From: Alejandro Lucero A PIO buffer is a region of device memory to which the driver can write a packet for TX, with the device handling the transmit doorbell without requiring a DMA for getting the packet data, which helps reducing latency in certain exchanges. With CXL mem protocol this latency can be lowered further. With a device supporting CXL and successfully initialised, use the cxl region to map the memory range and use this mapping for PIO buffers. Add the disabling of those CXL-based PIO buffers if the callback for potential cxl endpoint removal by the CXL code happens. Signed-off-by: Alejandro Lucero --- drivers/net/ethernet/sfc/ef10.c | 50 +++++++++++++++++++++++---- drivers/net/ethernet/sfc/efx.h | 1 - drivers/net/ethernet/sfc/efx_cxl.c | 31 ++++++++++++++--- drivers/net/ethernet/sfc/net_driver.h | 2 ++ drivers/net/ethernet/sfc/nic.h | 3 ++ 5 files changed, 75 insertions(+), 12 deletions(-) diff --git a/drivers/net/ethernet/sfc/ef10.c b/drivers/net/ethernet/sfc/ef10.c index 47349c148c0c..1a13fdbbc1b3 100644 --- a/drivers/net/ethernet/sfc/ef10.c +++ b/drivers/net/ethernet/sfc/ef10.c @@ -24,6 +24,7 @@ #include #include #include +#include "efx_cxl.h" /* Hardware control for EF10 architecture including 'Huntington'. */ @@ -106,7 +107,7 @@ static int efx_ef10_get_vf_index(struct efx_nic *efx) static int efx_ef10_init_datapath_caps(struct efx_nic *efx) { - MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CAPABILITIES_V4_OUT_LEN); + MCDI_DECLARE_BUF(outbuf, MC_CMD_GET_CAPABILITIES_V7_OUT_LEN); struct efx_ef10_nic_data *nic_data = efx->nic_data; size_t outlen; int rc; @@ -177,6 +178,12 @@ static int efx_ef10_init_datapath_caps(struct efx_nic *efx) efx->num_mac_stats); } + if (outlen < MC_CMD_GET_CAPABILITIES_V7_OUT_LEN) + nic_data->datapath_caps3 = 0; + else + nic_data->datapath_caps3 = MCDI_DWORD(outbuf, + GET_CAPABILITIES_V7_OUT_FLAGS3); + return 0; } @@ -919,6 +926,9 @@ static void efx_ef10_forget_old_piobufs(struct efx_nic *efx) static void efx_ef10_remove(struct efx_nic *efx) { struct efx_ef10_nic_data *nic_data = efx->nic_data; +#ifdef CONFIG_SFC_CXL + struct efx_probe_data *probe_data; +#endif int rc; #ifdef CONFIG_SFC_SRIOV @@ -949,7 +959,12 @@ static void efx_ef10_remove(struct efx_nic *efx) efx_mcdi_rx_free_indir_table(efx); +#ifdef CONFIG_SFC_CXL + probe_data = container_of(efx, struct efx_probe_data, efx); + if (nic_data->wc_membase && !probe_data->cxl_pio_in_use) +#else if (nic_data->wc_membase) +#endif iounmap(nic_data->wc_membase); rc = efx_mcdi_free_vis(efx); @@ -1140,6 +1155,9 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx) unsigned int channel_vis, pio_write_vi_base, max_vis; struct efx_ef10_nic_data *nic_data = efx->nic_data; unsigned int uc_mem_map_size, wc_mem_map_size; +#ifdef CONFIG_SFC_CXL + struct efx_probe_data *probe_data; +#endif void __iomem *membase; int rc; @@ -1263,8 +1281,25 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx) iounmap(efx->membase); efx->membase = membase; - /* Set up the WC mapping if needed */ - if (wc_mem_map_size) { + if (!wc_mem_map_size) + goto skip_pio; + + /* Set up the WC mapping */ + +#ifdef CONFIG_SFC_CXL + probe_data = container_of(efx, struct efx_probe_data, efx); + if ((nic_data->datapath_caps3 & + (1 << MC_CMD_GET_CAPABILITIES_V7_OUT_CXL_CONFIG_ENABLE_LBN)) && + probe_data->cxl_pio_initialised) { + /* Using PIO through CXL mapping? */ + nic_data->pio_write_base = probe_data->cxl->ctpio_cxl + + (pio_write_vi_base * efx->vi_stride + + ER_DZ_TX_PIOBUF - uc_mem_map_size); + probe_data->cxl_pio_in_use = true; + } else +#endif + { + /* Using legacy PIO BAR mapping */ nic_data->wc_membase = ioremap_wc(efx->membase_phys + uc_mem_map_size, wc_mem_map_size); @@ -1279,12 +1314,13 @@ static int efx_ef10_dimension_resources(struct efx_nic *efx) nic_data->wc_membase + (pio_write_vi_base * efx->vi_stride + ER_DZ_TX_PIOBUF - uc_mem_map_size); - - rc = efx_ef10_link_piobufs(efx); - if (rc) - efx_ef10_free_piobufs(efx); } + rc = efx_ef10_link_piobufs(efx); + if (rc) + efx_ef10_free_piobufs(efx); + +skip_pio: 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, diff --git a/drivers/net/ethernet/sfc/efx.h b/drivers/net/ethernet/sfc/efx.h index 45e191686625..057d30090894 100644 --- a/drivers/net/ethernet/sfc/efx.h +++ b/drivers/net/ethernet/sfc/efx.h @@ -236,5 +236,4 @@ static inline bool efx_rwsem_assert_write_locked(struct rw_semaphore *sem) int efx_xdp_tx_buffers(struct efx_nic *efx, int n, struct xdp_frame **xdpfs, bool flush); - #endif /* EFX_EFX_H */ diff --git a/drivers/net/ethernet/sfc/efx_cxl.c b/drivers/net/ethernet/sfc/efx_cxl.c index 79fe99d83f9f..a84ce45398c1 100644 --- a/drivers/net/ethernet/sfc/efx_cxl.c +++ b/drivers/net/ethernet/sfc/efx_cxl.c @@ -11,6 +11,7 @@ #include #include "net_driver.h" #include "efx_cxl.h" +#include "efx.h" #define EFX_CTPIO_BUFFER_SIZE SZ_256M @@ -20,6 +21,7 @@ int efx_cxl_init(struct efx_probe_data *probe_data) struct pci_dev *pci_dev = efx->pci_dev; resource_size_t max_size; struct efx_cxl *cxl; + struct range range; u16 dvsec; int rc; @@ -119,19 +121,40 @@ int efx_cxl_init(struct efx_probe_data *probe_data) cxl->efx_region = cxl_create_region(cxl->cxlrd, &cxl->cxled, 1); if (IS_ERR(cxl->efx_region)) { pci_err(pci_dev, "CXL accel create region failed"); - cxl_put_root_decoder(cxl->cxlrd); - cxl_dpa_free(cxl->cxled); - return PTR_ERR(cxl->efx_region); + rc = PTR_ERR(cxl->efx_region); + goto err_dpa; + } + + rc = cxl_get_region_range(cxl->efx_region, &range); + if (rc) { + pci_err(pci_dev, "CXL getting regions params failed"); + goto err_detach; + } + + cxl->ctpio_cxl = ioremap(range.start, range.end - range.start + 1); + if (!cxl->ctpio_cxl) { + pci_err(pci_dev, "CXL ioremap region (%pra) failed", &range); + rc = -ENOMEM; + goto err_detach; } probe_data->cxl = cxl; + probe_data->cxl_pio_initialised = true; return 0; + +err_detach: + cxl_decoder_detach(NULL, cxl->cxled, 0, DETACH_INVALIDATE); +err_dpa: + cxl_put_root_decoder(cxl->cxlrd); + cxl_dpa_free(cxl->cxled); + return rc; } void efx_cxl_exit(struct efx_probe_data *probe_data) { - if (probe_data->cxl) { + if (probe_data->cxl_pio_initialised) { + iounmap(probe_data->cxl->ctpio_cxl); cxl_decoder_detach(NULL, probe_data->cxl->cxled, 0, DETACH_INVALIDATE); cxl_dpa_free(probe_data->cxl->cxled); diff --git a/drivers/net/ethernet/sfc/net_driver.h b/drivers/net/ethernet/sfc/net_driver.h index 0e685b8a9980..894b62d6ada9 100644 --- a/drivers/net/ethernet/sfc/net_driver.h +++ b/drivers/net/ethernet/sfc/net_driver.h @@ -1209,6 +1209,7 @@ struct efx_cxl; * @efx: Efx NIC details * @cxl: details of related cxl objects * @cxl_pio_initialised: cxl initialization outcome. + * @cxl_pio_in_use: PIO using CXL mapping */ struct efx_probe_data { struct pci_dev *pci_dev; @@ -1216,6 +1217,7 @@ struct efx_probe_data { #ifdef CONFIG_SFC_CXL struct efx_cxl *cxl; bool cxl_pio_initialised; + bool cxl_pio_in_use; #endif }; diff --git a/drivers/net/ethernet/sfc/nic.h b/drivers/net/ethernet/sfc/nic.h index 9fa5c4c713ab..c87cc9214690 100644 --- a/drivers/net/ethernet/sfc/nic.h +++ b/drivers/net/ethernet/sfc/nic.h @@ -152,6 +152,8 @@ enum { * %MC_CMD_GET_CAPABILITIES response) * @datapath_caps2: Further Capabilities of datapath firmware (FLAGS2 field of * %MC_CMD_GET_CAPABILITIES response) + * @datapath_caps3: Further Capabilities of datapath firmware (FLAGS3 field of + * %MC_CMD_GET_CAPABILITIES response) * @rx_dpcpu_fw_id: Firmware ID of the RxDPCPU * @tx_dpcpu_fw_id: Firmware ID of the TxDPCPU * @must_probe_vswitching: Flag: vswitching has yet to be setup after MC reboot @@ -186,6 +188,7 @@ struct efx_ef10_nic_data { bool must_check_datapath_caps; u32 datapath_caps; u32 datapath_caps2; + u32 datapath_caps3; unsigned int rx_dpcpu_fw_id; unsigned int tx_dpcpu_fw_id; bool must_probe_vswitching; -- 2.34.1