diff options
Diffstat (limited to 'drivers/net/ethernet/sfc')
28 files changed, 4154 insertions, 1556 deletions
diff --git a/drivers/net/ethernet/sfc/Kconfig b/drivers/net/ethernet/sfc/Kconfig index 8b7152565c5..08892129444 100644 --- a/drivers/net/ethernet/sfc/Kconfig +++ b/drivers/net/ethernet/sfc/Kconfig @@ -7,7 +7,7 @@ config SFC select I2C_ALGOBIT select PTP_1588_CLOCK ---help--- - This driver supports 10-gigabit Ethernet cards based on + This driver supports 10/40-gigabit Ethernet cards based on the Solarflare SFC4000, SFC9000-family and SFC9100-family controllers. diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 5f42313b496..b5ed30a3914 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -14,6 +14,7 @@ #include "mcdi_pcol.h" #include "nic.h" #include "workarounds.h" +#include "selftest.h" #include <linux/in.h> #include <linux/jhash.h> #include <linux/wait.h> @@ -52,31 +53,31 @@ struct efx_ef10_filter_table { struct { unsigned long spec; /* pointer to spec plus flag bits */ -/* BUSY flag indicates that an update is in progress. STACK_OLD is - * used to mark and sweep stack-owned MAC filters. +/* BUSY flag indicates that an update is in progress. AUTO_OLD is + * used to mark and sweep MAC filters for the device address lists. */ #define EFX_EF10_FILTER_FLAG_BUSY 1UL -#define EFX_EF10_FILTER_FLAG_STACK_OLD 2UL +#define EFX_EF10_FILTER_FLAG_AUTO_OLD 2UL #define EFX_EF10_FILTER_FLAGS 3UL u64 handle; /* firmware handle */ } *entry; wait_queue_head_t waitq; /* Shadow of net_device address lists, guarded by mac_lock */ -#define EFX_EF10_FILTER_STACK_UC_MAX 32 -#define EFX_EF10_FILTER_STACK_MC_MAX 256 +#define EFX_EF10_FILTER_DEV_UC_MAX 32 +#define EFX_EF10_FILTER_DEV_MC_MAX 256 struct { u8 addr[ETH_ALEN]; u16 id; - } stack_uc_list[EFX_EF10_FILTER_STACK_UC_MAX], - stack_mc_list[EFX_EF10_FILTER_STACK_MC_MAX]; - int stack_uc_count; /* negative for PROMISC */ - int stack_mc_count; /* negative for PROMISC/ALLMULTI */ + } dev_uc_list[EFX_EF10_FILTER_DEV_UC_MAX], + dev_mc_list[EFX_EF10_FILTER_DEV_MC_MAX]; + int dev_uc_count; /* negative for PROMISC */ + int dev_mc_count; /* negative for PROMISC/ALLMULTI */ }; /* An arbitrary search limit for the software hash table */ #define EFX_EF10_FILTER_SEARCH_LIMIT 200 -static void efx_ef10_rx_push_indir_table(struct efx_nic *efx); +static void efx_ef10_rx_push_rss_config(struct efx_nic *efx); static void efx_ef10_rx_free_indir_table(struct efx_nic *efx); static void efx_ef10_filter_table_remove(struct efx_nic *efx); @@ -94,7 +95,7 @@ static unsigned int efx_ef10_mem_map_size(struct efx_nic *efx) return resource_size(&efx->pci_dev->resource[EFX_MEM_BAR]); } -static int efx_ef10_init_capabilities(struct efx_nic *efx) +static int efx_ef10_init_datapath_caps(struct efx_nic *efx) { MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CAPABILITIES_OUT_LEN); struct efx_ef10_nic_data *nic_data = efx->nic_data; @@ -107,16 +108,27 @@ static int efx_ef10_init_capabilities(struct efx_nic *efx) outbuf, sizeof(outbuf), &outlen); if (rc) return rc; + if (outlen < sizeof(outbuf)) { + netif_err(efx, drv, efx->net_dev, + "unable to read datapath firmware capabilities\n"); + return -EIO; + } - if (outlen >= sizeof(outbuf)) { - nic_data->datapath_caps = - MCDI_DWORD(outbuf, GET_CAPABILITIES_OUT_FLAGS1); - if (!(nic_data->datapath_caps & - (1 << MC_CMD_GET_CAPABILITIES_OUT_TX_TSO_LBN))) { - netif_err(efx, drv, efx->net_dev, - "Capabilities don't indicate TSO support.\n"); - return -ENODEV; - } + nic_data->datapath_caps = + MCDI_DWORD(outbuf, GET_CAPABILITIES_OUT_FLAGS1); + + if (!(nic_data->datapath_caps & + (1 << MC_CMD_GET_CAPABILITIES_OUT_TX_TSO_LBN))) { + netif_err(efx, drv, efx->net_dev, + "current firmware does not support TSO\n"); + return -ENODEV; + } + + if (!(nic_data->datapath_caps & + (1 << MC_CMD_GET_CAPABILITIES_OUT_RX_PREFIX_LEN_14_LBN))) { + netif_err(efx, probe, efx->net_dev, + "current firmware does not support an RX prefix\n"); + return -ENODEV; } return 0; @@ -150,8 +162,8 @@ static int efx_ef10_get_mac_address(struct efx_nic *efx, u8 *mac_address) if (outlen < MC_CMD_GET_MAC_ADDRESSES_OUT_LEN) return -EIO; - memcpy(mac_address, - MCDI_PTR(outbuf, GET_MAC_ADDRESSES_OUT_MAC_ADDR_BASE), ETH_ALEN); + ether_addr_copy(mac_address, + MCDI_PTR(outbuf, GET_MAC_ADDRESSES_OUT_MAC_ADDR_BASE)); return 0; } @@ -160,8 +172,8 @@ static int efx_ef10_probe(struct efx_nic *efx) struct efx_ef10_nic_data *nic_data; int i, rc; - /* We can have one VI for each 8K region. However we need - * multiple TX queues per channel. + /* We can have one VI for each 8K region. However, until we + * use TX option descriptors we need two TX queues per channel. */ efx->max_channels = min_t(unsigned int, @@ -217,21 +229,13 @@ static int efx_ef10_probe(struct efx_nic *efx) if (rc) goto fail3; - rc = efx_ef10_init_capabilities(efx); + rc = efx_ef10_init_datapath_caps(efx); if (rc < 0) goto fail3; efx->rx_packet_len_offset = ES_DZ_RX_PREFIX_PKTLEN_OFST - ES_DZ_RX_PREFIX_SIZE; - if (!(nic_data->datapath_caps & - (1 << MC_CMD_GET_CAPABILITIES_OUT_RX_PREFIX_LEN_14_LBN))) { - netif_err(efx, probe, efx->net_dev, - "current firmware does not support an RX prefix\n"); - rc = -ENODEV; - goto fail3; - } - rc = efx_mcdi_port_get_number(efx); if (rc < 0) goto fail3; @@ -260,7 +264,7 @@ static int efx_ef10_probe(struct efx_nic *efx) if (rc) goto fail3; - efx_ptp_probe(efx); + efx_ptp_probe(efx, NULL); return 0; @@ -276,27 +280,215 @@ fail1: static int efx_ef10_free_vis(struct efx_nic *efx) { - int rc = efx_mcdi_rpc(efx, MC_CMD_FREE_VIS, NULL, 0, NULL, 0, NULL); + MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, 0); + size_t outlen; + int rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FREE_VIS, NULL, 0, + outbuf, sizeof(outbuf), &outlen); /* -EALREADY means nothing to free, so ignore */ if (rc == -EALREADY) rc = 0; + if (rc) + efx_mcdi_display_error(efx, MC_CMD_FREE_VIS, 0, outbuf, outlen, + rc); + return rc; +} + +#ifdef EFX_USE_PIO + +static void efx_ef10_free_piobufs(struct efx_nic *efx) +{ + struct efx_ef10_nic_data *nic_data = efx->nic_data; + MCDI_DECLARE_BUF(inbuf, MC_CMD_FREE_PIOBUF_IN_LEN); + unsigned int i; + int rc; + + BUILD_BUG_ON(MC_CMD_FREE_PIOBUF_OUT_LEN != 0); + + for (i = 0; i < nic_data->n_piobufs; i++) { + MCDI_SET_DWORD(inbuf, FREE_PIOBUF_IN_PIOBUF_HANDLE, + nic_data->piobuf_handle[i]); + rc = efx_mcdi_rpc(efx, MC_CMD_FREE_PIOBUF, inbuf, sizeof(inbuf), + NULL, 0, NULL); + WARN_ON(rc); + } + + nic_data->n_piobufs = 0; +} + +static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n) +{ + struct efx_ef10_nic_data *nic_data = efx->nic_data; + MCDI_DECLARE_BUF(outbuf, MC_CMD_ALLOC_PIOBUF_OUT_LEN); + unsigned int i; + size_t outlen; + int rc = 0; + + BUILD_BUG_ON(MC_CMD_ALLOC_PIOBUF_IN_LEN != 0); + + for (i = 0; i < n; i++) { + rc = efx_mcdi_rpc(efx, MC_CMD_ALLOC_PIOBUF, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (rc) + break; + if (outlen < MC_CMD_ALLOC_PIOBUF_OUT_LEN) { + rc = -EIO; + break; + } + nic_data->piobuf_handle[i] = + MCDI_DWORD(outbuf, ALLOC_PIOBUF_OUT_PIOBUF_HANDLE); + netif_dbg(efx, probe, efx->net_dev, + "allocated PIO buffer %u handle %x\n", i, + nic_data->piobuf_handle[i]); + } + + nic_data->n_piobufs = i; + if (rc) + efx_ef10_free_piobufs(efx); + return rc; +} + +static int efx_ef10_link_piobufs(struct efx_nic *efx) +{ + struct efx_ef10_nic_data *nic_data = efx->nic_data; + MCDI_DECLARE_BUF(inbuf, + max(MC_CMD_LINK_PIOBUF_IN_LEN, + MC_CMD_UNLINK_PIOBUF_IN_LEN)); + struct efx_channel *channel; + struct efx_tx_queue *tx_queue; + unsigned int offset, index; + int rc; + + BUILD_BUG_ON(MC_CMD_LINK_PIOBUF_OUT_LEN != 0); + BUILD_BUG_ON(MC_CMD_UNLINK_PIOBUF_OUT_LEN != 0); + + /* Link a buffer to each VI in the write-combining mapping */ + for (index = 0; index < nic_data->n_piobufs; ++index) { + MCDI_SET_DWORD(inbuf, LINK_PIOBUF_IN_PIOBUF_HANDLE, + nic_data->piobuf_handle[index]); + MCDI_SET_DWORD(inbuf, LINK_PIOBUF_IN_TXQ_INSTANCE, + nic_data->pio_write_vi_base + index); + rc = efx_mcdi_rpc(efx, MC_CMD_LINK_PIOBUF, + inbuf, MC_CMD_LINK_PIOBUF_IN_LEN, + NULL, 0, NULL); + if (rc) { + netif_err(efx, drv, efx->net_dev, + "failed to link VI %u to PIO buffer %u (%d)\n", + nic_data->pio_write_vi_base + index, index, + rc); + goto fail; + } + netif_dbg(efx, probe, efx->net_dev, + "linked VI %u to PIO buffer %u\n", + nic_data->pio_write_vi_base + index, index); + } + + /* Link a buffer to each TX queue */ + efx_for_each_channel(channel, efx) { + efx_for_each_channel_tx_queue(tx_queue, channel) { + /* We assign the PIO buffers to queues in + * reverse order to allow for the following + * special case. + */ + offset = ((efx->tx_channel_offset + efx->n_tx_channels - + tx_queue->channel->channel - 1) * + efx_piobuf_size); + index = offset / ER_DZ_TX_PIOBUF_SIZE; + offset = offset % ER_DZ_TX_PIOBUF_SIZE; + + /* When the host page size is 4K, the first + * host page in the WC mapping may be within + * the same VI page as the last TX queue. We + * can only link one buffer to each VI. + */ + if (tx_queue->queue == nic_data->pio_write_vi_base) { + BUG_ON(index != 0); + rc = 0; + } else { + MCDI_SET_DWORD(inbuf, + LINK_PIOBUF_IN_PIOBUF_HANDLE, + nic_data->piobuf_handle[index]); + MCDI_SET_DWORD(inbuf, + LINK_PIOBUF_IN_TXQ_INSTANCE, + tx_queue->queue); + rc = efx_mcdi_rpc(efx, MC_CMD_LINK_PIOBUF, + inbuf, MC_CMD_LINK_PIOBUF_IN_LEN, + NULL, 0, NULL); + } + + if (rc) { + /* This is non-fatal; the TX path just + * won't use PIO for this queue + */ + netif_err(efx, drv, efx->net_dev, + "failed to link VI %u to PIO buffer %u (%d)\n", + tx_queue->queue, index, rc); + tx_queue->piobuf = NULL; + } else { + tx_queue->piobuf = + nic_data->pio_write_base + + index * EFX_VI_PAGE_SIZE + offset; + tx_queue->piobuf_offset = offset; + netif_dbg(efx, probe, efx->net_dev, + "linked VI %u to PIO buffer %u offset %x addr %p\n", + tx_queue->queue, index, + tx_queue->piobuf_offset, + tx_queue->piobuf); + } + } + } + + return 0; + +fail: + while (index--) { + MCDI_SET_DWORD(inbuf, UNLINK_PIOBUF_IN_TXQ_INSTANCE, + nic_data->pio_write_vi_base + index); + efx_mcdi_rpc(efx, MC_CMD_UNLINK_PIOBUF, + inbuf, MC_CMD_UNLINK_PIOBUF_IN_LEN, + NULL, 0, NULL); + } return rc; } +#else /* !EFX_USE_PIO */ + +static int efx_ef10_alloc_piobufs(struct efx_nic *efx, unsigned int n) +{ + return n == 0 ? 0 : -ENOBUFS; +} + +static int efx_ef10_link_piobufs(struct efx_nic *efx) +{ + return 0; +} + +static void efx_ef10_free_piobufs(struct efx_nic *efx) +{ +} + +#endif /* EFX_USE_PIO */ + static void efx_ef10_remove(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data = efx->nic_data; int rc; + efx_ptp_remove(efx); + efx_mcdi_mon_remove(efx); - /* This needs to be after efx_ptp_remove_channel() with no filters */ efx_ef10_rx_free_indir_table(efx); + if (nic_data->wc_membase) + iounmap(nic_data->wc_membase); + rc = efx_ef10_free_vis(efx); WARN_ON(rc != 0); + if (!nic_data->must_restore_piobufs) + efx_ef10_free_piobufs(efx); + efx_mcdi_fini(efx); efx_nic_free_buffer(efx, &nic_data->mcdi_buf); kfree(nic_data); @@ -329,12 +521,133 @@ static int efx_ef10_alloc_vis(struct efx_nic *efx, return 0; } +/* Note that the failure path of this function does not free + * resources, as this will be done by efx_ef10_remove(). + */ static int efx_ef10_dimension_resources(struct efx_nic *efx) { - unsigned int n_vis = - max(efx->n_channels, efx->n_tx_channels * EFX_TXQ_TYPES); + struct efx_ef10_nic_data *nic_data = efx->nic_data; + unsigned int uc_mem_map_size, wc_mem_map_size; + unsigned int min_vis, pio_write_vi_base, max_vis; + void __iomem *membase; + int rc; + + min_vis = max(efx->n_channels, efx->n_tx_channels * EFX_TXQ_TYPES); - return efx_ef10_alloc_vis(efx, n_vis, n_vis); +#ifdef EFX_USE_PIO + /* Try to allocate PIO buffers if wanted and if the full + * number of PIO buffers would be sufficient to allocate one + * copy-buffer per TX channel. Failure is non-fatal, as there + * are only a small number of PIO buffers shared between all + * functions of the controller. + */ + if (efx_piobuf_size != 0 && + ER_DZ_TX_PIOBUF_SIZE / efx_piobuf_size * EF10_TX_PIOBUF_COUNT >= + efx->n_tx_channels) { + unsigned int n_piobufs = + DIV_ROUND_UP(efx->n_tx_channels, + ER_DZ_TX_PIOBUF_SIZE / efx_piobuf_size); + + rc = efx_ef10_alloc_piobufs(efx, n_piobufs); + if (rc) + netif_err(efx, probe, efx->net_dev, + "failed to allocate PIO buffers (%d)\n", rc); + else + netif_dbg(efx, probe, efx->net_dev, + "allocated %u PIO buffers\n", n_piobufs); + } +#else + nic_data->n_piobufs = 0; +#endif + + /* PIO buffers should be mapped with write-combining enabled, + * and we want to make single UC and WC mappings rather than + * several of each (in fact that's the only option if host + * page size is >4K). So we may allocate some extra VIs just + * for writing PIO buffers through. + * + * The UC mapping contains (min_vis - 1) complete VIs and the + * first half of the next VI. Then the WC mapping begins with + * the second half of this last VI. + */ + uc_mem_map_size = PAGE_ALIGN((min_vis - 1) * EFX_VI_PAGE_SIZE + + ER_DZ_TX_PIOBUF); + if (nic_data->n_piobufs) { + /* pio_write_vi_base rounds down to give the number of complete + * VIs inside the UC mapping. + */ + pio_write_vi_base = uc_mem_map_size / EFX_VI_PAGE_SIZE; + wc_mem_map_size = (PAGE_ALIGN((pio_write_vi_base + + nic_data->n_piobufs) * + EFX_VI_PAGE_SIZE) - + uc_mem_map_size); + max_vis = pio_write_vi_base + nic_data->n_piobufs; + } else { + pio_write_vi_base = 0; + wc_mem_map_size = 0; + max_vis = min_vis; + } + + /* In case the last attached driver failed to free VIs, do it now */ + rc = efx_ef10_free_vis(efx); + if (rc != 0) + return rc; + + rc = efx_ef10_alloc_vis(efx, min_vis, max_vis); + if (rc != 0) + return rc; + + /* If we didn't get enough VIs to map all the PIO buffers, free the + * PIO buffers + */ + if (nic_data->n_piobufs && + nic_data->n_allocated_vis < + pio_write_vi_base + nic_data->n_piobufs) { + netif_dbg(efx, probe, efx->net_dev, + "%u VIs are not sufficient to map %u PIO buffers\n", + nic_data->n_allocated_vis, nic_data->n_piobufs); + efx_ef10_free_piobufs(efx); + } + + /* Shrink the original UC mapping of the memory BAR */ + membase = ioremap_nocache(efx->membase_phys, uc_mem_map_size); + if (!membase) { + netif_err(efx, probe, efx->net_dev, + "could not shrink memory BAR to %x\n", + uc_mem_map_size); + return -ENOMEM; + } + iounmap(efx->membase); + efx->membase = membase; + + /* Set up the WC mapping if needed */ + if (wc_mem_map_size) { + nic_data->wc_membase = ioremap_wc(efx->membase_phys + + uc_mem_map_size, + wc_mem_map_size); + if (!nic_data->wc_membase) { + netif_err(efx, probe, efx->net_dev, + "could not allocate WC mapping of size %x\n", + wc_mem_map_size); + return -ENOMEM; + } + nic_data->pio_write_vi_base = pio_write_vi_base; + nic_data->pio_write_base = + nic_data->wc_membase + + (pio_write_vi_base * EFX_VI_PAGE_SIZE + ER_DZ_TX_PIOBUF - + uc_mem_map_size); + + rc = efx_ef10_link_piobufs(efx); + if (rc) + efx_ef10_free_piobufs(efx); + } + + netif_dbg(efx, probe, efx->net_dev, + "memory BAR at %pa (virtual %p+%x UC, %p+%x WC)\n", + &efx->membase_phys, efx->membase, uc_mem_map_size, + nic_data->wc_membase, wc_mem_map_size); + + return 0; } static int efx_ef10_init_nic(struct efx_nic *efx) @@ -342,6 +655,13 @@ static int efx_ef10_init_nic(struct efx_nic *efx) struct efx_ef10_nic_data *nic_data = efx->nic_data; int rc; + if (nic_data->must_check_datapath_caps) { + rc = efx_ef10_init_datapath_caps(efx); + if (rc) + return rc; + nic_data->must_check_datapath_caps = false; + } + if (nic_data->must_realloc_vis) { /* We cannot let the number of VIs change now */ rc = efx_ef10_alloc_vis(efx, nic_data->n_allocated_vis, @@ -351,10 +671,36 @@ static int efx_ef10_init_nic(struct efx_nic *efx) nic_data->must_realloc_vis = false; } - efx_ef10_rx_push_indir_table(efx); + if (nic_data->must_restore_piobufs && nic_data->n_piobufs) { + rc = efx_ef10_alloc_piobufs(efx, nic_data->n_piobufs); + if (rc == 0) { + rc = efx_ef10_link_piobufs(efx); + if (rc) + efx_ef10_free_piobufs(efx); + } + + /* Log an error on failure, but this is non-fatal */ + if (rc) + netif_err(efx, drv, efx->net_dev, + "failed to restore PIO buffers (%d)\n", rc); + nic_data->must_restore_piobufs = false; + } + + efx_ef10_rx_push_rss_config(efx); return 0; } +static void efx_ef10_reset_mc_allocations(struct efx_nic *efx) +{ + struct efx_ef10_nic_data *nic_data = efx->nic_data; + + /* All our allocations have been reset */ + nic_data->must_realloc_vis = true; + nic_data->must_restore_filters = true; + nic_data->must_restore_piobufs = true; + nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID; +} + static int efx_ef10_map_reset_flags(u32 *flags) { enum { @@ -385,6 +731,22 @@ static int efx_ef10_map_reset_flags(u32 *flags) return -EINVAL; } +static int efx_ef10_reset(struct efx_nic *efx, enum reset_type reset_type) +{ + int rc = efx_mcdi_reset(efx, reset_type); + + /* If it was a port reset, trigger reallocation of MC resources. + * Note that on an MC reset nothing needs to be done now because we'll + * detect the MC reset later and handle it then. + * For an FLR, we never get an MC reset event, but the MC has reset all + * resources assigned to us, so we have to trigger reallocation now. + */ + if ((reset_type == RESET_TYPE_ALL || + reset_type == RESET_TYPE_MCDI_TIMEOUT) && !rc) + efx_ef10_reset_mc_allocations(efx); + return rc; +} + #define EF10_DMA_STAT(ext_name, mcdi_name) \ [EF10_STAT_ ## ext_name] = \ { #ext_name, 64, 8 * MC_CMD_MAC_ ## mcdi_name } @@ -436,6 +798,18 @@ static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = { EF10_DMA_STAT(rx_align_error, RX_ALIGN_ERROR_PKTS), EF10_DMA_STAT(rx_length_error, RX_LENGTH_ERROR_PKTS), EF10_DMA_STAT(rx_nodesc_drops, RX_NODESC_DROPS), + EF10_DMA_STAT(rx_pm_trunc_bb_overflow, PM_TRUNC_BB_OVERFLOW), + EF10_DMA_STAT(rx_pm_discard_bb_overflow, PM_DISCARD_BB_OVERFLOW), + EF10_DMA_STAT(rx_pm_trunc_vfifo_full, PM_TRUNC_VFIFO_FULL), + EF10_DMA_STAT(rx_pm_discard_vfifo_full, PM_DISCARD_VFIFO_FULL), + EF10_DMA_STAT(rx_pm_trunc_qbb, PM_TRUNC_QBB), + EF10_DMA_STAT(rx_pm_discard_qbb, PM_DISCARD_QBB), + EF10_DMA_STAT(rx_pm_discard_mapping, PM_DISCARD_MAPPING), + EF10_DMA_STAT(rx_dp_q_disabled_packets, RXDP_Q_DISABLED_PKTS), + EF10_DMA_STAT(rx_dp_di_dropped_packets, RXDP_DI_DROPPED_PKTS), + EF10_DMA_STAT(rx_dp_streaming_packets, RXDP_STREAMING_PKTS), + EF10_DMA_STAT(rx_dp_hlb_fetch, RXDP_EMERGENCY_FETCH_CONDITIONS), + EF10_DMA_STAT(rx_dp_hlb_wait, RXDP_EMERGENCY_WAIT_CONDITIONS), }; #define HUNT_COMMON_STAT_MASK ((1ULL << EF10_STAT_tx_bytes) | \ @@ -490,44 +864,72 @@ static const struct efx_hw_stat_desc efx_ef10_stat_desc[EF10_STAT_COUNT] = { #define HUNT_40G_EXTRA_STAT_MASK ((1ULL << EF10_STAT_rx_align_error) | \ (1ULL << EF10_STAT_rx_length_error)) -#if BITS_PER_LONG == 64 -#define STAT_MASK_BITMAP(bits) (bits) -#else -#define STAT_MASK_BITMAP(bits) (bits) & 0xffffffff, (bits) >> 32 -#endif - -static const unsigned long *efx_ef10_stat_mask(struct efx_nic *efx) -{ - static const unsigned long hunt_40g_stat_mask[] = { - STAT_MASK_BITMAP(HUNT_COMMON_STAT_MASK | - HUNT_40G_EXTRA_STAT_MASK) - }; - static const unsigned long hunt_10g_only_stat_mask[] = { - STAT_MASK_BITMAP(HUNT_COMMON_STAT_MASK | - HUNT_10G_ONLY_STAT_MASK) - }; +/* These statistics are only provided if the firmware supports the + * capability PM_AND_RXDP_COUNTERS. + */ +#define HUNT_PM_AND_RXDP_STAT_MASK ( \ + (1ULL << EF10_STAT_rx_pm_trunc_bb_overflow) | \ + (1ULL << EF10_STAT_rx_pm_discard_bb_overflow) | \ + (1ULL << EF10_STAT_rx_pm_trunc_vfifo_full) | \ + (1ULL << EF10_STAT_rx_pm_discard_vfifo_full) | \ + (1ULL << EF10_STAT_rx_pm_trunc_qbb) | \ + (1ULL << EF10_STAT_rx_pm_discard_qbb) | \ + (1ULL << EF10_STAT_rx_pm_discard_mapping) | \ + (1ULL << EF10_STAT_rx_dp_q_disabled_packets) | \ + (1ULL << EF10_STAT_rx_dp_di_dropped_packets) | \ + (1ULL << EF10_STAT_rx_dp_streaming_packets) | \ + (1ULL << EF10_STAT_rx_dp_hlb_fetch) | \ + (1ULL << EF10_STAT_rx_dp_hlb_wait)) + +static u64 efx_ef10_raw_stat_mask(struct efx_nic *efx) +{ + u64 raw_mask = HUNT_COMMON_STAT_MASK; u32 port_caps = efx_mcdi_phy_get_caps(efx); + struct efx_ef10_nic_data *nic_data = efx->nic_data; if (port_caps & (1 << MC_CMD_PHY_CAP_40000FDX_LBN)) - return hunt_40g_stat_mask; + raw_mask |= HUNT_40G_EXTRA_STAT_MASK; else - return hunt_10g_only_stat_mask; + raw_mask |= HUNT_10G_ONLY_STAT_MASK; + + if (nic_data->datapath_caps & + (1 << MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_LBN)) + raw_mask |= HUNT_PM_AND_RXDP_STAT_MASK; + + return raw_mask; +} + +static void efx_ef10_get_stat_mask(struct efx_nic *efx, unsigned long *mask) +{ + u64 raw_mask = efx_ef10_raw_stat_mask(efx); + +#if BITS_PER_LONG == 64 + mask[0] = raw_mask; +#else + mask[0] = raw_mask & 0xffffffff; + mask[1] = raw_mask >> 32; +#endif } static size_t efx_ef10_describe_stats(struct efx_nic *efx, u8 *names) { + DECLARE_BITMAP(mask, EF10_STAT_COUNT); + + efx_ef10_get_stat_mask(efx, mask); return efx_nic_describe_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, - efx_ef10_stat_mask(efx), names); + mask, names); } static int efx_ef10_try_update_nic_stats(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data = efx->nic_data; - const unsigned long *stats_mask = efx_ef10_stat_mask(efx); + DECLARE_BITMAP(mask, EF10_STAT_COUNT); __le64 generation_start, generation_end; u64 *stats = nic_data->stats; __le64 *dma_stats; + efx_ef10_get_stat_mask(efx, mask); + dma_stats = efx->stats_buffer.addr; nic_data = efx->nic_data; @@ -535,13 +937,15 @@ static int efx_ef10_try_update_nic_stats(struct efx_nic *efx) if (generation_end == EFX_MC_STATS_GENERATION_INVALID) return 0; rmb(); - efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, stats_mask, + efx_nic_update_stats(efx_ef10_stat_desc, EF10_STAT_COUNT, mask, stats, efx->stats_buffer.addr, false); + rmb(); generation_start = dma_stats[MC_CMD_MAC_GENERATION_START]; if (generation_end != generation_start) return -EAGAIN; /* Update derived statistics */ + efx_nic_fix_nodesc_drop_stat(efx, &stats[EF10_STAT_rx_nodesc_drops]); stats[EF10_STAT_rx_good_bytes] = stats[EF10_STAT_rx_bytes] - stats[EF10_STAT_rx_bytes_minus_good_bytes]; @@ -555,12 +959,14 @@ static int efx_ef10_try_update_nic_stats(struct efx_nic *efx) static size_t efx_ef10_update_stats(struct efx_nic *efx, u64 *full_stats, struct rtnl_link_stats64 *core_stats) { - const unsigned long *mask = efx_ef10_stat_mask(efx); + DECLARE_BITMAP(mask, EF10_STAT_COUNT); struct efx_ef10_nic_data *nic_data = efx->nic_data; u64 *stats = nic_data->stats; size_t stats_count = 0, index; int retry; + efx_ef10_get_stat_mask(efx, mask); + /* If we're unlucky enough to read statistics during the DMA, wait * up to 10ms for it to finish (typically takes <500us) */ @@ -706,9 +1112,15 @@ static int efx_ef10_mcdi_poll_reboot(struct efx_nic *efx) nic_data->warm_boot_count = rc; /* All our allocations have been reset */ - nic_data->must_realloc_vis = true; - nic_data->must_restore_filters = true; - nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID; + efx_ef10_reset_mc_allocations(efx); + + /* The datapath firmware might have been changed */ + nic_data->must_check_datapath_caps = true; + + /* MAC statistics have been cleared on the NIC; clear the local + * statistic that we update with efx_update_diff_stat(). + */ + nic_data->stats[EF10_STAT_rx_bad_bytes] = 0; return -EIO; } @@ -871,8 +1283,8 @@ static void efx_ef10_tx_init(struct efx_tx_queue *tx_queue) return; fail: - WARN_ON(true); - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); + netdev_WARN(efx->net_dev, "failed to initialise TXQ %d\n", + tx_queue->queue); } static void efx_ef10_tx_fini(struct efx_tx_queue *tx_queue) @@ -886,7 +1298,7 @@ static void efx_ef10_tx_fini(struct efx_tx_queue *tx_queue) MCDI_SET_DWORD(inbuf, FINI_TXQ_IN_INSTANCE, tx_queue->queue); - rc = efx_mcdi_rpc(efx, MC_CMD_FINI_TXQ, inbuf, sizeof(inbuf), + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_TXQ, inbuf, sizeof(inbuf), outbuf, sizeof(outbuf), &outlen); if (rc && rc != -EALREADY) @@ -895,7 +1307,8 @@ static void efx_ef10_tx_fini(struct efx_tx_queue *tx_queue) return; fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); + efx_mcdi_display_error(efx, MC_CMD_FINI_TXQ, MC_CMD_FINI_TXQ_IN_LEN, + outbuf, outlen, rc); } static void efx_ef10_tx_remove(struct efx_tx_queue *tx_queue) @@ -1038,12 +1451,12 @@ static void efx_ef10_rx_free_indir_table(struct efx_nic *efx) nic_data->rx_rss_context = EFX_EF10_RSS_CONTEXT_INVALID; } -static void efx_ef10_rx_push_indir_table(struct efx_nic *efx) +static void efx_ef10_rx_push_rss_config(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data = efx->nic_data; int rc; - netif_dbg(efx, drv, efx->net_dev, "pushing RX indirection table\n"); + netif_dbg(efx, drv, efx->net_dev, "pushing RSS config\n"); if (nic_data->rx_rss_context == EFX_EF10_RSS_CONTEXT_INVALID) { rc = efx_ef10_alloc_rss_context(efx, &nic_data->rx_rss_context); @@ -1091,8 +1504,9 @@ static void efx_ef10_rx_init(struct efx_rx_queue *rx_queue) MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_LABEL, efx_rx_queue_index(rx_queue)); MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_INSTANCE, efx_rx_queue_index(rx_queue)); - MCDI_POPULATE_DWORD_1(inbuf, INIT_RXQ_IN_FLAGS, - INIT_RXQ_IN_FLAG_PREFIX, 1); + MCDI_POPULATE_DWORD_2(inbuf, INIT_RXQ_IN_FLAGS, + INIT_RXQ_IN_FLAG_PREFIX, 1, + INIT_RXQ_IN_FLAG_TIMESTAMP, 1); MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_OWNER_ID, 0); MCDI_SET_DWORD(inbuf, INIT_RXQ_IN_PORT_ID, EVB_PORT_ID_ASSIGNED); @@ -1111,13 +1525,8 @@ static void efx_ef10_rx_init(struct efx_rx_queue *rx_queue) rc = efx_mcdi_rpc(efx, MC_CMD_INIT_RXQ, inbuf, inlen, outbuf, sizeof(outbuf), &outlen); if (rc) - goto fail; - - return; - -fail: - WARN_ON(true); - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); + netdev_WARN(efx->net_dev, "failed to initialise RXQ %d\n", + efx_rx_queue_index(rx_queue)); } static void efx_ef10_rx_fini(struct efx_rx_queue *rx_queue) @@ -1131,7 +1540,7 @@ static void efx_ef10_rx_fini(struct efx_rx_queue *rx_queue) MCDI_SET_DWORD(inbuf, FINI_RXQ_IN_INSTANCE, efx_rx_queue_index(rx_queue)); - rc = efx_mcdi_rpc(efx, MC_CMD_FINI_RXQ, inbuf, sizeof(inbuf), + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_RXQ, inbuf, sizeof(inbuf), outbuf, sizeof(outbuf), &outlen); if (rc && rc != -EALREADY) @@ -1140,7 +1549,8 @@ static void efx_ef10_rx_fini(struct efx_rx_queue *rx_queue) return; fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); + efx_mcdi_display_error(efx, MC_CMD_FINI_RXQ, MC_CMD_FINI_RXQ_IN_LEN, + outbuf, outlen, rc); } static void efx_ef10_rx_remove(struct efx_rx_queue *rx_queue) @@ -1277,15 +1687,7 @@ static int efx_ef10_ev_init(struct efx_channel *channel) rc = efx_mcdi_rpc(efx, MC_CMD_INIT_EVQ, inbuf, inlen, outbuf, sizeof(outbuf), &outlen); - if (rc) - goto fail; - /* IRQ return is ignored */ - - return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); return rc; } @@ -1299,7 +1701,7 @@ static void efx_ef10_ev_fini(struct efx_channel *channel) MCDI_SET_DWORD(inbuf, FINI_EVQ_IN_INSTANCE, channel->channel); - rc = efx_mcdi_rpc(efx, MC_CMD_FINI_EVQ, inbuf, sizeof(inbuf), + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_FINI_EVQ, inbuf, sizeof(inbuf), outbuf, sizeof(outbuf), &outlen); if (rc && rc != -EALREADY) @@ -1308,7 +1710,8 @@ static void efx_ef10_ev_fini(struct efx_channel *channel) return; fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); + efx_mcdi_display_error(efx, MC_CMD_FINI_EVQ, MC_CMD_FINI_EVQ_IN_LEN, + outbuf, outlen, rc); } static void efx_ef10_ev_remove(struct efx_channel *channel) @@ -1347,8 +1750,6 @@ static void efx_ef10_handle_rx_abort(struct efx_rx_queue *rx_queue) { unsigned int rx_desc_ptr; - WARN_ON(rx_queue->scatter_n == 0); - netif_dbg(rx_queue->efx, hw, rx_queue->efx->net_dev, "scattered RX aborted (dropping %u buffers)\n", rx_queue->scatter_n); @@ -1384,7 +1785,10 @@ static int efx_ef10_handle_rx_event(struct efx_channel *channel, rx_l4_class = EFX_QWORD_FIELD(*event, ESF_DZ_RX_L4_CLASS); rx_cont = EFX_QWORD_FIELD(*event, ESF_DZ_RX_CONT); - WARN_ON(EFX_QWORD_FIELD(*event, ESF_DZ_RX_DROP_EVENT)); + if (EFX_QWORD_FIELD(*event, ESF_DZ_RX_DROP_EVENT)) + netdev_WARN(efx->net_dev, "saw RX_DROP_EVENT: event=" + EFX_QWORD_FMT "\n", + EFX_QWORD_VAL(*event)); rx_queue = efx_channel_get_rx_queue(channel); @@ -1395,17 +1799,27 @@ static int efx_ef10_handle_rx_event(struct efx_channel *channel, ((1 << ESF_DZ_RX_DSC_PTR_LBITS_WIDTH) - 1)); if (n_descs != rx_queue->scatter_n + 1) { + struct efx_ef10_nic_data *nic_data = efx->nic_data; + /* detect rx abort */ if (unlikely(n_descs == rx_queue->scatter_n)) { - WARN_ON(rx_bytes != 0); + if (rx_queue->scatter_n == 0 || rx_bytes != 0) + netdev_WARN(efx->net_dev, + "invalid RX abort: scatter_n=%u event=" + EFX_QWORD_FMT "\n", + rx_queue->scatter_n, + EFX_QWORD_VAL(*event)); efx_ef10_handle_rx_abort(rx_queue); return 0; } - if (unlikely(rx_queue->scatter_n != 0)) { - /* Scattered packet completions cannot be - * merged, so something has gone wrong. - */ + /* Check that RX completion merging is valid, i.e. + * the current firmware supports it and this is a + * non-scattered packet. + */ + if (!(nic_data->datapath_caps & + (1 << MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_LBN)) || + rx_queue->scatter_n != 0 || rx_cont) { efx_ef10_handle_rx_bad_lbits( rx_queue, next_ptr_lbits, (rx_queue->removed_count + @@ -1531,7 +1945,7 @@ static void efx_ef10_handle_driver_generated_event(struct efx_channel *channel, * events, so efx_process_channel() won't refill the * queue. Refill it here */ - efx_fast_push_rx_descriptors(&channel->rx_queue); + efx_fast_push_rx_descriptors(&channel->rx_queue, true); break; default: netif_err(efx, hw, efx->net_dev, @@ -1551,6 +1965,9 @@ static int efx_ef10_ev_process(struct efx_channel *channel, int quota) int tx_descs = 0; int spent = 0; + if (quota <= 0) + return spent; + read_ptr = channel->eventq_read_ptr; for (;;) { @@ -1727,6 +2144,11 @@ static int efx_ef10_fini_dmaq(struct efx_nic *efx) return 0; } +static void efx_ef10_prepare_flr(struct efx_nic *efx) +{ + atomic_set(&efx->active_queues, 0); +} + static bool efx_ef10_filter_equal(const struct efx_filter_spec *left, const struct efx_filter_spec *right) { @@ -1862,7 +2284,9 @@ static void efx_ef10_filter_push_prep(struct efx_nic *efx, MC_CMD_FILTER_OP_IN_RX_DEST_HOST); MCDI_SET_DWORD(inbuf, FILTER_OP_IN_TX_DEST, MC_CMD_FILTER_OP_IN_TX_DEST_DEFAULT); - MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_QUEUE, spec->dmaq_id); + MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_QUEUE, + spec->dmaq_id == EFX_FILTER_RX_DMAQ_ID_DROP ? + 0 : spec->dmaq_id); MCDI_SET_DWORD(inbuf, FILTER_OP_IN_RX_MODE, (spec->flags & EFX_FILTER_FLAG_RX_RSS) ? MC_CMD_FILTER_OP_IN_RX_MODE_RSS : @@ -1887,6 +2311,8 @@ static int efx_ef10_filter_push(struct efx_nic *efx, outbuf, sizeof(outbuf), NULL); if (rc == 0) *handle = MCDI_QWORD(outbuf, FILTER_OP_OUT_HANDLE); + if (rc == -ENOSPC) + rc = -EBUSY; /* to match efx_farch_filter_insert() */ return rc; } @@ -1956,10 +2382,7 @@ static s32 efx_ef10_filter_insert(struct efx_nic *efx, EFX_EF10_FILTER_FLAG_BUSY) break; if (spec->priority < saved_spec->priority && - !(saved_spec->priority == - EFX_FILTER_PRI_REQUIRED && - saved_spec->flags & - EFX_FILTER_FLAG_RX_STACK)) { + spec->priority != EFX_FILTER_PRI_AUTO) { rc = -EPERM; goto out_unlock; } @@ -2013,11 +2436,13 @@ found: */ saved_spec = efx_ef10_filter_entry_spec(table, ins_index); if (saved_spec) { - if (spec->flags & EFX_FILTER_FLAG_RX_STACK) { + if (spec->priority == EFX_FILTER_PRI_AUTO && + saved_spec->priority >= EFX_FILTER_PRI_AUTO) { /* Just make sure it won't be removed */ - saved_spec->flags |= EFX_FILTER_FLAG_RX_STACK; + if (saved_spec->priority > EFX_FILTER_PRI_AUTO) + saved_spec->flags |= EFX_FILTER_FLAG_RX_OVER_AUTO; table->entry[ins_index].spec &= - ~EFX_EF10_FILTER_FLAG_STACK_OLD; + ~EFX_EF10_FILTER_FLAG_AUTO_OLD; rc = ins_index; goto out_unlock; } @@ -2057,8 +2482,11 @@ found: if (rc == 0) { if (replacing) { /* Update the fields that may differ */ + if (saved_spec->priority == EFX_FILTER_PRI_AUTO) + saved_spec->flags |= + EFX_FILTER_FLAG_RX_OVER_AUTO; saved_spec->priority = spec->priority; - saved_spec->flags &= EFX_FILTER_FLAG_RX_STACK; + saved_spec->flags &= EFX_FILTER_FLAG_RX_OVER_AUTO; saved_spec->flags |= spec->flags; saved_spec->rss_context = spec->rss_context; saved_spec->dmaq_id = spec->dmaq_id; @@ -2121,19 +2549,19 @@ out_unlock: return rc; } -void efx_ef10_filter_update_rx_scatter(struct efx_nic *efx) +static void efx_ef10_filter_update_rx_scatter(struct efx_nic *efx) { /* no need to do anything here on EF10 */ } /* Remove a filter. - * If !stack_requested, remove by ID - * If stack_requested, remove by index + * If !by_index, remove by ID + * If by_index, remove by index * Filter ID may come from userland and must be range-checked. */ static int efx_ef10_filter_remove_internal(struct efx_nic *efx, - enum efx_filter_priority priority, - u32 filter_id, bool stack_requested) + unsigned int priority_mask, + u32 filter_id, bool by_index) { unsigned int filter_idx = filter_id % HUNT_FILTER_TBL_ROWS; struct efx_ef10_filter_table *table = efx->filter_state; @@ -2157,26 +2585,41 @@ static int efx_ef10_filter_remove_internal(struct efx_nic *efx, spin_unlock_bh(&efx->filter_lock); schedule(); } + spec = efx_ef10_filter_entry_spec(table, filter_idx); - if (!spec || spec->priority > priority || - (!stack_requested && + if (!spec || + (!by_index && efx_ef10_filter_rx_match_pri(table, spec->match_flags) != filter_id / HUNT_FILTER_TBL_ROWS)) { rc = -ENOENT; goto out_unlock; } + + if (spec->flags & EFX_FILTER_FLAG_RX_OVER_AUTO && + priority_mask == (1U << EFX_FILTER_PRI_AUTO)) { + /* Just remove flags */ + spec->flags &= ~EFX_FILTER_FLAG_RX_OVER_AUTO; + table->entry[filter_idx].spec &= ~EFX_EF10_FILTER_FLAG_AUTO_OLD; + rc = 0; + goto out_unlock; + } + + if (!(priority_mask & (1U << spec->priority))) { + rc = -ENOENT; + goto out_unlock; + } + table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_BUSY; spin_unlock_bh(&efx->filter_lock); - if (spec->flags & EFX_FILTER_FLAG_RX_STACK && !stack_requested) { - /* Reset steering of a stack-owned filter */ + if (spec->flags & EFX_FILTER_FLAG_RX_OVER_AUTO) { + /* Reset to an automatic filter */ struct efx_filter_spec new_spec = *spec; - new_spec.priority = EFX_FILTER_PRI_REQUIRED; + new_spec.priority = EFX_FILTER_PRI_AUTO; new_spec.flags = (EFX_FILTER_FLAG_RX | - EFX_FILTER_FLAG_RX_RSS | - EFX_FILTER_FLAG_RX_STACK); + EFX_FILTER_FLAG_RX_RSS); new_spec.dmaq_id = 0; new_spec.rss_context = EFX_FILTER_RSS_CONTEXT_DEFAULT; rc = efx_ef10_filter_push(efx, &new_spec, @@ -2204,6 +2647,7 @@ static int efx_ef10_filter_remove_internal(struct efx_nic *efx, efx_ef10_filter_set_entry(table, filter_idx, NULL, 0); } } + table->entry[filter_idx].spec &= ~EFX_EF10_FILTER_FLAG_BUSY; wake_up_all(&table->waitq); out_unlock: @@ -2216,7 +2660,8 @@ static int efx_ef10_filter_remove_safe(struct efx_nic *efx, enum efx_filter_priority priority, u32 filter_id) { - return efx_ef10_filter_remove_internal(efx, priority, filter_id, false); + return efx_ef10_filter_remove_internal(efx, 1U << priority, + filter_id, false); } static int efx_ef10_filter_get_safe(struct efx_nic *efx, @@ -2242,10 +2687,24 @@ static int efx_ef10_filter_get_safe(struct efx_nic *efx, return rc; } -static void efx_ef10_filter_clear_rx(struct efx_nic *efx, +static int efx_ef10_filter_clear_rx(struct efx_nic *efx, enum efx_filter_priority priority) { - /* TODO */ + unsigned int priority_mask; + unsigned int i; + int rc; + + priority_mask = (((1U << (priority + 1)) - 1) & + ~(1U << EFX_FILTER_PRI_AUTO)); + + for (i = 0; i < HUNT_FILTER_TBL_ROWS; i++) { + rc = efx_ef10_filter_remove_internal(efx, priority_mask, + i, true); + if (rc && rc != -ENOENT) + return rc; + } + + return 0; } static u32 efx_ef10_filter_count_rx_used(struct efx_nic *efx, @@ -2346,8 +2805,6 @@ static s32 efx_ef10_filter_rfs_insert(struct efx_nic *efx, rc = -EBUSY; goto fail_unlock; } - EFX_WARN_ON_PARANOID(saved_spec->flags & - EFX_FILTER_FLAG_RX_STACK); if (spec->priority < saved_spec->priority) { rc = -EPERM; goto fail_unlock; @@ -2657,8 +3114,11 @@ static void efx_ef10_filter_table_remove(struct efx_nic *efx) table->entry[filter_idx].handle); rc = efx_mcdi_rpc(efx, MC_CMD_FILTER_OP, inbuf, sizeof(inbuf), NULL, 0, NULL); - - WARN_ON(rc != 0); + if (rc) + netdev_WARN(efx->net_dev, + "filter_idx=%#x handle=%#llx\n", + filter_idx, + table->entry[filter_idx].handle); kfree(spec); } @@ -2682,15 +3142,15 @@ static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx) /* Mark old filters that may need to be removed */ spin_lock_bh(&efx->filter_lock); - n = table->stack_uc_count < 0 ? 1 : table->stack_uc_count; + n = table->dev_uc_count < 0 ? 1 : table->dev_uc_count; for (i = 0; i < n; i++) { - filter_idx = table->stack_uc_list[i].id % HUNT_FILTER_TBL_ROWS; - table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_STACK_OLD; + filter_idx = table->dev_uc_list[i].id % HUNT_FILTER_TBL_ROWS; + table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD; } - n = table->stack_mc_count < 0 ? 1 : table->stack_mc_count; + n = table->dev_mc_count < 0 ? 1 : table->dev_mc_count; for (i = 0; i < n; i++) { - filter_idx = table->stack_mc_list[i].id % HUNT_FILTER_TBL_ROWS; - table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_STACK_OLD; + filter_idx = table->dev_mc_list[i].id % HUNT_FILTER_TBL_ROWS; + table->entry[filter_idx].spec |= EFX_EF10_FILTER_FLAG_AUTO_OLD; } spin_unlock_bh(&efx->filter_lock); @@ -2699,119 +3159,112 @@ static void efx_ef10_filter_sync_rx_mode(struct efx_nic *efx) */ netif_addr_lock_bh(net_dev); if (net_dev->flags & IFF_PROMISC || - netdev_uc_count(net_dev) >= EFX_EF10_FILTER_STACK_UC_MAX) { - table->stack_uc_count = -1; + netdev_uc_count(net_dev) >= EFX_EF10_FILTER_DEV_UC_MAX) { + table->dev_uc_count = -1; } else { - table->stack_uc_count = 1 + netdev_uc_count(net_dev); - memcpy(table->stack_uc_list[0].addr, net_dev->dev_addr, - ETH_ALEN); + table->dev_uc_count = 1 + netdev_uc_count(net_dev); + ether_addr_copy(table->dev_uc_list[0].addr, net_dev->dev_addr); i = 1; netdev_for_each_uc_addr(uc, net_dev) { - memcpy(table->stack_uc_list[i].addr, - uc->addr, ETH_ALEN); + ether_addr_copy(table->dev_uc_list[i].addr, uc->addr); i++; } } if (net_dev->flags & (IFF_PROMISC | IFF_ALLMULTI) || - netdev_mc_count(net_dev) >= EFX_EF10_FILTER_STACK_MC_MAX) { - table->stack_mc_count = -1; + netdev_mc_count(net_dev) >= EFX_EF10_FILTER_DEV_MC_MAX) { + table->dev_mc_count = -1; } else { - table->stack_mc_count = 1 + netdev_mc_count(net_dev); - eth_broadcast_addr(table->stack_mc_list[0].addr); + table->dev_mc_count = 1 + netdev_mc_count(net_dev); + eth_broadcast_addr(table->dev_mc_list[0].addr); i = 1; netdev_for_each_mc_addr(mc, net_dev) { - memcpy(table->stack_mc_list[i].addr, - mc->addr, ETH_ALEN); + ether_addr_copy(table->dev_mc_list[i].addr, mc->addr); i++; } } netif_addr_unlock_bh(net_dev); /* Insert/renew unicast filters */ - if (table->stack_uc_count >= 0) { - for (i = 0; i < table->stack_uc_count; i++) { - efx_filter_init_rx(&spec, EFX_FILTER_PRI_REQUIRED, - EFX_FILTER_FLAG_RX_RSS | - EFX_FILTER_FLAG_RX_STACK, + if (table->dev_uc_count >= 0) { + for (i = 0; i < table->dev_uc_count; i++) { + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, + EFX_FILTER_FLAG_RX_RSS, 0); efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, - table->stack_uc_list[i].addr); + table->dev_uc_list[i].addr); rc = efx_ef10_filter_insert(efx, &spec, true); if (rc < 0) { /* Fall back to unicast-promisc */ while (i--) efx_ef10_filter_remove_safe( - efx, EFX_FILTER_PRI_REQUIRED, - table->stack_uc_list[i].id); - table->stack_uc_count = -1; + efx, EFX_FILTER_PRI_AUTO, + table->dev_uc_list[i].id); + table->dev_uc_count = -1; break; } - table->stack_uc_list[i].id = rc; + table->dev_uc_list[i].id = rc; } } - if (table->stack_uc_count < 0) { - efx_filter_init_rx(&spec, EFX_FILTER_PRI_REQUIRED, - EFX_FILTER_FLAG_RX_RSS | - EFX_FILTER_FLAG_RX_STACK, + if (table->dev_uc_count < 0) { + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, + EFX_FILTER_FLAG_RX_RSS, 0); efx_filter_set_uc_def(&spec); rc = efx_ef10_filter_insert(efx, &spec, true); if (rc < 0) { WARN_ON(1); - table->stack_uc_count = 0; + table->dev_uc_count = 0; } else { - table->stack_uc_list[0].id = rc; + table->dev_uc_list[0].id = rc; } } /* Insert/renew multicast filters */ - if (table->stack_mc_count >= 0) { - for (i = 0; i < table->stack_mc_count; i++) { - efx_filter_init_rx(&spec, EFX_FILTER_PRI_REQUIRED, - EFX_FILTER_FLAG_RX_RSS | - EFX_FILTER_FLAG_RX_STACK, + if (table->dev_mc_count >= 0) { + for (i = 0; i < table->dev_mc_count; i++) { + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, + EFX_FILTER_FLAG_RX_RSS, 0); efx_filter_set_eth_local(&spec, EFX_FILTER_VID_UNSPEC, - table->stack_mc_list[i].addr); + table->dev_mc_list[i].addr); rc = efx_ef10_filter_insert(efx, &spec, true); if (rc < 0) { /* Fall back to multicast-promisc */ while (i--) efx_ef10_filter_remove_safe( - efx, EFX_FILTER_PRI_REQUIRED, - table->stack_mc_list[i].id); - table->stack_mc_count = -1; + efx, EFX_FILTER_PRI_AUTO, + table->dev_mc_list[i].id); + table->dev_mc_count = -1; break; } - table->stack_mc_list[i].id = rc; + table->dev_mc_list[i].id = rc; } } - if (table->stack_mc_count < 0) { - efx_filter_init_rx(&spec, EFX_FILTER_PRI_REQUIRED, - EFX_FILTER_FLAG_RX_RSS | - EFX_FILTER_FLAG_RX_STACK, + if (table->dev_mc_count < 0) { + efx_filter_init_rx(&spec, EFX_FILTER_PRI_AUTO, + EFX_FILTER_FLAG_RX_RSS, 0); efx_filter_set_mc_def(&spec); rc = efx_ef10_filter_insert(efx, &spec, true); if (rc < 0) { WARN_ON(1); - table->stack_mc_count = 0; + table->dev_mc_count = 0; } else { - table->stack_mc_list[0].id = rc; + table->dev_mc_list[0].id = rc; } } /* Remove filters that weren't renewed. Since nothing else - * changes the STACK_OLD flag or removes these filters, we + * changes the AUTO_OLD flag or removes these filters, we * don't need to hold the filter_lock while scanning for * these filters. */ for (i = 0; i < HUNT_FILTER_TBL_ROWS; i++) { if (ACCESS_ONCE(table->entry[i].spec) & - EFX_EF10_FILTER_FLAG_STACK_OLD) { - if (efx_ef10_filter_remove_internal(efx, - EFX_FILTER_PRI_REQUIRED, - i, true) < 0) + EFX_EF10_FILTER_FLAG_AUTO_OLD) { + if (efx_ef10_filter_remove_internal( + efx, 1U << EFX_FILTER_PRI_AUTO, + i, true) < 0) remove_failed = true; } } @@ -2825,6 +3278,87 @@ static int efx_ef10_mac_reconfigure(struct efx_nic *efx) return efx_mcdi_set_mac(efx); } +static int efx_ef10_start_bist(struct efx_nic *efx, u32 bist_type) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_START_BIST_IN_LEN); + + MCDI_SET_DWORD(inbuf, START_BIST_IN_TYPE, bist_type); + return efx_mcdi_rpc(efx, MC_CMD_START_BIST, inbuf, sizeof(inbuf), + NULL, 0, NULL); +} + +/* MC BISTs follow a different poll mechanism to phy BISTs. + * The BIST is done in the poll handler on the MC, and the MCDI command + * will block until the BIST is done. + */ +static int efx_ef10_poll_bist(struct efx_nic *efx) +{ + int rc; + MCDI_DECLARE_BUF(outbuf, MC_CMD_POLL_BIST_OUT_LEN); + size_t outlen; + u32 result; + + rc = efx_mcdi_rpc(efx, MC_CMD_POLL_BIST, NULL, 0, + outbuf, sizeof(outbuf), &outlen); + if (rc != 0) + return rc; + + if (outlen < MC_CMD_POLL_BIST_OUT_LEN) + return -EIO; + + result = MCDI_DWORD(outbuf, POLL_BIST_OUT_RESULT); + switch (result) { + case MC_CMD_POLL_BIST_PASSED: + netif_dbg(efx, hw, efx->net_dev, "BIST passed.\n"); + return 0; + case MC_CMD_POLL_BIST_TIMEOUT: + netif_err(efx, hw, efx->net_dev, "BIST timed out\n"); + return -EIO; + case MC_CMD_POLL_BIST_FAILED: + netif_err(efx, hw, efx->net_dev, "BIST failed.\n"); + return -EIO; + default: + netif_err(efx, hw, efx->net_dev, + "BIST returned unknown result %u", result); + return -EIO; + } +} + +static int efx_ef10_run_bist(struct efx_nic *efx, u32 bist_type) +{ + int rc; + + netif_dbg(efx, drv, efx->net_dev, "starting BIST type %u\n", bist_type); + + rc = efx_ef10_start_bist(efx, bist_type); + if (rc != 0) + return rc; + + return efx_ef10_poll_bist(efx); +} + +static int +efx_ef10_test_chip(struct efx_nic *efx, struct efx_self_tests *tests) +{ + int rc, rc2; + + efx_reset_down(efx, RESET_TYPE_WORLD); + + rc = efx_mcdi_rpc(efx, MC_CMD_ENABLE_OFFLINE_BIST, + NULL, 0, NULL, 0, NULL); + if (rc != 0) + goto out; + + tests->memory = efx_ef10_run_bist(efx, MC_CMD_MC_MEM_BIST) ? -1 : 1; + tests->registers = efx_ef10_run_bist(efx, MC_CMD_REG_BIST) ? -1 : 1; + + rc = efx_mcdi_reset(efx, RESET_TYPE_WORLD); + +out: + rc2 = efx_reset_up(efx, RESET_TYPE_WORLD, rc == 0); + return rc ? rc : rc2; +} + #ifdef CONFIG_SFC_MTD struct efx_ef10_nvram_type_info { @@ -2843,6 +3377,7 @@ static const struct efx_ef10_nvram_type_info efx_ef10_nvram_types[] = { { NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT1, 0, 1, "sfc_exp_rom_cfg" }, { NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT2, 0, 2, "sfc_exp_rom_cfg" }, { NVRAM_PARTITION_TYPE_EXPROM_CONFIG_PORT3, 0, 3, "sfc_exp_rom_cfg" }, + { NVRAM_PARTITION_TYPE_LICENSE, 0, 0, "sfc_license" }, { NVRAM_PARTITION_TYPE_PHY_MIN, 0xff, 0, "sfc_phy_fw" }, }; @@ -2950,6 +3485,119 @@ static void efx_ef10_ptp_write_host_time(struct efx_nic *efx, u32 host_time) _efx_writed(efx, cpu_to_le32(host_time), ER_DZ_MC_DB_LWRD); } +static int efx_ef10_rx_enable_timestamping(struct efx_channel *channel, + bool temp) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_LEN); + int rc; + + if (channel->sync_events_state == SYNC_EVENTS_REQUESTED || + channel->sync_events_state == SYNC_EVENTS_VALID || + (temp && channel->sync_events_state == SYNC_EVENTS_DISABLED)) + return 0; + channel->sync_events_state = SYNC_EVENTS_REQUESTED; + + MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_TIME_EVENT_SUBSCRIBE); + MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0); + MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_SUBSCRIBE_QUEUE, + channel->channel); + + rc = efx_mcdi_rpc(channel->efx, MC_CMD_PTP, + inbuf, sizeof(inbuf), NULL, 0, NULL); + + if (rc != 0) + channel->sync_events_state = temp ? SYNC_EVENTS_QUIESCENT : + SYNC_EVENTS_DISABLED; + + return rc; +} + +static int efx_ef10_rx_disable_timestamping(struct efx_channel *channel, + bool temp) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_LEN); + int rc; + + if (channel->sync_events_state == SYNC_EVENTS_DISABLED || + (temp && channel->sync_events_state == SYNC_EVENTS_QUIESCENT)) + return 0; + if (channel->sync_events_state == SYNC_EVENTS_QUIESCENT) { + channel->sync_events_state = SYNC_EVENTS_DISABLED; + return 0; + } + channel->sync_events_state = temp ? SYNC_EVENTS_QUIESCENT : + SYNC_EVENTS_DISABLED; + + MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_TIME_EVENT_UNSUBSCRIBE); + MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0); + MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_UNSUBSCRIBE_CONTROL, + MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_SINGLE); + MCDI_SET_DWORD(inbuf, PTP_IN_TIME_EVENT_UNSUBSCRIBE_QUEUE, + channel->channel); + + rc = efx_mcdi_rpc(channel->efx, MC_CMD_PTP, + inbuf, sizeof(inbuf), NULL, 0, NULL); + + return rc; +} + +static int efx_ef10_ptp_set_ts_sync_events(struct efx_nic *efx, bool en, + bool temp) +{ + int (*set)(struct efx_channel *channel, bool temp); + struct efx_channel *channel; + + set = en ? + efx_ef10_rx_enable_timestamping : + efx_ef10_rx_disable_timestamping; + + efx_for_each_channel(channel, efx) { + int rc = set(channel, temp); + if (en && rc != 0) { + efx_ef10_ptp_set_ts_sync_events(efx, false, temp); + return rc; + } + } + + return 0; +} + +static int efx_ef10_ptp_set_ts_config(struct efx_nic *efx, + struct hwtstamp_config *init) +{ + int rc; + + switch (init->rx_filter) { + case HWTSTAMP_FILTER_NONE: + efx_ef10_ptp_set_ts_sync_events(efx, false, false); + /* if TX timestamping is still requested then leave PTP on */ + return efx_ptp_change_mode(efx, + init->tx_type != HWTSTAMP_TX_OFF, 0); + case HWTSTAMP_FILTER_ALL: + 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_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: + init->rx_filter = HWTSTAMP_FILTER_ALL; + rc = efx_ptp_change_mode(efx, true, 0); + if (!rc) + rc = efx_ef10_ptp_set_ts_sync_events(efx, true, false); + if (rc) + efx_ptp_change_mode(efx, false, 0); + return rc; + default: + return -ERANGE; + } +} + const struct efx_nic_type efx_hunt_a0_nic_type = { .mem_map_size = efx_ef10_mem_map_size, .probe = efx_ef10_probe, @@ -2959,13 +3607,16 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .fini = efx_port_dummy_op_void, .map_reset_reason = efx_mcdi_map_reset_reason, .map_reset_flags = efx_ef10_map_reset_flags, - .reset = efx_mcdi_reset, + .reset = efx_ef10_reset, .probe_port = efx_mcdi_port_probe, .remove_port = efx_mcdi_port_remove, .fini_dmaq = efx_ef10_fini_dmaq, + .prepare_flr = efx_ef10_prepare_flr, + .finish_flr = efx_port_dummy_op_void, .describe_stats = efx_ef10_describe_stats, .update_stats = efx_ef10_update_stats, .start_stats = efx_mcdi_mac_start_stats, + .pull_stats = efx_mcdi_mac_pull_stats, .stop_stats = efx_mcdi_mac_stop_stats, .set_id_led = efx_mcdi_set_id_led, .push_irq_moderation = efx_ef10_push_irq_moderation, @@ -2975,7 +3626,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .get_wol = efx_ef10_get_wol, .set_wol = efx_ef10_set_wol, .resume_wol = efx_port_dummy_op_void, - /* TODO: test_chip */ + .test_chip = efx_ef10_test_chip, .test_nvram = efx_mcdi_nvram_test_all, .mcdi_request = efx_ef10_mcdi_request, .mcdi_poll_response = efx_ef10_mcdi_poll_response, @@ -2990,7 +3641,7 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .tx_init = efx_ef10_tx_init, .tx_remove = efx_ef10_tx_remove, .tx_write = efx_ef10_tx_write, - .rx_push_indir_table = efx_ef10_rx_push_indir_table, + .rx_push_rss_config = efx_ef10_rx_push_rss_config, .rx_probe = efx_ef10_rx_probe, .rx_init = efx_ef10_rx_init, .rx_remove = efx_ef10_rx_remove, @@ -3027,11 +3678,14 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { .mtd_sync = efx_mcdi_mtd_sync, #endif .ptp_write_host_time = efx_ef10_ptp_write_host_time, + .ptp_set_ts_sync_events = efx_ef10_ptp_set_ts_sync_events, + .ptp_set_ts_config = efx_ef10_ptp_set_ts_config, .revision = EFX_REV_HUNT_A0, .max_dma_mask = DMA_BIT_MASK(ESF_DZ_TX_KER_BUF_ADDR_WIDTH), .rx_prefix_size = ES_DZ_RX_PREFIX_SIZE, .rx_hash_offset = ES_DZ_RX_PREFIX_HASH_OFST, + .rx_ts_offset = ES_DZ_RX_PREFIX_TSTAMP_OFST, .can_rx_scatter = true, .always_rx_scatter = true, .max_interrupt_mode = EFX_INT_MODE_MSIX, @@ -3040,4 +3694,6 @@ const struct efx_nic_type efx_hunt_a0_nic_type = { NETIF_F_RXHASH | NETIF_F_NTUPLE), .mcdi_max_ver = 2, .max_rx_ip_filters = HUNT_FILTER_TBL_ROWS, + .hwtstamp_filters = 1 << HWTSTAMP_FILTER_NONE | + 1 << HWTSTAMP_FILTER_ALL, }; diff --git a/drivers/net/ethernet/sfc/ef10_regs.h b/drivers/net/ethernet/sfc/ef10_regs.h index b3f4e3755fd..62a55dde61d 100644 --- a/drivers/net/ethernet/sfc/ef10_regs.h +++ b/drivers/net/ethernet/sfc/ef10_regs.h @@ -227,36 +227,6 @@ #define ESF_DZ_RX_KER_BUF_ADDR_LBN 0 #define ESF_DZ_RX_KER_BUF_ADDR_WIDTH 48 -/* RX_USER_DESC */ -#define ESF_DZ_RX_USR_RESERVED_LBN 62 -#define ESF_DZ_RX_USR_RESERVED_WIDTH 2 -#define ESF_DZ_RX_USR_BYTE_CNT_LBN 48 -#define ESF_DZ_RX_USR_BYTE_CNT_WIDTH 14 -#define ESF_DZ_RX_USR_BUF_PAGE_SIZE_LBN 44 -#define ESF_DZ_RX_USR_BUF_PAGE_SIZE_WIDTH 4 -#define ESE_DZ_USR_BUF_PAGE_SZ_4MB 10 -#define ESE_DZ_USR_BUF_PAGE_SZ_1MB 8 -#define ESE_DZ_USR_BUF_PAGE_SZ_64KB 4 -#define ESE_DZ_USR_BUF_PAGE_SZ_4KB 0 -#define ESF_DZ_RX_USR_BUF_ID_OFFSET_LBN 0 -#define ESF_DZ_RX_USR_BUF_ID_OFFSET_WIDTH 44 -#define ESF_DZ_RX_USR_4KBPS_BUF_ID_LBN 12 -#define ESF_DZ_RX_USR_4KBPS_BUF_ID_WIDTH 32 -#define ESF_DZ_RX_USR_64KBPS_BUF_ID_LBN 16 -#define ESF_DZ_RX_USR_64KBPS_BUF_ID_WIDTH 28 -#define ESF_DZ_RX_USR_1MBPS_BUF_ID_LBN 20 -#define ESF_DZ_RX_USR_1MBPS_BUF_ID_WIDTH 24 -#define ESF_DZ_RX_USR_4MBPS_BUF_ID_LBN 22 -#define ESF_DZ_RX_USR_4MBPS_BUF_ID_WIDTH 22 -#define ESF_DZ_RX_USR_4MBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_RX_USR_4MBPS_BYTE_OFFSET_WIDTH 22 -#define ESF_DZ_RX_USR_1MBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_RX_USR_1MBPS_BYTE_OFFSET_WIDTH 20 -#define ESF_DZ_RX_USR_64KBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_RX_USR_64KBPS_BYTE_OFFSET_WIDTH 16 -#define ESF_DZ_RX_USR_4KBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_RX_USR_4KBPS_BYTE_OFFSET_WIDTH 12 - /* TX_CSUM_TSTAMP_DESC */ #define ESF_DZ_TX_DESC_IS_OPT_LBN 63 #define ESF_DZ_TX_DESC_IS_OPT_WIDTH 1 @@ -315,6 +285,7 @@ #define ESF_DZ_TX_PIO_TYPE_WIDTH 1 #define ESF_DZ_TX_PIO_OPT_LBN 60 #define ESF_DZ_TX_PIO_OPT_WIDTH 3 +#define ESE_DZ_TX_OPTION_DESC_PIO 1 #define ESF_DZ_TX_PIO_CONT_LBN 59 #define ESF_DZ_TX_PIO_CONT_WIDTH 1 #define ESF_DZ_TX_PIO_BYTE_CNT_LBN 32 @@ -337,37 +308,6 @@ #define ESF_DZ_TX_TSO_TCP_SEQNO_LBN 0 #define ESF_DZ_TX_TSO_TCP_SEQNO_WIDTH 32 -/* TX_USER_DESC */ -#define ESF_DZ_TX_USR_TYPE_LBN 63 -#define ESF_DZ_TX_USR_TYPE_WIDTH 1 -#define ESF_DZ_TX_USR_CONT_LBN 62 -#define ESF_DZ_TX_USR_CONT_WIDTH 1 -#define ESF_DZ_TX_USR_BYTE_CNT_LBN 48 -#define ESF_DZ_TX_USR_BYTE_CNT_WIDTH 14 -#define ESF_DZ_TX_USR_BUF_PAGE_SIZE_LBN 44 -#define ESF_DZ_TX_USR_BUF_PAGE_SIZE_WIDTH 4 -#define ESE_DZ_USR_BUF_PAGE_SZ_4MB 10 -#define ESE_DZ_USR_BUF_PAGE_SZ_1MB 8 -#define ESE_DZ_USR_BUF_PAGE_SZ_64KB 4 -#define ESE_DZ_USR_BUF_PAGE_SZ_4KB 0 -#define ESF_DZ_TX_USR_BUF_ID_OFFSET_LBN 0 -#define ESF_DZ_TX_USR_BUF_ID_OFFSET_WIDTH 44 -#define ESF_DZ_TX_USR_4KBPS_BUF_ID_LBN 12 -#define ESF_DZ_TX_USR_4KBPS_BUF_ID_WIDTH 32 -#define ESF_DZ_TX_USR_64KBPS_BUF_ID_LBN 16 -#define ESF_DZ_TX_USR_64KBPS_BUF_ID_WIDTH 28 -#define ESF_DZ_TX_USR_1MBPS_BUF_ID_LBN 20 -#define ESF_DZ_TX_USR_1MBPS_BUF_ID_WIDTH 24 -#define ESF_DZ_TX_USR_4MBPS_BUF_ID_LBN 22 -#define ESF_DZ_TX_USR_4MBPS_BUF_ID_WIDTH 22 -#define ESF_DZ_TX_USR_4MBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_TX_USR_4MBPS_BYTE_OFFSET_WIDTH 22 -#define ESF_DZ_TX_USR_1MBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_TX_USR_1MBPS_BYTE_OFFSET_WIDTH 20 -#define ESF_DZ_TX_USR_64KBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_TX_USR_64KBPS_BYTE_OFFSET_WIDTH 16 -#define ESF_DZ_TX_USR_4KBPS_BYTE_OFFSET_LBN 0 -#define ESF_DZ_TX_USR_4KBPS_BYTE_OFFSET_WIDTH 12 /*************************************************************************/ /* TX_DESC_UPD_REG: Transmit descriptor update register. diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index 07c9bc4c61b..1e274045970 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -76,6 +76,7 @@ const char *const efx_reset_type_names[] = { [RESET_TYPE_RECOVER_OR_ALL] = "RECOVER_OR_ALL", [RESET_TYPE_WORLD] = "WORLD", [RESET_TYPE_RECOVER_OR_DISABLE] = "RECOVER_OR_DISABLE", + [RESET_TYPE_MC_BIST] = "MC_BIST", [RESET_TYPE_DISABLE] = "DISABLE", [RESET_TYPE_TX_WATCHDOG] = "TX_WATCHDOG", [RESET_TYPE_INT_ERROR] = "INT_ERROR", @@ -83,6 +84,7 @@ const char *const efx_reset_type_names[] = { [RESET_TYPE_DMA_ERROR] = "DMA_ERROR", [RESET_TYPE_TX_SKIP] = "TX_SKIP", [RESET_TYPE_MC_FAILURE] = "MC_FAILURE", + [RESET_TYPE_MCDI_TIMEOUT] = "MCDI_TIMEOUT (FLR)", }; /* Reset workqueue. If any NIC has a hardware failure then a reset will be @@ -91,6 +93,12 @@ const char *const efx_reset_type_names[] = { */ static struct workqueue_struct *reset_workqueue; +/* How often and how many times to poll for a reset while waiting for a + * BIST that another function started to complete. + */ +#define BIST_WAIT_DELAY_MS 100 +#define BIST_WAIT_DELAY_COUNT 100 + /************************************************************************** * * Configurable values @@ -246,7 +254,7 @@ static int efx_process_channel(struct efx_channel *channel, int budget) efx_channel_get_rx_queue(channel); efx_rx_flush_packet(channel); - efx_fast_push_rx_descriptors(rx_queue); + efx_fast_push_rx_descriptors(rx_queue, true); } return spent; @@ -496,8 +504,6 @@ static int efx_probe_channel(struct efx_channel *channel) goto fail; } - channel->n_rx_frm_trunc = 0; - return 0; fail: @@ -585,7 +591,7 @@ static void efx_start_datapath(struct efx_nic *efx) EFX_MAX_FRAME_LEN(efx->net_dev->mtu) + efx->type->rx_buffer_padding); rx_buf_len = (sizeof(struct efx_rx_page_state) + - NET_IP_ALIGN + efx->rx_dma_len); + efx->rx_ip_align + efx->rx_dma_len); if (rx_buf_len <= PAGE_SIZE) { efx->rx_scatter = efx->type->always_rx_scatter; efx->rx_buffer_order = 0; @@ -639,12 +645,16 @@ static void efx_start_datapath(struct efx_nic *efx) efx_for_each_channel_rx_queue(rx_queue, channel) { efx_init_rx_queue(rx_queue); atomic_inc(&efx->active_queues); - efx_nic_generate_fill_event(rx_queue); + efx_stop_eventq(channel); + efx_fast_push_rx_descriptors(rx_queue, false); + efx_start_eventq(channel); } WARN_ON(channel->rx_pkt_n_frags); } + efx_ptp_start_datapath(efx); + if (netif_device_present(efx->net_dev)) netif_tx_wake_all_queues(efx->net_dev); } @@ -659,6 +669,8 @@ static void efx_stop_datapath(struct efx_nic *efx) EFX_ASSERT_RESET_SERIALISED(efx); BUG_ON(efx->port_enabled); + efx_ptp_stop_datapath(efx); + /* Stop RX refill */ efx_for_each_channel(channel, efx) { efx_for_each_channel_rx_queue(rx_queue, channel) @@ -1001,7 +1013,7 @@ static int efx_probe_port(struct efx_nic *efx) return rc; /* Initialise MAC address to permanent address */ - memcpy(efx->net_dev->dev_addr, efx->net_dev->perm_addr, ETH_ALEN); + ether_addr_copy(efx->net_dev->dev_addr, efx->net_dev->perm_addr); return 0; } @@ -1047,18 +1059,23 @@ static void efx_start_port(struct efx_nic *efx) mutex_lock(&efx->mac_lock); efx->port_enabled = true; - /* efx_mac_work() might have been scheduled after efx_stop_port(), - * and then cancelled by efx_flush_all() */ + /* Ensure MAC ingress/egress is enabled */ efx->type->reconfigure_mac(efx); mutex_unlock(&efx->mac_lock); } -/* Prevent efx_mac_work() and efx_monitor() from working */ +/* Cancel work for MAC reconfiguration, periodic hardware monitoring + * and the async self-test, wait for them to finish and prevent them + * being scheduled again. This doesn't cover online resets, which + * should only be cancelled when removing the device. + */ static void efx_stop_port(struct efx_nic *efx) { netif_dbg(efx, ifdown, efx->net_dev, "stop port\n"); + EFX_ASSERT_RESET_SERIALISED(efx); + mutex_lock(&efx->mac_lock); efx->port_enabled = false; mutex_unlock(&efx->mac_lock); @@ -1066,6 +1083,10 @@ static void efx_stop_port(struct efx_nic *efx) /* Serialise against efx_set_multicast_list() */ netif_addr_lock_bh(efx->net_dev); netif_addr_unlock_bh(efx->net_dev); + + cancel_delayed_work_sync(&efx->monitor_work); + efx_selftest_async_cancel(efx); + cancel_work_sync(&efx->mac_work); } static void efx_fini_port(struct efx_nic *efx) @@ -1095,6 +1116,77 @@ static void efx_remove_port(struct efx_nic *efx) * **************************************************************************/ +static LIST_HEAD(efx_primary_list); +static LIST_HEAD(efx_unassociated_list); + +static bool efx_same_controller(struct efx_nic *left, struct efx_nic *right) +{ + return left->type == right->type && + left->vpd_sn && right->vpd_sn && + !strcmp(left->vpd_sn, right->vpd_sn); +} + +static void efx_associate(struct efx_nic *efx) +{ + struct efx_nic *other, *next; + + if (efx->primary == efx) { + /* Adding primary function; look for secondaries */ + + netif_dbg(efx, probe, efx->net_dev, "adding to primary list\n"); + list_add_tail(&efx->node, &efx_primary_list); + + list_for_each_entry_safe(other, next, &efx_unassociated_list, + node) { + if (efx_same_controller(efx, other)) { + list_del(&other->node); + netif_dbg(other, probe, other->net_dev, + "moving to secondary list of %s %s\n", + pci_name(efx->pci_dev), + efx->net_dev->name); + list_add_tail(&other->node, + &efx->secondary_list); + other->primary = efx; + } + } + } else { + /* Adding secondary function; look for primary */ + + list_for_each_entry(other, &efx_primary_list, node) { + if (efx_same_controller(efx, other)) { + netif_dbg(efx, probe, efx->net_dev, + "adding to secondary list of %s %s\n", + pci_name(other->pci_dev), + other->net_dev->name); + list_add_tail(&efx->node, + &other->secondary_list); + efx->primary = other; + return; + } + } + + netif_dbg(efx, probe, efx->net_dev, + "adding to unassociated list\n"); + list_add_tail(&efx->node, &efx_unassociated_list); + } +} + +static void efx_dissociate(struct efx_nic *efx) +{ + struct efx_nic *other, *next; + + list_del(&efx->node); + efx->primary = NULL; + + list_for_each_entry_safe(other, next, &efx->secondary_list, node) { + list_del(&other->node); + netif_dbg(other, probe, other->net_dev, + "moving to unassociated list\n"); + list_add_tail(&other->node, &efx_unassociated_list); + other->primary = NULL; + } +} + /* This configures the PCI device to enable I/O and DMA. */ static int efx_init_io(struct efx_nic *efx) { @@ -1121,7 +1213,7 @@ static int efx_init_io(struct efx_nic *efx) */ while (dma_mask > 0x7fffffffUL) { if (dma_supported(&pci_dev->dev, dma_mask)) { - rc = dma_set_mask(&pci_dev->dev, dma_mask); + rc = dma_set_mask_and_coherent(&pci_dev->dev, dma_mask); if (rc == 0) break; } @@ -1134,16 +1226,6 @@ static int efx_init_io(struct efx_nic *efx) } netif_dbg(efx, probe, efx->net_dev, "using DMA mask %llx\n", (unsigned long long) dma_mask); - rc = dma_set_coherent_mask(&pci_dev->dev, dma_mask); - if (rc) { - /* dma_set_coherent_mask() is not *allowed* to - * fail with a mask that dma_set_mask() accepted, - * but just in case... - */ - netif_err(efx, probe, efx->net_dev, - "failed to set consistent DMA mask\n"); - goto fail2; - } efx->membase_phys = pci_resource_start(efx->pci_dev, EFX_MEM_BAR); rc = pci_request_region(pci_dev, EFX_MEM_BAR, "sfc"); @@ -1263,20 +1345,23 @@ static int efx_probe_interrupts(struct efx_nic *efx) for (i = 0; i < n_channels; i++) xentries[i].entry = i; - rc = pci_enable_msix(efx->pci_dev, xentries, n_channels); - if (rc > 0) { + rc = pci_enable_msix_range(efx->pci_dev, + xentries, 1, n_channels); + if (rc < 0) { + /* Fall back to single channel MSI */ + efx->interrupt_mode = EFX_INT_MODE_MSI; + netif_err(efx, drv, efx->net_dev, + "could not enable MSI-X\n"); + } else if (rc < n_channels) { netif_err(efx, drv, efx->net_dev, "WARNING: Insufficient MSI-X vectors" " available (%d < %u).\n", rc, n_channels); netif_err(efx, drv, efx->net_dev, "WARNING: Performance may be reduced.\n"); - EFX_BUG_ON_PARANOID(rc >= n_channels); n_channels = rc; - rc = pci_enable_msix(efx->pci_dev, xentries, - n_channels); } - if (rc == 0) { + if (rc > 0) { efx->n_channels = n_channels; if (n_channels > extra_channels) n_channels -= extra_channels; @@ -1292,11 +1377,6 @@ static int efx_probe_interrupts(struct efx_nic *efx) for (i = 0; i < efx->n_channels; i++) efx_get_channel(efx, i)->irq = xentries[i].vector; - } else { - /* Fall back to single channel MSI */ - efx->interrupt_mode = EFX_INT_MODE_MSI; - netif_err(efx, drv, efx->net_dev, - "could not enable MSI-X\n"); } } @@ -1520,6 +1600,8 @@ static int efx_probe_nic(struct efx_nic *efx) if (rc) goto fail1; + efx_set_channels(efx); + rc = efx->type->dimension_resources(efx); if (rc) goto fail2; @@ -1530,7 +1612,6 @@ static int efx_probe_nic(struct efx_nic *efx) efx->rx_indir_table[i] = ethtool_rxfh_indir_default(i, efx->rss_spread); - efx_set_channels(efx); netif_set_real_num_tx_queues(efx->net_dev, efx->n_tx_channels); netif_set_real_num_rx_queues(efx->net_dev, efx->n_rx_channels); @@ -1659,7 +1740,8 @@ static void efx_start_all(struct efx_nic *efx) /* Check that it is appropriate to restart the interface. All * of these flags are safe to read under just the rtnl lock */ - if (efx->port_enabled || !netif_running(efx->net_dev)) + if (efx->port_enabled || !netif_running(efx->net_dev) || + efx->reset_pending) return; efx_start_port(efx); @@ -1681,18 +1763,10 @@ static void efx_start_all(struct efx_nic *efx) } efx->type->start_stats(efx); -} - -/* Flush all delayed work. Should only be called when no more delayed work - * will be scheduled. This doesn't flush pending online resets (efx_reset), - * since we're holding the rtnl_lock at this point. */ -static void efx_flush_all(struct efx_nic *efx) -{ - /* Make sure the hardware monitor and event self-test are stopped */ - cancel_delayed_work_sync(&efx->monitor_work); - efx_selftest_async_cancel(efx); - /* Stop scheduled port reconfigurations */ - cancel_work_sync(&efx->mac_work); + efx->type->pull_stats(efx); + spin_lock_bh(&efx->stats_lock); + efx->type->update_stats(efx, NULL, NULL); + spin_unlock_bh(&efx->stats_lock); } /* Quiesce the hardware and software data path, and regular activity @@ -1708,12 +1782,16 @@ static void efx_stop_all(struct efx_nic *efx) if (!efx->port_enabled) return; + /* update stats before we go down so we can accurately count + * rx_nodesc_drops + */ + efx->type->pull_stats(efx); + spin_lock_bh(&efx->stats_lock); + efx->type->update_stats(efx, NULL, NULL); + spin_unlock_bh(&efx->stats_lock); efx->type->stop_stats(efx); efx_stop_port(efx); - /* Flush efx_mac_work(), refill_workqueue, monitor_work */ - efx_flush_all(efx); - /* Stop the kernel transmit interface. This is only valid if * the device is stopped or detached; otherwise the watchdog * may fire immediately. @@ -1857,7 +1935,9 @@ static int efx_ioctl(struct net_device *net_dev, struct ifreq *ifr, int cmd) struct mii_ioctl_data *data = if_mii(ifr); if (cmd == SIOCSHWTSTAMP) - return efx_ptp_ioctl(efx, ifr, cmd); + return efx_ptp_set_ts_config(efx, ifr); + if (cmd == SIOCGHWTSTAMP) + return efx_ptp_get_ts_config(efx, ifr); /* Convert phy_id from older PRTAD/DEVAD format */ if ((cmd == SIOCGMIIREG || cmd == SIOCSMIIREG) && @@ -2034,7 +2114,7 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data) { struct efx_nic *efx = netdev_priv(net_dev); struct sockaddr *addr = data; - char *new_addr = addr->sa_data; + u8 *new_addr = addr->sa_data; if (!is_valid_ether_addr(new_addr)) { netif_err(efx, drv, efx->net_dev, @@ -2043,7 +2123,7 @@ static int efx_set_mac_address(struct net_device *net_dev, void *data) return -EADDRNOTAVAIL; } - memcpy(net_dev->dev_addr, new_addr, net_dev->addr_len); + ether_addr_copy(net_dev->dev_addr, new_addr); efx_sriov_mac_address_changed(efx); /* Reconfigure the MAC */ @@ -2070,7 +2150,7 @@ static int efx_set_features(struct net_device *net_dev, netdev_features_t data) /* If disabling RX n-tuple filtering, clear existing filters */ if (net_dev->features & ~data & NETIF_F_NTUPLE) - efx_filter_clear_rx(efx, EFX_FILTER_PRI_MANUAL); + return efx->type->filter_clear_rx(efx, EFX_FILTER_PRI_MANUAL); return 0; } @@ -2168,7 +2248,7 @@ static int efx_register_netdev(struct efx_nic *efx) } else { net_dev->netdev_ops = &efx_farch_netdev_ops; } - SET_ETHTOOL_OPS(net_dev, &efx_ethtool_ops); + net_dev->ethtool_ops = &efx_ethtool_ops; net_dev->gso_max_segs = EFX_TSO_MAX_SEGS; rtnl_lock(); @@ -2204,6 +2284,8 @@ static int efx_register_netdev(struct efx_nic *efx) efx_init_tx_queue_core_txq(tx_queue); } + efx_associate(efx); + rtnl_unlock(); rc = device_create_file(&efx->pci_dev->dev, &dev_attr_phy_type); @@ -2217,6 +2299,7 @@ static int efx_register_netdev(struct efx_nic *efx) fail_registered: rtnl_lock(); + efx_dissociate(efx); unregister_netdevice(net_dev); fail_locked: efx->state = STATE_UNINIT; @@ -2253,6 +2336,9 @@ void efx_reset_down(struct efx_nic *efx, enum reset_type method) { EFX_ASSERT_RESET_SERIALISED(efx); + if (method == RESET_TYPE_MCDI_TIMEOUT) + efx->type->prepare_flr(efx); + efx_stop_all(efx); efx_disable_interrupts(efx); @@ -2273,6 +2359,10 @@ int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok) EFX_ASSERT_RESET_SERIALISED(efx); + if (method == RESET_TYPE_MCDI_TIMEOUT) + efx->type->finish_flr(efx); + + /* Ensure that SRAM is initialised even if we're disabling the device */ rc = efx->type->init(efx); if (rc) { netif_err(efx, drv, efx->net_dev, "failed to initialise NIC\n"); @@ -2336,7 +2426,10 @@ int efx_reset(struct efx_nic *efx, enum reset_type method) /* Clear flags for the scopes we covered. We assume the NIC and * driver are now quiescent so that there is no race here. */ - efx->reset_pending &= -(1 << (method + 1)); + if (method < RESET_TYPE_MAX_METHOD) + efx->reset_pending &= -(1 << (method + 1)); + else /* it doesn't fit into the well-ordered scope hierarchy */ + __clear_bit(method, &efx->reset_pending); /* Reinitialise bus-mastering, which may have been turned off before * the reset was scheduled. This is still appropriate, even in the @@ -2393,6 +2486,24 @@ int efx_try_recovery(struct efx_nic *efx) return 0; } +static void efx_wait_for_bist_end(struct efx_nic *efx) +{ + int i; + + for (i = 0; i < BIST_WAIT_DELAY_COUNT; ++i) { + if (efx_mcdi_poll_reboot(efx)) + goto out; + msleep(BIST_WAIT_DELAY_MS); + } + + netif_err(efx, drv, efx->net_dev, "Warning: No MC reboot after BIST mode\n"); +out: + /* Either way unset the BIST flag. If we found no reboot we probably + * won't recover, but we should try. + */ + efx->mc_bist_for_other_fn = false; +} + /* The worker thread exists so that code that cannot sleep can * schedule a reset for later. */ @@ -2405,6 +2516,9 @@ static void efx_reset_work(struct work_struct *data) pending = ACCESS_ONCE(efx->reset_pending); method = fls(pending) - 1; + if (method == RESET_TYPE_MC_BIST) + efx_wait_for_bist_end(efx); + if ((method == RESET_TYPE_RECOVER_OR_DISABLE || method == RESET_TYPE_RECOVER_OR_ALL) && efx_try_recovery(efx)) @@ -2443,6 +2557,8 @@ void efx_schedule_reset(struct efx_nic *efx, enum reset_type type) case RESET_TYPE_WORLD: case RESET_TYPE_DISABLE: case RESET_TYPE_RECOVER_OR_DISABLE: + case RESET_TYPE_MC_BIST: + case RESET_TYPE_MCDI_TIMEOUT: method = type; netif_dbg(efx, drv, efx->net_dev, "scheduling %s reset\n", RESET_TYPE(method)); @@ -2536,6 +2652,8 @@ static int efx_init_struct(struct efx_nic *efx, int i; /* Initialise common structures */ + INIT_LIST_HEAD(&efx->node); + INIT_LIST_HEAD(&efx->secondary_list); spin_lock_init(&efx->biu_lock); #ifdef CONFIG_SFC_MTD INIT_LIST_HEAD(&efx->mtd_list); @@ -2550,8 +2668,12 @@ static int efx_init_struct(struct efx_nic *efx, efx->net_dev = net_dev; efx->rx_prefix_size = efx->type->rx_prefix_size; + efx->rx_ip_align = + NET_IP_ALIGN ? (efx->rx_prefix_size + NET_IP_ALIGN) % 4 : 0; efx->rx_packet_hash_offset = efx->type->rx_hash_offset - efx->type->rx_prefix_size; + efx->rx_packet_ts_offset = + efx->type->rx_ts_offset - efx->type->rx_prefix_size; spin_lock_init(&efx->stats_lock); mutex_init(&efx->mac_lock); efx->phy_op = &efx_dummy_phy_operations; @@ -2592,6 +2714,8 @@ static void efx_fini_struct(struct efx_nic *efx) for (i = 0; i < EFX_MAX_CHANNELS; i++) kfree(efx->channel[i]); + kfree(efx->vpd_sn); + if (efx->workqueue) { destroy_workqueue(efx->workqueue); efx->workqueue = NULL; @@ -2636,6 +2760,7 @@ static void efx_pci_remove(struct pci_dev *pci_dev) /* Mark the NIC as fini, then stop the interface */ rtnl_lock(); + efx_dissociate(efx); dev_close(efx->net_dev); efx_disable_interrupts(efx); rtnl_unlock(); @@ -2651,7 +2776,6 @@ static void efx_pci_remove(struct pci_dev *pci_dev) netif_dbg(efx, drv, efx->net_dev, "shutdown successful\n"); efx_fini_struct(efx); - pci_set_drvdata(pci_dev, NULL); free_netdev(efx->net_dev); pci_disable_pcie_error_reporting(pci_dev); @@ -2663,12 +2787,12 @@ static void efx_pci_remove(struct pci_dev *pci_dev) * always appear within the first 512 bytes. */ #define SFC_VPD_LEN 512 -static void efx_print_product_vpd(struct efx_nic *efx) +static void efx_probe_vpd_strings(struct efx_nic *efx) { struct pci_dev *dev = efx->pci_dev; char vpd_data[SFC_VPD_LEN]; ssize_t vpd_size; - int i, j; + int ro_start, ro_size, i, j; /* Get the vpd data from the device */ vpd_size = pci_read_vpd(dev, 0, sizeof(vpd_data), vpd_data); @@ -2678,14 +2802,15 @@ static void efx_print_product_vpd(struct efx_nic *efx) } /* Get the Read only section */ - i = pci_vpd_find_tag(vpd_data, 0, vpd_size, PCI_VPD_LRDT_RO_DATA); - if (i < 0) { + ro_start = pci_vpd_find_tag(vpd_data, 0, vpd_size, PCI_VPD_LRDT_RO_DATA); + if (ro_start < 0) { netif_err(efx, drv, efx->net_dev, "VPD Read-only not found\n"); return; } - j = pci_vpd_lrdt_size(&vpd_data[i]); - i += PCI_VPD_LRDT_TAG_SIZE; + ro_size = pci_vpd_lrdt_size(&vpd_data[ro_start]); + j = ro_size; + i = ro_start + PCI_VPD_LRDT_TAG_SIZE; if (i + j > vpd_size) j = vpd_size - i; @@ -2705,6 +2830,27 @@ static void efx_print_product_vpd(struct efx_nic *efx) netif_info(efx, drv, efx->net_dev, "Part Number : %.*s\n", j, &vpd_data[i]); + + i = ro_start + PCI_VPD_LRDT_TAG_SIZE; + j = ro_size; + i = pci_vpd_find_info_keyword(vpd_data, i, j, "SN"); + if (i < 0) { + netif_err(efx, drv, efx->net_dev, "Serial number not found\n"); + return; + } + + j = pci_vpd_info_field_size(&vpd_data[i]); + i += PCI_VPD_INFO_FLD_HDR_SIZE; + if (i + j > vpd_size) { + netif_err(efx, drv, efx->net_dev, "Incomplete serial number\n"); + return; + } + + efx->vpd_sn = kmalloc(j + 1, GFP_KERNEL); + if (!efx->vpd_sn) + return; + + snprintf(efx->vpd_sn, j + 1, "%s", &vpd_data[i]); } @@ -2801,7 +2947,7 @@ static int efx_pci_probe(struct pci_dev *pci_dev, netif_info(efx, probe, efx->net_dev, "Solarflare NIC detected\n"); - efx_print_product_vpd(efx); + efx_probe_vpd_strings(efx); /* Set up basic I/O (BAR mappings etc) */ rc = efx_init_io(efx); @@ -2845,7 +2991,6 @@ static int efx_pci_probe(struct pci_dev *pci_dev, fail2: efx_fini_struct(efx); fail1: - pci_set_drvdata(pci_dev, NULL); WARN_ON(rc > 0); netif_dbg(efx, drv, efx->net_dev, "initialisation failed. rc=%d\n", rc); free_netdev(net_dev); @@ -3138,6 +3283,6 @@ module_exit(efx_exit_module); MODULE_AUTHOR("Solarflare Communications and " "Michael Brown <mbrown@fensystems.co.uk>"); -MODULE_DESCRIPTION("Solarflare Communications network driver"); +MODULE_DESCRIPTION("Solarflare network driver"); MODULE_LICENSE("GPL"); MODULE_DEVICE_TABLE(pci, efx_pci_table); diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index 34d00f5771f..99032581336 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -14,41 +14,40 @@ #include "net_driver.h" #include "filter.h" -/* Solarstorm controllers use BAR 0 for I/O space and BAR 2(&3) for memory */ +/* All controllers use BAR 0 for I/O space and BAR 2(&3) for memory */ #define EFX_MEM_BAR 2 /* TX */ -extern int efx_probe_tx_queue(struct efx_tx_queue *tx_queue); -extern void efx_remove_tx_queue(struct efx_tx_queue *tx_queue); -extern void efx_init_tx_queue(struct efx_tx_queue *tx_queue); -extern void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue); -extern void efx_fini_tx_queue(struct efx_tx_queue *tx_queue); -extern netdev_tx_t -efx_hard_start_xmit(struct sk_buff *skb, struct net_device *net_dev); -extern netdev_tx_t -efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); -extern void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); -extern int efx_setup_tc(struct net_device *net_dev, u8 num_tc); -extern unsigned int efx_tx_max_skb_descs(struct efx_nic *efx); +int efx_probe_tx_queue(struct efx_tx_queue *tx_queue); +void efx_remove_tx_queue(struct efx_tx_queue *tx_queue); +void efx_init_tx_queue(struct efx_tx_queue *tx_queue); +void efx_init_tx_queue_core_txq(struct efx_tx_queue *tx_queue); +void efx_fini_tx_queue(struct efx_tx_queue *tx_queue); +netdev_tx_t efx_hard_start_xmit(struct sk_buff *skb, + struct net_device *net_dev); +netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb); +void efx_xmit_done(struct efx_tx_queue *tx_queue, unsigned int index); +int efx_setup_tc(struct net_device *net_dev, u8 num_tc); +unsigned int efx_tx_max_skb_descs(struct efx_nic *efx); +extern unsigned int efx_piobuf_size; /* RX */ -extern void efx_rx_config_page_split(struct efx_nic *efx); -extern int efx_probe_rx_queue(struct efx_rx_queue *rx_queue); -extern void efx_remove_rx_queue(struct efx_rx_queue *rx_queue); -extern void efx_init_rx_queue(struct efx_rx_queue *rx_queue); -extern void efx_fini_rx_queue(struct efx_rx_queue *rx_queue); -extern void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue); -extern void efx_rx_slow_fill(unsigned long context); -extern void __efx_rx_packet(struct efx_channel *channel); -extern void efx_rx_packet(struct efx_rx_queue *rx_queue, - unsigned int index, unsigned int n_frags, - unsigned int len, u16 flags); +void efx_rx_config_page_split(struct efx_nic *efx); +int efx_probe_rx_queue(struct efx_rx_queue *rx_queue); +void efx_remove_rx_queue(struct efx_rx_queue *rx_queue); +void efx_init_rx_queue(struct efx_rx_queue *rx_queue); +void efx_fini_rx_queue(struct efx_rx_queue *rx_queue); +void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic); +void efx_rx_slow_fill(unsigned long context); +void __efx_rx_packet(struct efx_channel *channel); +void efx_rx_packet(struct efx_rx_queue *rx_queue, unsigned int index, + unsigned int n_frags, unsigned int len, u16 flags); static inline void efx_rx_flush_packet(struct efx_channel *channel) { if (channel->rx_pkt_n_frags) __efx_rx_packet(channel); } -extern void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue); +void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue); #define EFX_MAX_DMAQ_SIZE 4096UL #define EFX_DEFAULT_DMAQ_SIZE 1024UL @@ -67,6 +66,9 @@ extern void efx_schedule_slow_fill(struct efx_rx_queue *rx_queue); #define EFX_RXQ_MIN_ENT 128U #define EFX_TXQ_MIN_ENT(efx) (2 * efx_tx_max_skb_descs(efx)) +#define EFX_TXQ_MAX_ENT(efx) (EFX_WORKAROUND_35388(efx) ? \ + EFX_MAX_DMAQ_SIZE / 2 : EFX_MAX_DMAQ_SIZE) + /* Filters */ /** @@ -135,17 +137,6 @@ efx_filter_get_filter_safe(struct efx_nic *efx, return efx->type->filter_get_safe(efx, priority, filter_id, spec); } -/** - * efx_farch_filter_clear_rx - remove RX filters by priority - * @efx: NIC from which to remove the filters - * @priority: Maximum priority to remove - */ -static inline void efx_filter_clear_rx(struct efx_nic *efx, - enum efx_filter_priority priority) -{ - return efx->type->filter_clear_rx(efx, priority); -} - static inline u32 efx_filter_count_rx_used(struct efx_nic *efx, enum efx_filter_priority priority) { @@ -162,9 +153,9 @@ static inline s32 efx_filter_get_rx_ids(struct efx_nic *efx, return efx->type->filter_get_rx_ids(efx, priority, buf, size); } #ifdef CONFIG_RFS_ACCEL -extern int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, - u16 rxq_index, u32 flow_id); -extern bool __efx_filter_rfs_expire(struct efx_nic *efx, unsigned quota); +int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, + u16 rxq_index, u32 flow_id); +bool __efx_filter_rfs_expire(struct efx_nic *efx, unsigned quota); static inline void efx_filter_rfs_expire(struct efx_channel *channel) { if (channel->rfs_filters_added >= 60 && @@ -176,50 +167,48 @@ static inline void efx_filter_rfs_expire(struct efx_channel *channel) static inline void efx_filter_rfs_expire(struct efx_channel *channel) {} #define efx_filter_rfs_enabled() 0 #endif -extern bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec); +bool efx_filter_is_mc_recipient(const struct efx_filter_spec *spec); /* Channels */ -extern int efx_channel_dummy_op_int(struct efx_channel *channel); -extern void efx_channel_dummy_op_void(struct efx_channel *channel); -extern int -efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries); +int efx_channel_dummy_op_int(struct efx_channel *channel); +void efx_channel_dummy_op_void(struct efx_channel *channel); +int efx_realloc_channels(struct efx_nic *efx, u32 rxq_entries, u32 txq_entries); /* Ports */ -extern int efx_reconfigure_port(struct efx_nic *efx); -extern int __efx_reconfigure_port(struct efx_nic *efx); +int efx_reconfigure_port(struct efx_nic *efx); +int __efx_reconfigure_port(struct efx_nic *efx); /* Ethtool support */ extern const struct ethtool_ops efx_ethtool_ops; /* Reset handling */ -extern int efx_reset(struct efx_nic *efx, enum reset_type method); -extern void efx_reset_down(struct efx_nic *efx, enum reset_type method); -extern int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok); -extern int efx_try_recovery(struct efx_nic *efx); +int efx_reset(struct efx_nic *efx, enum reset_type method); +void efx_reset_down(struct efx_nic *efx, enum reset_type method); +int efx_reset_up(struct efx_nic *efx, enum reset_type method, bool ok); +int efx_try_recovery(struct efx_nic *efx); /* Global */ -extern void efx_schedule_reset(struct efx_nic *efx, enum reset_type type); -extern int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs, - unsigned int rx_usecs, bool rx_adaptive, - bool rx_may_override_tx); -extern void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs, - unsigned int *rx_usecs, bool *rx_adaptive); +void efx_schedule_reset(struct efx_nic *efx, enum reset_type type); +int efx_init_irq_moderation(struct efx_nic *efx, unsigned int tx_usecs, + unsigned int rx_usecs, bool rx_adaptive, + bool rx_may_override_tx); +void efx_get_irq_moderation(struct efx_nic *efx, unsigned int *tx_usecs, + unsigned int *rx_usecs, bool *rx_adaptive); /* Dummy PHY ops for PHY drivers */ -extern int efx_port_dummy_op_int(struct efx_nic *efx); -extern void efx_port_dummy_op_void(struct efx_nic *efx); - +int efx_port_dummy_op_int(struct efx_nic *efx); +void efx_port_dummy_op_void(struct efx_nic *efx); /* MTD */ #ifdef CONFIG_SFC_MTD -extern int efx_mtd_add(struct efx_nic *efx, struct efx_mtd_partition *parts, - size_t n_parts, size_t sizeof_part); +int efx_mtd_add(struct efx_nic *efx, struct efx_mtd_partition *parts, + size_t n_parts, size_t sizeof_part); static inline int efx_mtd_probe(struct efx_nic *efx) { return efx->type->mtd_probe(efx); } -extern void efx_mtd_rename(struct efx_nic *efx); -extern void efx_mtd_remove(struct efx_nic *efx); +void efx_mtd_rename(struct efx_nic *efx); +void efx_mtd_remove(struct efx_nic *efx); #else static inline int efx_mtd_probe(struct efx_nic *efx) { return 0; } static inline void efx_mtd_rename(struct efx_nic *efx) {} @@ -241,9 +230,9 @@ static inline void efx_schedule_channel_irq(struct efx_channel *channel) efx_schedule_channel(channel); } -extern void efx_link_status_changed(struct efx_nic *efx); -extern void efx_link_set_advertising(struct efx_nic *efx, u32); -extern void efx_link_set_wanted_fc(struct efx_nic *efx, u8); +void efx_link_status_changed(struct efx_nic *efx); +void efx_link_set_advertising(struct efx_nic *efx, u32); +void efx_link_set_wanted_fc(struct efx_nic *efx, u8); static inline void efx_device_detach_sync(struct efx_nic *efx) { diff --git a/drivers/net/ethernet/sfc/enum.h b/drivers/net/ethernet/sfc/enum.h index 7fdfee01909..d1dbb5fb31b 100644 --- a/drivers/net/ethernet/sfc/enum.h +++ b/drivers/net/ethernet/sfc/enum.h @@ -143,6 +143,7 @@ enum efx_loopback_mode { * @RESET_TYPE_WORLD: Reset as much as possible * @RESET_TYPE_RECOVER_OR_DISABLE: Try to recover. Apply RESET_TYPE_DISABLE if * unsuccessful. + * @RESET_TYPE_MC_BIST: MC entering BIST mode. * @RESET_TYPE_DISABLE: Reset datapath, MAC and PHY; leave NIC disabled * @RESET_TYPE_TX_WATCHDOG: reset due to TX watchdog * @RESET_TYPE_INT_ERROR: reset due to internal error @@ -150,14 +151,16 @@ enum efx_loopback_mode { * @RESET_TYPE_DMA_ERROR: DMA error * @RESET_TYPE_TX_SKIP: hardware completed empty tx descriptors * @RESET_TYPE_MC_FAILURE: MC reboot/assertion + * @RESET_TYPE_MCDI_TIMEOUT: MCDI timeout. */ enum reset_type { - RESET_TYPE_INVISIBLE = 0, - RESET_TYPE_RECOVER_OR_ALL = 1, - RESET_TYPE_ALL = 2, - RESET_TYPE_WORLD = 3, - RESET_TYPE_RECOVER_OR_DISABLE = 4, - RESET_TYPE_DISABLE = 5, + RESET_TYPE_INVISIBLE, + RESET_TYPE_RECOVER_OR_ALL, + RESET_TYPE_ALL, + RESET_TYPE_WORLD, + RESET_TYPE_RECOVER_OR_DISABLE, + RESET_TYPE_MC_BIST, + RESET_TYPE_DISABLE, RESET_TYPE_MAX_METHOD, RESET_TYPE_TX_WATCHDOG, RESET_TYPE_INT_ERROR, @@ -165,6 +168,13 @@ enum reset_type { RESET_TYPE_DMA_ERROR, RESET_TYPE_TX_SKIP, RESET_TYPE_MC_FAILURE, + /* RESET_TYPE_MCDI_TIMEOUT is actually a method, not just a reason, but + * it doesn't fit the scope hierarchy (not well-ordered by inclusion). + * We encode this by having its enum value be greater than + * RESET_TYPE_MAX_METHOD. This also prevents issuing it with + * efx_ioctl_reset. + */ + RESET_TYPE_MCDI_TIMEOUT, RESET_TYPE_MAX, }; diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c index 5b471cf5c32..74739c4b999 100644 --- a/drivers/net/ethernet/sfc/ethtool.c +++ b/drivers/net/ethernet/sfc/ethtool.c @@ -70,6 +70,7 @@ static const struct efx_sw_stat_desc efx_sw_stat_desc[] = { EFX_ETHTOOL_UINT_TXQ_STAT(tso_long_headers), EFX_ETHTOOL_UINT_TXQ_STAT(tso_packets), EFX_ETHTOOL_UINT_TXQ_STAT(pushes), + EFX_ETHTOOL_UINT_TXQ_STAT(pio_packets), EFX_ETHTOOL_ATOMIC_NIC_ERROR_STAT(rx_reset), EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_tobe_disc), EFX_ETHTOOL_UINT_CHANNEL_STAT(rx_ip_hdr_chksum_err), @@ -250,6 +251,9 @@ static void efx_fill_test(unsigned int test_index, u8 *strings, u64 *data, * @test_index: Starting index of the test * @strings: Ethtool strings, or %NULL * @data: Ethtool test results, or %NULL + * + * Fill in a block of loopback self-test entries. Return new test + * index. */ static int efx_fill_loopback_test(struct efx_nic *efx, struct efx_loopback_self_tests *lb_tests, @@ -289,6 +293,12 @@ static int efx_fill_loopback_test(struct efx_nic *efx, * @tests: Efx self-test results structure, or %NULL * @strings: Ethtool strings, or %NULL * @data: Ethtool test results, or %NULL + * + * Get self-test number of strings, strings, and/or test results. + * Return number of strings (== number of test results). + * + * The reason for merging these three functions is to make sure that + * they can never be inconsistent. */ static int efx_ethtool_fill_self_tests(struct efx_nic *efx, struct efx_self_tests *tests, @@ -317,6 +327,8 @@ static int efx_ethtool_fill_self_tests(struct efx_nic *efx, "eventq.int", NULL); } + efx_fill_test(n++, strings, data, &tests->memory, + "core", 0, "memory", NULL); efx_fill_test(n++, strings, data, &tests->registers, "core", 0, "registers", NULL); @@ -356,7 +368,8 @@ static int efx_ethtool_get_sset_count(struct net_device *net_dev, switch (string_set) { case ETH_SS_STATS: return efx->type->describe_stats(efx, NULL) + - EFX_ETHTOOL_SW_STAT_COUNT; + EFX_ETHTOOL_SW_STAT_COUNT + + efx_ptp_describe_stats(efx, NULL); case ETH_SS_TEST: return efx_ethtool_fill_self_tests(efx, NULL, NULL, NULL); default: @@ -377,6 +390,8 @@ static void efx_ethtool_get_strings(struct net_device *net_dev, for (i = 0; i < EFX_ETHTOOL_SW_STAT_COUNT; i++) strlcpy(strings + i * ETH_GSTRING_LEN, efx_sw_stat_desc[i].name, ETH_GSTRING_LEN); + strings += EFX_ETHTOOL_SW_STAT_COUNT * ETH_GSTRING_LEN; + efx_ptp_describe_stats(efx, strings); break; case ETH_SS_TEST: efx_ethtool_fill_self_tests(efx, NULL, strings, NULL); @@ -426,8 +441,11 @@ static void efx_ethtool_get_stats(struct net_device *net_dev, break; } } + data += EFX_ETHTOOL_SW_STAT_COUNT; spin_unlock_bh(&efx->stats_lock); + + efx_ptp_update_stats(efx, data); } static void efx_ethtool_self_test(struct net_device *net_dev, @@ -435,7 +453,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev, { struct efx_nic *efx = netdev_priv(net_dev); struct efx_self_tests *efx_tests; - int already_up; + bool already_up; int rc = -ENOMEM; efx_tests = kzalloc(sizeof(*efx_tests), GFP_KERNEL); @@ -443,8 +461,8 @@ static void efx_ethtool_self_test(struct net_device *net_dev, goto fail; if (efx->state != STATE_READY) { - rc = -EIO; - goto fail1; + rc = -EBUSY; + goto out; } netif_info(efx, drv, efx->net_dev, "starting %sline testing\n", @@ -457,7 +475,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev, if (rc) { netif_err(efx, drv, efx->net_dev, "failed opening device.\n"); - goto fail1; + goto out; } } @@ -470,8 +488,7 @@ static void efx_ethtool_self_test(struct net_device *net_dev, rc == 0 ? "passed" : "failed", (test->flags & ETH_TEST_FL_OFFLINE) ? "off" : "on"); -fail1: - /* Fill ethtool results structures */ +out: efx_ethtool_fill_self_tests(efx, efx_tests, NULL, data); kfree(efx_tests); fail: @@ -582,7 +599,7 @@ static void efx_ethtool_get_ringparam(struct net_device *net_dev, struct efx_nic *efx = netdev_priv(net_dev); ring->rx_max_pending = EFX_MAX_DMAQ_SIZE; - ring->tx_max_pending = EFX_MAX_DMAQ_SIZE; + ring->tx_max_pending = EFX_TXQ_MAX_ENT(efx); ring->rx_pending = efx->rxq_entries; ring->tx_pending = efx->txq_entries; } @@ -595,7 +612,7 @@ static int efx_ethtool_set_ringparam(struct net_device *net_dev, if (ring->rx_mini_pending || ring->rx_jumbo_pending || ring->rx_pending > EFX_MAX_DMAQ_SIZE || - ring->tx_pending > EFX_MAX_DMAQ_SIZE) + ring->tx_pending > EFX_TXQ_MAX_ENT(efx)) return -EINVAL; if (ring->rx_pending < EFX_RXQ_MIN_ENT) { @@ -682,7 +699,6 @@ static void efx_ethtool_get_pauseparam(struct net_device *net_dev, pause->autoneg = !!(efx->wanted_fc & EFX_FC_AUTO); } - static void efx_ethtool_get_wol(struct net_device *net_dev, struct ethtool_wolinfo *wol) { @@ -711,7 +727,7 @@ static int efx_ethtool_reset(struct net_device *net_dev, u32 *flags) } /* MAC address mask including only I/G bit */ -static const u8 mac_addr_ig_mask[ETH_ALEN] = { 0x01, 0, 0, 0, 0, 0 }; +static const u8 mac_addr_ig_mask[ETH_ALEN] __aligned(2) = {0x01, 0, 0, 0, 0, 0}; #define IP4_ADDR_FULL_MASK ((__force __be32)~0) #define PORT_FULL_MASK ((__force __be16)~0) @@ -771,16 +787,16 @@ static int efx_ethtool_get_class_rule(struct efx_nic *efx, rule->flow_type = ETHER_FLOW; if (spec.match_flags & (EFX_FILTER_MATCH_LOC_MAC | EFX_FILTER_MATCH_LOC_MAC_IG)) { - memcpy(mac_entry->h_dest, spec.loc_mac, ETH_ALEN); + ether_addr_copy(mac_entry->h_dest, spec.loc_mac); if (spec.match_flags & EFX_FILTER_MATCH_LOC_MAC) - memset(mac_mask->h_dest, ~0, ETH_ALEN); + eth_broadcast_addr(mac_mask->h_dest); else - memcpy(mac_mask->h_dest, mac_addr_ig_mask, - ETH_ALEN); + ether_addr_copy(mac_mask->h_dest, + mac_addr_ig_mask); } if (spec.match_flags & EFX_FILTER_MATCH_REM_MAC) { - memcpy(mac_entry->h_source, spec.rem_mac, ETH_ALEN); - memset(mac_mask->h_source, ~0, ETH_ALEN); + ether_addr_copy(mac_entry->h_source, spec.rem_mac); + eth_broadcast_addr(mac_mask->h_source); } if (spec.match_flags & EFX_FILTER_MATCH_ETHER_TYPE) { mac_entry->h_proto = spec.ether_type; @@ -952,13 +968,13 @@ static int efx_ethtool_set_class_rule(struct efx_nic *efx, spec.match_flags |= EFX_FILTER_MATCH_LOC_MAC; else return -EINVAL; - memcpy(spec.loc_mac, mac_entry->h_dest, ETH_ALEN); + ether_addr_copy(spec.loc_mac, mac_entry->h_dest); } if (!is_zero_ether_addr(mac_mask->h_source)) { if (!is_broadcast_ether_addr(mac_mask->h_source)) return -EINVAL; spec.match_flags |= EFX_FILTER_MATCH_REM_MAC; - memcpy(spec.rem_mac, mac_entry->h_source, ETH_ALEN); + ether_addr_copy(spec.rem_mac, mac_entry->h_source); } if (mac_mask->h_proto) { if (mac_mask->h_proto != ETHER_TYPE_FULL_MASK) @@ -1017,7 +1033,7 @@ static u32 efx_ethtool_get_rxfh_indir_size(struct net_device *net_dev) 0 : ARRAY_SIZE(efx->rx_indir_table)); } -static int efx_ethtool_get_rxfh_indir(struct net_device *net_dev, u32 *indir) +static int efx_ethtool_get_rxfh(struct net_device *net_dev, u32 *indir, u8 *key) { struct efx_nic *efx = netdev_priv(net_dev); @@ -1025,18 +1041,18 @@ static int efx_ethtool_get_rxfh_indir(struct net_device *net_dev, u32 *indir) return 0; } -static int efx_ethtool_set_rxfh_indir(struct net_device *net_dev, - const u32 *indir) +static int efx_ethtool_set_rxfh(struct net_device *net_dev, + const u32 *indir, const u8 *key) { struct efx_nic *efx = netdev_priv(net_dev); memcpy(efx->rx_indir_table, indir, sizeof(efx->rx_indir_table)); - efx_nic_push_rx_indir_table(efx); + efx->type->rx_push_rss_config(efx); return 0; } -int efx_ethtool_get_ts_info(struct net_device *net_dev, - struct ethtool_ts_info *ts_info) +static int efx_ethtool_get_ts_info(struct net_device *net_dev, + struct ethtool_ts_info *ts_info) { struct efx_nic *efx = netdev_priv(net_dev); @@ -1109,8 +1125,8 @@ const struct ethtool_ops efx_ethtool_ops = { .get_rxnfc = efx_ethtool_get_rxnfc, .set_rxnfc = efx_ethtool_set_rxnfc, .get_rxfh_indir_size = efx_ethtool_get_rxfh_indir_size, - .get_rxfh_indir = efx_ethtool_get_rxfh_indir, - .set_rxfh_indir = efx_ethtool_set_rxfh_indir, + .get_rxfh = efx_ethtool_get_rxfh, + .set_rxfh = efx_ethtool_set_rxfh, .get_ts_info = efx_ethtool_get_ts_info, .get_module_info = efx_ethtool_get_module_info, .get_module_eeprom = efx_ethtool_get_module_eeprom, diff --git a/drivers/net/ethernet/sfc/falcon.c b/drivers/net/ethernet/sfc/falcon.c index ff5d322b9b4..fae25a41864 100644 --- a/drivers/net/ethernet/sfc/falcon.c +++ b/drivers/net/ethernet/sfc/falcon.c @@ -422,7 +422,6 @@ static inline void falcon_irq_ack_a1(struct efx_nic *efx) efx_readd(efx, ®, FR_AA_WORK_AROUND_BROKEN_PCI_READS); } - static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id) { struct efx_nic *efx = dev_id; @@ -467,6 +466,25 @@ static irqreturn_t falcon_legacy_interrupt_a1(int irq, void *dev_id) efx_schedule_channel_irq(efx_get_channel(efx, 1)); return IRQ_HANDLED; } + +/************************************************************************** + * + * RSS + * + ************************************************************************** + */ + +static void falcon_b0_rx_push_rss_config(struct efx_nic *efx) +{ + efx_oword_t temp; + + /* Set hash key for IPv4 */ + memcpy(&temp, efx->rx_hash_key, sizeof(temp)); + efx_writeo(efx, &temp, FR_BZ_RX_RSS_TKEY); + + efx_farch_rx_push_indir_table(efx); +} + /************************************************************************** * * EEPROM/flash @@ -1340,6 +1358,7 @@ static void falcon_reconfigure_mac_wrapper(struct efx_nic *efx) case 100: link_speed = 1; break; default: link_speed = 0; break; } + /* MAC_LINK_STATUS controls MAC backpressure but doesn't work * as advertised. Disable to ensure packets are not * indefinitely held and TX queue can be flushed at any point @@ -2164,7 +2183,7 @@ static int falcon_probe_nvconfig(struct efx_nic *efx) } /* Read the MAC addresses */ - memcpy(efx->net_dev->perm_addr, nvconfig->mac_address[0], ETH_ALEN); + ether_addr_copy(efx->net_dev->perm_addr, nvconfig->mac_address[0]); netif_dbg(efx, probe, efx->net_dev, "PHY is %d phy_id %d\n", efx->phy_type, efx->mdio.prtad); @@ -2247,6 +2266,8 @@ static int falcon_probe_nic(struct efx_nic *efx) struct falcon_board *board; int rc; + efx->primary = efx; /* only one usable function per controller */ + /* Allocate storage for hardware specific data */ nic_data = kzalloc(sizeof(*nic_data), GFP_KERNEL); if (!nic_data) @@ -2482,9 +2503,7 @@ static int falcon_init_nic(struct efx_nic *efx) falcon_init_rx_cfg(efx); if (efx_nic_rev(efx) >= EFX_REV_FALCON_B0) { - /* Set hash key for IPv4 */ - memcpy(&temp, efx->rx_hash_key, sizeof(temp)); - efx_writeo(efx, &temp, FR_BZ_RX_RSS_TKEY); + falcon_b0_rx_push_rss_config(efx); /* Set destination of both TX and RX Flush events */ EFX_POPULATE_OWORD_1(temp, FRF_BZ_FLS_EVQ_ID, 0); @@ -2593,6 +2612,14 @@ void falcon_start_nic_stats(struct efx_nic *efx) spin_unlock_bh(&efx->stats_lock); } +/* We don't acutally pull stats on falcon. Wait 10ms so that + * they arrive when we call this just after start_stats + */ +static void falcon_pull_nic_stats(struct efx_nic *efx) +{ + msleep(10); +} + void falcon_stop_nic_stats(struct efx_nic *efx) { struct falcon_nic_data *nic_data = efx->nic_data; @@ -2669,9 +2696,12 @@ const struct efx_nic_type falcon_a1_nic_type = { .fini_dmaq = efx_farch_fini_dmaq, .prepare_flush = falcon_prepare_flush, .finish_flush = efx_port_dummy_op_void, + .prepare_flr = efx_port_dummy_op_void, + .finish_flr = efx_farch_finish_flr, .describe_stats = falcon_describe_nic_stats, .update_stats = falcon_update_nic_stats, .start_stats = falcon_start_nic_stats, + .pull_stats = falcon_pull_nic_stats, .stop_stats = falcon_stop_nic_stats, .set_id_led = falcon_set_id_led, .push_irq_moderation = falcon_push_irq_moderation, @@ -2692,7 +2722,7 @@ const struct efx_nic_type falcon_a1_nic_type = { .tx_init = efx_farch_tx_init, .tx_remove = efx_farch_tx_remove, .tx_write = efx_farch_tx_write, - .rx_push_indir_table = efx_farch_rx_push_indir_table, + .rx_push_rss_config = efx_port_dummy_op_void, .rx_probe = efx_farch_rx_probe, .rx_init = efx_farch_rx_init, .rx_remove = efx_farch_rx_remove, @@ -2762,9 +2792,12 @@ const struct efx_nic_type falcon_b0_nic_type = { .fini_dmaq = efx_farch_fini_dmaq, .prepare_flush = falcon_prepare_flush, .finish_flush = efx_port_dummy_op_void, + .prepare_flr = efx_port_dummy_op_void, + .finish_flr = efx_farch_finish_flr, .describe_stats = falcon_describe_nic_stats, .update_stats = falcon_update_nic_stats, .start_stats = falcon_start_nic_stats, + .pull_stats = falcon_pull_nic_stats, .stop_stats = falcon_stop_nic_stats, .set_id_led = falcon_set_id_led, .push_irq_moderation = falcon_push_irq_moderation, @@ -2786,7 +2819,7 @@ const struct efx_nic_type falcon_b0_nic_type = { .tx_init = efx_farch_tx_init, .tx_remove = efx_farch_tx_remove, .tx_write = efx_farch_tx_write, - .rx_push_indir_table = efx_farch_rx_push_indir_table, + .rx_push_rss_config = falcon_b0_rx_push_rss_config, .rx_probe = efx_farch_rx_probe, .rx_init = efx_farch_rx_init, .rx_remove = efx_farch_rx_remove, @@ -2840,4 +2873,3 @@ const struct efx_nic_type falcon_b0_nic_type = { .mcdi_max_ver = -1, .max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS, }; - diff --git a/drivers/net/ethernet/sfc/farch.c b/drivers/net/ethernet/sfc/farch.c index c0907d884d7..0537381cd2f 100644 --- a/drivers/net/ethernet/sfc/farch.c +++ b/drivers/net/ethernet/sfc/farch.c @@ -311,7 +311,6 @@ static inline void efx_farch_push_tx_desc(struct efx_tx_queue *tx_queue, */ void efx_farch_tx_write(struct efx_tx_queue *tx_queue) { - struct efx_tx_buffer *buffer; efx_qword_t *txd; unsigned write_ptr; @@ -742,6 +741,28 @@ int efx_farch_fini_dmaq(struct efx_nic *efx) return rc; } +/* Reset queue and flush accounting after FLR + * + * One possible cause of FLR recovery is that DMA may be failing (eg. if bus + * mastering was disabled), in which case we don't receive (RXQ) flush + * completion events. This means that efx->rxq_flush_outstanding remained at 4 + * after the FLR; also, efx->active_queues was non-zero (as no flush completion + * events were received, and we didn't go through efx_check_tx_flush_complete()) + * If we don't fix this up, on the next call to efx_realloc_channels() we won't + * flush any RX queues because efx->rxq_flush_outstanding is at the limit of 4 + * for batched flush requests; and the efx->active_queues gets messed up because + * we keep incrementing for the newly initialised queues, but it never went to + * zero previously. Then we get a timeout every time we try to restart the + * queues, as it doesn't go back to zero when we should be flushing the queues. + */ +void efx_farch_finish_flr(struct efx_nic *efx) +{ + atomic_set(&efx->rxq_flush_pending, 0); + atomic_set(&efx->rxq_flush_outstanding, 0); + atomic_set(&efx->active_queues, 0); +} + + /************************************************************************** * * Event queue processing @@ -1147,7 +1168,7 @@ static void efx_farch_handle_generated_event(struct efx_channel *channel, /* The queue must be empty, so we won't receive any rx * events, so efx_process_channel() won't refill the * queue. Refill it here */ - efx_fast_push_rx_descriptors(rx_queue); + efx_fast_push_rx_descriptors(rx_queue, true); } else if (rx_queue && magic == EFX_CHANNEL_MAGIC_RX_DRAIN(rx_queue)) { efx_farch_handle_drain_event(channel); } else if (code == _EFX_CHANNEL_MAGIC_TX_DRAIN) { @@ -1249,6 +1270,9 @@ int efx_farch_ev_process(struct efx_channel *channel, int budget) int tx_packets = 0; int spent = 0; + if (budget <= 0) + return spent; + read_ptr = channel->eventq_read_ptr; for (;;) { @@ -1609,7 +1633,6 @@ irqreturn_t efx_farch_msi_interrupt(int irq, void *dev_id) return IRQ_HANDLED; } - /* Setup RSS indirection table. * This maps from the hash value of the packet to RXQ */ @@ -1618,8 +1641,7 @@ void efx_farch_rx_push_indir_table(struct efx_nic *efx) size_t i = 0; efx_dword_t dword; - if (efx_nic_rev(efx) < EFX_REV_FALCON_B0) - return; + BUG_ON(efx_nic_rev(efx) < EFX_REV_FALCON_B0); BUILD_BUG_ON(ARRAY_SIZE(efx->rx_indir_table) != FR_BZ_RX_INDIRECTION_TBL_ROWS); @@ -1745,8 +1767,6 @@ void efx_farch_init_common(struct efx_nic *efx) EFX_INVERT_OWORD(temp); efx_writeo(efx, &temp, FR_AZ_FATAL_INTR_KER); - efx_farch_rx_push_indir_table(efx); - /* Disable the ugly timer-based TX DMA backoff and allow TX DMA to be * controlled by the RX FIFO fill level. Set arbitration to one pkt/Q. */ @@ -2187,14 +2207,14 @@ efx_farch_filter_to_gen_spec(struct efx_filter_spec *gen_spec, } static void -efx_farch_filter_init_rx_for_stack(struct efx_nic *efx, - struct efx_farch_filter_spec *spec) +efx_farch_filter_init_rx_auto(struct efx_nic *efx, + struct efx_farch_filter_spec *spec) { /* If there's only one channel then disable RSS for non VF * traffic, thereby allowing VFs to use RSS when the PF can't. */ - spec->priority = EFX_FILTER_PRI_REQUIRED; - spec->flags = (EFX_FILTER_FLAG_RX | EFX_FILTER_FLAG_RX_STACK | + spec->priority = EFX_FILTER_PRI_AUTO; + spec->flags = (EFX_FILTER_FLAG_RX | (efx->n_rx_channels > 1 ? EFX_FILTER_FLAG_RX_RSS : 0) | (efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0)); spec->dmaq_id = 0; @@ -2459,20 +2479,13 @@ s32 efx_farch_filter_insert(struct efx_nic *efx, rc = -EEXIST; goto out; } - if (spec.priority < saved_spec->priority && - !(saved_spec->priority == EFX_FILTER_PRI_REQUIRED && - saved_spec->flags & EFX_FILTER_FLAG_RX_STACK)) { + if (spec.priority < saved_spec->priority) { rc = -EPERM; goto out; } - if (spec.flags & EFX_FILTER_FLAG_RX_STACK) { - /* Just make sure it won't be removed */ - saved_spec->flags |= EFX_FILTER_FLAG_RX_STACK; - rc = 0; - goto out; - } - /* Retain the RX_STACK flag */ - spec.flags |= saved_spec->flags & EFX_FILTER_FLAG_RX_STACK; + if (saved_spec->priority == EFX_FILTER_PRI_AUTO || + saved_spec->flags & EFX_FILTER_FLAG_RX_OVER_AUTO) + spec.flags |= EFX_FILTER_FLAG_RX_OVER_AUTO; } /* Insert the filter */ @@ -2553,11 +2566,11 @@ static int efx_farch_filter_remove(struct efx_nic *efx, struct efx_farch_filter_spec *spec = &table->spec[filter_idx]; if (!test_bit(filter_idx, table->used_bitmap) || - spec->priority > priority) + spec->priority != priority) return -ENOENT; - if (spec->flags & EFX_FILTER_FLAG_RX_STACK) { - efx_farch_filter_init_rx_for_stack(efx, spec); + if (spec->flags & EFX_FILTER_FLAG_RX_OVER_AUTO) { + efx_farch_filter_init_rx_auto(efx, spec); efx_farch_filter_push_rx_config(efx); } else { efx_farch_filter_table_clear_entry(efx, table, filter_idx); @@ -2640,12 +2653,15 @@ efx_farch_filter_table_clear(struct efx_nic *efx, unsigned int filter_idx; spin_lock_bh(&efx->filter_lock); - for (filter_idx = 0; filter_idx < table->size; ++filter_idx) - efx_farch_filter_remove(efx, table, filter_idx, priority); + for (filter_idx = 0; filter_idx < table->size; ++filter_idx) { + if (table->spec[filter_idx].priority != EFX_FILTER_PRI_AUTO) + efx_farch_filter_remove(efx, table, + filter_idx, priority); + } spin_unlock_bh(&efx->filter_lock); } -void efx_farch_filter_clear_rx(struct efx_nic *efx, +int efx_farch_filter_clear_rx(struct efx_nic *efx, enum efx_filter_priority priority) { efx_farch_filter_table_clear(efx, EFX_FARCH_FILTER_TABLE_RX_IP, @@ -2654,6 +2670,7 @@ void efx_farch_filter_clear_rx(struct efx_nic *efx, priority); efx_farch_filter_table_clear(efx, EFX_FARCH_FILTER_TABLE_RX_DEF, priority); + return 0; } u32 efx_farch_filter_count_rx_used(struct efx_nic *efx, @@ -2822,7 +2839,7 @@ int efx_farch_filter_table_probe(struct efx_nic *efx) for (i = 0; i < EFX_FARCH_FILTER_SIZE_RX_DEF; i++) { spec = &table->spec[i]; spec->type = EFX_FARCH_FILTER_UC_DEF + i; - efx_farch_filter_init_rx_for_stack(efx, spec); + efx_farch_filter_init_rx_auto(efx, spec); __set_bit(i, table->used_bitmap); } } diff --git a/drivers/net/ethernet/sfc/filter.h b/drivers/net/ethernet/sfc/filter.h index 63c77a55717..d0ed7f71ea7 100644 --- a/drivers/net/ethernet/sfc/filter.h +++ b/drivers/net/ethernet/sfc/filter.h @@ -59,12 +59,16 @@ enum efx_filter_match_flags { /** * enum efx_filter_priority - priority of a hardware filter specification * @EFX_FILTER_PRI_HINT: Performance hint + * @EFX_FILTER_PRI_AUTO: Automatic filter based on device address list + * or hardware requirements. This may only be used by the filter + * implementation for each NIC type. * @EFX_FILTER_PRI_MANUAL: Manually configured filter * @EFX_FILTER_PRI_REQUIRED: Required for correct behaviour (user-level * networking and SR-IOV) */ enum efx_filter_priority { EFX_FILTER_PRI_HINT = 0, + EFX_FILTER_PRI_AUTO, EFX_FILTER_PRI_MANUAL, EFX_FILTER_PRI_REQUIRED, }; @@ -78,19 +82,18 @@ enum efx_filter_priority { * according to the indirection table. * @EFX_FILTER_FLAG_RX_SCATTER: Enable DMA scatter on the receiving * queue. - * @EFX_FILTER_FLAG_RX_STACK: Indicates a filter inserted for the - * network stack. The filter must have a priority of - * %EFX_FILTER_PRI_REQUIRED. It can be steered by a replacement - * request with priority %EFX_FILTER_PRI_MANUAL, and a removal - * request with priority %EFX_FILTER_PRI_MANUAL will reset the - * steering (but not remove the filter). + * @EFX_FILTER_FLAG_RX_OVER_AUTO: Indicates a filter that is + * overriding an automatic filter (priority + * %EFX_FILTER_PRI_AUTO). This may only be set by the filter + * implementation for each type. A removal request will restore + * the automatic filter in its place. * @EFX_FILTER_FLAG_RX: Filter is for RX * @EFX_FILTER_FLAG_TX: Filter is for TX */ enum efx_filter_flags { EFX_FILTER_FLAG_RX_RSS = 0x01, EFX_FILTER_FLAG_RX_SCATTER = 0x02, - EFX_FILTER_FLAG_RX_STACK = 0x04, + EFX_FILTER_FLAG_RX_OVER_AUTO = 0x04, EFX_FILTER_FLAG_RX = 0x08, EFX_FILTER_FLAG_TX = 0x10, }; @@ -240,7 +243,7 @@ static inline int efx_filter_set_eth_local(struct efx_filter_spec *spec, } if (addr != NULL) { spec->match_flags |= EFX_FILTER_MATCH_LOC_MAC; - memcpy(spec->loc_mac, addr, ETH_ALEN); + ether_addr_copy(spec->loc_mac, addr); } return 0; } diff --git a/drivers/net/ethernet/sfc/io.h b/drivers/net/ethernet/sfc/io.h index 96ce507d860..afb94aa2c15 100644 --- a/drivers/net/ethernet/sfc/io.h +++ b/drivers/net/ethernet/sfc/io.h @@ -66,6 +66,18 @@ #define EFX_USE_QWORD_IO 1 #endif +/* Hardware issue requires that only 64-bit naturally aligned writes + * are seen by hardware. Its not strictly necessary to restrict to + * x86_64 arch, but done for safety since unusual write combining behaviour + * can break PIO. + */ +#ifdef CONFIG_X86_64 +/* PIO is a win only if write-combining is possible */ +#ifdef ARCH_HAS_IOREMAP_WC +#define EFX_USE_PIO 1 +#endif +#endif + #ifdef EFX_USE_QWORD_IO static inline void _efx_writeq(struct efx_nic *efx, __le64 value, unsigned int reg) diff --git a/drivers/net/ethernet/sfc/mcdi.c b/drivers/net/ethernet/sfc/mcdi.c index 128d7cdf9eb..5239cf9bdc5 100644 --- a/drivers/net/ethernet/sfc/mcdi.c +++ b/drivers/net/ethernet/sfc/mcdi.c @@ -27,10 +27,10 @@ /* A reboot/assertion causes the MCDI status word to be set after the * command word is set or a REBOOT event is sent. If we notice a reboot - * via these mechanisms then wait 20ms for the status word to be set. + * via these mechanisms then wait 250ms for the status word to be set. */ #define MCDI_STATUS_DELAY_US 100 -#define MCDI_STATUS_DELAY_COUNT 200 +#define MCDI_STATUS_DELAY_COUNT 2500 #define MCDI_STATUS_SLEEP_MS \ (MCDI_STATUS_DELAY_US * MCDI_STATUS_DELAY_COUNT / 1000) @@ -42,6 +42,7 @@ struct efx_mcdi_async_param { unsigned int cmd; size_t inlen; size_t outlen; + bool quiet; efx_mcdi_async_completer *complete; unsigned long cookie; /* followed by request/response buffer */ @@ -50,12 +51,8 @@ struct efx_mcdi_async_param { static void efx_mcdi_timeout_async(unsigned long context); static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating, bool *was_attached_out); - -static inline struct efx_mcdi_iface *efx_mcdi(struct efx_nic *efx) -{ - EFX_BUG_ON_PARANOID(!efx->mcdi); - return &efx->mcdi->iface; -} +static bool efx_mcdi_poll_once(struct efx_nic *efx); +static void efx_mcdi_abandon(struct efx_nic *efx); int efx_mcdi_init(struct efx_nic *efx) { @@ -100,6 +97,10 @@ int efx_mcdi_init(struct efx_nic *efx) netif_err(efx, probe, efx->net_dev, "Host already registered with MCPU\n"); + if (efx->mcdi->fn_flags & + (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY)) + efx->primary = efx; + return 0; } @@ -190,6 +191,8 @@ static int efx_mcdi_errno(unsigned int mcdi_err) TRANSLATE_ERROR(EALREADY); TRANSLATE_ERROR(ENOSPC); #undef TRANSLATE_ERROR + case MC_CMD_ERR_ENOTSUP: + return -EOPNOTSUPP; case MC_CMD_ERR_ALLOC_FAIL: return -ENOBUFS; case MC_CMD_ERR_MAC_EXIST: @@ -237,6 +240,21 @@ static void efx_mcdi_read_response_header(struct efx_nic *efx) } } +static bool efx_mcdi_poll_once(struct efx_nic *efx) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + + rmb(); + if (!efx->type->mcdi_poll_response(efx)) + return false; + + spin_lock_bh(&mcdi->iface_lock); + efx_mcdi_read_response_header(efx); + spin_unlock_bh(&mcdi->iface_lock); + + return true; +} + static int efx_mcdi_poll(struct efx_nic *efx) { struct efx_mcdi_iface *mcdi = efx_mcdi(efx); @@ -272,18 +290,13 @@ static int efx_mcdi_poll(struct efx_nic *efx) time = jiffies; - rmb(); - if (efx->type->mcdi_poll_response(efx)) + if (efx_mcdi_poll_once(efx)) break; if (time_after(time, finish)) return -ETIMEDOUT; } - spin_lock_bh(&mcdi->iface_lock); - efx_mcdi_read_response_header(efx); - spin_unlock_bh(&mcdi->iface_lock); - /* Return rc=0 like wait_event_timeout() */ return 0; } @@ -391,8 +404,9 @@ static bool efx_mcdi_complete_async(struct efx_mcdi_iface *mcdi, bool timeout) { struct efx_nic *efx = mcdi->efx; struct efx_mcdi_async_param *async; - size_t hdr_len, data_len; + size_t hdr_len, data_len, err_len; efx_dword_t *outbuf; + MCDI_DECLARE_BUF_OUT_OR_ERR(errbuf, 0); int rc; if (cmpxchg(&mcdi->state, @@ -433,6 +447,13 @@ static bool efx_mcdi_complete_async(struct efx_mcdi_iface *mcdi, bool timeout) outbuf = (efx_dword_t *)(async + 1); efx->type->mcdi_read_response(efx, outbuf, hdr_len, min(async->outlen, data_len)); + if (!timeout && rc && !async->quiet) { + err_len = min(sizeof(errbuf), data_len); + efx->type->mcdi_read_response(efx, errbuf, hdr_len, + sizeof(errbuf)); + efx_mcdi_display_error(efx, async->cmd, async->inlen, errbuf, + err_len, rc); + } async->complete(efx, async->cookie, rc, outbuf, data_len); kfree(async); @@ -508,18 +529,131 @@ efx_mcdi_check_supported(struct efx_nic *efx, unsigned int cmd, size_t inlen) return 0; } +static int _efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, + efx_dword_t *outbuf, size_t outlen, + size_t *outlen_actual, bool quiet) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + MCDI_DECLARE_BUF_OUT_OR_ERR(errbuf, 0); + int rc; + + if (mcdi->mode == MCDI_MODE_POLL) + rc = efx_mcdi_poll(efx); + else + rc = efx_mcdi_await_completion(efx); + + if (rc != 0) { + netif_err(efx, hw, efx->net_dev, + "MC command 0x%x inlen %d mode %d timed out\n", + cmd, (int)inlen, mcdi->mode); + + if (mcdi->mode == MCDI_MODE_EVENTS && efx_mcdi_poll_once(efx)) { + netif_err(efx, hw, efx->net_dev, + "MCDI request was completed without an event\n"); + rc = 0; + } + + efx_mcdi_abandon(efx); + + /* Close the race with efx_mcdi_ev_cpl() executing just too late + * and completing a request we've just cancelled, by ensuring + * that the seqno check therein fails. + */ + spin_lock_bh(&mcdi->iface_lock); + ++mcdi->seqno; + ++mcdi->credits; + spin_unlock_bh(&mcdi->iface_lock); + } + + if (rc != 0) { + if (outlen_actual) + *outlen_actual = 0; + } else { + size_t hdr_len, data_len, err_len; + + /* At the very least we need a memory barrier here to ensure + * we pick up changes from efx_mcdi_ev_cpl(). Protect against + * a spurious efx_mcdi_ev_cpl() running concurrently by + * acquiring the iface_lock. */ + spin_lock_bh(&mcdi->iface_lock); + rc = mcdi->resprc; + hdr_len = mcdi->resp_hdr_len; + data_len = mcdi->resp_data_len; + err_len = min(sizeof(errbuf), data_len); + spin_unlock_bh(&mcdi->iface_lock); + + BUG_ON(rc > 0); + + efx->type->mcdi_read_response(efx, outbuf, hdr_len, + min(outlen, data_len)); + if (outlen_actual) + *outlen_actual = data_len; + + efx->type->mcdi_read_response(efx, errbuf, hdr_len, err_len); + + if (cmd == MC_CMD_REBOOT && rc == -EIO) { + /* Don't reset if MC_CMD_REBOOT returns EIO */ + } else if (rc == -EIO || rc == -EINTR) { + netif_err(efx, hw, efx->net_dev, "MC fatal error %d\n", + -rc); + efx_schedule_reset(efx, RESET_TYPE_MC_FAILURE); + } else if (rc && !quiet) { + efx_mcdi_display_error(efx, cmd, inlen, errbuf, err_len, + rc); + } + + if (rc == -EIO || rc == -EINTR) { + msleep(MCDI_STATUS_SLEEP_MS); + efx_mcdi_poll_reboot(efx); + mcdi->new_epoch = true; + } + } + + efx_mcdi_release(mcdi); + return rc; +} + +static int _efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, + const efx_dword_t *inbuf, size_t inlen, + efx_dword_t *outbuf, size_t outlen, + size_t *outlen_actual, bool quiet) +{ + int rc; + + rc = efx_mcdi_rpc_start(efx, cmd, inbuf, inlen); + if (rc) { + if (outlen_actual) + *outlen_actual = 0; + return rc; + } + return _efx_mcdi_rpc_finish(efx, cmd, inlen, outbuf, outlen, + outlen_actual, quiet); +} + int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, const efx_dword_t *inbuf, size_t inlen, efx_dword_t *outbuf, size_t outlen, size_t *outlen_actual) { - int rc; + return _efx_mcdi_rpc(efx, cmd, inbuf, inlen, outbuf, outlen, + outlen_actual, false); +} - rc = efx_mcdi_rpc_start(efx, cmd, inbuf, inlen); - if (rc) - return rc; - return efx_mcdi_rpc_finish(efx, cmd, inlen, - outbuf, outlen, outlen_actual); +/* Normally, on receiving an error code in the MCDI response, + * efx_mcdi_rpc will log an error message containing (among other + * things) the raw error code, by means of efx_mcdi_display_error. + * This _quiet version suppresses that; if the caller wishes to log + * the error conditionally on the return code, it should call this + * function and is then responsible for calling efx_mcdi_display_error + * as needed. + */ +int efx_mcdi_rpc_quiet(struct efx_nic *efx, unsigned cmd, + const efx_dword_t *inbuf, size_t inlen, + efx_dword_t *outbuf, size_t outlen, + size_t *outlen_actual) +{ + return _efx_mcdi_rpc(efx, cmd, inbuf, inlen, outbuf, outlen, + outlen_actual, true); } int efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd, @@ -532,35 +666,22 @@ int efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd, if (rc) return rc; + if (efx->mc_bist_for_other_fn) + return -ENETDOWN; + + if (mcdi->mode == MCDI_MODE_FAIL) + return -ENETDOWN; + efx_mcdi_acquire_sync(mcdi); efx_mcdi_send_request(efx, cmd, inbuf, inlen); return 0; } -/** - * efx_mcdi_rpc_async - Schedule an MCDI command to run asynchronously - * @efx: NIC through which to issue the command - * @cmd: Command type number - * @inbuf: Command parameters - * @inlen: Length of command parameters, in bytes - * @outlen: Length to allocate for response buffer, in bytes - * @complete: Function to be called on completion or cancellation. - * @cookie: Arbitrary value to be passed to @complete. - * - * This function does not sleep and therefore may be called in atomic - * context. It will fail if event queues are disabled or if MCDI - * event completions have been disabled due to an error. - * - * If it succeeds, the @complete function will be called exactly once - * in atomic context, when one of the following occurs: - * (a) the completion event is received (in NAPI context) - * (b) event queues are disabled (in the process that disables them) - * (c) the request times-out (in timer context) - */ -int -efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd, - const efx_dword_t *inbuf, size_t inlen, size_t outlen, - efx_mcdi_async_completer *complete, unsigned long cookie) +static int _efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd, + const efx_dword_t *inbuf, size_t inlen, + size_t outlen, + efx_mcdi_async_completer *complete, + unsigned long cookie, bool quiet) { struct efx_mcdi_iface *mcdi = efx_mcdi(efx); struct efx_mcdi_async_param *async; @@ -570,6 +691,9 @@ efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd, if (rc) return rc; + if (efx->mc_bist_for_other_fn) + return -ENETDOWN; + async = kmalloc(sizeof(*async) + ALIGN(max(inlen, outlen), 4), GFP_ATOMIC); if (!async) @@ -578,6 +702,7 @@ efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd, async->cmd = cmd; async->inlen = inlen; async->outlen = outlen; + async->quiet = quiet; async->complete = complete; async->cookie = cookie; memcpy(async + 1, inbuf, inlen); @@ -606,71 +731,73 @@ efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd, return rc; } +/** + * efx_mcdi_rpc_async - Schedule an MCDI command to run asynchronously + * @efx: NIC through which to issue the command + * @cmd: Command type number + * @inbuf: Command parameters + * @inlen: Length of command parameters, in bytes + * @outlen: Length to allocate for response buffer, in bytes + * @complete: Function to be called on completion or cancellation. + * @cookie: Arbitrary value to be passed to @complete. + * + * This function does not sleep and therefore may be called in atomic + * context. It will fail if event queues are disabled or if MCDI + * event completions have been disabled due to an error. + * + * If it succeeds, the @complete function will be called exactly once + * in atomic context, when one of the following occurs: + * (a) the completion event is received (in NAPI context) + * (b) event queues are disabled (in the process that disables them) + * (c) the request times-out (in timer context) + */ +int +efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd, + const efx_dword_t *inbuf, size_t inlen, size_t outlen, + efx_mcdi_async_completer *complete, unsigned long cookie) +{ + return _efx_mcdi_rpc_async(efx, cmd, inbuf, inlen, outlen, complete, + cookie, false); +} + +int efx_mcdi_rpc_async_quiet(struct efx_nic *efx, unsigned int cmd, + const efx_dword_t *inbuf, size_t inlen, + size_t outlen, efx_mcdi_async_completer *complete, + unsigned long cookie) +{ + return _efx_mcdi_rpc_async(efx, cmd, inbuf, inlen, outlen, complete, + cookie, true); +} + int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, efx_dword_t *outbuf, size_t outlen, size_t *outlen_actual) { - struct efx_mcdi_iface *mcdi = efx_mcdi(efx); - int rc; - - if (mcdi->mode == MCDI_MODE_POLL) - rc = efx_mcdi_poll(efx); - else - rc = efx_mcdi_await_completion(efx); - - if (rc != 0) { - /* Close the race with efx_mcdi_ev_cpl() executing just too late - * and completing a request we've just cancelled, by ensuring - * that the seqno check therein fails. - */ - spin_lock_bh(&mcdi->iface_lock); - ++mcdi->seqno; - ++mcdi->credits; - spin_unlock_bh(&mcdi->iface_lock); - - netif_err(efx, hw, efx->net_dev, - "MC command 0x%x inlen %d mode %d timed out\n", - cmd, (int)inlen, mcdi->mode); - } else { - size_t hdr_len, data_len; - - /* At the very least we need a memory barrier here to ensure - * we pick up changes from efx_mcdi_ev_cpl(). Protect against - * a spurious efx_mcdi_ev_cpl() running concurrently by - * acquiring the iface_lock. */ - spin_lock_bh(&mcdi->iface_lock); - rc = mcdi->resprc; - hdr_len = mcdi->resp_hdr_len; - data_len = mcdi->resp_data_len; - spin_unlock_bh(&mcdi->iface_lock); - - BUG_ON(rc > 0); + return _efx_mcdi_rpc_finish(efx, cmd, inlen, outbuf, outlen, + outlen_actual, false); +} - if (rc == 0) { - efx->type->mcdi_read_response(efx, outbuf, hdr_len, - min(outlen, data_len)); - if (outlen_actual != NULL) - *outlen_actual = data_len; - } else if (cmd == MC_CMD_REBOOT && rc == -EIO) - ; /* Don't reset if MC_CMD_REBOOT returns EIO */ - else if (rc == -EIO || rc == -EINTR) { - netif_err(efx, hw, efx->net_dev, "MC fatal error %d\n", - -rc); - efx_schedule_reset(efx, RESET_TYPE_MC_FAILURE); - } else - netif_dbg(efx, hw, efx->net_dev, - "MC command 0x%x inlen %d failed rc=%d\n", - cmd, (int)inlen, -rc); +int efx_mcdi_rpc_finish_quiet(struct efx_nic *efx, unsigned cmd, size_t inlen, + efx_dword_t *outbuf, size_t outlen, + size_t *outlen_actual) +{ + return _efx_mcdi_rpc_finish(efx, cmd, inlen, outbuf, outlen, + outlen_actual, true); +} - if (rc == -EIO || rc == -EINTR) { - msleep(MCDI_STATUS_SLEEP_MS); - efx_mcdi_poll_reboot(efx); - mcdi->new_epoch = true; - } - } +void efx_mcdi_display_error(struct efx_nic *efx, unsigned cmd, + size_t inlen, efx_dword_t *outbuf, + size_t outlen, int rc) +{ + int code = 0, err_arg = 0; - efx_mcdi_release(mcdi); - return rc; + if (outlen >= MC_CMD_ERR_CODE_OFST + 4) + code = MCDI_DWORD(outbuf, ERR_CODE); + if (outlen >= MC_CMD_ERR_ARG_OFST + 4) + err_arg = MCDI_DWORD(outbuf, ERR_ARG); + netif_err(efx, hw, efx->net_dev, + "MC command 0x%x inlen %d failed rc=%d (raw=%d) arg=%d\n", + cmd, (int)inlen, rc, code, err_arg); } /* Switch to polled MCDI completions. This can be called in various @@ -685,7 +812,11 @@ void efx_mcdi_mode_poll(struct efx_nic *efx) return; mcdi = efx_mcdi(efx); - if (mcdi->mode == MCDI_MODE_POLL) + /* If already in polling mode, nothing to do. + * If in fail-fast state, don't switch to polled completion. + * FLR recovery will do that later. + */ + if (mcdi->mode == MCDI_MODE_POLL || mcdi->mode == MCDI_MODE_FAIL) return; /* We can switch from event completion to polled completion, because @@ -714,8 +845,8 @@ void efx_mcdi_flush_async(struct efx_nic *efx) mcdi = efx_mcdi(efx); - /* We must be in polling mode so no more requests can be queued */ - BUG_ON(mcdi->mode != MCDI_MODE_POLL); + /* We must be in poll or fail mode so no more requests can be queued */ + BUG_ON(mcdi->mode == MCDI_MODE_EVENTS); del_timer_sync(&mcdi->async_timer); @@ -748,8 +879,11 @@ void efx_mcdi_mode_event(struct efx_nic *efx) return; mcdi = efx_mcdi(efx); - - if (mcdi->mode == MCDI_MODE_EVENTS) + /* If already in event completion mode, nothing to do. + * If in fail-fast state, don't switch to event completion. FLR + * recovery will do that later. + */ + if (mcdi->mode == MCDI_MODE_EVENTS || mcdi->mode == MCDI_MODE_FAIL) return; /* We can't switch from polled to event completion in the middle of a @@ -800,9 +934,6 @@ static void efx_mcdi_ev_death(struct efx_nic *efx, int rc) } else { int count; - /* Nobody was waiting for an MCDI request, so trigger a reset */ - efx_schedule_reset(efx, RESET_TYPE_MC_FAILURE); - /* Consume the status word since efx_mcdi_rpc_finish() won't */ for (count = 0; count < MCDI_STATUS_DELAY_COUNT; ++count) { if (efx_mcdi_poll_reboot(efx)) @@ -810,11 +941,51 @@ static void efx_mcdi_ev_death(struct efx_nic *efx, int rc) udelay(MCDI_STATUS_DELAY_US); } mcdi->new_epoch = true; + + /* Nobody was waiting for an MCDI request, so trigger a reset */ + efx_schedule_reset(efx, RESET_TYPE_MC_FAILURE); } spin_unlock(&mcdi->iface_lock); } +/* The MC is going down in to BIST mode. set the BIST flag to block + * new MCDI, cancel any outstanding MCDI and and schedule a BIST-type reset + * (which doesn't actually execute a reset, it waits for the controlling + * function to reset it). + */ +static void efx_mcdi_ev_bist(struct efx_nic *efx) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + + spin_lock(&mcdi->iface_lock); + efx->mc_bist_for_other_fn = true; + if (efx_mcdi_complete_sync(mcdi)) { + if (mcdi->mode == MCDI_MODE_EVENTS) { + mcdi->resprc = -EIO; + mcdi->resp_hdr_len = 0; + mcdi->resp_data_len = 0; + ++mcdi->credits; + } + } + mcdi->new_epoch = true; + efx_schedule_reset(efx, RESET_TYPE_MC_BIST); + spin_unlock(&mcdi->iface_lock); +} + +/* MCDI timeouts seen, so make all MCDI calls fail-fast and issue an FLR to try + * to recover. + */ +static void efx_mcdi_abandon(struct efx_nic *efx) +{ + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + + if (xchg(&mcdi->mode, MCDI_MODE_FAIL) == MCDI_MODE_FAIL) + return; /* it had already been done */ + netif_dbg(efx, hw, efx->net_dev, "MCDI is timing out; trying to recover\n"); + efx_schedule_reset(efx, RESET_TYPE_MCDI_TIMEOUT); +} + /* Called from falcon_process_eventq for MCDI events */ void efx_mcdi_process_event(struct efx_channel *channel, efx_qword_t *event) @@ -848,14 +1019,18 @@ void efx_mcdi_process_event(struct efx_channel *channel, efx_mcdi_sensor_event(efx, event); break; case MCDI_EVENT_CODE_SCHEDERR: - netif_info(efx, hw, efx->net_dev, - "MC Scheduler error address=0x%x\n", data); + netif_dbg(efx, hw, efx->net_dev, + "MC Scheduler alert (0x%x)\n", data); break; case MCDI_EVENT_CODE_REBOOT: case MCDI_EVENT_CODE_MC_REBOOT: netif_info(efx, hw, efx->net_dev, "MC Reboot\n"); efx_mcdi_ev_death(efx, -EIO); break; + case MCDI_EVENT_CODE_MC_BIST: + netif_info(efx, hw, efx->net_dev, "MC entered BIST mode\n"); + efx_mcdi_ev_bist(efx); + break; case MCDI_EVENT_CODE_MAC_STATS_DMA: /* MAC stats are gather lazily. We can ignore this. */ break; @@ -867,6 +1042,9 @@ void efx_mcdi_process_event(struct efx_channel *channel, case MCDI_EVENT_CODE_PTP_PPS: efx_ptp_event(efx, event); break; + case MCDI_EVENT_CODE_PTP_TIME: + efx_time_sync_event(channel, event); + break; case MCDI_EVENT_CODE_TX_FLUSH: case MCDI_EVENT_CODE_RX_FLUSH: /* Two flush events will be sent: one to the same event @@ -963,7 +1141,7 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating, bool *was_attached) { MCDI_DECLARE_BUF(inbuf, MC_CMD_DRV_ATTACH_IN_LEN); - MCDI_DECLARE_BUF(outbuf, MC_CMD_DRV_ATTACH_OUT_LEN); + MCDI_DECLARE_BUF(outbuf, MC_CMD_DRV_ATTACH_EXT_OUT_LEN); size_t outlen; int rc; @@ -981,6 +1159,36 @@ static int efx_mcdi_drv_attach(struct efx_nic *efx, bool driver_operating, goto fail; } + if (driver_operating) { + if (outlen >= MC_CMD_DRV_ATTACH_EXT_OUT_LEN) { + efx->mcdi->fn_flags = + MCDI_DWORD(outbuf, + DRV_ATTACH_EXT_OUT_FUNC_FLAGS); + } else { + /* Synthesise flags for Siena */ + efx->mcdi->fn_flags = + 1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL | + 1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED | + (efx_port_num(efx) == 0) << + MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY; + } + } + + /* We currently assume we have control of the external link + * and are completely trusted by firmware. Abort probing + * if that's not true for this function. + */ + if (driver_operating && + (efx->mcdi->fn_flags & + (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL | + 1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED)) != + (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_LINKCTRL | + 1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_TRUSTED)) { + netif_err(efx, probe, efx->net_dev, + "This driver version only supports one function per port\n"); + return -ENODEV; + } + if (was_attached != NULL) *was_attached = MCDI_DWORD(outbuf, DRV_ATTACH_OUT_OLD_STATE); return 0; @@ -999,6 +1207,9 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address, int rc; BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_IN_LEN != 0); + /* we need __aligned(2) for ether_addr_copy */ + BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0_OFST & 1); + BUILD_BUG_ON(MC_CMD_GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1_OFST & 1); rc = efx_mcdi_rpc(efx, MC_CMD_GET_BOARD_CFG, NULL, 0, outbuf, sizeof(outbuf), &outlen); @@ -1011,11 +1222,10 @@ int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address, } if (mac_address) - memcpy(mac_address, - port_num ? - MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1) : - MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0), - ETH_ALEN); + ether_addr_copy(mac_address, + port_num ? + MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT1) : + MCDI_PTR(outbuf, GET_BOARD_CFG_OUT_MAC_ADDR_BASE_PORT0)); if (fw_subtype_list) { for (i = 0; i < MCDI_VAR_ARRAY_LEN(outlen, @@ -1062,13 +1272,6 @@ int efx_mcdi_log_ctrl(struct efx_nic *efx, bool evq, bool uart, u32 dest_evq) rc = efx_mcdi_rpc(efx, MC_CMD_LOG_CTRL, inbuf, sizeof(inbuf), NULL, 0, NULL); - if (rc) - goto fail; - - return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); return rc; } @@ -1185,7 +1388,7 @@ fail1: static int efx_mcdi_read_assertion(struct efx_nic *efx) { MCDI_DECLARE_BUF(inbuf, MC_CMD_GET_ASSERTS_IN_LEN); - MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_ASSERTS_OUT_LEN); + MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, MC_CMD_GET_ASSERTS_OUT_LEN); unsigned int flags, index; const char *reason; size_t outlen; @@ -1200,13 +1403,17 @@ static int efx_mcdi_read_assertion(struct efx_nic *efx) retry = 2; do { MCDI_SET_DWORD(inbuf, GET_ASSERTS_IN_CLEAR, 1); - rc = efx_mcdi_rpc(efx, MC_CMD_GET_ASSERTS, - inbuf, MC_CMD_GET_ASSERTS_IN_LEN, - outbuf, sizeof(outbuf), &outlen); + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_GET_ASSERTS, + inbuf, MC_CMD_GET_ASSERTS_IN_LEN, + outbuf, sizeof(outbuf), &outlen); } while ((rc == -EINTR || rc == -EIO) && retry-- > 0); - if (rc) + if (rc) { + efx_mcdi_display_error(efx, MC_CMD_GET_ASSERTS, + MC_CMD_GET_ASSERTS_IN_LEN, outbuf, + outlen, rc); return rc; + } if (outlen < MC_CMD_GET_ASSERTS_OUT_LEN) return -EIO; @@ -1284,17 +1491,18 @@ void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode) rc = efx_mcdi_rpc(efx, MC_CMD_SET_ID_LED, inbuf, sizeof(inbuf), NULL, 0, NULL); - if (rc) - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", - __func__, rc); } -static int efx_mcdi_reset_port(struct efx_nic *efx) +static int efx_mcdi_reset_func(struct efx_nic *efx) { - int rc = efx_mcdi_rpc(efx, MC_CMD_ENTITY_RESET, NULL, 0, NULL, 0, NULL); - if (rc) - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", - __func__, rc); + MCDI_DECLARE_BUF(inbuf, MC_CMD_ENTITY_RESET_IN_LEN); + int rc; + + BUILD_BUG_ON(MC_CMD_ENTITY_RESET_OUT_LEN != 0); + MCDI_POPULATE_DWORD_1(inbuf, ENTITY_RESET_IN_FLAG, + ENTITY_RESET_IN_FUNCTION_RESOURCE_RESET, 1); + rc = efx_mcdi_rpc(efx, MC_CMD_ENTITY_RESET, inbuf, sizeof(inbuf), + NULL, 0, NULL); return rc; } @@ -1312,7 +1520,6 @@ static int efx_mcdi_reset_mc(struct efx_nic *efx) return 0; if (rc == 0) rc = -EIO; - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); return rc; } @@ -1325,6 +1532,19 @@ int efx_mcdi_reset(struct efx_nic *efx, enum reset_type method) { int rc; + /* If MCDI is down, we can't handle_assertion */ + if (method == RESET_TYPE_MCDI_TIMEOUT) { + rc = pci_reset_function(efx->pci_dev); + if (rc) + return rc; + /* Re-enable polled MCDI completion */ + if (efx->mcdi) { + struct efx_mcdi_iface *mcdi = efx_mcdi(efx); + mcdi->mode = MCDI_MODE_POLL; + } + return 0; + } + /* Recover from a failed assertion pre-reset */ rc = efx_mcdi_handle_assertion(efx); if (rc) @@ -1333,7 +1553,7 @@ int efx_mcdi_reset(struct efx_nic *efx, enum reset_type method) if (method == RESET_TYPE_WORLD) return efx_mcdi_reset_mc(efx); else - return efx_mcdi_reset_port(efx); + return efx_mcdi_reset_func(efx); } static int efx_mcdi_wol_filter_set(struct efx_nic *efx, u32 type, @@ -1347,7 +1567,7 @@ static int efx_mcdi_wol_filter_set(struct efx_nic *efx, u32 type, MCDI_SET_DWORD(inbuf, WOL_FILTER_SET_IN_WOL_TYPE, type); MCDI_SET_DWORD(inbuf, WOL_FILTER_SET_IN_FILTER_MODE, MC_CMD_FILTER_MODE_SIMPLE); - memcpy(MCDI_PTR(inbuf, WOL_FILTER_SET_IN_MAGIC_MAC), mac, ETH_ALEN); + ether_addr_copy(MCDI_PTR(inbuf, WOL_FILTER_SET_IN_MAGIC_MAC), mac); rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_SET, inbuf, sizeof(inbuf), outbuf, sizeof(outbuf), &outlen); @@ -1414,13 +1634,6 @@ int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id) rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_REMOVE, inbuf, sizeof(inbuf), NULL, 0, NULL); - if (rc) - goto fail; - - return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); return rc; } @@ -1461,13 +1674,6 @@ int efx_mcdi_wol_filter_reset(struct efx_nic *efx) int rc; rc = efx_mcdi_rpc(efx, MC_CMD_WOL_FILTER_RESET, NULL, 0, NULL, 0, NULL); - if (rc) - goto fail; - - return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); return rc; } @@ -1497,13 +1703,6 @@ static int efx_mcdi_nvram_update_start(struct efx_nic *efx, unsigned int type) rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_START, inbuf, sizeof(inbuf), NULL, 0, NULL); - if (rc) - goto fail; - - return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); return rc; } @@ -1523,14 +1722,10 @@ static int efx_mcdi_nvram_read(struct efx_nic *efx, unsigned int type, rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_READ, inbuf, sizeof(inbuf), outbuf, sizeof(outbuf), &outlen); if (rc) - goto fail; + return rc; memcpy(buffer, MCDI_PTR(outbuf, NVRAM_READ_OUT_READ_BUFFER), length); return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); - return rc; } static int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type, @@ -1550,13 +1745,6 @@ static int efx_mcdi_nvram_write(struct efx_nic *efx, unsigned int type, rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_WRITE, inbuf, ALIGN(MC_CMD_NVRAM_WRITE_IN_LEN(length), 4), NULL, 0, NULL); - if (rc) - goto fail; - - return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); return rc; } @@ -1574,13 +1762,6 @@ static int efx_mcdi_nvram_erase(struct efx_nic *efx, unsigned int type, rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_ERASE, inbuf, sizeof(inbuf), NULL, 0, NULL); - if (rc) - goto fail; - - return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); return rc; } @@ -1595,13 +1776,6 @@ static int efx_mcdi_nvram_update_finish(struct efx_nic *efx, unsigned int type) rc = efx_mcdi_rpc(efx, MC_CMD_NVRAM_UPDATE_FINISH, inbuf, sizeof(inbuf), NULL, 0, NULL); - if (rc) - goto fail; - - return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); return rc; } diff --git a/drivers/net/ethernet/sfc/mcdi.h b/drivers/net/ethernet/sfc/mcdi.h index c34d0d4e10e..56465f7465a 100644 --- a/drivers/net/ethernet/sfc/mcdi.h +++ b/drivers/net/ethernet/sfc/mcdi.h @@ -28,9 +28,16 @@ enum efx_mcdi_state { MCDI_STATE_COMPLETED, }; +/** + * enum efx_mcdi_mode - MCDI transaction mode + * @MCDI_MODE_POLL: poll for MCDI completion, until timeout + * @MCDI_MODE_EVENTS: wait for an mcdi_event. On timeout, poll once + * @MCDI_MODE_FAIL: we think MCDI is dead, so fail-fast all calls + */ enum efx_mcdi_mode { MCDI_MODE_POLL, MCDI_MODE_EVENTS, + MCDI_MODE_FAIL, }; /** @@ -75,6 +82,8 @@ struct efx_mcdi_mon { unsigned long last_update; struct device *device; struct efx_mcdi_mon_attribute *attrs; + struct attribute_group group; + const struct attribute_group *groups[2]; unsigned int n_attrs; }; @@ -92,14 +101,22 @@ struct efx_mcdi_mtd_partition { * struct efx_mcdi_data - extra state for NICs that implement MCDI * @iface: Interface/protocol state * @hwmon: Hardware monitor state + * @fn_flags: Flags for this function, as returned by %MC_CMD_DRV_ATTACH. */ struct efx_mcdi_data { struct efx_mcdi_iface iface; #ifdef CONFIG_SFC_MCDI_MON struct efx_mcdi_mon hwmon; #endif + u32 fn_flags; }; +static inline struct efx_mcdi_iface *efx_mcdi(struct efx_nic *efx) +{ + EFX_BUG_ON_PARANOID(!efx->mcdi); + return &efx->mcdi->iface; +} + #ifdef CONFIG_SFC_MCDI_MON static inline struct efx_mcdi_mon *efx_mcdi_mon(struct efx_nic *efx) { @@ -108,38 +125,51 @@ static inline struct efx_mcdi_mon *efx_mcdi_mon(struct efx_nic *efx) } #endif -extern int efx_mcdi_init(struct efx_nic *efx); -extern void efx_mcdi_fini(struct efx_nic *efx); +int efx_mcdi_init(struct efx_nic *efx); +void efx_mcdi_fini(struct efx_nic *efx); + +int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, const efx_dword_t *inbuf, + size_t inlen, efx_dword_t *outbuf, size_t outlen, + size_t *outlen_actual); +int efx_mcdi_rpc_quiet(struct efx_nic *efx, unsigned cmd, + const efx_dword_t *inbuf, size_t inlen, + efx_dword_t *outbuf, size_t outlen, + size_t *outlen_actual); -extern int efx_mcdi_rpc(struct efx_nic *efx, unsigned cmd, - const efx_dword_t *inbuf, size_t inlen, +int efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd, + const efx_dword_t *inbuf, size_t inlen); +int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, efx_dword_t *outbuf, size_t outlen, size_t *outlen_actual); - -extern int efx_mcdi_rpc_start(struct efx_nic *efx, unsigned cmd, - const efx_dword_t *inbuf, size_t inlen); -extern int efx_mcdi_rpc_finish(struct efx_nic *efx, unsigned cmd, size_t inlen, - efx_dword_t *outbuf, size_t outlen, - size_t *outlen_actual); +int efx_mcdi_rpc_finish_quiet(struct efx_nic *efx, unsigned cmd, + size_t inlen, efx_dword_t *outbuf, + size_t outlen, size_t *outlen_actual); typedef void efx_mcdi_async_completer(struct efx_nic *efx, unsigned long cookie, int rc, efx_dword_t *outbuf, size_t outlen_actual); -extern int efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd, - const efx_dword_t *inbuf, size_t inlen, - size_t outlen, - efx_mcdi_async_completer *complete, - unsigned long cookie); +int efx_mcdi_rpc_async(struct efx_nic *efx, unsigned int cmd, + const efx_dword_t *inbuf, size_t inlen, size_t outlen, + efx_mcdi_async_completer *complete, + unsigned long cookie); +int efx_mcdi_rpc_async_quiet(struct efx_nic *efx, unsigned int cmd, + const efx_dword_t *inbuf, size_t inlen, + size_t outlen, + efx_mcdi_async_completer *complete, + unsigned long cookie); + +void efx_mcdi_display_error(struct efx_nic *efx, unsigned cmd, + size_t inlen, efx_dword_t *outbuf, + size_t outlen, int rc); -extern int efx_mcdi_poll_reboot(struct efx_nic *efx); -extern void efx_mcdi_mode_poll(struct efx_nic *efx); -extern void efx_mcdi_mode_event(struct efx_nic *efx); -extern void efx_mcdi_flush_async(struct efx_nic *efx); +int efx_mcdi_poll_reboot(struct efx_nic *efx); +void efx_mcdi_mode_poll(struct efx_nic *efx); +void efx_mcdi_mode_event(struct efx_nic *efx); +void efx_mcdi_flush_async(struct efx_nic *efx); -extern void efx_mcdi_process_event(struct efx_channel *channel, - efx_qword_t *event); -extern void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev); +void efx_mcdi_process_event(struct efx_channel *channel, efx_qword_t *event); +void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev); /* We expect that 16- and 32-bit fields in MCDI requests and responses * are appropriately aligned, but 64-bit fields are only @@ -148,6 +178,8 @@ extern void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev); */ #define MCDI_DECLARE_BUF(_name, _len) \ efx_dword_t _name[DIV_ROUND_UP(_len, 4)] +#define MCDI_DECLARE_BUF_OUT_OR_ERR(_name, _len) \ + MCDI_DECLARE_BUF(_name, max_t(size_t, _len, 8)) #define _MCDI_PTR(_buf, _offset) \ ((u8 *)(_buf) + (_offset)) #define MCDI_PTR(_buf, _field) \ @@ -275,55 +307,55 @@ extern void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev); #define MCDI_EVENT_FIELD(_ev, _field) \ EFX_QWORD_FIELD(_ev, MCDI_EVENT_ ## _field) -extern void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len); -extern int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address, - u16 *fw_subtype_list, u32 *capabilities); -extern int efx_mcdi_log_ctrl(struct efx_nic *efx, bool evq, bool uart, - u32 dest_evq); -extern int efx_mcdi_nvram_types(struct efx_nic *efx, u32 *nvram_types_out); -extern int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type, - size_t *size_out, size_t *erase_size_out, - bool *protected_out); -extern int efx_mcdi_nvram_test_all(struct efx_nic *efx); -extern int efx_mcdi_handle_assertion(struct efx_nic *efx); -extern void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode); -extern int efx_mcdi_wol_filter_set_magic(struct efx_nic *efx, - const u8 *mac, int *id_out); -extern int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out); -extern int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id); -extern int efx_mcdi_wol_filter_reset(struct efx_nic *efx); -extern int efx_mcdi_flush_rxqs(struct efx_nic *efx); -extern int efx_mcdi_port_probe(struct efx_nic *efx); -extern void efx_mcdi_port_remove(struct efx_nic *efx); -extern int efx_mcdi_port_reconfigure(struct efx_nic *efx); -extern int efx_mcdi_port_get_number(struct efx_nic *efx); -extern u32 efx_mcdi_phy_get_caps(struct efx_nic *efx); -extern void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev); -extern int efx_mcdi_set_mac(struct efx_nic *efx); +void efx_mcdi_print_fwver(struct efx_nic *efx, char *buf, size_t len); +int efx_mcdi_get_board_cfg(struct efx_nic *efx, u8 *mac_address, + u16 *fw_subtype_list, u32 *capabilities); +int efx_mcdi_log_ctrl(struct efx_nic *efx, bool evq, bool uart, u32 dest_evq); +int efx_mcdi_nvram_types(struct efx_nic *efx, u32 *nvram_types_out); +int efx_mcdi_nvram_info(struct efx_nic *efx, unsigned int type, + size_t *size_out, size_t *erase_size_out, + bool *protected_out); +int efx_mcdi_nvram_test_all(struct efx_nic *efx); +int efx_mcdi_handle_assertion(struct efx_nic *efx); +void efx_mcdi_set_id_led(struct efx_nic *efx, enum efx_led_mode mode); +int efx_mcdi_wol_filter_set_magic(struct efx_nic *efx, const u8 *mac, + int *id_out); +int efx_mcdi_wol_filter_get_magic(struct efx_nic *efx, int *id_out); +int efx_mcdi_wol_filter_remove(struct efx_nic *efx, int id); +int efx_mcdi_wol_filter_reset(struct efx_nic *efx); +int efx_mcdi_flush_rxqs(struct efx_nic *efx); +int efx_mcdi_port_probe(struct efx_nic *efx); +void efx_mcdi_port_remove(struct efx_nic *efx); +int efx_mcdi_port_reconfigure(struct efx_nic *efx); +int efx_mcdi_port_get_number(struct efx_nic *efx); +u32 efx_mcdi_phy_get_caps(struct efx_nic *efx); +void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev); +int efx_mcdi_set_mac(struct efx_nic *efx); #define EFX_MC_STATS_GENERATION_INVALID ((__force __le64)(-1)) -extern void efx_mcdi_mac_start_stats(struct efx_nic *efx); -extern void efx_mcdi_mac_stop_stats(struct efx_nic *efx); -extern bool efx_mcdi_mac_check_fault(struct efx_nic *efx); -extern enum reset_type efx_mcdi_map_reset_reason(enum reset_type reason); -extern int efx_mcdi_reset(struct efx_nic *efx, enum reset_type method); -extern int efx_mcdi_set_workaround(struct efx_nic *efx, u32 type, bool enabled); +void efx_mcdi_mac_start_stats(struct efx_nic *efx); +void efx_mcdi_mac_stop_stats(struct efx_nic *efx); +void efx_mcdi_mac_pull_stats(struct efx_nic *efx); +bool efx_mcdi_mac_check_fault(struct efx_nic *efx); +enum reset_type efx_mcdi_map_reset_reason(enum reset_type reason); +int efx_mcdi_reset(struct efx_nic *efx, enum reset_type method); +int efx_mcdi_set_workaround(struct efx_nic *efx, u32 type, bool enabled); #ifdef CONFIG_SFC_MCDI_MON -extern int efx_mcdi_mon_probe(struct efx_nic *efx); -extern void efx_mcdi_mon_remove(struct efx_nic *efx); +int efx_mcdi_mon_probe(struct efx_nic *efx); +void efx_mcdi_mon_remove(struct efx_nic *efx); #else static inline int efx_mcdi_mon_probe(struct efx_nic *efx) { return 0; } static inline void efx_mcdi_mon_remove(struct efx_nic *efx) {} #endif #ifdef CONFIG_SFC_MTD -extern int efx_mcdi_mtd_read(struct mtd_info *mtd, loff_t start, - size_t len, size_t *retlen, u8 *buffer); -extern int efx_mcdi_mtd_erase(struct mtd_info *mtd, loff_t start, size_t len); -extern int efx_mcdi_mtd_write(struct mtd_info *mtd, loff_t start, - size_t len, size_t *retlen, const u8 *buffer); -extern int efx_mcdi_mtd_sync(struct mtd_info *mtd); -extern void efx_mcdi_mtd_rename(struct efx_mtd_partition *part); +int efx_mcdi_mtd_read(struct mtd_info *mtd, loff_t start, size_t len, + size_t *retlen, u8 *buffer); +int efx_mcdi_mtd_erase(struct mtd_info *mtd, loff_t start, size_t len); +int efx_mcdi_mtd_write(struct mtd_info *mtd, loff_t start, size_t len, + size_t *retlen, const u8 *buffer); +int efx_mcdi_mtd_sync(struct mtd_info *mtd); +void efx_mcdi_mtd_rename(struct efx_mtd_partition *part); #endif #endif /* EFX_MCDI_H */ diff --git a/drivers/net/ethernet/sfc/mcdi_mon.c b/drivers/net/ethernet/sfc/mcdi_mon.c index 4cc5d95b2a5..bc27d5b580f 100644 --- a/drivers/net/ethernet/sfc/mcdi_mon.c +++ b/drivers/net/ethernet/sfc/mcdi_mon.c @@ -24,6 +24,15 @@ enum efx_hwmon_type { EFX_HWMON_IN, /* voltage */ EFX_HWMON_CURR, /* current */ EFX_HWMON_POWER, /* power */ + EFX_HWMON_TYPES_COUNT +}; + +static const char *const efx_hwmon_unit[EFX_HWMON_TYPES_COUNT] = { + [EFX_HWMON_TEMP] = " degC", + [EFX_HWMON_COOL] = " rpm", /* though nonsense for a heatsink */ + [EFX_HWMON_IN] = " mV", + [EFX_HWMON_CURR] = " mA", + [EFX_HWMON_POWER] = " W", }; static const struct { @@ -33,13 +42,13 @@ static const struct { } efx_mcdi_sensor_type[] = { #define SENSOR(name, label, hwmon_type, port) \ [MC_CMD_SENSOR_##name] = { label, EFX_HWMON_ ## hwmon_type, port } - SENSOR(CONTROLLER_TEMP, "Controller ext. temp.", TEMP, -1), + SENSOR(CONTROLLER_TEMP, "Controller board temp.", TEMP, -1), SENSOR(PHY_COMMON_TEMP, "PHY temp.", TEMP, -1), - SENSOR(CONTROLLER_COOLING, "Controller cooling", COOL, -1), + SENSOR(CONTROLLER_COOLING, "Controller heat sink", COOL, -1), SENSOR(PHY0_TEMP, "PHY temp.", TEMP, 0), - SENSOR(PHY0_COOLING, "PHY cooling", COOL, 0), + SENSOR(PHY0_COOLING, "PHY heat sink", COOL, 0), SENSOR(PHY1_TEMP, "PHY temp.", TEMP, 1), - SENSOR(PHY1_COOLING, "PHY cooling", COOL, 1), + SENSOR(PHY1_COOLING, "PHY heat sink", COOL, 1), SENSOR(IN_1V0, "1.0V supply", IN, -1), SENSOR(IN_1V2, "1.2V supply", IN, -1), SENSOR(IN_1V8, "1.8V supply", IN, -1), @@ -47,36 +56,42 @@ static const struct { SENSOR(IN_3V3, "3.3V supply", IN, -1), SENSOR(IN_12V0, "12.0V supply", IN, -1), SENSOR(IN_1V2A, "1.2V analogue supply", IN, -1), - SENSOR(IN_VREF, "ref. voltage", IN, -1), - SENSOR(OUT_VAOE, "AOE power supply", IN, -1), - SENSOR(AOE_TEMP, "AOE temp.", TEMP, -1), - SENSOR(PSU_AOE_TEMP, "AOE PSU temp.", TEMP, -1), - SENSOR(PSU_TEMP, "Controller PSU temp.", TEMP, -1), - SENSOR(FAN_0, NULL, COOL, -1), - SENSOR(FAN_1, NULL, COOL, -1), - SENSOR(FAN_2, NULL, COOL, -1), - SENSOR(FAN_3, NULL, COOL, -1), - SENSOR(FAN_4, NULL, COOL, -1), + SENSOR(IN_VREF, "Ref. voltage", IN, -1), + SENSOR(OUT_VAOE, "AOE FPGA supply", IN, -1), + SENSOR(AOE_TEMP, "AOE FPGA temp.", TEMP, -1), + SENSOR(PSU_AOE_TEMP, "AOE regulator temp.", TEMP, -1), + SENSOR(PSU_TEMP, "Controller regulator temp.", + TEMP, -1), + SENSOR(FAN_0, "Fan 0", COOL, -1), + SENSOR(FAN_1, "Fan 1", COOL, -1), + SENSOR(FAN_2, "Fan 2", COOL, -1), + SENSOR(FAN_3, "Fan 3", COOL, -1), + SENSOR(FAN_4, "Fan 4", COOL, -1), SENSOR(IN_VAOE, "AOE input supply", IN, -1), SENSOR(OUT_IAOE, "AOE output current", CURR, -1), SENSOR(IN_IAOE, "AOE input current", CURR, -1), SENSOR(NIC_POWER, "Board power use", POWER, -1), SENSOR(IN_0V9, "0.9V supply", IN, -1), - SENSOR(IN_I0V9, "0.9V input current", CURR, -1), - SENSOR(IN_I1V2, "1.2V input current", CURR, -1), - SENSOR(IN_0V9_ADC, "0.9V supply (at ADC)", IN, -1), - SENSOR(CONTROLLER_2_TEMP, "Controller ext. temp. 2", TEMP, -1), - SENSOR(VREG_INTERNAL_TEMP, "Voltage regulator temp.", TEMP, -1), + SENSOR(IN_I0V9, "0.9V supply current", CURR, -1), + SENSOR(IN_I1V2, "1.2V supply current", CURR, -1), + SENSOR(IN_0V9_ADC, "0.9V supply (ext. ADC)", IN, -1), + SENSOR(CONTROLLER_2_TEMP, "Controller board temp. 2", TEMP, -1), + SENSOR(VREG_INTERNAL_TEMP, "Regulator die temp.", TEMP, -1), SENSOR(VREG_0V9_TEMP, "0.9V regulator temp.", TEMP, -1), SENSOR(VREG_1V2_TEMP, "1.2V regulator temp.", TEMP, -1), - SENSOR(CONTROLLER_VPTAT, "Controller int. temp. raw", IN, -1), - SENSOR(CONTROLLER_INTERNAL_TEMP, "Controller int. temp.", TEMP, -1), + SENSOR(CONTROLLER_VPTAT, + "Controller PTAT voltage (int. ADC)", IN, -1), + SENSOR(CONTROLLER_INTERNAL_TEMP, + "Controller die temp. (int. ADC)", TEMP, -1), SENSOR(CONTROLLER_VPTAT_EXTADC, - "Controller int. temp. raw (at ADC)", IN, -1), + "Controller PTAT voltage (ext. ADC)", IN, -1), SENSOR(CONTROLLER_INTERNAL_TEMP_EXTADC, - "Controller int. temp. (via ADC)", TEMP, -1), + "Controller die temp. (ext. ADC)", TEMP, -1), SENSOR(AMBIENT_TEMP, "Ambient temp.", TEMP, -1), SENSOR(AIRFLOW, "Air flow raw", IN, -1), + SENSOR(VDD08D_VSS08D_CSR, "0.9V die (int. ADC)", IN, -1), + SENSOR(VDD08D_VSS08D_CSR_EXTADC, "0.9V die (ext. ADC)", IN, -1), + SENSOR(HOTPOINT_TEMP, "Controller board temp. (hotpoint)", TEMP, -1), #undef SENSOR }; @@ -91,7 +106,8 @@ static const char *const sensor_status_names[] = { void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev) { unsigned int type, state, value; - const char *name = NULL, *state_txt; + enum efx_hwmon_type hwmon_type = EFX_HWMON_UNKNOWN; + const char *name = NULL, *state_txt, *unit; type = EFX_QWORD_FIELD(*ev, MCDI_EVENT_SENSOREVT_MONITOR); state = EFX_QWORD_FIELD(*ev, MCDI_EVENT_SENSOREVT_STATE); @@ -99,16 +115,22 @@ void efx_mcdi_sensor_event(struct efx_nic *efx, efx_qword_t *ev) /* Deal gracefully with the board having more drivers than we * know about, but do not expect new sensor states. */ - if (type < ARRAY_SIZE(efx_mcdi_sensor_type)) + if (type < ARRAY_SIZE(efx_mcdi_sensor_type)) { name = efx_mcdi_sensor_type[type].label; + hwmon_type = efx_mcdi_sensor_type[type].hwmon_type; + } if (!name) name = "No sensor name available"; EFX_BUG_ON_PARANOID(state >= ARRAY_SIZE(sensor_status_names)); state_txt = sensor_status_names[state]; + EFX_BUG_ON_PARANOID(hwmon_type >= EFX_HWMON_TYPES_COUNT); + unit = efx_hwmon_unit[hwmon_type]; + if (!unit) + unit = ""; netif_err(efx, hw, efx->net_dev, - "Sensor %d (%s) reports condition '%s' for raw value %d\n", - type, name, state_txt, value); + "Sensor %d (%s) reports condition '%s' for value %d%s\n", + type, name, state_txt, value, unit); } #ifdef CONFIG_SFC_MCDI_MON @@ -139,17 +161,10 @@ static int efx_mcdi_mon_update(struct efx_nic *efx) return rc; } -static ssize_t efx_mcdi_mon_show_name(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - return sprintf(buf, "%s\n", KBUILD_MODNAME); -} - static int efx_mcdi_mon_get_entry(struct device *dev, unsigned int index, efx_dword_t *entry) { - struct efx_nic *efx = dev_get_drvdata(dev); + struct efx_nic *efx = dev_get_drvdata(dev->parent); struct efx_mcdi_mon *hwmon = efx_mcdi_mon(efx); int rc; @@ -263,7 +278,7 @@ static ssize_t efx_mcdi_mon_show_label(struct device *dev, efx_mcdi_sensor_type[mon_attr->type].label); } -static int +static void efx_mcdi_mon_add_attr(struct efx_nic *efx, const char *name, ssize_t (*reader)(struct device *, struct device_attribute *, char *), @@ -272,7 +287,6 @@ efx_mcdi_mon_add_attr(struct efx_nic *efx, const char *name, { struct efx_mcdi_mon *hwmon = efx_mcdi_mon(efx); struct efx_mcdi_mon_attribute *attr = &hwmon->attrs[hwmon->n_attrs]; - int rc; strlcpy(attr->name, name, sizeof(attr->name)); attr->index = index; @@ -286,10 +300,7 @@ efx_mcdi_mon_add_attr(struct efx_nic *efx, const char *name, attr->dev_attr.attr.name = attr->name; attr->dev_attr.attr.mode = S_IRUGO; attr->dev_attr.show = reader; - rc = device_create_file(&efx->pci_dev->dev, &attr->dev_attr); - if (rc == 0) - ++hwmon->n_attrs; - return rc; + hwmon->group.attrs[hwmon->n_attrs++] = &attr->dev_attr.attr; } int efx_mcdi_mon_probe(struct efx_nic *efx) @@ -338,26 +349,22 @@ int efx_mcdi_mon_probe(struct efx_nic *efx) efx_mcdi_mon_update(efx); /* Allocate space for the maximum possible number of - * attributes for this set of sensors: name of the driver plus + * attributes for this set of sensors: * value, min, max, crit, alarm and label for each sensor. */ - n_attrs = 1 + 6 * n_sensors; + n_attrs = 6 * n_sensors; hwmon->attrs = kcalloc(n_attrs, sizeof(*hwmon->attrs), GFP_KERNEL); if (!hwmon->attrs) { rc = -ENOMEM; goto fail; } - - hwmon->device = hwmon_device_register(&efx->pci_dev->dev); - if (IS_ERR(hwmon->device)) { - rc = PTR_ERR(hwmon->device); + hwmon->group.attrs = kcalloc(n_attrs + 1, sizeof(struct attribute *), + GFP_KERNEL); + if (!hwmon->group.attrs) { + rc = -ENOMEM; goto fail; } - rc = efx_mcdi_mon_add_attr(efx, "name", efx_mcdi_mon_show_name, 0, 0, 0); - if (rc) - goto fail; - for (i = 0, j = -1, type = -1; ; i++) { enum efx_hwmon_type hwmon_type; const char *hwmon_prefix; @@ -372,7 +379,7 @@ int efx_mcdi_mon_probe(struct efx_nic *efx) page = type / 32; j = -1; if (page == n_pages) - return 0; + goto hwmon_register; MCDI_SET_DWORD(inbuf, SENSOR_INFO_EXT_IN_PAGE, page); @@ -453,28 +460,22 @@ int efx_mcdi_mon_probe(struct efx_nic *efx) if (min1 != max1) { snprintf(name, sizeof(name), "%s%u_input", hwmon_prefix, hwmon_index); - rc = efx_mcdi_mon_add_attr( + efx_mcdi_mon_add_attr( efx, name, efx_mcdi_mon_show_value, i, type, 0); - if (rc) - goto fail; if (hwmon_type != EFX_HWMON_POWER) { snprintf(name, sizeof(name), "%s%u_min", hwmon_prefix, hwmon_index); - rc = efx_mcdi_mon_add_attr( + efx_mcdi_mon_add_attr( efx, name, efx_mcdi_mon_show_limit, i, type, min1); - if (rc) - goto fail; } snprintf(name, sizeof(name), "%s%u_max", hwmon_prefix, hwmon_index); - rc = efx_mcdi_mon_add_attr( + efx_mcdi_mon_add_attr( efx, name, efx_mcdi_mon_show_limit, i, type, max1); - if (rc) - goto fail; if (min2 != max2) { /* Assume max2 is critical value. @@ -482,32 +483,38 @@ int efx_mcdi_mon_probe(struct efx_nic *efx) */ snprintf(name, sizeof(name), "%s%u_crit", hwmon_prefix, hwmon_index); - rc = efx_mcdi_mon_add_attr( + efx_mcdi_mon_add_attr( efx, name, efx_mcdi_mon_show_limit, i, type, max2); - if (rc) - goto fail; } } snprintf(name, sizeof(name), "%s%u_alarm", hwmon_prefix, hwmon_index); - rc = efx_mcdi_mon_add_attr( + efx_mcdi_mon_add_attr( efx, name, efx_mcdi_mon_show_alarm, i, type, 0); - if (rc) - goto fail; if (type < ARRAY_SIZE(efx_mcdi_sensor_type) && efx_mcdi_sensor_type[type].label) { snprintf(name, sizeof(name), "%s%u_label", hwmon_prefix, hwmon_index); - rc = efx_mcdi_mon_add_attr( + efx_mcdi_mon_add_attr( efx, name, efx_mcdi_mon_show_label, i, type, 0); - if (rc) - goto fail; } } +hwmon_register: + hwmon->groups[0] = &hwmon->group; + hwmon->device = hwmon_device_register_with_groups(&efx->pci_dev->dev, + KBUILD_MODNAME, NULL, + hwmon->groups); + if (IS_ERR(hwmon->device)) { + rc = PTR_ERR(hwmon->device); + goto fail; + } + + return 0; + fail: efx_mcdi_mon_remove(efx); return rc; @@ -516,14 +523,11 @@ fail: void efx_mcdi_mon_remove(struct efx_nic *efx) { struct efx_mcdi_mon *hwmon = efx_mcdi_mon(efx); - unsigned int i; - for (i = 0; i < hwmon->n_attrs; i++) - device_remove_file(&efx->pci_dev->dev, - &hwmon->attrs[i].dev_attr); - kfree(hwmon->attrs); if (hwmon->device) hwmon_device_unregister(hwmon->device); + kfree(hwmon->attrs); + kfree(hwmon->group.attrs); efx_nic_free_buffer(efx, &hwmon->dma_buf); } diff --git a/drivers/net/ethernet/sfc/mcdi_pcol.h b/drivers/net/ethernet/sfc/mcdi_pcol.h index b5cf62492f8..a707fb5ef14 100644 --- a/drivers/net/ethernet/sfc/mcdi_pcol.h +++ b/drivers/net/ethernet/sfc/mcdi_pcol.h @@ -224,6 +224,8 @@ #define MC_CMD_ERR_MAC_EXIST 0x1009 /* Slave core not present */ #define MC_CMD_ERR_SLAVE_NOT_PRESENT 0x100a +/* The datapath is disabled. */ +#define MC_CMD_ERR_DATAPATH_DISABLED 0x100b #define MC_CMD_ERR_CODE_OFST 0 @@ -390,6 +392,8 @@ * AOE_ERR_DATA) */ #define MCDI_EVENT_AOE_BYTEBLASTER 0x9 +/* enum: DDR ECC status update */ +#define MCDI_EVENT_AOE_DDR_ECC_STATUS 0xa #define MCDI_EVENT_AOE_ERR_DATA_LBN 8 #define MCDI_EVENT_AOE_ERR_DATA_WIDTH 8 #define MCDI_EVENT_RX_ERR_RXQ_LBN 0 @@ -462,6 +466,10 @@ #define MCDI_EVENT_CODE_ECC_CORR_ERR 0x17 /* enum: the MC has detected an uncorrectable error */ #define MCDI_EVENT_CODE_ECC_FATAL_ERR 0x18 +/* enum: The MC has entered offline BIST mode */ +#define MCDI_EVENT_CODE_MC_BIST 0x19 +/* enum: PTP tick event providing current NIC time */ +#define MCDI_EVENT_CODE_PTP_TIME 0x1a /* enum: Artificial event generated by host and posted via MC for test * purposes. */ @@ -481,15 +489,32 @@ #define MCDI_EVENT_TX_ERR_DATA_OFST 0 #define MCDI_EVENT_TX_ERR_DATA_LBN 0 #define MCDI_EVENT_TX_ERR_DATA_WIDTH 32 -/* Seconds field of timestamp */ +/* For CODE_PTP_RX, CODE_PTP_PPS and CODE_HW_PPS events the seconds field of + * timestamp + */ #define MCDI_EVENT_PTP_SECONDS_OFST 0 #define MCDI_EVENT_PTP_SECONDS_LBN 0 #define MCDI_EVENT_PTP_SECONDS_WIDTH 32 -/* Nanoseconds field of timestamp */ +/* For CODE_PTP_RX, CODE_PTP_PPS and CODE_HW_PPS events the major field of + * timestamp + */ +#define MCDI_EVENT_PTP_MAJOR_OFST 0 +#define MCDI_EVENT_PTP_MAJOR_LBN 0 +#define MCDI_EVENT_PTP_MAJOR_WIDTH 32 +/* For CODE_PTP_RX, CODE_PTP_PPS and CODE_HW_PPS events the nanoseconds field + * of timestamp + */ #define MCDI_EVENT_PTP_NANOSECONDS_OFST 0 #define MCDI_EVENT_PTP_NANOSECONDS_LBN 0 #define MCDI_EVENT_PTP_NANOSECONDS_WIDTH 32 -/* Lowest four bytes of sourceUUID from PTP packet */ +/* For CODE_PTP_RX, CODE_PTP_PPS and CODE_HW_PPS events the minor field of + * timestamp + */ +#define MCDI_EVENT_PTP_MINOR_OFST 0 +#define MCDI_EVENT_PTP_MINOR_LBN 0 +#define MCDI_EVENT_PTP_MINOR_WIDTH 32 +/* For CODE_PTP_RX events, the lowest four bytes of sourceUUID from PTP packet + */ #define MCDI_EVENT_PTP_UUID_OFST 0 #define MCDI_EVENT_PTP_UUID_LBN 0 #define MCDI_EVENT_PTP_UUID_WIDTH 32 @@ -505,6 +530,13 @@ #define MCDI_EVENT_ECC_FATAL_ERR_DATA_OFST 0 #define MCDI_EVENT_ECC_FATAL_ERR_DATA_LBN 0 #define MCDI_EVENT_ECC_FATAL_ERR_DATA_WIDTH 32 +/* For CODE_PTP_TIME events, the major value of the PTP clock */ +#define MCDI_EVENT_PTP_TIME_MAJOR_OFST 0 +#define MCDI_EVENT_PTP_TIME_MAJOR_LBN 0 +#define MCDI_EVENT_PTP_TIME_MAJOR_WIDTH 32 +/* For CODE_PTP_TIME events, bits 19-26 of the minor value of the PTP clock */ +#define MCDI_EVENT_PTP_TIME_MINOR_26_19_LBN 36 +#define MCDI_EVENT_PTP_TIME_MINOR_26_19_WIDTH 8 /* FCDI_EVENT structuredef */ #define FCDI_EVENT_LEN 8 @@ -545,8 +577,10 @@ #define FCDI_EVENT_CODE_TIMED_READ 0x5 /* enum: One or more PPS IN events */ #define FCDI_EVENT_CODE_PPS_IN 0x6 -/* enum: One or more PPS OUT events */ -#define FCDI_EVENT_CODE_PPS_OUT 0x7 +/* enum: Tick event from PTP clock */ +#define FCDI_EVENT_CODE_PTP_TICK 0x7 +/* enum: ECC error counters */ +#define FCDI_EVENT_CODE_DDR_ECC_STATUS 0x8 #define FCDI_EVENT_ASSERT_INSTR_ADDRESS_OFST 0 #define FCDI_EVENT_ASSERT_INSTR_ADDRESS_LBN 0 #define FCDI_EVENT_ASSERT_INSTR_ADDRESS_WIDTH 32 @@ -560,14 +594,21 @@ #define FCDI_EVENT_LINK_STATE_DATA_OFST 0 #define FCDI_EVENT_LINK_STATE_DATA_LBN 0 #define FCDI_EVENT_LINK_STATE_DATA_WIDTH 32 -#define FCDI_EVENT_PPS_COUNT_OFST 0 -#define FCDI_EVENT_PPS_COUNT_LBN 0 -#define FCDI_EVENT_PPS_COUNT_WIDTH 32 - -/* FCDI_EXTENDED_EVENT structuredef */ -#define FCDI_EXTENDED_EVENT_LENMIN 16 -#define FCDI_EXTENDED_EVENT_LENMAX 248 -#define FCDI_EXTENDED_EVENT_LEN(num) (8+8*(num)) +#define FCDI_EVENT_DDR_ECC_STATUS_BANK_ID_LBN 36 +#define FCDI_EVENT_DDR_ECC_STATUS_BANK_ID_WIDTH 8 +#define FCDI_EVENT_DDR_ECC_STATUS_STATUS_OFST 0 +#define FCDI_EVENT_DDR_ECC_STATUS_STATUS_LBN 0 +#define FCDI_EVENT_DDR_ECC_STATUS_STATUS_WIDTH 32 + +/* FCDI_EXTENDED_EVENT_PPS structuredef: Extended FCDI event to send PPS events + * to the MC. Note that this structure | is overlayed over a normal FCDI event + * such that bits 32-63 containing | event code, level, source etc remain the + * same. In this case the data | field of the header is defined to be the + * number of timestamps + */ +#define FCDI_EXTENDED_EVENT_PPS_LENMIN 16 +#define FCDI_EXTENDED_EVENT_PPS_LENMAX 248 +#define FCDI_EXTENDED_EVENT_PPS_LEN(num) (8+8*(num)) /* Number of timestamps following */ #define FCDI_EXTENDED_EVENT_PPS_COUNT_OFST 0 #define FCDI_EXTENDED_EVENT_PPS_COUNT_LBN 0 @@ -581,14 +622,14 @@ #define FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_LBN 96 #define FCDI_EXTENDED_EVENT_PPS_NANOSECONDS_WIDTH 32 /* Timestamp records comprising the event */ -#define FCDI_EXTENDED_EVENT_PPS_TIME_OFST 8 -#define FCDI_EXTENDED_EVENT_PPS_TIME_LEN 8 -#define FCDI_EXTENDED_EVENT_PPS_TIME_LO_OFST 8 -#define FCDI_EXTENDED_EVENT_PPS_TIME_HI_OFST 12 -#define FCDI_EXTENDED_EVENT_PPS_TIME_MINNUM 1 -#define FCDI_EXTENDED_EVENT_PPS_TIME_MAXNUM 30 -#define FCDI_EXTENDED_EVENT_PPS_TIME_LBN 64 -#define FCDI_EXTENDED_EVENT_PPS_TIME_WIDTH 64 +#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_OFST 8 +#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LEN 8 +#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LO_OFST 8 +#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_HI_OFST 12 +#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_MINNUM 1 +#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_MAXNUM 30 +#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_LBN 64 +#define FCDI_EXTENDED_EVENT_PPS_TIMESTAMPS_WIDTH 64 /***********************************/ @@ -642,6 +683,10 @@ #define MC_CMD_COPYCODE_IN_LEN 16 /* Source address */ #define MC_CMD_COPYCODE_IN_SRC_ADDR_OFST 0 +/* enum: The main image should be entered via a copy of a single word from and + * to this address when none of the other magic behaviours are required. + */ +#define MC_CMD_COPYCODE_HUNT_NO_MAGIC_ADDR 0x10000 /* enum: Entering the main image via a copy of a single word from and to this * address indicates that it should not attempt to start the datapath CPUs. * This is useful for certain soft rebooting scenarios. (Huntington only) @@ -872,8 +917,28 @@ #define MC_CMD_PTP_OP_RST_CLK 0x14 /* enum: Enable the forwarding of PPS events to the host */ #define MC_CMD_PTP_OP_PPS_ENABLE 0x15 +/* enum: Get the time format used by this NIC for PTP operations */ +#define MC_CMD_PTP_OP_GET_TIME_FORMAT 0x16 +/* enum: Get the clock attributes. NOTE- extended version of + * MC_CMD_PTP_OP_GET_TIME_FORMAT + */ +#define MC_CMD_PTP_OP_GET_ATTRIBUTES 0x16 +/* enum: Get corrections that should be applied to the various different + * timestamps + */ +#define MC_CMD_PTP_OP_GET_TIMESTAMP_CORRECTIONS 0x17 +/* enum: Subscribe to receive periodic time events indicating the current NIC + * time + */ +#define MC_CMD_PTP_OP_TIME_EVENT_SUBSCRIBE 0x18 +/* enum: Unsubscribe to stop receiving time events */ +#define MC_CMD_PTP_OP_TIME_EVENT_UNSUBSCRIBE 0x19 +/* enum: PPS based manfacturing tests. Requires PPS output to be looped to PPS + * input on the same NIC. + */ +#define MC_CMD_PTP_OP_MANFTEST_PPS 0x1a /* enum: Above this for future use. */ -#define MC_CMD_PTP_OP_MAX 0x16 +#define MC_CMD_PTP_OP_MAX 0x1b /* MC_CMD_PTP_IN_ENABLE msgrequest */ #define MC_CMD_PTP_IN_ENABLE_LEN 16 @@ -938,8 +1003,12 @@ #define MC_CMD_PTP_IN_ADJUST_BITS 0x28 /* Time adjustment in seconds */ #define MC_CMD_PTP_IN_ADJUST_SECONDS_OFST 16 +/* Time adjustment major value */ +#define MC_CMD_PTP_IN_ADJUST_MAJOR_OFST 16 /* Time adjustment in nanoseconds */ #define MC_CMD_PTP_IN_ADJUST_NANOSECONDS_OFST 20 +/* Time adjustment minor value */ +#define MC_CMD_PTP_IN_ADJUST_MINOR_OFST 20 /* MC_CMD_PTP_IN_SYNCHRONIZE msgrequest */ #define MC_CMD_PTP_IN_SYNCHRONIZE_LEN 20 @@ -1005,8 +1074,12 @@ /* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */ /* Time adjustment in seconds */ #define MC_CMD_PTP_IN_CLOCK_OFFSET_ADJUST_SECONDS_OFST 8 +/* Time adjustment major value */ +#define MC_CMD_PTP_IN_CLOCK_OFFSET_ADJUST_MAJOR_OFST 8 /* Time adjustment in nanoseconds */ #define MC_CMD_PTP_IN_CLOCK_OFFSET_ADJUST_NANOSECONDS_OFST 12 +/* Time adjustment minor value */ +#define MC_CMD_PTP_IN_CLOCK_OFFSET_ADJUST_MINOR_OFST 12 /* MC_CMD_PTP_IN_CLOCK_FREQ_ADJUST msgrequest */ #define MC_CMD_PTP_IN_CLOCK_FREQ_ADJUST_LEN 16 @@ -1078,9 +1151,51 @@ #define MC_CMD_PTP_ENABLE_PPS 0x0 /* enum: Disable */ #define MC_CMD_PTP_DISABLE_PPS 0x1 -/* Queueid to send events back */ +/* Queue id to send events back */ #define MC_CMD_PTP_IN_PPS_ENABLE_QUEUE_ID_OFST 8 +/* MC_CMD_PTP_IN_GET_TIME_FORMAT msgrequest */ +#define MC_CMD_PTP_IN_GET_TIME_FORMAT_LEN 8 +/* MC_CMD_PTP_IN_CMD_OFST 0 */ +/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */ + +/* MC_CMD_PTP_IN_GET_ATTRIBUTES msgrequest */ +#define MC_CMD_PTP_IN_GET_ATTRIBUTES_LEN 8 +/* MC_CMD_PTP_IN_CMD_OFST 0 */ +/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */ + +/* MC_CMD_PTP_IN_GET_TIMESTAMP_CORRECTIONS msgrequest */ +#define MC_CMD_PTP_IN_GET_TIMESTAMP_CORRECTIONS_LEN 8 +/* MC_CMD_PTP_IN_CMD_OFST 0 */ +/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */ + +/* MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE msgrequest */ +#define MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_LEN 12 +/* MC_CMD_PTP_IN_CMD_OFST 0 */ +/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */ +/* Event queue to send PTP time events to */ +#define MC_CMD_PTP_IN_TIME_EVENT_SUBSCRIBE_QUEUE_OFST 8 + +/* MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE msgrequest */ +#define MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_LEN 16 +/* MC_CMD_PTP_IN_CMD_OFST 0 */ +/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */ +/* Unsubscribe options */ +#define MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_CONTROL_OFST 8 +/* enum: Unsubscribe a single queue */ +#define MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_SINGLE 0x0 +/* enum: Unsubscribe all queues */ +#define MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_ALL 0x1 +/* Event queue ID */ +#define MC_CMD_PTP_IN_TIME_EVENT_UNSUBSCRIBE_QUEUE_OFST 12 + +/* MC_CMD_PTP_IN_MANFTEST_PPS msgrequest */ +#define MC_CMD_PTP_IN_MANFTEST_PPS_LEN 12 +/* MC_CMD_PTP_IN_CMD_OFST 0 */ +/* MC_CMD_PTP_IN_PERIPH_ID_OFST 4 */ +/* 1 to enable PPS test mode, 0 to disable and return result. */ +#define MC_CMD_PTP_IN_MANFTEST_PPS_TEST_ENABLE_OFST 8 + /* MC_CMD_PTP_OUT msgresponse */ #define MC_CMD_PTP_OUT_LEN 0 @@ -1088,15 +1203,29 @@ #define MC_CMD_PTP_OUT_TRANSMIT_LEN 8 /* Value of seconds timestamp */ #define MC_CMD_PTP_OUT_TRANSMIT_SECONDS_OFST 0 +/* Timestamp major value */ +#define MC_CMD_PTP_OUT_TRANSMIT_MAJOR_OFST 0 /* Value of nanoseconds timestamp */ #define MC_CMD_PTP_OUT_TRANSMIT_NANOSECONDS_OFST 4 +/* Timestamp minor value */ +#define MC_CMD_PTP_OUT_TRANSMIT_MINOR_OFST 4 + +/* MC_CMD_PTP_OUT_TIME_EVENT_SUBSCRIBE msgresponse */ +#define MC_CMD_PTP_OUT_TIME_EVENT_SUBSCRIBE_LEN 0 + +/* MC_CMD_PTP_OUT_TIME_EVENT_UNSUBSCRIBE msgresponse */ +#define MC_CMD_PTP_OUT_TIME_EVENT_UNSUBSCRIBE_LEN 0 /* MC_CMD_PTP_OUT_READ_NIC_TIME msgresponse */ #define MC_CMD_PTP_OUT_READ_NIC_TIME_LEN 8 /* Value of seconds timestamp */ #define MC_CMD_PTP_OUT_READ_NIC_TIME_SECONDS_OFST 0 +/* Timestamp major value */ +#define MC_CMD_PTP_OUT_READ_NIC_TIME_MAJOR_OFST 0 /* Value of nanoseconds timestamp */ #define MC_CMD_PTP_OUT_READ_NIC_TIME_NANOSECONDS_OFST 4 +/* Timestamp minor value */ +#define MC_CMD_PTP_OUT_READ_NIC_TIME_MINOR_OFST 4 /* MC_CMD_PTP_OUT_STATUS msgresponse */ #define MC_CMD_PTP_OUT_STATUS_LEN 64 @@ -1116,21 +1245,21 @@ #define MC_CMD_PTP_OUT_STATUS_STATS_PPS_OFLOW_OFST 24 /* Number of PPS bad periods */ #define MC_CMD_PTP_OUT_STATUS_STATS_PPS_BAD_OFST 28 -/* Minimum period of PPS pulse */ +/* Minimum period of PPS pulse in nanoseconds */ #define MC_CMD_PTP_OUT_STATUS_STATS_PPS_PER_MIN_OFST 32 -/* Maximum period of PPS pulse */ +/* Maximum period of PPS pulse in nanoseconds */ #define MC_CMD_PTP_OUT_STATUS_STATS_PPS_PER_MAX_OFST 36 -/* Last period of PPS pulse */ +/* Last period of PPS pulse in nanoseconds */ #define MC_CMD_PTP_OUT_STATUS_STATS_PPS_PER_LAST_OFST 40 -/* Mean period of PPS pulse */ +/* Mean period of PPS pulse in nanoseconds */ #define MC_CMD_PTP_OUT_STATUS_STATS_PPS_PER_MEAN_OFST 44 -/* Minimum offset of PPS pulse (signed) */ +/* Minimum offset of PPS pulse in nanoseconds (signed) */ #define MC_CMD_PTP_OUT_STATUS_STATS_PPS_OFF_MIN_OFST 48 -/* Maximum offset of PPS pulse (signed) */ +/* Maximum offset of PPS pulse in nanoseconds (signed) */ #define MC_CMD_PTP_OUT_STATUS_STATS_PPS_OFF_MAX_OFST 52 -/* Last offset of PPS pulse (signed) */ +/* Last offset of PPS pulse in nanoseconds (signed) */ #define MC_CMD_PTP_OUT_STATUS_STATS_PPS_OFF_LAST_OFST 56 -/* Mean offset of PPS pulse (signed) */ +/* Mean offset of PPS pulse in nanoseconds (signed) */ #define MC_CMD_PTP_OUT_STATUS_STATS_PPS_OFF_MEAN_OFST 60 /* MC_CMD_PTP_OUT_SYNCHRONIZE msgresponse */ @@ -1146,8 +1275,12 @@ #define MC_CMD_PTP_OUT_SYNCHRONIZE_HOSTSTART_OFST 0 /* Value of seconds timestamp */ #define MC_CMD_PTP_OUT_SYNCHRONIZE_SECONDS_OFST 4 +/* Timestamp major value */ +#define MC_CMD_PTP_OUT_SYNCHRONIZE_MAJOR_OFST 4 /* Value of nanoseconds timestamp */ #define MC_CMD_PTP_OUT_SYNCHRONIZE_NANOSECONDS_OFST 8 +/* Timestamp minor value */ +#define MC_CMD_PTP_OUT_SYNCHRONIZE_MINOR_OFST 8 /* Host time immediately after NIC's hardware clock read */ #define MC_CMD_PTP_OUT_SYNCHRONIZE_HOSTEND_OFST 12 /* Number of nanoseconds waited after reading NIC's hardware clock */ @@ -1177,6 +1310,16 @@ #define MC_CMD_PTP_MANF_PACKET_ENOUGH 0x8 /* enum: Timestamp trigger GPIO not working */ #define MC_CMD_PTP_MANF_GPIO_TRIGGER 0x9 +/* enum: Insufficient PPS events to perform checks */ +#define MC_CMD_PTP_MANF_PPS_ENOUGH 0xa +/* enum: PPS time event period not sufficiently close to 1s. */ +#define MC_CMD_PTP_MANF_PPS_PERIOD 0xb +/* enum: PPS time event nS reading not sufficiently close to zero. */ +#define MC_CMD_PTP_MANF_PPS_NS 0xc +/* enum: PTP peripheral registers incorrect */ +#define MC_CMD_PTP_MANF_REGISTERS 0xd +/* enum: Failed to read time from PTP peripheral */ +#define MC_CMD_PTP_MANF_CLOCK_READ 0xe /* Presence of external oscillator */ #define MC_CMD_PTP_OUT_MANFTEST_BASIC_TEST_EXTOSC_OFST 4 @@ -1198,6 +1341,62 @@ #define MC_CMD_PTP_OUT_FPGAREAD_BUFFER_MINNUM 1 #define MC_CMD_PTP_OUT_FPGAREAD_BUFFER_MAXNUM 252 +/* MC_CMD_PTP_OUT_GET_TIME_FORMAT msgresponse */ +#define MC_CMD_PTP_OUT_GET_TIME_FORMAT_LEN 4 +/* Time format required/used by for this NIC. Applies to all PTP MCDI + * operations that pass times between the host and firmware. If this operation + * is not supported (older firmware) a format of seconds and nanoseconds should + * be assumed. + */ +#define MC_CMD_PTP_OUT_GET_TIME_FORMAT_FORMAT_OFST 0 +/* enum: Times are in seconds and nanoseconds */ +#define MC_CMD_PTP_OUT_GET_TIME_FORMAT_SECONDS_NANOSECONDS 0x0 +/* enum: Major register has units of 16 second per tick, minor 8 ns per tick */ +#define MC_CMD_PTP_OUT_GET_TIME_FORMAT_16SECONDS_8NANOSECONDS 0x1 +/* enum: Major register has units of seconds, minor 2^-27s per tick */ +#define MC_CMD_PTP_OUT_GET_TIME_FORMAT_SECONDS_27FRACTION 0x2 + +/* MC_CMD_PTP_OUT_GET_ATTRIBUTES msgresponse */ +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_LEN 8 +/* Time format required/used by for this NIC. Applies to all PTP MCDI + * operations that pass times between the host and firmware. If this operation + * is not supported (older firmware) a format of seconds and nanoseconds should + * be assumed. + */ +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_TIME_FORMAT_OFST 0 +/* enum: Times are in seconds and nanoseconds */ +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS 0x0 +/* enum: Major register has units of 16 second per tick, minor 8 ns per tick */ +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_16SECONDS_8NANOSECONDS 0x1 +/* enum: Major register has units of seconds, minor 2^-27s per tick */ +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_27FRACTION 0x2 +/* Minimum acceptable value for a corrected synchronization timeset. When + * comparing host and NIC clock times, the MC returns a set of samples that + * contain the host start and end time, the MC time when the host start was + * detected and the time the MC waited between reading the time and detecting + * the host end. The corrected sync window is the difference between the host + * end and start times minus the time that the MC waited for host end. + */ +#define MC_CMD_PTP_OUT_GET_ATTRIBUTES_SYNC_WINDOW_MIN_OFST 4 + +/* MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS msgresponse */ +#define MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_LEN 16 +/* Uncorrected error on transmit timestamps in NIC clock format */ +#define MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_TRANSMIT_OFST 0 +/* Uncorrected error on receive timestamps in NIC clock format */ +#define MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_RECEIVE_OFST 4 +/* Uncorrected error on PPS output in NIC clock format */ +#define MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_OUT_OFST 8 +/* Uncorrected error on PPS input in NIC clock format */ +#define MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_IN_OFST 12 + +/* MC_CMD_PTP_OUT_MANFTEST_PPS msgresponse */ +#define MC_CMD_PTP_OUT_MANFTEST_PPS_LEN 4 +/* Results of testing */ +#define MC_CMD_PTP_OUT_MANFTEST_PPS_TEST_RESULT_OFST 0 +/* Enum values, see field(s): */ +/* MC_CMD_PTP_OUT_MANFTEST_BASIC/TEST_RESULT */ + /***********************************/ /* MC_CMD_CSR_READ32 @@ -1923,6 +2122,8 @@ #define MC_CMD_MEDIA_SFP_PLUS 0x5 /* enum: 10GBaseT. */ #define MC_CMD_MEDIA_BASE_T 0x6 +/* enum: QSFP+. */ +#define MC_CMD_MEDIA_QSFP_PLUS 0x7 #define MC_CMD_GET_PHY_CFG_OUT_MMD_MASK_OFST 48 /* enum: Native clause 22 */ #define MC_CMD_MMD_CLAUSE22 0x0 @@ -2223,6 +2424,8 @@ #define MC_CMD_LOOPBACK_SD_FEP_WS 0x21 /* enum: KR Serdes Serial Wireside. */ #define MC_CMD_LOOPBACK_SD_FES_WS 0x22 +/* enum: Near side of AOE Siena side port */ +#define MC_CMD_LOOPBACK_AOE_INT_NEAR 0x23 /* Supported loopbacks. */ #define MC_CMD_GET_LOOPBACK_MODES_OUT_1G_OFST 8 #define MC_CMD_GET_LOOPBACK_MODES_OUT_1G_LEN 8 @@ -2286,6 +2489,10 @@ #define MC_CMD_GET_LINK_OUT_BPX_LINK_WIDTH 1 #define MC_CMD_GET_LINK_OUT_PHY_LINK_LBN 3 #define MC_CMD_GET_LINK_OUT_PHY_LINK_WIDTH 1 +#define MC_CMD_GET_LINK_OUT_LINK_FAULT_RX_LBN 6 +#define MC_CMD_GET_LINK_OUT_LINK_FAULT_RX_WIDTH 1 +#define MC_CMD_GET_LINK_OUT_LINK_FAULT_TX_LBN 7 +#define MC_CMD_GET_LINK_OUT_LINK_FAULT_TX_WIDTH 1 /* This returns the negotiated flow control value. */ #define MC_CMD_GET_LINK_OUT_FCNTL_OFST 20 /* enum: Flow control is off. */ @@ -2574,8 +2781,58 @@ #define MC_CMD_MAC_RX_LANES01_DISP_ERR 0x39 /* enum */ #define MC_CMD_MAC_RX_LANES23_DISP_ERR 0x3a /* enum */ #define MC_CMD_MAC_RX_MATCH_FAULT 0x3b /* enum */ -#define MC_CMD_GMAC_DMABUF_START 0x40 /* enum */ -#define MC_CMD_GMAC_DMABUF_END 0x5f /* enum */ +/* enum: PM trunc_bb_overflow counter. Valid for EF10 with PM_AND_RXDP_COUNTERS + * capability only. + */ +#define MC_CMD_MAC_PM_TRUNC_BB_OVERFLOW 0x3c +/* enum: PM discard_bb_overflow counter. Valid for EF10 with + * PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_PM_DISCARD_BB_OVERFLOW 0x3d +/* enum: PM trunc_vfifo_full counter. Valid for EF10 with PM_AND_RXDP_COUNTERS + * capability only. + */ +#define MC_CMD_MAC_PM_TRUNC_VFIFO_FULL 0x3e +/* enum: PM discard_vfifo_full counter. Valid for EF10 with + * PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_PM_DISCARD_VFIFO_FULL 0x3f +/* enum: PM trunc_qbb counter. Valid for EF10 with PM_AND_RXDP_COUNTERS + * capability only. + */ +#define MC_CMD_MAC_PM_TRUNC_QBB 0x40 +/* enum: PM discard_qbb counter. Valid for EF10 with PM_AND_RXDP_COUNTERS + * capability only. + */ +#define MC_CMD_MAC_PM_DISCARD_QBB 0x41 +/* enum: PM discard_mapping counter. Valid for EF10 with PM_AND_RXDP_COUNTERS + * capability only. + */ +#define MC_CMD_MAC_PM_DISCARD_MAPPING 0x42 +/* enum: RXDP counter: Number of packets dropped due to the queue being + * disabled. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_RXDP_Q_DISABLED_PKTS 0x43 +/* enum: RXDP counter: Number of packets dropped by the DICPU. Valid for EF10 + * with PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_RXDP_DI_DROPPED_PKTS 0x45 +/* enum: RXDP counter: Number of non-host packets. Valid for EF10 with + * PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_RXDP_STREAMING_PKTS 0x46 +/* enum: RXDP counter: Number of times an emergency descriptor fetch was + * performed. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_RXDP_EMERGENCY_FETCH_CONDITIONS 0x47 +/* enum: RXDP counter: Number of times the DPCPU waited for an existing + * descriptor fetch. Valid for EF10 with PM_AND_RXDP_COUNTERS capability only. + */ +#define MC_CMD_MAC_RXDP_EMERGENCY_WAIT_CONDITIONS 0x48 +/* enum: Start of GMAC stats buffer space, for Siena only. */ +#define MC_CMD_GMAC_DMABUF_START 0x40 +/* enum: End of GMAC stats buffer space, for Siena only. */ +#define MC_CMD_GMAC_DMABUF_END 0x5f #define MC_CMD_MAC_GENERATION_END 0x60 /* enum */ #define MC_CMD_MAC_NSTATS 0x61 /* enum */ @@ -3125,7 +3382,7 @@ #define MC_CMD_SENSOR_INFO_EXT_IN_PAGE_OFST 0 /* MC_CMD_SENSOR_INFO_OUT msgresponse */ -#define MC_CMD_SENSOR_INFO_OUT_LENMIN 12 +#define MC_CMD_SENSOR_INFO_OUT_LENMIN 4 #define MC_CMD_SENSOR_INFO_OUT_LENMAX 252 #define MC_CMD_SENSOR_INFO_OUT_LEN(num) (4+8*(num)) #define MC_CMD_SENSOR_INFO_OUT_MASK_OFST 0 @@ -3219,16 +3476,18 @@ #define MC_CMD_SENSOR_VDD08D_VSS08D_CSR 0x2b /* enum: voltage between VSS08D and VSS08D at CSR (external ADC): mV */ #define MC_CMD_SENSOR_VDD08D_VSS08D_CSR_EXTADC 0x2c +/* enum: Hotpoint temperature: degC */ +#define MC_CMD_SENSOR_HOTPOINT_TEMP 0x2d /* MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF */ #define MC_CMD_SENSOR_ENTRY_OFST 4 #define MC_CMD_SENSOR_ENTRY_LEN 8 #define MC_CMD_SENSOR_ENTRY_LO_OFST 4 #define MC_CMD_SENSOR_ENTRY_HI_OFST 8 -#define MC_CMD_SENSOR_ENTRY_MINNUM 1 +#define MC_CMD_SENSOR_ENTRY_MINNUM 0 #define MC_CMD_SENSOR_ENTRY_MAXNUM 31 /* MC_CMD_SENSOR_INFO_EXT_OUT msgresponse */ -#define MC_CMD_SENSOR_INFO_EXT_OUT_LENMIN 12 +#define MC_CMD_SENSOR_INFO_EXT_OUT_LENMIN 4 #define MC_CMD_SENSOR_INFO_EXT_OUT_LENMAX 252 #define MC_CMD_SENSOR_INFO_EXT_OUT_LEN(num) (4+8*(num)) #define MC_CMD_SENSOR_INFO_EXT_OUT_MASK_OFST 0 @@ -3241,7 +3500,7 @@ /* MC_CMD_SENSOR_ENTRY_LEN 8 */ /* MC_CMD_SENSOR_ENTRY_LO_OFST 4 */ /* MC_CMD_SENSOR_ENTRY_HI_OFST 8 */ -/* MC_CMD_SENSOR_ENTRY_MINNUM 1 */ +/* MC_CMD_SENSOR_ENTRY_MINNUM 0 */ /* MC_CMD_SENSOR_ENTRY_MAXNUM 31 */ /* MC_CMD_SENSOR_INFO_ENTRY_TYPEDEF structuredef */ @@ -3814,6 +4073,18 @@ #define NVRAM_PARTITION_TYPE_ID_LBN 0 #define NVRAM_PARTITION_TYPE_ID_WIDTH 16 +/* LICENSED_APP_ID structuredef */ +#define LICENSED_APP_ID_LEN 4 +#define LICENSED_APP_ID_ID_OFST 0 +/* enum: OpenOnload */ +#define LICENSED_APP_ID_ONLOAD 0x1 +/* enum: PTP timestamping */ +#define LICENSED_APP_ID_PTP 0x2 +/* enum: SolarCapture Pro */ +#define LICENSED_APP_ID_SOLARCAPTURE_PRO 0x4 +#define LICENSED_APP_ID_ID_LBN 0 +#define LICENSED_APP_ID_ID_WIDTH 32 + /***********************************/ /* MC_CMD_READ_REGS @@ -3971,6 +4242,8 @@ #define MC_CMD_INIT_RXQ_IN_FLAG_CHAIN_WIDTH 1 #define MC_CMD_INIT_RXQ_IN_FLAG_PREFIX_LBN 8 #define MC_CMD_INIT_RXQ_IN_FLAG_PREFIX_WIDTH 1 +#define MC_CMD_INIT_RXQ_IN_FLAG_DISABLE_SCATTER_LBN 9 +#define MC_CMD_INIT_RXQ_IN_FLAG_DISABLE_SCATTER_WIDTH 1 /* Owner ID to use if in buffer mode (zero if physical) */ #define MC_CMD_INIT_RXQ_IN_OWNER_ID_OFST 20 /* The port ID associated with the v-adaptor which should contain this DMAQ. */ @@ -4129,6 +4402,9 @@ #define MC_CMD_PROXY_CMD_IN_TARGET_VF_WIDTH 16 #define MC_CMD_PROXY_CMD_IN_VF_NULL 0xffff /* enum */ +/* MC_CMD_PROXY_CMD_OUT msgresponse */ +#define MC_CMD_PROXY_CMD_OUT_LEN 0 + /***********************************/ /* MC_CMD_ALLOC_BUFTBL_CHUNK @@ -4163,7 +4439,7 @@ /* MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN msgrequest */ #define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMIN 20 -#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMAX 252 +#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LENMAX 268 #define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_LEN(num) (12+8*(num)) #define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_HANDLE_OFST 0 /* ID */ @@ -4176,7 +4452,7 @@ #define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_LO_OFST 12 #define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_HI_OFST 16 #define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_MINNUM 1 -#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_MAXNUM 30 +#define MC_CMD_PROGRAM_BUFTBL_ENTRIES_IN_ENTRY_MAXNUM 32 /* MC_CMD_PROGRAM_BUFTBL_ENTRIES_OUT msgresponse */ #define MC_CMD_PROGRAM_BUFTBL_ENTRIES_OUT_LEN 0 @@ -5065,6 +5341,8 @@ #define MC_CMD_GET_CAPABILITIES_OUT_RX_BATCHING_WIDTH 1 #define MC_CMD_GET_CAPABILITIES_OUT_MCAST_FILTER_CHAINING_LBN 26 #define MC_CMD_GET_CAPABILITIES_OUT_MCAST_FILTER_CHAINING_WIDTH 1 +#define MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_LBN 27 +#define MC_CMD_GET_CAPABILITIES_OUT_PM_AND_RXDP_COUNTERS_WIDTH 1 /* RxDPCPU firmware id. */ #define MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_OFST 4 #define MC_CMD_GET_CAPABILITIES_OUT_RX_DPCPU_FW_ID_LEN 2 @@ -6748,6 +7026,30 @@ /***********************************/ +/* MC_CMD_CAP_BLK_READ + * Read multiple 64bit words from capture block memory + */ +#define MC_CMD_CAP_BLK_READ 0xe7 + +/* MC_CMD_CAP_BLK_READ_IN msgrequest */ +#define MC_CMD_CAP_BLK_READ_IN_LEN 12 +#define MC_CMD_CAP_BLK_READ_IN_CAP_REG_OFST 0 +#define MC_CMD_CAP_BLK_READ_IN_ADDR_OFST 4 +#define MC_CMD_CAP_BLK_READ_IN_COUNT_OFST 8 + +/* MC_CMD_CAP_BLK_READ_OUT msgresponse */ +#define MC_CMD_CAP_BLK_READ_OUT_LENMIN 8 +#define MC_CMD_CAP_BLK_READ_OUT_LENMAX 248 +#define MC_CMD_CAP_BLK_READ_OUT_LEN(num) (0+8*(num)) +#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_OFST 0 +#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_LEN 8 +#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_LO_OFST 0 +#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_HI_OFST 4 +#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_MINNUM 1 +#define MC_CMD_CAP_BLK_READ_OUT_BUFFER_MAXNUM 31 + + +/***********************************/ /* MC_CMD_DUMP_DO * Take a dump of the DUT state */ @@ -6774,6 +7076,10 @@ #define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_HOST_MEMORY_MLI_DEPTH_OFST 20 #define MC_CMD_DUMP_DO_IN_HOST_MEMORY_MLI_MAX_DEPTH 0x2 /* enum */ #define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_UART_PORT_OFST 12 +/* enum: The uart port this command was received over (if using a uart + * transport) + */ +#define MC_CMD_DUMP_DO_IN_UART_PORT_SRC 0xff #define MC_CMD_DUMP_DO_IN_DUMPSPEC_SRC_CUSTOM_SIZE_OFST 24 #define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_OFST 28 #define MC_CMD_DUMP_DO_IN_DUMPFILE_DST_CUSTOM 0x0 /* enum */ @@ -6890,39 +7196,68 @@ /***********************************/ -/* MC_CMD_START_KR_EYE_PLOT - * Start KR Serdes Eye diagram plot on a given lane. Lane must have valid - * signal. - */ -#define MC_CMD_START_KR_EYE_PLOT 0xee - -/* MC_CMD_START_KR_EYE_PLOT_IN msgrequest */ -#define MC_CMD_START_KR_EYE_PLOT_IN_LEN 4 -#define MC_CMD_START_KR_EYE_PLOT_IN_LANE_OFST 0 - -/* MC_CMD_START_KR_EYE_PLOT_OUT msgresponse */ -#define MC_CMD_START_KR_EYE_PLOT_OUT_LEN 0 - - -/***********************************/ -/* MC_CMD_POLL_KR_EYE_PLOT - * Poll KR Serdes Eye diagram plot. Returns one row of BER data. The caller - * should call this command repeatedly after starting eye plot, until no more - * data is returned. - */ -#define MC_CMD_POLL_KR_EYE_PLOT 0xef - -/* MC_CMD_POLL_KR_EYE_PLOT_IN msgrequest */ -#define MC_CMD_POLL_KR_EYE_PLOT_IN_LEN 0 - -/* MC_CMD_POLL_KR_EYE_PLOT_OUT msgresponse */ -#define MC_CMD_POLL_KR_EYE_PLOT_OUT_LENMIN 0 -#define MC_CMD_POLL_KR_EYE_PLOT_OUT_LENMAX 252 -#define MC_CMD_POLL_KR_EYE_PLOT_OUT_LEN(num) (0+2*(num)) -#define MC_CMD_POLL_KR_EYE_PLOT_OUT_SAMPLES_OFST 0 -#define MC_CMD_POLL_KR_EYE_PLOT_OUT_SAMPLES_LEN 2 -#define MC_CMD_POLL_KR_EYE_PLOT_OUT_SAMPLES_MINNUM 0 -#define MC_CMD_POLL_KR_EYE_PLOT_OUT_SAMPLES_MAXNUM 126 +/* MC_CMD_UART_SEND_DATA + * Send checksummed[sic] block of data over the uart. Response is a placeholder + * should we wish to make this reliable; currently requests are fire-and- + * forget. + */ +#define MC_CMD_UART_SEND_DATA 0xee + +/* MC_CMD_UART_SEND_DATA_OUT msgrequest */ +#define MC_CMD_UART_SEND_DATA_OUT_LENMIN 16 +#define MC_CMD_UART_SEND_DATA_OUT_LENMAX 252 +#define MC_CMD_UART_SEND_DATA_OUT_LEN(num) (16+1*(num)) +/* CRC32 over OFFSET, LENGTH, RESERVED, DATA */ +#define MC_CMD_UART_SEND_DATA_OUT_CHECKSUM_OFST 0 +/* Offset at which to write the data */ +#define MC_CMD_UART_SEND_DATA_OUT_OFFSET_OFST 4 +/* Length of data */ +#define MC_CMD_UART_SEND_DATA_OUT_LENGTH_OFST 8 +/* Reserved for future use */ +#define MC_CMD_UART_SEND_DATA_OUT_RESERVED_OFST 12 +#define MC_CMD_UART_SEND_DATA_OUT_DATA_OFST 16 +#define MC_CMD_UART_SEND_DATA_OUT_DATA_LEN 1 +#define MC_CMD_UART_SEND_DATA_OUT_DATA_MINNUM 0 +#define MC_CMD_UART_SEND_DATA_OUT_DATA_MAXNUM 236 + +/* MC_CMD_UART_SEND_DATA_IN msgresponse */ +#define MC_CMD_UART_SEND_DATA_IN_LEN 0 + + +/***********************************/ +/* MC_CMD_UART_RECV_DATA + * Request checksummed[sic] block of data over the uart. Only a placeholder, + * subject to change and not currently implemented. + */ +#define MC_CMD_UART_RECV_DATA 0xef + +/* MC_CMD_UART_RECV_DATA_OUT msgrequest */ +#define MC_CMD_UART_RECV_DATA_OUT_LEN 16 +/* CRC32 over OFFSET, LENGTH, RESERVED */ +#define MC_CMD_UART_RECV_DATA_OUT_CHECKSUM_OFST 0 +/* Offset from which to read the data */ +#define MC_CMD_UART_RECV_DATA_OUT_OFFSET_OFST 4 +/* Length of data */ +#define MC_CMD_UART_RECV_DATA_OUT_LENGTH_OFST 8 +/* Reserved for future use */ +#define MC_CMD_UART_RECV_DATA_OUT_RESERVED_OFST 12 + +/* MC_CMD_UART_RECV_DATA_IN msgresponse */ +#define MC_CMD_UART_RECV_DATA_IN_LENMIN 16 +#define MC_CMD_UART_RECV_DATA_IN_LENMAX 252 +#define MC_CMD_UART_RECV_DATA_IN_LEN(num) (16+1*(num)) +/* CRC32 over RESERVED1, RESERVED2, RESERVED3, DATA */ +#define MC_CMD_UART_RECV_DATA_IN_CHECKSUM_OFST 0 +/* Offset at which to write the data */ +#define MC_CMD_UART_RECV_DATA_IN_RESERVED1_OFST 4 +/* Length of data */ +#define MC_CMD_UART_RECV_DATA_IN_RESERVED2_OFST 8 +/* Reserved for future use */ +#define MC_CMD_UART_RECV_DATA_IN_RESERVED3_OFST 12 +#define MC_CMD_UART_RECV_DATA_IN_DATA_OFST 16 +#define MC_CMD_UART_RECV_DATA_IN_DATA_LEN 1 +#define MC_CMD_UART_RECV_DATA_IN_DATA_MINNUM 0 +#define MC_CMD_UART_RECV_DATA_IN_DATA_MAXNUM 236 /***********************************/ @@ -6974,6 +7309,15 @@ #define MC_CMD_KR_TUNE_IN_TXEQ_SET 0x3 /* enum: Force KR Serdes reset / recalibration */ #define MC_CMD_KR_TUNE_IN_RECAL 0x4 +/* enum: Start KR Serdes Eye diagram plot on a given lane. Lane must have valid + * signal. + */ +#define MC_CMD_KR_TUNE_IN_START_EYE_PLOT 0x5 +/* enum: Poll KR Serdes Eye diagram plot. Returns one row of BER data. The + * caller should call this command repeatedly after starting eye plot, until no + * more data is returned. + */ +#define MC_CMD_KR_TUNE_IN_POLL_EYE_PLOT 0x6 /* Align the arguments to 32 bits */ #define MC_CMD_KR_TUNE_IN_KR_TUNE_RSVD_OFST 1 #define MC_CMD_KR_TUNE_IN_KR_TUNE_RSVD_LEN 3 @@ -7071,6 +7415,91 @@ /* MC_CMD_KR_TUNE_RXEQ_SET_OUT msgresponse */ #define MC_CMD_KR_TUNE_RXEQ_SET_OUT_LEN 0 +/* MC_CMD_KR_TUNE_TXEQ_GET_IN msgrequest */ +#define MC_CMD_KR_TUNE_TXEQ_GET_IN_LEN 4 +/* Requested operation */ +#define MC_CMD_KR_TUNE_TXEQ_GET_IN_KR_TUNE_OP_OFST 0 +#define MC_CMD_KR_TUNE_TXEQ_GET_IN_KR_TUNE_OP_LEN 1 +/* Align the arguments to 32 bits */ +#define MC_CMD_KR_TUNE_TXEQ_GET_IN_KR_TUNE_RSVD_OFST 1 +#define MC_CMD_KR_TUNE_TXEQ_GET_IN_KR_TUNE_RSVD_LEN 3 + +/* MC_CMD_KR_TUNE_TXEQ_GET_OUT msgresponse */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LENMIN 4 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LENMAX 252 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LEN(num) (0+4*(num)) +/* TXEQ Parameter */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_OFST 0 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LEN 4 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_MINNUM 1 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_MAXNUM 63 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_ID_LBN 0 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_ID_WIDTH 8 +/* enum: TX Amplitude */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_LEV 0x0 +/* enum: De-Emphasis Tap1 Magnitude (0-7) */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_MODE 0x1 +/* enum: De-Emphasis Tap1 Fine */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_DTLEV 0x2 +/* enum: De-Emphasis Tap2 Magnitude (0-6) */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_D2 0x3 +/* enum: De-Emphasis Tap2 Fine */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_D2TLEV 0x4 +/* enum: Pre-Emphasis Magnitude */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_E 0x5 +/* enum: Pre-Emphasis Fine */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_ETLEV 0x6 +/* enum: TX Slew Rate Coarse control */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_PREDRV_DLY 0x7 +/* enum: TX Slew Rate Fine control */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_TX_SR_SET 0x8 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LANE_LBN 8 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_LANE_WIDTH 3 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_0 0x0 /* enum */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_1 0x1 /* enum */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_2 0x2 /* enum */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_3 0x3 /* enum */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_LANE_ALL 0x4 /* enum */ +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_RESERVED_LBN 11 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_RESERVED_WIDTH 5 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_INITIAL_LBN 16 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_PARAM_INITIAL_WIDTH 8 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_RESERVED2_LBN 24 +#define MC_CMD_KR_TUNE_TXEQ_GET_OUT_RESERVED2_WIDTH 8 + +/* MC_CMD_KR_TUNE_TXEQ_SET_IN msgrequest */ +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_LENMIN 8 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_LENMAX 252 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_LEN(num) (4+4*(num)) +/* Requested operation */ +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_KR_TUNE_OP_OFST 0 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_KR_TUNE_OP_LEN 1 +/* Align the arguments to 32 bits */ +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_KR_TUNE_RSVD_OFST 1 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_KR_TUNE_RSVD_LEN 3 +/* TXEQ Parameter */ +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_OFST 4 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_LEN 4 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_MINNUM 1 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_MAXNUM 62 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_ID_LBN 0 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_ID_WIDTH 8 +/* Enum values, see field(s): */ +/* MC_CMD_KR_TUNE_TXEQ_GET_OUT/PARAM_ID */ +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_LANE_LBN 8 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_LANE_WIDTH 3 +/* Enum values, see field(s): */ +/* MC_CMD_KR_TUNE_TXEQ_GET_OUT/PARAM_LANE */ +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_RESERVED_LBN 11 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_RESERVED_WIDTH 5 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_INITIAL_LBN 16 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_PARAM_INITIAL_WIDTH 8 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_RESERVED2_LBN 24 +#define MC_CMD_KR_TUNE_TXEQ_SET_IN_RESERVED2_WIDTH 8 + +/* MC_CMD_KR_TUNE_TXEQ_SET_OUT msgresponse */ +#define MC_CMD_KR_TUNE_TXEQ_SET_OUT_LEN 0 + /* MC_CMD_KR_TUNE_RECAL_IN msgrequest */ #define MC_CMD_KR_TUNE_RECAL_IN_LEN 4 /* Requested operation */ @@ -7083,6 +7512,37 @@ /* MC_CMD_KR_TUNE_RECAL_OUT msgresponse */ #define MC_CMD_KR_TUNE_RECAL_OUT_LEN 0 +/* MC_CMD_KR_TUNE_START_EYE_PLOT_IN msgrequest */ +#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_LEN 8 +/* Requested operation */ +#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_KR_TUNE_OP_OFST 0 +#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_KR_TUNE_OP_LEN 1 +/* Align the arguments to 32 bits */ +#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_KR_TUNE_RSVD_OFST 1 +#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_KR_TUNE_RSVD_LEN 3 +#define MC_CMD_KR_TUNE_START_EYE_PLOT_IN_LANE_OFST 4 + +/* MC_CMD_KR_TUNE_START_EYE_PLOT_OUT msgresponse */ +#define MC_CMD_KR_TUNE_START_EYE_PLOT_OUT_LEN 0 + +/* MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN msgrequest */ +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN_LEN 4 +/* Requested operation */ +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN_KR_TUNE_OP_OFST 0 +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN_KR_TUNE_OP_LEN 1 +/* Align the arguments to 32 bits */ +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN_KR_TUNE_RSVD_OFST 1 +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_IN_KR_TUNE_RSVD_LEN 3 + +/* MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT msgresponse */ +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_LENMIN 0 +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_LENMAX 252 +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_LEN(num) (0+2*(num)) +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_OFST 0 +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_LEN 2 +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MINNUM 0 +#define MC_CMD_KR_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MAXNUM 126 + /***********************************/ /* MC_CMD_PCIE_TUNE @@ -7105,6 +7565,13 @@ #define MC_CMD_PCIE_TUNE_IN_TXEQ_GET 0x2 /* enum: Override TX Driver settings */ #define MC_CMD_PCIE_TUNE_IN_TXEQ_SET 0x3 +/* enum: Start PCIe Serdes Eye diagram plot on a given lane. */ +#define MC_CMD_PCIE_TUNE_IN_START_EYE_PLOT 0x5 +/* enum: Poll PCIe Serdes Eye diagram plot. Returns one row of BER data. The + * caller should call this command repeatedly after starting eye plot, until no + * more data is returned. + */ +#define MC_CMD_PCIE_TUNE_IN_POLL_EYE_PLOT 0x6 /* Align the arguments to 32 bits */ #define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_RSVD_OFST 1 #define MC_CMD_PCIE_TUNE_IN_PCIE_TUNE_RSVD_LEN 3 @@ -7206,6 +7673,37 @@ #define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_CURRENT_LBN 24 #define MC_CMD_PCIE_TUNE_TXEQ_GET_OUT_PARAM_CURRENT_WIDTH 8 +/* MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN msgrequest */ +#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_LEN 8 +/* Requested operation */ +#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_OP_OFST 0 +#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_OP_LEN 1 +/* Align the arguments to 32 bits */ +#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_RSVD_OFST 1 +#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_PCIE_TUNE_RSVD_LEN 3 +#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_IN_LANE_OFST 4 + +/* MC_CMD_PCIE_TUNE_START_EYE_PLOT_OUT msgresponse */ +#define MC_CMD_PCIE_TUNE_START_EYE_PLOT_OUT_LEN 0 + +/* MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN msgrequest */ +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_LEN 4 +/* Requested operation */ +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_OP_OFST 0 +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_OP_LEN 1 +/* Align the arguments to 32 bits */ +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_RSVD_OFST 1 +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_IN_PCIE_TUNE_RSVD_LEN 3 + +/* MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT msgresponse */ +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LENMIN 0 +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LENMAX 252 +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_LEN(num) (0+2*(num)) +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_OFST 0 +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_LEN 2 +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MINNUM 0 +#define MC_CMD_PCIE_TUNE_POLL_EYE_PLOT_OUT_SAMPLES_MAXNUM 126 + /***********************************/ /* MC_CMD_LICENSING @@ -7258,5 +7756,152 @@ */ #define MC_CMD_MC2MC_PROXY 0xf4 +/* MC_CMD_MC2MC_PROXY_IN msgrequest */ +#define MC_CMD_MC2MC_PROXY_IN_LEN 0 + +/* MC_CMD_MC2MC_PROXY_OUT msgresponse */ +#define MC_CMD_MC2MC_PROXY_OUT_LEN 0 + + +/***********************************/ +/* MC_CMD_GET_LICENSED_APP_STATE + * Query the state of an individual licensed application. (Note that the actual + * state may be invalidated by the MC_CMD_LICENSING OP_UPDATE_LICENSE operation + * or a reboot of the MC.) + */ +#define MC_CMD_GET_LICENSED_APP_STATE 0xf5 + +/* MC_CMD_GET_LICENSED_APP_STATE_IN msgrequest */ +#define MC_CMD_GET_LICENSED_APP_STATE_IN_LEN 4 +/* application ID to query (LICENSED_APP_ID_xxx) */ +#define MC_CMD_GET_LICENSED_APP_STATE_IN_APP_ID_OFST 0 + +/* MC_CMD_GET_LICENSED_APP_STATE_OUT msgresponse */ +#define MC_CMD_GET_LICENSED_APP_STATE_OUT_LEN 4 +/* state of this application */ +#define MC_CMD_GET_LICENSED_APP_STATE_OUT_STATE_OFST 0 +/* enum: no (or invalid) license is present for the application */ +#define MC_CMD_GET_LICENSED_APP_STATE_OUT_NOT_LICENSED 0x0 +/* enum: a valid license is present for the application */ +#define MC_CMD_GET_LICENSED_APP_STATE_OUT_LICENSED 0x1 + + +/***********************************/ +/* MC_CMD_LICENSED_APP_OP + * Perform an action for an individual licensed application. + */ +#define MC_CMD_LICENSED_APP_OP 0xf6 + +/* MC_CMD_LICENSED_APP_OP_IN msgrequest */ +#define MC_CMD_LICENSED_APP_OP_IN_LENMIN 8 +#define MC_CMD_LICENSED_APP_OP_IN_LENMAX 252 +#define MC_CMD_LICENSED_APP_OP_IN_LEN(num) (8+4*(num)) +/* application ID */ +#define MC_CMD_LICENSED_APP_OP_IN_APP_ID_OFST 0 +/* the type of operation requested */ +#define MC_CMD_LICENSED_APP_OP_IN_OP_OFST 4 +/* enum: validate application */ +#define MC_CMD_LICENSED_APP_OP_IN_OP_VALIDATE 0x0 +/* arguments specific to this particular operation */ +#define MC_CMD_LICENSED_APP_OP_IN_ARGS_OFST 8 +#define MC_CMD_LICENSED_APP_OP_IN_ARGS_LEN 4 +#define MC_CMD_LICENSED_APP_OP_IN_ARGS_MINNUM 0 +#define MC_CMD_LICENSED_APP_OP_IN_ARGS_MAXNUM 61 + +/* MC_CMD_LICENSED_APP_OP_OUT msgresponse */ +#define MC_CMD_LICENSED_APP_OP_OUT_LENMIN 0 +#define MC_CMD_LICENSED_APP_OP_OUT_LENMAX 252 +#define MC_CMD_LICENSED_APP_OP_OUT_LEN(num) (0+4*(num)) +/* result specific to this particular operation */ +#define MC_CMD_LICENSED_APP_OP_OUT_RESULT_OFST 0 +#define MC_CMD_LICENSED_APP_OP_OUT_RESULT_LEN 4 +#define MC_CMD_LICENSED_APP_OP_OUT_RESULT_MINNUM 0 +#define MC_CMD_LICENSED_APP_OP_OUT_RESULT_MAXNUM 63 + +/* MC_CMD_LICENSED_APP_OP_VALIDATE_IN msgrequest */ +#define MC_CMD_LICENSED_APP_OP_VALIDATE_IN_LEN 72 +/* application ID */ +#define MC_CMD_LICENSED_APP_OP_VALIDATE_IN_APP_ID_OFST 0 +/* the type of operation requested */ +#define MC_CMD_LICENSED_APP_OP_VALIDATE_IN_OP_OFST 4 +/* validation challenge */ +#define MC_CMD_LICENSED_APP_OP_VALIDATE_IN_CHALLENGE_OFST 8 +#define MC_CMD_LICENSED_APP_OP_VALIDATE_IN_CHALLENGE_LEN 64 + +/* MC_CMD_LICENSED_APP_OP_VALIDATE_OUT msgresponse */ +#define MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_LEN 68 +/* feature expiry (time_t) */ +#define MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_EXPIRY_OFST 0 +/* validation response */ +#define MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_RESPONSE_OFST 4 +#define MC_CMD_LICENSED_APP_OP_VALIDATE_OUT_RESPONSE_LEN 64 + + +/***********************************/ +/* MC_CMD_SET_PORT_SNIFF_CONFIG + * Configure port sniffing for the physical port associated with the calling + * function. Only a privileged function may change the port sniffing + * configuration. A copy of all traffic delivered to the host (non-promiscuous + * mode) or all traffic arriving at the port (promiscuous mode) may be + * delivered to a specific queue, or a set of queues with RSS. + */ +#define MC_CMD_SET_PORT_SNIFF_CONFIG 0xf7 + +/* MC_CMD_SET_PORT_SNIFF_CONFIG_IN msgrequest */ +#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_LEN 16 +/* configuration flags */ +#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_FLAGS_OFST 0 +#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_ENABLE_LBN 0 +#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_ENABLE_WIDTH 1 +#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_PROMISCUOUS_LBN 1 +#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_PROMISCUOUS_WIDTH 1 +/* receive queue handle (for RSS mode, this is the base queue) */ +#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_QUEUE_OFST 4 +/* receive mode */ +#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_OFST 8 +/* enum: receive to just the specified queue */ +#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_SIMPLE 0x0 +/* enum: receive to multiple queues using RSS context */ +#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_MODE_RSS 0x1 +/* RSS context (for RX_MODE_RSS) as returned by MC_CMD_RSS_CONTEXT_ALLOC. Note + * that these handles should be considered opaque to the host, although a value + * of 0xFFFFFFFF is guaranteed never to be a valid handle. + */ +#define MC_CMD_SET_PORT_SNIFF_CONFIG_IN_RX_CONTEXT_OFST 12 + +/* MC_CMD_SET_PORT_SNIFF_CONFIG_OUT msgresponse */ +#define MC_CMD_SET_PORT_SNIFF_CONFIG_OUT_LEN 0 + + +/***********************************/ +/* MC_CMD_GET_PORT_SNIFF_CONFIG + * Obtain the current port sniffing configuration for the physical port + * associated with the calling function. Only a privileged function may read + * the configuration. + */ +#define MC_CMD_GET_PORT_SNIFF_CONFIG 0xf8 + +/* MC_CMD_GET_PORT_SNIFF_CONFIG_IN msgrequest */ +#define MC_CMD_GET_PORT_SNIFF_CONFIG_IN_LEN 0 + +/* MC_CMD_GET_PORT_SNIFF_CONFIG_OUT msgresponse */ +#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_LEN 16 +/* configuration flags */ +#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_FLAGS_OFST 0 +#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_ENABLE_LBN 0 +#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_ENABLE_WIDTH 1 +#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_PROMISCUOUS_LBN 1 +#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_PROMISCUOUS_WIDTH 1 +/* receiving queue handle (for RSS mode, this is the base queue) */ +#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_QUEUE_OFST 4 +/* receive mode */ +#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_OFST 8 +/* enum: receiving to just the specified queue */ +#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_SIMPLE 0x0 +/* enum: receiving to multiple queues using RSS context */ +#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_MODE_RSS 0x1 +/* RSS context (for RX_MODE_RSS) */ +#define MC_CMD_GET_PORT_SNIFF_CONFIG_OUT_RX_CONTEXT_OFST 12 + #endif /* MCDI_PCOL_H */ diff --git a/drivers/net/ethernet/sfc/mcdi_port.c b/drivers/net/ethernet/sfc/mcdi_port.c index 8d33da6697f..e5fc4e1574b 100644 --- a/drivers/net/ethernet/sfc/mcdi_port.c +++ b/drivers/net/ethernet/sfc/mcdi_port.c @@ -90,13 +90,6 @@ static int efx_mcdi_set_link(struct efx_nic *efx, u32 capabilities, rc = efx_mcdi_rpc(efx, MC_CMD_SET_LINK, inbuf, sizeof(inbuf), NULL, 0, NULL); - if (rc) - goto fail; - - return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); return rc; } @@ -143,17 +136,13 @@ static int efx_mcdi_mdio_read(struct net_device *net_dev, rc = efx_mcdi_rpc(efx, MC_CMD_MDIO_READ, inbuf, sizeof(inbuf), outbuf, sizeof(outbuf), &outlen); if (rc) - goto fail; + return rc; if (MCDI_DWORD(outbuf, MDIO_READ_OUT_STATUS) != MC_CMD_MDIO_STATUS_GOOD) return -EIO; return (u16)MCDI_DWORD(outbuf, MDIO_READ_OUT_VALUE); - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); - return rc; } static int efx_mcdi_mdio_write(struct net_device *net_dev, @@ -174,17 +163,13 @@ static int efx_mcdi_mdio_write(struct net_device *net_dev, rc = efx_mcdi_rpc(efx, MC_CMD_MDIO_WRITE, inbuf, sizeof(inbuf), outbuf, sizeof(outbuf), &outlen); if (rc) - goto fail; + return rc; if (MCDI_DWORD(outbuf, MDIO_WRITE_OUT_STATUS) != MC_CMD_MDIO_STATUS_GOOD) return -EIO; return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", __func__, rc); - return rc; } static u32 mcdi_to_ethtool_cap(u32 media, u32 cap) @@ -487,17 +472,14 @@ static bool efx_mcdi_phy_poll(struct efx_nic *efx) rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, outbuf, sizeof(outbuf), NULL); - if (rc) { - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", - __func__, rc); + if (rc) efx->link_state.up = false; - } else { + else efx_mcdi_phy_decode_link( efx, &efx->link_state, MCDI_DWORD(outbuf, GET_LINK_OUT_LINK_SPEED), MCDI_DWORD(outbuf, GET_LINK_OUT_FLAGS), MCDI_DWORD(outbuf, GET_LINK_OUT_FCNTL)); - } return !efx_link_state_equal(&efx->link_state, &old_state); } @@ -531,11 +513,8 @@ static void efx_mcdi_phy_get_settings(struct efx_nic *efx, struct ethtool_cmd *e BUILD_BUG_ON(MC_CMD_GET_LINK_IN_LEN != 0); rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, outbuf, sizeof(outbuf), NULL); - if (rc) { - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", - __func__, rc); + if (rc) return; - } ecmd->lp_advertising = mcdi_to_ethtool_cap(phy_cfg->media, MCDI_DWORD(outbuf, GET_LINK_OUT_LP_CAP)); @@ -556,6 +535,7 @@ static int efx_mcdi_phy_set_settings(struct efx_nic *efx, struct ethtool_cmd *ec case 100: caps = 1 << MC_CMD_PHY_CAP_100FDX_LBN; break; case 1000: caps = 1 << MC_CMD_PHY_CAP_1000FDX_LBN; break; case 10000: caps = 1 << MC_CMD_PHY_CAP_10000FDX_LBN; break; + case 40000: caps = 1 << MC_CMD_PHY_CAP_40000FDX_LBN; break; default: return -EINVAL; } } else { @@ -841,6 +821,7 @@ static unsigned int efx_mcdi_event_link_speed[] = { [MCDI_EVENT_LINKCHANGE_SPEED_100M] = 100, [MCDI_EVENT_LINKCHANGE_SPEED_1G] = 1000, [MCDI_EVENT_LINKCHANGE_SPEED_10G] = 10000, + [MCDI_EVENT_LINKCHANGE_SPEED_40G] = 40000, }; void efx_mcdi_process_link_change(struct efx_nic *efx, efx_qword_t *ev) @@ -873,8 +854,8 @@ int efx_mcdi_set_mac(struct efx_nic *efx) BUILD_BUG_ON(MC_CMD_SET_MAC_OUT_LEN != 0); - memcpy(MCDI_PTR(cmdbytes, SET_MAC_IN_ADDR), - efx->net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(MCDI_PTR(cmdbytes, SET_MAC_IN_ADDR), + efx->net_dev->dev_addr); MCDI_SET_DWORD(cmdbytes, SET_MAC_IN_MTU, EFX_MAX_FRAME_LEN(efx->net_dev->mtu)); @@ -916,21 +897,29 @@ bool efx_mcdi_mac_check_fault(struct efx_nic *efx) rc = efx_mcdi_rpc(efx, MC_CMD_GET_LINK, NULL, 0, outbuf, sizeof(outbuf), &outlength); - if (rc) { - netif_err(efx, hw, efx->net_dev, "%s: failed rc=%d\n", - __func__, rc); + if (rc) return true; - } return MCDI_DWORD(outbuf, GET_LINK_OUT_MAC_FAULT) != 0; } -static int efx_mcdi_mac_stats(struct efx_nic *efx, dma_addr_t dma_addr, - u32 dma_len, int enable, int clear) +enum efx_stats_action { + EFX_STATS_ENABLE, + EFX_STATS_DISABLE, + EFX_STATS_PULL, +}; + +static int efx_mcdi_mac_stats(struct efx_nic *efx, + enum efx_stats_action action, int clear) { MCDI_DECLARE_BUF(inbuf, MC_CMD_MAC_STATS_IN_LEN); int rc; - int period = enable ? 1000 : 0; + int change = action == EFX_STATS_PULL ? 0 : 1; + int enable = action == EFX_STATS_ENABLE ? 1 : 0; + int period = action == EFX_STATS_ENABLE ? 1000 : 0; + dma_addr_t dma_addr = efx->stats_buffer.dma_addr; + u32 dma_len = action != EFX_STATS_DISABLE ? + MC_CMD_MAC_NSTATS * sizeof(u64) : 0; BUILD_BUG_ON(MC_CMD_MAC_STATS_OUT_DMA_LEN != 0); @@ -938,8 +927,8 @@ static int efx_mcdi_mac_stats(struct efx_nic *efx, dma_addr_t dma_addr, MCDI_POPULATE_DWORD_7(inbuf, MAC_STATS_IN_CMD, MAC_STATS_IN_DMA, !!enable, MAC_STATS_IN_CLEAR, clear, - MAC_STATS_IN_PERIODIC_CHANGE, 1, - MAC_STATS_IN_PERIODIC_ENABLE, !!enable, + MAC_STATS_IN_PERIODIC_CHANGE, change, + MAC_STATS_IN_PERIODIC_ENABLE, enable, MAC_STATS_IN_PERIODIC_CLEAR, 0, MAC_STATS_IN_PERIODIC_NOEVENT, 1, MAC_STATS_IN_PERIOD_MS, period); @@ -947,14 +936,6 @@ static int efx_mcdi_mac_stats(struct efx_nic *efx, dma_addr_t dma_addr, rc = efx_mcdi_rpc(efx, MC_CMD_MAC_STATS, inbuf, sizeof(inbuf), NULL, 0, NULL); - if (rc) - goto fail; - - return 0; - -fail: - netif_err(efx, hw, efx->net_dev, "%s: %s failed rc=%d\n", - __func__, enable ? "enable" : "disable", rc); return rc; } @@ -964,13 +945,29 @@ void efx_mcdi_mac_start_stats(struct efx_nic *efx) dma_stats[MC_CMD_MAC_GENERATION_END] = EFX_MC_STATS_GENERATION_INVALID; - efx_mcdi_mac_stats(efx, efx->stats_buffer.dma_addr, - MC_CMD_MAC_NSTATS * sizeof(u64), 1, 0); + efx_mcdi_mac_stats(efx, EFX_STATS_ENABLE, 0); } void efx_mcdi_mac_stop_stats(struct efx_nic *efx) { - efx_mcdi_mac_stats(efx, efx->stats_buffer.dma_addr, 0, 0, 0); + efx_mcdi_mac_stats(efx, EFX_STATS_DISABLE, 0); +} + +#define EFX_MAC_STATS_WAIT_US 100 +#define EFX_MAC_STATS_WAIT_ATTEMPTS 10 + +void efx_mcdi_mac_pull_stats(struct efx_nic *efx) +{ + __le64 *dma_stats = efx->stats_buffer.addr; + int attempts = EFX_MAC_STATS_WAIT_ATTEMPTS; + + dma_stats[MC_CMD_MAC_GENERATION_END] = EFX_MC_STATS_GENERATION_INVALID; + efx_mcdi_mac_stats(efx, EFX_STATS_PULL, 0); + + while (dma_stats[MC_CMD_MAC_GENERATION_END] == + EFX_MC_STATS_GENERATION_INVALID && + attempts-- != 0) + udelay(EFX_MAC_STATS_WAIT_US); } int efx_mcdi_port_probe(struct efx_nic *efx) @@ -1001,7 +998,7 @@ int efx_mcdi_port_probe(struct efx_nic *efx) efx->stats_buffer.addr, (u64)virt_to_phys(efx->stats_buffer.addr)); - efx_mcdi_mac_stats(efx, efx->stats_buffer.dma_addr, 0, 0, 1); + efx_mcdi_mac_stats(efx, EFX_STATS_DISABLE, 1); return 0; } diff --git a/drivers/net/ethernet/sfc/mdio_10g.h b/drivers/net/ethernet/sfc/mdio_10g.h index 16824fecc5e..4a2dc4c281b 100644 --- a/drivers/net/ethernet/sfc/mdio_10g.h +++ b/drivers/net/ethernet/sfc/mdio_10g.h @@ -20,7 +20,7 @@ static inline unsigned efx_mdio_id_rev(u32 id) { return id & 0xf; } static inline unsigned efx_mdio_id_model(u32 id) { return (id >> 4) & 0x3f; } -extern unsigned efx_mdio_id_oui(u32 id); +unsigned efx_mdio_id_oui(u32 id); static inline int efx_mdio_read(struct efx_nic *efx, int devad, int addr) { @@ -56,7 +56,7 @@ static inline bool efx_mdio_phyxgxs_lane_sync(struct efx_nic *efx) return sync; } -extern const char *efx_mdio_mmd_name(int mmd); +const char *efx_mdio_mmd_name(int mmd); /* * Reset a specific MMD and wait for reset to clear. @@ -64,30 +64,29 @@ extern const char *efx_mdio_mmd_name(int mmd); * * This function will sleep */ -extern int efx_mdio_reset_mmd(struct efx_nic *efx, int mmd, - int spins, int spintime); +int efx_mdio_reset_mmd(struct efx_nic *efx, int mmd, int spins, int spintime); /* As efx_mdio_check_mmd but for multiple MMDs */ int efx_mdio_check_mmds(struct efx_nic *efx, unsigned int mmd_mask); /* Check the link status of specified mmds in bit mask */ -extern bool efx_mdio_links_ok(struct efx_nic *efx, unsigned int mmd_mask); +bool efx_mdio_links_ok(struct efx_nic *efx, unsigned int mmd_mask); /* Generic transmit disable support though PMAPMD */ -extern void efx_mdio_transmit_disable(struct efx_nic *efx); +void efx_mdio_transmit_disable(struct efx_nic *efx); /* Generic part of reconfigure: set/clear loopback bits */ -extern void efx_mdio_phy_reconfigure(struct efx_nic *efx); +void efx_mdio_phy_reconfigure(struct efx_nic *efx); /* Set the power state of the specified MMDs */ -extern void efx_mdio_set_mmds_lpower(struct efx_nic *efx, - int low_power, unsigned int mmd_mask); +void efx_mdio_set_mmds_lpower(struct efx_nic *efx, int low_power, + unsigned int mmd_mask); /* Set (some of) the PHY settings over MDIO */ -extern int efx_mdio_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd); +int efx_mdio_set_settings(struct efx_nic *efx, struct ethtool_cmd *ecmd); /* Push advertising flags and restart autonegotiation */ -extern void efx_mdio_an_reconfigure(struct efx_nic *efx); +void efx_mdio_an_reconfigure(struct efx_nic *efx); /* Get pause parameters from AN if available (otherwise return * requested pause parameters) @@ -95,8 +94,7 @@ extern void efx_mdio_an_reconfigure(struct efx_nic *efx); u8 efx_mdio_get_pause(struct efx_nic *efx); /* Wait for specified MMDs to exit reset within a timeout */ -extern int efx_mdio_wait_reset_mmds(struct efx_nic *efx, - unsigned int mmd_mask); +int efx_mdio_wait_reset_mmds(struct efx_nic *efx, unsigned int mmd_mask); /* Set or clear flag, debouncing */ static inline void @@ -107,6 +105,6 @@ efx_mdio_set_flag(struct efx_nic *efx, int devad, int addr, } /* Liveness self-test for MDIO PHYs */ -extern int efx_mdio_test_alive(struct efx_nic *efx); +int efx_mdio_test_alive(struct efx_nic *efx); #endif /* EFX_MDIO_10G_H */ diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index b172ed13305..5bdae8ed7c5 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -91,6 +91,7 @@ /* Forward declare Precision Time Protocol (PTP) support structure. */ struct efx_ptp_data; +struct hwtstamp_config; struct efx_self_tests; @@ -141,6 +142,8 @@ struct efx_special_buffer { * @len: Length of this fragment. * This field is zero when the queue slot is empty. * @unmap_len: Length of this fragment to unmap + * @dma_offset: Offset of @dma_addr from the address of the backing DMA mapping. + * Only valid if @unmap_len != 0. */ struct efx_tx_buffer { union { @@ -154,6 +157,7 @@ struct efx_tx_buffer { unsigned short flags; unsigned short len; unsigned short unmap_len; + unsigned short dma_offset; }; #define EFX_TX_BUF_CONT 1 /* not last descriptor of packet */ #define EFX_TX_BUF_SKB 2 /* buffer is last part of skb */ @@ -182,6 +186,9 @@ struct efx_tx_buffer { * @tsoh_page: Array of pages of TSO header buffers * @txd: The hardware descriptor ring * @ptr_mask: The size of the ring minus 1. + * @piobuf: PIO buffer region for this TX queue (shared with its partner). + * Size of the region is efx_piobuf_size. + * @piobuf_offset: Buffer offset to be specified in PIO descriptors * @initialised: Has hardware queue been initialised? * @read_count: Current read pointer. * This is the number of buffers that have been removed from both rings. @@ -209,6 +216,7 @@ struct efx_tx_buffer { * blocks * @tso_packets: Number of packets via the TSO xmit path * @pushes: Number of times the TX push feature has been used + * @pio_packets: Number of times the TX PIO feature has been used * @empty_read_count: If the completion path has seen the queue as empty * and the transmission path has not yet checked this, the value of * @read_count bitwise-added to %EFX_EMPTY_COUNT_VALID; otherwise 0. @@ -223,6 +231,8 @@ struct efx_tx_queue { struct efx_buffer *tsoh_page; struct efx_special_buffer txd; unsigned int ptr_mask; + void __iomem *piobuf; + unsigned int piobuf_offset; bool initialised; /* Members used mainly on the completion path */ @@ -238,6 +248,7 @@ struct efx_tx_queue { unsigned int tso_long_headers; unsigned int tso_packets; unsigned int pushes; + unsigned int pio_packets; /* Members shared between paths and sometimes updated */ unsigned int empty_read_count ____cacheline_aligned_in_smp; @@ -277,12 +288,9 @@ struct efx_rx_buffer { * Used to facilitate sharing dma mappings between recycled rx buffers * and those passed up to the kernel. * - * @refcnt: Number of struct efx_rx_buffer's referencing this page. - * When refcnt falls to zero, the page is unmapped for dma * @dma_addr: The dma address of this page. */ struct efx_rx_page_state { - unsigned refcnt; dma_addr_t dma_addr; unsigned int __pad[0] ____cacheline_aligned; @@ -352,10 +360,11 @@ struct efx_rx_queue { unsigned int slow_fill_count; }; -enum efx_rx_alloc_method { - RX_ALLOC_METHOD_AUTO = 0, - RX_ALLOC_METHOD_SKB = 1, - RX_ALLOC_METHOD_PAGE = 2, +enum efx_sync_events_state { + SYNC_EVENTS_DISABLED = 0, + SYNC_EVENTS_QUIESCENT, + SYNC_EVENTS_REQUESTED, + SYNC_EVENTS_VALID, }; /** @@ -397,6 +406,9 @@ enum efx_rx_alloc_method { * by __efx_rx_packet(), if @rx_pkt_n_frags != 0 * @rx_queue: RX queue for this channel * @tx_queue: TX queues for this channel + * @sync_events_state: Current state of sync events on this channel + * @sync_timestamp_major: Major part of the last ptp sync event + * @sync_timestamp_minor: Minor part of the last ptp sync event */ struct efx_channel { struct efx_nic *efx; @@ -435,6 +447,10 @@ struct efx_channel { struct efx_rx_queue rx_queue; struct efx_tx_queue tx_queue[EFX_TXQ_TYPES]; + + enum efx_sync_events_state sync_events_state; + u32 sync_timestamp_major; + u32 sync_timestamp_minor; }; /** @@ -510,15 +526,6 @@ enum nic_state { STATE_RECOVERY = 3, /* device recovering from PCI error */ }; -/* - * Alignment of the skb->head which wraps a page-allocated RX buffer - * - * The skb allocated to wrap an rx_buffer can have this alignment. Since - * the data is memcpy'd from the rx_buf, it does not need to be equal to - * NET_IP_ALIGN. - */ -#define EFX_PAGE_SKB_ALIGN 2 - /* Forward declaration */ struct efx_nic; @@ -641,6 +648,13 @@ struct vfdi_status; * struct efx_nic - an Efx NIC * @name: Device name (net device name or bus id before net device registered) * @pci_dev: The PCI device + * @node: List node for maintaning primary/secondary function lists + * @primary: &struct efx_nic instance for the primary function of this + * controller. May be the same structure, and may be %NULL if no + * primary function is bound. Serialised by rtnl_lock. + * @secondary_list: List of &struct efx_nic instances for the secondary PCI + * functions of the controller, if this is for the primary function. + * Serialised by rtnl_lock. * @type: Controller type attributes * @legacy_irq: IRQ number * @workqueue: Workqueue for port reconfigures and the HW monitor. @@ -673,6 +687,8 @@ struct vfdi_status; * @n_channels: Number of channels in use * @n_rx_channels: Number of channels used for RX (= number of RX queues) * @n_tx_channels: Number of channels used for TX + * @rx_ip_align: RX DMA address offset to have IP header aligned in + * in accordance with NET_IP_ALIGN * @rx_dma_len: Current maximum RX DMA length * @rx_buffer_order: Order (log2) of number of pages for each RX buffer * @rx_buffer_truesize: Amortised allocation size of an RX buffer, @@ -682,6 +698,8 @@ struct vfdi_status; * (valid only if @rx_prefix_size != 0; always negative) * @rx_packet_len_offset: Offset of RX packet length from start of packet data * (valid only for NICs that set %EFX_RX_PKT_PREFIX_LEN; always negative) + * @rx_packet_ts_offset: Offset of timestamp from start of packet data + * (valid only if channel->sync_timestamps_enabled; always negative) * @rx_hash_key: Toeplitz hash key for RSS * @rx_indir_table: Indirection table for RSS * @rx_scatter: Scatter mode enabled for receives @@ -751,6 +769,7 @@ struct vfdi_status; * @local_lock: Mutex protecting %local_addr_list and %local_page_list. * @peer_work: Work item to broadcast peer addresses to VMs. * @ptp_data: PTP state data + * @vpd_sn: Serial number read from VPD * @monitor_work: Hardware monitor workitem * @biu_lock: BIU (bus interface unit) lock * @last_irq_cpu: Last CPU to handle a possible test interrupt. This @@ -765,6 +784,9 @@ struct efx_nic { /* The following fields should be written very rarely */ char name[IFNAMSIZ]; + struct list_head node; + struct efx_nic *primary; + struct list_head secondary_list; struct pci_dev *pci_dev; unsigned int port_num; const struct efx_nic_type *type; @@ -806,6 +828,7 @@ struct efx_nic { unsigned rss_spread; unsigned tx_channel_offset; unsigned n_tx_channels; + unsigned int rx_ip_align; unsigned int rx_dma_len; unsigned int rx_buffer_order; unsigned int rx_buffer_truesize; @@ -815,6 +838,7 @@ struct efx_nic { unsigned int rx_prefix_size; int rx_packet_hash_offset; int rx_packet_len_offset; + int rx_packet_ts_offset; u8 rx_hash_key[40]; u32 rx_indir_table[128]; bool rx_scatter; @@ -839,10 +863,14 @@ struct efx_nic { struct work_struct mac_work; bool port_enabled; + bool mc_bist_for_other_fn; bool port_initialized; struct net_device *net_dev; struct efx_buffer stats_buffer; + u64 rx_nodesc_drops_total; + u64 rx_nodesc_drops_while_down; + bool rx_nodesc_drops_prev_state; unsigned int phy_type; const struct efx_phy_operations *phy_op; @@ -894,6 +922,8 @@ struct efx_nic { struct efx_ptp_data *ptp_data; + char *vpd_sn; + /* The following fields may be written more often */ struct delayed_work monitor_work ____cacheline_aligned_in_smp; @@ -942,10 +972,13 @@ struct efx_mtd_partition { * (for Falcon architecture) * @finish_flush: Clean up after flushing the DMA queues (for Falcon * architecture) + * @prepare_flr: Prepare for an FLR + * @finish_flr: Clean up after an FLR * @describe_stats: Describe statistics for ethtool * @update_stats: Update statistics not provided by event handling. * Either argument may be %NULL. * @start_stats: Start the regular fetching of statistics + * @pull_stats: Pull stats from the NIC and wait until they arrive. * @stop_stats: Stop the regular fetching of statistics * @set_id_led: Set state of identifying LED or revert to automatic function * @push_irq_moderation: Apply interrupt moderation value @@ -984,7 +1017,7 @@ struct efx_mtd_partition { * @tx_init: Initialise TX queue on the NIC * @tx_remove: Free resources for TX queue * @tx_write: Write TX descriptors and doorbell - * @rx_push_indir_table: Write RSS indirection table to the NIC + * @rx_push_rss_config: Write RSS hash key and indirection table to the NIC * @rx_probe: Allocate resources for RX queue * @rx_init: Initialise RX queue on the NIC * @rx_remove: Free resources for RX queue @@ -1004,7 +1037,8 @@ struct efx_mtd_partition { * @filter_insert: add or replace a filter * @filter_remove_safe: remove a filter by ID, carefully * @filter_get_safe: retrieve a filter by ID, carefully - * @filter_clear_rx: remove RX filters by priority + * @filter_clear_rx: Remove all RX filters whose priority is less than or + * equal to the given priority and is not %EFX_FILTER_PRI_AUTO * @filter_count_rx_used: Get the number of filters in use at a given priority * @filter_get_rx_id_limit: Get maximum value of a filter id, plus 1 * @filter_get_rx_ids: Get list of RX filters at a given priority @@ -1024,6 +1058,12 @@ struct efx_mtd_partition { * @mtd_sync: Wait for write-back to complete on MTD partition. This * also notifies the driver that a writer has finished using this * partition. + * @ptp_write_host_time: Send host time to MC as part of sync protocol + * @ptp_set_ts_sync_events: Enable or disable sync events for inline RX + * timestamping, possibly only temporarily for the purposes of a reset. + * @ptp_set_ts_config: Set hardware timestamp configuration. The flags + * and tx_type will already have been validated but this operation + * must validate and update rx_filter. * @revision: Hardware architecture revision * @txd_ptr_tbl_base: TX descriptor ring base address * @rxd_ptr_tbl_base: RX descriptor ring base address @@ -1033,6 +1073,7 @@ struct efx_mtd_partition { * @max_dma_mask: Maximum possible DMA mask * @rx_prefix_size: Size of RX prefix before packet data * @rx_hash_offset: Offset of RX flow hash within prefix + * @rx_ts_offset: Offset of timestamp within prefix * @rx_buffer_padding: Size of padding at end of RX packet * @can_rx_scatter: NIC is able to scatter packets to multiple buffers * @always_rx_scatter: NIC will always scatter packets to multiple buffers @@ -1042,6 +1083,7 @@ struct efx_mtd_partition { * @offload_features: net_device feature flags for protocol offload * features implemented in hardware * @mcdi_max_ver: Maximum MCDI version supported + * @hwtstamp_filters: Mask of hardware timestamp filter types supported */ struct efx_nic_type { unsigned int (*mem_map_size)(struct efx_nic *efx); @@ -1060,10 +1102,13 @@ struct efx_nic_type { int (*fini_dmaq)(struct efx_nic *efx); void (*prepare_flush)(struct efx_nic *efx); void (*finish_flush)(struct efx_nic *efx); + void (*prepare_flr)(struct efx_nic *efx); + void (*finish_flr)(struct efx_nic *efx); size_t (*describe_stats)(struct efx_nic *efx, u8 *names); size_t (*update_stats)(struct efx_nic *efx, u64 *full_stats, struct rtnl_link_stats64 *core_stats); void (*start_stats)(struct efx_nic *efx); + void (*pull_stats)(struct efx_nic *efx); void (*stop_stats)(struct efx_nic *efx); void (*set_id_led)(struct efx_nic *efx, enum efx_led_mode mode); void (*push_irq_moderation)(struct efx_channel *channel); @@ -1092,7 +1137,7 @@ struct efx_nic_type { void (*tx_init)(struct efx_tx_queue *tx_queue); void (*tx_remove)(struct efx_tx_queue *tx_queue); void (*tx_write)(struct efx_tx_queue *tx_queue); - void (*rx_push_indir_table)(struct efx_nic *efx); + void (*rx_push_rss_config)(struct efx_nic *efx); int (*rx_probe)(struct efx_rx_queue *rx_queue); void (*rx_init)(struct efx_rx_queue *rx_queue); void (*rx_remove)(struct efx_rx_queue *rx_queue); @@ -1117,8 +1162,8 @@ struct efx_nic_type { int (*filter_get_safe)(struct efx_nic *efx, enum efx_filter_priority priority, u32 filter_id, struct efx_filter_spec *); - void (*filter_clear_rx)(struct efx_nic *efx, - enum efx_filter_priority priority); + int (*filter_clear_rx)(struct efx_nic *efx, + enum efx_filter_priority priority); u32 (*filter_count_rx_used)(struct efx_nic *efx, enum efx_filter_priority priority); u32 (*filter_get_rx_id_limit)(struct efx_nic *efx); @@ -1142,6 +1187,9 @@ struct efx_nic_type { int (*mtd_sync)(struct mtd_info *mtd); #endif void (*ptp_write_host_time)(struct efx_nic *efx, u32 host_time); + int (*ptp_set_ts_sync_events)(struct efx_nic *efx, bool en, bool temp); + int (*ptp_set_ts_config)(struct efx_nic *efx, + struct hwtstamp_config *init); int revision; unsigned int txd_ptr_tbl_base; @@ -1152,6 +1200,7 @@ struct efx_nic_type { u64 max_dma_mask; unsigned int rx_prefix_size; unsigned int rx_hash_offset; + unsigned int rx_ts_offset; unsigned int rx_buffer_padding; bool can_rx_scatter; bool always_rx_scatter; @@ -1160,6 +1209,7 @@ struct efx_nic_type { netdev_features_t offload_features; int mcdi_max_ver; unsigned int max_rx_ip_filters; + u32 hwtstamp_filters; }; /************************************************************************** @@ -1277,7 +1327,6 @@ static inline struct efx_rx_buffer *efx_rx_buffer(struct efx_rx_queue *rx_queue, return &rx_queue->buffer[index]; } - /** * EFX_MAX_FRAME_LEN - calculate maximum frame length * diff --git a/drivers/net/ethernet/sfc/nic.c b/drivers/net/ethernet/sfc/nic.c index e7dbd2dd202..89b83e59e1d 100644 --- a/drivers/net/ethernet/sfc/nic.c +++ b/drivers/net/ethernet/sfc/nic.c @@ -19,6 +19,7 @@ #include "bitfield.h" #include "efx.h" #include "nic.h" +#include "ef10_regs.h" #include "farch_regs.h" #include "io.h" #include "workarounds.h" @@ -155,37 +156,43 @@ void efx_nic_fini_interrupt(struct efx_nic *efx) efx->net_dev->rx_cpu_rmap = NULL; #endif - /* Disable MSI/MSI-X interrupts */ - efx_for_each_channel(channel, efx) - free_irq(channel->irq, &efx->msi_context[channel->channel]); - - /* Disable legacy interrupt */ - if (efx->legacy_irq) + if (EFX_INT_MODE_USE_MSI(efx)) { + /* Disable MSI/MSI-X interrupts */ + efx_for_each_channel(channel, efx) + free_irq(channel->irq, + &efx->msi_context[channel->channel]); + } else { + /* Disable legacy interrupt */ free_irq(efx->legacy_irq, efx); + } } /* Register dump */ -#define REGISTER_REVISION_A 1 -#define REGISTER_REVISION_B 2 -#define REGISTER_REVISION_C 3 -#define REGISTER_REVISION_Z 3 /* latest revision */ +#define REGISTER_REVISION_FA 1 +#define REGISTER_REVISION_FB 2 +#define REGISTER_REVISION_FC 3 +#define REGISTER_REVISION_FZ 3 /* last Falcon arch revision */ +#define REGISTER_REVISION_ED 4 +#define REGISTER_REVISION_EZ 4 /* latest EF10 revision */ struct efx_nic_reg { u32 offset:24; - u32 min_revision:2, max_revision:2; + u32 min_revision:3, max_revision:3; }; -#define REGISTER(name, min_rev, max_rev) { \ - FR_ ## min_rev ## max_rev ## _ ## name, \ - REGISTER_REVISION_ ## min_rev, REGISTER_REVISION_ ## max_rev \ +#define REGISTER(name, arch, min_rev, max_rev) { \ + arch ## R_ ## min_rev ## max_rev ## _ ## name, \ + REGISTER_REVISION_ ## arch ## min_rev, \ + REGISTER_REVISION_ ## arch ## max_rev \ } -#define REGISTER_AA(name) REGISTER(name, A, A) -#define REGISTER_AB(name) REGISTER(name, A, B) -#define REGISTER_AZ(name) REGISTER(name, A, Z) -#define REGISTER_BB(name) REGISTER(name, B, B) -#define REGISTER_BZ(name) REGISTER(name, B, Z) -#define REGISTER_CZ(name) REGISTER(name, C, Z) +#define REGISTER_AA(name) REGISTER(name, F, A, A) +#define REGISTER_AB(name) REGISTER(name, F, A, B) +#define REGISTER_AZ(name) REGISTER(name, F, A, Z) +#define REGISTER_BB(name) REGISTER(name, F, B, B) +#define REGISTER_BZ(name) REGISTER(name, F, B, Z) +#define REGISTER_CZ(name) REGISTER(name, F, C, Z) +#define REGISTER_DZ(name) REGISTER(name, E, D, Z) static const struct efx_nic_reg efx_nic_regs[] = { REGISTER_AZ(ADR_REGION), @@ -292,37 +299,42 @@ static const struct efx_nic_reg efx_nic_regs[] = { REGISTER_AB(XX_TXDRV_CTL), /* XX_PRBS_CTL, XX_PRBS_CHK and XX_PRBS_ERR are not used */ /* XX_CORE_STAT is partly RC */ + REGISTER_DZ(BIU_HW_REV_ID), + REGISTER_DZ(MC_DB_LWRD), + REGISTER_DZ(MC_DB_HWRD), }; struct efx_nic_reg_table { u32 offset:24; - u32 min_revision:2, max_revision:2; + u32 min_revision:3, max_revision:3; u32 step:6, rows:21; }; -#define REGISTER_TABLE_DIMENSIONS(_, offset, min_rev, max_rev, step, rows) { \ +#define REGISTER_TABLE_DIMENSIONS(_, offset, arch, min_rev, max_rev, step, rows) { \ offset, \ - REGISTER_REVISION_ ## min_rev, REGISTER_REVISION_ ## max_rev, \ + REGISTER_REVISION_ ## arch ## min_rev, \ + REGISTER_REVISION_ ## arch ## max_rev, \ step, rows \ } -#define REGISTER_TABLE(name, min_rev, max_rev) \ +#define REGISTER_TABLE(name, arch, min_rev, max_rev) \ REGISTER_TABLE_DIMENSIONS( \ - name, FR_ ## min_rev ## max_rev ## _ ## name, \ - min_rev, max_rev, \ - FR_ ## min_rev ## max_rev ## _ ## name ## _STEP, \ - FR_ ## min_rev ## max_rev ## _ ## name ## _ROWS) -#define REGISTER_TABLE_AA(name) REGISTER_TABLE(name, A, A) -#define REGISTER_TABLE_AZ(name) REGISTER_TABLE(name, A, Z) -#define REGISTER_TABLE_BB(name) REGISTER_TABLE(name, B, B) -#define REGISTER_TABLE_BZ(name) REGISTER_TABLE(name, B, Z) + name, arch ## R_ ## min_rev ## max_rev ## _ ## name, \ + arch, min_rev, max_rev, \ + arch ## R_ ## min_rev ## max_rev ## _ ## name ## _STEP, \ + arch ## R_ ## min_rev ## max_rev ## _ ## name ## _ROWS) +#define REGISTER_TABLE_AA(name) REGISTER_TABLE(name, F, A, A) +#define REGISTER_TABLE_AZ(name) REGISTER_TABLE(name, F, A, Z) +#define REGISTER_TABLE_BB(name) REGISTER_TABLE(name, F, B, B) +#define REGISTER_TABLE_BZ(name) REGISTER_TABLE(name, F, B, Z) #define REGISTER_TABLE_BB_CZ(name) \ - REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, B, B, \ + REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, F, B, B, \ FR_BZ_ ## name ## _STEP, \ FR_BB_ ## name ## _ROWS), \ - REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, C, Z, \ + REGISTER_TABLE_DIMENSIONS(name, FR_BZ_ ## name, F, C, Z, \ FR_BZ_ ## name ## _STEP, \ FR_CZ_ ## name ## _ROWS) -#define REGISTER_TABLE_CZ(name) REGISTER_TABLE(name, C, Z) +#define REGISTER_TABLE_CZ(name) REGISTER_TABLE(name, F, C, Z) +#define REGISTER_TABLE_DZ(name) REGISTER_TABLE(name, E, D, Z) static const struct efx_nic_reg_table efx_nic_reg_tables[] = { /* DRIVER is not used */ @@ -340,9 +352,9 @@ static const struct efx_nic_reg_table efx_nic_reg_tables[] = { * 1K entries allows for some expansion of queue count and * size before we need to change the version. */ REGISTER_TABLE_DIMENSIONS(BUF_FULL_TBL_KER, FR_AA_BUF_FULL_TBL_KER, - A, A, 8, 1024), + F, A, A, 8, 1024), REGISTER_TABLE_DIMENSIONS(BUF_FULL_TBL, FR_BZ_BUF_FULL_TBL, - B, Z, 8, 1024), + F, B, Z, 8, 1024), REGISTER_TABLE_CZ(RX_MAC_FILTER_TBL0), REGISTER_TABLE_BB_CZ(TIMER_TBL), REGISTER_TABLE_BB_CZ(TX_PACE_TBL), @@ -353,6 +365,7 @@ static const struct efx_nic_reg_table efx_nic_reg_tables[] = { /* MSIX_PBA_TABLE is not mapped */ /* SRM_DBG is not mapped (and is redundant with BUF_FLL_TBL) */ REGISTER_TABLE_BZ(RX_FILTER_TBL0), + REGISTER_TABLE_DZ(BIU_MC_SFT_STATUS), }; size_t efx_nic_get_regs_len(struct efx_nic *efx) @@ -469,8 +482,7 @@ size_t efx_nic_describe_stats(const struct efx_hw_stat_desc *desc, size_t count, * @count: Length of the @desc array * @mask: Bitmask of which elements of @desc are enabled * @stats: Buffer to update with the converted statistics. The length - * of this array must be at least the number of set bits in the - * first @count bits of @mask. + * of this array must be at least @count. * @dma_buf: DMA buffer containing hardware statistics * @accumulate: If set, the converted values will be added rather than * directly stored to the corresponding elements of @stats @@ -503,11 +515,20 @@ void efx_nic_update_stats(const struct efx_hw_stat_desc *desc, size_t count, } if (accumulate) - *stats += val; + stats[index] += val; else - *stats = val; + stats[index] = val; } - - ++stats; } } + +void efx_nic_fix_nodesc_drop_stat(struct efx_nic *efx, u64 *rx_nodesc_drops) +{ + /* if down, or this is the first update after coming up */ + if (!(efx->net_dev->flags & IFF_UP) || !efx->rx_nodesc_drops_prev_state) + efx->rx_nodesc_drops_while_down += + *rx_nodesc_drops - efx->rx_nodesc_drops_total; + efx->rx_nodesc_drops_total = *rx_nodesc_drops; + efx->rx_nodesc_drops_prev_state = !!(efx->net_dev->flags & IFF_UP); + *rx_nodesc_drops -= efx->rx_nodesc_drops_while_down; +} diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h index 4b1e188f7a2..d3ad8ed8d90 100644 --- a/drivers/net/ethernet/sfc/nic.h +++ b/drivers/net/ethernet/sfc/nic.h @@ -30,7 +30,7 @@ static inline int efx_nic_rev(struct efx_nic *efx) return efx->type->revision; } -extern u32 efx_farch_fpga_ver(struct efx_nic *efx); +u32 efx_farch_fpga_ver(struct efx_nic *efx); /* NIC has two interlinked PCI functions for the same port. */ static inline bool efx_nic_is_dual_func(struct efx_nic *efx) @@ -71,6 +71,26 @@ efx_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index) return ((efx_qword_t *) (tx_queue->txd.buf.addr)) + index; } +/* Report whether the NIC considers this TX queue empty, given the + * write_count used for the last doorbell push. May return false + * negative. + */ +static inline bool __efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue, + unsigned int write_count) +{ + unsigned int empty_read_count = ACCESS_ONCE(tx_queue->empty_read_count); + + if (empty_read_count == 0) + return false; + + return ((empty_read_count ^ write_count) & ~EFX_EMPTY_COUNT_VALID) == 0; +} + +static inline bool efx_nic_tx_is_empty(struct efx_tx_queue *tx_queue) +{ + return __efx_nic_tx_is_empty(tx_queue, tx_queue->write_count); +} + /* Decide whether to push a TX descriptor to the NIC vs merely writing * the doorbell. This can reduce latency when we are adding a single * descriptor to an empty queue, but is otherwise pointless. Further, @@ -80,14 +100,10 @@ efx_tx_desc(struct efx_tx_queue *tx_queue, unsigned int index) static inline bool efx_nic_may_push_tx_desc(struct efx_tx_queue *tx_queue, unsigned int write_count) { - unsigned empty_read_count = ACCESS_ONCE(tx_queue->empty_read_count); - - if (empty_read_count == 0) - return false; + bool was_empty = __efx_nic_tx_is_empty(tx_queue, write_count); tx_queue->empty_read_count = 0; - return ((empty_read_count ^ write_count) & ~EFX_EMPTY_COUNT_VALID) == 0 - && tx_queue->write_count - write_count == 1; + return was_empty && tx_queue->write_count - write_count == 1; } /* Returns a pointer to the specified descriptor in the RX descriptor queue */ @@ -386,9 +402,27 @@ enum { EF10_STAT_rx_align_error, EF10_STAT_rx_length_error, EF10_STAT_rx_nodesc_drops, + EF10_STAT_rx_pm_trunc_bb_overflow, + EF10_STAT_rx_pm_discard_bb_overflow, + EF10_STAT_rx_pm_trunc_vfifo_full, + EF10_STAT_rx_pm_discard_vfifo_full, + EF10_STAT_rx_pm_trunc_qbb, + EF10_STAT_rx_pm_discard_qbb, + EF10_STAT_rx_pm_discard_mapping, + EF10_STAT_rx_dp_q_disabled_packets, + EF10_STAT_rx_dp_di_dropped_packets, + EF10_STAT_rx_dp_streaming_packets, + EF10_STAT_rx_dp_hlb_fetch, + EF10_STAT_rx_dp_hlb_wait, EF10_STAT_COUNT }; +/* Maximum number of TX PIO buffers we may allocate to a function. + * This matches the total number of buffers on each SFC9100-family + * controller. + */ +#define EF10_TX_PIOBUF_COUNT 16 + /** * struct efx_ef10_nic_data - EF10 architecture NIC state * @mcdi_buf: DMA buffer for MCDI @@ -397,9 +431,18 @@ enum { * @n_allocated_vis: Number of VIs allocated to this function * @must_realloc_vis: Flag: VIs have yet to be reallocated after MC reboot * @must_restore_filters: Flag: filters have yet to be restored after MC reboot + * @n_piobufs: Number of PIO buffers allocated to this function + * @wc_membase: Base address of write-combining mapping of the memory BAR + * @pio_write_base: Base address for writing PIO buffers + * @pio_write_vi_base: Relative VI number for @pio_write_base + * @piobuf_handle: Handle of each PIO buffer allocated + * @must_restore_piobufs: Flag: PIO buffers have yet to be restored after MC + * reboot * @rx_rss_context: Firmware handle for our RSS context * @stats: Hardware statistics * @workaround_35388: Flag: firmware supports workaround for bug 35388 + * @must_check_datapath_caps: Flag: @datapath_caps needs to be revalidated + * after MC reboot * @datapath_caps: Capabilities of datapath firmware (FLAGS1 field of * %MC_CMD_GET_CAPABILITIES response) */ @@ -410,9 +453,15 @@ struct efx_ef10_nic_data { unsigned int n_allocated_vis; bool must_realloc_vis; bool must_restore_filters; + unsigned int n_piobufs; + void __iomem *wc_membase, *pio_write_base; + unsigned int pio_write_vi_base; + unsigned int piobuf_handle[EF10_TX_PIOBUF_COUNT]; + bool must_restore_piobufs; u32 rx_rss_context; u64 stats[EF10_STAT_COUNT]; bool workaround_35388; + bool must_check_datapath_caps; u32 datapath_caps; }; @@ -460,18 +509,18 @@ static inline unsigned int efx_vf_size(struct efx_nic *efx) return 1 << efx->vi_scale; } -extern int efx_init_sriov(void); -extern void efx_sriov_probe(struct efx_nic *efx); -extern int efx_sriov_init(struct efx_nic *efx); -extern void efx_sriov_mac_address_changed(struct efx_nic *efx); -extern void efx_sriov_tx_flush_done(struct efx_nic *efx, efx_qword_t *event); -extern void efx_sriov_rx_flush_done(struct efx_nic *efx, efx_qword_t *event); -extern void efx_sriov_event(struct efx_channel *channel, efx_qword_t *event); -extern void efx_sriov_desc_fetch_err(struct efx_nic *efx, unsigned dmaq); -extern void efx_sriov_flr(struct efx_nic *efx, unsigned flr); -extern void efx_sriov_reset(struct efx_nic *efx); -extern void efx_sriov_fini(struct efx_nic *efx); -extern void efx_fini_sriov(void); +int efx_init_sriov(void); +void efx_sriov_probe(struct efx_nic *efx); +int efx_sriov_init(struct efx_nic *efx); +void efx_sriov_mac_address_changed(struct efx_nic *efx); +void efx_sriov_tx_flush_done(struct efx_nic *efx, efx_qword_t *event); +void efx_sriov_rx_flush_done(struct efx_nic *efx, efx_qword_t *event); +void efx_sriov_event(struct efx_channel *channel, efx_qword_t *event); +void efx_sriov_desc_fetch_err(struct efx_nic *efx, unsigned dmaq); +void efx_sriov_flr(struct efx_nic *efx, unsigned flr); +void efx_sriov_reset(struct efx_nic *efx); +void efx_sriov_fini(struct efx_nic *efx); +void efx_fini_sriov(void); #else @@ -497,22 +546,39 @@ static inline void efx_fini_sriov(void) {} #endif -extern int efx_sriov_set_vf_mac(struct net_device *dev, int vf, u8 *mac); -extern int efx_sriov_set_vf_vlan(struct net_device *dev, int vf, - u16 vlan, u8 qos); -extern int efx_sriov_get_vf_config(struct net_device *dev, int vf, - struct ifla_vf_info *ivf); -extern int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf, - bool spoofchk); +int efx_sriov_set_vf_mac(struct net_device *dev, int vf, u8 *mac); +int efx_sriov_set_vf_vlan(struct net_device *dev, int vf, u16 vlan, u8 qos); +int efx_sriov_get_vf_config(struct net_device *dev, int vf, + struct ifla_vf_info *ivf); +int efx_sriov_set_vf_spoofchk(struct net_device *net_dev, int vf, + bool spoofchk); struct ethtool_ts_info; -extern void efx_ptp_probe(struct efx_nic *efx); -extern int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd); -extern void efx_ptp_get_ts_info(struct efx_nic *efx, - struct ethtool_ts_info *ts_info); -extern bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb); -extern int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb); -extern void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev); +int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel); +void efx_ptp_defer_probe_with_channel(struct efx_nic *efx); +void efx_ptp_remove(struct efx_nic *efx); +int efx_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr); +int efx_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr); +void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info); +bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb); +int efx_ptp_get_mode(struct efx_nic *efx); +int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted, + unsigned int new_mode); +int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb); +void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev); +size_t efx_ptp_describe_stats(struct efx_nic *efx, u8 *strings); +size_t efx_ptp_update_stats(struct efx_nic *efx, u64 *stats); +void efx_time_sync_event(struct efx_channel *channel, efx_qword_t *ev); +void __efx_rx_skb_attach_timestamp(struct efx_channel *channel, + struct sk_buff *skb); +static inline void efx_rx_skb_attach_timestamp(struct efx_channel *channel, + struct sk_buff *skb) +{ + if (channel->sync_events_state == SYNC_EVENTS_VALID) + __efx_rx_skb_attach_timestamp(channel, skb); +} +void efx_ptp_start_datapath(struct efx_nic *efx); +void efx_ptp_stop_datapath(struct efx_nic *efx); extern const struct efx_nic_type falcon_a1_nic_type; extern const struct efx_nic_type falcon_b0_nic_type; @@ -526,7 +592,7 @@ extern const struct efx_nic_type efx_hunt_a0_nic_type; ************************************************************************** */ -extern int falcon_probe_board(struct efx_nic *efx, u16 revision_info); +int falcon_probe_board(struct efx_nic *efx, u16 revision_info); /* TX data path */ static inline int efx_nic_probe_tx(struct efx_tx_queue *tx_queue) @@ -594,58 +660,58 @@ static inline void efx_nic_eventq_read_ack(struct efx_channel *channel) { channel->efx->type->ev_read_ack(channel); } -extern void efx_nic_event_test_start(struct efx_channel *channel); +void efx_nic_event_test_start(struct efx_channel *channel); /* Falcon/Siena queue operations */ -extern int efx_farch_tx_probe(struct efx_tx_queue *tx_queue); -extern void efx_farch_tx_init(struct efx_tx_queue *tx_queue); -extern void efx_farch_tx_fini(struct efx_tx_queue *tx_queue); -extern void efx_farch_tx_remove(struct efx_tx_queue *tx_queue); -extern void efx_farch_tx_write(struct efx_tx_queue *tx_queue); -extern int efx_farch_rx_probe(struct efx_rx_queue *rx_queue); -extern void efx_farch_rx_init(struct efx_rx_queue *rx_queue); -extern void efx_farch_rx_fini(struct efx_rx_queue *rx_queue); -extern void efx_farch_rx_remove(struct efx_rx_queue *rx_queue); -extern void efx_farch_rx_write(struct efx_rx_queue *rx_queue); -extern void efx_farch_rx_defer_refill(struct efx_rx_queue *rx_queue); -extern int efx_farch_ev_probe(struct efx_channel *channel); -extern int efx_farch_ev_init(struct efx_channel *channel); -extern void efx_farch_ev_fini(struct efx_channel *channel); -extern void efx_farch_ev_remove(struct efx_channel *channel); -extern int efx_farch_ev_process(struct efx_channel *channel, int quota); -extern void efx_farch_ev_read_ack(struct efx_channel *channel); -extern void efx_farch_ev_test_generate(struct efx_channel *channel); +int efx_farch_tx_probe(struct efx_tx_queue *tx_queue); +void efx_farch_tx_init(struct efx_tx_queue *tx_queue); +void efx_farch_tx_fini(struct efx_tx_queue *tx_queue); +void efx_farch_tx_remove(struct efx_tx_queue *tx_queue); +void efx_farch_tx_write(struct efx_tx_queue *tx_queue); +int efx_farch_rx_probe(struct efx_rx_queue *rx_queue); +void efx_farch_rx_init(struct efx_rx_queue *rx_queue); +void efx_farch_rx_fini(struct efx_rx_queue *rx_queue); +void efx_farch_rx_remove(struct efx_rx_queue *rx_queue); +void efx_farch_rx_write(struct efx_rx_queue *rx_queue); +void efx_farch_rx_defer_refill(struct efx_rx_queue *rx_queue); +int efx_farch_ev_probe(struct efx_channel *channel); +int efx_farch_ev_init(struct efx_channel *channel); +void efx_farch_ev_fini(struct efx_channel *channel); +void efx_farch_ev_remove(struct efx_channel *channel); +int efx_farch_ev_process(struct efx_channel *channel, int quota); +void efx_farch_ev_read_ack(struct efx_channel *channel); +void efx_farch_ev_test_generate(struct efx_channel *channel); /* Falcon/Siena filter operations */ -extern int efx_farch_filter_table_probe(struct efx_nic *efx); -extern void efx_farch_filter_table_restore(struct efx_nic *efx); -extern void efx_farch_filter_table_remove(struct efx_nic *efx); -extern void efx_farch_filter_update_rx_scatter(struct efx_nic *efx); -extern s32 efx_farch_filter_insert(struct efx_nic *efx, - struct efx_filter_spec *spec, bool replace); -extern int efx_farch_filter_remove_safe(struct efx_nic *efx, - enum efx_filter_priority priority, - u32 filter_id); -extern int efx_farch_filter_get_safe(struct efx_nic *efx, - enum efx_filter_priority priority, - u32 filter_id, struct efx_filter_spec *); -extern void efx_farch_filter_clear_rx(struct efx_nic *efx, - enum efx_filter_priority priority); -extern u32 efx_farch_filter_count_rx_used(struct efx_nic *efx, - enum efx_filter_priority priority); -extern u32 efx_farch_filter_get_rx_id_limit(struct efx_nic *efx); -extern s32 efx_farch_filter_get_rx_ids(struct efx_nic *efx, - enum efx_filter_priority priority, - u32 *buf, u32 size); +int efx_farch_filter_table_probe(struct efx_nic *efx); +void efx_farch_filter_table_restore(struct efx_nic *efx); +void efx_farch_filter_table_remove(struct efx_nic *efx); +void efx_farch_filter_update_rx_scatter(struct efx_nic *efx); +s32 efx_farch_filter_insert(struct efx_nic *efx, struct efx_filter_spec *spec, + bool replace); +int efx_farch_filter_remove_safe(struct efx_nic *efx, + enum efx_filter_priority priority, + u32 filter_id); +int efx_farch_filter_get_safe(struct efx_nic *efx, + enum efx_filter_priority priority, u32 filter_id, + struct efx_filter_spec *); +int efx_farch_filter_clear_rx(struct efx_nic *efx, + enum efx_filter_priority priority); +u32 efx_farch_filter_count_rx_used(struct efx_nic *efx, + enum efx_filter_priority priority); +u32 efx_farch_filter_get_rx_id_limit(struct efx_nic *efx); +s32 efx_farch_filter_get_rx_ids(struct efx_nic *efx, + enum efx_filter_priority priority, u32 *buf, + u32 size); #ifdef CONFIG_RFS_ACCEL -extern s32 efx_farch_filter_rfs_insert(struct efx_nic *efx, - struct efx_filter_spec *spec); -extern bool efx_farch_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id, - unsigned int index); +s32 efx_farch_filter_rfs_insert(struct efx_nic *efx, + struct efx_filter_spec *spec); +bool efx_farch_filter_rfs_expire_one(struct efx_nic *efx, u32 flow_id, + unsigned int index); #endif -extern void efx_farch_filter_sync_rx_mode(struct efx_nic *efx); +void efx_farch_filter_sync_rx_mode(struct efx_nic *efx); -extern bool efx_nic_event_present(struct efx_channel *channel); +bool efx_nic_event_present(struct efx_channel *channel); /* Some statistics are computed as A - B where A and B each increase * linearly with some hardware counter(s) and the counters are read @@ -666,17 +732,17 @@ static inline void efx_update_diff_stat(u64 *stat, u64 diff) } /* Interrupts */ -extern int efx_nic_init_interrupt(struct efx_nic *efx); -extern void efx_nic_irq_test_start(struct efx_nic *efx); -extern void efx_nic_fini_interrupt(struct efx_nic *efx); +int efx_nic_init_interrupt(struct efx_nic *efx); +void efx_nic_irq_test_start(struct efx_nic *efx); +void efx_nic_fini_interrupt(struct efx_nic *efx); /* Falcon/Siena interrupts */ -extern void efx_farch_irq_enable_master(struct efx_nic *efx); -extern void efx_farch_irq_test_generate(struct efx_nic *efx); -extern void efx_farch_irq_disable_master(struct efx_nic *efx); -extern irqreturn_t efx_farch_msi_interrupt(int irq, void *dev_id); -extern irqreturn_t efx_farch_legacy_interrupt(int irq, void *dev_id); -extern irqreturn_t efx_farch_fatal_interrupt(struct efx_nic *efx); +void efx_farch_irq_enable_master(struct efx_nic *efx); +void efx_farch_irq_test_generate(struct efx_nic *efx); +void efx_farch_irq_disable_master(struct efx_nic *efx); +irqreturn_t efx_farch_msi_interrupt(int irq, void *dev_id); +irqreturn_t efx_farch_legacy_interrupt(int irq, void *dev_id); +irqreturn_t efx_farch_fatal_interrupt(struct efx_nic *efx); static inline int efx_nic_event_test_irq_cpu(struct efx_channel *channel) { @@ -688,21 +754,18 @@ static inline int efx_nic_irq_test_irq_cpu(struct efx_nic *efx) } /* Global Resources */ -extern int efx_nic_flush_queues(struct efx_nic *efx); -extern void siena_prepare_flush(struct efx_nic *efx); -extern int efx_farch_fini_dmaq(struct efx_nic *efx); -extern void siena_finish_flush(struct efx_nic *efx); -extern void falcon_start_nic_stats(struct efx_nic *efx); -extern void falcon_stop_nic_stats(struct efx_nic *efx); -extern int falcon_reset_xaui(struct efx_nic *efx); -extern void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw); -extern void efx_farch_init_common(struct efx_nic *efx); -extern void efx_ef10_handle_drain_event(struct efx_nic *efx); -static inline void efx_nic_push_rx_indir_table(struct efx_nic *efx) -{ - efx->type->rx_push_indir_table(efx); -} -extern void efx_farch_rx_push_indir_table(struct efx_nic *efx); +int efx_nic_flush_queues(struct efx_nic *efx); +void siena_prepare_flush(struct efx_nic *efx); +int efx_farch_fini_dmaq(struct efx_nic *efx); +void efx_farch_finish_flr(struct efx_nic *efx); +void siena_finish_flush(struct efx_nic *efx); +void falcon_start_nic_stats(struct efx_nic *efx); +void falcon_stop_nic_stats(struct efx_nic *efx); +int falcon_reset_xaui(struct efx_nic *efx); +void efx_farch_dimension_resources(struct efx_nic *efx, unsigned sram_lim_qw); +void efx_farch_init_common(struct efx_nic *efx); +void efx_ef10_handle_drain_event(struct efx_nic *efx); +void efx_farch_rx_push_indir_table(struct efx_nic *efx); int efx_nic_alloc_buffer(struct efx_nic *efx, struct efx_buffer *buffer, unsigned int len, gfp_t gfp_flags); @@ -713,24 +776,23 @@ struct efx_farch_register_test { unsigned address; efx_oword_t mask; }; -extern int efx_farch_test_registers(struct efx_nic *efx, - const struct efx_farch_register_test *regs, - size_t n_regs); +int efx_farch_test_registers(struct efx_nic *efx, + const struct efx_farch_register_test *regs, + size_t n_regs); -extern size_t efx_nic_get_regs_len(struct efx_nic *efx); -extern void efx_nic_get_regs(struct efx_nic *efx, void *buf); +size_t efx_nic_get_regs_len(struct efx_nic *efx); +void efx_nic_get_regs(struct efx_nic *efx, void *buf); -extern size_t -efx_nic_describe_stats(const struct efx_hw_stat_desc *desc, size_t count, - const unsigned long *mask, u8 *names); -extern void -efx_nic_update_stats(const struct efx_hw_stat_desc *desc, size_t count, - const unsigned long *mask, - u64 *stats, const void *dma_buf, bool accumulate); +size_t efx_nic_describe_stats(const struct efx_hw_stat_desc *desc, size_t count, + const unsigned long *mask, u8 *names); +void efx_nic_update_stats(const struct efx_hw_stat_desc *desc, size_t count, + const unsigned long *mask, u64 *stats, + const void *dma_buf, bool accumulate); +void efx_nic_fix_nodesc_drop_stat(struct efx_nic *efx, u64 *stat); #define EFX_MAX_FLUSH_TIME 5000 -extern void efx_farch_generate_event(struct efx_nic *efx, unsigned int evq, - efx_qword_t *event); +void efx_farch_generate_event(struct efx_nic *efx, unsigned int evq, + efx_qword_t *event); #endif /* EFX_NIC_H */ diff --git a/drivers/net/ethernet/sfc/phy.h b/drivers/net/ethernet/sfc/phy.h index 45eeb707515..803bf445c08 100644 --- a/drivers/net/ethernet/sfc/phy.h +++ b/drivers/net/ethernet/sfc/phy.h @@ -15,7 +15,7 @@ */ extern const struct efx_phy_operations falcon_sfx7101_phy_ops; -extern void tenxpress_set_id_led(struct efx_nic *efx, enum efx_led_mode mode); +void tenxpress_set_id_led(struct efx_nic *efx, enum efx_led_mode mode); /**************************************************************************** * AMCC/Quake QT202x PHYs @@ -34,7 +34,7 @@ extern const struct efx_phy_operations falcon_qt202x_phy_ops; #define QUAKE_LED_TXLINK (0) #define QUAKE_LED_RXLINK (8) -extern void falcon_qt202x_set_led(struct efx_nic *p, int led, int state); +void falcon_qt202x_set_led(struct efx_nic *p, int led, int state); /**************************************************************************** * Transwitch CX4 retimer @@ -44,7 +44,7 @@ extern const struct efx_phy_operations falcon_txc_phy_ops; #define TXC_GPIO_DIR_INPUT 0 #define TXC_GPIO_DIR_OUTPUT 1 -extern void falcon_txc_set_gpio_dir(struct efx_nic *efx, int pin, int dir); -extern void falcon_txc_set_gpio_val(struct efx_nic *efx, int pin, int val); +void falcon_txc_set_gpio_dir(struct efx_nic *efx, int pin, int dir); +void falcon_txc_set_gpio_val(struct efx_nic *efx, int pin, int val); #endif diff --git a/drivers/net/ethernet/sfc/ptp.c b/drivers/net/ethernet/sfc/ptp.c index 03acf57df04..6b861e3de4b 100644 --- a/drivers/net/ethernet/sfc/ptp.c +++ b/drivers/net/ethernet/sfc/ptp.c @@ -62,7 +62,7 @@ #define SYNCHRONISATION_GRANULARITY_NS 200 /* Minimum permitted length of a (corrected) synchronisation time */ -#define MIN_SYNCHRONISATION_NS 120 +#define DEFAULT_MIN_SYNCHRONISATION_NS 120 /* Maximum permitted length of a (corrected) synchronisation time */ #define MAX_SYNCHRONISATION_NS 1000 @@ -195,26 +195,29 @@ struct efx_ptp_event_rx { /** * struct efx_ptp_timeset - Synchronisation between host and MC * @host_start: Host time immediately before hardware timestamp taken - * @seconds: Hardware timestamp, seconds - * @nanoseconds: Hardware timestamp, nanoseconds + * @major: Hardware timestamp, major + * @minor: Hardware timestamp, minor * @host_end: Host time immediately after hardware timestamp taken - * @waitns: Number of nanoseconds between hardware timestamp being read and + * @wait: Number of NIC clock ticks between hardware timestamp being read and * host end time being seen * @window: Difference of host_end and host_start * @valid: Whether this timeset is valid */ struct efx_ptp_timeset { u32 host_start; - u32 seconds; - u32 nanoseconds; + u32 major; + u32 minor; u32 host_end; - u32 waitns; + u32 wait; u32 window; /* Derived: end - start, allowing for wrap */ }; /** * struct efx_ptp_data - Precision Time Protocol (PTP) state - * @channel: The PTP channel + * @efx: The NIC context + * @channel: The PTP channel (Siena only) + * @rx_ts_inline: Flag for whether RX timestamps are inline (else they are + * separate events) * @rxq: Receive queue (awaiting timestamps) * @txq: Transmit queue * @evt_list: List of MC receive events awaiting packets @@ -230,41 +233,42 @@ struct efx_ptp_timeset { * @config: Current timestamp configuration * @enabled: PTP operation enabled * @mode: Mode in which PTP operating (PTP version) + * @time_format: Time format supported by this NIC + * @ns_to_nic_time: Function to convert from scalar nanoseconds to NIC time + * @nic_to_kernel_time: Function to convert from NIC to kernel time + * @min_synchronisation_ns: Minimum acceptable corrected sync window + * @ts_corrections.tx: Required driver correction of transmit timestamps + * @ts_corrections.rx: Required driver correction of receive timestamps + * @ts_corrections.pps_out: PPS output error (information only) + * @ts_corrections.pps_in: Required driver correction of PPS input timestamps * @evt_frags: Partly assembled PTP events * @evt_frag_idx: Current fragment number * @evt_code: Last event code * @start: Address at which MC indicates ready for synchronisation * @host_time_pps: Host time at last PPS - * @last_sync_ns: Last number of nanoseconds between readings when synchronising - * @base_sync_ns: Number of nanoseconds for last synchronisation. - * @base_sync_valid: Whether base_sync_time is valid. * @current_adjfreq: Current ppb adjustment. - * @phc_clock: Pointer to registered phc device + * @phc_clock: Pointer to registered phc device (if primary function) * @phc_clock_info: Registration structure for phc device * @pps_work: pps work task for handling pps events * @pps_workwq: pps work queue * @nic_ts_enabled: Flag indicating if NIC generated TS events are handled * @txbuf: Buffer for use when transmitting (PTP) packets to MC (avoids * allocations in main data path). - * @debug_ptp_dir: PTP debugfs directory - * @missed_rx_sync: Number of packets received without syncrhonisation. * @good_syncs: Number of successful synchronisations. - * @no_time_syncs: Number of synchronisations with no good times. - * @bad_sync_durations: Number of synchronisations with bad durations. + * @fast_syncs: Number of synchronisations requiring short delay * @bad_syncs: Number of failed synchronisations. - * @last_sync_time: Number of nanoseconds for last synchronisation. * @sync_timeouts: Number of synchronisation timeouts - * @fast_syncs: Number of synchronisations requiring short delay - * @min_sync_delta: Minimum time between event and synchronisation - * @max_sync_delta: Maximum time between event and synchronisation - * @average_sync_delta: Average time between event and synchronisation. - * Modified moving average. - * @last_sync_delta: Last time between event and synchronisation - * @mc_stats: Context value for MC statistics + * @no_time_syncs: Number of synchronisations with no good times. + * @invalid_sync_windows: Number of sync windows with bad durations. + * @undersize_sync_windows: Number of corrected sync windows that are too small + * @oversize_sync_windows: Number of corrected sync windows that are too large + * @rx_no_timestamp: Number of packets received without a timestamp. * @timeset: Last set of synchronisation statistics. */ struct efx_ptp_data { + struct efx_nic *efx; struct efx_channel *channel; + bool rx_ts_inline; struct sk_buff_head rxq; struct sk_buff_head txq; struct list_head evt_list; @@ -280,14 +284,22 @@ struct efx_ptp_data { struct hwtstamp_config config; bool enabled; unsigned int mode; + unsigned int time_format; + void (*ns_to_nic_time)(s64 ns, u32 *nic_major, u32 *nic_minor); + ktime_t (*nic_to_kernel_time)(u32 nic_major, u32 nic_minor, + s32 correction); + unsigned int min_synchronisation_ns; + struct { + s32 tx; + s32 rx; + s32 pps_out; + s32 pps_in; + } ts_corrections; efx_qword_t evt_frags[MAX_EVENT_FRAGS]; int evt_frag_idx; int evt_code; struct efx_buffer start; struct pps_event_time host_time_pps; - unsigned last_sync_ns; - unsigned base_sync_ns; - bool base_sync_valid; s64 current_adjfreq; struct ptp_clock *phc_clock; struct ptp_clock_info phc_clock_info; @@ -295,6 +307,16 @@ struct efx_ptp_data { struct workqueue_struct *pps_workwq; bool nic_ts_enabled; MCDI_DECLARE_BUF(txbuf, MC_CMD_PTP_IN_TRANSMIT_LENMAX); + + unsigned int good_syncs; + unsigned int fast_syncs; + unsigned int bad_syncs; + unsigned int sync_timeouts; + unsigned int no_time_syncs; + unsigned int invalid_sync_windows; + unsigned int undersize_sync_windows; + unsigned int oversize_sync_windows; + unsigned int rx_no_timestamp; struct efx_ptp_timeset timeset[MC_CMD_PTP_OUT_SYNCHRONIZE_TIMESET_MAXNUM]; }; @@ -307,19 +329,263 @@ static int efx_phc_settime(struct ptp_clock_info *ptp, static int efx_phc_enable(struct ptp_clock_info *ptp, struct ptp_clock_request *request, int on); +#define PTP_SW_STAT(ext_name, field_name) \ + { #ext_name, 0, offsetof(struct efx_ptp_data, field_name) } +#define PTP_MC_STAT(ext_name, mcdi_name) \ + { #ext_name, 32, MC_CMD_PTP_OUT_STATUS_STATS_ ## mcdi_name ## _OFST } +static const struct efx_hw_stat_desc efx_ptp_stat_desc[] = { + PTP_SW_STAT(ptp_good_syncs, good_syncs), + PTP_SW_STAT(ptp_fast_syncs, fast_syncs), + PTP_SW_STAT(ptp_bad_syncs, bad_syncs), + PTP_SW_STAT(ptp_sync_timeouts, sync_timeouts), + PTP_SW_STAT(ptp_no_time_syncs, no_time_syncs), + PTP_SW_STAT(ptp_invalid_sync_windows, invalid_sync_windows), + PTP_SW_STAT(ptp_undersize_sync_windows, undersize_sync_windows), + PTP_SW_STAT(ptp_oversize_sync_windows, oversize_sync_windows), + PTP_SW_STAT(ptp_rx_no_timestamp, rx_no_timestamp), + PTP_MC_STAT(ptp_tx_timestamp_packets, TX), + PTP_MC_STAT(ptp_rx_timestamp_packets, RX), + PTP_MC_STAT(ptp_timestamp_packets, TS), + PTP_MC_STAT(ptp_filter_matches, FM), + PTP_MC_STAT(ptp_non_filter_matches, NFM), +}; +#define PTP_STAT_COUNT ARRAY_SIZE(efx_ptp_stat_desc) +static const unsigned long efx_ptp_stat_mask[] = { + [0 ... BITS_TO_LONGS(PTP_STAT_COUNT) - 1] = ~0UL, +}; + +size_t efx_ptp_describe_stats(struct efx_nic *efx, u8 *strings) +{ + if (!efx->ptp_data) + return 0; + + return efx_nic_describe_stats(efx_ptp_stat_desc, PTP_STAT_COUNT, + efx_ptp_stat_mask, strings); +} + +size_t efx_ptp_update_stats(struct efx_nic *efx, u64 *stats) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_STATUS_LEN); + MCDI_DECLARE_BUF(outbuf, MC_CMD_PTP_OUT_STATUS_LEN); + size_t i; + int rc; + + if (!efx->ptp_data) + return 0; + + /* Copy software statistics */ + for (i = 0; i < PTP_STAT_COUNT; i++) { + if (efx_ptp_stat_desc[i].dma_width) + continue; + stats[i] = *(unsigned int *)((char *)efx->ptp_data + + efx_ptp_stat_desc[i].offset); + } + + /* Fetch MC statistics. We *must* fill in all statistics or + * risk leaking kernel memory to userland, so if the MCDI + * request fails we pretend we got zeroes. + */ + MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_STATUS); + MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0); + rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), NULL); + if (rc) { + netif_err(efx, hw, efx->net_dev, + "MC_CMD_PTP_OP_STATUS failed (%d)\n", rc); + memset(outbuf, 0, sizeof(outbuf)); + } + efx_nic_update_stats(efx_ptp_stat_desc, PTP_STAT_COUNT, + efx_ptp_stat_mask, + stats, _MCDI_PTR(outbuf, 0), false); + + return PTP_STAT_COUNT; +} + +/* For Siena platforms NIC time is s and ns */ +static void efx_ptp_ns_to_s_ns(s64 ns, u32 *nic_major, u32 *nic_minor) +{ + struct timespec ts = ns_to_timespec(ns); + *nic_major = ts.tv_sec; + *nic_minor = ts.tv_nsec; +} + +static ktime_t efx_ptp_s_ns_to_ktime_correction(u32 nic_major, u32 nic_minor, + s32 correction) +{ + ktime_t kt = ktime_set(nic_major, nic_minor); + if (correction >= 0) + kt = ktime_add_ns(kt, (u64)correction); + else + kt = ktime_sub_ns(kt, (u64)-correction); + return kt; +} + +/* To convert from s27 format to ns we multiply then divide by a power of 2. + * For the conversion from ns to s27, the operation is also converted to a + * multiply and shift. + */ +#define S27_TO_NS_SHIFT (27) +#define NS_TO_S27_MULT (((1ULL << 63) + NSEC_PER_SEC / 2) / NSEC_PER_SEC) +#define NS_TO_S27_SHIFT (63 - S27_TO_NS_SHIFT) +#define S27_MINOR_MAX (1 << S27_TO_NS_SHIFT) + +/* For Huntington platforms NIC time is in seconds and fractions of a second + * where the minor register only uses 27 bits in units of 2^-27s. + */ +static void efx_ptp_ns_to_s27(s64 ns, u32 *nic_major, u32 *nic_minor) +{ + struct timespec ts = ns_to_timespec(ns); + u32 maj = ts.tv_sec; + u32 min = (u32)(((u64)ts.tv_nsec * NS_TO_S27_MULT + + (1ULL << (NS_TO_S27_SHIFT - 1))) >> NS_TO_S27_SHIFT); + + /* The conversion can result in the minor value exceeding the maximum. + * In this case, round up to the next second. + */ + if (min >= S27_MINOR_MAX) { + min -= S27_MINOR_MAX; + maj++; + } + + *nic_major = maj; + *nic_minor = min; +} + +static inline ktime_t efx_ptp_s27_to_ktime(u32 nic_major, u32 nic_minor) +{ + u32 ns = (u32)(((u64)nic_minor * NSEC_PER_SEC + + (1ULL << (S27_TO_NS_SHIFT - 1))) >> S27_TO_NS_SHIFT); + return ktime_set(nic_major, ns); +} + +static ktime_t efx_ptp_s27_to_ktime_correction(u32 nic_major, u32 nic_minor, + s32 correction) +{ + /* Apply the correction and deal with carry */ + nic_minor += correction; + if ((s32)nic_minor < 0) { + nic_minor += S27_MINOR_MAX; + nic_major--; + } else if (nic_minor >= S27_MINOR_MAX) { + nic_minor -= S27_MINOR_MAX; + nic_major++; + } + + return efx_ptp_s27_to_ktime(nic_major, nic_minor); +} + +/* Get PTP attributes and set up time conversions */ +static int efx_ptp_get_attributes(struct efx_nic *efx) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_GET_ATTRIBUTES_LEN); + MCDI_DECLARE_BUF(outbuf, MC_CMD_PTP_OUT_GET_ATTRIBUTES_LEN); + struct efx_ptp_data *ptp = efx->ptp_data; + int rc; + u32 fmt; + size_t out_len; + + /* Get the PTP attributes. If the NIC doesn't support the operation we + * use the default format for compatibility with older NICs i.e. + * seconds and nanoseconds. + */ + MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_GET_ATTRIBUTES); + MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0); + rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), &out_len); + if (rc == 0) + fmt = MCDI_DWORD(outbuf, PTP_OUT_GET_ATTRIBUTES_TIME_FORMAT); + else if (rc == -EINVAL) + fmt = MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS; + else + return rc; + + if (fmt == MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_27FRACTION) { + ptp->ns_to_nic_time = efx_ptp_ns_to_s27; + ptp->nic_to_kernel_time = efx_ptp_s27_to_ktime_correction; + } else if (fmt == MC_CMD_PTP_OUT_GET_ATTRIBUTES_SECONDS_NANOSECONDS) { + ptp->ns_to_nic_time = efx_ptp_ns_to_s_ns; + ptp->nic_to_kernel_time = efx_ptp_s_ns_to_ktime_correction; + } else { + return -ERANGE; + } + + ptp->time_format = fmt; + + /* MC_CMD_PTP_OP_GET_ATTRIBUTES is an extended version of an older + * operation MC_CMD_PTP_OP_GET_TIME_FORMAT that also returns a value + * to use for the minimum acceptable corrected synchronization window. + * If we have the extra information store it. For older firmware that + * does not implement the extended command use the default value. + */ + if (rc == 0 && out_len >= MC_CMD_PTP_OUT_GET_ATTRIBUTES_LEN) + ptp->min_synchronisation_ns = + MCDI_DWORD(outbuf, + PTP_OUT_GET_ATTRIBUTES_SYNC_WINDOW_MIN); + else + ptp->min_synchronisation_ns = DEFAULT_MIN_SYNCHRONISATION_NS; + + return 0; +} + +/* Get PTP timestamp corrections */ +static int efx_ptp_get_timestamp_corrections(struct efx_nic *efx) +{ + MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_GET_TIMESTAMP_CORRECTIONS_LEN); + MCDI_DECLARE_BUF(outbuf, MC_CMD_PTP_OUT_GET_TIMESTAMP_CORRECTIONS_LEN); + int rc; + + /* Get the timestamp corrections from the NIC. If this operation is + * not supported (older NICs) then no correction is required. + */ + MCDI_SET_DWORD(inbuf, PTP_IN_OP, + MC_CMD_PTP_OP_GET_TIMESTAMP_CORRECTIONS); + MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0); + + rc = efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), NULL); + if (rc == 0) { + efx->ptp_data->ts_corrections.tx = MCDI_DWORD(outbuf, + PTP_OUT_GET_TIMESTAMP_CORRECTIONS_TRANSMIT); + efx->ptp_data->ts_corrections.rx = MCDI_DWORD(outbuf, + PTP_OUT_GET_TIMESTAMP_CORRECTIONS_RECEIVE); + efx->ptp_data->ts_corrections.pps_out = MCDI_DWORD(outbuf, + PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_OUT); + efx->ptp_data->ts_corrections.pps_in = MCDI_DWORD(outbuf, + PTP_OUT_GET_TIMESTAMP_CORRECTIONS_PPS_IN); + } else if (rc == -EINVAL) { + efx->ptp_data->ts_corrections.tx = 0; + efx->ptp_data->ts_corrections.rx = 0; + efx->ptp_data->ts_corrections.pps_out = 0; + efx->ptp_data->ts_corrections.pps_in = 0; + } else { + return rc; + } + + return 0; +} + /* Enable MCDI PTP support. */ static int efx_ptp_enable(struct efx_nic *efx) { MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_ENABLE_LEN); + MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, 0); + int rc; MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ENABLE); MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0); MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_QUEUE, - efx->ptp_data->channel->channel); + efx->ptp_data->channel ? + efx->ptp_data->channel->channel : 0); MCDI_SET_DWORD(inbuf, PTP_IN_ENABLE_MODE, efx->ptp_data->mode); - return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), - NULL, 0, NULL); + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), NULL); + rc = (rc == -EALREADY) ? 0 : rc; + if (rc) + efx_mcdi_display_error(efx, MC_CMD_PTP, + MC_CMD_PTP_IN_ENABLE_LEN, + outbuf, sizeof(outbuf), rc); + return rc; } /* Disable MCDI PTP support. @@ -330,11 +596,19 @@ static int efx_ptp_enable(struct efx_nic *efx) static int efx_ptp_disable(struct efx_nic *efx) { MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_DISABLE_LEN); + MCDI_DECLARE_BUF_OUT_OR_ERR(outbuf, 0); + int rc; MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_DISABLE); MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0); - return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), - NULL, 0, NULL); + rc = efx_mcdi_rpc_quiet(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), + outbuf, sizeof(outbuf), NULL); + rc = (rc == -EALREADY) ? 0 : rc; + if (rc) + efx_mcdi_display_error(efx, MC_CMD_PTP, + MC_CMD_PTP_IN_DISABLE_LEN, + outbuf, sizeof(outbuf), rc); + return rc; } static void efx_ptp_deliver_rx_queue(struct sk_buff_head *q) @@ -402,11 +676,10 @@ static void efx_ptp_read_timeset(MCDI_DECLARE_STRUCT_PTR(data), unsigned start_ns, end_ns; timeset->host_start = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTSTART); - timeset->seconds = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_SECONDS); - timeset->nanoseconds = MCDI_DWORD(data, - PTP_OUT_SYNCHRONIZE_NANOSECONDS); + timeset->major = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_MAJOR); + timeset->minor = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_MINOR); timeset->host_end = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_HOSTEND), - timeset->waitns = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_WAITNS); + timeset->wait = MCDI_DWORD(data, PTP_OUT_SYNCHRONIZE_WAITNS); /* Ignore seconds */ start_ns = timeset->host_start & MC_NANOSECOND_MASK; @@ -435,84 +708,94 @@ efx_ptp_process_times(struct efx_nic *efx, MCDI_DECLARE_STRUCT_PTR(synch_buf), MCDI_VAR_ARRAY_LEN(response_length, PTP_OUT_SYNCHRONIZE_TIMESET); unsigned i; - unsigned total; unsigned ngood = 0; unsigned last_good = 0; struct efx_ptp_data *ptp = efx->ptp_data; u32 last_sec; u32 start_sec; struct timespec delta; + ktime_t mc_time; if (number_readings == 0) return -EAGAIN; - /* Read the set of results and increment stats for any results that - * appera to be erroneous. + /* Read the set of results and find the last good host-MC + * synchronization result. The MC times when it finishes reading the + * host time so the corrected window time should be fairly constant + * for a given platform. Increment stats for any results that appear + * to be erroneous. */ for (i = 0; i < number_readings; i++) { + s32 window, corrected; + struct timespec wait; + efx_ptp_read_timeset( MCDI_ARRAY_STRUCT_PTR(synch_buf, PTP_OUT_SYNCHRONIZE_TIMESET, i), &ptp->timeset[i]); - } - /* Find the last good host-MC synchronization result. The MC times - * when it finishes reading the host time so the corrected window time - * should be fairly constant for a given platform. - */ - total = 0; - for (i = 0; i < number_readings; i++) - if (ptp->timeset[i].window > ptp->timeset[i].waitns) { - unsigned win; - - win = ptp->timeset[i].window - ptp->timeset[i].waitns; - if (win >= MIN_SYNCHRONISATION_NS && - win < MAX_SYNCHRONISATION_NS) { - total += ptp->timeset[i].window; - ngood++; - last_good = i; - } + wait = ktime_to_timespec( + ptp->nic_to_kernel_time(0, ptp->timeset[i].wait, 0)); + window = ptp->timeset[i].window; + corrected = window - wait.tv_nsec; + + /* We expect the uncorrected synchronization window to be at + * least as large as the interval between host start and end + * times. If it is smaller than this then this is mostly likely + * to be a consequence of the host's time being adjusted. + * Check that the corrected sync window is in a reasonable + * range. If it is out of range it is likely to be because an + * interrupt or other delay occurred between reading the system + * time and writing it to MC memory. + */ + if (window < SYNCHRONISATION_GRANULARITY_NS) { + ++ptp->invalid_sync_windows; + } else if (corrected >= MAX_SYNCHRONISATION_NS) { + ++ptp->oversize_sync_windows; + } else if (corrected < ptp->min_synchronisation_ns) { + ++ptp->undersize_sync_windows; + } else { + ngood++; + last_good = i; } + } if (ngood == 0) { netif_warn(efx, drv, efx->net_dev, - "PTP no suitable synchronisations %dns\n", - ptp->base_sync_ns); + "PTP no suitable synchronisations\n"); return -EAGAIN; } - /* Average minimum this synchronisation */ - ptp->last_sync_ns = DIV_ROUND_UP(total, ngood); - if (!ptp->base_sync_valid || (ptp->last_sync_ns < ptp->base_sync_ns)) { - ptp->base_sync_valid = true; - ptp->base_sync_ns = ptp->last_sync_ns; - } - - /* Calculate delay from actual PPS to last_time */ - delta.tv_nsec = - ptp->timeset[last_good].nanoseconds + - last_time->ts_real.tv_nsec - - (ptp->timeset[last_good].host_start & MC_NANOSECOND_MASK); - - /* It is possible that the seconds rolled over between taking + /* Calculate delay from last good sync (host time) to last_time. + * It is possible that the seconds rolled over between taking * the start reading and the last value written by the host. The * timescales are such that a gap of more than one second is never - * expected. + * expected. delta is *not* normalised. */ start_sec = ptp->timeset[last_good].host_start >> MC_NANOSECOND_BITS; last_sec = last_time->ts_real.tv_sec & MC_SECOND_MASK; - if (start_sec != last_sec) { - if (((start_sec + 1) & MC_SECOND_MASK) != last_sec) { - netif_warn(efx, hw, efx->net_dev, - "PTP bad synchronisation seconds\n"); - return -EAGAIN; - } else { - delta.tv_sec = 1; - } - } else { - delta.tv_sec = 0; + if (start_sec != last_sec && + ((start_sec + 1) & MC_SECOND_MASK) != last_sec) { + netif_warn(efx, hw, efx->net_dev, + "PTP bad synchronisation seconds\n"); + return -EAGAIN; } + delta.tv_sec = (last_sec - start_sec) & 1; + delta.tv_nsec = + last_time->ts_real.tv_nsec - + (ptp->timeset[last_good].host_start & MC_NANOSECOND_MASK); + + /* Convert the NIC time at last good sync into kernel time. + * No correction is required - this time is the output of a + * firmware process. + */ + mc_time = ptp->nic_to_kernel_time(ptp->timeset[last_good].major, + ptp->timeset[last_good].minor, 0); + + /* Calculate delay from NIC top of second to last_time */ + delta.tv_nsec += ktime_to_timespec(mc_time).tv_nsec; + /* Set PPS timestamp to match NIC top of second */ ptp->host_time_pps = *last_time; pps_sub_ts(&ptp->host_time_pps, delta); @@ -551,6 +834,11 @@ static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings) loops++; } + if (loops <= 1) + ++ptp->fast_syncs; + if (!time_before(jiffies, timeout)) + ++ptp->sync_timeouts; + if (ACCESS_ONCE(*start)) efx_ptp_send_times(efx, &last_time); @@ -559,9 +847,20 @@ static int efx_ptp_synchronize(struct efx_nic *efx, unsigned int num_readings) MC_CMD_PTP_IN_SYNCHRONIZE_LEN, synch_buf, sizeof(synch_buf), &response_length); - if (rc == 0) + if (rc == 0) { rc = efx_ptp_process_times(efx, synch_buf, response_length, &last_time); + if (rc == 0) + ++ptp->good_syncs; + else + ++ptp->no_time_syncs; + } + + /* Increment the bad syncs counter if the synchronize fails, whatever + * the reason. + */ + if (rc != 0) + ++ptp->bad_syncs; return rc; } @@ -600,9 +899,10 @@ static int efx_ptp_xmit_skb(struct efx_nic *efx, struct sk_buff *skb) goto fail; memset(×tamps, 0, sizeof(timestamps)); - timestamps.hwtstamp = ktime_set( - MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_SECONDS), - MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_NANOSECONDS)); + timestamps.hwtstamp = ptp_data->nic_to_kernel_time( + MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_MAJOR), + MCDI_DWORD(txtime, PTP_OUT_TRANSMIT_MINOR), + ptp_data->ts_corrections.tx); skb_tstamp_tx(skb, ×tamps); @@ -620,6 +920,9 @@ static void efx_ptp_drop_time_expired_events(struct efx_nic *efx) struct list_head *cursor; struct list_head *next; + if (ptp->rx_ts_inline) + return; + /* Drop time-expired events */ spin_lock_bh(&ptp->evt_lock); if (!list_empty(&ptp->evt_list)) { @@ -648,6 +951,8 @@ static enum ptp_packet_state efx_ptp_match_rx(struct efx_nic *efx, struct efx_ptp_match *match; enum ptp_packet_state rc = PTP_PACKET_STATE_UNMATCHED; + WARN_ON_ONCE(ptp->rx_ts_inline); + spin_lock_bh(&ptp->evt_lock); evts_waiting = !list_empty(&ptp->evt_list); spin_unlock_bh(&ptp->evt_lock); @@ -684,13 +989,10 @@ static enum ptp_packet_state efx_ptp_match_rx(struct efx_nic *efx, /* Process any queued receive events and corresponding packets * * q is returned with all the packets that are ready for delivery. - * true is returned if at least one of those packets requires - * synchronisation. */ -static bool efx_ptp_process_events(struct efx_nic *efx, struct sk_buff_head *q) +static void efx_ptp_process_events(struct efx_nic *efx, struct sk_buff_head *q) { struct efx_ptp_data *ptp = efx->ptp_data; - bool rc = false; struct sk_buff *skb; while ((skb = skb_dequeue(&ptp->rxq))) { @@ -701,12 +1003,10 @@ static bool efx_ptp_process_events(struct efx_nic *efx, struct sk_buff_head *q) __skb_queue_tail(q, skb); } else if (efx_ptp_match_rx(efx, skb) == PTP_PACKET_STATE_MATCHED) { - rc = true; __skb_queue_tail(q, skb); } else if (time_after(jiffies, match->expiry)) { match->state = PTP_PACKET_STATE_TIMED_OUT; - netif_warn(efx, rx_err, efx->net_dev, - "PTP packet - no timestamp seen\n"); + ++ptp->rx_no_timestamp; __skb_queue_tail(q, skb); } else { /* Replace unprocessed entry and stop */ @@ -714,8 +1014,6 @@ static bool efx_ptp_process_events(struct efx_nic *efx, struct sk_buff_head *q) break; } } - - return rc; } /* Complete processing of a received packet */ @@ -726,13 +1024,27 @@ static inline void efx_ptp_process_rx(struct efx_nic *efx, struct sk_buff *skb) local_bh_enable(); } -static int efx_ptp_start(struct efx_nic *efx) +static void efx_ptp_remove_multicast_filters(struct efx_nic *efx) +{ + struct efx_ptp_data *ptp = efx->ptp_data; + + if (ptp->rxfilter_installed) { + efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED, + ptp->rxfilter_general); + efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED, + ptp->rxfilter_event); + ptp->rxfilter_installed = false; + } +} + +static int efx_ptp_insert_multicast_filters(struct efx_nic *efx) { struct efx_ptp_data *ptp = efx->ptp_data; struct efx_filter_spec rxfilter; int rc; - ptp->reset_required = false; + if (!ptp->channel || ptp->rxfilter_installed) + return 0; /* Must filter on both event and general ports to ensure * that there is no packet re-ordering. @@ -765,40 +1077,53 @@ static int efx_ptp_start(struct efx_nic *efx) goto fail; ptp->rxfilter_general = rc; + ptp->rxfilter_installed = true; + return 0; + +fail: + efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED, + ptp->rxfilter_event); + return rc; +} + +static int efx_ptp_start(struct efx_nic *efx) +{ + struct efx_ptp_data *ptp = efx->ptp_data; + int rc; + + ptp->reset_required = false; + + rc = efx_ptp_insert_multicast_filters(efx); + if (rc) + return rc; + rc = efx_ptp_enable(efx); if (rc != 0) - goto fail2; + goto fail; ptp->evt_frag_idx = 0; ptp->current_adjfreq = 0; - ptp->rxfilter_installed = true; return 0; -fail2: - efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED, - ptp->rxfilter_general); fail: - efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED, - ptp->rxfilter_event); - + efx_ptp_remove_multicast_filters(efx); return rc; } static int efx_ptp_stop(struct efx_nic *efx) { struct efx_ptp_data *ptp = efx->ptp_data; - int rc = efx_ptp_disable(efx); struct list_head *cursor; struct list_head *next; + int rc; - if (ptp->rxfilter_installed) { - efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED, - ptp->rxfilter_general); - efx_filter_remove_id_safe(efx, EFX_FILTER_PRI_REQUIRED, - ptp->rxfilter_event); - ptp->rxfilter_installed = false; - } + if (ptp == NULL) + return 0; + + rc = efx_ptp_disable(efx); + + efx_ptp_remove_multicast_filters(efx); /* Make sure RX packets are really delivered */ efx_ptp_deliver_rx_queue(&efx->ptp_data->rxq); @@ -814,11 +1139,18 @@ static int efx_ptp_stop(struct efx_nic *efx) return rc; } +static int efx_ptp_restart(struct efx_nic *efx) +{ + if (efx->ptp_data && efx->ptp_data->enabled) + return efx_ptp_start(efx); + return 0; +} + static void efx_ptp_pps_worker(struct work_struct *work) { struct efx_ptp_data *ptp = container_of(work, struct efx_ptp_data, pps_work); - struct efx_nic *efx = ptp->channel->efx; + struct efx_nic *efx = ptp->efx; struct ptp_clock_event ptp_evt; if (efx_ptp_synchronize(efx, PTP_SYNC_ATTEMPTS)) @@ -829,13 +1161,11 @@ static void efx_ptp_pps_worker(struct work_struct *work) ptp_clock_event(ptp->phc_clock, &ptp_evt); } -/* Process any pending transmissions and timestamp any received packets. - */ static void efx_ptp_worker(struct work_struct *work) { struct efx_ptp_data *ptp_data = container_of(work, struct efx_ptp_data, work); - struct efx_nic *efx = ptp_data->channel->efx; + struct efx_nic *efx = ptp_data->efx; struct sk_buff *skb; struct sk_buff_head tempq; @@ -848,42 +1178,51 @@ static void efx_ptp_worker(struct work_struct *work) efx_ptp_drop_time_expired_events(efx); __skb_queue_head_init(&tempq); - if (efx_ptp_process_events(efx, &tempq) || - !skb_queue_empty(&ptp_data->txq)) { + efx_ptp_process_events(efx, &tempq); - while ((skb = skb_dequeue(&ptp_data->txq))) - efx_ptp_xmit_skb(efx, skb); - } + while ((skb = skb_dequeue(&ptp_data->txq))) + efx_ptp_xmit_skb(efx, skb); while ((skb = __skb_dequeue(&tempq))) efx_ptp_process_rx(efx, skb); } -/* Initialise PTP channel and state. - * - * Setting core_index to zero causes the queue to be initialised and doesn't - * overlap with 'rxq0' because ptp.c doesn't use skb_record_rx_queue. - */ -static int efx_ptp_probe_channel(struct efx_channel *channel) +static const struct ptp_clock_info efx_phc_clock_info = { + .owner = THIS_MODULE, + .name = "sfc", + .max_adj = MAX_PPB, + .n_alarm = 0, + .n_ext_ts = 0, + .n_per_out = 0, + .n_pins = 0, + .pps = 1, + .adjfreq = efx_phc_adjfreq, + .adjtime = efx_phc_adjtime, + .gettime = efx_phc_gettime, + .settime = efx_phc_settime, + .enable = efx_phc_enable, +}; + +/* Initialise PTP state. */ +int efx_ptp_probe(struct efx_nic *efx, struct efx_channel *channel) { - struct efx_nic *efx = channel->efx; struct efx_ptp_data *ptp; int rc = 0; unsigned int pos; - channel->irq_moderation = 0; - channel->rx_queue.core_index = 0; - ptp = kzalloc(sizeof(struct efx_ptp_data), GFP_KERNEL); efx->ptp_data = ptp; if (!efx->ptp_data) return -ENOMEM; + ptp->efx = efx; + ptp->channel = channel; + ptp->rx_ts_inline = efx_nic_rev(efx) >= EFX_REV_HUNT_A0; + rc = efx_nic_alloc_buffer(efx, &ptp->start, sizeof(int), GFP_KERNEL); if (rc != 0) goto fail1; - ptp->channel = channel; skb_queue_head_init(&ptp->rxq); skb_queue_head_init(&ptp->txq); ptp->workwq = create_singlethread_workqueue("sfc_ptp"); @@ -902,33 +1241,32 @@ static int efx_ptp_probe_channel(struct efx_channel *channel) for (pos = 0; pos < MAX_RECEIVE_EVENTS; pos++) list_add(&ptp->rx_evts[pos].link, &ptp->evt_free_list); - ptp->phc_clock_info.owner = THIS_MODULE; - snprintf(ptp->phc_clock_info.name, - sizeof(ptp->phc_clock_info.name), - "%pm", efx->net_dev->perm_addr); - ptp->phc_clock_info.max_adj = MAX_PPB; - ptp->phc_clock_info.n_alarm = 0; - ptp->phc_clock_info.n_ext_ts = 0; - ptp->phc_clock_info.n_per_out = 0; - ptp->phc_clock_info.pps = 1; - ptp->phc_clock_info.adjfreq = efx_phc_adjfreq; - ptp->phc_clock_info.adjtime = efx_phc_adjtime; - ptp->phc_clock_info.gettime = efx_phc_gettime; - ptp->phc_clock_info.settime = efx_phc_settime; - ptp->phc_clock_info.enable = efx_phc_enable; - - ptp->phc_clock = ptp_clock_register(&ptp->phc_clock_info, - &efx->pci_dev->dev); - if (IS_ERR(ptp->phc_clock)) { - rc = PTR_ERR(ptp->phc_clock); + /* Get the NIC PTP attributes and set up time conversions */ + rc = efx_ptp_get_attributes(efx); + if (rc < 0) goto fail3; - } - INIT_WORK(&ptp->pps_work, efx_ptp_pps_worker); - ptp->pps_workwq = create_singlethread_workqueue("sfc_pps"); - if (!ptp->pps_workwq) { - rc = -ENOMEM; - goto fail4; + /* Get the timestamp corrections */ + rc = efx_ptp_get_timestamp_corrections(efx); + if (rc < 0) + goto fail3; + + if (efx->mcdi->fn_flags & + (1 << MC_CMD_DRV_ATTACH_EXT_OUT_FLAG_PRIMARY)) { + ptp->phc_clock_info = efx_phc_clock_info; + ptp->phc_clock = ptp_clock_register(&ptp->phc_clock_info, + &efx->pci_dev->dev); + if (IS_ERR(ptp->phc_clock)) { + rc = PTR_ERR(ptp->phc_clock); + goto fail3; + } + + INIT_WORK(&ptp->pps_work, efx_ptp_pps_worker); + ptp->pps_workwq = create_singlethread_workqueue("sfc_pps"); + if (!ptp->pps_workwq) { + rc = -ENOMEM; + goto fail4; + } } ptp->nic_ts_enabled = false; @@ -949,14 +1287,27 @@ fail1: return rc; } -static void efx_ptp_remove_channel(struct efx_channel *channel) +/* Initialise PTP channel. + * + * Setting core_index to zero causes the queue to be initialised and doesn't + * overlap with 'rxq0' because ptp.c doesn't use skb_record_rx_queue. + */ +static int efx_ptp_probe_channel(struct efx_channel *channel) { struct efx_nic *efx = channel->efx; + channel->irq_moderation = 0; + channel->rx_queue.core_index = 0; + + return efx_ptp_probe(efx, channel); +} + +void efx_ptp_remove(struct efx_nic *efx) +{ if (!efx->ptp_data) return; - (void)efx_ptp_disable(channel->efx); + (void)efx_ptp_disable(efx); cancel_work_sync(&efx->ptp_data->work); cancel_work_sync(&efx->ptp_data->pps_work); @@ -964,15 +1315,22 @@ static void efx_ptp_remove_channel(struct efx_channel *channel) skb_queue_purge(&efx->ptp_data->rxq); skb_queue_purge(&efx->ptp_data->txq); - ptp_clock_unregister(efx->ptp_data->phc_clock); + if (efx->ptp_data->phc_clock) { + destroy_workqueue(efx->ptp_data->pps_workwq); + ptp_clock_unregister(efx->ptp_data->phc_clock); + } destroy_workqueue(efx->ptp_data->workwq); - destroy_workqueue(efx->ptp_data->pps_workwq); efx_nic_free_buffer(efx, &efx->ptp_data->start); kfree(efx->ptp_data); } +static void efx_ptp_remove_channel(struct efx_channel *channel) +{ + efx_ptp_remove(channel->efx); +} + static void efx_ptp_get_channel_name(struct efx_channel *channel, char *buf, size_t len) { @@ -989,7 +1347,11 @@ bool efx_ptp_is_ptp_tx(struct efx_nic *efx, struct sk_buff *skb) skb->len >= PTP_MIN_LENGTH && skb->len <= MC_CMD_PTP_IN_TRANSMIT_PACKET_MAXNUM && likely(skb->protocol == htons(ETH_P_IP)) && + skb_transport_header_was_set(skb) && + skb_network_header_len(skb) >= sizeof(struct iphdr) && ip_hdr(skb)->protocol == IPPROTO_UDP && + skb_headlen(skb) >= + skb_transport_offset(skb) + sizeof(struct udphdr) && udp_hdr(skb)->dest == htons(PTP_EVENT_PORT); } @@ -1004,6 +1366,7 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb) struct efx_ptp_match *match = (struct efx_ptp_match *)skb->cb; u8 *match_data_012, *match_data_345; unsigned int version; + u8 *data; match->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS); @@ -1012,7 +1375,8 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb) if (!pskb_may_pull(skb, PTP_V1_MIN_LENGTH)) { return false; } - version = ntohs(*(__be16 *)&skb->data[PTP_V1_VERSION_OFFSET]); + data = skb->data; + version = ntohs(*(__be16 *)&data[PTP_V1_VERSION_OFFSET]); if (version != PTP_VERSION_V1) { return false; } @@ -1020,13 +1384,14 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb) /* PTP V1 uses all six bytes of the UUID to match the packet * to the timestamp */ - match_data_012 = skb->data + PTP_V1_UUID_OFFSET; - match_data_345 = skb->data + PTP_V1_UUID_OFFSET + 3; + match_data_012 = data + PTP_V1_UUID_OFFSET; + match_data_345 = data + PTP_V1_UUID_OFFSET + 3; } else { if (!pskb_may_pull(skb, PTP_V2_MIN_LENGTH)) { return false; } - version = skb->data[PTP_V2_VERSION_OFFSET]; + data = skb->data; + version = data[PTP_V2_VERSION_OFFSET]; if ((version & PTP_VERSION_V2_MASK) != PTP_VERSION_V2) { return false; } @@ -1038,25 +1403,19 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb) * enhanced mode fixes this issue and uses bytes 0-2 * and byte 5-7 of the UUID. */ - match_data_345 = skb->data + PTP_V2_UUID_OFFSET + 5; + match_data_345 = data + PTP_V2_UUID_OFFSET + 5; if (ptp->mode == MC_CMD_PTP_MODE_V2) { - match_data_012 = skb->data + PTP_V2_UUID_OFFSET + 2; + match_data_012 = data + PTP_V2_UUID_OFFSET + 2; } else { - match_data_012 = skb->data + PTP_V2_UUID_OFFSET + 0; + match_data_012 = data + PTP_V2_UUID_OFFSET + 0; BUG_ON(ptp->mode != MC_CMD_PTP_MODE_V2_ENHANCED); } } /* Does this packet require timestamping? */ - if (ntohs(*(__be16 *)&skb->data[PTP_DPORT_OFFSET]) == PTP_EVENT_PORT) { - struct skb_shared_hwtstamps *timestamps; - + if (ntohs(*(__be16 *)&data[PTP_DPORT_OFFSET]) == PTP_EVENT_PORT) { match->state = PTP_PACKET_STATE_UNMATCHED; - /* Clear all timestamps held: filled in later */ - timestamps = skb_hwtstamps(skb); - memset(timestamps, 0, sizeof(*timestamps)); - /* We expect the sequence number to be in the same position in * the packet for PTP V1 and V2 */ @@ -1070,8 +1429,8 @@ static bool efx_ptp_rx(struct efx_channel *channel, struct sk_buff *skb) (match_data_345[0] << 24)); match->words[1] = (match_data_345[1] | (match_data_345[2] << 8) | - (skb->data[PTP_V1_SEQUENCE_OFFSET + - PTP_V1_SEQUENCE_LENGTH - 1] << + (data[PTP_V1_SEQUENCE_OFFSET + + PTP_V1_SEQUENCE_LENGTH - 1] << 16)); } else { match->state = PTP_PACKET_STATE_MATCH_UNWANTED; @@ -1101,12 +1460,17 @@ int efx_ptp_tx(struct efx_nic *efx, struct sk_buff *skb) return NETDEV_TX_OK; } -static int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted, - unsigned int new_mode) +int efx_ptp_get_mode(struct efx_nic *efx) +{ + return efx->ptp_data->mode; +} + +int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted, + unsigned int new_mode) { if ((enable_wanted != efx->ptp_data->enabled) || (enable_wanted && (efx->ptp_data->mode != new_mode))) { - int rc; + int rc = 0; if (enable_wanted) { /* Change of mode requires disable */ @@ -1123,7 +1487,8 @@ static int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted, * succeed. */ efx->ptp_data->mode = new_mode; - rc = efx_ptp_start(efx); + if (netif_running(efx->net_dev)) + rc = efx_ptp_start(efx); if (rc == 0) { rc = efx_ptp_synchronize(efx, PTP_SYNC_ATTEMPTS * 2); @@ -1145,8 +1510,6 @@ static int efx_ptp_change_mode(struct efx_nic *efx, bool enable_wanted, static int efx_ptp_ts_init(struct efx_nic *efx, struct hwtstamp_config *init) { - bool enable_wanted = false; - unsigned int new_mode; int rc; if (init->flags) @@ -1156,63 +1519,20 @@ static int efx_ptp_ts_init(struct efx_nic *efx, struct hwtstamp_config *init) (init->tx_type != HWTSTAMP_TX_ON)) return -ERANGE; - new_mode = efx->ptp_data->mode; - /* Determine whether any PTP HW operations are required */ - switch (init->rx_filter) { - case HWTSTAMP_FILTER_NONE: - break; - case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: - init->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; - new_mode = MC_CMD_PTP_MODE_V1; - enable_wanted = true; - break; - case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: - /* Although these three are accepted only IPV4 packets will be - * timestamped - */ - init->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; - new_mode = MC_CMD_PTP_MODE_V2_ENHANCED; - enable_wanted = true; - break; - case HWTSTAMP_FILTER_PTP_V2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ: - case HWTSTAMP_FILTER_PTP_V2_L2_EVENT: - case HWTSTAMP_FILTER_PTP_V2_L2_SYNC: - case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ: - /* Non-IP + IPv6 timestamping not supported */ - return -ERANGE; - break; - default: - return -ERANGE; - } - - if (init->tx_type != HWTSTAMP_TX_OFF) - enable_wanted = true; - - /* Old versions of the firmware do not support the improved - * UUID filtering option (SF bug 33070). If the firmware does - * not accept the enhanced mode, fall back to the standard PTP - * v2 UUID filtering. - */ - rc = efx_ptp_change_mode(efx, enable_wanted, new_mode); - if ((rc != 0) && (new_mode == MC_CMD_PTP_MODE_V2_ENHANCED)) - rc = efx_ptp_change_mode(efx, enable_wanted, MC_CMD_PTP_MODE_V2); - if (rc != 0) + rc = efx->type->ptp_set_ts_config(efx, init); + if (rc) return rc; efx->ptp_data->config = *init; - return 0; } void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info) { struct efx_ptp_data *ptp = efx->ptp_data; + struct efx_nic *primary = efx->primary; + + ASSERT_RTNL(); if (!ptp) return; @@ -1220,18 +1540,14 @@ void efx_ptp_get_ts_info(struct efx_nic *efx, struct ethtool_ts_info *ts_info) ts_info->so_timestamping |= (SOF_TIMESTAMPING_TX_HARDWARE | SOF_TIMESTAMPING_RX_HARDWARE | SOF_TIMESTAMPING_RAW_HARDWARE); - ts_info->phc_index = ptp_clock_index(ptp->phc_clock); + if (primary && primary->ptp_data && primary->ptp_data->phc_clock) + ts_info->phc_index = + ptp_clock_index(primary->ptp_data->phc_clock); ts_info->tx_types = 1 << HWTSTAMP_TX_OFF | 1 << HWTSTAMP_TX_ON; - ts_info->rx_filters = (1 << HWTSTAMP_FILTER_NONE | - 1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT | - 1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC | - 1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ | - 1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT | - 1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC | - 1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ); + ts_info->rx_filters = ptp->efx->type->hwtstamp_filters; } -int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd) +int efx_ptp_set_ts_config(struct efx_nic *efx, struct ifreq *ifr) { struct hwtstamp_config config; int rc; @@ -1251,6 +1567,15 @@ int efx_ptp_ioctl(struct efx_nic *efx, struct ifreq *ifr, int cmd) ? -EFAULT : 0; } +int efx_ptp_get_ts_config(struct efx_nic *efx, struct ifreq *ifr) +{ + if (!efx->ptp_data) + return -EOPNOTSUPP; + + return copy_to_user(ifr->ifr_data, &efx->ptp_data->config, + sizeof(efx->ptp_data->config)) ? -EFAULT : 0; +} + static void ptp_event_failure(struct efx_nic *efx, int expected_frag_len) { struct efx_ptp_data *ptp = efx->ptp_data; @@ -1270,6 +1595,9 @@ static void ptp_event_rx(struct efx_nic *efx, struct efx_ptp_data *ptp) { struct efx_ptp_event_rx *evt = NULL; + if (WARN_ON_ONCE(ptp->rx_ts_inline)) + return; + if (ptp->evt_frag_idx != 3) { ptp_event_failure(efx, 3); return; @@ -1288,15 +1616,17 @@ static void ptp_event_rx(struct efx_nic *efx, struct efx_ptp_data *ptp) MCDI_EVENT_SRC) << 8) | (EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_SRC) << 16)); - evt->hwtimestamp = ktime_set( + evt->hwtimestamp = efx->ptp_data->nic_to_kernel_time( EFX_QWORD_FIELD(ptp->evt_frags[0], MCDI_EVENT_DATA), - EFX_QWORD_FIELD(ptp->evt_frags[1], MCDI_EVENT_DATA)); + EFX_QWORD_FIELD(ptp->evt_frags[1], MCDI_EVENT_DATA), + ptp->ts_corrections.rx); evt->expiry = jiffies + msecs_to_jiffies(PKT_EVENT_LIFETIME_MS); list_add_tail(&evt->link, &ptp->evt_list); queue_work(ptp->workwq, &ptp->work); - } else { - netif_err(efx, rx_err, efx->net_dev, "No free PTP event"); + } else if (net_ratelimit()) { + /* Log a rate-limited warning message. */ + netif_err(efx, rx_err, efx->net_dev, "PTP event queue overflow\n"); } spin_unlock_bh(&ptp->evt_lock); } @@ -1323,6 +1653,13 @@ void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev) struct efx_ptp_data *ptp = efx->ptp_data; int code = EFX_QWORD_FIELD(*ev, MCDI_EVENT_CODE); + if (!ptp) { + if (net_ratelimit()) + netif_warn(efx, drv, efx->net_dev, + "Received PTP event but PTP not set up\n"); + return; + } + if (!ptp->enabled) return; @@ -1360,12 +1697,99 @@ void efx_ptp_event(struct efx_nic *efx, efx_qword_t *ev) } } +void efx_time_sync_event(struct efx_channel *channel, efx_qword_t *ev) +{ + channel->sync_timestamp_major = MCDI_EVENT_FIELD(*ev, PTP_TIME_MAJOR); + channel->sync_timestamp_minor = + MCDI_EVENT_FIELD(*ev, PTP_TIME_MINOR_26_19) << 19; + /* if sync events have been disabled then we want to silently ignore + * this event, so throw away result. + */ + (void) cmpxchg(&channel->sync_events_state, SYNC_EVENTS_REQUESTED, + SYNC_EVENTS_VALID); +} + +/* make some assumptions about the time representation rather than abstract it, + * since we currently only support one type of inline timestamping and only on + * EF10. + */ +#define MINOR_TICKS_PER_SECOND 0x8000000 +/* Fuzz factor for sync events to be out of order with RX events */ +#define FUZZ (MINOR_TICKS_PER_SECOND / 10) +#define EXPECTED_SYNC_EVENTS_PER_SECOND 4 + +static inline u32 efx_rx_buf_timestamp_minor(struct efx_nic *efx, const u8 *eh) +{ +#if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) + return __le32_to_cpup((const __le32 *)(eh + efx->rx_packet_ts_offset)); +#else + const u8 *data = eh + efx->rx_packet_ts_offset; + return (u32)data[0] | + (u32)data[1] << 8 | + (u32)data[2] << 16 | + (u32)data[3] << 24; +#endif +} + +void __efx_rx_skb_attach_timestamp(struct efx_channel *channel, + struct sk_buff *skb) +{ + struct efx_nic *efx = channel->efx; + u32 pkt_timestamp_major, pkt_timestamp_minor; + u32 diff, carry; + struct skb_shared_hwtstamps *timestamps; + + pkt_timestamp_minor = (efx_rx_buf_timestamp_minor(efx, + skb_mac_header(skb)) + + (u32) efx->ptp_data->ts_corrections.rx) & + (MINOR_TICKS_PER_SECOND - 1); + + /* get the difference between the packet and sync timestamps, + * modulo one second + */ + diff = (pkt_timestamp_minor - channel->sync_timestamp_minor) & + (MINOR_TICKS_PER_SECOND - 1); + /* do we roll over a second boundary and need to carry the one? */ + carry = channel->sync_timestamp_minor + diff > MINOR_TICKS_PER_SECOND ? + 1 : 0; + + if (diff <= MINOR_TICKS_PER_SECOND / EXPECTED_SYNC_EVENTS_PER_SECOND + + FUZZ) { + /* packet is ahead of the sync event by a quarter of a second or + * less (allowing for fuzz) + */ + pkt_timestamp_major = channel->sync_timestamp_major + carry; + } else if (diff >= MINOR_TICKS_PER_SECOND - FUZZ) { + /* packet is behind the sync event but within the fuzz factor. + * This means the RX packet and sync event crossed as they were + * placed on the event queue, which can sometimes happen. + */ + pkt_timestamp_major = channel->sync_timestamp_major - 1 + carry; + } else { + /* it's outside tolerance in both directions. this might be + * indicative of us missing sync events for some reason, so + * we'll call it an error rather than risk giving a bogus + * timestamp. + */ + netif_vdbg(efx, drv, efx->net_dev, + "packet timestamp %x too far from sync event %x:%x\n", + pkt_timestamp_minor, channel->sync_timestamp_major, + channel->sync_timestamp_minor); + return; + } + + /* attach the timestamps to the skb */ + timestamps = skb_hwtstamps(skb); + timestamps->hwtstamp = + efx_ptp_s27_to_ktime(pkt_timestamp_major, pkt_timestamp_minor); +} + static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) { struct efx_ptp_data *ptp_data = container_of(ptp, struct efx_ptp_data, phc_clock_info); - struct efx_nic *efx = ptp_data->channel->efx; + struct efx_nic *efx = ptp_data->efx; MCDI_DECLARE_BUF(inadj, MC_CMD_PTP_IN_ADJUST_LEN); s64 adjustment_ns; int rc; @@ -1389,24 +1813,26 @@ static int efx_phc_adjfreq(struct ptp_clock_info *ptp, s32 delta) if (rc != 0) return rc; - ptp_data->current_adjfreq = delta; + ptp_data->current_adjfreq = adjustment_ns; return 0; } static int efx_phc_adjtime(struct ptp_clock_info *ptp, s64 delta) { + u32 nic_major, nic_minor; struct efx_ptp_data *ptp_data = container_of(ptp, struct efx_ptp_data, phc_clock_info); - struct efx_nic *efx = ptp_data->channel->efx; - struct timespec delta_ts = ns_to_timespec(delta); + struct efx_nic *efx = ptp_data->efx; MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_ADJUST_LEN); + efx->ptp_data->ns_to_nic_time(delta, &nic_major, &nic_minor); + MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_ADJUST); MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0); - MCDI_SET_QWORD(inbuf, PTP_IN_ADJUST_FREQ, 0); - MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_SECONDS, (u32)delta_ts.tv_sec); - MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_NANOSECONDS, (u32)delta_ts.tv_nsec); + MCDI_SET_QWORD(inbuf, PTP_IN_ADJUST_FREQ, ptp_data->current_adjfreq); + MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_MAJOR, nic_major); + MCDI_SET_DWORD(inbuf, PTP_IN_ADJUST_MINOR, nic_minor); return efx_mcdi_rpc(efx, MC_CMD_PTP, inbuf, sizeof(inbuf), NULL, 0, NULL); } @@ -1416,10 +1842,11 @@ static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts) struct efx_ptp_data *ptp_data = container_of(ptp, struct efx_ptp_data, phc_clock_info); - struct efx_nic *efx = ptp_data->channel->efx; + struct efx_nic *efx = ptp_data->efx; MCDI_DECLARE_BUF(inbuf, MC_CMD_PTP_IN_READ_NIC_TIME_LEN); MCDI_DECLARE_BUF(outbuf, MC_CMD_PTP_OUT_READ_NIC_TIME_LEN); int rc; + ktime_t kt; MCDI_SET_DWORD(inbuf, PTP_IN_OP, MC_CMD_PTP_OP_READ_NIC_TIME); MCDI_SET_DWORD(inbuf, PTP_IN_PERIPH_ID, 0); @@ -1429,8 +1856,10 @@ static int efx_phc_gettime(struct ptp_clock_info *ptp, struct timespec *ts) if (rc != 0) return rc; - ts->tv_sec = MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_SECONDS); - ts->tv_nsec = MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_NANOSECONDS); + kt = ptp_data->nic_to_kernel_time( + MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_MAJOR), + MCDI_DWORD(outbuf, PTP_OUT_READ_NIC_TIME_MINOR), 0); + *ts = ktime_to_timespec(kt); return 0; } @@ -1482,7 +1911,7 @@ static const struct efx_channel_type efx_ptp_channel_type = { .keep_eventq = false, }; -void efx_ptp_probe(struct efx_nic *efx) +void efx_ptp_defer_probe_with_channel(struct efx_nic *efx) { /* Check whether PTP is implemented on this NIC. The DISABLE * operation will succeed if and only if it is implemented. @@ -1491,3 +1920,20 @@ void efx_ptp_probe(struct efx_nic *efx) efx->extra_channel_type[EFX_EXTRA_CHANNEL_PTP] = &efx_ptp_channel_type; } + +void efx_ptp_start_datapath(struct efx_nic *efx) +{ + if (efx_ptp_restart(efx)) + netif_err(efx, drv, efx->net_dev, "Failed to restart PTP.\n"); + /* re-enable timestamping if it was previously enabled */ + if (efx->type->ptp_set_ts_sync_events) + efx->type->ptp_set_ts_sync_events(efx, true, true); +} + +void efx_ptp_stop_datapath(struct efx_nic *efx) +{ + /* temporarily disable timestamping */ + if (efx->type->ptp_set_ts_sync_events) + efx->type->ptp_set_ts_sync_events(efx, false, true); + efx_ptp_stop(efx); +} diff --git a/drivers/net/ethernet/sfc/rx.c b/drivers/net/ethernet/sfc/rx.c index 4a596725023..48588ddf81b 100644 --- a/drivers/net/ethernet/sfc/rx.c +++ b/drivers/net/ethernet/sfc/rx.c @@ -12,6 +12,7 @@ #include <linux/in.h> #include <linux/slab.h> #include <linux/ip.h> +#include <linux/ipv6.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/prefetch.h> @@ -93,7 +94,7 @@ static inline void efx_sync_rx_buffer(struct efx_nic *efx, void efx_rx_config_page_split(struct efx_nic *efx) { - efx->rx_page_buf_step = ALIGN(efx->rx_dma_len + NET_IP_ALIGN, + efx->rx_page_buf_step = ALIGN(efx->rx_dma_len + efx->rx_ip_align, EFX_RX_BUF_ALIGNMENT); efx->rx_bufs_per_page = efx->rx_buffer_order ? 1 : ((PAGE_SIZE - sizeof(struct efx_rx_page_state)) / @@ -148,7 +149,7 @@ static struct page *efx_reuse_page(struct efx_rx_queue *rx_queue) * 0 on success. If a single page can be used for multiple buffers, * then the page will either be inserted fully, or not at all. */ -static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue) +static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue, bool atomic) { struct efx_nic *efx = rx_queue->efx; struct efx_rx_buffer *rx_buf; @@ -162,7 +163,8 @@ static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue) do { page = efx_reuse_page(rx_queue); if (page == NULL) { - page = alloc_pages(__GFP_COLD | __GFP_COMP | GFP_ATOMIC, + page = alloc_pages(__GFP_COLD | __GFP_COMP | + (atomic ? GFP_ATOMIC : GFP_KERNEL), efx->rx_buffer_order); if (unlikely(page == NULL)) return -ENOMEM; @@ -188,9 +190,9 @@ static int efx_init_rx_buffers(struct efx_rx_queue *rx_queue) do { index = rx_queue->added_count & rx_queue->ptr_mask; rx_buf = efx_rx_buffer(rx_queue, index); - rx_buf->dma_addr = dma_addr + NET_IP_ALIGN; + rx_buf->dma_addr = dma_addr + efx->rx_ip_align; rx_buf->page = page; - rx_buf->page_offset = page_offset + NET_IP_ALIGN; + rx_buf->page_offset = page_offset + efx->rx_ip_align; rx_buf->len = efx->rx_dma_len; rx_buf->flags = 0; ++rx_queue->added_count; @@ -320,7 +322,7 @@ static void efx_discard_rx_packet(struct efx_channel *channel, * this means this function must run from the NAPI handler, or be called * when NAPI is disabled. */ -void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue) +void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue, bool atomic) { struct efx_nic *efx = rx_queue->efx; unsigned int fill_level, batch_size; @@ -353,7 +355,7 @@ void efx_fast_push_rx_descriptors(struct efx_rx_queue *rx_queue) do { - rc = efx_init_rx_buffers(rx_queue); + rc = efx_init_rx_buffers(rx_queue, atomic); if (unlikely(rc)) { /* Ensure that we don't leave the rx queue empty */ if (rx_queue->added_count == rx_queue->removed_count) @@ -438,7 +440,8 @@ efx_rx_packet_gro(struct efx_channel *channel, struct efx_rx_buffer *rx_buf, } if (efx->net_dev->features & NETIF_F_RXHASH) - skb->rxhash = efx_rx_buf_hash(efx, eh); + skb_set_hash(skb, efx_rx_buf_hash(efx, eh), + PKT_HASH_TYPE_L3); skb->ip_summed = ((rx_buf->flags & EFX_RX_PKT_CSUMMED) ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE); @@ -474,14 +477,18 @@ static struct sk_buff *efx_rx_mk_skb(struct efx_channel *channel, struct sk_buff *skb; /* Allocate an SKB to store the headers */ - skb = netdev_alloc_skb(efx->net_dev, hdr_len + EFX_PAGE_SKB_ALIGN); + skb = netdev_alloc_skb(efx->net_dev, + efx->rx_ip_align + efx->rx_prefix_size + + hdr_len); if (unlikely(skb == NULL)) return NULL; EFX_BUG_ON_PARANOID(rx_buf->len < hdr_len); - skb_reserve(skb, EFX_PAGE_SKB_ALIGN); - memcpy(__skb_put(skb, hdr_len), eh, hdr_len); + memcpy(skb->data + efx->rx_ip_align, eh - efx->rx_prefix_size, + efx->rx_prefix_size + hdr_len); + skb_reserve(skb, efx->rx_ip_align + efx->rx_prefix_size); + __skb_put(skb, hdr_len); /* Append the remaining page(s) onto the frag list */ if (rx_buf->len > hdr_len) { @@ -618,6 +625,8 @@ static void efx_rx_deliver(struct efx_channel *channel, u8 *eh, if (likely(rx_buf->flags & EFX_RX_PKT_CSUMMED)) skb->ip_summed = CHECKSUM_UNNECESSARY; + efx_rx_skb_attach_timestamp(channel, skb); + if (channel->type->receive_skb) if (channel->type->receive_skb(channel, skb)) return; @@ -818,44 +827,70 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, struct efx_nic *efx = netdev_priv(net_dev); struct efx_channel *channel; struct efx_filter_spec spec; - const struct iphdr *ip; const __be16 *ports; + __be16 ether_type; int nhoff; int rc; - nhoff = skb_network_offset(skb); + /* The core RPS/RFS code has already parsed and validated + * VLAN, IP and transport headers. We assume they are in the + * header area. + */ if (skb->protocol == htons(ETH_P_8021Q)) { - EFX_BUG_ON_PARANOID(skb_headlen(skb) < - nhoff + sizeof(struct vlan_hdr)); - if (((const struct vlan_hdr *)skb->data + nhoff)-> - h_vlan_encapsulated_proto != htons(ETH_P_IP)) - return -EPROTONOSUPPORT; + const struct vlan_hdr *vh = + (const struct vlan_hdr *)skb->data; - /* This is IP over 802.1q VLAN. We can't filter on the - * IP 5-tuple and the vlan together, so just strip the - * vlan header and filter on the IP part. + /* We can't filter on the IP 5-tuple and the vlan + * together, so just strip the vlan header and filter + * on the IP part. */ - nhoff += sizeof(struct vlan_hdr); - } else if (skb->protocol != htons(ETH_P_IP)) { - return -EPROTONOSUPPORT; + EFX_BUG_ON_PARANOID(skb_headlen(skb) < sizeof(*vh)); + ether_type = vh->h_vlan_encapsulated_proto; + nhoff = sizeof(struct vlan_hdr); + } else { + ether_type = skb->protocol; + nhoff = 0; } - /* RFS must validate the IP header length before calling us */ - EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + sizeof(*ip)); - ip = (const struct iphdr *)(skb->data + nhoff); - if (ip_is_fragment(ip)) + if (ether_type != htons(ETH_P_IP) && ether_type != htons(ETH_P_IPV6)) return -EPROTONOSUPPORT; - EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + 4 * ip->ihl + 4); - ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl); efx_filter_init_rx(&spec, EFX_FILTER_PRI_HINT, efx->rx_scatter ? EFX_FILTER_FLAG_RX_SCATTER : 0, rxq_index); - rc = efx_filter_set_ipv4_full(&spec, ip->protocol, - ip->daddr, ports[1], ip->saddr, ports[0]); - if (rc) - return rc; + spec.match_flags = + EFX_FILTER_MATCH_ETHER_TYPE | EFX_FILTER_MATCH_IP_PROTO | + EFX_FILTER_MATCH_LOC_HOST | EFX_FILTER_MATCH_LOC_PORT | + EFX_FILTER_MATCH_REM_HOST | EFX_FILTER_MATCH_REM_PORT; + spec.ether_type = ether_type; + + if (ether_type == htons(ETH_P_IP)) { + const struct iphdr *ip = + (const struct iphdr *)(skb->data + nhoff); + + EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + sizeof(*ip)); + if (ip_is_fragment(ip)) + return -EPROTONOSUPPORT; + spec.ip_proto = ip->protocol; + spec.rem_host[0] = ip->saddr; + spec.loc_host[0] = ip->daddr; + EFX_BUG_ON_PARANOID(skb_headlen(skb) < nhoff + 4 * ip->ihl + 4); + ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl); + } else { + const struct ipv6hdr *ip6 = + (const struct ipv6hdr *)(skb->data + nhoff); + + EFX_BUG_ON_PARANOID(skb_headlen(skb) < + nhoff + sizeof(*ip6) + 4); + spec.ip_proto = ip6->nexthdr; + memcpy(spec.rem_host, &ip6->saddr, sizeof(ip6->saddr)); + memcpy(spec.loc_host, &ip6->daddr, sizeof(ip6->daddr)); + ports = (const __be16 *)(ip6 + 1); + } + + spec.rem_port = ports[0]; + spec.loc_port = ports[1]; rc = efx->type->filter_rfs_insert(efx, &spec); if (rc < 0) @@ -866,11 +901,18 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, channel = efx_get_channel(efx, skb_get_rx_queue(skb)); ++channel->rfs_filters_added; - netif_info(efx, rx_status, efx->net_dev, - "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n", - (ip->protocol == IPPROTO_TCP) ? "TCP" : "UDP", - &ip->saddr, ntohs(ports[0]), &ip->daddr, ntohs(ports[1]), - rxq_index, flow_id, rc); + if (ether_type == htons(ETH_P_IP)) + netif_info(efx, rx_status, efx->net_dev, + "steering %s %pI4:%u:%pI4:%u to queue %u [flow %u filter %d]\n", + (spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP", + spec.rem_host, ntohs(ports[0]), spec.loc_host, + ntohs(ports[1]), rxq_index, flow_id, rc); + else + netif_info(efx, rx_status, efx->net_dev, + "steering %s [%pI6]:%u:[%pI6]:%u to queue %u [flow %u filter %d]\n", + (spec.ip_proto == IPPROTO_TCP) ? "TCP" : "UDP", + spec.rem_host, ntohs(ports[0]), spec.loc_host, + ntohs(ports[1]), rxq_index, flow_id, rc); return rc; } diff --git a/drivers/net/ethernet/sfc/selftest.c b/drivers/net/ethernet/sfc/selftest.c index 144bbff5a4a..0fc5baef45b 100644 --- a/drivers/net/ethernet/sfc/selftest.c +++ b/drivers/net/ethernet/sfc/selftest.c @@ -50,7 +50,7 @@ struct efx_loopback_payload { } __packed; /* Loopback test source MAC address */ -static const unsigned char payload_source[ETH_ALEN] = { +static const u8 payload_source[ETH_ALEN] __aligned(2) = { 0x00, 0x0f, 0x53, 0x1b, 0x1b, 0x1b, }; @@ -366,8 +366,8 @@ static void efx_iterate_state(struct efx_nic *efx) struct efx_loopback_payload *payload = &state->payload; /* Initialise the layerII header */ - memcpy(&payload->header.h_dest, net_dev->dev_addr, ETH_ALEN); - memcpy(&payload->header.h_source, &payload_source, ETH_ALEN); + ether_addr_copy((u8 *)&payload->header.h_dest, net_dev->dev_addr); + ether_addr_copy((u8 *)&payload->header.h_source, payload_source); payload->header.h_proto = htons(ETH_P_IP); /* saddr set later and used as incrementing count */ @@ -722,7 +722,7 @@ int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests, return rc_reset; } - if ((tests->registers < 0) && !rc_test) + if ((tests->memory < 0 || tests->registers < 0) && !rc_test) rc_test = -EIO; } diff --git a/drivers/net/ethernet/sfc/selftest.h b/drivers/net/ethernet/sfc/selftest.h index 87698ae0bf7..009dbe88f3b 100644 --- a/drivers/net/ethernet/sfc/selftest.h +++ b/drivers/net/ethernet/sfc/selftest.h @@ -38,18 +38,18 @@ struct efx_self_tests { int eventq_dma[EFX_MAX_CHANNELS]; int eventq_int[EFX_MAX_CHANNELS]; /* offline tests */ + int memory; int registers; int phy_ext[EFX_MAX_PHY_TESTS]; struct efx_loopback_self_tests loopback[LOOPBACK_TEST_MAX + 1]; }; -extern void efx_loopback_rx_packet(struct efx_nic *efx, - const char *buf_ptr, int pkt_len); -extern int efx_selftest(struct efx_nic *efx, - struct efx_self_tests *tests, - unsigned flags); -extern void efx_selftest_async_start(struct efx_nic *efx); -extern void efx_selftest_async_cancel(struct efx_nic *efx); -extern void efx_selftest_async_work(struct work_struct *data); +void efx_loopback_rx_packet(struct efx_nic *efx, const char *buf_ptr, + int pkt_len); +int efx_selftest(struct efx_nic *efx, struct efx_self_tests *tests, + unsigned flags); +void efx_selftest_async_start(struct efx_nic *efx); +void efx_selftest_async_cancel(struct efx_nic *efx); +void efx_selftest_async_work(struct work_struct *data); #endif /* EFX_SELFTEST_H */ diff --git a/drivers/net/ethernet/sfc/siena.c b/drivers/net/ethernet/sfc/siena.c index d034bcd124e..50ffefed492 100644 --- a/drivers/net/ethernet/sfc/siena.c +++ b/drivers/net/ethernet/sfc/siena.c @@ -118,6 +118,54 @@ out: /************************************************************************** * + * PTP + * + ************************************************************************** + */ + +static void siena_ptp_write_host_time(struct efx_nic *efx, u32 host_time) +{ + _efx_writed(efx, cpu_to_le32(host_time), + FR_CZ_MC_TREG_SMEM + MC_SMEM_P0_PTP_TIME_OFST); +} + +static int siena_ptp_set_ts_config(struct efx_nic *efx, + struct hwtstamp_config *init) +{ + int rc; + + switch (init->rx_filter) { + case HWTSTAMP_FILTER_NONE: + /* if TX timestamping is still requested then leave PTP on */ + return efx_ptp_change_mode(efx, + init->tx_type != HWTSTAMP_TX_OFF, + efx_ptp_get_mode(efx)); + case HWTSTAMP_FILTER_PTP_V1_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V1_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ: + init->rx_filter = HWTSTAMP_FILTER_PTP_V1_L4_EVENT; + return efx_ptp_change_mode(efx, true, MC_CMD_PTP_MODE_V1); + case HWTSTAMP_FILTER_PTP_V2_L4_EVENT: + case HWTSTAMP_FILTER_PTP_V2_L4_SYNC: + case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ: + init->rx_filter = HWTSTAMP_FILTER_PTP_V2_L4_EVENT; + rc = efx_ptp_change_mode(efx, true, + MC_CMD_PTP_MODE_V2_ENHANCED); + /* bug 33070 - old versions of the firmware do not support the + * improved UUID filtering option. Similarly old versions of the + * application do not expect it to be enabled. If the firmware + * does not accept the enhanced mode, fall back to the standard + * PTP v2 UUID filtering. */ + if (rc != 0) + rc = efx_ptp_change_mode(efx, true, MC_CMD_PTP_MODE_V2); + return rc; + default: + return -ERANGE; + } +} + +/************************************************************************** + * * Device reset * ************************************************************************** @@ -259,7 +307,7 @@ static int siena_probe_nic(struct efx_nic *efx) goto fail5; efx_sriov_probe(efx); - efx_ptp_probe(efx); + efx_ptp_defer_probe_with_channel(efx); return 0; @@ -273,6 +321,31 @@ fail1: return rc; } +static void siena_rx_push_rss_config(struct efx_nic *efx) +{ + efx_oword_t temp; + + /* Set hash key for IPv4 */ + memcpy(&temp, efx->rx_hash_key, sizeof(temp)); + efx_writeo(efx, &temp, FR_BZ_RX_RSS_TKEY); + + /* Enable IPv6 RSS */ + BUILD_BUG_ON(sizeof(efx->rx_hash_key) < + 2 * sizeof(temp) + FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8 || + FRF_CZ_RX_RSS_IPV6_TKEY_HI_LBN != 0); + memcpy(&temp, efx->rx_hash_key, sizeof(temp)); + efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG1); + memcpy(&temp, efx->rx_hash_key + sizeof(temp), sizeof(temp)); + efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG2); + EFX_POPULATE_OWORD_2(temp, FRF_CZ_RX_RSS_IPV6_THASH_ENABLE, 1, + FRF_CZ_RX_RSS_IPV6_IP_THASH_ENABLE, 1); + memcpy(&temp, efx->rx_hash_key + 2 * sizeof(temp), + FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8); + efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG3); + + efx_farch_rx_push_indir_table(efx); +} + /* This call performs hardware-specific global initialisation, such as * defining the descriptor cache sizes and number of RSS channels. * It does not set up any buffers, descriptor rings or event queues. @@ -313,23 +386,7 @@ static int siena_init_nic(struct efx_nic *efx) EFX_RX_USR_BUF_SIZE >> 5); efx_writeo(efx, &temp, FR_AZ_RX_CFG); - /* Set hash key for IPv4 */ - memcpy(&temp, efx->rx_hash_key, sizeof(temp)); - efx_writeo(efx, &temp, FR_BZ_RX_RSS_TKEY); - - /* Enable IPv6 RSS */ - BUILD_BUG_ON(sizeof(efx->rx_hash_key) < - 2 * sizeof(temp) + FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8 || - FRF_CZ_RX_RSS_IPV6_TKEY_HI_LBN != 0); - memcpy(&temp, efx->rx_hash_key, sizeof(temp)); - efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG1); - memcpy(&temp, efx->rx_hash_key + sizeof(temp), sizeof(temp)); - efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG2); - EFX_POPULATE_OWORD_2(temp, FRF_CZ_RX_RSS_IPV6_THASH_ENABLE, 1, - FRF_CZ_RX_RSS_IPV6_IP_THASH_ENABLE, 1); - memcpy(&temp, efx->rx_hash_key + 2 * sizeof(temp), - FRF_CZ_RX_RSS_IPV6_TKEY_HI_WIDTH / 8); - efx_writeo(efx, &temp, FR_CZ_RX_RSS_IPV6_REG3); + siena_rx_push_rss_config(efx); /* Enable event logging */ rc = efx_mcdi_log_ctrl(efx, true, false, 0); @@ -458,6 +515,8 @@ static int siena_try_update_nic_stats(struct efx_nic *efx) return -EAGAIN; /* Update derived statistics */ + efx_nic_fix_nodesc_drop_stat(efx, + &stats[SIENA_STAT_rx_nodesc_drop_cnt]); efx_update_diff_stat(&stats[SIENA_STAT_tx_good_bytes], stats[SIENA_STAT_tx_bytes] - stats[SIENA_STAT_tx_bad_bytes]); @@ -837,19 +896,6 @@ fail: /************************************************************************** * - * PTP - * - ************************************************************************** - */ - -static void siena_ptp_write_host_time(struct efx_nic *efx, u32 host_time) -{ - _efx_writed(efx, cpu_to_le32(host_time), - FR_CZ_MC_TREG_SMEM + MC_SMEM_P0_PTP_TIME_OFST); -} - -/************************************************************************** - * * Revision-dependent attributes used by efx.c and nic.c * ************************************************************************** @@ -875,9 +921,12 @@ const struct efx_nic_type siena_a0_nic_type = { .fini_dmaq = efx_farch_fini_dmaq, .prepare_flush = siena_prepare_flush, .finish_flush = siena_finish_flush, + .prepare_flr = efx_port_dummy_op_void, + .finish_flr = efx_farch_finish_flr, .describe_stats = siena_describe_nic_stats, .update_stats = siena_update_nic_stats, .start_stats = efx_mcdi_mac_start_stats, + .pull_stats = efx_mcdi_mac_pull_stats, .stop_stats = efx_mcdi_mac_stop_stats, .set_id_led = efx_mcdi_set_id_led, .push_irq_moderation = siena_push_irq_moderation, @@ -902,7 +951,7 @@ const struct efx_nic_type siena_a0_nic_type = { .tx_init = efx_farch_tx_init, .tx_remove = efx_farch_tx_remove, .tx_write = efx_farch_tx_write, - .rx_push_indir_table = efx_farch_rx_push_indir_table, + .rx_push_rss_config = siena_rx_push_rss_config, .rx_probe = efx_farch_rx_probe, .rx_init = efx_farch_rx_init, .rx_remove = efx_farch_rx_remove, @@ -939,6 +988,7 @@ const struct efx_nic_type siena_a0_nic_type = { .mtd_sync = efx_mcdi_mtd_sync, #endif .ptp_write_host_time = siena_ptp_write_host_time, + .ptp_set_ts_config = siena_ptp_set_ts_config, .revision = EFX_REV_SIENA_A0, .txd_ptr_tbl_base = FR_BZ_TX_DESC_PTR_TBL, @@ -957,4 +1007,11 @@ const struct efx_nic_type siena_a0_nic_type = { NETIF_F_RXHASH | NETIF_F_NTUPLE), .mcdi_max_ver = 1, .max_rx_ip_filters = FR_BZ_RX_FILTER_TBL0_ROWS, + .hwtstamp_filters = (1 << HWTSTAMP_FILTER_NONE | + 1 << HWTSTAMP_FILTER_PTP_V1_L4_EVENT | + 1 << HWTSTAMP_FILTER_PTP_V1_L4_SYNC | + 1 << HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ | + 1 << HWTSTAMP_FILTER_PTP_V2_L4_EVENT | + 1 << HWTSTAMP_FILTER_PTP_V2_L4_SYNC | + 1 << HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ), }; diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c index 0c38f926871..43d2e64546e 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.c +++ b/drivers/net/ethernet/sfc/siena_sriov.c @@ -1095,7 +1095,7 @@ static void efx_sriov_peer_work(struct work_struct *data) /* Fill the remaining addresses */ list_for_each_entry(local_addr, &efx->local_addr_list, link) { - memcpy(peer->mac_addr, local_addr->addr, ETH_ALEN); + ether_addr_copy(peer->mac_addr, local_addr->addr); peer->tci = 0; ++peer; ++peer_count; @@ -1303,8 +1303,7 @@ int efx_sriov_init(struct efx_nic *efx) goto fail_vfs; rtnl_lock(); - memcpy(vfdi_status->peers[0].mac_addr, - net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(vfdi_status->peers[0].mac_addr, net_dev->dev_addr); efx->vf_init_count = efx->vf_count; rtnl_unlock(); @@ -1452,8 +1451,8 @@ void efx_sriov_mac_address_changed(struct efx_nic *efx) if (!efx->vf_init_count) return; - memcpy(vfdi_status->peers[0].mac_addr, - efx->net_dev->dev_addr, ETH_ALEN); + ether_addr_copy(vfdi_status->peers[0].mac_addr, + efx->net_dev->dev_addr); queue_work(vfdi_workqueue, &efx->peer_work); } @@ -1570,7 +1569,7 @@ int efx_sriov_set_vf_mac(struct net_device *net_dev, int vf_i, u8 *mac) vf = efx->vf + vf_i; mutex_lock(&vf->status_lock); - memcpy(vf->addr.mac_addr, mac, ETH_ALEN); + ether_addr_copy(vf->addr.mac_addr, mac); __efx_sriov_update_vf_addr(vf); mutex_unlock(&vf->status_lock); @@ -1633,8 +1632,9 @@ int efx_sriov_get_vf_config(struct net_device *net_dev, int vf_i, vf = efx->vf + vf_i; ivi->vf = vf_i; - memcpy(ivi->mac, vf->addr.mac_addr, ETH_ALEN); - ivi->tx_rate = 0; + ether_addr_copy(ivi->mac, vf->addr.mac_addr); + ivi->max_tx_rate = 0; + ivi->min_tx_rate = 0; tci = ntohs(vf->addr.tci); ivi->vlan = tci & VLAN_VID_MASK; ivi->qos = (tci >> VLAN_PRIO_SHIFT) & 0x7; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index 2ac91c5b5ee..ede8dcca0ff 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -17,10 +17,46 @@ #include <net/ipv6.h> #include <linux/if_ether.h> #include <linux/highmem.h> +#include <linux/cache.h> #include "net_driver.h" #include "efx.h" +#include "io.h" #include "nic.h" #include "workarounds.h" +#include "ef10_regs.h" + +#ifdef EFX_USE_PIO + +#define EFX_PIOBUF_SIZE_MAX ER_DZ_TX_PIOBUF_SIZE +#define EFX_PIOBUF_SIZE_DEF ALIGN(256, L1_CACHE_BYTES) +unsigned int efx_piobuf_size __read_mostly = EFX_PIOBUF_SIZE_DEF; + +#endif /* EFX_USE_PIO */ + +static inline unsigned int +efx_tx_queue_get_insert_index(const struct efx_tx_queue *tx_queue) +{ + return tx_queue->insert_count & tx_queue->ptr_mask; +} + +static inline struct efx_tx_buffer * +__efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue) +{ + return &tx_queue->buffer[efx_tx_queue_get_insert_index(tx_queue)]; +} + +static inline struct efx_tx_buffer * +efx_tx_queue_get_insert_buffer(const struct efx_tx_queue *tx_queue) +{ + struct efx_tx_buffer *buffer = + __efx_tx_queue_get_insert_buffer(tx_queue); + + EFX_BUG_ON_PARANOID(buffer->len); + EFX_BUG_ON_PARANOID(buffer->flags); + EFX_BUG_ON_PARANOID(buffer->unmap_len); + + return buffer; +} static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue, struct efx_tx_buffer *buffer, @@ -29,8 +65,7 @@ static void efx_dequeue_buffer(struct efx_tx_queue *tx_queue, { if (buffer->unmap_len) { struct device *dma_dev = &tx_queue->efx->pci_dev->dev; - dma_addr_t unmap_addr = (buffer->dma_addr + buffer->len - - buffer->unmap_len); + dma_addr_t unmap_addr = buffer->dma_addr - buffer->dma_offset; if (buffer->flags & EFX_TX_BUF_MAP_SINGLE) dma_unmap_single(dma_dev, unmap_addr, buffer->unmap_len, DMA_TO_DEVICE); @@ -83,8 +118,10 @@ unsigned int efx_tx_max_skb_descs(struct efx_nic *efx) */ unsigned int max_descs = EFX_TSO_MAX_SEGS * 2 + MAX_SKB_FRAGS; - /* Possibly one more per segment for the alignment workaround */ - if (EFX_WORKAROUND_5391(efx)) + /* Possibly one more per segment for the alignment workaround, + * or for option descriptors + */ + if (EFX_WORKAROUND_5391(efx) || efx_nic_rev(efx) >= EFX_REV_HUNT_A0) max_descs += EFX_TSO_MAX_SEGS; /* Possibly more for PCIe page boundaries within input fragments */ @@ -145,6 +182,157 @@ static void efx_tx_maybe_stop_queue(struct efx_tx_queue *txq1) } } +#ifdef EFX_USE_PIO + +struct efx_short_copy_buffer { + int used; + u8 buf[L1_CACHE_BYTES]; +}; + +/* Copy in explicit 64-bit writes. */ +static void efx_memcpy_64(void __iomem *dest, void *src, size_t len) +{ + u64 *src64 = src; + u64 __iomem *dest64 = dest; + size_t l64 = len / 8; + size_t i; + + for (i = 0; i < l64; i++) + writeq(src64[i], &dest64[i]); +} + +/* Copy to PIO, respecting that writes to PIO buffers must be dword aligned. + * Advances piobuf pointer. Leaves additional data in the copy buffer. + */ +static void efx_memcpy_toio_aligned(struct efx_nic *efx, u8 __iomem **piobuf, + u8 *data, int len, + struct efx_short_copy_buffer *copy_buf) +{ + int block_len = len & ~(sizeof(copy_buf->buf) - 1); + + efx_memcpy_64(*piobuf, data, block_len); + *piobuf += block_len; + len -= block_len; + + if (len) { + data += block_len; + BUG_ON(copy_buf->used); + BUG_ON(len > sizeof(copy_buf->buf)); + memcpy(copy_buf->buf, data, len); + copy_buf->used = len; + } +} + +/* Copy to PIO, respecting dword alignment, popping data from copy buffer first. + * Advances piobuf pointer. Leaves additional data in the copy buffer. + */ +static void efx_memcpy_toio_aligned_cb(struct efx_nic *efx, u8 __iomem **piobuf, + u8 *data, int len, + struct efx_short_copy_buffer *copy_buf) +{ + if (copy_buf->used) { + /* if the copy buffer is partially full, fill it up and write */ + int copy_to_buf = + min_t(int, sizeof(copy_buf->buf) - copy_buf->used, len); + + memcpy(copy_buf->buf + copy_buf->used, data, copy_to_buf); + copy_buf->used += copy_to_buf; + + /* if we didn't fill it up then we're done for now */ + if (copy_buf->used < sizeof(copy_buf->buf)) + return; + + efx_memcpy_64(*piobuf, copy_buf->buf, sizeof(copy_buf->buf)); + *piobuf += sizeof(copy_buf->buf); + data += copy_to_buf; + len -= copy_to_buf; + copy_buf->used = 0; + } + + efx_memcpy_toio_aligned(efx, piobuf, data, len, copy_buf); +} + +static void efx_flush_copy_buffer(struct efx_nic *efx, u8 __iomem *piobuf, + struct efx_short_copy_buffer *copy_buf) +{ + /* if there's anything in it, write the whole buffer, including junk */ + if (copy_buf->used) + efx_memcpy_64(piobuf, copy_buf->buf, sizeof(copy_buf->buf)); +} + +/* Traverse skb structure and copy fragments in to PIO buffer. + * Advances piobuf pointer. + */ +static void efx_skb_copy_bits_to_pio(struct efx_nic *efx, struct sk_buff *skb, + u8 __iomem **piobuf, + struct efx_short_copy_buffer *copy_buf) +{ + int i; + + efx_memcpy_toio_aligned(efx, piobuf, skb->data, skb_headlen(skb), + copy_buf); + + for (i = 0; i < skb_shinfo(skb)->nr_frags; ++i) { + skb_frag_t *f = &skb_shinfo(skb)->frags[i]; + u8 *vaddr; + + vaddr = kmap_atomic(skb_frag_page(f)); + + efx_memcpy_toio_aligned_cb(efx, piobuf, vaddr + f->page_offset, + skb_frag_size(f), copy_buf); + kunmap_atomic(vaddr); + } + + EFX_BUG_ON_PARANOID(skb_shinfo(skb)->frag_list); +} + +static struct efx_tx_buffer * +efx_enqueue_skb_pio(struct efx_tx_queue *tx_queue, struct sk_buff *skb) +{ + struct efx_tx_buffer *buffer = + efx_tx_queue_get_insert_buffer(tx_queue); + u8 __iomem *piobuf = tx_queue->piobuf; + + /* Copy to PIO buffer. Ensure the writes are padded to the end + * of a cache line, as this is required for write-combining to be + * effective on at least x86. + */ + + if (skb_shinfo(skb)->nr_frags) { + /* The size of the copy buffer will ensure all writes + * are the size of a cache line. + */ + struct efx_short_copy_buffer copy_buf; + + copy_buf.used = 0; + + efx_skb_copy_bits_to_pio(tx_queue->efx, skb, + &piobuf, ©_buf); + efx_flush_copy_buffer(tx_queue->efx, piobuf, ©_buf); + } else { + /* Pad the write to the size of a cache line. + * We can do this because we know the skb_shared_info sruct is + * after the source, and the destination buffer is big enough. + */ + BUILD_BUG_ON(L1_CACHE_BYTES > + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); + efx_memcpy_64(tx_queue->piobuf, skb->data, + ALIGN(skb->len, L1_CACHE_BYTES)); + } + + EFX_POPULATE_QWORD_5(buffer->option, + ESF_DZ_TX_DESC_IS_OPT, 1, + ESF_DZ_TX_OPTION_TYPE, ESE_DZ_TX_OPTION_DESC_PIO, + ESF_DZ_TX_PIO_CONT, 0, + ESF_DZ_TX_PIO_BYTE_CNT, skb->len, + ESF_DZ_TX_PIO_BUF_ADDR, + tx_queue->piobuf_offset); + ++tx_queue->pio_packets; + ++tx_queue->insert_count; + return buffer; +} +#endif /* EFX_USE_PIO */ + /* * Add a socket buffer to a TX queue * @@ -167,7 +355,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) struct device *dma_dev = &efx->pci_dev->dev; struct efx_tx_buffer *buffer; skb_frag_t *fragment; - unsigned int len, unmap_len = 0, insert_ptr; + unsigned int len, unmap_len = 0; dma_addr_t dma_addr, unmap_addr = 0; unsigned int dma_len; unsigned short dma_flags; @@ -189,6 +377,17 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) return NETDEV_TX_OK; } + /* Consider using PIO for short packets */ +#ifdef EFX_USE_PIO + if (skb->len <= efx_piobuf_size && tx_queue->piobuf && + efx_nic_tx_is_empty(tx_queue) && + efx_nic_tx_is_empty(efx_tx_queue_partner(tx_queue))) { + buffer = efx_enqueue_skb_pio(tx_queue, skb); + dma_flags = EFX_TX_BUF_OPTION; + goto finish_packet; + } +#endif + /* Map for DMA. Use dma_map_single rather than dma_map_page * since this is more efficient on machines with sparse * memory. @@ -208,11 +407,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) /* Add to TX queue, splitting across DMA boundaries */ do { - insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask; - buffer = &tx_queue->buffer[insert_ptr]; - EFX_BUG_ON_PARANOID(buffer->flags); - EFX_BUG_ON_PARANOID(buffer->len); - EFX_BUG_ON_PARANOID(buffer->unmap_len); + buffer = efx_tx_queue_get_insert_buffer(tx_queue); dma_len = efx_max_tx_len(efx, dma_addr); if (likely(dma_len >= len)) @@ -230,6 +425,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) /* Transfer ownership of the unmapping to the final buffer */ buffer->flags = EFX_TX_BUF_CONT | dma_flags; buffer->unmap_len = unmap_len; + buffer->dma_offset = buffer->dma_addr - unmap_addr; unmap_len = 0; /* Get address and size of next fragment */ @@ -245,6 +441,9 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) } /* Transfer ownership of the skb to the final buffer */ +#ifdef EFX_USE_PIO +finish_packet: +#endif buffer->skb = skb; buffer->flags = EFX_TX_BUF_SKB | dma_flags; @@ -270,8 +469,7 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) while (tx_queue->insert_count != tx_queue->write_count) { unsigned int pkts_compl = 0, bytes_compl = 0; --tx_queue->insert_count; - insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask; - buffer = &tx_queue->buffer[insert_ptr]; + buffer = __efx_tx_queue_get_insert_buffer(tx_queue); efx_dequeue_buffer(tx_queue, buffer, &pkts_compl, &bytes_compl); } @@ -601,15 +799,6 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) * Requires TX checksum offload support. */ -/* Number of bytes inserted at the start of a TSO header buffer, - * similar to NET_IP_ALIGN. - */ -#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS -#define TSOH_OFFSET 0 -#else -#define TSOH_OFFSET NET_IP_ALIGN -#endif - #define PTR_DIFF(p1, p2) ((u8 *)(p1) - (u8 *)(p2)) /** @@ -628,6 +817,9 @@ void efx_remove_tx_queue(struct efx_tx_queue *tx_queue) * @tcp_off: Offset of TCP header * @header_len: Number of bytes of header * @ip_base_len: IPv4 tot_len or IPv6 payload_len, before TCP payload + * @header_dma_addr: Header DMA address, when using option descriptors + * @header_unmap_len: Header DMA mapped length, or 0 if not using option + * descriptors * * The state used during segmentation. It is put into this data structure * just to make it easy to pass into inline functions. @@ -636,7 +828,7 @@ struct tso_state { /* Output position */ unsigned out_len; unsigned seqnum; - unsigned ipv4_id; + u16 ipv4_id; unsigned packet_space; /* Input position */ @@ -651,6 +843,8 @@ struct tso_state { unsigned int tcp_off; unsigned header_len; unsigned int ip_base_len; + dma_addr_t header_dma_addr; + unsigned int header_unmap_len; }; @@ -691,13 +885,13 @@ static u8 *efx_tsoh_get_buffer(struct efx_tx_queue *tx_queue, EFX_BUG_ON_PARANOID(buffer->flags); EFX_BUG_ON_PARANOID(buffer->unmap_len); - if (likely(len <= TSOH_STD_SIZE - TSOH_OFFSET)) { + if (likely(len <= TSOH_STD_SIZE - NET_IP_ALIGN)) { unsigned index = (tx_queue->insert_count & tx_queue->ptr_mask) / 2; struct efx_buffer *page_buf = &tx_queue->tsoh_page[index / TSOH_PER_PAGE]; unsigned offset = - TSOH_STD_SIZE * (index % TSOH_PER_PAGE) + TSOH_OFFSET; + TSOH_STD_SIZE * (index % TSOH_PER_PAGE) + NET_IP_ALIGN; if (unlikely(!page_buf->addr) && efx_nic_alloc_buffer(tx_queue->efx, page_buf, PAGE_SIZE, @@ -710,10 +904,10 @@ static u8 *efx_tsoh_get_buffer(struct efx_tx_queue *tx_queue, } else { tx_queue->tso_long_headers++; - buffer->heap_buf = kmalloc(TSOH_OFFSET + len, GFP_ATOMIC); + buffer->heap_buf = kmalloc(NET_IP_ALIGN + len, GFP_ATOMIC); if (unlikely(!buffer->heap_buf)) return NULL; - result = (u8 *)buffer->heap_buf + TSOH_OFFSET; + result = (u8 *)buffer->heap_buf + NET_IP_ALIGN; buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_HEAP; } @@ -737,23 +931,18 @@ static void efx_tx_queue_insert(struct efx_tx_queue *tx_queue, { struct efx_tx_buffer *buffer; struct efx_nic *efx = tx_queue->efx; - unsigned dma_len, insert_ptr; + unsigned dma_len; EFX_BUG_ON_PARANOID(len <= 0); while (1) { - insert_ptr = tx_queue->insert_count & tx_queue->ptr_mask; - buffer = &tx_queue->buffer[insert_ptr]; + buffer = efx_tx_queue_get_insert_buffer(tx_queue); ++tx_queue->insert_count; EFX_BUG_ON_PARANOID(tx_queue->insert_count - tx_queue->read_count >= efx->txq_entries); - EFX_BUG_ON_PARANOID(buffer->len); - EFX_BUG_ON_PARANOID(buffer->unmap_len); - EFX_BUG_ON_PARANOID(buffer->flags); - buffer->dma_addr = dma_addr; dma_len = efx_max_tx_len(efx, dma_addr); @@ -796,6 +985,7 @@ static int efx_tso_put_header(struct efx_tx_queue *tx_queue, return -ENOMEM; } buffer->unmap_len = buffer->len; + buffer->dma_offset = 0; buffer->flags |= EFX_TX_BUF_MAP_SINGLE; } @@ -814,19 +1004,27 @@ static void efx_enqueue_unwind(struct efx_tx_queue *tx_queue) /* Work backwards until we hit the original insert pointer value */ while (tx_queue->insert_count != tx_queue->write_count) { --tx_queue->insert_count; - buffer = &tx_queue->buffer[tx_queue->insert_count & - tx_queue->ptr_mask]; + buffer = __efx_tx_queue_get_insert_buffer(tx_queue); efx_dequeue_buffer(tx_queue, buffer, NULL, NULL); } } /* Parse the SKB header and initialise state. */ -static void tso_start(struct tso_state *st, const struct sk_buff *skb) +static int tso_start(struct tso_state *st, struct efx_nic *efx, + const struct sk_buff *skb) { + bool use_opt_desc = efx_nic_rev(efx) >= EFX_REV_HUNT_A0; + struct device *dma_dev = &efx->pci_dev->dev; + unsigned int header_len, in_len; + dma_addr_t dma_addr; + st->ip_off = skb_network_header(skb) - skb->data; st->tcp_off = skb_transport_header(skb) - skb->data; - st->header_len = st->tcp_off + (tcp_hdr(skb)->doff << 2u); + header_len = st->tcp_off + (tcp_hdr(skb)->doff << 2u); + in_len = skb_headlen(skb) - header_len; + st->header_len = header_len; + st->in_len = in_len; if (st->protocol == htons(ETH_P_IP)) { st->ip_base_len = st->header_len - st->ip_off; st->ipv4_id = ntohs(ip_hdr(skb)->id); @@ -840,9 +1038,34 @@ static void tso_start(struct tso_state *st, const struct sk_buff *skb) EFX_BUG_ON_PARANOID(tcp_hdr(skb)->syn); EFX_BUG_ON_PARANOID(tcp_hdr(skb)->rst); - st->out_len = skb->len - st->header_len; - st->unmap_len = 0; - st->dma_flags = 0; + st->out_len = skb->len - header_len; + + if (!use_opt_desc) { + st->header_unmap_len = 0; + + if (likely(in_len == 0)) { + st->dma_flags = 0; + st->unmap_len = 0; + return 0; + } + + dma_addr = dma_map_single(dma_dev, skb->data + header_len, + in_len, DMA_TO_DEVICE); + st->dma_flags = EFX_TX_BUF_MAP_SINGLE; + st->dma_addr = dma_addr; + st->unmap_addr = dma_addr; + st->unmap_len = in_len; + } else { + dma_addr = dma_map_single(dma_dev, skb->data, + skb_headlen(skb), DMA_TO_DEVICE); + st->header_dma_addr = dma_addr; + st->header_unmap_len = skb_headlen(skb); + st->dma_flags = 0; + st->dma_addr = dma_addr + header_len; + st->unmap_len = 0; + } + + return unlikely(dma_mapping_error(dma_dev, dma_addr)) ? -ENOMEM : 0; } static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx, @@ -860,24 +1083,6 @@ static int tso_get_fragment(struct tso_state *st, struct efx_nic *efx, return -ENOMEM; } -static int tso_get_head_fragment(struct tso_state *st, struct efx_nic *efx, - const struct sk_buff *skb) -{ - int hl = st->header_len; - int len = skb_headlen(skb) - hl; - - st->unmap_addr = dma_map_single(&efx->pci_dev->dev, skb->data + hl, - len, DMA_TO_DEVICE); - if (likely(!dma_mapping_error(&efx->pci_dev->dev, st->unmap_addr))) { - st->dma_flags = EFX_TX_BUF_MAP_SINGLE; - st->unmap_len = len; - st->in_len = len; - st->dma_addr = st->unmap_addr; - return 0; - } - return -ENOMEM; -} - /** * tso_fill_packet_with_fragment - form descriptors for the current fragment @@ -922,6 +1127,7 @@ static void tso_fill_packet_with_fragment(struct efx_tx_queue *tx_queue, if (st->in_len == 0) { /* Transfer ownership of the DMA mapping */ buffer->unmap_len = st->unmap_len; + buffer->dma_offset = buffer->unmap_len - buffer->len; buffer->flags |= st->dma_flags; st->unmap_len = 0; } @@ -944,55 +1150,98 @@ static int tso_start_new_packet(struct efx_tx_queue *tx_queue, struct tso_state *st) { struct efx_tx_buffer *buffer = - &tx_queue->buffer[tx_queue->insert_count & tx_queue->ptr_mask]; - struct tcphdr *tsoh_th; - unsigned ip_length; - u8 *header; - int rc; - - /* Allocate and insert a DMA-mapped header buffer. */ - header = efx_tsoh_get_buffer(tx_queue, buffer, st->header_len); - if (!header) - return -ENOMEM; + efx_tx_queue_get_insert_buffer(tx_queue); + bool is_last = st->out_len <= skb_shinfo(skb)->gso_size; + u8 tcp_flags_clear; - tsoh_th = (struct tcphdr *)(header + st->tcp_off); - - /* Copy and update the headers. */ - memcpy(header, skb->data, st->header_len); - - tsoh_th->seq = htonl(st->seqnum); - st->seqnum += skb_shinfo(skb)->gso_size; - if (st->out_len > skb_shinfo(skb)->gso_size) { - /* This packet will not finish the TSO burst. */ + if (!is_last) { st->packet_space = skb_shinfo(skb)->gso_size; - tsoh_th->fin = 0; - tsoh_th->psh = 0; + tcp_flags_clear = 0x09; /* mask out FIN and PSH */ } else { - /* This packet will be the last in the TSO burst. */ st->packet_space = st->out_len; - tsoh_th->fin = tcp_hdr(skb)->fin; - tsoh_th->psh = tcp_hdr(skb)->psh; + tcp_flags_clear = 0x00; } - ip_length = st->ip_base_len + st->packet_space; - if (st->protocol == htons(ETH_P_IP)) { - struct iphdr *tsoh_iph = (struct iphdr *)(header + st->ip_off); + if (!st->header_unmap_len) { + /* Allocate and insert a DMA-mapped header buffer. */ + struct tcphdr *tsoh_th; + unsigned ip_length; + u8 *header; + int rc; + + header = efx_tsoh_get_buffer(tx_queue, buffer, st->header_len); + if (!header) + return -ENOMEM; + + tsoh_th = (struct tcphdr *)(header + st->tcp_off); + + /* Copy and update the headers. */ + memcpy(header, skb->data, st->header_len); + + tsoh_th->seq = htonl(st->seqnum); + ((u8 *)tsoh_th)[13] &= ~tcp_flags_clear; + + ip_length = st->ip_base_len + st->packet_space; + + if (st->protocol == htons(ETH_P_IP)) { + struct iphdr *tsoh_iph = + (struct iphdr *)(header + st->ip_off); + + tsoh_iph->tot_len = htons(ip_length); + tsoh_iph->id = htons(st->ipv4_id); + } else { + struct ipv6hdr *tsoh_iph = + (struct ipv6hdr *)(header + st->ip_off); - tsoh_iph->tot_len = htons(ip_length); + tsoh_iph->payload_len = htons(ip_length); + } - /* Linux leaves suitable gaps in the IP ID space for us to fill. */ - tsoh_iph->id = htons(st->ipv4_id); - st->ipv4_id++; + rc = efx_tso_put_header(tx_queue, buffer, header); + if (unlikely(rc)) + return rc; } else { - struct ipv6hdr *tsoh_iph = - (struct ipv6hdr *)(header + st->ip_off); + /* Send the original headers with a TSO option descriptor + * in front + */ + u8 tcp_flags = ((u8 *)tcp_hdr(skb))[13] & ~tcp_flags_clear; + + buffer->flags = EFX_TX_BUF_OPTION; + buffer->len = 0; + buffer->unmap_len = 0; + EFX_POPULATE_QWORD_5(buffer->option, + ESF_DZ_TX_DESC_IS_OPT, 1, + ESF_DZ_TX_OPTION_TYPE, + ESE_DZ_TX_OPTION_DESC_TSO, + ESF_DZ_TX_TSO_TCP_FLAGS, tcp_flags, + ESF_DZ_TX_TSO_IP_ID, st->ipv4_id, + ESF_DZ_TX_TSO_TCP_SEQNO, st->seqnum); + ++tx_queue->insert_count; - tsoh_iph->payload_len = htons(ip_length); + /* We mapped the headers in tso_start(). Unmap them + * when the last segment is completed. + */ + buffer = efx_tx_queue_get_insert_buffer(tx_queue); + buffer->dma_addr = st->header_dma_addr; + buffer->len = st->header_len; + if (is_last) { + buffer->flags = EFX_TX_BUF_CONT | EFX_TX_BUF_MAP_SINGLE; + buffer->unmap_len = st->header_unmap_len; + buffer->dma_offset = 0; + /* Ensure we only unmap them once in case of a + * later DMA mapping error and rollback + */ + st->header_unmap_len = 0; + } else { + buffer->flags = EFX_TX_BUF_CONT; + buffer->unmap_len = 0; + } + ++tx_queue->insert_count; } - rc = efx_tso_put_header(tx_queue, buffer, header); - if (unlikely(rc)) - return rc; + st->seqnum += skb_shinfo(skb)->gso_size; + + /* Linux leaves suitable gaps in the IP ID space for us to fill. */ + ++st->ipv4_id; ++tx_queue->tso_packets; @@ -1023,12 +1272,11 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, EFX_BUG_ON_PARANOID(tx_queue->write_count != tx_queue->insert_count); - tso_start(&state, skb); + rc = tso_start(&state, efx, skb); + if (rc) + goto mem_err; - /* Assume that skb header area contains exactly the headers, and - * all payload is in the frag list. - */ - if (skb_headlen(skb) == state.header_len) { + if (likely(state.in_len == 0)) { /* Grab the first payload fragment. */ EFX_BUG_ON_PARANOID(skb_shinfo(skb)->nr_frags < 1); frag_i = 0; @@ -1037,9 +1285,7 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, if (rc) goto mem_err; } else { - rc = tso_get_head_fragment(&state, efx, skb); - if (rc) - goto mem_err; + /* Payload starts in the header area. */ frag_i = -1; } @@ -1091,6 +1337,11 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, state.unmap_len, DMA_TO_DEVICE); } + /* Free the header DMA mapping, if using option descriptors */ + if (state.header_unmap_len) + dma_unmap_single(&efx->pci_dev->dev, state.header_dma_addr, + state.header_unmap_len, DMA_TO_DEVICE); + efx_enqueue_unwind(tx_queue); return NETDEV_TX_OK; } |