30), - PROC_ADDR_ERR = (1 << 29), - PROC_ADDR_DA = (1 << 28), - PROC_ADDR_FUNC0_MBI = 0x00001180, - PROC_ADDR_FUNC0_MBO = (PROC_ADDR_FUNC0_MBI + MAILBOX_COUNT), - PROC_ADDR_FUNC0_CTL = 0x000011a1, - PROC_ADDR_FUNC2_MBI = 0x00001280, - PROC_ADDR_FUNC2_MBO = (PROC_ADDR_FUNC2_MBI + MAILBOX_COUNT), - PROC_ADDR_FUNC2_CTL = 0x000012a1, - PROC_ADDR_MPI_RISC = 0x00000000, - PROC_ADDR_MDE = 0x00010000, - PROC_ADDR_REGBLOCK = 0x00020000, - PROC_ADDR_RISC_REG = 0x00030000, -}; - -/* - * System Register (SYS) bit definitions. - */ -enum { - SYS_EFE = (1 << 0), - SYS_FAE = (1 << 1), - SYS_MDC = (1 << 2), - SYS_DST = (1 << 3), - SYS_DWC = (1 << 4), - SYS_EVW = (1 << 5), - SYS_OMP_DLY_MASK = 0x3f000000, - /* - * There are no values defined as of edit #15. - */ - SYS_ODI = (1 << 14), -}; - -/* - * Reset/Failover Register (RST_FO) bit definitions. - */ -enum { - RST_FO_TFO = (1 << 0), - RST_FO_RR_MASK = 0x00060000, - RST_FO_RR_CQ_CAM = 0x00000000, - RST_FO_RR_DROP = 0x00000002, - RST_FO_RR_DQ = 0x00000004, - RST_FO_RR_RCV_FUNC_CQ = 0x00000006, - RST_FO_FRB = (1 << 12), - RST_FO_MOP = (1 << 13), - RST_FO_REG = (1 << 14), - RST_FO_FR = (1 << 15), -}; - -/* - * Function Specific Control Register (FSC) bit definitions. - */ -enum { - FSC_DBRST_MASK = 0x00070000, - FSC_DBRST_256 = 0x00000000, - FSC_DBRST_512 = 0x00000001, - FSC_DBRST_768 = 0x00000002, - FSC_DBRST_1024 = 0x00000003, - FSC_DBL_MASK = 0x00180000, - FSC_DBL_DBRST = 0x00000000, - FSC_DBL_MAX_PLD = 0x00000008, - FSC_DBL_MAX_BRST = 0x00000010, - FSC_DBL_128_BYTES = 0x00000018, - FSC_EC = (1 << 5), - FSC_EPC_MASK = 0x00c00000, - FSC_EPC_INBOUND = (1 << 6), - FSC_EPC_OUTBOUND = (1 << 7), - FSC_VM_PAGESIZE_MASK = 0x07000000, - FSC_VM_PAGE_2K = 0x00000100, - FSC_VM_PAGE_4K = 0x00000200, - FSC_VM_PAGE_8K = 0x00000300, - FSC_VM_PAGE_64K = 0x00000600, - FSC_SH = (1 << 11), - FSC_DSB = (1 << 12), - FSC_STE = (1 << 13), - FSC_FE = (1 << 15), -}; - -/* - * Host Command Status Register (CSR) bit definitions. - */ -enum { - CSR_ERR_STS_MASK = 0x0000003f, - /* - * There are no valued defined as of edit #15. - */ - CSR_RR = (1 << 8), - CSR_HRI = (1 << 9), - CSR_RP = (1 << 10), - CSR_CMD_PARM_SHIFT = 22, - CSR_CMD_NOP = 0x00000000, - CSR_CMD_SET_RST = 0x10000000, - CSR_CMD_CLR_RST = 0x20000000, - CSR_CMD_SET_PAUSE = 0x30000000, - CSR_CMD_CLR_PAUSE = 0x40000000, - CSR_CMD_SET_H2R_INT = 0x50000000, - CSR_CMD_CLR_H2R_INT = 0x60000000, - CSR_CMD_PAR_EN = 0x70000000, - CSR_CMD_SET_BAD_PAR = 0x80000000, - CSR_CMD_CLR_BAD_PAR = 0x90000000, - CSR_CMD_CLR_R2PCI_INT = 0xa0000000, -}; - -/* - * Configuration Register (CFG) bit definitions. - */ -enum { - CFG_LRQ = (1 << 0), - CFG_DRQ = (1 << 1), - CFG_LR = (1 << 2), - CFG_DR = (1 << 3), - CFG_LE = (1 << 5), - CFG_LCQ = (1 << 6), - CFG_DCQ = (1 << 7), - CFG_Q_SHIFT = 8, - CFG_Q_MASK = 0x7f000000, -}; - -/* - * Status Register (STS) bit definitions. - */ -enum { - STS_FE = (1 << 0), - STS_PI = (1 << 1), - STS_PL0 = (1 << 2), - STS_PL1 = (1 << 3), - STS_PI0 = (1 << 4), - STS_PI1 = (1 << 5), - STS_FUNC_ID_MASK = 0x000000c0, - STS_FUNC_ID_SHIFT = 6, - STS_F0E = (1 << 8), - STS_F1E = (1 << 9), - STS_F2E = (1 << 10), - STS_F3E = (1 << 11), - STS_NFE = (1 << 12), -}; - -/* - * Interrupt Enable Register (INTR_EN) bit definitions. - */ -enum { - INTR_EN_INTR_MASK = 0x007f0000, - INTR_EN_TYPE_MASK = 0x03000000, - INTR_EN_TYPE_ENABLE = 0x00000100, - INTR_EN_TYPE_DISABLE = 0x00000200, - INTR_EN_TYPE_READ = 0x00000300, - INTR_EN_IHD = (1 << 13), - INTR_EN_IHD_MASK = (INTR_EN_IHD << 16), - INTR_EN_EI = (1 << 14), - INTR_EN_EN = (1 << 15), -}; - -/* - * Interrupt Mask Register (INTR_MASK) bit definitions. - */ -enum { - INTR_MASK_PI = (1 << 0), - INTR_MASK_HL0 = (1 << 1), - INTR_MASK_LH0 = (1 << 2), - INTR_MASK_HL1 = (1 << 3), - INTR_MASK_LH1 = (1 << 4), - INTR_MASK_SE = (1 << 5), - INTR_MASK_LSC = (1 << 6), - INTR_MASK_MC = (1 << 7), - INTR_MASK_LINK_IRQS = INTR_MASK_LSC | INTR_MASK_SE | INTR_MASK_MC, -}; - -/* - * Register (REV_ID) bit definitions. - */ -enum { - REV_ID_MASK = 0x0000000f, - REV_ID_NICROLL_SHIFT = 0, - REV_ID_NICREV_SHIFT = 4, - REV_ID_XGROLL_SHIFT = 8, - REV_ID_XGREV_SHIFT = 12, - REV_ID_CHIPREV_SHIFT = 28, -}; - -/* - * Force ECC Error Register (FRC_ECC_ERR) bit definitions. - */ -enum { - FRC_ECC_ERR_VW = (1 << 12), - FRC_ECC_ERR_VB = (1 << 13), - FRC_ECC_ERR_NI = (1 << 14), - FRC_ECC_ERR_NO = (1 << 15), - FRC_ECC_PFE_SHIFT = 16, - FRC_ECC_ERR_DO = (1 << 18), - FRC_ECC_P14 = (1 << 19), -}; - -/* - * Error Status Register (ERR_STS) bit definitions. - */ -enum { - ERR_STS_NOF = (1 << 0), - ERR_STS_NIF = (1 << 1), - ERR_STS_DRP = (1 << 2), - ERR_STS_XGP = (1 << 3), - ERR_STS_FOU = (1 << 4), - ERR_STS_FOC = (1 << 5), - ERR_STS_FOF = (1 << 6), - ERR_STS_FIU = (1 << 7), - ERR_STS_FIC = (1 << 8), - ERR_STS_FIF = (1 << 9), - ERR_STS_MOF = (1 << 10), - ERR_STS_TA = (1 << 11), - ERR_STS_MA = (1 << 12), - ERR_STS_MPE = (1 << 13), - ERR_STS_SCE = (1 << 14), - ERR_STS_STE = (1 << 15), - ERR_STS_FOW = (1 << 16), - ERR_STS_UE = (1 << 17), - ERR_STS_MCH = (1 << 26), - ERR_STS_LOC_SHIFT = 27, -}; - -/* - * RAM Debug Address Register (RAM_DBG_ADDR) bit definitions. - */ -enum { - RAM_DBG_ADDR_FW = (1 << 30), - RAM_DBG_ADDR_FR = (1 << 31), -}; - -/* - * Semaphore Register (SEM) bit definitions. - */ -enum { - /* - * Example: - * reg = SEM_XGMAC0_MASK | (SEM_SET << SEM_XGMAC0_SHIFT) - */ - SEM_CLEAR = 0, - SEM_SET = 1, - SEM_FORCE = 3, - SEM_XGMAC0_SHIFT = 0, - SEM_XGMAC1_SHIFT = 2, - SEM_ICB_SHIFT = 4, - SEM_MAC_ADDR_SHIFT = 6, - SEM_FLASH_SHIFT = 8, - SEM_PROBE_SHIFT = 10, - SEM_RT_IDX_SHIFT = 12, - SEM_PROC_REG_SHIFT = 14, - SEM_XGMAC0_MASK = 0x00030000, - SEM_XGMAC1_MASK = 0x000c0000, - SEM_ICB_MASK = 0x00300000, - SEM_MAC_ADDR_MASK = 0x00c00000, - SEM_FLASH_MASK = 0x03000000, - SEM_PROBE_MASK = 0x0c000000, - SEM_RT_IDX_MASK = 0x30000000, - SEM_PROC_REG_MASK = 0xc0000000, -}; - -/* - * 10G MAC Address Register (XGMAC_ADDR) bit definitions. - */ -enum { - XGMAC_ADDR_RDY = (1 << 31), - XGMAC_ADDR_R = (1 << 30), - XGMAC_ADDR_XME = (1 << 29), - - /* XGMAC control registers */ - PAUSE_SRC_LO = 0x00000100, - PAUSE_SRC_HI = 0x00000104, - GLOBAL_CFG = 0x00000108, - GLOBAL_CFG_RESET = (1 << 0), - GLOBAL_CFG_JUMBO = (1 << 6), - GLOBAL_CFG_TX_STAT_EN = (1 << 10), - GLOBAL_CFG_RX_STAT_EN = (1 << 11), - TX_CFG = 0x0000010c, - TX_CFG_RESET = (1 << 0), - TX_CFG_EN = (1 << 1), - TX_CFG_PREAM = (1 << 2), - RX_CFG = 0x00000110, - RX_CFG_RESET = (1 << 0), - RX_CFG_EN = (1 << 1), - RX_CFG_PREAM = (1 << 2), - FLOW_CTL = 0x0000011c, - PAUSE_OPCODE = 0x00000120, - PAUSE_TIMER = 0x00000124, - PAUSE_FRM_DEST_LO = 0x00000128, - PAUSE_FRM_DEST_HI = 0x0000012c, - MAC_TX_PARAMS = 0x00000134, - MAC_TX_PARAMS_JUMBO = (1 << 31), - MAC_TX_PARAMS_SIZE_SHIFT = 16, - MAC_RX_PARAMS = 0x00000138, - MAC_SYS_INT = 0x00000144, - MAC_SYS_INT_MASK = 0x00000148, - MAC_MGMT_INT = 0x0000014c, - MAC_MGMT_IN_MASK = 0x00000150, - EXT_ARB_MODE = 0x000001fc, - - /* XGMAC TX statistics registers */ - TX_PKTS = 0x00000200, - TX_BYTES = 0x00000208, - TX_MCAST_PKTS = 0x00000210, - TX_BCAST_PKTS = 0x00000218, - TX_UCAST_PKTS = 0x00000220, - TX_CTL_PKTS = 0x00000228, - TX_PAUSE_PKTS = 0x00000230, - TX_64_PKT = 0x00000238, - TX_65_TO_127_PKT = 0x00000240, - TX_128_TO_255_PKT = 0x00000248, - TX_256_511_PKT = 0x00000250, - TX_512_TO_1023_PKT = 0x00000258, - TX_1024_TO_1518_PKT = 0x00000260, - TX_1519_TO_MAX_PKT = 0x00000268, - TX_UNDERSIZE_PKT = 0x00000270, - TX_OVERSIZE_PKT = 0x00000278, - - /* XGMAC statistics control registers */ - RX_HALF_FULL_DET = 0x000002a0, - TX_HALF_FULL_DET = 0x000002a4, - RX_OVERFLOW_DET = 0x000002a8, - TX_OVERFLOW_DET = 0x000002ac, - RX_HALF_FULL_MASK = 0x000002b0, - TX_HALF_FULL_MASK = 0x000002b4, - RX_OVERFLOW_MASK = 0x000002b8, - TX_OVERFLOW_MASK = 0x000002bc, - STAT_CNT_CTL = 0x000002c0, - STAT_CNT_CTL_CLEAR_TX = (1 << 0), - STAT_CNT_CTL_CLEAR_RX = (1 << 1), - AUX_RX_HALF_FULL_DET = 0x000002d0, - AUX_TX_HALF_FULL_DET = 0x000002d4, - AUX_RX_OVERFLOW_DET = 0x000002d8, - AUX_TX_OVERFLOW_DET = 0x000002dc, - AUX_RX_HALF_FULL_MASK = 0x000002f0, - AUX_TX_HALF_FULL_MASK = 0x000002f4, - AUX_RX_OVERFLOW_MASK = 0x000002f8, - AUX_TX_OVERFLOW_MASK = 0x000002fc, - - /* XGMAC RX statistics registers */ - RX_BYTES = 0x00000300, - RX_BYTES_OK = 0x00000308, - RX_PKTS = 0x00000310, - RX_PKTS_OK = 0x00000318, - RX_BCAST_PKTS = 0x00000320, - RX_MCAST_PKTS = 0x00000328, - RX_UCAST_PKTS = 0x00000330, - RX_UNDERSIZE_PKTS = 0x00000338, - RX_OVERSIZE_PKTS = 0x00000340, - RX_JABBER_PKTS = 0x00000348, - RX_UNDERSIZE_FCERR_PKTS = 0x00000350, - RX_DROP_EVENTS = 0x00000358, - RX_FCERR_PKTS = 0x00000360, - RX_ALIGN_ERR = 0x00000368, - RX_SYMBOL_ERR = 0x00000370, - RX_MAC_ERR = 0x00000378, - RX_CTL_PKTS = 0x00000380, - RX_PAUSE_PKTS = 0x00000388, - RX_64_PKTS = 0x00000390, - RX_65_TO_127_PKTS = 0x00000398, - RX_128_255_PKTS = 0x000003a0, - RX_256_511_PKTS = 0x000003a8, - RX_512_TO_1023_PKTS = 0x000003b0, - RX_1024_TO_1518_PKTS = 0x000003b8, - RX_1519_TO_MAX_PKTS = 0x000003c0, - RX_LEN_ERR_PKTS = 0x000003c8, - - /* XGMAC MDIO control registers */ - MDIO_TX_DATA = 0x00000400, - MDIO_RX_DATA = 0x00000410, - MDIO_CMD = 0x00000420, - MDIO_PHY_ADDR = 0x00000430, - MDIO_PORT = 0x00000440, - MDIO_STATUS = 0x00000450, - - XGMAC_REGISTER_END = 0x00000740, -}; - -/* - * Enhanced Transmission Schedule Registers (NIC_ETS,CNA_ETS) bit definitions. - */ -enum { - ETS_QUEUE_SHIFT = 29, - ETS_REF = (1 << 26), - ETS_RS = (1 << 27), - ETS_P = (1 << 28), - ETS_FC_COS_SHIFT = 23, -}; - -/* - * Flash Address Register (FLASH_ADDR) bit definitions. - */ -enum { - FLASH_ADDR_RDY = (1 << 31), - FLASH_ADDR_R = (1 << 30), - FLASH_ADDR_ERR = (1 << 29), -}; - -/* - * Stop CQ Processing Register (CQ_STOP) bit definitions. - */ -enum { - CQ_STOP_QUEUE_MASK = (0x007f0000), - CQ_STOP_TYPE_MASK = (0x03000000), - CQ_STOP_TYPE_START = 0x00000100, - CQ_STOP_TYPE_STOP = 0x00000200, - CQ_STOP_TYPE_READ = 0x00000300, - CQ_STOP_EN = (1 << 15), -}; - -/* - * MAC Protocol Address Index Register (MAC_ADDR_IDX) bit definitions. - */ -enum { - MAC_ADDR_IDX_SHIFT = 4, - MAC_ADDR_TYPE_SHIFT = 16, - MAC_ADDR_TYPE_COUNT = 10, - MAC_ADDR_TYPE_MASK = 0x000f0000, - MAC_ADDR_TYPE_CAM_MAC = 0x00000000, - MAC_ADDR_TYPE_MULTI_MAC = 0x00010000, - MAC_ADDR_TYPE_VLAN = 0x00020000, - MAC_ADDR_TYPE_MULTI_FLTR = 0x00030000, - MAC_ADDR_TYPE_FC_MAC = 0x00040000, - MAC_ADDR_TYPE_MGMT_MAC = 0x00050000, - MAC_ADDR_TYPE_MGMT_VLAN = 0x00060000, - MAC_ADDR_TYPE_MGMT_V4 = 0x00070000, - MAC_ADDR_TYPE_MGMT_V6 = 0x00080000, - MAC_ADDR_TYPE_MGMT_TU_DP = 0x00090000, - MAC_ADDR_ADR = (1 << 25), - MAC_ADDR_RS = (1 << 26), - MAC_ADDR_E = (1 << 27), - MAC_ADDR_MR = (1 << 30), - MAC_ADDR_MW = (1 << 31), - MAX_MULTICAST_ENTRIES = 32, - - /* Entry count and words per entry - * for each address type in the filter. - */ - MAC_ADDR_MAX_CAM_ENTRIES = 512, - MAC_ADDR_MAX_CAM_WCOUNT = 3, - MAC_ADDR_MAX_MULTICAST_ENTRIES = 32, - MAC_ADDR_MAX_MULTICAST_WCOUNT = 2, - MAC_ADDR_MAX_VLAN_ENTRIES = 4096, - MAC_ADDR_MAX_VLAN_WCOUNT = 1, - MAC_ADDR_MAX_MCAST_FLTR_ENTRIES = 4096, - MAC_ADDR_MAX_MCAST_FLTR_WCOUNT = 1, - MAC_ADDR_MAX_FC_MAC_ENTRIES = 4, - MAC_ADDR_MAX_FC_MAC_WCOUNT = 2, - MAC_ADDR_MAX_MGMT_MAC_ENTRIES = 8, - MAC_ADDR_MAX_MGMT_MAC_WCOUNT = 2, - MAC_ADDR_MAX_MGMT_VLAN_ENTRIES = 16, - MAC_ADDR_MAX_MGMT_VLAN_WCOUNT = 1, - MAC_ADDR_MAX_MGMT_V4_ENTRIES = 4, - MAC_ADDR_MAX_MGMT_V4_WCOUNT = 1, - MAC_ADDR_MAX_MGMT_V6_ENTRIES = 4, - MAC_ADDR_MAX_MGMT_V6_WCOUNT = 4, - MAC_ADDR_MAX_MGMT_TU_DP_ENTRIES = 4, - MAC_ADDR_MAX_MGMT_TU_DP_WCOUNT = 1, -}; - -/* - * MAC Protocol Address Index Register (SPLT_HDR) bit definitions. - */ -enum { - SPLT_HDR_EP = (1 << 31), -}; - -/* - * FCoE Receive Configuration Register (FC_RCV_CFG) bit definitions. - */ -enum { - FC_RCV_CFG_ECT = (1 << 15), - FC_RCV_CFG_DFH = (1 << 20), - FC_RCV_CFG_DVF = (1 << 21), - FC_RCV_CFG_RCE = (1 << 27), - FC_RCV_CFG_RFE = (1 << 28), - FC_RCV_CFG_TEE = (1 << 29), - FC_RCV_CFG_TCE = (1 << 30), - FC_RCV_CFG_TFE = (1 << 31), -}; - -/* - * NIC Receive Configuration Register (NIC_RCV_CFG) bit definitions. - */ -enum { - NIC_RCV_CFG_PPE = (1 << 0), - NIC_RCV_CFG_VLAN_MASK = 0x00060000, - NIC_RCV_CFG_VLAN_ALL = 0x00000000, - NIC_RCV_CFG_VLAN_MATCH_ONLY = 0x00000002, - NIC_RCV_CFG_VLAN_MATCH_AND_NON = 0x00000004, - NIC_RCV_CFG_VLAN_NONE_AND_NON = 0x00000006, - NIC_RCV_CFG_RV = (1 << 3), - NIC_RCV_CFG_DFQ_MASK = (0x7f000000), - NIC_RCV_CFG_DFQ_SHIFT = 8, - NIC_RCV_CFG_DFQ = 0, /* HARDCODE default queue to 0. */ -}; - -/* - * Mgmt Receive Configuration Register (MGMT_RCV_CFG) bit definitions. - */ -enum { - MGMT_RCV_CFG_ARP = (1 << 0), - MGMT_RCV_CFG_DHC = (1 << 1), - MGMT_RCV_CFG_DHS = (1 << 2), - MGMT_RCV_CFG_NP = (1 << 3), - MGMT_RCV_CFG_I6N = (1 << 4), - MGMT_RCV_CFG_I6R = (1 << 5), - MGMT_RCV_CFG_DH6 = (1 << 6), - MGMT_RCV_CFG_UD1 = (1 << 7), - MGMT_RCV_CFG_UD0 = (1 << 8), - MGMT_RCV_CFG_BCT = (1 << 9), - MGMT_RCV_CFG_MCT = (1 << 10), - MGMT_RCV_CFG_DM = (1 << 11), - MGMT_RCV_CFG_RM = (1 << 12), - MGMT_RCV_CFG_STL = (1 << 13), - MGMT_RCV_CFG_VLAN_MASK = 0xc0000000, - MGMT_RCV_CFG_VLAN_ALL = 0x00000000, - MGMT_RCV_CFG_VLAN_MATCH_ONLY = 0x00004000, - MGMT_RCV_CFG_VLAN_MATCH_AND_NON = 0x00008000, - MGMT_RCV_CFG_VLAN_NONE_AND_NON = 0x0000c000, -}; - -/* - * Routing Index Register (RT_IDX) bit definitions. - */ -enum { - RT_IDX_IDX_SHIFT = 8, - RT_IDX_TYPE_MASK = 0x000f0000, - RT_IDX_TYPE_SHIFT = 16, - RT_IDX_TYPE_RT = 0x00000000, - RT_IDX_TYPE_RT_INV = 0x00010000, - RT_IDX_TYPE_NICQ = 0x00020000, - RT_IDX_TYPE_NICQ_INV = 0x00030000, - RT_IDX_DST_MASK = 0x00700000, - RT_IDX_DST_RSS = 0x00000000, - RT_IDX_DST_CAM_Q = 0x00100000, - RT_IDX_DST_COS_Q = 0x00200000, - RT_IDX_DST_DFLT_Q = 0x00300000, - RT_IDX_DST_DEST_Q = 0x00400000, - RT_IDX_RS = (1 << 26), - RT_IDX_E = (1 << 27), - RT_IDX_MR = (1 << 30), - RT_IDX_MW = (1 << 31), - - /* Nic Queue format - type 2 bits */ - RT_IDX_BCAST = (1 << 0), - RT_IDX_MCAST = (1 << 1), - RT_IDX_MCAST_MATCH = (1 << 2), - RT_IDX_MCAST_REG_MATCH = (1 << 3), - RT_IDX_MCAST_HASH_MATCH = (1 << 4), - RT_IDX_FC_MACH = (1 << 5), - RT_IDX_ETH_FCOE = (1 << 6), - RT_IDX_CAM_HIT = (1 << 7), - RT_IDX_CAM_BIT0 = (1 << 8), - RT_IDX_CAM_BIT1 = (1 << 9), - RT_IDX_VLAN_TAG = (1 << 10), - RT_IDX_VLAN_MATCH = (1 << 11), - RT_IDX_VLAN_FILTER = (1 << 12), - RT_IDX_ETH_SKIP1 = (1 << 13), - RT_IDX_ETH_SKIP2 = (1 << 14), - RT_IDX_BCAST_MCAST_MATCH = (1 << 15), - RT_IDX_802_3 = (1 << 16), - RT_IDX_LLDP = (1 << 17), - RT_IDX_UNUSED018 = (1 << 18), - RT_IDX_UNUSED019 = (1 << 19), - RT_IDX_UNUSED20 = (1 << 20), - RT_IDX_UNUSED21 = (1 << 21), - RT_IDX_ERR = (1 << 22), - RT_IDX_VALID = (1 << 23), - RT_IDX_TU_CSUM_ERR = (1 << 24), - RT_IDX_IP_CSUM_ERR = (1 << 25), - RT_IDX_MAC_ERR = (1 << 26), - RT_IDX_RSS_TCP6 = (1 << 27), - RT_IDX_RSS_TCP4 = (1 << 28), - RT_IDX_RSS_IPV6 = (1 << 29), - RT_IDX_RSS_IPV4 = (1 << 30), - RT_IDX_RSS_MATCH = (1 << 31), - - /* Hierarchy for the NIC Queue Mask */ - RT_IDX_ALL_ERR_SLOT = 0, - RT_IDX_MAC_ERR_SLOT = 0, - RT_IDX_IP_CSUM_ERR_SLOT = 1, - RT_IDX_TCP_UDP_CSUM_ERR_SLOT = 2, - RT_IDX_BCAST_SLOT = 3, - RT_IDX_MCAST_MATCH_SLOT = 4, - RT_IDX_ALLMULTI_SLOT = 5, - RT_IDX_UNUSED6_SLOT = 6, - RT_IDX_UNUSED7_SLOT = 7, - RT_IDX_RSS_MATCH_SLOT = 8, - RT_IDX_RSS_IPV4_SLOT = 8, - RT_IDX_RSS_IPV6_SLOT = 9, - RT_IDX_RSS_TCP4_SLOT = 10, - RT_IDX_RSS_TCP6_SLOT = 11, - RT_IDX_CAM_HIT_SLOT = 12, - RT_IDX_UNUSED013 = 13, - RT_IDX_UNUSED014 = 14, - RT_IDX_PROMISCUOUS_SLOT = 15, - RT_IDX_MAX_RT_SLOTS = 8, - RT_IDX_MAX_NIC_SLOTS = 16, -}; - -/* - * Serdes Address Register (XG_SERDES_ADDR) bit definitions. - */ -enum { - XG_SERDES_ADDR_RDY = (1 << 31), - XG_SERDES_ADDR_R = (1 << 30), - - XG_SERDES_ADDR_STS = 0x00001E06, - XG_SERDES_ADDR_XFI1_PWR_UP = 0x00000005, - XG_SERDES_ADDR_XFI2_PWR_UP = 0x0000000a, - XG_SERDES_ADDR_XAUI_PWR_DOWN = 0x00000001, - - /* Serdes coredump definitions. */ - XG_SERDES_XAUI_AN_START = 0x00000000, - XG_SERDES_XAUI_AN_END = 0x00000034, - XG_SERDES_XAUI_HSS_PCS_START = 0x00000800, - XG_SERDES_XAUI_HSS_PCS_END = 0x0000880, - XG_SERDES_XFI_AN_START = 0x00001000, - XG_SERDES_XFI_AN_END = 0x00001034, - XG_SERDES_XFI_TRAIN_START = 0x10001050, - XG_SERDES_XFI_TRAIN_END = 0x1000107C, - XG_SERDES_XFI_HSS_PCS_START = 0x00001800, - XG_SERDES_XFI_HSS_PCS_END = 0x00001838, - XG_SERDES_XFI_HSS_TX_START = 0x00001c00, - XG_SERDES_XFI_HSS_TX_END = 0x00001c1f, - XG_SERDES_XFI_HSS_RX_START = 0x00001c40, - XG_SERDES_XFI_HSS_RX_END = 0x00001c5f, - XG_SERDES_XFI_HSS_PLL_START = 0x00001e00, - XG_SERDES_XFI_HSS_PLL_END = 0x00001e1f, -}; - -/* - * NIC Probe Mux Address Register (PRB_MX_ADDR) bit definitions. - */ -enum { - PRB_MX_ADDR_ARE = (1 << 16), - PRB_MX_ADDR_UP = (1 << 15), - PRB_MX_ADDR_SWP = (1 << 14), - - /* Module select values. */ - PRB_MX_ADDR_MAX_MODS = 21, - PRB_MX_ADDR_MOD_SEL_SHIFT = 9, - PRB_MX_ADDR_MOD_SEL_TBD = 0, - PRB_MX_ADDR_MOD_SEL_IDE1 = 1, - PRB_MX_ADDR_MOD_SEL_IDE2 = 2, - PRB_MX_ADDR_MOD_SEL_FRB = 3, - PRB_MX_ADDR_MOD_SEL_ODE1 = 4, - PRB_MX_ADDR_MOD_SEL_ODE2 = 5, - PRB_MX_ADDR_MOD_SEL_DA1 = 6, - PRB_MX_ADDR_MOD_SEL_DA2 = 7, - PRB_MX_ADDR_MOD_SEL_IMP1 = 8, - PRB_MX_ADDR_MOD_SEL_IMP2 = 9, - PRB_MX_ADDR_MOD_SEL_OMP1 = 10, - PRB_MX_ADDR_MOD_SEL_OMP2 = 11, - PRB_MX_ADDR_MOD_SEL_ORS1 = 12, - PRB_MX_ADDR_MOD_SEL_ORS2 = 13, - PRB_MX_ADDR_MOD_SEL_REG = 14, - PRB_MX_ADDR_MOD_SEL_MAC1 = 16, - PRB_MX_ADDR_MOD_SEL_MAC2 = 17, - PRB_MX_ADDR_MOD_SEL_VQM1 = 18, - PRB_MX_ADDR_MOD_SEL_VQM2 = 19, - PRB_MX_ADDR_MOD_SEL_MOP = 20, - /* Bit fields indicating which modules - * are valid for each clock domain. - */ - PRB_MX_ADDR_VALID_SYS_MOD = 0x000f7ff7, - PRB_MX_ADDR_VALID_PCI_MOD = 0x000040c1, - PRB_MX_ADDR_VALID_XGM_MOD = 0x00037309, - PRB_MX_ADDR_VALID_FC_MOD = 0x00003001, - PRB_MX_ADDR_VALID_TOTAL = 34, - - /* Clock domain values. */ - PRB_MX_ADDR_CLOCK_SHIFT = 6, - PRB_MX_ADDR_SYS_CLOCK = 0, - PRB_MX_ADDR_PCI_CLOCK = 2, - PRB_MX_ADDR_FC_CLOCK = 5, - PRB_MX_ADDR_XGM_CLOCK = 6, - - PRB_MX_ADDR_MAX_MUX = 64, -}; - -/* - * Control Register Set Map - */ -enum { - PROC_ADDR = 0, /* Use semaphore */ - PROC_DATA = 0x04, /* Use semaphore */ - SYS = 0x08, - RST_FO = 0x0c, - FSC = 0x10, - CSR = 0x14, - LED = 0x18, - ICB_RID = 0x1c, /* Use semaphore */ - ICB_L = 0x20, /* Use semaphore */ - ICB_H = 0x24, /* Use semaphore */ - CFG = 0x28, - BIOS_ADDR = 0x2c, - STS = 0x30, - INTR_EN = 0x34, - INTR_MASK = 0x38, - ISR1 = 0x3c, - ISR2 = 0x40, - ISR3 = 0x44, - ISR4 = 0x48, - REV_ID = 0x4c, - FRC_ECC_ERR = 0x50, - ERR_STS = 0x54, - RAM_DBG_ADDR = 0x58, - RAM_DBG_DATA = 0x5c, - ECC_ERR_CNT = 0x60, - SEM = 0x64, - GPIO_1 = 0x68, /* Use semaphore */ - GPIO_2 = 0x6c, /* Use semaphore */ - GPIO_3 = 0x70, /* Use semaphore */ - RSVD2 = 0x74, - XGMAC_ADDR = 0x78, /* Use semaphore */ - XGMAC_DATA = 0x7c, /* Use semaphore */ - NIC_ETS = 0x80, - CNA_ETS = 0x84, - FLASH_ADDR = 0x88, /* Use semaphore */ - FLASH_DATA = 0x8c, /* Use semaphore */ - CQ_STOP = 0x90, - PAGE_TBL_RID = 0x94, - WQ_PAGE_TBL_LO = 0x98, - WQ_PAGE_TBL_HI = 0x9c, - CQ_PAGE_TBL_LO = 0xa0, - CQ_PAGE_TBL_HI = 0xa4, - MAC_ADDR_IDX = 0xa8, /* Use semaphore */ - MAC_ADDR_DATA = 0xac, /* Use semaphore */ - COS_DFLT_CQ1 = 0xb0, - COS_DFLT_CQ2 = 0xb4, - ETYPE_SKIP1 = 0xb8, - ETYPE_SKIP2 = 0xbc, - SPLT_HDR = 0xc0, - FC_PAUSE_THRES = 0xc4, - NIC_PAUSE_THRES = 0xc8, - FC_ETHERTYPE = 0xcc, - FC_RCV_CFG = 0xd0, - NIC_RCV_CFG = 0xd4, - FC_COS_TAGS = 0xd8, - NIC_COS_TAGS = 0xdc, - MGMT_RCV_CFG = 0xe0, - RT_IDX = 0xe4, - RT_DATA = 0xe8, - RSVD7 = 0xec, - XG_SERDES_ADDR = 0xf0, - XG_SERDES_DATA = 0xf4, - PRB_MX_ADDR = 0xf8, /* Use semaphore */ - PRB_MX_DATA = 0xfc, /* Use semaphore */ -}; - -#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS -#define SMALL_BUFFER_SIZE 256 -#define SMALL_BUF_MAP_SIZE SMALL_BUFFER_SIZE -#define SPLT_SETTING FSC_DBRST_1024 -#define SPLT_LEN 0 -#define QLGE_SB_PAD 0 -#else -#define SMALL_BUFFER_SIZE 512 -#define SMALL_BUF_MAP_SIZE (SMALL_BUFFER_SIZE / 2) -#define SPLT_SETTING FSC_SH -#define SPLT_LEN (SPLT_HDR_EP | \ - min(SMALL_BUF_MAP_SIZE, 1023)) -#define QLGE_SB_PAD 32 -#endif - -/* - * CAM output format. - */ -enum { - CAM_OUT_ROUTE_FC = 0, - CAM_OUT_ROUTE_NIC = 1, - CAM_OUT_FUNC_SHIFT = 2, - CAM_OUT_RV = (1 << 4), - CAM_OUT_SH = (1 << 15), - CAM_OUT_CQ_ID_SHIFT = 5, -}; - -/* - * Mailbox definitions - */ -enum { - /* Asynchronous Event Notifications */ - AEN_SYS_ERR = 0x00008002, - AEN_LINK_UP = 0x00008011, - AEN_LINK_DOWN = 0x00008012, - AEN_IDC_CMPLT = 0x00008100, - AEN_IDC_REQ = 0x00008101, - AEN_IDC_EXT = 0x00008102, - AEN_DCBX_CHG = 0x00008110, - AEN_AEN_LOST = 0x00008120, - AEN_AEN_SFP_IN = 0x00008130, - AEN_AEN_SFP_OUT = 0x00008131, - AEN_FW_INIT_DONE = 0x00008400, - AEN_FW_INIT_FAIL = 0x00008401, - - /* Mailbox Command Opcodes. */ - MB_CMD_NOP = 0x00000000, - MB_CMD_EX_FW = 0x00000002, - MB_CMD_MB_TEST = 0x00000006, - MB_CMD_CSUM_TEST = 0x00000007, /* Verify Checksum */ - MB_CMD_ABOUT_FW = 0x00000008, - MB_CMD_COPY_RISC_RAM = 0x0000000a, - MB_CMD_LOAD_RISC_RAM = 0x0000000b, - MB_CMD_DUMP_RISC_RAM = 0x0000000c, - MB_CMD_WRITE_RAM = 0x0000000d, - MB_CMD_INIT_RISC_RAM = 0x0000000e, - MB_CMD_READ_RAM = 0x0000000f, - MB_CMD_STOP_FW = 0x00000014, - MB_CMD_MAKE_SYS_ERR = 0x0000002a, - MB_CMD_WRITE_SFP = 0x00000030, - MB_CMD_READ_SFP = 0x00000031, - MB_CMD_INIT_FW = 0x00000060, - MB_CMD_GET_IFCB = 0x00000061, - MB_CMD_GET_FW_STATE = 0x00000069, - MB_CMD_IDC_REQ = 0x00000100, /* Inter-Driver Communication */ - MB_CMD_IDC_ACK = 0x00000101, /* Inter-Driver Communication */ - MB_CMD_SET_WOL_MODE = 0x00000110, /* Wake On Lan */ - MB_WOL_DISABLE = 0, - MB_WOL_MAGIC_PKT = (1 << 1), - MB_WOL_FLTR = (1 << 2), - MB_WOL_UCAST = (1 << 3), - MB_WOL_MCAST = (1 << 4), - MB_WOL_BCAST = (1 << 5), - MB_WOL_LINK_UP = (1 << 6), - MB_WOL_LINK_DOWN = (1 << 7), - MB_WOL_MODE_ON = (1 << 16), /* Wake on Lan Mode on */ - MB_CMD_SET_WOL_FLTR = 0x00000111, /* Wake On Lan Filter */ - MB_CMD_CLEAR_WOL_FLTR = 0x00000112, /* Wake On Lan Filter */ - MB_CMD_SET_WOL_MAGIC = 0x00000113, /* Wake On Lan Magic Packet */ - MB_CMD_CLEAR_WOL_MAGIC = 0x00000114,/* Wake On Lan Magic Packet */ - MB_CMD_SET_WOL_IMMED = 0x00000115, - MB_CMD_PORT_RESET = 0x00000120, - MB_CMD_SET_PORT_CFG = 0x00000122, - MB_CMD_GET_PORT_CFG = 0x00000123, - MB_CMD_GET_LINK_STS = 0x00000124, - MB_CMD_SET_LED_CFG = 0x00000125, /* Set LED Configuration Register */ - QL_LED_BLINK = 0x03e803e8, - MB_CMD_GET_LED_CFG = 0x00000126, /* Get LED Configuration Register */ - MB_CMD_SET_MGMNT_TFK_CTL = 0x00000160, /* Set Mgmnt Traffic Control */ - MB_SET_MPI_TFK_STOP = (1 << 0), - MB_SET_MPI_TFK_RESUME = (1 << 1), - MB_CMD_GET_MGMNT_TFK_CTL = 0x00000161, /* Get Mgmnt Traffic Control */ - MB_GET_MPI_TFK_STOPPED = (1 << 0), - MB_GET_MPI_TFK_FIFO_EMPTY = (1 << 1), - /* Sub-commands for IDC request. - * This describes the reason for the - * IDC request. - */ - MB_CMD_IOP_NONE = 0x0000, - MB_CMD_IOP_PREP_UPDATE_MPI = 0x0001, - MB_CMD_IOP_COMP_UPDATE_MPI = 0x0002, - MB_CMD_IOP_PREP_LINK_DOWN = 0x0010, - MB_CMD_IOP_DVR_START = 0x0100, - MB_CMD_IOP_FLASH_ACC = 0x0101, - MB_CMD_IOP_RESTART_MPI = 0x0102, - MB_CMD_IOP_CORE_DUMP_MPI = 0x0103, - - /* Mailbox Command Status. */ - MB_CMD_STS_GOOD = 0x00004000, /* Success. */ - MB_CMD_STS_INTRMDT = 0x00001000, /* Intermediate Complete. */ - MB_CMD_STS_INVLD_CMD = 0x00004001, /* Invalid. */ - MB_CMD_STS_XFC_ERR = 0x00004002, /* Interface Error. */ - MB_CMD_STS_CSUM_ERR = 0x00004003, /* Csum Error. */ - MB_CMD_STS_ERR = 0x00004005, /* System Error. */ - MB_CMD_STS_PARAM_ERR = 0x00004006, /* Parameter Error. */ -}; - -struct mbox_params { - u32 mbox_in[MAILBOX_COUNT]; - u32 mbox_out[MAILBOX_COUNT]; - int in_count; - int out_count; -}; - -struct flash_params_8012 { - u8 dev_id_str[4]; - __le16 size; - __le16 csum; - __le16 ver; - __le16 sub_dev_id; - u8 mac_addr[6]; - __le16 res; -}; - -/* 8000 device's flash is a different structure - * at a different offset in flash. - */ -#define FUNC0_FLASH_OFFSET 0x140200 -#define FUNC1_FLASH_OFFSET 0x140600 - -/* Flash related data structures. */ -struct flash_params_8000 { - u8 dev_id_str[4]; /* "8000" */ - __le16 ver; - __le16 size; - __le16 csum; - __le16 reserved0; - __le16 total_size; - __le16 entry_count; - u8 data_type0; - u8 data_size0; - u8 mac_addr[6]; - u8 data_type1; - u8 data_size1; - u8 mac_addr1[6]; - u8 data_type2; - u8 data_size2; - __le16 vlan_id; - u8 data_type3; - u8 data_size3; - __le16 last; - u8 reserved1[464]; - __le16 subsys_ven_id; - __le16 subsys_dev_id; - u8 reserved2[4]; -}; - -union flash_params { - struct flash_params_8012 flash_params_8012; - struct flash_params_8000 flash_params_8000; -}; - -/* - * doorbell space for the rx ring context - */ -struct rx_doorbell_context { - u32 cnsmr_idx; /* 0x00 */ - u32 valid; /* 0x04 */ - u32 reserved[4]; /* 0x08-0x14 */ - u32 lbq_prod_idx; /* 0x18 */ - u32 sbq_prod_idx; /* 0x1c */ -}; - -/* - * doorbell space for the tx ring context - */ -struct tx_doorbell_context { - u32 prod_idx; /* 0x00 */ - u32 valid; /* 0x04 */ - u32 reserved[4]; /* 0x08-0x14 */ - u32 lbq_prod_idx; /* 0x18 */ - u32 sbq_prod_idx; /* 0x1c */ -}; - -/* DATA STRUCTURES SHARED WITH HARDWARE. */ -struct tx_buf_desc { - __le64 addr; - __le32 len; -#define TX_DESC_LEN_MASK 0x000fffff -#define TX_DESC_C 0x40000000 -#define TX_DESC_E 0x80000000 -} __packed; - -/* - * IOCB Definitions... - */ - -#define OPCODE_OB_MAC_IOCB 0x01 -#define OPCODE_OB_MAC_TSO_IOCB 0x02 -#define OPCODE_IB_MAC_IOCB 0x20 -#define OPCODE_IB_MPI_IOCB 0x21 -#define OPCODE_IB_AE_IOCB 0x3f - -struct ob_mac_iocb_req { - u8 opcode; - u8 flags1; -#define OB_MAC_IOCB_REQ_OI 0x01 -#define OB_MAC_IOCB_REQ_I 0x02 -#define OB_MAC_IOCB_REQ_D 0x08 -#define OB_MAC_IOCB_REQ_F 0x10 - u8 flags2; - u8 flags3; -#define OB_MAC_IOCB_DFP 0x02 -#define OB_MAC_IOCB_V 0x04 - __le32 reserved1[2]; - __le16 frame_len; -#define OB_MAC_IOCB_LEN_MASK 0x3ffff - __le16 reserved2; - u32 tid; - u32 txq_idx; - __le32 reserved3; - __le16 vlan_tci; - __le16 reserved4; - struct tx_buf_desc tbd[TX_DESC_PER_IOCB]; -} __packed; - -struct ob_mac_iocb_rsp { - u8 opcode; /* */ - u8 flags1; /* */ -#define OB_MAC_IOCB_RSP_OI 0x01 /* */ -#define OB_MAC_IOCB_RSP_I 0x02 /* */ -#define OB_MAC_IOCB_RSP_E 0x08 /* */ -#define OB_MAC_IOCB_RSP_S 0x10 /* too Short */ -#define OB_MAC_IOCB_RSP_L 0x20 /* too Large */ -#define OB_MAC_IOCB_RSP_P 0x40 /* Padded */ - u8 flags2; /* */ - u8 flags3; /* */ -#define OB_MAC_IOCB_RSP_B 0x80 /* */ - u32 tid; - u32 txq_idx; - __le32 reserved[13]; -} __packed; - -struct ob_mac_tso_iocb_req { - u8 opcode; - u8 flags1; -#define OB_MAC_TSO_IOCB_OI 0x01 -#define OB_MAC_TSO_IOCB_I 0x02 -#define OB_MAC_TSO_IOCB_D 0x08 -#define OB_MAC_TSO_IOCB_IP4 0x40 -#define OB_MAC_TSO_IOCB_IP6 0x80 - u8 flags2; -#define OB_MAC_TSO_IOCB_LSO 0x20 -#define OB_MAC_TSO_IOCB_UC 0x40 -#define OB_MAC_TSO_IOCB_TC 0x80 - u8 flags3; -#define OB_MAC_TSO_IOCB_IC 0x01 -#define OB_MAC_TSO_IOCB_DFP 0x02 -#define OB_MAC_TSO_IOCB_V 0x04 - __le32 reserved1[2]; - __le32 frame_len; - u32 tid; - u32 txq_idx; - __le16 total_hdrs_len; - __le16 net_trans_offset; -#define OB_MAC_TRANSPORT_HDR_SHIFT 6 - __le16 vlan_tci; - __le16 mss; - struct tx_buf_desc tbd[TX_DESC_PER_IOCB]; -} __packed; - -struct ob_mac_tso_iocb_rsp { - u8 opcode; - u8 flags1; -#define OB_MAC_TSO_IOCB_RSP_OI 0x01 -#define OB_MAC_TSO_IOCB_RSP_I 0x02 -#define OB_MAC_TSO_IOCB_RSP_E 0x08 -#define OB_MAC_TSO_IOCB_RSP_S 0x10 -#define OB_MAC_TSO_IOCB_RSP_L 0x20 -#define OB_MAC_TSO_IOCB_RSP_P 0x40 - u8 flags2; /* */ - u8 flags3; /* */ -#define OB_MAC_TSO_IOCB_RSP_B 0x8000 - u32 tid; - u32 txq_idx; - __le32 reserved2[13]; -} __packed; - -struct ib_mac_iocb_rsp { - u8 opcode; /* 0x20 */ - u8 flags1; -#define IB_MAC_IOCB_RSP_OI 0x01 /* Override intr delay */ -#define IB_MAC_IOCB_RSP_I 0x02 /* Disable Intr Generation */ -#define IB_MAC_CSUM_ERR_MASK 0x1c /* A mask to use for csum errs */ -#define IB_MAC_IOCB_RSP_TE 0x04 /* Checksum error */ -#define IB_MAC_IOCB_RSP_NU 0x08 /* No checksum rcvd */ -#define IB_MAC_IOCB_RSP_IE 0x10 /* IPv4 checksum error */ -#define IB_MAC_IOCB_RSP_M_MASK 0x60 /* Multicast info */ -#define IB_MAC_IOCB_RSP_M_NONE 0x00 /* Not mcast frame */ -#define IB_MAC_IOCB_RSP_M_HASH 0x20 /* HASH mcast frame */ -#define IB_MAC_IOCB_RSP_M_REG 0x40 /* Registered mcast frame */ -#define IB_MAC_IOCB_RSP_M_PROM 0x60 /* Promiscuous mcast frame */ -#define IB_MAC_IOCB_RSP_B 0x80 /* Broadcast frame */ - u8 flags2; -#define IB_MAC_IOCB_RSP_P 0x01 /* Promiscuous frame */ -#define IB_MAC_IOCB_RSP_V 0x02 /* Vlan tag present */ -#define IB_MAC_IOCB_RSP_ERR_MASK 0x1c /* */ -#define IB_MAC_IOCB_RSP_ERR_CODE_ERR 0x04 -#define IB_MAC_IOCB_RSP_ERR_OVERSIZE 0x08 -#define IB_MAC_IOCB_RSP_ERR_UNDERSIZE 0x10 -#define IB_MAC_IOCB_RSP_ERR_PREAMBLE 0x14 -#define IB_MAC_IOCB_RSP_ERR_FRAME_LEN 0x18 -#define IB_MAC_IOCB_RSP_ERR_CRC 0x1c -#define IB_MAC_IOCB_RSP_U 0x20 /* UDP packet */ -#define IB_MAC_IOCB_RSP_T 0x40 /* TCP packet */ -#define IB_MAC_IOCB_RSP_FO 0x80 /* Failover port */ - u8 flags3; -#define IB_MAC_IOCB_RSP_RSS_MASK 0x07 /* RSS mask */ -#define IB_MAC_IOCB_RSP_M_NONE 0x00 /* No RSS match */ -#define IB_MAC_IOCB_RSP_M_IPV4 0x04 /* IPv4 RSS match */ -#define IB_MAC_IOCB_RSP_M_IPV6 0x02 /* IPv6 RSS match */ -#define IB_MAC_IOCB_RSP_M_TCP_V4 0x05 /* TCP with IPv4 */ -#define IB_MAC_IOCB_RSP_M_TCP_V6 0x03 /* TCP with IPv6 */ -#define IB_MAC_IOCB_RSP_V4 0x08 /* IPV4 */ -#define IB_MAC_IOCB_RSP_V6 0x10 /* IPV6 */ -#define IB_MAC_IOCB_RSP_IH 0x20 /* Split after IP header */ -#define IB_MAC_IOCB_RSP_DS 0x40 /* data is in small buffer */ -#define IB_MAC_IOCB_RSP_DL 0x80 /* data is in large buffer */ - __le32 data_len; /* */ - __le64 data_addr; /* */ - __le32 rss; /* */ - __le16 vlan_id; /* 12 bits */ -#define IB_MAC_IOCB_RSP_C 0x1000 /* VLAN CFI bit */ -#define IB_MAC_IOCB_RSP_COS_SHIFT 12 /* class of service value */ -#define IB_MAC_IOCB_RSP_VLAN_MASK 0x0ffff - - __le16 reserved1; - __le32 reserved2[6]; - u8 reserved3[3]; - u8 flags4; -#define IB_MAC_IOCB_RSP_HV 0x20 -#define IB_MAC_IOCB_RSP_HS 0x40 -#define IB_MAC_IOCB_RSP_HL 0x80 - __le32 hdr_len; /* */ - __le64 hdr_addr; /* */ -} __packed; - -struct ib_ae_iocb_rsp { - u8 opcode; - u8 flags1; -#define IB_AE_IOCB_RSP_OI 0x01 -#define IB_AE_IOCB_RSP_I 0x02 - u8 event; -#define LINK_UP_EVENT 0x00 -#define LINK_DOWN_EVENT 0x01 -#define CAM_LOOKUP_ERR_EVENT 0x06 -#define SOFT_ECC_ERROR_EVENT 0x07 -#define MGMT_ERR_EVENT 0x08 -#define TEN_GIG_MAC_EVENT 0x09 -#define GPI0_H2L_EVENT 0x10 -#define GPI0_L2H_EVENT 0x20 -#define GPI1_H2L_EVENT 0x11 -#define GPI1_L2H_EVENT 0x21 -#define PCI_ERR_ANON_BUF_RD 0x40 - u8 q_id; - __le32 reserved[15]; -} __packed; - -/* - * These three structures are for generic - * handling of ib and ob iocbs. - */ -struct ql_net_rsp_iocb { - u8 opcode; - u8 flags0; - __le16 length; - __le32 tid; - __le32 reserved[14]; -} __packed; - -struct net_req_iocb { - u8 opcode; - u8 flags0; - __le16 flags1; - __le32 tid; - __le32 reserved1[30]; -} __packed; - -/* - * tx ring initialization control block for chip. - * It is defined as: - * "Work Queue Initialization Control Block" - */ -struct wqicb { - __le16 len; -#define Q_LEN_V (1 << 4) -#define Q_LEN_CPP_CONT 0x0000 -#define Q_LEN_CPP_16 0x0001 -#define Q_LEN_CPP_32 0x0002 -#define Q_LEN_CPP_64 0x0003 -#define Q_LEN_CPP_512 0x0006 - __le16 flags; -#define Q_PRI_SHIFT 1 -#define Q_FLAGS_LC 0x1000 -#define Q_FLAGS_LB 0x2000 -#define Q_FLAGS_LI 0x4000 -#define Q_FLAGS_LO 0x8000 - __le16 cq_id_rss; -#define Q_CQ_ID_RSS_RV 0x8000 - __le16 rid; - __le64 addr; - __le64 cnsmr_idx_addr; -} __packed; - -/* - * rx ring initialization control block for chip. - * It is defined as: - * "Completion Queue Initialization Control Block" - */ -struct cqicb { - u8 msix_vect; - u8 reserved1; - u8 reserved2; - u8 flags; -#define FLAGS_LV 0x08 -#define FLAGS_LS 0x10 -#define FLAGS_LL 0x20 -#define FLAGS_LI 0x40 -#define FLAGS_LC 0x80 - __le16 len; -#define LEN_V (1 << 4) -#define LEN_CPP_CONT 0x0000 -#define LEN_CPP_32 0x0001 -#define LEN_CPP_64 0x0002 -#define LEN_CPP_128 0x0003 - __le16 rid; - __le64 addr; - __le64 prod_idx_addr; - __le16 pkt_delay; - __le16 irq_delay; - __le64 lbq_addr; - __le16 lbq_buf_size; - __le16 lbq_len; /* entry count */ - __le64 sbq_addr; - __le16 sbq_buf_size; - __le16 sbq_len; /* entry count */ -} __packed; - -struct ricb { - u8 base_cq; -#define RSS_L4K 0x80 - u8 flags; -#define RSS_L6K 0x01 -#define RSS_LI 0x02 -#define RSS_LB 0x04 -#define RSS_LM 0x08 -#define RSS_RI4 0x10 -#define RSS_RT4 0x20 -#define RSS_RI6 0x40 -#define RSS_RT6 0x80 - __le16 mask; - u8 hash_cq_id[1024]; - __le32 ipv6_hash_key[10]; - __le32 ipv4_hash_key[4]; -} __packed; - -/* SOFTWARE/DRIVER DATA STRUCTURES. */ - -struct oal { - struct tx_buf_desc oal[TX_DESC_PER_OAL]; -}; - -struct map_list { - DEFINE_DMA_UNMAP_ADDR(mapaddr); - DEFINE_DMA_UNMAP_LEN(maplen); -}; - -struct tx_ring_desc { - struct sk_buff *skb; - struct ob_mac_iocb_req *queue_entry; - u32 index; - struct oal oal; - struct map_list map[MAX_SKB_FRAGS + 2]; - int map_cnt; - struct tx_ring_desc *next; -}; - -struct page_chunk { - struct page *page; /* master page */ - char *va; /* virt addr for this chunk */ - u64 map; /* mapping for master */ - unsigned int offset; /* offset for this chunk */ - unsigned int last_flag; /* flag set for last chunk in page */ -}; - -struct bq_desc { - union { - struct page_chunk pg_chunk; - struct sk_buff *skb; - } p; - __le64 *addr; - u32 index; - DEFINE_DMA_UNMAP_ADDR(mapaddr); - DEFINE_DMA_UNMAP_LEN(maplen); -}; - -#define QL_TXQ_IDX(qdev, skb) (smp_processor_id()%(qdev->tx_ring_count)) - -struct tx_ring { - /* - * queue info. - */ - struct wqicb wqicb; /* structure used to inform chip of new queue */ - void *wq_base; /* pci_alloc:virtual addr for tx */ - dma_addr_t wq_base_dma; /* pci_alloc:dma addr for tx */ - __le32 *cnsmr_idx_sh_reg; /* shadow copy of consumer idx */ - dma_addr_t cnsmr_idx_sh_reg_dma; /* dma-shadow copy of consumer */ - u32 wq_size; /* size in bytes of queue area */ - u32 wq_len; /* number of entries in queue */ - void __iomem *prod_idx_db_reg; /* doorbell area index reg at offset 0x00 */ - void __iomem *valid_db_reg; /* doorbell area valid reg at offset 0x04 */ - u16 prod_idx; /* current value for prod idx */ - u16 cq_id; /* completion (rx) queue for tx completions */ - u8 wq_id; /* queue id for this entry */ - u8 reserved1[3]; - struct tx_ring_desc *q; /* descriptor list for the queue */ - spinlock_t lock; - atomic_t tx_count; /* counts down for every outstanding IO */ - struct delayed_work tx_work; - struct ql_adapter *qdev; - u64 tx_packets; - u64 tx_bytes; - u64 tx_errors; -}; - -/* - * Type of inbound queue. - */ -enum { - DEFAULT_Q = 2, /* Handles slow queue and chip/MPI events. */ - TX_Q = 3, /* Handles outbound completions. */ - RX_Q = 4, /* Handles inbound completions. */ -}; - -struct rx_ring { - struct cqicb cqicb; /* The chip's completion queue init control block. */ - - /* Completion queue elements. */ - void *cq_base; - dma_addr_t cq_base_dma; - u32 cq_size; - u32 cq_len; - u16 cq_id; - __le32 *prod_idx_sh_reg; /* Shadowed producer register. */ - dma_addr_t prod_idx_sh_reg_dma; - void __iomem *cnsmr_idx_db_reg; /* PCI doorbell mem area + 0 */ - u32 cnsmr_idx; /* current sw idx */ - struct ql_net_rsp_iocb *curr_entry; /* next entry on queue */ - void __iomem *valid_db_reg; /* PCI doorbell mem area + 0x04 */ - - /* Large buffer queue elements. */ - u32 lbq_len; /* entry count */ - u32 lbq_size; /* size in bytes of queue */ - u32 lbq_buf_size; - void *lbq_base; - dma_addr_t lbq_base_dma; - void *lbq_base_indirect; - dma_addr_t lbq_base_indirect_dma; - struct page_chunk pg_chunk; /* current page for chunks */ - struct bq_desc *lbq; /* array of control blocks */ - void __iomem *lbq_prod_idx_db_reg; /* PCI doorbell mem area + 0x18 */ - u32 lbq_prod_idx; /* current sw prod idx */ - u32 lbq_curr_idx; /* next entry we expect */ - u32 lbq_clean_idx; /* beginning of new descs */ - u32 lbq_free_cnt; /* free buffer desc cnt */ - - /* Small buffer queue elements. */ - u32 sbq_len; /* entry count */ - u32 sbq_size; /* size in bytes of queue */ - u32 sbq_buf_size; - void *sbq_base; - dma_addr_t sbq_base_dma; - void *sbq_base_indirect; - dma_addr_t sbq_base_indirect_dma; - struct bq_desc *sbq; /* array of control blocks */ - void __iomem *sbq_prod_idx_db_reg; /* PCI doorbell mem area + 0x1c */ - u32 sbq_prod_idx; /* current sw prod idx */ - u32 sbq_curr_idx; /* next entry we expect */ - u32 sbq_clean_idx; /* beginning of new descs */ - u32 sbq_free_cnt; /* free buffer desc cnt */ - - /* Misc. handler elements. */ - u32 type; /* Type of queue, tx, rx. */ - u32 irq; /* Which vector this ring is assigned. */ - u32 cpu; /* Which CPU this should run on. */ - char name[IFNAMSIZ + 5]; - struct napi_struct napi; - u8 reserved; - struct ql_adapter *qdev; - u64 rx_packets; - u64 rx_multicast; - u64 rx_bytes; - u64 rx_dropped; - u64 rx_errors; -}; - -/* - * RSS Initialization Control Block - */ -struct hash_id { - u8 value[4]; -}; - -struct nic_stats { - /* - * These stats come from offset 200h to 278h - * in the XGMAC register. - */ - u64 tx_pkts; - u64 tx_bytes; - u64 tx_mcast_pkts; - u64 tx_bcast_pkts; - u64 tx_ucast_pkts; - u64 tx_ctl_pkts; - u64 tx_pause_pkts; - u64 tx_64_pkt; - u64 tx_65_to_127_pkt; - u64 tx_128_to_255_pkt; - u64 tx_256_511_pkt; - u64 tx_512_to_1023_pkt; - u64 tx_1024_to_1518_pkt; - u64 tx_1519_to_max_pkt; - u64 tx_undersize_pkt; - u64 tx_oversize_pkt; - - /* - * These stats come from offset 300h to 3C8h - * in the XGMAC register. - */ - u64 rx_bytes; - u64 rx_bytes_ok; - u64 rx_pkts; - u64 rx_pkts_ok; - u64 rx_bcast_pkts; - u64 rx_mcast_pkts; - u64 rx_ucast_pkts; - u64 rx_undersize_pkts; - u64 rx_oversize_pkts; - u64 rx_jabber_pkts; - u64 rx_undersize_fcerr_pkts; - u64 rx_drop_events; - u64 rx_fcerr_pkts; - u64 rx_align_err; - u64 rx_symbol_err; - u64 rx_mac_err; - u64 rx_ctl_pkts; - u64 rx_pause_pkts; - u64 rx_64_pkts; - u64 rx_65_to_127_pkts; - u64 rx_128_255_pkts; - u64 rx_256_511_pkts; - u64 rx_512_to_1023_pkts; - u64 rx_1024_to_1518_pkts; - u64 rx_1519_to_max_pkts; - u64 rx_len_err_pkts; - /* Receive Mac Err stats */ - u64 rx_code_err; - u64 rx_oversize_err; - u64 rx_undersize_err; - u64 rx_preamble_err; - u64 rx_frame_len_err; - u64 rx_crc_err; - u64 rx_err_count; - /* - * These stats come from offset 500h to 5C8h - * in the XGMAC register. - */ - u64 tx_cbfc_pause_frames0; - u64 tx_cbfc_pause_frames1; - u64 tx_cbfc_pause_frames2; - u64 tx_cbfc_pause_frames3; - u64 tx_cbfc_pause_frames4; - u64 tx_cbfc_pause_frames5; - u64 tx_cbfc_pause_frames6; - u64 tx_cbfc_pause_frames7; - u64 rx_cbfc_pause_frames0; - u64 rx_cbfc_pause_frames1; - u64 rx_cbfc_pause_frames2; - u64 rx_cbfc_pause_frames3; - u64 rx_cbfc_pause_frames4; - u64 rx_cbfc_pause_frames5; - u64 rx_cbfc_pause_frames6; - u64 rx_cbfc_pause_frames7; - u64 rx_nic_fifo_drop; -}; - -/* Firmware coredump internal register address/length pairs. */ -enum { - MPI_CORE_REGS_ADDR = 0x00030000, - MPI_CORE_REGS_CNT = 127, - MPI_CORE_SH_REGS_CNT = 16, - TEST_REGS_ADDR = 0x00001000, - TEST_REGS_CNT = 23, - RMII_REGS_ADDR = 0x00001040, - RMII_REGS_CNT = 64, - FCMAC1_REGS_ADDR = 0x00001080, - FCMAC2_REGS_ADDR = 0x000010c0, - FCMAC_REGS_CNT = 64, - FC1_MBX_REGS_ADDR = 0x00001100, - FC2_MBX_REGS_ADDR = 0x00001240, - FC_MBX_REGS_CNT = 64, - IDE_REGS_ADDR = 0x00001140, - IDE_REGS_CNT = 64, - NIC1_MBX_REGS_ADDR = 0x00001180, - NIC2_MBX_REGS_ADDR = 0x00001280, - NIC_MBX_REGS_CNT = 64, - SMBUS_REGS_ADDR = 0x00001200, - SMBUS_REGS_CNT = 64, - I2C_REGS_ADDR = 0x00001fc0, - I2C_REGS_CNT = 64, - MEMC_REGS_ADDR = 0x00003000, - MEMC_REGS_CNT = 256, - PBUS_REGS_ADDR = 0x00007c00, - PBUS_REGS_CNT = 256, - MDE_REGS_ADDR = 0x00010000, - MDE_REGS_CNT = 6, - CODE_RAM_ADDR = 0x00020000, - CODE_RAM_CNT = 0x2000, - MEMC_RAM_ADDR = 0x00100000, - MEMC_RAM_CNT = 0x2000, -}; - -#define MPI_COREDUMP_COOKIE 0x5555aaaa -struct mpi_coredump_global_header { - u32 cookie; - u8 idString[16]; - u32 timeLo; - u32 timeHi; - u32 imageSize; - u32 headerSize; - u8 info[220]; -}; - -struct mpi_coredump_segment_header { - u32 cookie; - u32 segNum; - u32 segSize; - u32 extra; - u8 description[16]; -}; - -/* Firmware coredump header segment numbers. */ -enum { - CORE_SEG_NUM = 1, - TEST_LOGIC_SEG_NUM = 2, - RMII_SEG_NUM = 3, - FCMAC1_SEG_NUM = 4, - FCMAC2_SEG_NUM = 5, - FC1_MBOX_SEG_NUM = 6, - IDE_SEG_NUM = 7, - NIC1_MBOX_SEG_NUM = 8, - SMBUS_SEG_NUM = 9, - FC2_MBOX_SEG_NUM = 10, - NIC2_MBOX_SEG_NUM = 11, - I2C_SEG_NUM = 12, - MEMC_SEG_NUM = 13, - PBUS_SEG_NUM = 14, - MDE_SEG_NUM = 15, - NIC1_CONTROL_SEG_NUM = 16, - NIC2_CONTROL_SEG_NUM = 17, - NIC1_XGMAC_SEG_NUM = 18, - NIC2_XGMAC_SEG_NUM = 19, - WCS_RAM_SEG_NUM = 20, - MEMC_RAM_SEG_NUM = 21, - XAUI_AN_SEG_NUM = 22, - XAUI_HSS_PCS_SEG_NUM = 23, - XFI_AN_SEG_NUM = 24, - XFI_TRAIN_SEG_NUM = 25, - XFI_HSS_PCS_SEG_NUM = 26, - XFI_HSS_TX_SEG_NUM = 27, - XFI_HSS_RX_SEG_NUM = 28, - XFI_HSS_PLL_SEG_NUM = 29, - MISC_NIC_INFO_SEG_NUM = 30, - INTR_STATES_SEG_NUM = 31, - CAM_ENTRIES_SEG_NUM = 32, - ROUTING_WORDS_SEG_NUM = 33, - ETS_SEG_NUM = 34, - PROBE_DUMP_SEG_NUM = 35, - ROUTING_INDEX_SEG_NUM = 36, - MAC_PROTOCOL_SEG_NUM = 37, - XAUI2_AN_SEG_NUM = 38, - XAUI2_HSS_PCS_SEG_NUM = 39, - XFI2_AN_SEG_NUM = 40, - XFI2_TRAIN_SEG_NUM = 41, - XFI2_HSS_PCS_SEG_NUM = 42, - XFI2_HSS_TX_SEG_NUM = 43, - XFI2_HSS_RX_SEG_NUM = 44, - XFI2_HSS_PLL_SEG_NUM = 45, - SEM_REGS_SEG_NUM = 50 - -}; - -/* There are 64 generic NIC registers. */ -#define NIC_REGS_DUMP_WORD_COUNT 64 -/* XGMAC word count. */ -#define XGMAC_DUMP_WORD_COUNT (XGMAC_REGISTER_END / 4) -/* Word counts for the SERDES blocks. */ -#define XG_SERDES_XAUI_AN_COUNT 14 -#define XG_SERDES_XAUI_HSS_PCS_COUNT 33 -#define XG_SERDES_XFI_AN_COUNT 14 -#define XG_SERDES_XFI_TRAIN_COUNT 12 -#define XG_SERDES_XFI_HSS_PCS_COUNT 15 -#define XG_SERDES_XFI_HSS_TX_COUNT 32 -#define XG_SERDES_XFI_HSS_RX_COUNT 32 -#define XG_SERDES_XFI_HSS_PLL_COUNT 32 - -/* There are 2 CNA ETS and 8 NIC ETS registers. */ -#define ETS_REGS_DUMP_WORD_COUNT 10 - -/* Each probe mux entry stores the probe type plus 64 entries - * that are each each 64-bits in length. There are a total of - * 34 (PRB_MX_ADDR_VALID_TOTAL) valid probes. - */ -#define PRB_MX_ADDR_PRB_WORD_COUNT (1 + (PRB_MX_ADDR_MAX_MUX * 2)) -#define PRB_MX_DUMP_TOT_COUNT (PRB_MX_ADDR_PRB_WORD_COUNT * \ - PRB_MX_ADDR_VALID_TOTAL) -/* Each routing entry consists of 4 32-bit words. - * They are route type, index, index word, and result. - * There are 2 route blocks with 8 entries each and - * 2 NIC blocks with 16 entries each. - * The totol entries is 48 with 4 words each. - */ -#define RT_IDX_DUMP_ENTRIES 48 -#define RT_IDX_DUMP_WORDS_PER_ENTRY 4 -#define RT_IDX_DUMP_TOT_WORDS (RT_IDX_DUMP_ENTRIES * \ - RT_IDX_DUMP_WORDS_PER_ENTRY) -/* There are 10 address blocks in filter, each with - * different entry counts and different word-count-per-entry. - */ -#define MAC_ADDR_DUMP_ENTRIES \ - ((MAC_ADDR_MAX_CAM_ENTRIES * MAC_ADDR_MAX_CAM_WCOUNT) + \ - (MAC_ADDR_MAX_MULTICAST_ENTRIES * MAC_ADDR_MAX_MULTICAST_WCOUNT) + \ - (MAC_ADDR_MAX_VLAN_ENTRIES * MAC_ADDR_MAX_VLAN_WCOUNT) + \ - (MAC_ADDR_MAX_MCAST_FLTR_ENTRIES * MAC_ADDR_MAX_MCAST_FLTR_WCOUNT) + \ - (MAC_ADDR_MAX_FC_MAC_ENTRIES * MAC_ADDR_MAX_FC_MAC_WCOUNT) + \ - (MAC_ADDR_MAX_MGMT_MAC_ENTRIES * MAC_ADDR_MAX_MGMT_MAC_WCOUNT) + \ - (MAC_ADDR_MAX_MGMT_VLAN_ENTRIES * MAC_ADDR_MAX_MGMT_VLAN_WCOUNT) + \ - (MAC_ADDR_MAX_MGMT_V4_ENTRIES * MAC_ADDR_MAX_MGMT_V4_WCOUNT) + \ - (MAC_ADDR_MAX_MGMT_V6_ENTRIES * MAC_ADDR_MAX_MGMT_V6_WCOUNT) + \ - (MAC_ADDR_MAX_MGMT_TU_DP_ENTRIES * MAC_ADDR_MAX_MGMT_TU_DP_WCOUNT)) -#define MAC_ADDR_DUMP_WORDS_PER_ENTRY 2 -#define MAC_ADDR_DUMP_TOT_WORDS (MAC_ADDR_DUMP_ENTRIES * \ - MAC_ADDR_DUMP_WORDS_PER_ENTRY) -/* Maximum of 4 functions whose semaphore registeres are - * in the coredump. - */ -#define MAX_SEMAPHORE_FUNCTIONS 4 -/* Defines for access the MPI shadow registers. */ -#define RISC_124 0x0003007c -#define RISC_127 0x0003007f -#define SHADOW_OFFSET 0xb0000000 -#define SHADOW_REG_SHIFT 20 - -struct ql_nic_misc { - u32 rx_ring_count; - u32 tx_ring_count; - u32 intr_count; - u32 function; -}; - -struct ql_reg_dump { - - /* segment 0 */ - struct mpi_coredump_global_header mpi_global_header; - - /* segment 16 */ - struct mpi_coredump_segment_header nic_regs_seg_hdr; - u32 nic_regs[64]; - - /* segment 30 */ - struct mpi_coredump_segment_header misc_nic_seg_hdr; - struct ql_nic_misc misc_nic_info; - - /* segment 31 */ - /* one interrupt state for each CQ */ - struct mpi_coredump_segment_header intr_states_seg_hdr; - u32 intr_states[MAX_CPUS]; - - /* segment 32 */ - /* 3 cam words each for 16 unicast, - * 2 cam words for each of 32 multicast. - */ - struct mpi_coredump_segment_header cam_entries_seg_hdr; - u32 cam_entries[(16 * 3) + (32 * 3)]; - - /* segment 33 */ - struct mpi_coredump_segment_header nic_routing_words_seg_hdr; - u32 nic_routing_words[16]; - - /* segment 34 */ - struct mpi_coredump_segment_header ets_seg_hdr; - u32 ets[8+2]; -}; - -struct ql_mpi_coredump { - /* segment 0 */ - struct mpi_coredump_global_header mpi_global_header; - - /* segment 1 */ - struct mpi_coredump_segment_header core_regs_seg_hdr; - u32 mpi_core_regs[MPI_CORE_REGS_CNT]; - u32 mpi_core_sh_regs[MPI_CORE_SH_REGS_CNT]; - - /* segment 2 */ - struct mpi_coredump_segment_header test_logic_regs_seg_hdr; - u32 test_logic_regs[TEST_REGS_CNT]; - - /* segment 3 */ - struct mpi_coredump_segment_header rmii_regs_seg_hdr; - u32 rmii_regs[RMII_REGS_CNT]; - - /* segment 4 */ - struct mpi_coredump_segment_header fcmac1_regs_seg_hdr; - u32 fcmac1_regs[FCMAC_REGS_CNT]; - - /* segment 5 */ - struct mpi_coredump_segment_header fcmac2_regs_seg_hdr; - u32 fcmac2_regs[FCMAC_REGS_CNT]; - - /* segment 6 */ - struct mpi_coredump_segment_header fc1_mbx_regs_seg_hdr; - u32 fc1_mbx_regs[FC_MBX_REGS_CNT]; - - /* segment 7 */ - struct mpi_coredump_segment_header ide_regs_seg_hdr; - u32 ide_regs[IDE_REGS_CNT]; - - /* segment 8 */ - struct mpi_coredump_segment_header nic1_mbx_regs_seg_hdr; - u32 nic1_mbx_regs[NIC_MBX_REGS_CNT]; - - /* segment 9 */ - struct mpi_coredump_segment_header smbus_regs_seg_hdr; - u32 smbus_regs[SMBUS_REGS_CNT]; - - /* segment 10 */ - struct mpi_coredump_segment_header fc2_mbx_regs_seg_hdr; - u32 fc2_mbx_regs[FC_MBX_REGS_CNT]; - - /* segment 11 */ - struct mpi_coredump_segment_header nic2_mbx_regs_seg_hdr; - u32 nic2_mbx_regs[NIC_MBX_REGS_CNT]; - - /* segment 12 */ - struct mpi_coredump_segment_header i2c_regs_seg_hdr; - u32 i2c_regs[I2C_REGS_CNT]; - /* segment 13 */ - struct mpi_coredump_segment_header memc_regs_seg_hdr; - u32 memc_regs[MEMC_REGS_CNT]; - - /* segment 14 */ - struct mpi_coredump_segment_header pbus_regs_seg_hdr; - u32 pbus_regs[PBUS_REGS_CNT]; - - /* segment 15 */ - struct mpi_coredump_segment_header mde_regs_seg_hdr; - u32 mde_regs[MDE_REGS_CNT]; - - /* segment 16 */ - struct mpi_coredump_segment_header nic_regs_seg_hdr; - u32 nic_regs[NIC_REGS_DUMP_WORD_COUNT]; - - /* segment 17 */ - struct mpi_coredump_segment_header nic2_regs_seg_hdr; - u32 nic2_regs[NIC_REGS_DUMP_WORD_COUNT]; - - /* segment 18 */ - struct mpi_coredump_segment_header xgmac1_seg_hdr; - u32 xgmac1[XGMAC_DUMP_WORD_COUNT]; - - /* segment 19 */ - struct mpi_coredump_segment_header xgmac2_seg_hdr; - u32 xgmac2[XGMAC_DUMP_WORD_COUNT]; - - /* segment 20 */ - struct mpi_coredump_segment_header code_ram_seg_hdr; - u32 code_ram[CODE_RAM_CNT]; - - /* segment 21 */ - struct mpi_coredump_segment_header memc_ram_seg_hdr; - u32 memc_ram[MEMC_RAM_CNT]; - - /* segment 22 */ - struct mpi_coredump_segment_header xaui_an_hdr; - u32 serdes_xaui_an[XG_SERDES_XAUI_AN_COUNT]; - - /* segment 23 */ - struct mpi_coredump_segment_header xaui_hss_pcs_hdr; - u32 serdes_xaui_hss_pcs[XG_SERDES_XAUI_HSS_PCS_COUNT]; - - /* segment 24 */ - struct mpi_coredump_segment_header xfi_an_hdr; - u32 serdes_xfi_an[XG_SERDES_XFI_AN_COUNT]; - - /* segment 25 */ - struct mpi_coredump_segment_header xfi_train_hdr; - u32 serdes_xfi_train[XG_SERDES_XFI_TRAIN_COUNT]; - - /* segment 26 */ - struct mpi_coredump_segment_header xfi_hss_pcs_hdr; - u32 serdes_xfi_hss_pcs[XG_SERDES_XFI_HSS_PCS_COUNT]; - - /* segment 27 */ - struct mpi_coredump_segment_header xfi_hss_tx_hdr; - u32 serdes_xfi_hss_tx[XG_SERDES_XFI_HSS_TX_COUNT]; - - /* segment 28 */ - struct mpi_coredump_segment_header xfi_hss_rx_hdr; - u32 serdes_xfi_hss_rx[XG_SERDES_XFI_HSS_RX_COUNT]; - - /* segment 29 */ - struct mpi_coredump_segment_header xfi_hss_pll_hdr; - u32 serdes_xfi_hss_pll[XG_SERDES_XFI_HSS_PLL_COUNT]; - - /* segment 30 */ - struct mpi_coredump_segment_header misc_nic_seg_hdr; - struct ql_nic_misc misc_nic_info; - - /* segment 31 */ - /* one interrupt state for each CQ */ - struct mpi_coredump_segment_header intr_states_seg_hdr; - u32 intr_states[MAX_RX_RINGS]; - - /* segment 32 */ - /* 3 cam words each for 16 unicast, - * 2 cam words for each of 32 multicast. - */ - struct mpi_coredump_segment_header cam_entries_seg_hdr; - u32 cam_entries[(16 * 3) + (32 * 3)]; - - /* segment 33 */ - struct mpi_coredump_segment_header nic_routing_words_seg_hdr; - u32 nic_routing_words[16]; - /* segment 34 */ - struct mpi_coredump_segment_header ets_seg_hdr; - u32 ets[ETS_REGS_DUMP_WORD_COUNT]; - - /* segment 35 */ - struct mpi_coredump_segment_header probe_dump_seg_hdr; - u32 probe_dump[PRB_MX_DUMP_TOT_COUNT]; - - /* segment 36 */ - struct mpi_coredump_segment_header routing_reg_seg_hdr; - u32 routing_regs[RT_IDX_DUMP_TOT_WORDS]; - - /* segment 37 */ - struct mpi_coredump_segment_header mac_prot_reg_seg_hdr; - u32 mac_prot_regs[MAC_ADDR_DUMP_TOT_WORDS]; - - /* segment 38 */ - struct mpi_coredump_segment_header xaui2_an_hdr; - u32 serdes2_xaui_an[XG_SERDES_XAUI_AN_COUNT]; - - /* segment 39 */ - struct mpi_coredump_segment_header xaui2_hss_pcs_hdr; - u32 serdes2_xaui_hss_pcs[XG_SERDES_XAUI_HSS_PCS_COUNT]; - - /* segment 40 */ - struct mpi_coredump_segment_header xfi2_an_hdr; - u32 serdes2_xfi_an[XG_SERDES_XFI_AN_COUNT]; - - /* segment 41 */ - struct mpi_coredump_segment_header xfi2_train_hdr; - u32 serdes2_xfi_train[XG_SERDES_XFI_TRAIN_COUNT]; - - /* segment 42 */ - struct mpi_coredump_segment_header xfi2_hss_pcs_hdr; - u32 serdes2_xfi_hss_pcs[XG_SERDES_XFI_HSS_PCS_COUNT]; - - /* segment 43 */ - struct mpi_coredump_segment_header xfi2_hss_tx_hdr; - u32 serdes2_xfi_hss_tx[XG_SERDES_XFI_HSS_TX_COUNT]; - - /* segment 44 */ - struct mpi_coredump_segment_header xfi2_hss_rx_hdr; - u32 serdes2_xfi_hss_rx[XG_SERDES_XFI_HSS_RX_COUNT]; - - /* segment 45 */ - struct mpi_coredump_segment_header xfi2_hss_pll_hdr; - u32 serdes2_xfi_hss_pll[XG_SERDES_XFI_HSS_PLL_COUNT]; - - /* segment 50 */ - /* semaphore register for all 5 functions */ - struct mpi_coredump_segment_header sem_regs_seg_hdr; - u32 sem_regs[MAX_SEMAPHORE_FUNCTIONS]; -}; - -/* - * intr_context structure is used during initialization - * to hook the interrupts. It is also used in a single - * irq environment as a context to the ISR. - */ -struct intr_context { - struct ql_adapter *qdev; - u32 intr; - u32 irq_mask; /* Mask of which rings the vector services. */ - u32 hooked; - u32 intr_en_mask; /* value/mask used to enable this intr */ - u32 intr_dis_mask; /* value/mask used to disable this intr */ - u32 intr_read_mask; /* value/mask used to read this intr */ - char name[IFNAMSIZ * 2]; - atomic_t irq_cnt; /* irq_cnt is used in single vector - * environment. It's incremented for each - * irq handler that is scheduled. When each - * handler finishes it decrements irq_cnt and - * enables interrupts if it's zero. */ - irq_handler_t handler; -}; - -/* adapter flags definitions. */ -enum { - QL_ADAPTER_UP = 0, /* Adapter has been brought up. */ - QL_LEGACY_ENABLED = 1, - QL_MSI_ENABLED = 2, - QL_MSIX_ENABLED = 3, - QL_DMA64 = 4, - QL_PROMISCUOUS = 5, - QL_ALLMULTI = 6, - QL_PORT_CFG = 7, - QL_CAM_RT_SET = 8, - QL_SELFTEST = 9, - QL_LB_LINK_UP = 10, - QL_FRC_COREDUMP = 11, - QL_EEH_FATAL = 12, - QL_ASIC_RECOVERY = 14, /* We are in ascic recovery. */ -}; - -/* link_status bit definitions */ -enum { - STS_LOOPBACK_MASK = 0x00000700, - STS_LOOPBACK_PCS = 0x00000100, - STS_LOOPBACK_HSS = 0x00000200, - STS_LOOPBACK_EXT = 0x00000300, - STS_PAUSE_MASK = 0x000000c0, - STS_PAUSE_STD = 0x00000040, - STS_PAUSE_PRI = 0x00000080, - STS_SPEED_MASK = 0x00000038, - STS_SPEED_100Mb = 0x00000000, - STS_SPEED_1Gb = 0x00000008, - STS_SPEED_10Gb = 0x00000010, - STS_LINK_TYPE_MASK = 0x00000007, - STS_LINK_TYPE_XFI = 0x00000001, - STS_LINK_TYPE_XAUI = 0x00000002, - STS_LINK_TYPE_XFI_BP = 0x00000003, - STS_LINK_TYPE_XAUI_BP = 0x00000004, - STS_LINK_TYPE_10GBASET = 0x00000005, -}; - -/* link_config bit definitions */ -enum { - CFG_JUMBO_FRAME_SIZE = 0x00010000, - CFG_PAUSE_MASK = 0x00000060, - CFG_PAUSE_STD = 0x00000020, - CFG_PAUSE_PRI = 0x00000040, - CFG_DCBX = 0x00000010, - CFG_LOOPBACK_MASK = 0x00000007, - CFG_LOOPBACK_PCS = 0x00000002, - CFG_LOOPBACK_HSS = 0x00000004, - CFG_LOOPBACK_EXT = 0x00000006, - CFG_DEFAULT_MAX_FRAME_SIZE = 0x00002580, -}; - -struct nic_operations { - - int (*get_flash) (struct ql_adapter *); - int (*port_initialize) (struct ql_adapter *); -}; - -/* - * The main Adapter structure definition. - * This structure has all fields relevant to the hardware. - */ -struct ql_adapter { - struct ricb ricb; - unsigned long flags; - u32 wol; - - struct nic_stats nic_stats; - - unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; - - /* PCI Configuration information for this device */ - struct pci_dev *pdev; - struct net_device *ndev; /* Parent NET device */ - - /* Hardware information */ - u32 chip_rev_id; - u32 fw_rev_id; - u32 func; /* PCI function for this adapter */ - u32 alt_func; /* PCI function for alternate adapter */ - u32 port; /* Port number this adapter */ - - spinlock_t adapter_lock; - spinlock_t hw_lock; - spinlock_t stats_lock; - - /* PCI Bus Relative Register Addresses */ - void __iomem *reg_base; - void __iomem *doorbell_area; - u32 doorbell_area_size; - - u32 msg_enable; - - /* Page for Shadow Registers */ - void *rx_ring_shadow_reg_area; - dma_addr_t rx_ring_shadow_reg_dma; - void *tx_ring_shadow_reg_area; - dma_addr_t tx_ring_shadow_reg_dma; - - u32 mailbox_in; - u32 mailbox_out; - struct mbox_params idc_mbc; - struct mutex mpi_mutex; - - int tx_ring_size; - int rx_ring_size; - u32 intr_count; - struct msix_entry *msi_x_entry; - struct intr_context intr_context[MAX_RX_RINGS]; - - int tx_ring_count; /* One per online CPU. */ - u32 rss_ring_count; /* One per irq vector. */ - /* - * rx_ring_count = - * (CPU count * outbound completion rx_ring) + - * (irq_vector_cnt * inbound (RSS) completion rx_ring) - */ - int rx_ring_count; - int ring_mem_size; - void *ring_mem; - - struct rx_ring rx_ring[MAX_RX_RINGS]; - struct tx_ring tx_ring[MAX_TX_RINGS]; - unsigned int lbq_buf_order; - - int rx_csum; - u32 default_rx_queue; - - u16 rx_coalesce_usecs; /* cqicb->int_delay */ - u16 rx_max_coalesced_frames; /* cqicb->pkt_int_delay */ - u16 tx_coalesce_usecs; /* cqicb->int_delay */ - u16 tx_max_coalesced_frames; /* cqicb->pkt_int_delay */ - - u32 xg_sem_mask; - u32 port_link_up; - u32 port_init; - u32 link_status; - struct ql_mpi_coredump *mpi_coredump; - u32 core_is_dumped; - u32 link_config; - u32 led_config; - u32 max_frame_size; - - union flash_params flash; - - struct workqueue_struct *workqueue; - struct delayed_work asic_reset_work; - struct delayed_work mpi_reset_work; - struct delayed_work mpi_work; - struct delayed_work mpi_port_cfg_work; - struct delayed_work mpi_idc_work; - struct delayed_work mpi_core_to_log; - struct completion ide_completion; - const struct nic_operations *nic_ops; - u16 device_id; - struct timer_list timer; - atomic_t lb_count; - /* Keep local copy of current mac address. */ - char current_mac_addr[ETH_ALEN]; -}; - -/* - * Typical Register accessor for memory mapped device. - */ -static inline u32 ql_read32(const struct ql_adapter *qdev, int reg) -{ - return readl(qdev->reg_base + reg); -} - -/* - * Typical Register accessor for memory mapped device. - */ -static inline void ql_write32(const struct ql_adapter *qdev, int reg, u32 val) -{ - writel(val, qdev->reg_base + reg); -} - -/* - * Doorbell Registers: - * Doorbell registers are virtual registers in the PCI memory space. - * The space is allocated by the chip during PCI initialization. The - * device driver finds the doorbell address in BAR 3 in PCI config space. - * The registers are used to control outbound and inbound queues. For - * example, the producer index for an outbound queue. Each queue uses - * 1 4k chunk of memory. The lower half of the space is for outbound - * queues. The upper half is for inbound queues. - */ -static inline void ql_write_db_reg(u32 val, void __iomem *addr) -{ - writel(val, addr); -} - -/* - * Doorbell Registers: - * Doorbell registers are virtual registers in the PCI memory space. - * The space is allocated by the chip during PCI initialization. The - * device driver finds the doorbell address in BAR 3 in PCI config space. - * The registers are used to control outbound and inbound queues. For - * example, the producer index for an outbound queue. Each queue uses - * 1 4k chunk of memory. The lower half of the space is for outbound - * queues. The upper half is for inbound queues. - * Caller has to guarantee ordering. - */ -static inline void ql_write_db_reg_relaxed(u32 val, void __iomem *addr) -{ - writel_relaxed(val, addr); -} - -/* - * Shadow Registers: - * Outbound queues have a consumer index that is maintained by the chip. - * Inbound queues have a producer index that is maintained by the chip. - * For lower overhead, these registers are "shadowed" to host memory - * which allows the device driver to track the queue progress without - * PCI reads. When an entry is placed on an inbound queue, the chip will - * update the relevant index register and then copy the value to the - * shadow register in host memory. - */ -static inline u32 ql_read_sh_reg(__le32 *addr) -{ - u32 reg; - reg = le32_to_cpu(*addr); - rmb(); - return reg; -} - -extern char qlge_driver_name[]; -extern const char qlge_driver_version[]; -extern const struct ethtool_ops qlge_ethtool_ops; - -int ql_sem_spinlock(struct ql_adapter *qdev, u32 sem_mask); -void ql_sem_unlock(struct ql_adapter *qdev, u32 sem_mask); -int ql_read_xgmac_reg(struct ql_adapter *qdev, u32 reg, u32 *data); -int ql_get_mac_addr_reg(struct ql_adapter *qdev, u32 type, u16 index, - u32 *value); -int ql_get_routing_reg(struct ql_adapter *qdev, u32 index, u32 *value); -int ql_write_cfg(struct ql_adapter *qdev, void *ptr, int size, u32 bit, - u16 q_id); -void ql_queue_fw_error(struct ql_adapter *qdev); -void ql_mpi_work(struct work_struct *work); -void ql_mpi_reset_work(struct work_struct *work); -void ql_mpi_core_to_log(struct work_struct *work); -int ql_wait_reg_rdy(struct ql_adapter *qdev, u32 reg, u32 bit, u32 ebit); -void ql_queue_asic_error(struct ql_adapter *qdev); -u32 ql_enable_completion_interrupt(struct ql_adapter *qdev, u32 intr); -void ql_set_ethtool_ops(struct net_device *ndev); -int ql_read_xgmac_reg64(struct ql_adapter *qdev, u32 reg, u64 *data); -void ql_mpi_idc_work(struct work_struct *work); -void ql_mpi_port_cfg_work(struct work_struct *work); -int ql_mb_get_fw_state(struct ql_adapter *qdev); -int ql_cam_route_initialize(struct ql_adapter *qdev); -int ql_read_mpi_reg(struct ql_adapter *qdev, u32 reg, u32 *data); -int ql_write_mpi_reg(struct ql_adapter *qdev, u32 reg, u32 data); -int ql_unpause_mpi_risc(struct ql_adapter *qdev); -int ql_pause_mpi_risc(struct ql_adapter *qdev); -int ql_hard_reset_mpi_risc(struct ql_adapter *qdev); -int ql_soft_reset_mpi_risc(struct ql_adapter *qdev); -int ql_dump_risc_ram_area(struct ql_adapter *qdev, void *buf, u32 ram_addr, - int word_count); -int ql_core_dump(struct ql_adapter *qdev, struct ql_mpi_coredump *mpi_coredump); -int ql_mb_about_fw(struct ql_adapter *qdev); -int ql_mb_wol_set_magic(struct ql_adapter *qdev, u32 enable_wol); -int ql_mb_wol_mode(struct ql_adapter *qdev, u32 wol); -int ql_mb_set_led_cfg(struct ql_adapter *qdev, u32 led_config); -int ql_mb_get_led_cfg(struct ql_adapter *qdev); -void ql_link_on(struct ql_adapter *qdev); -void ql_link_off(struct ql_adapter *qdev); -int ql_mb_set_mgmnt_traffic_ctl(struct ql_adapter *qdev, u32 control); -int ql_mb_get_port_cfg(struct ql_adapter *qdev); -int ql_mb_set_port_cfg(struct ql_adapter *qdev); -int ql_wait_fifo_empty(struct ql_adapter *qdev); -void ql_get_dump(struct ql_adapter *qdev, void *buff); -netdev_tx_t ql_lb_send(struct sk_buff *skb, struct net_device *ndev); -void ql_check_lb_frame(struct ql_adapter *, struct sk_buff *); -int ql_own_firmware(struct ql_adapter *qdev); -int ql_clean_lb_rx_ring(struct rx_ring *rx_ring, int budget); - -/* #define QL_ALL_DUMP */ -/* #define QL_REG_DUMP */ -/* #define QL_DEV_DUMP */ -/* #define QL_CB_DUMP */ -/* #define QL_IB_DUMP */ -/* #define QL_OB_DUMP */ - -#ifdef QL_REG_DUMP -void ql_dump_xgmac_control_regs(struct ql_adapter *qdev); -void ql_dump_routing_entries(struct ql_adapter *qdev); -void ql_dump_regs(struct ql_adapter *qdev); -#define QL_DUMP_REGS(qdev) ql_dump_regs(qdev) -#define QL_DUMP_ROUTE(qdev) ql_dump_routing_entries(qdev) -#define QL_DUMP_XGMAC_CONTROL_REGS(qdev) ql_dump_xgmac_control_regs(qdev) -#else -#define QL_DUMP_REGS(qdev) -#define QL_DUMP_ROUTE(qdev) -#define QL_DUMP_XGMAC_CONTROL_REGS(qdev) -#endif - -#ifdef QL_STAT_DUMP -void ql_dump_stat(struct ql_adapter *qdev); -#define QL_DUMP_STAT(qdev) ql_dump_stat(qdev) -#else -#define QL_DUMP_STAT(qdev) -#endif - -#ifdef QL_DEV_DUMP -void ql_dump_qdev(struct ql_adapter *qdev); -#define QL_DUMP_QDEV(qdev) ql_dump_qdev(qdev) -#else -#define QL_DUMP_QDEV(qdev) -#endif - -#ifdef QL_CB_DUMP -void ql_dump_wqicb(struct wqicb *wqicb); -void ql_dump_tx_ring(struct tx_ring *tx_ring); -void ql_dump_ricb(struct ricb *ricb); -void ql_dump_cqicb(struct cqicb *cqicb); -void ql_dump_rx_ring(struct rx_ring *rx_ring); -void ql_dump_hw_cb(struct ql_adapter *qdev, int size, u32 bit, u16 q_id); -#define QL_DUMP_RICB(ricb) ql_dump_ricb(ricb) -#define QL_DUMP_WQICB(wqicb) ql_dump_wqicb(wqicb) -#define QL_DUMP_TX_RING(tx_ring) ql_dump_tx_ring(tx_ring) -#define QL_DUMP_CQICB(cqicb) ql_dump_cqicb(cqicb) -#define QL_DUMP_RX_RING(rx_ring) ql_dump_rx_ring(rx_ring) -#define QL_DUMP_HW_CB(qdev, size, bit, q_id) \ - ql_dump_hw_cb(qdev, size, bit, q_id) -#else -#define QL_DUMP_RICB(ricb) -#define QL_DUMP_WQICB(wqicb) -#define QL_DUMP_TX_RING(tx_ring) -#define QL_DUMP_CQICB(cqicb) -#define QL_DUMP_RX_RING(rx_ring) -#define QL_DUMP_HW_CB(qdev, size, bit, q_id) -#endif - -#ifdef QL_OB_DUMP -void ql_dump_tx_desc(struct tx_buf_desc *tbd); -void ql_dump_ob_mac_iocb(struct ob_mac_iocb_req *ob_mac_iocb); -void ql_dump_ob_mac_rsp(struct ob_mac_iocb_rsp *ob_mac_rsp); -#define QL_DUMP_OB_MAC_IOCB(ob_mac_iocb) ql_dump_ob_mac_iocb(ob_mac_iocb) -#define QL_DUMP_OB_MAC_RSP(ob_mac_rsp) ql_dump_ob_mac_rsp(ob_mac_rsp) -#else -#define QL_DUMP_OB_MAC_IOCB(ob_mac_iocb) -#define QL_DUMP_OB_MAC_RSP(ob_mac_rsp) -#endif - -#ifdef QL_IB_DUMP -void ql_dump_ib_mac_rsp(struct ib_mac_iocb_rsp *ib_mac_rsp); -#define QL_DUMP_IB_MAC_RSP(ib_mac_rsp) ql_dump_ib_mac_rsp(ib_mac_rsp) -#else -#define QL_DUMP_IB_MAC_RSP(ib_mac_rsp) -#endif - -#ifdef QL_ALL_DUMP -void ql_dump_all(struct ql_adapter *qdev); -#define QL_DUMP_ALL(qdev) ql_dump_all(qdev) -#else -#define QL_DUMP_ALL(qdev) -#endif - -#endif /* _QLGE_H_ */ diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c b/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c deleted file mode 100644 index 31389ab8bdf7..000000000000 --- a/drivers/net/ethernet/qlogic/qlge/qlge_dbg.c +++ /dev/null @@ -1,2024 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/slab.h> - -#include "qlge.h" - -/* Read a NIC register from the alternate function. */ -static u32 ql_read_other_func_reg(struct ql_adapter *qdev, - u32 reg) -{ - u32 register_to_read; - u32 reg_val; - unsigned int status = 0; - - register_to_read = MPI_NIC_REG_BLOCK - | MPI_NIC_READ - | (qdev->alt_func << MPI_NIC_FUNCTION_SHIFT) - | reg; - status = ql_read_mpi_reg(qdev, register_to_read, ®_val); - if (status != 0) - return 0xffffffff; - - return reg_val; -} - -/* Write a NIC register from the alternate function. */ -static int ql_write_other_func_reg(struct ql_adapter *qdev, - u32 reg, u32 reg_val) -{ - u32 register_to_read; - int status = 0; - - register_to_read = MPI_NIC_REG_BLOCK - | MPI_NIC_READ - | (qdev->alt_func << MPI_NIC_FUNCTION_SHIFT) - | reg; - status = ql_write_mpi_reg(qdev, register_to_read, reg_val); - - return status; -} - -static int ql_wait_other_func_reg_rdy(struct ql_adapter *qdev, u32 reg, - u32 bit, u32 err_bit) -{ - u32 temp; - int count = 10; - - while (count) { - temp = ql_read_other_func_reg(qdev, reg); - - /* check for errors */ - if (temp & err_bit) - return -1; - else if (temp & bit) - return 0; - mdelay(10); - count--; - } - return -1; -} - -static int ql_read_other_func_serdes_reg(struct ql_adapter *qdev, u32 reg, - u32 *data) -{ - int status; - - /* wait for reg to come ready */ - status = ql_wait_other_func_reg_rdy(qdev, XG_SERDES_ADDR / 4, - XG_SERDES_ADDR_RDY, 0); - if (status) - goto exit; - - /* set up for reg read */ - ql_write_other_func_reg(qdev, XG_SERDES_ADDR/4, reg | PROC_ADDR_R); - - /* wait for reg to come ready */ - status = ql_wait_other_func_reg_rdy(qdev, XG_SERDES_ADDR / 4, - XG_SERDES_ADDR_RDY, 0); - if (status) - goto exit; - - /* get the data */ - *data = ql_read_other_func_reg(qdev, (XG_SERDES_DATA / 4)); -exit: - return status; -} - -/* Read out the SERDES registers */ -static int ql_read_serdes_reg(struct ql_adapter *qdev, u32 reg, u32 *data) -{ - int status; - - /* wait for reg to come ready */ - status = ql_wait_reg_rdy(qdev, XG_SERDES_ADDR, XG_SERDES_ADDR_RDY, 0); - if (status) - goto exit; - - /* set up for reg read */ - ql_write32(qdev, XG_SERDES_ADDR, reg | PROC_ADDR_R); - - /* wait for reg to come ready */ - status = ql_wait_reg_rdy(qdev, XG_SERDES_ADDR, XG_SERDES_ADDR_RDY, 0); - if (status) - goto exit; - - /* get the data */ - *data = ql_read32(qdev, XG_SERDES_DATA); -exit: - return status; -} - -static void ql_get_both_serdes(struct ql_adapter *qdev, u32 addr, - u32 *direct_ptr, u32 *indirect_ptr, - unsigned int direct_valid, unsigned int indirect_valid) -{ - unsigned int status; - - status = 1; - if (direct_valid) - status = ql_read_serdes_reg(qdev, addr, direct_ptr); - /* Dead fill any failures or invalids. */ - if (status) - *direct_ptr = 0xDEADBEEF; - - status = 1; - if (indirect_valid) - status = ql_read_other_func_serdes_reg( - qdev, addr, indirect_ptr); - /* Dead fill any failures or invalids. */ - if (status) - *indirect_ptr = 0xDEADBEEF; -} - -static int ql_get_serdes_regs(struct ql_adapter *qdev, - struct ql_mpi_coredump *mpi_coredump) -{ - int status; - unsigned int xfi_direct_valid, xfi_indirect_valid, xaui_direct_valid; - unsigned int xaui_indirect_valid, i; - u32 *direct_ptr, temp; - u32 *indirect_ptr; - - xfi_direct_valid = xfi_indirect_valid = 0; - xaui_direct_valid = xaui_indirect_valid = 1; - - /* The XAUI needs to be read out per port */ - status = ql_read_other_func_serdes_reg(qdev, - XG_SERDES_XAUI_HSS_PCS_START, &temp); - if (status) - temp = XG_SERDES_ADDR_XAUI_PWR_DOWN; - - if ((temp & XG_SERDES_ADDR_XAUI_PWR_DOWN) == - XG_SERDES_ADDR_XAUI_PWR_DOWN) - xaui_indirect_valid = 0; - - status = ql_read_serdes_reg(qdev, XG_SERDES_XAUI_HSS_PCS_START, &temp); - - if (status) - temp = XG_SERDES_ADDR_XAUI_PWR_DOWN; - - if ((temp & XG_SERDES_ADDR_XAUI_PWR_DOWN) == - XG_SERDES_ADDR_XAUI_PWR_DOWN) - xaui_direct_valid = 0; - - /* - * XFI register is shared so only need to read one - * functions and then check the bits. - */ - status = ql_read_serdes_reg(qdev, XG_SERDES_ADDR_STS, &temp); - if (status) - temp = 0; - - if ((temp & XG_SERDES_ADDR_XFI1_PWR_UP) == - XG_SERDES_ADDR_XFI1_PWR_UP) { - /* now see if i'm NIC 1 or NIC 2 */ - if (qdev->func & 1) - /* I'm NIC 2, so the indirect (NIC1) xfi is up. */ - xfi_indirect_valid = 1; - else - xfi_direct_valid = 1; - } - if ((temp & XG_SERDES_ADDR_XFI2_PWR_UP) == - XG_SERDES_ADDR_XFI2_PWR_UP) { - /* now see if i'm NIC 1 or NIC 2 */ - if (qdev->func & 1) - /* I'm NIC 2, so the indirect (NIC1) xfi is up. */ - xfi_direct_valid = 1; - else - xfi_indirect_valid = 1; - } - - /* Get XAUI_AN register block. */ - if (qdev->func & 1) { - /* Function 2 is direct */ - direct_ptr = mpi_coredump->serdes2_xaui_an; - indirect_ptr = mpi_coredump->serdes_xaui_an; - } else { - /* Function 1 is direct */ - direct_ptr = mpi_coredump->serdes_xaui_an; - indirect_ptr = mpi_coredump->serdes2_xaui_an; - } - - for (i = 0; i <= 0x000000034; i += 4, direct_ptr++, indirect_ptr++) - ql_get_both_serdes(qdev, i, direct_ptr, indirect_ptr, - xaui_direct_valid, xaui_indirect_valid); - - /* Get XAUI_HSS_PCS register block. */ - if (qdev->func & 1) { - direct_ptr = - mpi_coredump->serdes2_xaui_hss_pcs; - indirect_ptr = - mpi_coredump->serdes_xaui_hss_pcs; - } else { - direct_ptr = - mpi_coredump->serdes_xaui_hss_pcs; - indirect_ptr = - mpi_coredump->serdes2_xaui_hss_pcs; - } - - for (i = 0x800; i <= 0x880; i += 4, direct_ptr++, indirect_ptr++) - ql_get_both_serdes(qdev, i, direct_ptr, indirect_ptr, - xaui_direct_valid, xaui_indirect_valid); - - /* Get XAUI_XFI_AN register block. */ - if (qdev->func & 1) { - direct_ptr = mpi_coredump->serdes2_xfi_an; - indirect_ptr = mpi_coredump->serdes_xfi_an; - } else { - direct_ptr = mpi_coredump->serdes_xfi_an; - indirect_ptr = mpi_coredump->serdes2_xfi_an; - } - - for (i = 0x1000; i <= 0x1034; i += 4, direct_ptr++, indirect_ptr++) - ql_get_both_serdes(qdev, i, direct_ptr, indirect_ptr, - xfi_direct_valid, xfi_indirect_valid); - - /* Get XAUI_XFI_TRAIN register block. */ - if (qdev->func & 1) { - direct_ptr = mpi_coredump->serdes2_xfi_train; - indirect_ptr = - mpi_coredump->serdes_xfi_train; - } else { - direct_ptr = mpi_coredump->serdes_xfi_train; - indirect_ptr = - mpi_coredump->serdes2_xfi_train; - } - - for (i = 0x1050; i <= 0x107c; i += 4, direct_ptr++, indirect_ptr++) - ql_get_both_serdes(qdev, i, direct_ptr, indirect_ptr, - xfi_direct_valid, xfi_indirect_valid); - - /* Get XAUI_XFI_HSS_PCS register block. */ - if (qdev->func & 1) { - direct_ptr = - mpi_coredump->serdes2_xfi_hss_pcs; - indirect_ptr = - mpi_coredump->serdes_xfi_hss_pcs; - } else { - direct_ptr = - mpi_coredump->serdes_xfi_hss_pcs; - indirect_ptr = - mpi_coredump->serdes2_xfi_hss_pcs; - } - - for (i = 0x1800; i <= 0x1838; i += 4, direct_ptr++, indirect_ptr++) - ql_get_both_serdes(qdev, i, direct_ptr, indirect_ptr, - xfi_direct_valid, xfi_indirect_valid); - - /* Get XAUI_XFI_HSS_TX register block. */ - if (qdev->func & 1) { - direct_ptr = - mpi_coredump->serdes2_xfi_hss_tx; - indirect_ptr = - mpi_coredump->serdes_xfi_hss_tx; - } else { - direct_ptr = mpi_coredump->serdes_xfi_hss_tx; - indirect_ptr = - mpi_coredump->serdes2_xfi_hss_tx; - } - for (i = 0x1c00; i <= 0x1c1f; i++, direct_ptr++, indirect_ptr++) - ql_get_both_serdes(qdev, i, direct_ptr, indirect_ptr, - xfi_direct_valid, xfi_indirect_valid); - - /* Get XAUI_XFI_HSS_RX register block. */ - if (qdev->func & 1) { - direct_ptr = - mpi_coredump->serdes2_xfi_hss_rx; - indirect_ptr = - mpi_coredump->serdes_xfi_hss_rx; - } else { - direct_ptr = mpi_coredump->serdes_xfi_hss_rx; - indirect_ptr = - mpi_coredump->serdes2_xfi_hss_rx; - } - - for (i = 0x1c40; i <= 0x1c5f; i++, direct_ptr++, indirect_ptr++) - ql_get_both_serdes(qdev, i, direct_ptr, indirect_ptr, - xfi_direct_valid, xfi_indirect_valid); - - - /* Get XAUI_XFI_HSS_PLL register block. */ - if (qdev->func & 1) { - direct_ptr = - mpi_coredump->serdes2_xfi_hss_pll; - indirect_ptr = - mpi_coredump->serdes_xfi_hss_pll; - } else { - direct_ptr = - mpi_coredump->serdes_xfi_hss_pll; - indirect_ptr = - mpi_coredump->serdes2_xfi_hss_pll; - } - for (i = 0x1e00; i <= 0x1e1f; i++, direct_ptr++, indirect_ptr++) - ql_get_both_serdes(qdev, i, direct_ptr, indirect_ptr, - xfi_direct_valid, xfi_indirect_valid); - return 0; -} - -static int ql_read_other_func_xgmac_reg(struct ql_adapter *qdev, u32 reg, - u32 *data) -{ - int status = 0; - - /* wait for reg to come ready */ - status = ql_wait_other_func_reg_rdy(qdev, XGMAC_ADDR / 4, - XGMAC_ADDR_RDY, XGMAC_ADDR_XME); - if (status) - goto exit; - - /* set up for reg read */ - ql_write_other_func_reg(qdev, XGMAC_ADDR / 4, reg | XGMAC_ADDR_R); - - /* wait for reg to come ready */ - status = ql_wait_other_func_reg_rdy(qdev, XGMAC_ADDR / 4, - XGMAC_ADDR_RDY, XGMAC_ADDR_XME); - if (status) - goto exit; - - /* get the data */ - *data = ql_read_other_func_reg(qdev, XGMAC_DATA / 4); -exit: - return status; -} - -/* Read the 400 xgmac control/statistics registers - * skipping unused locations. - */ -static int ql_get_xgmac_regs(struct ql_adapter *qdev, u32 *buf, - unsigned int other_function) -{ - int status = 0; - int i; - - for (i = PAUSE_SRC_LO; i < XGMAC_REGISTER_END; i += 4, buf++) { - /* We're reading 400 xgmac registers, but we filter out - * serveral locations that are non-responsive to reads. - */ - if ((i == 0x00000114) || - (i == 0x00000118) || - (i == 0x0000013c) || - (i == 0x00000140) || - (i > 0x00000150 && i < 0x000001fc) || - (i > 0x00000278 && i < 0x000002a0) || - (i > 0x000002c0 && i < 0x000002cf) || - (i > 0x000002dc && i < 0x000002f0) || - (i > 0x000003c8 && i < 0x00000400) || - (i > 0x00000400 && i < 0x00000410) || - (i > 0x00000410 && i < 0x00000420) || - (i > 0x00000420 && i < 0x00000430) || - (i > 0x00000430 && i < 0x00000440) || - (i > 0x00000440 && i < 0x00000450) || - (i > 0x00000450 && i < 0x00000500) || - (i > 0x0000054c && i < 0x00000568) || - (i > 0x000005c8 && i < 0x00000600)) { - if (other_function) - status = - ql_read_other_func_xgmac_reg(qdev, i, buf); - else - status = ql_read_xgmac_reg(qdev, i, buf); - - if (status) - *buf = 0xdeadbeef; - break; - } - } - return status; -} - -static int ql_get_ets_regs(struct ql_adapter *qdev, u32 *buf) -{ - int status = 0; - int i; - - for (i = 0; i < 8; i++, buf++) { - ql_write32(qdev, NIC_ETS, i << 29 | 0x08000000); - *buf = ql_read32(qdev, NIC_ETS); - } - - for (i = 0; i < 2; i++, buf++) { - ql_write32(qdev, CNA_ETS, i << 29 | 0x08000000); - *buf = ql_read32(qdev, CNA_ETS); - } - - return status; -} - -static void ql_get_intr_states(struct ql_adapter *qdev, u32 *buf) -{ - int i; - - for (i = 0; i < qdev->rx_ring_count; i++, buf++) { - ql_write32(qdev, INTR_EN, - qdev->intr_context[i].intr_read_mask); - *buf = ql_read32(qdev, INTR_EN); - } -} - -static int ql_get_cam_entries(struct ql_adapter *qdev, u32 *buf) -{ - int i, status; - u32 value[3]; - - status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK); - if (status) - return status; - - for (i = 0; i < 16; i++) { - status = ql_get_mac_addr_reg(qdev, - MAC_ADDR_TYPE_CAM_MAC, i, value); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Failed read of mac index register\n"); - goto err; - } - *buf++ = value[0]; /* lower MAC address */ - *buf++ = value[1]; /* upper MAC address */ - *buf++ = value[2]; /* output */ - } - for (i = 0; i < 32; i++) { - status = ql_get_mac_addr_reg(qdev, - MAC_ADDR_TYPE_MULTI_MAC, i, value); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Failed read of mac index register\n"); - goto err; - } - *buf++ = value[0]; /* lower Mcast address */ - *buf++ = value[1]; /* upper Mcast address */ - } -err: - ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK); - return status; -} - -static int ql_get_routing_entries(struct ql_adapter *qdev, u32 *buf) -{ - int status; - u32 value, i; - - status = ql_sem_spinlock(qdev, SEM_RT_IDX_MASK); - if (status) - return status; - - for (i = 0; i < 16; i++) { - status = ql_get_routing_reg(qdev, i, &value); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Failed read of routing index register\n"); - goto err; - } else { - *buf++ = value; - } - } -err: - ql_sem_unlock(qdev, SEM_RT_IDX_MASK); - return status; -} - -/* Read the MPI Processor shadow registers */ -static int ql_get_mpi_shadow_regs(struct ql_adapter *qdev, u32 *buf) -{ - u32 i; - int status; - - for (i = 0; i < MPI_CORE_SH_REGS_CNT; i++, buf++) { - status = ql_write_mpi_reg(qdev, RISC_124, - (SHADOW_OFFSET | i << SHADOW_REG_SHIFT)); - if (status) - goto end; - status = ql_read_mpi_reg(qdev, RISC_127, buf); - if (status) - goto end; - } -end: - return status; -} - -/* Read the MPI Processor core registers */ -static int ql_get_mpi_regs(struct ql_adapter *qdev, u32 *buf, - u32 offset, u32 count) -{ - int i, status = 0; - for (i = 0; i < count; i++, buf++) { - status = ql_read_mpi_reg(qdev, offset + i, buf); - if (status) - return status; - } - return status; -} - -/* Read the ASIC probe dump */ -static unsigned int *ql_get_probe(struct ql_adapter *qdev, u32 clock, - u32 valid, u32 *buf) -{ - u32 module, mux_sel, probe, lo_val, hi_val; - - for (module = 0; module < PRB_MX_ADDR_MAX_MODS; module++) { - if (!((valid >> module) & 1)) - continue; - for (mux_sel = 0; mux_sel < PRB_MX_ADDR_MAX_MUX; mux_sel++) { - probe = clock - | PRB_MX_ADDR_ARE - | mux_sel - | (module << PRB_MX_ADDR_MOD_SEL_SHIFT); - ql_write32(qdev, PRB_MX_ADDR, probe); - lo_val = ql_read32(qdev, PRB_MX_DATA); - if (mux_sel == 0) { - *buf = probe; - buf++; - } - probe |= PRB_MX_ADDR_UP; - ql_write32(qdev, PRB_MX_ADDR, probe); - hi_val = ql_read32(qdev, PRB_MX_DATA); - *buf = lo_val; - buf++; - *buf = hi_val; - buf++; - } - } - return buf; -} - -static int ql_get_probe_dump(struct ql_adapter *qdev, unsigned int *buf) -{ - /* First we have to enable the probe mux */ - ql_write_mpi_reg(qdev, MPI_TEST_FUNC_PRB_CTL, MPI_TEST_FUNC_PRB_EN); - buf = ql_get_probe(qdev, PRB_MX_ADDR_SYS_CLOCK, - PRB_MX_ADDR_VALID_SYS_MOD, buf); - buf = ql_get_probe(qdev, PRB_MX_ADDR_PCI_CLOCK, - PRB_MX_ADDR_VALID_PCI_MOD, buf); - buf = ql_get_probe(qdev, PRB_MX_ADDR_XGM_CLOCK, - PRB_MX_ADDR_VALID_XGM_MOD, buf); - buf = ql_get_probe(qdev, PRB_MX_ADDR_FC_CLOCK, - PRB_MX_ADDR_VALID_FC_MOD, buf); - return 0; - -} - -/* Read out the routing index registers */ -static int ql_get_routing_index_registers(struct ql_adapter *qdev, u32 *buf) -{ - int status; - u32 type, index, index_max; - u32 result_index; - u32 result_data; - u32 val; - - status = ql_sem_spinlock(qdev, SEM_RT_IDX_MASK); - if (status) - return status; - - for (type = 0; type < 4; type++) { - if (type < 2) - index_max = 8; - else - index_max = 16; - for (index = 0; index < index_max; index++) { - val = RT_IDX_RS - | (type << RT_IDX_TYPE_SHIFT) - | (index << RT_IDX_IDX_SHIFT); - ql_write32(qdev, RT_IDX, val); - result_index = 0; - while ((result_index & RT_IDX_MR) == 0) - result_index = ql_read32(qdev, RT_IDX); - result_data = ql_read32(qdev, RT_DATA); - *buf = type; - buf++; - *buf = index; - buf++; - *buf = result_index; - buf++; - *buf = result_data; - buf++; - } - } - ql_sem_unlock(qdev, SEM_RT_IDX_MASK); - return status; -} - -/* Read out the MAC protocol registers */ -static void ql_get_mac_protocol_registers(struct ql_adapter *qdev, u32 *buf) -{ - u32 result_index, result_data; - u32 type; - u32 index; - u32 offset; - u32 val; - u32 initial_val = MAC_ADDR_RS; - u32 max_index; - u32 max_offset; - - for (type = 0; type < MAC_ADDR_TYPE_COUNT; type++) { - switch (type) { - - case 0: /* CAM */ - initial_val |= MAC_ADDR_ADR; - max_index = MAC_ADDR_MAX_CAM_ENTRIES; - max_offset = MAC_ADDR_MAX_CAM_WCOUNT; - break; - case 1: /* Multicast MAC Address */ - max_index = MAC_ADDR_MAX_CAM_WCOUNT; - max_offset = MAC_ADDR_MAX_CAM_WCOUNT; - break; - case 2: /* VLAN filter mask */ - case 3: /* MC filter mask */ - max_index = MAC_ADDR_MAX_CAM_WCOUNT; - max_offset = MAC_ADDR_MAX_CAM_WCOUNT; - break; - case 4: /* FC MAC addresses */ - max_index = MAC_ADDR_MAX_FC_MAC_ENTRIES; - max_offset = MAC_ADDR_MAX_FC_MAC_WCOUNT; - break; - case 5: /* Mgmt MAC addresses */ - max_index = MAC_ADDR_MAX_MGMT_MAC_ENTRIES; - max_offset = MAC_ADDR_MAX_MGMT_MAC_WCOUNT; - break; - case 6: /* Mgmt VLAN addresses */ - max_index = MAC_ADDR_MAX_MGMT_VLAN_ENTRIES; - max_offset = MAC_ADDR_MAX_MGMT_VLAN_WCOUNT; - break; - case 7: /* Mgmt IPv4 address */ - max_index = MAC_ADDR_MAX_MGMT_V4_ENTRIES; - max_offset = MAC_ADDR_MAX_MGMT_V4_WCOUNT; - break; - case 8: /* Mgmt IPv6 address */ - max_index = MAC_ADDR_MAX_MGMT_V6_ENTRIES; - max_offset = MAC_ADDR_MAX_MGMT_V6_WCOUNT; - break; - case 9: /* Mgmt TCP/UDP Dest port */ - max_index = MAC_ADDR_MAX_MGMT_TU_DP_ENTRIES; - max_offset = MAC_ADDR_MAX_MGMT_TU_DP_WCOUNT; - break; - default: - pr_err("Bad type!!! 0x%08x\n", type); - max_index = 0; - max_offset = 0; - break; - } - for (index = 0; index < max_index; index++) { - for (offset = 0; offset < max_offset; offset++) { - val = initial_val - | (type << MAC_ADDR_TYPE_SHIFT) - | (index << MAC_ADDR_IDX_SHIFT) - | (offset); - ql_write32(qdev, MAC_ADDR_IDX, val); - result_index = 0; - while ((result_index & MAC_ADDR_MR) == 0) { - result_index = ql_read32(qdev, - MAC_ADDR_IDX); - } - result_data = ql_read32(qdev, MAC_ADDR_DATA); - *buf = result_index; - buf++; - *buf = result_data; - buf++; - } - } - } -} - -static void ql_get_sem_registers(struct ql_adapter *qdev, u32 *buf) -{ - u32 func_num, reg, reg_val; - int status; - - for (func_num = 0; func_num < MAX_SEMAPHORE_FUNCTIONS ; func_num++) { - reg = MPI_NIC_REG_BLOCK - | (func_num << MPI_NIC_FUNCTION_SHIFT) - | (SEM / 4); - status = ql_read_mpi_reg(qdev, reg, ®_val); - *buf = reg_val; - /* if the read failed then dead fill the element. */ - if (!status) - *buf = 0xdeadbeef; - buf++; - } -} - -/* Create a coredump segment header */ -static void ql_build_coredump_seg_header( - struct mpi_coredump_segment_header *seg_hdr, - u32 seg_number, u32 seg_size, u8 *desc) -{ - memset(seg_hdr, 0, sizeof(struct mpi_coredump_segment_header)); - seg_hdr->cookie = MPI_COREDUMP_COOKIE; - seg_hdr->segNum = seg_number; - seg_hdr->segSize = seg_size; - strncpy(seg_hdr->description, desc, (sizeof(seg_hdr->description)) - 1); -} - -/* - * This function should be called when a coredump / probedump - * is to be extracted from the HBA. It is assumed there is a - * qdev structure that contains the base address of the register - * space for this function as well as a coredump structure that - * will contain the dump. - */ -int ql_core_dump(struct ql_adapter *qdev, struct ql_mpi_coredump *mpi_coredump) -{ - int status; - int i; - - if (!mpi_coredump) { - netif_err(qdev, drv, qdev->ndev, "No memory allocated\n"); - return -EINVAL; - } - - /* Try to get the spinlock, but dont worry if - * it isn't available. If the firmware died it - * might be holding the sem. - */ - ql_sem_spinlock(qdev, SEM_PROC_REG_MASK); - - status = ql_pause_mpi_risc(qdev); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Failed RISC pause. Status = 0x%.08x\n", status); - goto err; - } - - /* Insert the global header */ - memset(&(mpi_coredump->mpi_global_header), 0, - sizeof(struct mpi_coredump_global_header)); - mpi_coredump->mpi_global_header.cookie = MPI_COREDUMP_COOKIE; - mpi_coredump->mpi_global_header.headerSize = - sizeof(struct mpi_coredump_global_header); - mpi_coredump->mpi_global_header.imageSize = - sizeof(struct ql_mpi_coredump); - strncpy(mpi_coredump->mpi_global_header.idString, "MPI Coredump", - sizeof(mpi_coredump->mpi_global_header.idString)); - - /* Get generic NIC reg dump */ - ql_build_coredump_seg_header(&mpi_coredump->nic_regs_seg_hdr, - NIC1_CONTROL_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->nic_regs), "NIC1 Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->nic2_regs_seg_hdr, - NIC2_CONTROL_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->nic2_regs), "NIC2 Registers"); - - /* Get XGMac registers. (Segment 18, Rev C. step 21) */ - ql_build_coredump_seg_header(&mpi_coredump->xgmac1_seg_hdr, - NIC1_XGMAC_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->xgmac1), "NIC1 XGMac Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xgmac2_seg_hdr, - NIC2_XGMAC_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->xgmac2), "NIC2 XGMac Registers"); - - if (qdev->func & 1) { - /* Odd means our function is NIC 2 */ - for (i = 0; i < NIC_REGS_DUMP_WORD_COUNT; i++) - mpi_coredump->nic2_regs[i] = - ql_read32(qdev, i * sizeof(u32)); - - for (i = 0; i < NIC_REGS_DUMP_WORD_COUNT; i++) - mpi_coredump->nic_regs[i] = - ql_read_other_func_reg(qdev, (i * sizeof(u32)) / 4); - - ql_get_xgmac_regs(qdev, &mpi_coredump->xgmac2[0], 0); - ql_get_xgmac_regs(qdev, &mpi_coredump->xgmac1[0], 1); - } else { - /* Even means our function is NIC 1 */ - for (i = 0; i < NIC_REGS_DUMP_WORD_COUNT; i++) - mpi_coredump->nic_regs[i] = - ql_read32(qdev, i * sizeof(u32)); - for (i = 0; i < NIC_REGS_DUMP_WORD_COUNT; i++) - mpi_coredump->nic2_regs[i] = - ql_read_other_func_reg(qdev, (i * sizeof(u32)) / 4); - - ql_get_xgmac_regs(qdev, &mpi_coredump->xgmac1[0], 0); - ql_get_xgmac_regs(qdev, &mpi_coredump->xgmac2[0], 1); - } - - /* Rev C. Step 20a */ - ql_build_coredump_seg_header(&mpi_coredump->xaui_an_hdr, - XAUI_AN_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes_xaui_an), - "XAUI AN Registers"); - - /* Rev C. Step 20b */ - ql_build_coredump_seg_header(&mpi_coredump->xaui_hss_pcs_hdr, - XAUI_HSS_PCS_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes_xaui_hss_pcs), - "XAUI HSS PCS Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi_an_hdr, XFI_AN_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes_xfi_an), - "XFI AN Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi_train_hdr, - XFI_TRAIN_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes_xfi_train), - "XFI TRAIN Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi_hss_pcs_hdr, - XFI_HSS_PCS_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes_xfi_hss_pcs), - "XFI HSS PCS Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi_hss_tx_hdr, - XFI_HSS_TX_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes_xfi_hss_tx), - "XFI HSS TX Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi_hss_rx_hdr, - XFI_HSS_RX_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes_xfi_hss_rx), - "XFI HSS RX Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi_hss_pll_hdr, - XFI_HSS_PLL_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes_xfi_hss_pll), - "XFI HSS PLL Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xaui2_an_hdr, - XAUI2_AN_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes2_xaui_an), - "XAUI2 AN Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xaui2_hss_pcs_hdr, - XAUI2_HSS_PCS_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes2_xaui_hss_pcs), - "XAUI2 HSS PCS Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi2_an_hdr, - XFI2_AN_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes2_xfi_an), - "XFI2 AN Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi2_train_hdr, - XFI2_TRAIN_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes2_xfi_train), - "XFI2 TRAIN Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi2_hss_pcs_hdr, - XFI2_HSS_PCS_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes2_xfi_hss_pcs), - "XFI2 HSS PCS Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi2_hss_tx_hdr, - XFI2_HSS_TX_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes2_xfi_hss_tx), - "XFI2 HSS TX Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi2_hss_rx_hdr, - XFI2_HSS_RX_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes2_xfi_hss_rx), - "XFI2 HSS RX Registers"); - - ql_build_coredump_seg_header(&mpi_coredump->xfi2_hss_pll_hdr, - XFI2_HSS_PLL_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->serdes2_xfi_hss_pll), - "XFI2 HSS PLL Registers"); - - status = ql_get_serdes_regs(qdev, mpi_coredump); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Failed Dump of Serdes Registers. Status = 0x%.08x\n", - status); - goto err; - } - - ql_build_coredump_seg_header(&mpi_coredump->core_regs_seg_hdr, - CORE_SEG_NUM, - sizeof(mpi_coredump->core_regs_seg_hdr) + - sizeof(mpi_coredump->mpi_core_regs) + - sizeof(mpi_coredump->mpi_core_sh_regs), - "Core Registers"); - - /* Get the MPI Core Registers */ - status = ql_get_mpi_regs(qdev, &mpi_coredump->mpi_core_regs[0], - MPI_CORE_REGS_ADDR, MPI_CORE_REGS_CNT); - if (status) - goto err; - /* Get the 16 MPI shadow registers */ - status = ql_get_mpi_shadow_regs(qdev, - &mpi_coredump->mpi_core_sh_regs[0]); - if (status) - goto err; - - /* Get the Test Logic Registers */ - ql_build_coredump_seg_header(&mpi_coredump->test_logic_regs_seg_hdr, - TEST_LOGIC_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->test_logic_regs), - "Test Logic Regs"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->test_logic_regs[0], - TEST_REGS_ADDR, TEST_REGS_CNT); - if (status) - goto err; - - /* Get the RMII Registers */ - ql_build_coredump_seg_header(&mpi_coredump->rmii_regs_seg_hdr, - RMII_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->rmii_regs), - "RMII Registers"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->rmii_regs[0], - RMII_REGS_ADDR, RMII_REGS_CNT); - if (status) - goto err; - - /* Get the FCMAC1 Registers */ - ql_build_coredump_seg_header(&mpi_coredump->fcmac1_regs_seg_hdr, - FCMAC1_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->fcmac1_regs), - "FCMAC1 Registers"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->fcmac1_regs[0], - FCMAC1_REGS_ADDR, FCMAC_REGS_CNT); - if (status) - goto err; - - /* Get the FCMAC2 Registers */ - - ql_build_coredump_seg_header(&mpi_coredump->fcmac2_regs_seg_hdr, - FCMAC2_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->fcmac2_regs), - "FCMAC2 Registers"); - - status = ql_get_mpi_regs(qdev, &mpi_coredump->fcmac2_regs[0], - FCMAC2_REGS_ADDR, FCMAC_REGS_CNT); - if (status) - goto err; - - /* Get the FC1 MBX Registers */ - ql_build_coredump_seg_header(&mpi_coredump->fc1_mbx_regs_seg_hdr, - FC1_MBOX_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->fc1_mbx_regs), - "FC1 MBox Regs"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->fc1_mbx_regs[0], - FC1_MBX_REGS_ADDR, FC_MBX_REGS_CNT); - if (status) - goto err; - - /* Get the IDE Registers */ - ql_build_coredump_seg_header(&mpi_coredump->ide_regs_seg_hdr, - IDE_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->ide_regs), - "IDE Registers"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->ide_regs[0], - IDE_REGS_ADDR, IDE_REGS_CNT); - if (status) - goto err; - - /* Get the NIC1 MBX Registers */ - ql_build_coredump_seg_header(&mpi_coredump->nic1_mbx_regs_seg_hdr, - NIC1_MBOX_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->nic1_mbx_regs), - "NIC1 MBox Regs"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->nic1_mbx_regs[0], - NIC1_MBX_REGS_ADDR, NIC_MBX_REGS_CNT); - if (status) - goto err; - - /* Get the SMBus Registers */ - ql_build_coredump_seg_header(&mpi_coredump->smbus_regs_seg_hdr, - SMBUS_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->smbus_regs), - "SMBus Registers"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->smbus_regs[0], - SMBUS_REGS_ADDR, SMBUS_REGS_CNT); - if (status) - goto err; - - /* Get the FC2 MBX Registers */ - ql_build_coredump_seg_header(&mpi_coredump->fc2_mbx_regs_seg_hdr, - FC2_MBOX_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->fc2_mbx_regs), - "FC2 MBox Regs"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->fc2_mbx_regs[0], - FC2_MBX_REGS_ADDR, FC_MBX_REGS_CNT); - if (status) - goto err; - - /* Get the NIC2 MBX Registers */ - ql_build_coredump_seg_header(&mpi_coredump->nic2_mbx_regs_seg_hdr, - NIC2_MBOX_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->nic2_mbx_regs), - "NIC2 MBox Regs"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->nic2_mbx_regs[0], - NIC2_MBX_REGS_ADDR, NIC_MBX_REGS_CNT); - if (status) - goto err; - - /* Get the I2C Registers */ - ql_build_coredump_seg_header(&mpi_coredump->i2c_regs_seg_hdr, - I2C_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->i2c_regs), - "I2C Registers"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->i2c_regs[0], - I2C_REGS_ADDR, I2C_REGS_CNT); - if (status) - goto err; - - /* Get the MEMC Registers */ - ql_build_coredump_seg_header(&mpi_coredump->memc_regs_seg_hdr, - MEMC_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->memc_regs), - "MEMC Registers"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->memc_regs[0], - MEMC_REGS_ADDR, MEMC_REGS_CNT); - if (status) - goto err; - - /* Get the PBus Registers */ - ql_build_coredump_seg_header(&mpi_coredump->pbus_regs_seg_hdr, - PBUS_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->pbus_regs), - "PBUS Registers"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->pbus_regs[0], - PBUS_REGS_ADDR, PBUS_REGS_CNT); - if (status) - goto err; - - /* Get the MDE Registers */ - ql_build_coredump_seg_header(&mpi_coredump->mde_regs_seg_hdr, - MDE_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->mde_regs), - "MDE Registers"); - status = ql_get_mpi_regs(qdev, &mpi_coredump->mde_regs[0], - MDE_REGS_ADDR, MDE_REGS_CNT); - if (status) - goto err; - - ql_build_coredump_seg_header(&mpi_coredump->misc_nic_seg_hdr, - MISC_NIC_INFO_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->misc_nic_info), - "MISC NIC INFO"); - mpi_coredump->misc_nic_info.rx_ring_count = qdev->rx_ring_count; - mpi_coredump->misc_nic_info.tx_ring_count = qdev->tx_ring_count; - mpi_coredump->misc_nic_info.intr_count = qdev->intr_count; - mpi_coredump->misc_nic_info.function = qdev->func; - - /* Segment 31 */ - /* Get indexed register values. */ - ql_build_coredump_seg_header(&mpi_coredump->intr_states_seg_hdr, - INTR_STATES_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->intr_states), - "INTR States"); - ql_get_intr_states(qdev, &mpi_coredump->intr_states[0]); - - ql_build_coredump_seg_header(&mpi_coredump->cam_entries_seg_hdr, - CAM_ENTRIES_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->cam_entries), - "CAM Entries"); - status = ql_get_cam_entries(qdev, &mpi_coredump->cam_entries[0]); - if (status) - goto err; - - ql_build_coredump_seg_header(&mpi_coredump->nic_routing_words_seg_hdr, - ROUTING_WORDS_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->nic_routing_words), - "Routing Words"); - status = ql_get_routing_entries(qdev, - &mpi_coredump->nic_routing_words[0]); - if (status) - goto err; - - /* Segment 34 (Rev C. step 23) */ - ql_build_coredump_seg_header(&mpi_coredump->ets_seg_hdr, - ETS_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->ets), - "ETS Registers"); - status = ql_get_ets_regs(qdev, &mpi_coredump->ets[0]); - if (status) - goto err; - - ql_build_coredump_seg_header(&mpi_coredump->probe_dump_seg_hdr, - PROBE_DUMP_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->probe_dump), - "Probe Dump"); - ql_get_probe_dump(qdev, &mpi_coredump->probe_dump[0]); - - ql_build_coredump_seg_header(&mpi_coredump->routing_reg_seg_hdr, - ROUTING_INDEX_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->routing_regs), - "Routing Regs"); - status = ql_get_routing_index_registers(qdev, - &mpi_coredump->routing_regs[0]); - if (status) - goto err; - - ql_build_coredump_seg_header(&mpi_coredump->mac_prot_reg_seg_hdr, - MAC_PROTOCOL_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->mac_prot_regs), - "MAC Prot Regs"); - ql_get_mac_protocol_registers(qdev, &mpi_coredump->mac_prot_regs[0]); - - /* Get the semaphore registers for all 5 functions */ - ql_build_coredump_seg_header(&mpi_coredump->sem_regs_seg_hdr, - SEM_REGS_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) + - sizeof(mpi_coredump->sem_regs), "Sem Registers"); - - ql_get_sem_registers(qdev, &mpi_coredump->sem_regs[0]); - - /* Prevent the mpi restarting while we dump the memory.*/ - ql_write_mpi_reg(qdev, MPI_TEST_FUNC_RST_STS, MPI_TEST_FUNC_RST_FRC); - - /* clear the pause */ - status = ql_unpause_mpi_risc(qdev); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Failed RISC unpause. Status = 0x%.08x\n", status); - goto err; - } - - /* Reset the RISC so we can dump RAM */ - status = ql_hard_reset_mpi_risc(qdev); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Failed RISC reset. Status = 0x%.08x\n", status); - goto err; - } - - ql_build_coredump_seg_header(&mpi_coredump->code_ram_seg_hdr, - WCS_RAM_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->code_ram), - "WCS RAM"); - status = ql_dump_risc_ram_area(qdev, &mpi_coredump->code_ram[0], - CODE_RAM_ADDR, CODE_RAM_CNT); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Failed Dump of CODE RAM. Status = 0x%.08x\n", - status); - goto err; - } - - /* Insert the segment header */ - ql_build_coredump_seg_header(&mpi_coredump->memc_ram_seg_hdr, - MEMC_RAM_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->memc_ram), - "MEMC RAM"); - status = ql_dump_risc_ram_area(qdev, &mpi_coredump->memc_ram[0], - MEMC_RAM_ADDR, MEMC_RAM_CNT); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Failed Dump of MEMC RAM. Status = 0x%.08x\n", - status); - goto err; - } -err: - ql_sem_unlock(qdev, SEM_PROC_REG_MASK); /* does flush too */ - return status; - -} - -static void ql_get_core_dump(struct ql_adapter *qdev) -{ - if (!ql_own_firmware(qdev)) { - netif_err(qdev, drv, qdev->ndev, "Don't own firmware!\n"); - return; - } - - if (!netif_running(qdev->ndev)) { - netif_err(qdev, ifup, qdev->ndev, - "Force Coredump can only be done from interface that is up\n"); - return; - } - ql_queue_fw_error(qdev); -} - -static void ql_gen_reg_dump(struct ql_adapter *qdev, - struct ql_reg_dump *mpi_coredump) -{ - int i, status; - - - memset(&(mpi_coredump->mpi_global_header), 0, - sizeof(struct mpi_coredump_global_header)); - mpi_coredump->mpi_global_header.cookie = MPI_COREDUMP_COOKIE; - mpi_coredump->mpi_global_header.headerSize = - sizeof(struct mpi_coredump_global_header); - mpi_coredump->mpi_global_header.imageSize = - sizeof(struct ql_reg_dump); - strncpy(mpi_coredump->mpi_global_header.idString, "MPI Coredump", - sizeof(mpi_coredump->mpi_global_header.idString)); - - - /* segment 16 */ - ql_build_coredump_seg_header(&mpi_coredump->misc_nic_seg_hdr, - MISC_NIC_INFO_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->misc_nic_info), - "MISC NIC INFO"); - mpi_coredump->misc_nic_info.rx_ring_count = qdev->rx_ring_count; - mpi_coredump->misc_nic_info.tx_ring_count = qdev->tx_ring_count; - mpi_coredump->misc_nic_info.intr_count = qdev->intr_count; - mpi_coredump->misc_nic_info.function = qdev->func; - - /* Segment 16, Rev C. Step 18 */ - ql_build_coredump_seg_header(&mpi_coredump->nic_regs_seg_hdr, - NIC1_CONTROL_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->nic_regs), - "NIC Registers"); - /* Get generic reg dump */ - for (i = 0; i < 64; i++) - mpi_coredump->nic_regs[i] = ql_read32(qdev, i * sizeof(u32)); - - /* Segment 31 */ - /* Get indexed register values. */ - ql_build_coredump_seg_header(&mpi_coredump->intr_states_seg_hdr, - INTR_STATES_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->intr_states), - "INTR States"); - ql_get_intr_states(qdev, &mpi_coredump->intr_states[0]); - - ql_build_coredump_seg_header(&mpi_coredump->cam_entries_seg_hdr, - CAM_ENTRIES_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->cam_entries), - "CAM Entries"); - status = ql_get_cam_entries(qdev, &mpi_coredump->cam_entries[0]); - if (status) - return; - - ql_build_coredump_seg_header(&mpi_coredump->nic_routing_words_seg_hdr, - ROUTING_WORDS_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->nic_routing_words), - "Routing Words"); - status = ql_get_routing_entries(qdev, - &mpi_coredump->nic_routing_words[0]); - if (status) - return; - - /* Segment 34 (Rev C. step 23) */ - ql_build_coredump_seg_header(&mpi_coredump->ets_seg_hdr, - ETS_SEG_NUM, - sizeof(struct mpi_coredump_segment_header) - + sizeof(mpi_coredump->ets), - "ETS Registers"); - status = ql_get_ets_regs(qdev, &mpi_coredump->ets[0]); - if (status) - return; -} - -void ql_get_dump(struct ql_adapter *qdev, void *buff) -{ - /* - * If the dump has already been taken and is stored - * in our internal buffer and if force dump is set then - * just start the spool to dump it to the log file - * and also, take a snapshot of the general regs to - * to the user's buffer or else take complete dump - * to the user's buffer if force is not set. - */ - - if (!test_bit(QL_FRC_COREDUMP, &qdev->flags)) { - if (!ql_core_dump(qdev, buff)) - ql_soft_reset_mpi_risc(qdev); - else - netif_err(qdev, drv, qdev->ndev, "coredump failed!\n"); - } else { - ql_gen_reg_dump(qdev, buff); - ql_get_core_dump(qdev); - } -} - -/* Coredump to messages log file using separate worker thread */ -void ql_mpi_core_to_log(struct work_struct *work) -{ - struct ql_adapter *qdev = - container_of(work, struct ql_adapter, mpi_core_to_log.work); - u32 *tmp, count; - int i; - - count = sizeof(struct ql_mpi_coredump) / sizeof(u32); - tmp = (u32 *)qdev->mpi_coredump; - netif_printk(qdev, drv, KERN_DEBUG, qdev->ndev, - "Core is dumping to log file!\n"); - - for (i = 0; i < count; i += 8) { - pr_err("%.08x: %.08x %.08x %.08x %.08x %.08x " - "%.08x %.08x %.08x\n", i, - tmp[i + 0], - tmp[i + 1], - tmp[i + 2], - tmp[i + 3], - tmp[i + 4], - tmp[i + 5], - tmp[i + 6], - tmp[i + 7]); - msleep(5); - } -} - -#ifdef QL_REG_DUMP -static void ql_dump_intr_states(struct ql_adapter *qdev) -{ - int i; - u32 value; - for (i = 0; i < qdev->intr_count; i++) { - ql_write32(qdev, INTR_EN, qdev->intr_context[i].intr_read_mask); - value = ql_read32(qdev, INTR_EN); - pr_err("%s: Interrupt %d is %s\n", - qdev->ndev->name, i, - (value & INTR_EN_EN ? "enabled" : "disabled")); - } -} - -#define DUMP_XGMAC(qdev, reg) \ -do { \ - u32 data; \ - ql_read_xgmac_reg(qdev, reg, &data); \ - pr_err("%s: %s = 0x%.08x\n", qdev->ndev->name, #reg, data); \ -} while (0) - -void ql_dump_xgmac_control_regs(struct ql_adapter *qdev) -{ - if (ql_sem_spinlock(qdev, qdev->xg_sem_mask)) { - pr_err("%s: Couldn't get xgmac sem\n", __func__); - return; - } - DUMP_XGMAC(qdev, PAUSE_SRC_LO); - DUMP_XGMAC(qdev, PAUSE_SRC_HI); - DUMP_XGMAC(qdev, GLOBAL_CFG); - DUMP_XGMAC(qdev, TX_CFG); - DUMP_XGMAC(qdev, RX_CFG); - DUMP_XGMAC(qdev, FLOW_CTL); - DUMP_XGMAC(qdev, PAUSE_OPCODE); - DUMP_XGMAC(qdev, PAUSE_TIMER); - DUMP_XGMAC(qdev, PAUSE_FRM_DEST_LO); - DUMP_XGMAC(qdev, PAUSE_FRM_DEST_HI); - DUMP_XGMAC(qdev, MAC_TX_PARAMS); - DUMP_XGMAC(qdev, MAC_RX_PARAMS); - DUMP_XGMAC(qdev, MAC_SYS_INT); - DUMP_XGMAC(qdev, MAC_SYS_INT_MASK); - DUMP_XGMAC(qdev, MAC_MGMT_INT); - DUMP_XGMAC(qdev, MAC_MGMT_IN_MASK); - DUMP_XGMAC(qdev, EXT_ARB_MODE); - ql_sem_unlock(qdev, qdev->xg_sem_mask); -} - -static void ql_dump_ets_regs(struct ql_adapter *qdev) -{ -} - -static void ql_dump_cam_entries(struct ql_adapter *qdev) -{ - int i; - u32 value[3]; - - i = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK); - if (i) - return; - for (i = 0; i < 4; i++) { - if (ql_get_mac_addr_reg(qdev, MAC_ADDR_TYPE_CAM_MAC, i, value)) { - pr_err("%s: Failed read of mac index register\n", - __func__); - return; - } else { - if (value[0]) - pr_err("%s: CAM index %d CAM Lookup Lower = 0x%.08x:%.08x, Output = 0x%.08x\n", - qdev->ndev->name, i, value[1], value[0], - value[2]); - } - } - for (i = 0; i < 32; i++) { - if (ql_get_mac_addr_reg - (qdev, MAC_ADDR_TYPE_MULTI_MAC, i, value)) { - pr_err("%s: Failed read of mac index register\n", - __func__); - return; - } else { - if (value[0]) - pr_err("%s: MCAST index %d CAM Lookup Lower = 0x%.08x:%.08x\n", - qdev->ndev->name, i, value[1], value[0]); - } - } - ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK); -} - -void ql_dump_routing_entries(struct ql_adapter *qdev) -{ - int i; - u32 value; - i = ql_sem_spinlock(qdev, SEM_RT_IDX_MASK); - if (i) - return; - for (i = 0; i < 16; i++) { - value = 0; - if (ql_get_routing_reg(qdev, i, &value)) { - pr_err("%s: Failed read of routing index register\n", - __func__); - return; - } else { - if (value) - pr_err("%s: Routing Mask %d = 0x%.08x\n", - qdev->ndev->name, i, value); - } - } - ql_sem_unlock(qdev, SEM_RT_IDX_MASK); -} - -#define DUMP_REG(qdev, reg) \ - pr_err("%-32s= 0x%x\n", #reg, ql_read32(qdev, reg)) - -void ql_dump_regs(struct ql_adapter *qdev) -{ - pr_err("reg dump for function #%d\n", qdev->func); - DUMP_REG(qdev, SYS); - DUMP_REG(qdev, RST_FO); - DUMP_REG(qdev, FSC); - DUMP_REG(qdev, CSR); - DUMP_REG(qdev, ICB_RID); - DUMP_REG(qdev, ICB_L); - DUMP_REG(qdev, ICB_H); - DUMP_REG(qdev, CFG); - DUMP_REG(qdev, BIOS_ADDR); - DUMP_REG(qdev, STS); - DUMP_REG(qdev, INTR_EN); - DUMP_REG(qdev, INTR_MASK); - DUMP_REG(qdev, ISR1); - DUMP_REG(qdev, ISR2); - DUMP_REG(qdev, ISR3); - DUMP_REG(qdev, ISR4); - DUMP_REG(qdev, REV_ID); - DUMP_REG(qdev, FRC_ECC_ERR); - DUMP_REG(qdev, ERR_STS); - DUMP_REG(qdev, RAM_DBG_ADDR); - DUMP_REG(qdev, RAM_DBG_DATA); - DUMP_REG(qdev, ECC_ERR_CNT); - DUMP_REG(qdev, SEM); - DUMP_REG(qdev, GPIO_1); - DUMP_REG(qdev, GPIO_2); - DUMP_REG(qdev, GPIO_3); - DUMP_REG(qdev, XGMAC_ADDR); - DUMP_REG(qdev, XGMAC_DATA); - DUMP_REG(qdev, NIC_ETS); - DUMP_REG(qdev, CNA_ETS); - DUMP_REG(qdev, FLASH_ADDR); - DUMP_REG(qdev, FLASH_DATA); - DUMP_REG(qdev, CQ_STOP); - DUMP_REG(qdev, PAGE_TBL_RID); - DUMP_REG(qdev, WQ_PAGE_TBL_LO); - DUMP_REG(qdev, WQ_PAGE_TBL_HI); - DUMP_REG(qdev, CQ_PAGE_TBL_LO); - DUMP_REG(qdev, CQ_PAGE_TBL_HI); - DUMP_REG(qdev, COS_DFLT_CQ1); - DUMP_REG(qdev, COS_DFLT_CQ2); - DUMP_REG(qdev, SPLT_HDR); - DUMP_REG(qdev, FC_PAUSE_THRES); - DUMP_REG(qdev, NIC_PAUSE_THRES); - DUMP_REG(qdev, FC_ETHERTYPE); - DUMP_REG(qdev, FC_RCV_CFG); - DUMP_REG(qdev, NIC_RCV_CFG); - DUMP_REG(qdev, FC_COS_TAGS); - DUMP_REG(qdev, NIC_COS_TAGS); - DUMP_REG(qdev, MGMT_RCV_CFG); - DUMP_REG(qdev, XG_SERDES_ADDR); - DUMP_REG(qdev, XG_SERDES_DATA); - DUMP_REG(qdev, PRB_MX_ADDR); - DUMP_REG(qdev, PRB_MX_DATA); - ql_dump_intr_states(qdev); - ql_dump_xgmac_control_regs(qdev); - ql_dump_ets_regs(qdev); - ql_dump_cam_entries(qdev); - ql_dump_routing_entries(qdev); -} -#endif - -#ifdef QL_STAT_DUMP - -#define DUMP_STAT(qdev, stat) \ - pr_err("%s = %ld\n", #stat, (unsigned long)qdev->nic_stats.stat) - -void ql_dump_stat(struct ql_adapter *qdev) -{ - pr_err("%s: Enter\n", __func__); - DUMP_STAT(qdev, tx_pkts); - DUMP_STAT(qdev, tx_bytes); - DUMP_STAT(qdev, tx_mcast_pkts); - DUMP_STAT(qdev, tx_bcast_pkts); - DUMP_STAT(qdev, tx_ucast_pkts); - DUMP_STAT(qdev, tx_ctl_pkts); - DUMP_STAT(qdev, tx_pause_pkts); - DUMP_STAT(qdev, tx_64_pkt); - DUMP_STAT(qdev, tx_65_to_127_pkt); - DUMP_STAT(qdev, tx_128_to_255_pkt); - DUMP_STAT(qdev, tx_256_511_pkt); - DUMP_STAT(qdev, tx_512_to_1023_pkt); - DUMP_STAT(qdev, tx_1024_to_1518_pkt); - DUMP_STAT(qdev, tx_1519_to_max_pkt); - DUMP_STAT(qdev, tx_undersize_pkt); - DUMP_STAT(qdev, tx_oversize_pkt); - DUMP_STAT(qdev, rx_bytes); - DUMP_STAT(qdev, rx_bytes_ok); - DUMP_STAT(qdev, rx_pkts); - DUMP_STAT(qdev, rx_pkts_ok); - DUMP_STAT(qdev, rx_bcast_pkts); - DUMP_STAT(qdev, rx_mcast_pkts); - DUMP_STAT(qdev, rx_ucast_pkts); - DUMP_STAT(qdev, rx_undersize_pkts); - DUMP_STAT(qdev, rx_oversize_pkts); - DUMP_STAT(qdev, rx_jabber_pkts); - DUMP_STAT(qdev, rx_undersize_fcerr_pkts); - DUMP_STAT(qdev, rx_drop_events); - DUMP_STAT(qdev, rx_fcerr_pkts); - DUMP_STAT(qdev, rx_align_err); - DUMP_STAT(qdev, rx_symbol_err); - DUMP_STAT(qdev, rx_mac_err); - DUMP_STAT(qdev, rx_ctl_pkts); - DUMP_STAT(qdev, rx_pause_pkts); - DUMP_STAT(qdev, rx_64_pkts); - DUMP_STAT(qdev, rx_65_to_127_pkts); - DUMP_STAT(qdev, rx_128_255_pkts); - DUMP_STAT(qdev, rx_256_511_pkts); - DUMP_STAT(qdev, rx_512_to_1023_pkts); - DUMP_STAT(qdev, rx_1024_to_1518_pkts); - DUMP_STAT(qdev, rx_1519_to_max_pkts); - DUMP_STAT(qdev, rx_len_err_pkts); -}; -#endif - -#ifdef QL_DEV_DUMP - -#define DUMP_QDEV_FIELD(qdev, type, field) \ - pr_err("qdev->%-24s = " type "\n", #field, qdev->field) -#define DUMP_QDEV_DMA_FIELD(qdev, field) \ - pr_err("qdev->%-24s = %llx\n", #field, (unsigned long long)qdev->field) -#define DUMP_QDEV_ARRAY(qdev, type, array, index, field) \ - pr_err("%s[%d].%s = " type "\n", \ - #array, index, #field, qdev->array[index].field); -void ql_dump_qdev(struct ql_adapter *qdev) -{ - int i; - DUMP_QDEV_FIELD(qdev, "%lx", flags); - DUMP_QDEV_FIELD(qdev, "%p", vlgrp); - DUMP_QDEV_FIELD(qdev, "%p", pdev); - DUMP_QDEV_FIELD(qdev, "%p", ndev); - DUMP_QDEV_FIELD(qdev, "%d", chip_rev_id); - DUMP_QDEV_FIELD(qdev, "%p", reg_base); - DUMP_QDEV_FIELD(qdev, "%p", doorbell_area); - DUMP_QDEV_FIELD(qdev, "%d", doorbell_area_size); - DUMP_QDEV_FIELD(qdev, "%x", msg_enable); - DUMP_QDEV_FIELD(qdev, "%p", rx_ring_shadow_reg_area); - DUMP_QDEV_DMA_FIELD(qdev, rx_ring_shadow_reg_dma); - DUMP_QDEV_FIELD(qdev, "%p", tx_ring_shadow_reg_area); - DUMP_QDEV_DMA_FIELD(qdev, tx_ring_shadow_reg_dma); - DUMP_QDEV_FIELD(qdev, "%d", intr_count); - if (qdev->msi_x_entry) - for (i = 0; i < qdev->intr_count; i++) { - DUMP_QDEV_ARRAY(qdev, "%d", msi_x_entry, i, vector); - DUMP_QDEV_ARRAY(qdev, "%d", msi_x_entry, i, entry); - } - for (i = 0; i < qdev->intr_count; i++) { - DUMP_QDEV_ARRAY(qdev, "%p", intr_context, i, qdev); - DUMP_QDEV_ARRAY(qdev, "%d", intr_context, i, intr); - DUMP_QDEV_ARRAY(qdev, "%d", intr_context, i, hooked); - DUMP_QDEV_ARRAY(qdev, "0x%08x", intr_context, i, intr_en_mask); - DUMP_QDEV_ARRAY(qdev, "0x%08x", intr_context, i, intr_dis_mask); - DUMP_QDEV_ARRAY(qdev, "0x%08x", intr_context, i, intr_read_mask); - } - DUMP_QDEV_FIELD(qdev, "%d", tx_ring_count); - DUMP_QDEV_FIELD(qdev, "%d", rx_ring_count); - DUMP_QDEV_FIELD(qdev, "%d", ring_mem_size); - DUMP_QDEV_FIELD(qdev, "%p", ring_mem); - DUMP_QDEV_FIELD(qdev, "%d", intr_count); - DUMP_QDEV_FIELD(qdev, "%p", tx_ring); - DUMP_QDEV_FIELD(qdev, "%d", rss_ring_count); - DUMP_QDEV_FIELD(qdev, "%p", rx_ring); - DUMP_QDEV_FIELD(qdev, "%d", default_rx_queue); - DUMP_QDEV_FIELD(qdev, "0x%08x", xg_sem_mask); - DUMP_QDEV_FIELD(qdev, "0x%08x", port_link_up); - DUMP_QDEV_FIELD(qdev, "0x%08x", port_init); -} -#endif - -#ifdef QL_CB_DUMP -void ql_dump_wqicb(struct wqicb *wqicb) -{ - pr_err("Dumping wqicb stuff...\n"); - pr_err("wqicb->len = 0x%x\n", le16_to_cpu(wqicb->len)); - pr_err("wqicb->flags = %x\n", le16_to_cpu(wqicb->flags)); - pr_err("wqicb->cq_id_rss = %d\n", - le16_to_cpu(wqicb->cq_id_rss)); - pr_err("wqicb->rid = 0x%x\n", le16_to_cpu(wqicb->rid)); - pr_err("wqicb->wq_addr = 0x%llx\n", - (unsigned long long) le64_to_cpu(wqicb->addr)); - pr_err("wqicb->wq_cnsmr_idx_addr = 0x%llx\n", - (unsigned long long) le64_to_cpu(wqicb->cnsmr_idx_addr)); -} - -void ql_dump_tx_ring(struct tx_ring *tx_ring) -{ - if (tx_ring == NULL) - return; - pr_err("===================== Dumping tx_ring %d ===============\n", - tx_ring->wq_id); - pr_err("tx_ring->base = %p\n", tx_ring->wq_base); - pr_err("tx_ring->base_dma = 0x%llx\n", - (unsigned long long) tx_ring->wq_base_dma); - pr_err("tx_ring->cnsmr_idx_sh_reg, addr = 0x%p, value = %d\n", - tx_ring->cnsmr_idx_sh_reg, - tx_ring->cnsmr_idx_sh_reg - ? ql_read_sh_reg(tx_ring->cnsmr_idx_sh_reg) : 0); - pr_err("tx_ring->size = %d\n", tx_ring->wq_size); - pr_err("tx_ring->len = %d\n", tx_ring->wq_len); - pr_err("tx_ring->prod_idx_db_reg = %p\n", tx_ring->prod_idx_db_reg); - pr_err("tx_ring->valid_db_reg = %p\n", tx_ring->valid_db_reg); - pr_err("tx_ring->prod_idx = %d\n", tx_ring->prod_idx); - pr_err("tx_ring->cq_id = %d\n", tx_ring->cq_id); - pr_err("tx_ring->wq_id = %d\n", tx_ring->wq_id); - pr_err("tx_ring->q = %p\n", tx_ring->q); - pr_err("tx_ring->tx_count = %d\n", atomic_read(&tx_ring->tx_count)); -} - -void ql_dump_ricb(struct ricb *ricb) -{ - int i; - pr_err("===================== Dumping ricb ===============\n"); - pr_err("Dumping ricb stuff...\n"); - - pr_err("ricb->base_cq = %d\n", ricb->base_cq & 0x1f); - pr_err("ricb->flags = %s%s%s%s%s%s%s%s%s\n", - ricb->base_cq & RSS_L4K ? "RSS_L4K " : "", - ricb->flags & RSS_L6K ? "RSS_L6K " : "", - ricb->flags & RSS_LI ? "RSS_LI " : "", - ricb->flags & RSS_LB ? "RSS_LB " : "", - ricb->flags & RSS_LM ? "RSS_LM " : "", - ricb->flags & RSS_RI4 ? "RSS_RI4 " : "", - ricb->flags & RSS_RT4 ? "RSS_RT4 " : "", - ricb->flags & RSS_RI6 ? "RSS_RI6 " : "", - ricb->flags & RSS_RT6 ? "RSS_RT6 " : ""); - pr_err("ricb->mask = 0x%.04x\n", le16_to_cpu(ricb->mask)); - for (i = 0; i < 16; i++) - pr_err("ricb->hash_cq_id[%d] = 0x%.08x\n", i, - le32_to_cpu(ricb->hash_cq_id[i])); - for (i = 0; i < 10; i++) - pr_err("ricb->ipv6_hash_key[%d] = 0x%.08x\n", i, - le32_to_cpu(ricb->ipv6_hash_key[i])); - for (i = 0; i < 4; i++) - pr_err("ricb->ipv4_hash_key[%d] = 0x%.08x\n", i, - le32_to_cpu(ricb->ipv4_hash_key[i])); -} - -void ql_dump_cqicb(struct cqicb *cqicb) -{ - pr_err("Dumping cqicb stuff...\n"); - - pr_err("cqicb->msix_vect = %d\n", cqicb->msix_vect); - pr_err("cqicb->flags = %x\n", cqicb->flags); - pr_err("cqicb->len = %d\n", le16_to_cpu(cqicb->len)); - pr_err("cqicb->addr = 0x%llx\n", - (unsigned long long) le64_to_cpu(cqicb->addr)); - pr_err("cqicb->prod_idx_addr = 0x%llx\n", - (unsigned long long) le64_to_cpu(cqicb->prod_idx_addr)); - pr_err("cqicb->pkt_delay = 0x%.04x\n", - le16_to_cpu(cqicb->pkt_delay)); - pr_err("cqicb->irq_delay = 0x%.04x\n", - le16_to_cpu(cqicb->irq_delay)); - pr_err("cqicb->lbq_addr = 0x%llx\n", - (unsigned long long) le64_to_cpu(cqicb->lbq_addr)); - pr_err("cqicb->lbq_buf_size = 0x%.04x\n", - le16_to_cpu(cqicb->lbq_buf_size)); - pr_err("cqicb->lbq_len = 0x%.04x\n", - le16_to_cpu(cqicb->lbq_len)); - pr_err("cqicb->sbq_addr = 0x%llx\n", - (unsigned long long) le64_to_cpu(cqicb->sbq_addr)); - pr_err("cqicb->sbq_buf_size = 0x%.04x\n", - le16_to_cpu(cqicb->sbq_buf_size)); - pr_err("cqicb->sbq_len = 0x%.04x\n", - le16_to_cpu(cqicb->sbq_len)); -} - -void ql_dump_rx_ring(struct rx_ring *rx_ring) -{ - if (rx_ring == NULL) - return; - pr_err("===================== Dumping rx_ring %d ===============\n", - rx_ring->cq_id); - pr_err("Dumping rx_ring %d, type = %s%s%s\n", - rx_ring->cq_id, rx_ring->type == DEFAULT_Q ? "DEFAULT" : "", - rx_ring->type == TX_Q ? "OUTBOUND COMPLETIONS" : "", - rx_ring->type == RX_Q ? "INBOUND_COMPLETIONS" : ""); - pr_err("rx_ring->cqicb = %p\n", &rx_ring->cqicb); - pr_err("rx_ring->cq_base = %p\n", rx_ring->cq_base); - pr_err("rx_ring->cq_base_dma = %llx\n", - (unsigned long long) rx_ring->cq_base_dma); - pr_err("rx_ring->cq_size = %d\n", rx_ring->cq_size); - pr_err("rx_ring->cq_len = %d\n", rx_ring->cq_len); - pr_err("rx_ring->prod_idx_sh_reg, addr = 0x%p, value = %d\n", - rx_ring->prod_idx_sh_reg, - rx_ring->prod_idx_sh_reg - ? ql_read_sh_reg(rx_ring->prod_idx_sh_reg) : 0); - pr_err("rx_ring->prod_idx_sh_reg_dma = %llx\n", - (unsigned long long) rx_ring->prod_idx_sh_reg_dma); - pr_err("rx_ring->cnsmr_idx_db_reg = %p\n", - rx_ring->cnsmr_idx_db_reg); - pr_err("rx_ring->cnsmr_idx = %d\n", rx_ring->cnsmr_idx); - pr_err("rx_ring->curr_entry = %p\n", rx_ring->curr_entry); - pr_err("rx_ring->valid_db_reg = %p\n", rx_ring->valid_db_reg); - - pr_err("rx_ring->lbq_base = %p\n", rx_ring->lbq_base); - pr_err("rx_ring->lbq_base_dma = %llx\n", - (unsigned long long) rx_ring->lbq_base_dma); - pr_err("rx_ring->lbq_base_indirect = %p\n", - rx_ring->lbq_base_indirect); - pr_err("rx_ring->lbq_base_indirect_dma = %llx\n", - (unsigned long long) rx_ring->lbq_base_indirect_dma); - pr_err("rx_ring->lbq = %p\n", rx_ring->lbq); - pr_err("rx_ring->lbq_len = %d\n", rx_ring->lbq_len); - pr_err("rx_ring->lbq_size = %d\n", rx_ring->lbq_size); - pr_err("rx_ring->lbq_prod_idx_db_reg = %p\n", - rx_ring->lbq_prod_idx_db_reg); - pr_err("rx_ring->lbq_prod_idx = %d\n", rx_ring->lbq_prod_idx); - pr_err("rx_ring->lbq_curr_idx = %d\n", rx_ring->lbq_curr_idx); - pr_err("rx_ring->lbq_clean_idx = %d\n", rx_ring->lbq_clean_idx); - pr_err("rx_ring->lbq_free_cnt = %d\n", rx_ring->lbq_free_cnt); - pr_err("rx_ring->lbq_buf_size = %d\n", rx_ring->lbq_buf_size); - - pr_err("rx_ring->sbq_base = %p\n", rx_ring->sbq_base); - pr_err("rx_ring->sbq_base_dma = %llx\n", - (unsigned long long) rx_ring->sbq_base_dma); - pr_err("rx_ring->sbq_base_indirect = %p\n", - rx_ring->sbq_base_indirect); - pr_err("rx_ring->sbq_base_indirect_dma = %llx\n", - (unsigned long long) rx_ring->sbq_base_indirect_dma); - pr_err("rx_ring->sbq = %p\n", rx_ring->sbq); - pr_err("rx_ring->sbq_len = %d\n", rx_ring->sbq_len); - pr_err("rx_ring->sbq_size = %d\n", rx_ring->sbq_size); - pr_err("rx_ring->sbq_prod_idx_db_reg addr = %p\n", - rx_ring->sbq_prod_idx_db_reg); - pr_err("rx_ring->sbq_prod_idx = %d\n", rx_ring->sbq_prod_idx); - pr_err("rx_ring->sbq_curr_idx = %d\n", rx_ring->sbq_curr_idx); - pr_err("rx_ring->sbq_clean_idx = %d\n", rx_ring->sbq_clean_idx); - pr_err("rx_ring->sbq_free_cnt = %d\n", rx_ring->sbq_free_cnt); - pr_err("rx_ring->sbq_buf_size = %d\n", rx_ring->sbq_buf_size); - pr_err("rx_ring->cq_id = %d\n", rx_ring->cq_id); - pr_err("rx_ring->irq = %d\n", rx_ring->irq); - pr_err("rx_ring->cpu = %d\n", rx_ring->cpu); - pr_err("rx_ring->qdev = %p\n", rx_ring->qdev); -} - -void ql_dump_hw_cb(struct ql_adapter *qdev, int size, u32 bit, u16 q_id) -{ - void *ptr; - - pr_err("%s: Enter\n", __func__); - - ptr = kmalloc(size, GFP_ATOMIC); - if (ptr == NULL) - return; - - if (ql_write_cfg(qdev, ptr, size, bit, q_id)) { - pr_err("%s: Failed to upload control block!\n", __func__); - goto fail_it; - } - switch (bit) { - case CFG_DRQ: - ql_dump_wqicb((struct wqicb *)ptr); - break; - case CFG_DCQ: - ql_dump_cqicb((struct cqicb *)ptr); - break; - case CFG_DR: - ql_dump_ricb((struct ricb *)ptr); - break; - default: - pr_err("%s: Invalid bit value = %x\n", __func__, bit); - break; - } -fail_it: - kfree(ptr); -} -#endif - -#ifdef QL_OB_DUMP -void ql_dump_tx_desc(struct tx_buf_desc *tbd) -{ - pr_err("tbd->addr = 0x%llx\n", - le64_to_cpu((u64) tbd->addr)); - pr_err("tbd->len = %d\n", - le32_to_cpu(tbd->len & TX_DESC_LEN_MASK)); - pr_err("tbd->flags = %s %s\n", - tbd->len & TX_DESC_C ? "C" : ".", - tbd->len & TX_DESC_E ? "E" : "."); - tbd++; - pr_err("tbd->addr = 0x%llx\n", - le64_to_cpu((u64) tbd->addr)); - pr_err("tbd->len = %d\n", - le32_to_cpu(tbd->len & TX_DESC_LEN_MASK)); - pr_err("tbd->flags = %s %s\n", - tbd->len & TX_DESC_C ? "C" : ".", - tbd->len & TX_DESC_E ? "E" : "."); - tbd++; - pr_err("tbd->addr = 0x%llx\n", - le64_to_cpu((u64) tbd->addr)); - pr_err("tbd->len = %d\n", - le32_to_cpu(tbd->len & TX_DESC_LEN_MASK)); - pr_err("tbd->flags = %s %s\n", - tbd->len & TX_DESC_C ? "C" : ".", - tbd->len & TX_DESC_E ? "E" : "."); - -} - -void ql_dump_ob_mac_iocb(struct ob_mac_iocb_req *ob_mac_iocb) -{ - struct ob_mac_tso_iocb_req *ob_mac_tso_iocb = - (struct ob_mac_tso_iocb_req *)ob_mac_iocb; - struct tx_buf_desc *tbd; - u16 frame_len; - - pr_err("%s\n", __func__); - pr_err("opcode = %s\n", - (ob_mac_iocb->opcode == OPCODE_OB_MAC_IOCB) ? "MAC" : "TSO"); - pr_err("flags1 = %s %s %s %s %s\n", - ob_mac_tso_iocb->flags1 & OB_MAC_TSO_IOCB_OI ? "OI" : "", - ob_mac_tso_iocb->flags1 & OB_MAC_TSO_IOCB_I ? "I" : "", - ob_mac_tso_iocb->flags1 & OB_MAC_TSO_IOCB_D ? "D" : "", - ob_mac_tso_iocb->flags1 & OB_MAC_TSO_IOCB_IP4 ? "IP4" : "", - ob_mac_tso_iocb->flags1 & OB_MAC_TSO_IOCB_IP6 ? "IP6" : ""); - pr_err("flags2 = %s %s %s\n", - ob_mac_tso_iocb->flags2 & OB_MAC_TSO_IOCB_LSO ? "LSO" : "", - ob_mac_tso_iocb->flags2 & OB_MAC_TSO_IOCB_UC ? "UC" : "", - ob_mac_tso_iocb->flags2 & OB_MAC_TSO_IOCB_TC ? "TC" : ""); - pr_err("flags3 = %s %s %s\n", - ob_mac_tso_iocb->flags3 & OB_MAC_TSO_IOCB_IC ? "IC" : "", - ob_mac_tso_iocb->flags3 & OB_MAC_TSO_IOCB_DFP ? "DFP" : "", - ob_mac_tso_iocb->flags3 & OB_MAC_TSO_IOCB_V ? "V" : ""); - pr_err("tid = %x\n", ob_mac_iocb->tid); - pr_err("txq_idx = %d\n", ob_mac_iocb->txq_idx); - pr_err("vlan_tci = %x\n", ob_mac_tso_iocb->vlan_tci); - if (ob_mac_iocb->opcode == OPCODE_OB_MAC_TSO_IOCB) { - pr_err("frame_len = %d\n", - le32_to_cpu(ob_mac_tso_iocb->frame_len)); - pr_err("mss = %d\n", - le16_to_cpu(ob_mac_tso_iocb->mss)); - pr_err("prot_hdr_len = %d\n", - le16_to_cpu(ob_mac_tso_iocb->total_hdrs_len)); - pr_err("hdr_offset = 0x%.04x\n", - le16_to_cpu(ob_mac_tso_iocb->net_trans_offset)); - frame_len = le32_to_cpu(ob_mac_tso_iocb->frame_len); - } else { - pr_err("frame_len = %d\n", - le16_to_cpu(ob_mac_iocb->frame_len)); - frame_len = le16_to_cpu(ob_mac_iocb->frame_len); - } - tbd = &ob_mac_iocb->tbd[0]; - ql_dump_tx_desc(tbd); -} - -void ql_dump_ob_mac_rsp(struct ob_mac_iocb_rsp *ob_mac_rsp) -{ - pr_err("%s\n", __func__); - pr_err("opcode = %d\n", ob_mac_rsp->opcode); - pr_err("flags = %s %s %s %s %s %s %s\n", - ob_mac_rsp->flags1 & OB_MAC_IOCB_RSP_OI ? "OI" : ".", - ob_mac_rsp->flags1 & OB_MAC_IOCB_RSP_I ? "I" : ".", - ob_mac_rsp->flags1 & OB_MAC_IOCB_RSP_E ? "E" : ".", - ob_mac_rsp->flags1 & OB_MAC_IOCB_RSP_S ? "S" : ".", - ob_mac_rsp->flags1 & OB_MAC_IOCB_RSP_L ? "L" : ".", - ob_mac_rsp->flags1 & OB_MAC_IOCB_RSP_P ? "P" : ".", - ob_mac_rsp->flags2 & OB_MAC_IOCB_RSP_B ? "B" : "."); - pr_err("tid = %x\n", ob_mac_rsp->tid); -} -#endif - -#ifdef QL_IB_DUMP -void ql_dump_ib_mac_rsp(struct ib_mac_iocb_rsp *ib_mac_rsp) -{ - pr_err("%s\n", __func__); - pr_err("opcode = 0x%x\n", ib_mac_rsp->opcode); - pr_err("flags1 = %s%s%s%s%s%s\n", - ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_OI ? "OI " : "", - ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_I ? "I " : "", - ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_TE ? "TE " : "", - ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_NU ? "NU " : "", - ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_IE ? "IE " : "", - ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_B ? "B " : ""); - - if (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) - pr_err("%s%s%s Multicast\n", - (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) == - IB_MAC_IOCB_RSP_M_HASH ? "Hash" : "", - (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) == - IB_MAC_IOCB_RSP_M_REG ? "Registered" : "", - (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) == - IB_MAC_IOCB_RSP_M_PROM ? "Promiscuous" : ""); - - pr_err("flags2 = %s%s%s%s%s\n", - (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_P) ? "P " : "", - (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_V) ? "V " : "", - (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_U) ? "U " : "", - (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_T) ? "T " : "", - (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_FO) ? "FO " : ""); - - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) - pr_err("%s%s%s%s%s error\n", - (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) == - IB_MAC_IOCB_RSP_ERR_OVERSIZE ? "oversize" : "", - (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) == - IB_MAC_IOCB_RSP_ERR_UNDERSIZE ? "undersize" : "", - (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) == - IB_MAC_IOCB_RSP_ERR_PREAMBLE ? "preamble" : "", - (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) == - IB_MAC_IOCB_RSP_ERR_FRAME_LEN ? "frame length" : "", - (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) == - IB_MAC_IOCB_RSP_ERR_CRC ? "CRC" : ""); - - pr_err("flags3 = %s%s\n", - ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_DS ? "DS " : "", - ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_DL ? "DL " : ""); - - if (ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_RSS_MASK) - pr_err("RSS flags = %s%s%s%s\n", - ((ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_RSS_MASK) == - IB_MAC_IOCB_RSP_M_IPV4) ? "IPv4 RSS" : "", - ((ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_RSS_MASK) == - IB_MAC_IOCB_RSP_M_IPV6) ? "IPv6 RSS " : "", - ((ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_RSS_MASK) == - IB_MAC_IOCB_RSP_M_TCP_V4) ? "TCP/IPv4 RSS" : "", - ((ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_RSS_MASK) == - IB_MAC_IOCB_RSP_M_TCP_V6) ? "TCP/IPv6 RSS" : ""); - - pr_err("data_len = %d\n", - le32_to_cpu(ib_mac_rsp->data_len)); - pr_err("data_addr = 0x%llx\n", - (unsigned long long) le64_to_cpu(ib_mac_rsp->data_addr)); - if (ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_RSS_MASK) - pr_err("rss = %x\n", - le32_to_cpu(ib_mac_rsp->rss)); - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_V) - pr_err("vlan_id = %x\n", - le16_to_cpu(ib_mac_rsp->vlan_id)); - - pr_err("flags4 = %s%s%s\n", - ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HV ? "HV " : "", - ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HS ? "HS " : "", - ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HL ? "HL " : ""); - - if (ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HV) { - pr_err("hdr length = %d\n", - le32_to_cpu(ib_mac_rsp->hdr_len)); - pr_err("hdr addr = 0x%llx\n", - (unsigned long long) le64_to_cpu(ib_mac_rsp->hdr_addr)); - } -} -#endif - -#ifdef QL_ALL_DUMP -void ql_dump_all(struct ql_adapter *qdev) -{ - int i; - - QL_DUMP_REGS(qdev); - QL_DUMP_QDEV(qdev); - for (i = 0; i < qdev->tx_ring_count; i++) { - QL_DUMP_TX_RING(&qdev->tx_ring[i]); - QL_DUMP_WQICB((struct wqicb *)&qdev->tx_ring[i]); - } - for (i = 0; i < qdev->rx_ring_count; i++) { - QL_DUMP_RX_RING(&qdev->rx_ring[i]); - QL_DUMP_CQICB((struct cqicb *)&qdev->rx_ring[i]); - } -} -#endif diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c b/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c deleted file mode 100644 index a6886cc5654c..000000000000 --- a/drivers/net/ethernet/qlogic/qlge/qlge_ethtool.c +++ /dev/null @@ -1,735 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/module.h> -#include <linux/list.h> -#include <linux/pci.h> -#include <linux/dma-mapping.h> -#include <linux/pagemap.h> -#include <linux/sched.h> -#include <linux/dmapool.h> -#include <linux/mempool.h> -#include <linux/spinlock.h> -#include <linux/kthread.h> -#include <linux/interrupt.h> -#include <linux/errno.h> -#include <linux/ioport.h> -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/ipv6.h> -#include <net/ipv6.h> -#include <linux/tcp.h> -#include <linux/udp.h> -#include <linux/if_arp.h> -#include <linux/if_ether.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/ethtool.h> -#include <linux/skbuff.h> -#include <linux/rtnetlink.h> -#include <linux/if_vlan.h> -#include <linux/delay.h> -#include <linux/mm.h> -#include <linux/vmalloc.h> - - -#include "qlge.h" - -struct ql_stats { - char stat_string[ETH_GSTRING_LEN]; - int sizeof_stat; - int stat_offset; -}; - -#define QL_SIZEOF(m) FIELD_SIZEOF(struct ql_adapter, m) -#define QL_OFF(m) offsetof(struct ql_adapter, m) - -static const struct ql_stats ql_gstrings_stats[] = { - {"tx_pkts", QL_SIZEOF(nic_stats.tx_pkts), QL_OFF(nic_stats.tx_pkts)}, - {"tx_bytes", QL_SIZEOF(nic_stats.tx_bytes), QL_OFF(nic_stats.tx_bytes)}, - {"tx_mcast_pkts", QL_SIZEOF(nic_stats.tx_mcast_pkts), - QL_OFF(nic_stats.tx_mcast_pkts)}, - {"tx_bcast_pkts", QL_SIZEOF(nic_stats.tx_bcast_pkts), - QL_OFF(nic_stats.tx_bcast_pkts)}, - {"tx_ucast_pkts", QL_SIZEOF(nic_stats.tx_ucast_pkts), - QL_OFF(nic_stats.tx_ucast_pkts)}, - {"tx_ctl_pkts", QL_SIZEOF(nic_stats.tx_ctl_pkts), - QL_OFF(nic_stats.tx_ctl_pkts)}, - {"tx_pause_pkts", QL_SIZEOF(nic_stats.tx_pause_pkts), - QL_OFF(nic_stats.tx_pause_pkts)}, - {"tx_64_pkts", QL_SIZEOF(nic_stats.tx_64_pkt), - QL_OFF(nic_stats.tx_64_pkt)}, - {"tx_65_to_127_pkts", QL_SIZEOF(nic_stats.tx_65_to_127_pkt), - QL_OFF(nic_stats.tx_65_to_127_pkt)}, - {"tx_128_to_255_pkts", QL_SIZEOF(nic_stats.tx_128_to_255_pkt), - QL_OFF(nic_stats.tx_128_to_255_pkt)}, - {"tx_256_511_pkts", QL_SIZEOF(nic_stats.tx_256_511_pkt), - QL_OFF(nic_stats.tx_256_511_pkt)}, - {"tx_512_to_1023_pkts", QL_SIZEOF(nic_stats.tx_512_to_1023_pkt), - QL_OFF(nic_stats.tx_512_to_1023_pkt)}, - {"tx_1024_to_1518_pkts", QL_SIZEOF(nic_stats.tx_1024_to_1518_pkt), - QL_OFF(nic_stats.tx_1024_to_1518_pkt)}, - {"tx_1519_to_max_pkts", QL_SIZEOF(nic_stats.tx_1519_to_max_pkt), - QL_OFF(nic_stats.tx_1519_to_max_pkt)}, - {"tx_undersize_pkts", QL_SIZEOF(nic_stats.tx_undersize_pkt), - QL_OFF(nic_stats.tx_undersize_pkt)}, - {"tx_oversize_pkts", QL_SIZEOF(nic_stats.tx_oversize_pkt), - QL_OFF(nic_stats.tx_oversize_pkt)}, - {"rx_bytes", QL_SIZEOF(nic_stats.rx_bytes), QL_OFF(nic_stats.rx_bytes)}, - {"rx_bytes_ok", QL_SIZEOF(nic_stats.rx_bytes_ok), - QL_OFF(nic_stats.rx_bytes_ok)}, - {"rx_pkts", QL_SIZEOF(nic_stats.rx_pkts), QL_OFF(nic_stats.rx_pkts)}, - {"rx_pkts_ok", QL_SIZEOF(nic_stats.rx_pkts_ok), - QL_OFF(nic_stats.rx_pkts_ok)}, - {"rx_bcast_pkts", QL_SIZEOF(nic_stats.rx_bcast_pkts), - QL_OFF(nic_stats.rx_bcast_pkts)}, - {"rx_mcast_pkts", QL_SIZEOF(nic_stats.rx_mcast_pkts), - QL_OFF(nic_stats.rx_mcast_pkts)}, - {"rx_ucast_pkts", QL_SIZEOF(nic_stats.rx_ucast_pkts), - QL_OFF(nic_stats.rx_ucast_pkts)}, - {"rx_undersize_pkts", QL_SIZEOF(nic_stats.rx_undersize_pkts), - QL_OFF(nic_stats.rx_undersize_pkts)}, - {"rx_oversize_pkts", QL_SIZEOF(nic_stats.rx_oversize_pkts), - QL_OFF(nic_stats.rx_oversize_pkts)}, - {"rx_jabber_pkts", QL_SIZEOF(nic_stats.rx_jabber_pkts), - QL_OFF(nic_stats.rx_jabber_pkts)}, - {"rx_undersize_fcerr_pkts", - QL_SIZEOF(nic_stats.rx_undersize_fcerr_pkts), - QL_OFF(nic_stats.rx_undersize_fcerr_pkts)}, - {"rx_drop_events", QL_SIZEOF(nic_stats.rx_drop_events), - QL_OFF(nic_stats.rx_drop_events)}, - {"rx_fcerr_pkts", QL_SIZEOF(nic_stats.rx_fcerr_pkts), - QL_OFF(nic_stats.rx_fcerr_pkts)}, - {"rx_align_err", QL_SIZEOF(nic_stats.rx_align_err), - QL_OFF(nic_stats.rx_align_err)}, - {"rx_symbol_err", QL_SIZEOF(nic_stats.rx_symbol_err), - QL_OFF(nic_stats.rx_symbol_err)}, - {"rx_mac_err", QL_SIZEOF(nic_stats.rx_mac_err), - QL_OFF(nic_stats.rx_mac_err)}, - {"rx_ctl_pkts", QL_SIZEOF(nic_stats.rx_ctl_pkts), - QL_OFF(nic_stats.rx_ctl_pkts)}, - {"rx_pause_pkts", QL_SIZEOF(nic_stats.rx_pause_pkts), - QL_OFF(nic_stats.rx_pause_pkts)}, - {"rx_64_pkts", QL_SIZEOF(nic_stats.rx_64_pkts), - QL_OFF(nic_stats.rx_64_pkts)}, - {"rx_65_to_127_pkts", QL_SIZEOF(nic_stats.rx_65_to_127_pkts), - QL_OFF(nic_stats.rx_65_to_127_pkts)}, - {"rx_128_255_pkts", QL_SIZEOF(nic_stats.rx_128_255_pkts), - QL_OFF(nic_stats.rx_128_255_pkts)}, - {"rx_256_511_pkts", QL_SIZEOF(nic_stats.rx_256_511_pkts), - QL_OFF(nic_stats.rx_256_511_pkts)}, - {"rx_512_to_1023_pkts", QL_SIZEOF(nic_stats.rx_512_to_1023_pkts), - QL_OFF(nic_stats.rx_512_to_1023_pkts)}, - {"rx_1024_to_1518_pkts", QL_SIZEOF(nic_stats.rx_1024_to_1518_pkts), - QL_OFF(nic_stats.rx_1024_to_1518_pkts)}, - {"rx_1519_to_max_pkts", QL_SIZEOF(nic_stats.rx_1519_to_max_pkts), - QL_OFF(nic_stats.rx_1519_to_max_pkts)}, - {"rx_len_err_pkts", QL_SIZEOF(nic_stats.rx_len_err_pkts), - QL_OFF(nic_stats.rx_len_err_pkts)}, - {"rx_code_err", QL_SIZEOF(nic_stats.rx_code_err), - QL_OFF(nic_stats.rx_code_err)}, - {"rx_oversize_err", QL_SIZEOF(nic_stats.rx_oversize_err), - QL_OFF(nic_stats.rx_oversize_err)}, - {"rx_undersize_err", QL_SIZEOF(nic_stats.rx_undersize_err), - QL_OFF(nic_stats.rx_undersize_err)}, - {"rx_preamble_err", QL_SIZEOF(nic_stats.rx_preamble_err), - QL_OFF(nic_stats.rx_preamble_err)}, - {"rx_frame_len_err", QL_SIZEOF(nic_stats.rx_frame_len_err), - QL_OFF(nic_stats.rx_frame_len_err)}, - {"rx_crc_err", QL_SIZEOF(nic_stats.rx_crc_err), - QL_OFF(nic_stats.rx_crc_err)}, - {"rx_err_count", QL_SIZEOF(nic_stats.rx_err_count), - QL_OFF(nic_stats.rx_err_count)}, - {"tx_cbfc_pause_frames0", QL_SIZEOF(nic_stats.tx_cbfc_pause_frames0), - QL_OFF(nic_stats.tx_cbfc_pause_frames0)}, - {"tx_cbfc_pause_frames1", QL_SIZEOF(nic_stats.tx_cbfc_pause_frames1), - QL_OFF(nic_stats.tx_cbfc_pause_frames1)}, - {"tx_cbfc_pause_frames2", QL_SIZEOF(nic_stats.tx_cbfc_pause_frames2), - QL_OFF(nic_stats.tx_cbfc_pause_frames2)}, - {"tx_cbfc_pause_frames3", QL_SIZEOF(nic_stats.tx_cbfc_pause_frames3), - QL_OFF(nic_stats.tx_cbfc_pause_frames3)}, - {"tx_cbfc_pause_frames4", QL_SIZEOF(nic_stats.tx_cbfc_pause_frames4), - QL_OFF(nic_stats.tx_cbfc_pause_frames4)}, - {"tx_cbfc_pause_frames5", QL_SIZEOF(nic_stats.tx_cbfc_pause_frames5), - QL_OFF(nic_stats.tx_cbfc_pause_frames5)}, - {"tx_cbfc_pause_frames6", QL_SIZEOF(nic_stats.tx_cbfc_pause_frames6), - QL_OFF(nic_stats.tx_cbfc_pause_frames6)}, - {"tx_cbfc_pause_frames7", QL_SIZEOF(nic_stats.tx_cbfc_pause_frames7), - QL_OFF(nic_stats.tx_cbfc_pause_frames7)}, - {"rx_cbfc_pause_frames0", QL_SIZEOF(nic_stats.rx_cbfc_pause_frames0), - QL_OFF(nic_stats.rx_cbfc_pause_frames0)}, - {"rx_cbfc_pause_frames1", QL_SIZEOF(nic_stats.rx_cbfc_pause_frames1), - QL_OFF(nic_stats.rx_cbfc_pause_frames1)}, - {"rx_cbfc_pause_frames2", QL_SIZEOF(nic_stats.rx_cbfc_pause_frames2), - QL_OFF(nic_stats.rx_cbfc_pause_frames2)}, - {"rx_cbfc_pause_frames3", QL_SIZEOF(nic_stats.rx_cbfc_pause_frames3), - QL_OFF(nic_stats.rx_cbfc_pause_frames3)}, - {"rx_cbfc_pause_frames4", QL_SIZEOF(nic_stats.rx_cbfc_pause_frames4), - QL_OFF(nic_stats.rx_cbfc_pause_frames4)}, - {"rx_cbfc_pause_frames5", QL_SIZEOF(nic_stats.rx_cbfc_pause_frames5), - QL_OFF(nic_stats.rx_cbfc_pause_frames5)}, - {"rx_cbfc_pause_frames6", QL_SIZEOF(nic_stats.rx_cbfc_pause_frames6), - QL_OFF(nic_stats.rx_cbfc_pause_frames6)}, - {"rx_cbfc_pause_frames7", QL_SIZEOF(nic_stats.rx_cbfc_pause_frames7), - QL_OFF(nic_stats.rx_cbfc_pause_frames7)}, - {"rx_nic_fifo_drop", QL_SIZEOF(nic_stats.rx_nic_fifo_drop), - QL_OFF(nic_stats.rx_nic_fifo_drop)}, -}; - -static const char ql_gstrings_test[][ETH_GSTRING_LEN] = { - "Loopback test (offline)" -}; -#define QLGE_TEST_LEN (sizeof(ql_gstrings_test) / ETH_GSTRING_LEN) -#define QLGE_STATS_LEN ARRAY_SIZE(ql_gstrings_stats) -#define QLGE_RCV_MAC_ERR_STATS 7 - -static int ql_update_ring_coalescing(struct ql_adapter *qdev) -{ - int i, status = 0; - struct rx_ring *rx_ring; - struct cqicb *cqicb; - - if (!netif_running(qdev->ndev)) - return status; - - /* Skip the default queue, and update the outbound handler - * queues if they changed. - */ - cqicb = (struct cqicb *)&qdev->rx_ring[qdev->rss_ring_count]; - if (le16_to_cpu(cqicb->irq_delay) != qdev->tx_coalesce_usecs || - le16_to_cpu(cqicb->pkt_delay) != - qdev->tx_max_coalesced_frames) { - for (i = qdev->rss_ring_count; i < qdev->rx_ring_count; i++) { - rx_ring = &qdev->rx_ring[i]; - cqicb = (struct cqicb *)rx_ring; - cqicb->irq_delay = cpu_to_le16(qdev->tx_coalesce_usecs); - cqicb->pkt_delay = - cpu_to_le16(qdev->tx_max_coalesced_frames); - cqicb->flags = FLAGS_LI; - status = ql_write_cfg(qdev, cqicb, sizeof(*cqicb), - CFG_LCQ, rx_ring->cq_id); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed to load CQICB.\n"); - goto exit; - } - } - } - - /* Update the inbound (RSS) handler queues if they changed. */ - cqicb = (struct cqicb *)&qdev->rx_ring[0]; - if (le16_to_cpu(cqicb->irq_delay) != qdev->rx_coalesce_usecs || - le16_to_cpu(cqicb->pkt_delay) != - qdev->rx_max_coalesced_frames) { - for (i = 0; i < qdev->rss_ring_count; i++, rx_ring++) { - rx_ring = &qdev->rx_ring[i]; - cqicb = (struct cqicb *)rx_ring; - cqicb->irq_delay = cpu_to_le16(qdev->rx_coalesce_usecs); - cqicb->pkt_delay = - cpu_to_le16(qdev->rx_max_coalesced_frames); - cqicb->flags = FLAGS_LI; - status = ql_write_cfg(qdev, cqicb, sizeof(*cqicb), - CFG_LCQ, rx_ring->cq_id); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed to load CQICB.\n"); - goto exit; - } - } - } -exit: - return status; -} - -static void ql_update_stats(struct ql_adapter *qdev) -{ - u32 i; - u64 data; - u64 *iter = &qdev->nic_stats.tx_pkts; - - spin_lock(&qdev->stats_lock); - if (ql_sem_spinlock(qdev, qdev->xg_sem_mask)) { - netif_err(qdev, drv, qdev->ndev, - "Couldn't get xgmac sem.\n"); - goto quit; - } - /* - * Get TX statistics. - */ - for (i = 0x200; i < 0x280; i += 8) { - if (ql_read_xgmac_reg64(qdev, i, &data)) { - netif_err(qdev, drv, qdev->ndev, - "Error reading status register 0x%.04x.\n", - i); - goto end; - } else - *iter = data; - iter++; - } - - /* - * Get RX statistics. - */ - for (i = 0x300; i < 0x3d0; i += 8) { - if (ql_read_xgmac_reg64(qdev, i, &data)) { - netif_err(qdev, drv, qdev->ndev, - "Error reading status register 0x%.04x.\n", - i); - goto end; - } else - *iter = data; - iter++; - } - - /* Update receive mac error statistics */ - iter += QLGE_RCV_MAC_ERR_STATS; - - /* - * Get Per-priority TX pause frame counter statistics. - */ - for (i = 0x500; i < 0x540; i += 8) { - if (ql_read_xgmac_reg64(qdev, i, &data)) { - netif_err(qdev, drv, qdev->ndev, - "Error reading status register 0x%.04x.\n", - i); - goto end; - } else - *iter = data; - iter++; - } - - /* - * Get Per-priority RX pause frame counter statistics. - */ - for (i = 0x568; i < 0x5a8; i += 8) { - if (ql_read_xgmac_reg64(qdev, i, &data)) { - netif_err(qdev, drv, qdev->ndev, - "Error reading status register 0x%.04x.\n", - i); - goto end; - } else - *iter = data; - iter++; - } - - /* - * Get RX NIC FIFO DROP statistics. - */ - if (ql_read_xgmac_reg64(qdev, 0x5b8, &data)) { - netif_err(qdev, drv, qdev->ndev, - "Error reading status register 0x%.04x.\n", i); - goto end; - } else - *iter = data; -end: - ql_sem_unlock(qdev, qdev->xg_sem_mask); -quit: - spin_unlock(&qdev->stats_lock); - - QL_DUMP_STAT(qdev); -} - -static void ql_get_strings(struct net_device *dev, u32 stringset, u8 *buf) -{ - int index; - switch (stringset) { - case ETH_SS_TEST: - memcpy(buf, *ql_gstrings_test, QLGE_TEST_LEN * ETH_GSTRING_LEN); - break; - case ETH_SS_STATS: - for (index = 0; index < QLGE_STATS_LEN; index++) { - memcpy(buf + index * ETH_GSTRING_LEN, - ql_gstrings_stats[index].stat_string, - ETH_GSTRING_LEN); - } - break; - } -} - -static int ql_get_sset_count(struct net_device *dev, int sset) -{ - switch (sset) { - case ETH_SS_TEST: - return QLGE_TEST_LEN; - case ETH_SS_STATS: - return QLGE_STATS_LEN; - default: - return -EOPNOTSUPP; - } -} - -static void -ql_get_ethtool_stats(struct net_device *ndev, - struct ethtool_stats *stats, u64 *data) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - int index, length; - - length = QLGE_STATS_LEN; - ql_update_stats(qdev); - - for (index = 0; index < length; index++) { - char *p = (char *)qdev + - ql_gstrings_stats[index].stat_offset; - *data++ = (ql_gstrings_stats[index].sizeof_stat == - sizeof(u64)) ? *(u64 *)p : (*(u32 *)p); - } -} - -static int ql_get_link_ksettings(struct net_device *ndev, - struct ethtool_link_ksettings *ecmd) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - u32 supported, advertising; - - supported = SUPPORTED_10000baseT_Full; - advertising = ADVERTISED_10000baseT_Full; - - if ((qdev->link_status & STS_LINK_TYPE_MASK) == - STS_LINK_TYPE_10GBASET) { - supported |= (SUPPORTED_TP | SUPPORTED_Autoneg); - advertising |= (ADVERTISED_TP | ADVERTISED_Autoneg); - ecmd->base.port = PORT_TP; - ecmd->base.autoneg = AUTONEG_ENABLE; - } else { - supported |= SUPPORTED_FIBRE; - advertising |= ADVERTISED_FIBRE; - ecmd->base.port = PORT_FIBRE; - } - - ecmd->base.speed = SPEED_10000; - ecmd->base.duplex = DUPLEX_FULL; - - ethtool_convert_legacy_u32_to_link_mode(ecmd->link_modes.supported, - supported); - ethtool_convert_legacy_u32_to_link_mode(ecmd->link_modes.advertising, - advertising); - - return 0; -} - -static void ql_get_drvinfo(struct net_device *ndev, - struct ethtool_drvinfo *drvinfo) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - strlcpy(drvinfo->driver, qlge_driver_name, sizeof(drvinfo->driver)); - strlcpy(drvinfo->version, qlge_driver_version, - sizeof(drvinfo->version)); - snprintf(drvinfo->fw_version, sizeof(drvinfo->fw_version), - "v%d.%d.%d", - (qdev->fw_rev_id & 0x00ff0000) >> 16, - (qdev->fw_rev_id & 0x0000ff00) >> 8, - (qdev->fw_rev_id & 0x000000ff)); - strlcpy(drvinfo->bus_info, pci_name(qdev->pdev), - sizeof(drvinfo->bus_info)); -} - -static void ql_get_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - unsigned short ssys_dev = qdev->pdev->subsystem_device; - - /* WOL is only supported for mezz card. */ - if (ssys_dev == QLGE_MEZZ_SSYS_ID_068 || - ssys_dev == QLGE_MEZZ_SSYS_ID_180) { - wol->supported = WAKE_MAGIC; - wol->wolopts = qdev->wol; - } -} - -static int ql_set_wol(struct net_device *ndev, struct ethtool_wolinfo *wol) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - unsigned short ssys_dev = qdev->pdev->subsystem_device; - - /* WOL is only supported for mezz card. */ - if (ssys_dev != QLGE_MEZZ_SSYS_ID_068 && - ssys_dev != QLGE_MEZZ_SSYS_ID_180) { - netif_info(qdev, drv, qdev->ndev, - "WOL is only supported for mezz card\n"); - return -EOPNOTSUPP; - } - if (wol->wolopts & ~WAKE_MAGIC) - return -EINVAL; - qdev->wol = wol->wolopts; - - netif_info(qdev, drv, qdev->ndev, "Set wol option 0x%x\n", qdev->wol); - return 0; -} - -static int ql_set_phys_id(struct net_device *ndev, - enum ethtool_phys_id_state state) - -{ - struct ql_adapter *qdev = netdev_priv(ndev); - - switch (state) { - case ETHTOOL_ID_ACTIVE: - /* Save the current LED settings */ - if (ql_mb_get_led_cfg(qdev)) - return -EIO; - - /* Start blinking */ - ql_mb_set_led_cfg(qdev, QL_LED_BLINK); - return 0; - - case ETHTOOL_ID_INACTIVE: - /* Restore LED settings */ - if (ql_mb_set_led_cfg(qdev, qdev->led_config)) - return -EIO; - return 0; - - default: - return -EINVAL; - } -} - -static int ql_start_loopback(struct ql_adapter *qdev) -{ - if (netif_carrier_ok(qdev->ndev)) { - set_bit(QL_LB_LINK_UP, &qdev->flags); - netif_carrier_off(qdev->ndev); - } else - clear_bit(QL_LB_LINK_UP, &qdev->flags); - qdev->link_config |= CFG_LOOPBACK_PCS; - return ql_mb_set_port_cfg(qdev); -} - -static void ql_stop_loopback(struct ql_adapter *qdev) -{ - qdev->link_config &= ~CFG_LOOPBACK_PCS; - ql_mb_set_port_cfg(qdev); - if (test_bit(QL_LB_LINK_UP, &qdev->flags)) { - netif_carrier_on(qdev->ndev); - clear_bit(QL_LB_LINK_UP, &qdev->flags); - } -} - -static void ql_create_lb_frame(struct sk_buff *skb, - unsigned int frame_size) -{ - memset(skb->data, 0xFF, frame_size); - frame_size &= ~1; - memset(&skb->data[frame_size / 2], 0xAA, frame_size / 2 - 1); - memset(&skb->data[frame_size / 2 + 10], 0xBE, 1); - memset(&skb->data[frame_size / 2 + 12], 0xAF, 1); -} - -void ql_check_lb_frame(struct ql_adapter *qdev, - struct sk_buff *skb) -{ - unsigned int frame_size = skb->len; - - if ((*(skb->data + 3) == 0xFF) && - (*(skb->data + frame_size / 2 + 10) == 0xBE) && - (*(skb->data + frame_size / 2 + 12) == 0xAF)) { - atomic_dec(&qdev->lb_count); - return; - } -} - -static int ql_run_loopback_test(struct ql_adapter *qdev) -{ - int i; - netdev_tx_t rc; - struct sk_buff *skb; - unsigned int size = SMALL_BUF_MAP_SIZE; - - for (i = 0; i < 64; i++) { - skb = netdev_alloc_skb(qdev->ndev, size); - if (!skb) - return -ENOMEM; - - skb->queue_mapping = 0; - skb_put(skb, size); - ql_create_lb_frame(skb, size); - rc = ql_lb_send(skb, qdev->ndev); - if (rc != NETDEV_TX_OK) - return -EPIPE; - atomic_inc(&qdev->lb_count); - } - /* Give queue time to settle before testing results. */ - msleep(2); - ql_clean_lb_rx_ring(&qdev->rx_ring[0], 128); - return atomic_read(&qdev->lb_count) ? -EIO : 0; -} - -static int ql_loopback_test(struct ql_adapter *qdev, u64 *data) -{ - *data = ql_start_loopback(qdev); - if (*data) - goto out; - *data = ql_run_loopback_test(qdev); -out: - ql_stop_loopback(qdev); - return *data; -} - -static void ql_self_test(struct net_device *ndev, - struct ethtool_test *eth_test, u64 *data) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - - memset(data, 0, sizeof(u64) * QLGE_TEST_LEN); - - if (netif_running(ndev)) { - set_bit(QL_SELFTEST, &qdev->flags); - if (eth_test->flags == ETH_TEST_FL_OFFLINE) { - /* Offline tests */ - if (ql_loopback_test(qdev, &data[0])) - eth_test->flags |= ETH_TEST_FL_FAILED; - - } else { - /* Online tests */ - data[0] = 0; - } - clear_bit(QL_SELFTEST, &qdev->flags); - /* Give link time to come up after - * port configuration changes. - */ - msleep_interruptible(4 * 1000); - } else { - netif_err(qdev, drv, qdev->ndev, - "is down, Loopback test will fail.\n"); - eth_test->flags |= ETH_TEST_FL_FAILED; - } -} - -static int ql_get_regs_len(struct net_device *ndev) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - - if (!test_bit(QL_FRC_COREDUMP, &qdev->flags)) - return sizeof(struct ql_mpi_coredump); - else - return sizeof(struct ql_reg_dump); -} - -static void ql_get_regs(struct net_device *ndev, - struct ethtool_regs *regs, void *p) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - - ql_get_dump(qdev, p); - qdev->core_is_dumped = 0; - if (!test_bit(QL_FRC_COREDUMP, &qdev->flags)) - regs->len = sizeof(struct ql_mpi_coredump); - else - regs->len = sizeof(struct ql_reg_dump); -} - -static int ql_get_coalesce(struct net_device *dev, struct ethtool_coalesce *c) -{ - struct ql_adapter *qdev = netdev_priv(dev); - - c->rx_coalesce_usecs = qdev->rx_coalesce_usecs; - c->tx_coalesce_usecs = qdev->tx_coalesce_usecs; - - /* This chip coalesces as follows: - * If a packet arrives, hold off interrupts until - * cqicb->int_delay expires, but if no other packets arrive don't - * wait longer than cqicb->pkt_int_delay. But ethtool doesn't use a - * timer to coalesce on a frame basis. So, we have to take ethtool's - * max_coalesced_frames value and convert it to a delay in microseconds. - * We do this by using a basic thoughput of 1,000,000 frames per - * second @ (1024 bytes). This means one frame per usec. So it's a - * simple one to one ratio. - */ - c->rx_max_coalesced_frames = qdev->rx_max_coalesced_frames; - c->tx_max_coalesced_frames = qdev->tx_max_coalesced_frames; - - return 0; -} - -static int ql_set_coalesce(struct net_device *ndev, struct ethtool_coalesce *c) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - - /* Validate user parameters. */ - if (c->rx_coalesce_usecs > qdev->rx_ring_size / 2) - return -EINVAL; - /* Don't wait more than 10 usec. */ - if (c->rx_max_coalesced_frames > MAX_INTER_FRAME_WAIT) - return -EINVAL; - if (c->tx_coalesce_usecs > qdev->tx_ring_size / 2) - return -EINVAL; - if (c->tx_max_coalesced_frames > MAX_INTER_FRAME_WAIT) - return -EINVAL; - - /* Verify a change took place before updating the hardware. */ - if (qdev->rx_coalesce_usecs == c->rx_coalesce_usecs && - qdev->tx_coalesce_usecs == c->tx_coalesce_usecs && - qdev->rx_max_coalesced_frames == c->rx_max_coalesced_frames && - qdev->tx_max_coalesced_frames == c->tx_max_coalesced_frames) - return 0; - - qdev->rx_coalesce_usecs = c->rx_coalesce_usecs; - qdev->tx_coalesce_usecs = c->tx_coalesce_usecs; - qdev->rx_max_coalesced_frames = c->rx_max_coalesced_frames; - qdev->tx_max_coalesced_frames = c->tx_max_coalesced_frames; - - return ql_update_ring_coalescing(qdev); -} - -static void ql_get_pauseparam(struct net_device *netdev, - struct ethtool_pauseparam *pause) -{ - struct ql_adapter *qdev = netdev_priv(netdev); - - ql_mb_get_port_cfg(qdev); - if (qdev->link_config & CFG_PAUSE_STD) { - pause->rx_pause = 1; - pause->tx_pause = 1; - } -} - -static int ql_set_pauseparam(struct net_device *netdev, - struct ethtool_pauseparam *pause) -{ - struct ql_adapter *qdev = netdev_priv(netdev); - int status = 0; - - if ((pause->rx_pause) && (pause->tx_pause)) - qdev->link_config |= CFG_PAUSE_STD; - else if (!pause->rx_pause && !pause->tx_pause) - qdev->link_config &= ~CFG_PAUSE_STD; - else - return -EINVAL; - - status = ql_mb_set_port_cfg(qdev); - return status; -} - -static u32 ql_get_msglevel(struct net_device *ndev) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - return qdev->msg_enable; -} - -static void ql_set_msglevel(struct net_device *ndev, u32 value) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - qdev->msg_enable = value; -} - -const struct ethtool_ops qlge_ethtool_ops = { - .get_drvinfo = ql_get_drvinfo, - .get_wol = ql_get_wol, - .set_wol = ql_set_wol, - .get_regs_len = ql_get_regs_len, - .get_regs = ql_get_regs, - .get_msglevel = ql_get_msglevel, - .set_msglevel = ql_set_msglevel, - .get_link = ethtool_op_get_link, - .set_phys_id = ql_set_phys_id, - .self_test = ql_self_test, - .get_pauseparam = ql_get_pauseparam, - .set_pauseparam = ql_set_pauseparam, - .get_coalesce = ql_get_coalesce, - .set_coalesce = ql_set_coalesce, - .get_sset_count = ql_get_sset_count, - .get_strings = ql_get_strings, - .get_ethtool_stats = ql_get_ethtool_stats, - .get_link_ksettings = ql_get_link_ksettings, -}; - diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_main.c b/drivers/net/ethernet/qlogic/qlge/qlge_main.c deleted file mode 100644 index 6cae33072496..000000000000 --- a/drivers/net/ethernet/qlogic/qlge/qlge_main.c +++ /dev/null @@ -1,5027 +0,0 @@ -/* - * QLogic qlge NIC HBA Driver - * Copyright (c) 2003-2008 QLogic Corporation - * See LICENSE.qlge for copyright and licensing details. - * Author: Linux qlge network device driver by - * Ron Mercer <ron.mercer@qlogic.com> - */ -#include <linux/kernel.h> -#include <linux/bitops.h> -#include <linux/types.h> -#include <linux/module.h> -#include <linux/list.h> -#include <linux/pci.h> -#include <linux/dma-mapping.h> -#include <linux/pagemap.h> -#include <linux/sched.h> -#include <linux/slab.h> -#include <linux/dmapool.h> -#include <linux/mempool.h> -#include <linux/spinlock.h> -#include <linux/kthread.h> -#include <linux/interrupt.h> -#include <linux/errno.h> -#include <linux/ioport.h> -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/ipv6.h> -#include <net/ipv6.h> -#include <linux/tcp.h> -#include <linux/udp.h> -#include <linux/if_arp.h> -#include <linux/if_ether.h> -#include <linux/netdevice.h> -#include <linux/etherdevice.h> -#include <linux/ethtool.h> -#include <linux/if_vlan.h> -#include <linux/skbuff.h> -#include <linux/delay.h> -#include <linux/mm.h> -#include <linux/vmalloc.h> -#include <linux/prefetch.h> -#include <net/ip6_checksum.h> - -#include "qlge.h" - -char qlge_driver_name[] = DRV_NAME; -const char qlge_driver_version[] = DRV_VERSION; - -MODULE_AUTHOR("Ron Mercer <ron.mercer@qlogic.com>"); -MODULE_DESCRIPTION(DRV_STRING " "); -MODULE_LICENSE("GPL"); -MODULE_VERSION(DRV_VERSION); - -static const u32 default_msg = - NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_LINK | -/* NETIF_MSG_TIMER | */ - NETIF_MSG_IFDOWN | - NETIF_MSG_IFUP | - NETIF_MSG_RX_ERR | - NETIF_MSG_TX_ERR | -/* NETIF_MSG_TX_QUEUED | */ -/* NETIF_MSG_INTR | NETIF_MSG_TX_DONE | NETIF_MSG_RX_STATUS | */ -/* NETIF_MSG_PKTDATA | */ - NETIF_MSG_HW | NETIF_MSG_WOL | 0; - -static int debug = -1; /* defaults above */ -module_param(debug, int, 0664); -MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)"); - -#define MSIX_IRQ 0 -#define MSI_IRQ 1 -#define LEG_IRQ 2 -static int qlge_irq_type = MSIX_IRQ; -module_param(qlge_irq_type, int, 0664); -MODULE_PARM_DESC(qlge_irq_type, "0 = MSI-X, 1 = MSI, 2 = Legacy."); - -static int qlge_mpi_coredump; -module_param(qlge_mpi_coredump, int, 0); -MODULE_PARM_DESC(qlge_mpi_coredump, - "Option to enable MPI firmware dump. " - "Default is OFF - Do Not allocate memory. "); - -static int qlge_force_coredump; -module_param(qlge_force_coredump, int, 0); -MODULE_PARM_DESC(qlge_force_coredump, - "Option to allow force of firmware core dump. " - "Default is OFF - Do not allow."); - -static const struct pci_device_id qlge_pci_tbl[] = { - {PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, QLGE_DEVICE_ID_8012)}, - {PCI_DEVICE(PCI_VENDOR_ID_QLOGIC, QLGE_DEVICE_ID_8000)}, - /* required last entry */ - {0,} -}; - -MODULE_DEVICE_TABLE(pci, qlge_pci_tbl); - -static int ql_wol(struct ql_adapter *); -static void qlge_set_multicast_list(struct net_device *); -static int ql_adapter_down(struct ql_adapter *); -static int ql_adapter_up(struct ql_adapter *); - -/* This hardware semaphore causes exclusive access to - * resources shared between the NIC driver, MPI firmware, - * FCOE firmware and the FC driver. - */ -static int ql_sem_trylock(struct ql_adapter *qdev, u32 sem_mask) -{ - u32 sem_bits = 0; - - switch (sem_mask) { - case SEM_XGMAC0_MASK: - sem_bits = SEM_SET << SEM_XGMAC0_SHIFT; - break; - case SEM_XGMAC1_MASK: - sem_bits = SEM_SET << SEM_XGMAC1_SHIFT; - break; - case SEM_ICB_MASK: - sem_bits = SEM_SET << SEM_ICB_SHIFT; - break; - case SEM_MAC_ADDR_MASK: - sem_bits = SEM_SET << SEM_MAC_ADDR_SHIFT; - break; - case SEM_FLASH_MASK: - sem_bits = SEM_SET << SEM_FLASH_SHIFT; - break; - case SEM_PROBE_MASK: - sem_bits = SEM_SET << SEM_PROBE_SHIFT; - break; - case SEM_RT_IDX_MASK: - sem_bits = SEM_SET << SEM_RT_IDX_SHIFT; - break; - case SEM_PROC_REG_MASK: - sem_bits = SEM_SET << SEM_PROC_REG_SHIFT; - break; - default: - netif_alert(qdev, probe, qdev->ndev, "bad Semaphore mask!.\n"); - return -EINVAL; - } - - ql_write32(qdev, SEM, sem_bits | sem_mask); - return !(ql_read32(qdev, SEM) & sem_bits); -} - -int ql_sem_spinlock(struct ql_adapter *qdev, u32 sem_mask) -{ - unsigned int wait_count = 30; - do { - if (!ql_sem_trylock(qdev, sem_mask)) - return 0; - udelay(100); - } while (--wait_count); - return -ETIMEDOUT; -} - -void ql_sem_unlock(struct ql_adapter *qdev, u32 sem_mask) -{ - ql_write32(qdev, SEM, sem_mask); - ql_read32(qdev, SEM); /* flush */ -} - -/* This function waits for a specific bit to come ready - * in a given register. It is used mostly by the initialize - * process, but is also used in kernel thread API such as - * netdev->set_multi, netdev->set_mac_address, netdev->vlan_rx_add_vid. - */ -int ql_wait_reg_rdy(struct ql_adapter *qdev, u32 reg, u32 bit, u32 err_bit) -{ - u32 temp; - int count = UDELAY_COUNT; - - while (count) { - temp = ql_read32(qdev, reg); - - /* check for errors */ - if (temp & err_bit) { - netif_alert(qdev, probe, qdev->ndev, - "register 0x%.08x access error, value = 0x%.08x!.\n", - reg, temp); - return -EIO; - } else if (temp & bit) - return 0; - udelay(UDELAY_DELAY); - count--; - } - netif_alert(qdev, probe, qdev->ndev, - "Timed out waiting for reg %x to come ready.\n", reg); - return -ETIMEDOUT; -} - -/* The CFG register is used to download TX and RX control blocks - * to the chip. This function waits for an operation to complete. - */ -static int ql_wait_cfg(struct ql_adapter *qdev, u32 bit) -{ - int count = UDELAY_COUNT; - u32 temp; - - while (count) { - temp = ql_read32(qdev, CFG); - if (temp & CFG_LE) - return -EIO; - if (!(temp & bit)) - return 0; - udelay(UDELAY_DELAY); - count--; - } - return -ETIMEDOUT; -} - - -/* Used to issue init control blocks to hw. Maps control block, - * sets address, triggers download, waits for completion. - */ -int ql_write_cfg(struct ql_adapter *qdev, void *ptr, int size, u32 bit, - u16 q_id) -{ - u64 map; - int status = 0; - int direction; - u32 mask; - u32 value; - - direction = - (bit & (CFG_LRQ | CFG_LR | CFG_LCQ)) ? PCI_DMA_TODEVICE : - PCI_DMA_FROMDEVICE; - - map = pci_map_single(qdev->pdev, ptr, size, direction); - if (pci_dma_mapping_error(qdev->pdev, map)) { - netif_err(qdev, ifup, qdev->ndev, "Couldn't map DMA area.\n"); - return -ENOMEM; - } - - status = ql_sem_spinlock(qdev, SEM_ICB_MASK); - if (status) - return status; - - status = ql_wait_cfg(qdev, bit); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Timed out waiting for CFG to come ready.\n"); - goto exit; - } - - ql_write32(qdev, ICB_L, (u32) map); - ql_write32(qdev, ICB_H, (u32) (map >> 32)); - - mask = CFG_Q_MASK | (bit << 16); - value = bit | (q_id << CFG_Q_SHIFT); - ql_write32(qdev, CFG, (mask | value)); - - /* - * Wait for the bit to clear after signaling hw. - */ - status = ql_wait_cfg(qdev, bit); -exit: - ql_sem_unlock(qdev, SEM_ICB_MASK); /* does flush too */ - pci_unmap_single(qdev->pdev, map, size, direction); - return status; -} - -/* Get a specific MAC address from the CAM. Used for debug and reg dump. */ -int ql_get_mac_addr_reg(struct ql_adapter *qdev, u32 type, u16 index, - u32 *value) -{ - u32 offset = 0; - int status; - - switch (type) { - case MAC_ADDR_TYPE_MULTI_MAC: - case MAC_ADDR_TYPE_CAM_MAC: - { - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MW, 0); - if (status) - goto exit; - ql_write32(qdev, MAC_ADDR_IDX, (offset++) | /* offset */ - (index << MAC_ADDR_IDX_SHIFT) | /* index */ - MAC_ADDR_ADR | MAC_ADDR_RS | type); /* type */ - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MR, 0); - if (status) - goto exit; - *value++ = ql_read32(qdev, MAC_ADDR_DATA); - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MW, 0); - if (status) - goto exit; - ql_write32(qdev, MAC_ADDR_IDX, (offset++) | /* offset */ - (index << MAC_ADDR_IDX_SHIFT) | /* index */ - MAC_ADDR_ADR | MAC_ADDR_RS | type); /* type */ - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MR, 0); - if (status) - goto exit; - *value++ = ql_read32(qdev, MAC_ADDR_DATA); - if (type == MAC_ADDR_TYPE_CAM_MAC) { - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MW, 0); - if (status) - goto exit; - ql_write32(qdev, MAC_ADDR_IDX, (offset++) | /* offset */ - (index << MAC_ADDR_IDX_SHIFT) | /* index */ - MAC_ADDR_ADR | MAC_ADDR_RS | type); /* type */ - status = - ql_wait_reg_rdy(qdev, MAC_ADDR_IDX, - MAC_ADDR_MR, 0); - if (status) - goto exit; - *value++ = ql_read32(qdev, MAC_ADDR_DATA); - } - break; - } - case MAC_ADDR_TYPE_VLAN: - case MAC_ADDR_TYPE_MULTI_FLTR: - default: - netif_crit(qdev, ifup, qdev->ndev, - "Address type %d not yet supported.\n", type); - status = -EPERM; - } -exit: - return status; -} - -/* Set up a MAC, multicast or VLAN address for the - * inbound frame matching. - */ -static int ql_set_mac_addr_reg(struct ql_adapter *qdev, u8 *addr, u32 type, - u16 index) -{ - u32 offset = 0; - int status = 0; - - switch (type) { - case MAC_ADDR_TYPE_MULTI_MAC: - { - u32 upper = (addr[0] << 8) | addr[1]; - u32 lower = (addr[2] << 24) | (addr[3] << 16) | - (addr[4] << 8) | (addr[5]); - - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MW, 0); - if (status) - goto exit; - ql_write32(qdev, MAC_ADDR_IDX, (offset++) | - (index << MAC_ADDR_IDX_SHIFT) | - type | MAC_ADDR_E); - ql_write32(qdev, MAC_ADDR_DATA, lower); - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MW, 0); - if (status) - goto exit; - ql_write32(qdev, MAC_ADDR_IDX, (offset++) | - (index << MAC_ADDR_IDX_SHIFT) | - type | MAC_ADDR_E); - - ql_write32(qdev, MAC_ADDR_DATA, upper); - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MW, 0); - if (status) - goto exit; - break; - } - case MAC_ADDR_TYPE_CAM_MAC: - { - u32 cam_output; - u32 upper = (addr[0] << 8) | addr[1]; - u32 lower = - (addr[2] << 24) | (addr[3] << 16) | (addr[4] << 8) | - (addr[5]); - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MW, 0); - if (status) - goto exit; - ql_write32(qdev, MAC_ADDR_IDX, (offset++) | /* offset */ - (index << MAC_ADDR_IDX_SHIFT) | /* index */ - type); /* type */ - ql_write32(qdev, MAC_ADDR_DATA, lower); - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MW, 0); - if (status) - goto exit; - ql_write32(qdev, MAC_ADDR_IDX, (offset++) | /* offset */ - (index << MAC_ADDR_IDX_SHIFT) | /* index */ - type); /* type */ - ql_write32(qdev, MAC_ADDR_DATA, upper); - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MW, 0); - if (status) - goto exit; - ql_write32(qdev, MAC_ADDR_IDX, (offset) | /* offset */ - (index << MAC_ADDR_IDX_SHIFT) | /* index */ - type); /* type */ - /* This field should also include the queue id - and possibly the function id. Right now we hardcode - the route field to NIC core. - */ - cam_output = (CAM_OUT_ROUTE_NIC | - (qdev-> - func << CAM_OUT_FUNC_SHIFT) | - (0 << CAM_OUT_CQ_ID_SHIFT)); - if (qdev->ndev->features & NETIF_F_HW_VLAN_CTAG_RX) - cam_output |= CAM_OUT_RV; - /* route to NIC core */ - ql_write32(qdev, MAC_ADDR_DATA, cam_output); - break; - } - case MAC_ADDR_TYPE_VLAN: - { - u32 enable_bit = *((u32 *) &addr[0]); - /* For VLAN, the addr actually holds a bit that - * either enables or disables the vlan id we are - * addressing. It's either MAC_ADDR_E on or off. - * That's bit-27 we're talking about. - */ - status = - ql_wait_reg_rdy(qdev, - MAC_ADDR_IDX, MAC_ADDR_MW, 0); - if (status) - goto exit; - ql_write32(qdev, MAC_ADDR_IDX, offset | /* offset */ - (index << MAC_ADDR_IDX_SHIFT) | /* index */ - type | /* type */ - enable_bit); /* enable/disable */ - break; - } - case MAC_ADDR_TYPE_MULTI_FLTR: - default: - netif_crit(qdev, ifup, qdev->ndev, - "Address type %d not yet supported.\n", type); - status = -EPERM; - } -exit: - return status; -} - -/* Set or clear MAC address in hardware. We sometimes - * have to clear it to prevent wrong frame routing - * especially in a bonding environment. - */ -static int ql_set_mac_addr(struct ql_adapter *qdev, int set) -{ - int status; - char zero_mac_addr[ETH_ALEN]; - char *addr; - - if (set) { - addr = &qdev->current_mac_addr[0]; - netif_printk(qdev, ifup, KERN_DEBUG, qdev->ndev, - "Set Mac addr %pM\n", addr); - } else { - eth_zero_addr(zero_mac_addr); - addr = &zero_mac_addr[0]; - netif_printk(qdev, ifup, KERN_DEBUG, qdev->ndev, - "Clearing MAC address\n"); - } - status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK); - if (status) - return status; - status = ql_set_mac_addr_reg(qdev, (u8 *) addr, - MAC_ADDR_TYPE_CAM_MAC, qdev->func * MAX_CQ); - ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK); - if (status) - netif_err(qdev, ifup, qdev->ndev, - "Failed to init mac address.\n"); - return status; -} - -void ql_link_on(struct ql_adapter *qdev) -{ - netif_err(qdev, link, qdev->ndev, "Link is up.\n"); - netif_carrier_on(qdev->ndev); - ql_set_mac_addr(qdev, 1); -} - -void ql_link_off(struct ql_adapter *qdev) -{ - netif_err(qdev, link, qdev->ndev, "Link is down.\n"); - netif_carrier_off(qdev->ndev); - ql_set_mac_addr(qdev, 0); -} - -/* Get a specific frame routing value from the CAM. - * Used for debug and reg dump. - */ -int ql_get_routing_reg(struct ql_adapter *qdev, u32 index, u32 *value) -{ - int status = 0; - - status = ql_wait_reg_rdy(qdev, RT_IDX, RT_IDX_MW, 0); - if (status) - goto exit; - - ql_write32(qdev, RT_IDX, - RT_IDX_TYPE_NICQ | RT_IDX_RS | (index << RT_IDX_IDX_SHIFT)); - status = ql_wait_reg_rdy(qdev, RT_IDX, RT_IDX_MR, 0); - if (status) - goto exit; - *value = ql_read32(qdev, RT_DATA); -exit: - return status; -} - -/* The NIC function for this chip has 16 routing indexes. Each one can be used - * to route different frame types to various inbound queues. We send broadcast/ - * multicast/error frames to the default queue for slow handling, - * and CAM hit/RSS frames to the fast handling queues. - */ -static int ql_set_routing_reg(struct ql_adapter *qdev, u32 index, u32 mask, - int enable) -{ - int status = -EINVAL; /* Return error if no mask match. */ - u32 value = 0; - - switch (mask) { - case RT_IDX_CAM_HIT: - { - value = RT_IDX_DST_CAM_Q | /* dest */ - RT_IDX_TYPE_NICQ | /* type */ - (RT_IDX_CAM_HIT_SLOT << RT_IDX_IDX_SHIFT);/* index */ - break; - } - case RT_IDX_VALID: /* Promiscuous Mode frames. */ - { - value = RT_IDX_DST_DFLT_Q | /* dest */ - RT_IDX_TYPE_NICQ | /* type */ - (RT_IDX_PROMISCUOUS_SLOT << RT_IDX_IDX_SHIFT);/* index */ - break; - } - case RT_IDX_ERR: /* Pass up MAC,IP,TCP/UDP error frames. */ - { - value = RT_IDX_DST_DFLT_Q | /* dest */ - RT_IDX_TYPE_NICQ | /* type */ - (RT_IDX_ALL_ERR_SLOT << RT_IDX_IDX_SHIFT);/* index */ - break; - } - case RT_IDX_IP_CSUM_ERR: /* Pass up IP CSUM error frames. */ - { - value = RT_IDX_DST_DFLT_Q | /* dest */ - RT_IDX_TYPE_NICQ | /* type */ - (RT_IDX_IP_CSUM_ERR_SLOT << - RT_IDX_IDX_SHIFT); /* index */ - break; - } - case RT_IDX_TU_CSUM_ERR: /* Pass up TCP/UDP CSUM error frames. */ - { - value = RT_IDX_DST_DFLT_Q | /* dest */ - RT_IDX_TYPE_NICQ | /* type */ - (RT_IDX_TCP_UDP_CSUM_ERR_SLOT << - RT_IDX_IDX_SHIFT); /* index */ - break; - } - case RT_IDX_BCAST: /* Pass up Broadcast frames to default Q. */ - { - value = RT_IDX_DST_DFLT_Q | /* dest */ - RT_IDX_TYPE_NICQ | /* type */ - (RT_IDX_BCAST_SLOT << RT_IDX_IDX_SHIFT);/* index */ - break; - } - case RT_IDX_MCAST: /* Pass up All Multicast frames. */ - { - value = RT_IDX_DST_DFLT_Q | /* dest */ - RT_IDX_TYPE_NICQ | /* type */ - (RT_IDX_ALLMULTI_SLOT << RT_IDX_IDX_SHIFT);/* index */ - break; - } - case RT_IDX_MCAST_MATCH: /* Pass up matched Multicast frames. */ - { - value = RT_IDX_DST_DFLT_Q | /* dest */ - RT_IDX_TYPE_NICQ | /* type */ - (RT_IDX_MCAST_MATCH_SLOT << RT_IDX_IDX_SHIFT);/* index */ - break; - } - case RT_IDX_RSS_MATCH: /* Pass up matched RSS frames. */ - { - value = RT_IDX_DST_RSS | /* dest */ - RT_IDX_TYPE_NICQ | /* type */ - (RT_IDX_RSS_MATCH_SLOT << RT_IDX_IDX_SHIFT);/* index */ - break; - } - case 0: /* Clear the E-bit on an entry. */ - { - value = RT_IDX_DST_DFLT_Q | /* dest */ - RT_IDX_TYPE_NICQ | /* type */ - (index << RT_IDX_IDX_SHIFT);/* index */ - break; - } - default: - netif_err(qdev, ifup, qdev->ndev, - "Mask type %d not yet supported.\n", mask); - status = -EPERM; - goto exit; - } - - if (value) { - status = ql_wait_reg_rdy(qdev, RT_IDX, RT_IDX_MW, 0); - if (status) - goto exit; - value |= (enable ? RT_IDX_E : 0); - ql_write32(qdev, RT_IDX, value); - ql_write32(qdev, RT_DATA, enable ? mask : 0); - } -exit: - return status; -} - -static void ql_enable_interrupts(struct ql_adapter *qdev) -{ - ql_write32(qdev, INTR_EN, (INTR_EN_EI << 16) | INTR_EN_EI); -} - -static void ql_disable_interrupts(struct ql_adapter *qdev) -{ - ql_write32(qdev, INTR_EN, (INTR_EN_EI << 16)); -} - -/* If we're running with multiple MSI-X vectors then we enable on the fly. - * Otherwise, we may have multiple outstanding workers and don't want to - * enable until the last one finishes. In this case, the irq_cnt gets - * incremented every time we queue a worker and decremented every time - * a worker finishes. Once it hits zero we enable the interrupt. - */ -u32 ql_enable_completion_interrupt(struct ql_adapter *qdev, u32 intr) -{ - u32 var = 0; - unsigned long hw_flags = 0; - struct intr_context *ctx = qdev->intr_context + intr; - - if (likely(test_bit(QL_MSIX_ENABLED, &qdev->flags) && intr)) { - /* Always enable if we're MSIX multi interrupts and - * it's not the default (zeroeth) interrupt. - */ - ql_write32(qdev, INTR_EN, - ctx->intr_en_mask); - var = ql_read32(qdev, STS); - return var; - } - - spin_lock_irqsave(&qdev->hw_lock, hw_flags); - if (atomic_dec_and_test(&ctx->irq_cnt)) { - ql_write32(qdev, INTR_EN, - ctx->intr_en_mask); - var = ql_read32(qdev, STS); - } - spin_unlock_irqrestore(&qdev->hw_lock, hw_flags); - return var; -} - -static u32 ql_disable_completion_interrupt(struct ql_adapter *qdev, u32 intr) -{ - u32 var = 0; - struct intr_context *ctx; - - /* HW disables for us if we're MSIX multi interrupts and - * it's not the default (zeroeth) interrupt. - */ - if (likely(test_bit(QL_MSIX_ENABLED, &qdev->flags) && intr)) - return 0; - - ctx = qdev->intr_context + intr; - spin_lock(&qdev->hw_lock); - if (!atomic_read(&ctx->irq_cnt)) { - ql_write32(qdev, INTR_EN, - ctx->intr_dis_mask); - var = ql_read32(qdev, STS); - } - atomic_inc(&ctx->irq_cnt); - spin_unlock(&qdev->hw_lock); - return var; -} - -static void ql_enable_all_completion_interrupts(struct ql_adapter *qdev) -{ - int i; - for (i = 0; i < qdev->intr_count; i++) { - /* The enable call does a atomic_dec_and_test - * and enables only if the result is zero. - * So we precharge it here. - */ - if (unlikely(!test_bit(QL_MSIX_ENABLED, &qdev->flags) || - i == 0)) - atomic_set(&qdev->intr_context[i].irq_cnt, 1); - ql_enable_completion_interrupt(qdev, i); - } - -} - -static int ql_validate_flash(struct ql_adapter *qdev, u32 size, const char *str) -{ - int status, i; - u16 csum = 0; - __le16 *flash = (__le16 *)&qdev->flash; - - status = strncmp((char *)&qdev->flash, str, 4); - if (status) { - netif_err(qdev, ifup, qdev->ndev, "Invalid flash signature.\n"); - return status; - } - - for (i = 0; i < size; i++) - csum += le16_to_cpu(*flash++); - - if (csum) - netif_err(qdev, ifup, qdev->ndev, - "Invalid flash checksum, csum = 0x%.04x.\n", csum); - - return csum; -} - -static int ql_read_flash_word(struct ql_adapter *qdev, int offset, __le32 *data) -{ - int status = 0; - /* wait for reg to come ready */ - status = ql_wait_reg_rdy(qdev, - FLASH_ADDR, FLASH_ADDR_RDY, FLASH_ADDR_ERR); - if (status) - goto exit; - /* set up for reg read */ - ql_write32(qdev, FLASH_ADDR, FLASH_ADDR_R | offset); - /* wait for reg to come ready */ - status = ql_wait_reg_rdy(qdev, - FLASH_ADDR, FLASH_ADDR_RDY, FLASH_ADDR_ERR); - if (status) - goto exit; - /* This data is stored on flash as an array of - * __le32. Since ql_read32() returns cpu endian - * we need to swap it back. - */ - *data = cpu_to_le32(ql_read32(qdev, FLASH_DATA)); -exit: - return status; -} - -static int ql_get_8000_flash_params(struct ql_adapter *qdev) -{ - u32 i, size; - int status; - __le32 *p = (__le32 *)&qdev->flash; - u32 offset; - u8 mac_addr[6]; - - /* Get flash offset for function and adjust - * for dword access. - */ - if (!qdev->port) - offset = FUNC0_FLASH_OFFSET / sizeof(u32); - else - offset = FUNC1_FLASH_OFFSET / sizeof(u32); - - if (ql_sem_spinlock(qdev, SEM_FLASH_MASK)) - return -ETIMEDOUT; - - size = sizeof(struct flash_params_8000) / sizeof(u32); - for (i = 0; i < size; i++, p++) { - status = ql_read_flash_word(qdev, i+offset, p); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Error reading flash.\n"); - goto exit; - } - } - - status = ql_validate_flash(qdev, - sizeof(struct flash_params_8000) / sizeof(u16), - "8000"); - if (status) { - netif_err(qdev, ifup, qdev->ndev, "Invalid flash.\n"); - status = -EINVAL; - goto exit; - } - - /* Extract either manufacturer or BOFM modified - * MAC address. - */ - if (qdev->flash.flash_params_8000.data_type1 == 2) - memcpy(mac_addr, - qdev->flash.flash_params_8000.mac_addr1, - qdev->ndev->addr_len); - else - memcpy(mac_addr, - qdev->flash.flash_params_8000.mac_addr, - qdev->ndev->addr_len); - - if (!is_valid_ether_addr(mac_addr)) { - netif_err(qdev, ifup, qdev->ndev, "Invalid MAC address.\n"); - status = -EINVAL; - goto exit; - } - - memcpy(qdev->ndev->dev_addr, - mac_addr, - qdev->ndev->addr_len); - -exit: - ql_sem_unlock(qdev, SEM_FLASH_MASK); - return status; -} - -static int ql_get_8012_flash_params(struct ql_adapter *qdev) -{ - int i; - int status; - __le32 *p = (__le32 *)&qdev->flash; - u32 offset = 0; - u32 size = sizeof(struct flash_params_8012) / sizeof(u32); - - /* Second function's parameters follow the first - * function's. - */ - if (qdev->port) - offset = size; - - if (ql_sem_spinlock(qdev, SEM_FLASH_MASK)) - return -ETIMEDOUT; - - for (i = 0; i < size; i++, p++) { - status = ql_read_flash_word(qdev, i+offset, p); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Error reading flash.\n"); - goto exit; - } - - } - - status = ql_validate_flash(qdev, - sizeof(struct flash_params_8012) / sizeof(u16), - "8012"); - if (status) { - netif_err(qdev, ifup, qdev->ndev, "Invalid flash.\n"); - status = -EINVAL; - goto exit; - } - - if (!is_valid_ether_addr(qdev->flash.flash_params_8012.mac_addr)) { - status = -EINVAL; - goto exit; - } - - memcpy(qdev->ndev->dev_addr, - qdev->flash.flash_params_8012.mac_addr, - qdev->ndev->addr_len); - -exit: - ql_sem_unlock(qdev, SEM_FLASH_MASK); - return status; -} - -/* xgmac register are located behind the xgmac_addr and xgmac_data - * register pair. Each read/write requires us to wait for the ready - * bit before reading/writing the data. - */ -static int ql_write_xgmac_reg(struct ql_adapter *qdev, u32 reg, u32 data) -{ - int status; - /* wait for reg to come ready */ - status = ql_wait_reg_rdy(qdev, - XGMAC_ADDR, XGMAC_ADDR_RDY, XGMAC_ADDR_XME); - if (status) - return status; - /* write the data to the data reg */ - ql_write32(qdev, XGMAC_DATA, data); - /* trigger the write */ - ql_write32(qdev, XGMAC_ADDR, reg); - return status; -} - -/* xgmac register are located behind the xgmac_addr and xgmac_data - * register pair. Each read/write requires us to wait for the ready - * bit before reading/writing the data. - */ -int ql_read_xgmac_reg(struct ql_adapter *qdev, u32 reg, u32 *data) -{ - int status = 0; - /* wait for reg to come ready */ - status = ql_wait_reg_rdy(qdev, - XGMAC_ADDR, XGMAC_ADDR_RDY, XGMAC_ADDR_XME); - if (status) - goto exit; - /* set up for reg read */ - ql_write32(qdev, XGMAC_ADDR, reg | XGMAC_ADDR_R); - /* wait for reg to come ready */ - status = ql_wait_reg_rdy(qdev, - XGMAC_ADDR, XGMAC_ADDR_RDY, XGMAC_ADDR_XME); - if (status) - goto exit; - /* get the data */ - *data = ql_read32(qdev, XGMAC_DATA); -exit: - return status; -} - -/* This is used for reading the 64-bit statistics regs. */ -int ql_read_xgmac_reg64(struct ql_adapter *qdev, u32 reg, u64 *data) -{ - int status = 0; - u32 hi = 0; - u32 lo = 0; - - status = ql_read_xgmac_reg(qdev, reg, &lo); - if (status) - goto exit; - - status = ql_read_xgmac_reg(qdev, reg + 4, &hi); - if (status) - goto exit; - - *data = (u64) lo | ((u64) hi << 32); - -exit: - return status; -} - -static int ql_8000_port_initialize(struct ql_adapter *qdev) -{ - int status; - /* - * Get MPI firmware version for driver banner - * and ethool info. - */ - status = ql_mb_about_fw(qdev); - if (status) - goto exit; - status = ql_mb_get_fw_state(qdev); - if (status) - goto exit; - /* Wake up a worker to get/set the TX/RX frame sizes. */ - queue_delayed_work(qdev->workqueue, &qdev->mpi_port_cfg_work, 0); -exit: - return status; -} - -/* Take the MAC Core out of reset. - * Enable statistics counting. - * Take the transmitter/receiver out of reset. - * This functionality may be done in the MPI firmware at a - * later date. - */ -static int ql_8012_port_initialize(struct ql_adapter *qdev) -{ - int status = 0; - u32 data; - - if (ql_sem_trylock(qdev, qdev->xg_sem_mask)) { - /* Another function has the semaphore, so - * wait for the port init bit to come ready. - */ - netif_info(qdev, link, qdev->ndev, - "Another function has the semaphore, so wait for the port init bit to come ready.\n"); - status = ql_wait_reg_rdy(qdev, STS, qdev->port_init, 0); - if (status) { - netif_crit(qdev, link, qdev->ndev, - "Port initialize timed out.\n"); - } - return status; - } - - netif_info(qdev, link, qdev->ndev, "Got xgmac semaphore!.\n"); - /* Set the core reset. */ - status = ql_read_xgmac_reg(qdev, GLOBAL_CFG, &data); - if (status) - goto end; - data |= GLOBAL_CFG_RESET; - status = ql_write_xgmac_reg(qdev, GLOBAL_CFG, data); - if (status) - goto end; - - /* Clear the core reset and turn on jumbo for receiver. */ - data &= ~GLOBAL_CFG_RESET; /* Clear core reset. */ - data |= GLOBAL_CFG_JUMBO; /* Turn on jumbo. */ - data |= GLOBAL_CFG_TX_STAT_EN; - data |= GLOBAL_CFG_RX_STAT_EN; - status = ql_write_xgmac_reg(qdev, GLOBAL_CFG, data); - if (status) - goto end; - - /* Enable transmitter, and clear it's reset. */ - status = ql_read_xgmac_reg(qdev, TX_CFG, &data); - if (status) - goto end; - data &= ~TX_CFG_RESET; /* Clear the TX MAC reset. */ - data |= TX_CFG_EN; /* Enable the transmitter. */ - status = ql_write_xgmac_reg(qdev, TX_CFG, data); - if (status) - goto end; - - /* Enable receiver and clear it's reset. */ - status = ql_read_xgmac_reg(qdev, RX_CFG, &data); - if (status) - goto end; - data &= ~RX_CFG_RESET; /* Clear the RX MAC reset. */ - data |= RX_CFG_EN; /* Enable the receiver. */ - status = ql_write_xgmac_reg(qdev, RX_CFG, data); - if (status) - goto end; - - /* Turn on jumbo. */ - status = - ql_write_xgmac_reg(qdev, MAC_TX_PARAMS, MAC_TX_PARAMS_JUMBO | (0x2580 << 16)); - if (status) - goto end; - status = - ql_write_xgmac_reg(qdev, MAC_RX_PARAMS, 0x2580); - if (status) - goto end; - - /* Signal to the world that the port is enabled. */ - ql_write32(qdev, STS, ((qdev->port_init << 16) | qdev->port_init)); -end: - ql_sem_unlock(qdev, qdev->xg_sem_mask); - return status; -} - -static inline unsigned int ql_lbq_block_size(struct ql_adapter *qdev) -{ - return PAGE_SIZE << qdev->lbq_buf_order; -} - -/* Get the next large buffer. */ -static struct bq_desc *ql_get_curr_lbuf(struct rx_ring *rx_ring) -{ - struct bq_desc *lbq_desc = &rx_ring->lbq[rx_ring->lbq_curr_idx]; - rx_ring->lbq_curr_idx++; - if (rx_ring->lbq_curr_idx == rx_ring->lbq_len) - rx_ring->lbq_curr_idx = 0; - rx_ring->lbq_free_cnt++; - return lbq_desc; -} - -static struct bq_desc *ql_get_curr_lchunk(struct ql_adapter *qdev, - struct rx_ring *rx_ring) -{ - struct bq_desc *lbq_desc = ql_get_curr_lbuf(rx_ring); - - pci_dma_sync_single_for_cpu(qdev->pdev, - dma_unmap_addr(lbq_desc, mapaddr), - rx_ring->lbq_buf_size, - PCI_DMA_FROMDEVICE); - - /* If it's the last chunk of our master page then - * we unmap it. - */ - if ((lbq_desc->p.pg_chunk.offset + rx_ring->lbq_buf_size) - == ql_lbq_block_size(qdev)) - pci_unmap_page(qdev->pdev, - lbq_desc->p.pg_chunk.map, - ql_lbq_block_size(qdev), - PCI_DMA_FROMDEVICE); - return lbq_desc; -} - -/* Get the next small buffer. */ -static struct bq_desc *ql_get_curr_sbuf(struct rx_ring *rx_ring) -{ - struct bq_desc *sbq_desc = &rx_ring->sbq[rx_ring->sbq_curr_idx]; - rx_ring->sbq_curr_idx++; - if (rx_ring->sbq_curr_idx == rx_ring->sbq_len) - rx_ring->sbq_curr_idx = 0; - rx_ring->sbq_free_cnt++; - return sbq_desc; -} - -/* Update an rx ring index. */ -static void ql_update_cq(struct rx_ring *rx_ring) -{ - rx_ring->cnsmr_idx++; - rx_ring->curr_entry++; - if (unlikely(rx_ring->cnsmr_idx == rx_ring->cq_len)) { - rx_ring->cnsmr_idx = 0; - rx_ring->curr_entry = rx_ring->cq_base; - } -} - -static void ql_write_cq_idx(struct rx_ring *rx_ring) -{ - ql_write_db_reg(rx_ring->cnsmr_idx, rx_ring->cnsmr_idx_db_reg); -} - -static int ql_get_next_chunk(struct ql_adapter *qdev, struct rx_ring *rx_ring, - struct bq_desc *lbq_desc) -{ - if (!rx_ring->pg_chunk.page) { - u64 map; - rx_ring->pg_chunk.page = alloc_pages(__GFP_COMP | GFP_ATOMIC, - qdev->lbq_buf_order); - if (unlikely(!rx_ring->pg_chunk.page)) { - netif_err(qdev, drv, qdev->ndev, - "page allocation failed.\n"); - return -ENOMEM; - } - rx_ring->pg_chunk.offset = 0; - map = pci_map_page(qdev->pdev, rx_ring->pg_chunk.page, - 0, ql_lbq_block_size(qdev), - PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(qdev->pdev, map)) { - __free_pages(rx_ring->pg_chunk.page, - qdev->lbq_buf_order); - rx_ring->pg_chunk.page = NULL; - netif_err(qdev, drv, qdev->ndev, - "PCI mapping failed.\n"); - return -ENOMEM; - } - rx_ring->pg_chunk.map = map; - rx_ring->pg_chunk.va = page_address(rx_ring->pg_chunk.page); - } - - /* Copy the current master pg_chunk info - * to the current descriptor. - */ - lbq_desc->p.pg_chunk = rx_ring->pg_chunk; - - /* Adjust the master page chunk for next - * buffer get. - */ - rx_ring->pg_chunk.offset += rx_ring->lbq_buf_size; - if (rx_ring->pg_chunk.offset == ql_lbq_block_size(qdev)) { - rx_ring->pg_chunk.page = NULL; - lbq_desc->p.pg_chunk.last_flag = 1; - } else { - rx_ring->pg_chunk.va += rx_ring->lbq_buf_size; - get_page(rx_ring->pg_chunk.page); - lbq_desc->p.pg_chunk.last_flag = 0; - } - return 0; -} -/* Process (refill) a large buffer queue. */ -static void ql_update_lbq(struct ql_adapter *qdev, struct rx_ring *rx_ring) -{ - u32 clean_idx = rx_ring->lbq_clean_idx; - u32 start_idx = clean_idx; - struct bq_desc *lbq_desc; - u64 map; - int i; - - while (rx_ring->lbq_free_cnt > 32) { - for (i = (rx_ring->lbq_clean_idx % 16); i < 16; i++) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "lbq: try cleaning clean_idx = %d.\n", - clean_idx); - lbq_desc = &rx_ring->lbq[clean_idx]; - if (ql_get_next_chunk(qdev, rx_ring, lbq_desc)) { - rx_ring->lbq_clean_idx = clean_idx; - netif_err(qdev, ifup, qdev->ndev, - "Could not get a page chunk, i=%d, clean_idx =%d .\n", - i, clean_idx); - return; - } - - map = lbq_desc->p.pg_chunk.map + - lbq_desc->p.pg_chunk.offset; - dma_unmap_addr_set(lbq_desc, mapaddr, map); - dma_unmap_len_set(lbq_desc, maplen, - rx_ring->lbq_buf_size); - *lbq_desc->addr = cpu_to_le64(map); - - pci_dma_sync_single_for_device(qdev->pdev, map, - rx_ring->lbq_buf_size, - PCI_DMA_FROMDEVICE); - clean_idx++; - if (clean_idx == rx_ring->lbq_len) - clean_idx = 0; - } - - rx_ring->lbq_clean_idx = clean_idx; - rx_ring->lbq_prod_idx += 16; - if (rx_ring->lbq_prod_idx == rx_ring->lbq_len) - rx_ring->lbq_prod_idx = 0; - rx_ring->lbq_free_cnt -= 16; - } - - if (start_idx != clean_idx) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "lbq: updating prod idx = %d.\n", - rx_ring->lbq_prod_idx); - ql_write_db_reg(rx_ring->lbq_prod_idx, - rx_ring->lbq_prod_idx_db_reg); - } -} - -/* Process (refill) a small buffer queue. */ -static void ql_update_sbq(struct ql_adapter *qdev, struct rx_ring *rx_ring) -{ - u32 clean_idx = rx_ring->sbq_clean_idx; - u32 start_idx = clean_idx; - struct bq_desc *sbq_desc; - u64 map; - int i; - - while (rx_ring->sbq_free_cnt > 16) { - for (i = (rx_ring->sbq_clean_idx % 16); i < 16; i++) { - sbq_desc = &rx_ring->sbq[clean_idx]; - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "sbq: try cleaning clean_idx = %d.\n", - clean_idx); - if (sbq_desc->p.skb == NULL) { - netif_printk(qdev, rx_status, KERN_DEBUG, - qdev->ndev, - "sbq: getting new skb for index %d.\n", - sbq_desc->index); - sbq_desc->p.skb = - netdev_alloc_skb(qdev->ndev, - SMALL_BUFFER_SIZE); - if (sbq_desc->p.skb == NULL) { - rx_ring->sbq_clean_idx = clean_idx; - return; - } - skb_reserve(sbq_desc->p.skb, QLGE_SB_PAD); - map = pci_map_single(qdev->pdev, - sbq_desc->p.skb->data, - rx_ring->sbq_buf_size, - PCI_DMA_FROMDEVICE); - if (pci_dma_mapping_error(qdev->pdev, map)) { - netif_err(qdev, ifup, qdev->ndev, - "PCI mapping failed.\n"); - rx_ring->sbq_clean_idx = clean_idx; - dev_kfree_skb_any(sbq_desc->p.skb); - sbq_desc->p.skb = NULL; - return; - } - dma_unmap_addr_set(sbq_desc, mapaddr, map); - dma_unmap_len_set(sbq_desc, maplen, - rx_ring->sbq_buf_size); - *sbq_desc->addr = cpu_to_le64(map); - } - - clean_idx++; - if (clean_idx == rx_ring->sbq_len) - clean_idx = 0; - } - rx_ring->sbq_clean_idx = clean_idx; - rx_ring->sbq_prod_idx += 16; - if (rx_ring->sbq_prod_idx == rx_ring->sbq_len) - rx_ring->sbq_prod_idx = 0; - rx_ring->sbq_free_cnt -= 16; - } - - if (start_idx != clean_idx) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "sbq: updating prod idx = %d.\n", - rx_ring->sbq_prod_idx); - ql_write_db_reg(rx_ring->sbq_prod_idx, - rx_ring->sbq_prod_idx_db_reg); - } -} - -static void ql_update_buffer_queues(struct ql_adapter *qdev, - struct rx_ring *rx_ring) -{ - ql_update_sbq(qdev, rx_ring); - ql_update_lbq(qdev, rx_ring); -} - -/* Unmaps tx buffers. Can be called from send() if a pci mapping - * fails at some stage, or from the interrupt when a tx completes. - */ -static void ql_unmap_send(struct ql_adapter *qdev, - struct tx_ring_desc *tx_ring_desc, int mapped) -{ - int i; - for (i = 0; i < mapped; i++) { - if (i == 0 || (i == 7 && mapped > 7)) { - /* - * Unmap the skb->data area, or the - * external sglist (AKA the Outbound - * Address List (OAL)). - * If its the zeroeth element, then it's - * the skb->data area. If it's the 7th - * element and there is more than 6 frags, - * then its an OAL. - */ - if (i == 7) { - netif_printk(qdev, tx_done, KERN_DEBUG, - qdev->ndev, - "unmapping OAL area.\n"); - } - pci_unmap_single(qdev->pdev, - dma_unmap_addr(&tx_ring_desc->map[i], - mapaddr), - dma_unmap_len(&tx_ring_desc->map[i], - maplen), - PCI_DMA_TODEVICE); - } else { - netif_printk(qdev, tx_done, KERN_DEBUG, qdev->ndev, - "unmapping frag %d.\n", i); - pci_unmap_page(qdev->pdev, - dma_unmap_addr(&tx_ring_desc->map[i], - mapaddr), - dma_unmap_len(&tx_ring_desc->map[i], - maplen), PCI_DMA_TODEVICE); - } - } - -} - -/* Map the buffers for this transmit. This will return - * NETDEV_TX_BUSY or NETDEV_TX_OK based on success. - */ -static int ql_map_send(struct ql_adapter *qdev, - struct ob_mac_iocb_req *mac_iocb_ptr, - struct sk_buff *skb, struct tx_ring_desc *tx_ring_desc) -{ - int len = skb_headlen(skb); - dma_addr_t map; - int frag_idx, err, map_idx = 0; - struct tx_buf_desc *tbd = mac_iocb_ptr->tbd; - int frag_cnt = skb_shinfo(skb)->nr_frags; - - if (frag_cnt) { - netif_printk(qdev, tx_queued, KERN_DEBUG, qdev->ndev, - "frag_cnt = %d.\n", frag_cnt); - } - /* - * Map the skb buffer first. - */ - map = pci_map_single(qdev->pdev, skb->data, len, PCI_DMA_TODEVICE); - - err = pci_dma_mapping_error(qdev->pdev, map); - if (err) { - netif_err(qdev, tx_queued, qdev->ndev, - "PCI mapping failed with error: %d\n", err); - - return NETDEV_TX_BUSY; - } - - tbd->len = cpu_to_le32(len); - tbd->addr = cpu_to_le64(map); - dma_unmap_addr_set(&tx_ring_desc->map[map_idx], mapaddr, map); - dma_unmap_len_set(&tx_ring_desc->map[map_idx], maplen, len); - map_idx++; - - /* - * This loop fills the remainder of the 8 address descriptors - * in the IOCB. If there are more than 7 fragments, then the - * eighth address desc will point to an external list (OAL). - * When this happens, the remainder of the frags will be stored - * in this list. - */ - for (frag_idx = 0; frag_idx < frag_cnt; frag_idx++, map_idx++) { - skb_frag_t *frag = &skb_shinfo(skb)->frags[frag_idx]; - tbd++; - if (frag_idx == 6 && frag_cnt > 7) { - /* Let's tack on an sglist. - * Our control block will now - * look like this: - * iocb->seg[0] = skb->data - * iocb->seg[1] = frag[0] - * iocb->seg[2] = frag[1] - * iocb->seg[3] = frag[2] - * iocb->seg[4] = frag[3] - * iocb->seg[5] = frag[4] - * iocb->seg[6] = frag[5] - * iocb->seg[7] = ptr to OAL (external sglist) - * oal->seg[0] = frag[6] - * oal->seg[1] = frag[7] - * oal->seg[2] = frag[8] - * oal->seg[3] = frag[9] - * oal->seg[4] = frag[10] - * etc... - */ - /* Tack on the OAL in the eighth segment of IOCB. */ - map = pci_map_single(qdev->pdev, &tx_ring_desc->oal, - sizeof(struct oal), - PCI_DMA_TODEVICE); - err = pci_dma_mapping_error(qdev->pdev, map); - if (err) { - netif_err(qdev, tx_queued, qdev->ndev, - "PCI mapping outbound address list with error: %d\n", - err); - goto map_error; - } - - tbd->addr = cpu_to_le64(map); - /* - * The length is the number of fragments - * that remain to be mapped times the length - * of our sglist (OAL). - */ - tbd->len = - cpu_to_le32((sizeof(struct tx_buf_desc) * - (frag_cnt - frag_idx)) | TX_DESC_C); - dma_unmap_addr_set(&tx_ring_desc->map[map_idx], mapaddr, - map); - dma_unmap_len_set(&tx_ring_desc->map[map_idx], maplen, - sizeof(struct oal)); - tbd = (struct tx_buf_desc *)&tx_ring_desc->oal; - map_idx++; - } - - map = skb_frag_dma_map(&qdev->pdev->dev, frag, 0, skb_frag_size(frag), - DMA_TO_DEVICE); - - err = dma_mapping_error(&qdev->pdev->dev, map); - if (err) { - netif_err(qdev, tx_queued, qdev->ndev, - "PCI mapping frags failed with error: %d.\n", - err); - goto map_error; - } - - tbd->addr = cpu_to_le64(map); - tbd->len = cpu_to_le32(skb_frag_size(frag)); - dma_unmap_addr_set(&tx_ring_desc->map[map_idx], mapaddr, map); - dma_unmap_len_set(&tx_ring_desc->map[map_idx], maplen, - skb_frag_size(frag)); - - } - /* Save the number of segments we've mapped. */ - tx_ring_desc->map_cnt = map_idx; - /* Terminate the last segment. */ - tbd->len = cpu_to_le32(le32_to_cpu(tbd->len) | TX_DESC_E); - return NETDEV_TX_OK; - -map_error: - /* - * If the first frag mapping failed, then i will be zero. - * This causes the unmap of the skb->data area. Otherwise - * we pass in the number of frags that mapped successfully - * so they can be umapped. - */ - ql_unmap_send(qdev, tx_ring_desc, map_idx); - return NETDEV_TX_BUSY; -} - -/* Categorizing receive firmware frame errors */ -static void ql_categorize_rx_err(struct ql_adapter *qdev, u8 rx_err, - struct rx_ring *rx_ring) -{ - struct nic_stats *stats = &qdev->nic_stats; - - stats->rx_err_count++; - rx_ring->rx_errors++; - - switch (rx_err & IB_MAC_IOCB_RSP_ERR_MASK) { - case IB_MAC_IOCB_RSP_ERR_CODE_ERR: - stats->rx_code_err++; - break; - case IB_MAC_IOCB_RSP_ERR_OVERSIZE: - stats->rx_oversize_err++; - break; - case IB_MAC_IOCB_RSP_ERR_UNDERSIZE: - stats->rx_undersize_err++; - break; - case IB_MAC_IOCB_RSP_ERR_PREAMBLE: - stats->rx_preamble_err++; - break; - case IB_MAC_IOCB_RSP_ERR_FRAME_LEN: - stats->rx_frame_len_err++; - break; - case IB_MAC_IOCB_RSP_ERR_CRC: - stats->rx_crc_err++; - default: - break; - } -} - -/** - * ql_update_mac_hdr_len - helper routine to update the mac header length - * based on vlan tags if present - */ -static void ql_update_mac_hdr_len(struct ql_adapter *qdev, - struct ib_mac_iocb_rsp *ib_mac_rsp, - void *page, size_t *len) -{ - u16 *tags; - - if (qdev->ndev->features & NETIF_F_HW_VLAN_CTAG_RX) - return; - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_V) { - tags = (u16 *)page; - /* Look for stacked vlan tags in ethertype field */ - if (tags[6] == ETH_P_8021Q && - tags[8] == ETH_P_8021Q) - *len += 2 * VLAN_HLEN; - else - *len += VLAN_HLEN; - } -} - -/* Process an inbound completion from an rx ring. */ -static void ql_process_mac_rx_gro_page(struct ql_adapter *qdev, - struct rx_ring *rx_ring, - struct ib_mac_iocb_rsp *ib_mac_rsp, - u32 length, - u16 vlan_id) -{ - struct sk_buff *skb; - struct bq_desc *lbq_desc = ql_get_curr_lchunk(qdev, rx_ring); - struct napi_struct *napi = &rx_ring->napi; - - /* Frame error, so drop the packet. */ - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { - ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); - put_page(lbq_desc->p.pg_chunk.page); - return; - } - napi->dev = qdev->ndev; - - skb = napi_get_frags(napi); - if (!skb) { - netif_err(qdev, drv, qdev->ndev, - "Couldn't get an skb, exiting.\n"); - rx_ring->rx_dropped++; - put_page(lbq_desc->p.pg_chunk.page); - return; - } - prefetch(lbq_desc->p.pg_chunk.va); - __skb_fill_page_desc(skb, skb_shinfo(skb)->nr_frags, - lbq_desc->p.pg_chunk.page, - lbq_desc->p.pg_chunk.offset, - length); - - skb->len += length; - skb->data_len += length; - skb->truesize += length; - skb_shinfo(skb)->nr_frags++; - - rx_ring->rx_packets++; - rx_ring->rx_bytes += length; - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb_record_rx_queue(skb, rx_ring->cq_id); - if (vlan_id != 0xffff) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_id); - napi_gro_frags(napi); -} - -/* Process an inbound completion from an rx ring. */ -static void ql_process_mac_rx_page(struct ql_adapter *qdev, - struct rx_ring *rx_ring, - struct ib_mac_iocb_rsp *ib_mac_rsp, - u32 length, - u16 vlan_id) -{ - struct net_device *ndev = qdev->ndev; - struct sk_buff *skb = NULL; - void *addr; - struct bq_desc *lbq_desc = ql_get_curr_lchunk(qdev, rx_ring); - struct napi_struct *napi = &rx_ring->napi; - size_t hlen = ETH_HLEN; - - skb = netdev_alloc_skb(ndev, length); - if (!skb) { - rx_ring->rx_dropped++; - put_page(lbq_desc->p.pg_chunk.page); - return; - } - - addr = lbq_desc->p.pg_chunk.va; - prefetch(addr); - - /* Frame error, so drop the packet. */ - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { - ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); - goto err_out; - } - - /* Update the MAC header length*/ - ql_update_mac_hdr_len(qdev, ib_mac_rsp, addr, &hlen); - - /* The max framesize filter on this chip is set higher than - * MTU since FCoE uses 2k frames. - */ - if (skb->len > ndev->mtu + hlen) { - netif_err(qdev, drv, qdev->ndev, - "Segment too small, dropping.\n"); - rx_ring->rx_dropped++; - goto err_out; - } - skb_put_data(skb, addr, hlen); - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "%d bytes of headers and data in large. Chain page to new skb and pull tail.\n", - length); - skb_fill_page_desc(skb, 0, lbq_desc->p.pg_chunk.page, - lbq_desc->p.pg_chunk.offset + hlen, - length - hlen); - skb->len += length - hlen; - skb->data_len += length - hlen; - skb->truesize += length - hlen; - - rx_ring->rx_packets++; - rx_ring->rx_bytes += skb->len; - skb->protocol = eth_type_trans(skb, ndev); - skb_checksum_none_assert(skb); - - if ((ndev->features & NETIF_F_RXCSUM) && - !(ib_mac_rsp->flags1 & IB_MAC_CSUM_ERR_MASK)) { - /* TCP frame. */ - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_T) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "TCP checksum done!\n"); - skb->ip_summed = CHECKSUM_UNNECESSARY; - } else if ((ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_U) && - (ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_V4)) { - /* Unfragmented ipv4 UDP frame. */ - struct iphdr *iph = - (struct iphdr *)((u8 *)addr + hlen); - if (!(iph->frag_off & - htons(IP_MF|IP_OFFSET))) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - netif_printk(qdev, rx_status, KERN_DEBUG, - qdev->ndev, - "UDP checksum done!\n"); - } - } - } - - skb_record_rx_queue(skb, rx_ring->cq_id); - if (vlan_id != 0xffff) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_id); - if (skb->ip_summed == CHECKSUM_UNNECESSARY) - napi_gro_receive(napi, skb); - else - netif_receive_skb(skb); - return; -err_out: - dev_kfree_skb_any(skb); - put_page(lbq_desc->p.pg_chunk.page); -} - -/* Process an inbound completion from an rx ring. */ -static void ql_process_mac_rx_skb(struct ql_adapter *qdev, - struct rx_ring *rx_ring, - struct ib_mac_iocb_rsp *ib_mac_rsp, - u32 length, - u16 vlan_id) -{ - struct net_device *ndev = qdev->ndev; - struct sk_buff *skb = NULL; - struct sk_buff *new_skb = NULL; - struct bq_desc *sbq_desc = ql_get_curr_sbuf(rx_ring); - - skb = sbq_desc->p.skb; - /* Allocate new_skb and copy */ - new_skb = netdev_alloc_skb(qdev->ndev, length + NET_IP_ALIGN); - if (new_skb == NULL) { - rx_ring->rx_dropped++; - return; - } - skb_reserve(new_skb, NET_IP_ALIGN); - - pci_dma_sync_single_for_cpu(qdev->pdev, - dma_unmap_addr(sbq_desc, mapaddr), - dma_unmap_len(sbq_desc, maplen), - PCI_DMA_FROMDEVICE); - - skb_put_data(new_skb, skb->data, length); - - pci_dma_sync_single_for_device(qdev->pdev, - dma_unmap_addr(sbq_desc, mapaddr), - dma_unmap_len(sbq_desc, maplen), - PCI_DMA_FROMDEVICE); - skb = new_skb; - - /* Frame error, so drop the packet. */ - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { - ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); - dev_kfree_skb_any(skb); - return; - } - - /* loopback self test for ethtool */ - if (test_bit(QL_SELFTEST, &qdev->flags)) { - ql_check_lb_frame(qdev, skb); - dev_kfree_skb_any(skb); - return; - } - - /* The max framesize filter on this chip is set higher than - * MTU since FCoE uses 2k frames. - */ - if (skb->len > ndev->mtu + ETH_HLEN) { - dev_kfree_skb_any(skb); - rx_ring->rx_dropped++; - return; - } - - prefetch(skb->data); - if (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "%s Multicast.\n", - (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) == - IB_MAC_IOCB_RSP_M_HASH ? "Hash" : - (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) == - IB_MAC_IOCB_RSP_M_REG ? "Registered" : - (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) == - IB_MAC_IOCB_RSP_M_PROM ? "Promiscuous" : ""); - } - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_P) - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "Promiscuous Packet.\n"); - - rx_ring->rx_packets++; - rx_ring->rx_bytes += skb->len; - skb->protocol = eth_type_trans(skb, ndev); - skb_checksum_none_assert(skb); - - /* If rx checksum is on, and there are no - * csum or frame errors. - */ - if ((ndev->features & NETIF_F_RXCSUM) && - !(ib_mac_rsp->flags1 & IB_MAC_CSUM_ERR_MASK)) { - /* TCP frame. */ - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_T) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "TCP checksum done!\n"); - skb->ip_summed = CHECKSUM_UNNECESSARY; - } else if ((ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_U) && - (ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_V4)) { - /* Unfragmented ipv4 UDP frame. */ - struct iphdr *iph = (struct iphdr *) skb->data; - if (!(iph->frag_off & - htons(IP_MF|IP_OFFSET))) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - netif_printk(qdev, rx_status, KERN_DEBUG, - qdev->ndev, - "UDP checksum done!\n"); - } - } - } - - skb_record_rx_queue(skb, rx_ring->cq_id); - if (vlan_id != 0xffff) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_id); - if (skb->ip_summed == CHECKSUM_UNNECESSARY) - napi_gro_receive(&rx_ring->napi, skb); - else - netif_receive_skb(skb); -} - -static void ql_realign_skb(struct sk_buff *skb, int len) -{ - void *temp_addr = skb->data; - - /* Undo the skb_reserve(skb,32) we did before - * giving to hardware, and realign data on - * a 2-byte boundary. - */ - skb->data -= QLGE_SB_PAD - NET_IP_ALIGN; - skb->tail -= QLGE_SB_PAD - NET_IP_ALIGN; - memmove(skb->data, temp_addr, len); -} - -/* - * This function builds an skb for the given inbound - * completion. It will be rewritten for readability in the near - * future, but for not it works well. - */ -static struct sk_buff *ql_build_rx_skb(struct ql_adapter *qdev, - struct rx_ring *rx_ring, - struct ib_mac_iocb_rsp *ib_mac_rsp) -{ - struct bq_desc *lbq_desc; - struct bq_desc *sbq_desc; - struct sk_buff *skb = NULL; - u32 length = le32_to_cpu(ib_mac_rsp->data_len); - u32 hdr_len = le32_to_cpu(ib_mac_rsp->hdr_len); - size_t hlen = ETH_HLEN; - - /* - * Handle the header buffer if present. - */ - if (ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HV && - ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HS) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "Header of %d bytes in small buffer.\n", hdr_len); - /* - * Headers fit nicely into a small buffer. - */ - sbq_desc = ql_get_curr_sbuf(rx_ring); - pci_unmap_single(qdev->pdev, - dma_unmap_addr(sbq_desc, mapaddr), - dma_unmap_len(sbq_desc, maplen), - PCI_DMA_FROMDEVICE); - skb = sbq_desc->p.skb; - ql_realign_skb(skb, hdr_len); - skb_put(skb, hdr_len); - sbq_desc->p.skb = NULL; - } - - /* - * Handle the data buffer(s). - */ - if (unlikely(!length)) { /* Is there data too? */ - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "No Data buffer in this packet.\n"); - return skb; - } - - if (ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_DS) { - if (ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HS) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "Headers in small, data of %d bytes in small, combine them.\n", - length); - /* - * Data is less than small buffer size so it's - * stuffed in a small buffer. - * For this case we append the data - * from the "data" small buffer to the "header" small - * buffer. - */ - sbq_desc = ql_get_curr_sbuf(rx_ring); - pci_dma_sync_single_for_cpu(qdev->pdev, - dma_unmap_addr - (sbq_desc, mapaddr), - dma_unmap_len - (sbq_desc, maplen), - PCI_DMA_FROMDEVICE); - skb_put_data(skb, sbq_desc->p.skb->data, length); - pci_dma_sync_single_for_device(qdev->pdev, - dma_unmap_addr - (sbq_desc, - mapaddr), - dma_unmap_len - (sbq_desc, - maplen), - PCI_DMA_FROMDEVICE); - } else { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "%d bytes in a single small buffer.\n", - length); - sbq_desc = ql_get_curr_sbuf(rx_ring); - skb = sbq_desc->p.skb; - ql_realign_skb(skb, length); - skb_put(skb, length); - pci_unmap_single(qdev->pdev, - dma_unmap_addr(sbq_desc, - mapaddr), - dma_unmap_len(sbq_desc, - maplen), - PCI_DMA_FROMDEVICE); - sbq_desc->p.skb = NULL; - } - } else if (ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_DL) { - if (ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HS) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "Header in small, %d bytes in large. Chain large to small!\n", - length); - /* - * The data is in a single large buffer. We - * chain it to the header buffer's skb and let - * it rip. - */ - lbq_desc = ql_get_curr_lchunk(qdev, rx_ring); - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "Chaining page at offset = %d, for %d bytes to skb.\n", - lbq_desc->p.pg_chunk.offset, length); - skb_fill_page_desc(skb, 0, lbq_desc->p.pg_chunk.page, - lbq_desc->p.pg_chunk.offset, - length); - skb->len += length; - skb->data_len += length; - skb->truesize += length; - } else { - /* - * The headers and data are in a single large buffer. We - * copy it to a new skb and let it go. This can happen with - * jumbo mtu on a non-TCP/UDP frame. - */ - lbq_desc = ql_get_curr_lchunk(qdev, rx_ring); - skb = netdev_alloc_skb(qdev->ndev, length); - if (skb == NULL) { - netif_printk(qdev, probe, KERN_DEBUG, qdev->ndev, - "No skb available, drop the packet.\n"); - return NULL; - } - pci_unmap_page(qdev->pdev, - dma_unmap_addr(lbq_desc, - mapaddr), - dma_unmap_len(lbq_desc, maplen), - PCI_DMA_FROMDEVICE); - skb_reserve(skb, NET_IP_ALIGN); - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "%d bytes of headers and data in large. Chain page to new skb and pull tail.\n", - length); - skb_fill_page_desc(skb, 0, - lbq_desc->p.pg_chunk.page, - lbq_desc->p.pg_chunk.offset, - length); - skb->len += length; - skb->data_len += length; - skb->truesize += length; - ql_update_mac_hdr_len(qdev, ib_mac_rsp, - lbq_desc->p.pg_chunk.va, - &hlen); - __pskb_pull_tail(skb, hlen); - } - } else { - /* - * The data is in a chain of large buffers - * pointed to by a small buffer. We loop - * thru and chain them to the our small header - * buffer's skb. - * frags: There are 18 max frags and our small - * buffer will hold 32 of them. The thing is, - * we'll use 3 max for our 9000 byte jumbo - * frames. If the MTU goes up we could - * eventually be in trouble. - */ - int size, i = 0; - sbq_desc = ql_get_curr_sbuf(rx_ring); - pci_unmap_single(qdev->pdev, - dma_unmap_addr(sbq_desc, mapaddr), - dma_unmap_len(sbq_desc, maplen), - PCI_DMA_FROMDEVICE); - if (!(ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HS)) { - /* - * This is an non TCP/UDP IP frame, so - * the headers aren't split into a small - * buffer. We have to use the small buffer - * that contains our sg list as our skb to - * send upstairs. Copy the sg list here to - * a local buffer and use it to find the - * pages to chain. - */ - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "%d bytes of headers & data in chain of large.\n", - length); - skb = sbq_desc->p.skb; - sbq_desc->p.skb = NULL; - skb_reserve(skb, NET_IP_ALIGN); - } - do { - lbq_desc = ql_get_curr_lchunk(qdev, rx_ring); - size = (length < rx_ring->lbq_buf_size) ? length : - rx_ring->lbq_buf_size; - - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "Adding page %d to skb for %d bytes.\n", - i, size); - skb_fill_page_desc(skb, i, - lbq_desc->p.pg_chunk.page, - lbq_desc->p.pg_chunk.offset, - size); - skb->len += size; - skb->data_len += size; - skb->truesize += size; - length -= size; - i++; - } while (length > 0); - ql_update_mac_hdr_len(qdev, ib_mac_rsp, lbq_desc->p.pg_chunk.va, - &hlen); - __pskb_pull_tail(skb, hlen); - } - return skb; -} - -/* Process an inbound completion from an rx ring. */ -static void ql_process_mac_split_rx_intr(struct ql_adapter *qdev, - struct rx_ring *rx_ring, - struct ib_mac_iocb_rsp *ib_mac_rsp, - u16 vlan_id) -{ - struct net_device *ndev = qdev->ndev; - struct sk_buff *skb = NULL; - - QL_DUMP_IB_MAC_RSP(ib_mac_rsp); - - skb = ql_build_rx_skb(qdev, rx_ring, ib_mac_rsp); - if (unlikely(!skb)) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "No skb available, drop packet.\n"); - rx_ring->rx_dropped++; - return; - } - - /* Frame error, so drop the packet. */ - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_ERR_MASK) { - ql_categorize_rx_err(qdev, ib_mac_rsp->flags2, rx_ring); - dev_kfree_skb_any(skb); - return; - } - - /* The max framesize filter on this chip is set higher than - * MTU since FCoE uses 2k frames. - */ - if (skb->len > ndev->mtu + ETH_HLEN) { - dev_kfree_skb_any(skb); - rx_ring->rx_dropped++; - return; - } - - /* loopback self test for ethtool */ - if (test_bit(QL_SELFTEST, &qdev->flags)) { - ql_check_lb_frame(qdev, skb); - dev_kfree_skb_any(skb); - return; - } - - prefetch(skb->data); - if (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, "%s Multicast.\n", - (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) == - IB_MAC_IOCB_RSP_M_HASH ? "Hash" : - (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) == - IB_MAC_IOCB_RSP_M_REG ? "Registered" : - (ib_mac_rsp->flags1 & IB_MAC_IOCB_RSP_M_MASK) == - IB_MAC_IOCB_RSP_M_PROM ? "Promiscuous" : ""); - rx_ring->rx_multicast++; - } - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_P) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "Promiscuous Packet.\n"); - } - - skb->protocol = eth_type_trans(skb, ndev); - skb_checksum_none_assert(skb); - - /* If rx checksum is on, and there are no - * csum or frame errors. - */ - if ((ndev->features & NETIF_F_RXCSUM) && - !(ib_mac_rsp->flags1 & IB_MAC_CSUM_ERR_MASK)) { - /* TCP frame. */ - if (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_T) { - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "TCP checksum done!\n"); - skb->ip_summed = CHECKSUM_UNNECESSARY; - } else if ((ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_U) && - (ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_V4)) { - /* Unfragmented ipv4 UDP frame. */ - struct iphdr *iph = (struct iphdr *) skb->data; - if (!(iph->frag_off & - htons(IP_MF|IP_OFFSET))) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "TCP checksum done!\n"); - } - } - } - - rx_ring->rx_packets++; - rx_ring->rx_bytes += skb->len; - skb_record_rx_queue(skb, rx_ring->cq_id); - if (vlan_id != 0xffff) - __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlan_id); - if (skb->ip_summed == CHECKSUM_UNNECESSARY) - napi_gro_receive(&rx_ring->napi, skb); - else - netif_receive_skb(skb); -} - -/* Process an inbound completion from an rx ring. */ -static unsigned long ql_process_mac_rx_intr(struct ql_adapter *qdev, - struct rx_ring *rx_ring, - struct ib_mac_iocb_rsp *ib_mac_rsp) -{ - u32 length = le32_to_cpu(ib_mac_rsp->data_len); - u16 vlan_id = ((ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_V) && - (qdev->ndev->features & NETIF_F_HW_VLAN_CTAG_RX)) ? - ((le16_to_cpu(ib_mac_rsp->vlan_id) & - IB_MAC_IOCB_RSP_VLAN_MASK)) : 0xffff; - - QL_DUMP_IB_MAC_RSP(ib_mac_rsp); - - if (ib_mac_rsp->flags4 & IB_MAC_IOCB_RSP_HV) { - /* The data and headers are split into - * separate buffers. - */ - ql_process_mac_split_rx_intr(qdev, rx_ring, ib_mac_rsp, - vlan_id); - } else if (ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_DS) { - /* The data fit in a single small buffer. - * Allocate a new skb, copy the data and - * return the buffer to the free pool. - */ - ql_process_mac_rx_skb(qdev, rx_ring, ib_mac_rsp, - length, vlan_id); - } else if ((ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_DL) && - !(ib_mac_rsp->flags1 & IB_MAC_CSUM_ERR_MASK) && - (ib_mac_rsp->flags2 & IB_MAC_IOCB_RSP_T)) { - /* TCP packet in a page chunk that's been checksummed. - * Tack it on to our GRO skb and let it go. - */ - ql_process_mac_rx_gro_page(qdev, rx_ring, ib_mac_rsp, - length, vlan_id); - } else if (ib_mac_rsp->flags3 & IB_MAC_IOCB_RSP_DL) { - /* Non-TCP packet in a page chunk. Allocate an - * skb, tack it on frags, and send it up. - */ - ql_process_mac_rx_page(qdev, rx_ring, ib_mac_rsp, - length, vlan_id); - } else { - /* Non-TCP/UDP large frames that span multiple buffers - * can be processed corrrectly by the split frame logic. - */ - ql_process_mac_split_rx_intr(qdev, rx_ring, ib_mac_rsp, - vlan_id); - } - - return (unsigned long)length; -} - -/* Process an outbound completion from an rx ring. */ -static void ql_process_mac_tx_intr(struct ql_adapter *qdev, - struct ob_mac_iocb_rsp *mac_rsp) -{ - struct tx_ring *tx_ring; - struct tx_ring_desc *tx_ring_desc; - - QL_DUMP_OB_MAC_RSP(mac_rsp); - tx_ring = &qdev->tx_ring[mac_rsp->txq_idx]; - tx_ring_desc = &tx_ring->q[mac_rsp->tid]; - ql_unmap_send(qdev, tx_ring_desc, tx_ring_desc->map_cnt); - tx_ring->tx_bytes += (tx_ring_desc->skb)->len; - tx_ring->tx_packets++; - dev_kfree_skb(tx_ring_desc->skb); - tx_ring_desc->skb = NULL; - - if (unlikely(mac_rsp->flags1 & (OB_MAC_IOCB_RSP_E | - OB_MAC_IOCB_RSP_S | - OB_MAC_IOCB_RSP_L | - OB_MAC_IOCB_RSP_P | OB_MAC_IOCB_RSP_B))) { - if (mac_rsp->flags1 & OB_MAC_IOCB_RSP_E) { - netif_warn(qdev, tx_done, qdev->ndev, - "Total descriptor length did not match transfer length.\n"); - } - if (mac_rsp->flags1 & OB_MAC_IOCB_RSP_S) { - netif_warn(qdev, tx_done, qdev->ndev, - "Frame too short to be valid, not sent.\n"); - } - if (mac_rsp->flags1 & OB_MAC_IOCB_RSP_L) { - netif_warn(qdev, tx_done, qdev->ndev, - "Frame too long, but sent anyway.\n"); - } - if (mac_rsp->flags1 & OB_MAC_IOCB_RSP_B) { - netif_warn(qdev, tx_done, qdev->ndev, - "PCI backplane error. Frame not sent.\n"); - } - } - atomic_inc(&tx_ring->tx_count); -} - -/* Fire up a handler to reset the MPI processor. */ -void ql_queue_fw_error(struct ql_adapter *qdev) -{ - ql_link_off(qdev); - queue_delayed_work(qdev->workqueue, &qdev->mpi_reset_work, 0); -} - -void ql_queue_asic_error(struct ql_adapter *qdev) -{ - ql_link_off(qdev); - ql_disable_interrupts(qdev); - /* Clear adapter up bit to signal the recovery - * process that it shouldn't kill the reset worker - * thread - */ - clear_bit(QL_ADAPTER_UP, &qdev->flags); - /* Set asic recovery bit to indicate reset process that we are - * in fatal error recovery process rather than normal close - */ - set_bit(QL_ASIC_RECOVERY, &qdev->flags); - queue_delayed_work(qdev->workqueue, &qdev->asic_reset_work, 0); -} - -static void ql_process_chip_ae_intr(struct ql_adapter *qdev, - struct ib_ae_iocb_rsp *ib_ae_rsp) -{ - switch (ib_ae_rsp->event) { - case MGMT_ERR_EVENT: - netif_err(qdev, rx_err, qdev->ndev, - "Management Processor Fatal Error.\n"); - ql_queue_fw_error(qdev); - return; - - case CAM_LOOKUP_ERR_EVENT: - netdev_err(qdev->ndev, "Multiple CAM hits lookup occurred.\n"); - netdev_err(qdev->ndev, "This event shouldn't occur.\n"); - ql_queue_asic_error(qdev); - return; - - case SOFT_ECC_ERROR_EVENT: - netdev_err(qdev->ndev, "Soft ECC error detected.\n"); - ql_queue_asic_error(qdev); - break; - - case PCI_ERR_ANON_BUF_RD: - netdev_err(qdev->ndev, "PCI error occurred when reading " - "anonymous buffers from rx_ring %d.\n", - ib_ae_rsp->q_id); - ql_queue_asic_error(qdev); - break; - - default: - netif_err(qdev, drv, qdev->ndev, "Unexpected event %d.\n", - ib_ae_rsp->event); - ql_queue_asic_error(qdev); - break; - } -} - -static int ql_clean_outbound_rx_ring(struct rx_ring *rx_ring) -{ - struct ql_adapter *qdev = rx_ring->qdev; - u32 prod = ql_read_sh_reg(rx_ring->prod_idx_sh_reg); - struct ob_mac_iocb_rsp *net_rsp = NULL; - int count = 0; - - struct tx_ring *tx_ring; - /* While there are entries in the completion queue. */ - while (prod != rx_ring->cnsmr_idx) { - - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "cq_id = %d, prod = %d, cnsmr = %d\n", - rx_ring->cq_id, prod, rx_ring->cnsmr_idx); - - net_rsp = (struct ob_mac_iocb_rsp *)rx_ring->curr_entry; - rmb(); - switch (net_rsp->opcode) { - - case OPCODE_OB_MAC_TSO_IOCB: - case OPCODE_OB_MAC_IOCB: - ql_process_mac_tx_intr(qdev, net_rsp); - break; - default: - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "Hit default case, not handled! dropping the packet, opcode = %x.\n", - net_rsp->opcode); - } - count++; - ql_update_cq(rx_ring); - prod = ql_read_sh_reg(rx_ring->prod_idx_sh_reg); - } - if (!net_rsp) - return 0; - ql_write_cq_idx(rx_ring); - tx_ring = &qdev->tx_ring[net_rsp->txq_idx]; - if (__netif_subqueue_stopped(qdev->ndev, tx_ring->wq_id)) { - if ((atomic_read(&tx_ring->tx_count) > (tx_ring->wq_len / 4))) - /* - * The queue got stopped because the tx_ring was full. - * Wake it up, because it's now at least 25% empty. - */ - netif_wake_subqueue(qdev->ndev, tx_ring->wq_id); - } - - return count; -} - -static int ql_clean_inbound_rx_ring(struct rx_ring *rx_ring, int budget) -{ - struct ql_adapter *qdev = rx_ring->qdev; - u32 prod = ql_read_sh_reg(rx_ring->prod_idx_sh_reg); - struct ql_net_rsp_iocb *net_rsp; - int count = 0; - - /* While there are entries in the completion queue. */ - while (prod != rx_ring->cnsmr_idx) { - - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "cq_id = %d, prod = %d, cnsmr = %d\n", - rx_ring->cq_id, prod, rx_ring->cnsmr_idx); - - net_rsp = rx_ring->curr_entry; - rmb(); - switch (net_rsp->opcode) { - case OPCODE_IB_MAC_IOCB: - ql_process_mac_rx_intr(qdev, rx_ring, - (struct ib_mac_iocb_rsp *) - net_rsp); - break; - - case OPCODE_IB_AE_IOCB: - ql_process_chip_ae_intr(qdev, (struct ib_ae_iocb_rsp *) - net_rsp); - break; - default: - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "Hit default case, not handled! dropping the packet, opcode = %x.\n", - net_rsp->opcode); - break; - } - count++; - ql_update_cq(rx_ring); - prod = ql_read_sh_reg(rx_ring->prod_idx_sh_reg); - if (count == budget) - break; - } - ql_update_buffer_queues(qdev, rx_ring); - ql_write_cq_idx(rx_ring); - return count; -} - -static int ql_napi_poll_msix(struct napi_struct *napi, int budget) -{ - struct rx_ring *rx_ring = container_of(napi, struct rx_ring, napi); - struct ql_adapter *qdev = rx_ring->qdev; - struct rx_ring *trx_ring; - int i, work_done = 0; - struct intr_context *ctx = &qdev->intr_context[rx_ring->cq_id]; - - netif_printk(qdev, rx_status, KERN_DEBUG, qdev->ndev, - "Enter, NAPI POLL cq_id = %d.\n", rx_ring->cq_id); - - /* Service the TX rings first. They start - * right after the RSS rings. */ - for (i = qdev->rss_ring_count; i < qdev->rx_ring_count; i++) { - trx_ring = &qdev->rx_ring[i]; - /* If this TX completion ring belongs to this vector and - * it's not empty then service it. - */ - if ((ctx->irq_mask & (1 << trx_ring->cq_id)) && - (ql_read_sh_reg(trx_ring->prod_idx_sh_reg) != - trx_ring->cnsmr_idx)) { - netif_printk(qdev, intr, KERN_DEBUG, qdev->ndev, - "%s: Servicing TX completion ring %d.\n", - __func__, trx_ring->cq_id); - ql_clean_outbound_rx_ring(trx_ring); - } - } - - /* - * Now service the RSS ring if it's active. - */ - if (ql_read_sh_reg(rx_ring->prod_idx_sh_reg) != - rx_ring->cnsmr_idx) { - netif_printk(qdev, intr, KERN_DEBUG, qdev->ndev, - "%s: Servicing RX completion ring %d.\n", - __func__, rx_ring->cq_id); - work_done = ql_clean_inbound_rx_ring(rx_ring, budget); - } - - if (work_done < budget) { - napi_complete_done(napi, work_done); - ql_enable_completion_interrupt(qdev, rx_ring->irq); - } - return work_done; -} - -static void qlge_vlan_mode(struct net_device *ndev, netdev_features_t features) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - - if (features & NETIF_F_HW_VLAN_CTAG_RX) { - ql_write32(qdev, NIC_RCV_CFG, NIC_RCV_CFG_VLAN_MASK | - NIC_RCV_CFG_VLAN_MATCH_AND_NON); - } else { - ql_write32(qdev, NIC_RCV_CFG, NIC_RCV_CFG_VLAN_MASK); - } -} - -/** - * qlge_update_hw_vlan_features - helper routine to reinitialize the adapter - * based on the features to enable/disable hardware vlan accel - */ -static int qlge_update_hw_vlan_features(struct net_device *ndev, - netdev_features_t features) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - int status = 0; - bool need_restart = netif_running(ndev); - - if (need_restart) { - status = ql_adapter_down(qdev); - if (status) { - netif_err(qdev, link, qdev->ndev, - "Failed to bring down the adapter\n"); - return status; - } - } - - /* update the features with resent change */ - ndev->features = features; - - if (need_restart) { - status = ql_adapter_up(qdev); - if (status) { - netif_err(qdev, link, qdev->ndev, - "Failed to bring up the adapter\n"); - return status; - } - } - - return status; -} - -static int qlge_set_features(struct net_device *ndev, - netdev_features_t features) -{ - netdev_features_t changed = ndev->features ^ features; - int err; - - if (changed & NETIF_F_HW_VLAN_CTAG_RX) { - /* Update the behavior of vlan accel in the adapter */ - err = qlge_update_hw_vlan_features(ndev, features); - if (err) - return err; - - qlge_vlan_mode(ndev, features); - } - - return 0; -} - -static int __qlge_vlan_rx_add_vid(struct ql_adapter *qdev, u16 vid) -{ - u32 enable_bit = MAC_ADDR_E; - int err; - - err = ql_set_mac_addr_reg(qdev, (u8 *) &enable_bit, - MAC_ADDR_TYPE_VLAN, vid); - if (err) - netif_err(qdev, ifup, qdev->ndev, - "Failed to init vlan address.\n"); - return err; -} - -static int qlge_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - int status; - int err; - - status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK); - if (status) - return status; - - err = __qlge_vlan_rx_add_vid(qdev, vid); - set_bit(vid, qdev->active_vlans); - - ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK); - - return err; -} - -static int __qlge_vlan_rx_kill_vid(struct ql_adapter *qdev, u16 vid) -{ - u32 enable_bit = 0; - int err; - - err = ql_set_mac_addr_reg(qdev, (u8 *) &enable_bit, - MAC_ADDR_TYPE_VLAN, vid); - if (err) - netif_err(qdev, ifup, qdev->ndev, - "Failed to clear vlan address.\n"); - return err; -} - -static int qlge_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - int status; - int err; - - status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK); - if (status) - return status; - - err = __qlge_vlan_rx_kill_vid(qdev, vid); - clear_bit(vid, qdev->active_vlans); - - ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK); - - return err; -} - -static void qlge_restore_vlan(struct ql_adapter *qdev) -{ - int status; - u16 vid; - - status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK); - if (status) - return; - - for_each_set_bit(vid, qdev->active_vlans, VLAN_N_VID) - __qlge_vlan_rx_add_vid(qdev, vid); - - ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK); -} - -/* MSI-X Multiple Vector Interrupt Handler for inbound completions. */ -static irqreturn_t qlge_msix_rx_isr(int irq, void *dev_id) -{ - struct rx_ring *rx_ring = dev_id; - napi_schedule(&rx_ring->napi); - return IRQ_HANDLED; -} - -/* This handles a fatal error, MPI activity, and the default - * rx_ring in an MSI-X multiple vector environment. - * In MSI/Legacy environment it also process the rest of - * the rx_rings. - */ -static irqreturn_t qlge_isr(int irq, void *dev_id) -{ - struct rx_ring *rx_ring = dev_id; - struct ql_adapter *qdev = rx_ring->qdev; - struct intr_context *intr_context = &qdev->intr_context[0]; - u32 var; - int work_done = 0; - - spin_lock(&qdev->hw_lock); - if (atomic_read(&qdev->intr_context[0].irq_cnt)) { - netif_printk(qdev, intr, KERN_DEBUG, qdev->ndev, - "Shared Interrupt, Not ours!\n"); - spin_unlock(&qdev->hw_lock); - return IRQ_NONE; - } - spin_unlock(&qdev->hw_lock); - - var = ql_disable_completion_interrupt(qdev, intr_context->intr); - - /* - * Check for fatal error. - */ - if (var & STS_FE) { - ql_queue_asic_error(qdev); - netdev_err(qdev->ndev, "Got fatal error, STS = %x.\n", var); - var = ql_read32(qdev, ERR_STS); - netdev_err(qdev->ndev, "Resetting chip. " - "Error Status Register = 0x%x\n", var); - return IRQ_HANDLED; - } - - /* - * Check MPI processor activity. - */ - if ((var & STS_PI) && - (ql_read32(qdev, INTR_MASK) & INTR_MASK_PI)) { - /* - * We've got an async event or mailbox completion. - * Handle it and clear the source of the interrupt. - */ - netif_err(qdev, intr, qdev->ndev, - "Got MPI processor interrupt.\n"); - ql_disable_completion_interrupt(qdev, intr_context->intr); - ql_write32(qdev, INTR_MASK, (INTR_MASK_PI << 16)); - queue_delayed_work_on(smp_processor_id(), - qdev->workqueue, &qdev->mpi_work, 0); - work_done++; - } - - /* - * Get the bit-mask that shows the active queues for this - * pass. Compare it to the queues that this irq services - * and call napi if there's a match. - */ - var = ql_read32(qdev, ISR1); - if (var & intr_context->irq_mask) { - netif_info(qdev, intr, qdev->ndev, - "Waking handler for rx_ring[0].\n"); - ql_disable_completion_interrupt(qdev, intr_context->intr); - napi_schedule(&rx_ring->napi); - work_done++; - } - ql_enable_completion_interrupt(qdev, intr_context->intr); - return work_done ? IRQ_HANDLED : IRQ_NONE; -} - -static int ql_tso(struct sk_buff *skb, struct ob_mac_tso_iocb_req *mac_iocb_ptr) -{ - - if (skb_is_gso(skb)) { - int err; - __be16 l3_proto = vlan_get_protocol(skb); - - err = skb_cow_head(skb, 0); - if (err < 0) - return err; - - mac_iocb_ptr->opcode = OPCODE_OB_MAC_TSO_IOCB; - mac_iocb_ptr->flags3 |= OB_MAC_TSO_IOCB_IC; - mac_iocb_ptr->frame_len = cpu_to_le32((u32) skb->len); - mac_iocb_ptr->total_hdrs_len = - cpu_to_le16(skb_transport_offset(skb) + tcp_hdrlen(skb)); - mac_iocb_ptr->net_trans_offset = - cpu_to_le16(skb_network_offset(skb) | - skb_transport_offset(skb) - << OB_MAC_TRANSPORT_HDR_SHIFT); - mac_iocb_ptr->mss = cpu_to_le16(skb_shinfo(skb)->gso_size); - mac_iocb_ptr->flags2 |= OB_MAC_TSO_IOCB_LSO; - if (likely(l3_proto == htons(ETH_P_IP))) { - struct iphdr *iph = ip_hdr(skb); - iph->check = 0; - mac_iocb_ptr->flags1 |= OB_MAC_TSO_IOCB_IP4; - tcp_hdr(skb)->check = ~csum_tcpudp_magic(iph->saddr, - iph->daddr, 0, - IPPROTO_TCP, - 0); - } else if (l3_proto == htons(ETH_P_IPV6)) { - mac_iocb_ptr->flags1 |= OB_MAC_TSO_IOCB_IP6; - tcp_hdr(skb)->check = - ~csum_ipv6_magic(&ipv6_hdr(skb)->saddr, - &ipv6_hdr(skb)->daddr, - 0, IPPROTO_TCP, 0); - } - return 1; - } - return 0; -} - -static void ql_hw_csum_setup(struct sk_buff *skb, - struct ob_mac_tso_iocb_req *mac_iocb_ptr) -{ - int len; - struct iphdr *iph = ip_hdr(skb); - __sum16 *check; - mac_iocb_ptr->opcode = OPCODE_OB_MAC_TSO_IOCB; - mac_iocb_ptr->frame_len = cpu_to_le32((u32) skb->len); - mac_iocb_ptr->net_trans_offset = - cpu_to_le16(skb_network_offset(skb) | - skb_transport_offset(skb) << OB_MAC_TRANSPORT_HDR_SHIFT); - - mac_iocb_ptr->flags1 |= OB_MAC_TSO_IOCB_IP4; - len = (ntohs(iph->tot_len) - (iph->ihl << 2)); - if (likely(iph->protocol == IPPROTO_TCP)) { - check = &(tcp_hdr(skb)->check); - mac_iocb_ptr->flags2 |= OB_MAC_TSO_IOCB_TC; - mac_iocb_ptr->total_hdrs_len = - cpu_to_le16(skb_transport_offset(skb) + - (tcp_hdr(skb)->doff << 2)); - } else { - check = &(udp_hdr(skb)->check); - mac_iocb_ptr->flags2 |= OB_MAC_TSO_IOCB_UC; - mac_iocb_ptr->total_hdrs_len = - cpu_to_le16(skb_transport_offset(skb) + - sizeof(struct udphdr)); - } - *check = ~csum_tcpudp_magic(iph->saddr, - iph->daddr, len, iph->protocol, 0); -} - -static netdev_tx_t qlge_send(struct sk_buff *skb, struct net_device *ndev) -{ - struct tx_ring_desc *tx_ring_desc; - struct ob_mac_iocb_req *mac_iocb_ptr; - struct ql_adapter *qdev = netdev_priv(ndev); - int tso; - struct tx_ring *tx_ring; - u32 tx_ring_idx = (u32) skb->queue_mapping; - - tx_ring = &qdev->tx_ring[tx_ring_idx]; - - if (skb_padto(skb, ETH_ZLEN)) - return NETDEV_TX_OK; - - if (unlikely(atomic_read(&tx_ring->tx_count) < 2)) { - netif_info(qdev, tx_queued, qdev->ndev, - "%s: BUG! shutting down tx queue %d due to lack of resources.\n", - __func__, tx_ring_idx); - netif_stop_subqueue(ndev, tx_ring->wq_id); - tx_ring->tx_errors++; - return NETDEV_TX_BUSY; - } - tx_ring_desc = &tx_ring->q[tx_ring->prod_idx]; - mac_iocb_ptr = tx_ring_desc->queue_entry; - memset((void *)mac_iocb_ptr, 0, sizeof(*mac_iocb_ptr)); - - mac_iocb_ptr->opcode = OPCODE_OB_MAC_IOCB; - mac_iocb_ptr->tid = tx_ring_desc->index; - /* We use the upper 32-bits to store the tx queue for this IO. - * When we get the completion we can use it to establish the context. - */ - mac_iocb_ptr->txq_idx = tx_ring_idx; - tx_ring_desc->skb = skb; - - mac_iocb_ptr->frame_len = cpu_to_le16((u16) skb->len); - - if (skb_vlan_tag_present(skb)) { - netif_printk(qdev, tx_queued, KERN_DEBUG, qdev->ndev, - "Adding a vlan tag %d.\n", skb_vlan_tag_get(skb)); - mac_iocb_ptr->flags3 |= OB_MAC_IOCB_V; - mac_iocb_ptr->vlan_tci = cpu_to_le16(skb_vlan_tag_get(skb)); - } - tso = ql_tso(skb, (struct ob_mac_tso_iocb_req *)mac_iocb_ptr); - if (tso < 0) { - dev_kfree_skb_any(skb); - return NETDEV_TX_OK; - } else if (unlikely(!tso) && (skb->ip_summed == CHECKSUM_PARTIAL)) { - ql_hw_csum_setup(skb, - (struct ob_mac_tso_iocb_req *)mac_iocb_ptr); - } - if (ql_map_send(qdev, mac_iocb_ptr, skb, tx_ring_desc) != - NETDEV_TX_OK) { - netif_err(qdev, tx_queued, qdev->ndev, - "Could not map the segments.\n"); - tx_ring->tx_errors++; - return NETDEV_TX_BUSY; - } - QL_DUMP_OB_MAC_IOCB(mac_iocb_ptr); - tx_ring->prod_idx++; - if (tx_ring->prod_idx == tx_ring->wq_len) - tx_ring->prod_idx = 0; - wmb(); - - ql_write_db_reg_relaxed(tx_ring->prod_idx, tx_ring->prod_idx_db_reg); - netif_printk(qdev, tx_queued, KERN_DEBUG, qdev->ndev, - "tx queued, slot %d, len %d\n", - tx_ring->prod_idx, skb->len); - - atomic_dec(&tx_ring->tx_count); - - if (unlikely(atomic_read(&tx_ring->tx_count) < 2)) { - netif_stop_subqueue(ndev, tx_ring->wq_id); - if ((atomic_read(&tx_ring->tx_count) > (tx_ring->wq_len / 4))) - /* - * The queue got stopped because the tx_ring was full. - * Wake it up, because it's now at least 25% empty. - */ - netif_wake_subqueue(qdev->ndev, tx_ring->wq_id); - } - return NETDEV_TX_OK; -} - - -static void ql_free_shadow_space(struct ql_adapter *qdev) -{ - if (qdev->rx_ring_shadow_reg_area) { - pci_free_consistent(qdev->pdev, - PAGE_SIZE, - qdev->rx_ring_shadow_reg_area, - qdev->rx_ring_shadow_reg_dma); - qdev->rx_ring_shadow_reg_area = NULL; - } - if (qdev->tx_ring_shadow_reg_area) { - pci_free_consistent(qdev->pdev, - PAGE_SIZE, - qdev->tx_ring_shadow_reg_area, - qdev->tx_ring_shadow_reg_dma); - qdev->tx_ring_shadow_reg_area = NULL; - } -} - -static int ql_alloc_shadow_space(struct ql_adapter *qdev) -{ - qdev->rx_ring_shadow_reg_area = - pci_zalloc_consistent(qdev->pdev, PAGE_SIZE, - &qdev->rx_ring_shadow_reg_dma); - if (qdev->rx_ring_shadow_reg_area == NULL) { - netif_err(qdev, ifup, qdev->ndev, - "Allocation of RX shadow space failed.\n"); - return -ENOMEM; - } - - qdev->tx_ring_shadow_reg_area = - pci_zalloc_consistent(qdev->pdev, PAGE_SIZE, - &qdev->tx_ring_shadow_reg_dma); - if (qdev->tx_ring_shadow_reg_area == NULL) { - netif_err(qdev, ifup, qdev->ndev, - "Allocation of TX shadow space failed.\n"); - goto err_wqp_sh_area; - } - return 0; - -err_wqp_sh_area: - pci_free_consistent(qdev->pdev, - PAGE_SIZE, - qdev->rx_ring_shadow_reg_area, - qdev->rx_ring_shadow_reg_dma); - return -ENOMEM; -} - -static void ql_init_tx_ring(struct ql_adapter *qdev, struct tx_ring *tx_ring) -{ - struct tx_ring_desc *tx_ring_desc; - int i; - struct ob_mac_iocb_req *mac_iocb_ptr; - - mac_iocb_ptr = tx_ring->wq_base; - tx_ring_desc = tx_ring->q; - for (i = 0; i < tx_ring->wq_len; i++) { - tx_ring_desc->index = i; - tx_ring_desc->skb = NULL; - tx_ring_desc->queue_entry = mac_iocb_ptr; - mac_iocb_ptr++; - tx_ring_desc++; - } - atomic_set(&tx_ring->tx_count, tx_ring->wq_len); -} - -static void ql_free_tx_resources(struct ql_adapter *qdev, - struct tx_ring *tx_ring) -{ - if (tx_ring->wq_base) { - pci_free_consistent(qdev->pdev, tx_ring->wq_size, - tx_ring->wq_base, tx_ring->wq_base_dma); - tx_ring->wq_base = NULL; - } - kfree(tx_ring->q); - tx_ring->q = NULL; -} - -static int ql_alloc_tx_resources(struct ql_adapter *qdev, - struct tx_ring *tx_ring) -{ - tx_ring->wq_base = - pci_alloc_consistent(qdev->pdev, tx_ring->wq_size, - &tx_ring->wq_base_dma); - - if ((tx_ring->wq_base == NULL) || - tx_ring->wq_base_dma & WQ_ADDR_ALIGN) - goto pci_alloc_err; - - tx_ring->q = - kmalloc_array(tx_ring->wq_len, sizeof(struct tx_ring_desc), - GFP_KERNEL); - if (tx_ring->q == NULL) - goto err; - - return 0; -err: - pci_free_consistent(qdev->pdev, tx_ring->wq_size, - tx_ring->wq_base, tx_ring->wq_base_dma); - tx_ring->wq_base = NULL; -pci_alloc_err: - netif_err(qdev, ifup, qdev->ndev, "tx_ring alloc failed.\n"); - return -ENOMEM; -} - -static void ql_free_lbq_buffers(struct ql_adapter *qdev, struct rx_ring *rx_ring) -{ - struct bq_desc *lbq_desc; - - uint32_t curr_idx, clean_idx; - - curr_idx = rx_ring->lbq_curr_idx; - clean_idx = rx_ring->lbq_clean_idx; - while (curr_idx != clean_idx) { - lbq_desc = &rx_ring->lbq[curr_idx]; - - if (lbq_desc->p.pg_chunk.last_flag) { - pci_unmap_page(qdev->pdev, - lbq_desc->p.pg_chunk.map, - ql_lbq_block_size(qdev), - PCI_DMA_FROMDEVICE); - lbq_desc->p.pg_chunk.last_flag = 0; - } - - put_page(lbq_desc->p.pg_chunk.page); - lbq_desc->p.pg_chunk.page = NULL; - - if (++curr_idx == rx_ring->lbq_len) - curr_idx = 0; - - } - if (rx_ring->pg_chunk.page) { - pci_unmap_page(qdev->pdev, rx_ring->pg_chunk.map, - ql_lbq_block_size(qdev), PCI_DMA_FROMDEVICE); - put_page(rx_ring->pg_chunk.page); - rx_ring->pg_chunk.page = NULL; - } -} - -static void ql_free_sbq_buffers(struct ql_adapter *qdev, struct rx_ring *rx_ring) -{ - int i; - struct bq_desc *sbq_desc; - - for (i = 0; i < rx_ring->sbq_len; i++) { - sbq_desc = &rx_ring->sbq[i]; - if (sbq_desc == NULL) { - netif_err(qdev, ifup, qdev->ndev, - "sbq_desc %d is NULL.\n", i); - return; - } - if (sbq_desc->p.skb) { - pci_unmap_single(qdev->pdev, - dma_unmap_addr(sbq_desc, mapaddr), - dma_unmap_len(sbq_desc, maplen), - PCI_DMA_FROMDEVICE); - dev_kfree_skb(sbq_desc->p.skb); - sbq_desc->p.skb = NULL; - } - } -} - -/* Free all large and small rx buffers associated - * with the completion queues for this device. - */ -static void ql_free_rx_buffers(struct ql_adapter *qdev) -{ - int i; - struct rx_ring *rx_ring; - - for (i = 0; i < qdev->rx_ring_count; i++) { - rx_ring = &qdev->rx_ring[i]; - if (rx_ring->lbq) - ql_free_lbq_buffers(qdev, rx_ring); - if (rx_ring->sbq) - ql_free_sbq_buffers(qdev, rx_ring); - } -} - -static void ql_alloc_rx_buffers(struct ql_adapter *qdev) -{ - struct rx_ring *rx_ring; - int i; - - for (i = 0; i < qdev->rx_ring_count; i++) { - rx_ring = &qdev->rx_ring[i]; - if (rx_ring->type != TX_Q) - ql_update_buffer_queues(qdev, rx_ring); - } -} - -static void ql_init_lbq_ring(struct ql_adapter *qdev, - struct rx_ring *rx_ring) -{ - int i; - struct bq_desc *lbq_desc; - __le64 *bq = rx_ring->lbq_base; - - memset(rx_ring->lbq, 0, rx_ring->lbq_len * sizeof(struct bq_desc)); - for (i = 0; i < rx_ring->lbq_len; i++) { - lbq_desc = &rx_ring->lbq[i]; - memset(lbq_desc, 0, sizeof(*lbq_desc)); - lbq_desc->index = i; - lbq_desc->addr = bq; - bq++; - } -} - -static void ql_init_sbq_ring(struct ql_adapter *qdev, - struct rx_ring *rx_ring) -{ - int i; - struct bq_desc *sbq_desc; - __le64 *bq = rx_ring->sbq_base; - - memset(rx_ring->sbq, 0, rx_ring->sbq_len * sizeof(struct bq_desc)); - for (i = 0; i < rx_ring->sbq_len; i++) { - sbq_desc = &rx_ring->sbq[i]; - memset(sbq_desc, 0, sizeof(*sbq_desc)); - sbq_desc->index = i; - sbq_desc->addr = bq; - bq++; - } -} - -static void ql_free_rx_resources(struct ql_adapter *qdev, - struct rx_ring *rx_ring) -{ - /* Free the small buffer queue. */ - if (rx_ring->sbq_base) { - pci_free_consistent(qdev->pdev, - rx_ring->sbq_size, - rx_ring->sbq_base, rx_ring->sbq_base_dma); - rx_ring->sbq_base = NULL; - } - - /* Free the small buffer queue control blocks. */ - kfree(rx_ring->sbq); - rx_ring->sbq = NULL; - - /* Free the large buffer queue. */ - if (rx_ring->lbq_base) { - pci_free_consistent(qdev->pdev, - rx_ring->lbq_size, - rx_ring->lbq_base, rx_ring->lbq_base_dma); - rx_ring->lbq_base = NULL; - } - - /* Free the large buffer queue control blocks. */ - kfree(rx_ring->lbq); - rx_ring->lbq = NULL; - - /* Free the rx queue. */ - if (rx_ring->cq_base) { - pci_free_consistent(qdev->pdev, - rx_ring->cq_size, - rx_ring->cq_base, rx_ring->cq_base_dma); - rx_ring->cq_base = NULL; - } -} - -/* Allocate queues and buffers for this completions queue based - * on the values in the parameter structure. */ -static int ql_alloc_rx_resources(struct ql_adapter *qdev, - struct rx_ring *rx_ring) -{ - - /* - * Allocate the completion queue for this rx_ring. - */ - rx_ring->cq_base = - pci_alloc_consistent(qdev->pdev, rx_ring->cq_size, - &rx_ring->cq_base_dma); - - if (rx_ring->cq_base == NULL) { - netif_err(qdev, ifup, qdev->ndev, "rx_ring alloc failed.\n"); - return -ENOMEM; - } - - if (rx_ring->sbq_len) { - /* - * Allocate small buffer queue. - */ - rx_ring->sbq_base = - pci_alloc_consistent(qdev->pdev, rx_ring->sbq_size, - &rx_ring->sbq_base_dma); - - if (rx_ring->sbq_base == NULL) { - netif_err(qdev, ifup, qdev->ndev, - "Small buffer queue allocation failed.\n"); - goto err_mem; - } - - /* - * Allocate small buffer queue control blocks. - */ - rx_ring->sbq = kmalloc_array(rx_ring->sbq_len, - sizeof(struct bq_desc), - GFP_KERNEL); - if (rx_ring->sbq == NULL) - goto err_mem; - - ql_init_sbq_ring(qdev, rx_ring); - } - - if (rx_ring->lbq_len) { - /* - * Allocate large buffer queue. - */ - rx_ring->lbq_base = - pci_alloc_consistent(qdev->pdev, rx_ring->lbq_size, - &rx_ring->lbq_base_dma); - - if (rx_ring->lbq_base == NULL) { - netif_err(qdev, ifup, qdev->ndev, - "Large buffer queue allocation failed.\n"); - goto err_mem; - } - /* - * Allocate large buffer queue control blocks. - */ - rx_ring->lbq = kmalloc_array(rx_ring->lbq_len, - sizeof(struct bq_desc), - GFP_KERNEL); - if (rx_ring->lbq == NULL) - goto err_mem; - - ql_init_lbq_ring(qdev, rx_ring); - } - - return 0; - -err_mem: - ql_free_rx_resources(qdev, rx_ring); - return -ENOMEM; -} - -static void ql_tx_ring_clean(struct ql_adapter *qdev) -{ - struct tx_ring *tx_ring; - struct tx_ring_desc *tx_ring_desc; - int i, j; - - /* - * Loop through all queues and free - * any resources. - */ - for (j = 0; j < qdev->tx_ring_count; j++) { - tx_ring = &qdev->tx_ring[j]; - for (i = 0; i < tx_ring->wq_len; i++) { - tx_ring_desc = &tx_ring->q[i]; - if (tx_ring_desc && tx_ring_desc->skb) { - netif_err(qdev, ifdown, qdev->ndev, - "Freeing lost SKB %p, from queue %d, index %d.\n", - tx_ring_desc->skb, j, - tx_ring_desc->index); - ql_unmap_send(qdev, tx_ring_desc, - tx_ring_desc->map_cnt); - dev_kfree_skb(tx_ring_desc->skb); - tx_ring_desc->skb = NULL; - } - } - } -} - -static void ql_free_mem_resources(struct ql_adapter *qdev) -{ - int i; - - for (i = 0; i < qdev->tx_ring_count; i++) - ql_free_tx_resources(qdev, &qdev->tx_ring[i]); - for (i = 0; i < qdev->rx_ring_count; i++) - ql_free_rx_resources(qdev, &qdev->rx_ring[i]); - ql_free_shadow_space(qdev); -} - -static int ql_alloc_mem_resources(struct ql_adapter *qdev) -{ - int i; - - /* Allocate space for our shadow registers and such. */ - if (ql_alloc_shadow_space(qdev)) - return -ENOMEM; - - for (i = 0; i < qdev->rx_ring_count; i++) { - if (ql_alloc_rx_resources(qdev, &qdev->rx_ring[i]) != 0) { - netif_err(qdev, ifup, qdev->ndev, - "RX resource allocation failed.\n"); - goto err_mem; - } - } - /* Allocate tx queue resources */ - for (i = 0; i < qdev->tx_ring_count; i++) { - if (ql_alloc_tx_resources(qdev, &qdev->tx_ring[i]) != 0) { - netif_err(qdev, ifup, qdev->ndev, - "TX resource allocation failed.\n"); - goto err_mem; - } - } - return 0; - -err_mem: - ql_free_mem_resources(qdev); - return -ENOMEM; -} - -/* Set up the rx ring control block and pass it to the chip. - * The control block is defined as - * "Completion Queue Initialization Control Block", or cqicb. - */ -static int ql_start_rx_ring(struct ql_adapter *qdev, struct rx_ring *rx_ring) -{ - struct cqicb *cqicb = &rx_ring->cqicb; - void *shadow_reg = qdev->rx_ring_shadow_reg_area + - (rx_ring->cq_id * RX_RING_SHADOW_SPACE); - u64 shadow_reg_dma = qdev->rx_ring_shadow_reg_dma + - (rx_ring->cq_id * RX_RING_SHADOW_SPACE); - void __iomem *doorbell_area = - qdev->doorbell_area + (DB_PAGE_SIZE * (128 + rx_ring->cq_id)); - int err = 0; - u16 bq_len; - u64 tmp; - __le64 *base_indirect_ptr; - int page_entries; - - /* Set up the shadow registers for this ring. */ - rx_ring->prod_idx_sh_reg = shadow_reg; - rx_ring->prod_idx_sh_reg_dma = shadow_reg_dma; - *rx_ring->prod_idx_sh_reg = 0; - shadow_reg += sizeof(u64); - shadow_reg_dma += sizeof(u64); - rx_ring->lbq_base_indirect = shadow_reg; - rx_ring->lbq_base_indirect_dma = shadow_reg_dma; - shadow_reg += (sizeof(u64) * MAX_DB_PAGES_PER_BQ(rx_ring->lbq_len)); - shadow_reg_dma += (sizeof(u64) * MAX_DB_PAGES_PER_BQ(rx_ring->lbq_len)); - rx_ring->sbq_base_indirect = shadow_reg; - rx_ring->sbq_base_indirect_dma = shadow_reg_dma; - - /* PCI doorbell mem area + 0x00 for consumer index register */ - rx_ring->cnsmr_idx_db_reg = (u32 __iomem *) doorbell_area; - rx_ring->cnsmr_idx = 0; - rx_ring->curr_entry = rx_ring->cq_base; - - /* PCI doorbell mem area + 0x04 for valid register */ - rx_ring->valid_db_reg = doorbell_area + 0x04; - - /* PCI doorbell mem area + 0x18 for large buffer consumer */ - rx_ring->lbq_prod_idx_db_reg = (u32 __iomem *) (doorbell_area + 0x18); - - /* PCI doorbell mem area + 0x1c */ - rx_ring->sbq_prod_idx_db_reg = (u32 __iomem *) (doorbell_area + 0x1c); - - memset((void *)cqicb, 0, sizeof(struct cqicb)); - cqicb->msix_vect = rx_ring->irq; - - bq_len = (rx_ring->cq_len == 65536) ? 0 : (u16) rx_ring->cq_len; - cqicb->len = cpu_to_le16(bq_len | LEN_V | LEN_CPP_CONT); - - cqicb->addr = cpu_to_le64(rx_ring->cq_base_dma); - - cqicb->prod_idx_addr = cpu_to_le64(rx_ring->prod_idx_sh_reg_dma); - - /* - * Set up the control block load flags. - */ - cqicb->flags = FLAGS_LC | /* Load queue base address */ - FLAGS_LV | /* Load MSI-X vector */ - FLAGS_LI; /* Load irq delay values */ - if (rx_ring->lbq_len) { - cqicb->flags |= FLAGS_LL; /* Load lbq values */ - tmp = (u64)rx_ring->lbq_base_dma; - base_indirect_ptr = rx_ring->lbq_base_indirect; - page_entries = 0; - do { - *base_indirect_ptr = cpu_to_le64(tmp); - tmp += DB_PAGE_SIZE; - base_indirect_ptr++; - page_entries++; - } while (page_entries < MAX_DB_PAGES_PER_BQ(rx_ring->lbq_len)); - cqicb->lbq_addr = - cpu_to_le64(rx_ring->lbq_base_indirect_dma); - bq_len = (rx_ring->lbq_buf_size == 65536) ? 0 : - (u16) rx_ring->lbq_buf_size; - cqicb->lbq_buf_size = cpu_to_le16(bq_len); - bq_len = (rx_ring->lbq_len == 65536) ? 0 : - (u16) rx_ring->lbq_len; - cqicb->lbq_len = cpu_to_le16(bq_len); - rx_ring->lbq_prod_idx = 0; - rx_ring->lbq_curr_idx = 0; - rx_ring->lbq_clean_idx = 0; - rx_ring->lbq_free_cnt = rx_ring->lbq_len; - } - if (rx_ring->sbq_len) { - cqicb->flags |= FLAGS_LS; /* Load sbq values */ - tmp = (u64)rx_ring->sbq_base_dma; - base_indirect_ptr = rx_ring->sbq_base_indirect; - page_entries = 0; - do { - *base_indirect_ptr = cpu_to_le64(tmp); - tmp += DB_PAGE_SIZE; - base_indirect_ptr++; - page_entries++; - } while (page_entries < MAX_DB_PAGES_PER_BQ(rx_ring->sbq_len)); - cqicb->sbq_addr = - cpu_to_le64(rx_ring->sbq_base_indirect_dma); - cqicb->sbq_buf_size = - cpu_to_le16((u16)(rx_ring->sbq_buf_size)); - bq_len = (rx_ring->sbq_len == 65536) ? 0 : - (u16) rx_ring->sbq_len; - cqicb->sbq_len = cpu_to_le16(bq_len); - rx_ring->sbq_prod_idx = 0; - rx_ring->sbq_curr_idx = 0; - rx_ring->sbq_clean_idx = 0; - rx_ring->sbq_free_cnt = rx_ring->sbq_len; - } - switch (rx_ring->type) { - case TX_Q: - cqicb->irq_delay = cpu_to_le16(qdev->tx_coalesce_usecs); - cqicb->pkt_delay = cpu_to_le16(qdev->tx_max_coalesced_frames); - break; - case RX_Q: - /* Inbound completion handling rx_rings run in - * separate NAPI contexts. - */ - netif_napi_add(qdev->ndev, &rx_ring->napi, ql_napi_poll_msix, - 64); - cqicb->irq_delay = cpu_to_le16(qdev->rx_coalesce_usecs); - cqicb->pkt_delay = cpu_to_le16(qdev->rx_max_coalesced_frames); - break; - default: - netif_printk(qdev, ifup, KERN_DEBUG, qdev->ndev, - "Invalid rx_ring->type = %d.\n", rx_ring->type); - } - err = ql_write_cfg(qdev, cqicb, sizeof(struct cqicb), - CFG_LCQ, rx_ring->cq_id); - if (err) { - netif_err(qdev, ifup, qdev->ndev, "Failed to load CQICB.\n"); - return err; - } - return err; -} - -static int ql_start_tx_ring(struct ql_adapter *qdev, struct tx_ring *tx_ring) -{ - struct wqicb *wqicb = (struct wqicb *)tx_ring; - void __iomem *doorbell_area = - qdev->doorbell_area + (DB_PAGE_SIZE * tx_ring->wq_id); - void *shadow_reg = qdev->tx_ring_shadow_reg_area + - (tx_ring->wq_id * sizeof(u64)); - u64 shadow_reg_dma = qdev->tx_ring_shadow_reg_dma + - (tx_ring->wq_id * sizeof(u64)); - int err = 0; - - /* - * Assign doorbell registers for this tx_ring. - */ - /* TX PCI doorbell mem area for tx producer index */ - tx_ring->prod_idx_db_reg = (u32 __iomem *) doorbell_area; - tx_ring->prod_idx = 0; - /* TX PCI doorbell mem area + 0x04 */ - tx_ring->valid_db_reg = doorbell_area + 0x04; - - /* - * Assign shadow registers for this tx_ring. - */ - tx_ring->cnsmr_idx_sh_reg = shadow_reg; - tx_ring->cnsmr_idx_sh_reg_dma = shadow_reg_dma; - - wqicb->len = cpu_to_le16(tx_ring->wq_len | Q_LEN_V | Q_LEN_CPP_CONT); - wqicb->flags = cpu_to_le16(Q_FLAGS_LC | - Q_FLAGS_LB | Q_FLAGS_LI | Q_FLAGS_LO); - wqicb->cq_id_rss = cpu_to_le16(tx_ring->cq_id); - wqicb->rid = 0; - wqicb->addr = cpu_to_le64(tx_ring->wq_base_dma); - - wqicb->cnsmr_idx_addr = cpu_to_le64(tx_ring->cnsmr_idx_sh_reg_dma); - - ql_init_tx_ring(qdev, tx_ring); - - err = ql_write_cfg(qdev, wqicb, sizeof(*wqicb), CFG_LRQ, - (u16) tx_ring->wq_id); - if (err) { - netif_err(qdev, ifup, qdev->ndev, "Failed to load tx_ring.\n"); - return err; - } - return err; -} - -static void ql_disable_msix(struct ql_adapter *qdev) -{ - if (test_bit(QL_MSIX_ENABLED, &qdev->flags)) { - pci_disable_msix(qdev->pdev); - clear_bit(QL_MSIX_ENABLED, &qdev->flags); - kfree(qdev->msi_x_entry); - qdev->msi_x_entry = NULL; - } else if (test_bit(QL_MSI_ENABLED, &qdev->flags)) { - pci_disable_msi(qdev->pdev); - clear_bit(QL_MSI_ENABLED, &qdev->flags); - } -} - -/* We start by trying to get the number of vectors - * stored in qdev->intr_count. If we don't get that - * many then we reduce the count and try again. - */ -static void ql_enable_msix(struct ql_adapter *qdev) -{ - int i, err; - - /* Get the MSIX vectors. */ - if (qlge_irq_type == MSIX_IRQ) { - /* Try to alloc space for the msix struct, - * if it fails then go to MSI/legacy. - */ - qdev->msi_x_entry = kcalloc(qdev->intr_count, - sizeof(struct msix_entry), - GFP_KERNEL); - if (!qdev->msi_x_entry) { - qlge_irq_type = MSI_IRQ; - goto msi; - } - - for (i = 0; i < qdev->intr_count; i++) - qdev->msi_x_entry[i].entry = i; - - err = pci_enable_msix_range(qdev->pdev, qdev->msi_x_entry, - 1, qdev->intr_count); - if (err < 0) { - kfree(qdev->msi_x_entry); - qdev->msi_x_entry = NULL; - netif_warn(qdev, ifup, qdev->ndev, - "MSI-X Enable failed, trying MSI.\n"); - qlge_irq_type = MSI_IRQ; - } else { - qdev->intr_count = err; - set_bit(QL_MSIX_ENABLED, &qdev->flags); - netif_info(qdev, ifup, qdev->ndev, - "MSI-X Enabled, got %d vectors.\n", - qdev->intr_count); - return; - } - } -msi: - qdev->intr_count = 1; - if (qlge_irq_type == MSI_IRQ) { - if (!pci_enable_msi(qdev->pdev)) { - set_bit(QL_MSI_ENABLED, &qdev->flags); - netif_info(qdev, ifup, qdev->ndev, - "Running with MSI interrupts.\n"); - return; - } - } - qlge_irq_type = LEG_IRQ; - netif_printk(qdev, ifup, KERN_DEBUG, qdev->ndev, - "Running with legacy interrupts.\n"); -} - -/* Each vector services 1 RSS ring and and 1 or more - * TX completion rings. This function loops through - * the TX completion rings and assigns the vector that - * will service it. An example would be if there are - * 2 vectors (so 2 RSS rings) and 8 TX completion rings. - * This would mean that vector 0 would service RSS ring 0 - * and TX completion rings 0,1,2 and 3. Vector 1 would - * service RSS ring 1 and TX completion rings 4,5,6 and 7. - */ -static void ql_set_tx_vect(struct ql_adapter *qdev) -{ - int i, j, vect; - u32 tx_rings_per_vector = qdev->tx_ring_count / qdev->intr_count; - - if (likely(test_bit(QL_MSIX_ENABLED, &qdev->flags))) { - /* Assign irq vectors to TX rx_rings.*/ - for (vect = 0, j = 0, i = qdev->rss_ring_count; - i < qdev->rx_ring_count; i++) { - if (j == tx_rings_per_vector) { - vect++; - j = 0; - } - qdev->rx_ring[i].irq = vect; - j++; - } - } else { - /* For single vector all rings have an irq - * of zero. - */ - for (i = 0; i < qdev->rx_ring_count; i++) - qdev->rx_ring[i].irq = 0; - } -} - -/* Set the interrupt mask for this vector. Each vector - * will service 1 RSS ring and 1 or more TX completion - * rings. This function sets up a bit mask per vector - * that indicates which rings it services. - */ -static void ql_set_irq_mask(struct ql_adapter *qdev, struct intr_context *ctx) -{ - int j, vect = ctx->intr; - u32 tx_rings_per_vector = qdev->tx_ring_count / qdev->intr_count; - - if (likely(test_bit(QL_MSIX_ENABLED, &qdev->flags))) { - /* Add the RSS ring serviced by this vector - * to the mask. - */ - ctx->irq_mask = (1 << qdev->rx_ring[vect].cq_id); - /* Add the TX ring(s) serviced by this vector - * to the mask. */ - for (j = 0; j < tx_rings_per_vector; j++) { - ctx->irq_mask |= - (1 << qdev->rx_ring[qdev->rss_ring_count + - (vect * tx_rings_per_vector) + j].cq_id); - } - } else { - /* For single vector we just shift each queue's - * ID into the mask. - */ - for (j = 0; j < qdev->rx_ring_count; j++) - ctx->irq_mask |= (1 << qdev->rx_ring[j].cq_id); - } -} - -/* - * Here we build the intr_context structures based on - * our rx_ring count and intr vector count. - * The intr_context structure is used to hook each vector - * to possibly different handlers. - */ -static void ql_resolve_queues_to_irqs(struct ql_adapter *qdev) -{ - int i = 0; - struct intr_context *intr_context = &qdev->intr_context[0]; - - if (likely(test_bit(QL_MSIX_ENABLED, &qdev->flags))) { - /* Each rx_ring has it's - * own intr_context since we have separate - * vectors for each queue. - */ - for (i = 0; i < qdev->intr_count; i++, intr_context++) { - qdev->rx_ring[i].irq = i; - intr_context->intr = i; - intr_context->qdev = qdev; - /* Set up this vector's bit-mask that indicates - * which queues it services. - */ - ql_set_irq_mask(qdev, intr_context); - /* - * We set up each vectors enable/disable/read bits so - * there's no bit/mask calculations in the critical path. - */ - intr_context->intr_en_mask = - INTR_EN_TYPE_MASK | INTR_EN_INTR_MASK | - INTR_EN_TYPE_ENABLE | INTR_EN_IHD_MASK | INTR_EN_IHD - | i; - intr_context->intr_dis_mask = - INTR_EN_TYPE_MASK | INTR_EN_INTR_MASK | - INTR_EN_TYPE_DISABLE | INTR_EN_IHD_MASK | - INTR_EN_IHD | i; - intr_context->intr_read_mask = - INTR_EN_TYPE_MASK | INTR_EN_INTR_MASK | - INTR_EN_TYPE_READ | INTR_EN_IHD_MASK | INTR_EN_IHD | - i; - if (i == 0) { - /* The first vector/queue handles - * broadcast/multicast, fatal errors, - * and firmware events. This in addition - * to normal inbound NAPI processing. - */ - intr_context->handler = qlge_isr; - sprintf(intr_context->name, "%s-rx-%d", - qdev->ndev->name, i); - } else { - /* - * Inbound queues handle unicast frames only. - */ - intr_context->handler = qlge_msix_rx_isr; - sprintf(intr_context->name, "%s-rx-%d", - qdev->ndev->name, i); - } - } - } else { - /* - * All rx_rings use the same intr_context since - * there is only one vector. - */ - intr_context->intr = 0; - intr_context->qdev = qdev; - /* - * We set up each vectors enable/disable/read bits so - * there's no bit/mask calculations in the critical path. - */ - intr_context->intr_en_mask = - INTR_EN_TYPE_MASK | INTR_EN_INTR_MASK | INTR_EN_TYPE_ENABLE; - intr_context->intr_dis_mask = - INTR_EN_TYPE_MASK | INTR_EN_INTR_MASK | - INTR_EN_TYPE_DISABLE; - intr_context->intr_read_mask = - INTR_EN_TYPE_MASK | INTR_EN_INTR_MASK | INTR_EN_TYPE_READ; - /* - * Single interrupt means one handler for all rings. - */ - intr_context->handler = qlge_isr; - sprintf(intr_context->name, "%s-single_irq", qdev->ndev->name); - /* Set up this vector's bit-mask that indicates - * which queues it services. In this case there is - * a single vector so it will service all RSS and - * TX completion rings. - */ - ql_set_irq_mask(qdev, intr_context); - } - /* Tell the TX completion rings which MSIx vector - * they will be using. - */ - ql_set_tx_vect(qdev); -} - -static void ql_free_irq(struct ql_adapter *qdev) -{ - int i; - struct intr_context *intr_context = &qdev->intr_context[0]; - - for (i = 0; i < qdev->intr_count; i++, intr_context++) { - if (intr_context->hooked) { - if (test_bit(QL_MSIX_ENABLED, &qdev->flags)) { - free_irq(qdev->msi_x_entry[i].vector, - &qdev->rx_ring[i]); - } else { - free_irq(qdev->pdev->irq, &qdev->rx_ring[0]); - } - } - } - ql_disable_msix(qdev); -} - -static int ql_request_irq(struct ql_adapter *qdev) -{ - int i; - int status = 0; - struct pci_dev *pdev = qdev->pdev; - struct intr_context *intr_context = &qdev->intr_context[0]; - - ql_resolve_queues_to_irqs(qdev); - - for (i = 0; i < qdev->intr_count; i++, intr_context++) { - atomic_set(&intr_context->irq_cnt, 0); - if (test_bit(QL_MSIX_ENABLED, &qdev->flags)) { - status = request_irq(qdev->msi_x_entry[i].vector, - intr_context->handler, - 0, - intr_context->name, - &qdev->rx_ring[i]); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed request for MSIX interrupt %d.\n", - i); - goto err_irq; - } - } else { - netif_printk(qdev, ifup, KERN_DEBUG, qdev->ndev, - "trying msi or legacy interrupts.\n"); - netif_printk(qdev, ifup, KERN_DEBUG, qdev->ndev, - "%s: irq = %d.\n", __func__, pdev->irq); - netif_printk(qdev, ifup, KERN_DEBUG, qdev->ndev, - "%s: context->name = %s.\n", __func__, - intr_context->name); - netif_printk(qdev, ifup, KERN_DEBUG, qdev->ndev, - "%s: dev_id = 0x%p.\n", __func__, - &qdev->rx_ring[0]); - status = - request_irq(pdev->irq, qlge_isr, - test_bit(QL_MSI_ENABLED, - &qdev-> - flags) ? 0 : IRQF_SHARED, - intr_context->name, &qdev->rx_ring[0]); - if (status) - goto err_irq; - - netif_err(qdev, ifup, qdev->ndev, - "Hooked intr %d, queue type %s, with name %s.\n", - i, - qdev->rx_ring[0].type == DEFAULT_Q ? - "DEFAULT_Q" : - qdev->rx_ring[0].type == TX_Q ? "TX_Q" : - qdev->rx_ring[0].type == RX_Q ? "RX_Q" : "", - intr_context->name); - } - intr_context->hooked = 1; - } - return status; -err_irq: - netif_err(qdev, ifup, qdev->ndev, "Failed to get the interrupts!!!\n"); - ql_free_irq(qdev); - return status; -} - -static int ql_start_rss(struct ql_adapter *qdev) -{ - static const u8 init_hash_seed[] = { - 0x6d, 0x5a, 0x56, 0xda, 0x25, 0x5b, 0x0e, 0xc2, - 0x41, 0x67, 0x25, 0x3d, 0x43, 0xa3, 0x8f, 0xb0, - 0xd0, 0xca, 0x2b, 0xcb, 0xae, 0x7b, 0x30, 0xb4, - 0x77, 0xcb, 0x2d, 0xa3, 0x80, 0x30, 0xf2, 0x0c, - 0x6a, 0x42, 0xb7, 0x3b, 0xbe, 0xac, 0x01, 0xfa - }; - struct ricb *ricb = &qdev->ricb; - int status = 0; - int i; - u8 *hash_id = (u8 *) ricb->hash_cq_id; - - memset((void *)ricb, 0, sizeof(*ricb)); - - ricb->base_cq = RSS_L4K; - ricb->flags = - (RSS_L6K | RSS_LI | RSS_LB | RSS_LM | RSS_RT4 | RSS_RT6); - ricb->mask = cpu_to_le16((u16)(0x3ff)); - - /* - * Fill out the Indirection Table. - */ - for (i = 0; i < 1024; i++) - hash_id[i] = (i & (qdev->rss_ring_count - 1)); - - memcpy((void *)&ricb->ipv6_hash_key[0], init_hash_seed, 40); - memcpy((void *)&ricb->ipv4_hash_key[0], init_hash_seed, 16); - - status = ql_write_cfg(qdev, ricb, sizeof(*ricb), CFG_LR, 0); - if (status) { - netif_err(qdev, ifup, qdev->ndev, "Failed to load RICB.\n"); - return status; - } - return status; -} - -static int ql_clear_routing_entries(struct ql_adapter *qdev) -{ - int i, status = 0; - - status = ql_sem_spinlock(qdev, SEM_RT_IDX_MASK); - if (status) - return status; - /* Clear all the entries in the routing table. */ - for (i = 0; i < 16; i++) { - status = ql_set_routing_reg(qdev, i, 0, 0); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed to init routing register for CAM packets.\n"); - break; - } - } - ql_sem_unlock(qdev, SEM_RT_IDX_MASK); - return status; -} - -/* Initialize the frame-to-queue routing. */ -static int ql_route_initialize(struct ql_adapter *qdev) -{ - int status = 0; - - /* Clear all the entries in the routing table. */ - status = ql_clear_routing_entries(qdev); - if (status) - return status; - - status = ql_sem_spinlock(qdev, SEM_RT_IDX_MASK); - if (status) - return status; - - status = ql_set_routing_reg(qdev, RT_IDX_IP_CSUM_ERR_SLOT, - RT_IDX_IP_CSUM_ERR, 1); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed to init routing register " - "for IP CSUM error packets.\n"); - goto exit; - } - status = ql_set_routing_reg(qdev, RT_IDX_TCP_UDP_CSUM_ERR_SLOT, - RT_IDX_TU_CSUM_ERR, 1); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed to init routing register " - "for TCP/UDP CSUM error packets.\n"); - goto exit; - } - status = ql_set_routing_reg(qdev, RT_IDX_BCAST_SLOT, RT_IDX_BCAST, 1); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed to init routing register for broadcast packets.\n"); - goto exit; - } - /* If we have more than one inbound queue, then turn on RSS in the - * routing block. - */ - if (qdev->rss_ring_count > 1) { - status = ql_set_routing_reg(qdev, RT_IDX_RSS_MATCH_SLOT, - RT_IDX_RSS_MATCH, 1); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed to init routing register for MATCH RSS packets.\n"); - goto exit; - } - } - - status = ql_set_routing_reg(qdev, RT_IDX_CAM_HIT_SLOT, - RT_IDX_CAM_HIT, 1); - if (status) - netif_err(qdev, ifup, qdev->ndev, - "Failed to init routing register for CAM packets.\n"); -exit: - ql_sem_unlock(qdev, SEM_RT_IDX_MASK); - return status; -} - -int ql_cam_route_initialize(struct ql_adapter *qdev) -{ - int status, set; - - /* If check if the link is up and use to - * determine if we are setting or clearing - * the MAC address in the CAM. - */ - set = ql_read32(qdev, STS); - set &= qdev->port_link_up; - status = ql_set_mac_addr(qdev, set); - if (status) { - netif_err(qdev, ifup, qdev->ndev, "Failed to init mac address.\n"); - return status; - } - - status = ql_route_initialize(qdev); - if (status) - netif_err(qdev, ifup, qdev->ndev, "Failed to init routing table.\n"); - - return status; -} - -static int ql_adapter_initialize(struct ql_adapter *qdev) -{ - u32 value, mask; - int i; - int status = 0; - - /* - * Set up the System register to halt on errors. - */ - value = SYS_EFE | SYS_FAE; - mask = value << 16; - ql_write32(qdev, SYS, mask | value); - - /* Set the default queue, and VLAN behavior. */ - value = NIC_RCV_CFG_DFQ; - mask = NIC_RCV_CFG_DFQ_MASK; - if (qdev->ndev->features & NETIF_F_HW_VLAN_CTAG_RX) { - value |= NIC_RCV_CFG_RV; - mask |= (NIC_RCV_CFG_RV << 16); - } - ql_write32(qdev, NIC_RCV_CFG, (mask | value)); - - /* Set the MPI interrupt to enabled. */ - ql_write32(qdev, INTR_MASK, (INTR_MASK_PI << 16) | INTR_MASK_PI); - - /* Enable the function, set pagesize, enable error checking. */ - value = FSC_FE | FSC_EPC_INBOUND | FSC_EPC_OUTBOUND | - FSC_EC | FSC_VM_PAGE_4K; - value |= SPLT_SETTING; - - /* Set/clear header splitting. */ - mask = FSC_VM_PAGESIZE_MASK | - FSC_DBL_MASK | FSC_DBRST_MASK | (value << 16); - ql_write32(qdev, FSC, mask | value); - - ql_write32(qdev, SPLT_HDR, SPLT_LEN); - - /* Set RX packet routing to use port/pci function on which the - * packet arrived on in addition to usual frame routing. - * This is helpful on bonding where both interfaces can have - * the same MAC address. - */ - ql_write32(qdev, RST_FO, RST_FO_RR_MASK | RST_FO_RR_RCV_FUNC_CQ); - /* Reroute all packets to our Interface. - * They may have been routed to MPI firmware - * due to WOL. - */ - value = ql_read32(qdev, MGMT_RCV_CFG); - value &= ~MGMT_RCV_CFG_RM; - mask = 0xffff0000; - - /* Sticky reg needs clearing due to WOL. */ - ql_write32(qdev, MGMT_RCV_CFG, mask); - ql_write32(qdev, MGMT_RCV_CFG, mask | value); - - /* Default WOL is enable on Mezz cards */ - if (qdev->pdev->subsystem_device == 0x0068 || - qdev->pdev->subsystem_device == 0x0180) - qdev->wol = WAKE_MAGIC; - - /* Start up the rx queues. */ - for (i = 0; i < qdev->rx_ring_count; i++) { - status = ql_start_rx_ring(qdev, &qdev->rx_ring[i]); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed to start rx ring[%d].\n", i); - return status; - } - } - - /* If there is more than one inbound completion queue - * then download a RICB to configure RSS. - */ - if (qdev->rss_ring_count > 1) { - status = ql_start_rss(qdev); - if (status) { - netif_err(qdev, ifup, qdev->ndev, "Failed to start RSS.\n"); - return status; - } - } - - /* Start up the tx queues. */ - for (i = 0; i < qdev->tx_ring_count; i++) { - status = ql_start_tx_ring(qdev, &qdev->tx_ring[i]); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed to start tx ring[%d].\n", i); - return status; - } - } - - /* Initialize the port and set the max framesize. */ - status = qdev->nic_ops->port_initialize(qdev); - if (status) - netif_err(qdev, ifup, qdev->ndev, "Failed to start port.\n"); - - /* Set up the MAC address and frame routing filter. */ - status = ql_cam_route_initialize(qdev); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed to init CAM/Routing tables.\n"); - return status; - } - - /* Start NAPI for the RSS queues. */ - for (i = 0; i < qdev->rss_ring_count; i++) - napi_enable(&qdev->rx_ring[i].napi); - - return status; -} - -/* Issue soft reset to chip. */ -static int ql_adapter_reset(struct ql_adapter *qdev) -{ - u32 value; - int status = 0; - unsigned long end_jiffies; - - /* Clear all the entries in the routing table. */ - status = ql_clear_routing_entries(qdev); - if (status) { - netif_err(qdev, ifup, qdev->ndev, "Failed to clear routing bits.\n"); - return status; - } - - /* Check if bit is set then skip the mailbox command and - * clear the bit, else we are in normal reset process. - */ - if (!test_bit(QL_ASIC_RECOVERY, &qdev->flags)) { - /* Stop management traffic. */ - ql_mb_set_mgmnt_traffic_ctl(qdev, MB_SET_MPI_TFK_STOP); - - /* Wait for the NIC and MGMNT FIFOs to empty. */ - ql_wait_fifo_empty(qdev); - } else - clear_bit(QL_ASIC_RECOVERY, &qdev->flags); - - ql_write32(qdev, RST_FO, (RST_FO_FR << 16) | RST_FO_FR); - - end_jiffies = jiffies + usecs_to_jiffies(30); - do { - value = ql_read32(qdev, RST_FO); - if ((value & RST_FO_FR) == 0) - break; - cpu_relax(); - } while (time_before(jiffies, end_jiffies)); - - if (value & RST_FO_FR) { - netif_err(qdev, ifdown, qdev->ndev, - "ETIMEDOUT!!! errored out of resetting the chip!\n"); - status = -ETIMEDOUT; - } - - /* Resume management traffic. */ - ql_mb_set_mgmnt_traffic_ctl(qdev, MB_SET_MPI_TFK_RESUME); - return status; -} - -static void ql_display_dev_info(struct net_device *ndev) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - - netif_info(qdev, probe, qdev->ndev, - "Function #%d, Port %d, NIC Roll %d, NIC Rev = %d, " - "XG Roll = %d, XG Rev = %d.\n", - qdev->func, - qdev->port, - qdev->chip_rev_id & 0x0000000f, - qdev->chip_rev_id >> 4 & 0x0000000f, - qdev->chip_rev_id >> 8 & 0x0000000f, - qdev->chip_rev_id >> 12 & 0x0000000f); - netif_info(qdev, probe, qdev->ndev, - "MAC address %pM\n", ndev->dev_addr); -} - -static int ql_wol(struct ql_adapter *qdev) -{ - int status = 0; - u32 wol = MB_WOL_DISABLE; - - /* The CAM is still intact after a reset, but if we - * are doing WOL, then we may need to program the - * routing regs. We would also need to issue the mailbox - * commands to instruct the MPI what to do per the ethtool - * settings. - */ - - if (qdev->wol & (WAKE_ARP | WAKE_MAGICSECURE | WAKE_PHY | WAKE_UCAST | - WAKE_MCAST | WAKE_BCAST)) { - netif_err(qdev, ifdown, qdev->ndev, - "Unsupported WOL parameter. qdev->wol = 0x%x.\n", - qdev->wol); - return -EINVAL; - } - - if (qdev->wol & WAKE_MAGIC) { - status = ql_mb_wol_set_magic(qdev, 1); - if (status) { - netif_err(qdev, ifdown, qdev->ndev, - "Failed to set magic packet on %s.\n", - qdev->ndev->name); - return status; - } else - netif_info(qdev, drv, qdev->ndev, - "Enabled magic packet successfully on %s.\n", - qdev->ndev->name); - - wol |= MB_WOL_MAGIC_PKT; - } - - if (qdev->wol) { - wol |= MB_WOL_MODE_ON; - status = ql_mb_wol_mode(qdev, wol); - netif_err(qdev, drv, qdev->ndev, - "WOL %s (wol code 0x%x) on %s\n", - (status == 0) ? "Successfully set" : "Failed", - wol, qdev->ndev->name); - } - - return status; -} - -static void ql_cancel_all_work_sync(struct ql_adapter *qdev) -{ - - /* Don't kill the reset worker thread if we - * are in the process of recovery. - */ - if (test_bit(QL_ADAPTER_UP, &qdev->flags)) - cancel_delayed_work_sync(&qdev->asic_reset_work); - cancel_delayed_work_sync(&qdev->mpi_reset_work); - cancel_delayed_work_sync(&qdev->mpi_work); - cancel_delayed_work_sync(&qdev->mpi_idc_work); - cancel_delayed_work_sync(&qdev->mpi_core_to_log); - cancel_delayed_work_sync(&qdev->mpi_port_cfg_work); -} - -static int ql_adapter_down(struct ql_adapter *qdev) -{ - int i, status = 0; - - ql_link_off(qdev); - - ql_cancel_all_work_sync(qdev); - - for (i = 0; i < qdev->rss_ring_count; i++) - napi_disable(&qdev->rx_ring[i].napi); - - clear_bit(QL_ADAPTER_UP, &qdev->flags); - - ql_disable_interrupts(qdev); - - ql_tx_ring_clean(qdev); - - /* Call netif_napi_del() from common point. - */ - for (i = 0; i < qdev->rss_ring_count; i++) - netif_napi_del(&qdev->rx_ring[i].napi); - - status = ql_adapter_reset(qdev); - if (status) - netif_err(qdev, ifdown, qdev->ndev, "reset(func #%d) FAILED!\n", - qdev->func); - ql_free_rx_buffers(qdev); - - return status; -} - -static int ql_adapter_up(struct ql_adapter *qdev) -{ - int err = 0; - - err = ql_adapter_initialize(qdev); - if (err) { - netif_info(qdev, ifup, qdev->ndev, "Unable to initialize adapter.\n"); - goto err_init; - } - set_bit(QL_ADAPTER_UP, &qdev->flags); - ql_alloc_rx_buffers(qdev); - /* If the port is initialized and the - * link is up the turn on the carrier. - */ - if ((ql_read32(qdev, STS) & qdev->port_init) && - (ql_read32(qdev, STS) & qdev->port_link_up)) - ql_link_on(qdev); - /* Restore rx mode. */ - clear_bit(QL_ALLMULTI, &qdev->flags); - clear_bit(QL_PROMISCUOUS, &qdev->flags); - qlge_set_multicast_list(qdev->ndev); - - /* Restore vlan setting. */ - qlge_restore_vlan(qdev); - - ql_enable_interrupts(qdev); - ql_enable_all_completion_interrupts(qdev); - netif_tx_start_all_queues(qdev->ndev); - - return 0; -err_init: - ql_adapter_reset(qdev); - return err; -} - -static void ql_release_adapter_resources(struct ql_adapter *qdev) -{ - ql_free_mem_resources(qdev); - ql_free_irq(qdev); -} - -static int ql_get_adapter_resources(struct ql_adapter *qdev) -{ - int status = 0; - - if (ql_alloc_mem_resources(qdev)) { - netif_err(qdev, ifup, qdev->ndev, "Unable to allocate memory.\n"); - return -ENOMEM; - } - status = ql_request_irq(qdev); - return status; -} - -static int qlge_close(struct net_device *ndev) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - - /* If we hit pci_channel_io_perm_failure - * failure condition, then we already - * brought the adapter down. - */ - if (test_bit(QL_EEH_FATAL, &qdev->flags)) { - netif_err(qdev, drv, qdev->ndev, "EEH fatal did unload.\n"); - clear_bit(QL_EEH_FATAL, &qdev->flags); - return 0; - } - - /* - * Wait for device to recover from a reset. - * (Rarely happens, but possible.) - */ - while (!test_bit(QL_ADAPTER_UP, &qdev->flags)) - msleep(1); - ql_adapter_down(qdev); - ql_release_adapter_resources(qdev); - return 0; -} - -static int ql_configure_rings(struct ql_adapter *qdev) -{ - int i; - struct rx_ring *rx_ring; - struct tx_ring *tx_ring; - int cpu_cnt = min(MAX_CPUS, (int)num_online_cpus()); - unsigned int lbq_buf_len = (qdev->ndev->mtu > 1500) ? - LARGE_BUFFER_MAX_SIZE : LARGE_BUFFER_MIN_SIZE; - - qdev->lbq_buf_order = get_order(lbq_buf_len); - - /* In a perfect world we have one RSS ring for each CPU - * and each has it's own vector. To do that we ask for - * cpu_cnt vectors. ql_enable_msix() will adjust the - * vector count to what we actually get. We then - * allocate an RSS ring for each. - * Essentially, we are doing min(cpu_count, msix_vector_count). - */ - qdev->intr_count = cpu_cnt; - ql_enable_msix(qdev); - /* Adjust the RSS ring count to the actual vector count. */ - qdev->rss_ring_count = qdev->intr_count; - qdev->tx_ring_count = cpu_cnt; - qdev->rx_ring_count = qdev->tx_ring_count + qdev->rss_ring_count; - - for (i = 0; i < qdev->tx_ring_count; i++) { - tx_ring = &qdev->tx_ring[i]; - memset((void *)tx_ring, 0, sizeof(*tx_ring)); - tx_ring->qdev = qdev; - tx_ring->wq_id = i; - tx_ring->wq_len = qdev->tx_ring_size; - tx_ring->wq_size = - tx_ring->wq_len * sizeof(struct ob_mac_iocb_req); - - /* - * The completion queue ID for the tx rings start - * immediately after the rss rings. - */ - tx_ring->cq_id = qdev->rss_ring_count + i; - } - - for (i = 0; i < qdev->rx_ring_count; i++) { - rx_ring = &qdev->rx_ring[i]; - memset((void *)rx_ring, 0, sizeof(*rx_ring)); - rx_ring->qdev = qdev; - rx_ring->cq_id = i; - rx_ring->cpu = i % cpu_cnt; /* CPU to run handler on. */ - if (i < qdev->rss_ring_count) { - /* - * Inbound (RSS) queues. - */ - rx_ring->cq_len = qdev->rx_ring_size; - rx_ring->cq_size = - rx_ring->cq_len * sizeof(struct ql_net_rsp_iocb); - rx_ring->lbq_len = NUM_LARGE_BUFFERS; - rx_ring->lbq_size = - rx_ring->lbq_len * sizeof(__le64); - rx_ring->lbq_buf_size = (u16)lbq_buf_len; - rx_ring->sbq_len = NUM_SMALL_BUFFERS; - rx_ring->sbq_size = - rx_ring->sbq_len * sizeof(__le64); - rx_ring->sbq_buf_size = SMALL_BUF_MAP_SIZE; - rx_ring->type = RX_Q; - } else { - /* - * Outbound queue handles outbound completions only. - */ - /* outbound cq is same size as tx_ring it services. */ - rx_ring->cq_len = qdev->tx_ring_size; - rx_ring->cq_size = - rx_ring->cq_len * sizeof(struct ql_net_rsp_iocb); - rx_ring->lbq_len = 0; - rx_ring->lbq_size = 0; - rx_ring->lbq_buf_size = 0; - rx_ring->sbq_len = 0; - rx_ring->sbq_size = 0; - rx_ring->sbq_buf_size = 0; - rx_ring->type = TX_Q; - } - } - return 0; -} - -static int qlge_open(struct net_device *ndev) -{ - int err = 0; - struct ql_adapter *qdev = netdev_priv(ndev); - - err = ql_adapter_reset(qdev); - if (err) - return err; - - err = ql_configure_rings(qdev); - if (err) - return err; - - err = ql_get_adapter_resources(qdev); - if (err) - goto error_up; - - err = ql_adapter_up(qdev); - if (err) - goto error_up; - - return err; - -error_up: - ql_release_adapter_resources(qdev); - return err; -} - -static int ql_change_rx_buffers(struct ql_adapter *qdev) -{ - struct rx_ring *rx_ring; - int i, status; - u32 lbq_buf_len; - - /* Wait for an outstanding reset to complete. */ - if (!test_bit(QL_ADAPTER_UP, &qdev->flags)) { - int i = 4; - - while (--i && !test_bit(QL_ADAPTER_UP, &qdev->flags)) { - netif_err(qdev, ifup, qdev->ndev, - "Waiting for adapter UP...\n"); - ssleep(1); - } - - if (!i) { - netif_err(qdev, ifup, qdev->ndev, - "Timed out waiting for adapter UP\n"); - return -ETIMEDOUT; - } - } - - status = ql_adapter_down(qdev); - if (status) - goto error; - - /* Get the new rx buffer size. */ - lbq_buf_len = (qdev->ndev->mtu > 1500) ? - LARGE_BUFFER_MAX_SIZE : LARGE_BUFFER_MIN_SIZE; - qdev->lbq_buf_order = get_order(lbq_buf_len); - - for (i = 0; i < qdev->rss_ring_count; i++) { - rx_ring = &qdev->rx_ring[i]; - /* Set the new size. */ - rx_ring->lbq_buf_size = lbq_buf_len; - } - - status = ql_adapter_up(qdev); - if (status) - goto error; - - return status; -error: - netif_alert(qdev, ifup, qdev->ndev, - "Driver up/down cycle failed, closing device.\n"); - set_bit(QL_ADAPTER_UP, &qdev->flags); - dev_close(qdev->ndev); - return status; -} - -static int qlge_change_mtu(struct net_device *ndev, int new_mtu) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - int status; - - if (ndev->mtu == 1500 && new_mtu == 9000) { - netif_err(qdev, ifup, qdev->ndev, "Changing to jumbo MTU.\n"); - } else if (ndev->mtu == 9000 && new_mtu == 1500) { - netif_err(qdev, ifup, qdev->ndev, "Changing to normal MTU.\n"); - } else - return -EINVAL; - - queue_delayed_work(qdev->workqueue, - &qdev->mpi_port_cfg_work, 3*HZ); - - ndev->mtu = new_mtu; - - if (!netif_running(qdev->ndev)) { - return 0; - } - - status = ql_change_rx_buffers(qdev); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Changing MTU failed.\n"); - } - - return status; -} - -static struct net_device_stats *qlge_get_stats(struct net_device - *ndev) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - struct rx_ring *rx_ring = &qdev->rx_ring[0]; - struct tx_ring *tx_ring = &qdev->tx_ring[0]; - unsigned long pkts, mcast, dropped, errors, bytes; - int i; - - /* Get RX stats. */ - pkts = mcast = dropped = errors = bytes = 0; - for (i = 0; i < qdev->rss_ring_count; i++, rx_ring++) { - pkts += rx_ring->rx_packets; - bytes += rx_ring->rx_bytes; - dropped += rx_ring->rx_dropped; - errors += rx_ring->rx_errors; - mcast += rx_ring->rx_multicast; - } - ndev->stats.rx_packets = pkts; - ndev->stats.rx_bytes = bytes; - ndev->stats.rx_dropped = dropped; - ndev->stats.rx_errors = errors; - ndev->stats.multicast = mcast; - - /* Get TX stats. */ - pkts = errors = bytes = 0; - for (i = 0; i < qdev->tx_ring_count; i++, tx_ring++) { - pkts += tx_ring->tx_packets; - bytes += tx_ring->tx_bytes; - errors += tx_ring->tx_errors; - } - ndev->stats.tx_packets = pkts; - ndev->stats.tx_bytes = bytes; - ndev->stats.tx_errors = errors; - return &ndev->stats; -} - -static void qlge_set_multicast_list(struct net_device *ndev) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - struct netdev_hw_addr *ha; - int i, status; - - status = ql_sem_spinlock(qdev, SEM_RT_IDX_MASK); - if (status) - return; - /* - * Set or clear promiscuous mode if a - * transition is taking place. - */ - if (ndev->flags & IFF_PROMISC) { - if (!test_bit(QL_PROMISCUOUS, &qdev->flags)) { - if (ql_set_routing_reg - (qdev, RT_IDX_PROMISCUOUS_SLOT, RT_IDX_VALID, 1)) { - netif_err(qdev, hw, qdev->ndev, - "Failed to set promiscuous mode.\n"); - } else { - set_bit(QL_PROMISCUOUS, &qdev->flags); - } - } - } else { - if (test_bit(QL_PROMISCUOUS, &qdev->flags)) { - if (ql_set_routing_reg - (qdev, RT_IDX_PROMISCUOUS_SLOT, RT_IDX_VALID, 0)) { - netif_err(qdev, hw, qdev->ndev, - "Failed to clear promiscuous mode.\n"); - } else { - clear_bit(QL_PROMISCUOUS, &qdev->flags); - } - } - } - - /* - * Set or clear all multicast mode if a - * transition is taking place. - */ - if ((ndev->flags & IFF_ALLMULTI) || - (netdev_mc_count(ndev) > MAX_MULTICAST_ENTRIES)) { - if (!test_bit(QL_ALLMULTI, &qdev->flags)) { - if (ql_set_routing_reg - (qdev, RT_IDX_ALLMULTI_SLOT, RT_IDX_MCAST, 1)) { - netif_err(qdev, hw, qdev->ndev, - "Failed to set all-multi mode.\n"); - } else { - set_bit(QL_ALLMULTI, &qdev->flags); - } - } - } else { - if (test_bit(QL_ALLMULTI, &qdev->flags)) { - if (ql_set_routing_reg - (qdev, RT_IDX_ALLMULTI_SLOT, RT_IDX_MCAST, 0)) { - netif_err(qdev, hw, qdev->ndev, - "Failed to clear all-multi mode.\n"); - } else { - clear_bit(QL_ALLMULTI, &qdev->flags); - } - } - } - - if (!netdev_mc_empty(ndev)) { - status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK); - if (status) - goto exit; - i = 0; - netdev_for_each_mc_addr(ha, ndev) { - if (ql_set_mac_addr_reg(qdev, (u8 *) ha->addr, - MAC_ADDR_TYPE_MULTI_MAC, i)) { - netif_err(qdev, hw, qdev->ndev, - "Failed to loadmulticast address.\n"); - ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK); - goto exit; - } - i++; - } - ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK); - if (ql_set_routing_reg - (qdev, RT_IDX_MCAST_MATCH_SLOT, RT_IDX_MCAST_MATCH, 1)) { - netif_err(qdev, hw, qdev->ndev, - "Failed to set multicast match mode.\n"); - } else { - set_bit(QL_ALLMULTI, &qdev->flags); - } - } -exit: - ql_sem_unlock(qdev, SEM_RT_IDX_MASK); -} - -static int qlge_set_mac_address(struct net_device *ndev, void *p) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - struct sockaddr *addr = p; - int status; - - if (!is_valid_ether_addr(addr->sa_data)) - return -EADDRNOTAVAIL; - memcpy(ndev->dev_addr, addr->sa_data, ndev->addr_len); - /* Update local copy of current mac address. */ - memcpy(qdev->current_mac_addr, ndev->dev_addr, ndev->addr_len); - - status = ql_sem_spinlock(qdev, SEM_MAC_ADDR_MASK); - if (status) - return status; - status = ql_set_mac_addr_reg(qdev, (u8 *) ndev->dev_addr, - MAC_ADDR_TYPE_CAM_MAC, qdev->func * MAX_CQ); - if (status) - netif_err(qdev, hw, qdev->ndev, "Failed to load MAC address.\n"); - ql_sem_unlock(qdev, SEM_MAC_ADDR_MASK); - return status; -} - -static void qlge_tx_timeout(struct net_device *ndev) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - ql_queue_asic_error(qdev); -} - -static void ql_asic_reset_work(struct work_struct *work) -{ - struct ql_adapter *qdev = - container_of(work, struct ql_adapter, asic_reset_work.work); - int status; - rtnl_lock(); - status = ql_adapter_down(qdev); - if (status) - goto error; - - status = ql_adapter_up(qdev); - if (status) - goto error; - - /* Restore rx mode. */ - clear_bit(QL_ALLMULTI, &qdev->flags); - clear_bit(QL_PROMISCUOUS, &qdev->flags); - qlge_set_multicast_list(qdev->ndev); - - rtnl_unlock(); - return; -error: - netif_alert(qdev, ifup, qdev->ndev, - "Driver up/down cycle failed, closing device\n"); - - set_bit(QL_ADAPTER_UP, &qdev->flags); - dev_close(qdev->ndev); - rtnl_unlock(); -} - -static const struct nic_operations qla8012_nic_ops = { - .get_flash = ql_get_8012_flash_params, - .port_initialize = ql_8012_port_initialize, -}; - -static const struct nic_operations qla8000_nic_ops = { - .get_flash = ql_get_8000_flash_params, - .port_initialize = ql_8000_port_initialize, -}; - -/* Find the pcie function number for the other NIC - * on this chip. Since both NIC functions share a - * common firmware we have the lowest enabled function - * do any common work. Examples would be resetting - * after a fatal firmware error, or doing a firmware - * coredump. - */ -static int ql_get_alt_pcie_func(struct ql_adapter *qdev) -{ - int status = 0; - u32 temp; - u32 nic_func1, nic_func2; - - status = ql_read_mpi_reg(qdev, MPI_TEST_FUNC_PORT_CFG, - &temp); - if (status) - return status; - - nic_func1 = ((temp >> MPI_TEST_NIC1_FUNC_SHIFT) & - MPI_TEST_NIC_FUNC_MASK); - nic_func2 = ((temp >> MPI_TEST_NIC2_FUNC_SHIFT) & - MPI_TEST_NIC_FUNC_MASK); - - if (qdev->func == nic_func1) - qdev->alt_func = nic_func2; - else if (qdev->func == nic_func2) - qdev->alt_func = nic_func1; - else - status = -EIO; - - return status; -} - -static int ql_get_board_info(struct ql_adapter *qdev) -{ - int status; - qdev->func = - (ql_read32(qdev, STS) & STS_FUNC_ID_MASK) >> STS_FUNC_ID_SHIFT; - if (qdev->func > 3) - return -EIO; - - status = ql_get_alt_pcie_func(qdev); - if (status) - return status; - - qdev->port = (qdev->func < qdev->alt_func) ? 0 : 1; - if (qdev->port) { - qdev->xg_sem_mask = SEM_XGMAC1_MASK; - qdev->port_link_up = STS_PL1; - qdev->port_init = STS_PI1; - qdev->mailbox_in = PROC_ADDR_MPI_RISC | PROC_ADDR_FUNC2_MBI; - qdev->mailbox_out = PROC_ADDR_MPI_RISC | PROC_ADDR_FUNC2_MBO; - } else { - qdev->xg_sem_mask = SEM_XGMAC0_MASK; - qdev->port_link_up = STS_PL0; - qdev->port_init = STS_PI0; - qdev->mailbox_in = PROC_ADDR_MPI_RISC | PROC_ADDR_FUNC0_MBI; - qdev->mailbox_out = PROC_ADDR_MPI_RISC | PROC_ADDR_FUNC0_MBO; - } - qdev->chip_rev_id = ql_read32(qdev, REV_ID); - qdev->device_id = qdev->pdev->device; - if (qdev->device_id == QLGE_DEVICE_ID_8012) - qdev->nic_ops = &qla8012_nic_ops; - else if (qdev->device_id == QLGE_DEVICE_ID_8000) - qdev->nic_ops = &qla8000_nic_ops; - return status; -} - -static void ql_release_all(struct pci_dev *pdev) -{ - struct net_device *ndev = pci_get_drvdata(pdev); - struct ql_adapter *qdev = netdev_priv(ndev); - - if (qdev->workqueue) { - destroy_workqueue(qdev->workqueue); - qdev->workqueue = NULL; - } - - if (qdev->reg_base) - iounmap(qdev->reg_base); - if (qdev->doorbell_area) - iounmap(qdev->doorbell_area); - vfree(qdev->mpi_coredump); - pci_release_regions(pdev); -} - -static int ql_init_device(struct pci_dev *pdev, struct net_device *ndev, - int cards_found) -{ - struct ql_adapter *qdev = netdev_priv(ndev); - int err = 0; - - memset((void *)qdev, 0, sizeof(*qdev)); - err = pci_enable_device(pdev); - if (err) { - dev_err(&pdev->dev, "PCI device enable failed.\n"); - return err; - } - - qdev->ndev = ndev; - qdev->pdev = pdev; - pci_set_drvdata(pdev, ndev); - - /* Set PCIe read request size */ - err = pcie_set_readrq(pdev, 4096); - if (err) { - dev_err(&pdev->dev, "Set readrq failed.\n"); - goto err_out1; - } - - err = pci_request_regions(pdev, DRV_NAME); - if (err) { - dev_err(&pdev->dev, "PCI region request failed.\n"); - return err; - } - - pci_set_master(pdev); - if (!pci_set_dma_mask(pdev, DMA_BIT_MASK(64))) { - set_bit(QL_DMA64, &qdev->flags); - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); - } else { - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); - if (!err) - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); - } - - if (err) { - dev_err(&pdev->dev, "No usable DMA configuration.\n"); - goto err_out2; - } - - /* Set PCIe reset type for EEH to fundamental. */ - pdev->needs_freset = 1; - pci_save_state(pdev); - qdev->reg_base = - ioremap_nocache(pci_resource_start(pdev, 1), - pci_resource_len(pdev, 1)); - if (!qdev->reg_base) { - dev_err(&pdev->dev, "Register mapping failed.\n"); - err = -ENOMEM; - goto err_out2; - } - - qdev->doorbell_area_size = pci_resource_len(pdev, 3); - qdev->doorbell_area = - ioremap_nocache(pci_resource_start(pdev, 3), - pci_resource_len(pdev, 3)); - if (!qdev->doorbell_area) { - dev_err(&pdev->dev, "Doorbell register mapping failed.\n"); - err = -ENOMEM; - goto err_out2; - } - - err = ql_get_board_info(qdev); - if (err) { - dev_err(&pdev->dev, "Register access failed.\n"); - err = -EIO; - goto err_out2; - } - qdev->msg_enable = netif_msg_init(debug, default_msg); - spin_lock_init(&qdev->hw_lock); - spin_lock_init(&qdev->stats_lock); - - if (qlge_mpi_coredump) { - qdev->mpi_coredump = - vmalloc(sizeof(struct ql_mpi_coredump)); - if (qdev->mpi_coredump == NULL) { - err = -ENOMEM; - goto err_out2; - } - if (qlge_force_coredump) - set_bit(QL_FRC_COREDUMP, &qdev->flags); - } - /* make sure the EEPROM is good */ - err = qdev->nic_ops->get_flash(qdev); - if (err) { - dev_err(&pdev->dev, "Invalid FLASH.\n"); - goto err_out2; - } - - /* Keep local copy of current mac address. */ - memcpy(qdev->current_mac_addr, ndev->dev_addr, ndev->addr_len); - - /* Set up the default ring sizes. */ - qdev->tx_ring_size = NUM_TX_RING_ENTRIES; - qdev->rx_ring_size = NUM_RX_RING_ENTRIES; - - /* Set up the coalescing parameters. */ - qdev->rx_coalesce_usecs = DFLT_COALESCE_WAIT; - qdev->tx_coalesce_usecs = DFLT_COALESCE_WAIT; - qdev->rx_max_coalesced_frames = DFLT_INTER_FRAME_WAIT; - qdev->tx_max_coalesced_frames = DFLT_INTER_FRAME_WAIT; - - /* - * Set up the operating parameters. - */ - qdev->workqueue = alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, - ndev->name); - if (!qdev->workqueue) { - err = -ENOMEM; - goto err_out2; - } - - INIT_DELAYED_WORK(&qdev->asic_reset_work, ql_asic_reset_work); - INIT_DELAYED_WORK(&qdev->mpi_reset_work, ql_mpi_reset_work); - INIT_DELAYED_WORK(&qdev->mpi_work, ql_mpi_work); - INIT_DELAYED_WORK(&qdev->mpi_port_cfg_work, ql_mpi_port_cfg_work); - INIT_DELAYED_WORK(&qdev->mpi_idc_work, ql_mpi_idc_work); - INIT_DELAYED_WORK(&qdev->mpi_core_to_log, ql_mpi_core_to_log); - init_completion(&qdev->ide_completion); - mutex_init(&qdev->mpi_mutex); - - if (!cards_found) { - dev_info(&pdev->dev, "%s\n", DRV_STRING); - dev_info(&pdev->dev, "Driver name: %s, Version: %s.\n", - DRV_NAME, DRV_VERSION); - } - return 0; -err_out2: - ql_release_all(pdev); -err_out1: - pci_disable_device(pdev); - return err; -} - -static const struct net_device_ops qlge_netdev_ops = { - .ndo_open = qlge_open, - .ndo_stop = qlge_close, - .ndo_start_xmit = qlge_send, - .ndo_change_mtu = qlge_change_mtu, - .ndo_get_stats = qlge_get_stats, - .ndo_set_rx_mode = qlge_set_multicast_list, - .ndo_set_mac_address = qlge_set_mac_address, - .ndo_validate_addr = eth_validate_addr, - .ndo_tx_timeout = qlge_tx_timeout, - .ndo_set_features = qlge_set_features, - .ndo_vlan_rx_add_vid = qlge_vlan_rx_add_vid, - .ndo_vlan_rx_kill_vid = qlge_vlan_rx_kill_vid, -}; - -static void ql_timer(struct timer_list *t) -{ - struct ql_adapter *qdev = from_timer(qdev, t, timer); - u32 var = 0; - - var = ql_read32(qdev, STS); - if (pci_channel_offline(qdev->pdev)) { - netif_err(qdev, ifup, qdev->ndev, "EEH STS = 0x%.08x.\n", var); - return; - } - - mod_timer(&qdev->timer, jiffies + (5*HZ)); -} - -static int qlge_probe(struct pci_dev *pdev, - const struct pci_device_id *pci_entry) -{ - struct net_device *ndev = NULL; - struct ql_adapter *qdev = NULL; - static int cards_found = 0; - int err = 0; - - ndev = alloc_etherdev_mq(sizeof(struct ql_adapter), - min(MAX_CPUS, netif_get_num_default_rss_queues())); - if (!ndev) - return -ENOMEM; - - err = ql_init_device(pdev, ndev, cards_found); - if (err < 0) { - free_netdev(ndev); - return err; - } - - qdev = netdev_priv(ndev); - SET_NETDEV_DEV(ndev, &pdev->dev); - ndev->hw_features = NETIF_F_SG | - NETIF_F_IP_CSUM | - NETIF_F_TSO | - NETIF_F_TSO_ECN | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX | - NETIF_F_HW_VLAN_CTAG_FILTER | - NETIF_F_RXCSUM; - ndev->features = ndev->hw_features; - ndev->vlan_features = ndev->hw_features; - /* vlan gets same features (except vlan filter) */ - ndev->vlan_features &= ~(NETIF_F_HW_VLAN_CTAG_FILTER | - NETIF_F_HW_VLAN_CTAG_TX | - NETIF_F_HW_VLAN_CTAG_RX); - - if (test_bit(QL_DMA64, &qdev->flags)) - ndev->features |= NETIF_F_HIGHDMA; - - /* - * Set up net_device structure. - */ - ndev->tx_queue_len = qdev->tx_ring_size; - ndev->irq = pdev->irq; - - ndev->netdev_ops = &qlge_netdev_ops; - ndev->ethtool_ops = &qlge_ethtool_ops; - ndev->watchdog_timeo = 10 * HZ; - - /* MTU range: this driver only supports 1500 or 9000, so this only - * filters out values above or below, and we'll rely on - * qlge_change_mtu to make sure only 1500 or 9000 are allowed - */ - ndev->min_mtu = ETH_DATA_LEN; - ndev->max_mtu = 9000; - - err = register_netdev(ndev); - if (err) { - dev_err(&pdev->dev, "net device registration failed.\n"); - ql_release_all(pdev); - pci_disable_device(pdev); - free_netdev(ndev); - return err; - } - /* Start up the timer to trigger EEH if - * the bus goes dead - */ - timer_setup(&qdev->timer, ql_timer, TIMER_DEFERRABLE); - mod_timer(&qdev->timer, jiffies + (5*HZ)); - ql_link_off(qdev); - ql_display_dev_info(ndev); - atomic_set(&qdev->lb_count, 0); - cards_found++; - return 0; -} - -netdev_tx_t ql_lb_send(struct sk_buff *skb, struct net_device *ndev) -{ - return qlge_send(skb, ndev); -} - -int ql_clean_lb_rx_ring(struct rx_ring *rx_ring, int budget) -{ - return ql_clean_inbound_rx_ring(rx_ring, budget); -} - -static void qlge_remove(struct pci_dev *pdev) -{ - struct net_device *ndev = pci_get_drvdata(pdev); - struct ql_adapter *qdev = netdev_priv(ndev); - del_timer_sync(&qdev->timer); - ql_cancel_all_work_sync(qdev); - unregister_netdev(ndev); - ql_release_all(pdev); - pci_disable_device(pdev); - free_netdev(ndev); -} - -/* Clean up resources without touching hardware. */ -static void ql_eeh_close(struct net_device *ndev) -{ - int i; - struct ql_adapter *qdev = netdev_priv(ndev); - - if (netif_carrier_ok(ndev)) { - netif_carrier_off(ndev); - netif_stop_queue(ndev); - } - - /* Disabling the timer */ - ql_cancel_all_work_sync(qdev); - - for (i = 0; i < qdev->rss_ring_count; i++) - netif_napi_del(&qdev->rx_ring[i].napi); - - clear_bit(QL_ADAPTER_UP, &qdev->flags); - ql_tx_ring_clean(qdev); - ql_free_rx_buffers(qdev); - ql_release_adapter_resources(qdev); -} - -/* - * This callback is called by the PCI subsystem whenever - * a PCI bus error is detected. - */ -static pci_ers_result_t qlge_io_error_detected(struct pci_dev *pdev, - enum pci_channel_state state) -{ - struct net_device *ndev = pci_get_drvdata(pdev); - struct ql_adapter *qdev = netdev_priv(ndev); - - switch (state) { - case pci_channel_io_normal: - return PCI_ERS_RESULT_CAN_RECOVER; - case pci_channel_io_frozen: - netif_device_detach(ndev); - del_timer_sync(&qdev->timer); - if (netif_running(ndev)) - ql_eeh_close(ndev); - pci_disable_device(pdev); - return PCI_ERS_RESULT_NEED_RESET; - case pci_channel_io_perm_failure: - dev_err(&pdev->dev, - "%s: pci_channel_io_perm_failure.\n", __func__); - del_timer_sync(&qdev->timer); - ql_eeh_close(ndev); - set_bit(QL_EEH_FATAL, &qdev->flags); - return PCI_ERS_RESULT_DISCONNECT; - } - - /* Request a slot reset. */ - return PCI_ERS_RESULT_NEED_RESET; -} - -/* - * This callback is called after the PCI buss has been reset. - * Basically, this tries to restart the card from scratch. - * This is a shortened version of the device probe/discovery code, - * it resembles the first-half of the () routine. - */ -static pci_ers_result_t qlge_io_slot_reset(struct pci_dev *pdev) -{ - struct net_device *ndev = pci_get_drvdata(pdev); - struct ql_adapter *qdev = netdev_priv(ndev); - - pdev->error_state = pci_channel_io_normal; - - pci_restore_state(pdev); - if (pci_enable_device(pdev)) { - netif_err(qdev, ifup, qdev->ndev, - "Cannot re-enable PCI device after reset.\n"); - return PCI_ERS_RESULT_DISCONNECT; - } - pci_set_master(pdev); - - if (ql_adapter_reset(qdev)) { - netif_err(qdev, drv, qdev->ndev, "reset FAILED!\n"); - set_bit(QL_EEH_FATAL, &qdev->flags); - return PCI_ERS_RESULT_DISCONNECT; - } - - return PCI_ERS_RESULT_RECOVERED; -} - -static void qlge_io_resume(struct pci_dev *pdev) -{ - struct net_device *ndev = pci_get_drvdata(pdev); - struct ql_adapter *qdev = netdev_priv(ndev); - int err = 0; - - if (netif_running(ndev)) { - err = qlge_open(ndev); - if (err) { - netif_err(qdev, ifup, qdev->ndev, - "Device initialization failed after reset.\n"); - return; - } - } else { - netif_err(qdev, ifup, qdev->ndev, - "Device was not running prior to EEH.\n"); - } - mod_timer(&qdev->timer, jiffies + (5*HZ)); - netif_device_attach(ndev); -} - -static const struct pci_error_handlers qlge_err_handler = { - .error_detected = qlge_io_error_detected, - .slot_reset = qlge_io_slot_reset, - .resume = qlge_io_resume, -}; - -static int qlge_suspend(struct pci_dev *pdev, pm_message_t state) -{ - struct net_device *ndev = pci_get_drvdata(pdev); - struct ql_adapter *qdev = netdev_priv(ndev); - int err; - - netif_device_detach(ndev); - del_timer_sync(&qdev->timer); - - if (netif_running(ndev)) { - err = ql_adapter_down(qdev); - if (!err) - return err; - } - - ql_wol(qdev); - err = pci_save_state(pdev); - if (err) - return err; - - pci_disable_device(pdev); - - pci_set_power_state(pdev, pci_choose_state(pdev, state)); - - return 0; -} - -#ifdef CONFIG_PM -static int qlge_resume(struct pci_dev *pdev) -{ - struct net_device *ndev = pci_get_drvdata(pdev); - struct ql_adapter *qdev = netdev_priv(ndev); - int err; - - pci_set_power_state(pdev, PCI_D0); - pci_restore_state(pdev); - err = pci_enable_device(pdev); - if (err) { - netif_err(qdev, ifup, qdev->ndev, "Cannot enable PCI device from suspend\n"); - return err; - } - pci_set_master(pdev); - - pci_enable_wake(pdev, PCI_D3hot, 0); - pci_enable_wake(pdev, PCI_D3cold, 0); - - if (netif_running(ndev)) { - err = ql_adapter_up(qdev); - if (err) - return err; - } - - mod_timer(&qdev->timer, jiffies + (5*HZ)); - netif_device_attach(ndev); - - return 0; -} -#endif /* CONFIG_PM */ - -static void qlge_shutdown(struct pci_dev *pdev) -{ - qlge_suspend(pdev, PMSG_SUSPEND); -} - -static struct pci_driver qlge_driver = { - .name = DRV_NAME, - .id_table = qlge_pci_tbl, - .probe = qlge_probe, - .remove = qlge_remove, -#ifdef CONFIG_PM - .suspend = qlge_suspend, - .resume = qlge_resume, -#endif - .shutdown = qlge_shutdown, - .err_handler = &qlge_err_handler -}; - -module_pci_driver(qlge_driver); diff --git a/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c b/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c deleted file mode 100644 index 957c72985a06..000000000000 --- a/drivers/net/ethernet/qlogic/qlge/qlge_mpi.c +++ /dev/null @@ -1,1285 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -#include "qlge.h" - -int ql_unpause_mpi_risc(struct ql_adapter *qdev) -{ - u32 tmp; - - /* Un-pause the RISC */ - tmp = ql_read32(qdev, CSR); - if (!(tmp & CSR_RP)) - return -EIO; - - ql_write32(qdev, CSR, CSR_CMD_CLR_PAUSE); - return 0; -} - -int ql_pause_mpi_risc(struct ql_adapter *qdev) -{ - u32 tmp; - int count = UDELAY_COUNT; - - /* Pause the RISC */ - ql_write32(qdev, CSR, CSR_CMD_SET_PAUSE); - do { - tmp = ql_read32(qdev, CSR); - if (tmp & CSR_RP) - break; - mdelay(UDELAY_DELAY); - count--; - } while (count); - return (count == 0) ? -ETIMEDOUT : 0; -} - -int ql_hard_reset_mpi_risc(struct ql_adapter *qdev) -{ - u32 tmp; - int count = UDELAY_COUNT; - - /* Reset the RISC */ - ql_write32(qdev, CSR, CSR_CMD_SET_RST); - do { - tmp = ql_read32(qdev, CSR); - if (tmp & CSR_RR) { - ql_write32(qdev, CSR, CSR_CMD_CLR_RST); - break; - } - mdelay(UDELAY_DELAY); - count--; - } while (count); - return (count == 0) ? -ETIMEDOUT : 0; -} - -int ql_read_mpi_reg(struct ql_adapter *qdev, u32 reg, u32 *data) -{ - int status; - /* wait for reg to come ready */ - status = ql_wait_reg_rdy(qdev, PROC_ADDR, PROC_ADDR_RDY, PROC_ADDR_ERR); - if (status) - goto exit; - /* set up for reg read */ - ql_write32(qdev, PROC_ADDR, reg | PROC_ADDR_R); - /* wait for reg to come ready */ - status = ql_wait_reg_rdy(qdev, PROC_ADDR, PROC_ADDR_RDY, PROC_ADDR_ERR); - if (status) - goto exit; - /* get the data */ - *data = ql_read32(qdev, PROC_DATA); -exit: - return status; -} - -int ql_write_mpi_reg(struct ql_adapter *qdev, u32 reg, u32 data) -{ - int status = 0; - /* wait for reg to come ready */ - status = ql_wait_reg_rdy(qdev, PROC_ADDR, PROC_ADDR_RDY, PROC_ADDR_ERR); - if (status) - goto exit; - /* write the data to the data reg */ - ql_write32(qdev, PROC_DATA, data); - /* trigger the write */ - ql_write32(qdev, PROC_ADDR, reg); - /* wait for reg to come ready */ - status = ql_wait_reg_rdy(qdev, PROC_ADDR, PROC_ADDR_RDY, PROC_ADDR_ERR); - if (status) - goto exit; -exit: - return status; -} - -int ql_soft_reset_mpi_risc(struct ql_adapter *qdev) -{ - int status; - status = ql_write_mpi_reg(qdev, 0x00001010, 1); - return status; -} - -/* Determine if we are in charge of the firwmare. If - * we are the lower of the 2 NIC pcie functions, or if - * we are the higher function and the lower function - * is not enabled. - */ -int ql_own_firmware(struct ql_adapter *qdev) -{ - u32 temp; - - /* If we are the lower of the 2 NIC functions - * on the chip the we are responsible for - * core dump and firmware reset after an error. - */ - if (qdev->func < qdev->alt_func) - return 1; - - /* If we are the higher of the 2 NIC functions - * on the chip and the lower function is not - * enabled, then we are responsible for - * core dump and firmware reset after an error. - */ - temp = ql_read32(qdev, STS); - if (!(temp & (1 << (8 + qdev->alt_func)))) - return 1; - - return 0; - -} - -static int ql_get_mb_sts(struct ql_adapter *qdev, struct mbox_params *mbcp) -{ - int i, status; - - status = ql_sem_spinlock(qdev, SEM_PROC_REG_MASK); - if (status) - return -EBUSY; - for (i = 0; i < mbcp->out_count; i++) { - status = - ql_read_mpi_reg(qdev, qdev->mailbox_out + i, - &mbcp->mbox_out[i]); - if (status) { - netif_err(qdev, drv, qdev->ndev, "Failed mailbox read.\n"); - break; - } - } - ql_sem_unlock(qdev, SEM_PROC_REG_MASK); /* does flush too */ - return status; -} - -/* Wait for a single mailbox command to complete. - * Returns zero on success. - */ -static int ql_wait_mbx_cmd_cmplt(struct ql_adapter *qdev) -{ - int count = 100; - u32 value; - - do { - value = ql_read32(qdev, STS); - if (value & STS_PI) - return 0; - mdelay(UDELAY_DELAY); /* 100ms */ - } while (--count); - return -ETIMEDOUT; -} - -/* Execute a single mailbox command. - * Caller must hold PROC_ADDR semaphore. - */ -static int ql_exec_mb_cmd(struct ql_adapter *qdev, struct mbox_params *mbcp) -{ - int i, status; - - /* - * Make sure there's nothing pending. - * This shouldn't happen. - */ - if (ql_read32(qdev, CSR) & CSR_HRI) - return -EIO; - - status = ql_sem_spinlock(qdev, SEM_PROC_REG_MASK); - if (status) - return status; - - /* - * Fill the outbound mailboxes. - */ - for (i = 0; i < mbcp->in_count; i++) { - status = ql_write_mpi_reg(qdev, qdev->mailbox_in + i, - mbcp->mbox_in[i]); - if (status) - goto end; - } - /* - * Wake up the MPI firmware. - */ - ql_write32(qdev, CSR, CSR_CMD_SET_H2R_INT); -end: - ql_sem_unlock(qdev, SEM_PROC_REG_MASK); - return status; -} - -/* We are being asked by firmware to accept - * a change to the port. This is only - * a change to max frame sizes (Tx/Rx), pause - * parameters, or loopback mode. We wake up a worker - * to handler processing this since a mailbox command - * will need to be sent to ACK the request. - */ -static int ql_idc_req_aen(struct ql_adapter *qdev) -{ - int status; - struct mbox_params *mbcp = &qdev->idc_mbc; - - netif_err(qdev, drv, qdev->ndev, "Enter!\n"); - /* Get the status data and start up a thread to - * handle the request. - */ - mbcp->out_count = 4; - status = ql_get_mb_sts(qdev, mbcp); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Could not read MPI, resetting ASIC!\n"); - ql_queue_asic_error(qdev); - } else { - /* Begin polled mode early so - * we don't get another interrupt - * when we leave mpi_worker. - */ - ql_write32(qdev, INTR_MASK, (INTR_MASK_PI << 16)); - queue_delayed_work(qdev->workqueue, &qdev->mpi_idc_work, 0); - } - return status; -} - -/* Process an inter-device event completion. - * If good, signal the caller's completion. - */ -static int ql_idc_cmplt_aen(struct ql_adapter *qdev) -{ - int status; - struct mbox_params *mbcp = &qdev->idc_mbc; - mbcp->out_count = 4; - status = ql_get_mb_sts(qdev, mbcp); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Could not read MPI, resetting RISC!\n"); - ql_queue_fw_error(qdev); - } else - /* Wake up the sleeping mpi_idc_work thread that is - * waiting for this event. - */ - complete(&qdev->ide_completion); - - return status; -} - -static void ql_link_up(struct ql_adapter *qdev, struct mbox_params *mbcp) -{ - int status; - mbcp->out_count = 2; - - status = ql_get_mb_sts(qdev, mbcp); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "%s: Could not get mailbox status.\n", __func__); - return; - } - - qdev->link_status = mbcp->mbox_out[1]; - netif_err(qdev, drv, qdev->ndev, "Link Up.\n"); - - /* If we're coming back from an IDC event - * then set up the CAM and frame routing. - */ - if (test_bit(QL_CAM_RT_SET, &qdev->flags)) { - status = ql_cam_route_initialize(qdev); - if (status) { - netif_err(qdev, ifup, qdev->ndev, - "Failed to init CAM/Routing tables.\n"); - return; - } else - clear_bit(QL_CAM_RT_SET, &qdev->flags); - } - - /* Queue up a worker to check the frame - * size information, and fix it if it's not - * to our liking. - */ - if (!test_bit(QL_PORT_CFG, &qdev->flags)) { - netif_err(qdev, drv, qdev->ndev, "Queue Port Config Worker!\n"); - set_bit(QL_PORT_CFG, &qdev->flags); - /* Begin polled mode early so - * we don't get another interrupt - * when we leave mpi_worker dpc. - */ - ql_write32(qdev, INTR_MASK, (INTR_MASK_PI << 16)); - queue_delayed_work(qdev->workqueue, - &qdev->mpi_port_cfg_work, 0); - } - - ql_link_on(qdev); -} - -static void ql_link_down(struct ql_adapter *qdev, struct mbox_params *mbcp) -{ - int status; - - mbcp->out_count = 3; - - status = ql_get_mb_sts(qdev, mbcp); - if (status) - netif_err(qdev, drv, qdev->ndev, "Link down AEN broken!\n"); - - ql_link_off(qdev); -} - -static int ql_sfp_in(struct ql_adapter *qdev, struct mbox_params *mbcp) -{ - int status; - - mbcp->out_count = 5; - - status = ql_get_mb_sts(qdev, mbcp); - if (status) - netif_err(qdev, drv, qdev->ndev, "SFP in AEN broken!\n"); - else - netif_err(qdev, drv, qdev->ndev, "SFP insertion detected.\n"); - - return status; -} - -static int ql_sfp_out(struct ql_adapter *qdev, struct mbox_params *mbcp) -{ - int status; - - mbcp->out_count = 1; - - status = ql_get_mb_sts(qdev, mbcp); - if (status) - netif_err(qdev, drv, qdev->ndev, "SFP out AEN broken!\n"); - else - netif_err(qdev, drv, qdev->ndev, "SFP removal detected.\n"); - - return status; -} - -static int ql_aen_lost(struct ql_adapter *qdev, struct mbox_params *mbcp) -{ - int status; - - mbcp->out_count = 6; - - status = ql_get_mb_sts(qdev, mbcp); - if (status) - netif_err(qdev, drv, qdev->ndev, "Lost AEN broken!\n"); - else { - int i; - netif_err(qdev, drv, qdev->ndev, "Lost AEN detected.\n"); - for (i = 0; i < mbcp->out_count; i++) - netif_err(qdev, drv, qdev->ndev, "mbox_out[%d] = 0x%.08x.\n", - i, mbcp->mbox_out[i]); - - } - - return status; -} - -static void ql_init_fw_done(struct ql_adapter *qdev, struct mbox_params *mbcp) -{ - int status; - - mbcp->out_count = 2; - - status = ql_get_mb_sts(qdev, mbcp); - if (status) { - netif_err(qdev, drv, qdev->ndev, "Firmware did not initialize!\n"); - } else { - netif_err(qdev, drv, qdev->ndev, "Firmware Revision = 0x%.08x.\n", - mbcp->mbox_out[1]); - qdev->fw_rev_id = mbcp->mbox_out[1]; - status = ql_cam_route_initialize(qdev); - if (status) - netif_err(qdev, ifup, qdev->ndev, - "Failed to init CAM/Routing tables.\n"); - } -} - -/* Process an async event and clear it unless it's an - * error condition. - * This can get called iteratively from the mpi_work thread - * when events arrive via an interrupt. - * It also gets called when a mailbox command is polling for - * it's completion. */ -static int ql_mpi_handler(struct ql_adapter *qdev, struct mbox_params *mbcp) -{ - int status; - int orig_count = mbcp->out_count; - - /* Just get mailbox zero for now. */ - mbcp->out_count = 1; - status = ql_get_mb_sts(qdev, mbcp); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Could not read MPI, resetting ASIC!\n"); - ql_queue_asic_error(qdev); - goto end; - } - - switch (mbcp->mbox_out[0]) { - - /* This case is only active when we arrive here - * as a result of issuing a mailbox command to - * the firmware. - */ - case MB_CMD_STS_INTRMDT: - case MB_CMD_STS_GOOD: - case MB_CMD_STS_INVLD_CMD: - case MB_CMD_STS_XFC_ERR: - case MB_CMD_STS_CSUM_ERR: - case MB_CMD_STS_ERR: - case MB_CMD_STS_PARAM_ERR: - /* We can only get mailbox status if we're polling from an - * unfinished command. Get the rest of the status data and - * return back to the caller. - * We only end up here when we're polling for a mailbox - * command completion. - */ - mbcp->out_count = orig_count; - status = ql_get_mb_sts(qdev, mbcp); - return status; - - /* We are being asked by firmware to accept - * a change to the port. This is only - * a change to max frame sizes (Tx/Rx), pause - * parameters, or loopback mode. - */ - case AEN_IDC_REQ: - status = ql_idc_req_aen(qdev); - break; - - /* Process and inbound IDC event. - * This will happen when we're trying to - * change tx/rx max frame size, change pause - * parameters or loopback mode. - */ - case AEN_IDC_CMPLT: - case AEN_IDC_EXT: - status = ql_idc_cmplt_aen(qdev); - break; - - case AEN_LINK_UP: - ql_link_up(qdev, mbcp); - break; - - case AEN_LINK_DOWN: - ql_link_down(qdev, mbcp); - break; - - case AEN_FW_INIT_DONE: - /* If we're in process on executing the firmware, - * then convert the status to normal mailbox status. - */ - if (mbcp->mbox_in[0] == MB_CMD_EX_FW) { - mbcp->out_count = orig_count; - status = ql_get_mb_sts(qdev, mbcp); - mbcp->mbox_out[0] = MB_CMD_STS_GOOD; - return status; - } - ql_init_fw_done(qdev, mbcp); - break; - - case AEN_AEN_SFP_IN: - ql_sfp_in(qdev, mbcp); - break; - - case AEN_AEN_SFP_OUT: - ql_sfp_out(qdev, mbcp); - break; - - /* This event can arrive at boot time or after an - * MPI reset if the firmware failed to initialize. - */ - case AEN_FW_INIT_FAIL: - /* If we're in process on executing the firmware, - * then convert the status to normal mailbox status. - */ - if (mbcp->mbox_in[0] == MB_CMD_EX_FW) { - mbcp->out_count = orig_count; - status = ql_get_mb_sts(qdev, mbcp); - mbcp->mbox_out[0] = MB_CMD_STS_ERR; - return status; - } - netif_err(qdev, drv, qdev->ndev, - "Firmware initialization failed.\n"); - status = -EIO; - ql_queue_fw_error(qdev); - break; - - case AEN_SYS_ERR: - netif_err(qdev, drv, qdev->ndev, "System Error.\n"); - ql_queue_fw_error(qdev); - status = -EIO; - break; - - case AEN_AEN_LOST: - ql_aen_lost(qdev, mbcp); - break; - - case AEN_DCBX_CHG: - /* Need to support AEN 8110 */ - break; - default: - netif_err(qdev, drv, qdev->ndev, - "Unsupported AE %.08x.\n", mbcp->mbox_out[0]); - /* Clear the MPI firmware status. */ - } -end: - ql_write32(qdev, CSR, CSR_CMD_CLR_R2PCI_INT); - /* Restore the original mailbox count to - * what the caller asked for. This can get - * changed when a mailbox command is waiting - * for a response and an AEN arrives and - * is handled. - * */ - mbcp->out_count = orig_count; - return status; -} - -/* Execute a single mailbox command. - * mbcp is a pointer to an array of u32. Each - * element in the array contains the value for it's - * respective mailbox register. - */ -static int ql_mailbox_command(struct ql_adapter *qdev, struct mbox_params *mbcp) -{ - int status; - unsigned long count; - - mutex_lock(&qdev->mpi_mutex); - - /* Begin polled mode for MPI */ - ql_write32(qdev, INTR_MASK, (INTR_MASK_PI << 16)); - - /* Load the mailbox registers and wake up MPI RISC. */ - status = ql_exec_mb_cmd(qdev, mbcp); - if (status) - goto end; - - - /* If we're generating a system error, then there's nothing - * to wait for. - */ - if (mbcp->mbox_in[0] == MB_CMD_MAKE_SYS_ERR) - goto end; - - /* Wait for the command to complete. We loop - * here because some AEN might arrive while - * we're waiting for the mailbox command to - * complete. If more than 5 seconds expire we can - * assume something is wrong. */ - count = jiffies + HZ * MAILBOX_TIMEOUT; - do { - /* Wait for the interrupt to come in. */ - status = ql_wait_mbx_cmd_cmplt(qdev); - if (status) - continue; - - /* Process the event. If it's an AEN, it - * will be handled in-line or a worker - * will be spawned. If it's our completion - * we will catch it below. - */ - status = ql_mpi_handler(qdev, mbcp); - if (status) - goto end; - - /* It's either the completion for our mailbox - * command complete or an AEN. If it's our - * completion then get out. - */ - if (((mbcp->mbox_out[0] & 0x0000f000) == - MB_CMD_STS_GOOD) || - ((mbcp->mbox_out[0] & 0x0000f000) == - MB_CMD_STS_INTRMDT)) - goto done; - } while (time_before(jiffies, count)); - - netif_err(qdev, drv, qdev->ndev, - "Timed out waiting for mailbox complete.\n"); - status = -ETIMEDOUT; - goto end; - -done: - - /* Now we can clear the interrupt condition - * and look at our status. - */ - ql_write32(qdev, CSR, CSR_CMD_CLR_R2PCI_INT); - - if (((mbcp->mbox_out[0] & 0x0000f000) != - MB_CMD_STS_GOOD) && - ((mbcp->mbox_out[0] & 0x0000f000) != - MB_CMD_STS_INTRMDT)) { - status = -EIO; - } -end: - /* End polled mode for MPI */ - ql_write32(qdev, INTR_MASK, (INTR_MASK_PI << 16) | INTR_MASK_PI); - mutex_unlock(&qdev->mpi_mutex); - return status; -} - -/* Get MPI firmware version. This will be used for - * driver banner and for ethtool info. - * Returns zero on success. - */ -int ql_mb_about_fw(struct ql_adapter *qdev) -{ - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int status = 0; - - memset(mbcp, 0, sizeof(struct mbox_params)); - - mbcp->in_count = 1; - mbcp->out_count = 3; - - mbcp->mbox_in[0] = MB_CMD_ABOUT_FW; - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] != MB_CMD_STS_GOOD) { - netif_err(qdev, drv, qdev->ndev, - "Failed about firmware command\n"); - status = -EIO; - } - - /* Store the firmware version */ - qdev->fw_rev_id = mbcp->mbox_out[1]; - - return status; -} - -/* Get functional state for MPI firmware. - * Returns zero on success. - */ -int ql_mb_get_fw_state(struct ql_adapter *qdev) -{ - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int status = 0; - - memset(mbcp, 0, sizeof(struct mbox_params)); - - mbcp->in_count = 1; - mbcp->out_count = 2; - - mbcp->mbox_in[0] = MB_CMD_GET_FW_STATE; - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] != MB_CMD_STS_GOOD) { - netif_err(qdev, drv, qdev->ndev, - "Failed Get Firmware State.\n"); - status = -EIO; - } - - /* If bit zero is set in mbx 1 then the firmware is - * running, but not initialized. This should never - * happen. - */ - if (mbcp->mbox_out[1] & 1) { - netif_err(qdev, drv, qdev->ndev, - "Firmware waiting for initialization.\n"); - status = -EIO; - } - - return status; -} - -/* Send and ACK mailbox command to the firmware to - * let it continue with the change. - */ -static int ql_mb_idc_ack(struct ql_adapter *qdev) -{ - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int status = 0; - - memset(mbcp, 0, sizeof(struct mbox_params)); - - mbcp->in_count = 5; - mbcp->out_count = 1; - - mbcp->mbox_in[0] = MB_CMD_IDC_ACK; - mbcp->mbox_in[1] = qdev->idc_mbc.mbox_out[1]; - mbcp->mbox_in[2] = qdev->idc_mbc.mbox_out[2]; - mbcp->mbox_in[3] = qdev->idc_mbc.mbox_out[3]; - mbcp->mbox_in[4] = qdev->idc_mbc.mbox_out[4]; - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] != MB_CMD_STS_GOOD) { - netif_err(qdev, drv, qdev->ndev, "Failed IDC ACK send.\n"); - status = -EIO; - } - return status; -} - -/* Get link settings and maximum frame size settings - * for the current port. - * Most likely will block. - */ -int ql_mb_set_port_cfg(struct ql_adapter *qdev) -{ - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int status = 0; - - memset(mbcp, 0, sizeof(struct mbox_params)); - - mbcp->in_count = 3; - mbcp->out_count = 1; - - mbcp->mbox_in[0] = MB_CMD_SET_PORT_CFG; - mbcp->mbox_in[1] = qdev->link_config; - mbcp->mbox_in[2] = qdev->max_frame_size; - - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] == MB_CMD_STS_INTRMDT) { - netif_err(qdev, drv, qdev->ndev, - "Port Config sent, wait for IDC.\n"); - } else if (mbcp->mbox_out[0] != MB_CMD_STS_GOOD) { - netif_err(qdev, drv, qdev->ndev, - "Failed Set Port Configuration.\n"); - status = -EIO; - } - return status; -} - -static int ql_mb_dump_ram(struct ql_adapter *qdev, u64 req_dma, u32 addr, - u32 size) -{ - int status = 0; - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - - memset(mbcp, 0, sizeof(struct mbox_params)); - - mbcp->in_count = 9; - mbcp->out_count = 1; - - mbcp->mbox_in[0] = MB_CMD_DUMP_RISC_RAM; - mbcp->mbox_in[1] = LSW(addr); - mbcp->mbox_in[2] = MSW(req_dma); - mbcp->mbox_in[3] = LSW(req_dma); - mbcp->mbox_in[4] = MSW(size); - mbcp->mbox_in[5] = LSW(size); - mbcp->mbox_in[6] = MSW(MSD(req_dma)); - mbcp->mbox_in[7] = LSW(MSD(req_dma)); - mbcp->mbox_in[8] = MSW(addr); - - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] != MB_CMD_STS_GOOD) { - netif_err(qdev, drv, qdev->ndev, "Failed to dump risc RAM.\n"); - status = -EIO; - } - return status; -} - -/* Issue a mailbox command to dump RISC RAM. */ -int ql_dump_risc_ram_area(struct ql_adapter *qdev, void *buf, - u32 ram_addr, int word_count) -{ - int status; - char *my_buf; - dma_addr_t buf_dma; - - my_buf = pci_alloc_consistent(qdev->pdev, word_count * sizeof(u32), - &buf_dma); - if (!my_buf) - return -EIO; - - status = ql_mb_dump_ram(qdev, buf_dma, ram_addr, word_count); - if (!status) - memcpy(buf, my_buf, word_count * sizeof(u32)); - - pci_free_consistent(qdev->pdev, word_count * sizeof(u32), my_buf, - buf_dma); - return status; -} - -/* Get link settings and maximum frame size settings - * for the current port. - * Most likely will block. - */ -int ql_mb_get_port_cfg(struct ql_adapter *qdev) -{ - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int status = 0; - - memset(mbcp, 0, sizeof(struct mbox_params)); - - mbcp->in_count = 1; - mbcp->out_count = 3; - - mbcp->mbox_in[0] = MB_CMD_GET_PORT_CFG; - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] != MB_CMD_STS_GOOD) { - netif_err(qdev, drv, qdev->ndev, - "Failed Get Port Configuration.\n"); - status = -EIO; - } else { - netif_printk(qdev, drv, KERN_DEBUG, qdev->ndev, - "Passed Get Port Configuration.\n"); - qdev->link_config = mbcp->mbox_out[1]; - qdev->max_frame_size = mbcp->mbox_out[2]; - } - return status; -} - -int ql_mb_wol_mode(struct ql_adapter *qdev, u32 wol) -{ - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int status; - - memset(mbcp, 0, sizeof(struct mbox_params)); - - mbcp->in_count = 2; - mbcp->out_count = 1; - - mbcp->mbox_in[0] = MB_CMD_SET_WOL_MODE; - mbcp->mbox_in[1] = wol; - - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] != MB_CMD_STS_GOOD) { - netif_err(qdev, drv, qdev->ndev, "Failed to set WOL mode.\n"); - status = -EIO; - } - return status; -} - -int ql_mb_wol_set_magic(struct ql_adapter *qdev, u32 enable_wol) -{ - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int status; - u8 *addr = qdev->ndev->dev_addr; - - memset(mbcp, 0, sizeof(struct mbox_params)); - - mbcp->in_count = 8; - mbcp->out_count = 1; - - mbcp->mbox_in[0] = MB_CMD_SET_WOL_MAGIC; - if (enable_wol) { - mbcp->mbox_in[1] = (u32)addr[0]; - mbcp->mbox_in[2] = (u32)addr[1]; - mbcp->mbox_in[3] = (u32)addr[2]; - mbcp->mbox_in[4] = (u32)addr[3]; - mbcp->mbox_in[5] = (u32)addr[4]; - mbcp->mbox_in[6] = (u32)addr[5]; - mbcp->mbox_in[7] = 0; - } else { - mbcp->mbox_in[1] = 0; - mbcp->mbox_in[2] = 1; - mbcp->mbox_in[3] = 1; - mbcp->mbox_in[4] = 1; - mbcp->mbox_in[5] = 1; - mbcp->mbox_in[6] = 1; - mbcp->mbox_in[7] = 0; - } - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] != MB_CMD_STS_GOOD) { - netif_err(qdev, drv, qdev->ndev, "Failed to set WOL mode.\n"); - status = -EIO; - } - return status; -} - -/* IDC - Inter Device Communication... - * Some firmware commands require consent of adjacent FCOE - * function. This function waits for the OK, or a - * counter-request for a little more time.i - * The firmware will complete the request if the other - * function doesn't respond. - */ -static int ql_idc_wait(struct ql_adapter *qdev) -{ - int status = -ETIMEDOUT; - long wait_time = 1 * HZ; - struct mbox_params *mbcp = &qdev->idc_mbc; - do { - /* Wait here for the command to complete - * via the IDC process. - */ - wait_time = - wait_for_completion_timeout(&qdev->ide_completion, - wait_time); - if (!wait_time) { - netif_err(qdev, drv, qdev->ndev, "IDC Timeout.\n"); - break; - } - /* Now examine the response from the IDC process. - * We might have a good completion or a request for - * more wait time. - */ - if (mbcp->mbox_out[0] == AEN_IDC_EXT) { - netif_err(qdev, drv, qdev->ndev, - "IDC Time Extension from function.\n"); - wait_time += (mbcp->mbox_out[1] >> 8) & 0x0000000f; - } else if (mbcp->mbox_out[0] == AEN_IDC_CMPLT) { - netif_err(qdev, drv, qdev->ndev, "IDC Success.\n"); - status = 0; - break; - } else { - netif_err(qdev, drv, qdev->ndev, - "IDC: Invalid State 0x%.04x.\n", - mbcp->mbox_out[0]); - status = -EIO; - break; - } - } while (wait_time); - - return status; -} - -int ql_mb_set_led_cfg(struct ql_adapter *qdev, u32 led_config) -{ - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int status; - - memset(mbcp, 0, sizeof(struct mbox_params)); - - mbcp->in_count = 2; - mbcp->out_count = 1; - - mbcp->mbox_in[0] = MB_CMD_SET_LED_CFG; - mbcp->mbox_in[1] = led_config; - - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] != MB_CMD_STS_GOOD) { - netif_err(qdev, drv, qdev->ndev, - "Failed to set LED Configuration.\n"); - status = -EIO; - } - - return status; -} - -int ql_mb_get_led_cfg(struct ql_adapter *qdev) -{ - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int status; - - memset(mbcp, 0, sizeof(struct mbox_params)); - - mbcp->in_count = 1; - mbcp->out_count = 2; - - mbcp->mbox_in[0] = MB_CMD_GET_LED_CFG; - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] != MB_CMD_STS_GOOD) { - netif_err(qdev, drv, qdev->ndev, - "Failed to get LED Configuration.\n"); - status = -EIO; - } else - qdev->led_config = mbcp->mbox_out[1]; - - return status; -} - -int ql_mb_set_mgmnt_traffic_ctl(struct ql_adapter *qdev, u32 control) -{ - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int status; - - memset(mbcp, 0, sizeof(struct mbox_params)); - - mbcp->in_count = 1; - mbcp->out_count = 2; - - mbcp->mbox_in[0] = MB_CMD_SET_MGMNT_TFK_CTL; - mbcp->mbox_in[1] = control; - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] == MB_CMD_STS_GOOD) - return status; - - if (mbcp->mbox_out[0] == MB_CMD_STS_INVLD_CMD) { - netif_err(qdev, drv, qdev->ndev, - "Command not supported by firmware.\n"); - status = -EINVAL; - } else if (mbcp->mbox_out[0] == MB_CMD_STS_ERR) { - /* This indicates that the firmware is - * already in the state we are trying to - * change it to. - */ - netif_err(qdev, drv, qdev->ndev, - "Command parameters make no change.\n"); - } - return status; -} - -/* Returns a negative error code or the mailbox command status. */ -static int ql_mb_get_mgmnt_traffic_ctl(struct ql_adapter *qdev, u32 *control) -{ - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int status; - - memset(mbcp, 0, sizeof(struct mbox_params)); - *control = 0; - - mbcp->in_count = 1; - mbcp->out_count = 1; - - mbcp->mbox_in[0] = MB_CMD_GET_MGMNT_TFK_CTL; - - status = ql_mailbox_command(qdev, mbcp); - if (status) - return status; - - if (mbcp->mbox_out[0] == MB_CMD_STS_GOOD) { - *control = mbcp->mbox_in[1]; - return status; - } - - if (mbcp->mbox_out[0] == MB_CMD_STS_INVLD_CMD) { - netif_err(qdev, drv, qdev->ndev, - "Command not supported by firmware.\n"); - status = -EINVAL; - } else if (mbcp->mbox_out[0] == MB_CMD_STS_ERR) { - netif_err(qdev, drv, qdev->ndev, - "Failed to get MPI traffic control.\n"); - status = -EIO; - } - return status; -} - -int ql_wait_fifo_empty(struct ql_adapter *qdev) -{ - int count = 5; - u32 mgmnt_fifo_empty; - u32 nic_fifo_empty; - - do { - nic_fifo_empty = ql_read32(qdev, STS) & STS_NFE; - ql_mb_get_mgmnt_traffic_ctl(qdev, &mgmnt_fifo_empty); - mgmnt_fifo_empty &= MB_GET_MPI_TFK_FIFO_EMPTY; - if (nic_fifo_empty && mgmnt_fifo_empty) - return 0; - msleep(100); - } while (count-- > 0); - return -ETIMEDOUT; -} - -/* API called in work thread context to set new TX/RX - * maximum frame size values to match MTU. - */ -static int ql_set_port_cfg(struct ql_adapter *qdev) -{ - int status; - status = ql_mb_set_port_cfg(qdev); - if (status) - return status; - status = ql_idc_wait(qdev); - return status; -} - -/* The following routines are worker threads that process - * events that may sleep waiting for completion. - */ - -/* This thread gets the maximum TX and RX frame size values - * from the firmware and, if necessary, changes them to match - * the MTU setting. - */ -void ql_mpi_port_cfg_work(struct work_struct *work) -{ - struct ql_adapter *qdev = - container_of(work, struct ql_adapter, mpi_port_cfg_work.work); - int status; - - status = ql_mb_get_port_cfg(qdev); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Bug: Failed to get port config data.\n"); - goto err; - } - - if (qdev->link_config & CFG_JUMBO_FRAME_SIZE && - qdev->max_frame_size == - CFG_DEFAULT_MAX_FRAME_SIZE) - goto end; - - qdev->link_config |= CFG_JUMBO_FRAME_SIZE; - qdev->max_frame_size = CFG_DEFAULT_MAX_FRAME_SIZE; - status = ql_set_port_cfg(qdev); - if (status) { - netif_err(qdev, drv, qdev->ndev, - "Bug: Failed to set port config data.\n"); - goto err; - } -end: - clear_bit(QL_PORT_CFG, &qdev->flags); - return; -err: - ql_queue_fw_error(qdev); - goto end; -} - -/* Process an inter-device request. This is issues by - * the firmware in response to another function requesting - * a change to the port. We set a flag to indicate a change - * has been made and then send a mailbox command ACKing - * the change request. - */ -void ql_mpi_idc_work(struct work_struct *work) -{ - struct ql_adapter *qdev = - container_of(work, struct ql_adapter, mpi_idc_work.work); - int status; - struct mbox_params *mbcp = &qdev->idc_mbc; - u32 aen; - int timeout; - - aen = mbcp->mbox_out[1] >> 16; - timeout = (mbcp->mbox_out[1] >> 8) & 0xf; - - switch (aen) { - default: - netif_err(qdev, drv, qdev->ndev, - "Bug: Unhandled IDC action.\n"); - break; - case MB_CMD_PORT_RESET: - case MB_CMD_STOP_FW: - ql_link_off(qdev); - /* Fall through */ - case MB_CMD_SET_PORT_CFG: - /* Signal the resulting link up AEN - * that the frame routing and mac addr - * needs to be set. - * */ - set_bit(QL_CAM_RT_SET, &qdev->flags); - /* Do ACK if required */ - if (timeout) { - status = ql_mb_idc_ack(qdev); - if (status) - netif_err(qdev, drv, qdev->ndev, - "Bug: No pending IDC!\n"); - } else { - netif_printk(qdev, drv, KERN_DEBUG, qdev->ndev, - "IDC ACK not required\n"); - status = 0; /* success */ - } - break; - - /* These sub-commands issued by another (FCoE) - * function are requesting to do an operation - * on the shared resource (MPI environment). - * We currently don't issue these so we just - * ACK the request. - */ - case MB_CMD_IOP_RESTART_MPI: - case MB_CMD_IOP_PREP_LINK_DOWN: - /* Drop the link, reload the routing - * table when link comes up. - */ - ql_link_off(qdev); - set_bit(QL_CAM_RT_SET, &qdev->flags); - /* Fall through. */ - case MB_CMD_IOP_DVR_START: - case MB_CMD_IOP_FLASH_ACC: - case MB_CMD_IOP_CORE_DUMP_MPI: - case MB_CMD_IOP_PREP_UPDATE_MPI: - case MB_CMD_IOP_COMP_UPDATE_MPI: - case MB_CMD_IOP_NONE: /* an IDC without params */ - /* Do ACK if required */ - if (timeout) { - status = ql_mb_idc_ack(qdev); - if (status) - netif_err(qdev, drv, qdev->ndev, - "Bug: No pending IDC!\n"); - } else { - netif_printk(qdev, drv, KERN_DEBUG, qdev->ndev, - "IDC ACK not required\n"); - status = 0; /* success */ - } - break; - } -} - -void ql_mpi_work(struct work_struct *work) -{ - struct ql_adapter *qdev = - container_of(work, struct ql_adapter, mpi_work.work); - struct mbox_params mbc; - struct mbox_params *mbcp = &mbc; - int err = 0; - - mutex_lock(&qdev->mpi_mutex); - /* Begin polled mode for MPI */ - ql_write32(qdev, INTR_MASK, (INTR_MASK_PI << 16)); - - while (ql_read32(qdev, STS) & STS_PI) { - memset(mbcp, 0, sizeof(struct mbox_params)); - mbcp->out_count = 1; - /* Don't continue if an async event - * did not complete properly. - */ - err = ql_mpi_handler(qdev, mbcp); - if (err) - break; - } - - /* End polled mode for MPI */ - ql_write32(qdev, INTR_MASK, (INTR_MASK_PI << 16) | INTR_MASK_PI); - mutex_unlock(&qdev->mpi_mutex); - ql_enable_completion_interrupt(qdev, 0); -} - -void ql_mpi_reset_work(struct work_struct *work) -{ - struct ql_adapter *qdev = - container_of(work, struct ql_adapter, mpi_reset_work.work); - cancel_delayed_work_sync(&qdev->mpi_work); - cancel_delayed_work_sync(&qdev->mpi_port_cfg_work); - cancel_delayed_work_sync(&qdev->mpi_idc_work); - /* If we're not the dominant NIC function, - * then there is nothing to do. - */ - if (!ql_own_firmware(qdev)) { - netif_err(qdev, drv, qdev->ndev, "Don't own firmware!\n"); - return; - } - - if (qdev->mpi_coredump && !ql_core_dump(qdev, qdev->mpi_coredump)) { - netif_err(qdev, drv, qdev->ndev, "Core is dumped!\n"); - qdev->core_is_dumped = 1; - queue_delayed_work(qdev->workqueue, - &qdev->mpi_core_to_log, 5 * HZ); - } - ql_soft_reset_mpi_risc(qdev); -} diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 707665b62eb7..bebe38d74d66 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -1385,15 +1385,13 @@ static void emac_tx_fill_tpd(struct emac_adapter *adpt, } for (i = 0; i < nr_frags; i++) { - struct skb_frag_struct *frag; - - frag = &skb_shinfo(skb)->frags[i]; + skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; tpbuf = GET_TPD_BUFFER(tx_q, tx_q->tpd.produce_idx); - tpbuf->length = frag->size; - tpbuf->dma_addr = dma_map_page(adpt->netdev->dev.parent, - frag->page.p, frag->page_offset, - tpbuf->length, DMA_TO_DEVICE); + tpbuf->length = skb_frag_size(frag); + tpbuf->dma_addr = skb_frag_dma_map(adpt->netdev->dev.parent, + frag, 0, tpbuf->length, + DMA_TO_DEVICE); ret = dma_mapping_error(adpt->netdev->dev.parent, tpbuf->dma_addr); if (ret) diff --git a/drivers/net/ethernet/qualcomm/emac/emac.c b/drivers/net/ethernet/qualcomm/emac/emac.c index 59c2349b59df..c84ab052ef26 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac.c @@ -544,7 +544,6 @@ static int emac_probe_resources(struct platform_device *pdev, struct emac_adapter *adpt) { struct net_device *netdev = adpt->netdev; - struct resource *res; char maddr[ETH_ALEN]; int ret = 0; @@ -556,22 +555,17 @@ static int emac_probe_resources(struct platform_device *pdev, /* Core 0 interrupt */ ret = platform_get_irq(pdev, 0); - if (ret < 0) { - dev_err(&pdev->dev, - "error: missing core0 irq resource (error=%i)\n", ret); + if (ret < 0) return ret; - } adpt->irq.irq = ret; /* base register address */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - adpt->base = devm_ioremap_resource(&pdev->dev, res); + adpt->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(adpt->base)) return PTR_ERR(adpt->base); /* CSR register address */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - adpt->csr = devm_ioremap_resource(&pdev->dev, res); + adpt->csr = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(adpt->csr)) return PTR_ERR(adpt->csr); diff --git a/drivers/net/ethernet/qualcomm/qca_debug.c b/drivers/net/ethernet/qualcomm/qca_debug.c index bcb890b18a94..702aa217a27a 100644 --- a/drivers/net/ethernet/qualcomm/qca_debug.c +++ b/drivers/net/ethernet/qualcomm/qca_debug.c @@ -131,17 +131,10 @@ DEFINE_SHOW_ATTRIBUTE(qcaspi_info); void qcaspi_init_device_debugfs(struct qcaspi *qca) { - struct dentry *device_root; + qca->device_root = debugfs_create_dir(dev_name(&qca->net_dev->dev), + NULL); - device_root = debugfs_create_dir(dev_name(&qca->net_dev->dev), NULL); - qca->device_root = device_root; - - if (IS_ERR(device_root) || !device_root) { - pr_warn("failed to create debugfs directory for %s\n", - dev_name(&qca->net_dev->dev)); - return; - } - debugfs_create_file("info", S_IFREG | 0444, device_root, qca, + debugfs_create_file("info", S_IFREG | 0444, qca->device_root, qca, &qcaspi_info_fops); } diff --git a/drivers/net/ethernet/qualcomm/qca_spi.c b/drivers/net/ethernet/qualcomm/qca_spi.c index b28360bc2255..5ecf61df78bd 100644 --- a/drivers/net/ethernet/qualcomm/qca_spi.c +++ b/drivers/net/ethernet/qualcomm/qca_spi.c @@ -837,8 +837,7 @@ qcaspi_netdev_uninit(struct net_device *dev) kfree(qca->rx_buffer); qca->buffer_size = 0; - if (qca->rx_skb) - dev_kfree_skb(qca->rx_skb); + dev_kfree_skb(qca->rx_skb); } static const struct net_device_ops qcaspi_netdev_ops = { diff --git a/drivers/net/ethernet/qualcomm/qca_uart.c b/drivers/net/ethernet/qualcomm/qca_uart.c index 590616846cd1..0981068504fa 100644 --- a/drivers/net/ethernet/qualcomm/qca_uart.c +++ b/drivers/net/ethernet/qualcomm/qca_uart.c @@ -285,8 +285,7 @@ static void qcauart_netdev_uninit(struct net_device *dev) { struct qcauart *qca = netdev_priv(dev); - if (qca->rx_skb) - dev_kfree_skb(qca->rx_skb); + dev_kfree_skb(qca->rx_skb); } static const struct net_device_ops qcauart_netdev_ops = { diff --git a/drivers/net/ethernet/realtek/Kconfig b/drivers/net/ethernet/realtek/Kconfig index b18e7a91d5cd..5e0b9d2f14f7 100644 --- a/drivers/net/ethernet/realtek/Kconfig +++ b/drivers/net/ethernet/realtek/Kconfig @@ -96,14 +96,19 @@ config 8139_OLD_RX_RESET old RX-reset behavior. If unsure, say N. config R8169 - tristate "Realtek 8169 gigabit ethernet support" + tristate "Realtek 8169/8168/8101/8125 ethernet support" depends on PCI select FW_LOADER select CRC32 select PHYLIB select REALTEK_PHY ---help--- - Say Y here if you have a Realtek 8169 PCI Gigabit Ethernet adapter. + Say Y here if you have a Realtek Ethernet adapter belonging to + the following families: + RTL8169 Gigabit Ethernet + RTL8168 Gigabit Ethernet + RTL8101 Fast Ethernet + RTL8125 2.5GBit Ethernet To compile this driver as a module, choose M here: the module will be called r8169. This is recommended. diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index bae0074ab9aa..0ef01db1f8b8 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -55,13 +55,14 @@ #define FIRMWARE_8168H_2 "rtl_nic/rtl8168h-2.fw" #define FIRMWARE_8107E_1 "rtl_nic/rtl8107e-1.fw" #define FIRMWARE_8107E_2 "rtl_nic/rtl8107e-2.fw" +#define FIRMWARE_8125A_3 "rtl_nic/rtl8125a-3.fw" #define R8169_MSG_DEFAULT \ (NETIF_MSG_DRV | NETIF_MSG_PROBE | NETIF_MSG_IFUP | NETIF_MSG_IFDOWN) /* Maximum number of multicast addresses to filter (vs. Rx-all-multicast). The RTL chips use a 64 element hash table based on the Ethernet CRC. */ -static const int multicast_filter_limit = 32; +#define MC_FILTER_LIMIT 32 #define TX_DMA_BURST 7 /* Maximum PCI burst, '7' is unlimited */ #define InterFrameGap 0x03 /* 3 means InterFrameGap = the shortest one */ @@ -135,6 +136,8 @@ enum mac_version { RTL_GIGA_MAC_VER_49, RTL_GIGA_MAC_VER_50, RTL_GIGA_MAC_VER_51, + RTL_GIGA_MAC_VER_60, + RTL_GIGA_MAC_VER_61, RTL_GIGA_MAC_NONE }; @@ -200,6 +203,8 @@ static const struct { [RTL_GIGA_MAC_VER_49] = {"RTL8168ep/8111ep" }, [RTL_GIGA_MAC_VER_50] = {"RTL8168ep/8111ep" }, [RTL_GIGA_MAC_VER_51] = {"RTL8168ep/8111ep" }, + [RTL_GIGA_MAC_VER_60] = {"RTL8125" }, + [RTL_GIGA_MAC_VER_61] = {"RTL8125", FIRMWARE_8125A_3}, }; static const struct pci_device_id rtl8169_pci_tbl[] = { @@ -220,6 +225,8 @@ static const struct pci_device_id rtl8169_pci_tbl[] = { { PCI_VDEVICE(USR, 0x0116) }, { PCI_VENDOR_ID_LINKSYS, 0x1032, PCI_ANY_ID, 0x0024 }, { 0x0001, 0x8168, PCI_ANY_ID, 0x2410 }, + { PCI_VDEVICE(REALTEK, 0x8125) }, + { PCI_VDEVICE(REALTEK, 0x3000) }, {} }; @@ -271,7 +278,6 @@ enum rtl_registers { Config3 = 0x54, Config4 = 0x55, Config5 = 0x56, - MultiIntr = 0x5c, PHYAR = 0x60, PHYstatus = 0x6c, RxMaxSize = 0xda, @@ -385,6 +391,19 @@ enum rtl8168_registers { #define EARLY_TALLY_EN (1 << 16) }; +enum rtl8125_registers { + IntrMask_8125 = 0x38, + IntrStatus_8125 = 0x3c, + TxPoll_8125 = 0x90, + MAC0_BKP = 0x19e0, +}; + +#define RX_VLAN_INNER_8125 BIT(22) +#define RX_VLAN_OUTER_8125 BIT(23) +#define RX_VLAN_8125 (RX_VLAN_INNER_8125 | RX_VLAN_OUTER_8125) + +#define RX_FETCH_DFLT_8125 (8 << 27) + enum rtl_register_content { /* InterruptStatusBits */ SYSErr = 0x8000, @@ -539,11 +558,11 @@ enum rtl_tx_desc_bit_1 { TD1_GTSENV4 = (1 << 26), /* Giant Send for IPv4 */ TD1_GTSENV6 = (1 << 25), /* Giant Send for IPv6 */ #define GTTCPHO_SHIFT 18 -#define GTTCPHO_MAX 0x7fU +#define GTTCPHO_MAX 0x7f /* Second doubleword. */ #define TCPHO_SHIFT 18 -#define TCPHO_MAX 0x3ffU +#define TCPHO_MAX 0x3ff #define TD1_MSS_SHIFT 18 /* MSS position (11 bits) */ TD1_IPv6_CS = (1 << 28), /* Calculate IPv6 checksum */ TD1_IPv4_CS = (1 << 29), /* Calculate IPv4 checksum */ @@ -569,6 +588,11 @@ enum rtl_rx_desc_bit { #define RsvdMask 0x3fffc000 +#define RTL_GSO_MAX_SIZE_V1 32000 +#define RTL_GSO_MAX_SEGS_V1 24 +#define RTL_GSO_MAX_SIZE_V2 64000 +#define RTL_GSO_MAX_SEGS_V2 64 + struct TxDesc { __le32 opts1; __le32 opts2; @@ -638,10 +662,10 @@ struct rtl8169_private { struct RxDesc *RxDescArray; /* 256-aligned Rx descriptor ring */ dma_addr_t TxPhyAddr; dma_addr_t RxPhyAddr; - void *Rx_databuff[NUM_RX_DESC]; /* Rx data buffers */ + struct page *Rx_databuff[NUM_RX_DESC]; /* Rx data buffers */ struct ring_info tx_skb[NUM_TX_DESC]; /* Tx data buffers */ u16 cp_cmd; - u16 irq_mask; + u32 irq_mask; struct clk *clk; struct { @@ -691,6 +715,7 @@ MODULE_FIRMWARE(FIRMWARE_8168H_1); MODULE_FIRMWARE(FIRMWARE_8168H_2); MODULE_FIRMWARE(FIRMWARE_8107E_1); MODULE_FIRMWARE(FIRMWARE_8107E_2); +MODULE_FIRMWARE(FIRMWARE_8125A_3); static inline struct device *tp_to_dev(struct rtl8169_private *tp) { @@ -723,12 +748,33 @@ static void rtl_tx_performance_tweak(struct rtl8169_private *tp, u16 force) PCI_EXP_DEVCTL_READRQ, force); } +static bool rtl_is_8125(struct rtl8169_private *tp) +{ + return tp->mac_version >= RTL_GIGA_MAC_VER_60; +} + static bool rtl_is_8168evl_up(struct rtl8169_private *tp) { return tp->mac_version >= RTL_GIGA_MAC_VER_34 && + tp->mac_version != RTL_GIGA_MAC_VER_39 && + tp->mac_version <= RTL_GIGA_MAC_VER_51; +} + +static bool rtl_supports_eee(struct rtl8169_private *tp) +{ + return tp->mac_version >= RTL_GIGA_MAC_VER_34 && + tp->mac_version != RTL_GIGA_MAC_VER_37 && tp->mac_version != RTL_GIGA_MAC_VER_39; } +static void rtl_read_mac_from_reg(struct rtl8169_private *tp, u8 *mac, int reg) +{ + int i; + + for (i = 0; i < ETH_ALEN; i++) + mac[i] = RTL_R8(tp, reg + i); +} + struct rtl_cond { bool (*check)(struct rtl8169_private *); const char *msg; @@ -846,6 +892,14 @@ static u16 r8168_mac_ocp_read(struct rtl8169_private *tp, u32 reg) return RTL_R32(tp, OCPDR); } +static void r8168_mac_ocp_modify(struct rtl8169_private *tp, u32 reg, u16 mask, + u16 set) +{ + u16 data = r8168_mac_ocp_read(tp, reg); + + r8168_mac_ocp_write(tp, reg, (data & ~mask) | set); +} + #define OCP_STD_PHY_BASE 0xa400 static void r8168g_mdio_write(struct rtl8169_private *tp, int reg, int value) @@ -995,7 +1049,7 @@ static void rtl_writephy(struct rtl8169_private *tp, int location, int val) case RTL_GIGA_MAC_VER_31: r8168dp_2_mdio_write(tp, location, val); break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_61: r8168g_mdio_write(tp, location, val); break; default: @@ -1012,7 +1066,7 @@ static int rtl_readphy(struct rtl8169_private *tp, int location) case RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: return r8168dp_2_mdio_read(tp, location); - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_61: return r8168g_mdio_read(tp, location); default: return r8169_mdio_read(tp, location); @@ -1294,14 +1348,28 @@ static u8 rtl8168d_efuse_read(struct rtl8169_private *tp, int reg_addr) RTL_R32(tp, EFUSEAR) & EFUSEAR_DATA_MASK : ~0; } -static void rtl_ack_events(struct rtl8169_private *tp, u16 bits) +static u32 rtl_get_events(struct rtl8169_private *tp) +{ + if (rtl_is_8125(tp)) + return RTL_R32(tp, IntrStatus_8125); + else + return RTL_R16(tp, IntrStatus); +} + +static void rtl_ack_events(struct rtl8169_private *tp, u32 bits) { - RTL_W16(tp, IntrStatus, bits); + if (rtl_is_8125(tp)) + RTL_W32(tp, IntrStatus_8125, bits); + else + RTL_W16(tp, IntrStatus, bits); } static void rtl_irq_disable(struct rtl8169_private *tp) { - RTL_W16(tp, IntrMask, 0); + if (rtl_is_8125(tp)) + RTL_W32(tp, IntrMask_8125, 0); + else + RTL_W16(tp, IntrMask, 0); tp->irq_enabled = 0; } @@ -1312,13 +1380,16 @@ static void rtl_irq_disable(struct rtl8169_private *tp) static void rtl_irq_enable(struct rtl8169_private *tp) { tp->irq_enabled = 1; - RTL_W16(tp, IntrMask, tp->irq_mask); + if (rtl_is_8125(tp)) + RTL_W32(tp, IntrMask_8125, tp->irq_mask); + else + RTL_W16(tp, IntrMask, tp->irq_mask); } static void rtl8169_irq_mask_and_ack(struct rtl8169_private *tp) { rtl_irq_disable(tp); - rtl_ack_events(tp, 0xffff); + rtl_ack_events(tp, 0xffffffff); /* PCI commit */ RTL_R8(tp, ChipCmd); } @@ -1377,7 +1448,6 @@ static void rtl8169_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol) static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) { - unsigned int i, tmp; static const struct { u32 opt; u16 reg; @@ -1390,20 +1460,25 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) { WAKE_ANY, Config5, LanWake }, { WAKE_MAGIC, Config3, MagicPacket } }; + unsigned int i, tmp = ARRAY_SIZE(cfg); u8 options; rtl_unlock_config_regs(tp); if (rtl_is_8168evl_up(tp)) { - tmp = ARRAY_SIZE(cfg) - 1; + tmp--; if (wolopts & WAKE_MAGIC) rtl_eri_set_bits(tp, 0x0dc, ERIAR_MASK_0100, MagicPacket_v2); else rtl_eri_clear_bits(tp, 0x0dc, ERIAR_MASK_0100, MagicPacket_v2); - } else { - tmp = ARRAY_SIZE(cfg); + } else if (rtl_is_8125(tp)) { + tmp--; + if (wolopts & WAKE_MAGIC) + r8168_mac_ocp_modify(tp, 0xc0b6, 0, BIT(0)); + else + r8168_mac_ocp_modify(tp, 0xc0b6, BIT(0), 0); } for (i = 0; i < tmp; i++) { @@ -1414,18 +1489,22 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) } switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_17: + case RTL_GIGA_MAC_VER_02 ... RTL_GIGA_MAC_VER_06: options = RTL_R8(tp, Config1) & ~PMEnable; if (wolopts) options |= PMEnable; RTL_W8(tp, Config1, options); break; - default: + case RTL_GIGA_MAC_VER_34: + case RTL_GIGA_MAC_VER_37: + case RTL_GIGA_MAC_VER_39 ... RTL_GIGA_MAC_VER_51: options = RTL_R8(tp, Config2) & ~PME_SIGNAL; if (wolopts) options |= PME_SIGNAL; RTL_W8(tp, Config2, options); break; + default: + break; } rtl_lock_config_regs(tp); @@ -1505,6 +1584,13 @@ static int rtl8169_set_features(struct net_device *dev, else rx_config &= ~(AcceptErr | AcceptRunt); + if (rtl_is_8125(tp)) { + if (features & NETIF_F_HW_VLAN_CTAG_RX) + rx_config |= RX_VLAN_8125; + else + rx_config &= ~RX_VLAN_8125; + } + RTL_W32(tp, RxConfig, rx_config); if (features & NETIF_F_RXCSUM) @@ -1512,10 +1598,12 @@ static int rtl8169_set_features(struct net_device *dev, else tp->cp_cmd &= ~RxChkSum; - if (features & NETIF_F_HW_VLAN_CTAG_RX) - tp->cp_cmd |= RxVlan; - else - tp->cp_cmd &= ~RxVlan; + if (!rtl_is_8125(tp)) { + if (features & NETIF_F_HW_VLAN_CTAG_RX) + tp->cp_cmd |= RxVlan; + else + tp->cp_cmd &= ~RxVlan; + } RTL_W16(tp, CPlusCmd, tp->cp_cmd); RTL_R16(tp, CPlusCmd); @@ -1814,6 +1902,9 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) int i; u16 w; + if (rtl_is_8125(tp)) + return -EOPNOTSUPP; + memset(ec, 0, sizeof(*ec)); /* get rx/tx scale corresponding to current speed and CPlusCmd[0:1] */ @@ -1882,6 +1973,9 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) u16 w = 0, cp01; int i; + if (rtl_is_8125(tp)) + return -EOPNOTSUPP; + scale = rtl_coalesce_choose_scale(dev, max(p[0].usecs, p[1].usecs) * 1000, &cp01); if (IS_ERR(scale)) @@ -1929,144 +2023,40 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) return 0; } -static int rtl_get_eee_supp(struct rtl8169_private *tp) -{ - struct phy_device *phydev = tp->phydev; - int ret; - - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_38: - ret = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE); - break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: - ret = phy_read_paged(phydev, 0x0a5c, 0x12); - break; - default: - ret = -EPROTONOSUPPORT; - break; - } - - return ret; -} - -static int rtl_get_eee_lpadv(struct rtl8169_private *tp) -{ - struct phy_device *phydev = tp->phydev; - int ret; - - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_38: - ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_LPABLE); - break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: - ret = phy_read_paged(phydev, 0x0a5d, 0x11); - break; - default: - ret = -EPROTONOSUPPORT; - break; - } - - return ret; -} - -static int rtl_get_eee_adv(struct rtl8169_private *tp) -{ - struct phy_device *phydev = tp->phydev; - int ret; - - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_38: - ret = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV); - break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: - ret = phy_read_paged(phydev, 0x0a5d, 0x10); - break; - default: - ret = -EPROTONOSUPPORT; - break; - } - - return ret; -} - -static int rtl_set_eee_adv(struct rtl8169_private *tp, int val) -{ - struct phy_device *phydev = tp->phydev; - int ret = 0; - - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_38: - ret = phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, val); - break; - case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: - phy_write_paged(phydev, 0x0a5d, 0x10, val); - break; - default: - ret = -EPROTONOSUPPORT; - break; - } - - return ret; -} - static int rtl8169_get_eee(struct net_device *dev, struct ethtool_eee *data) { struct rtl8169_private *tp = netdev_priv(dev); struct device *d = tp_to_dev(tp); int ret; + if (!rtl_supports_eee(tp)) + return -EOPNOTSUPP; + pm_runtime_get_noresume(d); if (!pm_runtime_active(d)) { ret = -EOPNOTSUPP; - goto out; + } else { + ret = phy_ethtool_get_eee(tp->phydev, data); } - /* Get Supported EEE */ - ret = rtl_get_eee_supp(tp); - if (ret < 0) - goto out; - data->supported = mmd_eee_cap_to_ethtool_sup_t(ret); - - /* Get advertisement EEE */ - ret = rtl_get_eee_adv(tp); - if (ret < 0) - goto out; - data->advertised = mmd_eee_adv_to_ethtool_adv_t(ret); - data->eee_enabled = !!data->advertised; - - /* Get LP advertisement EEE */ - ret = rtl_get_eee_lpadv(tp); - if (ret < 0) - goto out; - data->lp_advertised = mmd_eee_adv_to_ethtool_adv_t(ret); - data->eee_active = !!(data->advertised & data->lp_advertised); -out: pm_runtime_put_noidle(d); - return ret < 0 ? ret : 0; + + return ret; } static int rtl8169_set_eee(struct net_device *dev, struct ethtool_eee *data) { struct rtl8169_private *tp = netdev_priv(dev); struct device *d = tp_to_dev(tp); - int old_adv, adv = 0, cap, ret; + int ret; + + if (!rtl_supports_eee(tp)) + return -EOPNOTSUPP; pm_runtime_get_noresume(d); - if (!dev->phydev || !pm_runtime_active(d)) { + if (!pm_runtime_active(d)) { ret = -EOPNOTSUPP; goto out; } @@ -2077,38 +2067,10 @@ static int rtl8169_set_eee(struct net_device *dev, struct ethtool_eee *data) goto out; } - /* Get Supported EEE */ - ret = rtl_get_eee_supp(tp); - if (ret < 0) - goto out; - cap = ret; - - ret = rtl_get_eee_adv(tp); - if (ret < 0) - goto out; - old_adv = ret; - - if (data->eee_enabled) { - adv = !data->advertised ? cap : - ethtool_adv_to_mmd_eee_adv_t(data->advertised) & cap; - /* Mask prohibited EEE modes */ - adv &= ~dev->phydev->eee_broken_modes; - } - - if (old_adv != adv) { - ret = rtl_set_eee_adv(tp, adv); - if (ret < 0) - goto out; - - /* Restart autonegotiation so the new modes get sent to the - * link partner. - */ - ret = phy_restart_aneg(dev->phydev); - } - + ret = phy_ethtool_set_eee(tp->phydev, data); out: pm_runtime_put_noidle(d); - return ret < 0 ? ret : 0; + return ret; } static const struct ethtool_ops rtl8169_ethtool_ops = { @@ -2135,10 +2097,11 @@ static const struct ethtool_ops rtl8169_ethtool_ops = { static void rtl_enable_eee(struct rtl8169_private *tp) { - int supported = rtl_get_eee_supp(tp); + struct phy_device *phydev = tp->phydev; + int supported = phy_read_mmd(phydev, MDIO_MMD_PCS, MDIO_PCS_EEE_ABLE); if (supported > 0) - rtl_set_eee_adv(tp, supported); + phy_write_mmd(phydev, MDIO_MMD_AN, MDIO_AN_EEE_ADV, supported); } static void rtl8169_get_mac_version(struct rtl8169_private *tp) @@ -2159,6 +2122,10 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp) u16 val; u16 mac_version; } mac_info[] = { + /* 8125 family. */ + { 0x7cf, 0x608, RTL_GIGA_MAC_VER_60 }, + { 0x7c8, 0x608, RTL_GIGA_MAC_VER_61 }, + /* 8168EP family. */ { 0x7cf, 0x502, RTL_GIGA_MAC_VER_51 }, { 0x7cf, 0x501, RTL_GIGA_MAC_VER_50 }, @@ -2304,6 +2271,12 @@ static void rtl8168_config_eee_mac(struct rtl8169_private *tp) rtl_eri_set_bits(tp, 0x1b0, ERIAR_MASK_1111, 0x0003); } +static void rtl8125_config_eee_mac(struct rtl8169_private *tp) +{ + r8168_mac_ocp_modify(tp, 0xe040, 0, BIT(1) | BIT(0)); + r8168_mac_ocp_modify(tp, 0xeb62, 0, BIT(2) | BIT(1)); +} + static void rtl8168f_config_eee_phy(struct rtl8169_private *tp) { struct phy_device *phydev = tp->phydev; @@ -2324,6 +2297,26 @@ static void rtl8168g_config_eee_phy(struct rtl8169_private *tp) phy_modify_paged(tp->phydev, 0x0a43, 0x11, 0, BIT(4)); } +static void rtl8168h_config_eee_phy(struct rtl8169_private *tp) +{ + struct phy_device *phydev = tp->phydev; + + rtl8168g_config_eee_phy(tp); + + phy_modify_paged(phydev, 0xa4a, 0x11, 0x0000, 0x0200); + phy_modify_paged(phydev, 0xa42, 0x14, 0x0000, 0x0080); +} + +static void rtl8125_config_eee_phy(struct rtl8169_private *tp) +{ + struct phy_device *phydev = tp->phydev; + + rtl8168h_config_eee_phy(tp); + + phy_modify_paged(phydev, 0xa6d, 0x12, 0x0001, 0x0000); + phy_modify_paged(phydev, 0xa6d, 0x14, 0x0010, 0x0000); +} + static void rtl8169s_hw_phy_config(struct rtl8169_private *tp) { static const struct phy_reg phy_reg_init[] = { @@ -3391,7 +3384,7 @@ static void rtl8168h_1_hw_phy_config(struct rtl8169_private *tp) phy_modify_paged(tp->phydev, 0x0a44, 0x11, BIT(7), 0); rtl8168g_disable_aldps(tp); - rtl8168g_config_eee_phy(tp); + rtl8168h_config_eee_phy(tp); rtl_enable_eee(tp); } @@ -3644,6 +3637,134 @@ static void rtl8106e_hw_phy_config(struct rtl8169_private *tp) rtl_eri_write(tp, 0x1d0, ERIAR_MASK_0011, 0x0000); } +static void rtl8125_1_hw_phy_config(struct rtl8169_private *tp) +{ + struct phy_device *phydev = tp->phydev; + + phy_modify_paged(phydev, 0xad4, 0x10, 0x03ff, 0x0084); + phy_modify_paged(phydev, 0xad4, 0x17, 0x0000, 0x0010); + phy_modify_paged(phydev, 0xad1, 0x13, 0x03ff, 0x0006); + phy_modify_paged(phydev, 0xad3, 0x11, 0x003f, 0x0006); + phy_modify_paged(phydev, 0xac0, 0x14, 0x0000, 0x1100); + phy_modify_paged(phydev, 0xac8, 0x15, 0xf000, 0x7000); + phy_modify_paged(phydev, 0xad1, 0x14, 0x0000, 0x0400); + phy_modify_paged(phydev, 0xad1, 0x15, 0x0000, 0x03ff); + phy_modify_paged(phydev, 0xad1, 0x16, 0x0000, 0x03ff); + + phy_write(phydev, 0x1f, 0x0a43); + phy_write(phydev, 0x13, 0x80ea); + phy_modify(phydev, 0x14, 0xff00, 0xc400); + phy_write(phydev, 0x13, 0x80eb); + phy_modify(phydev, 0x14, 0x0700, 0x0300); + phy_write(phydev, 0x13, 0x80f8); + phy_modify(phydev, 0x14, 0xff00, 0x1c00); + phy_write(phydev, 0x13, 0x80f1); + phy_modify(phydev, 0x14, 0xff00, 0x3000); + phy_write(phydev, 0x13, 0x80fe); + phy_modify(phydev, 0x14, 0xff00, 0xa500); + phy_write(phydev, 0x13, 0x8102); + phy_modify(phydev, 0x14, 0xff00, 0x5000); + phy_write(phydev, 0x13, 0x8105); + phy_modify(phydev, 0x14, 0xff00, 0x3300); + phy_write(phydev, 0x13, 0x8100); + phy_modify(phydev, 0x14, 0xff00, 0x7000); + phy_write(phydev, 0x13, 0x8104); + phy_modify(phydev, 0x14, 0xff00, 0xf000); + phy_write(phydev, 0x13, 0x8106); + phy_modify(phydev, 0x14, 0xff00, 0x6500); + phy_write(phydev, 0x13, 0x80dc); + phy_modify(phydev, 0x14, 0xff00, 0xed00); + phy_write(phydev, 0x13, 0x80df); + phy_set_bits(phydev, 0x14, BIT(8)); + phy_write(phydev, 0x13, 0x80e1); + phy_clear_bits(phydev, 0x14, BIT(8)); + phy_write(phydev, 0x1f, 0x0000); + + phy_modify_paged(phydev, 0xbf0, 0x13, 0x003f, 0x0038); + phy_write_paged(phydev, 0xa43, 0x13, 0x819f); + phy_write_paged(phydev, 0xa43, 0x14, 0xd0b6); + + phy_write_paged(phydev, 0xbc3, 0x12, 0x5555); + phy_modify_paged(phydev, 0xbf0, 0x15, 0x0e00, 0x0a00); + phy_modify_paged(phydev, 0xa5c, 0x10, 0x0400, 0x0000); + phy_modify_paged(phydev, 0xa44, 0x11, 0x0000, 0x0800); + + rtl8125_config_eee_phy(tp); + rtl_enable_eee(tp); +} + +static void rtl8125_2_hw_phy_config(struct rtl8169_private *tp) +{ + struct phy_device *phydev = tp->phydev; + int i; + + phy_modify_paged(phydev, 0xad4, 0x17, 0x0000, 0x0010); + phy_modify_paged(phydev, 0xad1, 0x13, 0x03ff, 0x03ff); + phy_modify_paged(phydev, 0xad3, 0x11, 0x003f, 0x0006); + phy_modify_paged(phydev, 0xac0, 0x14, 0x1100, 0x0000); + phy_modify_paged(phydev, 0xacc, 0x10, 0x0003, 0x0002); + phy_modify_paged(phydev, 0xad4, 0x10, 0x00e7, 0x0044); + phy_modify_paged(phydev, 0xac1, 0x12, 0x0080, 0x0000); + phy_modify_paged(phydev, 0xac8, 0x10, 0x0300, 0x0000); + phy_modify_paged(phydev, 0xac5, 0x17, 0x0007, 0x0002); + phy_write_paged(phydev, 0xad4, 0x16, 0x00a8); + phy_write_paged(phydev, 0xac5, 0x16, 0x01ff); + phy_modify_paged(phydev, 0xac8, 0x15, 0x00f0, 0x0030); + + phy_write(phydev, 0x1f, 0x0b87); + phy_write(phydev, 0x16, 0x80a2); + phy_write(phydev, 0x17, 0x0153); + phy_write(phydev, 0x16, 0x809c); + phy_write(phydev, 0x17, 0x0153); + phy_write(phydev, 0x1f, 0x0000); + + phy_write(phydev, 0x1f, 0x0a43); + phy_write(phydev, 0x13, 0x81B3); + phy_write(phydev, 0x14, 0x0043); + phy_write(phydev, 0x14, 0x00A7); + phy_write(phydev, 0x14, 0x00D6); + phy_write(phydev, 0x14, 0x00EC); + phy_write(phydev, 0x14, 0x00F6); + phy_write(phydev, 0x14, 0x00FB); + phy_write(phydev, 0x14, 0x00FD); + phy_write(phydev, 0x14, 0x00FF); + phy_write(phydev, 0x14, 0x00BB); + phy_write(phydev, 0x14, 0x0058); + phy_write(phydev, 0x14, 0x0029); + phy_write(phydev, 0x14, 0x0013); + phy_write(phydev, 0x14, 0x0009); + phy_write(phydev, 0x14, 0x0004); + phy_write(phydev, 0x14, 0x0002); + for (i = 0; i < 25; i++) + phy_write(phydev, 0x14, 0x0000); + + phy_write(phydev, 0x13, 0x8257); + phy_write(phydev, 0x14, 0x020F); + + phy_write(phydev, 0x13, 0x80EA); + phy_write(phydev, 0x14, 0x7843); + phy_write(phydev, 0x1f, 0x0000); + + rtl_apply_firmware(tp); + + phy_modify_paged(phydev, 0xd06, 0x14, 0x0000, 0x2000); + + phy_write(phydev, 0x1f, 0x0a43); + phy_write(phydev, 0x13, 0x81a2); + phy_set_bits(phydev, 0x14, BIT(8)); + phy_write(phydev, 0x1f, 0x0000); + + phy_modify_paged(phydev, 0xb54, 0x16, 0xff00, 0xdb00); + phy_modify_paged(phydev, 0xa45, 0x12, 0x0001, 0x0000); + phy_modify_paged(phydev, 0xa5d, 0x12, 0x0000, 0x0020); + phy_modify_paged(phydev, 0xad4, 0x17, 0x0010, 0x0000); + phy_modify_paged(phydev, 0xa86, 0x15, 0x0001, 0x0000); + phy_modify_paged(phydev, 0xa44, 0x11, 0x0000, 0x0800); + + rtl8125_config_eee_phy(tp); + rtl_enable_eee(tp); +} + static void rtl_hw_phy_config(struct net_device *dev) { static const rtl_generic_fct phy_configs[] = { @@ -3699,6 +3820,8 @@ static void rtl_hw_phy_config(struct net_device *dev) [RTL_GIGA_MAC_VER_49] = rtl8168ep_1_hw_phy_config, [RTL_GIGA_MAC_VER_50] = rtl8168ep_2_hw_phy_config, [RTL_GIGA_MAC_VER_51] = rtl8168ep_2_hw_phy_config, + [RTL_GIGA_MAC_VER_60] = rtl8125_1_hw_phy_config, + [RTL_GIGA_MAC_VER_61] = rtl8125_2_hw_phy_config, }; struct rtl8169_private *tp = netdev_priv(dev); @@ -3826,6 +3949,8 @@ static void rtl_pll_power_down(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_48: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_60: + case RTL_GIGA_MAC_VER_61: RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~0x80); break; case RTL_GIGA_MAC_VER_40: @@ -3855,6 +3980,8 @@ static void rtl_pll_power_up(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_48: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_60: + case RTL_GIGA_MAC_VER_61: RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0xc0); break; case RTL_GIGA_MAC_VER_40: @@ -3887,6 +4014,10 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); break; + case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_61: + RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_VLAN_8125 | + RX_DMA_BURST); + break; default: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_DMA_BURST); break; @@ -4146,54 +4277,46 @@ static void rtl8169_set_magic_reg(struct rtl8169_private *tp, unsigned mac_versi static void rtl_set_rx_mode(struct net_device *dev) { + u32 rx_mode = AcceptBroadcast | AcceptMyPhys | AcceptMulticast; + /* Multicast hash filter */ + u32 mc_filter[2] = { 0xffffffff, 0xffffffff }; struct rtl8169_private *tp = netdev_priv(dev); - u32 mc_filter[2]; /* Multicast hash filter */ - int rx_mode; - u32 tmp = 0; + u32 tmp; if (dev->flags & IFF_PROMISC) { /* Unconditionally log net taps. */ netif_notice(tp, link, dev, "Promiscuous mode enabled\n"); - rx_mode = - AcceptBroadcast | AcceptMulticast | AcceptMyPhys | - AcceptAllPhys; - mc_filter[1] = mc_filter[0] = 0xffffffff; - } else if ((netdev_mc_count(dev) > multicast_filter_limit) || - (dev->flags & IFF_ALLMULTI)) { - /* Too many to filter perfectly -- accept all multicasts. */ - rx_mode = AcceptBroadcast | AcceptMulticast | AcceptMyPhys; - mc_filter[1] = mc_filter[0] = 0xffffffff; + rx_mode |= AcceptAllPhys; + } else if (netdev_mc_count(dev) > MC_FILTER_LIMIT || + dev->flags & IFF_ALLMULTI || + tp->mac_version == RTL_GIGA_MAC_VER_35) { + /* accept all multicasts */ + } else if (netdev_mc_empty(dev)) { + rx_mode &= ~AcceptMulticast; } else { struct netdev_hw_addr *ha; - rx_mode = AcceptBroadcast | AcceptMyPhys; mc_filter[1] = mc_filter[0] = 0; netdev_for_each_mc_addr(ha, dev) { - int bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; - mc_filter[bit_nr >> 5] |= 1 << (bit_nr & 31); - rx_mode |= AcceptMulticast; + u32 bit_nr = ether_crc(ETH_ALEN, ha->addr) >> 26; + mc_filter[bit_nr >> 5] |= BIT(bit_nr & 31); + } + + if (tp->mac_version > RTL_GIGA_MAC_VER_06) { + tmp = mc_filter[0]; + mc_filter[0] = swab32(mc_filter[1]); + mc_filter[1] = swab32(tmp); } } if (dev->features & NETIF_F_RXALL) rx_mode |= (AcceptErr | AcceptRunt); - tmp = (RTL_R32(tp, RxConfig) & ~RX_CONFIG_ACCEPT_MASK) | rx_mode; - - if (tp->mac_version > RTL_GIGA_MAC_VER_06) { - u32 data = mc_filter[0]; - - mc_filter[0] = swab32(mc_filter[1]); - mc_filter[1] = swab32(data); - } - - if (tp->mac_version == RTL_GIGA_MAC_VER_35) - mc_filter[1] = mc_filter[0] = 0xffffffff; - RTL_W32(tp, MAR0 + 4, mc_filter[1]); RTL_W32(tp, MAR0 + 0, mc_filter[0]); - RTL_W32(tp, RxConfig, tmp); + tmp = RTL_R32(tp, RxConfig); + RTL_W32(tp, RxConfig, (tmp & ~RX_CONFIG_ACCEPT_MASK) | rx_mode); } DECLARE_RTL_COND(rtl_csiar_cond) @@ -4407,7 +4530,7 @@ static void rtl_hw_start_8168c_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168c_2[] = { { 0x01, 0, 0x0001 }, - { 0x03, 0x0400, 0x0220 } + { 0x03, 0x0400, 0x0020 } }; rtl_set_def_aspm_entry_latency(tp); @@ -4454,7 +4577,8 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp) static const struct ephy_info e_info_8168d_4[] = { { 0x0b, 0x0000, 0x0048 }, { 0x19, 0x0020, 0x0050 }, - { 0x0c, 0x0100, 0x0020 } + { 0x0c, 0x0100, 0x0020 }, + { 0x10, 0x0004, 0x0000 }, }; rtl_set_def_aspm_entry_latency(tp); @@ -4504,7 +4628,9 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168e_2[] = { { 0x09, 0x0000, 0x0080 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_set_def_aspm_entry_latency(tp); @@ -4566,7 +4692,9 @@ static void rtl_hw_start_8168f_1(struct rtl8169_private *tp) { 0x06, 0x00c0, 0x0020 }, { 0x08, 0x0001, 0x0002 }, { 0x09, 0x0000, 0x0080 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_hw_start_8168f(tp); @@ -4581,8 +4709,9 @@ static void rtl_hw_start_8411(struct rtl8169_private *tp) static const struct ephy_info e_info_8168f_1[] = { { 0x06, 0x00c0, 0x0020 }, { 0x0f, 0xffff, 0x5200 }, - { 0x1e, 0x0000, 0x4000 }, - { 0x19, 0x0000, 0x0224 } + { 0x19, 0x0000, 0x0224 }, + { 0x00, 0x0000, 0x0004 }, + { 0x0c, 0x3df0, 0x0200 }, }; rtl_hw_start_8168f(tp); @@ -4621,8 +4750,8 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp) static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168g_1[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x37d0, 0x0820 }, + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x3ff0, 0x0820 }, { 0x1e, 0x0000, 0x0001 }, { 0x19, 0x8000, 0x0000 } }; @@ -4638,10 +4767,15 @@ static void rtl_hw_start_8168g_1(struct rtl8169_private *tp) static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8168g_2[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x3df0, 0x0200 }, - { 0x19, 0xffff, 0xfc00 }, - { 0x1e, 0xffff, 0x20eb } + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x3ff0, 0x0820 }, + { 0x19, 0xffff, 0x7c00 }, + { 0x1e, 0xffff, 0x20eb }, + { 0x0d, 0xffff, 0x1666 }, + { 0x00, 0xffff, 0x10a3 }, + { 0x06, 0xffff, 0xf050 }, + { 0x04, 0x0000, 0x0010 }, + { 0x1d, 0x4000, 0x0000 }, }; rtl_hw_start_8168g(tp); @@ -4655,11 +4789,16 @@ static void rtl_hw_start_8168g_2(struct rtl8169_private *tp) static void rtl_hw_start_8411_2(struct rtl8169_private *tp) { static const struct ephy_info e_info_8411_2[] = { - { 0x00, 0x0000, 0x0008 }, - { 0x0c, 0x3df0, 0x0200 }, - { 0x0f, 0xffff, 0x5200 }, - { 0x19, 0x0020, 0x0000 }, - { 0x1e, 0x0000, 0x2000 } + { 0x00, 0x0008, 0x0000 }, + { 0x0c, 0x37d0, 0x0820 }, + { 0x1e, 0x0000, 0x0001 }, + { 0x19, 0x8021, 0x0000 }, + { 0x1e, 0x0000, 0x2000 }, + { 0x0d, 0x0100, 0x0200 }, + { 0x00, 0x0000, 0x0080 }, + { 0x06, 0x0000, 0x0010 }, + { 0x04, 0x0000, 0x0010 }, + { 0x1d, 0x0000, 0x4000 }, }; rtl_hw_start_8168g(tp); @@ -4809,16 +4948,15 @@ static void rtl_hw_start_8411_2(struct rtl8169_private *tp) static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) { - int rg_saw_cnt; - u32 data; static const struct ephy_info e_info_8168h_1[] = { { 0x1e, 0x0800, 0x0001 }, { 0x1d, 0x0000, 0x0800 }, { 0x05, 0xffff, 0x2089 }, { 0x06, 0xffff, 0x5881 }, - { 0x04, 0xffff, 0x154a }, + { 0x04, 0xffff, 0x854a }, { 0x01, 0xffff, 0x068b } }; + int rg_saw_cnt; /* disable aspm and clock request before access ephy */ rtl_hw_aspm_clkreq_enable(tp, false); @@ -4863,31 +5001,13 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) sw_cnt_1ms_ini = 16000000/rg_saw_cnt; sw_cnt_1ms_ini &= 0x0fff; - data = r8168_mac_ocp_read(tp, 0xd412); - data &= ~0x0fff; - data |= sw_cnt_1ms_ini; - r8168_mac_ocp_write(tp, 0xd412, data); + r8168_mac_ocp_modify(tp, 0xd412, 0x0fff, sw_cnt_1ms_ini); } - data = r8168_mac_ocp_read(tp, 0xe056); - data &= ~0xf0; - data |= 0x70; - r8168_mac_ocp_write(tp, 0xe056, data); - - data = r8168_mac_ocp_read(tp, 0xe052); - data &= ~0x6000; - data |= 0x8008; - r8168_mac_ocp_write(tp, 0xe052, data); - - data = r8168_mac_ocp_read(tp, 0xe0d6); - data &= ~0x01ff; - data |= 0x017f; - r8168_mac_ocp_write(tp, 0xe0d6, data); - - data = r8168_mac_ocp_read(tp, 0xd420); - data &= ~0x0fff; - data |= 0x047f; - r8168_mac_ocp_write(tp, 0xd420, data); + r8168_mac_ocp_modify(tp, 0xe056, 0x00f0, 0x0070); + r8168_mac_ocp_modify(tp, 0xe052, 0x6000, 0x8008); + r8168_mac_ocp_modify(tp, 0xe0d6, 0x01ff, 0x017f); + r8168_mac_ocp_modify(tp, 0xd420, 0x0fff, 0x047f); r8168_mac_ocp_write(tp, 0xe63e, 0x0001); r8168_mac_ocp_write(tp, 0xe63e, 0x0000); @@ -4969,12 +5089,11 @@ static void rtl_hw_start_8168ep_2(struct rtl8169_private *tp) static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) { - u32 data; static const struct ephy_info e_info_8168ep_3[] = { - { 0x00, 0xffff, 0x10a3 }, - { 0x19, 0xffff, 0x7c00 }, - { 0x1e, 0xffff, 0x20eb }, - { 0x0d, 0xffff, 0x1666 } + { 0x00, 0x0000, 0x0080 }, + { 0x0d, 0x0100, 0x0200 }, + { 0x19, 0x8021, 0x0000 }, + { 0x1e, 0x0000, 0x2000 }, }; /* disable aspm and clock request before access ephy */ @@ -4986,18 +5105,9 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) RTL_W8(tp, DLLPR, RTL_R8(tp, DLLPR) & ~PFM_EN); RTL_W8(tp, MISC_1, RTL_R8(tp, MISC_1) & ~PFM_D3COLD_EN); - data = r8168_mac_ocp_read(tp, 0xd3e2); - data &= 0xf000; - data |= 0x0271; - r8168_mac_ocp_write(tp, 0xd3e2, data); - - data = r8168_mac_ocp_read(tp, 0xd3e4); - data &= 0xff00; - r8168_mac_ocp_write(tp, 0xd3e4, data); - - data = r8168_mac_ocp_read(tp, 0xe860); - data |= 0x0080; - r8168_mac_ocp_write(tp, 0xe860, data); + r8168_mac_ocp_modify(tp, 0xd3e2, 0x0fff, 0x0271); + r8168_mac_ocp_modify(tp, 0xd3e4, 0x00ff, 0x0000); + r8168_mac_ocp_modify(tp, 0xe860, 0x0000, 0x0080); rtl_hw_aspm_clkreq_enable(tp, true); } @@ -5125,6 +5235,128 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) rtl_hw_aspm_clkreq_enable(tp, true); } +DECLARE_RTL_COND(rtl_mac_ocp_e00e_cond) +{ + return r8168_mac_ocp_read(tp, 0xe00e) & BIT(13); +} + +static void rtl_hw_start_8125_common(struct rtl8169_private *tp) +{ + rtl_pcie_state_l2l3_disable(tp); + + RTL_W16(tp, 0x382, 0x221b); + RTL_W8(tp, 0x4500, 0); + RTL_W16(tp, 0x4800, 0); + + /* disable UPS */ + r8168_mac_ocp_modify(tp, 0xd40a, 0x0010, 0x0000); + + RTL_W8(tp, Config1, RTL_R8(tp, Config1) & ~0x10); + + r8168_mac_ocp_write(tp, 0xc140, 0xffff); + r8168_mac_ocp_write(tp, 0xc142, 0xffff); + + r8168_mac_ocp_modify(tp, 0xd3e2, 0x0fff, 0x03a9); + r8168_mac_ocp_modify(tp, 0xd3e4, 0x00ff, 0x0000); + r8168_mac_ocp_modify(tp, 0xe860, 0x0000, 0x0080); + + /* disable new tx descriptor format */ + r8168_mac_ocp_modify(tp, 0xeb58, 0x0001, 0x0000); + + r8168_mac_ocp_modify(tp, 0xe614, 0x0700, 0x0400); + r8168_mac_ocp_modify(tp, 0xe63e, 0x0c30, 0x0020); + r8168_mac_ocp_modify(tp, 0xc0b4, 0x0000, 0x000c); + r8168_mac_ocp_modify(tp, 0xeb6a, 0x00ff, 0x0033); + r8168_mac_ocp_modify(tp, 0xeb50, 0x03e0, 0x0040); + r8168_mac_ocp_modify(tp, 0xe056, 0x00f0, 0x0030); + r8168_mac_ocp_modify(tp, 0xe040, 0x1000, 0x0000); + r8168_mac_ocp_modify(tp, 0xe0c0, 0x4f0f, 0x4403); + r8168_mac_ocp_modify(tp, 0xe052, 0x0080, 0x0067); + r8168_mac_ocp_modify(tp, 0xc0ac, 0x0080, 0x1f00); + r8168_mac_ocp_modify(tp, 0xd430, 0x0fff, 0x047f); + r8168_mac_ocp_modify(tp, 0xe84c, 0x0000, 0x00c0); + r8168_mac_ocp_modify(tp, 0xea1c, 0x0004, 0x0000); + r8168_mac_ocp_modify(tp, 0xeb54, 0x0000, 0x0001); + udelay(1); + r8168_mac_ocp_modify(tp, 0xeb54, 0x0001, 0x0000); + RTL_W16(tp, 0x1880, RTL_R16(tp, 0x1880) & ~0x0030); + + r8168_mac_ocp_write(tp, 0xe098, 0xc302); + + rtl_udelay_loop_wait_low(tp, &rtl_mac_ocp_e00e_cond, 1000, 10); + + rtl8125_config_eee_mac(tp); + + RTL_W32(tp, MISC, RTL_R32(tp, MISC) & ~RXDV_GATED_EN); + udelay(10); +} + +static void rtl_hw_start_8125_1(struct rtl8169_private *tp) +{ + static const struct ephy_info e_info_8125_1[] = { + { 0x01, 0xffff, 0xa812 }, + { 0x09, 0xffff, 0x520c }, + { 0x04, 0xffff, 0xd000 }, + { 0x0d, 0xffff, 0xf702 }, + { 0x0a, 0xffff, 0x8653 }, + { 0x06, 0xffff, 0x001e }, + { 0x08, 0xffff, 0x3595 }, + { 0x20, 0xffff, 0x9455 }, + { 0x21, 0xffff, 0x99ff }, + { 0x02, 0xffff, 0x6046 }, + { 0x29, 0xffff, 0xfe00 }, + { 0x23, 0xffff, 0xab62 }, + + { 0x41, 0xffff, 0xa80c }, + { 0x49, 0xffff, 0x520c }, + { 0x44, 0xffff, 0xd000 }, + { 0x4d, 0xffff, 0xf702 }, + { 0x4a, 0xffff, 0x8653 }, + { 0x46, 0xffff, 0x001e }, + { 0x48, 0xffff, 0x3595 }, + { 0x60, 0xffff, 0x9455 }, + { 0x61, 0xffff, 0x99ff }, + { 0x42, 0xffff, 0x6046 }, + { 0x69, 0xffff, 0xfe00 }, + { 0x63, 0xffff, 0xab62 }, + }; + + rtl_set_def_aspm_entry_latency(tp); + + /* disable aspm and clock request before access ephy */ + rtl_hw_aspm_clkreq_enable(tp, false); + rtl_ephy_init(tp, e_info_8125_1); + + rtl_hw_start_8125_common(tp); +} + +static void rtl_hw_start_8125_2(struct rtl8169_private *tp) +{ + static const struct ephy_info e_info_8125_2[] = { + { 0x04, 0xffff, 0xd000 }, + { 0x0a, 0xffff, 0x8653 }, + { 0x23, 0xffff, 0xab66 }, + { 0x20, 0xffff, 0x9455 }, + { 0x21, 0xffff, 0x99ff }, + { 0x29, 0xffff, 0xfe04 }, + + { 0x44, 0xffff, 0xd000 }, + { 0x4a, 0xffff, 0x8653 }, + { 0x63, 0xffff, 0xab66 }, + { 0x60, 0xffff, 0x9455 }, + { 0x61, 0xffff, 0x99ff }, + { 0x69, 0xffff, 0xfe04 }, + }; + + rtl_set_def_aspm_entry_latency(tp); + + /* disable aspm and clock request before access ephy */ + rtl_hw_aspm_clkreq_enable(tp, false); + rtl_ephy_init(tp, e_info_8125_2); + + rtl_hw_start_8125_common(tp); +} + static void rtl_hw_config(struct rtl8169_private *tp) { static const rtl_generic_fct hw_configs[] = { @@ -5173,12 +5405,25 @@ static void rtl_hw_config(struct rtl8169_private *tp) [RTL_GIGA_MAC_VER_49] = rtl_hw_start_8168ep_1, [RTL_GIGA_MAC_VER_50] = rtl_hw_start_8168ep_2, [RTL_GIGA_MAC_VER_51] = rtl_hw_start_8168ep_3, + [RTL_GIGA_MAC_VER_60] = rtl_hw_start_8125_1, + [RTL_GIGA_MAC_VER_61] = rtl_hw_start_8125_2, }; if (hw_configs[tp->mac_version]) hw_configs[tp->mac_version](tp); } +static void rtl_hw_start_8125(struct rtl8169_private *tp) +{ + int i; + + /* disable interrupt coalescing */ + for (i = 0xa00; i < 0xb00; i += 4) + RTL_W32(tp, i, 0); + + rtl_hw_config(tp); +} + static void rtl_hw_start_8168(struct rtl8169_private *tp) { if (tp->mac_version == RTL_GIGA_MAC_VER_13 || @@ -5192,6 +5437,9 @@ static void rtl_hw_start_8168(struct rtl8169_private *tp) RTL_W8(tp, MaxTxPacketSize, TxPacketMax); rtl_hw_config(tp); + + /* disable interrupt coalescing */ + RTL_W16(tp, IntrMitigate, 0x0000); } static void rtl_hw_start_8169(struct rtl8169_private *tp) @@ -5215,6 +5463,9 @@ static void rtl_hw_start_8169(struct rtl8169_private *tp) rtl8169_set_magic_reg(tp, tp->mac_version); RTL_W32(tp, RxMissed, 0); + + /* disable interrupt coalescing */ + RTL_W16(tp, IntrMitigate, 0x0000); } static void rtl_hw_start(struct rtl8169_private *tp) @@ -5226,6 +5477,8 @@ static void rtl_hw_start(struct rtl8169_private *tp) if (tp->mac_version <= RTL_GIGA_MAC_VER_06) rtl_hw_start_8169(tp); + else if (rtl_is_8125(tp)) + rtl_hw_start_8125(tp); else rtl_hw_start_8168(tp); @@ -5233,17 +5486,12 @@ static void rtl_hw_start(struct rtl8169_private *tp) rtl_set_rx_tx_desc_registers(tp); rtl_lock_config_regs(tp); - /* disable interrupt coalescing */ - RTL_W16(tp, IntrMitigate, 0x0000); /* Initially a 10 us delay. Turned it into a PCI commit. - FR */ - RTL_R8(tp, IntrMask); + RTL_R16(tp, CPlusCmd); RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); rtl_init_rxcfg(tp); rtl_set_tx_config_registers(tp); - rtl_set_rx_mode(tp->dev); - /* no early-rx interrupts */ - RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); rtl_irq_enable(tp); } @@ -5268,17 +5516,6 @@ static inline void rtl8169_make_unusable_by_asic(struct RxDesc *desc) desc->opts1 &= ~cpu_to_le32(DescOwn | RsvdMask); } -static void rtl8169_free_rx_databuff(struct rtl8169_private *tp, - void **data_buff, struct RxDesc *desc) -{ - dma_unmap_single(tp_to_dev(tp), le64_to_cpu(desc->addr), - R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); - - kfree(*data_buff); - *data_buff = NULL; - rtl8169_make_unusable_by_asic(desc); -} - static inline void rtl8169_mark_to_asic(struct RxDesc *desc) { u32 eor = le32_to_cpu(desc->opts1) & RingEnd; @@ -5289,49 +5526,43 @@ static inline void rtl8169_mark_to_asic(struct RxDesc *desc) desc->opts1 = cpu_to_le32(DescOwn | eor | R8169_RX_BUF_SIZE); } -static struct sk_buff *rtl8169_alloc_rx_data(struct rtl8169_private *tp, - struct RxDesc *desc) +static struct page *rtl8169_alloc_rx_data(struct rtl8169_private *tp, + struct RxDesc *desc) { - void *data; - dma_addr_t mapping; struct device *d = tp_to_dev(tp); int node = dev_to_node(d); + dma_addr_t mapping; + struct page *data; - data = kmalloc_node(R8169_RX_BUF_SIZE, GFP_KERNEL, node); + data = alloc_pages_node(node, GFP_KERNEL, get_order(R8169_RX_BUF_SIZE)); if (!data) return NULL; - /* Memory should be properly aligned, but better check. */ - if (!IS_ALIGNED((unsigned long)data, 8)) { - netdev_err_once(tp->dev, "RX buffer not 8-byte-aligned\n"); - goto err_out; - } - - mapping = dma_map_single(d, data, R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); + mapping = dma_map_page(d, data, 0, R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(d, mapping))) { if (net_ratelimit()) netif_err(tp, drv, tp->dev, "Failed to map RX DMA!\n"); - goto err_out; + __free_pages(data, get_order(R8169_RX_BUF_SIZE)); + return NULL; } desc->addr = cpu_to_le64(mapping); rtl8169_mark_to_asic(desc); - return data; -err_out: - kfree(data); - return NULL; + return data; } static void rtl8169_rx_clear(struct rtl8169_private *tp) { unsigned int i; - for (i = 0; i < NUM_RX_DESC; i++) { - if (tp->Rx_databuff[i]) { - rtl8169_free_rx_databuff(tp, tp->Rx_databuff + i, - tp->RxDescArray + i); - } + for (i = 0; i < NUM_RX_DESC && tp->Rx_databuff[i]; i++) { + dma_unmap_page(tp_to_dev(tp), + le64_to_cpu(tp->RxDescArray[i].addr), + R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); + __free_pages(tp->Rx_databuff[i], get_order(R8169_RX_BUF_SIZE)); + tp->Rx_databuff[i] = NULL; + rtl8169_make_unusable_by_asic(tp->RxDescArray + i); } } @@ -5345,7 +5576,7 @@ static int rtl8169_rx_fill(struct rtl8169_private *tp) unsigned int i; for (i = 0; i < NUM_RX_DESC; i++) { - void *data; + struct page *data; data = rtl8169_alloc_rx_data(tp, tp->RxDescArray + i); if (!data) { @@ -5507,44 +5738,6 @@ static bool rtl_test_hw_pad_bug(struct rtl8169_private *tp, struct sk_buff *skb) return skb->len < ETH_ZLEN && tp->mac_version == RTL_GIGA_MAC_VER_34; } -static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, - struct net_device *dev); -/* r8169_csum_workaround() - * The hw limites the value the transport offset. When the offset is out of the - * range, calculate the checksum by sw. - */ -static void r8169_csum_workaround(struct rtl8169_private *tp, - struct sk_buff *skb) -{ - if (skb_is_gso(skb)) { - netdev_features_t features = tp->dev->features; - struct sk_buff *segs, *nskb; - - features &= ~(NETIF_F_SG | NETIF_F_IPV6_CSUM | NETIF_F_TSO6); - segs = skb_gso_segment(skb, features); - if (IS_ERR(segs) || !segs) - goto drop; - - do { - nskb = segs; - segs = segs->next; - nskb->next = NULL; - rtl8169_start_xmit(nskb, tp->dev); - } while (segs); - - dev_consume_skb_any(skb); - } else if (skb->ip_summed == CHECKSUM_PARTIAL) { - if (skb_checksum_help(skb) < 0) - goto drop; - - rtl8169_start_xmit(skb, tp->dev); - } else { -drop: - tp->dev->stats.tx_dropped++; - dev_kfree_skb_any(skb); - } -} - /* msdn_giant_send_check() * According to the document of microsoft, the TCP Pseudo Header excludes the * packet length for IPv6 TCP large packets. @@ -5594,13 +5787,6 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, u32 mss = skb_shinfo(skb)->gso_size; if (mss) { - if (transport_offset > GTTCPHO_MAX) { - netif_warn(tp, tx_err, tp->dev, - "Invalid transport offset 0x%x for TSO\n", - transport_offset); - return false; - } - switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): opts[0] |= TD1_GTSENV4; @@ -5623,16 +5809,6 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, } else if (skb->ip_summed == CHECKSUM_PARTIAL) { u8 ip_protocol; - if (unlikely(rtl_test_hw_pad_bug(tp, skb))) - return !(skb_checksum_help(skb) || eth_skb_pad(skb)); - - if (transport_offset > TCPHO_MAX) { - netif_warn(tp, tx_err, tp->dev, - "Invalid transport offset 0x%x\n", - transport_offset); - return false; - } - switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): opts[1] |= TD1_IPv4_CS; @@ -5686,6 +5862,14 @@ static bool rtl_chip_supports_csum_v2(struct rtl8169_private *tp) } } +static void rtl8169_doorbell(struct rtl8169_private *tp) +{ + if (rtl_is_8125(tp)) + RTL_W16(tp, TxPoll_8125, BIT(0)); + else + RTL_W8(tp, TxPoll, NPQ); +} + static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, struct net_device *dev) { @@ -5695,6 +5879,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, struct device *d = tp_to_dev(tp); dma_addr_t mapping; u32 opts[2], len; + bool stop_queue; + bool door_bell; int frags; if (unlikely(!rtl_tx_slots_avail(tp, skb_shinfo(skb)->nr_frags))) { @@ -5709,10 +5895,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, opts[0] = DescOwn; if (rtl_chip_supports_csum_v2(tp)) { - if (!rtl8169_tso_csum_v2(tp, skb, opts)) { - r8169_csum_workaround(tp, skb); - return NETDEV_TX_OK; - } + if (!rtl8169_tso_csum_v2(tp, skb, opts)) + goto err_dma_0; } else { rtl8169_tso_csum_v1(skb, opts); } @@ -5740,13 +5924,13 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, txd->opts2 = cpu_to_le32(opts[1]); - netdev_sent_queue(dev, skb->len); - skb_tx_timestamp(skb); /* Force memory writes to complete before releasing descriptor */ dma_wmb(); + door_bell = __netdev_sent_queue(dev, skb->len, netdev_xmit_more()); + txd->opts1 = rtl8169_get_txd_opts1(opts[0], len, entry); /* Force all memory writes to complete before notifying device */ @@ -5754,14 +5938,20 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb, tp->cur_tx += frags + 1; - RTL_W8(tp, TxPoll, NPQ); - - if (!rtl_tx_slots_avail(tp, MAX_SKB_FRAGS)) { + stop_queue = !rtl_tx_slots_avail(tp, MAX_SKB_FRAGS); + if (unlikely(stop_queue)) { /* Avoid wrongly optimistic queue wake-up: rtl_tx thread must * not miss a ring update when it notices a stopped queue. */ smp_wmb(); netif_stop_queue(dev); + door_bell = true; + } + + if (door_bell) + rtl8169_doorbell(tp); + + if (unlikely(stop_queue)) { /* Sync with rtl_tx: * - publish queue status and cur_tx ring index (write barrier) * - refresh dirty_tx ring index (read barrier). @@ -5789,6 +5979,39 @@ err_stop_0: return NETDEV_TX_BUSY; } +static netdev_features_t rtl8169_features_check(struct sk_buff *skb, + struct net_device *dev, + netdev_features_t features) +{ + int transport_offset = skb_transport_offset(skb); + struct rtl8169_private *tp = netdev_priv(dev); + + if (skb_is_gso(skb)) { + if (transport_offset > GTTCPHO_MAX && + rtl_chip_supports_csum_v2(tp)) + features &= ~NETIF_F_ALL_TSO; + } else if (skb->ip_summed == CHECKSUM_PARTIAL) { + if (skb->len < ETH_ZLEN) { + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_11: + case RTL_GIGA_MAC_VER_12: + case RTL_GIGA_MAC_VER_17: + case RTL_GIGA_MAC_VER_34: + features &= ~NETIF_F_CSUM_MASK; + break; + default: + break; + } + } + + if (transport_offset > TCPHO_MAX && + rtl_chip_supports_csum_v2(tp)) + features &= ~NETIF_F_CSUM_MASK; + } + + return vlan_features_check(skb, features); +} + static void rtl8169_pcierr_interrupt(struct net_device *dev) { struct rtl8169_private *tp = netdev_priv(dev); @@ -5850,7 +6073,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp, rtl8169_unmap_tx_skb(tp_to_dev(tp), tx_skb, tp->TxDescArray + entry); - if (status & LastFrag) { + if (tx_skb->skb) { pkts_compl++; bytes_compl += tx_skb->skb->len; napi_consume_skb(tx_skb->skb, budget); @@ -5888,7 +6111,7 @@ static void rtl_tx(struct net_device *dev, struct rtl8169_private *tp, * it is slow enough). -- FR */ if (tp->cur_tx != dirty_tx) - RTL_W8(tp, TxPoll, NPQ); + rtl8169_doorbell(tp); } } @@ -5908,24 +6131,6 @@ static inline void rtl8169_rx_csum(struct sk_buff *skb, u32 opts1) skb_checksum_none_assert(skb); } -static struct sk_buff *rtl8169_try_rx_copy(void *data, - struct rtl8169_private *tp, - int pkt_size, - dma_addr_t addr) -{ - struct sk_buff *skb; - struct device *d = tp_to_dev(tp); - - dma_sync_single_for_cpu(d, addr, pkt_size, DMA_FROM_DEVICE); - prefetch(data); - skb = napi_alloc_skb(&tp->napi, pkt_size); - if (skb) - skb_copy_to_linear_data(skb, data, pkt_size); - dma_sync_single_for_device(d, addr, pkt_size, DMA_FROM_DEVICE); - - return skb; -} - static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget) { unsigned int cur_rx, rx_left; @@ -5935,6 +6140,7 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget for (rx_left = min(budget, NUM_RX_DESC); rx_left > 0; rx_left--, cur_rx++) { unsigned int entry = cur_rx % NUM_RX_DESC; + const void *rx_buf = page_address(tp->Rx_databuff[entry]); struct RxDesc *desc = tp->RxDescArray + entry; u32 status; @@ -5961,17 +6167,13 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget goto process_pkt; } } else { + unsigned int pkt_size; struct sk_buff *skb; - dma_addr_t addr; - int pkt_size; process_pkt: - addr = le64_to_cpu(desc->addr); + pkt_size = status & GENMASK(13, 0); if (likely(!(dev->features & NETIF_F_RXFCS))) - pkt_size = (status & 0x00003fff) - 4; - else - pkt_size = status & 0x00003fff; - + pkt_size -= ETH_FCS_LEN; /* * The driver does not support incoming fragmented * frames. They are seen as a symptom of over-mtu @@ -5983,15 +6185,25 @@ process_pkt: goto release_descriptor; } - skb = rtl8169_try_rx_copy(tp->Rx_databuff[entry], - tp, pkt_size, addr); - if (!skb) { + skb = napi_alloc_skb(&tp->napi, pkt_size); + if (unlikely(!skb)) { dev->stats.rx_dropped++; goto release_descriptor; } + dma_sync_single_for_cpu(tp_to_dev(tp), + le64_to_cpu(desc->addr), + pkt_size, DMA_FROM_DEVICE); + prefetch(rx_buf); + skb_copy_to_linear_data(skb, rx_buf, pkt_size); + skb->tail += pkt_size; + skb->len = pkt_size; + + dma_sync_single_for_device(tp_to_dev(tp), + le64_to_cpu(desc->addr), + pkt_size, DMA_FROM_DEVICE); + rtl8169_rx_csum(skb, status); - skb_put(skb, pkt_size); skb->protocol = eth_type_trans(skb, dev); rtl8169_rx_vlan_tag(desc, skb); @@ -6020,9 +6232,10 @@ release_descriptor: static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) { struct rtl8169_private *tp = dev_instance; - u16 status = RTL_R16(tp, IntrStatus); + u32 status = rtl_get_events(tp); - if (!tp->irq_enabled || status == 0xffff || !(status & tp->irq_mask)) + if (!tp->irq_enabled || (status & 0xffff) == 0xffff || + !(status & tp->irq_mask)) return IRQ_NONE; if (unlikely(status & SYSErr)) { @@ -6332,7 +6545,7 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) stats->multicast = dev->stats.multicast; /* - * Fetch additonal counter values missing in stats collected by driver + * Fetch additional counter values missing in stats collected by driver * from tally counters. */ if (pm_runtime_active(&pdev->dev)) @@ -6556,6 +6769,7 @@ static const struct net_device_ops rtl_netdev_ops = { .ndo_stop = rtl8169_close, .ndo_get_stats64 = rtl8169_get_stats64, .ndo_start_xmit = rtl8169_start_xmit, + .ndo_features_check = rtl8169_features_check, .ndo_tx_timeout = rtl8169_tx_timeout, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = rtl8169_change_mtu, @@ -6619,6 +6833,8 @@ static void rtl_read_mac_address(struct rtl8169_private *tp, value = rtl_eri_read(tp, 0xe4); mac_addr[4] = (value >> 0) & 0xff; mac_addr[5] = (value >> 8) & 0xff; + } else if (rtl_is_8125(tp)) { + rtl_read_mac_from_reg(tp, mac_addr, MAC0_BKP); } } @@ -6692,8 +6908,6 @@ static int r8169_mdio_register(struct rtl8169_private *tp) static void rtl_hw_init_8168g(struct rtl8169_private *tp) { - u32 data; - tp->ocp_base = OCP_STD_PHY_BASE; RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN); @@ -6708,16 +6922,37 @@ static void rtl_hw_init_8168g(struct rtl8169_private *tp) msleep(1); RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); - data = r8168_mac_ocp_read(tp, 0xe8de); - data &= ~(1 << 14); - r8168_mac_ocp_write(tp, 0xe8de, data); + r8168_mac_ocp_modify(tp, 0xe8de, BIT(14), 0); if (!rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42)) return; - data = r8168_mac_ocp_read(tp, 0xe8de); - data |= (1 << 15); - r8168_mac_ocp_write(tp, 0xe8de, data); + r8168_mac_ocp_modify(tp, 0xe8de, 0, BIT(15)); + + rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42); +} + +static void rtl_hw_init_8125(struct rtl8169_private *tp) +{ + tp->ocp_base = OCP_STD_PHY_BASE; + + RTL_W32(tp, MISC, RTL_R32(tp, MISC) | RXDV_GATED_EN); + + if (!rtl_udelay_loop_wait_high(tp, &rtl_rxtx_empty_cond, 100, 42)) + return; + + RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) & ~(CmdTxEnb | CmdRxEnb)); + msleep(1); + RTL_W8(tp, MCU, RTL_R8(tp, MCU) & ~NOW_IS_OOB); + + r8168_mac_ocp_modify(tp, 0xe8de, BIT(14), 0); + + if (!rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42)) + return; + + r8168_mac_ocp_write(tp, 0xc0aa, 0x07d0); + r8168_mac_ocp_write(tp, 0xc0a6, 0x0150); + r8168_mac_ocp_write(tp, 0xc01e, 0x5555); rtl_udelay_loop_wait_high(tp, &rtl_link_list_ready_cond, 100, 42); } @@ -6731,6 +6966,9 @@ static void rtl_hw_initialize(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48: rtl_hw_init_8168g(tp); break; + case RTL_GIGA_MAC_VER_60 ... RTL_GIGA_MAC_VER_61: + rtl_hw_init_8125(tp); + break; default: break; } @@ -6794,7 +7032,7 @@ static void rtl_init_mac_address(struct rtl8169_private *tp) { struct net_device *dev = tp->dev; u8 *mac_addr = dev->dev_addr; - int rc, i; + int rc; rc = eth_platform_get_mac_address(tp_to_dev(tp), mac_addr); if (!rc) @@ -6804,8 +7042,7 @@ static void rtl_init_mac_address(struct rtl8169_private *tp) if (is_valid_ether_addr(mac_addr)) goto done; - for (i = 0; i < ETH_ALEN; i++) - mac_addr[i] = RTL_R8(tp, MAC0 + i); + rtl_read_mac_from_reg(tp, mac_addr, MAC0); if (is_valid_ether_addr(mac_addr)) goto done; @@ -6917,11 +7154,9 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) netif_napi_add(dev, &tp->napi, rtl8169_poll, NAPI_POLL_WEIGHT); - /* don't enable SG, IP_CSUM and TSO by default - it might not work - * properly for all devices */ - dev->features |= NETIF_F_RXCSUM | - NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; - + dev->features |= NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | + NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_RX; dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX; @@ -6929,8 +7164,10 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_HIGHDMA; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; - tp->cp_cmd |= RxChkSum | RxVlan; - + tp->cp_cmd |= RxChkSum; + /* RTL8125 uses register RxConfig for VLAN offloading config */ + if (!rtl_is_8125(tp)) + tp->cp_cmd |= RxVlan; /* * Pretend we are using VLANs; This bypasses a nasty bug where * Interrupts stop flowing on high load on 8110SCd controllers. @@ -6939,8 +7176,22 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* Disallow toggling */ dev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_RX; - if (rtl_chip_supports_csum_v2(tp)) + if (rtl_chip_supports_csum_v2(tp)) { dev->hw_features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6; + dev->features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6; + dev->gso_max_size = RTL_GSO_MAX_SIZE_V2; + dev->gso_max_segs = RTL_GSO_MAX_SEGS_V2; + } else { + dev->gso_max_size = RTL_GSO_MAX_SIZE_V1; + dev->gso_max_segs = RTL_GSO_MAX_SEGS_V1; + } + + /* RTL8168e-vl has a HW issue with TSO */ + if (tp->mac_version == RTL_GIGA_MAC_VER_34) { + dev->vlan_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); + dev->hw_features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); + dev->features &= ~(NETIF_F_ALL_TSO | NETIF_F_SG); + } dev->hw_features |= NETIF_F_RXALL; dev->hw_features |= NETIF_F_RXFCS; diff --git a/drivers/net/ethernet/renesas/ravb.h b/drivers/net/ethernet/renesas/ravb.h index ac9195add811..a9c89d5d8898 100644 --- a/drivers/net/ethernet/renesas/ravb.h +++ b/drivers/net/ethernet/renesas/ravb.h @@ -193,16 +193,12 @@ enum ravb_reg { GECMR = 0x05b0, MAHR = 0x05c0, MALR = 0x05c8, - TROCR = 0x0700, /* Undocumented? */ - CDCR = 0x0708, /* Undocumented? */ - LCCR = 0x0710, /* Undocumented? */ + TROCR = 0x0700, /* R-Car Gen3 only */ CEFCR = 0x0740, FRECR = 0x0748, TSFRCR = 0x0750, TLFRCR = 0x0758, RFCR = 0x0760, - CERCR = 0x0768, /* Undocumented? */ - CEECR = 0x0770, /* Undocumented? */ MAFCR = 0x0778, }; @@ -220,7 +216,6 @@ enum CCC_BIT { CCC_CSEL_HPB = 0x00010000, CCC_CSEL_ETH_TX = 0x00020000, CCC_CSEL_GMII_REF = 0x00030000, - CCC_BOC = 0x00100000, /* Undocumented? */ CCC_LBME = 0x01000000, }; @@ -317,7 +312,7 @@ enum UFCD_BIT { /* SFO */ enum SFO_BIT { - SFO_FPB = 0x0000003F, + SFO_FBP = 0x0000003F, }; /* RTC */ diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c index 6cacd5e893ac..de9aa8c47f1c 100644 --- a/drivers/net/ethernet/renesas/ravb_main.c +++ b/drivers/net/ethernet/renesas/ravb_main.c @@ -447,12 +447,6 @@ static int ravb_dmac_init(struct net_device *ndev) ravb_ring_format(ndev, RAVB_BE); ravb_ring_format(ndev, RAVB_NC); -#if defined(__LITTLE_ENDIAN) - ravb_modify(ndev, CCC, CCC_BOC, 0); -#else - ravb_modify(ndev, CCC, CCC_BOC, CCC_BOC); -#endif - /* Set AVB RX */ ravb_write(ndev, RCR_EFFS | RCR_ENCF | RCR_ETS0 | RCR_ESF | 0x18000000, RCR); @@ -1627,17 +1621,10 @@ static struct net_device_stats *ravb_get_stats(struct net_device *ndev) stats0 = &priv->stats[RAVB_BE]; stats1 = &priv->stats[RAVB_NC]; - nstats->tx_dropped += ravb_read(ndev, TROCR); - ravb_write(ndev, 0, TROCR); /* (write clear) */ - nstats->collisions += ravb_read(ndev, CDCR); - ravb_write(ndev, 0, CDCR); /* (write clear) */ - nstats->tx_carrier_errors += ravb_read(ndev, LCCR); - ravb_write(ndev, 0, LCCR); /* (write clear) */ - - nstats->tx_carrier_errors += ravb_read(ndev, CERCR); - ravb_write(ndev, 0, CERCR); /* (write clear) */ - nstats->tx_carrier_errors += ravb_read(ndev, CEECR); - ravb_write(ndev, 0, CEECR); /* (write clear) */ + if (priv->chip_id == RCAR_GEN3) { + nstats->tx_dropped += ravb_read(ndev, TROCR); + ravb_write(ndev, 0, TROCR); /* (write clear) */ + } nstats->rx_packets = stats0->rx_packets + stats1->rx_packets; nstats->tx_packets = stats0->tx_packets + stats1->tx_packets; diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 2c5d3f5b84dd..786b158bd305 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2189,6 +2189,9 @@ static int rocker_router_fib_event(struct notifier_block *nb, struct rocker_fib_event_work *fib_work; struct fib_notifier_info *info = ptr; + if (!net_eq(info->net, &init_net)) + return NOTIFY_DONE; + if (info->family != AF_INET) return NOTIFY_DONE; diff --git a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c index d2c48116f181..2412c87561e0 100644 --- a/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c +++ b/drivers/net/ethernet/samsung/sxgbe/sxgbe_platform.c @@ -78,7 +78,6 @@ static int sxgbe_platform_probe(struct platform_device *pdev) { int ret; int i, chan; - struct resource *res; struct device *dev = &pdev->dev; void __iomem *addr; struct sxgbe_priv_data *priv = NULL; @@ -88,8 +87,7 @@ static int sxgbe_platform_probe(struct platform_device *pdev) struct device_node *node = dev->of_node; /* Get memory resource */ - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - addr = devm_ioremap_resource(dev, res); + addr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(addr)) return PTR_ERR(addr); diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 16d6952c312a..0ec13f520e90 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -508,7 +508,7 @@ static ssize_t efx_ef10_show_link_control_flag(struct device *dev, struct device_attribute *attr, char *buf) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", ((efx->mcdi->fn_flags) & @@ -520,7 +520,7 @@ static ssize_t efx_ef10_show_primary_flag(struct device *dev, struct device_attribute *attr, char *buf) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", ((efx->mcdi->fn_flags) & diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index ab58b837df47..2fef7402233e 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -2517,7 +2517,7 @@ static struct notifier_block efx_netdev_notifier = { static ssize_t show_phy_type(struct device *dev, struct device_attribute *attr, char *buf) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", efx->phy_type); } static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL); @@ -2526,7 +2526,7 @@ static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL); static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr, char *buf) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); struct efx_mcdi_iface *mcdi = efx_mcdi(efx); return scnprintf(buf, PAGE_SIZE, "%d\n", mcdi->logging_enabled); @@ -2534,7 +2534,7 @@ static ssize_t show_mcdi_log(struct device *dev, struct device_attribute *attr, static ssize_t set_mcdi_log(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); struct efx_mcdi_iface *mcdi = efx_mcdi(efx); bool enable = count > 0 && *buf != '0'; @@ -3654,7 +3654,7 @@ static int efx_pci_sriov_configure(struct pci_dev *dev, int num_vfs) static int efx_pm_freeze(struct device *dev) { - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); rtnl_lock(); @@ -3675,7 +3675,7 @@ static int efx_pm_freeze(struct device *dev) static int efx_pm_thaw(struct device *dev) { int rc; - struct efx_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct efx_nic *efx = dev_get_drvdata(dev); rtnl_lock(); diff --git a/drivers/net/ethernet/sfc/falcon/efx.c b/drivers/net/ethernet/sfc/falcon/efx.c index 9b15c39ac670..eecc348b1c32 100644 --- a/drivers/net/ethernet/sfc/falcon/efx.c +++ b/drivers/net/ethernet/sfc/falcon/efx.c @@ -2256,7 +2256,7 @@ static struct notifier_block ef4_netdev_notifier = { static ssize_t show_phy_type(struct device *dev, struct device_attribute *attr, char *buf) { - struct ef4_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct ef4_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", efx->phy_type); } static DEVICE_ATTR(phy_type, 0444, show_phy_type, NULL); @@ -2999,7 +2999,7 @@ static int ef4_pci_probe(struct pci_dev *pci_dev, static int ef4_pm_freeze(struct device *dev) { - struct ef4_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct ef4_nic *efx = dev_get_drvdata(dev); rtnl_lock(); @@ -3020,7 +3020,7 @@ static int ef4_pm_freeze(struct device *dev) static int ef4_pm_thaw(struct device *dev) { int rc; - struct ef4_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct ef4_nic *efx = dev_get_drvdata(dev); rtnl_lock(); diff --git a/drivers/net/ethernet/sfc/falcon/falcon_boards.c b/drivers/net/ethernet/sfc/falcon/falcon_boards.c index 839189dab98e..605f486fa675 100644 --- a/drivers/net/ethernet/sfc/falcon/falcon_boards.c +++ b/drivers/net/ethernet/sfc/falcon/falcon_boards.c @@ -357,7 +357,7 @@ fail_on: static ssize_t show_phy_flash_cfg(struct device *dev, struct device_attribute *attr, char *buf) { - struct ef4_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct ef4_nic *efx = dev_get_drvdata(dev); return sprintf(buf, "%d\n", !!(efx->phy_mode & PHY_MODE_SPECIAL)); } @@ -365,7 +365,7 @@ static ssize_t set_phy_flash_cfg(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - struct ef4_nic *efx = pci_get_drvdata(to_pci_dev(dev)); + struct ef4_nic *efx = dev_get_drvdata(dev); enum ef4_phy_mode old_mode, new_mode; int err; @@ -454,13 +454,13 @@ static int sfe4001_init(struct ef4_nic *efx) #if IS_ENABLED(CONFIG_SENSORS_LM90) board->hwmon_client = - i2c_new_device(&board->i2c_adap, &sfe4001_hwmon_info); + i2c_new_client_device(&board->i2c_adap, &sfe4001_hwmon_info); #else board->hwmon_client = - i2c_new_dummy(&board->i2c_adap, sfe4001_hwmon_info.addr); + i2c_new_dummy_device(&board->i2c_adap, sfe4001_hwmon_info.addr); #endif - if (!board->hwmon_client) - return -EIO; + if (IS_ERR(board->hwmon_client)) + return PTR_ERR(board->hwmon_client); /* Raise board/PHY high limit from 85 to 90 degrees Celsius */ rc = i2c_smbus_write_byte_data(board->hwmon_client, @@ -468,9 +468,9 @@ static int sfe4001_init(struct ef4_nic *efx) if (rc) goto fail_hwmon; - board->ioexp_client = i2c_new_dummy(&board->i2c_adap, PCA9539); - if (!board->ioexp_client) { - rc = -EIO; + board->ioexp_client = i2c_new_dummy_device(&board->i2c_adap, PCA9539); + if (IS_ERR(board->ioexp_client)) { + rc = PTR_ERR(board->ioexp_client); goto fail_hwmon; } diff --git a/drivers/net/ethernet/sfc/falcon/rx.c b/drivers/net/ethernet/sfc/falcon/rx.c index fd850d3d8ec0..05ea3523890a 100644 --- a/drivers/net/ethernet/sfc/falcon/rx.c +++ b/drivers/net/ethernet/sfc/falcon/rx.c @@ -424,7 +424,6 @@ ef4_rx_packet_gro(struct ef4_channel *channel, struct ef4_rx_buffer *rx_buf, unsigned int n_frags, u8 *eh) { struct napi_struct *napi = &channel->napi_str; - gro_result_t gro_result; struct ef4_nic *efx = channel->efx; struct sk_buff *skb; @@ -460,9 +459,7 @@ ef4_rx_packet_gro(struct ef4_channel *channel, struct ef4_rx_buffer *rx_buf, skb_record_rx_queue(skb, channel->rx_queue.core_index); - gro_result = napi_gro_frags(napi); - if (gro_result != GRO_DROP) - channel->irq_mod_score += 2; + napi_gro_frags(napi); } /* Allocate and construct an SKB around page fragments */ diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index d5db045535d3..85ec07f5a674 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -412,7 +412,6 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf, unsigned int n_frags, u8 *eh) { struct napi_struct *napi = &channel->napi_str; - gro_result_t gro_result; struct efx_nic *efx = channel->efx; struct sk_buff *skb; @@ -449,9 +448,7 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf, skb_record_rx_queue(skb, channel->rx_queue.core_index); - gro_result = napi_gro_frags(napi); - if (gro_result != GRO_DROP) - channel->irq_mod_score += 2; + napi_gro_frags(napi); } /* Allocate and construct an SKB around page fragments */ diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 31ec56091a5d..65e81ec1b314 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -274,7 +274,7 @@ static void efx_skb_copy_bits_to_pio(struct efx_nic *efx, struct sk_buff *skb, vaddr = kmap_atomic(skb_frag_page(f)); - efx_memcpy_toio_aligned_cb(efx, piobuf, vaddr + f->page_offset, + efx_memcpy_toio_aligned_cb(efx, piobuf, vaddr + skb_frag_off(f), skb_frag_size(f), copy_buf); kunmap_atomic(vaddr); } diff --git a/drivers/net/ethernet/sgi/ioc3-eth.c b/drivers/net/ethernet/sgi/ioc3-eth.c index 358e66b81926..deb636d653f3 100644 --- a/drivers/net/ethernet/sgi/ioc3-eth.c +++ b/drivers/net/ethernet/sgi/ioc3-eth.c @@ -1,9 +1,5 @@ -/* - * This file is subject to the terms and conditions of the GNU General Public - * License. See the file "COPYING" in the main directory of this archive - * for more details. - * - * Driver for SGI's IOC3 based Ethernet cards as found in the PCI card. +// SPDX-License-Identifier: GPL-2.0 +/* Driver for SGI's IOC3 based Ethernet cards as found in the PCI card. * * Copyright (C) 1999, 2000, 01, 03, 06 Ralf Baechle * Copyright (C) 1995, 1999, 2000, 2001 by Silicon Graphics, Inc. @@ -15,11 +11,8 @@ * * To do: * - * o Handle allocation failures in ioc3_alloc_skb() more gracefully. - * o Handle allocation failures in ioc3_init_rings(). * o Use prefetching for large packets. What is a good lower limit for * prefetching? - * o We're probably allocating a bit too much memory. * o Use hardware checksums. * o Convert to using a IOC3 meta driver. * o Which PHYs might possibly be attached to the IOC3 in real live, @@ -39,10 +32,10 @@ #include <linux/crc32.h> #include <linux/mii.h> #include <linux/in.h> +#include <linux/io.h> #include <linux/ip.h> #include <linux/tcp.h> #include <linux/udp.h> -#include <linux/dma-mapping.h> #include <linux/gfp.h> #ifdef CONFIG_SERIAL_8250 @@ -55,32 +48,52 @@ #include <linux/etherdevice.h> #include <linux/ethtool.h> #include <linux/skbuff.h> +#include <linux/dma-direct.h> + #include <net/ip.h> #include <asm/byteorder.h> -#include <asm/io.h> #include <asm/pgtable.h> #include <linux/uaccess.h> #include <asm/sn/types.h> #include <asm/sn/ioc3.h> #include <asm/pci/bridge.h> -/* - * 64 RX buffers. This is tunable in the range of 16 <= x < 512. The - * value must be a power of two. +/* Number of RX buffers. This is tunable in the range of 16 <= x < 512. + * The value must be a power of two. */ -#define RX_BUFFS 64 +#define RX_BUFFS 64 +#define RX_RING_ENTRIES 512 /* fixed in hardware */ +#define RX_RING_MASK (RX_RING_ENTRIES - 1) +#define RX_RING_SIZE (RX_RING_ENTRIES * sizeof(u64)) + +/* 128 TX buffers (not tunable) */ +#define TX_RING_ENTRIES 128 +#define TX_RING_MASK (TX_RING_ENTRIES - 1) +#define TX_RING_SIZE (TX_RING_ENTRIES * sizeof(struct ioc3_etxd)) + +/* IOC3 does dma transfers in 128 byte blocks */ +#define IOC3_DMA_XFER_LEN 128UL + +/* Every RX buffer starts with 8 byte descriptor data */ +#define RX_OFFSET (sizeof(struct ioc3_erxbuf) + NET_IP_ALIGN) +#define RX_BUF_SIZE (13 * IOC3_DMA_XFER_LEN) -#define ETCSR_FD ((17<<ETCSR_IPGR2_SHIFT) | (11<<ETCSR_IPGR1_SHIFT) | 21) -#define ETCSR_HD ((21<<ETCSR_IPGR2_SHIFT) | (21<<ETCSR_IPGR1_SHIFT) | 21) +#define ETCSR_FD ((21 << ETCSR_IPGR2_SHIFT) | (21 << ETCSR_IPGR1_SHIFT) | 21) +#define ETCSR_HD ((17 << ETCSR_IPGR2_SHIFT) | (11 << ETCSR_IPGR1_SHIFT) | 21) /* Private per NIC data of the driver. */ struct ioc3_private { - struct ioc3 *regs; + struct ioc3_ethregs *regs; + struct ioc3 *all_regs; + struct device *dma_dev; + u32 *ssram; unsigned long *rxr; /* pointer to receiver ring */ struct ioc3_etxd *txr; - struct sk_buff *rx_skbs[512]; - struct sk_buff *tx_skbs[128]; + dma_addr_t rxr_dma; + dma_addr_t txr_dma; + struct sk_buff *rx_skbs[RX_RING_ENTRIES]; + struct sk_buff *tx_skbs[TX_RING_ENTRIES]; int rx_ci; /* RX consumer index */ int rx_pi; /* RX producer index */ int tx_ci; /* TX consumer index */ @@ -102,190 +115,138 @@ static void ioc3_set_multicast_list(struct net_device *dev); static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev); static void ioc3_timeout(struct net_device *dev); static inline unsigned int ioc3_hash(const unsigned char *addr); +static void ioc3_start(struct ioc3_private *ip); static inline void ioc3_stop(struct ioc3_private *ip); static void ioc3_init(struct net_device *dev); +static int ioc3_alloc_rx_bufs(struct net_device *dev); +static void ioc3_free_rx_bufs(struct ioc3_private *ip); +static inline void ioc3_clean_tx_ring(struct ioc3_private *ip); static const char ioc3_str[] = "IOC3 Ethernet"; static const struct ethtool_ops ioc3_ethtool_ops; -/* We use this to acquire receive skb's that we can DMA directly into. */ - -#define IOC3_CACHELINE 128UL static inline unsigned long aligned_rx_skb_addr(unsigned long addr) { - return (~addr + 1) & (IOC3_CACHELINE - 1UL); + return (~addr + 1) & (IOC3_DMA_XFER_LEN - 1UL); } -static inline struct sk_buff * ioc3_alloc_skb(unsigned long length, - unsigned int gfp_mask) +static inline int ioc3_alloc_skb(struct ioc3_private *ip, struct sk_buff **skb, + struct ioc3_erxbuf **rxb, dma_addr_t *rxb_dma) { - struct sk_buff *skb; + struct sk_buff *new_skb; + dma_addr_t d; + int offset; + + new_skb = alloc_skb(RX_BUF_SIZE + IOC3_DMA_XFER_LEN - 1, GFP_ATOMIC); + if (!new_skb) + return -ENOMEM; + + /* ensure buffer is aligned to IOC3_DMA_XFER_LEN */ + offset = aligned_rx_skb_addr((unsigned long)new_skb->data); + if (offset) + skb_reserve(new_skb, offset); - skb = alloc_skb(length + IOC3_CACHELINE - 1, gfp_mask); - if (likely(skb)) { - int offset = aligned_rx_skb_addr((unsigned long) skb->data); - if (offset) - skb_reserve(skb, offset); + d = dma_map_single(ip->dma_dev, new_skb->data, + RX_BUF_SIZE, DMA_FROM_DEVICE); + + if (dma_mapping_error(ip->dma_dev, d)) { + dev_kfree_skb_any(new_skb); + return -ENOMEM; } + *rxb_dma = d; + *rxb = (struct ioc3_erxbuf *)new_skb->data; + skb_reserve(new_skb, RX_OFFSET); + *skb = new_skb; - return skb; + return 0; } -static inline unsigned long ioc3_map(void *ptr, unsigned long vdev) +#ifdef CONFIG_PCI_XTALK_BRIDGE +static inline unsigned long ioc3_map(dma_addr_t addr, unsigned long attr) { -#ifdef CONFIG_SGI_IP27 - vdev <<= 57; /* Shift to PCI64_ATTR_VIRTUAL */ + return (addr & ~PCI64_ATTR_BAR) | attr; +} - return vdev | (0xaUL << PCI64_ATTR_TARG_SHFT) | PCI64_ATTR_PREF | - ((unsigned long)ptr & TO_PHYS_MASK); +#define ERBAR_VAL (ERBAR_BARRIER_BIT << ERBAR_RXBARR_SHIFT) #else - return virt_to_bus(ptr); -#endif +static inline unsigned long ioc3_map(dma_addr_t addr, unsigned long attr) +{ + return addr; } -/* BEWARE: The IOC3 documentation documents the size of rx buffers as - 1644 while it's actually 1664. This one was nasty to track down ... */ -#define RX_OFFSET 10 -#define RX_BUF_ALLOC_SIZE (1664 + RX_OFFSET + IOC3_CACHELINE) - -/* DMA barrier to separate cached and uncached accesses. */ -#define BARRIER() \ - __asm__("sync" ::: "memory") - +#define ERBAR_VAL 0 +#endif #define IOC3_SIZE 0x100000 -/* - * IOC3 is a big endian device - * - * Unorthodox but makes the users of these macros more readable - the pointer - * to the IOC3's memory mapped registers is expected as struct ioc3 * ioc3 - * in the environment. - */ -#define ioc3_r_mcr() be32_to_cpu(ioc3->mcr) -#define ioc3_w_mcr(v) do { ioc3->mcr = cpu_to_be32(v); } while (0) -#define ioc3_w_gpcr_s(v) do { ioc3->gpcr_s = cpu_to_be32(v); } while (0) -#define ioc3_r_emcr() be32_to_cpu(ioc3->emcr) -#define ioc3_w_emcr(v) do { ioc3->emcr = cpu_to_be32(v); } while (0) -#define ioc3_r_eisr() be32_to_cpu(ioc3->eisr) -#define ioc3_w_eisr(v) do { ioc3->eisr = cpu_to_be32(v); } while (0) -#define ioc3_r_eier() be32_to_cpu(ioc3->eier) -#define ioc3_w_eier(v) do { ioc3->eier = cpu_to_be32(v); } while (0) -#define ioc3_r_ercsr() be32_to_cpu(ioc3->ercsr) -#define ioc3_w_ercsr(v) do { ioc3->ercsr = cpu_to_be32(v); } while (0) -#define ioc3_r_erbr_h() be32_to_cpu(ioc3->erbr_h) -#define ioc3_w_erbr_h(v) do { ioc3->erbr_h = cpu_to_be32(v); } while (0) -#define ioc3_r_erbr_l() be32_to_cpu(ioc3->erbr_l) -#define ioc3_w_erbr_l(v) do { ioc3->erbr_l = cpu_to_be32(v); } while (0) -#define ioc3_r_erbar() be32_to_cpu(ioc3->erbar) -#define ioc3_w_erbar(v) do { ioc3->erbar = cpu_to_be32(v); } while (0) -#define ioc3_r_ercir() be32_to_cpu(ioc3->ercir) -#define ioc3_w_ercir(v) do { ioc3->ercir = cpu_to_be32(v); } while (0) -#define ioc3_r_erpir() be32_to_cpu(ioc3->erpir) -#define ioc3_w_erpir(v) do { ioc3->erpir = cpu_to_be32(v); } while (0) -#define ioc3_r_ertr() be32_to_cpu(ioc3->ertr) -#define ioc3_w_ertr(v) do { ioc3->ertr = cpu_to_be32(v); } while (0) -#define ioc3_r_etcsr() be32_to_cpu(ioc3->etcsr) -#define ioc3_w_etcsr(v) do { ioc3->etcsr = cpu_to_be32(v); } while (0) -#define ioc3_r_ersr() be32_to_cpu(ioc3->ersr) -#define ioc3_w_ersr(v) do { ioc3->ersr = cpu_to_be32(v); } while (0) -#define ioc3_r_etcdc() be32_to_cpu(ioc3->etcdc) -#define ioc3_w_etcdc(v) do { ioc3->etcdc = cpu_to_be32(v); } while (0) -#define ioc3_r_ebir() be32_to_cpu(ioc3->ebir) -#define ioc3_w_ebir(v) do { ioc3->ebir = cpu_to_be32(v); } while (0) -#define ioc3_r_etbr_h() be32_to_cpu(ioc3->etbr_h) -#define ioc3_w_etbr_h(v) do { ioc3->etbr_h = cpu_to_be32(v); } while (0) -#define ioc3_r_etbr_l() be32_to_cpu(ioc3->etbr_l) -#define ioc3_w_etbr_l(v) do { ioc3->etbr_l = cpu_to_be32(v); } while (0) -#define ioc3_r_etcir() be32_to_cpu(ioc3->etcir) -#define ioc3_w_etcir(v) do { ioc3->etcir = cpu_to_be32(v); } while (0) -#define ioc3_r_etpir() be32_to_cpu(ioc3->etpir) -#define ioc3_w_etpir(v) do { ioc3->etpir = cpu_to_be32(v); } while (0) -#define ioc3_r_emar_h() be32_to_cpu(ioc3->emar_h) -#define ioc3_w_emar_h(v) do { ioc3->emar_h = cpu_to_be32(v); } while (0) -#define ioc3_r_emar_l() be32_to_cpu(ioc3->emar_l) -#define ioc3_w_emar_l(v) do { ioc3->emar_l = cpu_to_be32(v); } while (0) -#define ioc3_r_ehar_h() be32_to_cpu(ioc3->ehar_h) -#define ioc3_w_ehar_h(v) do { ioc3->ehar_h = cpu_to_be32(v); } while (0) -#define ioc3_r_ehar_l() be32_to_cpu(ioc3->ehar_l) -#define ioc3_w_ehar_l(v) do { ioc3->ehar_l = cpu_to_be32(v); } while (0) -#define ioc3_r_micr() be32_to_cpu(ioc3->micr) -#define ioc3_w_micr(v) do { ioc3->micr = cpu_to_be32(v); } while (0) -#define ioc3_r_midr_r() be32_to_cpu(ioc3->midr_r) -#define ioc3_w_midr_r(v) do { ioc3->midr_r = cpu_to_be32(v); } while (0) -#define ioc3_r_midr_w() be32_to_cpu(ioc3->midr_w) -#define ioc3_w_midr_w(v) do { ioc3->midr_w = cpu_to_be32(v); } while (0) - static inline u32 mcr_pack(u32 pulse, u32 sample) { return (pulse << 10) | (sample << 2); } -static int nic_wait(struct ioc3 *ioc3) +static int nic_wait(u32 __iomem *mcr) { - u32 mcr; + u32 m; - do { - mcr = ioc3_r_mcr(); - } while (!(mcr & 2)); + do { + m = readl(mcr); + } while (!(m & 2)); - return mcr & 1; + return m & 1; } -static int nic_reset(struct ioc3 *ioc3) +static int nic_reset(u32 __iomem *mcr) { - int presence; + int presence; - ioc3_w_mcr(mcr_pack(500, 65)); - presence = nic_wait(ioc3); + writel(mcr_pack(500, 65), mcr); + presence = nic_wait(mcr); - ioc3_w_mcr(mcr_pack(0, 500)); - nic_wait(ioc3); + writel(mcr_pack(0, 500), mcr); + nic_wait(mcr); - return presence; + return presence; } -static inline int nic_read_bit(struct ioc3 *ioc3) +static inline int nic_read_bit(u32 __iomem *mcr) { int result; - ioc3_w_mcr(mcr_pack(6, 13)); - result = nic_wait(ioc3); - ioc3_w_mcr(mcr_pack(0, 100)); - nic_wait(ioc3); + writel(mcr_pack(6, 13), mcr); + result = nic_wait(mcr); + writel(mcr_pack(0, 100), mcr); + nic_wait(mcr); return result; } -static inline void nic_write_bit(struct ioc3 *ioc3, int bit) +static inline void nic_write_bit(u32 __iomem *mcr, int bit) { if (bit) - ioc3_w_mcr(mcr_pack(6, 110)); + writel(mcr_pack(6, 110), mcr); else - ioc3_w_mcr(mcr_pack(80, 30)); + writel(mcr_pack(80, 30), mcr); - nic_wait(ioc3); + nic_wait(mcr); } -/* - * Read a byte from an iButton device +/* Read a byte from an iButton device */ -static u32 nic_read_byte(struct ioc3 *ioc3) +static u32 nic_read_byte(u32 __iomem *mcr) { u32 result = 0; int i; for (i = 0; i < 8; i++) - result = (result >> 1) | (nic_read_bit(ioc3) << 7); + result = (result >> 1) | (nic_read_bit(mcr) << 7); return result; } -/* - * Write a byte to an iButton device +/* Write a byte to an iButton device */ -static void nic_write_byte(struct ioc3 *ioc3, int byte) +static void nic_write_byte(u32 __iomem *mcr, int byte) { int i, bit; @@ -293,26 +254,26 @@ static void nic_write_byte(struct ioc3 *ioc3, int byte) bit = byte & 1; byte >>= 1; - nic_write_bit(ioc3, bit); + nic_write_bit(mcr, bit); } } -static u64 nic_find(struct ioc3 *ioc3, int *last) +static u64 nic_find(u32 __iomem *mcr, int *last) { int a, b, index, disc; u64 address = 0; - nic_reset(ioc3); + nic_reset(mcr); /* Search ROM. */ - nic_write_byte(ioc3, 0xf0); + nic_write_byte(mcr, 0xf0); /* Algorithm from ``Book of iButton Standards''. */ for (index = 0, disc = 0; index < 64; index++) { - a = nic_read_bit(ioc3); - b = nic_read_bit(ioc3); + a = nic_read_bit(mcr); + b = nic_read_bit(mcr); if (a && b) { - printk("NIC search failed (not fatal).\n"); + pr_warn("NIC search failed (not fatal).\n"); *last = 0; return 0; } @@ -323,16 +284,17 @@ static u64 nic_find(struct ioc3 *ioc3, int *last) } else if (index > *last) { address &= ~(1UL << index); disc = index; - } else if ((address & (1UL << index)) == 0) + } else if ((address & (1UL << index)) == 0) { disc = index; - nic_write_bit(ioc3, address & (1UL << index)); + } + nic_write_bit(mcr, address & (1UL << index)); continue; } else { if (a) address |= 1UL << index; else address &= ~(1UL << index); - nic_write_bit(ioc3, a); + nic_write_bit(mcr, a); continue; } } @@ -342,7 +304,7 @@ static u64 nic_find(struct ioc3 *ioc3, int *last) return address; } -static int nic_init(struct ioc3 *ioc3) +static int nic_init(u32 __iomem *mcr) { const char *unknown = "unknown"; const char *type = unknown; @@ -352,7 +314,8 @@ static int nic_init(struct ioc3 *ioc3) while (1) { u64 reg; - reg = nic_find(ioc3, &save); + + reg = nic_find(mcr, &save); switch (reg & 0xff) { case 0x91: @@ -366,12 +329,12 @@ static int nic_init(struct ioc3 *ioc3) continue; } - nic_reset(ioc3); + nic_reset(mcr); /* Match ROM. */ - nic_write_byte(ioc3, 0x55); + nic_write_byte(mcr, 0x55); for (i = 0; i < 8; i++) - nic_write_byte(ioc3, (reg >> (i << 3)) & 0xff); + nic_write_byte(mcr, (reg >> (i << 3)) & 0xff); reg >>= 8; /* Shift out type. */ for (i = 0; i < 6; i++) { @@ -382,52 +345,50 @@ static int nic_init(struct ioc3 *ioc3) break; } - printk("Found %s NIC", type); + pr_info("Found %s NIC", type); if (type != unknown) - printk (" registration number %pM, CRC %02x", serial, crc); - printk(".\n"); + pr_cont(" registration number %pM, CRC %02x", serial, crc); + pr_cont(".\n"); return 0; } -/* - * Read the NIC (Number-In-a-Can) device used to store the MAC address on +/* Read the NIC (Number-In-a-Can) device used to store the MAC address on * SN0 / SN00 nodeboards and PCI cards. */ static void ioc3_get_eaddr_nic(struct ioc3_private *ip) { - struct ioc3 *ioc3 = ip->regs; - u8 nic[14]; + u32 __iomem *mcr = &ip->all_regs->mcr; int tries = 2; /* There may be some problem with the battery? */ + u8 nic[14]; int i; - ioc3_w_gpcr_s(1 << 21); + writel(1 << 21, &ip->all_regs->gpcr_s); while (tries--) { - if (!nic_init(ioc3)) + if (!nic_init(mcr)) break; udelay(500); } if (tries < 0) { - printk("Failed to read MAC address\n"); + pr_err("Failed to read MAC address\n"); return; } /* Read Memory. */ - nic_write_byte(ioc3, 0xf0); - nic_write_byte(ioc3, 0x00); - nic_write_byte(ioc3, 0x00); + nic_write_byte(mcr, 0xf0); + nic_write_byte(mcr, 0x00); + nic_write_byte(mcr, 0x00); for (i = 13; i >= 0; i--) - nic[i] = nic_read_byte(ioc3); + nic[i] = nic_read_byte(mcr); for (i = 2; i < 8; i++) ip->dev->dev_addr[i - 2] = nic[i]; } -/* - * Ok, this is hosed by design. It's necessary to know what machine the +/* Ok, this is hosed by design. It's necessary to know what machine the * NIC is in in order to know how to read the NIC address. We also have * to know if it's a PCI card or a NIC in on the node board ... */ @@ -435,17 +396,21 @@ static void ioc3_get_eaddr(struct ioc3_private *ip) { ioc3_get_eaddr_nic(ip); - printk("Ethernet address is %pM.\n", ip->dev->dev_addr); + pr_info("Ethernet address is %pM.\n", ip->dev->dev_addr); } static void __ioc3_set_mac_address(struct net_device *dev) { struct ioc3_private *ip = netdev_priv(dev); - struct ioc3 *ioc3 = ip->regs; - ioc3_w_emar_h((dev->dev_addr[5] << 8) | dev->dev_addr[4]); - ioc3_w_emar_l((dev->dev_addr[3] << 24) | (dev->dev_addr[2] << 16) | - (dev->dev_addr[1] << 8) | dev->dev_addr[0]); + writel((dev->dev_addr[5] << 8) | + dev->dev_addr[4], + &ip->regs->emar_h); + writel((dev->dev_addr[3] << 24) | + (dev->dev_addr[2] << 16) | + (dev->dev_addr[1] << 8) | + dev->dev_addr[0], + &ip->regs->emar_l); } static int ioc3_set_mac_address(struct net_device *dev, void *addr) @@ -462,31 +427,35 @@ static int ioc3_set_mac_address(struct net_device *dev, void *addr) return 0; } -/* - * Caller must hold the ioc3_lock ever for MII readers. This is also +/* Caller must hold the ioc3_lock ever for MII readers. This is also * used to protect the transmitter side but it's low contention. */ static int ioc3_mdio_read(struct net_device *dev, int phy, int reg) { struct ioc3_private *ip = netdev_priv(dev); - struct ioc3 *ioc3 = ip->regs; + struct ioc3_ethregs *regs = ip->regs; - while (ioc3_r_micr() & MICR_BUSY); - ioc3_w_micr((phy << MICR_PHYADDR_SHIFT) | reg | MICR_READTRIG); - while (ioc3_r_micr() & MICR_BUSY); + while (readl(®s->micr) & MICR_BUSY) + ; + writel((phy << MICR_PHYADDR_SHIFT) | reg | MICR_READTRIG, + ®s->micr); + while (readl(®s->micr) & MICR_BUSY) + ; - return ioc3_r_midr_r() & MIDR_DATA_MASK; + return readl(®s->midr_r) & MIDR_DATA_MASK; } static void ioc3_mdio_write(struct net_device *dev, int phy, int reg, int data) { struct ioc3_private *ip = netdev_priv(dev); - struct ioc3 *ioc3 = ip->regs; - - while (ioc3_r_micr() & MICR_BUSY); - ioc3_w_midr_w(data); - ioc3_w_micr((phy << MICR_PHYADDR_SHIFT) | reg); - while (ioc3_r_micr() & MICR_BUSY); + struct ioc3_ethregs *regs = ip->regs; + + while (readl(®s->micr) & MICR_BUSY) + ; + writel(data, ®s->midr_w); + writel((phy << MICR_PHYADDR_SHIFT) | reg, ®s->micr); + while (readl(®s->micr) & MICR_BUSY) + ; } static int ioc3_mii_init(struct ioc3_private *ip); @@ -494,23 +463,22 @@ static int ioc3_mii_init(struct ioc3_private *ip); static struct net_device_stats *ioc3_get_stats(struct net_device *dev) { struct ioc3_private *ip = netdev_priv(dev); - struct ioc3 *ioc3 = ip->regs; + struct ioc3_ethregs *regs = ip->regs; - dev->stats.collisions += (ioc3_r_etcdc() & ETCDC_COLLCNT_MASK); + dev->stats.collisions += readl(®s->etcdc) & ETCDC_COLLCNT_MASK; return &dev->stats; } -static void ioc3_tcpudp_checksum(struct sk_buff *skb, uint32_t hwsum, int len) +static void ioc3_tcpudp_checksum(struct sk_buff *skb, u32 hwsum, int len) { struct ethhdr *eh = eth_hdr(skb); - uint32_t csum, ehsum; unsigned int proto; - struct iphdr *ih; - uint16_t *ew; unsigned char *cp; + struct iphdr *ih; + u32 csum, ehsum; + u16 *ew; - /* - * Did hardware handle the checksum at all? The cases we can handle + /* Did hardware handle the checksum at all? The cases we can handle * are: * * - TCP and UDP checksums of IPv4 only. @@ -526,7 +494,7 @@ static void ioc3_tcpudp_checksum(struct sk_buff *skb, uint32_t hwsum, int len) if (eh->h_proto != htons(ETH_P_IP)) return; - ih = (struct iphdr *) ((char *)eh + ETH_HLEN); + ih = (struct iphdr *)((char *)eh + ETH_HLEN); if (ip_is_fragment(ih)) return; @@ -537,12 +505,12 @@ static void ioc3_tcpudp_checksum(struct sk_buff *skb, uint32_t hwsum, int len) /* Same as tx - compute csum of pseudo header */ csum = hwsum + (ih->tot_len - (ih->ihl << 2)) + - htons((uint16_t)ih->protocol) + + htons((u16)ih->protocol) + (ih->saddr >> 16) + (ih->saddr & 0xffff) + (ih->daddr >> 16) + (ih->daddr & 0xffff); /* Sum up ethernet dest addr, src addr and protocol */ - ew = (uint16_t *) eh; + ew = (u16 *)eh; ehsum = ew[0] + ew[1] + ew[2] + ew[3] + ew[4] + ew[5] + ew[6]; ehsum = (ehsum & 0xffff) + (ehsum >> 16); @@ -551,14 +519,15 @@ static void ioc3_tcpudp_checksum(struct sk_buff *skb, uint32_t hwsum, int len) csum += 0xffff ^ ehsum; /* In the next step we also subtract the 1's complement - checksum of the trailing ethernet CRC. */ + * checksum of the trailing ethernet CRC. + */ cp = (char *)eh + len; /* points at trailing CRC */ if (len & 1) { - csum += 0xffff ^ (uint16_t) ((cp[1] << 8) | cp[0]); - csum += 0xffff ^ (uint16_t) ((cp[3] << 8) | cp[2]); + csum += 0xffff ^ (u16)((cp[1] << 8) | cp[0]); + csum += 0xffff ^ (u16)((cp[3] << 8) | cp[2]); } else { - csum += 0xffff ^ (uint16_t) ((cp[0] << 8) | cp[1]); - csum += 0xffff ^ (uint16_t) ((cp[2] << 8) | cp[3]); + csum += 0xffff ^ (u16)((cp[0] << 8) | cp[1]); + csum += 0xffff ^ (u16)((cp[2] << 8) | cp[3]); } csum = (csum & 0xffff) + (csum >> 16); @@ -572,10 +541,10 @@ static inline void ioc3_rx(struct net_device *dev) { struct ioc3_private *ip = netdev_priv(dev); struct sk_buff *skb, *new_skb; - struct ioc3 *ioc3 = ip->regs; int rx_entry, n_entry, len; struct ioc3_erxbuf *rxb; unsigned long *rxr; + dma_addr_t d; u32 w0, err; rxr = ip->rxr; /* Ring base */ @@ -583,64 +552,67 @@ static inline void ioc3_rx(struct net_device *dev) n_entry = ip->rx_pi; skb = ip->rx_skbs[rx_entry]; - rxb = (struct ioc3_erxbuf *) (skb->data - RX_OFFSET); + rxb = (struct ioc3_erxbuf *)(skb->data - RX_OFFSET); w0 = be32_to_cpu(rxb->w0); while (w0 & ERXBUF_V) { err = be32_to_cpu(rxb->err); /* It's valid ... */ if (err & ERXBUF_GOODPKT) { len = ((w0 >> ERXBUF_BYTECNT_SHIFT) & 0x7ff) - 4; - skb_trim(skb, len); + skb_put(skb, len); skb->protocol = eth_type_trans(skb, dev); - new_skb = ioc3_alloc_skb(RX_BUF_ALLOC_SIZE, GFP_ATOMIC); - if (!new_skb) { + if (ioc3_alloc_skb(ip, &new_skb, &rxb, &d)) { /* Ouch, drop packet and just recycle packet - to keep the ring filled. */ + * to keep the ring filled. + */ dev->stats.rx_dropped++; new_skb = skb; + d = rxr[rx_entry]; goto next; } if (likely(dev->features & NETIF_F_RXCSUM)) ioc3_tcpudp_checksum(skb, - w0 & ERXBUF_IPCKSUM_MASK, len); + w0 & ERXBUF_IPCKSUM_MASK, + len); + + dma_unmap_single(ip->dma_dev, rxr[rx_entry], + RX_BUF_SIZE, DMA_FROM_DEVICE); netif_rx(skb); ip->rx_skbs[rx_entry] = NULL; /* Poison */ - /* Because we reserve afterwards. */ - skb_put(new_skb, (1664 + RX_OFFSET)); - rxb = (struct ioc3_erxbuf *) new_skb->data; - skb_reserve(new_skb, RX_OFFSET); - dev->stats.rx_packets++; /* Statistics */ dev->stats.rx_bytes += len; } else { /* The frame is invalid and the skb never - reached the network layer so we can just - recycle it. */ + * reached the network layer so we can just + * recycle it. + */ new_skb = skb; + d = rxr[rx_entry]; dev->stats.rx_errors++; } if (err & ERXBUF_CRCERR) /* Statistics */ dev->stats.rx_crc_errors++; if (err & ERXBUF_FRAMERR) dev->stats.rx_frame_errors++; + next: ip->rx_skbs[n_entry] = new_skb; - rxr[n_entry] = cpu_to_be64(ioc3_map(rxb, 1)); + rxr[n_entry] = cpu_to_be64(ioc3_map(d, PCI64_ATTR_BAR)); rxb->w0 = 0; /* Clear valid flag */ - n_entry = (n_entry + 1) & 511; /* Update erpir */ + n_entry = (n_entry + 1) & RX_RING_MASK; /* Update erpir */ /* Now go on to the next ring entry. */ - rx_entry = (rx_entry + 1) & 511; + rx_entry = (rx_entry + 1) & RX_RING_MASK; skb = ip->rx_skbs[rx_entry]; - rxb = (struct ioc3_erxbuf *) (skb->data - RX_OFFSET); + rxb = (struct ioc3_erxbuf *)(skb->data - RX_OFFSET); w0 = be32_to_cpu(rxb->w0); } - ioc3_w_erpir((n_entry << 3) | ERPIR_ARM); + writel((n_entry << 3) | ERPIR_ARM, &ip->regs->erpir); ip->rx_pi = n_entry; ip->rx_ci = rx_entry; } @@ -648,16 +620,16 @@ next: static inline void ioc3_tx(struct net_device *dev) { struct ioc3_private *ip = netdev_priv(dev); + struct ioc3_ethregs *regs = ip->regs; unsigned long packets, bytes; - struct ioc3 *ioc3 = ip->regs; int tx_entry, o_entry; struct sk_buff *skb; u32 etcir; spin_lock(&ip->ioc3_lock); - etcir = ioc3_r_etcir(); + etcir = readl(®s->etcir); - tx_entry = (etcir >> 7) & 127; + tx_entry = (etcir >> 7) & TX_RING_MASK; o_entry = ip->tx_ci; packets = 0; bytes = 0; @@ -669,25 +641,24 @@ static inline void ioc3_tx(struct net_device *dev) dev_consume_skb_irq(skb); ip->tx_skbs[o_entry] = NULL; - o_entry = (o_entry + 1) & 127; /* Next */ + o_entry = (o_entry + 1) & TX_RING_MASK; /* Next */ - etcir = ioc3_r_etcir(); /* More pkts sent? */ - tx_entry = (etcir >> 7) & 127; + etcir = readl(®s->etcir); /* More pkts sent? */ + tx_entry = (etcir >> 7) & TX_RING_MASK; } dev->stats.tx_packets += packets; dev->stats.tx_bytes += bytes; ip->txqlen -= packets; - if (ip->txqlen < 128) + if (netif_queue_stopped(dev) && ip->txqlen < TX_RING_ENTRIES) netif_wake_queue(dev); ip->tx_ci = o_entry; spin_unlock(&ip->ioc3_lock); } -/* - * Deal with fatal IOC3 errors. This condition might be caused by a hard or +/* Deal with fatal IOC3 errors. This condition might be caused by a hard or * software problems, so we should try to recover * more gracefully if this ever happens. In theory we might be flooded * with such error interrupts if something really goes wrong, so we might @@ -696,25 +667,33 @@ static inline void ioc3_tx(struct net_device *dev) static void ioc3_error(struct net_device *dev, u32 eisr) { struct ioc3_private *ip = netdev_priv(dev); - unsigned char *iface = dev->name; spin_lock(&ip->ioc3_lock); if (eisr & EISR_RXOFLO) - printk(KERN_ERR "%s: RX overflow.\n", iface); + net_err_ratelimited("%s: RX overflow.\n", dev->name); if (eisr & EISR_RXBUFOFLO) - printk(KERN_ERR "%s: RX buffer overflow.\n", iface); + net_err_ratelimited("%s: RX buffer overflow.\n", dev->name); if (eisr & EISR_RXMEMERR) - printk(KERN_ERR "%s: RX PCI error.\n", iface); + net_err_ratelimited("%s: RX PCI error.\n", dev->name); if (eisr & EISR_RXPARERR) - printk(KERN_ERR "%s: RX SSRAM parity error.\n", iface); + net_err_ratelimited("%s: RX SSRAM parity error.\n", dev->name); if (eisr & EISR_TXBUFUFLO) - printk(KERN_ERR "%s: TX buffer underflow.\n", iface); + net_err_ratelimited("%s: TX buffer underflow.\n", dev->name); if (eisr & EISR_TXMEMERR) - printk(KERN_ERR "%s: TX PCI error.\n", iface); + net_err_ratelimited("%s: TX PCI error.\n", dev->name); ioc3_stop(ip); + ioc3_free_rx_bufs(ip); + ioc3_clean_tx_ring(ip); + ioc3_init(dev); + if (ioc3_alloc_rx_bufs(dev)) { + netdev_err(dev, "%s: rx buffer allocation failed\n", __func__); + spin_unlock(&ip->ioc3_lock); + return; + } + ioc3_start(ip); ioc3_mii_init(ip); netif_wake_queue(dev); @@ -723,45 +702,45 @@ static void ioc3_error(struct net_device *dev, u32 eisr) } /* The interrupt handler does all of the Rx thread work and cleans up - after the Tx thread. */ -static irqreturn_t ioc3_interrupt(int irq, void *_dev) + * after the Tx thread. + */ +static irqreturn_t ioc3_interrupt(int irq, void *dev_id) { - struct net_device *dev = (struct net_device *)_dev; - struct ioc3_private *ip = netdev_priv(dev); - struct ioc3 *ioc3 = ip->regs; - const u32 enabled = EISR_RXTIMERINT | EISR_RXOFLO | EISR_RXBUFOFLO | - EISR_RXMEMERR | EISR_RXPARERR | EISR_TXBUFUFLO | - EISR_TXEXPLICIT | EISR_TXMEMERR; + struct ioc3_private *ip = netdev_priv(dev_id); + struct ioc3_ethregs *regs = ip->regs; u32 eisr; - eisr = ioc3_r_eisr() & enabled; - - ioc3_w_eisr(eisr); - (void) ioc3_r_eisr(); /* Flush */ + eisr = readl(®s->eisr); + writel(eisr, ®s->eisr); + readl(®s->eisr); /* Flush */ if (eisr & (EISR_RXOFLO | EISR_RXBUFOFLO | EISR_RXMEMERR | - EISR_RXPARERR | EISR_TXBUFUFLO | EISR_TXMEMERR)) - ioc3_error(dev, eisr); + EISR_RXPARERR | EISR_TXBUFUFLO | EISR_TXMEMERR)) + ioc3_error(dev_id, eisr); if (eisr & EISR_RXTIMERINT) - ioc3_rx(dev); + ioc3_rx(dev_id); if (eisr & EISR_TXEXPLICIT) - ioc3_tx(dev); + ioc3_tx(dev_id); return IRQ_HANDLED; } static inline void ioc3_setup_duplex(struct ioc3_private *ip) { - struct ioc3 *ioc3 = ip->regs; + struct ioc3_ethregs *regs = ip->regs; + + spin_lock_irq(&ip->ioc3_lock); if (ip->mii.full_duplex) { - ioc3_w_etcsr(ETCSR_FD); + writel(ETCSR_FD, ®s->etcsr); ip->emcr |= EMCR_DUPLEX; } else { - ioc3_w_etcsr(ETCSR_HD); + writel(ETCSR_HD, ®s->etcsr); ip->emcr &= ~EMCR_DUPLEX; } - ioc3_w_emcr(ip->emcr); + writel(ip->emcr, ®s->emcr); + + spin_unlock_irq(&ip->ioc3_lock); } static void ioc3_timer(struct timer_list *t) @@ -772,12 +751,11 @@ static void ioc3_timer(struct timer_list *t) mii_check_media(&ip->mii, 1, 0); ioc3_setup_duplex(ip); - ip->ioc3_timer.expires = jiffies + ((12 * HZ)/10); /* 1.2s */ + ip->ioc3_timer.expires = jiffies + ((12 * HZ) / 10); /* 1.2s */ add_timer(&ip->ioc3_timer); } -/* - * Try to find a PHY. There is no apparent relation between the MII addresses +/* Try to find a PHY. There is no apparent relation between the MII addresses * in the SGI documentation and what we find in reality, so we simply probe * for the PHY. It seems IOC3 PHYs usually live on address 31. One of my * onboard IOC3s has the special oddity that probing doesn't seem to find it @@ -786,8 +764,8 @@ static void ioc3_timer(struct timer_list *t) */ static int ioc3_mii_init(struct ioc3_private *ip) { - int i, found = 0, res = 0; int ioc3_phy_workaround = 1; + int i, found = 0, res = 0; u16 word; for (i = 0; i < 32; i++) { @@ -800,9 +778,9 @@ static int ioc3_mii_init(struct ioc3_private *ip) } if (!found) { - if (ioc3_phy_workaround) + if (ioc3_phy_workaround) { i = 31; - else { + } else { ip->mii.phy_id = -1; res = -ENODEV; goto out; @@ -817,27 +795,27 @@ out: static void ioc3_mii_start(struct ioc3_private *ip) { - ip->ioc3_timer.expires = jiffies + (12 * HZ)/10; /* 1.2 sec. */ + ip->ioc3_timer.expires = jiffies + (12 * HZ) / 10; /* 1.2 sec. */ add_timer(&ip->ioc3_timer); } -static inline void ioc3_clean_rx_ring(struct ioc3_private *ip) +static inline void ioc3_tx_unmap(struct ioc3_private *ip, int entry) { - struct sk_buff *skb; - int i; - - for (i = ip->rx_ci; i & 15; i++) { - ip->rx_skbs[ip->rx_pi] = ip->rx_skbs[ip->rx_ci]; - ip->rxr[ip->rx_pi++] = ip->rxr[ip->rx_ci++]; + struct ioc3_etxd *desc; + u32 cmd, bufcnt, len; + + desc = &ip->txr[entry]; + cmd = be32_to_cpu(desc->cmd); + bufcnt = be32_to_cpu(desc->bufcnt); + if (cmd & ETXD_B1V) { + len = (bufcnt & ETXD_B1CNT_MASK) >> ETXD_B1CNT_SHIFT; + dma_unmap_single(ip->dma_dev, be64_to_cpu(desc->p1), + len, DMA_TO_DEVICE); } - ip->rx_pi &= 511; - ip->rx_ci &= 511; - - for (i = ip->rx_ci; i != ip->rx_pi; i = (i+1) & 511) { - struct ioc3_erxbuf *rxb; - skb = ip->rx_skbs[i]; - rxb = (struct ioc3_erxbuf *) (skb->data - RX_OFFSET); - rxb->w0 = 0; + if (cmd & ETXD_B2V) { + len = (bufcnt & ETXD_B2CNT_MASK) >> ETXD_B2CNT_SHIFT; + dma_unmap_single(ip->dma_dev, be64_to_cpu(desc->p2), + len, DMA_TO_DEVICE); } } @@ -846,9 +824,10 @@ static inline void ioc3_clean_tx_ring(struct ioc3_private *ip) struct sk_buff *skb; int i; - for (i=0; i < 128; i++) { + for (i = 0; i < TX_RING_ENTRIES; i++) { skb = ip->tx_skbs[i]; if (skb) { + ioc3_tx_unmap(ip, i); ip->tx_skbs[i] = NULL; dev_kfree_skb_any(skb); } @@ -858,179 +837,137 @@ static inline void ioc3_clean_tx_ring(struct ioc3_private *ip) ip->tx_ci = 0; } -static void ioc3_free_rings(struct ioc3_private *ip) +static void ioc3_free_rx_bufs(struct ioc3_private *ip) { - struct sk_buff *skb; int rx_entry, n_entry; + struct sk_buff *skb; - if (ip->txr) { - ioc3_clean_tx_ring(ip); - free_pages((unsigned long)ip->txr, 2); - ip->txr = NULL; - } - - if (ip->rxr) { - n_entry = ip->rx_ci; - rx_entry = ip->rx_pi; - - while (n_entry != rx_entry) { - skb = ip->rx_skbs[n_entry]; - if (skb) - dev_kfree_skb_any(skb); + n_entry = ip->rx_ci; + rx_entry = ip->rx_pi; - n_entry = (n_entry + 1) & 511; + while (n_entry != rx_entry) { + skb = ip->rx_skbs[n_entry]; + if (skb) { + dma_unmap_single(ip->dma_dev, + be64_to_cpu(ip->rxr[n_entry]), + RX_BUF_SIZE, DMA_FROM_DEVICE); + dev_kfree_skb_any(skb); } - free_page((unsigned long)ip->rxr); - ip->rxr = NULL; + n_entry = (n_entry + 1) & RX_RING_MASK; } } -static void ioc3_alloc_rings(struct net_device *dev) +static int ioc3_alloc_rx_bufs(struct net_device *dev) { struct ioc3_private *ip = netdev_priv(dev); struct ioc3_erxbuf *rxb; - unsigned long *rxr; + dma_addr_t d; int i; - if (ip->rxr == NULL) { - /* Allocate and initialize rx ring. 4kb = 512 entries */ - ip->rxr = (unsigned long *) get_zeroed_page(GFP_ATOMIC); - rxr = ip->rxr; - if (!rxr) - printk("ioc3_alloc_rings(): get_zeroed_page() failed!\n"); - - /* Now the rx buffers. The RX ring may be larger but - we only allocate 16 buffers for now. Need to tune - this for performance and memory later. */ - for (i = 0; i < RX_BUFFS; i++) { - struct sk_buff *skb; - - skb = ioc3_alloc_skb(RX_BUF_ALLOC_SIZE, GFP_ATOMIC); - if (!skb) { - show_free_areas(0, NULL); - continue; - } - - ip->rx_skbs[i] = skb; - - /* Because we reserve afterwards. */ - skb_put(skb, (1664 + RX_OFFSET)); - rxb = (struct ioc3_erxbuf *) skb->data; - rxr[i] = cpu_to_be64(ioc3_map(rxb, 1)); - skb_reserve(skb, RX_OFFSET); - } - ip->rx_ci = 0; - ip->rx_pi = RX_BUFFS; - } + /* Now the rx buffers. The RX ring may be larger but + * we only allocate 16 buffers for now. Need to tune + * this for performance and memory later. + */ + for (i = 0; i < RX_BUFFS; i++) { + if (ioc3_alloc_skb(ip, &ip->rx_skbs[i], &rxb, &d)) + return -ENOMEM; - if (ip->txr == NULL) { - /* Allocate and initialize tx rings. 16kb = 128 bufs. */ - ip->txr = (struct ioc3_etxd *)__get_free_pages(GFP_KERNEL, 2); - if (!ip->txr) - printk("ioc3_alloc_rings(): __get_free_pages() failed!\n"); - ip->tx_pi = 0; - ip->tx_ci = 0; + rxb->w0 = 0; /* Clear valid flag */ + ip->rxr[i] = cpu_to_be64(ioc3_map(d, PCI64_ATTR_BAR)); } -} - -static void ioc3_init_rings(struct net_device *dev) -{ - struct ioc3_private *ip = netdev_priv(dev); - struct ioc3 *ioc3 = ip->regs; - unsigned long ring; - - ioc3_free_rings(ip); - ioc3_alloc_rings(dev); - - ioc3_clean_rx_ring(ip); - ioc3_clean_tx_ring(ip); + ip->rx_ci = 0; + ip->rx_pi = RX_BUFFS; - /* Now the rx ring base, consume & produce registers. */ - ring = ioc3_map(ip->rxr, 0); - ioc3_w_erbr_h(ring >> 32); - ioc3_w_erbr_l(ring & 0xffffffff); - ioc3_w_ercir(ip->rx_ci << 3); - ioc3_w_erpir((ip->rx_pi << 3) | ERPIR_ARM); - - ring = ioc3_map(ip->txr, 0); - - ip->txqlen = 0; /* nothing queued */ - - /* Now the tx ring base, consume & produce registers. */ - ioc3_w_etbr_h(ring >> 32); - ioc3_w_etbr_l(ring & 0xffffffff); - ioc3_w_etpir(ip->tx_pi << 7); - ioc3_w_etcir(ip->tx_ci << 7); - (void) ioc3_r_etcir(); /* Flush */ + return 0; } static inline void ioc3_ssram_disc(struct ioc3_private *ip) { - struct ioc3 *ioc3 = ip->regs; - volatile u32 *ssram0 = &ioc3->ssram[0x0000]; - volatile u32 *ssram1 = &ioc3->ssram[0x4000]; - unsigned int pattern = 0x5555; + struct ioc3_ethregs *regs = ip->regs; + u32 *ssram0 = &ip->ssram[0x0000]; + u32 *ssram1 = &ip->ssram[0x4000]; + u32 pattern = 0x5555; /* Assume the larger size SSRAM and enable parity checking */ - ioc3_w_emcr(ioc3_r_emcr() | (EMCR_BUFSIZ | EMCR_RAMPAR)); + writel(readl(®s->emcr) | (EMCR_BUFSIZ | EMCR_RAMPAR), ®s->emcr); + readl(®s->emcr); /* Flush */ - *ssram0 = pattern; - *ssram1 = ~pattern & IOC3_SSRAM_DM; + writel(pattern, ssram0); + writel(~pattern & IOC3_SSRAM_DM, ssram1); - if ((*ssram0 & IOC3_SSRAM_DM) != pattern || - (*ssram1 & IOC3_SSRAM_DM) != (~pattern & IOC3_SSRAM_DM)) { + if ((readl(ssram0) & IOC3_SSRAM_DM) != pattern || + (readl(ssram1) & IOC3_SSRAM_DM) != (~pattern & IOC3_SSRAM_DM)) { /* set ssram size to 64 KB */ - ip->emcr = EMCR_RAMPAR; - ioc3_w_emcr(ioc3_r_emcr() & ~EMCR_BUFSIZ); - } else - ip->emcr = EMCR_BUFSIZ | EMCR_RAMPAR; + ip->emcr |= EMCR_RAMPAR; + writel(readl(®s->emcr) & ~EMCR_BUFSIZ, ®s->emcr); + } else { + ip->emcr |= EMCR_BUFSIZ | EMCR_RAMPAR; + } } static void ioc3_init(struct net_device *dev) { struct ioc3_private *ip = netdev_priv(dev); - struct ioc3 *ioc3 = ip->regs; + struct ioc3_ethregs *regs = ip->regs; del_timer_sync(&ip->ioc3_timer); /* Kill if running */ - ioc3_w_emcr(EMCR_RST); /* Reset */ - (void) ioc3_r_emcr(); /* Flush WB */ + writel(EMCR_RST, ®s->emcr); /* Reset */ + readl(®s->emcr); /* Flush WB */ udelay(4); /* Give it time ... */ - ioc3_w_emcr(0); - (void) ioc3_r_emcr(); + writel(0, ®s->emcr); + readl(®s->emcr); /* Misc registers */ -#ifdef CONFIG_SGI_IP27 - ioc3_w_erbar(PCI64_ATTR_BAR >> 32); /* Barrier on last store */ -#else - ioc3_w_erbar(0); /* Let PCI API get it right */ -#endif - (void) ioc3_r_etcdc(); /* Clear on read */ - ioc3_w_ercsr(15); /* RX low watermark */ - ioc3_w_ertr(0); /* Interrupt immediately */ + writel(ERBAR_VAL, ®s->erbar); + readl(®s->etcdc); /* Clear on read */ + writel(15, ®s->ercsr); /* RX low watermark */ + writel(0, ®s->ertr); /* Interrupt immediately */ __ioc3_set_mac_address(dev); - ioc3_w_ehar_h(ip->ehar_h); - ioc3_w_ehar_l(ip->ehar_l); - ioc3_w_ersr(42); /* XXX should be random */ + writel(ip->ehar_h, ®s->ehar_h); + writel(ip->ehar_l, ®s->ehar_l); + writel(42, ®s->ersr); /* XXX should be random */ +} - ioc3_init_rings(dev); +static void ioc3_start(struct ioc3_private *ip) +{ + struct ioc3_ethregs *regs = ip->regs; + unsigned long ring; + + /* Now the rx ring base, consume & produce registers. */ + ring = ioc3_map(ip->rxr_dma, PCI64_ATTR_PREC); + writel(ring >> 32, ®s->erbr_h); + writel(ring & 0xffffffff, ®s->erbr_l); + writel(ip->rx_ci << 3, ®s->ercir); + writel((ip->rx_pi << 3) | ERPIR_ARM, ®s->erpir); + + ring = ioc3_map(ip->txr_dma, PCI64_ATTR_PREC); + + ip->txqlen = 0; /* nothing queued */ + + /* Now the tx ring base, consume & produce registers. */ + writel(ring >> 32, ®s->etbr_h); + writel(ring & 0xffffffff, ®s->etbr_l); + writel(ip->tx_pi << 7, ®s->etpir); + writel(ip->tx_ci << 7, ®s->etcir); + readl(®s->etcir); /* Flush */ ip->emcr |= ((RX_OFFSET / 2) << EMCR_RXOFF_SHIFT) | EMCR_TXDMAEN | - EMCR_TXEN | EMCR_RXDMAEN | EMCR_RXEN | EMCR_PADEN; - ioc3_w_emcr(ip->emcr); - ioc3_w_eier(EISR_RXTIMERINT | EISR_RXOFLO | EISR_RXBUFOFLO | - EISR_RXMEMERR | EISR_RXPARERR | EISR_TXBUFUFLO | - EISR_TXEXPLICIT | EISR_TXMEMERR); - (void) ioc3_r_eier(); + EMCR_TXEN | EMCR_RXDMAEN | EMCR_RXEN | EMCR_PADEN; + writel(ip->emcr, ®s->emcr); + writel(EISR_RXTIMERINT | EISR_RXOFLO | EISR_RXBUFOFLO | + EISR_RXMEMERR | EISR_RXPARERR | EISR_TXBUFUFLO | + EISR_TXEXPLICIT | EISR_TXMEMERR, ®s->eier); + readl(®s->eier); } static inline void ioc3_stop(struct ioc3_private *ip) { - struct ioc3 *ioc3 = ip->regs; + struct ioc3_ethregs *regs = ip->regs; - ioc3_w_emcr(0); /* Shutup */ - ioc3_w_eier(0); /* Disable interrupts */ - (void) ioc3_r_eier(); /* Flush */ + writel(0, ®s->emcr); /* Shutup */ + writel(0, ®s->eier); /* Disable interrupts */ + readl(®s->eier); /* Flush */ } static int ioc3_open(struct net_device *dev) @@ -1038,14 +975,20 @@ static int ioc3_open(struct net_device *dev) struct ioc3_private *ip = netdev_priv(dev); if (request_irq(dev->irq, ioc3_interrupt, IRQF_SHARED, ioc3_str, dev)) { - printk(KERN_ERR "%s: Can't get irq %d\n", dev->name, dev->irq); + netdev_err(dev, "Can't get irq %d\n", dev->irq); return -EAGAIN; } ip->ehar_h = 0; ip->ehar_l = 0; + ioc3_init(dev); + if (ioc3_alloc_rx_bufs(dev)) { + netdev_err(dev, "%s: rx buffer allocation failed\n", __func__); + return -ENOMEM; + } + ioc3_start(ip); ioc3_mii_start(ip); netif_start_queue(dev); @@ -1063,12 +1006,13 @@ static int ioc3_close(struct net_device *dev) ioc3_stop(ip); free_irq(dev->irq, dev); - ioc3_free_rings(ip); + ioc3_free_rx_bufs(ip); + ioc3_clean_tx_ring(ip); + return 0; } -/* - * MENET cards have four IOC3 chips, which are attached to two sets of +/* MENET cards have four IOC3 chips, which are attached to two sets of * PCI slot resources each: the primary connections are on slots * 0..3 and the secondaries are on 4..7 * @@ -1085,7 +1029,7 @@ static int ioc3_adjacent_is_ioc3(struct pci_dev *pdev, int slot) if (dev) { if (dev->vendor == PCI_VENDOR_ID_SGI && - dev->device == PCI_DEVICE_ID_SGI_IOC3) + dev->device == PCI_DEVICE_ID_SGI_IOC3) ret = 1; pci_dev_put(dev); } @@ -1095,15 +1039,14 @@ static int ioc3_adjacent_is_ioc3(struct pci_dev *pdev, int slot) static int ioc3_is_menet(struct pci_dev *pdev) { - return pdev->bus->parent == NULL && + return !pdev->bus->parent && ioc3_adjacent_is_ioc3(pdev, 0) && ioc3_adjacent_is_ioc3(pdev, 1) && ioc3_adjacent_is_ioc3(pdev, 2); } #ifdef CONFIG_SERIAL_8250 -/* - * Note about serial ports and consoles: +/* Note about serial ports and consoles: * For console output, everyone uses the IOC3 UARTA (offset 0x178) * connected to the master node (look in ip27_setup_console() and * ip27prom_console_write()). @@ -1140,31 +1083,32 @@ static void ioc3_8250_register(struct ioc3_uartregs __iomem *uart) #define COSMISC_CONSTANT 6 struct uart_8250_port port = { - .port = { + .port = { .irq = 0, .flags = UPF_SKIP_TEST | UPF_BOOT_AUTOCONF, .iotype = UPIO_MEM, .regshift = 0, .uartclk = (22000000 << 1) / COSMISC_CONSTANT, - .membase = (unsigned char __iomem *) uart, - .mapbase = (unsigned long) uart, - } + .membase = (unsigned char __iomem *)uart, + .mapbase = (unsigned long)uart, + } }; unsigned char lcr; - lcr = uart->iu_lcr; - uart->iu_lcr = lcr | UART_LCR_DLAB; - uart->iu_scr = COSMISC_CONSTANT, - uart->iu_lcr = lcr; - uart->iu_lcr; + lcr = readb(&uart->iu_lcr); + writeb(lcr | UART_LCR_DLAB, &uart->iu_lcr); + writeb(COSMISC_CONSTANT, &uart->iu_scr); + writeb(lcr, &uart->iu_lcr); + readb(&uart->iu_lcr); serial8250_register_8250_port(&port); } static void ioc3_serial_probe(struct pci_dev *pdev, struct ioc3 *ioc3) { - /* - * We need to recognice and treat the fourth MENET serial as it + u32 sio_iec; + + /* We need to recognice and treat the fourth MENET serial as it * does not have an SuperIO chip attached to it, therefore attempting * to access it will result in bus errors. We call something an * MENET if PCI slot 0, 1, 2 and 3 of a master PCI bus all have an IOC3 @@ -1175,33 +1119,34 @@ static void ioc3_serial_probe(struct pci_dev *pdev, struct ioc3 *ioc3) if (ioc3_is_menet(pdev) && PCI_SLOT(pdev->devfn) == 3) return; - /* - * Switch IOC3 to PIO mode. It probably already was but let's be + /* Switch IOC3 to PIO mode. It probably already was but let's be * paranoid */ - ioc3->gpcr_s = GPCR_UARTA_MODESEL | GPCR_UARTB_MODESEL; - ioc3->gpcr_s; - ioc3->gppr_6 = 0; - ioc3->gppr_6; - ioc3->gppr_7 = 0; - ioc3->gppr_7; - ioc3->sscr_a = ioc3->sscr_a & ~SSCR_DMA_EN; - ioc3->sscr_a; - ioc3->sscr_b = ioc3->sscr_b & ~SSCR_DMA_EN; - ioc3->sscr_b; + writel(GPCR_UARTA_MODESEL | GPCR_UARTB_MODESEL, &ioc3->gpcr_s); + readl(&ioc3->gpcr_s); + writel(0, &ioc3->gppr[6]); + readl(&ioc3->gppr[6]); + writel(0, &ioc3->gppr[7]); + readl(&ioc3->gppr[7]); + writel(readl(&ioc3->port_a.sscr) & ~SSCR_DMA_EN, &ioc3->port_a.sscr); + readl(&ioc3->port_a.sscr); + writel(readl(&ioc3->port_b.sscr) & ~SSCR_DMA_EN, &ioc3->port_b.sscr); + readl(&ioc3->port_b.sscr); /* Disable all SA/B interrupts except for SA/B_INT in SIO_IEC. */ - ioc3->sio_iec &= ~ (SIO_IR_SA_TX_MT | SIO_IR_SA_RX_FULL | - SIO_IR_SA_RX_HIGH | SIO_IR_SA_RX_TIMER | - SIO_IR_SA_DELTA_DCD | SIO_IR_SA_DELTA_CTS | - SIO_IR_SA_TX_EXPLICIT | SIO_IR_SA_MEMERR); - ioc3->sio_iec |= SIO_IR_SA_INT; - ioc3->sscr_a = 0; - ioc3->sio_iec &= ~ (SIO_IR_SB_TX_MT | SIO_IR_SB_RX_FULL | - SIO_IR_SB_RX_HIGH | SIO_IR_SB_RX_TIMER | - SIO_IR_SB_DELTA_DCD | SIO_IR_SB_DELTA_CTS | - SIO_IR_SB_TX_EXPLICIT | SIO_IR_SB_MEMERR); - ioc3->sio_iec |= SIO_IR_SB_INT; - ioc3->sscr_b = 0; + sio_iec = readl(&ioc3->sio_iec); + sio_iec &= ~(SIO_IR_SA_TX_MT | SIO_IR_SA_RX_FULL | + SIO_IR_SA_RX_HIGH | SIO_IR_SA_RX_TIMER | + SIO_IR_SA_DELTA_DCD | SIO_IR_SA_DELTA_CTS | + SIO_IR_SA_TX_EXPLICIT | SIO_IR_SA_MEMERR); + sio_iec |= SIO_IR_SA_INT; + sio_iec &= ~(SIO_IR_SB_TX_MT | SIO_IR_SB_RX_FULL | + SIO_IR_SB_RX_HIGH | SIO_IR_SB_RX_TIMER | + SIO_IR_SB_DELTA_DCD | SIO_IR_SB_DELTA_CTS | + SIO_IR_SB_TX_EXPLICIT | SIO_IR_SB_MEMERR); + sio_iec |= SIO_IR_SB_INT; + writel(sio_iec, &ioc3->sio_iec); + writel(0, &ioc3->port_a.sscr); + writel(0, &ioc3->port_b.sscr); ioc3_8250_register(&ioc3->sregs.uarta); ioc3_8250_register(&ioc3->sregs.uartb); @@ -1236,15 +1181,15 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) pci_using_dac = 1; err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); if (err < 0) { - printk(KERN_ERR "%s: Unable to obtain 64 bit DMA " - "for consistent allocations\n", pci_name(pdev)); + pr_err("%s: Unable to obtain 64 bit DMA for consistent allocations\n", + pci_name(pdev)); goto out; } } else { err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (err) { - printk(KERN_ERR "%s: No usable DMA configuration, " - "aborting.\n", pci_name(pdev)); + pr_err("%s: No usable DMA configuration, aborting.\n", + pci_name(pdev)); goto out; } pci_using_dac = 0; @@ -1270,19 +1215,22 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ip = netdev_priv(dev); ip->dev = dev; + ip->dma_dev = &pdev->dev; dev->irq = pdev->irq; ioc3_base = pci_resource_start(pdev, 0); ioc3_size = pci_resource_len(pdev, 0); - ioc3 = (struct ioc3 *) ioremap(ioc3_base, ioc3_size); + ioc3 = (struct ioc3 *)ioremap(ioc3_base, ioc3_size); if (!ioc3) { - printk(KERN_CRIT "ioc3eth(%s): ioremap failed, goodbye.\n", + pr_err("ioc3eth(%s): ioremap failed, goodbye.\n", pci_name(pdev)); err = -ENOMEM; goto out_res; } - ip->regs = ioc3; + ip->regs = &ioc3->eth; + ip->ssram = ioc3->ssram; + ip->all_regs = ioc3; #ifdef CONFIG_SERIAL_8250 ioc3_serial_probe(pdev, ioc3); @@ -1292,6 +1240,26 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) timer_setup(&ip->ioc3_timer, ioc3_timer, 0); ioc3_stop(ip); + + /* Allocate rx ring. 4kb = 512 entries, must be 4kb aligned */ + ip->rxr = dma_direct_alloc_pages(ip->dma_dev, RX_RING_SIZE, + &ip->rxr_dma, GFP_ATOMIC, 0); + if (!ip->rxr) { + pr_err("ioc3-eth: rx ring allocation failed\n"); + err = -ENOMEM; + goto out_stop; + } + + /* Allocate tx rings. 16kb = 128 bufs, must be 16kb aligned */ + ip->txr = dma_direct_alloc_pages(ip->dma_dev, TX_RING_SIZE, + &ip->txr_dma, + GFP_KERNEL | __GFP_ZERO, 0); + if (!ip->txr) { + pr_err("ioc3-eth: tx ring allocation failed\n"); + err = -ENOMEM; + goto out_stop; + } + ioc3_init(dev); ip->pdev = pdev; @@ -1305,7 +1273,7 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) ioc3_mii_init(ip); if (ip->mii.phy_id == -1) { - printk(KERN_CRIT "ioc3-eth(%s): Didn't find a PHY, goodbye.\n", + pr_err("ioc3-eth(%s): Didn't find a PHY, goodbye.\n", pci_name(pdev)); err = -ENODEV; goto out_stop; @@ -1335,24 +1303,27 @@ static int ioc3_probe(struct pci_dev *pdev, const struct pci_device_id *ent) vendor = (sw_physid1 << 12) | (sw_physid2 >> 4); model = (sw_physid2 >> 4) & 0x3f; rev = sw_physid2 & 0xf; - printk(KERN_INFO "%s: Using PHY %d, vendor 0x%x, model %d, " - "rev %d.\n", dev->name, ip->mii.phy_id, vendor, model, rev); - printk(KERN_INFO "%s: IOC3 SSRAM has %d kbyte.\n", dev->name, - ip->emcr & EMCR_BUFSIZ ? 128 : 64); + netdev_info(dev, "Using PHY %d, vendor 0x%x, model %d, rev %d.\n", + ip->mii.phy_id, vendor, model, rev); + netdev_info(dev, "IOC3 SSRAM has %d kbyte.\n", + ip->emcr & EMCR_BUFSIZ ? 128 : 64); return 0; out_stop: - ioc3_stop(ip); del_timer_sync(&ip->ioc3_timer); - ioc3_free_rings(ip); + if (ip->rxr) + dma_direct_free_pages(ip->dma_dev, RX_RING_SIZE, ip->rxr, + ip->rxr_dma, 0); + if (ip->txr) + dma_direct_free_pages(ip->dma_dev, TX_RING_SIZE, ip->txr, + ip->txr_dma, 0); out_res: pci_release_regions(pdev); out_free: free_netdev(dev); out_disable: - /* - * We should call pci_disable_device(pdev); here if the IOC3 wasn't + /* We should call pci_disable_device(pdev); here if the IOC3 wasn't * such a weird device ... */ out: @@ -1363,16 +1334,19 @@ static void ioc3_remove_one(struct pci_dev *pdev) { struct net_device *dev = pci_get_drvdata(pdev); struct ioc3_private *ip = netdev_priv(dev); - struct ioc3 *ioc3 = ip->regs; + + dma_direct_free_pages(ip->dma_dev, RX_RING_SIZE, ip->rxr, + ip->rxr_dma, 0); + dma_direct_free_pages(ip->dma_dev, TX_RING_SIZE, ip->txr, + ip->txr_dma, 0); unregister_netdev(dev); del_timer_sync(&ip->ioc3_timer); - iounmap(ioc3); + iounmap(ip->all_regs); pci_release_regions(pdev); free_netdev(dev); - /* - * We should call pci_disable_device(pdev); here if the IOC3 wasn't + /* We should call pci_disable_device(pdev); here if the IOC3 wasn't * such a weird device ... */ } @@ -1392,16 +1366,14 @@ static struct pci_driver ioc3_driver = { static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev) { - unsigned long data; struct ioc3_private *ip = netdev_priv(dev); - struct ioc3 *ioc3 = ip->regs; - unsigned int len; struct ioc3_etxd *desc; - uint32_t w0 = 0; + unsigned long data; + unsigned int len; int produce; + u32 w0 = 0; - /* - * IOC3 has a fairly simple minded checksumming hardware which simply + /* IOC3 has a fairly simple minded checksumming hardware which simply * adds up the 1's complement checksum for the entire packet and * inserts it at an offset which can be specified in the descriptor * into the transmit packet. This means we have to compensate for the @@ -1412,25 +1384,23 @@ static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev) const struct iphdr *ih = ip_hdr(skb); const int proto = ntohs(ih->protocol); unsigned int csoff; - uint32_t csum, ehsum; - uint16_t *eh; + u32 csum, ehsum; + u16 *eh; /* The MAC header. skb->mac seem the logic approach - to find the MAC header - except it's a NULL pointer ... */ - eh = (uint16_t *) skb->data; + * to find the MAC header - except it's a NULL pointer ... + */ + eh = (u16 *)skb->data; /* Sum up dest addr, src addr and protocol */ ehsum = eh[0] + eh[1] + eh[2] + eh[3] + eh[4] + eh[5] + eh[6]; - /* Fold ehsum. can't use csum_fold which negates also ... */ - ehsum = (ehsum & 0xffff) + (ehsum >> 16); - ehsum = (ehsum & 0xffff) + (ehsum >> 16); - /* Skip IP header; it's sum is always zero and was - already filled in by ip_output.c */ + * already filled in by ip_output.c + */ csum = csum_tcpudp_nofold(ih->saddr, ih->daddr, - ih->tot_len - (ih->ihl << 2), - proto, 0xffff ^ ehsum); + ih->tot_len - (ih->ihl << 2), + proto, csum_fold(ehsum)); csum = (csum & 0xffff) + (csum >> 16); /* Fold again */ csum = (csum & 0xffff) + (csum >> 16); @@ -1450,7 +1420,7 @@ static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev) spin_lock_irq(&ip->ioc3_lock); - data = (unsigned long) skb->data; + data = (unsigned long)skb->data; len = skb->len; produce = ip->tx_pi; @@ -1470,47 +1440,78 @@ static netdev_tx_t ioc3_start_xmit(struct sk_buff *skb, struct net_device *dev) unsigned long b2 = (data | 0x3fffUL) + 1UL; unsigned long s1 = b2 - data; unsigned long s2 = data + len - b2; + dma_addr_t d1, d2; desc->cmd = cpu_to_be32(len | ETXD_INTWHENDONE | - ETXD_B1V | ETXD_B2V | w0); + ETXD_B1V | ETXD_B2V | w0); desc->bufcnt = cpu_to_be32((s1 << ETXD_B1CNT_SHIFT) | - (s2 << ETXD_B2CNT_SHIFT)); - desc->p1 = cpu_to_be64(ioc3_map(skb->data, 1)); - desc->p2 = cpu_to_be64(ioc3_map((void *) b2, 1)); + (s2 << ETXD_B2CNT_SHIFT)); + d1 = dma_map_single(ip->dma_dev, skb->data, s1, DMA_TO_DEVICE); + if (dma_mapping_error(ip->dma_dev, d1)) + goto drop_packet; + d2 = dma_map_single(ip->dma_dev, (void *)b2, s1, DMA_TO_DEVICE); + if (dma_mapping_error(ip->dma_dev, d2)) { + dma_unmap_single(ip->dma_dev, d1, len, DMA_TO_DEVICE); + goto drop_packet; + } + desc->p1 = cpu_to_be64(ioc3_map(d1, PCI64_ATTR_PREF)); + desc->p2 = cpu_to_be64(ioc3_map(d2, PCI64_ATTR_PREF)); } else { + dma_addr_t d; + /* Normal sized packet that doesn't cross a page boundary. */ desc->cmd = cpu_to_be32(len | ETXD_INTWHENDONE | ETXD_B1V | w0); desc->bufcnt = cpu_to_be32(len << ETXD_B1CNT_SHIFT); - desc->p1 = cpu_to_be64(ioc3_map(skb->data, 1)); + d = dma_map_single(ip->dma_dev, skb->data, len, DMA_TO_DEVICE); + if (dma_mapping_error(ip->dma_dev, d)) + goto drop_packet; + desc->p1 = cpu_to_be64(ioc3_map(d, PCI64_ATTR_PREF)); } - BARRIER(); + mb(); /* make sure all descriptor changes are visible */ ip->tx_skbs[produce] = skb; /* Remember skb */ - produce = (produce + 1) & 127; + produce = (produce + 1) & TX_RING_MASK; ip->tx_pi = produce; - ioc3_w_etpir(produce << 7); /* Fire ... */ + writel(produce << 7, &ip->regs->etpir); /* Fire ... */ ip->txqlen++; - if (ip->txqlen >= 127) + if (ip->txqlen >= (TX_RING_ENTRIES - 1)) netif_stop_queue(dev); spin_unlock_irq(&ip->ioc3_lock); return NETDEV_TX_OK; + +drop_packet: + dev_kfree_skb_any(skb); + dev->stats.tx_dropped++; + + spin_unlock_irq(&ip->ioc3_lock); + + return NETDEV_TX_OK; } static void ioc3_timeout(struct net_device *dev) { struct ioc3_private *ip = netdev_priv(dev); - printk(KERN_ERR "%s: transmit timed out, resetting\n", dev->name); + netdev_err(dev, "transmit timed out, resetting\n"); spin_lock_irq(&ip->ioc3_lock); ioc3_stop(ip); + ioc3_free_rx_bufs(ip); + ioc3_clean_tx_ring(ip); + ioc3_init(dev); + if (ioc3_alloc_rx_bufs(dev)) { + netdev_err(dev, "%s: rx buffer allocation failed\n", __func__); + spin_unlock_irq(&ip->ioc3_lock); + return; + } + ioc3_start(ip); ioc3_mii_init(ip); ioc3_mii_start(ip); @@ -1519,16 +1520,14 @@ static void ioc3_timeout(struct net_device *dev) netif_wake_queue(dev); } -/* - * Given a multicast ethernet address, this routine calculates the +/* Given a multicast ethernet address, this routine calculates the * address's bit index in the logical address filter mask */ - static inline unsigned int ioc3_hash(const unsigned char *addr) { unsigned int temp = 0; - u32 crc; int bits; + u32 crc; crc = ether_crc_le(ETH_ALEN, addr); @@ -1542,8 +1541,8 @@ static inline unsigned int ioc3_hash(const unsigned char *addr) return temp; } -static void ioc3_get_drvinfo (struct net_device *dev, - struct ethtool_drvinfo *info) +static void ioc3_get_drvinfo(struct net_device *dev, + struct ethtool_drvinfo *info) { struct ioc3_private *ip = netdev_priv(dev); @@ -1623,27 +1622,28 @@ static int ioc3_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) static void ioc3_set_multicast_list(struct net_device *dev) { - struct netdev_hw_addr *ha; struct ioc3_private *ip = netdev_priv(dev); - struct ioc3 *ioc3 = ip->regs; + struct ioc3_ethregs *regs = ip->regs; + struct netdev_hw_addr *ha; u64 ehar = 0; - netif_stop_queue(dev); /* Lock out others. */ + spin_lock_irq(&ip->ioc3_lock); if (dev->flags & IFF_PROMISC) { /* Set promiscuous. */ ip->emcr |= EMCR_PROMISC; - ioc3_w_emcr(ip->emcr); - (void) ioc3_r_emcr(); + writel(ip->emcr, ®s->emcr); + readl(®s->emcr); } else { ip->emcr &= ~EMCR_PROMISC; - ioc3_w_emcr(ip->emcr); /* Clear promiscuous. */ - (void) ioc3_r_emcr(); + writel(ip->emcr, ®s->emcr); /* Clear promiscuous. */ + readl(®s->emcr); if ((dev->flags & IFF_ALLMULTI) || (netdev_mc_count(dev) > 64)) { /* Too many for hashing to make sense or we want all - multicast packets anyway, so skip computing all the - hashes and just accept all packets. */ + * multicast packets anyway, so skip computing all the + * hashes and just accept all packets. + */ ip->ehar_h = 0xffffffff; ip->ehar_l = 0xffffffff; } else { @@ -1653,11 +1653,11 @@ static void ioc3_set_multicast_list(struct net_device *dev) ip->ehar_h = ehar >> 32; ip->ehar_l = ehar & 0xffffffff; } - ioc3_w_ehar_h(ip->ehar_h); - ioc3_w_ehar_l(ip->ehar_l); + writel(ip->ehar_h, ®s->ehar_h); + writel(ip->ehar_l, ®s->ehar_l); } - netif_wake_queue(dev); /* Let us get going again. */ + spin_unlock_irq(&ip->ioc3_lock); } module_pci_driver(ioc3_driver); diff --git a/drivers/net/ethernet/sgi/meth.c b/drivers/net/ethernet/sgi/meth.c index 00660dd820e2..539bc5db989c 100644 --- a/drivers/net/ethernet/sgi/meth.c +++ b/drivers/net/ethernet/sgi/meth.c @@ -247,8 +247,7 @@ static void meth_free_tx_ring(struct meth_private *priv) /* Remove any pending skb */ for (i = 0; i < TX_RING_ENTRIES; i++) { - if (priv->tx_skbs[i]) - dev_kfree_skb(priv->tx_skbs[i]); + dev_kfree_skb(priv->tx_skbs[i]); priv->tx_skbs[i] = NULL; } dma_free_coherent(&priv->pdev->dev, TX_RING_BUFFER_SIZE, priv->tx_ring, diff --git a/drivers/net/ethernet/sis/sis900.c b/drivers/net/ethernet/sis/sis900.c index 6e07f5ebacfc..85eaccbbbac1 100644 --- a/drivers/net/ethernet/sis/sis900.c +++ b/drivers/net/ethernet/sis/sis900.c @@ -191,6 +191,8 @@ struct sis900_private { unsigned int tx_full; /* The Tx queue is full. */ u8 host_bridge_rev; u8 chipset_rev; + /* EEPROM data */ + int eeprom_size; }; MODULE_AUTHOR("Jim Huang <cmhuang@sis.com.tw>, Ollie Lho <ollie@sis.com.tw>"); @@ -475,6 +477,8 @@ static int sis900_probe(struct pci_dev *pci_dev, sis_priv->pci_dev = pci_dev; spin_lock_init(&sis_priv->lock); + sis_priv->eeprom_size = 24; + pci_set_drvdata(pci_dev, net_dev); ring_space = pci_alloc_consistent(pci_dev, TX_TOTAL_SIZE, &ring_dma); @@ -2122,6 +2126,68 @@ static void sis900_get_wol(struct net_device *net_dev, struct ethtool_wolinfo *w wol->supported = (WAKE_PHY | WAKE_MAGIC); } +static int sis900_get_eeprom_len(struct net_device *dev) +{ + struct sis900_private *sis_priv = netdev_priv(dev); + + return sis_priv->eeprom_size; +} + +static int sis900_read_eeprom(struct net_device *net_dev, u8 *buf) +{ + struct sis900_private *sis_priv = netdev_priv(net_dev); + void __iomem *ioaddr = sis_priv->ioaddr; + int wait, ret = -EAGAIN; + u16 signature; + u16 *ebuf = (u16 *)buf; + int i; + + if (sis_priv->chipset_rev == SIS96x_900_REV) { + sw32(mear, EEREQ); + for (wait = 0; wait < 2000; wait++) { + if (sr32(mear) & EEGNT) { + /* read 16 bits, and index by 16 bits */ + for (i = 0; i < sis_priv->eeprom_size / 2; i++) + ebuf[i] = (u16)read_eeprom(ioaddr, i); + ret = 0; + break; + } + udelay(1); + } + sw32(mear, EEDONE); + } else { + signature = (u16)read_eeprom(ioaddr, EEPROMSignature); + if (signature != 0xffff && signature != 0x0000) { + /* read 16 bits, and index by 16 bits */ + for (i = 0; i < sis_priv->eeprom_size / 2; i++) + ebuf[i] = (u16)read_eeprom(ioaddr, i); + ret = 0; + } + } + return ret; +} + +#define SIS900_EEPROM_MAGIC 0xBABE +static int sis900_get_eeprom(struct net_device *dev, struct ethtool_eeprom *eeprom, u8 *data) +{ + struct sis900_private *sis_priv = netdev_priv(dev); + u8 *eebuf; + int res; + + eebuf = kmalloc(sis_priv->eeprom_size, GFP_KERNEL); + if (!eebuf) + return -ENOMEM; + + eeprom->magic = SIS900_EEPROM_MAGIC; + spin_lock_irq(&sis_priv->lock); + res = sis900_read_eeprom(dev, eebuf); + spin_unlock_irq(&sis_priv->lock); + if (!res) + memcpy(data, eebuf + eeprom->offset, eeprom->len); + kfree(eebuf); + return res; +} + static const struct ethtool_ops sis900_ethtool_ops = { .get_drvinfo = sis900_get_drvinfo, .get_msglevel = sis900_get_msglevel, @@ -2132,6 +2198,8 @@ static const struct ethtool_ops sis900_ethtool_ops = { .set_wol = sis900_set_wol, .get_link_ksettings = sis900_get_link_ksettings, .set_link_ksettings = sis900_set_link_ksettings, + .get_eeprom_len = sis900_get_eeprom_len, + .get_eeprom = sis900_get_eeprom, }; /** diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 601e76ad99a0..3a6761131f4c 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -378,8 +378,7 @@ static void smc_shutdown(struct net_device *dev) pending_skb = lp->pending_tx_skb; lp->pending_tx_skb = NULL; spin_unlock_irq(&lp->lock); - if (pending_skb) - dev_kfree_skb(pending_skb); + dev_kfree_skb(pending_skb); /* and tell the card to stay away from that nasty outside world */ SMC_SELECT_BANK(lp, 0); diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 51a7b48db4bc..10d0c3e478ab 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -1553,7 +1553,6 @@ static int ave_probe(struct platform_device *pdev) struct ave_private *priv; struct net_device *ndev; struct device_node *np; - struct resource *res; const void *mac_addr; void __iomem *base; const char *name; @@ -1573,13 +1572,10 @@ static int ave_probe(struct platform_device *pdev) } irq = platform_get_irq(pdev, 0); - if (irq < 0) { - dev_err(dev, "IRQ not found\n"); + if (irq < 0) return irq; - } - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - base = devm_ioremap_resource(dev, res); + base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(base)) return PTR_ERR(base); diff --git a/drivers/net/ethernet/stmicro/stmmac/Kconfig b/drivers/net/ethernet/stmicro/stmmac/Kconfig index 2325b40dff6e..338e25a6374e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Kconfig +++ b/drivers/net/ethernet/stmicro/stmmac/Kconfig @@ -200,6 +200,7 @@ endif config STMMAC_PCI tristate "STMMAC PCI bus support" depends on STMMAC_ETH && PCI + depends on COMMON_CLK ---help--- This selects the platform specific bus support for the stmmac driver. This driver was tested on XLINX XC2V3000 FF1152AMT0221 diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index ed872eed1cab..912bbb6515b2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -75,6 +75,7 @@ struct stmmac_extra_stats { unsigned long rx_missed_cntr; unsigned long rx_overflow_cntr; unsigned long rx_vlan; + unsigned long rx_split_hdr_pkt_n; /* Tx/Rx IRQ error info */ unsigned long tx_undeflow_irq; unsigned long tx_process_stopped_irq; @@ -354,6 +355,13 @@ struct dma_features { unsigned int frpbs; unsigned int frpes; unsigned int addr64; + unsigned int rssen; + unsigned int vlhash; + unsigned int sphen; + unsigned int vlins; + unsigned int dvlan; + unsigned int l3l4fnum; + unsigned int arpoffsel; }; /* GMAC TX FIFO is 8K, Rx FIFO is 16K */ @@ -381,6 +389,16 @@ struct dma_features { #define JUMBO_LEN 9000 +/* Receive Side Scaling */ +#define STMMAC_RSS_HASH_KEY_SIZE 40 +#define STMMAC_RSS_MAX_TABLE_SIZE 256 + +/* VLAN */ +#define STMMAC_VLAN_NONE 0x0 +#define STMMAC_VLAN_REMOVE 0x1 +#define STMMAC_VLAN_INSERT 0x2 +#define STMMAC_VLAN_REPLACE 0x3 + extern const struct stmmac_desc_ops enh_desc_ops; extern const struct stmmac_desc_ops ndesc_ops; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c index 6ce3a7fb41ab..527f93320a5a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-anarion.c @@ -62,12 +62,10 @@ static void anarion_gmac_exit(struct platform_device *pdev, void *priv) static struct anarion_gmac *anarion_config_dt(struct platform_device *pdev) { int phy_mode; - struct resource *res; void __iomem *ctl_block; struct anarion_gmac *gmac; - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - ctl_block = devm_ioremap_resource(&pdev->dev, res); + ctl_block = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(ctl_block)) { dev_err(&pdev->dev, "Cannot get reset region (%ld)!\n", PTR_ERR(ctl_block)); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c index 3a14cdd01f5f..dd9967aeda22 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-dwc-qos-eth.c @@ -333,6 +333,9 @@ static void *tegra_eqos_probe(struct platform_device *pdev, usleep_range(2000, 4000); gpiod_set_value(eqos->reset, 0); + /* MDIO bus was already reset just above */ + data->mdio_bus_data->needs_reset = false; + eqos->rst = devm_reset_control_get(&pdev->dev, "eqos"); if (IS_ERR(eqos->rst)) { err = PTR_ERR(eqos->rst); @@ -415,7 +418,6 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) const struct dwc_eth_dwmac_data *data; struct plat_stmmacenet_data *plat_dat; struct stmmac_resources stmmac_res; - struct resource *res; void *priv; int ret; @@ -428,17 +430,11 @@ static int dwc_eth_dwmac_probe(struct platform_device *pdev) * resource initialization is done in the glue logic. */ stmmac_res.irq = platform_get_irq(pdev, 0); - if (stmmac_res.irq < 0) { - if (stmmac_res.irq != -EPROBE_DEFER) - dev_err(&pdev->dev, - "IRQ configuration information not found\n"); - + if (stmmac_res.irq < 0) return stmmac_res.irq; - } stmmac_res.wol_irq = stmmac_res.irq; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - stmmac_res.addr = devm_ioremap_resource(&pdev->dev, res); + stmmac_res.addr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(stmmac_res.addr)) return PTR_ERR(stmmac_res.addr); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c index 88eb16954627..bbc16b5a410a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson.c @@ -46,7 +46,6 @@ static int meson6_dwmac_probe(struct platform_device *pdev) struct plat_stmmacenet_data *plat_dat; struct stmmac_resources stmmac_res; struct meson_dwmac *dwmac; - struct resource *res; int ret; ret = stmmac_get_platform_resources(pdev, &stmmac_res); @@ -63,8 +62,7 @@ static int meson6_dwmac_probe(struct platform_device *pdev) goto err_remove_config_dt; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - dwmac->reg = devm_ioremap_resource(&pdev->dev, res); + dwmac->reg = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(dwmac->reg)) { ret = PTR_ERR(dwmac->reg); goto err_remove_config_dt; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 786ca4a7bf36..9cda29e4b89d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -308,7 +308,6 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) { struct plat_stmmacenet_data *plat_dat; struct stmmac_resources stmmac_res; - struct resource *res; struct meson8b_dwmac *dwmac; int ret; @@ -332,8 +331,7 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) ret = -EINVAL; goto err_remove_config_dt; } - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - dwmac->regs = devm_ioremap_resource(&pdev->dev, res); + dwmac->regs = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(dwmac->regs)) { ret = PTR_ERR(dwmac->regs); goto err_remove_config_dt; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c index c141fe783e87..e0212d2fc2a1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c @@ -46,7 +46,6 @@ struct socfpga_dwmac_ops { }; struct socfpga_dwmac { - int interface; u32 reg_offset; u32 reg_shift; struct device *dev; @@ -110,8 +109,6 @@ static int socfpga_dwmac_parse_data(struct socfpga_dwmac *dwmac, struct device * struct resource res_tse_pcs; struct resource res_sgmii_adapter; - dwmac->interface = of_get_phy_mode(np); - sys_mgr_base_addr = altr_sysmgr_regmap_lookup_by_phandle(np, "altr,sysmgr-syscon"); if (IS_ERR(sys_mgr_base_addr)) { @@ -231,6 +228,14 @@ err_node_put: return ret; } +static int socfpga_get_plat_phymode(struct socfpga_dwmac *dwmac) +{ + struct net_device *ndev = dev_get_drvdata(dwmac->dev); + struct stmmac_priv *priv = netdev_priv(ndev); + + return priv->plat->interface; +} + static int socfpga_set_phy_mode_common(int phymode, u32 *val) { switch (phymode) { @@ -255,7 +260,7 @@ static int socfpga_set_phy_mode_common(int phymode, u32 *val) static int socfpga_gen5_set_phy_mode(struct socfpga_dwmac *dwmac) { struct regmap *sys_mgr_base_addr = dwmac->sys_mgr_base_addr; - int phymode = dwmac->interface; + int phymode = socfpga_get_plat_phymode(dwmac); u32 reg_offset = dwmac->reg_offset; u32 reg_shift = dwmac->reg_shift; u32 ctrl, val, module; @@ -314,7 +319,7 @@ static int socfpga_gen5_set_phy_mode(struct socfpga_dwmac *dwmac) static int socfpga_gen10_set_phy_mode(struct socfpga_dwmac *dwmac) { struct regmap *sys_mgr_base_addr = dwmac->sys_mgr_base_addr; - int phymode = dwmac->interface; + int phymode = socfpga_get_plat_phymode(dwmac); u32 reg_offset = dwmac->reg_offset; u32 reg_shift = dwmac->reg_shift; u32 ctrl, val, module; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index 2ed11a581d80..89a3420eba42 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -16,7 +16,10 @@ #define GMAC_CONFIG 0x00000000 #define GMAC_PACKET_FILTER 0x00000008 #define GMAC_HASH_TAB(x) (0x10 + (x) * 4) +#define GMAC_VLAN_TAG 0x00000050 +#define GMAC_VLAN_HASH_TABLE 0x00000058 #define GMAC_RX_FLOW_CTRL 0x00000090 +#define GMAC_VLAN_INCL 0x00000060 #define GMAC_QX_TX_FLOW_CTRL(x) (0x70 + x * 4) #define GMAC_TXQ_PRTY_MAP0 0x98 #define GMAC_TXQ_PRTY_MAP1 0x9C @@ -37,6 +40,7 @@ #define GMAC_HW_FEATURE3 0x00000128 #define GMAC_MDIO_ADDR 0x00000200 #define GMAC_MDIO_DATA 0x00000204 +#define GMAC_ARP_ADDR 0x00000210 #define GMAC_ADDR_HIGH(reg) (0x300 + reg * 8) #define GMAC_ADDR_LOW(reg) (0x304 + reg * 8) @@ -62,9 +66,22 @@ #define GMAC_PACKET_FILTER_PM BIT(4) #define GMAC_PACKET_FILTER_PCF BIT(7) #define GMAC_PACKET_FILTER_HPF BIT(10) +#define GMAC_PACKET_FILTER_VTFE BIT(16) #define GMAC_MAX_PERFECT_ADDRESSES 128 +/* MAC VLAN */ +#define GMAC_VLAN_EDVLP BIT(26) +#define GMAC_VLAN_VTHM BIT(25) +#define GMAC_VLAN_DOVLTC BIT(20) +#define GMAC_VLAN_ESVL BIT(18) +#define GMAC_VLAN_ETV BIT(16) +#define GMAC_VLAN_VID GENMASK(15, 0) +#define GMAC_VLAN_VLTI BIT(20) +#define GMAC_VLAN_CSVL BIT(19) +#define GMAC_VLAN_VLC GENMASK(17, 16) +#define GMAC_VLAN_VLC_SHIFT 16 + /* MAC RX Queue Enable */ #define GMAC_RX_QUEUE_CLEAR(queue) ~(GENMASK(1, 0) << ((queue) * 2)) #define GMAC_RX_AV_QUEUE_ENABLE(queue) BIT((queue) * 2) @@ -149,6 +166,9 @@ enum power_event { #define GMAC_DEBUG_RPESTS BIT(0) /* MAC config */ +#define GMAC_CONFIG_ARPEN BIT(31) +#define GMAC_CONFIG_SARC GENMASK(30, 28) +#define GMAC_CONFIG_SARC_SHIFT 28 #define GMAC_CONFIG_IPC BIT(27) #define GMAC_CONFIG_2K BIT(22) #define GMAC_CONFIG_ACS BIT(20) @@ -164,11 +184,13 @@ enum power_event { #define GMAC_CONFIG_RE BIT(0) /* MAC HW features0 bitmap */ +#define GMAC_HW_FEAT_SAVLANINS BIT(27) #define GMAC_HW_FEAT_ADDMAC BIT(18) #define GMAC_HW_FEAT_RXCOESEL BIT(16) #define GMAC_HW_FEAT_TXCOSEL BIT(14) #define GMAC_HW_FEAT_EEESEL BIT(13) #define GMAC_HW_FEAT_TSSEL BIT(12) +#define GMAC_HW_FEAT_ARPOFFSEL BIT(9) #define GMAC_HW_FEAT_MMCSEL BIT(8) #define GMAC_HW_FEAT_MGKSEL BIT(7) #define GMAC_HW_FEAT_RWKSEL BIT(6) @@ -198,6 +220,7 @@ enum power_event { #define GMAC_HW_FEAT_FRPES GENMASK(14, 13) #define GMAC_HW_FEAT_FRPBS GENMASK(12, 11) #define GMAC_HW_FEAT_FRPSEL BIT(10) +#define GMAC_HW_FEAT_DVLAN BIT(5) /* MAC HW ADDR regs */ #define GMAC_HI_DCS GENMASK(18, 16) @@ -352,7 +375,8 @@ enum power_event { /* Default operating mode of the MAC */ #define GMAC_CORE_INIT (GMAC_CONFIG_JD | GMAC_CONFIG_PS | \ - GMAC_CONFIG_BE | GMAC_CONFIG_DCRS) + GMAC_CONFIG_BE | GMAC_CONFIG_DCRS | \ + GMAC_CONFIG_JE) /* To dump the core regs excluding the Address Registers */ #define GMAC_REG_NUM 132 diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index fc9954e4a772..9b4b5f69fc02 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -25,15 +25,9 @@ static void dwmac4_core_init(struct mac_device_info *hw, { void __iomem *ioaddr = hw->pcsr; u32 value = readl(ioaddr + GMAC_CONFIG); - int mtu = dev->mtu; value |= GMAC_CORE_INIT; - if (mtu > 1500) - value |= GMAC_CONFIG_2K; - if (mtu > 2000) - value |= GMAC_CONFIG_JE; - if (hw->ps) { value |= GMAC_CONFIG_TE; @@ -737,6 +731,73 @@ static void dwmac4_set_mac_loopback(void __iomem *ioaddr, bool enable) writel(value, ioaddr + GMAC_CONFIG); } +static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash, + bool is_double) +{ + void __iomem *ioaddr = hw->pcsr; + + writel(hash, ioaddr + GMAC_VLAN_HASH_TABLE); + + if (hash) { + u32 value = GMAC_VLAN_VTHM | GMAC_VLAN_ETV; + if (is_double) { + value |= GMAC_VLAN_EDVLP; + value |= GMAC_VLAN_ESVL; + value |= GMAC_VLAN_DOVLTC; + } + + writel(value, ioaddr + GMAC_VLAN_TAG); + } else { + u32 value = readl(ioaddr + GMAC_VLAN_TAG); + + value &= ~(GMAC_VLAN_VTHM | GMAC_VLAN_ETV); + value &= ~(GMAC_VLAN_EDVLP | GMAC_VLAN_ESVL); + value &= ~GMAC_VLAN_DOVLTC; + value &= ~GMAC_VLAN_VID; + + writel(value, ioaddr + GMAC_VLAN_TAG); + } +} + +static void dwmac4_sarc_configure(void __iomem *ioaddr, int val) +{ + u32 value = readl(ioaddr + GMAC_CONFIG); + + value &= ~GMAC_CONFIG_SARC; + value |= val << GMAC_CONFIG_SARC_SHIFT; + + writel(value, ioaddr + GMAC_CONFIG); +} + +static void dwmac4_enable_vlan(struct mac_device_info *hw, u32 type) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + value = readl(ioaddr + GMAC_VLAN_INCL); + value |= GMAC_VLAN_VLTI; + value |= GMAC_VLAN_CSVL; /* Only use SVLAN */ + value &= ~GMAC_VLAN_VLC; + value |= (type << GMAC_VLAN_VLC_SHIFT) & GMAC_VLAN_VLC; + writel(value, ioaddr + GMAC_VLAN_INCL); +} + +static void dwmac4_set_arp_offload(struct mac_device_info *hw, bool en, + u32 addr) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + writel(addr, ioaddr + GMAC_ARP_ADDR); + + value = readl(ioaddr + GMAC_CONFIG); + if (en) + value |= GMAC_CONFIG_ARPEN; + else + value &= ~GMAC_CONFIG_ARPEN; + writel(value, ioaddr + GMAC_CONFIG); +} + const struct stmmac_ops dwmac4_ops = { .core_init = dwmac4_core_init, .set_mac = stmmac_set_mac, @@ -767,6 +828,10 @@ const struct stmmac_ops dwmac4_ops = { .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, .set_mac_loopback = dwmac4_set_mac_loopback, + .update_vlan_hash = dwmac4_update_vlan_hash, + .sarc_configure = dwmac4_sarc_configure, + .enable_vlan = dwmac4_enable_vlan, + .set_arp_offload = dwmac4_set_arp_offload, }; const struct stmmac_ops dwmac410_ops = { @@ -799,6 +864,10 @@ const struct stmmac_ops dwmac410_ops = { .debug = dwmac4_debug, .set_filter = dwmac4_set_filter, .set_mac_loopback = dwmac4_set_mac_loopback, + .update_vlan_hash = dwmac4_update_vlan_hash, + .sarc_configure = dwmac4_sarc_configure, + .enable_vlan = dwmac4_enable_vlan, + .set_arp_offload = dwmac4_set_arp_offload, }; const struct stmmac_ops dwmac510_ops = { @@ -836,6 +905,10 @@ const struct stmmac_ops dwmac510_ops = { .rxp_config = dwmac5_rxp_config, .flex_pps_config = dwmac5_flex_pps_config, .set_mac_loopback = dwmac4_set_mac_loopback, + .update_vlan_hash = dwmac4_update_vlan_hash, + .sarc_configure = dwmac4_sarc_configure, + .enable_vlan = dwmac4_enable_vlan, + .set_arp_offload = dwmac4_set_arp_offload, }; int dwmac4_setup(struct stmmac_priv *priv) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index dbde23e7e169..15eb1abba91d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -443,6 +443,13 @@ static void dwmac4_clear(struct dma_desc *p) p->des3 = 0; } +static void dwmac4_set_sarc(struct dma_desc *p, u32 sarc_type) +{ + sarc_type <<= TDES3_SA_INSERT_CTRL_SHIFT; + + p->des3 |= cpu_to_le32(sarc_type & TDES3_SA_INSERT_CTRL_MASK); +} + static int set_16kib_bfsize(int mtu) { int ret = 0; @@ -452,6 +459,39 @@ static int set_16kib_bfsize(int mtu) return ret; } +static void dwmac4_set_vlan_tag(struct dma_desc *p, u16 tag, u16 inner_tag, + u32 inner_type) +{ + p->des0 = 0; + p->des1 = 0; + p->des2 = 0; + p->des3 = 0; + + /* Inner VLAN */ + if (inner_type) { + u32 des = inner_tag << TDES2_IVT_SHIFT; + + des &= TDES2_IVT_MASK; + p->des2 = cpu_to_le32(des); + + des = inner_type << TDES3_IVTIR_SHIFT; + des &= TDES3_IVTIR_MASK; + p->des3 = cpu_to_le32(des | TDES3_IVLTV); + } + + /* Outer VLAN */ + p->des3 |= cpu_to_le32(tag & TDES3_VLAN_TAG); + p->des3 |= cpu_to_le32(TDES3_VLTV); + + p->des3 |= cpu_to_le32(TDES3_CONTEXT_TYPE); +} + +static void dwmac4_set_vlan(struct dma_desc *p, u32 type) +{ + type <<= TDES2_VLAN_TAG_SHIFT; + p->des2 |= cpu_to_le32(type & TDES2_VLAN_TAG_MASK); +} + const struct stmmac_desc_ops dwmac4_desc_ops = { .tx_status = dwmac4_wrback_get_tx_status, .rx_status = dwmac4_wrback_get_rx_status, @@ -476,6 +516,9 @@ const struct stmmac_desc_ops dwmac4_desc_ops = { .get_addr = dwmac4_get_addr, .set_addr = dwmac4_set_addr, .clear = dwmac4_clear, + .set_sarc = dwmac4_set_sarc, + .set_vlan_tag = dwmac4_set_vlan_tag, + .set_vlan = dwmac4_set_vlan, }; const struct stmmac_mode_ops dwmac4_ring_mode_ops = { diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h index f58191174287..0d7b3bbcd5a7 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.h @@ -18,13 +18,21 @@ /* TDES2 (read format) */ #define TDES2_BUFFER1_SIZE_MASK GENMASK(13, 0) #define TDES2_VLAN_TAG_MASK GENMASK(15, 14) +#define TDES2_VLAN_TAG_SHIFT 14 #define TDES2_BUFFER2_SIZE_MASK GENMASK(29, 16) #define TDES2_BUFFER2_SIZE_MASK_SHIFT 16 +#define TDES3_IVTIR_MASK GENMASK(19, 18) +#define TDES3_IVTIR_SHIFT 18 +#define TDES3_IVLTV BIT(17) #define TDES2_TIMESTAMP_ENABLE BIT(30) +#define TDES2_IVT_MASK GENMASK(31, 16) +#define TDES2_IVT_SHIFT 16 #define TDES2_INTERRUPT_ON_COMPLETION BIT(31) /* TDES3 (read format) */ #define TDES3_PACKET_SIZE_MASK GENMASK(14, 0) +#define TDES3_VLAN_TAG GENMASK(15, 0) +#define TDES3_VLTV BIT(16) #define TDES3_CHECKSUM_INSERTION_MASK GENMASK(17, 16) #define TDES3_CHECKSUM_INSERTION_SHIFT 16 #define TDES3_TCP_PKT_PAYLOAD_MASK GENMASK(17, 0) @@ -32,6 +40,7 @@ #define TDES3_HDR_LEN_SHIFT 19 #define TDES3_SLOT_NUMBER_MASK GENMASK(22, 19) #define TDES3_SA_INSERT_CTRL_MASK GENMASK(25, 23) +#define TDES3_SA_INSERT_CTRL_SHIFT 23 #define TDES3_CRC_PAD_CTRL_MASK GENMASK(27, 26) /* TDES3 (write back format) */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index 3ed5508586ef..68c157979b94 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -333,7 +333,7 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr, dma_cap->mbps_10_100 = (hw_cap & GMAC_HW_FEAT_MIISEL); dma_cap->mbps_1000 = (hw_cap & GMAC_HW_FEAT_GMIISEL) >> 1; dma_cap->half_duplex = (hw_cap & GMAC_HW_FEAT_HDSEL) >> 2; - dma_cap->hash_filter = (hw_cap & GMAC_HW_FEAT_VLHASH) >> 4; + dma_cap->vlhash = (hw_cap & GMAC_HW_FEAT_VLHASH) >> 4; dma_cap->multi_addr = (hw_cap & GMAC_HW_FEAT_ADDMAC) >> 18; dma_cap->pcs = (hw_cap & GMAC_HW_FEAT_PCSSEL) >> 3; dma_cap->sma_mdio = (hw_cap & GMAC_HW_FEAT_SMASEL) >> 5; @@ -348,6 +348,8 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr, /* TX and RX csum */ dma_cap->tx_coe = (hw_cap & GMAC_HW_FEAT_TXCOSEL) >> 14; dma_cap->rx_coe = (hw_cap & GMAC_HW_FEAT_RXCOESEL) >> 16; + dma_cap->vlins = (hw_cap & GMAC_HW_FEAT_SAVLANINS) >> 27; + dma_cap->arpoffsel = (hw_cap & GMAC_HW_FEAT_ARPOFFSEL) >> 9; /* MAC HW feature1 */ hw_cap = readl(ioaddr + GMAC_HW_FEATURE1); @@ -385,6 +387,7 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr, dma_cap->frpes = (hw_cap & GMAC_HW_FEAT_FRPES) >> 13; dma_cap->frpbs = (hw_cap & GMAC_HW_FEAT_FRPBS) >> 11; dma_cap->frpsel = (hw_cap & GMAC_HW_FEAT_FRPSEL) >> 10; + dma_cap->dvlan = (hw_cap & GMAC_HW_FEAT_DVLAN) >> 5; } /* Enable/disable TSO feature and set MSS */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h index 3174b701aa90..5923ca62d793 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2.h @@ -32,6 +32,9 @@ #define XGMAC_CONFIG_ARPEN BIT(31) #define XGMAC_CONFIG_GPSL GENMASK(29, 16) #define XGMAC_CONFIG_GPSL_SHIFT 16 +#define XGMAC_CONFIG_HDSMS GENMASK(14, 12) +#define XGMAC_CONFIG_HDSMS_SHIFT 12 +#define XGMAC_CONFIG_HDSMS_256 (0x2 << XGMAC_CONFIG_HDSMS_SHIFT) #define XGMAC_CONFIG_S2KP BIT(11) #define XGMAC_CONFIG_LM BIT(10) #define XGMAC_CONFIG_IPC BIT(9) @@ -41,9 +44,12 @@ #define XGMAC_CONFIG_CST BIT(2) #define XGMAC_CONFIG_ACS BIT(1) #define XGMAC_CONFIG_RE BIT(0) -#define XGMAC_CORE_INIT_RX 0 +#define XGMAC_CORE_INIT_RX (XGMAC_CONFIG_GPSLCE | XGMAC_CONFIG_WD | \ + (XGMAC_JUMBO_LEN << XGMAC_CONFIG_GPSL_SHIFT)) #define XGMAC_PACKET_FILTER 0x00000008 #define XGMAC_FILTER_RA BIT(31) +#define XGMAC_FILTER_IPFE BIT(20) +#define XGMAC_FILTER_VTFE BIT(16) #define XGMAC_FILTER_HPF BIT(10) #define XGMAC_FILTER_PCF BIT(7) #define XGMAC_FILTER_PM BIT(4) @@ -51,6 +57,19 @@ #define XGMAC_FILTER_PR BIT(0) #define XGMAC_HASH_TABLE(x) (0x00000010 + (x) * 4) #define XGMAC_MAX_HASH_TABLE 8 +#define XGMAC_VLAN_TAG 0x00000050 +#define XGMAC_VLAN_EDVLP BIT(26) +#define XGMAC_VLAN_VTHM BIT(25) +#define XGMAC_VLAN_DOVLTC BIT(20) +#define XGMAC_VLAN_ESVL BIT(18) +#define XGMAC_VLAN_ETV BIT(16) +#define XGMAC_VLAN_VID GENMASK(15, 0) +#define XGMAC_VLAN_HASH_TABLE 0x00000058 +#define XGMAC_VLAN_INCL 0x00000060 +#define XGMAC_VLAN_VLTI BIT(20) +#define XGMAC_VLAN_CSVL BIT(19) +#define XGMAC_VLAN_VLC GENMASK(17, 16) +#define XGMAC_VLAN_VLC_SHIFT 16 #define XGMAC_RXQ_CTRL0 0x000000a0 #define XGMAC_RXQEN(x) GENMASK((x) * 2 + 1, (x) * 2) #define XGMAC_RXQEN_SHIFT(x) ((x) * 2) @@ -59,6 +78,7 @@ #define XGMAC_PSRQ(x) GENMASK((x) * 8 + 7, (x) * 8) #define XGMAC_PSRQ_SHIFT(x) ((x) * 8) #define XGMAC_INT_STATUS 0x000000b0 +#define XGMAC_LPIIS BIT(5) #define XGMAC_PMTIS BIT(4) #define XGMAC_INT_EN 0x000000b4 #define XGMAC_TSIE BIT(12) @@ -76,19 +96,35 @@ #define XGMAC_RWKPKTEN BIT(2) #define XGMAC_MGKPKTEN BIT(1) #define XGMAC_PWRDWN BIT(0) +#define XGMAC_LPI_CTRL 0x000000d0 +#define XGMAC_TXCGE BIT(21) +#define XGMAC_LPITXA BIT(19) +#define XGMAC_PLS BIT(17) +#define XGMAC_LPITXEN BIT(16) +#define XGMAC_RLPIEX BIT(3) +#define XGMAC_RLPIEN BIT(2) +#define XGMAC_TLPIEX BIT(1) +#define XGMAC_TLPIEN BIT(0) +#define XGMAC_LPI_TIMER_CTRL 0x000000d4 #define XGMAC_HW_FEATURE0 0x0000011c #define XGMAC_HWFEAT_SAVLANINS BIT(27) #define XGMAC_HWFEAT_RXCOESEL BIT(16) #define XGMAC_HWFEAT_TXCOESEL BIT(14) +#define XGMAC_HWFEAT_EEESEL BIT(13) #define XGMAC_HWFEAT_TSSEL BIT(12) #define XGMAC_HWFEAT_AVSEL BIT(11) #define XGMAC_HWFEAT_RAVSEL BIT(10) #define XGMAC_HWFEAT_ARPOFFSEL BIT(9) +#define XGMAC_HWFEAT_MMCSEL BIT(8) #define XGMAC_HWFEAT_MGKSEL BIT(7) #define XGMAC_HWFEAT_RWKSEL BIT(6) +#define XGMAC_HWFEAT_VLHASH BIT(4) #define XGMAC_HWFEAT_GMIISEL BIT(1) #define XGMAC_HW_FEATURE1 0x00000120 +#define XGMAC_HWFEAT_L3L4FNUM GENMASK(30, 27) +#define XGMAC_HWFEAT_RSSEN BIT(20) #define XGMAC_HWFEAT_TSOEN BIT(18) +#define XGMAC_HWFEAT_SPHEN BIT(17) #define XGMAC_HWFEAT_ADDR64 GENMASK(15, 14) #define XGMAC_HWFEAT_TXFIFOSIZE GENMASK(10, 6) #define XGMAC_HWFEAT_RXFIFOSIZE GENMASK(4, 0) @@ -98,6 +134,16 @@ #define XGMAC_HWFEAT_RXCHCNT GENMASK(15, 12) #define XGMAC_HWFEAT_TXQCNT GENMASK(9, 6) #define XGMAC_HWFEAT_RXQCNT GENMASK(3, 0) +#define XGMAC_HW_FEATURE3 0x00000128 +#define XGMAC_HWFEAT_ASP GENMASK(15, 14) +#define XGMAC_HWFEAT_DVLAN BIT(13) +#define XGMAC_HWFEAT_FRPES GENMASK(12, 11) +#define XGMAC_HWFEAT_FRPPB GENMASK(10, 9) +#define XGMAC_HWFEAT_FRPSEL BIT(3) +#define XGMAC_MAC_DPP_FSM_INT_STATUS 0x00000150 +#define XGMAC_MAC_FSM_CONTROL 0x00000158 +#define XGMAC_PRTYEN BIT(1) +#define XGMAC_TMOUTEN BIT(0) #define XGMAC_MDIO_ADDR 0x00000200 #define XGMAC_MDIO_DATA 0x00000204 #define XGMAC_MDIO_C22P 0x00000220 @@ -107,15 +153,74 @@ #define XGMAC_DCS GENMASK(19, 16) #define XGMAC_DCS_SHIFT 16 #define XGMAC_ADDRx_LOW(x) (0x00000304 + (x) * 0x8) +#define XGMAC_L3L4_ADDR_CTRL 0x00000c00 +#define XGMAC_IDDR GENMASK(15, 8) +#define XGMAC_IDDR_SHIFT 8 +#define XGMAC_IDDR_FNUM 4 +#define XGMAC_TT BIT(1) +#define XGMAC_XB BIT(0) +#define XGMAC_L3L4_DATA 0x00000c04 +#define XGMAC_L3L4_CTRL 0x0 +#define XGMAC_L4DPIM0 BIT(21) +#define XGMAC_L4DPM0 BIT(20) +#define XGMAC_L4SPIM0 BIT(19) +#define XGMAC_L4SPM0 BIT(18) +#define XGMAC_L4PEN0 BIT(16) +#define XGMAC_L3HDBM0 GENMASK(15, 11) +#define XGMAC_L3HSBM0 GENMASK(10, 6) +#define XGMAC_L3DAIM0 BIT(5) +#define XGMAC_L3DAM0 BIT(4) +#define XGMAC_L3SAIM0 BIT(3) +#define XGMAC_L3SAM0 BIT(2) +#define XGMAC_L3PEN0 BIT(0) +#define XGMAC_L4_ADDR 0x1 +#define XGMAC_L4DP0 GENMASK(31, 16) +#define XGMAC_L4DP0_SHIFT 16 +#define XGMAC_L4SP0 GENMASK(15, 0) +#define XGMAC_L3_ADDR0 0x4 +#define XGMAC_L3_ADDR1 0x5 +#define XGMAC_L3_ADDR2 0x6 +#define XMGAC_L3_ADDR3 0x7 #define XGMAC_ARP_ADDR 0x00000c10 +#define XGMAC_RSS_CTRL 0x00000c80 +#define XGMAC_UDP4TE BIT(3) +#define XGMAC_TCP4TE BIT(2) +#define XGMAC_IP2TE BIT(1) +#define XGMAC_RSSE BIT(0) +#define XGMAC_RSS_ADDR 0x00000c88 +#define XGMAC_RSSIA_SHIFT 8 +#define XGMAC_ADDRT BIT(2) +#define XGMAC_CT BIT(1) +#define XGMAC_OB BIT(0) +#define XGMAC_RSS_DATA 0x00000c8c #define XGMAC_TIMESTAMP_STATUS 0x00000d20 #define XGMAC_TXTSC BIT(15) #define XGMAC_TXTIMESTAMP_NSEC 0x00000d30 #define XGMAC_TXTSSTSLO GENMASK(30, 0) #define XGMAC_TXTIMESTAMP_SEC 0x00000d34 +#define XGMAC_PPS_CONTROL 0x00000d70 +#define XGMAC_PPS_MAXIDX(x) ((((x) + 1) * 8) - 1) +#define XGMAC_PPS_MINIDX(x) ((x) * 8) +#define XGMAC_PPSx_MASK(x) \ + GENMASK(XGMAC_PPS_MAXIDX(x), XGMAC_PPS_MINIDX(x)) +#define XGMAC_TRGTMODSELx(x, val) \ + GENMASK(XGMAC_PPS_MAXIDX(x) - 1, XGMAC_PPS_MAXIDX(x) - 2) & \ + ((val) << (XGMAC_PPS_MAXIDX(x) - 2)) +#define XGMAC_PPSCMDx(x, val) \ + GENMASK(XGMAC_PPS_MINIDX(x) + 3, XGMAC_PPS_MINIDX(x)) & \ + ((val) << XGMAC_PPS_MINIDX(x)) +#define XGMAC_PPSCMD_START 0x2 +#define XGMAC_PPSCMD_STOP 0x5 +#define XGMAC_PPSEN0 BIT(4) +#define XGMAC_PPSx_TARGET_TIME_SEC(x) (0x00000d80 + (x) * 0x10) +#define XGMAC_PPSx_TARGET_TIME_NSEC(x) (0x00000d84 + (x) * 0x10) +#define XGMAC_TRGTBUSY0 BIT(31) +#define XGMAC_PPSx_INTERVAL(x) (0x00000d88 + (x) * 0x10) +#define XGMAC_PPSx_WIDTH(x) (0x00000d8c + (x) * 0x10) /* MTL Registers */ #define XGMAC_MTL_OPMODE 0x00001000 +#define XGMAC_FRPE BIT(15) #define XGMAC_ETSALG GENMASK(6, 5) #define XGMAC_WRR (0x0 << 5) #define XGMAC_WFQ (0x1 << 5) @@ -124,8 +229,32 @@ #define XGMAC_MTL_INT_STATUS 0x00001020 #define XGMAC_MTL_RXQ_DMA_MAP0 0x00001030 #define XGMAC_MTL_RXQ_DMA_MAP1 0x00001034 -#define XGMAC_QxMDMACH(x) GENMASK((x) * 8 + 3, (x) * 8) +#define XGMAC_QxMDMACH(x) GENMASK((x) * 8 + 7, (x) * 8) #define XGMAC_QxMDMACH_SHIFT(x) ((x) * 8) +#define XGMAC_QDDMACH BIT(7) +#define XGMAC_TC_PRTY_MAP0 0x00001040 +#define XGMAC_TC_PRTY_MAP1 0x00001044 +#define XGMAC_PSTC(x) GENMASK((x) * 8 + 7, (x) * 8) +#define XGMAC_PSTC_SHIFT(x) ((x) * 8) +#define XGMAC_MTL_RXP_CONTROL_STATUS 0x000010a0 +#define XGMAC_RXPI BIT(31) +#define XGMAC_NPE GENMASK(23, 16) +#define XGMAC_NVE GENMASK(7, 0) +#define XGMAC_MTL_RXP_IACC_CTRL_ST 0x000010b0 +#define XGMAC_STARTBUSY BIT(31) +#define XGMAC_WRRDN BIT(16) +#define XGMAC_ADDR GENMASK(9, 0) +#define XGMAC_MTL_RXP_IACC_DATA 0x000010b4 +#define XGMAC_MTL_ECC_CONTROL 0x000010c0 +#define XGMAC_MTL_SAFETY_INT_STATUS 0x000010c4 +#define XGMAC_MEUIS BIT(1) +#define XGMAC_MECIS BIT(0) +#define XGMAC_MTL_ECC_INT_ENABLE 0x000010c8 +#define XGMAC_RPCEIE BIT(12) +#define XGMAC_ECEIE BIT(8) +#define XGMAC_RXCEIE BIT(4) +#define XGMAC_TXCEIE BIT(0) +#define XGMAC_MTL_ECC_INT_STATUS 0x000010cc #define XGMAC_MTL_TXQ_OPMODE(x) (0x00001100 + (0x80 * (x))) #define XGMAC_TQS GENMASK(25, 16) #define XGMAC_TQS_SHIFT 16 @@ -164,6 +293,7 @@ #define XGMAC_RXOVFIS BIT(16) #define XGMAC_ABPSIS BIT(1) #define XGMAC_TXUNFIS BIT(0) +#define XGMAC_MAC_REGSIZE (XGMAC_MTL_QINT_STATUS(15) / 4) /* DMA Registers */ #define XGMAC_DMA_MODE 0x00003000 @@ -190,7 +320,18 @@ #define XGMAC_TDPS GENMASK(29, 0) #define XGMAC_RX_EDMA_CTRL 0x00003044 #define XGMAC_RDPS GENMASK(29, 0) +#define XGMAC_DMA_SAFETY_INT_STATUS 0x00003064 +#define XGMAC_MCSIS BIT(31) +#define XGMAC_MSUIS BIT(29) +#define XGMAC_MSCIS BIT(28) +#define XGMAC_DEUIS BIT(1) +#define XGMAC_DECIS BIT(0) +#define XGMAC_DMA_ECC_INT_ENABLE 0x00003068 +#define XGMAC_DCEIE BIT(1) +#define XGMAC_TCEIE BIT(0) +#define XGMAC_DMA_ECC_INT_STATUS 0x0000306c #define XGMAC_DMA_CH_CONTROL(x) (0x00003100 + (0x80 * (x))) +#define XGMAC_SPH BIT(24) #define XGMAC_PBLx8 BIT(16) #define XGMAC_DMA_CH_TX_CONTROL(x) (0x00003104 + (0x80 * (x))) #define XGMAC_TxPBL GENMASK(21, 16) @@ -230,12 +371,17 @@ #define XGMAC_TBU BIT(2) #define XGMAC_TPS BIT(1) #define XGMAC_TI BIT(0) +#define XGMAC_REGSIZE ((0x0000317c + (0x80 * 15)) / 4) /* Descriptors */ +#define XGMAC_TDES2_IVT GENMASK(31, 16) +#define XGMAC_TDES2_IVT_SHIFT 16 #define XGMAC_TDES2_IOC BIT(31) #define XGMAC_TDES2_TTSE BIT(30) #define XGMAC_TDES2_B2L GENMASK(29, 16) #define XGMAC_TDES2_B2L_SHIFT 16 +#define XGMAC_TDES2_VTIR GENMASK(15, 14) +#define XGMAC_TDES2_VTIR_SHIFT 14 #define XGMAC_TDES2_B1L GENMASK(13, 0) #define XGMAC_TDES3_OWN BIT(31) #define XGMAC_TDES3_CTXT BIT(30) @@ -244,18 +390,33 @@ #define XGMAC_TDES3_CPC GENMASK(27, 26) #define XGMAC_TDES3_CPC_SHIFT 26 #define XGMAC_TDES3_TCMSSV BIT(26) +#define XGMAC_TDES3_SAIC GENMASK(25, 23) +#define XGMAC_TDES3_SAIC_SHIFT 23 #define XGMAC_TDES3_THL GENMASK(22, 19) #define XGMAC_TDES3_THL_SHIFT 19 +#define XGMAC_TDES3_IVTIR GENMASK(19, 18) +#define XGMAC_TDES3_IVTIR_SHIFT 18 #define XGMAC_TDES3_TSE BIT(18) +#define XGMAC_TDES3_IVLTV BIT(17) #define XGMAC_TDES3_CIC GENMASK(17, 16) #define XGMAC_TDES3_CIC_SHIFT 16 #define XGMAC_TDES3_TPL GENMASK(17, 0) +#define XGMAC_TDES3_VLTV BIT(16) +#define XGMAC_TDES3_VT GENMASK(15, 0) #define XGMAC_TDES3_FL GENMASK(14, 0) +#define XGMAC_RDES2_HL GENMASK(9, 0) #define XGMAC_RDES3_OWN BIT(31) #define XGMAC_RDES3_CTXT BIT(30) #define XGMAC_RDES3_IOC BIT(30) #define XGMAC_RDES3_LD BIT(28) #define XGMAC_RDES3_CDA BIT(27) +#define XGMAC_RDES3_RSV BIT(26) +#define XGMAC_RDES3_L34T GENMASK(23, 20) +#define XGMAC_RDES3_L34T_SHIFT 20 +#define XGMAC_L34T_IP4TCP 0x1 +#define XGMAC_L34T_IP4UDP 0x2 +#define XGMAC_L34T_IP6TCP 0x9 +#define XGMAC_L34T_IP6UDP 0xA #define XGMAC_RDES3_ES BIT(15) #define XGMAC_RDES3_PL GENMASK(13, 0) #define XGMAC_RDES3_TSD BIT(6) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c index 85c68b7ee8c6..d5173dd02a71 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c @@ -6,14 +6,15 @@ #include <linux/bitrev.h> #include <linux/crc32.h> +#include <linux/iopoll.h> #include "stmmac.h" +#include "stmmac_ptp.h" #include "dwxgmac2.h" static void dwxgmac2_core_init(struct mac_device_info *hw, struct net_device *dev) { void __iomem *ioaddr = hw->pcsr; - int mtu = dev->mtu; u32 tx, rx; tx = readl(ioaddr + XGMAC_TX_CONFIG); @@ -22,16 +23,6 @@ static void dwxgmac2_core_init(struct mac_device_info *hw, tx |= XGMAC_CORE_INIT_TX; rx |= XGMAC_CORE_INIT_RX; - if (mtu >= 9000) { - rx |= XGMAC_CONFIG_GPSLCE; - rx |= XGMAC_JUMBO_LEN << XGMAC_CONFIG_GPSL_SHIFT; - rx |= XGMAC_CONFIG_WD; - } else if (mtu > 2000) { - rx |= XGMAC_CONFIG_JE; - } else if (mtu > 1500) { - rx |= XGMAC_CONFIG_S2KP; - } - if (hw->ps) { tx |= XGMAC_CONFIG_TE; tx &= ~hw->link.speed_mask; @@ -118,6 +109,23 @@ static void dwxgmac2_rx_queue_prio(struct mac_device_info *hw, u32 prio, writel(value, ioaddr + reg); } +static void dwxgmac2_tx_queue_prio(struct mac_device_info *hw, u32 prio, + u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value, reg; + + reg = (queue < 4) ? XGMAC_TC_PRTY_MAP0 : XGMAC_TC_PRTY_MAP1; + if (queue >= 4) + queue -= 4; + + value = readl(ioaddr + reg); + value &= ~XGMAC_PSTC(queue); + value |= (prio << XGMAC_PSTC_SHIFT(queue)) & XGMAC_PSTC(queue); + + writel(value, ioaddr + reg); +} + static void dwxgmac2_prog_mtl_rx_algorithms(struct mac_device_info *hw, u32 rx_alg) { @@ -144,7 +152,9 @@ static void dwxgmac2_prog_mtl_tx_algorithms(struct mac_device_info *hw, u32 tx_alg) { void __iomem *ioaddr = hw->pcsr; + bool ets = true; u32 value; + int i; value = readl(ioaddr + XGMAC_MTL_OPMODE); value &= ~XGMAC_ETSALG; @@ -160,10 +170,28 @@ static void dwxgmac2_prog_mtl_tx_algorithms(struct mac_device_info *hw, value |= XGMAC_DWRR; break; default: + ets = false; break; } writel(value, ioaddr + XGMAC_MTL_OPMODE); + + /* Set ETS if desired */ + for (i = 0; i < MTL_MAX_TX_QUEUES; i++) { + value = readl(ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(i)); + value &= ~XGMAC_TSA; + if (ets) + value |= XGMAC_ETS; + writel(value, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(i)); + } +} + +static void dwxgmac2_set_mtl_tx_queue_weight(struct mac_device_info *hw, + u32 weight, u32 queue) +{ + void __iomem *ioaddr = hw->pcsr; + + writel(weight, ioaddr + XGMAC_MTL_TCx_QUANTUM_WEIGHT(queue)); } static void dwxgmac2_map_mtl_to_dma(struct mac_device_info *hw, u32 queue, @@ -200,11 +228,21 @@ static void dwxgmac2_config_cbs(struct mac_device_info *hw, writel(value, ioaddr + XGMAC_MTL_TCx_ETS_CONTROL(queue)); } +static void dwxgmac2_dump_regs(struct mac_device_info *hw, u32 *reg_space) +{ + void __iomem *ioaddr = hw->pcsr; + int i; + + for (i = 0; i < XGMAC_MAC_REGSIZE; i++) + reg_space[i] = readl(ioaddr + i * 4); +} + static int dwxgmac2_host_irq_status(struct mac_device_info *hw, struct stmmac_extra_stats *x) { void __iomem *ioaddr = hw->pcsr; u32 stat, en; + int ret = 0; en = readl(ioaddr + XGMAC_INT_EN); stat = readl(ioaddr + XGMAC_INT_STATUS); @@ -216,7 +254,24 @@ static int dwxgmac2_host_irq_status(struct mac_device_info *hw, readl(ioaddr + XGMAC_PMT); } - return 0; + if (stat & XGMAC_LPIIS) { + u32 lpi = readl(ioaddr + XGMAC_LPI_CTRL); + + if (lpi & XGMAC_TLPIEN) { + ret |= CORE_IRQ_TX_PATH_IN_LPI_MODE; + x->irq_tx_path_in_lpi_mode_n++; + } + if (lpi & XGMAC_TLPIEX) { + ret |= CORE_IRQ_TX_PATH_EXIT_LPI_MODE; + x->irq_tx_path_exit_lpi_mode_n++; + } + if (lpi & XGMAC_RLPIEN) + x->irq_rx_path_in_lpi_mode_n++; + if (lpi & XGMAC_RLPIEX) + x->irq_rx_path_exit_lpi_mode_n++; + } + + return ret; } static int dwxgmac2_host_mtl_irq_status(struct mac_device_info *hw, u32 chan) @@ -309,6 +364,53 @@ static void dwxgmac2_get_umac_addr(struct mac_device_info *hw, addr[5] = (hi_addr >> 8) & 0xff; } +static void dwxgmac2_set_eee_mode(struct mac_device_info *hw, + bool en_tx_lpi_clockgating) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + value = readl(ioaddr + XGMAC_LPI_CTRL); + + value |= XGMAC_LPITXEN | XGMAC_LPITXA; + if (en_tx_lpi_clockgating) + value |= XGMAC_TXCGE; + + writel(value, ioaddr + XGMAC_LPI_CTRL); +} + +static void dwxgmac2_reset_eee_mode(struct mac_device_info *hw) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + value = readl(ioaddr + XGMAC_LPI_CTRL); + value &= ~(XGMAC_LPITXEN | XGMAC_LPITXA | XGMAC_TXCGE); + writel(value, ioaddr + XGMAC_LPI_CTRL); +} + +static void dwxgmac2_set_eee_pls(struct mac_device_info *hw, int link) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + value = readl(ioaddr + XGMAC_LPI_CTRL); + if (link) + value |= XGMAC_PLS; + else + value &= ~XGMAC_PLS; + writel(value, ioaddr + XGMAC_LPI_CTRL); +} + +static void dwxgmac2_set_eee_timer(struct mac_device_info *hw, int ls, int tw) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + value = (tw & 0xffff) | ((ls & 0x3ff) << 16); + writel(value, ioaddr + XGMAC_LPI_TIMER_CTRL); +} + static void dwxgmac2_set_mchash(void __iomem *ioaddr, u32 *mcfilterbits, int mcbitslog2) { @@ -402,36 +504,888 @@ static void dwxgmac2_set_mac_loopback(void __iomem *ioaddr, bool enable) writel(value, ioaddr + XGMAC_RX_CONFIG); } +static int dwxgmac2_rss_write_reg(void __iomem *ioaddr, bool is_key, int idx, + u32 val) +{ + u32 ctrl = 0; + + writel(val, ioaddr + XGMAC_RSS_DATA); + ctrl |= idx << XGMAC_RSSIA_SHIFT; + ctrl |= is_key ? XGMAC_ADDRT : 0x0; + ctrl |= XGMAC_OB; + writel(ctrl, ioaddr + XGMAC_RSS_ADDR); + + return readl_poll_timeout(ioaddr + XGMAC_RSS_ADDR, ctrl, + !(ctrl & XGMAC_OB), 100, 10000); +} + +static int dwxgmac2_rss_configure(struct mac_device_info *hw, + struct stmmac_rss *cfg, u32 num_rxq) +{ + void __iomem *ioaddr = hw->pcsr; + u32 *key = (u32 *)cfg->key; + int i, ret; + u32 value; + + value = readl(ioaddr + XGMAC_RSS_CTRL); + if (!cfg->enable) { + value &= ~XGMAC_RSSE; + writel(value, ioaddr + XGMAC_RSS_CTRL); + return 0; + } + + for (i = 0; i < (sizeof(cfg->key) / sizeof(u32)); i++) { + ret = dwxgmac2_rss_write_reg(ioaddr, true, i, *key++); + if (ret) + return ret; + } + + for (i = 0; i < ARRAY_SIZE(cfg->table); i++) { + ret = dwxgmac2_rss_write_reg(ioaddr, false, i, cfg->table[i]); + if (ret) + return ret; + } + + for (i = 0; i < num_rxq; i++) + dwxgmac2_map_mtl_to_dma(hw, i, XGMAC_QDDMACH); + + value |= XGMAC_UDP4TE | XGMAC_TCP4TE | XGMAC_IP2TE | XGMAC_RSSE; + writel(value, ioaddr + XGMAC_RSS_CTRL); + return 0; +} + +static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash, + bool is_double) +{ + void __iomem *ioaddr = hw->pcsr; + + writel(hash, ioaddr + XGMAC_VLAN_HASH_TABLE); + + if (hash) { + u32 value = readl(ioaddr + XGMAC_PACKET_FILTER); + + value |= XGMAC_FILTER_VTFE; + + writel(value, ioaddr + XGMAC_PACKET_FILTER); + + value = XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV; + if (is_double) { + value |= XGMAC_VLAN_EDVLP; + value |= XGMAC_VLAN_ESVL; + value |= XGMAC_VLAN_DOVLTC; + } + + writel(value, ioaddr + XGMAC_VLAN_TAG); + } else { + u32 value = readl(ioaddr + XGMAC_PACKET_FILTER); + + value &= ~XGMAC_FILTER_VTFE; + + writel(value, ioaddr + XGMAC_PACKET_FILTER); + + value = readl(ioaddr + XGMAC_VLAN_TAG); + + value &= ~(XGMAC_VLAN_VTHM | XGMAC_VLAN_ETV); + value &= ~(XGMAC_VLAN_EDVLP | XGMAC_VLAN_ESVL); + value &= ~XGMAC_VLAN_DOVLTC; + value &= ~XGMAC_VLAN_VID; + + writel(value, ioaddr + XGMAC_VLAN_TAG); + } +} + +struct dwxgmac3_error_desc { + bool valid; + const char *desc; + const char *detailed_desc; +}; + +#define STAT_OFF(field) offsetof(struct stmmac_safety_stats, field) + +static void dwxgmac3_log_error(struct net_device *ndev, u32 value, bool corr, + const char *module_name, + const struct dwxgmac3_error_desc *desc, + unsigned long field_offset, + struct stmmac_safety_stats *stats) +{ + unsigned long loc, mask; + u8 *bptr = (u8 *)stats; + unsigned long *ptr; + + ptr = (unsigned long *)(bptr + field_offset); + + mask = value; + for_each_set_bit(loc, &mask, 32) { + netdev_err(ndev, "Found %s error in %s: '%s: %s'\n", corr ? + "correctable" : "uncorrectable", module_name, + desc[loc].desc, desc[loc].detailed_desc); + + /* Update counters */ + ptr[loc]++; + } +} + +static const struct dwxgmac3_error_desc dwxgmac3_mac_errors[32]= { + { true, "ATPES", "Application Transmit Interface Parity Check Error" }, + { true, "DPES", "Descriptor Cache Data Path Parity Check Error" }, + { true, "TPES", "TSO Data Path Parity Check Error" }, + { true, "TSOPES", "TSO Header Data Path Parity Check Error" }, + { true, "MTPES", "MTL Data Path Parity Check Error" }, + { true, "MTSPES", "MTL TX Status Data Path Parity Check Error" }, + { true, "MTBUPES", "MAC TBU Data Path Parity Check Error" }, + { true, "MTFCPES", "MAC TFC Data Path Parity Check Error" }, + { true, "ARPES", "Application Receive Interface Data Path Parity Check Error" }, + { true, "MRWCPES", "MTL RWC Data Path Parity Check Error" }, + { true, "MRRCPES", "MTL RCC Data Path Parity Check Error" }, + { true, "CWPES", "CSR Write Data Path Parity Check Error" }, + { true, "ASRPES", "AXI Slave Read Data Path Parity Check Error" }, + { true, "TTES", "TX FSM Timeout Error" }, + { true, "RTES", "RX FSM Timeout Error" }, + { true, "CTES", "CSR FSM Timeout Error" }, + { true, "ATES", "APP FSM Timeout Error" }, + { true, "PTES", "PTP FSM Timeout Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 18 */ + { false, "UNKNOWN", "Unknown Error" }, /* 19 */ + { false, "UNKNOWN", "Unknown Error" }, /* 20 */ + { true, "MSTTES", "Master Read/Write Timeout Error" }, + { true, "SLVTES", "Slave Read/Write Timeout Error" }, + { true, "ATITES", "Application Timeout on ATI Interface Error" }, + { true, "ARITES", "Application Timeout on ARI Interface Error" }, + { true, "FSMPES", "FSM State Parity Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 26 */ + { false, "UNKNOWN", "Unknown Error" }, /* 27 */ + { false, "UNKNOWN", "Unknown Error" }, /* 28 */ + { false, "UNKNOWN", "Unknown Error" }, /* 29 */ + { false, "UNKNOWN", "Unknown Error" }, /* 30 */ + { true, "CPI", "Control Register Parity Check Error" }, +}; + +static void dwxgmac3_handle_mac_err(struct net_device *ndev, + void __iomem *ioaddr, bool correctable, + struct stmmac_safety_stats *stats) +{ + u32 value; + + value = readl(ioaddr + XGMAC_MAC_DPP_FSM_INT_STATUS); + writel(value, ioaddr + XGMAC_MAC_DPP_FSM_INT_STATUS); + + dwxgmac3_log_error(ndev, value, correctable, "MAC", + dwxgmac3_mac_errors, STAT_OFF(mac_errors), stats); +} + +static const struct dwxgmac3_error_desc dwxgmac3_mtl_errors[32]= { + { true, "TXCES", "MTL TX Memory Error" }, + { true, "TXAMS", "MTL TX Memory Address Mismatch Error" }, + { true, "TXUES", "MTL TX Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 3 */ + { true, "RXCES", "MTL RX Memory Error" }, + { true, "RXAMS", "MTL RX Memory Address Mismatch Error" }, + { true, "RXUES", "MTL RX Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 7 */ + { true, "ECES", "MTL EST Memory Error" }, + { true, "EAMS", "MTL EST Memory Address Mismatch Error" }, + { true, "EUES", "MTL EST Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 11 */ + { true, "RPCES", "MTL RX Parser Memory Error" }, + { true, "RPAMS", "MTL RX Parser Memory Address Mismatch Error" }, + { true, "RPUES", "MTL RX Parser Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 15 */ + { false, "UNKNOWN", "Unknown Error" }, /* 16 */ + { false, "UNKNOWN", "Unknown Error" }, /* 17 */ + { false, "UNKNOWN", "Unknown Error" }, /* 18 */ + { false, "UNKNOWN", "Unknown Error" }, /* 19 */ + { false, "UNKNOWN", "Unknown Error" }, /* 20 */ + { false, "UNKNOWN", "Unknown Error" }, /* 21 */ + { false, "UNKNOWN", "Unknown Error" }, /* 22 */ + { false, "UNKNOWN", "Unknown Error" }, /* 23 */ + { false, "UNKNOWN", "Unknown Error" }, /* 24 */ + { false, "UNKNOWN", "Unknown Error" }, /* 25 */ + { false, "UNKNOWN", "Unknown Error" }, /* 26 */ + { false, "UNKNOWN", "Unknown Error" }, /* 27 */ + { false, "UNKNOWN", "Unknown Error" }, /* 28 */ + { false, "UNKNOWN", "Unknown Error" }, /* 29 */ + { false, "UNKNOWN", "Unknown Error" }, /* 30 */ + { false, "UNKNOWN", "Unknown Error" }, /* 31 */ +}; + +static void dwxgmac3_handle_mtl_err(struct net_device *ndev, + void __iomem *ioaddr, bool correctable, + struct stmmac_safety_stats *stats) +{ + u32 value; + + value = readl(ioaddr + XGMAC_MTL_ECC_INT_STATUS); + writel(value, ioaddr + XGMAC_MTL_ECC_INT_STATUS); + + dwxgmac3_log_error(ndev, value, correctable, "MTL", + dwxgmac3_mtl_errors, STAT_OFF(mtl_errors), stats); +} + +static const struct dwxgmac3_error_desc dwxgmac3_dma_errors[32]= { + { true, "TCES", "DMA TSO Memory Error" }, + { true, "TAMS", "DMA TSO Memory Address Mismatch Error" }, + { true, "TUES", "DMA TSO Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 3 */ + { true, "DCES", "DMA DCACHE Memory Error" }, + { true, "DAMS", "DMA DCACHE Address Mismatch Error" }, + { true, "DUES", "DMA DCACHE Memory Error" }, + { false, "UNKNOWN", "Unknown Error" }, /* 7 */ + { false, "UNKNOWN", "Unknown Error" }, /* 8 */ + { false, "UNKNOWN", "Unknown Error" }, /* 9 */ + { false, "UNKNOWN", "Unknown Error" }, /* 10 */ + { false, "UNKNOWN", "Unknown Error" }, /* 11 */ + { false, "UNKNOWN", "Unknown Error" }, /* 12 */ + { false, "UNKNOWN", "Unknown Error" }, /* 13 */ + { false, "UNKNOWN", "Unknown Error" }, /* 14 */ + { false, "UNKNOWN", "Unknown Error" }, /* 15 */ + { false, "UNKNOWN", "Unknown Error" }, /* 16 */ + { false, "UNKNOWN", "Unknown Error" }, /* 17 */ + { false, "UNKNOWN", "Unknown Error" }, /* 18 */ + { false, "UNKNOWN", "Unknown Error" }, /* 19 */ + { false, "UNKNOWN", "Unknown Error" }, /* 20 */ + { false, "UNKNOWN", "Unknown Error" }, /* 21 */ + { false, "UNKNOWN", "Unknown Error" }, /* 22 */ + { false, "UNKNOWN", "Unknown Error" }, /* 23 */ + { false, "UNKNOWN", "Unknown Error" }, /* 24 */ + { false, "UNKNOWN", "Unknown Error" }, /* 25 */ + { false, "UNKNOWN", "Unknown Error" }, /* 26 */ + { false, "UNKNOWN", "Unknown Error" }, /* 27 */ + { false, "UNKNOWN", "Unknown Error" }, /* 28 */ + { false, "UNKNOWN", "Unknown Error" }, /* 29 */ + { false, "UNKNOWN", "Unknown Error" }, /* 30 */ + { false, "UNKNOWN", "Unknown Error" }, /* 31 */ +}; + +static void dwxgmac3_handle_dma_err(struct net_device *ndev, + void __iomem *ioaddr, bool correctable, + struct stmmac_safety_stats *stats) +{ + u32 value; + + value = readl(ioaddr + XGMAC_DMA_ECC_INT_STATUS); + writel(value, ioaddr + XGMAC_DMA_ECC_INT_STATUS); + + dwxgmac3_log_error(ndev, value, correctable, "DMA", + dwxgmac3_dma_errors, STAT_OFF(dma_errors), stats); +} + +static int dwxgmac3_safety_feat_config(void __iomem *ioaddr, unsigned int asp) +{ + u32 value; + + if (!asp) + return -EINVAL; + + /* 1. Enable Safety Features */ + writel(0x0, ioaddr + XGMAC_MTL_ECC_CONTROL); + + /* 2. Enable MTL Safety Interrupts */ + value = readl(ioaddr + XGMAC_MTL_ECC_INT_ENABLE); + value |= XGMAC_RPCEIE; /* RX Parser Memory Correctable Error */ + value |= XGMAC_ECEIE; /* EST Memory Correctable Error */ + value |= XGMAC_RXCEIE; /* RX Memory Correctable Error */ + value |= XGMAC_TXCEIE; /* TX Memory Correctable Error */ + writel(value, ioaddr + XGMAC_MTL_ECC_INT_ENABLE); + + /* 3. Enable DMA Safety Interrupts */ + value = readl(ioaddr + XGMAC_DMA_ECC_INT_ENABLE); + value |= XGMAC_DCEIE; /* Descriptor Cache Memory Correctable Error */ + value |= XGMAC_TCEIE; /* TSO Memory Correctable Error */ + writel(value, ioaddr + XGMAC_DMA_ECC_INT_ENABLE); + + /* Only ECC Protection for External Memory feature is selected */ + if (asp <= 0x1) + return 0; + + /* 4. Enable Parity and Timeout for FSM */ + value = readl(ioaddr + XGMAC_MAC_FSM_CONTROL); + value |= XGMAC_PRTYEN; /* FSM Parity Feature */ + value |= XGMAC_TMOUTEN; /* FSM Timeout Feature */ + writel(value, ioaddr + XGMAC_MAC_FSM_CONTROL); + + return 0; +} + +static int dwxgmac3_safety_feat_irq_status(struct net_device *ndev, + void __iomem *ioaddr, + unsigned int asp, + struct stmmac_safety_stats *stats) +{ + bool err, corr; + u32 mtl, dma; + int ret = 0; + + if (!asp) + return -EINVAL; + + mtl = readl(ioaddr + XGMAC_MTL_SAFETY_INT_STATUS); + dma = readl(ioaddr + XGMAC_DMA_SAFETY_INT_STATUS); + + err = (mtl & XGMAC_MCSIS) || (dma & XGMAC_MCSIS); + corr = false; + if (err) { + dwxgmac3_handle_mac_err(ndev, ioaddr, corr, stats); + ret |= !corr; + } + + err = (mtl & (XGMAC_MEUIS | XGMAC_MECIS)) || + (dma & (XGMAC_MSUIS | XGMAC_MSCIS)); + corr = (mtl & XGMAC_MECIS) || (dma & XGMAC_MSCIS); + if (err) { + dwxgmac3_handle_mtl_err(ndev, ioaddr, corr, stats); + ret |= !corr; + } + + err = dma & (XGMAC_DEUIS | XGMAC_DECIS); + corr = dma & XGMAC_DECIS; + if (err) { + dwxgmac3_handle_dma_err(ndev, ioaddr, corr, stats); + ret |= !corr; + } + + return ret; +} + +static const struct dwxgmac3_error { + const struct dwxgmac3_error_desc *desc; +} dwxgmac3_all_errors[] = { + { dwxgmac3_mac_errors }, + { dwxgmac3_mtl_errors }, + { dwxgmac3_dma_errors }, +}; + +static int dwxgmac3_safety_feat_dump(struct stmmac_safety_stats *stats, + int index, unsigned long *count, + const char **desc) +{ + int module = index / 32, offset = index % 32; + unsigned long *ptr = (unsigned long *)stats; + + if (module >= ARRAY_SIZE(dwxgmac3_all_errors)) + return -EINVAL; + if (!dwxgmac3_all_errors[module].desc[offset].valid) + return -EINVAL; + if (count) + *count = *(ptr + index); + if (desc) + *desc = dwxgmac3_all_errors[module].desc[offset].desc; + return 0; +} + +static int dwxgmac3_rxp_disable(void __iomem *ioaddr) +{ + u32 val = readl(ioaddr + XGMAC_MTL_OPMODE); + + val &= ~XGMAC_FRPE; + writel(val, ioaddr + XGMAC_MTL_OPMODE); + + return 0; +} + +static void dwxgmac3_rxp_enable(void __iomem *ioaddr) +{ + u32 val; + + val = readl(ioaddr + XGMAC_MTL_OPMODE); + val |= XGMAC_FRPE; + writel(val, ioaddr + XGMAC_MTL_OPMODE); +} + +static int dwxgmac3_rxp_update_single_entry(void __iomem *ioaddr, + struct stmmac_tc_entry *entry, + int pos) +{ + int ret, i; + + for (i = 0; i < (sizeof(entry->val) / sizeof(u32)); i++) { + int real_pos = pos * (sizeof(entry->val) / sizeof(u32)) + i; + u32 val; + + /* Wait for ready */ + ret = readl_poll_timeout(ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST, + val, !(val & XGMAC_STARTBUSY), 1, 10000); + if (ret) + return ret; + + /* Write data */ + val = *((u32 *)&entry->val + i); + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_DATA); + + /* Write pos */ + val = real_pos & XGMAC_ADDR; + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST); + + /* Write OP */ + val |= XGMAC_WRRDN; + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST); + + /* Start Write */ + val |= XGMAC_STARTBUSY; + writel(val, ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST); + + /* Wait for done */ + ret = readl_poll_timeout(ioaddr + XGMAC_MTL_RXP_IACC_CTRL_ST, + val, !(val & XGMAC_STARTBUSY), 1, 10000); + if (ret) + return ret; + } + + return 0; +} + +static struct stmmac_tc_entry * +dwxgmac3_rxp_get_next_entry(struct stmmac_tc_entry *entries, + unsigned int count, u32 curr_prio) +{ + struct stmmac_tc_entry *entry; + u32 min_prio = ~0x0; + int i, min_prio_idx; + bool found = false; + + for (i = count - 1; i >= 0; i--) { + entry = &entries[i]; + + /* Do not update unused entries */ + if (!entry->in_use) + continue; + /* Do not update already updated entries (i.e. fragments) */ + if (entry->in_hw) + continue; + /* Let last entry be updated last */ + if (entry->is_last) + continue; + /* Do not return fragments */ + if (entry->is_frag) + continue; + /* Check if we already checked this prio */ + if (entry->prio < curr_prio) + continue; + /* Check if this is the minimum prio */ + if (entry->prio < min_prio) { + min_prio = entry->prio; + min_prio_idx = i; + found = true; + } + } + + if (found) + return &entries[min_prio_idx]; + return NULL; +} + +static int dwxgmac3_rxp_config(void __iomem *ioaddr, + struct stmmac_tc_entry *entries, + unsigned int count) +{ + struct stmmac_tc_entry *entry, *frag; + int i, ret, nve = 0; + u32 curr_prio = 0; + u32 old_val, val; + + /* Force disable RX */ + old_val = readl(ioaddr + XGMAC_RX_CONFIG); + val = old_val & ~XGMAC_CONFIG_RE; + writel(val, ioaddr + XGMAC_RX_CONFIG); + + /* Disable RX Parser */ + ret = dwxgmac3_rxp_disable(ioaddr); + if (ret) + goto re_enable; + + /* Set all entries as NOT in HW */ + for (i = 0; i < count; i++) { + entry = &entries[i]; + entry->in_hw = false; + } + + /* Update entries by reverse order */ + while (1) { + entry = dwxgmac3_rxp_get_next_entry(entries, count, curr_prio); + if (!entry) + break; + + curr_prio = entry->prio; + frag = entry->frag_ptr; + + /* Set special fragment requirements */ + if (frag) { + entry->val.af = 0; + entry->val.rf = 0; + entry->val.nc = 1; + entry->val.ok_index = nve + 2; + } + + ret = dwxgmac3_rxp_update_single_entry(ioaddr, entry, nve); + if (ret) + goto re_enable; + + entry->table_pos = nve++; + entry->in_hw = true; + + if (frag && !frag->in_hw) { + ret = dwxgmac3_rxp_update_single_entry(ioaddr, frag, nve); + if (ret) + goto re_enable; + frag->table_pos = nve++; + frag->in_hw = true; + } + } + + if (!nve) + goto re_enable; + + /* Update all pass entry */ + for (i = 0; i < count; i++) { + entry = &entries[i]; + if (!entry->is_last) + continue; + + ret = dwxgmac3_rxp_update_single_entry(ioaddr, entry, nve); + if (ret) + goto re_enable; + + entry->table_pos = nve++; + } + + /* Assume n. of parsable entries == n. of valid entries */ + val = (nve << 16) & XGMAC_NPE; + val |= nve & XGMAC_NVE; + writel(val, ioaddr + XGMAC_MTL_RXP_CONTROL_STATUS); + + /* Enable RX Parser */ + dwxgmac3_rxp_enable(ioaddr); + +re_enable: + /* Re-enable RX */ + writel(old_val, ioaddr + XGMAC_RX_CONFIG); + return ret; +} + +static int dwxgmac2_get_mac_tx_timestamp(struct mac_device_info *hw, u64 *ts) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + if (readl_poll_timeout_atomic(ioaddr + XGMAC_TIMESTAMP_STATUS, + value, value & XGMAC_TXTSC, 100, 10000)) + return -EBUSY; + + *ts = readl(ioaddr + XGMAC_TXTIMESTAMP_NSEC) & XGMAC_TXTSSTSLO; + *ts += readl(ioaddr + XGMAC_TXTIMESTAMP_SEC) * 1000000000ULL; + return 0; +} + +static int dwxgmac2_flex_pps_config(void __iomem *ioaddr, int index, + struct stmmac_pps_cfg *cfg, bool enable, + u32 sub_second_inc, u32 systime_flags) +{ + u32 tnsec = readl(ioaddr + XGMAC_PPSx_TARGET_TIME_NSEC(index)); + u32 val = readl(ioaddr + XGMAC_PPS_CONTROL); + u64 period; + + if (!cfg->available) + return -EINVAL; + if (tnsec & XGMAC_TRGTBUSY0) + return -EBUSY; + if (!sub_second_inc || !systime_flags) + return -EINVAL; + + val &= ~XGMAC_PPSx_MASK(index); + + if (!enable) { + val |= XGMAC_PPSCMDx(index, XGMAC_PPSCMD_STOP); + writel(val, ioaddr + XGMAC_PPS_CONTROL); + return 0; + } + + val |= XGMAC_PPSCMDx(index, XGMAC_PPSCMD_START); + val |= XGMAC_TRGTMODSELx(index, XGMAC_PPSCMD_START); + val |= XGMAC_PPSEN0; + + writel(cfg->start.tv_sec, ioaddr + XGMAC_PPSx_TARGET_TIME_SEC(index)); + + if (!(systime_flags & PTP_TCR_TSCTRLSSR)) + cfg->start.tv_nsec = (cfg->start.tv_nsec * 1000) / 465; + writel(cfg->start.tv_nsec, ioaddr + XGMAC_PPSx_TARGET_TIME_NSEC(index)); + + period = cfg->period.tv_sec * 1000000000; + period += cfg->period.tv_nsec; + + do_div(period, sub_second_inc); + + if (period <= 1) + return -EINVAL; + + writel(period - 1, ioaddr + XGMAC_PPSx_INTERVAL(index)); + + period >>= 1; + if (period <= 1) + return -EINVAL; + + writel(period - 1, ioaddr + XGMAC_PPSx_WIDTH(index)); + + /* Finally, activate it */ + writel(val, ioaddr + XGMAC_PPS_CONTROL); + return 0; +} + +static void dwxgmac2_sarc_configure(void __iomem *ioaddr, int val) +{ + u32 value = readl(ioaddr + XGMAC_TX_CONFIG); + + value &= ~XGMAC_CONFIG_SARC; + value |= val << XGMAC_CONFIG_SARC_SHIFT; + + writel(value, ioaddr + XGMAC_TX_CONFIG); +} + +static void dwxgmac2_enable_vlan(struct mac_device_info *hw, u32 type) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + value = readl(ioaddr + XGMAC_VLAN_INCL); + value |= XGMAC_VLAN_VLTI; + value |= XGMAC_VLAN_CSVL; /* Only use SVLAN */ + value &= ~XGMAC_VLAN_VLC; + value |= (type << XGMAC_VLAN_VLC_SHIFT) & XGMAC_VLAN_VLC; + writel(value, ioaddr + XGMAC_VLAN_INCL); +} + +static int dwxgmac2_filter_wait(struct mac_device_info *hw) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + if (readl_poll_timeout(ioaddr + XGMAC_L3L4_ADDR_CTRL, value, + !(value & XGMAC_XB), 100, 10000)) + return -EBUSY; + return 0; +} + +static int dwxgmac2_filter_read(struct mac_device_info *hw, u32 filter_no, + u8 reg, u32 *data) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + int ret; + + ret = dwxgmac2_filter_wait(hw); + if (ret) + return ret; + + value = ((filter_no << XGMAC_IDDR_FNUM) | reg) << XGMAC_IDDR_SHIFT; + value |= XGMAC_TT | XGMAC_XB; + writel(value, ioaddr + XGMAC_L3L4_ADDR_CTRL); + + ret = dwxgmac2_filter_wait(hw); + if (ret) + return ret; + + *data = readl(ioaddr + XGMAC_L3L4_DATA); + return 0; +} + +static int dwxgmac2_filter_write(struct mac_device_info *hw, u32 filter_no, + u8 reg, u32 data) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + int ret; + + ret = dwxgmac2_filter_wait(hw); + if (ret) + return ret; + + writel(data, ioaddr + XGMAC_L3L4_DATA); + + value = ((filter_no << XGMAC_IDDR_FNUM) | reg) << XGMAC_IDDR_SHIFT; + value |= XGMAC_XB; + writel(value, ioaddr + XGMAC_L3L4_ADDR_CTRL); + + return dwxgmac2_filter_wait(hw); +} + +static int dwxgmac2_config_l3_filter(struct mac_device_info *hw, u32 filter_no, + bool en, bool ipv6, bool sa, bool inv, + u32 match) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + int ret; + + value = readl(ioaddr + XGMAC_PACKET_FILTER); + value |= XGMAC_FILTER_IPFE; + writel(value, ioaddr + XGMAC_PACKET_FILTER); + + ret = dwxgmac2_filter_read(hw, filter_no, XGMAC_L3L4_CTRL, &value); + if (ret) + return ret; + + /* For IPv6 not both SA/DA filters can be active */ + if (ipv6) { + value |= XGMAC_L3PEN0; + value &= ~(XGMAC_L3SAM0 | XGMAC_L3SAIM0); + value &= ~(XGMAC_L3DAM0 | XGMAC_L3DAIM0); + if (sa) { + value |= XGMAC_L3SAM0; + if (inv) + value |= XGMAC_L3SAIM0; + } else { + value |= XGMAC_L3DAM0; + if (inv) + value |= XGMAC_L3DAIM0; + } + } else { + value &= ~XGMAC_L3PEN0; + if (sa) { + value |= XGMAC_L3SAM0; + if (inv) + value |= XGMAC_L3SAIM0; + } else { + value |= XGMAC_L3DAM0; + if (inv) + value |= XGMAC_L3DAIM0; + } + } + + ret = dwxgmac2_filter_write(hw, filter_no, XGMAC_L3L4_CTRL, value); + if (ret) + return ret; + + if (sa) { + ret = dwxgmac2_filter_write(hw, filter_no, XGMAC_L3_ADDR0, match); + if (ret) + return ret; + } else { + ret = dwxgmac2_filter_write(hw, filter_no, XGMAC_L3_ADDR1, match); + if (ret) + return ret; + } + + if (!en) + return dwxgmac2_filter_write(hw, filter_no, XGMAC_L3L4_CTRL, 0); + + return 0; +} + +static int dwxgmac2_config_l4_filter(struct mac_device_info *hw, u32 filter_no, + bool en, bool udp, bool sa, bool inv, + u32 match) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + int ret; + + value = readl(ioaddr + XGMAC_PACKET_FILTER); + value |= XGMAC_FILTER_IPFE; + writel(value, ioaddr + XGMAC_PACKET_FILTER); + + ret = dwxgmac2_filter_read(hw, filter_no, XGMAC_L3L4_CTRL, &value); + if (ret) + return ret; + + if (udp) { + value |= XGMAC_L4PEN0; + } else { + value &= ~XGMAC_L4PEN0; + } + + value &= ~(XGMAC_L4SPM0 | XGMAC_L4SPIM0); + value &= ~(XGMAC_L4DPM0 | XGMAC_L4DPIM0); + if (sa) { + value |= XGMAC_L4SPM0; + if (inv) + value |= XGMAC_L4SPIM0; + } else { + value |= XGMAC_L4DPM0; + if (inv) + value |= XGMAC_L4DPIM0; + } + + ret = dwxgmac2_filter_write(hw, filter_no, XGMAC_L3L4_CTRL, value); + if (ret) + return ret; + + if (sa) { + value = match & XGMAC_L4SP0; + + ret = dwxgmac2_filter_write(hw, filter_no, XGMAC_L4_ADDR, value); + if (ret) + return ret; + } else { + value = (match << XGMAC_L4DP0_SHIFT) & XGMAC_L4DP0; + + ret = dwxgmac2_filter_write(hw, filter_no, XGMAC_L4_ADDR, value); + if (ret) + return ret; + } + + if (!en) + return dwxgmac2_filter_write(hw, filter_no, XGMAC_L3L4_CTRL, 0); + + return 0; +} + +static void dwxgmac2_set_arp_offload(struct mac_device_info *hw, bool en, + u32 addr) +{ + void __iomem *ioaddr = hw->pcsr; + u32 value; + + writel(addr, ioaddr + XGMAC_ARP_ADDR); + + value = readl(ioaddr + XGMAC_RX_CONFIG); + if (en) + value |= XGMAC_CONFIG_ARPEN; + else + value &= ~XGMAC_CONFIG_ARPEN; + writel(value, ioaddr + XGMAC_RX_CONFIG); +} + const struct stmmac_ops dwxgmac210_ops = { .core_init = dwxgmac2_core_init, .set_mac = dwxgmac2_set_mac, .rx_ipc = dwxgmac2_rx_ipc, .rx_queue_enable = dwxgmac2_rx_queue_enable, .rx_queue_prio = dwxgmac2_rx_queue_prio, - .tx_queue_prio = NULL, + .tx_queue_prio = dwxgmac2_tx_queue_prio, .rx_queue_routing = NULL, .prog_mtl_rx_algorithms = dwxgmac2_prog_mtl_rx_algorithms, .prog_mtl_tx_algorithms = dwxgmac2_prog_mtl_tx_algorithms, - .set_mtl_tx_queue_weight = NULL, + .set_mtl_tx_queue_weight = dwxgmac2_set_mtl_tx_queue_weight, .map_mtl_to_dma = dwxgmac2_map_mtl_to_dma, .config_cbs = dwxgmac2_config_cbs, - .dump_regs = NULL, + .dump_regs = dwxgmac2_dump_regs, .host_irq_status = dwxgmac2_host_irq_status, .host_mtl_irq_status = dwxgmac2_host_mtl_irq_status, .flow_ctrl = dwxgmac2_flow_ctrl, .pmt = dwxgmac2_pmt, .set_umac_addr = dwxgmac2_set_umac_addr, .get_umac_addr = dwxgmac2_get_umac_addr, - .set_eee_mode = NULL, - .reset_eee_mode = NULL, - .set_eee_timer = NULL, - .set_eee_pls = NULL, + .set_eee_mode = dwxgmac2_set_eee_mode, + .reset_eee_mode = dwxgmac2_reset_eee_mode, + .set_eee_timer = dwxgmac2_set_eee_timer, + .set_eee_pls = dwxgmac2_set_eee_pls, .pcs_ctrl_ane = NULL, .pcs_rane = NULL, .pcs_get_adv_lp = NULL, .debug = NULL, .set_filter = dwxgmac2_set_filter, + .safety_feat_config = dwxgmac3_safety_feat_config, + .safety_feat_irq_status = dwxgmac3_safety_feat_irq_status, + .safety_feat_dump = dwxgmac3_safety_feat_dump, .set_mac_loopback = dwxgmac2_set_mac_loopback, + .rss_configure = dwxgmac2_rss_configure, + .update_vlan_hash = dwxgmac2_update_vlan_hash, + .rxp_config = dwxgmac3_rxp_config, + .get_mac_tx_timestamp = dwxgmac2_get_mac_tx_timestamp, + .flex_pps_config = dwxgmac2_flex_pps_config, + .sarc_configure = dwxgmac2_sarc_configure, + .enable_vlan = dwxgmac2_enable_vlan, + .config_l3_filter = dwxgmac2_config_l3_filter, + .config_l4_filter = dwxgmac2_config_l4_filter, + .set_arp_offload = dwxgmac2_set_arp_offload, }; int dwxgmac2_setup(struct stmmac_priv *priv) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c index c4c45402b8f8..ae48154f933c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_descs.c @@ -26,16 +26,17 @@ static int dwxgmac2_get_rx_status(void *data, struct stmmac_extra_stats *x, struct dma_desc *p) { unsigned int rdes3 = le32_to_cpu(p->des3); - int ret = good_frame; if (unlikely(rdes3 & XGMAC_RDES3_OWN)) return dma_own; + if (unlikely(rdes3 & XGMAC_RDES3_CTXT)) + return discard_frame; if (likely(!(rdes3 & XGMAC_RDES3_LD))) + return rx_not_ls; + if (unlikely((rdes3 & XGMAC_RDES3_ES) && (rdes3 & XGMAC_RDES3_LD))) return discard_frame; - if (unlikely(rdes3 & XGMAC_RDES3_ES)) - ret = discard_frame; - return ret; + return good_frame; } static int dwxgmac2_get_tx_len(struct dma_desc *p) @@ -55,7 +56,7 @@ static void dwxgmac2_set_tx_owner(struct dma_desc *p) static void dwxgmac2_set_rx_owner(struct dma_desc *p, int disable_rx_ic) { - p->des3 = cpu_to_le32(XGMAC_RDES3_OWN); + p->des3 |= cpu_to_le32(XGMAC_RDES3_OWN); if (!disable_rx_ic) p->des3 |= cpu_to_le32(XGMAC_RDES3_IOC); @@ -98,11 +99,17 @@ static int dwxgmac2_rx_check_timestamp(void *desc) unsigned int rdes3 = le32_to_cpu(p->des3); bool desc_valid, ts_valid; + dma_rmb(); + desc_valid = !(rdes3 & XGMAC_RDES3_OWN) && (rdes3 & XGMAC_RDES3_CTXT); ts_valid = !(rdes3 & XGMAC_RDES3_TSD) && (rdes3 & XGMAC_RDES3_TSA); - if (likely(desc_valid && ts_valid)) + if (likely(desc_valid && ts_valid)) { + if ((p->des0 == 0xffffffff) && (p->des1 == 0xffffffff)) + return -EINVAL; return 0; + } + return -EINVAL; } @@ -113,13 +120,10 @@ static int dwxgmac2_get_rx_timestamp_status(void *desc, void *next_desc, unsigned int rdes3 = le32_to_cpu(p->des3); int ret = -EBUSY; - if (likely(rdes3 & XGMAC_RDES3_CDA)) { + if (likely(rdes3 & XGMAC_RDES3_CDA)) ret = dwxgmac2_rx_check_timestamp(next_desc); - if (ret) - return ret; - } - return ret; + return !ret; } static void dwxgmac2_init_rx_desc(struct dma_desc *p, int disable_rx_ic, @@ -144,7 +148,7 @@ static void dwxgmac2_prepare_tx_desc(struct dma_desc *p, int is_fs, int len, p->des2 |= cpu_to_le32(len & XGMAC_TDES2_B1L); - tdes3 = tot_pkt_len & XGMAC_TDES3_FL; + tdes3 |= tot_pkt_len & XGMAC_TDES3_FL; if (is_fs) tdes3 |= XGMAC_TDES3_FD; else @@ -254,6 +258,86 @@ static void dwxgmac2_clear(struct dma_desc *p) p->des3 = 0; } +static int dwxgmac2_get_rx_hash(struct dma_desc *p, u32 *hash, + enum pkt_hash_types *type) +{ + unsigned int rdes3 = le32_to_cpu(p->des3); + u32 ptype; + + if (rdes3 & XGMAC_RDES3_RSV) { + ptype = (rdes3 & XGMAC_RDES3_L34T) >> XGMAC_RDES3_L34T_SHIFT; + + switch (ptype) { + case XGMAC_L34T_IP4TCP: + case XGMAC_L34T_IP4UDP: + case XGMAC_L34T_IP6TCP: + case XGMAC_L34T_IP6UDP: + *type = PKT_HASH_TYPE_L4; + break; + default: + *type = PKT_HASH_TYPE_L3; + break; + } + + *hash = le32_to_cpu(p->des1); + return 0; + } + + return -EINVAL; +} + +static int dwxgmac2_get_rx_header_len(struct dma_desc *p, unsigned int *len) +{ + *len = le32_to_cpu(p->des2) & XGMAC_RDES2_HL; + return 0; +} + +static void dwxgmac2_set_sec_addr(struct dma_desc *p, dma_addr_t addr) +{ + p->des2 = cpu_to_le32(lower_32_bits(addr)); + p->des3 = cpu_to_le32(upper_32_bits(addr)); +} + +static void dwxgmac2_set_sarc(struct dma_desc *p, u32 sarc_type) +{ + sarc_type <<= XGMAC_TDES3_SAIC_SHIFT; + + p->des3 |= cpu_to_le32(sarc_type & XGMAC_TDES3_SAIC); +} + +static void dwxgmac2_set_vlan_tag(struct dma_desc *p, u16 tag, u16 inner_tag, + u32 inner_type) +{ + p->des0 = 0; + p->des1 = 0; + p->des2 = 0; + p->des3 = 0; + + /* Inner VLAN */ + if (inner_type) { + u32 des = inner_tag << XGMAC_TDES2_IVT_SHIFT; + + des &= XGMAC_TDES2_IVT; + p->des2 = cpu_to_le32(des); + + des = inner_type << XGMAC_TDES3_IVTIR_SHIFT; + des &= XGMAC_TDES3_IVTIR; + p->des3 = cpu_to_le32(des | XGMAC_TDES3_IVLTV); + } + + /* Outer VLAN */ + p->des3 |= cpu_to_le32(tag & XGMAC_TDES3_VT); + p->des3 |= cpu_to_le32(XGMAC_TDES3_VLTV); + + p->des3 |= cpu_to_le32(XGMAC_TDES3_CTXT); +} + +static void dwxgmac2_set_vlan(struct dma_desc *p, u32 type) +{ + type <<= XGMAC_TDES2_VTIR_SHIFT; + p->des2 |= cpu_to_le32(type & XGMAC_TDES2_VTIR); +} + const struct stmmac_desc_ops dwxgmac210_desc_ops = { .tx_status = dwxgmac2_get_tx_status, .rx_status = dwxgmac2_get_rx_status, @@ -277,4 +361,10 @@ const struct stmmac_desc_ops dwxgmac210_desc_ops = { .get_addr = dwxgmac2_get_addr, .set_addr = dwxgmac2_set_addr, .clear = dwxgmac2_clear, + .get_rx_hash = dwxgmac2_get_rx_hash, + .get_rx_header_len = dwxgmac2_get_rx_header_len, + .set_sec_addr = dwxgmac2_set_sec_addr, + .set_sarc = dwxgmac2_set_sarc, + .set_vlan_tag = dwxgmac2_set_vlan_tag, + .set_vlan = dwxgmac2_set_vlan, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c index a4f236e3593e..53c4a40d8386 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_dma.c @@ -128,6 +128,14 @@ static void dwxgmac2_dma_axi(void __iomem *ioaddr, struct stmmac_axi *axi) writel(XGMAC_RDPS, ioaddr + XGMAC_RX_EDMA_CTRL); } +static void dwxgmac2_dma_dump_regs(void __iomem *ioaddr, u32 *reg_space) +{ + int i; + + for (i = (XGMAC_DMA_MODE / 4); i < XGMAC_REGSIZE; i++) + reg_space[i] = readl(ioaddr + i * 4); +} + static void dwxgmac2_dma_rx_mode(void __iomem *ioaddr, int mode, u32 channel, int fifosz, u8 qmode) { @@ -314,6 +322,10 @@ static int dwxgmac2_dma_interrupt(void __iomem *ioaddr, /* ABNORMAL interrupts */ if (unlikely(intr_status & XGMAC_AIS)) { + if (unlikely(intr_status & XGMAC_RBU)) { + x->rx_buf_unav_irq++; + ret |= handle_rx; + } if (unlikely(intr_status & XGMAC_TPS)) { x->tx_process_stopped_irq++; ret |= tx_hard_error; @@ -351,18 +363,26 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, /* MAC HW feature 0 */ hw_cap = readl(ioaddr + XGMAC_HW_FEATURE0); + dma_cap->vlins = (hw_cap & XGMAC_HWFEAT_SAVLANINS) >> 27; dma_cap->rx_coe = (hw_cap & XGMAC_HWFEAT_RXCOESEL) >> 16; dma_cap->tx_coe = (hw_cap & XGMAC_HWFEAT_TXCOESEL) >> 14; + dma_cap->eee = (hw_cap & XGMAC_HWFEAT_EEESEL) >> 13; dma_cap->atime_stamp = (hw_cap & XGMAC_HWFEAT_TSSEL) >> 12; dma_cap->av = (hw_cap & XGMAC_HWFEAT_AVSEL) >> 11; - dma_cap->av &= (hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10; + dma_cap->av &= !(hw_cap & XGMAC_HWFEAT_RAVSEL) >> 10; + dma_cap->arpoffsel = (hw_cap & XGMAC_HWFEAT_ARPOFFSEL) >> 9; + dma_cap->rmon = (hw_cap & XGMAC_HWFEAT_MMCSEL) >> 8; dma_cap->pmt_magic_frame = (hw_cap & XGMAC_HWFEAT_MGKSEL) >> 7; dma_cap->pmt_remote_wake_up = (hw_cap & XGMAC_HWFEAT_RWKSEL) >> 6; + dma_cap->vlhash = (hw_cap & XGMAC_HWFEAT_VLHASH) >> 4; dma_cap->mbps_1000 = (hw_cap & XGMAC_HWFEAT_GMIISEL) >> 1; /* MAC HW feature 1 */ hw_cap = readl(ioaddr + XGMAC_HW_FEATURE1); + dma_cap->l3l4fnum = (hw_cap & XGMAC_HWFEAT_L3L4FNUM) >> 27; + dma_cap->rssen = (hw_cap & XGMAC_HWFEAT_RSSEN) >> 20; dma_cap->tsoen = (hw_cap & XGMAC_HWFEAT_TSOEN) >> 18; + dma_cap->sphen = (hw_cap & XGMAC_HWFEAT_SPHEN) >> 17; dma_cap->addr64 = (hw_cap & XGMAC_HWFEAT_ADDR64) >> 14; switch (dma_cap->addr64) { @@ -396,6 +416,14 @@ static void dwxgmac2_get_hw_feature(void __iomem *ioaddr, ((hw_cap & XGMAC_HWFEAT_TXQCNT) >> 6) + 1; dma_cap->number_rx_queues = ((hw_cap & XGMAC_HWFEAT_RXQCNT) >> 0) + 1; + + /* MAC HW feature 3 */ + hw_cap = readl(ioaddr + XGMAC_HW_FEATURE3); + dma_cap->asp = (hw_cap & XGMAC_HWFEAT_ASP) >> 14; + dma_cap->dvlan = (hw_cap & XGMAC_HWFEAT_DVLAN) >> 13; + dma_cap->frpes = (hw_cap & XGMAC_HWFEAT_FRPES) >> 11; + dma_cap->frpbs = (hw_cap & XGMAC_HWFEAT_FRPPB) >> 9; + dma_cap->frpsel = (hw_cap & XGMAC_HWFEAT_FRPSEL) >> 3; } static void dwxgmac2_rx_watchdog(void __iomem *ioaddr, u32 riwt, u32 nchan) @@ -462,6 +490,22 @@ static void dwxgmac2_set_bfsize(void __iomem *ioaddr, int bfsize, u32 chan) writel(value, ioaddr + XGMAC_DMA_CH_RX_CONTROL(chan)); } +static void dwxgmac2_enable_sph(void __iomem *ioaddr, bool en, u32 chan) +{ + u32 value = readl(ioaddr + XGMAC_RX_CONFIG); + + value &= ~XGMAC_CONFIG_HDSMS; + value |= XGMAC_CONFIG_HDSMS_256; /* Segment max 256 bytes */ + writel(value, ioaddr + XGMAC_RX_CONFIG); + + value = readl(ioaddr + XGMAC_DMA_CH_CONTROL(chan)); + if (en) + value |= XGMAC_SPH; + else + value &= ~XGMAC_SPH; + writel(value, ioaddr + XGMAC_DMA_CH_CONTROL(chan)); +} + const struct stmmac_dma_ops dwxgmac210_dma_ops = { .reset = dwxgmac2_dma_reset, .init = dwxgmac2_dma_init, @@ -469,7 +513,7 @@ const struct stmmac_dma_ops dwxgmac210_dma_ops = { .init_rx_chan = dwxgmac2_dma_init_rx_chan, .init_tx_chan = dwxgmac2_dma_init_tx_chan, .axi = dwxgmac2_dma_axi, - .dump_regs = NULL, + .dump_regs = dwxgmac2_dma_dump_regs, .dma_rx_mode = dwxgmac2_dma_rx_mode, .dma_tx_mode = dwxgmac2_dma_tx_mode, .enable_dma_irq = dwxgmac2_enable_dma_irq, @@ -488,4 +532,5 @@ const struct stmmac_dma_ops dwxgmac210_dma_ops = { .enable_tso = dwxgmac2_enable_tso, .qmode = dwxgmac2_qmode, .set_bfsize = dwxgmac2_set_bfsize, + .enable_sph = dwxgmac2_enable_sph, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index 6c61b753b55e..3af2e5015245 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -201,7 +201,7 @@ static const struct stmmac_hwif_entry { .min_id = DWXGMAC_CORE_2_10, .regs = { .ptp_off = PTP_XGMAC_OFFSET, - .mmc_off = 0, + .mmc_off = MMC_XGMAC_OFFSET, }, .desc = &dwxgmac210_desc_ops, .dma = &dwxgmac210_dma_ops, @@ -209,7 +209,7 @@ static const struct stmmac_hwif_entry { .hwtimestamp = &stmmac_ptp, .mode = NULL, .tc = &dwmac510_tc_ops, - .mmc = NULL, + .mmc = &dwxgmac_mmc_ops, .setup = dwxgmac2_setup, .quirks = NULL, }, diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h index 278c0dbec9d9..ddb851d99618 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.h +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -86,6 +86,15 @@ struct stmmac_desc_ops { void (*set_addr)(struct dma_desc *p, dma_addr_t addr); /* clear descriptor */ void (*clear)(struct dma_desc *p); + /* RSS */ + int (*get_rx_hash)(struct dma_desc *p, u32 *hash, + enum pkt_hash_types *type); + int (*get_rx_header_len)(struct dma_desc *p, unsigned int *len); + void (*set_sec_addr)(struct dma_desc *p, dma_addr_t addr); + void (*set_sarc)(struct dma_desc *p, u32 sarc_type); + void (*set_vlan_tag)(struct dma_desc *p, u16 tag, u16 inner_tag, + u32 inner_type); + void (*set_vlan)(struct dma_desc *p, u32 type); }; #define stmmac_init_rx_desc(__priv, __args...) \ @@ -136,6 +145,18 @@ struct stmmac_desc_ops { stmmac_do_void_callback(__priv, desc, set_addr, __args) #define stmmac_clear_desc(__priv, __args...) \ stmmac_do_void_callback(__priv, desc, clear, __args) +#define stmmac_get_rx_hash(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_rx_hash, __args) +#define stmmac_get_rx_header_len(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_rx_header_len, __args) +#define stmmac_set_desc_sec_addr(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_sec_addr, __args) +#define stmmac_set_desc_sarc(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_sarc, __args) +#define stmmac_set_desc_vlan_tag(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_vlan_tag, __args) +#define stmmac_set_desc_vlan(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_vlan, __args) struct stmmac_dma_cfg; struct dma_features; @@ -186,6 +207,7 @@ struct stmmac_dma_ops { void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan); void (*qmode)(void __iomem *ioaddr, u32 channel, u8 qmode); void (*set_bfsize)(void __iomem *ioaddr, int bfsize, u32 chan); + void (*enable_sph)(void __iomem *ioaddr, bool en, u32 chan); }; #define stmmac_reset(__priv, __args...) \ @@ -242,6 +264,8 @@ struct stmmac_dma_ops { stmmac_do_void_callback(__priv, dma, qmode, __args) #define stmmac_set_dma_bfsize(__priv, __args...) \ stmmac_do_void_callback(__priv, dma, set_bfsize, __args) +#define stmmac_enable_sph(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, enable_sph, __args) struct mac_device_info; struct net_device; @@ -249,6 +273,7 @@ struct rgmii_adv; struct stmmac_safety_stats; struct stmmac_tc_entry; struct stmmac_pps_cfg; +struct stmmac_rss; /* Helpers to program the MAC core */ struct stmmac_ops { @@ -327,6 +352,25 @@ struct stmmac_ops { u32 sub_second_inc, u32 systime_flags); /* Loopback for selftests */ void (*set_mac_loopback)(void __iomem *ioaddr, bool enable); + /* RSS */ + int (*rss_configure)(struct mac_device_info *hw, + struct stmmac_rss *cfg, u32 num_rxq); + /* VLAN */ + void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash, + bool is_double); + void (*enable_vlan)(struct mac_device_info *hw, u32 type); + /* TX Timestamp */ + int (*get_mac_tx_timestamp)(struct mac_device_info *hw, u64 *ts); + /* Source Address Insertion / Replacement */ + void (*sarc_configure)(void __iomem *ioaddr, int val); + /* Filtering */ + int (*config_l3_filter)(struct mac_device_info *hw, u32 filter_no, + bool en, bool ipv6, bool sa, bool inv, + u32 match); + int (*config_l4_filter)(struct mac_device_info *hw, u32 filter_no, + bool en, bool udp, bool sa, bool inv, + u32 match); + void (*set_arp_offload)(struct mac_device_info *hw, bool en, u32 addr); }; #define stmmac_core_init(__priv, __args...) \ @@ -397,6 +441,22 @@ struct stmmac_ops { stmmac_do_callback(__priv, mac, flex_pps_config, __args) #define stmmac_set_mac_loopback(__priv, __args...) \ stmmac_do_void_callback(__priv, mac, set_mac_loopback, __args) +#define stmmac_rss_configure(__priv, __args...) \ + stmmac_do_callback(__priv, mac, rss_configure, __args) +#define stmmac_update_vlan_hash(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, update_vlan_hash, __args) +#define stmmac_enable_vlan(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, enable_vlan, __args) +#define stmmac_get_mac_tx_timestamp(__priv, __args...) \ + stmmac_do_callback(__priv, mac, get_mac_tx_timestamp, __args) +#define stmmac_sarc_configure(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, sarc_configure, __args) +#define stmmac_config_l3_filter(__priv, __args...) \ + stmmac_do_callback(__priv, mac, config_l3_filter, __args) +#define stmmac_config_l4_filter(__priv, __args...) \ + stmmac_do_callback(__priv, mac, config_l4_filter, __args) +#define stmmac_set_arp_offload(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, set_arp_offload, __args) /* PTP and HW Timer helpers */ struct stmmac_hwtimestamp { @@ -453,6 +513,7 @@ struct stmmac_mode_ops { struct stmmac_priv; struct tc_cls_u32_offload; struct tc_cbs_qopt_offload; +struct flow_cls_offload; struct stmmac_tc_ops { int (*init)(struct stmmac_priv *priv); @@ -460,6 +521,8 @@ struct stmmac_tc_ops { struct tc_cls_u32_offload *cls); int (*setup_cbs)(struct stmmac_priv *priv, struct tc_cbs_qopt_offload *qopt); + int (*setup_cls)(struct stmmac_priv *priv, + struct flow_cls_offload *cls); }; #define stmmac_tc_init(__priv, __args...) \ @@ -468,6 +531,8 @@ struct stmmac_tc_ops { stmmac_do_callback(__priv, tc, setup_cls_u32, __args) #define stmmac_tc_setup_cbs(__priv, __args...) \ stmmac_do_callback(__priv, tc, setup_cbs, __args) +#define stmmac_tc_setup_cls(__priv, __args...) \ + stmmac_do_callback(__priv, tc, setup_cls, __args) struct stmmac_counters; @@ -503,6 +568,7 @@ extern const struct stmmac_ops dwxgmac210_ops; extern const struct stmmac_dma_ops dwxgmac210_dma_ops; extern const struct stmmac_desc_ops dwxgmac210_desc_ops; extern const struct stmmac_mmc_ops dwmac_mmc_ops; +extern const struct stmmac_mmc_ops dwxgmac_mmc_ops; #define GMAC_VERSION 0x00000020 /* GMAC CORE Version */ #define GMAC4_VERSION 0x00000110 /* GMAC4+ CORE Version */ diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc.h b/drivers/net/ethernet/stmicro/stmmac/mmc.h index 3587ceb9faf5..a0c05925883e 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc.h +++ b/drivers/net/ethernet/stmicro/stmmac/mmc.h @@ -24,6 +24,7 @@ #define MMC_GMAC4_OFFSET 0x700 #define MMC_GMAC3_X_OFFSET 0x100 +#define MMC_XGMAC_OFFSET 0x800 struct stmmac_counters { unsigned int mmc_tx_octetcount_gb; @@ -116,6 +117,14 @@ struct stmmac_counters { unsigned int mmc_rx_tcp_err_octets; unsigned int mmc_rx_icmp_gd_octets; unsigned int mmc_rx_icmp_err_octets; + + /* FPE */ + unsigned int mmc_tx_fpe_fragment_cntr; + unsigned int mmc_tx_hold_req_cntr; + unsigned int mmc_rx_packet_assembly_err_cntr; + unsigned int mmc_rx_packet_smd_err_cntr; + unsigned int mmc_rx_packet_assembly_ok_cntr; + unsigned int mmc_rx_fpe_fragment_cntr; }; #endif /* __MMC_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c index a471db6d7b11..a223584f5f9a 100644 --- a/drivers/net/ethernet/stmicro/stmmac/mmc_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/mmc_core.c @@ -119,6 +119,64 @@ #define MMC_RX_ICMP_GD_OCTETS 0x180 #define MMC_RX_ICMP_ERR_OCTETS 0x184 +/* XGMAC MMC Registers */ +#define MMC_XGMAC_TX_OCTET_GB 0x14 +#define MMC_XGMAC_TX_PKT_GB 0x1c +#define MMC_XGMAC_TX_BROAD_PKT_G 0x24 +#define MMC_XGMAC_TX_MULTI_PKT_G 0x2c +#define MMC_XGMAC_TX_64OCT_GB 0x34 +#define MMC_XGMAC_TX_65OCT_GB 0x3c +#define MMC_XGMAC_TX_128OCT_GB 0x44 +#define MMC_XGMAC_TX_256OCT_GB 0x4c +#define MMC_XGMAC_TX_512OCT_GB 0x54 +#define MMC_XGMAC_TX_1024OCT_GB 0x5c +#define MMC_XGMAC_TX_UNI_PKT_GB 0x64 +#define MMC_XGMAC_TX_MULTI_PKT_GB 0x6c +#define MMC_XGMAC_TX_BROAD_PKT_GB 0x74 +#define MMC_XGMAC_TX_UNDER 0x7c +#define MMC_XGMAC_TX_OCTET_G 0x84 +#define MMC_XGMAC_TX_PKT_G 0x8c +#define MMC_XGMAC_TX_PAUSE 0x94 +#define MMC_XGMAC_TX_VLAN_PKT_G 0x9c +#define MMC_XGMAC_TX_LPI_USEC 0xa4 +#define MMC_XGMAC_TX_LPI_TRAN 0xa8 + +#define MMC_XGMAC_RX_PKT_GB 0x100 +#define MMC_XGMAC_RX_OCTET_GB 0x108 +#define MMC_XGMAC_RX_OCTET_G 0x110 +#define MMC_XGMAC_RX_BROAD_PKT_G 0x118 +#define MMC_XGMAC_RX_MULTI_PKT_G 0x120 +#define MMC_XGMAC_RX_CRC_ERR 0x128 +#define MMC_XGMAC_RX_RUNT_ERR 0x130 +#define MMC_XGMAC_RX_JABBER_ERR 0x134 +#define MMC_XGMAC_RX_UNDER 0x138 +#define MMC_XGMAC_RX_OVER 0x13c +#define MMC_XGMAC_RX_64OCT_GB 0x140 +#define MMC_XGMAC_RX_65OCT_GB 0x148 +#define MMC_XGMAC_RX_128OCT_GB 0x150 +#define MMC_XGMAC_RX_256OCT_GB 0x158 +#define MMC_XGMAC_RX_512OCT_GB 0x160 +#define MMC_XGMAC_RX_1024OCT_GB 0x168 +#define MMC_XGMAC_RX_UNI_PKT_G 0x170 +#define MMC_XGMAC_RX_LENGTH_ERR 0x178 +#define MMC_XGMAC_RX_RANGE 0x180 +#define MMC_XGMAC_RX_PAUSE 0x188 +#define MMC_XGMAC_RX_FIFOOVER_PKT 0x190 +#define MMC_XGMAC_RX_VLAN_PKT_GB 0x198 +#define MMC_XGMAC_RX_WATCHDOG_ERR 0x1a0 +#define MMC_XGMAC_RX_LPI_USEC 0x1a4 +#define MMC_XGMAC_RX_LPI_TRAN 0x1a8 +#define MMC_XGMAC_RX_DISCARD_PKT_GB 0x1ac +#define MMC_XGMAC_RX_DISCARD_OCT_GB 0x1b4 +#define MMC_XGMAC_RX_ALIGN_ERR_PKT 0x1bc + +#define MMC_XGMAC_TX_FPE_FRAG 0x208 +#define MMC_XGMAC_TX_HOLD_REQ 0x20c +#define MMC_XGMAC_RX_PKT_ASSEMBLY_ERR 0x228 +#define MMC_XGMAC_RX_PKT_SMD_ERR 0x22c +#define MMC_XGMAC_RX_PKT_ASSEMBLY_OK 0x230 +#define MMC_XGMAC_RX_FPE_FRAG 0x234 + static void dwmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode) { u32 value = readl(mmcaddr + MMC_CNTRL); @@ -263,3 +321,137 @@ const struct stmmac_mmc_ops dwmac_mmc_ops = { .intr_all_mask = dwmac_mmc_intr_all_mask, .read = dwmac_mmc_read, }; + +static void dwxgmac_mmc_ctrl(void __iomem *mmcaddr, unsigned int mode) +{ + u32 value = readl(mmcaddr + MMC_CNTRL); + + value |= (mode & 0x3F); + + writel(value, mmcaddr + MMC_CNTRL); +} + +static void dwxgmac_mmc_intr_all_mask(void __iomem *mmcaddr) +{ + writel(MMC_DEFAULT_MASK, mmcaddr + MMC_RX_INTR_MASK); + writel(MMC_DEFAULT_MASK, mmcaddr + MMC_TX_INTR_MASK); +} + +static void dwxgmac_read_mmc_reg(void __iomem *addr, u32 reg, u32 *dest) +{ + u64 tmp = 0; + + tmp += readl(addr + reg); + tmp += ((u64 )readl(addr + reg + 0x4)) << 32; + if (tmp > GENMASK(31, 0)) + *dest = ~0x0; + else + *dest = *dest + tmp; +} + +/* This reads the MAC core counters (if actaully supported). + * by default the MMC core is programmed to reset each + * counter after a read. So all the field of the mmc struct + * have to be incremented. + */ +static void dwxgmac_mmc_read(void __iomem *mmcaddr, struct stmmac_counters *mmc) +{ + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_OCTET_GB, + &mmc->mmc_tx_octetcount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_PKT_GB, + &mmc->mmc_tx_framecount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_BROAD_PKT_G, + &mmc->mmc_tx_broadcastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_MULTI_PKT_G, + &mmc->mmc_tx_multicastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_64OCT_GB, + &mmc->mmc_tx_64_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_65OCT_GB, + &mmc->mmc_tx_65_to_127_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_128OCT_GB, + &mmc->mmc_tx_128_to_255_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_256OCT_GB, + &mmc->mmc_tx_256_to_511_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_512OCT_GB, + &mmc->mmc_tx_512_to_1023_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_1024OCT_GB, + &mmc->mmc_tx_1024_to_max_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_UNI_PKT_GB, + &mmc->mmc_tx_unicast_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_MULTI_PKT_GB, + &mmc->mmc_tx_multicast_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_BROAD_PKT_GB, + &mmc->mmc_tx_broadcast_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_UNDER, + &mmc->mmc_tx_underflow_error); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_OCTET_G, + &mmc->mmc_tx_octetcount_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_PKT_G, + &mmc->mmc_tx_framecount_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_PAUSE, + &mmc->mmc_tx_pause_frame); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_TX_VLAN_PKT_G, + &mmc->mmc_tx_vlan_frame_g); + + /* MMC RX counter registers */ + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_PKT_GB, + &mmc->mmc_rx_framecount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_OCTET_GB, + &mmc->mmc_rx_octetcount_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_OCTET_G, + &mmc->mmc_rx_octetcount_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_BROAD_PKT_G, + &mmc->mmc_rx_broadcastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_MULTI_PKT_G, + &mmc->mmc_rx_multicastframe_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_CRC_ERR, + &mmc->mmc_rx_crc_error); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_CRC_ERR, + &mmc->mmc_rx_crc_error); + mmc->mmc_rx_run_error += readl(mmcaddr + MMC_XGMAC_RX_RUNT_ERR); + mmc->mmc_rx_jabber_error += readl(mmcaddr + MMC_XGMAC_RX_JABBER_ERR); + mmc->mmc_rx_undersize_g += readl(mmcaddr + MMC_XGMAC_RX_UNDER); + mmc->mmc_rx_oversize_g += readl(mmcaddr + MMC_XGMAC_RX_OVER); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_64OCT_GB, + &mmc->mmc_rx_64_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_65OCT_GB, + &mmc->mmc_rx_65_to_127_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_128OCT_GB, + &mmc->mmc_rx_128_to_255_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_256OCT_GB, + &mmc->mmc_rx_256_to_511_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_512OCT_GB, + &mmc->mmc_rx_512_to_1023_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_1024OCT_GB, + &mmc->mmc_rx_1024_to_max_octets_gb); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_UNI_PKT_G, + &mmc->mmc_rx_unicast_g); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_LENGTH_ERR, + &mmc->mmc_rx_length_error); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_RANGE, + &mmc->mmc_rx_autofrangetype); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_PAUSE, + &mmc->mmc_rx_pause_frames); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_FIFOOVER_PKT, + &mmc->mmc_rx_fifo_overflow); + dwxgmac_read_mmc_reg(mmcaddr, MMC_XGMAC_RX_VLAN_PKT_GB, + &mmc->mmc_rx_vlan_frames_gb); + mmc->mmc_rx_watchdog_error += readl(mmcaddr + MMC_XGMAC_RX_WATCHDOG_ERR); + + mmc->mmc_tx_fpe_fragment_cntr += readl(mmcaddr + MMC_XGMAC_TX_FPE_FRAG); + mmc->mmc_tx_hold_req_cntr += readl(mmcaddr + MMC_XGMAC_TX_HOLD_REQ); + mmc->mmc_rx_packet_assembly_err_cntr += + readl(mmcaddr + MMC_XGMAC_RX_PKT_ASSEMBLY_ERR); + mmc->mmc_rx_packet_smd_err_cntr += + readl(mmcaddr + MMC_XGMAC_RX_PKT_SMD_ERR); + mmc->mmc_rx_packet_assembly_ok_cntr += + readl(mmcaddr + MMC_XGMAC_RX_PKT_ASSEMBLY_OK); + mmc->mmc_rx_fpe_fragment_cntr += + readl(mmcaddr + MMC_XGMAC_RX_FPE_FRAG); +} + +const struct stmmac_mmc_ops dwxgmac_mmc_ops = { + .ctrl = dwxgmac_mmc_ctrl, + .intr_all_mask = dwxgmac_mmc_intr_all_mask, + .read = dwxgmac_mmc_read, +}; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index 5cd966c154f3..d993fc7e82c3 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -13,6 +13,7 @@ #define DRV_MODULE_VERSION "Jan_2016" #include <linux/clk.h> +#include <linux/if_vlan.h> #include <linux/stmmac.h> #include <linux/phylink.h> #include <linux/pci.h> @@ -57,7 +58,9 @@ struct stmmac_tx_queue { struct stmmac_rx_buffer { struct page *page; + struct page *sec_page; dma_addr_t addr; + dma_addr_t sec_addr; }; struct stmmac_rx_queue { @@ -73,6 +76,12 @@ struct stmmac_rx_queue { u32 rx_zeroc_thresh; dma_addr_t dma_rx_phy; u32 rx_tail_addr; + unsigned int state_saved; + struct { + struct sk_buff *skb; + unsigned int len; + unsigned int error; + } state; }; struct stmmac_channel { @@ -113,6 +122,22 @@ struct stmmac_pps_cfg { struct timespec64 period; }; +struct stmmac_rss { + int enable; + u8 key[STMMAC_RSS_HASH_KEY_SIZE]; + u32 table[STMMAC_RSS_MAX_TABLE_SIZE]; +}; + +#define STMMAC_FLOW_ACTION_DROP BIT(0) +struct stmmac_flow_entry { + unsigned long cookie; + unsigned long action; + u8 ip_proto; + int in_use; + int idx; + int is_l4; +}; + struct stmmac_priv { /* Frequently used values are kept adjacent for cache effect */ u32 tx_coal_frames; @@ -123,6 +148,8 @@ struct stmmac_priv { int hwts_tx_en; bool tx_path_in_lpi_mode; bool tso; + int sph; + u32 sarc_type; unsigned int dma_buf_sz; unsigned int rx_copybreak; @@ -185,11 +212,10 @@ struct stmmac_priv { spinlock_t ptp_lock; void __iomem *mmcaddr; void __iomem *ptpaddr; + unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; #ifdef CONFIG_DEBUG_FS struct dentry *dbgfs_dir; - struct dentry *dbgfs_rings_status; - struct dentry *dbgfs_dma_cap; #endif unsigned long state; @@ -200,9 +226,14 @@ struct stmmac_priv { unsigned int tc_entries_max; unsigned int tc_off_max; struct stmmac_tc_entry *tc_entries; + unsigned int flow_entries_max; + struct stmmac_flow_entry *flow_entries; /* Pulse Per Second output */ struct stmmac_pps_cfg pps[STMMAC_PPS_MAX]; + + /* Receive Side Scaling */ + struct stmmac_rss rss; }; enum stmmac_state { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 6efb66820d4c..1a768837ca72 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -18,10 +18,12 @@ #include "stmmac.h" #include "dwmac_dma.h" +#include "dwxgmac2.h" #define REG_SPACE_SIZE 0x1060 #define MAC100_ETHTOOL_NAME "st_mac100" #define GMAC_ETHTOOL_NAME "st_gmac" +#define XGMAC_ETHTOOL_NAME "st_xgmac" #define ETHTOOL_DMA_OFFSET 55 @@ -65,6 +67,7 @@ static const struct stmmac_stats stmmac_gstrings_stats[] = { STMMAC_STAT(rx_missed_cntr), STMMAC_STAT(rx_overflow_cntr), STMMAC_STAT(rx_vlan), + STMMAC_STAT(rx_split_hdr_pkt_n), /* Tx/Rx IRQ error info */ STMMAC_STAT(tx_undeflow_irq), STMMAC_STAT(tx_process_stopped_irq), @@ -243,6 +246,12 @@ static const struct stmmac_stats stmmac_mmc[] = { STMMAC_MMC_STAT(mmc_rx_tcp_err_octets), STMMAC_MMC_STAT(mmc_rx_icmp_gd_octets), STMMAC_MMC_STAT(mmc_rx_icmp_err_octets), + STMMAC_MMC_STAT(mmc_tx_fpe_fragment_cntr), + STMMAC_MMC_STAT(mmc_tx_hold_req_cntr), + STMMAC_MMC_STAT(mmc_rx_packet_assembly_err_cntr), + STMMAC_MMC_STAT(mmc_rx_packet_smd_err_cntr), + STMMAC_MMC_STAT(mmc_rx_packet_assembly_ok_cntr), + STMMAC_MMC_STAT(mmc_rx_fpe_fragment_cntr), }; #define STMMAC_MMC_STATS_LEN ARRAY_SIZE(stmmac_mmc) @@ -253,6 +262,8 @@ static void stmmac_ethtool_getdrvinfo(struct net_device *dev, if (priv->plat->has_gmac || priv->plat->has_gmac4) strlcpy(info->driver, GMAC_ETHTOOL_NAME, sizeof(info->driver)); + else if (priv->plat->has_xgmac) + strlcpy(info->driver, XGMAC_ETHTOOL_NAME, sizeof(info->driver)); else strlcpy(info->driver, MAC100_ETHTOOL_NAME, sizeof(info->driver)); @@ -398,23 +409,28 @@ static int stmmac_check_if_running(struct net_device *dev) static int stmmac_ethtool_get_regs_len(struct net_device *dev) { + struct stmmac_priv *priv = netdev_priv(dev); + + if (priv->plat->has_xgmac) + return XGMAC_REGSIZE * 4; return REG_SPACE_SIZE; } static void stmmac_ethtool_gregs(struct net_device *dev, struct ethtool_regs *regs, void *space) { - u32 *reg_space = (u32 *) space; - struct stmmac_priv *priv = netdev_priv(dev); - - memset(reg_space, 0x0, REG_SPACE_SIZE); + u32 *reg_space = (u32 *) space; stmmac_dump_mac_regs(priv, priv->hw, reg_space); stmmac_dump_dma_regs(priv, priv->ioaddr, reg_space); - /* Copy DMA registers to where ethtool expects them */ - memcpy(®_space[ETHTOOL_DMA_OFFSET], ®_space[DMA_BUS_MODE / 4], - NUM_DWMAC1000_DMA_REGS * 4); + + if (!priv->plat->has_xgmac) { + /* Copy DMA registers to where ethtool expects them */ + memcpy(®_space[ETHTOOL_DMA_OFFSET], + ®_space[DMA_BUS_MODE / 4], + NUM_DWMAC1000_DMA_REGS * 4); + } } static int stmmac_nway_reset(struct net_device *dev) @@ -730,8 +746,15 @@ static int stmmac_set_coalesce(struct net_device *dev, (ec->tx_max_coalesced_frames_high) || (ec->rate_sample_interval)) return -EOPNOTSUPP; - if (ec->rx_coalesce_usecs == 0) - return -EINVAL; + if (priv->use_riwt && (ec->rx_coalesce_usecs > 0)) { + rx_riwt = stmmac_usec2riwt(ec->rx_coalesce_usecs, priv); + + if ((rx_riwt > MAX_DMA_RIWT) || (rx_riwt < MIN_DMA_RIWT)) + return -EINVAL; + + priv->rx_riwt = rx_riwt; + stmmac_rx_watchdog(priv, priv->ioaddr, priv->rx_riwt, rx_cnt); + } if ((ec->tx_coalesce_usecs == 0) && (ec->tx_max_coalesced_frames == 0)) @@ -741,23 +764,83 @@ static int stmmac_set_coalesce(struct net_device *dev, (ec->tx_max_coalesced_frames > STMMAC_TX_MAX_FRAMES)) return -EINVAL; - rx_riwt = stmmac_usec2riwt(ec->rx_coalesce_usecs, priv); - - if ((rx_riwt > MAX_DMA_RIWT) || (rx_riwt < MIN_DMA_RIWT)) - return -EINVAL; - else if (!priv->use_riwt) - return -EOPNOTSUPP; - /* Only copy relevant parameters, ignore all others. */ priv->tx_coal_frames = ec->tx_max_coalesced_frames; priv->tx_coal_timer = ec->tx_coalesce_usecs; priv->rx_coal_frames = ec->rx_max_coalesced_frames; - priv->rx_riwt = rx_riwt; - stmmac_rx_watchdog(priv, priv->ioaddr, priv->rx_riwt, rx_cnt); + return 0; +} + +static int stmmac_get_rxnfc(struct net_device *dev, + struct ethtool_rxnfc *rxnfc, u32 *rule_locs) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + switch (rxnfc->cmd) { + case ETHTOOL_GRXRINGS: + rxnfc->data = priv->plat->rx_queues_to_use; + break; + default: + return -EOPNOTSUPP; + } + + return 0; +} + +static u32 stmmac_get_rxfh_key_size(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + return sizeof(priv->rss.key); +} + +static u32 stmmac_get_rxfh_indir_size(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + return ARRAY_SIZE(priv->rss.table); +} + +static int stmmac_get_rxfh(struct net_device *dev, u32 *indir, u8 *key, + u8 *hfunc) +{ + struct stmmac_priv *priv = netdev_priv(dev); + int i; + + if (indir) { + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + indir[i] = priv->rss.table[i]; + } + + if (key) + memcpy(key, priv->rss.key, sizeof(priv->rss.key)); + if (hfunc) + *hfunc = ETH_RSS_HASH_TOP; return 0; } +static int stmmac_set_rxfh(struct net_device *dev, const u32 *indir, + const u8 *key, const u8 hfunc) +{ + struct stmmac_priv *priv = netdev_priv(dev); + int i; + + if ((hfunc != ETH_RSS_HASH_NO_CHANGE) && (hfunc != ETH_RSS_HASH_TOP)) + return -EOPNOTSUPP; + + if (indir) { + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + priv->rss.table[i] = indir[i]; + } + + if (key) + memcpy(priv->rss.key, key, sizeof(priv->rss.key)); + + return stmmac_rss_configure(priv, priv->hw, &priv->rss, + priv->plat->rx_queues_to_use); +} + static int stmmac_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { @@ -849,6 +932,11 @@ static const struct ethtool_ops stmmac_ethtool_ops = { .get_eee = stmmac_ethtool_op_get_eee, .set_eee = stmmac_ethtool_op_set_eee, .get_sset_count = stmmac_get_sset_count, + .get_rxnfc = stmmac_get_rxnfc, + .get_rxfh_key_size = stmmac_get_rxfh_key_size, + .get_rxfh_indir_size = stmmac_get_rxfh_indir_size, + .get_rxfh = stmmac_get_rxfh, + .set_rxfh = stmmac_set_rxfh, .get_ts_info = stmmac_get_ts_info, .get_coalesce = stmmac_get_coalesce, .set_coalesce = stmmac_set_coalesce, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index fd54c7c87485..a6cb2aa60e64 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -105,7 +105,7 @@ MODULE_PARM_DESC(chain_mode, "To use chain instead of ring mode"); static irqreturn_t stmmac_interrupt(int irq, void *dev_id); #ifdef CONFIG_DEBUG_FS -static int stmmac_init_fs(struct net_device *dev); +static void stmmac_init_fs(struct net_device *dev); static void stmmac_exit_fs(struct net_device *dev); #endif @@ -432,6 +432,7 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, struct sk_buff *skb) { struct skb_shared_hwtstamps shhwtstamp; + bool found = false; u64 ns = 0; if (!priv->hwts_tx_en) @@ -443,9 +444,13 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, /* check tx tstamp status */ if (stmmac_get_tx_timestamp_status(priv, p)) { - /* get the valid tstamp */ stmmac_get_timestamp(priv, p, priv->adv_ts, &ns); + found = true; + } else if (!stmmac_get_mac_tx_timestamp(priv, priv->hw, &ns)) { + found = true; + } + if (found) { memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); shhwtstamp.hwtstamp = ns_to_ktime(ns); @@ -453,8 +458,6 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, /* pass tstamp to stack */ skb_tstamp_tx(skb, &shhwtstamp); } - - return; } /* stmmac_get_rx_hwtstamp - get HW RX timestamps @@ -828,15 +831,22 @@ static void stmmac_validate(struct phylink_config *config, phylink_set(mask, 1000baseT_Full); phylink_set(mask, 1000baseX_Full); } else if (priv->plat->has_xgmac) { - phylink_set(mac_supported, 2500baseT_Full); - phylink_set(mac_supported, 5000baseT_Full); - phylink_set(mac_supported, 10000baseSR_Full); - phylink_set(mac_supported, 10000baseLR_Full); - phylink_set(mac_supported, 10000baseER_Full); - phylink_set(mac_supported, 10000baseLRM_Full); - phylink_set(mac_supported, 10000baseT_Full); - phylink_set(mac_supported, 10000baseKX4_Full); - phylink_set(mac_supported, 10000baseKR_Full); + if (!max_speed || (max_speed >= 2500)) { + phylink_set(mac_supported, 2500baseT_Full); + phylink_set(mac_supported, 2500baseX_Full); + } + if (!max_speed || (max_speed >= 5000)) { + phylink_set(mac_supported, 5000baseT_Full); + } + if (!max_speed || (max_speed >= 10000)) { + phylink_set(mac_supported, 10000baseSR_Full); + phylink_set(mac_supported, 10000baseLR_Full); + phylink_set(mac_supported, 10000baseER_Full); + phylink_set(mac_supported, 10000baseLRM_Full); + phylink_set(mac_supported, 10000baseT_Full); + phylink_set(mac_supported, 10000baseKX4_Full); + phylink_set(mac_supported, 10000baseKR_Full); + } } /* Half-Duplex can only work with single queue */ @@ -1026,7 +1036,7 @@ static int stmmac_init_phy(struct net_device *dev) static int stmmac_phy_setup(struct stmmac_priv *priv) { struct fwnode_handle *fwnode = of_fwnode_handle(priv->plat->phylink_node); - int mode = priv->plat->interface; + int mode = priv->plat->phy_interface; struct phylink *phylink; priv->phylink_config.dev = &priv->dev->dev; @@ -1198,6 +1208,17 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, if (!buf->page) return -ENOMEM; + if (priv->sph) { + buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool); + if (!buf->sec_page) + return -ENOMEM; + + buf->sec_addr = page_pool_get_dma_addr(buf->sec_page); + stmmac_set_desc_sec_addr(priv, p, buf->sec_addr); + } else { + buf->sec_page = NULL; + } + buf->addr = page_pool_get_dma_addr(buf->page); stmmac_set_desc_addr(priv, p, buf->addr); if (priv->dma_buf_sz == BUF_SIZE_16KiB) @@ -1220,6 +1241,10 @@ static void stmmac_free_rx_buffer(struct stmmac_priv *priv, u32 queue, int i) if (buf->page) page_pool_put_page(rx_q->page_pool, buf->page, false); buf->page = NULL; + + if (buf->sec_page) + page_pool_put_page(rx_q->page_pool, buf->sec_page, false); + buf->sec_page = NULL; } /** @@ -2417,6 +2442,22 @@ static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv) } } +static void stmmac_mac_config_rss(struct stmmac_priv *priv) +{ + if (!priv->dma_cap.rssen || !priv->plat->rss_en) { + priv->rss.enable = false; + return; + } + + if (priv->dev->features & NETIF_F_RXHASH) + priv->rss.enable = true; + else + priv->rss.enable = false; + + stmmac_rss_configure(priv, priv->hw, &priv->rss, + priv->plat->rx_queues_to_use); +} + /** * stmmac_mtl_configuration - Configure MTL * @priv: driver private structure @@ -2461,6 +2502,10 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) /* Set RX routing */ if (rx_queues_count > 1) stmmac_mac_config_rx_queues_routing(priv); + + /* Receive Side Scaling */ + if (rx_queues_count > 1) + stmmac_mac_config_rss(priv); } static void stmmac_safety_feat_configuration(struct stmmac_priv *priv) @@ -2573,6 +2618,16 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) stmmac_enable_tso(priv, priv->ioaddr, 1, chan); } + /* Enable Split Header */ + if (priv->sph && priv->hw->rx_csum) { + for (chan = 0; chan < rx_cnt; chan++) + stmmac_enable_sph(priv, priv->ioaddr, 1, chan); + } + + /* VLAN Tag Insertion */ + if (priv->dma_cap.vlins) + stmmac_enable_vlan(priv, priv->hw, STMMAC_VLAN_INSERT); + /* Start the ball rolling... */ stmmac_start_all_dma(priv); @@ -2750,6 +2805,33 @@ static int stmmac_release(struct net_device *dev) return 0; } +static bool stmmac_vlan_insert(struct stmmac_priv *priv, struct sk_buff *skb, + struct stmmac_tx_queue *tx_q) +{ + u16 tag = 0x0, inner_tag = 0x0; + u32 inner_type = 0x0; + struct dma_desc *p; + + if (!priv->dma_cap.vlins) + return false; + if (!skb_vlan_tag_present(skb)) + return false; + if (skb->vlan_proto == htons(ETH_P_8021AD)) { + inner_tag = skb_vlan_tag_get(skb); + inner_type = STMMAC_VLAN_INSERT; + } + + tag = skb_vlan_tag_get(skb); + + p = tx_q->dma_tx + tx_q->cur_tx; + if (stmmac_set_desc_vlan_tag(priv, p, tag, inner_tag, inner_type)) + return false; + + stmmac_set_tx_owner(priv, p); + tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); + return true; +} + /** * stmmac_tso_allocator - close entry point of the driver * @priv: driver private structure @@ -2829,12 +2911,13 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) struct stmmac_priv *priv = netdev_priv(dev); int nfrags = skb_shinfo(skb)->nr_frags; u32 queue = skb_get_queue_mapping(skb); - unsigned int first_entry; struct stmmac_tx_queue *tx_q; + unsigned int first_entry; int tmp_pay_len = 0; u32 pay_len, mss; u8 proto_hdr_len; dma_addr_t des; + bool has_vlan; int i; tx_q = &priv->tx_queue[queue]; @@ -2876,12 +2959,18 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) skb->data_len); } + /* Check if VLAN can be inserted by HW */ + has_vlan = stmmac_vlan_insert(priv, skb, tx_q); + first_entry = tx_q->cur_tx; WARN_ON(tx_q->tx_skbuff[first_entry]); desc = tx_q->dma_tx + first_entry; first = desc; + if (has_vlan) + stmmac_set_desc_vlan(priv, first, STMMAC_VLAN_INSERT); + /* first descriptor: fill Headers on Buf1 */ des = dma_map_single(priv->device, skb->data, skb_headlen(skb), DMA_TO_DEVICE); @@ -2960,6 +3049,9 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) priv->xstats.tx_set_ic_bit++; } + if (priv->sarc_type) + stmmac_set_desc_sarc(priv, first, priv->sarc_type); + skb_tx_timestamp(skb); if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) && @@ -3038,6 +3130,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) unsigned int first_entry; unsigned int enh_desc; dma_addr_t des; + bool has_vlan; int entry; tx_q = &priv->tx_queue[queue]; @@ -3063,6 +3156,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) return NETDEV_TX_BUSY; } + /* Check if VLAN can be inserted by HW */ + has_vlan = stmmac_vlan_insert(priv, skb, tx_q); + entry = tx_q->cur_tx; first_entry = entry; WARN_ON(tx_q->tx_skbuff[first_entry]); @@ -3076,6 +3172,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) first = desc; + if (has_vlan) + stmmac_set_desc_vlan(priv, first, STMMAC_VLAN_INSERT); + enh_desc = priv->plat->enh_desc; /* To program the descriptors according to the size of the frame */ if (enh_desc) @@ -3173,6 +3272,9 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) priv->xstats.tx_set_ic_bit++; } + if (priv->sarc_type) + stmmac_set_desc_sarc(priv, first, priv->sarc_type); + skb_tx_timestamp(skb); /* Ready to fill the first descriptor and set the OWN bit w/o any @@ -3292,6 +3394,17 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) break; } + if (priv->sph && !buf->sec_page) { + buf->sec_page = page_pool_dev_alloc_pages(rx_q->page_pool); + if (!buf->sec_page) + break; + + buf->sec_addr = page_pool_get_dma_addr(buf->sec_page); + + dma_sync_single_for_device(priv->device, buf->sec_addr, + len, DMA_FROM_DEVICE); + } + buf->addr = page_pool_get_dma_addr(buf->page); /* Sync whole allocation to device. This will invalidate old @@ -3301,10 +3414,13 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) DMA_FROM_DEVICE); stmmac_set_desc_addr(priv, p, buf->addr); + stmmac_set_desc_sec_addr(priv, p, buf->sec_addr); stmmac_refill_desc3(priv, rx_q, p); rx_q->rx_count_frames++; - rx_q->rx_count_frames %= priv->rx_coal_frames; + rx_q->rx_count_frames += priv->rx_coal_frames; + if (rx_q->rx_count_frames > priv->rx_coal_frames) + rx_q->rx_count_frames = 0; use_rx_wd = priv->use_riwt && rx_q->rx_count_frames; dma_wmb(); @@ -3330,9 +3446,10 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) { struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; struct stmmac_channel *ch = &priv->channel[queue]; + unsigned int count = 0, error = 0, len = 0; + int status = 0, coe = priv->hw->rx_csum; unsigned int next_entry = rx_q->cur_rx; - int coe = priv->hw->rx_csum; - unsigned int count = 0; + struct sk_buff *skb = NULL; if (netif_msg_rx_status(priv)) { void *rx_head; @@ -3346,10 +3463,30 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) stmmac_display_ring(priv, rx_head, DMA_RX_SIZE, true); } while (count < limit) { + unsigned int hlen = 0, prev_len = 0; + enum pkt_hash_types hash_type; struct stmmac_rx_buffer *buf; struct dma_desc *np, *p; - int entry, status; + unsigned int sec_len; + int entry; + u32 hash; + + if (!count && rx_q->state_saved) { + skb = rx_q->state.skb; + error = rx_q->state.error; + len = rx_q->state.len; + } else { + rx_q->state_saved = false; + skb = NULL; + error = 0; + len = 0; + } + if (count >= limit) + break; + +read_again: + sec_len = 0; entry = next_entry; buf = &rx_q->buf_pool[entry]; @@ -3376,34 +3513,33 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) np = rx_q->dma_rx + next_entry; prefetch(np); + prefetch(page_address(buf->page)); if (priv->extend_desc) stmmac_rx_extended_status(priv, &priv->dev->stats, &priv->xstats, rx_q->dma_erx + entry); if (unlikely(status == discard_frame)) { page_pool_recycle_direct(rx_q->page_pool, buf->page); - priv->dev->stats.rx_errors++; buf->page = NULL; - } else { - struct sk_buff *skb; - int frame_len; - unsigned int des; + error = 1; + if (!priv->hwts_rx_en) + priv->dev->stats.rx_errors++; + } - stmmac_get_desc_addr(priv, p, &des); - frame_len = stmmac_get_rx_frame_len(priv, p, coe); + if (unlikely(error && (status & rx_not_ls))) + goto read_again; + if (unlikely(error)) { + dev_kfree_skb(skb); + continue; + } - /* If frame length is greater than skb buffer size - * (preallocated during init) then the packet is - * ignored - */ - if (frame_len > priv->dma_buf_sz) { - if (net_ratelimit()) - netdev_err(priv->dev, - "len %d larger than size (%d)\n", - frame_len, priv->dma_buf_sz); - priv->dev->stats.rx_length_errors++; - continue; - } + /* Buffer is good. Go on. */ + + if (likely(status & rx_not_ls)) { + len += priv->dma_buf_sz; + } else { + prev_len = len; + len = stmmac_get_rx_frame_len(priv, p, coe); /* ACS is set; GMAC core strips PAD/FCS for IEEE 802.3 * Type frames (LLC/LLC-SNAP) @@ -3414,53 +3550,97 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) */ if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00) || unlikely(status != llc_snap)) - frame_len -= ETH_FCS_LEN; + len -= ETH_FCS_LEN; + } + + if (!skb) { + int ret = stmmac_get_rx_header_len(priv, p, &hlen); - if (netif_msg_rx_status(priv)) { - netdev_dbg(priv->dev, "\tdesc: %p [entry %d] buff=0x%x\n", - p, entry, des); - netdev_dbg(priv->dev, "frame size %d, COE: %d\n", - frame_len, status); + if (priv->sph && !ret && (hlen > 0)) { + sec_len = len; + if (!(status & rx_not_ls)) + sec_len = sec_len - hlen; + len = hlen; + + prefetch(page_address(buf->sec_page)); + priv->xstats.rx_split_hdr_pkt_n++; } - skb = netdev_alloc_skb_ip_align(priv->dev, frame_len); - if (unlikely(!skb)) { + skb = napi_alloc_skb(&ch->rx_napi, len); + if (!skb) { priv->dev->stats.rx_dropped++; continue; } - dma_sync_single_for_cpu(priv->device, buf->addr, - frame_len, DMA_FROM_DEVICE); + dma_sync_single_for_cpu(priv->device, buf->addr, len, + DMA_FROM_DEVICE); skb_copy_to_linear_data(skb, page_address(buf->page), - frame_len); - skb_put(skb, frame_len); + len); + skb_put(skb, len); - if (netif_msg_pktdata(priv)) { - netdev_dbg(priv->dev, "frame received (%dbytes)", - frame_len); - print_pkt(skb->data, frame_len); - } - - stmmac_get_rx_hwtstamp(priv, p, np, skb); + /* Data payload copied into SKB, page ready for recycle */ + page_pool_recycle_direct(rx_q->page_pool, buf->page); + buf->page = NULL; + } else { + unsigned int buf_len = len - prev_len; - stmmac_rx_vlan(priv->dev, skb); + if (likely(status & rx_not_ls)) + buf_len = priv->dma_buf_sz; - skb->protocol = eth_type_trans(skb, priv->dev); + dma_sync_single_for_cpu(priv->device, buf->addr, + buf_len, DMA_FROM_DEVICE); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + buf->page, 0, buf_len, + priv->dma_buf_sz); - if (unlikely(!coe)) - skb_checksum_none_assert(skb); - else - skb->ip_summed = CHECKSUM_UNNECESSARY; + /* Data payload appended into SKB */ + page_pool_release_page(rx_q->page_pool, buf->page); + buf->page = NULL; + } - napi_gro_receive(&ch->rx_napi, skb); + if (sec_len > 0) { + dma_sync_single_for_cpu(priv->device, buf->sec_addr, + sec_len, DMA_FROM_DEVICE); + skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, + buf->sec_page, 0, sec_len, + priv->dma_buf_sz); - /* Data payload copied into SKB, page ready for recycle */ - page_pool_recycle_direct(rx_q->page_pool, buf->page); - buf->page = NULL; + len += sec_len; - priv->dev->stats.rx_packets++; - priv->dev->stats.rx_bytes += frame_len; + /* Data payload appended into SKB */ + page_pool_release_page(rx_q->page_pool, buf->sec_page); + buf->sec_page = NULL; } + + if (likely(status & rx_not_ls)) + goto read_again; + + /* Got entire packet into SKB. Finish it. */ + + stmmac_get_rx_hwtstamp(priv, p, np, skb); + stmmac_rx_vlan(priv->dev, skb); + skb->protocol = eth_type_trans(skb, priv->dev); + + if (unlikely(!coe)) + skb_checksum_none_assert(skb); + else + skb->ip_summed = CHECKSUM_UNNECESSARY; + + if (!stmmac_get_rx_hash(priv, p, &hash, &hash_type)) + skb_set_hash(skb, hash, hash_type); + + skb_record_rx_queue(skb, queue); + napi_gro_receive(&ch->rx_napi, skb); + + priv->dev->stats.rx_packets++; + priv->dev->stats.rx_bytes += len; + } + + if (status & rx_not_ls) { + rx_q->state_saved = true; + rx_q->state.skb = skb; + rx_q->state.error = error; + rx_q->state.len = len; } stmmac_rx_refill(priv, queue); @@ -3606,6 +3786,8 @@ static int stmmac_set_features(struct net_device *netdev, netdev_features_t features) { struct stmmac_priv *priv = netdev_priv(netdev); + bool sph_en; + u32 chan; /* Keep the COE Type in case of csum is supporting */ if (features & NETIF_F_RXCSUM) @@ -3617,6 +3799,10 @@ static int stmmac_set_features(struct net_device *netdev, */ stmmac_rx_ipc(priv, priv->hw); + sph_en = (priv->hw->rx_csum > 0) && priv->sph; + for (chan = 0; chan < priv->plat->rx_queues_to_use; chan++) + stmmac_enable_sph(priv, priv->ioaddr, sph_en, chan); + return 0; } @@ -3755,12 +3941,17 @@ static int stmmac_setup_tc_block_cb(enum tc_setup_type type, void *type_data, struct stmmac_priv *priv = cb_priv; int ret = -EOPNOTSUPP; + if (!tc_cls_can_offload_and_chain0(priv->dev, type_data)) + return ret; + stmmac_disable_all_queues(priv); switch (type) { case TC_SETUP_CLSU32: - if (tc_cls_can_offload_and_chain0(priv->dev, type_data)) - ret = stmmac_tc_setup_cls_u32(priv, priv, type_data); + ret = stmmac_tc_setup_cls_u32(priv, priv, type_data); + break; + case TC_SETUP_CLSFLOWER: + ret = stmmac_tc_setup_cls(priv, priv, type_data); break; default: break; @@ -3962,54 +4153,102 @@ static int stmmac_dma_cap_show(struct seq_file *seq, void *v) } DEFINE_SHOW_ATTRIBUTE(stmmac_dma_cap); -static int stmmac_init_fs(struct net_device *dev) +static void stmmac_init_fs(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); /* Create per netdev entries */ priv->dbgfs_dir = debugfs_create_dir(dev->name, stmmac_fs_dir); - if (!priv->dbgfs_dir || IS_ERR(priv->dbgfs_dir)) { - netdev_err(priv->dev, "ERROR failed to create debugfs directory\n"); + /* Entry to report DMA RX/TX rings */ + debugfs_create_file("descriptors_status", 0444, priv->dbgfs_dir, dev, + &stmmac_rings_status_fops); - return -ENOMEM; + /* Entry to report the DMA HW features */ + debugfs_create_file("dma_cap", 0444, priv->dbgfs_dir, dev, + &stmmac_dma_cap_fops); +} + +static void stmmac_exit_fs(struct net_device *dev) +{ + struct stmmac_priv *priv = netdev_priv(dev); + + debugfs_remove_recursive(priv->dbgfs_dir); +} +#endif /* CONFIG_DEBUG_FS */ + +static u32 stmmac_vid_crc32_le(__le16 vid_le) +{ + unsigned char *data = (unsigned char *)&vid_le; + unsigned char data_byte = 0; + u32 crc = ~0x0; + u32 temp = 0; + int i, bits; + + bits = get_bitmask_order(VLAN_VID_MASK); + for (i = 0; i < bits; i++) { + if ((i % 8) == 0) + data_byte = data[i / 8]; + + temp = ((crc & 1) ^ data_byte) & 1; + crc >>= 1; + data_byte >>= 1; + + if (temp) + crc ^= 0xedb88320; } - /* Entry to report DMA RX/TX rings */ - priv->dbgfs_rings_status = - debugfs_create_file("descriptors_status", 0444, - priv->dbgfs_dir, dev, - &stmmac_rings_status_fops); + return crc; +} - if (!priv->dbgfs_rings_status || IS_ERR(priv->dbgfs_rings_status)) { - netdev_err(priv->dev, "ERROR creating stmmac ring debugfs file\n"); - debugfs_remove_recursive(priv->dbgfs_dir); +static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double) +{ + u32 crc, hash = 0; + u16 vid; - return -ENOMEM; + for_each_set_bit(vid, priv->active_vlans, VLAN_N_VID) { + __le16 vid_le = cpu_to_le16(vid); + crc = bitrev32(~stmmac_vid_crc32_le(vid_le)) >> 28; + hash |= (1 << crc); } - /* Entry to report the DMA HW features */ - priv->dbgfs_dma_cap = debugfs_create_file("dma_cap", 0444, - priv->dbgfs_dir, - dev, &stmmac_dma_cap_fops); + return stmmac_update_vlan_hash(priv, priv->hw, hash, is_double); +} + +static int stmmac_vlan_rx_add_vid(struct net_device *ndev, __be16 proto, u16 vid) +{ + struct stmmac_priv *priv = netdev_priv(ndev); + bool is_double = false; + int ret; - if (!priv->dbgfs_dma_cap || IS_ERR(priv->dbgfs_dma_cap)) { - netdev_err(priv->dev, "ERROR creating stmmac MMC debugfs file\n"); - debugfs_remove_recursive(priv->dbgfs_dir); + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + if (be16_to_cpu(proto) == ETH_P_8021AD) + is_double = true; - return -ENOMEM; + set_bit(vid, priv->active_vlans); + ret = stmmac_vlan_update(priv, is_double); + if (ret) { + clear_bit(vid, priv->active_vlans); + return ret; } - return 0; + return ret; } -static void stmmac_exit_fs(struct net_device *dev) +static int stmmac_vlan_rx_kill_vid(struct net_device *ndev, __be16 proto, u16 vid) { - struct stmmac_priv *priv = netdev_priv(dev); + struct stmmac_priv *priv = netdev_priv(ndev); + bool is_double = false; - debugfs_remove_recursive(priv->dbgfs_dir); + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + if (be16_to_cpu(proto) == ETH_P_8021AD) + is_double = true; + + clear_bit(vid, priv->active_vlans); + return stmmac_vlan_update(priv, is_double); } -#endif /* CONFIG_DEBUG_FS */ static const struct net_device_ops stmmac_netdev_ops = { .ndo_open = stmmac_open, @@ -4027,6 +4266,8 @@ static const struct net_device_ops stmmac_netdev_ops = { .ndo_poll_controller = stmmac_poll_controller, #endif .ndo_set_mac_address = stmmac_set_mac_address, + .ndo_vlan_rx_add_vid = stmmac_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = stmmac_vlan_rx_kill_vid, }; static void stmmac_reset_subtask(struct stmmac_priv *priv) @@ -4175,8 +4416,8 @@ int stmmac_dvr_probe(struct device *device, { struct net_device *ndev = NULL; struct stmmac_priv *priv; - u32 queue, maxq; - int ret = 0; + u32 queue, rxq, maxq; + int i, ret = 0; ndev = devm_alloc_etherdev_mqs(device, sizeof(struct stmmac_priv), MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES); @@ -4259,6 +4500,12 @@ int stmmac_dvr_probe(struct device *device, dev_info(priv->device, "TSO feature enabled\n"); } + if (priv->dma_cap.sphen) { + ndev->hw_features |= NETIF_F_GRO; + priv->sph = true; + dev_info(priv->device, "SPH feature enabled\n"); + } + if (priv->dma_cap.addr64) { ret = dma_set_mask_and_coherent(device, DMA_BIT_MASK(priv->dma_cap.addr64)); @@ -4281,15 +4528,33 @@ int stmmac_dvr_probe(struct device *device, #ifdef STMMAC_VLAN_TAG_USED /* Both mac100 and gmac support receive VLAN tag detection */ ndev->features |= NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_STAG_RX; + if (priv->dma_cap.vlhash) { + ndev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + ndev->features |= NETIF_F_HW_VLAN_STAG_FILTER; + } + if (priv->dma_cap.vlins) { + ndev->features |= NETIF_F_HW_VLAN_CTAG_TX; + if (priv->dma_cap.dvlan) + ndev->features |= NETIF_F_HW_VLAN_STAG_TX; + } #endif priv->msg_enable = netif_msg_init(debug, default_msg_level); + /* Initialize RSS */ + rxq = priv->plat->rx_queues_to_use; + netdev_rss_key_fill(priv->rss.key, sizeof(priv->rss.key)); + for (i = 0; i < ARRAY_SIZE(priv->rss.table); i++) + priv->rss.table[i] = ethtool_rxfh_indir_default(i, rxq); + + if (priv->dma_cap.rssen && priv->plat->rss_en) + ndev->features |= NETIF_F_RXHASH; + /* MTU range: 46 - hw-specific max */ ndev->min_mtu = ETH_ZLEN - ETH_HLEN; - if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00)) - ndev->max_mtu = JUMBO_LEN; - else if (priv->plat->has_xgmac) + if (priv->plat->has_xgmac) ndev->max_mtu = XGMAC_JUMBO_LEN; + else if ((priv->plat->enh_desc) || (priv->synopsys_id >= DWMAC_CORE_4_00)) + ndev->max_mtu = JUMBO_LEN; else ndev->max_mtu = SKB_MAX_HEAD(NET_SKB_PAD + NET_IP_ALIGN); /* Will not overwrite ndev->max_mtu if plat->maxmtu > ndev->max_mtu @@ -4368,10 +4633,7 @@ int stmmac_dvr_probe(struct device *device, } #ifdef CONFIG_DEBUG_FS - ret = stmmac_init_fs(ndev); - if (ret < 0) - netdev_warn(priv->dev, "%s: failed debugFS registration\n", - __func__); + stmmac_init_fs(ndev); #endif return ret; @@ -4451,10 +4713,12 @@ int stmmac_suspend(struct device *dev) if (!ndev || !netif_running(ndev)) return 0; - phylink_stop(priv->phylink); - mutex_lock(&priv->lock); + rtnl_lock(); + phylink_stop(priv->phylink); + rtnl_unlock(); + netif_device_detach(ndev); stmmac_stop_all_queues(priv); @@ -4558,9 +4822,11 @@ int stmmac_resume(struct device *dev) stmmac_start_all_queues(priv); - mutex_unlock(&priv->lock); - + rtnl_lock(); phylink_start(priv->phylink); + rtnl_unlock(); + + mutex_unlock(&priv->lock); return 0; } @@ -4617,16 +4883,8 @@ static int __init stmmac_init(void) { #ifdef CONFIG_DEBUG_FS /* Create debugfs main directory if it doesn't exist yet */ - if (!stmmac_fs_dir) { + if (!stmmac_fs_dir) stmmac_fs_dir = debugfs_create_dir(STMMAC_RESOURCE_NAME, NULL); - - if (!stmmac_fs_dir || IS_ERR(stmmac_fs_dir)) { - pr_err("ERROR %s, debugfs create directory failed\n", - STMMAC_RESOURCE_NAME); - - return -ENOMEM; - } - } #endif return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c index 4304c1abc5d1..40c42637ad75 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_mdio.c @@ -348,7 +348,9 @@ int stmmac_mdio_register(struct net_device *ndev) max_addr = PHY_MAX_ADDR; } - new_bus->reset = &stmmac_mdio_reset; + if (mdio_bus_data->needs_reset) + new_bus->reset = &stmmac_mdio_reset; + snprintf(new_bus->id, MII_BUS_ID_SIZE, "%s-%x", new_bus->name, priv->plat->bus_id); new_bus->priv = ndev; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 86f9c07a38cf..292045f4581f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -9,6 +9,7 @@ Author: Giuseppe Cavallaro <peppe.cavallaro@st.com> *******************************************************************************/ +#include <linux/clk-provider.h> #include <linux/pci.h> #include <linux/dmi.h> @@ -63,6 +64,7 @@ static void common_default_data(struct plat_stmmacenet_data *plat) plat->has_gmac = 1; plat->force_sf_dma_mode = 1; + plat->mdio_bus_data->needs_reset = true; plat->mdio_bus_data->phy_mask = 0; /* Set default value for multicast hash bins */ @@ -107,6 +109,166 @@ static const struct stmmac_pci_info stmmac_pci_info = { .setup = stmmac_default_data, }; +static int intel_mgbe_common_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + int i; + + plat->clk_csr = 5; + plat->has_gmac = 0; + plat->has_gmac4 = 1; + plat->force_sf_dma_mode = 0; + plat->tso_en = 1; + + plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; + + for (i = 0; i < plat->rx_queues_to_use; i++) { + plat->rx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; + plat->rx_queues_cfg[i].chan = i; + + /* Disable Priority config by default */ + plat->rx_queues_cfg[i].use_prio = false; + + /* Disable RX queues routing by default */ + plat->rx_queues_cfg[i].pkt_route = 0x0; + } + + for (i = 0; i < plat->tx_queues_to_use; i++) { + plat->tx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; + + /* Disable Priority config by default */ + plat->tx_queues_cfg[i].use_prio = false; + } + + /* FIFO size is 4096 bytes for 1 tx/rx queue */ + plat->tx_fifo_size = plat->tx_queues_to_use * 4096; + plat->rx_fifo_size = plat->rx_queues_to_use * 4096; + + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR; + plat->tx_queues_cfg[0].weight = 0x09; + plat->tx_queues_cfg[1].weight = 0x0A; + plat->tx_queues_cfg[2].weight = 0x0B; + plat->tx_queues_cfg[3].weight = 0x0C; + plat->tx_queues_cfg[4].weight = 0x0D; + plat->tx_queues_cfg[5].weight = 0x0E; + plat->tx_queues_cfg[6].weight = 0x0F; + plat->tx_queues_cfg[7].weight = 0x10; + + plat->mdio_bus_data->phy_mask = 0; + + plat->dma_cfg->pbl = 32; + plat->dma_cfg->pblx8 = true; + plat->dma_cfg->fixed_burst = 0; + plat->dma_cfg->mixed_burst = 0; + plat->dma_cfg->aal = 0; + + plat->axi = devm_kzalloc(&pdev->dev, sizeof(*plat->axi), + GFP_KERNEL); + if (!plat->axi) + return -ENOMEM; + + plat->axi->axi_lpi_en = 0; + plat->axi->axi_xit_frm = 0; + plat->axi->axi_wr_osr_lmt = 1; + plat->axi->axi_rd_osr_lmt = 1; + plat->axi->axi_blen[0] = 4; + plat->axi->axi_blen[1] = 8; + plat->axi->axi_blen[2] = 16; + + plat->ptp_max_adj = plat->clk_ptp_rate; + + /* Set system clock */ + plat->stmmac_clk = clk_register_fixed_rate(&pdev->dev, + "stmmac-clk", NULL, 0, + plat->clk_ptp_rate); + + if (IS_ERR(plat->stmmac_clk)) { + dev_warn(&pdev->dev, "Fail to register stmmac-clk\n"); + plat->stmmac_clk = NULL; + } + clk_prepare_enable(plat->stmmac_clk); + + /* Set default value for multicast hash bins */ + plat->multicast_filter_bins = HASH_TABLE_SIZE; + + /* Set default value for unicast filter entries */ + plat->unicast_filter_entries = 1; + + /* Set the maxmtu to a default of JUMBO_LEN */ + plat->maxmtu = JUMBO_LEN; + + return 0; +} + +static int ehl_common_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + int ret; + + plat->rx_queues_to_use = 8; + plat->tx_queues_to_use = 8; + plat->clk_ptp_rate = 200000000; + ret = intel_mgbe_common_data(pdev, plat); + if (ret) + return ret; + + return 0; +} + +static int ehl_sgmii_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + plat->bus_id = 1; + plat->phy_addr = 0; + plat->interface = PHY_INTERFACE_MODE_SGMII; + return ehl_common_data(pdev, plat); +} + +static struct stmmac_pci_info ehl_sgmii1g_pci_info = { + .setup = ehl_sgmii_data, +}; + +static int ehl_rgmii_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + plat->bus_id = 1; + plat->phy_addr = 0; + plat->interface = PHY_INTERFACE_MODE_RGMII; + return ehl_common_data(pdev, plat); +} + +static struct stmmac_pci_info ehl_rgmii1g_pci_info = { + .setup = ehl_rgmii_data, +}; + +static int tgl_common_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + int ret; + + plat->rx_queues_to_use = 6; + plat->tx_queues_to_use = 4; + plat->clk_ptp_rate = 200000000; + ret = intel_mgbe_common_data(pdev, plat); + if (ret) + return ret; + + return 0; +} + +static int tgl_sgmii_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + plat->bus_id = 1; + plat->phy_addr = 0; + plat->interface = PHY_INTERFACE_MODE_SGMII; + return tgl_common_data(pdev, plat); +} + +static struct stmmac_pci_info tgl_sgmii1g_pci_info = { + .setup = tgl_sgmii_data, +}; + static const struct stmmac_pci_func_data galileo_stmmac_func_data[] = { { .func = 6, @@ -213,6 +375,75 @@ static const struct stmmac_pci_info quark_pci_info = { .setup = quark_default_data, }; +static int snps_gmac5_default_data(struct pci_dev *pdev, + struct plat_stmmacenet_data *plat) +{ + int i; + + plat->clk_csr = 5; + plat->has_gmac4 = 1; + plat->force_sf_dma_mode = 1; + plat->tso_en = 1; + plat->pmt = 1; + + plat->mdio_bus_data->phy_mask = 0; + + /* Set default value for multicast hash bins */ + plat->multicast_filter_bins = HASH_TABLE_SIZE; + + /* Set default value for unicast filter entries */ + plat->unicast_filter_entries = 1; + + /* Set the maxmtu to a default of JUMBO_LEN */ + plat->maxmtu = JUMBO_LEN; + + /* Set default number of RX and TX queues to use */ + plat->tx_queues_to_use = 4; + plat->rx_queues_to_use = 4; + + plat->tx_sched_algorithm = MTL_TX_ALGORITHM_WRR; + for (i = 0; i < plat->tx_queues_to_use; i++) { + plat->tx_queues_cfg[i].use_prio = false; + plat->tx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; + plat->tx_queues_cfg[i].weight = 25; + } + + plat->rx_sched_algorithm = MTL_RX_ALGORITHM_SP; + for (i = 0; i < plat->rx_queues_to_use; i++) { + plat->rx_queues_cfg[i].use_prio = false; + plat->rx_queues_cfg[i].mode_to_use = MTL_QUEUE_DCB; + plat->rx_queues_cfg[i].pkt_route = 0x0; + plat->rx_queues_cfg[i].chan = i; + } + + plat->bus_id = 1; + plat->phy_addr = -1; + plat->interface = PHY_INTERFACE_MODE_GMII; + + plat->dma_cfg->pbl = 32; + plat->dma_cfg->pblx8 = true; + + /* Axi Configuration */ + plat->axi = devm_kzalloc(&pdev->dev, sizeof(*plat->axi), GFP_KERNEL); + if (!plat->axi) + return -ENOMEM; + + plat->axi->axi_wr_osr_lmt = 31; + plat->axi->axi_rd_osr_lmt = 31; + + plat->axi->axi_fb = false; + plat->axi->axi_blen[0] = 4; + plat->axi->axi_blen[1] = 8; + plat->axi->axi_blen[2] = 16; + plat->axi->axi_blen[3] = 32; + + return 0; +} + +static const struct stmmac_pci_info snps_gmac5_pci_info = { + .setup = snps_gmac5_default_data, +}; + /** * stmmac_pci_probe * @@ -292,10 +523,15 @@ static int stmmac_pci_probe(struct pci_dev *pdev, */ static void stmmac_pci_remove(struct pci_dev *pdev) { + struct net_device *ndev = dev_get_drvdata(&pdev->dev); + struct stmmac_priv *priv = netdev_priv(ndev); int i; stmmac_dvr_remove(&pdev->dev); + if (priv->plat->stmmac_clk) + clk_unregister_fixed_rate(priv->plat->stmmac_clk); + for (i = 0; i <= PCI_STD_RESOURCE_END; i++) { if (pci_resource_len(pdev, i) == 0) continue; @@ -348,6 +584,10 @@ static SIMPLE_DEV_PM_OPS(stmmac_pm_ops, stmmac_pci_suspend, stmmac_pci_resume); #define STMMAC_QUARK_ID 0x0937 #define STMMAC_DEVICE_ID 0x1108 +#define STMMAC_EHL_RGMII1G_ID 0x4b30 +#define STMMAC_EHL_SGMII1G_ID 0x4b31 +#define STMMAC_TGL_SGMII1G_ID 0xa0ac +#define STMMAC_GMAC5_ID 0x7102 #define STMMAC_DEVICE(vendor_id, dev_id, info) { \ PCI_VDEVICE(vendor_id, dev_id), \ @@ -358,6 +598,10 @@ static const struct pci_device_id stmmac_id_table[] = { STMMAC_DEVICE(STMMAC, STMMAC_DEVICE_ID, stmmac_pci_info), STMMAC_DEVICE(STMICRO, PCI_DEVICE_ID_STMICRO_MAC, stmmac_pci_info), STMMAC_DEVICE(INTEL, STMMAC_QUARK_ID, quark_pci_info), + STMMAC_DEVICE(INTEL, STMMAC_EHL_RGMII1G_ID, ehl_rgmii1g_pci_info), + STMMAC_DEVICE(INTEL, STMMAC_EHL_SGMII1G_ID, ehl_sgmii1g_pci_info), + STMMAC_DEVICE(INTEL, STMMAC_TGL_SGMII1G_ID, tgl_sgmii1g_pci_info), + STMMAC_DEVICE(SYNOPSYS, STMMAC_GMAC5_ID, snps_gmac5_pci_info), {} }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c index 154daf4d1072..170c3a052b14 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_platform.c @@ -23,6 +23,7 @@ /** * dwmac1000_validate_mcast_bins - validates the number of Multicast filter bins + * @dev: struct device of the platform device * @mcast_bins: Multicast filtering bins * Description: * this function validates the number of Multicast filtering bins specified @@ -33,7 +34,7 @@ * invalid and will cause the filtering algorithm to use Multicast * promiscuous mode. */ -static int dwmac1000_validate_mcast_bins(int mcast_bins) +static int dwmac1000_validate_mcast_bins(struct device *dev, int mcast_bins) { int x = mcast_bins; @@ -44,8 +45,8 @@ static int dwmac1000_validate_mcast_bins(int mcast_bins) break; default: x = 0; - pr_info("Hash table entries set to unexpected value %d", - mcast_bins); + dev_info(dev, "Hash table entries set to unexpected value %d\n", + mcast_bins); break; } return x; @@ -53,6 +54,7 @@ static int dwmac1000_validate_mcast_bins(int mcast_bins) /** * dwmac1000_validate_ucast_entries - validate the Unicast address entries + * @dev: struct device of the platform device * @ucast_entries: number of Unicast address entries * Description: * This function validates the number of Unicast address entries supported @@ -62,7 +64,8 @@ static int dwmac1000_validate_mcast_bins(int mcast_bins) * selected, and defaults to 1 Unicast address if an unsupported * configuration is selected. */ -static int dwmac1000_validate_ucast_entries(int ucast_entries) +static int dwmac1000_validate_ucast_entries(struct device *dev, + int ucast_entries) { int x = ucast_entries; @@ -73,8 +76,8 @@ static int dwmac1000_validate_ucast_entries(int ucast_entries) break; default: x = 1; - pr_info("Unicast table entries set to unexpected value %d\n", - ucast_entries); + dev_info(dev, "Unicast table entries set to unexpected value %d\n", + ucast_entries); break; } return x; @@ -342,14 +345,46 @@ static int stmmac_dt_phy(struct plat_stmmacenet_data *plat, mdio = true; } - if (mdio) + if (mdio) { plat->mdio_bus_data = devm_kzalloc(dev, sizeof(struct stmmac_mdio_bus_data), GFP_KERNEL); + if (!plat->mdio_bus_data) + return -ENOMEM; + + plat->mdio_bus_data->needs_reset = true; + } + return 0; } /** + * stmmac_of_get_mac_mode - retrieves the interface of the MAC + * @np - device-tree node + * Description: + * Similar to `of_get_phy_mode()`, this function will retrieve (from + * the device-tree) the interface mode on the MAC side. This assumes + * that there is mode converter in-between the MAC & PHY + * (e.g. GMII-to-RGMII). + */ +static int stmmac_of_get_mac_mode(struct device_node *np) +{ + const char *pm; + int err, i; + + err = of_property_read_string(np, "mac-mode", &pm); + if (err < 0) + return err; + + for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++) { + if (!strcasecmp(pm, phy_modes(i))) + return i; + } + + return -ENODEV; +} + +/** * stmmac_probe_config_dt - parse device-tree driver parameters * @pdev: platform_device structure * @mac: MAC address to use @@ -377,7 +412,13 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) *mac = NULL; } - plat->interface = of_get_phy_mode(np); + plat->phy_interface = of_get_phy_mode(np); + if (plat->phy_interface < 0) + return ERR_PTR(plat->phy_interface); + + plat->interface = stmmac_of_get_mac_mode(np); + if (plat->interface < 0) + plat->interface = plat->phy_interface; /* Some wrapper drivers still rely on phy_node. Let's save it while * they are not converted to phylink. */ @@ -457,9 +498,9 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) of_property_read_u32(np, "snps,perfect-filter-entries", &plat->unicast_filter_entries); plat->unicast_filter_entries = dwmac1000_validate_ucast_entries( - plat->unicast_filter_entries); + &pdev->dev, plat->unicast_filter_entries); plat->multicast_filter_bins = dwmac1000_validate_mcast_bins( - plat->multicast_filter_bins); + &pdev->dev, plat->multicast_filter_bins); plat->has_gmac = 1; plat->pmt = 1; } @@ -508,7 +549,8 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) plat->force_thresh_dma_mode = of_property_read_bool(np, "snps,force_thresh_dma_mode"); if (plat->force_thresh_dma_mode) { plat->force_sf_dma_mode = 0; - pr_warn("force_sf_dma_mode is ignored if force_thresh_dma_mode is set."); + dev_warn(&pdev->dev, + "force_sf_dma_mode is ignored if force_thresh_dma_mode is set.\n"); } of_property_read_u32(np, "snps,ps-speed", &plat->mac_port_sel_speed); @@ -522,13 +564,15 @@ stmmac_probe_config_dt(struct platform_device *pdev, const char **mac) } /* clock setup */ - plat->stmmac_clk = devm_clk_get(&pdev->dev, - STMMAC_RESOURCE_NAME); - if (IS_ERR(plat->stmmac_clk)) { - dev_warn(&pdev->dev, "Cannot get CSR clock\n"); - plat->stmmac_clk = NULL; + if (!of_device_is_compatible(np, "snps,dwc-qos-ethernet-4.10")) { + plat->stmmac_clk = devm_clk_get(&pdev->dev, + STMMAC_RESOURCE_NAME); + if (IS_ERR(plat->stmmac_clk)) { + dev_warn(&pdev->dev, "Cannot get CSR clock\n"); + plat->stmmac_clk = NULL; + } + clk_prepare_enable(plat->stmmac_clk); } - clk_prepare_enable(plat->stmmac_clk); plat->pclk = devm_clk_get(&pdev->dev, "pclk"); if (IS_ERR(plat->pclk)) { @@ -609,13 +653,8 @@ int stmmac_get_platform_resources(struct platform_device *pdev, * probe if needed before we went too far with resource allocation. */ stmmac_res->irq = platform_get_irq_byname(pdev, "macirq"); - if (stmmac_res->irq < 0) { - if (stmmac_res->irq != -EPROBE_DEFER) { - dev_err(&pdev->dev, - "MAC IRQ configuration information not found\n"); - } + if (stmmac_res->irq < 0) return stmmac_res->irq; - } /* On some platforms e.g. SPEAr the wake up irq differs from the mac irq * The external wake up irq can be passed through the platform code diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index c48224973a37..173493db038c 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -194,6 +194,9 @@ void stmmac_ptp_register(struct stmmac_priv *priv) priv->pps[i].available = true; } + if (priv->plat->ptp_max_adj) + stmmac_ptp_clock_ops.max_adj = priv->plat->ptp_max_adj; + stmmac_ptp_clock_ops.n_per_out = priv->dma_cap.pps_out_num; spin_lock_init(&priv->ptp_lock); diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c index a97b1ea76438..c56e89e1ae56 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_selftests.c @@ -11,8 +11,10 @@ #include <linux/ip.h> #include <linux/phy.h> #include <linux/udp.h> +#include <net/pkt_cls.h> #include <net/tcp.h> #include <net/udp.h> +#include <net/tc_act/tc_gact.h> #include "stmmac.h" struct stmmachdr { @@ -41,8 +43,11 @@ struct stmmac_packet_attrs { int dont_wait; int timeout; int size; + int max_size; int remove_sa; u8 id; + int sarc; + u16 queue_mapping; }; static u8 stmmac_test_next_id; @@ -70,12 +75,14 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv, else size += sizeof(struct udphdr); - skb = netdev_alloc_skb(priv->dev, size); + if (attr->max_size && (attr->max_size > size)) + size = attr->max_size; + + skb = netdev_alloc_skb_ip_align(priv->dev, size); if (!skb) return NULL; prefetchw(skb->data); - skb_reserve(skb, NET_IP_ALIGN); if (attr->vlan > 1) ehdr = skb_push(skb, ETH_HLEN + 8); @@ -144,6 +151,9 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv, uhdr->source = htons(attr->sport); uhdr->dest = htons(attr->dport); uhdr->len = htons(sizeof(*shdr) + sizeof(*uhdr) + attr->size); + if (attr->max_size) + uhdr->len = htons(attr->max_size - + (sizeof(*ihdr) + sizeof(*ehdr))); uhdr->check = 0; } @@ -159,9 +169,13 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv, iplen += sizeof(*thdr); else iplen += sizeof(*uhdr); + + if (attr->max_size) + iplen = attr->max_size - sizeof(*ehdr); + ihdr->tot_len = htons(iplen); ihdr->frag_off = 0; - ihdr->saddr = 0; + ihdr->saddr = htonl(attr->ip_src); ihdr->daddr = htonl(attr->ip_dst); ihdr->tos = 0; ihdr->id = 0; @@ -175,6 +189,8 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv, if (attr->size) skb_put(skb, attr->size); + if (attr->max_size && (attr->max_size > skb->len)) + skb_put(skb, attr->max_size - skb->len); skb->csum = 0; skb->ip_summed = CHECKSUM_PARTIAL; @@ -193,6 +209,24 @@ static struct sk_buff *stmmac_test_get_udp_skb(struct stmmac_priv *priv, return skb; } +static struct sk_buff *stmmac_test_get_arp_skb(struct stmmac_priv *priv, + struct stmmac_packet_attrs *attr) +{ + __be32 ip_src = htonl(attr->ip_src); + __be32 ip_dst = htonl(attr->ip_dst); + struct sk_buff *skb = NULL; + + skb = arp_create(ARPOP_REQUEST, ETH_P_ARP, ip_dst, priv->dev, ip_src, + NULL, attr->src, attr->dst); + if (!skb) + return NULL; + + skb->pkt_type = PACKET_HOST; + skb->dev = priv->dev; + + return skb; +} + struct stmmac_test_priv { struct stmmac_packet_attrs *packet; struct packet_type pt; @@ -228,8 +262,11 @@ static int stmmac_test_loopback_validate(struct sk_buff *skb, if (!ether_addr_equal(ehdr->h_dest, tpriv->packet->dst)) goto out; } - if (tpriv->packet->src) { - if (!ether_addr_equal(ehdr->h_source, orig_ndev->dev_addr)) + if (tpriv->packet->sarc) { + if (!ether_addr_equal(ehdr->h_source, ehdr->h_dest)) + goto out; + } else if (tpriv->packet->src) { + if (!ether_addr_equal(ehdr->h_source, tpriv->packet->src)) goto out; } @@ -290,7 +327,9 @@ static int __stmmac_test_loopback(struct stmmac_priv *priv, tpriv->pt.dev = priv->dev; tpriv->pt.af_packet_priv = tpriv; tpriv->packet = attr; - dev_add_pack(&tpriv->pt); + + if (!attr->dont_wait) + dev_add_pack(&tpriv->pt); skb = stmmac_test_get_udp_skb(priv, attr); if (!skb) { @@ -298,7 +337,7 @@ static int __stmmac_test_loopback(struct stmmac_priv *priv, goto cleanup; } - skb_set_queue_mapping(skb, 0); + skb_set_queue_mapping(skb, attr->queue_mapping); ret = dev_queue_xmit(skb); if (ret) goto cleanup; @@ -310,10 +349,11 @@ static int __stmmac_test_loopback(struct stmmac_priv *priv, attr->timeout = STMMAC_LB_TIMEOUT; wait_for_completion_timeout(&tpriv->comp, attr->timeout); - ret = !tpriv->ok; + ret = tpriv->ok ? 0 : -ETIMEDOUT; cleanup: - dev_remove_pack(&tpriv->pt); + if (!attr->dont_wait) + dev_remove_pack(&tpriv->pt); kfree(tpriv); return ret; } @@ -471,7 +511,7 @@ static int stmmac_test_hfilt(struct stmmac_priv *priv) /* Shall NOT receive packet */ ret = __stmmac_test_loopback(priv, &attr); - ret = !ret; + ret = ret ? 0 : -EINVAL; cleanup: dev_mc_del(priv->dev, gd_addr); @@ -503,7 +543,7 @@ static int stmmac_test_pfilt(struct stmmac_priv *priv) /* Shall NOT receive packet */ ret = __stmmac_test_loopback(priv, &attr); - ret = !ret; + ret = ret ? 0 : -EINVAL; cleanup: dev_uc_del(priv->dev, gd_addr); @@ -553,7 +593,7 @@ static int stmmac_test_mcfilt(struct stmmac_priv *priv) /* Shall NOT receive packet */ ret = __stmmac_test_loopback(priv, &attr); - ret = !ret; + ret = ret ? 0 : -EINVAL; cleanup: dev_uc_del(priv->dev, uc_addr); @@ -591,7 +631,7 @@ static int stmmac_test_ucfilt(struct stmmac_priv *priv) /* Shall NOT receive packet */ ret = __stmmac_test_loopback(priv, &attr); - ret = !ret; + ret = ret ? 0 : -EINVAL; cleanup: dev_mc_del(priv->dev, mc_addr); @@ -682,15 +722,21 @@ static int stmmac_test_flowctrl(struct stmmac_priv *priv) for (i = 0; i < rx_cnt; i++) { struct stmmac_channel *ch = &priv->channel[i]; + u32 tail; + tail = priv->rx_queue[i].dma_rx_phy + + (DMA_RX_SIZE * sizeof(struct dma_desc)); + + stmmac_set_rx_tail_ptr(priv, priv->ioaddr, tail, i); stmmac_start_rx(priv, priv->ioaddr, i); + local_bh_disable(); napi_reschedule(&ch->rx_napi); local_bh_enable(); } wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT); - ret = !tpriv->ok; + ret = tpriv->ok ? 0 : -ETIMEDOUT; cleanup: dev_mc_del(priv->dev, paddr); @@ -700,6 +746,901 @@ cleanup: return ret; } +static int stmmac_test_rss(struct stmmac_priv *priv) +{ + struct stmmac_packet_attrs attr = { }; + + if (!priv->dma_cap.rssen || !priv->rss.enable) + return -EOPNOTSUPP; + + attr.dst = priv->dev->dev_addr; + attr.exp_hash = true; + attr.sport = 0x321; + attr.dport = 0x123; + + return __stmmac_test_loopback(priv, &attr); +} + +static int stmmac_test_vlan_validate(struct sk_buff *skb, + struct net_device *ndev, + struct packet_type *pt, + struct net_device *orig_ndev) +{ + struct stmmac_test_priv *tpriv = pt->af_packet_priv; + struct stmmachdr *shdr; + struct ethhdr *ehdr; + struct udphdr *uhdr; + struct iphdr *ihdr; + u16 proto; + + proto = tpriv->double_vlan ? ETH_P_8021AD : ETH_P_8021Q; + + skb = skb_unshare(skb, GFP_ATOMIC); + if (!skb) + goto out; + + if (skb_linearize(skb)) + goto out; + if (skb_headlen(skb) < (STMMAC_TEST_PKT_SIZE - ETH_HLEN)) + goto out; + if (tpriv->vlan_id) { + if (skb->vlan_proto != htons(proto)) + goto out; + if (skb->vlan_tci != tpriv->vlan_id) + goto out; + } + + ehdr = (struct ethhdr *)skb_mac_header(skb); + if (!ether_addr_equal(ehdr->h_dest, tpriv->packet->dst)) + goto out; + + ihdr = ip_hdr(skb); + if (tpriv->double_vlan) + ihdr = (struct iphdr *)(skb_network_header(skb) + 4); + if (ihdr->protocol != IPPROTO_UDP) + goto out; + + uhdr = (struct udphdr *)((u8 *)ihdr + 4 * ihdr->ihl); + if (uhdr->dest != htons(tpriv->packet->dport)) + goto out; + + shdr = (struct stmmachdr *)((u8 *)uhdr + sizeof(*uhdr)); + if (shdr->magic != cpu_to_be64(STMMAC_TEST_PKT_MAGIC)) + goto out; + + tpriv->ok = true; + complete(&tpriv->comp); + +out: + kfree_skb(skb); + return 0; +} + +static int stmmac_test_vlanfilt(struct stmmac_priv *priv) +{ + struct stmmac_packet_attrs attr = { }; + struct stmmac_test_priv *tpriv; + struct sk_buff *skb = NULL; + int ret = 0, i; + + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + + tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL); + if (!tpriv) + return -ENOMEM; + + tpriv->ok = false; + init_completion(&tpriv->comp); + + tpriv->pt.type = htons(ETH_P_IP); + tpriv->pt.func = stmmac_test_vlan_validate; + tpriv->pt.dev = priv->dev; + tpriv->pt.af_packet_priv = tpriv; + tpriv->packet = &attr; + + /* + * As we use HASH filtering, false positives may appear. This is a + * specially chosen ID so that adjacent IDs (+4) have different + * HASH values. + */ + tpriv->vlan_id = 0x123; + dev_add_pack(&tpriv->pt); + + ret = vlan_vid_add(priv->dev, htons(ETH_P_8021Q), tpriv->vlan_id); + if (ret) + goto cleanup; + + for (i = 0; i < 4; i++) { + attr.vlan = 1; + attr.vlan_id_out = tpriv->vlan_id + i; + attr.dst = priv->dev->dev_addr; + attr.sport = 9; + attr.dport = 9; + + skb = stmmac_test_get_udp_skb(priv, &attr); + if (!skb) { + ret = -ENOMEM; + goto vlan_del; + } + + skb_set_queue_mapping(skb, 0); + ret = dev_queue_xmit(skb); + if (ret) + goto vlan_del; + + wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT); + ret = tpriv->ok ? 0 : -ETIMEDOUT; + if (ret && !i) { + goto vlan_del; + } else if (!ret && i) { + ret = -EINVAL; + goto vlan_del; + } else { + ret = 0; + } + + tpriv->ok = false; + } + +vlan_del: + vlan_vid_del(priv->dev, htons(ETH_P_8021Q), tpriv->vlan_id); +cleanup: + dev_remove_pack(&tpriv->pt); + kfree(tpriv); + return ret; +} + +static int stmmac_test_dvlanfilt(struct stmmac_priv *priv) +{ + struct stmmac_packet_attrs attr = { }; + struct stmmac_test_priv *tpriv; + struct sk_buff *skb = NULL; + int ret = 0, i; + + if (!priv->dma_cap.vlhash) + return -EOPNOTSUPP; + + tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL); + if (!tpriv) + return -ENOMEM; + + tpriv->ok = false; + tpriv->double_vlan = true; + init_completion(&tpriv->comp); + + tpriv->pt.type = htons(ETH_P_8021Q); + tpriv->pt.func = stmmac_test_vlan_validate; + tpriv->pt.dev = priv->dev; + tpriv->pt.af_packet_priv = tpriv; + tpriv->packet = &attr; + + /* + * As we use HASH filtering, false positives may appear. This is a + * specially chosen ID so that adjacent IDs (+4) have different + * HASH values. + */ + tpriv->vlan_id = 0x123; + dev_add_pack(&tpriv->pt); + + ret = vlan_vid_add(priv->dev, htons(ETH_P_8021AD), tpriv->vlan_id); + if (ret) + goto cleanup; + + for (i = 0; i < 4; i++) { + attr.vlan = 2; + attr.vlan_id_out = tpriv->vlan_id + i; + attr.dst = priv->dev->dev_addr; + attr.sport = 9; + attr.dport = 9; + + skb = stmmac_test_get_udp_skb(priv, &attr); + if (!skb) { + ret = -ENOMEM; + goto vlan_del; + } + + skb_set_queue_mapping(skb, 0); + ret = dev_queue_xmit(skb); + if (ret) + goto vlan_del; + + wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT); + ret = tpriv->ok ? 0 : -ETIMEDOUT; + if (ret && !i) { + goto vlan_del; + } else if (!ret && i) { + ret = -EINVAL; + goto vlan_del; + } else { + ret = 0; + } + + tpriv->ok = false; + } + +vlan_del: + vlan_vid_del(priv->dev, htons(ETH_P_8021AD), tpriv->vlan_id); +cleanup: + dev_remove_pack(&tpriv->pt); + kfree(tpriv); + return ret; +} + +#ifdef CONFIG_NET_CLS_ACT +static int stmmac_test_rxp(struct stmmac_priv *priv) +{ + unsigned char addr[ETH_ALEN] = {0xde, 0xad, 0xbe, 0xef, 0x00, 0x00}; + struct tc_cls_u32_offload cls_u32 = { }; + struct stmmac_packet_attrs attr = { }; + struct tc_action **actions, *act; + struct tc_u32_sel *sel; + struct tcf_exts *exts; + int ret, i, nk = 1; + + if (!tc_can_offload(priv->dev)) + return -EOPNOTSUPP; + if (!priv->dma_cap.frpsel) + return -EOPNOTSUPP; + + sel = kzalloc(sizeof(*sel) + nk * sizeof(struct tc_u32_key), GFP_KERNEL); + if (!sel) + return -ENOMEM; + + exts = kzalloc(sizeof(*exts), GFP_KERNEL); + if (!exts) { + ret = -ENOMEM; + goto cleanup_sel; + } + + actions = kzalloc(nk * sizeof(*actions), GFP_KERNEL); + if (!actions) { + ret = -ENOMEM; + goto cleanup_exts; + } + + act = kzalloc(nk * sizeof(*act), GFP_KERNEL); + if (!act) { + ret = -ENOMEM; + goto cleanup_actions; + } + + cls_u32.command = TC_CLSU32_NEW_KNODE; + cls_u32.common.chain_index = 0; + cls_u32.common.protocol = htons(ETH_P_ALL); + cls_u32.knode.exts = exts; + cls_u32.knode.sel = sel; + cls_u32.knode.handle = 0x123; + + exts->nr_actions = nk; + exts->actions = actions; + for (i = 0; i < nk; i++) { + struct tcf_gact *gact = to_gact(&act[i]); + + actions[i] = &act[i]; + gact->tcf_action = TC_ACT_SHOT; + } + + sel->nkeys = nk; + sel->offshift = 0; + sel->keys[0].off = 6; + sel->keys[0].val = htonl(0xdeadbeef); + sel->keys[0].mask = ~0x0; + + ret = stmmac_tc_setup_cls_u32(priv, priv, &cls_u32); + if (ret) + goto cleanup_act; + + attr.dst = priv->dev->dev_addr; + attr.src = addr; + + ret = __stmmac_test_loopback(priv, &attr); + ret = ret ? 0 : -EINVAL; /* Shall NOT receive packet */ + + cls_u32.command = TC_CLSU32_DELETE_KNODE; + stmmac_tc_setup_cls_u32(priv, priv, &cls_u32); + +cleanup_act: + kfree(act); +cleanup_actions: + kfree(actions); +cleanup_exts: + kfree(exts); +cleanup_sel: + kfree(sel); + return ret; +} +#else +static int stmmac_test_rxp(struct stmmac_priv *priv) +{ + return -EOPNOTSUPP; +} +#endif + +static int stmmac_test_desc_sai(struct stmmac_priv *priv) +{ + unsigned char src[ETH_ALEN] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + struct stmmac_packet_attrs attr = { }; + int ret; + + if (!priv->dma_cap.vlins) + return -EOPNOTSUPP; + + attr.remove_sa = true; + attr.sarc = true; + attr.src = src; + attr.dst = priv->dev->dev_addr; + + priv->sarc_type = 0x1; + + ret = __stmmac_test_loopback(priv, &attr); + + priv->sarc_type = 0x0; + return ret; +} + +static int stmmac_test_desc_sar(struct stmmac_priv *priv) +{ + unsigned char src[ETH_ALEN] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + struct stmmac_packet_attrs attr = { }; + int ret; + + if (!priv->dma_cap.vlins) + return -EOPNOTSUPP; + + attr.sarc = true; + attr.src = src; + attr.dst = priv->dev->dev_addr; + + priv->sarc_type = 0x2; + + ret = __stmmac_test_loopback(priv, &attr); + + priv->sarc_type = 0x0; + return ret; +} + +static int stmmac_test_reg_sai(struct stmmac_priv *priv) +{ + unsigned char src[ETH_ALEN] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + struct stmmac_packet_attrs attr = { }; + int ret; + + if (!priv->dma_cap.vlins) + return -EOPNOTSUPP; + + attr.remove_sa = true; + attr.sarc = true; + attr.src = src; + attr.dst = priv->dev->dev_addr; + + if (stmmac_sarc_configure(priv, priv->ioaddr, 0x2)) + return -EOPNOTSUPP; + + ret = __stmmac_test_loopback(priv, &attr); + + stmmac_sarc_configure(priv, priv->ioaddr, 0x0); + return ret; +} + +static int stmmac_test_reg_sar(struct stmmac_priv *priv) +{ + unsigned char src[ETH_ALEN] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00}; + struct stmmac_packet_attrs attr = { }; + int ret; + + if (!priv->dma_cap.vlins) + return -EOPNOTSUPP; + + attr.sarc = true; + attr.src = src; + attr.dst = priv->dev->dev_addr; + + if (stmmac_sarc_configure(priv, priv->ioaddr, 0x3)) + return -EOPNOTSUPP; + + ret = __stmmac_test_loopback(priv, &attr); + + stmmac_sarc_configure(priv, priv->ioaddr, 0x0); + return ret; +} + +static int stmmac_test_vlanoff_common(struct stmmac_priv *priv, bool svlan) +{ + struct stmmac_packet_attrs attr = { }; + struct stmmac_test_priv *tpriv; + struct sk_buff *skb = NULL; + int ret = 0; + u16 proto; + + if (!priv->dma_cap.vlins) + return -EOPNOTSUPP; + + tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL); + if (!tpriv) + return -ENOMEM; + + proto = svlan ? ETH_P_8021AD : ETH_P_8021Q; + + tpriv->ok = false; + tpriv->double_vlan = svlan; + init_completion(&tpriv->comp); + + tpriv->pt.type = svlan ? htons(ETH_P_8021Q) : htons(ETH_P_IP); + tpriv->pt.func = stmmac_test_vlan_validate; + tpriv->pt.dev = priv->dev; + tpriv->pt.af_packet_priv = tpriv; + tpriv->packet = &attr; + tpriv->vlan_id = 0x123; + dev_add_pack(&tpriv->pt); + + ret = vlan_vid_add(priv->dev, htons(proto), tpriv->vlan_id); + if (ret) + goto cleanup; + + attr.dst = priv->dev->dev_addr; + + skb = stmmac_test_get_udp_skb(priv, &attr); + if (!skb) { + ret = -ENOMEM; + goto vlan_del; + } + + __vlan_hwaccel_put_tag(skb, htons(proto), tpriv->vlan_id); + skb->protocol = htons(proto); + + skb_set_queue_mapping(skb, 0); + ret = dev_queue_xmit(skb); + if (ret) + goto vlan_del; + + wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT); + ret = tpriv->ok ? 0 : -ETIMEDOUT; + +vlan_del: + vlan_vid_del(priv->dev, htons(proto), tpriv->vlan_id); +cleanup: + dev_remove_pack(&tpriv->pt); + kfree(tpriv); + return ret; +} + +static int stmmac_test_vlanoff(struct stmmac_priv *priv) +{ + return stmmac_test_vlanoff_common(priv, false); +} + +static int stmmac_test_svlanoff(struct stmmac_priv *priv) +{ + if (!priv->dma_cap.dvlan) + return -EOPNOTSUPP; + return stmmac_test_vlanoff_common(priv, true); +} + +#ifdef CONFIG_NET_CLS_ACT +static int __stmmac_test_l3filt(struct stmmac_priv *priv, u32 dst, u32 src, + u32 dst_mask, u32 src_mask) +{ + struct flow_dissector_key_ipv4_addrs key, mask; + unsigned long dummy_cookie = 0xdeadbeef; + struct stmmac_packet_attrs attr = { }; + struct flow_dissector *dissector; + struct flow_cls_offload *cls; + struct flow_rule *rule; + int ret; + + if (!tc_can_offload(priv->dev)) + return -EOPNOTSUPP; + if (!priv->dma_cap.l3l4fnum) + return -EOPNOTSUPP; + if (priv->rss.enable) { + struct stmmac_rss rss = { .enable = false, }; + + stmmac_rss_configure(priv, priv->hw, &rss, + priv->plat->rx_queues_to_use); + } + + dissector = kzalloc(sizeof(*dissector), GFP_KERNEL); + if (!dissector) { + ret = -ENOMEM; + goto cleanup_rss; + } + + dissector->used_keys |= (1 << FLOW_DISSECTOR_KEY_IPV4_ADDRS); + dissector->offset[FLOW_DISSECTOR_KEY_IPV4_ADDRS] = 0; + + cls = kzalloc(sizeof(*cls), GFP_KERNEL); + if (!cls) { + ret = -ENOMEM; + goto cleanup_dissector; + } + + cls->common.chain_index = 0; + cls->command = FLOW_CLS_REPLACE; + cls->cookie = dummy_cookie; + + rule = kzalloc(struct_size(rule, action.entries, 1), GFP_KERNEL); + if (!rule) { + ret = -ENOMEM; + goto cleanup_cls; + } + + rule->match.dissector = dissector; + rule->match.key = (void *)&key; + rule->match.mask = (void *)&mask; + + key.src = htonl(src); + key.dst = htonl(dst); + mask.src = src_mask; + mask.dst = dst_mask; + + cls->rule = rule; + + rule->action.entries[0].id = FLOW_ACTION_DROP; + rule->action.num_entries = 1; + + attr.dst = priv->dev->dev_addr; + attr.ip_dst = dst; + attr.ip_src = src; + + /* Shall receive packet */ + ret = __stmmac_test_loopback(priv, &attr); + if (ret) + goto cleanup_rule; + + ret = stmmac_tc_setup_cls(priv, priv, cls); + if (ret) + goto cleanup_rule; + + /* Shall NOT receive packet */ + ret = __stmmac_test_loopback(priv, &attr); + ret = ret ? 0 : -EINVAL; + + cls->command = FLOW_CLS_DESTROY; + stmmac_tc_setup_cls(priv, priv, cls); +cleanup_rule: + kfree(rule); +cleanup_cls: + kfree(cls); +cleanup_dissector: + kfree(dissector); +cleanup_rss: + if (priv->rss.enable) { + stmmac_rss_configure(priv, priv->hw, &priv->rss, + priv->plat->rx_queues_to_use); + } + + return ret; +} +#else +static int __stmmac_test_l3filt(struct stmmac_priv *priv, u32 dst, u32 src, + u32 dst_mask, u32 src_mask) +{ + return -EOPNOTSUPP; +} +#endif + +static int stmmac_test_l3filt_da(struct stmmac_priv *priv) +{ + u32 addr = 0x10203040; + + return __stmmac_test_l3filt(priv, addr, 0, ~0, 0); +} + +static int stmmac_test_l3filt_sa(struct stmmac_priv *priv) +{ + u32 addr = 0x10203040; + + return __stmmac_test_l3filt(priv, 0, addr, 0, ~0); +} + +#ifdef CONFIG_NET_CLS_ACT +static int __stmmac_test_l4filt(struct stmmac_priv *priv, u32 dst, u32 src, + u32 dst_mask, u32 src_mask, bool udp) +{ + struct { + struct flow_dissector_key_basic bkey; + struct flow_dissector_key_ports key; + } __aligned(BITS_PER_LONG / 8) keys; + struct { + struct flow_dissector_key_basic bmask; + struct flow_dissector_key_ports mask; + } __aligned(BITS_PER_LONG / 8) masks; + unsigned long dummy_cookie = 0xdeadbeef; + struct stmmac_packet_attrs attr = { }; + struct flow_dissector *dissector; + struct flow_cls_offload *cls; + struct flow_rule *rule; + int ret; + + if (!tc_can_offload(priv->dev)) + return -EOPNOTSUPP; + if (!priv->dma_cap.l3l4fnum) + return -EOPNOTSUPP; + if (priv->rss.enable) { + struct stmmac_rss rss = { .enable = false, }; + + stmmac_rss_configure(priv, priv->hw, &rss, + priv->plat->rx_queues_to_use); + } + + dissector = kzalloc(sizeof(*dissector), GFP_KERNEL); + if (!dissector) { + ret = -ENOMEM; + goto cleanup_rss; + } + + dissector->used_keys |= (1 << FLOW_DISSECTOR_KEY_BASIC); + dissector->used_keys |= (1 << FLOW_DISSECTOR_KEY_PORTS); + dissector->offset[FLOW_DISSECTOR_KEY_BASIC] = 0; + dissector->offset[FLOW_DISSECTOR_KEY_PORTS] = offsetof(typeof(keys), key); + + cls = kzalloc(sizeof(*cls), GFP_KERNEL); + if (!cls) { + ret = -ENOMEM; + goto cleanup_dissector; + } + + cls->common.chain_index = 0; + cls->command = FLOW_CLS_REPLACE; + cls->cookie = dummy_cookie; + + rule = kzalloc(struct_size(rule, action.entries, 1), GFP_KERNEL); + if (!rule) { + ret = -ENOMEM; + goto cleanup_cls; + } + + rule->match.dissector = dissector; + rule->match.key = (void *)&keys; + rule->match.mask = (void *)&masks; + + keys.bkey.ip_proto = udp ? IPPROTO_UDP : IPPROTO_TCP; + keys.key.src = htons(src); + keys.key.dst = htons(dst); + masks.mask.src = src_mask; + masks.mask.dst = dst_mask; + + cls->rule = rule; + + rule->action.entries[0].id = FLOW_ACTION_DROP; + rule->action.num_entries = 1; + + attr.dst = priv->dev->dev_addr; + attr.tcp = !udp; + attr.sport = src; + attr.dport = dst; + attr.ip_dst = 0; + + /* Shall receive packet */ + ret = __stmmac_test_loopback(priv, &attr); + if (ret) + goto cleanup_rule; + + ret = stmmac_tc_setup_cls(priv, priv, cls); + if (ret) + goto cleanup_rule; + + /* Shall NOT receive packet */ + ret = __stmmac_test_loopback(priv, &attr); + ret = ret ? 0 : -EINVAL; + + cls->command = FLOW_CLS_DESTROY; + stmmac_tc_setup_cls(priv, priv, cls); +cleanup_rule: + kfree(rule); +cleanup_cls: + kfree(cls); +cleanup_dissector: + kfree(dissector); +cleanup_rss: + if (priv->rss.enable) { + stmmac_rss_configure(priv, priv->hw, &priv->rss, + priv->plat->rx_queues_to_use); + } + + return ret; +} +#else +static int __stmmac_test_l4filt(struct stmmac_priv *priv, u32 dst, u32 src, + u32 dst_mask, u32 src_mask, bool udp) +{ + return -EOPNOTSUPP; +} +#endif + +static int stmmac_test_l4filt_da_tcp(struct stmmac_priv *priv) +{ + u16 dummy_port = 0x123; + + return __stmmac_test_l4filt(priv, dummy_port, 0, ~0, 0, false); +} + +static int stmmac_test_l4filt_sa_tcp(struct stmmac_priv *priv) +{ + u16 dummy_port = 0x123; + + return __stmmac_test_l4filt(priv, 0, dummy_port, 0, ~0, false); +} + +static int stmmac_test_l4filt_da_udp(struct stmmac_priv *priv) +{ + u16 dummy_port = 0x123; + + return __stmmac_test_l4filt(priv, dummy_port, 0, ~0, 0, true); +} + +static int stmmac_test_l4filt_sa_udp(struct stmmac_priv *priv) +{ + u16 dummy_port = 0x123; + + return __stmmac_test_l4filt(priv, 0, dummy_port, 0, ~0, true); +} + +static int stmmac_test_arp_validate(struct sk_buff *skb, + struct net_device *ndev, + struct packet_type *pt, + struct net_device *orig_ndev) +{ + struct stmmac_test_priv *tpriv = pt->af_packet_priv; + struct ethhdr *ehdr; + struct arphdr *ahdr; + + ehdr = (struct ethhdr *)skb_mac_header(skb); + if (!ether_addr_equal(ehdr->h_dest, tpriv->packet->src)) + goto out; + + ahdr = arp_hdr(skb); + if (ahdr->ar_op != htons(ARPOP_REPLY)) + goto out; + + tpriv->ok = true; + complete(&tpriv->comp); +out: + kfree_skb(skb); + return 0; +} + +static int stmmac_test_arpoffload(struct stmmac_priv *priv) +{ + unsigned char src[ETH_ALEN] = {0x01, 0x02, 0x03, 0x04, 0x05, 0x06}; + unsigned char dst[ETH_ALEN] = {0xff, 0xff, 0xff, 0xff, 0xff, 0xff}; + struct stmmac_packet_attrs attr = { }; + struct stmmac_test_priv *tpriv; + struct sk_buff *skb = NULL; + u32 ip_addr = 0xdeadcafe; + u32 ip_src = 0xdeadbeef; + int ret; + + if (!priv->dma_cap.arpoffsel) + return -EOPNOTSUPP; + + tpriv = kzalloc(sizeof(*tpriv), GFP_KERNEL); + if (!tpriv) + return -ENOMEM; + + tpriv->ok = false; + init_completion(&tpriv->comp); + + tpriv->pt.type = htons(ETH_P_ARP); + tpriv->pt.func = stmmac_test_arp_validate; + tpriv->pt.dev = priv->dev; + tpriv->pt.af_packet_priv = tpriv; + tpriv->packet = &attr; + dev_add_pack(&tpriv->pt); + + attr.src = src; + attr.ip_src = ip_src; + attr.dst = dst; + attr.ip_dst = ip_addr; + + skb = stmmac_test_get_arp_skb(priv, &attr); + if (!skb) { + ret = -ENOMEM; + goto cleanup; + } + + ret = stmmac_set_arp_offload(priv, priv->hw, true, ip_addr); + if (ret) + goto cleanup; + + ret = dev_set_promiscuity(priv->dev, 1); + if (ret) + goto cleanup; + + skb_set_queue_mapping(skb, 0); + ret = dev_queue_xmit(skb); + if (ret) + goto cleanup_promisc; + + wait_for_completion_timeout(&tpriv->comp, STMMAC_LB_TIMEOUT); + ret = tpriv->ok ? 0 : -ETIMEDOUT; + +cleanup_promisc: + dev_set_promiscuity(priv->dev, -1); +cleanup: + stmmac_set_arp_offload(priv, priv->hw, false, 0x0); + dev_remove_pack(&tpriv->pt); + kfree(tpriv); + return ret; +} + +static int __stmmac_test_jumbo(struct stmmac_priv *priv, u16 queue) +{ + struct stmmac_packet_attrs attr = { }; + int size = priv->dma_buf_sz; + + /* Only XGMAC has SW support for multiple RX descs in same packet */ + if (priv->plat->has_xgmac) + size = priv->dev->max_mtu; + + attr.dst = priv->dev->dev_addr; + attr.max_size = size - ETH_FCS_LEN; + attr.queue_mapping = queue; + + return __stmmac_test_loopback(priv, &attr); +} + +static int stmmac_test_jumbo(struct stmmac_priv *priv) +{ + return __stmmac_test_jumbo(priv, 0); +} + +static int stmmac_test_mjumbo(struct stmmac_priv *priv) +{ + u32 chan, tx_cnt = priv->plat->tx_queues_to_use; + int ret; + + if (tx_cnt <= 1) + return -EOPNOTSUPP; + + for (chan = 0; chan < tx_cnt; chan++) { + ret = __stmmac_test_jumbo(priv, chan); + if (ret) + return ret; + } + + return 0; +} + +static int stmmac_test_sph(struct stmmac_priv *priv) +{ + unsigned long cnt_end, cnt_start = priv->xstats.rx_split_hdr_pkt_n; + struct stmmac_packet_attrs attr = { }; + int ret; + + if (!priv->sph) + return -EOPNOTSUPP; + + /* Check for UDP first */ + attr.dst = priv->dev->dev_addr; + attr.tcp = false; + + ret = __stmmac_test_loopback(priv, &attr); + if (ret) + return ret; + + cnt_end = priv->xstats.rx_split_hdr_pkt_n; + if (cnt_end <= cnt_start) + return -EINVAL; + + /* Check for TCP now */ + cnt_start = cnt_end; + + attr.dst = priv->dev->dev_addr; + attr.tcp = true; + + ret = __stmmac_test_loopback(priv, &attr); + if (ret) + return ret; + + cnt_end = priv->xstats.rx_split_hdr_pkt_n; + if (cnt_end <= cnt_start) + return -EINVAL; + + return 0; +} + #define STMMAC_LOOPBACK_NONE 0 #define STMMAC_LOOPBACK_MAC 1 #define STMMAC_LOOPBACK_PHY 2 @@ -745,6 +1686,86 @@ static const struct stmmac_test { .name = "Flow Control ", .lb = STMMAC_LOOPBACK_PHY, .fn = stmmac_test_flowctrl, + }, { + .name = "RSS ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_rss, + }, { + .name = "VLAN Filtering ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_vlanfilt, + }, { + .name = "Double VLAN Filtering", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_dvlanfilt, + }, { + .name = "Flexible RX Parser ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_rxp, + }, { + .name = "SA Insertion (desc) ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_desc_sai, + }, { + .name = "SA Replacement (desc)", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_desc_sar, + }, { + .name = "SA Insertion (reg) ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_reg_sai, + }, { + .name = "SA Replacement (reg)", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_reg_sar, + }, { + .name = "VLAN TX Insertion ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_vlanoff, + }, { + .name = "SVLAN TX Insertion ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_svlanoff, + }, { + .name = "L3 DA Filtering ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_l3filt_da, + }, { + .name = "L3 SA Filtering ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_l3filt_sa, + }, { + .name = "L4 DA TCP Filtering ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_l4filt_da_tcp, + }, { + .name = "L4 SA TCP Filtering ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_l4filt_sa_tcp, + }, { + .name = "L4 DA UDP Filtering ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_l4filt_da_udp, + }, { + .name = "L4 SA UDP Filtering ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_l4filt_sa_udp, + }, { + .name = "ARP Offload ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_arpoffload, + }, { + .name = "Jumbo Frame ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_jumbo, + }, { + .name = "Multichannel Jumbo ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_mjumbo, + }, { + .name = "Split Header ", + .lb = STMMAC_LOOPBACK_PHY, + .fn = stmmac_test_sph, }, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c index 6c305b6ecad0..e231098061b6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -242,9 +242,27 @@ static int tc_init(struct stmmac_priv *priv) { struct dma_features *dma_cap = &priv->dma_cap; unsigned int count; + int i; + + if (dma_cap->l3l4fnum) { + priv->flow_entries_max = dma_cap->l3l4fnum; + priv->flow_entries = devm_kcalloc(priv->device, + dma_cap->l3l4fnum, + sizeof(*priv->flow_entries), + GFP_KERNEL); + if (!priv->flow_entries) + return -ENOMEM; + for (i = 0; i < priv->flow_entries_max; i++) + priv->flow_entries[i].idx = i; + + dev_info(priv->device, "Enabled Flow TC (entries=%d)\n", + priv->flow_entries_max); + } + + /* Fail silently as we can still use remaining features, e.g. CBS */ if (!dma_cap->frpsel) - return -EINVAL; + return 0; switch (dma_cap->frpbs) { case 0x0: @@ -349,8 +367,235 @@ static int tc_setup_cbs(struct stmmac_priv *priv, return 0; } +static int tc_parse_flow_actions(struct stmmac_priv *priv, + struct flow_action *action, + struct stmmac_flow_entry *entry) +{ + struct flow_action_entry *act; + int i; + + if (!flow_action_has_entries(action)) + return -EINVAL; + + flow_action_for_each(i, act, action) { + switch (act->id) { + case FLOW_ACTION_DROP: + entry->action |= STMMAC_FLOW_ACTION_DROP; + return 0; + default: + break; + } + } + + /* Nothing to do, maybe inverse filter ? */ + return 0; +} + +static int tc_add_basic_flow(struct stmmac_priv *priv, + struct flow_cls_offload *cls, + struct stmmac_flow_entry *entry) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(cls); + struct flow_dissector *dissector = rule->match.dissector; + struct flow_match_basic match; + + /* Nothing to do here */ + if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_BASIC)) + return -EINVAL; + + flow_rule_match_basic(rule, &match); + entry->ip_proto = match.key->ip_proto; + return 0; +} + +static int tc_add_ip4_flow(struct stmmac_priv *priv, + struct flow_cls_offload *cls, + struct stmmac_flow_entry *entry) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(cls); + struct flow_dissector *dissector = rule->match.dissector; + bool inv = entry->action & STMMAC_FLOW_ACTION_DROP; + struct flow_match_ipv4_addrs match; + u32 hw_match; + int ret; + + /* Nothing to do here */ + if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_IPV4_ADDRS)) + return -EINVAL; + + flow_rule_match_ipv4_addrs(rule, &match); + hw_match = ntohl(match.key->src) & ntohl(match.mask->src); + if (hw_match) { + ret = stmmac_config_l3_filter(priv, priv->hw, entry->idx, true, + false, true, inv, hw_match); + if (ret) + return ret; + } + + hw_match = ntohl(match.key->dst) & ntohl(match.mask->dst); + if (hw_match) { + ret = stmmac_config_l3_filter(priv, priv->hw, entry->idx, true, + false, false, inv, hw_match); + if (ret) + return ret; + } + + return 0; +} + +static int tc_add_ports_flow(struct stmmac_priv *priv, + struct flow_cls_offload *cls, + struct stmmac_flow_entry *entry) +{ + struct flow_rule *rule = flow_cls_offload_flow_rule(cls); + struct flow_dissector *dissector = rule->match.dissector; + bool inv = entry->action & STMMAC_FLOW_ACTION_DROP; + struct flow_match_ports match; + u32 hw_match; + bool is_udp; + int ret; + + /* Nothing to do here */ + if (!dissector_uses_key(dissector, FLOW_DISSECTOR_KEY_PORTS)) + return -EINVAL; + + switch (entry->ip_proto) { + case IPPROTO_TCP: + is_udp = false; + break; + case IPPROTO_UDP: + is_udp = true; + break; + default: + return -EINVAL; + } + + flow_rule_match_ports(rule, &match); + + hw_match = ntohs(match.key->src) & ntohs(match.mask->src); + if (hw_match) { + ret = stmmac_config_l4_filter(priv, priv->hw, entry->idx, true, + is_udp, true, inv, hw_match); + if (ret) + return ret; + } + + hw_match = ntohs(match.key->dst) & ntohs(match.mask->dst); + if (hw_match) { + ret = stmmac_config_l4_filter(priv, priv->hw, entry->idx, true, + is_udp, false, inv, hw_match); + if (ret) + return ret; + } + + entry->is_l4 = true; + return 0; +} + +static struct stmmac_flow_entry *tc_find_flow(struct stmmac_priv *priv, + struct flow_cls_offload *cls, + bool get_free) +{ + int i; + + for (i = 0; i < priv->flow_entries_max; i++) { + struct stmmac_flow_entry *entry = &priv->flow_entries[i]; + + if (entry->cookie == cls->cookie) + return entry; + if (get_free && (entry->in_use == false)) + return entry; + } + + return NULL; +} + +struct { + int (*fn)(struct stmmac_priv *priv, struct flow_cls_offload *cls, + struct stmmac_flow_entry *entry); +} tc_flow_parsers[] = { + { .fn = tc_add_basic_flow }, + { .fn = tc_add_ip4_flow }, + { .fn = tc_add_ports_flow }, +}; + +static int tc_add_flow(struct stmmac_priv *priv, + struct flow_cls_offload *cls) +{ + struct stmmac_flow_entry *entry = tc_find_flow(priv, cls, false); + struct flow_rule *rule = flow_cls_offload_flow_rule(cls); + int i, ret; + + if (!entry) { + entry = tc_find_flow(priv, cls, true); + if (!entry) + return -ENOENT; + } + + ret = tc_parse_flow_actions(priv, &rule->action, entry); + if (ret) + return ret; + + for (i = 0; i < ARRAY_SIZE(tc_flow_parsers); i++) { + ret = tc_flow_parsers[i].fn(priv, cls, entry); + if (!ret) { + entry->in_use = true; + continue; + } + } + + if (!entry->in_use) + return -EINVAL; + + entry->cookie = cls->cookie; + return 0; +} + +static int tc_del_flow(struct stmmac_priv *priv, + struct flow_cls_offload *cls) +{ + struct stmmac_flow_entry *entry = tc_find_flow(priv, cls, false); + int ret; + + if (!entry || !entry->in_use) + return -ENOENT; + + if (entry->is_l4) { + ret = stmmac_config_l4_filter(priv, priv->hw, entry->idx, false, + false, false, false, 0); + } else { + ret = stmmac_config_l3_filter(priv, priv->hw, entry->idx, false, + false, false, false, 0); + } + + entry->in_use = false; + entry->cookie = 0; + entry->is_l4 = false; + return ret; +} + +static int tc_setup_cls(struct stmmac_priv *priv, + struct flow_cls_offload *cls) +{ + int ret = 0; + + switch (cls->command) { + case FLOW_CLS_REPLACE: + ret = tc_add_flow(priv, cls); + break; + case FLOW_CLS_DESTROY: + ret = tc_del_flow(priv, cls); + break; + default: + return -EOPNOTSUPP; + } + + return ret; +} + const struct stmmac_tc_ops dwmac510_tc_ops = { .init = tc_init, .setup_cls_u32 = tc_setup_cls_u32, .setup_cbs = tc_setup_cbs, + .setup_cls = tc_setup_cls, }; diff --git a/drivers/net/ethernet/sun/cassini.c b/drivers/net/ethernet/sun/cassini.c index 6fc05c106afc..c91876f8c536 100644 --- a/drivers/net/ethernet/sun/cassini.c +++ b/drivers/net/ethernet/sun/cassini.c @@ -2034,7 +2034,7 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, __skb_frag_set_page(frag, page->buffer); __skb_frag_ref(frag); - frag->page_offset = off; + skb_frag_off_set(frag, off); skb_frag_size_set(frag, hlen - swivel); /* any more data? */ @@ -2058,7 +2058,7 @@ static int cas_rx_process_pkt(struct cas *cp, struct cas_rx_comp *rxc, __skb_frag_set_page(frag, page->buffer); __skb_frag_ref(frag); - frag->page_offset = 0; + skb_frag_off_set(frag, 0); skb_frag_size_set(frag, hlen); RX_USED_ADD(page, hlen + cp->crc_size); } @@ -2816,7 +2816,7 @@ static inline int cas_xmit_tx_ringN(struct cas *cp, int ring, mapping = skb_frag_dma_map(&cp->pdev->dev, fragp, 0, len, DMA_TO_DEVICE); - tabort = cas_calc_tabort(cp, fragp->page_offset, len); + tabort = cas_calc_tabort(cp, skb_frag_off(fragp), len); if (unlikely(tabort)) { void *addr; @@ -2827,7 +2827,7 @@ static inline int cas_xmit_tx_ringN(struct cas *cp, int ring, addr = cas_page_map(skb_frag_page(fragp)); memcpy(tx_tiny_buf(cp, ring, entry), - addr + fragp->page_offset + len - tabort, + addr + skb_frag_off(fragp) + len - tabort, tabort); cas_page_unmap(addr); mapping = tx_tiny_map(cp, ring, entry, tentry); diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 0bc5863bffeb..f5fd1f3c07cc 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -6695,7 +6695,7 @@ static netdev_tx_t niu_start_xmit(struct sk_buff *skb, len = skb_frag_size(frag); mapping = np->ops->map_page(np->device, skb_frag_page(frag), - frag->page_offset, len, + skb_frag_off(frag), len, DMA_TO_DEVICE); rp->tx_buffs[prod].skb = NULL; diff --git a/drivers/net/ethernet/sun/sunvnet_common.c b/drivers/net/ethernet/sun/sunvnet_common.c index baa3088b475c..8b94d9ad9e2b 100644 --- a/drivers/net/ethernet/sun/sunvnet_common.c +++ b/drivers/net/ethernet/sun/sunvnet_common.c @@ -1088,7 +1088,7 @@ static inline int vnet_skb_map(struct ldc_channel *lp, struct sk_buff *skb, vaddr = kmap_atomic(skb_frag_page(f)); blen = skb_frag_size(f); blen += 8 - (blen & 7); - err = ldc_map_single(lp, vaddr + f->page_offset, + err = ldc_map_single(lp, vaddr + skb_frag_off(f), blen, cookies + nc, ncookies - nc, map_perm); kunmap_atomic(vaddr); @@ -1124,7 +1124,7 @@ static inline struct sk_buff *vnet_skb_shape(struct sk_buff *skb, int ncookies) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *f = &skb_shinfo(skb)->frags[i]; - docopy |= f->page_offset & 7; + docopy |= skb_frag_off(f) & 7; } if (((unsigned long)skb->data & 7) != VNET_PACKET_SKIP || skb_tailroom(skb) < pad || @@ -1532,8 +1532,7 @@ out_dropped: else if (port) del_timer(&port->clean_timer); rcu_read_unlock(); - if (skb) - dev_kfree_skb(skb); + dev_kfree_skb(skb); vnet_free_skbs(freeskbs); dev->stats.tx_dropped++; return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c index 031cf9c3435a..8c4195a9a2cc 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-desc.c @@ -503,7 +503,7 @@ static int xlgmac_map_tx_skb(struct xlgmac_channel *channel, struct xlgmac_desc_data *desc_data; unsigned int offset, datalen, len; struct xlgmac_pkt_info *pkt_info; - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned int tso, vlan; dma_addr_t skb_dma; unsigned int i; diff --git a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c index 1f8e9601592a..a1f5a1e61040 100644 --- a/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c +++ b/drivers/net/ethernet/synopsys/dwc-xlgmac-net.c @@ -116,7 +116,7 @@ static void xlgmac_prep_tx_pkt(struct xlgmac_pdata *pdata, struct sk_buff *skb, struct xlgmac_pkt_info *pkt_info) { - struct skb_frag_struct *frag; + skb_frag_t *frag; unsigned int context_desc; unsigned int len; unsigned int i; diff --git a/drivers/net/ethernet/tehuti/tehuti.c b/drivers/net/ethernet/tehuti/tehuti.c index 5d6960fe3309..0f8a924fc60c 100644 --- a/drivers/net/ethernet/tehuti/tehuti.c +++ b/drivers/net/ethernet/tehuti/tehuti.c @@ -1501,7 +1501,7 @@ bdx_tx_map_skb(struct bdx_priv *priv, struct sk_buff *skb, bdx_tx_db_inc_wptr(db); for (i = 0; i < nr_frags; i++) { - const struct skb_frag_struct *frag; + const skb_frag_t *frag; frag = &skb_shinfo(skb)->frags[i]; db->wptr->len = skb_frag_size(frag); diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index a46b8b2e44e1..f298d714efd6 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -2764,7 +2764,7 @@ static int cpsw_probe(struct platform_device *pdev) struct net_device *ndev; struct cpsw_priv *priv; void __iomem *ss_regs; - struct resource *res, *ss_res; + struct resource *ss_res; struct gpio_descs *mode; const struct soc_device_attribute *soc; struct cpsw_common *cpsw; @@ -2799,8 +2799,7 @@ static int cpsw_probe(struct platform_device *pdev) return PTR_ERR(ss_regs); cpsw->regs = ss_regs; - res = platform_get_resource(pdev, IORESOURCE_MEM, 1); - cpsw->wr_regs = devm_ioremap_resource(dev, res); + cpsw->wr_regs = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(cpsw->wr_regs)) return PTR_ERR(cpsw->wr_regs); diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index 642843945031..1b2702f74455 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1116,7 +1116,7 @@ netcp_tx_map_skb(struct sk_buff *skb, struct netcp_intf *netcp) for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; struct page *page = skb_frag_page(frag); - u32 page_offset = frag->page_offset; + u32 page_offset = skb_frag_off(frag); u32 buf_len = skb_frag_size(frag); dma_addr_t desc_dma; u32 desc_dma_32; diff --git a/drivers/net/ethernet/toshiba/spider_net.c b/drivers/net/ethernet/toshiba/spider_net.c index 0f346761a2b2..538e70810d3d 100644 --- a/drivers/net/ethernet/toshiba/spider_net.c +++ b/drivers/net/ethernet/toshiba/spider_net.c @@ -2311,11 +2311,9 @@ spider_net_alloc_card(void) { struct net_device *netdev; struct spider_net_card *card; - size_t alloc_size; - alloc_size = sizeof(struct spider_net_card) + - (tx_descriptors + rx_descriptors) * sizeof(struct spider_net_descr); - netdev = alloc_etherdev(alloc_size); + netdev = alloc_etherdev(struct_size(card, darray, + tx_descriptors + rx_descriptors)); if (!netdev) return NULL; diff --git a/drivers/net/ethernet/via/via-rhine.c b/drivers/net/ethernet/via/via-rhine.c index ab55416a10fa..ed12dbd156f0 100644 --- a/drivers/net/ethernet/via/via-rhine.c +++ b/drivers/net/ethernet/via/via-rhine.c @@ -1127,15 +1127,13 @@ static int rhine_init_one_platform(struct platform_device *pdev) const struct of_device_id *match; const u32 *quirks; int irq; - struct resource *res; void __iomem *ioaddr; match = of_match_device(rhine_of_tbl, &pdev->dev); if (!match) return -EINVAL; - res = platform_get_resource(pdev, IORESOURCE_MEM, 0); - ioaddr = devm_ioremap_resource(&pdev->dev, res); + ioaddr = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(ioaddr)) return PTR_ERR(ioaddr); |