From b6f897d75d651f86a3988a602e767696f9e08de6 Mon Sep 17 00:00:00 2001 From: Tomer Tayar Date: Tue, 5 Mar 2019 16:48:42 +0200 Subject: [PATCH] habanalabs: Move PCI code into common file Move duplicated PCI-related code from ASIC-specific files into the common pci.c file. Signed-off-by: Tomer Tayar Signed-off-by: Oded Gabbay --- drivers/misc/habanalabs/Makefile | 2 +- drivers/misc/habanalabs/goya/goya.c | 272 ++------------- drivers/misc/habanalabs/habanalabs.h | 20 ++ .../habanalabs/include/goya/asic_reg/goya_masks.h | 12 - .../habanalabs/include/hw_ip/pci/pci_general.h | 23 ++ drivers/misc/habanalabs/pci.c | 370 +++++++++++++++++++++ 6 files changed, 434 insertions(+), 265 deletions(-) create mode 100644 drivers/misc/habanalabs/include/hw_ip/pci/pci_general.h create mode 100644 drivers/misc/habanalabs/pci.c diff --git a/drivers/misc/habanalabs/Makefile b/drivers/misc/habanalabs/Makefile index 598740d..f8e8524 100644 --- a/drivers/misc/habanalabs/Makefile +++ b/drivers/misc/habanalabs/Makefile @@ -6,7 +6,7 @@ obj-m := habanalabs.o habanalabs-y := habanalabs_drv.o device.o context.o asid.o habanalabs_ioctl.o \ command_buffer.o hw_queue.o irq.o sysfs.o hwmon.o memory.o \ - command_submission.o mmu.o firmware_if.o + command_submission.o mmu.o firmware_if.o pci.o habanalabs-$(CONFIG_DEBUG_FS) += debugfs.o diff --git a/drivers/misc/habanalabs/goya/goya.c b/drivers/misc/habanalabs/goya/goya.c index 78eacd1..5ce3a34 100644 --- a/drivers/misc/habanalabs/goya/goya.c +++ b/drivers/misc/habanalabs/goya/goya.c @@ -363,12 +363,13 @@ static void goya_get_fixed_properties(struct hl_device *hdev) prop->cfg_size = CFG_SIZE; prop->max_asid = MAX_ASID; prop->num_of_events = GOYA_ASYNC_EVENT_ID_SIZE; + prop->high_pll = PLL_HIGH_DEFAULT; prop->cb_pool_cb_cnt = GOYA_CB_POOL_CB_CNT; prop->cb_pool_cb_size = GOYA_CB_POOL_CB_SIZE; prop->max_power_default = MAX_POWER_DEFAULT; prop->tpc_enabled_mask = TPC_ENABLED_MASK; - - prop->high_pll = PLL_HIGH_DEFAULT; + prop->pcie_dbi_base_address = mmPCIE_DBI_BASE; + prop->pcie_aux_dbi_reg_addr = CFG_BASE + mmPCIE_AUX_DBI; } /* @@ -382,161 +383,20 @@ static void goya_get_fixed_properties(struct hl_device *hdev) */ static int goya_pci_bars_map(struct hl_device *hdev) { - struct pci_dev *pdev = hdev->pdev; + static const char * const name[] = {"SRAM_CFG", "MSIX", "DDR"}; + bool is_wc[3] = {false, false, true}; int rc; - rc = pci_request_regions(pdev, HL_NAME); - if (rc) { - dev_err(hdev->dev, "Cannot obtain PCI resources\n"); + rc = hl_pci_bars_map(hdev, name, is_wc); + if (rc) return rc; - } - - hdev->pcie_bar[SRAM_CFG_BAR_ID] = - pci_ioremap_bar(pdev, SRAM_CFG_BAR_ID); - if (!hdev->pcie_bar[SRAM_CFG_BAR_ID]) { - dev_err(hdev->dev, "pci_ioremap_bar failed for CFG\n"); - rc = -ENODEV; - goto err_release_regions; - } - - hdev->pcie_bar[MSIX_BAR_ID] = pci_ioremap_bar(pdev, MSIX_BAR_ID); - if (!hdev->pcie_bar[MSIX_BAR_ID]) { - dev_err(hdev->dev, "pci_ioremap_bar failed for MSIX\n"); - rc = -ENODEV; - goto err_unmap_sram_cfg; - } - - hdev->pcie_bar[DDR_BAR_ID] = pci_ioremap_wc_bar(pdev, DDR_BAR_ID); - if (!hdev->pcie_bar[DDR_BAR_ID]) { - dev_err(hdev->dev, "pci_ioremap_bar failed for DDR\n"); - rc = -ENODEV; - goto err_unmap_msix; - } hdev->rmmio = hdev->pcie_bar[SRAM_CFG_BAR_ID] + - (CFG_BASE - SRAM_BASE_ADDR); - - return 0; - -err_unmap_msix: - iounmap(hdev->pcie_bar[MSIX_BAR_ID]); -err_unmap_sram_cfg: - iounmap(hdev->pcie_bar[SRAM_CFG_BAR_ID]); -err_release_regions: - pci_release_regions(pdev); - - return rc; -} - -/* - * goya_pci_bars_unmap - Unmap PCI BARS of Goya device - * - * @hdev: pointer to hl_device structure - * - * Release all PCI BARS and unmap their virtual addresses - * - */ -static void goya_pci_bars_unmap(struct hl_device *hdev) -{ - struct pci_dev *pdev = hdev->pdev; - - iounmap(hdev->pcie_bar[DDR_BAR_ID]); - iounmap(hdev->pcie_bar[MSIX_BAR_ID]); - iounmap(hdev->pcie_bar[SRAM_CFG_BAR_ID]); - pci_release_regions(pdev); -} - -/* - * goya_elbi_write - Write through the ELBI interface - * - * @hdev: pointer to hl_device structure - * - * return 0 on success, -1 on failure - * - */ -static int goya_elbi_write(struct hl_device *hdev, u64 addr, u32 data) -{ - struct pci_dev *pdev = hdev->pdev; - ktime_t timeout; - u32 val; - - /* Clear previous status */ - pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, 0); - - pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_ADDR, (u32) addr); - pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_DATA, data); - pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_CTRL, - PCI_CONFIG_ELBI_CTRL_WRITE); - - timeout = ktime_add_ms(ktime_get(), 10); - for (;;) { - pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, &val); - if (val & PCI_CONFIG_ELBI_STS_MASK) - break; - if (ktime_compare(ktime_get(), timeout) > 0) { - pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, - &val); - break; - } - usleep_range(300, 500); - } - - if ((val & PCI_CONFIG_ELBI_STS_MASK) == PCI_CONFIG_ELBI_STS_DONE) - return 0; - - if (val & PCI_CONFIG_ELBI_STS_ERR) { - dev_err(hdev->dev, "Error writing to ELBI\n"); - return -EIO; - } - - if (!(val & PCI_CONFIG_ELBI_STS_MASK)) { - dev_err(hdev->dev, "ELBI write didn't finish in time\n"); - return -EIO; - } - - dev_err(hdev->dev, "ELBI write has undefined bits in status\n"); - return -EIO; -} - -/* - * goya_iatu_write - iatu write routine - * - * @hdev: pointer to hl_device structure - * - */ -static int goya_iatu_write(struct hl_device *hdev, u32 addr, u32 data) -{ - u32 dbi_offset; - int rc; - - dbi_offset = addr & 0xFFF; - - rc = goya_elbi_write(hdev, CFG_BASE + mmPCIE_AUX_DBI, 0x00300000); - rc |= goya_elbi_write(hdev, mmPCIE_DBI_BASE + dbi_offset, data); - - if (rc) - return -EIO; + (CFG_BASE - SRAM_BASE_ADDR); return 0; } -static void goya_reset_link_through_bridge(struct hl_device *hdev) -{ - struct pci_dev *pdev = hdev->pdev; - struct pci_dev *parent_port; - u16 val; - - parent_port = pdev->bus->self; - pci_read_config_word(parent_port, PCI_BRIDGE_CONTROL, &val); - val |= PCI_BRIDGE_CTL_BUS_RESET; - pci_write_config_word(parent_port, PCI_BRIDGE_CONTROL, val); - ssleep(1); - - val &= ~(PCI_BRIDGE_CTL_BUS_RESET); - pci_write_config_word(parent_port, PCI_BRIDGE_CONTROL, val); - ssleep(3); -} - /* * goya_set_ddr_bar_base - set DDR bar to map specific device address * @@ -556,20 +416,9 @@ static int goya_set_ddr_bar_base(struct hl_device *hdev, u64 addr) return 0; /* Inbound Region 1 - Bar 4 - Point to DDR */ - rc = goya_iatu_write(hdev, 0x314, lower_32_bits(addr)); - rc |= goya_iatu_write(hdev, 0x318, upper_32_bits(addr)); - rc |= goya_iatu_write(hdev, 0x300, 0); - /* Enable + Bar match + match enable + Bar 4 */ - rc |= goya_iatu_write(hdev, 0x304, 0xC0080400); - - /* Return the DBI window to the default location */ - rc |= goya_elbi_write(hdev, CFG_BASE + mmPCIE_AUX_DBI, 0); - rc |= goya_elbi_write(hdev, CFG_BASE + mmPCIE_AUX_DBI_32, 0); - - if (rc) { - dev_err(hdev->dev, "failed to map DDR bar to 0x%08llx\n", addr); - return -EIO; - } + rc = hl_pci_set_dram_bar_base(hdev, 1, 4, addr); + if (rc) + return rc; if (goya) goya->ddr_bar_cur_addr = addr; @@ -587,40 +436,8 @@ static int goya_set_ddr_bar_base(struct hl_device *hdev, u64 addr) */ static int goya_init_iatu(struct hl_device *hdev) { - int rc; - - /* Inbound Region 0 - Bar 0 - Point to SRAM_BASE_ADDR */ - rc = goya_iatu_write(hdev, 0x114, lower_32_bits(SRAM_BASE_ADDR)); - rc |= goya_iatu_write(hdev, 0x118, upper_32_bits(SRAM_BASE_ADDR)); - rc |= goya_iatu_write(hdev, 0x100, 0); - /* Enable + Bar match + match enable */ - rc |= goya_iatu_write(hdev, 0x104, 0xC0080000); - - /* Inbound Region 1 - Bar 4 - Point to DDR */ - rc |= goya_set_ddr_bar_base(hdev, DRAM_PHYS_BASE); - - /* Outbound Region 0 - Point to Host */ - rc |= goya_iatu_write(hdev, 0x008, lower_32_bits(HOST_PHYS_BASE)); - rc |= goya_iatu_write(hdev, 0x00C, upper_32_bits(HOST_PHYS_BASE)); - rc |= goya_iatu_write(hdev, 0x010, - lower_32_bits(HOST_PHYS_BASE + HOST_PHYS_SIZE - 1)); - rc |= goya_iatu_write(hdev, 0x014, 0); - rc |= goya_iatu_write(hdev, 0x018, 0); - rc |= goya_iatu_write(hdev, 0x020, - upper_32_bits(HOST_PHYS_BASE + HOST_PHYS_SIZE - 1)); - /* Increase region size */ - rc |= goya_iatu_write(hdev, 0x000, 0x00002000); - /* Enable */ - rc |= goya_iatu_write(hdev, 0x004, 0x80000000); - - /* Return the DBI window to the default location */ - rc |= goya_elbi_write(hdev, CFG_BASE + mmPCIE_AUX_DBI, 0); - rc |= goya_elbi_write(hdev, CFG_BASE + mmPCIE_AUX_DBI_32, 0); - - if (rc) - return -EIO; - - return 0; + return hl_pci_init_iatu(hdev, SRAM_BASE_ADDR, DRAM_PHYS_BASE, + HOST_PHYS_SIZE); } /* @@ -666,52 +483,9 @@ static int goya_early_init(struct hl_device *hdev) prop->dram_pci_bar_size = pci_resource_len(pdev, DDR_BAR_ID); - /* set DMA mask for GOYA */ - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(39)); - if (rc) { - dev_warn(hdev->dev, "Unable to set pci dma mask to 39 bits\n"); - rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); - if (rc) { - dev_err(hdev->dev, - "Unable to set pci dma mask to 32 bits\n"); - return rc; - } - } - - rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39)); - if (rc) { - dev_warn(hdev->dev, - "Unable to set pci consistent dma mask to 39 bits\n"); - rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); - if (rc) { - dev_err(hdev->dev, - "Unable to set pci consistent dma mask to 32 bits\n"); - return rc; - } - } - - if (hdev->reset_pcilink) - goya_reset_link_through_bridge(hdev); - - rc = pci_enable_device_mem(pdev); - if (rc) { - dev_err(hdev->dev, "can't enable PCI device\n"); + rc = hl_pci_init(hdev); + if (rc) return rc; - } - - pci_set_master(pdev); - - rc = goya_init_iatu(hdev); - if (rc) { - dev_err(hdev->dev, "Failed to initialize iATU\n"); - goto disable_device; - } - - rc = goya_pci_bars_map(hdev); - if (rc) { - dev_err(hdev->dev, "Failed to initialize PCI BARS\n"); - goto disable_device; - } if (!hdev->pldm) { val = RREG32(mmPSOC_GLOBAL_CONF_BOOT_STRAP_PINS); @@ -721,12 +495,6 @@ static int goya_early_init(struct hl_device *hdev) } return 0; - -disable_device: - pci_clear_master(pdev); - pci_disable_device(pdev); - - return rc; } /* @@ -739,10 +507,7 @@ disable_device: */ static int goya_early_fini(struct hl_device *hdev) { - goya_pci_bars_unmap(hdev); - - pci_clear_master(hdev->pdev); - pci_disable_device(hdev->pdev); + hl_pci_fini(hdev); return 0; } @@ -5071,7 +4836,10 @@ static const struct hl_asic_funcs goya_funcs = { .get_pci_id = goya_get_pci_id, .get_eeprom_data = goya_get_eeprom_data, .send_cpu_message = goya_send_cpu_message, - .get_hw_state = goya_get_hw_state + .get_hw_state = goya_get_hw_state, + .pci_bars_map = goya_pci_bars_map, + .set_dram_bar_base = goya_set_ddr_bar_base, + .init_iatu = goya_init_iatu }; /* diff --git a/drivers/misc/habanalabs/habanalabs.h b/drivers/misc/habanalabs/habanalabs.h index 1445ba1c..ed3649d 100644 --- a/drivers/misc/habanalabs/habanalabs.h +++ b/drivers/misc/habanalabs/habanalabs.h @@ -148,6 +148,8 @@ enum hl_device_hw_state { * mapping DRAM memory. * @dram_size_for_default_page_mapping: DRAM size needed to map to avoid page * fault. + * @pcie_dbi_base_address: Base address of the PCIE_DBI block. + * @pcie_aux_dbi_reg_addr: Address of the PCIE_AUX DBI register. * @mmu_pgt_addr: base physical address in DRAM of MMU page tables. * @mmu_dram_default_page_addr: DRAM default page physical address. * @mmu_pgt_size: MMU page tables total size. @@ -189,6 +191,8 @@ struct asic_fixed_properties { u64 va_space_dram_start_address; u64 va_space_dram_end_address; u64 dram_size_for_default_page_mapping; + u64 pcie_dbi_base_address; + u64 pcie_aux_dbi_reg_addr; u64 mmu_pgt_addr; u64 mmu_dram_default_page_addr; u32 mmu_pgt_size; @@ -485,6 +489,9 @@ enum hl_pll_frequency { * @get_eeprom_data: retrieve EEPROM data from F/W. * @send_cpu_message: send buffer to ArmCP. * @get_hw_state: retrieve the H/W state + * @pci_bars_map: Map PCI BARs. + * @set_dram_bar_base: Set DRAM BAR to map specific device address. + * @init_iatu: Initialize the iATU unit inside the PCI controller. */ struct hl_asic_funcs { int (*early_init)(struct hl_device *hdev); @@ -558,6 +565,9 @@ struct hl_asic_funcs { int (*send_cpu_message)(struct hl_device *hdev, u32 *msg, u16 len, u32 timeout, long *result); enum hl_device_hw_state (*get_hw_state)(struct hl_device *hdev); + int (*pci_bars_map)(struct hl_device *hdev); + int (*set_dram_bar_base)(struct hl_device *hdev, u64 addr); + int (*init_iatu)(struct hl_device *hdev); }; @@ -1368,6 +1378,16 @@ int hl_fw_send_heartbeat(struct hl_device *hdev); int hl_fw_armcp_info_get(struct hl_device *hdev); int hl_fw_get_eeprom_data(struct hl_device *hdev, void *data, size_t max_size); +int hl_pci_bars_map(struct hl_device *hdev, const char * const name[3], + bool is_wc[3]); +int hl_pci_iatu_write(struct hl_device *hdev, u32 addr, u32 data); +int hl_pci_set_dram_bar_base(struct hl_device *hdev, u8 inbound_region, u8 bar, + u64 addr); +int hl_pci_init_iatu(struct hl_device *hdev, u64 sram_base_address, + u64 dram_base_address, u64 host_phys_size); +int hl_pci_init(struct hl_device *hdev); +void hl_pci_fini(struct hl_device *hdev); + long hl_get_frequency(struct hl_device *hdev, u32 pll_index, bool curr); void hl_set_frequency(struct hl_device *hdev, u32 pll_index, u64 freq); long hl_get_temperature(struct hl_device *hdev, int sensor_index, u32 attr); diff --git a/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h b/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h index a161ecf..8618891 100644 --- a/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h +++ b/drivers/misc/habanalabs/include/goya/asic_reg/goya_masks.h @@ -189,18 +189,6 @@ 1 << CPU_CA53_CFG_ARM_RST_CONTROL_NL2RESET_SHIFT |\ 1 << CPU_CA53_CFG_ARM_RST_CONTROL_NMBISTRESET_SHIFT) -/* PCI CONFIGURATION SPACE */ -#define mmPCI_CONFIG_ELBI_ADDR 0xFF0 -#define mmPCI_CONFIG_ELBI_DATA 0xFF4 -#define mmPCI_CONFIG_ELBI_CTRL 0xFF8 -#define PCI_CONFIG_ELBI_CTRL_WRITE (1 << 31) - -#define mmPCI_CONFIG_ELBI_STS 0xFFC -#define PCI_CONFIG_ELBI_STS_ERR (1 << 30) -#define PCI_CONFIG_ELBI_STS_DONE (1 << 31) -#define PCI_CONFIG_ELBI_STS_MASK (PCI_CONFIG_ELBI_STS_ERR | \ - PCI_CONFIG_ELBI_STS_DONE) - #define GOYA_IRQ_HBW_ID_MASK 0x1FFF #define GOYA_IRQ_HBW_ID_SHIFT 0 #define GOYA_IRQ_HBW_INTERNAL_ID_MASK 0xE000 diff --git a/drivers/misc/habanalabs/include/hw_ip/pci/pci_general.h b/drivers/misc/habanalabs/include/hw_ip/pci/pci_general.h new file mode 100644 index 0000000..d232081d --- /dev/null +++ b/drivers/misc/habanalabs/include/hw_ip/pci/pci_general.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * Copyright 2016-2019 HabanaLabs, Ltd. + * All Rights Reserved. + * + */ + +#ifndef INCLUDE_PCI_GENERAL_H_ +#define INCLUDE_PCI_GENERAL_H_ + +/* PCI CONFIGURATION SPACE */ +#define mmPCI_CONFIG_ELBI_ADDR 0xFF0 +#define mmPCI_CONFIG_ELBI_DATA 0xFF4 +#define mmPCI_CONFIG_ELBI_CTRL 0xFF8 +#define PCI_CONFIG_ELBI_CTRL_WRITE (1 << 31) + +#define mmPCI_CONFIG_ELBI_STS 0xFFC +#define PCI_CONFIG_ELBI_STS_ERR (1 << 30) +#define PCI_CONFIG_ELBI_STS_DONE (1 << 31) +#define PCI_CONFIG_ELBI_STS_MASK (PCI_CONFIG_ELBI_STS_ERR | \ + PCI_CONFIG_ELBI_STS_DONE) + +#endif /* INCLUDE_PCI_GENERAL_H_ */ diff --git a/drivers/misc/habanalabs/pci.c b/drivers/misc/habanalabs/pci.c new file mode 100644 index 0000000..822ac11 --- /dev/null +++ b/drivers/misc/habanalabs/pci.c @@ -0,0 +1,370 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright 2016-2019 HabanaLabs, Ltd. + * All Rights Reserved. + */ + +#include "habanalabs.h" +#include "include/hw_ip/pci/pci_general.h" + +#include + +/** + * hl_pci_bars_map() - Map PCI BARs. + * @hdev: Pointer to hl_device structure. + * @bar_name: Array of BAR names. + * @is_wc: Array with flag per BAR whether a write-combined mapping is needed. + * + * Request PCI regions and map them to kernel virtual addresses. + * + * Return: 0 on success, non-zero for failure. + */ +int hl_pci_bars_map(struct hl_device *hdev, const char * const name[3], + bool is_wc[3]) +{ + struct pci_dev *pdev = hdev->pdev; + int rc, i, bar; + + rc = pci_request_regions(pdev, HL_NAME); + if (rc) { + dev_err(hdev->dev, "Cannot obtain PCI resources\n"); + return rc; + } + + for (i = 0 ; i < 3 ; i++) { + bar = i * 2; /* 64-bit BARs */ + hdev->pcie_bar[bar] = is_wc[i] ? + pci_ioremap_wc_bar(pdev, bar) : + pci_ioremap_bar(pdev, bar); + if (!hdev->pcie_bar[bar]) { + dev_err(hdev->dev, "pci_ioremap%s_bar failed for %s\n", + is_wc[i] ? "_wc" : "", name[i]); + rc = -ENODEV; + goto err; + } + } + + return 0; + +err: + for (i = 2 ; i >= 0 ; i--) { + bar = i * 2; /* 64-bit BARs */ + if (hdev->pcie_bar[bar]) + iounmap(hdev->pcie_bar[bar]); + } + + pci_release_regions(pdev); + + return rc; +} + +/* + * hl_pci_bars_unmap() - Unmap PCI BARS. + * @hdev: Pointer to hl_device structure. + * + * Release all PCI BARs and unmap their virtual addresses. + */ +static void hl_pci_bars_unmap(struct hl_device *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int i, bar; + + for (i = 2 ; i >= 0 ; i--) { + bar = i * 2; /* 64-bit BARs */ + iounmap(hdev->pcie_bar[bar]); + } + + pci_release_regions(pdev); +} + +/* + * hl_pci_elbi_write() - Write through the ELBI interface. + * @hdev: Pointer to hl_device structure. + * + * Return: 0 on success, negative value for failure. + */ +static int hl_pci_elbi_write(struct hl_device *hdev, u64 addr, u32 data) +{ + struct pci_dev *pdev = hdev->pdev; + ktime_t timeout; + u32 val; + + /* Clear previous status */ + pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, 0); + + pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_ADDR, (u32) addr); + pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_DATA, data); + pci_write_config_dword(pdev, mmPCI_CONFIG_ELBI_CTRL, + PCI_CONFIG_ELBI_CTRL_WRITE); + + timeout = ktime_add_ms(ktime_get(), 10); + for (;;) { + pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, &val); + if (val & PCI_CONFIG_ELBI_STS_MASK) + break; + if (ktime_compare(ktime_get(), timeout) > 0) { + pci_read_config_dword(pdev, mmPCI_CONFIG_ELBI_STS, + &val); + break; + } + + usleep_range(300, 500); + } + + if ((val & PCI_CONFIG_ELBI_STS_MASK) == PCI_CONFIG_ELBI_STS_DONE) + return 0; + + if (val & PCI_CONFIG_ELBI_STS_ERR) { + dev_err(hdev->dev, "Error writing to ELBI\n"); + return -EIO; + } + + if (!(val & PCI_CONFIG_ELBI_STS_MASK)) { + dev_err(hdev->dev, "ELBI write didn't finish in time\n"); + return -EIO; + } + + dev_err(hdev->dev, "ELBI write has undefined bits in status\n"); + return -EIO; +} + +/** + * hl_pci_iatu_write() - iatu write routine. + * @hdev: Pointer to hl_device structure. + * + * Return: 0 on success, negative value for failure. + */ +int hl_pci_iatu_write(struct hl_device *hdev, u32 addr, u32 data) +{ + struct asic_fixed_properties *prop = &hdev->asic_prop; + u32 dbi_offset; + int rc; + + dbi_offset = addr & 0xFFF; + + rc = hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0x00300000); + rc |= hl_pci_elbi_write(hdev, prop->pcie_dbi_base_address + dbi_offset, + data); + + if (rc) + return -EIO; + + return 0; +} + +/* + * hl_pci_reset_link_through_bridge() - Reset PCI link. + * @hdev: Pointer to hl_device structure. + */ +static void hl_pci_reset_link_through_bridge(struct hl_device *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + struct pci_dev *parent_port; + u16 val; + + parent_port = pdev->bus->self; + pci_read_config_word(parent_port, PCI_BRIDGE_CONTROL, &val); + val |= PCI_BRIDGE_CTL_BUS_RESET; + pci_write_config_word(parent_port, PCI_BRIDGE_CONTROL, val); + ssleep(1); + + val &= ~(PCI_BRIDGE_CTL_BUS_RESET); + pci_write_config_word(parent_port, PCI_BRIDGE_CONTROL, val); + ssleep(3); +} + +/** + * hl_pci_set_dram_bar_base() - Set DDR BAR to map specific device address. + * @hdev: Pointer to hl_device structure. + * @inbound_region: Inbound region number. + * @bar: PCI BAR number. + * @addr: Address in DRAM. Must be aligned to DRAM bar size. + * + * Configure the iATU so that the DRAM bar will start at the specified address. + * + * Return: 0 on success, negative value for failure. + */ +int hl_pci_set_dram_bar_base(struct hl_device *hdev, u8 inbound_region, u8 bar, + u64 addr) +{ + struct asic_fixed_properties *prop = &hdev->asic_prop; + u32 offset; + int rc; + + switch (inbound_region) { + case 0: + offset = 0x100; + break; + case 1: + offset = 0x300; + break; + case 2: + offset = 0x500; + break; + default: + dev_err(hdev->dev, "Invalid inbound region %d\n", + inbound_region); + return -EINVAL; + } + + if (bar != 0 && bar != 2 && bar != 4) { + dev_err(hdev->dev, "Invalid PCI BAR %d\n", bar); + return -EINVAL; + } + + /* Point to the specified address */ + rc = hl_pci_iatu_write(hdev, offset + 0x14, lower_32_bits(addr)); + rc |= hl_pci_iatu_write(hdev, offset + 0x18, upper_32_bits(addr)); + rc |= hl_pci_iatu_write(hdev, offset + 0x0, 0); + /* Enable + BAR match + match enable + BAR number */ + rc |= hl_pci_iatu_write(hdev, offset + 0x4, 0xC0080000 | (bar << 8)); + + /* Return the DBI window to the default location */ + rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0); + rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr + 4, 0); + + if (rc) + dev_err(hdev->dev, "failed to map DRAM bar to 0x%08llx\n", + addr); + + return rc; +} + +/** + * hl_pci_init_iatu() - Initialize the iATU unit inside the PCI controller. + * @hdev: Pointer to hl_device structure. + * @sram_base_address: SRAM base address. + * @dram_base_address: DRAM base address. + * @host_phys_size: Size of host memory for device transactions. + * + * This is needed in case the firmware doesn't initialize the iATU. + * + * Return: 0 on success, negative value for failure. + */ +int hl_pci_init_iatu(struct hl_device *hdev, u64 sram_base_address, + u64 dram_base_address, u64 host_phys_size) +{ + struct asic_fixed_properties *prop = &hdev->asic_prop; + u64 host_phys_end_addr; + int rc = 0; + + /* Inbound Region 0 - Bar 0 - Point to SRAM base address */ + rc = hl_pci_iatu_write(hdev, 0x114, lower_32_bits(sram_base_address)); + rc |= hl_pci_iatu_write(hdev, 0x118, upper_32_bits(sram_base_address)); + rc |= hl_pci_iatu_write(hdev, 0x100, 0); + /* Enable + Bar match + match enable */ + rc |= hl_pci_iatu_write(hdev, 0x104, 0xC0080000); + + /* Point to DRAM */ + if (!hdev->asic_funcs->set_dram_bar_base) + return -EINVAL; + rc |= hdev->asic_funcs->set_dram_bar_base(hdev, dram_base_address); + + /* Outbound Region 0 - Point to Host */ + host_phys_end_addr = prop->host_phys_base_address + host_phys_size - 1; + rc |= hl_pci_iatu_write(hdev, 0x008, + lower_32_bits(prop->host_phys_base_address)); + rc |= hl_pci_iatu_write(hdev, 0x00C, + upper_32_bits(prop->host_phys_base_address)); + rc |= hl_pci_iatu_write(hdev, 0x010, lower_32_bits(host_phys_end_addr)); + rc |= hl_pci_iatu_write(hdev, 0x014, 0); + rc |= hl_pci_iatu_write(hdev, 0x018, 0); + rc |= hl_pci_iatu_write(hdev, 0x020, upper_32_bits(host_phys_end_addr)); + /* Increase region size */ + rc |= hl_pci_iatu_write(hdev, 0x000, 0x00002000); + /* Enable */ + rc |= hl_pci_iatu_write(hdev, 0x004, 0x80000000); + + /* Return the DBI window to the default location */ + rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr, 0); + rc |= hl_pci_elbi_write(hdev, prop->pcie_aux_dbi_reg_addr + 4, 0); + + if (rc) + return -EIO; + + return 0; +} + +/** + * hl_pci_init() - PCI initialization code. + * @hdev: Pointer to hl_device structure. + * + * Set DMA masks, initialize the PCI controller and map the PCI BARs. + * + * Return: 0 on success, non-zero for failure. + */ +int hl_pci_init(struct hl_device *hdev) +{ + struct pci_dev *pdev = hdev->pdev; + int rc; + + /* set DMA mask */ + rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(39)); + if (rc) { + dev_warn(hdev->dev, "Unable to set pci dma mask to 39 bits\n"); + rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + if (rc) { + dev_err(hdev->dev, + "Unable to set pci dma mask to 32 bits\n"); + return rc; + } + } + + rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(39)); + if (rc) { + dev_warn(hdev->dev, + "Unable to set pci consistent dma mask to 39 bits\n"); + rc = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + if (rc) { + dev_err(hdev->dev, + "Unable to set pci consistent dma mask to 32 bits\n"); + return rc; + } + } + + if (hdev->reset_pcilink) + hl_pci_reset_link_through_bridge(hdev); + + rc = pci_enable_device_mem(pdev); + if (rc) { + dev_err(hdev->dev, "can't enable PCI device\n"); + return rc; + } + + pci_set_master(pdev); + + rc = hdev->asic_funcs->init_iatu(hdev); + if (rc) { + dev_err(hdev->dev, "Failed to initialize iATU\n"); + goto disable_device; + } + + rc = hdev->asic_funcs->pci_bars_map(hdev); + if (rc) { + dev_err(hdev->dev, "Failed to initialize PCI BARs\n"); + goto disable_device; + } + + return 0; + +disable_device: + pci_clear_master(pdev); + pci_disable_device(pdev); + + return rc; +} + +/** + * hl_fw_fini() - PCI finalization code. + * @hdev: Pointer to hl_device structure + * + * Unmap PCI bars and disable PCI device. + */ +void hl_pci_fini(struct hl_device *hdev) +{ + hl_pci_bars_unmap(hdev); + + pci_clear_master(hdev->pdev); + pci_disable_device(hdev->pdev); +} -- 2.7.4