diff options
Diffstat (limited to 'drivers/pci/controller')
92 files changed, 58548 insertions, 0 deletions
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig new file mode 100644 index 000000000..bfd9bac37 --- /dev/null +++ b/drivers/pci/controller/Kconfig @@ -0,0 +1,349 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "PCI controller drivers" + depends on PCI + +config PCI_MVEBU + tristate "Marvell EBU PCIe controller" + depends on ARCH_MVEBU || ARCH_DOVE || COMPILE_TEST + depends on MVEBU_MBUS + depends on ARM + depends on OF + select PCI_BRIDGE_EMUL + help + Add support for Marvell EBU PCIe controller. This PCIe controller + is used on 32-bit Marvell ARM SoCs: Dove, Kirkwood, Armada 370, + Armada XP, Armada 375, Armada 38x and Armada 39x. + +config PCI_AARDVARK + tristate "Aardvark PCIe controller" + depends on (ARCH_MVEBU && ARM64) || COMPILE_TEST + depends on OF + depends on PCI_MSI_IRQ_DOMAIN + select PCI_BRIDGE_EMUL + help + Add support for Aardvark 64bit PCIe Host Controller. This + controller is part of the South Bridge of the Marvel Armada + 3700 SoC. + +config PCIE_XILINX_NWL + bool "NWL PCIe Core" + depends on ARCH_ZYNQMP || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + help + Say 'Y' here if you want kernel support for Xilinx + NWL PCIe controller. The controller can act as Root Port + or End Point. The current option selection will only + support root port enabling. + +config PCI_FTPCI100 + bool "Faraday Technology FTPCI100 PCI controller" + depends on OF + default ARCH_GEMINI + +config PCI_IXP4XX + bool "Intel IXP4xx PCI controller" + depends on ARM && OF + depends on ARCH_IXP4XX || COMPILE_TEST + default ARCH_IXP4XX + help + Say Y here if you want support for the PCI host controller found + in the Intel IXP4xx XScale-based network processor SoC. + +config PCI_TEGRA + bool "NVIDIA Tegra PCIe controller" + depends on ARCH_TEGRA || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + help + Say Y here if you want support for the PCIe host controller found + on NVIDIA Tegra SoCs. + +config PCI_RCAR_GEN2 + bool "Renesas R-Car Gen2 Internal PCI controller" + depends on ARCH_RENESAS || COMPILE_TEST + depends on ARM + help + Say Y here if you want internal PCI support on R-Car Gen2 SoC. + There are 3 internal PCI controllers available with a single + built-in EHCI/OHCI host controller present on each one. + +config PCIE_RCAR_HOST + bool "Renesas R-Car PCIe host controller" + depends on ARCH_RENESAS || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + help + Say Y here if you want PCIe controller support on R-Car SoCs in host + mode. + +config PCIE_RCAR_EP + bool "Renesas R-Car PCIe endpoint controller" + depends on ARCH_RENESAS || COMPILE_TEST + depends on PCI_ENDPOINT + help + Say Y here if you want PCIe controller support on R-Car SoCs in + endpoint mode. + +config PCI_HOST_COMMON + tristate + select PCI_ECAM + +config PCI_HOST_GENERIC + tristate "Generic PCI host controller" + depends on OF + select PCI_HOST_COMMON + select IRQ_DOMAIN + help + Say Y here if you want to support a simple generic PCI host + controller, such as the one emulated by kvmtool. + +config PCIE_XILINX + bool "Xilinx AXI PCIe host bridge support" + depends on OF || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + help + Say 'Y' here if you want kernel to support the Xilinx AXI PCIe + Host Bridge driver. + +config PCIE_XILINX_CPM + bool "Xilinx Versal CPM host bridge support" + depends on ARCH_ZYNQMP || COMPILE_TEST + select PCI_HOST_COMMON + help + Say 'Y' here if you want kernel support for the + Xilinx Versal CPM host bridge. + +config PCI_XGENE + bool "X-Gene PCIe controller" + depends on ARM64 || COMPILE_TEST + depends on OF || (ACPI && PCI_QUIRKS) + help + Say Y here if you want internal PCI support on APM X-Gene SoC. + There are 5 internal PCIe ports available. Each port is GEN3 capable + and have varied lanes from x1 to x8. + +config PCI_XGENE_MSI + bool "X-Gene v1 PCIe MSI feature" + depends on PCI_XGENE + depends on PCI_MSI_IRQ_DOMAIN + default y + help + Say Y here if you want PCIe MSI support for the APM X-Gene v1 SoC. + This MSI driver supports 5 PCIe ports on the APM X-Gene v1 SoC. + +config PCI_V3_SEMI + bool "V3 Semiconductor PCI controller" + depends on OF + depends on ARM || COMPILE_TEST + default ARCH_INTEGRATOR_AP + +config PCI_VERSATILE + bool "ARM Versatile PB PCI controller" + depends on ARCH_VERSATILE || COMPILE_TEST + +config PCIE_IPROC + tristate + help + This enables the iProc PCIe core controller support for Broadcom's + iProc family of SoCs. An appropriate bus interface driver needs + to be enabled to select this. + +config PCIE_IPROC_PLATFORM + tristate "Broadcom iProc PCIe platform bus driver" + depends on ARCH_BCM_IPROC || (ARM && COMPILE_TEST) + depends on OF + select PCIE_IPROC + default ARCH_BCM_IPROC + help + Say Y here if you want to use the Broadcom iProc PCIe controller + through the generic platform bus interface + +config PCIE_IPROC_BCMA + tristate "Broadcom iProc PCIe BCMA bus driver" + depends on ARM && (ARCH_BCM_IPROC || COMPILE_TEST) + select PCIE_IPROC + select BCMA + default ARCH_BCM_5301X + help + Say Y here if you want to use the Broadcom iProc PCIe controller + through the BCMA bus interface + +config PCIE_IPROC_MSI + bool "Broadcom iProc PCIe MSI support" + depends on PCIE_IPROC_PLATFORM || PCIE_IPROC_BCMA + depends on PCI_MSI_IRQ_DOMAIN + default ARCH_BCM_IPROC + help + Say Y here if you want to enable MSI support for Broadcom's iProc + PCIe controller + +config PCIE_ALTERA + tristate "Altera PCIe controller" + depends on ARM || NIOS2 || ARM64 || COMPILE_TEST + help + Say Y here if you want to enable PCIe controller support on Altera + FPGA. + +config PCIE_ALTERA_MSI + tristate "Altera PCIe MSI feature" + depends on PCIE_ALTERA + depends on PCI_MSI_IRQ_DOMAIN + help + Say Y here if you want PCIe MSI support for the Altera FPGA. + This MSI driver supports Altera MSI to GIC controller IP. + +config PCI_HOST_THUNDER_PEM + bool "Cavium Thunder PCIe controller to off-chip devices" + depends on ARM64 || COMPILE_TEST + depends on OF || (ACPI && PCI_QUIRKS) + select PCI_HOST_COMMON + help + Say Y here if you want PCIe support for CN88XX Cavium Thunder SoCs. + +config PCI_HOST_THUNDER_ECAM + bool "Cavium Thunder ECAM controller to on-chip devices on pass-1.x silicon" + depends on ARM64 || COMPILE_TEST + depends on OF || (ACPI && PCI_QUIRKS) + select PCI_HOST_COMMON + help + Say Y here if you want ECAM support for CN88XX-Pass-1.x Cavium Thunder SoCs. + +config PCIE_ROCKCHIP + bool + depends on PCI + +config PCIE_ROCKCHIP_HOST + tristate "Rockchip PCIe host controller" + depends on ARCH_ROCKCHIP || COMPILE_TEST + depends on OF + depends on PCI_MSI_IRQ_DOMAIN + select MFD_SYSCON + select PCIE_ROCKCHIP + help + Say Y here if you want internal PCI support on Rockchip SoC. + There is 1 internal PCIe port available to support GEN2 with + 4 slots. + +config PCIE_ROCKCHIP_EP + bool "Rockchip PCIe endpoint controller" + depends on ARCH_ROCKCHIP || COMPILE_TEST + depends on OF + depends on PCI_ENDPOINT + select MFD_SYSCON + select PCIE_ROCKCHIP + help + Say Y here if you want to support Rockchip PCIe controller in + endpoint mode on Rockchip SoC. There is 1 internal PCIe port + available to support GEN2 with 4 slots. + +config PCIE_MEDIATEK + tristate "MediaTek PCIe controller" + depends on ARCH_AIROHA || ARCH_MEDIATEK || COMPILE_TEST + depends on OF + depends on PCI_MSI_IRQ_DOMAIN + help + Say Y here if you want to enable PCIe controller support on + MediaTek SoCs. + +config PCIE_MEDIATEK_GEN3 + tristate "MediaTek Gen3 PCIe controller" + depends on ARCH_MEDIATEK || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + help + Adds support for PCIe Gen3 MAC controller for MediaTek SoCs. + This PCIe controller is compatible with Gen3, Gen2 and Gen1 speed, + and support up to 256 MSI interrupt numbers for + multi-function devices. + + Say Y here if you want to enable Gen3 PCIe controller support on + MediaTek SoCs. + +config VMD + depends on PCI_MSI && X86_64 && SRCU && !UML + tristate "Intel Volume Management Device Driver" + help + Adds support for the Intel Volume Management Device (VMD). VMD is a + secondary PCI host bridge that allows PCI Express root ports, + and devices attached to them, to be removed from the default + PCI domain and placed within the VMD domain. This provides + more bus resources than are otherwise possible with a + single domain. If you know your system provides one of these and + has devices attached to it, say Y; if you are not sure, say N. + + To compile this driver as a module, choose M here: the + module will be called vmd. + +config PCIE_BRCMSTB + tristate "Broadcom Brcmstb PCIe host controller" + depends on ARCH_BRCMSTB || ARCH_BCM2835 || ARCH_BCMBCA || \ + BMIPS_GENERIC || COMPILE_TEST + depends on OF + depends on PCI_MSI_IRQ_DOMAIN + default ARCH_BRCMSTB || BMIPS_GENERIC + help + Say Y here to enable PCIe host controller support for + Broadcom STB based SoCs, like the Raspberry Pi 4. + +config PCI_HYPERV_INTERFACE + tristate "Hyper-V PCI Interface" + depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN + help + The Hyper-V PCI Interface is a helper driver allows other drivers to + have a common interface with the Hyper-V PCI frontend driver. + +config PCI_LOONGSON + bool "LOONGSON PCI Controller" + depends on MACH_LOONGSON64 || COMPILE_TEST + depends on OF || ACPI + depends on PCI_QUIRKS + default MACH_LOONGSON64 + help + Say Y here if you want to enable PCI controller support on + Loongson systems. + +config PCIE_MICROCHIP_HOST + bool "Microchip AXI PCIe host bridge support" + depends on PCI_MSI && OF + select PCI_MSI_IRQ_DOMAIN + select GENERIC_MSI_IRQ_DOMAIN + select PCI_HOST_COMMON + help + Say Y here if you want kernel to support the Microchip AXI PCIe + Host Bridge driver. + +config PCIE_HISI_ERR + depends on ACPI_APEI_GHES && (ARM64 || COMPILE_TEST) + bool "HiSilicon HIP PCIe controller error handling driver" + help + Say Y here if you want error handling support + for the PCIe controller's errors on HiSilicon HIP SoCs + +config PCIE_APPLE_MSI_DOORBELL_ADDR + hex + default 0xfffff000 + depends on PCIE_APPLE + +config PCIE_APPLE + tristate "Apple PCIe controller" + depends on ARCH_APPLE || COMPILE_TEST + depends on OF + depends on PCI_MSI_IRQ_DOMAIN + select PCI_HOST_COMMON + help + Say Y here if you want to enable PCIe controller support on Apple + system-on-chips, like the Apple M1. This is required for the USB + type-A ports, Ethernet, Wi-Fi, and Bluetooth. + + If unsure, say Y if you have an Apple Silicon system. + +config PCIE_MT7621 + tristate "MediaTek MT7621 PCIe Controller" + depends on SOC_MT7621 || COMPILE_TEST + select PHY_MT7621_PCI + default SOC_MT7621 + help + This selects a driver for the MediaTek MT7621 PCIe Controller. + +source "drivers/pci/controller/dwc/Kconfig" +source "drivers/pci/controller/mobiveil/Kconfig" +source "drivers/pci/controller/cadence/Kconfig" +endmenu diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile new file mode 100644 index 000000000..37c8663de --- /dev/null +++ b/drivers/pci/controller/Makefile @@ -0,0 +1,64 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_PCIE_CADENCE) += cadence/ +obj-$(CONFIG_PCI_FTPCI100) += pci-ftpci100.o +obj-$(CONFIG_PCI_IXP4XX) += pci-ixp4xx.o +obj-$(CONFIG_PCI_HYPERV) += pci-hyperv.o +obj-$(CONFIG_PCI_HYPERV_INTERFACE) += pci-hyperv-intf.o +obj-$(CONFIG_PCI_MVEBU) += pci-mvebu.o +obj-$(CONFIG_PCI_AARDVARK) += pci-aardvark.o +obj-$(CONFIG_PCI_TEGRA) += pci-tegra.o +obj-$(CONFIG_PCI_RCAR_GEN2) += pci-rcar-gen2.o +obj-$(CONFIG_PCIE_RCAR_HOST) += pcie-rcar.o pcie-rcar-host.o +obj-$(CONFIG_PCIE_RCAR_EP) += pcie-rcar.o pcie-rcar-ep.o +obj-$(CONFIG_PCI_HOST_COMMON) += pci-host-common.o +obj-$(CONFIG_PCI_HOST_GENERIC) += pci-host-generic.o +obj-$(CONFIG_PCI_HOST_THUNDER_ECAM) += pci-thunder-ecam.o +obj-$(CONFIG_PCI_HOST_THUNDER_PEM) += pci-thunder-pem.o +obj-$(CONFIG_PCIE_XILINX) += pcie-xilinx.o +obj-$(CONFIG_PCIE_XILINX_NWL) += pcie-xilinx-nwl.o +obj-$(CONFIG_PCIE_XILINX_CPM) += pcie-xilinx-cpm.o +obj-$(CONFIG_PCI_V3_SEMI) += pci-v3-semi.o +obj-$(CONFIG_PCI_XGENE) += pci-xgene.o +obj-$(CONFIG_PCI_XGENE_MSI) += pci-xgene-msi.o +obj-$(CONFIG_PCI_VERSATILE) += pci-versatile.o +obj-$(CONFIG_PCIE_IPROC) += pcie-iproc.o +obj-$(CONFIG_PCIE_IPROC_MSI) += pcie-iproc-msi.o +obj-$(CONFIG_PCIE_IPROC_PLATFORM) += pcie-iproc-platform.o +obj-$(CONFIG_PCIE_IPROC_BCMA) += pcie-iproc-bcma.o +obj-$(CONFIG_PCIE_ALTERA) += pcie-altera.o +obj-$(CONFIG_PCIE_ALTERA_MSI) += pcie-altera-msi.o +obj-$(CONFIG_PCIE_ROCKCHIP) += pcie-rockchip.o +obj-$(CONFIG_PCIE_ROCKCHIP_EP) += pcie-rockchip-ep.o +obj-$(CONFIG_PCIE_ROCKCHIP_HOST) += pcie-rockchip-host.o +obj-$(CONFIG_PCIE_MEDIATEK) += pcie-mediatek.o +obj-$(CONFIG_PCIE_MEDIATEK_GEN3) += pcie-mediatek-gen3.o +obj-$(CONFIG_PCIE_MICROCHIP_HOST) += pcie-microchip-host.o +obj-$(CONFIG_VMD) += vmd.o +obj-$(CONFIG_PCIE_BRCMSTB) += pcie-brcmstb.o +obj-$(CONFIG_PCI_LOONGSON) += pci-loongson.o +obj-$(CONFIG_PCIE_HISI_ERR) += pcie-hisi-error.o +obj-$(CONFIG_PCIE_APPLE) += pcie-apple.o +obj-$(CONFIG_PCIE_MT7621) += pcie-mt7621.o + +# pcie-hisi.o quirks are needed even without CONFIG_PCIE_DW +obj-y += dwc/ +obj-y += mobiveil/ + + +# The following drivers are for devices that use the generic ACPI +# pci_root.c driver but don't support standard ECAM config access. +# They contain MCFG quirks to replace the generic ECAM accessors with +# device-specific ones that are shared with the DT driver. + +# The ACPI driver is generic and should not require driver-specific +# config options to be enabled, so we always build these drivers on +# ARM64 and use internal ifdefs to only build the pieces we need +# depending on whether ACPI, the DT driver, or both are enabled. + +ifdef CONFIG_ACPI +ifdef CONFIG_PCI_QUIRKS +obj-$(CONFIG_ARM64) += pci-thunder-ecam.o +obj-$(CONFIG_ARM64) += pci-thunder-pem.o +obj-$(CONFIG_ARM64) += pci-xgene.o +endif +endif diff --git a/drivers/pci/controller/cadence/Kconfig b/drivers/pci/controller/cadence/Kconfig new file mode 100644 index 000000000..5d3056419 --- /dev/null +++ b/drivers/pci/controller/cadence/Kconfig @@ -0,0 +1,68 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "Cadence PCIe controllers support" + depends on PCI + +config PCIE_CADENCE + bool + +config PCIE_CADENCE_HOST + bool + depends on OF + select IRQ_DOMAIN + select PCIE_CADENCE + +config PCIE_CADENCE_EP + bool + depends on OF + depends on PCI_ENDPOINT + select PCIE_CADENCE + +config PCIE_CADENCE_PLAT + bool + +config PCIE_CADENCE_PLAT_HOST + bool "Cadence PCIe platform host controller" + depends on OF + select PCIE_CADENCE_HOST + select PCIE_CADENCE_PLAT + help + Say Y here if you want to support the Cadence PCIe platform controller in + host mode. This PCIe controller may be embedded into many different + vendors SoCs. + +config PCIE_CADENCE_PLAT_EP + bool "Cadence PCIe platform endpoint controller" + depends on OF + depends on PCI_ENDPOINT + select PCIE_CADENCE_EP + select PCIE_CADENCE_PLAT + help + Say Y here if you want to support the Cadence PCIe platform controller in + endpoint mode. This PCIe controller may be embedded into many + different vendors SoCs. + +config PCI_J721E + bool + +config PCI_J721E_HOST + bool "TI J721E PCIe platform host controller" + depends on OF + select PCIE_CADENCE_HOST + select PCI_J721E + help + Say Y here if you want to support the TI J721E PCIe platform + controller in host mode. TI J721E PCIe controller uses Cadence PCIe + core. + +config PCI_J721E_EP + bool "TI J721E PCIe platform endpoint controller" + depends on OF + depends on PCI_ENDPOINT + select PCIE_CADENCE_EP + select PCI_J721E + help + Say Y here if you want to support the TI J721E PCIe platform + controller in endpoint mode. TI J721E PCIe controller uses Cadence PCIe + core. +endmenu diff --git a/drivers/pci/controller/cadence/Makefile b/drivers/pci/controller/cadence/Makefile new file mode 100644 index 000000000..9bac5fb2f --- /dev/null +++ b/drivers/pci/controller/cadence/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_PCIE_CADENCE) += pcie-cadence.o +obj-$(CONFIG_PCIE_CADENCE_HOST) += pcie-cadence-host.o +obj-$(CONFIG_PCIE_CADENCE_EP) += pcie-cadence-ep.o +obj-$(CONFIG_PCIE_CADENCE_PLAT) += pcie-cadence-plat.o +obj-$(CONFIG_PCI_J721E) += pci-j721e.o diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c new file mode 100644 index 000000000..a82f845cc --- /dev/null +++ b/drivers/pci/controller/cadence/pci-j721e.c @@ -0,0 +1,569 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * pci-j721e - PCIe controller driver for TI's J721E SoCs + * + * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com + * Author: Kishon Vijay Abraham I <kishon@ti.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/io.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/mfd/syscon.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_irq.h> +#include <linux/pci.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> + +#include "../../pci.h" +#include "pcie-cadence.h" + +#define ENABLE_REG_SYS_2 0x108 +#define STATUS_REG_SYS_2 0x508 +#define STATUS_CLR_REG_SYS_2 0x708 +#define LINK_DOWN BIT(1) +#define J7200_LINK_DOWN BIT(10) + +#define J721E_PCIE_USER_CMD_STATUS 0x4 +#define LINK_TRAINING_ENABLE BIT(0) + +#define J721E_PCIE_USER_LINKSTATUS 0x14 +#define LINK_STATUS GENMASK(1, 0) + +enum link_status { + NO_RECEIVERS_DETECTED, + LINK_TRAINING_IN_PROGRESS, + LINK_UP_DL_IN_PROGRESS, + LINK_UP_DL_COMPLETED, +}; + +#define J721E_MODE_RC BIT(7) +#define LANE_COUNT_MASK BIT(8) +#define LANE_COUNT(n) ((n) << 8) + +#define GENERATION_SEL_MASK GENMASK(1, 0) + +#define MAX_LANES 2 + +struct j721e_pcie { + struct cdns_pcie *cdns_pcie; + struct clk *refclk; + u32 mode; + u32 num_lanes; + void __iomem *user_cfg_base; + void __iomem *intd_cfg_base; + u32 linkdown_irq_regfield; +}; + +enum j721e_pcie_mode { + PCI_MODE_RC, + PCI_MODE_EP, +}; + +struct j721e_pcie_data { + enum j721e_pcie_mode mode; + unsigned int quirk_retrain_flag:1; + unsigned int quirk_detect_quiet_flag:1; + unsigned int quirk_disable_flr:1; + u32 linkdown_irq_regfield; + unsigned int byte_access_allowed:1; +}; + +static inline u32 j721e_pcie_user_readl(struct j721e_pcie *pcie, u32 offset) +{ + return readl(pcie->user_cfg_base + offset); +} + +static inline void j721e_pcie_user_writel(struct j721e_pcie *pcie, u32 offset, + u32 value) +{ + writel(value, pcie->user_cfg_base + offset); +} + +static inline u32 j721e_pcie_intd_readl(struct j721e_pcie *pcie, u32 offset) +{ + return readl(pcie->intd_cfg_base + offset); +} + +static inline void j721e_pcie_intd_writel(struct j721e_pcie *pcie, u32 offset, + u32 value) +{ + writel(value, pcie->intd_cfg_base + offset); +} + +static irqreturn_t j721e_pcie_link_irq_handler(int irq, void *priv) +{ + struct j721e_pcie *pcie = priv; + struct device *dev = pcie->cdns_pcie->dev; + u32 reg; + + reg = j721e_pcie_intd_readl(pcie, STATUS_REG_SYS_2); + if (!(reg & pcie->linkdown_irq_regfield)) + return IRQ_NONE; + + dev_err(dev, "LINK DOWN!\n"); + + j721e_pcie_intd_writel(pcie, STATUS_CLR_REG_SYS_2, pcie->linkdown_irq_regfield); + return IRQ_HANDLED; +} + +static void j721e_pcie_config_link_irq(struct j721e_pcie *pcie) +{ + u32 reg; + + reg = j721e_pcie_intd_readl(pcie, ENABLE_REG_SYS_2); + reg |= pcie->linkdown_irq_regfield; + j721e_pcie_intd_writel(pcie, ENABLE_REG_SYS_2, reg); +} + +static int j721e_pcie_start_link(struct cdns_pcie *cdns_pcie) +{ + struct j721e_pcie *pcie = dev_get_drvdata(cdns_pcie->dev); + u32 reg; + + reg = j721e_pcie_user_readl(pcie, J721E_PCIE_USER_CMD_STATUS); + reg |= LINK_TRAINING_ENABLE; + j721e_pcie_user_writel(pcie, J721E_PCIE_USER_CMD_STATUS, reg); + + return 0; +} + +static void j721e_pcie_stop_link(struct cdns_pcie *cdns_pcie) +{ + struct j721e_pcie *pcie = dev_get_drvdata(cdns_pcie->dev); + u32 reg; + + reg = j721e_pcie_user_readl(pcie, J721E_PCIE_USER_CMD_STATUS); + reg &= ~LINK_TRAINING_ENABLE; + j721e_pcie_user_writel(pcie, J721E_PCIE_USER_CMD_STATUS, reg); +} + +static bool j721e_pcie_link_up(struct cdns_pcie *cdns_pcie) +{ + struct j721e_pcie *pcie = dev_get_drvdata(cdns_pcie->dev); + u32 reg; + + reg = j721e_pcie_user_readl(pcie, J721E_PCIE_USER_LINKSTATUS); + reg &= LINK_STATUS; + if (reg == LINK_UP_DL_COMPLETED) + return true; + + return false; +} + +static const struct cdns_pcie_ops j721e_pcie_ops = { + .start_link = j721e_pcie_start_link, + .stop_link = j721e_pcie_stop_link, + .link_up = j721e_pcie_link_up, +}; + +static int j721e_pcie_set_mode(struct j721e_pcie *pcie, struct regmap *syscon, + unsigned int offset) +{ + struct device *dev = pcie->cdns_pcie->dev; + u32 mask = J721E_MODE_RC; + u32 mode = pcie->mode; + u32 val = 0; + int ret = 0; + + if (mode == PCI_MODE_RC) + val = J721E_MODE_RC; + + ret = regmap_update_bits(syscon, offset, mask, val); + if (ret) + dev_err(dev, "failed to set pcie mode\n"); + + return ret; +} + +static int j721e_pcie_set_link_speed(struct j721e_pcie *pcie, + struct regmap *syscon, unsigned int offset) +{ + struct device *dev = pcie->cdns_pcie->dev; + struct device_node *np = dev->of_node; + int link_speed; + u32 val = 0; + int ret; + + link_speed = of_pci_get_max_link_speed(np); + if (link_speed < 2) + link_speed = 2; + + val = link_speed - 1; + ret = regmap_update_bits(syscon, offset, GENERATION_SEL_MASK, val); + if (ret) + dev_err(dev, "failed to set link speed\n"); + + return ret; +} + +static int j721e_pcie_set_lane_count(struct j721e_pcie *pcie, + struct regmap *syscon, unsigned int offset) +{ + struct device *dev = pcie->cdns_pcie->dev; + u32 lanes = pcie->num_lanes; + u32 val = 0; + int ret; + + val = LANE_COUNT(lanes - 1); + ret = regmap_update_bits(syscon, offset, LANE_COUNT_MASK, val); + if (ret) + dev_err(dev, "failed to set link count\n"); + + return ret; +} + +static int j721e_pcie_ctrl_init(struct j721e_pcie *pcie) +{ + struct device *dev = pcie->cdns_pcie->dev; + struct device_node *node = dev->of_node; + struct of_phandle_args args; + unsigned int offset = 0; + struct regmap *syscon; + int ret; + + syscon = syscon_regmap_lookup_by_phandle(node, "ti,syscon-pcie-ctrl"); + if (IS_ERR(syscon)) { + dev_err(dev, "Unable to get ti,syscon-pcie-ctrl regmap\n"); + return PTR_ERR(syscon); + } + + /* Do not error out to maintain old DT compatibility */ + ret = of_parse_phandle_with_fixed_args(node, "ti,syscon-pcie-ctrl", 1, + 0, &args); + if (!ret) + offset = args.args[0]; + + ret = j721e_pcie_set_mode(pcie, syscon, offset); + if (ret < 0) { + dev_err(dev, "Failed to set pci mode\n"); + return ret; + } + + ret = j721e_pcie_set_link_speed(pcie, syscon, offset); + if (ret < 0) { + dev_err(dev, "Failed to set link speed\n"); + return ret; + } + + ret = j721e_pcie_set_lane_count(pcie, syscon, offset); + if (ret < 0) { + dev_err(dev, "Failed to set num-lanes\n"); + return ret; + } + + return 0; +} + +static int cdns_ti_pcie_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *value) +{ + if (pci_is_root_bus(bus)) + return pci_generic_config_read32(bus, devfn, where, size, + value); + + return pci_generic_config_read(bus, devfn, where, size, value); +} + +static int cdns_ti_pcie_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 value) +{ + if (pci_is_root_bus(bus)) + return pci_generic_config_write32(bus, devfn, where, size, + value); + + return pci_generic_config_write(bus, devfn, where, size, value); +} + +static struct pci_ops cdns_ti_pcie_host_ops = { + .map_bus = cdns_pci_map_bus, + .read = cdns_ti_pcie_config_read, + .write = cdns_ti_pcie_config_write, +}; + +static const struct j721e_pcie_data j721e_pcie_rc_data = { + .mode = PCI_MODE_RC, + .quirk_retrain_flag = true, + .byte_access_allowed = false, + .linkdown_irq_regfield = LINK_DOWN, +}; + +static const struct j721e_pcie_data j721e_pcie_ep_data = { + .mode = PCI_MODE_EP, + .linkdown_irq_regfield = LINK_DOWN, +}; + +static const struct j721e_pcie_data j7200_pcie_rc_data = { + .mode = PCI_MODE_RC, + .quirk_detect_quiet_flag = true, + .linkdown_irq_regfield = J7200_LINK_DOWN, + .byte_access_allowed = true, +}; + +static const struct j721e_pcie_data j7200_pcie_ep_data = { + .mode = PCI_MODE_EP, + .quirk_detect_quiet_flag = true, + .quirk_disable_flr = true, +}; + +static const struct j721e_pcie_data am64_pcie_rc_data = { + .mode = PCI_MODE_RC, + .linkdown_irq_regfield = J7200_LINK_DOWN, + .byte_access_allowed = true, +}; + +static const struct j721e_pcie_data am64_pcie_ep_data = { + .mode = PCI_MODE_EP, + .linkdown_irq_regfield = J7200_LINK_DOWN, +}; + +static const struct of_device_id of_j721e_pcie_match[] = { + { + .compatible = "ti,j721e-pcie-host", + .data = &j721e_pcie_rc_data, + }, + { + .compatible = "ti,j721e-pcie-ep", + .data = &j721e_pcie_ep_data, + }, + { + .compatible = "ti,j7200-pcie-host", + .data = &j7200_pcie_rc_data, + }, + { + .compatible = "ti,j7200-pcie-ep", + .data = &j7200_pcie_ep_data, + }, + { + .compatible = "ti,am64-pcie-host", + .data = &am64_pcie_rc_data, + }, + { + .compatible = "ti,am64-pcie-ep", + .data = &am64_pcie_ep_data, + }, + {}, +}; + +static int j721e_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *node = dev->of_node; + struct pci_host_bridge *bridge; + const struct j721e_pcie_data *data; + struct cdns_pcie *cdns_pcie; + struct j721e_pcie *pcie; + struct cdns_pcie_rc *rc = NULL; + struct cdns_pcie_ep *ep = NULL; + struct gpio_desc *gpiod; + void __iomem *base; + struct clk *clk; + u32 num_lanes; + u32 mode; + int ret; + int irq; + + data = of_device_get_match_data(dev); + if (!data) + return -EINVAL; + + mode = (u32)data->mode; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + switch (mode) { + case PCI_MODE_RC: + if (!IS_ENABLED(CONFIG_PCIE_CADENCE_HOST)) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc)); + if (!bridge) + return -ENOMEM; + + if (!data->byte_access_allowed) + bridge->ops = &cdns_ti_pcie_host_ops; + rc = pci_host_bridge_priv(bridge); + rc->quirk_retrain_flag = data->quirk_retrain_flag; + rc->quirk_detect_quiet_flag = data->quirk_detect_quiet_flag; + + cdns_pcie = &rc->pcie; + cdns_pcie->dev = dev; + cdns_pcie->ops = &j721e_pcie_ops; + pcie->cdns_pcie = cdns_pcie; + break; + case PCI_MODE_EP: + if (!IS_ENABLED(CONFIG_PCIE_CADENCE_EP)) + return -ENODEV; + + ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + ep->quirk_detect_quiet_flag = data->quirk_detect_quiet_flag; + ep->quirk_disable_flr = data->quirk_disable_flr; + + cdns_pcie = &ep->pcie; + cdns_pcie->dev = dev; + cdns_pcie->ops = &j721e_pcie_ops; + pcie->cdns_pcie = cdns_pcie; + break; + default: + dev_err(dev, "INVALID device type %d\n", mode); + return 0; + } + + pcie->mode = mode; + pcie->linkdown_irq_regfield = data->linkdown_irq_regfield; + + base = devm_platform_ioremap_resource_byname(pdev, "intd_cfg"); + if (IS_ERR(base)) + return PTR_ERR(base); + pcie->intd_cfg_base = base; + + base = devm_platform_ioremap_resource_byname(pdev, "user_cfg"); + if (IS_ERR(base)) + return PTR_ERR(base); + pcie->user_cfg_base = base; + + ret = of_property_read_u32(node, "num-lanes", &num_lanes); + if (ret || num_lanes > MAX_LANES) + num_lanes = 1; + pcie->num_lanes = num_lanes; + + if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(48))) + return -EINVAL; + + irq = platform_get_irq_byname(pdev, "link_state"); + if (irq < 0) + return irq; + + dev_set_drvdata(dev, pcie); + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "pm_runtime_get_sync failed\n"); + goto err_get_sync; + } + + ret = j721e_pcie_ctrl_init(pcie); + if (ret < 0) { + dev_err(dev, "pm_runtime_get_sync failed\n"); + goto err_get_sync; + } + + ret = devm_request_irq(dev, irq, j721e_pcie_link_irq_handler, 0, + "j721e-pcie-link-down-irq", pcie); + if (ret < 0) { + dev_err(dev, "failed to request link state IRQ %d\n", irq); + goto err_get_sync; + } + + j721e_pcie_config_link_irq(pcie); + + switch (mode) { + case PCI_MODE_RC: + gpiod = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(gpiod)) { + ret = PTR_ERR(gpiod); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get reset GPIO\n"); + goto err_get_sync; + } + + ret = cdns_pcie_init_phy(dev, cdns_pcie); + if (ret) { + dev_err(dev, "Failed to init phy\n"); + goto err_get_sync; + } + + clk = devm_clk_get_optional(dev, "pcie_refclk"); + if (IS_ERR(clk)) { + ret = PTR_ERR(clk); + dev_err(dev, "failed to get pcie_refclk\n"); + goto err_pcie_setup; + } + + ret = clk_prepare_enable(clk); + if (ret) { + dev_err(dev, "failed to enable pcie_refclk\n"); + goto err_pcie_setup; + } + pcie->refclk = clk; + + /* + * "Power Sequencing and Reset Signal Timings" table in + * PCI EXPRESS CARD ELECTROMECHANICAL SPECIFICATION, REV. 3.0 + * indicates PERST# should be deasserted after minimum of 100us + * once REFCLK is stable. The REFCLK to the connector in RC + * mode is selected while enabling the PHY. So deassert PERST# + * after 100 us. + */ + if (gpiod) { + usleep_range(100, 200); + gpiod_set_value_cansleep(gpiod, 1); + } + + ret = cdns_pcie_host_setup(rc); + if (ret < 0) { + clk_disable_unprepare(pcie->refclk); + goto err_pcie_setup; + } + + break; + case PCI_MODE_EP: + ret = cdns_pcie_init_phy(dev, cdns_pcie); + if (ret) { + dev_err(dev, "Failed to init phy\n"); + goto err_get_sync; + } + + ret = cdns_pcie_ep_setup(ep); + if (ret < 0) + goto err_pcie_setup; + + break; + } + + return 0; + +err_pcie_setup: + cdns_pcie_disable_phy(cdns_pcie); + +err_get_sync: + pm_runtime_put(dev); + pm_runtime_disable(dev); + + return ret; +} + +static int j721e_pcie_remove(struct platform_device *pdev) +{ + struct j721e_pcie *pcie = platform_get_drvdata(pdev); + struct cdns_pcie *cdns_pcie = pcie->cdns_pcie; + struct device *dev = &pdev->dev; + + clk_disable_unprepare(pcie->refclk); + cdns_pcie_disable_phy(cdns_pcie); + pm_runtime_put(dev); + pm_runtime_disable(dev); + + return 0; +} + +static struct platform_driver j721e_pcie_driver = { + .probe = j721e_pcie_probe, + .remove = j721e_pcie_remove, + .driver = { + .name = "j721e-pcie", + .of_match_table = of_j721e_pcie_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver(j721e_pcie_driver); diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c new file mode 100644 index 000000000..b8b655d40 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c @@ -0,0 +1,743 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Cadence +// Cadence PCIe endpoint controller driver. +// Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> + +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/pci-epc.h> +#include <linux/platform_device.h> +#include <linux/sizes.h> + +#include "pcie-cadence.h" + +#define CDNS_PCIE_EP_MIN_APERTURE 128 /* 128 bytes */ +#define CDNS_PCIE_EP_IRQ_PCI_ADDR_NONE 0x1 +#define CDNS_PCIE_EP_IRQ_PCI_ADDR_LEGACY 0x3 + +static u8 cdns_pcie_get_fn_from_vfn(struct cdns_pcie *pcie, u8 fn, u8 vfn) +{ + u32 cap = CDNS_PCIE_EP_FUNC_SRIOV_CAP_OFFSET; + u32 first_vf_offset, stride; + + if (vfn == 0) + return fn; + + first_vf_offset = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_SRIOV_VF_OFFSET); + stride = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_SRIOV_VF_STRIDE); + fn = fn + first_vf_offset + ((vfn - 1) * stride); + + return fn; +} + +static int cdns_pcie_ep_write_header(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_header *hdr) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + u32 cap = CDNS_PCIE_EP_FUNC_SRIOV_CAP_OFFSET; + struct cdns_pcie *pcie = &ep->pcie; + u32 reg; + + if (vfn > 1) { + dev_err(&epc->dev, "Only Virtual Function #1 has deviceID\n"); + return -EINVAL; + } else if (vfn == 1) { + reg = cap + PCI_SRIOV_VF_DID; + cdns_pcie_ep_fn_writew(pcie, fn, reg, hdr->deviceid); + return 0; + } + + cdns_pcie_ep_fn_writew(pcie, fn, PCI_DEVICE_ID, hdr->deviceid); + cdns_pcie_ep_fn_writeb(pcie, fn, PCI_REVISION_ID, hdr->revid); + cdns_pcie_ep_fn_writeb(pcie, fn, PCI_CLASS_PROG, hdr->progif_code); + cdns_pcie_ep_fn_writew(pcie, fn, PCI_CLASS_DEVICE, + hdr->subclass_code | hdr->baseclass_code << 8); + cdns_pcie_ep_fn_writeb(pcie, fn, PCI_CACHE_LINE_SIZE, + hdr->cache_line_size); + cdns_pcie_ep_fn_writew(pcie, fn, PCI_SUBSYSTEM_ID, hdr->subsys_id); + cdns_pcie_ep_fn_writeb(pcie, fn, PCI_INTERRUPT_PIN, hdr->interrupt_pin); + + /* + * Vendor ID can only be modified from function 0, all other functions + * use the same vendor ID as function 0. + */ + if (fn == 0) { + /* Update the vendor IDs. */ + u32 id = CDNS_PCIE_LM_ID_VENDOR(hdr->vendorid) | + CDNS_PCIE_LM_ID_SUBSYS(hdr->subsys_vendor_id); + + cdns_pcie_writel(pcie, CDNS_PCIE_LM_ID, id); + } + + return 0; +} + +static int cdns_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_bar *epf_bar) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie_epf *epf = &ep->epf[fn]; + struct cdns_pcie *pcie = &ep->pcie; + dma_addr_t bar_phys = epf_bar->phys_addr; + enum pci_barno bar = epf_bar->barno; + int flags = epf_bar->flags; + u32 addr0, addr1, reg, cfg, b, aperture, ctrl; + u64 sz; + + /* BAR size is 2^(aperture + 7) */ + sz = max_t(size_t, epf_bar->size, CDNS_PCIE_EP_MIN_APERTURE); + /* + * roundup_pow_of_two() returns an unsigned long, which is not suited + * for 64bit values. + */ + sz = 1ULL << fls64(sz - 1); + aperture = ilog2(sz) - 7; /* 128B -> 0, 256B -> 1, 512B -> 2, ... */ + + if ((flags & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) { + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_IO_32BITS; + } else { + bool is_prefetch = !!(flags & PCI_BASE_ADDRESS_MEM_PREFETCH); + bool is_64bits = sz > SZ_2G; + + if (is_64bits && (bar & 1)) + return -EINVAL; + + if (is_64bits && !(flags & PCI_BASE_ADDRESS_MEM_TYPE_64)) + epf_bar->flags |= PCI_BASE_ADDRESS_MEM_TYPE_64; + + if (is_64bits && is_prefetch) + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_PREFETCH_MEM_64BITS; + else if (is_prefetch) + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_PREFETCH_MEM_32BITS; + else if (is_64bits) + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_MEM_64BITS; + else + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_MEM_32BITS; + } + + addr0 = lower_32_bits(bar_phys); + addr1 = upper_32_bits(bar_phys); + + if (vfn == 1) + reg = CDNS_PCIE_LM_EP_VFUNC_BAR_CFG(bar, fn); + else + reg = CDNS_PCIE_LM_EP_FUNC_BAR_CFG(bar, fn); + b = (bar < BAR_4) ? bar : bar - BAR_4; + + if (vfn == 0 || vfn == 1) { + cfg = cdns_pcie_readl(pcie, reg); + cfg &= ~(CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b) | + CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)); + cfg |= (CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE(b, aperture) | + CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL(b, ctrl)); + cdns_pcie_writel(pcie, reg, cfg); + } + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar), + addr0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar), + addr1); + + if (vfn > 0) + epf = &epf->epf[vfn - 1]; + epf->epf_bar[bar] = epf_bar; + + return 0; +} + +static void cdns_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_bar *epf_bar) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie_epf *epf = &ep->epf[fn]; + struct cdns_pcie *pcie = &ep->pcie; + enum pci_barno bar = epf_bar->barno; + u32 reg, cfg, b, ctrl; + + if (vfn == 1) + reg = CDNS_PCIE_LM_EP_VFUNC_BAR_CFG(bar, fn); + else + reg = CDNS_PCIE_LM_EP_FUNC_BAR_CFG(bar, fn); + b = (bar < BAR_4) ? bar : bar - BAR_4; + + if (vfn == 0 || vfn == 1) { + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_DISABLED; + cfg = cdns_pcie_readl(pcie, reg); + cfg &= ~(CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b) | + CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)); + cfg |= CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL(b, ctrl); + cdns_pcie_writel(pcie, reg, cfg); + } + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar), 0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar), 0); + + if (vfn > 0) + epf = &epf->epf[vfn - 1]; + epf->epf_bar[bar] = NULL; +} + +static int cdns_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr, u64 pci_addr, size_t size) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + u32 r; + + r = find_first_zero_bit(&ep->ob_region_map, BITS_PER_LONG); + if (r >= ep->max_regions - 1) { + dev_err(&epc->dev, "no free outbound region\n"); + return -EINVAL; + } + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + cdns_pcie_set_outbound_region(pcie, 0, fn, r, false, addr, pci_addr, size); + + set_bit(r, &ep->ob_region_map); + ep->ob_addr[r] = addr; + + return 0; +} + +static void cdns_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + u32 r; + + for (r = 0; r < ep->max_regions - 1; r++) + if (ep->ob_addr[r] == addr) + break; + + if (r == ep->max_regions - 1) + return; + + cdns_pcie_reset_outbound_region(pcie, r); + + ep->ob_addr[r] = 0; + clear_bit(r, &ep->ob_region_map); +} + +static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 mmc) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + u32 cap = CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET; + u16 flags; + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + + /* + * Set the Multiple Message Capable bitfield into the Message Control + * register. + */ + flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); + flags = (flags & ~PCI_MSI_FLAGS_QMASK) | (mmc << 1); + flags |= PCI_MSI_FLAGS_64BIT; + flags &= ~PCI_MSI_FLAGS_MASKBIT; + cdns_pcie_ep_fn_writew(pcie, fn, cap + PCI_MSI_FLAGS, flags); + + return 0; +} + +static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + u32 cap = CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET; + u16 flags, mme; + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + + /* Validate that the MSI feature is actually enabled. */ + flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); + if (!(flags & PCI_MSI_FLAGS_ENABLE)) + return -EINVAL; + + /* + * Get the Multiple Message Enable bitfield from the Message Control + * register. + */ + mme = (flags & PCI_MSI_FLAGS_QSIZE) >> 4; + + return mme; +} + +static int cdns_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + u32 cap = CDNS_PCIE_EP_FUNC_MSIX_CAP_OFFSET; + u32 val, reg; + + func_no = cdns_pcie_get_fn_from_vfn(pcie, func_no, vfunc_no); + + reg = cap + PCI_MSIX_FLAGS; + val = cdns_pcie_ep_fn_readw(pcie, func_no, reg); + if (!(val & PCI_MSIX_FLAGS_ENABLE)) + return -EINVAL; + + val &= PCI_MSIX_FLAGS_QSIZE; + + return val; +} + +static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn, + u16 interrupts, enum pci_barno bir, + u32 offset) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + u32 cap = CDNS_PCIE_EP_FUNC_MSIX_CAP_OFFSET; + u32 val, reg; + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + + reg = cap + PCI_MSIX_FLAGS; + val = cdns_pcie_ep_fn_readw(pcie, fn, reg); + val &= ~PCI_MSIX_FLAGS_QSIZE; + val |= interrupts; + cdns_pcie_ep_fn_writew(pcie, fn, reg, val); + + /* Set MSIX BAR and offset */ + reg = cap + PCI_MSIX_TABLE; + val = offset | bir; + cdns_pcie_ep_fn_writel(pcie, fn, reg, val); + + /* Set PBA BAR and offset. BAR must match MSIX BAR */ + reg = cap + PCI_MSIX_PBA; + val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; + cdns_pcie_ep_fn_writel(pcie, fn, reg, val); + + return 0; +} + +static void cdns_pcie_ep_assert_intx(struct cdns_pcie_ep *ep, u8 fn, u8 intx, + bool is_asserted) +{ + struct cdns_pcie *pcie = &ep->pcie; + unsigned long flags; + u32 offset; + u16 status; + u8 msg_code; + + intx &= 3; + + /* Set the outbound region if needed. */ + if (unlikely(ep->irq_pci_addr != CDNS_PCIE_EP_IRQ_PCI_ADDR_LEGACY || + ep->irq_pci_fn != fn)) { + /* First region was reserved for IRQ writes. */ + cdns_pcie_set_outbound_region_for_normal_msg(pcie, 0, fn, 0, + ep->irq_phys_addr); + ep->irq_pci_addr = CDNS_PCIE_EP_IRQ_PCI_ADDR_LEGACY; + ep->irq_pci_fn = fn; + } + + if (is_asserted) { + ep->irq_pending |= BIT(intx); + msg_code = MSG_CODE_ASSERT_INTA + intx; + } else { + ep->irq_pending &= ~BIT(intx); + msg_code = MSG_CODE_DEASSERT_INTA + intx; + } + + spin_lock_irqsave(&ep->lock, flags); + status = cdns_pcie_ep_fn_readw(pcie, fn, PCI_STATUS); + if (((status & PCI_STATUS_INTERRUPT) != 0) ^ (ep->irq_pending != 0)) { + status ^= PCI_STATUS_INTERRUPT; + cdns_pcie_ep_fn_writew(pcie, fn, PCI_STATUS, status); + } + spin_unlock_irqrestore(&ep->lock, flags); + + offset = CDNS_PCIE_NORMAL_MSG_ROUTING(MSG_ROUTING_LOCAL) | + CDNS_PCIE_NORMAL_MSG_CODE(msg_code) | + CDNS_PCIE_MSG_NO_DATA; + writel(0, ep->irq_cpu_addr + offset); +} + +static int cdns_pcie_ep_send_legacy_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn, + u8 intx) +{ + u16 cmd; + + cmd = cdns_pcie_ep_fn_readw(&ep->pcie, fn, PCI_COMMAND); + if (cmd & PCI_COMMAND_INTX_DISABLE) + return -EINVAL; + + cdns_pcie_ep_assert_intx(ep, fn, intx, true); + /* + * The mdelay() value was taken from dra7xx_pcie_raise_legacy_irq() + */ + mdelay(1); + cdns_pcie_ep_assert_intx(ep, fn, intx, false); + return 0; +} + +static int cdns_pcie_ep_send_msi_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn, + u8 interrupt_num) +{ + struct cdns_pcie *pcie = &ep->pcie; + u32 cap = CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET; + u16 flags, mme, data, data_mask; + u8 msi_count; + u64 pci_addr, pci_addr_mask = 0xff; + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + + /* Check whether the MSI feature has been enabled by the PCI host. */ + flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); + if (!(flags & PCI_MSI_FLAGS_ENABLE)) + return -EINVAL; + + /* Get the number of enabled MSIs */ + mme = (flags & PCI_MSI_FLAGS_QSIZE) >> 4; + msi_count = 1 << mme; + if (!interrupt_num || interrupt_num > msi_count) + return -EINVAL; + + /* Compute the data value to be written. */ + data_mask = msi_count - 1; + data = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_DATA_64); + data = (data & ~data_mask) | ((interrupt_num - 1) & data_mask); + + /* Get the PCI address where to write the data into. */ + pci_addr = cdns_pcie_ep_fn_readl(pcie, fn, cap + PCI_MSI_ADDRESS_HI); + pci_addr <<= 32; + pci_addr |= cdns_pcie_ep_fn_readl(pcie, fn, cap + PCI_MSI_ADDRESS_LO); + pci_addr &= GENMASK_ULL(63, 2); + + /* Set the outbound region if needed. */ + if (unlikely(ep->irq_pci_addr != (pci_addr & ~pci_addr_mask) || + ep->irq_pci_fn != fn)) { + /* First region was reserved for IRQ writes. */ + cdns_pcie_set_outbound_region(pcie, 0, fn, 0, + false, + ep->irq_phys_addr, + pci_addr & ~pci_addr_mask, + pci_addr_mask + 1); + ep->irq_pci_addr = (pci_addr & ~pci_addr_mask); + ep->irq_pci_fn = fn; + } + writel(data, ep->irq_cpu_addr + (pci_addr & pci_addr_mask)); + + return 0; +} + +static int cdns_pcie_ep_map_msi_irq(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr, u8 interrupt_num, + u32 entry_size, u32 *msi_data, + u32 *msi_addr_offset) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + u32 cap = CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET; + struct cdns_pcie *pcie = &ep->pcie; + u64 pci_addr, pci_addr_mask = 0xff; + u16 flags, mme, data, data_mask; + u8 msi_count; + int ret; + int i; + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + + /* Check whether the MSI feature has been enabled by the PCI host. */ + flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_FLAGS); + if (!(flags & PCI_MSI_FLAGS_ENABLE)) + return -EINVAL; + + /* Get the number of enabled MSIs */ + mme = (flags & PCI_MSI_FLAGS_QSIZE) >> 4; + msi_count = 1 << mme; + if (!interrupt_num || interrupt_num > msi_count) + return -EINVAL; + + /* Compute the data value to be written. */ + data_mask = msi_count - 1; + data = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSI_DATA_64); + data = data & ~data_mask; + + /* Get the PCI address where to write the data into. */ + pci_addr = cdns_pcie_ep_fn_readl(pcie, fn, cap + PCI_MSI_ADDRESS_HI); + pci_addr <<= 32; + pci_addr |= cdns_pcie_ep_fn_readl(pcie, fn, cap + PCI_MSI_ADDRESS_LO); + pci_addr &= GENMASK_ULL(63, 2); + + for (i = 0; i < interrupt_num; i++) { + ret = cdns_pcie_ep_map_addr(epc, fn, vfn, addr, + pci_addr & ~pci_addr_mask, + entry_size); + if (ret) + return ret; + addr = addr + entry_size; + } + + *msi_data = data; + *msi_addr_offset = pci_addr & pci_addr_mask; + + return 0; +} + +static int cdns_pcie_ep_send_msix_irq(struct cdns_pcie_ep *ep, u8 fn, u8 vfn, + u16 interrupt_num) +{ + u32 cap = CDNS_PCIE_EP_FUNC_MSIX_CAP_OFFSET; + u32 tbl_offset, msg_data, reg; + struct cdns_pcie *pcie = &ep->pcie; + struct pci_epf_msix_tbl *msix_tbl; + struct cdns_pcie_epf *epf; + u64 pci_addr_mask = 0xff; + u64 msg_addr; + u16 flags; + u8 bir; + + epf = &ep->epf[fn]; + if (vfn > 0) + epf = &epf->epf[vfn - 1]; + + fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); + + /* Check whether the MSI-X feature has been enabled by the PCI host. */ + flags = cdns_pcie_ep_fn_readw(pcie, fn, cap + PCI_MSIX_FLAGS); + if (!(flags & PCI_MSIX_FLAGS_ENABLE)) + return -EINVAL; + + reg = cap + PCI_MSIX_TABLE; + tbl_offset = cdns_pcie_ep_fn_readl(pcie, fn, reg); + bir = tbl_offset & PCI_MSIX_TABLE_BIR; + tbl_offset &= PCI_MSIX_TABLE_OFFSET; + + msix_tbl = epf->epf_bar[bir]->addr + tbl_offset; + msg_addr = msix_tbl[(interrupt_num - 1)].msg_addr; + msg_data = msix_tbl[(interrupt_num - 1)].msg_data; + + /* Set the outbound region if needed. */ + if (ep->irq_pci_addr != (msg_addr & ~pci_addr_mask) || + ep->irq_pci_fn != fn) { + /* First region was reserved for IRQ writes. */ + cdns_pcie_set_outbound_region(pcie, 0, fn, 0, + false, + ep->irq_phys_addr, + msg_addr & ~pci_addr_mask, + pci_addr_mask + 1); + ep->irq_pci_addr = (msg_addr & ~pci_addr_mask); + ep->irq_pci_fn = fn; + } + writel(msg_data, ep->irq_cpu_addr + (msg_addr & pci_addr_mask)); + + return 0; +} + +static int cdns_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn, + enum pci_epc_irq_type type, + u16 interrupt_num) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + struct device *dev = pcie->dev; + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + if (vfn > 0) { + dev_err(dev, "Cannot raise legacy interrupts for VF\n"); + return -EINVAL; + } + return cdns_pcie_ep_send_legacy_irq(ep, fn, vfn, 0); + + case PCI_EPC_IRQ_MSI: + return cdns_pcie_ep_send_msi_irq(ep, fn, vfn, interrupt_num); + + case PCI_EPC_IRQ_MSIX: + return cdns_pcie_ep_send_msix_irq(ep, fn, vfn, interrupt_num); + + default: + break; + } + + return -EINVAL; +} + +static int cdns_pcie_ep_start(struct pci_epc *epc) +{ + struct cdns_pcie_ep *ep = epc_get_drvdata(epc); + struct cdns_pcie *pcie = &ep->pcie; + struct device *dev = pcie->dev; + int max_epfs = sizeof(epc->function_num_map) * 8; + int ret, value, epf; + + /* + * BIT(0) is hardwired to 1, hence function 0 is always enabled + * and can't be disabled anyway. + */ + cdns_pcie_writel(pcie, CDNS_PCIE_LM_EP_FUNC_CFG, epc->function_num_map); + + if (ep->quirk_disable_flr) { + for (epf = 0; epf < max_epfs; epf++) { + if (!(epc->function_num_map & BIT(epf))) + continue; + + value = cdns_pcie_ep_fn_readl(pcie, epf, + CDNS_PCIE_EP_FUNC_DEV_CAP_OFFSET + + PCI_EXP_DEVCAP); + value &= ~PCI_EXP_DEVCAP_FLR; + cdns_pcie_ep_fn_writel(pcie, epf, + CDNS_PCIE_EP_FUNC_DEV_CAP_OFFSET + + PCI_EXP_DEVCAP, value); + } + } + + ret = cdns_pcie_start_link(pcie); + if (ret) { + dev_err(dev, "Failed to start link\n"); + return ret; + } + + return 0; +} + +static const struct pci_epc_features cdns_pcie_epc_vf_features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = true, + .align = 65536, +}; + +static const struct pci_epc_features cdns_pcie_epc_features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = true, + .align = 256, +}; + +static const struct pci_epc_features* +cdns_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) +{ + if (!vfunc_no) + return &cdns_pcie_epc_features; + + return &cdns_pcie_epc_vf_features; +} + +static const struct pci_epc_ops cdns_pcie_epc_ops = { + .write_header = cdns_pcie_ep_write_header, + .set_bar = cdns_pcie_ep_set_bar, + .clear_bar = cdns_pcie_ep_clear_bar, + .map_addr = cdns_pcie_ep_map_addr, + .unmap_addr = cdns_pcie_ep_unmap_addr, + .set_msi = cdns_pcie_ep_set_msi, + .get_msi = cdns_pcie_ep_get_msi, + .set_msix = cdns_pcie_ep_set_msix, + .get_msix = cdns_pcie_ep_get_msix, + .raise_irq = cdns_pcie_ep_raise_irq, + .map_msi_irq = cdns_pcie_ep_map_msi_irq, + .start = cdns_pcie_ep_start, + .get_features = cdns_pcie_ep_get_features, +}; + + +int cdns_pcie_ep_setup(struct cdns_pcie_ep *ep) +{ + struct device *dev = ep->pcie.dev; + struct platform_device *pdev = to_platform_device(dev); + struct device_node *np = dev->of_node; + struct cdns_pcie *pcie = &ep->pcie; + struct cdns_pcie_epf *epf; + struct resource *res; + struct pci_epc *epc; + int ret; + int i; + + pcie->is_rc = false; + + pcie->reg_base = devm_platform_ioremap_resource_byname(pdev, "reg"); + if (IS_ERR(pcie->reg_base)) { + dev_err(dev, "missing \"reg\"\n"); + return PTR_ERR(pcie->reg_base); + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mem"); + if (!res) { + dev_err(dev, "missing \"mem\"\n"); + return -EINVAL; + } + pcie->mem_res = res; + + ep->max_regions = CDNS_PCIE_MAX_OB; + of_property_read_u32(np, "cdns,max-outbound-regions", &ep->max_regions); + + ep->ob_addr = devm_kcalloc(dev, + ep->max_regions, sizeof(*ep->ob_addr), + GFP_KERNEL); + if (!ep->ob_addr) + return -ENOMEM; + + /* Disable all but function 0 (anyway BIT(0) is hardwired to 1). */ + cdns_pcie_writel(pcie, CDNS_PCIE_LM_EP_FUNC_CFG, BIT(0)); + + epc = devm_pci_epc_create(dev, &cdns_pcie_epc_ops); + if (IS_ERR(epc)) { + dev_err(dev, "failed to create epc device\n"); + return PTR_ERR(epc); + } + + epc_set_drvdata(epc, ep); + + if (of_property_read_u8(np, "max-functions", &epc->max_functions) < 0) + epc->max_functions = 1; + + ep->epf = devm_kcalloc(dev, epc->max_functions, sizeof(*ep->epf), + GFP_KERNEL); + if (!ep->epf) + return -ENOMEM; + + epc->max_vfs = devm_kcalloc(dev, epc->max_functions, + sizeof(*epc->max_vfs), GFP_KERNEL); + if (!epc->max_vfs) + return -ENOMEM; + + ret = of_property_read_u8_array(np, "max-virtual-functions", + epc->max_vfs, epc->max_functions); + if (ret == 0) { + for (i = 0; i < epc->max_functions; i++) { + epf = &ep->epf[i]; + if (epc->max_vfs[i] == 0) + continue; + epf->epf = devm_kcalloc(dev, epc->max_vfs[i], + sizeof(*ep->epf), GFP_KERNEL); + if (!epf->epf) + return -ENOMEM; + } + } + + ret = pci_epc_mem_init(epc, pcie->mem_res->start, + resource_size(pcie->mem_res), PAGE_SIZE); + if (ret < 0) { + dev_err(dev, "failed to initialize the memory space\n"); + return ret; + } + + ep->irq_cpu_addr = pci_epc_mem_alloc_addr(epc, &ep->irq_phys_addr, + SZ_128K); + if (!ep->irq_cpu_addr) { + dev_err(dev, "failed to reserve memory space for MSI\n"); + ret = -ENOMEM; + goto free_epc_mem; + } + ep->irq_pci_addr = CDNS_PCIE_EP_IRQ_PCI_ADDR_NONE; + /* Reserve region 0 for IRQs */ + set_bit(0, &ep->ob_region_map); + + if (ep->quirk_detect_quiet_flag) + cdns_pcie_detect_quiet_min_delay_set(&ep->pcie); + + spin_lock_init(&ep->lock); + + return 0; + + free_epc_mem: + pci_epc_mem_exit(epc); + + return ret; +} diff --git a/drivers/pci/controller/cadence/pcie-cadence-host.c b/drivers/pci/controller/cadence/pcie-cadence-host.c new file mode 100644 index 000000000..5b14f7ee3 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-host.c @@ -0,0 +1,571 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Cadence +// Cadence PCIe host controller driver. +// Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> + +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/list_sort.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/platform_device.h> + +#include "pcie-cadence.h" + +#define LINK_RETRAIN_TIMEOUT HZ + +static u64 bar_max_size[] = { + [RP_BAR0] = _ULL(128 * SZ_2G), + [RP_BAR1] = SZ_2G, + [RP_NO_BAR] = _BITULL(63), +}; + +static u8 bar_aperture_mask[] = { + [RP_BAR0] = 0x1F, + [RP_BAR1] = 0xF, +}; + +void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) +{ + struct pci_host_bridge *bridge = pci_find_host_bridge(bus); + struct cdns_pcie_rc *rc = pci_host_bridge_priv(bridge); + struct cdns_pcie *pcie = &rc->pcie; + unsigned int busn = bus->number; + u32 addr0, desc0; + + if (pci_is_root_bus(bus)) { + /* + * Only the root port (devfn == 0) is connected to this bus. + * All other PCI devices are behind some bridge hence on another + * bus. + */ + if (devfn) + return NULL; + + return pcie->reg_base + (where & 0xfff); + } + /* Check that the link is up */ + if (!(cdns_pcie_readl(pcie, CDNS_PCIE_LM_BASE) & 0x1)) + return NULL; + /* Clear AXI link-down status */ + cdns_pcie_writel(pcie, CDNS_PCIE_AT_LINKDOWN, 0x0); + + /* Update Output registers for AXI region 0. */ + addr0 = CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_NBITS(12) | + CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_DEVFN(devfn) | + CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_BUS(busn); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_PCI_ADDR0(0), addr0); + + /* Configuration Type 0 or Type 1 access. */ + desc0 = CDNS_PCIE_AT_OB_REGION_DESC0_HARDCODED_RID | + CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN(0); + /* + * The bus number was already set once for all in desc1 by + * cdns_pcie_host_init_address_translation(). + */ + if (busn == bridge->busnr + 1) + desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_CONF_TYPE0; + else + desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_CONF_TYPE1; + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC0(0), desc0); + + return rc->cfg_base + (where & 0xfff); +} + +static struct pci_ops cdns_pcie_host_ops = { + .map_bus = cdns_pci_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static int cdns_pcie_host_training_complete(struct cdns_pcie *pcie) +{ + u32 pcie_cap_off = CDNS_PCIE_RP_CAP_OFFSET; + unsigned long end_jiffies; + u16 lnk_stat; + + /* Wait for link training to complete. Exit after timeout. */ + end_jiffies = jiffies + LINK_RETRAIN_TIMEOUT; + do { + lnk_stat = cdns_pcie_rp_readw(pcie, pcie_cap_off + PCI_EXP_LNKSTA); + if (!(lnk_stat & PCI_EXP_LNKSTA_LT)) + break; + usleep_range(0, 1000); + } while (time_before(jiffies, end_jiffies)); + + if (!(lnk_stat & PCI_EXP_LNKSTA_LT)) + return 0; + + return -ETIMEDOUT; +} + +static int cdns_pcie_host_wait_for_link(struct cdns_pcie *pcie) +{ + struct device *dev = pcie->dev; + int retries; + + /* Check if the link is up or not */ + for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { + if (cdns_pcie_link_up(pcie)) { + dev_info(dev, "Link up\n"); + return 0; + } + usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX); + } + + return -ETIMEDOUT; +} + +static int cdns_pcie_retrain(struct cdns_pcie *pcie) +{ + u32 lnk_cap_sls, pcie_cap_off = CDNS_PCIE_RP_CAP_OFFSET; + u16 lnk_stat, lnk_ctl; + int ret = 0; + + /* + * Set retrain bit if current speed is 2.5 GB/s, + * but the PCIe root port support is > 2.5 GB/s. + */ + + lnk_cap_sls = cdns_pcie_readl(pcie, (CDNS_PCIE_RP_BASE + pcie_cap_off + + PCI_EXP_LNKCAP)); + if ((lnk_cap_sls & PCI_EXP_LNKCAP_SLS) <= PCI_EXP_LNKCAP_SLS_2_5GB) + return ret; + + lnk_stat = cdns_pcie_rp_readw(pcie, pcie_cap_off + PCI_EXP_LNKSTA); + if ((lnk_stat & PCI_EXP_LNKSTA_CLS) == PCI_EXP_LNKSTA_CLS_2_5GB) { + lnk_ctl = cdns_pcie_rp_readw(pcie, + pcie_cap_off + PCI_EXP_LNKCTL); + lnk_ctl |= PCI_EXP_LNKCTL_RL; + cdns_pcie_rp_writew(pcie, pcie_cap_off + PCI_EXP_LNKCTL, + lnk_ctl); + + ret = cdns_pcie_host_training_complete(pcie); + if (ret) + return ret; + + ret = cdns_pcie_host_wait_for_link(pcie); + } + return ret; +} + +static void cdns_pcie_host_enable_ptm_response(struct cdns_pcie *pcie) +{ + u32 val; + + val = cdns_pcie_readl(pcie, CDNS_PCIE_LM_PTM_CTRL); + cdns_pcie_writel(pcie, CDNS_PCIE_LM_PTM_CTRL, val | CDNS_PCIE_LM_TPM_CTRL_PTMRSEN); +} + +static int cdns_pcie_host_start_link(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + int ret; + + ret = cdns_pcie_host_wait_for_link(pcie); + + /* + * Retrain link for Gen2 training defect + * if quirk flag is set. + */ + if (!ret && rc->quirk_retrain_flag) + ret = cdns_pcie_retrain(pcie); + + return ret; +} + +static int cdns_pcie_host_init_root_port(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + u32 value, ctrl; + u32 id; + + /* + * Set the root complex BAR configuration register: + * - disable both BAR0 and BAR1. + * - enable Prefetchable Memory Base and Limit registers in type 1 + * config space (64 bits). + * - enable IO Base and Limit registers in type 1 config + * space (32 bits). + */ + ctrl = CDNS_PCIE_LM_BAR_CFG_CTRL_DISABLED; + value = CDNS_PCIE_LM_RC_BAR_CFG_BAR0_CTRL(ctrl) | + CDNS_PCIE_LM_RC_BAR_CFG_BAR1_CTRL(ctrl) | + CDNS_PCIE_LM_RC_BAR_CFG_PREFETCH_MEM_ENABLE | + CDNS_PCIE_LM_RC_BAR_CFG_PREFETCH_MEM_64BITS | + CDNS_PCIE_LM_RC_BAR_CFG_IO_ENABLE | + CDNS_PCIE_LM_RC_BAR_CFG_IO_32BITS; + cdns_pcie_writel(pcie, CDNS_PCIE_LM_RC_BAR_CFG, value); + + /* Set root port configuration space */ + if (rc->vendor_id != 0xffff) { + id = CDNS_PCIE_LM_ID_VENDOR(rc->vendor_id) | + CDNS_PCIE_LM_ID_SUBSYS(rc->vendor_id); + cdns_pcie_writel(pcie, CDNS_PCIE_LM_ID, id); + } + + if (rc->device_id != 0xffff) + cdns_pcie_rp_writew(pcie, PCI_DEVICE_ID, rc->device_id); + + cdns_pcie_rp_writeb(pcie, PCI_CLASS_REVISION, 0); + cdns_pcie_rp_writeb(pcie, PCI_CLASS_PROG, 0); + cdns_pcie_rp_writew(pcie, PCI_CLASS_DEVICE, PCI_CLASS_BRIDGE_PCI); + + return 0; +} + +static int cdns_pcie_host_bar_ib_config(struct cdns_pcie_rc *rc, + enum cdns_pcie_rp_bar bar, + u64 cpu_addr, u64 size, + unsigned long flags) +{ + struct cdns_pcie *pcie = &rc->pcie; + u32 addr0, addr1, aperture, value; + + if (!rc->avail_ib_bar[bar]) + return -EBUSY; + + rc->avail_ib_bar[bar] = false; + + aperture = ilog2(size); + addr0 = CDNS_PCIE_AT_IB_RP_BAR_ADDR0_NBITS(aperture) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_RP_BAR_ADDR0(bar), addr0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_RP_BAR_ADDR1(bar), addr1); + + if (bar == RP_NO_BAR) + return 0; + + value = cdns_pcie_readl(pcie, CDNS_PCIE_LM_RC_BAR_CFG); + value &= ~(LM_RC_BAR_CFG_CTRL_MEM_64BITS(bar) | + LM_RC_BAR_CFG_CTRL_PREF_MEM_64BITS(bar) | + LM_RC_BAR_CFG_CTRL_MEM_32BITS(bar) | + LM_RC_BAR_CFG_CTRL_PREF_MEM_32BITS(bar) | + LM_RC_BAR_CFG_APERTURE(bar, bar_aperture_mask[bar] + 2)); + if (size + cpu_addr >= SZ_4G) { + if (!(flags & IORESOURCE_PREFETCH)) + value |= LM_RC_BAR_CFG_CTRL_MEM_64BITS(bar); + value |= LM_RC_BAR_CFG_CTRL_PREF_MEM_64BITS(bar); + } else { + if (!(flags & IORESOURCE_PREFETCH)) + value |= LM_RC_BAR_CFG_CTRL_MEM_32BITS(bar); + value |= LM_RC_BAR_CFG_CTRL_PREF_MEM_32BITS(bar); + } + + value |= LM_RC_BAR_CFG_APERTURE(bar, aperture); + cdns_pcie_writel(pcie, CDNS_PCIE_LM_RC_BAR_CFG, value); + + return 0; +} + +static enum cdns_pcie_rp_bar +cdns_pcie_host_find_min_bar(struct cdns_pcie_rc *rc, u64 size) +{ + enum cdns_pcie_rp_bar bar, sel_bar; + + sel_bar = RP_BAR_UNDEFINED; + for (bar = RP_BAR0; bar <= RP_NO_BAR; bar++) { + if (!rc->avail_ib_bar[bar]) + continue; + + if (size <= bar_max_size[bar]) { + if (sel_bar == RP_BAR_UNDEFINED) { + sel_bar = bar; + continue; + } + + if (bar_max_size[bar] < bar_max_size[sel_bar]) + sel_bar = bar; + } + } + + return sel_bar; +} + +static enum cdns_pcie_rp_bar +cdns_pcie_host_find_max_bar(struct cdns_pcie_rc *rc, u64 size) +{ + enum cdns_pcie_rp_bar bar, sel_bar; + + sel_bar = RP_BAR_UNDEFINED; + for (bar = RP_BAR0; bar <= RP_NO_BAR; bar++) { + if (!rc->avail_ib_bar[bar]) + continue; + + if (size >= bar_max_size[bar]) { + if (sel_bar == RP_BAR_UNDEFINED) { + sel_bar = bar; + continue; + } + + if (bar_max_size[bar] > bar_max_size[sel_bar]) + sel_bar = bar; + } + } + + return sel_bar; +} + +static int cdns_pcie_host_bar_config(struct cdns_pcie_rc *rc, + struct resource_entry *entry) +{ + u64 cpu_addr, pci_addr, size, winsize; + struct cdns_pcie *pcie = &rc->pcie; + struct device *dev = pcie->dev; + enum cdns_pcie_rp_bar bar; + unsigned long flags; + int ret; + + cpu_addr = entry->res->start; + pci_addr = entry->res->start - entry->offset; + flags = entry->res->flags; + size = resource_size(entry->res); + + if (entry->offset) { + dev_err(dev, "PCI addr: %llx must be equal to CPU addr: %llx\n", + pci_addr, cpu_addr); + return -EINVAL; + } + + while (size > 0) { + /* + * Try to find a minimum BAR whose size is greater than + * or equal to the remaining resource_entry size. This will + * fail if the size of each of the available BARs is less than + * the remaining resource_entry size. + * If a minimum BAR is found, IB ATU will be configured and + * exited. + */ + bar = cdns_pcie_host_find_min_bar(rc, size); + if (bar != RP_BAR_UNDEFINED) { + ret = cdns_pcie_host_bar_ib_config(rc, bar, cpu_addr, + size, flags); + if (ret) + dev_err(dev, "IB BAR: %d config failed\n", bar); + return ret; + } + + /* + * If the control reaches here, it would mean the remaining + * resource_entry size cannot be fitted in a single BAR. So we + * find a maximum BAR whose size is less than or equal to the + * remaining resource_entry size and split the resource entry + * so that part of resource entry is fitted inside the maximum + * BAR. The remaining size would be fitted during the next + * iteration of the loop. + * If a maximum BAR is not found, there is no way we can fit + * this resource_entry, so we error out. + */ + bar = cdns_pcie_host_find_max_bar(rc, size); + if (bar == RP_BAR_UNDEFINED) { + dev_err(dev, "No free BAR to map cpu_addr %llx\n", + cpu_addr); + return -EINVAL; + } + + winsize = bar_max_size[bar]; + ret = cdns_pcie_host_bar_ib_config(rc, bar, cpu_addr, winsize, + flags); + if (ret) { + dev_err(dev, "IB BAR: %d config failed\n", bar); + return ret; + } + + size -= winsize; + cpu_addr += winsize; + } + + return 0; +} + +static int cdns_pcie_host_dma_ranges_cmp(void *priv, const struct list_head *a, + const struct list_head *b) +{ + struct resource_entry *entry1, *entry2; + + entry1 = container_of(a, struct resource_entry, node); + entry2 = container_of(b, struct resource_entry, node); + + return resource_size(entry2->res) - resource_size(entry1->res); +} + +static int cdns_pcie_host_map_dma_ranges(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + struct device *dev = pcie->dev; + struct device_node *np = dev->of_node; + struct pci_host_bridge *bridge; + struct resource_entry *entry; + u32 no_bar_nbits = 32; + int err; + + bridge = pci_host_bridge_from_priv(rc); + if (!bridge) + return -ENOMEM; + + if (list_empty(&bridge->dma_ranges)) { + of_property_read_u32(np, "cdns,no-bar-match-nbits", + &no_bar_nbits); + err = cdns_pcie_host_bar_ib_config(rc, RP_NO_BAR, 0x0, + (u64)1 << no_bar_nbits, 0); + if (err) + dev_err(dev, "IB BAR: %d config failed\n", RP_NO_BAR); + return err; + } + + list_sort(NULL, &bridge->dma_ranges, cdns_pcie_host_dma_ranges_cmp); + + resource_list_for_each_entry(entry, &bridge->dma_ranges) { + err = cdns_pcie_host_bar_config(rc, entry); + if (err) { + dev_err(dev, "Fail to configure IB using dma-ranges\n"); + return err; + } + } + + return 0; +} + +static int cdns_pcie_host_init_address_translation(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(rc); + struct resource *cfg_res = rc->cfg_res; + struct resource_entry *entry; + u64 cpu_addr = cfg_res->start; + u32 addr0, addr1, desc1; + int r, busnr = 0; + + entry = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (entry) + busnr = entry->res->start; + + /* + * Reserve region 0 for PCI configure space accesses: + * OB_REGION_PCI_ADDR0 and OB_REGION_DESC0 are updated dynamically by + * cdns_pci_map_bus(), other region registers are set here once for all. + */ + addr1 = 0; /* Should be programmed to zero. */ + desc1 = CDNS_PCIE_AT_OB_REGION_DESC1_BUS(busnr); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_PCI_ADDR1(0), addr1); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC1(0), desc1); + + if (pcie->ops->cpu_addr_fixup) + cpu_addr = pcie->ops->cpu_addr_fixup(pcie, cpu_addr); + + addr0 = CDNS_PCIE_AT_OB_REGION_CPU_ADDR0_NBITS(12) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(0), addr0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(0), addr1); + + r = 1; + resource_list_for_each_entry(entry, &bridge->windows) { + struct resource *res = entry->res; + u64 pci_addr = res->start - entry->offset; + + if (resource_type(res) == IORESOURCE_IO) + cdns_pcie_set_outbound_region(pcie, busnr, 0, r, + true, + pci_pio_to_address(res->start), + pci_addr, + resource_size(res)); + else + cdns_pcie_set_outbound_region(pcie, busnr, 0, r, + false, + res->start, + pci_addr, + resource_size(res)); + + r++; + } + + return cdns_pcie_host_map_dma_ranges(rc); +} + +static int cdns_pcie_host_init(struct device *dev, + struct cdns_pcie_rc *rc) +{ + int err; + + err = cdns_pcie_host_init_root_port(rc); + if (err) + return err; + + return cdns_pcie_host_init_address_translation(rc); +} + +int cdns_pcie_host_setup(struct cdns_pcie_rc *rc) +{ + struct device *dev = rc->pcie.dev; + struct platform_device *pdev = to_platform_device(dev); + struct device_node *np = dev->of_node; + struct pci_host_bridge *bridge; + enum cdns_pcie_rp_bar bar; + struct cdns_pcie *pcie; + struct resource *res; + int ret; + + bridge = pci_host_bridge_from_priv(rc); + if (!bridge) + return -ENOMEM; + + pcie = &rc->pcie; + pcie->is_rc = true; + + rc->vendor_id = 0xffff; + of_property_read_u32(np, "vendor-id", &rc->vendor_id); + + rc->device_id = 0xffff; + of_property_read_u32(np, "device-id", &rc->device_id); + + pcie->reg_base = devm_platform_ioremap_resource_byname(pdev, "reg"); + if (IS_ERR(pcie->reg_base)) { + dev_err(dev, "missing \"reg\"\n"); + return PTR_ERR(pcie->reg_base); + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg"); + rc->cfg_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(rc->cfg_base)) + return PTR_ERR(rc->cfg_base); + rc->cfg_res = res; + + if (rc->quirk_detect_quiet_flag) + cdns_pcie_detect_quiet_min_delay_set(&rc->pcie); + + cdns_pcie_host_enable_ptm_response(pcie); + + ret = cdns_pcie_start_link(pcie); + if (ret) { + dev_err(dev, "Failed to start link\n"); + return ret; + } + + ret = cdns_pcie_host_start_link(rc); + if (ret) + dev_dbg(dev, "PCIe link never came up\n"); + + for (bar = RP_BAR0; bar <= RP_NO_BAR; bar++) + rc->avail_ib_bar[bar] = true; + + ret = cdns_pcie_host_init(dev, rc); + if (ret) + return ret; + + if (!bridge->ops) + bridge->ops = &cdns_pcie_host_ops; + + ret = pci_host_probe(bridge); + if (ret < 0) + goto err_init; + + return 0; + + err_init: + pm_runtime_put_sync(dev); + + return ret; +} diff --git a/drivers/pci/controller/cadence/pcie-cadence-plat.c b/drivers/pci/controller/cadence/pcie-cadence-plat.c new file mode 100644 index 000000000..bac054131 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-plat.c @@ -0,0 +1,186 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Cadence PCIe platform driver. + * + * Copyright (c) 2019, Cadence Design Systems + * Author: Tom Joseph <tjoseph@cadence.com> + */ +#include <linux/kernel.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/of_device.h> +#include "pcie-cadence.h" + +#define CDNS_PLAT_CPU_TO_BUS_ADDR 0x0FFFFFFF + +/** + * struct cdns_plat_pcie - private data for this PCIe platform driver + * @pcie: Cadence PCIe controller + * @is_rc: Set to 1 indicates the PCIe controller mode is Root Complex, + * if 0 it is in Endpoint mode. + */ +struct cdns_plat_pcie { + struct cdns_pcie *pcie; + bool is_rc; +}; + +struct cdns_plat_pcie_of_data { + bool is_rc; +}; + +static const struct of_device_id cdns_plat_pcie_of_match[]; + +static u64 cdns_plat_cpu_addr_fixup(struct cdns_pcie *pcie, u64 cpu_addr) +{ + return cpu_addr & CDNS_PLAT_CPU_TO_BUS_ADDR; +} + +static const struct cdns_pcie_ops cdns_plat_ops = { + .cpu_addr_fixup = cdns_plat_cpu_addr_fixup, +}; + +static int cdns_plat_pcie_probe(struct platform_device *pdev) +{ + const struct cdns_plat_pcie_of_data *data; + struct cdns_plat_pcie *cdns_plat_pcie; + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + struct cdns_pcie_ep *ep; + struct cdns_pcie_rc *rc; + int phy_count; + bool is_rc; + int ret; + + data = of_device_get_match_data(dev); + if (!data) + return -EINVAL; + + is_rc = data->is_rc; + + pr_debug(" Started %s with is_rc: %d\n", __func__, is_rc); + cdns_plat_pcie = devm_kzalloc(dev, sizeof(*cdns_plat_pcie), GFP_KERNEL); + if (!cdns_plat_pcie) + return -ENOMEM; + + platform_set_drvdata(pdev, cdns_plat_pcie); + if (is_rc) { + if (!IS_ENABLED(CONFIG_PCIE_CADENCE_PLAT_HOST)) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc)); + if (!bridge) + return -ENOMEM; + + rc = pci_host_bridge_priv(bridge); + rc->pcie.dev = dev; + rc->pcie.ops = &cdns_plat_ops; + cdns_plat_pcie->pcie = &rc->pcie; + cdns_plat_pcie->is_rc = is_rc; + + ret = cdns_pcie_init_phy(dev, cdns_plat_pcie->pcie); + if (ret) { + dev_err(dev, "failed to init phy\n"); + return ret; + } + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "pm_runtime_get_sync() failed\n"); + goto err_get_sync; + } + + ret = cdns_pcie_host_setup(rc); + if (ret) + goto err_init; + } else { + if (!IS_ENABLED(CONFIG_PCIE_CADENCE_PLAT_EP)) + return -ENODEV; + + ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + ep->pcie.dev = dev; + ep->pcie.ops = &cdns_plat_ops; + cdns_plat_pcie->pcie = &ep->pcie; + cdns_plat_pcie->is_rc = is_rc; + + ret = cdns_pcie_init_phy(dev, cdns_plat_pcie->pcie); + if (ret) { + dev_err(dev, "failed to init phy\n"); + return ret; + } + + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "pm_runtime_get_sync() failed\n"); + goto err_get_sync; + } + + ret = cdns_pcie_ep_setup(ep); + if (ret) + goto err_init; + } + + return 0; + + err_init: + err_get_sync: + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); + cdns_pcie_disable_phy(cdns_plat_pcie->pcie); + phy_count = cdns_plat_pcie->pcie->phy_count; + while (phy_count--) + device_link_del(cdns_plat_pcie->pcie->link[phy_count]); + + return 0; +} + +static void cdns_plat_pcie_shutdown(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct cdns_pcie *pcie = dev_get_drvdata(dev); + int ret; + + ret = pm_runtime_put_sync(dev); + if (ret < 0) + dev_dbg(dev, "pm_runtime_put_sync failed\n"); + + pm_runtime_disable(dev); + + cdns_pcie_disable_phy(pcie); +} + +static const struct cdns_plat_pcie_of_data cdns_plat_pcie_host_of_data = { + .is_rc = true, +}; + +static const struct cdns_plat_pcie_of_data cdns_plat_pcie_ep_of_data = { + .is_rc = false, +}; + +static const struct of_device_id cdns_plat_pcie_of_match[] = { + { + .compatible = "cdns,cdns-pcie-host", + .data = &cdns_plat_pcie_host_of_data, + }, + { + .compatible = "cdns,cdns-pcie-ep", + .data = &cdns_plat_pcie_ep_of_data, + }, + {}, +}; + +static struct platform_driver cdns_plat_pcie_driver = { + .driver = { + .name = "cdns-pcie", + .of_match_table = cdns_plat_pcie_of_match, + .pm = &cdns_pcie_pm_ops, + }, + .probe = cdns_plat_pcie_probe, + .shutdown = cdns_plat_pcie_shutdown, +}; +builtin_platform_driver(cdns_plat_pcie_driver); diff --git a/drivers/pci/controller/cadence/pcie-cadence.c b/drivers/pci/controller/cadence/pcie-cadence.c new file mode 100644 index 000000000..13c4032ca --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence.c @@ -0,0 +1,272 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017 Cadence +// Cadence PCIe controller driver. +// Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> + +#include <linux/kernel.h> + +#include "pcie-cadence.h" + +void cdns_pcie_detect_quiet_min_delay_set(struct cdns_pcie *pcie) +{ + u32 delay = 0x3; + u32 ltssm_control_cap; + + /* + * Set the LTSSM Detect Quiet state min. delay to 2ms. + */ + ltssm_control_cap = cdns_pcie_readl(pcie, CDNS_PCIE_LTSSM_CONTROL_CAP); + ltssm_control_cap = ((ltssm_control_cap & + ~CDNS_PCIE_DETECT_QUIET_MIN_DELAY_MASK) | + CDNS_PCIE_DETECT_QUIET_MIN_DELAY(delay)); + + cdns_pcie_writel(pcie, CDNS_PCIE_LTSSM_CONTROL_CAP, ltssm_control_cap); +} + +void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 busnr, u8 fn, + u32 r, bool is_io, + u64 cpu_addr, u64 pci_addr, size_t size) +{ + /* + * roundup_pow_of_two() returns an unsigned long, which is not suited + * for 64bit values. + */ + u64 sz = 1ULL << fls64(size - 1); + int nbits = ilog2(sz); + u32 addr0, addr1, desc0, desc1; + + if (nbits < 8) + nbits = 8; + + /* Set the PCI address */ + addr0 = CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_NBITS(nbits) | + (lower_32_bits(pci_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(pci_addr); + + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_PCI_ADDR0(r), addr0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_PCI_ADDR1(r), addr1); + + /* Set the PCIe header descriptor */ + if (is_io) + desc0 = CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_IO; + else + desc0 = CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_MEM; + desc1 = 0; + + /* + * Whatever Bit [23] is set or not inside DESC0 register of the outbound + * PCIe descriptor, the PCI function number must be set into + * Bits [26:24] of DESC0 anyway. + * + * In Root Complex mode, the function number is always 0 but in Endpoint + * mode, the PCIe controller may support more than one function. This + * function number needs to be set properly into the outbound PCIe + * descriptor. + * + * Besides, setting Bit [23] is mandatory when in Root Complex mode: + * then the driver must provide the bus, resp. device, number in + * Bits [7:0] of DESC1, resp. Bits[31:27] of DESC0. Like the function + * number, the device number is always 0 in Root Complex mode. + * + * However when in Endpoint mode, we can clear Bit [23] of DESC0, hence + * the PCIe controller will use the captured values for the bus and + * device numbers. + */ + if (pcie->is_rc) { + /* The device and function numbers are always 0. */ + desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_HARDCODED_RID | + CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN(0); + desc1 |= CDNS_PCIE_AT_OB_REGION_DESC1_BUS(busnr); + } else { + /* + * Use captured values for bus and device numbers but still + * need to set the function number. + */ + desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN(fn); + } + + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC0(r), desc0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC1(r), desc1); + + /* Set the CPU address */ + if (pcie->ops->cpu_addr_fixup) + cpu_addr = pcie->ops->cpu_addr_fixup(pcie, cpu_addr); + + addr0 = CDNS_PCIE_AT_OB_REGION_CPU_ADDR0_NBITS(nbits) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(r), addr0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(r), addr1); +} + +void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, + u8 busnr, u8 fn, + u32 r, u64 cpu_addr) +{ + u32 addr0, addr1, desc0, desc1; + + desc0 = CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_NORMAL_MSG; + desc1 = 0; + + /* See cdns_pcie_set_outbound_region() comments above. */ + if (pcie->is_rc) { + desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_HARDCODED_RID | + CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN(0); + desc1 |= CDNS_PCIE_AT_OB_REGION_DESC1_BUS(busnr); + } else { + desc0 |= CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN(fn); + } + + /* Set the CPU address */ + if (pcie->ops->cpu_addr_fixup) + cpu_addr = pcie->ops->cpu_addr_fixup(pcie, cpu_addr); + + addr0 = CDNS_PCIE_AT_OB_REGION_CPU_ADDR0_NBITS(17) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_PCI_ADDR0(r), 0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_PCI_ADDR1(r), 0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC0(r), desc0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC1(r), desc1); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(r), addr0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(r), addr1); +} + +void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r) +{ + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_PCI_ADDR0(r), 0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_PCI_ADDR1(r), 0); + + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC0(r), 0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC1(r), 0); + + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(r), 0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(r), 0); +} + +void cdns_pcie_disable_phy(struct cdns_pcie *pcie) +{ + int i = pcie->phy_count; + + while (i--) { + phy_power_off(pcie->phy[i]); + phy_exit(pcie->phy[i]); + } +} + +int cdns_pcie_enable_phy(struct cdns_pcie *pcie) +{ + int ret; + int i; + + for (i = 0; i < pcie->phy_count; i++) { + ret = phy_init(pcie->phy[i]); + if (ret < 0) + goto err_phy; + + ret = phy_power_on(pcie->phy[i]); + if (ret < 0) { + phy_exit(pcie->phy[i]); + goto err_phy; + } + } + + return 0; + +err_phy: + while (--i >= 0) { + phy_power_off(pcie->phy[i]); + phy_exit(pcie->phy[i]); + } + + return ret; +} + +int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie) +{ + struct device_node *np = dev->of_node; + int phy_count; + struct phy **phy; + struct device_link **link; + int i; + int ret; + const char *name; + + phy_count = of_property_count_strings(np, "phy-names"); + if (phy_count < 1) { + dev_err(dev, "no phy-names. PHY will not be initialized\n"); + pcie->phy_count = 0; + return 0; + } + + phy = devm_kcalloc(dev, phy_count, sizeof(*phy), GFP_KERNEL); + if (!phy) + return -ENOMEM; + + link = devm_kcalloc(dev, phy_count, sizeof(*link), GFP_KERNEL); + if (!link) + return -ENOMEM; + + for (i = 0; i < phy_count; i++) { + of_property_read_string_index(np, "phy-names", i, &name); + phy[i] = devm_phy_get(dev, name); + if (IS_ERR(phy[i])) { + ret = PTR_ERR(phy[i]); + goto err_phy; + } + link[i] = device_link_add(dev, &phy[i]->dev, DL_FLAG_STATELESS); + if (!link[i]) { + devm_phy_put(dev, phy[i]); + ret = -EINVAL; + goto err_phy; + } + } + + pcie->phy_count = phy_count; + pcie->phy = phy; + pcie->link = link; + + ret = cdns_pcie_enable_phy(pcie); + if (ret) + goto err_phy; + + return 0; + +err_phy: + while (--i >= 0) { + device_link_del(link[i]); + devm_phy_put(dev, phy[i]); + } + + return ret; +} + +static int cdns_pcie_suspend_noirq(struct device *dev) +{ + struct cdns_pcie *pcie = dev_get_drvdata(dev); + + cdns_pcie_disable_phy(pcie); + + return 0; +} + +static int cdns_pcie_resume_noirq(struct device *dev) +{ + struct cdns_pcie *pcie = dev_get_drvdata(dev); + int ret; + + ret = cdns_pcie_enable_phy(pcie); + if (ret) { + dev_err(dev, "failed to enable phy\n"); + return ret; + } + + return 0; +} + +const struct dev_pm_ops cdns_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(cdns_pcie_suspend_noirq, + cdns_pcie_resume_noirq) +}; diff --git a/drivers/pci/controller/cadence/pcie-cadence.h b/drivers/pci/controller/cadence/pcie-cadence.h new file mode 100644 index 000000000..190786e47 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence.h @@ -0,0 +1,559 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +// Copyright (c) 2017 Cadence +// Cadence PCIe controller driver. +// Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> + +#ifndef _PCIE_CADENCE_H +#define _PCIE_CADENCE_H + +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/pci-epf.h> +#include <linux/phy/phy.h> + +/* Parameters for the waiting for link up routine */ +#define LINK_WAIT_MAX_RETRIES 10 +#define LINK_WAIT_USLEEP_MIN 90000 +#define LINK_WAIT_USLEEP_MAX 100000 + +/* + * Local Management Registers + */ +#define CDNS_PCIE_LM_BASE 0x00100000 + +/* Vendor ID Register */ +#define CDNS_PCIE_LM_ID (CDNS_PCIE_LM_BASE + 0x0044) +#define CDNS_PCIE_LM_ID_VENDOR_MASK GENMASK(15, 0) +#define CDNS_PCIE_LM_ID_VENDOR_SHIFT 0 +#define CDNS_PCIE_LM_ID_VENDOR(vid) \ + (((vid) << CDNS_PCIE_LM_ID_VENDOR_SHIFT) & CDNS_PCIE_LM_ID_VENDOR_MASK) +#define CDNS_PCIE_LM_ID_SUBSYS_MASK GENMASK(31, 16) +#define CDNS_PCIE_LM_ID_SUBSYS_SHIFT 16 +#define CDNS_PCIE_LM_ID_SUBSYS(sub) \ + (((sub) << CDNS_PCIE_LM_ID_SUBSYS_SHIFT) & CDNS_PCIE_LM_ID_SUBSYS_MASK) + +/* Root Port Requestor ID Register */ +#define CDNS_PCIE_LM_RP_RID (CDNS_PCIE_LM_BASE + 0x0228) +#define CDNS_PCIE_LM_RP_RID_MASK GENMASK(15, 0) +#define CDNS_PCIE_LM_RP_RID_SHIFT 0 +#define CDNS_PCIE_LM_RP_RID_(rid) \ + (((rid) << CDNS_PCIE_LM_RP_RID_SHIFT) & CDNS_PCIE_LM_RP_RID_MASK) + +/* Endpoint Bus and Device Number Register */ +#define CDNS_PCIE_LM_EP_ID (CDNS_PCIE_LM_BASE + 0x022c) +#define CDNS_PCIE_LM_EP_ID_DEV_MASK GENMASK(4, 0) +#define CDNS_PCIE_LM_EP_ID_DEV_SHIFT 0 +#define CDNS_PCIE_LM_EP_ID_BUS_MASK GENMASK(15, 8) +#define CDNS_PCIE_LM_EP_ID_BUS_SHIFT 8 + +/* Endpoint Function f BAR b Configuration Registers */ +#define CDNS_PCIE_LM_EP_FUNC_BAR_CFG(bar, fn) \ + (((bar) < BAR_4) ? CDNS_PCIE_LM_EP_FUNC_BAR_CFG0(fn) : CDNS_PCIE_LM_EP_FUNC_BAR_CFG1(fn)) +#define CDNS_PCIE_LM_EP_FUNC_BAR_CFG0(fn) \ + (CDNS_PCIE_LM_BASE + 0x0240 + (fn) * 0x0008) +#define CDNS_PCIE_LM_EP_FUNC_BAR_CFG1(fn) \ + (CDNS_PCIE_LM_BASE + 0x0244 + (fn) * 0x0008) +#define CDNS_PCIE_LM_EP_VFUNC_BAR_CFG(bar, fn) \ + (((bar) < BAR_4) ? CDNS_PCIE_LM_EP_VFUNC_BAR_CFG0(fn) : CDNS_PCIE_LM_EP_VFUNC_BAR_CFG1(fn)) +#define CDNS_PCIE_LM_EP_VFUNC_BAR_CFG0(fn) \ + (CDNS_PCIE_LM_BASE + 0x0280 + (fn) * 0x0008) +#define CDNS_PCIE_LM_EP_VFUNC_BAR_CFG1(fn) \ + (CDNS_PCIE_LM_BASE + 0x0284 + (fn) * 0x0008) +#define CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b) \ + (GENMASK(4, 0) << ((b) * 8)) +#define CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE(b, a) \ + (((a) << ((b) * 8)) & CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b)) +#define CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b) \ + (GENMASK(7, 5) << ((b) * 8)) +#define CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL(b, c) \ + (((c) << ((b) * 8 + 5)) & CDNS_PCIE_LM_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)) + +/* Endpoint Function Configuration Register */ +#define CDNS_PCIE_LM_EP_FUNC_CFG (CDNS_PCIE_LM_BASE + 0x02c0) + +/* Root Complex BAR Configuration Register */ +#define CDNS_PCIE_LM_RC_BAR_CFG (CDNS_PCIE_LM_BASE + 0x0300) +#define CDNS_PCIE_LM_RC_BAR_CFG_BAR0_APERTURE_MASK GENMASK(5, 0) +#define CDNS_PCIE_LM_RC_BAR_CFG_BAR0_APERTURE(a) \ + (((a) << 0) & CDNS_PCIE_LM_RC_BAR_CFG_BAR0_APERTURE_MASK) +#define CDNS_PCIE_LM_RC_BAR_CFG_BAR0_CTRL_MASK GENMASK(8, 6) +#define CDNS_PCIE_LM_RC_BAR_CFG_BAR0_CTRL(c) \ + (((c) << 6) & CDNS_PCIE_LM_RC_BAR_CFG_BAR0_CTRL_MASK) +#define CDNS_PCIE_LM_RC_BAR_CFG_BAR1_APERTURE_MASK GENMASK(13, 9) +#define CDNS_PCIE_LM_RC_BAR_CFG_BAR1_APERTURE(a) \ + (((a) << 9) & CDNS_PCIE_LM_RC_BAR_CFG_BAR1_APERTURE_MASK) +#define CDNS_PCIE_LM_RC_BAR_CFG_BAR1_CTRL_MASK GENMASK(16, 14) +#define CDNS_PCIE_LM_RC_BAR_CFG_BAR1_CTRL(c) \ + (((c) << 14) & CDNS_PCIE_LM_RC_BAR_CFG_BAR1_CTRL_MASK) +#define CDNS_PCIE_LM_RC_BAR_CFG_PREFETCH_MEM_ENABLE BIT(17) +#define CDNS_PCIE_LM_RC_BAR_CFG_PREFETCH_MEM_32BITS 0 +#define CDNS_PCIE_LM_RC_BAR_CFG_PREFETCH_MEM_64BITS BIT(18) +#define CDNS_PCIE_LM_RC_BAR_CFG_IO_ENABLE BIT(19) +#define CDNS_PCIE_LM_RC_BAR_CFG_IO_16BITS 0 +#define CDNS_PCIE_LM_RC_BAR_CFG_IO_32BITS BIT(20) +#define CDNS_PCIE_LM_RC_BAR_CFG_CHECK_ENABLE BIT(31) + +/* BAR control values applicable to both Endpoint Function and Root Complex */ +#define CDNS_PCIE_LM_BAR_CFG_CTRL_DISABLED 0x0 +#define CDNS_PCIE_LM_BAR_CFG_CTRL_IO_32BITS 0x1 +#define CDNS_PCIE_LM_BAR_CFG_CTRL_MEM_32BITS 0x4 +#define CDNS_PCIE_LM_BAR_CFG_CTRL_PREFETCH_MEM_32BITS 0x5 +#define CDNS_PCIE_LM_BAR_CFG_CTRL_MEM_64BITS 0x6 +#define CDNS_PCIE_LM_BAR_CFG_CTRL_PREFETCH_MEM_64BITS 0x7 + +#define LM_RC_BAR_CFG_CTRL_DISABLED(bar) \ + (CDNS_PCIE_LM_BAR_CFG_CTRL_DISABLED << (((bar) * 8) + 6)) +#define LM_RC_BAR_CFG_CTRL_IO_32BITS(bar) \ + (CDNS_PCIE_LM_BAR_CFG_CTRL_IO_32BITS << (((bar) * 8) + 6)) +#define LM_RC_BAR_CFG_CTRL_MEM_32BITS(bar) \ + (CDNS_PCIE_LM_BAR_CFG_CTRL_MEM_32BITS << (((bar) * 8) + 6)) +#define LM_RC_BAR_CFG_CTRL_PREF_MEM_32BITS(bar) \ + (CDNS_PCIE_LM_BAR_CFG_CTRL_PREFETCH_MEM_32BITS << (((bar) * 8) + 6)) +#define LM_RC_BAR_CFG_CTRL_MEM_64BITS(bar) \ + (CDNS_PCIE_LM_BAR_CFG_CTRL_MEM_64BITS << (((bar) * 8) + 6)) +#define LM_RC_BAR_CFG_CTRL_PREF_MEM_64BITS(bar) \ + (CDNS_PCIE_LM_BAR_CFG_CTRL_PREFETCH_MEM_64BITS << (((bar) * 8) + 6)) +#define LM_RC_BAR_CFG_APERTURE(bar, aperture) \ + (((aperture) - 2) << ((bar) * 8)) + +/* PTM Control Register */ +#define CDNS_PCIE_LM_PTM_CTRL (CDNS_PCIE_LM_BASE + 0x0da8) +#define CDNS_PCIE_LM_TPM_CTRL_PTMRSEN BIT(17) + +/* + * Endpoint Function Registers (PCI configuration space for endpoint functions) + */ +#define CDNS_PCIE_EP_FUNC_BASE(fn) (((fn) << 12) & GENMASK(19, 12)) + +#define CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET 0x90 +#define CDNS_PCIE_EP_FUNC_MSIX_CAP_OFFSET 0xb0 +#define CDNS_PCIE_EP_FUNC_DEV_CAP_OFFSET 0xc0 +#define CDNS_PCIE_EP_FUNC_SRIOV_CAP_OFFSET 0x200 + +/* + * Root Port Registers (PCI configuration space for the root port function) + */ +#define CDNS_PCIE_RP_BASE 0x00200000 +#define CDNS_PCIE_RP_CAP_OFFSET 0xc0 + +/* + * Address Translation Registers + */ +#define CDNS_PCIE_AT_BASE 0x00400000 + +/* Region r Outbound AXI to PCIe Address Translation Register 0 */ +#define CDNS_PCIE_AT_OB_REGION_PCI_ADDR0(r) \ + (CDNS_PCIE_AT_BASE + 0x0000 + ((r) & 0x1f) * 0x0020) +#define CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_NBITS_MASK GENMASK(5, 0) +#define CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_NBITS(nbits) \ + (((nbits) - 1) & CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_NBITS_MASK) +#define CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_DEVFN_MASK GENMASK(19, 12) +#define CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_DEVFN(devfn) \ + (((devfn) << 12) & CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_DEVFN_MASK) +#define CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_BUS_MASK GENMASK(27, 20) +#define CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_BUS(bus) \ + (((bus) << 20) & CDNS_PCIE_AT_OB_REGION_PCI_ADDR0_BUS_MASK) + +/* Region r Outbound AXI to PCIe Address Translation Register 1 */ +#define CDNS_PCIE_AT_OB_REGION_PCI_ADDR1(r) \ + (CDNS_PCIE_AT_BASE + 0x0004 + ((r) & 0x1f) * 0x0020) + +/* Region r Outbound PCIe Descriptor Register 0 */ +#define CDNS_PCIE_AT_OB_REGION_DESC0(r) \ + (CDNS_PCIE_AT_BASE + 0x0008 + ((r) & 0x1f) * 0x0020) +#define CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_MASK GENMASK(3, 0) +#define CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_MEM 0x2 +#define CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_IO 0x6 +#define CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_CONF_TYPE0 0xa +#define CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_CONF_TYPE1 0xb +#define CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_NORMAL_MSG 0xc +#define CDNS_PCIE_AT_OB_REGION_DESC0_TYPE_VENDOR_MSG 0xd +/* Bit 23 MUST be set in RC mode. */ +#define CDNS_PCIE_AT_OB_REGION_DESC0_HARDCODED_RID BIT(23) +#define CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN_MASK GENMASK(31, 24) +#define CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN(devfn) \ + (((devfn) << 24) & CDNS_PCIE_AT_OB_REGION_DESC0_DEVFN_MASK) + +/* Region r Outbound PCIe Descriptor Register 1 */ +#define CDNS_PCIE_AT_OB_REGION_DESC1(r) \ + (CDNS_PCIE_AT_BASE + 0x000c + ((r) & 0x1f) * 0x0020) +#define CDNS_PCIE_AT_OB_REGION_DESC1_BUS_MASK GENMASK(7, 0) +#define CDNS_PCIE_AT_OB_REGION_DESC1_BUS(bus) \ + ((bus) & CDNS_PCIE_AT_OB_REGION_DESC1_BUS_MASK) + +/* Region r AXI Region Base Address Register 0 */ +#define CDNS_PCIE_AT_OB_REGION_CPU_ADDR0(r) \ + (CDNS_PCIE_AT_BASE + 0x0018 + ((r) & 0x1f) * 0x0020) +#define CDNS_PCIE_AT_OB_REGION_CPU_ADDR0_NBITS_MASK GENMASK(5, 0) +#define CDNS_PCIE_AT_OB_REGION_CPU_ADDR0_NBITS(nbits) \ + (((nbits) - 1) & CDNS_PCIE_AT_OB_REGION_CPU_ADDR0_NBITS_MASK) + +/* Region r AXI Region Base Address Register 1 */ +#define CDNS_PCIE_AT_OB_REGION_CPU_ADDR1(r) \ + (CDNS_PCIE_AT_BASE + 0x001c + ((r) & 0x1f) * 0x0020) + +/* Root Port BAR Inbound PCIe to AXI Address Translation Register */ +#define CDNS_PCIE_AT_IB_RP_BAR_ADDR0(bar) \ + (CDNS_PCIE_AT_BASE + 0x0800 + (bar) * 0x0008) +#define CDNS_PCIE_AT_IB_RP_BAR_ADDR0_NBITS_MASK GENMASK(5, 0) +#define CDNS_PCIE_AT_IB_RP_BAR_ADDR0_NBITS(nbits) \ + (((nbits) - 1) & CDNS_PCIE_AT_IB_RP_BAR_ADDR0_NBITS_MASK) +#define CDNS_PCIE_AT_IB_RP_BAR_ADDR1(bar) \ + (CDNS_PCIE_AT_BASE + 0x0804 + (bar) * 0x0008) + +/* AXI link down register */ +#define CDNS_PCIE_AT_LINKDOWN (CDNS_PCIE_AT_BASE + 0x0824) + +/* LTSSM Capabilities register */ +#define CDNS_PCIE_LTSSM_CONTROL_CAP (CDNS_PCIE_LM_BASE + 0x0054) +#define CDNS_PCIE_DETECT_QUIET_MIN_DELAY_MASK GENMASK(2, 1) +#define CDNS_PCIE_DETECT_QUIET_MIN_DELAY_SHIFT 1 +#define CDNS_PCIE_DETECT_QUIET_MIN_DELAY(delay) \ + (((delay) << CDNS_PCIE_DETECT_QUIET_MIN_DELAY_SHIFT) & \ + CDNS_PCIE_DETECT_QUIET_MIN_DELAY_MASK) + +enum cdns_pcie_rp_bar { + RP_BAR_UNDEFINED = -1, + RP_BAR0, + RP_BAR1, + RP_NO_BAR +}; + +#define CDNS_PCIE_RP_MAX_IB 0x3 +#define CDNS_PCIE_MAX_OB 32 + +struct cdns_pcie_rp_ib_bar { + u64 size; + bool free; +}; + +/* Endpoint Function BAR Inbound PCIe to AXI Address Translation Register */ +#define CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar) \ + (CDNS_PCIE_AT_BASE + 0x0840 + (fn) * 0x0040 + (bar) * 0x0008) +#define CDNS_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar) \ + (CDNS_PCIE_AT_BASE + 0x0844 + (fn) * 0x0040 + (bar) * 0x0008) + +/* Normal/Vendor specific message access: offset inside some outbound region */ +#define CDNS_PCIE_NORMAL_MSG_ROUTING_MASK GENMASK(7, 5) +#define CDNS_PCIE_NORMAL_MSG_ROUTING(route) \ + (((route) << 5) & CDNS_PCIE_NORMAL_MSG_ROUTING_MASK) +#define CDNS_PCIE_NORMAL_MSG_CODE_MASK GENMASK(15, 8) +#define CDNS_PCIE_NORMAL_MSG_CODE(code) \ + (((code) << 8) & CDNS_PCIE_NORMAL_MSG_CODE_MASK) +#define CDNS_PCIE_MSG_NO_DATA BIT(16) + +struct cdns_pcie; + +enum cdns_pcie_msg_code { + MSG_CODE_ASSERT_INTA = 0x20, + MSG_CODE_ASSERT_INTB = 0x21, + MSG_CODE_ASSERT_INTC = 0x22, + MSG_CODE_ASSERT_INTD = 0x23, + MSG_CODE_DEASSERT_INTA = 0x24, + MSG_CODE_DEASSERT_INTB = 0x25, + MSG_CODE_DEASSERT_INTC = 0x26, + MSG_CODE_DEASSERT_INTD = 0x27, +}; + +enum cdns_pcie_msg_routing { + /* Route to Root Complex */ + MSG_ROUTING_TO_RC, + + /* Use Address Routing */ + MSG_ROUTING_BY_ADDR, + + /* Use ID Routing */ + MSG_ROUTING_BY_ID, + + /* Route as Broadcast Message from Root Complex */ + MSG_ROUTING_BCAST, + + /* Local message; terminate at receiver (INTx messages) */ + MSG_ROUTING_LOCAL, + + /* Gather & route to Root Complex (PME_TO_Ack message) */ + MSG_ROUTING_GATHER, +}; + +struct cdns_pcie_ops { + int (*start_link)(struct cdns_pcie *pcie); + void (*stop_link)(struct cdns_pcie *pcie); + bool (*link_up)(struct cdns_pcie *pcie); + u64 (*cpu_addr_fixup)(struct cdns_pcie *pcie, u64 cpu_addr); +}; + +/** + * struct cdns_pcie - private data for Cadence PCIe controller drivers + * @reg_base: IO mapped register base + * @mem_res: start/end offsets in the physical system memory to map PCI accesses + * @dev: PCIe controller + * @is_rc: tell whether the PCIe controller mode is Root Complex or Endpoint. + * @phy_count: number of supported PHY devices + * @phy: list of pointers to specific PHY control blocks + * @link: list of pointers to corresponding device link representations + * @ops: Platform-specific ops to control various inputs from Cadence PCIe + * wrapper + */ +struct cdns_pcie { + void __iomem *reg_base; + struct resource *mem_res; + struct device *dev; + bool is_rc; + int phy_count; + struct phy **phy; + struct device_link **link; + const struct cdns_pcie_ops *ops; +}; + +/** + * struct cdns_pcie_rc - private data for this PCIe Root Complex driver + * @pcie: Cadence PCIe controller + * @dev: pointer to PCIe device + * @cfg_res: start/end offsets in the physical system memory to map PCI + * configuration space accesses + * @cfg_base: IO mapped window to access the PCI configuration space of a + * single function at a time + * @vendor_id: PCI vendor ID + * @device_id: PCI device ID + * @avail_ib_bar: Status of RP_BAR0, RP_BAR1 and RP_NO_BAR if it's free or + * available + * @quirk_retrain_flag: Retrain link as quirk for PCIe Gen2 + * @quirk_detect_quiet_flag: LTSSM Detect Quiet min delay set as quirk + */ +struct cdns_pcie_rc { + struct cdns_pcie pcie; + struct resource *cfg_res; + void __iomem *cfg_base; + u32 vendor_id; + u32 device_id; + bool avail_ib_bar[CDNS_PCIE_RP_MAX_IB]; + unsigned int quirk_retrain_flag:1; + unsigned int quirk_detect_quiet_flag:1; +}; + +/** + * struct cdns_pcie_epf - Structure to hold info about endpoint function + * @epf: Info about virtual functions attached to the physical function + * @epf_bar: reference to the pci_epf_bar for the six Base Address Registers + */ +struct cdns_pcie_epf { + struct cdns_pcie_epf *epf; + struct pci_epf_bar *epf_bar[PCI_STD_NUM_BARS]; +}; + +/** + * struct cdns_pcie_ep - private data for this PCIe endpoint controller driver + * @pcie: Cadence PCIe controller + * @max_regions: maximum number of regions supported by hardware + * @ob_region_map: bitmask of mapped outbound regions + * @ob_addr: base addresses in the AXI bus where the outbound regions start + * @irq_phys_addr: base address on the AXI bus where the MSI/legacy IRQ + * dedicated outbound regions is mapped. + * @irq_cpu_addr: base address in the CPU space where a write access triggers + * the sending of a memory write (MSI) / normal message (legacy + * IRQ) TLP through the PCIe bus. + * @irq_pci_addr: used to save the current mapping of the MSI/legacy IRQ + * dedicated outbound region. + * @irq_pci_fn: the latest PCI function that has updated the mapping of + * the MSI/legacy IRQ dedicated outbound region. + * @irq_pending: bitmask of asserted legacy IRQs. + * @lock: spin lock to disable interrupts while modifying PCIe controller + * registers fields (RMW) accessible by both remote RC and EP to + * minimize time between read and write + * @epf: Structure to hold info about endpoint function + * @quirk_detect_quiet_flag: LTSSM Detect Quiet min delay set as quirk + * @quirk_disable_flr: Disable FLR (Function Level Reset) quirk flag + */ +struct cdns_pcie_ep { + struct cdns_pcie pcie; + u32 max_regions; + unsigned long ob_region_map; + phys_addr_t *ob_addr; + phys_addr_t irq_phys_addr; + void __iomem *irq_cpu_addr; + u64 irq_pci_addr; + u8 irq_pci_fn; + u8 irq_pending; + /* protect writing to PCI_STATUS while raising legacy interrupts */ + spinlock_t lock; + struct cdns_pcie_epf *epf; + unsigned int quirk_detect_quiet_flag:1; + unsigned int quirk_disable_flr:1; +}; + + +/* Register access */ +static inline void cdns_pcie_writel(struct cdns_pcie *pcie, u32 reg, u32 value) +{ + writel(value, pcie->reg_base + reg); +} + +static inline u32 cdns_pcie_readl(struct cdns_pcie *pcie, u32 reg) +{ + return readl(pcie->reg_base + reg); +} + +static inline u32 cdns_pcie_read_sz(void __iomem *addr, int size) +{ + void __iomem *aligned_addr = PTR_ALIGN_DOWN(addr, 0x4); + unsigned int offset = (unsigned long)addr & 0x3; + u32 val = readl(aligned_addr); + + if (!IS_ALIGNED((uintptr_t)addr, size)) { + pr_warn("Address %p and size %d are not aligned\n", addr, size); + return 0; + } + + if (size > 2) + return val; + + return (val >> (8 * offset)) & ((1 << (size * 8)) - 1); +} + +static inline void cdns_pcie_write_sz(void __iomem *addr, int size, u32 value) +{ + void __iomem *aligned_addr = PTR_ALIGN_DOWN(addr, 0x4); + unsigned int offset = (unsigned long)addr & 0x3; + u32 mask; + u32 val; + + if (!IS_ALIGNED((uintptr_t)addr, size)) { + pr_warn("Address %p and size %d are not aligned\n", addr, size); + return; + } + + if (size > 2) { + writel(value, addr); + return; + } + + mask = ~(((1 << (size * 8)) - 1) << (offset * 8)); + val = readl(aligned_addr) & mask; + val |= value << (offset * 8); + writel(val, aligned_addr); +} + +/* Root Port register access */ +static inline void cdns_pcie_rp_writeb(struct cdns_pcie *pcie, + u32 reg, u8 value) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_RP_BASE + reg; + + cdns_pcie_write_sz(addr, 0x1, value); +} + +static inline void cdns_pcie_rp_writew(struct cdns_pcie *pcie, + u32 reg, u16 value) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_RP_BASE + reg; + + cdns_pcie_write_sz(addr, 0x2, value); +} + +static inline u16 cdns_pcie_rp_readw(struct cdns_pcie *pcie, u32 reg) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_RP_BASE + reg; + + return cdns_pcie_read_sz(addr, 0x2); +} + +/* Endpoint Function register access */ +static inline void cdns_pcie_ep_fn_writeb(struct cdns_pcie *pcie, u8 fn, + u32 reg, u8 value) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg; + + cdns_pcie_write_sz(addr, 0x1, value); +} + +static inline void cdns_pcie_ep_fn_writew(struct cdns_pcie *pcie, u8 fn, + u32 reg, u16 value) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg; + + cdns_pcie_write_sz(addr, 0x2, value); +} + +static inline void cdns_pcie_ep_fn_writel(struct cdns_pcie *pcie, u8 fn, + u32 reg, u32 value) +{ + writel(value, pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg); +} + +static inline u16 cdns_pcie_ep_fn_readw(struct cdns_pcie *pcie, u8 fn, u32 reg) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg; + + return cdns_pcie_read_sz(addr, 0x2); +} + +static inline u32 cdns_pcie_ep_fn_readl(struct cdns_pcie *pcie, u8 fn, u32 reg) +{ + return readl(pcie->reg_base + CDNS_PCIE_EP_FUNC_BASE(fn) + reg); +} + +static inline int cdns_pcie_start_link(struct cdns_pcie *pcie) +{ + if (pcie->ops->start_link) + return pcie->ops->start_link(pcie); + + return 0; +} + +static inline void cdns_pcie_stop_link(struct cdns_pcie *pcie) +{ + if (pcie->ops->stop_link) + pcie->ops->stop_link(pcie); +} + +static inline bool cdns_pcie_link_up(struct cdns_pcie *pcie) +{ + if (pcie->ops->link_up) + return pcie->ops->link_up(pcie); + + return true; +} + +#ifdef CONFIG_PCIE_CADENCE_HOST +int cdns_pcie_host_setup(struct cdns_pcie_rc *rc); +void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn, + int where); +#else +static inline int cdns_pcie_host_setup(struct cdns_pcie_rc *rc) +{ + return 0; +} + +static inline void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) +{ + return NULL; +} +#endif + +#ifdef CONFIG_PCIE_CADENCE_EP +int cdns_pcie_ep_setup(struct cdns_pcie_ep *ep); +#else +static inline int cdns_pcie_ep_setup(struct cdns_pcie_ep *ep) +{ + return 0; +} +#endif + +void cdns_pcie_detect_quiet_min_delay_set(struct cdns_pcie *pcie); + +void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 busnr, u8 fn, + u32 r, bool is_io, + u64 cpu_addr, u64 pci_addr, size_t size); + +void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, + u8 busnr, u8 fn, + u32 r, u64 cpu_addr); + +void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r); +void cdns_pcie_disable_phy(struct cdns_pcie *pcie); +int cdns_pcie_enable_phy(struct cdns_pcie *pcie); +int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie); +extern const struct dev_pm_ops cdns_pcie_pm_ops; + +#endif /* _PCIE_CADENCE_H */ diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig new file mode 100644 index 000000000..ae9d083c4 --- /dev/null +++ b/drivers/pci/controller/dwc/Kconfig @@ -0,0 +1,388 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "DesignWare PCI Core Support" + depends on PCI + +config PCIE_DW + bool + +config PCIE_DW_HOST + bool + select PCIE_DW + +config PCIE_DW_EP + bool + select PCIE_DW + +config PCI_DRA7XX + tristate + +config PCI_DRA7XX_HOST + tristate "TI DRA7xx PCIe controller Host Mode" + depends on SOC_DRA7XX || COMPILE_TEST + depends on OF && HAS_IOMEM && TI_PIPE3 + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + select PCI_DRA7XX + default y if SOC_DRA7XX + help + Enables support for the PCIe controller in the DRA7xx SoC to work in + host mode. There are two instances of PCIe controller in DRA7xx. + This controller can work either as EP or RC. In order to enable + host-specific features PCI_DRA7XX_HOST must be selected and in order + to enable device-specific features PCI_DRA7XX_EP must be selected. + This uses the DesignWare core. + +config PCI_DRA7XX_EP + tristate "TI DRA7xx PCIe controller Endpoint Mode" + depends on SOC_DRA7XX || COMPILE_TEST + depends on OF && HAS_IOMEM && TI_PIPE3 + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PCI_DRA7XX + help + Enables support for the PCIe controller in the DRA7xx SoC to work in + endpoint mode. There are two instances of PCIe controller in DRA7xx. + This controller can work either as EP or RC. In order to enable + host-specific features PCI_DRA7XX_HOST must be selected and in order + to enable device-specific features PCI_DRA7XX_EP must be selected. + This uses the DesignWare core. + +config PCIE_DW_PLAT + bool + +config PCIE_DW_PLAT_HOST + bool "Platform bus based DesignWare PCIe Controller - Host mode" + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + select PCIE_DW_PLAT + help + Enables support for the PCIe controller in the Designware IP to + work in host mode. There are two instances of PCIe controller in + Designware IP. + This controller can work either as EP or RC. In order to enable + host-specific features PCIE_DW_PLAT_HOST must be selected and in + order to enable device-specific features PCI_DW_PLAT_EP must be + selected. + +config PCIE_DW_PLAT_EP + bool "Platform bus based DesignWare PCIe Controller - Endpoint mode" + depends on PCI && PCI_MSI_IRQ_DOMAIN + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PCIE_DW_PLAT + help + Enables support for the PCIe controller in the Designware IP to + work in endpoint mode. There are two instances of PCIe controller + in Designware IP. + This controller can work either as EP or RC. In order to enable + host-specific features PCIE_DW_PLAT_HOST must be selected and in + order to enable device-specific features PCI_DW_PLAT_EP must be + selected. + +config PCI_EXYNOS + tristate "Samsung Exynos PCIe controller" + depends on ARCH_EXYNOS || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + help + Enables support for the PCIe controller in the Samsung Exynos SoCs + to work in host mode. The PCI controller is based on the DesignWare + hardware and therefore the driver re-uses the DesignWare core + functions to implement the driver. + +config PCI_IMX6 + bool "Freescale i.MX6/7/8 PCIe controller" + depends on ARCH_MXC || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + +config PCIE_SPEAR13XX + bool "STMicroelectronics SPEAr PCIe controller" + depends on ARCH_SPEAR13XX || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + help + Say Y here if you want PCIe support on SPEAr13XX SoCs. + +config PCI_KEYSTONE + bool + +config PCI_KEYSTONE_HOST + bool "PCI Keystone Host Mode" + depends on ARCH_KEYSTONE || ARCH_K3 || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + select PCI_KEYSTONE + help + Enables support for the PCIe controller in the Keystone SoC to + work in host mode. The PCI controller on Keystone is based on + DesignWare hardware and therefore the driver re-uses the + DesignWare core functions to implement the driver. + +config PCI_KEYSTONE_EP + bool "PCI Keystone Endpoint Mode" + depends on ARCH_KEYSTONE || ARCH_K3 || COMPILE_TEST + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PCI_KEYSTONE + help + Enables support for the PCIe controller in the Keystone SoC to + work in endpoint mode. The PCI controller on Keystone is based + on DesignWare hardware and therefore the driver re-uses the + DesignWare core functions to implement the driver. + +config PCI_LAYERSCAPE + bool "Freescale Layerscape PCIe controller - Host mode" + depends on OF && (ARM || ARCH_LAYERSCAPE || COMPILE_TEST) + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + select MFD_SYSCON + help + Say Y here if you want to enable PCIe controller support on Layerscape + SoCs to work in Host mode. + This controller can work either as EP or RC. The RCW[HOST_AGT_PEX] + determines which PCIe controller works in EP mode and which PCIe + controller works in RC mode. + +config PCI_LAYERSCAPE_EP + bool "Freescale Layerscape PCIe controller - Endpoint mode" + depends on OF && (ARM || ARCH_LAYERSCAPE || COMPILE_TEST) + depends on PCI_ENDPOINT + select PCIE_DW_EP + help + Say Y here if you want to enable PCIe controller support on Layerscape + SoCs to work in Endpoint mode. + This controller can work either as EP or RC. The RCW[HOST_AGT_PEX] + determines which PCIe controller works in EP mode and which PCIe + controller works in RC mode. + +config PCI_HISI + depends on OF && (ARM64 || COMPILE_TEST) + bool "HiSilicon Hip05 and Hip06 SoCs PCIe controllers" + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + select PCI_HOST_COMMON + help + Say Y here if you want PCIe controller support on HiSilicon + Hip05 and Hip06 SoCs + +config PCIE_QCOM + bool "Qualcomm PCIe controller" + depends on OF && (ARCH_QCOM || COMPILE_TEST) + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + select CRC8 + help + Say Y here to enable PCIe controller support on Qualcomm SoCs. The + PCIe controller uses the DesignWare core plus Qualcomm-specific + hardware wrappers. + +config PCIE_QCOM_EP + tristate "Qualcomm PCIe controller - Endpoint mode" + depends on OF && (ARCH_QCOM || COMPILE_TEST) + depends on PCI_ENDPOINT + select PCIE_DW_EP + help + Say Y here to enable support for the PCIe controllers on Qualcomm SoCs + to work in endpoint mode. The PCIe controller uses the DesignWare core + plus Qualcomm-specific hardware wrappers. + +config PCIE_ARMADA_8K + bool "Marvell Armada-8K PCIe controller" + depends on ARCH_MVEBU || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + help + Say Y here if you want to enable PCIe controller support on + Armada-8K SoCs. The PCIe controller on Armada-8K is based on + DesignWare hardware and therefore the driver re-uses the + DesignWare core functions to implement the driver. + +config PCIE_ARTPEC6 + bool + +config PCIE_ARTPEC6_HOST + bool "Axis ARTPEC-6 PCIe controller Host Mode" + depends on MACH_ARTPEC6 || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + select PCIE_ARTPEC6 + help + Enables support for the PCIe controller in the ARTPEC-6 SoC to work in + host mode. This uses the DesignWare core. + +config PCIE_ARTPEC6_EP + bool "Axis ARTPEC-6 PCIe controller Endpoint Mode" + depends on MACH_ARTPEC6 || COMPILE_TEST + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PCIE_ARTPEC6 + help + Enables support for the PCIe controller in the ARTPEC-6 SoC to work in + endpoint mode. This uses the DesignWare core. + +config PCIE_ROCKCHIP_DW_HOST + bool "Rockchip DesignWare PCIe controller" + select PCIE_DW + select PCIE_DW_HOST + depends on PCI_MSI_IRQ_DOMAIN + depends on ARCH_ROCKCHIP || COMPILE_TEST + depends on OF + help + Enables support for the DesignWare PCIe controller in the + Rockchip SoC except RK3399. + +config PCIE_INTEL_GW + bool "Intel Gateway PCIe host controller support" + depends on OF && (X86 || COMPILE_TEST) + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + help + Say 'Y' here to enable PCIe Host controller support on Intel + Gateway SoCs. + The PCIe controller uses the DesignWare core plus Intel-specific + hardware wrappers. + +config PCIE_KEEMBAY + bool + +config PCIE_KEEMBAY_HOST + bool "Intel Keem Bay PCIe controller - Host mode" + depends on ARCH_KEEMBAY || COMPILE_TEST + depends on PCI && PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + select PCIE_KEEMBAY + help + Say 'Y' here to enable support for the PCIe controller in Keem Bay + to work in host mode. + The PCIe controller is based on DesignWare Hardware and uses + DesignWare core functions. + +config PCIE_KEEMBAY_EP + bool "Intel Keem Bay PCIe controller - Endpoint mode" + depends on ARCH_KEEMBAY || COMPILE_TEST + depends on PCI && PCI_MSI_IRQ_DOMAIN + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PCIE_KEEMBAY + help + Say 'Y' here to enable support for the PCIe controller in Keem Bay + to work in endpoint mode. + The PCIe controller is based on DesignWare Hardware and uses + DesignWare core functions. + +config PCIE_KIRIN + depends on OF && (ARM64 || COMPILE_TEST) + tristate "HiSilicon Kirin series SoCs PCIe controllers" + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + help + Say Y here if you want PCIe controller support + on HiSilicon Kirin series SoCs. + +config PCIE_HISI_STB + bool "HiSilicon STB SoCs PCIe controllers" + depends on ARCH_HISI || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + help + Say Y here if you want PCIe controller support on HiSilicon STB SoCs + +config PCI_MESON + tristate "MESON PCIe controller" + default m if ARCH_MESON + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + select REGMAP_MMIO + help + Say Y here if you want to enable PCI controller support on Amlogic + SoCs. The PCI controller on Amlogic is based on DesignWare hardware + and therefore the driver re-uses the DesignWare core functions to + implement the driver. + +config PCIE_TEGRA194 + tristate + +config PCIE_TEGRA194_HOST + tristate "NVIDIA Tegra194 (and later) PCIe controller - Host Mode" + depends on ARCH_TEGRA_194_SOC || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + select PHY_TEGRA194_P2U + select PCIE_TEGRA194 + help + Enables support for the PCIe controller in the NVIDIA Tegra194 SoC to + work in host mode. There are two instances of PCIe controllers in + Tegra194. This controller can work either as EP or RC. In order to + enable host-specific features PCIE_TEGRA194_HOST must be selected and + in order to enable device-specific features PCIE_TEGRA194_EP must be + selected. This uses the DesignWare core. + +config PCIE_TEGRA194_EP + tristate "NVIDIA Tegra194 (and later) PCIe controller - Endpoint Mode" + depends on ARCH_TEGRA_194_SOC || COMPILE_TEST + depends on PCI_ENDPOINT + select PCIE_DW_EP + select PHY_TEGRA194_P2U + select PCIE_TEGRA194 + help + Enables support for the PCIe controller in the NVIDIA Tegra194 SoC to + work in endpoint mode. There are two instances of PCIe controllers in + Tegra194. This controller can work either as EP or RC. In order to + enable host-specific features PCIE_TEGRA194_HOST must be selected and + in order to enable device-specific features PCIE_TEGRA194_EP must be + selected. This uses the DesignWare core. + +config PCIE_VISCONTI_HOST + bool "Toshiba Visconti PCIe controllers" + depends on ARCH_VISCONTI || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + help + Say Y here if you want PCIe controller support on Toshiba Visconti SoC. + This driver supports TMPV7708 SoC. + +config PCIE_UNIPHIER + bool "Socionext UniPhier PCIe host controllers" + depends on ARCH_UNIPHIER || COMPILE_TEST + depends on OF && HAS_IOMEM + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + help + Say Y here if you want PCIe host controller support on UniPhier SoCs. + This driver supports LD20 and PXs3 SoCs. + +config PCIE_UNIPHIER_EP + bool "Socionext UniPhier PCIe endpoint controllers" + depends on ARCH_UNIPHIER || COMPILE_TEST + depends on OF && HAS_IOMEM + depends on PCI_ENDPOINT + select PCIE_DW_EP + help + Say Y here if you want PCIe endpoint controller support on + UniPhier SoCs. This driver supports Pro5 SoC. + +config PCIE_AL + bool "Amazon Annapurna Labs PCIe controller" + depends on OF && (ARM64 || COMPILE_TEST) + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_DW_HOST + select PCI_ECAM + help + Say Y here to enable support of the Amazon's Annapurna Labs PCIe + controller IP on Amazon SoCs. The PCIe controller uses the DesignWare + core plus Annapurna Labs proprietary hardware wrappers. This is + required only for DT-based platforms. ACPI platforms with the + Annapurna Labs PCIe controller don't need to enable this. + +config PCIE_FU740 + bool "SiFive FU740 PCIe host controller" + depends on PCI_MSI_IRQ_DOMAIN + depends on SOC_SIFIVE || COMPILE_TEST + select PCIE_DW_HOST + help + Say Y here if you want PCIe controller support for the SiFive + FU740. + +endmenu diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile new file mode 100644 index 000000000..8ba7b67f5 --- /dev/null +++ b/drivers/pci/controller/dwc/Makefile @@ -0,0 +1,48 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_PCIE_DW) += pcie-designware.o +obj-$(CONFIG_PCIE_DW_HOST) += pcie-designware-host.o +obj-$(CONFIG_PCIE_DW_EP) += pcie-designware-ep.o +obj-$(CONFIG_PCIE_DW_PLAT) += pcie-designware-plat.o +obj-$(CONFIG_PCI_DRA7XX) += pci-dra7xx.o +obj-$(CONFIG_PCI_EXYNOS) += pci-exynos.o +obj-$(CONFIG_PCIE_FU740) += pcie-fu740.o +obj-$(CONFIG_PCI_IMX6) += pci-imx6.o +obj-$(CONFIG_PCIE_SPEAR13XX) += pcie-spear13xx.o +obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone.o +obj-$(CONFIG_PCI_LAYERSCAPE) += pci-layerscape.o +obj-$(CONFIG_PCI_LAYERSCAPE_EP) += pci-layerscape-ep.o +obj-$(CONFIG_PCIE_QCOM) += pcie-qcom.o +obj-$(CONFIG_PCIE_QCOM_EP) += pcie-qcom-ep.o +obj-$(CONFIG_PCIE_ARMADA_8K) += pcie-armada8k.o +obj-$(CONFIG_PCIE_ARTPEC6) += pcie-artpec6.o +obj-$(CONFIG_PCIE_ROCKCHIP_DW_HOST) += pcie-dw-rockchip.o +obj-$(CONFIG_PCIE_INTEL_GW) += pcie-intel-gw.o +obj-$(CONFIG_PCIE_KEEMBAY) += pcie-keembay.o +obj-$(CONFIG_PCIE_KIRIN) += pcie-kirin.o +obj-$(CONFIG_PCIE_HISI_STB) += pcie-histb.o +obj-$(CONFIG_PCI_MESON) += pci-meson.o +obj-$(CONFIG_PCIE_TEGRA194) += pcie-tegra194.o +obj-$(CONFIG_PCIE_UNIPHIER) += pcie-uniphier.o +obj-$(CONFIG_PCIE_UNIPHIER_EP) += pcie-uniphier-ep.o +obj-$(CONFIG_PCIE_VISCONTI_HOST) += pcie-visconti.o + +# The following drivers are for devices that use the generic ACPI +# pci_root.c driver but don't support standard ECAM config access. +# They contain MCFG quirks to replace the generic ECAM accessors with +# device-specific ones that are shared with the DT driver. + +# The ACPI driver is generic and should not require driver-specific +# config options to be enabled, so we always build these drivers on +# ARM64 and use internal ifdefs to only build the pieces we need +# depending on whether ACPI, the DT driver, or both are enabled. + +obj-$(CONFIG_PCIE_AL) += pcie-al.o +obj-$(CONFIG_PCI_HISI) += pcie-hisi.o + +ifdef CONFIG_ACPI +ifdef CONFIG_PCI_QUIRKS +obj-$(CONFIG_ARM64) += pcie-al.o +obj-$(CONFIG_ARM64) += pcie-hisi.o +obj-$(CONFIG_ARM64) += pcie-tegra194-acpi.o +endif +endif diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c new file mode 100644 index 000000000..38462ed11 --- /dev/null +++ b/drivers/pci/controller/dwc/pci-dra7xx.c @@ -0,0 +1,960 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * pcie-dra7xx - PCIe controller driver for TI DRA7xx SoCs + * + * Copyright (C) 2013-2014 Texas Instruments Incorporated - https://www.ti.com + * + * Authors: Kishon Vijay Abraham I <kishon@ti.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/of_gpio.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/resource.h> +#include <linux/types.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> +#include <linux/gpio/consumer.h> + +#include "../../pci.h" +#include "pcie-designware.h" + +/* PCIe controller wrapper DRA7XX configuration registers */ + +#define PCIECTRL_DRA7XX_CONF_IRQSTATUS_MAIN 0x0024 +#define PCIECTRL_DRA7XX_CONF_IRQENABLE_SET_MAIN 0x0028 +#define ERR_SYS BIT(0) +#define ERR_FATAL BIT(1) +#define ERR_NONFATAL BIT(2) +#define ERR_COR BIT(3) +#define ERR_AXI BIT(4) +#define ERR_ECRC BIT(5) +#define PME_TURN_OFF BIT(8) +#define PME_TO_ACK BIT(9) +#define PM_PME BIT(10) +#define LINK_REQ_RST BIT(11) +#define LINK_UP_EVT BIT(12) +#define CFG_BME_EVT BIT(13) +#define CFG_MSE_EVT BIT(14) +#define INTERRUPTS (ERR_SYS | ERR_FATAL | ERR_NONFATAL | ERR_COR | ERR_AXI | \ + ERR_ECRC | PME_TURN_OFF | PME_TO_ACK | PM_PME | \ + LINK_REQ_RST | LINK_UP_EVT | CFG_BME_EVT | CFG_MSE_EVT) + +#define PCIECTRL_DRA7XX_CONF_IRQSTATUS_MSI 0x0034 +#define PCIECTRL_DRA7XX_CONF_IRQENABLE_SET_MSI 0x0038 +#define INTA BIT(0) +#define INTB BIT(1) +#define INTC BIT(2) +#define INTD BIT(3) +#define MSI BIT(4) +#define LEG_EP_INTERRUPTS (INTA | INTB | INTC | INTD) + +#define PCIECTRL_TI_CONF_DEVICE_TYPE 0x0100 +#define DEVICE_TYPE_EP 0x0 +#define DEVICE_TYPE_LEG_EP 0x1 +#define DEVICE_TYPE_RC 0x4 + +#define PCIECTRL_DRA7XX_CONF_DEVICE_CMD 0x0104 +#define LTSSM_EN 0x1 + +#define PCIECTRL_DRA7XX_CONF_PHY_CS 0x010C +#define LINK_UP BIT(16) +#define DRA7XX_CPU_TO_BUS_ADDR 0x0FFFFFFF + +#define PCIECTRL_TI_CONF_INTX_ASSERT 0x0124 +#define PCIECTRL_TI_CONF_INTX_DEASSERT 0x0128 + +#define PCIECTRL_TI_CONF_MSI_XMT 0x012c +#define MSI_REQ_GRANT BIT(0) +#define MSI_VECTOR_SHIFT 7 + +#define PCIE_1LANE_2LANE_SELECTION BIT(13) +#define PCIE_B1C0_MODE_SEL BIT(2) +#define PCIE_B0_B1_TSYNCEN BIT(0) + +struct dra7xx_pcie { + struct dw_pcie *pci; + void __iomem *base; /* DT ti_conf */ + int phy_count; /* DT phy-names count */ + struct phy **phy; + struct irq_domain *irq_domain; + struct clk *clk; + enum dw_pcie_device_mode mode; +}; + +struct dra7xx_pcie_of_data { + enum dw_pcie_device_mode mode; + u32 b1co_mode_sel_mask; +}; + +#define to_dra7xx_pcie(x) dev_get_drvdata((x)->dev) + +static inline u32 dra7xx_pcie_readl(struct dra7xx_pcie *pcie, u32 offset) +{ + return readl(pcie->base + offset); +} + +static inline void dra7xx_pcie_writel(struct dra7xx_pcie *pcie, u32 offset, + u32 value) +{ + writel(value, pcie->base + offset); +} + +static u64 dra7xx_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 pci_addr) +{ + return pci_addr & DRA7XX_CPU_TO_BUS_ADDR; +} + +static int dra7xx_pcie_link_up(struct dw_pcie *pci) +{ + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); + u32 reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_PHY_CS); + + return !!(reg & LINK_UP); +} + +static void dra7xx_pcie_stop_link(struct dw_pcie *pci) +{ + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); + u32 reg; + + reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD); + reg &= ~LTSSM_EN; + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD, reg); +} + +static int dra7xx_pcie_establish_link(struct dw_pcie *pci) +{ + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); + struct device *dev = pci->dev; + u32 reg; + + if (dw_pcie_link_up(pci)) { + dev_err(dev, "link is already up\n"); + return 0; + } + + reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD); + reg |= LTSSM_EN; + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD, reg); + + return 0; +} + +static void dra7xx_pcie_enable_msi_interrupts(struct dra7xx_pcie *dra7xx) +{ + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MSI, + LEG_EP_INTERRUPTS | MSI); + + dra7xx_pcie_writel(dra7xx, + PCIECTRL_DRA7XX_CONF_IRQENABLE_SET_MSI, + MSI | LEG_EP_INTERRUPTS); +} + +static void dra7xx_pcie_enable_wrapper_interrupts(struct dra7xx_pcie *dra7xx) +{ + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MAIN, + INTERRUPTS); + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_IRQENABLE_SET_MAIN, + INTERRUPTS); +} + +static void dra7xx_pcie_enable_interrupts(struct dra7xx_pcie *dra7xx) +{ + dra7xx_pcie_enable_wrapper_interrupts(dra7xx); + dra7xx_pcie_enable_msi_interrupts(dra7xx); +} + +static int dra7xx_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); + + dra7xx_pcie_enable_interrupts(dra7xx); + + return 0; +} + +static int dra7xx_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &dummy_irq_chip, handle_simple_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops intx_domain_ops = { + .map = dra7xx_pcie_intx_map, + .xlate = pci_irqd_intx_xlate, +}; + +static int dra7xx_pcie_handle_msi(struct dw_pcie_rp *pp, int index) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + unsigned long val; + int pos; + + val = dw_pcie_readl_dbi(pci, PCIE_MSI_INTR0_STATUS + + (index * MSI_REG_CTRL_BLOCK_SIZE)); + if (!val) + return 0; + + pos = find_first_bit(&val, MAX_MSI_IRQS_PER_CTRL); + while (pos != MAX_MSI_IRQS_PER_CTRL) { + generic_handle_domain_irq(pp->irq_domain, + (index * MAX_MSI_IRQS_PER_CTRL) + pos); + pos++; + pos = find_next_bit(&val, MAX_MSI_IRQS_PER_CTRL, pos); + } + + return 1; +} + +static void dra7xx_pcie_handle_msi_irq(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + int ret, i, count, num_ctrls; + + num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; + + /** + * Need to make sure all MSI status bits read 0 before exiting. + * Else, new MSI IRQs are not registered by the wrapper. Have an + * upperbound for the loop and exit the IRQ in case of IRQ flood + * to avoid locking up system in interrupt context. + */ + count = 0; + do { + ret = 0; + + for (i = 0; i < num_ctrls; i++) + ret |= dra7xx_pcie_handle_msi(pp, i); + count++; + } while (ret && count <= 1000); + + if (count > 1000) + dev_warn_ratelimited(pci->dev, + "Too many MSI IRQs to handle\n"); +} + +static void dra7xx_pcie_msi_irq_handler(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct dra7xx_pcie *dra7xx; + struct dw_pcie_rp *pp; + struct dw_pcie *pci; + unsigned long reg; + u32 bit; + + chained_irq_enter(chip, desc); + + pp = irq_desc_get_handler_data(desc); + pci = to_dw_pcie_from_pp(pp); + dra7xx = to_dra7xx_pcie(pci); + + reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MSI); + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MSI, reg); + + switch (reg) { + case MSI: + dra7xx_pcie_handle_msi_irq(pp); + break; + case INTA: + case INTB: + case INTC: + case INTD: + for_each_set_bit(bit, ®, PCI_NUM_INTX) + generic_handle_domain_irq(dra7xx->irq_domain, bit); + break; + } + + chained_irq_exit(chip, desc); +} + +static irqreturn_t dra7xx_pcie_irq_handler(int irq, void *arg) +{ + struct dra7xx_pcie *dra7xx = arg; + struct dw_pcie *pci = dra7xx->pci; + struct device *dev = pci->dev; + struct dw_pcie_ep *ep = &pci->ep; + u32 reg; + + reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MAIN); + + if (reg & ERR_SYS) + dev_dbg(dev, "System Error\n"); + + if (reg & ERR_FATAL) + dev_dbg(dev, "Fatal Error\n"); + + if (reg & ERR_NONFATAL) + dev_dbg(dev, "Non Fatal Error\n"); + + if (reg & ERR_COR) + dev_dbg(dev, "Correctable Error\n"); + + if (reg & ERR_AXI) + dev_dbg(dev, "AXI tag lookup fatal Error\n"); + + if (reg & ERR_ECRC) + dev_dbg(dev, "ECRC Error\n"); + + if (reg & PME_TURN_OFF) + dev_dbg(dev, + "Power Management Event Turn-Off message received\n"); + + if (reg & PME_TO_ACK) + dev_dbg(dev, + "Power Management Turn-Off Ack message received\n"); + + if (reg & PM_PME) + dev_dbg(dev, "PM Power Management Event message received\n"); + + if (reg & LINK_REQ_RST) + dev_dbg(dev, "Link Request Reset\n"); + + if (reg & LINK_UP_EVT) { + if (dra7xx->mode == DW_PCIE_EP_TYPE) + dw_pcie_ep_linkup(ep); + dev_dbg(dev, "Link-up state change\n"); + } + + if (reg & CFG_BME_EVT) + dev_dbg(dev, "CFG 'Bus Master Enable' change\n"); + + if (reg & CFG_MSE_EVT) + dev_dbg(dev, "CFG 'Memory Space Enable' change\n"); + + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_IRQSTATUS_MAIN, reg); + + return IRQ_HANDLED; +} + +static int dra7xx_pcie_init_irq_domain(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); + struct device_node *node = dev->of_node; + struct device_node *pcie_intc_node = of_get_next_child(node, NULL); + + if (!pcie_intc_node) { + dev_err(dev, "No PCIe Intc node found\n"); + return -ENODEV; + } + + irq_set_chained_handler_and_data(pp->irq, dra7xx_pcie_msi_irq_handler, + pp); + dra7xx->irq_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, + &intx_domain_ops, pp); + of_node_put(pcie_intc_node); + if (!dra7xx->irq_domain) { + dev_err(dev, "Failed to get a INTx IRQ domain\n"); + return -ENODEV; + } + + return 0; +} + +static const struct dw_pcie_host_ops dra7xx_pcie_host_ops = { + .host_init = dra7xx_pcie_host_init, +}; + +static void dra7xx_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); + enum pci_barno bar; + + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) + dw_pcie_ep_reset_bar(pci, bar); + + dra7xx_pcie_enable_wrapper_interrupts(dra7xx); +} + +static void dra7xx_pcie_raise_legacy_irq(struct dra7xx_pcie *dra7xx) +{ + dra7xx_pcie_writel(dra7xx, PCIECTRL_TI_CONF_INTX_ASSERT, 0x1); + mdelay(1); + dra7xx_pcie_writel(dra7xx, PCIECTRL_TI_CONF_INTX_DEASSERT, 0x1); +} + +static void dra7xx_pcie_raise_msi_irq(struct dra7xx_pcie *dra7xx, + u8 interrupt_num) +{ + u32 reg; + + reg = (interrupt_num - 1) << MSI_VECTOR_SHIFT; + reg |= MSI_REQ_GRANT; + dra7xx_pcie_writel(dra7xx, PCIECTRL_TI_CONF_MSI_XMT, reg); +} + +static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + enum pci_epc_irq_type type, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + dra7xx_pcie_raise_legacy_irq(dra7xx); + break; + case PCI_EPC_IRQ_MSI: + dra7xx_pcie_raise_msi_irq(dra7xx, interrupt_num); + break; + default: + dev_err(pci->dev, "UNKNOWN IRQ type\n"); + } + + return 0; +} + +static const struct pci_epc_features dra7xx_pcie_epc_features = { + .linkup_notifier = true, + .msi_capable = true, + .msix_capable = false, +}; + +static const struct pci_epc_features* +dra7xx_pcie_get_features(struct dw_pcie_ep *ep) +{ + return &dra7xx_pcie_epc_features; +} + +static const struct dw_pcie_ep_ops pcie_ep_ops = { + .ep_init = dra7xx_pcie_ep_init, + .raise_irq = dra7xx_pcie_raise_irq, + .get_features = dra7xx_pcie_get_features, +}; + +static int dra7xx_add_pcie_ep(struct dra7xx_pcie *dra7xx, + struct platform_device *pdev) +{ + int ret; + struct dw_pcie_ep *ep; + struct device *dev = &pdev->dev; + struct dw_pcie *pci = dra7xx->pci; + + ep = &pci->ep; + ep->ops = &pcie_ep_ops; + + pci->dbi_base = devm_platform_ioremap_resource_byname(pdev, "ep_dbics"); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + + pci->dbi_base2 = + devm_platform_ioremap_resource_byname(pdev, "ep_dbics2"); + if (IS_ERR(pci->dbi_base2)) + return PTR_ERR(pci->dbi_base2); + + ret = dw_pcie_ep_init(ep); + if (ret) { + dev_err(dev, "failed to initialize endpoint\n"); + return ret; + } + + return 0; +} + +static int dra7xx_add_pcie_port(struct dra7xx_pcie *dra7xx, + struct platform_device *pdev) +{ + int ret; + struct dw_pcie *pci = dra7xx->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = pci->dev; + + pp->irq = platform_get_irq(pdev, 1); + if (pp->irq < 0) + return pp->irq; + + /* MSI IRQ is muxed */ + pp->msi_irq[0] = -ENODEV; + + ret = dra7xx_pcie_init_irq_domain(pp); + if (ret < 0) + return ret; + + pci->dbi_base = devm_platform_ioremap_resource_byname(pdev, "rc_dbics"); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + + pp->ops = &dra7xx_pcie_host_ops; + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "failed to initialize host\n"); + return ret; + } + + return 0; +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .cpu_addr_fixup = dra7xx_pcie_cpu_addr_fixup, + .start_link = dra7xx_pcie_establish_link, + .stop_link = dra7xx_pcie_stop_link, + .link_up = dra7xx_pcie_link_up, +}; + +static void dra7xx_pcie_disable_phy(struct dra7xx_pcie *dra7xx) +{ + int phy_count = dra7xx->phy_count; + + while (phy_count--) { + phy_power_off(dra7xx->phy[phy_count]); + phy_exit(dra7xx->phy[phy_count]); + } +} + +static int dra7xx_pcie_enable_phy(struct dra7xx_pcie *dra7xx) +{ + int phy_count = dra7xx->phy_count; + int ret; + int i; + + for (i = 0; i < phy_count; i++) { + ret = phy_set_mode(dra7xx->phy[i], PHY_MODE_PCIE); + if (ret < 0) + goto err_phy; + + ret = phy_init(dra7xx->phy[i]); + if (ret < 0) + goto err_phy; + + ret = phy_power_on(dra7xx->phy[i]); + if (ret < 0) { + phy_exit(dra7xx->phy[i]); + goto err_phy; + } + } + + return 0; + +err_phy: + while (--i >= 0) { + phy_power_off(dra7xx->phy[i]); + phy_exit(dra7xx->phy[i]); + } + + return ret; +} + +static const struct dra7xx_pcie_of_data dra7xx_pcie_rc_of_data = { + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct dra7xx_pcie_of_data dra7xx_pcie_ep_of_data = { + .mode = DW_PCIE_EP_TYPE, +}; + +static const struct dra7xx_pcie_of_data dra746_pcie_rc_of_data = { + .b1co_mode_sel_mask = BIT(2), + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct dra7xx_pcie_of_data dra726_pcie_rc_of_data = { + .b1co_mode_sel_mask = GENMASK(3, 2), + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct dra7xx_pcie_of_data dra746_pcie_ep_of_data = { + .b1co_mode_sel_mask = BIT(2), + .mode = DW_PCIE_EP_TYPE, +}; + +static const struct dra7xx_pcie_of_data dra726_pcie_ep_of_data = { + .b1co_mode_sel_mask = GENMASK(3, 2), + .mode = DW_PCIE_EP_TYPE, +}; + +static const struct of_device_id of_dra7xx_pcie_match[] = { + { + .compatible = "ti,dra7-pcie", + .data = &dra7xx_pcie_rc_of_data, + }, + { + .compatible = "ti,dra7-pcie-ep", + .data = &dra7xx_pcie_ep_of_data, + }, + { + .compatible = "ti,dra746-pcie-rc", + .data = &dra746_pcie_rc_of_data, + }, + { + .compatible = "ti,dra726-pcie-rc", + .data = &dra726_pcie_rc_of_data, + }, + { + .compatible = "ti,dra746-pcie-ep", + .data = &dra746_pcie_ep_of_data, + }, + { + .compatible = "ti,dra726-pcie-ep", + .data = &dra726_pcie_ep_of_data, + }, + {}, +}; +MODULE_DEVICE_TABLE(of, of_dra7xx_pcie_match); + +/* + * dra7xx_pcie_unaligned_memaccess: workaround for AM572x/AM571x Errata i870 + * @dra7xx: the dra7xx device where the workaround should be applied + * + * Access to the PCIe slave port that are not 32-bit aligned will result + * in incorrect mapping to TLP Address and Byte enable fields. Therefore, + * byte and half-word accesses are not possible to byte offset 0x1, 0x2, or + * 0x3. + * + * To avoid this issue set PCIE_SS1_AXI2OCP_LEGACY_MODE_ENABLE to 1. + */ +static int dra7xx_pcie_unaligned_memaccess(struct device *dev) +{ + int ret; + struct device_node *np = dev->of_node; + struct of_phandle_args args; + struct regmap *regmap; + + regmap = syscon_regmap_lookup_by_phandle(np, + "ti,syscon-unaligned-access"); + if (IS_ERR(regmap)) { + dev_dbg(dev, "can't get ti,syscon-unaligned-access\n"); + return -EINVAL; + } + + ret = of_parse_phandle_with_fixed_args(np, "ti,syscon-unaligned-access", + 2, 0, &args); + if (ret) { + dev_err(dev, "failed to parse ti,syscon-unaligned-access\n"); + return ret; + } + + ret = regmap_update_bits(regmap, args.args[0], args.args[1], + args.args[1]); + if (ret) + dev_err(dev, "failed to enable unaligned access\n"); + + of_node_put(args.np); + + return ret; +} + +static int dra7xx_pcie_configure_two_lane(struct device *dev, + u32 b1co_mode_sel_mask) +{ + struct device_node *np = dev->of_node; + struct regmap *pcie_syscon; + unsigned int pcie_reg; + u32 mask; + u32 val; + + pcie_syscon = syscon_regmap_lookup_by_phandle(np, "ti,syscon-lane-sel"); + if (IS_ERR(pcie_syscon)) { + dev_err(dev, "unable to get ti,syscon-lane-sel\n"); + return -EINVAL; + } + + if (of_property_read_u32_index(np, "ti,syscon-lane-sel", 1, + &pcie_reg)) { + dev_err(dev, "couldn't get lane selection reg offset\n"); + return -EINVAL; + } + + mask = b1co_mode_sel_mask | PCIE_B0_B1_TSYNCEN; + val = PCIE_B1C0_MODE_SEL | PCIE_B0_B1_TSYNCEN; + regmap_update_bits(pcie_syscon, pcie_reg, mask, val); + + return 0; +} + +static int dra7xx_pcie_probe(struct platform_device *pdev) +{ + u32 reg; + int ret; + int irq; + int i; + int phy_count; + struct phy **phy; + struct device_link **link; + void __iomem *base; + struct dw_pcie *pci; + struct dra7xx_pcie *dra7xx; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + char name[10]; + struct gpio_desc *reset; + const struct dra7xx_pcie_of_data *data; + enum dw_pcie_device_mode mode; + u32 b1co_mode_sel_mask; + + data = of_device_get_match_data(dev); + if (!data) + return -EINVAL; + + mode = (enum dw_pcie_device_mode)data->mode; + b1co_mode_sel_mask = data->b1co_mode_sel_mask; + + dra7xx = devm_kzalloc(dev, sizeof(*dra7xx), GFP_KERNEL); + if (!dra7xx) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pci->dev = dev; + pci->ops = &dw_pcie_ops; + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + base = devm_platform_ioremap_resource_byname(pdev, "ti_conf"); + if (IS_ERR(base)) + return PTR_ERR(base); + + phy_count = of_property_count_strings(np, "phy-names"); + if (phy_count < 0) { + dev_err(dev, "unable to find the strings\n"); + return phy_count; + } + + phy = devm_kcalloc(dev, phy_count, sizeof(*phy), GFP_KERNEL); + if (!phy) + return -ENOMEM; + + link = devm_kcalloc(dev, phy_count, sizeof(*link), GFP_KERNEL); + if (!link) + return -ENOMEM; + + dra7xx->clk = devm_clk_get_optional(dev, NULL); + if (IS_ERR(dra7xx->clk)) + return dev_err_probe(dev, PTR_ERR(dra7xx->clk), + "clock request failed"); + + ret = clk_prepare_enable(dra7xx->clk); + if (ret) + return ret; + + for (i = 0; i < phy_count; i++) { + snprintf(name, sizeof(name), "pcie-phy%d", i); + phy[i] = devm_phy_get(dev, name); + if (IS_ERR(phy[i])) + return PTR_ERR(phy[i]); + + link[i] = device_link_add(dev, &phy[i]->dev, DL_FLAG_STATELESS); + if (!link[i]) { + ret = -EINVAL; + goto err_link; + } + } + + dra7xx->base = base; + dra7xx->phy = phy; + dra7xx->pci = pci; + dra7xx->phy_count = phy_count; + + if (phy_count == 2) { + ret = dra7xx_pcie_configure_two_lane(dev, b1co_mode_sel_mask); + if (ret < 0) + dra7xx->phy_count = 1; /* Fallback to x1 lane mode */ + } + + ret = dra7xx_pcie_enable_phy(dra7xx); + if (ret) { + dev_err(dev, "failed to enable phy\n"); + return ret; + } + + platform_set_drvdata(pdev, dra7xx); + + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "pm_runtime_get_sync failed\n"); + goto err_get_sync; + } + + reset = devm_gpiod_get_optional(dev, NULL, GPIOD_OUT_HIGH); + if (IS_ERR(reset)) { + ret = PTR_ERR(reset); + dev_err(&pdev->dev, "gpio request failed, ret %d\n", ret); + goto err_gpio; + } + + reg = dra7xx_pcie_readl(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD); + reg &= ~LTSSM_EN; + dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD, reg); + + switch (mode) { + case DW_PCIE_RC_TYPE: + if (!IS_ENABLED(CONFIG_PCI_DRA7XX_HOST)) { + ret = -ENODEV; + goto err_gpio; + } + + dra7xx_pcie_writel(dra7xx, PCIECTRL_TI_CONF_DEVICE_TYPE, + DEVICE_TYPE_RC); + + ret = dra7xx_pcie_unaligned_memaccess(dev); + if (ret) + dev_err(dev, "WA for Errata i870 not applied\n"); + + ret = dra7xx_add_pcie_port(dra7xx, pdev); + if (ret < 0) + goto err_gpio; + break; + case DW_PCIE_EP_TYPE: + if (!IS_ENABLED(CONFIG_PCI_DRA7XX_EP)) { + ret = -ENODEV; + goto err_gpio; + } + + dra7xx_pcie_writel(dra7xx, PCIECTRL_TI_CONF_DEVICE_TYPE, + DEVICE_TYPE_EP); + + ret = dra7xx_pcie_unaligned_memaccess(dev); + if (ret) + goto err_gpio; + + ret = dra7xx_add_pcie_ep(dra7xx, pdev); + if (ret < 0) + goto err_gpio; + break; + default: + dev_err(dev, "INVALID device type %d\n", mode); + } + dra7xx->mode = mode; + + ret = devm_request_irq(dev, irq, dra7xx_pcie_irq_handler, + IRQF_SHARED, "dra7xx-pcie-main", dra7xx); + if (ret) { + dev_err(dev, "failed to request irq\n"); + goto err_gpio; + } + + return 0; + +err_gpio: +err_get_sync: + pm_runtime_put(dev); + pm_runtime_disable(dev); + dra7xx_pcie_disable_phy(dra7xx); + +err_link: + while (--i >= 0) + device_link_del(link[i]); + + return ret; +} + +static int dra7xx_pcie_suspend(struct device *dev) +{ + struct dra7xx_pcie *dra7xx = dev_get_drvdata(dev); + struct dw_pcie *pci = dra7xx->pci; + u32 val; + + if (dra7xx->mode != DW_PCIE_RC_TYPE) + return 0; + + /* clear MSE */ + val = dw_pcie_readl_dbi(pci, PCI_COMMAND); + val &= ~PCI_COMMAND_MEMORY; + dw_pcie_writel_dbi(pci, PCI_COMMAND, val); + + return 0; +} + +static int dra7xx_pcie_resume(struct device *dev) +{ + struct dra7xx_pcie *dra7xx = dev_get_drvdata(dev); + struct dw_pcie *pci = dra7xx->pci; + u32 val; + + if (dra7xx->mode != DW_PCIE_RC_TYPE) + return 0; + + /* set MSE */ + val = dw_pcie_readl_dbi(pci, PCI_COMMAND); + val |= PCI_COMMAND_MEMORY; + dw_pcie_writel_dbi(pci, PCI_COMMAND, val); + + return 0; +} + +static int dra7xx_pcie_suspend_noirq(struct device *dev) +{ + struct dra7xx_pcie *dra7xx = dev_get_drvdata(dev); + + dra7xx_pcie_disable_phy(dra7xx); + + return 0; +} + +static int dra7xx_pcie_resume_noirq(struct device *dev) +{ + struct dra7xx_pcie *dra7xx = dev_get_drvdata(dev); + int ret; + + ret = dra7xx_pcie_enable_phy(dra7xx); + if (ret) { + dev_err(dev, "failed to enable phy\n"); + return ret; + } + + return 0; +} + +static void dra7xx_pcie_shutdown(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dra7xx_pcie *dra7xx = dev_get_drvdata(dev); + int ret; + + dra7xx_pcie_stop_link(dra7xx->pci); + + ret = pm_runtime_put_sync(dev); + if (ret < 0) + dev_dbg(dev, "pm_runtime_put_sync failed\n"); + + pm_runtime_disable(dev); + dra7xx_pcie_disable_phy(dra7xx); + + clk_disable_unprepare(dra7xx->clk); +} + +static const struct dev_pm_ops dra7xx_pcie_pm_ops = { + SYSTEM_SLEEP_PM_OPS(dra7xx_pcie_suspend, dra7xx_pcie_resume) + NOIRQ_SYSTEM_SLEEP_PM_OPS(dra7xx_pcie_suspend_noirq, + dra7xx_pcie_resume_noirq) +}; + +static struct platform_driver dra7xx_pcie_driver = { + .probe = dra7xx_pcie_probe, + .driver = { + .name = "dra7-pcie", + .of_match_table = of_dra7xx_pcie_match, + .suppress_bind_attrs = true, + .pm = &dra7xx_pcie_pm_ops, + }, + .shutdown = dra7xx_pcie_shutdown, +}; +module_platform_driver(dra7xx_pcie_driver); + +MODULE_AUTHOR("Kishon Vijay Abraham I <kishon@ti.com>"); +MODULE_DESCRIPTION("PCIe controller driver for TI DRA7xx SoCs"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c new file mode 100644 index 000000000..e5519978b --- /dev/null +++ b/drivers/pci/controller/dwc/pci-exynos.c @@ -0,0 +1,443 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Samsung Exynos SoCs + * + * Copyright (C) 2013-2020 Samsung Electronics Co., Ltd. + * https://www.samsung.com + * + * Author: Jingoo Han <jg1.han@samsung.com> + * Jaehoon Chung <jh80.chung@samsung.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of_device.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/phy/phy.h> +#include <linux/regulator/consumer.h> +#include <linux/module.h> + +#include "pcie-designware.h" + +#define to_exynos_pcie(x) dev_get_drvdata((x)->dev) + +/* PCIe ELBI registers */ +#define PCIE_IRQ_PULSE 0x000 +#define IRQ_INTA_ASSERT BIT(0) +#define IRQ_INTB_ASSERT BIT(2) +#define IRQ_INTC_ASSERT BIT(4) +#define IRQ_INTD_ASSERT BIT(6) +#define PCIE_IRQ_LEVEL 0x004 +#define PCIE_IRQ_SPECIAL 0x008 +#define PCIE_IRQ_EN_PULSE 0x00c +#define PCIE_IRQ_EN_LEVEL 0x010 +#define PCIE_IRQ_EN_SPECIAL 0x014 +#define PCIE_SW_WAKE 0x018 +#define PCIE_BUS_EN BIT(1) +#define PCIE_CORE_RESET 0x01c +#define PCIE_CORE_RESET_ENABLE BIT(0) +#define PCIE_STICKY_RESET 0x020 +#define PCIE_NONSTICKY_RESET 0x024 +#define PCIE_APP_INIT_RESET 0x028 +#define PCIE_APP_LTSSM_ENABLE 0x02c +#define PCIE_ELBI_RDLH_LINKUP 0x074 +#define PCIE_ELBI_XMLH_LINKUP BIT(4) +#define PCIE_ELBI_LTSSM_ENABLE 0x1 +#define PCIE_ELBI_SLV_AWMISC 0x11c +#define PCIE_ELBI_SLV_ARMISC 0x120 +#define PCIE_ELBI_SLV_DBI_ENABLE BIT(21) + +struct exynos_pcie { + struct dw_pcie pci; + void __iomem *elbi_base; + struct clk *clk; + struct clk *bus_clk; + struct phy *phy; + struct regulator_bulk_data supplies[2]; +}; + +static int exynos_pcie_init_clk_resources(struct exynos_pcie *ep) +{ + struct device *dev = ep->pci.dev; + int ret; + + ret = clk_prepare_enable(ep->clk); + if (ret) { + dev_err(dev, "cannot enable pcie rc clock"); + return ret; + } + + ret = clk_prepare_enable(ep->bus_clk); + if (ret) { + dev_err(dev, "cannot enable pcie bus clock"); + goto err_bus_clk; + } + + return 0; + +err_bus_clk: + clk_disable_unprepare(ep->clk); + + return ret; +} + +static void exynos_pcie_deinit_clk_resources(struct exynos_pcie *ep) +{ + clk_disable_unprepare(ep->bus_clk); + clk_disable_unprepare(ep->clk); +} + +static void exynos_pcie_writel(void __iomem *base, u32 val, u32 reg) +{ + writel(val, base + reg); +} + +static u32 exynos_pcie_readl(void __iomem *base, u32 reg) +{ + return readl(base + reg); +} + +static void exynos_pcie_sideband_dbi_w_mode(struct exynos_pcie *ep, bool on) +{ + u32 val; + + val = exynos_pcie_readl(ep->elbi_base, PCIE_ELBI_SLV_AWMISC); + if (on) + val |= PCIE_ELBI_SLV_DBI_ENABLE; + else + val &= ~PCIE_ELBI_SLV_DBI_ENABLE; + exynos_pcie_writel(ep->elbi_base, val, PCIE_ELBI_SLV_AWMISC); +} + +static void exynos_pcie_sideband_dbi_r_mode(struct exynos_pcie *ep, bool on) +{ + u32 val; + + val = exynos_pcie_readl(ep->elbi_base, PCIE_ELBI_SLV_ARMISC); + if (on) + val |= PCIE_ELBI_SLV_DBI_ENABLE; + else + val &= ~PCIE_ELBI_SLV_DBI_ENABLE; + exynos_pcie_writel(ep->elbi_base, val, PCIE_ELBI_SLV_ARMISC); +} + +static void exynos_pcie_assert_core_reset(struct exynos_pcie *ep) +{ + u32 val; + + val = exynos_pcie_readl(ep->elbi_base, PCIE_CORE_RESET); + val &= ~PCIE_CORE_RESET_ENABLE; + exynos_pcie_writel(ep->elbi_base, val, PCIE_CORE_RESET); + exynos_pcie_writel(ep->elbi_base, 0, PCIE_STICKY_RESET); + exynos_pcie_writel(ep->elbi_base, 0, PCIE_NONSTICKY_RESET); +} + +static void exynos_pcie_deassert_core_reset(struct exynos_pcie *ep) +{ + u32 val; + + val = exynos_pcie_readl(ep->elbi_base, PCIE_CORE_RESET); + val |= PCIE_CORE_RESET_ENABLE; + + exynos_pcie_writel(ep->elbi_base, val, PCIE_CORE_RESET); + exynos_pcie_writel(ep->elbi_base, 1, PCIE_STICKY_RESET); + exynos_pcie_writel(ep->elbi_base, 1, PCIE_NONSTICKY_RESET); + exynos_pcie_writel(ep->elbi_base, 1, PCIE_APP_INIT_RESET); + exynos_pcie_writel(ep->elbi_base, 0, PCIE_APP_INIT_RESET); +} + +static int exynos_pcie_start_link(struct dw_pcie *pci) +{ + struct exynos_pcie *ep = to_exynos_pcie(pci); + u32 val; + + val = exynos_pcie_readl(ep->elbi_base, PCIE_SW_WAKE); + val &= ~PCIE_BUS_EN; + exynos_pcie_writel(ep->elbi_base, val, PCIE_SW_WAKE); + + /* assert LTSSM enable */ + exynos_pcie_writel(ep->elbi_base, PCIE_ELBI_LTSSM_ENABLE, + PCIE_APP_LTSSM_ENABLE); + return 0; +} + +static void exynos_pcie_clear_irq_pulse(struct exynos_pcie *ep) +{ + u32 val = exynos_pcie_readl(ep->elbi_base, PCIE_IRQ_PULSE); + + exynos_pcie_writel(ep->elbi_base, val, PCIE_IRQ_PULSE); +} + +static irqreturn_t exynos_pcie_irq_handler(int irq, void *arg) +{ + struct exynos_pcie *ep = arg; + + exynos_pcie_clear_irq_pulse(ep); + return IRQ_HANDLED; +} + +static void exynos_pcie_enable_irq_pulse(struct exynos_pcie *ep) +{ + u32 val = IRQ_INTA_ASSERT | IRQ_INTB_ASSERT | + IRQ_INTC_ASSERT | IRQ_INTD_ASSERT; + + exynos_pcie_writel(ep->elbi_base, val, PCIE_IRQ_EN_PULSE); + exynos_pcie_writel(ep->elbi_base, 0, PCIE_IRQ_EN_LEVEL); + exynos_pcie_writel(ep->elbi_base, 0, PCIE_IRQ_EN_SPECIAL); +} + +static u32 exynos_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, + u32 reg, size_t size) +{ + struct exynos_pcie *ep = to_exynos_pcie(pci); + u32 val; + + exynos_pcie_sideband_dbi_r_mode(ep, true); + dw_pcie_read(base + reg, size, &val); + exynos_pcie_sideband_dbi_r_mode(ep, false); + return val; +} + +static void exynos_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, + u32 reg, size_t size, u32 val) +{ + struct exynos_pcie *ep = to_exynos_pcie(pci); + + exynos_pcie_sideband_dbi_w_mode(ep, true); + dw_pcie_write(base + reg, size, val); + exynos_pcie_sideband_dbi_w_mode(ep, false); +} + +static int exynos_pcie_rd_own_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); + + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + *val = dw_pcie_read_dbi(pci, where, size); + return PCIBIOS_SUCCESSFUL; +} + +static int exynos_pcie_wr_own_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); + + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + dw_pcie_write_dbi(pci, where, size, val); + return PCIBIOS_SUCCESSFUL; +} + +static struct pci_ops exynos_pci_ops = { + .read = exynos_pcie_rd_own_conf, + .write = exynos_pcie_wr_own_conf, +}; + +static int exynos_pcie_link_up(struct dw_pcie *pci) +{ + struct exynos_pcie *ep = to_exynos_pcie(pci); + u32 val = exynos_pcie_readl(ep->elbi_base, PCIE_ELBI_RDLH_LINKUP); + + return (val & PCIE_ELBI_XMLH_LINKUP); +} + +static int exynos_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct exynos_pcie *ep = to_exynos_pcie(pci); + + pp->bridge->ops = &exynos_pci_ops; + + exynos_pcie_assert_core_reset(ep); + + phy_init(ep->phy); + phy_power_on(ep->phy); + + exynos_pcie_deassert_core_reset(ep); + exynos_pcie_enable_irq_pulse(ep); + + return 0; +} + +static const struct dw_pcie_host_ops exynos_pcie_host_ops = { + .host_init = exynos_pcie_host_init, +}; + +static int exynos_add_pcie_port(struct exynos_pcie *ep, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &ep->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = &pdev->dev; + int ret; + + pp->irq = platform_get_irq(pdev, 0); + if (pp->irq < 0) + return pp->irq; + + ret = devm_request_irq(dev, pp->irq, exynos_pcie_irq_handler, + IRQF_SHARED, "exynos-pcie", ep); + if (ret) { + dev_err(dev, "failed to request irq\n"); + return ret; + } + + pp->ops = &exynos_pcie_host_ops; + pp->msi_irq[0] = -ENODEV; + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "failed to initialize host\n"); + return ret; + } + + return 0; +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .read_dbi = exynos_pcie_read_dbi, + .write_dbi = exynos_pcie_write_dbi, + .link_up = exynos_pcie_link_up, + .start_link = exynos_pcie_start_link, +}; + +static int exynos_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct exynos_pcie *ep; + struct device_node *np = dev->of_node; + int ret; + + ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + ep->pci.dev = dev; + ep->pci.ops = &dw_pcie_ops; + + ep->phy = devm_of_phy_get(dev, np, NULL); + if (IS_ERR(ep->phy)) + return PTR_ERR(ep->phy); + + /* External Local Bus interface (ELBI) registers */ + ep->elbi_base = devm_platform_ioremap_resource_byname(pdev, "elbi"); + if (IS_ERR(ep->elbi_base)) + return PTR_ERR(ep->elbi_base); + + ep->clk = devm_clk_get(dev, "pcie"); + if (IS_ERR(ep->clk)) { + dev_err(dev, "Failed to get pcie rc clock\n"); + return PTR_ERR(ep->clk); + } + + ep->bus_clk = devm_clk_get(dev, "pcie_bus"); + if (IS_ERR(ep->bus_clk)) { + dev_err(dev, "Failed to get pcie bus clock\n"); + return PTR_ERR(ep->bus_clk); + } + + ep->supplies[0].supply = "vdd18"; + ep->supplies[1].supply = "vdd10"; + ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(ep->supplies), + ep->supplies); + if (ret) + return ret; + + ret = exynos_pcie_init_clk_resources(ep); + if (ret) + return ret; + + ret = regulator_bulk_enable(ARRAY_SIZE(ep->supplies), ep->supplies); + if (ret) + return ret; + + platform_set_drvdata(pdev, ep); + + ret = exynos_add_pcie_port(ep, pdev); + if (ret < 0) + goto fail_probe; + + return 0; + +fail_probe: + phy_exit(ep->phy); + exynos_pcie_deinit_clk_resources(ep); + regulator_bulk_disable(ARRAY_SIZE(ep->supplies), ep->supplies); + + return ret; +} + +static int exynos_pcie_remove(struct platform_device *pdev) +{ + struct exynos_pcie *ep = platform_get_drvdata(pdev); + + dw_pcie_host_deinit(&ep->pci.pp); + exynos_pcie_assert_core_reset(ep); + phy_power_off(ep->phy); + phy_exit(ep->phy); + exynos_pcie_deinit_clk_resources(ep); + regulator_bulk_disable(ARRAY_SIZE(ep->supplies), ep->supplies); + + return 0; +} + +static int exynos_pcie_suspend_noirq(struct device *dev) +{ + struct exynos_pcie *ep = dev_get_drvdata(dev); + + exynos_pcie_assert_core_reset(ep); + phy_power_off(ep->phy); + phy_exit(ep->phy); + regulator_bulk_disable(ARRAY_SIZE(ep->supplies), ep->supplies); + + return 0; +} + +static int exynos_pcie_resume_noirq(struct device *dev) +{ + struct exynos_pcie *ep = dev_get_drvdata(dev); + struct dw_pcie *pci = &ep->pci; + struct dw_pcie_rp *pp = &pci->pp; + int ret; + + ret = regulator_bulk_enable(ARRAY_SIZE(ep->supplies), ep->supplies); + if (ret) + return ret; + + /* exynos_pcie_host_init controls ep->phy */ + exynos_pcie_host_init(pp); + dw_pcie_setup_rc(pp); + exynos_pcie_start_link(pci); + return dw_pcie_wait_for_link(pci); +} + +static const struct dev_pm_ops exynos_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(exynos_pcie_suspend_noirq, + exynos_pcie_resume_noirq) +}; + +static const struct of_device_id exynos_pcie_of_match[] = { + { .compatible = "samsung,exynos5433-pcie", }, + { }, +}; + +static struct platform_driver exynos_pcie_driver = { + .probe = exynos_pcie_probe, + .remove = exynos_pcie_remove, + .driver = { + .name = "exynos-pcie", + .of_match_table = exynos_pcie_of_match, + .pm = &exynos_pcie_pm_ops, + }, +}; +module_platform_driver(exynos_pcie_driver); +MODULE_LICENSE("GPL v2"); +MODULE_DEVICE_TABLE(of, exynos_pcie_of_match); diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c new file mode 100644 index 000000000..388354a8e --- /dev/null +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -0,0 +1,1426 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Freescale i.MX6 SoCs + * + * Copyright (C) 2013 Kosagi + * https://www.kosagi.com + * + * Author: Sean Cross <xobs@kosagi.com> + */ + +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/mfd/syscon/imx6q-iomuxc-gpr.h> +#include <linux/mfd/syscon/imx7-iomuxc-gpr.h> +#include <linux/module.h> +#include <linux/of_gpio.h> +#include <linux/of_device.h> +#include <linux/of_address.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/regulator/consumer.h> +#include <linux/resource.h> +#include <linux/signal.h> +#include <linux/types.h> +#include <linux/interrupt.h> +#include <linux/reset.h> +#include <linux/phy/phy.h> +#include <linux/pm_domain.h> +#include <linux/pm_runtime.h> + +#include "pcie-designware.h" + +#define IMX8MQ_GPR_PCIE_REF_USE_PAD BIT(9) +#define IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN BIT(10) +#define IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE BIT(11) +#define IMX8MQ_GPR_PCIE_VREG_BYPASS BIT(12) +#define IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE GENMASK(11, 8) +#define IMX8MQ_PCIE2_BASE_ADDR 0x33c00000 + +#define to_imx6_pcie(x) dev_get_drvdata((x)->dev) + +enum imx6_pcie_variants { + IMX6Q, + IMX6SX, + IMX6QP, + IMX7D, + IMX8MQ, + IMX8MM, + IMX8MP, +}; + +#define IMX6_PCIE_FLAG_IMX6_PHY BIT(0) +#define IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE BIT(1) +#define IMX6_PCIE_FLAG_SUPPORTS_SUSPEND BIT(2) + +struct imx6_pcie_drvdata { + enum imx6_pcie_variants variant; + u32 flags; + int dbi_length; + const char *gpr; +}; + +struct imx6_pcie { + struct dw_pcie *pci; + int reset_gpio; + bool gpio_active_high; + bool link_is_up; + struct clk *pcie_bus; + struct clk *pcie_phy; + struct clk *pcie_inbound_axi; + struct clk *pcie; + struct clk *pcie_aux; + struct regmap *iomuxc_gpr; + u32 controller_id; + struct reset_control *pciephy_reset; + struct reset_control *apps_reset; + struct reset_control *turnoff_reset; + u32 tx_deemph_gen1; + u32 tx_deemph_gen2_3p5db; + u32 tx_deemph_gen2_6db; + u32 tx_swing_full; + u32 tx_swing_low; + struct regulator *vpcie; + struct regulator *vph; + void __iomem *phy_base; + + /* power domain for pcie */ + struct device *pd_pcie; + /* power domain for pcie phy */ + struct device *pd_pcie_phy; + struct phy *phy; + const struct imx6_pcie_drvdata *drvdata; +}; + +/* Parameters for the waiting for PCIe PHY PLL to lock on i.MX7 */ +#define PHY_PLL_LOCK_WAIT_USLEEP_MAX 200 +#define PHY_PLL_LOCK_WAIT_TIMEOUT (2000 * PHY_PLL_LOCK_WAIT_USLEEP_MAX) + +/* PCIe Port Logic registers (memory-mapped) */ +#define PL_OFFSET 0x700 + +#define PCIE_PHY_CTRL (PL_OFFSET + 0x114) +#define PCIE_PHY_CTRL_DATA(x) FIELD_PREP(GENMASK(15, 0), (x)) +#define PCIE_PHY_CTRL_CAP_ADR BIT(16) +#define PCIE_PHY_CTRL_CAP_DAT BIT(17) +#define PCIE_PHY_CTRL_WR BIT(18) +#define PCIE_PHY_CTRL_RD BIT(19) + +#define PCIE_PHY_STAT (PL_OFFSET + 0x110) +#define PCIE_PHY_STAT_ACK BIT(16) + +/* PHY registers (not memory-mapped) */ +#define PCIE_PHY_ATEOVRD 0x10 +#define PCIE_PHY_ATEOVRD_EN BIT(2) +#define PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT 0 +#define PCIE_PHY_ATEOVRD_REF_CLKDIV_MASK 0x1 + +#define PCIE_PHY_MPLL_OVRD_IN_LO 0x11 +#define PCIE_PHY_MPLL_MULTIPLIER_SHIFT 2 +#define PCIE_PHY_MPLL_MULTIPLIER_MASK 0x7f +#define PCIE_PHY_MPLL_MULTIPLIER_OVRD BIT(9) + +#define PCIE_PHY_RX_ASIC_OUT 0x100D +#define PCIE_PHY_RX_ASIC_OUT_VALID (1 << 0) + +/* iMX7 PCIe PHY registers */ +#define PCIE_PHY_CMN_REG4 0x14 +/* These are probably the bits that *aren't* DCC_FB_EN */ +#define PCIE_PHY_CMN_REG4_DCC_FB_EN 0x29 + +#define PCIE_PHY_CMN_REG15 0x54 +#define PCIE_PHY_CMN_REG15_DLY_4 BIT(2) +#define PCIE_PHY_CMN_REG15_PLL_PD BIT(5) +#define PCIE_PHY_CMN_REG15_OVRD_PLL_PD BIT(7) + +#define PCIE_PHY_CMN_REG24 0x90 +#define PCIE_PHY_CMN_REG24_RX_EQ BIT(6) +#define PCIE_PHY_CMN_REG24_RX_EQ_SEL BIT(3) + +#define PCIE_PHY_CMN_REG26 0x98 +#define PCIE_PHY_CMN_REG26_ATT_MODE 0xBC + +#define PHY_RX_OVRD_IN_LO 0x1005 +#define PHY_RX_OVRD_IN_LO_RX_DATA_EN BIT(5) +#define PHY_RX_OVRD_IN_LO_RX_PLL_EN BIT(3) + +static unsigned int imx6_pcie_grp_offset(const struct imx6_pcie *imx6_pcie) +{ + WARN_ON(imx6_pcie->drvdata->variant != IMX8MQ && + imx6_pcie->drvdata->variant != IMX8MM && + imx6_pcie->drvdata->variant != IMX8MP); + return imx6_pcie->controller_id == 1 ? IOMUXC_GPR16 : IOMUXC_GPR14; +} + +static void imx6_pcie_configure_type(struct imx6_pcie *imx6_pcie) +{ + unsigned int mask, val; + + if (imx6_pcie->drvdata->variant == IMX8MQ && + imx6_pcie->controller_id == 1) { + mask = IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE; + val = FIELD_PREP(IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE, + PCI_EXP_TYPE_ROOT_PORT); + } else { + mask = IMX6Q_GPR12_DEVICE_TYPE; + val = FIELD_PREP(IMX6Q_GPR12_DEVICE_TYPE, + PCI_EXP_TYPE_ROOT_PORT); + } + + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, mask, val); +} + +static int pcie_phy_poll_ack(struct imx6_pcie *imx6_pcie, bool exp_val) +{ + struct dw_pcie *pci = imx6_pcie->pci; + bool val; + u32 max_iterations = 10; + u32 wait_counter = 0; + + do { + val = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT) & + PCIE_PHY_STAT_ACK; + wait_counter++; + + if (val == exp_val) + return 0; + + udelay(1); + } while (wait_counter < max_iterations); + + return -ETIMEDOUT; +} + +static int pcie_phy_wait_ack(struct imx6_pcie *imx6_pcie, int addr) +{ + struct dw_pcie *pci = imx6_pcie->pci; + u32 val; + int ret; + + val = PCIE_PHY_CTRL_DATA(addr); + dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val); + + val |= PCIE_PHY_CTRL_CAP_ADR; + dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val); + + ret = pcie_phy_poll_ack(imx6_pcie, true); + if (ret) + return ret; + + val = PCIE_PHY_CTRL_DATA(addr); + dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val); + + return pcie_phy_poll_ack(imx6_pcie, false); +} + +/* Read from the 16-bit PCIe PHY control registers (not memory-mapped) */ +static int pcie_phy_read(struct imx6_pcie *imx6_pcie, int addr, u16 *data) +{ + struct dw_pcie *pci = imx6_pcie->pci; + u32 phy_ctl; + int ret; + + ret = pcie_phy_wait_ack(imx6_pcie, addr); + if (ret) + return ret; + + /* assert Read signal */ + phy_ctl = PCIE_PHY_CTRL_RD; + dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, phy_ctl); + + ret = pcie_phy_poll_ack(imx6_pcie, true); + if (ret) + return ret; + + *data = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT); + + /* deassert Read signal */ + dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, 0x00); + + return pcie_phy_poll_ack(imx6_pcie, false); +} + +static int pcie_phy_write(struct imx6_pcie *imx6_pcie, int addr, u16 data) +{ + struct dw_pcie *pci = imx6_pcie->pci; + u32 var; + int ret; + + /* write addr */ + /* cap addr */ + ret = pcie_phy_wait_ack(imx6_pcie, addr); + if (ret) + return ret; + + var = PCIE_PHY_CTRL_DATA(data); + dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var); + + /* capture data */ + var |= PCIE_PHY_CTRL_CAP_DAT; + dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var); + + ret = pcie_phy_poll_ack(imx6_pcie, true); + if (ret) + return ret; + + /* deassert cap data */ + var = PCIE_PHY_CTRL_DATA(data); + dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var); + + /* wait for ack de-assertion */ + ret = pcie_phy_poll_ack(imx6_pcie, false); + if (ret) + return ret; + + /* assert wr signal */ + var = PCIE_PHY_CTRL_WR; + dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var); + + /* wait for ack */ + ret = pcie_phy_poll_ack(imx6_pcie, true); + if (ret) + return ret; + + /* deassert wr signal */ + var = PCIE_PHY_CTRL_DATA(data); + dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var); + + /* wait for ack de-assertion */ + ret = pcie_phy_poll_ack(imx6_pcie, false); + if (ret) + return ret; + + dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, 0x0); + + return 0; +} + +static void imx6_pcie_init_phy(struct imx6_pcie *imx6_pcie) +{ + switch (imx6_pcie->drvdata->variant) { + case IMX8MM: + case IMX8MP: + /* + * The PHY initialization had been done in the PHY + * driver, break here directly. + */ + break; + case IMX8MQ: + /* + * TODO: Currently this code assumes external + * oscillator is being used + */ + regmap_update_bits(imx6_pcie->iomuxc_gpr, + imx6_pcie_grp_offset(imx6_pcie), + IMX8MQ_GPR_PCIE_REF_USE_PAD, + IMX8MQ_GPR_PCIE_REF_USE_PAD); + /* + * Regarding the datasheet, the PCIE_VPH is suggested + * to be 1.8V. If the PCIE_VPH is supplied by 3.3V, the + * VREG_BYPASS should be cleared to zero. + */ + if (imx6_pcie->vph && + regulator_get_voltage(imx6_pcie->vph) > 3000000) + regmap_update_bits(imx6_pcie->iomuxc_gpr, + imx6_pcie_grp_offset(imx6_pcie), + IMX8MQ_GPR_PCIE_VREG_BYPASS, + 0); + break; + case IMX7D: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, 0); + break; + case IMX6SX: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_RX_EQ_MASK, + IMX6SX_GPR12_PCIE_RX_EQ_2); + fallthrough; + default: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6Q_GPR12_PCIE_CTL_2, 0 << 10); + + /* configure constant input signal to the pcie ctrl and phy */ + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6Q_GPR12_LOS_LEVEL, 9 << 4); + + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8, + IMX6Q_GPR8_TX_DEEMPH_GEN1, + imx6_pcie->tx_deemph_gen1 << 0); + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8, + IMX6Q_GPR8_TX_DEEMPH_GEN2_3P5DB, + imx6_pcie->tx_deemph_gen2_3p5db << 6); + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8, + IMX6Q_GPR8_TX_DEEMPH_GEN2_6DB, + imx6_pcie->tx_deemph_gen2_6db << 12); + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8, + IMX6Q_GPR8_TX_SWING_FULL, + imx6_pcie->tx_swing_full << 18); + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8, + IMX6Q_GPR8_TX_SWING_LOW, + imx6_pcie->tx_swing_low << 25); + break; + } + + imx6_pcie_configure_type(imx6_pcie); +} + +static void imx7d_pcie_wait_for_phy_pll_lock(struct imx6_pcie *imx6_pcie) +{ + u32 val; + struct device *dev = imx6_pcie->pci->dev; + + if (regmap_read_poll_timeout(imx6_pcie->iomuxc_gpr, + IOMUXC_GPR22, val, + val & IMX7D_GPR22_PCIE_PHY_PLL_LOCKED, + PHY_PLL_LOCK_WAIT_USLEEP_MAX, + PHY_PLL_LOCK_WAIT_TIMEOUT)) + dev_err(dev, "PCIe PLL lock timeout\n"); +} + +static int imx6_setup_phy_mpll(struct imx6_pcie *imx6_pcie) +{ + unsigned long phy_rate = clk_get_rate(imx6_pcie->pcie_phy); + int mult, div; + u16 val; + + if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_IMX6_PHY)) + return 0; + + switch (phy_rate) { + case 125000000: + /* + * The default settings of the MPLL are for a 125MHz input + * clock, so no need to reconfigure anything in that case. + */ + return 0; + case 100000000: + mult = 25; + div = 0; + break; + case 200000000: + mult = 25; + div = 1; + break; + default: + dev_err(imx6_pcie->pci->dev, + "Unsupported PHY reference clock rate %lu\n", phy_rate); + return -EINVAL; + } + + pcie_phy_read(imx6_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, &val); + val &= ~(PCIE_PHY_MPLL_MULTIPLIER_MASK << + PCIE_PHY_MPLL_MULTIPLIER_SHIFT); + val |= mult << PCIE_PHY_MPLL_MULTIPLIER_SHIFT; + val |= PCIE_PHY_MPLL_MULTIPLIER_OVRD; + pcie_phy_write(imx6_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, val); + + pcie_phy_read(imx6_pcie, PCIE_PHY_ATEOVRD, &val); + val &= ~(PCIE_PHY_ATEOVRD_REF_CLKDIV_MASK << + PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT); + val |= div << PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT; + val |= PCIE_PHY_ATEOVRD_EN; + pcie_phy_write(imx6_pcie, PCIE_PHY_ATEOVRD, val); + + return 0; +} + +static void imx6_pcie_reset_phy(struct imx6_pcie *imx6_pcie) +{ + u16 tmp; + + if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_IMX6_PHY)) + return; + + pcie_phy_read(imx6_pcie, PHY_RX_OVRD_IN_LO, &tmp); + tmp |= (PHY_RX_OVRD_IN_LO_RX_DATA_EN | + PHY_RX_OVRD_IN_LO_RX_PLL_EN); + pcie_phy_write(imx6_pcie, PHY_RX_OVRD_IN_LO, tmp); + + usleep_range(2000, 3000); + + pcie_phy_read(imx6_pcie, PHY_RX_OVRD_IN_LO, &tmp); + tmp &= ~(PHY_RX_OVRD_IN_LO_RX_DATA_EN | + PHY_RX_OVRD_IN_LO_RX_PLL_EN); + pcie_phy_write(imx6_pcie, PHY_RX_OVRD_IN_LO, tmp); +} + +#ifdef CONFIG_ARM +/* Added for PCI abort handling */ +static int imx6q_pcie_abort_handler(unsigned long addr, + unsigned int fsr, struct pt_regs *regs) +{ + unsigned long pc = instruction_pointer(regs); + unsigned long instr = *(unsigned long *)pc; + int reg = (instr >> 12) & 15; + + /* + * If the instruction being executed was a read, + * make it look like it read all-ones. + */ + if ((instr & 0x0c100000) == 0x04100000) { + unsigned long val; + + if (instr & 0x00400000) + val = 255; + else + val = -1; + + regs->uregs[reg] = val; + regs->ARM_pc += 4; + return 0; + } + + if ((instr & 0x0e100090) == 0x00100090) { + regs->uregs[reg] = -1; + regs->ARM_pc += 4; + return 0; + } + + return 1; +} +#endif + +static int imx6_pcie_attach_pd(struct device *dev) +{ + struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); + struct device_link *link; + + /* Do nothing when in a single power domain */ + if (dev->pm_domain) + return 0; + + imx6_pcie->pd_pcie = dev_pm_domain_attach_by_name(dev, "pcie"); + if (IS_ERR(imx6_pcie->pd_pcie)) + return PTR_ERR(imx6_pcie->pd_pcie); + /* Do nothing when power domain missing */ + if (!imx6_pcie->pd_pcie) + return 0; + link = device_link_add(dev, imx6_pcie->pd_pcie, + DL_FLAG_STATELESS | + DL_FLAG_PM_RUNTIME | + DL_FLAG_RPM_ACTIVE); + if (!link) { + dev_err(dev, "Failed to add device_link to pcie pd.\n"); + return -EINVAL; + } + + imx6_pcie->pd_pcie_phy = dev_pm_domain_attach_by_name(dev, "pcie_phy"); + if (IS_ERR(imx6_pcie->pd_pcie_phy)) + return PTR_ERR(imx6_pcie->pd_pcie_phy); + + link = device_link_add(dev, imx6_pcie->pd_pcie_phy, + DL_FLAG_STATELESS | + DL_FLAG_PM_RUNTIME | + DL_FLAG_RPM_ACTIVE); + if (!link) { + dev_err(dev, "Failed to add device_link to pcie_phy pd.\n"); + return -EINVAL; + } + + return 0; +} + +static int imx6_pcie_enable_ref_clk(struct imx6_pcie *imx6_pcie) +{ + struct dw_pcie *pci = imx6_pcie->pci; + struct device *dev = pci->dev; + unsigned int offset; + int ret = 0; + + switch (imx6_pcie->drvdata->variant) { + case IMX6SX: + ret = clk_prepare_enable(imx6_pcie->pcie_inbound_axi); + if (ret) { + dev_err(dev, "unable to enable pcie_axi clock\n"); + break; + } + + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_TEST_POWERDOWN, 0); + break; + case IMX6QP: + case IMX6Q: + /* power up core phy and enable ref clock */ + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, + IMX6Q_GPR1_PCIE_TEST_PD, 0 << 18); + /* + * the async reset input need ref clock to sync internally, + * when the ref clock comes after reset, internal synced + * reset time is too short, cannot meet the requirement. + * add one ~10us delay here. + */ + usleep_range(10, 100); + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, + IMX6Q_GPR1_PCIE_REF_CLK_EN, 1 << 16); + break; + case IMX7D: + break; + case IMX8MM: + case IMX8MQ: + case IMX8MP: + ret = clk_prepare_enable(imx6_pcie->pcie_aux); + if (ret) { + dev_err(dev, "unable to enable pcie_aux clock\n"); + break; + } + + offset = imx6_pcie_grp_offset(imx6_pcie); + /* + * Set the over ride low and enabled + * make sure that REF_CLK is turned on. + */ + regmap_update_bits(imx6_pcie->iomuxc_gpr, offset, + IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE, + 0); + regmap_update_bits(imx6_pcie->iomuxc_gpr, offset, + IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN, + IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN); + break; + } + + return ret; +} + +static void imx6_pcie_disable_ref_clk(struct imx6_pcie *imx6_pcie) +{ + switch (imx6_pcie->drvdata->variant) { + case IMX6SX: + clk_disable_unprepare(imx6_pcie->pcie_inbound_axi); + break; + case IMX6QP: + case IMX6Q: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, + IMX6Q_GPR1_PCIE_REF_CLK_EN, 0); + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, + IMX6Q_GPR1_PCIE_TEST_PD, + IMX6Q_GPR1_PCIE_TEST_PD); + break; + case IMX7D: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, + IMX7D_GPR12_PCIE_PHY_REFCLK_SEL); + break; + case IMX8MM: + case IMX8MQ: + case IMX8MP: + clk_disable_unprepare(imx6_pcie->pcie_aux); + break; + default: + break; + } +} + +static int imx6_pcie_clk_enable(struct imx6_pcie *imx6_pcie) +{ + struct dw_pcie *pci = imx6_pcie->pci; + struct device *dev = pci->dev; + int ret; + + ret = clk_prepare_enable(imx6_pcie->pcie_phy); + if (ret) { + dev_err(dev, "unable to enable pcie_phy clock\n"); + return ret; + } + + ret = clk_prepare_enable(imx6_pcie->pcie_bus); + if (ret) { + dev_err(dev, "unable to enable pcie_bus clock\n"); + goto err_pcie_bus; + } + + ret = clk_prepare_enable(imx6_pcie->pcie); + if (ret) { + dev_err(dev, "unable to enable pcie clock\n"); + goto err_pcie; + } + + ret = imx6_pcie_enable_ref_clk(imx6_pcie); + if (ret) { + dev_err(dev, "unable to enable pcie ref clock\n"); + goto err_ref_clk; + } + + /* allow the clocks to stabilize */ + usleep_range(200, 500); + return 0; + +err_ref_clk: + clk_disable_unprepare(imx6_pcie->pcie); +err_pcie: + clk_disable_unprepare(imx6_pcie->pcie_bus); +err_pcie_bus: + clk_disable_unprepare(imx6_pcie->pcie_phy); + + return ret; +} + +static void imx6_pcie_clk_disable(struct imx6_pcie *imx6_pcie) +{ + imx6_pcie_disable_ref_clk(imx6_pcie); + clk_disable_unprepare(imx6_pcie->pcie); + clk_disable_unprepare(imx6_pcie->pcie_bus); + clk_disable_unprepare(imx6_pcie->pcie_phy); +} + +static void imx6_pcie_assert_core_reset(struct imx6_pcie *imx6_pcie) +{ + switch (imx6_pcie->drvdata->variant) { + case IMX7D: + case IMX8MQ: + reset_control_assert(imx6_pcie->pciephy_reset); + fallthrough; + case IMX8MM: + case IMX8MP: + reset_control_assert(imx6_pcie->apps_reset); + break; + case IMX6SX: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_TEST_POWERDOWN, + IMX6SX_GPR12_PCIE_TEST_POWERDOWN); + /* Force PCIe PHY reset */ + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR5, + IMX6SX_GPR5_PCIE_BTNRST_RESET, + IMX6SX_GPR5_PCIE_BTNRST_RESET); + break; + case IMX6QP: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, + IMX6Q_GPR1_PCIE_SW_RST, + IMX6Q_GPR1_PCIE_SW_RST); + break; + case IMX6Q: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, + IMX6Q_GPR1_PCIE_TEST_PD, 1 << 18); + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, + IMX6Q_GPR1_PCIE_REF_CLK_EN, 0 << 16); + break; + } + + /* Some boards don't have PCIe reset GPIO. */ + if (gpio_is_valid(imx6_pcie->reset_gpio)) + gpio_set_value_cansleep(imx6_pcie->reset_gpio, + imx6_pcie->gpio_active_high); +} + +static int imx6_pcie_deassert_core_reset(struct imx6_pcie *imx6_pcie) +{ + struct dw_pcie *pci = imx6_pcie->pci; + struct device *dev = pci->dev; + + switch (imx6_pcie->drvdata->variant) { + case IMX8MQ: + reset_control_deassert(imx6_pcie->pciephy_reset); + break; + case IMX7D: + reset_control_deassert(imx6_pcie->pciephy_reset); + + /* Workaround for ERR010728, failure of PCI-e PLL VCO to + * oscillate, especially when cold. This turns off "Duty-cycle + * Corrector" and other mysterious undocumented things. + */ + if (likely(imx6_pcie->phy_base)) { + /* De-assert DCC_FB_EN */ + writel(PCIE_PHY_CMN_REG4_DCC_FB_EN, + imx6_pcie->phy_base + PCIE_PHY_CMN_REG4); + /* Assert RX_EQS and RX_EQS_SEL */ + writel(PCIE_PHY_CMN_REG24_RX_EQ_SEL + | PCIE_PHY_CMN_REG24_RX_EQ, + imx6_pcie->phy_base + PCIE_PHY_CMN_REG24); + /* Assert ATT_MODE */ + writel(PCIE_PHY_CMN_REG26_ATT_MODE, + imx6_pcie->phy_base + PCIE_PHY_CMN_REG26); + } else { + dev_warn(dev, "Unable to apply ERR010728 workaround. DT missing fsl,imx7d-pcie-phy phandle ?\n"); + } + + imx7d_pcie_wait_for_phy_pll_lock(imx6_pcie); + break; + case IMX6SX: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR5, + IMX6SX_GPR5_PCIE_BTNRST_RESET, 0); + break; + case IMX6QP: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, + IMX6Q_GPR1_PCIE_SW_RST, 0); + + usleep_range(200, 500); + break; + case IMX6Q: /* Nothing to do */ + case IMX8MM: + case IMX8MP: + break; + } + + /* Some boards don't have PCIe reset GPIO. */ + if (gpio_is_valid(imx6_pcie->reset_gpio)) { + msleep(100); + gpio_set_value_cansleep(imx6_pcie->reset_gpio, + !imx6_pcie->gpio_active_high); + /* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */ + msleep(100); + } + + return 0; +} + +static int imx6_pcie_wait_for_speed_change(struct imx6_pcie *imx6_pcie) +{ + struct dw_pcie *pci = imx6_pcie->pci; + struct device *dev = pci->dev; + u32 tmp; + unsigned int retries; + + for (retries = 0; retries < 200; retries++) { + tmp = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + /* Test if the speed change finished. */ + if (!(tmp & PORT_LOGIC_SPEED_CHANGE)) + return 0; + usleep_range(100, 1000); + } + + dev_err(dev, "Speed change timeout\n"); + return -ETIMEDOUT; +} + +static void imx6_pcie_ltssm_enable(struct device *dev) +{ + struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); + + switch (imx6_pcie->drvdata->variant) { + case IMX6Q: + case IMX6SX: + case IMX6QP: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6Q_GPR12_PCIE_CTL_2, + IMX6Q_GPR12_PCIE_CTL_2); + break; + case IMX7D: + case IMX8MQ: + case IMX8MM: + case IMX8MP: + reset_control_deassert(imx6_pcie->apps_reset); + break; + } +} + +static void imx6_pcie_ltssm_disable(struct device *dev) +{ + struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); + + switch (imx6_pcie->drvdata->variant) { + case IMX6Q: + case IMX6SX: + case IMX6QP: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6Q_GPR12_PCIE_CTL_2, 0); + break; + case IMX7D: + case IMX8MQ: + case IMX8MM: + case IMX8MP: + reset_control_assert(imx6_pcie->apps_reset); + break; + } +} + +static int imx6_pcie_start_link(struct dw_pcie *pci) +{ + struct imx6_pcie *imx6_pcie = to_imx6_pcie(pci); + struct device *dev = pci->dev; + u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + u32 tmp; + int ret; + + /* + * Force Gen1 operation when starting the link. In case the link is + * started in Gen2 mode, there is a possibility the devices on the + * bus will not be detected at all. This happens with PCIe switches. + */ + dw_pcie_dbi_ro_wr_en(pci); + tmp = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + tmp &= ~PCI_EXP_LNKCAP_SLS; + tmp |= PCI_EXP_LNKCAP_SLS_2_5GB; + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, tmp); + dw_pcie_dbi_ro_wr_dis(pci); + + /* Start LTSSM. */ + imx6_pcie_ltssm_enable(dev); + + ret = dw_pcie_wait_for_link(pci); + if (ret) + goto err_reset_phy; + + if (pci->link_gen > 1) { + /* Allow faster modes after the link is up */ + dw_pcie_dbi_ro_wr_en(pci); + tmp = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + tmp &= ~PCI_EXP_LNKCAP_SLS; + tmp |= pci->link_gen; + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, tmp); + + /* + * Start Directed Speed Change so the best possible + * speed both link partners support can be negotiated. + */ + tmp = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + tmp |= PORT_LOGIC_SPEED_CHANGE; + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, tmp); + dw_pcie_dbi_ro_wr_dis(pci); + + if (imx6_pcie->drvdata->flags & + IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE) { + /* + * On i.MX7, DIRECT_SPEED_CHANGE behaves differently + * from i.MX6 family when no link speed transition + * occurs and we go Gen1 -> yep, Gen1. The difference + * is that, in such case, it will not be cleared by HW + * which will cause the following code to report false + * failure. + */ + + ret = imx6_pcie_wait_for_speed_change(imx6_pcie); + if (ret) { + dev_err(dev, "Failed to bring link up!\n"); + goto err_reset_phy; + } + } + + /* Make sure link training is finished as well! */ + ret = dw_pcie_wait_for_link(pci); + if (ret) + goto err_reset_phy; + } else { + dev_info(dev, "Link: Only Gen1 is enabled\n"); + } + + imx6_pcie->link_is_up = true; + tmp = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA); + dev_info(dev, "Link up, Gen%i\n", tmp & PCI_EXP_LNKSTA_CLS); + return 0; + +err_reset_phy: + imx6_pcie->link_is_up = false; + dev_dbg(dev, "PHY DEBUG_R0=0x%08x DEBUG_R1=0x%08x\n", + dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0), + dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG1)); + imx6_pcie_reset_phy(imx6_pcie); + return 0; +} + +static void imx6_pcie_stop_link(struct dw_pcie *pci) +{ + struct device *dev = pci->dev; + + /* Turn off PCIe LTSSM */ + imx6_pcie_ltssm_disable(dev); +} + +static int imx6_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct imx6_pcie *imx6_pcie = to_imx6_pcie(pci); + int ret; + + if (imx6_pcie->vpcie) { + ret = regulator_enable(imx6_pcie->vpcie); + if (ret) { + dev_err(dev, "failed to enable vpcie regulator: %d\n", + ret); + return ret; + } + } + + imx6_pcie_assert_core_reset(imx6_pcie); + imx6_pcie_init_phy(imx6_pcie); + + ret = imx6_pcie_clk_enable(imx6_pcie); + if (ret) { + dev_err(dev, "unable to enable pcie clocks: %d\n", ret); + goto err_reg_disable; + } + + if (imx6_pcie->phy) { + ret = phy_init(imx6_pcie->phy); + if (ret) { + dev_err(dev, "pcie PHY power up failed\n"); + goto err_clk_disable; + } + } + + if (imx6_pcie->phy) { + ret = phy_power_on(imx6_pcie->phy); + if (ret) { + dev_err(dev, "waiting for PHY ready timeout!\n"); + goto err_phy_off; + } + } + + ret = imx6_pcie_deassert_core_reset(imx6_pcie); + if (ret < 0) { + dev_err(dev, "pcie deassert core reset failed: %d\n", ret); + goto err_phy_off; + } + + imx6_setup_phy_mpll(imx6_pcie); + + return 0; + +err_phy_off: + if (imx6_pcie->phy) + phy_exit(imx6_pcie->phy); +err_clk_disable: + imx6_pcie_clk_disable(imx6_pcie); +err_reg_disable: + if (imx6_pcie->vpcie) + regulator_disable(imx6_pcie->vpcie); + return ret; +} + +static void imx6_pcie_host_exit(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct imx6_pcie *imx6_pcie = to_imx6_pcie(pci); + + if (imx6_pcie->phy) { + if (phy_power_off(imx6_pcie->phy)) + dev_err(pci->dev, "unable to power off PHY\n"); + phy_exit(imx6_pcie->phy); + } + imx6_pcie_clk_disable(imx6_pcie); + + if (imx6_pcie->vpcie) + regulator_disable(imx6_pcie->vpcie); +} + +static const struct dw_pcie_host_ops imx6_pcie_host_ops = { + .host_init = imx6_pcie_host_init, + .host_deinit = imx6_pcie_host_exit, +}; + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = imx6_pcie_start_link, +}; + +static void imx6_pcie_pm_turnoff(struct imx6_pcie *imx6_pcie) +{ + struct device *dev = imx6_pcie->pci->dev; + + /* Some variants have a turnoff reset in DT */ + if (imx6_pcie->turnoff_reset) { + reset_control_assert(imx6_pcie->turnoff_reset); + reset_control_deassert(imx6_pcie->turnoff_reset); + goto pm_turnoff_sleep; + } + + /* Others poke directly at IOMUXC registers */ + switch (imx6_pcie->drvdata->variant) { + case IMX6SX: + case IMX6QP: + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_PM_TURN_OFF, + IMX6SX_GPR12_PCIE_PM_TURN_OFF); + regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_PM_TURN_OFF, 0); + break; + default: + dev_err(dev, "PME_Turn_Off not implemented\n"); + return; + } + + /* + * Components with an upstream port must respond to + * PME_Turn_Off with PME_TO_Ack but we can't check. + * + * The standard recommends a 1-10ms timeout after which to + * proceed anyway as if acks were received. + */ +pm_turnoff_sleep: + usleep_range(1000, 10000); +} + +static int imx6_pcie_suspend_noirq(struct device *dev) +{ + struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); + struct dw_pcie_rp *pp = &imx6_pcie->pci->pp; + + if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_SUPPORTS_SUSPEND)) + return 0; + + imx6_pcie_pm_turnoff(imx6_pcie); + imx6_pcie_stop_link(imx6_pcie->pci); + imx6_pcie_host_exit(pp); + + return 0; +} + +static int imx6_pcie_resume_noirq(struct device *dev) +{ + int ret; + struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev); + struct dw_pcie_rp *pp = &imx6_pcie->pci->pp; + + if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_SUPPORTS_SUSPEND)) + return 0; + + ret = imx6_pcie_host_init(pp); + if (ret) + return ret; + dw_pcie_setup_rc(pp); + + if (imx6_pcie->link_is_up) + imx6_pcie_start_link(imx6_pcie->pci); + + return 0; +} + +static const struct dev_pm_ops imx6_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(imx6_pcie_suspend_noirq, + imx6_pcie_resume_noirq) +}; + +static int imx6_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci; + struct imx6_pcie *imx6_pcie; + struct device_node *np; + struct resource *dbi_base; + struct device_node *node = dev->of_node; + int ret; + u16 val; + + imx6_pcie = devm_kzalloc(dev, sizeof(*imx6_pcie), GFP_KERNEL); + if (!imx6_pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pci->dev = dev; + pci->ops = &dw_pcie_ops; + pci->pp.ops = &imx6_pcie_host_ops; + + imx6_pcie->pci = pci; + imx6_pcie->drvdata = of_device_get_match_data(dev); + + /* Find the PHY if one is defined, only imx7d uses it */ + np = of_parse_phandle(node, "fsl,imx7d-pcie-phy", 0); + if (np) { + struct resource res; + + ret = of_address_to_resource(np, 0, &res); + if (ret) { + dev_err(dev, "Unable to map PCIe PHY\n"); + return ret; + } + imx6_pcie->phy_base = devm_ioremap_resource(dev, &res); + if (IS_ERR(imx6_pcie->phy_base)) + return PTR_ERR(imx6_pcie->phy_base); + } + + dbi_base = platform_get_resource(pdev, IORESOURCE_MEM, 0); + pci->dbi_base = devm_ioremap_resource(dev, dbi_base); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + + /* Fetch GPIOs */ + imx6_pcie->reset_gpio = of_get_named_gpio(node, "reset-gpio", 0); + imx6_pcie->gpio_active_high = of_property_read_bool(node, + "reset-gpio-active-high"); + if (gpio_is_valid(imx6_pcie->reset_gpio)) { + ret = devm_gpio_request_one(dev, imx6_pcie->reset_gpio, + imx6_pcie->gpio_active_high ? + GPIOF_OUT_INIT_HIGH : + GPIOF_OUT_INIT_LOW, + "PCIe reset"); + if (ret) { + dev_err(dev, "unable to get reset gpio\n"); + return ret; + } + } else if (imx6_pcie->reset_gpio == -EPROBE_DEFER) { + return imx6_pcie->reset_gpio; + } + + /* Fetch clocks */ + imx6_pcie->pcie_bus = devm_clk_get(dev, "pcie_bus"); + if (IS_ERR(imx6_pcie->pcie_bus)) + return dev_err_probe(dev, PTR_ERR(imx6_pcie->pcie_bus), + "pcie_bus clock source missing or invalid\n"); + + imx6_pcie->pcie = devm_clk_get(dev, "pcie"); + if (IS_ERR(imx6_pcie->pcie)) + return dev_err_probe(dev, PTR_ERR(imx6_pcie->pcie), + "pcie clock source missing or invalid\n"); + + switch (imx6_pcie->drvdata->variant) { + case IMX6SX: + imx6_pcie->pcie_inbound_axi = devm_clk_get(dev, + "pcie_inbound_axi"); + if (IS_ERR(imx6_pcie->pcie_inbound_axi)) + return dev_err_probe(dev, PTR_ERR(imx6_pcie->pcie_inbound_axi), + "pcie_inbound_axi clock missing or invalid\n"); + break; + case IMX8MQ: + imx6_pcie->pcie_aux = devm_clk_get(dev, "pcie_aux"); + if (IS_ERR(imx6_pcie->pcie_aux)) + return dev_err_probe(dev, PTR_ERR(imx6_pcie->pcie_aux), + "pcie_aux clock source missing or invalid\n"); + fallthrough; + case IMX7D: + if (dbi_base->start == IMX8MQ_PCIE2_BASE_ADDR) + imx6_pcie->controller_id = 1; + + imx6_pcie->pciephy_reset = devm_reset_control_get_exclusive(dev, + "pciephy"); + if (IS_ERR(imx6_pcie->pciephy_reset)) { + dev_err(dev, "Failed to get PCIEPHY reset control\n"); + return PTR_ERR(imx6_pcie->pciephy_reset); + } + + imx6_pcie->apps_reset = devm_reset_control_get_exclusive(dev, + "apps"); + if (IS_ERR(imx6_pcie->apps_reset)) { + dev_err(dev, "Failed to get PCIE APPS reset control\n"); + return PTR_ERR(imx6_pcie->apps_reset); + } + break; + case IMX8MM: + case IMX8MP: + imx6_pcie->pcie_aux = devm_clk_get(dev, "pcie_aux"); + if (IS_ERR(imx6_pcie->pcie_aux)) + return dev_err_probe(dev, PTR_ERR(imx6_pcie->pcie_aux), + "pcie_aux clock source missing or invalid\n"); + imx6_pcie->apps_reset = devm_reset_control_get_exclusive(dev, + "apps"); + if (IS_ERR(imx6_pcie->apps_reset)) + return dev_err_probe(dev, PTR_ERR(imx6_pcie->apps_reset), + "failed to get pcie apps reset control\n"); + + imx6_pcie->phy = devm_phy_get(dev, "pcie-phy"); + if (IS_ERR(imx6_pcie->phy)) + return dev_err_probe(dev, PTR_ERR(imx6_pcie->phy), + "failed to get pcie phy\n"); + + break; + default: + break; + } + /* Don't fetch the pcie_phy clock, if it has abstract PHY driver */ + if (imx6_pcie->phy == NULL) { + imx6_pcie->pcie_phy = devm_clk_get(dev, "pcie_phy"); + if (IS_ERR(imx6_pcie->pcie_phy)) + return dev_err_probe(dev, PTR_ERR(imx6_pcie->pcie_phy), + "pcie_phy clock source missing or invalid\n"); + } + + + /* Grab turnoff reset */ + imx6_pcie->turnoff_reset = devm_reset_control_get_optional_exclusive(dev, "turnoff"); + if (IS_ERR(imx6_pcie->turnoff_reset)) { + dev_err(dev, "Failed to get TURNOFF reset control\n"); + return PTR_ERR(imx6_pcie->turnoff_reset); + } + + /* Grab GPR config register range */ + imx6_pcie->iomuxc_gpr = + syscon_regmap_lookup_by_compatible(imx6_pcie->drvdata->gpr); + if (IS_ERR(imx6_pcie->iomuxc_gpr)) { + dev_err(dev, "unable to find iomuxc registers\n"); + return PTR_ERR(imx6_pcie->iomuxc_gpr); + } + + /* Grab PCIe PHY Tx Settings */ + if (of_property_read_u32(node, "fsl,tx-deemph-gen1", + &imx6_pcie->tx_deemph_gen1)) + imx6_pcie->tx_deemph_gen1 = 0; + + if (of_property_read_u32(node, "fsl,tx-deemph-gen2-3p5db", + &imx6_pcie->tx_deemph_gen2_3p5db)) + imx6_pcie->tx_deemph_gen2_3p5db = 0; + + if (of_property_read_u32(node, "fsl,tx-deemph-gen2-6db", + &imx6_pcie->tx_deemph_gen2_6db)) + imx6_pcie->tx_deemph_gen2_6db = 20; + + if (of_property_read_u32(node, "fsl,tx-swing-full", + &imx6_pcie->tx_swing_full)) + imx6_pcie->tx_swing_full = 127; + + if (of_property_read_u32(node, "fsl,tx-swing-low", + &imx6_pcie->tx_swing_low)) + imx6_pcie->tx_swing_low = 127; + + /* Limit link speed */ + pci->link_gen = 1; + of_property_read_u32(node, "fsl,max-link-speed", &pci->link_gen); + + imx6_pcie->vpcie = devm_regulator_get_optional(&pdev->dev, "vpcie"); + if (IS_ERR(imx6_pcie->vpcie)) { + if (PTR_ERR(imx6_pcie->vpcie) != -ENODEV) + return PTR_ERR(imx6_pcie->vpcie); + imx6_pcie->vpcie = NULL; + } + + imx6_pcie->vph = devm_regulator_get_optional(&pdev->dev, "vph"); + if (IS_ERR(imx6_pcie->vph)) { + if (PTR_ERR(imx6_pcie->vph) != -ENODEV) + return PTR_ERR(imx6_pcie->vph); + imx6_pcie->vph = NULL; + } + + platform_set_drvdata(pdev, imx6_pcie); + + ret = imx6_pcie_attach_pd(dev); + if (ret) + return ret; + + ret = dw_pcie_host_init(&pci->pp); + if (ret < 0) + return ret; + + if (pci_msi_enabled()) { + u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_MSI); + val = dw_pcie_readw_dbi(pci, offset + PCI_MSI_FLAGS); + val |= PCI_MSI_FLAGS_ENABLE; + dw_pcie_writew_dbi(pci, offset + PCI_MSI_FLAGS, val); + } + + return 0; +} + +static void imx6_pcie_shutdown(struct platform_device *pdev) +{ + struct imx6_pcie *imx6_pcie = platform_get_drvdata(pdev); + + /* bring down link, so bootloader gets clean state in case of reboot */ + imx6_pcie_assert_core_reset(imx6_pcie); +} + +static const struct imx6_pcie_drvdata drvdata[] = { + [IMX6Q] = { + .variant = IMX6Q, + .flags = IMX6_PCIE_FLAG_IMX6_PHY | + IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE, + .dbi_length = 0x200, + .gpr = "fsl,imx6q-iomuxc-gpr", + }, + [IMX6SX] = { + .variant = IMX6SX, + .flags = IMX6_PCIE_FLAG_IMX6_PHY | + IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE | + IMX6_PCIE_FLAG_SUPPORTS_SUSPEND, + .gpr = "fsl,imx6q-iomuxc-gpr", + }, + [IMX6QP] = { + .variant = IMX6QP, + .flags = IMX6_PCIE_FLAG_IMX6_PHY | + IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE | + IMX6_PCIE_FLAG_SUPPORTS_SUSPEND, + .dbi_length = 0x200, + .gpr = "fsl,imx6q-iomuxc-gpr", + }, + [IMX7D] = { + .variant = IMX7D, + .flags = IMX6_PCIE_FLAG_SUPPORTS_SUSPEND, + .gpr = "fsl,imx7d-iomuxc-gpr", + }, + [IMX8MQ] = { + .variant = IMX8MQ, + .gpr = "fsl,imx8mq-iomuxc-gpr", + }, + [IMX8MM] = { + .variant = IMX8MM, + .flags = IMX6_PCIE_FLAG_SUPPORTS_SUSPEND, + .gpr = "fsl,imx8mm-iomuxc-gpr", + }, + [IMX8MP] = { + .variant = IMX8MP, + .flags = IMX6_PCIE_FLAG_SUPPORTS_SUSPEND, + .gpr = "fsl,imx8mp-iomuxc-gpr", + }, +}; + +static const struct of_device_id imx6_pcie_of_match[] = { + { .compatible = "fsl,imx6q-pcie", .data = &drvdata[IMX6Q], }, + { .compatible = "fsl,imx6sx-pcie", .data = &drvdata[IMX6SX], }, + { .compatible = "fsl,imx6qp-pcie", .data = &drvdata[IMX6QP], }, + { .compatible = "fsl,imx7d-pcie", .data = &drvdata[IMX7D], }, + { .compatible = "fsl,imx8mq-pcie", .data = &drvdata[IMX8MQ], }, + { .compatible = "fsl,imx8mm-pcie", .data = &drvdata[IMX8MM], }, + { .compatible = "fsl,imx8mp-pcie", .data = &drvdata[IMX8MP], }, + {}, +}; + +static struct platform_driver imx6_pcie_driver = { + .driver = { + .name = "imx6q-pcie", + .of_match_table = imx6_pcie_of_match, + .suppress_bind_attrs = true, + .pm = &imx6_pcie_pm_ops, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, + .probe = imx6_pcie_probe, + .shutdown = imx6_pcie_shutdown, +}; + +static void imx6_pcie_quirk(struct pci_dev *dev) +{ + struct pci_bus *bus = dev->bus; + struct dw_pcie_rp *pp = bus->sysdata; + + /* Bus parent is the PCI bridge, its parent is this platform driver */ + if (!bus->dev.parent || !bus->dev.parent->parent) + return; + + /* Make sure we only quirk devices associated with this driver */ + if (bus->dev.parent->parent->driver != &imx6_pcie_driver.driver) + return; + + if (pci_is_root_bus(bus)) { + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct imx6_pcie *imx6_pcie = to_imx6_pcie(pci); + + /* + * Limit config length to avoid the kernel reading beyond + * the register set and causing an abort on i.MX 6Quad + */ + if (imx6_pcie->drvdata->dbi_length) { + dev->cfg_size = imx6_pcie->drvdata->dbi_length; + dev_info(&dev->dev, "Limiting cfg_size to %d\n", + dev->cfg_size); + } + } +} +DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_SYNOPSYS, 0xabcd, + PCI_CLASS_BRIDGE_PCI, 8, imx6_pcie_quirk); + +static int __init imx6_pcie_init(void) +{ +#ifdef CONFIG_ARM + struct device_node *np; + + np = of_find_matching_node(NULL, imx6_pcie_of_match); + if (!np) + return -ENODEV; + of_node_put(np); + + /* + * Since probe() can be deferred we need to make sure that + * hook_fault_code is not called after __init memory is freed + * by kernel and since imx6q_pcie_abort_handler() is a no-op, + * we can install the handler here without risking it + * accessing some uninitialized driver state. + */ + hook_fault_code(8, imx6q_pcie_abort_handler, SIGBUS, 0, + "external abort on non-linefetch"); +#endif + + return platform_driver_register(&imx6_pcie_driver); +} +device_initcall(imx6_pcie_init); diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c new file mode 100644 index 000000000..7ecad72cf --- /dev/null +++ b/drivers/pci/controller/dwc/pci-keystone.c @@ -0,0 +1,1339 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Texas Instruments Keystone SoCs + * + * Copyright (C) 2013-2014 Texas Instruments., Ltd. + * https://www.ti.com + * + * Author: Murali Karicheri <m-karicheri2@ti.com> + * Implementation based on pci-exynos.c and pcie-designware.c + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/mfd/syscon.h> +#include <linux/msi.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_irq.h> +#include <linux/of_pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/resource.h> +#include <linux/signal.h> + +#include "../../pci.h" +#include "pcie-designware.h" + +#define PCIE_VENDORID_MASK 0xffff +#define PCIE_DEVICEID_SHIFT 16 + +/* Application registers */ +#define CMD_STATUS 0x004 +#define LTSSM_EN_VAL BIT(0) +#define OB_XLAT_EN_VAL BIT(1) +#define DBI_CS2 BIT(5) + +#define CFG_SETUP 0x008 +#define CFG_BUS(x) (((x) & 0xff) << 16) +#define CFG_DEVICE(x) (((x) & 0x1f) << 8) +#define CFG_FUNC(x) ((x) & 0x7) +#define CFG_TYPE1 BIT(24) + +#define OB_SIZE 0x030 +#define OB_OFFSET_INDEX(n) (0x200 + (8 * (n))) +#define OB_OFFSET_HI(n) (0x204 + (8 * (n))) +#define OB_ENABLEN BIT(0) +#define OB_WIN_SIZE 8 /* 8MB */ + +#define PCIE_LEGACY_IRQ_ENABLE_SET(n) (0x188 + (0x10 * ((n) - 1))) +#define PCIE_LEGACY_IRQ_ENABLE_CLR(n) (0x18c + (0x10 * ((n) - 1))) +#define PCIE_EP_IRQ_SET 0x64 +#define PCIE_EP_IRQ_CLR 0x68 +#define INT_ENABLE BIT(0) + +/* IRQ register defines */ +#define IRQ_EOI 0x050 + +#define MSI_IRQ 0x054 +#define MSI_IRQ_STATUS(n) (0x104 + ((n) << 4)) +#define MSI_IRQ_ENABLE_SET(n) (0x108 + ((n) << 4)) +#define MSI_IRQ_ENABLE_CLR(n) (0x10c + ((n) << 4)) +#define MSI_IRQ_OFFSET 4 + +#define IRQ_STATUS(n) (0x184 + ((n) << 4)) +#define IRQ_ENABLE_SET(n) (0x188 + ((n) << 4)) +#define INTx_EN BIT(0) + +#define ERR_IRQ_STATUS 0x1c4 +#define ERR_IRQ_ENABLE_SET 0x1c8 +#define ERR_AER BIT(5) /* ECRC error */ +#define AM6_ERR_AER BIT(4) /* AM6 ECRC error */ +#define ERR_AXI BIT(4) /* AXI tag lookup fatal error */ +#define ERR_CORR BIT(3) /* Correctable error */ +#define ERR_NONFATAL BIT(2) /* Non-fatal error */ +#define ERR_FATAL BIT(1) /* Fatal error */ +#define ERR_SYS BIT(0) /* System error */ +#define ERR_IRQ_ALL (ERR_AER | ERR_AXI | ERR_CORR | \ + ERR_NONFATAL | ERR_FATAL | ERR_SYS) + +/* PCIE controller device IDs */ +#define PCIE_RC_K2HK 0xb008 +#define PCIE_RC_K2E 0xb009 +#define PCIE_RC_K2L 0xb00a +#define PCIE_RC_K2G 0xb00b + +#define KS_PCIE_DEV_TYPE_MASK (0x3 << 1) +#define KS_PCIE_DEV_TYPE(mode) ((mode) << 1) + +#define EP 0x0 +#define LEG_EP 0x1 +#define RC 0x2 + +#define KS_PCIE_SYSCLOCKOUTEN BIT(0) + +#define AM654_PCIE_DEV_TYPE_MASK 0x3 +#define AM654_WIN_SIZE SZ_64K + +#define APP_ADDR_SPACE_0 (16 * SZ_1K) + +#define to_keystone_pcie(x) dev_get_drvdata((x)->dev) + +struct ks_pcie_of_data { + enum dw_pcie_device_mode mode; + const struct dw_pcie_host_ops *host_ops; + const struct dw_pcie_ep_ops *ep_ops; + u32 version; +}; + +struct keystone_pcie { + struct dw_pcie *pci; + /* PCI Device ID */ + u32 device_id; + int legacy_host_irqs[PCI_NUM_INTX]; + struct device_node *legacy_intc_np; + + int msi_host_irq; + int num_lanes; + u32 num_viewport; + struct phy **phy; + struct device_link **link; + struct device_node *msi_intc_np; + struct irq_domain *legacy_irq_domain; + struct device_node *np; + + /* Application register space */ + void __iomem *va_app_base; /* DT 1st resource */ + struct resource app; + bool is_am6; +}; + +static u32 ks_pcie_app_readl(struct keystone_pcie *ks_pcie, u32 offset) +{ + return readl(ks_pcie->va_app_base + offset); +} + +static void ks_pcie_app_writel(struct keystone_pcie *ks_pcie, u32 offset, + u32 val) +{ + writel(val, ks_pcie->va_app_base + offset); +} + +static void ks_pcie_msi_irq_ack(struct irq_data *data) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(data); + struct keystone_pcie *ks_pcie; + u32 irq = data->hwirq; + struct dw_pcie *pci; + u32 reg_offset; + u32 bit_pos; + + pci = to_dw_pcie_from_pp(pp); + ks_pcie = to_keystone_pcie(pci); + + reg_offset = irq % 8; + bit_pos = irq >> 3; + + ks_pcie_app_writel(ks_pcie, MSI_IRQ_STATUS(reg_offset), + BIT(bit_pos)); + ks_pcie_app_writel(ks_pcie, IRQ_EOI, reg_offset + MSI_IRQ_OFFSET); +} + +static void ks_pcie_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(data); + struct keystone_pcie *ks_pcie; + struct dw_pcie *pci; + u64 msi_target; + + pci = to_dw_pcie_from_pp(pp); + ks_pcie = to_keystone_pcie(pci); + + msi_target = ks_pcie->app.start + MSI_IRQ; + msg->address_lo = lower_32_bits(msi_target); + msg->address_hi = upper_32_bits(msi_target); + msg->data = data->hwirq; + + dev_dbg(pci->dev, "msi#%d address_hi %#x address_lo %#x\n", + (int)data->hwirq, msg->address_hi, msg->address_lo); +} + +static int ks_pcie_msi_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static void ks_pcie_msi_mask(struct irq_data *data) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(data); + struct keystone_pcie *ks_pcie; + u32 irq = data->hwirq; + struct dw_pcie *pci; + unsigned long flags; + u32 reg_offset; + u32 bit_pos; + + raw_spin_lock_irqsave(&pp->lock, flags); + + pci = to_dw_pcie_from_pp(pp); + ks_pcie = to_keystone_pcie(pci); + + reg_offset = irq % 8; + bit_pos = irq >> 3; + + ks_pcie_app_writel(ks_pcie, MSI_IRQ_ENABLE_CLR(reg_offset), + BIT(bit_pos)); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +} + +static void ks_pcie_msi_unmask(struct irq_data *data) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(data); + struct keystone_pcie *ks_pcie; + u32 irq = data->hwirq; + struct dw_pcie *pci; + unsigned long flags; + u32 reg_offset; + u32 bit_pos; + + raw_spin_lock_irqsave(&pp->lock, flags); + + pci = to_dw_pcie_from_pp(pp); + ks_pcie = to_keystone_pcie(pci); + + reg_offset = irq % 8; + bit_pos = irq >> 3; + + ks_pcie_app_writel(ks_pcie, MSI_IRQ_ENABLE_SET(reg_offset), + BIT(bit_pos)); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +} + +static struct irq_chip ks_pcie_msi_irq_chip = { + .name = "KEYSTONE-PCI-MSI", + .irq_ack = ks_pcie_msi_irq_ack, + .irq_compose_msi_msg = ks_pcie_compose_msi_msg, + .irq_set_affinity = ks_pcie_msi_set_affinity, + .irq_mask = ks_pcie_msi_mask, + .irq_unmask = ks_pcie_msi_unmask, +}; + +static int ks_pcie_msi_host_init(struct dw_pcie_rp *pp) +{ + pp->msi_irq_chip = &ks_pcie_msi_irq_chip; + return dw_pcie_allocate_domains(pp); +} + +static void ks_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie, + int offset) +{ + struct dw_pcie *pci = ks_pcie->pci; + struct device *dev = pci->dev; + u32 pending; + + pending = ks_pcie_app_readl(ks_pcie, IRQ_STATUS(offset)); + + if (BIT(0) & pending) { + dev_dbg(dev, ": irq: irq_offset %d", offset); + generic_handle_domain_irq(ks_pcie->legacy_irq_domain, offset); + } + + /* EOI the INTx interrupt */ + ks_pcie_app_writel(ks_pcie, IRQ_EOI, offset); +} + +static void ks_pcie_enable_error_irq(struct keystone_pcie *ks_pcie) +{ + ks_pcie_app_writel(ks_pcie, ERR_IRQ_ENABLE_SET, ERR_IRQ_ALL); +} + +static irqreturn_t ks_pcie_handle_error_irq(struct keystone_pcie *ks_pcie) +{ + u32 reg; + struct device *dev = ks_pcie->pci->dev; + + reg = ks_pcie_app_readl(ks_pcie, ERR_IRQ_STATUS); + if (!reg) + return IRQ_NONE; + + if (reg & ERR_SYS) + dev_err(dev, "System Error\n"); + + if (reg & ERR_FATAL) + dev_err(dev, "Fatal Error\n"); + + if (reg & ERR_NONFATAL) + dev_dbg(dev, "Non Fatal Error\n"); + + if (reg & ERR_CORR) + dev_dbg(dev, "Correctable Error\n"); + + if (!ks_pcie->is_am6 && (reg & ERR_AXI)) + dev_err(dev, "AXI tag lookup fatal Error\n"); + + if (reg & ERR_AER || (ks_pcie->is_am6 && (reg & AM6_ERR_AER))) + dev_err(dev, "ECRC Error\n"); + + ks_pcie_app_writel(ks_pcie, ERR_IRQ_STATUS, reg); + + return IRQ_HANDLED; +} + +static void ks_pcie_ack_legacy_irq(struct irq_data *d) +{ +} + +static void ks_pcie_mask_legacy_irq(struct irq_data *d) +{ +} + +static void ks_pcie_unmask_legacy_irq(struct irq_data *d) +{ +} + +static struct irq_chip ks_pcie_legacy_irq_chip = { + .name = "Keystone-PCI-Legacy-IRQ", + .irq_ack = ks_pcie_ack_legacy_irq, + .irq_mask = ks_pcie_mask_legacy_irq, + .irq_unmask = ks_pcie_unmask_legacy_irq, +}; + +static int ks_pcie_init_legacy_irq_map(struct irq_domain *d, + unsigned int irq, + irq_hw_number_t hw_irq) +{ + irq_set_chip_and_handler(irq, &ks_pcie_legacy_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, d->host_data); + + return 0; +} + +static const struct irq_domain_ops ks_pcie_legacy_irq_domain_ops = { + .map = ks_pcie_init_legacy_irq_map, + .xlate = irq_domain_xlate_onetwocell, +}; + +/** + * ks_pcie_set_dbi_mode() - Set DBI mode to access overlaid BAR mask registers + * @ks_pcie: A pointer to the keystone_pcie structure which holds the KeyStone + * PCIe host controller driver information. + * + * Since modification of dbi_cs2 involves different clock domain, read the + * status back to ensure the transition is complete. + */ +static void ks_pcie_set_dbi_mode(struct keystone_pcie *ks_pcie) +{ + u32 val; + + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + val |= DBI_CS2; + ks_pcie_app_writel(ks_pcie, CMD_STATUS, val); + + do { + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + } while (!(val & DBI_CS2)); +} + +/** + * ks_pcie_clear_dbi_mode() - Disable DBI mode + * @ks_pcie: A pointer to the keystone_pcie structure which holds the KeyStone + * PCIe host controller driver information. + * + * Since modification of dbi_cs2 involves different clock domain, read the + * status back to ensure the transition is complete. + */ +static void ks_pcie_clear_dbi_mode(struct keystone_pcie *ks_pcie) +{ + u32 val; + + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + val &= ~DBI_CS2; + ks_pcie_app_writel(ks_pcie, CMD_STATUS, val); + + do { + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + } while (val & DBI_CS2); +} + +static void ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie) +{ + u32 val; + u32 num_viewport = ks_pcie->num_viewport; + struct dw_pcie *pci = ks_pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + u64 start, end; + struct resource *mem; + int i; + + mem = resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM)->res; + start = mem->start; + end = mem->end; + + /* Disable BARs for inbound access */ + ks_pcie_set_dbi_mode(ks_pcie); + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0); + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_1, 0); + ks_pcie_clear_dbi_mode(ks_pcie); + + if (ks_pcie->is_am6) + return; + + val = ilog2(OB_WIN_SIZE); + ks_pcie_app_writel(ks_pcie, OB_SIZE, val); + + /* Using Direct 1:1 mapping of RC <-> PCI memory space */ + for (i = 0; i < num_viewport && (start < end); i++) { + ks_pcie_app_writel(ks_pcie, OB_OFFSET_INDEX(i), + lower_32_bits(start) | OB_ENABLEN); + ks_pcie_app_writel(ks_pcie, OB_OFFSET_HI(i), + upper_32_bits(start)); + start += OB_WIN_SIZE * SZ_1M; + } + + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + val |= OB_XLAT_EN_VAL; + ks_pcie_app_writel(ks_pcie, CMD_STATUS, val); +} + +static void __iomem *ks_pcie_other_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); + u32 reg; + + reg = CFG_BUS(bus->number) | CFG_DEVICE(PCI_SLOT(devfn)) | + CFG_FUNC(PCI_FUNC(devfn)); + if (!pci_is_root_bus(bus->parent)) + reg |= CFG_TYPE1; + ks_pcie_app_writel(ks_pcie, CFG_SETUP, reg); + + return pp->va_cfg0_base + where; +} + +static struct pci_ops ks_child_pcie_ops = { + .map_bus = ks_pcie_other_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +/** + * ks_pcie_v3_65_add_bus() - keystone add_bus post initialization + * @bus: A pointer to the PCI bus structure. + * + * This sets BAR0 to enable inbound access for MSI_IRQ register + */ +static int ks_pcie_v3_65_add_bus(struct pci_bus *bus) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); + + if (!pci_is_root_bus(bus)) + return 0; + + /* Configure and set up BAR0 */ + ks_pcie_set_dbi_mode(ks_pcie); + + /* Enable BAR0 */ + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 1); + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, SZ_4K - 1); + + ks_pcie_clear_dbi_mode(ks_pcie); + + /* + * For BAR0, just setting bus address for inbound writes (MSI) should + * be sufficient. Use physical address to avoid any conflicts. + */ + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, ks_pcie->app.start); + + return 0; +} + +static struct pci_ops ks_pcie_ops = { + .map_bus = dw_pcie_own_conf_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + .add_bus = ks_pcie_v3_65_add_bus, +}; + +/** + * ks_pcie_link_up() - Check if link up + * @pci: A pointer to the dw_pcie structure which holds the DesignWare PCIe host + * controller driver information. + */ +static int ks_pcie_link_up(struct dw_pcie *pci) +{ + u32 val; + + val = dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0); + val &= PORT_LOGIC_LTSSM_STATE_MASK; + return (val == PORT_LOGIC_LTSSM_STATE_L0); +} + +static void ks_pcie_stop_link(struct dw_pcie *pci) +{ + struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); + u32 val; + + /* Disable Link training */ + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + val &= ~LTSSM_EN_VAL; + ks_pcie_app_writel(ks_pcie, CMD_STATUS, val); +} + +static int ks_pcie_start_link(struct dw_pcie *pci) +{ + struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); + u32 val; + + /* Initiate Link Training */ + val = ks_pcie_app_readl(ks_pcie, CMD_STATUS); + ks_pcie_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val); + + return 0; +} + +static void ks_pcie_quirk(struct pci_dev *dev) +{ + struct pci_bus *bus = dev->bus; + struct pci_dev *bridge; + static const struct pci_device_id rc_pci_devids[] = { + { PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2HK), + .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, }, + { PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2E), + .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, }, + { PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2L), + .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, }, + { PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2G), + .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, }, + { 0, }, + }; + + if (pci_is_root_bus(bus)) + bridge = dev; + + /* look for the host bridge */ + while (!pci_is_root_bus(bus)) { + bridge = bus->self; + bus = bus->parent; + } + + if (!bridge) + return; + + /* + * Keystone PCI controller has a h/w limitation of + * 256 bytes maximum read request size. It can't handle + * anything higher than this. So force this limit on + * all downstream devices. + */ + if (pci_match_id(rc_pci_devids, bridge)) { + if (pcie_get_readrq(dev) > 256) { + dev_info(&dev->dev, "limiting MRRS to 256\n"); + pcie_set_readrq(dev, 256); + } + } +} +DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, ks_pcie_quirk); + +static void ks_pcie_msi_irq_handler(struct irq_desc *desc) +{ + unsigned int irq = desc->irq_data.hwirq; + struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc); + u32 offset = irq - ks_pcie->msi_host_irq; + struct dw_pcie *pci = ks_pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = pci->dev; + struct irq_chip *chip = irq_desc_get_chip(desc); + u32 vector, reg, pos; + + dev_dbg(dev, "%s, irq %d\n", __func__, irq); + + /* + * The chained irq handler installation would have replaced normal + * interrupt driver handler so we need to take care of mask/unmask and + * ack operation. + */ + chained_irq_enter(chip, desc); + + reg = ks_pcie_app_readl(ks_pcie, MSI_IRQ_STATUS(offset)); + /* + * MSI0 status bit 0-3 shows vectors 0, 8, 16, 24, MSI1 status bit + * shows 1, 9, 17, 25 and so forth + */ + for (pos = 0; pos < 4; pos++) { + if (!(reg & BIT(pos))) + continue; + + vector = offset + (pos << 3); + dev_dbg(dev, "irq: bit %d, vector %d\n", pos, vector); + generic_handle_domain_irq(pp->irq_domain, vector); + } + + chained_irq_exit(chip, desc); +} + +/** + * ks_pcie_legacy_irq_handler() - Handle legacy interrupt + * @desc: Pointer to irq descriptor + * + * Traverse through pending legacy interrupts and invoke handler for each. Also + * takes care of interrupt controller level mask/ack operation. + */ +static void ks_pcie_legacy_irq_handler(struct irq_desc *desc) +{ + unsigned int irq = irq_desc_get_irq(desc); + struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc); + struct dw_pcie *pci = ks_pcie->pci; + struct device *dev = pci->dev; + u32 irq_offset = irq - ks_pcie->legacy_host_irqs[0]; + struct irq_chip *chip = irq_desc_get_chip(desc); + + dev_dbg(dev, ": Handling legacy irq %d\n", irq); + + /* + * The chained irq handler installation would have replaced normal + * interrupt driver handler so we need to take care of mask/unmask and + * ack operation. + */ + chained_irq_enter(chip, desc); + ks_pcie_handle_legacy_irq(ks_pcie, irq_offset); + chained_irq_exit(chip, desc); +} + +static int ks_pcie_config_msi_irq(struct keystone_pcie *ks_pcie) +{ + struct device *dev = ks_pcie->pci->dev; + struct device_node *np = ks_pcie->np; + struct device_node *intc_np; + struct irq_data *irq_data; + int irq_count, irq, ret, i; + + if (!IS_ENABLED(CONFIG_PCI_MSI)) + return 0; + + intc_np = of_get_child_by_name(np, "msi-interrupt-controller"); + if (!intc_np) { + if (ks_pcie->is_am6) + return 0; + dev_warn(dev, "msi-interrupt-controller node is absent\n"); + return -EINVAL; + } + + irq_count = of_irq_count(intc_np); + if (!irq_count) { + dev_err(dev, "No IRQ entries in msi-interrupt-controller\n"); + ret = -EINVAL; + goto err; + } + + for (i = 0; i < irq_count; i++) { + irq = irq_of_parse_and_map(intc_np, i); + if (!irq) { + ret = -EINVAL; + goto err; + } + + if (!ks_pcie->msi_host_irq) { + irq_data = irq_get_irq_data(irq); + if (!irq_data) { + ret = -EINVAL; + goto err; + } + ks_pcie->msi_host_irq = irq_data->hwirq; + } + + irq_set_chained_handler_and_data(irq, ks_pcie_msi_irq_handler, + ks_pcie); + } + + of_node_put(intc_np); + return 0; + +err: + of_node_put(intc_np); + return ret; +} + +static int ks_pcie_config_legacy_irq(struct keystone_pcie *ks_pcie) +{ + struct device *dev = ks_pcie->pci->dev; + struct irq_domain *legacy_irq_domain; + struct device_node *np = ks_pcie->np; + struct device_node *intc_np; + int irq_count, irq, ret = 0, i; + + intc_np = of_get_child_by_name(np, "legacy-interrupt-controller"); + if (!intc_np) { + /* + * Since legacy interrupts are modeled as edge-interrupts in + * AM6, keep it disabled for now. + */ + if (ks_pcie->is_am6) + return 0; + dev_warn(dev, "legacy-interrupt-controller node is absent\n"); + return -EINVAL; + } + + irq_count = of_irq_count(intc_np); + if (!irq_count) { + dev_err(dev, "No IRQ entries in legacy-interrupt-controller\n"); + ret = -EINVAL; + goto err; + } + + for (i = 0; i < irq_count; i++) { + irq = irq_of_parse_and_map(intc_np, i); + if (!irq) { + ret = -EINVAL; + goto err; + } + ks_pcie->legacy_host_irqs[i] = irq; + + irq_set_chained_handler_and_data(irq, + ks_pcie_legacy_irq_handler, + ks_pcie); + } + + legacy_irq_domain = + irq_domain_add_linear(intc_np, PCI_NUM_INTX, + &ks_pcie_legacy_irq_domain_ops, NULL); + if (!legacy_irq_domain) { + dev_err(dev, "Failed to add irq domain for legacy irqs\n"); + ret = -EINVAL; + goto err; + } + ks_pcie->legacy_irq_domain = legacy_irq_domain; + + for (i = 0; i < PCI_NUM_INTX; i++) + ks_pcie_app_writel(ks_pcie, IRQ_ENABLE_SET(i), INTx_EN); + +err: + of_node_put(intc_np); + return ret; +} + +#ifdef CONFIG_ARM +/* + * When a PCI device does not exist during config cycles, keystone host + * gets a bus error instead of returning 0xffffffff (PCI_ERROR_RESPONSE). + * This handler always returns 0 for this kind of fault. + */ +static int ks_pcie_fault(unsigned long addr, unsigned int fsr, + struct pt_regs *regs) +{ + unsigned long instr = *(unsigned long *) instruction_pointer(regs); + + if ((instr & 0x0e100090) == 0x00100090) { + int reg = (instr >> 12) & 15; + + regs->uregs[reg] = -1; + regs->ARM_pc += 4; + } + + return 0; +} +#endif + +static int __init ks_pcie_init_id(struct keystone_pcie *ks_pcie) +{ + int ret; + unsigned int id; + struct regmap *devctrl_regs; + struct dw_pcie *pci = ks_pcie->pci; + struct device *dev = pci->dev; + struct device_node *np = dev->of_node; + struct of_phandle_args args; + unsigned int offset = 0; + + devctrl_regs = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pcie-id"); + if (IS_ERR(devctrl_regs)) + return PTR_ERR(devctrl_regs); + + /* Do not error out to maintain old DT compatibility */ + ret = of_parse_phandle_with_fixed_args(np, "ti,syscon-pcie-id", 1, 0, &args); + if (!ret) + offset = args.args[0]; + + ret = regmap_read(devctrl_regs, offset, &id); + if (ret) + return ret; + + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writew_dbi(pci, PCI_VENDOR_ID, id & PCIE_VENDORID_MASK); + dw_pcie_writew_dbi(pci, PCI_DEVICE_ID, id >> PCIE_DEVICEID_SHIFT); + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static int __init ks_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); + int ret; + + pp->bridge->ops = &ks_pcie_ops; + if (!ks_pcie->is_am6) + pp->bridge->child_ops = &ks_child_pcie_ops; + + ret = ks_pcie_config_legacy_irq(ks_pcie); + if (ret) + return ret; + + ret = ks_pcie_config_msi_irq(ks_pcie); + if (ret) + return ret; + + ks_pcie_stop_link(pci); + ks_pcie_setup_rc_app_regs(ks_pcie); + writew(PCI_IO_RANGE_TYPE_32 | (PCI_IO_RANGE_TYPE_32 << 8), + pci->dbi_base + PCI_IO_BASE); + + ret = ks_pcie_init_id(ks_pcie); + if (ret < 0) + return ret; + +#ifdef CONFIG_ARM + /* + * PCIe access errors that result into OCP errors are caught by ARM as + * "External aborts" + */ + hook_fault_code(17, ks_pcie_fault, SIGBUS, 0, + "Asynchronous external abort"); +#endif + + return 0; +} + +static const struct dw_pcie_host_ops ks_pcie_host_ops = { + .host_init = ks_pcie_host_init, + .msi_host_init = ks_pcie_msi_host_init, +}; + +static const struct dw_pcie_host_ops ks_pcie_am654_host_ops = { + .host_init = ks_pcie_host_init, +}; + +static irqreturn_t ks_pcie_err_irq_handler(int irq, void *priv) +{ + struct keystone_pcie *ks_pcie = priv; + + return ks_pcie_handle_error_irq(ks_pcie); +} + +static void ks_pcie_am654_write_dbi2(struct dw_pcie *pci, void __iomem *base, + u32 reg, size_t size, u32 val) +{ + struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); + + ks_pcie_set_dbi_mode(ks_pcie); + dw_pcie_write(base + reg, size, val); + ks_pcie_clear_dbi_mode(ks_pcie); +} + +static const struct dw_pcie_ops ks_pcie_dw_pcie_ops = { + .start_link = ks_pcie_start_link, + .stop_link = ks_pcie_stop_link, + .link_up = ks_pcie_link_up, + .write_dbi2 = ks_pcie_am654_write_dbi2, +}; + +static void ks_pcie_am654_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + int flags; + + ep->page_size = AM654_WIN_SIZE; + flags = PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_32; + dw_pcie_writel_dbi2(pci, PCI_BASE_ADDRESS_0, APP_ADDR_SPACE_0 - 1); + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, flags); +} + +static void ks_pcie_am654_raise_legacy_irq(struct keystone_pcie *ks_pcie) +{ + struct dw_pcie *pci = ks_pcie->pci; + u8 int_pin; + + int_pin = dw_pcie_readb_dbi(pci, PCI_INTERRUPT_PIN); + if (int_pin == 0 || int_pin > 4) + return; + + ks_pcie_app_writel(ks_pcie, PCIE_LEGACY_IRQ_ENABLE_SET(int_pin), + INT_ENABLE); + ks_pcie_app_writel(ks_pcie, PCIE_EP_IRQ_SET, INT_ENABLE); + mdelay(1); + ks_pcie_app_writel(ks_pcie, PCIE_EP_IRQ_CLR, INT_ENABLE); + ks_pcie_app_writel(ks_pcie, PCIE_LEGACY_IRQ_ENABLE_CLR(int_pin), + INT_ENABLE); +} + +static int ks_pcie_am654_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + enum pci_epc_irq_type type, + u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + ks_pcie_am654_raise_legacy_irq(ks_pcie); + break; + case PCI_EPC_IRQ_MSI: + dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num); + break; + case PCI_EPC_IRQ_MSIX: + dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num); + break; + default: + dev_err(pci->dev, "UNKNOWN IRQ type\n"); + return -EINVAL; + } + + return 0; +} + +static const struct pci_epc_features ks_pcie_am654_epc_features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = true, + .reserved_bar = 1 << BAR_0 | 1 << BAR_1, + .bar_fixed_64bit = 1 << BAR_0, + .bar_fixed_size[2] = SZ_1M, + .bar_fixed_size[3] = SZ_64K, + .bar_fixed_size[4] = 256, + .bar_fixed_size[5] = SZ_1M, + .align = SZ_1M, +}; + +static const struct pci_epc_features* +ks_pcie_am654_get_features(struct dw_pcie_ep *ep) +{ + return &ks_pcie_am654_epc_features; +} + +static const struct dw_pcie_ep_ops ks_pcie_am654_ep_ops = { + .ep_init = ks_pcie_am654_ep_init, + .raise_irq = ks_pcie_am654_raise_irq, + .get_features = &ks_pcie_am654_get_features, +}; + +static void ks_pcie_disable_phy(struct keystone_pcie *ks_pcie) +{ + int num_lanes = ks_pcie->num_lanes; + + while (num_lanes--) { + phy_power_off(ks_pcie->phy[num_lanes]); + phy_exit(ks_pcie->phy[num_lanes]); + } +} + +static int ks_pcie_enable_phy(struct keystone_pcie *ks_pcie) +{ + int i; + int ret; + int num_lanes = ks_pcie->num_lanes; + + for (i = 0; i < num_lanes; i++) { + ret = phy_reset(ks_pcie->phy[i]); + if (ret < 0) + goto err_phy; + + ret = phy_init(ks_pcie->phy[i]); + if (ret < 0) + goto err_phy; + + ret = phy_power_on(ks_pcie->phy[i]); + if (ret < 0) { + phy_exit(ks_pcie->phy[i]); + goto err_phy; + } + } + + return 0; + +err_phy: + while (--i >= 0) { + phy_power_off(ks_pcie->phy[i]); + phy_exit(ks_pcie->phy[i]); + } + + return ret; +} + +static int ks_pcie_set_mode(struct device *dev) +{ + struct device_node *np = dev->of_node; + struct of_phandle_args args; + unsigned int offset = 0; + struct regmap *syscon; + u32 val; + u32 mask; + int ret = 0; + + syscon = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pcie-mode"); + if (IS_ERR(syscon)) + return 0; + + /* Do not error out to maintain old DT compatibility */ + ret = of_parse_phandle_with_fixed_args(np, "ti,syscon-pcie-mode", 1, 0, &args); + if (!ret) + offset = args.args[0]; + + mask = KS_PCIE_DEV_TYPE_MASK | KS_PCIE_SYSCLOCKOUTEN; + val = KS_PCIE_DEV_TYPE(RC) | KS_PCIE_SYSCLOCKOUTEN; + + ret = regmap_update_bits(syscon, offset, mask, val); + if (ret) { + dev_err(dev, "failed to set pcie mode\n"); + return ret; + } + + return 0; +} + +static int ks_pcie_am654_set_mode(struct device *dev, + enum dw_pcie_device_mode mode) +{ + struct device_node *np = dev->of_node; + struct of_phandle_args args; + unsigned int offset = 0; + struct regmap *syscon; + u32 val; + u32 mask; + int ret = 0; + + syscon = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pcie-mode"); + if (IS_ERR(syscon)) + return 0; + + /* Do not error out to maintain old DT compatibility */ + ret = of_parse_phandle_with_fixed_args(np, "ti,syscon-pcie-mode", 1, 0, &args); + if (!ret) + offset = args.args[0]; + + mask = AM654_PCIE_DEV_TYPE_MASK; + + switch (mode) { + case DW_PCIE_RC_TYPE: + val = RC; + break; + case DW_PCIE_EP_TYPE: + val = EP; + break; + default: + dev_err(dev, "INVALID device type %d\n", mode); + return -EINVAL; + } + + ret = regmap_update_bits(syscon, offset, mask, val); + if (ret) { + dev_err(dev, "failed to set pcie mode\n"); + return ret; + } + + return 0; +} + +static const struct ks_pcie_of_data ks_pcie_rc_of_data = { + .host_ops = &ks_pcie_host_ops, + .version = DW_PCIE_VER_365A, +}; + +static const struct ks_pcie_of_data ks_pcie_am654_rc_of_data = { + .host_ops = &ks_pcie_am654_host_ops, + .mode = DW_PCIE_RC_TYPE, + .version = DW_PCIE_VER_490A, +}; + +static const struct ks_pcie_of_data ks_pcie_am654_ep_of_data = { + .ep_ops = &ks_pcie_am654_ep_ops, + .mode = DW_PCIE_EP_TYPE, + .version = DW_PCIE_VER_490A, +}; + +static const struct of_device_id ks_pcie_of_match[] = { + { + .type = "pci", + .data = &ks_pcie_rc_of_data, + .compatible = "ti,keystone-pcie", + }, + { + .data = &ks_pcie_am654_rc_of_data, + .compatible = "ti,am654-pcie-rc", + }, + { + .data = &ks_pcie_am654_ep_of_data, + .compatible = "ti,am654-pcie-ep", + }, + { }, +}; + +static int ks_pcie_probe(struct platform_device *pdev) +{ + const struct dw_pcie_host_ops *host_ops; + const struct dw_pcie_ep_ops *ep_ops; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + const struct ks_pcie_of_data *data; + enum dw_pcie_device_mode mode; + struct dw_pcie *pci; + struct keystone_pcie *ks_pcie; + struct device_link **link; + struct gpio_desc *gpiod; + struct resource *res; + void __iomem *base; + u32 num_viewport; + struct phy **phy; + u32 num_lanes; + char name[10]; + u32 version; + int ret; + int irq; + int i; + + data = of_device_get_match_data(dev); + if (!data) + return -EINVAL; + + version = data->version; + host_ops = data->host_ops; + ep_ops = data->ep_ops; + mode = data->mode; + + ks_pcie = devm_kzalloc(dev, sizeof(*ks_pcie), GFP_KERNEL); + if (!ks_pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "app"); + ks_pcie->va_app_base = devm_ioremap_resource(dev, res); + if (IS_ERR(ks_pcie->va_app_base)) + return PTR_ERR(ks_pcie->va_app_base); + + ks_pcie->app = *res; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbics"); + base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(base)) + return PTR_ERR(base); + + if (of_device_is_compatible(np, "ti,am654-pcie-rc")) + ks_pcie->is_am6 = true; + + pci->dbi_base = base; + pci->dbi_base2 = base; + pci->dev = dev; + pci->ops = &ks_pcie_dw_pcie_ops; + pci->version = version; + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + ret = request_irq(irq, ks_pcie_err_irq_handler, IRQF_SHARED, + "ks-pcie-error-irq", ks_pcie); + if (ret < 0) { + dev_err(dev, "failed to request error IRQ %d\n", + irq); + return ret; + } + + ret = of_property_read_u32(np, "num-lanes", &num_lanes); + if (ret) + num_lanes = 1; + + phy = devm_kzalloc(dev, sizeof(*phy) * num_lanes, GFP_KERNEL); + if (!phy) + return -ENOMEM; + + link = devm_kzalloc(dev, sizeof(*link) * num_lanes, GFP_KERNEL); + if (!link) + return -ENOMEM; + + for (i = 0; i < num_lanes; i++) { + snprintf(name, sizeof(name), "pcie-phy%d", i); + phy[i] = devm_phy_optional_get(dev, name); + if (IS_ERR(phy[i])) { + ret = PTR_ERR(phy[i]); + goto err_link; + } + + if (!phy[i]) + continue; + + link[i] = device_link_add(dev, &phy[i]->dev, DL_FLAG_STATELESS); + if (!link[i]) { + ret = -EINVAL; + goto err_link; + } + } + + ks_pcie->np = np; + ks_pcie->pci = pci; + ks_pcie->link = link; + ks_pcie->num_lanes = num_lanes; + ks_pcie->phy = phy; + + gpiod = devm_gpiod_get_optional(dev, "reset", + GPIOD_OUT_LOW); + if (IS_ERR(gpiod)) { + ret = PTR_ERR(gpiod); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get reset GPIO\n"); + goto err_link; + } + + /* Obtain references to the PHYs */ + for (i = 0; i < num_lanes; i++) + phy_pm_runtime_get_sync(ks_pcie->phy[i]); + + ret = ks_pcie_enable_phy(ks_pcie); + + /* Release references to the PHYs */ + for (i = 0; i < num_lanes; i++) + phy_pm_runtime_put_sync(ks_pcie->phy[i]); + + if (ret) { + dev_err(dev, "failed to enable phy\n"); + goto err_link; + } + + platform_set_drvdata(pdev, ks_pcie); + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "pm_runtime_get_sync failed\n"); + goto err_get_sync; + } + + if (dw_pcie_ver_is_ge(pci, 480A)) + ret = ks_pcie_am654_set_mode(dev, mode); + else + ret = ks_pcie_set_mode(dev); + if (ret < 0) + goto err_get_sync; + + switch (mode) { + case DW_PCIE_RC_TYPE: + if (!IS_ENABLED(CONFIG_PCI_KEYSTONE_HOST)) { + ret = -ENODEV; + goto err_get_sync; + } + + ret = of_property_read_u32(np, "num-viewport", &num_viewport); + if (ret < 0) { + dev_err(dev, "unable to read *num-viewport* property\n"); + goto err_get_sync; + } + + /* + * "Power Sequencing and Reset Signal Timings" table in + * PCI EXPRESS CARD ELECTROMECHANICAL SPECIFICATION, REV. 2.0 + * indicates PERST# should be deasserted after minimum of 100us + * once REFCLK is stable. The REFCLK to the connector in RC + * mode is selected while enabling the PHY. So deassert PERST# + * after 100 us. + */ + if (gpiod) { + usleep_range(100, 200); + gpiod_set_value_cansleep(gpiod, 1); + } + + ks_pcie->num_viewport = num_viewport; + pci->pp.ops = host_ops; + ret = dw_pcie_host_init(&pci->pp); + if (ret < 0) + goto err_get_sync; + break; + case DW_PCIE_EP_TYPE: + if (!IS_ENABLED(CONFIG_PCI_KEYSTONE_EP)) { + ret = -ENODEV; + goto err_get_sync; + } + + pci->ep.ops = ep_ops; + ret = dw_pcie_ep_init(&pci->ep); + if (ret < 0) + goto err_get_sync; + break; + default: + dev_err(dev, "INVALID device type %d\n", mode); + } + + ks_pcie_enable_error_irq(ks_pcie); + + return 0; + +err_get_sync: + pm_runtime_put(dev); + pm_runtime_disable(dev); + ks_pcie_disable_phy(ks_pcie); + +err_link: + while (--i >= 0 && link[i]) + device_link_del(link[i]); + + return ret; +} + +static int ks_pcie_remove(struct platform_device *pdev) +{ + struct keystone_pcie *ks_pcie = platform_get_drvdata(pdev); + struct device_link **link = ks_pcie->link; + int num_lanes = ks_pcie->num_lanes; + struct device *dev = &pdev->dev; + + pm_runtime_put(dev); + pm_runtime_disable(dev); + ks_pcie_disable_phy(ks_pcie); + while (num_lanes--) + device_link_del(link[num_lanes]); + + return 0; +} + +static struct platform_driver ks_pcie_driver = { + .probe = ks_pcie_probe, + .remove = ks_pcie_remove, + .driver = { + .name = "keystone-pcie", + .of_match_table = ks_pcie_of_match, + }, +}; +builtin_platform_driver(ks_pcie_driver); diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c new file mode 100644 index 000000000..ad99707b3 --- /dev/null +++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c @@ -0,0 +1,169 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe controller EP driver for Freescale Layerscape SoCs + * + * Copyright (C) 2018 NXP Semiconductor. + * + * Author: Xiaowei Bao <xiaowei.bao@nxp.com> + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/of_address.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> + +#include "pcie-designware.h" + +#define to_ls_pcie_ep(x) dev_get_drvdata((x)->dev) + +struct ls_pcie_ep_drvdata { + u32 func_offset; + const struct dw_pcie_ep_ops *ops; + const struct dw_pcie_ops *dw_pcie_ops; +}; + +struct ls_pcie_ep { + struct dw_pcie *pci; + struct pci_epc_features *ls_epc; + const struct ls_pcie_ep_drvdata *drvdata; +}; + +static const struct pci_epc_features* +ls_pcie_ep_get_features(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct ls_pcie_ep *pcie = to_ls_pcie_ep(pci); + + return pcie->ls_epc; +} + +static void ls_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct ls_pcie_ep *pcie = to_ls_pcie_ep(pci); + struct dw_pcie_ep_func *ep_func; + enum pci_barno bar; + + ep_func = dw_pcie_ep_get_func_from_ep(ep, 0); + if (!ep_func) + return; + + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) + dw_pcie_ep_reset_bar(pci, bar); + + pcie->ls_epc->msi_capable = ep_func->msi_cap ? true : false; + pcie->ls_epc->msix_capable = ep_func->msix_cap ? true : false; +} + +static int ls_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + enum pci_epc_irq_type type, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + return dw_pcie_ep_raise_legacy_irq(ep, func_no); + case PCI_EPC_IRQ_MSI: + return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num); + case PCI_EPC_IRQ_MSIX: + return dw_pcie_ep_raise_msix_irq_doorbell(ep, func_no, + interrupt_num); + default: + dev_err(pci->dev, "UNKNOWN IRQ type\n"); + return -EINVAL; + } +} + +static unsigned int ls_pcie_ep_func_conf_select(struct dw_pcie_ep *ep, + u8 func_no) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct ls_pcie_ep *pcie = to_ls_pcie_ep(pci); + + WARN_ON(func_no && !pcie->drvdata->func_offset); + return pcie->drvdata->func_offset * func_no; +} + +static const struct dw_pcie_ep_ops ls_pcie_ep_ops = { + .ep_init = ls_pcie_ep_init, + .raise_irq = ls_pcie_ep_raise_irq, + .get_features = ls_pcie_ep_get_features, + .func_conf_select = ls_pcie_ep_func_conf_select, +}; + +static const struct ls_pcie_ep_drvdata ls1_ep_drvdata = { + .ops = &ls_pcie_ep_ops, +}; + +static const struct ls_pcie_ep_drvdata ls2_ep_drvdata = { + .func_offset = 0x20000, + .ops = &ls_pcie_ep_ops, +}; + +static const struct ls_pcie_ep_drvdata lx2_ep_drvdata = { + .func_offset = 0x8000, + .ops = &ls_pcie_ep_ops, +}; + +static const struct of_device_id ls_pcie_ep_of_match[] = { + { .compatible = "fsl,ls1046a-pcie-ep", .data = &ls1_ep_drvdata }, + { .compatible = "fsl,ls1088a-pcie-ep", .data = &ls2_ep_drvdata }, + { .compatible = "fsl,ls2088a-pcie-ep", .data = &ls2_ep_drvdata }, + { .compatible = "fsl,lx2160ar2-pcie-ep", .data = &lx2_ep_drvdata }, + { }, +}; + +static int __init ls_pcie_ep_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci; + struct ls_pcie_ep *pcie; + struct pci_epc_features *ls_epc; + struct resource *dbi_base; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + ls_epc = devm_kzalloc(dev, sizeof(*ls_epc), GFP_KERNEL); + if (!ls_epc) + return -ENOMEM; + + pcie->drvdata = of_device_get_match_data(dev); + + pci->dev = dev; + pci->ops = pcie->drvdata->dw_pcie_ops; + + ls_epc->bar_fixed_64bit = (1 << BAR_2) | (1 << BAR_4); + + pcie->pci = pci; + pcie->ls_epc = ls_epc; + + dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs"); + pci->dbi_base = devm_pci_remap_cfg_resource(dev, dbi_base); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + + pci->ep.ops = &ls_pcie_ep_ops; + + platform_set_drvdata(pdev, pcie); + + return dw_pcie_ep_init(&pci->ep); +} + +static struct platform_driver ls_pcie_ep_driver = { + .driver = { + .name = "layerscape-pcie-ep", + .of_match_table = ls_pcie_ep_of_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver_probe(ls_pcie_ep_driver, ls_pcie_ep_probe); diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c new file mode 100644 index 000000000..879b8692f --- /dev/null +++ b/drivers/pci/controller/dwc/pci-layerscape.c @@ -0,0 +1,151 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Freescale Layerscape SoCs + * + * Copyright (C) 2014 Freescale Semiconductor. + * Copyright 2021 NXP + * + * Author: Minghuan Lian <Minghuan.Lian@freescale.com> + */ + +#include <linux/kernel.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/of_irq.h> +#include <linux/of_address.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> + +#include "pcie-designware.h" + +/* PEX Internal Configuration Registers */ +#define PCIE_STRFMR1 0x71c /* Symbol Timer & Filter Mask Register1 */ +#define PCIE_ABSERR 0x8d0 /* Bridge Slave Error Response Register */ +#define PCIE_ABSERR_SETTING 0x9401 /* Forward error of non-posted request */ + +#define PCIE_IATU_NUM 6 + +struct ls_pcie { + struct dw_pcie *pci; +}; + +#define to_ls_pcie(x) dev_get_drvdata((x)->dev) + +static bool ls_pcie_is_bridge(struct ls_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + u32 header_type; + + header_type = ioread8(pci->dbi_base + PCI_HEADER_TYPE); + header_type &= 0x7f; + + return header_type == PCI_HEADER_TYPE_BRIDGE; +} + +/* Clear multi-function bit */ +static void ls_pcie_clear_multifunction(struct ls_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + + iowrite8(PCI_HEADER_TYPE_BRIDGE, pci->dbi_base + PCI_HEADER_TYPE); +} + +/* Drop MSG TLP except for Vendor MSG */ +static void ls_pcie_drop_msg_tlp(struct ls_pcie *pcie) +{ + u32 val; + struct dw_pcie *pci = pcie->pci; + + val = ioread32(pci->dbi_base + PCIE_STRFMR1); + val &= 0xDFFFFFFF; + iowrite32(val, pci->dbi_base + PCIE_STRFMR1); +} + +/* Forward error response of outbound non-posted requests */ +static void ls_pcie_fix_error_response(struct ls_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + + iowrite32(PCIE_ABSERR_SETTING, pci->dbi_base + PCIE_ABSERR); +} + +static int ls_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct ls_pcie *pcie = to_ls_pcie(pci); + + ls_pcie_fix_error_response(pcie); + + dw_pcie_dbi_ro_wr_en(pci); + ls_pcie_clear_multifunction(pcie); + dw_pcie_dbi_ro_wr_dis(pci); + + ls_pcie_drop_msg_tlp(pcie); + + return 0; +} + +static const struct dw_pcie_host_ops ls_pcie_host_ops = { + .host_init = ls_pcie_host_init, +}; + +static const struct of_device_id ls_pcie_of_match[] = { + { .compatible = "fsl,ls1012a-pcie", }, + { .compatible = "fsl,ls1021a-pcie", }, + { .compatible = "fsl,ls1028a-pcie", }, + { .compatible = "fsl,ls1043a-pcie", }, + { .compatible = "fsl,ls1046a-pcie", }, + { .compatible = "fsl,ls2080a-pcie", }, + { .compatible = "fsl,ls2085a-pcie", }, + { .compatible = "fsl,ls2088a-pcie", }, + { .compatible = "fsl,ls1088a-pcie", }, + { }, +}; + +static int ls_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci; + struct ls_pcie *pcie; + struct resource *dbi_base; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pci->dev = dev; + pci->pp.ops = &ls_pcie_host_ops; + + pcie->pci = pci; + + dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs"); + pci->dbi_base = devm_pci_remap_cfg_resource(dev, dbi_base); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + + if (!ls_pcie_is_bridge(pcie)) + return -ENODEV; + + platform_set_drvdata(pdev, pcie); + + return dw_pcie_host_init(&pci->pp); +} + +static struct platform_driver ls_pcie_driver = { + .probe = ls_pcie_probe, + .driver = { + .name = "layerscape-pcie", + .of_match_table = ls_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver(ls_pcie_driver); diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c new file mode 100644 index 000000000..c1527693b --- /dev/null +++ b/drivers/pci/controller/dwc/pci-meson.c @@ -0,0 +1,492 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Amlogic MESON SoCs + * + * Copyright (c) 2018 Amlogic, inc. + * Author: Yue Wang <yue.wang@amlogic.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/of_device.h> +#include <linux/of_gpio.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/reset.h> +#include <linux/resource.h> +#include <linux/types.h> +#include <linux/phy/phy.h> +#include <linux/module.h> + +#include "pcie-designware.h" + +#define to_meson_pcie(x) dev_get_drvdata((x)->dev) + +#define PCIE_CAP_MAX_PAYLOAD_SIZE(x) ((x) << 5) +#define PCIE_CAP_MAX_READ_REQ_SIZE(x) ((x) << 12) + +/* PCIe specific config registers */ +#define PCIE_CFG0 0x0 +#define APP_LTSSM_ENABLE BIT(7) + +#define PCIE_CFG_STATUS12 0x30 +#define IS_SMLH_LINK_UP(x) ((x) & (1 << 6)) +#define IS_RDLH_LINK_UP(x) ((x) & (1 << 16)) +#define IS_LTSSM_UP(x) ((((x) >> 10) & 0x1f) == 0x11) + +#define PCIE_CFG_STATUS17 0x44 +#define PM_CURRENT_STATE(x) (((x) >> 7) & 0x1) + +#define WAIT_LINKUP_TIMEOUT 4000 +#define PORT_CLK_RATE 100000000UL +#define MAX_PAYLOAD_SIZE 256 +#define MAX_READ_REQ_SIZE 256 +#define PCIE_RESET_DELAY 500 +#define PCIE_SHARED_RESET 1 +#define PCIE_NORMAL_RESET 0 + +enum pcie_data_rate { + PCIE_GEN1, + PCIE_GEN2, + PCIE_GEN3, + PCIE_GEN4 +}; + +struct meson_pcie_clk_res { + struct clk *clk; + struct clk *port_clk; + struct clk *general_clk; +}; + +struct meson_pcie_rc_reset { + struct reset_control *port; + struct reset_control *apb; +}; + +struct meson_pcie { + struct dw_pcie pci; + void __iomem *cfg_base; + struct meson_pcie_clk_res clk_res; + struct meson_pcie_rc_reset mrst; + struct gpio_desc *reset_gpio; + struct phy *phy; +}; + +static struct reset_control *meson_pcie_get_reset(struct meson_pcie *mp, + const char *id, + u32 reset_type) +{ + struct device *dev = mp->pci.dev; + struct reset_control *reset; + + if (reset_type == PCIE_SHARED_RESET) + reset = devm_reset_control_get_shared(dev, id); + else + reset = devm_reset_control_get(dev, id); + + return reset; +} + +static int meson_pcie_get_resets(struct meson_pcie *mp) +{ + struct meson_pcie_rc_reset *mrst = &mp->mrst; + + mrst->port = meson_pcie_get_reset(mp, "port", PCIE_NORMAL_RESET); + if (IS_ERR(mrst->port)) + return PTR_ERR(mrst->port); + reset_control_deassert(mrst->port); + + mrst->apb = meson_pcie_get_reset(mp, "apb", PCIE_SHARED_RESET); + if (IS_ERR(mrst->apb)) + return PTR_ERR(mrst->apb); + reset_control_deassert(mrst->apb); + + return 0; +} + +static int meson_pcie_get_mems(struct platform_device *pdev, + struct meson_pcie *mp) +{ + struct dw_pcie *pci = &mp->pci; + + pci->dbi_base = devm_platform_ioremap_resource_byname(pdev, "elbi"); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + + mp->cfg_base = devm_platform_ioremap_resource_byname(pdev, "cfg"); + if (IS_ERR(mp->cfg_base)) + return PTR_ERR(mp->cfg_base); + + return 0; +} + +static int meson_pcie_power_on(struct meson_pcie *mp) +{ + int ret = 0; + + ret = phy_init(mp->phy); + if (ret) + return ret; + + ret = phy_power_on(mp->phy); + if (ret) { + phy_exit(mp->phy); + return ret; + } + + return 0; +} + +static void meson_pcie_power_off(struct meson_pcie *mp) +{ + phy_power_off(mp->phy); + phy_exit(mp->phy); +} + +static int meson_pcie_reset(struct meson_pcie *mp) +{ + struct meson_pcie_rc_reset *mrst = &mp->mrst; + int ret = 0; + + ret = phy_reset(mp->phy); + if (ret) + return ret; + + reset_control_assert(mrst->port); + reset_control_assert(mrst->apb); + udelay(PCIE_RESET_DELAY); + reset_control_deassert(mrst->port); + reset_control_deassert(mrst->apb); + udelay(PCIE_RESET_DELAY); + + return 0; +} + +static inline struct clk *meson_pcie_probe_clock(struct device *dev, + const char *id, u64 rate) +{ + struct clk *clk; + int ret; + + clk = devm_clk_get(dev, id); + if (IS_ERR(clk)) + return clk; + + if (rate) { + ret = clk_set_rate(clk, rate); + if (ret) { + dev_err(dev, "set clk rate failed, ret = %d\n", ret); + return ERR_PTR(ret); + } + } + + ret = clk_prepare_enable(clk); + if (ret) { + dev_err(dev, "couldn't enable clk\n"); + return ERR_PTR(ret); + } + + devm_add_action_or_reset(dev, + (void (*) (void *))clk_disable_unprepare, + clk); + + return clk; +} + +static int meson_pcie_probe_clocks(struct meson_pcie *mp) +{ + struct device *dev = mp->pci.dev; + struct meson_pcie_clk_res *res = &mp->clk_res; + + res->port_clk = meson_pcie_probe_clock(dev, "port", PORT_CLK_RATE); + if (IS_ERR(res->port_clk)) + return PTR_ERR(res->port_clk); + + res->general_clk = meson_pcie_probe_clock(dev, "general", 0); + if (IS_ERR(res->general_clk)) + return PTR_ERR(res->general_clk); + + res->clk = meson_pcie_probe_clock(dev, "pclk", 0); + if (IS_ERR(res->clk)) + return PTR_ERR(res->clk); + + return 0; +} + +static inline u32 meson_cfg_readl(struct meson_pcie *mp, u32 reg) +{ + return readl(mp->cfg_base + reg); +} + +static inline void meson_cfg_writel(struct meson_pcie *mp, u32 val, u32 reg) +{ + writel(val, mp->cfg_base + reg); +} + +static void meson_pcie_assert_reset(struct meson_pcie *mp) +{ + gpiod_set_value_cansleep(mp->reset_gpio, 1); + udelay(500); + gpiod_set_value_cansleep(mp->reset_gpio, 0); +} + +static void meson_pcie_ltssm_enable(struct meson_pcie *mp) +{ + u32 val; + + val = meson_cfg_readl(mp, PCIE_CFG0); + val |= APP_LTSSM_ENABLE; + meson_cfg_writel(mp, val, PCIE_CFG0); +} + +static int meson_size_to_payload(struct meson_pcie *mp, int size) +{ + struct device *dev = mp->pci.dev; + + /* + * dwc supports 2^(val+7) payload size, which val is 0~5 default to 1. + * So if input size is not 2^order alignment or less than 2^7 or bigger + * than 2^12, just set to default size 2^(1+7). + */ + if (!is_power_of_2(size) || size < 128 || size > 4096) { + dev_warn(dev, "payload size %d, set to default 256\n", size); + return 1; + } + + return fls(size) - 8; +} + +static void meson_set_max_payload(struct meson_pcie *mp, int size) +{ + struct dw_pcie *pci = &mp->pci; + u32 val; + u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + int max_payload_size = meson_size_to_payload(mp, size); + + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_DEVCTL); + val &= ~PCI_EXP_DEVCTL_PAYLOAD; + dw_pcie_writel_dbi(pci, offset + PCI_EXP_DEVCTL, val); + + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_DEVCTL); + val |= PCIE_CAP_MAX_PAYLOAD_SIZE(max_payload_size); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_DEVCTL, val); +} + +static void meson_set_max_rd_req_size(struct meson_pcie *mp, int size) +{ + struct dw_pcie *pci = &mp->pci; + u32 val; + u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + int max_rd_req_size = meson_size_to_payload(mp, size); + + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_DEVCTL); + val &= ~PCI_EXP_DEVCTL_READRQ; + dw_pcie_writel_dbi(pci, offset + PCI_EXP_DEVCTL, val); + + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_DEVCTL); + val |= PCIE_CAP_MAX_READ_REQ_SIZE(max_rd_req_size); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_DEVCTL, val); +} + +static int meson_pcie_start_link(struct dw_pcie *pci) +{ + struct meson_pcie *mp = to_meson_pcie(pci); + + meson_pcie_ltssm_enable(mp); + meson_pcie_assert_reset(mp); + + return 0; +} + +static int meson_pcie_rd_own_conf(struct pci_bus *bus, u32 devfn, + int where, int size, u32 *val) +{ + int ret; + + ret = pci_generic_config_read(bus, devfn, where, size, val); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + /* + * There is a bug in the MESON AXG PCIe controller whereby software + * cannot program the PCI_CLASS_DEVICE register, so we must fabricate + * the return value in the config accessors. + */ + if ((where & ~3) == PCI_CLASS_REVISION) { + if (size <= 2) + *val = (*val & ((1 << (size * 8)) - 1)) << (8 * (where & 3)); + *val &= ~0xffffff00; + *val |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8; + if (size <= 2) + *val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); + } + + return PCIBIOS_SUCCESSFUL; +} + +static struct pci_ops meson_pci_ops = { + .map_bus = dw_pcie_own_conf_map_bus, + .read = meson_pcie_rd_own_conf, + .write = pci_generic_config_write, +}; + +static int meson_pcie_link_up(struct dw_pcie *pci) +{ + struct meson_pcie *mp = to_meson_pcie(pci); + struct device *dev = pci->dev; + u32 speed_okay = 0; + u32 cnt = 0; + u32 state12, state17, smlh_up, ltssm_up, rdlh_up; + + do { + state12 = meson_cfg_readl(mp, PCIE_CFG_STATUS12); + state17 = meson_cfg_readl(mp, PCIE_CFG_STATUS17); + smlh_up = IS_SMLH_LINK_UP(state12); + rdlh_up = IS_RDLH_LINK_UP(state12); + ltssm_up = IS_LTSSM_UP(state12); + + if (PM_CURRENT_STATE(state17) < PCIE_GEN3) + speed_okay = 1; + + if (smlh_up) + dev_dbg(dev, "smlh_link_up is on\n"); + if (rdlh_up) + dev_dbg(dev, "rdlh_link_up is on\n"); + if (ltssm_up) + dev_dbg(dev, "ltssm_up is on\n"); + if (speed_okay) + dev_dbg(dev, "speed_okay\n"); + + if (smlh_up && rdlh_up && ltssm_up && speed_okay) + return 1; + + cnt++; + + udelay(10); + } while (cnt < WAIT_LINKUP_TIMEOUT); + + dev_err(dev, "error: wait linkup timeout\n"); + return 0; +} + +static int meson_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct meson_pcie *mp = to_meson_pcie(pci); + + pp->bridge->ops = &meson_pci_ops; + + meson_set_max_payload(mp, MAX_PAYLOAD_SIZE); + meson_set_max_rd_req_size(mp, MAX_READ_REQ_SIZE); + + return 0; +} + +static const struct dw_pcie_host_ops meson_pcie_host_ops = { + .host_init = meson_pcie_host_init, +}; + +static const struct dw_pcie_ops dw_pcie_ops = { + .link_up = meson_pcie_link_up, + .start_link = meson_pcie_start_link, +}; + +static int meson_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci; + struct meson_pcie *mp; + int ret; + + mp = devm_kzalloc(dev, sizeof(*mp), GFP_KERNEL); + if (!mp) + return -ENOMEM; + + pci = &mp->pci; + pci->dev = dev; + pci->ops = &dw_pcie_ops; + pci->pp.ops = &meson_pcie_host_ops; + pci->num_lanes = 1; + + mp->phy = devm_phy_get(dev, "pcie"); + if (IS_ERR(mp->phy)) { + dev_err(dev, "get phy failed, %ld\n", PTR_ERR(mp->phy)); + return PTR_ERR(mp->phy); + } + + mp->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(mp->reset_gpio)) { + dev_err(dev, "get reset gpio failed\n"); + return PTR_ERR(mp->reset_gpio); + } + + ret = meson_pcie_get_resets(mp); + if (ret) { + dev_err(dev, "get reset resource failed, %d\n", ret); + return ret; + } + + ret = meson_pcie_get_mems(pdev, mp); + if (ret) { + dev_err(dev, "get memory resource failed, %d\n", ret); + return ret; + } + + ret = meson_pcie_power_on(mp); + if (ret) { + dev_err(dev, "phy power on failed, %d\n", ret); + return ret; + } + + ret = meson_pcie_reset(mp); + if (ret) { + dev_err(dev, "reset failed, %d\n", ret); + goto err_phy; + } + + ret = meson_pcie_probe_clocks(mp); + if (ret) { + dev_err(dev, "init clock resources failed, %d\n", ret); + goto err_phy; + } + + platform_set_drvdata(pdev, mp); + + ret = dw_pcie_host_init(&pci->pp); + if (ret < 0) { + dev_err(dev, "Add PCIe port failed, %d\n", ret); + goto err_phy; + } + + return 0; + +err_phy: + meson_pcie_power_off(mp); + return ret; +} + +static const struct of_device_id meson_pcie_of_match[] = { + { + .compatible = "amlogic,axg-pcie", + }, + { + .compatible = "amlogic,g12a-pcie", + }, + {}, +}; +MODULE_DEVICE_TABLE(of, meson_pcie_of_match); + +static struct platform_driver meson_pcie_driver = { + .probe = meson_pcie_probe, + .driver = { + .name = "meson-pcie", + .of_match_table = meson_pcie_of_match, + }, +}; + +module_platform_driver(meson_pcie_driver); + +MODULE_AUTHOR("Yue Wang <yue.wang@amlogic.com>"); +MODULE_DESCRIPTION("Amlogic PCIe Controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pcie-al.c b/drivers/pci/controller/dwc/pcie-al.c new file mode 100644 index 000000000..b8cb77c9c --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-al.c @@ -0,0 +1,380 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Amazon's Annapurna Labs IP (used in chips + * such as Graviton and Alpine) + * + * Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved. + * + * Author: Jonathan Chocron <jonnyc@amazon.com> + */ + +#include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/pci-acpi.h> +#include "../../pci.h" + +#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) + +struct al_pcie_acpi { + void __iomem *dbi_base; +}; + +static void __iomem *al_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) +{ + struct pci_config_window *cfg = bus->sysdata; + struct al_pcie_acpi *pcie = cfg->priv; + void __iomem *dbi_base = pcie->dbi_base; + + if (bus->number == cfg->busr.start) { + /* + * The DW PCIe core doesn't filter out transactions to other + * devices/functions on the root bus num, so we do this here. + */ + if (PCI_SLOT(devfn) > 0) + return NULL; + else + return dbi_base + where; + } + + return pci_ecam_map_bus(bus, devfn, where); +} + +static int al_pcie_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct acpi_device *adev = to_acpi_device(dev); + struct acpi_pci_root *root = acpi_driver_data(adev); + struct al_pcie_acpi *al_pcie; + struct resource *res; + int ret; + + al_pcie = devm_kzalloc(dev, sizeof(*al_pcie), GFP_KERNEL); + if (!al_pcie) + return -ENOMEM; + + res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL); + if (!res) + return -ENOMEM; + + ret = acpi_get_rc_resources(dev, "AMZN0001", root->segment, res); + if (ret) { + dev_err(dev, "can't get rc dbi base address for SEG %d\n", + root->segment); + return ret; + } + + dev_dbg(dev, "Root port dbi res: %pR\n", res); + + al_pcie->dbi_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(al_pcie->dbi_base)) + return PTR_ERR(al_pcie->dbi_base); + + cfg->priv = al_pcie; + + return 0; +} + +const struct pci_ecam_ops al_pcie_ops = { + .init = al_pcie_init, + .pci_ops = { + .map_bus = al_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +#endif /* defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) */ + +#ifdef CONFIG_PCIE_AL + +#include <linux/of_pci.h> +#include "pcie-designware.h" + +#define AL_PCIE_REV_ID_2 2 +#define AL_PCIE_REV_ID_3 3 +#define AL_PCIE_REV_ID_4 4 + +#define AXI_BASE_OFFSET 0x0 + +#define DEVICE_ID_OFFSET 0x16c + +#define DEVICE_REV_ID 0x0 +#define DEVICE_REV_ID_DEV_ID_MASK GENMASK(31, 16) + +#define DEVICE_REV_ID_DEV_ID_X4 0 +#define DEVICE_REV_ID_DEV_ID_X8 2 +#define DEVICE_REV_ID_DEV_ID_X16 4 + +#define OB_CTRL_REV1_2_OFFSET 0x0040 +#define OB_CTRL_REV3_5_OFFSET 0x0030 + +#define CFG_TARGET_BUS 0x0 +#define CFG_TARGET_BUS_MASK_MASK GENMASK(7, 0) +#define CFG_TARGET_BUS_BUSNUM_MASK GENMASK(15, 8) + +#define CFG_CONTROL 0x4 +#define CFG_CONTROL_SUBBUS_MASK GENMASK(15, 8) +#define CFG_CONTROL_SEC_BUS_MASK GENMASK(23, 16) + +struct al_pcie_reg_offsets { + unsigned int ob_ctrl; +}; + +struct al_pcie_target_bus_cfg { + u8 reg_val; + u8 reg_mask; + u8 ecam_mask; +}; + +struct al_pcie { + struct dw_pcie *pci; + void __iomem *controller_base; /* base of PCIe unit (not DW core) */ + struct device *dev; + resource_size_t ecam_size; + unsigned int controller_rev_id; + struct al_pcie_reg_offsets reg_offsets; + struct al_pcie_target_bus_cfg target_bus_cfg; +}; + +#define to_al_pcie(x) dev_get_drvdata((x)->dev) + +static inline u32 al_pcie_controller_readl(struct al_pcie *pcie, u32 offset) +{ + return readl_relaxed(pcie->controller_base + offset); +} + +static inline void al_pcie_controller_writel(struct al_pcie *pcie, u32 offset, + u32 val) +{ + writel_relaxed(val, pcie->controller_base + offset); +} + +static int al_pcie_rev_id_get(struct al_pcie *pcie, unsigned int *rev_id) +{ + u32 dev_rev_id_val; + u32 dev_id_val; + + dev_rev_id_val = al_pcie_controller_readl(pcie, AXI_BASE_OFFSET + + DEVICE_ID_OFFSET + + DEVICE_REV_ID); + dev_id_val = FIELD_GET(DEVICE_REV_ID_DEV_ID_MASK, dev_rev_id_val); + + switch (dev_id_val) { + case DEVICE_REV_ID_DEV_ID_X4: + *rev_id = AL_PCIE_REV_ID_2; + break; + case DEVICE_REV_ID_DEV_ID_X8: + *rev_id = AL_PCIE_REV_ID_3; + break; + case DEVICE_REV_ID_DEV_ID_X16: + *rev_id = AL_PCIE_REV_ID_4; + break; + default: + dev_err(pcie->dev, "Unsupported dev_id_val (0x%x)\n", + dev_id_val); + return -EINVAL; + } + + dev_dbg(pcie->dev, "dev_id_val: 0x%x\n", dev_id_val); + + return 0; +} + +static int al_pcie_reg_offsets_set(struct al_pcie *pcie) +{ + switch (pcie->controller_rev_id) { + case AL_PCIE_REV_ID_2: + pcie->reg_offsets.ob_ctrl = OB_CTRL_REV1_2_OFFSET; + break; + case AL_PCIE_REV_ID_3: + case AL_PCIE_REV_ID_4: + pcie->reg_offsets.ob_ctrl = OB_CTRL_REV3_5_OFFSET; + break; + default: + dev_err(pcie->dev, "Unsupported controller rev_id: 0x%x\n", + pcie->controller_rev_id); + return -EINVAL; + } + + return 0; +} + +static inline void al_pcie_target_bus_set(struct al_pcie *pcie, + u8 target_bus, + u8 mask_target_bus) +{ + u32 reg; + + reg = FIELD_PREP(CFG_TARGET_BUS_MASK_MASK, mask_target_bus) | + FIELD_PREP(CFG_TARGET_BUS_BUSNUM_MASK, target_bus); + + al_pcie_controller_writel(pcie, AXI_BASE_OFFSET + + pcie->reg_offsets.ob_ctrl + CFG_TARGET_BUS, + reg); +} + +static void __iomem *al_pcie_conf_addr_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct al_pcie *pcie = to_al_pcie(to_dw_pcie_from_pp(pp)); + unsigned int busnr = bus->number; + struct al_pcie_target_bus_cfg *target_bus_cfg = &pcie->target_bus_cfg; + unsigned int busnr_ecam = busnr & target_bus_cfg->ecam_mask; + unsigned int busnr_reg = busnr & target_bus_cfg->reg_mask; + + if (busnr_reg != target_bus_cfg->reg_val) { + dev_dbg(pcie->pci->dev, "Changing target bus busnum val from 0x%x to 0x%x\n", + target_bus_cfg->reg_val, busnr_reg); + target_bus_cfg->reg_val = busnr_reg; + al_pcie_target_bus_set(pcie, + target_bus_cfg->reg_val, + target_bus_cfg->reg_mask); + } + + return pp->va_cfg0_base + PCIE_ECAM_OFFSET(busnr_ecam, devfn, where); +} + +static struct pci_ops al_child_pci_ops = { + .map_bus = al_pcie_conf_addr_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static void al_pcie_config_prepare(struct al_pcie *pcie) +{ + struct al_pcie_target_bus_cfg *target_bus_cfg; + struct dw_pcie_rp *pp = &pcie->pci->pp; + unsigned int ecam_bus_mask; + u32 cfg_control_offset; + u8 subordinate_bus; + u8 secondary_bus; + u32 cfg_control; + u32 reg; + struct resource *bus = resource_list_first_type(&pp->bridge->windows, IORESOURCE_BUS)->res; + + target_bus_cfg = &pcie->target_bus_cfg; + + ecam_bus_mask = (pcie->ecam_size >> PCIE_ECAM_BUS_SHIFT) - 1; + if (ecam_bus_mask > 255) { + dev_warn(pcie->dev, "ECAM window size is larger than 256MB. Cutting off at 256\n"); + ecam_bus_mask = 255; + } + + /* This portion is taken from the transaction address */ + target_bus_cfg->ecam_mask = ecam_bus_mask; + /* This portion is taken from the cfg_target_bus reg */ + target_bus_cfg->reg_mask = ~target_bus_cfg->ecam_mask; + target_bus_cfg->reg_val = bus->start & target_bus_cfg->reg_mask; + + al_pcie_target_bus_set(pcie, target_bus_cfg->reg_val, + target_bus_cfg->reg_mask); + + secondary_bus = bus->start + 1; + subordinate_bus = bus->end; + + /* Set the valid values of secondary and subordinate buses */ + cfg_control_offset = AXI_BASE_OFFSET + pcie->reg_offsets.ob_ctrl + + CFG_CONTROL; + + cfg_control = al_pcie_controller_readl(pcie, cfg_control_offset); + + reg = cfg_control & + ~(CFG_CONTROL_SEC_BUS_MASK | CFG_CONTROL_SUBBUS_MASK); + + reg |= FIELD_PREP(CFG_CONTROL_SUBBUS_MASK, subordinate_bus) | + FIELD_PREP(CFG_CONTROL_SEC_BUS_MASK, secondary_bus); + + al_pcie_controller_writel(pcie, cfg_control_offset, reg); +} + +static int al_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct al_pcie *pcie = to_al_pcie(pci); + int rc; + + pp->bridge->child_ops = &al_child_pci_ops; + + rc = al_pcie_rev_id_get(pcie, &pcie->controller_rev_id); + if (rc) + return rc; + + rc = al_pcie_reg_offsets_set(pcie); + if (rc) + return rc; + + al_pcie_config_prepare(pcie); + + return 0; +} + +static const struct dw_pcie_host_ops al_pcie_host_ops = { + .host_init = al_pcie_host_init, +}; + +static int al_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct resource *controller_res; + struct resource *ecam_res; + struct al_pcie *al_pcie; + struct dw_pcie *pci; + + al_pcie = devm_kzalloc(dev, sizeof(*al_pcie), GFP_KERNEL); + if (!al_pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pci->dev = dev; + pci->pp.ops = &al_pcie_host_ops; + + al_pcie->pci = pci; + al_pcie->dev = dev; + + ecam_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config"); + if (!ecam_res) { + dev_err(dev, "couldn't find 'config' reg in DT\n"); + return -ENOENT; + } + al_pcie->ecam_size = resource_size(ecam_res); + + controller_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "controller"); + al_pcie->controller_base = devm_ioremap_resource(dev, controller_res); + if (IS_ERR(al_pcie->controller_base)) { + dev_err(dev, "couldn't remap controller base %pR\n", + controller_res); + return PTR_ERR(al_pcie->controller_base); + } + + dev_dbg(dev, "From DT: controller_base: %pR\n", controller_res); + + platform_set_drvdata(pdev, al_pcie); + + return dw_pcie_host_init(&pci->pp); +} + +static const struct of_device_id al_pcie_of_match[] = { + { .compatible = "amazon,al-alpine-v2-pcie", + }, + { .compatible = "amazon,al-alpine-v3-pcie", + }, + {}, +}; + +static struct platform_driver al_pcie_driver = { + .driver = { + .name = "al-pcie", + .of_match_table = al_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = al_pcie_probe, +}; +builtin_platform_driver(al_pcie_driver); + +#endif /* CONFIG_PCIE_AL*/ diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c new file mode 100644 index 000000000..dc469ef8e --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-armada8k.c @@ -0,0 +1,350 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Marvell Armada-8K SoCs + * + * Armada-8K PCIe Glue Layer Source Code + * + * Copyright (C) 2016 Marvell Technology Group Ltd. + * + * Author: Yehuda Yitshak <yehuday@marvell.com> + * Author: Shadi Ammouri <shadi@marvell.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/of_pci.h> +#include <linux/of_irq.h> + +#include "pcie-designware.h" + +#define ARMADA8K_PCIE_MAX_LANES PCIE_LNK_X4 + +struct armada8k_pcie { + struct dw_pcie *pci; + struct clk *clk; + struct clk *clk_reg; + struct phy *phy[ARMADA8K_PCIE_MAX_LANES]; + unsigned int phy_count; +}; + +#define PCIE_VENDOR_REGS_OFFSET 0x8000 + +#define PCIE_GLOBAL_CONTROL_REG (PCIE_VENDOR_REGS_OFFSET + 0x0) +#define PCIE_APP_LTSSM_EN BIT(2) +#define PCIE_DEVICE_TYPE_SHIFT 4 +#define PCIE_DEVICE_TYPE_MASK 0xF +#define PCIE_DEVICE_TYPE_RC 0x4 /* Root complex */ + +#define PCIE_GLOBAL_STATUS_REG (PCIE_VENDOR_REGS_OFFSET + 0x8) +#define PCIE_GLB_STS_RDLH_LINK_UP BIT(1) +#define PCIE_GLB_STS_PHY_LINK_UP BIT(9) + +#define PCIE_GLOBAL_INT_CAUSE1_REG (PCIE_VENDOR_REGS_OFFSET + 0x1C) +#define PCIE_GLOBAL_INT_MASK1_REG (PCIE_VENDOR_REGS_OFFSET + 0x20) +#define PCIE_INT_A_ASSERT_MASK BIT(9) +#define PCIE_INT_B_ASSERT_MASK BIT(10) +#define PCIE_INT_C_ASSERT_MASK BIT(11) +#define PCIE_INT_D_ASSERT_MASK BIT(12) + +#define PCIE_ARCACHE_TRC_REG (PCIE_VENDOR_REGS_OFFSET + 0x50) +#define PCIE_AWCACHE_TRC_REG (PCIE_VENDOR_REGS_OFFSET + 0x54) +#define PCIE_ARUSER_REG (PCIE_VENDOR_REGS_OFFSET + 0x5C) +#define PCIE_AWUSER_REG (PCIE_VENDOR_REGS_OFFSET + 0x60) +/* + * AR/AW Cache defaults: Normal memory, Write-Back, Read / Write + * allocate + */ +#define ARCACHE_DEFAULT_VALUE 0x3511 +#define AWCACHE_DEFAULT_VALUE 0x5311 + +#define DOMAIN_OUTER_SHAREABLE 0x2 +#define AX_USER_DOMAIN_MASK 0x3 +#define AX_USER_DOMAIN_SHIFT 4 + +#define to_armada8k_pcie(x) dev_get_drvdata((x)->dev) + +static void armada8k_pcie_disable_phys(struct armada8k_pcie *pcie) +{ + int i; + + for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) { + phy_power_off(pcie->phy[i]); + phy_exit(pcie->phy[i]); + } +} + +static int armada8k_pcie_enable_phys(struct armada8k_pcie *pcie) +{ + int ret; + int i; + + for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) { + ret = phy_init(pcie->phy[i]); + if (ret) + return ret; + + ret = phy_set_mode_ext(pcie->phy[i], PHY_MODE_PCIE, + pcie->phy_count); + if (ret) { + phy_exit(pcie->phy[i]); + return ret; + } + + ret = phy_power_on(pcie->phy[i]); + if (ret) { + phy_exit(pcie->phy[i]); + return ret; + } + } + + return 0; +} + +static int armada8k_pcie_setup_phys(struct armada8k_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + struct device_node *node = dev->of_node; + int ret = 0; + int i; + + for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) { + pcie->phy[i] = devm_of_phy_get_by_index(dev, node, i); + if (IS_ERR(pcie->phy[i])) { + if (PTR_ERR(pcie->phy[i]) != -ENODEV) + return PTR_ERR(pcie->phy[i]); + + pcie->phy[i] = NULL; + continue; + } + + pcie->phy_count++; + } + + /* Old bindings miss the PHY handle, so just warn if there is no PHY */ + if (!pcie->phy_count) + dev_warn(dev, "No available PHY\n"); + + ret = armada8k_pcie_enable_phys(pcie); + if (ret) + dev_err(dev, "Failed to initialize PHY(s) (%d)\n", ret); + + return ret; +} + +static int armada8k_pcie_link_up(struct dw_pcie *pci) +{ + u32 reg; + u32 mask = PCIE_GLB_STS_RDLH_LINK_UP | PCIE_GLB_STS_PHY_LINK_UP; + + reg = dw_pcie_readl_dbi(pci, PCIE_GLOBAL_STATUS_REG); + + if ((reg & mask) == mask) + return 1; + + dev_dbg(pci->dev, "No link detected (Global-Status: 0x%08x).\n", reg); + return 0; +} + +static int armada8k_pcie_start_link(struct dw_pcie *pci) +{ + u32 reg; + + /* Start LTSSM */ + reg = dw_pcie_readl_dbi(pci, PCIE_GLOBAL_CONTROL_REG); + reg |= PCIE_APP_LTSSM_EN; + dw_pcie_writel_dbi(pci, PCIE_GLOBAL_CONTROL_REG, reg); + + return 0; +} + +static int armada8k_pcie_host_init(struct dw_pcie_rp *pp) +{ + u32 reg; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + + if (!dw_pcie_link_up(pci)) { + /* Disable LTSSM state machine to enable configuration */ + reg = dw_pcie_readl_dbi(pci, PCIE_GLOBAL_CONTROL_REG); + reg &= ~(PCIE_APP_LTSSM_EN); + dw_pcie_writel_dbi(pci, PCIE_GLOBAL_CONTROL_REG, reg); + } + + /* Set the device to root complex mode */ + reg = dw_pcie_readl_dbi(pci, PCIE_GLOBAL_CONTROL_REG); + reg &= ~(PCIE_DEVICE_TYPE_MASK << PCIE_DEVICE_TYPE_SHIFT); + reg |= PCIE_DEVICE_TYPE_RC << PCIE_DEVICE_TYPE_SHIFT; + dw_pcie_writel_dbi(pci, PCIE_GLOBAL_CONTROL_REG, reg); + + /* Set the PCIe master AxCache attributes */ + dw_pcie_writel_dbi(pci, PCIE_ARCACHE_TRC_REG, ARCACHE_DEFAULT_VALUE); + dw_pcie_writel_dbi(pci, PCIE_AWCACHE_TRC_REG, AWCACHE_DEFAULT_VALUE); + + /* Set the PCIe master AxDomain attributes */ + reg = dw_pcie_readl_dbi(pci, PCIE_ARUSER_REG); + reg &= ~(AX_USER_DOMAIN_MASK << AX_USER_DOMAIN_SHIFT); + reg |= DOMAIN_OUTER_SHAREABLE << AX_USER_DOMAIN_SHIFT; + dw_pcie_writel_dbi(pci, PCIE_ARUSER_REG, reg); + + reg = dw_pcie_readl_dbi(pci, PCIE_AWUSER_REG); + reg &= ~(AX_USER_DOMAIN_MASK << AX_USER_DOMAIN_SHIFT); + reg |= DOMAIN_OUTER_SHAREABLE << AX_USER_DOMAIN_SHIFT; + dw_pcie_writel_dbi(pci, PCIE_AWUSER_REG, reg); + + /* Enable INT A-D interrupts */ + reg = dw_pcie_readl_dbi(pci, PCIE_GLOBAL_INT_MASK1_REG); + reg |= PCIE_INT_A_ASSERT_MASK | PCIE_INT_B_ASSERT_MASK | + PCIE_INT_C_ASSERT_MASK | PCIE_INT_D_ASSERT_MASK; + dw_pcie_writel_dbi(pci, PCIE_GLOBAL_INT_MASK1_REG, reg); + + return 0; +} + +static irqreturn_t armada8k_pcie_irq_handler(int irq, void *arg) +{ + struct armada8k_pcie *pcie = arg; + struct dw_pcie *pci = pcie->pci; + u32 val; + + /* + * Interrupts are directly handled by the device driver of the + * PCI device. However, they are also latched into the PCIe + * controller, so we simply discard them. + */ + val = dw_pcie_readl_dbi(pci, PCIE_GLOBAL_INT_CAUSE1_REG); + dw_pcie_writel_dbi(pci, PCIE_GLOBAL_INT_CAUSE1_REG, val); + + return IRQ_HANDLED; +} + +static const struct dw_pcie_host_ops armada8k_pcie_host_ops = { + .host_init = armada8k_pcie_host_init, +}; + +static int armada8k_add_pcie_port(struct armada8k_pcie *pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = &pdev->dev; + int ret; + + pp->ops = &armada8k_pcie_host_ops; + + pp->irq = platform_get_irq(pdev, 0); + if (pp->irq < 0) + return pp->irq; + + ret = devm_request_irq(dev, pp->irq, armada8k_pcie_irq_handler, + IRQF_SHARED, "armada8k-pcie", pcie); + if (ret) { + dev_err(dev, "failed to request irq %d\n", pp->irq); + return ret; + } + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "failed to initialize host: %d\n", ret); + return ret; + } + + return 0; +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .link_up = armada8k_pcie_link_up, + .start_link = armada8k_pcie_start_link, +}; + +static int armada8k_pcie_probe(struct platform_device *pdev) +{ + struct dw_pcie *pci; + struct armada8k_pcie *pcie; + struct device *dev = &pdev->dev; + struct resource *base; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pci->dev = dev; + pci->ops = &dw_pcie_ops; + + pcie->pci = pci; + + pcie->clk = devm_clk_get(dev, NULL); + if (IS_ERR(pcie->clk)) + return PTR_ERR(pcie->clk); + + ret = clk_prepare_enable(pcie->clk); + if (ret) + return ret; + + pcie->clk_reg = devm_clk_get(dev, "reg"); + if (pcie->clk_reg == ERR_PTR(-EPROBE_DEFER)) { + ret = -EPROBE_DEFER; + goto fail; + } + if (!IS_ERR(pcie->clk_reg)) { + ret = clk_prepare_enable(pcie->clk_reg); + if (ret) + goto fail_clkreg; + } + + /* Get the dw-pcie unit configuration/control registers base. */ + base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ctrl"); + pci->dbi_base = devm_pci_remap_cfg_resource(dev, base); + if (IS_ERR(pci->dbi_base)) { + ret = PTR_ERR(pci->dbi_base); + goto fail_clkreg; + } + + ret = armada8k_pcie_setup_phys(pcie); + if (ret) + goto fail_clkreg; + + platform_set_drvdata(pdev, pcie); + + ret = armada8k_add_pcie_port(pcie, pdev); + if (ret) + goto disable_phy; + + return 0; + +disable_phy: + armada8k_pcie_disable_phys(pcie); +fail_clkreg: + clk_disable_unprepare(pcie->clk_reg); +fail: + clk_disable_unprepare(pcie->clk); + + return ret; +} + +static const struct of_device_id armada8k_pcie_of_match[] = { + { .compatible = "marvell,armada8k-pcie", }, + {}, +}; + +static struct platform_driver armada8k_pcie_driver = { + .probe = armada8k_pcie_probe, + .driver = { + .name = "armada8k-pcie", + .of_match_table = armada8k_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver(armada8k_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c new file mode 100644 index 000000000..98102079e --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-artpec6.c @@ -0,0 +1,500 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Axis ARTPEC-6 SoC + * + * Author: Niklas Cassel <niklas.cassel@axis.com> + * + * Based on work done by Phil Edworthy <phil@edworthys.org> + */ + +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of_device.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/signal.h> +#include <linux/types.h> +#include <linux/interrupt.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> + +#include "pcie-designware.h" + +#define to_artpec6_pcie(x) dev_get_drvdata((x)->dev) + +enum artpec_pcie_variants { + ARTPEC6, + ARTPEC7, +}; + +struct artpec6_pcie { + struct dw_pcie *pci; + struct regmap *regmap; /* DT axis,syscon-pcie */ + void __iomem *phy_base; /* DT phy */ + enum artpec_pcie_variants variant; + enum dw_pcie_device_mode mode; +}; + +struct artpec_pcie_of_data { + enum artpec_pcie_variants variant; + enum dw_pcie_device_mode mode; +}; + +static const struct of_device_id artpec6_pcie_of_match[]; + +/* ARTPEC-6 specific registers */ +#define PCIECFG 0x18 +#define PCIECFG_DBG_OEN BIT(24) +#define PCIECFG_CORE_RESET_REQ BIT(21) +#define PCIECFG_LTSSM_ENABLE BIT(20) +#define PCIECFG_DEVICE_TYPE_MASK GENMASK(19, 16) +#define PCIECFG_CLKREQ_B BIT(11) +#define PCIECFG_REFCLK_ENABLE BIT(10) +#define PCIECFG_PLL_ENABLE BIT(9) +#define PCIECFG_PCLK_ENABLE BIT(8) +#define PCIECFG_RISRCREN BIT(4) +#define PCIECFG_MODE_TX_DRV_EN BIT(3) +#define PCIECFG_CISRREN BIT(2) +#define PCIECFG_MACRO_ENABLE BIT(0) +/* ARTPEC-7 specific fields */ +#define PCIECFG_REFCLKSEL BIT(23) +#define PCIECFG_NOC_RESET BIT(3) + +#define PCIESTAT 0x1c +/* ARTPEC-7 specific fields */ +#define PCIESTAT_EXTREFCLK BIT(3) + +#define NOCCFG 0x40 +#define NOCCFG_ENABLE_CLK_PCIE BIT(4) +#define NOCCFG_POWER_PCIE_IDLEACK BIT(3) +#define NOCCFG_POWER_PCIE_IDLE BIT(2) +#define NOCCFG_POWER_PCIE_IDLEREQ BIT(1) + +#define PHY_STATUS 0x118 +#define PHY_COSPLLLOCK BIT(0) + +#define PHY_TX_ASIC_OUT 0x4040 +#define PHY_TX_ASIC_OUT_TX_ACK BIT(0) + +#define PHY_RX_ASIC_OUT 0x405c +#define PHY_RX_ASIC_OUT_ACK BIT(0) + +static u32 artpec6_pcie_readl(struct artpec6_pcie *artpec6_pcie, u32 offset) +{ + u32 val; + + regmap_read(artpec6_pcie->regmap, offset, &val); + return val; +} + +static void artpec6_pcie_writel(struct artpec6_pcie *artpec6_pcie, u32 offset, u32 val) +{ + regmap_write(artpec6_pcie->regmap, offset, val); +} + +static u64 artpec6_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 pci_addr) +{ + struct artpec6_pcie *artpec6_pcie = to_artpec6_pcie(pci); + struct dw_pcie_rp *pp = &pci->pp; + struct dw_pcie_ep *ep = &pci->ep; + + switch (artpec6_pcie->mode) { + case DW_PCIE_RC_TYPE: + return pci_addr - pp->cfg0_base; + case DW_PCIE_EP_TYPE: + return pci_addr - ep->phys_base; + default: + dev_err(pci->dev, "UNKNOWN device type\n"); + } + return pci_addr; +} + +static int artpec6_pcie_establish_link(struct dw_pcie *pci) +{ + struct artpec6_pcie *artpec6_pcie = to_artpec6_pcie(pci); + u32 val; + + val = artpec6_pcie_readl(artpec6_pcie, PCIECFG); + val |= PCIECFG_LTSSM_ENABLE; + artpec6_pcie_writel(artpec6_pcie, PCIECFG, val); + + return 0; +} + +static void artpec6_pcie_stop_link(struct dw_pcie *pci) +{ + struct artpec6_pcie *artpec6_pcie = to_artpec6_pcie(pci); + u32 val; + + val = artpec6_pcie_readl(artpec6_pcie, PCIECFG); + val &= ~PCIECFG_LTSSM_ENABLE; + artpec6_pcie_writel(artpec6_pcie, PCIECFG, val); +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .cpu_addr_fixup = artpec6_pcie_cpu_addr_fixup, + .start_link = artpec6_pcie_establish_link, + .stop_link = artpec6_pcie_stop_link, +}; + +static void artpec6_pcie_wait_for_phy_a6(struct artpec6_pcie *artpec6_pcie) +{ + struct dw_pcie *pci = artpec6_pcie->pci; + struct device *dev = pci->dev; + u32 val; + unsigned int retries; + + retries = 50; + do { + usleep_range(1000, 2000); + val = artpec6_pcie_readl(artpec6_pcie, NOCCFG); + retries--; + } while (retries && + (val & (NOCCFG_POWER_PCIE_IDLEACK | NOCCFG_POWER_PCIE_IDLE))); + if (!retries) + dev_err(dev, "PCIe clock manager did not leave idle state\n"); + + retries = 50; + do { + usleep_range(1000, 2000); + val = readl(artpec6_pcie->phy_base + PHY_STATUS); + retries--; + } while (retries && !(val & PHY_COSPLLLOCK)); + if (!retries) + dev_err(dev, "PHY PLL did not lock\n"); +} + +static void artpec6_pcie_wait_for_phy_a7(struct artpec6_pcie *artpec6_pcie) +{ + struct dw_pcie *pci = artpec6_pcie->pci; + struct device *dev = pci->dev; + u32 val; + u16 phy_status_tx, phy_status_rx; + unsigned int retries; + + retries = 50; + do { + usleep_range(1000, 2000); + val = artpec6_pcie_readl(artpec6_pcie, NOCCFG); + retries--; + } while (retries && + (val & (NOCCFG_POWER_PCIE_IDLEACK | NOCCFG_POWER_PCIE_IDLE))); + if (!retries) + dev_err(dev, "PCIe clock manager did not leave idle state\n"); + + retries = 50; + do { + usleep_range(1000, 2000); + phy_status_tx = readw(artpec6_pcie->phy_base + PHY_TX_ASIC_OUT); + phy_status_rx = readw(artpec6_pcie->phy_base + PHY_RX_ASIC_OUT); + retries--; + } while (retries && ((phy_status_tx & PHY_TX_ASIC_OUT_TX_ACK) || + (phy_status_rx & PHY_RX_ASIC_OUT_ACK))); + if (!retries) + dev_err(dev, "PHY did not enter Pn state\n"); +} + +static void artpec6_pcie_wait_for_phy(struct artpec6_pcie *artpec6_pcie) +{ + switch (artpec6_pcie->variant) { + case ARTPEC6: + artpec6_pcie_wait_for_phy_a6(artpec6_pcie); + break; + case ARTPEC7: + artpec6_pcie_wait_for_phy_a7(artpec6_pcie); + break; + } +} + +static void artpec6_pcie_init_phy_a6(struct artpec6_pcie *artpec6_pcie) +{ + u32 val; + + val = artpec6_pcie_readl(artpec6_pcie, PCIECFG); + val |= PCIECFG_RISRCREN | /* Receiver term. 50 Ohm */ + PCIECFG_MODE_TX_DRV_EN | + PCIECFG_CISRREN | /* Reference clock term. 100 Ohm */ + PCIECFG_MACRO_ENABLE; + val |= PCIECFG_REFCLK_ENABLE; + val &= ~PCIECFG_DBG_OEN; + val &= ~PCIECFG_CLKREQ_B; + artpec6_pcie_writel(artpec6_pcie, PCIECFG, val); + usleep_range(5000, 6000); + + val = artpec6_pcie_readl(artpec6_pcie, NOCCFG); + val |= NOCCFG_ENABLE_CLK_PCIE; + artpec6_pcie_writel(artpec6_pcie, NOCCFG, val); + usleep_range(20, 30); + + val = artpec6_pcie_readl(artpec6_pcie, PCIECFG); + val |= PCIECFG_PCLK_ENABLE | PCIECFG_PLL_ENABLE; + artpec6_pcie_writel(artpec6_pcie, PCIECFG, val); + usleep_range(6000, 7000); + + val = artpec6_pcie_readl(artpec6_pcie, NOCCFG); + val &= ~NOCCFG_POWER_PCIE_IDLEREQ; + artpec6_pcie_writel(artpec6_pcie, NOCCFG, val); +} + +static void artpec6_pcie_init_phy_a7(struct artpec6_pcie *artpec6_pcie) +{ + struct dw_pcie *pci = artpec6_pcie->pci; + u32 val; + bool extrefclk; + + /* Check if external reference clock is connected */ + val = artpec6_pcie_readl(artpec6_pcie, PCIESTAT); + extrefclk = !!(val & PCIESTAT_EXTREFCLK); + dev_dbg(pci->dev, "Using reference clock: %s\n", + extrefclk ? "external" : "internal"); + + val = artpec6_pcie_readl(artpec6_pcie, PCIECFG); + val |= PCIECFG_RISRCREN | /* Receiver term. 50 Ohm */ + PCIECFG_PCLK_ENABLE; + if (extrefclk) + val |= PCIECFG_REFCLKSEL; + else + val &= ~PCIECFG_REFCLKSEL; + artpec6_pcie_writel(artpec6_pcie, PCIECFG, val); + usleep_range(10, 20); + + val = artpec6_pcie_readl(artpec6_pcie, NOCCFG); + val |= NOCCFG_ENABLE_CLK_PCIE; + artpec6_pcie_writel(artpec6_pcie, NOCCFG, val); + usleep_range(20, 30); + + val = artpec6_pcie_readl(artpec6_pcie, NOCCFG); + val &= ~NOCCFG_POWER_PCIE_IDLEREQ; + artpec6_pcie_writel(artpec6_pcie, NOCCFG, val); +} + +static void artpec6_pcie_init_phy(struct artpec6_pcie *artpec6_pcie) +{ + switch (artpec6_pcie->variant) { + case ARTPEC6: + artpec6_pcie_init_phy_a6(artpec6_pcie); + break; + case ARTPEC7: + artpec6_pcie_init_phy_a7(artpec6_pcie); + break; + } +} + +static void artpec6_pcie_assert_core_reset(struct artpec6_pcie *artpec6_pcie) +{ + u32 val; + + val = artpec6_pcie_readl(artpec6_pcie, PCIECFG); + switch (artpec6_pcie->variant) { + case ARTPEC6: + val |= PCIECFG_CORE_RESET_REQ; + break; + case ARTPEC7: + val &= ~PCIECFG_NOC_RESET; + break; + } + artpec6_pcie_writel(artpec6_pcie, PCIECFG, val); +} + +static void artpec6_pcie_deassert_core_reset(struct artpec6_pcie *artpec6_pcie) +{ + u32 val; + + val = artpec6_pcie_readl(artpec6_pcie, PCIECFG); + switch (artpec6_pcie->variant) { + case ARTPEC6: + val &= ~PCIECFG_CORE_RESET_REQ; + break; + case ARTPEC7: + val |= PCIECFG_NOC_RESET; + break; + } + artpec6_pcie_writel(artpec6_pcie, PCIECFG, val); + usleep_range(100, 200); +} + +static int artpec6_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct artpec6_pcie *artpec6_pcie = to_artpec6_pcie(pci); + + if (artpec6_pcie->variant == ARTPEC7) { + pci->n_fts[0] = 180; + pci->n_fts[1] = 180; + } + artpec6_pcie_assert_core_reset(artpec6_pcie); + artpec6_pcie_init_phy(artpec6_pcie); + artpec6_pcie_deassert_core_reset(artpec6_pcie); + artpec6_pcie_wait_for_phy(artpec6_pcie); + + return 0; +} + +static const struct dw_pcie_host_ops artpec6_pcie_host_ops = { + .host_init = artpec6_pcie_host_init, +}; + +static void artpec6_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct artpec6_pcie *artpec6_pcie = to_artpec6_pcie(pci); + enum pci_barno bar; + + artpec6_pcie_assert_core_reset(artpec6_pcie); + artpec6_pcie_init_phy(artpec6_pcie); + artpec6_pcie_deassert_core_reset(artpec6_pcie); + artpec6_pcie_wait_for_phy(artpec6_pcie); + + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) + dw_pcie_ep_reset_bar(pci, bar); +} + +static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + enum pci_epc_irq_type type, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + dev_err(pci->dev, "EP cannot trigger legacy IRQs\n"); + return -EINVAL; + case PCI_EPC_IRQ_MSI: + return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num); + default: + dev_err(pci->dev, "UNKNOWN IRQ type\n"); + } + + return 0; +} + +static const struct dw_pcie_ep_ops pcie_ep_ops = { + .ep_init = artpec6_pcie_ep_init, + .raise_irq = artpec6_pcie_raise_irq, +}; + +static int artpec6_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci; + struct artpec6_pcie *artpec6_pcie; + int ret; + const struct artpec_pcie_of_data *data; + enum artpec_pcie_variants variant; + enum dw_pcie_device_mode mode; + u32 val; + + data = of_device_get_match_data(dev); + if (!data) + return -EINVAL; + + variant = (enum artpec_pcie_variants)data->variant; + mode = (enum dw_pcie_device_mode)data->mode; + + artpec6_pcie = devm_kzalloc(dev, sizeof(*artpec6_pcie), GFP_KERNEL); + if (!artpec6_pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pci->dev = dev; + pci->ops = &dw_pcie_ops; + + artpec6_pcie->pci = pci; + artpec6_pcie->variant = variant; + artpec6_pcie->mode = mode; + + artpec6_pcie->phy_base = + devm_platform_ioremap_resource_byname(pdev, "phy"); + if (IS_ERR(artpec6_pcie->phy_base)) + return PTR_ERR(artpec6_pcie->phy_base); + + artpec6_pcie->regmap = + syscon_regmap_lookup_by_phandle(dev->of_node, + "axis,syscon-pcie"); + if (IS_ERR(artpec6_pcie->regmap)) + return PTR_ERR(artpec6_pcie->regmap); + + platform_set_drvdata(pdev, artpec6_pcie); + + switch (artpec6_pcie->mode) { + case DW_PCIE_RC_TYPE: + if (!IS_ENABLED(CONFIG_PCIE_ARTPEC6_HOST)) + return -ENODEV; + + pci->pp.ops = &artpec6_pcie_host_ops; + + ret = dw_pcie_host_init(&pci->pp); + if (ret < 0) + return ret; + break; + case DW_PCIE_EP_TYPE: + if (!IS_ENABLED(CONFIG_PCIE_ARTPEC6_EP)) + return -ENODEV; + + val = artpec6_pcie_readl(artpec6_pcie, PCIECFG); + val &= ~PCIECFG_DEVICE_TYPE_MASK; + artpec6_pcie_writel(artpec6_pcie, PCIECFG, val); + + pci->ep.ops = &pcie_ep_ops; + + return dw_pcie_ep_init(&pci->ep); + default: + dev_err(dev, "INVALID device type %d\n", artpec6_pcie->mode); + } + + return 0; +} + +static const struct artpec_pcie_of_data artpec6_pcie_rc_of_data = { + .variant = ARTPEC6, + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct artpec_pcie_of_data artpec6_pcie_ep_of_data = { + .variant = ARTPEC6, + .mode = DW_PCIE_EP_TYPE, +}; + +static const struct artpec_pcie_of_data artpec7_pcie_rc_of_data = { + .variant = ARTPEC7, + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct artpec_pcie_of_data artpec7_pcie_ep_of_data = { + .variant = ARTPEC7, + .mode = DW_PCIE_EP_TYPE, +}; + +static const struct of_device_id artpec6_pcie_of_match[] = { + { + .compatible = "axis,artpec6-pcie", + .data = &artpec6_pcie_rc_of_data, + }, + { + .compatible = "axis,artpec6-pcie-ep", + .data = &artpec6_pcie_ep_of_data, + }, + { + .compatible = "axis,artpec7-pcie", + .data = &artpec7_pcie_rc_of_data, + }, + { + .compatible = "axis,artpec7-pcie-ep", + .data = &artpec7_pcie_ep_of_data, + }, + {}, +}; + +static struct platform_driver artpec6_pcie_driver = { + .probe = artpec6_pcie_probe, + .driver = { + .name = "artpec6-pcie", + .of_match_table = artpec6_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver(artpec6_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c new file mode 100644 index 000000000..59c164b5c --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -0,0 +1,812 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Synopsys DesignWare PCIe Endpoint controller driver + * + * Copyright (C) 2017 Texas Instruments + * Author: Kishon Vijay Abraham I <kishon@ti.com> + */ + +#include <linux/of.h> +#include <linux/platform_device.h> + +#include "pcie-designware.h" +#include <linux/pci-epc.h> +#include <linux/pci-epf.h> + +#include "../../pci.h" + +void dw_pcie_ep_linkup(struct dw_pcie_ep *ep) +{ + struct pci_epc *epc = ep->epc; + + pci_epc_linkup(epc); +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_linkup); + +void dw_pcie_ep_init_notify(struct dw_pcie_ep *ep) +{ + struct pci_epc *epc = ep->epc; + + pci_epc_init_notify(epc); +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_init_notify); + +struct dw_pcie_ep_func * +dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no) +{ + struct dw_pcie_ep_func *ep_func; + + list_for_each_entry(ep_func, &ep->func_list, list) { + if (ep_func->func_no == func_no) + return ep_func; + } + + return NULL; +} + +static unsigned int dw_pcie_ep_func_select(struct dw_pcie_ep *ep, u8 func_no) +{ + unsigned int func_offset = 0; + + if (ep->ops->func_conf_select) + func_offset = ep->ops->func_conf_select(ep, func_no); + + return func_offset; +} + +static void __dw_pcie_ep_reset_bar(struct dw_pcie *pci, u8 func_no, + enum pci_barno bar, int flags) +{ + u32 reg; + unsigned int func_offset = 0; + struct dw_pcie_ep *ep = &pci->ep; + + func_offset = dw_pcie_ep_func_select(ep, func_no); + + reg = func_offset + PCI_BASE_ADDRESS_0 + (4 * bar); + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writel_dbi2(pci, reg, 0x0); + dw_pcie_writel_dbi(pci, reg, 0x0); + if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) { + dw_pcie_writel_dbi2(pci, reg + 4, 0x0); + dw_pcie_writel_dbi(pci, reg + 4, 0x0); + } + dw_pcie_dbi_ro_wr_dis(pci); +} + +void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar) +{ + u8 func_no, funcs; + + funcs = pci->ep.epc->max_functions; + + for (func_no = 0; func_no < funcs; func_no++) + __dw_pcie_ep_reset_bar(pci, func_no, bar, 0); +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_reset_bar); + +static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie_ep *ep, u8 func_no, + u8 cap_ptr, u8 cap) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + unsigned int func_offset = 0; + u8 cap_id, next_cap_ptr; + u16 reg; + + if (!cap_ptr) + return 0; + + func_offset = dw_pcie_ep_func_select(ep, func_no); + + reg = dw_pcie_readw_dbi(pci, func_offset + cap_ptr); + cap_id = (reg & 0x00ff); + + if (cap_id > PCI_CAP_ID_MAX) + return 0; + + if (cap_id == cap) + return cap_ptr; + + next_cap_ptr = (reg & 0xff00) >> 8; + return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap); +} + +static u8 dw_pcie_ep_find_capability(struct dw_pcie_ep *ep, u8 func_no, u8 cap) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + unsigned int func_offset = 0; + u8 next_cap_ptr; + u16 reg; + + func_offset = dw_pcie_ep_func_select(ep, func_no); + + reg = dw_pcie_readw_dbi(pci, func_offset + PCI_CAPABILITY_LIST); + next_cap_ptr = (reg & 0x00ff); + + return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap); +} + +static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + struct pci_epf_header *hdr) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + unsigned int func_offset = 0; + + func_offset = dw_pcie_ep_func_select(ep, func_no); + + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writew_dbi(pci, func_offset + PCI_VENDOR_ID, hdr->vendorid); + dw_pcie_writew_dbi(pci, func_offset + PCI_DEVICE_ID, hdr->deviceid); + dw_pcie_writeb_dbi(pci, func_offset + PCI_REVISION_ID, hdr->revid); + dw_pcie_writeb_dbi(pci, func_offset + PCI_CLASS_PROG, hdr->progif_code); + dw_pcie_writew_dbi(pci, func_offset + PCI_CLASS_DEVICE, + hdr->subclass_code | hdr->baseclass_code << 8); + dw_pcie_writeb_dbi(pci, func_offset + PCI_CACHE_LINE_SIZE, + hdr->cache_line_size); + dw_pcie_writew_dbi(pci, func_offset + PCI_SUBSYSTEM_VENDOR_ID, + hdr->subsys_vendor_id); + dw_pcie_writew_dbi(pci, func_offset + PCI_SUBSYSTEM_ID, hdr->subsys_id); + dw_pcie_writeb_dbi(pci, func_offset + PCI_INTERRUPT_PIN, + hdr->interrupt_pin); + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no, int type, + dma_addr_t cpu_addr, enum pci_barno bar) +{ + int ret; + u32 free_win; + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + if (!ep->bar_to_atu[bar]) + free_win = find_first_zero_bit(ep->ib_window_map, pci->num_ib_windows); + else + free_win = ep->bar_to_atu[bar]; + + if (free_win >= pci->num_ib_windows) { + dev_err(pci->dev, "No free inbound window\n"); + return -EINVAL; + } + + ret = dw_pcie_prog_inbound_atu(pci, func_no, free_win, type, + cpu_addr, bar); + if (ret < 0) { + dev_err(pci->dev, "Failed to program IB window\n"); + return ret; + } + + ep->bar_to_atu[bar] = free_win; + set_bit(free_win, ep->ib_window_map); + + return 0; +} + +static int dw_pcie_ep_outbound_atu(struct dw_pcie_ep *ep, u8 func_no, + phys_addr_t phys_addr, + u64 pci_addr, size_t size) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 free_win; + int ret; + + free_win = find_first_zero_bit(ep->ob_window_map, pci->num_ob_windows); + if (free_win >= pci->num_ob_windows) { + dev_err(pci->dev, "No free outbound window\n"); + return -EINVAL; + } + + ret = dw_pcie_prog_ep_outbound_atu(pci, func_no, free_win, PCIE_ATU_TYPE_MEM, + phys_addr, pci_addr, size); + if (ret) + return ret; + + set_bit(free_win, ep->ob_window_map); + ep->outbound_addr[free_win] = phys_addr; + + return 0; +} + +static void dw_pcie_ep_clear_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + struct pci_epf_bar *epf_bar) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar = epf_bar->barno; + u32 atu_index = ep->bar_to_atu[bar]; + + __dw_pcie_ep_reset_bar(pci, func_no, bar, epf_bar->flags); + + dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_IB, atu_index); + clear_bit(atu_index, ep->ib_window_map); + ep->epf_bar[bar] = NULL; + ep->bar_to_atu[bar] = 0; +} + +static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + struct pci_epf_bar *epf_bar) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar = epf_bar->barno; + size_t size = epf_bar->size; + int flags = epf_bar->flags; + unsigned int func_offset = 0; + int ret, type; + u32 reg; + + func_offset = dw_pcie_ep_func_select(ep, func_no); + + reg = PCI_BASE_ADDRESS_0 + (4 * bar) + func_offset; + + if (!(flags & PCI_BASE_ADDRESS_SPACE)) + type = PCIE_ATU_TYPE_MEM; + else + type = PCIE_ATU_TYPE_IO; + + ret = dw_pcie_ep_inbound_atu(ep, func_no, type, epf_bar->phys_addr, bar); + if (ret) + return ret; + + if (ep->epf_bar[bar]) + return 0; + + dw_pcie_dbi_ro_wr_en(pci); + + dw_pcie_writel_dbi2(pci, reg, lower_32_bits(size - 1)); + dw_pcie_writel_dbi(pci, reg, flags); + + if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) { + dw_pcie_writel_dbi2(pci, reg + 4, upper_32_bits(size - 1)); + dw_pcie_writel_dbi(pci, reg + 4, 0); + } + + ep->epf_bar[bar] = epf_bar; + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static int dw_pcie_find_index(struct dw_pcie_ep *ep, phys_addr_t addr, + u32 *atu_index) +{ + u32 index; + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + for (index = 0; index < pci->num_ob_windows; index++) { + if (ep->outbound_addr[index] != addr) + continue; + *atu_index = index; + return 0; + } + + return -EINVAL; +} + +static void dw_pcie_ep_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + phys_addr_t addr) +{ + int ret; + u32 atu_index; + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + ret = dw_pcie_find_index(ep, addr, &atu_index); + if (ret < 0) + return; + + dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_OB, atu_index); + clear_bit(atu_index, ep->ob_window_map); +} + +static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + phys_addr_t addr, u64 pci_addr, size_t size) +{ + int ret; + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + ret = dw_pcie_ep_outbound_atu(ep, func_no, addr, pci_addr, size); + if (ret) { + dev_err(pci->dev, "Failed to enable address\n"); + return ret; + } + + return 0; +} + +static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 val, reg; + unsigned int func_offset = 0; + struct dw_pcie_ep_func *ep_func; + + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msi_cap) + return -EINVAL; + + func_offset = dw_pcie_ep_func_select(ep, func_no); + + reg = ep_func->msi_cap + func_offset + PCI_MSI_FLAGS; + val = dw_pcie_readw_dbi(pci, reg); + if (!(val & PCI_MSI_FLAGS_ENABLE)) + return -EINVAL; + + val = (val & PCI_MSI_FLAGS_QSIZE) >> 4; + + return val; +} + +static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + u8 interrupts) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 val, reg; + unsigned int func_offset = 0; + struct dw_pcie_ep_func *ep_func; + + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msi_cap) + return -EINVAL; + + func_offset = dw_pcie_ep_func_select(ep, func_no); + + reg = ep_func->msi_cap + func_offset + PCI_MSI_FLAGS; + val = dw_pcie_readw_dbi(pci, reg); + val &= ~PCI_MSI_FLAGS_QMASK; + val |= (interrupts << 1) & PCI_MSI_FLAGS_QMASK; + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writew_dbi(pci, reg, val); + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 val, reg; + unsigned int func_offset = 0; + struct dw_pcie_ep_func *ep_func; + + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msix_cap) + return -EINVAL; + + func_offset = dw_pcie_ep_func_select(ep, func_no); + + reg = ep_func->msix_cap + func_offset + PCI_MSIX_FLAGS; + val = dw_pcie_readw_dbi(pci, reg); + if (!(val & PCI_MSIX_FLAGS_ENABLE)) + return -EINVAL; + + val &= PCI_MSIX_FLAGS_QSIZE; + + return val; +} + +static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + u16 interrupts, enum pci_barno bir, u32 offset) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 val, reg; + unsigned int func_offset = 0; + struct dw_pcie_ep_func *ep_func; + + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msix_cap) + return -EINVAL; + + dw_pcie_dbi_ro_wr_en(pci); + + func_offset = dw_pcie_ep_func_select(ep, func_no); + + reg = ep_func->msix_cap + func_offset + PCI_MSIX_FLAGS; + val = dw_pcie_readw_dbi(pci, reg); + val &= ~PCI_MSIX_FLAGS_QSIZE; + val |= interrupts; + dw_pcie_writew_dbi(pci, reg, val); + + reg = ep_func->msix_cap + func_offset + PCI_MSIX_TABLE; + val = offset | bir; + dw_pcie_writel_dbi(pci, reg, val); + + reg = ep_func->msix_cap + func_offset + PCI_MSIX_PBA; + val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; + dw_pcie_writel_dbi(pci, reg, val); + + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static int dw_pcie_ep_raise_irq(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + enum pci_epc_irq_type type, u16 interrupt_num) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + + if (!ep->ops->raise_irq) + return -EINVAL; + + return ep->ops->raise_irq(ep, func_no, type, interrupt_num); +} + +static void dw_pcie_ep_stop(struct pci_epc *epc) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + dw_pcie_stop_link(pci); +} + +static int dw_pcie_ep_start(struct pci_epc *epc) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + return dw_pcie_start_link(pci); +} + +static const struct pci_epc_features* +dw_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + + if (!ep->ops->get_features) + return NULL; + + return ep->ops->get_features(ep); +} + +static const struct pci_epc_ops epc_ops = { + .write_header = dw_pcie_ep_write_header, + .set_bar = dw_pcie_ep_set_bar, + .clear_bar = dw_pcie_ep_clear_bar, + .map_addr = dw_pcie_ep_map_addr, + .unmap_addr = dw_pcie_ep_unmap_addr, + .set_msi = dw_pcie_ep_set_msi, + .get_msi = dw_pcie_ep_get_msi, + .set_msix = dw_pcie_ep_set_msix, + .get_msix = dw_pcie_ep_get_msix, + .raise_irq = dw_pcie_ep_raise_irq, + .start = dw_pcie_ep_start, + .stop = dw_pcie_ep_stop, + .get_features = dw_pcie_ep_get_features, +}; + +int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct device *dev = pci->dev; + + dev_err(dev, "EP cannot trigger legacy IRQs\n"); + + return -EINVAL; +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_legacy_irq); + +int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, + u8 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct dw_pcie_ep_func *ep_func; + struct pci_epc *epc = ep->epc; + unsigned int aligned_offset; + unsigned int func_offset = 0; + u16 msg_ctrl, msg_data; + u32 msg_addr_lower, msg_addr_upper, reg; + u64 msg_addr; + bool has_upper; + int ret; + + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msi_cap) + return -EINVAL; + + func_offset = dw_pcie_ep_func_select(ep, func_no); + + /* Raise MSI per the PCI Local Bus Specification Revision 3.0, 6.8.1. */ + reg = ep_func->msi_cap + func_offset + PCI_MSI_FLAGS; + msg_ctrl = dw_pcie_readw_dbi(pci, reg); + has_upper = !!(msg_ctrl & PCI_MSI_FLAGS_64BIT); + reg = ep_func->msi_cap + func_offset + PCI_MSI_ADDRESS_LO; + msg_addr_lower = dw_pcie_readl_dbi(pci, reg); + if (has_upper) { + reg = ep_func->msi_cap + func_offset + PCI_MSI_ADDRESS_HI; + msg_addr_upper = dw_pcie_readl_dbi(pci, reg); + reg = ep_func->msi_cap + func_offset + PCI_MSI_DATA_64; + msg_data = dw_pcie_readw_dbi(pci, reg); + } else { + msg_addr_upper = 0; + reg = ep_func->msi_cap + func_offset + PCI_MSI_DATA_32; + msg_data = dw_pcie_readw_dbi(pci, reg); + } + aligned_offset = msg_addr_lower & (epc->mem->window.page_size - 1); + msg_addr = ((u64)msg_addr_upper) << 32 | + (msg_addr_lower & ~aligned_offset); + ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, + epc->mem->window.page_size); + if (ret) + return ret; + + writel(msg_data | (interrupt_num - 1), ep->msi_mem + aligned_offset); + + dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys); + + return 0; +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_msi_irq); + +int dw_pcie_ep_raise_msix_irq_doorbell(struct dw_pcie_ep *ep, u8 func_no, + u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct dw_pcie_ep_func *ep_func; + u32 msg_data; + + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msix_cap) + return -EINVAL; + + msg_data = (func_no << PCIE_MSIX_DOORBELL_PF_SHIFT) | + (interrupt_num - 1); + + dw_pcie_writel_dbi(pci, PCIE_MSIX_DOORBELL, msg_data); + + return 0; +} + +int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, + u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct dw_pcie_ep_func *ep_func; + struct pci_epf_msix_tbl *msix_tbl; + struct pci_epc *epc = ep->epc; + unsigned int func_offset = 0; + u32 reg, msg_data, vec_ctrl; + unsigned int aligned_offset; + u32 tbl_offset; + u64 msg_addr; + int ret; + u8 bir; + + ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + if (!ep_func || !ep_func->msix_cap) + return -EINVAL; + + func_offset = dw_pcie_ep_func_select(ep, func_no); + + reg = ep_func->msix_cap + func_offset + PCI_MSIX_TABLE; + tbl_offset = dw_pcie_readl_dbi(pci, reg); + bir = (tbl_offset & PCI_MSIX_TABLE_BIR); + tbl_offset &= PCI_MSIX_TABLE_OFFSET; + + msix_tbl = ep->epf_bar[bir]->addr + tbl_offset; + msg_addr = msix_tbl[(interrupt_num - 1)].msg_addr; + msg_data = msix_tbl[(interrupt_num - 1)].msg_data; + vec_ctrl = msix_tbl[(interrupt_num - 1)].vector_ctrl; + + if (vec_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT) { + dev_dbg(pci->dev, "MSI-X entry ctrl set\n"); + return -EPERM; + } + + aligned_offset = msg_addr & (epc->mem->window.page_size - 1); + msg_addr &= ~aligned_offset; + ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, + epc->mem->window.page_size); + if (ret) + return ret; + + writel(msg_data, ep->msi_mem + aligned_offset); + + dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys); + + return 0; +} + +void dw_pcie_ep_exit(struct dw_pcie_ep *ep) +{ + struct pci_epc *epc = ep->epc; + + pci_epc_mem_free_addr(epc, ep->msi_mem_phys, ep->msi_mem, + epc->mem->window.page_size); + + pci_epc_mem_exit(epc); +} + +static unsigned int dw_pcie_ep_find_ext_capability(struct dw_pcie *pci, int cap) +{ + u32 header; + int pos = PCI_CFG_SPACE_SIZE; + + while (pos) { + header = dw_pcie_readl_dbi(pci, pos); + if (PCI_EXT_CAP_ID(header) == cap) + return pos; + + pos = PCI_EXT_CAP_NEXT(header); + if (!pos) + break; + } + + return 0; +} + +int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + unsigned int offset; + unsigned int nbars; + u8 hdr_type; + u32 reg; + int i; + + hdr_type = dw_pcie_readb_dbi(pci, PCI_HEADER_TYPE) & + PCI_HEADER_TYPE_MASK; + if (hdr_type != PCI_HEADER_TYPE_NORMAL) { + dev_err(pci->dev, + "PCIe controller is not set to EP mode (hdr_type:0x%x)!\n", + hdr_type); + return -EIO; + } + + offset = dw_pcie_ep_find_ext_capability(pci, PCI_EXT_CAP_ID_REBAR); + + dw_pcie_dbi_ro_wr_en(pci); + + if (offset) { + reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL); + nbars = (reg & PCI_REBAR_CTRL_NBAR_MASK) >> + PCI_REBAR_CTRL_NBAR_SHIFT; + + for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL) + dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, 0x0); + } + + dw_pcie_setup(pci); + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_init_complete); + +int dw_pcie_ep_init(struct dw_pcie_ep *ep) +{ + int ret; + void *addr; + u8 func_no; + struct resource *res; + struct pci_epc *epc; + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct device *dev = pci->dev; + struct platform_device *pdev = to_platform_device(dev); + struct device_node *np = dev->of_node; + const struct pci_epc_features *epc_features; + struct dw_pcie_ep_func *ep_func; + + INIT_LIST_HEAD(&ep->func_list); + + if (!pci->dbi_base) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); + pci->dbi_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + } + + if (!pci->dbi_base2) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi2"); + if (!res) { + pci->dbi_base2 = pci->dbi_base + SZ_4K; + } else { + pci->dbi_base2 = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pci->dbi_base2)) + return PTR_ERR(pci->dbi_base2); + } + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "addr_space"); + if (!res) + return -EINVAL; + + ep->phys_base = res->start; + ep->addr_size = resource_size(res); + + dw_pcie_version_detect(pci); + + dw_pcie_iatu_detect(pci); + + ep->ib_window_map = devm_bitmap_zalloc(dev, pci->num_ib_windows, + GFP_KERNEL); + if (!ep->ib_window_map) + return -ENOMEM; + + ep->ob_window_map = devm_bitmap_zalloc(dev, pci->num_ob_windows, + GFP_KERNEL); + if (!ep->ob_window_map) + return -ENOMEM; + + addr = devm_kcalloc(dev, pci->num_ob_windows, sizeof(phys_addr_t), + GFP_KERNEL); + if (!addr) + return -ENOMEM; + ep->outbound_addr = addr; + + if (pci->link_gen < 1) + pci->link_gen = of_pci_get_max_link_speed(np); + + epc = devm_pci_epc_create(dev, &epc_ops); + if (IS_ERR(epc)) { + dev_err(dev, "Failed to create epc device\n"); + return PTR_ERR(epc); + } + + ep->epc = epc; + epc_set_drvdata(epc, ep); + + ret = of_property_read_u8(np, "max-functions", &epc->max_functions); + if (ret < 0) + epc->max_functions = 1; + + for (func_no = 0; func_no < epc->max_functions; func_no++) { + ep_func = devm_kzalloc(dev, sizeof(*ep_func), GFP_KERNEL); + if (!ep_func) + return -ENOMEM; + + ep_func->func_no = func_no; + ep_func->msi_cap = dw_pcie_ep_find_capability(ep, func_no, + PCI_CAP_ID_MSI); + ep_func->msix_cap = dw_pcie_ep_find_capability(ep, func_no, + PCI_CAP_ID_MSIX); + + list_add_tail(&ep_func->list, &ep->func_list); + } + + if (ep->ops->ep_init) + ep->ops->ep_init(ep); + + ret = pci_epc_mem_init(epc, ep->phys_base, ep->addr_size, + ep->page_size); + if (ret < 0) { + dev_err(dev, "Failed to initialize address space\n"); + return ret; + } + + ep->msi_mem = pci_epc_mem_alloc_addr(epc, &ep->msi_mem_phys, + epc->mem->window.page_size); + if (!ep->msi_mem) { + ret = -ENOMEM; + dev_err(dev, "Failed to reserve memory for MSI/MSI-X\n"); + goto err_exit_epc_mem; + } + + if (ep->ops->get_features) { + epc_features = ep->ops->get_features(ep); + if (epc_features->core_init_notifier) + return 0; + } + + ret = dw_pcie_ep_init_complete(ep); + if (ret) + goto err_free_epc_mem; + + return 0; + +err_free_epc_mem: + pci_epc_mem_free_addr(epc, ep->msi_mem_phys, ep->msi_mem, + epc->mem->window.page_size); + +err_exit_epc_mem: + pci_epc_mem_exit(epc); + + return ret; +} +EXPORT_SYMBOL_GPL(dw_pcie_ep_init); diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c new file mode 100644 index 000000000..39f3b37d4 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -0,0 +1,771 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Synopsys DesignWare PCIe host controller driver + * + * Copyright (C) 2013 Samsung Electronics Co., Ltd. + * https://www.samsung.com + * + * Author: Jingoo Han <jg1.han@samsung.com> + */ + +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/pci_regs.h> +#include <linux/platform_device.h> + +#include "../../pci.h" +#include "pcie-designware.h" + +static struct pci_ops dw_pcie_ops; +static struct pci_ops dw_child_pcie_ops; + +static void dw_msi_ack_irq(struct irq_data *d) +{ + irq_chip_ack_parent(d); +} + +static void dw_msi_mask_irq(struct irq_data *d) +{ + pci_msi_mask_irq(d); + irq_chip_mask_parent(d); +} + +static void dw_msi_unmask_irq(struct irq_data *d) +{ + pci_msi_unmask_irq(d); + irq_chip_unmask_parent(d); +} + +static struct irq_chip dw_pcie_msi_irq_chip = { + .name = "PCI-MSI", + .irq_ack = dw_msi_ack_irq, + .irq_mask = dw_msi_mask_irq, + .irq_unmask = dw_msi_unmask_irq, +}; + +static struct msi_domain_info dw_pcie_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX | MSI_FLAG_MULTI_PCI_MSI), + .chip = &dw_pcie_msi_irq_chip, +}; + +/* MSI int handler */ +irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp) +{ + int i, pos; + unsigned long val; + u32 status, num_ctrls; + irqreturn_t ret = IRQ_NONE; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + + num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; + + for (i = 0; i < num_ctrls; i++) { + status = dw_pcie_readl_dbi(pci, PCIE_MSI_INTR0_STATUS + + (i * MSI_REG_CTRL_BLOCK_SIZE)); + if (!status) + continue; + + ret = IRQ_HANDLED; + val = status; + pos = 0; + while ((pos = find_next_bit(&val, MAX_MSI_IRQS_PER_CTRL, + pos)) != MAX_MSI_IRQS_PER_CTRL) { + generic_handle_domain_irq(pp->irq_domain, + (i * MAX_MSI_IRQS_PER_CTRL) + + pos); + pos++; + } + } + + return ret; +} + +/* Chained MSI interrupt service routine */ +static void dw_chained_msi_isr(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct dw_pcie_rp *pp; + + chained_irq_enter(chip, desc); + + pp = irq_desc_get_handler_data(desc); + dw_handle_msi_irq(pp); + + chained_irq_exit(chip, desc); +} + +static void dw_pci_setup_msi_msg(struct irq_data *d, struct msi_msg *msg) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + u64 msi_target; + + msi_target = (u64)pp->msi_data; + + msg->address_lo = lower_32_bits(msi_target); + msg->address_hi = upper_32_bits(msi_target); + + msg->data = d->hwirq; + + dev_dbg(pci->dev, "msi#%d address_hi %#x address_lo %#x\n", + (int)d->hwirq, msg->address_hi, msg->address_lo); +} + +static int dw_pci_msi_set_affinity(struct irq_data *d, + const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static void dw_pci_bottom_mask(struct irq_data *d) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + unsigned int res, bit, ctrl; + unsigned long flags; + + raw_spin_lock_irqsave(&pp->lock, flags); + + ctrl = d->hwirq / MAX_MSI_IRQS_PER_CTRL; + res = ctrl * MSI_REG_CTRL_BLOCK_SIZE; + bit = d->hwirq % MAX_MSI_IRQS_PER_CTRL; + + pp->irq_mask[ctrl] |= BIT(bit); + dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_MASK + res, pp->irq_mask[ctrl]); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +} + +static void dw_pci_bottom_unmask(struct irq_data *d) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + unsigned int res, bit, ctrl; + unsigned long flags; + + raw_spin_lock_irqsave(&pp->lock, flags); + + ctrl = d->hwirq / MAX_MSI_IRQS_PER_CTRL; + res = ctrl * MSI_REG_CTRL_BLOCK_SIZE; + bit = d->hwirq % MAX_MSI_IRQS_PER_CTRL; + + pp->irq_mask[ctrl] &= ~BIT(bit); + dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_MASK + res, pp->irq_mask[ctrl]); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +} + +static void dw_pci_bottom_ack(struct irq_data *d) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + unsigned int res, bit, ctrl; + + ctrl = d->hwirq / MAX_MSI_IRQS_PER_CTRL; + res = ctrl * MSI_REG_CTRL_BLOCK_SIZE; + bit = d->hwirq % MAX_MSI_IRQS_PER_CTRL; + + dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_STATUS + res, BIT(bit)); +} + +static struct irq_chip dw_pci_msi_bottom_irq_chip = { + .name = "DWPCI-MSI", + .irq_ack = dw_pci_bottom_ack, + .irq_compose_msi_msg = dw_pci_setup_msi_msg, + .irq_set_affinity = dw_pci_msi_set_affinity, + .irq_mask = dw_pci_bottom_mask, + .irq_unmask = dw_pci_bottom_unmask, +}; + +static int dw_pcie_irq_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *args) +{ + struct dw_pcie_rp *pp = domain->host_data; + unsigned long flags; + u32 i; + int bit; + + raw_spin_lock_irqsave(&pp->lock, flags); + + bit = bitmap_find_free_region(pp->msi_irq_in_use, pp->num_vectors, + order_base_2(nr_irqs)); + + raw_spin_unlock_irqrestore(&pp->lock, flags); + + if (bit < 0) + return -ENOSPC; + + for (i = 0; i < nr_irqs; i++) + irq_domain_set_info(domain, virq + i, bit + i, + pp->msi_irq_chip, + pp, handle_edge_irq, + NULL, NULL); + + return 0; +} + +static void dw_pcie_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct dw_pcie_rp *pp = domain->host_data; + unsigned long flags; + + raw_spin_lock_irqsave(&pp->lock, flags); + + bitmap_release_region(pp->msi_irq_in_use, d->hwirq, + order_base_2(nr_irqs)); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +} + +static const struct irq_domain_ops dw_pcie_msi_domain_ops = { + .alloc = dw_pcie_irq_domain_alloc, + .free = dw_pcie_irq_domain_free, +}; + +int dw_pcie_allocate_domains(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct fwnode_handle *fwnode = of_node_to_fwnode(pci->dev->of_node); + + pp->irq_domain = irq_domain_create_linear(fwnode, pp->num_vectors, + &dw_pcie_msi_domain_ops, pp); + if (!pp->irq_domain) { + dev_err(pci->dev, "Failed to create IRQ domain\n"); + return -ENOMEM; + } + + irq_domain_update_bus_token(pp->irq_domain, DOMAIN_BUS_NEXUS); + + pp->msi_domain = pci_msi_create_irq_domain(fwnode, + &dw_pcie_msi_domain_info, + pp->irq_domain); + if (!pp->msi_domain) { + dev_err(pci->dev, "Failed to create MSI domain\n"); + irq_domain_remove(pp->irq_domain); + return -ENOMEM; + } + + return 0; +} + +static void dw_pcie_free_msi(struct dw_pcie_rp *pp) +{ + u32 ctrl; + + for (ctrl = 0; ctrl < MAX_MSI_CTRLS; ctrl++) { + if (pp->msi_irq[ctrl] > 0) + irq_set_chained_handler_and_data(pp->msi_irq[ctrl], + NULL, NULL); + } + + irq_domain_remove(pp->msi_domain); + irq_domain_remove(pp->irq_domain); +} + +static void dw_pcie_msi_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + u64 msi_target = (u64)pp->msi_data; + + if (!pci_msi_enabled() || !pp->has_msi_ctrl) + return; + + /* Program the msi_data */ + dw_pcie_writel_dbi(pci, PCIE_MSI_ADDR_LO, lower_32_bits(msi_target)); + dw_pcie_writel_dbi(pci, PCIE_MSI_ADDR_HI, upper_32_bits(msi_target)); +} + +static int dw_pcie_parse_split_msi_irq(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct platform_device *pdev = to_platform_device(dev); + u32 ctrl, max_vectors; + int irq; + + /* Parse any "msiX" IRQs described in the devicetree */ + for (ctrl = 0; ctrl < MAX_MSI_CTRLS; ctrl++) { + char msi_name[] = "msiX"; + + msi_name[3] = '0' + ctrl; + irq = platform_get_irq_byname_optional(pdev, msi_name); + if (irq == -ENXIO) + break; + if (irq < 0) + return dev_err_probe(dev, irq, + "Failed to parse MSI IRQ '%s'\n", + msi_name); + + pp->msi_irq[ctrl] = irq; + } + + /* If no "msiX" IRQs, caller should fallback to "msi" IRQ */ + if (ctrl == 0) + return -ENXIO; + + max_vectors = ctrl * MAX_MSI_IRQS_PER_CTRL; + if (pp->num_vectors > max_vectors) { + dev_warn(dev, "Exceeding number of MSI vectors, limiting to %u\n", + max_vectors); + pp->num_vectors = max_vectors; + } + if (!pp->num_vectors) + pp->num_vectors = max_vectors; + + return 0; +} + +static int dw_pcie_msi_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct platform_device *pdev = to_platform_device(dev); + u64 *msi_vaddr; + int ret; + u32 ctrl, num_ctrls; + + for (ctrl = 0; ctrl < MAX_MSI_CTRLS; ctrl++) + pp->irq_mask[ctrl] = ~0; + + if (!pp->msi_irq[0]) { + ret = dw_pcie_parse_split_msi_irq(pp); + if (ret < 0 && ret != -ENXIO) + return ret; + } + + if (!pp->num_vectors) + pp->num_vectors = MSI_DEF_NUM_VECTORS; + num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; + + if (!pp->msi_irq[0]) { + pp->msi_irq[0] = platform_get_irq_byname_optional(pdev, "msi"); + if (pp->msi_irq[0] < 0) { + pp->msi_irq[0] = platform_get_irq(pdev, 0); + if (pp->msi_irq[0] < 0) + return pp->msi_irq[0]; + } + } + + dev_dbg(dev, "Using %d MSI vectors\n", pp->num_vectors); + + pp->msi_irq_chip = &dw_pci_msi_bottom_irq_chip; + + ret = dw_pcie_allocate_domains(pp); + if (ret) + return ret; + + for (ctrl = 0; ctrl < num_ctrls; ctrl++) { + if (pp->msi_irq[ctrl] > 0) + irq_set_chained_handler_and_data(pp->msi_irq[ctrl], + dw_chained_msi_isr, pp); + } + + ret = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32)); + if (ret) + dev_warn(dev, "Failed to set DMA mask to 32-bit. Devices with only 32-bit MSI support may not work properly\n"); + + msi_vaddr = dmam_alloc_coherent(dev, sizeof(u64), &pp->msi_data, + GFP_KERNEL); + if (!msi_vaddr) { + dev_err(dev, "Failed to alloc and map MSI data\n"); + dw_pcie_free_msi(pp); + return -ENOMEM; + } + + return 0; +} + +int dw_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct device_node *np = dev->of_node; + struct platform_device *pdev = to_platform_device(dev); + struct resource_entry *win; + struct pci_host_bridge *bridge; + struct resource *res; + int ret; + + raw_spin_lock_init(&pp->lock); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config"); + if (res) { + pp->cfg0_size = resource_size(res); + pp->cfg0_base = res->start; + + pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pp->va_cfg0_base)) + return PTR_ERR(pp->va_cfg0_base); + } else { + dev_err(dev, "Missing *config* reg space\n"); + return -ENODEV; + } + + if (!pci->dbi_base) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); + pci->dbi_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + } + + bridge = devm_pci_alloc_host_bridge(dev, 0); + if (!bridge) + return -ENOMEM; + + pp->bridge = bridge; + + /* Get the I/O range from DT */ + win = resource_list_first_type(&bridge->windows, IORESOURCE_IO); + if (win) { + pp->io_size = resource_size(win->res); + pp->io_bus_addr = win->res->start - win->offset; + pp->io_base = pci_pio_to_address(win->res->start); + } + + if (pci->link_gen < 1) + pci->link_gen = of_pci_get_max_link_speed(np); + + /* Set default bus ops */ + bridge->ops = &dw_pcie_ops; + bridge->child_ops = &dw_child_pcie_ops; + + if (pp->ops->host_init) { + ret = pp->ops->host_init(pp); + if (ret) + return ret; + } + + if (pci_msi_enabled()) { + pp->has_msi_ctrl = !(pp->ops->msi_host_init || + of_property_read_bool(np, "msi-parent") || + of_property_read_bool(np, "msi-map")); + + /* + * For the has_msi_ctrl case the default assignment is handled + * in the dw_pcie_msi_host_init(). + */ + if (!pp->has_msi_ctrl && !pp->num_vectors) { + pp->num_vectors = MSI_DEF_NUM_VECTORS; + } else if (pp->num_vectors > MAX_MSI_IRQS) { + dev_err(dev, "Invalid number of vectors\n"); + ret = -EINVAL; + goto err_deinit_host; + } + + if (pp->ops->msi_host_init) { + ret = pp->ops->msi_host_init(pp); + if (ret < 0) + goto err_deinit_host; + } else if (pp->has_msi_ctrl) { + ret = dw_pcie_msi_host_init(pp); + if (ret < 0) + goto err_deinit_host; + } + } + + dw_pcie_version_detect(pci); + + dw_pcie_iatu_detect(pci); + + ret = dw_pcie_setup_rc(pp); + if (ret) + goto err_free_msi; + + if (!dw_pcie_link_up(pci)) { + ret = dw_pcie_start_link(pci); + if (ret) + goto err_free_msi; + } + + /* Ignore errors, the link may come up later */ + dw_pcie_wait_for_link(pci); + + bridge->sysdata = pp; + + ret = pci_host_probe(bridge); + if (ret) + goto err_stop_link; + + return 0; + +err_stop_link: + dw_pcie_stop_link(pci); + +err_free_msi: + if (pp->has_msi_ctrl) + dw_pcie_free_msi(pp); + +err_deinit_host: + if (pp->ops->host_deinit) + pp->ops->host_deinit(pp); + + return ret; +} +EXPORT_SYMBOL_GPL(dw_pcie_host_init); + +void dw_pcie_host_deinit(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + + pci_stop_root_bus(pp->bridge->bus); + pci_remove_root_bus(pp->bridge->bus); + + dw_pcie_stop_link(pci); + + if (pp->has_msi_ctrl) + dw_pcie_free_msi(pp); + + if (pp->ops->host_deinit) + pp->ops->host_deinit(pp); +} +EXPORT_SYMBOL_GPL(dw_pcie_host_deinit); + +static void __iomem *dw_pcie_other_conf_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + int type, ret; + u32 busdev; + + /* + * Checking whether the link is up here is a last line of defense + * against platforms that forward errors on the system bus as + * SError upon PCI configuration transactions issued when the link + * is down. This check is racy by definition and does not stop + * the system from triggering an SError if the link goes down + * after this check is performed. + */ + if (!dw_pcie_link_up(pci)) + return NULL; + + busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) | + PCIE_ATU_FUNC(PCI_FUNC(devfn)); + + if (pci_is_root_bus(bus->parent)) + type = PCIE_ATU_TYPE_CFG0; + else + type = PCIE_ATU_TYPE_CFG1; + + ret = dw_pcie_prog_outbound_atu(pci, 0, type, pp->cfg0_base, busdev, + pp->cfg0_size); + if (ret) + return NULL; + + return pp->va_cfg0_base + where; +} + +static int dw_pcie_rd_other_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + int ret; + + ret = pci_generic_config_read(bus, devfn, where, size, val); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + if (pp->cfg0_io_shared) { + ret = dw_pcie_prog_outbound_atu(pci, 0, PCIE_ATU_TYPE_IO, + pp->io_base, pp->io_bus_addr, + pp->io_size); + if (ret) + return PCIBIOS_SET_FAILED; + } + + return PCIBIOS_SUCCESSFUL; +} + +static int dw_pcie_wr_other_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + int ret; + + ret = pci_generic_config_write(bus, devfn, where, size, val); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + if (pp->cfg0_io_shared) { + ret = dw_pcie_prog_outbound_atu(pci, 0, PCIE_ATU_TYPE_IO, + pp->io_base, pp->io_bus_addr, + pp->io_size); + if (ret) + return PCIBIOS_SET_FAILED; + } + + return PCIBIOS_SUCCESSFUL; +} + +static struct pci_ops dw_child_pcie_ops = { + .map_bus = dw_pcie_other_conf_map_bus, + .read = dw_pcie_rd_other_conf, + .write = dw_pcie_wr_other_conf, +}; + +void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, unsigned int devfn, int where) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + + if (PCI_SLOT(devfn) > 0) + return NULL; + + return pci->dbi_base + where; +} +EXPORT_SYMBOL_GPL(dw_pcie_own_conf_map_bus); + +static struct pci_ops dw_pcie_ops = { + .map_bus = dw_pcie_own_conf_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct resource_entry *entry; + int i, ret; + + /* Note the very first outbound ATU is used for CFG IOs */ + if (!pci->num_ob_windows) { + dev_err(pci->dev, "No outbound iATU found\n"); + return -EINVAL; + } + + /* + * Ensure all outbound windows are disabled before proceeding with + * the MEM/IO ranges setups. + */ + for (i = 0; i < pci->num_ob_windows; i++) + dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_OB, i); + + i = 0; + resource_list_for_each_entry(entry, &pp->bridge->windows) { + if (resource_type(entry->res) != IORESOURCE_MEM) + continue; + + if (pci->num_ob_windows <= ++i) + break; + + ret = dw_pcie_prog_outbound_atu(pci, i, PCIE_ATU_TYPE_MEM, + entry->res->start, + entry->res->start - entry->offset, + resource_size(entry->res)); + if (ret) { + dev_err(pci->dev, "Failed to set MEM range %pr\n", + entry->res); + return ret; + } + } + + if (pp->io_size) { + if (pci->num_ob_windows > ++i) { + ret = dw_pcie_prog_outbound_atu(pci, i, PCIE_ATU_TYPE_IO, + pp->io_base, + pp->io_bus_addr, + pp->io_size); + if (ret) { + dev_err(pci->dev, "Failed to set IO range %pr\n", + entry->res); + return ret; + } + } else { + pp->cfg0_io_shared = true; + } + } + + if (pci->num_ob_windows <= i) + dev_warn(pci->dev, "Resources exceed number of ATU entries (%d)\n", + pci->num_ob_windows); + + return 0; +} + +int dw_pcie_setup_rc(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + u32 val, ctrl, num_ctrls; + int ret; + + /* + * Enable DBI read-only registers for writing/updating configuration. + * Write permission gets disabled towards the end of this function. + */ + dw_pcie_dbi_ro_wr_en(pci); + + dw_pcie_setup(pci); + + if (pp->has_msi_ctrl) { + num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; + + /* Initialize IRQ Status array */ + for (ctrl = 0; ctrl < num_ctrls; ctrl++) { + dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_MASK + + (ctrl * MSI_REG_CTRL_BLOCK_SIZE), + pp->irq_mask[ctrl]); + dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_ENABLE + + (ctrl * MSI_REG_CTRL_BLOCK_SIZE), + ~0); + } + } + + dw_pcie_msi_init(pp); + + /* Setup RC BARs */ + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0x00000004); + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_1, 0x00000000); + + /* Setup interrupt pins */ + val = dw_pcie_readl_dbi(pci, PCI_INTERRUPT_LINE); + val &= 0xffff00ff; + val |= 0x00000100; + dw_pcie_writel_dbi(pci, PCI_INTERRUPT_LINE, val); + + /* Setup bus numbers */ + val = dw_pcie_readl_dbi(pci, PCI_PRIMARY_BUS); + val &= 0xff000000; + val |= 0x00ff0100; + dw_pcie_writel_dbi(pci, PCI_PRIMARY_BUS, val); + + /* Setup command register */ + val = dw_pcie_readl_dbi(pci, PCI_COMMAND); + val &= 0xffff0000; + val |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY | + PCI_COMMAND_MASTER | PCI_COMMAND_SERR; + dw_pcie_writel_dbi(pci, PCI_COMMAND, val); + + /* + * If the platform provides its own child bus config accesses, it means + * the platform uses its own address translation component rather than + * ATU, so we should not program the ATU here. + */ + if (pp->bridge->child_ops == &dw_child_pcie_ops) { + ret = dw_pcie_iatu_setup(pp); + if (ret) + return ret; + } + + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0); + + /* Program correct class for RC */ + dw_pcie_writew_dbi(pci, PCI_CLASS_DEVICE, PCI_CLASS_BRIDGE_PCI); + + val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + val |= PORT_LOGIC_SPEED_CHANGE; + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} +EXPORT_SYMBOL_GPL(dw_pcie_setup_rc); diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c new file mode 100644 index 000000000..1fcfb840f --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-designware-plat.c @@ -0,0 +1,187 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe RC driver for Synopsys DesignWare Core + * + * Copyright (C) 2015-2016 Synopsys, Inc. (www.synopsys.com) + * + * Authors: Joao Pinto <Joao.Pinto@synopsys.com> + */ +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of_device.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/types.h> + +#include "pcie-designware.h" + +struct dw_plat_pcie { + struct dw_pcie *pci; + enum dw_pcie_device_mode mode; +}; + +struct dw_plat_pcie_of_data { + enum dw_pcie_device_mode mode; +}; + +static const struct dw_pcie_host_ops dw_plat_pcie_host_ops = { +}; + +static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar; + + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) + dw_pcie_ep_reset_bar(pci, bar); +} + +static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + enum pci_epc_irq_type type, + u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + return dw_pcie_ep_raise_legacy_irq(ep, func_no); + case PCI_EPC_IRQ_MSI: + return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num); + case PCI_EPC_IRQ_MSIX: + return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num); + default: + dev_err(pci->dev, "UNKNOWN IRQ type\n"); + } + + return 0; +} + +static const struct pci_epc_features dw_plat_pcie_epc_features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = true, +}; + +static const struct pci_epc_features* +dw_plat_pcie_get_features(struct dw_pcie_ep *ep) +{ + return &dw_plat_pcie_epc_features; +} + +static const struct dw_pcie_ep_ops pcie_ep_ops = { + .ep_init = dw_plat_pcie_ep_init, + .raise_irq = dw_plat_pcie_ep_raise_irq, + .get_features = dw_plat_pcie_get_features, +}; + +static int dw_plat_add_pcie_port(struct dw_plat_pcie *dw_plat_pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = dw_plat_pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = &pdev->dev; + int ret; + + pp->irq = platform_get_irq(pdev, 1); + if (pp->irq < 0) + return pp->irq; + + pp->num_vectors = MAX_MSI_IRQS; + pp->ops = &dw_plat_pcie_host_ops; + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "Failed to initialize host\n"); + return ret; + } + + return 0; +} + +static int dw_plat_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_plat_pcie *dw_plat_pcie; + struct dw_pcie *pci; + int ret; + const struct dw_plat_pcie_of_data *data; + enum dw_pcie_device_mode mode; + + data = of_device_get_match_data(dev); + if (!data) + return -EINVAL; + + mode = (enum dw_pcie_device_mode)data->mode; + + dw_plat_pcie = devm_kzalloc(dev, sizeof(*dw_plat_pcie), GFP_KERNEL); + if (!dw_plat_pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pci->dev = dev; + + dw_plat_pcie->pci = pci; + dw_plat_pcie->mode = mode; + + platform_set_drvdata(pdev, dw_plat_pcie); + + switch (dw_plat_pcie->mode) { + case DW_PCIE_RC_TYPE: + if (!IS_ENABLED(CONFIG_PCIE_DW_PLAT_HOST)) + return -ENODEV; + + ret = dw_plat_add_pcie_port(dw_plat_pcie, pdev); + break; + case DW_PCIE_EP_TYPE: + if (!IS_ENABLED(CONFIG_PCIE_DW_PLAT_EP)) + return -ENODEV; + + pci->ep.ops = &pcie_ep_ops; + ret = dw_pcie_ep_init(&pci->ep); + break; + default: + dev_err(dev, "INVALID device type %d\n", dw_plat_pcie->mode); + ret = -EINVAL; + break; + } + + return ret; +} + +static const struct dw_plat_pcie_of_data dw_plat_pcie_rc_of_data = { + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct dw_plat_pcie_of_data dw_plat_pcie_ep_of_data = { + .mode = DW_PCIE_EP_TYPE, +}; + +static const struct of_device_id dw_plat_pcie_of_match[] = { + { + .compatible = "snps,dw-pcie", + .data = &dw_plat_pcie_rc_of_data, + }, + { + .compatible = "snps,dw-pcie-ep", + .data = &dw_plat_pcie_ep_of_data, + }, + {}, +}; + +static struct platform_driver dw_plat_pcie_driver = { + .driver = { + .name = "dw-pcie", + .of_match_table = dw_plat_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = dw_plat_pcie_probe, +}; +builtin_platform_driver(dw_plat_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c new file mode 100644 index 000000000..575834cae --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -0,0 +1,706 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Synopsys DesignWare PCIe host controller driver + * + * Copyright (C) 2013 Samsung Electronics Co., Ltd. + * https://www.samsung.com + * + * Author: Jingoo Han <jg1.han@samsung.com> + */ + +#include <linux/align.h> +#include <linux/bitops.h> +#include <linux/delay.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/sizes.h> +#include <linux/types.h> + +#include "../../pci.h" +#include "pcie-designware.h" + +void dw_pcie_version_detect(struct dw_pcie *pci) +{ + u32 ver; + + /* The content of the CSR is zero on DWC PCIe older than v4.70a */ + ver = dw_pcie_readl_dbi(pci, PCIE_VERSION_NUMBER); + if (!ver) + return; + + if (pci->version && pci->version != ver) + dev_warn(pci->dev, "Versions don't match (%08x != %08x)\n", + pci->version, ver); + else + pci->version = ver; + + ver = dw_pcie_readl_dbi(pci, PCIE_VERSION_TYPE); + + if (pci->type && pci->type != ver) + dev_warn(pci->dev, "Types don't match (%08x != %08x)\n", + pci->type, ver); + else + pci->type = ver; +} + +/* + * These interfaces resemble the pci_find_*capability() interfaces, but these + * are for configuring host controllers, which are bridges *to* PCI devices but + * are not PCI devices themselves. + */ +static u8 __dw_pcie_find_next_cap(struct dw_pcie *pci, u8 cap_ptr, + u8 cap) +{ + u8 cap_id, next_cap_ptr; + u16 reg; + + if (!cap_ptr) + return 0; + + reg = dw_pcie_readw_dbi(pci, cap_ptr); + cap_id = (reg & 0x00ff); + + if (cap_id > PCI_CAP_ID_MAX) + return 0; + + if (cap_id == cap) + return cap_ptr; + + next_cap_ptr = (reg & 0xff00) >> 8; + return __dw_pcie_find_next_cap(pci, next_cap_ptr, cap); +} + +u8 dw_pcie_find_capability(struct dw_pcie *pci, u8 cap) +{ + u8 next_cap_ptr; + u16 reg; + + reg = dw_pcie_readw_dbi(pci, PCI_CAPABILITY_LIST); + next_cap_ptr = (reg & 0x00ff); + + return __dw_pcie_find_next_cap(pci, next_cap_ptr, cap); +} +EXPORT_SYMBOL_GPL(dw_pcie_find_capability); + +static u16 dw_pcie_find_next_ext_capability(struct dw_pcie *pci, u16 start, + u8 cap) +{ + u32 header; + int ttl; + int pos = PCI_CFG_SPACE_SIZE; + + /* minimum 8 bytes per capability */ + ttl = (PCI_CFG_SPACE_EXP_SIZE - PCI_CFG_SPACE_SIZE) / 8; + + if (start) + pos = start; + + header = dw_pcie_readl_dbi(pci, pos); + /* + * If we have no capabilities, this is indicated by cap ID, + * cap version and next pointer all being 0. + */ + if (header == 0) + return 0; + + while (ttl-- > 0) { + if (PCI_EXT_CAP_ID(header) == cap && pos != start) + return pos; + + pos = PCI_EXT_CAP_NEXT(header); + if (pos < PCI_CFG_SPACE_SIZE) + break; + + header = dw_pcie_readl_dbi(pci, pos); + } + + return 0; +} + +u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap) +{ + return dw_pcie_find_next_ext_capability(pci, 0, cap); +} +EXPORT_SYMBOL_GPL(dw_pcie_find_ext_capability); + +int dw_pcie_read(void __iomem *addr, int size, u32 *val) +{ + if (!IS_ALIGNED((uintptr_t)addr, size)) { + *val = 0; + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + if (size == 4) { + *val = readl(addr); + } else if (size == 2) { + *val = readw(addr); + } else if (size == 1) { + *val = readb(addr); + } else { + *val = 0; + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + return PCIBIOS_SUCCESSFUL; +} +EXPORT_SYMBOL_GPL(dw_pcie_read); + +int dw_pcie_write(void __iomem *addr, int size, u32 val) +{ + if (!IS_ALIGNED((uintptr_t)addr, size)) + return PCIBIOS_BAD_REGISTER_NUMBER; + + if (size == 4) + writel(val, addr); + else if (size == 2) + writew(val, addr); + else if (size == 1) + writeb(val, addr); + else + return PCIBIOS_BAD_REGISTER_NUMBER; + + return PCIBIOS_SUCCESSFUL; +} +EXPORT_SYMBOL_GPL(dw_pcie_write); + +u32 dw_pcie_read_dbi(struct dw_pcie *pci, u32 reg, size_t size) +{ + int ret; + u32 val; + + if (pci->ops && pci->ops->read_dbi) + return pci->ops->read_dbi(pci, pci->dbi_base, reg, size); + + ret = dw_pcie_read(pci->dbi_base + reg, size, &val); + if (ret) + dev_err(pci->dev, "Read DBI address failed\n"); + + return val; +} +EXPORT_SYMBOL_GPL(dw_pcie_read_dbi); + +void dw_pcie_write_dbi(struct dw_pcie *pci, u32 reg, size_t size, u32 val) +{ + int ret; + + if (pci->ops && pci->ops->write_dbi) { + pci->ops->write_dbi(pci, pci->dbi_base, reg, size, val); + return; + } + + ret = dw_pcie_write(pci->dbi_base + reg, size, val); + if (ret) + dev_err(pci->dev, "Write DBI address failed\n"); +} +EXPORT_SYMBOL_GPL(dw_pcie_write_dbi); + +void dw_pcie_write_dbi2(struct dw_pcie *pci, u32 reg, size_t size, u32 val) +{ + int ret; + + if (pci->ops && pci->ops->write_dbi2) { + pci->ops->write_dbi2(pci, pci->dbi_base2, reg, size, val); + return; + } + + ret = dw_pcie_write(pci->dbi_base2 + reg, size, val); + if (ret) + dev_err(pci->dev, "write DBI address failed\n"); +} + +static inline void __iomem *dw_pcie_select_atu(struct dw_pcie *pci, u32 dir, + u32 index) +{ + if (pci->iatu_unroll_enabled) + return pci->atu_base + PCIE_ATU_UNROLL_BASE(dir, index); + + dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, dir | index); + return pci->atu_base; +} + +static u32 dw_pcie_readl_atu(struct dw_pcie *pci, u32 dir, u32 index, u32 reg) +{ + void __iomem *base; + int ret; + u32 val; + + base = dw_pcie_select_atu(pci, dir, index); + + if (pci->ops && pci->ops->read_dbi) + return pci->ops->read_dbi(pci, base, reg, 4); + + ret = dw_pcie_read(base + reg, 4, &val); + if (ret) + dev_err(pci->dev, "Read ATU address failed\n"); + + return val; +} + +static void dw_pcie_writel_atu(struct dw_pcie *pci, u32 dir, u32 index, + u32 reg, u32 val) +{ + void __iomem *base; + int ret; + + base = dw_pcie_select_atu(pci, dir, index); + + if (pci->ops && pci->ops->write_dbi) { + pci->ops->write_dbi(pci, base, reg, 4, val); + return; + } + + ret = dw_pcie_write(base + reg, 4, val); + if (ret) + dev_err(pci->dev, "Write ATU address failed\n"); +} + +static inline u32 dw_pcie_readl_atu_ob(struct dw_pcie *pci, u32 index, u32 reg) +{ + return dw_pcie_readl_atu(pci, PCIE_ATU_REGION_DIR_OB, index, reg); +} + +static inline void dw_pcie_writel_atu_ob(struct dw_pcie *pci, u32 index, u32 reg, + u32 val) +{ + dw_pcie_writel_atu(pci, PCIE_ATU_REGION_DIR_OB, index, reg, val); +} + +static inline u32 dw_pcie_enable_ecrc(u32 val) +{ + /* + * DesignWare core version 4.90A has a design issue where the 'TD' + * bit in the Control register-1 of the ATU outbound region acts + * like an override for the ECRC setting, i.e., the presence of TLP + * Digest (ECRC) in the outgoing TLPs is solely determined by this + * bit. This is contrary to the PCIe spec which says that the + * enablement of the ECRC is solely determined by the AER + * registers. + * + * Because of this, even when the ECRC is enabled through AER + * registers, the transactions going through ATU won't have TLP + * Digest as there is no way the PCI core AER code could program + * the TD bit which is specific to the DesignWare core. + * + * The best way to handle this scenario is to program the TD bit + * always. It affects only the traffic from root port to downstream + * devices. + * + * At this point, + * When ECRC is enabled in AER registers, everything works normally + * When ECRC is NOT enabled in AER registers, then, + * on Root Port:- TLP Digest (DWord size) gets appended to each packet + * even through it is not required. Since downstream + * TLPs are mostly for configuration accesses and BAR + * accesses, they are not in critical path and won't + * have much negative effect on the performance. + * on End Point:- TLP Digest is received for some/all the packets coming + * from the root port. TLP Digest is ignored because, + * as per the PCIe Spec r5.0 v1.0 section 2.2.3 + * "TLP Digest Rules", when an endpoint receives TLP + * Digest when its ECRC check functionality is disabled + * in AER registers, received TLP Digest is just ignored. + * Since there is no issue or error reported either side, best way to + * handle the scenario is to program TD bit by default. + */ + + return val | PCIE_ATU_TD; +} + +static int __dw_pcie_prog_outbound_atu(struct dw_pcie *pci, u8 func_no, + int index, int type, u64 cpu_addr, + u64 pci_addr, u64 size) +{ + u32 retries, val; + u64 limit_addr; + + if (pci->ops && pci->ops->cpu_addr_fixup) + cpu_addr = pci->ops->cpu_addr_fixup(pci, cpu_addr); + + limit_addr = cpu_addr + size - 1; + + if ((limit_addr & ~pci->region_limit) != (cpu_addr & ~pci->region_limit) || + !IS_ALIGNED(cpu_addr, pci->region_align) || + !IS_ALIGNED(pci_addr, pci->region_align) || !size) { + return -EINVAL; + } + + dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_LOWER_BASE, + lower_32_bits(cpu_addr)); + dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_UPPER_BASE, + upper_32_bits(cpu_addr)); + + dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_LIMIT, + lower_32_bits(limit_addr)); + if (dw_pcie_ver_is_ge(pci, 460A)) + dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_UPPER_LIMIT, + upper_32_bits(limit_addr)); + + dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_LOWER_TARGET, + lower_32_bits(pci_addr)); + dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_UPPER_TARGET, + upper_32_bits(pci_addr)); + + val = type | PCIE_ATU_FUNC_NUM(func_no); + if (upper_32_bits(limit_addr) > upper_32_bits(cpu_addr) && + dw_pcie_ver_is_ge(pci, 460A)) + val |= PCIE_ATU_INCREASE_REGION_SIZE; + if (dw_pcie_ver_is(pci, 490A)) + val = dw_pcie_enable_ecrc(val); + dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_REGION_CTRL1, val); + + dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_REGION_CTRL2, PCIE_ATU_ENABLE); + + /* + * Make sure ATU enable takes effect before any subsequent config + * and I/O accesses. + */ + for (retries = 0; retries < LINK_WAIT_MAX_IATU_RETRIES; retries++) { + val = dw_pcie_readl_atu_ob(pci, index, PCIE_ATU_REGION_CTRL2); + if (val & PCIE_ATU_ENABLE) + return 0; + + mdelay(LINK_WAIT_IATU); + } + + dev_err(pci->dev, "Outbound iATU is not being enabled\n"); + + return -ETIMEDOUT; +} + +int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index, int type, + u64 cpu_addr, u64 pci_addr, u64 size) +{ + return __dw_pcie_prog_outbound_atu(pci, 0, index, type, + cpu_addr, pci_addr, size); +} + +int dw_pcie_prog_ep_outbound_atu(struct dw_pcie *pci, u8 func_no, int index, + int type, u64 cpu_addr, u64 pci_addr, + u64 size) +{ + return __dw_pcie_prog_outbound_atu(pci, func_no, index, type, + cpu_addr, pci_addr, size); +} + +static inline u32 dw_pcie_readl_atu_ib(struct dw_pcie *pci, u32 index, u32 reg) +{ + return dw_pcie_readl_atu(pci, PCIE_ATU_REGION_DIR_IB, index, reg); +} + +static inline void dw_pcie_writel_atu_ib(struct dw_pcie *pci, u32 index, u32 reg, + u32 val) +{ + dw_pcie_writel_atu(pci, PCIE_ATU_REGION_DIR_IB, index, reg, val); +} + +int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, u8 func_no, int index, + int type, u64 cpu_addr, u8 bar) +{ + u32 retries, val; + + if (!IS_ALIGNED(cpu_addr, pci->region_align)) + return -EINVAL; + + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LOWER_TARGET, + lower_32_bits(cpu_addr)); + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_UPPER_TARGET, + upper_32_bits(cpu_addr)); + + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_REGION_CTRL1, type | + PCIE_ATU_FUNC_NUM(func_no)); + dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_REGION_CTRL2, + PCIE_ATU_ENABLE | PCIE_ATU_FUNC_NUM_MATCH_EN | + PCIE_ATU_BAR_MODE_ENABLE | (bar << 8)); + + /* + * Make sure ATU enable takes effect before any subsequent config + * and I/O accesses. + */ + for (retries = 0; retries < LINK_WAIT_MAX_IATU_RETRIES; retries++) { + val = dw_pcie_readl_atu_ib(pci, index, PCIE_ATU_REGION_CTRL2); + if (val & PCIE_ATU_ENABLE) + return 0; + + mdelay(LINK_WAIT_IATU); + } + + dev_err(pci->dev, "Inbound iATU is not being enabled\n"); + + return -ETIMEDOUT; +} + +void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index) +{ + dw_pcie_writel_atu(pci, dir, index, PCIE_ATU_REGION_CTRL2, 0); +} + +int dw_pcie_wait_for_link(struct dw_pcie *pci) +{ + u32 offset, val; + int retries; + + /* Check if the link is up or not */ + for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { + if (dw_pcie_link_up(pci)) + break; + + usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX); + } + + if (retries >= LINK_WAIT_MAX_RETRIES) { + dev_err(pci->dev, "Phy link never came up\n"); + return -ETIMEDOUT; + } + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + val = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA); + + dev_info(pci->dev, "PCIe Gen.%u x%u link up\n", + FIELD_GET(PCI_EXP_LNKSTA_CLS, val), + FIELD_GET(PCI_EXP_LNKSTA_NLW, val)); + + return 0; +} +EXPORT_SYMBOL_GPL(dw_pcie_wait_for_link); + +int dw_pcie_link_up(struct dw_pcie *pci) +{ + u32 val; + + if (pci->ops && pci->ops->link_up) + return pci->ops->link_up(pci); + + val = dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG1); + return ((val & PCIE_PORT_DEBUG1_LINK_UP) && + (!(val & PCIE_PORT_DEBUG1_LINK_IN_TRAINING))); +} +EXPORT_SYMBOL_GPL(dw_pcie_link_up); + +void dw_pcie_upconfig_setup(struct dw_pcie *pci) +{ + u32 val; + + val = dw_pcie_readl_dbi(pci, PCIE_PORT_MULTI_LANE_CTRL); + val |= PORT_MLTI_UPCFG_SUPPORT; + dw_pcie_writel_dbi(pci, PCIE_PORT_MULTI_LANE_CTRL, val); +} +EXPORT_SYMBOL_GPL(dw_pcie_upconfig_setup); + +static void dw_pcie_link_set_max_speed(struct dw_pcie *pci, u32 link_gen) +{ + u32 cap, ctrl2, link_speed; + u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + + cap = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + ctrl2 = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCTL2); + ctrl2 &= ~PCI_EXP_LNKCTL2_TLS; + + switch (pcie_link_speed[link_gen]) { + case PCIE_SPEED_2_5GT: + link_speed = PCI_EXP_LNKCTL2_TLS_2_5GT; + break; + case PCIE_SPEED_5_0GT: + link_speed = PCI_EXP_LNKCTL2_TLS_5_0GT; + break; + case PCIE_SPEED_8_0GT: + link_speed = PCI_EXP_LNKCTL2_TLS_8_0GT; + break; + case PCIE_SPEED_16_0GT: + link_speed = PCI_EXP_LNKCTL2_TLS_16_0GT; + break; + default: + /* Use hardware capability */ + link_speed = FIELD_GET(PCI_EXP_LNKCAP_SLS, cap); + ctrl2 &= ~PCI_EXP_LNKCTL2_HASD; + break; + } + + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCTL2, ctrl2 | link_speed); + + cap &= ~((u32)PCI_EXP_LNKCAP_SLS); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, cap | link_speed); + +} + +static bool dw_pcie_iatu_unroll_enabled(struct dw_pcie *pci) +{ + u32 val; + + val = dw_pcie_readl_dbi(pci, PCIE_ATU_VIEWPORT); + if (val == 0xffffffff) + return true; + + return false; +} + +static void dw_pcie_iatu_detect_regions(struct dw_pcie *pci) +{ + int max_region, ob, ib; + u32 val, min, dir; + u64 max; + + if (pci->iatu_unroll_enabled) { + max_region = min((int)pci->atu_size / 512, 256); + } else { + dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, 0xFF); + max_region = dw_pcie_readl_dbi(pci, PCIE_ATU_VIEWPORT) + 1; + } + + for (ob = 0; ob < max_region; ob++) { + dw_pcie_writel_atu_ob(pci, ob, PCIE_ATU_LOWER_TARGET, 0x11110000); + val = dw_pcie_readl_atu_ob(pci, ob, PCIE_ATU_LOWER_TARGET); + if (val != 0x11110000) + break; + } + + for (ib = 0; ib < max_region; ib++) { + dw_pcie_writel_atu_ib(pci, ib, PCIE_ATU_LOWER_TARGET, 0x11110000); + val = dw_pcie_readl_atu_ib(pci, ib, PCIE_ATU_LOWER_TARGET); + if (val != 0x11110000) + break; + } + + if (ob) { + dir = PCIE_ATU_REGION_DIR_OB; + } else if (ib) { + dir = PCIE_ATU_REGION_DIR_IB; + } else { + dev_err(pci->dev, "No iATU regions found\n"); + return; + } + + dw_pcie_writel_atu(pci, dir, 0, PCIE_ATU_LIMIT, 0x0); + min = dw_pcie_readl_atu(pci, dir, 0, PCIE_ATU_LIMIT); + + if (dw_pcie_ver_is_ge(pci, 460A)) { + dw_pcie_writel_atu(pci, dir, 0, PCIE_ATU_UPPER_LIMIT, 0xFFFFFFFF); + max = dw_pcie_readl_atu(pci, dir, 0, PCIE_ATU_UPPER_LIMIT); + } else { + max = 0; + } + + pci->num_ob_windows = ob; + pci->num_ib_windows = ib; + pci->region_align = 1 << fls(min); + pci->region_limit = (max << 32) | (SZ_4G - 1); +} + +void dw_pcie_iatu_detect(struct dw_pcie *pci) +{ + struct platform_device *pdev = to_platform_device(pci->dev); + + pci->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pci); + if (pci->iatu_unroll_enabled) { + if (!pci->atu_base) { + struct resource *res = + platform_get_resource_byname(pdev, IORESOURCE_MEM, "atu"); + if (res) { + pci->atu_size = resource_size(res); + pci->atu_base = devm_ioremap_resource(pci->dev, res); + } + if (!pci->atu_base || IS_ERR(pci->atu_base)) + pci->atu_base = pci->dbi_base + DEFAULT_DBI_ATU_OFFSET; + } + + if (!pci->atu_size) + /* Pick a minimal default, enough for 8 in and 8 out windows */ + pci->atu_size = SZ_4K; + } else { + pci->atu_base = pci->dbi_base + PCIE_ATU_VIEWPORT_BASE; + pci->atu_size = PCIE_ATU_VIEWPORT_SIZE; + } + + dw_pcie_iatu_detect_regions(pci); + + dev_info(pci->dev, "iATU unroll: %s\n", pci->iatu_unroll_enabled ? + "enabled" : "disabled"); + + dev_info(pci->dev, "iATU regions: %u ob, %u ib, align %uK, limit %lluG\n", + pci->num_ob_windows, pci->num_ib_windows, + pci->region_align / SZ_1K, (pci->region_limit + 1) / SZ_1G); +} + +void dw_pcie_setup(struct dw_pcie *pci) +{ + struct device_node *np = pci->dev->of_node; + u32 val; + + if (pci->link_gen > 0) + dw_pcie_link_set_max_speed(pci, pci->link_gen); + + /* Configure Gen1 N_FTS */ + if (pci->n_fts[0]) { + val = dw_pcie_readl_dbi(pci, PCIE_PORT_AFR); + val &= ~(PORT_AFR_N_FTS_MASK | PORT_AFR_CC_N_FTS_MASK); + val |= PORT_AFR_N_FTS(pci->n_fts[0]); + val |= PORT_AFR_CC_N_FTS(pci->n_fts[0]); + dw_pcie_writel_dbi(pci, PCIE_PORT_AFR, val); + } + + /* Configure Gen2+ N_FTS */ + if (pci->n_fts[1]) { + val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + val &= ~PORT_LOGIC_N_FTS_MASK; + val |= pci->n_fts[1]; + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + } + + if (of_property_read_bool(np, "snps,enable-cdm-check")) { + val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS); + val |= PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS | + PCIE_PL_CHK_REG_CHK_REG_START; + dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val); + } + + val = dw_pcie_readl_dbi(pci, PCIE_PORT_LINK_CONTROL); + val &= ~PORT_LINK_FAST_LINK_MODE; + val |= PORT_LINK_DLL_LINK_EN; + dw_pcie_writel_dbi(pci, PCIE_PORT_LINK_CONTROL, val); + + of_property_read_u32(np, "num-lanes", &pci->num_lanes); + if (!pci->num_lanes) { + dev_dbg(pci->dev, "Using h/w default number of lanes\n"); + return; + } + + /* Set the number of lanes */ + val &= ~PORT_LINK_FAST_LINK_MODE; + val &= ~PORT_LINK_MODE_MASK; + switch (pci->num_lanes) { + case 1: + val |= PORT_LINK_MODE_1_LANES; + break; + case 2: + val |= PORT_LINK_MODE_2_LANES; + break; + case 4: + val |= PORT_LINK_MODE_4_LANES; + break; + case 8: + val |= PORT_LINK_MODE_8_LANES; + break; + default: + dev_err(pci->dev, "num-lanes %u: invalid value\n", pci->num_lanes); + return; + } + dw_pcie_writel_dbi(pci, PCIE_PORT_LINK_CONTROL, val); + + /* Set link width speed control register */ + val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + val &= ~PORT_LOGIC_LINK_WIDTH_MASK; + switch (pci->num_lanes) { + case 1: + val |= PORT_LOGIC_LINK_WIDTH_1_LANES; + break; + case 2: + val |= PORT_LOGIC_LINK_WIDTH_2_LANES; + break; + case 4: + val |= PORT_LOGIC_LINK_WIDTH_4_LANES; + break; + case 8: + val |= PORT_LOGIC_LINK_WIDTH_8_LANES; + break; + } + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); +} diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h new file mode 100644 index 000000000..a871ae7eb --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -0,0 +1,539 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Synopsys DesignWare PCIe host controller driver + * + * Copyright (C) 2013 Samsung Electronics Co., Ltd. + * https://www.samsung.com + * + * Author: Jingoo Han <jg1.han@samsung.com> + */ + +#ifndef _PCIE_DESIGNWARE_H +#define _PCIE_DESIGNWARE_H + +#include <linux/bitfield.h> +#include <linux/dma-mapping.h> +#include <linux/irq.h> +#include <linux/msi.h> +#include <linux/pci.h> + +#include <linux/pci-epc.h> +#include <linux/pci-epf.h> + +/* DWC PCIe IP-core versions (native support since v4.70a) */ +#define DW_PCIE_VER_365A 0x3336352a +#define DW_PCIE_VER_460A 0x3436302a +#define DW_PCIE_VER_470A 0x3437302a +#define DW_PCIE_VER_480A 0x3438302a +#define DW_PCIE_VER_490A 0x3439302a +#define DW_PCIE_VER_520A 0x3532302a + +#define __dw_pcie_ver_cmp(_pci, _ver, _op) \ + ((_pci)->version _op DW_PCIE_VER_ ## _ver) + +#define dw_pcie_ver_is(_pci, _ver) __dw_pcie_ver_cmp(_pci, _ver, ==) + +#define dw_pcie_ver_is_ge(_pci, _ver) __dw_pcie_ver_cmp(_pci, _ver, >=) + +#define dw_pcie_ver_type_is(_pci, _ver, _type) \ + (__dw_pcie_ver_cmp(_pci, _ver, ==) && \ + __dw_pcie_ver_cmp(_pci, TYPE_ ## _type, ==)) + +#define dw_pcie_ver_type_is_ge(_pci, _ver, _type) \ + (__dw_pcie_ver_cmp(_pci, _ver, ==) && \ + __dw_pcie_ver_cmp(_pci, TYPE_ ## _type, >=)) + +/* Parameters for the waiting for link up routine */ +#define LINK_WAIT_MAX_RETRIES 10 +#define LINK_WAIT_USLEEP_MIN 90000 +#define LINK_WAIT_USLEEP_MAX 100000 + +/* Parameters for the waiting for iATU enabled routine */ +#define LINK_WAIT_MAX_IATU_RETRIES 5 +#define LINK_WAIT_IATU 9 + +/* Synopsys-specific PCIe configuration registers */ +#define PCIE_PORT_AFR 0x70C +#define PORT_AFR_N_FTS_MASK GENMASK(15, 8) +#define PORT_AFR_N_FTS(n) FIELD_PREP(PORT_AFR_N_FTS_MASK, n) +#define PORT_AFR_CC_N_FTS_MASK GENMASK(23, 16) +#define PORT_AFR_CC_N_FTS(n) FIELD_PREP(PORT_AFR_CC_N_FTS_MASK, n) +#define PORT_AFR_ENTER_ASPM BIT(30) +#define PORT_AFR_L0S_ENTRANCE_LAT_SHIFT 24 +#define PORT_AFR_L0S_ENTRANCE_LAT_MASK GENMASK(26, 24) +#define PORT_AFR_L1_ENTRANCE_LAT_SHIFT 27 +#define PORT_AFR_L1_ENTRANCE_LAT_MASK GENMASK(29, 27) + +#define PCIE_PORT_LINK_CONTROL 0x710 +#define PORT_LINK_DLL_LINK_EN BIT(5) +#define PORT_LINK_FAST_LINK_MODE BIT(7) +#define PORT_LINK_MODE_MASK GENMASK(21, 16) +#define PORT_LINK_MODE(n) FIELD_PREP(PORT_LINK_MODE_MASK, n) +#define PORT_LINK_MODE_1_LANES PORT_LINK_MODE(0x1) +#define PORT_LINK_MODE_2_LANES PORT_LINK_MODE(0x3) +#define PORT_LINK_MODE_4_LANES PORT_LINK_MODE(0x7) +#define PORT_LINK_MODE_8_LANES PORT_LINK_MODE(0xf) + +#define PCIE_PORT_DEBUG0 0x728 +#define PORT_LOGIC_LTSSM_STATE_MASK 0x1f +#define PORT_LOGIC_LTSSM_STATE_L0 0x11 +#define PCIE_PORT_DEBUG1 0x72C +#define PCIE_PORT_DEBUG1_LINK_UP BIT(4) +#define PCIE_PORT_DEBUG1_LINK_IN_TRAINING BIT(29) + +#define PCIE_LINK_WIDTH_SPEED_CONTROL 0x80C +#define PORT_LOGIC_N_FTS_MASK GENMASK(7, 0) +#define PORT_LOGIC_SPEED_CHANGE BIT(17) +#define PORT_LOGIC_LINK_WIDTH_MASK GENMASK(12, 8) +#define PORT_LOGIC_LINK_WIDTH(n) FIELD_PREP(PORT_LOGIC_LINK_WIDTH_MASK, n) +#define PORT_LOGIC_LINK_WIDTH_1_LANES PORT_LOGIC_LINK_WIDTH(0x1) +#define PORT_LOGIC_LINK_WIDTH_2_LANES PORT_LOGIC_LINK_WIDTH(0x2) +#define PORT_LOGIC_LINK_WIDTH_4_LANES PORT_LOGIC_LINK_WIDTH(0x4) +#define PORT_LOGIC_LINK_WIDTH_8_LANES PORT_LOGIC_LINK_WIDTH(0x8) + +#define PCIE_MSI_ADDR_LO 0x820 +#define PCIE_MSI_ADDR_HI 0x824 +#define PCIE_MSI_INTR0_ENABLE 0x828 +#define PCIE_MSI_INTR0_MASK 0x82C +#define PCIE_MSI_INTR0_STATUS 0x830 + +#define GEN3_RELATED_OFF 0x890 +#define GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL BIT(0) +#define GEN3_RELATED_OFF_RXEQ_RGRDLESS_RXTS BIT(13) +#define GEN3_RELATED_OFF_GEN3_EQ_DISABLE BIT(16) +#define GEN3_RELATED_OFF_RATE_SHADOW_SEL_SHIFT 24 +#define GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK GENMASK(25, 24) + +#define PCIE_PORT_MULTI_LANE_CTRL 0x8C0 +#define PORT_MLTI_UPCFG_SUPPORT BIT(7) + +#define PCIE_VERSION_NUMBER 0x8F8 +#define PCIE_VERSION_TYPE 0x8FC + +/* + * iATU inbound and outbound windows CSRs. Before the IP-core v4.80a each + * iATU region CSRs had been indirectly accessible by means of the dedicated + * viewport selector. The iATU/eDMA CSRs space was re-designed in DWC PCIe + * v4.80a in a way so the viewport was unrolled into the directly accessible + * iATU/eDMA CSRs space. + */ +#define PCIE_ATU_VIEWPORT 0x900 +#define PCIE_ATU_REGION_DIR_IB BIT(31) +#define PCIE_ATU_REGION_DIR_OB 0 +#define PCIE_ATU_VIEWPORT_BASE 0x904 +#define PCIE_ATU_UNROLL_BASE(dir, index) \ + (((index) << 9) | ((dir == PCIE_ATU_REGION_DIR_IB) ? BIT(8) : 0)) +#define PCIE_ATU_VIEWPORT_SIZE 0x2C +#define PCIE_ATU_REGION_CTRL1 0x000 +#define PCIE_ATU_INCREASE_REGION_SIZE BIT(13) +#define PCIE_ATU_TYPE_MEM 0x0 +#define PCIE_ATU_TYPE_IO 0x2 +#define PCIE_ATU_TYPE_CFG0 0x4 +#define PCIE_ATU_TYPE_CFG1 0x5 +#define PCIE_ATU_TD BIT(8) +#define PCIE_ATU_FUNC_NUM(pf) ((pf) << 20) +#define PCIE_ATU_REGION_CTRL2 0x004 +#define PCIE_ATU_ENABLE BIT(31) +#define PCIE_ATU_BAR_MODE_ENABLE BIT(30) +#define PCIE_ATU_FUNC_NUM_MATCH_EN BIT(19) +#define PCIE_ATU_LOWER_BASE 0x008 +#define PCIE_ATU_UPPER_BASE 0x00C +#define PCIE_ATU_LIMIT 0x010 +#define PCIE_ATU_LOWER_TARGET 0x014 +#define PCIE_ATU_BUS(x) FIELD_PREP(GENMASK(31, 24), x) +#define PCIE_ATU_DEV(x) FIELD_PREP(GENMASK(23, 19), x) +#define PCIE_ATU_FUNC(x) FIELD_PREP(GENMASK(18, 16), x) +#define PCIE_ATU_UPPER_TARGET 0x018 +#define PCIE_ATU_UPPER_LIMIT 0x020 + +#define PCIE_MISC_CONTROL_1_OFF 0x8BC +#define PCIE_DBI_RO_WR_EN BIT(0) + +#define PCIE_MSIX_DOORBELL 0x948 +#define PCIE_MSIX_DOORBELL_PF_SHIFT 24 + +#define PCIE_PL_CHK_REG_CONTROL_STATUS 0xB20 +#define PCIE_PL_CHK_REG_CHK_REG_START BIT(0) +#define PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS BIT(1) +#define PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR BIT(16) +#define PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR BIT(17) +#define PCIE_PL_CHK_REG_CHK_REG_COMPLETE BIT(18) + +#define PCIE_PL_CHK_REG_ERR_ADDR 0xB28 + +/* + * iATU Unroll-specific register definitions + * From 4.80 core version the address translation will be made by unroll + */ +#define PCIE_ATU_UNR_REGION_CTRL1 0x00 +#define PCIE_ATU_UNR_REGION_CTRL2 0x04 +#define PCIE_ATU_UNR_LOWER_BASE 0x08 +#define PCIE_ATU_UNR_UPPER_BASE 0x0C +#define PCIE_ATU_UNR_LOWER_LIMIT 0x10 +#define PCIE_ATU_UNR_LOWER_TARGET 0x14 +#define PCIE_ATU_UNR_UPPER_TARGET 0x18 +#define PCIE_ATU_UNR_UPPER_LIMIT 0x20 + +/* + * RAS-DES register definitions + */ +#define PCIE_RAS_DES_EVENT_COUNTER_CONTROL 0x8 +#define EVENT_COUNTER_ALL_CLEAR 0x3 +#define EVENT_COUNTER_ENABLE_ALL 0x7 +#define EVENT_COUNTER_ENABLE_SHIFT 2 +#define EVENT_COUNTER_EVENT_SEL_MASK GENMASK(7, 0) +#define EVENT_COUNTER_EVENT_SEL_SHIFT 16 +#define EVENT_COUNTER_EVENT_Tx_L0S 0x2 +#define EVENT_COUNTER_EVENT_Rx_L0S 0x3 +#define EVENT_COUNTER_EVENT_L1 0x5 +#define EVENT_COUNTER_EVENT_L1_1 0x7 +#define EVENT_COUNTER_EVENT_L1_2 0x8 +#define EVENT_COUNTER_GROUP_SEL_SHIFT 24 +#define EVENT_COUNTER_GROUP_5 0x5 + +#define PCIE_RAS_DES_EVENT_COUNTER_DATA 0xc + +/* + * The default address offset between dbi_base and atu_base. Root controller + * drivers are not required to initialize atu_base if the offset matches this + * default; the driver core automatically derives atu_base from dbi_base using + * this offset, if atu_base not set. + */ +#define DEFAULT_DBI_ATU_OFFSET (0x3 << 20) + +#define MAX_MSI_IRQS 256 +#define MAX_MSI_IRQS_PER_CTRL 32 +#define MAX_MSI_CTRLS (MAX_MSI_IRQS / MAX_MSI_IRQS_PER_CTRL) +#define MSI_REG_CTRL_BLOCK_SIZE 12 +#define MSI_DEF_NUM_VECTORS 32 + +/* Maximum number of inbound/outbound iATUs */ +#define MAX_IATU_IN 256 +#define MAX_IATU_OUT 256 + +struct dw_pcie; +struct dw_pcie_rp; +struct dw_pcie_ep; + +enum dw_pcie_device_mode { + DW_PCIE_UNKNOWN_TYPE, + DW_PCIE_EP_TYPE, + DW_PCIE_LEG_EP_TYPE, + DW_PCIE_RC_TYPE, +}; + +struct dw_pcie_host_ops { + int (*host_init)(struct dw_pcie_rp *pp); + void (*host_deinit)(struct dw_pcie_rp *pp); + int (*msi_host_init)(struct dw_pcie_rp *pp); +}; + +struct dw_pcie_rp { + bool has_msi_ctrl:1; + bool cfg0_io_shared:1; + u64 cfg0_base; + void __iomem *va_cfg0_base; + u32 cfg0_size; + resource_size_t io_base; + phys_addr_t io_bus_addr; + u32 io_size; + int irq; + const struct dw_pcie_host_ops *ops; + int msi_irq[MAX_MSI_CTRLS]; + struct irq_domain *irq_domain; + struct irq_domain *msi_domain; + dma_addr_t msi_data; + struct irq_chip *msi_irq_chip; + u32 num_vectors; + u32 irq_mask[MAX_MSI_CTRLS]; + struct pci_host_bridge *bridge; + raw_spinlock_t lock; + DECLARE_BITMAP(msi_irq_in_use, MAX_MSI_IRQS); +}; + +struct dw_pcie_ep_ops { + void (*ep_init)(struct dw_pcie_ep *ep); + int (*raise_irq)(struct dw_pcie_ep *ep, u8 func_no, + enum pci_epc_irq_type type, u16 interrupt_num); + const struct pci_epc_features* (*get_features)(struct dw_pcie_ep *ep); + /* + * Provide a method to implement the different func config space + * access for different platform, if different func have different + * offset, return the offset of func. if use write a register way + * return a 0, and implement code in callback function of platform + * driver. + */ + unsigned int (*func_conf_select)(struct dw_pcie_ep *ep, u8 func_no); +}; + +struct dw_pcie_ep_func { + struct list_head list; + u8 func_no; + u8 msi_cap; /* MSI capability offset */ + u8 msix_cap; /* MSI-X capability offset */ +}; + +struct dw_pcie_ep { + struct pci_epc *epc; + struct list_head func_list; + const struct dw_pcie_ep_ops *ops; + phys_addr_t phys_base; + size_t addr_size; + size_t page_size; + u8 bar_to_atu[PCI_STD_NUM_BARS]; + phys_addr_t *outbound_addr; + unsigned long *ib_window_map; + unsigned long *ob_window_map; + void __iomem *msi_mem; + phys_addr_t msi_mem_phys; + struct pci_epf_bar *epf_bar[PCI_STD_NUM_BARS]; +}; + +struct dw_pcie_ops { + u64 (*cpu_addr_fixup)(struct dw_pcie *pcie, u64 cpu_addr); + u32 (*read_dbi)(struct dw_pcie *pcie, void __iomem *base, u32 reg, + size_t size); + void (*write_dbi)(struct dw_pcie *pcie, void __iomem *base, u32 reg, + size_t size, u32 val); + void (*write_dbi2)(struct dw_pcie *pcie, void __iomem *base, u32 reg, + size_t size, u32 val); + int (*link_up)(struct dw_pcie *pcie); + int (*start_link)(struct dw_pcie *pcie); + void (*stop_link)(struct dw_pcie *pcie); +}; + +struct dw_pcie { + struct device *dev; + void __iomem *dbi_base; + void __iomem *dbi_base2; + void __iomem *atu_base; + size_t atu_size; + u32 num_ib_windows; + u32 num_ob_windows; + u32 region_align; + u64 region_limit; + struct dw_pcie_rp pp; + struct dw_pcie_ep ep; + const struct dw_pcie_ops *ops; + u32 version; + u32 type; + int num_lanes; + int link_gen; + u8 n_fts[2]; + bool iatu_unroll_enabled: 1; +}; + +#define to_dw_pcie_from_pp(port) container_of((port), struct dw_pcie, pp) + +#define to_dw_pcie_from_ep(endpoint) \ + container_of((endpoint), struct dw_pcie, ep) + +void dw_pcie_version_detect(struct dw_pcie *pci); + +u8 dw_pcie_find_capability(struct dw_pcie *pci, u8 cap); +u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap); + +int dw_pcie_read(void __iomem *addr, int size, u32 *val); +int dw_pcie_write(void __iomem *addr, int size, u32 val); + +u32 dw_pcie_read_dbi(struct dw_pcie *pci, u32 reg, size_t size); +void dw_pcie_write_dbi(struct dw_pcie *pci, u32 reg, size_t size, u32 val); +void dw_pcie_write_dbi2(struct dw_pcie *pci, u32 reg, size_t size, u32 val); +int dw_pcie_link_up(struct dw_pcie *pci); +void dw_pcie_upconfig_setup(struct dw_pcie *pci); +int dw_pcie_wait_for_link(struct dw_pcie *pci); +int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index, int type, + u64 cpu_addr, u64 pci_addr, u64 size); +int dw_pcie_prog_ep_outbound_atu(struct dw_pcie *pci, u8 func_no, int index, + int type, u64 cpu_addr, u64 pci_addr, u64 size); +int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, u8 func_no, int index, + int type, u64 cpu_addr, u8 bar); +void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index); +void dw_pcie_setup(struct dw_pcie *pci); +void dw_pcie_iatu_detect(struct dw_pcie *pci); + +static inline void dw_pcie_writel_dbi(struct dw_pcie *pci, u32 reg, u32 val) +{ + dw_pcie_write_dbi(pci, reg, 0x4, val); +} + +static inline u32 dw_pcie_readl_dbi(struct dw_pcie *pci, u32 reg) +{ + return dw_pcie_read_dbi(pci, reg, 0x4); +} + +static inline void dw_pcie_writew_dbi(struct dw_pcie *pci, u32 reg, u16 val) +{ + dw_pcie_write_dbi(pci, reg, 0x2, val); +} + +static inline u16 dw_pcie_readw_dbi(struct dw_pcie *pci, u32 reg) +{ + return dw_pcie_read_dbi(pci, reg, 0x2); +} + +static inline void dw_pcie_writeb_dbi(struct dw_pcie *pci, u32 reg, u8 val) +{ + dw_pcie_write_dbi(pci, reg, 0x1, val); +} + +static inline u8 dw_pcie_readb_dbi(struct dw_pcie *pci, u32 reg) +{ + return dw_pcie_read_dbi(pci, reg, 0x1); +} + +static inline void dw_pcie_writel_dbi2(struct dw_pcie *pci, u32 reg, u32 val) +{ + dw_pcie_write_dbi2(pci, reg, 0x4, val); +} + +static inline void dw_pcie_dbi_ro_wr_en(struct dw_pcie *pci) +{ + u32 reg; + u32 val; + + reg = PCIE_MISC_CONTROL_1_OFF; + val = dw_pcie_readl_dbi(pci, reg); + val |= PCIE_DBI_RO_WR_EN; + dw_pcie_writel_dbi(pci, reg, val); +} + +static inline void dw_pcie_dbi_ro_wr_dis(struct dw_pcie *pci) +{ + u32 reg; + u32 val; + + reg = PCIE_MISC_CONTROL_1_OFF; + val = dw_pcie_readl_dbi(pci, reg); + val &= ~PCIE_DBI_RO_WR_EN; + dw_pcie_writel_dbi(pci, reg, val); +} + +static inline int dw_pcie_start_link(struct dw_pcie *pci) +{ + if (pci->ops && pci->ops->start_link) + return pci->ops->start_link(pci); + + return 0; +} + +static inline void dw_pcie_stop_link(struct dw_pcie *pci) +{ + if (pci->ops && pci->ops->stop_link) + pci->ops->stop_link(pci); +} + +#ifdef CONFIG_PCIE_DW_HOST +irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp); +int dw_pcie_setup_rc(struct dw_pcie_rp *pp); +int dw_pcie_host_init(struct dw_pcie_rp *pp); +void dw_pcie_host_deinit(struct dw_pcie_rp *pp); +int dw_pcie_allocate_domains(struct dw_pcie_rp *pp); +void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, unsigned int devfn, + int where); +#else +static inline irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp) +{ + return IRQ_NONE; +} + +static inline int dw_pcie_setup_rc(struct dw_pcie_rp *pp) +{ + return 0; +} + +static inline int dw_pcie_host_init(struct dw_pcie_rp *pp) +{ + return 0; +} + +static inline void dw_pcie_host_deinit(struct dw_pcie_rp *pp) +{ +} + +static inline int dw_pcie_allocate_domains(struct dw_pcie_rp *pp) +{ + return 0; +} +static inline void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, + unsigned int devfn, + int where) +{ + return NULL; +} +#endif + +#ifdef CONFIG_PCIE_DW_EP +void dw_pcie_ep_linkup(struct dw_pcie_ep *ep); +int dw_pcie_ep_init(struct dw_pcie_ep *ep); +int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep); +void dw_pcie_ep_init_notify(struct dw_pcie_ep *ep); +void dw_pcie_ep_exit(struct dw_pcie_ep *ep); +int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no); +int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, + u8 interrupt_num); +int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, + u16 interrupt_num); +int dw_pcie_ep_raise_msix_irq_doorbell(struct dw_pcie_ep *ep, u8 func_no, + u16 interrupt_num); +void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar); +struct dw_pcie_ep_func * +dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no); +#else +static inline void dw_pcie_ep_linkup(struct dw_pcie_ep *ep) +{ +} + +static inline int dw_pcie_ep_init(struct dw_pcie_ep *ep) +{ + return 0; +} + +static inline int dw_pcie_ep_init_complete(struct dw_pcie_ep *ep) +{ + return 0; +} + +static inline void dw_pcie_ep_init_notify(struct dw_pcie_ep *ep) +{ +} + +static inline void dw_pcie_ep_exit(struct dw_pcie_ep *ep) +{ +} + +static inline int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no) +{ + return 0; +} + +static inline int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, + u8 interrupt_num) +{ + return 0; +} + +static inline int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, + u16 interrupt_num) +{ + return 0; +} + +static inline int dw_pcie_ep_raise_msix_irq_doorbell(struct dw_pcie_ep *ep, + u8 func_no, + u16 interrupt_num) +{ + return 0; +} + +static inline void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar) +{ +} + +static inline struct dw_pcie_ep_func * +dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no) +{ + return NULL; +} +#endif +#endif /* _PCIE_DESIGNWARE_H */ diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c new file mode 100644 index 000000000..c1e7653e5 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c @@ -0,0 +1,368 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Rockchip SoCs. + * + * Copyright (C) 2021 Rockchip Electronics Co., Ltd. + * http://www.rock-chips.com + * + * Author: Simon Xue <xxm@rock-chips.com> + */ + +#include <linux/clk.h> +#include <linux/gpio/consumer.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/of_irq.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/reset.h> + +#include "pcie-designware.h" + +/* + * The upper 16 bits of PCIE_CLIENT_CONFIG are a write + * mask for the lower 16 bits. + */ +#define HIWORD_UPDATE(mask, val) (((mask) << 16) | (val)) +#define HIWORD_UPDATE_BIT(val) HIWORD_UPDATE(val, val) +#define HIWORD_DISABLE_BIT(val) HIWORD_UPDATE(val, ~val) + +#define to_rockchip_pcie(x) dev_get_drvdata((x)->dev) + +#define PCIE_CLIENT_RC_MODE HIWORD_UPDATE_BIT(0x40) +#define PCIE_CLIENT_ENABLE_LTSSM HIWORD_UPDATE_BIT(0xc) +#define PCIE_SMLH_LINKUP BIT(16) +#define PCIE_RDLH_LINKUP BIT(17) +#define PCIE_LINKUP (PCIE_SMLH_LINKUP | PCIE_RDLH_LINKUP) +#define PCIE_L0S_ENTRY 0x11 +#define PCIE_CLIENT_GENERAL_CONTROL 0x0 +#define PCIE_CLIENT_INTR_STATUS_LEGACY 0x8 +#define PCIE_CLIENT_INTR_MASK_LEGACY 0x1c +#define PCIE_CLIENT_GENERAL_DEBUG 0x104 +#define PCIE_CLIENT_HOT_RESET_CTRL 0x180 +#define PCIE_CLIENT_LTSSM_STATUS 0x300 +#define PCIE_LTSSM_ENABLE_ENHANCE BIT(4) +#define PCIE_LTSSM_STATUS_MASK GENMASK(5, 0) + +struct rockchip_pcie { + struct dw_pcie pci; + void __iomem *apb_base; + struct phy *phy; + struct clk_bulk_data *clks; + unsigned int clk_cnt; + struct reset_control *rst; + struct gpio_desc *rst_gpio; + struct regulator *vpcie3v3; + struct irq_domain *irq_domain; +}; + +static int rockchip_pcie_readl_apb(struct rockchip_pcie *rockchip, + u32 reg) +{ + return readl_relaxed(rockchip->apb_base + reg); +} + +static void rockchip_pcie_writel_apb(struct rockchip_pcie *rockchip, + u32 val, u32 reg) +{ + writel_relaxed(val, rockchip->apb_base + reg); +} + +static void rockchip_pcie_legacy_int_handler(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct rockchip_pcie *rockchip = irq_desc_get_handler_data(desc); + unsigned long reg, hwirq; + + chained_irq_enter(chip, desc); + + reg = rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_INTR_STATUS_LEGACY); + + for_each_set_bit(hwirq, ®, 4) + generic_handle_domain_irq(rockchip->irq_domain, hwirq); + + chained_irq_exit(chip, desc); +} + +static void rockchip_intx_mask(struct irq_data *data) +{ + rockchip_pcie_writel_apb(irq_data_get_irq_chip_data(data), + HIWORD_UPDATE_BIT(BIT(data->hwirq)), + PCIE_CLIENT_INTR_MASK_LEGACY); +}; + +static void rockchip_intx_unmask(struct irq_data *data) +{ + rockchip_pcie_writel_apb(irq_data_get_irq_chip_data(data), + HIWORD_DISABLE_BIT(BIT(data->hwirq)), + PCIE_CLIENT_INTR_MASK_LEGACY); +}; + +static struct irq_chip rockchip_intx_irq_chip = { + .name = "INTx", + .irq_mask = rockchip_intx_mask, + .irq_unmask = rockchip_intx_unmask, + .flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, +}; + +static int rockchip_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &rockchip_intx_irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops intx_domain_ops = { + .map = rockchip_pcie_intx_map, +}; + +static int rockchip_pcie_init_irq_domain(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->pci.dev; + struct device_node *intc; + + intc = of_get_child_by_name(dev->of_node, "legacy-interrupt-controller"); + if (!intc) { + dev_err(dev, "missing child interrupt-controller node\n"); + return -EINVAL; + } + + rockchip->irq_domain = irq_domain_add_linear(intc, PCI_NUM_INTX, + &intx_domain_ops, rockchip); + of_node_put(intc); + if (!rockchip->irq_domain) { + dev_err(dev, "failed to get a INTx IRQ domain\n"); + return -EINVAL; + } + + return 0; +} + +static void rockchip_pcie_enable_ltssm(struct rockchip_pcie *rockchip) +{ + rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_ENABLE_LTSSM, + PCIE_CLIENT_GENERAL_CONTROL); +} + +static int rockchip_pcie_link_up(struct dw_pcie *pci) +{ + struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); + u32 val = rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_LTSSM_STATUS); + + if ((val & PCIE_LINKUP) == PCIE_LINKUP && + (val & PCIE_LTSSM_STATUS_MASK) == PCIE_L0S_ENTRY) + return 1; + + return 0; +} + +static int rockchip_pcie_start_link(struct dw_pcie *pci) +{ + struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); + + /* Reset device */ + gpiod_set_value_cansleep(rockchip->rst_gpio, 0); + + rockchip_pcie_enable_ltssm(rockchip); + + /* + * PCIe requires the refclk to be stable for 100µs prior to releasing + * PERST. See table 2-4 in section 2.6.2 AC Specifications of the PCI + * Express Card Electromechanical Specification, 1.1. However, we don't + * know if the refclk is coming from RC's PHY or external OSC. If it's + * from RC, so enabling LTSSM is the just right place to release #PERST. + * We need more extra time as before, rather than setting just + * 100us as we don't know how long should the device need to reset. + */ + msleep(100); + gpiod_set_value_cansleep(rockchip->rst_gpio, 1); + + return 0; +} + +static int rockchip_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); + struct device *dev = rockchip->pci.dev; + u32 val = HIWORD_UPDATE_BIT(PCIE_LTSSM_ENABLE_ENHANCE); + int irq, ret; + + irq = of_irq_get_byname(dev->of_node, "legacy"); + if (irq < 0) + return irq; + + ret = rockchip_pcie_init_irq_domain(rockchip); + if (ret < 0) + dev_err(dev, "failed to init irq domain\n"); + + irq_set_chained_handler_and_data(irq, rockchip_pcie_legacy_int_handler, + rockchip); + + /* LTSSM enable control mode */ + rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_HOT_RESET_CTRL); + + rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_RC_MODE, + PCIE_CLIENT_GENERAL_CONTROL); + + return 0; +} + +static const struct dw_pcie_host_ops rockchip_pcie_host_ops = { + .host_init = rockchip_pcie_host_init, +}; + +static int rockchip_pcie_clk_init(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->pci.dev; + int ret; + + ret = devm_clk_bulk_get_all(dev, &rockchip->clks); + if (ret < 0) + return ret; + + rockchip->clk_cnt = ret; + + return clk_bulk_prepare_enable(rockchip->clk_cnt, rockchip->clks); +} + +static int rockchip_pcie_resource_get(struct platform_device *pdev, + struct rockchip_pcie *rockchip) +{ + rockchip->apb_base = devm_platform_ioremap_resource_byname(pdev, "apb"); + if (IS_ERR(rockchip->apb_base)) + return PTR_ERR(rockchip->apb_base); + + rockchip->rst_gpio = devm_gpiod_get_optional(&pdev->dev, "reset", + GPIOD_OUT_HIGH); + if (IS_ERR(rockchip->rst_gpio)) + return PTR_ERR(rockchip->rst_gpio); + + rockchip->rst = devm_reset_control_array_get_exclusive(&pdev->dev); + if (IS_ERR(rockchip->rst)) + return dev_err_probe(&pdev->dev, PTR_ERR(rockchip->rst), + "failed to get reset lines\n"); + + return 0; +} + +static int rockchip_pcie_phy_init(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->pci.dev; + int ret; + + rockchip->phy = devm_phy_get(dev, "pcie-phy"); + if (IS_ERR(rockchip->phy)) + return dev_err_probe(dev, PTR_ERR(rockchip->phy), + "missing PHY\n"); + + ret = phy_init(rockchip->phy); + if (ret < 0) + return ret; + + ret = phy_power_on(rockchip->phy); + if (ret) + phy_exit(rockchip->phy); + + return ret; +} + +static void rockchip_pcie_phy_deinit(struct rockchip_pcie *rockchip) +{ + phy_exit(rockchip->phy); + phy_power_off(rockchip->phy); +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .link_up = rockchip_pcie_link_up, + .start_link = rockchip_pcie_start_link, +}; + +static int rockchip_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rockchip_pcie *rockchip; + struct dw_pcie_rp *pp; + int ret; + + rockchip = devm_kzalloc(dev, sizeof(*rockchip), GFP_KERNEL); + if (!rockchip) + return -ENOMEM; + + platform_set_drvdata(pdev, rockchip); + + rockchip->pci.dev = dev; + rockchip->pci.ops = &dw_pcie_ops; + + pp = &rockchip->pci.pp; + pp->ops = &rockchip_pcie_host_ops; + + ret = rockchip_pcie_resource_get(pdev, rockchip); + if (ret) + return ret; + + ret = reset_control_assert(rockchip->rst); + if (ret) + return ret; + + /* DON'T MOVE ME: must be enable before PHY init */ + rockchip->vpcie3v3 = devm_regulator_get_optional(dev, "vpcie3v3"); + if (IS_ERR(rockchip->vpcie3v3)) { + if (PTR_ERR(rockchip->vpcie3v3) != -ENODEV) + return dev_err_probe(dev, PTR_ERR(rockchip->vpcie3v3), + "failed to get vpcie3v3 regulator\n"); + rockchip->vpcie3v3 = NULL; + } else { + ret = regulator_enable(rockchip->vpcie3v3); + if (ret) { + dev_err(dev, "failed to enable vpcie3v3 regulator\n"); + return ret; + } + } + + ret = rockchip_pcie_phy_init(rockchip); + if (ret) + goto disable_regulator; + + ret = reset_control_deassert(rockchip->rst); + if (ret) + goto deinit_phy; + + ret = rockchip_pcie_clk_init(rockchip); + if (ret) + goto deinit_phy; + + ret = dw_pcie_host_init(pp); + if (!ret) + return 0; + + clk_bulk_disable_unprepare(rockchip->clk_cnt, rockchip->clks); +deinit_phy: + rockchip_pcie_phy_deinit(rockchip); +disable_regulator: + if (rockchip->vpcie3v3) + regulator_disable(rockchip->vpcie3v3); + + return ret; +} + +static const struct of_device_id rockchip_pcie_of_match[] = { + { .compatible = "rockchip,rk3568-pcie", }, + {}, +}; + +static struct platform_driver rockchip_pcie_driver = { + .driver = { + .name = "rockchip-dw-pcie", + .of_match_table = rockchip_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = rockchip_pcie_probe, +}; +builtin_platform_driver(rockchip_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-fu740.c b/drivers/pci/controller/dwc/pcie-fu740.c new file mode 100644 index 000000000..1e9b44b8b --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-fu740.c @@ -0,0 +1,357 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * FU740 DesignWare PCIe Controller integration + * Copyright (C) 2019-2021 SiFive, Inc. + * Paul Walmsley + * Greentime Hu + * + * Based in part on the i.MX6 PCIe host controller shim which is: + * + * Copyright (C) 2013 Kosagi + * https://www.kosagi.com + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio.h> +#include <linux/gpio/consumer.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/types.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/reset.h> + +#include "pcie-designware.h" + +#define to_fu740_pcie(x) dev_get_drvdata((x)->dev) + +struct fu740_pcie { + struct dw_pcie pci; + void __iomem *mgmt_base; + struct gpio_desc *reset; + struct gpio_desc *pwren; + struct clk *pcie_aux; + struct reset_control *rst; +}; + +#define SIFIVE_DEVICESRESETREG 0x28 + +#define PCIEX8MGMT_PERST_N 0x0 +#define PCIEX8MGMT_APP_LTSSM_ENABLE 0x10 +#define PCIEX8MGMT_APP_HOLD_PHY_RST 0x18 +#define PCIEX8MGMT_DEVICE_TYPE 0x708 +#define PCIEX8MGMT_PHY0_CR_PARA_ADDR 0x860 +#define PCIEX8MGMT_PHY0_CR_PARA_RD_EN 0x870 +#define PCIEX8MGMT_PHY0_CR_PARA_RD_DATA 0x878 +#define PCIEX8MGMT_PHY0_CR_PARA_SEL 0x880 +#define PCIEX8MGMT_PHY0_CR_PARA_WR_DATA 0x888 +#define PCIEX8MGMT_PHY0_CR_PARA_WR_EN 0x890 +#define PCIEX8MGMT_PHY0_CR_PARA_ACK 0x898 +#define PCIEX8MGMT_PHY1_CR_PARA_ADDR 0x8a0 +#define PCIEX8MGMT_PHY1_CR_PARA_RD_EN 0x8b0 +#define PCIEX8MGMT_PHY1_CR_PARA_RD_DATA 0x8b8 +#define PCIEX8MGMT_PHY1_CR_PARA_SEL 0x8c0 +#define PCIEX8MGMT_PHY1_CR_PARA_WR_DATA 0x8c8 +#define PCIEX8MGMT_PHY1_CR_PARA_WR_EN 0x8d0 +#define PCIEX8MGMT_PHY1_CR_PARA_ACK 0x8d8 + +#define PCIEX8MGMT_PHY_CDR_TRACK_EN BIT(0) +#define PCIEX8MGMT_PHY_LOS_THRSHLD BIT(5) +#define PCIEX8MGMT_PHY_TERM_EN BIT(9) +#define PCIEX8MGMT_PHY_TERM_ACDC BIT(10) +#define PCIEX8MGMT_PHY_EN BIT(11) +#define PCIEX8MGMT_PHY_INIT_VAL (PCIEX8MGMT_PHY_CDR_TRACK_EN|\ + PCIEX8MGMT_PHY_LOS_THRSHLD|\ + PCIEX8MGMT_PHY_TERM_EN|\ + PCIEX8MGMT_PHY_TERM_ACDC|\ + PCIEX8MGMT_PHY_EN) + +#define PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 0x1008 +#define PCIEX8MGMT_PHY_LANE_OFF 0x100 +#define PCIEX8MGMT_PHY_LANE0_BASE (PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 0) +#define PCIEX8MGMT_PHY_LANE1_BASE (PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 1) +#define PCIEX8MGMT_PHY_LANE2_BASE (PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 2) +#define PCIEX8MGMT_PHY_LANE3_BASE (PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 3) + +static void fu740_pcie_assert_reset(struct fu740_pcie *afp) +{ + /* Assert PERST_N GPIO */ + gpiod_set_value_cansleep(afp->reset, 0); + /* Assert controller PERST_N */ + writel_relaxed(0x0, afp->mgmt_base + PCIEX8MGMT_PERST_N); +} + +static void fu740_pcie_deassert_reset(struct fu740_pcie *afp) +{ + /* Deassert controller PERST_N */ + writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_PERST_N); + /* Deassert PERST_N GPIO */ + gpiod_set_value_cansleep(afp->reset, 1); +} + +static void fu740_pcie_power_on(struct fu740_pcie *afp) +{ + gpiod_set_value_cansleep(afp->pwren, 1); + /* + * Ensure that PERST has been asserted for at least 100 ms. + * Section 2.2 of PCI Express Card Electromechanical Specification + * Revision 3.0 + */ + msleep(100); +} + +static void fu740_pcie_drive_reset(struct fu740_pcie *afp) +{ + fu740_pcie_assert_reset(afp); + fu740_pcie_power_on(afp); + fu740_pcie_deassert_reset(afp); +} + +static void fu740_phyregwrite(const uint8_t phy, const uint16_t addr, + const uint16_t wrdata, struct fu740_pcie *afp) +{ + struct device *dev = afp->pci.dev; + void __iomem *phy_cr_para_addr; + void __iomem *phy_cr_para_wr_data; + void __iomem *phy_cr_para_wr_en; + void __iomem *phy_cr_para_ack; + int ret, val; + + /* Setup */ + if (phy) { + phy_cr_para_addr = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_ADDR; + phy_cr_para_wr_data = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_WR_DATA; + phy_cr_para_wr_en = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_WR_EN; + phy_cr_para_ack = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_ACK; + } else { + phy_cr_para_addr = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_ADDR; + phy_cr_para_wr_data = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_WR_DATA; + phy_cr_para_wr_en = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_WR_EN; + phy_cr_para_ack = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_ACK; + } + + writel_relaxed(addr, phy_cr_para_addr); + writel_relaxed(wrdata, phy_cr_para_wr_data); + writel_relaxed(1, phy_cr_para_wr_en); + + /* Wait for wait_idle */ + ret = readl_poll_timeout(phy_cr_para_ack, val, val, 10, 5000); + if (ret) + dev_warn(dev, "Wait for wait_idle state failed!\n"); + + /* Clear */ + writel_relaxed(0, phy_cr_para_wr_en); + + /* Wait for ~wait_idle */ + ret = readl_poll_timeout(phy_cr_para_ack, val, !val, 10, 5000); + if (ret) + dev_warn(dev, "Wait for !wait_idle state failed!\n"); +} + +static void fu740_pcie_init_phy(struct fu740_pcie *afp) +{ + /* Enable phy cr_para_sel interfaces */ + writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_SEL); + writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_SEL); + + /* + * Wait 10 cr_para cycles to guarantee that the registers are ready + * to be edited. + */ + ndelay(10); + + /* Set PHY AC termination mode */ + fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE0_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE1_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE2_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE3_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE0_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE1_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE2_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); + fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE3_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp); +} + +static int fu740_pcie_start_link(struct dw_pcie *pci) +{ + struct device *dev = pci->dev; + struct fu740_pcie *afp = dev_get_drvdata(dev); + u8 cap_exp = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + int ret; + u32 orig, tmp; + + /* + * Force 2.5GT/s when starting the link, due to some devices not + * probing at higher speeds. This happens with the PCIe switch + * on the Unmatched board when U-Boot has not initialised the PCIe. + * The fix in U-Boot is to force 2.5GT/s, which then gets cleared + * by the soft reset done by this driver. + */ + dev_dbg(dev, "cap_exp at %x\n", cap_exp); + dw_pcie_dbi_ro_wr_en(pci); + + tmp = dw_pcie_readl_dbi(pci, cap_exp + PCI_EXP_LNKCAP); + orig = tmp & PCI_EXP_LNKCAP_SLS; + tmp &= ~PCI_EXP_LNKCAP_SLS; + tmp |= PCI_EXP_LNKCAP_SLS_2_5GB; + dw_pcie_writel_dbi(pci, cap_exp + PCI_EXP_LNKCAP, tmp); + + /* Enable LTSSM */ + writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_APP_LTSSM_ENABLE); + + ret = dw_pcie_wait_for_link(pci); + if (ret) { + dev_err(dev, "error: link did not start\n"); + goto err; + } + + tmp = dw_pcie_readl_dbi(pci, cap_exp + PCI_EXP_LNKCAP); + if ((tmp & PCI_EXP_LNKCAP_SLS) != orig) { + dev_dbg(dev, "changing speed back to original\n"); + + tmp &= ~PCI_EXP_LNKCAP_SLS; + tmp |= orig; + dw_pcie_writel_dbi(pci, cap_exp + PCI_EXP_LNKCAP, tmp); + + tmp = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + tmp |= PORT_LOGIC_SPEED_CHANGE; + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, tmp); + + ret = dw_pcie_wait_for_link(pci); + if (ret) { + dev_err(dev, "error: link did not start at new speed\n"); + goto err; + } + } + + ret = 0; +err: + WARN_ON(ret); /* we assume that errors will be very rare */ + dw_pcie_dbi_ro_wr_dis(pci); + return ret; +} + +static int fu740_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct fu740_pcie *afp = to_fu740_pcie(pci); + struct device *dev = pci->dev; + int ret; + + /* Power on reset */ + fu740_pcie_drive_reset(afp); + + /* Enable pcieauxclk */ + ret = clk_prepare_enable(afp->pcie_aux); + if (ret) { + dev_err(dev, "unable to enable pcie_aux clock\n"); + return ret; + } + + /* + * Assert hold_phy_rst (hold the controller LTSSM in reset after + * power_up_rst_n for register programming with cr_para) + */ + writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_APP_HOLD_PHY_RST); + + /* Deassert power_up_rst_n */ + ret = reset_control_deassert(afp->rst); + if (ret) { + dev_err(dev, "unable to deassert pcie_power_up_rst_n\n"); + return ret; + } + + fu740_pcie_init_phy(afp); + + /* Disable pcieauxclk */ + clk_disable_unprepare(afp->pcie_aux); + /* Clear hold_phy_rst */ + writel_relaxed(0x0, afp->mgmt_base + PCIEX8MGMT_APP_HOLD_PHY_RST); + /* Enable pcieauxclk */ + clk_prepare_enable(afp->pcie_aux); + /* Set RC mode */ + writel_relaxed(0x4, afp->mgmt_base + PCIEX8MGMT_DEVICE_TYPE); + + return 0; +} + +static const struct dw_pcie_host_ops fu740_pcie_host_ops = { + .host_init = fu740_pcie_host_init, +}; + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = fu740_pcie_start_link, +}; + +static int fu740_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci; + struct fu740_pcie *afp; + + afp = devm_kzalloc(dev, sizeof(*afp), GFP_KERNEL); + if (!afp) + return -ENOMEM; + pci = &afp->pci; + pci->dev = dev; + pci->ops = &dw_pcie_ops; + pci->pp.ops = &fu740_pcie_host_ops; + pci->pp.num_vectors = MAX_MSI_IRQS; + + /* SiFive specific region: mgmt */ + afp->mgmt_base = devm_platform_ioremap_resource_byname(pdev, "mgmt"); + if (IS_ERR(afp->mgmt_base)) + return PTR_ERR(afp->mgmt_base); + + /* Fetch GPIOs */ + afp->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(afp->reset)) + return dev_err_probe(dev, PTR_ERR(afp->reset), "unable to get reset-gpios\n"); + + afp->pwren = devm_gpiod_get_optional(dev, "pwren", GPIOD_OUT_LOW); + if (IS_ERR(afp->pwren)) + return dev_err_probe(dev, PTR_ERR(afp->pwren), "unable to get pwren-gpios\n"); + + /* Fetch clocks */ + afp->pcie_aux = devm_clk_get(dev, "pcie_aux"); + if (IS_ERR(afp->pcie_aux)) + return dev_err_probe(dev, PTR_ERR(afp->pcie_aux), + "pcie_aux clock source missing or invalid\n"); + + /* Fetch reset */ + afp->rst = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(afp->rst)) + return dev_err_probe(dev, PTR_ERR(afp->rst), "unable to get reset\n"); + + platform_set_drvdata(pdev, afp); + + return dw_pcie_host_init(&pci->pp); +} + +static void fu740_pcie_shutdown(struct platform_device *pdev) +{ + struct fu740_pcie *afp = platform_get_drvdata(pdev); + + /* Bring down link, so bootloader gets clean state in case of reboot */ + fu740_pcie_assert_reset(afp); +} + +static const struct of_device_id fu740_pcie_of_match[] = { + { .compatible = "sifive,fu740-pcie", }, + {}, +}; + +static struct platform_driver fu740_pcie_driver = { + .driver = { + .name = "fu740-pcie", + .of_match_table = fu740_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = fu740_pcie_probe, + .shutdown = fu740_pcie_shutdown, +}; + +builtin_platform_driver(fu740_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-hisi.c b/drivers/pci/controller/dwc/pcie-hisi.c new file mode 100644 index 000000000..8904b5b85 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-hisi.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for HiSilicon SoCs + * + * Copyright (C) 2015 HiSilicon Co., Ltd. http://www.hisilicon.com + * + * Authors: Zhou Wang <wangzhou1@hisilicon.com> + * Dacai Zhu <zhudacai@hisilicon.com> + * Gabriele Paoloni <gabriele.paoloni@huawei.com> + */ +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/platform_device.h> +#include <linux/pci.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> +#include "../../pci.h" + +#if defined(CONFIG_PCI_HISI) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)) + +struct hisi_pcie { + void __iomem *reg_base; +}; + +static int hisi_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, + int size, u32 *val) +{ + struct pci_config_window *cfg = bus->sysdata; + int dev = PCI_SLOT(devfn); + + if (bus->number == cfg->busr.start) { + /* access only one slot on each root port */ + if (dev > 0) + return PCIBIOS_DEVICE_NOT_FOUND; + else + return pci_generic_config_read32(bus, devfn, where, + size, val); + } + + return pci_generic_config_read(bus, devfn, where, size, val); +} + +static int hisi_pcie_wr_conf(struct pci_bus *bus, u32 devfn, + int where, int size, u32 val) +{ + struct pci_config_window *cfg = bus->sysdata; + int dev = PCI_SLOT(devfn); + + if (bus->number == cfg->busr.start) { + /* access only one slot on each root port */ + if (dev > 0) + return PCIBIOS_DEVICE_NOT_FOUND; + else + return pci_generic_config_write32(bus, devfn, where, + size, val); + } + + return pci_generic_config_write(bus, devfn, where, size, val); +} + +static void __iomem *hisi_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) +{ + struct pci_config_window *cfg = bus->sysdata; + struct hisi_pcie *pcie = cfg->priv; + + if (bus->number == cfg->busr.start) + return pcie->reg_base + where; + else + return pci_ecam_map_bus(bus, devfn, where); +} + +#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) + +static int hisi_pcie_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct hisi_pcie *pcie; + struct acpi_device *adev = to_acpi_device(dev); + struct acpi_pci_root *root = acpi_driver_data(adev); + struct resource *res; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + /* + * Retrieve RC base and size from a HISI0081 device with _UID + * matching our segment. + */ + res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL); + if (!res) + return -ENOMEM; + + ret = acpi_get_rc_resources(dev, "HISI0081", root->segment, res); + if (ret) { + dev_err(dev, "can't get rc base address\n"); + return -ENOMEM; + } + + pcie->reg_base = devm_pci_remap_cfgspace(dev, res->start, resource_size(res)); + if (!pcie->reg_base) + return -ENOMEM; + + cfg->priv = pcie; + return 0; +} + +const struct pci_ecam_ops hisi_pcie_ops = { + .init = hisi_pcie_init, + .pci_ops = { + .map_bus = hisi_pcie_map_bus, + .read = hisi_pcie_rd_conf, + .write = hisi_pcie_wr_conf, + } +}; + +#endif + +#ifdef CONFIG_PCI_HISI + +static int hisi_pcie_platform_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct hisi_pcie *pcie; + struct platform_device *pdev = to_platform_device(dev); + struct resource *res; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!res) { + dev_err(dev, "missing \"reg[1]\"property\n"); + return -EINVAL; + } + + pcie->reg_base = devm_pci_remap_cfgspace(dev, res->start, resource_size(res)); + if (!pcie->reg_base) + return -ENOMEM; + + cfg->priv = pcie; + return 0; +} + +static const struct pci_ecam_ops hisi_pcie_platform_ops = { + .init = hisi_pcie_platform_init, + .pci_ops = { + .map_bus = hisi_pcie_map_bus, + .read = hisi_pcie_rd_conf, + .write = hisi_pcie_wr_conf, + } +}; + +static const struct of_device_id hisi_pcie_almost_ecam_of_match[] = { + { + .compatible = "hisilicon,hip06-pcie-ecam", + .data = &hisi_pcie_platform_ops, + }, + { + .compatible = "hisilicon,hip07-pcie-ecam", + .data = &hisi_pcie_platform_ops, + }, + {}, +}; + +static struct platform_driver hisi_pcie_almost_ecam_driver = { + .probe = pci_host_common_probe, + .driver = { + .name = "hisi-pcie-almost-ecam", + .of_match_table = hisi_pcie_almost_ecam_of_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver(hisi_pcie_almost_ecam_driver); + +#endif +#endif diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c new file mode 100644 index 000000000..e2b80f100 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-histb.c @@ -0,0 +1,454 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for HiSilicon STB SoCs + * + * Copyright (C) 2016-2017 HiSilicon Co., Ltd. http://www.hisilicon.com + * + * Authors: Ruqiang Ju <juruqiang@hisilicon.com> + * Jianguo Sun <sunjianguo1@huawei.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_gpio.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/reset.h> + +#include "pcie-designware.h" + +#define to_histb_pcie(x) dev_get_drvdata((x)->dev) + +#define PCIE_SYS_CTRL0 0x0000 +#define PCIE_SYS_CTRL1 0x0004 +#define PCIE_SYS_CTRL7 0x001C +#define PCIE_SYS_CTRL13 0x0034 +#define PCIE_SYS_CTRL15 0x003C +#define PCIE_SYS_CTRL16 0x0040 +#define PCIE_SYS_CTRL17 0x0044 + +#define PCIE_SYS_STAT0 0x0100 +#define PCIE_SYS_STAT4 0x0110 + +#define PCIE_RDLH_LINK_UP BIT(5) +#define PCIE_XMLH_LINK_UP BIT(15) +#define PCIE_ELBI_SLV_DBI_ENABLE BIT(21) +#define PCIE_APP_LTSSM_ENABLE BIT(11) + +#define PCIE_DEVICE_TYPE_MASK GENMASK(31, 28) +#define PCIE_WM_EP 0 +#define PCIE_WM_LEGACY BIT(1) +#define PCIE_WM_RC BIT(30) + +#define PCIE_LTSSM_STATE_MASK GENMASK(5, 0) +#define PCIE_LTSSM_STATE_ACTIVE 0x11 + +struct histb_pcie { + struct dw_pcie *pci; + struct clk *aux_clk; + struct clk *pipe_clk; + struct clk *sys_clk; + struct clk *bus_clk; + struct phy *phy; + struct reset_control *soft_reset; + struct reset_control *sys_reset; + struct reset_control *bus_reset; + void __iomem *ctrl; + int reset_gpio; + struct regulator *vpcie; +}; + +static u32 histb_pcie_readl(struct histb_pcie *histb_pcie, u32 reg) +{ + return readl(histb_pcie->ctrl + reg); +} + +static void histb_pcie_writel(struct histb_pcie *histb_pcie, u32 reg, u32 val) +{ + writel(val, histb_pcie->ctrl + reg); +} + +static void histb_pcie_dbi_w_mode(struct dw_pcie_rp *pp, bool enable) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct histb_pcie *hipcie = to_histb_pcie(pci); + u32 val; + + val = histb_pcie_readl(hipcie, PCIE_SYS_CTRL0); + if (enable) + val |= PCIE_ELBI_SLV_DBI_ENABLE; + else + val &= ~PCIE_ELBI_SLV_DBI_ENABLE; + histb_pcie_writel(hipcie, PCIE_SYS_CTRL0, val); +} + +static void histb_pcie_dbi_r_mode(struct dw_pcie_rp *pp, bool enable) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct histb_pcie *hipcie = to_histb_pcie(pci); + u32 val; + + val = histb_pcie_readl(hipcie, PCIE_SYS_CTRL1); + if (enable) + val |= PCIE_ELBI_SLV_DBI_ENABLE; + else + val &= ~PCIE_ELBI_SLV_DBI_ENABLE; + histb_pcie_writel(hipcie, PCIE_SYS_CTRL1, val); +} + +static u32 histb_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, + u32 reg, size_t size) +{ + u32 val; + + histb_pcie_dbi_r_mode(&pci->pp, true); + dw_pcie_read(base + reg, size, &val); + histb_pcie_dbi_r_mode(&pci->pp, false); + + return val; +} + +static void histb_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, + u32 reg, size_t size, u32 val) +{ + histb_pcie_dbi_w_mode(&pci->pp, true); + dw_pcie_write(base + reg, size, val); + histb_pcie_dbi_w_mode(&pci->pp, false); +} + +static int histb_pcie_rd_own_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); + + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + *val = dw_pcie_read_dbi(pci, where, size); + return PCIBIOS_SUCCESSFUL; +} + +static int histb_pcie_wr_own_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); + + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + dw_pcie_write_dbi(pci, where, size, val); + return PCIBIOS_SUCCESSFUL; +} + +static struct pci_ops histb_pci_ops = { + .read = histb_pcie_rd_own_conf, + .write = histb_pcie_wr_own_conf, +}; + +static int histb_pcie_link_up(struct dw_pcie *pci) +{ + struct histb_pcie *hipcie = to_histb_pcie(pci); + u32 regval; + u32 status; + + regval = histb_pcie_readl(hipcie, PCIE_SYS_STAT0); + status = histb_pcie_readl(hipcie, PCIE_SYS_STAT4); + status &= PCIE_LTSSM_STATE_MASK; + if ((regval & PCIE_XMLH_LINK_UP) && (regval & PCIE_RDLH_LINK_UP) && + (status == PCIE_LTSSM_STATE_ACTIVE)) + return 1; + + return 0; +} + +static int histb_pcie_start_link(struct dw_pcie *pci) +{ + struct histb_pcie *hipcie = to_histb_pcie(pci); + u32 regval; + + /* assert LTSSM enable */ + regval = histb_pcie_readl(hipcie, PCIE_SYS_CTRL7); + regval |= PCIE_APP_LTSSM_ENABLE; + histb_pcie_writel(hipcie, PCIE_SYS_CTRL7, regval); + + return 0; +} + +static int histb_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct histb_pcie *hipcie = to_histb_pcie(pci); + u32 regval; + + pp->bridge->ops = &histb_pci_ops; + + /* PCIe RC work mode */ + regval = histb_pcie_readl(hipcie, PCIE_SYS_CTRL0); + regval &= ~PCIE_DEVICE_TYPE_MASK; + regval |= PCIE_WM_RC; + histb_pcie_writel(hipcie, PCIE_SYS_CTRL0, regval); + + return 0; +} + +static const struct dw_pcie_host_ops histb_pcie_host_ops = { + .host_init = histb_pcie_host_init, +}; + +static void histb_pcie_host_disable(struct histb_pcie *hipcie) +{ + reset_control_assert(hipcie->soft_reset); + reset_control_assert(hipcie->sys_reset); + reset_control_assert(hipcie->bus_reset); + + clk_disable_unprepare(hipcie->aux_clk); + clk_disable_unprepare(hipcie->pipe_clk); + clk_disable_unprepare(hipcie->sys_clk); + clk_disable_unprepare(hipcie->bus_clk); + + if (gpio_is_valid(hipcie->reset_gpio)) + gpio_set_value_cansleep(hipcie->reset_gpio, 0); + + if (hipcie->vpcie) + regulator_disable(hipcie->vpcie); +} + +static int histb_pcie_host_enable(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct histb_pcie *hipcie = to_histb_pcie(pci); + struct device *dev = pci->dev; + int ret; + + /* power on PCIe device if have */ + if (hipcie->vpcie) { + ret = regulator_enable(hipcie->vpcie); + if (ret) { + dev_err(dev, "failed to enable regulator: %d\n", ret); + return ret; + } + } + + if (gpio_is_valid(hipcie->reset_gpio)) + gpio_set_value_cansleep(hipcie->reset_gpio, 1); + + ret = clk_prepare_enable(hipcie->bus_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable bus clk\n"); + goto err_bus_clk; + } + + ret = clk_prepare_enable(hipcie->sys_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable sys clk\n"); + goto err_sys_clk; + } + + ret = clk_prepare_enable(hipcie->pipe_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable pipe clk\n"); + goto err_pipe_clk; + } + + ret = clk_prepare_enable(hipcie->aux_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable aux clk\n"); + goto err_aux_clk; + } + + reset_control_assert(hipcie->soft_reset); + reset_control_deassert(hipcie->soft_reset); + + reset_control_assert(hipcie->sys_reset); + reset_control_deassert(hipcie->sys_reset); + + reset_control_assert(hipcie->bus_reset); + reset_control_deassert(hipcie->bus_reset); + + return 0; + +err_aux_clk: + clk_disable_unprepare(hipcie->pipe_clk); +err_pipe_clk: + clk_disable_unprepare(hipcie->sys_clk); +err_sys_clk: + clk_disable_unprepare(hipcie->bus_clk); +err_bus_clk: + if (hipcie->vpcie) + regulator_disable(hipcie->vpcie); + + return ret; +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .read_dbi = histb_pcie_read_dbi, + .write_dbi = histb_pcie_write_dbi, + .link_up = histb_pcie_link_up, + .start_link = histb_pcie_start_link, +}; + +static int histb_pcie_probe(struct platform_device *pdev) +{ + struct histb_pcie *hipcie; + struct dw_pcie *pci; + struct dw_pcie_rp *pp; + struct device_node *np = pdev->dev.of_node; + struct device *dev = &pdev->dev; + enum of_gpio_flags of_flags; + unsigned long flag = GPIOF_DIR_OUT; + int ret; + + hipcie = devm_kzalloc(dev, sizeof(*hipcie), GFP_KERNEL); + if (!hipcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + hipcie->pci = pci; + pp = &pci->pp; + pci->dev = dev; + pci->ops = &dw_pcie_ops; + + hipcie->ctrl = devm_platform_ioremap_resource_byname(pdev, "control"); + if (IS_ERR(hipcie->ctrl)) { + dev_err(dev, "cannot get control reg base\n"); + return PTR_ERR(hipcie->ctrl); + } + + pci->dbi_base = devm_platform_ioremap_resource_byname(pdev, "rc-dbi"); + if (IS_ERR(pci->dbi_base)) { + dev_err(dev, "cannot get rc-dbi base\n"); + return PTR_ERR(pci->dbi_base); + } + + hipcie->vpcie = devm_regulator_get_optional(dev, "vpcie"); + if (IS_ERR(hipcie->vpcie)) { + if (PTR_ERR(hipcie->vpcie) != -ENODEV) + return PTR_ERR(hipcie->vpcie); + hipcie->vpcie = NULL; + } + + hipcie->reset_gpio = of_get_named_gpio_flags(np, + "reset-gpios", 0, &of_flags); + if (of_flags & OF_GPIO_ACTIVE_LOW) + flag |= GPIOF_ACTIVE_LOW; + if (gpio_is_valid(hipcie->reset_gpio)) { + ret = devm_gpio_request_one(dev, hipcie->reset_gpio, + flag, "PCIe device power control"); + if (ret) { + dev_err(dev, "unable to request gpio\n"); + return ret; + } + } + + hipcie->aux_clk = devm_clk_get(dev, "aux"); + if (IS_ERR(hipcie->aux_clk)) { + dev_err(dev, "Failed to get PCIe aux clk\n"); + return PTR_ERR(hipcie->aux_clk); + } + + hipcie->pipe_clk = devm_clk_get(dev, "pipe"); + if (IS_ERR(hipcie->pipe_clk)) { + dev_err(dev, "Failed to get PCIe pipe clk\n"); + return PTR_ERR(hipcie->pipe_clk); + } + + hipcie->sys_clk = devm_clk_get(dev, "sys"); + if (IS_ERR(hipcie->sys_clk)) { + dev_err(dev, "Failed to get PCIEe sys clk\n"); + return PTR_ERR(hipcie->sys_clk); + } + + hipcie->bus_clk = devm_clk_get(dev, "bus"); + if (IS_ERR(hipcie->bus_clk)) { + dev_err(dev, "Failed to get PCIe bus clk\n"); + return PTR_ERR(hipcie->bus_clk); + } + + hipcie->soft_reset = devm_reset_control_get(dev, "soft"); + if (IS_ERR(hipcie->soft_reset)) { + dev_err(dev, "couldn't get soft reset\n"); + return PTR_ERR(hipcie->soft_reset); + } + + hipcie->sys_reset = devm_reset_control_get(dev, "sys"); + if (IS_ERR(hipcie->sys_reset)) { + dev_err(dev, "couldn't get sys reset\n"); + return PTR_ERR(hipcie->sys_reset); + } + + hipcie->bus_reset = devm_reset_control_get(dev, "bus"); + if (IS_ERR(hipcie->bus_reset)) { + dev_err(dev, "couldn't get bus reset\n"); + return PTR_ERR(hipcie->bus_reset); + } + + hipcie->phy = devm_phy_get(dev, "phy"); + if (IS_ERR(hipcie->phy)) { + dev_info(dev, "no pcie-phy found\n"); + hipcie->phy = NULL; + /* fall through here! + * if no pcie-phy found, phy init + * should be done under boot! + */ + } else { + phy_init(hipcie->phy); + } + + pp->ops = &histb_pcie_host_ops; + + platform_set_drvdata(pdev, hipcie); + + ret = histb_pcie_host_enable(pp); + if (ret) { + dev_err(dev, "failed to enable host\n"); + return ret; + } + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "failed to initialize host\n"); + return ret; + } + + return 0; +} + +static int histb_pcie_remove(struct platform_device *pdev) +{ + struct histb_pcie *hipcie = platform_get_drvdata(pdev); + + histb_pcie_host_disable(hipcie); + + if (hipcie->phy) + phy_exit(hipcie->phy); + + return 0; +} + +static const struct of_device_id histb_pcie_of_match[] = { + { .compatible = "hisilicon,hi3798cv200-pcie", }, + {}, +}; +MODULE_DEVICE_TABLE(of, histb_pcie_of_match); + +static struct platform_driver histb_pcie_platform_driver = { + .probe = histb_pcie_probe, + .remove = histb_pcie_remove, + .driver = { + .name = "histb-pcie", + .of_match_table = histb_pcie_of_match, + }, +}; +module_platform_driver(histb_pcie_platform_driver); + +MODULE_DESCRIPTION("HiSilicon STB PCIe host controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pcie-intel-gw.c b/drivers/pci/controller/dwc/pcie-intel-gw.c new file mode 100644 index 000000000..333c33d98 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-intel-gw.c @@ -0,0 +1,453 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Intel Gateway SoCs + * + * Copyright (c) 2019 Intel Corporation. + */ + +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/gpio/consumer.h> +#include <linux/iopoll.h> +#include <linux/pci_regs.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/reset.h> + +#include "../../pci.h" +#include "pcie-designware.h" + +#define PORT_AFR_N_FTS_GEN12_DFT (SZ_128 - 1) +#define PORT_AFR_N_FTS_GEN3 180 +#define PORT_AFR_N_FTS_GEN4 196 + +/* PCIe Application logic Registers */ +#define PCIE_APP_CCR 0x10 +#define PCIE_APP_CCR_LTSSM_ENABLE BIT(0) + +#define PCIE_APP_MSG_CR 0x30 +#define PCIE_APP_MSG_XMT_PM_TURNOFF BIT(0) + +#define PCIE_APP_PMC 0x44 +#define PCIE_APP_PMC_IN_L2 BIT(20) + +#define PCIE_APP_IRNEN 0xF4 +#define PCIE_APP_IRNCR 0xF8 +#define PCIE_APP_IRN_AER_REPORT BIT(0) +#define PCIE_APP_IRN_PME BIT(2) +#define PCIE_APP_IRN_RX_VDM_MSG BIT(4) +#define PCIE_APP_IRN_PM_TO_ACK BIT(9) +#define PCIE_APP_IRN_LINK_AUTO_BW_STAT BIT(11) +#define PCIE_APP_IRN_BW_MGT BIT(12) +#define PCIE_APP_IRN_INTA BIT(13) +#define PCIE_APP_IRN_INTB BIT(14) +#define PCIE_APP_IRN_INTC BIT(15) +#define PCIE_APP_IRN_INTD BIT(16) +#define PCIE_APP_IRN_MSG_LTR BIT(18) +#define PCIE_APP_IRN_SYS_ERR_RC BIT(29) +#define PCIE_APP_INTX_OFST 12 + +#define PCIE_APP_IRN_INT \ + (PCIE_APP_IRN_AER_REPORT | PCIE_APP_IRN_PME | \ + PCIE_APP_IRN_RX_VDM_MSG | PCIE_APP_IRN_SYS_ERR_RC | \ + PCIE_APP_IRN_PM_TO_ACK | PCIE_APP_IRN_MSG_LTR | \ + PCIE_APP_IRN_BW_MGT | PCIE_APP_IRN_LINK_AUTO_BW_STAT | \ + PCIE_APP_IRN_INTA | PCIE_APP_IRN_INTB | \ + PCIE_APP_IRN_INTC | PCIE_APP_IRN_INTD) + +#define BUS_IATU_OFFSET SZ_256M +#define RESET_INTERVAL_MS 100 + +struct intel_pcie { + struct dw_pcie pci; + void __iomem *app_base; + struct gpio_desc *reset_gpio; + u32 rst_intrvl; + struct clk *core_clk; + struct reset_control *core_rst; + struct phy *phy; +}; + +static void pcie_update_bits(void __iomem *base, u32 ofs, u32 mask, u32 val) +{ + u32 old; + + old = readl(base + ofs); + val = (old & ~mask) | (val & mask); + + if (val != old) + writel(val, base + ofs); +} + +static inline void pcie_app_wr(struct intel_pcie *pcie, u32 ofs, u32 val) +{ + writel(val, pcie->app_base + ofs); +} + +static void pcie_app_wr_mask(struct intel_pcie *pcie, u32 ofs, + u32 mask, u32 val) +{ + pcie_update_bits(pcie->app_base, ofs, mask, val); +} + +static inline u32 pcie_rc_cfg_rd(struct intel_pcie *pcie, u32 ofs) +{ + return dw_pcie_readl_dbi(&pcie->pci, ofs); +} + +static inline void pcie_rc_cfg_wr(struct intel_pcie *pcie, u32 ofs, u32 val) +{ + dw_pcie_writel_dbi(&pcie->pci, ofs, val); +} + +static void pcie_rc_cfg_wr_mask(struct intel_pcie *pcie, u32 ofs, + u32 mask, u32 val) +{ + pcie_update_bits(pcie->pci.dbi_base, ofs, mask, val); +} + +static void intel_pcie_ltssm_enable(struct intel_pcie *pcie) +{ + pcie_app_wr_mask(pcie, PCIE_APP_CCR, PCIE_APP_CCR_LTSSM_ENABLE, + PCIE_APP_CCR_LTSSM_ENABLE); +} + +static void intel_pcie_ltssm_disable(struct intel_pcie *pcie) +{ + pcie_app_wr_mask(pcie, PCIE_APP_CCR, PCIE_APP_CCR_LTSSM_ENABLE, 0); +} + +static void intel_pcie_link_setup(struct intel_pcie *pcie) +{ + u32 val; + u8 offset = dw_pcie_find_capability(&pcie->pci, PCI_CAP_ID_EXP); + + val = pcie_rc_cfg_rd(pcie, offset + PCI_EXP_LNKCTL); + + val &= ~(PCI_EXP_LNKCTL_LD | PCI_EXP_LNKCTL_ASPMC); + pcie_rc_cfg_wr(pcie, offset + PCI_EXP_LNKCTL, val); +} + +static void intel_pcie_init_n_fts(struct dw_pcie *pci) +{ + switch (pci->link_gen) { + case 3: + pci->n_fts[1] = PORT_AFR_N_FTS_GEN3; + break; + case 4: + pci->n_fts[1] = PORT_AFR_N_FTS_GEN4; + break; + default: + pci->n_fts[1] = PORT_AFR_N_FTS_GEN12_DFT; + break; + } + pci->n_fts[0] = PORT_AFR_N_FTS_GEN12_DFT; +} + +static int intel_pcie_ep_rst_init(struct intel_pcie *pcie) +{ + struct device *dev = pcie->pci.dev; + int ret; + + pcie->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(pcie->reset_gpio)) { + ret = PTR_ERR(pcie->reset_gpio); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to request PCIe GPIO: %d\n", ret); + return ret; + } + + /* Make initial reset last for 100us */ + usleep_range(100, 200); + + return 0; +} + +static void intel_pcie_core_rst_assert(struct intel_pcie *pcie) +{ + reset_control_assert(pcie->core_rst); +} + +static void intel_pcie_core_rst_deassert(struct intel_pcie *pcie) +{ + /* + * One micro-second delay to make sure the reset pulse + * wide enough so that core reset is clean. + */ + udelay(1); + reset_control_deassert(pcie->core_rst); + + /* + * Some SoC core reset also reset PHY, more delay needed + * to make sure the reset process is done. + */ + usleep_range(1000, 2000); +} + +static void intel_pcie_device_rst_assert(struct intel_pcie *pcie) +{ + gpiod_set_value_cansleep(pcie->reset_gpio, 1); +} + +static void intel_pcie_device_rst_deassert(struct intel_pcie *pcie) +{ + msleep(pcie->rst_intrvl); + gpiod_set_value_cansleep(pcie->reset_gpio, 0); +} + +static void intel_pcie_core_irq_disable(struct intel_pcie *pcie) +{ + pcie_app_wr(pcie, PCIE_APP_IRNEN, 0); + pcie_app_wr(pcie, PCIE_APP_IRNCR, PCIE_APP_IRN_INT); +} + +static int intel_pcie_get_resources(struct platform_device *pdev) +{ + struct intel_pcie *pcie = platform_get_drvdata(pdev); + struct dw_pcie *pci = &pcie->pci; + struct device *dev = pci->dev; + int ret; + + pcie->core_clk = devm_clk_get(dev, NULL); + if (IS_ERR(pcie->core_clk)) { + ret = PTR_ERR(pcie->core_clk); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get clks: %d\n", ret); + return ret; + } + + pcie->core_rst = devm_reset_control_get(dev, NULL); + if (IS_ERR(pcie->core_rst)) { + ret = PTR_ERR(pcie->core_rst); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get resets: %d\n", ret); + return ret; + } + + ret = device_property_read_u32(dev, "reset-assert-ms", + &pcie->rst_intrvl); + if (ret) + pcie->rst_intrvl = RESET_INTERVAL_MS; + + pcie->app_base = devm_platform_ioremap_resource_byname(pdev, "app"); + if (IS_ERR(pcie->app_base)) + return PTR_ERR(pcie->app_base); + + pcie->phy = devm_phy_get(dev, "pcie"); + if (IS_ERR(pcie->phy)) { + ret = PTR_ERR(pcie->phy); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Couldn't get pcie-phy: %d\n", ret); + return ret; + } + + return 0; +} + +static int intel_pcie_wait_l2(struct intel_pcie *pcie) +{ + u32 value; + int ret; + struct dw_pcie *pci = &pcie->pci; + + if (pci->link_gen < 3) + return 0; + + /* Send PME_TURN_OFF message */ + pcie_app_wr_mask(pcie, PCIE_APP_MSG_CR, PCIE_APP_MSG_XMT_PM_TURNOFF, + PCIE_APP_MSG_XMT_PM_TURNOFF); + + /* Read PMC status and wait for falling into L2 link state */ + ret = readl_poll_timeout(pcie->app_base + PCIE_APP_PMC, value, + value & PCIE_APP_PMC_IN_L2, 20, + jiffies_to_usecs(5 * HZ)); + if (ret) + dev_err(pcie->pci.dev, "PCIe link enter L2 timeout!\n"); + + return ret; +} + +static void intel_pcie_turn_off(struct intel_pcie *pcie) +{ + if (dw_pcie_link_up(&pcie->pci)) + intel_pcie_wait_l2(pcie); + + /* Put endpoint device in reset state */ + intel_pcie_device_rst_assert(pcie); + pcie_rc_cfg_wr_mask(pcie, PCI_COMMAND, PCI_COMMAND_MEMORY, 0); +} + +static int intel_pcie_host_setup(struct intel_pcie *pcie) +{ + int ret; + struct dw_pcie *pci = &pcie->pci; + + intel_pcie_core_rst_assert(pcie); + intel_pcie_device_rst_assert(pcie); + + ret = phy_init(pcie->phy); + if (ret) + return ret; + + intel_pcie_core_rst_deassert(pcie); + + ret = clk_prepare_enable(pcie->core_clk); + if (ret) { + dev_err(pcie->pci.dev, "Core clock enable failed: %d\n", ret); + goto clk_err; + } + + pci->atu_base = pci->dbi_base + 0xC0000; + + intel_pcie_ltssm_disable(pcie); + intel_pcie_link_setup(pcie); + intel_pcie_init_n_fts(pci); + + ret = dw_pcie_setup_rc(&pci->pp); + if (ret) + goto app_init_err; + + dw_pcie_upconfig_setup(pci); + + intel_pcie_device_rst_deassert(pcie); + intel_pcie_ltssm_enable(pcie); + + ret = dw_pcie_wait_for_link(pci); + if (ret) + goto app_init_err; + + /* Enable integrated interrupts */ + pcie_app_wr_mask(pcie, PCIE_APP_IRNEN, PCIE_APP_IRN_INT, + PCIE_APP_IRN_INT); + + return 0; + +app_init_err: + clk_disable_unprepare(pcie->core_clk); +clk_err: + intel_pcie_core_rst_assert(pcie); + phy_exit(pcie->phy); + + return ret; +} + +static void __intel_pcie_remove(struct intel_pcie *pcie) +{ + intel_pcie_core_irq_disable(pcie); + intel_pcie_turn_off(pcie); + clk_disable_unprepare(pcie->core_clk); + intel_pcie_core_rst_assert(pcie); + phy_exit(pcie->phy); +} + +static int intel_pcie_remove(struct platform_device *pdev) +{ + struct intel_pcie *pcie = platform_get_drvdata(pdev); + struct dw_pcie_rp *pp = &pcie->pci.pp; + + dw_pcie_host_deinit(pp); + __intel_pcie_remove(pcie); + + return 0; +} + +static int intel_pcie_suspend_noirq(struct device *dev) +{ + struct intel_pcie *pcie = dev_get_drvdata(dev); + int ret; + + intel_pcie_core_irq_disable(pcie); + ret = intel_pcie_wait_l2(pcie); + if (ret) + return ret; + + phy_exit(pcie->phy); + clk_disable_unprepare(pcie->core_clk); + return ret; +} + +static int intel_pcie_resume_noirq(struct device *dev) +{ + struct intel_pcie *pcie = dev_get_drvdata(dev); + + return intel_pcie_host_setup(pcie); +} + +static int intel_pcie_rc_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct intel_pcie *pcie = dev_get_drvdata(pci->dev); + + return intel_pcie_host_setup(pcie); +} + +static u64 intel_pcie_cpu_addr(struct dw_pcie *pcie, u64 cpu_addr) +{ + return cpu_addr + BUS_IATU_OFFSET; +} + +static const struct dw_pcie_ops intel_pcie_ops = { + .cpu_addr_fixup = intel_pcie_cpu_addr, +}; + +static const struct dw_pcie_host_ops intel_pcie_dw_ops = { + .host_init = intel_pcie_rc_init, +}; + +static int intel_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct intel_pcie *pcie; + struct dw_pcie_rp *pp; + struct dw_pcie *pci; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + platform_set_drvdata(pdev, pcie); + pci = &pcie->pci; + pci->dev = dev; + pp = &pci->pp; + + ret = intel_pcie_get_resources(pdev); + if (ret) + return ret; + + ret = intel_pcie_ep_rst_init(pcie); + if (ret) + return ret; + + pci->ops = &intel_pcie_ops; + pp->ops = &intel_pcie_dw_ops; + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "Cannot initialize host\n"); + return ret; + } + + return 0; +} + +static const struct dev_pm_ops intel_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(intel_pcie_suspend_noirq, + intel_pcie_resume_noirq) +}; + +static const struct of_device_id of_intel_pcie_match[] = { + { .compatible = "intel,lgm-pcie" }, + {} +}; + +static struct platform_driver intel_pcie_driver = { + .probe = intel_pcie_probe, + .remove = intel_pcie_remove, + .driver = { + .name = "intel-gw-pcie", + .of_match_table = of_intel_pcie_match, + .pm = &intel_pcie_pm_ops, + }, +}; +builtin_platform_driver(intel_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-keembay.c b/drivers/pci/controller/dwc/pcie-keembay.c new file mode 100644 index 000000000..f90f36bac --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-keembay.c @@ -0,0 +1,460 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * PCIe controller driver for Intel Keem Bay + * Copyright (C) 2020 Intel Corporation + */ + +#include <linux/bitfield.h> +#include <linux/bits.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/gpio/consumer.h> +#include <linux/init.h> +#include <linux/iopoll.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/kernel.h> +#include <linux/mod_devicetable.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/property.h> + +#include "pcie-designware.h" + +/* PCIE_REGS_APB_SLV Registers */ +#define PCIE_REGS_PCIE_CFG 0x0004 +#define PCIE_DEVICE_TYPE BIT(8) +#define PCIE_RSTN BIT(0) +#define PCIE_REGS_PCIE_APP_CNTRL 0x0008 +#define APP_LTSSM_ENABLE BIT(0) +#define PCIE_REGS_INTERRUPT_ENABLE 0x0028 +#define MSI_CTRL_INT_EN BIT(8) +#define EDMA_INT_EN GENMASK(7, 0) +#define PCIE_REGS_INTERRUPT_STATUS 0x002c +#define MSI_CTRL_INT BIT(8) +#define PCIE_REGS_PCIE_SII_PM_STATE 0x00b0 +#define SMLH_LINK_UP BIT(19) +#define RDLH_LINK_UP BIT(8) +#define PCIE_REGS_PCIE_SII_LINK_UP (SMLH_LINK_UP | RDLH_LINK_UP) +#define PCIE_REGS_PCIE_PHY_CNTL 0x0164 +#define PHY0_SRAM_BYPASS BIT(8) +#define PCIE_REGS_PCIE_PHY_STAT 0x0168 +#define PHY0_MPLLA_STATE BIT(1) +#define PCIE_REGS_LJPLL_STA 0x016c +#define LJPLL_LOCK BIT(0) +#define PCIE_REGS_LJPLL_CNTRL_0 0x0170 +#define LJPLL_EN BIT(29) +#define LJPLL_FOUT_EN GENMASK(24, 21) +#define PCIE_REGS_LJPLL_CNTRL_2 0x0178 +#define LJPLL_REF_DIV GENMASK(17, 12) +#define LJPLL_FB_DIV GENMASK(11, 0) +#define PCIE_REGS_LJPLL_CNTRL_3 0x017c +#define LJPLL_POST_DIV3A GENMASK(24, 22) +#define LJPLL_POST_DIV2A GENMASK(18, 16) + +#define PERST_DELAY_US 1000 +#define AUX_CLK_RATE_HZ 24000000 + +struct keembay_pcie { + struct dw_pcie pci; + void __iomem *apb_base; + enum dw_pcie_device_mode mode; + + struct clk *clk_master; + struct clk *clk_aux; + struct gpio_desc *reset; +}; + +struct keembay_pcie_of_data { + enum dw_pcie_device_mode mode; +}; + +static void keembay_ep_reset_assert(struct keembay_pcie *pcie) +{ + gpiod_set_value_cansleep(pcie->reset, 1); + usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500); +} + +static void keembay_ep_reset_deassert(struct keembay_pcie *pcie) +{ + /* + * Ensure that PERST# is asserted for a minimum of 100ms. + * + * For more details, refer to PCI Express Card Electromechanical + * Specification Revision 1.1, Table-2.4. + */ + msleep(100); + + gpiod_set_value_cansleep(pcie->reset, 0); + usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500); +} + +static void keembay_pcie_ltssm_set(struct keembay_pcie *pcie, bool enable) +{ + u32 val; + + val = readl(pcie->apb_base + PCIE_REGS_PCIE_APP_CNTRL); + if (enable) + val |= APP_LTSSM_ENABLE; + else + val &= ~APP_LTSSM_ENABLE; + writel(val, pcie->apb_base + PCIE_REGS_PCIE_APP_CNTRL); +} + +static int keembay_pcie_link_up(struct dw_pcie *pci) +{ + struct keembay_pcie *pcie = dev_get_drvdata(pci->dev); + u32 val; + + val = readl(pcie->apb_base + PCIE_REGS_PCIE_SII_PM_STATE); + + return (val & PCIE_REGS_PCIE_SII_LINK_UP) == PCIE_REGS_PCIE_SII_LINK_UP; +} + +static int keembay_pcie_start_link(struct dw_pcie *pci) +{ + struct keembay_pcie *pcie = dev_get_drvdata(pci->dev); + u32 val; + int ret; + + if (pcie->mode == DW_PCIE_EP_TYPE) + return 0; + + keembay_pcie_ltssm_set(pcie, false); + + ret = readl_poll_timeout(pcie->apb_base + PCIE_REGS_PCIE_PHY_STAT, + val, val & PHY0_MPLLA_STATE, 20, + 500 * USEC_PER_MSEC); + if (ret) { + dev_err(pci->dev, "MPLLA is not locked\n"); + return ret; + } + + keembay_pcie_ltssm_set(pcie, true); + + return 0; +} + +static void keembay_pcie_stop_link(struct dw_pcie *pci) +{ + struct keembay_pcie *pcie = dev_get_drvdata(pci->dev); + + keembay_pcie_ltssm_set(pcie, false); +} + +static const struct dw_pcie_ops keembay_pcie_ops = { + .link_up = keembay_pcie_link_up, + .start_link = keembay_pcie_start_link, + .stop_link = keembay_pcie_stop_link, +}; + +static inline struct clk *keembay_pcie_probe_clock(struct device *dev, + const char *id, u64 rate) +{ + struct clk *clk; + int ret; + + clk = devm_clk_get(dev, id); + if (IS_ERR(clk)) + return clk; + + if (rate) { + ret = clk_set_rate(clk, rate); + if (ret) + return ERR_PTR(ret); + } + + ret = clk_prepare_enable(clk); + if (ret) + return ERR_PTR(ret); + + ret = devm_add_action_or_reset(dev, + (void(*)(void *))clk_disable_unprepare, + clk); + if (ret) + return ERR_PTR(ret); + + return clk; +} + +static int keembay_pcie_probe_clocks(struct keembay_pcie *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + struct device *dev = pci->dev; + + pcie->clk_master = keembay_pcie_probe_clock(dev, "master", 0); + if (IS_ERR(pcie->clk_master)) + return dev_err_probe(dev, PTR_ERR(pcie->clk_master), + "Failed to enable master clock"); + + pcie->clk_aux = keembay_pcie_probe_clock(dev, "aux", AUX_CLK_RATE_HZ); + if (IS_ERR(pcie->clk_aux)) + return dev_err_probe(dev, PTR_ERR(pcie->clk_aux), + "Failed to enable auxiliary clock"); + + return 0; +} + +/* + * Initialize the internal PCIe PLL in Host mode. + * See the following sections in Keem Bay data book, + * (1) 6.4.6.1 PCIe Subsystem Example Initialization, + * (2) 6.8 PCIe Low Jitter PLL for Ref Clk Generation. + */ +static int keembay_pcie_pll_init(struct keembay_pcie *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + u32 val; + int ret; + + val = FIELD_PREP(LJPLL_REF_DIV, 0) | FIELD_PREP(LJPLL_FB_DIV, 0x32); + writel(val, pcie->apb_base + PCIE_REGS_LJPLL_CNTRL_2); + + val = FIELD_PREP(LJPLL_POST_DIV3A, 0x2) | + FIELD_PREP(LJPLL_POST_DIV2A, 0x2); + writel(val, pcie->apb_base + PCIE_REGS_LJPLL_CNTRL_3); + + val = FIELD_PREP(LJPLL_EN, 0x1) | FIELD_PREP(LJPLL_FOUT_EN, 0xc); + writel(val, pcie->apb_base + PCIE_REGS_LJPLL_CNTRL_0); + + ret = readl_poll_timeout(pcie->apb_base + PCIE_REGS_LJPLL_STA, + val, val & LJPLL_LOCK, 20, + 500 * USEC_PER_MSEC); + if (ret) + dev_err(pci->dev, "Low jitter PLL is not locked\n"); + + return ret; +} + +static void keembay_pcie_msi_irq_handler(struct irq_desc *desc) +{ + struct keembay_pcie *pcie = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + u32 val, mask, status; + struct dw_pcie_rp *pp; + + /* + * Keem Bay PCIe Controller provides an additional IP logic on top of + * standard DWC IP to clear MSI IRQ by writing '1' to the respective + * bit of the status register. + * + * So, a chained irq handler is defined to handle this additional + * IP logic. + */ + + chained_irq_enter(chip, desc); + + pp = &pcie->pci.pp; + val = readl(pcie->apb_base + PCIE_REGS_INTERRUPT_STATUS); + mask = readl(pcie->apb_base + PCIE_REGS_INTERRUPT_ENABLE); + + status = val & mask; + + if (status & MSI_CTRL_INT) { + dw_handle_msi_irq(pp); + writel(status, pcie->apb_base + PCIE_REGS_INTERRUPT_STATUS); + } + + chained_irq_exit(chip, desc); +} + +static int keembay_pcie_setup_msi_irq(struct keembay_pcie *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + struct device *dev = pci->dev; + struct platform_device *pdev = to_platform_device(dev); + int irq; + + irq = platform_get_irq_byname(pdev, "pcie"); + if (irq < 0) + return irq; + + irq_set_chained_handler_and_data(irq, keembay_pcie_msi_irq_handler, + pcie); + + return 0; +} + +static void keembay_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct keembay_pcie *pcie = dev_get_drvdata(pci->dev); + + writel(EDMA_INT_EN, pcie->apb_base + PCIE_REGS_INTERRUPT_ENABLE); +} + +static int keembay_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + enum pci_epc_irq_type type, + u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + /* Legacy interrupts are not supported in Keem Bay */ + dev_err(pci->dev, "Legacy IRQ is not supported\n"); + return -EINVAL; + case PCI_EPC_IRQ_MSI: + return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num); + case PCI_EPC_IRQ_MSIX: + return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num); + default: + dev_err(pci->dev, "Unknown IRQ type %d\n", type); + return -EINVAL; + } +} + +static const struct pci_epc_features keembay_pcie_epc_features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = true, + .reserved_bar = BIT(BAR_1) | BIT(BAR_3) | BIT(BAR_5), + .bar_fixed_64bit = BIT(BAR_0) | BIT(BAR_2) | BIT(BAR_4), + .align = SZ_16K, +}; + +static const struct pci_epc_features * +keembay_pcie_get_features(struct dw_pcie_ep *ep) +{ + return &keembay_pcie_epc_features; +} + +static const struct dw_pcie_ep_ops keembay_pcie_ep_ops = { + .ep_init = keembay_pcie_ep_init, + .raise_irq = keembay_pcie_ep_raise_irq, + .get_features = keembay_pcie_get_features, +}; + +static const struct dw_pcie_host_ops keembay_pcie_host_ops = { +}; + +static int keembay_pcie_add_pcie_port(struct keembay_pcie *pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = &pdev->dev; + u32 val; + int ret; + + pp->ops = &keembay_pcie_host_ops; + pp->msi_irq[0] = -ENODEV; + + ret = keembay_pcie_setup_msi_irq(pcie); + if (ret) + return ret; + + pcie->reset = devm_gpiod_get(dev, "reset", GPIOD_OUT_HIGH); + if (IS_ERR(pcie->reset)) + return PTR_ERR(pcie->reset); + + ret = keembay_pcie_probe_clocks(pcie); + if (ret) + return ret; + + val = readl(pcie->apb_base + PCIE_REGS_PCIE_PHY_CNTL); + val |= PHY0_SRAM_BYPASS; + writel(val, pcie->apb_base + PCIE_REGS_PCIE_PHY_CNTL); + + writel(PCIE_DEVICE_TYPE, pcie->apb_base + PCIE_REGS_PCIE_CFG); + + ret = keembay_pcie_pll_init(pcie); + if (ret) + return ret; + + val = readl(pcie->apb_base + PCIE_REGS_PCIE_CFG); + writel(val | PCIE_RSTN, pcie->apb_base + PCIE_REGS_PCIE_CFG); + keembay_ep_reset_deassert(pcie); + + ret = dw_pcie_host_init(pp); + if (ret) { + keembay_ep_reset_assert(pcie); + dev_err(dev, "Failed to initialize host: %d\n", ret); + return ret; + } + + val = readl(pcie->apb_base + PCIE_REGS_INTERRUPT_ENABLE); + if (IS_ENABLED(CONFIG_PCI_MSI)) + val |= MSI_CTRL_INT_EN; + writel(val, pcie->apb_base + PCIE_REGS_INTERRUPT_ENABLE); + + return 0; +} + +static int keembay_pcie_probe(struct platform_device *pdev) +{ + const struct keembay_pcie_of_data *data; + struct device *dev = &pdev->dev; + struct keembay_pcie *pcie; + struct dw_pcie *pci; + enum dw_pcie_device_mode mode; + + data = device_get_match_data(dev); + if (!data) + return -ENODEV; + + mode = (enum dw_pcie_device_mode)data->mode; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = &pcie->pci; + pci->dev = dev; + pci->ops = &keembay_pcie_ops; + + pcie->mode = mode; + + pcie->apb_base = devm_platform_ioremap_resource_byname(pdev, "apb"); + if (IS_ERR(pcie->apb_base)) + return PTR_ERR(pcie->apb_base); + + platform_set_drvdata(pdev, pcie); + + switch (pcie->mode) { + case DW_PCIE_RC_TYPE: + if (!IS_ENABLED(CONFIG_PCIE_KEEMBAY_HOST)) + return -ENODEV; + + return keembay_pcie_add_pcie_port(pcie, pdev); + case DW_PCIE_EP_TYPE: + if (!IS_ENABLED(CONFIG_PCIE_KEEMBAY_EP)) + return -ENODEV; + + pci->ep.ops = &keembay_pcie_ep_ops; + return dw_pcie_ep_init(&pci->ep); + default: + dev_err(dev, "Invalid device type %d\n", pcie->mode); + return -ENODEV; + } +} + +static const struct keembay_pcie_of_data keembay_pcie_rc_of_data = { + .mode = DW_PCIE_RC_TYPE, +}; + +static const struct keembay_pcie_of_data keembay_pcie_ep_of_data = { + .mode = DW_PCIE_EP_TYPE, +}; + +static const struct of_device_id keembay_pcie_of_match[] = { + { + .compatible = "intel,keembay-pcie", + .data = &keembay_pcie_rc_of_data, + }, + { + .compatible = "intel,keembay-pcie-ep", + .data = &keembay_pcie_ep_of_data, + }, + {} +}; + +static struct platform_driver keembay_pcie_driver = { + .driver = { + .name = "keembay-pcie", + .of_match_table = keembay_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = keembay_pcie_probe, +}; +builtin_platform_driver(keembay_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c new file mode 100644 index 000000000..a824d8e8e --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-kirin.c @@ -0,0 +1,834 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Kirin Phone SoCs + * + * Copyright (C) 2017 HiSilicon Electronics Co., Ltd. + * https://www.huawei.com + * + * Author: Xiaowei Song <songxiaowei@huawei.com> + */ + +#include <linux/clk.h> +#include <linux/compiler.h> +#include <linux/delay.h> +#include <linux/err.h> +#include <linux/gpio.h> +#include <linux/gpio/consumer.h> +#include <linux/interrupt.h> +#include <linux/mfd/syscon.h> +#include <linux/of_address.h> +#include <linux/of_device.h> +#include <linux/of_gpio.h> +#include <linux/of_pci.h> +#include <linux/phy/phy.h> +#include <linux/pci.h> +#include <linux/pci_regs.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/resource.h> +#include <linux/types.h> +#include "pcie-designware.h" + +#define to_kirin_pcie(x) dev_get_drvdata((x)->dev) + +/* PCIe ELBI registers */ +#define SOC_PCIECTRL_CTRL0_ADDR 0x000 +#define SOC_PCIECTRL_CTRL1_ADDR 0x004 +#define PCIE_ELBI_SLV_DBI_ENABLE (0x1 << 21) + +/* info located in APB */ +#define PCIE_APP_LTSSM_ENABLE 0x01c +#define PCIE_APB_PHY_STATUS0 0x400 +#define PCIE_LINKUP_ENABLE (0x8020) +#define PCIE_LTSSM_ENABLE_BIT (0x1 << 11) + +/* info located in sysctrl */ +#define SCTRL_PCIE_CMOS_OFFSET 0x60 +#define SCTRL_PCIE_CMOS_BIT 0x10 +#define SCTRL_PCIE_ISO_OFFSET 0x44 +#define SCTRL_PCIE_ISO_BIT 0x30 +#define SCTRL_PCIE_HPCLK_OFFSET 0x190 +#define SCTRL_PCIE_HPCLK_BIT 0x184000 +#define SCTRL_PCIE_OE_OFFSET 0x14a +#define PCIE_DEBOUNCE_PARAM 0xF0F400 +#define PCIE_OE_BYPASS (0x3 << 28) + +/* + * Max number of connected PCI slots at an external PCI bridge + * + * This is used on HiKey 970, which has a PEX 8606 bridge with 4 connected + * lanes (lane 0 upstream, and the other three lanes, one connected to an + * in-board Ethernet adapter and the other two connected to M.2 and mini + * PCI slots. + * + * Each slot has a different clock source and uses a separate PERST# pin. + */ +#define MAX_PCI_SLOTS 3 + +enum pcie_kirin_phy_type { + PCIE_KIRIN_INTERNAL_PHY, + PCIE_KIRIN_EXTERNAL_PHY +}; + +struct kirin_pcie { + enum pcie_kirin_phy_type type; + + struct dw_pcie *pci; + struct regmap *apb; + struct phy *phy; + void *phy_priv; /* only for PCIE_KIRIN_INTERNAL_PHY */ + + /* DWC PERST# */ + int gpio_id_dwc_perst; + + /* Per-slot PERST# */ + int num_slots; + int gpio_id_reset[MAX_PCI_SLOTS]; + const char *reset_names[MAX_PCI_SLOTS]; + + /* Per-slot clkreq */ + int n_gpio_clkreq; + int gpio_id_clkreq[MAX_PCI_SLOTS]; + const char *clkreq_names[MAX_PCI_SLOTS]; +}; + +/* + * Kirin 960 PHY. Can't be split into a PHY driver without changing the + * DT schema. + */ + +#define REF_CLK_FREQ 100000000 + +/* PHY info located in APB */ +#define PCIE_APB_PHY_CTRL0 0x0 +#define PCIE_APB_PHY_CTRL1 0x4 +#define PCIE_APB_PHY_STATUS0 0x400 +#define PIPE_CLK_STABLE BIT(19) +#define PHY_REF_PAD_BIT BIT(8) +#define PHY_PWR_DOWN_BIT BIT(22) +#define PHY_RST_ACK_BIT BIT(16) + +/* peri_crg ctrl */ +#define CRGCTRL_PCIE_ASSERT_OFFSET 0x88 +#define CRGCTRL_PCIE_ASSERT_BIT 0x8c000000 + +/* Time for delay */ +#define REF_2_PERST_MIN 21000 +#define REF_2_PERST_MAX 25000 +#define PERST_2_ACCESS_MIN 10000 +#define PERST_2_ACCESS_MAX 12000 +#define PIPE_CLK_WAIT_MIN 550 +#define PIPE_CLK_WAIT_MAX 600 +#define TIME_CMOS_MIN 100 +#define TIME_CMOS_MAX 105 +#define TIME_PHY_PD_MIN 10 +#define TIME_PHY_PD_MAX 11 + +struct hi3660_pcie_phy { + struct device *dev; + void __iomem *base; + struct regmap *crgctrl; + struct regmap *sysctrl; + struct clk *apb_sys_clk; + struct clk *apb_phy_clk; + struct clk *phy_ref_clk; + struct clk *aclk; + struct clk *aux_clk; +}; + +/* Registers in PCIePHY */ +static inline void kirin_apb_phy_writel(struct hi3660_pcie_phy *hi3660_pcie_phy, + u32 val, u32 reg) +{ + writel(val, hi3660_pcie_phy->base + reg); +} + +static inline u32 kirin_apb_phy_readl(struct hi3660_pcie_phy *hi3660_pcie_phy, + u32 reg) +{ + return readl(hi3660_pcie_phy->base + reg); +} + +static int hi3660_pcie_phy_get_clk(struct hi3660_pcie_phy *phy) +{ + struct device *dev = phy->dev; + + phy->phy_ref_clk = devm_clk_get(dev, "pcie_phy_ref"); + if (IS_ERR(phy->phy_ref_clk)) + return PTR_ERR(phy->phy_ref_clk); + + phy->aux_clk = devm_clk_get(dev, "pcie_aux"); + if (IS_ERR(phy->aux_clk)) + return PTR_ERR(phy->aux_clk); + + phy->apb_phy_clk = devm_clk_get(dev, "pcie_apb_phy"); + if (IS_ERR(phy->apb_phy_clk)) + return PTR_ERR(phy->apb_phy_clk); + + phy->apb_sys_clk = devm_clk_get(dev, "pcie_apb_sys"); + if (IS_ERR(phy->apb_sys_clk)) + return PTR_ERR(phy->apb_sys_clk); + + phy->aclk = devm_clk_get(dev, "pcie_aclk"); + if (IS_ERR(phy->aclk)) + return PTR_ERR(phy->aclk); + + return 0; +} + +static int hi3660_pcie_phy_get_resource(struct hi3660_pcie_phy *phy) +{ + struct device *dev = phy->dev; + struct platform_device *pdev; + + /* registers */ + pdev = container_of(dev, struct platform_device, dev); + + phy->base = devm_platform_ioremap_resource_byname(pdev, "phy"); + if (IS_ERR(phy->base)) + return PTR_ERR(phy->base); + + phy->crgctrl = syscon_regmap_lookup_by_compatible("hisilicon,hi3660-crgctrl"); + if (IS_ERR(phy->crgctrl)) + return PTR_ERR(phy->crgctrl); + + phy->sysctrl = syscon_regmap_lookup_by_compatible("hisilicon,hi3660-sctrl"); + if (IS_ERR(phy->sysctrl)) + return PTR_ERR(phy->sysctrl); + + return 0; +} + +static int hi3660_pcie_phy_start(struct hi3660_pcie_phy *phy) +{ + struct device *dev = phy->dev; + u32 reg_val; + + reg_val = kirin_apb_phy_readl(phy, PCIE_APB_PHY_CTRL1); + reg_val &= ~PHY_REF_PAD_BIT; + kirin_apb_phy_writel(phy, reg_val, PCIE_APB_PHY_CTRL1); + + reg_val = kirin_apb_phy_readl(phy, PCIE_APB_PHY_CTRL0); + reg_val &= ~PHY_PWR_DOWN_BIT; + kirin_apb_phy_writel(phy, reg_val, PCIE_APB_PHY_CTRL0); + usleep_range(TIME_PHY_PD_MIN, TIME_PHY_PD_MAX); + + reg_val = kirin_apb_phy_readl(phy, PCIE_APB_PHY_CTRL1); + reg_val &= ~PHY_RST_ACK_BIT; + kirin_apb_phy_writel(phy, reg_val, PCIE_APB_PHY_CTRL1); + + usleep_range(PIPE_CLK_WAIT_MIN, PIPE_CLK_WAIT_MAX); + reg_val = kirin_apb_phy_readl(phy, PCIE_APB_PHY_STATUS0); + if (reg_val & PIPE_CLK_STABLE) { + dev_err(dev, "PIPE clk is not stable\n"); + return -EINVAL; + } + + return 0; +} + +static void hi3660_pcie_phy_oe_enable(struct hi3660_pcie_phy *phy) +{ + u32 val; + + regmap_read(phy->sysctrl, SCTRL_PCIE_OE_OFFSET, &val); + val |= PCIE_DEBOUNCE_PARAM; + val &= ~PCIE_OE_BYPASS; + regmap_write(phy->sysctrl, SCTRL_PCIE_OE_OFFSET, val); +} + +static int hi3660_pcie_phy_clk_ctrl(struct hi3660_pcie_phy *phy, bool enable) +{ + int ret = 0; + + if (!enable) + goto close_clk; + + ret = clk_set_rate(phy->phy_ref_clk, REF_CLK_FREQ); + if (ret) + return ret; + + ret = clk_prepare_enable(phy->phy_ref_clk); + if (ret) + return ret; + + ret = clk_prepare_enable(phy->apb_sys_clk); + if (ret) + goto apb_sys_fail; + + ret = clk_prepare_enable(phy->apb_phy_clk); + if (ret) + goto apb_phy_fail; + + ret = clk_prepare_enable(phy->aclk); + if (ret) + goto aclk_fail; + + ret = clk_prepare_enable(phy->aux_clk); + if (ret) + goto aux_clk_fail; + + return 0; + +close_clk: + clk_disable_unprepare(phy->aux_clk); +aux_clk_fail: + clk_disable_unprepare(phy->aclk); +aclk_fail: + clk_disable_unprepare(phy->apb_phy_clk); +apb_phy_fail: + clk_disable_unprepare(phy->apb_sys_clk); +apb_sys_fail: + clk_disable_unprepare(phy->phy_ref_clk); + + return ret; +} + +static int hi3660_pcie_phy_power_on(struct kirin_pcie *pcie) +{ + struct hi3660_pcie_phy *phy = pcie->phy_priv; + int ret; + + /* Power supply for Host */ + regmap_write(phy->sysctrl, + SCTRL_PCIE_CMOS_OFFSET, SCTRL_PCIE_CMOS_BIT); + usleep_range(TIME_CMOS_MIN, TIME_CMOS_MAX); + + hi3660_pcie_phy_oe_enable(phy); + + ret = hi3660_pcie_phy_clk_ctrl(phy, true); + if (ret) + return ret; + + /* ISO disable, PCIeCtrl, PHY assert and clk gate clear */ + regmap_write(phy->sysctrl, + SCTRL_PCIE_ISO_OFFSET, SCTRL_PCIE_ISO_BIT); + regmap_write(phy->crgctrl, + CRGCTRL_PCIE_ASSERT_OFFSET, CRGCTRL_PCIE_ASSERT_BIT); + regmap_write(phy->sysctrl, + SCTRL_PCIE_HPCLK_OFFSET, SCTRL_PCIE_HPCLK_BIT); + + ret = hi3660_pcie_phy_start(phy); + if (ret) + goto disable_clks; + + return 0; + +disable_clks: + hi3660_pcie_phy_clk_ctrl(phy, false); + return ret; +} + +static int hi3660_pcie_phy_init(struct platform_device *pdev, + struct kirin_pcie *pcie) +{ + struct device *dev = &pdev->dev; + struct hi3660_pcie_phy *phy; + int ret; + + phy = devm_kzalloc(dev, sizeof(*phy), GFP_KERNEL); + if (!phy) + return -ENOMEM; + + pcie->phy_priv = phy; + phy->dev = dev; + + ret = hi3660_pcie_phy_get_clk(phy); + if (ret) + return ret; + + return hi3660_pcie_phy_get_resource(phy); +} + +static int hi3660_pcie_phy_power_off(struct kirin_pcie *pcie) +{ + struct hi3660_pcie_phy *phy = pcie->phy_priv; + + /* Drop power supply for Host */ + regmap_write(phy->sysctrl, SCTRL_PCIE_CMOS_OFFSET, 0x00); + + hi3660_pcie_phy_clk_ctrl(phy, false); + + return 0; +} + +/* + * The non-PHY part starts here + */ + +static const struct regmap_config pcie_kirin_regmap_conf = { + .name = "kirin_pcie_apb", + .reg_bits = 32, + .val_bits = 32, + .reg_stride = 4, +}; + +static int kirin_pcie_get_gpio_enable(struct kirin_pcie *pcie, + struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + char name[32]; + int ret, i; + + /* This is an optional property */ + ret = gpiod_count(dev, "hisilicon,clken"); + if (ret < 0) + return 0; + + if (ret > MAX_PCI_SLOTS) { + dev_err(dev, "Too many GPIO clock requests!\n"); + return -EINVAL; + } + + pcie->n_gpio_clkreq = ret; + + for (i = 0; i < pcie->n_gpio_clkreq; i++) { + pcie->gpio_id_clkreq[i] = of_get_named_gpio(dev->of_node, + "hisilicon,clken-gpios", i); + if (pcie->gpio_id_clkreq[i] < 0) + return pcie->gpio_id_clkreq[i]; + + sprintf(name, "pcie_clkreq_%d", i); + pcie->clkreq_names[i] = devm_kstrdup_const(dev, name, + GFP_KERNEL); + if (!pcie->clkreq_names[i]) + return -ENOMEM; + } + + return 0; +} + +static int kirin_pcie_parse_port(struct kirin_pcie *pcie, + struct platform_device *pdev, + struct device_node *node) +{ + struct device *dev = &pdev->dev; + struct device_node *parent, *child; + int ret, slot, i; + char name[32]; + + for_each_available_child_of_node(node, parent) { + for_each_available_child_of_node(parent, child) { + i = pcie->num_slots; + + pcie->gpio_id_reset[i] = of_get_named_gpio(child, + "reset-gpios", 0); + if (pcie->gpio_id_reset[i] < 0) + continue; + + pcie->num_slots++; + if (pcie->num_slots > MAX_PCI_SLOTS) { + dev_err(dev, "Too many PCI slots!\n"); + ret = -EINVAL; + goto put_node; + } + + ret = of_pci_get_devfn(child); + if (ret < 0) { + dev_err(dev, "failed to parse devfn: %d\n", ret); + goto put_node; + } + + slot = PCI_SLOT(ret); + + sprintf(name, "pcie_perst_%d", slot); + pcie->reset_names[i] = devm_kstrdup_const(dev, name, + GFP_KERNEL); + if (!pcie->reset_names[i]) { + ret = -ENOMEM; + goto put_node; + } + } + } + + return 0; + +put_node: + of_node_put(child); + of_node_put(parent); + return ret; +} + +static long kirin_pcie_get_resource(struct kirin_pcie *kirin_pcie, + struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *child, *node = dev->of_node; + void __iomem *apb_base; + int ret; + + apb_base = devm_platform_ioremap_resource_byname(pdev, "apb"); + if (IS_ERR(apb_base)) + return PTR_ERR(apb_base); + + kirin_pcie->apb = devm_regmap_init_mmio(dev, apb_base, + &pcie_kirin_regmap_conf); + if (IS_ERR(kirin_pcie->apb)) + return PTR_ERR(kirin_pcie->apb); + + /* pcie internal PERST# gpio */ + kirin_pcie->gpio_id_dwc_perst = of_get_named_gpio(dev->of_node, + "reset-gpios", 0); + if (kirin_pcie->gpio_id_dwc_perst == -EPROBE_DEFER) { + return -EPROBE_DEFER; + } else if (!gpio_is_valid(kirin_pcie->gpio_id_dwc_perst)) { + dev_err(dev, "unable to get a valid gpio pin\n"); + return -ENODEV; + } + + ret = kirin_pcie_get_gpio_enable(kirin_pcie, pdev); + if (ret) + return ret; + + /* Parse OF children */ + for_each_available_child_of_node(node, child) { + ret = kirin_pcie_parse_port(kirin_pcie, pdev, child); + if (ret) + goto put_node; + } + + return 0; + +put_node: + of_node_put(child); + return ret; +} + +static void kirin_pcie_sideband_dbi_w_mode(struct kirin_pcie *kirin_pcie, + bool on) +{ + u32 val; + + regmap_read(kirin_pcie->apb, SOC_PCIECTRL_CTRL0_ADDR, &val); + if (on) + val = val | PCIE_ELBI_SLV_DBI_ENABLE; + else + val = val & ~PCIE_ELBI_SLV_DBI_ENABLE; + + regmap_write(kirin_pcie->apb, SOC_PCIECTRL_CTRL0_ADDR, val); +} + +static void kirin_pcie_sideband_dbi_r_mode(struct kirin_pcie *kirin_pcie, + bool on) +{ + u32 val; + + regmap_read(kirin_pcie->apb, SOC_PCIECTRL_CTRL1_ADDR, &val); + if (on) + val = val | PCIE_ELBI_SLV_DBI_ENABLE; + else + val = val & ~PCIE_ELBI_SLV_DBI_ENABLE; + + regmap_write(kirin_pcie->apb, SOC_PCIECTRL_CTRL1_ADDR, val); +} + +static int kirin_pcie_rd_own_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); + + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + *val = dw_pcie_read_dbi(pci, where, size); + return PCIBIOS_SUCCESSFUL; +} + +static int kirin_pcie_wr_own_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); + + if (PCI_SLOT(devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + dw_pcie_write_dbi(pci, where, size, val); + return PCIBIOS_SUCCESSFUL; +} + +static int kirin_pcie_add_bus(struct pci_bus *bus) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(bus->sysdata); + struct kirin_pcie *kirin_pcie = to_kirin_pcie(pci); + int i, ret; + + if (!kirin_pcie->num_slots) + return 0; + + /* Send PERST# to each slot */ + for (i = 0; i < kirin_pcie->num_slots; i++) { + ret = gpio_direction_output(kirin_pcie->gpio_id_reset[i], 1); + if (ret) { + dev_err(pci->dev, "PERST# %s error: %d\n", + kirin_pcie->reset_names[i], ret); + } + } + usleep_range(PERST_2_ACCESS_MIN, PERST_2_ACCESS_MAX); + + return 0; +} + +static struct pci_ops kirin_pci_ops = { + .read = kirin_pcie_rd_own_conf, + .write = kirin_pcie_wr_own_conf, + .add_bus = kirin_pcie_add_bus, +}; + +static u32 kirin_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, + u32 reg, size_t size) +{ + struct kirin_pcie *kirin_pcie = to_kirin_pcie(pci); + u32 ret; + + kirin_pcie_sideband_dbi_r_mode(kirin_pcie, true); + dw_pcie_read(base + reg, size, &ret); + kirin_pcie_sideband_dbi_r_mode(kirin_pcie, false); + + return ret; +} + +static void kirin_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, + u32 reg, size_t size, u32 val) +{ + struct kirin_pcie *kirin_pcie = to_kirin_pcie(pci); + + kirin_pcie_sideband_dbi_w_mode(kirin_pcie, true); + dw_pcie_write(base + reg, size, val); + kirin_pcie_sideband_dbi_w_mode(kirin_pcie, false); +} + +static int kirin_pcie_link_up(struct dw_pcie *pci) +{ + struct kirin_pcie *kirin_pcie = to_kirin_pcie(pci); + u32 val; + + regmap_read(kirin_pcie->apb, PCIE_APB_PHY_STATUS0, &val); + if ((val & PCIE_LINKUP_ENABLE) == PCIE_LINKUP_ENABLE) + return 1; + + return 0; +} + +static int kirin_pcie_start_link(struct dw_pcie *pci) +{ + struct kirin_pcie *kirin_pcie = to_kirin_pcie(pci); + + /* assert LTSSM enable */ + regmap_write(kirin_pcie->apb, PCIE_APP_LTSSM_ENABLE, + PCIE_LTSSM_ENABLE_BIT); + + return 0; +} + +static int kirin_pcie_host_init(struct dw_pcie_rp *pp) +{ + pp->bridge->ops = &kirin_pci_ops; + + return 0; +} + +static int kirin_pcie_gpio_request(struct kirin_pcie *kirin_pcie, + struct device *dev) +{ + int ret, i; + + for (i = 0; i < kirin_pcie->num_slots; i++) { + if (!gpio_is_valid(kirin_pcie->gpio_id_reset[i])) { + dev_err(dev, "unable to get a valid %s gpio\n", + kirin_pcie->reset_names[i]); + return -ENODEV; + } + + ret = devm_gpio_request(dev, kirin_pcie->gpio_id_reset[i], + kirin_pcie->reset_names[i]); + if (ret) + return ret; + } + + for (i = 0; i < kirin_pcie->n_gpio_clkreq; i++) { + if (!gpio_is_valid(kirin_pcie->gpio_id_clkreq[i])) { + dev_err(dev, "unable to get a valid %s gpio\n", + kirin_pcie->clkreq_names[i]); + return -ENODEV; + } + + ret = devm_gpio_request(dev, kirin_pcie->gpio_id_clkreq[i], + kirin_pcie->clkreq_names[i]); + if (ret) + return ret; + + ret = gpio_direction_output(kirin_pcie->gpio_id_clkreq[i], 0); + if (ret) + return ret; + } + + return 0; +} + +static const struct dw_pcie_ops kirin_dw_pcie_ops = { + .read_dbi = kirin_pcie_read_dbi, + .write_dbi = kirin_pcie_write_dbi, + .link_up = kirin_pcie_link_up, + .start_link = kirin_pcie_start_link, +}; + +static const struct dw_pcie_host_ops kirin_pcie_host_ops = { + .host_init = kirin_pcie_host_init, +}; + +static int kirin_pcie_power_off(struct kirin_pcie *kirin_pcie) +{ + int i; + + if (kirin_pcie->type == PCIE_KIRIN_INTERNAL_PHY) + return hi3660_pcie_phy_power_off(kirin_pcie); + + for (i = 0; i < kirin_pcie->n_gpio_clkreq; i++) + gpio_direction_output(kirin_pcie->gpio_id_clkreq[i], 1); + + phy_power_off(kirin_pcie->phy); + phy_exit(kirin_pcie->phy); + + return 0; +} + +static int kirin_pcie_power_on(struct platform_device *pdev, + struct kirin_pcie *kirin_pcie) +{ + struct device *dev = &pdev->dev; + int ret; + + if (kirin_pcie->type == PCIE_KIRIN_INTERNAL_PHY) { + ret = hi3660_pcie_phy_init(pdev, kirin_pcie); + if (ret) + return ret; + + ret = hi3660_pcie_phy_power_on(kirin_pcie); + if (ret) + return ret; + } else { + kirin_pcie->phy = devm_of_phy_get(dev, dev->of_node, NULL); + if (IS_ERR(kirin_pcie->phy)) + return PTR_ERR(kirin_pcie->phy); + + ret = kirin_pcie_gpio_request(kirin_pcie, dev); + if (ret) + return ret; + + ret = phy_init(kirin_pcie->phy); + if (ret) + goto err; + + ret = phy_power_on(kirin_pcie->phy); + if (ret) + goto err; + } + + /* perst assert Endpoint */ + usleep_range(REF_2_PERST_MIN, REF_2_PERST_MAX); + + if (!gpio_request(kirin_pcie->gpio_id_dwc_perst, "pcie_perst_bridge")) { + ret = gpio_direction_output(kirin_pcie->gpio_id_dwc_perst, 1); + if (ret) + goto err; + } + + usleep_range(PERST_2_ACCESS_MIN, PERST_2_ACCESS_MAX); + + return 0; +err: + kirin_pcie_power_off(kirin_pcie); + + return ret; +} + +static int kirin_pcie_remove(struct platform_device *pdev) +{ + struct kirin_pcie *kirin_pcie = platform_get_drvdata(pdev); + + dw_pcie_host_deinit(&kirin_pcie->pci->pp); + + kirin_pcie_power_off(kirin_pcie); + + return 0; +} + +struct kirin_pcie_data { + enum pcie_kirin_phy_type phy_type; +}; + +static const struct kirin_pcie_data kirin_960_data = { + .phy_type = PCIE_KIRIN_INTERNAL_PHY, +}; + +static const struct kirin_pcie_data kirin_970_data = { + .phy_type = PCIE_KIRIN_EXTERNAL_PHY, +}; + +static const struct of_device_id kirin_pcie_match[] = { + { .compatible = "hisilicon,kirin960-pcie", .data = &kirin_960_data }, + { .compatible = "hisilicon,kirin970-pcie", .data = &kirin_970_data }, + {}, +}; + +static int kirin_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + const struct kirin_pcie_data *data; + struct kirin_pcie *kirin_pcie; + struct dw_pcie *pci; + int ret; + + if (!dev->of_node) { + dev_err(dev, "NULL node\n"); + return -EINVAL; + } + + data = of_device_get_match_data(dev); + if (!data) { + dev_err(dev, "OF data missing\n"); + return -EINVAL; + } + + kirin_pcie = devm_kzalloc(dev, sizeof(struct kirin_pcie), GFP_KERNEL); + if (!kirin_pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pci->dev = dev; + pci->ops = &kirin_dw_pcie_ops; + pci->pp.ops = &kirin_pcie_host_ops; + kirin_pcie->pci = pci; + kirin_pcie->type = data->phy_type; + + ret = kirin_pcie_get_resource(kirin_pcie, pdev); + if (ret) + return ret; + + platform_set_drvdata(pdev, kirin_pcie); + + ret = kirin_pcie_power_on(pdev, kirin_pcie); + if (ret) + return ret; + + return dw_pcie_host_init(&pci->pp); +} + +static struct platform_driver kirin_pcie_driver = { + .probe = kirin_pcie_probe, + .remove = kirin_pcie_remove, + .driver = { + .name = "kirin-pcie", + .of_match_table = kirin_pcie_match, + .suppress_bind_attrs = true, + }, +}; +module_platform_driver(kirin_pcie_driver); + +MODULE_DEVICE_TABLE(of, kirin_pcie_match); +MODULE_DESCRIPTION("PCIe host controller driver for Kirin Phone SoCs"); +MODULE_AUTHOR("Xiaowei Song <songxiaowei@huawei.com>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c new file mode 100644 index 000000000..1c7fd05ce --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c @@ -0,0 +1,836 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Qualcomm PCIe Endpoint controller driver + * + * Copyright (c) 2020, The Linux Foundation. All rights reserved. + * Author: Siddartha Mohanadoss <smohanad@codeaurora.org + * + * Copyright (c) 2021, Linaro Ltd. + * Author: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org + */ + +#include <linux/clk.h> +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/mfd/syscon.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_domain.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <linux/module.h> + +#include "pcie-designware.h" + +/* PARF registers */ +#define PARF_SYS_CTRL 0x00 +#define PARF_DB_CTRL 0x10 +#define PARF_PM_CTRL 0x20 +#define PARF_MHI_CLOCK_RESET_CTRL 0x174 +#define PARF_MHI_BASE_ADDR_LOWER 0x178 +#define PARF_MHI_BASE_ADDR_UPPER 0x17c +#define PARF_DEBUG_INT_EN 0x190 +#define PARF_AXI_MSTR_RD_HALT_NO_WRITES 0x1a4 +#define PARF_AXI_MSTR_WR_ADDR_HALT 0x1a8 +#define PARF_Q2A_FLUSH 0x1ac +#define PARF_LTSSM 0x1b0 +#define PARF_CFG_BITS 0x210 +#define PARF_INT_ALL_STATUS 0x224 +#define PARF_INT_ALL_CLEAR 0x228 +#define PARF_INT_ALL_MASK 0x22c +#define PARF_SLV_ADDR_MSB_CTRL 0x2c0 +#define PARF_DBI_BASE_ADDR 0x350 +#define PARF_DBI_BASE_ADDR_HI 0x354 +#define PARF_SLV_ADDR_SPACE_SIZE 0x358 +#define PARF_SLV_ADDR_SPACE_SIZE_HI 0x35c +#define PARF_ATU_BASE_ADDR 0x634 +#define PARF_ATU_BASE_ADDR_HI 0x638 +#define PARF_SRIS_MODE 0x644 +#define PARF_DEBUG_CNT_PM_LINKST_IN_L2 0xc04 +#define PARF_DEBUG_CNT_PM_LINKST_IN_L1 0xc0c +#define PARF_DEBUG_CNT_PM_LINKST_IN_L0S 0xc10 +#define PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L1 0xc84 +#define PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L2 0xc88 +#define PARF_DEVICE_TYPE 0x1000 +#define PARF_BDF_TO_SID_CFG 0x2c00 + +/* PARF_INT_ALL_{STATUS/CLEAR/MASK} register fields */ +#define PARF_INT_ALL_LINK_DOWN BIT(1) +#define PARF_INT_ALL_BME BIT(2) +#define PARF_INT_ALL_PM_TURNOFF BIT(3) +#define PARF_INT_ALL_DEBUG BIT(4) +#define PARF_INT_ALL_LTR BIT(5) +#define PARF_INT_ALL_MHI_Q6 BIT(6) +#define PARF_INT_ALL_MHI_A7 BIT(7) +#define PARF_INT_ALL_DSTATE_CHANGE BIT(8) +#define PARF_INT_ALL_L1SUB_TIMEOUT BIT(9) +#define PARF_INT_ALL_MMIO_WRITE BIT(10) +#define PARF_INT_ALL_CFG_WRITE BIT(11) +#define PARF_INT_ALL_BRIDGE_FLUSH_N BIT(12) +#define PARF_INT_ALL_LINK_UP BIT(13) +#define PARF_INT_ALL_AER_LEGACY BIT(14) +#define PARF_INT_ALL_PLS_ERR BIT(15) +#define PARF_INT_ALL_PME_LEGACY BIT(16) +#define PARF_INT_ALL_PLS_PME BIT(17) + +/* PARF_BDF_TO_SID_CFG register fields */ +#define PARF_BDF_TO_SID_BYPASS BIT(0) + +/* PARF_DEBUG_INT_EN register fields */ +#define PARF_DEBUG_INT_PM_DSTATE_CHANGE BIT(1) +#define PARF_DEBUG_INT_CFG_BUS_MASTER_EN BIT(2) +#define PARF_DEBUG_INT_RADM_PM_TURNOFF BIT(3) + +/* PARF_DEVICE_TYPE register fields */ +#define PARF_DEVICE_TYPE_EP 0x0 + +/* PARF_PM_CTRL register fields */ +#define PARF_PM_CTRL_REQ_EXIT_L1 BIT(1) +#define PARF_PM_CTRL_READY_ENTR_L23 BIT(2) +#define PARF_PM_CTRL_REQ_NOT_ENTR_L1 BIT(5) + +/* PARF_MHI_CLOCK_RESET_CTRL fields */ +#define PARF_MSTR_AXI_CLK_EN BIT(1) + +/* PARF_AXI_MSTR_RD_HALT_NO_WRITES register fields */ +#define PARF_AXI_MSTR_RD_HALT_NO_WRITE_EN BIT(0) + +/* PARF_AXI_MSTR_WR_ADDR_HALT register fields */ +#define PARF_AXI_MSTR_WR_ADDR_HALT_EN BIT(31) + +/* PARF_Q2A_FLUSH register fields */ +#define PARF_Q2A_FLUSH_EN BIT(16) + +/* PARF_SYS_CTRL register fields */ +#define PARF_SYS_CTRL_AUX_PWR_DET BIT(4) +#define PARF_SYS_CTRL_CORE_CLK_CGC_DIS BIT(6) +#define PARF_SYS_CTRL_MSTR_ACLK_CGC_DIS BIT(10) +#define PARF_SYS_CTRL_SLV_DBI_WAKE_DISABLE BIT(11) + +/* PARF_DB_CTRL register fields */ +#define PARF_DB_CTRL_INSR_DBNCR_BLOCK BIT(0) +#define PARF_DB_CTRL_RMVL_DBNCR_BLOCK BIT(1) +#define PARF_DB_CTRL_DBI_WKP_BLOCK BIT(4) +#define PARF_DB_CTRL_SLV_WKP_BLOCK BIT(5) +#define PARF_DB_CTRL_MST_WKP_BLOCK BIT(6) + +/* PARF_CFG_BITS register fields */ +#define PARF_CFG_BITS_REQ_EXIT_L1SS_MSI_LTR_EN BIT(1) + +/* ELBI registers */ +#define ELBI_SYS_STTS 0x08 +#define ELBI_CS2_ENABLE 0xa4 + +/* DBI registers */ +#define DBI_CON_STATUS 0x44 + +/* DBI register fields */ +#define DBI_CON_STATUS_POWER_STATE_MASK GENMASK(1, 0) + +#define XMLH_LINK_UP 0x400 +#define CORE_RESET_TIME_US_MIN 1000 +#define CORE_RESET_TIME_US_MAX 1005 +#define WAKE_DELAY_US 2000 /* 2 ms */ + +#define to_pcie_ep(x) dev_get_drvdata((x)->dev) + +enum qcom_pcie_ep_link_status { + QCOM_PCIE_EP_LINK_DISABLED, + QCOM_PCIE_EP_LINK_ENABLED, + QCOM_PCIE_EP_LINK_UP, + QCOM_PCIE_EP_LINK_DOWN, +}; + +/** + * struct qcom_pcie_ep - Qualcomm PCIe Endpoint Controller + * @pci: Designware PCIe controller struct + * @parf: Qualcomm PCIe specific PARF register base + * @elbi: Designware PCIe specific ELBI register base + * @mmio: MMIO register base + * @perst_map: PERST regmap + * @mmio_res: MMIO region resource + * @core_reset: PCIe Endpoint core reset + * @reset: PERST# GPIO + * @wake: WAKE# GPIO + * @phy: PHY controller block + * @debugfs: PCIe Endpoint Debugfs directory + * @clks: PCIe clocks + * @num_clks: PCIe clocks count + * @perst_en: Flag for PERST enable + * @perst_sep_en: Flag for PERST separation enable + * @link_status: PCIe Link status + * @global_irq: Qualcomm PCIe specific Global IRQ + * @perst_irq: PERST# IRQ + */ +struct qcom_pcie_ep { + struct dw_pcie pci; + + void __iomem *parf; + void __iomem *elbi; + void __iomem *mmio; + struct regmap *perst_map; + struct resource *mmio_res; + + struct reset_control *core_reset; + struct gpio_desc *reset; + struct gpio_desc *wake; + struct phy *phy; + struct dentry *debugfs; + + struct clk_bulk_data *clks; + int num_clks; + + u32 perst_en; + u32 perst_sep_en; + + enum qcom_pcie_ep_link_status link_status; + int global_irq; + int perst_irq; +}; + +static int qcom_pcie_ep_core_reset(struct qcom_pcie_ep *pcie_ep) +{ + struct dw_pcie *pci = &pcie_ep->pci; + struct device *dev = pci->dev; + int ret; + + ret = reset_control_assert(pcie_ep->core_reset); + if (ret) { + dev_err(dev, "Cannot assert core reset\n"); + return ret; + } + + usleep_range(CORE_RESET_TIME_US_MIN, CORE_RESET_TIME_US_MAX); + + ret = reset_control_deassert(pcie_ep->core_reset); + if (ret) { + dev_err(dev, "Cannot de-assert core reset\n"); + return ret; + } + + usleep_range(CORE_RESET_TIME_US_MIN, CORE_RESET_TIME_US_MAX); + + return 0; +} + +/* + * Delatch PERST_EN and PERST_SEPARATION_ENABLE with TCSR to avoid + * device reset during host reboot and hibernation. The driver is + * expected to handle this situation. + */ +static void qcom_pcie_ep_configure_tcsr(struct qcom_pcie_ep *pcie_ep) +{ + if (pcie_ep->perst_map) { + regmap_write(pcie_ep->perst_map, pcie_ep->perst_en, 0); + regmap_write(pcie_ep->perst_map, pcie_ep->perst_sep_en, 0); + } +} + +static int qcom_pcie_dw_link_up(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + u32 reg; + + reg = readl_relaxed(pcie_ep->elbi + ELBI_SYS_STTS); + + return reg & XMLH_LINK_UP; +} + +static int qcom_pcie_dw_start_link(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + + enable_irq(pcie_ep->perst_irq); + + return 0; +} + +static void qcom_pcie_dw_stop_link(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + + disable_irq(pcie_ep->perst_irq); +} + +static void qcom_pcie_dw_write_dbi2(struct dw_pcie *pci, void __iomem *base, + u32 reg, size_t size, u32 val) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + int ret; + + writel(1, pcie_ep->elbi + ELBI_CS2_ENABLE); + + ret = dw_pcie_write(pci->dbi_base2 + reg, size, val); + if (ret) + dev_err(pci->dev, "Failed to write DBI2 register (0x%x): %d\n", reg, ret); + + writel(0, pcie_ep->elbi + ELBI_CS2_ENABLE); +} + +static int qcom_pcie_enable_resources(struct qcom_pcie_ep *pcie_ep) +{ + int ret; + + ret = clk_bulk_prepare_enable(pcie_ep->num_clks, pcie_ep->clks); + if (ret) + return ret; + + ret = qcom_pcie_ep_core_reset(pcie_ep); + if (ret) + goto err_disable_clk; + + ret = phy_init(pcie_ep->phy); + if (ret) + goto err_disable_clk; + + ret = phy_power_on(pcie_ep->phy); + if (ret) + goto err_phy_exit; + + return 0; + +err_phy_exit: + phy_exit(pcie_ep->phy); +err_disable_clk: + clk_bulk_disable_unprepare(pcie_ep->num_clks, pcie_ep->clks); + + return ret; +} + +static void qcom_pcie_disable_resources(struct qcom_pcie_ep *pcie_ep) +{ + phy_power_off(pcie_ep->phy); + phy_exit(pcie_ep->phy); + clk_bulk_disable_unprepare(pcie_ep->num_clks, pcie_ep->clks); +} + +static int qcom_pcie_perst_deassert(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + struct device *dev = pci->dev; + u32 val, offset; + int ret; + + ret = qcom_pcie_enable_resources(pcie_ep); + if (ret) { + dev_err(dev, "Failed to enable resources: %d\n", ret); + return ret; + } + + /* Assert WAKE# to RC to indicate device is ready */ + gpiod_set_value_cansleep(pcie_ep->wake, 1); + usleep_range(WAKE_DELAY_US, WAKE_DELAY_US + 500); + gpiod_set_value_cansleep(pcie_ep->wake, 0); + + qcom_pcie_ep_configure_tcsr(pcie_ep); + + /* Disable BDF to SID mapping */ + val = readl_relaxed(pcie_ep->parf + PARF_BDF_TO_SID_CFG); + val |= PARF_BDF_TO_SID_BYPASS; + writel_relaxed(val, pcie_ep->parf + PARF_BDF_TO_SID_CFG); + + /* Enable debug IRQ */ + val = readl_relaxed(pcie_ep->parf + PARF_DEBUG_INT_EN); + val |= PARF_DEBUG_INT_RADM_PM_TURNOFF | + PARF_DEBUG_INT_CFG_BUS_MASTER_EN | + PARF_DEBUG_INT_PM_DSTATE_CHANGE; + writel_relaxed(val, pcie_ep->parf + PARF_DEBUG_INT_EN); + + /* Configure PCIe to endpoint mode */ + writel_relaxed(PARF_DEVICE_TYPE_EP, pcie_ep->parf + PARF_DEVICE_TYPE); + + /* Allow entering L1 state */ + val = readl_relaxed(pcie_ep->parf + PARF_PM_CTRL); + val &= ~PARF_PM_CTRL_REQ_NOT_ENTR_L1; + writel_relaxed(val, pcie_ep->parf + PARF_PM_CTRL); + + /* Read halts write */ + val = readl_relaxed(pcie_ep->parf + PARF_AXI_MSTR_RD_HALT_NO_WRITES); + val &= ~PARF_AXI_MSTR_RD_HALT_NO_WRITE_EN; + writel_relaxed(val, pcie_ep->parf + PARF_AXI_MSTR_RD_HALT_NO_WRITES); + + /* Write after write halt */ + val = readl_relaxed(pcie_ep->parf + PARF_AXI_MSTR_WR_ADDR_HALT); + val |= PARF_AXI_MSTR_WR_ADDR_HALT_EN; + writel_relaxed(val, pcie_ep->parf + PARF_AXI_MSTR_WR_ADDR_HALT); + + /* Q2A flush disable */ + val = readl_relaxed(pcie_ep->parf + PARF_Q2A_FLUSH); + val &= ~PARF_Q2A_FLUSH_EN; + writel_relaxed(val, pcie_ep->parf + PARF_Q2A_FLUSH); + + /* + * Disable Master AXI clock during idle. Do not allow DBI access + * to take the core out of L1. Disable core clock gating that + * gates PIPE clock from propagating to core clock. Report to the + * host that Vaux is present. + */ + val = readl_relaxed(pcie_ep->parf + PARF_SYS_CTRL); + val &= ~PARF_SYS_CTRL_MSTR_ACLK_CGC_DIS; + val |= PARF_SYS_CTRL_SLV_DBI_WAKE_DISABLE | + PARF_SYS_CTRL_CORE_CLK_CGC_DIS | + PARF_SYS_CTRL_AUX_PWR_DET; + writel_relaxed(val, pcie_ep->parf + PARF_SYS_CTRL); + + /* Disable the debouncers */ + val = readl_relaxed(pcie_ep->parf + PARF_DB_CTRL); + val |= PARF_DB_CTRL_INSR_DBNCR_BLOCK | PARF_DB_CTRL_RMVL_DBNCR_BLOCK | + PARF_DB_CTRL_DBI_WKP_BLOCK | PARF_DB_CTRL_SLV_WKP_BLOCK | + PARF_DB_CTRL_MST_WKP_BLOCK; + writel_relaxed(val, pcie_ep->parf + PARF_DB_CTRL); + + /* Request to exit from L1SS for MSI and LTR MSG */ + val = readl_relaxed(pcie_ep->parf + PARF_CFG_BITS); + val |= PARF_CFG_BITS_REQ_EXIT_L1SS_MSI_LTR_EN; + writel_relaxed(val, pcie_ep->parf + PARF_CFG_BITS); + + dw_pcie_dbi_ro_wr_en(pci); + + /* Set the L0s Exit Latency to 2us-4us = 0x6 */ + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_L0SEL; + val |= FIELD_PREP(PCI_EXP_LNKCAP_L0SEL, 0x6); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, val); + + /* Set the L1 Exit Latency to be 32us-64 us = 0x6 */ + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + val = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_L1EL; + val |= FIELD_PREP(PCI_EXP_LNKCAP_L1EL, 0x6); + dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, val); + + dw_pcie_dbi_ro_wr_dis(pci); + + writel_relaxed(0, pcie_ep->parf + PARF_INT_ALL_MASK); + val = PARF_INT_ALL_LINK_DOWN | PARF_INT_ALL_BME | + PARF_INT_ALL_PM_TURNOFF | PARF_INT_ALL_DSTATE_CHANGE | + PARF_INT_ALL_LINK_UP; + writel_relaxed(val, pcie_ep->parf + PARF_INT_ALL_MASK); + + ret = dw_pcie_ep_init_complete(&pcie_ep->pci.ep); + if (ret) { + dev_err(dev, "Failed to complete initialization: %d\n", ret); + goto err_disable_resources; + } + + /* + * The physical address of the MMIO region which is exposed as the BAR + * should be written to MHI BASE registers. + */ + writel_relaxed(pcie_ep->mmio_res->start, + pcie_ep->parf + PARF_MHI_BASE_ADDR_LOWER); + writel_relaxed(0, pcie_ep->parf + PARF_MHI_BASE_ADDR_UPPER); + + /* Gate Master AXI clock to MHI bus during L1SS */ + val = readl_relaxed(pcie_ep->parf + PARF_MHI_CLOCK_RESET_CTRL); + val &= ~PARF_MSTR_AXI_CLK_EN; + writel_relaxed(val, pcie_ep->parf + PARF_MHI_CLOCK_RESET_CTRL); + + dw_pcie_ep_init_notify(&pcie_ep->pci.ep); + + /* Enable LTSSM */ + val = readl_relaxed(pcie_ep->parf + PARF_LTSSM); + val |= BIT(8); + writel_relaxed(val, pcie_ep->parf + PARF_LTSSM); + + return 0; + +err_disable_resources: + qcom_pcie_disable_resources(pcie_ep); + + return ret; +} + +static void qcom_pcie_perst_assert(struct dw_pcie *pci) +{ + struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); + struct device *dev = pci->dev; + + if (pcie_ep->link_status == QCOM_PCIE_EP_LINK_DISABLED) { + dev_dbg(dev, "Link is already disabled\n"); + return; + } + + qcom_pcie_disable_resources(pcie_ep); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_DISABLED; +} + +/* Common DWC controller ops */ +static const struct dw_pcie_ops pci_ops = { + .link_up = qcom_pcie_dw_link_up, + .start_link = qcom_pcie_dw_start_link, + .stop_link = qcom_pcie_dw_stop_link, + .write_dbi2 = qcom_pcie_dw_write_dbi2, +}; + +static int qcom_pcie_ep_get_io_resources(struct platform_device *pdev, + struct qcom_pcie_ep *pcie_ep) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci = &pcie_ep->pci; + struct device_node *syscon; + struct resource *res; + int ret; + + pcie_ep->parf = devm_platform_ioremap_resource_byname(pdev, "parf"); + if (IS_ERR(pcie_ep->parf)) + return PTR_ERR(pcie_ep->parf); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); + pci->dbi_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pci->dbi_base)) + return PTR_ERR(pci->dbi_base); + pci->dbi_base2 = pci->dbi_base; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "elbi"); + pcie_ep->elbi = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pcie_ep->elbi)) + return PTR_ERR(pcie_ep->elbi); + + pcie_ep->mmio_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "mmio"); + if (!pcie_ep->mmio_res) { + dev_err(dev, "Failed to get mmio resource\n"); + return -EINVAL; + } + + pcie_ep->mmio = devm_pci_remap_cfg_resource(dev, pcie_ep->mmio_res); + if (IS_ERR(pcie_ep->mmio)) + return PTR_ERR(pcie_ep->mmio); + + syscon = of_parse_phandle(dev->of_node, "qcom,perst-regs", 0); + if (!syscon) { + dev_dbg(dev, "PERST separation not available\n"); + return 0; + } + + pcie_ep->perst_map = syscon_node_to_regmap(syscon); + of_node_put(syscon); + if (IS_ERR(pcie_ep->perst_map)) + return PTR_ERR(pcie_ep->perst_map); + + ret = of_property_read_u32_index(dev->of_node, "qcom,perst-regs", + 1, &pcie_ep->perst_en); + if (ret < 0) { + dev_err(dev, "No Perst Enable offset in syscon\n"); + return ret; + } + + ret = of_property_read_u32_index(dev->of_node, "qcom,perst-regs", + 2, &pcie_ep->perst_sep_en); + if (ret < 0) { + dev_err(dev, "No Perst Separation Enable offset in syscon\n"); + return ret; + } + + return 0; +} + +static int qcom_pcie_ep_get_resources(struct platform_device *pdev, + struct qcom_pcie_ep *pcie_ep) +{ + struct device *dev = &pdev->dev; + int ret; + + ret = qcom_pcie_ep_get_io_resources(pdev, pcie_ep); + if (ret) { + dev_err(dev, "Failed to get io resources %d\n", ret); + return ret; + } + + pcie_ep->num_clks = devm_clk_bulk_get_all(dev, &pcie_ep->clks); + if (pcie_ep->num_clks < 0) { + dev_err(dev, "Failed to get clocks\n"); + return pcie_ep->num_clks; + } + + pcie_ep->core_reset = devm_reset_control_get_exclusive(dev, "core"); + if (IS_ERR(pcie_ep->core_reset)) + return PTR_ERR(pcie_ep->core_reset); + + pcie_ep->reset = devm_gpiod_get(dev, "reset", GPIOD_IN); + if (IS_ERR(pcie_ep->reset)) + return PTR_ERR(pcie_ep->reset); + + pcie_ep->wake = devm_gpiod_get_optional(dev, "wake", GPIOD_OUT_LOW); + if (IS_ERR(pcie_ep->wake)) + return PTR_ERR(pcie_ep->wake); + + pcie_ep->phy = devm_phy_optional_get(dev, "pciephy"); + if (IS_ERR(pcie_ep->phy)) + ret = PTR_ERR(pcie_ep->phy); + + return ret; +} + +/* TODO: Notify clients about PCIe state change */ +static irqreturn_t qcom_pcie_ep_global_irq_thread(int irq, void *data) +{ + struct qcom_pcie_ep *pcie_ep = data; + struct dw_pcie *pci = &pcie_ep->pci; + struct device *dev = pci->dev; + u32 status = readl_relaxed(pcie_ep->parf + PARF_INT_ALL_STATUS); + u32 mask = readl_relaxed(pcie_ep->parf + PARF_INT_ALL_MASK); + u32 dstate, val; + + writel_relaxed(status, pcie_ep->parf + PARF_INT_ALL_CLEAR); + status &= mask; + + if (FIELD_GET(PARF_INT_ALL_LINK_DOWN, status)) { + dev_dbg(dev, "Received Linkdown event\n"); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_DOWN; + } else if (FIELD_GET(PARF_INT_ALL_BME, status)) { + dev_dbg(dev, "Received BME event. Link is enabled!\n"); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_ENABLED; + } else if (FIELD_GET(PARF_INT_ALL_PM_TURNOFF, status)) { + dev_dbg(dev, "Received PM Turn-off event! Entering L23\n"); + val = readl_relaxed(pcie_ep->parf + PARF_PM_CTRL); + val |= PARF_PM_CTRL_READY_ENTR_L23; + writel_relaxed(val, pcie_ep->parf + PARF_PM_CTRL); + } else if (FIELD_GET(PARF_INT_ALL_DSTATE_CHANGE, status)) { + dstate = dw_pcie_readl_dbi(pci, DBI_CON_STATUS) & + DBI_CON_STATUS_POWER_STATE_MASK; + dev_dbg(dev, "Received D%d state event\n", dstate); + if (dstate == 3) { + val = readl_relaxed(pcie_ep->parf + PARF_PM_CTRL); + val |= PARF_PM_CTRL_REQ_EXIT_L1; + writel_relaxed(val, pcie_ep->parf + PARF_PM_CTRL); + } + } else if (FIELD_GET(PARF_INT_ALL_LINK_UP, status)) { + dev_dbg(dev, "Received Linkup event. Enumeration complete!\n"); + dw_pcie_ep_linkup(&pci->ep); + pcie_ep->link_status = QCOM_PCIE_EP_LINK_UP; + } else { + dev_dbg(dev, "Received unknown event: %d\n", status); + } + + return IRQ_HANDLED; +} + +static irqreturn_t qcom_pcie_ep_perst_irq_thread(int irq, void *data) +{ + struct qcom_pcie_ep *pcie_ep = data; + struct dw_pcie *pci = &pcie_ep->pci; + struct device *dev = pci->dev; + u32 perst; + + perst = gpiod_get_value(pcie_ep->reset); + if (perst) { + dev_dbg(dev, "PERST asserted by host. Shutting down the PCIe link!\n"); + qcom_pcie_perst_assert(pci); + } else { + dev_dbg(dev, "PERST de-asserted by host. Starting link training!\n"); + qcom_pcie_perst_deassert(pci); + } + + irq_set_irq_type(gpiod_to_irq(pcie_ep->reset), + (perst ? IRQF_TRIGGER_HIGH : IRQF_TRIGGER_LOW)); + + return IRQ_HANDLED; +} + +static int qcom_pcie_ep_enable_irq_resources(struct platform_device *pdev, + struct qcom_pcie_ep *pcie_ep) +{ + int ret; + + pcie_ep->global_irq = platform_get_irq_byname(pdev, "global"); + if (pcie_ep->global_irq < 0) + return pcie_ep->global_irq; + + ret = devm_request_threaded_irq(&pdev->dev, pcie_ep->global_irq, NULL, + qcom_pcie_ep_global_irq_thread, + IRQF_ONESHOT, + "global_irq", pcie_ep); + if (ret) { + dev_err(&pdev->dev, "Failed to request Global IRQ\n"); + return ret; + } + + pcie_ep->perst_irq = gpiod_to_irq(pcie_ep->reset); + irq_set_status_flags(pcie_ep->perst_irq, IRQ_NOAUTOEN); + ret = devm_request_threaded_irq(&pdev->dev, pcie_ep->perst_irq, NULL, + qcom_pcie_ep_perst_irq_thread, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + "perst_irq", pcie_ep); + if (ret) { + dev_err(&pdev->dev, "Failed to request PERST IRQ\n"); + disable_irq(pcie_ep->global_irq); + return ret; + } + + return 0; +} + +static int qcom_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + enum pci_epc_irq_type type, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + return dw_pcie_ep_raise_legacy_irq(ep, func_no); + case PCI_EPC_IRQ_MSI: + return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num); + default: + dev_err(pci->dev, "Unknown IRQ type\n"); + return -EINVAL; + } +} + +static int qcom_pcie_ep_link_transition_count(struct seq_file *s, void *data) +{ + struct qcom_pcie_ep *pcie_ep = (struct qcom_pcie_ep *) + dev_get_drvdata(s->private); + + seq_printf(s, "L0s transition count: %u\n", + readl_relaxed(pcie_ep->mmio + PARF_DEBUG_CNT_PM_LINKST_IN_L0S)); + + seq_printf(s, "L1 transition count: %u\n", + readl_relaxed(pcie_ep->mmio + PARF_DEBUG_CNT_PM_LINKST_IN_L1)); + + seq_printf(s, "L1.1 transition count: %u\n", + readl_relaxed(pcie_ep->mmio + PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L1)); + + seq_printf(s, "L1.2 transition count: %u\n", + readl_relaxed(pcie_ep->mmio + PARF_DEBUG_CNT_AUX_CLK_IN_L1SUB_L2)); + + seq_printf(s, "L2 transition count: %u\n", + readl_relaxed(pcie_ep->mmio + PARF_DEBUG_CNT_PM_LINKST_IN_L2)); + + return 0; +} + +static void qcom_pcie_ep_init_debugfs(struct qcom_pcie_ep *pcie_ep) +{ + struct dw_pcie *pci = &pcie_ep->pci; + + debugfs_create_devm_seqfile(pci->dev, "link_transition_count", pcie_ep->debugfs, + qcom_pcie_ep_link_transition_count); +} + +static const struct pci_epc_features qcom_pcie_epc_features = { + .linkup_notifier = true, + .core_init_notifier = true, + .msi_capable = true, + .msix_capable = false, +}; + +static const struct pci_epc_features * +qcom_pcie_epc_get_features(struct dw_pcie_ep *pci_ep) +{ + return &qcom_pcie_epc_features; +} + +static void qcom_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar; + + for (bar = BAR_0; bar <= BAR_5; bar++) + dw_pcie_ep_reset_bar(pci, bar); +} + +static const struct dw_pcie_ep_ops pci_ep_ops = { + .ep_init = qcom_pcie_ep_init, + .raise_irq = qcom_pcie_ep_raise_irq, + .get_features = qcom_pcie_epc_get_features, +}; + +static int qcom_pcie_ep_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct qcom_pcie_ep *pcie_ep; + char *name; + int ret; + + pcie_ep = devm_kzalloc(dev, sizeof(*pcie_ep), GFP_KERNEL); + if (!pcie_ep) + return -ENOMEM; + + pcie_ep->pci.dev = dev; + pcie_ep->pci.ops = &pci_ops; + pcie_ep->pci.ep.ops = &pci_ep_ops; + platform_set_drvdata(pdev, pcie_ep); + + ret = qcom_pcie_ep_get_resources(pdev, pcie_ep); + if (ret) + return ret; + + ret = qcom_pcie_enable_resources(pcie_ep); + if (ret) { + dev_err(dev, "Failed to enable resources: %d\n", ret); + return ret; + } + + ret = dw_pcie_ep_init(&pcie_ep->pci.ep); + if (ret) { + dev_err(dev, "Failed to initialize endpoint: %d\n", ret); + goto err_disable_resources; + } + + ret = qcom_pcie_ep_enable_irq_resources(pdev, pcie_ep); + if (ret) + goto err_disable_resources; + + name = devm_kasprintf(dev, GFP_KERNEL, "%pOFP", dev->of_node); + if (!name) { + ret = -ENOMEM; + goto err_disable_irqs; + } + + pcie_ep->debugfs = debugfs_create_dir(name, NULL); + qcom_pcie_ep_init_debugfs(pcie_ep); + + return 0; + +err_disable_irqs: + disable_irq(pcie_ep->global_irq); + disable_irq(pcie_ep->perst_irq); + +err_disable_resources: + qcom_pcie_disable_resources(pcie_ep); + + return ret; +} + +static int qcom_pcie_ep_remove(struct platform_device *pdev) +{ + struct qcom_pcie_ep *pcie_ep = platform_get_drvdata(pdev); + + disable_irq(pcie_ep->global_irq); + disable_irq(pcie_ep->perst_irq); + + debugfs_remove_recursive(pcie_ep->debugfs); + + if (pcie_ep->link_status == QCOM_PCIE_EP_LINK_DISABLED) + return 0; + + qcom_pcie_disable_resources(pcie_ep); + + return 0; +} + +static const struct of_device_id qcom_pcie_ep_match[] = { + { .compatible = "qcom,sdx55-pcie-ep", }, + { .compatible = "qcom,sm8450-pcie-ep", }, + { } +}; +MODULE_DEVICE_TABLE(of, qcom_pcie_ep_match); + +static struct platform_driver qcom_pcie_ep_driver = { + .probe = qcom_pcie_ep_probe, + .remove = qcom_pcie_ep_remove, + .driver = { + .name = "qcom-pcie-ep", + .of_match_table = qcom_pcie_ep_match, + }, +}; +builtin_platform_driver(qcom_pcie_ep_driver); + +MODULE_AUTHOR("Siddartha Mohanadoss <smohanad@codeaurora.org>"); +MODULE_AUTHOR("Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>"); +MODULE_DESCRIPTION("Qualcomm PCIe Endpoint controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c new file mode 100644 index 000000000..0ccd92faf --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -0,0 +1,1799 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Qualcomm PCIe root complex driver + * + * Copyright (c) 2014-2015, The Linux Foundation. All rights reserved. + * Copyright 2015 Linaro Limited. + * + * Author: Stanimir Varbanov <svarbanov@mm-sol.com> + */ + +#include <linux/clk.h> +#include <linux/crc8.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/iopoll.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of_device.h> +#include <linux/of_gpio.h> +#include <linux/pci.h> +#include <linux/pm_runtime.h> +#include <linux/platform_device.h> +#include <linux/phy/phy.h> +#include <linux/regulator/consumer.h> +#include <linux/reset.h> +#include <linux/slab.h> +#include <linux/types.h> + +#include "../../pci.h" +#include "pcie-designware.h" + +/* PARF registers */ +#define PARF_SYS_CTRL 0x00 +#define PARF_PM_CTRL 0x20 +#define PARF_PCS_DEEMPH 0x34 +#define PARF_PCS_SWING 0x38 +#define PARF_PHY_CTRL 0x40 +#define PARF_PHY_REFCLK 0x4c +#define PARF_CONFIG_BITS 0x50 +#define PARF_DBI_BASE_ADDR 0x168 +#define PARF_MHI_CLOCK_RESET_CTRL 0x174 +#define PARF_AXI_MSTR_WR_ADDR_HALT 0x178 +#define PARF_AXI_MSTR_WR_ADDR_HALT_V2 0x1a8 +#define PARF_Q2A_FLUSH 0x1ac +#define PARF_LTSSM 0x1b0 +#define PARF_SID_OFFSET 0x234 +#define PARF_BDF_TRANSLATE_CFG 0x24c +#define PARF_SLV_ADDR_SPACE_SIZE 0x358 +#define PARF_DEVICE_TYPE 0x1000 +#define PARF_BDF_TO_SID_TABLE_N 0x2000 + +/* ELBI registers */ +#define ELBI_SYS_CTRL 0x04 + +/* DBI registers */ +#define AXI_MSTR_RESP_COMP_CTRL0 0x818 +#define AXI_MSTR_RESP_COMP_CTRL1 0x81c + +/* PARF_SYS_CTRL register fields */ +#define MST_WAKEUP_EN BIT(13) +#define SLV_WAKEUP_EN BIT(12) +#define MSTR_ACLK_CGC_DIS BIT(10) +#define SLV_ACLK_CGC_DIS BIT(9) +#define CORE_CLK_CGC_DIS BIT(6) +#define AUX_PWR_DET BIT(4) +#define L23_CLK_RMV_DIS BIT(2) +#define L1_CLK_RMV_DIS BIT(1) + +/* PARF_PM_CTRL register fields */ +#define REQ_NOT_ENTR_L1 BIT(5) + +/* PARF_PCS_DEEMPH register fields */ +#define PCS_DEEMPH_TX_DEEMPH_GEN1(x) ((x) << 16) +#define PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(x) ((x) << 8) +#define PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(x) ((x) << 0) + +/* PARF_PCS_SWING register fields */ +#define PCS_SWING_TX_SWING_FULL(x) ((x) << 8) +#define PCS_SWING_TX_SWING_LOW(x) ((x) << 0) + +/* PARF_PHY_CTRL register fields */ +#define PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK GENMASK(20, 16) +#define PHY_CTRL_PHY_TX0_TERM_OFFSET(x) ((x) << 16) + +/* PARF_PHY_REFCLK register fields */ +#define PHY_REFCLK_SSP_EN BIT(16) +#define PHY_REFCLK_USE_PAD BIT(12) + +/* PARF_CONFIG_BITS register fields */ +#define PHY_RX0_EQ(x) ((x) << 24) + +/* PARF_SLV_ADDR_SPACE_SIZE register value */ +#define SLV_ADDR_SPACE_SZ 0x10000000 + +/* PARF_MHI_CLOCK_RESET_CTRL register fields */ +#define AHB_CLK_EN BIT(0) +#define MSTR_AXI_CLK_EN BIT(1) +#define BYPASS BIT(4) + +/* PARF_DEVICE_TYPE register fields */ +#define DEVICE_TYPE_RC 0x4 + +/* ELBI_SYS_CTRL register fields */ +#define ELBI_SYS_CTRL_LT_ENABLE BIT(0) + +/* AXI_MSTR_RESP_COMP_CTRL0 register fields */ +#define CFG_REMOTE_RD_REQ_BRIDGE_SIZE_2K 0x4 +#define CFG_REMOTE_RD_REQ_BRIDGE_SIZE_4K 0x5 + +/* AXI_MSTR_RESP_COMP_CTRL1 register fields */ +#define CFG_BRIDGE_SB_INIT BIT(0) + +/* PCI_EXP_SLTCAP register fields */ +#define PCIE_CAP_SLOT_POWER_LIMIT_VAL FIELD_PREP(PCI_EXP_SLTCAP_SPLV, 250) +#define PCIE_CAP_SLOT_POWER_LIMIT_SCALE FIELD_PREP(PCI_EXP_SLTCAP_SPLS, 1) +#define PCIE_CAP_SLOT_VAL (PCI_EXP_SLTCAP_ABP | \ + PCI_EXP_SLTCAP_PCP | \ + PCI_EXP_SLTCAP_MRLSP | \ + PCI_EXP_SLTCAP_AIP | \ + PCI_EXP_SLTCAP_PIP | \ + PCI_EXP_SLTCAP_HPS | \ + PCI_EXP_SLTCAP_HPC | \ + PCI_EXP_SLTCAP_EIP | \ + PCIE_CAP_SLOT_POWER_LIMIT_VAL | \ + PCIE_CAP_SLOT_POWER_LIMIT_SCALE) + +#define PERST_DELAY_US 1000 + +#define QCOM_PCIE_2_1_0_MAX_SUPPLY 3 +#define QCOM_PCIE_2_1_0_MAX_CLOCKS 5 + +#define QCOM_PCIE_CRC8_POLYNOMIAL (BIT(2) | BIT(1) | BIT(0)) + +struct qcom_pcie_resources_2_1_0 { + struct clk_bulk_data clks[QCOM_PCIE_2_1_0_MAX_CLOCKS]; + struct reset_control *pci_reset; + struct reset_control *axi_reset; + struct reset_control *ahb_reset; + struct reset_control *por_reset; + struct reset_control *phy_reset; + struct reset_control *ext_reset; + struct regulator_bulk_data supplies[QCOM_PCIE_2_1_0_MAX_SUPPLY]; +}; + +struct qcom_pcie_resources_1_0_0 { + struct clk *iface; + struct clk *aux; + struct clk *master_bus; + struct clk *slave_bus; + struct reset_control *core; + struct regulator *vdda; +}; + +#define QCOM_PCIE_2_3_2_MAX_SUPPLY 2 +struct qcom_pcie_resources_2_3_2 { + struct clk *aux_clk; + struct clk *master_clk; + struct clk *slave_clk; + struct clk *cfg_clk; + struct regulator_bulk_data supplies[QCOM_PCIE_2_3_2_MAX_SUPPLY]; +}; + +#define QCOM_PCIE_2_4_0_MAX_CLOCKS 4 +struct qcom_pcie_resources_2_4_0 { + struct clk_bulk_data clks[QCOM_PCIE_2_4_0_MAX_CLOCKS]; + int num_clks; + struct reset_control *axi_m_reset; + struct reset_control *axi_s_reset; + struct reset_control *pipe_reset; + struct reset_control *axi_m_vmid_reset; + struct reset_control *axi_s_xpu_reset; + struct reset_control *parf_reset; + struct reset_control *phy_reset; + struct reset_control *axi_m_sticky_reset; + struct reset_control *pipe_sticky_reset; + struct reset_control *pwr_reset; + struct reset_control *ahb_reset; + struct reset_control *phy_ahb_reset; +}; + +struct qcom_pcie_resources_2_3_3 { + struct clk *iface; + struct clk *axi_m_clk; + struct clk *axi_s_clk; + struct clk *ahb_clk; + struct clk *aux_clk; + struct reset_control *rst[7]; +}; + +/* 6 clocks typically, 7 for sm8250 */ +struct qcom_pcie_resources_2_7_0 { + struct clk_bulk_data clks[12]; + int num_clks; + struct regulator_bulk_data supplies[2]; + struct reset_control *pci_reset; +}; + +struct qcom_pcie_resources_2_9_0 { + struct clk_bulk_data clks[5]; + struct reset_control *rst; +}; + +union qcom_pcie_resources { + struct qcom_pcie_resources_1_0_0 v1_0_0; + struct qcom_pcie_resources_2_1_0 v2_1_0; + struct qcom_pcie_resources_2_3_2 v2_3_2; + struct qcom_pcie_resources_2_3_3 v2_3_3; + struct qcom_pcie_resources_2_4_0 v2_4_0; + struct qcom_pcie_resources_2_7_0 v2_7_0; + struct qcom_pcie_resources_2_9_0 v2_9_0; +}; + +struct qcom_pcie; + +struct qcom_pcie_ops { + int (*get_resources)(struct qcom_pcie *pcie); + int (*init)(struct qcom_pcie *pcie); + int (*post_init)(struct qcom_pcie *pcie); + void (*deinit)(struct qcom_pcie *pcie); + void (*ltssm_enable)(struct qcom_pcie *pcie); + int (*config_sid)(struct qcom_pcie *pcie); +}; + +struct qcom_pcie_cfg { + const struct qcom_pcie_ops *ops; +}; + +struct qcom_pcie { + struct dw_pcie *pci; + void __iomem *parf; /* DT parf */ + void __iomem *elbi; /* DT elbi */ + union qcom_pcie_resources res; + struct phy *phy; + struct gpio_desc *reset; + const struct qcom_pcie_cfg *cfg; +}; + +#define to_qcom_pcie(x) dev_get_drvdata((x)->dev) + +static void qcom_ep_reset_assert(struct qcom_pcie *pcie) +{ + gpiod_set_value_cansleep(pcie->reset, 1); + usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500); +} + +static void qcom_ep_reset_deassert(struct qcom_pcie *pcie) +{ + /* Ensure that PERST has been asserted for at least 100 ms */ + msleep(100); + gpiod_set_value_cansleep(pcie->reset, 0); + usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500); +} + +static int qcom_pcie_start_link(struct dw_pcie *pci) +{ + struct qcom_pcie *pcie = to_qcom_pcie(pci); + + /* Enable Link Training state machine */ + if (pcie->cfg->ops->ltssm_enable) + pcie->cfg->ops->ltssm_enable(pcie); + + return 0; +} + +static void qcom_pcie_2_1_0_ltssm_enable(struct qcom_pcie *pcie) +{ + u32 val; + + /* enable link training */ + val = readl(pcie->elbi + ELBI_SYS_CTRL); + val |= ELBI_SYS_CTRL_LT_ENABLE; + writel(val, pcie->elbi + ELBI_SYS_CTRL); +} + +static int qcom_pcie_get_resources_2_1_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int ret; + + res->supplies[0].supply = "vdda"; + res->supplies[1].supply = "vdda_phy"; + res->supplies[2].supply = "vdda_refclk"; + ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(res->supplies), + res->supplies); + if (ret) + return ret; + + res->clks[0].id = "iface"; + res->clks[1].id = "core"; + res->clks[2].id = "phy"; + res->clks[3].id = "aux"; + res->clks[4].id = "ref"; + + /* iface, core, phy are required */ + ret = devm_clk_bulk_get(dev, 3, res->clks); + if (ret < 0) + return ret; + + /* aux, ref are optional */ + ret = devm_clk_bulk_get_optional(dev, 2, res->clks + 3); + if (ret < 0) + return ret; + + res->pci_reset = devm_reset_control_get_exclusive(dev, "pci"); + if (IS_ERR(res->pci_reset)) + return PTR_ERR(res->pci_reset); + + res->axi_reset = devm_reset_control_get_exclusive(dev, "axi"); + if (IS_ERR(res->axi_reset)) + return PTR_ERR(res->axi_reset); + + res->ahb_reset = devm_reset_control_get_exclusive(dev, "ahb"); + if (IS_ERR(res->ahb_reset)) + return PTR_ERR(res->ahb_reset); + + res->por_reset = devm_reset_control_get_exclusive(dev, "por"); + if (IS_ERR(res->por_reset)) + return PTR_ERR(res->por_reset); + + res->ext_reset = devm_reset_control_get_optional_exclusive(dev, "ext"); + if (IS_ERR(res->ext_reset)) + return PTR_ERR(res->ext_reset); + + res->phy_reset = devm_reset_control_get_exclusive(dev, "phy"); + return PTR_ERR_OR_ZERO(res->phy_reset); +} + +static void qcom_pcie_deinit_2_1_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0; + + clk_bulk_disable_unprepare(ARRAY_SIZE(res->clks), res->clks); + reset_control_assert(res->pci_reset); + reset_control_assert(res->axi_reset); + reset_control_assert(res->ahb_reset); + reset_control_assert(res->por_reset); + reset_control_assert(res->ext_reset); + reset_control_assert(res->phy_reset); + + writel(1, pcie->parf + PARF_PHY_CTRL); + + regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); +} + +static int qcom_pcie_init_2_1_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int ret; + + /* reset the PCIe interface as uboot can leave it undefined state */ + reset_control_assert(res->pci_reset); + reset_control_assert(res->axi_reset); + reset_control_assert(res->ahb_reset); + reset_control_assert(res->por_reset); + reset_control_assert(res->ext_reset); + reset_control_assert(res->phy_reset); + + ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies); + if (ret < 0) { + dev_err(dev, "cannot enable regulators\n"); + return ret; + } + + ret = reset_control_deassert(res->ahb_reset); + if (ret) { + dev_err(dev, "cannot deassert ahb reset\n"); + goto err_deassert_ahb; + } + + ret = reset_control_deassert(res->ext_reset); + if (ret) { + dev_err(dev, "cannot deassert ext reset\n"); + goto err_deassert_ext; + } + + ret = reset_control_deassert(res->phy_reset); + if (ret) { + dev_err(dev, "cannot deassert phy reset\n"); + goto err_deassert_phy; + } + + ret = reset_control_deassert(res->pci_reset); + if (ret) { + dev_err(dev, "cannot deassert pci reset\n"); + goto err_deassert_pci; + } + + ret = reset_control_deassert(res->por_reset); + if (ret) { + dev_err(dev, "cannot deassert por reset\n"); + goto err_deassert_por; + } + + ret = reset_control_deassert(res->axi_reset); + if (ret) { + dev_err(dev, "cannot deassert axi reset\n"); + goto err_deassert_axi; + } + + return 0; + +err_deassert_axi: + reset_control_assert(res->por_reset); +err_deassert_por: + reset_control_assert(res->pci_reset); +err_deassert_pci: + reset_control_assert(res->phy_reset); +err_deassert_phy: + reset_control_assert(res->ext_reset); +err_deassert_ext: + reset_control_assert(res->ahb_reset); +err_deassert_ahb: + regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); + + return ret; +} + +static int qcom_pcie_post_init_2_1_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + struct device_node *node = dev->of_node; + u32 val; + int ret; + + /* enable PCIe clocks and resets */ + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~BIT(0); + writel(val, pcie->parf + PARF_PHY_CTRL); + + ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks); + if (ret) + return ret; + + if (of_device_is_compatible(node, "qcom,pcie-ipq8064") || + of_device_is_compatible(node, "qcom,pcie-ipq8064-v2")) { + writel(PCS_DEEMPH_TX_DEEMPH_GEN1(24) | + PCS_DEEMPH_TX_DEEMPH_GEN2_3_5DB(24) | + PCS_DEEMPH_TX_DEEMPH_GEN2_6DB(34), + pcie->parf + PARF_PCS_DEEMPH); + writel(PCS_SWING_TX_SWING_FULL(120) | + PCS_SWING_TX_SWING_LOW(120), + pcie->parf + PARF_PCS_SWING); + writel(PHY_RX0_EQ(4), pcie->parf + PARF_CONFIG_BITS); + } + + if (of_device_is_compatible(node, "qcom,pcie-ipq8064")) { + /* set TX termination offset */ + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK; + val |= PHY_CTRL_PHY_TX0_TERM_OFFSET(7); + writel(val, pcie->parf + PARF_PHY_CTRL); + } + + /* enable external reference clock */ + val = readl(pcie->parf + PARF_PHY_REFCLK); + /* USE_PAD is required only for ipq806x */ + if (!of_device_is_compatible(node, "qcom,pcie-apq8064")) + val &= ~PHY_REFCLK_USE_PAD; + val |= PHY_REFCLK_SSP_EN; + writel(val, pcie->parf + PARF_PHY_REFCLK); + + /* wait for clock acquisition */ + usleep_range(1000, 1500); + + /* Set the Max TLP size to 2K, instead of using default of 4K */ + writel(CFG_REMOTE_RD_REQ_BRIDGE_SIZE_2K, + pci->dbi_base + AXI_MSTR_RESP_COMP_CTRL0); + writel(CFG_BRIDGE_SB_INIT, + pci->dbi_base + AXI_MSTR_RESP_COMP_CTRL1); + + return 0; +} + +static int qcom_pcie_get_resources_1_0_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_1_0_0 *res = &pcie->res.v1_0_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + + res->vdda = devm_regulator_get(dev, "vdda"); + if (IS_ERR(res->vdda)) + return PTR_ERR(res->vdda); + + res->iface = devm_clk_get(dev, "iface"); + if (IS_ERR(res->iface)) + return PTR_ERR(res->iface); + + res->aux = devm_clk_get(dev, "aux"); + if (IS_ERR(res->aux)) + return PTR_ERR(res->aux); + + res->master_bus = devm_clk_get(dev, "master_bus"); + if (IS_ERR(res->master_bus)) + return PTR_ERR(res->master_bus); + + res->slave_bus = devm_clk_get(dev, "slave_bus"); + if (IS_ERR(res->slave_bus)) + return PTR_ERR(res->slave_bus); + + res->core = devm_reset_control_get_exclusive(dev, "core"); + return PTR_ERR_OR_ZERO(res->core); +} + +static void qcom_pcie_deinit_1_0_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_1_0_0 *res = &pcie->res.v1_0_0; + + reset_control_assert(res->core); + clk_disable_unprepare(res->slave_bus); + clk_disable_unprepare(res->master_bus); + clk_disable_unprepare(res->iface); + clk_disable_unprepare(res->aux); + regulator_disable(res->vdda); +} + +static int qcom_pcie_init_1_0_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_1_0_0 *res = &pcie->res.v1_0_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int ret; + + ret = reset_control_deassert(res->core); + if (ret) { + dev_err(dev, "cannot deassert core reset\n"); + return ret; + } + + ret = clk_prepare_enable(res->aux); + if (ret) { + dev_err(dev, "cannot prepare/enable aux clock\n"); + goto err_res; + } + + ret = clk_prepare_enable(res->iface); + if (ret) { + dev_err(dev, "cannot prepare/enable iface clock\n"); + goto err_aux; + } + + ret = clk_prepare_enable(res->master_bus); + if (ret) { + dev_err(dev, "cannot prepare/enable master_bus clock\n"); + goto err_iface; + } + + ret = clk_prepare_enable(res->slave_bus); + if (ret) { + dev_err(dev, "cannot prepare/enable slave_bus clock\n"); + goto err_master; + } + + ret = regulator_enable(res->vdda); + if (ret) { + dev_err(dev, "cannot enable vdda regulator\n"); + goto err_slave; + } + + return 0; +err_slave: + clk_disable_unprepare(res->slave_bus); +err_master: + clk_disable_unprepare(res->master_bus); +err_iface: + clk_disable_unprepare(res->iface); +err_aux: + clk_disable_unprepare(res->aux); +err_res: + reset_control_assert(res->core); + + return ret; +} + +static int qcom_pcie_post_init_1_0_0(struct qcom_pcie *pcie) +{ + /* change DBI base address */ + writel(0, pcie->parf + PARF_DBI_BASE_ADDR); + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + u32 val = readl(pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT); + + val |= BIT(31); + writel(val, pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT); + } + + return 0; +} + +static void qcom_pcie_2_3_2_ltssm_enable(struct qcom_pcie *pcie) +{ + u32 val; + + /* enable link training */ + val = readl(pcie->parf + PARF_LTSSM); + val |= BIT(8); + writel(val, pcie->parf + PARF_LTSSM); +} + +static int qcom_pcie_get_resources_2_3_2(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_3_2 *res = &pcie->res.v2_3_2; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int ret; + + res->supplies[0].supply = "vdda"; + res->supplies[1].supply = "vddpe-3v3"; + ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(res->supplies), + res->supplies); + if (ret) + return ret; + + res->aux_clk = devm_clk_get(dev, "aux"); + if (IS_ERR(res->aux_clk)) + return PTR_ERR(res->aux_clk); + + res->cfg_clk = devm_clk_get(dev, "cfg"); + if (IS_ERR(res->cfg_clk)) + return PTR_ERR(res->cfg_clk); + + res->master_clk = devm_clk_get(dev, "bus_master"); + if (IS_ERR(res->master_clk)) + return PTR_ERR(res->master_clk); + + res->slave_clk = devm_clk_get(dev, "bus_slave"); + if (IS_ERR(res->slave_clk)) + return PTR_ERR(res->slave_clk); + + return 0; +} + +static void qcom_pcie_deinit_2_3_2(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_3_2 *res = &pcie->res.v2_3_2; + + clk_disable_unprepare(res->slave_clk); + clk_disable_unprepare(res->master_clk); + clk_disable_unprepare(res->cfg_clk); + clk_disable_unprepare(res->aux_clk); + + regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); +} + +static int qcom_pcie_init_2_3_2(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_3_2 *res = &pcie->res.v2_3_2; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int ret; + + ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies); + if (ret < 0) { + dev_err(dev, "cannot enable regulators\n"); + return ret; + } + + ret = clk_prepare_enable(res->aux_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable aux clock\n"); + goto err_aux_clk; + } + + ret = clk_prepare_enable(res->cfg_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable cfg clock\n"); + goto err_cfg_clk; + } + + ret = clk_prepare_enable(res->master_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable master clock\n"); + goto err_master_clk; + } + + ret = clk_prepare_enable(res->slave_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable slave clock\n"); + goto err_slave_clk; + } + + return 0; + +err_slave_clk: + clk_disable_unprepare(res->master_clk); +err_master_clk: + clk_disable_unprepare(res->cfg_clk); +err_cfg_clk: + clk_disable_unprepare(res->aux_clk); + +err_aux_clk: + regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); + + return ret; +} + +static int qcom_pcie_post_init_2_3_2(struct qcom_pcie *pcie) +{ + u32 val; + + /* enable PCIe clocks and resets */ + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~BIT(0); + writel(val, pcie->parf + PARF_PHY_CTRL); + + /* change DBI base address */ + writel(0, pcie->parf + PARF_DBI_BASE_ADDR); + + /* MAC PHY_POWERDOWN MUX DISABLE */ + val = readl(pcie->parf + PARF_SYS_CTRL); + val &= ~BIT(29); + writel(val, pcie->parf + PARF_SYS_CTRL); + + val = readl(pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); + val |= BIT(4); + writel(val, pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); + + val = readl(pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2); + val |= BIT(31); + writel(val, pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2); + + return 0; +} + +static int qcom_pcie_get_resources_2_4_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_4_0 *res = &pcie->res.v2_4_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + bool is_ipq = of_device_is_compatible(dev->of_node, "qcom,pcie-ipq4019"); + int ret; + + res->clks[0].id = "aux"; + res->clks[1].id = "master_bus"; + res->clks[2].id = "slave_bus"; + res->clks[3].id = "iface"; + + /* qcom,pcie-ipq4019 is defined without "iface" */ + res->num_clks = is_ipq ? 3 : 4; + + ret = devm_clk_bulk_get(dev, res->num_clks, res->clks); + if (ret < 0) + return ret; + + res->axi_m_reset = devm_reset_control_get_exclusive(dev, "axi_m"); + if (IS_ERR(res->axi_m_reset)) + return PTR_ERR(res->axi_m_reset); + + res->axi_s_reset = devm_reset_control_get_exclusive(dev, "axi_s"); + if (IS_ERR(res->axi_s_reset)) + return PTR_ERR(res->axi_s_reset); + + if (is_ipq) { + /* + * These resources relates to the PHY or are secure clocks, but + * are controlled here for IPQ4019 + */ + res->pipe_reset = devm_reset_control_get_exclusive(dev, "pipe"); + if (IS_ERR(res->pipe_reset)) + return PTR_ERR(res->pipe_reset); + + res->axi_m_vmid_reset = devm_reset_control_get_exclusive(dev, + "axi_m_vmid"); + if (IS_ERR(res->axi_m_vmid_reset)) + return PTR_ERR(res->axi_m_vmid_reset); + + res->axi_s_xpu_reset = devm_reset_control_get_exclusive(dev, + "axi_s_xpu"); + if (IS_ERR(res->axi_s_xpu_reset)) + return PTR_ERR(res->axi_s_xpu_reset); + + res->parf_reset = devm_reset_control_get_exclusive(dev, "parf"); + if (IS_ERR(res->parf_reset)) + return PTR_ERR(res->parf_reset); + + res->phy_reset = devm_reset_control_get_exclusive(dev, "phy"); + if (IS_ERR(res->phy_reset)) + return PTR_ERR(res->phy_reset); + } + + res->axi_m_sticky_reset = devm_reset_control_get_exclusive(dev, + "axi_m_sticky"); + if (IS_ERR(res->axi_m_sticky_reset)) + return PTR_ERR(res->axi_m_sticky_reset); + + res->pipe_sticky_reset = devm_reset_control_get_exclusive(dev, + "pipe_sticky"); + if (IS_ERR(res->pipe_sticky_reset)) + return PTR_ERR(res->pipe_sticky_reset); + + res->pwr_reset = devm_reset_control_get_exclusive(dev, "pwr"); + if (IS_ERR(res->pwr_reset)) + return PTR_ERR(res->pwr_reset); + + res->ahb_reset = devm_reset_control_get_exclusive(dev, "ahb"); + if (IS_ERR(res->ahb_reset)) + return PTR_ERR(res->ahb_reset); + + if (is_ipq) { + res->phy_ahb_reset = devm_reset_control_get_exclusive(dev, "phy_ahb"); + if (IS_ERR(res->phy_ahb_reset)) + return PTR_ERR(res->phy_ahb_reset); + } + + return 0; +} + +static void qcom_pcie_deinit_2_4_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_4_0 *res = &pcie->res.v2_4_0; + + reset_control_assert(res->axi_m_reset); + reset_control_assert(res->axi_s_reset); + reset_control_assert(res->pipe_reset); + reset_control_assert(res->pipe_sticky_reset); + reset_control_assert(res->phy_reset); + reset_control_assert(res->phy_ahb_reset); + reset_control_assert(res->axi_m_sticky_reset); + reset_control_assert(res->pwr_reset); + reset_control_assert(res->ahb_reset); + clk_bulk_disable_unprepare(res->num_clks, res->clks); +} + +static int qcom_pcie_init_2_4_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_4_0 *res = &pcie->res.v2_4_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int ret; + + ret = reset_control_assert(res->axi_m_reset); + if (ret) { + dev_err(dev, "cannot assert axi master reset\n"); + return ret; + } + + ret = reset_control_assert(res->axi_s_reset); + if (ret) { + dev_err(dev, "cannot assert axi slave reset\n"); + return ret; + } + + usleep_range(10000, 12000); + + ret = reset_control_assert(res->pipe_reset); + if (ret) { + dev_err(dev, "cannot assert pipe reset\n"); + return ret; + } + + ret = reset_control_assert(res->pipe_sticky_reset); + if (ret) { + dev_err(dev, "cannot assert pipe sticky reset\n"); + return ret; + } + + ret = reset_control_assert(res->phy_reset); + if (ret) { + dev_err(dev, "cannot assert phy reset\n"); + return ret; + } + + ret = reset_control_assert(res->phy_ahb_reset); + if (ret) { + dev_err(dev, "cannot assert phy ahb reset\n"); + return ret; + } + + usleep_range(10000, 12000); + + ret = reset_control_assert(res->axi_m_sticky_reset); + if (ret) { + dev_err(dev, "cannot assert axi master sticky reset\n"); + return ret; + } + + ret = reset_control_assert(res->pwr_reset); + if (ret) { + dev_err(dev, "cannot assert power reset\n"); + return ret; + } + + ret = reset_control_assert(res->ahb_reset); + if (ret) { + dev_err(dev, "cannot assert ahb reset\n"); + return ret; + } + + usleep_range(10000, 12000); + + ret = reset_control_deassert(res->phy_ahb_reset); + if (ret) { + dev_err(dev, "cannot deassert phy ahb reset\n"); + return ret; + } + + ret = reset_control_deassert(res->phy_reset); + if (ret) { + dev_err(dev, "cannot deassert phy reset\n"); + goto err_rst_phy; + } + + ret = reset_control_deassert(res->pipe_reset); + if (ret) { + dev_err(dev, "cannot deassert pipe reset\n"); + goto err_rst_pipe; + } + + ret = reset_control_deassert(res->pipe_sticky_reset); + if (ret) { + dev_err(dev, "cannot deassert pipe sticky reset\n"); + goto err_rst_pipe_sticky; + } + + usleep_range(10000, 12000); + + ret = reset_control_deassert(res->axi_m_reset); + if (ret) { + dev_err(dev, "cannot deassert axi master reset\n"); + goto err_rst_axi_m; + } + + ret = reset_control_deassert(res->axi_m_sticky_reset); + if (ret) { + dev_err(dev, "cannot deassert axi master sticky reset\n"); + goto err_rst_axi_m_sticky; + } + + ret = reset_control_deassert(res->axi_s_reset); + if (ret) { + dev_err(dev, "cannot deassert axi slave reset\n"); + goto err_rst_axi_s; + } + + ret = reset_control_deassert(res->pwr_reset); + if (ret) { + dev_err(dev, "cannot deassert power reset\n"); + goto err_rst_pwr; + } + + ret = reset_control_deassert(res->ahb_reset); + if (ret) { + dev_err(dev, "cannot deassert ahb reset\n"); + goto err_rst_ahb; + } + + usleep_range(10000, 12000); + + ret = clk_bulk_prepare_enable(res->num_clks, res->clks); + if (ret) + goto err_clks; + + return 0; + +err_clks: + reset_control_assert(res->ahb_reset); +err_rst_ahb: + reset_control_assert(res->pwr_reset); +err_rst_pwr: + reset_control_assert(res->axi_s_reset); +err_rst_axi_s: + reset_control_assert(res->axi_m_sticky_reset); +err_rst_axi_m_sticky: + reset_control_assert(res->axi_m_reset); +err_rst_axi_m: + reset_control_assert(res->pipe_sticky_reset); +err_rst_pipe_sticky: + reset_control_assert(res->pipe_reset); +err_rst_pipe: + reset_control_assert(res->phy_reset); +err_rst_phy: + reset_control_assert(res->phy_ahb_reset); + return ret; +} + +static int qcom_pcie_post_init_2_4_0(struct qcom_pcie *pcie) +{ + u32 val; + + /* enable PCIe clocks and resets */ + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~BIT(0); + writel(val, pcie->parf + PARF_PHY_CTRL); + + /* change DBI base address */ + writel(0, pcie->parf + PARF_DBI_BASE_ADDR); + + /* MAC PHY_POWERDOWN MUX DISABLE */ + val = readl(pcie->parf + PARF_SYS_CTRL); + val &= ~BIT(29); + writel(val, pcie->parf + PARF_SYS_CTRL); + + val = readl(pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); + val |= BIT(4); + writel(val, pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); + + val = readl(pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2); + val |= BIT(31); + writel(val, pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2); + + return 0; +} + +static int qcom_pcie_get_resources_2_3_3(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int i; + const char *rst_names[] = { "axi_m", "axi_s", "pipe", + "axi_m_sticky", "sticky", + "ahb", "sleep", }; + + res->iface = devm_clk_get(dev, "iface"); + if (IS_ERR(res->iface)) + return PTR_ERR(res->iface); + + res->axi_m_clk = devm_clk_get(dev, "axi_m"); + if (IS_ERR(res->axi_m_clk)) + return PTR_ERR(res->axi_m_clk); + + res->axi_s_clk = devm_clk_get(dev, "axi_s"); + if (IS_ERR(res->axi_s_clk)) + return PTR_ERR(res->axi_s_clk); + + res->ahb_clk = devm_clk_get(dev, "ahb"); + if (IS_ERR(res->ahb_clk)) + return PTR_ERR(res->ahb_clk); + + res->aux_clk = devm_clk_get(dev, "aux"); + if (IS_ERR(res->aux_clk)) + return PTR_ERR(res->aux_clk); + + for (i = 0; i < ARRAY_SIZE(rst_names); i++) { + res->rst[i] = devm_reset_control_get(dev, rst_names[i]); + if (IS_ERR(res->rst[i])) + return PTR_ERR(res->rst[i]); + } + + return 0; +} + +static void qcom_pcie_deinit_2_3_3(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3; + + clk_disable_unprepare(res->iface); + clk_disable_unprepare(res->axi_m_clk); + clk_disable_unprepare(res->axi_s_clk); + clk_disable_unprepare(res->ahb_clk); + clk_disable_unprepare(res->aux_clk); +} + +static int qcom_pcie_init_2_3_3(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int i, ret; + + for (i = 0; i < ARRAY_SIZE(res->rst); i++) { + ret = reset_control_assert(res->rst[i]); + if (ret) { + dev_err(dev, "reset #%d assert failed (%d)\n", i, ret); + return ret; + } + } + + usleep_range(2000, 2500); + + for (i = 0; i < ARRAY_SIZE(res->rst); i++) { + ret = reset_control_deassert(res->rst[i]); + if (ret) { + dev_err(dev, "reset #%d deassert failed (%d)\n", i, + ret); + return ret; + } + } + + /* + * Don't have a way to see if the reset has completed. + * Wait for some time. + */ + usleep_range(2000, 2500); + + ret = clk_prepare_enable(res->iface); + if (ret) { + dev_err(dev, "cannot prepare/enable core clock\n"); + goto err_clk_iface; + } + + ret = clk_prepare_enable(res->axi_m_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable core clock\n"); + goto err_clk_axi_m; + } + + ret = clk_prepare_enable(res->axi_s_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable axi slave clock\n"); + goto err_clk_axi_s; + } + + ret = clk_prepare_enable(res->ahb_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable ahb clock\n"); + goto err_clk_ahb; + } + + ret = clk_prepare_enable(res->aux_clk); + if (ret) { + dev_err(dev, "cannot prepare/enable aux clock\n"); + goto err_clk_aux; + } + + return 0; + +err_clk_aux: + clk_disable_unprepare(res->ahb_clk); +err_clk_ahb: + clk_disable_unprepare(res->axi_s_clk); +err_clk_axi_s: + clk_disable_unprepare(res->axi_m_clk); +err_clk_axi_m: + clk_disable_unprepare(res->iface); +err_clk_iface: + /* + * Not checking for failure, will anyway return + * the original failure in 'ret'. + */ + for (i = 0; i < ARRAY_SIZE(res->rst); i++) + reset_control_assert(res->rst[i]); + + return ret; +} + +static int qcom_pcie_post_init_2_3_3(struct qcom_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + u32 val; + + writel(SLV_ADDR_SPACE_SZ, pcie->parf + PARF_SLV_ADDR_SPACE_SIZE); + + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~BIT(0); + writel(val, pcie->parf + PARF_PHY_CTRL); + + writel(0, pcie->parf + PARF_DBI_BASE_ADDR); + + writel(MST_WAKEUP_EN | SLV_WAKEUP_EN | MSTR_ACLK_CGC_DIS + | SLV_ACLK_CGC_DIS | CORE_CLK_CGC_DIS | + AUX_PWR_DET | L23_CLK_RMV_DIS | L1_CLK_RMV_DIS, + pcie->parf + PARF_SYS_CTRL); + writel(0, pcie->parf + PARF_Q2A_FLUSH); + + writel(PCI_COMMAND_MASTER, pci->dbi_base + PCI_COMMAND); + + dw_pcie_dbi_ro_wr_en(pci); + + writel(PCIE_CAP_SLOT_VAL, pci->dbi_base + offset + PCI_EXP_SLTCAP); + + val = readl(pci->dbi_base + offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_ASPMS; + writel(val, pci->dbi_base + offset + PCI_EXP_LNKCAP); + + writel(PCI_EXP_DEVCTL2_COMP_TMOUT_DIS, pci->dbi_base + offset + + PCI_EXP_DEVCTL2); + + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + unsigned int num_clks, num_opt_clks; + unsigned int idx; + int ret; + + res->pci_reset = devm_reset_control_get_exclusive(dev, "pci"); + if (IS_ERR(res->pci_reset)) + return PTR_ERR(res->pci_reset); + + res->supplies[0].supply = "vdda"; + res->supplies[1].supply = "vddpe-3v3"; + ret = devm_regulator_bulk_get(dev, ARRAY_SIZE(res->supplies), + res->supplies); + if (ret) + return ret; + + idx = 0; + res->clks[idx++].id = "aux"; + res->clks[idx++].id = "cfg"; + res->clks[idx++].id = "bus_master"; + res->clks[idx++].id = "bus_slave"; + res->clks[idx++].id = "slave_q2a"; + + num_clks = idx; + + ret = devm_clk_bulk_get(dev, num_clks, res->clks); + if (ret < 0) + return ret; + + res->clks[idx++].id = "tbu"; + res->clks[idx++].id = "ddrss_sf_tbu"; + res->clks[idx++].id = "aggre0"; + res->clks[idx++].id = "aggre1"; + res->clks[idx++].id = "noc_aggr_4"; + res->clks[idx++].id = "noc_aggr_south_sf"; + res->clks[idx++].id = "cnoc_qx"; + + num_opt_clks = idx - num_clks; + res->num_clks = idx; + + ret = devm_clk_bulk_get_optional(dev, num_opt_clks, res->clks + num_clks); + if (ret < 0) + return ret; + + return 0; +} + +static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + u32 val; + int ret; + + ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies); + if (ret < 0) { + dev_err(dev, "cannot enable regulators\n"); + return ret; + } + + ret = clk_bulk_prepare_enable(res->num_clks, res->clks); + if (ret < 0) + goto err_disable_regulators; + + ret = reset_control_assert(res->pci_reset); + if (ret < 0) { + dev_err(dev, "cannot deassert pci reset\n"); + goto err_disable_clocks; + } + + usleep_range(1000, 1500); + + ret = reset_control_deassert(res->pci_reset); + if (ret < 0) { + dev_err(dev, "cannot deassert pci reset\n"); + goto err_disable_clocks; + } + + /* Wait for reset to complete, required on SM8450 */ + usleep_range(1000, 1500); + + /* configure PCIe to RC mode */ + writel(DEVICE_TYPE_RC, pcie->parf + PARF_DEVICE_TYPE); + + /* enable PCIe clocks and resets */ + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~BIT(0); + writel(val, pcie->parf + PARF_PHY_CTRL); + + /* change DBI base address */ + writel(0, pcie->parf + PARF_DBI_BASE_ADDR); + + /* MAC PHY_POWERDOWN MUX DISABLE */ + val = readl(pcie->parf + PARF_SYS_CTRL); + val &= ~BIT(29); + writel(val, pcie->parf + PARF_SYS_CTRL); + + val = readl(pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); + val |= BIT(4); + writel(val, pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); + + /* Enable L1 and L1SS */ + val = readl(pcie->parf + PARF_PM_CTRL); + val &= ~REQ_NOT_ENTR_L1; + writel(val, pcie->parf + PARF_PM_CTRL); + + val = readl(pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2); + val |= BIT(31); + writel(val, pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2); + + return 0; +err_disable_clocks: + clk_bulk_disable_unprepare(res->num_clks, res->clks); +err_disable_regulators: + regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); + + return ret; +} + +static void qcom_pcie_deinit_2_7_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0; + + clk_bulk_disable_unprepare(res->num_clks, res->clks); + + regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies); +} + +static int qcom_pcie_get_resources_2_9_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0; + struct dw_pcie *pci = pcie->pci; + struct device *dev = pci->dev; + int ret; + + res->clks[0].id = "iface"; + res->clks[1].id = "axi_m"; + res->clks[2].id = "axi_s"; + res->clks[3].id = "axi_bridge"; + res->clks[4].id = "rchng"; + + ret = devm_clk_bulk_get(dev, ARRAY_SIZE(res->clks), res->clks); + if (ret < 0) + return ret; + + res->rst = devm_reset_control_array_get_exclusive(dev); + if (IS_ERR(res->rst)) + return PTR_ERR(res->rst); + + return 0; +} + +static void qcom_pcie_deinit_2_9_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0; + + clk_bulk_disable_unprepare(ARRAY_SIZE(res->clks), res->clks); +} + +static int qcom_pcie_init_2_9_0(struct qcom_pcie *pcie) +{ + struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0; + struct device *dev = pcie->pci->dev; + int ret; + + ret = reset_control_assert(res->rst); + if (ret) { + dev_err(dev, "reset assert failed (%d)\n", ret); + return ret; + } + + /* + * Delay periods before and after reset deassert are working values + * from downstream Codeaurora kernel + */ + usleep_range(2000, 2500); + + ret = reset_control_deassert(res->rst); + if (ret) { + dev_err(dev, "reset deassert failed (%d)\n", ret); + return ret; + } + + usleep_range(2000, 2500); + + return clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks); +} + +static int qcom_pcie_post_init_2_9_0(struct qcom_pcie *pcie) +{ + struct dw_pcie *pci = pcie->pci; + u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + u32 val; + int i; + + writel(SLV_ADDR_SPACE_SZ, + pcie->parf + PARF_SLV_ADDR_SPACE_SIZE); + + val = readl(pcie->parf + PARF_PHY_CTRL); + val &= ~BIT(0); + writel(val, pcie->parf + PARF_PHY_CTRL); + + writel(0, pcie->parf + PARF_DBI_BASE_ADDR); + + writel(DEVICE_TYPE_RC, pcie->parf + PARF_DEVICE_TYPE); + writel(BYPASS | MSTR_AXI_CLK_EN | AHB_CLK_EN, + pcie->parf + PARF_MHI_CLOCK_RESET_CTRL); + writel(GEN3_RELATED_OFF_RXEQ_RGRDLESS_RXTS | + GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL, + pci->dbi_base + GEN3_RELATED_OFF); + + writel(MST_WAKEUP_EN | SLV_WAKEUP_EN | MSTR_ACLK_CGC_DIS | + SLV_ACLK_CGC_DIS | CORE_CLK_CGC_DIS | + AUX_PWR_DET | L23_CLK_RMV_DIS | L1_CLK_RMV_DIS, + pcie->parf + PARF_SYS_CTRL); + + writel(0, pcie->parf + PARF_Q2A_FLUSH); + + dw_pcie_dbi_ro_wr_en(pci); + + writel(PCIE_CAP_SLOT_VAL, pci->dbi_base + offset + PCI_EXP_SLTCAP); + + val = readl(pci->dbi_base + offset + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_ASPMS; + writel(val, pci->dbi_base + offset + PCI_EXP_LNKCAP); + + writel(PCI_EXP_DEVCTL2_COMP_TMOUT_DIS, pci->dbi_base + offset + + PCI_EXP_DEVCTL2); + + dw_pcie_dbi_ro_wr_dis(pci); + + for (i = 0; i < 256; i++) + writel(0, pcie->parf + PARF_BDF_TO_SID_TABLE_N + (4 * i)); + + return 0; +} + +static int qcom_pcie_link_up(struct dw_pcie *pci) +{ + u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + u16 val = readw(pci->dbi_base + offset + PCI_EXP_LNKSTA); + + return !!(val & PCI_EXP_LNKSTA_DLLLA); +} + +static int qcom_pcie_config_sid_sm8250(struct qcom_pcie *pcie) +{ + /* iommu map structure */ + struct { + u32 bdf; + u32 phandle; + u32 smmu_sid; + u32 smmu_sid_len; + } *map; + void __iomem *bdf_to_sid_base = pcie->parf + PARF_BDF_TO_SID_TABLE_N; + struct device *dev = pcie->pci->dev; + u8 qcom_pcie_crc8_table[CRC8_TABLE_SIZE]; + int i, nr_map, size = 0; + u32 smmu_sid_base; + + of_get_property(dev->of_node, "iommu-map", &size); + if (!size) + return 0; + + map = kzalloc(size, GFP_KERNEL); + if (!map) + return -ENOMEM; + + of_property_read_u32_array(dev->of_node, + "iommu-map", (u32 *)map, size / sizeof(u32)); + + nr_map = size / (sizeof(*map)); + + crc8_populate_msb(qcom_pcie_crc8_table, QCOM_PCIE_CRC8_POLYNOMIAL); + + /* Registers need to be zero out first */ + memset_io(bdf_to_sid_base, 0, CRC8_TABLE_SIZE * sizeof(u32)); + + /* Extract the SMMU SID base from the first entry of iommu-map */ + smmu_sid_base = map[0].smmu_sid; + + /* Look for an available entry to hold the mapping */ + for (i = 0; i < nr_map; i++) { + __be16 bdf_be = cpu_to_be16(map[i].bdf); + u32 val; + u8 hash; + + hash = crc8(qcom_pcie_crc8_table, (u8 *)&bdf_be, sizeof(bdf_be), + 0); + + val = readl(bdf_to_sid_base + hash * sizeof(u32)); + + /* If the register is already populated, look for next available entry */ + while (val) { + u8 current_hash = hash++; + u8 next_mask = 0xff; + + /* If NEXT field is NULL then update it with next hash */ + if (!(val & next_mask)) { + val |= (u32)hash; + writel(val, bdf_to_sid_base + current_hash * sizeof(u32)); + } + + val = readl(bdf_to_sid_base + hash * sizeof(u32)); + } + + /* BDF [31:16] | SID [15:8] | NEXT [7:0] */ + val = map[i].bdf << 16 | (map[i].smmu_sid - smmu_sid_base) << 8 | 0; + writel(val, bdf_to_sid_base + hash * sizeof(u32)); + } + + kfree(map); + + return 0; +} + +static int qcom_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct qcom_pcie *pcie = to_qcom_pcie(pci); + int ret; + + qcom_ep_reset_assert(pcie); + + ret = pcie->cfg->ops->init(pcie); + if (ret) + return ret; + + ret = phy_power_on(pcie->phy); + if (ret) + goto err_deinit; + + if (pcie->cfg->ops->post_init) { + ret = pcie->cfg->ops->post_init(pcie); + if (ret) + goto err_disable_phy; + } + + qcom_ep_reset_deassert(pcie); + + if (pcie->cfg->ops->config_sid) { + ret = pcie->cfg->ops->config_sid(pcie); + if (ret) + goto err_assert_reset; + } + + return 0; + +err_assert_reset: + qcom_ep_reset_assert(pcie); +err_disable_phy: + phy_power_off(pcie->phy); +err_deinit: + pcie->cfg->ops->deinit(pcie); + + return ret; +} + +static void qcom_pcie_host_deinit(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct qcom_pcie *pcie = to_qcom_pcie(pci); + + qcom_ep_reset_assert(pcie); + phy_power_off(pcie->phy); + pcie->cfg->ops->deinit(pcie); +} + +static const struct dw_pcie_host_ops qcom_pcie_dw_ops = { + .host_init = qcom_pcie_host_init, + .host_deinit = qcom_pcie_host_deinit, +}; + +/* Qcom IP rev.: 2.1.0 Synopsys IP rev.: 4.01a */ +static const struct qcom_pcie_ops ops_2_1_0 = { + .get_resources = qcom_pcie_get_resources_2_1_0, + .init = qcom_pcie_init_2_1_0, + .post_init = qcom_pcie_post_init_2_1_0, + .deinit = qcom_pcie_deinit_2_1_0, + .ltssm_enable = qcom_pcie_2_1_0_ltssm_enable, +}; + +/* Qcom IP rev.: 1.0.0 Synopsys IP rev.: 4.11a */ +static const struct qcom_pcie_ops ops_1_0_0 = { + .get_resources = qcom_pcie_get_resources_1_0_0, + .init = qcom_pcie_init_1_0_0, + .post_init = qcom_pcie_post_init_1_0_0, + .deinit = qcom_pcie_deinit_1_0_0, + .ltssm_enable = qcom_pcie_2_1_0_ltssm_enable, +}; + +/* Qcom IP rev.: 2.3.2 Synopsys IP rev.: 4.21a */ +static const struct qcom_pcie_ops ops_2_3_2 = { + .get_resources = qcom_pcie_get_resources_2_3_2, + .init = qcom_pcie_init_2_3_2, + .post_init = qcom_pcie_post_init_2_3_2, + .deinit = qcom_pcie_deinit_2_3_2, + .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, +}; + +/* Qcom IP rev.: 2.4.0 Synopsys IP rev.: 4.20a */ +static const struct qcom_pcie_ops ops_2_4_0 = { + .get_resources = qcom_pcie_get_resources_2_4_0, + .init = qcom_pcie_init_2_4_0, + .post_init = qcom_pcie_post_init_2_4_0, + .deinit = qcom_pcie_deinit_2_4_0, + .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, +}; + +/* Qcom IP rev.: 2.3.3 Synopsys IP rev.: 4.30a */ +static const struct qcom_pcie_ops ops_2_3_3 = { + .get_resources = qcom_pcie_get_resources_2_3_3, + .init = qcom_pcie_init_2_3_3, + .post_init = qcom_pcie_post_init_2_3_3, + .deinit = qcom_pcie_deinit_2_3_3, + .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, +}; + +/* Qcom IP rev.: 2.7.0 Synopsys IP rev.: 4.30a */ +static const struct qcom_pcie_ops ops_2_7_0 = { + .get_resources = qcom_pcie_get_resources_2_7_0, + .init = qcom_pcie_init_2_7_0, + .deinit = qcom_pcie_deinit_2_7_0, + .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, +}; + +/* Qcom IP rev.: 1.9.0 */ +static const struct qcom_pcie_ops ops_1_9_0 = { + .get_resources = qcom_pcie_get_resources_2_7_0, + .init = qcom_pcie_init_2_7_0, + .deinit = qcom_pcie_deinit_2_7_0, + .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, + .config_sid = qcom_pcie_config_sid_sm8250, +}; + +/* Qcom IP rev.: 2.9.0 Synopsys IP rev.: 5.00a */ +static const struct qcom_pcie_ops ops_2_9_0 = { + .get_resources = qcom_pcie_get_resources_2_9_0, + .init = qcom_pcie_init_2_9_0, + .post_init = qcom_pcie_post_init_2_9_0, + .deinit = qcom_pcie_deinit_2_9_0, + .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, +}; + +static const struct qcom_pcie_cfg cfg_1_0_0 = { + .ops = &ops_1_0_0, +}; + +static const struct qcom_pcie_cfg cfg_1_9_0 = { + .ops = &ops_1_9_0, +}; + +static const struct qcom_pcie_cfg cfg_2_1_0 = { + .ops = &ops_2_1_0, +}; + +static const struct qcom_pcie_cfg cfg_2_3_2 = { + .ops = &ops_2_3_2, +}; + +static const struct qcom_pcie_cfg cfg_2_3_3 = { + .ops = &ops_2_3_3, +}; + +static const struct qcom_pcie_cfg cfg_2_4_0 = { + .ops = &ops_2_4_0, +}; + +static const struct qcom_pcie_cfg cfg_2_7_0 = { + .ops = &ops_2_7_0, +}; + +static const struct qcom_pcie_cfg cfg_2_9_0 = { + .ops = &ops_2_9_0, +}; + +static const struct dw_pcie_ops dw_pcie_ops = { + .link_up = qcom_pcie_link_up, + .start_link = qcom_pcie_start_link, +}; + +static int qcom_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_pcie_rp *pp; + struct dw_pcie *pci; + struct qcom_pcie *pcie; + const struct qcom_pcie_cfg *pcie_cfg; + int ret; + + pcie_cfg = of_device_get_match_data(dev); + if (!pcie_cfg || !pcie_cfg->ops) { + dev_err(dev, "Invalid platform data\n"); + return -EINVAL; + } + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) + goto err_pm_runtime_put; + + pci->dev = dev; + pci->ops = &dw_pcie_ops; + pp = &pci->pp; + + pcie->pci = pci; + + pcie->cfg = pcie_cfg; + + pcie->reset = devm_gpiod_get_optional(dev, "perst", GPIOD_OUT_HIGH); + if (IS_ERR(pcie->reset)) { + ret = PTR_ERR(pcie->reset); + goto err_pm_runtime_put; + } + + pcie->parf = devm_platform_ioremap_resource_byname(pdev, "parf"); + if (IS_ERR(pcie->parf)) { + ret = PTR_ERR(pcie->parf); + goto err_pm_runtime_put; + } + + pcie->elbi = devm_platform_ioremap_resource_byname(pdev, "elbi"); + if (IS_ERR(pcie->elbi)) { + ret = PTR_ERR(pcie->elbi); + goto err_pm_runtime_put; + } + + pcie->phy = devm_phy_optional_get(dev, "pciephy"); + if (IS_ERR(pcie->phy)) { + ret = PTR_ERR(pcie->phy); + goto err_pm_runtime_put; + } + + ret = pcie->cfg->ops->get_resources(pcie); + if (ret) + goto err_pm_runtime_put; + + pp->ops = &qcom_pcie_dw_ops; + + ret = phy_init(pcie->phy); + if (ret) + goto err_pm_runtime_put; + + platform_set_drvdata(pdev, pcie); + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "cannot initialize host\n"); + goto err_phy_exit; + } + + return 0; + +err_phy_exit: + phy_exit(pcie->phy); +err_pm_runtime_put: + pm_runtime_put(dev); + pm_runtime_disable(dev); + + return ret; +} + +static const struct of_device_id qcom_pcie_match[] = { + { .compatible = "qcom,pcie-apq8064", .data = &cfg_2_1_0 }, + { .compatible = "qcom,pcie-apq8084", .data = &cfg_1_0_0 }, + { .compatible = "qcom,pcie-ipq4019", .data = &cfg_2_4_0 }, + { .compatible = "qcom,pcie-ipq6018", .data = &cfg_2_9_0 }, + { .compatible = "qcom,pcie-ipq8064", .data = &cfg_2_1_0 }, + { .compatible = "qcom,pcie-ipq8064-v2", .data = &cfg_2_1_0 }, + { .compatible = "qcom,pcie-ipq8074", .data = &cfg_2_3_3 }, + { .compatible = "qcom,pcie-msm8996", .data = &cfg_2_3_2 }, + { .compatible = "qcom,pcie-qcs404", .data = &cfg_2_4_0 }, + { .compatible = "qcom,pcie-sa8540p", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sc7280", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sc8180x", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sc8280xp", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sdm845", .data = &cfg_2_7_0 }, + { .compatible = "qcom,pcie-sm8150", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sm8250", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sm8450-pcie0", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-sm8450-pcie1", .data = &cfg_1_9_0 }, + { } +}; + +static void qcom_fixup_class(struct pci_dev *dev) +{ + dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0101, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0104, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0106, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0107, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0302, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x1000, qcom_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x1001, qcom_fixup_class); + +static struct platform_driver qcom_pcie_driver = { + .probe = qcom_pcie_probe, + .driver = { + .name = "qcom-pcie", + .suppress_bind_attrs = true, + .of_match_table = qcom_pcie_match, + }, +}; +builtin_platform_driver(qcom_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-spear13xx.c b/drivers/pci/controller/dwc/pcie-spear13xx.c new file mode 100644 index 000000000..99d47ae80 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-spear13xx.c @@ -0,0 +1,266 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for ST Microelectronics SPEAr13xx SoCs + * + * SPEAr13xx PCIe Glue Layer Source Code + * + * Copyright (C) 2010-2014 ST Microelectronics + * Pratyush Anand <pratyush.anand@gmail.com> + * Mohit Kumar <mohit.kumar.dhaka@gmail.com> + */ + +#include <linux/clk.h> +#include <linux/interrupt.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/of.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/resource.h> + +#include "pcie-designware.h" + +struct spear13xx_pcie { + struct dw_pcie *pci; + void __iomem *app_base; + struct phy *phy; + struct clk *clk; +}; + +struct pcie_app_reg { + u32 app_ctrl_0; /* cr0 */ + u32 app_ctrl_1; /* cr1 */ + u32 app_status_0; /* cr2 */ + u32 app_status_1; /* cr3 */ + u32 msg_status; /* cr4 */ + u32 msg_payload; /* cr5 */ + u32 int_sts; /* cr6 */ + u32 int_clr; /* cr7 */ + u32 int_mask; /* cr8 */ + u32 mst_bmisc; /* cr9 */ + u32 phy_ctrl; /* cr10 */ + u32 phy_status; /* cr11 */ + u32 cxpl_debug_info_0; /* cr12 */ + u32 cxpl_debug_info_1; /* cr13 */ + u32 ven_msg_ctrl_0; /* cr14 */ + u32 ven_msg_ctrl_1; /* cr15 */ + u32 ven_msg_data_0; /* cr16 */ + u32 ven_msg_data_1; /* cr17 */ + u32 ven_msi_0; /* cr18 */ + u32 ven_msi_1; /* cr19 */ + u32 mst_rmisc; /* cr20 */ +}; + +/* CR0 ID */ +#define APP_LTSSM_ENABLE_ID 3 +#define DEVICE_TYPE_RC (4 << 25) +#define MISCTRL_EN_ID 30 +#define REG_TRANSLATION_ENABLE 31 + +/* CR3 ID */ +#define XMLH_LINK_UP (1 << 6) + +/* CR6 */ +#define MSI_CTRL_INT (1 << 26) + +#define to_spear13xx_pcie(x) dev_get_drvdata((x)->dev) + +static int spear13xx_pcie_start_link(struct dw_pcie *pci) +{ + struct spear13xx_pcie *spear13xx_pcie = to_spear13xx_pcie(pci); + struct pcie_app_reg __iomem *app_reg = spear13xx_pcie->app_base; + + /* enable ltssm */ + writel(DEVICE_TYPE_RC | (1 << MISCTRL_EN_ID) + | (1 << APP_LTSSM_ENABLE_ID) + | ((u32)1 << REG_TRANSLATION_ENABLE), + &app_reg->app_ctrl_0); + + return 0; +} + +static irqreturn_t spear13xx_pcie_irq_handler(int irq, void *arg) +{ + struct spear13xx_pcie *spear13xx_pcie = arg; + struct pcie_app_reg __iomem *app_reg = spear13xx_pcie->app_base; + struct dw_pcie *pci = spear13xx_pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + unsigned int status; + + status = readl(&app_reg->int_sts); + + if (status & MSI_CTRL_INT) { + BUG_ON(!IS_ENABLED(CONFIG_PCI_MSI)); + dw_handle_msi_irq(pp); + } + + writel(status, &app_reg->int_clr); + + return IRQ_HANDLED; +} + +static void spear13xx_pcie_enable_interrupts(struct spear13xx_pcie *spear13xx_pcie) +{ + struct pcie_app_reg __iomem *app_reg = spear13xx_pcie->app_base; + + /* Enable MSI interrupt */ + if (IS_ENABLED(CONFIG_PCI_MSI)) + writel(readl(&app_reg->int_mask) | + MSI_CTRL_INT, &app_reg->int_mask); +} + +static int spear13xx_pcie_link_up(struct dw_pcie *pci) +{ + struct spear13xx_pcie *spear13xx_pcie = to_spear13xx_pcie(pci); + struct pcie_app_reg __iomem *app_reg = spear13xx_pcie->app_base; + + if (readl(&app_reg->app_status_1) & XMLH_LINK_UP) + return 1; + + return 0; +} + +static int spear13xx_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct spear13xx_pcie *spear13xx_pcie = to_spear13xx_pcie(pci); + u32 exp_cap_off = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + u32 val; + + spear13xx_pcie->app_base = pci->dbi_base + 0x2000; + + /* + * this controller support only 128 bytes read size, however its + * default value in capability register is 512 bytes. So force + * it to 128 here. + */ + val = dw_pcie_readw_dbi(pci, exp_cap_off + PCI_EXP_DEVCTL); + val &= ~PCI_EXP_DEVCTL_READRQ; + dw_pcie_writew_dbi(pci, exp_cap_off + PCI_EXP_DEVCTL, val); + + dw_pcie_writew_dbi(pci, PCI_VENDOR_ID, 0x104A); + dw_pcie_writew_dbi(pci, PCI_DEVICE_ID, 0xCD80); + + spear13xx_pcie_enable_interrupts(spear13xx_pcie); + + return 0; +} + +static const struct dw_pcie_host_ops spear13xx_pcie_host_ops = { + .host_init = spear13xx_pcie_host_init, +}; + +static int spear13xx_add_pcie_port(struct spear13xx_pcie *spear13xx_pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = spear13xx_pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = &pdev->dev; + int ret; + + pp->irq = platform_get_irq(pdev, 0); + if (pp->irq < 0) + return pp->irq; + + ret = devm_request_irq(dev, pp->irq, spear13xx_pcie_irq_handler, + IRQF_SHARED | IRQF_NO_THREAD, + "spear1340-pcie", spear13xx_pcie); + if (ret) { + dev_err(dev, "failed to request irq %d\n", pp->irq); + return ret; + } + + pp->ops = &spear13xx_pcie_host_ops; + pp->msi_irq[0] = -ENODEV; + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "failed to initialize host\n"); + return ret; + } + + return 0; +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .link_up = spear13xx_pcie_link_up, + .start_link = spear13xx_pcie_start_link, +}; + +static int spear13xx_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct dw_pcie *pci; + struct spear13xx_pcie *spear13xx_pcie; + struct device_node *np = dev->of_node; + int ret; + + spear13xx_pcie = devm_kzalloc(dev, sizeof(*spear13xx_pcie), GFP_KERNEL); + if (!spear13xx_pcie) + return -ENOMEM; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pci->dev = dev; + pci->ops = &dw_pcie_ops; + + spear13xx_pcie->pci = pci; + + spear13xx_pcie->phy = devm_phy_get(dev, "pcie-phy"); + if (IS_ERR(spear13xx_pcie->phy)) { + ret = PTR_ERR(spear13xx_pcie->phy); + if (ret == -EPROBE_DEFER) + dev_info(dev, "probe deferred\n"); + else + dev_err(dev, "couldn't get pcie-phy\n"); + return ret; + } + + phy_init(spear13xx_pcie->phy); + + spear13xx_pcie->clk = devm_clk_get(dev, NULL); + if (IS_ERR(spear13xx_pcie->clk)) { + dev_err(dev, "couldn't get clk for pcie\n"); + return PTR_ERR(spear13xx_pcie->clk); + } + ret = clk_prepare_enable(spear13xx_pcie->clk); + if (ret) { + dev_err(dev, "couldn't enable clk for pcie\n"); + return ret; + } + + if (of_property_read_bool(np, "st,pcie-is-gen1")) + pci->link_gen = 1; + + platform_set_drvdata(pdev, spear13xx_pcie); + + ret = spear13xx_add_pcie_port(spear13xx_pcie, pdev); + if (ret < 0) + goto fail_clk; + + return 0; + +fail_clk: + clk_disable_unprepare(spear13xx_pcie->clk); + + return ret; +} + +static const struct of_device_id spear13xx_pcie_of_match[] = { + { .compatible = "st,spear1340-pcie", }, + {}, +}; + +static struct platform_driver spear13xx_pcie_driver = { + .probe = spear13xx_pcie_probe, + .driver = { + .name = "spear-pcie", + .of_match_table = spear13xx_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; + +builtin_platform_driver(spear13xx_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-tegra194-acpi.c b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c new file mode 100644 index 000000000..55f61914a --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c @@ -0,0 +1,109 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * ACPI quirks for Tegra194 PCIe host controller + * + * Copyright (C) 2021 NVIDIA Corporation. + * + * Author: Vidya Sagar <vidyas@nvidia.com> + */ + +#include <linux/pci.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> + +#include "pcie-designware.h" + +struct tegra194_pcie_ecam { + void __iomem *config_base; + void __iomem *iatu_base; + void __iomem *dbi_base; +}; + +static int tegra194_acpi_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct tegra194_pcie_ecam *pcie_ecam; + + pcie_ecam = devm_kzalloc(dev, sizeof(*pcie_ecam), GFP_KERNEL); + if (!pcie_ecam) + return -ENOMEM; + + pcie_ecam->config_base = cfg->win; + pcie_ecam->iatu_base = cfg->win + SZ_256K; + pcie_ecam->dbi_base = cfg->win + SZ_512K; + cfg->priv = pcie_ecam; + + return 0; +} + +static void atu_reg_write(struct tegra194_pcie_ecam *pcie_ecam, int index, + u32 val, u32 reg) +{ + u32 offset = PCIE_ATU_UNROLL_BASE(PCIE_ATU_REGION_DIR_OB, index) + + PCIE_ATU_VIEWPORT_BASE; + + writel(val, pcie_ecam->iatu_base + offset + reg); +} + +static void program_outbound_atu(struct tegra194_pcie_ecam *pcie_ecam, + int index, int type, u64 cpu_addr, + u64 pci_addr, u64 size) +{ + atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr), + PCIE_ATU_LOWER_BASE); + atu_reg_write(pcie_ecam, index, upper_32_bits(cpu_addr), + PCIE_ATU_UPPER_BASE); + atu_reg_write(pcie_ecam, index, lower_32_bits(pci_addr), + PCIE_ATU_LOWER_TARGET); + atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr + size - 1), + PCIE_ATU_LIMIT); + atu_reg_write(pcie_ecam, index, upper_32_bits(pci_addr), + PCIE_ATU_UPPER_TARGET); + atu_reg_write(pcie_ecam, index, type, PCIE_ATU_REGION_CTRL1); + atu_reg_write(pcie_ecam, index, PCIE_ATU_ENABLE, PCIE_ATU_REGION_CTRL2); +} + +static void __iomem *tegra194_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct pci_config_window *cfg = bus->sysdata; + struct tegra194_pcie_ecam *pcie_ecam = cfg->priv; + u32 busdev; + int type; + + if (bus->number < cfg->busr.start || bus->number > cfg->busr.end) + return NULL; + + if (bus->number == cfg->busr.start) { + if (PCI_SLOT(devfn) == 0) + return pcie_ecam->dbi_base + where; + else + return NULL; + } + + busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) | + PCIE_ATU_FUNC(PCI_FUNC(devfn)); + + if (bus->parent->number == cfg->busr.start) { + if (PCI_SLOT(devfn) == 0) + type = PCIE_ATU_TYPE_CFG0; + else + return NULL; + } else { + type = PCIE_ATU_TYPE_CFG1; + } + + program_outbound_atu(pcie_ecam, 0, type, cfg->res.start, busdev, + SZ_256K); + + return pcie_ecam->config_base + where; +} + +const struct pci_ecam_ops tegra194_pcie_ops = { + .init = tegra194_acpi_init, + .pci_ops = { + .map_bus = tegra194_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c new file mode 100644 index 000000000..5d1ae2706 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -0,0 +1,2494 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * PCIe host controller driver for the following SoCs + * Tegra194 + * Tegra234 + * + * Copyright (C) 2019-2022 NVIDIA Corporation. + * + * Author: Vidya Sagar <vidyas@nvidia.com> + */ + +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/gpio.h> +#include <linux/gpio/consumer.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/of_gpio.h> +#include <linux/of_irq.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/pinctrl/consumer.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/random.h> +#include <linux/reset.h> +#include <linux/resource.h> +#include <linux/types.h> +#include "pcie-designware.h" +#include <soc/tegra/bpmp.h> +#include <soc/tegra/bpmp-abi.h> +#include "../../pci.h" + +#define TEGRA194_DWC_IP_VER 0x490A +#define TEGRA234_DWC_IP_VER 0x562A + +#define APPL_PINMUX 0x0 +#define APPL_PINMUX_PEX_RST BIT(0) +#define APPL_PINMUX_CLKREQ_OVERRIDE_EN BIT(2) +#define APPL_PINMUX_CLKREQ_OVERRIDE BIT(3) +#define APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE_EN BIT(4) +#define APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE BIT(5) + +#define APPL_CTRL 0x4 +#define APPL_CTRL_SYS_PRE_DET_STATE BIT(6) +#define APPL_CTRL_LTSSM_EN BIT(7) +#define APPL_CTRL_HW_HOT_RST_EN BIT(20) +#define APPL_CTRL_HW_HOT_RST_MODE_MASK GENMASK(1, 0) +#define APPL_CTRL_HW_HOT_RST_MODE_SHIFT 22 +#define APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST 0x1 +#define APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST_LTSSM_EN 0x2 + +#define APPL_INTR_EN_L0_0 0x8 +#define APPL_INTR_EN_L0_0_LINK_STATE_INT_EN BIT(0) +#define APPL_INTR_EN_L0_0_MSI_RCV_INT_EN BIT(4) +#define APPL_INTR_EN_L0_0_INT_INT_EN BIT(8) +#define APPL_INTR_EN_L0_0_PCI_CMD_EN_INT_EN BIT(15) +#define APPL_INTR_EN_L0_0_CDM_REG_CHK_INT_EN BIT(19) +#define APPL_INTR_EN_L0_0_SYS_INTR_EN BIT(30) +#define APPL_INTR_EN_L0_0_SYS_MSI_INTR_EN BIT(31) + +#define APPL_INTR_STATUS_L0 0xC +#define APPL_INTR_STATUS_L0_LINK_STATE_INT BIT(0) +#define APPL_INTR_STATUS_L0_INT_INT BIT(8) +#define APPL_INTR_STATUS_L0_PCI_CMD_EN_INT BIT(15) +#define APPL_INTR_STATUS_L0_PEX_RST_INT BIT(16) +#define APPL_INTR_STATUS_L0_CDM_REG_CHK_INT BIT(18) + +#define APPL_INTR_EN_L1_0_0 0x1C +#define APPL_INTR_EN_L1_0_0_LINK_REQ_RST_NOT_INT_EN BIT(1) +#define APPL_INTR_EN_L1_0_0_RDLH_LINK_UP_INT_EN BIT(3) +#define APPL_INTR_EN_L1_0_0_HOT_RESET_DONE_INT_EN BIT(30) + +#define APPL_INTR_STATUS_L1_0_0 0x20 +#define APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED BIT(1) +#define APPL_INTR_STATUS_L1_0_0_RDLH_LINK_UP_CHGED BIT(3) +#define APPL_INTR_STATUS_L1_0_0_HOT_RESET_DONE BIT(30) + +#define APPL_INTR_STATUS_L1_1 0x2C +#define APPL_INTR_STATUS_L1_2 0x30 +#define APPL_INTR_STATUS_L1_3 0x34 +#define APPL_INTR_STATUS_L1_6 0x3C +#define APPL_INTR_STATUS_L1_7 0x40 +#define APPL_INTR_STATUS_L1_15_CFG_BME_CHGED BIT(1) + +#define APPL_INTR_EN_L1_8_0 0x44 +#define APPL_INTR_EN_L1_8_BW_MGT_INT_EN BIT(2) +#define APPL_INTR_EN_L1_8_AUTO_BW_INT_EN BIT(3) +#define APPL_INTR_EN_L1_8_INTX_EN BIT(11) +#define APPL_INTR_EN_L1_8_AER_INT_EN BIT(15) + +#define APPL_INTR_STATUS_L1_8_0 0x4C +#define APPL_INTR_STATUS_L1_8_0_EDMA_INT_MASK GENMASK(11, 6) +#define APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS BIT(2) +#define APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS BIT(3) + +#define APPL_INTR_STATUS_L1_9 0x54 +#define APPL_INTR_STATUS_L1_10 0x58 +#define APPL_INTR_STATUS_L1_11 0x64 +#define APPL_INTR_STATUS_L1_13 0x74 +#define APPL_INTR_STATUS_L1_14 0x78 +#define APPL_INTR_STATUS_L1_15 0x7C +#define APPL_INTR_STATUS_L1_17 0x88 + +#define APPL_INTR_EN_L1_18 0x90 +#define APPL_INTR_EN_L1_18_CDM_REG_CHK_CMPLT BIT(2) +#define APPL_INTR_EN_L1_18_CDM_REG_CHK_CMP_ERR BIT(1) +#define APPL_INTR_EN_L1_18_CDM_REG_CHK_LOGIC_ERR BIT(0) + +#define APPL_INTR_STATUS_L1_18 0x94 +#define APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT BIT(2) +#define APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR BIT(1) +#define APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR BIT(0) + +#define APPL_MSI_CTRL_1 0xAC + +#define APPL_MSI_CTRL_2 0xB0 + +#define APPL_LEGACY_INTX 0xB8 + +#define APPL_LTR_MSG_1 0xC4 +#define LTR_MSG_REQ BIT(15) +#define LTR_MST_NO_SNOOP_SHIFT 16 + +#define APPL_LTR_MSG_2 0xC8 +#define APPL_LTR_MSG_2_LTR_MSG_REQ_STATE BIT(3) + +#define APPL_LINK_STATUS 0xCC +#define APPL_LINK_STATUS_RDLH_LINK_UP BIT(0) + +#define APPL_DEBUG 0xD0 +#define APPL_DEBUG_PM_LINKST_IN_L2_LAT BIT(21) +#define APPL_DEBUG_PM_LINKST_IN_L0 0x11 +#define APPL_DEBUG_LTSSM_STATE_MASK GENMASK(8, 3) +#define APPL_DEBUG_LTSSM_STATE_SHIFT 3 +#define LTSSM_STATE_PRE_DETECT 5 + +#define APPL_RADM_STATUS 0xE4 +#define APPL_PM_XMT_TURNOFF_STATE BIT(0) + +#define APPL_DM_TYPE 0x100 +#define APPL_DM_TYPE_MASK GENMASK(3, 0) +#define APPL_DM_TYPE_RP 0x4 +#define APPL_DM_TYPE_EP 0x0 + +#define APPL_CFG_BASE_ADDR 0x104 +#define APPL_CFG_BASE_ADDR_MASK GENMASK(31, 12) + +#define APPL_CFG_IATU_DMA_BASE_ADDR 0x108 +#define APPL_CFG_IATU_DMA_BASE_ADDR_MASK GENMASK(31, 18) + +#define APPL_CFG_MISC 0x110 +#define APPL_CFG_MISC_SLV_EP_MODE BIT(14) +#define APPL_CFG_MISC_ARCACHE_MASK GENMASK(13, 10) +#define APPL_CFG_MISC_ARCACHE_SHIFT 10 +#define APPL_CFG_MISC_ARCACHE_VAL 3 + +#define APPL_CFG_SLCG_OVERRIDE 0x114 +#define APPL_CFG_SLCG_OVERRIDE_SLCG_EN_MASTER BIT(0) + +#define APPL_CAR_RESET_OVRD 0x12C +#define APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N BIT(0) + +#define IO_BASE_IO_DECODE BIT(0) +#define IO_BASE_IO_DECODE_BIT8 BIT(8) + +#define CFG_PREF_MEM_LIMIT_BASE_MEM_DECODE BIT(0) +#define CFG_PREF_MEM_LIMIT_BASE_MEM_LIMIT_DECODE BIT(16) + +#define CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF 0x718 +#define CFG_TIMER_CTRL_ACK_NAK_SHIFT (19) + +#define N_FTS_VAL 52 +#define FTS_VAL 52 + +#define GEN3_EQ_CONTROL_OFF 0x8a8 +#define GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_SHIFT 8 +#define GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_MASK GENMASK(23, 8) +#define GEN3_EQ_CONTROL_OFF_FB_MODE_MASK GENMASK(3, 0) + +#define PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT 0x8D0 +#define AMBA_ERROR_RESPONSE_CRS_SHIFT 3 +#define AMBA_ERROR_RESPONSE_CRS_MASK GENMASK(1, 0) +#define AMBA_ERROR_RESPONSE_CRS_OKAY 0 +#define AMBA_ERROR_RESPONSE_CRS_OKAY_FFFFFFFF 1 +#define AMBA_ERROR_RESPONSE_CRS_OKAY_FFFF0001 2 + +#define MSIX_ADDR_MATCH_LOW_OFF 0x940 +#define MSIX_ADDR_MATCH_LOW_OFF_EN BIT(0) +#define MSIX_ADDR_MATCH_LOW_OFF_MASK GENMASK(31, 2) + +#define MSIX_ADDR_MATCH_HIGH_OFF 0x944 +#define MSIX_ADDR_MATCH_HIGH_OFF_MASK GENMASK(31, 0) + +#define PORT_LOGIC_MSIX_DOORBELL 0x948 + +#define CAP_SPCIE_CAP_OFF 0x154 +#define CAP_SPCIE_CAP_OFF_DSP_TX_PRESET0_MASK GENMASK(3, 0) +#define CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_MASK GENMASK(11, 8) +#define CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_SHIFT 8 + +#define PME_ACK_TIMEOUT 10000 + +#define LTSSM_TIMEOUT 50000 /* 50ms */ + +#define GEN3_GEN4_EQ_PRESET_INIT 5 + +#define GEN1_CORE_CLK_FREQ 62500000 +#define GEN2_CORE_CLK_FREQ 125000000 +#define GEN3_CORE_CLK_FREQ 250000000 +#define GEN4_CORE_CLK_FREQ 500000000 + +#define LTR_MSG_TIMEOUT (100 * 1000) + +#define PERST_DEBOUNCE_TIME (5 * 1000) + +#define EP_STATE_DISABLED 0 +#define EP_STATE_ENABLED 1 + +static const unsigned int pcie_gen_freq[] = { + GEN1_CORE_CLK_FREQ, /* PCI_EXP_LNKSTA_CLS == 0; undefined */ + GEN1_CORE_CLK_FREQ, + GEN2_CORE_CLK_FREQ, + GEN3_CORE_CLK_FREQ, + GEN4_CORE_CLK_FREQ +}; + +struct tegra_pcie_dw_of_data { + u32 version; + enum dw_pcie_device_mode mode; + bool has_msix_doorbell_access_fix; + bool has_sbr_reset_fix; + bool has_l1ss_exit_fix; + bool has_ltr_req_fix; + u32 cdm_chk_int_en_bit; + u32 gen4_preset_vec; + u8 n_fts[2]; +}; + +struct tegra_pcie_dw { + struct device *dev; + struct resource *appl_res; + struct resource *dbi_res; + struct resource *atu_dma_res; + void __iomem *appl_base; + struct clk *core_clk; + struct reset_control *core_apb_rst; + struct reset_control *core_rst; + struct dw_pcie pci; + struct tegra_bpmp *bpmp; + + struct tegra_pcie_dw_of_data *of_data; + + bool supports_clkreq; + bool enable_cdm_check; + bool enable_srns; + bool link_state; + bool update_fc_fixup; + bool enable_ext_refclk; + u8 init_link_width; + u32 msi_ctrl_int; + u32 num_lanes; + u32 cid; + u32 cfg_link_cap_l1sub; + u32 ras_des_cap; + u32 pcie_cap_base; + u32 aspm_cmrt; + u32 aspm_pwr_on_t; + u32 aspm_l0s_enter_lat; + + struct regulator *pex_ctl_supply; + struct regulator *slot_ctl_3v3; + struct regulator *slot_ctl_12v; + + unsigned int phy_count; + struct phy **phys; + + struct dentry *debugfs; + + /* Endpoint mode specific */ + struct gpio_desc *pex_rst_gpiod; + struct gpio_desc *pex_refclk_sel_gpiod; + unsigned int pex_rst_irq; + int ep_state; +}; + +static inline struct tegra_pcie_dw *to_tegra_pcie(struct dw_pcie *pci) +{ + return container_of(pci, struct tegra_pcie_dw, pci); +} + +static inline void appl_writel(struct tegra_pcie_dw *pcie, const u32 value, + const u32 reg) +{ + writel_relaxed(value, pcie->appl_base + reg); +} + +static inline u32 appl_readl(struct tegra_pcie_dw *pcie, const u32 reg) +{ + return readl_relaxed(pcie->appl_base + reg); +} + +struct tegra_pcie_soc { + enum dw_pcie_device_mode mode; +}; + +static void apply_bad_link_workaround(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + u32 current_link_width; + u16 val; + + /* + * NOTE:- Since this scenario is uncommon and link as such is not + * stable anyway, not waiting to confirm if link is really + * transitioning to Gen-2 speed + */ + val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA); + if (val & PCI_EXP_LNKSTA_LBMS) { + current_link_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, val); + if (pcie->init_link_width > current_link_width) { + dev_warn(pci->dev, "PCIe link is bad, width reduced\n"); + val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKCTL2); + val &= ~PCI_EXP_LNKCTL2_TLS; + val |= PCI_EXP_LNKCTL2_TLS_2_5GT; + dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKCTL2, val); + + val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKCTL); + val |= PCI_EXP_LNKCTL_RL; + dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKCTL, val); + } + } +} + +static irqreturn_t tegra_pcie_rp_irq_handler(int irq, void *arg) +{ + struct tegra_pcie_dw *pcie = arg; + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + u32 val, status_l0, status_l1; + u16 val_w; + + status_l0 = appl_readl(pcie, APPL_INTR_STATUS_L0); + if (status_l0 & APPL_INTR_STATUS_L0_LINK_STATE_INT) { + status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_0_0); + appl_writel(pcie, status_l1, APPL_INTR_STATUS_L1_0_0); + if (!pcie->of_data->has_sbr_reset_fix && + status_l1 & APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED) { + /* SBR & Surprise Link Down WAR */ + val = appl_readl(pcie, APPL_CAR_RESET_OVRD); + val &= ~APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N; + appl_writel(pcie, val, APPL_CAR_RESET_OVRD); + udelay(1); + val = appl_readl(pcie, APPL_CAR_RESET_OVRD); + val |= APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N; + appl_writel(pcie, val, APPL_CAR_RESET_OVRD); + + val = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); + val |= PORT_LOGIC_SPEED_CHANGE; + dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val); + } + } + + if (status_l0 & APPL_INTR_STATUS_L0_INT_INT) { + status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_8_0); + if (status_l1 & APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS) { + appl_writel(pcie, + APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS, + APPL_INTR_STATUS_L1_8_0); + apply_bad_link_workaround(pp); + } + if (status_l1 & APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS) { + val_w = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA); + val_w |= PCI_EXP_LNKSTA_LBMS; + dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA, val_w); + + appl_writel(pcie, + APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS, + APPL_INTR_STATUS_L1_8_0); + + val_w = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA); + dev_dbg(pci->dev, "Link Speed : Gen-%u\n", val_w & + PCI_EXP_LNKSTA_CLS); + } + } + + if (status_l0 & APPL_INTR_STATUS_L0_CDM_REG_CHK_INT) { + status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_18); + val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS); + if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT) { + dev_info(pci->dev, "CDM check complete\n"); + val |= PCIE_PL_CHK_REG_CHK_REG_COMPLETE; + } + if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR) { + dev_err(pci->dev, "CDM comparison mismatch\n"); + val |= PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR; + } + if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR) { + dev_err(pci->dev, "CDM Logic error\n"); + val |= PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR; + } + dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val); + val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_ERR_ADDR); + dev_err(pci->dev, "CDM Error Address Offset = 0x%08X\n", val); + } + + return IRQ_HANDLED; +} + +static void pex_ep_event_hot_rst_done(struct tegra_pcie_dw *pcie) +{ + u32 val; + + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_0_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_1); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_2); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_3); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_6); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_7); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_8_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_9); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_10); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_11); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_13); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_14); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_15); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_17); + appl_writel(pcie, 0xFFFFFFFF, APPL_MSI_CTRL_2); + + val = appl_readl(pcie, APPL_CTRL); + val |= APPL_CTRL_LTSSM_EN; + appl_writel(pcie, val, APPL_CTRL); +} + +static irqreturn_t tegra_pcie_ep_irq_thread(int irq, void *arg) +{ + struct tegra_pcie_dw *pcie = arg; + struct dw_pcie *pci = &pcie->pci; + u32 val, speed; + + speed = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA) & + PCI_EXP_LNKSTA_CLS; + + if (speed >= ARRAY_SIZE(pcie_gen_freq)) + speed = 0; + + clk_set_rate(pcie->core_clk, pcie_gen_freq[speed]); + + if (pcie->of_data->has_ltr_req_fix) + return IRQ_HANDLED; + + /* If EP doesn't advertise L1SS, just return */ + val = dw_pcie_readl_dbi(pci, pcie->cfg_link_cap_l1sub); + if (!(val & (PCI_L1SS_CAP_ASPM_L1_1 | PCI_L1SS_CAP_ASPM_L1_2))) + return IRQ_HANDLED; + + /* Check if BME is set to '1' */ + val = dw_pcie_readl_dbi(pci, PCI_COMMAND); + if (val & PCI_COMMAND_MASTER) { + ktime_t timeout; + + /* 110us for both snoop and no-snoop */ + val = 110 | (2 << PCI_LTR_SCALE_SHIFT) | LTR_MSG_REQ; + val |= (val << LTR_MST_NO_SNOOP_SHIFT); + appl_writel(pcie, val, APPL_LTR_MSG_1); + + /* Send LTR upstream */ + val = appl_readl(pcie, APPL_LTR_MSG_2); + val |= APPL_LTR_MSG_2_LTR_MSG_REQ_STATE; + appl_writel(pcie, val, APPL_LTR_MSG_2); + + timeout = ktime_add_us(ktime_get(), LTR_MSG_TIMEOUT); + for (;;) { + val = appl_readl(pcie, APPL_LTR_MSG_2); + if (!(val & APPL_LTR_MSG_2_LTR_MSG_REQ_STATE)) + break; + if (ktime_after(ktime_get(), timeout)) + break; + usleep_range(1000, 1100); + } + if (val & APPL_LTR_MSG_2_LTR_MSG_REQ_STATE) + dev_err(pcie->dev, "Failed to send LTR message\n"); + } + + return IRQ_HANDLED; +} + +static irqreturn_t tegra_pcie_ep_hard_irq(int irq, void *arg) +{ + struct tegra_pcie_dw *pcie = arg; + struct dw_pcie_ep *ep = &pcie->pci.ep; + int spurious = 1; + u32 status_l0, status_l1, link_status; + + status_l0 = appl_readl(pcie, APPL_INTR_STATUS_L0); + if (status_l0 & APPL_INTR_STATUS_L0_LINK_STATE_INT) { + status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_0_0); + appl_writel(pcie, status_l1, APPL_INTR_STATUS_L1_0_0); + + if (status_l1 & APPL_INTR_STATUS_L1_0_0_HOT_RESET_DONE) + pex_ep_event_hot_rst_done(pcie); + + if (status_l1 & APPL_INTR_STATUS_L1_0_0_RDLH_LINK_UP_CHGED) { + link_status = appl_readl(pcie, APPL_LINK_STATUS); + if (link_status & APPL_LINK_STATUS_RDLH_LINK_UP) { + dev_dbg(pcie->dev, "Link is up with Host\n"); + dw_pcie_ep_linkup(ep); + } + } + + spurious = 0; + } + + if (status_l0 & APPL_INTR_STATUS_L0_PCI_CMD_EN_INT) { + status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_15); + appl_writel(pcie, status_l1, APPL_INTR_STATUS_L1_15); + + if (status_l1 & APPL_INTR_STATUS_L1_15_CFG_BME_CHGED) + return IRQ_WAKE_THREAD; + + spurious = 0; + } + + if (spurious) { + dev_warn(pcie->dev, "Random interrupt (STATUS = 0x%08X)\n", + status_l0); + appl_writel(pcie, status_l0, APPL_INTR_STATUS_L0); + } + + return IRQ_HANDLED; +} + +static int tegra_pcie_dw_rd_own_conf(struct pci_bus *bus, u32 devfn, int where, + int size, u32 *val) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + + /* + * This is an endpoint mode specific register happen to appear even + * when controller is operating in root port mode and system hangs + * when it is accessed with link being in ASPM-L1 state. + * So skip accessing it altogether + */ + if (!pcie->of_data->has_msix_doorbell_access_fix && + !PCI_SLOT(devfn) && where == PORT_LOGIC_MSIX_DOORBELL) { + *val = 0x00000000; + return PCIBIOS_SUCCESSFUL; + } + + return pci_generic_config_read(bus, devfn, where, size, val); +} + +static int tegra_pcie_dw_wr_own_conf(struct pci_bus *bus, u32 devfn, int where, + int size, u32 val) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + + /* + * This is an endpoint mode specific register happen to appear even + * when controller is operating in root port mode and system hangs + * when it is accessed with link being in ASPM-L1 state. + * So skip accessing it altogether + */ + if (!pcie->of_data->has_msix_doorbell_access_fix && + !PCI_SLOT(devfn) && where == PORT_LOGIC_MSIX_DOORBELL) + return PCIBIOS_SUCCESSFUL; + + return pci_generic_config_write(bus, devfn, where, size, val); +} + +static struct pci_ops tegra_pci_ops = { + .map_bus = dw_pcie_own_conf_map_bus, + .read = tegra_pcie_dw_rd_own_conf, + .write = tegra_pcie_dw_wr_own_conf, +}; + +#if defined(CONFIG_PCIEASPM) +static void disable_aspm_l11(struct tegra_pcie_dw *pcie) +{ + u32 val; + + val = dw_pcie_readl_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub); + val &= ~PCI_L1SS_CAP_ASPM_L1_1; + dw_pcie_writel_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub, val); +} + +static void disable_aspm_l12(struct tegra_pcie_dw *pcie) +{ + u32 val; + + val = dw_pcie_readl_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub); + val &= ~PCI_L1SS_CAP_ASPM_L1_2; + dw_pcie_writel_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub, val); +} + +static inline u32 event_counter_prog(struct tegra_pcie_dw *pcie, u32 event) +{ + u32 val; + + val = dw_pcie_readl_dbi(&pcie->pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_CONTROL); + val &= ~(EVENT_COUNTER_EVENT_SEL_MASK << EVENT_COUNTER_EVENT_SEL_SHIFT); + val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT; + val |= event << EVENT_COUNTER_EVENT_SEL_SHIFT; + val |= EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT; + dw_pcie_writel_dbi(&pcie->pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_CONTROL, val); + val = dw_pcie_readl_dbi(&pcie->pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_DATA); + + return val; +} + +static int aspm_state_cnt(struct seq_file *s, void *data) +{ + struct tegra_pcie_dw *pcie = (struct tegra_pcie_dw *) + dev_get_drvdata(s->private); + u32 val; + + seq_printf(s, "Tx L0s entry count : %u\n", + event_counter_prog(pcie, EVENT_COUNTER_EVENT_Tx_L0S)); + + seq_printf(s, "Rx L0s entry count : %u\n", + event_counter_prog(pcie, EVENT_COUNTER_EVENT_Rx_L0S)); + + seq_printf(s, "Link L1 entry count : %u\n", + event_counter_prog(pcie, EVENT_COUNTER_EVENT_L1)); + + seq_printf(s, "Link L1.1 entry count : %u\n", + event_counter_prog(pcie, EVENT_COUNTER_EVENT_L1_1)); + + seq_printf(s, "Link L1.2 entry count : %u\n", + event_counter_prog(pcie, EVENT_COUNTER_EVENT_L1_2)); + + /* Clear all counters */ + dw_pcie_writel_dbi(&pcie->pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_CONTROL, + EVENT_COUNTER_ALL_CLEAR); + + /* Re-enable counting */ + val = EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT; + val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT; + dw_pcie_writel_dbi(&pcie->pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_CONTROL, val); + + return 0; +} + +static void init_host_aspm(struct tegra_pcie_dw *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + u32 val; + + val = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_L1SS); + pcie->cfg_link_cap_l1sub = val + PCI_L1SS_CAP; + + pcie->ras_des_cap = dw_pcie_find_ext_capability(&pcie->pci, + PCI_EXT_CAP_ID_VNDR); + + /* Enable ASPM counters */ + val = EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT; + val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT; + dw_pcie_writel_dbi(pci, pcie->ras_des_cap + + PCIE_RAS_DES_EVENT_COUNTER_CONTROL, val); + + /* Program T_cmrt and T_pwr_on values */ + val = dw_pcie_readl_dbi(pci, pcie->cfg_link_cap_l1sub); + val &= ~(PCI_L1SS_CAP_CM_RESTORE_TIME | PCI_L1SS_CAP_P_PWR_ON_VALUE); + val |= (pcie->aspm_cmrt << 8); + val |= (pcie->aspm_pwr_on_t << 19); + dw_pcie_writel_dbi(pci, pcie->cfg_link_cap_l1sub, val); + + /* Program L0s and L1 entrance latencies */ + val = dw_pcie_readl_dbi(pci, PCIE_PORT_AFR); + val &= ~PORT_AFR_L0S_ENTRANCE_LAT_MASK; + val |= (pcie->aspm_l0s_enter_lat << PORT_AFR_L0S_ENTRANCE_LAT_SHIFT); + val |= PORT_AFR_ENTER_ASPM; + dw_pcie_writel_dbi(pci, PCIE_PORT_AFR, val); +} + +static void init_debugfs(struct tegra_pcie_dw *pcie) +{ + debugfs_create_devm_seqfile(pcie->dev, "aspm_state_cnt", pcie->debugfs, + aspm_state_cnt); +} +#else +static inline void disable_aspm_l12(struct tegra_pcie_dw *pcie) { return; } +static inline void disable_aspm_l11(struct tegra_pcie_dw *pcie) { return; } +static inline void init_host_aspm(struct tegra_pcie_dw *pcie) { return; } +static inline void init_debugfs(struct tegra_pcie_dw *pcie) { return; } +#endif + +static void tegra_pcie_enable_system_interrupts(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + u32 val; + u16 val_w; + + val = appl_readl(pcie, APPL_INTR_EN_L0_0); + val |= APPL_INTR_EN_L0_0_LINK_STATE_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L0_0); + + if (!pcie->of_data->has_sbr_reset_fix) { + val = appl_readl(pcie, APPL_INTR_EN_L1_0_0); + val |= APPL_INTR_EN_L1_0_0_LINK_REQ_RST_NOT_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L1_0_0); + } + + if (pcie->enable_cdm_check) { + val = appl_readl(pcie, APPL_INTR_EN_L0_0); + val |= pcie->of_data->cdm_chk_int_en_bit; + appl_writel(pcie, val, APPL_INTR_EN_L0_0); + + val = appl_readl(pcie, APPL_INTR_EN_L1_18); + val |= APPL_INTR_EN_L1_18_CDM_REG_CHK_CMP_ERR; + val |= APPL_INTR_EN_L1_18_CDM_REG_CHK_LOGIC_ERR; + appl_writel(pcie, val, APPL_INTR_EN_L1_18); + } + + val_w = dw_pcie_readw_dbi(&pcie->pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA); + pcie->init_link_width = FIELD_GET(PCI_EXP_LNKSTA_NLW, val_w); + + val_w = dw_pcie_readw_dbi(&pcie->pci, pcie->pcie_cap_base + + PCI_EXP_LNKCTL); + val_w |= PCI_EXP_LNKCTL_LBMIE; + dw_pcie_writew_dbi(&pcie->pci, pcie->pcie_cap_base + PCI_EXP_LNKCTL, + val_w); +} + +static void tegra_pcie_enable_legacy_interrupts(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + u32 val; + + /* Enable legacy interrupt generation */ + val = appl_readl(pcie, APPL_INTR_EN_L0_0); + val |= APPL_INTR_EN_L0_0_SYS_INTR_EN; + val |= APPL_INTR_EN_L0_0_INT_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L0_0); + + val = appl_readl(pcie, APPL_INTR_EN_L1_8_0); + val |= APPL_INTR_EN_L1_8_INTX_EN; + val |= APPL_INTR_EN_L1_8_AUTO_BW_INT_EN; + val |= APPL_INTR_EN_L1_8_BW_MGT_INT_EN; + if (IS_ENABLED(CONFIG_PCIEAER)) + val |= APPL_INTR_EN_L1_8_AER_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L1_8_0); +} + +static void tegra_pcie_enable_msi_interrupts(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + u32 val; + + /* Enable MSI interrupt generation */ + val = appl_readl(pcie, APPL_INTR_EN_L0_0); + val |= APPL_INTR_EN_L0_0_SYS_MSI_INTR_EN; + val |= APPL_INTR_EN_L0_0_MSI_RCV_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L0_0); +} + +static void tegra_pcie_enable_interrupts(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + + /* Clear interrupt statuses before enabling interrupts */ + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_0_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_1); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_2); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_3); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_6); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_7); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_8_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_9); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_10); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_11); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_13); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_14); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_15); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_17); + + tegra_pcie_enable_system_interrupts(pp); + tegra_pcie_enable_legacy_interrupts(pp); + if (IS_ENABLED(CONFIG_PCI_MSI)) + tegra_pcie_enable_msi_interrupts(pp); +} + +static void config_gen3_gen4_eq_presets(struct tegra_pcie_dw *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + u32 val, offset, i; + + /* Program init preset */ + for (i = 0; i < pcie->num_lanes; i++) { + val = dw_pcie_readw_dbi(pci, CAP_SPCIE_CAP_OFF + (i * 2)); + val &= ~CAP_SPCIE_CAP_OFF_DSP_TX_PRESET0_MASK; + val |= GEN3_GEN4_EQ_PRESET_INIT; + val &= ~CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_MASK; + val |= (GEN3_GEN4_EQ_PRESET_INIT << + CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_SHIFT); + dw_pcie_writew_dbi(pci, CAP_SPCIE_CAP_OFF + (i * 2), val); + + offset = dw_pcie_find_ext_capability(pci, + PCI_EXT_CAP_ID_PL_16GT) + + PCI_PL_16GT_LE_CTRL; + val = dw_pcie_readb_dbi(pci, offset + i); + val &= ~PCI_PL_16GT_LE_CTRL_DSP_TX_PRESET_MASK; + val |= GEN3_GEN4_EQ_PRESET_INIT; + val &= ~PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK; + val |= (GEN3_GEN4_EQ_PRESET_INIT << + PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT); + dw_pcie_writeb_dbi(pci, offset + i, val); + } + + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val &= ~GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK; + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); + + val = dw_pcie_readl_dbi(pci, GEN3_EQ_CONTROL_OFF); + val &= ~GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_MASK; + val |= (0x3ff << GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_SHIFT); + val &= ~GEN3_EQ_CONTROL_OFF_FB_MODE_MASK; + dw_pcie_writel_dbi(pci, GEN3_EQ_CONTROL_OFF, val); + + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val &= ~GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK; + val |= (0x1 << GEN3_RELATED_OFF_RATE_SHADOW_SEL_SHIFT); + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); + + val = dw_pcie_readl_dbi(pci, GEN3_EQ_CONTROL_OFF); + val &= ~GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_MASK; + val |= (pcie->of_data->gen4_preset_vec << + GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_SHIFT); + val &= ~GEN3_EQ_CONTROL_OFF_FB_MODE_MASK; + dw_pcie_writel_dbi(pci, GEN3_EQ_CONTROL_OFF, val); + + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val &= ~GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK; + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); +} + +static int tegra_pcie_dw_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + u32 val; + u16 val_16; + + pp->bridge->ops = &tegra_pci_ops; + + if (!pcie->pcie_cap_base) + pcie->pcie_cap_base = dw_pcie_find_capability(&pcie->pci, + PCI_CAP_ID_EXP); + + val = dw_pcie_readl_dbi(pci, PCI_IO_BASE); + val &= ~(IO_BASE_IO_DECODE | IO_BASE_IO_DECODE_BIT8); + dw_pcie_writel_dbi(pci, PCI_IO_BASE, val); + + val = dw_pcie_readl_dbi(pci, PCI_PREF_MEMORY_BASE); + val |= CFG_PREF_MEM_LIMIT_BASE_MEM_DECODE; + val |= CFG_PREF_MEM_LIMIT_BASE_MEM_LIMIT_DECODE; + dw_pcie_writel_dbi(pci, PCI_PREF_MEMORY_BASE, val); + + dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0); + + /* Enable as 0xFFFF0001 response for CRS */ + val = dw_pcie_readl_dbi(pci, PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT); + val &= ~(AMBA_ERROR_RESPONSE_CRS_MASK << AMBA_ERROR_RESPONSE_CRS_SHIFT); + val |= (AMBA_ERROR_RESPONSE_CRS_OKAY_FFFF0001 << + AMBA_ERROR_RESPONSE_CRS_SHIFT); + dw_pcie_writel_dbi(pci, PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT, val); + + /* Configure Max lane width from DT */ + val = dw_pcie_readl_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKCAP); + val &= ~PCI_EXP_LNKCAP_MLW; + val |= FIELD_PREP(PCI_EXP_LNKCAP_MLW, pcie->num_lanes); + dw_pcie_writel_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKCAP, val); + + /* Clear Slot Clock Configuration bit if SRNS configuration */ + if (pcie->enable_srns) { + val_16 = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA); + val_16 &= ~PCI_EXP_LNKSTA_SLC; + dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA, + val_16); + } + + config_gen3_gen4_eq_presets(pcie); + + init_host_aspm(pcie); + + /* Disable ASPM-L1SS advertisement if there is no CLKREQ routing */ + if (!pcie->supports_clkreq) { + disable_aspm_l11(pcie); + disable_aspm_l12(pcie); + } + + if (!pcie->of_data->has_l1ss_exit_fix) { + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL; + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); + } + + if (pcie->update_fc_fixup) { + val = dw_pcie_readl_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF); + val |= 0x1 << CFG_TIMER_CTRL_ACK_NAK_SHIFT; + dw_pcie_writel_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF, val); + } + + clk_set_rate(pcie->core_clk, GEN4_CORE_CLK_FREQ); + + return 0; +} + +static int tegra_pcie_dw_start_link(struct dw_pcie *pci) +{ + u32 val, offset, speed, tmp; + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + struct dw_pcie_rp *pp = &pci->pp; + bool retry = true; + + if (pcie->of_data->mode == DW_PCIE_EP_TYPE) { + enable_irq(pcie->pex_rst_irq); + return 0; + } + +retry_link: + /* Assert RST */ + val = appl_readl(pcie, APPL_PINMUX); + val &= ~APPL_PINMUX_PEX_RST; + appl_writel(pcie, val, APPL_PINMUX); + + usleep_range(100, 200); + + /* Enable LTSSM */ + val = appl_readl(pcie, APPL_CTRL); + val |= APPL_CTRL_LTSSM_EN; + appl_writel(pcie, val, APPL_CTRL); + + /* De-assert RST */ + val = appl_readl(pcie, APPL_PINMUX); + val |= APPL_PINMUX_PEX_RST; + appl_writel(pcie, val, APPL_PINMUX); + + msleep(100); + + if (dw_pcie_wait_for_link(pci)) { + if (!retry) + return 0; + /* + * There are some endpoints which can't get the link up if + * root port has Data Link Feature (DLF) enabled. + * Refer Spec rev 4.0 ver 1.0 sec 3.4.2 & 7.7.4 for more info + * on Scaled Flow Control and DLF. + * So, need to confirm that is indeed the case here and attempt + * link up once again with DLF disabled. + */ + val = appl_readl(pcie, APPL_DEBUG); + val &= APPL_DEBUG_LTSSM_STATE_MASK; + val >>= APPL_DEBUG_LTSSM_STATE_SHIFT; + tmp = appl_readl(pcie, APPL_LINK_STATUS); + tmp &= APPL_LINK_STATUS_RDLH_LINK_UP; + if (!(val == 0x11 && !tmp)) { + /* Link is down for all good reasons */ + return 0; + } + + dev_info(pci->dev, "Link is down in DLL"); + dev_info(pci->dev, "Trying again with DLFE disabled\n"); + /* Disable LTSSM */ + val = appl_readl(pcie, APPL_CTRL); + val &= ~APPL_CTRL_LTSSM_EN; + appl_writel(pcie, val, APPL_CTRL); + + reset_control_assert(pcie->core_rst); + reset_control_deassert(pcie->core_rst); + + offset = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_DLF); + val = dw_pcie_readl_dbi(pci, offset + PCI_DLF_CAP); + val &= ~PCI_DLF_EXCHANGE_ENABLE; + dw_pcie_writel_dbi(pci, offset + PCI_DLF_CAP, val); + + tegra_pcie_dw_host_init(pp); + dw_pcie_setup_rc(pp); + + retry = false; + goto retry_link; + } + + speed = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA) & + PCI_EXP_LNKSTA_CLS; + + if (speed >= ARRAY_SIZE(pcie_gen_freq)) + speed = 0; + + clk_set_rate(pcie->core_clk, pcie_gen_freq[speed]); + + tegra_pcie_enable_interrupts(pp); + + return 0; +} + +static int tegra_pcie_dw_link_up(struct dw_pcie *pci) +{ + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + u32 val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA); + + return !!(val & PCI_EXP_LNKSTA_DLLLA); +} + +static void tegra_pcie_dw_stop_link(struct dw_pcie *pci) +{ + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + + disable_irq(pcie->pex_rst_irq); +} + +static const struct dw_pcie_ops tegra_dw_pcie_ops = { + .link_up = tegra_pcie_dw_link_up, + .start_link = tegra_pcie_dw_start_link, + .stop_link = tegra_pcie_dw_stop_link, +}; + +static const struct dw_pcie_host_ops tegra_pcie_dw_host_ops = { + .host_init = tegra_pcie_dw_host_init, +}; + +static void tegra_pcie_disable_phy(struct tegra_pcie_dw *pcie) +{ + unsigned int phy_count = pcie->phy_count; + + while (phy_count--) { + phy_power_off(pcie->phys[phy_count]); + phy_exit(pcie->phys[phy_count]); + } +} + +static int tegra_pcie_enable_phy(struct tegra_pcie_dw *pcie) +{ + unsigned int i; + int ret; + + for (i = 0; i < pcie->phy_count; i++) { + ret = phy_init(pcie->phys[i]); + if (ret < 0) + goto phy_power_off; + + ret = phy_power_on(pcie->phys[i]); + if (ret < 0) + goto phy_exit; + } + + return 0; + +phy_power_off: + while (i--) { + phy_power_off(pcie->phys[i]); +phy_exit: + phy_exit(pcie->phys[i]); + } + + return ret; +} + +static int tegra_pcie_dw_parse_dt(struct tegra_pcie_dw *pcie) +{ + struct platform_device *pdev = to_platform_device(pcie->dev); + struct device_node *np = pcie->dev->of_node; + int ret; + + pcie->dbi_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi"); + if (!pcie->dbi_res) { + dev_err(pcie->dev, "Failed to find \"dbi\" region\n"); + return -ENODEV; + } + + ret = of_property_read_u32(np, "nvidia,aspm-cmrt-us", &pcie->aspm_cmrt); + if (ret < 0) { + dev_info(pcie->dev, "Failed to read ASPM T_cmrt: %d\n", ret); + return ret; + } + + ret = of_property_read_u32(np, "nvidia,aspm-pwr-on-t-us", + &pcie->aspm_pwr_on_t); + if (ret < 0) + dev_info(pcie->dev, "Failed to read ASPM Power On time: %d\n", + ret); + + ret = of_property_read_u32(np, "nvidia,aspm-l0s-entrance-latency-us", + &pcie->aspm_l0s_enter_lat); + if (ret < 0) + dev_info(pcie->dev, + "Failed to read ASPM L0s Entrance latency: %d\n", ret); + + ret = of_property_read_u32(np, "num-lanes", &pcie->num_lanes); + if (ret < 0) { + dev_err(pcie->dev, "Failed to read num-lanes: %d\n", ret); + return ret; + } + + ret = of_property_read_u32_index(np, "nvidia,bpmp", 1, &pcie->cid); + if (ret) { + dev_err(pcie->dev, "Failed to read Controller-ID: %d\n", ret); + return ret; + } + + ret = of_property_count_strings(np, "phy-names"); + if (ret < 0) { + dev_err(pcie->dev, "Failed to find PHY entries: %d\n", + ret); + return ret; + } + pcie->phy_count = ret; + + if (of_property_read_bool(np, "nvidia,update-fc-fixup")) + pcie->update_fc_fixup = true; + + /* RP using an external REFCLK is supported only in Tegra234 */ + if (pcie->of_data->version == TEGRA194_DWC_IP_VER) { + if (pcie->of_data->mode == DW_PCIE_EP_TYPE) + pcie->enable_ext_refclk = true; + } else { + pcie->enable_ext_refclk = + of_property_read_bool(pcie->dev->of_node, + "nvidia,enable-ext-refclk"); + } + + pcie->supports_clkreq = + of_property_read_bool(pcie->dev->of_node, "supports-clkreq"); + + pcie->enable_cdm_check = + of_property_read_bool(np, "snps,enable-cdm-check"); + + if (pcie->of_data->version == TEGRA234_DWC_IP_VER) + pcie->enable_srns = + of_property_read_bool(np, "nvidia,enable-srns"); + + if (pcie->of_data->mode == DW_PCIE_RC_TYPE) + return 0; + + /* Endpoint mode specific DT entries */ + pcie->pex_rst_gpiod = devm_gpiod_get(pcie->dev, "reset", GPIOD_IN); + if (IS_ERR(pcie->pex_rst_gpiod)) { + int err = PTR_ERR(pcie->pex_rst_gpiod); + const char *level = KERN_ERR; + + if (err == -EPROBE_DEFER) + level = KERN_DEBUG; + + dev_printk(level, pcie->dev, + dev_fmt("Failed to get PERST GPIO: %d\n"), + err); + return err; + } + + pcie->pex_refclk_sel_gpiod = devm_gpiod_get(pcie->dev, + "nvidia,refclk-select", + GPIOD_OUT_HIGH); + if (IS_ERR(pcie->pex_refclk_sel_gpiod)) { + int err = PTR_ERR(pcie->pex_refclk_sel_gpiod); + const char *level = KERN_ERR; + + if (err == -EPROBE_DEFER) + level = KERN_DEBUG; + + dev_printk(level, pcie->dev, + dev_fmt("Failed to get REFCLK select GPIOs: %d\n"), + err); + pcie->pex_refclk_sel_gpiod = NULL; + } + + return 0; +} + +static int tegra_pcie_bpmp_set_ctrl_state(struct tegra_pcie_dw *pcie, + bool enable) +{ + struct mrq_uphy_response resp; + struct tegra_bpmp_message msg; + struct mrq_uphy_request req; + + /* + * Controller-5 doesn't need to have its state set by BPMP-FW in + * Tegra194 + */ + if (pcie->of_data->version == TEGRA194_DWC_IP_VER && pcie->cid == 5) + return 0; + + memset(&req, 0, sizeof(req)); + memset(&resp, 0, sizeof(resp)); + + req.cmd = CMD_UPHY_PCIE_CONTROLLER_STATE; + req.controller_state.pcie_controller = pcie->cid; + req.controller_state.enable = enable; + + memset(&msg, 0, sizeof(msg)); + msg.mrq = MRQ_UPHY; + msg.tx.data = &req; + msg.tx.size = sizeof(req); + msg.rx.data = &resp; + msg.rx.size = sizeof(resp); + + return tegra_bpmp_transfer(pcie->bpmp, &msg); +} + +static int tegra_pcie_bpmp_set_pll_state(struct tegra_pcie_dw *pcie, + bool enable) +{ + struct mrq_uphy_response resp; + struct tegra_bpmp_message msg; + struct mrq_uphy_request req; + + memset(&req, 0, sizeof(req)); + memset(&resp, 0, sizeof(resp)); + + if (enable) { + req.cmd = CMD_UPHY_PCIE_EP_CONTROLLER_PLL_INIT; + req.ep_ctrlr_pll_init.ep_controller = pcie->cid; + } else { + req.cmd = CMD_UPHY_PCIE_EP_CONTROLLER_PLL_OFF; + req.ep_ctrlr_pll_off.ep_controller = pcie->cid; + } + + memset(&msg, 0, sizeof(msg)); + msg.mrq = MRQ_UPHY; + msg.tx.data = &req; + msg.tx.size = sizeof(req); + msg.rx.data = &resp; + msg.rx.size = sizeof(resp); + + return tegra_bpmp_transfer(pcie->bpmp, &msg); +} + +static void tegra_pcie_downstream_dev_to_D0(struct tegra_pcie_dw *pcie) +{ + struct dw_pcie_rp *pp = &pcie->pci.pp; + struct pci_bus *child, *root_bus = NULL; + struct pci_dev *pdev; + + /* + * link doesn't go into L2 state with some of the endpoints with Tegra + * if they are not in D0 state. So, need to make sure that immediate + * downstream devices are in D0 state before sending PME_TurnOff to put + * link into L2 state. + * This is as per PCI Express Base r4.0 v1.0 September 27-2017, + * 5.2 Link State Power Management (Page #428). + */ + + list_for_each_entry(child, &pp->bridge->bus->children, node) { + /* Bring downstream devices to D0 if they are not already in */ + if (child->parent == pp->bridge->bus) { + root_bus = child; + break; + } + } + + if (!root_bus) { + dev_err(pcie->dev, "Failed to find downstream devices\n"); + return; + } + + list_for_each_entry(pdev, &root_bus->devices, bus_list) { + if (PCI_SLOT(pdev->devfn) == 0) { + if (pci_set_power_state(pdev, PCI_D0)) + dev_err(pcie->dev, + "Failed to transition %s to D0 state\n", + dev_name(&pdev->dev)); + } + } +} + +static int tegra_pcie_get_slot_regulators(struct tegra_pcie_dw *pcie) +{ + pcie->slot_ctl_3v3 = devm_regulator_get_optional(pcie->dev, "vpcie3v3"); + if (IS_ERR(pcie->slot_ctl_3v3)) { + if (PTR_ERR(pcie->slot_ctl_3v3) != -ENODEV) + return PTR_ERR(pcie->slot_ctl_3v3); + + pcie->slot_ctl_3v3 = NULL; + } + + pcie->slot_ctl_12v = devm_regulator_get_optional(pcie->dev, "vpcie12v"); + if (IS_ERR(pcie->slot_ctl_12v)) { + if (PTR_ERR(pcie->slot_ctl_12v) != -ENODEV) + return PTR_ERR(pcie->slot_ctl_12v); + + pcie->slot_ctl_12v = NULL; + } + + return 0; +} + +static int tegra_pcie_enable_slot_regulators(struct tegra_pcie_dw *pcie) +{ + int ret; + + if (pcie->slot_ctl_3v3) { + ret = regulator_enable(pcie->slot_ctl_3v3); + if (ret < 0) { + dev_err(pcie->dev, + "Failed to enable 3.3V slot supply: %d\n", ret); + return ret; + } + } + + if (pcie->slot_ctl_12v) { + ret = regulator_enable(pcie->slot_ctl_12v); + if (ret < 0) { + dev_err(pcie->dev, + "Failed to enable 12V slot supply: %d\n", ret); + goto fail_12v_enable; + } + } + + /* + * According to PCI Express Card Electromechanical Specification + * Revision 1.1, Table-2.4, T_PVPERL (Power stable to PERST# inactive) + * should be a minimum of 100ms. + */ + if (pcie->slot_ctl_3v3 || pcie->slot_ctl_12v) + msleep(100); + + return 0; + +fail_12v_enable: + if (pcie->slot_ctl_3v3) + regulator_disable(pcie->slot_ctl_3v3); + return ret; +} + +static void tegra_pcie_disable_slot_regulators(struct tegra_pcie_dw *pcie) +{ + if (pcie->slot_ctl_12v) + regulator_disable(pcie->slot_ctl_12v); + if (pcie->slot_ctl_3v3) + regulator_disable(pcie->slot_ctl_3v3); +} + +static int tegra_pcie_config_controller(struct tegra_pcie_dw *pcie, + bool en_hw_hot_rst) +{ + int ret; + u32 val; + + ret = tegra_pcie_bpmp_set_ctrl_state(pcie, true); + if (ret) { + dev_err(pcie->dev, + "Failed to enable controller %u: %d\n", pcie->cid, ret); + return ret; + } + + if (pcie->enable_ext_refclk) { + ret = tegra_pcie_bpmp_set_pll_state(pcie, true); + if (ret) { + dev_err(pcie->dev, "Failed to init UPHY: %d\n", ret); + goto fail_pll_init; + } + } + + ret = tegra_pcie_enable_slot_regulators(pcie); + if (ret < 0) + goto fail_slot_reg_en; + + ret = regulator_enable(pcie->pex_ctl_supply); + if (ret < 0) { + dev_err(pcie->dev, "Failed to enable regulator: %d\n", ret); + goto fail_reg_en; + } + + ret = clk_prepare_enable(pcie->core_clk); + if (ret) { + dev_err(pcie->dev, "Failed to enable core clock: %d\n", ret); + goto fail_core_clk; + } + + ret = reset_control_deassert(pcie->core_apb_rst); + if (ret) { + dev_err(pcie->dev, "Failed to deassert core APB reset: %d\n", + ret); + goto fail_core_apb_rst; + } + + if (en_hw_hot_rst || pcie->of_data->has_sbr_reset_fix) { + /* Enable HW_HOT_RST mode */ + val = appl_readl(pcie, APPL_CTRL); + val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK << + APPL_CTRL_HW_HOT_RST_MODE_SHIFT); + val |= (APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST_LTSSM_EN << + APPL_CTRL_HW_HOT_RST_MODE_SHIFT); + val |= APPL_CTRL_HW_HOT_RST_EN; + appl_writel(pcie, val, APPL_CTRL); + } + + ret = tegra_pcie_enable_phy(pcie); + if (ret) { + dev_err(pcie->dev, "Failed to enable PHY: %d\n", ret); + goto fail_phy; + } + + /* Update CFG base address */ + appl_writel(pcie, pcie->dbi_res->start & APPL_CFG_BASE_ADDR_MASK, + APPL_CFG_BASE_ADDR); + + /* Configure this core for RP mode operation */ + appl_writel(pcie, APPL_DM_TYPE_RP, APPL_DM_TYPE); + + appl_writel(pcie, 0x0, APPL_CFG_SLCG_OVERRIDE); + + val = appl_readl(pcie, APPL_CTRL); + appl_writel(pcie, val | APPL_CTRL_SYS_PRE_DET_STATE, APPL_CTRL); + + val = appl_readl(pcie, APPL_CFG_MISC); + val |= (APPL_CFG_MISC_ARCACHE_VAL << APPL_CFG_MISC_ARCACHE_SHIFT); + appl_writel(pcie, val, APPL_CFG_MISC); + + if (pcie->enable_srns || pcie->enable_ext_refclk) { + /* + * When Tegra PCIe RP is using external clock, it cannot supply + * same clock to its downstream hierarchy. Hence, gate PCIe RP + * REFCLK out pads when RP & EP are using separate clocks or RP + * is using an external REFCLK. + */ + val = appl_readl(pcie, APPL_PINMUX); + val |= APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE_EN; + val &= ~APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE; + appl_writel(pcie, val, APPL_PINMUX); + } + + if (!pcie->supports_clkreq) { + val = appl_readl(pcie, APPL_PINMUX); + val |= APPL_PINMUX_CLKREQ_OVERRIDE_EN; + val &= ~APPL_PINMUX_CLKREQ_OVERRIDE; + appl_writel(pcie, val, APPL_PINMUX); + } + + /* Update iATU_DMA base address */ + appl_writel(pcie, + pcie->atu_dma_res->start & APPL_CFG_IATU_DMA_BASE_ADDR_MASK, + APPL_CFG_IATU_DMA_BASE_ADDR); + + reset_control_deassert(pcie->core_rst); + + return ret; + +fail_phy: + reset_control_assert(pcie->core_apb_rst); +fail_core_apb_rst: + clk_disable_unprepare(pcie->core_clk); +fail_core_clk: + regulator_disable(pcie->pex_ctl_supply); +fail_reg_en: + tegra_pcie_disable_slot_regulators(pcie); +fail_slot_reg_en: + if (pcie->enable_ext_refclk) + tegra_pcie_bpmp_set_pll_state(pcie, false); +fail_pll_init: + tegra_pcie_bpmp_set_ctrl_state(pcie, false); + + return ret; +} + +static void tegra_pcie_unconfig_controller(struct tegra_pcie_dw *pcie) +{ + int ret; + + ret = reset_control_assert(pcie->core_rst); + if (ret) + dev_err(pcie->dev, "Failed to assert \"core\" reset: %d\n", ret); + + tegra_pcie_disable_phy(pcie); + + ret = reset_control_assert(pcie->core_apb_rst); + if (ret) + dev_err(pcie->dev, "Failed to assert APB reset: %d\n", ret); + + clk_disable_unprepare(pcie->core_clk); + + ret = regulator_disable(pcie->pex_ctl_supply); + if (ret) + dev_err(pcie->dev, "Failed to disable regulator: %d\n", ret); + + tegra_pcie_disable_slot_regulators(pcie); + + if (pcie->enable_ext_refclk) { + ret = tegra_pcie_bpmp_set_pll_state(pcie, false); + if (ret) + dev_err(pcie->dev, "Failed to deinit UPHY: %d\n", ret); + } + + ret = tegra_pcie_bpmp_set_ctrl_state(pcie, false); + if (ret) + dev_err(pcie->dev, "Failed to disable controller %d: %d\n", + pcie->cid, ret); +} + +static int tegra_pcie_init_controller(struct tegra_pcie_dw *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + int ret; + + ret = tegra_pcie_config_controller(pcie, false); + if (ret < 0) + return ret; + + pp->ops = &tegra_pcie_dw_host_ops; + + ret = dw_pcie_host_init(pp); + if (ret < 0) { + dev_err(pcie->dev, "Failed to add PCIe port: %d\n", ret); + goto fail_host_init; + } + + return 0; + +fail_host_init: + tegra_pcie_unconfig_controller(pcie); + return ret; +} + +static int tegra_pcie_try_link_l2(struct tegra_pcie_dw *pcie) +{ + u32 val; + + if (!tegra_pcie_dw_link_up(&pcie->pci)) + return 0; + + val = appl_readl(pcie, APPL_RADM_STATUS); + val |= APPL_PM_XMT_TURNOFF_STATE; + appl_writel(pcie, val, APPL_RADM_STATUS); + + return readl_poll_timeout_atomic(pcie->appl_base + APPL_DEBUG, val, + val & APPL_DEBUG_PM_LINKST_IN_L2_LAT, + 1, PME_ACK_TIMEOUT); +} + +static void tegra_pcie_dw_pme_turnoff(struct tegra_pcie_dw *pcie) +{ + u32 data; + int err; + + if (!tegra_pcie_dw_link_up(&pcie->pci)) { + dev_dbg(pcie->dev, "PCIe link is not up...!\n"); + return; + } + + /* + * PCIe controller exits from L2 only if reset is applied, so + * controller doesn't handle interrupts. But in cases where + * L2 entry fails, PERST# is asserted which can trigger surprise + * link down AER. However this function call happens in + * suspend_noirq(), so AER interrupt will not be processed. + * Disable all interrupts to avoid such a scenario. + */ + appl_writel(pcie, 0x0, APPL_INTR_EN_L0_0); + + if (tegra_pcie_try_link_l2(pcie)) { + dev_info(pcie->dev, "Link didn't transition to L2 state\n"); + /* + * TX lane clock freq will reset to Gen1 only if link is in L2 + * or detect state. + * So apply pex_rst to end point to force RP to go into detect + * state + */ + data = appl_readl(pcie, APPL_PINMUX); + data &= ~APPL_PINMUX_PEX_RST; + appl_writel(pcie, data, APPL_PINMUX); + + /* + * Some cards do not go to detect state even after de-asserting + * PERST#. So, de-assert LTSSM to bring link to detect state. + */ + data = readl(pcie->appl_base + APPL_CTRL); + data &= ~APPL_CTRL_LTSSM_EN; + writel(data, pcie->appl_base + APPL_CTRL); + + err = readl_poll_timeout_atomic(pcie->appl_base + APPL_DEBUG, + data, + ((data & + APPL_DEBUG_LTSSM_STATE_MASK) >> + APPL_DEBUG_LTSSM_STATE_SHIFT) == + LTSSM_STATE_PRE_DETECT, + 1, LTSSM_TIMEOUT); + if (err) + dev_info(pcie->dev, "Link didn't go to detect state\n"); + } + /* + * DBI registers may not be accessible after this as PLL-E would be + * down depending on how CLKREQ is pulled by end point + */ + data = appl_readl(pcie, APPL_PINMUX); + data |= (APPL_PINMUX_CLKREQ_OVERRIDE_EN | APPL_PINMUX_CLKREQ_OVERRIDE); + /* Cut REFCLK to slot */ + data |= APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE_EN; + data &= ~APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE; + appl_writel(pcie, data, APPL_PINMUX); +} + +static void tegra_pcie_deinit_controller(struct tegra_pcie_dw *pcie) +{ + tegra_pcie_downstream_dev_to_D0(pcie); + dw_pcie_host_deinit(&pcie->pci.pp); + tegra_pcie_dw_pme_turnoff(pcie); + tegra_pcie_unconfig_controller(pcie); +} + +static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie) +{ + struct device *dev = pcie->dev; + char *name; + int ret; + + pm_runtime_enable(dev); + + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "Failed to get runtime sync for PCIe dev: %d\n", + ret); + goto fail_pm_get_sync; + } + + ret = pinctrl_pm_select_default_state(dev); + if (ret < 0) { + dev_err(dev, "Failed to configure sideband pins: %d\n", ret); + goto fail_pm_get_sync; + } + + ret = tegra_pcie_init_controller(pcie); + if (ret < 0) { + dev_err(dev, "Failed to initialize controller: %d\n", ret); + goto fail_pm_get_sync; + } + + pcie->link_state = tegra_pcie_dw_link_up(&pcie->pci); + if (!pcie->link_state) { + ret = -ENOMEDIUM; + goto fail_host_init; + } + + name = devm_kasprintf(dev, GFP_KERNEL, "%pOFP", dev->of_node); + if (!name) { + ret = -ENOMEM; + goto fail_host_init; + } + + pcie->debugfs = debugfs_create_dir(name, NULL); + init_debugfs(pcie); + + return ret; + +fail_host_init: + tegra_pcie_deinit_controller(pcie); +fail_pm_get_sync: + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); + return ret; +} + +static void pex_ep_event_pex_rst_assert(struct tegra_pcie_dw *pcie) +{ + u32 val; + int ret; + + if (pcie->ep_state == EP_STATE_DISABLED) + return; + + /* Disable LTSSM */ + val = appl_readl(pcie, APPL_CTRL); + val &= ~APPL_CTRL_LTSSM_EN; + appl_writel(pcie, val, APPL_CTRL); + + ret = readl_poll_timeout(pcie->appl_base + APPL_DEBUG, val, + ((val & APPL_DEBUG_LTSSM_STATE_MASK) >> + APPL_DEBUG_LTSSM_STATE_SHIFT) == + LTSSM_STATE_PRE_DETECT, + 1, LTSSM_TIMEOUT); + if (ret) + dev_err(pcie->dev, "Failed to go Detect state: %d\n", ret); + + reset_control_assert(pcie->core_rst); + + tegra_pcie_disable_phy(pcie); + + reset_control_assert(pcie->core_apb_rst); + + clk_disable_unprepare(pcie->core_clk); + + pm_runtime_put_sync(pcie->dev); + + if (pcie->enable_ext_refclk) { + ret = tegra_pcie_bpmp_set_pll_state(pcie, false); + if (ret) + dev_err(pcie->dev, "Failed to turn off UPHY: %d\n", + ret); + } + + ret = tegra_pcie_bpmp_set_pll_state(pcie, false); + if (ret) + dev_err(pcie->dev, "Failed to turn off UPHY: %d\n", ret); + + pcie->ep_state = EP_STATE_DISABLED; + dev_dbg(pcie->dev, "Uninitialization of endpoint is completed\n"); +} + +static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_ep *ep = &pci->ep; + struct device *dev = pcie->dev; + u32 val; + int ret; + u16 val_16; + + if (pcie->ep_state == EP_STATE_ENABLED) + return; + + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) { + dev_err(dev, "Failed to get runtime sync for PCIe dev: %d\n", + ret); + return; + } + + ret = tegra_pcie_bpmp_set_ctrl_state(pcie, true); + if (ret) { + dev_err(pcie->dev, "Failed to enable controller %u: %d\n", + pcie->cid, ret); + goto fail_set_ctrl_state; + } + + if (pcie->enable_ext_refclk) { + ret = tegra_pcie_bpmp_set_pll_state(pcie, true); + if (ret) { + dev_err(dev, "Failed to init UPHY for PCIe EP: %d\n", + ret); + goto fail_pll_init; + } + } + + ret = clk_prepare_enable(pcie->core_clk); + if (ret) { + dev_err(dev, "Failed to enable core clock: %d\n", ret); + goto fail_core_clk_enable; + } + + ret = reset_control_deassert(pcie->core_apb_rst); + if (ret) { + dev_err(dev, "Failed to deassert core APB reset: %d\n", ret); + goto fail_core_apb_rst; + } + + ret = tegra_pcie_enable_phy(pcie); + if (ret) { + dev_err(dev, "Failed to enable PHY: %d\n", ret); + goto fail_phy; + } + + /* Clear any stale interrupt statuses */ + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_0_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_1); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_2); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_3); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_6); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_7); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_8_0); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_9); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_10); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_11); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_13); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_14); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_15); + appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_17); + + /* configure this core for EP mode operation */ + val = appl_readl(pcie, APPL_DM_TYPE); + val &= ~APPL_DM_TYPE_MASK; + val |= APPL_DM_TYPE_EP; + appl_writel(pcie, val, APPL_DM_TYPE); + + appl_writel(pcie, 0x0, APPL_CFG_SLCG_OVERRIDE); + + val = appl_readl(pcie, APPL_CTRL); + val |= APPL_CTRL_SYS_PRE_DET_STATE; + val |= APPL_CTRL_HW_HOT_RST_EN; + appl_writel(pcie, val, APPL_CTRL); + + val = appl_readl(pcie, APPL_CFG_MISC); + val |= APPL_CFG_MISC_SLV_EP_MODE; + val |= (APPL_CFG_MISC_ARCACHE_VAL << APPL_CFG_MISC_ARCACHE_SHIFT); + appl_writel(pcie, val, APPL_CFG_MISC); + + val = appl_readl(pcie, APPL_PINMUX); + val |= APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE_EN; + val |= APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE; + appl_writel(pcie, val, APPL_PINMUX); + + appl_writel(pcie, pcie->dbi_res->start & APPL_CFG_BASE_ADDR_MASK, + APPL_CFG_BASE_ADDR); + + appl_writel(pcie, pcie->atu_dma_res->start & + APPL_CFG_IATU_DMA_BASE_ADDR_MASK, + APPL_CFG_IATU_DMA_BASE_ADDR); + + val = appl_readl(pcie, APPL_INTR_EN_L0_0); + val |= APPL_INTR_EN_L0_0_SYS_INTR_EN; + val |= APPL_INTR_EN_L0_0_LINK_STATE_INT_EN; + val |= APPL_INTR_EN_L0_0_PCI_CMD_EN_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L0_0); + + val = appl_readl(pcie, APPL_INTR_EN_L1_0_0); + val |= APPL_INTR_EN_L1_0_0_HOT_RESET_DONE_INT_EN; + val |= APPL_INTR_EN_L1_0_0_RDLH_LINK_UP_INT_EN; + appl_writel(pcie, val, APPL_INTR_EN_L1_0_0); + + reset_control_deassert(pcie->core_rst); + + if (pcie->update_fc_fixup) { + val = dw_pcie_readl_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF); + val |= 0x1 << CFG_TIMER_CTRL_ACK_NAK_SHIFT; + dw_pcie_writel_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF, val); + } + + config_gen3_gen4_eq_presets(pcie); + + init_host_aspm(pcie); + + /* Disable ASPM-L1SS advertisement if there is no CLKREQ routing */ + if (!pcie->supports_clkreq) { + disable_aspm_l11(pcie); + disable_aspm_l12(pcie); + } + + if (!pcie->of_data->has_l1ss_exit_fix) { + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL; + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); + } + + pcie->pcie_cap_base = dw_pcie_find_capability(&pcie->pci, + PCI_CAP_ID_EXP); + + /* Clear Slot Clock Configuration bit if SRNS configuration */ + if (pcie->enable_srns) { + val_16 = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + + PCI_EXP_LNKSTA); + val_16 &= ~PCI_EXP_LNKSTA_SLC; + dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA, + val_16); + } + + clk_set_rate(pcie->core_clk, GEN4_CORE_CLK_FREQ); + + val = (ep->msi_mem_phys & MSIX_ADDR_MATCH_LOW_OFF_MASK); + val |= MSIX_ADDR_MATCH_LOW_OFF_EN; + dw_pcie_writel_dbi(pci, MSIX_ADDR_MATCH_LOW_OFF, val); + val = (upper_32_bits(ep->msi_mem_phys) & MSIX_ADDR_MATCH_HIGH_OFF_MASK); + dw_pcie_writel_dbi(pci, MSIX_ADDR_MATCH_HIGH_OFF, val); + + ret = dw_pcie_ep_init_complete(ep); + if (ret) { + dev_err(dev, "Failed to complete initialization: %d\n", ret); + goto fail_init_complete; + } + + dw_pcie_ep_init_notify(ep); + + /* Program the private control to allow sending LTR upstream */ + if (pcie->of_data->has_ltr_req_fix) { + val = appl_readl(pcie, APPL_LTR_MSG_2); + val |= APPL_LTR_MSG_2_LTR_MSG_REQ_STATE; + appl_writel(pcie, val, APPL_LTR_MSG_2); + } + + /* Enable LTSSM */ + val = appl_readl(pcie, APPL_CTRL); + val |= APPL_CTRL_LTSSM_EN; + appl_writel(pcie, val, APPL_CTRL); + + pcie->ep_state = EP_STATE_ENABLED; + dev_dbg(dev, "Initialization of endpoint is completed\n"); + + return; + +fail_init_complete: + reset_control_assert(pcie->core_rst); + tegra_pcie_disable_phy(pcie); +fail_phy: + reset_control_assert(pcie->core_apb_rst); +fail_core_apb_rst: + clk_disable_unprepare(pcie->core_clk); +fail_core_clk_enable: + tegra_pcie_bpmp_set_pll_state(pcie, false); +fail_pll_init: + tegra_pcie_bpmp_set_ctrl_state(pcie, false); +fail_set_ctrl_state: + pm_runtime_put_sync(dev); +} + +static irqreturn_t tegra_pcie_ep_pex_rst_irq(int irq, void *arg) +{ + struct tegra_pcie_dw *pcie = arg; + + if (gpiod_get_value(pcie->pex_rst_gpiod)) + pex_ep_event_pex_rst_assert(pcie); + else + pex_ep_event_pex_rst_deassert(pcie); + + return IRQ_HANDLED; +} + +static int tegra_pcie_ep_raise_legacy_irq(struct tegra_pcie_dw *pcie, u16 irq) +{ + /* Tegra194 supports only INTA */ + if (irq > 1) + return -EINVAL; + + appl_writel(pcie, 1, APPL_LEGACY_INTX); + usleep_range(1000, 2000); + appl_writel(pcie, 0, APPL_LEGACY_INTX); + return 0; +} + +static int tegra_pcie_ep_raise_msi_irq(struct tegra_pcie_dw *pcie, u16 irq) +{ + if (unlikely(irq > 31)) + return -EINVAL; + + appl_writel(pcie, BIT(irq), APPL_MSI_CTRL_1); + + return 0; +} + +static int tegra_pcie_ep_raise_msix_irq(struct tegra_pcie_dw *pcie, u16 irq) +{ + struct dw_pcie_ep *ep = &pcie->pci.ep; + + writel(irq, ep->msi_mem); + + return 0; +} + +static int tegra_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + enum pci_epc_irq_type type, + u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct tegra_pcie_dw *pcie = to_tegra_pcie(pci); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + return tegra_pcie_ep_raise_legacy_irq(pcie, interrupt_num); + + case PCI_EPC_IRQ_MSI: + return tegra_pcie_ep_raise_msi_irq(pcie, interrupt_num); + + case PCI_EPC_IRQ_MSIX: + return tegra_pcie_ep_raise_msix_irq(pcie, interrupt_num); + + default: + dev_err(pci->dev, "Unknown IRQ type\n"); + return -EPERM; + } + + return 0; +} + +static const struct pci_epc_features tegra_pcie_epc_features = { + .linkup_notifier = true, + .core_init_notifier = true, + .msi_capable = false, + .msix_capable = false, + .reserved_bar = 1 << BAR_2 | 1 << BAR_3 | 1 << BAR_4 | 1 << BAR_5, + .bar_fixed_64bit = 1 << BAR_0, + .bar_fixed_size[0] = SZ_1M, +}; + +static const struct pci_epc_features* +tegra_pcie_ep_get_features(struct dw_pcie_ep *ep) +{ + return &tegra_pcie_epc_features; +} + +static const struct dw_pcie_ep_ops pcie_ep_ops = { + .raise_irq = tegra_pcie_ep_raise_irq, + .get_features = tegra_pcie_ep_get_features, +}; + +static int tegra_pcie_config_ep(struct tegra_pcie_dw *pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &pcie->pci; + struct device *dev = pcie->dev; + struct dw_pcie_ep *ep; + char *name; + int ret; + + ep = &pci->ep; + ep->ops = &pcie_ep_ops; + + ep->page_size = SZ_64K; + + ret = gpiod_set_debounce(pcie->pex_rst_gpiod, PERST_DEBOUNCE_TIME); + if (ret < 0) { + dev_err(dev, "Failed to set PERST GPIO debounce time: %d\n", + ret); + return ret; + } + + ret = gpiod_to_irq(pcie->pex_rst_gpiod); + if (ret < 0) { + dev_err(dev, "Failed to get IRQ for PERST GPIO: %d\n", ret); + return ret; + } + pcie->pex_rst_irq = (unsigned int)ret; + + name = devm_kasprintf(dev, GFP_KERNEL, "tegra_pcie_%u_pex_rst_irq", + pcie->cid); + if (!name) { + dev_err(dev, "Failed to create PERST IRQ string\n"); + return -ENOMEM; + } + + irq_set_status_flags(pcie->pex_rst_irq, IRQ_NOAUTOEN); + + pcie->ep_state = EP_STATE_DISABLED; + + ret = devm_request_threaded_irq(dev, pcie->pex_rst_irq, NULL, + tegra_pcie_ep_pex_rst_irq, + IRQF_TRIGGER_RISING | + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + name, (void *)pcie); + if (ret < 0) { + dev_err(dev, "Failed to request IRQ for PERST: %d\n", ret); + return ret; + } + + pm_runtime_enable(dev); + + ret = dw_pcie_ep_init(ep); + if (ret) { + dev_err(dev, "Failed to initialize DWC Endpoint subsystem: %d\n", + ret); + pm_runtime_disable(dev); + return ret; + } + + return 0; +} + +static int tegra_pcie_dw_probe(struct platform_device *pdev) +{ + const struct tegra_pcie_dw_of_data *data; + struct device *dev = &pdev->dev; + struct resource *atu_dma_res; + struct tegra_pcie_dw *pcie; + struct dw_pcie_rp *pp; + struct dw_pcie *pci; + struct phy **phys; + char *name; + int ret; + u32 i; + + data = of_device_get_match_data(dev); + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = &pcie->pci; + pci->dev = &pdev->dev; + pci->ops = &tegra_dw_pcie_ops; + pcie->dev = &pdev->dev; + pcie->of_data = (struct tegra_pcie_dw_of_data *)data; + pci->n_fts[0] = pcie->of_data->n_fts[0]; + pci->n_fts[1] = pcie->of_data->n_fts[1]; + pp = &pci->pp; + pp->num_vectors = MAX_MSI_IRQS; + + ret = tegra_pcie_dw_parse_dt(pcie); + if (ret < 0) { + const char *level = KERN_ERR; + + if (ret == -EPROBE_DEFER) + level = KERN_DEBUG; + + dev_printk(level, dev, + dev_fmt("Failed to parse device tree: %d\n"), + ret); + return ret; + } + + ret = tegra_pcie_get_slot_regulators(pcie); + if (ret < 0) { + const char *level = KERN_ERR; + + if (ret == -EPROBE_DEFER) + level = KERN_DEBUG; + + dev_printk(level, dev, + dev_fmt("Failed to get slot regulators: %d\n"), + ret); + return ret; + } + + if (pcie->pex_refclk_sel_gpiod) + gpiod_set_value(pcie->pex_refclk_sel_gpiod, 1); + + pcie->pex_ctl_supply = devm_regulator_get(dev, "vddio-pex-ctl"); + if (IS_ERR(pcie->pex_ctl_supply)) { + ret = PTR_ERR(pcie->pex_ctl_supply); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get regulator: %ld\n", + PTR_ERR(pcie->pex_ctl_supply)); + return ret; + } + + pcie->core_clk = devm_clk_get(dev, "core"); + if (IS_ERR(pcie->core_clk)) { + dev_err(dev, "Failed to get core clock: %ld\n", + PTR_ERR(pcie->core_clk)); + return PTR_ERR(pcie->core_clk); + } + + pcie->appl_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "appl"); + if (!pcie->appl_res) { + dev_err(dev, "Failed to find \"appl\" region\n"); + return -ENODEV; + } + + pcie->appl_base = devm_ioremap_resource(dev, pcie->appl_res); + if (IS_ERR(pcie->appl_base)) + return PTR_ERR(pcie->appl_base); + + pcie->core_apb_rst = devm_reset_control_get(dev, "apb"); + if (IS_ERR(pcie->core_apb_rst)) { + dev_err(dev, "Failed to get APB reset: %ld\n", + PTR_ERR(pcie->core_apb_rst)); + return PTR_ERR(pcie->core_apb_rst); + } + + phys = devm_kcalloc(dev, pcie->phy_count, sizeof(*phys), GFP_KERNEL); + if (!phys) + return -ENOMEM; + + for (i = 0; i < pcie->phy_count; i++) { + name = kasprintf(GFP_KERNEL, "p2u-%u", i); + if (!name) { + dev_err(dev, "Failed to create P2U string\n"); + return -ENOMEM; + } + phys[i] = devm_phy_get(dev, name); + kfree(name); + if (IS_ERR(phys[i])) { + ret = PTR_ERR(phys[i]); + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get PHY: %d\n", ret); + return ret; + } + } + + pcie->phys = phys; + + atu_dma_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "atu_dma"); + if (!atu_dma_res) { + dev_err(dev, "Failed to find \"atu_dma\" region\n"); + return -ENODEV; + } + pcie->atu_dma_res = atu_dma_res; + + pci->atu_size = resource_size(atu_dma_res); + pci->atu_base = devm_ioremap_resource(dev, atu_dma_res); + if (IS_ERR(pci->atu_base)) + return PTR_ERR(pci->atu_base); + + pcie->core_rst = devm_reset_control_get(dev, "core"); + if (IS_ERR(pcie->core_rst)) { + dev_err(dev, "Failed to get core reset: %ld\n", + PTR_ERR(pcie->core_rst)); + return PTR_ERR(pcie->core_rst); + } + + pp->irq = platform_get_irq_byname(pdev, "intr"); + if (pp->irq < 0) + return pp->irq; + + pcie->bpmp = tegra_bpmp_get(dev); + if (IS_ERR(pcie->bpmp)) + return PTR_ERR(pcie->bpmp); + + platform_set_drvdata(pdev, pcie); + + switch (pcie->of_data->mode) { + case DW_PCIE_RC_TYPE: + ret = devm_request_irq(dev, pp->irq, tegra_pcie_rp_irq_handler, + IRQF_SHARED, "tegra-pcie-intr", pcie); + if (ret) { + dev_err(dev, "Failed to request IRQ %d: %d\n", pp->irq, + ret); + goto fail; + } + + ret = tegra_pcie_config_rp(pcie); + if (ret && ret != -ENOMEDIUM) + goto fail; + else + return 0; + break; + + case DW_PCIE_EP_TYPE: + ret = devm_request_threaded_irq(dev, pp->irq, + tegra_pcie_ep_hard_irq, + tegra_pcie_ep_irq_thread, + IRQF_SHARED | IRQF_ONESHOT, + "tegra-pcie-ep-intr", pcie); + if (ret) { + dev_err(dev, "Failed to request IRQ %d: %d\n", pp->irq, + ret); + goto fail; + } + + ret = tegra_pcie_config_ep(pcie, pdev); + if (ret < 0) + goto fail; + break; + + default: + dev_err(dev, "Invalid PCIe device type %d\n", + pcie->of_data->mode); + } + +fail: + tegra_bpmp_put(pcie->bpmp); + return ret; +} + +static int tegra_pcie_dw_remove(struct platform_device *pdev) +{ + struct tegra_pcie_dw *pcie = platform_get_drvdata(pdev); + + if (pcie->of_data->mode == DW_PCIE_RC_TYPE) { + if (!pcie->link_state) + return 0; + + debugfs_remove_recursive(pcie->debugfs); + tegra_pcie_deinit_controller(pcie); + pm_runtime_put_sync(pcie->dev); + } else { + disable_irq(pcie->pex_rst_irq); + pex_ep_event_pex_rst_assert(pcie); + } + + pm_runtime_disable(pcie->dev); + tegra_bpmp_put(pcie->bpmp); + if (pcie->pex_refclk_sel_gpiod) + gpiod_set_value(pcie->pex_refclk_sel_gpiod, 0); + + return 0; +} + +static int tegra_pcie_dw_suspend_late(struct device *dev) +{ + struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); + u32 val; + + if (pcie->of_data->mode == DW_PCIE_EP_TYPE) { + dev_err(dev, "Failed to Suspend as Tegra PCIe is in EP mode\n"); + return -EPERM; + } + + if (!pcie->link_state) + return 0; + + /* Enable HW_HOT_RST mode */ + if (!pcie->of_data->has_sbr_reset_fix) { + val = appl_readl(pcie, APPL_CTRL); + val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK << + APPL_CTRL_HW_HOT_RST_MODE_SHIFT); + val |= APPL_CTRL_HW_HOT_RST_EN; + appl_writel(pcie, val, APPL_CTRL); + } + + return 0; +} + +static int tegra_pcie_dw_suspend_noirq(struct device *dev) +{ + struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); + + if (!pcie->link_state) + return 0; + + tegra_pcie_downstream_dev_to_D0(pcie); + tegra_pcie_dw_pme_turnoff(pcie); + tegra_pcie_unconfig_controller(pcie); + + return 0; +} + +static int tegra_pcie_dw_resume_noirq(struct device *dev) +{ + struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); + int ret; + + if (!pcie->link_state) + return 0; + + ret = tegra_pcie_config_controller(pcie, true); + if (ret < 0) + return ret; + + ret = tegra_pcie_dw_host_init(&pcie->pci.pp); + if (ret < 0) { + dev_err(dev, "Failed to init host: %d\n", ret); + goto fail_host_init; + } + + dw_pcie_setup_rc(&pcie->pci.pp); + + ret = tegra_pcie_dw_start_link(&pcie->pci); + if (ret < 0) + goto fail_host_init; + + return 0; + +fail_host_init: + tegra_pcie_unconfig_controller(pcie); + return ret; +} + +static int tegra_pcie_dw_resume_early(struct device *dev) +{ + struct tegra_pcie_dw *pcie = dev_get_drvdata(dev); + u32 val; + + if (pcie->of_data->mode == DW_PCIE_EP_TYPE) { + dev_err(dev, "Suspend is not supported in EP mode"); + return -ENOTSUPP; + } + + if (!pcie->link_state) + return 0; + + /* Disable HW_HOT_RST mode */ + if (!pcie->of_data->has_sbr_reset_fix) { + val = appl_readl(pcie, APPL_CTRL); + val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK << + APPL_CTRL_HW_HOT_RST_MODE_SHIFT); + val |= APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST << + APPL_CTRL_HW_HOT_RST_MODE_SHIFT; + val &= ~APPL_CTRL_HW_HOT_RST_EN; + appl_writel(pcie, val, APPL_CTRL); + } + + return 0; +} + +static void tegra_pcie_dw_shutdown(struct platform_device *pdev) +{ + struct tegra_pcie_dw *pcie = platform_get_drvdata(pdev); + + if (pcie->of_data->mode == DW_PCIE_RC_TYPE) { + if (!pcie->link_state) + return; + + debugfs_remove_recursive(pcie->debugfs); + tegra_pcie_downstream_dev_to_D0(pcie); + + disable_irq(pcie->pci.pp.irq); + if (IS_ENABLED(CONFIG_PCI_MSI)) + disable_irq(pcie->pci.pp.msi_irq[0]); + + tegra_pcie_dw_pme_turnoff(pcie); + tegra_pcie_unconfig_controller(pcie); + pm_runtime_put_sync(pcie->dev); + } else { + disable_irq(pcie->pex_rst_irq); + pex_ep_event_pex_rst_assert(pcie); + } +} + +static const struct tegra_pcie_dw_of_data tegra194_pcie_dw_rc_of_data = { + .version = TEGRA194_DWC_IP_VER, + .mode = DW_PCIE_RC_TYPE, + .cdm_chk_int_en_bit = BIT(19), + /* Gen4 - 5, 6, 8 and 9 presets enabled */ + .gen4_preset_vec = 0x360, + .n_fts = { 52, 52 }, +}; + +static const struct tegra_pcie_dw_of_data tegra194_pcie_dw_ep_of_data = { + .version = TEGRA194_DWC_IP_VER, + .mode = DW_PCIE_EP_TYPE, + .cdm_chk_int_en_bit = BIT(19), + /* Gen4 - 5, 6, 8 and 9 presets enabled */ + .gen4_preset_vec = 0x360, + .n_fts = { 52, 52 }, +}; + +static const struct tegra_pcie_dw_of_data tegra234_pcie_dw_rc_of_data = { + .version = TEGRA234_DWC_IP_VER, + .mode = DW_PCIE_RC_TYPE, + .has_msix_doorbell_access_fix = true, + .has_sbr_reset_fix = true, + .has_l1ss_exit_fix = true, + .cdm_chk_int_en_bit = BIT(18), + /* Gen4 - 6, 8 and 9 presets enabled */ + .gen4_preset_vec = 0x340, + .n_fts = { 52, 80 }, +}; + +static const struct tegra_pcie_dw_of_data tegra234_pcie_dw_ep_of_data = { + .version = TEGRA234_DWC_IP_VER, + .mode = DW_PCIE_EP_TYPE, + .has_l1ss_exit_fix = true, + .has_ltr_req_fix = true, + .cdm_chk_int_en_bit = BIT(18), + /* Gen4 - 6, 8 and 9 presets enabled */ + .gen4_preset_vec = 0x340, + .n_fts = { 52, 80 }, +}; + +static const struct of_device_id tegra_pcie_dw_of_match[] = { + { + .compatible = "nvidia,tegra194-pcie", + .data = &tegra194_pcie_dw_rc_of_data, + }, + { + .compatible = "nvidia,tegra194-pcie-ep", + .data = &tegra194_pcie_dw_ep_of_data, + }, + { + .compatible = "nvidia,tegra234-pcie", + .data = &tegra234_pcie_dw_rc_of_data, + }, + { + .compatible = "nvidia,tegra234-pcie-ep", + .data = &tegra234_pcie_dw_ep_of_data, + }, + {} +}; + +static const struct dev_pm_ops tegra_pcie_dw_pm_ops = { + .suspend_late = tegra_pcie_dw_suspend_late, + .suspend_noirq = tegra_pcie_dw_suspend_noirq, + .resume_noirq = tegra_pcie_dw_resume_noirq, + .resume_early = tegra_pcie_dw_resume_early, +}; + +static struct platform_driver tegra_pcie_dw_driver = { + .probe = tegra_pcie_dw_probe, + .remove = tegra_pcie_dw_remove, + .shutdown = tegra_pcie_dw_shutdown, + .driver = { + .name = "tegra194-pcie", + .pm = &tegra_pcie_dw_pm_ops, + .of_match_table = tegra_pcie_dw_of_match, + }, +}; +module_platform_driver(tegra_pcie_dw_driver); + +MODULE_DEVICE_TABLE(of, tegra_pcie_dw_of_match); + +MODULE_AUTHOR("Vidya Sagar <vidyas@nvidia.com>"); +MODULE_DESCRIPTION("NVIDIA PCIe host controller driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/dwc/pcie-uniphier-ep.c b/drivers/pci/controller/dwc/pcie-uniphier-ep.c new file mode 100644 index 000000000..4d0a587c0 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-uniphier-ep.c @@ -0,0 +1,453 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe endpoint controller driver for UniPhier SoCs + * Copyright 2018 Socionext Inc. + * Author: Kunihiko Hayashi <hayashi.kunihiko@socionext.com> + */ + +#include <linux/bitops.h> +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/iopoll.h> +#include <linux/of_device.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/reset.h> + +#include "pcie-designware.h" + +/* Link Glue registers */ +#define PCL_RSTCTRL0 0x0010 +#define PCL_RSTCTRL_AXI_REG BIT(3) +#define PCL_RSTCTRL_AXI_SLAVE BIT(2) +#define PCL_RSTCTRL_AXI_MASTER BIT(1) +#define PCL_RSTCTRL_PIPE3 BIT(0) + +#define PCL_RSTCTRL1 0x0020 +#define PCL_RSTCTRL_PERST BIT(0) + +#define PCL_RSTCTRL2 0x0024 +#define PCL_RSTCTRL_PHY_RESET BIT(0) + +#define PCL_PINCTRL0 0x002c +#define PCL_PERST_PLDN_REGEN BIT(12) +#define PCL_PERST_NOE_REGEN BIT(11) +#define PCL_PERST_OUT_REGEN BIT(8) +#define PCL_PERST_PLDN_REGVAL BIT(4) +#define PCL_PERST_NOE_REGVAL BIT(3) +#define PCL_PERST_OUT_REGVAL BIT(0) + +#define PCL_PIPEMON 0x0044 +#define PCL_PCLK_ALIVE BIT(15) + +#define PCL_MODE 0x8000 +#define PCL_MODE_REGEN BIT(8) +#define PCL_MODE_REGVAL BIT(0) + +#define PCL_APP_CLK_CTRL 0x8004 +#define PCL_APP_CLK_REQ BIT(0) + +#define PCL_APP_READY_CTRL 0x8008 +#define PCL_APP_LTSSM_ENABLE BIT(0) + +#define PCL_APP_MSI0 0x8040 +#define PCL_APP_VEN_MSI_TC_MASK GENMASK(10, 8) +#define PCL_APP_VEN_MSI_VECTOR_MASK GENMASK(4, 0) + +#define PCL_APP_MSI1 0x8044 +#define PCL_APP_MSI_REQ BIT(0) + +#define PCL_APP_INTX 0x8074 +#define PCL_APP_INTX_SYS_INT BIT(0) + +#define PCL_APP_PM0 0x8078 +#define PCL_SYS_AUX_PWR_DET BIT(8) + +/* assertion time of INTx in usec */ +#define PCL_INTX_WIDTH_USEC 30 + +struct uniphier_pcie_ep_priv { + void __iomem *base; + struct dw_pcie pci; + struct clk *clk, *clk_gio; + struct reset_control *rst, *rst_gio; + struct phy *phy; + const struct uniphier_pcie_ep_soc_data *data; +}; + +struct uniphier_pcie_ep_soc_data { + bool has_gio; + void (*init)(struct uniphier_pcie_ep_priv *priv); + int (*wait)(struct uniphier_pcie_ep_priv *priv); + const struct pci_epc_features features; +}; + +#define to_uniphier_pcie(x) dev_get_drvdata((x)->dev) + +static void uniphier_pcie_ltssm_enable(struct uniphier_pcie_ep_priv *priv, + bool enable) +{ + u32 val; + + val = readl(priv->base + PCL_APP_READY_CTRL); + if (enable) + val |= PCL_APP_LTSSM_ENABLE; + else + val &= ~PCL_APP_LTSSM_ENABLE; + writel(val, priv->base + PCL_APP_READY_CTRL); +} + +static void uniphier_pcie_phy_reset(struct uniphier_pcie_ep_priv *priv, + bool assert) +{ + u32 val; + + val = readl(priv->base + PCL_RSTCTRL2); + if (assert) + val |= PCL_RSTCTRL_PHY_RESET; + else + val &= ~PCL_RSTCTRL_PHY_RESET; + writel(val, priv->base + PCL_RSTCTRL2); +} + +static void uniphier_pcie_pro5_init_ep(struct uniphier_pcie_ep_priv *priv) +{ + u32 val; + + /* set EP mode */ + val = readl(priv->base + PCL_MODE); + val |= PCL_MODE_REGEN | PCL_MODE_REGVAL; + writel(val, priv->base + PCL_MODE); + + /* clock request */ + val = readl(priv->base + PCL_APP_CLK_CTRL); + val &= ~PCL_APP_CLK_REQ; + writel(val, priv->base + PCL_APP_CLK_CTRL); + + /* deassert PIPE3 and AXI reset */ + val = readl(priv->base + PCL_RSTCTRL0); + val |= PCL_RSTCTRL_AXI_REG | PCL_RSTCTRL_AXI_SLAVE + | PCL_RSTCTRL_AXI_MASTER | PCL_RSTCTRL_PIPE3; + writel(val, priv->base + PCL_RSTCTRL0); + + uniphier_pcie_ltssm_enable(priv, false); + + msleep(100); +} + +static void uniphier_pcie_nx1_init_ep(struct uniphier_pcie_ep_priv *priv) +{ + u32 val; + + /* set EP mode */ + val = readl(priv->base + PCL_MODE); + val |= PCL_MODE_REGEN | PCL_MODE_REGVAL; + writel(val, priv->base + PCL_MODE); + + /* use auxiliary power detection */ + val = readl(priv->base + PCL_APP_PM0); + val |= PCL_SYS_AUX_PWR_DET; + writel(val, priv->base + PCL_APP_PM0); + + /* assert PERST# */ + val = readl(priv->base + PCL_PINCTRL0); + val &= ~(PCL_PERST_NOE_REGVAL | PCL_PERST_OUT_REGVAL + | PCL_PERST_PLDN_REGVAL); + val |= PCL_PERST_NOE_REGEN | PCL_PERST_OUT_REGEN + | PCL_PERST_PLDN_REGEN; + writel(val, priv->base + PCL_PINCTRL0); + + uniphier_pcie_ltssm_enable(priv, false); + + usleep_range(100000, 200000); + + /* deassert PERST# */ + val = readl(priv->base + PCL_PINCTRL0); + val |= PCL_PERST_OUT_REGVAL | PCL_PERST_OUT_REGEN; + writel(val, priv->base + PCL_PINCTRL0); +} + +static int uniphier_pcie_nx1_wait_ep(struct uniphier_pcie_ep_priv *priv) +{ + u32 status; + int ret; + + /* wait PIPE clock */ + ret = readl_poll_timeout(priv->base + PCL_PIPEMON, status, + status & PCL_PCLK_ALIVE, 100000, 1000000); + if (ret) { + dev_err(priv->pci.dev, + "Failed to initialize controller in EP mode\n"); + return ret; + } + + return 0; +} + +static int uniphier_pcie_start_link(struct dw_pcie *pci) +{ + struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci); + + uniphier_pcie_ltssm_enable(priv, true); + + return 0; +} + +static void uniphier_pcie_stop_link(struct dw_pcie *pci) +{ + struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci); + + uniphier_pcie_ltssm_enable(priv, false); +} + +static void uniphier_pcie_ep_init(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar; + + for (bar = BAR_0; bar <= BAR_5; bar++) + dw_pcie_ep_reset_bar(pci, bar); +} + +static int uniphier_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci); + u32 val; + + /* + * This makes pulse signal to send INTx to the RC, so this should + * be cleared as soon as possible. This sequence is covered with + * mutex in pci_epc_raise_irq(). + */ + /* assert INTx */ + val = readl(priv->base + PCL_APP_INTX); + val |= PCL_APP_INTX_SYS_INT; + writel(val, priv->base + PCL_APP_INTX); + + udelay(PCL_INTX_WIDTH_USEC); + + /* deassert INTx */ + val &= ~PCL_APP_INTX_SYS_INT; + writel(val, priv->base + PCL_APP_INTX); + + return 0; +} + +static int uniphier_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, + u8 func_no, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci); + u32 val; + + val = FIELD_PREP(PCL_APP_VEN_MSI_TC_MASK, func_no) + | FIELD_PREP(PCL_APP_VEN_MSI_VECTOR_MASK, interrupt_num - 1); + writel(val, priv->base + PCL_APP_MSI0); + + val = readl(priv->base + PCL_APP_MSI1); + val |= PCL_APP_MSI_REQ; + writel(val, priv->base + PCL_APP_MSI1); + + return 0; +} + +static int uniphier_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + enum pci_epc_irq_type type, + u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + return uniphier_pcie_ep_raise_legacy_irq(ep); + case PCI_EPC_IRQ_MSI: + return uniphier_pcie_ep_raise_msi_irq(ep, func_no, + interrupt_num); + default: + dev_err(pci->dev, "UNKNOWN IRQ type (%d)\n", type); + } + + return 0; +} + +static const struct pci_epc_features* +uniphier_pcie_get_features(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci); + + return &priv->data->features; +} + +static const struct dw_pcie_ep_ops uniphier_pcie_ep_ops = { + .ep_init = uniphier_pcie_ep_init, + .raise_irq = uniphier_pcie_ep_raise_irq, + .get_features = uniphier_pcie_get_features, +}; + +static int uniphier_pcie_ep_enable(struct uniphier_pcie_ep_priv *priv) +{ + int ret; + + ret = clk_prepare_enable(priv->clk); + if (ret) + return ret; + + ret = clk_prepare_enable(priv->clk_gio); + if (ret) + goto out_clk_disable; + + ret = reset_control_deassert(priv->rst); + if (ret) + goto out_clk_gio_disable; + + ret = reset_control_deassert(priv->rst_gio); + if (ret) + goto out_rst_assert; + + if (priv->data->init) + priv->data->init(priv); + + uniphier_pcie_phy_reset(priv, true); + + ret = phy_init(priv->phy); + if (ret) + goto out_rst_gio_assert; + + uniphier_pcie_phy_reset(priv, false); + + if (priv->data->wait) { + ret = priv->data->wait(priv); + if (ret) + goto out_phy_exit; + } + + return 0; + +out_phy_exit: + phy_exit(priv->phy); +out_rst_gio_assert: + reset_control_assert(priv->rst_gio); +out_rst_assert: + reset_control_assert(priv->rst); +out_clk_gio_disable: + clk_disable_unprepare(priv->clk_gio); +out_clk_disable: + clk_disable_unprepare(priv->clk); + + return ret; +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = uniphier_pcie_start_link, + .stop_link = uniphier_pcie_stop_link, +}; + +static int uniphier_pcie_ep_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct uniphier_pcie_ep_priv *priv; + int ret; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->data = of_device_get_match_data(dev); + if (WARN_ON(!priv->data)) + return -EINVAL; + + priv->pci.dev = dev; + priv->pci.ops = &dw_pcie_ops; + + priv->base = devm_platform_ioremap_resource_byname(pdev, "link"); + if (IS_ERR(priv->base)) + return PTR_ERR(priv->base); + + if (priv->data->has_gio) { + priv->clk_gio = devm_clk_get(dev, "gio"); + if (IS_ERR(priv->clk_gio)) + return PTR_ERR(priv->clk_gio); + + priv->rst_gio = devm_reset_control_get_shared(dev, "gio"); + if (IS_ERR(priv->rst_gio)) + return PTR_ERR(priv->rst_gio); + } + + priv->clk = devm_clk_get(dev, "link"); + if (IS_ERR(priv->clk)) + return PTR_ERR(priv->clk); + + priv->rst = devm_reset_control_get_shared(dev, "link"); + if (IS_ERR(priv->rst)) + return PTR_ERR(priv->rst); + + priv->phy = devm_phy_optional_get(dev, "pcie-phy"); + if (IS_ERR(priv->phy)) { + ret = PTR_ERR(priv->phy); + dev_err(dev, "Failed to get phy (%d)\n", ret); + return ret; + } + + platform_set_drvdata(pdev, priv); + + ret = uniphier_pcie_ep_enable(priv); + if (ret) + return ret; + + priv->pci.ep.ops = &uniphier_pcie_ep_ops; + return dw_pcie_ep_init(&priv->pci.ep); +} + +static const struct uniphier_pcie_ep_soc_data uniphier_pro5_data = { + .has_gio = true, + .init = uniphier_pcie_pro5_init_ep, + .wait = NULL, + .features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = false, + .align = 1 << 16, + .bar_fixed_64bit = BIT(BAR_0) | BIT(BAR_2) | BIT(BAR_4), + .reserved_bar = BIT(BAR_4), + }, +}; + +static const struct uniphier_pcie_ep_soc_data uniphier_nx1_data = { + .has_gio = false, + .init = uniphier_pcie_nx1_init_ep, + .wait = uniphier_pcie_nx1_wait_ep, + .features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = false, + .align = 1 << 12, + .bar_fixed_64bit = BIT(BAR_0) | BIT(BAR_2) | BIT(BAR_4), + }, +}; + +static const struct of_device_id uniphier_pcie_ep_match[] = { + { + .compatible = "socionext,uniphier-pro5-pcie-ep", + .data = &uniphier_pro5_data, + }, + { + .compatible = "socionext,uniphier-nx1-pcie-ep", + .data = &uniphier_nx1_data, + }, + { /* sentinel */ }, +}; + +static struct platform_driver uniphier_pcie_ep_driver = { + .probe = uniphier_pcie_ep_probe, + .driver = { + .name = "uniphier-pcie-ep", + .of_match_table = uniphier_pcie_ep_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver(uniphier_pcie_ep_driver); diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c new file mode 100644 index 000000000..48c3eba81 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-uniphier.c @@ -0,0 +1,409 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for UniPhier SoCs + * Copyright 2018 Socionext Inc. + * Author: Kunihiko Hayashi <hayashi.kunihiko@socionext.com> + */ + +#include <linux/bitops.h> +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/of_irq.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/reset.h> + +#include "pcie-designware.h" + +#define PCL_PINCTRL0 0x002c +#define PCL_PERST_PLDN_REGEN BIT(12) +#define PCL_PERST_NOE_REGEN BIT(11) +#define PCL_PERST_OUT_REGEN BIT(8) +#define PCL_PERST_PLDN_REGVAL BIT(4) +#define PCL_PERST_NOE_REGVAL BIT(3) +#define PCL_PERST_OUT_REGVAL BIT(0) + +#define PCL_PIPEMON 0x0044 +#define PCL_PCLK_ALIVE BIT(15) + +#define PCL_MODE 0x8000 +#define PCL_MODE_REGEN BIT(8) +#define PCL_MODE_REGVAL BIT(0) + +#define PCL_APP_READY_CTRL 0x8008 +#define PCL_APP_LTSSM_ENABLE BIT(0) + +#define PCL_APP_PM0 0x8078 +#define PCL_SYS_AUX_PWR_DET BIT(8) + +#define PCL_RCV_INT 0x8108 +#define PCL_RCV_INT_ALL_ENABLE GENMASK(20, 17) +#define PCL_CFG_BW_MGT_STATUS BIT(4) +#define PCL_CFG_LINK_AUTO_BW_STATUS BIT(3) +#define PCL_CFG_AER_RC_ERR_MSI_STATUS BIT(2) +#define PCL_CFG_PME_MSI_STATUS BIT(1) + +#define PCL_RCV_INTX 0x810c +#define PCL_RCV_INTX_ALL_ENABLE GENMASK(19, 16) +#define PCL_RCV_INTX_ALL_MASK GENMASK(11, 8) +#define PCL_RCV_INTX_MASK_SHIFT 8 +#define PCL_RCV_INTX_ALL_STATUS GENMASK(3, 0) +#define PCL_RCV_INTX_STATUS_SHIFT 0 + +#define PCL_STATUS_LINK 0x8140 +#define PCL_RDLH_LINK_UP BIT(1) +#define PCL_XMLH_LINK_UP BIT(0) + +struct uniphier_pcie { + struct dw_pcie pci; + void __iomem *base; + struct clk *clk; + struct reset_control *rst; + struct phy *phy; + struct irq_domain *legacy_irq_domain; +}; + +#define to_uniphier_pcie(x) dev_get_drvdata((x)->dev) + +static void uniphier_pcie_ltssm_enable(struct uniphier_pcie *pcie, + bool enable) +{ + u32 val; + + val = readl(pcie->base + PCL_APP_READY_CTRL); + if (enable) + val |= PCL_APP_LTSSM_ENABLE; + else + val &= ~PCL_APP_LTSSM_ENABLE; + writel(val, pcie->base + PCL_APP_READY_CTRL); +} + +static void uniphier_pcie_init_rc(struct uniphier_pcie *pcie) +{ + u32 val; + + /* set RC MODE */ + val = readl(pcie->base + PCL_MODE); + val |= PCL_MODE_REGEN; + val &= ~PCL_MODE_REGVAL; + writel(val, pcie->base + PCL_MODE); + + /* use auxiliary power detection */ + val = readl(pcie->base + PCL_APP_PM0); + val |= PCL_SYS_AUX_PWR_DET; + writel(val, pcie->base + PCL_APP_PM0); + + /* assert PERST# */ + val = readl(pcie->base + PCL_PINCTRL0); + val &= ~(PCL_PERST_NOE_REGVAL | PCL_PERST_OUT_REGVAL + | PCL_PERST_PLDN_REGVAL); + val |= PCL_PERST_NOE_REGEN | PCL_PERST_OUT_REGEN + | PCL_PERST_PLDN_REGEN; + writel(val, pcie->base + PCL_PINCTRL0); + + uniphier_pcie_ltssm_enable(pcie, false); + + usleep_range(100000, 200000); + + /* deassert PERST# */ + val = readl(pcie->base + PCL_PINCTRL0); + val |= PCL_PERST_OUT_REGVAL | PCL_PERST_OUT_REGEN; + writel(val, pcie->base + PCL_PINCTRL0); +} + +static int uniphier_pcie_wait_rc(struct uniphier_pcie *pcie) +{ + u32 status; + int ret; + + /* wait PIPE clock */ + ret = readl_poll_timeout(pcie->base + PCL_PIPEMON, status, + status & PCL_PCLK_ALIVE, 100000, 1000000); + if (ret) { + dev_err(pcie->pci.dev, + "Failed to initialize controller in RC mode\n"); + return ret; + } + + return 0; +} + +static int uniphier_pcie_link_up(struct dw_pcie *pci) +{ + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); + u32 val, mask; + + val = readl(pcie->base + PCL_STATUS_LINK); + mask = PCL_RDLH_LINK_UP | PCL_XMLH_LINK_UP; + + return (val & mask) == mask; +} + +static int uniphier_pcie_start_link(struct dw_pcie *pci) +{ + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); + + uniphier_pcie_ltssm_enable(pcie, true); + + return 0; +} + +static void uniphier_pcie_stop_link(struct dw_pcie *pci) +{ + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); + + uniphier_pcie_ltssm_enable(pcie, false); +} + +static void uniphier_pcie_irq_enable(struct uniphier_pcie *pcie) +{ + writel(PCL_RCV_INT_ALL_ENABLE, pcie->base + PCL_RCV_INT); + writel(PCL_RCV_INTX_ALL_ENABLE, pcie->base + PCL_RCV_INTX); +} + + +static void uniphier_pcie_irq_mask(struct irq_data *d) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pp->lock, flags); + + val = readl(pcie->base + PCL_RCV_INTX); + val |= BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_MASK_SHIFT); + writel(val, pcie->base + PCL_RCV_INTX); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +} + +static void uniphier_pcie_irq_unmask(struct irq_data *d) +{ + struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pp->lock, flags); + + val = readl(pcie->base + PCL_RCV_INTX); + val &= ~BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_MASK_SHIFT); + writel(val, pcie->base + PCL_RCV_INTX); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +} + +static struct irq_chip uniphier_pcie_irq_chip = { + .name = "PCI", + .irq_mask = uniphier_pcie_irq_mask, + .irq_unmask = uniphier_pcie_irq_unmask, +}; + +static int uniphier_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &uniphier_pcie_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops uniphier_intx_domain_ops = { + .map = uniphier_pcie_intx_map, +}; + +static void uniphier_pcie_irq_handler(struct irq_desc *desc) +{ + struct dw_pcie_rp *pp = irq_desc_get_handler_data(desc); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned long reg; + u32 val, bit; + + /* INT for debug */ + val = readl(pcie->base + PCL_RCV_INT); + + if (val & PCL_CFG_BW_MGT_STATUS) + dev_dbg(pci->dev, "Link Bandwidth Management Event\n"); + if (val & PCL_CFG_LINK_AUTO_BW_STATUS) + dev_dbg(pci->dev, "Link Autonomous Bandwidth Event\n"); + if (val & PCL_CFG_AER_RC_ERR_MSI_STATUS) + dev_dbg(pci->dev, "Root Error\n"); + if (val & PCL_CFG_PME_MSI_STATUS) + dev_dbg(pci->dev, "PME Interrupt\n"); + + writel(val, pcie->base + PCL_RCV_INT); + + /* INTx */ + chained_irq_enter(chip, desc); + + val = readl(pcie->base + PCL_RCV_INTX); + reg = FIELD_GET(PCL_RCV_INTX_ALL_STATUS, val); + + for_each_set_bit(bit, ®, PCI_NUM_INTX) + generic_handle_domain_irq(pcie->legacy_irq_domain, bit); + + chained_irq_exit(chip, desc); +} + +static int uniphier_pcie_config_legacy_irq(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); + struct device_node *np = pci->dev->of_node; + struct device_node *np_intc; + int ret = 0; + + np_intc = of_get_child_by_name(np, "legacy-interrupt-controller"); + if (!np_intc) { + dev_err(pci->dev, "Failed to get legacy-interrupt-controller node\n"); + return -EINVAL; + } + + pp->irq = irq_of_parse_and_map(np_intc, 0); + if (!pp->irq) { + dev_err(pci->dev, "Failed to get an IRQ entry in legacy-interrupt-controller\n"); + ret = -EINVAL; + goto out_put_node; + } + + pcie->legacy_irq_domain = irq_domain_add_linear(np_intc, PCI_NUM_INTX, + &uniphier_intx_domain_ops, pp); + if (!pcie->legacy_irq_domain) { + dev_err(pci->dev, "Failed to get INTx domain\n"); + ret = -ENODEV; + goto out_put_node; + } + + irq_set_chained_handler_and_data(pp->irq, uniphier_pcie_irq_handler, + pp); + +out_put_node: + of_node_put(np_intc); + return ret; +} + +static int uniphier_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct uniphier_pcie *pcie = to_uniphier_pcie(pci); + int ret; + + ret = uniphier_pcie_config_legacy_irq(pp); + if (ret) + return ret; + + uniphier_pcie_irq_enable(pcie); + + return 0; +} + +static const struct dw_pcie_host_ops uniphier_pcie_host_ops = { + .host_init = uniphier_pcie_host_init, +}; + +static int uniphier_pcie_host_enable(struct uniphier_pcie *pcie) +{ + int ret; + + ret = clk_prepare_enable(pcie->clk); + if (ret) + return ret; + + ret = reset_control_deassert(pcie->rst); + if (ret) + goto out_clk_disable; + + uniphier_pcie_init_rc(pcie); + + ret = phy_init(pcie->phy); + if (ret) + goto out_rst_assert; + + ret = uniphier_pcie_wait_rc(pcie); + if (ret) + goto out_phy_exit; + + return 0; + +out_phy_exit: + phy_exit(pcie->phy); +out_rst_assert: + reset_control_assert(pcie->rst); +out_clk_disable: + clk_disable_unprepare(pcie->clk); + + return ret; +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = uniphier_pcie_start_link, + .stop_link = uniphier_pcie_stop_link, + .link_up = uniphier_pcie_link_up, +}; + +static int uniphier_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct uniphier_pcie *pcie; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pcie->pci.dev = dev; + pcie->pci.ops = &dw_pcie_ops; + + pcie->base = devm_platform_ioremap_resource_byname(pdev, "link"); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + + pcie->clk = devm_clk_get(dev, NULL); + if (IS_ERR(pcie->clk)) + return PTR_ERR(pcie->clk); + + pcie->rst = devm_reset_control_get_shared(dev, NULL); + if (IS_ERR(pcie->rst)) + return PTR_ERR(pcie->rst); + + pcie->phy = devm_phy_optional_get(dev, "pcie-phy"); + if (IS_ERR(pcie->phy)) + return PTR_ERR(pcie->phy); + + platform_set_drvdata(pdev, pcie); + + ret = uniphier_pcie_host_enable(pcie); + if (ret) + return ret; + + pcie->pci.pp.ops = &uniphier_pcie_host_ops; + + return dw_pcie_host_init(&pcie->pci.pp); +} + +static const struct of_device_id uniphier_pcie_match[] = { + { .compatible = "socionext,uniphier-pcie", }, + { /* sentinel */ }, +}; + +static struct platform_driver uniphier_pcie_driver = { + .probe = uniphier_pcie_probe, + .driver = { + .name = "uniphier-pcie", + .of_match_table = uniphier_pcie_match, + }, +}; +builtin_platform_driver(uniphier_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-visconti.c b/drivers/pci/controller/dwc/pcie-visconti.c new file mode 100644 index 000000000..71026fefa --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-visconti.c @@ -0,0 +1,329 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * DWC PCIe RC driver for Toshiba Visconti ARM SoC + * + * Copyright (C) 2021 Toshiba Electronic Device & Storage Corporation + * Copyright (C) 2021 TOSHIBA CORPORATION + * + * Nobuhiro Iwamatsu <nobuhiro1.iwamatsu@toshiba.co.jp> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/iopoll.h> +#include <linux/kernel.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/types.h> + +#include "pcie-designware.h" +#include "../../pci.h" + +struct visconti_pcie { + struct dw_pcie pci; + void __iomem *ulreg_base; + void __iomem *smu_base; + void __iomem *mpu_base; + struct clk *refclk; + struct clk *coreclk; + struct clk *auxclk; +}; + +#define PCIE_UL_REG_S_PCIE_MODE 0x00F4 +#define PCIE_UL_REG_S_PCIE_MODE_EP 0x00 +#define PCIE_UL_REG_S_PCIE_MODE_RC 0x04 + +#define PCIE_UL_REG_S_PERSTN_CTRL 0x00F8 +#define PCIE_UL_IOM_PCIE_PERSTN_I_EN BIT(3) +#define PCIE_UL_DIRECT_PERSTN_EN BIT(2) +#define PCIE_UL_PERSTN_OUT BIT(1) +#define PCIE_UL_DIRECT_PERSTN BIT(0) +#define PCIE_UL_REG_S_PERSTN_CTRL_INIT (PCIE_UL_IOM_PCIE_PERSTN_I_EN | \ + PCIE_UL_DIRECT_PERSTN_EN | \ + PCIE_UL_DIRECT_PERSTN) + +#define PCIE_UL_REG_S_PHY_INIT_02 0x0104 +#define PCIE_UL_PHY0_SRAM_EXT_LD_DONE BIT(0) + +#define PCIE_UL_REG_S_PHY_INIT_03 0x0108 +#define PCIE_UL_PHY0_SRAM_INIT_DONE BIT(0) + +#define PCIE_UL_REG_S_INT_EVENT_MASK1 0x0138 +#define PCIE_UL_CFG_PME_INT BIT(0) +#define PCIE_UL_CFG_LINK_EQ_REQ_INT BIT(1) +#define PCIE_UL_EDMA_INT0 BIT(2) +#define PCIE_UL_EDMA_INT1 BIT(3) +#define PCIE_UL_EDMA_INT2 BIT(4) +#define PCIE_UL_EDMA_INT3 BIT(5) +#define PCIE_UL_S_INT_EVENT_MASK1_ALL (PCIE_UL_CFG_PME_INT | \ + PCIE_UL_CFG_LINK_EQ_REQ_INT | \ + PCIE_UL_EDMA_INT0 | \ + PCIE_UL_EDMA_INT1 | \ + PCIE_UL_EDMA_INT2 | \ + PCIE_UL_EDMA_INT3) + +#define PCIE_UL_REG_S_SB_MON 0x0198 +#define PCIE_UL_REG_S_SIG_MON 0x019C +#define PCIE_UL_CORE_RST_N_MON BIT(0) + +#define PCIE_UL_REG_V_SII_DBG_00 0x0844 +#define PCIE_UL_REG_V_SII_GEN_CTRL_01 0x0860 +#define PCIE_UL_APP_LTSSM_ENABLE BIT(0) + +#define PCIE_UL_REG_V_PHY_ST_00 0x0864 +#define PCIE_UL_SMLH_LINK_UP BIT(0) + +#define PCIE_UL_REG_V_PHY_ST_02 0x0868 +#define PCIE_UL_S_DETECT_ACT 0x01 +#define PCIE_UL_S_L0 0x11 + +#define PISMU_CKON_PCIE 0x0038 +#define PISMU_CKON_PCIE_AUX_CLK BIT(1) +#define PISMU_CKON_PCIE_MSTR_ACLK BIT(0) + +#define PISMU_RSOFF_PCIE 0x0538 +#define PISMU_RSOFF_PCIE_ULREG_RST_N BIT(1) +#define PISMU_RSOFF_PCIE_PWR_UP_RST_N BIT(0) + +#define PCIE_MPU_REG_MP_EN 0x0 +#define MPU_MP_EN_DISABLE BIT(0) + +/* Access registers in PCIe ulreg */ +static void visconti_ulreg_writel(struct visconti_pcie *pcie, u32 val, u32 reg) +{ + writel_relaxed(val, pcie->ulreg_base + reg); +} + +static u32 visconti_ulreg_readl(struct visconti_pcie *pcie, u32 reg) +{ + return readl_relaxed(pcie->ulreg_base + reg); +} + +/* Access registers in PCIe smu */ +static void visconti_smu_writel(struct visconti_pcie *pcie, u32 val, u32 reg) +{ + writel_relaxed(val, pcie->smu_base + reg); +} + +/* Access registers in PCIe mpu */ +static void visconti_mpu_writel(struct visconti_pcie *pcie, u32 val, u32 reg) +{ + writel_relaxed(val, pcie->mpu_base + reg); +} + +static u32 visconti_mpu_readl(struct visconti_pcie *pcie, u32 reg) +{ + return readl_relaxed(pcie->mpu_base + reg); +} + +static int visconti_pcie_link_up(struct dw_pcie *pci) +{ + struct visconti_pcie *pcie = dev_get_drvdata(pci->dev); + void __iomem *addr = pcie->ulreg_base; + u32 val = readl_relaxed(addr + PCIE_UL_REG_V_PHY_ST_02); + + return !!(val & PCIE_UL_S_L0); +} + +static int visconti_pcie_start_link(struct dw_pcie *pci) +{ + struct visconti_pcie *pcie = dev_get_drvdata(pci->dev); + void __iomem *addr = pcie->ulreg_base; + u32 val; + int ret; + + visconti_ulreg_writel(pcie, PCIE_UL_APP_LTSSM_ENABLE, + PCIE_UL_REG_V_SII_GEN_CTRL_01); + + ret = readl_relaxed_poll_timeout(addr + PCIE_UL_REG_V_PHY_ST_02, + val, (val & PCIE_UL_S_L0), + 90000, 100000); + if (ret) + return ret; + + visconti_ulreg_writel(pcie, PCIE_UL_S_INT_EVENT_MASK1_ALL, + PCIE_UL_REG_S_INT_EVENT_MASK1); + + if (dw_pcie_link_up(pci)) { + val = visconti_mpu_readl(pcie, PCIE_MPU_REG_MP_EN); + visconti_mpu_writel(pcie, val & ~MPU_MP_EN_DISABLE, + PCIE_MPU_REG_MP_EN); + } + + return 0; +} + +static void visconti_pcie_stop_link(struct dw_pcie *pci) +{ + struct visconti_pcie *pcie = dev_get_drvdata(pci->dev); + u32 val; + + val = visconti_ulreg_readl(pcie, PCIE_UL_REG_V_SII_GEN_CTRL_01); + val &= ~PCIE_UL_APP_LTSSM_ENABLE; + visconti_ulreg_writel(pcie, val, PCIE_UL_REG_V_SII_GEN_CTRL_01); + + val = visconti_mpu_readl(pcie, PCIE_MPU_REG_MP_EN); + visconti_mpu_writel(pcie, val | MPU_MP_EN_DISABLE, PCIE_MPU_REG_MP_EN); +} + +/* + * In this SoC specification, the CPU bus outputs the offset value from + * 0x40000000 to the PCIe bus, so 0x40000000 is subtracted from the CPU + * bus address. This 0x40000000 is also based on io_base from DT. + */ +static u64 visconti_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 cpu_addr) +{ + struct dw_pcie_rp *pp = &pci->pp; + + return cpu_addr & ~pp->io_base; +} + +static const struct dw_pcie_ops dw_pcie_ops = { + .cpu_addr_fixup = visconti_pcie_cpu_addr_fixup, + .link_up = visconti_pcie_link_up, + .start_link = visconti_pcie_start_link, + .stop_link = visconti_pcie_stop_link, +}; + +static int visconti_pcie_host_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct visconti_pcie *pcie = dev_get_drvdata(pci->dev); + void __iomem *addr; + int err; + u32 val; + + visconti_smu_writel(pcie, + PISMU_CKON_PCIE_AUX_CLK | PISMU_CKON_PCIE_MSTR_ACLK, + PISMU_CKON_PCIE); + ndelay(250); + + visconti_smu_writel(pcie, PISMU_RSOFF_PCIE_ULREG_RST_N, + PISMU_RSOFF_PCIE); + visconti_ulreg_writel(pcie, PCIE_UL_REG_S_PCIE_MODE_RC, + PCIE_UL_REG_S_PCIE_MODE); + + val = PCIE_UL_REG_S_PERSTN_CTRL_INIT; + visconti_ulreg_writel(pcie, val, PCIE_UL_REG_S_PERSTN_CTRL); + udelay(100); + + val |= PCIE_UL_PERSTN_OUT; + visconti_ulreg_writel(pcie, val, PCIE_UL_REG_S_PERSTN_CTRL); + udelay(100); + + visconti_smu_writel(pcie, PISMU_RSOFF_PCIE_PWR_UP_RST_N, + PISMU_RSOFF_PCIE); + + addr = pcie->ulreg_base + PCIE_UL_REG_S_PHY_INIT_03; + err = readl_relaxed_poll_timeout(addr, val, + (val & PCIE_UL_PHY0_SRAM_INIT_DONE), + 100, 1000); + if (err) + return err; + + visconti_ulreg_writel(pcie, PCIE_UL_PHY0_SRAM_EXT_LD_DONE, + PCIE_UL_REG_S_PHY_INIT_02); + + addr = pcie->ulreg_base + PCIE_UL_REG_S_SIG_MON; + return readl_relaxed_poll_timeout(addr, val, + (val & PCIE_UL_CORE_RST_N_MON), 100, + 1000); +} + +static const struct dw_pcie_host_ops visconti_pcie_host_ops = { + .host_init = visconti_pcie_host_init, +}; + +static int visconti_get_resources(struct platform_device *pdev, + struct visconti_pcie *pcie) +{ + struct device *dev = &pdev->dev; + + pcie->ulreg_base = devm_platform_ioremap_resource_byname(pdev, "ulreg"); + if (IS_ERR(pcie->ulreg_base)) + return PTR_ERR(pcie->ulreg_base); + + pcie->smu_base = devm_platform_ioremap_resource_byname(pdev, "smu"); + if (IS_ERR(pcie->smu_base)) + return PTR_ERR(pcie->smu_base); + + pcie->mpu_base = devm_platform_ioremap_resource_byname(pdev, "mpu"); + if (IS_ERR(pcie->mpu_base)) + return PTR_ERR(pcie->mpu_base); + + pcie->refclk = devm_clk_get(dev, "ref"); + if (IS_ERR(pcie->refclk)) + return dev_err_probe(dev, PTR_ERR(pcie->refclk), + "Failed to get ref clock\n"); + + pcie->coreclk = devm_clk_get(dev, "core"); + if (IS_ERR(pcie->coreclk)) + return dev_err_probe(dev, PTR_ERR(pcie->coreclk), + "Failed to get core clock\n"); + + pcie->auxclk = devm_clk_get(dev, "aux"); + if (IS_ERR(pcie->auxclk)) + return dev_err_probe(dev, PTR_ERR(pcie->auxclk), + "Failed to get aux clock\n"); + + return 0; +} + +static int visconti_add_pcie_port(struct visconti_pcie *pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + + pp->irq = platform_get_irq_byname(pdev, "intr"); + if (pp->irq < 0) + return pp->irq; + + pp->ops = &visconti_pcie_host_ops; + + return dw_pcie_host_init(pp); +} + +static int visconti_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct visconti_pcie *pcie; + struct dw_pcie *pci; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pci = &pcie->pci; + pci->dev = dev; + pci->ops = &dw_pcie_ops; + + ret = visconti_get_resources(pdev, pcie); + if (ret) + return ret; + + platform_set_drvdata(pdev, pcie); + + return visconti_add_pcie_port(pcie, pdev); +} + +static const struct of_device_id visconti_pcie_match[] = { + { .compatible = "toshiba,visconti-pcie" }, + {}, +}; + +static struct platform_driver visconti_pcie_driver = { + .probe = visconti_pcie_probe, + .driver = { + .name = "visconti-pcie", + .of_match_table = visconti_pcie_match, + .suppress_bind_attrs = true, + }, +}; +builtin_platform_driver(visconti_pcie_driver); diff --git a/drivers/pci/controller/mobiveil/Kconfig b/drivers/pci/controller/mobiveil/Kconfig new file mode 100644 index 000000000..e4643fb94 --- /dev/null +++ b/drivers/pci/controller/mobiveil/Kconfig @@ -0,0 +1,33 @@ +# SPDX-License-Identifier: GPL-2.0 + +menu "Mobiveil PCIe Core Support" + depends on PCI + +config PCIE_MOBIVEIL + bool + +config PCIE_MOBIVEIL_HOST + bool + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_MOBIVEIL + +config PCIE_MOBIVEIL_PLAT + bool "Mobiveil AXI PCIe controller" + depends on ARCH_ZYNQMP || COMPILE_TEST + depends on OF + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_MOBIVEIL_HOST + help + Say Y here if you want to enable support for the Mobiveil AXI PCIe + Soft IP. It has up to 8 outbound and inbound windows + for address translation and it is a PCIe Gen4 IP. + +config PCIE_LAYERSCAPE_GEN4 + bool "Freescale Layerscape PCIe Gen4 controller" + depends on ARCH_LAYERSCAPE || COMPILE_TEST + depends on PCI_MSI_IRQ_DOMAIN + select PCIE_MOBIVEIL_HOST + help + Say Y here if you want PCIe Gen4 controller support on + Layerscape SoCs. +endmenu diff --git a/drivers/pci/controller/mobiveil/Makefile b/drivers/pci/controller/mobiveil/Makefile new file mode 100644 index 000000000..99d879de3 --- /dev/null +++ b/drivers/pci/controller/mobiveil/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +obj-$(CONFIG_PCIE_MOBIVEIL) += pcie-mobiveil.o +obj-$(CONFIG_PCIE_MOBIVEIL_HOST) += pcie-mobiveil-host.o +obj-$(CONFIG_PCIE_MOBIVEIL_PLAT) += pcie-mobiveil-plat.o +obj-$(CONFIG_PCIE_LAYERSCAPE_GEN4) += pcie-layerscape-gen4.o diff --git a/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c b/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c new file mode 100644 index 000000000..d7b7350f0 --- /dev/null +++ b/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c @@ -0,0 +1,255 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe Gen4 host controller driver for NXP Layerscape SoCs + * + * Copyright 2019-2020 NXP + * + * Author: Zhiqiang Hou <Zhiqiang.Hou@nxp.com> + */ + +#include <linux/kernel.h> +#include <linux/interrupt.h> +#include <linux/init.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/of_irq.h> +#include <linux/of_address.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/resource.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> + +#include "pcie-mobiveil.h" + +/* LUT and PF control registers */ +#define PCIE_LUT_OFF 0x80000 +#define PCIE_PF_OFF 0xc0000 +#define PCIE_PF_INT_STAT 0x18 +#define PF_INT_STAT_PABRST BIT(31) + +#define PCIE_PF_DBG 0x7fc +#define PF_DBG_LTSSM_MASK 0x3f +#define PF_DBG_LTSSM_L0 0x2d /* L0 state */ +#define PF_DBG_WE BIT(31) +#define PF_DBG_PABR BIT(27) + +#define to_ls_g4_pcie(x) platform_get_drvdata((x)->pdev) + +struct ls_g4_pcie { + struct mobiveil_pcie pci; + struct delayed_work dwork; + int irq; +}; + +static inline u32 ls_g4_pcie_pf_readl(struct ls_g4_pcie *pcie, u32 off) +{ + return ioread32(pcie->pci.csr_axi_slave_base + PCIE_PF_OFF + off); +} + +static inline void ls_g4_pcie_pf_writel(struct ls_g4_pcie *pcie, + u32 off, u32 val) +{ + iowrite32(val, pcie->pci.csr_axi_slave_base + PCIE_PF_OFF + off); +} + +static int ls_g4_pcie_link_up(struct mobiveil_pcie *pci) +{ + struct ls_g4_pcie *pcie = to_ls_g4_pcie(pci); + u32 state; + + state = ls_g4_pcie_pf_readl(pcie, PCIE_PF_DBG); + state = state & PF_DBG_LTSSM_MASK; + + if (state == PF_DBG_LTSSM_L0) + return 1; + + return 0; +} + +static void ls_g4_pcie_disable_interrupt(struct ls_g4_pcie *pcie) +{ + struct mobiveil_pcie *mv_pci = &pcie->pci; + + mobiveil_csr_writel(mv_pci, 0, PAB_INTP_AMBA_MISC_ENB); +} + +static void ls_g4_pcie_enable_interrupt(struct ls_g4_pcie *pcie) +{ + struct mobiveil_pcie *mv_pci = &pcie->pci; + u32 val; + + /* Clear the interrupt status */ + mobiveil_csr_writel(mv_pci, 0xffffffff, PAB_INTP_AMBA_MISC_STAT); + + val = PAB_INTP_INTX_MASK | PAB_INTP_MSI | PAB_INTP_RESET | + PAB_INTP_PCIE_UE | PAB_INTP_IE_PMREDI | PAB_INTP_IE_EC; + mobiveil_csr_writel(mv_pci, val, PAB_INTP_AMBA_MISC_ENB); +} + +static int ls_g4_pcie_reinit_hw(struct ls_g4_pcie *pcie) +{ + struct mobiveil_pcie *mv_pci = &pcie->pci; + struct device *dev = &mv_pci->pdev->dev; + u32 val, act_stat; + int to = 100; + + /* Poll for pab_csb_reset to set and PAB activity to clear */ + do { + usleep_range(10, 15); + val = ls_g4_pcie_pf_readl(pcie, PCIE_PF_INT_STAT); + act_stat = mobiveil_csr_readl(mv_pci, PAB_ACTIVITY_STAT); + } while (((val & PF_INT_STAT_PABRST) == 0 || act_stat) && to--); + if (to < 0) { + dev_err(dev, "Poll PABRST&PABACT timeout\n"); + return -EIO; + } + + /* clear PEX_RESET bit in PEX_PF0_DBG register */ + val = ls_g4_pcie_pf_readl(pcie, PCIE_PF_DBG); + val |= PF_DBG_WE; + ls_g4_pcie_pf_writel(pcie, PCIE_PF_DBG, val); + + val = ls_g4_pcie_pf_readl(pcie, PCIE_PF_DBG); + val |= PF_DBG_PABR; + ls_g4_pcie_pf_writel(pcie, PCIE_PF_DBG, val); + + val = ls_g4_pcie_pf_readl(pcie, PCIE_PF_DBG); + val &= ~PF_DBG_WE; + ls_g4_pcie_pf_writel(pcie, PCIE_PF_DBG, val); + + mobiveil_host_init(mv_pci, true); + + to = 100; + while (!ls_g4_pcie_link_up(mv_pci) && to--) + usleep_range(200, 250); + if (to < 0) { + dev_err(dev, "PCIe link training timeout\n"); + return -EIO; + } + + return 0; +} + +static irqreturn_t ls_g4_pcie_isr(int irq, void *dev_id) +{ + struct ls_g4_pcie *pcie = (struct ls_g4_pcie *)dev_id; + struct mobiveil_pcie *mv_pci = &pcie->pci; + u32 val; + + val = mobiveil_csr_readl(mv_pci, PAB_INTP_AMBA_MISC_STAT); + if (!val) + return IRQ_NONE; + + if (val & PAB_INTP_RESET) { + ls_g4_pcie_disable_interrupt(pcie); + schedule_delayed_work(&pcie->dwork, msecs_to_jiffies(1)); + } + + mobiveil_csr_writel(mv_pci, val, PAB_INTP_AMBA_MISC_STAT); + + return IRQ_HANDLED; +} + +static int ls_g4_pcie_interrupt_init(struct mobiveil_pcie *mv_pci) +{ + struct ls_g4_pcie *pcie = to_ls_g4_pcie(mv_pci); + struct platform_device *pdev = mv_pci->pdev; + struct device *dev = &pdev->dev; + int ret; + + pcie->irq = platform_get_irq_byname(pdev, "intr"); + if (pcie->irq < 0) + return pcie->irq; + + ret = devm_request_irq(dev, pcie->irq, ls_g4_pcie_isr, + IRQF_SHARED, pdev->name, pcie); + if (ret) { + dev_err(dev, "Can't register PCIe IRQ, errno = %d\n", ret); + return ret; + } + + return 0; +} + +static void ls_g4_pcie_reset(struct work_struct *work) +{ + struct delayed_work *dwork = container_of(work, struct delayed_work, + work); + struct ls_g4_pcie *pcie = container_of(dwork, struct ls_g4_pcie, dwork); + struct mobiveil_pcie *mv_pci = &pcie->pci; + u16 ctrl; + + ctrl = mobiveil_csr_readw(mv_pci, PCI_BRIDGE_CONTROL); + ctrl &= ~PCI_BRIDGE_CTL_BUS_RESET; + mobiveil_csr_writew(mv_pci, ctrl, PCI_BRIDGE_CONTROL); + + if (!ls_g4_pcie_reinit_hw(pcie)) + return; + + ls_g4_pcie_enable_interrupt(pcie); +} + +static struct mobiveil_rp_ops ls_g4_pcie_rp_ops = { + .interrupt_init = ls_g4_pcie_interrupt_init, +}; + +static const struct mobiveil_pab_ops ls_g4_pcie_pab_ops = { + .link_up = ls_g4_pcie_link_up, +}; + +static int __init ls_g4_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + struct mobiveil_pcie *mv_pci; + struct ls_g4_pcie *pcie; + struct device_node *np = dev->of_node; + int ret; + + if (!of_parse_phandle(np, "msi-parent", 0)) { + dev_err(dev, "Failed to find msi-parent\n"); + return -EINVAL; + } + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + mv_pci = &pcie->pci; + + mv_pci->pdev = pdev; + mv_pci->ops = &ls_g4_pcie_pab_ops; + mv_pci->rp.ops = &ls_g4_pcie_rp_ops; + mv_pci->rp.bridge = bridge; + + platform_set_drvdata(pdev, pcie); + + INIT_DELAYED_WORK(&pcie->dwork, ls_g4_pcie_reset); + + ret = mobiveil_pcie_host_probe(mv_pci); + if (ret) { + dev_err(dev, "Fail to probe\n"); + return ret; + } + + ls_g4_pcie_enable_interrupt(pcie); + + return 0; +} + +static const struct of_device_id ls_g4_pcie_of_match[] = { + { .compatible = "fsl,lx2160a-pcie", }, + { }, +}; + +static struct platform_driver ls_g4_pcie_driver = { + .driver = { + .name = "layerscape-pcie-gen4", + .of_match_table = ls_g4_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; + +builtin_platform_driver_probe(ls_g4_pcie_driver, ls_g4_pcie_probe); diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c new file mode 100644 index 000000000..31a7bdebe --- /dev/null +++ b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c @@ -0,0 +1,593 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Mobiveil PCIe Host controller + * + * Copyright (c) 2018 Mobiveil Inc. + * Copyright 2019-2020 NXP + * + * Author: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in> + * Hou Zhiqiang <Zhiqiang.Hou@nxp.com> + */ + +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_platform.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "pcie-mobiveil.h" + +static bool mobiveil_pcie_valid_device(struct pci_bus *bus, unsigned int devfn) +{ + /* Only one device down on each root port */ + if (pci_is_root_bus(bus) && (devfn > 0)) + return false; + + /* + * Do not read more than one device on the bus directly + * attached to RC + */ + if ((bus->primary == to_pci_host_bridge(bus->bridge)->busnr) && (PCI_SLOT(devfn) > 0)) + return false; + + return true; +} + +/* + * mobiveil_pcie_map_bus - routine to get the configuration base of either + * root port or endpoint + */ +static void __iomem *mobiveil_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct mobiveil_pcie *pcie = bus->sysdata; + struct mobiveil_root_port *rp = &pcie->rp; + u32 value; + + if (!mobiveil_pcie_valid_device(bus, devfn)) + return NULL; + + /* RC config access */ + if (pci_is_root_bus(bus)) + return pcie->csr_axi_slave_base + where; + + /* + * EP config access (in Config/APIO space) + * Program PEX Address base (31..16 bits) with appropriate value + * (BDF) in PAB_AXI_AMAP_PEX_WIN_L0 Register. + * Relies on pci_lock serialization + */ + value = bus->number << PAB_BUS_SHIFT | + PCI_SLOT(devfn) << PAB_DEVICE_SHIFT | + PCI_FUNC(devfn) << PAB_FUNCTION_SHIFT; + + mobiveil_csr_writel(pcie, value, PAB_AXI_AMAP_PEX_WIN_L(WIN_NUM_0)); + + return rp->config_axi_slave_base + where; +} + +static struct pci_ops mobiveil_pcie_ops = { + .map_bus = mobiveil_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static void mobiveil_pcie_isr(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct mobiveil_pcie *pcie = irq_desc_get_handler_data(desc); + struct device *dev = &pcie->pdev->dev; + struct mobiveil_root_port *rp = &pcie->rp; + struct mobiveil_msi *msi = &rp->msi; + u32 msi_data, msi_addr_lo, msi_addr_hi; + u32 intr_status, msi_status; + unsigned long shifted_status; + u32 bit, val, mask; + + /* + * The core provides a single interrupt for both INTx/MSI messages. + * So we'll read both INTx and MSI status + */ + + chained_irq_enter(chip, desc); + + /* read INTx status */ + val = mobiveil_csr_readl(pcie, PAB_INTP_AMBA_MISC_STAT); + mask = mobiveil_csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB); + intr_status = val & mask; + + /* Handle INTx */ + if (intr_status & PAB_INTP_INTX_MASK) { + shifted_status = mobiveil_csr_readl(pcie, + PAB_INTP_AMBA_MISC_STAT); + shifted_status &= PAB_INTP_INTX_MASK; + shifted_status >>= PAB_INTX_START; + do { + for_each_set_bit(bit, &shifted_status, PCI_NUM_INTX) { + int ret; + ret = generic_handle_domain_irq(rp->intx_domain, + bit + 1); + if (ret) + dev_err_ratelimited(dev, "unexpected IRQ, INT%d\n", + bit); + + /* clear interrupt handled */ + mobiveil_csr_writel(pcie, + 1 << (PAB_INTX_START + bit), + PAB_INTP_AMBA_MISC_STAT); + } + + shifted_status = mobiveil_csr_readl(pcie, + PAB_INTP_AMBA_MISC_STAT); + shifted_status &= PAB_INTP_INTX_MASK; + shifted_status >>= PAB_INTX_START; + } while (shifted_status != 0); + } + + /* read extra MSI status register */ + msi_status = readl_relaxed(pcie->apb_csr_base + MSI_STATUS_OFFSET); + + /* handle MSI interrupts */ + while (msi_status & 1) { + msi_data = readl_relaxed(pcie->apb_csr_base + MSI_DATA_OFFSET); + + /* + * MSI_STATUS_OFFSET register gets updated to zero + * once we pop not only the MSI data but also address + * from MSI hardware FIFO. So keeping these following + * two dummy reads. + */ + msi_addr_lo = readl_relaxed(pcie->apb_csr_base + + MSI_ADDR_L_OFFSET); + msi_addr_hi = readl_relaxed(pcie->apb_csr_base + + MSI_ADDR_H_OFFSET); + dev_dbg(dev, "MSI registers, data: %08x, addr: %08x:%08x\n", + msi_data, msi_addr_hi, msi_addr_lo); + + generic_handle_domain_irq(msi->dev_domain, msi_data); + + msi_status = readl_relaxed(pcie->apb_csr_base + + MSI_STATUS_OFFSET); + } + + /* Clear the interrupt status */ + mobiveil_csr_writel(pcie, intr_status, PAB_INTP_AMBA_MISC_STAT); + chained_irq_exit(chip, desc); +} + +static int mobiveil_pcie_parse_dt(struct mobiveil_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + struct platform_device *pdev = pcie->pdev; + struct device_node *node = dev->of_node; + struct mobiveil_root_port *rp = &pcie->rp; + struct resource *res; + + /* map config resource */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "config_axi_slave"); + rp->config_axi_slave_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(rp->config_axi_slave_base)) + return PTR_ERR(rp->config_axi_slave_base); + rp->ob_io_res = res; + + /* map csr resource */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "csr_axi_slave"); + pcie->csr_axi_slave_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pcie->csr_axi_slave_base)) + return PTR_ERR(pcie->csr_axi_slave_base); + pcie->pcie_reg_base = res->start; + + /* read the number of windows requested */ + if (of_property_read_u32(node, "apio-wins", &pcie->apio_wins)) + pcie->apio_wins = MAX_PIO_WINDOWS; + + if (of_property_read_u32(node, "ppio-wins", &pcie->ppio_wins)) + pcie->ppio_wins = MAX_PIO_WINDOWS; + + return 0; +} + +static void mobiveil_pcie_enable_msi(struct mobiveil_pcie *pcie) +{ + phys_addr_t msg_addr = pcie->pcie_reg_base; + struct mobiveil_msi *msi = &pcie->rp.msi; + + msi->num_of_vectors = PCI_NUM_MSI; + msi->msi_pages_phys = (phys_addr_t)msg_addr; + + writel_relaxed(lower_32_bits(msg_addr), + pcie->apb_csr_base + MSI_BASE_LO_OFFSET); + writel_relaxed(upper_32_bits(msg_addr), + pcie->apb_csr_base + MSI_BASE_HI_OFFSET); + writel_relaxed(4096, pcie->apb_csr_base + MSI_SIZE_OFFSET); + writel_relaxed(1, pcie->apb_csr_base + MSI_ENABLE_OFFSET); +} + +int mobiveil_host_init(struct mobiveil_pcie *pcie, bool reinit) +{ + struct mobiveil_root_port *rp = &pcie->rp; + struct pci_host_bridge *bridge = rp->bridge; + u32 value, pab_ctrl, type; + struct resource_entry *win; + + pcie->ib_wins_configured = 0; + pcie->ob_wins_configured = 0; + + if (!reinit) { + /* setup bus numbers */ + value = mobiveil_csr_readl(pcie, PCI_PRIMARY_BUS); + value &= 0xff000000; + value |= 0x00ff0100; + mobiveil_csr_writel(pcie, value, PCI_PRIMARY_BUS); + } + + /* + * program Bus Master Enable Bit in Command Register in PAB Config + * Space + */ + value = mobiveil_csr_readl(pcie, PCI_COMMAND); + value |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER; + mobiveil_csr_writel(pcie, value, PCI_COMMAND); + + /* + * program PIO Enable Bit to 1 (and PEX PIO Enable to 1) in PAB_CTRL + * register + */ + pab_ctrl = mobiveil_csr_readl(pcie, PAB_CTRL); + pab_ctrl |= (1 << AMBA_PIO_ENABLE_SHIFT) | (1 << PEX_PIO_ENABLE_SHIFT); + mobiveil_csr_writel(pcie, pab_ctrl, PAB_CTRL); + + /* + * program PIO Enable Bit to 1 and Config Window Enable Bit to 1 in + * PAB_AXI_PIO_CTRL Register + */ + value = mobiveil_csr_readl(pcie, PAB_AXI_PIO_CTRL); + value |= APIO_EN_MASK; + mobiveil_csr_writel(pcie, value, PAB_AXI_PIO_CTRL); + + /* Enable PCIe PIO master */ + value = mobiveil_csr_readl(pcie, PAB_PEX_PIO_CTRL); + value |= 1 << PIO_ENABLE_SHIFT; + mobiveil_csr_writel(pcie, value, PAB_PEX_PIO_CTRL); + + /* + * we'll program one outbound window for config reads and + * another default inbound window for all the upstream traffic + * rest of the outbound windows will be configured according to + * the "ranges" field defined in device tree + */ + + /* config outbound translation window */ + program_ob_windows(pcie, WIN_NUM_0, rp->ob_io_res->start, 0, + CFG_WINDOW_TYPE, resource_size(rp->ob_io_res)); + + /* memory inbound translation window */ + program_ib_windows(pcie, WIN_NUM_0, 0, 0, MEM_WINDOW_TYPE, IB_WIN_SIZE); + + /* Get the I/O and memory ranges from DT */ + resource_list_for_each_entry(win, &bridge->windows) { + if (resource_type(win->res) == IORESOURCE_MEM) + type = MEM_WINDOW_TYPE; + else if (resource_type(win->res) == IORESOURCE_IO) + type = IO_WINDOW_TYPE; + else + continue; + + /* configure outbound translation window */ + program_ob_windows(pcie, pcie->ob_wins_configured, + win->res->start, + win->res->start - win->offset, + type, resource_size(win->res)); + } + + /* fixup for PCIe class register */ + value = mobiveil_csr_readl(pcie, PAB_INTP_AXI_PIO_CLASS); + value &= 0xff; + value |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8; + mobiveil_csr_writel(pcie, value, PAB_INTP_AXI_PIO_CLASS); + + return 0; +} + +static void mobiveil_mask_intx_irq(struct irq_data *data) +{ + struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(data); + struct mobiveil_root_port *rp; + unsigned long flags; + u32 mask, shifted_val; + + rp = &pcie->rp; + mask = 1 << ((data->hwirq + PAB_INTX_START) - 1); + raw_spin_lock_irqsave(&rp->intx_mask_lock, flags); + shifted_val = mobiveil_csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB); + shifted_val &= ~mask; + mobiveil_csr_writel(pcie, shifted_val, PAB_INTP_AMBA_MISC_ENB); + raw_spin_unlock_irqrestore(&rp->intx_mask_lock, flags); +} + +static void mobiveil_unmask_intx_irq(struct irq_data *data) +{ + struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(data); + struct mobiveil_root_port *rp; + unsigned long flags; + u32 shifted_val, mask; + + rp = &pcie->rp; + mask = 1 << ((data->hwirq + PAB_INTX_START) - 1); + raw_spin_lock_irqsave(&rp->intx_mask_lock, flags); + shifted_val = mobiveil_csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB); + shifted_val |= mask; + mobiveil_csr_writel(pcie, shifted_val, PAB_INTP_AMBA_MISC_ENB); + raw_spin_unlock_irqrestore(&rp->intx_mask_lock, flags); +} + +static struct irq_chip intx_irq_chip = { + .name = "mobiveil_pcie:intx", + .irq_enable = mobiveil_unmask_intx_irq, + .irq_disable = mobiveil_mask_intx_irq, + .irq_mask = mobiveil_mask_intx_irq, + .irq_unmask = mobiveil_unmask_intx_irq, +}; + +/* routine to setup the INTx related data */ +static int mobiveil_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &intx_irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +/* INTx domain operations structure */ +static const struct irq_domain_ops intx_domain_ops = { + .map = mobiveil_pcie_intx_map, +}; + +static struct irq_chip mobiveil_msi_irq_chip = { + .name = "Mobiveil PCIe MSI", + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, +}; + +static struct msi_domain_info mobiveil_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX), + .chip = &mobiveil_msi_irq_chip, +}; + +static void mobiveil_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(data); + phys_addr_t addr = pcie->pcie_reg_base + (data->hwirq * sizeof(int)); + + msg->address_lo = lower_32_bits(addr); + msg->address_hi = upper_32_bits(addr); + msg->data = data->hwirq; + + dev_dbg(&pcie->pdev->dev, "msi#%d address_hi %#x address_lo %#x\n", + (int)data->hwirq, msg->address_hi, msg->address_lo); +} + +static int mobiveil_msi_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static struct irq_chip mobiveil_msi_bottom_irq_chip = { + .name = "Mobiveil MSI", + .irq_compose_msi_msg = mobiveil_compose_msi_msg, + .irq_set_affinity = mobiveil_msi_set_affinity, +}; + +static int mobiveil_irq_msi_domain_alloc(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct mobiveil_pcie *pcie = domain->host_data; + struct mobiveil_msi *msi = &pcie->rp.msi; + unsigned long bit; + + WARN_ON(nr_irqs != 1); + mutex_lock(&msi->lock); + + bit = find_first_zero_bit(msi->msi_irq_in_use, msi->num_of_vectors); + if (bit >= msi->num_of_vectors) { + mutex_unlock(&msi->lock); + return -ENOSPC; + } + + set_bit(bit, msi->msi_irq_in_use); + + mutex_unlock(&msi->lock); + + irq_domain_set_info(domain, virq, bit, &mobiveil_msi_bottom_irq_chip, + domain->host_data, handle_level_irq, NULL, NULL); + return 0; +} + +static void mobiveil_irq_msi_domain_free(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(d); + struct mobiveil_msi *msi = &pcie->rp.msi; + + mutex_lock(&msi->lock); + + if (!test_bit(d->hwirq, msi->msi_irq_in_use)) + dev_err(&pcie->pdev->dev, "trying to free unused MSI#%lu\n", + d->hwirq); + else + __clear_bit(d->hwirq, msi->msi_irq_in_use); + + mutex_unlock(&msi->lock); +} +static const struct irq_domain_ops msi_domain_ops = { + .alloc = mobiveil_irq_msi_domain_alloc, + .free = mobiveil_irq_msi_domain_free, +}; + +static int mobiveil_allocate_msi_domains(struct mobiveil_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + struct fwnode_handle *fwnode = of_node_to_fwnode(dev->of_node); + struct mobiveil_msi *msi = &pcie->rp.msi; + + mutex_init(&msi->lock); + msi->dev_domain = irq_domain_add_linear(NULL, msi->num_of_vectors, + &msi_domain_ops, pcie); + if (!msi->dev_domain) { + dev_err(dev, "failed to create IRQ domain\n"); + return -ENOMEM; + } + + msi->msi_domain = pci_msi_create_irq_domain(fwnode, + &mobiveil_msi_domain_info, + msi->dev_domain); + if (!msi->msi_domain) { + dev_err(dev, "failed to create MSI domain\n"); + irq_domain_remove(msi->dev_domain); + return -ENOMEM; + } + + return 0; +} + +static int mobiveil_pcie_init_irq_domain(struct mobiveil_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + struct device_node *node = dev->of_node; + struct mobiveil_root_port *rp = &pcie->rp; + + /* setup INTx */ + rp->intx_domain = irq_domain_add_linear(node, PCI_NUM_INTX, + &intx_domain_ops, pcie); + + if (!rp->intx_domain) { + dev_err(dev, "Failed to get a INTx IRQ domain\n"); + return -ENOMEM; + } + + raw_spin_lock_init(&rp->intx_mask_lock); + + /* setup MSI */ + return mobiveil_allocate_msi_domains(pcie); +} + +static int mobiveil_pcie_integrated_interrupt_init(struct mobiveil_pcie *pcie) +{ + struct platform_device *pdev = pcie->pdev; + struct device *dev = &pdev->dev; + struct mobiveil_root_port *rp = &pcie->rp; + struct resource *res; + int ret; + + /* map MSI config resource */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "apb_csr"); + pcie->apb_csr_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pcie->apb_csr_base)) + return PTR_ERR(pcie->apb_csr_base); + + /* setup MSI hardware registers */ + mobiveil_pcie_enable_msi(pcie); + + rp->irq = platform_get_irq(pdev, 0); + if (rp->irq < 0) + return rp->irq; + + /* initialize the IRQ domains */ + ret = mobiveil_pcie_init_irq_domain(pcie); + if (ret) { + dev_err(dev, "Failed creating IRQ Domain\n"); + return ret; + } + + irq_set_chained_handler_and_data(rp->irq, mobiveil_pcie_isr, pcie); + + /* Enable interrupts */ + mobiveil_csr_writel(pcie, (PAB_INTP_INTX_MASK | PAB_INTP_MSI_MASK), + PAB_INTP_AMBA_MISC_ENB); + + + return 0; +} + +static int mobiveil_pcie_interrupt_init(struct mobiveil_pcie *pcie) +{ + struct mobiveil_root_port *rp = &pcie->rp; + + if (rp->ops->interrupt_init) + return rp->ops->interrupt_init(pcie); + + return mobiveil_pcie_integrated_interrupt_init(pcie); +} + +static bool mobiveil_pcie_is_bridge(struct mobiveil_pcie *pcie) +{ + u32 header_type; + + header_type = mobiveil_csr_readb(pcie, PCI_HEADER_TYPE); + header_type &= 0x7f; + + return header_type == PCI_HEADER_TYPE_BRIDGE; +} + +int mobiveil_pcie_host_probe(struct mobiveil_pcie *pcie) +{ + struct mobiveil_root_port *rp = &pcie->rp; + struct pci_host_bridge *bridge = rp->bridge; + struct device *dev = &pcie->pdev->dev; + int ret; + + ret = mobiveil_pcie_parse_dt(pcie); + if (ret) { + dev_err(dev, "Parsing DT failed, ret: %x\n", ret); + return ret; + } + + if (!mobiveil_pcie_is_bridge(pcie)) + return -ENODEV; + + /* + * configure all inbound and outbound windows and prepare the RC for + * config access + */ + ret = mobiveil_host_init(pcie, false); + if (ret) { + dev_err(dev, "Failed to initialize host\n"); + return ret; + } + + ret = mobiveil_pcie_interrupt_init(pcie); + if (ret) { + dev_err(dev, "Interrupt init failed\n"); + return ret; + } + + /* Initialize bridge */ + bridge->sysdata = pcie; + bridge->ops = &mobiveil_pcie_ops; + + ret = mobiveil_bringup_link(pcie); + if (ret) { + dev_info(dev, "link bring-up failed\n"); + return ret; + } + + return pci_host_probe(bridge); +} diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil-plat.c b/drivers/pci/controller/mobiveil/pcie-mobiveil-plat.c new file mode 100644 index 000000000..f6fcd95c2 --- /dev/null +++ b/drivers/pci/controller/mobiveil/pcie-mobiveil-plat.c @@ -0,0 +1,61 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Mobiveil PCIe Host controller + * + * Copyright (c) 2018 Mobiveil Inc. + * Copyright 2019 NXP + * + * Author: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in> + * Hou Zhiqiang <Zhiqiang.Hou@nxp.com> + */ + +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "pcie-mobiveil.h" + +static int mobiveil_pcie_probe(struct platform_device *pdev) +{ + struct mobiveil_pcie *pcie; + struct pci_host_bridge *bridge; + struct device *dev = &pdev->dev; + + /* allocate the PCIe port */ + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + pcie->rp.bridge = bridge; + + pcie->pdev = pdev; + + return mobiveil_pcie_host_probe(pcie); +} + +static const struct of_device_id mobiveil_pcie_of_match[] = { + {.compatible = "mbvl,gpex40-pcie",}, + {}, +}; + +MODULE_DEVICE_TABLE(of, mobiveil_pcie_of_match); + +static struct platform_driver mobiveil_pcie_driver = { + .probe = mobiveil_pcie_probe, + .driver = { + .name = "mobiveil-pcie", + .of_match_table = mobiveil_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; + +builtin_platform_driver(mobiveil_pcie_driver); + +MODULE_LICENSE("GPL v2"); +MODULE_DESCRIPTION("Mobiveil PCIe host controller driver"); +MODULE_AUTHOR("Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in>"); diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil.c b/drivers/pci/controller/mobiveil/pcie-mobiveil.c new file mode 100644 index 000000000..62ecbaeb0 --- /dev/null +++ b/drivers/pci/controller/mobiveil/pcie-mobiveil.c @@ -0,0 +1,231 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for Mobiveil PCIe Host controller + * + * Copyright (c) 2018 Mobiveil Inc. + * Copyright 2019 NXP + * + * Author: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in> + * Hou Zhiqiang <Zhiqiang.Hou@nxp.com> + */ + +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/platform_device.h> + +#include "pcie-mobiveil.h" + +/* + * mobiveil_pcie_sel_page - routine to access paged register + * + * Registers whose address greater than PAGED_ADDR_BNDRY (0xc00) are paged, + * for this scheme to work extracted higher 6 bits of the offset will be + * written to pg_sel field of PAB_CTRL register and rest of the lower 10 + * bits enabled with PAGED_ADDR_BNDRY are used as offset of the register. + */ +static void mobiveil_pcie_sel_page(struct mobiveil_pcie *pcie, u8 pg_idx) +{ + u32 val; + + val = readl(pcie->csr_axi_slave_base + PAB_CTRL); + val &= ~(PAGE_SEL_MASK << PAGE_SEL_SHIFT); + val |= (pg_idx & PAGE_SEL_MASK) << PAGE_SEL_SHIFT; + + writel(val, pcie->csr_axi_slave_base + PAB_CTRL); +} + +static void __iomem *mobiveil_pcie_comp_addr(struct mobiveil_pcie *pcie, + u32 off) +{ + if (off < PAGED_ADDR_BNDRY) { + /* For directly accessed registers, clear the pg_sel field */ + mobiveil_pcie_sel_page(pcie, 0); + return pcie->csr_axi_slave_base + off; + } + + mobiveil_pcie_sel_page(pcie, OFFSET_TO_PAGE_IDX(off)); + return pcie->csr_axi_slave_base + OFFSET_TO_PAGE_ADDR(off); +} + +static int mobiveil_pcie_read(void __iomem *addr, int size, u32 *val) +{ + if ((uintptr_t)addr & (size - 1)) { + *val = 0; + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + switch (size) { + case 4: + *val = readl(addr); + break; + case 2: + *val = readw(addr); + break; + case 1: + *val = readb(addr); + break; + default: + *val = 0; + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + return PCIBIOS_SUCCESSFUL; +} + +static int mobiveil_pcie_write(void __iomem *addr, int size, u32 val) +{ + if ((uintptr_t)addr & (size - 1)) + return PCIBIOS_BAD_REGISTER_NUMBER; + + switch (size) { + case 4: + writel(val, addr); + break; + case 2: + writew(val, addr); + break; + case 1: + writeb(val, addr); + break; + default: + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + return PCIBIOS_SUCCESSFUL; +} + +u32 mobiveil_csr_read(struct mobiveil_pcie *pcie, u32 off, size_t size) +{ + void __iomem *addr; + u32 val; + int ret; + + addr = mobiveil_pcie_comp_addr(pcie, off); + + ret = mobiveil_pcie_read(addr, size, &val); + if (ret) + dev_err(&pcie->pdev->dev, "read CSR address failed\n"); + + return val; +} + +void mobiveil_csr_write(struct mobiveil_pcie *pcie, u32 val, u32 off, + size_t size) +{ + void __iomem *addr; + int ret; + + addr = mobiveil_pcie_comp_addr(pcie, off); + + ret = mobiveil_pcie_write(addr, size, val); + if (ret) + dev_err(&pcie->pdev->dev, "write CSR address failed\n"); +} + +bool mobiveil_pcie_link_up(struct mobiveil_pcie *pcie) +{ + if (pcie->ops->link_up) + return pcie->ops->link_up(pcie); + + return (mobiveil_csr_readl(pcie, LTSSM_STATUS) & + LTSSM_STATUS_L0_MASK) == LTSSM_STATUS_L0; +} + +void program_ib_windows(struct mobiveil_pcie *pcie, int win_num, + u64 cpu_addr, u64 pci_addr, u32 type, u64 size) +{ + u32 value; + u64 size64 = ~(size - 1); + + if (win_num >= pcie->ppio_wins) { + dev_err(&pcie->pdev->dev, + "ERROR: max inbound windows reached !\n"); + return; + } + + value = mobiveil_csr_readl(pcie, PAB_PEX_AMAP_CTRL(win_num)); + value &= ~(AMAP_CTRL_TYPE_MASK << AMAP_CTRL_TYPE_SHIFT | WIN_SIZE_MASK); + value |= type << AMAP_CTRL_TYPE_SHIFT | 1 << AMAP_CTRL_EN_SHIFT | + (lower_32_bits(size64) & WIN_SIZE_MASK); + mobiveil_csr_writel(pcie, value, PAB_PEX_AMAP_CTRL(win_num)); + + mobiveil_csr_writel(pcie, upper_32_bits(size64), + PAB_EXT_PEX_AMAP_SIZEN(win_num)); + + mobiveil_csr_writel(pcie, lower_32_bits(cpu_addr), + PAB_PEX_AMAP_AXI_WIN(win_num)); + mobiveil_csr_writel(pcie, upper_32_bits(cpu_addr), + PAB_EXT_PEX_AMAP_AXI_WIN(win_num)); + + mobiveil_csr_writel(pcie, lower_32_bits(pci_addr), + PAB_PEX_AMAP_PEX_WIN_L(win_num)); + mobiveil_csr_writel(pcie, upper_32_bits(pci_addr), + PAB_PEX_AMAP_PEX_WIN_H(win_num)); + + pcie->ib_wins_configured++; +} + +/* + * routine to program the outbound windows + */ +void program_ob_windows(struct mobiveil_pcie *pcie, int win_num, + u64 cpu_addr, u64 pci_addr, u32 type, u64 size) +{ + u32 value; + u64 size64 = ~(size - 1); + + if (win_num >= pcie->apio_wins) { + dev_err(&pcie->pdev->dev, + "ERROR: max outbound windows reached !\n"); + return; + } + + /* + * program Enable Bit to 1, Type Bit to (00) base 2, AXI Window Size Bit + * to 4 KB in PAB_AXI_AMAP_CTRL register + */ + value = mobiveil_csr_readl(pcie, PAB_AXI_AMAP_CTRL(win_num)); + value &= ~(WIN_TYPE_MASK << WIN_TYPE_SHIFT | WIN_SIZE_MASK); + value |= 1 << WIN_ENABLE_SHIFT | type << WIN_TYPE_SHIFT | + (lower_32_bits(size64) & WIN_SIZE_MASK); + mobiveil_csr_writel(pcie, value, PAB_AXI_AMAP_CTRL(win_num)); + + mobiveil_csr_writel(pcie, upper_32_bits(size64), + PAB_EXT_AXI_AMAP_SIZE(win_num)); + + /* + * program AXI window base with appropriate value in + * PAB_AXI_AMAP_AXI_WIN0 register + */ + mobiveil_csr_writel(pcie, + lower_32_bits(cpu_addr) & (~AXI_WINDOW_ALIGN_MASK), + PAB_AXI_AMAP_AXI_WIN(win_num)); + mobiveil_csr_writel(pcie, upper_32_bits(cpu_addr), + PAB_EXT_AXI_AMAP_AXI_WIN(win_num)); + + mobiveil_csr_writel(pcie, lower_32_bits(pci_addr), + PAB_AXI_AMAP_PEX_WIN_L(win_num)); + mobiveil_csr_writel(pcie, upper_32_bits(pci_addr), + PAB_AXI_AMAP_PEX_WIN_H(win_num)); + + pcie->ob_wins_configured++; +} + +int mobiveil_bringup_link(struct mobiveil_pcie *pcie) +{ + int retries; + + /* check if the link is up or not */ + for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { + if (mobiveil_pcie_link_up(pcie)) + return 0; + + usleep_range(LINK_WAIT_MIN, LINK_WAIT_MAX); + } + + dev_err(&pcie->pdev->dev, "link never came up\n"); + + return -ETIMEDOUT; +} diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil.h b/drivers/pci/controller/mobiveil/pcie-mobiveil.h new file mode 100644 index 000000000..6082b8afb --- /dev/null +++ b/drivers/pci/controller/mobiveil/pcie-mobiveil.h @@ -0,0 +1,225 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PCIe host controller driver for Mobiveil PCIe Host controller + * + * Copyright (c) 2018 Mobiveil Inc. + * Copyright 2019 NXP + * + * Author: Subrahmanya Lingappa <l.subrahmanya@mobiveil.co.in> + * Hou Zhiqiang <Zhiqiang.Hou@nxp.com> + */ + +#ifndef _PCIE_MOBIVEIL_H +#define _PCIE_MOBIVEIL_H + +#include <linux/pci.h> +#include <linux/irq.h> +#include <linux/msi.h> +#include "../../pci.h" + +/* register offsets and bit positions */ + +/* + * translation tables are grouped into windows, each window registers are + * grouped into blocks of 4 or 16 registers each + */ +#define PAB_REG_BLOCK_SIZE 16 +#define PAB_EXT_REG_BLOCK_SIZE 4 + +#define PAB_REG_ADDR(offset, win) \ + (offset + (win * PAB_REG_BLOCK_SIZE)) +#define PAB_EXT_REG_ADDR(offset, win) \ + (offset + (win * PAB_EXT_REG_BLOCK_SIZE)) + +#define LTSSM_STATUS 0x0404 +#define LTSSM_STATUS_L0_MASK 0x3f +#define LTSSM_STATUS_L0 0x2d + +#define PAB_CTRL 0x0808 +#define AMBA_PIO_ENABLE_SHIFT 0 +#define PEX_PIO_ENABLE_SHIFT 1 +#define PAGE_SEL_SHIFT 13 +#define PAGE_SEL_MASK 0x3f +#define PAGE_LO_MASK 0x3ff +#define PAGE_SEL_OFFSET_SHIFT 10 + +#define PAB_ACTIVITY_STAT 0x81c + +#define PAB_AXI_PIO_CTRL 0x0840 +#define APIO_EN_MASK 0xf + +#define PAB_PEX_PIO_CTRL 0x08c0 +#define PIO_ENABLE_SHIFT 0 + +#define PAB_INTP_AMBA_MISC_ENB 0x0b0c +#define PAB_INTP_AMBA_MISC_STAT 0x0b1c +#define PAB_INTP_RESET BIT(1) +#define PAB_INTP_MSI BIT(3) +#define PAB_INTP_INTA BIT(5) +#define PAB_INTP_INTB BIT(6) +#define PAB_INTP_INTC BIT(7) +#define PAB_INTP_INTD BIT(8) +#define PAB_INTP_PCIE_UE BIT(9) +#define PAB_INTP_IE_PMREDI BIT(29) +#define PAB_INTP_IE_EC BIT(30) +#define PAB_INTP_MSI_MASK PAB_INTP_MSI +#define PAB_INTP_INTX_MASK (PAB_INTP_INTA | PAB_INTP_INTB |\ + PAB_INTP_INTC | PAB_INTP_INTD) + +#define PAB_AXI_AMAP_CTRL(win) PAB_REG_ADDR(0x0ba0, win) +#define WIN_ENABLE_SHIFT 0 +#define WIN_TYPE_SHIFT 1 +#define WIN_TYPE_MASK 0x3 +#define WIN_SIZE_MASK 0xfffffc00 + +#define PAB_EXT_AXI_AMAP_SIZE(win) PAB_EXT_REG_ADDR(0xbaf0, win) + +#define PAB_EXT_AXI_AMAP_AXI_WIN(win) PAB_EXT_REG_ADDR(0x80a0, win) +#define PAB_AXI_AMAP_AXI_WIN(win) PAB_REG_ADDR(0x0ba4, win) +#define AXI_WINDOW_ALIGN_MASK 3 + +#define PAB_AXI_AMAP_PEX_WIN_L(win) PAB_REG_ADDR(0x0ba8, win) +#define PAB_BUS_SHIFT 24 +#define PAB_DEVICE_SHIFT 19 +#define PAB_FUNCTION_SHIFT 16 + +#define PAB_AXI_AMAP_PEX_WIN_H(win) PAB_REG_ADDR(0x0bac, win) +#define PAB_INTP_AXI_PIO_CLASS 0x474 + +#define PAB_PEX_AMAP_CTRL(win) PAB_REG_ADDR(0x4ba0, win) +#define AMAP_CTRL_EN_SHIFT 0 +#define AMAP_CTRL_TYPE_SHIFT 1 +#define AMAP_CTRL_TYPE_MASK 3 + +#define PAB_EXT_PEX_AMAP_SIZEN(win) PAB_EXT_REG_ADDR(0xbef0, win) +#define PAB_EXT_PEX_AMAP_AXI_WIN(win) PAB_EXT_REG_ADDR(0xb4a0, win) +#define PAB_PEX_AMAP_AXI_WIN(win) PAB_REG_ADDR(0x4ba4, win) +#define PAB_PEX_AMAP_PEX_WIN_L(win) PAB_REG_ADDR(0x4ba8, win) +#define PAB_PEX_AMAP_PEX_WIN_H(win) PAB_REG_ADDR(0x4bac, win) + +/* starting offset of INTX bits in status register */ +#define PAB_INTX_START 5 + +/* supported number of MSI interrupts */ +#define PCI_NUM_MSI 16 + +/* MSI registers */ +#define MSI_BASE_LO_OFFSET 0x04 +#define MSI_BASE_HI_OFFSET 0x08 +#define MSI_SIZE_OFFSET 0x0c +#define MSI_ENABLE_OFFSET 0x14 +#define MSI_STATUS_OFFSET 0x18 +#define MSI_DATA_OFFSET 0x20 +#define MSI_ADDR_L_OFFSET 0x24 +#define MSI_ADDR_H_OFFSET 0x28 + +/* outbound and inbound window definitions */ +#define WIN_NUM_0 0 +#define WIN_NUM_1 1 +#define CFG_WINDOW_TYPE 0 +#define IO_WINDOW_TYPE 1 +#define MEM_WINDOW_TYPE 2 +#define IB_WIN_SIZE ((u64)256 * 1024 * 1024 * 1024) +#define MAX_PIO_WINDOWS 8 + +/* Parameters for the waiting for link up routine */ +#define LINK_WAIT_MAX_RETRIES 10 +#define LINK_WAIT_MIN 90000 +#define LINK_WAIT_MAX 100000 + +#define PAGED_ADDR_BNDRY 0xc00 +#define OFFSET_TO_PAGE_ADDR(off) \ + ((off & PAGE_LO_MASK) | PAGED_ADDR_BNDRY) +#define OFFSET_TO_PAGE_IDX(off) \ + ((off >> PAGE_SEL_OFFSET_SHIFT) & PAGE_SEL_MASK) + +struct mobiveil_msi { /* MSI information */ + struct mutex lock; /* protect bitmap variable */ + struct irq_domain *msi_domain; + struct irq_domain *dev_domain; + phys_addr_t msi_pages_phys; + int num_of_vectors; + DECLARE_BITMAP(msi_irq_in_use, PCI_NUM_MSI); +}; + +struct mobiveil_pcie; + +struct mobiveil_rp_ops { + int (*interrupt_init)(struct mobiveil_pcie *pcie); +}; + +struct mobiveil_root_port { + void __iomem *config_axi_slave_base; /* endpoint config base */ + struct resource *ob_io_res; + struct mobiveil_rp_ops *ops; + int irq; + raw_spinlock_t intx_mask_lock; + struct irq_domain *intx_domain; + struct mobiveil_msi msi; + struct pci_host_bridge *bridge; +}; + +struct mobiveil_pab_ops { + int (*link_up)(struct mobiveil_pcie *pcie); +}; + +struct mobiveil_pcie { + struct platform_device *pdev; + void __iomem *csr_axi_slave_base; /* root port config base */ + void __iomem *apb_csr_base; /* MSI register base */ + phys_addr_t pcie_reg_base; /* Physical PCIe Controller Base */ + int apio_wins; + int ppio_wins; + int ob_wins_configured; /* configured outbound windows */ + int ib_wins_configured; /* configured inbound windows */ + const struct mobiveil_pab_ops *ops; + struct mobiveil_root_port rp; +}; + +int mobiveil_pcie_host_probe(struct mobiveil_pcie *pcie); +int mobiveil_host_init(struct mobiveil_pcie *pcie, bool reinit); +bool mobiveil_pcie_link_up(struct mobiveil_pcie *pcie); +int mobiveil_bringup_link(struct mobiveil_pcie *pcie); +void program_ob_windows(struct mobiveil_pcie *pcie, int win_num, u64 cpu_addr, + u64 pci_addr, u32 type, u64 size); +void program_ib_windows(struct mobiveil_pcie *pcie, int win_num, u64 cpu_addr, + u64 pci_addr, u32 type, u64 size); +u32 mobiveil_csr_read(struct mobiveil_pcie *pcie, u32 off, size_t size); +void mobiveil_csr_write(struct mobiveil_pcie *pcie, u32 val, u32 off, + size_t size); + +static inline u32 mobiveil_csr_readl(struct mobiveil_pcie *pcie, u32 off) +{ + return mobiveil_csr_read(pcie, off, 0x4); +} + +static inline u16 mobiveil_csr_readw(struct mobiveil_pcie *pcie, u32 off) +{ + return mobiveil_csr_read(pcie, off, 0x2); +} + +static inline u8 mobiveil_csr_readb(struct mobiveil_pcie *pcie, u32 off) +{ + return mobiveil_csr_read(pcie, off, 0x1); +} + + +static inline void mobiveil_csr_writel(struct mobiveil_pcie *pcie, u32 val, + u32 off) +{ + mobiveil_csr_write(pcie, val, off, 0x4); +} + +static inline void mobiveil_csr_writew(struct mobiveil_pcie *pcie, u16 val, + u32 off) +{ + mobiveil_csr_write(pcie, val, off, 0x2); +} + +static inline void mobiveil_csr_writeb(struct mobiveil_pcie *pcie, u8 val, + u32 off) +{ + mobiveil_csr_write(pcie, val, off, 0x1); +} + +#endif /* _PCIE_MOBIVEIL_H */ diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c new file mode 100644 index 000000000..ba36bbc58 --- /dev/null +++ b/drivers/pci/controller/pci-aardvark.c @@ -0,0 +1,2015 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Driver for the Aardvark PCIe controller, used on Marvell Armada + * 3700. + * + * Copyright (C) 2016 Marvell + * + * Author: Hezi Shahmoon <hezi.shahmoon@marvell.com> + */ + +#include <linux/bitfield.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/init.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_gpio.h> +#include <linux/of_pci.h> + +#include "../pci.h" +#include "../pci-bridge-emul.h" + +/* PCIe core registers */ +#define PCIE_CORE_DEV_ID_REG 0x0 +#define PCIE_CORE_CMD_STATUS_REG 0x4 +#define PCIE_CORE_DEV_REV_REG 0x8 +#define PCIE_CORE_SSDEV_ID_REG 0x2c +#define PCIE_CORE_PCIEXP_CAP 0xc0 +#define PCIE_CORE_PCIERR_CAP 0x100 +#define PCIE_CORE_ERR_CAPCTL_REG 0x118 +#define PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX BIT(5) +#define PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN BIT(6) +#define PCIE_CORE_ERR_CAPCTL_ECRC_CHCK BIT(7) +#define PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV BIT(8) +/* PIO registers base address and register offsets */ +#define PIO_BASE_ADDR 0x4000 +#define PIO_CTRL (PIO_BASE_ADDR + 0x0) +#define PIO_CTRL_TYPE_MASK GENMASK(3, 0) +#define PIO_CTRL_ADDR_WIN_DISABLE BIT(24) +#define PIO_STAT (PIO_BASE_ADDR + 0x4) +#define PIO_COMPLETION_STATUS_SHIFT 7 +#define PIO_COMPLETION_STATUS_MASK GENMASK(9, 7) +#define PIO_COMPLETION_STATUS_OK 0 +#define PIO_COMPLETION_STATUS_UR 1 +#define PIO_COMPLETION_STATUS_CRS 2 +#define PIO_COMPLETION_STATUS_CA 4 +#define PIO_NON_POSTED_REQ BIT(10) +#define PIO_ERR_STATUS BIT(11) +#define PIO_ADDR_LS (PIO_BASE_ADDR + 0x8) +#define PIO_ADDR_MS (PIO_BASE_ADDR + 0xc) +#define PIO_WR_DATA (PIO_BASE_ADDR + 0x10) +#define PIO_WR_DATA_STRB (PIO_BASE_ADDR + 0x14) +#define PIO_RD_DATA (PIO_BASE_ADDR + 0x18) +#define PIO_START (PIO_BASE_ADDR + 0x1c) +#define PIO_ISR (PIO_BASE_ADDR + 0x20) +#define PIO_ISRM (PIO_BASE_ADDR + 0x24) + +/* Aardvark Control registers */ +#define CONTROL_BASE_ADDR 0x4800 +#define PCIE_CORE_CTRL0_REG (CONTROL_BASE_ADDR + 0x0) +#define PCIE_GEN_SEL_MSK 0x3 +#define PCIE_GEN_SEL_SHIFT 0x0 +#define SPEED_GEN_1 0 +#define SPEED_GEN_2 1 +#define SPEED_GEN_3 2 +#define IS_RC_MSK 1 +#define IS_RC_SHIFT 2 +#define LANE_CNT_MSK 0x18 +#define LANE_CNT_SHIFT 0x3 +#define LANE_COUNT_1 (0 << LANE_CNT_SHIFT) +#define LANE_COUNT_2 (1 << LANE_CNT_SHIFT) +#define LANE_COUNT_4 (2 << LANE_CNT_SHIFT) +#define LANE_COUNT_8 (3 << LANE_CNT_SHIFT) +#define LINK_TRAINING_EN BIT(6) +#define LEGACY_INTA BIT(28) +#define LEGACY_INTB BIT(29) +#define LEGACY_INTC BIT(30) +#define LEGACY_INTD BIT(31) +#define PCIE_CORE_CTRL1_REG (CONTROL_BASE_ADDR + 0x4) +#define HOT_RESET_GEN BIT(0) +#define PCIE_CORE_CTRL2_REG (CONTROL_BASE_ADDR + 0x8) +#define PCIE_CORE_CTRL2_RESERVED 0x7 +#define PCIE_CORE_CTRL2_TD_ENABLE BIT(4) +#define PCIE_CORE_CTRL2_STRICT_ORDER_ENABLE BIT(5) +#define PCIE_CORE_CTRL2_OB_WIN_ENABLE BIT(6) +#define PCIE_CORE_CTRL2_MSI_ENABLE BIT(10) +#define PCIE_CORE_REF_CLK_REG (CONTROL_BASE_ADDR + 0x14) +#define PCIE_CORE_REF_CLK_TX_ENABLE BIT(1) +#define PCIE_CORE_REF_CLK_RX_ENABLE BIT(2) +#define PCIE_MSG_LOG_REG (CONTROL_BASE_ADDR + 0x30) +#define PCIE_ISR0_REG (CONTROL_BASE_ADDR + 0x40) +#define PCIE_MSG_PM_PME_MASK BIT(7) +#define PCIE_ISR0_MASK_REG (CONTROL_BASE_ADDR + 0x44) +#define PCIE_ISR0_MSI_INT_PENDING BIT(24) +#define PCIE_ISR0_CORR_ERR BIT(11) +#define PCIE_ISR0_NFAT_ERR BIT(12) +#define PCIE_ISR0_FAT_ERR BIT(13) +#define PCIE_ISR0_ERR_MASK GENMASK(13, 11) +#define PCIE_ISR0_INTX_ASSERT(val) BIT(16 + (val)) +#define PCIE_ISR0_INTX_DEASSERT(val) BIT(20 + (val)) +#define PCIE_ISR0_ALL_MASK GENMASK(31, 0) +#define PCIE_ISR1_REG (CONTROL_BASE_ADDR + 0x48) +#define PCIE_ISR1_MASK_REG (CONTROL_BASE_ADDR + 0x4C) +#define PCIE_ISR1_POWER_STATE_CHANGE BIT(4) +#define PCIE_ISR1_FLUSH BIT(5) +#define PCIE_ISR1_INTX_ASSERT(val) BIT(8 + (val)) +#define PCIE_ISR1_ALL_MASK GENMASK(31, 0) +#define PCIE_MSI_ADDR_LOW_REG (CONTROL_BASE_ADDR + 0x50) +#define PCIE_MSI_ADDR_HIGH_REG (CONTROL_BASE_ADDR + 0x54) +#define PCIE_MSI_STATUS_REG (CONTROL_BASE_ADDR + 0x58) +#define PCIE_MSI_MASK_REG (CONTROL_BASE_ADDR + 0x5C) +#define PCIE_MSI_ALL_MASK GENMASK(31, 0) +#define PCIE_MSI_PAYLOAD_REG (CONTROL_BASE_ADDR + 0x9C) +#define PCIE_MSI_DATA_MASK GENMASK(15, 0) + +/* PCIe window configuration */ +#define OB_WIN_BASE_ADDR 0x4c00 +#define OB_WIN_BLOCK_SIZE 0x20 +#define OB_WIN_COUNT 8 +#define OB_WIN_REG_ADDR(win, offset) (OB_WIN_BASE_ADDR + \ + OB_WIN_BLOCK_SIZE * (win) + \ + (offset)) +#define OB_WIN_MATCH_LS(win) OB_WIN_REG_ADDR(win, 0x00) +#define OB_WIN_ENABLE BIT(0) +#define OB_WIN_MATCH_MS(win) OB_WIN_REG_ADDR(win, 0x04) +#define OB_WIN_REMAP_LS(win) OB_WIN_REG_ADDR(win, 0x08) +#define OB_WIN_REMAP_MS(win) OB_WIN_REG_ADDR(win, 0x0c) +#define OB_WIN_MASK_LS(win) OB_WIN_REG_ADDR(win, 0x10) +#define OB_WIN_MASK_MS(win) OB_WIN_REG_ADDR(win, 0x14) +#define OB_WIN_ACTIONS(win) OB_WIN_REG_ADDR(win, 0x18) +#define OB_WIN_DEFAULT_ACTIONS (OB_WIN_ACTIONS(OB_WIN_COUNT-1) + 0x4) +#define OB_WIN_FUNC_NUM_MASK GENMASK(31, 24) +#define OB_WIN_FUNC_NUM_SHIFT 24 +#define OB_WIN_FUNC_NUM_ENABLE BIT(23) +#define OB_WIN_BUS_NUM_BITS_MASK GENMASK(22, 20) +#define OB_WIN_BUS_NUM_BITS_SHIFT 20 +#define OB_WIN_MSG_CODE_ENABLE BIT(22) +#define OB_WIN_MSG_CODE_MASK GENMASK(21, 14) +#define OB_WIN_MSG_CODE_SHIFT 14 +#define OB_WIN_MSG_PAYLOAD_LEN BIT(12) +#define OB_WIN_ATTR_ENABLE BIT(11) +#define OB_WIN_ATTR_TC_MASK GENMASK(10, 8) +#define OB_WIN_ATTR_TC_SHIFT 8 +#define OB_WIN_ATTR_RELAXED BIT(7) +#define OB_WIN_ATTR_NOSNOOP BIT(6) +#define OB_WIN_ATTR_POISON BIT(5) +#define OB_WIN_ATTR_IDO BIT(4) +#define OB_WIN_TYPE_MASK GENMASK(3, 0) +#define OB_WIN_TYPE_SHIFT 0 +#define OB_WIN_TYPE_MEM 0x0 +#define OB_WIN_TYPE_IO 0x4 +#define OB_WIN_TYPE_CONFIG_TYPE0 0x8 +#define OB_WIN_TYPE_CONFIG_TYPE1 0x9 +#define OB_WIN_TYPE_MSG 0xc + +/* LMI registers base address and register offsets */ +#define LMI_BASE_ADDR 0x6000 +#define CFG_REG (LMI_BASE_ADDR + 0x0) +#define LTSSM_SHIFT 24 +#define LTSSM_MASK 0x3f +#define RC_BAR_CONFIG 0x300 + +/* LTSSM values in CFG_REG */ +enum { + LTSSM_DETECT_QUIET = 0x0, + LTSSM_DETECT_ACTIVE = 0x1, + LTSSM_POLLING_ACTIVE = 0x2, + LTSSM_POLLING_COMPLIANCE = 0x3, + LTSSM_POLLING_CONFIGURATION = 0x4, + LTSSM_CONFIG_LINKWIDTH_START = 0x5, + LTSSM_CONFIG_LINKWIDTH_ACCEPT = 0x6, + LTSSM_CONFIG_LANENUM_ACCEPT = 0x7, + LTSSM_CONFIG_LANENUM_WAIT = 0x8, + LTSSM_CONFIG_COMPLETE = 0x9, + LTSSM_CONFIG_IDLE = 0xa, + LTSSM_RECOVERY_RCVR_LOCK = 0xb, + LTSSM_RECOVERY_SPEED = 0xc, + LTSSM_RECOVERY_RCVR_CFG = 0xd, + LTSSM_RECOVERY_IDLE = 0xe, + LTSSM_L0 = 0x10, + LTSSM_RX_L0S_ENTRY = 0x11, + LTSSM_RX_L0S_IDLE = 0x12, + LTSSM_RX_L0S_FTS = 0x13, + LTSSM_TX_L0S_ENTRY = 0x14, + LTSSM_TX_L0S_IDLE = 0x15, + LTSSM_TX_L0S_FTS = 0x16, + LTSSM_L1_ENTRY = 0x17, + LTSSM_L1_IDLE = 0x18, + LTSSM_L2_IDLE = 0x19, + LTSSM_L2_TRANSMIT_WAKE = 0x1a, + LTSSM_DISABLED = 0x20, + LTSSM_LOOPBACK_ENTRY_MASTER = 0x21, + LTSSM_LOOPBACK_ACTIVE_MASTER = 0x22, + LTSSM_LOOPBACK_EXIT_MASTER = 0x23, + LTSSM_LOOPBACK_ENTRY_SLAVE = 0x24, + LTSSM_LOOPBACK_ACTIVE_SLAVE = 0x25, + LTSSM_LOOPBACK_EXIT_SLAVE = 0x26, + LTSSM_HOT_RESET = 0x27, + LTSSM_RECOVERY_EQUALIZATION_PHASE0 = 0x28, + LTSSM_RECOVERY_EQUALIZATION_PHASE1 = 0x29, + LTSSM_RECOVERY_EQUALIZATION_PHASE2 = 0x2a, + LTSSM_RECOVERY_EQUALIZATION_PHASE3 = 0x2b, +}; + +#define VENDOR_ID_REG (LMI_BASE_ADDR + 0x44) + +/* PCIe core controller registers */ +#define CTRL_CORE_BASE_ADDR 0x18000 +#define CTRL_CONFIG_REG (CTRL_CORE_BASE_ADDR + 0x0) +#define CTRL_MODE_SHIFT 0x0 +#define CTRL_MODE_MASK 0x1 +#define PCIE_CORE_MODE_DIRECT 0x0 +#define PCIE_CORE_MODE_COMMAND 0x1 + +/* PCIe Central Interrupts Registers */ +#define CENTRAL_INT_BASE_ADDR 0x1b000 +#define HOST_CTRL_INT_STATUS_REG (CENTRAL_INT_BASE_ADDR + 0x0) +#define HOST_CTRL_INT_MASK_REG (CENTRAL_INT_BASE_ADDR + 0x4) +#define PCIE_IRQ_CMDQ_INT BIT(0) +#define PCIE_IRQ_MSI_STATUS_INT BIT(1) +#define PCIE_IRQ_CMD_SENT_DONE BIT(3) +#define PCIE_IRQ_DMA_INT BIT(4) +#define PCIE_IRQ_IB_DXFERDONE BIT(5) +#define PCIE_IRQ_OB_DXFERDONE BIT(6) +#define PCIE_IRQ_OB_RXFERDONE BIT(7) +#define PCIE_IRQ_COMPQ_INT BIT(12) +#define PCIE_IRQ_DIR_RD_DDR_DET BIT(13) +#define PCIE_IRQ_DIR_WR_DDR_DET BIT(14) +#define PCIE_IRQ_CORE_INT BIT(16) +#define PCIE_IRQ_CORE_INT_PIO BIT(17) +#define PCIE_IRQ_DPMU_INT BIT(18) +#define PCIE_IRQ_PCIE_MIS_INT BIT(19) +#define PCIE_IRQ_MSI_INT1_DET BIT(20) +#define PCIE_IRQ_MSI_INT2_DET BIT(21) +#define PCIE_IRQ_RC_DBELL_DET BIT(22) +#define PCIE_IRQ_EP_STATUS BIT(23) +#define PCIE_IRQ_ALL_MASK GENMASK(31, 0) +#define PCIE_IRQ_ENABLE_INTS_MASK PCIE_IRQ_CORE_INT + +/* Transaction types */ +#define PCIE_CONFIG_RD_TYPE0 0x8 +#define PCIE_CONFIG_RD_TYPE1 0x9 +#define PCIE_CONFIG_WR_TYPE0 0xa +#define PCIE_CONFIG_WR_TYPE1 0xb + +#define PIO_RETRY_CNT 750000 /* 1.5 s */ +#define PIO_RETRY_DELAY 2 /* 2 us*/ + +#define LINK_WAIT_MAX_RETRIES 10 +#define LINK_WAIT_USLEEP_MIN 90000 +#define LINK_WAIT_USLEEP_MAX 100000 +#define RETRAIN_WAIT_MAX_RETRIES 10 +#define RETRAIN_WAIT_USLEEP_US 2000 + +#define MSI_IRQ_NUM 32 + +#define CFG_RD_CRS_VAL 0xffff0001 + +struct advk_pcie { + struct platform_device *pdev; + void __iomem *base; + struct { + phys_addr_t match; + phys_addr_t remap; + phys_addr_t mask; + u32 actions; + } wins[OB_WIN_COUNT]; + u8 wins_count; + struct irq_domain *rp_irq_domain; + struct irq_domain *irq_domain; + struct irq_chip irq_chip; + raw_spinlock_t irq_lock; + struct irq_domain *msi_domain; + struct irq_domain *msi_inner_domain; + raw_spinlock_t msi_irq_lock; + DECLARE_BITMAP(msi_used, MSI_IRQ_NUM); + struct mutex msi_used_lock; + int link_gen; + struct pci_bridge_emul bridge; + struct gpio_desc *reset_gpio; + struct phy *phy; +}; + +static inline void advk_writel(struct advk_pcie *pcie, u32 val, u64 reg) +{ + writel(val, pcie->base + reg); +} + +static inline u32 advk_readl(struct advk_pcie *pcie, u64 reg) +{ + return readl(pcie->base + reg); +} + +static u8 advk_pcie_ltssm_state(struct advk_pcie *pcie) +{ + u32 val; + u8 ltssm_state; + + val = advk_readl(pcie, CFG_REG); + ltssm_state = (val >> LTSSM_SHIFT) & LTSSM_MASK; + return ltssm_state; +} + +static inline bool advk_pcie_link_up(struct advk_pcie *pcie) +{ + /* check if LTSSM is in normal operation - some L* state */ + u8 ltssm_state = advk_pcie_ltssm_state(pcie); + return ltssm_state >= LTSSM_L0 && ltssm_state < LTSSM_DISABLED; +} + +static inline bool advk_pcie_link_active(struct advk_pcie *pcie) +{ + /* + * According to PCIe Base specification 3.0, Table 4-14: Link + * Status Mapped to the LTSSM, and 4.2.6.3.6 Configuration.Idle + * is Link Up mapped to LTSSM Configuration.Idle, Recovery, L0, + * L0s, L1 and L2 states. And according to 3.2.1. Data Link + * Control and Management State Machine Rules is DL Up status + * reported in DL Active state. + */ + u8 ltssm_state = advk_pcie_ltssm_state(pcie); + return ltssm_state >= LTSSM_CONFIG_IDLE && ltssm_state < LTSSM_DISABLED; +} + +static inline bool advk_pcie_link_training(struct advk_pcie *pcie) +{ + /* + * According to PCIe Base specification 3.0, Table 4-14: Link + * Status Mapped to the LTSSM is Link Training mapped to LTSSM + * Configuration and Recovery states. + */ + u8 ltssm_state = advk_pcie_ltssm_state(pcie); + return ((ltssm_state >= LTSSM_CONFIG_LINKWIDTH_START && + ltssm_state < LTSSM_L0) || + (ltssm_state >= LTSSM_RECOVERY_EQUALIZATION_PHASE0 && + ltssm_state <= LTSSM_RECOVERY_EQUALIZATION_PHASE3)); +} + +static int advk_pcie_wait_for_link(struct advk_pcie *pcie) +{ + int retries; + + /* check if the link is up or not */ + for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { + if (advk_pcie_link_up(pcie)) + return 0; + + usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX); + } + + return -ETIMEDOUT; +} + +static void advk_pcie_wait_for_retrain(struct advk_pcie *pcie) +{ + size_t retries; + + for (retries = 0; retries < RETRAIN_WAIT_MAX_RETRIES; ++retries) { + if (advk_pcie_link_training(pcie)) + break; + udelay(RETRAIN_WAIT_USLEEP_US); + } +} + +static void advk_pcie_issue_perst(struct advk_pcie *pcie) +{ + if (!pcie->reset_gpio) + return; + + /* 10ms delay is needed for some cards */ + dev_info(&pcie->pdev->dev, "issuing PERST via reset GPIO for 10ms\n"); + gpiod_set_value_cansleep(pcie->reset_gpio, 1); + usleep_range(10000, 11000); + gpiod_set_value_cansleep(pcie->reset_gpio, 0); +} + +static void advk_pcie_train_link(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + u32 reg; + int ret; + + /* + * Setup PCIe rev / gen compliance based on device tree property + * 'max-link-speed' which also forces maximal link speed. + */ + reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + reg &= ~PCIE_GEN_SEL_MSK; + if (pcie->link_gen == 3) + reg |= SPEED_GEN_3; + else if (pcie->link_gen == 2) + reg |= SPEED_GEN_2; + else + reg |= SPEED_GEN_1; + advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + + /* + * Set maximal link speed value also into PCIe Link Control 2 register. + * Armada 3700 Functional Specification says that default value is based + * on SPEED_GEN but tests showed that default value is always 8.0 GT/s. + */ + reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2); + reg &= ~PCI_EXP_LNKCTL2_TLS; + if (pcie->link_gen == 3) + reg |= PCI_EXP_LNKCTL2_TLS_8_0GT; + else if (pcie->link_gen == 2) + reg |= PCI_EXP_LNKCTL2_TLS_5_0GT; + else + reg |= PCI_EXP_LNKCTL2_TLS_2_5GT; + advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_LNKCTL2); + + /* Enable link training after selecting PCIe generation */ + reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + reg |= LINK_TRAINING_EN; + advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + + /* + * Reset PCIe card via PERST# signal. Some cards are not detected + * during link training when they are in some non-initial state. + */ + advk_pcie_issue_perst(pcie); + + /* + * PERST# signal could have been asserted by pinctrl subsystem before + * probe() callback has been called or issued explicitly by reset gpio + * function advk_pcie_issue_perst(), making the endpoint going into + * fundamental reset. As required by PCI Express spec (PCI Express + * Base Specification, REV. 4.0 PCI Express, February 19 2014, 6.6.1 + * Conventional Reset) a delay for at least 100ms after such a reset + * before sending a Configuration Request to the device is needed. + * So wait until PCIe link is up. Function advk_pcie_wait_for_link() + * waits for link at least 900ms. + */ + ret = advk_pcie_wait_for_link(pcie); + if (ret < 0) + dev_err(dev, "link never came up\n"); + else + dev_info(dev, "link up\n"); +} + +/* + * Set PCIe address window register which could be used for memory + * mapping. + */ +static void advk_pcie_set_ob_win(struct advk_pcie *pcie, u8 win_num, + phys_addr_t match, phys_addr_t remap, + phys_addr_t mask, u32 actions) +{ + advk_writel(pcie, OB_WIN_ENABLE | + lower_32_bits(match), OB_WIN_MATCH_LS(win_num)); + advk_writel(pcie, upper_32_bits(match), OB_WIN_MATCH_MS(win_num)); + advk_writel(pcie, lower_32_bits(remap), OB_WIN_REMAP_LS(win_num)); + advk_writel(pcie, upper_32_bits(remap), OB_WIN_REMAP_MS(win_num)); + advk_writel(pcie, lower_32_bits(mask), OB_WIN_MASK_LS(win_num)); + advk_writel(pcie, upper_32_bits(mask), OB_WIN_MASK_MS(win_num)); + advk_writel(pcie, actions, OB_WIN_ACTIONS(win_num)); +} + +static void advk_pcie_disable_ob_win(struct advk_pcie *pcie, u8 win_num) +{ + advk_writel(pcie, 0, OB_WIN_MATCH_LS(win_num)); + advk_writel(pcie, 0, OB_WIN_MATCH_MS(win_num)); + advk_writel(pcie, 0, OB_WIN_REMAP_LS(win_num)); + advk_writel(pcie, 0, OB_WIN_REMAP_MS(win_num)); + advk_writel(pcie, 0, OB_WIN_MASK_LS(win_num)); + advk_writel(pcie, 0, OB_WIN_MASK_MS(win_num)); + advk_writel(pcie, 0, OB_WIN_ACTIONS(win_num)); +} + +static void advk_pcie_setup_hw(struct advk_pcie *pcie) +{ + phys_addr_t msi_addr; + u32 reg; + int i; + + /* + * Configure PCIe Reference clock. Direction is from the PCIe + * controller to the endpoint card, so enable transmitting of + * Reference clock differential signal off-chip and disable + * receiving off-chip differential signal. + */ + reg = advk_readl(pcie, PCIE_CORE_REF_CLK_REG); + reg |= PCIE_CORE_REF_CLK_TX_ENABLE; + reg &= ~PCIE_CORE_REF_CLK_RX_ENABLE; + advk_writel(pcie, reg, PCIE_CORE_REF_CLK_REG); + + /* Set to Direct mode */ + reg = advk_readl(pcie, CTRL_CONFIG_REG); + reg &= ~(CTRL_MODE_MASK << CTRL_MODE_SHIFT); + reg |= ((PCIE_CORE_MODE_DIRECT & CTRL_MODE_MASK) << CTRL_MODE_SHIFT); + advk_writel(pcie, reg, CTRL_CONFIG_REG); + + /* Set PCI global control register to RC mode */ + reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + reg |= (IS_RC_MSK << IS_RC_SHIFT); + advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + + /* + * Replace incorrect PCI vendor id value 0x1b4b by correct value 0x11ab. + * VENDOR_ID_REG contains vendor id in low 16 bits and subsystem vendor + * id in high 16 bits. Updating this register changes readback value of + * read-only vendor id bits in PCIE_CORE_DEV_ID_REG register. Workaround + * for erratum 4.1: "The value of device and vendor ID is incorrect". + */ + reg = (PCI_VENDOR_ID_MARVELL << 16) | PCI_VENDOR_ID_MARVELL; + advk_writel(pcie, reg, VENDOR_ID_REG); + + /* + * Change Class Code of PCI Bridge device to PCI Bridge (0x600400), + * because the default value is Mass storage controller (0x010400). + * + * Note that this Aardvark PCI Bridge does not have compliant Type 1 + * Configuration Space and it even cannot be accessed via Aardvark's + * PCI config space access method. Something like config space is + * available in internal Aardvark registers starting at offset 0x0 + * and is reported as Type 0. In range 0x10 - 0x34 it has totally + * different registers. + * + * Therefore driver uses emulation of PCI Bridge which emulates + * access to configuration space via internal Aardvark registers or + * emulated configuration buffer. + */ + reg = advk_readl(pcie, PCIE_CORE_DEV_REV_REG); + reg &= ~0xffffff00; + reg |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8; + advk_writel(pcie, reg, PCIE_CORE_DEV_REV_REG); + + /* Disable Root Bridge I/O space, memory space and bus mastering */ + reg = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); + reg &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); + advk_writel(pcie, reg, PCIE_CORE_CMD_STATUS_REG); + + /* Set Advanced Error Capabilities and Control PF0 register */ + reg = PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX | + PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN | + PCIE_CORE_ERR_CAPCTL_ECRC_CHCK | + PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV; + advk_writel(pcie, reg, PCIE_CORE_ERR_CAPCTL_REG); + + /* Set PCIe Device Control register */ + reg = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL); + reg &= ~PCI_EXP_DEVCTL_RELAX_EN; + reg &= ~PCI_EXP_DEVCTL_NOSNOOP_EN; + reg &= ~PCI_EXP_DEVCTL_PAYLOAD; + reg &= ~PCI_EXP_DEVCTL_READRQ; + reg |= PCI_EXP_DEVCTL_PAYLOAD_512B; + reg |= PCI_EXP_DEVCTL_READRQ_512B; + advk_writel(pcie, reg, PCIE_CORE_PCIEXP_CAP + PCI_EXP_DEVCTL); + + /* Program PCIe Control 2 to disable strict ordering */ + reg = PCIE_CORE_CTRL2_RESERVED | + PCIE_CORE_CTRL2_TD_ENABLE; + advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG); + + /* Set lane X1 */ + reg = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + reg &= ~LANE_CNT_MSK; + reg |= LANE_COUNT_1; + advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG); + + /* Set MSI address */ + msi_addr = virt_to_phys(pcie); + advk_writel(pcie, lower_32_bits(msi_addr), PCIE_MSI_ADDR_LOW_REG); + advk_writel(pcie, upper_32_bits(msi_addr), PCIE_MSI_ADDR_HIGH_REG); + + /* Enable MSI */ + reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG); + reg |= PCIE_CORE_CTRL2_MSI_ENABLE; + advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG); + + /* Clear all interrupts */ + advk_writel(pcie, PCIE_MSI_ALL_MASK, PCIE_MSI_STATUS_REG); + advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_REG); + advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_REG); + advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG); + + /* Disable All ISR0/1 and MSI Sources */ + advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_MASK_REG); + advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG); + advk_writel(pcie, PCIE_MSI_ALL_MASK, PCIE_MSI_MASK_REG); + + /* Unmask summary MSI interrupt */ + reg = advk_readl(pcie, PCIE_ISR0_MASK_REG); + reg &= ~PCIE_ISR0_MSI_INT_PENDING; + advk_writel(pcie, reg, PCIE_ISR0_MASK_REG); + + /* Unmask PME interrupt for processing of PME requester */ + reg = advk_readl(pcie, PCIE_ISR0_MASK_REG); + reg &= ~PCIE_MSG_PM_PME_MASK; + advk_writel(pcie, reg, PCIE_ISR0_MASK_REG); + + /* Enable summary interrupt for GIC SPI source */ + reg = PCIE_IRQ_ALL_MASK & (~PCIE_IRQ_ENABLE_INTS_MASK); + advk_writel(pcie, reg, HOST_CTRL_INT_MASK_REG); + + /* + * Enable AXI address window location generation: + * When it is enabled, the default outbound window + * configurations (Default User Field: 0xD0074CFC) + * are used to transparent address translation for + * the outbound transactions. Thus, PCIe address + * windows are not required for transparent memory + * access when default outbound window configuration + * is set for memory access. + */ + reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG); + reg |= PCIE_CORE_CTRL2_OB_WIN_ENABLE; + advk_writel(pcie, reg, PCIE_CORE_CTRL2_REG); + + /* + * Set memory access in Default User Field so it + * is not required to configure PCIe address for + * transparent memory access. + */ + advk_writel(pcie, OB_WIN_TYPE_MEM, OB_WIN_DEFAULT_ACTIONS); + + /* + * Bypass the address window mapping for PIO: + * Since PIO access already contains all required + * info over AXI interface by PIO registers, the + * address window is not required. + */ + reg = advk_readl(pcie, PIO_CTRL); + reg |= PIO_CTRL_ADDR_WIN_DISABLE; + advk_writel(pcie, reg, PIO_CTRL); + + /* + * Configure PCIe address windows for non-memory or + * non-transparent access as by default PCIe uses + * transparent memory access. + */ + for (i = 0; i < pcie->wins_count; i++) + advk_pcie_set_ob_win(pcie, i, + pcie->wins[i].match, pcie->wins[i].remap, + pcie->wins[i].mask, pcie->wins[i].actions); + + /* Disable remaining PCIe outbound windows */ + for (i = pcie->wins_count; i < OB_WIN_COUNT; i++) + advk_pcie_disable_ob_win(pcie, i); + + advk_pcie_train_link(pcie); +} + +static int advk_pcie_check_pio_status(struct advk_pcie *pcie, bool allow_crs, u32 *val) +{ + struct device *dev = &pcie->pdev->dev; + u32 reg; + unsigned int status; + char *strcomp_status, *str_posted; + int ret; + + reg = advk_readl(pcie, PIO_STAT); + status = (reg & PIO_COMPLETION_STATUS_MASK) >> + PIO_COMPLETION_STATUS_SHIFT; + + /* + * According to HW spec, the PIO status check sequence as below: + * 1) even if COMPLETION_STATUS(bit9:7) indicates successful, + * it still needs to check Error Status(bit11), only when this bit + * indicates no error happen, the operation is successful. + * 2) value Unsupported Request(1) of COMPLETION_STATUS(bit9:7) only + * means a PIO write error, and for PIO read it is successful with + * a read value of 0xFFFFFFFF. + * 3) value Completion Retry Status(CRS) of COMPLETION_STATUS(bit9:7) + * only means a PIO write error, and for PIO read it is successful + * with a read value of 0xFFFF0001. + * 4) value Completer Abort (CA) of COMPLETION_STATUS(bit9:7) means + * error for both PIO read and PIO write operation. + * 5) other errors are indicated as 'unknown'. + */ + switch (status) { + case PIO_COMPLETION_STATUS_OK: + if (reg & PIO_ERR_STATUS) { + strcomp_status = "COMP_ERR"; + ret = -EFAULT; + break; + } + /* Get the read result */ + if (val) + *val = advk_readl(pcie, PIO_RD_DATA); + /* No error */ + strcomp_status = NULL; + ret = 0; + break; + case PIO_COMPLETION_STATUS_UR: + strcomp_status = "UR"; + ret = -EOPNOTSUPP; + break; + case PIO_COMPLETION_STATUS_CRS: + if (allow_crs && val) { + /* PCIe r4.0, sec 2.3.2, says: + * If CRS Software Visibility is enabled: + * For a Configuration Read Request that includes both + * bytes of the Vendor ID field of a device Function's + * Configuration Space Header, the Root Complex must + * complete the Request to the host by returning a + * read-data value of 0001h for the Vendor ID field and + * all '1's for any additional bytes included in the + * request. + * + * So CRS in this case is not an error status. + */ + *val = CFG_RD_CRS_VAL; + strcomp_status = NULL; + ret = 0; + break; + } + /* PCIe r4.0, sec 2.3.2, says: + * If CRS Software Visibility is not enabled, the Root Complex + * must re-issue the Configuration Request as a new Request. + * If CRS Software Visibility is enabled: For a Configuration + * Write Request or for any other Configuration Read Request, + * the Root Complex must re-issue the Configuration Request as + * a new Request. + * A Root Complex implementation may choose to limit the number + * of Configuration Request/CRS Completion Status loops before + * determining that something is wrong with the target of the + * Request and taking appropriate action, e.g., complete the + * Request to the host as a failed transaction. + * + * So return -EAGAIN and caller (pci-aardvark.c driver) will + * re-issue request again up to the PIO_RETRY_CNT retries. + */ + strcomp_status = "CRS"; + ret = -EAGAIN; + break; + case PIO_COMPLETION_STATUS_CA: + strcomp_status = "CA"; + ret = -ECANCELED; + break; + default: + strcomp_status = "Unknown"; + ret = -EINVAL; + break; + } + + if (!strcomp_status) + return ret; + + if (reg & PIO_NON_POSTED_REQ) + str_posted = "Non-posted"; + else + str_posted = "Posted"; + + dev_dbg(dev, "%s PIO Response Status: %s, %#x @ %#x\n", + str_posted, strcomp_status, reg, advk_readl(pcie, PIO_ADDR_LS)); + + return ret; +} + +static int advk_pcie_wait_pio(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + int i; + + for (i = 1; i <= PIO_RETRY_CNT; i++) { + u32 start, isr; + + start = advk_readl(pcie, PIO_START); + isr = advk_readl(pcie, PIO_ISR); + if (!start && isr) + return i; + udelay(PIO_RETRY_DELAY); + } + + dev_err(dev, "PIO read/write transfer time out\n"); + return -ETIMEDOUT; +} + +static pci_bridge_emul_read_status_t +advk_pci_bridge_emul_base_conf_read(struct pci_bridge_emul *bridge, + int reg, u32 *value) +{ + struct advk_pcie *pcie = bridge->data; + + switch (reg) { + case PCI_COMMAND: + *value = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); + return PCI_BRIDGE_EMUL_HANDLED; + + case PCI_INTERRUPT_LINE: { + /* + * From the whole 32bit register we support reading from HW only + * two bits: PCI_BRIDGE_CTL_BUS_RESET and PCI_BRIDGE_CTL_SERR. + * Other bits are retrieved only from emulated config buffer. + */ + __le32 *cfgspace = (__le32 *)&bridge->conf; + u32 val = le32_to_cpu(cfgspace[PCI_INTERRUPT_LINE / 4]); + if (advk_readl(pcie, PCIE_ISR0_MASK_REG) & PCIE_ISR0_ERR_MASK) + val &= ~(PCI_BRIDGE_CTL_SERR << 16); + else + val |= PCI_BRIDGE_CTL_SERR << 16; + if (advk_readl(pcie, PCIE_CORE_CTRL1_REG) & HOT_RESET_GEN) + val |= PCI_BRIDGE_CTL_BUS_RESET << 16; + else + val &= ~(PCI_BRIDGE_CTL_BUS_RESET << 16); + *value = val; + return PCI_BRIDGE_EMUL_HANDLED; + } + + default: + return PCI_BRIDGE_EMUL_NOT_HANDLED; + } +} + +static void +advk_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge, + int reg, u32 old, u32 new, u32 mask) +{ + struct advk_pcie *pcie = bridge->data; + + switch (reg) { + case PCI_COMMAND: + advk_writel(pcie, new, PCIE_CORE_CMD_STATUS_REG); + break; + + case PCI_INTERRUPT_LINE: + /* + * According to Figure 6-3: Pseudo Logic Diagram for Error + * Message Controls in PCIe base specification, SERR# Enable bit + * in Bridge Control register enable receiving of ERR_* messages + */ + if (mask & (PCI_BRIDGE_CTL_SERR << 16)) { + u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG); + if (new & (PCI_BRIDGE_CTL_SERR << 16)) + val &= ~PCIE_ISR0_ERR_MASK; + else + val |= PCIE_ISR0_ERR_MASK; + advk_writel(pcie, val, PCIE_ISR0_MASK_REG); + } + if (mask & (PCI_BRIDGE_CTL_BUS_RESET << 16)) { + u32 val = advk_readl(pcie, PCIE_CORE_CTRL1_REG); + if (new & (PCI_BRIDGE_CTL_BUS_RESET << 16)) + val |= HOT_RESET_GEN; + else + val &= ~HOT_RESET_GEN; + advk_writel(pcie, val, PCIE_CORE_CTRL1_REG); + } + break; + + default: + break; + } +} + +static pci_bridge_emul_read_status_t +advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, + int reg, u32 *value) +{ + struct advk_pcie *pcie = bridge->data; + + + switch (reg) { + /* + * PCI_EXP_SLTCAP, PCI_EXP_SLTCTL, PCI_EXP_RTCTL and PCI_EXP_RTSTA are + * also supported, but do not need to be handled here, because their + * values are stored in emulated config space buffer, and we read them + * from there when needed. + */ + + case PCI_EXP_LNKCAP: { + u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg); + /* + * PCI_EXP_LNKCAP_DLLLARC bit is hardwired in aardvark HW to 0. + * But support for PCI_EXP_LNKSTA_DLLLA is emulated via ltssm + * state so explicitly enable PCI_EXP_LNKCAP_DLLLARC flag. + */ + val |= PCI_EXP_LNKCAP_DLLLARC; + *value = val; + return PCI_BRIDGE_EMUL_HANDLED; + } + + case PCI_EXP_LNKCTL: { + /* u32 contains both PCI_EXP_LNKCTL and PCI_EXP_LNKSTA */ + u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg) & + ~(PCI_EXP_LNKSTA_LT << 16); + if (advk_pcie_link_training(pcie)) + val |= (PCI_EXP_LNKSTA_LT << 16); + if (advk_pcie_link_active(pcie)) + val |= (PCI_EXP_LNKSTA_DLLLA << 16); + *value = val; + return PCI_BRIDGE_EMUL_HANDLED; + } + + case PCI_EXP_DEVCAP: + case PCI_EXP_DEVCTL: + case PCI_EXP_DEVCAP2: + case PCI_EXP_DEVCTL2: + case PCI_EXP_LNKCAP2: + case PCI_EXP_LNKCTL2: + *value = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg); + return PCI_BRIDGE_EMUL_HANDLED; + + default: + return PCI_BRIDGE_EMUL_NOT_HANDLED; + } + +} + +static void +advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge, + int reg, u32 old, u32 new, u32 mask) +{ + struct advk_pcie *pcie = bridge->data; + + switch (reg) { + case PCI_EXP_LNKCTL: + advk_writel(pcie, new, PCIE_CORE_PCIEXP_CAP + reg); + if (new & PCI_EXP_LNKCTL_RL) + advk_pcie_wait_for_retrain(pcie); + break; + + case PCI_EXP_RTCTL: { + u16 rootctl = le16_to_cpu(bridge->pcie_conf.rootctl); + /* Only emulation of PMEIE and CRSSVE bits is provided */ + rootctl &= PCI_EXP_RTCTL_PMEIE | PCI_EXP_RTCTL_CRSSVE; + bridge->pcie_conf.rootctl = cpu_to_le16(rootctl); + break; + } + + /* + * PCI_EXP_RTSTA is also supported, but does not need to be handled + * here, because its value is stored in emulated config space buffer, + * and we write it there when needed. + */ + + case PCI_EXP_DEVCTL: + case PCI_EXP_DEVCTL2: + case PCI_EXP_LNKCTL2: + advk_writel(pcie, new, PCIE_CORE_PCIEXP_CAP + reg); + break; + + default: + break; + } +} + +static pci_bridge_emul_read_status_t +advk_pci_bridge_emul_ext_conf_read(struct pci_bridge_emul *bridge, + int reg, u32 *value) +{ + struct advk_pcie *pcie = bridge->data; + + switch (reg) { + case 0: + *value = advk_readl(pcie, PCIE_CORE_PCIERR_CAP + reg); + + /* + * PCI_EXT_CAP_NEXT bits are set to offset 0x150, but Armada + * 3700 Functional Specification does not document registers + * at those addresses. + * + * Thus we clear PCI_EXT_CAP_NEXT bits to make Advanced Error + * Reporting Capability header the last Extended Capability. + * If we obtain documentation for those registers in the + * future, this can be changed. + */ + *value &= 0x000fffff; + return PCI_BRIDGE_EMUL_HANDLED; + + case PCI_ERR_UNCOR_STATUS: + case PCI_ERR_UNCOR_MASK: + case PCI_ERR_UNCOR_SEVER: + case PCI_ERR_COR_STATUS: + case PCI_ERR_COR_MASK: + case PCI_ERR_CAP: + case PCI_ERR_HEADER_LOG + 0: + case PCI_ERR_HEADER_LOG + 4: + case PCI_ERR_HEADER_LOG + 8: + case PCI_ERR_HEADER_LOG + 12: + case PCI_ERR_ROOT_COMMAND: + case PCI_ERR_ROOT_STATUS: + case PCI_ERR_ROOT_ERR_SRC: + *value = advk_readl(pcie, PCIE_CORE_PCIERR_CAP + reg); + return PCI_BRIDGE_EMUL_HANDLED; + + default: + return PCI_BRIDGE_EMUL_NOT_HANDLED; + } +} + +static void +advk_pci_bridge_emul_ext_conf_write(struct pci_bridge_emul *bridge, + int reg, u32 old, u32 new, u32 mask) +{ + struct advk_pcie *pcie = bridge->data; + + switch (reg) { + /* These are W1C registers, so clear other bits */ + case PCI_ERR_UNCOR_STATUS: + case PCI_ERR_COR_STATUS: + case PCI_ERR_ROOT_STATUS: + new &= mask; + fallthrough; + + case PCI_ERR_UNCOR_MASK: + case PCI_ERR_UNCOR_SEVER: + case PCI_ERR_COR_MASK: + case PCI_ERR_CAP: + case PCI_ERR_HEADER_LOG + 0: + case PCI_ERR_HEADER_LOG + 4: + case PCI_ERR_HEADER_LOG + 8: + case PCI_ERR_HEADER_LOG + 12: + case PCI_ERR_ROOT_COMMAND: + case PCI_ERR_ROOT_ERR_SRC: + advk_writel(pcie, new, PCIE_CORE_PCIERR_CAP + reg); + break; + + default: + break; + } +} + +static const struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = { + .read_base = advk_pci_bridge_emul_base_conf_read, + .write_base = advk_pci_bridge_emul_base_conf_write, + .read_pcie = advk_pci_bridge_emul_pcie_conf_read, + .write_pcie = advk_pci_bridge_emul_pcie_conf_write, + .read_ext = advk_pci_bridge_emul_ext_conf_read, + .write_ext = advk_pci_bridge_emul_ext_conf_write, +}; + +/* + * Initialize the configuration space of the PCI-to-PCI bridge + * associated with the given PCIe interface. + */ +static int advk_sw_pci_bridge_init(struct advk_pcie *pcie) +{ + struct pci_bridge_emul *bridge = &pcie->bridge; + + bridge->conf.vendor = + cpu_to_le16(advk_readl(pcie, PCIE_CORE_DEV_ID_REG) & 0xffff); + bridge->conf.device = + cpu_to_le16(advk_readl(pcie, PCIE_CORE_DEV_ID_REG) >> 16); + bridge->conf.class_revision = + cpu_to_le32(advk_readl(pcie, PCIE_CORE_DEV_REV_REG) & 0xff); + + /* Support 32 bits I/O addressing */ + bridge->conf.iobase = PCI_IO_RANGE_TYPE_32; + bridge->conf.iolimit = PCI_IO_RANGE_TYPE_32; + + /* Support 64 bits memory pref */ + bridge->conf.pref_mem_base = cpu_to_le16(PCI_PREF_RANGE_TYPE_64); + bridge->conf.pref_mem_limit = cpu_to_le16(PCI_PREF_RANGE_TYPE_64); + + /* Support interrupt A for MSI feature */ + bridge->conf.intpin = PCI_INTERRUPT_INTA; + + /* + * Aardvark HW provides PCIe Capability structure in version 2 and + * indicate slot support, which is emulated. + */ + bridge->pcie_conf.cap = cpu_to_le16(2 | PCI_EXP_FLAGS_SLOT); + + /* + * Set Presence Detect State bit permanently since there is no support + * for unplugging the card nor detecting whether it is plugged. (If a + * platform exists in the future that supports it, via a GPIO for + * example, it should be implemented via this bit.) + * + * Set physical slot number to 1 since there is only one port and zero + * value is reserved for ports within the same silicon as Root Port + * which is not our case. + */ + bridge->pcie_conf.slotcap = cpu_to_le32(FIELD_PREP(PCI_EXP_SLTCAP_PSN, + 1)); + bridge->pcie_conf.slotsta = cpu_to_le16(PCI_EXP_SLTSTA_PDS); + + /* Indicates supports for Completion Retry Status */ + bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_CRSVIS); + + bridge->subsystem_vendor_id = advk_readl(pcie, PCIE_CORE_SSDEV_ID_REG) & 0xffff; + bridge->subsystem_id = advk_readl(pcie, PCIE_CORE_SSDEV_ID_REG) >> 16; + bridge->has_pcie = true; + bridge->pcie_start = PCIE_CORE_PCIEXP_CAP; + bridge->data = pcie; + bridge->ops = &advk_pci_bridge_emul_ops; + + return pci_bridge_emul_init(bridge, 0); +} + +static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus, + int devfn) +{ + if (pci_is_root_bus(bus) && PCI_SLOT(devfn) != 0) + return false; + + /* + * If the link goes down after we check for link-up, we have a problem: + * if a PIO request is executed while link-down, the whole controller + * gets stuck in a non-functional state, and even after link comes up + * again, PIO requests won't work anymore, and a reset of the whole PCIe + * controller is needed. Therefore we need to prevent sending PIO + * requests while the link is down. + */ + if (!pci_is_root_bus(bus) && !advk_pcie_link_up(pcie)) + return false; + + return true; +} + +static bool advk_pcie_pio_is_running(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + + /* + * Trying to start a new PIO transfer when previous has not completed + * cause External Abort on CPU which results in kernel panic: + * + * SError Interrupt on CPU0, code 0xbf000002 -- SError + * Kernel panic - not syncing: Asynchronous SError Interrupt + * + * Functions advk_pcie_rd_conf() and advk_pcie_wr_conf() are protected + * by raw_spin_lock_irqsave() at pci_lock_config() level to prevent + * concurrent calls at the same time. But because PIO transfer may take + * about 1.5s when link is down or card is disconnected, it means that + * advk_pcie_wait_pio() does not always have to wait for completion. + * + * Some versions of ARM Trusted Firmware handles this External Abort at + * EL3 level and mask it to prevent kernel panic. Relevant TF-A commit: + * https://git.trustedfirmware.org/TF-A/trusted-firmware-a.git/commit/?id=3c7dcdac5c50 + */ + if (advk_readl(pcie, PIO_START)) { + dev_err(dev, "Previous PIO read/write transfer is still running\n"); + return true; + } + + return false; +} + +static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn, + int where, int size, u32 *val) +{ + struct advk_pcie *pcie = bus->sysdata; + int retry_count; + bool allow_crs; + u32 reg; + int ret; + + if (!advk_pcie_valid_device(pcie, bus, devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (pci_is_root_bus(bus)) + return pci_bridge_emul_conf_read(&pcie->bridge, where, + size, val); + + /* + * Completion Retry Status is possible to return only when reading all + * 4 bytes from PCI_VENDOR_ID and PCI_DEVICE_ID registers at once and + * CRSSVE flag on Root Bridge is enabled. + */ + allow_crs = (where == PCI_VENDOR_ID) && (size == 4) && + (le16_to_cpu(pcie->bridge.pcie_conf.rootctl) & + PCI_EXP_RTCTL_CRSSVE); + + if (advk_pcie_pio_is_running(pcie)) + goto try_crs; + + /* Program the control register */ + reg = advk_readl(pcie, PIO_CTRL); + reg &= ~PIO_CTRL_TYPE_MASK; + if (pci_is_root_bus(bus->parent)) + reg |= PCIE_CONFIG_RD_TYPE0; + else + reg |= PCIE_CONFIG_RD_TYPE1; + advk_writel(pcie, reg, PIO_CTRL); + + /* Program the address registers */ + reg = ALIGN_DOWN(PCIE_ECAM_OFFSET(bus->number, devfn, where), 4); + advk_writel(pcie, reg, PIO_ADDR_LS); + advk_writel(pcie, 0, PIO_ADDR_MS); + + /* Program the data strobe */ + advk_writel(pcie, 0xf, PIO_WR_DATA_STRB); + + retry_count = 0; + do { + /* Clear PIO DONE ISR and start the transfer */ + advk_writel(pcie, 1, PIO_ISR); + advk_writel(pcie, 1, PIO_START); + + ret = advk_pcie_wait_pio(pcie); + if (ret < 0) + goto try_crs; + + retry_count += ret; + + /* Check PIO status and get the read result */ + ret = advk_pcie_check_pio_status(pcie, allow_crs, val); + } while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT); + + if (ret < 0) + goto fail; + + if (size == 1) + *val = (*val >> (8 * (where & 3))) & 0xff; + else if (size == 2) + *val = (*val >> (8 * (where & 3))) & 0xffff; + + return PCIBIOS_SUCCESSFUL; + +try_crs: + /* + * If it is possible, return Completion Retry Status so that caller + * tries to issue the request again instead of failing. + */ + if (allow_crs) { + *val = CFG_RD_CRS_VAL; + return PCIBIOS_SUCCESSFUL; + } + +fail: + *val = 0xffffffff; + return PCIBIOS_SET_FAILED; +} + +static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn, + int where, int size, u32 val) +{ + struct advk_pcie *pcie = bus->sysdata; + u32 reg; + u32 data_strobe = 0x0; + int retry_count; + int offset; + int ret; + + if (!advk_pcie_valid_device(pcie, bus, devfn)) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (pci_is_root_bus(bus)) + return pci_bridge_emul_conf_write(&pcie->bridge, where, + size, val); + + if (where % size) + return PCIBIOS_SET_FAILED; + + if (advk_pcie_pio_is_running(pcie)) + return PCIBIOS_SET_FAILED; + + /* Program the control register */ + reg = advk_readl(pcie, PIO_CTRL); + reg &= ~PIO_CTRL_TYPE_MASK; + if (pci_is_root_bus(bus->parent)) + reg |= PCIE_CONFIG_WR_TYPE0; + else + reg |= PCIE_CONFIG_WR_TYPE1; + advk_writel(pcie, reg, PIO_CTRL); + + /* Program the address registers */ + reg = ALIGN_DOWN(PCIE_ECAM_OFFSET(bus->number, devfn, where), 4); + advk_writel(pcie, reg, PIO_ADDR_LS); + advk_writel(pcie, 0, PIO_ADDR_MS); + + /* Calculate the write strobe */ + offset = where & 0x3; + reg = val << (8 * offset); + data_strobe = GENMASK(size - 1, 0) << offset; + + /* Program the data register */ + advk_writel(pcie, reg, PIO_WR_DATA); + + /* Program the data strobe */ + advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB); + + retry_count = 0; + do { + /* Clear PIO DONE ISR and start the transfer */ + advk_writel(pcie, 1, PIO_ISR); + advk_writel(pcie, 1, PIO_START); + + ret = advk_pcie_wait_pio(pcie); + if (ret < 0) + return PCIBIOS_SET_FAILED; + + retry_count += ret; + + ret = advk_pcie_check_pio_status(pcie, false, NULL); + } while (ret == -EAGAIN && retry_count < PIO_RETRY_CNT); + + return ret < 0 ? PCIBIOS_SET_FAILED : PCIBIOS_SUCCESSFUL; +} + +static struct pci_ops advk_pcie_ops = { + .read = advk_pcie_rd_conf, + .write = advk_pcie_wr_conf, +}; + +static void advk_msi_irq_compose_msi_msg(struct irq_data *data, + struct msi_msg *msg) +{ + struct advk_pcie *pcie = irq_data_get_irq_chip_data(data); + phys_addr_t msi_addr = virt_to_phys(pcie); + + msg->address_lo = lower_32_bits(msi_addr); + msg->address_hi = upper_32_bits(msi_addr); + msg->data = data->hwirq; +} + +static int advk_msi_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static void advk_msi_irq_mask(struct irq_data *d) +{ + struct advk_pcie *pcie = d->domain->host_data; + irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; + u32 mask; + + raw_spin_lock_irqsave(&pcie->msi_irq_lock, flags); + mask = advk_readl(pcie, PCIE_MSI_MASK_REG); + mask |= BIT(hwirq); + advk_writel(pcie, mask, PCIE_MSI_MASK_REG); + raw_spin_unlock_irqrestore(&pcie->msi_irq_lock, flags); +} + +static void advk_msi_irq_unmask(struct irq_data *d) +{ + struct advk_pcie *pcie = d->domain->host_data; + irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; + u32 mask; + + raw_spin_lock_irqsave(&pcie->msi_irq_lock, flags); + mask = advk_readl(pcie, PCIE_MSI_MASK_REG); + mask &= ~BIT(hwirq); + advk_writel(pcie, mask, PCIE_MSI_MASK_REG); + raw_spin_unlock_irqrestore(&pcie->msi_irq_lock, flags); +} + +static void advk_msi_top_irq_mask(struct irq_data *d) +{ + pci_msi_mask_irq(d); + irq_chip_mask_parent(d); +} + +static void advk_msi_top_irq_unmask(struct irq_data *d) +{ + pci_msi_unmask_irq(d); + irq_chip_unmask_parent(d); +} + +static struct irq_chip advk_msi_bottom_irq_chip = { + .name = "MSI", + .irq_compose_msi_msg = advk_msi_irq_compose_msi_msg, + .irq_set_affinity = advk_msi_set_affinity, + .irq_mask = advk_msi_irq_mask, + .irq_unmask = advk_msi_irq_unmask, +}; + +static int advk_msi_irq_domain_alloc(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct advk_pcie *pcie = domain->host_data; + int hwirq, i; + + mutex_lock(&pcie->msi_used_lock); + hwirq = bitmap_find_free_region(pcie->msi_used, MSI_IRQ_NUM, + order_base_2(nr_irqs)); + mutex_unlock(&pcie->msi_used_lock); + if (hwirq < 0) + return -ENOSPC; + + for (i = 0; i < nr_irqs; i++) + irq_domain_set_info(domain, virq + i, hwirq + i, + &advk_msi_bottom_irq_chip, + domain->host_data, handle_simple_irq, + NULL, NULL); + + return 0; +} + +static void advk_msi_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct advk_pcie *pcie = domain->host_data; + + mutex_lock(&pcie->msi_used_lock); + bitmap_release_region(pcie->msi_used, d->hwirq, order_base_2(nr_irqs)); + mutex_unlock(&pcie->msi_used_lock); +} + +static const struct irq_domain_ops advk_msi_domain_ops = { + .alloc = advk_msi_irq_domain_alloc, + .free = advk_msi_irq_domain_free, +}; + +static void advk_pcie_irq_mask(struct irq_data *d) +{ + struct advk_pcie *pcie = d->domain->host_data; + irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; + u32 mask; + + raw_spin_lock_irqsave(&pcie->irq_lock, flags); + mask = advk_readl(pcie, PCIE_ISR1_MASK_REG); + mask |= PCIE_ISR1_INTX_ASSERT(hwirq); + advk_writel(pcie, mask, PCIE_ISR1_MASK_REG); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); +} + +static void advk_pcie_irq_unmask(struct irq_data *d) +{ + struct advk_pcie *pcie = d->domain->host_data; + irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; + u32 mask; + + raw_spin_lock_irqsave(&pcie->irq_lock, flags); + mask = advk_readl(pcie, PCIE_ISR1_MASK_REG); + mask &= ~PCIE_ISR1_INTX_ASSERT(hwirq); + advk_writel(pcie, mask, PCIE_ISR1_MASK_REG); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); +} + +static int advk_pcie_irq_map(struct irq_domain *h, + unsigned int virq, irq_hw_number_t hwirq) +{ + struct advk_pcie *pcie = h->host_data; + + irq_set_status_flags(virq, IRQ_LEVEL); + irq_set_chip_and_handler(virq, &pcie->irq_chip, + handle_level_irq); + irq_set_chip_data(virq, pcie); + + return 0; +} + +static const struct irq_domain_ops advk_pcie_irq_domain_ops = { + .map = advk_pcie_irq_map, + .xlate = irq_domain_xlate_onecell, +}; + +static struct irq_chip advk_msi_irq_chip = { + .name = "advk-MSI", + .irq_mask = advk_msi_top_irq_mask, + .irq_unmask = advk_msi_top_irq_unmask, +}; + +static struct msi_domain_info advk_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX, + .chip = &advk_msi_irq_chip, +}; + +static int advk_pcie_init_msi_irq_domain(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + + raw_spin_lock_init(&pcie->msi_irq_lock); + mutex_init(&pcie->msi_used_lock); + + pcie->msi_inner_domain = + irq_domain_add_linear(NULL, MSI_IRQ_NUM, + &advk_msi_domain_ops, pcie); + if (!pcie->msi_inner_domain) + return -ENOMEM; + + pcie->msi_domain = + pci_msi_create_irq_domain(dev_fwnode(dev), + &advk_msi_domain_info, + pcie->msi_inner_domain); + if (!pcie->msi_domain) { + irq_domain_remove(pcie->msi_inner_domain); + return -ENOMEM; + } + + return 0; +} + +static void advk_pcie_remove_msi_irq_domain(struct advk_pcie *pcie) +{ + irq_domain_remove(pcie->msi_domain); + irq_domain_remove(pcie->msi_inner_domain); +} + +static int advk_pcie_init_irq_domain(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + struct device_node *node = dev->of_node; + struct device_node *pcie_intc_node; + struct irq_chip *irq_chip; + int ret = 0; + + raw_spin_lock_init(&pcie->irq_lock); + + pcie_intc_node = of_get_next_child(node, NULL); + if (!pcie_intc_node) { + dev_err(dev, "No PCIe Intc node found\n"); + return -ENODEV; + } + + irq_chip = &pcie->irq_chip; + + irq_chip->name = devm_kasprintf(dev, GFP_KERNEL, "%s-irq", + dev_name(dev)); + if (!irq_chip->name) { + ret = -ENOMEM; + goto out_put_node; + } + + irq_chip->irq_mask = advk_pcie_irq_mask; + irq_chip->irq_unmask = advk_pcie_irq_unmask; + + pcie->irq_domain = + irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, + &advk_pcie_irq_domain_ops, pcie); + if (!pcie->irq_domain) { + dev_err(dev, "Failed to get a INTx IRQ domain\n"); + ret = -ENOMEM; + goto out_put_node; + } + +out_put_node: + of_node_put(pcie_intc_node); + return ret; +} + +static void advk_pcie_remove_irq_domain(struct advk_pcie *pcie) +{ + irq_domain_remove(pcie->irq_domain); +} + +static struct irq_chip advk_rp_irq_chip = { + .name = "advk-RP", +}; + +static int advk_pcie_rp_irq_map(struct irq_domain *h, + unsigned int virq, irq_hw_number_t hwirq) +{ + struct advk_pcie *pcie = h->host_data; + + irq_set_chip_and_handler(virq, &advk_rp_irq_chip, handle_simple_irq); + irq_set_chip_data(virq, pcie); + + return 0; +} + +static const struct irq_domain_ops advk_pcie_rp_irq_domain_ops = { + .map = advk_pcie_rp_irq_map, + .xlate = irq_domain_xlate_onecell, +}; + +static int advk_pcie_init_rp_irq_domain(struct advk_pcie *pcie) +{ + pcie->rp_irq_domain = irq_domain_add_linear(NULL, 1, + &advk_pcie_rp_irq_domain_ops, + pcie); + if (!pcie->rp_irq_domain) { + dev_err(&pcie->pdev->dev, "Failed to add Root Port IRQ domain\n"); + return -ENOMEM; + } + + return 0; +} + +static void advk_pcie_remove_rp_irq_domain(struct advk_pcie *pcie) +{ + irq_domain_remove(pcie->rp_irq_domain); +} + +static void advk_pcie_handle_pme(struct advk_pcie *pcie) +{ + u32 requester = advk_readl(pcie, PCIE_MSG_LOG_REG) >> 16; + + advk_writel(pcie, PCIE_MSG_PM_PME_MASK, PCIE_ISR0_REG); + + /* + * PCIE_MSG_LOG_REG contains the last inbound message, so store + * the requester ID only when PME was not asserted yet. + * Also do not trigger PME interrupt when PME is still asserted. + */ + if (!(le32_to_cpu(pcie->bridge.pcie_conf.rootsta) & PCI_EXP_RTSTA_PME)) { + pcie->bridge.pcie_conf.rootsta = cpu_to_le32(requester | PCI_EXP_RTSTA_PME); + + /* + * Trigger PME interrupt only if PMEIE bit in Root Control is set. + * Aardvark HW returns zero for PCI_EXP_FLAGS_IRQ, so use PCIe interrupt 0. + */ + if (!(le16_to_cpu(pcie->bridge.pcie_conf.rootctl) & PCI_EXP_RTCTL_PMEIE)) + return; + + if (generic_handle_domain_irq(pcie->rp_irq_domain, 0) == -EINVAL) + dev_err_ratelimited(&pcie->pdev->dev, "unhandled PME IRQ\n"); + } +} + +static void advk_pcie_handle_msi(struct advk_pcie *pcie) +{ + u32 msi_val, msi_mask, msi_status, msi_idx; + + msi_mask = advk_readl(pcie, PCIE_MSI_MASK_REG); + msi_val = advk_readl(pcie, PCIE_MSI_STATUS_REG); + msi_status = msi_val & ((~msi_mask) & PCIE_MSI_ALL_MASK); + + for (msi_idx = 0; msi_idx < MSI_IRQ_NUM; msi_idx++) { + if (!(BIT(msi_idx) & msi_status)) + continue; + + advk_writel(pcie, BIT(msi_idx), PCIE_MSI_STATUS_REG); + if (generic_handle_domain_irq(pcie->msi_inner_domain, msi_idx) == -EINVAL) + dev_err_ratelimited(&pcie->pdev->dev, "unexpected MSI 0x%02x\n", msi_idx); + } + + advk_writel(pcie, PCIE_ISR0_MSI_INT_PENDING, + PCIE_ISR0_REG); +} + +static void advk_pcie_handle_int(struct advk_pcie *pcie) +{ + u32 isr0_val, isr0_mask, isr0_status; + u32 isr1_val, isr1_mask, isr1_status; + int i; + + isr0_val = advk_readl(pcie, PCIE_ISR0_REG); + isr0_mask = advk_readl(pcie, PCIE_ISR0_MASK_REG); + isr0_status = isr0_val & ((~isr0_mask) & PCIE_ISR0_ALL_MASK); + + isr1_val = advk_readl(pcie, PCIE_ISR1_REG); + isr1_mask = advk_readl(pcie, PCIE_ISR1_MASK_REG); + isr1_status = isr1_val & ((~isr1_mask) & PCIE_ISR1_ALL_MASK); + + /* Process PME interrupt as the first one to do not miss PME requester id */ + if (isr0_status & PCIE_MSG_PM_PME_MASK) + advk_pcie_handle_pme(pcie); + + /* Process ERR interrupt */ + if (isr0_status & PCIE_ISR0_ERR_MASK) { + advk_writel(pcie, PCIE_ISR0_ERR_MASK, PCIE_ISR0_REG); + + /* + * Aardvark HW returns zero for PCI_ERR_ROOT_AER_IRQ, so use + * PCIe interrupt 0 + */ + if (generic_handle_domain_irq(pcie->rp_irq_domain, 0) == -EINVAL) + dev_err_ratelimited(&pcie->pdev->dev, "unhandled ERR IRQ\n"); + } + + /* Process MSI interrupts */ + if (isr0_status & PCIE_ISR0_MSI_INT_PENDING) + advk_pcie_handle_msi(pcie); + + /* Process legacy interrupts */ + for (i = 0; i < PCI_NUM_INTX; i++) { + if (!(isr1_status & PCIE_ISR1_INTX_ASSERT(i))) + continue; + + advk_writel(pcie, PCIE_ISR1_INTX_ASSERT(i), + PCIE_ISR1_REG); + + if (generic_handle_domain_irq(pcie->irq_domain, i) == -EINVAL) + dev_err_ratelimited(&pcie->pdev->dev, "unexpected INT%c IRQ\n", + (char)i + 'A'); + } +} + +static irqreturn_t advk_pcie_irq_handler(int irq, void *arg) +{ + struct advk_pcie *pcie = arg; + u32 status; + + status = advk_readl(pcie, HOST_CTRL_INT_STATUS_REG); + if (!(status & PCIE_IRQ_CORE_INT)) + return IRQ_NONE; + + advk_pcie_handle_int(pcie); + + /* Clear interrupt */ + advk_writel(pcie, PCIE_IRQ_CORE_INT, HOST_CTRL_INT_STATUS_REG); + + return IRQ_HANDLED; +} + +static int advk_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +{ + struct advk_pcie *pcie = dev->bus->sysdata; + + /* + * Emulated root bridge has its own emulated irq chip and irq domain. + * Argument pin is the INTx pin (1=INTA, 2=INTB, 3=INTC, 4=INTD) and + * hwirq for irq_create_mapping() is indexed from zero. + */ + if (pci_is_root_bus(dev->bus)) + return irq_create_mapping(pcie->rp_irq_domain, pin - 1); + else + return of_irq_parse_and_map_pci(dev, slot, pin); +} + +static void advk_pcie_disable_phy(struct advk_pcie *pcie) +{ + phy_power_off(pcie->phy); + phy_exit(pcie->phy); +} + +static int advk_pcie_enable_phy(struct advk_pcie *pcie) +{ + int ret; + + if (!pcie->phy) + return 0; + + ret = phy_init(pcie->phy); + if (ret) + return ret; + + ret = phy_set_mode(pcie->phy, PHY_MODE_PCIE); + if (ret) { + phy_exit(pcie->phy); + return ret; + } + + ret = phy_power_on(pcie->phy); + if (ret) { + phy_exit(pcie->phy); + return ret; + } + + return 0; +} + +static int advk_pcie_setup_phy(struct advk_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + struct device_node *node = dev->of_node; + int ret = 0; + + pcie->phy = devm_of_phy_get(dev, node, NULL); + if (IS_ERR(pcie->phy) && (PTR_ERR(pcie->phy) == -EPROBE_DEFER)) + return PTR_ERR(pcie->phy); + + /* Old bindings miss the PHY handle */ + if (IS_ERR(pcie->phy)) { + dev_warn(dev, "PHY unavailable (%ld)\n", PTR_ERR(pcie->phy)); + pcie->phy = NULL; + return 0; + } + + ret = advk_pcie_enable_phy(pcie); + if (ret) + dev_err(dev, "Failed to initialize PHY (%d)\n", ret); + + return ret; +} + +static int advk_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct advk_pcie *pcie; + struct pci_host_bridge *bridge; + struct resource_entry *entry; + int ret, irq; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct advk_pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + pcie->pdev = pdev; + platform_set_drvdata(pdev, pcie); + + resource_list_for_each_entry(entry, &bridge->windows) { + resource_size_t start = entry->res->start; + resource_size_t size = resource_size(entry->res); + unsigned long type = resource_type(entry->res); + u64 win_size; + + /* + * Aardvark hardware allows to configure also PCIe window + * for config type 0 and type 1 mapping, but driver uses + * only PIO for issuing configuration transfers which does + * not use PCIe window configuration. + */ + if (type != IORESOURCE_MEM && type != IORESOURCE_IO) + continue; + + /* + * Skip transparent memory resources. Default outbound access + * configuration is set to transparent memory access so it + * does not need window configuration. + */ + if (type == IORESOURCE_MEM && entry->offset == 0) + continue; + + /* + * The n-th PCIe window is configured by tuple (match, remap, mask) + * and an access to address A uses this window if A matches the + * match with given mask. + * So every PCIe window size must be a power of two and every start + * address must be aligned to window size. Minimal size is 64 KiB + * because lower 16 bits of mask must be zero. Remapped address + * may have set only bits from the mask. + */ + while (pcie->wins_count < OB_WIN_COUNT && size > 0) { + /* Calculate the largest aligned window size */ + win_size = (1ULL << (fls64(size)-1)) | + (start ? (1ULL << __ffs64(start)) : 0); + win_size = 1ULL << __ffs64(win_size); + if (win_size < 0x10000) + break; + + dev_dbg(dev, + "Configuring PCIe window %d: [0x%llx-0x%llx] as %lu\n", + pcie->wins_count, (unsigned long long)start, + (unsigned long long)start + win_size, type); + + if (type == IORESOURCE_IO) { + pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_IO; + pcie->wins[pcie->wins_count].match = pci_pio_to_address(start); + } else { + pcie->wins[pcie->wins_count].actions = OB_WIN_TYPE_MEM; + pcie->wins[pcie->wins_count].match = start; + } + pcie->wins[pcie->wins_count].remap = start - entry->offset; + pcie->wins[pcie->wins_count].mask = ~(win_size - 1); + + if (pcie->wins[pcie->wins_count].remap & (win_size - 1)) + break; + + start += win_size; + size -= win_size; + pcie->wins_count++; + } + + if (size > 0) { + dev_err(&pcie->pdev->dev, + "Invalid PCIe region [0x%llx-0x%llx]\n", + (unsigned long long)entry->res->start, + (unsigned long long)entry->res->end + 1); + return -EINVAL; + } + } + + pcie->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + ret = devm_request_irq(dev, irq, advk_pcie_irq_handler, + IRQF_SHARED | IRQF_NO_THREAD, "advk-pcie", + pcie); + if (ret) { + dev_err(dev, "Failed to register interrupt\n"); + return ret; + } + + pcie->reset_gpio = devm_gpiod_get_from_of_node(dev, dev->of_node, + "reset-gpios", 0, + GPIOD_OUT_LOW, + "pcie1-reset"); + ret = PTR_ERR_OR_ZERO(pcie->reset_gpio); + if (ret) { + if (ret == -ENOENT) { + pcie->reset_gpio = NULL; + } else { + if (ret != -EPROBE_DEFER) + dev_err(dev, "Failed to get reset-gpio: %i\n", + ret); + return ret; + } + } + + ret = of_pci_get_max_link_speed(dev->of_node); + if (ret <= 0 || ret > 3) + pcie->link_gen = 3; + else + pcie->link_gen = ret; + + ret = advk_pcie_setup_phy(pcie); + if (ret) + return ret; + + advk_pcie_setup_hw(pcie); + + ret = advk_sw_pci_bridge_init(pcie); + if (ret) { + dev_err(dev, "Failed to register emulated root PCI bridge\n"); + return ret; + } + + ret = advk_pcie_init_irq_domain(pcie); + if (ret) { + dev_err(dev, "Failed to initialize irq\n"); + return ret; + } + + ret = advk_pcie_init_msi_irq_domain(pcie); + if (ret) { + dev_err(dev, "Failed to initialize irq\n"); + advk_pcie_remove_irq_domain(pcie); + return ret; + } + + ret = advk_pcie_init_rp_irq_domain(pcie); + if (ret) { + dev_err(dev, "Failed to initialize irq\n"); + advk_pcie_remove_msi_irq_domain(pcie); + advk_pcie_remove_irq_domain(pcie); + return ret; + } + + bridge->sysdata = pcie; + bridge->ops = &advk_pcie_ops; + bridge->map_irq = advk_pcie_map_irq; + + ret = pci_host_probe(bridge); + if (ret < 0) { + advk_pcie_remove_rp_irq_domain(pcie); + advk_pcie_remove_msi_irq_domain(pcie); + advk_pcie_remove_irq_domain(pcie); + return ret; + } + + return 0; +} + +static int advk_pcie_remove(struct platform_device *pdev) +{ + struct advk_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + u32 val; + int i; + + /* Remove PCI bus with all devices */ + pci_lock_rescan_remove(); + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); + pci_unlock_rescan_remove(); + + /* Disable Root Bridge I/O space, memory space and bus mastering */ + val = advk_readl(pcie, PCIE_CORE_CMD_STATUS_REG); + val &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); + advk_writel(pcie, val, PCIE_CORE_CMD_STATUS_REG); + + /* Disable MSI */ + val = advk_readl(pcie, PCIE_CORE_CTRL2_REG); + val &= ~PCIE_CORE_CTRL2_MSI_ENABLE; + advk_writel(pcie, val, PCIE_CORE_CTRL2_REG); + + /* Clear MSI address */ + advk_writel(pcie, 0, PCIE_MSI_ADDR_LOW_REG); + advk_writel(pcie, 0, PCIE_MSI_ADDR_HIGH_REG); + + /* Mask all interrupts */ + advk_writel(pcie, PCIE_MSI_ALL_MASK, PCIE_MSI_MASK_REG); + advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_MASK_REG); + advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG); + advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_MASK_REG); + + /* Clear all interrupts */ + advk_writel(pcie, PCIE_MSI_ALL_MASK, PCIE_MSI_STATUS_REG); + advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_REG); + advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_REG); + advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG); + + /* Remove IRQ domains */ + advk_pcie_remove_rp_irq_domain(pcie); + advk_pcie_remove_msi_irq_domain(pcie); + advk_pcie_remove_irq_domain(pcie); + + /* Free config space for emulated root bridge */ + pci_bridge_emul_cleanup(&pcie->bridge); + + /* Assert PERST# signal which prepares PCIe card for power down */ + if (pcie->reset_gpio) + gpiod_set_value_cansleep(pcie->reset_gpio, 1); + + /* Disable link training */ + val = advk_readl(pcie, PCIE_CORE_CTRL0_REG); + val &= ~LINK_TRAINING_EN; + advk_writel(pcie, val, PCIE_CORE_CTRL0_REG); + + /* Disable outbound address windows mapping */ + for (i = 0; i < OB_WIN_COUNT; i++) + advk_pcie_disable_ob_win(pcie, i); + + /* Disable phy */ + advk_pcie_disable_phy(pcie); + + return 0; +} + +static const struct of_device_id advk_pcie_of_match_table[] = { + { .compatible = "marvell,armada-3700-pcie", }, + {}, +}; +MODULE_DEVICE_TABLE(of, advk_pcie_of_match_table); + +static struct platform_driver advk_pcie_driver = { + .driver = { + .name = "advk-pcie", + .of_match_table = advk_pcie_of_match_table, + }, + .probe = advk_pcie_probe, + .remove = advk_pcie_remove, +}; +module_platform_driver(advk_pcie_driver); + +MODULE_DESCRIPTION("Aardvark PCIe controller"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c new file mode 100644 index 000000000..f7e61e169 --- /dev/null +++ b/drivers/pci/controller/pci-ftpci100.c @@ -0,0 +1,551 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for Faraday Technology FTPC100 PCI Controller + * + * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> + * + * Based on the out-of-tree OpenWRT patch for Cortina Gemini: + * Copyright (C) 2009 Janos Laube <janos.dev@gmail.com> + * Copyright (C) 2009 Paulius Zaleckas <paulius.zaleckas@teltonika.lt> + * Based on SL2312 PCI controller code + * Storlink (C) 2003 + */ + +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/of_address.h> +#include <linux/of_device.h> +#include <linux/of_irq.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/irqdomain.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/bitops.h> +#include <linux/irq.h> +#include <linux/clk.h> + +#include "../pci.h" + +/* + * Special configuration registers directly in the first few words + * in I/O space. + */ +#define FTPCI_IOSIZE 0x00 +#define FTPCI_PROT 0x04 /* AHB protection */ +#define FTPCI_CTRL 0x08 /* PCI control signal */ +#define FTPCI_SOFTRST 0x10 /* Soft reset counter and response error enable */ +#define FTPCI_CONFIG 0x28 /* PCI configuration command register */ +#define FTPCI_DATA 0x2C + +#define FARADAY_PCI_STATUS_CMD 0x04 /* Status and command */ +#define FARADAY_PCI_PMC 0x40 /* Power management control */ +#define FARADAY_PCI_PMCSR 0x44 /* Power management status */ +#define FARADAY_PCI_CTRL1 0x48 /* Control register 1 */ +#define FARADAY_PCI_CTRL2 0x4C /* Control register 2 */ +#define FARADAY_PCI_MEM1_BASE_SIZE 0x50 /* Memory base and size #1 */ +#define FARADAY_PCI_MEM2_BASE_SIZE 0x54 /* Memory base and size #2 */ +#define FARADAY_PCI_MEM3_BASE_SIZE 0x58 /* Memory base and size #3 */ + +#define PCI_STATUS_66MHZ_CAPABLE BIT(21) + +/* Bits 31..28 gives INTD..INTA status */ +#define PCI_CTRL2_INTSTS_SHIFT 28 +#define PCI_CTRL2_INTMASK_CMDERR BIT(27) +#define PCI_CTRL2_INTMASK_PARERR BIT(26) +/* Bits 25..22 masks INTD..INTA */ +#define PCI_CTRL2_INTMASK_SHIFT 22 +#define PCI_CTRL2_INTMASK_MABRT_RX BIT(21) +#define PCI_CTRL2_INTMASK_TABRT_RX BIT(20) +#define PCI_CTRL2_INTMASK_TABRT_TX BIT(19) +#define PCI_CTRL2_INTMASK_RETRY4 BIT(18) +#define PCI_CTRL2_INTMASK_SERR_RX BIT(17) +#define PCI_CTRL2_INTMASK_PERR_RX BIT(16) +/* Bit 15 reserved */ +#define PCI_CTRL2_MSTPRI_REQ6 BIT(14) +#define PCI_CTRL2_MSTPRI_REQ5 BIT(13) +#define PCI_CTRL2_MSTPRI_REQ4 BIT(12) +#define PCI_CTRL2_MSTPRI_REQ3 BIT(11) +#define PCI_CTRL2_MSTPRI_REQ2 BIT(10) +#define PCI_CTRL2_MSTPRI_REQ1 BIT(9) +#define PCI_CTRL2_MSTPRI_REQ0 BIT(8) +/* Bits 7..4 reserved */ +/* Bits 3..0 TRDYW */ + +/* + * Memory configs: + * Bit 31..20 defines the PCI side memory base + * Bit 19..16 (4 bits) defines the size per below + */ +#define FARADAY_PCI_MEMBASE_MASK 0xfff00000 +#define FARADAY_PCI_MEMSIZE_1MB 0x0 +#define FARADAY_PCI_MEMSIZE_2MB 0x1 +#define FARADAY_PCI_MEMSIZE_4MB 0x2 +#define FARADAY_PCI_MEMSIZE_8MB 0x3 +#define FARADAY_PCI_MEMSIZE_16MB 0x4 +#define FARADAY_PCI_MEMSIZE_32MB 0x5 +#define FARADAY_PCI_MEMSIZE_64MB 0x6 +#define FARADAY_PCI_MEMSIZE_128MB 0x7 +#define FARADAY_PCI_MEMSIZE_256MB 0x8 +#define FARADAY_PCI_MEMSIZE_512MB 0x9 +#define FARADAY_PCI_MEMSIZE_1GB 0xa +#define FARADAY_PCI_MEMSIZE_2GB 0xb +#define FARADAY_PCI_MEMSIZE_SHIFT 16 + +/* + * The DMA base is set to 0x0 for all memory segments, it reflects the + * fact that the memory of the host system starts at 0x0. + */ +#define FARADAY_PCI_DMA_MEM1_BASE 0x00000000 +#define FARADAY_PCI_DMA_MEM2_BASE 0x00000000 +#define FARADAY_PCI_DMA_MEM3_BASE 0x00000000 + +/** + * struct faraday_pci_variant - encodes IP block differences + * @cascaded_irq: this host has cascaded IRQs from an interrupt controller + * embedded in the host bridge. + */ +struct faraday_pci_variant { + bool cascaded_irq; +}; + +struct faraday_pci { + struct device *dev; + void __iomem *base; + struct irq_domain *irqdomain; + struct pci_bus *bus; + struct clk *bus_clk; +}; + +static int faraday_res_to_memcfg(resource_size_t mem_base, + resource_size_t mem_size, u32 *val) +{ + u32 outval; + + switch (mem_size) { + case SZ_1M: + outval = FARADAY_PCI_MEMSIZE_1MB; + break; + case SZ_2M: + outval = FARADAY_PCI_MEMSIZE_2MB; + break; + case SZ_4M: + outval = FARADAY_PCI_MEMSIZE_4MB; + break; + case SZ_8M: + outval = FARADAY_PCI_MEMSIZE_8MB; + break; + case SZ_16M: + outval = FARADAY_PCI_MEMSIZE_16MB; + break; + case SZ_32M: + outval = FARADAY_PCI_MEMSIZE_32MB; + break; + case SZ_64M: + outval = FARADAY_PCI_MEMSIZE_64MB; + break; + case SZ_128M: + outval = FARADAY_PCI_MEMSIZE_128MB; + break; + case SZ_256M: + outval = FARADAY_PCI_MEMSIZE_256MB; + break; + case SZ_512M: + outval = FARADAY_PCI_MEMSIZE_512MB; + break; + case SZ_1G: + outval = FARADAY_PCI_MEMSIZE_1GB; + break; + case SZ_2G: + outval = FARADAY_PCI_MEMSIZE_2GB; + break; + default: + return -EINVAL; + } + outval <<= FARADAY_PCI_MEMSIZE_SHIFT; + + /* This is probably not good */ + if (mem_base & ~(FARADAY_PCI_MEMBASE_MASK)) + pr_warn("truncated PCI memory base\n"); + /* Translate to bridge side address space */ + outval |= (mem_base & FARADAY_PCI_MEMBASE_MASK); + pr_debug("Translated pci base @%pap, size %pap to config %08x\n", + &mem_base, &mem_size, outval); + + *val = outval; + return 0; +} + +static int faraday_raw_pci_read_config(struct faraday_pci *p, int bus_number, + unsigned int fn, int config, int size, + u32 *value) +{ + writel(PCI_CONF1_ADDRESS(bus_number, PCI_SLOT(fn), + PCI_FUNC(fn), config), + p->base + FTPCI_CONFIG); + + *value = readl(p->base + FTPCI_DATA); + + if (size == 1) + *value = (*value >> (8 * (config & 3))) & 0xFF; + else if (size == 2) + *value = (*value >> (8 * (config & 3))) & 0xFFFF; + + return PCIBIOS_SUCCESSFUL; +} + +static int faraday_pci_read_config(struct pci_bus *bus, unsigned int fn, + int config, int size, u32 *value) +{ + struct faraday_pci *p = bus->sysdata; + + dev_dbg(&bus->dev, + "[read] slt: %.2d, fnc: %d, cnf: 0x%.2X, val (%d bytes): 0x%.8X\n", + PCI_SLOT(fn), PCI_FUNC(fn), config, size, *value); + + return faraday_raw_pci_read_config(p, bus->number, fn, config, size, value); +} + +static int faraday_raw_pci_write_config(struct faraday_pci *p, int bus_number, + unsigned int fn, int config, int size, + u32 value) +{ + int ret = PCIBIOS_SUCCESSFUL; + + writel(PCI_CONF1_ADDRESS(bus_number, PCI_SLOT(fn), + PCI_FUNC(fn), config), + p->base + FTPCI_CONFIG); + + switch (size) { + case 4: + writel(value, p->base + FTPCI_DATA); + break; + case 2: + writew(value, p->base + FTPCI_DATA + (config & 3)); + break; + case 1: + writeb(value, p->base + FTPCI_DATA + (config & 3)); + break; + default: + ret = PCIBIOS_BAD_REGISTER_NUMBER; + } + + return ret; +} + +static int faraday_pci_write_config(struct pci_bus *bus, unsigned int fn, + int config, int size, u32 value) +{ + struct faraday_pci *p = bus->sysdata; + + dev_dbg(&bus->dev, + "[write] slt: %.2d, fnc: %d, cnf: 0x%.2X, val (%d bytes): 0x%.8X\n", + PCI_SLOT(fn), PCI_FUNC(fn), config, size, value); + + return faraday_raw_pci_write_config(p, bus->number, fn, config, size, + value); +} + +static struct pci_ops faraday_pci_ops = { + .read = faraday_pci_read_config, + .write = faraday_pci_write_config, +}; + +static void faraday_pci_ack_irq(struct irq_data *d) +{ + struct faraday_pci *p = irq_data_get_irq_chip_data(d); + unsigned int reg; + + faraday_raw_pci_read_config(p, 0, 0, FARADAY_PCI_CTRL2, 4, ®); + reg &= ~(0xF << PCI_CTRL2_INTSTS_SHIFT); + reg |= BIT(irqd_to_hwirq(d) + PCI_CTRL2_INTSTS_SHIFT); + faraday_raw_pci_write_config(p, 0, 0, FARADAY_PCI_CTRL2, 4, reg); +} + +static void faraday_pci_mask_irq(struct irq_data *d) +{ + struct faraday_pci *p = irq_data_get_irq_chip_data(d); + unsigned int reg; + + faraday_raw_pci_read_config(p, 0, 0, FARADAY_PCI_CTRL2, 4, ®); + reg &= ~((0xF << PCI_CTRL2_INTSTS_SHIFT) + | BIT(irqd_to_hwirq(d) + PCI_CTRL2_INTMASK_SHIFT)); + faraday_raw_pci_write_config(p, 0, 0, FARADAY_PCI_CTRL2, 4, reg); +} + +static void faraday_pci_unmask_irq(struct irq_data *d) +{ + struct faraday_pci *p = irq_data_get_irq_chip_data(d); + unsigned int reg; + + faraday_raw_pci_read_config(p, 0, 0, FARADAY_PCI_CTRL2, 4, ®); + reg &= ~(0xF << PCI_CTRL2_INTSTS_SHIFT); + reg |= BIT(irqd_to_hwirq(d) + PCI_CTRL2_INTMASK_SHIFT); + faraday_raw_pci_write_config(p, 0, 0, FARADAY_PCI_CTRL2, 4, reg); +} + +static void faraday_pci_irq_handler(struct irq_desc *desc) +{ + struct faraday_pci *p = irq_desc_get_handler_data(desc); + struct irq_chip *irqchip = irq_desc_get_chip(desc); + unsigned int irq_stat, reg, i; + + faraday_raw_pci_read_config(p, 0, 0, FARADAY_PCI_CTRL2, 4, ®); + irq_stat = reg >> PCI_CTRL2_INTSTS_SHIFT; + + chained_irq_enter(irqchip, desc); + + for (i = 0; i < 4; i++) { + if ((irq_stat & BIT(i)) == 0) + continue; + generic_handle_domain_irq(p->irqdomain, i); + } + + chained_irq_exit(irqchip, desc); +} + +static struct irq_chip faraday_pci_irq_chip = { + .name = "PCI", + .irq_ack = faraday_pci_ack_irq, + .irq_mask = faraday_pci_mask_irq, + .irq_unmask = faraday_pci_unmask_irq, +}; + +static int faraday_pci_irq_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &faraday_pci_irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops faraday_pci_irqdomain_ops = { + .map = faraday_pci_irq_map, +}; + +static int faraday_pci_setup_cascaded_irq(struct faraday_pci *p) +{ + struct device_node *intc = of_get_next_child(p->dev->of_node, NULL); + int irq; + int i; + + if (!intc) { + dev_err(p->dev, "missing child interrupt-controller node\n"); + return -EINVAL; + } + + /* All PCI IRQs cascade off this one */ + irq = of_irq_get(intc, 0); + if (irq <= 0) { + dev_err(p->dev, "failed to get parent IRQ\n"); + of_node_put(intc); + return irq ?: -EINVAL; + } + + p->irqdomain = irq_domain_add_linear(intc, PCI_NUM_INTX, + &faraday_pci_irqdomain_ops, p); + of_node_put(intc); + if (!p->irqdomain) { + dev_err(p->dev, "failed to create Gemini PCI IRQ domain\n"); + return -EINVAL; + } + + irq_set_chained_handler_and_data(irq, faraday_pci_irq_handler, p); + + for (i = 0; i < 4; i++) + irq_create_mapping(p->irqdomain, i); + + return 0; +} + +static int faraday_pci_parse_map_dma_ranges(struct faraday_pci *p) +{ + struct device *dev = p->dev; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(p); + struct resource_entry *entry; + u32 confreg[3] = { + FARADAY_PCI_MEM1_BASE_SIZE, + FARADAY_PCI_MEM2_BASE_SIZE, + FARADAY_PCI_MEM3_BASE_SIZE, + }; + int i = 0; + u32 val; + + resource_list_for_each_entry(entry, &bridge->dma_ranges) { + u64 pci_addr = entry->res->start - entry->offset; + u64 end = entry->res->end - entry->offset; + int ret; + + ret = faraday_res_to_memcfg(pci_addr, + resource_size(entry->res), &val); + if (ret) { + dev_err(dev, + "DMA range %d: illegal MEM resource size\n", i); + return -EINVAL; + } + + dev_info(dev, "DMA MEM%d BASE: 0x%016llx -> 0x%016llx config %08x\n", + i + 1, pci_addr, end, val); + if (i <= 2) { + faraday_raw_pci_write_config(p, 0, 0, confreg[i], + 4, val); + } else { + dev_err(dev, "ignore extraneous dma-range %d\n", i); + break; + } + + i++; + } + + return 0; +} + +static int faraday_pci_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + const struct faraday_pci_variant *variant = + of_device_get_match_data(dev); + struct resource_entry *win; + struct faraday_pci *p; + struct resource *io; + struct pci_host_bridge *host; + struct clk *clk; + unsigned char max_bus_speed = PCI_SPEED_33MHz; + unsigned char cur_bus_speed = PCI_SPEED_33MHz; + int ret; + u32 val; + + host = devm_pci_alloc_host_bridge(dev, sizeof(*p)); + if (!host) + return -ENOMEM; + + host->ops = &faraday_pci_ops; + p = pci_host_bridge_priv(host); + host->sysdata = p; + p->dev = dev; + + /* Retrieve and enable optional clocks */ + clk = devm_clk_get_enabled(dev, "PCLK"); + if (IS_ERR(clk)) + return PTR_ERR(clk); + p->bus_clk = devm_clk_get_enabled(dev, "PCICLK"); + if (IS_ERR(p->bus_clk)) + return PTR_ERR(p->bus_clk); + + p->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(p->base)) + return PTR_ERR(p->base); + + win = resource_list_first_type(&host->windows, IORESOURCE_IO); + if (win) { + io = win->res; + if (!faraday_res_to_memcfg(io->start - win->offset, + resource_size(io), &val)) { + /* setup I/O space size */ + writel(val, p->base + FTPCI_IOSIZE); + } else { + dev_err(dev, "illegal IO mem size\n"); + return -EINVAL; + } + } + + /* Setup hostbridge */ + val = readl(p->base + FTPCI_CTRL); + val |= PCI_COMMAND_IO; + val |= PCI_COMMAND_MEMORY; + val |= PCI_COMMAND_MASTER; + writel(val, p->base + FTPCI_CTRL); + /* Mask and clear all interrupts */ + faraday_raw_pci_write_config(p, 0, 0, FARADAY_PCI_CTRL2 + 2, 2, 0xF000); + if (variant->cascaded_irq) { + ret = faraday_pci_setup_cascaded_irq(p); + if (ret) { + dev_err(dev, "failed to setup cascaded IRQ\n"); + return ret; + } + } + + /* Check bus clock if we can gear up to 66 MHz */ + if (!IS_ERR(p->bus_clk)) { + unsigned long rate; + u32 val; + + faraday_raw_pci_read_config(p, 0, 0, + FARADAY_PCI_STATUS_CMD, 4, &val); + rate = clk_get_rate(p->bus_clk); + + if ((rate == 33000000) && (val & PCI_STATUS_66MHZ_CAPABLE)) { + dev_info(dev, "33MHz bus is 66MHz capable\n"); + max_bus_speed = PCI_SPEED_66MHz; + ret = clk_set_rate(p->bus_clk, 66000000); + if (ret) + dev_err(dev, "failed to set bus clock\n"); + } else { + dev_info(dev, "33MHz only bus\n"); + max_bus_speed = PCI_SPEED_33MHz; + } + + /* Bumping the clock may fail so read back the rate */ + rate = clk_get_rate(p->bus_clk); + if (rate == 33000000) + cur_bus_speed = PCI_SPEED_33MHz; + if (rate == 66000000) + cur_bus_speed = PCI_SPEED_66MHz; + } + + ret = faraday_pci_parse_map_dma_ranges(p); + if (ret) + return ret; + + ret = pci_scan_root_bus_bridge(host); + if (ret) { + dev_err(dev, "failed to scan host: %d\n", ret); + return ret; + } + p->bus = host->bus; + p->bus->max_bus_speed = max_bus_speed; + p->bus->cur_bus_speed = cur_bus_speed; + + pci_bus_assign_resources(p->bus); + pci_bus_add_devices(p->bus); + + return 0; +} + +/* + * We encode bridge variants here, we have at least two so it doesn't + * hurt to have infrastructure to encompass future variants as well. + */ +static const struct faraday_pci_variant faraday_regular = { + .cascaded_irq = true, +}; + +static const struct faraday_pci_variant faraday_dual = { + .cascaded_irq = false, +}; + +static const struct of_device_id faraday_pci_of_match[] = { + { + .compatible = "faraday,ftpci100", + .data = &faraday_regular, + }, + { + .compatible = "faraday,ftpci100-dual", + .data = &faraday_dual, + }, + {}, +}; + +static struct platform_driver faraday_pci_driver = { + .driver = { + .name = "ftpci100", + .of_match_table = of_match_ptr(faraday_pci_of_match), + .suppress_bind_attrs = true, + }, + .probe = faraday_pci_probe, +}; +builtin_platform_driver(faraday_pci_driver); diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c new file mode 100644 index 000000000..d3924a44d --- /dev/null +++ b/drivers/pci/controller/pci-host-common.c @@ -0,0 +1,101 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Generic PCI host driver common code + * + * Copyright (C) 2014 ARM Limited + * + * Author: Will Deacon <will.deacon@arm.com> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_device.h> +#include <linux/of_pci.h> +#include <linux/pci-ecam.h> +#include <linux/platform_device.h> + +static void gen_pci_unmap_cfg(void *ptr) +{ + pci_ecam_free((struct pci_config_window *)ptr); +} + +static struct pci_config_window *gen_pci_init(struct device *dev, + struct pci_host_bridge *bridge, const struct pci_ecam_ops *ops) +{ + int err; + struct resource cfgres; + struct resource_entry *bus; + struct pci_config_window *cfg; + + err = of_address_to_resource(dev->of_node, 0, &cfgres); + if (err) { + dev_err(dev, "missing \"reg\" property\n"); + return ERR_PTR(err); + } + + bus = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (!bus) + return ERR_PTR(-ENODEV); + + cfg = pci_ecam_create(dev, &cfgres, bus->res, ops); + if (IS_ERR(cfg)) + return cfg; + + err = devm_add_action_or_reset(dev, gen_pci_unmap_cfg, cfg); + if (err) + return ERR_PTR(err); + + return cfg; +} + +int pci_host_common_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + struct pci_config_window *cfg; + const struct pci_ecam_ops *ops; + + ops = of_device_get_match_data(&pdev->dev); + if (!ops) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, 0); + if (!bridge) + return -ENOMEM; + + platform_set_drvdata(pdev, bridge); + + of_pci_check_probe_only(); + + /* Parse and map our Configuration Space windows */ + cfg = gen_pci_init(dev, bridge, ops); + if (IS_ERR(cfg)) + return PTR_ERR(cfg); + + /* Do not reassign resources if probe only */ + if (!pci_has_flag(PCI_PROBE_ONLY)) + pci_add_flags(PCI_REASSIGN_ALL_BUS); + + bridge->sysdata = cfg; + bridge->ops = (struct pci_ops *)&ops->pci_ops; + bridge->msi_domain = true; + + return pci_host_probe(bridge); +} +EXPORT_SYMBOL_GPL(pci_host_common_probe); + +int pci_host_common_remove(struct platform_device *pdev) +{ + struct pci_host_bridge *bridge = platform_get_drvdata(pdev); + + pci_lock_rescan_remove(); + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); + pci_unlock_rescan_remove(); + + return 0; +} +EXPORT_SYMBOL_GPL(pci_host_common_remove); + +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-host-generic.c b/drivers/pci/controller/pci-host-generic.c new file mode 100644 index 000000000..63865aeb6 --- /dev/null +++ b/drivers/pci/controller/pci-host-generic.c @@ -0,0 +1,89 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Simple, generic PCI host controller driver targeting firmware-initialised + * systems and virtual machines (e.g. the PCI emulation provided by kvmtool). + * + * Copyright (C) 2014 ARM Limited + * + * Author: Will Deacon <will.deacon@arm.com> + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/pci-ecam.h> +#include <linux/platform_device.h> + +static const struct pci_ecam_ops gen_pci_cfg_cam_bus_ops = { + .bus_shift = 16, + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +static bool pci_dw_valid_device(struct pci_bus *bus, unsigned int devfn) +{ + struct pci_config_window *cfg = bus->sysdata; + + /* + * The Synopsys DesignWare PCIe controller in ECAM mode will not filter + * type 0 config TLPs sent to devices 1 and up on its downstream port, + * resulting in devices appearing multiple times on bus 0 unless we + * filter out those accesses here. + */ + if (bus->number == cfg->busr.start && PCI_SLOT(devfn) > 0) + return false; + + return true; +} + +static void __iomem *pci_dw_ecam_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + if (!pci_dw_valid_device(bus, devfn)) + return NULL; + + return pci_ecam_map_bus(bus, devfn, where); +} + +static const struct pci_ecam_ops pci_dw_ecam_bus_ops = { + .pci_ops = { + .map_bus = pci_dw_ecam_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +static const struct of_device_id gen_pci_of_match[] = { + { .compatible = "pci-host-cam-generic", + .data = &gen_pci_cfg_cam_bus_ops }, + + { .compatible = "pci-host-ecam-generic", + .data = &pci_generic_ecam_ops }, + + { .compatible = "marvell,armada8k-pcie-ecam", + .data = &pci_dw_ecam_bus_ops }, + + { .compatible = "socionext,synquacer-pcie-ecam", + .data = &pci_dw_ecam_bus_ops }, + + { .compatible = "snps,dw-pcie-ecam", + .data = &pci_dw_ecam_bus_ops }, + + { }, +}; +MODULE_DEVICE_TABLE(of, gen_pci_of_match); + +static struct platform_driver gen_pci_driver = { + .driver = { + .name = "pci-host-generic", + .of_match_table = gen_pci_of_match, + }, + .probe = pci_host_common_probe, + .remove = pci_host_common_remove, +}; +module_platform_driver(gen_pci_driver); + +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-hyperv-intf.c b/drivers/pci/controller/pci-hyperv-intf.c new file mode 100644 index 000000000..cc96be450 --- /dev/null +++ b/drivers/pci/controller/pci-hyperv-intf.c @@ -0,0 +1,67 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) Microsoft Corporation. + * + * Author: + * Haiyang Zhang <haiyangz@microsoft.com> + * + * This small module is a helper driver allows other drivers to + * have a common interface with the Hyper-V PCI frontend driver. + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/hyperv.h> + +struct hyperv_pci_block_ops hvpci_block_ops; +EXPORT_SYMBOL_GPL(hvpci_block_ops); + +int hyperv_read_cfg_blk(struct pci_dev *dev, void *buf, unsigned int buf_len, + unsigned int block_id, unsigned int *bytes_returned) +{ + if (!hvpci_block_ops.read_block) + return -EOPNOTSUPP; + + return hvpci_block_ops.read_block(dev, buf, buf_len, block_id, + bytes_returned); +} +EXPORT_SYMBOL_GPL(hyperv_read_cfg_blk); + +int hyperv_write_cfg_blk(struct pci_dev *dev, void *buf, unsigned int len, + unsigned int block_id) +{ + if (!hvpci_block_ops.write_block) + return -EOPNOTSUPP; + + return hvpci_block_ops.write_block(dev, buf, len, block_id); +} +EXPORT_SYMBOL_GPL(hyperv_write_cfg_blk); + +int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)) +{ + if (!hvpci_block_ops.reg_blk_invalidate) + return -EOPNOTSUPP; + + return hvpci_block_ops.reg_blk_invalidate(dev, context, + block_invalidate); +} +EXPORT_SYMBOL_GPL(hyperv_reg_block_invalidate); + +static void __exit exit_hv_pci_intf(void) +{ +} + +static int __init init_hv_pci_intf(void) +{ + return 0; +} + +module_init(init_hv_pci_intf); +module_exit(exit_hv_pci_intf); + +MODULE_DESCRIPTION("Hyper-V PCI Interface"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c new file mode 100644 index 000000000..9693bab59 --- /dev/null +++ b/drivers/pci/controller/pci-hyperv.c @@ -0,0 +1,4068 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) Microsoft Corporation. + * + * Author: + * Jake Oshins <jakeo@microsoft.com> + * + * This driver acts as a paravirtual front-end for PCI Express root buses. + * When a PCI Express function (either an entire device or an SR-IOV + * Virtual Function) is being passed through to the VM, this driver exposes + * a new bus to the guest VM. This is modeled as a root PCI bus because + * no bridges are being exposed to the VM. In fact, with a "Generation 2" + * VM within Hyper-V, there may seem to be no PCI bus at all in the VM + * until a device as been exposed using this driver. + * + * Each root PCI bus has its own PCI domain, which is called "Segment" in + * the PCI Firmware Specifications. Thus while each device passed through + * to the VM using this front-end will appear at "device 0", the domain will + * be unique. Typically, each bus will have one PCI function on it, though + * this driver does support more than one. + * + * In order to map the interrupts from the device through to the guest VM, + * this driver also implements an IRQ Domain, which handles interrupts (either + * MSI or MSI-X) associated with the functions on the bus. As interrupts are + * set up, torn down, or reaffined, this driver communicates with the + * underlying hypervisor to adjust the mappings in the I/O MMU so that each + * interrupt will be delivered to the correct virtual processor at the right + * vector. This driver does not support level-triggered (line-based) + * interrupts, and will report that the Interrupt Line register in the + * function's configuration space is zero. + * + * The rest of this driver mostly maps PCI concepts onto underlying Hyper-V + * facilities. For instance, the configuration space of a function exposed + * by Hyper-V is mapped into a single page of memory space, and the + * read and write handlers for config space must be aware of this mechanism. + * Similarly, device setup and teardown involves messages sent to and from + * the PCI back-end driver in Hyper-V. + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/delay.h> +#include <linux/semaphore.h> +#include <linux/irq.h> +#include <linux/msi.h> +#include <linux/hyperv.h> +#include <linux/refcount.h> +#include <linux/irqdomain.h> +#include <linux/acpi.h> +#include <asm/mshyperv.h> + +/* + * Protocol versions. The low word is the minor version, the high word the + * major version. + */ + +#define PCI_MAKE_VERSION(major, minor) ((u32)(((major) << 16) | (minor))) +#define PCI_MAJOR_VERSION(version) ((u32)(version) >> 16) +#define PCI_MINOR_VERSION(version) ((u32)(version) & 0xff) + +enum pci_protocol_version_t { + PCI_PROTOCOL_VERSION_1_1 = PCI_MAKE_VERSION(1, 1), /* Win10 */ + PCI_PROTOCOL_VERSION_1_2 = PCI_MAKE_VERSION(1, 2), /* RS1 */ + PCI_PROTOCOL_VERSION_1_3 = PCI_MAKE_VERSION(1, 3), /* Vibranium */ + PCI_PROTOCOL_VERSION_1_4 = PCI_MAKE_VERSION(1, 4), /* WS2022 */ +}; + +#define CPU_AFFINITY_ALL -1ULL + +/* + * Supported protocol versions in the order of probing - highest go + * first. + */ +static enum pci_protocol_version_t pci_protocol_versions[] = { + PCI_PROTOCOL_VERSION_1_4, + PCI_PROTOCOL_VERSION_1_3, + PCI_PROTOCOL_VERSION_1_2, + PCI_PROTOCOL_VERSION_1_1, +}; + +#define PCI_CONFIG_MMIO_LENGTH 0x2000 +#define CFG_PAGE_OFFSET 0x1000 +#define CFG_PAGE_SIZE (PCI_CONFIG_MMIO_LENGTH - CFG_PAGE_OFFSET) + +#define MAX_SUPPORTED_MSI_MESSAGES 0x400 + +#define STATUS_REVISION_MISMATCH 0xC0000059 + +/* space for 32bit serial number as string */ +#define SLOT_NAME_SIZE 11 + +/* + * Size of requestor for VMbus; the value is based on the observation + * that having more than one request outstanding is 'rare', and so 64 + * should be generous in ensuring that we don't ever run out. + */ +#define HV_PCI_RQSTOR_SIZE 64 + +/* + * Message Types + */ + +enum pci_message_type { + /* + * Version 1.1 + */ + PCI_MESSAGE_BASE = 0x42490000, + PCI_BUS_RELATIONS = PCI_MESSAGE_BASE + 0, + PCI_QUERY_BUS_RELATIONS = PCI_MESSAGE_BASE + 1, + PCI_POWER_STATE_CHANGE = PCI_MESSAGE_BASE + 4, + PCI_QUERY_RESOURCE_REQUIREMENTS = PCI_MESSAGE_BASE + 5, + PCI_QUERY_RESOURCE_RESOURCES = PCI_MESSAGE_BASE + 6, + PCI_BUS_D0ENTRY = PCI_MESSAGE_BASE + 7, + PCI_BUS_D0EXIT = PCI_MESSAGE_BASE + 8, + PCI_READ_BLOCK = PCI_MESSAGE_BASE + 9, + PCI_WRITE_BLOCK = PCI_MESSAGE_BASE + 0xA, + PCI_EJECT = PCI_MESSAGE_BASE + 0xB, + PCI_QUERY_STOP = PCI_MESSAGE_BASE + 0xC, + PCI_REENABLE = PCI_MESSAGE_BASE + 0xD, + PCI_QUERY_STOP_FAILED = PCI_MESSAGE_BASE + 0xE, + PCI_EJECTION_COMPLETE = PCI_MESSAGE_BASE + 0xF, + PCI_RESOURCES_ASSIGNED = PCI_MESSAGE_BASE + 0x10, + PCI_RESOURCES_RELEASED = PCI_MESSAGE_BASE + 0x11, + PCI_INVALIDATE_BLOCK = PCI_MESSAGE_BASE + 0x12, + PCI_QUERY_PROTOCOL_VERSION = PCI_MESSAGE_BASE + 0x13, + PCI_CREATE_INTERRUPT_MESSAGE = PCI_MESSAGE_BASE + 0x14, + PCI_DELETE_INTERRUPT_MESSAGE = PCI_MESSAGE_BASE + 0x15, + PCI_RESOURCES_ASSIGNED2 = PCI_MESSAGE_BASE + 0x16, + PCI_CREATE_INTERRUPT_MESSAGE2 = PCI_MESSAGE_BASE + 0x17, + PCI_DELETE_INTERRUPT_MESSAGE2 = PCI_MESSAGE_BASE + 0x18, /* unused */ + PCI_BUS_RELATIONS2 = PCI_MESSAGE_BASE + 0x19, + PCI_RESOURCES_ASSIGNED3 = PCI_MESSAGE_BASE + 0x1A, + PCI_CREATE_INTERRUPT_MESSAGE3 = PCI_MESSAGE_BASE + 0x1B, + PCI_MESSAGE_MAXIMUM +}; + +/* + * Structures defining the virtual PCI Express protocol. + */ + +union pci_version { + struct { + u16 minor_version; + u16 major_version; + } parts; + u32 version; +} __packed; + +/* + * Function numbers are 8-bits wide on Express, as interpreted through ARI, + * which is all this driver does. This representation is the one used in + * Windows, which is what is expected when sending this back and forth with + * the Hyper-V parent partition. + */ +union win_slot_encoding { + struct { + u32 dev:5; + u32 func:3; + u32 reserved:24; + } bits; + u32 slot; +} __packed; + +/* + * Pretty much as defined in the PCI Specifications. + */ +struct pci_function_description { + u16 v_id; /* vendor ID */ + u16 d_id; /* device ID */ + u8 rev; + u8 prog_intf; + u8 subclass; + u8 base_class; + u32 subsystem_id; + union win_slot_encoding win_slot; + u32 ser; /* serial number */ +} __packed; + +enum pci_device_description_flags { + HV_PCI_DEVICE_FLAG_NONE = 0x0, + HV_PCI_DEVICE_FLAG_NUMA_AFFINITY = 0x1, +}; + +struct pci_function_description2 { + u16 v_id; /* vendor ID */ + u16 d_id; /* device ID */ + u8 rev; + u8 prog_intf; + u8 subclass; + u8 base_class; + u32 subsystem_id; + union win_slot_encoding win_slot; + u32 ser; /* serial number */ + u32 flags; + u16 virtual_numa_node; + u16 reserved; +} __packed; + +/** + * struct hv_msi_desc + * @vector: IDT entry + * @delivery_mode: As defined in Intel's Programmer's + * Reference Manual, Volume 3, Chapter 8. + * @vector_count: Number of contiguous entries in the + * Interrupt Descriptor Table that are + * occupied by this Message-Signaled + * Interrupt. For "MSI", as first defined + * in PCI 2.2, this can be between 1 and + * 32. For "MSI-X," as first defined in PCI + * 3.0, this must be 1, as each MSI-X table + * entry would have its own descriptor. + * @reserved: Empty space + * @cpu_mask: All the target virtual processors. + */ +struct hv_msi_desc { + u8 vector; + u8 delivery_mode; + u16 vector_count; + u32 reserved; + u64 cpu_mask; +} __packed; + +/** + * struct hv_msi_desc2 - 1.2 version of hv_msi_desc + * @vector: IDT entry + * @delivery_mode: As defined in Intel's Programmer's + * Reference Manual, Volume 3, Chapter 8. + * @vector_count: Number of contiguous entries in the + * Interrupt Descriptor Table that are + * occupied by this Message-Signaled + * Interrupt. For "MSI", as first defined + * in PCI 2.2, this can be between 1 and + * 32. For "MSI-X," as first defined in PCI + * 3.0, this must be 1, as each MSI-X table + * entry would have its own descriptor. + * @processor_count: number of bits enabled in array. + * @processor_array: All the target virtual processors. + */ +struct hv_msi_desc2 { + u8 vector; + u8 delivery_mode; + u16 vector_count; + u16 processor_count; + u16 processor_array[32]; +} __packed; + +/* + * struct hv_msi_desc3 - 1.3 version of hv_msi_desc + * Everything is the same as in 'hv_msi_desc2' except that the size of the + * 'vector' field is larger to support bigger vector values. For ex: LPI + * vectors on ARM. + */ +struct hv_msi_desc3 { + u32 vector; + u8 delivery_mode; + u8 reserved; + u16 vector_count; + u16 processor_count; + u16 processor_array[32]; +} __packed; + +/** + * struct tran_int_desc + * @reserved: unused, padding + * @vector_count: same as in hv_msi_desc + * @data: This is the "data payload" value that is + * written by the device when it generates + * a message-signaled interrupt, either MSI + * or MSI-X. + * @address: This is the address to which the data + * payload is written on interrupt + * generation. + */ +struct tran_int_desc { + u16 reserved; + u16 vector_count; + u32 data; + u64 address; +} __packed; + +/* + * A generic message format for virtual PCI. + * Specific message formats are defined later in the file. + */ + +struct pci_message { + u32 type; +} __packed; + +struct pci_child_message { + struct pci_message message_type; + union win_slot_encoding wslot; +} __packed; + +struct pci_incoming_message { + struct vmpacket_descriptor hdr; + struct pci_message message_type; +} __packed; + +struct pci_response { + struct vmpacket_descriptor hdr; + s32 status; /* negative values are failures */ +} __packed; + +struct pci_packet { + void (*completion_func)(void *context, struct pci_response *resp, + int resp_packet_size); + void *compl_ctxt; + + struct pci_message message[]; +}; + +/* + * Specific message types supporting the PCI protocol. + */ + +/* + * Version negotiation message. Sent from the guest to the host. + * The guest is free to try different versions until the host + * accepts the version. + * + * pci_version: The protocol version requested. + * is_last_attempt: If TRUE, this is the last version guest will request. + * reservedz: Reserved field, set to zero. + */ + +struct pci_version_request { + struct pci_message message_type; + u32 protocol_version; +} __packed; + +/* + * Bus D0 Entry. This is sent from the guest to the host when the virtual + * bus (PCI Express port) is ready for action. + */ + +struct pci_bus_d0_entry { + struct pci_message message_type; + u32 reserved; + u64 mmio_base; +} __packed; + +struct pci_bus_relations { + struct pci_incoming_message incoming; + u32 device_count; + struct pci_function_description func[]; +} __packed; + +struct pci_bus_relations2 { + struct pci_incoming_message incoming; + u32 device_count; + struct pci_function_description2 func[]; +} __packed; + +struct pci_q_res_req_response { + struct vmpacket_descriptor hdr; + s32 status; /* negative values are failures */ + u32 probed_bar[PCI_STD_NUM_BARS]; +} __packed; + +struct pci_set_power { + struct pci_message message_type; + union win_slot_encoding wslot; + u32 power_state; /* In Windows terms */ + u32 reserved; +} __packed; + +struct pci_set_power_response { + struct vmpacket_descriptor hdr; + s32 status; /* negative values are failures */ + union win_slot_encoding wslot; + u32 resultant_state; /* In Windows terms */ + u32 reserved; +} __packed; + +struct pci_resources_assigned { + struct pci_message message_type; + union win_slot_encoding wslot; + u8 memory_range[0x14][6]; /* not used here */ + u32 msi_descriptors; + u32 reserved[4]; +} __packed; + +struct pci_resources_assigned2 { + struct pci_message message_type; + union win_slot_encoding wslot; + u8 memory_range[0x14][6]; /* not used here */ + u32 msi_descriptor_count; + u8 reserved[70]; +} __packed; + +struct pci_create_interrupt { + struct pci_message message_type; + union win_slot_encoding wslot; + struct hv_msi_desc int_desc; +} __packed; + +struct pci_create_int_response { + struct pci_response response; + u32 reserved; + struct tran_int_desc int_desc; +} __packed; + +struct pci_create_interrupt2 { + struct pci_message message_type; + union win_slot_encoding wslot; + struct hv_msi_desc2 int_desc; +} __packed; + +struct pci_create_interrupt3 { + struct pci_message message_type; + union win_slot_encoding wslot; + struct hv_msi_desc3 int_desc; +} __packed; + +struct pci_delete_interrupt { + struct pci_message message_type; + union win_slot_encoding wslot; + struct tran_int_desc int_desc; +} __packed; + +/* + * Note: the VM must pass a valid block id, wslot and bytes_requested. + */ +struct pci_read_block { + struct pci_message message_type; + u32 block_id; + union win_slot_encoding wslot; + u32 bytes_requested; +} __packed; + +struct pci_read_block_response { + struct vmpacket_descriptor hdr; + u32 status; + u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX]; +} __packed; + +/* + * Note: the VM must pass a valid block id, wslot and byte_count. + */ +struct pci_write_block { + struct pci_message message_type; + u32 block_id; + union win_slot_encoding wslot; + u32 byte_count; + u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX]; +} __packed; + +struct pci_dev_inval_block { + struct pci_incoming_message incoming; + union win_slot_encoding wslot; + u64 block_mask; +} __packed; + +struct pci_dev_incoming { + struct pci_incoming_message incoming; + union win_slot_encoding wslot; +} __packed; + +struct pci_eject_response { + struct pci_message message_type; + union win_slot_encoding wslot; + u32 status; +} __packed; + +static int pci_ring_size = (4 * PAGE_SIZE); + +/* + * Driver specific state. + */ + +enum hv_pcibus_state { + hv_pcibus_init = 0, + hv_pcibus_probed, + hv_pcibus_installed, + hv_pcibus_removing, + hv_pcibus_maximum +}; + +struct hv_pcibus_device { +#ifdef CONFIG_X86 + struct pci_sysdata sysdata; +#elif defined(CONFIG_ARM64) + struct pci_config_window sysdata; +#endif + struct pci_host_bridge *bridge; + struct fwnode_handle *fwnode; + /* Protocol version negotiated with the host */ + enum pci_protocol_version_t protocol_version; + + struct mutex state_lock; + enum hv_pcibus_state state; + + struct hv_device *hdev; + resource_size_t low_mmio_space; + resource_size_t high_mmio_space; + struct resource *mem_config; + struct resource *low_mmio_res; + struct resource *high_mmio_res; + struct completion *survey_event; + struct pci_bus *pci_bus; + spinlock_t config_lock; /* Avoid two threads writing index page */ + spinlock_t device_list_lock; /* Protect lists below */ + void __iomem *cfg_addr; + + struct list_head children; + struct list_head dr_list; + + struct msi_domain_info msi_info; + struct irq_domain *irq_domain; + + spinlock_t retarget_msi_interrupt_lock; + + struct workqueue_struct *wq; + + /* Highest slot of child device with resources allocated */ + int wslot_res_allocated; + + /* hypercall arg, must not cross page boundary */ + struct hv_retarget_device_interrupt retarget_msi_interrupt_params; + + /* + * Don't put anything here: retarget_msi_interrupt_params must be last + */ +}; + +/* + * Tracks "Device Relations" messages from the host, which must be both + * processed in order and deferred so that they don't run in the context + * of the incoming packet callback. + */ +struct hv_dr_work { + struct work_struct wrk; + struct hv_pcibus_device *bus; +}; + +struct hv_pcidev_description { + u16 v_id; /* vendor ID */ + u16 d_id; /* device ID */ + u8 rev; + u8 prog_intf; + u8 subclass; + u8 base_class; + u32 subsystem_id; + union win_slot_encoding win_slot; + u32 ser; /* serial number */ + u32 flags; + u16 virtual_numa_node; +}; + +struct hv_dr_state { + struct list_head list_entry; + u32 device_count; + struct hv_pcidev_description func[]; +}; + +struct hv_pci_dev { + /* List protected by pci_rescan_remove_lock */ + struct list_head list_entry; + refcount_t refs; + struct pci_slot *pci_slot; + struct hv_pcidev_description desc; + bool reported_missing; + struct hv_pcibus_device *hbus; + struct work_struct wrk; + + void (*block_invalidate)(void *context, u64 block_mask); + void *invalidate_context; + + /* + * What would be observed if one wrote 0xFFFFFFFF to a BAR and then + * read it back, for each of the BAR offsets within config space. + */ + u32 probed_bar[PCI_STD_NUM_BARS]; +}; + +struct hv_pci_compl { + struct completion host_event; + s32 completion_status; +}; + +static void hv_pci_onchannelcallback(void *context); + +#ifdef CONFIG_X86 +#define DELIVERY_MODE APIC_DELIVERY_MODE_FIXED +#define FLOW_HANDLER handle_edge_irq +#define FLOW_NAME "edge" + +static int hv_pci_irqchip_init(void) +{ + return 0; +} + +static struct irq_domain *hv_pci_get_root_domain(void) +{ + return x86_vector_domain; +} + +static unsigned int hv_msi_get_int_vector(struct irq_data *data) +{ + struct irq_cfg *cfg = irqd_cfg(data); + + return cfg->vector; +} + +static int hv_msi_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *info) +{ + int ret = pci_msi_prepare(domain, dev, nvec, info); + + /* + * By using the interrupt remapper in the hypervisor IOMMU, contiguous + * CPU vectors is not needed for multi-MSI + */ + if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI) + info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS; + + return ret; +} + +/** + * hv_arch_irq_unmask() - "Unmask" the IRQ by setting its current + * affinity. + * @data: Describes the IRQ + * + * Build new a destination for the MSI and make a hypercall to + * update the Interrupt Redirection Table. "Device Logical ID" + * is built out of this PCI bus's instance GUID and the function + * number of the device. + */ +static void hv_arch_irq_unmask(struct irq_data *data) +{ + struct msi_desc *msi_desc = irq_data_get_msi_desc(data); + struct hv_retarget_device_interrupt *params; + struct tran_int_desc *int_desc; + struct hv_pcibus_device *hbus; + const struct cpumask *dest; + cpumask_var_t tmp; + struct pci_bus *pbus; + struct pci_dev *pdev; + unsigned long flags; + u32 var_size = 0; + int cpu, nr_bank; + u64 res; + + dest = irq_data_get_effective_affinity_mask(data); + pdev = msi_desc_to_pci_dev(msi_desc); + pbus = pdev->bus; + hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); + int_desc = data->chip_data; + if (!int_desc) { + dev_warn(&hbus->hdev->device, "%s() can not unmask irq %u\n", + __func__, data->irq); + return; + } + + spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags); + + params = &hbus->retarget_msi_interrupt_params; + memset(params, 0, sizeof(*params)); + params->partition_id = HV_PARTITION_ID_SELF; + params->int_entry.source = HV_INTERRUPT_SOURCE_MSI; + params->int_entry.msi_entry.address.as_uint32 = int_desc->address & 0xffffffff; + params->int_entry.msi_entry.data.as_uint32 = int_desc->data; + params->device_id = (hbus->hdev->dev_instance.b[5] << 24) | + (hbus->hdev->dev_instance.b[4] << 16) | + (hbus->hdev->dev_instance.b[7] << 8) | + (hbus->hdev->dev_instance.b[6] & 0xf8) | + PCI_FUNC(pdev->devfn); + params->int_target.vector = hv_msi_get_int_vector(data); + + /* + * Honoring apic->delivery_mode set to APIC_DELIVERY_MODE_FIXED by + * setting the HV_DEVICE_INTERRUPT_TARGET_MULTICAST flag results in a + * spurious interrupt storm. Not doing so does not seem to have a + * negative effect (yet?). + */ + + if (hbus->protocol_version >= PCI_PROTOCOL_VERSION_1_2) { + /* + * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the + * HVCALL_RETARGET_INTERRUPT hypercall, which also coincides + * with >64 VP support. + * ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED + * is not sufficient for this hypercall. + */ + params->int_target.flags |= + HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET; + + if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) { + res = 1; + goto exit_unlock; + } + + cpumask_and(tmp, dest, cpu_online_mask); + nr_bank = cpumask_to_vpset(¶ms->int_target.vp_set, tmp); + free_cpumask_var(tmp); + + if (nr_bank <= 0) { + res = 1; + goto exit_unlock; + } + + /* + * var-sized hypercall, var-size starts after vp_mask (thus + * vp_set.format does not count, but vp_set.valid_bank_mask + * does). + */ + var_size = 1 + nr_bank; + } else { + for_each_cpu_and(cpu, dest, cpu_online_mask) { + params->int_target.vp_mask |= + (1ULL << hv_cpu_number_to_vp_number(cpu)); + } + } + + res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17), + params, NULL); + +exit_unlock: + spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags); + + /* + * During hibernation, when a CPU is offlined, the kernel tries + * to move the interrupt to the remaining CPUs that haven't + * been offlined yet. In this case, the below hv_do_hypercall() + * always fails since the vmbus channel has been closed: + * refer to cpu_disable_common() -> fixup_irqs() -> + * irq_migrate_all_off_this_cpu() -> migrate_one_irq(). + * + * Suppress the error message for hibernation because the failure + * during hibernation does not matter (at this time all the devices + * have been frozen). Note: the correct affinity info is still updated + * into the irqdata data structure in migrate_one_irq() -> + * irq_do_set_affinity() -> hv_set_affinity(), so later when the VM + * resumes, hv_pci_restore_msi_state() is able to correctly restore + * the interrupt with the correct affinity. + */ + if (!hv_result_success(res) && hbus->state != hv_pcibus_removing) + dev_err(&hbus->hdev->device, + "%s() failed: %#llx", __func__, res); +} +#elif defined(CONFIG_ARM64) +/* + * SPI vectors to use for vPCI; arch SPIs range is [32, 1019], but leaving a bit + * of room at the start to allow for SPIs to be specified through ACPI and + * starting with a power of two to satisfy power of 2 multi-MSI requirement. + */ +#define HV_PCI_MSI_SPI_START 64 +#define HV_PCI_MSI_SPI_NR (1020 - HV_PCI_MSI_SPI_START) +#define DELIVERY_MODE 0 +#define FLOW_HANDLER NULL +#define FLOW_NAME NULL +#define hv_msi_prepare NULL + +struct hv_pci_chip_data { + DECLARE_BITMAP(spi_map, HV_PCI_MSI_SPI_NR); + struct mutex map_lock; +}; + +/* Hyper-V vPCI MSI GIC IRQ domain */ +static struct irq_domain *hv_msi_gic_irq_domain; + +/* Hyper-V PCI MSI IRQ chip */ +static struct irq_chip hv_arm64_msi_irq_chip = { + .name = "MSI", + .irq_set_affinity = irq_chip_set_affinity_parent, + .irq_eoi = irq_chip_eoi_parent, + .irq_mask = irq_chip_mask_parent, + .irq_unmask = irq_chip_unmask_parent +}; + +static unsigned int hv_msi_get_int_vector(struct irq_data *irqd) +{ + return irqd->parent_data->hwirq; +} + +/* + * @nr_bm_irqs: Indicates the number of IRQs that were allocated from + * the bitmap. + * @nr_dom_irqs: Indicates the number of IRQs that were allocated from + * the parent domain. + */ +static void hv_pci_vec_irq_free(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_bm_irqs, + unsigned int nr_dom_irqs) +{ + struct hv_pci_chip_data *chip_data = domain->host_data; + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + int first = d->hwirq - HV_PCI_MSI_SPI_START; + int i; + + mutex_lock(&chip_data->map_lock); + bitmap_release_region(chip_data->spi_map, + first, + get_count_order(nr_bm_irqs)); + mutex_unlock(&chip_data->map_lock); + for (i = 0; i < nr_dom_irqs; i++) { + if (i) + d = irq_domain_get_irq_data(domain, virq + i); + irq_domain_reset_irq_data(d); + } + + irq_domain_free_irqs_parent(domain, virq, nr_dom_irqs); +} + +static void hv_pci_vec_irq_domain_free(struct irq_domain *domain, + unsigned int virq, + unsigned int nr_irqs) +{ + hv_pci_vec_irq_free(domain, virq, nr_irqs, nr_irqs); +} + +static int hv_pci_vec_alloc_device_irq(struct irq_domain *domain, + unsigned int nr_irqs, + irq_hw_number_t *hwirq) +{ + struct hv_pci_chip_data *chip_data = domain->host_data; + int index; + + /* Find and allocate region from the SPI bitmap */ + mutex_lock(&chip_data->map_lock); + index = bitmap_find_free_region(chip_data->spi_map, + HV_PCI_MSI_SPI_NR, + get_count_order(nr_irqs)); + mutex_unlock(&chip_data->map_lock); + if (index < 0) + return -ENOSPC; + + *hwirq = index + HV_PCI_MSI_SPI_START; + + return 0; +} + +static int hv_pci_vec_irq_gic_domain_alloc(struct irq_domain *domain, + unsigned int virq, + irq_hw_number_t hwirq) +{ + struct irq_fwspec fwspec; + struct irq_data *d; + int ret; + + fwspec.fwnode = domain->parent->fwnode; + fwspec.param_count = 2; + fwspec.param[0] = hwirq; + fwspec.param[1] = IRQ_TYPE_EDGE_RISING; + + ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec); + if (ret) + return ret; + + /* + * Since the interrupt specifier is not coming from ACPI or DT, the + * trigger type will need to be set explicitly. Otherwise, it will be + * set to whatever is in the GIC configuration. + */ + d = irq_domain_get_irq_data(domain->parent, virq); + + return d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING); +} + +static int hv_pci_vec_irq_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *args) +{ + irq_hw_number_t hwirq; + unsigned int i; + int ret; + + ret = hv_pci_vec_alloc_device_irq(domain, nr_irqs, &hwirq); + if (ret) + return ret; + + for (i = 0; i < nr_irqs; i++) { + ret = hv_pci_vec_irq_gic_domain_alloc(domain, virq + i, + hwirq + i); + if (ret) { + hv_pci_vec_irq_free(domain, virq, nr_irqs, i); + return ret; + } + + irq_domain_set_hwirq_and_chip(domain, virq + i, + hwirq + i, + &hv_arm64_msi_irq_chip, + domain->host_data); + pr_debug("pID:%d vID:%u\n", (int)(hwirq + i), virq + i); + } + + return 0; +} + +/* + * Pick the first cpu as the irq affinity that can be temporarily used for + * composing MSI from the hypervisor. GIC will eventually set the right + * affinity for the irq and the 'unmask' will retarget the interrupt to that + * cpu. + */ +static int hv_pci_vec_irq_domain_activate(struct irq_domain *domain, + struct irq_data *irqd, bool reserve) +{ + int cpu = cpumask_first(cpu_present_mask); + + irq_data_update_effective_affinity(irqd, cpumask_of(cpu)); + + return 0; +} + +static const struct irq_domain_ops hv_pci_domain_ops = { + .alloc = hv_pci_vec_irq_domain_alloc, + .free = hv_pci_vec_irq_domain_free, + .activate = hv_pci_vec_irq_domain_activate, +}; + +static int hv_pci_irqchip_init(void) +{ + static struct hv_pci_chip_data *chip_data; + struct fwnode_handle *fn = NULL; + int ret = -ENOMEM; + + chip_data = kzalloc(sizeof(*chip_data), GFP_KERNEL); + if (!chip_data) + return ret; + + mutex_init(&chip_data->map_lock); + fn = irq_domain_alloc_named_fwnode("hv_vpci_arm64"); + if (!fn) + goto free_chip; + + /* + * IRQ domain once enabled, should not be removed since there is no + * way to ensure that all the corresponding devices are also gone and + * no interrupts will be generated. + */ + hv_msi_gic_irq_domain = acpi_irq_create_hierarchy(0, HV_PCI_MSI_SPI_NR, + fn, &hv_pci_domain_ops, + chip_data); + + if (!hv_msi_gic_irq_domain) { + pr_err("Failed to create Hyper-V arm64 vPCI MSI IRQ domain\n"); + goto free_chip; + } + + return 0; + +free_chip: + kfree(chip_data); + if (fn) + irq_domain_free_fwnode(fn); + + return ret; +} + +static struct irq_domain *hv_pci_get_root_domain(void) +{ + return hv_msi_gic_irq_domain; +} + +/* + * SPIs are used for interrupts of PCI devices and SPIs is managed via GICD + * registers which Hyper-V already supports, so no hypercall needed. + */ +static void hv_arch_irq_unmask(struct irq_data *data) { } +#endif /* CONFIG_ARM64 */ + +/** + * hv_pci_generic_compl() - Invoked for a completion packet + * @context: Set up by the sender of the packet. + * @resp: The response packet + * @resp_packet_size: Size in bytes of the packet + * + * This function is used to trigger an event and report status + * for any message for which the completion packet contains a + * status and nothing else. + */ +static void hv_pci_generic_compl(void *context, struct pci_response *resp, + int resp_packet_size) +{ + struct hv_pci_compl *comp_pkt = context; + + comp_pkt->completion_status = resp->status; + complete(&comp_pkt->host_event); +} + +static struct hv_pci_dev *get_pcichild_wslot(struct hv_pcibus_device *hbus, + u32 wslot); + +static void get_pcichild(struct hv_pci_dev *hpdev) +{ + refcount_inc(&hpdev->refs); +} + +static void put_pcichild(struct hv_pci_dev *hpdev) +{ + if (refcount_dec_and_test(&hpdev->refs)) + kfree(hpdev); +} + +/* + * There is no good way to get notified from vmbus_onoffer_rescind(), + * so let's use polling here, since this is not a hot path. + */ +static int wait_for_response(struct hv_device *hdev, + struct completion *comp) +{ + while (true) { + if (hdev->channel->rescind) { + dev_warn_once(&hdev->device, "The device is gone.\n"); + return -ENODEV; + } + + if (wait_for_completion_timeout(comp, HZ / 10)) + break; + } + + return 0; +} + +/** + * devfn_to_wslot() - Convert from Linux PCI slot to Windows + * @devfn: The Linux representation of PCI slot + * + * Windows uses a slightly different representation of PCI slot. + * + * Return: The Windows representation + */ +static u32 devfn_to_wslot(int devfn) +{ + union win_slot_encoding wslot; + + wslot.slot = 0; + wslot.bits.dev = PCI_SLOT(devfn); + wslot.bits.func = PCI_FUNC(devfn); + + return wslot.slot; +} + +/** + * wslot_to_devfn() - Convert from Windows PCI slot to Linux + * @wslot: The Windows representation of PCI slot + * + * Windows uses a slightly different representation of PCI slot. + * + * Return: The Linux representation + */ +static int wslot_to_devfn(u32 wslot) +{ + union win_slot_encoding slot_no; + + slot_no.slot = wslot; + return PCI_DEVFN(slot_no.bits.dev, slot_no.bits.func); +} + +/* + * PCI Configuration Space for these root PCI buses is implemented as a pair + * of pages in memory-mapped I/O space. Writing to the first page chooses + * the PCI function being written or read. Once the first page has been + * written to, the following page maps in the entire configuration space of + * the function. + */ + +/** + * _hv_pcifront_read_config() - Internal PCI config read + * @hpdev: The PCI driver's representation of the device + * @where: Offset within config space + * @size: Size of the transfer + * @val: Pointer to the buffer receiving the data + */ +static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where, + int size, u32 *val) +{ + unsigned long flags; + void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where; + + /* + * If the attempt is to read the IDs or the ROM BAR, simulate that. + */ + if (where + size <= PCI_COMMAND) { + memcpy(val, ((u8 *)&hpdev->desc.v_id) + where, size); + } else if (where >= PCI_CLASS_REVISION && where + size <= + PCI_CACHE_LINE_SIZE) { + memcpy(val, ((u8 *)&hpdev->desc.rev) + where - + PCI_CLASS_REVISION, size); + } else if (where >= PCI_SUBSYSTEM_VENDOR_ID && where + size <= + PCI_ROM_ADDRESS) { + memcpy(val, (u8 *)&hpdev->desc.subsystem_id + where - + PCI_SUBSYSTEM_VENDOR_ID, size); + } else if (where >= PCI_ROM_ADDRESS && where + size <= + PCI_CAPABILITY_LIST) { + /* ROM BARs are unimplemented */ + *val = 0; + } else if (where >= PCI_INTERRUPT_LINE && where + size <= + PCI_INTERRUPT_PIN) { + /* + * Interrupt Line and Interrupt PIN are hard-wired to zero + * because this front-end only supports message-signaled + * interrupts. + */ + *val = 0; + } else if (where + size <= CFG_PAGE_SIZE) { + spin_lock_irqsave(&hpdev->hbus->config_lock, flags); + /* Choose the function to be read. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); + /* Make sure the function was chosen before we start reading. */ + mb(); + /* Read from that function's config space. */ + switch (size) { + case 1: + *val = readb(addr); + break; + case 2: + *val = readw(addr); + break; + default: + *val = readl(addr); + break; + } + /* + * Make sure the read was done before we release the spinlock + * allowing consecutive reads/writes. + */ + mb(); + spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + } else { + dev_err(&hpdev->hbus->hdev->device, + "Attempt to read beyond a function's config space.\n"); + } +} + +static u16 hv_pcifront_get_vendor_id(struct hv_pci_dev *hpdev) +{ + u16 ret; + unsigned long flags; + void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + + PCI_VENDOR_ID; + + spin_lock_irqsave(&hpdev->hbus->config_lock, flags); + + /* Choose the function to be read. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); + /* Make sure the function was chosen before we start reading. */ + mb(); + /* Read from that function's config space. */ + ret = readw(addr); + /* + * mb() is not required here, because the spin_unlock_irqrestore() + * is a barrier. + */ + + spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + + return ret; +} + +/** + * _hv_pcifront_write_config() - Internal PCI config write + * @hpdev: The PCI driver's representation of the device + * @where: Offset within config space + * @size: Size of the transfer + * @val: The data being transferred + */ +static void _hv_pcifront_write_config(struct hv_pci_dev *hpdev, int where, + int size, u32 val) +{ + unsigned long flags; + void __iomem *addr = hpdev->hbus->cfg_addr + CFG_PAGE_OFFSET + where; + + if (where >= PCI_SUBSYSTEM_VENDOR_ID && + where + size <= PCI_CAPABILITY_LIST) { + /* SSIDs and ROM BARs are read-only */ + } else if (where >= PCI_COMMAND && where + size <= CFG_PAGE_SIZE) { + spin_lock_irqsave(&hpdev->hbus->config_lock, flags); + /* Choose the function to be written. (See comment above) */ + writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr); + /* Make sure the function was chosen before we start writing. */ + wmb(); + /* Write to that function's config space. */ + switch (size) { + case 1: + writeb(val, addr); + break; + case 2: + writew(val, addr); + break; + default: + writel(val, addr); + break; + } + /* + * Make sure the write was done before we release the spinlock + * allowing consecutive reads/writes. + */ + mb(); + spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags); + } else { + dev_err(&hpdev->hbus->hdev->device, + "Attempt to write beyond a function's config space.\n"); + } +} + +/** + * hv_pcifront_read_config() - Read configuration space + * @bus: PCI Bus structure + * @devfn: Device/function + * @where: Offset from base + * @size: Byte/word/dword + * @val: Value to be read + * + * Return: PCIBIOS_SUCCESSFUL on success + * PCIBIOS_DEVICE_NOT_FOUND on failure + */ +static int hv_pcifront_read_config(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct hv_pcibus_device *hbus = + container_of(bus->sysdata, struct hv_pcibus_device, sysdata); + struct hv_pci_dev *hpdev; + + hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(devfn)); + if (!hpdev) + return PCIBIOS_DEVICE_NOT_FOUND; + + _hv_pcifront_read_config(hpdev, where, size, val); + + put_pcichild(hpdev); + return PCIBIOS_SUCCESSFUL; +} + +/** + * hv_pcifront_write_config() - Write configuration space + * @bus: PCI Bus structure + * @devfn: Device/function + * @where: Offset from base + * @size: Byte/word/dword + * @val: Value to be written to device + * + * Return: PCIBIOS_SUCCESSFUL on success + * PCIBIOS_DEVICE_NOT_FOUND on failure + */ +static int hv_pcifront_write_config(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct hv_pcibus_device *hbus = + container_of(bus->sysdata, struct hv_pcibus_device, sysdata); + struct hv_pci_dev *hpdev; + + hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(devfn)); + if (!hpdev) + return PCIBIOS_DEVICE_NOT_FOUND; + + _hv_pcifront_write_config(hpdev, where, size, val); + + put_pcichild(hpdev); + return PCIBIOS_SUCCESSFUL; +} + +/* PCIe operations */ +static struct pci_ops hv_pcifront_ops = { + .read = hv_pcifront_read_config, + .write = hv_pcifront_write_config, +}; + +/* + * Paravirtual backchannel + * + * Hyper-V SR-IOV provides a backchannel mechanism in software for + * communication between a VF driver and a PF driver. These + * "configuration blocks" are similar in concept to PCI configuration space, + * but instead of doing reads and writes in 32-bit chunks through a very slow + * path, packets of up to 128 bytes can be sent or received asynchronously. + * + * Nearly every SR-IOV device contains just such a communications channel in + * hardware, so using this one in software is usually optional. Using the + * software channel, however, allows driver implementers to leverage software + * tools that fuzz the communications channel looking for vulnerabilities. + * + * The usage model for these packets puts the responsibility for reading or + * writing on the VF driver. The VF driver sends a read or a write packet, + * indicating which "block" is being referred to by number. + * + * If the PF driver wishes to initiate communication, it can "invalidate" one or + * more of the first 64 blocks. This invalidation is delivered via a callback + * supplied by the VF driver by this driver. + * + * No protocol is implied, except that supplied by the PF and VF drivers. + */ + +struct hv_read_config_compl { + struct hv_pci_compl comp_pkt; + void *buf; + unsigned int len; + unsigned int bytes_returned; +}; + +/** + * hv_pci_read_config_compl() - Invoked when a response packet + * for a read config block operation arrives. + * @context: Identifies the read config operation + * @resp: The response packet itself + * @resp_packet_size: Size in bytes of the response packet + */ +static void hv_pci_read_config_compl(void *context, struct pci_response *resp, + int resp_packet_size) +{ + struct hv_read_config_compl *comp = context; + struct pci_read_block_response *read_resp = + (struct pci_read_block_response *)resp; + unsigned int data_len, hdr_len; + + hdr_len = offsetof(struct pci_read_block_response, bytes); + if (resp_packet_size < hdr_len) { + comp->comp_pkt.completion_status = -1; + goto out; + } + + data_len = resp_packet_size - hdr_len; + if (data_len > 0 && read_resp->status == 0) { + comp->bytes_returned = min(comp->len, data_len); + memcpy(comp->buf, read_resp->bytes, comp->bytes_returned); + } else { + comp->bytes_returned = 0; + } + + comp->comp_pkt.completion_status = read_resp->status; +out: + complete(&comp->comp_pkt.host_event); +} + +/** + * hv_read_config_block() - Sends a read config block request to + * the back-end driver running in the Hyper-V parent partition. + * @pdev: The PCI driver's representation for this device. + * @buf: Buffer into which the config block will be copied. + * @len: Size in bytes of buf. + * @block_id: Identifies the config block which has been requested. + * @bytes_returned: Size which came back from the back-end driver. + * + * Return: 0 on success, -errno on failure + */ +static int hv_read_config_block(struct pci_dev *pdev, void *buf, + unsigned int len, unsigned int block_id, + unsigned int *bytes_returned) +{ + struct hv_pcibus_device *hbus = + container_of(pdev->bus->sysdata, struct hv_pcibus_device, + sysdata); + struct { + struct pci_packet pkt; + char buf[sizeof(struct pci_read_block)]; + } pkt; + struct hv_read_config_compl comp_pkt; + struct pci_read_block *read_blk; + int ret; + + if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX) + return -EINVAL; + + init_completion(&comp_pkt.comp_pkt.host_event); + comp_pkt.buf = buf; + comp_pkt.len = len; + + memset(&pkt, 0, sizeof(pkt)); + pkt.pkt.completion_func = hv_pci_read_config_compl; + pkt.pkt.compl_ctxt = &comp_pkt; + read_blk = (struct pci_read_block *)&pkt.pkt.message; + read_blk->message_type.type = PCI_READ_BLOCK; + read_blk->wslot.slot = devfn_to_wslot(pdev->devfn); + read_blk->block_id = block_id; + read_blk->bytes_requested = len; + + ret = vmbus_sendpacket(hbus->hdev->channel, read_blk, + sizeof(*read_blk), (unsigned long)&pkt.pkt, + VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (ret) + return ret; + + ret = wait_for_response(hbus->hdev, &comp_pkt.comp_pkt.host_event); + if (ret) + return ret; + + if (comp_pkt.comp_pkt.completion_status != 0 || + comp_pkt.bytes_returned == 0) { + dev_err(&hbus->hdev->device, + "Read Config Block failed: 0x%x, bytes_returned=%d\n", + comp_pkt.comp_pkt.completion_status, + comp_pkt.bytes_returned); + return -EIO; + } + + *bytes_returned = comp_pkt.bytes_returned; + return 0; +} + +/** + * hv_pci_write_config_compl() - Invoked when a response packet for a write + * config block operation arrives. + * @context: Identifies the write config operation + * @resp: The response packet itself + * @resp_packet_size: Size in bytes of the response packet + */ +static void hv_pci_write_config_compl(void *context, struct pci_response *resp, + int resp_packet_size) +{ + struct hv_pci_compl *comp_pkt = context; + + comp_pkt->completion_status = resp->status; + complete(&comp_pkt->host_event); +} + +/** + * hv_write_config_block() - Sends a write config block request to the + * back-end driver running in the Hyper-V parent partition. + * @pdev: The PCI driver's representation for this device. + * @buf: Buffer from which the config block will be copied. + * @len: Size in bytes of buf. + * @block_id: Identifies the config block which is being written. + * + * Return: 0 on success, -errno on failure + */ +static int hv_write_config_block(struct pci_dev *pdev, void *buf, + unsigned int len, unsigned int block_id) +{ + struct hv_pcibus_device *hbus = + container_of(pdev->bus->sysdata, struct hv_pcibus_device, + sysdata); + struct { + struct pci_packet pkt; + char buf[sizeof(struct pci_write_block)]; + u32 reserved; + } pkt; + struct hv_pci_compl comp_pkt; + struct pci_write_block *write_blk; + u32 pkt_size; + int ret; + + if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX) + return -EINVAL; + + init_completion(&comp_pkt.host_event); + + memset(&pkt, 0, sizeof(pkt)); + pkt.pkt.completion_func = hv_pci_write_config_compl; + pkt.pkt.compl_ctxt = &comp_pkt; + write_blk = (struct pci_write_block *)&pkt.pkt.message; + write_blk->message_type.type = PCI_WRITE_BLOCK; + write_blk->wslot.slot = devfn_to_wslot(pdev->devfn); + write_blk->block_id = block_id; + write_blk->byte_count = len; + memcpy(write_blk->bytes, buf, len); + pkt_size = offsetof(struct pci_write_block, bytes) + len; + /* + * This quirk is required on some hosts shipped around 2018, because + * these hosts don't check the pkt_size correctly (new hosts have been + * fixed since early 2019). The quirk is also safe on very old hosts + * and new hosts, because, on them, what really matters is the length + * specified in write_blk->byte_count. + */ + pkt_size += sizeof(pkt.reserved); + + ret = vmbus_sendpacket(hbus->hdev->channel, write_blk, pkt_size, + (unsigned long)&pkt.pkt, VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (ret) + return ret; + + ret = wait_for_response(hbus->hdev, &comp_pkt.host_event); + if (ret) + return ret; + + if (comp_pkt.completion_status != 0) { + dev_err(&hbus->hdev->device, + "Write Config Block failed: 0x%x\n", + comp_pkt.completion_status); + return -EIO; + } + + return 0; +} + +/** + * hv_register_block_invalidate() - Invoked when a config block invalidation + * arrives from the back-end driver. + * @pdev: The PCI driver's representation for this device. + * @context: Identifies the device. + * @block_invalidate: Identifies all of the blocks being invalidated. + * + * Return: 0 on success, -errno on failure + */ +static int hv_register_block_invalidate(struct pci_dev *pdev, void *context, + void (*block_invalidate)(void *context, + u64 block_mask)) +{ + struct hv_pcibus_device *hbus = + container_of(pdev->bus->sysdata, struct hv_pcibus_device, + sysdata); + struct hv_pci_dev *hpdev; + + hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn)); + if (!hpdev) + return -ENODEV; + + hpdev->block_invalidate = block_invalidate; + hpdev->invalidate_context = context; + + put_pcichild(hpdev); + return 0; + +} + +/* Interrupt management hooks */ +static void hv_int_desc_free(struct hv_pci_dev *hpdev, + struct tran_int_desc *int_desc) +{ + struct pci_delete_interrupt *int_pkt; + struct { + struct pci_packet pkt; + u8 buffer[sizeof(struct pci_delete_interrupt)]; + } ctxt; + + if (!int_desc->vector_count) { + kfree(int_desc); + return; + } + memset(&ctxt, 0, sizeof(ctxt)); + int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message; + int_pkt->message_type.type = + PCI_DELETE_INTERRUPT_MESSAGE; + int_pkt->wslot.slot = hpdev->desc.win_slot.slot; + int_pkt->int_desc = *int_desc; + vmbus_sendpacket(hpdev->hbus->hdev->channel, int_pkt, sizeof(*int_pkt), + 0, VM_PKT_DATA_INBAND, 0); + kfree(int_desc); +} + +/** + * hv_msi_free() - Free the MSI. + * @domain: The interrupt domain pointer + * @info: Extra MSI-related context + * @irq: Identifies the IRQ. + * + * The Hyper-V parent partition and hypervisor are tracking the + * messages that are in use, keeping the interrupt redirection + * table up to date. This callback sends a message that frees + * the IRT entry and related tracking nonsense. + */ +static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info, + unsigned int irq) +{ + struct hv_pcibus_device *hbus; + struct hv_pci_dev *hpdev; + struct pci_dev *pdev; + struct tran_int_desc *int_desc; + struct irq_data *irq_data = irq_domain_get_irq_data(domain, irq); + struct msi_desc *msi = irq_data_get_msi_desc(irq_data); + + pdev = msi_desc_to_pci_dev(msi); + hbus = info->data; + int_desc = irq_data_get_irq_chip_data(irq_data); + if (!int_desc) + return; + + irq_data->chip_data = NULL; + hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn)); + if (!hpdev) { + kfree(int_desc); + return; + } + + hv_int_desc_free(hpdev, int_desc); + put_pcichild(hpdev); +} + +static void hv_irq_mask(struct irq_data *data) +{ + pci_msi_mask_irq(data); + if (data->parent_data->chip->irq_mask) + irq_chip_mask_parent(data); +} + +static void hv_irq_unmask(struct irq_data *data) +{ + hv_arch_irq_unmask(data); + + if (data->parent_data->chip->irq_unmask) + irq_chip_unmask_parent(data); + pci_msi_unmask_irq(data); +} + +struct compose_comp_ctxt { + struct hv_pci_compl comp_pkt; + struct tran_int_desc int_desc; +}; + +static void hv_pci_compose_compl(void *context, struct pci_response *resp, + int resp_packet_size) +{ + struct compose_comp_ctxt *comp_pkt = context; + struct pci_create_int_response *int_resp = + (struct pci_create_int_response *)resp; + + if (resp_packet_size < sizeof(*int_resp)) { + comp_pkt->comp_pkt.completion_status = -1; + goto out; + } + comp_pkt->comp_pkt.completion_status = resp->status; + comp_pkt->int_desc = int_resp->int_desc; +out: + complete(&comp_pkt->comp_pkt.host_event); +} + +static u32 hv_compose_msi_req_v1( + struct pci_create_interrupt *int_pkt, + u32 slot, u8 vector, u16 vector_count) +{ + int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE; + int_pkt->wslot.slot = slot; + int_pkt->int_desc.vector = vector; + int_pkt->int_desc.vector_count = vector_count; + int_pkt->int_desc.delivery_mode = DELIVERY_MODE; + + /* + * Create MSI w/ dummy vCPU set, overwritten by subsequent retarget in + * hv_irq_unmask(). + */ + int_pkt->int_desc.cpu_mask = CPU_AFFINITY_ALL; + + return sizeof(*int_pkt); +} + +/* + * The vCPU selected by hv_compose_multi_msi_req_get_cpu() and + * hv_compose_msi_req_get_cpu() is a "dummy" vCPU because the final vCPU to be + * interrupted is specified later in hv_irq_unmask() and communicated to Hyper-V + * via the HVCALL_RETARGET_INTERRUPT hypercall. But the choice of dummy vCPU is + * not irrelevant because Hyper-V chooses the physical CPU to handle the + * interrupts based on the vCPU specified in message sent to the vPCI VSP in + * hv_compose_msi_msg(). Hyper-V's choice of pCPU is not visible to the guest, + * but assigning too many vPCI device interrupts to the same pCPU can cause a + * performance bottleneck. So we spread out the dummy vCPUs to influence Hyper-V + * to spread out the pCPUs that it selects. + * + * For the single-MSI and MSI-X cases, it's OK for hv_compose_msi_req_get_cpu() + * to always return the same dummy vCPU, because a second call to + * hv_compose_msi_msg() contains the "real" vCPU, causing Hyper-V to choose a + * new pCPU for the interrupt. But for the multi-MSI case, the second call to + * hv_compose_msi_msg() exits without sending a message to the vPCI VSP, so the + * original dummy vCPU is used. This dummy vCPU must be round-robin'ed so that + * the pCPUs are spread out. All interrupts for a multi-MSI device end up using + * the same pCPU, even though the vCPUs will be spread out by later calls + * to hv_irq_unmask(), but that is the best we can do now. + * + * With Hyper-V in Nov 2022, the HVCALL_RETARGET_INTERRUPT hypercall does *not* + * cause Hyper-V to reselect the pCPU based on the specified vCPU. Such an + * enhancement is planned for a future version. With that enhancement, the + * dummy vCPU selection won't matter, and interrupts for the same multi-MSI + * device will be spread across multiple pCPUs. + */ + +/* + * Create MSI w/ dummy vCPU set targeting just one vCPU, overwritten + * by subsequent retarget in hv_irq_unmask(). + */ +static int hv_compose_msi_req_get_cpu(const struct cpumask *affinity) +{ + return cpumask_first_and(affinity, cpu_online_mask); +} + +/* + * Make sure the dummy vCPU values for multi-MSI don't all point to vCPU0. + */ +static int hv_compose_multi_msi_req_get_cpu(void) +{ + static DEFINE_SPINLOCK(multi_msi_cpu_lock); + + /* -1 means starting with CPU 0 */ + static int cpu_next = -1; + + unsigned long flags; + int cpu; + + spin_lock_irqsave(&multi_msi_cpu_lock, flags); + + cpu_next = cpumask_next_wrap(cpu_next, cpu_online_mask, nr_cpu_ids, + false); + cpu = cpu_next; + + spin_unlock_irqrestore(&multi_msi_cpu_lock, flags); + + return cpu; +} + +static u32 hv_compose_msi_req_v2( + struct pci_create_interrupt2 *int_pkt, int cpu, + u32 slot, u8 vector, u16 vector_count) +{ + int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE2; + int_pkt->wslot.slot = slot; + int_pkt->int_desc.vector = vector; + int_pkt->int_desc.vector_count = vector_count; + int_pkt->int_desc.delivery_mode = DELIVERY_MODE; + int_pkt->int_desc.processor_array[0] = + hv_cpu_number_to_vp_number(cpu); + int_pkt->int_desc.processor_count = 1; + + return sizeof(*int_pkt); +} + +static u32 hv_compose_msi_req_v3( + struct pci_create_interrupt3 *int_pkt, int cpu, + u32 slot, u32 vector, u16 vector_count) +{ + int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE3; + int_pkt->wslot.slot = slot; + int_pkt->int_desc.vector = vector; + int_pkt->int_desc.reserved = 0; + int_pkt->int_desc.vector_count = vector_count; + int_pkt->int_desc.delivery_mode = DELIVERY_MODE; + int_pkt->int_desc.processor_array[0] = + hv_cpu_number_to_vp_number(cpu); + int_pkt->int_desc.processor_count = 1; + + return sizeof(*int_pkt); +} + +/** + * hv_compose_msi_msg() - Supplies a valid MSI address/data + * @data: Everything about this MSI + * @msg: Buffer that is filled in by this function + * + * This function unpacks the IRQ looking for target CPU set, IDT + * vector and mode and sends a message to the parent partition + * asking for a mapping for that tuple in this partition. The + * response supplies a data value and address to which that data + * should be written to trigger that interrupt. + */ +static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct hv_pcibus_device *hbus; + struct vmbus_channel *channel; + struct hv_pci_dev *hpdev; + struct pci_bus *pbus; + struct pci_dev *pdev; + const struct cpumask *dest; + struct compose_comp_ctxt comp; + struct tran_int_desc *int_desc; + struct msi_desc *msi_desc; + /* + * vector_count should be u16: see hv_msi_desc, hv_msi_desc2 + * and hv_msi_desc3. vector must be u32: see hv_msi_desc3. + */ + u16 vector_count; + u32 vector; + struct { + struct pci_packet pci_pkt; + union { + struct pci_create_interrupt v1; + struct pci_create_interrupt2 v2; + struct pci_create_interrupt3 v3; + } int_pkts; + } __packed ctxt; + bool multi_msi; + u64 trans_id; + u32 size; + int ret; + int cpu; + + msi_desc = irq_data_get_msi_desc(data); + multi_msi = !msi_desc->pci.msi_attrib.is_msix && + msi_desc->nvec_used > 1; + + /* Reuse the previous allocation */ + if (data->chip_data && multi_msi) { + int_desc = data->chip_data; + msg->address_hi = int_desc->address >> 32; + msg->address_lo = int_desc->address & 0xffffffff; + msg->data = int_desc->data; + return; + } + + pdev = msi_desc_to_pci_dev(msi_desc); + dest = irq_data_get_effective_affinity_mask(data); + pbus = pdev->bus; + hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata); + channel = hbus->hdev->channel; + hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn)); + if (!hpdev) + goto return_null_message; + + /* Free any previous message that might have already been composed. */ + if (data->chip_data && !multi_msi) { + int_desc = data->chip_data; + data->chip_data = NULL; + hv_int_desc_free(hpdev, int_desc); + } + + int_desc = kzalloc(sizeof(*int_desc), GFP_ATOMIC); + if (!int_desc) + goto drop_reference; + + if (multi_msi) { + /* + * If this is not the first MSI of Multi MSI, we already have + * a mapping. Can exit early. + */ + if (msi_desc->irq != data->irq) { + data->chip_data = int_desc; + int_desc->address = msi_desc->msg.address_lo | + (u64)msi_desc->msg.address_hi << 32; + int_desc->data = msi_desc->msg.data + + (data->irq - msi_desc->irq); + msg->address_hi = msi_desc->msg.address_hi; + msg->address_lo = msi_desc->msg.address_lo; + msg->data = int_desc->data; + put_pcichild(hpdev); + return; + } + /* + * The vector we select here is a dummy value. The correct + * value gets sent to the hypervisor in unmask(). This needs + * to be aligned with the count, and also not zero. Multi-msi + * is powers of 2 up to 32, so 32 will always work here. + */ + vector = 32; + vector_count = msi_desc->nvec_used; + cpu = hv_compose_multi_msi_req_get_cpu(); + } else { + vector = hv_msi_get_int_vector(data); + vector_count = 1; + cpu = hv_compose_msi_req_get_cpu(dest); + } + + /* + * hv_compose_msi_req_v1 and v2 are for x86 only, meaning 'vector' + * can't exceed u8. Cast 'vector' down to u8 for v1/v2 explicitly + * for better readability. + */ + memset(&ctxt, 0, sizeof(ctxt)); + init_completion(&comp.comp_pkt.host_event); + ctxt.pci_pkt.completion_func = hv_pci_compose_compl; + ctxt.pci_pkt.compl_ctxt = ∁ + + switch (hbus->protocol_version) { + case PCI_PROTOCOL_VERSION_1_1: + size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1, + hpdev->desc.win_slot.slot, + (u8)vector, + vector_count); + break; + + case PCI_PROTOCOL_VERSION_1_2: + case PCI_PROTOCOL_VERSION_1_3: + size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2, + cpu, + hpdev->desc.win_slot.slot, + (u8)vector, + vector_count); + break; + + case PCI_PROTOCOL_VERSION_1_4: + size = hv_compose_msi_req_v3(&ctxt.int_pkts.v3, + cpu, + hpdev->desc.win_slot.slot, + vector, + vector_count); + break; + + default: + /* As we only negotiate protocol versions known to this driver, + * this path should never hit. However, this is it not a hot + * path so we print a message to aid future updates. + */ + dev_err(&hbus->hdev->device, + "Unexpected vPCI protocol, update driver."); + goto free_int_desc; + } + + ret = vmbus_sendpacket_getid(hpdev->hbus->hdev->channel, &ctxt.int_pkts, + size, (unsigned long)&ctxt.pci_pkt, + &trans_id, VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (ret) { + dev_err(&hbus->hdev->device, + "Sending request for interrupt failed: 0x%x", + comp.comp_pkt.completion_status); + goto free_int_desc; + } + + /* + * Prevents hv_pci_onchannelcallback() from running concurrently + * in the tasklet. + */ + tasklet_disable_in_atomic(&channel->callback_event); + + /* + * Since this function is called with IRQ locks held, can't + * do normal wait for completion; instead poll. + */ + while (!try_wait_for_completion(&comp.comp_pkt.host_event)) { + unsigned long flags; + + /* 0xFFFF means an invalid PCI VENDOR ID. */ + if (hv_pcifront_get_vendor_id(hpdev) == 0xFFFF) { + dev_err_once(&hbus->hdev->device, + "the device has gone\n"); + goto enable_tasklet; + } + + /* + * Make sure that the ring buffer data structure doesn't get + * freed while we dereference the ring buffer pointer. Test + * for the channel's onchannel_callback being NULL within a + * sched_lock critical section. See also the inline comments + * in vmbus_reset_channel_cb(). + */ + spin_lock_irqsave(&channel->sched_lock, flags); + if (unlikely(channel->onchannel_callback == NULL)) { + spin_unlock_irqrestore(&channel->sched_lock, flags); + goto enable_tasklet; + } + hv_pci_onchannelcallback(hbus); + spin_unlock_irqrestore(&channel->sched_lock, flags); + + udelay(100); + } + + tasklet_enable(&channel->callback_event); + + if (comp.comp_pkt.completion_status < 0) { + dev_err(&hbus->hdev->device, + "Request for interrupt failed: 0x%x", + comp.comp_pkt.completion_status); + goto free_int_desc; + } + + /* + * Record the assignment so that this can be unwound later. Using + * irq_set_chip_data() here would be appropriate, but the lock it takes + * is already held. + */ + *int_desc = comp.int_desc; + data->chip_data = int_desc; + + /* Pass up the result. */ + msg->address_hi = comp.int_desc.address >> 32; + msg->address_lo = comp.int_desc.address & 0xffffffff; + msg->data = comp.int_desc.data; + + put_pcichild(hpdev); + return; + +enable_tasklet: + tasklet_enable(&channel->callback_event); + /* + * The completion packet on the stack becomes invalid after 'return'; + * remove the ID from the VMbus requestor if the identifier is still + * mapped to/associated with the packet. (The identifier could have + * been 're-used', i.e., already removed and (re-)mapped.) + * + * Cf. hv_pci_onchannelcallback(). + */ + vmbus_request_addr_match(channel, trans_id, (unsigned long)&ctxt.pci_pkt); +free_int_desc: + kfree(int_desc); +drop_reference: + put_pcichild(hpdev); +return_null_message: + msg->address_hi = 0; + msg->address_lo = 0; + msg->data = 0; +} + +/* HW Interrupt Chip Descriptor */ +static struct irq_chip hv_msi_irq_chip = { + .name = "Hyper-V PCIe MSI", + .irq_compose_msi_msg = hv_compose_msi_msg, + .irq_set_affinity = irq_chip_set_affinity_parent, +#ifdef CONFIG_X86 + .irq_ack = irq_chip_ack_parent, +#elif defined(CONFIG_ARM64) + .irq_eoi = irq_chip_eoi_parent, +#endif + .irq_mask = hv_irq_mask, + .irq_unmask = hv_irq_unmask, +}; + +static struct msi_domain_ops hv_msi_ops = { + .msi_prepare = hv_msi_prepare, + .msi_free = hv_msi_free, +}; + +/** + * hv_pcie_init_irq_domain() - Initialize IRQ domain + * @hbus: The root PCI bus + * + * This function creates an IRQ domain which will be used for + * interrupts from devices that have been passed through. These + * devices only support MSI and MSI-X, not line-based interrupts + * or simulations of line-based interrupts through PCIe's + * fabric-layer messages. Because interrupts are remapped, we + * can support multi-message MSI here. + * + * Return: '0' on success and error value on failure + */ +static int hv_pcie_init_irq_domain(struct hv_pcibus_device *hbus) +{ + hbus->msi_info.chip = &hv_msi_irq_chip; + hbus->msi_info.ops = &hv_msi_ops; + hbus->msi_info.flags = (MSI_FLAG_USE_DEF_DOM_OPS | + MSI_FLAG_USE_DEF_CHIP_OPS | MSI_FLAG_MULTI_PCI_MSI | + MSI_FLAG_PCI_MSIX); + hbus->msi_info.handler = FLOW_HANDLER; + hbus->msi_info.handler_name = FLOW_NAME; + hbus->msi_info.data = hbus; + hbus->irq_domain = pci_msi_create_irq_domain(hbus->fwnode, + &hbus->msi_info, + hv_pci_get_root_domain()); + if (!hbus->irq_domain) { + dev_err(&hbus->hdev->device, + "Failed to build an MSI IRQ domain\n"); + return -ENODEV; + } + + dev_set_msi_domain(&hbus->bridge->dev, hbus->irq_domain); + + return 0; +} + +/** + * get_bar_size() - Get the address space consumed by a BAR + * @bar_val: Value that a BAR returned after -1 was written + * to it. + * + * This function returns the size of the BAR, rounded up to 1 + * page. It has to be rounded up because the hypervisor's page + * table entry that maps the BAR into the VM can't specify an + * offset within a page. The invariant is that the hypervisor + * must place any BARs of smaller than page length at the + * beginning of a page. + * + * Return: Size in bytes of the consumed MMIO space. + */ +static u64 get_bar_size(u64 bar_val) +{ + return round_up((1 + ~(bar_val & PCI_BASE_ADDRESS_MEM_MASK)), + PAGE_SIZE); +} + +/** + * survey_child_resources() - Total all MMIO requirements + * @hbus: Root PCI bus, as understood by this driver + */ +static void survey_child_resources(struct hv_pcibus_device *hbus) +{ + struct hv_pci_dev *hpdev; + resource_size_t bar_size = 0; + unsigned long flags; + struct completion *event; + u64 bar_val; + int i; + + /* If nobody is waiting on the answer, don't compute it. */ + event = xchg(&hbus->survey_event, NULL); + if (!event) + return; + + /* If the answer has already been computed, go with it. */ + if (hbus->low_mmio_space || hbus->high_mmio_space) { + complete(event); + return; + } + + spin_lock_irqsave(&hbus->device_list_lock, flags); + + /* + * Due to an interesting quirk of the PCI spec, all memory regions + * for a child device are a power of 2 in size and aligned in memory, + * so it's sufficient to just add them up without tracking alignment. + */ + list_for_each_entry(hpdev, &hbus->children, list_entry) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (hpdev->probed_bar[i] & PCI_BASE_ADDRESS_SPACE_IO) + dev_err(&hbus->hdev->device, + "There's an I/O BAR in this list!\n"); + + if (hpdev->probed_bar[i] != 0) { + /* + * A probed BAR has all the upper bits set that + * can be changed. + */ + + bar_val = hpdev->probed_bar[i]; + if (bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64) + bar_val |= + ((u64)hpdev->probed_bar[++i] << 32); + else + bar_val |= 0xffffffff00000000ULL; + + bar_size = get_bar_size(bar_val); + + if (bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64) + hbus->high_mmio_space += bar_size; + else + hbus->low_mmio_space += bar_size; + } + } + } + + spin_unlock_irqrestore(&hbus->device_list_lock, flags); + complete(event); +} + +/** + * prepopulate_bars() - Fill in BARs with defaults + * @hbus: Root PCI bus, as understood by this driver + * + * The core PCI driver code seems much, much happier if the BARs + * for a device have values upon first scan. So fill them in. + * The algorithm below works down from large sizes to small, + * attempting to pack the assignments optimally. The assumption, + * enforced in other parts of the code, is that the beginning of + * the memory-mapped I/O space will be aligned on the largest + * BAR size. + */ +static void prepopulate_bars(struct hv_pcibus_device *hbus) +{ + resource_size_t high_size = 0; + resource_size_t low_size = 0; + resource_size_t high_base = 0; + resource_size_t low_base = 0; + resource_size_t bar_size; + struct hv_pci_dev *hpdev; + unsigned long flags; + u64 bar_val; + u32 command; + bool high; + int i; + + if (hbus->low_mmio_space) { + low_size = 1ULL << (63 - __builtin_clzll(hbus->low_mmio_space)); + low_base = hbus->low_mmio_res->start; + } + + if (hbus->high_mmio_space) { + high_size = 1ULL << + (63 - __builtin_clzll(hbus->high_mmio_space)); + high_base = hbus->high_mmio_res->start; + } + + spin_lock_irqsave(&hbus->device_list_lock, flags); + + /* + * Clear the memory enable bit, in case it's already set. This occurs + * in the suspend path of hibernation, where the device is suspended, + * resumed and suspended again: see hibernation_snapshot() and + * hibernation_platform_enter(). + * + * If the memory enable bit is already set, Hyper-V silently ignores + * the below BAR updates, and the related PCI device driver can not + * work, because reading from the device register(s) always returns + * 0xFFFFFFFF (PCI_ERROR_RESPONSE). + */ + list_for_each_entry(hpdev, &hbus->children, list_entry) { + _hv_pcifront_read_config(hpdev, PCI_COMMAND, 2, &command); + command &= ~PCI_COMMAND_MEMORY; + _hv_pcifront_write_config(hpdev, PCI_COMMAND, 2, command); + } + + /* Pick addresses for the BARs. */ + do { + list_for_each_entry(hpdev, &hbus->children, list_entry) { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + bar_val = hpdev->probed_bar[i]; + if (bar_val == 0) + continue; + high = bar_val & PCI_BASE_ADDRESS_MEM_TYPE_64; + if (high) { + bar_val |= + ((u64)hpdev->probed_bar[i + 1] + << 32); + } else { + bar_val |= 0xffffffffULL << 32; + } + bar_size = get_bar_size(bar_val); + if (high) { + if (high_size != bar_size) { + i++; + continue; + } + _hv_pcifront_write_config(hpdev, + PCI_BASE_ADDRESS_0 + (4 * i), + 4, + (u32)(high_base & 0xffffff00)); + i++; + _hv_pcifront_write_config(hpdev, + PCI_BASE_ADDRESS_0 + (4 * i), + 4, (u32)(high_base >> 32)); + high_base += bar_size; + } else { + if (low_size != bar_size) + continue; + _hv_pcifront_write_config(hpdev, + PCI_BASE_ADDRESS_0 + (4 * i), + 4, + (u32)(low_base & 0xffffff00)); + low_base += bar_size; + } + } + if (high_size <= 1 && low_size <= 1) { + /* + * No need to set the PCI_COMMAND_MEMORY bit as + * the core PCI driver doesn't require the bit + * to be pre-set. Actually here we intentionally + * keep the bit off so that the PCI BAR probing + * in the core PCI driver doesn't cause Hyper-V + * to unnecessarily unmap/map the virtual BARs + * from/to the physical BARs multiple times. + * This reduces the VM boot time significantly + * if the BAR sizes are huge. + */ + break; + } + } + + high_size >>= 1; + low_size >>= 1; + } while (high_size || low_size); + + spin_unlock_irqrestore(&hbus->device_list_lock, flags); +} + +/* + * Assign entries in sysfs pci slot directory. + * + * Note that this function does not need to lock the children list + * because it is called from pci_devices_present_work which + * is serialized with hv_eject_device_work because they are on the + * same ordered workqueue. Therefore hbus->children list will not change + * even when pci_create_slot sleeps. + */ +static void hv_pci_assign_slots(struct hv_pcibus_device *hbus) +{ + struct hv_pci_dev *hpdev; + char name[SLOT_NAME_SIZE]; + int slot_nr; + + list_for_each_entry(hpdev, &hbus->children, list_entry) { + if (hpdev->pci_slot) + continue; + + slot_nr = PCI_SLOT(wslot_to_devfn(hpdev->desc.win_slot.slot)); + snprintf(name, SLOT_NAME_SIZE, "%u", hpdev->desc.ser); + hpdev->pci_slot = pci_create_slot(hbus->bridge->bus, slot_nr, + name, NULL); + if (IS_ERR(hpdev->pci_slot)) { + pr_warn("pci_create slot %s failed\n", name); + hpdev->pci_slot = NULL; + } + } +} + +/* + * Remove entries in sysfs pci slot directory. + */ +static void hv_pci_remove_slots(struct hv_pcibus_device *hbus) +{ + struct hv_pci_dev *hpdev; + + list_for_each_entry(hpdev, &hbus->children, list_entry) { + if (!hpdev->pci_slot) + continue; + pci_destroy_slot(hpdev->pci_slot); + hpdev->pci_slot = NULL; + } +} + +/* + * Set NUMA node for the devices on the bus + */ +static void hv_pci_assign_numa_node(struct hv_pcibus_device *hbus) +{ + struct pci_dev *dev; + struct pci_bus *bus = hbus->bridge->bus; + struct hv_pci_dev *hv_dev; + + list_for_each_entry(dev, &bus->devices, bus_list) { + hv_dev = get_pcichild_wslot(hbus, devfn_to_wslot(dev->devfn)); + if (!hv_dev) + continue; + + if (hv_dev->desc.flags & HV_PCI_DEVICE_FLAG_NUMA_AFFINITY && + hv_dev->desc.virtual_numa_node < num_possible_nodes()) + /* + * The kernel may boot with some NUMA nodes offline + * (e.g. in a KDUMP kernel) or with NUMA disabled via + * "numa=off". In those cases, adjust the host provided + * NUMA node to a valid NUMA node used by the kernel. + */ + set_dev_node(&dev->dev, + numa_map_to_online_node( + hv_dev->desc.virtual_numa_node)); + + put_pcichild(hv_dev); + } +} + +/** + * create_root_hv_pci_bus() - Expose a new root PCI bus + * @hbus: Root PCI bus, as understood by this driver + * + * Return: 0 on success, -errno on failure + */ +static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus) +{ + int error; + struct pci_host_bridge *bridge = hbus->bridge; + + bridge->dev.parent = &hbus->hdev->device; + bridge->sysdata = &hbus->sysdata; + bridge->ops = &hv_pcifront_ops; + + error = pci_scan_root_bus_bridge(bridge); + if (error) + return error; + + pci_lock_rescan_remove(); + hv_pci_assign_numa_node(hbus); + pci_bus_assign_resources(bridge->bus); + hv_pci_assign_slots(hbus); + pci_bus_add_devices(bridge->bus); + pci_unlock_rescan_remove(); + hbus->state = hv_pcibus_installed; + return 0; +} + +struct q_res_req_compl { + struct completion host_event; + struct hv_pci_dev *hpdev; +}; + +/** + * q_resource_requirements() - Query Resource Requirements + * @context: The completion context. + * @resp: The response that came from the host. + * @resp_packet_size: The size in bytes of resp. + * + * This function is invoked on completion of a Query Resource + * Requirements packet. + */ +static void q_resource_requirements(void *context, struct pci_response *resp, + int resp_packet_size) +{ + struct q_res_req_compl *completion = context; + struct pci_q_res_req_response *q_res_req = + (struct pci_q_res_req_response *)resp; + s32 status; + int i; + + status = (resp_packet_size < sizeof(*q_res_req)) ? -1 : resp->status; + if (status < 0) { + dev_err(&completion->hpdev->hbus->hdev->device, + "query resource requirements failed: %x\n", + status); + } else { + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + completion->hpdev->probed_bar[i] = + q_res_req->probed_bar[i]; + } + } + + complete(&completion->host_event); +} + +/** + * new_pcichild_device() - Create a new child device + * @hbus: The internal struct tracking this root PCI bus. + * @desc: The information supplied so far from the host + * about the device. + * + * This function creates the tracking structure for a new child + * device and kicks off the process of figuring out what it is. + * + * Return: Pointer to the new tracking struct + */ +static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus, + struct hv_pcidev_description *desc) +{ + struct hv_pci_dev *hpdev; + struct pci_child_message *res_req; + struct q_res_req_compl comp_pkt; + struct { + struct pci_packet init_packet; + u8 buffer[sizeof(struct pci_child_message)]; + } pkt; + unsigned long flags; + int ret; + + hpdev = kzalloc(sizeof(*hpdev), GFP_KERNEL); + if (!hpdev) + return NULL; + + hpdev->hbus = hbus; + + memset(&pkt, 0, sizeof(pkt)); + init_completion(&comp_pkt.host_event); + comp_pkt.hpdev = hpdev; + pkt.init_packet.compl_ctxt = &comp_pkt; + pkt.init_packet.completion_func = q_resource_requirements; + res_req = (struct pci_child_message *)&pkt.init_packet.message; + res_req->message_type.type = PCI_QUERY_RESOURCE_REQUIREMENTS; + res_req->wslot.slot = desc->win_slot.slot; + + ret = vmbus_sendpacket(hbus->hdev->channel, res_req, + sizeof(struct pci_child_message), + (unsigned long)&pkt.init_packet, + VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (ret) + goto error; + + if (wait_for_response(hbus->hdev, &comp_pkt.host_event)) + goto error; + + hpdev->desc = *desc; + refcount_set(&hpdev->refs, 1); + get_pcichild(hpdev); + spin_lock_irqsave(&hbus->device_list_lock, flags); + + list_add_tail(&hpdev->list_entry, &hbus->children); + spin_unlock_irqrestore(&hbus->device_list_lock, flags); + return hpdev; + +error: + kfree(hpdev); + return NULL; +} + +/** + * get_pcichild_wslot() - Find device from slot + * @hbus: Root PCI bus, as understood by this driver + * @wslot: Location on the bus + * + * This function looks up a PCI device and returns the internal + * representation of it. It acquires a reference on it, so that + * the device won't be deleted while somebody is using it. The + * caller is responsible for calling put_pcichild() to release + * this reference. + * + * Return: Internal representation of a PCI device + */ +static struct hv_pci_dev *get_pcichild_wslot(struct hv_pcibus_device *hbus, + u32 wslot) +{ + unsigned long flags; + struct hv_pci_dev *iter, *hpdev = NULL; + + spin_lock_irqsave(&hbus->device_list_lock, flags); + list_for_each_entry(iter, &hbus->children, list_entry) { + if (iter->desc.win_slot.slot == wslot) { + hpdev = iter; + get_pcichild(hpdev); + break; + } + } + spin_unlock_irqrestore(&hbus->device_list_lock, flags); + + return hpdev; +} + +/** + * pci_devices_present_work() - Handle new list of child devices + * @work: Work struct embedded in struct hv_dr_work + * + * "Bus Relations" is the Windows term for "children of this + * bus." The terminology is preserved here for people trying to + * debug the interaction between Hyper-V and Linux. This + * function is called when the parent partition reports a list + * of functions that should be observed under this PCI Express + * port (bus). + * + * This function updates the list, and must tolerate being + * called multiple times with the same information. The typical + * number of child devices is one, with very atypical cases + * involving three or four, so the algorithms used here can be + * simple and inefficient. + * + * It must also treat the omission of a previously observed device as + * notification that the device no longer exists. + * + * Note that this function is serialized with hv_eject_device_work(), + * because both are pushed to the ordered workqueue hbus->wq. + */ +static void pci_devices_present_work(struct work_struct *work) +{ + u32 child_no; + bool found; + struct hv_pcidev_description *new_desc; + struct hv_pci_dev *hpdev; + struct hv_pcibus_device *hbus; + struct list_head removed; + struct hv_dr_work *dr_wrk; + struct hv_dr_state *dr = NULL; + unsigned long flags; + + dr_wrk = container_of(work, struct hv_dr_work, wrk); + hbus = dr_wrk->bus; + kfree(dr_wrk); + + INIT_LIST_HEAD(&removed); + + /* Pull this off the queue and process it if it was the last one. */ + spin_lock_irqsave(&hbus->device_list_lock, flags); + while (!list_empty(&hbus->dr_list)) { + dr = list_first_entry(&hbus->dr_list, struct hv_dr_state, + list_entry); + list_del(&dr->list_entry); + + /* Throw this away if the list still has stuff in it. */ + if (!list_empty(&hbus->dr_list)) { + kfree(dr); + continue; + } + } + spin_unlock_irqrestore(&hbus->device_list_lock, flags); + + if (!dr) + return; + + mutex_lock(&hbus->state_lock); + + /* First, mark all existing children as reported missing. */ + spin_lock_irqsave(&hbus->device_list_lock, flags); + list_for_each_entry(hpdev, &hbus->children, list_entry) { + hpdev->reported_missing = true; + } + spin_unlock_irqrestore(&hbus->device_list_lock, flags); + + /* Next, add back any reported devices. */ + for (child_no = 0; child_no < dr->device_count; child_no++) { + found = false; + new_desc = &dr->func[child_no]; + + spin_lock_irqsave(&hbus->device_list_lock, flags); + list_for_each_entry(hpdev, &hbus->children, list_entry) { + if ((hpdev->desc.win_slot.slot == new_desc->win_slot.slot) && + (hpdev->desc.v_id == new_desc->v_id) && + (hpdev->desc.d_id == new_desc->d_id) && + (hpdev->desc.ser == new_desc->ser)) { + hpdev->reported_missing = false; + found = true; + } + } + spin_unlock_irqrestore(&hbus->device_list_lock, flags); + + if (!found) { + hpdev = new_pcichild_device(hbus, new_desc); + if (!hpdev) + dev_err(&hbus->hdev->device, + "couldn't record a child device.\n"); + } + } + + /* Move missing children to a list on the stack. */ + spin_lock_irqsave(&hbus->device_list_lock, flags); + do { + found = false; + list_for_each_entry(hpdev, &hbus->children, list_entry) { + if (hpdev->reported_missing) { + found = true; + put_pcichild(hpdev); + list_move_tail(&hpdev->list_entry, &removed); + break; + } + } + } while (found); + spin_unlock_irqrestore(&hbus->device_list_lock, flags); + + /* Delete everything that should no longer exist. */ + while (!list_empty(&removed)) { + hpdev = list_first_entry(&removed, struct hv_pci_dev, + list_entry); + list_del(&hpdev->list_entry); + + if (hpdev->pci_slot) + pci_destroy_slot(hpdev->pci_slot); + + put_pcichild(hpdev); + } + + switch (hbus->state) { + case hv_pcibus_installed: + /* + * Tell the core to rescan bus + * because there may have been changes. + */ + pci_lock_rescan_remove(); + pci_scan_child_bus(hbus->bridge->bus); + hv_pci_assign_numa_node(hbus); + hv_pci_assign_slots(hbus); + pci_unlock_rescan_remove(); + break; + + case hv_pcibus_init: + case hv_pcibus_probed: + survey_child_resources(hbus); + break; + + default: + break; + } + + mutex_unlock(&hbus->state_lock); + + kfree(dr); +} + +/** + * hv_pci_start_relations_work() - Queue work to start device discovery + * @hbus: Root PCI bus, as understood by this driver + * @dr: The list of children returned from host + * + * Return: 0 on success, -errno on failure + */ +static int hv_pci_start_relations_work(struct hv_pcibus_device *hbus, + struct hv_dr_state *dr) +{ + struct hv_dr_work *dr_wrk; + unsigned long flags; + bool pending_dr; + + if (hbus->state == hv_pcibus_removing) { + dev_info(&hbus->hdev->device, + "PCI VMBus BUS_RELATIONS: ignored\n"); + return -ENOENT; + } + + dr_wrk = kzalloc(sizeof(*dr_wrk), GFP_NOWAIT); + if (!dr_wrk) + return -ENOMEM; + + INIT_WORK(&dr_wrk->wrk, pci_devices_present_work); + dr_wrk->bus = hbus; + + spin_lock_irqsave(&hbus->device_list_lock, flags); + /* + * If pending_dr is true, we have already queued a work, + * which will see the new dr. Otherwise, we need to + * queue a new work. + */ + pending_dr = !list_empty(&hbus->dr_list); + list_add_tail(&dr->list_entry, &hbus->dr_list); + spin_unlock_irqrestore(&hbus->device_list_lock, flags); + + if (pending_dr) + kfree(dr_wrk); + else + queue_work(hbus->wq, &dr_wrk->wrk); + + return 0; +} + +/** + * hv_pci_devices_present() - Handle list of new children + * @hbus: Root PCI bus, as understood by this driver + * @relations: Packet from host listing children + * + * Process a new list of devices on the bus. The list of devices is + * discovered by VSP and sent to us via VSP message PCI_BUS_RELATIONS, + * whenever a new list of devices for this bus appears. + */ +static void hv_pci_devices_present(struct hv_pcibus_device *hbus, + struct pci_bus_relations *relations) +{ + struct hv_dr_state *dr; + int i; + + dr = kzalloc(struct_size(dr, func, relations->device_count), + GFP_NOWAIT); + if (!dr) + return; + + dr->device_count = relations->device_count; + for (i = 0; i < dr->device_count; i++) { + dr->func[i].v_id = relations->func[i].v_id; + dr->func[i].d_id = relations->func[i].d_id; + dr->func[i].rev = relations->func[i].rev; + dr->func[i].prog_intf = relations->func[i].prog_intf; + dr->func[i].subclass = relations->func[i].subclass; + dr->func[i].base_class = relations->func[i].base_class; + dr->func[i].subsystem_id = relations->func[i].subsystem_id; + dr->func[i].win_slot = relations->func[i].win_slot; + dr->func[i].ser = relations->func[i].ser; + } + + if (hv_pci_start_relations_work(hbus, dr)) + kfree(dr); +} + +/** + * hv_pci_devices_present2() - Handle list of new children + * @hbus: Root PCI bus, as understood by this driver + * @relations: Packet from host listing children + * + * This function is the v2 version of hv_pci_devices_present() + */ +static void hv_pci_devices_present2(struct hv_pcibus_device *hbus, + struct pci_bus_relations2 *relations) +{ + struct hv_dr_state *dr; + int i; + + dr = kzalloc(struct_size(dr, func, relations->device_count), + GFP_NOWAIT); + if (!dr) + return; + + dr->device_count = relations->device_count; + for (i = 0; i < dr->device_count; i++) { + dr->func[i].v_id = relations->func[i].v_id; + dr->func[i].d_id = relations->func[i].d_id; + dr->func[i].rev = relations->func[i].rev; + dr->func[i].prog_intf = relations->func[i].prog_intf; + dr->func[i].subclass = relations->func[i].subclass; + dr->func[i].base_class = relations->func[i].base_class; + dr->func[i].subsystem_id = relations->func[i].subsystem_id; + dr->func[i].win_slot = relations->func[i].win_slot; + dr->func[i].ser = relations->func[i].ser; + dr->func[i].flags = relations->func[i].flags; + dr->func[i].virtual_numa_node = + relations->func[i].virtual_numa_node; + } + + if (hv_pci_start_relations_work(hbus, dr)) + kfree(dr); +} + +/** + * hv_eject_device_work() - Asynchronously handles ejection + * @work: Work struct embedded in internal device struct + * + * This function handles ejecting a device. Windows will + * attempt to gracefully eject a device, waiting 60 seconds to + * hear back from the guest OS that this completed successfully. + * If this timer expires, the device will be forcibly removed. + */ +static void hv_eject_device_work(struct work_struct *work) +{ + struct pci_eject_response *ejct_pkt; + struct hv_pcibus_device *hbus; + struct hv_pci_dev *hpdev; + struct pci_dev *pdev; + unsigned long flags; + int wslot; + struct { + struct pci_packet pkt; + u8 buffer[sizeof(struct pci_eject_response)]; + } ctxt; + + hpdev = container_of(work, struct hv_pci_dev, wrk); + hbus = hpdev->hbus; + + mutex_lock(&hbus->state_lock); + + /* + * Ejection can come before or after the PCI bus has been set up, so + * attempt to find it and tear down the bus state, if it exists. This + * must be done without constructs like pci_domain_nr(hbus->bridge->bus) + * because hbus->bridge->bus may not exist yet. + */ + wslot = wslot_to_devfn(hpdev->desc.win_slot.slot); + pdev = pci_get_domain_bus_and_slot(hbus->bridge->domain_nr, 0, wslot); + if (pdev) { + pci_lock_rescan_remove(); + pci_stop_and_remove_bus_device(pdev); + pci_dev_put(pdev); + pci_unlock_rescan_remove(); + } + + spin_lock_irqsave(&hbus->device_list_lock, flags); + list_del(&hpdev->list_entry); + spin_unlock_irqrestore(&hbus->device_list_lock, flags); + + if (hpdev->pci_slot) + pci_destroy_slot(hpdev->pci_slot); + + memset(&ctxt, 0, sizeof(ctxt)); + ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message; + ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE; + ejct_pkt->wslot.slot = hpdev->desc.win_slot.slot; + vmbus_sendpacket(hbus->hdev->channel, ejct_pkt, + sizeof(*ejct_pkt), 0, + VM_PKT_DATA_INBAND, 0); + + /* For the get_pcichild() in hv_pci_eject_device() */ + put_pcichild(hpdev); + /* For the two refs got in new_pcichild_device() */ + put_pcichild(hpdev); + put_pcichild(hpdev); + /* hpdev has been freed. Do not use it any more. */ + + mutex_unlock(&hbus->state_lock); +} + +/** + * hv_pci_eject_device() - Handles device ejection + * @hpdev: Internal device tracking struct + * + * This function is invoked when an ejection packet arrives. It + * just schedules work so that we don't re-enter the packet + * delivery code handling the ejection. + */ +static void hv_pci_eject_device(struct hv_pci_dev *hpdev) +{ + struct hv_pcibus_device *hbus = hpdev->hbus; + struct hv_device *hdev = hbus->hdev; + + if (hbus->state == hv_pcibus_removing) { + dev_info(&hdev->device, "PCI VMBus EJECT: ignored\n"); + return; + } + + get_pcichild(hpdev); + INIT_WORK(&hpdev->wrk, hv_eject_device_work); + queue_work(hbus->wq, &hpdev->wrk); +} + +/** + * hv_pci_onchannelcallback() - Handles incoming packets + * @context: Internal bus tracking struct + * + * This function is invoked whenever the host sends a packet to + * this channel (which is private to this root PCI bus). + */ +static void hv_pci_onchannelcallback(void *context) +{ + const int packet_size = 0x100; + int ret; + struct hv_pcibus_device *hbus = context; + struct vmbus_channel *chan = hbus->hdev->channel; + u32 bytes_recvd; + u64 req_id, req_addr; + struct vmpacket_descriptor *desc; + unsigned char *buffer; + int bufferlen = packet_size; + struct pci_packet *comp_packet; + struct pci_response *response; + struct pci_incoming_message *new_message; + struct pci_bus_relations *bus_rel; + struct pci_bus_relations2 *bus_rel2; + struct pci_dev_inval_block *inval; + struct pci_dev_incoming *dev_message; + struct hv_pci_dev *hpdev; + unsigned long flags; + + buffer = kmalloc(bufferlen, GFP_ATOMIC); + if (!buffer) + return; + + while (1) { + ret = vmbus_recvpacket_raw(chan, buffer, bufferlen, + &bytes_recvd, &req_id); + + if (ret == -ENOBUFS) { + kfree(buffer); + /* Handle large packet */ + bufferlen = bytes_recvd; + buffer = kmalloc(bytes_recvd, GFP_ATOMIC); + if (!buffer) + return; + continue; + } + + /* Zero length indicates there are no more packets. */ + if (ret || !bytes_recvd) + break; + + /* + * All incoming packets must be at least as large as a + * response. + */ + if (bytes_recvd <= sizeof(struct pci_response)) + continue; + desc = (struct vmpacket_descriptor *)buffer; + + switch (desc->type) { + case VM_PKT_COMP: + + lock_requestor(chan, flags); + req_addr = __vmbus_request_addr_match(chan, req_id, + VMBUS_RQST_ADDR_ANY); + if (req_addr == VMBUS_RQST_ERROR) { + unlock_requestor(chan, flags); + dev_err(&hbus->hdev->device, + "Invalid transaction ID %llx\n", + req_id); + break; + } + comp_packet = (struct pci_packet *)req_addr; + response = (struct pci_response *)buffer; + /* + * Call ->completion_func() within the critical section to make + * sure that the packet pointer is still valid during the call: + * here 'valid' means that there's a task still waiting for the + * completion, and that the packet data is still on the waiting + * task's stack. Cf. hv_compose_msi_msg(). + */ + comp_packet->completion_func(comp_packet->compl_ctxt, + response, + bytes_recvd); + unlock_requestor(chan, flags); + break; + + case VM_PKT_DATA_INBAND: + + new_message = (struct pci_incoming_message *)buffer; + switch (new_message->message_type.type) { + case PCI_BUS_RELATIONS: + + bus_rel = (struct pci_bus_relations *)buffer; + if (bytes_recvd < sizeof(*bus_rel) || + bytes_recvd < + struct_size(bus_rel, func, + bus_rel->device_count)) { + dev_err(&hbus->hdev->device, + "bus relations too small\n"); + break; + } + + hv_pci_devices_present(hbus, bus_rel); + break; + + case PCI_BUS_RELATIONS2: + + bus_rel2 = (struct pci_bus_relations2 *)buffer; + if (bytes_recvd < sizeof(*bus_rel2) || + bytes_recvd < + struct_size(bus_rel2, func, + bus_rel2->device_count)) { + dev_err(&hbus->hdev->device, + "bus relations v2 too small\n"); + break; + } + + hv_pci_devices_present2(hbus, bus_rel2); + break; + + case PCI_EJECT: + + dev_message = (struct pci_dev_incoming *)buffer; + if (bytes_recvd < sizeof(*dev_message)) { + dev_err(&hbus->hdev->device, + "eject message too small\n"); + break; + } + hpdev = get_pcichild_wslot(hbus, + dev_message->wslot.slot); + if (hpdev) { + hv_pci_eject_device(hpdev); + put_pcichild(hpdev); + } + break; + + case PCI_INVALIDATE_BLOCK: + + inval = (struct pci_dev_inval_block *)buffer; + if (bytes_recvd < sizeof(*inval)) { + dev_err(&hbus->hdev->device, + "invalidate message too small\n"); + break; + } + hpdev = get_pcichild_wslot(hbus, + inval->wslot.slot); + if (hpdev) { + if (hpdev->block_invalidate) { + hpdev->block_invalidate( + hpdev->invalidate_context, + inval->block_mask); + } + put_pcichild(hpdev); + } + break; + + default: + dev_warn(&hbus->hdev->device, + "Unimplemented protocol message %x\n", + new_message->message_type.type); + break; + } + break; + + default: + dev_err(&hbus->hdev->device, + "unhandled packet type %d, tid %llx len %d\n", + desc->type, req_id, bytes_recvd); + break; + } + } + + kfree(buffer); +} + +/** + * hv_pci_protocol_negotiation() - Set up protocol + * @hdev: VMBus's tracking struct for this root PCI bus. + * @version: Array of supported channel protocol versions in + * the order of probing - highest go first. + * @num_version: Number of elements in the version array. + * + * This driver is intended to support running on Windows 10 + * (server) and later versions. It will not run on earlier + * versions, as they assume that many of the operations which + * Linux needs accomplished with a spinlock held were done via + * asynchronous messaging via VMBus. Windows 10 increases the + * surface area of PCI emulation so that these actions can take + * place by suspending a virtual processor for their duration. + * + * This function negotiates the channel protocol version, + * failing if the host doesn't support the necessary protocol + * level. + */ +static int hv_pci_protocol_negotiation(struct hv_device *hdev, + enum pci_protocol_version_t version[], + int num_version) +{ + struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); + struct pci_version_request *version_req; + struct hv_pci_compl comp_pkt; + struct pci_packet *pkt; + int ret; + int i; + + /* + * Initiate the handshake with the host and negotiate + * a version that the host can support. We start with the + * highest version number and go down if the host cannot + * support it. + */ + pkt = kzalloc(sizeof(*pkt) + sizeof(*version_req), GFP_KERNEL); + if (!pkt) + return -ENOMEM; + + init_completion(&comp_pkt.host_event); + pkt->completion_func = hv_pci_generic_compl; + pkt->compl_ctxt = &comp_pkt; + version_req = (struct pci_version_request *)&pkt->message; + version_req->message_type.type = PCI_QUERY_PROTOCOL_VERSION; + + for (i = 0; i < num_version; i++) { + version_req->protocol_version = version[i]; + ret = vmbus_sendpacket(hdev->channel, version_req, + sizeof(struct pci_version_request), + (unsigned long)pkt, VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (!ret) + ret = wait_for_response(hdev, &comp_pkt.host_event); + + if (ret) { + dev_err(&hdev->device, + "PCI Pass-through VSP failed to request version: %d", + ret); + goto exit; + } + + if (comp_pkt.completion_status >= 0) { + hbus->protocol_version = version[i]; + dev_info(&hdev->device, + "PCI VMBus probing: Using version %#x\n", + hbus->protocol_version); + goto exit; + } + + if (comp_pkt.completion_status != STATUS_REVISION_MISMATCH) { + dev_err(&hdev->device, + "PCI Pass-through VSP failed version request: %#x", + comp_pkt.completion_status); + ret = -EPROTO; + goto exit; + } + + reinit_completion(&comp_pkt.host_event); + } + + dev_err(&hdev->device, + "PCI pass-through VSP failed to find supported version"); + ret = -EPROTO; + +exit: + kfree(pkt); + return ret; +} + +/** + * hv_pci_free_bridge_windows() - Release memory regions for the + * bus + * @hbus: Root PCI bus, as understood by this driver + */ +static void hv_pci_free_bridge_windows(struct hv_pcibus_device *hbus) +{ + /* + * Set the resources back to the way they looked when they + * were allocated by setting IORESOURCE_BUSY again. + */ + + if (hbus->low_mmio_space && hbus->low_mmio_res) { + hbus->low_mmio_res->flags |= IORESOURCE_BUSY; + vmbus_free_mmio(hbus->low_mmio_res->start, + resource_size(hbus->low_mmio_res)); + } + + if (hbus->high_mmio_space && hbus->high_mmio_res) { + hbus->high_mmio_res->flags |= IORESOURCE_BUSY; + vmbus_free_mmio(hbus->high_mmio_res->start, + resource_size(hbus->high_mmio_res)); + } +} + +/** + * hv_pci_allocate_bridge_windows() - Allocate memory regions + * for the bus + * @hbus: Root PCI bus, as understood by this driver + * + * This function calls vmbus_allocate_mmio(), which is itself a + * bit of a compromise. Ideally, we might change the pnp layer + * in the kernel such that it comprehends either PCI devices + * which are "grandchildren of ACPI," with some intermediate bus + * node (in this case, VMBus) or change it such that it + * understands VMBus. The pnp layer, however, has been declared + * deprecated, and not subject to change. + * + * The workaround, implemented here, is to ask VMBus to allocate + * MMIO space for this bus. VMBus itself knows which ranges are + * appropriate by looking at its own ACPI objects. Then, after + * these ranges are claimed, they're modified to look like they + * would have looked if the ACPI and pnp code had allocated + * bridge windows. These descriptors have to exist in this form + * in order to satisfy the code which will get invoked when the + * endpoint PCI function driver calls request_mem_region() or + * request_mem_region_exclusive(). + * + * Return: 0 on success, -errno on failure + */ +static int hv_pci_allocate_bridge_windows(struct hv_pcibus_device *hbus) +{ + resource_size_t align; + int ret; + + if (hbus->low_mmio_space) { + align = 1ULL << (63 - __builtin_clzll(hbus->low_mmio_space)); + ret = vmbus_allocate_mmio(&hbus->low_mmio_res, hbus->hdev, 0, + (u64)(u32)0xffffffff, + hbus->low_mmio_space, + align, false); + if (ret) { + dev_err(&hbus->hdev->device, + "Need %#llx of low MMIO space. Consider reconfiguring the VM.\n", + hbus->low_mmio_space); + return ret; + } + + /* Modify this resource to become a bridge window. */ + hbus->low_mmio_res->flags |= IORESOURCE_WINDOW; + hbus->low_mmio_res->flags &= ~IORESOURCE_BUSY; + pci_add_resource(&hbus->bridge->windows, hbus->low_mmio_res); + } + + if (hbus->high_mmio_space) { + align = 1ULL << (63 - __builtin_clzll(hbus->high_mmio_space)); + ret = vmbus_allocate_mmio(&hbus->high_mmio_res, hbus->hdev, + 0x100000000, -1, + hbus->high_mmio_space, align, + false); + if (ret) { + dev_err(&hbus->hdev->device, + "Need %#llx of high MMIO space. Consider reconfiguring the VM.\n", + hbus->high_mmio_space); + goto release_low_mmio; + } + + /* Modify this resource to become a bridge window. */ + hbus->high_mmio_res->flags |= IORESOURCE_WINDOW; + hbus->high_mmio_res->flags &= ~IORESOURCE_BUSY; + pci_add_resource(&hbus->bridge->windows, hbus->high_mmio_res); + } + + return 0; + +release_low_mmio: + if (hbus->low_mmio_res) { + vmbus_free_mmio(hbus->low_mmio_res->start, + resource_size(hbus->low_mmio_res)); + } + + return ret; +} + +/** + * hv_allocate_config_window() - Find MMIO space for PCI Config + * @hbus: Root PCI bus, as understood by this driver + * + * This function claims memory-mapped I/O space for accessing + * configuration space for the functions on this bus. + * + * Return: 0 on success, -errno on failure + */ +static int hv_allocate_config_window(struct hv_pcibus_device *hbus) +{ + int ret; + + /* + * Set up a region of MMIO space to use for accessing configuration + * space. + */ + ret = vmbus_allocate_mmio(&hbus->mem_config, hbus->hdev, 0, -1, + PCI_CONFIG_MMIO_LENGTH, 0x1000, false); + if (ret) + return ret; + + /* + * vmbus_allocate_mmio() gets used for allocating both device endpoint + * resource claims (those which cannot be overlapped) and the ranges + * which are valid for the children of this bus, which are intended + * to be overlapped by those children. Set the flag on this claim + * meaning that this region can't be overlapped. + */ + + hbus->mem_config->flags |= IORESOURCE_BUSY; + + return 0; +} + +static void hv_free_config_window(struct hv_pcibus_device *hbus) +{ + vmbus_free_mmio(hbus->mem_config->start, PCI_CONFIG_MMIO_LENGTH); +} + +static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs); + +/** + * hv_pci_enter_d0() - Bring the "bus" into the D0 power state + * @hdev: VMBus's tracking struct for this root PCI bus + * + * Return: 0 on success, -errno on failure + */ +static int hv_pci_enter_d0(struct hv_device *hdev) +{ + struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); + struct pci_bus_d0_entry *d0_entry; + struct hv_pci_compl comp_pkt; + struct pci_packet *pkt; + bool retry = true; + int ret; + +enter_d0_retry: + /* + * Tell the host that the bus is ready to use, and moved into the + * powered-on state. This includes telling the host which region + * of memory-mapped I/O space has been chosen for configuration space + * access. + */ + pkt = kzalloc(sizeof(*pkt) + sizeof(*d0_entry), GFP_KERNEL); + if (!pkt) + return -ENOMEM; + + init_completion(&comp_pkt.host_event); + pkt->completion_func = hv_pci_generic_compl; + pkt->compl_ctxt = &comp_pkt; + d0_entry = (struct pci_bus_d0_entry *)&pkt->message; + d0_entry->message_type.type = PCI_BUS_D0ENTRY; + d0_entry->mmio_base = hbus->mem_config->start; + + ret = vmbus_sendpacket(hdev->channel, d0_entry, sizeof(*d0_entry), + (unsigned long)pkt, VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (!ret) + ret = wait_for_response(hdev, &comp_pkt.host_event); + + if (ret) + goto exit; + + /* + * In certain case (Kdump) the pci device of interest was + * not cleanly shut down and resource is still held on host + * side, the host could return invalid device status. + * We need to explicitly request host to release the resource + * and try to enter D0 again. + */ + if (comp_pkt.completion_status < 0 && retry) { + retry = false; + + dev_err(&hdev->device, "Retrying D0 Entry\n"); + + /* + * Hv_pci_bus_exit() calls hv_send_resource_released() + * to free up resources of its child devices. + * In the kdump kernel we need to set the + * wslot_res_allocated to 255 so it scans all child + * devices to release resources allocated in the + * normal kernel before panic happened. + */ + hbus->wslot_res_allocated = 255; + + ret = hv_pci_bus_exit(hdev, true); + + if (ret == 0) { + kfree(pkt); + goto enter_d0_retry; + } + dev_err(&hdev->device, + "Retrying D0 failed with ret %d\n", ret); + } + + if (comp_pkt.completion_status < 0) { + dev_err(&hdev->device, + "PCI Pass-through VSP failed D0 Entry with status %x\n", + comp_pkt.completion_status); + ret = -EPROTO; + goto exit; + } + + ret = 0; + +exit: + kfree(pkt); + return ret; +} + +/** + * hv_pci_query_relations() - Ask host to send list of child + * devices + * @hdev: VMBus's tracking struct for this root PCI bus + * + * Return: 0 on success, -errno on failure + */ +static int hv_pci_query_relations(struct hv_device *hdev) +{ + struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); + struct pci_message message; + struct completion comp; + int ret; + + /* Ask the host to send along the list of child devices */ + init_completion(&comp); + if (cmpxchg(&hbus->survey_event, NULL, &comp)) + return -ENOTEMPTY; + + memset(&message, 0, sizeof(message)); + message.type = PCI_QUERY_BUS_RELATIONS; + + ret = vmbus_sendpacket(hdev->channel, &message, sizeof(message), + 0, VM_PKT_DATA_INBAND, 0); + if (!ret) + ret = wait_for_response(hdev, &comp); + + /* + * In the case of fast device addition/removal, it's possible that + * vmbus_sendpacket() or wait_for_response() returns -ENODEV but we + * already got a PCI_BUS_RELATIONS* message from the host and the + * channel callback already scheduled a work to hbus->wq, which can be + * running pci_devices_present_work() -> survey_child_resources() -> + * complete(&hbus->survey_event), even after hv_pci_query_relations() + * exits and the stack variable 'comp' is no longer valid; as a result, + * a hang or a page fault may happen when the complete() calls + * raw_spin_lock_irqsave(). Flush hbus->wq before we exit from + * hv_pci_query_relations() to avoid the issues. Note: if 'ret' is + * -ENODEV, there can't be any more work item scheduled to hbus->wq + * after the flush_workqueue(): see vmbus_onoffer_rescind() -> + * vmbus_reset_channel_cb(), vmbus_rescind_cleanup() -> + * channel->rescind = true. + */ + flush_workqueue(hbus->wq); + + return ret; +} + +/** + * hv_send_resources_allocated() - Report local resource choices + * @hdev: VMBus's tracking struct for this root PCI bus + * + * The host OS is expecting to be sent a request as a message + * which contains all the resources that the device will use. + * The response contains those same resources, "translated" + * which is to say, the values which should be used by the + * hardware, when it delivers an interrupt. (MMIO resources are + * used in local terms.) This is nice for Windows, and lines up + * with the FDO/PDO split, which doesn't exist in Linux. Linux + * is deeply expecting to scan an emulated PCI configuration + * space. So this message is sent here only to drive the state + * machine on the host forward. + * + * Return: 0 on success, -errno on failure + */ +static int hv_send_resources_allocated(struct hv_device *hdev) +{ + struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); + struct pci_resources_assigned *res_assigned; + struct pci_resources_assigned2 *res_assigned2; + struct hv_pci_compl comp_pkt; + struct hv_pci_dev *hpdev; + struct pci_packet *pkt; + size_t size_res; + int wslot; + int ret; + + size_res = (hbus->protocol_version < PCI_PROTOCOL_VERSION_1_2) + ? sizeof(*res_assigned) : sizeof(*res_assigned2); + + pkt = kmalloc(sizeof(*pkt) + size_res, GFP_KERNEL); + if (!pkt) + return -ENOMEM; + + ret = 0; + + for (wslot = 0; wslot < 256; wslot++) { + hpdev = get_pcichild_wslot(hbus, wslot); + if (!hpdev) + continue; + + memset(pkt, 0, sizeof(*pkt) + size_res); + init_completion(&comp_pkt.host_event); + pkt->completion_func = hv_pci_generic_compl; + pkt->compl_ctxt = &comp_pkt; + + if (hbus->protocol_version < PCI_PROTOCOL_VERSION_1_2) { + res_assigned = + (struct pci_resources_assigned *)&pkt->message; + res_assigned->message_type.type = + PCI_RESOURCES_ASSIGNED; + res_assigned->wslot.slot = hpdev->desc.win_slot.slot; + } else { + res_assigned2 = + (struct pci_resources_assigned2 *)&pkt->message; + res_assigned2->message_type.type = + PCI_RESOURCES_ASSIGNED2; + res_assigned2->wslot.slot = hpdev->desc.win_slot.slot; + } + put_pcichild(hpdev); + + ret = vmbus_sendpacket(hdev->channel, &pkt->message, + size_res, (unsigned long)pkt, + VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (!ret) + ret = wait_for_response(hdev, &comp_pkt.host_event); + if (ret) + break; + + if (comp_pkt.completion_status < 0) { + ret = -EPROTO; + dev_err(&hdev->device, + "resource allocated returned 0x%x", + comp_pkt.completion_status); + break; + } + + hbus->wslot_res_allocated = wslot; + } + + kfree(pkt); + return ret; +} + +/** + * hv_send_resources_released() - Report local resources + * released + * @hdev: VMBus's tracking struct for this root PCI bus + * + * Return: 0 on success, -errno on failure + */ +static int hv_send_resources_released(struct hv_device *hdev) +{ + struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); + struct pci_child_message pkt; + struct hv_pci_dev *hpdev; + int wslot; + int ret; + + for (wslot = hbus->wslot_res_allocated; wslot >= 0; wslot--) { + hpdev = get_pcichild_wslot(hbus, wslot); + if (!hpdev) + continue; + + memset(&pkt, 0, sizeof(pkt)); + pkt.message_type.type = PCI_RESOURCES_RELEASED; + pkt.wslot.slot = hpdev->desc.win_slot.slot; + + put_pcichild(hpdev); + + ret = vmbus_sendpacket(hdev->channel, &pkt, sizeof(pkt), 0, + VM_PKT_DATA_INBAND, 0); + if (ret) + return ret; + + hbus->wslot_res_allocated = wslot - 1; + } + + hbus->wslot_res_allocated = -1; + + return 0; +} + +#define HVPCI_DOM_MAP_SIZE (64 * 1024) +static DECLARE_BITMAP(hvpci_dom_map, HVPCI_DOM_MAP_SIZE); + +/* + * PCI domain number 0 is used by emulated devices on Gen1 VMs, so define 0 + * as invalid for passthrough PCI devices of this driver. + */ +#define HVPCI_DOM_INVALID 0 + +/** + * hv_get_dom_num() - Get a valid PCI domain number + * Check if the PCI domain number is in use, and return another number if + * it is in use. + * + * @dom: Requested domain number + * + * return: domain number on success, HVPCI_DOM_INVALID on failure + */ +static u16 hv_get_dom_num(u16 dom) +{ + unsigned int i; + + if (test_and_set_bit(dom, hvpci_dom_map) == 0) + return dom; + + for_each_clear_bit(i, hvpci_dom_map, HVPCI_DOM_MAP_SIZE) { + if (test_and_set_bit(i, hvpci_dom_map) == 0) + return i; + } + + return HVPCI_DOM_INVALID; +} + +/** + * hv_put_dom_num() - Mark the PCI domain number as free + * @dom: Domain number to be freed + */ +static void hv_put_dom_num(u16 dom) +{ + clear_bit(dom, hvpci_dom_map); +} + +/** + * hv_pci_probe() - New VMBus channel probe, for a root PCI bus + * @hdev: VMBus's tracking struct for this root PCI bus + * @dev_id: Identifies the device itself + * + * Return: 0 on success, -errno on failure + */ +static int hv_pci_probe(struct hv_device *hdev, + const struct hv_vmbus_device_id *dev_id) +{ + struct pci_host_bridge *bridge; + struct hv_pcibus_device *hbus; + u16 dom_req, dom; + char *name; + int ret; + + /* + * hv_pcibus_device contains the hypercall arguments for retargeting in + * hv_irq_unmask(). Those must not cross a page boundary. + */ + BUILD_BUG_ON(sizeof(*hbus) > HV_HYP_PAGE_SIZE); + + bridge = devm_pci_alloc_host_bridge(&hdev->device, 0); + if (!bridge) + return -ENOMEM; + + /* + * With the recent 59bb47985c1d ("mm, sl[aou]b: guarantee natural + * alignment for kmalloc(power-of-two)"), kzalloc() is able to allocate + * a 4KB buffer that is guaranteed to be 4KB-aligned. Here the size and + * alignment of hbus is important because hbus's field + * retarget_msi_interrupt_params must not cross a 4KB page boundary. + * + * Here we prefer kzalloc to get_zeroed_page(), because a buffer + * allocated by the latter is not tracked and scanned by kmemleak, and + * hence kmemleak reports the pointer contained in the hbus buffer + * (i.e. the hpdev struct, which is created in new_pcichild_device() and + * is tracked by hbus->children) as memory leak (false positive). + * + * If the kernel doesn't have 59bb47985c1d, get_zeroed_page() *must* be + * used to allocate the hbus buffer and we can avoid the kmemleak false + * positive by using kmemleak_alloc() and kmemleak_free() to ask + * kmemleak to track and scan the hbus buffer. + */ + hbus = kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL); + if (!hbus) + return -ENOMEM; + + hbus->bridge = bridge; + mutex_init(&hbus->state_lock); + hbus->state = hv_pcibus_init; + hbus->wslot_res_allocated = -1; + + /* + * The PCI bus "domain" is what is called "segment" in ACPI and other + * specs. Pull it from the instance ID, to get something usually + * unique. In rare cases of collision, we will find out another number + * not in use. + * + * Note that, since this code only runs in a Hyper-V VM, Hyper-V + * together with this guest driver can guarantee that (1) The only + * domain used by Gen1 VMs for something that looks like a physical + * PCI bus (which is actually emulated by the hypervisor) is domain 0. + * (2) There will be no overlap between domains (after fixing possible + * collisions) in the same VM. + */ + dom_req = hdev->dev_instance.b[5] << 8 | hdev->dev_instance.b[4]; + dom = hv_get_dom_num(dom_req); + + if (dom == HVPCI_DOM_INVALID) { + dev_err(&hdev->device, + "Unable to use dom# 0x%x or other numbers", dom_req); + ret = -EINVAL; + goto free_bus; + } + + if (dom != dom_req) + dev_info(&hdev->device, + "PCI dom# 0x%x has collision, using 0x%x", + dom_req, dom); + + hbus->bridge->domain_nr = dom; +#ifdef CONFIG_X86 + hbus->sysdata.domain = dom; +#elif defined(CONFIG_ARM64) + /* + * Set the PCI bus parent to be the corresponding VMbus + * device. Then the VMbus device will be assigned as the + * ACPI companion in pcibios_root_bridge_prepare() and + * pci_dma_configure() will propagate device coherence + * information to devices created on the bus. + */ + hbus->sysdata.parent = hdev->device.parent; +#endif + + hbus->hdev = hdev; + INIT_LIST_HEAD(&hbus->children); + INIT_LIST_HEAD(&hbus->dr_list); + spin_lock_init(&hbus->config_lock); + spin_lock_init(&hbus->device_list_lock); + spin_lock_init(&hbus->retarget_msi_interrupt_lock); + hbus->wq = alloc_ordered_workqueue("hv_pci_%x", 0, + hbus->bridge->domain_nr); + if (!hbus->wq) { + ret = -ENOMEM; + goto free_dom; + } + + hdev->channel->next_request_id_callback = vmbus_next_request_id; + hdev->channel->request_addr_callback = vmbus_request_addr; + hdev->channel->rqstor_size = HV_PCI_RQSTOR_SIZE; + + ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0, + hv_pci_onchannelcallback, hbus); + if (ret) + goto destroy_wq; + + hv_set_drvdata(hdev, hbus); + + ret = hv_pci_protocol_negotiation(hdev, pci_protocol_versions, + ARRAY_SIZE(pci_protocol_versions)); + if (ret) + goto close; + + ret = hv_allocate_config_window(hbus); + if (ret) + goto close; + + hbus->cfg_addr = ioremap(hbus->mem_config->start, + PCI_CONFIG_MMIO_LENGTH); + if (!hbus->cfg_addr) { + dev_err(&hdev->device, + "Unable to map a virtual address for config space\n"); + ret = -ENOMEM; + goto free_config; + } + + name = kasprintf(GFP_KERNEL, "%pUL", &hdev->dev_instance); + if (!name) { + ret = -ENOMEM; + goto unmap; + } + + hbus->fwnode = irq_domain_alloc_named_fwnode(name); + kfree(name); + if (!hbus->fwnode) { + ret = -ENOMEM; + goto unmap; + } + + ret = hv_pcie_init_irq_domain(hbus); + if (ret) + goto free_fwnode; + + ret = hv_pci_query_relations(hdev); + if (ret) + goto free_irq_domain; + + mutex_lock(&hbus->state_lock); + + ret = hv_pci_enter_d0(hdev); + if (ret) + goto release_state_lock; + + ret = hv_pci_allocate_bridge_windows(hbus); + if (ret) + goto exit_d0; + + ret = hv_send_resources_allocated(hdev); + if (ret) + goto free_windows; + + prepopulate_bars(hbus); + + hbus->state = hv_pcibus_probed; + + ret = create_root_hv_pci_bus(hbus); + if (ret) + goto free_windows; + + mutex_unlock(&hbus->state_lock); + return 0; + +free_windows: + hv_pci_free_bridge_windows(hbus); +exit_d0: + (void) hv_pci_bus_exit(hdev, true); +release_state_lock: + mutex_unlock(&hbus->state_lock); +free_irq_domain: + irq_domain_remove(hbus->irq_domain); +free_fwnode: + irq_domain_free_fwnode(hbus->fwnode); +unmap: + iounmap(hbus->cfg_addr); +free_config: + hv_free_config_window(hbus); +close: + vmbus_close(hdev->channel); +destroy_wq: + destroy_workqueue(hbus->wq); +free_dom: + hv_put_dom_num(hbus->bridge->domain_nr); +free_bus: + kfree(hbus); + return ret; +} + +static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs) +{ + struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); + struct vmbus_channel *chan = hdev->channel; + struct { + struct pci_packet teardown_packet; + u8 buffer[sizeof(struct pci_message)]; + } pkt; + struct hv_pci_compl comp_pkt; + struct hv_pci_dev *hpdev, *tmp; + unsigned long flags; + u64 trans_id; + int ret; + + /* + * After the host sends the RESCIND_CHANNEL message, it doesn't + * access the per-channel ringbuffer any longer. + */ + if (chan->rescind) + return 0; + + if (!keep_devs) { + struct list_head removed; + + /* Move all present children to the list on stack */ + INIT_LIST_HEAD(&removed); + spin_lock_irqsave(&hbus->device_list_lock, flags); + list_for_each_entry_safe(hpdev, tmp, &hbus->children, list_entry) + list_move_tail(&hpdev->list_entry, &removed); + spin_unlock_irqrestore(&hbus->device_list_lock, flags); + + /* Remove all children in the list */ + list_for_each_entry_safe(hpdev, tmp, &removed, list_entry) { + list_del(&hpdev->list_entry); + if (hpdev->pci_slot) + pci_destroy_slot(hpdev->pci_slot); + /* For the two refs got in new_pcichild_device() */ + put_pcichild(hpdev); + put_pcichild(hpdev); + } + } + + ret = hv_send_resources_released(hdev); + if (ret) { + dev_err(&hdev->device, + "Couldn't send resources released packet(s)\n"); + return ret; + } + + memset(&pkt.teardown_packet, 0, sizeof(pkt.teardown_packet)); + init_completion(&comp_pkt.host_event); + pkt.teardown_packet.completion_func = hv_pci_generic_compl; + pkt.teardown_packet.compl_ctxt = &comp_pkt; + pkt.teardown_packet.message[0].type = PCI_BUS_D0EXIT; + + ret = vmbus_sendpacket_getid(chan, &pkt.teardown_packet.message, + sizeof(struct pci_message), + (unsigned long)&pkt.teardown_packet, + &trans_id, VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (ret) + return ret; + + if (wait_for_completion_timeout(&comp_pkt.host_event, 10 * HZ) == 0) { + /* + * The completion packet on the stack becomes invalid after + * 'return'; remove the ID from the VMbus requestor if the + * identifier is still mapped to/associated with the packet. + * + * Cf. hv_pci_onchannelcallback(). + */ + vmbus_request_addr_match(chan, trans_id, + (unsigned long)&pkt.teardown_packet); + return -ETIMEDOUT; + } + + return 0; +} + +/** + * hv_pci_remove() - Remove routine for this VMBus channel + * @hdev: VMBus's tracking struct for this root PCI bus + * + * Return: 0 on success, -errno on failure + */ +static int hv_pci_remove(struct hv_device *hdev) +{ + struct hv_pcibus_device *hbus; + int ret; + + hbus = hv_get_drvdata(hdev); + if (hbus->state == hv_pcibus_installed) { + tasklet_disable(&hdev->channel->callback_event); + hbus->state = hv_pcibus_removing; + tasklet_enable(&hdev->channel->callback_event); + destroy_workqueue(hbus->wq); + hbus->wq = NULL; + /* + * At this point, no work is running or can be scheduled + * on hbus-wq. We can't race with hv_pci_devices_present() + * or hv_pci_eject_device(), it's safe to proceed. + */ + + /* Remove the bus from PCI's point of view. */ + pci_lock_rescan_remove(); + pci_stop_root_bus(hbus->bridge->bus); + hv_pci_remove_slots(hbus); + pci_remove_root_bus(hbus->bridge->bus); + pci_unlock_rescan_remove(); + } + + ret = hv_pci_bus_exit(hdev, false); + + vmbus_close(hdev->channel); + + iounmap(hbus->cfg_addr); + hv_free_config_window(hbus); + hv_pci_free_bridge_windows(hbus); + irq_domain_remove(hbus->irq_domain); + irq_domain_free_fwnode(hbus->fwnode); + + hv_put_dom_num(hbus->bridge->domain_nr); + + kfree(hbus); + return ret; +} + +static int hv_pci_suspend(struct hv_device *hdev) +{ + struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); + enum hv_pcibus_state old_state; + int ret; + + /* + * hv_pci_suspend() must make sure there are no pending work items + * before calling vmbus_close(), since it runs in a process context + * as a callback in dpm_suspend(). When it starts to run, the channel + * callback hv_pci_onchannelcallback(), which runs in a tasklet + * context, can be still running concurrently and scheduling new work + * items onto hbus->wq in hv_pci_devices_present() and + * hv_pci_eject_device(), and the work item handlers can access the + * vmbus channel, which can be being closed by hv_pci_suspend(), e.g. + * the work item handler pci_devices_present_work() -> + * new_pcichild_device() writes to the vmbus channel. + * + * To eliminate the race, hv_pci_suspend() disables the channel + * callback tasklet, sets hbus->state to hv_pcibus_removing, and + * re-enables the tasklet. This way, when hv_pci_suspend() proceeds, + * it knows that no new work item can be scheduled, and then it flushes + * hbus->wq and safely closes the vmbus channel. + */ + tasklet_disable(&hdev->channel->callback_event); + + /* Change the hbus state to prevent new work items. */ + old_state = hbus->state; + if (hbus->state == hv_pcibus_installed) + hbus->state = hv_pcibus_removing; + + tasklet_enable(&hdev->channel->callback_event); + + if (old_state != hv_pcibus_installed) + return -EINVAL; + + flush_workqueue(hbus->wq); + + ret = hv_pci_bus_exit(hdev, true); + if (ret) + return ret; + + vmbus_close(hdev->channel); + + return 0; +} + +static int hv_pci_restore_msi_msg(struct pci_dev *pdev, void *arg) +{ + struct irq_data *irq_data; + struct msi_desc *entry; + int ret = 0; + + if (!pdev->msi_enabled && !pdev->msix_enabled) + return 0; + + msi_lock_descs(&pdev->dev); + msi_for_each_desc(entry, &pdev->dev, MSI_DESC_ASSOCIATED) { + irq_data = irq_get_irq_data(entry->irq); + if (WARN_ON_ONCE(!irq_data)) { + ret = -EINVAL; + break; + } + + hv_compose_msi_msg(irq_data, &entry->msg); + } + msi_unlock_descs(&pdev->dev); + + return ret; +} + +/* + * Upon resume, pci_restore_msi_state() -> ... -> __pci_write_msi_msg() + * directly writes the MSI/MSI-X registers via MMIO, but since Hyper-V + * doesn't trap and emulate the MMIO accesses, here hv_compose_msi_msg() + * must be used to ask Hyper-V to re-create the IOMMU Interrupt Remapping + * Table entries. + */ +static void hv_pci_restore_msi_state(struct hv_pcibus_device *hbus) +{ + pci_walk_bus(hbus->bridge->bus, hv_pci_restore_msi_msg, NULL); +} + +static int hv_pci_resume(struct hv_device *hdev) +{ + struct hv_pcibus_device *hbus = hv_get_drvdata(hdev); + enum pci_protocol_version_t version[1]; + int ret; + + hbus->state = hv_pcibus_init; + + hdev->channel->next_request_id_callback = vmbus_next_request_id; + hdev->channel->request_addr_callback = vmbus_request_addr; + hdev->channel->rqstor_size = HV_PCI_RQSTOR_SIZE; + + ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0, + hv_pci_onchannelcallback, hbus); + if (ret) + return ret; + + /* Only use the version that was in use before hibernation. */ + version[0] = hbus->protocol_version; + ret = hv_pci_protocol_negotiation(hdev, version, 1); + if (ret) + goto out; + + ret = hv_pci_query_relations(hdev); + if (ret) + goto out; + + mutex_lock(&hbus->state_lock); + + ret = hv_pci_enter_d0(hdev); + if (ret) + goto release_state_lock; + + ret = hv_send_resources_allocated(hdev); + if (ret) + goto release_state_lock; + + prepopulate_bars(hbus); + + hv_pci_restore_msi_state(hbus); + + hbus->state = hv_pcibus_installed; + mutex_unlock(&hbus->state_lock); + return 0; + +release_state_lock: + mutex_unlock(&hbus->state_lock); +out: + vmbus_close(hdev->channel); + return ret; +} + +static const struct hv_vmbus_device_id hv_pci_id_table[] = { + /* PCI Pass-through Class ID */ + /* 44C4F61D-4444-4400-9D52-802E27EDE19F */ + { HV_PCIE_GUID, }, + { }, +}; + +MODULE_DEVICE_TABLE(vmbus, hv_pci_id_table); + +static struct hv_driver hv_pci_drv = { + .name = "hv_pci", + .id_table = hv_pci_id_table, + .probe = hv_pci_probe, + .remove = hv_pci_remove, + .suspend = hv_pci_suspend, + .resume = hv_pci_resume, +}; + +static void __exit exit_hv_pci_drv(void) +{ + vmbus_driver_unregister(&hv_pci_drv); + + hvpci_block_ops.read_block = NULL; + hvpci_block_ops.write_block = NULL; + hvpci_block_ops.reg_blk_invalidate = NULL; +} + +static int __init init_hv_pci_drv(void) +{ + int ret; + + if (!hv_is_hyperv_initialized()) + return -ENODEV; + + ret = hv_pci_irqchip_init(); + if (ret) + return ret; + + /* Set the invalid domain number's bit, so it will not be used */ + set_bit(HVPCI_DOM_INVALID, hvpci_dom_map); + + /* Initialize PCI block r/w interface */ + hvpci_block_ops.read_block = hv_read_config_block; + hvpci_block_ops.write_block = hv_write_config_block; + hvpci_block_ops.reg_blk_invalidate = hv_register_block_invalidate; + + return vmbus_driver_register(&hv_pci_drv); +} + +module_init(init_hv_pci_drv); +module_exit(exit_hv_pci_drv); + +MODULE_DESCRIPTION("Hyper-V PCI"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-ixp4xx.c b/drivers/pci/controller/pci-ixp4xx.c new file mode 100644 index 000000000..654ac4a82 --- /dev/null +++ b/drivers/pci/controller/pci-ixp4xx.c @@ -0,0 +1,671 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for Intel IXP4xx PCI host controller + * + * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> + * + * Based on the IXP4xx arch/arm/mach-ixp4xx/common-pci.c driver + * Copyright (C) 2002 Intel Corporation + * Copyright (C) 2003 Greg Ungerer <gerg@linux-m68k.org> + * Copyright (C) 2003-2004 MontaVista Software, Inc. + * Copyright (C) 2005 Deepak Saxena <dsaxena@plexity.net> + * Copyright (C) 2005 Alessandro Zummo <a.zummo@towertech.it> + * + * TODO: + * - Test IO-space access + * - DMA support + */ + +#include <linux/init.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/of_address.h> +#include <linux/of_device.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/bits.h> + +/* Register offsets */ +#define IXP4XX_PCI_NP_AD 0x00 +#define IXP4XX_PCI_NP_CBE 0x04 +#define IXP4XX_PCI_NP_WDATA 0x08 +#define IXP4XX_PCI_NP_RDATA 0x0c +#define IXP4XX_PCI_CRP_AD_CBE 0x10 +#define IXP4XX_PCI_CRP_WDATA 0x14 +#define IXP4XX_PCI_CRP_RDATA 0x18 +#define IXP4XX_PCI_CSR 0x1c +#define IXP4XX_PCI_ISR 0x20 +#define IXP4XX_PCI_INTEN 0x24 +#define IXP4XX_PCI_DMACTRL 0x28 +#define IXP4XX_PCI_AHBMEMBASE 0x2c +#define IXP4XX_PCI_AHBIOBASE 0x30 +#define IXP4XX_PCI_PCIMEMBASE 0x34 +#define IXP4XX_PCI_AHBDOORBELL 0x38 +#define IXP4XX_PCI_PCIDOORBELL 0x3c +#define IXP4XX_PCI_ATPDMA0_AHBADDR 0x40 +#define IXP4XX_PCI_ATPDMA0_PCIADDR 0x44 +#define IXP4XX_PCI_ATPDMA0_LENADDR 0x48 +#define IXP4XX_PCI_ATPDMA1_AHBADDR 0x4c +#define IXP4XX_PCI_ATPDMA1_PCIADDR 0x50 +#define IXP4XX_PCI_ATPDMA1_LENADDR 0x54 + +/* CSR bit definitions */ +#define IXP4XX_PCI_CSR_HOST BIT(0) +#define IXP4XX_PCI_CSR_ARBEN BIT(1) +#define IXP4XX_PCI_CSR_ADS BIT(2) +#define IXP4XX_PCI_CSR_PDS BIT(3) +#define IXP4XX_PCI_CSR_ABE BIT(4) +#define IXP4XX_PCI_CSR_DBT BIT(5) +#define IXP4XX_PCI_CSR_ASE BIT(8) +#define IXP4XX_PCI_CSR_IC BIT(15) +#define IXP4XX_PCI_CSR_PRST BIT(16) + +/* ISR (Interrupt status) Register bit definitions */ +#define IXP4XX_PCI_ISR_PSE BIT(0) +#define IXP4XX_PCI_ISR_PFE BIT(1) +#define IXP4XX_PCI_ISR_PPE BIT(2) +#define IXP4XX_PCI_ISR_AHBE BIT(3) +#define IXP4XX_PCI_ISR_APDC BIT(4) +#define IXP4XX_PCI_ISR_PADC BIT(5) +#define IXP4XX_PCI_ISR_ADB BIT(6) +#define IXP4XX_PCI_ISR_PDB BIT(7) + +/* INTEN (Interrupt Enable) Register bit definitions */ +#define IXP4XX_PCI_INTEN_PSE BIT(0) +#define IXP4XX_PCI_INTEN_PFE BIT(1) +#define IXP4XX_PCI_INTEN_PPE BIT(2) +#define IXP4XX_PCI_INTEN_AHBE BIT(3) +#define IXP4XX_PCI_INTEN_APDC BIT(4) +#define IXP4XX_PCI_INTEN_PADC BIT(5) +#define IXP4XX_PCI_INTEN_ADB BIT(6) +#define IXP4XX_PCI_INTEN_PDB BIT(7) + +/* Shift value for byte enable on NP cmd/byte enable register */ +#define IXP4XX_PCI_NP_CBE_BESL 4 + +/* PCI commands supported by NP access unit */ +#define NP_CMD_IOREAD 0x2 +#define NP_CMD_IOWRITE 0x3 +#define NP_CMD_CONFIGREAD 0xa +#define NP_CMD_CONFIGWRITE 0xb +#define NP_CMD_MEMREAD 0x6 +#define NP_CMD_MEMWRITE 0x7 + +/* Constants for CRP access into local config space */ +#define CRP_AD_CBE_BESL 20 +#define CRP_AD_CBE_WRITE 0x00010000 + +/* Special PCI configuration space registers for this controller */ +#define IXP4XX_PCI_RTOTTO 0x40 + +struct ixp4xx_pci { + struct device *dev; + void __iomem *base; + bool errata_hammer; + bool host_mode; +}; + +/* + * The IXP4xx has a peculiar address bus that will change the + * byte order on SoC peripherals depending on whether the device + * operates in big-endian or little-endian mode. That means that + * readl() and writel() that always use little-endian access + * will not work for SoC peripherals such as the PCI controller + * when used in big-endian mode. The accesses to the individual + * PCI devices on the other hand, are always little-endian and + * can use readl() and writel(). + * + * For local AHB bus access we need to use __raw_[readl|writel]() + * to make sure that we access the SoC devices in the CPU native + * endianness. + */ +static inline u32 ixp4xx_readl(struct ixp4xx_pci *p, u32 reg) +{ + return __raw_readl(p->base + reg); +} + +static inline void ixp4xx_writel(struct ixp4xx_pci *p, u32 reg, u32 val) +{ + __raw_writel(val, p->base + reg); +} + +static int ixp4xx_pci_check_master_abort(struct ixp4xx_pci *p) +{ + u32 isr = ixp4xx_readl(p, IXP4XX_PCI_ISR); + + if (isr & IXP4XX_PCI_ISR_PFE) { + /* Make sure the master abort bit is reset */ + ixp4xx_writel(p, IXP4XX_PCI_ISR, IXP4XX_PCI_ISR_PFE); + dev_dbg(p->dev, "master abort detected\n"); + return -EINVAL; + } + + return 0; +} + +static int ixp4xx_pci_read_indirect(struct ixp4xx_pci *p, u32 addr, u32 cmd, u32 *data) +{ + ixp4xx_writel(p, IXP4XX_PCI_NP_AD, addr); + + if (p->errata_hammer) { + int i; + + /* + * PCI workaround - only works if NP PCI space reads have + * no side effects. Hammer the register and read twice 8 + * times. last one will be good. + */ + for (i = 0; i < 8; i++) { + ixp4xx_writel(p, IXP4XX_PCI_NP_CBE, cmd); + *data = ixp4xx_readl(p, IXP4XX_PCI_NP_RDATA); + *data = ixp4xx_readl(p, IXP4XX_PCI_NP_RDATA); + } + } else { + ixp4xx_writel(p, IXP4XX_PCI_NP_CBE, cmd); + *data = ixp4xx_readl(p, IXP4XX_PCI_NP_RDATA); + } + + return ixp4xx_pci_check_master_abort(p); +} + +static int ixp4xx_pci_write_indirect(struct ixp4xx_pci *p, u32 addr, u32 cmd, u32 data) +{ + ixp4xx_writel(p, IXP4XX_PCI_NP_AD, addr); + + /* Set up the write */ + ixp4xx_writel(p, IXP4XX_PCI_NP_CBE, cmd); + + /* Execute the write by writing to NP_WDATA */ + ixp4xx_writel(p, IXP4XX_PCI_NP_WDATA, data); + + return ixp4xx_pci_check_master_abort(p); +} + +static u32 ixp4xx_config_addr(u8 bus_num, u16 devfn, int where) +{ + /* Root bus is always 0 in this hardware */ + if (bus_num == 0) { + /* type 0 */ + return BIT(32-PCI_SLOT(devfn)) | ((PCI_FUNC(devfn)) << 8) | + (where & ~3); + } else { + /* type 1 */ + return (bus_num << 16) | ((PCI_SLOT(devfn)) << 11) | + ((PCI_FUNC(devfn)) << 8) | (where & ~3) | 1; + } +} + +/* + * CRP functions are "Controller Configuration Port" accesses + * initiated from within this driver itself to read/write PCI + * control information in the config space. + */ +static u32 ixp4xx_crp_byte_lane_enable_bits(u32 n, int size) +{ + if (size == 1) + return (0xf & ~BIT(n)) << CRP_AD_CBE_BESL; + if (size == 2) + return (0xf & ~(BIT(n) | BIT(n+1))) << CRP_AD_CBE_BESL; + if (size == 4) + return 0; + return 0xffffffff; +} + +static int ixp4xx_crp_read_config(struct ixp4xx_pci *p, int where, int size, + u32 *value) +{ + u32 n, cmd, val; + + n = where % 4; + cmd = where & ~3; + + dev_dbg(p->dev, "%s from %d size %d cmd %08x\n", + __func__, where, size, cmd); + + ixp4xx_writel(p, IXP4XX_PCI_CRP_AD_CBE, cmd); + val = ixp4xx_readl(p, IXP4XX_PCI_CRP_RDATA); + + val >>= (8*n); + switch (size) { + case 1: + val &= U8_MAX; + dev_dbg(p->dev, "%s read byte %02x\n", __func__, val); + break; + case 2: + val &= U16_MAX; + dev_dbg(p->dev, "%s read word %04x\n", __func__, val); + break; + case 4: + val &= U32_MAX; + dev_dbg(p->dev, "%s read long %08x\n", __func__, val); + break; + default: + /* Should not happen */ + dev_err(p->dev, "%s illegal size\n", __func__); + return PCIBIOS_DEVICE_NOT_FOUND; + } + *value = val; + + return PCIBIOS_SUCCESSFUL; +} + +static int ixp4xx_crp_write_config(struct ixp4xx_pci *p, int where, int size, + u32 value) +{ + u32 n, cmd, val; + + n = where % 4; + cmd = ixp4xx_crp_byte_lane_enable_bits(n, size); + if (cmd == 0xffffffff) + return PCIBIOS_BAD_REGISTER_NUMBER; + cmd |= where & ~3; + cmd |= CRP_AD_CBE_WRITE; + + val = value << (8*n); + + dev_dbg(p->dev, "%s to %d size %d cmd %08x val %08x\n", + __func__, where, size, cmd, val); + + ixp4xx_writel(p, IXP4XX_PCI_CRP_AD_CBE, cmd); + ixp4xx_writel(p, IXP4XX_PCI_CRP_WDATA, val); + + return PCIBIOS_SUCCESSFUL; +} + +/* + * Then follows the functions that read and write from the common PCI + * configuration space. + */ +static u32 ixp4xx_byte_lane_enable_bits(u32 n, int size) +{ + if (size == 1) + return (0xf & ~BIT(n)) << 4; + if (size == 2) + return (0xf & ~(BIT(n) | BIT(n+1))) << 4; + if (size == 4) + return 0; + return 0xffffffff; +} + +static int ixp4xx_pci_read_config(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *value) +{ + struct ixp4xx_pci *p = bus->sysdata; + u32 n, addr, val, cmd; + u8 bus_num = bus->number; + int ret; + + *value = 0xffffffff; + n = where % 4; + cmd = ixp4xx_byte_lane_enable_bits(n, size); + if (cmd == 0xffffffff) + return PCIBIOS_BAD_REGISTER_NUMBER; + + addr = ixp4xx_config_addr(bus_num, devfn, where); + cmd |= NP_CMD_CONFIGREAD; + dev_dbg(p->dev, "read_config from %d size %d dev %d:%d:%d address: %08x cmd: %08x\n", + where, size, bus_num, PCI_SLOT(devfn), PCI_FUNC(devfn), addr, cmd); + + ret = ixp4xx_pci_read_indirect(p, addr, cmd, &val); + if (ret) + return PCIBIOS_DEVICE_NOT_FOUND; + + val >>= (8*n); + switch (size) { + case 1: + val &= U8_MAX; + dev_dbg(p->dev, "%s read byte %02x\n", __func__, val); + break; + case 2: + val &= U16_MAX; + dev_dbg(p->dev, "%s read word %04x\n", __func__, val); + break; + case 4: + val &= U32_MAX; + dev_dbg(p->dev, "%s read long %08x\n", __func__, val); + break; + default: + /* Should not happen */ + dev_err(p->dev, "%s illegal size\n", __func__); + return PCIBIOS_DEVICE_NOT_FOUND; + } + *value = val; + + return PCIBIOS_SUCCESSFUL; +} + +static int ixp4xx_pci_write_config(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 value) +{ + struct ixp4xx_pci *p = bus->sysdata; + u32 n, addr, val, cmd; + u8 bus_num = bus->number; + int ret; + + n = where % 4; + cmd = ixp4xx_byte_lane_enable_bits(n, size); + if (cmd == 0xffffffff) + return PCIBIOS_BAD_REGISTER_NUMBER; + + addr = ixp4xx_config_addr(bus_num, devfn, where); + cmd |= NP_CMD_CONFIGWRITE; + val = value << (8*n); + + dev_dbg(p->dev, "write_config_byte %#x to %d size %d dev %d:%d:%d addr: %08x cmd %08x\n", + value, where, size, bus_num, PCI_SLOT(devfn), PCI_FUNC(devfn), addr, cmd); + + ret = ixp4xx_pci_write_indirect(p, addr, cmd, val); + if (ret) + return PCIBIOS_DEVICE_NOT_FOUND; + + return PCIBIOS_SUCCESSFUL; +} + +static struct pci_ops ixp4xx_pci_ops = { + .read = ixp4xx_pci_read_config, + .write = ixp4xx_pci_write_config, +}; + +static u32 ixp4xx_pci_addr_to_64mconf(phys_addr_t addr) +{ + u8 base; + + base = ((addr & 0xff000000) >> 24); + return (base << 24) | ((base + 1) << 16) + | ((base + 2) << 8) | (base + 3); +} + +static int ixp4xx_pci_parse_map_ranges(struct ixp4xx_pci *p) +{ + struct device *dev = p->dev; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(p); + struct resource_entry *win; + struct resource *res; + phys_addr_t addr; + + win = resource_list_first_type(&bridge->windows, IORESOURCE_MEM); + if (win) { + u32 pcimembase; + + res = win->res; + addr = res->start - win->offset; + + if (res->flags & IORESOURCE_PREFETCH) + res->name = "IXP4xx PCI PRE-MEM"; + else + res->name = "IXP4xx PCI NON-PRE-MEM"; + + dev_dbg(dev, "%s window %pR, bus addr %pa\n", + res->name, res, &addr); + if (resource_size(res) != SZ_64M) { + dev_err(dev, "memory range is not 64MB\n"); + return -EINVAL; + } + + pcimembase = ixp4xx_pci_addr_to_64mconf(addr); + /* Commit configuration */ + ixp4xx_writel(p, IXP4XX_PCI_PCIMEMBASE, pcimembase); + } else { + dev_err(dev, "no AHB memory mapping defined\n"); + } + + win = resource_list_first_type(&bridge->windows, IORESOURCE_IO); + if (win) { + res = win->res; + + addr = pci_pio_to_address(res->start); + if (addr & 0xff) { + dev_err(dev, "IO mem at uneven address: %pa\n", &addr); + return -EINVAL; + } + + res->name = "IXP4xx PCI IO MEM"; + /* + * Setup I/O space location for PCI->AHB access, the + * upper 24 bits of the address goes into the lower + * 24 bits of this register. + */ + ixp4xx_writel(p, IXP4XX_PCI_AHBIOBASE, (addr >> 8)); + } else { + dev_info(dev, "no IO space AHB memory mapping defined\n"); + } + + return 0; +} + +static int ixp4xx_pci_parse_map_dma_ranges(struct ixp4xx_pci *p) +{ + struct device *dev = p->dev; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(p); + struct resource_entry *win; + struct resource *res; + phys_addr_t addr; + u32 ahbmembase; + + win = resource_list_first_type(&bridge->dma_ranges, IORESOURCE_MEM); + if (win) { + res = win->res; + addr = res->start - win->offset; + + if (resource_size(res) != SZ_64M) { + dev_err(dev, "DMA memory range is not 64MB\n"); + return -EINVAL; + } + + dev_dbg(dev, "DMA MEM BASE: %pa\n", &addr); + /* + * 4 PCI-to-AHB windows of 16 MB each, write the 8 high bits + * into each byte of the PCI_AHBMEMBASE register. + */ + ahbmembase = ixp4xx_pci_addr_to_64mconf(addr); + /* Commit AHB membase */ + ixp4xx_writel(p, IXP4XX_PCI_AHBMEMBASE, ahbmembase); + } else { + dev_err(dev, "no DMA memory range defined\n"); + } + + return 0; +} + +/* Only used to get context for abort handling */ +static struct ixp4xx_pci *ixp4xx_pci_abort_singleton; + +static int ixp4xx_pci_abort_handler(unsigned long addr, unsigned int fsr, + struct pt_regs *regs) +{ + struct ixp4xx_pci *p = ixp4xx_pci_abort_singleton; + u32 isr, status; + int ret; + + isr = ixp4xx_readl(p, IXP4XX_PCI_ISR); + ret = ixp4xx_crp_read_config(p, PCI_STATUS, 2, &status); + if (ret) { + dev_err(p->dev, "unable to read abort status\n"); + return -EINVAL; + } + + dev_err(p->dev, + "PCI: abort_handler addr = %#lx, isr = %#x, status = %#x\n", + addr, isr, status); + + /* Make sure the Master Abort bit is reset */ + ixp4xx_writel(p, IXP4XX_PCI_ISR, IXP4XX_PCI_ISR_PFE); + status |= PCI_STATUS_REC_MASTER_ABORT; + ret = ixp4xx_crp_write_config(p, PCI_STATUS, 2, status); + if (ret) + dev_err(p->dev, "unable to clear abort status bit\n"); + + /* + * If it was an imprecise abort, then we need to correct the + * return address to be _after_ the instruction. + */ + if (fsr & (1 << 10)) { + dev_err(p->dev, "imprecise abort\n"); + regs->ARM_pc += 4; + } + + return 0; +} + +static int __init ixp4xx_pci_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct ixp4xx_pci *p; + struct pci_host_bridge *host; + int ret; + u32 val; + phys_addr_t addr; + u32 basereg[4] = { + PCI_BASE_ADDRESS_0, + PCI_BASE_ADDRESS_1, + PCI_BASE_ADDRESS_2, + PCI_BASE_ADDRESS_3, + }; + int i; + + host = devm_pci_alloc_host_bridge(dev, sizeof(*p)); + if (!host) + return -ENOMEM; + + host->ops = &ixp4xx_pci_ops; + p = pci_host_bridge_priv(host); + host->sysdata = p; + p->dev = dev; + dev_set_drvdata(dev, p); + + /* + * Set up quirk for erratic behaviour in the 42x variant + * when accessing config space. + */ + if (of_device_is_compatible(np, "intel,ixp42x-pci")) { + p->errata_hammer = true; + dev_info(dev, "activate hammering errata\n"); + } + + p->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(p->base)) + return PTR_ERR(p->base); + + val = ixp4xx_readl(p, IXP4XX_PCI_CSR); + p->host_mode = !!(val & IXP4XX_PCI_CSR_HOST); + dev_info(dev, "controller is in %s mode\n", + p->host_mode ? "host" : "option"); + + /* Hook in our fault handler for PCI errors */ + ixp4xx_pci_abort_singleton = p; + hook_fault_code(16+6, ixp4xx_pci_abort_handler, SIGBUS, 0, + "imprecise external abort"); + + ret = ixp4xx_pci_parse_map_ranges(p); + if (ret) + return ret; + + ret = ixp4xx_pci_parse_map_dma_ranges(p); + if (ret) + return ret; + + /* This is only configured in host mode */ + if (p->host_mode) { + addr = __pa(PAGE_OFFSET); + /* This is a noop (0x00) but explains what is going on */ + addr |= PCI_BASE_ADDRESS_SPACE_MEMORY; + + for (i = 0; i < 4; i++) { + /* Write this directly into the config space */ + ret = ixp4xx_crp_write_config(p, basereg[i], 4, addr); + if (ret) + dev_err(dev, "failed to set up PCI_BASE_ADDRESS_%d\n", i); + else + dev_info(dev, "set PCI_BASE_ADDR_%d to %pa\n", i, &addr); + addr += SZ_16M; + } + + /* + * Enable CSR window at 64 MiB to allow PCI masters to continue + * prefetching past the 64 MiB boundary, if all AHB to PCI + * windows are consecutive. + */ + ret = ixp4xx_crp_write_config(p, PCI_BASE_ADDRESS_4, 4, addr); + if (ret) + dev_err(dev, "failed to set up PCI_BASE_ADDRESS_4\n"); + else + dev_info(dev, "set PCI_BASE_ADDR_4 to %pa\n", &addr); + + /* + * Put the IO memory window at the very end of physical memory + * at 0xfffffc00. This is when the system is trying to access IO + * memory over AHB. + */ + addr = 0xfffffc00; + addr |= PCI_BASE_ADDRESS_SPACE_IO; + ret = ixp4xx_crp_write_config(p, PCI_BASE_ADDRESS_5, 4, addr); + if (ret) + dev_err(dev, "failed to set up PCI_BASE_ADDRESS_5\n"); + else + dev_info(dev, "set PCI_BASE_ADDR_5 to %pa\n", &addr); + + /* + * Retry timeout to 0x80 + * Transfer ready timeout to 0xff + */ + ret = ixp4xx_crp_write_config(p, IXP4XX_PCI_RTOTTO, 4, + 0x000080ff); + if (ret) + dev_err(dev, "failed to set up TRDY limit\n"); + else + dev_info(dev, "set TRDY limit to 0x80ff\n"); + } + + /* Clear interrupts */ + val = IXP4XX_PCI_ISR_PSE | IXP4XX_PCI_ISR_PFE | IXP4XX_PCI_ISR_PPE | IXP4XX_PCI_ISR_AHBE; + ixp4xx_writel(p, IXP4XX_PCI_ISR, val); + + /* + * Set Initialize Complete in PCI Control Register: allow IXP4XX to + * generate PCI configuration cycles. Specify that the AHB bus is + * operating in big-endian mode. Set up byte lane swapping between + * little-endian PCI and the big-endian AHB bus. + */ + val = IXP4XX_PCI_CSR_IC | IXP4XX_PCI_CSR_ABE; + if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) + val |= (IXP4XX_PCI_CSR_PDS | IXP4XX_PCI_CSR_ADS); + ixp4xx_writel(p, IXP4XX_PCI_CSR, val); + + ret = ixp4xx_crp_write_config(p, PCI_COMMAND, 2, PCI_COMMAND_MASTER | PCI_COMMAND_MEMORY); + if (ret) + dev_err(dev, "unable to initialize master and command memory\n"); + else + dev_info(dev, "initialized as master\n"); + + pci_host_probe(host); + + return 0; +} + +static const struct of_device_id ixp4xx_pci_of_match[] = { + { + .compatible = "intel,ixp42x-pci", + }, + { + .compatible = "intel,ixp43x-pci", + }, + {}, +}; + +/* + * This driver needs to be a builtin module with suppressed bind + * attributes since the probe() is initializing a hard exception + * handler and this can only be done from __init-tagged code + * sections. This module cannot be removed and inserted at all. + */ +static struct platform_driver ixp4xx_pci_driver = { + .driver = { + .name = "ixp4xx-pci", + .suppress_bind_attrs = true, + .of_match_table = ixp4xx_pci_of_match, + }, +}; +builtin_platform_driver_probe(ixp4xx_pci_driver, ixp4xx_pci_probe); diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c new file mode 100644 index 000000000..a860f2547 --- /dev/null +++ b/drivers/pci/controller/pci-loongson.c @@ -0,0 +1,397 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Loongson PCI Host Controller Driver + * + * Copyright (C) 2020 Jiaxun Yang <jiaxun.yang@flygoat.com> + */ + +#include <linux/of_device.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/pci_ids.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> + +#include "../pci.h" + +/* Device IDs */ +#define DEV_LS2K_PCIE_PORT0 0x1a05 +#define DEV_LS7A_PCIE_PORT0 0x7a09 +#define DEV_LS7A_PCIE_PORT1 0x7a19 +#define DEV_LS7A_PCIE_PORT2 0x7a29 +#define DEV_LS7A_PCIE_PORT3 0x7a39 +#define DEV_LS7A_PCIE_PORT4 0x7a49 +#define DEV_LS7A_PCIE_PORT5 0x7a59 +#define DEV_LS7A_PCIE_PORT6 0x7a69 + +#define DEV_LS2K_APB 0x7a02 +#define DEV_LS7A_GMAC 0x7a03 +#define DEV_LS7A_DC1 0x7a06 +#define DEV_LS7A_LPC 0x7a0c +#define DEV_LS7A_AHCI 0x7a08 +#define DEV_LS7A_CONF 0x7a10 +#define DEV_LS7A_GNET 0x7a13 +#define DEV_LS7A_EHCI 0x7a14 +#define DEV_LS7A_DC2 0x7a36 +#define DEV_LS7A_HDMI 0x7a37 + +#define FLAG_CFG0 BIT(0) +#define FLAG_CFG1 BIT(1) +#define FLAG_DEV_FIX BIT(2) +#define FLAG_DEV_HIDDEN BIT(3) + +struct loongson_pci_data { + u32 flags; + struct pci_ops *ops; +}; + +struct loongson_pci { + void __iomem *cfg0_base; + void __iomem *cfg1_base; + struct platform_device *pdev; + const struct loongson_pci_data *data; +}; + +/* Fixup wrong class code in PCIe bridges */ +static void bridge_class_quirk(struct pci_dev *dev) +{ + dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT0, bridge_class_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT1, bridge_class_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT2, bridge_class_quirk); + +static void system_bus_quirk(struct pci_dev *pdev) +{ + /* + * The address space consumed by these devices is outside the + * resources of the host bridge. + */ + pdev->mmio_always_on = 1; + pdev->non_compliant_bars = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS2K_APB, system_bus_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_CONF, system_bus_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_LPC, system_bus_quirk); + +/* + * Some Loongson PCIe ports have hardware limitations on their Maximum Read + * Request Size. They can't handle anything larger than this. Sane + * firmware will set proper MRRS at boot, so we only need no_inc_mrrs for + * bridges. However, some MIPS Loongson firmware doesn't set MRRS properly, + * so we have to enforce maximum safe MRRS, which is 256 bytes. + */ +#ifdef CONFIG_MIPS +static void loongson_set_min_mrrs_quirk(struct pci_dev *pdev) +{ + struct pci_bus *bus = pdev->bus; + struct pci_dev *bridge; + static const struct pci_device_id bridge_devids[] = { + { PCI_VDEVICE(LOONGSON, DEV_LS2K_PCIE_PORT0) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT0) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT1) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT2) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT3) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT4) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT5) }, + { PCI_VDEVICE(LOONGSON, DEV_LS7A_PCIE_PORT6) }, + { 0, }, + }; + + /* look for the matching bridge */ + while (!pci_is_root_bus(bus)) { + bridge = bus->self; + bus = bus->parent; + + if (pci_match_id(bridge_devids, bridge)) { + if (pcie_get_readrq(pdev) > 256) { + pci_info(pdev, "limiting MRRS to 256\n"); + pcie_set_readrq(pdev, 256); + } + break; + } + } +} +DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_set_min_mrrs_quirk); +#endif + +static void loongson_mrrs_quirk(struct pci_dev *pdev) +{ + struct pci_host_bridge *bridge = pci_find_host_bridge(pdev->bus); + + bridge->no_inc_mrrs = 1; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS2K_PCIE_PORT0, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT0, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT1, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT2, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT3, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT4, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT5, loongson_mrrs_quirk); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_PCIE_PORT6, loongson_mrrs_quirk); + +static void loongson_pci_pin_quirk(struct pci_dev *pdev) +{ + pdev->pin = 1 + (PCI_FUNC(pdev->devfn) & 3); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_DC1, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_DC2, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_GMAC, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_AHCI, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_EHCI, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_GNET, loongson_pci_pin_quirk); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, + DEV_LS7A_HDMI, loongson_pci_pin_quirk); + +static struct loongson_pci *pci_bus_to_loongson_pci(struct pci_bus *bus) +{ + struct pci_config_window *cfg; + + if (acpi_disabled) + return (struct loongson_pci *)(bus->sysdata); + + cfg = bus->sysdata; + return (struct loongson_pci *)(cfg->priv); +} + +static void __iomem *cfg0_map(struct loongson_pci *priv, struct pci_bus *bus, + unsigned int devfn, int where) +{ + unsigned long addroff = 0x0; + unsigned char busnum = bus->number; + + if (!pci_is_root_bus(bus)) { + addroff |= BIT(24); /* Type 1 Access */ + addroff |= (busnum << 16); + } + addroff |= (devfn << 8) | where; + return priv->cfg0_base + addroff; +} + +static void __iomem *cfg1_map(struct loongson_pci *priv, struct pci_bus *bus, + unsigned int devfn, int where) +{ + unsigned long addroff = 0x0; + unsigned char busnum = bus->number; + + if (!pci_is_root_bus(bus)) { + addroff |= BIT(28); /* Type 1 Access */ + addroff |= (busnum << 16); + } + addroff |= (devfn << 8) | (where & 0xff) | ((where & 0xf00) << 16); + return priv->cfg1_base + addroff; +} + +static bool pdev_may_exist(struct pci_bus *bus, unsigned int device, + unsigned int function) +{ + return !(pci_is_root_bus(bus) && + (device >= 9 && device <= 20) && (function > 0)); +} + +static void __iomem *pci_loongson_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + unsigned int device = PCI_SLOT(devfn); + unsigned int function = PCI_FUNC(devfn); + struct loongson_pci *priv = pci_bus_to_loongson_pci(bus); + + /* + * Do not read more than one device on the bus other than + * the host bus. + */ + if ((priv->data->flags & FLAG_DEV_FIX) && bus->self) { + if (!pci_is_root_bus(bus) && (device > 0)) + return NULL; + } + + /* Don't access non-existent devices */ + if (priv->data->flags & FLAG_DEV_HIDDEN) { + if (!pdev_may_exist(bus, device, function)) + return NULL; + } + + /* CFG0 can only access standard space */ + if (where < PCI_CFG_SPACE_SIZE && priv->cfg0_base) + return cfg0_map(priv, bus, devfn, where); + + /* CFG1 can access extended space */ + if (where < PCI_CFG_SPACE_EXP_SIZE && priv->cfg1_base) + return cfg1_map(priv, bus, devfn, where); + + return NULL; +} + +#ifdef CONFIG_OF + +static int loongson_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +{ + int irq; + u8 val; + + irq = of_irq_parse_and_map_pci(dev, slot, pin); + if (irq > 0) + return irq; + + /* Care i8259 legacy systems */ + pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &val); + /* i8259 only have 15 IRQs */ + if (val > 15) + return 0; + + return val; +} + +/* LS2K/LS7A accept 8/16/32-bit PCI config operations */ +static struct pci_ops loongson_pci_ops = { + .map_bus = pci_loongson_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +/* RS780/SR5690 only accept 32-bit PCI config operations */ +static struct pci_ops loongson_pci_ops32 = { + .map_bus = pci_loongson_map_bus, + .read = pci_generic_config_read32, + .write = pci_generic_config_write32, +}; + +static const struct loongson_pci_data ls2k_pci_data = { + .flags = FLAG_CFG1 | FLAG_DEV_FIX | FLAG_DEV_HIDDEN, + .ops = &loongson_pci_ops, +}; + +static const struct loongson_pci_data ls7a_pci_data = { + .flags = FLAG_CFG1 | FLAG_DEV_FIX | FLAG_DEV_HIDDEN, + .ops = &loongson_pci_ops, +}; + +static const struct loongson_pci_data rs780e_pci_data = { + .flags = FLAG_CFG0, + .ops = &loongson_pci_ops32, +}; + +static const struct of_device_id loongson_pci_of_match[] = { + { .compatible = "loongson,ls2k-pci", + .data = &ls2k_pci_data, }, + { .compatible = "loongson,ls7a-pci", + .data = &ls7a_pci_data, }, + { .compatible = "loongson,rs780e-pci", + .data = &rs780e_pci_data, }, + {} +}; + +static int loongson_pci_probe(struct platform_device *pdev) +{ + struct loongson_pci *priv; + struct device *dev = &pdev->dev; + struct device_node *node = dev->of_node; + struct pci_host_bridge *bridge; + struct resource *regs; + + if (!node) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*priv)); + if (!bridge) + return -ENODEV; + + priv = pci_host_bridge_priv(bridge); + priv->pdev = pdev; + priv->data = of_device_get_match_data(dev); + + if (priv->data->flags & FLAG_CFG0) { + regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (!regs) + dev_err(dev, "missing mem resources for cfg0\n"); + else { + priv->cfg0_base = devm_pci_remap_cfg_resource(dev, regs); + if (IS_ERR(priv->cfg0_base)) + return PTR_ERR(priv->cfg0_base); + } + } + + if (priv->data->flags & FLAG_CFG1) { + regs = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!regs) + dev_info(dev, "missing mem resource for cfg1\n"); + else { + priv->cfg1_base = devm_pci_remap_cfg_resource(dev, regs); + if (IS_ERR(priv->cfg1_base)) + priv->cfg1_base = NULL; + } + } + + bridge->sysdata = priv; + bridge->ops = priv->data->ops; + bridge->map_irq = loongson_map_irq; + + return pci_host_probe(bridge); +} + +static struct platform_driver loongson_pci_driver = { + .driver = { + .name = "loongson-pci", + .of_match_table = loongson_pci_of_match, + }, + .probe = loongson_pci_probe, +}; +builtin_platform_driver(loongson_pci_driver); + +#endif + +#ifdef CONFIG_ACPI + +static int loongson_pci_ecam_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct loongson_pci *priv; + struct loongson_pci_data *data; + + priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + cfg->priv = priv; + data->flags = FLAG_CFG1 | FLAG_DEV_HIDDEN; + priv->data = data; + priv->cfg1_base = cfg->win - (cfg->busr.start << 16); + + return 0; +} + +const struct pci_ecam_ops loongson_pci_ecam_ops = { + .bus_shift = 16, + .init = loongson_pci_ecam_init, + .pci_ops = { + .map_bus = pci_loongson_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +#endif diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c new file mode 100644 index 000000000..668601fd0 --- /dev/null +++ b/drivers/pci/controller/pci-mvebu.c @@ -0,0 +1,1756 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe driver for Marvell Armada 370 and Armada XP SoCs + * + * Author: Thomas Petazzoni <thomas.petazzoni@free-electrons.com> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/pci.h> +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio.h> +#include <linux/init.h> +#include <linux/mbus.h> +#include <linux/slab.h> +#include <linux/platform_device.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_gpio.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> + +#include "../pci.h" +#include "../pci-bridge-emul.h" + +/* + * PCIe unit register offsets. + */ +#define PCIE_DEV_ID_OFF 0x0000 +#define PCIE_CMD_OFF 0x0004 +#define PCIE_DEV_REV_OFF 0x0008 +#define PCIE_BAR_LO_OFF(n) (0x0010 + ((n) << 3)) +#define PCIE_BAR_HI_OFF(n) (0x0014 + ((n) << 3)) +#define PCIE_SSDEV_ID_OFF 0x002c +#define PCIE_CAP_PCIEXP 0x0060 +#define PCIE_CAP_PCIERR_OFF 0x0100 +#define PCIE_BAR_CTRL_OFF(n) (0x1804 + (((n) - 1) * 4)) +#define PCIE_WIN04_CTRL_OFF(n) (0x1820 + ((n) << 4)) +#define PCIE_WIN04_BASE_OFF(n) (0x1824 + ((n) << 4)) +#define PCIE_WIN04_REMAP_OFF(n) (0x182c + ((n) << 4)) +#define PCIE_WIN5_CTRL_OFF 0x1880 +#define PCIE_WIN5_BASE_OFF 0x1884 +#define PCIE_WIN5_REMAP_OFF 0x188c +#define PCIE_CONF_ADDR_OFF 0x18f8 +#define PCIE_CONF_ADDR_EN 0x80000000 +#define PCIE_CONF_REG(r) ((((r) & 0xf00) << 16) | ((r) & 0xfc)) +#define PCIE_CONF_BUS(b) (((b) & 0xff) << 16) +#define PCIE_CONF_DEV(d) (((d) & 0x1f) << 11) +#define PCIE_CONF_FUNC(f) (((f) & 0x7) << 8) +#define PCIE_CONF_ADDR(bus, devfn, where) \ + (PCIE_CONF_BUS(bus) | PCIE_CONF_DEV(PCI_SLOT(devfn)) | \ + PCIE_CONF_FUNC(PCI_FUNC(devfn)) | PCIE_CONF_REG(where) | \ + PCIE_CONF_ADDR_EN) +#define PCIE_CONF_DATA_OFF 0x18fc +#define PCIE_INT_CAUSE_OFF 0x1900 +#define PCIE_INT_UNMASK_OFF 0x1910 +#define PCIE_INT_INTX(i) BIT(24+i) +#define PCIE_INT_PM_PME BIT(28) +#define PCIE_INT_ALL_MASK GENMASK(31, 0) +#define PCIE_CTRL_OFF 0x1a00 +#define PCIE_CTRL_X1_MODE 0x0001 +#define PCIE_CTRL_RC_MODE BIT(1) +#define PCIE_CTRL_MASTER_HOT_RESET BIT(24) +#define PCIE_STAT_OFF 0x1a04 +#define PCIE_STAT_BUS 0xff00 +#define PCIE_STAT_DEV 0x1f0000 +#define PCIE_STAT_LINK_DOWN BIT(0) +#define PCIE_SSPL_OFF 0x1a0c +#define PCIE_SSPL_VALUE_SHIFT 0 +#define PCIE_SSPL_VALUE_MASK GENMASK(7, 0) +#define PCIE_SSPL_SCALE_SHIFT 8 +#define PCIE_SSPL_SCALE_MASK GENMASK(9, 8) +#define PCIE_SSPL_ENABLE BIT(16) +#define PCIE_RC_RTSTA 0x1a14 +#define PCIE_DEBUG_CTRL 0x1a60 +#define PCIE_DEBUG_SOFT_RESET BIT(20) + +struct mvebu_pcie_port; + +/* Structure representing all PCIe interfaces */ +struct mvebu_pcie { + struct platform_device *pdev; + struct mvebu_pcie_port *ports; + struct resource io; + struct resource realio; + struct resource mem; + struct resource busn; + int nports; +}; + +struct mvebu_pcie_window { + phys_addr_t base; + phys_addr_t remap; + size_t size; +}; + +/* Structure representing one PCIe interface */ +struct mvebu_pcie_port { + char *name; + void __iomem *base; + u32 port; + u32 lane; + bool is_x4; + int devfn; + unsigned int mem_target; + unsigned int mem_attr; + unsigned int io_target; + unsigned int io_attr; + struct clk *clk; + struct gpio_desc *reset_gpio; + char *reset_name; + struct pci_bridge_emul bridge; + struct device_node *dn; + struct mvebu_pcie *pcie; + struct mvebu_pcie_window memwin; + struct mvebu_pcie_window iowin; + u32 saved_pcie_stat; + struct resource regs; + u8 slot_power_limit_value; + u8 slot_power_limit_scale; + struct irq_domain *intx_irq_domain; + raw_spinlock_t irq_lock; + int intx_irq; +}; + +static inline void mvebu_writel(struct mvebu_pcie_port *port, u32 val, u32 reg) +{ + writel(val, port->base + reg); +} + +static inline u32 mvebu_readl(struct mvebu_pcie_port *port, u32 reg) +{ + return readl(port->base + reg); +} + +static inline bool mvebu_has_ioport(struct mvebu_pcie_port *port) +{ + return port->io_target != -1 && port->io_attr != -1; +} + +static bool mvebu_pcie_link_up(struct mvebu_pcie_port *port) +{ + return !(mvebu_readl(port, PCIE_STAT_OFF) & PCIE_STAT_LINK_DOWN); +} + +static u8 mvebu_pcie_get_local_bus_nr(struct mvebu_pcie_port *port) +{ + return (mvebu_readl(port, PCIE_STAT_OFF) & PCIE_STAT_BUS) >> 8; +} + +static void mvebu_pcie_set_local_bus_nr(struct mvebu_pcie_port *port, int nr) +{ + u32 stat; + + stat = mvebu_readl(port, PCIE_STAT_OFF); + stat &= ~PCIE_STAT_BUS; + stat |= nr << 8; + mvebu_writel(port, stat, PCIE_STAT_OFF); +} + +static void mvebu_pcie_set_local_dev_nr(struct mvebu_pcie_port *port, int nr) +{ + u32 stat; + + stat = mvebu_readl(port, PCIE_STAT_OFF); + stat &= ~PCIE_STAT_DEV; + stat |= nr << 16; + mvebu_writel(port, stat, PCIE_STAT_OFF); +} + +static void mvebu_pcie_disable_wins(struct mvebu_pcie_port *port) +{ + int i; + + mvebu_writel(port, 0, PCIE_BAR_LO_OFF(0)); + mvebu_writel(port, 0, PCIE_BAR_HI_OFF(0)); + + for (i = 1; i < 3; i++) { + mvebu_writel(port, 0, PCIE_BAR_CTRL_OFF(i)); + mvebu_writel(port, 0, PCIE_BAR_LO_OFF(i)); + mvebu_writel(port, 0, PCIE_BAR_HI_OFF(i)); + } + + for (i = 0; i < 5; i++) { + mvebu_writel(port, 0, PCIE_WIN04_CTRL_OFF(i)); + mvebu_writel(port, 0, PCIE_WIN04_BASE_OFF(i)); + mvebu_writel(port, 0, PCIE_WIN04_REMAP_OFF(i)); + } + + mvebu_writel(port, 0, PCIE_WIN5_CTRL_OFF); + mvebu_writel(port, 0, PCIE_WIN5_BASE_OFF); + mvebu_writel(port, 0, PCIE_WIN5_REMAP_OFF); +} + +/* + * Setup PCIE BARs and Address Decode Wins: + * BAR[0] -> internal registers (needed for MSI) + * BAR[1] -> covers all DRAM banks + * BAR[2] -> Disabled + * WIN[0-3] -> DRAM bank[0-3] + */ +static void mvebu_pcie_setup_wins(struct mvebu_pcie_port *port) +{ + const struct mbus_dram_target_info *dram; + u32 size; + int i; + + dram = mv_mbus_dram_info(); + + /* First, disable and clear BARs and windows. */ + mvebu_pcie_disable_wins(port); + + /* Setup windows for DDR banks. Count total DDR size on the fly. */ + size = 0; + for (i = 0; i < dram->num_cs; i++) { + const struct mbus_dram_window *cs = dram->cs + i; + + mvebu_writel(port, cs->base & 0xffff0000, + PCIE_WIN04_BASE_OFF(i)); + mvebu_writel(port, 0, PCIE_WIN04_REMAP_OFF(i)); + mvebu_writel(port, + ((cs->size - 1) & 0xffff0000) | + (cs->mbus_attr << 8) | + (dram->mbus_dram_target_id << 4) | 1, + PCIE_WIN04_CTRL_OFF(i)); + + size += cs->size; + } + + /* Round up 'size' to the nearest power of two. */ + if ((size & (size - 1)) != 0) + size = 1 << fls(size); + + /* Setup BAR[1] to all DRAM banks. */ + mvebu_writel(port, dram->cs[0].base, PCIE_BAR_LO_OFF(1)); + mvebu_writel(port, 0, PCIE_BAR_HI_OFF(1)); + mvebu_writel(port, ((size - 1) & 0xffff0000) | 1, + PCIE_BAR_CTRL_OFF(1)); + + /* + * Point BAR[0] to the device's internal registers. + */ + mvebu_writel(port, round_down(port->regs.start, SZ_1M), PCIE_BAR_LO_OFF(0)); + mvebu_writel(port, 0, PCIE_BAR_HI_OFF(0)); +} + +static void mvebu_pcie_setup_hw(struct mvebu_pcie_port *port) +{ + u32 ctrl, lnkcap, cmd, dev_rev, unmask, sspl; + + /* Setup PCIe controller to Root Complex mode. */ + ctrl = mvebu_readl(port, PCIE_CTRL_OFF); + ctrl |= PCIE_CTRL_RC_MODE; + mvebu_writel(port, ctrl, PCIE_CTRL_OFF); + + /* + * Set Maximum Link Width to X1 or X4 in Root Port's PCIe Link + * Capability register. This register is defined by PCIe specification + * as read-only but this mvebu controller has it as read-write and must + * be set to number of SerDes PCIe lanes (1 or 4). If this register is + * not set correctly then link with endpoint card is not established. + */ + lnkcap = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP); + lnkcap &= ~PCI_EXP_LNKCAP_MLW; + lnkcap |= FIELD_PREP(PCI_EXP_LNKCAP_MLW, port->is_x4 ? 4 : 1); + mvebu_writel(port, lnkcap, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP); + + /* Disable Root Bridge I/O space, memory space and bus mastering. */ + cmd = mvebu_readl(port, PCIE_CMD_OFF); + cmd &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); + mvebu_writel(port, cmd, PCIE_CMD_OFF); + + /* + * Change Class Code of PCI Bridge device to PCI Bridge (0x6004) + * because default value is Memory controller (0x5080). + * + * Note that this mvebu PCI Bridge does not have compliant Type 1 + * Configuration Space. Header Type is reported as Type 0 and it + * has format of Type 0 config space. + * + * Moreover Type 0 BAR registers (ranges 0x10 - 0x28 and 0x30 - 0x34) + * have the same format in Marvell's specification as in PCIe + * specification, but their meaning is totally different and they do + * different things: they are aliased into internal mvebu registers + * (e.g. PCIE_BAR_LO_OFF) and these should not be changed or + * reconfigured by pci device drivers. + * + * Therefore driver uses emulation of PCI Bridge which emulates + * access to configuration space via internal mvebu registers or + * emulated configuration buffer. Driver access these PCI Bridge + * directly for simplification, but these registers can be accessed + * also via standard mvebu way for accessing PCI config space. + */ + dev_rev = mvebu_readl(port, PCIE_DEV_REV_OFF); + dev_rev &= ~0xffffff00; + dev_rev |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8; + mvebu_writel(port, dev_rev, PCIE_DEV_REV_OFF); + + /* Point PCIe unit MBUS decode windows to DRAM space. */ + mvebu_pcie_setup_wins(port); + + /* + * Program Root Port to automatically send Set_Slot_Power_Limit + * PCIe Message when changing status from Dl_Down to Dl_Up and valid + * slot power limit was specified. + */ + sspl = mvebu_readl(port, PCIE_SSPL_OFF); + sspl &= ~(PCIE_SSPL_VALUE_MASK | PCIE_SSPL_SCALE_MASK | PCIE_SSPL_ENABLE); + if (port->slot_power_limit_value) { + sspl |= port->slot_power_limit_value << PCIE_SSPL_VALUE_SHIFT; + sspl |= port->slot_power_limit_scale << PCIE_SSPL_SCALE_SHIFT; + sspl |= PCIE_SSPL_ENABLE; + } + mvebu_writel(port, sspl, PCIE_SSPL_OFF); + + /* Mask all interrupt sources. */ + mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_UNMASK_OFF); + + /* Clear all interrupt causes. */ + mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_CAUSE_OFF); + + /* Check if "intx" interrupt was specified in DT. */ + if (port->intx_irq > 0) + return; + + /* + * Fallback code when "intx" interrupt was not specified in DT: + * Unmask all legacy INTx interrupts as driver does not provide a way + * for masking and unmasking of individual legacy INTx interrupts. + * Legacy INTx are reported via one shared GIC source and therefore + * kernel cannot distinguish which individual legacy INTx was triggered. + * These interrupts are shared, so it should not cause any issue. Just + * performance penalty as every PCIe interrupt handler needs to be + * called when some interrupt is triggered. + */ + unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF); + unmask |= PCIE_INT_INTX(0) | PCIE_INT_INTX(1) | + PCIE_INT_INTX(2) | PCIE_INT_INTX(3); + mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF); +} + +static struct mvebu_pcie_port *mvebu_pcie_find_port(struct mvebu_pcie *pcie, + struct pci_bus *bus, + int devfn); + +static int mvebu_pcie_child_rd_conf(struct pci_bus *bus, u32 devfn, int where, + int size, u32 *val) +{ + struct mvebu_pcie *pcie = bus->sysdata; + struct mvebu_pcie_port *port; + void __iomem *conf_data; + + port = mvebu_pcie_find_port(pcie, bus, devfn); + if (!port) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (!mvebu_pcie_link_up(port)) + return PCIBIOS_DEVICE_NOT_FOUND; + + conf_data = port->base + PCIE_CONF_DATA_OFF; + + mvebu_writel(port, PCIE_CONF_ADDR(bus->number, devfn, where), + PCIE_CONF_ADDR_OFF); + + switch (size) { + case 1: + *val = readb_relaxed(conf_data + (where & 3)); + break; + case 2: + *val = readw_relaxed(conf_data + (where & 2)); + break; + case 4: + *val = readl_relaxed(conf_data); + break; + default: + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + return PCIBIOS_SUCCESSFUL; +} + +static int mvebu_pcie_child_wr_conf(struct pci_bus *bus, u32 devfn, + int where, int size, u32 val) +{ + struct mvebu_pcie *pcie = bus->sysdata; + struct mvebu_pcie_port *port; + void __iomem *conf_data; + + port = mvebu_pcie_find_port(pcie, bus, devfn); + if (!port) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (!mvebu_pcie_link_up(port)) + return PCIBIOS_DEVICE_NOT_FOUND; + + conf_data = port->base + PCIE_CONF_DATA_OFF; + + mvebu_writel(port, PCIE_CONF_ADDR(bus->number, devfn, where), + PCIE_CONF_ADDR_OFF); + + switch (size) { + case 1: + writeb(val, conf_data + (where & 3)); + break; + case 2: + writew(val, conf_data + (where & 2)); + break; + case 4: + writel(val, conf_data); + break; + default: + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + return PCIBIOS_SUCCESSFUL; +} + +static struct pci_ops mvebu_pcie_child_ops = { + .read = mvebu_pcie_child_rd_conf, + .write = mvebu_pcie_child_wr_conf, +}; + +/* + * Remove windows, starting from the largest ones to the smallest + * ones. + */ +static void mvebu_pcie_del_windows(struct mvebu_pcie_port *port, + phys_addr_t base, size_t size) +{ + while (size) { + size_t sz = 1 << (fls(size) - 1); + + mvebu_mbus_del_window(base, sz); + base += sz; + size -= sz; + } +} + +/* + * MBus windows can only have a power of two size, but PCI BARs do not + * have this constraint. Therefore, we have to split the PCI BAR into + * areas each having a power of two size. We start from the largest + * one (i.e highest order bit set in the size). + */ +static int mvebu_pcie_add_windows(struct mvebu_pcie_port *port, + unsigned int target, unsigned int attribute, + phys_addr_t base, size_t size, + phys_addr_t remap) +{ + size_t size_mapped = 0; + + while (size) { + size_t sz = 1 << (fls(size) - 1); + int ret; + + ret = mvebu_mbus_add_window_remap_by_id(target, attribute, base, + sz, remap); + if (ret) { + phys_addr_t end = base + sz - 1; + + dev_err(&port->pcie->pdev->dev, + "Could not create MBus window at [mem %pa-%pa]: %d\n", + &base, &end, ret); + mvebu_pcie_del_windows(port, base - size_mapped, + size_mapped); + return ret; + } + + size -= sz; + size_mapped += sz; + base += sz; + if (remap != MVEBU_MBUS_NO_REMAP) + remap += sz; + } + + return 0; +} + +static int mvebu_pcie_set_window(struct mvebu_pcie_port *port, + unsigned int target, unsigned int attribute, + const struct mvebu_pcie_window *desired, + struct mvebu_pcie_window *cur) +{ + int ret; + + if (desired->base == cur->base && desired->remap == cur->remap && + desired->size == cur->size) + return 0; + + if (cur->size != 0) { + mvebu_pcie_del_windows(port, cur->base, cur->size); + cur->size = 0; + cur->base = 0; + + /* + * If something tries to change the window while it is enabled + * the change will not be done atomically. That would be + * difficult to do in the general case. + */ + } + + if (desired->size == 0) + return 0; + + ret = mvebu_pcie_add_windows(port, target, attribute, desired->base, + desired->size, desired->remap); + if (ret) { + cur->size = 0; + cur->base = 0; + return ret; + } + + *cur = *desired; + return 0; +} + +static int mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port) +{ + struct mvebu_pcie_window desired = {}; + struct pci_bridge_emul_conf *conf = &port->bridge.conf; + + /* Are the new iobase/iolimit values invalid? */ + if (conf->iolimit < conf->iobase || + le16_to_cpu(conf->iolimitupper) < le16_to_cpu(conf->iobaseupper)) + return mvebu_pcie_set_window(port, port->io_target, port->io_attr, + &desired, &port->iowin); + + /* + * We read the PCI-to-PCI bridge emulated registers, and + * calculate the base address and size of the address decoding + * window to setup, according to the PCI-to-PCI bridge + * specifications. iobase is the bus address, port->iowin_base + * is the CPU address. + */ + desired.remap = ((conf->iobase & 0xF0) << 8) | + (le16_to_cpu(conf->iobaseupper) << 16); + desired.base = port->pcie->io.start + desired.remap; + desired.size = ((0xFFF | ((conf->iolimit & 0xF0) << 8) | + (le16_to_cpu(conf->iolimitupper) << 16)) - + desired.remap) + + 1; + + return mvebu_pcie_set_window(port, port->io_target, port->io_attr, &desired, + &port->iowin); +} + +static int mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port) +{ + struct mvebu_pcie_window desired = {.remap = MVEBU_MBUS_NO_REMAP}; + struct pci_bridge_emul_conf *conf = &port->bridge.conf; + + /* Are the new membase/memlimit values invalid? */ + if (le16_to_cpu(conf->memlimit) < le16_to_cpu(conf->membase)) + return mvebu_pcie_set_window(port, port->mem_target, port->mem_attr, + &desired, &port->memwin); + + /* + * We read the PCI-to-PCI bridge emulated registers, and + * calculate the base address and size of the address decoding + * window to setup, according to the PCI-to-PCI bridge + * specifications. + */ + desired.base = ((le16_to_cpu(conf->membase) & 0xFFF0) << 16); + desired.size = (((le16_to_cpu(conf->memlimit) & 0xFFF0) << 16) | 0xFFFFF) - + desired.base + 1; + + return mvebu_pcie_set_window(port, port->mem_target, port->mem_attr, &desired, + &port->memwin); +} + +static pci_bridge_emul_read_status_t +mvebu_pci_bridge_emul_base_conf_read(struct pci_bridge_emul *bridge, + int reg, u32 *value) +{ + struct mvebu_pcie_port *port = bridge->data; + + switch (reg) { + case PCI_COMMAND: + *value = mvebu_readl(port, PCIE_CMD_OFF); + break; + + case PCI_PRIMARY_BUS: { + /* + * From the whole 32bit register we support reading from HW only + * secondary bus number which is mvebu local bus number. + * Other bits are retrieved only from emulated config buffer. + */ + __le32 *cfgspace = (__le32 *)&bridge->conf; + u32 val = le32_to_cpu(cfgspace[PCI_PRIMARY_BUS / 4]); + val &= ~0xff00; + val |= mvebu_pcie_get_local_bus_nr(port) << 8; + *value = val; + break; + } + + case PCI_INTERRUPT_LINE: { + /* + * From the whole 32bit register we support reading from HW only + * one bit: PCI_BRIDGE_CTL_BUS_RESET. + * Other bits are retrieved only from emulated config buffer. + */ + __le32 *cfgspace = (__le32 *)&bridge->conf; + u32 val = le32_to_cpu(cfgspace[PCI_INTERRUPT_LINE / 4]); + if (mvebu_readl(port, PCIE_CTRL_OFF) & PCIE_CTRL_MASTER_HOT_RESET) + val |= PCI_BRIDGE_CTL_BUS_RESET << 16; + else + val &= ~(PCI_BRIDGE_CTL_BUS_RESET << 16); + *value = val; + break; + } + + default: + return PCI_BRIDGE_EMUL_NOT_HANDLED; + } + + return PCI_BRIDGE_EMUL_HANDLED; +} + +static pci_bridge_emul_read_status_t +mvebu_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge, + int reg, u32 *value) +{ + struct mvebu_pcie_port *port = bridge->data; + + switch (reg) { + case PCI_EXP_DEVCAP: + *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_DEVCAP); + break; + + case PCI_EXP_DEVCTL: + *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL); + break; + + case PCI_EXP_LNKCAP: + /* + * PCIe requires that the Clock Power Management capability bit + * is hard-wired to zero for downstream ports but HW returns 1. + * Additionally enable Data Link Layer Link Active Reporting + * Capable bit as DL_Active indication is provided too. + */ + *value = (mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP) & + ~PCI_EXP_LNKCAP_CLKPM) | PCI_EXP_LNKCAP_DLLLARC; + break; + + case PCI_EXP_LNKCTL: + /* DL_Active indication is provided via PCIE_STAT_OFF */ + *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL) | + (mvebu_pcie_link_up(port) ? + (PCI_EXP_LNKSTA_DLLLA << 16) : 0); + break; + + case PCI_EXP_SLTCTL: { + u16 slotctl = le16_to_cpu(bridge->pcie_conf.slotctl); + u16 slotsta = le16_to_cpu(bridge->pcie_conf.slotsta); + u32 val = 0; + /* + * When slot power limit was not specified in DT then + * ASPL_DISABLE bit is stored only in emulated config space. + * Otherwise reflect status of PCIE_SSPL_ENABLE bit in HW. + */ + if (!port->slot_power_limit_value) + val |= slotctl & PCI_EXP_SLTCTL_ASPL_DISABLE; + else if (!(mvebu_readl(port, PCIE_SSPL_OFF) & PCIE_SSPL_ENABLE)) + val |= PCI_EXP_SLTCTL_ASPL_DISABLE; + /* This callback is 32-bit and in high bits is slot status. */ + val |= slotsta << 16; + *value = val; + break; + } + + case PCI_EXP_RTSTA: + *value = mvebu_readl(port, PCIE_RC_RTSTA); + break; + + case PCI_EXP_DEVCAP2: + *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_DEVCAP2); + break; + + case PCI_EXP_DEVCTL2: + *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL2); + break; + + case PCI_EXP_LNKCTL2: + *value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL2); + break; + + default: + return PCI_BRIDGE_EMUL_NOT_HANDLED; + } + + return PCI_BRIDGE_EMUL_HANDLED; +} + +static pci_bridge_emul_read_status_t +mvebu_pci_bridge_emul_ext_conf_read(struct pci_bridge_emul *bridge, + int reg, u32 *value) +{ + struct mvebu_pcie_port *port = bridge->data; + + switch (reg) { + case 0: + case PCI_ERR_UNCOR_STATUS: + case PCI_ERR_UNCOR_MASK: + case PCI_ERR_UNCOR_SEVER: + case PCI_ERR_COR_STATUS: + case PCI_ERR_COR_MASK: + case PCI_ERR_CAP: + case PCI_ERR_HEADER_LOG+0: + case PCI_ERR_HEADER_LOG+4: + case PCI_ERR_HEADER_LOG+8: + case PCI_ERR_HEADER_LOG+12: + case PCI_ERR_ROOT_COMMAND: + case PCI_ERR_ROOT_STATUS: + case PCI_ERR_ROOT_ERR_SRC: + *value = mvebu_readl(port, PCIE_CAP_PCIERR_OFF + reg); + break; + + default: + return PCI_BRIDGE_EMUL_NOT_HANDLED; + } + + return PCI_BRIDGE_EMUL_HANDLED; +} + +static void +mvebu_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge, + int reg, u32 old, u32 new, u32 mask) +{ + struct mvebu_pcie_port *port = bridge->data; + struct pci_bridge_emul_conf *conf = &bridge->conf; + + switch (reg) { + case PCI_COMMAND: + mvebu_writel(port, new, PCIE_CMD_OFF); + break; + + case PCI_IO_BASE: + if ((mask & 0xffff) && mvebu_has_ioport(port) && + mvebu_pcie_handle_iobase_change(port)) { + /* On error disable IO range */ + conf->iobase &= ~0xf0; + conf->iolimit &= ~0xf0; + conf->iobase |= 0xf0; + conf->iobaseupper = cpu_to_le16(0x0000); + conf->iolimitupper = cpu_to_le16(0x0000); + } + break; + + case PCI_MEMORY_BASE: + if (mvebu_pcie_handle_membase_change(port)) { + /* On error disable mem range */ + conf->membase = cpu_to_le16(le16_to_cpu(conf->membase) & ~0xfff0); + conf->memlimit = cpu_to_le16(le16_to_cpu(conf->memlimit) & ~0xfff0); + conf->membase = cpu_to_le16(le16_to_cpu(conf->membase) | 0xfff0); + } + break; + + case PCI_IO_BASE_UPPER16: + if (mvebu_has_ioport(port) && + mvebu_pcie_handle_iobase_change(port)) { + /* On error disable IO range */ + conf->iobase &= ~0xf0; + conf->iolimit &= ~0xf0; + conf->iobase |= 0xf0; + conf->iobaseupper = cpu_to_le16(0x0000); + conf->iolimitupper = cpu_to_le16(0x0000); + } + break; + + case PCI_PRIMARY_BUS: + if (mask & 0xff00) + mvebu_pcie_set_local_bus_nr(port, conf->secondary_bus); + break; + + case PCI_INTERRUPT_LINE: + if (mask & (PCI_BRIDGE_CTL_BUS_RESET << 16)) { + u32 ctrl = mvebu_readl(port, PCIE_CTRL_OFF); + if (new & (PCI_BRIDGE_CTL_BUS_RESET << 16)) + ctrl |= PCIE_CTRL_MASTER_HOT_RESET; + else + ctrl &= ~PCIE_CTRL_MASTER_HOT_RESET; + mvebu_writel(port, ctrl, PCIE_CTRL_OFF); + } + break; + + default: + break; + } +} + +static void +mvebu_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge, + int reg, u32 old, u32 new, u32 mask) +{ + struct mvebu_pcie_port *port = bridge->data; + + switch (reg) { + case PCI_EXP_DEVCTL: + mvebu_writel(port, new, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL); + break; + + case PCI_EXP_LNKCTL: + /* + * PCIe requires that the Enable Clock Power Management bit + * is hard-wired to zero for downstream ports but HW allows + * to change it. + */ + new &= ~PCI_EXP_LNKCTL_CLKREQ_EN; + + mvebu_writel(port, new, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL); + break; + + case PCI_EXP_SLTCTL: + /* + * Allow to change PCIE_SSPL_ENABLE bit only when slot power + * limit was specified in DT and configured into HW. + */ + if ((mask & PCI_EXP_SLTCTL_ASPL_DISABLE) && + port->slot_power_limit_value) { + u32 sspl = mvebu_readl(port, PCIE_SSPL_OFF); + if (new & PCI_EXP_SLTCTL_ASPL_DISABLE) + sspl &= ~PCIE_SSPL_ENABLE; + else + sspl |= PCIE_SSPL_ENABLE; + mvebu_writel(port, sspl, PCIE_SSPL_OFF); + } + break; + + case PCI_EXP_RTSTA: + /* + * PME Status bit in Root Status Register (PCIE_RC_RTSTA) + * is read-only and can be cleared only by writing 0b to the + * Interrupt Cause RW0C register (PCIE_INT_CAUSE_OFF). So + * clear PME via Interrupt Cause. + */ + if (new & PCI_EXP_RTSTA_PME) + mvebu_writel(port, ~PCIE_INT_PM_PME, PCIE_INT_CAUSE_OFF); + break; + + case PCI_EXP_DEVCTL2: + mvebu_writel(port, new, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL2); + break; + + case PCI_EXP_LNKCTL2: + mvebu_writel(port, new, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL2); + break; + + default: + break; + } +} + +static void +mvebu_pci_bridge_emul_ext_conf_write(struct pci_bridge_emul *bridge, + int reg, u32 old, u32 new, u32 mask) +{ + struct mvebu_pcie_port *port = bridge->data; + + switch (reg) { + /* These are W1C registers, so clear other bits */ + case PCI_ERR_UNCOR_STATUS: + case PCI_ERR_COR_STATUS: + case PCI_ERR_ROOT_STATUS: + new &= mask; + fallthrough; + + case PCI_ERR_UNCOR_MASK: + case PCI_ERR_UNCOR_SEVER: + case PCI_ERR_COR_MASK: + case PCI_ERR_CAP: + case PCI_ERR_HEADER_LOG+0: + case PCI_ERR_HEADER_LOG+4: + case PCI_ERR_HEADER_LOG+8: + case PCI_ERR_HEADER_LOG+12: + case PCI_ERR_ROOT_COMMAND: + case PCI_ERR_ROOT_ERR_SRC: + mvebu_writel(port, new, PCIE_CAP_PCIERR_OFF + reg); + break; + + default: + break; + } +} + +static const struct pci_bridge_emul_ops mvebu_pci_bridge_emul_ops = { + .read_base = mvebu_pci_bridge_emul_base_conf_read, + .write_base = mvebu_pci_bridge_emul_base_conf_write, + .read_pcie = mvebu_pci_bridge_emul_pcie_conf_read, + .write_pcie = mvebu_pci_bridge_emul_pcie_conf_write, + .read_ext = mvebu_pci_bridge_emul_ext_conf_read, + .write_ext = mvebu_pci_bridge_emul_ext_conf_write, +}; + +/* + * Initialize the configuration space of the PCI-to-PCI bridge + * associated with the given PCIe interface. + */ +static int mvebu_pci_bridge_emul_init(struct mvebu_pcie_port *port) +{ + unsigned int bridge_flags = PCI_BRIDGE_EMUL_NO_PREFMEM_FORWARD; + struct pci_bridge_emul *bridge = &port->bridge; + u32 dev_id = mvebu_readl(port, PCIE_DEV_ID_OFF); + u32 dev_rev = mvebu_readl(port, PCIE_DEV_REV_OFF); + u32 ssdev_id = mvebu_readl(port, PCIE_SSDEV_ID_OFF); + u32 pcie_cap = mvebu_readl(port, PCIE_CAP_PCIEXP); + u8 pcie_cap_ver = ((pcie_cap >> 16) & PCI_EXP_FLAGS_VERS); + + bridge->conf.vendor = cpu_to_le16(dev_id & 0xffff); + bridge->conf.device = cpu_to_le16(dev_id >> 16); + bridge->conf.class_revision = cpu_to_le32(dev_rev & 0xff); + + if (mvebu_has_ioport(port)) { + /* We support 32 bits I/O addressing */ + bridge->conf.iobase = PCI_IO_RANGE_TYPE_32; + bridge->conf.iolimit = PCI_IO_RANGE_TYPE_32; + } else { + bridge_flags |= PCI_BRIDGE_EMUL_NO_IO_FORWARD; + } + + /* + * Older mvebu hardware provides PCIe Capability structure only in + * version 1. New hardware provides it in version 2. + * Enable slot support which is emulated. + */ + bridge->pcie_conf.cap = cpu_to_le16(pcie_cap_ver | PCI_EXP_FLAGS_SLOT); + + /* + * Set Presence Detect State bit permanently as there is no support for + * unplugging PCIe card from the slot. Assume that PCIe card is always + * connected in slot. + * + * Set physical slot number to port+1 as mvebu ports are indexed from + * zero and zero value is reserved for ports within the same silicon + * as Root Port which is not mvebu case. + * + * Also set correct slot power limit. + */ + bridge->pcie_conf.slotcap = cpu_to_le32( + FIELD_PREP(PCI_EXP_SLTCAP_SPLV, port->slot_power_limit_value) | + FIELD_PREP(PCI_EXP_SLTCAP_SPLS, port->slot_power_limit_scale) | + FIELD_PREP(PCI_EXP_SLTCAP_PSN, port->port+1)); + bridge->pcie_conf.slotsta = cpu_to_le16(PCI_EXP_SLTSTA_PDS); + + bridge->subsystem_vendor_id = ssdev_id & 0xffff; + bridge->subsystem_id = ssdev_id >> 16; + bridge->has_pcie = true; + bridge->pcie_start = PCIE_CAP_PCIEXP; + bridge->data = port; + bridge->ops = &mvebu_pci_bridge_emul_ops; + + return pci_bridge_emul_init(bridge, bridge_flags); +} + +static inline struct mvebu_pcie *sys_to_pcie(struct pci_sys_data *sys) +{ + return sys->private_data; +} + +static struct mvebu_pcie_port *mvebu_pcie_find_port(struct mvebu_pcie *pcie, + struct pci_bus *bus, + int devfn) +{ + int i; + + for (i = 0; i < pcie->nports; i++) { + struct mvebu_pcie_port *port = &pcie->ports[i]; + + if (!port->base) + continue; + + if (bus->number == 0 && port->devfn == devfn) + return port; + if (bus->number != 0 && + bus->number >= port->bridge.conf.secondary_bus && + bus->number <= port->bridge.conf.subordinate_bus) + return port; + } + + return NULL; +} + +/* PCI configuration space write function */ +static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn, + int where, int size, u32 val) +{ + struct mvebu_pcie *pcie = bus->sysdata; + struct mvebu_pcie_port *port; + + port = mvebu_pcie_find_port(pcie, bus, devfn); + if (!port) + return PCIBIOS_DEVICE_NOT_FOUND; + + return pci_bridge_emul_conf_write(&port->bridge, where, size, val); +} + +/* PCI configuration space read function */ +static int mvebu_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, + int size, u32 *val) +{ + struct mvebu_pcie *pcie = bus->sysdata; + struct mvebu_pcie_port *port; + + port = mvebu_pcie_find_port(pcie, bus, devfn); + if (!port) + return PCIBIOS_DEVICE_NOT_FOUND; + + return pci_bridge_emul_conf_read(&port->bridge, where, size, val); +} + +static struct pci_ops mvebu_pcie_ops = { + .read = mvebu_pcie_rd_conf, + .write = mvebu_pcie_wr_conf, +}; + +static void mvebu_pcie_intx_irq_mask(struct irq_data *d) +{ + struct mvebu_pcie_port *port = d->domain->host_data; + irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; + u32 unmask; + + raw_spin_lock_irqsave(&port->irq_lock, flags); + unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF); + unmask &= ~PCIE_INT_INTX(hwirq); + mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF); + raw_spin_unlock_irqrestore(&port->irq_lock, flags); +} + +static void mvebu_pcie_intx_irq_unmask(struct irq_data *d) +{ + struct mvebu_pcie_port *port = d->domain->host_data; + irq_hw_number_t hwirq = irqd_to_hwirq(d); + unsigned long flags; + u32 unmask; + + raw_spin_lock_irqsave(&port->irq_lock, flags); + unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF); + unmask |= PCIE_INT_INTX(hwirq); + mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF); + raw_spin_unlock_irqrestore(&port->irq_lock, flags); +} + +static struct irq_chip intx_irq_chip = { + .name = "mvebu-INTx", + .irq_mask = mvebu_pcie_intx_irq_mask, + .irq_unmask = mvebu_pcie_intx_irq_unmask, +}; + +static int mvebu_pcie_intx_irq_map(struct irq_domain *h, + unsigned int virq, irq_hw_number_t hwirq) +{ + struct mvebu_pcie_port *port = h->host_data; + + irq_set_status_flags(virq, IRQ_LEVEL); + irq_set_chip_and_handler(virq, &intx_irq_chip, handle_level_irq); + irq_set_chip_data(virq, port); + + return 0; +} + +static const struct irq_domain_ops mvebu_pcie_intx_irq_domain_ops = { + .map = mvebu_pcie_intx_irq_map, + .xlate = irq_domain_xlate_onecell, +}; + +static int mvebu_pcie_init_irq_domain(struct mvebu_pcie_port *port) +{ + struct device *dev = &port->pcie->pdev->dev; + struct device_node *pcie_intc_node; + + raw_spin_lock_init(&port->irq_lock); + + pcie_intc_node = of_get_next_child(port->dn, NULL); + if (!pcie_intc_node) { + dev_err(dev, "No PCIe Intc node found for %s\n", port->name); + return -ENODEV; + } + + port->intx_irq_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, + &mvebu_pcie_intx_irq_domain_ops, + port); + of_node_put(pcie_intc_node); + if (!port->intx_irq_domain) { + dev_err(dev, "Failed to get INTx IRQ domain for %s\n", port->name); + return -ENOMEM; + } + + return 0; +} + +static void mvebu_pcie_irq_handler(struct irq_desc *desc) +{ + struct mvebu_pcie_port *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + struct device *dev = &port->pcie->pdev->dev; + u32 cause, unmask, status; + int i; + + chained_irq_enter(chip, desc); + + cause = mvebu_readl(port, PCIE_INT_CAUSE_OFF); + unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF); + status = cause & unmask; + + /* Process legacy INTx interrupts */ + for (i = 0; i < PCI_NUM_INTX; i++) { + if (!(status & PCIE_INT_INTX(i))) + continue; + + if (generic_handle_domain_irq(port->intx_irq_domain, i) == -EINVAL) + dev_err_ratelimited(dev, "unexpected INT%c IRQ\n", (char)i+'A'); + } + + chained_irq_exit(chip, desc); +} + +static int mvebu_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +{ + /* Interrupt support on mvebu emulated bridges is not implemented yet */ + if (dev->bus->number == 0) + return 0; /* Proper return code 0 == NO_IRQ */ + + return of_irq_parse_and_map_pci(dev, slot, pin); +} + +static resource_size_t mvebu_pcie_align_resource(struct pci_dev *dev, + const struct resource *res, + resource_size_t start, + resource_size_t size, + resource_size_t align) +{ + if (dev->bus->number != 0) + return start; + + /* + * On the PCI-to-PCI bridge side, the I/O windows must have at + * least a 64 KB size and the memory windows must have at + * least a 1 MB size. Moreover, MBus windows need to have a + * base address aligned on their size, and their size must be + * a power of two. This means that if the BAR doesn't have a + * power of two size, several MBus windows will actually be + * created. We need to ensure that the biggest MBus window + * (which will be the first one) is aligned on its size, which + * explains the rounddown_pow_of_two() being done here. + */ + if (res->flags & IORESOURCE_IO) + return round_up(start, max_t(resource_size_t, SZ_64K, + rounddown_pow_of_two(size))); + else if (res->flags & IORESOURCE_MEM) + return round_up(start, max_t(resource_size_t, SZ_1M, + rounddown_pow_of_two(size))); + else + return start; +} + +static void __iomem *mvebu_pcie_map_registers(struct platform_device *pdev, + struct device_node *np, + struct mvebu_pcie_port *port) +{ + int ret = 0; + + ret = of_address_to_resource(np, 0, &port->regs); + if (ret) + return (void __iomem *)ERR_PTR(ret); + + return devm_ioremap_resource(&pdev->dev, &port->regs); +} + +#define DT_FLAGS_TO_TYPE(flags) (((flags) >> 24) & 0x03) +#define DT_TYPE_IO 0x1 +#define DT_TYPE_MEM32 0x2 +#define DT_CPUADDR_TO_TARGET(cpuaddr) (((cpuaddr) >> 56) & 0xFF) +#define DT_CPUADDR_TO_ATTR(cpuaddr) (((cpuaddr) >> 48) & 0xFF) + +static int mvebu_get_tgt_attr(struct device_node *np, int devfn, + unsigned long type, + unsigned int *tgt, + unsigned int *attr) +{ + const int na = 3, ns = 2; + const __be32 *range; + int rlen, nranges, rangesz, pna, i; + + *tgt = -1; + *attr = -1; + + range = of_get_property(np, "ranges", &rlen); + if (!range) + return -EINVAL; + + pna = of_n_addr_cells(np); + rangesz = pna + na + ns; + nranges = rlen / sizeof(__be32) / rangesz; + + for (i = 0; i < nranges; i++, range += rangesz) { + u32 flags = of_read_number(range, 1); + u32 slot = of_read_number(range + 1, 1); + u64 cpuaddr = of_read_number(range + na, pna); + unsigned long rtype; + + if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_IO) + rtype = IORESOURCE_IO; + else if (DT_FLAGS_TO_TYPE(flags) == DT_TYPE_MEM32) + rtype = IORESOURCE_MEM; + else + continue; + + if (slot == PCI_SLOT(devfn) && type == rtype) { + *tgt = DT_CPUADDR_TO_TARGET(cpuaddr); + *attr = DT_CPUADDR_TO_ATTR(cpuaddr); + return 0; + } + } + + return -ENOENT; +} + +static int mvebu_pcie_suspend(struct device *dev) +{ + struct mvebu_pcie *pcie; + int i; + + pcie = dev_get_drvdata(dev); + for (i = 0; i < pcie->nports; i++) { + struct mvebu_pcie_port *port = pcie->ports + i; + if (!port->base) + continue; + port->saved_pcie_stat = mvebu_readl(port, PCIE_STAT_OFF); + } + + return 0; +} + +static int mvebu_pcie_resume(struct device *dev) +{ + struct mvebu_pcie *pcie; + int i; + + pcie = dev_get_drvdata(dev); + for (i = 0; i < pcie->nports; i++) { + struct mvebu_pcie_port *port = pcie->ports + i; + if (!port->base) + continue; + mvebu_writel(port, port->saved_pcie_stat, PCIE_STAT_OFF); + mvebu_pcie_setup_hw(port); + } + + return 0; +} + +static void mvebu_pcie_port_clk_put(void *data) +{ + struct mvebu_pcie_port *port = data; + + clk_put(port->clk); +} + +static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie, + struct mvebu_pcie_port *port, struct device_node *child) +{ + struct device *dev = &pcie->pdev->dev; + enum of_gpio_flags flags; + u32 slot_power_limit; + int reset_gpio, ret; + u32 num_lanes; + + port->pcie = pcie; + + if (of_property_read_u32(child, "marvell,pcie-port", &port->port)) { + dev_warn(dev, "ignoring %pOF, missing pcie-port property\n", + child); + goto skip; + } + + if (of_property_read_u32(child, "marvell,pcie-lane", &port->lane)) + port->lane = 0; + + if (!of_property_read_u32(child, "num-lanes", &num_lanes) && num_lanes == 4) + port->is_x4 = true; + + port->name = devm_kasprintf(dev, GFP_KERNEL, "pcie%d.%d", port->port, + port->lane); + if (!port->name) { + ret = -ENOMEM; + goto err; + } + + port->devfn = of_pci_get_devfn(child); + if (port->devfn < 0) + goto skip; + if (PCI_FUNC(port->devfn) != 0) { + dev_err(dev, "%s: invalid function number, must be zero\n", + port->name); + goto skip; + } + + ret = mvebu_get_tgt_attr(dev->of_node, port->devfn, IORESOURCE_MEM, + &port->mem_target, &port->mem_attr); + if (ret < 0) { + dev_err(dev, "%s: cannot get tgt/attr for mem window\n", + port->name); + goto skip; + } + + if (resource_size(&pcie->io) != 0) { + mvebu_get_tgt_attr(dev->of_node, port->devfn, IORESOURCE_IO, + &port->io_target, &port->io_attr); + } else { + port->io_target = -1; + port->io_attr = -1; + } + + /* + * Old DT bindings do not contain "intx" interrupt + * so do not fail probing driver when interrupt does not exist. + */ + port->intx_irq = of_irq_get_byname(child, "intx"); + if (port->intx_irq == -EPROBE_DEFER) { + ret = port->intx_irq; + goto err; + } + if (port->intx_irq <= 0) { + dev_warn(dev, "%s: legacy INTx interrupts cannot be masked individually, " + "%pOF does not contain intx interrupt\n", + port->name, child); + } + + reset_gpio = of_get_named_gpio_flags(child, "reset-gpios", 0, &flags); + if (reset_gpio == -EPROBE_DEFER) { + ret = reset_gpio; + goto err; + } + + if (gpio_is_valid(reset_gpio)) { + unsigned long gpio_flags; + + port->reset_name = devm_kasprintf(dev, GFP_KERNEL, "%s-reset", + port->name); + if (!port->reset_name) { + ret = -ENOMEM; + goto err; + } + + if (flags & OF_GPIO_ACTIVE_LOW) { + dev_info(dev, "%pOF: reset gpio is active low\n", + child); + gpio_flags = GPIOF_ACTIVE_LOW | + GPIOF_OUT_INIT_LOW; + } else { + gpio_flags = GPIOF_OUT_INIT_HIGH; + } + + ret = devm_gpio_request_one(dev, reset_gpio, gpio_flags, + port->reset_name); + if (ret) { + if (ret == -EPROBE_DEFER) + goto err; + goto skip; + } + + port->reset_gpio = gpio_to_desc(reset_gpio); + } + + slot_power_limit = of_pci_get_slot_power_limit(child, + &port->slot_power_limit_value, + &port->slot_power_limit_scale); + if (slot_power_limit) + dev_info(dev, "%s: Slot power limit %u.%uW\n", + port->name, + slot_power_limit / 1000, + (slot_power_limit / 100) % 10); + + port->clk = of_clk_get_by_name(child, NULL); + if (IS_ERR(port->clk)) { + dev_err(dev, "%s: cannot get clock\n", port->name); + goto skip; + } + + ret = devm_add_action(dev, mvebu_pcie_port_clk_put, port); + if (ret < 0) { + clk_put(port->clk); + goto err; + } + + return 1; + +skip: + ret = 0; + + /* In the case of skipping, we need to free these */ + devm_kfree(dev, port->reset_name); + port->reset_name = NULL; + devm_kfree(dev, port->name); + port->name = NULL; + +err: + return ret; +} + +/* + * Power up a PCIe port. PCIe requires the refclk to be stable for 100µs + * prior to releasing PERST. See table 2-4 in section 2.6.2 AC Specifications + * of the PCI Express Card Electromechanical Specification, 1.1. + */ +static int mvebu_pcie_powerup(struct mvebu_pcie_port *port) +{ + int ret; + + ret = clk_prepare_enable(port->clk); + if (ret < 0) + return ret; + + if (port->reset_gpio) { + u32 reset_udelay = PCI_PM_D3COLD_WAIT * 1000; + + of_property_read_u32(port->dn, "reset-delay-us", + &reset_udelay); + + udelay(100); + + gpiod_set_value_cansleep(port->reset_gpio, 0); + msleep(reset_udelay / 1000); + } + + return 0; +} + +/* + * Power down a PCIe port. Strictly, PCIe requires us to place the card + * in D3hot state before asserting PERST#. + */ +static void mvebu_pcie_powerdown(struct mvebu_pcie_port *port) +{ + gpiod_set_value_cansleep(port->reset_gpio, 1); + + clk_disable_unprepare(port->clk); +} + +/* + * devm_of_pci_get_host_bridge_resources() only sets up translateable resources, + * so we need extra resource setup parsing our special DT properties encoding + * the MEM and IO apertures. + */ +static int mvebu_pcie_parse_request_resources(struct mvebu_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + int ret; + + /* Get the PCIe memory aperture */ + mvebu_mbus_get_pcie_mem_aperture(&pcie->mem); + if (resource_size(&pcie->mem) == 0) { + dev_err(dev, "invalid memory aperture size\n"); + return -EINVAL; + } + + pcie->mem.name = "PCI MEM"; + pci_add_resource(&bridge->windows, &pcie->mem); + ret = devm_request_resource(dev, &iomem_resource, &pcie->mem); + if (ret) + return ret; + + /* Get the PCIe IO aperture */ + mvebu_mbus_get_pcie_io_aperture(&pcie->io); + + if (resource_size(&pcie->io) != 0) { + pcie->realio.flags = pcie->io.flags; + pcie->realio.start = PCIBIOS_MIN_IO; + pcie->realio.end = min_t(resource_size_t, + IO_SPACE_LIMIT - SZ_64K, + resource_size(&pcie->io) - 1); + pcie->realio.name = "PCI I/O"; + + ret = devm_pci_remap_iospace(dev, &pcie->realio, pcie->io.start); + if (ret) + return ret; + + pci_add_resource(&bridge->windows, &pcie->realio); + ret = devm_request_resource(dev, &ioport_resource, &pcie->realio); + if (ret) + return ret; + } + + return 0; +} + +static int mvebu_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mvebu_pcie *pcie; + struct pci_host_bridge *bridge; + struct device_node *np = dev->of_node; + struct device_node *child; + int num, i, ret; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct mvebu_pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + pcie->pdev = pdev; + platform_set_drvdata(pdev, pcie); + + ret = mvebu_pcie_parse_request_resources(pcie); + if (ret) + return ret; + + num = of_get_available_child_count(np); + + pcie->ports = devm_kcalloc(dev, num, sizeof(*pcie->ports), GFP_KERNEL); + if (!pcie->ports) + return -ENOMEM; + + i = 0; + for_each_available_child_of_node(np, child) { + struct mvebu_pcie_port *port = &pcie->ports[i]; + + ret = mvebu_pcie_parse_port(pcie, port, child); + if (ret < 0) { + of_node_put(child); + return ret; + } else if (ret == 0) { + continue; + } + + port->dn = child; + i++; + } + pcie->nports = i; + + for (i = 0; i < pcie->nports; i++) { + struct mvebu_pcie_port *port = &pcie->ports[i]; + int irq = port->intx_irq; + + child = port->dn; + if (!child) + continue; + + ret = mvebu_pcie_powerup(port); + if (ret < 0) + continue; + + port->base = mvebu_pcie_map_registers(pdev, child, port); + if (IS_ERR(port->base)) { + dev_err(dev, "%s: cannot map registers\n", port->name); + port->base = NULL; + mvebu_pcie_powerdown(port); + continue; + } + + ret = mvebu_pci_bridge_emul_init(port); + if (ret < 0) { + dev_err(dev, "%s: cannot init emulated bridge\n", + port->name); + devm_iounmap(dev, port->base); + port->base = NULL; + mvebu_pcie_powerdown(port); + continue; + } + + if (irq > 0) { + ret = mvebu_pcie_init_irq_domain(port); + if (ret) { + dev_err(dev, "%s: cannot init irq domain\n", + port->name); + pci_bridge_emul_cleanup(&port->bridge); + devm_iounmap(dev, port->base); + port->base = NULL; + mvebu_pcie_powerdown(port); + continue; + } + irq_set_chained_handler_and_data(irq, + mvebu_pcie_irq_handler, + port); + } + + /* + * PCIe topology exported by mvebu hw is quite complicated. In + * reality has something like N fully independent host bridges + * where each host bridge has one PCIe Root Port (which acts as + * PCI Bridge device). Each host bridge has its own independent + * internal registers, independent access to PCI config space, + * independent interrupt lines, independent window and memory + * access configuration. But additionally there is some kind of + * peer-to-peer support between PCIe devices behind different + * host bridges limited just to forwarding of memory and I/O + * transactions (forwarding of error messages and config cycles + * is not supported). So we could say there are N independent + * PCIe Root Complexes. + * + * For this kind of setup DT should have been structured into + * N independent PCIe controllers / host bridges. But instead + * structure in past was defined to put PCIe Root Ports of all + * host bridges into one bus zero, like in classic multi-port + * Root Complex setup with just one host bridge. + * + * This means that pci-mvebu.c driver provides "virtual" bus 0 + * on which registers all PCIe Root Ports (PCI Bridge devices) + * specified in DT by their BDF addresses and virtually routes + * PCI config access of each PCI bridge device to specific PCIe + * host bridge. + * + * Normally PCI Bridge should choose between Type 0 and Type 1 + * config requests based on primary and secondary bus numbers + * configured on the bridge itself. But because mvebu PCI Bridge + * does not have registers for primary and secondary bus numbers + * in its config space, it determinates type of config requests + * via its own custom way. + * + * There are two options how mvebu determinate type of config + * request. + * + * 1. If Secondary Bus Number Enable bit is not set or is not + * available (applies for pre-XP PCIe controllers) then Type 0 + * is used if target bus number equals Local Bus Number (bits + * [15:8] in register 0x1a04) and target device number differs + * from Local Device Number (bits [20:16] in register 0x1a04). + * Type 1 is used if target bus number differs from Local Bus + * Number. And when target bus number equals Local Bus Number + * and target device equals Local Device Number then request is + * routed to Local PCI Bridge (PCIe Root Port). + * + * 2. If Secondary Bus Number Enable bit is set (bit 7 in + * register 0x1a2c) then mvebu hw determinate type of config + * request like compliant PCI Bridge based on primary bus number + * which is configured via Local Bus Number (bits [15:8] in + * register 0x1a04) and secondary bus number which is configured + * via Secondary Bus Number (bits [7:0] in register 0x1a2c). + * Local PCI Bridge (PCIe Root Port) is available on primary bus + * as device with Local Device Number (bits [20:16] in register + * 0x1a04). + * + * Secondary Bus Number Enable bit is disabled by default and + * option 2. is not available on pre-XP PCIe controllers. Hence + * this driver always use option 1. + * + * Basically it means that primary and secondary buses shares + * one virtual number configured via Local Bus Number bits and + * Local Device Number bits determinates if accessing primary + * or secondary bus. Set Local Device Number to 1 and redirect + * all writes of PCI Bridge Secondary Bus Number register to + * Local Bus Number (bits [15:8] in register 0x1a04). + * + * So when accessing devices on buses behind secondary bus + * number it would work correctly. And also when accessing + * device 0 at secondary bus number via config space would be + * correctly routed to secondary bus. Due to issues described + * in mvebu_pcie_setup_hw(), PCI Bridges at primary bus (zero) + * are not accessed directly via PCI config space but rarher + * indirectly via kernel emulated PCI bridge driver. + */ + mvebu_pcie_setup_hw(port); + mvebu_pcie_set_local_dev_nr(port, 1); + mvebu_pcie_set_local_bus_nr(port, 0); + } + + bridge->sysdata = pcie; + bridge->ops = &mvebu_pcie_ops; + bridge->child_ops = &mvebu_pcie_child_ops; + bridge->align_resource = mvebu_pcie_align_resource; + bridge->map_irq = mvebu_pcie_map_irq; + + return pci_host_probe(bridge); +} + +static int mvebu_pcie_remove(struct platform_device *pdev) +{ + struct mvebu_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + u32 cmd, sspl; + int i; + + /* Remove PCI bus with all devices. */ + pci_lock_rescan_remove(); + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); + pci_unlock_rescan_remove(); + + for (i = 0; i < pcie->nports; i++) { + struct mvebu_pcie_port *port = &pcie->ports[i]; + int irq = port->intx_irq; + + if (!port->base) + continue; + + /* Disable Root Bridge I/O space, memory space and bus mastering. */ + cmd = mvebu_readl(port, PCIE_CMD_OFF); + cmd &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); + mvebu_writel(port, cmd, PCIE_CMD_OFF); + + /* Mask all interrupt sources. */ + mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_UNMASK_OFF); + + /* Clear all interrupt causes. */ + mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_CAUSE_OFF); + + if (irq > 0) + irq_set_chained_handler_and_data(irq, NULL, NULL); + + /* Remove IRQ domains. */ + if (port->intx_irq_domain) + irq_domain_remove(port->intx_irq_domain); + + /* Free config space for emulated root bridge. */ + pci_bridge_emul_cleanup(&port->bridge); + + /* Disable sending Set_Slot_Power_Limit PCIe Message. */ + sspl = mvebu_readl(port, PCIE_SSPL_OFF); + sspl &= ~(PCIE_SSPL_VALUE_MASK | PCIE_SSPL_SCALE_MASK | PCIE_SSPL_ENABLE); + mvebu_writel(port, sspl, PCIE_SSPL_OFF); + + /* Disable and clear BARs and windows. */ + mvebu_pcie_disable_wins(port); + + /* Delete PCIe IO and MEM windows. */ + if (port->iowin.size) + mvebu_pcie_del_windows(port, port->iowin.base, port->iowin.size); + if (port->memwin.size) + mvebu_pcie_del_windows(port, port->memwin.base, port->memwin.size); + + /* Power down card and disable clocks. Must be the last step. */ + mvebu_pcie_powerdown(port); + } + + return 0; +} + +static const struct of_device_id mvebu_pcie_of_match_table[] = { + { .compatible = "marvell,armada-xp-pcie", }, + { .compatible = "marvell,armada-370-pcie", }, + { .compatible = "marvell,dove-pcie", }, + { .compatible = "marvell,kirkwood-pcie", }, + {}, +}; + +static const struct dev_pm_ops mvebu_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(mvebu_pcie_suspend, mvebu_pcie_resume) +}; + +static struct platform_driver mvebu_pcie_driver = { + .driver = { + .name = "mvebu-pcie", + .of_match_table = mvebu_pcie_of_match_table, + .pm = &mvebu_pcie_pm_ops, + }, + .probe = mvebu_pcie_probe, + .remove = mvebu_pcie_remove, +}; +module_platform_driver(mvebu_pcie_driver); + +MODULE_AUTHOR("Thomas Petazzoni <thomas.petazzoni@bootlin.com>"); +MODULE_AUTHOR("Pali Rohár <pali@kernel.org>"); +MODULE_DESCRIPTION("Marvell EBU PCIe controller"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-rcar-gen2.c b/drivers/pci/controller/pci-rcar-gen2.c new file mode 100644 index 000000000..839695791 --- /dev/null +++ b/drivers/pci/controller/pci-rcar-gen2.c @@ -0,0 +1,343 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * pci-rcar-gen2: internal PCI bus support + * + * Copyright (C) 2013 Renesas Solutions Corp. + * Copyright (C) 2013 Cogent Embedded, Inc. + * + * Author: Valentine Barshak <valentine.barshak@cogentembedded.com> + */ + +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/sizes.h> +#include <linux/slab.h> + +#include "../pci.h" + +/* AHB-PCI Bridge PCI communication registers */ +#define RCAR_AHBPCI_PCICOM_OFFSET 0x800 + +#define RCAR_PCIAHB_WIN1_CTR_REG (RCAR_AHBPCI_PCICOM_OFFSET + 0x00) +#define RCAR_PCIAHB_WIN2_CTR_REG (RCAR_AHBPCI_PCICOM_OFFSET + 0x04) +#define RCAR_PCIAHB_PREFETCH0 0x0 +#define RCAR_PCIAHB_PREFETCH4 0x1 +#define RCAR_PCIAHB_PREFETCH8 0x2 +#define RCAR_PCIAHB_PREFETCH16 0x3 + +#define RCAR_AHBPCI_WIN1_CTR_REG (RCAR_AHBPCI_PCICOM_OFFSET + 0x10) +#define RCAR_AHBPCI_WIN2_CTR_REG (RCAR_AHBPCI_PCICOM_OFFSET + 0x14) +#define RCAR_AHBPCI_WIN_CTR_MEM (3 << 1) +#define RCAR_AHBPCI_WIN_CTR_CFG (5 << 1) +#define RCAR_AHBPCI_WIN1_HOST (1 << 30) +#define RCAR_AHBPCI_WIN1_DEVICE (1 << 31) + +#define RCAR_PCI_INT_ENABLE_REG (RCAR_AHBPCI_PCICOM_OFFSET + 0x20) +#define RCAR_PCI_INT_STATUS_REG (RCAR_AHBPCI_PCICOM_OFFSET + 0x24) +#define RCAR_PCI_INT_SIGTABORT (1 << 0) +#define RCAR_PCI_INT_SIGRETABORT (1 << 1) +#define RCAR_PCI_INT_REMABORT (1 << 2) +#define RCAR_PCI_INT_PERR (1 << 3) +#define RCAR_PCI_INT_SIGSERR (1 << 4) +#define RCAR_PCI_INT_RESERR (1 << 5) +#define RCAR_PCI_INT_WIN1ERR (1 << 12) +#define RCAR_PCI_INT_WIN2ERR (1 << 13) +#define RCAR_PCI_INT_A (1 << 16) +#define RCAR_PCI_INT_B (1 << 17) +#define RCAR_PCI_INT_PME (1 << 19) +#define RCAR_PCI_INT_ALLERRORS (RCAR_PCI_INT_SIGTABORT | \ + RCAR_PCI_INT_SIGRETABORT | \ + RCAR_PCI_INT_REMABORT | \ + RCAR_PCI_INT_PERR | \ + RCAR_PCI_INT_SIGSERR | \ + RCAR_PCI_INT_RESERR | \ + RCAR_PCI_INT_WIN1ERR | \ + RCAR_PCI_INT_WIN2ERR) + +#define RCAR_AHB_BUS_CTR_REG (RCAR_AHBPCI_PCICOM_OFFSET + 0x30) +#define RCAR_AHB_BUS_MMODE_HTRANS (1 << 0) +#define RCAR_AHB_BUS_MMODE_BYTE_BURST (1 << 1) +#define RCAR_AHB_BUS_MMODE_WR_INCR (1 << 2) +#define RCAR_AHB_BUS_MMODE_HBUS_REQ (1 << 7) +#define RCAR_AHB_BUS_SMODE_READYCTR (1 << 17) +#define RCAR_AHB_BUS_MODE (RCAR_AHB_BUS_MMODE_HTRANS | \ + RCAR_AHB_BUS_MMODE_BYTE_BURST | \ + RCAR_AHB_BUS_MMODE_WR_INCR | \ + RCAR_AHB_BUS_MMODE_HBUS_REQ | \ + RCAR_AHB_BUS_SMODE_READYCTR) + +#define RCAR_USBCTR_REG (RCAR_AHBPCI_PCICOM_OFFSET + 0x34) +#define RCAR_USBCTR_USBH_RST (1 << 0) +#define RCAR_USBCTR_PCICLK_MASK (1 << 1) +#define RCAR_USBCTR_PLL_RST (1 << 2) +#define RCAR_USBCTR_DIRPD (1 << 8) +#define RCAR_USBCTR_PCIAHB_WIN2_EN (1 << 9) +#define RCAR_USBCTR_PCIAHB_WIN1_256M (0 << 10) +#define RCAR_USBCTR_PCIAHB_WIN1_512M (1 << 10) +#define RCAR_USBCTR_PCIAHB_WIN1_1G (2 << 10) +#define RCAR_USBCTR_PCIAHB_WIN1_2G (3 << 10) +#define RCAR_USBCTR_PCIAHB_WIN1_MASK (3 << 10) + +#define RCAR_PCI_ARBITER_CTR_REG (RCAR_AHBPCI_PCICOM_OFFSET + 0x40) +#define RCAR_PCI_ARBITER_PCIREQ0 (1 << 0) +#define RCAR_PCI_ARBITER_PCIREQ1 (1 << 1) +#define RCAR_PCI_ARBITER_PCIBP_MODE (1 << 12) + +#define RCAR_PCI_UNIT_REV_REG (RCAR_AHBPCI_PCICOM_OFFSET + 0x48) + +struct rcar_pci { + struct device *dev; + void __iomem *reg; + struct resource mem_res; + struct resource *cfg_res; + int irq; +}; + +/* PCI configuration space operations */ +static void __iomem *rcar_pci_cfg_base(struct pci_bus *bus, unsigned int devfn, + int where) +{ + struct rcar_pci *priv = bus->sysdata; + int slot, val; + + if (!pci_is_root_bus(bus) || PCI_FUNC(devfn)) + return NULL; + + /* Only one EHCI/OHCI device built-in */ + slot = PCI_SLOT(devfn); + if (slot > 2) + return NULL; + + /* bridge logic only has registers to 0x40 */ + if (slot == 0x0 && where >= 0x40) + return NULL; + + val = slot ? RCAR_AHBPCI_WIN1_DEVICE | RCAR_AHBPCI_WIN_CTR_CFG : + RCAR_AHBPCI_WIN1_HOST | RCAR_AHBPCI_WIN_CTR_CFG; + + iowrite32(val, priv->reg + RCAR_AHBPCI_WIN1_CTR_REG); + return priv->reg + (slot >> 1) * 0x100 + where; +} + +#ifdef CONFIG_PCI_DEBUG +/* if debug enabled, then attach an error handler irq to the bridge */ + +static irqreturn_t rcar_pci_err_irq(int irq, void *pw) +{ + struct rcar_pci *priv = pw; + struct device *dev = priv->dev; + u32 status = ioread32(priv->reg + RCAR_PCI_INT_STATUS_REG); + + if (status & RCAR_PCI_INT_ALLERRORS) { + dev_err(dev, "error irq: status %08x\n", status); + + /* clear the error(s) */ + iowrite32(status & RCAR_PCI_INT_ALLERRORS, + priv->reg + RCAR_PCI_INT_STATUS_REG); + return IRQ_HANDLED; + } + + return IRQ_NONE; +} + +static void rcar_pci_setup_errirq(struct rcar_pci *priv) +{ + struct device *dev = priv->dev; + int ret; + u32 val; + + ret = devm_request_irq(dev, priv->irq, rcar_pci_err_irq, + IRQF_SHARED, "error irq", priv); + if (ret) { + dev_err(dev, "cannot claim IRQ for error handling\n"); + return; + } + + val = ioread32(priv->reg + RCAR_PCI_INT_ENABLE_REG); + val |= RCAR_PCI_INT_ALLERRORS; + iowrite32(val, priv->reg + RCAR_PCI_INT_ENABLE_REG); +} +#else +static inline void rcar_pci_setup_errirq(struct rcar_pci *priv) { } +#endif + +/* PCI host controller setup */ +static void rcar_pci_setup(struct rcar_pci *priv) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(priv); + struct device *dev = priv->dev; + void __iomem *reg = priv->reg; + struct resource_entry *entry; + unsigned long window_size; + unsigned long window_addr; + unsigned long window_pci; + u32 val; + + entry = resource_list_first_type(&bridge->dma_ranges, IORESOURCE_MEM); + if (!entry) { + window_addr = 0x40000000; + window_pci = 0x40000000; + window_size = SZ_1G; + } else { + window_addr = entry->res->start; + window_pci = entry->res->start - entry->offset; + window_size = resource_size(entry->res); + } + + pm_runtime_enable(dev); + pm_runtime_get_sync(dev); + + val = ioread32(reg + RCAR_PCI_UNIT_REV_REG); + dev_info(dev, "PCI: revision %x\n", val); + + /* Disable Direct Power Down State and assert reset */ + val = ioread32(reg + RCAR_USBCTR_REG) & ~RCAR_USBCTR_DIRPD; + val |= RCAR_USBCTR_USBH_RST | RCAR_USBCTR_PLL_RST; + iowrite32(val, reg + RCAR_USBCTR_REG); + udelay(4); + + /* De-assert reset and reset PCIAHB window1 size */ + val &= ~(RCAR_USBCTR_PCIAHB_WIN1_MASK | RCAR_USBCTR_PCICLK_MASK | + RCAR_USBCTR_USBH_RST | RCAR_USBCTR_PLL_RST); + + /* Setup PCIAHB window1 size */ + switch (window_size) { + case SZ_2G: + val |= RCAR_USBCTR_PCIAHB_WIN1_2G; + break; + case SZ_1G: + val |= RCAR_USBCTR_PCIAHB_WIN1_1G; + break; + case SZ_512M: + val |= RCAR_USBCTR_PCIAHB_WIN1_512M; + break; + default: + pr_warn("unknown window size %ld - defaulting to 256M\n", + window_size); + window_size = SZ_256M; + fallthrough; + case SZ_256M: + val |= RCAR_USBCTR_PCIAHB_WIN1_256M; + break; + } + iowrite32(val, reg + RCAR_USBCTR_REG); + + /* Configure AHB master and slave modes */ + iowrite32(RCAR_AHB_BUS_MODE, reg + RCAR_AHB_BUS_CTR_REG); + + /* Configure PCI arbiter */ + val = ioread32(reg + RCAR_PCI_ARBITER_CTR_REG); + val |= RCAR_PCI_ARBITER_PCIREQ0 | RCAR_PCI_ARBITER_PCIREQ1 | + RCAR_PCI_ARBITER_PCIBP_MODE; + iowrite32(val, reg + RCAR_PCI_ARBITER_CTR_REG); + + /* PCI-AHB mapping */ + iowrite32(window_addr | RCAR_PCIAHB_PREFETCH16, + reg + RCAR_PCIAHB_WIN1_CTR_REG); + + /* AHB-PCI mapping: OHCI/EHCI registers */ + val = priv->mem_res.start | RCAR_AHBPCI_WIN_CTR_MEM; + iowrite32(val, reg + RCAR_AHBPCI_WIN2_CTR_REG); + + /* Enable AHB-PCI bridge PCI configuration access */ + iowrite32(RCAR_AHBPCI_WIN1_HOST | RCAR_AHBPCI_WIN_CTR_CFG, + reg + RCAR_AHBPCI_WIN1_CTR_REG); + /* Set PCI-AHB Window1 address */ + iowrite32(window_pci | PCI_BASE_ADDRESS_MEM_PREFETCH, + reg + PCI_BASE_ADDRESS_1); + /* Set AHB-PCI bridge PCI communication area address */ + val = priv->cfg_res->start + RCAR_AHBPCI_PCICOM_OFFSET; + iowrite32(val, reg + PCI_BASE_ADDRESS_0); + + val = ioread32(reg + PCI_COMMAND); + val |= PCI_COMMAND_SERR | PCI_COMMAND_PARITY | + PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER; + iowrite32(val, reg + PCI_COMMAND); + + /* Enable PCI interrupts */ + iowrite32(RCAR_PCI_INT_A | RCAR_PCI_INT_B | RCAR_PCI_INT_PME, + reg + RCAR_PCI_INT_ENABLE_REG); + + rcar_pci_setup_errirq(priv); +} + +static struct pci_ops rcar_pci_ops = { + .map_bus = rcar_pci_cfg_base, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static int rcar_pci_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct resource *cfg_res, *mem_res; + struct rcar_pci *priv; + struct pci_host_bridge *bridge; + void __iomem *reg; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*priv)); + if (!bridge) + return -ENOMEM; + + priv = pci_host_bridge_priv(bridge); + bridge->sysdata = priv; + + cfg_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + reg = devm_ioremap_resource(dev, cfg_res); + if (IS_ERR(reg)) + return PTR_ERR(reg); + + mem_res = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!mem_res || !mem_res->start) + return -ENODEV; + + if (mem_res->start & 0xFFFF) + return -EINVAL; + + priv->mem_res = *mem_res; + priv->cfg_res = cfg_res; + + priv->irq = platform_get_irq(pdev, 0); + priv->reg = reg; + priv->dev = dev; + + if (priv->irq < 0) { + dev_err(dev, "no valid irq found\n"); + return priv->irq; + } + + bridge->ops = &rcar_pci_ops; + + pci_add_flags(PCI_REASSIGN_ALL_BUS); + + rcar_pci_setup(priv); + + return pci_host_probe(bridge); +} + +static const struct of_device_id rcar_pci_of_match[] = { + { .compatible = "renesas,pci-r8a7790", }, + { .compatible = "renesas,pci-r8a7791", }, + { .compatible = "renesas,pci-r8a7794", }, + { .compatible = "renesas,pci-rcar-gen2", }, + { .compatible = "renesas,pci-rzn1", }, + { }, +}; + +static struct platform_driver rcar_pci_driver = { + .driver = { + .name = "pci-rcar-gen2", + .suppress_bind_attrs = true, + .of_match_table = rcar_pci_of_match, + }, + .probe = rcar_pci_probe, +}; +builtin_platform_driver(rcar_pci_driver); diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c new file mode 100644 index 000000000..8e323e93b --- /dev/null +++ b/drivers/pci/controller/pci-tegra.c @@ -0,0 +1,2816 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * PCIe host controller driver for Tegra SoCs + * + * Copyright (c) 2010, CompuLab, Ltd. + * Author: Mike Rapoport <mike@compulab.co.il> + * + * Based on NVIDIA PCIe driver + * Copyright (c) 2008-2009, NVIDIA Corporation. + * + * Bits taken from arch/arm/mach-dove/pcie.c + * + * Author: Thierry Reding <treding@nvidia.com> + */ + +#include <linux/clk.h> +#include <linux/debugfs.h> +#include <linux/delay.h> +#include <linux/export.h> +#include <linux/gpio/consumer.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/pinctrl/consumer.h> +#include <linux/platform_device.h> +#include <linux/reset.h> +#include <linux/sizes.h> +#include <linux/slab.h> +#include <linux/vmalloc.h> +#include <linux/regulator/consumer.h> + +#include <soc/tegra/cpuidle.h> +#include <soc/tegra/pmc.h> + +#include "../pci.h" + +#define INT_PCI_MSI_NR (8 * 32) + +/* register definitions */ + +#define AFI_AXI_BAR0_SZ 0x00 +#define AFI_AXI_BAR1_SZ 0x04 +#define AFI_AXI_BAR2_SZ 0x08 +#define AFI_AXI_BAR3_SZ 0x0c +#define AFI_AXI_BAR4_SZ 0x10 +#define AFI_AXI_BAR5_SZ 0x14 + +#define AFI_AXI_BAR0_START 0x18 +#define AFI_AXI_BAR1_START 0x1c +#define AFI_AXI_BAR2_START 0x20 +#define AFI_AXI_BAR3_START 0x24 +#define AFI_AXI_BAR4_START 0x28 +#define AFI_AXI_BAR5_START 0x2c + +#define AFI_FPCI_BAR0 0x30 +#define AFI_FPCI_BAR1 0x34 +#define AFI_FPCI_BAR2 0x38 +#define AFI_FPCI_BAR3 0x3c +#define AFI_FPCI_BAR4 0x40 +#define AFI_FPCI_BAR5 0x44 + +#define AFI_CACHE_BAR0_SZ 0x48 +#define AFI_CACHE_BAR0_ST 0x4c +#define AFI_CACHE_BAR1_SZ 0x50 +#define AFI_CACHE_BAR1_ST 0x54 + +#define AFI_MSI_BAR_SZ 0x60 +#define AFI_MSI_FPCI_BAR_ST 0x64 +#define AFI_MSI_AXI_BAR_ST 0x68 + +#define AFI_MSI_VEC(x) (0x6c + ((x) * 4)) +#define AFI_MSI_EN_VEC(x) (0x8c + ((x) * 4)) + +#define AFI_CONFIGURATION 0xac +#define AFI_CONFIGURATION_EN_FPCI (1 << 0) +#define AFI_CONFIGURATION_CLKEN_OVERRIDE (1 << 31) + +#define AFI_FPCI_ERROR_MASKS 0xb0 + +#define AFI_INTR_MASK 0xb4 +#define AFI_INTR_MASK_INT_MASK (1 << 0) +#define AFI_INTR_MASK_MSI_MASK (1 << 8) + +#define AFI_INTR_CODE 0xb8 +#define AFI_INTR_CODE_MASK 0xf +#define AFI_INTR_INI_SLAVE_ERROR 1 +#define AFI_INTR_INI_DECODE_ERROR 2 +#define AFI_INTR_TARGET_ABORT 3 +#define AFI_INTR_MASTER_ABORT 4 +#define AFI_INTR_INVALID_WRITE 5 +#define AFI_INTR_LEGACY 6 +#define AFI_INTR_FPCI_DECODE_ERROR 7 +#define AFI_INTR_AXI_DECODE_ERROR 8 +#define AFI_INTR_FPCI_TIMEOUT 9 +#define AFI_INTR_PE_PRSNT_SENSE 10 +#define AFI_INTR_PE_CLKREQ_SENSE 11 +#define AFI_INTR_CLKCLAMP_SENSE 12 +#define AFI_INTR_RDY4PD_SENSE 13 +#define AFI_INTR_P2P_ERROR 14 + +#define AFI_INTR_SIGNATURE 0xbc +#define AFI_UPPER_FPCI_ADDRESS 0xc0 +#define AFI_SM_INTR_ENABLE 0xc4 +#define AFI_SM_INTR_INTA_ASSERT (1 << 0) +#define AFI_SM_INTR_INTB_ASSERT (1 << 1) +#define AFI_SM_INTR_INTC_ASSERT (1 << 2) +#define AFI_SM_INTR_INTD_ASSERT (1 << 3) +#define AFI_SM_INTR_INTA_DEASSERT (1 << 4) +#define AFI_SM_INTR_INTB_DEASSERT (1 << 5) +#define AFI_SM_INTR_INTC_DEASSERT (1 << 6) +#define AFI_SM_INTR_INTD_DEASSERT (1 << 7) + +#define AFI_AFI_INTR_ENABLE 0xc8 +#define AFI_INTR_EN_INI_SLVERR (1 << 0) +#define AFI_INTR_EN_INI_DECERR (1 << 1) +#define AFI_INTR_EN_TGT_SLVERR (1 << 2) +#define AFI_INTR_EN_TGT_DECERR (1 << 3) +#define AFI_INTR_EN_TGT_WRERR (1 << 4) +#define AFI_INTR_EN_DFPCI_DECERR (1 << 5) +#define AFI_INTR_EN_AXI_DECERR (1 << 6) +#define AFI_INTR_EN_FPCI_TIMEOUT (1 << 7) +#define AFI_INTR_EN_PRSNT_SENSE (1 << 8) + +#define AFI_PCIE_PME 0xf0 + +#define AFI_PCIE_CONFIG 0x0f8 +#define AFI_PCIE_CONFIG_PCIE_DISABLE(x) (1 << ((x) + 1)) +#define AFI_PCIE_CONFIG_PCIE_DISABLE_ALL 0xe +#define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK (0xf << 20) +#define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_SINGLE (0x0 << 20) +#define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_420 (0x0 << 20) +#define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_X2_X1 (0x0 << 20) +#define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_401 (0x0 << 20) +#define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_DUAL (0x1 << 20) +#define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_222 (0x1 << 20) +#define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_X4_X1 (0x1 << 20) +#define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_211 (0x1 << 20) +#define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_411 (0x2 << 20) +#define AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_111 (0x2 << 20) +#define AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(x) (1 << ((x) + 29)) +#define AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL (0x7 << 29) + +#define AFI_FUSE 0x104 +#define AFI_FUSE_PCIE_T0_GEN2_DIS (1 << 2) + +#define AFI_PEX0_CTRL 0x110 +#define AFI_PEX1_CTRL 0x118 +#define AFI_PEX_CTRL_RST (1 << 0) +#define AFI_PEX_CTRL_CLKREQ_EN (1 << 1) +#define AFI_PEX_CTRL_REFCLK_EN (1 << 3) +#define AFI_PEX_CTRL_OVERRIDE_EN (1 << 4) + +#define AFI_PLLE_CONTROL 0x160 +#define AFI_PLLE_CONTROL_BYPASS_PADS2PLLE_CONTROL (1 << 9) +#define AFI_PLLE_CONTROL_PADS2PLLE_CONTROL_EN (1 << 1) + +#define AFI_PEXBIAS_CTRL_0 0x168 + +#define RP_ECTL_2_R1 0x00000e84 +#define RP_ECTL_2_R1_RX_CTLE_1C_MASK 0xffff + +#define RP_ECTL_4_R1 0x00000e8c +#define RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK (0xffff << 16) +#define RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT 16 + +#define RP_ECTL_5_R1 0x00000e90 +#define RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK 0xffffffff + +#define RP_ECTL_6_R1 0x00000e94 +#define RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK 0xffffffff + +#define RP_ECTL_2_R2 0x00000ea4 +#define RP_ECTL_2_R2_RX_CTLE_1C_MASK 0xffff + +#define RP_ECTL_4_R2 0x00000eac +#define RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK (0xffff << 16) +#define RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT 16 + +#define RP_ECTL_5_R2 0x00000eb0 +#define RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK 0xffffffff + +#define RP_ECTL_6_R2 0x00000eb4 +#define RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK 0xffffffff + +#define RP_VEND_XP 0x00000f00 +#define RP_VEND_XP_DL_UP (1 << 30) +#define RP_VEND_XP_OPPORTUNISTIC_ACK (1 << 27) +#define RP_VEND_XP_OPPORTUNISTIC_UPDATEFC (1 << 28) +#define RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK (0xff << 18) + +#define RP_VEND_CTL0 0x00000f44 +#define RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK (0xf << 12) +#define RP_VEND_CTL0_DSK_RST_PULSE_WIDTH (0x9 << 12) + +#define RP_VEND_CTL1 0x00000f48 +#define RP_VEND_CTL1_ERPT (1 << 13) + +#define RP_VEND_XP_BIST 0x00000f4c +#define RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE (1 << 28) + +#define RP_VEND_CTL2 0x00000fa8 +#define RP_VEND_CTL2_PCA_ENABLE (1 << 7) + +#define RP_PRIV_MISC 0x00000fe0 +#define RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT (0xe << 0) +#define RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT (0xf << 0) +#define RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK (0x7f << 16) +#define RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD (0xf << 16) +#define RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE (1 << 23) +#define RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK (0x7f << 24) +#define RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD (0xf << 24) +#define RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE (1 << 31) + +#define RP_LINK_CONTROL_STATUS 0x00000090 +#define RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE 0x20000000 +#define RP_LINK_CONTROL_STATUS_LINKSTAT_MASK 0x3fff0000 + +#define RP_LINK_CONTROL_STATUS_2 0x000000b0 + +#define PADS_CTL_SEL 0x0000009c + +#define PADS_CTL 0x000000a0 +#define PADS_CTL_IDDQ_1L (1 << 0) +#define PADS_CTL_TX_DATA_EN_1L (1 << 6) +#define PADS_CTL_RX_DATA_EN_1L (1 << 10) + +#define PADS_PLL_CTL_TEGRA20 0x000000b8 +#define PADS_PLL_CTL_TEGRA30 0x000000b4 +#define PADS_PLL_CTL_RST_B4SM (1 << 1) +#define PADS_PLL_CTL_LOCKDET (1 << 8) +#define PADS_PLL_CTL_REFCLK_MASK (0x3 << 16) +#define PADS_PLL_CTL_REFCLK_INTERNAL_CML (0 << 16) +#define PADS_PLL_CTL_REFCLK_INTERNAL_CMOS (1 << 16) +#define PADS_PLL_CTL_REFCLK_EXTERNAL (2 << 16) +#define PADS_PLL_CTL_TXCLKREF_MASK (0x1 << 20) +#define PADS_PLL_CTL_TXCLKREF_DIV10 (0 << 20) +#define PADS_PLL_CTL_TXCLKREF_DIV5 (1 << 20) +#define PADS_PLL_CTL_TXCLKREF_BUF_EN (1 << 22) + +#define PADS_REFCLK_CFG0 0x000000c8 +#define PADS_REFCLK_CFG1 0x000000cc +#define PADS_REFCLK_BIAS 0x000000d0 + +/* + * Fields in PADS_REFCLK_CFG*. Those registers form an array of 16-bit + * entries, one entry per PCIe port. These field definitions and desired + * values aren't in the TRM, but do come from NVIDIA. + */ +#define PADS_REFCLK_CFG_TERM_SHIFT 2 /* 6:2 */ +#define PADS_REFCLK_CFG_E_TERM_SHIFT 7 +#define PADS_REFCLK_CFG_PREDI_SHIFT 8 /* 11:8 */ +#define PADS_REFCLK_CFG_DRVI_SHIFT 12 /* 15:12 */ + +#define PME_ACK_TIMEOUT 10000 +#define LINK_RETRAIN_TIMEOUT 100000 /* in usec */ + +struct tegra_msi { + DECLARE_BITMAP(used, INT_PCI_MSI_NR); + struct irq_domain *domain; + struct mutex map_lock; + spinlock_t mask_lock; + void *virt; + dma_addr_t phys; + int irq; +}; + +/* used to differentiate between Tegra SoC generations */ +struct tegra_pcie_port_soc { + struct { + u8 turnoff_bit; + u8 ack_bit; + } pme; +}; + +struct tegra_pcie_soc { + unsigned int num_ports; + const struct tegra_pcie_port_soc *ports; + unsigned int msi_base_shift; + unsigned long afi_pex2_ctrl; + u32 pads_pll_ctl; + u32 tx_ref_sel; + u32 pads_refclk_cfg0; + u32 pads_refclk_cfg1; + u32 update_fc_threshold; + bool has_pex_clkreq_en; + bool has_pex_bias_ctrl; + bool has_intr_prsnt_sense; + bool has_cml_clk; + bool has_gen2; + bool force_pca_enable; + bool program_uphy; + bool update_clamp_threshold; + bool program_deskew_time; + bool update_fc_timer; + bool has_cache_bars; + struct { + struct { + u32 rp_ectl_2_r1; + u32 rp_ectl_4_r1; + u32 rp_ectl_5_r1; + u32 rp_ectl_6_r1; + u32 rp_ectl_2_r2; + u32 rp_ectl_4_r2; + u32 rp_ectl_5_r2; + u32 rp_ectl_6_r2; + } regs; + bool enable; + } ectl; +}; + +struct tegra_pcie { + struct device *dev; + + void __iomem *pads; + void __iomem *afi; + void __iomem *cfg; + int irq; + + struct resource cs; + + struct clk *pex_clk; + struct clk *afi_clk; + struct clk *pll_e; + struct clk *cml_clk; + + struct reset_control *pex_rst; + struct reset_control *afi_rst; + struct reset_control *pcie_xrst; + + bool legacy_phy; + struct phy *phy; + + struct tegra_msi msi; + + struct list_head ports; + u32 xbar_config; + + struct regulator_bulk_data *supplies; + unsigned int num_supplies; + + const struct tegra_pcie_soc *soc; + struct dentry *debugfs; +}; + +static inline struct tegra_pcie *msi_to_pcie(struct tegra_msi *msi) +{ + return container_of(msi, struct tegra_pcie, msi); +} + +struct tegra_pcie_port { + struct tegra_pcie *pcie; + struct device_node *np; + struct list_head list; + struct resource regs; + void __iomem *base; + unsigned int index; + unsigned int lanes; + + struct phy **phys; + + struct gpio_desc *reset_gpio; +}; + +static inline void afi_writel(struct tegra_pcie *pcie, u32 value, + unsigned long offset) +{ + writel(value, pcie->afi + offset); +} + +static inline u32 afi_readl(struct tegra_pcie *pcie, unsigned long offset) +{ + return readl(pcie->afi + offset); +} + +static inline void pads_writel(struct tegra_pcie *pcie, u32 value, + unsigned long offset) +{ + writel(value, pcie->pads + offset); +} + +static inline u32 pads_readl(struct tegra_pcie *pcie, unsigned long offset) +{ + return readl(pcie->pads + offset); +} + +/* + * The configuration space mapping on Tegra is somewhat similar to the ECAM + * defined by PCIe. However it deviates a bit in how the 4 bits for extended + * register accesses are mapped: + * + * [27:24] extended register number + * [23:16] bus number + * [15:11] device number + * [10: 8] function number + * [ 7: 0] register number + * + * Mapping the whole extended configuration space would require 256 MiB of + * virtual address space, only a small part of which will actually be used. + * + * To work around this, a 4 KiB region is used to generate the required + * configuration transaction with relevant B:D:F and register offset values. + * This is achieved by dynamically programming base address and size of + * AFI_AXI_BAR used for end point config space mapping to make sure that the + * address (access to which generates correct config transaction) falls in + * this 4 KiB region. + */ +static unsigned int tegra_pcie_conf_offset(u8 bus, unsigned int devfn, + unsigned int where) +{ + return ((where & 0xf00) << 16) | (bus << 16) | (PCI_SLOT(devfn) << 11) | + (PCI_FUNC(devfn) << 8) | (where & 0xff); +} + +static void __iomem *tegra_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, + int where) +{ + struct tegra_pcie *pcie = bus->sysdata; + void __iomem *addr = NULL; + + if (bus->number == 0) { + unsigned int slot = PCI_SLOT(devfn); + struct tegra_pcie_port *port; + + list_for_each_entry(port, &pcie->ports, list) { + if (port->index + 1 == slot) { + addr = port->base + (where & ~3); + break; + } + } + } else { + unsigned int offset; + u32 base; + + offset = tegra_pcie_conf_offset(bus->number, devfn, where); + + /* move 4 KiB window to offset within the FPCI region */ + base = 0xfe100000 + ((offset & ~(SZ_4K - 1)) >> 8); + afi_writel(pcie, base, AFI_FPCI_BAR0); + + /* move to correct offset within the 4 KiB page */ + addr = pcie->cfg + (offset & (SZ_4K - 1)); + } + + return addr; +} + +static int tegra_pcie_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *value) +{ + if (bus->number == 0) + return pci_generic_config_read32(bus, devfn, where, size, + value); + + return pci_generic_config_read(bus, devfn, where, size, value); +} + +static int tegra_pcie_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 value) +{ + if (bus->number == 0) + return pci_generic_config_write32(bus, devfn, where, size, + value); + + return pci_generic_config_write(bus, devfn, where, size, value); +} + +static struct pci_ops tegra_pcie_ops = { + .map_bus = tegra_pcie_map_bus, + .read = tegra_pcie_config_read, + .write = tegra_pcie_config_write, +}; + +static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port) +{ + const struct tegra_pcie_soc *soc = port->pcie->soc; + unsigned long ret = 0; + + switch (port->index) { + case 0: + ret = AFI_PEX0_CTRL; + break; + + case 1: + ret = AFI_PEX1_CTRL; + break; + + case 2: + ret = soc->afi_pex2_ctrl; + break; + } + + return ret; +} + +static void tegra_pcie_port_reset(struct tegra_pcie_port *port) +{ + unsigned long ctrl = tegra_pcie_port_get_pex_ctrl(port); + unsigned long value; + + /* pulse reset signal */ + if (port->reset_gpio) { + gpiod_set_value(port->reset_gpio, 1); + } else { + value = afi_readl(port->pcie, ctrl); + value &= ~AFI_PEX_CTRL_RST; + afi_writel(port->pcie, value, ctrl); + } + + usleep_range(1000, 2000); + + if (port->reset_gpio) { + gpiod_set_value(port->reset_gpio, 0); + } else { + value = afi_readl(port->pcie, ctrl); + value |= AFI_PEX_CTRL_RST; + afi_writel(port->pcie, value, ctrl); + } +} + +static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port) +{ + const struct tegra_pcie_soc *soc = port->pcie->soc; + u32 value; + + /* Enable AER capability */ + value = readl(port->base + RP_VEND_CTL1); + value |= RP_VEND_CTL1_ERPT; + writel(value, port->base + RP_VEND_CTL1); + + /* Optimal settings to enhance bandwidth */ + value = readl(port->base + RP_VEND_XP); + value |= RP_VEND_XP_OPPORTUNISTIC_ACK; + value |= RP_VEND_XP_OPPORTUNISTIC_UPDATEFC; + writel(value, port->base + RP_VEND_XP); + + /* + * LTSSM will wait for DLLP to finish before entering L1 or L2, + * to avoid truncation of PM messages which results in receiver errors + */ + value = readl(port->base + RP_VEND_XP_BIST); + value |= RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE; + writel(value, port->base + RP_VEND_XP_BIST); + + value = readl(port->base + RP_PRIV_MISC); + value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE; + value |= RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE; + + if (soc->update_clamp_threshold) { + value &= ~(RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK | + RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK); + value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD | + RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD; + } + + writel(value, port->base + RP_PRIV_MISC); +} + +static void tegra_pcie_program_ectl_settings(struct tegra_pcie_port *port) +{ + const struct tegra_pcie_soc *soc = port->pcie->soc; + u32 value; + + value = readl(port->base + RP_ECTL_2_R1); + value &= ~RP_ECTL_2_R1_RX_CTLE_1C_MASK; + value |= soc->ectl.regs.rp_ectl_2_r1; + writel(value, port->base + RP_ECTL_2_R1); + + value = readl(port->base + RP_ECTL_4_R1); + value &= ~RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK; + value |= soc->ectl.regs.rp_ectl_4_r1 << + RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT; + writel(value, port->base + RP_ECTL_4_R1); + + value = readl(port->base + RP_ECTL_5_R1); + value &= ~RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK; + value |= soc->ectl.regs.rp_ectl_5_r1; + writel(value, port->base + RP_ECTL_5_R1); + + value = readl(port->base + RP_ECTL_6_R1); + value &= ~RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK; + value |= soc->ectl.regs.rp_ectl_6_r1; + writel(value, port->base + RP_ECTL_6_R1); + + value = readl(port->base + RP_ECTL_2_R2); + value &= ~RP_ECTL_2_R2_RX_CTLE_1C_MASK; + value |= soc->ectl.regs.rp_ectl_2_r2; + writel(value, port->base + RP_ECTL_2_R2); + + value = readl(port->base + RP_ECTL_4_R2); + value &= ~RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK; + value |= soc->ectl.regs.rp_ectl_4_r2 << + RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT; + writel(value, port->base + RP_ECTL_4_R2); + + value = readl(port->base + RP_ECTL_5_R2); + value &= ~RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK; + value |= soc->ectl.regs.rp_ectl_5_r2; + writel(value, port->base + RP_ECTL_5_R2); + + value = readl(port->base + RP_ECTL_6_R2); + value &= ~RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK; + value |= soc->ectl.regs.rp_ectl_6_r2; + writel(value, port->base + RP_ECTL_6_R2); +} + +static void tegra_pcie_apply_sw_fixup(struct tegra_pcie_port *port) +{ + const struct tegra_pcie_soc *soc = port->pcie->soc; + u32 value; + + /* + * Sometimes link speed change from Gen2 to Gen1 fails due to + * instability in deskew logic on lane-0. Increase the deskew + * retry time to resolve this issue. + */ + if (soc->program_deskew_time) { + value = readl(port->base + RP_VEND_CTL0); + value &= ~RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK; + value |= RP_VEND_CTL0_DSK_RST_PULSE_WIDTH; + writel(value, port->base + RP_VEND_CTL0); + } + + if (soc->update_fc_timer) { + value = readl(port->base + RP_VEND_XP); + value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK; + value |= soc->update_fc_threshold; + writel(value, port->base + RP_VEND_XP); + } + + /* + * PCIe link doesn't come up with few legacy PCIe endpoints if + * root port advertises both Gen-1 and Gen-2 speeds in Tegra. + * Hence, the strategy followed here is to initially advertise + * only Gen-1 and after link is up, retrain link to Gen-2 speed + */ + value = readl(port->base + RP_LINK_CONTROL_STATUS_2); + value &= ~PCI_EXP_LNKSTA_CLS; + value |= PCI_EXP_LNKSTA_CLS_2_5GB; + writel(value, port->base + RP_LINK_CONTROL_STATUS_2); +} + +static void tegra_pcie_port_enable(struct tegra_pcie_port *port) +{ + unsigned long ctrl = tegra_pcie_port_get_pex_ctrl(port); + const struct tegra_pcie_soc *soc = port->pcie->soc; + unsigned long value; + + /* enable reference clock */ + value = afi_readl(port->pcie, ctrl); + value |= AFI_PEX_CTRL_REFCLK_EN; + + if (soc->has_pex_clkreq_en) + value |= AFI_PEX_CTRL_CLKREQ_EN; + + value |= AFI_PEX_CTRL_OVERRIDE_EN; + + afi_writel(port->pcie, value, ctrl); + + tegra_pcie_port_reset(port); + + if (soc->force_pca_enable) { + value = readl(port->base + RP_VEND_CTL2); + value |= RP_VEND_CTL2_PCA_ENABLE; + writel(value, port->base + RP_VEND_CTL2); + } + + tegra_pcie_enable_rp_features(port); + + if (soc->ectl.enable) + tegra_pcie_program_ectl_settings(port); + + tegra_pcie_apply_sw_fixup(port); +} + +static void tegra_pcie_port_disable(struct tegra_pcie_port *port) +{ + unsigned long ctrl = tegra_pcie_port_get_pex_ctrl(port); + const struct tegra_pcie_soc *soc = port->pcie->soc; + unsigned long value; + + /* assert port reset */ + value = afi_readl(port->pcie, ctrl); + value &= ~AFI_PEX_CTRL_RST; + afi_writel(port->pcie, value, ctrl); + + /* disable reference clock */ + value = afi_readl(port->pcie, ctrl); + + if (soc->has_pex_clkreq_en) + value &= ~AFI_PEX_CTRL_CLKREQ_EN; + + value &= ~AFI_PEX_CTRL_REFCLK_EN; + afi_writel(port->pcie, value, ctrl); + + /* disable PCIe port and set CLKREQ# as GPIO to allow PLLE power down */ + value = afi_readl(port->pcie, AFI_PCIE_CONFIG); + value |= AFI_PCIE_CONFIG_PCIE_DISABLE(port->index); + value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index); + afi_writel(port->pcie, value, AFI_PCIE_CONFIG); +} + +static void tegra_pcie_port_free(struct tegra_pcie_port *port) +{ + struct tegra_pcie *pcie = port->pcie; + struct device *dev = pcie->dev; + + devm_iounmap(dev, port->base); + devm_release_mem_region(dev, port->regs.start, + resource_size(&port->regs)); + list_del(&port->list); + devm_kfree(dev, port); +} + +/* Tegra PCIE root complex wrongly reports device class */ +static void tegra_pcie_fixup_class(struct pci_dev *dev) +{ + dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf0, tegra_pcie_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_fixup_class); + +/* Tegra20 and Tegra30 PCIE requires relaxed ordering */ +static void tegra_pcie_relax_enable(struct pci_dev *dev) +{ + pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN); +} +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf0, tegra_pcie_relax_enable); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_relax_enable); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_relax_enable); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_relax_enable); + +static int tegra_pcie_map_irq(const struct pci_dev *pdev, u8 slot, u8 pin) +{ + struct tegra_pcie *pcie = pdev->bus->sysdata; + int irq; + + tegra_cpuidle_pcie_irqs_in_use(); + + irq = of_irq_parse_and_map_pci(pdev, slot, pin); + if (!irq) + irq = pcie->irq; + + return irq; +} + +static irqreturn_t tegra_pcie_isr(int irq, void *arg) +{ + static const char * const err_msg[] = { + "Unknown", + "AXI slave error", + "AXI decode error", + "Target abort", + "Master abort", + "Invalid write", + "Legacy interrupt", + "Response decoding error", + "AXI response decoding error", + "Transaction timeout", + "Slot present pin change", + "Slot clock request change", + "TMS clock ramp change", + "TMS ready for power down", + "Peer2Peer error", + }; + struct tegra_pcie *pcie = arg; + struct device *dev = pcie->dev; + u32 code, signature; + + code = afi_readl(pcie, AFI_INTR_CODE) & AFI_INTR_CODE_MASK; + signature = afi_readl(pcie, AFI_INTR_SIGNATURE); + afi_writel(pcie, 0, AFI_INTR_CODE); + + if (code == AFI_INTR_LEGACY) + return IRQ_NONE; + + if (code >= ARRAY_SIZE(err_msg)) + code = 0; + + /* + * do not pollute kernel log with master abort reports since they + * happen a lot during enumeration + */ + if (code == AFI_INTR_MASTER_ABORT || code == AFI_INTR_PE_PRSNT_SENSE) + dev_dbg(dev, "%s, signature: %08x\n", err_msg[code], signature); + else + dev_err(dev, "%s, signature: %08x\n", err_msg[code], signature); + + if (code == AFI_INTR_TARGET_ABORT || code == AFI_INTR_MASTER_ABORT || + code == AFI_INTR_FPCI_DECODE_ERROR) { + u32 fpci = afi_readl(pcie, AFI_UPPER_FPCI_ADDRESS) & 0xff; + u64 address = (u64)fpci << 32 | (signature & 0xfffffffc); + + if (code == AFI_INTR_MASTER_ABORT) + dev_dbg(dev, " FPCI address: %10llx\n", address); + else + dev_err(dev, " FPCI address: %10llx\n", address); + } + + return IRQ_HANDLED; +} + +/* + * FPCI map is as follows: + * - 0xfdfc000000: I/O space + * - 0xfdfe000000: type 0 configuration space + * - 0xfdff000000: type 1 configuration space + * - 0xfe00000000: type 0 extended configuration space + * - 0xfe10000000: type 1 extended configuration space + */ +static void tegra_pcie_setup_translations(struct tegra_pcie *pcie) +{ + u32 size; + struct resource_entry *entry; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + + /* Bar 0: type 1 extended configuration space */ + size = resource_size(&pcie->cs); + afi_writel(pcie, pcie->cs.start, AFI_AXI_BAR0_START); + afi_writel(pcie, size >> 12, AFI_AXI_BAR0_SZ); + + resource_list_for_each_entry(entry, &bridge->windows) { + u32 fpci_bar, axi_address; + struct resource *res = entry->res; + + size = resource_size(res); + + switch (resource_type(res)) { + case IORESOURCE_IO: + /* Bar 1: downstream IO bar */ + fpci_bar = 0xfdfc0000; + axi_address = pci_pio_to_address(res->start); + afi_writel(pcie, axi_address, AFI_AXI_BAR1_START); + afi_writel(pcie, size >> 12, AFI_AXI_BAR1_SZ); + afi_writel(pcie, fpci_bar, AFI_FPCI_BAR1); + break; + case IORESOURCE_MEM: + fpci_bar = (((res->start >> 12) & 0x0fffffff) << 4) | 0x1; + axi_address = res->start; + + if (res->flags & IORESOURCE_PREFETCH) { + /* Bar 2: prefetchable memory BAR */ + afi_writel(pcie, axi_address, AFI_AXI_BAR2_START); + afi_writel(pcie, size >> 12, AFI_AXI_BAR2_SZ); + afi_writel(pcie, fpci_bar, AFI_FPCI_BAR2); + + } else { + /* Bar 3: non prefetchable memory BAR */ + afi_writel(pcie, axi_address, AFI_AXI_BAR3_START); + afi_writel(pcie, size >> 12, AFI_AXI_BAR3_SZ); + afi_writel(pcie, fpci_bar, AFI_FPCI_BAR3); + } + break; + } + } + + /* NULL out the remaining BARs as they are not used */ + afi_writel(pcie, 0, AFI_AXI_BAR4_START); + afi_writel(pcie, 0, AFI_AXI_BAR4_SZ); + afi_writel(pcie, 0, AFI_FPCI_BAR4); + + afi_writel(pcie, 0, AFI_AXI_BAR5_START); + afi_writel(pcie, 0, AFI_AXI_BAR5_SZ); + afi_writel(pcie, 0, AFI_FPCI_BAR5); + + if (pcie->soc->has_cache_bars) { + /* map all upstream transactions as uncached */ + afi_writel(pcie, 0, AFI_CACHE_BAR0_ST); + afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ); + afi_writel(pcie, 0, AFI_CACHE_BAR1_ST); + afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ); + } + + /* MSI translations are setup only when needed */ + afi_writel(pcie, 0, AFI_MSI_FPCI_BAR_ST); + afi_writel(pcie, 0, AFI_MSI_BAR_SZ); + afi_writel(pcie, 0, AFI_MSI_AXI_BAR_ST); + afi_writel(pcie, 0, AFI_MSI_BAR_SZ); +} + +static int tegra_pcie_pll_wait(struct tegra_pcie *pcie, unsigned long timeout) +{ + const struct tegra_pcie_soc *soc = pcie->soc; + u32 value; + + timeout = jiffies + msecs_to_jiffies(timeout); + + while (time_before(jiffies, timeout)) { + value = pads_readl(pcie, soc->pads_pll_ctl); + if (value & PADS_PLL_CTL_LOCKDET) + return 0; + } + + return -ETIMEDOUT; +} + +static int tegra_pcie_phy_enable(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + const struct tegra_pcie_soc *soc = pcie->soc; + u32 value; + int err; + + /* initialize internal PHY, enable up to 16 PCIE lanes */ + pads_writel(pcie, 0x0, PADS_CTL_SEL); + + /* override IDDQ to 1 on all 4 lanes */ + value = pads_readl(pcie, PADS_CTL); + value |= PADS_CTL_IDDQ_1L; + pads_writel(pcie, value, PADS_CTL); + + /* + * Set up PHY PLL inputs select PLLE output as refclock, + * set TX ref sel to div10 (not div5). + */ + value = pads_readl(pcie, soc->pads_pll_ctl); + value &= ~(PADS_PLL_CTL_REFCLK_MASK | PADS_PLL_CTL_TXCLKREF_MASK); + value |= PADS_PLL_CTL_REFCLK_INTERNAL_CML | soc->tx_ref_sel; + pads_writel(pcie, value, soc->pads_pll_ctl); + + /* reset PLL */ + value = pads_readl(pcie, soc->pads_pll_ctl); + value &= ~PADS_PLL_CTL_RST_B4SM; + pads_writel(pcie, value, soc->pads_pll_ctl); + + usleep_range(20, 100); + + /* take PLL out of reset */ + value = pads_readl(pcie, soc->pads_pll_ctl); + value |= PADS_PLL_CTL_RST_B4SM; + pads_writel(pcie, value, soc->pads_pll_ctl); + + /* wait for the PLL to lock */ + err = tegra_pcie_pll_wait(pcie, 500); + if (err < 0) { + dev_err(dev, "PLL failed to lock: %d\n", err); + return err; + } + + /* turn off IDDQ override */ + value = pads_readl(pcie, PADS_CTL); + value &= ~PADS_CTL_IDDQ_1L; + pads_writel(pcie, value, PADS_CTL); + + /* enable TX/RX data */ + value = pads_readl(pcie, PADS_CTL); + value |= PADS_CTL_TX_DATA_EN_1L | PADS_CTL_RX_DATA_EN_1L; + pads_writel(pcie, value, PADS_CTL); + + return 0; +} + +static int tegra_pcie_phy_disable(struct tegra_pcie *pcie) +{ + const struct tegra_pcie_soc *soc = pcie->soc; + u32 value; + + /* disable TX/RX data */ + value = pads_readl(pcie, PADS_CTL); + value &= ~(PADS_CTL_TX_DATA_EN_1L | PADS_CTL_RX_DATA_EN_1L); + pads_writel(pcie, value, PADS_CTL); + + /* override IDDQ */ + value = pads_readl(pcie, PADS_CTL); + value |= PADS_CTL_IDDQ_1L; + pads_writel(pcie, value, PADS_CTL); + + /* reset PLL */ + value = pads_readl(pcie, soc->pads_pll_ctl); + value &= ~PADS_PLL_CTL_RST_B4SM; + pads_writel(pcie, value, soc->pads_pll_ctl); + + usleep_range(20, 100); + + return 0; +} + +static int tegra_pcie_port_phy_power_on(struct tegra_pcie_port *port) +{ + struct device *dev = port->pcie->dev; + unsigned int i; + int err; + + for (i = 0; i < port->lanes; i++) { + err = phy_power_on(port->phys[i]); + if (err < 0) { + dev_err(dev, "failed to power on PHY#%u: %d\n", i, err); + return err; + } + } + + return 0; +} + +static int tegra_pcie_port_phy_power_off(struct tegra_pcie_port *port) +{ + struct device *dev = port->pcie->dev; + unsigned int i; + int err; + + for (i = 0; i < port->lanes; i++) { + err = phy_power_off(port->phys[i]); + if (err < 0) { + dev_err(dev, "failed to power off PHY#%u: %d\n", i, + err); + return err; + } + } + + return 0; +} + +static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct tegra_pcie_port *port; + int err; + + if (pcie->legacy_phy) { + if (pcie->phy) + err = phy_power_on(pcie->phy); + else + err = tegra_pcie_phy_enable(pcie); + + if (err < 0) + dev_err(dev, "failed to power on PHY: %d\n", err); + + return err; + } + + list_for_each_entry(port, &pcie->ports, list) { + err = tegra_pcie_port_phy_power_on(port); + if (err < 0) { + dev_err(dev, + "failed to power on PCIe port %u PHY: %d\n", + port->index, err); + return err; + } + } + + return 0; +} + +static int tegra_pcie_phy_power_off(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct tegra_pcie_port *port; + int err; + + if (pcie->legacy_phy) { + if (pcie->phy) + err = phy_power_off(pcie->phy); + else + err = tegra_pcie_phy_disable(pcie); + + if (err < 0) + dev_err(dev, "failed to power off PHY: %d\n", err); + + return err; + } + + list_for_each_entry(port, &pcie->ports, list) { + err = tegra_pcie_port_phy_power_off(port); + if (err < 0) { + dev_err(dev, + "failed to power off PCIe port %u PHY: %d\n", + port->index, err); + return err; + } + } + + return 0; +} + +static void tegra_pcie_enable_controller(struct tegra_pcie *pcie) +{ + const struct tegra_pcie_soc *soc = pcie->soc; + struct tegra_pcie_port *port; + unsigned long value; + + /* enable PLL power down */ + if (pcie->phy) { + value = afi_readl(pcie, AFI_PLLE_CONTROL); + value &= ~AFI_PLLE_CONTROL_BYPASS_PADS2PLLE_CONTROL; + value |= AFI_PLLE_CONTROL_PADS2PLLE_CONTROL_EN; + afi_writel(pcie, value, AFI_PLLE_CONTROL); + } + + /* power down PCIe slot clock bias pad */ + if (soc->has_pex_bias_ctrl) + afi_writel(pcie, 0, AFI_PEXBIAS_CTRL_0); + + /* configure mode and disable all ports */ + value = afi_readl(pcie, AFI_PCIE_CONFIG); + value &= ~AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK; + value |= AFI_PCIE_CONFIG_PCIE_DISABLE_ALL | pcie->xbar_config; + value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL; + + list_for_each_entry(port, &pcie->ports, list) { + value &= ~AFI_PCIE_CONFIG_PCIE_DISABLE(port->index); + value &= ~AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index); + } + + afi_writel(pcie, value, AFI_PCIE_CONFIG); + + if (soc->has_gen2) { + value = afi_readl(pcie, AFI_FUSE); + value &= ~AFI_FUSE_PCIE_T0_GEN2_DIS; + afi_writel(pcie, value, AFI_FUSE); + } else { + value = afi_readl(pcie, AFI_FUSE); + value |= AFI_FUSE_PCIE_T0_GEN2_DIS; + afi_writel(pcie, value, AFI_FUSE); + } + + /* Disable AFI dynamic clock gating and enable PCIe */ + value = afi_readl(pcie, AFI_CONFIGURATION); + value |= AFI_CONFIGURATION_EN_FPCI; + value |= AFI_CONFIGURATION_CLKEN_OVERRIDE; + afi_writel(pcie, value, AFI_CONFIGURATION); + + value = AFI_INTR_EN_INI_SLVERR | AFI_INTR_EN_INI_DECERR | + AFI_INTR_EN_TGT_SLVERR | AFI_INTR_EN_TGT_DECERR | + AFI_INTR_EN_TGT_WRERR | AFI_INTR_EN_DFPCI_DECERR; + + if (soc->has_intr_prsnt_sense) + value |= AFI_INTR_EN_PRSNT_SENSE; + + afi_writel(pcie, value, AFI_AFI_INTR_ENABLE); + afi_writel(pcie, 0xffffffff, AFI_SM_INTR_ENABLE); + + /* don't enable MSI for now, only when needed */ + afi_writel(pcie, AFI_INTR_MASK_INT_MASK, AFI_INTR_MASK); + + /* disable all exceptions */ + afi_writel(pcie, 0, AFI_FPCI_ERROR_MASKS); +} + +static void tegra_pcie_power_off(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + const struct tegra_pcie_soc *soc = pcie->soc; + int err; + + reset_control_assert(pcie->afi_rst); + + clk_disable_unprepare(pcie->pll_e); + if (soc->has_cml_clk) + clk_disable_unprepare(pcie->cml_clk); + clk_disable_unprepare(pcie->afi_clk); + + if (!dev->pm_domain) + tegra_powergate_power_off(TEGRA_POWERGATE_PCIE); + + err = regulator_bulk_disable(pcie->num_supplies, pcie->supplies); + if (err < 0) + dev_warn(dev, "failed to disable regulators: %d\n", err); +} + +static int tegra_pcie_power_on(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + const struct tegra_pcie_soc *soc = pcie->soc; + int err; + + reset_control_assert(pcie->pcie_xrst); + reset_control_assert(pcie->afi_rst); + reset_control_assert(pcie->pex_rst); + + if (!dev->pm_domain) + tegra_powergate_power_off(TEGRA_POWERGATE_PCIE); + + /* enable regulators */ + err = regulator_bulk_enable(pcie->num_supplies, pcie->supplies); + if (err < 0) + dev_err(dev, "failed to enable regulators: %d\n", err); + + if (!dev->pm_domain) { + err = tegra_powergate_power_on(TEGRA_POWERGATE_PCIE); + if (err) { + dev_err(dev, "failed to power ungate: %d\n", err); + goto regulator_disable; + } + err = tegra_powergate_remove_clamping(TEGRA_POWERGATE_PCIE); + if (err) { + dev_err(dev, "failed to remove clamp: %d\n", err); + goto powergate; + } + } + + err = clk_prepare_enable(pcie->afi_clk); + if (err < 0) { + dev_err(dev, "failed to enable AFI clock: %d\n", err); + goto powergate; + } + + if (soc->has_cml_clk) { + err = clk_prepare_enable(pcie->cml_clk); + if (err < 0) { + dev_err(dev, "failed to enable CML clock: %d\n", err); + goto disable_afi_clk; + } + } + + err = clk_prepare_enable(pcie->pll_e); + if (err < 0) { + dev_err(dev, "failed to enable PLLE clock: %d\n", err); + goto disable_cml_clk; + } + + reset_control_deassert(pcie->afi_rst); + + return 0; + +disable_cml_clk: + if (soc->has_cml_clk) + clk_disable_unprepare(pcie->cml_clk); +disable_afi_clk: + clk_disable_unprepare(pcie->afi_clk); +powergate: + if (!dev->pm_domain) + tegra_powergate_power_off(TEGRA_POWERGATE_PCIE); +regulator_disable: + regulator_bulk_disable(pcie->num_supplies, pcie->supplies); + + return err; +} + +static void tegra_pcie_apply_pad_settings(struct tegra_pcie *pcie) +{ + const struct tegra_pcie_soc *soc = pcie->soc; + + /* Configure the reference clock driver */ + pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0); + + if (soc->num_ports > 2) + pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1); +} + +static int tegra_pcie_clocks_get(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + const struct tegra_pcie_soc *soc = pcie->soc; + + pcie->pex_clk = devm_clk_get(dev, "pex"); + if (IS_ERR(pcie->pex_clk)) + return PTR_ERR(pcie->pex_clk); + + pcie->afi_clk = devm_clk_get(dev, "afi"); + if (IS_ERR(pcie->afi_clk)) + return PTR_ERR(pcie->afi_clk); + + pcie->pll_e = devm_clk_get(dev, "pll_e"); + if (IS_ERR(pcie->pll_e)) + return PTR_ERR(pcie->pll_e); + + if (soc->has_cml_clk) { + pcie->cml_clk = devm_clk_get(dev, "cml"); + if (IS_ERR(pcie->cml_clk)) + return PTR_ERR(pcie->cml_clk); + } + + return 0; +} + +static int tegra_pcie_resets_get(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + + pcie->pex_rst = devm_reset_control_get_exclusive(dev, "pex"); + if (IS_ERR(pcie->pex_rst)) + return PTR_ERR(pcie->pex_rst); + + pcie->afi_rst = devm_reset_control_get_exclusive(dev, "afi"); + if (IS_ERR(pcie->afi_rst)) + return PTR_ERR(pcie->afi_rst); + + pcie->pcie_xrst = devm_reset_control_get_exclusive(dev, "pcie_x"); + if (IS_ERR(pcie->pcie_xrst)) + return PTR_ERR(pcie->pcie_xrst); + + return 0; +} + +static int tegra_pcie_phys_get_legacy(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + int err; + + pcie->phy = devm_phy_optional_get(dev, "pcie"); + if (IS_ERR(pcie->phy)) { + err = PTR_ERR(pcie->phy); + dev_err(dev, "failed to get PHY: %d\n", err); + return err; + } + + err = phy_init(pcie->phy); + if (err < 0) { + dev_err(dev, "failed to initialize PHY: %d\n", err); + return err; + } + + pcie->legacy_phy = true; + + return 0; +} + +static struct phy *devm_of_phy_optional_get_index(struct device *dev, + struct device_node *np, + const char *consumer, + unsigned int index) +{ + struct phy *phy; + char *name; + + name = kasprintf(GFP_KERNEL, "%s-%u", consumer, index); + if (!name) + return ERR_PTR(-ENOMEM); + + phy = devm_of_phy_get(dev, np, name); + kfree(name); + + if (PTR_ERR(phy) == -ENODEV) + phy = NULL; + + return phy; +} + +static int tegra_pcie_port_get_phys(struct tegra_pcie_port *port) +{ + struct device *dev = port->pcie->dev; + struct phy *phy; + unsigned int i; + int err; + + port->phys = devm_kcalloc(dev, sizeof(phy), port->lanes, GFP_KERNEL); + if (!port->phys) + return -ENOMEM; + + for (i = 0; i < port->lanes; i++) { + phy = devm_of_phy_optional_get_index(dev, port->np, "pcie", i); + if (IS_ERR(phy)) { + dev_err(dev, "failed to get PHY#%u: %ld\n", i, + PTR_ERR(phy)); + return PTR_ERR(phy); + } + + err = phy_init(phy); + if (err < 0) { + dev_err(dev, "failed to initialize PHY#%u: %d\n", i, + err); + return err; + } + + port->phys[i] = phy; + } + + return 0; +} + +static int tegra_pcie_phys_get(struct tegra_pcie *pcie) +{ + const struct tegra_pcie_soc *soc = pcie->soc; + struct device_node *np = pcie->dev->of_node; + struct tegra_pcie_port *port; + int err; + + if (!soc->has_gen2 || of_find_property(np, "phys", NULL) != NULL) + return tegra_pcie_phys_get_legacy(pcie); + + list_for_each_entry(port, &pcie->ports, list) { + err = tegra_pcie_port_get_phys(port); + if (err < 0) + return err; + } + + return 0; +} + +static void tegra_pcie_phys_put(struct tegra_pcie *pcie) +{ + struct tegra_pcie_port *port; + struct device *dev = pcie->dev; + int err, i; + + if (pcie->legacy_phy) { + err = phy_exit(pcie->phy); + if (err < 0) + dev_err(dev, "failed to teardown PHY: %d\n", err); + return; + } + + list_for_each_entry(port, &pcie->ports, list) { + for (i = 0; i < port->lanes; i++) { + err = phy_exit(port->phys[i]); + if (err < 0) + dev_err(dev, "failed to teardown PHY#%u: %d\n", + i, err); + } + } +} + +static int tegra_pcie_get_resources(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + struct resource *res; + const struct tegra_pcie_soc *soc = pcie->soc; + int err; + + err = tegra_pcie_clocks_get(pcie); + if (err) { + dev_err(dev, "failed to get clocks: %d\n", err); + return err; + } + + err = tegra_pcie_resets_get(pcie); + if (err) { + dev_err(dev, "failed to get resets: %d\n", err); + return err; + } + + if (soc->program_uphy) { + err = tegra_pcie_phys_get(pcie); + if (err < 0) { + dev_err(dev, "failed to get PHYs: %d\n", err); + return err; + } + } + + pcie->pads = devm_platform_ioremap_resource_byname(pdev, "pads"); + if (IS_ERR(pcie->pads)) { + err = PTR_ERR(pcie->pads); + goto phys_put; + } + + pcie->afi = devm_platform_ioremap_resource_byname(pdev, "afi"); + if (IS_ERR(pcie->afi)) { + err = PTR_ERR(pcie->afi); + goto phys_put; + } + + /* request configuration space, but remap later, on demand */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cs"); + if (!res) { + err = -EADDRNOTAVAIL; + goto phys_put; + } + + pcie->cs = *res; + + /* constrain configuration space to 4 KiB */ + pcie->cs.end = pcie->cs.start + SZ_4K - 1; + + pcie->cfg = devm_ioremap_resource(dev, &pcie->cs); + if (IS_ERR(pcie->cfg)) { + err = PTR_ERR(pcie->cfg); + goto phys_put; + } + + /* request interrupt */ + err = platform_get_irq_byname(pdev, "intr"); + if (err < 0) + goto phys_put; + + pcie->irq = err; + + err = request_irq(pcie->irq, tegra_pcie_isr, IRQF_SHARED, "PCIE", pcie); + if (err) { + dev_err(dev, "failed to register IRQ: %d\n", err); + goto phys_put; + } + + return 0; + +phys_put: + if (soc->program_uphy) + tegra_pcie_phys_put(pcie); + + return err; +} + +static int tegra_pcie_put_resources(struct tegra_pcie *pcie) +{ + const struct tegra_pcie_soc *soc = pcie->soc; + + if (pcie->irq > 0) + free_irq(pcie->irq, pcie); + + if (soc->program_uphy) + tegra_pcie_phys_put(pcie); + + return 0; +} + +static void tegra_pcie_pme_turnoff(struct tegra_pcie_port *port) +{ + struct tegra_pcie *pcie = port->pcie; + const struct tegra_pcie_soc *soc = pcie->soc; + int err; + u32 val; + u8 ack_bit; + + val = afi_readl(pcie, AFI_PCIE_PME); + val |= (0x1 << soc->ports[port->index].pme.turnoff_bit); + afi_writel(pcie, val, AFI_PCIE_PME); + + ack_bit = soc->ports[port->index].pme.ack_bit; + err = readl_poll_timeout(pcie->afi + AFI_PCIE_PME, val, + val & (0x1 << ack_bit), 1, PME_ACK_TIMEOUT); + if (err) + dev_err(pcie->dev, "PME Ack is not received on port: %d\n", + port->index); + + usleep_range(10000, 11000); + + val = afi_readl(pcie, AFI_PCIE_PME); + val &= ~(0x1 << soc->ports[port->index].pme.turnoff_bit); + afi_writel(pcie, val, AFI_PCIE_PME); +} + +static void tegra_pcie_msi_irq(struct irq_desc *desc) +{ + struct tegra_pcie *pcie = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + struct tegra_msi *msi = &pcie->msi; + struct device *dev = pcie->dev; + unsigned int i; + + chained_irq_enter(chip, desc); + + for (i = 0; i < 8; i++) { + unsigned long reg = afi_readl(pcie, AFI_MSI_VEC(i)); + + while (reg) { + unsigned int offset = find_first_bit(®, 32); + unsigned int index = i * 32 + offset; + int ret; + + ret = generic_handle_domain_irq(msi->domain->parent, index); + if (ret) { + /* + * that's weird who triggered this? + * just clear it + */ + dev_info(dev, "unexpected MSI\n"); + afi_writel(pcie, BIT(index % 32), AFI_MSI_VEC(index)); + } + + /* see if there's any more pending in this vector */ + reg = afi_readl(pcie, AFI_MSI_VEC(i)); + } + } + + chained_irq_exit(chip, desc); +} + +static void tegra_msi_top_irq_ack(struct irq_data *d) +{ + irq_chip_ack_parent(d); +} + +static void tegra_msi_top_irq_mask(struct irq_data *d) +{ + pci_msi_mask_irq(d); + irq_chip_mask_parent(d); +} + +static void tegra_msi_top_irq_unmask(struct irq_data *d) +{ + pci_msi_unmask_irq(d); + irq_chip_unmask_parent(d); +} + +static struct irq_chip tegra_msi_top_chip = { + .name = "Tegra PCIe MSI", + .irq_ack = tegra_msi_top_irq_ack, + .irq_mask = tegra_msi_top_irq_mask, + .irq_unmask = tegra_msi_top_irq_unmask, +}; + +static void tegra_msi_irq_ack(struct irq_data *d) +{ + struct tegra_msi *msi = irq_data_get_irq_chip_data(d); + struct tegra_pcie *pcie = msi_to_pcie(msi); + unsigned int index = d->hwirq / 32; + + /* clear the interrupt */ + afi_writel(pcie, BIT(d->hwirq % 32), AFI_MSI_VEC(index)); +} + +static void tegra_msi_irq_mask(struct irq_data *d) +{ + struct tegra_msi *msi = irq_data_get_irq_chip_data(d); + struct tegra_pcie *pcie = msi_to_pcie(msi); + unsigned int index = d->hwirq / 32; + unsigned long flags; + u32 value; + + spin_lock_irqsave(&msi->mask_lock, flags); + value = afi_readl(pcie, AFI_MSI_EN_VEC(index)); + value &= ~BIT(d->hwirq % 32); + afi_writel(pcie, value, AFI_MSI_EN_VEC(index)); + spin_unlock_irqrestore(&msi->mask_lock, flags); +} + +static void tegra_msi_irq_unmask(struct irq_data *d) +{ + struct tegra_msi *msi = irq_data_get_irq_chip_data(d); + struct tegra_pcie *pcie = msi_to_pcie(msi); + unsigned int index = d->hwirq / 32; + unsigned long flags; + u32 value; + + spin_lock_irqsave(&msi->mask_lock, flags); + value = afi_readl(pcie, AFI_MSI_EN_VEC(index)); + value |= BIT(d->hwirq % 32); + afi_writel(pcie, value, AFI_MSI_EN_VEC(index)); + spin_unlock_irqrestore(&msi->mask_lock, flags); +} + +static int tegra_msi_set_affinity(struct irq_data *d, const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static void tegra_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct tegra_msi *msi = irq_data_get_irq_chip_data(data); + + msg->address_lo = lower_32_bits(msi->phys); + msg->address_hi = upper_32_bits(msi->phys); + msg->data = data->hwirq; +} + +static struct irq_chip tegra_msi_bottom_chip = { + .name = "Tegra MSI", + .irq_ack = tegra_msi_irq_ack, + .irq_mask = tegra_msi_irq_mask, + .irq_unmask = tegra_msi_irq_unmask, + .irq_set_affinity = tegra_msi_set_affinity, + .irq_compose_msi_msg = tegra_compose_msi_msg, +}; + +static int tegra_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct tegra_msi *msi = domain->host_data; + unsigned int i; + int hwirq; + + mutex_lock(&msi->map_lock); + + hwirq = bitmap_find_free_region(msi->used, INT_PCI_MSI_NR, order_base_2(nr_irqs)); + + mutex_unlock(&msi->map_lock); + + if (hwirq < 0) + return -ENOSPC; + + for (i = 0; i < nr_irqs; i++) + irq_domain_set_info(domain, virq + i, hwirq + i, + &tegra_msi_bottom_chip, domain->host_data, + handle_edge_irq, NULL, NULL); + + tegra_cpuidle_pcie_irqs_in_use(); + + return 0; +} + +static void tegra_msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct tegra_msi *msi = domain->host_data; + + mutex_lock(&msi->map_lock); + + bitmap_release_region(msi->used, d->hwirq, order_base_2(nr_irqs)); + + mutex_unlock(&msi->map_lock); +} + +static const struct irq_domain_ops tegra_msi_domain_ops = { + .alloc = tegra_msi_domain_alloc, + .free = tegra_msi_domain_free, +}; + +static struct msi_domain_info tegra_msi_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX), + .chip = &tegra_msi_top_chip, +}; + +static int tegra_allocate_domains(struct tegra_msi *msi) +{ + struct tegra_pcie *pcie = msi_to_pcie(msi); + struct fwnode_handle *fwnode = dev_fwnode(pcie->dev); + struct irq_domain *parent; + + parent = irq_domain_create_linear(fwnode, INT_PCI_MSI_NR, + &tegra_msi_domain_ops, msi); + if (!parent) { + dev_err(pcie->dev, "failed to create IRQ domain\n"); + return -ENOMEM; + } + irq_domain_update_bus_token(parent, DOMAIN_BUS_NEXUS); + + msi->domain = pci_msi_create_irq_domain(fwnode, &tegra_msi_info, parent); + if (!msi->domain) { + dev_err(pcie->dev, "failed to create MSI domain\n"); + irq_domain_remove(parent); + return -ENOMEM; + } + + return 0; +} + +static void tegra_free_domains(struct tegra_msi *msi) +{ + struct irq_domain *parent = msi->domain->parent; + + irq_domain_remove(msi->domain); + irq_domain_remove(parent); +} + +static int tegra_pcie_msi_setup(struct tegra_pcie *pcie) +{ + struct platform_device *pdev = to_platform_device(pcie->dev); + struct tegra_msi *msi = &pcie->msi; + struct device *dev = pcie->dev; + int err; + + mutex_init(&msi->map_lock); + spin_lock_init(&msi->mask_lock); + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + err = tegra_allocate_domains(msi); + if (err) + return err; + } + + err = platform_get_irq_byname(pdev, "msi"); + if (err < 0) + goto free_irq_domain; + + msi->irq = err; + + irq_set_chained_handler_and_data(msi->irq, tegra_pcie_msi_irq, pcie); + + /* Though the PCIe controller can address >32-bit address space, to + * facilitate endpoints that support only 32-bit MSI target address, + * the mask is set to 32-bit to make sure that MSI target address is + * always a 32-bit address + */ + err = dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); + if (err < 0) { + dev_err(dev, "failed to set DMA coherent mask: %d\n", err); + goto free_irq; + } + + msi->virt = dma_alloc_attrs(dev, PAGE_SIZE, &msi->phys, GFP_KERNEL, + DMA_ATTR_NO_KERNEL_MAPPING); + if (!msi->virt) { + dev_err(dev, "failed to allocate DMA memory for MSI\n"); + err = -ENOMEM; + goto free_irq; + } + + return 0; + +free_irq: + irq_set_chained_handler_and_data(msi->irq, NULL, NULL); +free_irq_domain: + if (IS_ENABLED(CONFIG_PCI_MSI)) + tegra_free_domains(msi); + + return err; +} + +static void tegra_pcie_enable_msi(struct tegra_pcie *pcie) +{ + const struct tegra_pcie_soc *soc = pcie->soc; + struct tegra_msi *msi = &pcie->msi; + u32 reg, msi_state[INT_PCI_MSI_NR / 32]; + int i; + + afi_writel(pcie, msi->phys >> soc->msi_base_shift, AFI_MSI_FPCI_BAR_ST); + afi_writel(pcie, msi->phys, AFI_MSI_AXI_BAR_ST); + /* this register is in 4K increments */ + afi_writel(pcie, 1, AFI_MSI_BAR_SZ); + + /* Restore the MSI allocation state */ + bitmap_to_arr32(msi_state, msi->used, INT_PCI_MSI_NR); + for (i = 0; i < ARRAY_SIZE(msi_state); i++) + afi_writel(pcie, msi_state[i], AFI_MSI_EN_VEC(i)); + + /* and unmask the MSI interrupt */ + reg = afi_readl(pcie, AFI_INTR_MASK); + reg |= AFI_INTR_MASK_MSI_MASK; + afi_writel(pcie, reg, AFI_INTR_MASK); +} + +static void tegra_pcie_msi_teardown(struct tegra_pcie *pcie) +{ + struct tegra_msi *msi = &pcie->msi; + unsigned int i, irq; + + dma_free_attrs(pcie->dev, PAGE_SIZE, msi->virt, msi->phys, + DMA_ATTR_NO_KERNEL_MAPPING); + + for (i = 0; i < INT_PCI_MSI_NR; i++) { + irq = irq_find_mapping(msi->domain, i); + if (irq > 0) + irq_domain_free_irqs(irq, 1); + } + + irq_set_chained_handler_and_data(msi->irq, NULL, NULL); + + if (IS_ENABLED(CONFIG_PCI_MSI)) + tegra_free_domains(msi); +} + +static int tegra_pcie_disable_msi(struct tegra_pcie *pcie) +{ + u32 value; + + /* mask the MSI interrupt */ + value = afi_readl(pcie, AFI_INTR_MASK); + value &= ~AFI_INTR_MASK_MSI_MASK; + afi_writel(pcie, value, AFI_INTR_MASK); + + return 0; +} + +static void tegra_pcie_disable_interrupts(struct tegra_pcie *pcie) +{ + u32 value; + + value = afi_readl(pcie, AFI_INTR_MASK); + value &= ~AFI_INTR_MASK_INT_MASK; + afi_writel(pcie, value, AFI_INTR_MASK); +} + +static int tegra_pcie_get_xbar_config(struct tegra_pcie *pcie, u32 lanes, + u32 *xbar) +{ + struct device *dev = pcie->dev; + struct device_node *np = dev->of_node; + + if (of_device_is_compatible(np, "nvidia,tegra186-pcie")) { + switch (lanes) { + case 0x010004: + dev_info(dev, "4x1, 1x1 configuration\n"); + *xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_401; + return 0; + + case 0x010102: + dev_info(dev, "2x1, 1X1, 1x1 configuration\n"); + *xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_211; + return 0; + + case 0x010101: + dev_info(dev, "1x1, 1x1, 1x1 configuration\n"); + *xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_111; + return 0; + + default: + dev_info(dev, "wrong configuration updated in DT, " + "switching to default 2x1, 1x1, 1x1 " + "configuration\n"); + *xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_211; + return 0; + } + } else if (of_device_is_compatible(np, "nvidia,tegra124-pcie") || + of_device_is_compatible(np, "nvidia,tegra210-pcie")) { + switch (lanes) { + case 0x0000104: + dev_info(dev, "4x1, 1x1 configuration\n"); + *xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_X4_X1; + return 0; + + case 0x0000102: + dev_info(dev, "2x1, 1x1 configuration\n"); + *xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_X2_X1; + return 0; + } + } else if (of_device_is_compatible(np, "nvidia,tegra30-pcie")) { + switch (lanes) { + case 0x00000204: + dev_info(dev, "4x1, 2x1 configuration\n"); + *xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_420; + return 0; + + case 0x00020202: + dev_info(dev, "2x3 configuration\n"); + *xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_222; + return 0; + + case 0x00010104: + dev_info(dev, "4x1, 1x2 configuration\n"); + *xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_411; + return 0; + } + } else if (of_device_is_compatible(np, "nvidia,tegra20-pcie")) { + switch (lanes) { + case 0x00000004: + dev_info(dev, "single-mode configuration\n"); + *xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_SINGLE; + return 0; + + case 0x00000202: + dev_info(dev, "dual-mode configuration\n"); + *xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_DUAL; + return 0; + } + } + + return -EINVAL; +} + +/* + * Check whether a given set of supplies is available in a device tree node. + * This is used to check whether the new or the legacy device tree bindings + * should be used. + */ +static bool of_regulator_bulk_available(struct device_node *np, + struct regulator_bulk_data *supplies, + unsigned int num_supplies) +{ + char property[32]; + unsigned int i; + + for (i = 0; i < num_supplies; i++) { + snprintf(property, 32, "%s-supply", supplies[i].supply); + + if (of_find_property(np, property, NULL) == NULL) + return false; + } + + return true; +} + +/* + * Old versions of the device tree binding for this device used a set of power + * supplies that didn't match the hardware inputs. This happened to work for a + * number of cases but is not future proof. However to preserve backwards- + * compatibility with old device trees, this function will try to use the old + * set of supplies. + */ +static int tegra_pcie_get_legacy_regulators(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct device_node *np = dev->of_node; + + if (of_device_is_compatible(np, "nvidia,tegra30-pcie")) + pcie->num_supplies = 3; + else if (of_device_is_compatible(np, "nvidia,tegra20-pcie")) + pcie->num_supplies = 2; + + if (pcie->num_supplies == 0) { + dev_err(dev, "device %pOF not supported in legacy mode\n", np); + return -ENODEV; + } + + pcie->supplies = devm_kcalloc(dev, pcie->num_supplies, + sizeof(*pcie->supplies), + GFP_KERNEL); + if (!pcie->supplies) + return -ENOMEM; + + pcie->supplies[0].supply = "pex-clk"; + pcie->supplies[1].supply = "vdd"; + + if (pcie->num_supplies > 2) + pcie->supplies[2].supply = "avdd"; + + return devm_regulator_bulk_get(dev, pcie->num_supplies, pcie->supplies); +} + +/* + * Obtains the list of regulators required for a particular generation of the + * IP block. + * + * This would've been nice to do simply by providing static tables for use + * with the regulator_bulk_*() API, but unfortunately Tegra30 is a bit quirky + * in that it has two pairs or AVDD_PEX and VDD_PEX supplies (PEXA and PEXB) + * and either seems to be optional depending on which ports are being used. + */ +static int tegra_pcie_get_regulators(struct tegra_pcie *pcie, u32 lane_mask) +{ + struct device *dev = pcie->dev; + struct device_node *np = dev->of_node; + unsigned int i = 0; + + if (of_device_is_compatible(np, "nvidia,tegra186-pcie")) { + pcie->num_supplies = 4; + + pcie->supplies = devm_kcalloc(pcie->dev, pcie->num_supplies, + sizeof(*pcie->supplies), + GFP_KERNEL); + if (!pcie->supplies) + return -ENOMEM; + + pcie->supplies[i++].supply = "dvdd-pex"; + pcie->supplies[i++].supply = "hvdd-pex-pll"; + pcie->supplies[i++].supply = "hvdd-pex"; + pcie->supplies[i++].supply = "vddio-pexctl-aud"; + } else if (of_device_is_compatible(np, "nvidia,tegra210-pcie")) { + pcie->num_supplies = 3; + + pcie->supplies = devm_kcalloc(pcie->dev, pcie->num_supplies, + sizeof(*pcie->supplies), + GFP_KERNEL); + if (!pcie->supplies) + return -ENOMEM; + + pcie->supplies[i++].supply = "hvddio-pex"; + pcie->supplies[i++].supply = "dvddio-pex"; + pcie->supplies[i++].supply = "vddio-pex-ctl"; + } else if (of_device_is_compatible(np, "nvidia,tegra124-pcie")) { + pcie->num_supplies = 4; + + pcie->supplies = devm_kcalloc(dev, pcie->num_supplies, + sizeof(*pcie->supplies), + GFP_KERNEL); + if (!pcie->supplies) + return -ENOMEM; + + pcie->supplies[i++].supply = "avddio-pex"; + pcie->supplies[i++].supply = "dvddio-pex"; + pcie->supplies[i++].supply = "hvdd-pex"; + pcie->supplies[i++].supply = "vddio-pex-ctl"; + } else if (of_device_is_compatible(np, "nvidia,tegra30-pcie")) { + bool need_pexa = false, need_pexb = false; + + /* VDD_PEXA and AVDD_PEXA supply lanes 0 to 3 */ + if (lane_mask & 0x0f) + need_pexa = true; + + /* VDD_PEXB and AVDD_PEXB supply lanes 4 to 5 */ + if (lane_mask & 0x30) + need_pexb = true; + + pcie->num_supplies = 4 + (need_pexa ? 2 : 0) + + (need_pexb ? 2 : 0); + + pcie->supplies = devm_kcalloc(dev, pcie->num_supplies, + sizeof(*pcie->supplies), + GFP_KERNEL); + if (!pcie->supplies) + return -ENOMEM; + + pcie->supplies[i++].supply = "avdd-pex-pll"; + pcie->supplies[i++].supply = "hvdd-pex"; + pcie->supplies[i++].supply = "vddio-pex-ctl"; + pcie->supplies[i++].supply = "avdd-plle"; + + if (need_pexa) { + pcie->supplies[i++].supply = "avdd-pexa"; + pcie->supplies[i++].supply = "vdd-pexa"; + } + + if (need_pexb) { + pcie->supplies[i++].supply = "avdd-pexb"; + pcie->supplies[i++].supply = "vdd-pexb"; + } + } else if (of_device_is_compatible(np, "nvidia,tegra20-pcie")) { + pcie->num_supplies = 5; + + pcie->supplies = devm_kcalloc(dev, pcie->num_supplies, + sizeof(*pcie->supplies), + GFP_KERNEL); + if (!pcie->supplies) + return -ENOMEM; + + pcie->supplies[0].supply = "avdd-pex"; + pcie->supplies[1].supply = "vdd-pex"; + pcie->supplies[2].supply = "avdd-pex-pll"; + pcie->supplies[3].supply = "avdd-plle"; + pcie->supplies[4].supply = "vddio-pex-clk"; + } + + if (of_regulator_bulk_available(dev->of_node, pcie->supplies, + pcie->num_supplies)) + return devm_regulator_bulk_get(dev, pcie->num_supplies, + pcie->supplies); + + /* + * If not all regulators are available for this new scheme, assume + * that the device tree complies with an older version of the device + * tree binding. + */ + dev_info(dev, "using legacy DT binding for power supplies\n"); + + devm_kfree(dev, pcie->supplies); + pcie->num_supplies = 0; + + return tegra_pcie_get_legacy_regulators(pcie); +} + +static int tegra_pcie_parse_dt(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct device_node *np = dev->of_node, *port; + const struct tegra_pcie_soc *soc = pcie->soc; + u32 lanes = 0, mask = 0; + unsigned int lane = 0; + int err; + + /* parse root ports */ + for_each_child_of_node(np, port) { + struct tegra_pcie_port *rp; + unsigned int index; + u32 value; + char *label; + + err = of_pci_get_devfn(port); + if (err < 0) { + dev_err(dev, "failed to parse address: %d\n", err); + goto err_node_put; + } + + index = PCI_SLOT(err); + + if (index < 1 || index > soc->num_ports) { + dev_err(dev, "invalid port number: %d\n", index); + err = -EINVAL; + goto err_node_put; + } + + index--; + + err = of_property_read_u32(port, "nvidia,num-lanes", &value); + if (err < 0) { + dev_err(dev, "failed to parse # of lanes: %d\n", + err); + goto err_node_put; + } + + if (value > 16) { + dev_err(dev, "invalid # of lanes: %u\n", value); + err = -EINVAL; + goto err_node_put; + } + + lanes |= value << (index << 3); + + if (!of_device_is_available(port)) { + lane += value; + continue; + } + + mask |= ((1 << value) - 1) << lane; + lane += value; + + rp = devm_kzalloc(dev, sizeof(*rp), GFP_KERNEL); + if (!rp) { + err = -ENOMEM; + goto err_node_put; + } + + err = of_address_to_resource(port, 0, &rp->regs); + if (err < 0) { + dev_err(dev, "failed to parse address: %d\n", err); + goto err_node_put; + } + + INIT_LIST_HEAD(&rp->list); + rp->index = index; + rp->lanes = value; + rp->pcie = pcie; + rp->np = port; + + rp->base = devm_pci_remap_cfg_resource(dev, &rp->regs); + if (IS_ERR(rp->base)) { + err = PTR_ERR(rp->base); + goto err_node_put; + } + + label = devm_kasprintf(dev, GFP_KERNEL, "pex-reset-%u", index); + if (!label) { + err = -ENOMEM; + goto err_node_put; + } + + /* + * Returns -ENOENT if reset-gpios property is not populated + * and in this case fall back to using AFI per port register + * to toggle PERST# SFIO line. + */ + rp->reset_gpio = devm_gpiod_get_from_of_node(dev, port, + "reset-gpios", 0, + GPIOD_OUT_LOW, + label); + if (IS_ERR(rp->reset_gpio)) { + if (PTR_ERR(rp->reset_gpio) == -ENOENT) { + rp->reset_gpio = NULL; + } else { + dev_err(dev, "failed to get reset GPIO: %ld\n", + PTR_ERR(rp->reset_gpio)); + err = PTR_ERR(rp->reset_gpio); + goto err_node_put; + } + } + + list_add_tail(&rp->list, &pcie->ports); + } + + err = tegra_pcie_get_xbar_config(pcie, lanes, &pcie->xbar_config); + if (err < 0) { + dev_err(dev, "invalid lane configuration\n"); + return err; + } + + err = tegra_pcie_get_regulators(pcie, mask); + if (err < 0) + return err; + + return 0; + +err_node_put: + of_node_put(port); + return err; +} + +/* + * FIXME: If there are no PCIe cards attached, then calling this function + * can result in the increase of the bootup time as there are big timeout + * loops. + */ +#define TEGRA_PCIE_LINKUP_TIMEOUT 200 /* up to 1.2 seconds */ +static bool tegra_pcie_port_check_link(struct tegra_pcie_port *port) +{ + struct device *dev = port->pcie->dev; + unsigned int retries = 3; + unsigned long value; + + /* override presence detection */ + value = readl(port->base + RP_PRIV_MISC); + value &= ~RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT; + value |= RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT; + writel(value, port->base + RP_PRIV_MISC); + + do { + unsigned int timeout = TEGRA_PCIE_LINKUP_TIMEOUT; + + do { + value = readl(port->base + RP_VEND_XP); + + if (value & RP_VEND_XP_DL_UP) + break; + + usleep_range(1000, 2000); + } while (--timeout); + + if (!timeout) { + dev_dbg(dev, "link %u down, retrying\n", port->index); + goto retry; + } + + timeout = TEGRA_PCIE_LINKUP_TIMEOUT; + + do { + value = readl(port->base + RP_LINK_CONTROL_STATUS); + + if (value & RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE) + return true; + + usleep_range(1000, 2000); + } while (--timeout); + +retry: + tegra_pcie_port_reset(port); + } while (--retries); + + return false; +} + +static void tegra_pcie_change_link_speed(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct tegra_pcie_port *port; + ktime_t deadline; + u32 value; + + list_for_each_entry(port, &pcie->ports, list) { + /* + * "Supported Link Speeds Vector" in "Link Capabilities 2" + * is not supported by Tegra. tegra_pcie_change_link_speed() + * is called only for Tegra chips which support Gen2. + * So there no harm if supported link speed is not verified. + */ + value = readl(port->base + RP_LINK_CONTROL_STATUS_2); + value &= ~PCI_EXP_LNKSTA_CLS; + value |= PCI_EXP_LNKSTA_CLS_5_0GB; + writel(value, port->base + RP_LINK_CONTROL_STATUS_2); + + /* + * Poll until link comes back from recovery to avoid race + * condition. + */ + deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT); + + while (ktime_before(ktime_get(), deadline)) { + value = readl(port->base + RP_LINK_CONTROL_STATUS); + if ((value & PCI_EXP_LNKSTA_LT) == 0) + break; + + usleep_range(2000, 3000); + } + + if (value & PCI_EXP_LNKSTA_LT) + dev_warn(dev, "PCIe port %u link is in recovery\n", + port->index); + + /* Retrain the link */ + value = readl(port->base + RP_LINK_CONTROL_STATUS); + value |= PCI_EXP_LNKCTL_RL; + writel(value, port->base + RP_LINK_CONTROL_STATUS); + + deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT); + + while (ktime_before(ktime_get(), deadline)) { + value = readl(port->base + RP_LINK_CONTROL_STATUS); + if ((value & PCI_EXP_LNKSTA_LT) == 0) + break; + + usleep_range(2000, 3000); + } + + if (value & PCI_EXP_LNKSTA_LT) + dev_err(dev, "failed to retrain link of port %u\n", + port->index); + } +} + +static void tegra_pcie_enable_ports(struct tegra_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct tegra_pcie_port *port, *tmp; + + list_for_each_entry_safe(port, tmp, &pcie->ports, list) { + dev_info(dev, "probing port %u, using %u lanes\n", + port->index, port->lanes); + + tegra_pcie_port_enable(port); + } + + /* Start LTSSM from Tegra side */ + reset_control_deassert(pcie->pcie_xrst); + + list_for_each_entry_safe(port, tmp, &pcie->ports, list) { + if (tegra_pcie_port_check_link(port)) + continue; + + dev_info(dev, "link %u down, ignoring\n", port->index); + + tegra_pcie_port_disable(port); + tegra_pcie_port_free(port); + } + + if (pcie->soc->has_gen2) + tegra_pcie_change_link_speed(pcie); +} + +static void tegra_pcie_disable_ports(struct tegra_pcie *pcie) +{ + struct tegra_pcie_port *port, *tmp; + + reset_control_assert(pcie->pcie_xrst); + + list_for_each_entry_safe(port, tmp, &pcie->ports, list) + tegra_pcie_port_disable(port); +} + +static const struct tegra_pcie_port_soc tegra20_pcie_ports[] = { + { .pme.turnoff_bit = 0, .pme.ack_bit = 5 }, + { .pme.turnoff_bit = 8, .pme.ack_bit = 10 }, +}; + +static const struct tegra_pcie_soc tegra20_pcie = { + .num_ports = 2, + .ports = tegra20_pcie_ports, + .msi_base_shift = 0, + .pads_pll_ctl = PADS_PLL_CTL_TEGRA20, + .tx_ref_sel = PADS_PLL_CTL_TXCLKREF_DIV10, + .pads_refclk_cfg0 = 0xfa5cfa5c, + .has_pex_clkreq_en = false, + .has_pex_bias_ctrl = false, + .has_intr_prsnt_sense = false, + .has_cml_clk = false, + .has_gen2 = false, + .force_pca_enable = false, + .program_uphy = true, + .update_clamp_threshold = false, + .program_deskew_time = false, + .update_fc_timer = false, + .has_cache_bars = true, + .ectl.enable = false, +}; + +static const struct tegra_pcie_port_soc tegra30_pcie_ports[] = { + { .pme.turnoff_bit = 0, .pme.ack_bit = 5 }, + { .pme.turnoff_bit = 8, .pme.ack_bit = 10 }, + { .pme.turnoff_bit = 16, .pme.ack_bit = 18 }, +}; + +static const struct tegra_pcie_soc tegra30_pcie = { + .num_ports = 3, + .ports = tegra30_pcie_ports, + .msi_base_shift = 8, + .afi_pex2_ctrl = 0x128, + .pads_pll_ctl = PADS_PLL_CTL_TEGRA30, + .tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN, + .pads_refclk_cfg0 = 0xfa5cfa5c, + .pads_refclk_cfg1 = 0xfa5cfa5c, + .has_pex_clkreq_en = true, + .has_pex_bias_ctrl = true, + .has_intr_prsnt_sense = true, + .has_cml_clk = true, + .has_gen2 = false, + .force_pca_enable = false, + .program_uphy = true, + .update_clamp_threshold = false, + .program_deskew_time = false, + .update_fc_timer = false, + .has_cache_bars = false, + .ectl.enable = false, +}; + +static const struct tegra_pcie_soc tegra124_pcie = { + .num_ports = 2, + .ports = tegra20_pcie_ports, + .msi_base_shift = 8, + .pads_pll_ctl = PADS_PLL_CTL_TEGRA30, + .tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN, + .pads_refclk_cfg0 = 0x44ac44ac, + .has_pex_clkreq_en = true, + .has_pex_bias_ctrl = true, + .has_intr_prsnt_sense = true, + .has_cml_clk = true, + .has_gen2 = true, + .force_pca_enable = false, + .program_uphy = true, + .update_clamp_threshold = true, + .program_deskew_time = false, + .update_fc_timer = false, + .has_cache_bars = false, + .ectl.enable = false, +}; + +static const struct tegra_pcie_soc tegra210_pcie = { + .num_ports = 2, + .ports = tegra20_pcie_ports, + .msi_base_shift = 8, + .pads_pll_ctl = PADS_PLL_CTL_TEGRA30, + .tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN, + .pads_refclk_cfg0 = 0x90b890b8, + /* FC threshold is bit[25:18] */ + .update_fc_threshold = 0x01800000, + .has_pex_clkreq_en = true, + .has_pex_bias_ctrl = true, + .has_intr_prsnt_sense = true, + .has_cml_clk = true, + .has_gen2 = true, + .force_pca_enable = true, + .program_uphy = true, + .update_clamp_threshold = true, + .program_deskew_time = true, + .update_fc_timer = true, + .has_cache_bars = false, + .ectl = { + .regs = { + .rp_ectl_2_r1 = 0x0000000f, + .rp_ectl_4_r1 = 0x00000067, + .rp_ectl_5_r1 = 0x55010000, + .rp_ectl_6_r1 = 0x00000001, + .rp_ectl_2_r2 = 0x0000008f, + .rp_ectl_4_r2 = 0x000000c7, + .rp_ectl_5_r2 = 0x55010000, + .rp_ectl_6_r2 = 0x00000001, + }, + .enable = true, + }, +}; + +static const struct tegra_pcie_port_soc tegra186_pcie_ports[] = { + { .pme.turnoff_bit = 0, .pme.ack_bit = 5 }, + { .pme.turnoff_bit = 8, .pme.ack_bit = 10 }, + { .pme.turnoff_bit = 12, .pme.ack_bit = 14 }, +}; + +static const struct tegra_pcie_soc tegra186_pcie = { + .num_ports = 3, + .ports = tegra186_pcie_ports, + .msi_base_shift = 8, + .afi_pex2_ctrl = 0x19c, + .pads_pll_ctl = PADS_PLL_CTL_TEGRA30, + .tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN, + .pads_refclk_cfg0 = 0x80b880b8, + .pads_refclk_cfg1 = 0x000480b8, + .has_pex_clkreq_en = true, + .has_pex_bias_ctrl = true, + .has_intr_prsnt_sense = true, + .has_cml_clk = false, + .has_gen2 = true, + .force_pca_enable = false, + .program_uphy = false, + .update_clamp_threshold = false, + .program_deskew_time = false, + .update_fc_timer = false, + .has_cache_bars = false, + .ectl.enable = false, +}; + +static const struct of_device_id tegra_pcie_of_match[] = { + { .compatible = "nvidia,tegra186-pcie", .data = &tegra186_pcie }, + { .compatible = "nvidia,tegra210-pcie", .data = &tegra210_pcie }, + { .compatible = "nvidia,tegra124-pcie", .data = &tegra124_pcie }, + { .compatible = "nvidia,tegra30-pcie", .data = &tegra30_pcie }, + { .compatible = "nvidia,tegra20-pcie", .data = &tegra20_pcie }, + { }, +}; +MODULE_DEVICE_TABLE(of, tegra_pcie_of_match); + +static void *tegra_pcie_ports_seq_start(struct seq_file *s, loff_t *pos) +{ + struct tegra_pcie *pcie = s->private; + + if (list_empty(&pcie->ports)) + return NULL; + + seq_puts(s, "Index Status\n"); + + return seq_list_start(&pcie->ports, *pos); +} + +static void *tegra_pcie_ports_seq_next(struct seq_file *s, void *v, loff_t *pos) +{ + struct tegra_pcie *pcie = s->private; + + return seq_list_next(v, &pcie->ports, pos); +} + +static void tegra_pcie_ports_seq_stop(struct seq_file *s, void *v) +{ +} + +static int tegra_pcie_ports_seq_show(struct seq_file *s, void *v) +{ + bool up = false, active = false; + struct tegra_pcie_port *port; + unsigned int value; + + port = list_entry(v, struct tegra_pcie_port, list); + + value = readl(port->base + RP_VEND_XP); + + if (value & RP_VEND_XP_DL_UP) + up = true; + + value = readl(port->base + RP_LINK_CONTROL_STATUS); + + if (value & RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE) + active = true; + + seq_printf(s, "%2u ", port->index); + + if (up) + seq_puts(s, "up"); + + if (active) { + if (up) + seq_puts(s, ", "); + + seq_puts(s, "active"); + } + + seq_puts(s, "\n"); + return 0; +} + +static const struct seq_operations tegra_pcie_ports_sops = { + .start = tegra_pcie_ports_seq_start, + .next = tegra_pcie_ports_seq_next, + .stop = tegra_pcie_ports_seq_stop, + .show = tegra_pcie_ports_seq_show, +}; + +DEFINE_SEQ_ATTRIBUTE(tegra_pcie_ports); + +static void tegra_pcie_debugfs_exit(struct tegra_pcie *pcie) +{ + debugfs_remove_recursive(pcie->debugfs); + pcie->debugfs = NULL; +} + +static void tegra_pcie_debugfs_init(struct tegra_pcie *pcie) +{ + pcie->debugfs = debugfs_create_dir("pcie", NULL); + + debugfs_create_file("ports", S_IFREG | S_IRUGO, pcie->debugfs, pcie, + &tegra_pcie_ports_fops); +} + +static int tegra_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct pci_host_bridge *host; + struct tegra_pcie *pcie; + int err; + + host = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!host) + return -ENOMEM; + + pcie = pci_host_bridge_priv(host); + host->sysdata = pcie; + platform_set_drvdata(pdev, pcie); + + pcie->soc = of_device_get_match_data(dev); + INIT_LIST_HEAD(&pcie->ports); + pcie->dev = dev; + + err = tegra_pcie_parse_dt(pcie); + if (err < 0) + return err; + + err = tegra_pcie_get_resources(pcie); + if (err < 0) { + dev_err(dev, "failed to request resources: %d\n", err); + return err; + } + + err = tegra_pcie_msi_setup(pcie); + if (err < 0) { + dev_err(dev, "failed to enable MSI support: %d\n", err); + goto put_resources; + } + + pm_runtime_enable(pcie->dev); + err = pm_runtime_get_sync(pcie->dev); + if (err < 0) { + dev_err(dev, "fail to enable pcie controller: %d\n", err); + goto pm_runtime_put; + } + + host->ops = &tegra_pcie_ops; + host->map_irq = tegra_pcie_map_irq; + + err = pci_host_probe(host); + if (err < 0) { + dev_err(dev, "failed to register host: %d\n", err); + goto pm_runtime_put; + } + + if (IS_ENABLED(CONFIG_DEBUG_FS)) + tegra_pcie_debugfs_init(pcie); + + return 0; + +pm_runtime_put: + pm_runtime_put_sync(pcie->dev); + pm_runtime_disable(pcie->dev); + tegra_pcie_msi_teardown(pcie); +put_resources: + tegra_pcie_put_resources(pcie); + return err; +} + +static int tegra_pcie_remove(struct platform_device *pdev) +{ + struct tegra_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + struct tegra_pcie_port *port, *tmp; + + if (IS_ENABLED(CONFIG_DEBUG_FS)) + tegra_pcie_debugfs_exit(pcie); + + pci_stop_root_bus(host->bus); + pci_remove_root_bus(host->bus); + pm_runtime_put_sync(pcie->dev); + pm_runtime_disable(pcie->dev); + + if (IS_ENABLED(CONFIG_PCI_MSI)) + tegra_pcie_msi_teardown(pcie); + + tegra_pcie_put_resources(pcie); + + list_for_each_entry_safe(port, tmp, &pcie->ports, list) + tegra_pcie_port_free(port); + + return 0; +} + +static int tegra_pcie_pm_suspend(struct device *dev) +{ + struct tegra_pcie *pcie = dev_get_drvdata(dev); + struct tegra_pcie_port *port; + int err; + + list_for_each_entry(port, &pcie->ports, list) + tegra_pcie_pme_turnoff(port); + + tegra_pcie_disable_ports(pcie); + + /* + * AFI_INTR is unmasked in tegra_pcie_enable_controller(), mask it to + * avoid unwanted interrupts raised by AFI after pex_rst is asserted. + */ + tegra_pcie_disable_interrupts(pcie); + + if (pcie->soc->program_uphy) { + err = tegra_pcie_phy_power_off(pcie); + if (err < 0) + dev_err(dev, "failed to power off PHY(s): %d\n", err); + } + + reset_control_assert(pcie->pex_rst); + clk_disable_unprepare(pcie->pex_clk); + + if (IS_ENABLED(CONFIG_PCI_MSI)) + tegra_pcie_disable_msi(pcie); + + pinctrl_pm_select_idle_state(dev); + tegra_pcie_power_off(pcie); + + return 0; +} + +static int tegra_pcie_pm_resume(struct device *dev) +{ + struct tegra_pcie *pcie = dev_get_drvdata(dev); + int err; + + err = tegra_pcie_power_on(pcie); + if (err) { + dev_err(dev, "tegra pcie power on fail: %d\n", err); + return err; + } + + err = pinctrl_pm_select_default_state(dev); + if (err < 0) { + dev_err(dev, "failed to disable PCIe IO DPD: %d\n", err); + goto poweroff; + } + + tegra_pcie_enable_controller(pcie); + tegra_pcie_setup_translations(pcie); + + if (IS_ENABLED(CONFIG_PCI_MSI)) + tegra_pcie_enable_msi(pcie); + + err = clk_prepare_enable(pcie->pex_clk); + if (err) { + dev_err(dev, "failed to enable PEX clock: %d\n", err); + goto pex_dpd_enable; + } + + reset_control_deassert(pcie->pex_rst); + + if (pcie->soc->program_uphy) { + err = tegra_pcie_phy_power_on(pcie); + if (err < 0) { + dev_err(dev, "failed to power on PHY(s): %d\n", err); + goto disable_pex_clk; + } + } + + tegra_pcie_apply_pad_settings(pcie); + tegra_pcie_enable_ports(pcie); + + return 0; + +disable_pex_clk: + reset_control_assert(pcie->pex_rst); + clk_disable_unprepare(pcie->pex_clk); +pex_dpd_enable: + pinctrl_pm_select_idle_state(dev); +poweroff: + tegra_pcie_power_off(pcie); + + return err; +} + +static const struct dev_pm_ops tegra_pcie_pm_ops = { + RUNTIME_PM_OPS(tegra_pcie_pm_suspend, tegra_pcie_pm_resume, NULL) + NOIRQ_SYSTEM_SLEEP_PM_OPS(tegra_pcie_pm_suspend, tegra_pcie_pm_resume) +}; + +static struct platform_driver tegra_pcie_driver = { + .driver = { + .name = "tegra-pcie", + .of_match_table = tegra_pcie_of_match, + .suppress_bind_attrs = true, + .pm = &tegra_pcie_pm_ops, + }, + .probe = tegra_pcie_probe, + .remove = tegra_pcie_remove, +}; +module_platform_driver(tegra_pcie_driver); +MODULE_LICENSE("GPL"); diff --git a/drivers/pci/controller/pci-thunder-ecam.c b/drivers/pci/controller/pci-thunder-ecam.c new file mode 100644 index 000000000..b5bd10a62 --- /dev/null +++ b/drivers/pci/controller/pci-thunder-ecam.c @@ -0,0 +1,363 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2015, 2016 Cavium, Inc. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/ioport.h> +#include <linux/of_pci.h> +#include <linux/of.h> +#include <linux/pci-ecam.h> +#include <linux/platform_device.h> + +#if defined(CONFIG_PCI_HOST_THUNDER_ECAM) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)) + +static void set_val(u32 v, int where, int size, u32 *val) +{ + int shift = (where & 3) * 8; + + pr_debug("set_val %04x: %08x\n", (unsigned int)(where & ~3), v); + v >>= shift; + if (size == 1) + v &= 0xff; + else if (size == 2) + v &= 0xffff; + *val = v; +} + +static int handle_ea_bar(u32 e0, int bar, struct pci_bus *bus, + unsigned int devfn, int where, int size, u32 *val) +{ + void __iomem *addr; + u32 v; + + /* Entries are 16-byte aligned; bits[2,3] select word in entry */ + int where_a = where & 0xc; + + if (where_a == 0) { + set_val(e0, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0x4) { + addr = bus->ops->map_bus(bus, devfn, bar); /* BAR 0 */ + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + v = readl(addr); + v &= ~0xf; + v |= 2; /* EA entry-1. Base-L */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0x8) { + u32 barl_orig; + u32 barl_rb; + + addr = bus->ops->map_bus(bus, devfn, bar); /* BAR 0 */ + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + barl_orig = readl(addr + 0); + writel(0xffffffff, addr + 0); + barl_rb = readl(addr + 0); + writel(barl_orig, addr + 0); + /* zeros in unsettable bits */ + v = ~barl_rb & ~3; + v |= 0xc; /* EA entry-2. Offset-L */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0xc) { + addr = bus->ops->map_bus(bus, devfn, bar + 4); /* BAR 1 */ + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + v = readl(addr); /* EA entry-3. Base-H */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + return PCIBIOS_DEVICE_NOT_FOUND; +} + +static int thunder_ecam_p2_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct pci_config_window *cfg = bus->sysdata; + int where_a = where & ~3; + void __iomem *addr; + u32 node_bits; + u32 v; + + /* EA Base[63:32] may be missing some bits ... */ + switch (where_a) { + case 0xa8: + case 0xbc: + case 0xd0: + case 0xe4: + break; + default: + return pci_generic_config_read(bus, devfn, where, size, val); + } + + addr = bus->ops->map_bus(bus, devfn, where_a); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + v = readl(addr); + + /* + * Bit 44 of the 64-bit Base must match the same bit in + * the config space access window. Since we are working with + * the high-order 32 bits, shift everything down by 32 bits. + */ + node_bits = upper_32_bits(cfg->res.start) & (1 << 12); + + v |= node_bits; + set_val(v, where, size, val); + + return PCIBIOS_SUCCESSFUL; +} + +static int thunder_ecam_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + u32 v; + u32 vendor_device; + u32 class_rev; + void __iomem *addr; + int cfg_type; + int where_a = where & ~3; + + addr = bus->ops->map_bus(bus, devfn, 0xc); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + v = readl(addr); + + /* Check for non type-00 header */ + cfg_type = (v >> 16) & 0x7f; + + addr = bus->ops->map_bus(bus, devfn, 8); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + class_rev = readl(addr); + if (class_rev == 0xffffffff) + goto no_emulation; + + if ((class_rev & 0xff) >= 8) { + /* Pass-2 handling */ + if (cfg_type) + goto no_emulation; + return thunder_ecam_p2_config_read(bus, devfn, where, + size, val); + } + + /* + * All BARs have fixed addresses specified by the EA + * capability; they must return zero on read. + */ + if (cfg_type == 0 && + ((where >= 0x10 && where < 0x2c) || + (where >= 0x1a4 && where < 0x1bc))) { + /* BAR or SR-IOV BAR */ + *val = 0; + return PCIBIOS_SUCCESSFUL; + } + + addr = bus->ops->map_bus(bus, devfn, 0); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + vendor_device = readl(addr); + if (vendor_device == 0xffffffff) + goto no_emulation; + + pr_debug("%04x:%04x - Fix pass#: %08x, where: %03x, devfn: %03x\n", + vendor_device & 0xffff, vendor_device >> 16, class_rev, + (unsigned int)where, devfn); + + /* Check for non type-00 header */ + if (cfg_type == 0) { + bool has_msix; + bool is_nic = (vendor_device == 0xa01e177d); + bool is_tns = (vendor_device == 0xa01f177d); + + addr = bus->ops->map_bus(bus, devfn, 0x70); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + /* E_CAP */ + v = readl(addr); + has_msix = (v & 0xff00) != 0; + + if (!has_msix && where_a == 0x70) { + v |= 0xbc00; /* next capability is EA at 0xbc */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0xb0) { + addr = bus->ops->map_bus(bus, devfn, where_a); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + v = readl(addr); + if (v & 0xff00) + pr_err("Bad MSIX cap header: %08x\n", v); + v |= 0xbc00; /* next capability is EA at 0xbc */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0xbc) { + if (is_nic) + v = 0x40014; /* EA last in chain, 4 entries */ + else if (is_tns) + v = 0x30014; /* EA last in chain, 3 entries */ + else if (has_msix) + v = 0x20014; /* EA last in chain, 2 entries */ + else + v = 0x10014; /* EA last in chain, 1 entry */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a >= 0xc0 && where_a < 0xd0) + /* EA entry-0. PP=0, BAR0 Size:3 */ + return handle_ea_bar(0x80ff0003, + 0x10, bus, devfn, where, + size, val); + if (where_a >= 0xd0 && where_a < 0xe0 && has_msix) + /* EA entry-1. PP=0, BAR4 Size:3 */ + return handle_ea_bar(0x80ff0043, + 0x20, bus, devfn, where, + size, val); + if (where_a >= 0xe0 && where_a < 0xf0 && is_tns) + /* EA entry-2. PP=0, BAR2, Size:3 */ + return handle_ea_bar(0x80ff0023, + 0x18, bus, devfn, where, + size, val); + if (where_a >= 0xe0 && where_a < 0xf0 && is_nic) + /* EA entry-2. PP=4, VF_BAR0 (9), Size:3 */ + return handle_ea_bar(0x80ff0493, + 0x1a4, bus, devfn, where, + size, val); + if (where_a >= 0xf0 && where_a < 0x100 && is_nic) + /* EA entry-3. PP=4, VF_BAR4 (d), Size:3 */ + return handle_ea_bar(0x80ff04d3, + 0x1b4, bus, devfn, where, + size, val); + } else if (cfg_type == 1) { + bool is_rsl_bridge = devfn == 0x08; + bool is_rad_bridge = devfn == 0xa0; + bool is_zip_bridge = devfn == 0xa8; + bool is_dfa_bridge = devfn == 0xb0; + bool is_nic_bridge = devfn == 0x10; + + if (where_a == 0x70) { + addr = bus->ops->map_bus(bus, devfn, where_a); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + v = readl(addr); + if (v & 0xff00) + pr_err("Bad PCIe cap header: %08x\n", v); + v |= 0xbc00; /* next capability is EA at 0xbc */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0xbc) { + if (is_nic_bridge) + v = 0x10014; /* EA last in chain, 1 entry */ + else + v = 0x00014; /* EA last in chain, no entries */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0xc0) { + if (is_rsl_bridge || is_nic_bridge) + v = 0x0101; /* subordinate:secondary = 1:1 */ + else if (is_rad_bridge) + v = 0x0202; /* subordinate:secondary = 2:2 */ + else if (is_zip_bridge) + v = 0x0303; /* subordinate:secondary = 3:3 */ + else if (is_dfa_bridge) + v = 0x0404; /* subordinate:secondary = 4:4 */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0xc4 && is_nic_bridge) { + /* Enabled, not-Write, SP=ff, PP=05, BEI=6, ES=4 */ + v = 0x80ff0564; + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0xc8 && is_nic_bridge) { + v = 0x00000002; /* Base-L 64-bit */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0xcc && is_nic_bridge) { + v = 0xfffffffe; /* MaxOffset-L 64-bit */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0xd0 && is_nic_bridge) { + v = 0x00008430; /* NIC Base-H */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + if (where_a == 0xd4 && is_nic_bridge) { + v = 0x0000000f; /* MaxOffset-H */ + set_val(v, where, size, val); + return PCIBIOS_SUCCESSFUL; + } + } +no_emulation: + return pci_generic_config_read(bus, devfn, where, size, val); +} + +static int thunder_ecam_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + /* + * All BARs have fixed addresses; ignore BAR writes so they + * don't get corrupted. + */ + if ((where >= 0x10 && where < 0x2c) || + (where >= 0x1a4 && where < 0x1bc)) + /* BAR or SR-IOV BAR */ + return PCIBIOS_SUCCESSFUL; + + return pci_generic_config_write(bus, devfn, where, size, val); +} + +const struct pci_ecam_ops pci_thunder_ecam_ops = { + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = thunder_ecam_config_read, + .write = thunder_ecam_config_write, + } +}; + +#ifdef CONFIG_PCI_HOST_THUNDER_ECAM + +static const struct of_device_id thunder_ecam_of_match[] = { + { + .compatible = "cavium,pci-host-thunder-ecam", + .data = &pci_thunder_ecam_ops, + }, + { }, +}; + +static struct platform_driver thunder_ecam_driver = { + .driver = { + .name = KBUILD_MODNAME, + .of_match_table = thunder_ecam_of_match, + .suppress_bind_attrs = true, + }, + .probe = pci_host_common_probe, +}; +builtin_platform_driver(thunder_ecam_driver); + +#endif +#endif diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c new file mode 100644 index 000000000..06a9855cb --- /dev/null +++ b/drivers/pci/controller/pci-thunder-pem.c @@ -0,0 +1,480 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2015 - 2016 Cavium, Inc. + */ + +#include <linux/bitfield.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/pci.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> +#include <linux/platform_device.h> +#include <linux/io-64-nonatomic-lo-hi.h> +#include "../pci.h" + +#if defined(CONFIG_PCI_HOST_THUNDER_PEM) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)) + +#define PEM_CFG_WR 0x28 +#define PEM_CFG_RD 0x30 + +/* + * Enhanced Configuration Access Mechanism (ECAM) + * + * N.B. This is a non-standard platform-specific ECAM bus shift value. For + * standard values defined in the PCI Express Base Specification see + * include/linux/pci-ecam.h. + */ +#define THUNDER_PCIE_ECAM_BUS_SHIFT 24 + +struct thunder_pem_pci { + u32 ea_entry[3]; + void __iomem *pem_reg_base; +}; + +static int thunder_pem_bridge_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + u64 read_val, tmp_val; + struct pci_config_window *cfg = bus->sysdata; + struct thunder_pem_pci *pem_pci = (struct thunder_pem_pci *)cfg->priv; + + if (devfn != 0 || where >= 2048) + return PCIBIOS_DEVICE_NOT_FOUND; + + /* + * 32-bit accesses only. Write the address to the low order + * bits of PEM_CFG_RD, then trigger the read by reading back. + * The config data lands in the upper 32-bits of PEM_CFG_RD. + */ + read_val = where & ~3ull; + writeq(read_val, pem_pci->pem_reg_base + PEM_CFG_RD); + read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD); + read_val >>= 32; + + /* + * The config space contains some garbage, fix it up. Also + * synthesize an EA capability for the BAR used by MSI-X. + */ + switch (where & ~3) { + case 0x40: + read_val &= 0xffff00ff; + read_val |= 0x00007000; /* Skip MSI CAP */ + break; + case 0x70: /* Express Cap */ + /* + * Change PME interrupt to vector 2 on T88 where it + * reads as 0, else leave it alone. + */ + if (!(read_val & (0x1f << 25))) + read_val |= (2u << 25); + break; + case 0xb0: /* MSI-X Cap */ + /* TableSize=2 or 4, Next Cap is EA */ + read_val &= 0xc00000ff; + /* + * If Express Cap(0x70) raw PME vector reads as 0 we are on + * T88 and TableSize is reported as 4, else TableSize + * is 2. + */ + writeq(0x70, pem_pci->pem_reg_base + PEM_CFG_RD); + tmp_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD); + tmp_val >>= 32; + if (!(tmp_val & (0x1f << 25))) + read_val |= 0x0003bc00; + else + read_val |= 0x0001bc00; + break; + case 0xb4: + /* Table offset=0, BIR=0 */ + read_val = 0x00000000; + break; + case 0xb8: + /* BPA offset=0xf0000, BIR=0 */ + read_val = 0x000f0000; + break; + case 0xbc: + /* EA, 1 entry, no next Cap */ + read_val = 0x00010014; + break; + case 0xc0: + /* DW2 for type-1 */ + read_val = 0x00000000; + break; + case 0xc4: + /* Entry BEI=0, PP=0x00, SP=0xff, ES=3 */ + read_val = 0x80ff0003; + break; + case 0xc8: + read_val = pem_pci->ea_entry[0]; + break; + case 0xcc: + read_val = pem_pci->ea_entry[1]; + break; + case 0xd0: + read_val = pem_pci->ea_entry[2]; + break; + default: + break; + } + read_val >>= (8 * (where & 3)); + switch (size) { + case 1: + read_val &= 0xff; + break; + case 2: + read_val &= 0xffff; + break; + default: + break; + } + *val = read_val; + return PCIBIOS_SUCCESSFUL; +} + +static int thunder_pem_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct pci_config_window *cfg = bus->sysdata; + + if (bus->number < cfg->busr.start || + bus->number > cfg->busr.end) + return PCIBIOS_DEVICE_NOT_FOUND; + + /* + * The first device on the bus is the PEM PCIe bridge. + * Special case its config access. + */ + if (bus->number == cfg->busr.start) + return thunder_pem_bridge_read(bus, devfn, where, size, val); + + return pci_generic_config_read(bus, devfn, where, size, val); +} + +/* + * Some of the w1c_bits below also include read-only or non-writable + * reserved bits, this makes the code simpler and is OK as the bits + * are not affected by writing zeros to them. + */ +static u32 thunder_pem_bridge_w1c_bits(u64 where_aligned) +{ + u32 w1c_bits = 0; + + switch (where_aligned) { + case 0x04: /* Command/Status */ + case 0x1c: /* Base and I/O Limit/Secondary Status */ + w1c_bits = 0xff000000; + break; + case 0x44: /* Power Management Control and Status */ + w1c_bits = 0xfffffe00; + break; + case 0x78: /* Device Control/Device Status */ + case 0x80: /* Link Control/Link Status */ + case 0x88: /* Slot Control/Slot Status */ + case 0x90: /* Root Status */ + case 0xa0: /* Link Control 2 Registers/Link Status 2 */ + w1c_bits = 0xffff0000; + break; + case 0x104: /* Uncorrectable Error Status */ + case 0x110: /* Correctable Error Status */ + case 0x130: /* Error Status */ + case 0x160: /* Link Control 4 */ + w1c_bits = 0xffffffff; + break; + default: + break; + } + return w1c_bits; +} + +/* Some bits must be written to one so they appear to be read-only. */ +static u32 thunder_pem_bridge_w1_bits(u64 where_aligned) +{ + u32 w1_bits; + + switch (where_aligned) { + case 0x1c: /* I/O Base / I/O Limit, Secondary Status */ + /* Force 32-bit I/O addressing. */ + w1_bits = 0x0101; + break; + case 0x24: /* Prefetchable Memory Base / Prefetchable Memory Limit */ + /* Force 64-bit addressing */ + w1_bits = 0x00010001; + break; + default: + w1_bits = 0; + break; + } + return w1_bits; +} + +static int thunder_pem_bridge_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct pci_config_window *cfg = bus->sysdata; + struct thunder_pem_pci *pem_pci = (struct thunder_pem_pci *)cfg->priv; + u64 write_val, read_val; + u64 where_aligned = where & ~3ull; + u32 mask = 0; + + + if (devfn != 0 || where >= 2048) + return PCIBIOS_DEVICE_NOT_FOUND; + + /* + * 32-bit accesses only. If the write is for a size smaller + * than 32-bits, we must first read the 32-bit value and merge + * in the desired bits and then write the whole 32-bits back + * out. + */ + switch (size) { + case 1: + writeq(where_aligned, pem_pci->pem_reg_base + PEM_CFG_RD); + read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD); + read_val >>= 32; + mask = ~(0xff << (8 * (where & 3))); + read_val &= mask; + val = (val & 0xff) << (8 * (where & 3)); + val |= (u32)read_val; + break; + case 2: + writeq(where_aligned, pem_pci->pem_reg_base + PEM_CFG_RD); + read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD); + read_val >>= 32; + mask = ~(0xffff << (8 * (where & 3))); + read_val &= mask; + val = (val & 0xffff) << (8 * (where & 3)); + val |= (u32)read_val; + break; + default: + break; + } + + /* + * By expanding the write width to 32 bits, we may + * inadvertently hit some W1C bits that were not intended to + * be written. Calculate the mask that must be applied to the + * data to be written to avoid these cases. + */ + if (mask) { + u32 w1c_bits = thunder_pem_bridge_w1c_bits(where); + + if (w1c_bits) { + mask &= w1c_bits; + val &= ~mask; + } + } + + /* + * Some bits must be read-only with value of one. Since the + * access method allows these to be cleared if a zero is + * written, force them to one before writing. + */ + val |= thunder_pem_bridge_w1_bits(where_aligned); + + /* + * Low order bits are the config address, the high order 32 + * bits are the data to be written. + */ + write_val = (((u64)val) << 32) | where_aligned; + writeq(write_val, pem_pci->pem_reg_base + PEM_CFG_WR); + return PCIBIOS_SUCCESSFUL; +} + +static int thunder_pem_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct pci_config_window *cfg = bus->sysdata; + + if (bus->number < cfg->busr.start || + bus->number > cfg->busr.end) + return PCIBIOS_DEVICE_NOT_FOUND; + /* + * The first device on the bus is the PEM PCIe bridge. + * Special case its config access. + */ + if (bus->number == cfg->busr.start) + return thunder_pem_bridge_write(bus, devfn, where, size, val); + + + return pci_generic_config_write(bus, devfn, where, size, val); +} + +static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg, + struct resource *res_pem) +{ + struct thunder_pem_pci *pem_pci; + resource_size_t bar4_start; + + pem_pci = devm_kzalloc(dev, sizeof(*pem_pci), GFP_KERNEL); + if (!pem_pci) + return -ENOMEM; + + pem_pci->pem_reg_base = devm_ioremap(dev, res_pem->start, 0x10000); + if (!pem_pci->pem_reg_base) + return -ENOMEM; + + /* + * The MSI-X BAR for the PEM and AER interrupts is located at + * a fixed offset from the PEM register base. Generate a + * fragment of the synthesized Enhanced Allocation capability + * structure here for the BAR. + */ + bar4_start = res_pem->start + 0xf00000; + pem_pci->ea_entry[0] = lower_32_bits(bar4_start) | 2; + pem_pci->ea_entry[1] = lower_32_bits(res_pem->end - bar4_start) & ~3u; + pem_pci->ea_entry[2] = upper_32_bits(bar4_start); + + cfg->priv = pem_pci; + return 0; +} + +#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) + +#define PEM_RES_BASE 0x87e0c0000000ULL +#define PEM_NODE_MASK GENMASK_ULL(45, 44) +#define PEM_INDX_MASK GENMASK_ULL(26, 24) +#define PEM_MIN_DOM_IN_NODE 4 +#define PEM_MAX_DOM_IN_NODE 10 + +static void thunder_pem_reserve_range(struct device *dev, int seg, + struct resource *r) +{ + resource_size_t start = r->start, end = r->end; + struct resource *res; + const char *regionid; + + regionid = kasprintf(GFP_KERNEL, "PEM RC:%d", seg); + if (!regionid) + return; + + res = request_mem_region(start, end - start + 1, regionid); + if (res) + res->flags &= ~IORESOURCE_BUSY; + else + kfree(regionid); + + dev_info(dev, "%pR %s reserved\n", r, + res ? "has been" : "could not be"); +} + +static void thunder_pem_legacy_fw(struct acpi_pci_root *root, + struct resource *res_pem) +{ + int node = acpi_get_node(root->device->handle); + int index; + + if (node == NUMA_NO_NODE) + node = 0; + + index = root->segment - PEM_MIN_DOM_IN_NODE; + index -= node * PEM_MAX_DOM_IN_NODE; + res_pem->start = PEM_RES_BASE | FIELD_PREP(PEM_NODE_MASK, node) | + FIELD_PREP(PEM_INDX_MASK, index); + res_pem->flags = IORESOURCE_MEM; +} + +static int thunder_pem_acpi_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct acpi_device *adev = to_acpi_device(dev); + struct acpi_pci_root *root = acpi_driver_data(adev); + struct resource *res_pem; + int ret; + + res_pem = devm_kzalloc(&adev->dev, sizeof(*res_pem), GFP_KERNEL); + if (!res_pem) + return -ENOMEM; + + ret = acpi_get_rc_resources(dev, "CAVA02B", root->segment, res_pem); + + /* + * If we fail to gather resources it means that we run with old + * FW where we need to calculate PEM-specific resources manually. + */ + if (ret) { + thunder_pem_legacy_fw(root, res_pem); + /* + * Reserve 64K size PEM specific resources. The full 16M range + * size is required for thunder_pem_init() call. + */ + res_pem->end = res_pem->start + SZ_64K - 1; + thunder_pem_reserve_range(dev, root->segment, res_pem); + res_pem->end = res_pem->start + SZ_16M - 1; + + /* Reserve PCI configuration space as well. */ + thunder_pem_reserve_range(dev, root->segment, &cfg->res); + } + + return thunder_pem_init(dev, cfg, res_pem); +} + +const struct pci_ecam_ops thunder_pem_ecam_ops = { + .bus_shift = THUNDER_PCIE_ECAM_BUS_SHIFT, + .init = thunder_pem_acpi_init, + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = thunder_pem_config_read, + .write = thunder_pem_config_write, + } +}; + +#endif + +#ifdef CONFIG_PCI_HOST_THUNDER_PEM + +static int thunder_pem_platform_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct platform_device *pdev = to_platform_device(dev); + struct resource *res_pem; + + if (!dev->of_node) + return -EINVAL; + + /* + * The second register range is the PEM bridge to the PCIe + * bus. It has a different config access method than those + * devices behind the bridge. + */ + res_pem = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (!res_pem) { + dev_err(dev, "missing \"reg[1]\"property\n"); + return -EINVAL; + } + + return thunder_pem_init(dev, cfg, res_pem); +} + +static const struct pci_ecam_ops pci_thunder_pem_ops = { + .bus_shift = THUNDER_PCIE_ECAM_BUS_SHIFT, + .init = thunder_pem_platform_init, + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = thunder_pem_config_read, + .write = thunder_pem_config_write, + } +}; + +static const struct of_device_id thunder_pem_of_match[] = { + { + .compatible = "cavium,pci-host-thunder-pem", + .data = &pci_thunder_pem_ops, + }, + { }, +}; + +static struct platform_driver thunder_pem_driver = { + .driver = { + .name = KBUILD_MODNAME, + .of_match_table = thunder_pem_of_match, + .suppress_bind_attrs = true, + }, + .probe = pci_host_common_probe, +}; +builtin_platform_driver(thunder_pem_driver); + +#endif +#endif diff --git a/drivers/pci/controller/pci-v3-semi.c b/drivers/pci/controller/pci-v3-semi.c new file mode 100644 index 000000000..154a53986 --- /dev/null +++ b/drivers/pci/controller/pci-v3-semi.c @@ -0,0 +1,910 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Support for V3 Semiconductor PCI Local Bus to PCI Bridge + * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org> + * + * Based on the code from arch/arm/mach-integrator/pci_v3.c + * Copyright (C) 1999 ARM Limited + * Copyright (C) 2000-2001 Deep Blue Solutions Ltd + * + * Contributors to the old driver include: + * Russell King <linux@armlinux.org.uk> + * David A. Rusling <david.rusling@linaro.org> (uHAL, ARM Firmware suite) + * Rob Herring <robh@kernel.org> + * Liviu Dudau <Liviu.Dudau@arm.com> + * Grant Likely <grant.likely@secretlab.ca> + * Arnd Bergmann <arnd@arndb.de> + * Bjorn Helgaas <bhelgaas@google.com> + */ +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/kernel.h> +#include <linux/of_address.h> +#include <linux/of_device.h> +#include <linux/of_irq.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/slab.h> +#include <linux/bitops.h> +#include <linux/irq.h> +#include <linux/mfd/syscon.h> +#include <linux/regmap.h> +#include <linux/clk.h> + +#include "../pci.h" + +#define V3_PCI_VENDOR 0x00000000 +#define V3_PCI_DEVICE 0x00000002 +#define V3_PCI_CMD 0x00000004 +#define V3_PCI_STAT 0x00000006 +#define V3_PCI_CC_REV 0x00000008 +#define V3_PCI_HDR_CFG 0x0000000C +#define V3_PCI_IO_BASE 0x00000010 +#define V3_PCI_BASE0 0x00000014 +#define V3_PCI_BASE1 0x00000018 +#define V3_PCI_SUB_VENDOR 0x0000002C +#define V3_PCI_SUB_ID 0x0000002E +#define V3_PCI_ROM 0x00000030 +#define V3_PCI_BPARAM 0x0000003C +#define V3_PCI_MAP0 0x00000040 +#define V3_PCI_MAP1 0x00000044 +#define V3_PCI_INT_STAT 0x00000048 +#define V3_PCI_INT_CFG 0x0000004C +#define V3_LB_BASE0 0x00000054 +#define V3_LB_BASE1 0x00000058 +#define V3_LB_MAP0 0x0000005E +#define V3_LB_MAP1 0x00000062 +#define V3_LB_BASE2 0x00000064 +#define V3_LB_MAP2 0x00000066 +#define V3_LB_SIZE 0x00000068 +#define V3_LB_IO_BASE 0x0000006E +#define V3_FIFO_CFG 0x00000070 +#define V3_FIFO_PRIORITY 0x00000072 +#define V3_FIFO_STAT 0x00000074 +#define V3_LB_ISTAT 0x00000076 +#define V3_LB_IMASK 0x00000077 +#define V3_SYSTEM 0x00000078 +#define V3_LB_CFG 0x0000007A +#define V3_PCI_CFG 0x0000007C +#define V3_DMA_PCI_ADR0 0x00000080 +#define V3_DMA_PCI_ADR1 0x00000090 +#define V3_DMA_LOCAL_ADR0 0x00000084 +#define V3_DMA_LOCAL_ADR1 0x00000094 +#define V3_DMA_LENGTH0 0x00000088 +#define V3_DMA_LENGTH1 0x00000098 +#define V3_DMA_CSR0 0x0000008B +#define V3_DMA_CSR1 0x0000009B +#define V3_DMA_CTLB_ADR0 0x0000008C +#define V3_DMA_CTLB_ADR1 0x0000009C +#define V3_DMA_DELAY 0x000000E0 +#define V3_MAIL_DATA 0x000000C0 +#define V3_PCI_MAIL_IEWR 0x000000D0 +#define V3_PCI_MAIL_IERD 0x000000D2 +#define V3_LB_MAIL_IEWR 0x000000D4 +#define V3_LB_MAIL_IERD 0x000000D6 +#define V3_MAIL_WR_STAT 0x000000D8 +#define V3_MAIL_RD_STAT 0x000000DA +#define V3_QBA_MAP 0x000000DC + +/* PCI STATUS bits */ +#define V3_PCI_STAT_PAR_ERR BIT(15) +#define V3_PCI_STAT_SYS_ERR BIT(14) +#define V3_PCI_STAT_M_ABORT_ERR BIT(13) +#define V3_PCI_STAT_T_ABORT_ERR BIT(12) + +/* LB ISTAT bits */ +#define V3_LB_ISTAT_MAILBOX BIT(7) +#define V3_LB_ISTAT_PCI_RD BIT(6) +#define V3_LB_ISTAT_PCI_WR BIT(5) +#define V3_LB_ISTAT_PCI_INT BIT(4) +#define V3_LB_ISTAT_PCI_PERR BIT(3) +#define V3_LB_ISTAT_I2O_QWR BIT(2) +#define V3_LB_ISTAT_DMA1 BIT(1) +#define V3_LB_ISTAT_DMA0 BIT(0) + +/* PCI COMMAND bits */ +#define V3_COMMAND_M_FBB_EN BIT(9) +#define V3_COMMAND_M_SERR_EN BIT(8) +#define V3_COMMAND_M_PAR_EN BIT(6) +#define V3_COMMAND_M_MASTER_EN BIT(2) +#define V3_COMMAND_M_MEM_EN BIT(1) +#define V3_COMMAND_M_IO_EN BIT(0) + +/* SYSTEM bits */ +#define V3_SYSTEM_M_RST_OUT BIT(15) +#define V3_SYSTEM_M_LOCK BIT(14) +#define V3_SYSTEM_UNLOCK 0xa05f + +/* PCI CFG bits */ +#define V3_PCI_CFG_M_I2O_EN BIT(15) +#define V3_PCI_CFG_M_IO_REG_DIS BIT(14) +#define V3_PCI_CFG_M_IO_DIS BIT(13) +#define V3_PCI_CFG_M_EN3V BIT(12) +#define V3_PCI_CFG_M_RETRY_EN BIT(10) +#define V3_PCI_CFG_M_AD_LOW1 BIT(9) +#define V3_PCI_CFG_M_AD_LOW0 BIT(8) +/* + * This is the value applied to C/BE[3:1], with bit 0 always held 0 + * during DMA access. + */ +#define V3_PCI_CFG_M_RTYPE_SHIFT 5 +#define V3_PCI_CFG_M_WTYPE_SHIFT 1 +#define V3_PCI_CFG_TYPE_DEFAULT 0x3 + +/* PCI BASE bits (PCI -> Local Bus) */ +#define V3_PCI_BASE_M_ADR_BASE 0xFFF00000U +#define V3_PCI_BASE_M_ADR_BASEL 0x000FFF00U +#define V3_PCI_BASE_M_PREFETCH BIT(3) +#define V3_PCI_BASE_M_TYPE (3 << 1) +#define V3_PCI_BASE_M_IO BIT(0) + +/* PCI MAP bits (PCI -> Local bus) */ +#define V3_PCI_MAP_M_MAP_ADR 0xFFF00000U +#define V3_PCI_MAP_M_RD_POST_INH BIT(15) +#define V3_PCI_MAP_M_ROM_SIZE (3 << 10) +#define V3_PCI_MAP_M_SWAP (3 << 8) +#define V3_PCI_MAP_M_ADR_SIZE 0x000000F0U +#define V3_PCI_MAP_M_REG_EN BIT(1) +#define V3_PCI_MAP_M_ENABLE BIT(0) + +/* LB_BASE0,1 bits (Local bus -> PCI) */ +#define V3_LB_BASE_ADR_BASE 0xfff00000U +#define V3_LB_BASE_SWAP (3 << 8) +#define V3_LB_BASE_ADR_SIZE (15 << 4) +#define V3_LB_BASE_PREFETCH BIT(3) +#define V3_LB_BASE_ENABLE BIT(0) + +#define V3_LB_BASE_ADR_SIZE_1MB (0 << 4) +#define V3_LB_BASE_ADR_SIZE_2MB (1 << 4) +#define V3_LB_BASE_ADR_SIZE_4MB (2 << 4) +#define V3_LB_BASE_ADR_SIZE_8MB (3 << 4) +#define V3_LB_BASE_ADR_SIZE_16MB (4 << 4) +#define V3_LB_BASE_ADR_SIZE_32MB (5 << 4) +#define V3_LB_BASE_ADR_SIZE_64MB (6 << 4) +#define V3_LB_BASE_ADR_SIZE_128MB (7 << 4) +#define V3_LB_BASE_ADR_SIZE_256MB (8 << 4) +#define V3_LB_BASE_ADR_SIZE_512MB (9 << 4) +#define V3_LB_BASE_ADR_SIZE_1GB (10 << 4) +#define V3_LB_BASE_ADR_SIZE_2GB (11 << 4) + +#define v3_addr_to_lb_base(a) ((a) & V3_LB_BASE_ADR_BASE) + +/* LB_MAP0,1 bits (Local bus -> PCI) */ +#define V3_LB_MAP_MAP_ADR 0xfff0U +#define V3_LB_MAP_TYPE (7 << 1) +#define V3_LB_MAP_AD_LOW_EN BIT(0) + +#define V3_LB_MAP_TYPE_IACK (0 << 1) +#define V3_LB_MAP_TYPE_IO (1 << 1) +#define V3_LB_MAP_TYPE_MEM (3 << 1) +#define V3_LB_MAP_TYPE_CONFIG (5 << 1) +#define V3_LB_MAP_TYPE_MEM_MULTIPLE (6 << 1) + +#define v3_addr_to_lb_map(a) (((a) >> 16) & V3_LB_MAP_MAP_ADR) + +/* LB_BASE2 bits (Local bus -> PCI IO) */ +#define V3_LB_BASE2_ADR_BASE 0xff00U +#define V3_LB_BASE2_SWAP_AUTO (3 << 6) +#define V3_LB_BASE2_ENABLE BIT(0) + +#define v3_addr_to_lb_base2(a) (((a) >> 16) & V3_LB_BASE2_ADR_BASE) + +/* LB_MAP2 bits (Local bus -> PCI IO) */ +#define V3_LB_MAP2_MAP_ADR 0xff00U + +#define v3_addr_to_lb_map2(a) (((a) >> 16) & V3_LB_MAP2_MAP_ADR) + +/* FIFO priority bits */ +#define V3_FIFO_PRIO_LOCAL BIT(12) +#define V3_FIFO_PRIO_LB_RD1_FLUSH_EOB BIT(10) +#define V3_FIFO_PRIO_LB_RD1_FLUSH_AP1 BIT(11) +#define V3_FIFO_PRIO_LB_RD1_FLUSH_ANY (BIT(10)|BIT(11)) +#define V3_FIFO_PRIO_LB_RD0_FLUSH_EOB BIT(8) +#define V3_FIFO_PRIO_LB_RD0_FLUSH_AP1 BIT(9) +#define V3_FIFO_PRIO_LB_RD0_FLUSH_ANY (BIT(8)|BIT(9)) +#define V3_FIFO_PRIO_PCI BIT(4) +#define V3_FIFO_PRIO_PCI_RD1_FLUSH_EOB BIT(2) +#define V3_FIFO_PRIO_PCI_RD1_FLUSH_AP1 BIT(3) +#define V3_FIFO_PRIO_PCI_RD1_FLUSH_ANY (BIT(2)|BIT(3)) +#define V3_FIFO_PRIO_PCI_RD0_FLUSH_EOB BIT(0) +#define V3_FIFO_PRIO_PCI_RD0_FLUSH_AP1 BIT(1) +#define V3_FIFO_PRIO_PCI_RD0_FLUSH_ANY (BIT(0)|BIT(1)) + +/* Local bus configuration bits */ +#define V3_LB_CFG_LB_TO_64_CYCLES 0x0000 +#define V3_LB_CFG_LB_TO_256_CYCLES BIT(13) +#define V3_LB_CFG_LB_TO_512_CYCLES BIT(14) +#define V3_LB_CFG_LB_TO_1024_CYCLES (BIT(13)|BIT(14)) +#define V3_LB_CFG_LB_RST BIT(12) +#define V3_LB_CFG_LB_PPC_RDY BIT(11) +#define V3_LB_CFG_LB_LB_INT BIT(10) +#define V3_LB_CFG_LB_ERR_EN BIT(9) +#define V3_LB_CFG_LB_RDY_EN BIT(8) +#define V3_LB_CFG_LB_BE_IMODE BIT(7) +#define V3_LB_CFG_LB_BE_OMODE BIT(6) +#define V3_LB_CFG_LB_ENDIAN BIT(5) +#define V3_LB_CFG_LB_PARK_EN BIT(4) +#define V3_LB_CFG_LB_FBB_DIS BIT(2) + +/* ARM Integrator-specific extended control registers */ +#define INTEGRATOR_SC_PCI_OFFSET 0x18 +#define INTEGRATOR_SC_PCI_ENABLE BIT(0) +#define INTEGRATOR_SC_PCI_INTCLR BIT(1) +#define INTEGRATOR_SC_LBFADDR_OFFSET 0x20 +#define INTEGRATOR_SC_LBFCODE_OFFSET 0x24 + +struct v3_pci { + struct device *dev; + void __iomem *base; + void __iomem *config_base; + u32 config_mem; + u32 non_pre_mem; + u32 pre_mem; + phys_addr_t non_pre_bus_addr; + phys_addr_t pre_bus_addr; + struct regmap *map; +}; + +/* + * The V3 PCI interface chip in Integrator provides several windows from + * local bus memory into the PCI memory areas. Unfortunately, there + * are not really enough windows for our usage, therefore we reuse + * one of the windows for access to PCI configuration space. On the + * Integrator/AP, the memory map is as follows: + * + * Local Bus Memory Usage + * + * 40000000 - 4FFFFFFF PCI memory. 256M non-prefetchable + * 50000000 - 5FFFFFFF PCI memory. 256M prefetchable + * 60000000 - 60FFFFFF PCI IO. 16M + * 61000000 - 61FFFFFF PCI Configuration. 16M + * + * There are three V3 windows, each described by a pair of V3 registers. + * These are LB_BASE0/LB_MAP0, LB_BASE1/LB_MAP1 and LB_BASE2/LB_MAP2. + * Base0 and Base1 can be used for any type of PCI memory access. Base2 + * can be used either for PCI I/O or for I20 accesses. By default, uHAL + * uses this only for PCI IO space. + * + * Normally these spaces are mapped using the following base registers: + * + * Usage Local Bus Memory Base/Map registers used + * + * Mem 40000000 - 4FFFFFFF LB_BASE0/LB_MAP0 + * Mem 50000000 - 5FFFFFFF LB_BASE1/LB_MAP1 + * IO 60000000 - 60FFFFFF LB_BASE2/LB_MAP2 + * Cfg 61000000 - 61FFFFFF + * + * This means that I20 and PCI configuration space accesses will fail. + * When PCI configuration accesses are needed (via the uHAL PCI + * configuration space primitives) we must remap the spaces as follows: + * + * Usage Local Bus Memory Base/Map registers used + * + * Mem 40000000 - 4FFFFFFF LB_BASE0/LB_MAP0 + * Mem 50000000 - 5FFFFFFF LB_BASE0/LB_MAP0 + * IO 60000000 - 60FFFFFF LB_BASE2/LB_MAP2 + * Cfg 61000000 - 61FFFFFF LB_BASE1/LB_MAP1 + * + * To make this work, the code depends on overlapping windows working. + * The V3 chip translates an address by checking its range within + * each of the BASE/MAP pairs in turn (in ascending register number + * order). It will use the first matching pair. So, for example, + * if the same address is mapped by both LB_BASE0/LB_MAP0 and + * LB_BASE1/LB_MAP1, the V3 will use the translation from + * LB_BASE0/LB_MAP0. + * + * To allow PCI Configuration space access, the code enlarges the + * window mapped by LB_BASE0/LB_MAP0 from 256M to 512M. This occludes + * the windows currently mapped by LB_BASE1/LB_MAP1 so that it can + * be remapped for use by configuration cycles. + * + * At the end of the PCI Configuration space accesses, + * LB_BASE1/LB_MAP1 is reset to map PCI Memory. Finally the window + * mapped by LB_BASE0/LB_MAP0 is reduced in size from 512M to 256M to + * reveal the now restored LB_BASE1/LB_MAP1 window. + * + * NOTE: We do not set up I2O mapping. I suspect that this is only + * for an intelligent (target) device. Using I2O disables most of + * the mappings into PCI memory. + */ +static void __iomem *v3_map_bus(struct pci_bus *bus, + unsigned int devfn, int offset) +{ + struct v3_pci *v3 = bus->sysdata; + unsigned int address, mapaddress, busnr; + + busnr = bus->number; + if (busnr == 0) { + int slot = PCI_SLOT(devfn); + + /* + * local bus segment so need a type 0 config cycle + * + * build the PCI configuration "address" with one-hot in + * A31-A11 + * + * mapaddress: + * 3:1 = config cycle (101) + * 0 = PCI A1 & A0 are 0 (0) + */ + address = PCI_FUNC(devfn) << 8; + mapaddress = V3_LB_MAP_TYPE_CONFIG; + + if (slot > 12) + /* + * high order bits are handled by the MAP register + */ + mapaddress |= BIT(slot - 5); + else + /* + * low order bits handled directly in the address + */ + address |= BIT(slot + 11); + } else { + /* + * not the local bus segment so need a type 1 config cycle + * + * address: + * 23:16 = bus number + * 15:11 = slot number (7:3 of devfn) + * 10:8 = func number (2:0 of devfn) + * + * mapaddress: + * 3:1 = config cycle (101) + * 0 = PCI A1 & A0 from host bus (1) + */ + mapaddress = V3_LB_MAP_TYPE_CONFIG | V3_LB_MAP_AD_LOW_EN; + address = (busnr << 16) | (devfn << 8); + } + + /* + * Set up base0 to see all 512Mbytes of memory space (not + * prefetchable), this frees up base1 for re-use by + * configuration memory + */ + writel(v3_addr_to_lb_base(v3->non_pre_mem) | + V3_LB_BASE_ADR_SIZE_512MB | V3_LB_BASE_ENABLE, + v3->base + V3_LB_BASE0); + + /* + * Set up base1/map1 to point into configuration space. + * The config mem is always 16MB. + */ + writel(v3_addr_to_lb_base(v3->config_mem) | + V3_LB_BASE_ADR_SIZE_16MB | V3_LB_BASE_ENABLE, + v3->base + V3_LB_BASE1); + writew(mapaddress, v3->base + V3_LB_MAP1); + + return v3->config_base + address + offset; +} + +static void v3_unmap_bus(struct v3_pci *v3) +{ + /* + * Reassign base1 for use by prefetchable PCI memory + */ + writel(v3_addr_to_lb_base(v3->pre_mem) | + V3_LB_BASE_ADR_SIZE_256MB | V3_LB_BASE_PREFETCH | + V3_LB_BASE_ENABLE, + v3->base + V3_LB_BASE1); + writew(v3_addr_to_lb_map(v3->pre_bus_addr) | + V3_LB_MAP_TYPE_MEM, /* was V3_LB_MAP_TYPE_MEM_MULTIPLE */ + v3->base + V3_LB_MAP1); + + /* + * And shrink base0 back to a 256M window (NOTE: MAP0 already correct) + */ + writel(v3_addr_to_lb_base(v3->non_pre_mem) | + V3_LB_BASE_ADR_SIZE_256MB | V3_LB_BASE_ENABLE, + v3->base + V3_LB_BASE0); +} + +static int v3_pci_read_config(struct pci_bus *bus, unsigned int fn, + int config, int size, u32 *value) +{ + struct v3_pci *v3 = bus->sysdata; + int ret; + + dev_dbg(&bus->dev, + "[read] slt: %.2d, fnc: %d, cnf: 0x%.2X, val (%d bytes): 0x%.8X\n", + PCI_SLOT(fn), PCI_FUNC(fn), config, size, *value); + ret = pci_generic_config_read(bus, fn, config, size, value); + v3_unmap_bus(v3); + return ret; +} + +static int v3_pci_write_config(struct pci_bus *bus, unsigned int fn, + int config, int size, u32 value) +{ + struct v3_pci *v3 = bus->sysdata; + int ret; + + dev_dbg(&bus->dev, + "[write] slt: %.2d, fnc: %d, cnf: 0x%.2X, val (%d bytes): 0x%.8X\n", + PCI_SLOT(fn), PCI_FUNC(fn), config, size, value); + ret = pci_generic_config_write(bus, fn, config, size, value); + v3_unmap_bus(v3); + return ret; +} + +static struct pci_ops v3_pci_ops = { + .map_bus = v3_map_bus, + .read = v3_pci_read_config, + .write = v3_pci_write_config, +}; + +static irqreturn_t v3_irq(int irq, void *data) +{ + struct v3_pci *v3 = data; + struct device *dev = v3->dev; + u32 status; + + status = readw(v3->base + V3_PCI_STAT); + if (status & V3_PCI_STAT_PAR_ERR) + dev_err(dev, "parity error interrupt\n"); + if (status & V3_PCI_STAT_SYS_ERR) + dev_err(dev, "system error interrupt\n"); + if (status & V3_PCI_STAT_M_ABORT_ERR) + dev_err(dev, "master abort error interrupt\n"); + if (status & V3_PCI_STAT_T_ABORT_ERR) + dev_err(dev, "target abort error interrupt\n"); + writew(status, v3->base + V3_PCI_STAT); + + status = readb(v3->base + V3_LB_ISTAT); + if (status & V3_LB_ISTAT_MAILBOX) + dev_info(dev, "PCI mailbox interrupt\n"); + if (status & V3_LB_ISTAT_PCI_RD) + dev_err(dev, "PCI target LB->PCI READ abort interrupt\n"); + if (status & V3_LB_ISTAT_PCI_WR) + dev_err(dev, "PCI target LB->PCI WRITE abort interrupt\n"); + if (status & V3_LB_ISTAT_PCI_INT) + dev_info(dev, "PCI pin interrupt\n"); + if (status & V3_LB_ISTAT_PCI_PERR) + dev_err(dev, "PCI parity error interrupt\n"); + if (status & V3_LB_ISTAT_I2O_QWR) + dev_info(dev, "I2O inbound post queue interrupt\n"); + if (status & V3_LB_ISTAT_DMA1) + dev_info(dev, "DMA channel 1 interrupt\n"); + if (status & V3_LB_ISTAT_DMA0) + dev_info(dev, "DMA channel 0 interrupt\n"); + /* Clear all possible interrupts on the local bus */ + writeb(0, v3->base + V3_LB_ISTAT); + if (v3->map) + regmap_write(v3->map, INTEGRATOR_SC_PCI_OFFSET, + INTEGRATOR_SC_PCI_ENABLE | + INTEGRATOR_SC_PCI_INTCLR); + + return IRQ_HANDLED; +} + +static int v3_integrator_init(struct v3_pci *v3) +{ + unsigned int val; + + v3->map = + syscon_regmap_lookup_by_compatible("arm,integrator-ap-syscon"); + if (IS_ERR(v3->map)) { + dev_err(v3->dev, "no syscon\n"); + return -ENODEV; + } + + regmap_read(v3->map, INTEGRATOR_SC_PCI_OFFSET, &val); + /* Take the PCI bridge out of reset, clear IRQs */ + regmap_write(v3->map, INTEGRATOR_SC_PCI_OFFSET, + INTEGRATOR_SC_PCI_ENABLE | + INTEGRATOR_SC_PCI_INTCLR); + + if (!(val & INTEGRATOR_SC_PCI_ENABLE)) { + /* If we were in reset we need to sleep a bit */ + msleep(230); + + /* Set the physical base for the controller itself */ + writel(0x6200, v3->base + V3_LB_IO_BASE); + + /* Wait for the mailbox to settle after reset */ + do { + writeb(0xaa, v3->base + V3_MAIL_DATA); + writeb(0x55, v3->base + V3_MAIL_DATA + 4); + } while (readb(v3->base + V3_MAIL_DATA) != 0xaa && + readb(v3->base + V3_MAIL_DATA) != 0x55); + } + + dev_info(v3->dev, "initialized PCI V3 Integrator/AP integration\n"); + + return 0; +} + +static int v3_pci_setup_resource(struct v3_pci *v3, + struct pci_host_bridge *host, + struct resource_entry *win) +{ + struct device *dev = v3->dev; + struct resource *mem; + struct resource *io; + + switch (resource_type(win->res)) { + case IORESOURCE_IO: + io = win->res; + + /* Setup window 2 - PCI I/O */ + writel(v3_addr_to_lb_base2(pci_pio_to_address(io->start)) | + V3_LB_BASE2_ENABLE, + v3->base + V3_LB_BASE2); + writew(v3_addr_to_lb_map2(io->start - win->offset), + v3->base + V3_LB_MAP2); + break; + case IORESOURCE_MEM: + mem = win->res; + if (mem->flags & IORESOURCE_PREFETCH) { + mem->name = "V3 PCI PRE-MEM"; + v3->pre_mem = mem->start; + v3->pre_bus_addr = mem->start - win->offset; + dev_dbg(dev, "PREFETCHABLE MEM window %pR, bus addr %pap\n", + mem, &v3->pre_bus_addr); + if (resource_size(mem) != SZ_256M) { + dev_err(dev, "prefetchable memory range is not 256MB\n"); + return -EINVAL; + } + if (v3->non_pre_mem && + (mem->start != v3->non_pre_mem + SZ_256M)) { + dev_err(dev, + "prefetchable memory is not adjacent to non-prefetchable memory\n"); + return -EINVAL; + } + /* Setup window 1 - PCI prefetchable memory */ + writel(v3_addr_to_lb_base(v3->pre_mem) | + V3_LB_BASE_ADR_SIZE_256MB | + V3_LB_BASE_PREFETCH | + V3_LB_BASE_ENABLE, + v3->base + V3_LB_BASE1); + writew(v3_addr_to_lb_map(v3->pre_bus_addr) | + V3_LB_MAP_TYPE_MEM, /* Was V3_LB_MAP_TYPE_MEM_MULTIPLE */ + v3->base + V3_LB_MAP1); + } else { + mem->name = "V3 PCI NON-PRE-MEM"; + v3->non_pre_mem = mem->start; + v3->non_pre_bus_addr = mem->start - win->offset; + dev_dbg(dev, "NON-PREFETCHABLE MEM window %pR, bus addr %pap\n", + mem, &v3->non_pre_bus_addr); + if (resource_size(mem) != SZ_256M) { + dev_err(dev, + "non-prefetchable memory range is not 256MB\n"); + return -EINVAL; + } + /* Setup window 0 - PCI non-prefetchable memory */ + writel(v3_addr_to_lb_base(v3->non_pre_mem) | + V3_LB_BASE_ADR_SIZE_256MB | + V3_LB_BASE_ENABLE, + v3->base + V3_LB_BASE0); + writew(v3_addr_to_lb_map(v3->non_pre_bus_addr) | + V3_LB_MAP_TYPE_MEM, + v3->base + V3_LB_MAP0); + } + break; + case IORESOURCE_BUS: + break; + default: + dev_info(dev, "Unknown resource type %lu\n", + resource_type(win->res)); + break; + } + + return 0; +} + +static int v3_get_dma_range_config(struct v3_pci *v3, + struct resource_entry *entry, + u32 *pci_base, u32 *pci_map) +{ + struct device *dev = v3->dev; + u64 cpu_addr = entry->res->start; + u64 cpu_end = entry->res->end; + u64 pci_end = cpu_end - entry->offset; + u64 pci_addr = entry->res->start - entry->offset; + u32 val; + + if (pci_addr & ~V3_PCI_BASE_M_ADR_BASE) { + dev_err(dev, "illegal range, only PCI bits 31..20 allowed\n"); + return -EINVAL; + } + val = ((u32)pci_addr) & V3_PCI_BASE_M_ADR_BASE; + *pci_base = val; + + if (cpu_addr & ~V3_PCI_MAP_M_MAP_ADR) { + dev_err(dev, "illegal range, only CPU bits 31..20 allowed\n"); + return -EINVAL; + } + val = ((u32)cpu_addr) & V3_PCI_MAP_M_MAP_ADR; + + switch (resource_size(entry->res)) { + case SZ_1M: + val |= V3_LB_BASE_ADR_SIZE_1MB; + break; + case SZ_2M: + val |= V3_LB_BASE_ADR_SIZE_2MB; + break; + case SZ_4M: + val |= V3_LB_BASE_ADR_SIZE_4MB; + break; + case SZ_8M: + val |= V3_LB_BASE_ADR_SIZE_8MB; + break; + case SZ_16M: + val |= V3_LB_BASE_ADR_SIZE_16MB; + break; + case SZ_32M: + val |= V3_LB_BASE_ADR_SIZE_32MB; + break; + case SZ_64M: + val |= V3_LB_BASE_ADR_SIZE_64MB; + break; + case SZ_128M: + val |= V3_LB_BASE_ADR_SIZE_128MB; + break; + case SZ_256M: + val |= V3_LB_BASE_ADR_SIZE_256MB; + break; + case SZ_512M: + val |= V3_LB_BASE_ADR_SIZE_512MB; + break; + case SZ_1G: + val |= V3_LB_BASE_ADR_SIZE_1GB; + break; + case SZ_2G: + val |= V3_LB_BASE_ADR_SIZE_2GB; + break; + default: + dev_err(v3->dev, "illegal dma memory chunk size\n"); + return -EINVAL; + } + val |= V3_PCI_MAP_M_REG_EN | V3_PCI_MAP_M_ENABLE; + *pci_map = val; + + dev_dbg(dev, + "DMA MEM CPU: 0x%016llx -> 0x%016llx => " + "PCI: 0x%016llx -> 0x%016llx base %08x map %08x\n", + cpu_addr, cpu_end, + pci_addr, pci_end, + *pci_base, *pci_map); + + return 0; +} + +static int v3_pci_parse_map_dma_ranges(struct v3_pci *v3, + struct device_node *np) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(v3); + struct device *dev = v3->dev; + struct resource_entry *entry; + int i = 0; + + resource_list_for_each_entry(entry, &bridge->dma_ranges) { + int ret; + u32 pci_base, pci_map; + + ret = v3_get_dma_range_config(v3, entry, &pci_base, &pci_map); + if (ret) + return ret; + + if (i == 0) { + writel(pci_base, v3->base + V3_PCI_BASE0); + writel(pci_map, v3->base + V3_PCI_MAP0); + } else if (i == 1) { + writel(pci_base, v3->base + V3_PCI_BASE1); + writel(pci_map, v3->base + V3_PCI_MAP1); + } else { + dev_err(dev, "too many ranges, only two supported\n"); + dev_err(dev, "range %d ignored\n", i); + } + i++; + } + return 0; +} + +static int v3_pci_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct resource *regs; + struct resource_entry *win; + struct v3_pci *v3; + struct pci_host_bridge *host; + struct clk *clk; + u16 val; + int irq; + int ret; + + host = devm_pci_alloc_host_bridge(dev, sizeof(*v3)); + if (!host) + return -ENOMEM; + + host->ops = &v3_pci_ops; + v3 = pci_host_bridge_priv(host); + host->sysdata = v3; + v3->dev = dev; + + /* Get and enable host clock */ + clk = devm_clk_get(dev, NULL); + if (IS_ERR(clk)) { + dev_err(dev, "clock not found\n"); + return PTR_ERR(clk); + } + ret = clk_prepare_enable(clk); + if (ret) { + dev_err(dev, "unable to enable clock\n"); + return ret; + } + + regs = platform_get_resource(pdev, IORESOURCE_MEM, 0); + v3->base = devm_ioremap_resource(dev, regs); + if (IS_ERR(v3->base)) + return PTR_ERR(v3->base); + /* + * The hardware has a register with the physical base address + * of the V3 controller itself, verify that this is the same + * as the physical memory we've remapped it from. + */ + if (readl(v3->base + V3_LB_IO_BASE) != (regs->start >> 16)) + dev_err(dev, "V3_LB_IO_BASE = %08x but device is @%pR\n", + readl(v3->base + V3_LB_IO_BASE), regs); + + /* Configuration space is 16MB directly mapped */ + regs = platform_get_resource(pdev, IORESOURCE_MEM, 1); + if (resource_size(regs) != SZ_16M) { + dev_err(dev, "config mem is not 16MB!\n"); + return -EINVAL; + } + v3->config_mem = regs->start; + v3->config_base = devm_ioremap_resource(dev, regs); + if (IS_ERR(v3->config_base)) + return PTR_ERR(v3->config_base); + + /* Get and request error IRQ resource */ + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + ret = devm_request_irq(dev, irq, v3_irq, 0, + "PCIv3 error", v3); + if (ret < 0) { + dev_err(dev, + "unable to request PCIv3 error IRQ %d (%d)\n", + irq, ret); + return ret; + } + + /* + * Unlock V3 registers, but only if they were previously locked. + */ + if (readw(v3->base + V3_SYSTEM) & V3_SYSTEM_M_LOCK) + writew(V3_SYSTEM_UNLOCK, v3->base + V3_SYSTEM); + + /* Disable all slave access while we set up the windows */ + val = readw(v3->base + V3_PCI_CMD); + val &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER); + writew(val, v3->base + V3_PCI_CMD); + + /* Put the PCI bus into reset */ + val = readw(v3->base + V3_SYSTEM); + val &= ~V3_SYSTEM_M_RST_OUT; + writew(val, v3->base + V3_SYSTEM); + + /* Retry until we're ready */ + val = readw(v3->base + V3_PCI_CFG); + val |= V3_PCI_CFG_M_RETRY_EN; + writew(val, v3->base + V3_PCI_CFG); + + /* Set up the local bus protocol */ + val = readw(v3->base + V3_LB_CFG); + val |= V3_LB_CFG_LB_BE_IMODE; /* Byte enable input */ + val |= V3_LB_CFG_LB_BE_OMODE; /* Byte enable output */ + val &= ~V3_LB_CFG_LB_ENDIAN; /* Little endian */ + val &= ~V3_LB_CFG_LB_PPC_RDY; /* TODO: when using on PPC403Gx, set to 1 */ + writew(val, v3->base + V3_LB_CFG); + + /* Enable the PCI bus master */ + val = readw(v3->base + V3_PCI_CMD); + val |= PCI_COMMAND_MASTER; + writew(val, v3->base + V3_PCI_CMD); + + /* Get the I/O and memory ranges from DT */ + resource_list_for_each_entry(win, &host->windows) { + ret = v3_pci_setup_resource(v3, host, win); + if (ret) { + dev_err(dev, "error setting up resources\n"); + return ret; + } + } + ret = v3_pci_parse_map_dma_ranges(v3, np); + if (ret) + return ret; + + /* + * Disable PCI to host IO cycles, enable I/O buffers @3.3V, + * set AD_LOW0 to 1 if one of the LB_MAP registers choose + * to use this (should be unused). + */ + writel(0x00000000, v3->base + V3_PCI_IO_BASE); + val = V3_PCI_CFG_M_IO_REG_DIS | V3_PCI_CFG_M_IO_DIS | + V3_PCI_CFG_M_EN3V | V3_PCI_CFG_M_AD_LOW0; + /* + * DMA read and write from PCI bus commands types + */ + val |= V3_PCI_CFG_TYPE_DEFAULT << V3_PCI_CFG_M_RTYPE_SHIFT; + val |= V3_PCI_CFG_TYPE_DEFAULT << V3_PCI_CFG_M_WTYPE_SHIFT; + writew(val, v3->base + V3_PCI_CFG); + + /* + * Set the V3 FIFO such that writes have higher priority than + * reads, and local bus write causes local bus read fifo flush + * on aperture 1. Same for PCI. + */ + writew(V3_FIFO_PRIO_LB_RD1_FLUSH_AP1 | + V3_FIFO_PRIO_LB_RD0_FLUSH_AP1 | + V3_FIFO_PRIO_PCI_RD1_FLUSH_AP1 | + V3_FIFO_PRIO_PCI_RD0_FLUSH_AP1, + v3->base + V3_FIFO_PRIORITY); + + + /* + * Clear any error interrupts, and enable parity and write error + * interrupts + */ + writeb(0, v3->base + V3_LB_ISTAT); + val = readw(v3->base + V3_LB_CFG); + val |= V3_LB_CFG_LB_LB_INT; + writew(val, v3->base + V3_LB_CFG); + writeb(V3_LB_ISTAT_PCI_WR | V3_LB_ISTAT_PCI_PERR, + v3->base + V3_LB_IMASK); + + /* Special Integrator initialization */ + if (of_device_is_compatible(np, "arm,integrator-ap-pci")) { + ret = v3_integrator_init(v3); + if (ret) + return ret; + } + + /* Post-init: enable PCI memory and invalidate (master already on) */ + val = readw(v3->base + V3_PCI_CMD); + val |= PCI_COMMAND_MEMORY | PCI_COMMAND_INVALIDATE; + writew(val, v3->base + V3_PCI_CMD); + + /* Clear pending interrupts */ + writeb(0, v3->base + V3_LB_ISTAT); + /* Read or write errors and parity errors cause interrupts */ + writeb(V3_LB_ISTAT_PCI_RD | V3_LB_ISTAT_PCI_WR | V3_LB_ISTAT_PCI_PERR, + v3->base + V3_LB_IMASK); + + /* Take the PCI bus out of reset so devices can initialize */ + val = readw(v3->base + V3_SYSTEM); + val |= V3_SYSTEM_M_RST_OUT; + writew(val, v3->base + V3_SYSTEM); + + /* + * Re-lock the system register. + */ + val = readw(v3->base + V3_SYSTEM); + val |= V3_SYSTEM_M_LOCK; + writew(val, v3->base + V3_SYSTEM); + + return pci_host_probe(host); +} + +static const struct of_device_id v3_pci_of_match[] = { + { + .compatible = "v3,v360epc-pci", + }, + {}, +}; + +static struct platform_driver v3_pci_driver = { + .driver = { + .name = "pci-v3-semi", + .of_match_table = of_match_ptr(v3_pci_of_match), + .suppress_bind_attrs = true, + }, + .probe = v3_pci_probe, +}; +builtin_platform_driver(v3_pci_driver); diff --git a/drivers/pci/controller/pci-versatile.c b/drivers/pci/controller/pci-versatile.c new file mode 100644 index 000000000..7991d334e --- /dev/null +++ b/drivers/pci/controller/pci-versatile.c @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright 2004 Koninklijke Philips Electronics NV + * + * Conversion to platform driver and DT: + * Copyright 2014 Linaro Ltd. + * + * 14/04/2005 Initial version, colin.king@philips.com + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/platform_device.h> + +#include "../pci.h" + +static void __iomem *versatile_pci_base; +static void __iomem *versatile_cfg_base[2]; + +#define PCI_IMAP(m) (versatile_pci_base + ((m) * 4)) +#define PCI_SMAP(m) (versatile_pci_base + 0x14 + ((m) * 4)) +#define PCI_SELFID (versatile_pci_base + 0xc) + +#define VP_PCI_DEVICE_ID 0x030010ee +#define VP_PCI_CLASS_ID 0x0b400000 + +static u32 pci_slot_ignore; + +static int __init versatile_pci_slot_ignore(char *str) +{ + int slot; + + while (get_option(&str, &slot)) { + if ((slot < 0) || (slot > 31)) + pr_err("Illegal slot value: %d\n", slot); + else + pci_slot_ignore |= (1 << slot); + } + return 1; +} +__setup("pci_slot_ignore=", versatile_pci_slot_ignore); + + +static void __iomem *versatile_map_bus(struct pci_bus *bus, + unsigned int devfn, int offset) +{ + unsigned int busnr = bus->number; + + if (pci_slot_ignore & (1 << PCI_SLOT(devfn))) + return NULL; + + return versatile_cfg_base[1] + ((busnr << 16) | (devfn << 8) | offset); +} + +static struct pci_ops pci_versatile_ops = { + .map_bus = versatile_map_bus, + .read = pci_generic_config_read32, + .write = pci_generic_config_write, +}; + +static int versatile_pci_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct resource *res; + struct resource_entry *entry; + int i, myslot = -1, mem = 1; + u32 val; + void __iomem *local_pci_cfg_base; + struct pci_host_bridge *bridge; + + bridge = devm_pci_alloc_host_bridge(dev, 0); + if (!bridge) + return -ENOMEM; + + versatile_pci_base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(versatile_pci_base)) + return PTR_ERR(versatile_pci_base); + + versatile_cfg_base[0] = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(versatile_cfg_base[0])) + return PTR_ERR(versatile_cfg_base[0]); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 2); + versatile_cfg_base[1] = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(versatile_cfg_base[1])) + return PTR_ERR(versatile_cfg_base[1]); + + resource_list_for_each_entry(entry, &bridge->windows) { + if (resource_type(entry->res) == IORESOURCE_MEM) { + writel(entry->res->start >> 28, PCI_IMAP(mem)); + writel(__pa(PAGE_OFFSET) >> 28, PCI_SMAP(mem)); + mem++; + } + } + + /* + * We need to discover the PCI core first to configure itself + * before the main PCI probing is performed + */ + for (i = 0; i < 32; i++) { + if ((readl(versatile_cfg_base[0] + (i << 11) + PCI_VENDOR_ID) == VP_PCI_DEVICE_ID) && + (readl(versatile_cfg_base[0] + (i << 11) + PCI_CLASS_REVISION) == VP_PCI_CLASS_ID)) { + myslot = i; + break; + } + } + if (myslot == -1) { + dev_err(dev, "Cannot find PCI core!\n"); + return -EIO; + } + /* + * Do not to map Versatile FPGA PCI device into memory space + */ + pci_slot_ignore |= (1 << myslot); + + dev_info(dev, "PCI core found (slot %d)\n", myslot); + + writel(myslot, PCI_SELFID); + local_pci_cfg_base = versatile_cfg_base[1] + (myslot << 11); + + val = readl(local_pci_cfg_base + PCI_COMMAND); + val |= PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER | PCI_COMMAND_INVALIDATE; + writel(val, local_pci_cfg_base + PCI_COMMAND); + + /* + * Configure the PCI inbound memory windows to be 1:1 mapped to SDRAM + */ + writel(__pa(PAGE_OFFSET), local_pci_cfg_base + PCI_BASE_ADDRESS_0); + writel(__pa(PAGE_OFFSET), local_pci_cfg_base + PCI_BASE_ADDRESS_1); + writel(__pa(PAGE_OFFSET), local_pci_cfg_base + PCI_BASE_ADDRESS_2); + + /* + * For many years the kernel and QEMU were symbiotically buggy + * in that they both assumed the same broken IRQ mapping. + * QEMU therefore attempts to auto-detect old broken kernels + * so that they still work on newer QEMU as they did on old + * QEMU. Since we now use the correct (ie matching-hardware) + * IRQ mapping we write a definitely different value to a + * PCI_INTERRUPT_LINE register to tell QEMU that we expect + * real hardware behaviour and it need not be backwards + * compatible for us. This write is harmless on real hardware. + */ + writel(0, versatile_cfg_base[0] + PCI_INTERRUPT_LINE); + + pci_add_flags(PCI_REASSIGN_ALL_BUS); + + bridge->ops = &pci_versatile_ops; + + return pci_host_probe(bridge); +} + +static const struct of_device_id versatile_pci_of_match[] = { + { .compatible = "arm,versatile-pci", }, + { }, +}; +MODULE_DEVICE_TABLE(of, versatile_pci_of_match); + +static struct platform_driver versatile_pci_driver = { + .driver = { + .name = "versatile-pci", + .of_match_table = versatile_pci_of_match, + .suppress_bind_attrs = true, + }, + .probe = versatile_pci_probe, +}; +module_platform_driver(versatile_pci_driver); + +MODULE_DESCRIPTION("Versatile PCI driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-xgene-msi.c b/drivers/pci/controller/pci-xgene-msi.c new file mode 100644 index 000000000..bfa259781 --- /dev/null +++ b/drivers/pci/controller/pci-xgene-msi.c @@ -0,0 +1,531 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * APM X-Gene MSI Driver + * + * Copyright (c) 2014, Applied Micro Circuits Corporation + * Author: Tanmay Inamdar <tinamdar@apm.com> + * Duc Dang <dhdang@apm.com> + */ +#include <linux/cpu.h> +#include <linux/interrupt.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/of_irq.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/of_pci.h> + +#define MSI_IR0 0x000000 +#define MSI_INT0 0x800000 +#define IDX_PER_GROUP 8 +#define IRQS_PER_IDX 16 +#define NR_HW_IRQS 16 +#define NR_MSI_VEC (IDX_PER_GROUP * IRQS_PER_IDX * NR_HW_IRQS) + +struct xgene_msi_group { + struct xgene_msi *msi; + int gic_irq; + u32 msi_grp; +}; + +struct xgene_msi { + struct device_node *node; + struct irq_domain *inner_domain; + struct irq_domain *msi_domain; + u64 msi_addr; + void __iomem *msi_regs; + unsigned long *bitmap; + struct mutex bitmap_lock; + struct xgene_msi_group *msi_groups; + int num_cpus; +}; + +/* Global data */ +static struct xgene_msi xgene_msi_ctrl; + +static struct irq_chip xgene_msi_top_irq_chip = { + .name = "X-Gene1 MSI", + .irq_enable = pci_msi_unmask_irq, + .irq_disable = pci_msi_mask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, +}; + +static struct msi_domain_info xgene_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX), + .chip = &xgene_msi_top_irq_chip, +}; + +/* + * X-Gene v1 has 16 groups of MSI termination registers MSInIRx, where + * n is group number (0..F), x is index of registers in each group (0..7) + * The register layout is as follows: + * MSI0IR0 base_addr + * MSI0IR1 base_addr + 0x10000 + * ... ... + * MSI0IR6 base_addr + 0x60000 + * MSI0IR7 base_addr + 0x70000 + * MSI1IR0 base_addr + 0x80000 + * MSI1IR1 base_addr + 0x90000 + * ... ... + * MSI1IR7 base_addr + 0xF0000 + * MSI2IR0 base_addr + 0x100000 + * ... ... + * MSIFIR0 base_addr + 0x780000 + * MSIFIR1 base_addr + 0x790000 + * ... ... + * MSIFIR7 base_addr + 0x7F0000 + * MSIINT0 base_addr + 0x800000 + * MSIINT1 base_addr + 0x810000 + * ... ... + * MSIINTF base_addr + 0x8F0000 + * + * Each index register supports 16 MSI vectors (0..15) to generate interrupt. + * There are total 16 GIC IRQs assigned for these 16 groups of MSI termination + * registers. + * + * Each MSI termination group has 1 MSIINTn register (n is 0..15) to indicate + * the MSI pending status caused by 1 of its 8 index registers. + */ + +/* MSInIRx read helper */ +static u32 xgene_msi_ir_read(struct xgene_msi *msi, + u32 msi_grp, u32 msir_idx) +{ + return readl_relaxed(msi->msi_regs + MSI_IR0 + + (msi_grp << 19) + (msir_idx << 16)); +} + +/* MSIINTn read helper */ +static u32 xgene_msi_int_read(struct xgene_msi *msi, u32 msi_grp) +{ + return readl_relaxed(msi->msi_regs + MSI_INT0 + (msi_grp << 16)); +} + +/* + * With 2048 MSI vectors supported, the MSI message can be constructed using + * following scheme: + * - Divide into 8 256-vector groups + * Group 0: 0-255 + * Group 1: 256-511 + * Group 2: 512-767 + * ... + * Group 7: 1792-2047 + * - Each 256-vector group is divided into 16 16-vector groups + * As an example: 16 16-vector groups for 256-vector group 0-255 is + * Group 0: 0-15 + * Group 1: 16-32 + * ... + * Group 15: 240-255 + * - The termination address of MSI vector in 256-vector group n and 16-vector + * group x is the address of MSIxIRn + * - The data for MSI vector in 16-vector group x is x + */ +static u32 hwirq_to_reg_set(unsigned long hwirq) +{ + return (hwirq / (NR_HW_IRQS * IRQS_PER_IDX)); +} + +static u32 hwirq_to_group(unsigned long hwirq) +{ + return (hwirq % NR_HW_IRQS); +} + +static u32 hwirq_to_msi_data(unsigned long hwirq) +{ + return ((hwirq / NR_HW_IRQS) % IRQS_PER_IDX); +} + +static void xgene_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct xgene_msi *msi = irq_data_get_irq_chip_data(data); + u32 reg_set = hwirq_to_reg_set(data->hwirq); + u32 group = hwirq_to_group(data->hwirq); + u64 target_addr = msi->msi_addr + (((8 * group) + reg_set) << 16); + + msg->address_hi = upper_32_bits(target_addr); + msg->address_lo = lower_32_bits(target_addr); + msg->data = hwirq_to_msi_data(data->hwirq); +} + +/* + * X-Gene v1 only has 16 MSI GIC IRQs for 2048 MSI vectors. To maintain + * the expected behaviour of .set_affinity for each MSI interrupt, the 16 + * MSI GIC IRQs are statically allocated to 8 X-Gene v1 cores (2 GIC IRQs + * for each core). The MSI vector is moved fom 1 MSI GIC IRQ to another + * MSI GIC IRQ to steer its MSI interrupt to correct X-Gene v1 core. As a + * consequence, the total MSI vectors that X-Gene v1 supports will be + * reduced to 256 (2048/8) vectors. + */ +static int hwirq_to_cpu(unsigned long hwirq) +{ + return (hwirq % xgene_msi_ctrl.num_cpus); +} + +static unsigned long hwirq_to_canonical_hwirq(unsigned long hwirq) +{ + return (hwirq - hwirq_to_cpu(hwirq)); +} + +static int xgene_msi_set_affinity(struct irq_data *irqdata, + const struct cpumask *mask, bool force) +{ + int target_cpu = cpumask_first(mask); + int curr_cpu; + + curr_cpu = hwirq_to_cpu(irqdata->hwirq); + if (curr_cpu == target_cpu) + return IRQ_SET_MASK_OK_DONE; + + /* Update MSI number to target the new CPU */ + irqdata->hwirq = hwirq_to_canonical_hwirq(irqdata->hwirq) + target_cpu; + + return IRQ_SET_MASK_OK; +} + +static struct irq_chip xgene_msi_bottom_irq_chip = { + .name = "MSI", + .irq_set_affinity = xgene_msi_set_affinity, + .irq_compose_msi_msg = xgene_compose_msi_msg, +}; + +static int xgene_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct xgene_msi *msi = domain->host_data; + int msi_irq; + + mutex_lock(&msi->bitmap_lock); + + msi_irq = bitmap_find_next_zero_area(msi->bitmap, NR_MSI_VEC, 0, + msi->num_cpus, 0); + if (msi_irq < NR_MSI_VEC) + bitmap_set(msi->bitmap, msi_irq, msi->num_cpus); + else + msi_irq = -ENOSPC; + + mutex_unlock(&msi->bitmap_lock); + + if (msi_irq < 0) + return msi_irq; + + irq_domain_set_info(domain, virq, msi_irq, + &xgene_msi_bottom_irq_chip, domain->host_data, + handle_simple_irq, NULL, NULL); + + return 0; +} + +static void xgene_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct xgene_msi *msi = irq_data_get_irq_chip_data(d); + u32 hwirq; + + mutex_lock(&msi->bitmap_lock); + + hwirq = hwirq_to_canonical_hwirq(d->hwirq); + bitmap_clear(msi->bitmap, hwirq, msi->num_cpus); + + mutex_unlock(&msi->bitmap_lock); + + irq_domain_free_irqs_parent(domain, virq, nr_irqs); +} + +static const struct irq_domain_ops msi_domain_ops = { + .alloc = xgene_irq_domain_alloc, + .free = xgene_irq_domain_free, +}; + +static int xgene_allocate_domains(struct xgene_msi *msi) +{ + msi->inner_domain = irq_domain_add_linear(NULL, NR_MSI_VEC, + &msi_domain_ops, msi); + if (!msi->inner_domain) + return -ENOMEM; + + msi->msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(msi->node), + &xgene_msi_domain_info, + msi->inner_domain); + + if (!msi->msi_domain) { + irq_domain_remove(msi->inner_domain); + return -ENOMEM; + } + + return 0; +} + +static void xgene_free_domains(struct xgene_msi *msi) +{ + if (msi->msi_domain) + irq_domain_remove(msi->msi_domain); + if (msi->inner_domain) + irq_domain_remove(msi->inner_domain); +} + +static int xgene_msi_init_allocator(struct xgene_msi *xgene_msi) +{ + xgene_msi->bitmap = bitmap_zalloc(NR_MSI_VEC, GFP_KERNEL); + if (!xgene_msi->bitmap) + return -ENOMEM; + + mutex_init(&xgene_msi->bitmap_lock); + + xgene_msi->msi_groups = kcalloc(NR_HW_IRQS, + sizeof(struct xgene_msi_group), + GFP_KERNEL); + if (!xgene_msi->msi_groups) + return -ENOMEM; + + return 0; +} + +static void xgene_msi_isr(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct xgene_msi_group *msi_groups; + struct xgene_msi *xgene_msi; + int msir_index, msir_val, hw_irq, ret; + u32 intr_index, grp_select, msi_grp; + + chained_irq_enter(chip, desc); + + msi_groups = irq_desc_get_handler_data(desc); + xgene_msi = msi_groups->msi; + msi_grp = msi_groups->msi_grp; + + /* + * MSIINTn (n is 0..F) indicates if there is a pending MSI interrupt + * If bit x of this register is set (x is 0..7), one or more interrupts + * corresponding to MSInIRx is set. + */ + grp_select = xgene_msi_int_read(xgene_msi, msi_grp); + while (grp_select) { + msir_index = ffs(grp_select) - 1; + /* + * Calculate MSInIRx address to read to check for interrupts + * (refer to termination address and data assignment + * described in xgene_compose_msi_msg() ) + */ + msir_val = xgene_msi_ir_read(xgene_msi, msi_grp, msir_index); + while (msir_val) { + intr_index = ffs(msir_val) - 1; + /* + * Calculate MSI vector number (refer to the termination + * address and data assignment described in + * xgene_compose_msi_msg function) + */ + hw_irq = (((msir_index * IRQS_PER_IDX) + intr_index) * + NR_HW_IRQS) + msi_grp; + /* + * As we have multiple hw_irq that maps to single MSI, + * always look up the virq using the hw_irq as seen from + * CPU0 + */ + hw_irq = hwirq_to_canonical_hwirq(hw_irq); + ret = generic_handle_domain_irq(xgene_msi->inner_domain, hw_irq); + WARN_ON_ONCE(ret); + msir_val &= ~(1 << intr_index); + } + grp_select &= ~(1 << msir_index); + + if (!grp_select) { + /* + * We handled all interrupts happened in this group, + * resample this group MSI_INTx register in case + * something else has been made pending in the meantime + */ + grp_select = xgene_msi_int_read(xgene_msi, msi_grp); + } + } + + chained_irq_exit(chip, desc); +} + +static enum cpuhp_state pci_xgene_online; + +static int xgene_msi_remove(struct platform_device *pdev) +{ + struct xgene_msi *msi = platform_get_drvdata(pdev); + + if (pci_xgene_online) + cpuhp_remove_state(pci_xgene_online); + cpuhp_remove_state(CPUHP_PCI_XGENE_DEAD); + + kfree(msi->msi_groups); + + bitmap_free(msi->bitmap); + msi->bitmap = NULL; + + xgene_free_domains(msi); + + return 0; +} + +static int xgene_msi_hwirq_alloc(unsigned int cpu) +{ + struct xgene_msi *msi = &xgene_msi_ctrl; + struct xgene_msi_group *msi_group; + cpumask_var_t mask; + int i; + int err; + + for (i = cpu; i < NR_HW_IRQS; i += msi->num_cpus) { + msi_group = &msi->msi_groups[i]; + if (!msi_group->gic_irq) + continue; + + irq_set_chained_handler_and_data(msi_group->gic_irq, + xgene_msi_isr, msi_group); + + /* + * Statically allocate MSI GIC IRQs to each CPU core. + * With 8-core X-Gene v1, 2 MSI GIC IRQs are allocated + * to each core. + */ + if (alloc_cpumask_var(&mask, GFP_KERNEL)) { + cpumask_clear(mask); + cpumask_set_cpu(cpu, mask); + err = irq_set_affinity(msi_group->gic_irq, mask); + if (err) + pr_err("failed to set affinity for GIC IRQ"); + free_cpumask_var(mask); + } else { + pr_err("failed to alloc CPU mask for affinity\n"); + err = -EINVAL; + } + + if (err) { + irq_set_chained_handler_and_data(msi_group->gic_irq, + NULL, NULL); + return err; + } + } + + return 0; +} + +static int xgene_msi_hwirq_free(unsigned int cpu) +{ + struct xgene_msi *msi = &xgene_msi_ctrl; + struct xgene_msi_group *msi_group; + int i; + + for (i = cpu; i < NR_HW_IRQS; i += msi->num_cpus) { + msi_group = &msi->msi_groups[i]; + if (!msi_group->gic_irq) + continue; + + irq_set_chained_handler_and_data(msi_group->gic_irq, NULL, + NULL); + } + return 0; +} + +static const struct of_device_id xgene_msi_match_table[] = { + {.compatible = "apm,xgene1-msi"}, + {}, +}; + +static int xgene_msi_probe(struct platform_device *pdev) +{ + struct resource *res; + int rc, irq_index; + struct xgene_msi *xgene_msi; + int virt_msir; + u32 msi_val, msi_idx; + + xgene_msi = &xgene_msi_ctrl; + + platform_set_drvdata(pdev, xgene_msi); + + res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + xgene_msi->msi_regs = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(xgene_msi->msi_regs)) { + rc = PTR_ERR(xgene_msi->msi_regs); + goto error; + } + xgene_msi->msi_addr = res->start; + xgene_msi->node = pdev->dev.of_node; + xgene_msi->num_cpus = num_possible_cpus(); + + rc = xgene_msi_init_allocator(xgene_msi); + if (rc) { + dev_err(&pdev->dev, "Error allocating MSI bitmap\n"); + goto error; + } + + rc = xgene_allocate_domains(xgene_msi); + if (rc) { + dev_err(&pdev->dev, "Failed to allocate MSI domain\n"); + goto error; + } + + for (irq_index = 0; irq_index < NR_HW_IRQS; irq_index++) { + virt_msir = platform_get_irq(pdev, irq_index); + if (virt_msir < 0) { + rc = virt_msir; + goto error; + } + xgene_msi->msi_groups[irq_index].gic_irq = virt_msir; + xgene_msi->msi_groups[irq_index].msi_grp = irq_index; + xgene_msi->msi_groups[irq_index].msi = xgene_msi; + } + + /* + * MSInIRx registers are read-to-clear; before registering + * interrupt handlers, read all of them to clear spurious + * interrupts that may occur before the driver is probed. + */ + for (irq_index = 0; irq_index < NR_HW_IRQS; irq_index++) { + for (msi_idx = 0; msi_idx < IDX_PER_GROUP; msi_idx++) + xgene_msi_ir_read(xgene_msi, irq_index, msi_idx); + + /* Read MSIINTn to confirm */ + msi_val = xgene_msi_int_read(xgene_msi, irq_index); + if (msi_val) { + dev_err(&pdev->dev, "Failed to clear spurious IRQ\n"); + rc = -EINVAL; + goto error; + } + } + + rc = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "pci/xgene:online", + xgene_msi_hwirq_alloc, NULL); + if (rc < 0) + goto err_cpuhp; + pci_xgene_online = rc; + rc = cpuhp_setup_state(CPUHP_PCI_XGENE_DEAD, "pci/xgene:dead", NULL, + xgene_msi_hwirq_free); + if (rc) + goto err_cpuhp; + + dev_info(&pdev->dev, "APM X-Gene PCIe MSI driver loaded\n"); + + return 0; + +err_cpuhp: + dev_err(&pdev->dev, "failed to add CPU MSI notifier\n"); +error: + xgene_msi_remove(pdev); + return rc; +} + +static struct platform_driver xgene_msi_driver = { + .driver = { + .name = "xgene-msi", + .of_match_table = xgene_msi_match_table, + }, + .probe = xgene_msi_probe, + .remove = xgene_msi_remove, +}; + +static int __init xgene_pcie_msi_init(void) +{ + return platform_driver_register(&xgene_msi_driver); +} +subsys_initcall(xgene_pcie_msi_init); diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c new file mode 100644 index 000000000..549d3bd6d --- /dev/null +++ b/drivers/pci/controller/pci-xgene.c @@ -0,0 +1,650 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * APM X-Gene PCIe Driver + * + * Copyright (c) 2014 Applied Micro Circuits Corporation. + * + * Author: Tanmay Inamdar <tinamdar@apm.com>. + */ +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/io.h> +#include <linux/jiffies.h> +#include <linux/memblock.h> +#include <linux/init.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "../pci.h" + +#define PCIECORE_CTLANDSTATUS 0x50 +#define PIM1_1L 0x80 +#define IBAR2 0x98 +#define IR2MSK 0x9c +#define PIM2_1L 0xa0 +#define IBAR3L 0xb4 +#define IR3MSKL 0xbc +#define PIM3_1L 0xc4 +#define OMR1BARL 0x100 +#define OMR2BARL 0x118 +#define OMR3BARL 0x130 +#define CFGBARL 0x154 +#define CFGBARH 0x158 +#define CFGCTL 0x15c +#define RTDID 0x160 +#define BRIDGE_CFG_0 0x2000 +#define BRIDGE_CFG_4 0x2010 +#define BRIDGE_STATUS_0 0x2600 + +#define LINK_UP_MASK 0x00000100 +#define AXI_EP_CFG_ACCESS 0x10000 +#define EN_COHERENCY 0xF0000000 +#define EN_REG 0x00000001 +#define OB_LO_IO 0x00000002 +#define XGENE_PCIE_DEVICEID 0xE004 +#define PIPE_PHY_RATE_RD(src) ((0xc000 & (u32)(src)) >> 0xe) + +#define XGENE_V1_PCI_EXP_CAP 0x40 + +/* PCIe IP version */ +#define XGENE_PCIE_IP_VER_UNKN 0 +#define XGENE_PCIE_IP_VER_1 1 +#define XGENE_PCIE_IP_VER_2 2 + +#if defined(CONFIG_PCI_XGENE) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)) +struct xgene_pcie { + struct device_node *node; + struct device *dev; + struct clk *clk; + void __iomem *csr_base; + void __iomem *cfg_base; + unsigned long cfg_addr; + bool link_up; + u32 version; +}; + +static u32 xgene_pcie_readl(struct xgene_pcie *port, u32 reg) +{ + return readl(port->csr_base + reg); +} + +static void xgene_pcie_writel(struct xgene_pcie *port, u32 reg, u32 val) +{ + writel(val, port->csr_base + reg); +} + +static inline u32 pcie_bar_low_val(u32 addr, u32 flags) +{ + return (addr & PCI_BASE_ADDRESS_MEM_MASK) | flags; +} + +static inline struct xgene_pcie *pcie_bus_to_port(struct pci_bus *bus) +{ + struct pci_config_window *cfg; + + if (acpi_disabled) + return (struct xgene_pcie *)(bus->sysdata); + + cfg = bus->sysdata; + return (struct xgene_pcie *)(cfg->priv); +} + +/* + * When the address bit [17:16] is 2'b01, the Configuration access will be + * treated as Type 1 and it will be forwarded to external PCIe device. + */ +static void __iomem *xgene_pcie_get_cfg_base(struct pci_bus *bus) +{ + struct xgene_pcie *port = pcie_bus_to_port(bus); + + if (bus->number >= (bus->primary + 1)) + return port->cfg_base + AXI_EP_CFG_ACCESS; + + return port->cfg_base; +} + +/* + * For Configuration request, RTDID register is used as Bus Number, + * Device Number and Function number of the header fields. + */ +static void xgene_pcie_set_rtdid_reg(struct pci_bus *bus, uint devfn) +{ + struct xgene_pcie *port = pcie_bus_to_port(bus); + unsigned int b, d, f; + u32 rtdid_val = 0; + + b = bus->number; + d = PCI_SLOT(devfn); + f = PCI_FUNC(devfn); + + if (!pci_is_root_bus(bus)) + rtdid_val = (b << 8) | (d << 3) | f; + + xgene_pcie_writel(port, RTDID, rtdid_val); + /* read the register back to ensure flush */ + xgene_pcie_readl(port, RTDID); +} + +/* + * X-Gene PCIe port uses BAR0-BAR1 of RC's configuration space as + * the translation from PCI bus to native BUS. Entire DDR region + * is mapped into PCIe space using these registers, so it can be + * reached by DMA from EP devices. The BAR0/1 of bridge should be + * hidden during enumeration to avoid the sizing and resource allocation + * by PCIe core. + */ +static bool xgene_pcie_hide_rc_bars(struct pci_bus *bus, int offset) +{ + if (pci_is_root_bus(bus) && ((offset == PCI_BASE_ADDRESS_0) || + (offset == PCI_BASE_ADDRESS_1))) + return true; + + return false; +} + +static void __iomem *xgene_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, + int offset) +{ + if ((pci_is_root_bus(bus) && devfn != 0) || + xgene_pcie_hide_rc_bars(bus, offset)) + return NULL; + + xgene_pcie_set_rtdid_reg(bus, devfn); + return xgene_pcie_get_cfg_base(bus) + offset; +} + +static int xgene_pcie_config_read32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct xgene_pcie *port = pcie_bus_to_port(bus); + + if (pci_generic_config_read32(bus, devfn, where & ~0x3, 4, val) != + PCIBIOS_SUCCESSFUL) + return PCIBIOS_DEVICE_NOT_FOUND; + + /* + * The v1 controller has a bug in its Configuration Request Retry + * Status (CRS) logic: when CRS Software Visibility is enabled and + * we read the Vendor and Device ID of a non-existent device, the + * controller fabricates return data of 0xFFFF0001 ("device exists + * but is not ready") instead of 0xFFFFFFFF (PCI_ERROR_RESPONSE) + * ("device does not exist"). This causes the PCI core to retry + * the read until it times out. Avoid this by not claiming to + * support CRS SV. + */ + if (pci_is_root_bus(bus) && (port->version == XGENE_PCIE_IP_VER_1) && + ((where & ~0x3) == XGENE_V1_PCI_EXP_CAP + PCI_EXP_RTCTL)) + *val &= ~(PCI_EXP_RTCAP_CRSVIS << 16); + + if (size <= 2) + *val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); + + return PCIBIOS_SUCCESSFUL; +} +#endif + +#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) +static int xgene_get_csr_resource(struct acpi_device *adev, + struct resource *res) +{ + struct device *dev = &adev->dev; + struct resource_entry *entry; + struct list_head list; + unsigned long flags; + int ret; + + INIT_LIST_HEAD(&list); + flags = IORESOURCE_MEM; + ret = acpi_dev_get_resources(adev, &list, + acpi_dev_filter_resource_type_cb, + (void *) flags); + if (ret < 0) { + dev_err(dev, "failed to parse _CRS method, error code %d\n", + ret); + return ret; + } + + if (ret == 0) { + dev_err(dev, "no IO and memory resources present in _CRS\n"); + return -EINVAL; + } + + entry = list_first_entry(&list, struct resource_entry, node); + *res = *entry->res; + acpi_dev_free_resource_list(&list); + return 0; +} + +static int xgene_pcie_ecam_init(struct pci_config_window *cfg, u32 ipversion) +{ + struct device *dev = cfg->parent; + struct acpi_device *adev = to_acpi_device(dev); + struct xgene_pcie *port; + struct resource csr; + int ret; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + ret = xgene_get_csr_resource(adev, &csr); + if (ret) { + dev_err(dev, "can't get CSR resource\n"); + return ret; + } + port->csr_base = devm_pci_remap_cfg_resource(dev, &csr); + if (IS_ERR(port->csr_base)) + return PTR_ERR(port->csr_base); + + port->cfg_base = cfg->win; + port->version = ipversion; + + cfg->priv = port; + return 0; +} + +static int xgene_v1_pcie_ecam_init(struct pci_config_window *cfg) +{ + return xgene_pcie_ecam_init(cfg, XGENE_PCIE_IP_VER_1); +} + +const struct pci_ecam_ops xgene_v1_pcie_ecam_ops = { + .init = xgene_v1_pcie_ecam_init, + .pci_ops = { + .map_bus = xgene_pcie_map_bus, + .read = xgene_pcie_config_read32, + .write = pci_generic_config_write, + } +}; + +static int xgene_v2_pcie_ecam_init(struct pci_config_window *cfg) +{ + return xgene_pcie_ecam_init(cfg, XGENE_PCIE_IP_VER_2); +} + +const struct pci_ecam_ops xgene_v2_pcie_ecam_ops = { + .init = xgene_v2_pcie_ecam_init, + .pci_ops = { + .map_bus = xgene_pcie_map_bus, + .read = xgene_pcie_config_read32, + .write = pci_generic_config_write, + } +}; +#endif + +#if defined(CONFIG_PCI_XGENE) +static u64 xgene_pcie_set_ib_mask(struct xgene_pcie *port, u32 addr, + u32 flags, u64 size) +{ + u64 mask = (~(size - 1) & PCI_BASE_ADDRESS_MEM_MASK) | flags; + u32 val32 = 0; + u32 val; + + val32 = xgene_pcie_readl(port, addr); + val = (val32 & 0x0000ffff) | (lower_32_bits(mask) << 16); + xgene_pcie_writel(port, addr, val); + + val32 = xgene_pcie_readl(port, addr + 0x04); + val = (val32 & 0xffff0000) | (lower_32_bits(mask) >> 16); + xgene_pcie_writel(port, addr + 0x04, val); + + val32 = xgene_pcie_readl(port, addr + 0x04); + val = (val32 & 0x0000ffff) | (upper_32_bits(mask) << 16); + xgene_pcie_writel(port, addr + 0x04, val); + + val32 = xgene_pcie_readl(port, addr + 0x08); + val = (val32 & 0xffff0000) | (upper_32_bits(mask) >> 16); + xgene_pcie_writel(port, addr + 0x08, val); + + return mask; +} + +static void xgene_pcie_linkup(struct xgene_pcie *port, + u32 *lanes, u32 *speed) +{ + u32 val32; + + port->link_up = false; + val32 = xgene_pcie_readl(port, PCIECORE_CTLANDSTATUS); + if (val32 & LINK_UP_MASK) { + port->link_up = true; + *speed = PIPE_PHY_RATE_RD(val32); + val32 = xgene_pcie_readl(port, BRIDGE_STATUS_0); + *lanes = val32 >> 26; + } +} + +static int xgene_pcie_init_port(struct xgene_pcie *port) +{ + struct device *dev = port->dev; + int rc; + + port->clk = clk_get(dev, NULL); + if (IS_ERR(port->clk)) { + dev_err(dev, "clock not available\n"); + return -ENODEV; + } + + rc = clk_prepare_enable(port->clk); + if (rc) { + dev_err(dev, "clock enable failed\n"); + return rc; + } + + return 0; +} + +static int xgene_pcie_map_reg(struct xgene_pcie *port, + struct platform_device *pdev) +{ + struct device *dev = port->dev; + struct resource *res; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "csr"); + port->csr_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(port->csr_base)) + return PTR_ERR(port->csr_base); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg"); + port->cfg_base = devm_ioremap_resource(dev, res); + if (IS_ERR(port->cfg_base)) + return PTR_ERR(port->cfg_base); + port->cfg_addr = res->start; + + return 0; +} + +static void xgene_pcie_setup_ob_reg(struct xgene_pcie *port, + struct resource *res, u32 offset, + u64 cpu_addr, u64 pci_addr) +{ + struct device *dev = port->dev; + resource_size_t size = resource_size(res); + u64 restype = resource_type(res); + u64 mask = 0; + u32 min_size; + u32 flag = EN_REG; + + if (restype == IORESOURCE_MEM) { + min_size = SZ_128M; + } else { + min_size = 128; + flag |= OB_LO_IO; + } + + if (size >= min_size) + mask = ~(size - 1) | flag; + else + dev_warn(dev, "res size 0x%llx less than minimum 0x%x\n", + (u64)size, min_size); + + xgene_pcie_writel(port, offset, lower_32_bits(cpu_addr)); + xgene_pcie_writel(port, offset + 0x04, upper_32_bits(cpu_addr)); + xgene_pcie_writel(port, offset + 0x08, lower_32_bits(mask)); + xgene_pcie_writel(port, offset + 0x0c, upper_32_bits(mask)); + xgene_pcie_writel(port, offset + 0x10, lower_32_bits(pci_addr)); + xgene_pcie_writel(port, offset + 0x14, upper_32_bits(pci_addr)); +} + +static void xgene_pcie_setup_cfg_reg(struct xgene_pcie *port) +{ + u64 addr = port->cfg_addr; + + xgene_pcie_writel(port, CFGBARL, lower_32_bits(addr)); + xgene_pcie_writel(port, CFGBARH, upper_32_bits(addr)); + xgene_pcie_writel(port, CFGCTL, EN_REG); +} + +static int xgene_pcie_map_ranges(struct xgene_pcie *port) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(port); + struct resource_entry *window; + struct device *dev = port->dev; + + resource_list_for_each_entry(window, &bridge->windows) { + struct resource *res = window->res; + u64 restype = resource_type(res); + + dev_dbg(dev, "%pR\n", res); + + switch (restype) { + case IORESOURCE_IO: + xgene_pcie_setup_ob_reg(port, res, OMR3BARL, + pci_pio_to_address(res->start), + res->start - window->offset); + break; + case IORESOURCE_MEM: + if (res->flags & IORESOURCE_PREFETCH) + xgene_pcie_setup_ob_reg(port, res, OMR2BARL, + res->start, + res->start - + window->offset); + else + xgene_pcie_setup_ob_reg(port, res, OMR1BARL, + res->start, + res->start - + window->offset); + break; + case IORESOURCE_BUS: + break; + default: + dev_err(dev, "invalid resource %pR\n", res); + return -EINVAL; + } + } + xgene_pcie_setup_cfg_reg(port); + return 0; +} + +static void xgene_pcie_setup_pims(struct xgene_pcie *port, u32 pim_reg, + u64 pim, u64 size) +{ + xgene_pcie_writel(port, pim_reg, lower_32_bits(pim)); + xgene_pcie_writel(port, pim_reg + 0x04, + upper_32_bits(pim) | EN_COHERENCY); + xgene_pcie_writel(port, pim_reg + 0x10, lower_32_bits(size)); + xgene_pcie_writel(port, pim_reg + 0x14, upper_32_bits(size)); +} + +/* + * X-Gene PCIe support maximum 3 inbound memory regions + * This function helps to select a region based on size of region + */ +static int xgene_pcie_select_ib_reg(u8 *ib_reg_mask, u64 size) +{ + if ((size > 4) && (size < SZ_16M) && !(*ib_reg_mask & (1 << 1))) { + *ib_reg_mask |= (1 << 1); + return 1; + } + + if ((size > SZ_1K) && (size < SZ_1T) && !(*ib_reg_mask & (1 << 0))) { + *ib_reg_mask |= (1 << 0); + return 0; + } + + if ((size > SZ_1M) && (size < SZ_1T) && !(*ib_reg_mask & (1 << 2))) { + *ib_reg_mask |= (1 << 2); + return 2; + } + + return -EINVAL; +} + +static void xgene_pcie_setup_ib_reg(struct xgene_pcie *port, + struct of_pci_range *range, u8 *ib_reg_mask) +{ + void __iomem *cfg_base = port->cfg_base; + struct device *dev = port->dev; + void __iomem *bar_addr; + u32 pim_reg; + u64 cpu_addr = range->cpu_addr; + u64 pci_addr = range->pci_addr; + u64 size = range->size; + u64 mask = ~(size - 1) | EN_REG; + u32 flags = PCI_BASE_ADDRESS_MEM_TYPE_64; + u32 bar_low; + int region; + + region = xgene_pcie_select_ib_reg(ib_reg_mask, range->size); + if (region < 0) { + dev_warn(dev, "invalid pcie dma-range config\n"); + return; + } + + if (range->flags & IORESOURCE_PREFETCH) + flags |= PCI_BASE_ADDRESS_MEM_PREFETCH; + + bar_low = pcie_bar_low_val((u32)cpu_addr, flags); + switch (region) { + case 0: + xgene_pcie_set_ib_mask(port, BRIDGE_CFG_4, flags, size); + bar_addr = cfg_base + PCI_BASE_ADDRESS_0; + writel(bar_low, bar_addr); + writel(upper_32_bits(cpu_addr), bar_addr + 0x4); + pim_reg = PIM1_1L; + break; + case 1: + xgene_pcie_writel(port, IBAR2, bar_low); + xgene_pcie_writel(port, IR2MSK, lower_32_bits(mask)); + pim_reg = PIM2_1L; + break; + case 2: + xgene_pcie_writel(port, IBAR3L, bar_low); + xgene_pcie_writel(port, IBAR3L + 0x4, upper_32_bits(cpu_addr)); + xgene_pcie_writel(port, IR3MSKL, lower_32_bits(mask)); + xgene_pcie_writel(port, IR3MSKL + 0x4, upper_32_bits(mask)); + pim_reg = PIM3_1L; + break; + } + + xgene_pcie_setup_pims(port, pim_reg, pci_addr, ~(size - 1)); +} + +static int xgene_pcie_parse_map_dma_ranges(struct xgene_pcie *port) +{ + struct device_node *np = port->node; + struct of_pci_range range; + struct of_pci_range_parser parser; + struct device *dev = port->dev; + u8 ib_reg_mask = 0; + + if (of_pci_dma_range_parser_init(&parser, np)) { + dev_err(dev, "missing dma-ranges property\n"); + return -EINVAL; + } + + /* Get the dma-ranges from DT */ + for_each_of_pci_range(&parser, &range) { + u64 end = range.cpu_addr + range.size - 1; + + dev_dbg(dev, "0x%08x 0x%016llx..0x%016llx -> 0x%016llx\n", + range.flags, range.cpu_addr, end, range.pci_addr); + xgene_pcie_setup_ib_reg(port, &range, &ib_reg_mask); + } + return 0; +} + +/* clear BAR configuration which was done by firmware */ +static void xgene_pcie_clear_config(struct xgene_pcie *port) +{ + int i; + + for (i = PIM1_1L; i <= CFGCTL; i += 4) + xgene_pcie_writel(port, i, 0); +} + +static int xgene_pcie_setup(struct xgene_pcie *port) +{ + struct device *dev = port->dev; + u32 val, lanes = 0, speed = 0; + int ret; + + xgene_pcie_clear_config(port); + + /* setup the vendor and device IDs correctly */ + val = (XGENE_PCIE_DEVICEID << 16) | PCI_VENDOR_ID_AMCC; + xgene_pcie_writel(port, BRIDGE_CFG_0, val); + + ret = xgene_pcie_map_ranges(port); + if (ret) + return ret; + + ret = xgene_pcie_parse_map_dma_ranges(port); + if (ret) + return ret; + + xgene_pcie_linkup(port, &lanes, &speed); + if (!port->link_up) + dev_info(dev, "(rc) link down\n"); + else + dev_info(dev, "(rc) x%d gen-%d link up\n", lanes, speed + 1); + return 0; +} + +static struct pci_ops xgene_pcie_ops = { + .map_bus = xgene_pcie_map_bus, + .read = xgene_pcie_config_read32, + .write = pci_generic_config_write32, +}; + +static int xgene_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct device_node *dn = dev->of_node; + struct xgene_pcie *port; + struct pci_host_bridge *bridge; + int ret; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*port)); + if (!bridge) + return -ENOMEM; + + port = pci_host_bridge_priv(bridge); + + port->node = of_node_get(dn); + port->dev = dev; + + port->version = XGENE_PCIE_IP_VER_UNKN; + if (of_device_is_compatible(port->node, "apm,xgene-pcie")) + port->version = XGENE_PCIE_IP_VER_1; + + ret = xgene_pcie_map_reg(port, pdev); + if (ret) + return ret; + + ret = xgene_pcie_init_port(port); + if (ret) + return ret; + + ret = xgene_pcie_setup(port); + if (ret) + return ret; + + bridge->sysdata = port; + bridge->ops = &xgene_pcie_ops; + + return pci_host_probe(bridge); +} + +static const struct of_device_id xgene_pcie_match_table[] = { + {.compatible = "apm,xgene-pcie",}, + {}, +}; + +static struct platform_driver xgene_pcie_driver = { + .driver = { + .name = "xgene-pcie", + .of_match_table = xgene_pcie_match_table, + .suppress_bind_attrs = true, + }, + .probe = xgene_pcie_probe, +}; +builtin_platform_driver(xgene_pcie_driver); +#endif diff --git a/drivers/pci/controller/pcie-altera-msi.c b/drivers/pci/controller/pcie-altera-msi.c new file mode 100644 index 000000000..7b1d3ebc3 --- /dev/null +++ b/drivers/pci/controller/pcie-altera-msi.c @@ -0,0 +1,294 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Altera PCIe MSI support + * + * Author: Ley Foon Tan <lftan@altera.com> + * + * Copyright Altera Corporation (C) 2013-2015. All rights reserved + */ + +#include <linux/interrupt.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#define MSI_STATUS 0x0 +#define MSI_ERROR 0x4 +#define MSI_INTMASK 0x8 + +#define MAX_MSI_VECTORS 32 + +struct altera_msi { + DECLARE_BITMAP(used, MAX_MSI_VECTORS); + struct mutex lock; /* protect "used" bitmap */ + struct platform_device *pdev; + struct irq_domain *msi_domain; + struct irq_domain *inner_domain; + void __iomem *csr_base; + void __iomem *vector_base; + phys_addr_t vector_phy; + u32 num_of_vectors; + int irq; +}; + +static inline void msi_writel(struct altera_msi *msi, const u32 value, + const u32 reg) +{ + writel_relaxed(value, msi->csr_base + reg); +} + +static inline u32 msi_readl(struct altera_msi *msi, const u32 reg) +{ + return readl_relaxed(msi->csr_base + reg); +} + +static void altera_msi_isr(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct altera_msi *msi; + unsigned long status; + u32 bit; + int ret; + + chained_irq_enter(chip, desc); + msi = irq_desc_get_handler_data(desc); + + while ((status = msi_readl(msi, MSI_STATUS)) != 0) { + for_each_set_bit(bit, &status, msi->num_of_vectors) { + /* Dummy read from vector to clear the interrupt */ + readl_relaxed(msi->vector_base + (bit * sizeof(u32))); + + ret = generic_handle_domain_irq(msi->inner_domain, bit); + if (ret) + dev_err_ratelimited(&msi->pdev->dev, "unexpected MSI\n"); + } + } + + chained_irq_exit(chip, desc); +} + +static struct irq_chip altera_msi_irq_chip = { + .name = "Altera PCIe MSI", + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, +}; + +static struct msi_domain_info altera_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX), + .chip = &altera_msi_irq_chip, +}; + +static void altera_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct altera_msi *msi = irq_data_get_irq_chip_data(data); + phys_addr_t addr = msi->vector_phy + (data->hwirq * sizeof(u32)); + + msg->address_lo = lower_32_bits(addr); + msg->address_hi = upper_32_bits(addr); + msg->data = data->hwirq; + + dev_dbg(&msi->pdev->dev, "msi#%d address_hi %#x address_lo %#x\n", + (int)data->hwirq, msg->address_hi, msg->address_lo); +} + +static int altera_msi_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static struct irq_chip altera_msi_bottom_irq_chip = { + .name = "Altera MSI", + .irq_compose_msi_msg = altera_compose_msi_msg, + .irq_set_affinity = altera_msi_set_affinity, +}; + +static int altera_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct altera_msi *msi = domain->host_data; + unsigned long bit; + u32 mask; + + WARN_ON(nr_irqs != 1); + mutex_lock(&msi->lock); + + bit = find_first_zero_bit(msi->used, msi->num_of_vectors); + if (bit >= msi->num_of_vectors) { + mutex_unlock(&msi->lock); + return -ENOSPC; + } + + set_bit(bit, msi->used); + + mutex_unlock(&msi->lock); + + irq_domain_set_info(domain, virq, bit, &altera_msi_bottom_irq_chip, + domain->host_data, handle_simple_irq, + NULL, NULL); + + mask = msi_readl(msi, MSI_INTMASK); + mask |= 1 << bit; + msi_writel(msi, mask, MSI_INTMASK); + + return 0; +} + +static void altera_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct altera_msi *msi = irq_data_get_irq_chip_data(d); + u32 mask; + + mutex_lock(&msi->lock); + + if (!test_bit(d->hwirq, msi->used)) { + dev_err(&msi->pdev->dev, "trying to free unused MSI#%lu\n", + d->hwirq); + } else { + __clear_bit(d->hwirq, msi->used); + mask = msi_readl(msi, MSI_INTMASK); + mask &= ~(1 << d->hwirq); + msi_writel(msi, mask, MSI_INTMASK); + } + + mutex_unlock(&msi->lock); +} + +static const struct irq_domain_ops msi_domain_ops = { + .alloc = altera_irq_domain_alloc, + .free = altera_irq_domain_free, +}; + +static int altera_allocate_domains(struct altera_msi *msi) +{ + struct fwnode_handle *fwnode = of_node_to_fwnode(msi->pdev->dev.of_node); + + msi->inner_domain = irq_domain_add_linear(NULL, msi->num_of_vectors, + &msi_domain_ops, msi); + if (!msi->inner_domain) { + dev_err(&msi->pdev->dev, "failed to create IRQ domain\n"); + return -ENOMEM; + } + + msi->msi_domain = pci_msi_create_irq_domain(fwnode, + &altera_msi_domain_info, msi->inner_domain); + if (!msi->msi_domain) { + dev_err(&msi->pdev->dev, "failed to create MSI domain\n"); + irq_domain_remove(msi->inner_domain); + return -ENOMEM; + } + + return 0; +} + +static void altera_free_domains(struct altera_msi *msi) +{ + irq_domain_remove(msi->msi_domain); + irq_domain_remove(msi->inner_domain); +} + +static int altera_msi_remove(struct platform_device *pdev) +{ + struct altera_msi *msi = platform_get_drvdata(pdev); + + msi_writel(msi, 0, MSI_INTMASK); + irq_set_chained_handler_and_data(msi->irq, NULL, NULL); + + altera_free_domains(msi); + + platform_set_drvdata(pdev, NULL); + return 0; +} + +static int altera_msi_probe(struct platform_device *pdev) +{ + struct altera_msi *msi; + struct device_node *np = pdev->dev.of_node; + struct resource *res; + int ret; + + msi = devm_kzalloc(&pdev->dev, sizeof(struct altera_msi), + GFP_KERNEL); + if (!msi) + return -ENOMEM; + + mutex_init(&msi->lock); + msi->pdev = pdev; + + msi->csr_base = devm_platform_ioremap_resource_byname(pdev, "csr"); + if (IS_ERR(msi->csr_base)) { + dev_err(&pdev->dev, "failed to map csr memory\n"); + return PTR_ERR(msi->csr_base); + } + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, + "vector_slave"); + msi->vector_base = devm_ioremap_resource(&pdev->dev, res); + if (IS_ERR(msi->vector_base)) + return PTR_ERR(msi->vector_base); + + msi->vector_phy = res->start; + + if (of_property_read_u32(np, "num-vectors", &msi->num_of_vectors)) { + dev_err(&pdev->dev, "failed to parse the number of vectors\n"); + return -EINVAL; + } + + ret = altera_allocate_domains(msi); + if (ret) + return ret; + + msi->irq = platform_get_irq(pdev, 0); + if (msi->irq < 0) { + ret = msi->irq; + goto err; + } + + irq_set_chained_handler_and_data(msi->irq, altera_msi_isr, msi); + platform_set_drvdata(pdev, msi); + + return 0; + +err: + altera_msi_remove(pdev); + return ret; +} + +static const struct of_device_id altera_msi_of_match[] = { + { .compatible = "altr,msi-1.0", NULL }, + { }, +}; + +static struct platform_driver altera_msi_driver = { + .driver = { + .name = "altera-msi", + .of_match_table = altera_msi_of_match, + }, + .probe = altera_msi_probe, + .remove = altera_msi_remove, +}; + +static int __init altera_msi_init(void) +{ + return platform_driver_register(&altera_msi_driver); +} + +static void __exit altera_msi_exit(void) +{ + platform_driver_unregister(&altera_msi_driver); +} + +subsys_initcall(altera_msi_init); +MODULE_DEVICE_TABLE(of, altera_msi_of_match); +module_exit(altera_msi_exit); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-altera.c b/drivers/pci/controller/pcie-altera.c new file mode 100644 index 000000000..18b2361d6 --- /dev/null +++ b/drivers/pci/controller/pcie-altera.c @@ -0,0 +1,832 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright Altera Corporation (C) 2013-2015. All rights reserved + * + * Author: Ley Foon Tan <lftan@altera.com> + * Description: Altera PCIe host controller driver + */ + +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_device.h> +#include <linux/of_irq.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/slab.h> + +#include "../pci.h" + +#define RP_TX_REG0 0x2000 +#define RP_TX_REG1 0x2004 +#define RP_TX_CNTRL 0x2008 +#define RP_TX_EOP 0x2 +#define RP_TX_SOP 0x1 +#define RP_RXCPL_STATUS 0x2010 +#define RP_RXCPL_EOP 0x2 +#define RP_RXCPL_SOP 0x1 +#define RP_RXCPL_REG0 0x2014 +#define RP_RXCPL_REG1 0x2018 +#define P2A_INT_STATUS 0x3060 +#define P2A_INT_STS_ALL 0xf +#define P2A_INT_ENABLE 0x3070 +#define P2A_INT_ENA_ALL 0xf +#define RP_LTSSM 0x3c64 +#define RP_LTSSM_MASK 0x1f +#define LTSSM_L0 0xf + +#define S10_RP_TX_CNTRL 0x2004 +#define S10_RP_RXCPL_REG 0x2008 +#define S10_RP_RXCPL_STATUS 0x200C +#define S10_RP_CFG_ADDR(pcie, reg) \ + (((pcie)->hip_base) + (reg) + (1 << 20)) +#define S10_RP_SECONDARY(pcie) \ + readb(S10_RP_CFG_ADDR(pcie, PCI_SECONDARY_BUS)) + +/* TLP configuration type 0 and 1 */ +#define TLP_FMTTYPE_CFGRD0 0x04 /* Configuration Read Type 0 */ +#define TLP_FMTTYPE_CFGWR0 0x44 /* Configuration Write Type 0 */ +#define TLP_FMTTYPE_CFGRD1 0x05 /* Configuration Read Type 1 */ +#define TLP_FMTTYPE_CFGWR1 0x45 /* Configuration Write Type 1 */ +#define TLP_PAYLOAD_SIZE 0x01 +#define TLP_READ_TAG 0x1d +#define TLP_WRITE_TAG 0x10 +#define RP_DEVFN 0 +#define TLP_REQ_ID(bus, devfn) (((bus) << 8) | (devfn)) +#define TLP_CFG_DW0(pcie, cfg) \ + (((cfg) << 24) | \ + TLP_PAYLOAD_SIZE) +#define TLP_CFG_DW1(pcie, tag, be) \ + (((TLP_REQ_ID(pcie->root_bus_nr, RP_DEVFN)) << 16) | (tag << 8) | (be)) +#define TLP_CFG_DW2(bus, devfn, offset) \ + (((bus) << 24) | ((devfn) << 16) | (offset)) +#define TLP_COMP_STATUS(s) (((s) >> 13) & 7) +#define TLP_BYTE_COUNT(s) (((s) >> 0) & 0xfff) +#define TLP_HDR_SIZE 3 +#define TLP_LOOP 500 + +#define LINK_UP_TIMEOUT HZ +#define LINK_RETRAIN_TIMEOUT HZ + +#define DWORD_MASK 3 + +#define S10_TLP_FMTTYPE_CFGRD0 0x05 +#define S10_TLP_FMTTYPE_CFGRD1 0x04 +#define S10_TLP_FMTTYPE_CFGWR0 0x45 +#define S10_TLP_FMTTYPE_CFGWR1 0x44 + +enum altera_pcie_version { + ALTERA_PCIE_V1 = 0, + ALTERA_PCIE_V2, +}; + +struct altera_pcie { + struct platform_device *pdev; + void __iomem *cra_base; + void __iomem *hip_base; + int irq; + u8 root_bus_nr; + struct irq_domain *irq_domain; + struct resource bus_range; + const struct altera_pcie_data *pcie_data; +}; + +struct altera_pcie_ops { + int (*tlp_read_pkt)(struct altera_pcie *pcie, u32 *value); + void (*tlp_write_pkt)(struct altera_pcie *pcie, u32 *headers, + u32 data, bool align); + bool (*get_link_status)(struct altera_pcie *pcie); + int (*rp_read_cfg)(struct altera_pcie *pcie, int where, + int size, u32 *value); + int (*rp_write_cfg)(struct altera_pcie *pcie, u8 busno, + int where, int size, u32 value); +}; + +struct altera_pcie_data { + const struct altera_pcie_ops *ops; + enum altera_pcie_version version; + u32 cap_offset; /* PCIe capability structure register offset */ + u32 cfgrd0; + u32 cfgrd1; + u32 cfgwr0; + u32 cfgwr1; +}; + +struct tlp_rp_regpair_t { + u32 ctrl; + u32 reg0; + u32 reg1; +}; + +static inline void cra_writel(struct altera_pcie *pcie, const u32 value, + const u32 reg) +{ + writel_relaxed(value, pcie->cra_base + reg); +} + +static inline u32 cra_readl(struct altera_pcie *pcie, const u32 reg) +{ + return readl_relaxed(pcie->cra_base + reg); +} + +static bool altera_pcie_link_up(struct altera_pcie *pcie) +{ + return !!((cra_readl(pcie, RP_LTSSM) & RP_LTSSM_MASK) == LTSSM_L0); +} + +static bool s10_altera_pcie_link_up(struct altera_pcie *pcie) +{ + void __iomem *addr = S10_RP_CFG_ADDR(pcie, + pcie->pcie_data->cap_offset + + PCI_EXP_LNKSTA); + + return !!(readw(addr) & PCI_EXP_LNKSTA_DLLLA); +} + +/* + * Altera PCIe port uses BAR0 of RC's configuration space as the translation + * from PCI bus to native BUS. Entire DDR region is mapped into PCIe space + * using these registers, so it can be reached by DMA from EP devices. + * This BAR0 will also access to MSI vector when receiving MSI/MSIX interrupt + * from EP devices, eventually trigger interrupt to GIC. The BAR0 of bridge + * should be hidden during enumeration to avoid the sizing and resource + * allocation by PCIe core. + */ +static bool altera_pcie_hide_rc_bar(struct pci_bus *bus, unsigned int devfn, + int offset) +{ + if (pci_is_root_bus(bus) && (devfn == 0) && + (offset == PCI_BASE_ADDRESS_0)) + return true; + + return false; +} + +static void tlp_write_tx(struct altera_pcie *pcie, + struct tlp_rp_regpair_t *tlp_rp_regdata) +{ + cra_writel(pcie, tlp_rp_regdata->reg0, RP_TX_REG0); + cra_writel(pcie, tlp_rp_regdata->reg1, RP_TX_REG1); + cra_writel(pcie, tlp_rp_regdata->ctrl, RP_TX_CNTRL); +} + +static void s10_tlp_write_tx(struct altera_pcie *pcie, u32 reg0, u32 ctrl) +{ + cra_writel(pcie, reg0, RP_TX_REG0); + cra_writel(pcie, ctrl, S10_RP_TX_CNTRL); +} + +static bool altera_pcie_valid_device(struct altera_pcie *pcie, + struct pci_bus *bus, int dev) +{ + /* If there is no link, then there is no device */ + if (bus->number != pcie->root_bus_nr) { + if (!pcie->pcie_data->ops->get_link_status(pcie)) + return false; + } + + /* access only one slot on each root port */ + if (bus->number == pcie->root_bus_nr && dev > 0) + return false; + + return true; +} + +static int tlp_read_packet(struct altera_pcie *pcie, u32 *value) +{ + int i; + bool sop = false; + u32 ctrl; + u32 reg0, reg1; + u32 comp_status = 1; + + /* + * Minimum 2 loops to read TLP headers and 1 loop to read data + * payload. + */ + for (i = 0; i < TLP_LOOP; i++) { + ctrl = cra_readl(pcie, RP_RXCPL_STATUS); + if ((ctrl & RP_RXCPL_SOP) || (ctrl & RP_RXCPL_EOP) || sop) { + reg0 = cra_readl(pcie, RP_RXCPL_REG0); + reg1 = cra_readl(pcie, RP_RXCPL_REG1); + + if (ctrl & RP_RXCPL_SOP) { + sop = true; + comp_status = TLP_COMP_STATUS(reg1); + } + + if (ctrl & RP_RXCPL_EOP) { + if (comp_status) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (value) + *value = reg0; + + return PCIBIOS_SUCCESSFUL; + } + } + udelay(5); + } + + return PCIBIOS_DEVICE_NOT_FOUND; +} + +static int s10_tlp_read_packet(struct altera_pcie *pcie, u32 *value) +{ + u32 ctrl; + u32 comp_status; + u32 dw[4]; + u32 count; + struct device *dev = &pcie->pdev->dev; + + for (count = 0; count < TLP_LOOP; count++) { + ctrl = cra_readl(pcie, S10_RP_RXCPL_STATUS); + if (ctrl & RP_RXCPL_SOP) { + /* Read first DW */ + dw[0] = cra_readl(pcie, S10_RP_RXCPL_REG); + break; + } + + udelay(5); + } + + /* SOP detection failed, return error */ + if (count == TLP_LOOP) + return PCIBIOS_DEVICE_NOT_FOUND; + + count = 1; + + /* Poll for EOP */ + while (count < ARRAY_SIZE(dw)) { + ctrl = cra_readl(pcie, S10_RP_RXCPL_STATUS); + dw[count++] = cra_readl(pcie, S10_RP_RXCPL_REG); + if (ctrl & RP_RXCPL_EOP) { + comp_status = TLP_COMP_STATUS(dw[1]); + if (comp_status) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (value && TLP_BYTE_COUNT(dw[1]) == sizeof(u32) && + count == 4) + *value = dw[3]; + + return PCIBIOS_SUCCESSFUL; + } + } + + dev_warn(dev, "Malformed TLP packet\n"); + + return PCIBIOS_DEVICE_NOT_FOUND; +} + +static void tlp_write_packet(struct altera_pcie *pcie, u32 *headers, + u32 data, bool align) +{ + struct tlp_rp_regpair_t tlp_rp_regdata; + + tlp_rp_regdata.reg0 = headers[0]; + tlp_rp_regdata.reg1 = headers[1]; + tlp_rp_regdata.ctrl = RP_TX_SOP; + tlp_write_tx(pcie, &tlp_rp_regdata); + + if (align) { + tlp_rp_regdata.reg0 = headers[2]; + tlp_rp_regdata.reg1 = 0; + tlp_rp_regdata.ctrl = 0; + tlp_write_tx(pcie, &tlp_rp_regdata); + + tlp_rp_regdata.reg0 = data; + tlp_rp_regdata.reg1 = 0; + } else { + tlp_rp_regdata.reg0 = headers[2]; + tlp_rp_regdata.reg1 = data; + } + + tlp_rp_regdata.ctrl = RP_TX_EOP; + tlp_write_tx(pcie, &tlp_rp_regdata); +} + +static void s10_tlp_write_packet(struct altera_pcie *pcie, u32 *headers, + u32 data, bool dummy) +{ + s10_tlp_write_tx(pcie, headers[0], RP_TX_SOP); + s10_tlp_write_tx(pcie, headers[1], 0); + s10_tlp_write_tx(pcie, headers[2], 0); + s10_tlp_write_tx(pcie, data, RP_TX_EOP); +} + +static void get_tlp_header(struct altera_pcie *pcie, u8 bus, u32 devfn, + int where, u8 byte_en, bool read, u32 *headers) +{ + u8 cfg; + u8 cfg0 = read ? pcie->pcie_data->cfgrd0 : pcie->pcie_data->cfgwr0; + u8 cfg1 = read ? pcie->pcie_data->cfgrd1 : pcie->pcie_data->cfgwr1; + u8 tag = read ? TLP_READ_TAG : TLP_WRITE_TAG; + + if (pcie->pcie_data->version == ALTERA_PCIE_V1) + cfg = (bus == pcie->root_bus_nr) ? cfg0 : cfg1; + else + cfg = (bus > S10_RP_SECONDARY(pcie)) ? cfg0 : cfg1; + + headers[0] = TLP_CFG_DW0(pcie, cfg); + headers[1] = TLP_CFG_DW1(pcie, tag, byte_en); + headers[2] = TLP_CFG_DW2(bus, devfn, where); +} + +static int tlp_cfg_dword_read(struct altera_pcie *pcie, u8 bus, u32 devfn, + int where, u8 byte_en, u32 *value) +{ + u32 headers[TLP_HDR_SIZE]; + + get_tlp_header(pcie, bus, devfn, where, byte_en, true, + headers); + + pcie->pcie_data->ops->tlp_write_pkt(pcie, headers, 0, false); + + return pcie->pcie_data->ops->tlp_read_pkt(pcie, value); +} + +static int tlp_cfg_dword_write(struct altera_pcie *pcie, u8 bus, u32 devfn, + int where, u8 byte_en, u32 value) +{ + u32 headers[TLP_HDR_SIZE]; + int ret; + + get_tlp_header(pcie, bus, devfn, where, byte_en, false, + headers); + + /* check alignment to Qword */ + if ((where & 0x7) == 0) + pcie->pcie_data->ops->tlp_write_pkt(pcie, headers, + value, true); + else + pcie->pcie_data->ops->tlp_write_pkt(pcie, headers, + value, false); + + ret = pcie->pcie_data->ops->tlp_read_pkt(pcie, NULL); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + /* + * Monitor changes to PCI_PRIMARY_BUS register on root port + * and update local copy of root bus number accordingly. + */ + if ((bus == pcie->root_bus_nr) && (where == PCI_PRIMARY_BUS)) + pcie->root_bus_nr = (u8)(value); + + return PCIBIOS_SUCCESSFUL; +} + +static int s10_rp_read_cfg(struct altera_pcie *pcie, int where, + int size, u32 *value) +{ + void __iomem *addr = S10_RP_CFG_ADDR(pcie, where); + + switch (size) { + case 1: + *value = readb(addr); + break; + case 2: + *value = readw(addr); + break; + default: + *value = readl(addr); + break; + } + + return PCIBIOS_SUCCESSFUL; +} + +static int s10_rp_write_cfg(struct altera_pcie *pcie, u8 busno, + int where, int size, u32 value) +{ + void __iomem *addr = S10_RP_CFG_ADDR(pcie, where); + + switch (size) { + case 1: + writeb(value, addr); + break; + case 2: + writew(value, addr); + break; + default: + writel(value, addr); + break; + } + + /* + * Monitor changes to PCI_PRIMARY_BUS register on root port + * and update local copy of root bus number accordingly. + */ + if (busno == pcie->root_bus_nr && where == PCI_PRIMARY_BUS) + pcie->root_bus_nr = value & 0xff; + + return PCIBIOS_SUCCESSFUL; +} + +static int _altera_pcie_cfg_read(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int where, int size, + u32 *value) +{ + int ret; + u32 data; + u8 byte_en; + + if (busno == pcie->root_bus_nr && pcie->pcie_data->ops->rp_read_cfg) + return pcie->pcie_data->ops->rp_read_cfg(pcie, where, + size, value); + + switch (size) { + case 1: + byte_en = 1 << (where & 3); + break; + case 2: + byte_en = 3 << (where & 3); + break; + default: + byte_en = 0xf; + break; + } + + ret = tlp_cfg_dword_read(pcie, busno, devfn, + (where & ~DWORD_MASK), byte_en, &data); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + switch (size) { + case 1: + *value = (data >> (8 * (where & 0x3))) & 0xff; + break; + case 2: + *value = (data >> (8 * (where & 0x2))) & 0xffff; + break; + default: + *value = data; + break; + } + + return PCIBIOS_SUCCESSFUL; +} + +static int _altera_pcie_cfg_write(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int where, int size, + u32 value) +{ + u32 data32; + u32 shift = 8 * (where & 3); + u8 byte_en; + + if (busno == pcie->root_bus_nr && pcie->pcie_data->ops->rp_write_cfg) + return pcie->pcie_data->ops->rp_write_cfg(pcie, busno, + where, size, value); + + switch (size) { + case 1: + data32 = (value & 0xff) << shift; + byte_en = 1 << (where & 3); + break; + case 2: + data32 = (value & 0xffff) << shift; + byte_en = 3 << (where & 3); + break; + default: + data32 = value; + byte_en = 0xf; + break; + } + + return tlp_cfg_dword_write(pcie, busno, devfn, (where & ~DWORD_MASK), + byte_en, data32); +} + +static int altera_pcie_cfg_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *value) +{ + struct altera_pcie *pcie = bus->sysdata; + + if (altera_pcie_hide_rc_bar(bus, devfn, where)) + return PCIBIOS_BAD_REGISTER_NUMBER; + + if (!altera_pcie_valid_device(pcie, bus, PCI_SLOT(devfn))) + return PCIBIOS_DEVICE_NOT_FOUND; + + return _altera_pcie_cfg_read(pcie, bus->number, devfn, where, size, + value); +} + +static int altera_pcie_cfg_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 value) +{ + struct altera_pcie *pcie = bus->sysdata; + + if (altera_pcie_hide_rc_bar(bus, devfn, where)) + return PCIBIOS_BAD_REGISTER_NUMBER; + + if (!altera_pcie_valid_device(pcie, bus, PCI_SLOT(devfn))) + return PCIBIOS_DEVICE_NOT_FOUND; + + return _altera_pcie_cfg_write(pcie, bus->number, devfn, where, size, + value); +} + +static struct pci_ops altera_pcie_ops = { + .read = altera_pcie_cfg_read, + .write = altera_pcie_cfg_write, +}; + +static int altera_read_cap_word(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int offset, u16 *value) +{ + u32 data; + int ret; + + ret = _altera_pcie_cfg_read(pcie, busno, devfn, + pcie->pcie_data->cap_offset + offset, + sizeof(*value), + &data); + *value = data; + return ret; +} + +static int altera_write_cap_word(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int offset, u16 value) +{ + return _altera_pcie_cfg_write(pcie, busno, devfn, + pcie->pcie_data->cap_offset + offset, + sizeof(value), + value); +} + +static void altera_wait_link_retrain(struct altera_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + u16 reg16; + unsigned long start_jiffies; + + /* Wait for link training end. */ + start_jiffies = jiffies; + for (;;) { + altera_read_cap_word(pcie, pcie->root_bus_nr, RP_DEVFN, + PCI_EXP_LNKSTA, ®16); + if (!(reg16 & PCI_EXP_LNKSTA_LT)) + break; + + if (time_after(jiffies, start_jiffies + LINK_RETRAIN_TIMEOUT)) { + dev_err(dev, "link retrain timeout\n"); + break; + } + udelay(100); + } + + /* Wait for link is up */ + start_jiffies = jiffies; + for (;;) { + if (pcie->pcie_data->ops->get_link_status(pcie)) + break; + + if (time_after(jiffies, start_jiffies + LINK_UP_TIMEOUT)) { + dev_err(dev, "link up timeout\n"); + break; + } + udelay(100); + } +} + +static void altera_pcie_retrain(struct altera_pcie *pcie) +{ + u16 linkcap, linkstat, linkctl; + + if (!pcie->pcie_data->ops->get_link_status(pcie)) + return; + + /* + * Set the retrain bit if the PCIe rootport support > 2.5GB/s, but + * current speed is 2.5 GB/s. + */ + altera_read_cap_word(pcie, pcie->root_bus_nr, RP_DEVFN, PCI_EXP_LNKCAP, + &linkcap); + if ((linkcap & PCI_EXP_LNKCAP_SLS) <= PCI_EXP_LNKCAP_SLS_2_5GB) + return; + + altera_read_cap_word(pcie, pcie->root_bus_nr, RP_DEVFN, PCI_EXP_LNKSTA, + &linkstat); + if ((linkstat & PCI_EXP_LNKSTA_CLS) == PCI_EXP_LNKSTA_CLS_2_5GB) { + altera_read_cap_word(pcie, pcie->root_bus_nr, RP_DEVFN, + PCI_EXP_LNKCTL, &linkctl); + linkctl |= PCI_EXP_LNKCTL_RL; + altera_write_cap_word(pcie, pcie->root_bus_nr, RP_DEVFN, + PCI_EXP_LNKCTL, linkctl); + + altera_wait_link_retrain(pcie); + } +} + +static int altera_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &dummy_irq_chip, handle_simple_irq); + irq_set_chip_data(irq, domain->host_data); + return 0; +} + +static const struct irq_domain_ops intx_domain_ops = { + .map = altera_pcie_intx_map, + .xlate = pci_irqd_intx_xlate, +}; + +static void altera_pcie_isr(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct altera_pcie *pcie; + struct device *dev; + unsigned long status; + u32 bit; + int ret; + + chained_irq_enter(chip, desc); + pcie = irq_desc_get_handler_data(desc); + dev = &pcie->pdev->dev; + + while ((status = cra_readl(pcie, P2A_INT_STATUS) + & P2A_INT_STS_ALL) != 0) { + for_each_set_bit(bit, &status, PCI_NUM_INTX) { + /* clear interrupts */ + cra_writel(pcie, 1 << bit, P2A_INT_STATUS); + + ret = generic_handle_domain_irq(pcie->irq_domain, bit); + if (ret) + dev_err_ratelimited(dev, "unexpected IRQ, INT%d\n", bit); + } + } + + chained_irq_exit(chip, desc); +} + +static int altera_pcie_init_irq_domain(struct altera_pcie *pcie) +{ + struct device *dev = &pcie->pdev->dev; + struct device_node *node = dev->of_node; + + /* Setup INTx */ + pcie->irq_domain = irq_domain_add_linear(node, PCI_NUM_INTX, + &intx_domain_ops, pcie); + if (!pcie->irq_domain) { + dev_err(dev, "Failed to get a INTx IRQ domain\n"); + return -ENOMEM; + } + + return 0; +} + +static void altera_pcie_irq_teardown(struct altera_pcie *pcie) +{ + irq_set_chained_handler_and_data(pcie->irq, NULL, NULL); + irq_domain_remove(pcie->irq_domain); + irq_dispose_mapping(pcie->irq); +} + +static int altera_pcie_parse_dt(struct altera_pcie *pcie) +{ + struct platform_device *pdev = pcie->pdev; + + pcie->cra_base = devm_platform_ioremap_resource_byname(pdev, "Cra"); + if (IS_ERR(pcie->cra_base)) + return PTR_ERR(pcie->cra_base); + + if (pcie->pcie_data->version == ALTERA_PCIE_V2) { + pcie->hip_base = + devm_platform_ioremap_resource_byname(pdev, "Hip"); + if (IS_ERR(pcie->hip_base)) + return PTR_ERR(pcie->hip_base); + } + + /* setup IRQ */ + pcie->irq = platform_get_irq(pdev, 0); + if (pcie->irq < 0) + return pcie->irq; + + irq_set_chained_handler_and_data(pcie->irq, altera_pcie_isr, pcie); + return 0; +} + +static void altera_pcie_host_init(struct altera_pcie *pcie) +{ + altera_pcie_retrain(pcie); +} + +static const struct altera_pcie_ops altera_pcie_ops_1_0 = { + .tlp_read_pkt = tlp_read_packet, + .tlp_write_pkt = tlp_write_packet, + .get_link_status = altera_pcie_link_up, +}; + +static const struct altera_pcie_ops altera_pcie_ops_2_0 = { + .tlp_read_pkt = s10_tlp_read_packet, + .tlp_write_pkt = s10_tlp_write_packet, + .get_link_status = s10_altera_pcie_link_up, + .rp_read_cfg = s10_rp_read_cfg, + .rp_write_cfg = s10_rp_write_cfg, +}; + +static const struct altera_pcie_data altera_pcie_1_0_data = { + .ops = &altera_pcie_ops_1_0, + .cap_offset = 0x80, + .version = ALTERA_PCIE_V1, + .cfgrd0 = TLP_FMTTYPE_CFGRD0, + .cfgrd1 = TLP_FMTTYPE_CFGRD1, + .cfgwr0 = TLP_FMTTYPE_CFGWR0, + .cfgwr1 = TLP_FMTTYPE_CFGWR1, +}; + +static const struct altera_pcie_data altera_pcie_2_0_data = { + .ops = &altera_pcie_ops_2_0, + .version = ALTERA_PCIE_V2, + .cap_offset = 0x70, + .cfgrd0 = S10_TLP_FMTTYPE_CFGRD0, + .cfgrd1 = S10_TLP_FMTTYPE_CFGRD1, + .cfgwr0 = S10_TLP_FMTTYPE_CFGWR0, + .cfgwr1 = S10_TLP_FMTTYPE_CFGWR1, +}; + +static const struct of_device_id altera_pcie_of_match[] = { + {.compatible = "altr,pcie-root-port-1.0", + .data = &altera_pcie_1_0_data }, + {.compatible = "altr,pcie-root-port-2.0", + .data = &altera_pcie_2_0_data }, + {}, +}; + +static int altera_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct altera_pcie *pcie; + struct pci_host_bridge *bridge; + int ret; + const struct altera_pcie_data *data; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + pcie->pdev = pdev; + platform_set_drvdata(pdev, pcie); + + data = of_device_get_match_data(&pdev->dev); + if (!data) + return -ENODEV; + + pcie->pcie_data = data; + + ret = altera_pcie_parse_dt(pcie); + if (ret) { + dev_err(dev, "Parsing DT failed\n"); + return ret; + } + + ret = altera_pcie_init_irq_domain(pcie); + if (ret) { + dev_err(dev, "Failed creating IRQ Domain\n"); + return ret; + } + + /* clear all interrupts */ + cra_writel(pcie, P2A_INT_STS_ALL, P2A_INT_STATUS); + /* enable all interrupts */ + cra_writel(pcie, P2A_INT_ENA_ALL, P2A_INT_ENABLE); + altera_pcie_host_init(pcie); + + bridge->sysdata = pcie; + bridge->busnr = pcie->root_bus_nr; + bridge->ops = &altera_pcie_ops; + + return pci_host_probe(bridge); +} + +static int altera_pcie_remove(struct platform_device *pdev) +{ + struct altera_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); + altera_pcie_irq_teardown(pcie); + + return 0; +} + +static struct platform_driver altera_pcie_driver = { + .probe = altera_pcie_probe, + .remove = altera_pcie_remove, + .driver = { + .name = "altera-pcie", + .of_match_table = altera_pcie_of_match, + }, +}; + +MODULE_DEVICE_TABLE(of, altera_pcie_of_match); +module_platform_driver(altera_pcie_driver); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c new file mode 100644 index 000000000..2340dab6c --- /dev/null +++ b/drivers/pci/controller/pcie-apple.c @@ -0,0 +1,842 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host bridge driver for Apple system-on-chips. + * + * The HW is ECAM compliant, so once the controller is initialized, + * the driver mostly deals MSI mapping and handling of per-port + * interrupts (INTx, management and error signals). + * + * Initialization requires enabling power and clocks, along with a + * number of register pokes. + * + * Copyright (C) 2021 Alyssa Rosenzweig <alyssa@rosenzweig.io> + * Copyright (C) 2021 Google LLC + * Copyright (C) 2021 Corellium LLC + * Copyright (C) 2021 Mark Kettenis <kettenis@openbsd.org> + * + * Author: Alyssa Rosenzweig <alyssa@rosenzweig.io> + * Author: Marc Zyngier <maz@kernel.org> + */ + +#include <linux/gpio/consumer.h> +#include <linux/kernel.h> +#include <linux/iopoll.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/list.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/notifier.h> +#include <linux/of_irq.h> +#include <linux/pci-ecam.h> + +#define CORE_RC_PHYIF_CTL 0x00024 +#define CORE_RC_PHYIF_CTL_RUN BIT(0) +#define CORE_RC_PHYIF_STAT 0x00028 +#define CORE_RC_PHYIF_STAT_REFCLK BIT(4) +#define CORE_RC_CTL 0x00050 +#define CORE_RC_CTL_RUN BIT(0) +#define CORE_RC_STAT 0x00058 +#define CORE_RC_STAT_READY BIT(0) +#define CORE_FABRIC_STAT 0x04000 +#define CORE_FABRIC_STAT_MASK 0x001F001F +#define CORE_LANE_CFG(port) (0x84000 + 0x4000 * (port)) +#define CORE_LANE_CFG_REFCLK0REQ BIT(0) +#define CORE_LANE_CFG_REFCLK1REQ BIT(1) +#define CORE_LANE_CFG_REFCLK0ACK BIT(2) +#define CORE_LANE_CFG_REFCLK1ACK BIT(3) +#define CORE_LANE_CFG_REFCLKEN (BIT(9) | BIT(10)) +#define CORE_LANE_CTL(port) (0x84004 + 0x4000 * (port)) +#define CORE_LANE_CTL_CFGACC BIT(15) + +#define PORT_LTSSMCTL 0x00080 +#define PORT_LTSSMCTL_START BIT(0) +#define PORT_INTSTAT 0x00100 +#define PORT_INT_TUNNEL_ERR 31 +#define PORT_INT_CPL_TIMEOUT 23 +#define PORT_INT_RID2SID_MAPERR 22 +#define PORT_INT_CPL_ABORT 21 +#define PORT_INT_MSI_BAD_DATA 19 +#define PORT_INT_MSI_ERR 18 +#define PORT_INT_REQADDR_GT32 17 +#define PORT_INT_AF_TIMEOUT 15 +#define PORT_INT_LINK_DOWN 14 +#define PORT_INT_LINK_UP 12 +#define PORT_INT_LINK_BWMGMT 11 +#define PORT_INT_AER_MASK (15 << 4) +#define PORT_INT_PORT_ERR 4 +#define PORT_INT_INTx(i) i +#define PORT_INT_INTx_MASK 15 +#define PORT_INTMSK 0x00104 +#define PORT_INTMSKSET 0x00108 +#define PORT_INTMSKCLR 0x0010c +#define PORT_MSICFG 0x00124 +#define PORT_MSICFG_EN BIT(0) +#define PORT_MSICFG_L2MSINUM_SHIFT 4 +#define PORT_MSIBASE 0x00128 +#define PORT_MSIBASE_1_SHIFT 16 +#define PORT_MSIADDR 0x00168 +#define PORT_LINKSTS 0x00208 +#define PORT_LINKSTS_UP BIT(0) +#define PORT_LINKSTS_BUSY BIT(2) +#define PORT_LINKCMDSTS 0x00210 +#define PORT_OUTS_NPREQS 0x00284 +#define PORT_OUTS_NPREQS_REQ BIT(24) +#define PORT_OUTS_NPREQS_CPL BIT(16) +#define PORT_RXWR_FIFO 0x00288 +#define PORT_RXWR_FIFO_HDR GENMASK(15, 10) +#define PORT_RXWR_FIFO_DATA GENMASK(9, 0) +#define PORT_RXRD_FIFO 0x0028C +#define PORT_RXRD_FIFO_REQ GENMASK(6, 0) +#define PORT_OUTS_CPLS 0x00290 +#define PORT_OUTS_CPLS_SHRD GENMASK(14, 8) +#define PORT_OUTS_CPLS_WAIT GENMASK(6, 0) +#define PORT_APPCLK 0x00800 +#define PORT_APPCLK_EN BIT(0) +#define PORT_APPCLK_CGDIS BIT(8) +#define PORT_STATUS 0x00804 +#define PORT_STATUS_READY BIT(0) +#define PORT_REFCLK 0x00810 +#define PORT_REFCLK_EN BIT(0) +#define PORT_REFCLK_CGDIS BIT(8) +#define PORT_PERST 0x00814 +#define PORT_PERST_OFF BIT(0) +#define PORT_RID2SID(i16) (0x00828 + 4 * (i16)) +#define PORT_RID2SID_VALID BIT(31) +#define PORT_RID2SID_SID_SHIFT 16 +#define PORT_RID2SID_BUS_SHIFT 8 +#define PORT_RID2SID_DEV_SHIFT 3 +#define PORT_RID2SID_FUNC_SHIFT 0 +#define PORT_OUTS_PREQS_HDR 0x00980 +#define PORT_OUTS_PREQS_HDR_MASK GENMASK(9, 0) +#define PORT_OUTS_PREQS_DATA 0x00984 +#define PORT_OUTS_PREQS_DATA_MASK GENMASK(15, 0) +#define PORT_TUNCTRL 0x00988 +#define PORT_TUNCTRL_PERST_ON BIT(0) +#define PORT_TUNCTRL_PERST_ACK_REQ BIT(1) +#define PORT_TUNSTAT 0x0098c +#define PORT_TUNSTAT_PERST_ON BIT(0) +#define PORT_TUNSTAT_PERST_ACK_PEND BIT(1) +#define PORT_PREFMEM_ENABLE 0x00994 + +#define MAX_RID2SID 64 + +/* + * The doorbell address is set to 0xfffff000, which by convention + * matches what MacOS does, and it is possible to use any other + * address (in the bottom 4GB, as the base register is only 32bit). + * However, it has to be excluded from the IOVA range, and the DART + * driver has to know about it. + */ +#define DOORBELL_ADDR CONFIG_PCIE_APPLE_MSI_DOORBELL_ADDR + +struct apple_pcie { + struct mutex lock; + struct device *dev; + void __iomem *base; + struct irq_domain *domain; + unsigned long *bitmap; + struct list_head ports; + struct completion event; + struct irq_fwspec fwspec; + u32 nvecs; +}; + +struct apple_pcie_port { + struct apple_pcie *pcie; + struct device_node *np; + void __iomem *base; + struct irq_domain *domain; + struct list_head entry; + DECLARE_BITMAP(sid_map, MAX_RID2SID); + int sid_map_sz; + int idx; +}; + +static void rmw_set(u32 set, void __iomem *addr) +{ + writel_relaxed(readl_relaxed(addr) | set, addr); +} + +static void rmw_clear(u32 clr, void __iomem *addr) +{ + writel_relaxed(readl_relaxed(addr) & ~clr, addr); +} + +static void apple_msi_top_irq_mask(struct irq_data *d) +{ + pci_msi_mask_irq(d); + irq_chip_mask_parent(d); +} + +static void apple_msi_top_irq_unmask(struct irq_data *d) +{ + pci_msi_unmask_irq(d); + irq_chip_unmask_parent(d); +} + +static struct irq_chip apple_msi_top_chip = { + .name = "PCIe MSI", + .irq_mask = apple_msi_top_irq_mask, + .irq_unmask = apple_msi_top_irq_unmask, + .irq_eoi = irq_chip_eoi_parent, + .irq_set_affinity = irq_chip_set_affinity_parent, + .irq_set_type = irq_chip_set_type_parent, +}; + +static void apple_msi_compose_msg(struct irq_data *data, struct msi_msg *msg) +{ + msg->address_hi = upper_32_bits(DOORBELL_ADDR); + msg->address_lo = lower_32_bits(DOORBELL_ADDR); + msg->data = data->hwirq; +} + +static struct irq_chip apple_msi_bottom_chip = { + .name = "MSI", + .irq_mask = irq_chip_mask_parent, + .irq_unmask = irq_chip_unmask_parent, + .irq_eoi = irq_chip_eoi_parent, + .irq_set_affinity = irq_chip_set_affinity_parent, + .irq_set_type = irq_chip_set_type_parent, + .irq_compose_msi_msg = apple_msi_compose_msg, +}; + +static int apple_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct apple_pcie *pcie = domain->host_data; + struct irq_fwspec fwspec = pcie->fwspec; + unsigned int i; + int ret, hwirq; + + mutex_lock(&pcie->lock); + + hwirq = bitmap_find_free_region(pcie->bitmap, pcie->nvecs, + order_base_2(nr_irqs)); + + mutex_unlock(&pcie->lock); + + if (hwirq < 0) + return -ENOSPC; + + fwspec.param[fwspec.param_count - 2] += hwirq; + + ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, &fwspec); + if (ret) + return ret; + + for (i = 0; i < nr_irqs; i++) { + irq_domain_set_hwirq_and_chip(domain, virq + i, hwirq + i, + &apple_msi_bottom_chip, + domain->host_data); + } + + return 0; +} + +static void apple_msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct apple_pcie *pcie = domain->host_data; + + mutex_lock(&pcie->lock); + + bitmap_release_region(pcie->bitmap, d->hwirq, order_base_2(nr_irqs)); + + mutex_unlock(&pcie->lock); +} + +static const struct irq_domain_ops apple_msi_domain_ops = { + .alloc = apple_msi_domain_alloc, + .free = apple_msi_domain_free, +}; + +static struct msi_domain_info apple_msi_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX), + .chip = &apple_msi_top_chip, +}; + +static void apple_port_irq_mask(struct irq_data *data) +{ + struct apple_pcie_port *port = irq_data_get_irq_chip_data(data); + + writel_relaxed(BIT(data->hwirq), port->base + PORT_INTMSKSET); +} + +static void apple_port_irq_unmask(struct irq_data *data) +{ + struct apple_pcie_port *port = irq_data_get_irq_chip_data(data); + + writel_relaxed(BIT(data->hwirq), port->base + PORT_INTMSKCLR); +} + +static bool hwirq_is_intx(unsigned int hwirq) +{ + return BIT(hwirq) & PORT_INT_INTx_MASK; +} + +static void apple_port_irq_ack(struct irq_data *data) +{ + struct apple_pcie_port *port = irq_data_get_irq_chip_data(data); + + if (!hwirq_is_intx(data->hwirq)) + writel_relaxed(BIT(data->hwirq), port->base + PORT_INTSTAT); +} + +static int apple_port_irq_set_type(struct irq_data *data, unsigned int type) +{ + /* + * It doesn't seem that there is any way to configure the + * trigger, so assume INTx have to be level (as per the spec), + * and the rest is edge (which looks likely). + */ + if (hwirq_is_intx(data->hwirq) ^ !!(type & IRQ_TYPE_LEVEL_MASK)) + return -EINVAL; + + irqd_set_trigger_type(data, type); + return 0; +} + +static struct irq_chip apple_port_irqchip = { + .name = "PCIe", + .irq_ack = apple_port_irq_ack, + .irq_mask = apple_port_irq_mask, + .irq_unmask = apple_port_irq_unmask, + .irq_set_type = apple_port_irq_set_type, +}; + +static int apple_port_irq_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *args) +{ + struct apple_pcie_port *port = domain->host_data; + struct irq_fwspec *fwspec = args; + int i; + + for (i = 0; i < nr_irqs; i++) { + irq_flow_handler_t flow = handle_edge_irq; + unsigned int type = IRQ_TYPE_EDGE_RISING; + + if (hwirq_is_intx(fwspec->param[0] + i)) { + flow = handle_level_irq; + type = IRQ_TYPE_LEVEL_HIGH; + } + + irq_domain_set_info(domain, virq + i, fwspec->param[0] + i, + &apple_port_irqchip, port, flow, + NULL, NULL); + + irq_set_irq_type(virq + i, type); + } + + return 0; +} + +static void apple_port_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + int i; + + for (i = 0; i < nr_irqs; i++) { + struct irq_data *d = irq_domain_get_irq_data(domain, virq + i); + + irq_set_handler(virq + i, NULL); + irq_domain_reset_irq_data(d); + } +} + +static const struct irq_domain_ops apple_port_irq_domain_ops = { + .translate = irq_domain_translate_onecell, + .alloc = apple_port_irq_domain_alloc, + .free = apple_port_irq_domain_free, +}; + +static void apple_port_irq_handler(struct irq_desc *desc) +{ + struct apple_pcie_port *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned long stat; + int i; + + chained_irq_enter(chip, desc); + + stat = readl_relaxed(port->base + PORT_INTSTAT); + + for_each_set_bit(i, &stat, 32) + generic_handle_domain_irq(port->domain, i); + + chained_irq_exit(chip, desc); +} + +static int apple_pcie_port_setup_irq(struct apple_pcie_port *port) +{ + struct fwnode_handle *fwnode = &port->np->fwnode; + unsigned int irq; + + /* FIXME: consider moving each interrupt under each port */ + irq = irq_of_parse_and_map(to_of_node(dev_fwnode(port->pcie->dev)), + port->idx); + if (!irq) + return -ENXIO; + + port->domain = irq_domain_create_linear(fwnode, 32, + &apple_port_irq_domain_ops, + port); + if (!port->domain) + return -ENOMEM; + + /* Disable all interrupts */ + writel_relaxed(~0, port->base + PORT_INTMSKSET); + writel_relaxed(~0, port->base + PORT_INTSTAT); + + irq_set_chained_handler_and_data(irq, apple_port_irq_handler, port); + + /* Configure MSI base address */ + BUILD_BUG_ON(upper_32_bits(DOORBELL_ADDR)); + writel_relaxed(lower_32_bits(DOORBELL_ADDR), port->base + PORT_MSIADDR); + + /* Enable MSIs, shared between all ports */ + writel_relaxed(0, port->base + PORT_MSIBASE); + writel_relaxed((ilog2(port->pcie->nvecs) << PORT_MSICFG_L2MSINUM_SHIFT) | + PORT_MSICFG_EN, port->base + PORT_MSICFG); + + return 0; +} + +static irqreturn_t apple_pcie_port_irq(int irq, void *data) +{ + struct apple_pcie_port *port = data; + unsigned int hwirq = irq_domain_get_irq_data(port->domain, irq)->hwirq; + + switch (hwirq) { + case PORT_INT_LINK_UP: + dev_info_ratelimited(port->pcie->dev, "Link up on %pOF\n", + port->np); + complete_all(&port->pcie->event); + break; + case PORT_INT_LINK_DOWN: + dev_info_ratelimited(port->pcie->dev, "Link down on %pOF\n", + port->np); + break; + default: + return IRQ_NONE; + } + + return IRQ_HANDLED; +} + +static int apple_pcie_port_register_irqs(struct apple_pcie_port *port) +{ + static struct { + unsigned int hwirq; + const char *name; + } port_irqs[] = { + { PORT_INT_LINK_UP, "Link up", }, + { PORT_INT_LINK_DOWN, "Link down", }, + }; + int i; + + for (i = 0; i < ARRAY_SIZE(port_irqs); i++) { + struct irq_fwspec fwspec = { + .fwnode = &port->np->fwnode, + .param_count = 1, + .param = { + [0] = port_irqs[i].hwirq, + }, + }; + unsigned int irq; + int ret; + + irq = irq_domain_alloc_irqs(port->domain, 1, NUMA_NO_NODE, + &fwspec); + if (WARN_ON(!irq)) + continue; + + ret = request_irq(irq, apple_pcie_port_irq, 0, + port_irqs[i].name, port); + WARN_ON(ret); + } + + return 0; +} + +static int apple_pcie_setup_refclk(struct apple_pcie *pcie, + struct apple_pcie_port *port) +{ + u32 stat; + int res; + + res = readl_relaxed_poll_timeout(pcie->base + CORE_RC_PHYIF_STAT, stat, + stat & CORE_RC_PHYIF_STAT_REFCLK, + 100, 50000); + if (res < 0) + return res; + + rmw_set(CORE_LANE_CTL_CFGACC, pcie->base + CORE_LANE_CTL(port->idx)); + rmw_set(CORE_LANE_CFG_REFCLK0REQ, pcie->base + CORE_LANE_CFG(port->idx)); + + res = readl_relaxed_poll_timeout(pcie->base + CORE_LANE_CFG(port->idx), + stat, stat & CORE_LANE_CFG_REFCLK0ACK, + 100, 50000); + if (res < 0) + return res; + + rmw_set(CORE_LANE_CFG_REFCLK1REQ, pcie->base + CORE_LANE_CFG(port->idx)); + res = readl_relaxed_poll_timeout(pcie->base + CORE_LANE_CFG(port->idx), + stat, stat & CORE_LANE_CFG_REFCLK1ACK, + 100, 50000); + + if (res < 0) + return res; + + rmw_clear(CORE_LANE_CTL_CFGACC, pcie->base + CORE_LANE_CTL(port->idx)); + + rmw_set(CORE_LANE_CFG_REFCLKEN, pcie->base + CORE_LANE_CFG(port->idx)); + rmw_set(PORT_REFCLK_EN, port->base + PORT_REFCLK); + + return 0; +} + +static u32 apple_pcie_rid2sid_write(struct apple_pcie_port *port, + int idx, u32 val) +{ + writel_relaxed(val, port->base + PORT_RID2SID(idx)); + /* Read back to ensure completion of the write */ + return readl_relaxed(port->base + PORT_RID2SID(idx)); +} + +static int apple_pcie_setup_port(struct apple_pcie *pcie, + struct device_node *np) +{ + struct platform_device *platform = to_platform_device(pcie->dev); + struct apple_pcie_port *port; + struct gpio_desc *reset; + u32 stat, idx; + int ret, i; + + reset = devm_fwnode_gpiod_get(pcie->dev, of_fwnode_handle(np), "reset", + GPIOD_OUT_LOW, "PERST#"); + if (IS_ERR(reset)) + return PTR_ERR(reset); + + port = devm_kzalloc(pcie->dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + ret = of_property_read_u32_index(np, "reg", 0, &idx); + if (ret) + return ret; + + /* Use the first reg entry to work out the port index */ + port->idx = idx >> 11; + port->pcie = pcie; + port->np = np; + + port->base = devm_platform_ioremap_resource(platform, port->idx + 2); + if (IS_ERR(port->base)) + return PTR_ERR(port->base); + + rmw_set(PORT_APPCLK_EN, port->base + PORT_APPCLK); + + /* Assert PERST# before setting up the clock */ + gpiod_set_value(reset, 1); + + ret = apple_pcie_setup_refclk(pcie, port); + if (ret < 0) + return ret; + + /* The minimal Tperst-clk value is 100us (PCIe CEM r5.0, 2.9.2) */ + usleep_range(100, 200); + + /* Deassert PERST# */ + rmw_set(PORT_PERST_OFF, port->base + PORT_PERST); + gpiod_set_value(reset, 0); + + /* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */ + msleep(100); + + ret = readl_relaxed_poll_timeout(port->base + PORT_STATUS, stat, + stat & PORT_STATUS_READY, 100, 250000); + if (ret < 0) { + dev_err(pcie->dev, "port %pOF ready wait timeout\n", np); + return ret; + } + + rmw_clear(PORT_REFCLK_CGDIS, port->base + PORT_REFCLK); + rmw_clear(PORT_APPCLK_CGDIS, port->base + PORT_APPCLK); + + ret = apple_pcie_port_setup_irq(port); + if (ret) + return ret; + + /* Reset all RID/SID mappings, and check for RAZ/WI registers */ + for (i = 0; i < MAX_RID2SID; i++) { + if (apple_pcie_rid2sid_write(port, i, 0xbad1d) != 0xbad1d) + break; + apple_pcie_rid2sid_write(port, i, 0); + } + + dev_dbg(pcie->dev, "%pOF: %d RID/SID mapping entries\n", np, i); + + port->sid_map_sz = i; + + list_add_tail(&port->entry, &pcie->ports); + init_completion(&pcie->event); + + ret = apple_pcie_port_register_irqs(port); + WARN_ON(ret); + + writel_relaxed(PORT_LTSSMCTL_START, port->base + PORT_LTSSMCTL); + + if (!wait_for_completion_timeout(&pcie->event, HZ / 10)) + dev_warn(pcie->dev, "%pOF link didn't come up\n", np); + + return 0; +} + +static int apple_msi_init(struct apple_pcie *pcie) +{ + struct fwnode_handle *fwnode = dev_fwnode(pcie->dev); + struct of_phandle_args args = {}; + struct irq_domain *parent; + int ret; + + ret = of_parse_phandle_with_args(to_of_node(fwnode), "msi-ranges", + "#interrupt-cells", 0, &args); + if (ret) + return ret; + + ret = of_property_read_u32_index(to_of_node(fwnode), "msi-ranges", + args.args_count + 1, &pcie->nvecs); + if (ret) + return ret; + + of_phandle_args_to_fwspec(args.np, args.args, args.args_count, + &pcie->fwspec); + + pcie->bitmap = devm_bitmap_zalloc(pcie->dev, pcie->nvecs, GFP_KERNEL); + if (!pcie->bitmap) + return -ENOMEM; + + parent = irq_find_matching_fwspec(&pcie->fwspec, DOMAIN_BUS_WIRED); + if (!parent) { + dev_err(pcie->dev, "failed to find parent domain\n"); + return -ENXIO; + } + + parent = irq_domain_create_hierarchy(parent, 0, pcie->nvecs, fwnode, + &apple_msi_domain_ops, pcie); + if (!parent) { + dev_err(pcie->dev, "failed to create IRQ domain\n"); + return -ENOMEM; + } + irq_domain_update_bus_token(parent, DOMAIN_BUS_NEXUS); + + pcie->domain = pci_msi_create_irq_domain(fwnode, &apple_msi_info, + parent); + if (!pcie->domain) { + dev_err(pcie->dev, "failed to create MSI domain\n"); + irq_domain_remove(parent); + return -ENOMEM; + } + + return 0; +} + +static struct apple_pcie_port *apple_pcie_get_port(struct pci_dev *pdev) +{ + struct pci_config_window *cfg = pdev->sysdata; + struct apple_pcie *pcie = cfg->priv; + struct pci_dev *port_pdev; + struct apple_pcie_port *port; + + /* Find the root port this device is on */ + port_pdev = pcie_find_root_port(pdev); + + /* If finding the port itself, nothing to do */ + if (WARN_ON(!port_pdev) || pdev == port_pdev) + return NULL; + + list_for_each_entry(port, &pcie->ports, entry) { + if (port->idx == PCI_SLOT(port_pdev->devfn)) + return port; + } + + return NULL; +} + +static int apple_pcie_add_device(struct apple_pcie_port *port, + struct pci_dev *pdev) +{ + u32 sid, rid = PCI_DEVID(pdev->bus->number, pdev->devfn); + int idx, err; + + dev_dbg(&pdev->dev, "added to bus %s, index %d\n", + pci_name(pdev->bus->self), port->idx); + + err = of_map_id(port->pcie->dev->of_node, rid, "iommu-map", + "iommu-map-mask", NULL, &sid); + if (err) + return err; + + mutex_lock(&port->pcie->lock); + + idx = bitmap_find_free_region(port->sid_map, port->sid_map_sz, 0); + if (idx >= 0) { + apple_pcie_rid2sid_write(port, idx, + PORT_RID2SID_VALID | + (sid << PORT_RID2SID_SID_SHIFT) | rid); + + dev_dbg(&pdev->dev, "mapping RID%x to SID%x (index %d)\n", + rid, sid, idx); + } + + mutex_unlock(&port->pcie->lock); + + return idx >= 0 ? 0 : -ENOSPC; +} + +static void apple_pcie_release_device(struct apple_pcie_port *port, + struct pci_dev *pdev) +{ + u32 rid = PCI_DEVID(pdev->bus->number, pdev->devfn); + int idx; + + mutex_lock(&port->pcie->lock); + + for_each_set_bit(idx, port->sid_map, port->sid_map_sz) { + u32 val; + + val = readl_relaxed(port->base + PORT_RID2SID(idx)); + if ((val & 0xffff) == rid) { + apple_pcie_rid2sid_write(port, idx, 0); + bitmap_release_region(port->sid_map, idx, 0); + dev_dbg(&pdev->dev, "Released %x (%d)\n", val, idx); + break; + } + } + + mutex_unlock(&port->pcie->lock); +} + +static int apple_pcie_bus_notifier(struct notifier_block *nb, + unsigned long action, + void *data) +{ + struct device *dev = data; + struct pci_dev *pdev = to_pci_dev(dev); + struct apple_pcie_port *port; + int err; + + /* + * This is a bit ugly. We assume that if we get notified for + * any PCI device, we must be in charge of it, and that there + * is no other PCI controller in the whole system. It probably + * holds for now, but who knows for how long? + */ + port = apple_pcie_get_port(pdev); + if (!port) + return NOTIFY_DONE; + + switch (action) { + case BUS_NOTIFY_ADD_DEVICE: + err = apple_pcie_add_device(port, pdev); + if (err) + return notifier_from_errno(err); + break; + case BUS_NOTIFY_DEL_DEVICE: + apple_pcie_release_device(port, pdev); + break; + default: + return NOTIFY_DONE; + } + + return NOTIFY_OK; +} + +static struct notifier_block apple_pcie_nb = { + .notifier_call = apple_pcie_bus_notifier, +}; + +static int apple_pcie_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct platform_device *platform = to_platform_device(dev); + struct device_node *of_port; + struct apple_pcie *pcie; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + pcie->dev = dev; + + mutex_init(&pcie->lock); + + pcie->base = devm_platform_ioremap_resource(platform, 1); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + + cfg->priv = pcie; + INIT_LIST_HEAD(&pcie->ports); + + ret = apple_msi_init(pcie); + if (ret) + return ret; + + for_each_child_of_node(dev->of_node, of_port) { + ret = apple_pcie_setup_port(pcie, of_port); + if (ret) { + dev_err(pcie->dev, "Port %pOF setup fail: %d\n", of_port, ret); + of_node_put(of_port); + return ret; + } + } + + return 0; +} + +static int apple_pcie_probe(struct platform_device *pdev) +{ + int ret; + + ret = bus_register_notifier(&pci_bus_type, &apple_pcie_nb); + if (ret) + return ret; + + ret = pci_host_common_probe(pdev); + if (ret) + bus_unregister_notifier(&pci_bus_type, &apple_pcie_nb); + + return ret; +} + +static const struct pci_ecam_ops apple_pcie_cfg_ecam_ops = { + .init = apple_pcie_init, + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +static const struct of_device_id apple_pcie_of_match[] = { + { .compatible = "apple,pcie", .data = &apple_pcie_cfg_ecam_ops }, + { } +}; +MODULE_DEVICE_TABLE(of, apple_pcie_of_match); + +static struct platform_driver apple_pcie_driver = { + .probe = apple_pcie_probe, + .driver = { + .name = "pcie-apple", + .of_match_table = apple_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; +module_platform_driver(apple_pcie_driver); + +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c new file mode 100644 index 000000000..521acd632 --- /dev/null +++ b/drivers/pci/controller/pcie-brcmstb.c @@ -0,0 +1,1615 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* Copyright (C) 2009 - 2019 Broadcom */ + +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/compiler.h> +#include <linux/delay.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/ioport.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/list.h> +#include <linux/log2.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/printk.h> +#include <linux/regulator/consumer.h> +#include <linux/reset.h> +#include <linux/sizes.h> +#include <linux/slab.h> +#include <linux/string.h> +#include <linux/types.h> + +#include "../pci.h" + +/* BRCM_PCIE_CAP_REGS - Offset for the mandatory capability config regs */ +#define BRCM_PCIE_CAP_REGS 0x00ac + +/* Broadcom STB PCIe Register Offsets */ +#define PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1 0x0188 +#define PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1_ENDIAN_MODE_BAR2_MASK 0xc +#define PCIE_RC_CFG_VENDOR_SPCIFIC_REG1_LITTLE_ENDIAN 0x0 + +#define PCIE_RC_CFG_PRIV1_ID_VAL3 0x043c +#define PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_MASK 0xffffff + +#define PCIE_RC_CFG_PRIV1_LINK_CAPABILITY 0x04dc +#define PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_ASPM_SUPPORT_MASK 0xc00 + +#define PCIE_RC_DL_MDIO_ADDR 0x1100 +#define PCIE_RC_DL_MDIO_WR_DATA 0x1104 +#define PCIE_RC_DL_MDIO_RD_DATA 0x1108 + +#define PCIE_MISC_MISC_CTRL 0x4008 +#define PCIE_MISC_MISC_CTRL_SCB_ACCESS_EN_MASK 0x1000 +#define PCIE_MISC_MISC_CTRL_CFG_READ_UR_MODE_MASK 0x2000 +#define PCIE_MISC_MISC_CTRL_MAX_BURST_SIZE_MASK 0x300000 + +#define PCIE_MISC_MISC_CTRL_SCB0_SIZE_MASK 0xf8000000 +#define PCIE_MISC_MISC_CTRL_SCB1_SIZE_MASK 0x07c00000 +#define PCIE_MISC_MISC_CTRL_SCB2_SIZE_MASK 0x0000001f +#define SCB_SIZE_MASK(x) PCIE_MISC_MISC_CTRL_SCB ## x ## _SIZE_MASK + +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LO 0x400c +#define PCIE_MEM_WIN0_LO(win) \ + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LO + ((win) * 8) + +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_HI 0x4010 +#define PCIE_MEM_WIN0_HI(win) \ + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_HI + ((win) * 8) + +#define PCIE_MISC_RC_BAR1_CONFIG_LO 0x402c +#define PCIE_MISC_RC_BAR1_CONFIG_LO_SIZE_MASK 0x1f + +#define PCIE_MISC_RC_BAR2_CONFIG_LO 0x4034 +#define PCIE_MISC_RC_BAR2_CONFIG_LO_SIZE_MASK 0x1f +#define PCIE_MISC_RC_BAR2_CONFIG_HI 0x4038 + +#define PCIE_MISC_RC_BAR3_CONFIG_LO 0x403c +#define PCIE_MISC_RC_BAR3_CONFIG_LO_SIZE_MASK 0x1f + +#define PCIE_MISC_MSI_BAR_CONFIG_LO 0x4044 +#define PCIE_MISC_MSI_BAR_CONFIG_HI 0x4048 + +#define PCIE_MISC_MSI_DATA_CONFIG 0x404c +#define PCIE_MISC_MSI_DATA_CONFIG_VAL_32 0xffe06540 +#define PCIE_MISC_MSI_DATA_CONFIG_VAL_8 0xfff86540 + +#define PCIE_MISC_PCIE_CTRL 0x4064 +#define PCIE_MISC_PCIE_CTRL_PCIE_L23_REQUEST_MASK 0x1 +#define PCIE_MISC_PCIE_CTRL_PCIE_PERSTB_MASK 0x4 + +#define PCIE_MISC_PCIE_STATUS 0x4068 +#define PCIE_MISC_PCIE_STATUS_PCIE_PORT_MASK 0x80 +#define PCIE_MISC_PCIE_STATUS_PCIE_DL_ACTIVE_MASK 0x20 +#define PCIE_MISC_PCIE_STATUS_PCIE_PHYLINKUP_MASK 0x10 +#define PCIE_MISC_PCIE_STATUS_PCIE_LINK_IN_L23_MASK 0x40 + +#define PCIE_MISC_REVISION 0x406c +#define BRCM_PCIE_HW_REV_33 0x0303 +#define BRCM_PCIE_HW_REV_3_20 0x0320 + +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT 0x4070 +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_LIMIT_MASK 0xfff00000 +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_BASE_MASK 0xfff0 +#define PCIE_MEM_WIN0_BASE_LIMIT(win) \ + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT + ((win) * 4) + +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI 0x4080 +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI_BASE_MASK 0xff +#define PCIE_MEM_WIN0_BASE_HI(win) \ + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI + ((win) * 8) + +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI 0x4084 +#define PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI_LIMIT_MASK 0xff +#define PCIE_MEM_WIN0_LIMIT_HI(win) \ + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI + ((win) * 8) + +#define PCIE_MISC_HARD_PCIE_HARD_DEBUG 0x4204 +#define PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK 0x2 +#define PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK 0x08000000 +#define PCIE_BMIPS_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK 0x00800000 + + +#define PCIE_INTR2_CPU_BASE 0x4300 +#define PCIE_MSI_INTR2_BASE 0x4500 +/* Offsets from PCIE_INTR2_CPU_BASE and PCIE_MSI_INTR2_BASE */ +#define MSI_INT_STATUS 0x0 +#define MSI_INT_CLR 0x8 +#define MSI_INT_MASK_SET 0x10 +#define MSI_INT_MASK_CLR 0x14 + +#define PCIE_EXT_CFG_DATA 0x8000 +#define PCIE_EXT_CFG_INDEX 0x9000 + +#define PCIE_RGR1_SW_INIT_1_PERST_MASK 0x1 +#define PCIE_RGR1_SW_INIT_1_PERST_SHIFT 0x0 + +#define RGR1_SW_INIT_1_INIT_GENERIC_MASK 0x2 +#define RGR1_SW_INIT_1_INIT_GENERIC_SHIFT 0x1 +#define RGR1_SW_INIT_1_INIT_7278_MASK 0x1 +#define RGR1_SW_INIT_1_INIT_7278_SHIFT 0x0 + +/* PCIe parameters */ +#define BRCM_NUM_PCIE_OUT_WINS 0x4 +#define BRCM_INT_PCI_MSI_NR 32 +#define BRCM_INT_PCI_MSI_LEGACY_NR 8 +#define BRCM_INT_PCI_MSI_SHIFT 0 +#define BRCM_INT_PCI_MSI_MASK GENMASK(BRCM_INT_PCI_MSI_NR - 1, 0) +#define BRCM_INT_PCI_MSI_LEGACY_MASK GENMASK(31, \ + 32 - BRCM_INT_PCI_MSI_LEGACY_NR) + +/* MSI target addresses */ +#define BRCM_MSI_TARGET_ADDR_LT_4GB 0x0fffffffcULL +#define BRCM_MSI_TARGET_ADDR_GT_4GB 0xffffffffcULL + +/* MDIO registers */ +#define MDIO_PORT0 0x0 +#define MDIO_DATA_MASK 0x7fffffff +#define MDIO_PORT_MASK 0xf0000 +#define MDIO_REGAD_MASK 0xffff +#define MDIO_CMD_MASK 0xfff00000 +#define MDIO_CMD_READ 0x1 +#define MDIO_CMD_WRITE 0x0 +#define MDIO_DATA_DONE_MASK 0x80000000 +#define MDIO_RD_DONE(x) (((x) & MDIO_DATA_DONE_MASK) ? 1 : 0) +#define MDIO_WT_DONE(x) (((x) & MDIO_DATA_DONE_MASK) ? 0 : 1) +#define SSC_REGS_ADDR 0x1100 +#define SET_ADDR_OFFSET 0x1f +#define SSC_CNTL_OFFSET 0x2 +#define SSC_CNTL_OVRD_EN_MASK 0x8000 +#define SSC_CNTL_OVRD_VAL_MASK 0x4000 +#define SSC_STATUS_OFFSET 0x1 +#define SSC_STATUS_SSC_MASK 0x400 +#define SSC_STATUS_PLL_LOCK_MASK 0x800 +#define PCIE_BRCM_MAX_MEMC 3 + +#define IDX_ADDR(pcie) (pcie->reg_offsets[EXT_CFG_INDEX]) +#define DATA_ADDR(pcie) (pcie->reg_offsets[EXT_CFG_DATA]) +#define PCIE_RGR1_SW_INIT_1(pcie) (pcie->reg_offsets[RGR1_SW_INIT_1]) + +/* Rescal registers */ +#define PCIE_DVT_PMU_PCIE_PHY_CTRL 0xc700 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_NFLDS 0x3 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_DIG_RESET_MASK 0x4 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_DIG_RESET_SHIFT 0x2 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_RESET_MASK 0x2 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_RESET_SHIFT 0x1 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_PWRDN_MASK 0x1 +#define PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_PWRDN_SHIFT 0x0 + +/* Forward declarations */ +struct brcm_pcie; + +enum { + RGR1_SW_INIT_1, + EXT_CFG_INDEX, + EXT_CFG_DATA, +}; + +enum { + RGR1_SW_INIT_1_INIT_MASK, + RGR1_SW_INIT_1_INIT_SHIFT, +}; + +enum pcie_type { + GENERIC, + BCM7425, + BCM7435, + BCM4908, + BCM7278, + BCM2711, +}; + +struct pcie_cfg_data { + const int *offsets; + const enum pcie_type type; + void (*perst_set)(struct brcm_pcie *pcie, u32 val); + void (*bridge_sw_init_set)(struct brcm_pcie *pcie, u32 val); +}; + +struct subdev_regulators { + unsigned int num_supplies; + struct regulator_bulk_data supplies[]; +}; + +struct brcm_msi { + struct device *dev; + void __iomem *base; + struct device_node *np; + struct irq_domain *msi_domain; + struct irq_domain *inner_domain; + struct mutex lock; /* guards the alloc/free operations */ + u64 target_addr; + int irq; + DECLARE_BITMAP(used, BRCM_INT_PCI_MSI_NR); + bool legacy; + /* Some chips have MSIs in bits [31..24] of a shared register. */ + int legacy_shift; + int nr; /* No. of MSI available, depends on chip */ + /* This is the base pointer for interrupt status/set/clr regs */ + void __iomem *intr_base; +}; + +/* Internal PCIe Host Controller Information.*/ +struct brcm_pcie { + struct device *dev; + void __iomem *base; + struct clk *clk; + struct device_node *np; + bool ssc; + int gen; + u64 msi_target_addr; + struct brcm_msi *msi; + const int *reg_offsets; + enum pcie_type type; + struct reset_control *rescal; + struct reset_control *perst_reset; + int num_memc; + u64 memc_size[PCIE_BRCM_MAX_MEMC]; + u32 hw_rev; + void (*perst_set)(struct brcm_pcie *pcie, u32 val); + void (*bridge_sw_init_set)(struct brcm_pcie *pcie, u32 val); + struct subdev_regulators *sr; + bool ep_wakeup_capable; +}; + +static inline bool is_bmips(const struct brcm_pcie *pcie) +{ + return pcie->type == BCM7435 || pcie->type == BCM7425; +} + +/* + * This is to convert the size of the inbound "BAR" region to the + * non-linear values of PCIE_X_MISC_RC_BAR[123]_CONFIG_LO.SIZE + */ +static int brcm_pcie_encode_ibar_size(u64 size) +{ + int log2_in = ilog2(size); + + if (log2_in >= 12 && log2_in <= 15) + /* Covers 4KB to 32KB (inclusive) */ + return (log2_in - 12) + 0x1c; + else if (log2_in >= 16 && log2_in <= 35) + /* Covers 64KB to 32GB, (inclusive) */ + return log2_in - 15; + /* Something is awry so disable */ + return 0; +} + +static u32 brcm_pcie_mdio_form_pkt(int port, int regad, int cmd) +{ + u32 pkt = 0; + + pkt |= FIELD_PREP(MDIO_PORT_MASK, port); + pkt |= FIELD_PREP(MDIO_REGAD_MASK, regad); + pkt |= FIELD_PREP(MDIO_CMD_MASK, cmd); + + return pkt; +} + +/* negative return value indicates error */ +static int brcm_pcie_mdio_read(void __iomem *base, u8 port, u8 regad, u32 *val) +{ + int tries; + u32 data; + + writel(brcm_pcie_mdio_form_pkt(port, regad, MDIO_CMD_READ), + base + PCIE_RC_DL_MDIO_ADDR); + readl(base + PCIE_RC_DL_MDIO_ADDR); + + data = readl(base + PCIE_RC_DL_MDIO_RD_DATA); + for (tries = 0; !MDIO_RD_DONE(data) && tries < 10; tries++) { + udelay(10); + data = readl(base + PCIE_RC_DL_MDIO_RD_DATA); + } + + *val = FIELD_GET(MDIO_DATA_MASK, data); + return MDIO_RD_DONE(data) ? 0 : -EIO; +} + +/* negative return value indicates error */ +static int brcm_pcie_mdio_write(void __iomem *base, u8 port, + u8 regad, u16 wrdata) +{ + int tries; + u32 data; + + writel(brcm_pcie_mdio_form_pkt(port, regad, MDIO_CMD_WRITE), + base + PCIE_RC_DL_MDIO_ADDR); + readl(base + PCIE_RC_DL_MDIO_ADDR); + writel(MDIO_DATA_DONE_MASK | wrdata, base + PCIE_RC_DL_MDIO_WR_DATA); + + data = readl(base + PCIE_RC_DL_MDIO_WR_DATA); + for (tries = 0; !MDIO_WT_DONE(data) && tries < 10; tries++) { + udelay(10); + data = readl(base + PCIE_RC_DL_MDIO_WR_DATA); + } + + return MDIO_WT_DONE(data) ? 0 : -EIO; +} + +/* + * Configures device for Spread Spectrum Clocking (SSC) mode; a negative + * return value indicates error. + */ +static int brcm_pcie_set_ssc(struct brcm_pcie *pcie) +{ + int pll, ssc; + int ret; + u32 tmp; + + ret = brcm_pcie_mdio_write(pcie->base, MDIO_PORT0, SET_ADDR_OFFSET, + SSC_REGS_ADDR); + if (ret < 0) + return ret; + + ret = brcm_pcie_mdio_read(pcie->base, MDIO_PORT0, + SSC_CNTL_OFFSET, &tmp); + if (ret < 0) + return ret; + + u32p_replace_bits(&tmp, 1, SSC_CNTL_OVRD_EN_MASK); + u32p_replace_bits(&tmp, 1, SSC_CNTL_OVRD_VAL_MASK); + ret = brcm_pcie_mdio_write(pcie->base, MDIO_PORT0, + SSC_CNTL_OFFSET, tmp); + if (ret < 0) + return ret; + + usleep_range(1000, 2000); + ret = brcm_pcie_mdio_read(pcie->base, MDIO_PORT0, + SSC_STATUS_OFFSET, &tmp); + if (ret < 0) + return ret; + + ssc = FIELD_GET(SSC_STATUS_SSC_MASK, tmp); + pll = FIELD_GET(SSC_STATUS_PLL_LOCK_MASK, tmp); + + return ssc && pll ? 0 : -EIO; +} + +/* Limits operation to a specific generation (1, 2, or 3) */ +static void brcm_pcie_set_gen(struct brcm_pcie *pcie, int gen) +{ + u16 lnkctl2 = readw(pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCTL2); + u32 lnkcap = readl(pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCAP); + + lnkcap = (lnkcap & ~PCI_EXP_LNKCAP_SLS) | gen; + writel(lnkcap, pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCAP); + + lnkctl2 = (lnkctl2 & ~0xf) | gen; + writew(lnkctl2, pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCTL2); +} + +static void brcm_pcie_set_outbound_win(struct brcm_pcie *pcie, + unsigned int win, u64 cpu_addr, + u64 pcie_addr, u64 size) +{ + u32 cpu_addr_mb_high, limit_addr_mb_high; + phys_addr_t cpu_addr_mb, limit_addr_mb; + int high_addr_shift; + u32 tmp; + + /* Set the base of the pcie_addr window */ + writel(lower_32_bits(pcie_addr), pcie->base + PCIE_MEM_WIN0_LO(win)); + writel(upper_32_bits(pcie_addr), pcie->base + PCIE_MEM_WIN0_HI(win)); + + /* Write the addr base & limit lower bits (in MBs) */ + cpu_addr_mb = cpu_addr / SZ_1M; + limit_addr_mb = (cpu_addr + size - 1) / SZ_1M; + + tmp = readl(pcie->base + PCIE_MEM_WIN0_BASE_LIMIT(win)); + u32p_replace_bits(&tmp, cpu_addr_mb, + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_BASE_MASK); + u32p_replace_bits(&tmp, limit_addr_mb, + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_LIMIT_MASK); + writel(tmp, pcie->base + PCIE_MEM_WIN0_BASE_LIMIT(win)); + + if (is_bmips(pcie)) + return; + + /* Write the cpu & limit addr upper bits */ + high_addr_shift = + HWEIGHT32(PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_LIMIT_BASE_MASK); + + cpu_addr_mb_high = cpu_addr_mb >> high_addr_shift; + tmp = readl(pcie->base + PCIE_MEM_WIN0_BASE_HI(win)); + u32p_replace_bits(&tmp, cpu_addr_mb_high, + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_BASE_HI_BASE_MASK); + writel(tmp, pcie->base + PCIE_MEM_WIN0_BASE_HI(win)); + + limit_addr_mb_high = limit_addr_mb >> high_addr_shift; + tmp = readl(pcie->base + PCIE_MEM_WIN0_LIMIT_HI(win)); + u32p_replace_bits(&tmp, limit_addr_mb_high, + PCIE_MISC_CPU_2_PCIE_MEM_WIN0_LIMIT_HI_LIMIT_MASK); + writel(tmp, pcie->base + PCIE_MEM_WIN0_LIMIT_HI(win)); +} + +static struct irq_chip brcm_msi_irq_chip = { + .name = "BRCM STB PCIe MSI", + .irq_ack = irq_chip_ack_parent, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, +}; + +static struct msi_domain_info brcm_msi_domain_info = { + /* Multi MSI is supported by the controller, but not by this driver */ + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS), + .chip = &brcm_msi_irq_chip, +}; + +static void brcm_pcie_msi_isr(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned long status; + struct brcm_msi *msi; + struct device *dev; + u32 bit; + + chained_irq_enter(chip, desc); + msi = irq_desc_get_handler_data(desc); + dev = msi->dev; + + status = readl(msi->intr_base + MSI_INT_STATUS); + status >>= msi->legacy_shift; + + for_each_set_bit(bit, &status, msi->nr) { + int ret; + ret = generic_handle_domain_irq(msi->inner_domain, bit); + if (ret) + dev_dbg(dev, "unexpected MSI\n"); + } + + chained_irq_exit(chip, desc); +} + +static void brcm_msi_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct brcm_msi *msi = irq_data_get_irq_chip_data(data); + + msg->address_lo = lower_32_bits(msi->target_addr); + msg->address_hi = upper_32_bits(msi->target_addr); + msg->data = (0xffff & PCIE_MISC_MSI_DATA_CONFIG_VAL_32) | data->hwirq; +} + +static int brcm_msi_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static void brcm_msi_ack_irq(struct irq_data *data) +{ + struct brcm_msi *msi = irq_data_get_irq_chip_data(data); + const int shift_amt = data->hwirq + msi->legacy_shift; + + writel(1 << shift_amt, msi->intr_base + MSI_INT_CLR); +} + + +static struct irq_chip brcm_msi_bottom_irq_chip = { + .name = "BRCM STB MSI", + .irq_compose_msi_msg = brcm_msi_compose_msi_msg, + .irq_set_affinity = brcm_msi_set_affinity, + .irq_ack = brcm_msi_ack_irq, +}; + +static int brcm_msi_alloc(struct brcm_msi *msi) +{ + int hwirq; + + mutex_lock(&msi->lock); + hwirq = bitmap_find_free_region(msi->used, msi->nr, 0); + mutex_unlock(&msi->lock); + + return hwirq; +} + +static void brcm_msi_free(struct brcm_msi *msi, unsigned long hwirq) +{ + mutex_lock(&msi->lock); + bitmap_release_region(msi->used, hwirq, 0); + mutex_unlock(&msi->lock); +} + +static int brcm_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct brcm_msi *msi = domain->host_data; + int hwirq; + + hwirq = brcm_msi_alloc(msi); + + if (hwirq < 0) + return hwirq; + + irq_domain_set_info(domain, virq, (irq_hw_number_t)hwirq, + &brcm_msi_bottom_irq_chip, domain->host_data, + handle_edge_irq, NULL, NULL); + return 0; +} + +static void brcm_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct brcm_msi *msi = irq_data_get_irq_chip_data(d); + + brcm_msi_free(msi, d->hwirq); +} + +static const struct irq_domain_ops msi_domain_ops = { + .alloc = brcm_irq_domain_alloc, + .free = brcm_irq_domain_free, +}; + +static int brcm_allocate_domains(struct brcm_msi *msi) +{ + struct fwnode_handle *fwnode = of_node_to_fwnode(msi->np); + struct device *dev = msi->dev; + + msi->inner_domain = irq_domain_add_linear(NULL, msi->nr, &msi_domain_ops, msi); + if (!msi->inner_domain) { + dev_err(dev, "failed to create IRQ domain\n"); + return -ENOMEM; + } + + msi->msi_domain = pci_msi_create_irq_domain(fwnode, + &brcm_msi_domain_info, + msi->inner_domain); + if (!msi->msi_domain) { + dev_err(dev, "failed to create MSI domain\n"); + irq_domain_remove(msi->inner_domain); + return -ENOMEM; + } + + return 0; +} + +static void brcm_free_domains(struct brcm_msi *msi) +{ + irq_domain_remove(msi->msi_domain); + irq_domain_remove(msi->inner_domain); +} + +static void brcm_msi_remove(struct brcm_pcie *pcie) +{ + struct brcm_msi *msi = pcie->msi; + + if (!msi) + return; + irq_set_chained_handler_and_data(msi->irq, NULL, NULL); + brcm_free_domains(msi); +} + +static void brcm_msi_set_regs(struct brcm_msi *msi) +{ + u32 val = msi->legacy ? BRCM_INT_PCI_MSI_LEGACY_MASK : + BRCM_INT_PCI_MSI_MASK; + + writel(val, msi->intr_base + MSI_INT_MASK_CLR); + writel(val, msi->intr_base + MSI_INT_CLR); + + /* + * The 0 bit of PCIE_MISC_MSI_BAR_CONFIG_LO is repurposed to MSI + * enable, which we set to 1. + */ + writel(lower_32_bits(msi->target_addr) | 0x1, + msi->base + PCIE_MISC_MSI_BAR_CONFIG_LO); + writel(upper_32_bits(msi->target_addr), + msi->base + PCIE_MISC_MSI_BAR_CONFIG_HI); + + val = msi->legacy ? PCIE_MISC_MSI_DATA_CONFIG_VAL_8 : PCIE_MISC_MSI_DATA_CONFIG_VAL_32; + writel(val, msi->base + PCIE_MISC_MSI_DATA_CONFIG); +} + +static int brcm_pcie_enable_msi(struct brcm_pcie *pcie) +{ + struct brcm_msi *msi; + int irq, ret; + struct device *dev = pcie->dev; + + irq = irq_of_parse_and_map(dev->of_node, 1); + if (irq <= 0) { + dev_err(dev, "cannot map MSI interrupt\n"); + return -ENODEV; + } + + msi = devm_kzalloc(dev, sizeof(struct brcm_msi), GFP_KERNEL); + if (!msi) + return -ENOMEM; + + mutex_init(&msi->lock); + msi->dev = dev; + msi->base = pcie->base; + msi->np = pcie->np; + msi->target_addr = pcie->msi_target_addr; + msi->irq = irq; + msi->legacy = pcie->hw_rev < BRCM_PCIE_HW_REV_33; + + /* + * Sanity check to make sure that the 'used' bitmap in struct brcm_msi + * is large enough. + */ + BUILD_BUG_ON(BRCM_INT_PCI_MSI_LEGACY_NR > BRCM_INT_PCI_MSI_NR); + + if (msi->legacy) { + msi->intr_base = msi->base + PCIE_INTR2_CPU_BASE; + msi->nr = BRCM_INT_PCI_MSI_LEGACY_NR; + msi->legacy_shift = 24; + } else { + msi->intr_base = msi->base + PCIE_MSI_INTR2_BASE; + msi->nr = BRCM_INT_PCI_MSI_NR; + msi->legacy_shift = 0; + } + + ret = brcm_allocate_domains(msi); + if (ret) + return ret; + + irq_set_chained_handler_and_data(msi->irq, brcm_pcie_msi_isr, msi); + + brcm_msi_set_regs(msi); + pcie->msi = msi; + + return 0; +} + +/* The controller is capable of serving in both RC and EP roles */ +static bool brcm_pcie_rc_mode(struct brcm_pcie *pcie) +{ + void __iomem *base = pcie->base; + u32 val = readl(base + PCIE_MISC_PCIE_STATUS); + + return !!FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_PORT_MASK, val); +} + +static bool brcm_pcie_link_up(struct brcm_pcie *pcie) +{ + u32 val = readl(pcie->base + PCIE_MISC_PCIE_STATUS); + u32 dla = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_DL_ACTIVE_MASK, val); + u32 plu = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_PHYLINKUP_MASK, val); + + return dla && plu; +} + +static void __iomem *brcm_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct brcm_pcie *pcie = bus->sysdata; + void __iomem *base = pcie->base; + int idx; + + /* Accesses to the RC go right to the RC registers if !devfn */ + if (pci_is_root_bus(bus)) + return devfn ? NULL : base + PCIE_ECAM_REG(where); + + /* An access to our HW w/o link-up will cause a CPU Abort */ + if (!brcm_pcie_link_up(pcie)) + return NULL; + + /* For devices, write to the config space index register */ + idx = PCIE_ECAM_OFFSET(bus->number, devfn, 0); + writel(idx, pcie->base + PCIE_EXT_CFG_INDEX); + return base + PCIE_EXT_CFG_DATA + PCIE_ECAM_REG(where); +} + +static void __iomem *brcm7425_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct brcm_pcie *pcie = bus->sysdata; + void __iomem *base = pcie->base; + int idx; + + /* Accesses to the RC go right to the RC registers if !devfn */ + if (pci_is_root_bus(bus)) + return devfn ? NULL : base + PCIE_ECAM_REG(where); + + /* An access to our HW w/o link-up will cause a CPU Abort */ + if (!brcm_pcie_link_up(pcie)) + return NULL; + + /* For devices, write to the config space index register */ + idx = PCIE_ECAM_OFFSET(bus->number, devfn, where); + writel(idx, base + IDX_ADDR(pcie)); + return base + DATA_ADDR(pcie); +} + +static inline void brcm_pcie_bridge_sw_init_set_generic(struct brcm_pcie *pcie, u32 val) +{ + u32 tmp, mask = RGR1_SW_INIT_1_INIT_GENERIC_MASK; + u32 shift = RGR1_SW_INIT_1_INIT_GENERIC_SHIFT; + + tmp = readl(pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); + tmp = (tmp & ~mask) | ((val << shift) & mask); + writel(tmp, pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); +} + +static inline void brcm_pcie_bridge_sw_init_set_7278(struct brcm_pcie *pcie, u32 val) +{ + u32 tmp, mask = RGR1_SW_INIT_1_INIT_7278_MASK; + u32 shift = RGR1_SW_INIT_1_INIT_7278_SHIFT; + + tmp = readl(pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); + tmp = (tmp & ~mask) | ((val << shift) & mask); + writel(tmp, pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); +} + +static inline void brcm_pcie_perst_set_4908(struct brcm_pcie *pcie, u32 val) +{ + if (WARN_ONCE(!pcie->perst_reset, "missing PERST# reset controller\n")) + return; + + if (val) + reset_control_assert(pcie->perst_reset); + else + reset_control_deassert(pcie->perst_reset); +} + +static inline void brcm_pcie_perst_set_7278(struct brcm_pcie *pcie, u32 val) +{ + u32 tmp; + + /* Perst bit has moved and assert value is 0 */ + tmp = readl(pcie->base + PCIE_MISC_PCIE_CTRL); + u32p_replace_bits(&tmp, !val, PCIE_MISC_PCIE_CTRL_PCIE_PERSTB_MASK); + writel(tmp, pcie->base + PCIE_MISC_PCIE_CTRL); +} + +static inline void brcm_pcie_perst_set_generic(struct brcm_pcie *pcie, u32 val) +{ + u32 tmp; + + tmp = readl(pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); + u32p_replace_bits(&tmp, val, PCIE_RGR1_SW_INIT_1_PERST_MASK); + writel(tmp, pcie->base + PCIE_RGR1_SW_INIT_1(pcie)); +} + +static inline int brcm_pcie_get_rc_bar2_size_and_offset(struct brcm_pcie *pcie, + u64 *rc_bar2_size, + u64 *rc_bar2_offset) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + struct resource_entry *entry; + struct device *dev = pcie->dev; + u64 lowest_pcie_addr = ~(u64)0; + int ret, i = 0; + u64 size = 0; + + resource_list_for_each_entry(entry, &bridge->dma_ranges) { + u64 pcie_beg = entry->res->start - entry->offset; + + size += entry->res->end - entry->res->start + 1; + if (pcie_beg < lowest_pcie_addr) + lowest_pcie_addr = pcie_beg; + } + + if (lowest_pcie_addr == ~(u64)0) { + dev_err(dev, "DT node has no dma-ranges\n"); + return -EINVAL; + } + + ret = of_property_read_variable_u64_array(pcie->np, "brcm,scb-sizes", pcie->memc_size, 1, + PCIE_BRCM_MAX_MEMC); + + if (ret <= 0) { + /* Make an educated guess */ + pcie->num_memc = 1; + pcie->memc_size[0] = 1ULL << fls64(size - 1); + } else { + pcie->num_memc = ret; + } + + /* Each memc is viewed through a "port" that is a power of 2 */ + for (i = 0, size = 0; i < pcie->num_memc; i++) + size += pcie->memc_size[i]; + + /* System memory starts at this address in PCIe-space */ + *rc_bar2_offset = lowest_pcie_addr; + /* The sum of all memc views must also be a power of 2 */ + *rc_bar2_size = 1ULL << fls64(size - 1); + + /* + * We validate the inbound memory view even though we should trust + * whatever the device-tree provides. This is because of an HW issue on + * early Raspberry Pi 4's revisions (bcm2711). It turns out its + * firmware has to dynamically edit dma-ranges due to a bug on the + * PCIe controller integration, which prohibits any access above the + * lower 3GB of memory. Given this, we decided to keep the dma-ranges + * in check, avoiding hard to debug device-tree related issues in the + * future: + * + * The PCIe host controller by design must set the inbound viewport to + * be a contiguous arrangement of all of the system's memory. In + * addition, its size mut be a power of two. To further complicate + * matters, the viewport must start on a pcie-address that is aligned + * on a multiple of its size. If a portion of the viewport does not + * represent system memory -- e.g. 3GB of memory requires a 4GB + * viewport -- we can map the outbound memory in or after 3GB and even + * though the viewport will overlap the outbound memory the controller + * will know to send outbound memory downstream and everything else + * upstream. + * + * For example: + * + * - The best-case scenario, memory up to 3GB, is to place the inbound + * region in the first 4GB of pcie-space, as some legacy devices can + * only address 32bits. We would also like to put the MSI under 4GB + * as well, since some devices require a 32bit MSI target address. + * + * - If the system memory is 4GB or larger we cannot start the inbound + * region at location 0 (since we have to allow some space for + * outbound memory @ 3GB). So instead it will start at the 1x + * multiple of its size + */ + if (!*rc_bar2_size || (*rc_bar2_offset & (*rc_bar2_size - 1)) || + (*rc_bar2_offset < SZ_4G && *rc_bar2_offset > SZ_2G)) { + dev_err(dev, "Invalid rc_bar2_offset/size: size 0x%llx, off 0x%llx\n", + *rc_bar2_size, *rc_bar2_offset); + return -EINVAL; + } + + return 0; +} + +static int brcm_pcie_setup(struct brcm_pcie *pcie) +{ + u64 rc_bar2_offset, rc_bar2_size; + void __iomem *base = pcie->base; + struct pci_host_bridge *bridge; + struct resource_entry *entry; + u32 tmp, burst, aspm_support; + int num_out_wins = 0; + int ret, memc; + + /* Reset the bridge */ + pcie->bridge_sw_init_set(pcie, 1); + usleep_range(100, 200); + + /* Take the bridge out of reset */ + pcie->bridge_sw_init_set(pcie, 0); + + tmp = readl(base + PCIE_MISC_HARD_PCIE_HARD_DEBUG); + if (is_bmips(pcie)) + tmp &= ~PCIE_BMIPS_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK; + else + tmp &= ~PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK; + writel(tmp, base + PCIE_MISC_HARD_PCIE_HARD_DEBUG); + /* Wait for SerDes to be stable */ + usleep_range(100, 200); + + /* + * SCB_MAX_BURST_SIZE is a two bit field. For GENERIC chips it + * is encoded as 0=128, 1=256, 2=512, 3=Rsvd, for BCM7278 it + * is encoded as 0=Rsvd, 1=128, 2=256, 3=512. + */ + if (is_bmips(pcie)) + burst = 0x1; /* 256 bytes */ + else if (pcie->type == BCM2711) + burst = 0x0; /* 128 bytes */ + else if (pcie->type == BCM7278) + burst = 0x3; /* 512 bytes */ + else + burst = 0x2; /* 512 bytes */ + + /* Set SCB_MAX_BURST_SIZE, CFG_READ_UR_MODE, SCB_ACCESS_EN */ + tmp = readl(base + PCIE_MISC_MISC_CTRL); + u32p_replace_bits(&tmp, 1, PCIE_MISC_MISC_CTRL_SCB_ACCESS_EN_MASK); + u32p_replace_bits(&tmp, 1, PCIE_MISC_MISC_CTRL_CFG_READ_UR_MODE_MASK); + u32p_replace_bits(&tmp, burst, PCIE_MISC_MISC_CTRL_MAX_BURST_SIZE_MASK); + writel(tmp, base + PCIE_MISC_MISC_CTRL); + + ret = brcm_pcie_get_rc_bar2_size_and_offset(pcie, &rc_bar2_size, + &rc_bar2_offset); + if (ret) + return ret; + + tmp = lower_32_bits(rc_bar2_offset); + u32p_replace_bits(&tmp, brcm_pcie_encode_ibar_size(rc_bar2_size), + PCIE_MISC_RC_BAR2_CONFIG_LO_SIZE_MASK); + writel(tmp, base + PCIE_MISC_RC_BAR2_CONFIG_LO); + writel(upper_32_bits(rc_bar2_offset), + base + PCIE_MISC_RC_BAR2_CONFIG_HI); + + tmp = readl(base + PCIE_MISC_MISC_CTRL); + for (memc = 0; memc < pcie->num_memc; memc++) { + u32 scb_size_val = ilog2(pcie->memc_size[memc]) - 15; + + if (memc == 0) + u32p_replace_bits(&tmp, scb_size_val, SCB_SIZE_MASK(0)); + else if (memc == 1) + u32p_replace_bits(&tmp, scb_size_val, SCB_SIZE_MASK(1)); + else if (memc == 2) + u32p_replace_bits(&tmp, scb_size_val, SCB_SIZE_MASK(2)); + } + writel(tmp, base + PCIE_MISC_MISC_CTRL); + + /* + * We ideally want the MSI target address to be located in the 32bit + * addressable memory area. Some devices might depend on it. This is + * possible either when the inbound window is located above the lower + * 4GB or when the inbound area is smaller than 4GB (taking into + * account the rounding-up we're forced to perform). + */ + if (rc_bar2_offset >= SZ_4G || (rc_bar2_size + rc_bar2_offset) < SZ_4G) + pcie->msi_target_addr = BRCM_MSI_TARGET_ADDR_LT_4GB; + else + pcie->msi_target_addr = BRCM_MSI_TARGET_ADDR_GT_4GB; + + if (!brcm_pcie_rc_mode(pcie)) { + dev_err(pcie->dev, "PCIe RC controller misconfigured as Endpoint\n"); + return -EINVAL; + } + + /* disable the PCIe->GISB memory window (RC_BAR1) */ + tmp = readl(base + PCIE_MISC_RC_BAR1_CONFIG_LO); + tmp &= ~PCIE_MISC_RC_BAR1_CONFIG_LO_SIZE_MASK; + writel(tmp, base + PCIE_MISC_RC_BAR1_CONFIG_LO); + + /* disable the PCIe->SCB memory window (RC_BAR3) */ + tmp = readl(base + PCIE_MISC_RC_BAR3_CONFIG_LO); + tmp &= ~PCIE_MISC_RC_BAR3_CONFIG_LO_SIZE_MASK; + writel(tmp, base + PCIE_MISC_RC_BAR3_CONFIG_LO); + + /* Don't advertise L0s capability if 'aspm-no-l0s' */ + aspm_support = PCIE_LINK_STATE_L1; + if (!of_property_read_bool(pcie->np, "aspm-no-l0s")) + aspm_support |= PCIE_LINK_STATE_L0S; + tmp = readl(base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY); + u32p_replace_bits(&tmp, aspm_support, + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_ASPM_SUPPORT_MASK); + writel(tmp, base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY); + + /* + * For config space accesses on the RC, show the right class for + * a PCIe-PCIe bridge (the default setting is to be EP mode). + */ + tmp = readl(base + PCIE_RC_CFG_PRIV1_ID_VAL3); + u32p_replace_bits(&tmp, 0x060400, + PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_MASK); + writel(tmp, base + PCIE_RC_CFG_PRIV1_ID_VAL3); + + bridge = pci_host_bridge_from_priv(pcie); + resource_list_for_each_entry(entry, &bridge->windows) { + struct resource *res = entry->res; + + if (resource_type(res) != IORESOURCE_MEM) + continue; + + if (num_out_wins >= BRCM_NUM_PCIE_OUT_WINS) { + dev_err(pcie->dev, "too many outbound wins\n"); + return -EINVAL; + } + + if (is_bmips(pcie)) { + u64 start = res->start; + unsigned int j, nwins = resource_size(res) / SZ_128M; + + /* bmips PCIe outbound windows have a 128MB max size */ + if (nwins > BRCM_NUM_PCIE_OUT_WINS) + nwins = BRCM_NUM_PCIE_OUT_WINS; + for (j = 0; j < nwins; j++, start += SZ_128M) + brcm_pcie_set_outbound_win(pcie, j, start, + start - entry->offset, + SZ_128M); + break; + } + brcm_pcie_set_outbound_win(pcie, num_out_wins, res->start, + res->start - entry->offset, + resource_size(res)); + num_out_wins++; + } + + /* PCIe->SCB endian mode for BAR */ + tmp = readl(base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1); + u32p_replace_bits(&tmp, PCIE_RC_CFG_VENDOR_SPCIFIC_REG1_LITTLE_ENDIAN, + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1_ENDIAN_MODE_BAR2_MASK); + writel(tmp, base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1); + + return 0; +} + +static int brcm_pcie_start_link(struct brcm_pcie *pcie) +{ + struct device *dev = pcie->dev; + void __iomem *base = pcie->base; + u16 nlw, cls, lnksta; + bool ssc_good = false; + u32 tmp; + int ret, i; + + /* Unassert the fundamental reset */ + pcie->perst_set(pcie, 0); + + /* + * Give the RC/EP time to wake up, before trying to configure RC. + * Intermittently check status for link-up, up to a total of 100ms. + */ + for (i = 0; i < 100 && !brcm_pcie_link_up(pcie); i += 5) + msleep(5); + + if (!brcm_pcie_link_up(pcie)) { + dev_err(dev, "link down\n"); + return -ENODEV; + } + + if (pcie->gen) + brcm_pcie_set_gen(pcie, pcie->gen); + + if (pcie->ssc) { + ret = brcm_pcie_set_ssc(pcie); + if (ret == 0) + ssc_good = true; + else + dev_err(dev, "failed attempt to enter ssc mode\n"); + } + + lnksta = readw(base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKSTA); + cls = FIELD_GET(PCI_EXP_LNKSTA_CLS, lnksta); + nlw = FIELD_GET(PCI_EXP_LNKSTA_NLW, lnksta); + dev_info(dev, "link up, %s x%u %s\n", + pci_speed_string(pcie_link_speed[cls]), nlw, + ssc_good ? "(SSC)" : "(!SSC)"); + + /* + * Refclk from RC should be gated with CLKREQ# input when ASPM L0s,L1 + * is enabled => setting the CLKREQ_DEBUG_ENABLE field to 1. + */ + tmp = readl(base + PCIE_MISC_HARD_PCIE_HARD_DEBUG); + tmp |= PCIE_MISC_HARD_PCIE_HARD_DEBUG_CLKREQ_DEBUG_ENABLE_MASK; + writel(tmp, base + PCIE_MISC_HARD_PCIE_HARD_DEBUG); + + return 0; +} + +static const char * const supplies[] = { + "vpcie3v3", + "vpcie3v3aux", + "vpcie12v", +}; + +static void *alloc_subdev_regulators(struct device *dev) +{ + const size_t size = sizeof(struct subdev_regulators) + + sizeof(struct regulator_bulk_data) * ARRAY_SIZE(supplies); + struct subdev_regulators *sr; + int i; + + sr = devm_kzalloc(dev, size, GFP_KERNEL); + if (sr) { + sr->num_supplies = ARRAY_SIZE(supplies); + for (i = 0; i < ARRAY_SIZE(supplies); i++) + sr->supplies[i].supply = supplies[i]; + } + + return sr; +} + +static int brcm_pcie_add_bus(struct pci_bus *bus) +{ + struct brcm_pcie *pcie = bus->sysdata; + struct device *dev = &bus->dev; + struct subdev_regulators *sr; + int ret; + + if (!bus->parent || !pci_is_root_bus(bus->parent)) + return 0; + + if (dev->of_node) { + sr = alloc_subdev_regulators(dev); + if (!sr) { + dev_info(dev, "Can't allocate regulators for downstream device\n"); + goto no_regulators; + } + + pcie->sr = sr; + + ret = regulator_bulk_get(dev, sr->num_supplies, sr->supplies); + if (ret) { + dev_info(dev, "No regulators for downstream device\n"); + goto no_regulators; + } + + ret = regulator_bulk_enable(sr->num_supplies, sr->supplies); + if (ret) { + dev_err(dev, "Can't enable regulators for downstream device\n"); + regulator_bulk_free(sr->num_supplies, sr->supplies); + pcie->sr = NULL; + } + } + +no_regulators: + brcm_pcie_start_link(pcie); + return 0; +} + +static void brcm_pcie_remove_bus(struct pci_bus *bus) +{ + struct brcm_pcie *pcie = bus->sysdata; + struct subdev_regulators *sr = pcie->sr; + struct device *dev = &bus->dev; + + if (!sr) + return; + + if (regulator_bulk_disable(sr->num_supplies, sr->supplies)) + dev_err(dev, "Failed to disable regulators for downstream device\n"); + regulator_bulk_free(sr->num_supplies, sr->supplies); + pcie->sr = NULL; +} + +/* L23 is a low-power PCIe link state */ +static void brcm_pcie_enter_l23(struct brcm_pcie *pcie) +{ + void __iomem *base = pcie->base; + int l23, i; + u32 tmp; + + /* Assert request for L23 */ + tmp = readl(base + PCIE_MISC_PCIE_CTRL); + u32p_replace_bits(&tmp, 1, PCIE_MISC_PCIE_CTRL_PCIE_L23_REQUEST_MASK); + writel(tmp, base + PCIE_MISC_PCIE_CTRL); + + /* Wait up to 36 msec for L23 */ + tmp = readl(base + PCIE_MISC_PCIE_STATUS); + l23 = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_LINK_IN_L23_MASK, tmp); + for (i = 0; i < 15 && !l23; i++) { + usleep_range(2000, 2400); + tmp = readl(base + PCIE_MISC_PCIE_STATUS); + l23 = FIELD_GET(PCIE_MISC_PCIE_STATUS_PCIE_LINK_IN_L23_MASK, + tmp); + } + + if (!l23) + dev_err(pcie->dev, "failed to enter low-power link state\n"); +} + +static int brcm_phy_cntl(struct brcm_pcie *pcie, const int start) +{ + static const u32 shifts[PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_NFLDS] = { + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_PWRDN_SHIFT, + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_RESET_SHIFT, + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_DIG_RESET_SHIFT,}; + static const u32 masks[PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_NFLDS] = { + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_PWRDN_MASK, + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_RESET_MASK, + PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_DIG_RESET_MASK,}; + const int beg = start ? 0 : PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_NFLDS - 1; + const int end = start ? PCIE_DVT_PMU_PCIE_PHY_CTRL_DAST_NFLDS : -1; + u32 tmp, combined_mask = 0; + u32 val; + void __iomem *base = pcie->base; + int i, ret; + + for (i = beg; i != end; start ? i++ : i--) { + val = start ? BIT_MASK(shifts[i]) : 0; + tmp = readl(base + PCIE_DVT_PMU_PCIE_PHY_CTRL); + tmp = (tmp & ~masks[i]) | (val & masks[i]); + writel(tmp, base + PCIE_DVT_PMU_PCIE_PHY_CTRL); + usleep_range(50, 200); + combined_mask |= masks[i]; + } + + tmp = readl(base + PCIE_DVT_PMU_PCIE_PHY_CTRL); + val = start ? combined_mask : 0; + + ret = (tmp & combined_mask) == val ? 0 : -EIO; + if (ret) + dev_err(pcie->dev, "failed to %s phy\n", (start ? "start" : "stop")); + + return ret; +} + +static inline int brcm_phy_start(struct brcm_pcie *pcie) +{ + return pcie->rescal ? brcm_phy_cntl(pcie, 1) : 0; +} + +static inline int brcm_phy_stop(struct brcm_pcie *pcie) +{ + return pcie->rescal ? brcm_phy_cntl(pcie, 0) : 0; +} + +static void brcm_pcie_turn_off(struct brcm_pcie *pcie) +{ + void __iomem *base = pcie->base; + int tmp; + + if (brcm_pcie_link_up(pcie)) + brcm_pcie_enter_l23(pcie); + /* Assert fundamental reset */ + pcie->perst_set(pcie, 1); + + /* Deassert request for L23 in case it was asserted */ + tmp = readl(base + PCIE_MISC_PCIE_CTRL); + u32p_replace_bits(&tmp, 0, PCIE_MISC_PCIE_CTRL_PCIE_L23_REQUEST_MASK); + writel(tmp, base + PCIE_MISC_PCIE_CTRL); + + /* Turn off SerDes */ + tmp = readl(base + PCIE_MISC_HARD_PCIE_HARD_DEBUG); + u32p_replace_bits(&tmp, 1, PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK); + writel(tmp, base + PCIE_MISC_HARD_PCIE_HARD_DEBUG); + + /* Shutdown PCIe bridge */ + pcie->bridge_sw_init_set(pcie, 1); +} + +static int pci_dev_may_wakeup(struct pci_dev *dev, void *data) +{ + bool *ret = data; + + if (device_may_wakeup(&dev->dev)) { + *ret = true; + dev_info(&dev->dev, "Possible wake-up device; regulators will not be disabled\n"); + } + return (int) *ret; +} + +static int brcm_pcie_suspend_noirq(struct device *dev) +{ + struct brcm_pcie *pcie = dev_get_drvdata(dev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + int ret; + + brcm_pcie_turn_off(pcie); + /* + * If brcm_phy_stop() returns an error, just dev_err(). If we + * return the error it will cause the suspend to fail and this is a + * forgivable offense that will probably be erased on resume. + */ + if (brcm_phy_stop(pcie)) + dev_err(dev, "Could not stop phy for suspend\n"); + + ret = reset_control_rearm(pcie->rescal); + if (ret) { + dev_err(dev, "Could not rearm rescal reset\n"); + return ret; + } + + if (pcie->sr) { + /* + * Now turn off the regulators, but if at least one + * downstream device is enabled as a wake-up source, do not + * turn off regulators. + */ + pcie->ep_wakeup_capable = false; + pci_walk_bus(bridge->bus, pci_dev_may_wakeup, + &pcie->ep_wakeup_capable); + if (!pcie->ep_wakeup_capable) { + ret = regulator_bulk_disable(pcie->sr->num_supplies, + pcie->sr->supplies); + if (ret) { + dev_err(dev, "Could not turn off regulators\n"); + reset_control_reset(pcie->rescal); + return ret; + } + } + } + clk_disable_unprepare(pcie->clk); + + return 0; +} + +static int brcm_pcie_resume_noirq(struct device *dev) +{ + struct brcm_pcie *pcie = dev_get_drvdata(dev); + void __iomem *base; + u32 tmp; + int ret; + + base = pcie->base; + ret = clk_prepare_enable(pcie->clk); + if (ret) + return ret; + + ret = reset_control_reset(pcie->rescal); + if (ret) + goto err_disable_clk; + + ret = brcm_phy_start(pcie); + if (ret) + goto err_reset; + + /* Take bridge out of reset so we can access the SERDES reg */ + pcie->bridge_sw_init_set(pcie, 0); + + /* SERDES_IDDQ = 0 */ + tmp = readl(base + PCIE_MISC_HARD_PCIE_HARD_DEBUG); + u32p_replace_bits(&tmp, 0, PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK); + writel(tmp, base + PCIE_MISC_HARD_PCIE_HARD_DEBUG); + + /* wait for serdes to be stable */ + udelay(100); + + ret = brcm_pcie_setup(pcie); + if (ret) + goto err_reset; + + if (pcie->sr) { + if (pcie->ep_wakeup_capable) { + /* + * We are resuming from a suspend. In the suspend we + * did not disable the power supplies, so there is + * no need to enable them (and falsely increase their + * usage count). + */ + pcie->ep_wakeup_capable = false; + } else { + ret = regulator_bulk_enable(pcie->sr->num_supplies, + pcie->sr->supplies); + if (ret) { + dev_err(dev, "Could not turn on regulators\n"); + goto err_reset; + } + } + } + + ret = brcm_pcie_start_link(pcie); + if (ret) + goto err_regulator; + + if (pcie->msi) + brcm_msi_set_regs(pcie->msi); + + return 0; + +err_regulator: + if (pcie->sr) + regulator_bulk_disable(pcie->sr->num_supplies, pcie->sr->supplies); +err_reset: + reset_control_rearm(pcie->rescal); +err_disable_clk: + clk_disable_unprepare(pcie->clk); + return ret; +} + +static void __brcm_pcie_remove(struct brcm_pcie *pcie) +{ + brcm_msi_remove(pcie); + brcm_pcie_turn_off(pcie); + if (brcm_phy_stop(pcie)) + dev_err(pcie->dev, "Could not stop phy\n"); + if (reset_control_rearm(pcie->rescal)) + dev_err(pcie->dev, "Could not rearm rescal reset\n"); + clk_disable_unprepare(pcie->clk); +} + +static int brcm_pcie_remove(struct platform_device *pdev) +{ + struct brcm_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); + __brcm_pcie_remove(pcie); + + return 0; +} + +static const int pcie_offsets[] = { + [RGR1_SW_INIT_1] = 0x9210, + [EXT_CFG_INDEX] = 0x9000, + [EXT_CFG_DATA] = 0x9004, +}; + +static const int pcie_offsets_bmips_7425[] = { + [RGR1_SW_INIT_1] = 0x8010, + [EXT_CFG_INDEX] = 0x8300, + [EXT_CFG_DATA] = 0x8304, +}; + +static const struct pcie_cfg_data generic_cfg = { + .offsets = pcie_offsets, + .type = GENERIC, + .perst_set = brcm_pcie_perst_set_generic, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, +}; + +static const struct pcie_cfg_data bcm7425_cfg = { + .offsets = pcie_offsets_bmips_7425, + .type = BCM7425, + .perst_set = brcm_pcie_perst_set_generic, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, +}; + +static const struct pcie_cfg_data bcm7435_cfg = { + .offsets = pcie_offsets, + .type = BCM7435, + .perst_set = brcm_pcie_perst_set_generic, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, +}; + +static const struct pcie_cfg_data bcm4908_cfg = { + .offsets = pcie_offsets, + .type = BCM4908, + .perst_set = brcm_pcie_perst_set_4908, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, +}; + +static const int pcie_offset_bcm7278[] = { + [RGR1_SW_INIT_1] = 0xc010, + [EXT_CFG_INDEX] = 0x9000, + [EXT_CFG_DATA] = 0x9004, +}; + +static const struct pcie_cfg_data bcm7278_cfg = { + .offsets = pcie_offset_bcm7278, + .type = BCM7278, + .perst_set = brcm_pcie_perst_set_7278, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_7278, +}; + +static const struct pcie_cfg_data bcm2711_cfg = { + .offsets = pcie_offsets, + .type = BCM2711, + .perst_set = brcm_pcie_perst_set_generic, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, +}; + +static const struct of_device_id brcm_pcie_match[] = { + { .compatible = "brcm,bcm2711-pcie", .data = &bcm2711_cfg }, + { .compatible = "brcm,bcm4908-pcie", .data = &bcm4908_cfg }, + { .compatible = "brcm,bcm7211-pcie", .data = &generic_cfg }, + { .compatible = "brcm,bcm7278-pcie", .data = &bcm7278_cfg }, + { .compatible = "brcm,bcm7216-pcie", .data = &bcm7278_cfg }, + { .compatible = "brcm,bcm7445-pcie", .data = &generic_cfg }, + { .compatible = "brcm,bcm7435-pcie", .data = &bcm7435_cfg }, + { .compatible = "brcm,bcm7425-pcie", .data = &bcm7425_cfg }, + {}, +}; + +static struct pci_ops brcm_pcie_ops = { + .map_bus = brcm_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + .add_bus = brcm_pcie_add_bus, + .remove_bus = brcm_pcie_remove_bus, +}; + +static struct pci_ops brcm7425_pcie_ops = { + .map_bus = brcm7425_pcie_map_bus, + .read = pci_generic_config_read32, + .write = pci_generic_config_write32, + .add_bus = brcm_pcie_add_bus, + .remove_bus = brcm_pcie_remove_bus, +}; + +static int brcm_pcie_probe(struct platform_device *pdev) +{ + struct device_node *np = pdev->dev.of_node, *msi_np; + struct pci_host_bridge *bridge; + const struct pcie_cfg_data *data; + struct brcm_pcie *pcie; + int ret; + + bridge = devm_pci_alloc_host_bridge(&pdev->dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + data = of_device_get_match_data(&pdev->dev); + if (!data) { + pr_err("failed to look up compatible string\n"); + return -EINVAL; + } + + pcie = pci_host_bridge_priv(bridge); + pcie->dev = &pdev->dev; + pcie->np = np; + pcie->reg_offsets = data->offsets; + pcie->type = data->type; + pcie->perst_set = data->perst_set; + pcie->bridge_sw_init_set = data->bridge_sw_init_set; + + pcie->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + + pcie->clk = devm_clk_get_optional(&pdev->dev, "sw_pcie"); + if (IS_ERR(pcie->clk)) + return PTR_ERR(pcie->clk); + + ret = of_pci_get_max_link_speed(np); + pcie->gen = (ret < 0) ? 0 : ret; + + pcie->ssc = of_property_read_bool(np, "brcm,enable-ssc"); + + ret = clk_prepare_enable(pcie->clk); + if (ret) { + dev_err(&pdev->dev, "could not enable clock\n"); + return ret; + } + pcie->rescal = devm_reset_control_get_optional_shared(&pdev->dev, "rescal"); + if (IS_ERR(pcie->rescal)) { + clk_disable_unprepare(pcie->clk); + return PTR_ERR(pcie->rescal); + } + pcie->perst_reset = devm_reset_control_get_optional_exclusive(&pdev->dev, "perst"); + if (IS_ERR(pcie->perst_reset)) { + clk_disable_unprepare(pcie->clk); + return PTR_ERR(pcie->perst_reset); + } + + ret = reset_control_reset(pcie->rescal); + if (ret) + dev_err(&pdev->dev, "failed to deassert 'rescal'\n"); + + ret = brcm_phy_start(pcie); + if (ret) { + reset_control_rearm(pcie->rescal); + clk_disable_unprepare(pcie->clk); + return ret; + } + + ret = brcm_pcie_setup(pcie); + if (ret) + goto fail; + + pcie->hw_rev = readl(pcie->base + PCIE_MISC_REVISION); + if (pcie->type == BCM4908 && pcie->hw_rev >= BRCM_PCIE_HW_REV_3_20) { + dev_err(pcie->dev, "hardware revision with unsupported PERST# setup\n"); + ret = -ENODEV; + goto fail; + } + + msi_np = of_parse_phandle(pcie->np, "msi-parent", 0); + if (pci_msi_enabled() && msi_np == pcie->np) { + ret = brcm_pcie_enable_msi(pcie); + if (ret) { + dev_err(pcie->dev, "probe of internal MSI failed"); + goto fail; + } + } + + bridge->ops = pcie->type == BCM7425 ? &brcm7425_pcie_ops : &brcm_pcie_ops; + bridge->sysdata = pcie; + + platform_set_drvdata(pdev, pcie); + + ret = pci_host_probe(bridge); + if (!ret && !brcm_pcie_link_up(pcie)) + ret = -ENODEV; + + if (ret) { + brcm_pcie_remove(pdev); + return ret; + } + + return 0; + +fail: + __brcm_pcie_remove(pcie); + return ret; +} + +MODULE_DEVICE_TABLE(of, brcm_pcie_match); + +static const struct dev_pm_ops brcm_pcie_pm_ops = { + .suspend_noirq = brcm_pcie_suspend_noirq, + .resume_noirq = brcm_pcie_resume_noirq, +}; + +static struct platform_driver brcm_pcie_driver = { + .probe = brcm_pcie_probe, + .remove = brcm_pcie_remove, + .driver = { + .name = "brcm-pcie", + .of_match_table = brcm_pcie_match, + .pm = &brcm_pcie_pm_ops, + }, +}; +module_platform_driver(brcm_pcie_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Broadcom STB PCIe RC driver"); +MODULE_AUTHOR("Broadcom"); diff --git a/drivers/pci/controller/pcie-hisi-error.c b/drivers/pci/controller/pcie-hisi-error.c new file mode 100644 index 000000000..7959c9c8d --- /dev/null +++ b/drivers/pci/controller/pcie-hisi-error.c @@ -0,0 +1,327 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Driver for handling the PCIe controller errors on + * HiSilicon HIP SoCs. + * + * Copyright (c) 2020 HiSilicon Limited. + */ + +#include <linux/acpi.h> +#include <acpi/ghes.h> +#include <linux/bitops.h> +#include <linux/delay.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/kfifo.h> +#include <linux/spinlock.h> + +/* HISI PCIe controller error definitions */ +#define HISI_PCIE_ERR_MISC_REGS 33 + +#define HISI_PCIE_LOCAL_VALID_VERSION BIT(0) +#define HISI_PCIE_LOCAL_VALID_SOC_ID BIT(1) +#define HISI_PCIE_LOCAL_VALID_SOCKET_ID BIT(2) +#define HISI_PCIE_LOCAL_VALID_NIMBUS_ID BIT(3) +#define HISI_PCIE_LOCAL_VALID_SUB_MODULE_ID BIT(4) +#define HISI_PCIE_LOCAL_VALID_CORE_ID BIT(5) +#define HISI_PCIE_LOCAL_VALID_PORT_ID BIT(6) +#define HISI_PCIE_LOCAL_VALID_ERR_TYPE BIT(7) +#define HISI_PCIE_LOCAL_VALID_ERR_SEVERITY BIT(8) +#define HISI_PCIE_LOCAL_VALID_ERR_MISC 9 + +static guid_t hisi_pcie_sec_guid = + GUID_INIT(0xB2889FC9, 0xE7D7, 0x4F9D, + 0xA8, 0x67, 0xAF, 0x42, 0xE9, 0x8B, 0xE7, 0x72); + +/* + * Firmware reports the socket port ID where the error occurred. These + * macros convert that to the core ID and core port ID required by the + * ACPI reset method. + */ +#define HISI_PCIE_PORT_ID(core, v) (((v) >> 1) + ((core) << 3)) +#define HISI_PCIE_CORE_ID(v) ((v) >> 3) +#define HISI_PCIE_CORE_PORT_ID(v) (((v) & 7) << 1) + +struct hisi_pcie_error_data { + u64 val_bits; + u8 version; + u8 soc_id; + u8 socket_id; + u8 nimbus_id; + u8 sub_module_id; + u8 core_id; + u8 port_id; + u8 err_severity; + u16 err_type; + u8 reserv[2]; + u32 err_misc[HISI_PCIE_ERR_MISC_REGS]; +}; + +struct hisi_pcie_error_private { + struct notifier_block nb; + struct device *dev; +}; + +enum hisi_pcie_submodule_id { + HISI_PCIE_SUB_MODULE_ID_AP, + HISI_PCIE_SUB_MODULE_ID_TL, + HISI_PCIE_SUB_MODULE_ID_MAC, + HISI_PCIE_SUB_MODULE_ID_DL, + HISI_PCIE_SUB_MODULE_ID_SDI, +}; + +static const char * const hisi_pcie_sub_module[] = { + [HISI_PCIE_SUB_MODULE_ID_AP] = "AP Layer", + [HISI_PCIE_SUB_MODULE_ID_TL] = "TL Layer", + [HISI_PCIE_SUB_MODULE_ID_MAC] = "MAC Layer", + [HISI_PCIE_SUB_MODULE_ID_DL] = "DL Layer", + [HISI_PCIE_SUB_MODULE_ID_SDI] = "SDI Layer", +}; + +enum hisi_pcie_err_severity { + HISI_PCIE_ERR_SEV_RECOVERABLE, + HISI_PCIE_ERR_SEV_FATAL, + HISI_PCIE_ERR_SEV_CORRECTED, + HISI_PCIE_ERR_SEV_NONE, +}; + +static const char * const hisi_pcie_error_sev[] = { + [HISI_PCIE_ERR_SEV_RECOVERABLE] = "recoverable", + [HISI_PCIE_ERR_SEV_FATAL] = "fatal", + [HISI_PCIE_ERR_SEV_CORRECTED] = "corrected", + [HISI_PCIE_ERR_SEV_NONE] = "none", +}; + +static const char *hisi_pcie_get_string(const char * const *array, + size_t n, u32 id) +{ + u32 index; + + for (index = 0; index < n; index++) { + if (index == id && array[index]) + return array[index]; + } + + return "unknown"; +} + +static int hisi_pcie_port_reset(struct platform_device *pdev, + u32 chip_id, u32 port_id) +{ + struct device *dev = &pdev->dev; + acpi_handle handle = ACPI_HANDLE(dev); + union acpi_object arg[3]; + struct acpi_object_list arg_list; + acpi_status s; + unsigned long long data = 0; + + arg[0].type = ACPI_TYPE_INTEGER; + arg[0].integer.value = chip_id; + arg[1].type = ACPI_TYPE_INTEGER; + arg[1].integer.value = HISI_PCIE_CORE_ID(port_id); + arg[2].type = ACPI_TYPE_INTEGER; + arg[2].integer.value = HISI_PCIE_CORE_PORT_ID(port_id); + + arg_list.count = 3; + arg_list.pointer = arg; + + s = acpi_evaluate_integer(handle, "RST", &arg_list, &data); + if (ACPI_FAILURE(s)) { + dev_err(dev, "No RST method\n"); + return -EIO; + } + + if (data) { + dev_err(dev, "Failed to Reset\n"); + return -EIO; + } + + return 0; +} + +static int hisi_pcie_port_do_recovery(struct platform_device *dev, + u32 chip_id, u32 port_id) +{ + acpi_status s; + struct device *device = &dev->dev; + acpi_handle root_handle = ACPI_HANDLE(device); + struct acpi_pci_root *pci_root; + struct pci_bus *root_bus; + struct pci_dev *pdev; + u32 domain, busnr, devfn; + + s = acpi_get_parent(root_handle, &root_handle); + if (ACPI_FAILURE(s)) + return -ENODEV; + pci_root = acpi_pci_find_root(root_handle); + if (!pci_root) + return -ENODEV; + root_bus = pci_root->bus; + domain = pci_root->segment; + + busnr = root_bus->number; + devfn = PCI_DEVFN(port_id, 0); + pdev = pci_get_domain_bus_and_slot(domain, busnr, devfn); + if (!pdev) { + dev_info(device, "Fail to get root port %04x:%02x:%02x.%d device\n", + domain, busnr, PCI_SLOT(devfn), PCI_FUNC(devfn)); + return -ENODEV; + } + + pci_stop_and_remove_bus_device_locked(pdev); + pci_dev_put(pdev); + + if (hisi_pcie_port_reset(dev, chip_id, port_id)) + return -EIO; + + /* + * The initialization time of subordinate devices after + * hot reset is no more than 1s, which is required by + * the PCI spec v5.0 sec 6.6.1. The time will shorten + * if Readiness Notifications mechanisms are used. But + * wait 1s here to adapt any conditions. + */ + ssleep(1UL); + + /* add root port and downstream devices */ + pci_lock_rescan_remove(); + pci_rescan_bus(root_bus); + pci_unlock_rescan_remove(); + + return 0; +} + +static void hisi_pcie_handle_error(struct platform_device *pdev, + const struct hisi_pcie_error_data *edata) +{ + struct device *dev = &pdev->dev; + int idx, rc; + const unsigned long valid_bits[] = {BITMAP_FROM_U64(edata->val_bits)}; + + if (edata->val_bits == 0) { + dev_warn(dev, "%s: no valid error information\n", __func__); + return; + } + + dev_info(dev, "\nHISI : HIP : PCIe controller error\n"); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_SOC_ID) + dev_info(dev, "Table version = %d\n", edata->version); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_SOCKET_ID) + dev_info(dev, "Socket ID = %d\n", edata->socket_id); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_NIMBUS_ID) + dev_info(dev, "Nimbus ID = %d\n", edata->nimbus_id); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_SUB_MODULE_ID) + dev_info(dev, "Sub Module = %s\n", + hisi_pcie_get_string(hisi_pcie_sub_module, + ARRAY_SIZE(hisi_pcie_sub_module), + edata->sub_module_id)); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_CORE_ID) + dev_info(dev, "Core ID = core%d\n", edata->core_id); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_PORT_ID) + dev_info(dev, "Port ID = port%d\n", edata->port_id); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_ERR_SEVERITY) + dev_info(dev, "Error severity = %s\n", + hisi_pcie_get_string(hisi_pcie_error_sev, + ARRAY_SIZE(hisi_pcie_error_sev), + edata->err_severity)); + if (edata->val_bits & HISI_PCIE_LOCAL_VALID_ERR_TYPE) + dev_info(dev, "Error type = 0x%x\n", edata->err_type); + + dev_info(dev, "Reg Dump:\n"); + idx = HISI_PCIE_LOCAL_VALID_ERR_MISC; + for_each_set_bit_from(idx, valid_bits, + HISI_PCIE_LOCAL_VALID_ERR_MISC + HISI_PCIE_ERR_MISC_REGS) + dev_info(dev, "ERR_MISC_%d = 0x%x\n", idx - HISI_PCIE_LOCAL_VALID_ERR_MISC, + edata->err_misc[idx - HISI_PCIE_LOCAL_VALID_ERR_MISC]); + + if (edata->err_severity != HISI_PCIE_ERR_SEV_RECOVERABLE) + return; + + /* Recovery for the PCIe controller errors, try reset + * PCI port for the error recovery + */ + rc = hisi_pcie_port_do_recovery(pdev, edata->socket_id, + HISI_PCIE_PORT_ID(edata->core_id, edata->port_id)); + if (rc) + dev_info(dev, "fail to do hisi pcie port reset\n"); +} + +static int hisi_pcie_notify_error(struct notifier_block *nb, + unsigned long event, void *data) +{ + struct acpi_hest_generic_data *gdata = data; + const struct hisi_pcie_error_data *error_data = acpi_hest_get_payload(gdata); + struct hisi_pcie_error_private *priv; + struct device *dev; + struct platform_device *pdev; + guid_t err_sec_guid; + u8 socket; + + import_guid(&err_sec_guid, gdata->section_type); + if (!guid_equal(&err_sec_guid, &hisi_pcie_sec_guid)) + return NOTIFY_DONE; + + priv = container_of(nb, struct hisi_pcie_error_private, nb); + dev = priv->dev; + + if (device_property_read_u8(dev, "socket", &socket)) + return NOTIFY_DONE; + + if (error_data->socket_id != socket) + return NOTIFY_DONE; + + pdev = container_of(dev, struct platform_device, dev); + hisi_pcie_handle_error(pdev, error_data); + + return NOTIFY_OK; +} + +static int hisi_pcie_error_handler_probe(struct platform_device *pdev) +{ + struct hisi_pcie_error_private *priv; + int ret; + + priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->nb.notifier_call = hisi_pcie_notify_error; + priv->dev = &pdev->dev; + ret = ghes_register_vendor_record_notifier(&priv->nb); + if (ret) { + dev_err(&pdev->dev, + "Failed to register hisi pcie controller error handler with apei\n"); + return ret; + } + + platform_set_drvdata(pdev, priv); + + return 0; +} + +static int hisi_pcie_error_handler_remove(struct platform_device *pdev) +{ + struct hisi_pcie_error_private *priv = platform_get_drvdata(pdev); + + ghes_unregister_vendor_record_notifier(&priv->nb); + + return 0; +} + +static const struct acpi_device_id hisi_pcie_acpi_match[] = { + { "HISI0361", 0 }, + { } +}; + +static struct platform_driver hisi_pcie_error_handler_driver = { + .driver = { + .name = "hisi-pcie-error-handler", + .acpi_match_table = hisi_pcie_acpi_match, + }, + .probe = hisi_pcie_error_handler_probe, + .remove = hisi_pcie_error_handler_remove, +}; +module_platform_driver(hisi_pcie_error_handler_driver); + +MODULE_DESCRIPTION("HiSilicon HIP PCIe controller error handling driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-iproc-bcma.c b/drivers/pci/controller/pcie-iproc-bcma.c new file mode 100644 index 000000000..99a999004 --- /dev/null +++ b/drivers/pci/controller/pcie-iproc-bcma.c @@ -0,0 +1,97 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2015 Broadcom Corporation + * Copyright (C) 2015 Hauke Mehrtens <hauke@hauke-m.de> + */ + +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/phy/phy.h> +#include <linux/bcma/bcma.h> +#include <linux/ioport.h> + +#include "pcie-iproc.h" + + +/* NS: CLASS field is R/O, and set to wrong 0x200 value */ +static void bcma_pcie2_fixup_class(struct pci_dev *dev) +{ + dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x8011, bcma_pcie2_fixup_class); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x8012, bcma_pcie2_fixup_class); + +static int iproc_bcma_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin) +{ + struct iproc_pcie *pcie = dev->sysdata; + struct bcma_device *bdev = container_of(pcie->dev, struct bcma_device, dev); + + return bcma_core_irq(bdev, 5); +} + +static int iproc_bcma_pcie_probe(struct bcma_device *bdev) +{ + struct device *dev = &bdev->dev; + struct iproc_pcie *pcie; + struct pci_host_bridge *bridge; + int ret; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + + pcie->dev = dev; + + pcie->type = IPROC_PCIE_PAXB_BCMA; + pcie->base = bdev->io_addr; + if (!pcie->base) { + dev_err(dev, "no controller registers\n"); + return -ENOMEM; + } + + pcie->base_addr = bdev->addr; + + pcie->mem.start = bdev->addr_s[0]; + pcie->mem.end = bdev->addr_s[0] + SZ_128M - 1; + pcie->mem.name = "PCIe MEM space"; + pcie->mem.flags = IORESOURCE_MEM; + pci_add_resource(&bridge->windows, &pcie->mem); + ret = devm_request_pci_bus_resources(dev, &bridge->windows); + if (ret) + return ret; + + pcie->map_irq = iproc_bcma_pcie_map_irq; + + bcma_set_drvdata(bdev, pcie); + + return iproc_pcie_setup(pcie, &bridge->windows); +} + +static void iproc_bcma_pcie_remove(struct bcma_device *bdev) +{ + struct iproc_pcie *pcie = bcma_get_drvdata(bdev); + + iproc_pcie_remove(pcie); +} + +static const struct bcma_device_id iproc_bcma_pcie_table[] = { + BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_NS_PCIEG2, BCMA_ANY_REV, BCMA_ANY_CLASS), + {}, +}; +MODULE_DEVICE_TABLE(bcma, iproc_bcma_pcie_table); + +static struct bcma_driver iproc_bcma_pcie_driver = { + .name = KBUILD_MODNAME, + .id_table = iproc_bcma_pcie_table, + .probe = iproc_bcma_pcie_probe, + .remove = iproc_bcma_pcie_remove, +}; +module_bcma_driver(iproc_bcma_pcie_driver); + +MODULE_AUTHOR("Hauke Mehrtens"); +MODULE_DESCRIPTION("Broadcom iProc PCIe BCMA driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-iproc-msi.c b/drivers/pci/controller/pcie-iproc-msi.c new file mode 100644 index 000000000..fee036b07 --- /dev/null +++ b/drivers/pci/controller/pcie-iproc-msi.c @@ -0,0 +1,682 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2015 Broadcom Corporation + */ + +#include <linux/interrupt.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/msi.h> +#include <linux/of_irq.h> +#include <linux/of_pci.h> +#include <linux/pci.h> + +#include "pcie-iproc.h" + +#define IPROC_MSI_INTR_EN_SHIFT 11 +#define IPROC_MSI_INTR_EN BIT(IPROC_MSI_INTR_EN_SHIFT) +#define IPROC_MSI_INT_N_EVENT_SHIFT 1 +#define IPROC_MSI_INT_N_EVENT BIT(IPROC_MSI_INT_N_EVENT_SHIFT) +#define IPROC_MSI_EQ_EN_SHIFT 0 +#define IPROC_MSI_EQ_EN BIT(IPROC_MSI_EQ_EN_SHIFT) + +#define IPROC_MSI_EQ_MASK 0x3f + +/* Max number of GIC interrupts */ +#define NR_HW_IRQS 6 + +/* Number of entries in each event queue */ +#define EQ_LEN 64 + +/* Size of each event queue memory region */ +#define EQ_MEM_REGION_SIZE SZ_4K + +/* Size of each MSI address region */ +#define MSI_MEM_REGION_SIZE SZ_4K + +enum iproc_msi_reg { + IPROC_MSI_EQ_PAGE = 0, + IPROC_MSI_EQ_PAGE_UPPER, + IPROC_MSI_PAGE, + IPROC_MSI_PAGE_UPPER, + IPROC_MSI_CTRL, + IPROC_MSI_EQ_HEAD, + IPROC_MSI_EQ_TAIL, + IPROC_MSI_INTS_EN, + IPROC_MSI_REG_SIZE, +}; + +struct iproc_msi; + +/** + * struct iproc_msi_grp - iProc MSI group + * + * One MSI group is allocated per GIC interrupt, serviced by one iProc MSI + * event queue. + * + * @msi: pointer to iProc MSI data + * @gic_irq: GIC interrupt + * @eq: Event queue number + */ +struct iproc_msi_grp { + struct iproc_msi *msi; + int gic_irq; + unsigned int eq; +}; + +/** + * struct iproc_msi - iProc event queue based MSI + * + * Only meant to be used on platforms without MSI support integrated into the + * GIC. + * + * @pcie: pointer to iProc PCIe data + * @reg_offsets: MSI register offsets + * @grps: MSI groups + * @nr_irqs: number of total interrupts connected to GIC + * @nr_cpus: number of toal CPUs + * @has_inten_reg: indicates the MSI interrupt enable register needs to be + * set explicitly (required for some legacy platforms) + * @bitmap: MSI vector bitmap + * @bitmap_lock: lock to protect access to the MSI bitmap + * @nr_msi_vecs: total number of MSI vectors + * @inner_domain: inner IRQ domain + * @msi_domain: MSI IRQ domain + * @nr_eq_region: required number of 4K aligned memory region for MSI event + * queues + * @nr_msi_region: required number of 4K aligned address region for MSI posted + * writes + * @eq_cpu: pointer to allocated memory region for MSI event queues + * @eq_dma: DMA address of MSI event queues + * @msi_addr: MSI address + */ +struct iproc_msi { + struct iproc_pcie *pcie; + const u16 (*reg_offsets)[IPROC_MSI_REG_SIZE]; + struct iproc_msi_grp *grps; + int nr_irqs; + int nr_cpus; + bool has_inten_reg; + unsigned long *bitmap; + struct mutex bitmap_lock; + unsigned int nr_msi_vecs; + struct irq_domain *inner_domain; + struct irq_domain *msi_domain; + unsigned int nr_eq_region; + unsigned int nr_msi_region; + void *eq_cpu; + dma_addr_t eq_dma; + phys_addr_t msi_addr; +}; + +static const u16 iproc_msi_reg_paxb[NR_HW_IRQS][IPROC_MSI_REG_SIZE] = { + { 0x200, 0x2c0, 0x204, 0x2c4, 0x210, 0x250, 0x254, 0x208 }, + { 0x200, 0x2c0, 0x204, 0x2c4, 0x214, 0x258, 0x25c, 0x208 }, + { 0x200, 0x2c0, 0x204, 0x2c4, 0x218, 0x260, 0x264, 0x208 }, + { 0x200, 0x2c0, 0x204, 0x2c4, 0x21c, 0x268, 0x26c, 0x208 }, + { 0x200, 0x2c0, 0x204, 0x2c4, 0x220, 0x270, 0x274, 0x208 }, + { 0x200, 0x2c0, 0x204, 0x2c4, 0x224, 0x278, 0x27c, 0x208 }, +}; + +static const u16 iproc_msi_reg_paxc[NR_HW_IRQS][IPROC_MSI_REG_SIZE] = { + { 0xc00, 0xc04, 0xc08, 0xc0c, 0xc40, 0xc50, 0xc60 }, + { 0xc10, 0xc14, 0xc18, 0xc1c, 0xc44, 0xc54, 0xc64 }, + { 0xc20, 0xc24, 0xc28, 0xc2c, 0xc48, 0xc58, 0xc68 }, + { 0xc30, 0xc34, 0xc38, 0xc3c, 0xc4c, 0xc5c, 0xc6c }, +}; + +static inline u32 iproc_msi_read_reg(struct iproc_msi *msi, + enum iproc_msi_reg reg, + unsigned int eq) +{ + struct iproc_pcie *pcie = msi->pcie; + + return readl_relaxed(pcie->base + msi->reg_offsets[eq][reg]); +} + +static inline void iproc_msi_write_reg(struct iproc_msi *msi, + enum iproc_msi_reg reg, + int eq, u32 val) +{ + struct iproc_pcie *pcie = msi->pcie; + + writel_relaxed(val, pcie->base + msi->reg_offsets[eq][reg]); +} + +static inline u32 hwirq_to_group(struct iproc_msi *msi, unsigned long hwirq) +{ + return (hwirq % msi->nr_irqs); +} + +static inline unsigned int iproc_msi_addr_offset(struct iproc_msi *msi, + unsigned long hwirq) +{ + if (msi->nr_msi_region > 1) + return hwirq_to_group(msi, hwirq) * MSI_MEM_REGION_SIZE; + else + return hwirq_to_group(msi, hwirq) * sizeof(u32); +} + +static inline unsigned int iproc_msi_eq_offset(struct iproc_msi *msi, u32 eq) +{ + if (msi->nr_eq_region > 1) + return eq * EQ_MEM_REGION_SIZE; + else + return eq * EQ_LEN * sizeof(u32); +} + +static struct irq_chip iproc_msi_irq_chip = { + .name = "iProc-MSI", +}; + +static struct msi_domain_info iproc_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX, + .chip = &iproc_msi_irq_chip, +}; + +/* + * In iProc PCIe core, each MSI group is serviced by a GIC interrupt and a + * dedicated event queue. Each MSI group can support up to 64 MSI vectors. + * + * The number of MSI groups varies between different iProc SoCs. The total + * number of CPU cores also varies. To support MSI IRQ affinity, we + * distribute GIC interrupts across all available CPUs. MSI vector is moved + * from one GIC interrupt to another to steer to the target CPU. + * + * Assuming: + * - the number of MSI groups is M + * - the number of CPU cores is N + * - M is always a multiple of N + * + * Total number of raw MSI vectors = M * 64 + * Total number of supported MSI vectors = (M * 64) / N + */ +static inline int hwirq_to_cpu(struct iproc_msi *msi, unsigned long hwirq) +{ + return (hwirq % msi->nr_cpus); +} + +static inline unsigned long hwirq_to_canonical_hwirq(struct iproc_msi *msi, + unsigned long hwirq) +{ + return (hwirq - hwirq_to_cpu(msi, hwirq)); +} + +static int iproc_msi_irq_set_affinity(struct irq_data *data, + const struct cpumask *mask, bool force) +{ + struct iproc_msi *msi = irq_data_get_irq_chip_data(data); + int target_cpu = cpumask_first(mask); + int curr_cpu; + int ret; + + curr_cpu = hwirq_to_cpu(msi, data->hwirq); + if (curr_cpu == target_cpu) + ret = IRQ_SET_MASK_OK_DONE; + else { + /* steer MSI to the target CPU */ + data->hwirq = hwirq_to_canonical_hwirq(msi, data->hwirq) + target_cpu; + ret = IRQ_SET_MASK_OK; + } + + irq_data_update_effective_affinity(data, cpumask_of(target_cpu)); + + return ret; +} + +static void iproc_msi_irq_compose_msi_msg(struct irq_data *data, + struct msi_msg *msg) +{ + struct iproc_msi *msi = irq_data_get_irq_chip_data(data); + dma_addr_t addr; + + addr = msi->msi_addr + iproc_msi_addr_offset(msi, data->hwirq); + msg->address_lo = lower_32_bits(addr); + msg->address_hi = upper_32_bits(addr); + msg->data = data->hwirq << 5; +} + +static struct irq_chip iproc_msi_bottom_irq_chip = { + .name = "MSI", + .irq_set_affinity = iproc_msi_irq_set_affinity, + .irq_compose_msi_msg = iproc_msi_irq_compose_msi_msg, +}; + +static int iproc_msi_irq_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *args) +{ + struct iproc_msi *msi = domain->host_data; + int hwirq, i; + + if (msi->nr_cpus > 1 && nr_irqs > 1) + return -EINVAL; + + mutex_lock(&msi->bitmap_lock); + + /* + * Allocate 'nr_irqs' multiplied by 'nr_cpus' number of MSI vectors + * each time + */ + hwirq = bitmap_find_free_region(msi->bitmap, msi->nr_msi_vecs, + order_base_2(msi->nr_cpus * nr_irqs)); + + mutex_unlock(&msi->bitmap_lock); + + if (hwirq < 0) + return -ENOSPC; + + for (i = 0; i < nr_irqs; i++) { + irq_domain_set_info(domain, virq + i, hwirq + i, + &iproc_msi_bottom_irq_chip, + domain->host_data, handle_simple_irq, + NULL, NULL); + } + + return 0; +} + +static void iproc_msi_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *data = irq_domain_get_irq_data(domain, virq); + struct iproc_msi *msi = irq_data_get_irq_chip_data(data); + unsigned int hwirq; + + mutex_lock(&msi->bitmap_lock); + + hwirq = hwirq_to_canonical_hwirq(msi, data->hwirq); + bitmap_release_region(msi->bitmap, hwirq, + order_base_2(msi->nr_cpus * nr_irqs)); + + mutex_unlock(&msi->bitmap_lock); + + irq_domain_free_irqs_parent(domain, virq, nr_irqs); +} + +static const struct irq_domain_ops msi_domain_ops = { + .alloc = iproc_msi_irq_domain_alloc, + .free = iproc_msi_irq_domain_free, +}; + +static inline u32 decode_msi_hwirq(struct iproc_msi *msi, u32 eq, u32 head) +{ + u32 __iomem *msg; + u32 hwirq; + unsigned int offs; + + offs = iproc_msi_eq_offset(msi, eq) + head * sizeof(u32); + msg = (u32 __iomem *)(msi->eq_cpu + offs); + hwirq = readl(msg); + hwirq = (hwirq >> 5) + (hwirq & 0x1f); + + /* + * Since we have multiple hwirq mapped to a single MSI vector, + * now we need to derive the hwirq at CPU0. It can then be used to + * mapped back to virq. + */ + return hwirq_to_canonical_hwirq(msi, hwirq); +} + +static void iproc_msi_handler(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct iproc_msi_grp *grp; + struct iproc_msi *msi; + u32 eq, head, tail, nr_events; + unsigned long hwirq; + + chained_irq_enter(chip, desc); + + grp = irq_desc_get_handler_data(desc); + msi = grp->msi; + eq = grp->eq; + + /* + * iProc MSI event queue is tracked by head and tail pointers. Head + * pointer indicates the next entry (MSI data) to be consumed by SW in + * the queue and needs to be updated by SW. iProc MSI core uses the + * tail pointer as the next data insertion point. + * + * Entries between head and tail pointers contain valid MSI data. MSI + * data is guaranteed to be in the event queue memory before the tail + * pointer is updated by the iProc MSI core. + */ + head = iproc_msi_read_reg(msi, IPROC_MSI_EQ_HEAD, + eq) & IPROC_MSI_EQ_MASK; + do { + tail = iproc_msi_read_reg(msi, IPROC_MSI_EQ_TAIL, + eq) & IPROC_MSI_EQ_MASK; + + /* + * Figure out total number of events (MSI data) to be + * processed. + */ + nr_events = (tail < head) ? + (EQ_LEN - (head - tail)) : (tail - head); + if (!nr_events) + break; + + /* process all outstanding events */ + while (nr_events--) { + hwirq = decode_msi_hwirq(msi, eq, head); + generic_handle_domain_irq(msi->inner_domain, hwirq); + + head++; + head %= EQ_LEN; + } + + /* + * Now all outstanding events have been processed. Update the + * head pointer. + */ + iproc_msi_write_reg(msi, IPROC_MSI_EQ_HEAD, eq, head); + + /* + * Now go read the tail pointer again to see if there are new + * outstanding events that came in during the above window. + */ + } while (true); + + chained_irq_exit(chip, desc); +} + +static void iproc_msi_enable(struct iproc_msi *msi) +{ + int i, eq; + u32 val; + + /* Program memory region for each event queue */ + for (i = 0; i < msi->nr_eq_region; i++) { + dma_addr_t addr = msi->eq_dma + (i * EQ_MEM_REGION_SIZE); + + iproc_msi_write_reg(msi, IPROC_MSI_EQ_PAGE, i, + lower_32_bits(addr)); + iproc_msi_write_reg(msi, IPROC_MSI_EQ_PAGE_UPPER, i, + upper_32_bits(addr)); + } + + /* Program address region for MSI posted writes */ + for (i = 0; i < msi->nr_msi_region; i++) { + phys_addr_t addr = msi->msi_addr + (i * MSI_MEM_REGION_SIZE); + + iproc_msi_write_reg(msi, IPROC_MSI_PAGE, i, + lower_32_bits(addr)); + iproc_msi_write_reg(msi, IPROC_MSI_PAGE_UPPER, i, + upper_32_bits(addr)); + } + + for (eq = 0; eq < msi->nr_irqs; eq++) { + /* Enable MSI event queue */ + val = IPROC_MSI_INTR_EN | IPROC_MSI_INT_N_EVENT | + IPROC_MSI_EQ_EN; + iproc_msi_write_reg(msi, IPROC_MSI_CTRL, eq, val); + + /* + * Some legacy platforms require the MSI interrupt enable + * register to be set explicitly. + */ + if (msi->has_inten_reg) { + val = iproc_msi_read_reg(msi, IPROC_MSI_INTS_EN, eq); + val |= BIT(eq); + iproc_msi_write_reg(msi, IPROC_MSI_INTS_EN, eq, val); + } + } +} + +static void iproc_msi_disable(struct iproc_msi *msi) +{ + u32 eq, val; + + for (eq = 0; eq < msi->nr_irqs; eq++) { + if (msi->has_inten_reg) { + val = iproc_msi_read_reg(msi, IPROC_MSI_INTS_EN, eq); + val &= ~BIT(eq); + iproc_msi_write_reg(msi, IPROC_MSI_INTS_EN, eq, val); + } + + val = iproc_msi_read_reg(msi, IPROC_MSI_CTRL, eq); + val &= ~(IPROC_MSI_INTR_EN | IPROC_MSI_INT_N_EVENT | + IPROC_MSI_EQ_EN); + iproc_msi_write_reg(msi, IPROC_MSI_CTRL, eq, val); + } +} + +static int iproc_msi_alloc_domains(struct device_node *node, + struct iproc_msi *msi) +{ + msi->inner_domain = irq_domain_add_linear(NULL, msi->nr_msi_vecs, + &msi_domain_ops, msi); + if (!msi->inner_domain) + return -ENOMEM; + + msi->msi_domain = pci_msi_create_irq_domain(of_node_to_fwnode(node), + &iproc_msi_domain_info, + msi->inner_domain); + if (!msi->msi_domain) { + irq_domain_remove(msi->inner_domain); + return -ENOMEM; + } + + return 0; +} + +static void iproc_msi_free_domains(struct iproc_msi *msi) +{ + if (msi->msi_domain) + irq_domain_remove(msi->msi_domain); + + if (msi->inner_domain) + irq_domain_remove(msi->inner_domain); +} + +static void iproc_msi_irq_free(struct iproc_msi *msi, unsigned int cpu) +{ + int i; + + for (i = cpu; i < msi->nr_irqs; i += msi->nr_cpus) { + irq_set_chained_handler_and_data(msi->grps[i].gic_irq, + NULL, NULL); + } +} + +static int iproc_msi_irq_setup(struct iproc_msi *msi, unsigned int cpu) +{ + int i, ret; + cpumask_var_t mask; + struct iproc_pcie *pcie = msi->pcie; + + for (i = cpu; i < msi->nr_irqs; i += msi->nr_cpus) { + irq_set_chained_handler_and_data(msi->grps[i].gic_irq, + iproc_msi_handler, + &msi->grps[i]); + /* Dedicate GIC interrupt to each CPU core */ + if (alloc_cpumask_var(&mask, GFP_KERNEL)) { + cpumask_clear(mask); + cpumask_set_cpu(cpu, mask); + ret = irq_set_affinity(msi->grps[i].gic_irq, mask); + if (ret) + dev_err(pcie->dev, + "failed to set affinity for IRQ%d\n", + msi->grps[i].gic_irq); + free_cpumask_var(mask); + } else { + dev_err(pcie->dev, "failed to alloc CPU mask\n"); + ret = -EINVAL; + } + + if (ret) { + /* Free all configured/unconfigured IRQs */ + iproc_msi_irq_free(msi, cpu); + return ret; + } + } + + return 0; +} + +int iproc_msi_init(struct iproc_pcie *pcie, struct device_node *node) +{ + struct iproc_msi *msi; + int i, ret; + unsigned int cpu; + + if (!of_device_is_compatible(node, "brcm,iproc-msi")) + return -ENODEV; + + if (!of_find_property(node, "msi-controller", NULL)) + return -ENODEV; + + if (pcie->msi) + return -EBUSY; + + msi = devm_kzalloc(pcie->dev, sizeof(*msi), GFP_KERNEL); + if (!msi) + return -ENOMEM; + + msi->pcie = pcie; + pcie->msi = msi; + msi->msi_addr = pcie->base_addr; + mutex_init(&msi->bitmap_lock); + msi->nr_cpus = num_possible_cpus(); + + if (msi->nr_cpus == 1) + iproc_msi_domain_info.flags |= MSI_FLAG_MULTI_PCI_MSI; + + msi->nr_irqs = of_irq_count(node); + if (!msi->nr_irqs) { + dev_err(pcie->dev, "found no MSI GIC interrupt\n"); + return -ENODEV; + } + + if (msi->nr_irqs > NR_HW_IRQS) { + dev_warn(pcie->dev, "too many MSI GIC interrupts defined %d\n", + msi->nr_irqs); + msi->nr_irqs = NR_HW_IRQS; + } + + if (msi->nr_irqs < msi->nr_cpus) { + dev_err(pcie->dev, + "not enough GIC interrupts for MSI affinity\n"); + return -EINVAL; + } + + if (msi->nr_irqs % msi->nr_cpus != 0) { + msi->nr_irqs -= msi->nr_irqs % msi->nr_cpus; + dev_warn(pcie->dev, "Reducing number of interrupts to %d\n", + msi->nr_irqs); + } + + switch (pcie->type) { + case IPROC_PCIE_PAXB_BCMA: + case IPROC_PCIE_PAXB: + msi->reg_offsets = iproc_msi_reg_paxb; + msi->nr_eq_region = 1; + msi->nr_msi_region = 1; + break; + case IPROC_PCIE_PAXC: + msi->reg_offsets = iproc_msi_reg_paxc; + msi->nr_eq_region = msi->nr_irqs; + msi->nr_msi_region = msi->nr_irqs; + break; + default: + dev_err(pcie->dev, "incompatible iProc PCIe interface\n"); + return -EINVAL; + } + + if (of_find_property(node, "brcm,pcie-msi-inten", NULL)) + msi->has_inten_reg = true; + + msi->nr_msi_vecs = msi->nr_irqs * EQ_LEN; + msi->bitmap = devm_bitmap_zalloc(pcie->dev, msi->nr_msi_vecs, + GFP_KERNEL); + if (!msi->bitmap) + return -ENOMEM; + + msi->grps = devm_kcalloc(pcie->dev, msi->nr_irqs, sizeof(*msi->grps), + GFP_KERNEL); + if (!msi->grps) + return -ENOMEM; + + for (i = 0; i < msi->nr_irqs; i++) { + unsigned int irq = irq_of_parse_and_map(node, i); + + if (!irq) { + dev_err(pcie->dev, "unable to parse/map interrupt\n"); + ret = -ENODEV; + goto free_irqs; + } + msi->grps[i].gic_irq = irq; + msi->grps[i].msi = msi; + msi->grps[i].eq = i; + } + + /* Reserve memory for event queue and make sure memories are zeroed */ + msi->eq_cpu = dma_alloc_coherent(pcie->dev, + msi->nr_eq_region * EQ_MEM_REGION_SIZE, + &msi->eq_dma, GFP_KERNEL); + if (!msi->eq_cpu) { + ret = -ENOMEM; + goto free_irqs; + } + + ret = iproc_msi_alloc_domains(node, msi); + if (ret) { + dev_err(pcie->dev, "failed to create MSI domains\n"); + goto free_eq_dma; + } + + for_each_online_cpu(cpu) { + ret = iproc_msi_irq_setup(msi, cpu); + if (ret) + goto free_msi_irq; + } + + iproc_msi_enable(msi); + + return 0; + +free_msi_irq: + for_each_online_cpu(cpu) + iproc_msi_irq_free(msi, cpu); + iproc_msi_free_domains(msi); + +free_eq_dma: + dma_free_coherent(pcie->dev, msi->nr_eq_region * EQ_MEM_REGION_SIZE, + msi->eq_cpu, msi->eq_dma); + +free_irqs: + for (i = 0; i < msi->nr_irqs; i++) { + if (msi->grps[i].gic_irq) + irq_dispose_mapping(msi->grps[i].gic_irq); + } + pcie->msi = NULL; + return ret; +} +EXPORT_SYMBOL(iproc_msi_init); + +void iproc_msi_exit(struct iproc_pcie *pcie) +{ + struct iproc_msi *msi = pcie->msi; + unsigned int i, cpu; + + if (!msi) + return; + + iproc_msi_disable(msi); + + for_each_online_cpu(cpu) + iproc_msi_irq_free(msi, cpu); + + iproc_msi_free_domains(msi); + + dma_free_coherent(pcie->dev, msi->nr_eq_region * EQ_MEM_REGION_SIZE, + msi->eq_cpu, msi->eq_dma); + + for (i = 0; i < msi->nr_irqs; i++) { + if (msi->grps[i].gic_irq) + irq_dispose_mapping(msi->grps[i].gic_irq); + } +} +EXPORT_SYMBOL(iproc_msi_exit); diff --git a/drivers/pci/controller/pcie-iproc-platform.c b/drivers/pci/controller/pcie-iproc-platform.c new file mode 100644 index 000000000..538115246 --- /dev/null +++ b/drivers/pci/controller/pcie-iproc-platform.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2015 Broadcom Corporation + */ + +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/clk.h> +#include <linux/module.h> +#include <linux/slab.h> +#include <linux/interrupt.h> +#include <linux/platform_device.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_irq.h> +#include <linux/of_platform.h> +#include <linux/phy/phy.h> + +#include "../pci.h" +#include "pcie-iproc.h" + +static const struct of_device_id iproc_pcie_of_match_table[] = { + { + .compatible = "brcm,iproc-pcie", + .data = (int *)IPROC_PCIE_PAXB, + }, { + .compatible = "brcm,iproc-pcie-paxb-v2", + .data = (int *)IPROC_PCIE_PAXB_V2, + }, { + .compatible = "brcm,iproc-pcie-paxc", + .data = (int *)IPROC_PCIE_PAXC, + }, { + .compatible = "brcm,iproc-pcie-paxc-v2", + .data = (int *)IPROC_PCIE_PAXC_V2, + }, + { /* sentinel */ } +}; +MODULE_DEVICE_TABLE(of, iproc_pcie_of_match_table); + +static int iproc_pltfm_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct iproc_pcie *pcie; + struct device_node *np = dev->of_node; + struct resource reg; + struct pci_host_bridge *bridge; + int ret; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + + pcie->dev = dev; + pcie->type = (enum iproc_pcie_type) of_device_get_match_data(dev); + + ret = of_address_to_resource(np, 0, ®); + if (ret < 0) { + dev_err(dev, "unable to obtain controller resources\n"); + return ret; + } + + pcie->base = devm_pci_remap_cfgspace(dev, reg.start, + resource_size(®)); + if (!pcie->base) { + dev_err(dev, "unable to map controller registers\n"); + return -ENOMEM; + } + pcie->base_addr = reg.start; + + if (of_property_read_bool(np, "brcm,pcie-ob")) { + u32 val; + + ret = of_property_read_u32(np, "brcm,pcie-ob-axi-offset", + &val); + if (ret) { + dev_err(dev, + "missing brcm,pcie-ob-axi-offset property\n"); + return ret; + } + pcie->ob.axi_offset = val; + pcie->need_ob_cfg = true; + } + + /* + * DT nodes are not used by all platforms that use the iProc PCIe + * core driver. For platforms that require explicit inbound mapping + * configuration, "dma-ranges" would have been present in DT + */ + pcie->need_ib_cfg = of_property_read_bool(np, "dma-ranges"); + + /* PHY use is optional */ + pcie->phy = devm_phy_optional_get(dev, "pcie-phy"); + if (IS_ERR(pcie->phy)) + return PTR_ERR(pcie->phy); + + /* PAXC doesn't support legacy IRQs, skip mapping */ + switch (pcie->type) { + case IPROC_PCIE_PAXC: + case IPROC_PCIE_PAXC_V2: + pcie->map_irq = NULL; + break; + default: + break; + } + + ret = iproc_pcie_setup(pcie, &bridge->windows); + if (ret) { + dev_err(dev, "PCIe controller setup failed\n"); + return ret; + } + + platform_set_drvdata(pdev, pcie); + return 0; +} + +static int iproc_pltfm_pcie_remove(struct platform_device *pdev) +{ + struct iproc_pcie *pcie = platform_get_drvdata(pdev); + + return iproc_pcie_remove(pcie); +} + +static void iproc_pltfm_pcie_shutdown(struct platform_device *pdev) +{ + struct iproc_pcie *pcie = platform_get_drvdata(pdev); + + iproc_pcie_shutdown(pcie); +} + +static struct platform_driver iproc_pltfm_pcie_driver = { + .driver = { + .name = "iproc-pcie", + .of_match_table = of_match_ptr(iproc_pcie_of_match_table), + }, + .probe = iproc_pltfm_pcie_probe, + .remove = iproc_pltfm_pcie_remove, + .shutdown = iproc_pltfm_pcie_shutdown, +}; +module_platform_driver(iproc_pltfm_pcie_driver); + +MODULE_AUTHOR("Ray Jui <rjui@broadcom.com>"); +MODULE_DESCRIPTION("Broadcom iPROC PCIe platform driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c new file mode 100644 index 000000000..2519201b0 --- /dev/null +++ b/drivers/pci/controller/pcie-iproc.c @@ -0,0 +1,1601 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (C) 2014 Hauke Mehrtens <hauke@hauke-m.de> + * Copyright (C) 2015 Broadcom Corporation + */ + +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/msi.h> +#include <linux/clk.h> +#include <linux/module.h> +#include <linux/mbus.h> +#include <linux/slab.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/irqchip/arm-gic-v3.h> +#include <linux/platform_device.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_irq.h> +#include <linux/of_platform.h> +#include <linux/phy/phy.h> + +#include "pcie-iproc.h" + +#define EP_PERST_SOURCE_SELECT_SHIFT 2 +#define EP_PERST_SOURCE_SELECT BIT(EP_PERST_SOURCE_SELECT_SHIFT) +#define EP_MODE_SURVIVE_PERST_SHIFT 1 +#define EP_MODE_SURVIVE_PERST BIT(EP_MODE_SURVIVE_PERST_SHIFT) +#define RC_PCIE_RST_OUTPUT_SHIFT 0 +#define RC_PCIE_RST_OUTPUT BIT(RC_PCIE_RST_OUTPUT_SHIFT) +#define PAXC_RESET_MASK 0x7f + +#define GIC_V3_CFG_SHIFT 0 +#define GIC_V3_CFG BIT(GIC_V3_CFG_SHIFT) + +#define MSI_ENABLE_CFG_SHIFT 0 +#define MSI_ENABLE_CFG BIT(MSI_ENABLE_CFG_SHIFT) + +#define CFG_IND_ADDR_MASK 0x00001ffc + +#define CFG_ADDR_REG_NUM_MASK 0x00000ffc +#define CFG_ADDR_CFG_TYPE_1 1 + +#define SYS_RC_INTX_MASK 0xf + +#define PCIE_PHYLINKUP_SHIFT 3 +#define PCIE_PHYLINKUP BIT(PCIE_PHYLINKUP_SHIFT) +#define PCIE_DL_ACTIVE_SHIFT 2 +#define PCIE_DL_ACTIVE BIT(PCIE_DL_ACTIVE_SHIFT) + +#define APB_ERR_EN_SHIFT 0 +#define APB_ERR_EN BIT(APB_ERR_EN_SHIFT) + +#define CFG_RD_SUCCESS 0 +#define CFG_RD_UR 1 +#define CFG_RD_CRS 2 +#define CFG_RD_CA 3 +#define CFG_RETRY_STATUS 0xffff0001 +#define CFG_RETRY_STATUS_TIMEOUT_US 500000 /* 500 milliseconds */ + +/* derive the enum index of the outbound/inbound mapping registers */ +#define MAP_REG(base_reg, index) ((base_reg) + (index) * 2) + +/* + * Maximum number of outbound mapping window sizes that can be supported by any + * OARR/OMAP mapping pair + */ +#define MAX_NUM_OB_WINDOW_SIZES 4 + +#define OARR_VALID_SHIFT 0 +#define OARR_VALID BIT(OARR_VALID_SHIFT) +#define OARR_SIZE_CFG_SHIFT 1 + +/* + * Maximum number of inbound mapping region sizes that can be supported by an + * IARR + */ +#define MAX_NUM_IB_REGION_SIZES 9 + +#define IMAP_VALID_SHIFT 0 +#define IMAP_VALID BIT(IMAP_VALID_SHIFT) + +#define IPROC_PCI_PM_CAP 0x48 +#define IPROC_PCI_PM_CAP_MASK 0xffff +#define IPROC_PCI_EXP_CAP 0xac + +#define IPROC_PCIE_REG_INVALID 0xffff + +/** + * struct iproc_pcie_ob_map - iProc PCIe outbound mapping controller-specific + * parameters + * @window_sizes: list of supported outbound mapping window sizes in MB + * @nr_sizes: number of supported outbound mapping window sizes + */ +struct iproc_pcie_ob_map { + resource_size_t window_sizes[MAX_NUM_OB_WINDOW_SIZES]; + unsigned int nr_sizes; +}; + +static const struct iproc_pcie_ob_map paxb_ob_map[] = { + { + /* OARR0/OMAP0 */ + .window_sizes = { 128, 256 }, + .nr_sizes = 2, + }, + { + /* OARR1/OMAP1 */ + .window_sizes = { 128, 256 }, + .nr_sizes = 2, + }, +}; + +static const struct iproc_pcie_ob_map paxb_v2_ob_map[] = { + { + /* OARR0/OMAP0 */ + .window_sizes = { 128, 256 }, + .nr_sizes = 2, + }, + { + /* OARR1/OMAP1 */ + .window_sizes = { 128, 256 }, + .nr_sizes = 2, + }, + { + /* OARR2/OMAP2 */ + .window_sizes = { 128, 256, 512, 1024 }, + .nr_sizes = 4, + }, + { + /* OARR3/OMAP3 */ + .window_sizes = { 128, 256, 512, 1024 }, + .nr_sizes = 4, + }, +}; + +/** + * enum iproc_pcie_ib_map_type - iProc PCIe inbound mapping type + * @IPROC_PCIE_IB_MAP_MEM: DDR memory + * @IPROC_PCIE_IB_MAP_IO: device I/O memory + * @IPROC_PCIE_IB_MAP_INVALID: invalid or unused + */ +enum iproc_pcie_ib_map_type { + IPROC_PCIE_IB_MAP_MEM = 0, + IPROC_PCIE_IB_MAP_IO, + IPROC_PCIE_IB_MAP_INVALID +}; + +/** + * struct iproc_pcie_ib_map - iProc PCIe inbound mapping controller-specific + * parameters + * @type: inbound mapping region type + * @size_unit: inbound mapping region size unit, could be SZ_1K, SZ_1M, or + * SZ_1G + * @region_sizes: list of supported inbound mapping region sizes in KB, MB, or + * GB, depending on the size unit + * @nr_sizes: number of supported inbound mapping region sizes + * @nr_windows: number of supported inbound mapping windows for the region + * @imap_addr_offset: register offset between the upper and lower 32-bit + * IMAP address registers + * @imap_window_offset: register offset between each IMAP window + */ +struct iproc_pcie_ib_map { + enum iproc_pcie_ib_map_type type; + unsigned int size_unit; + resource_size_t region_sizes[MAX_NUM_IB_REGION_SIZES]; + unsigned int nr_sizes; + unsigned int nr_windows; + u16 imap_addr_offset; + u16 imap_window_offset; +}; + +static const struct iproc_pcie_ib_map paxb_v2_ib_map[] = { + { + /* IARR0/IMAP0 */ + .type = IPROC_PCIE_IB_MAP_IO, + .size_unit = SZ_1K, + .region_sizes = { 32 }, + .nr_sizes = 1, + .nr_windows = 8, + .imap_addr_offset = 0x40, + .imap_window_offset = 0x4, + }, + { + /* IARR1/IMAP1 */ + .type = IPROC_PCIE_IB_MAP_MEM, + .size_unit = SZ_1M, + .region_sizes = { 8 }, + .nr_sizes = 1, + .nr_windows = 8, + .imap_addr_offset = 0x4, + .imap_window_offset = 0x8, + + }, + { + /* IARR2/IMAP2 */ + .type = IPROC_PCIE_IB_MAP_MEM, + .size_unit = SZ_1M, + .region_sizes = { 64, 128, 256, 512, 1024, 2048, 4096, 8192, + 16384 }, + .nr_sizes = 9, + .nr_windows = 1, + .imap_addr_offset = 0x4, + .imap_window_offset = 0x8, + }, + { + /* IARR3/IMAP3 */ + .type = IPROC_PCIE_IB_MAP_MEM, + .size_unit = SZ_1G, + .region_sizes = { 1, 2, 4, 8, 16, 32 }, + .nr_sizes = 6, + .nr_windows = 8, + .imap_addr_offset = 0x4, + .imap_window_offset = 0x8, + }, + { + /* IARR4/IMAP4 */ + .type = IPROC_PCIE_IB_MAP_MEM, + .size_unit = SZ_1G, + .region_sizes = { 32, 64, 128, 256, 512 }, + .nr_sizes = 5, + .nr_windows = 8, + .imap_addr_offset = 0x4, + .imap_window_offset = 0x8, + }, +}; + +/* + * iProc PCIe host registers + */ +enum iproc_pcie_reg { + /* clock/reset signal control */ + IPROC_PCIE_CLK_CTRL = 0, + + /* + * To allow MSI to be steered to an external MSI controller (e.g., ARM + * GICv3 ITS) + */ + IPROC_PCIE_MSI_GIC_MODE, + + /* + * IPROC_PCIE_MSI_BASE_ADDR and IPROC_PCIE_MSI_WINDOW_SIZE define the + * window where the MSI posted writes are written, for the writes to be + * interpreted as MSI writes. + */ + IPROC_PCIE_MSI_BASE_ADDR, + IPROC_PCIE_MSI_WINDOW_SIZE, + + /* + * To hold the address of the register where the MSI writes are + * programmed. When ARM GICv3 ITS is used, this should be programmed + * with the address of the GITS_TRANSLATER register. + */ + IPROC_PCIE_MSI_ADDR_LO, + IPROC_PCIE_MSI_ADDR_HI, + + /* enable MSI */ + IPROC_PCIE_MSI_EN_CFG, + + /* allow access to root complex configuration space */ + IPROC_PCIE_CFG_IND_ADDR, + IPROC_PCIE_CFG_IND_DATA, + + /* allow access to device configuration space */ + IPROC_PCIE_CFG_ADDR, + IPROC_PCIE_CFG_DATA, + + /* enable INTx */ + IPROC_PCIE_INTX_EN, + + /* outbound address mapping */ + IPROC_PCIE_OARR0, + IPROC_PCIE_OMAP0, + IPROC_PCIE_OARR1, + IPROC_PCIE_OMAP1, + IPROC_PCIE_OARR2, + IPROC_PCIE_OMAP2, + IPROC_PCIE_OARR3, + IPROC_PCIE_OMAP3, + + /* inbound address mapping */ + IPROC_PCIE_IARR0, + IPROC_PCIE_IMAP0, + IPROC_PCIE_IARR1, + IPROC_PCIE_IMAP1, + IPROC_PCIE_IARR2, + IPROC_PCIE_IMAP2, + IPROC_PCIE_IARR3, + IPROC_PCIE_IMAP3, + IPROC_PCIE_IARR4, + IPROC_PCIE_IMAP4, + + /* config read status */ + IPROC_PCIE_CFG_RD_STATUS, + + /* link status */ + IPROC_PCIE_LINK_STATUS, + + /* enable APB error for unsupported requests */ + IPROC_PCIE_APB_ERR_EN, + + /* total number of core registers */ + IPROC_PCIE_MAX_NUM_REG, +}; + +/* iProc PCIe PAXB BCMA registers */ +static const u16 iproc_pcie_reg_paxb_bcma[IPROC_PCIE_MAX_NUM_REG] = { + [IPROC_PCIE_CLK_CTRL] = 0x000, + [IPROC_PCIE_CFG_IND_ADDR] = 0x120, + [IPROC_PCIE_CFG_IND_DATA] = 0x124, + [IPROC_PCIE_CFG_ADDR] = 0x1f8, + [IPROC_PCIE_CFG_DATA] = 0x1fc, + [IPROC_PCIE_INTX_EN] = 0x330, + [IPROC_PCIE_LINK_STATUS] = 0xf0c, +}; + +/* iProc PCIe PAXB registers */ +static const u16 iproc_pcie_reg_paxb[IPROC_PCIE_MAX_NUM_REG] = { + [IPROC_PCIE_CLK_CTRL] = 0x000, + [IPROC_PCIE_CFG_IND_ADDR] = 0x120, + [IPROC_PCIE_CFG_IND_DATA] = 0x124, + [IPROC_PCIE_CFG_ADDR] = 0x1f8, + [IPROC_PCIE_CFG_DATA] = 0x1fc, + [IPROC_PCIE_INTX_EN] = 0x330, + [IPROC_PCIE_OARR0] = 0xd20, + [IPROC_PCIE_OMAP0] = 0xd40, + [IPROC_PCIE_OARR1] = 0xd28, + [IPROC_PCIE_OMAP1] = 0xd48, + [IPROC_PCIE_LINK_STATUS] = 0xf0c, + [IPROC_PCIE_APB_ERR_EN] = 0xf40, +}; + +/* iProc PCIe PAXB v2 registers */ +static const u16 iproc_pcie_reg_paxb_v2[IPROC_PCIE_MAX_NUM_REG] = { + [IPROC_PCIE_CLK_CTRL] = 0x000, + [IPROC_PCIE_CFG_IND_ADDR] = 0x120, + [IPROC_PCIE_CFG_IND_DATA] = 0x124, + [IPROC_PCIE_CFG_ADDR] = 0x1f8, + [IPROC_PCIE_CFG_DATA] = 0x1fc, + [IPROC_PCIE_INTX_EN] = 0x330, + [IPROC_PCIE_OARR0] = 0xd20, + [IPROC_PCIE_OMAP0] = 0xd40, + [IPROC_PCIE_OARR1] = 0xd28, + [IPROC_PCIE_OMAP1] = 0xd48, + [IPROC_PCIE_OARR2] = 0xd60, + [IPROC_PCIE_OMAP2] = 0xd68, + [IPROC_PCIE_OARR3] = 0xdf0, + [IPROC_PCIE_OMAP3] = 0xdf8, + [IPROC_PCIE_IARR0] = 0xd00, + [IPROC_PCIE_IMAP0] = 0xc00, + [IPROC_PCIE_IARR1] = 0xd08, + [IPROC_PCIE_IMAP1] = 0xd70, + [IPROC_PCIE_IARR2] = 0xd10, + [IPROC_PCIE_IMAP2] = 0xcc0, + [IPROC_PCIE_IARR3] = 0xe00, + [IPROC_PCIE_IMAP3] = 0xe08, + [IPROC_PCIE_IARR4] = 0xe68, + [IPROC_PCIE_IMAP4] = 0xe70, + [IPROC_PCIE_CFG_RD_STATUS] = 0xee0, + [IPROC_PCIE_LINK_STATUS] = 0xf0c, + [IPROC_PCIE_APB_ERR_EN] = 0xf40, +}; + +/* iProc PCIe PAXC v1 registers */ +static const u16 iproc_pcie_reg_paxc[IPROC_PCIE_MAX_NUM_REG] = { + [IPROC_PCIE_CLK_CTRL] = 0x000, + [IPROC_PCIE_CFG_IND_ADDR] = 0x1f0, + [IPROC_PCIE_CFG_IND_DATA] = 0x1f4, + [IPROC_PCIE_CFG_ADDR] = 0x1f8, + [IPROC_PCIE_CFG_DATA] = 0x1fc, +}; + +/* iProc PCIe PAXC v2 registers */ +static const u16 iproc_pcie_reg_paxc_v2[IPROC_PCIE_MAX_NUM_REG] = { + [IPROC_PCIE_MSI_GIC_MODE] = 0x050, + [IPROC_PCIE_MSI_BASE_ADDR] = 0x074, + [IPROC_PCIE_MSI_WINDOW_SIZE] = 0x078, + [IPROC_PCIE_MSI_ADDR_LO] = 0x07c, + [IPROC_PCIE_MSI_ADDR_HI] = 0x080, + [IPROC_PCIE_MSI_EN_CFG] = 0x09c, + [IPROC_PCIE_CFG_IND_ADDR] = 0x1f0, + [IPROC_PCIE_CFG_IND_DATA] = 0x1f4, + [IPROC_PCIE_CFG_ADDR] = 0x1f8, + [IPROC_PCIE_CFG_DATA] = 0x1fc, +}; + +/* + * List of device IDs of controllers that have corrupted capability list that + * require SW fixup + */ +static const u16 iproc_pcie_corrupt_cap_did[] = { + 0x16cd, + 0x16f0, + 0xd802, + 0xd804 +}; + +static inline struct iproc_pcie *iproc_data(struct pci_bus *bus) +{ + struct iproc_pcie *pcie = bus->sysdata; + return pcie; +} + +static inline bool iproc_pcie_reg_is_invalid(u16 reg_offset) +{ + return !!(reg_offset == IPROC_PCIE_REG_INVALID); +} + +static inline u16 iproc_pcie_reg_offset(struct iproc_pcie *pcie, + enum iproc_pcie_reg reg) +{ + return pcie->reg_offsets[reg]; +} + +static inline u32 iproc_pcie_read_reg(struct iproc_pcie *pcie, + enum iproc_pcie_reg reg) +{ + u16 offset = iproc_pcie_reg_offset(pcie, reg); + + if (iproc_pcie_reg_is_invalid(offset)) + return 0; + + return readl(pcie->base + offset); +} + +static inline void iproc_pcie_write_reg(struct iproc_pcie *pcie, + enum iproc_pcie_reg reg, u32 val) +{ + u16 offset = iproc_pcie_reg_offset(pcie, reg); + + if (iproc_pcie_reg_is_invalid(offset)) + return; + + writel(val, pcie->base + offset); +} + +/* + * APB error forwarding can be disabled during access of configuration + * registers of the endpoint device, to prevent unsupported requests + * (typically seen during enumeration with multi-function devices) from + * triggering a system exception. + */ +static inline void iproc_pcie_apb_err_disable(struct pci_bus *bus, + bool disable) +{ + struct iproc_pcie *pcie = iproc_data(bus); + u32 val; + + if (bus->number && pcie->has_apb_err_disable) { + val = iproc_pcie_read_reg(pcie, IPROC_PCIE_APB_ERR_EN); + if (disable) + val &= ~APB_ERR_EN; + else + val |= APB_ERR_EN; + iproc_pcie_write_reg(pcie, IPROC_PCIE_APB_ERR_EN, val); + } +} + +static void __iomem *iproc_pcie_map_ep_cfg_reg(struct iproc_pcie *pcie, + unsigned int busno, + unsigned int devfn, + int where) +{ + u16 offset; + u32 val; + + /* EP device access */ + val = ALIGN_DOWN(PCIE_ECAM_OFFSET(busno, devfn, where), 4) | + CFG_ADDR_CFG_TYPE_1; + + iproc_pcie_write_reg(pcie, IPROC_PCIE_CFG_ADDR, val); + offset = iproc_pcie_reg_offset(pcie, IPROC_PCIE_CFG_DATA); + + if (iproc_pcie_reg_is_invalid(offset)) + return NULL; + + return (pcie->base + offset); +} + +static unsigned int iproc_pcie_cfg_retry(struct iproc_pcie *pcie, + void __iomem *cfg_data_p) +{ + int timeout = CFG_RETRY_STATUS_TIMEOUT_US; + unsigned int data; + u32 status; + + /* + * As per PCIe spec r3.1, sec 2.3.2, CRS Software Visibility only + * affects config reads of the Vendor ID. For config writes or any + * other config reads, the Root may automatically reissue the + * configuration request again as a new request. + * + * For config reads, this hardware returns CFG_RETRY_STATUS data + * when it receives a CRS completion, regardless of the address of + * the read or the CRS Software Visibility Enable bit. As a + * partial workaround for this, we retry in software any read that + * returns CFG_RETRY_STATUS. + * + * Note that a non-Vendor ID config register may have a value of + * CFG_RETRY_STATUS. If we read that, we can't distinguish it from + * a CRS completion, so we will incorrectly retry the read and + * eventually return the wrong data (0xffffffff). + */ + data = readl(cfg_data_p); + while (data == CFG_RETRY_STATUS && timeout--) { + /* + * CRS state is set in CFG_RD status register + * This will handle the case where CFG_RETRY_STATUS is + * valid config data. + */ + status = iproc_pcie_read_reg(pcie, IPROC_PCIE_CFG_RD_STATUS); + if (status != CFG_RD_CRS) + return data; + + udelay(1); + data = readl(cfg_data_p); + } + + if (data == CFG_RETRY_STATUS) + data = 0xffffffff; + + return data; +} + +static void iproc_pcie_fix_cap(struct iproc_pcie *pcie, int where, u32 *val) +{ + u32 i, dev_id; + + switch (where & ~0x3) { + case PCI_VENDOR_ID: + dev_id = *val >> 16; + + /* + * Activate fixup for those controllers that have corrupted + * capability list registers + */ + for (i = 0; i < ARRAY_SIZE(iproc_pcie_corrupt_cap_did); i++) + if (dev_id == iproc_pcie_corrupt_cap_did[i]) + pcie->fix_paxc_cap = true; + break; + + case IPROC_PCI_PM_CAP: + if (pcie->fix_paxc_cap) { + /* advertise PM, force next capability to PCIe */ + *val &= ~IPROC_PCI_PM_CAP_MASK; + *val |= IPROC_PCI_EXP_CAP << 8 | PCI_CAP_ID_PM; + } + break; + + case IPROC_PCI_EXP_CAP: + if (pcie->fix_paxc_cap) { + /* advertise root port, version 2, terminate here */ + *val = (PCI_EXP_TYPE_ROOT_PORT << 4 | 2) << 16 | + PCI_CAP_ID_EXP; + } + break; + + case IPROC_PCI_EXP_CAP + PCI_EXP_RTCTL: + /* Don't advertise CRS SV support */ + *val &= ~(PCI_EXP_RTCAP_CRSVIS << 16); + break; + + default: + break; + } +} + +static int iproc_pcie_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct iproc_pcie *pcie = iproc_data(bus); + unsigned int busno = bus->number; + void __iomem *cfg_data_p; + unsigned int data; + int ret; + + /* root complex access */ + if (busno == 0) { + ret = pci_generic_config_read32(bus, devfn, where, size, val); + if (ret == PCIBIOS_SUCCESSFUL) + iproc_pcie_fix_cap(pcie, where, val); + + return ret; + } + + cfg_data_p = iproc_pcie_map_ep_cfg_reg(pcie, busno, devfn, where); + + if (!cfg_data_p) + return PCIBIOS_DEVICE_NOT_FOUND; + + data = iproc_pcie_cfg_retry(pcie, cfg_data_p); + + *val = data; + if (size <= 2) + *val = (data >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); + + /* + * For PAXC and PAXCv2, the total number of PFs that one can enumerate + * depends on the firmware configuration. Unfortunately, due to an ASIC + * bug, unconfigured PFs cannot be properly hidden from the root + * complex. As a result, write access to these PFs will cause bus lock + * up on the embedded processor + * + * Since all unconfigured PFs are left with an incorrect, staled device + * ID of 0x168e (PCI_DEVICE_ID_NX2_57810), we try to catch those access + * early here and reject them all + */ +#define DEVICE_ID_MASK 0xffff0000 +#define DEVICE_ID_SHIFT 16 + if (pcie->rej_unconfig_pf && + (where & CFG_ADDR_REG_NUM_MASK) == PCI_VENDOR_ID) + if ((*val & DEVICE_ID_MASK) == + (PCI_DEVICE_ID_NX2_57810 << DEVICE_ID_SHIFT)) + return PCIBIOS_FUNC_NOT_SUPPORTED; + + return PCIBIOS_SUCCESSFUL; +} + +/* + * Note access to the configuration registers are protected at the higher layer + * by 'pci_lock' in drivers/pci/access.c + */ +static void __iomem *iproc_pcie_map_cfg_bus(struct iproc_pcie *pcie, + int busno, unsigned int devfn, + int where) +{ + u16 offset; + + /* root complex access */ + if (busno == 0) { + if (PCIE_ECAM_DEVFN(devfn) > 0) + return NULL; + + iproc_pcie_write_reg(pcie, IPROC_PCIE_CFG_IND_ADDR, + where & CFG_IND_ADDR_MASK); + offset = iproc_pcie_reg_offset(pcie, IPROC_PCIE_CFG_IND_DATA); + if (iproc_pcie_reg_is_invalid(offset)) + return NULL; + else + return (pcie->base + offset); + } + + return iproc_pcie_map_ep_cfg_reg(pcie, busno, devfn, where); +} + +static void __iomem *iproc_pcie_bus_map_cfg_bus(struct pci_bus *bus, + unsigned int devfn, + int where) +{ + return iproc_pcie_map_cfg_bus(iproc_data(bus), bus->number, devfn, + where); +} + +static int iproc_pci_raw_config_read32(struct iproc_pcie *pcie, + unsigned int devfn, int where, + int size, u32 *val) +{ + void __iomem *addr; + + addr = iproc_pcie_map_cfg_bus(pcie, 0, devfn, where & ~0x3); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + *val = readl(addr); + + if (size <= 2) + *val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); + + return PCIBIOS_SUCCESSFUL; +} + +static int iproc_pci_raw_config_write32(struct iproc_pcie *pcie, + unsigned int devfn, int where, + int size, u32 val) +{ + void __iomem *addr; + u32 mask, tmp; + + addr = iproc_pcie_map_cfg_bus(pcie, 0, devfn, where & ~0x3); + if (!addr) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (size == 4) { + writel(val, addr); + return PCIBIOS_SUCCESSFUL; + } + + mask = ~(((1 << (size * 8)) - 1) << ((where & 0x3) * 8)); + tmp = readl(addr) & mask; + tmp |= val << ((where & 0x3) * 8); + writel(tmp, addr); + + return PCIBIOS_SUCCESSFUL; +} + +static int iproc_pcie_config_read32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + int ret; + struct iproc_pcie *pcie = iproc_data(bus); + + iproc_pcie_apb_err_disable(bus, true); + if (pcie->iproc_cfg_read) + ret = iproc_pcie_config_read(bus, devfn, where, size, val); + else + ret = pci_generic_config_read32(bus, devfn, where, size, val); + iproc_pcie_apb_err_disable(bus, false); + + return ret; +} + +static int iproc_pcie_config_write32(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + int ret; + + iproc_pcie_apb_err_disable(bus, true); + ret = pci_generic_config_write32(bus, devfn, where, size, val); + iproc_pcie_apb_err_disable(bus, false); + + return ret; +} + +static struct pci_ops iproc_pcie_ops = { + .map_bus = iproc_pcie_bus_map_cfg_bus, + .read = iproc_pcie_config_read32, + .write = iproc_pcie_config_write32, +}; + +static void iproc_pcie_perst_ctrl(struct iproc_pcie *pcie, bool assert) +{ + u32 val; + + /* + * PAXC and the internal emulated endpoint device downstream should not + * be reset. If firmware has been loaded on the endpoint device at an + * earlier boot stage, reset here causes issues. + */ + if (pcie->ep_is_internal) + return; + + if (assert) { + val = iproc_pcie_read_reg(pcie, IPROC_PCIE_CLK_CTRL); + val &= ~EP_PERST_SOURCE_SELECT & ~EP_MODE_SURVIVE_PERST & + ~RC_PCIE_RST_OUTPUT; + iproc_pcie_write_reg(pcie, IPROC_PCIE_CLK_CTRL, val); + udelay(250); + } else { + val = iproc_pcie_read_reg(pcie, IPROC_PCIE_CLK_CTRL); + val |= RC_PCIE_RST_OUTPUT; + iproc_pcie_write_reg(pcie, IPROC_PCIE_CLK_CTRL, val); + msleep(100); + } +} + +int iproc_pcie_shutdown(struct iproc_pcie *pcie) +{ + iproc_pcie_perst_ctrl(pcie, true); + msleep(500); + + return 0; +} +EXPORT_SYMBOL_GPL(iproc_pcie_shutdown); + +static int iproc_pcie_check_link(struct iproc_pcie *pcie) +{ + struct device *dev = pcie->dev; + u32 hdr_type, link_ctrl, link_status, class, val; + bool link_is_active = false; + + /* + * PAXC connects to emulated endpoint devices directly and does not + * have a Serdes. Therefore skip the link detection logic here. + */ + if (pcie->ep_is_internal) + return 0; + + val = iproc_pcie_read_reg(pcie, IPROC_PCIE_LINK_STATUS); + if (!(val & PCIE_PHYLINKUP) || !(val & PCIE_DL_ACTIVE)) { + dev_err(dev, "PHY or data link is INACTIVE!\n"); + return -ENODEV; + } + + /* make sure we are not in EP mode */ + iproc_pci_raw_config_read32(pcie, 0, PCI_HEADER_TYPE, 1, &hdr_type); + if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE) { + dev_err(dev, "in EP mode, hdr=%#02x\n", hdr_type); + return -EFAULT; + } + + /* force class to PCI_CLASS_BRIDGE_PCI_NORMAL (0x060400) */ +#define PCI_BRIDGE_CTRL_REG_OFFSET 0x43c +#define PCI_BRIDGE_CTRL_REG_CLASS_MASK 0xffffff + iproc_pci_raw_config_read32(pcie, 0, PCI_BRIDGE_CTRL_REG_OFFSET, + 4, &class); + class &= ~PCI_BRIDGE_CTRL_REG_CLASS_MASK; + class |= PCI_CLASS_BRIDGE_PCI_NORMAL; + iproc_pci_raw_config_write32(pcie, 0, PCI_BRIDGE_CTRL_REG_OFFSET, + 4, class); + + /* check link status to see if link is active */ + iproc_pci_raw_config_read32(pcie, 0, IPROC_PCI_EXP_CAP + PCI_EXP_LNKSTA, + 2, &link_status); + if (link_status & PCI_EXP_LNKSTA_NLW) + link_is_active = true; + + if (!link_is_active) { + /* try GEN 1 link speed */ +#define PCI_TARGET_LINK_SPEED_MASK 0xf +#define PCI_TARGET_LINK_SPEED_GEN2 0x2 +#define PCI_TARGET_LINK_SPEED_GEN1 0x1 + iproc_pci_raw_config_read32(pcie, 0, + IPROC_PCI_EXP_CAP + PCI_EXP_LNKCTL2, + 4, &link_ctrl); + if ((link_ctrl & PCI_TARGET_LINK_SPEED_MASK) == + PCI_TARGET_LINK_SPEED_GEN2) { + link_ctrl &= ~PCI_TARGET_LINK_SPEED_MASK; + link_ctrl |= PCI_TARGET_LINK_SPEED_GEN1; + iproc_pci_raw_config_write32(pcie, 0, + IPROC_PCI_EXP_CAP + PCI_EXP_LNKCTL2, + 4, link_ctrl); + msleep(100); + + iproc_pci_raw_config_read32(pcie, 0, + IPROC_PCI_EXP_CAP + PCI_EXP_LNKSTA, + 2, &link_status); + if (link_status & PCI_EXP_LNKSTA_NLW) + link_is_active = true; + } + } + + dev_info(dev, "link: %s\n", link_is_active ? "UP" : "DOWN"); + + return link_is_active ? 0 : -ENODEV; +} + +static void iproc_pcie_enable(struct iproc_pcie *pcie) +{ + iproc_pcie_write_reg(pcie, IPROC_PCIE_INTX_EN, SYS_RC_INTX_MASK); +} + +static inline bool iproc_pcie_ob_is_valid(struct iproc_pcie *pcie, + int window_idx) +{ + u32 val; + + val = iproc_pcie_read_reg(pcie, MAP_REG(IPROC_PCIE_OARR0, window_idx)); + + return !!(val & OARR_VALID); +} + +static inline int iproc_pcie_ob_write(struct iproc_pcie *pcie, int window_idx, + int size_idx, u64 axi_addr, u64 pci_addr) +{ + struct device *dev = pcie->dev; + u16 oarr_offset, omap_offset; + + /* + * Derive the OARR/OMAP offset from the first pair (OARR0/OMAP0) based + * on window index. + */ + oarr_offset = iproc_pcie_reg_offset(pcie, MAP_REG(IPROC_PCIE_OARR0, + window_idx)); + omap_offset = iproc_pcie_reg_offset(pcie, MAP_REG(IPROC_PCIE_OMAP0, + window_idx)); + if (iproc_pcie_reg_is_invalid(oarr_offset) || + iproc_pcie_reg_is_invalid(omap_offset)) + return -EINVAL; + + /* + * Program the OARR registers. The upper 32-bit OARR register is + * always right after the lower 32-bit OARR register. + */ + writel(lower_32_bits(axi_addr) | (size_idx << OARR_SIZE_CFG_SHIFT) | + OARR_VALID, pcie->base + oarr_offset); + writel(upper_32_bits(axi_addr), pcie->base + oarr_offset + 4); + + /* now program the OMAP registers */ + writel(lower_32_bits(pci_addr), pcie->base + omap_offset); + writel(upper_32_bits(pci_addr), pcie->base + omap_offset + 4); + + dev_dbg(dev, "ob window [%d]: offset 0x%x axi %pap pci %pap\n", + window_idx, oarr_offset, &axi_addr, &pci_addr); + dev_dbg(dev, "oarr lo 0x%x oarr hi 0x%x\n", + readl(pcie->base + oarr_offset), + readl(pcie->base + oarr_offset + 4)); + dev_dbg(dev, "omap lo 0x%x omap hi 0x%x\n", + readl(pcie->base + omap_offset), + readl(pcie->base + omap_offset + 4)); + + return 0; +} + +/* + * Some iProc SoCs require the SW to configure the outbound address mapping + * + * Outbound address translation: + * + * iproc_pcie_address = axi_address - axi_offset + * OARR = iproc_pcie_address + * OMAP = pci_addr + * + * axi_addr -> iproc_pcie_address -> OARR -> OMAP -> pci_address + */ +static int iproc_pcie_setup_ob(struct iproc_pcie *pcie, u64 axi_addr, + u64 pci_addr, resource_size_t size) +{ + struct iproc_pcie_ob *ob = &pcie->ob; + struct device *dev = pcie->dev; + int ret = -EINVAL, window_idx, size_idx; + + if (axi_addr < ob->axi_offset) { + dev_err(dev, "axi address %pap less than offset %pap\n", + &axi_addr, &ob->axi_offset); + return -EINVAL; + } + + /* + * Translate the AXI address to the internal address used by the iProc + * PCIe core before programming the OARR + */ + axi_addr -= ob->axi_offset; + + /* iterate through all OARR/OMAP mapping windows */ + for (window_idx = ob->nr_windows - 1; window_idx >= 0; window_idx--) { + const struct iproc_pcie_ob_map *ob_map = + &pcie->ob_map[window_idx]; + + /* + * If current outbound window is already in use, move on to the + * next one. + */ + if (iproc_pcie_ob_is_valid(pcie, window_idx)) + continue; + + /* + * Iterate through all supported window sizes within the + * OARR/OMAP pair to find a match. Go through the window sizes + * in a descending order. + */ + for (size_idx = ob_map->nr_sizes - 1; size_idx >= 0; + size_idx--) { + resource_size_t window_size = + ob_map->window_sizes[size_idx] * SZ_1M; + + /* + * Keep iterating until we reach the last window and + * with the minimal window size at index zero. In this + * case, we take a compromise by mapping it using the + * minimum window size that can be supported + */ + if (size < window_size) { + if (size_idx > 0 || window_idx > 0) + continue; + + /* + * For the corner case of reaching the minimal + * window size that can be supported on the + * last window + */ + axi_addr = ALIGN_DOWN(axi_addr, window_size); + pci_addr = ALIGN_DOWN(pci_addr, window_size); + size = window_size; + } + + if (!IS_ALIGNED(axi_addr, window_size) || + !IS_ALIGNED(pci_addr, window_size)) { + dev_err(dev, + "axi %pap or pci %pap not aligned\n", + &axi_addr, &pci_addr); + return -EINVAL; + } + + /* + * Match found! Program both OARR and OMAP and mark + * them as a valid entry. + */ + ret = iproc_pcie_ob_write(pcie, window_idx, size_idx, + axi_addr, pci_addr); + if (ret) + goto err_ob; + + size -= window_size; + if (size == 0) + return 0; + + /* + * If we are here, we are done with the current window, + * but not yet finished all mappings. Need to move on + * to the next window. + */ + axi_addr += window_size; + pci_addr += window_size; + break; + } + } + +err_ob: + dev_err(dev, "unable to configure outbound mapping\n"); + dev_err(dev, + "axi %pap, axi offset %pap, pci %pap, res size %pap\n", + &axi_addr, &ob->axi_offset, &pci_addr, &size); + + return ret; +} + +static int iproc_pcie_map_ranges(struct iproc_pcie *pcie, + struct list_head *resources) +{ + struct device *dev = pcie->dev; + struct resource_entry *window; + int ret; + + resource_list_for_each_entry(window, resources) { + struct resource *res = window->res; + u64 res_type = resource_type(res); + + switch (res_type) { + case IORESOURCE_IO: + case IORESOURCE_BUS: + break; + case IORESOURCE_MEM: + ret = iproc_pcie_setup_ob(pcie, res->start, + res->start - window->offset, + resource_size(res)); + if (ret) + return ret; + break; + default: + dev_err(dev, "invalid resource %pR\n", res); + return -EINVAL; + } + } + + return 0; +} + +static inline bool iproc_pcie_ib_is_in_use(struct iproc_pcie *pcie, + int region_idx) +{ + const struct iproc_pcie_ib_map *ib_map = &pcie->ib_map[region_idx]; + u32 val; + + val = iproc_pcie_read_reg(pcie, MAP_REG(IPROC_PCIE_IARR0, region_idx)); + + return !!(val & (BIT(ib_map->nr_sizes) - 1)); +} + +static inline bool iproc_pcie_ib_check_type(const struct iproc_pcie_ib_map *ib_map, + enum iproc_pcie_ib_map_type type) +{ + return !!(ib_map->type == type); +} + +static int iproc_pcie_ib_write(struct iproc_pcie *pcie, int region_idx, + int size_idx, int nr_windows, u64 axi_addr, + u64 pci_addr, resource_size_t size) +{ + struct device *dev = pcie->dev; + const struct iproc_pcie_ib_map *ib_map = &pcie->ib_map[region_idx]; + u16 iarr_offset, imap_offset; + u32 val; + int window_idx; + + iarr_offset = iproc_pcie_reg_offset(pcie, + MAP_REG(IPROC_PCIE_IARR0, region_idx)); + imap_offset = iproc_pcie_reg_offset(pcie, + MAP_REG(IPROC_PCIE_IMAP0, region_idx)); + if (iproc_pcie_reg_is_invalid(iarr_offset) || + iproc_pcie_reg_is_invalid(imap_offset)) + return -EINVAL; + + dev_dbg(dev, "ib region [%d]: offset 0x%x axi %pap pci %pap\n", + region_idx, iarr_offset, &axi_addr, &pci_addr); + + /* + * Program the IARR registers. The upper 32-bit IARR register is + * always right after the lower 32-bit IARR register. + */ + writel(lower_32_bits(pci_addr) | BIT(size_idx), + pcie->base + iarr_offset); + writel(upper_32_bits(pci_addr), pcie->base + iarr_offset + 4); + + dev_dbg(dev, "iarr lo 0x%x iarr hi 0x%x\n", + readl(pcie->base + iarr_offset), + readl(pcie->base + iarr_offset + 4)); + + /* + * Now program the IMAP registers. Each IARR region may have one or + * more IMAP windows. + */ + size >>= ilog2(nr_windows); + for (window_idx = 0; window_idx < nr_windows; window_idx++) { + val = readl(pcie->base + imap_offset); + val |= lower_32_bits(axi_addr) | IMAP_VALID; + writel(val, pcie->base + imap_offset); + writel(upper_32_bits(axi_addr), + pcie->base + imap_offset + ib_map->imap_addr_offset); + + dev_dbg(dev, "imap window [%d] lo 0x%x hi 0x%x\n", + window_idx, readl(pcie->base + imap_offset), + readl(pcie->base + imap_offset + + ib_map->imap_addr_offset)); + + imap_offset += ib_map->imap_window_offset; + axi_addr += size; + } + + return 0; +} + +static int iproc_pcie_setup_ib(struct iproc_pcie *pcie, + struct resource_entry *entry, + enum iproc_pcie_ib_map_type type) +{ + struct device *dev = pcie->dev; + struct iproc_pcie_ib *ib = &pcie->ib; + int ret; + unsigned int region_idx, size_idx; + u64 axi_addr = entry->res->start; + u64 pci_addr = entry->res->start - entry->offset; + resource_size_t size = resource_size(entry->res); + + /* iterate through all IARR mapping regions */ + for (region_idx = 0; region_idx < ib->nr_regions; region_idx++) { + const struct iproc_pcie_ib_map *ib_map = + &pcie->ib_map[region_idx]; + + /* + * If current inbound region is already in use or not a + * compatible type, move on to the next. + */ + if (iproc_pcie_ib_is_in_use(pcie, region_idx) || + !iproc_pcie_ib_check_type(ib_map, type)) + continue; + + /* iterate through all supported region sizes to find a match */ + for (size_idx = 0; size_idx < ib_map->nr_sizes; size_idx++) { + resource_size_t region_size = + ib_map->region_sizes[size_idx] * ib_map->size_unit; + + if (size != region_size) + continue; + + if (!IS_ALIGNED(axi_addr, region_size) || + !IS_ALIGNED(pci_addr, region_size)) { + dev_err(dev, + "axi %pap or pci %pap not aligned\n", + &axi_addr, &pci_addr); + return -EINVAL; + } + + /* Match found! Program IARR and all IMAP windows. */ + ret = iproc_pcie_ib_write(pcie, region_idx, size_idx, + ib_map->nr_windows, axi_addr, + pci_addr, size); + if (ret) + goto err_ib; + else + return 0; + + } + } + ret = -EINVAL; + +err_ib: + dev_err(dev, "unable to configure inbound mapping\n"); + dev_err(dev, "axi %pap, pci %pap, res size %pap\n", + &axi_addr, &pci_addr, &size); + + return ret; +} + +static int iproc_pcie_map_dma_ranges(struct iproc_pcie *pcie) +{ + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + struct resource_entry *entry; + int ret = 0; + + resource_list_for_each_entry(entry, &host->dma_ranges) { + /* Each range entry corresponds to an inbound mapping region */ + ret = iproc_pcie_setup_ib(pcie, entry, IPROC_PCIE_IB_MAP_MEM); + if (ret) + break; + } + + return ret; +} + +static void iproc_pcie_invalidate_mapping(struct iproc_pcie *pcie) +{ + struct iproc_pcie_ib *ib = &pcie->ib; + struct iproc_pcie_ob *ob = &pcie->ob; + int idx; + + if (pcie->ep_is_internal) + return; + + if (pcie->need_ob_cfg) { + /* iterate through all OARR mapping regions */ + for (idx = ob->nr_windows - 1; idx >= 0; idx--) { + iproc_pcie_write_reg(pcie, + MAP_REG(IPROC_PCIE_OARR0, idx), 0); + } + } + + if (pcie->need_ib_cfg) { + /* iterate through all IARR mapping regions */ + for (idx = 0; idx < ib->nr_regions; idx++) { + iproc_pcie_write_reg(pcie, + MAP_REG(IPROC_PCIE_IARR0, idx), 0); + } + } +} + +static int iproce_pcie_get_msi(struct iproc_pcie *pcie, + struct device_node *msi_node, + u64 *msi_addr) +{ + struct device *dev = pcie->dev; + int ret; + struct resource res; + + /* + * Check if 'msi-map' points to ARM GICv3 ITS, which is the only + * supported external MSI controller that requires steering. + */ + if (!of_device_is_compatible(msi_node, "arm,gic-v3-its")) { + dev_err(dev, "unable to find compatible MSI controller\n"); + return -ENODEV; + } + + /* derive GITS_TRANSLATER address from GICv3 */ + ret = of_address_to_resource(msi_node, 0, &res); + if (ret < 0) { + dev_err(dev, "unable to obtain MSI controller resources\n"); + return ret; + } + + *msi_addr = res.start + GITS_TRANSLATER; + return 0; +} + +static int iproc_pcie_paxb_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr) +{ + int ret; + struct resource_entry entry; + + memset(&entry, 0, sizeof(entry)); + entry.res = &entry.__res; + + msi_addr &= ~(SZ_32K - 1); + entry.res->start = msi_addr; + entry.res->end = msi_addr + SZ_32K - 1; + + ret = iproc_pcie_setup_ib(pcie, &entry, IPROC_PCIE_IB_MAP_IO); + return ret; +} + +static void iproc_pcie_paxc_v2_msi_steer(struct iproc_pcie *pcie, u64 msi_addr, + bool enable) +{ + u32 val; + + if (!enable) { + /* + * Disable PAXC MSI steering. All write transfers will be + * treated as non-MSI transfers + */ + val = iproc_pcie_read_reg(pcie, IPROC_PCIE_MSI_EN_CFG); + val &= ~MSI_ENABLE_CFG; + iproc_pcie_write_reg(pcie, IPROC_PCIE_MSI_EN_CFG, val); + return; + } + + /* + * Program bits [43:13] of address of GITS_TRANSLATER register into + * bits [30:0] of the MSI base address register. In fact, in all iProc + * based SoCs, all I/O register bases are well below the 32-bit + * boundary, so we can safely assume bits [43:32] are always zeros. + */ + iproc_pcie_write_reg(pcie, IPROC_PCIE_MSI_BASE_ADDR, + (u32)(msi_addr >> 13)); + + /* use a default 8K window size */ + iproc_pcie_write_reg(pcie, IPROC_PCIE_MSI_WINDOW_SIZE, 0); + + /* steering MSI to GICv3 ITS */ + val = iproc_pcie_read_reg(pcie, IPROC_PCIE_MSI_GIC_MODE); + val |= GIC_V3_CFG; + iproc_pcie_write_reg(pcie, IPROC_PCIE_MSI_GIC_MODE, val); + + /* + * Program bits [43:2] of address of GITS_TRANSLATER register into the + * iProc MSI address registers. + */ + msi_addr >>= 2; + iproc_pcie_write_reg(pcie, IPROC_PCIE_MSI_ADDR_HI, + upper_32_bits(msi_addr)); + iproc_pcie_write_reg(pcie, IPROC_PCIE_MSI_ADDR_LO, + lower_32_bits(msi_addr)); + + /* enable MSI */ + val = iproc_pcie_read_reg(pcie, IPROC_PCIE_MSI_EN_CFG); + val |= MSI_ENABLE_CFG; + iproc_pcie_write_reg(pcie, IPROC_PCIE_MSI_EN_CFG, val); +} + +static int iproc_pcie_msi_steer(struct iproc_pcie *pcie, + struct device_node *msi_node) +{ + struct device *dev = pcie->dev; + int ret; + u64 msi_addr; + + ret = iproce_pcie_get_msi(pcie, msi_node, &msi_addr); + if (ret < 0) { + dev_err(dev, "msi steering failed\n"); + return ret; + } + + switch (pcie->type) { + case IPROC_PCIE_PAXB_V2: + ret = iproc_pcie_paxb_v2_msi_steer(pcie, msi_addr); + if (ret) + return ret; + break; + case IPROC_PCIE_PAXC_V2: + iproc_pcie_paxc_v2_msi_steer(pcie, msi_addr, true); + break; + default: + return -EINVAL; + } + + return 0; +} + +static int iproc_pcie_msi_enable(struct iproc_pcie *pcie) +{ + struct device_node *msi_node; + int ret; + + /* + * Either the "msi-parent" or the "msi-map" phandle needs to exist + * for us to obtain the MSI node. + */ + + msi_node = of_parse_phandle(pcie->dev->of_node, "msi-parent", 0); + if (!msi_node) { + const __be32 *msi_map = NULL; + int len; + u32 phandle; + + msi_map = of_get_property(pcie->dev->of_node, "msi-map", &len); + if (!msi_map) + return -ENODEV; + + phandle = be32_to_cpup(msi_map + 1); + msi_node = of_find_node_by_phandle(phandle); + if (!msi_node) + return -ENODEV; + } + + /* + * Certain revisions of the iProc PCIe controller require additional + * configurations to steer the MSI writes towards an external MSI + * controller. + */ + if (pcie->need_msi_steer) { + ret = iproc_pcie_msi_steer(pcie, msi_node); + if (ret) + goto out_put_node; + } + + /* + * If another MSI controller is being used, the call below should fail + * but that is okay + */ + ret = iproc_msi_init(pcie, msi_node); + +out_put_node: + of_node_put(msi_node); + return ret; +} + +static void iproc_pcie_msi_disable(struct iproc_pcie *pcie) +{ + iproc_msi_exit(pcie); +} + +static int iproc_pcie_rev_init(struct iproc_pcie *pcie) +{ + struct device *dev = pcie->dev; + unsigned int reg_idx; + const u16 *regs; + + switch (pcie->type) { + case IPROC_PCIE_PAXB_BCMA: + regs = iproc_pcie_reg_paxb_bcma; + break; + case IPROC_PCIE_PAXB: + regs = iproc_pcie_reg_paxb; + pcie->has_apb_err_disable = true; + if (pcie->need_ob_cfg) { + pcie->ob_map = paxb_ob_map; + pcie->ob.nr_windows = ARRAY_SIZE(paxb_ob_map); + } + break; + case IPROC_PCIE_PAXB_V2: + regs = iproc_pcie_reg_paxb_v2; + pcie->iproc_cfg_read = true; + pcie->has_apb_err_disable = true; + if (pcie->need_ob_cfg) { + pcie->ob_map = paxb_v2_ob_map; + pcie->ob.nr_windows = ARRAY_SIZE(paxb_v2_ob_map); + } + pcie->ib.nr_regions = ARRAY_SIZE(paxb_v2_ib_map); + pcie->ib_map = paxb_v2_ib_map; + pcie->need_msi_steer = true; + dev_warn(dev, "reads of config registers that contain %#x return incorrect data\n", + CFG_RETRY_STATUS); + break; + case IPROC_PCIE_PAXC: + regs = iproc_pcie_reg_paxc; + pcie->ep_is_internal = true; + pcie->iproc_cfg_read = true; + pcie->rej_unconfig_pf = true; + break; + case IPROC_PCIE_PAXC_V2: + regs = iproc_pcie_reg_paxc_v2; + pcie->ep_is_internal = true; + pcie->iproc_cfg_read = true; + pcie->rej_unconfig_pf = true; + pcie->need_msi_steer = true; + break; + default: + dev_err(dev, "incompatible iProc PCIe interface\n"); + return -EINVAL; + } + + pcie->reg_offsets = devm_kcalloc(dev, IPROC_PCIE_MAX_NUM_REG, + sizeof(*pcie->reg_offsets), + GFP_KERNEL); + if (!pcie->reg_offsets) + return -ENOMEM; + + /* go through the register table and populate all valid registers */ + pcie->reg_offsets[0] = (pcie->type == IPROC_PCIE_PAXC_V2) ? + IPROC_PCIE_REG_INVALID : regs[0]; + for (reg_idx = 1; reg_idx < IPROC_PCIE_MAX_NUM_REG; reg_idx++) + pcie->reg_offsets[reg_idx] = regs[reg_idx] ? + regs[reg_idx] : IPROC_PCIE_REG_INVALID; + + return 0; +} + +int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res) +{ + struct device *dev; + int ret; + struct pci_dev *pdev; + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + + dev = pcie->dev; + + ret = iproc_pcie_rev_init(pcie); + if (ret) { + dev_err(dev, "unable to initialize controller parameters\n"); + return ret; + } + + ret = phy_init(pcie->phy); + if (ret) { + dev_err(dev, "unable to initialize PCIe PHY\n"); + return ret; + } + + ret = phy_power_on(pcie->phy); + if (ret) { + dev_err(dev, "unable to power on PCIe PHY\n"); + goto err_exit_phy; + } + + iproc_pcie_perst_ctrl(pcie, true); + iproc_pcie_perst_ctrl(pcie, false); + + iproc_pcie_invalidate_mapping(pcie); + + if (pcie->need_ob_cfg) { + ret = iproc_pcie_map_ranges(pcie, res); + if (ret) { + dev_err(dev, "map failed\n"); + goto err_power_off_phy; + } + } + + if (pcie->need_ib_cfg) { + ret = iproc_pcie_map_dma_ranges(pcie); + if (ret && ret != -ENOENT) + goto err_power_off_phy; + } + + ret = iproc_pcie_check_link(pcie); + if (ret) { + dev_err(dev, "no PCIe EP device detected\n"); + goto err_power_off_phy; + } + + iproc_pcie_enable(pcie); + + if (IS_ENABLED(CONFIG_PCI_MSI)) + if (iproc_pcie_msi_enable(pcie)) + dev_info(dev, "not using iProc MSI\n"); + + host->ops = &iproc_pcie_ops; + host->sysdata = pcie; + host->map_irq = pcie->map_irq; + + ret = pci_host_probe(host); + if (ret < 0) { + dev_err(dev, "failed to scan host: %d\n", ret); + goto err_power_off_phy; + } + + for_each_pci_bridge(pdev, host->bus) { + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) + pcie_print_link_status(pdev); + } + + return 0; + +err_power_off_phy: + phy_power_off(pcie->phy); +err_exit_phy: + phy_exit(pcie->phy); + return ret; +} +EXPORT_SYMBOL(iproc_pcie_setup); + +int iproc_pcie_remove(struct iproc_pcie *pcie) +{ + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + + pci_stop_root_bus(host->bus); + pci_remove_root_bus(host->bus); + + iproc_pcie_msi_disable(pcie); + + phy_power_off(pcie->phy); + phy_exit(pcie->phy); + + return 0; +} +EXPORT_SYMBOL(iproc_pcie_remove); + +/* + * The MSI parsing logic in certain revisions of Broadcom PAXC based root + * complex does not work and needs to be disabled + */ +static void quirk_paxc_disable_msi_parsing(struct pci_dev *pdev) +{ + struct iproc_pcie *pcie = iproc_data(pdev->bus); + + if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + iproc_pcie_paxc_v2_msi_steer(pcie, 0, false); +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, + quirk_paxc_disable_msi_parsing); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, + quirk_paxc_disable_msi_parsing); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, + quirk_paxc_disable_msi_parsing); + +static void quirk_paxc_bridge(struct pci_dev *pdev) +{ + /* + * The PCI config space is shared with the PAXC root port and the first + * Ethernet device. So, we need to workaround this by telling the PCI + * code that the bridge is not an Ethernet device. + */ + if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE) + pdev->class = PCI_CLASS_BRIDGE_PCI_NORMAL; + + /* + * MPSS is not being set properly (as it is currently 0). This is + * because that area of the PCI config space is hard coded to zero, and + * is not modifiable by firmware. Set this to 2 (e.g., 512 byte MPS) + * so that the MPS can be set to the real max value. + */ + pdev->pcie_mpss = 2; +} +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16cd, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x16f0, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd750, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd802, quirk_paxc_bridge); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0xd804, quirk_paxc_bridge); + +MODULE_AUTHOR("Ray Jui <rjui@broadcom.com>"); +MODULE_DESCRIPTION("Broadcom iPROC PCIe common driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-iproc.h b/drivers/pci/controller/pcie-iproc.h new file mode 100644 index 000000000..dcca31589 --- /dev/null +++ b/drivers/pci/controller/pcie-iproc.h @@ -0,0 +1,131 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Copyright (C) 2014-2015 Broadcom Corporation + */ + +#ifndef _PCIE_IPROC_H +#define _PCIE_IPROC_H + +/** + * enum iproc_pcie_type - iProc PCIe interface type + * @IPROC_PCIE_PAXB_BCMA: BCMA-based host controllers + * @IPROC_PCIE_PAXB: PAXB-based host controllers for + * NS, NSP, Cygnus, NS2, and Pegasus SOCs + * @IPROC_PCIE_PAXB_V2: PAXB-based host controllers for Stingray SoCs + * @IPROC_PCIE_PAXC: PAXC-based host controllers + * @IPROC_PCIE_PAXC_V2: PAXC-based host controllers (second generation) + * + * PAXB is the wrapper used in root complex that can be connected to an + * external endpoint device. + * + * PAXC is the wrapper used in root complex dedicated for internal emulated + * endpoint devices. + */ +enum iproc_pcie_type { + IPROC_PCIE_PAXB_BCMA = 0, + IPROC_PCIE_PAXB, + IPROC_PCIE_PAXB_V2, + IPROC_PCIE_PAXC, + IPROC_PCIE_PAXC_V2, +}; + +/** + * struct iproc_pcie_ob - iProc PCIe outbound mapping + * @axi_offset: offset from the AXI address to the internal address used by + * the iProc PCIe core + * @nr_windows: total number of supported outbound mapping windows + */ +struct iproc_pcie_ob { + resource_size_t axi_offset; + unsigned int nr_windows; +}; + +/** + * struct iproc_pcie_ib - iProc PCIe inbound mapping + * @nr_regions: total number of supported inbound mapping regions + */ +struct iproc_pcie_ib { + unsigned int nr_regions; +}; + +struct iproc_pcie_ob_map; +struct iproc_pcie_ib_map; +struct iproc_msi; + +/** + * struct iproc_pcie - iProc PCIe device + * @dev: pointer to device data structure + * @type: iProc PCIe interface type + * @reg_offsets: register offsets + * @base: PCIe host controller I/O register base + * @base_addr: PCIe host controller register base physical address + * @mem: host bridge memory window resource + * @phy: optional PHY device that controls the Serdes + * @map_irq: function callback to map interrupts + * @ep_is_internal: indicates an internal emulated endpoint device is connected + * @iproc_cfg_read: indicates the iProc config read function should be used + * @rej_unconfig_pf: indicates the root complex needs to detect and reject + * enumeration against unconfigured physical functions emulated in the ASIC + * @has_apb_err_disable: indicates the controller can be configured to prevent + * unsupported request from being forwarded as an APB bus error + * @fix_paxc_cap: indicates the controller has corrupted capability list in its + * config space registers and requires SW based fixup + * + * @need_ob_cfg: indicates SW needs to configure the outbound mapping window + * @ob: outbound mapping related parameters + * @ob_map: outbound mapping related parameters specific to the controller + * + * @need_ib_cfg: indicates SW needs to configure the inbound mapping window + * @ib: inbound mapping related parameters + * @ib_map: outbound mapping region related parameters + * + * @need_msi_steer: indicates additional configuration of the iProc PCIe + * controller is required to steer MSI writes to external interrupt controller + * @msi: MSI data + */ +struct iproc_pcie { + struct device *dev; + enum iproc_pcie_type type; + u16 *reg_offsets; + void __iomem *base; + phys_addr_t base_addr; + struct resource mem; + struct phy *phy; + int (*map_irq)(const struct pci_dev *, u8, u8); + bool ep_is_internal; + bool iproc_cfg_read; + bool rej_unconfig_pf; + bool has_apb_err_disable; + bool fix_paxc_cap; + + bool need_ob_cfg; + struct iproc_pcie_ob ob; + const struct iproc_pcie_ob_map *ob_map; + + bool need_ib_cfg; + struct iproc_pcie_ib ib; + const struct iproc_pcie_ib_map *ib_map; + + bool need_msi_steer; + struct iproc_msi *msi; +}; + +int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res); +int iproc_pcie_remove(struct iproc_pcie *pcie); +int iproc_pcie_shutdown(struct iproc_pcie *pcie); + +#ifdef CONFIG_PCIE_IPROC_MSI +int iproc_msi_init(struct iproc_pcie *pcie, struct device_node *node); +void iproc_msi_exit(struct iproc_pcie *pcie); +#else +static inline int iproc_msi_init(struct iproc_pcie *pcie, + struct device_node *node) +{ + return -ENODEV; +} +static inline void iproc_msi_exit(struct iproc_pcie *pcie) +{ +} +#endif + +#endif /* _PCIE_IPROC_H */ diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c new file mode 100644 index 000000000..40c38ca5a --- /dev/null +++ b/drivers/pci/controller/pcie-mediatek-gen3.c @@ -0,0 +1,1096 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * MediaTek PCIe host controller driver. + * + * Copyright (c) 2020 MediaTek Inc. + * Author: Jianjun Wang <jianjun.wang@mediatek.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/iopoll.h> +#include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_domain.h> +#include <linux/pm_runtime.h> +#include <linux/reset.h> + +#include "../pci.h" + +#define PCIE_SETTING_REG 0x80 +#define PCIE_PCI_IDS_1 0x9c +#define PCI_CLASS(class) (class << 8) +#define PCIE_RC_MODE BIT(0) + +#define PCIE_CFGNUM_REG 0x140 +#define PCIE_CFG_DEVFN(devfn) ((devfn) & GENMASK(7, 0)) +#define PCIE_CFG_BUS(bus) (((bus) << 8) & GENMASK(15, 8)) +#define PCIE_CFG_BYTE_EN(bytes) (((bytes) << 16) & GENMASK(19, 16)) +#define PCIE_CFG_FORCE_BYTE_EN BIT(20) +#define PCIE_CFG_OFFSET_ADDR 0x1000 +#define PCIE_CFG_HEADER(bus, devfn) \ + (PCIE_CFG_BUS(bus) | PCIE_CFG_DEVFN(devfn)) + +#define PCIE_RST_CTRL_REG 0x148 +#define PCIE_MAC_RSTB BIT(0) +#define PCIE_PHY_RSTB BIT(1) +#define PCIE_BRG_RSTB BIT(2) +#define PCIE_PE_RSTB BIT(3) + +#define PCIE_LTSSM_STATUS_REG 0x150 +#define PCIE_LTSSM_STATE_MASK GENMASK(28, 24) +#define PCIE_LTSSM_STATE(val) ((val & PCIE_LTSSM_STATE_MASK) >> 24) +#define PCIE_LTSSM_STATE_L2_IDLE 0x14 + +#define PCIE_LINK_STATUS_REG 0x154 +#define PCIE_PORT_LINKUP BIT(8) + +#define PCIE_MSI_SET_NUM 8 +#define PCIE_MSI_IRQS_PER_SET 32 +#define PCIE_MSI_IRQS_NUM \ + (PCIE_MSI_IRQS_PER_SET * PCIE_MSI_SET_NUM) + +#define PCIE_INT_ENABLE_REG 0x180 +#define PCIE_MSI_ENABLE GENMASK(PCIE_MSI_SET_NUM + 8 - 1, 8) +#define PCIE_MSI_SHIFT 8 +#define PCIE_INTX_SHIFT 24 +#define PCIE_INTX_ENABLE \ + GENMASK(PCIE_INTX_SHIFT + PCI_NUM_INTX - 1, PCIE_INTX_SHIFT) + +#define PCIE_INT_STATUS_REG 0x184 +#define PCIE_MSI_SET_ENABLE_REG 0x190 +#define PCIE_MSI_SET_ENABLE GENMASK(PCIE_MSI_SET_NUM - 1, 0) + +#define PCIE_MSI_SET_BASE_REG 0xc00 +#define PCIE_MSI_SET_OFFSET 0x10 +#define PCIE_MSI_SET_STATUS_OFFSET 0x04 +#define PCIE_MSI_SET_ENABLE_OFFSET 0x08 + +#define PCIE_MSI_SET_ADDR_HI_BASE 0xc80 +#define PCIE_MSI_SET_ADDR_HI_OFFSET 0x04 + +#define PCIE_ICMD_PM_REG 0x198 +#define PCIE_TURN_OFF_LINK BIT(4) + +#define PCIE_MISC_CTRL_REG 0x348 +#define PCIE_DISABLE_DVFSRC_VLT_REQ BIT(1) + +#define PCIE_TRANS_TABLE_BASE_REG 0x800 +#define PCIE_ATR_SRC_ADDR_MSB_OFFSET 0x4 +#define PCIE_ATR_TRSL_ADDR_LSB_OFFSET 0x8 +#define PCIE_ATR_TRSL_ADDR_MSB_OFFSET 0xc +#define PCIE_ATR_TRSL_PARAM_OFFSET 0x10 +#define PCIE_ATR_TLB_SET_OFFSET 0x20 + +#define PCIE_MAX_TRANS_TABLES 8 +#define PCIE_ATR_EN BIT(0) +#define PCIE_ATR_SIZE(size) \ + (((((size) - 1) << 1) & GENMASK(6, 1)) | PCIE_ATR_EN) +#define PCIE_ATR_ID(id) ((id) & GENMASK(3, 0)) +#define PCIE_ATR_TYPE_MEM PCIE_ATR_ID(0) +#define PCIE_ATR_TYPE_IO PCIE_ATR_ID(1) +#define PCIE_ATR_TLP_TYPE(type) (((type) << 16) & GENMASK(18, 16)) +#define PCIE_ATR_TLP_TYPE_MEM PCIE_ATR_TLP_TYPE(0) +#define PCIE_ATR_TLP_TYPE_IO PCIE_ATR_TLP_TYPE(2) + +/** + * struct mtk_msi_set - MSI information for each set + * @base: IO mapped register base + * @msg_addr: MSI message address + * @saved_irq_state: IRQ enable state saved at suspend time + */ +struct mtk_msi_set { + void __iomem *base; + phys_addr_t msg_addr; + u32 saved_irq_state; +}; + +/** + * struct mtk_gen3_pcie - PCIe port information + * @dev: pointer to PCIe device + * @base: IO mapped register base + * @reg_base: physical register base + * @mac_reset: MAC reset control + * @phy_reset: PHY reset control + * @phy: PHY controller block + * @clks: PCIe clocks + * @num_clks: PCIe clocks count for this port + * @irq: PCIe controller interrupt number + * @saved_irq_state: IRQ enable state saved at suspend time + * @irq_lock: lock protecting IRQ register access + * @intx_domain: legacy INTx IRQ domain + * @msi_domain: MSI IRQ domain + * @msi_bottom_domain: MSI IRQ bottom domain + * @msi_sets: MSI sets information + * @lock: lock protecting IRQ bit map + * @msi_irq_in_use: bit map for assigned MSI IRQ + */ +struct mtk_gen3_pcie { + struct device *dev; + void __iomem *base; + phys_addr_t reg_base; + struct reset_control *mac_reset; + struct reset_control *phy_reset; + struct phy *phy; + struct clk_bulk_data *clks; + int num_clks; + + int irq; + u32 saved_irq_state; + raw_spinlock_t irq_lock; + struct irq_domain *intx_domain; + struct irq_domain *msi_domain; + struct irq_domain *msi_bottom_domain; + struct mtk_msi_set msi_sets[PCIE_MSI_SET_NUM]; + struct mutex lock; + DECLARE_BITMAP(msi_irq_in_use, PCIE_MSI_IRQS_NUM); +}; + +/* LTSSM state in PCIE_LTSSM_STATUS_REG bit[28:24] */ +static const char *const ltssm_str[] = { + "detect.quiet", /* 0x00 */ + "detect.active", /* 0x01 */ + "polling.active", /* 0x02 */ + "polling.compliance", /* 0x03 */ + "polling.configuration", /* 0x04 */ + "config.linkwidthstart", /* 0x05 */ + "config.linkwidthaccept", /* 0x06 */ + "config.lanenumwait", /* 0x07 */ + "config.lanenumaccept", /* 0x08 */ + "config.complete", /* 0x09 */ + "config.idle", /* 0x0A */ + "recovery.receiverlock", /* 0x0B */ + "recovery.equalization", /* 0x0C */ + "recovery.speed", /* 0x0D */ + "recovery.receiverconfig", /* 0x0E */ + "recovery.idle", /* 0x0F */ + "L0", /* 0x10 */ + "L0s", /* 0x11 */ + "L1.entry", /* 0x12 */ + "L1.idle", /* 0x13 */ + "L2.idle", /* 0x14 */ + "L2.transmitwake", /* 0x15 */ + "disable", /* 0x16 */ + "loopback.entry", /* 0x17 */ + "loopback.active", /* 0x18 */ + "loopback.exit", /* 0x19 */ + "hotreset", /* 0x1A */ +}; + +/** + * mtk_pcie_config_tlp_header() - Configure a configuration TLP header + * @bus: PCI bus to query + * @devfn: device/function number + * @where: offset in config space + * @size: data size in TLP header + * + * Set byte enable field and device information in configuration TLP header. + */ +static void mtk_pcie_config_tlp_header(struct pci_bus *bus, unsigned int devfn, + int where, int size) +{ + struct mtk_gen3_pcie *pcie = bus->sysdata; + int bytes; + u32 val; + + bytes = (GENMASK(size - 1, 0) & 0xf) << (where & 0x3); + + val = PCIE_CFG_FORCE_BYTE_EN | PCIE_CFG_BYTE_EN(bytes) | + PCIE_CFG_HEADER(bus->number, devfn); + + writel_relaxed(val, pcie->base + PCIE_CFGNUM_REG); +} + +static void __iomem *mtk_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) +{ + struct mtk_gen3_pcie *pcie = bus->sysdata; + + return pcie->base + PCIE_CFG_OFFSET_ADDR + where; +} + +static int mtk_pcie_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + mtk_pcie_config_tlp_header(bus, devfn, where, size); + + return pci_generic_config_read32(bus, devfn, where, size, val); +} + +static int mtk_pcie_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + mtk_pcie_config_tlp_header(bus, devfn, where, size); + + if (size <= 2) + val <<= (where & 0x3) * 8; + + return pci_generic_config_write32(bus, devfn, where, 4, val); +} + +static struct pci_ops mtk_pcie_ops = { + .map_bus = mtk_pcie_map_bus, + .read = mtk_pcie_config_read, + .write = mtk_pcie_config_write, +}; + +static int mtk_pcie_set_trans_table(struct mtk_gen3_pcie *pcie, + resource_size_t cpu_addr, + resource_size_t pci_addr, + resource_size_t size, + unsigned long type, int *num) +{ + resource_size_t remaining = size; + resource_size_t table_size; + resource_size_t addr_align; + const char *range_type; + void __iomem *table; + u32 val; + + while (remaining && (*num < PCIE_MAX_TRANS_TABLES)) { + /* Table size needs to be a power of 2 */ + table_size = BIT(fls(remaining) - 1); + + if (cpu_addr > 0) { + addr_align = BIT(ffs(cpu_addr) - 1); + table_size = min(table_size, addr_align); + } + + /* Minimum size of translate table is 4KiB */ + if (table_size < 0x1000) { + dev_err(pcie->dev, "illegal table size %#llx\n", + (unsigned long long)table_size); + return -EINVAL; + } + + table = pcie->base + PCIE_TRANS_TABLE_BASE_REG + *num * PCIE_ATR_TLB_SET_OFFSET; + writel_relaxed(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(table_size) - 1), table); + writel_relaxed(upper_32_bits(cpu_addr), table + PCIE_ATR_SRC_ADDR_MSB_OFFSET); + writel_relaxed(lower_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET); + writel_relaxed(upper_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET); + + if (type == IORESOURCE_IO) { + val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO; + range_type = "IO"; + } else { + val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM; + range_type = "MEM"; + } + + writel_relaxed(val, table + PCIE_ATR_TRSL_PARAM_OFFSET); + + dev_dbg(pcie->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n", + range_type, *num, (unsigned long long)cpu_addr, + (unsigned long long)pci_addr, (unsigned long long)table_size); + + cpu_addr += table_size; + pci_addr += table_size; + remaining -= table_size; + (*num)++; + } + + if (remaining) + dev_warn(pcie->dev, "not enough translate table for addr: %#llx, limited to [%d]\n", + (unsigned long long)cpu_addr, PCIE_MAX_TRANS_TABLES); + + return 0; +} + +static void mtk_pcie_enable_msi(struct mtk_gen3_pcie *pcie) +{ + int i; + u32 val; + + for (i = 0; i < PCIE_MSI_SET_NUM; i++) { + struct mtk_msi_set *msi_set = &pcie->msi_sets[i]; + + msi_set->base = pcie->base + PCIE_MSI_SET_BASE_REG + + i * PCIE_MSI_SET_OFFSET; + msi_set->msg_addr = pcie->reg_base + PCIE_MSI_SET_BASE_REG + + i * PCIE_MSI_SET_OFFSET; + + /* Configure the MSI capture address */ + writel_relaxed(lower_32_bits(msi_set->msg_addr), msi_set->base); + writel_relaxed(upper_32_bits(msi_set->msg_addr), + pcie->base + PCIE_MSI_SET_ADDR_HI_BASE + + i * PCIE_MSI_SET_ADDR_HI_OFFSET); + } + + val = readl_relaxed(pcie->base + PCIE_MSI_SET_ENABLE_REG); + val |= PCIE_MSI_SET_ENABLE; + writel_relaxed(val, pcie->base + PCIE_MSI_SET_ENABLE_REG); + + val = readl_relaxed(pcie->base + PCIE_INT_ENABLE_REG); + val |= PCIE_MSI_ENABLE; + writel_relaxed(val, pcie->base + PCIE_INT_ENABLE_REG); +} + +static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie) +{ + struct resource_entry *entry; + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + unsigned int table_index = 0; + int err; + u32 val; + + /* Set as RC mode */ + val = readl_relaxed(pcie->base + PCIE_SETTING_REG); + val |= PCIE_RC_MODE; + writel_relaxed(val, pcie->base + PCIE_SETTING_REG); + + /* Set class code */ + val = readl_relaxed(pcie->base + PCIE_PCI_IDS_1); + val &= ~GENMASK(31, 8); + val |= PCI_CLASS(PCI_CLASS_BRIDGE_PCI_NORMAL); + writel_relaxed(val, pcie->base + PCIE_PCI_IDS_1); + + /* Mask all INTx interrupts */ + val = readl_relaxed(pcie->base + PCIE_INT_ENABLE_REG); + val &= ~PCIE_INTX_ENABLE; + writel_relaxed(val, pcie->base + PCIE_INT_ENABLE_REG); + + /* Disable DVFSRC voltage request */ + val = readl_relaxed(pcie->base + PCIE_MISC_CTRL_REG); + val |= PCIE_DISABLE_DVFSRC_VLT_REQ; + writel_relaxed(val, pcie->base + PCIE_MISC_CTRL_REG); + + /* Assert all reset signals */ + val = readl_relaxed(pcie->base + PCIE_RST_CTRL_REG); + val |= PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB | PCIE_PE_RSTB; + writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); + + /* + * Described in PCIe CEM specification sections 2.2 (PERST# Signal) + * and 2.2.1 (Initial Power-Up (G3 to S0)). + * The deassertion of PERST# should be delayed 100ms (TPVPERL) + * for the power and clock to become stable. + */ + msleep(100); + + /* De-assert reset signals */ + val &= ~(PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB | PCIE_PE_RSTB); + writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); + + /* Check if the link is up or not */ + err = readl_poll_timeout(pcie->base + PCIE_LINK_STATUS_REG, val, + !!(val & PCIE_PORT_LINKUP), 20, + PCI_PM_D3COLD_WAIT * USEC_PER_MSEC); + if (err) { + const char *ltssm_state; + int ltssm_index; + + val = readl_relaxed(pcie->base + PCIE_LTSSM_STATUS_REG); + ltssm_index = PCIE_LTSSM_STATE(val); + ltssm_state = ltssm_index >= ARRAY_SIZE(ltssm_str) ? + "Unknown state" : ltssm_str[ltssm_index]; + dev_err(pcie->dev, + "PCIe link down, current LTSSM state: %s (%#x)\n", + ltssm_state, val); + return err; + } + + mtk_pcie_enable_msi(pcie); + + /* Set PCIe translation windows */ + resource_list_for_each_entry(entry, &host->windows) { + struct resource *res = entry->res; + unsigned long type = resource_type(res); + resource_size_t cpu_addr; + resource_size_t pci_addr; + resource_size_t size; + + if (type == IORESOURCE_IO) + cpu_addr = pci_pio_to_address(res->start); + else if (type == IORESOURCE_MEM) + cpu_addr = res->start; + else + continue; + + pci_addr = res->start - entry->offset; + size = resource_size(res); + err = mtk_pcie_set_trans_table(pcie, cpu_addr, pci_addr, size, + type, &table_index); + if (err) + return err; + } + + return 0; +} + +static int mtk_pcie_set_affinity(struct irq_data *data, + const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static void mtk_pcie_msi_irq_mask(struct irq_data *data) +{ + pci_msi_mask_irq(data); + irq_chip_mask_parent(data); +} + +static void mtk_pcie_msi_irq_unmask(struct irq_data *data) +{ + pci_msi_unmask_irq(data); + irq_chip_unmask_parent(data); +} + +static struct irq_chip mtk_msi_irq_chip = { + .irq_ack = irq_chip_ack_parent, + .irq_mask = mtk_pcie_msi_irq_mask, + .irq_unmask = mtk_pcie_msi_irq_unmask, + .name = "MSI", +}; + +static struct msi_domain_info mtk_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX | MSI_FLAG_MULTI_PCI_MSI), + .chip = &mtk_msi_irq_chip, +}; + +static void mtk_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data); + struct mtk_gen3_pcie *pcie = data->domain->host_data; + unsigned long hwirq; + + hwirq = data->hwirq % PCIE_MSI_IRQS_PER_SET; + + msg->address_hi = upper_32_bits(msi_set->msg_addr); + msg->address_lo = lower_32_bits(msi_set->msg_addr); + msg->data = hwirq; + dev_dbg(pcie->dev, "msi#%#lx address_hi %#x address_lo %#x data %d\n", + hwirq, msg->address_hi, msg->address_lo, msg->data); +} + +static void mtk_msi_bottom_irq_ack(struct irq_data *data) +{ + struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data); + unsigned long hwirq; + + hwirq = data->hwirq % PCIE_MSI_IRQS_PER_SET; + + writel_relaxed(BIT(hwirq), msi_set->base + PCIE_MSI_SET_STATUS_OFFSET); +} + +static void mtk_msi_bottom_irq_mask(struct irq_data *data) +{ + struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data); + struct mtk_gen3_pcie *pcie = data->domain->host_data; + unsigned long hwirq, flags; + u32 val; + + hwirq = data->hwirq % PCIE_MSI_IRQS_PER_SET; + + raw_spin_lock_irqsave(&pcie->irq_lock, flags); + val = readl_relaxed(msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + val &= ~BIT(hwirq); + writel_relaxed(val, msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); +} + +static void mtk_msi_bottom_irq_unmask(struct irq_data *data) +{ + struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data); + struct mtk_gen3_pcie *pcie = data->domain->host_data; + unsigned long hwirq, flags; + u32 val; + + hwirq = data->hwirq % PCIE_MSI_IRQS_PER_SET; + + raw_spin_lock_irqsave(&pcie->irq_lock, flags); + val = readl_relaxed(msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + val |= BIT(hwirq); + writel_relaxed(val, msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); +} + +static struct irq_chip mtk_msi_bottom_irq_chip = { + .irq_ack = mtk_msi_bottom_irq_ack, + .irq_mask = mtk_msi_bottom_irq_mask, + .irq_unmask = mtk_msi_bottom_irq_unmask, + .irq_compose_msi_msg = mtk_compose_msi_msg, + .irq_set_affinity = mtk_pcie_set_affinity, + .name = "MSI", +}; + +static int mtk_msi_bottom_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *arg) +{ + struct mtk_gen3_pcie *pcie = domain->host_data; + struct mtk_msi_set *msi_set; + int i, hwirq, set_idx; + + mutex_lock(&pcie->lock); + + hwirq = bitmap_find_free_region(pcie->msi_irq_in_use, PCIE_MSI_IRQS_NUM, + order_base_2(nr_irqs)); + + mutex_unlock(&pcie->lock); + + if (hwirq < 0) + return -ENOSPC; + + set_idx = hwirq / PCIE_MSI_IRQS_PER_SET; + msi_set = &pcie->msi_sets[set_idx]; + + for (i = 0; i < nr_irqs; i++) + irq_domain_set_info(domain, virq + i, hwirq + i, + &mtk_msi_bottom_irq_chip, msi_set, + handle_edge_irq, NULL, NULL); + + return 0; +} + +static void mtk_msi_bottom_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct mtk_gen3_pcie *pcie = domain->host_data; + struct irq_data *data = irq_domain_get_irq_data(domain, virq); + + mutex_lock(&pcie->lock); + + bitmap_release_region(pcie->msi_irq_in_use, data->hwirq, + order_base_2(nr_irqs)); + + mutex_unlock(&pcie->lock); + + irq_domain_free_irqs_common(domain, virq, nr_irqs); +} + +static const struct irq_domain_ops mtk_msi_bottom_domain_ops = { + .alloc = mtk_msi_bottom_domain_alloc, + .free = mtk_msi_bottom_domain_free, +}; + +static void mtk_intx_mask(struct irq_data *data) +{ + struct mtk_gen3_pcie *pcie = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pcie->irq_lock, flags); + val = readl_relaxed(pcie->base + PCIE_INT_ENABLE_REG); + val &= ~BIT(data->hwirq + PCIE_INTX_SHIFT); + writel_relaxed(val, pcie->base + PCIE_INT_ENABLE_REG); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); +} + +static void mtk_intx_unmask(struct irq_data *data) +{ + struct mtk_gen3_pcie *pcie = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pcie->irq_lock, flags); + val = readl_relaxed(pcie->base + PCIE_INT_ENABLE_REG); + val |= BIT(data->hwirq + PCIE_INTX_SHIFT); + writel_relaxed(val, pcie->base + PCIE_INT_ENABLE_REG); + raw_spin_unlock_irqrestore(&pcie->irq_lock, flags); +} + +/** + * mtk_intx_eoi() - Clear INTx IRQ status at the end of interrupt + * @data: pointer to chip specific data + * + * As an emulated level IRQ, its interrupt status will remain + * until the corresponding de-assert message is received; hence that + * the status can only be cleared when the interrupt has been serviced. + */ +static void mtk_intx_eoi(struct irq_data *data) +{ + struct mtk_gen3_pcie *pcie = irq_data_get_irq_chip_data(data); + unsigned long hwirq; + + hwirq = data->hwirq + PCIE_INTX_SHIFT; + writel_relaxed(BIT(hwirq), pcie->base + PCIE_INT_STATUS_REG); +} + +static struct irq_chip mtk_intx_irq_chip = { + .irq_mask = mtk_intx_mask, + .irq_unmask = mtk_intx_unmask, + .irq_eoi = mtk_intx_eoi, + .irq_set_affinity = mtk_pcie_set_affinity, + .name = "INTx", +}; + +static int mtk_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_data(irq, domain->host_data); + irq_set_chip_and_handler_name(irq, &mtk_intx_irq_chip, + handle_fasteoi_irq, "INTx"); + return 0; +} + +static const struct irq_domain_ops intx_domain_ops = { + .map = mtk_pcie_intx_map, +}; + +static int mtk_pcie_init_irq_domains(struct mtk_gen3_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct device_node *intc_node, *node = dev->of_node; + int ret; + + raw_spin_lock_init(&pcie->irq_lock); + + /* Setup INTx */ + intc_node = of_get_child_by_name(node, "interrupt-controller"); + if (!intc_node) { + dev_err(dev, "missing interrupt-controller node\n"); + return -ENODEV; + } + + pcie->intx_domain = irq_domain_add_linear(intc_node, PCI_NUM_INTX, + &intx_domain_ops, pcie); + if (!pcie->intx_domain) { + dev_err(dev, "failed to create INTx IRQ domain\n"); + ret = -ENODEV; + goto out_put_node; + } + + /* Setup MSI */ + mutex_init(&pcie->lock); + + pcie->msi_bottom_domain = irq_domain_add_linear(node, PCIE_MSI_IRQS_NUM, + &mtk_msi_bottom_domain_ops, pcie); + if (!pcie->msi_bottom_domain) { + dev_err(dev, "failed to create MSI bottom domain\n"); + ret = -ENODEV; + goto err_msi_bottom_domain; + } + + pcie->msi_domain = pci_msi_create_irq_domain(dev->fwnode, + &mtk_msi_domain_info, + pcie->msi_bottom_domain); + if (!pcie->msi_domain) { + dev_err(dev, "failed to create MSI domain\n"); + ret = -ENODEV; + goto err_msi_domain; + } + + of_node_put(intc_node); + return 0; + +err_msi_domain: + irq_domain_remove(pcie->msi_bottom_domain); +err_msi_bottom_domain: + irq_domain_remove(pcie->intx_domain); +out_put_node: + of_node_put(intc_node); + return ret; +} + +static void mtk_pcie_irq_teardown(struct mtk_gen3_pcie *pcie) +{ + irq_set_chained_handler_and_data(pcie->irq, NULL, NULL); + + if (pcie->intx_domain) + irq_domain_remove(pcie->intx_domain); + + if (pcie->msi_domain) + irq_domain_remove(pcie->msi_domain); + + if (pcie->msi_bottom_domain) + irq_domain_remove(pcie->msi_bottom_domain); + + irq_dispose_mapping(pcie->irq); +} + +static void mtk_pcie_msi_handler(struct mtk_gen3_pcie *pcie, int set_idx) +{ + struct mtk_msi_set *msi_set = &pcie->msi_sets[set_idx]; + unsigned long msi_enable, msi_status; + irq_hw_number_t bit, hwirq; + + msi_enable = readl_relaxed(msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + + do { + msi_status = readl_relaxed(msi_set->base + + PCIE_MSI_SET_STATUS_OFFSET); + msi_status &= msi_enable; + if (!msi_status) + break; + + for_each_set_bit(bit, &msi_status, PCIE_MSI_IRQS_PER_SET) { + hwirq = bit + set_idx * PCIE_MSI_IRQS_PER_SET; + generic_handle_domain_irq(pcie->msi_bottom_domain, hwirq); + } + } while (true); +} + +static void mtk_pcie_irq_handler(struct irq_desc *desc) +{ + struct mtk_gen3_pcie *pcie = irq_desc_get_handler_data(desc); + struct irq_chip *irqchip = irq_desc_get_chip(desc); + unsigned long status; + irq_hw_number_t irq_bit = PCIE_INTX_SHIFT; + + chained_irq_enter(irqchip, desc); + + status = readl_relaxed(pcie->base + PCIE_INT_STATUS_REG); + for_each_set_bit_from(irq_bit, &status, PCI_NUM_INTX + + PCIE_INTX_SHIFT) + generic_handle_domain_irq(pcie->intx_domain, + irq_bit - PCIE_INTX_SHIFT); + + irq_bit = PCIE_MSI_SHIFT; + for_each_set_bit_from(irq_bit, &status, PCIE_MSI_SET_NUM + + PCIE_MSI_SHIFT) { + mtk_pcie_msi_handler(pcie, irq_bit - PCIE_MSI_SHIFT); + + writel_relaxed(BIT(irq_bit), pcie->base + PCIE_INT_STATUS_REG); + } + + chained_irq_exit(irqchip, desc); +} + +static int mtk_pcie_setup_irq(struct mtk_gen3_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + int err; + + err = mtk_pcie_init_irq_domains(pcie); + if (err) + return err; + + pcie->irq = platform_get_irq(pdev, 0); + if (pcie->irq < 0) + return pcie->irq; + + irq_set_chained_handler_and_data(pcie->irq, mtk_pcie_irq_handler, pcie); + + return 0; +} + +static int mtk_pcie_parse_port(struct mtk_gen3_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + struct resource *regs; + int ret; + + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pcie-mac"); + if (!regs) + return -EINVAL; + pcie->base = devm_ioremap_resource(dev, regs); + if (IS_ERR(pcie->base)) { + dev_err(dev, "failed to map register base\n"); + return PTR_ERR(pcie->base); + } + + pcie->reg_base = regs->start; + + pcie->phy_reset = devm_reset_control_get_optional_exclusive(dev, "phy"); + if (IS_ERR(pcie->phy_reset)) { + ret = PTR_ERR(pcie->phy_reset); + if (ret != -EPROBE_DEFER) + dev_err(dev, "failed to get PHY reset\n"); + + return ret; + } + + pcie->mac_reset = devm_reset_control_get_optional_exclusive(dev, "mac"); + if (IS_ERR(pcie->mac_reset)) { + ret = PTR_ERR(pcie->mac_reset); + if (ret != -EPROBE_DEFER) + dev_err(dev, "failed to get MAC reset\n"); + + return ret; + } + + pcie->phy = devm_phy_optional_get(dev, "pcie-phy"); + if (IS_ERR(pcie->phy)) { + ret = PTR_ERR(pcie->phy); + if (ret != -EPROBE_DEFER) + dev_err(dev, "failed to get PHY\n"); + + return ret; + } + + pcie->num_clks = devm_clk_bulk_get_all(dev, &pcie->clks); + if (pcie->num_clks < 0) { + dev_err(dev, "failed to get clocks\n"); + return pcie->num_clks; + } + + return 0; +} + +static int mtk_pcie_power_up(struct mtk_gen3_pcie *pcie) +{ + struct device *dev = pcie->dev; + int err; + + /* PHY power on and enable pipe clock */ + reset_control_deassert(pcie->phy_reset); + + err = phy_init(pcie->phy); + if (err) { + dev_err(dev, "failed to initialize PHY\n"); + goto err_phy_init; + } + + err = phy_power_on(pcie->phy); + if (err) { + dev_err(dev, "failed to power on PHY\n"); + goto err_phy_on; + } + + /* MAC power on and enable transaction layer clocks */ + reset_control_deassert(pcie->mac_reset); + + pm_runtime_enable(dev); + pm_runtime_get_sync(dev); + + err = clk_bulk_prepare_enable(pcie->num_clks, pcie->clks); + if (err) { + dev_err(dev, "failed to enable clocks\n"); + goto err_clk_init; + } + + return 0; + +err_clk_init: + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); + reset_control_assert(pcie->mac_reset); + phy_power_off(pcie->phy); +err_phy_on: + phy_exit(pcie->phy); +err_phy_init: + reset_control_assert(pcie->phy_reset); + + return err; +} + +static void mtk_pcie_power_down(struct mtk_gen3_pcie *pcie) +{ + clk_bulk_disable_unprepare(pcie->num_clks, pcie->clks); + + pm_runtime_put_sync(pcie->dev); + pm_runtime_disable(pcie->dev); + reset_control_assert(pcie->mac_reset); + + phy_power_off(pcie->phy); + phy_exit(pcie->phy); + reset_control_assert(pcie->phy_reset); +} + +static int mtk_pcie_setup(struct mtk_gen3_pcie *pcie) +{ + int err; + + err = mtk_pcie_parse_port(pcie); + if (err) + return err; + + /* + * The controller may have been left out of reset by the bootloader + * so make sure that we get a clean start by asserting resets here. + */ + reset_control_assert(pcie->phy_reset); + reset_control_assert(pcie->mac_reset); + usleep_range(10, 20); + + /* Don't touch the hardware registers before power up */ + err = mtk_pcie_power_up(pcie); + if (err) + return err; + + /* Try link up */ + err = mtk_pcie_startup_port(pcie); + if (err) + goto err_setup; + + err = mtk_pcie_setup_irq(pcie); + if (err) + goto err_setup; + + return 0; + +err_setup: + mtk_pcie_power_down(pcie); + + return err; +} + +static int mtk_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mtk_gen3_pcie *pcie; + struct pci_host_bridge *host; + int err; + + host = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!host) + return -ENOMEM; + + pcie = pci_host_bridge_priv(host); + + pcie->dev = dev; + platform_set_drvdata(pdev, pcie); + + err = mtk_pcie_setup(pcie); + if (err) + return err; + + host->ops = &mtk_pcie_ops; + host->sysdata = pcie; + + err = pci_host_probe(host); + if (err) { + mtk_pcie_irq_teardown(pcie); + mtk_pcie_power_down(pcie); + return err; + } + + return 0; +} + +static int mtk_pcie_remove(struct platform_device *pdev) +{ + struct mtk_gen3_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + + pci_lock_rescan_remove(); + pci_stop_root_bus(host->bus); + pci_remove_root_bus(host->bus); + pci_unlock_rescan_remove(); + + mtk_pcie_irq_teardown(pcie); + mtk_pcie_power_down(pcie); + + return 0; +} + +static void mtk_pcie_irq_save(struct mtk_gen3_pcie *pcie) +{ + int i; + + raw_spin_lock(&pcie->irq_lock); + + pcie->saved_irq_state = readl_relaxed(pcie->base + PCIE_INT_ENABLE_REG); + + for (i = 0; i < PCIE_MSI_SET_NUM; i++) { + struct mtk_msi_set *msi_set = &pcie->msi_sets[i]; + + msi_set->saved_irq_state = readl_relaxed(msi_set->base + + PCIE_MSI_SET_ENABLE_OFFSET); + } + + raw_spin_unlock(&pcie->irq_lock); +} + +static void mtk_pcie_irq_restore(struct mtk_gen3_pcie *pcie) +{ + int i; + + raw_spin_lock(&pcie->irq_lock); + + writel_relaxed(pcie->saved_irq_state, pcie->base + PCIE_INT_ENABLE_REG); + + for (i = 0; i < PCIE_MSI_SET_NUM; i++) { + struct mtk_msi_set *msi_set = &pcie->msi_sets[i]; + + writel_relaxed(msi_set->saved_irq_state, + msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET); + } + + raw_spin_unlock(&pcie->irq_lock); +} + +static int mtk_pcie_turn_off_link(struct mtk_gen3_pcie *pcie) +{ + u32 val; + + val = readl_relaxed(pcie->base + PCIE_ICMD_PM_REG); + val |= PCIE_TURN_OFF_LINK; + writel_relaxed(val, pcie->base + PCIE_ICMD_PM_REG); + + /* Check the link is L2 */ + return readl_poll_timeout(pcie->base + PCIE_LTSSM_STATUS_REG, val, + (PCIE_LTSSM_STATE(val) == + PCIE_LTSSM_STATE_L2_IDLE), 20, + 50 * USEC_PER_MSEC); +} + +static int mtk_pcie_suspend_noirq(struct device *dev) +{ + struct mtk_gen3_pcie *pcie = dev_get_drvdata(dev); + int err; + u32 val; + + /* Trigger link to L2 state */ + err = mtk_pcie_turn_off_link(pcie); + if (err) { + dev_err(pcie->dev, "cannot enter L2 state\n"); + return err; + } + + /* Pull down the PERST# pin */ + val = readl_relaxed(pcie->base + PCIE_RST_CTRL_REG); + val |= PCIE_PE_RSTB; + writel_relaxed(val, pcie->base + PCIE_RST_CTRL_REG); + + dev_dbg(pcie->dev, "entered L2 states successfully"); + + mtk_pcie_irq_save(pcie); + mtk_pcie_power_down(pcie); + + return 0; +} + +static int mtk_pcie_resume_noirq(struct device *dev) +{ + struct mtk_gen3_pcie *pcie = dev_get_drvdata(dev); + int err; + + err = mtk_pcie_power_up(pcie); + if (err) + return err; + + err = mtk_pcie_startup_port(pcie); + if (err) { + mtk_pcie_power_down(pcie); + return err; + } + + mtk_pcie_irq_restore(pcie); + + return 0; +} + +static const struct dev_pm_ops mtk_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_pcie_suspend_noirq, + mtk_pcie_resume_noirq) +}; + +static const struct of_device_id mtk_pcie_of_match[] = { + { .compatible = "mediatek,mt8192-pcie" }, + {}, +}; +MODULE_DEVICE_TABLE(of, mtk_pcie_of_match); + +static struct platform_driver mtk_pcie_driver = { + .probe = mtk_pcie_probe, + .remove = mtk_pcie_remove, + .driver = { + .name = "mtk-pcie-gen3", + .of_match_table = mtk_pcie_of_match, + .pm = &mtk_pcie_pm_ops, + }, +}; + +module_platform_driver(mtk_pcie_driver); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c new file mode 100644 index 000000000..11bdef206 --- /dev/null +++ b/drivers/pci/controller/pcie-mediatek.c @@ -0,0 +1,1257 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * MediaTek PCIe host controller driver. + * + * Copyright (c) 2017 MediaTek Inc. + * Author: Ryder Lee <ryder.lee@mediatek.com> + * Honghui Zhang <honghui.zhang@mediatek.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/iopoll.h> +#include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/msi.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> +#include <linux/reset.h> + +#include "../pci.h" + +/* PCIe shared registers */ +#define PCIE_SYS_CFG 0x00 +#define PCIE_INT_ENABLE 0x0c +#define PCIE_CFG_ADDR 0x20 +#define PCIE_CFG_DATA 0x24 + +/* PCIe per port registers */ +#define PCIE_BAR0_SETUP 0x10 +#define PCIE_CLASS 0x34 +#define PCIE_LINK_STATUS 0x50 + +#define PCIE_PORT_INT_EN(x) BIT(20 + (x)) +#define PCIE_PORT_PERST(x) BIT(1 + (x)) +#define PCIE_PORT_LINKUP BIT(0) +#define PCIE_BAR_MAP_MAX GENMASK(31, 16) + +#define PCIE_BAR_ENABLE BIT(0) +#define PCIE_REVISION_ID BIT(0) +#define PCIE_CLASS_CODE (0x60400 << 8) +#define PCIE_CONF_REG(regn) (((regn) & GENMASK(7, 2)) | \ + ((((regn) >> 8) & GENMASK(3, 0)) << 24)) +#define PCIE_CONF_FUN(fun) (((fun) << 8) & GENMASK(10, 8)) +#define PCIE_CONF_DEV(dev) (((dev) << 11) & GENMASK(15, 11)) +#define PCIE_CONF_BUS(bus) (((bus) << 16) & GENMASK(23, 16)) +#define PCIE_CONF_ADDR(regn, fun, dev, bus) \ + (PCIE_CONF_REG(regn) | PCIE_CONF_FUN(fun) | \ + PCIE_CONF_DEV(dev) | PCIE_CONF_BUS(bus)) + +/* MediaTek specific configuration registers */ +#define PCIE_FTS_NUM 0x70c +#define PCIE_FTS_NUM_MASK GENMASK(15, 8) +#define PCIE_FTS_NUM_L0(x) ((x) & 0xff << 8) + +#define PCIE_FC_CREDIT 0x73c +#define PCIE_FC_CREDIT_MASK (GENMASK(31, 31) | GENMASK(28, 16)) +#define PCIE_FC_CREDIT_VAL(x) ((x) << 16) + +/* PCIe V2 share registers */ +#define PCIE_SYS_CFG_V2 0x0 +#define PCIE_CSR_LTSSM_EN(x) BIT(0 + (x) * 8) +#define PCIE_CSR_ASPM_L1_EN(x) BIT(1 + (x) * 8) + +/* PCIe V2 per-port registers */ +#define PCIE_MSI_VECTOR 0x0c0 + +#define PCIE_CONF_VEND_ID 0x100 +#define PCIE_CONF_DEVICE_ID 0x102 +#define PCIE_CONF_CLASS_ID 0x106 + +#define PCIE_INT_MASK 0x420 +#define INTX_MASK GENMASK(19, 16) +#define INTX_SHIFT 16 +#define PCIE_INT_STATUS 0x424 +#define MSI_STATUS BIT(23) +#define PCIE_IMSI_STATUS 0x42c +#define PCIE_IMSI_ADDR 0x430 +#define MSI_MASK BIT(23) +#define MTK_MSI_IRQS_NUM 32 + +#define PCIE_AHB_TRANS_BASE0_L 0x438 +#define PCIE_AHB_TRANS_BASE0_H 0x43c +#define AHB2PCIE_SIZE(x) ((x) & GENMASK(4, 0)) +#define PCIE_AXI_WINDOW0 0x448 +#define WIN_ENABLE BIT(7) +/* + * Define PCIe to AHB window size as 2^33 to support max 8GB address space + * translate, support least 4GB DRAM size access from EP DMA(physical DRAM + * start from 0x40000000). + */ +#define PCIE2AHB_SIZE 0x21 + +/* PCIe V2 configuration transaction header */ +#define PCIE_CFG_HEADER0 0x460 +#define PCIE_CFG_HEADER1 0x464 +#define PCIE_CFG_HEADER2 0x468 +#define PCIE_CFG_WDATA 0x470 +#define PCIE_APP_TLP_REQ 0x488 +#define PCIE_CFG_RDATA 0x48c +#define APP_CFG_REQ BIT(0) +#define APP_CPL_STATUS GENMASK(7, 5) + +#define CFG_WRRD_TYPE_0 4 +#define CFG_WR_FMT 2 +#define CFG_RD_FMT 0 + +#define CFG_DW0_LENGTH(length) ((length) & GENMASK(9, 0)) +#define CFG_DW0_TYPE(type) (((type) << 24) & GENMASK(28, 24)) +#define CFG_DW0_FMT(fmt) (((fmt) << 29) & GENMASK(31, 29)) +#define CFG_DW2_REGN(regn) ((regn) & GENMASK(11, 2)) +#define CFG_DW2_FUN(fun) (((fun) << 16) & GENMASK(18, 16)) +#define CFG_DW2_DEV(dev) (((dev) << 19) & GENMASK(23, 19)) +#define CFG_DW2_BUS(bus) (((bus) << 24) & GENMASK(31, 24)) +#define CFG_HEADER_DW0(type, fmt) \ + (CFG_DW0_LENGTH(1) | CFG_DW0_TYPE(type) | CFG_DW0_FMT(fmt)) +#define CFG_HEADER_DW1(where, size) \ + (GENMASK(((size) - 1), 0) << ((where) & 0x3)) +#define CFG_HEADER_DW2(regn, fun, dev, bus) \ + (CFG_DW2_REGN(regn) | CFG_DW2_FUN(fun) | \ + CFG_DW2_DEV(dev) | CFG_DW2_BUS(bus)) + +#define PCIE_RST_CTRL 0x510 +#define PCIE_PHY_RSTB BIT(0) +#define PCIE_PIPE_SRSTB BIT(1) +#define PCIE_MAC_SRSTB BIT(2) +#define PCIE_CRSTB BIT(3) +#define PCIE_PERSTB BIT(8) +#define PCIE_LINKDOWN_RST_EN GENMASK(15, 13) +#define PCIE_LINK_STATUS_V2 0x804 +#define PCIE_PORT_LINKUP_V2 BIT(10) + +struct mtk_pcie_port; + +/** + * struct mtk_pcie_soc - differentiate between host generations + * @need_fix_class_id: whether this host's class ID needed to be fixed or not + * @need_fix_device_id: whether this host's device ID needed to be fixed or not + * @no_msi: Bridge has no MSI support, and relies on an external block + * @device_id: device ID which this host need to be fixed + * @ops: pointer to configuration access functions + * @startup: pointer to controller setting functions + * @setup_irq: pointer to initialize IRQ functions + */ +struct mtk_pcie_soc { + bool need_fix_class_id; + bool need_fix_device_id; + bool no_msi; + unsigned int device_id; + struct pci_ops *ops; + int (*startup)(struct mtk_pcie_port *port); + int (*setup_irq)(struct mtk_pcie_port *port, struct device_node *node); +}; + +/** + * struct mtk_pcie_port - PCIe port information + * @base: IO mapped register base + * @list: port list + * @pcie: pointer to PCIe host info + * @reset: pointer to port reset control + * @sys_ck: pointer to transaction/data link layer clock + * @ahb_ck: pointer to AHB slave interface operating clock for CSR access + * and RC initiated MMIO access + * @axi_ck: pointer to application layer MMIO channel operating clock + * @aux_ck: pointer to pe2_mac_bridge and pe2_mac_core operating clock + * when pcie_mac_ck/pcie_pipe_ck is turned off + * @obff_ck: pointer to OBFF functional block operating clock + * @pipe_ck: pointer to LTSSM and PHY/MAC layer operating clock + * @phy: pointer to PHY control block + * @slot: port slot + * @irq: GIC irq + * @irq_domain: legacy INTx IRQ domain + * @inner_domain: inner IRQ domain + * @msi_domain: MSI IRQ domain + * @lock: protect the msi_irq_in_use bitmap + * @msi_irq_in_use: bit map for assigned MSI IRQ + */ +struct mtk_pcie_port { + void __iomem *base; + struct list_head list; + struct mtk_pcie *pcie; + struct reset_control *reset; + struct clk *sys_ck; + struct clk *ahb_ck; + struct clk *axi_ck; + struct clk *aux_ck; + struct clk *obff_ck; + struct clk *pipe_ck; + struct phy *phy; + u32 slot; + int irq; + struct irq_domain *irq_domain; + struct irq_domain *inner_domain; + struct irq_domain *msi_domain; + struct mutex lock; + DECLARE_BITMAP(msi_irq_in_use, MTK_MSI_IRQS_NUM); +}; + +/** + * struct mtk_pcie - PCIe host information + * @dev: pointer to PCIe device + * @base: IO mapped register base + * @cfg: IO mapped register map for PCIe config + * @free_ck: free-run reference clock + * @mem: non-prefetchable memory resource + * @ports: pointer to PCIe port information + * @soc: pointer to SoC-dependent operations + */ +struct mtk_pcie { + struct device *dev; + void __iomem *base; + struct regmap *cfg; + struct clk *free_ck; + + struct list_head ports; + const struct mtk_pcie_soc *soc; +}; + +static void mtk_pcie_subsys_powerdown(struct mtk_pcie *pcie) +{ + struct device *dev = pcie->dev; + + clk_disable_unprepare(pcie->free_ck); + + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); +} + +static void mtk_pcie_port_free(struct mtk_pcie_port *port) +{ + struct mtk_pcie *pcie = port->pcie; + struct device *dev = pcie->dev; + + devm_iounmap(dev, port->base); + list_del(&port->list); + devm_kfree(dev, port); +} + +static void mtk_pcie_put_resources(struct mtk_pcie *pcie) +{ + struct mtk_pcie_port *port, *tmp; + + list_for_each_entry_safe(port, tmp, &pcie->ports, list) { + phy_power_off(port->phy); + phy_exit(port->phy); + clk_disable_unprepare(port->pipe_ck); + clk_disable_unprepare(port->obff_ck); + clk_disable_unprepare(port->axi_ck); + clk_disable_unprepare(port->aux_ck); + clk_disable_unprepare(port->ahb_ck); + clk_disable_unprepare(port->sys_ck); + mtk_pcie_port_free(port); + } + + mtk_pcie_subsys_powerdown(pcie); +} + +static int mtk_pcie_check_cfg_cpld(struct mtk_pcie_port *port) +{ + u32 val; + int err; + + err = readl_poll_timeout_atomic(port->base + PCIE_APP_TLP_REQ, val, + !(val & APP_CFG_REQ), 10, + 100 * USEC_PER_MSEC); + if (err) + return PCIBIOS_SET_FAILED; + + if (readl(port->base + PCIE_APP_TLP_REQ) & APP_CPL_STATUS) + return PCIBIOS_SET_FAILED; + + return PCIBIOS_SUCCESSFUL; +} + +static int mtk_pcie_hw_rd_cfg(struct mtk_pcie_port *port, u32 bus, u32 devfn, + int where, int size, u32 *val) +{ + u32 tmp; + + /* Write PCIe configuration transaction header for Cfgrd */ + writel(CFG_HEADER_DW0(CFG_WRRD_TYPE_0, CFG_RD_FMT), + port->base + PCIE_CFG_HEADER0); + writel(CFG_HEADER_DW1(where, size), port->base + PCIE_CFG_HEADER1); + writel(CFG_HEADER_DW2(where, PCI_FUNC(devfn), PCI_SLOT(devfn), bus), + port->base + PCIE_CFG_HEADER2); + + /* Trigger h/w to transmit Cfgrd TLP */ + tmp = readl(port->base + PCIE_APP_TLP_REQ); + tmp |= APP_CFG_REQ; + writel(tmp, port->base + PCIE_APP_TLP_REQ); + + /* Check completion status */ + if (mtk_pcie_check_cfg_cpld(port)) + return PCIBIOS_SET_FAILED; + + /* Read cpld payload of Cfgrd */ + *val = readl(port->base + PCIE_CFG_RDATA); + + if (size == 1) + *val = (*val >> (8 * (where & 3))) & 0xff; + else if (size == 2) + *val = (*val >> (8 * (where & 3))) & 0xffff; + + return PCIBIOS_SUCCESSFUL; +} + +static int mtk_pcie_hw_wr_cfg(struct mtk_pcie_port *port, u32 bus, u32 devfn, + int where, int size, u32 val) +{ + /* Write PCIe configuration transaction header for Cfgwr */ + writel(CFG_HEADER_DW0(CFG_WRRD_TYPE_0, CFG_WR_FMT), + port->base + PCIE_CFG_HEADER0); + writel(CFG_HEADER_DW1(where, size), port->base + PCIE_CFG_HEADER1); + writel(CFG_HEADER_DW2(where, PCI_FUNC(devfn), PCI_SLOT(devfn), bus), + port->base + PCIE_CFG_HEADER2); + + /* Write Cfgwr data */ + val = val << 8 * (where & 3); + writel(val, port->base + PCIE_CFG_WDATA); + + /* Trigger h/w to transmit Cfgwr TLP */ + val = readl(port->base + PCIE_APP_TLP_REQ); + val |= APP_CFG_REQ; + writel(val, port->base + PCIE_APP_TLP_REQ); + + /* Check completion status */ + return mtk_pcie_check_cfg_cpld(port); +} + +static struct mtk_pcie_port *mtk_pcie_find_port(struct pci_bus *bus, + unsigned int devfn) +{ + struct mtk_pcie *pcie = bus->sysdata; + struct mtk_pcie_port *port; + struct pci_dev *dev = NULL; + + /* + * Walk the bus hierarchy to get the devfn value + * of the port in the root bus. + */ + while (bus && bus->number) { + dev = bus->self; + bus = dev->bus; + devfn = dev->devfn; + } + + list_for_each_entry(port, &pcie->ports, list) + if (port->slot == PCI_SLOT(devfn)) + return port; + + return NULL; +} + +static int mtk_pcie_config_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct mtk_pcie_port *port; + u32 bn = bus->number; + + port = mtk_pcie_find_port(bus, devfn); + if (!port) + return PCIBIOS_DEVICE_NOT_FOUND; + + return mtk_pcie_hw_rd_cfg(port, bn, devfn, where, size, val); +} + +static int mtk_pcie_config_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct mtk_pcie_port *port; + u32 bn = bus->number; + + port = mtk_pcie_find_port(bus, devfn); + if (!port) + return PCIBIOS_DEVICE_NOT_FOUND; + + return mtk_pcie_hw_wr_cfg(port, bn, devfn, where, size, val); +} + +static struct pci_ops mtk_pcie_ops_v2 = { + .read = mtk_pcie_config_read, + .write = mtk_pcie_config_write, +}; + +static void mtk_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct mtk_pcie_port *port = irq_data_get_irq_chip_data(data); + phys_addr_t addr; + + /* MT2712/MT7622 only support 32-bit MSI addresses */ + addr = virt_to_phys(port->base + PCIE_MSI_VECTOR); + msg->address_hi = 0; + msg->address_lo = lower_32_bits(addr); + + msg->data = data->hwirq; + + dev_dbg(port->pcie->dev, "msi#%d address_hi %#x address_lo %#x\n", + (int)data->hwirq, msg->address_hi, msg->address_lo); +} + +static int mtk_msi_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static void mtk_msi_ack_irq(struct irq_data *data) +{ + struct mtk_pcie_port *port = irq_data_get_irq_chip_data(data); + u32 hwirq = data->hwirq; + + writel(1 << hwirq, port->base + PCIE_IMSI_STATUS); +} + +static struct irq_chip mtk_msi_bottom_irq_chip = { + .name = "MTK MSI", + .irq_compose_msi_msg = mtk_compose_msi_msg, + .irq_set_affinity = mtk_msi_set_affinity, + .irq_ack = mtk_msi_ack_irq, +}; + +static int mtk_pcie_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct mtk_pcie_port *port = domain->host_data; + unsigned long bit; + + WARN_ON(nr_irqs != 1); + mutex_lock(&port->lock); + + bit = find_first_zero_bit(port->msi_irq_in_use, MTK_MSI_IRQS_NUM); + if (bit >= MTK_MSI_IRQS_NUM) { + mutex_unlock(&port->lock); + return -ENOSPC; + } + + __set_bit(bit, port->msi_irq_in_use); + + mutex_unlock(&port->lock); + + irq_domain_set_info(domain, virq, bit, &mtk_msi_bottom_irq_chip, + domain->host_data, handle_edge_irq, + NULL, NULL); + + return 0; +} + +static void mtk_pcie_irq_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct mtk_pcie_port *port = irq_data_get_irq_chip_data(d); + + mutex_lock(&port->lock); + + if (!test_bit(d->hwirq, port->msi_irq_in_use)) + dev_err(port->pcie->dev, "trying to free unused MSI#%lu\n", + d->hwirq); + else + __clear_bit(d->hwirq, port->msi_irq_in_use); + + mutex_unlock(&port->lock); + + irq_domain_free_irqs_parent(domain, virq, nr_irqs); +} + +static const struct irq_domain_ops msi_domain_ops = { + .alloc = mtk_pcie_irq_domain_alloc, + .free = mtk_pcie_irq_domain_free, +}; + +static struct irq_chip mtk_msi_irq_chip = { + .name = "MTK PCIe MSI", + .irq_ack = irq_chip_ack_parent, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, +}; + +static struct msi_domain_info mtk_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX), + .chip = &mtk_msi_irq_chip, +}; + +static int mtk_pcie_allocate_msi_domains(struct mtk_pcie_port *port) +{ + struct fwnode_handle *fwnode = of_node_to_fwnode(port->pcie->dev->of_node); + + mutex_init(&port->lock); + + port->inner_domain = irq_domain_create_linear(fwnode, MTK_MSI_IRQS_NUM, + &msi_domain_ops, port); + if (!port->inner_domain) { + dev_err(port->pcie->dev, "failed to create IRQ domain\n"); + return -ENOMEM; + } + + port->msi_domain = pci_msi_create_irq_domain(fwnode, &mtk_msi_domain_info, + port->inner_domain); + if (!port->msi_domain) { + dev_err(port->pcie->dev, "failed to create MSI domain\n"); + irq_domain_remove(port->inner_domain); + return -ENOMEM; + } + + return 0; +} + +static void mtk_pcie_enable_msi(struct mtk_pcie_port *port) +{ + u32 val; + phys_addr_t msg_addr; + + msg_addr = virt_to_phys(port->base + PCIE_MSI_VECTOR); + val = lower_32_bits(msg_addr); + writel(val, port->base + PCIE_IMSI_ADDR); + + val = readl(port->base + PCIE_INT_MASK); + val &= ~MSI_MASK; + writel(val, port->base + PCIE_INT_MASK); +} + +static void mtk_pcie_irq_teardown(struct mtk_pcie *pcie) +{ + struct mtk_pcie_port *port, *tmp; + + list_for_each_entry_safe(port, tmp, &pcie->ports, list) { + irq_set_chained_handler_and_data(port->irq, NULL, NULL); + + if (port->irq_domain) + irq_domain_remove(port->irq_domain); + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + if (port->msi_domain) + irq_domain_remove(port->msi_domain); + if (port->inner_domain) + irq_domain_remove(port->inner_domain); + } + + irq_dispose_mapping(port->irq); + } +} + +static int mtk_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &dummy_irq_chip, handle_simple_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops intx_domain_ops = { + .map = mtk_pcie_intx_map, +}; + +static int mtk_pcie_init_irq_domain(struct mtk_pcie_port *port, + struct device_node *node) +{ + struct device *dev = port->pcie->dev; + struct device_node *pcie_intc_node; + int ret; + + /* Setup INTx */ + pcie_intc_node = of_get_next_child(node, NULL); + if (!pcie_intc_node) { + dev_err(dev, "no PCIe Intc node found\n"); + return -ENODEV; + } + + port->irq_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, + &intx_domain_ops, port); + of_node_put(pcie_intc_node); + if (!port->irq_domain) { + dev_err(dev, "failed to get INTx IRQ domain\n"); + return -ENODEV; + } + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + ret = mtk_pcie_allocate_msi_domains(port); + if (ret) + return ret; + } + + return 0; +} + +static void mtk_pcie_intr_handler(struct irq_desc *desc) +{ + struct mtk_pcie_port *port = irq_desc_get_handler_data(desc); + struct irq_chip *irqchip = irq_desc_get_chip(desc); + unsigned long status; + u32 bit = INTX_SHIFT; + + chained_irq_enter(irqchip, desc); + + status = readl(port->base + PCIE_INT_STATUS); + if (status & INTX_MASK) { + for_each_set_bit_from(bit, &status, PCI_NUM_INTX + INTX_SHIFT) { + /* Clear the INTx */ + writel(1 << bit, port->base + PCIE_INT_STATUS); + generic_handle_domain_irq(port->irq_domain, + bit - INTX_SHIFT); + } + } + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + if (status & MSI_STATUS){ + unsigned long imsi_status; + + /* + * The interrupt status can be cleared even if the + * MSI status remains pending. As such, given the + * edge-triggered interrupt type, its status should + * be cleared before being dispatched to the + * handler of the underlying device. + */ + writel(MSI_STATUS, port->base + PCIE_INT_STATUS); + while ((imsi_status = readl(port->base + PCIE_IMSI_STATUS))) { + for_each_set_bit(bit, &imsi_status, MTK_MSI_IRQS_NUM) + generic_handle_domain_irq(port->inner_domain, bit); + } + } + } + + chained_irq_exit(irqchip, desc); +} + +static int mtk_pcie_setup_irq(struct mtk_pcie_port *port, + struct device_node *node) +{ + struct mtk_pcie *pcie = port->pcie; + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + int err; + + err = mtk_pcie_init_irq_domain(port, node); + if (err) { + dev_err(dev, "failed to init PCIe IRQ domain\n"); + return err; + } + + if (of_find_property(dev->of_node, "interrupt-names", NULL)) + port->irq = platform_get_irq_byname(pdev, "pcie_irq"); + else + port->irq = platform_get_irq(pdev, port->slot); + + if (port->irq < 0) + return port->irq; + + irq_set_chained_handler_and_data(port->irq, + mtk_pcie_intr_handler, port); + + return 0; +} + +static int mtk_pcie_startup_port_v2(struct mtk_pcie_port *port) +{ + struct mtk_pcie *pcie = port->pcie; + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + struct resource *mem = NULL; + struct resource_entry *entry; + const struct mtk_pcie_soc *soc = port->pcie->soc; + u32 val; + int err; + + entry = resource_list_first_type(&host->windows, IORESOURCE_MEM); + if (entry) + mem = entry->res; + if (!mem) + return -EINVAL; + + /* MT7622 platforms need to enable LTSSM and ASPM from PCIe subsys */ + if (pcie->base) { + val = readl(pcie->base + PCIE_SYS_CFG_V2); + val |= PCIE_CSR_LTSSM_EN(port->slot) | + PCIE_CSR_ASPM_L1_EN(port->slot); + writel(val, pcie->base + PCIE_SYS_CFG_V2); + } else if (pcie->cfg) { + val = PCIE_CSR_LTSSM_EN(port->slot) | + PCIE_CSR_ASPM_L1_EN(port->slot); + regmap_update_bits(pcie->cfg, PCIE_SYS_CFG_V2, val, val); + } + + /* Assert all reset signals */ + writel(0, port->base + PCIE_RST_CTRL); + + /* + * Enable PCIe link down reset, if link status changed from link up to + * link down, this will reset MAC control registers and configuration + * space. + */ + writel(PCIE_LINKDOWN_RST_EN, port->base + PCIE_RST_CTRL); + + /* + * Described in PCIe CEM specification sections 2.2 (PERST# Signal) and + * 2.2.1 (Initial Power-Up (G3 to S0)). The deassertion of PERST# should + * be delayed 100ms (TPVPERL) for the power and clock to become stable. + */ + msleep(100); + + /* De-assert PHY, PE, PIPE, MAC and configuration reset */ + val = readl(port->base + PCIE_RST_CTRL); + val |= PCIE_PHY_RSTB | PCIE_PERSTB | PCIE_PIPE_SRSTB | + PCIE_MAC_SRSTB | PCIE_CRSTB; + writel(val, port->base + PCIE_RST_CTRL); + + /* Set up vendor ID and class code */ + if (soc->need_fix_class_id) { + val = PCI_VENDOR_ID_MEDIATEK; + writew(val, port->base + PCIE_CONF_VEND_ID); + + val = PCI_CLASS_BRIDGE_PCI; + writew(val, port->base + PCIE_CONF_CLASS_ID); + } + + if (soc->need_fix_device_id) + writew(soc->device_id, port->base + PCIE_CONF_DEVICE_ID); + + /* 100ms timeout value should be enough for Gen1/2 training */ + err = readl_poll_timeout(port->base + PCIE_LINK_STATUS_V2, val, + !!(val & PCIE_PORT_LINKUP_V2), 20, + 100 * USEC_PER_MSEC); + if (err) + return -ETIMEDOUT; + + /* Set INTx mask */ + val = readl(port->base + PCIE_INT_MASK); + val &= ~INTX_MASK; + writel(val, port->base + PCIE_INT_MASK); + + if (IS_ENABLED(CONFIG_PCI_MSI)) + mtk_pcie_enable_msi(port); + + /* Set AHB to PCIe translation windows */ + val = lower_32_bits(mem->start) | + AHB2PCIE_SIZE(fls(resource_size(mem))); + writel(val, port->base + PCIE_AHB_TRANS_BASE0_L); + + val = upper_32_bits(mem->start); + writel(val, port->base + PCIE_AHB_TRANS_BASE0_H); + + /* Set PCIe to AXI translation memory space.*/ + val = PCIE2AHB_SIZE | WIN_ENABLE; + writel(val, port->base + PCIE_AXI_WINDOW0); + + return 0; +} + +static void __iomem *mtk_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct mtk_pcie *pcie = bus->sysdata; + + writel(PCIE_CONF_ADDR(where, PCI_FUNC(devfn), PCI_SLOT(devfn), + bus->number), pcie->base + PCIE_CFG_ADDR); + + return pcie->base + PCIE_CFG_DATA + (where & 3); +} + +static struct pci_ops mtk_pcie_ops = { + .map_bus = mtk_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static int mtk_pcie_startup_port(struct mtk_pcie_port *port) +{ + struct mtk_pcie *pcie = port->pcie; + u32 func = PCI_FUNC(port->slot); + u32 slot = PCI_SLOT(port->slot << 3); + u32 val; + int err; + + /* assert port PERST_N */ + val = readl(pcie->base + PCIE_SYS_CFG); + val |= PCIE_PORT_PERST(port->slot); + writel(val, pcie->base + PCIE_SYS_CFG); + + /* de-assert port PERST_N */ + val = readl(pcie->base + PCIE_SYS_CFG); + val &= ~PCIE_PORT_PERST(port->slot); + writel(val, pcie->base + PCIE_SYS_CFG); + + /* 100ms timeout value should be enough for Gen1/2 training */ + err = readl_poll_timeout(port->base + PCIE_LINK_STATUS, val, + !!(val & PCIE_PORT_LINKUP), 20, + 100 * USEC_PER_MSEC); + if (err) + return -ETIMEDOUT; + + /* enable interrupt */ + val = readl(pcie->base + PCIE_INT_ENABLE); + val |= PCIE_PORT_INT_EN(port->slot); + writel(val, pcie->base + PCIE_INT_ENABLE); + + /* map to all DDR region. We need to set it before cfg operation. */ + writel(PCIE_BAR_MAP_MAX | PCIE_BAR_ENABLE, + port->base + PCIE_BAR0_SETUP); + + /* configure class code and revision ID */ + writel(PCIE_CLASS_CODE | PCIE_REVISION_ID, port->base + PCIE_CLASS); + + /* configure FC credit */ + writel(PCIE_CONF_ADDR(PCIE_FC_CREDIT, func, slot, 0), + pcie->base + PCIE_CFG_ADDR); + val = readl(pcie->base + PCIE_CFG_DATA); + val &= ~PCIE_FC_CREDIT_MASK; + val |= PCIE_FC_CREDIT_VAL(0x806c); + writel(PCIE_CONF_ADDR(PCIE_FC_CREDIT, func, slot, 0), + pcie->base + PCIE_CFG_ADDR); + writel(val, pcie->base + PCIE_CFG_DATA); + + /* configure RC FTS number to 250 when it leaves L0s */ + writel(PCIE_CONF_ADDR(PCIE_FTS_NUM, func, slot, 0), + pcie->base + PCIE_CFG_ADDR); + val = readl(pcie->base + PCIE_CFG_DATA); + val &= ~PCIE_FTS_NUM_MASK; + val |= PCIE_FTS_NUM_L0(0x50); + writel(PCIE_CONF_ADDR(PCIE_FTS_NUM, func, slot, 0), + pcie->base + PCIE_CFG_ADDR); + writel(val, pcie->base + PCIE_CFG_DATA); + + return 0; +} + +static void mtk_pcie_enable_port(struct mtk_pcie_port *port) +{ + struct mtk_pcie *pcie = port->pcie; + struct device *dev = pcie->dev; + int err; + + err = clk_prepare_enable(port->sys_ck); + if (err) { + dev_err(dev, "failed to enable sys_ck%d clock\n", port->slot); + goto err_sys_clk; + } + + err = clk_prepare_enable(port->ahb_ck); + if (err) { + dev_err(dev, "failed to enable ahb_ck%d\n", port->slot); + goto err_ahb_clk; + } + + err = clk_prepare_enable(port->aux_ck); + if (err) { + dev_err(dev, "failed to enable aux_ck%d\n", port->slot); + goto err_aux_clk; + } + + err = clk_prepare_enable(port->axi_ck); + if (err) { + dev_err(dev, "failed to enable axi_ck%d\n", port->slot); + goto err_axi_clk; + } + + err = clk_prepare_enable(port->obff_ck); + if (err) { + dev_err(dev, "failed to enable obff_ck%d\n", port->slot); + goto err_obff_clk; + } + + err = clk_prepare_enable(port->pipe_ck); + if (err) { + dev_err(dev, "failed to enable pipe_ck%d\n", port->slot); + goto err_pipe_clk; + } + + reset_control_assert(port->reset); + reset_control_deassert(port->reset); + + err = phy_init(port->phy); + if (err) { + dev_err(dev, "failed to initialize port%d phy\n", port->slot); + goto err_phy_init; + } + + err = phy_power_on(port->phy); + if (err) { + dev_err(dev, "failed to power on port%d phy\n", port->slot); + goto err_phy_on; + } + + if (!pcie->soc->startup(port)) + return; + + dev_info(dev, "Port%d link down\n", port->slot); + + phy_power_off(port->phy); +err_phy_on: + phy_exit(port->phy); +err_phy_init: + clk_disable_unprepare(port->pipe_ck); +err_pipe_clk: + clk_disable_unprepare(port->obff_ck); +err_obff_clk: + clk_disable_unprepare(port->axi_ck); +err_axi_clk: + clk_disable_unprepare(port->aux_ck); +err_aux_clk: + clk_disable_unprepare(port->ahb_ck); +err_ahb_clk: + clk_disable_unprepare(port->sys_ck); +err_sys_clk: + mtk_pcie_port_free(port); +} + +static int mtk_pcie_parse_port(struct mtk_pcie *pcie, + struct device_node *node, + int slot) +{ + struct mtk_pcie_port *port; + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + char name[10]; + int err; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + snprintf(name, sizeof(name), "port%d", slot); + port->base = devm_platform_ioremap_resource_byname(pdev, name); + if (IS_ERR(port->base)) { + dev_err(dev, "failed to map port%d base\n", slot); + return PTR_ERR(port->base); + } + + snprintf(name, sizeof(name), "sys_ck%d", slot); + port->sys_ck = devm_clk_get(dev, name); + if (IS_ERR(port->sys_ck)) { + dev_err(dev, "failed to get sys_ck%d clock\n", slot); + return PTR_ERR(port->sys_ck); + } + + /* sys_ck might be divided into the following parts in some chips */ + snprintf(name, sizeof(name), "ahb_ck%d", slot); + port->ahb_ck = devm_clk_get_optional(dev, name); + if (IS_ERR(port->ahb_ck)) + return PTR_ERR(port->ahb_ck); + + snprintf(name, sizeof(name), "axi_ck%d", slot); + port->axi_ck = devm_clk_get_optional(dev, name); + if (IS_ERR(port->axi_ck)) + return PTR_ERR(port->axi_ck); + + snprintf(name, sizeof(name), "aux_ck%d", slot); + port->aux_ck = devm_clk_get_optional(dev, name); + if (IS_ERR(port->aux_ck)) + return PTR_ERR(port->aux_ck); + + snprintf(name, sizeof(name), "obff_ck%d", slot); + port->obff_ck = devm_clk_get_optional(dev, name); + if (IS_ERR(port->obff_ck)) + return PTR_ERR(port->obff_ck); + + snprintf(name, sizeof(name), "pipe_ck%d", slot); + port->pipe_ck = devm_clk_get_optional(dev, name); + if (IS_ERR(port->pipe_ck)) + return PTR_ERR(port->pipe_ck); + + snprintf(name, sizeof(name), "pcie-rst%d", slot); + port->reset = devm_reset_control_get_optional_exclusive(dev, name); + if (PTR_ERR(port->reset) == -EPROBE_DEFER) + return PTR_ERR(port->reset); + + /* some platforms may use default PHY setting */ + snprintf(name, sizeof(name), "pcie-phy%d", slot); + port->phy = devm_phy_optional_get(dev, name); + if (IS_ERR(port->phy)) + return PTR_ERR(port->phy); + + port->slot = slot; + port->pcie = pcie; + + if (pcie->soc->setup_irq) { + err = pcie->soc->setup_irq(port, node); + if (err) + return err; + } + + INIT_LIST_HEAD(&port->list); + list_add_tail(&port->list, &pcie->ports); + + return 0; +} + +static int mtk_pcie_subsys_powerup(struct mtk_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + struct resource *regs; + struct device_node *cfg_node; + int err; + + /* get shared registers, which are optional */ + regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "subsys"); + if (regs) { + pcie->base = devm_ioremap_resource(dev, regs); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + } + + cfg_node = of_find_compatible_node(NULL, NULL, + "mediatek,generic-pciecfg"); + if (cfg_node) { + pcie->cfg = syscon_node_to_regmap(cfg_node); + of_node_put(cfg_node); + if (IS_ERR(pcie->cfg)) + return PTR_ERR(pcie->cfg); + } + + pcie->free_ck = devm_clk_get(dev, "free_ck"); + if (IS_ERR(pcie->free_ck)) { + if (PTR_ERR(pcie->free_ck) == -EPROBE_DEFER) + return -EPROBE_DEFER; + + pcie->free_ck = NULL; + } + + pm_runtime_enable(dev); + pm_runtime_get_sync(dev); + + /* enable top level clock */ + err = clk_prepare_enable(pcie->free_ck); + if (err) { + dev_err(dev, "failed to enable free_ck\n"); + goto err_free_ck; + } + + return 0; + +err_free_ck: + pm_runtime_put_sync(dev); + pm_runtime_disable(dev); + + return err; +} + +static int mtk_pcie_setup(struct mtk_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct device_node *node = dev->of_node, *child; + struct mtk_pcie_port *port, *tmp; + int err, slot; + + slot = of_get_pci_domain_nr(dev->of_node); + if (slot < 0) { + for_each_available_child_of_node(node, child) { + err = of_pci_get_devfn(child); + if (err < 0) { + dev_err(dev, "failed to get devfn: %d\n", err); + goto error_put_node; + } + + slot = PCI_SLOT(err); + + err = mtk_pcie_parse_port(pcie, child, slot); + if (err) + goto error_put_node; + } + } else { + err = mtk_pcie_parse_port(pcie, node, slot); + if (err) + return err; + } + + err = mtk_pcie_subsys_powerup(pcie); + if (err) + return err; + + /* enable each port, and then check link status */ + list_for_each_entry_safe(port, tmp, &pcie->ports, list) + mtk_pcie_enable_port(port); + + /* power down PCIe subsys if slots are all empty (link down) */ + if (list_empty(&pcie->ports)) + mtk_pcie_subsys_powerdown(pcie); + + return 0; +error_put_node: + of_node_put(child); + return err; +} + +static int mtk_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct mtk_pcie *pcie; + struct pci_host_bridge *host; + int err; + + host = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!host) + return -ENOMEM; + + pcie = pci_host_bridge_priv(host); + + pcie->dev = dev; + pcie->soc = of_device_get_match_data(dev); + platform_set_drvdata(pdev, pcie); + INIT_LIST_HEAD(&pcie->ports); + + err = mtk_pcie_setup(pcie); + if (err) + return err; + + host->ops = pcie->soc->ops; + host->sysdata = pcie; + host->msi_domain = pcie->soc->no_msi; + + err = pci_host_probe(host); + if (err) + goto put_resources; + + return 0; + +put_resources: + if (!list_empty(&pcie->ports)) + mtk_pcie_put_resources(pcie); + + return err; +} + + +static void mtk_pcie_free_resources(struct mtk_pcie *pcie) +{ + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + struct list_head *windows = &host->windows; + + pci_free_resource_list(windows); +} + +static int mtk_pcie_remove(struct platform_device *pdev) +{ + struct mtk_pcie *pcie = platform_get_drvdata(pdev); + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); + + pci_stop_root_bus(host->bus); + pci_remove_root_bus(host->bus); + mtk_pcie_free_resources(pcie); + + mtk_pcie_irq_teardown(pcie); + + mtk_pcie_put_resources(pcie); + + return 0; +} + +static int mtk_pcie_suspend_noirq(struct device *dev) +{ + struct mtk_pcie *pcie = dev_get_drvdata(dev); + struct mtk_pcie_port *port; + + if (list_empty(&pcie->ports)) + return 0; + + list_for_each_entry(port, &pcie->ports, list) { + clk_disable_unprepare(port->pipe_ck); + clk_disable_unprepare(port->obff_ck); + clk_disable_unprepare(port->axi_ck); + clk_disable_unprepare(port->aux_ck); + clk_disable_unprepare(port->ahb_ck); + clk_disable_unprepare(port->sys_ck); + phy_power_off(port->phy); + phy_exit(port->phy); + } + + clk_disable_unprepare(pcie->free_ck); + + return 0; +} + +static int mtk_pcie_resume_noirq(struct device *dev) +{ + struct mtk_pcie *pcie = dev_get_drvdata(dev); + struct mtk_pcie_port *port, *tmp; + + if (list_empty(&pcie->ports)) + return 0; + + clk_prepare_enable(pcie->free_ck); + + list_for_each_entry_safe(port, tmp, &pcie->ports, list) + mtk_pcie_enable_port(port); + + /* In case of EP was removed while system suspend. */ + if (list_empty(&pcie->ports)) + clk_disable_unprepare(pcie->free_ck); + + return 0; +} + +static const struct dev_pm_ops mtk_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_pcie_suspend_noirq, + mtk_pcie_resume_noirq) +}; + +static const struct mtk_pcie_soc mtk_pcie_soc_v1 = { + .no_msi = true, + .ops = &mtk_pcie_ops, + .startup = mtk_pcie_startup_port, +}; + +static const struct mtk_pcie_soc mtk_pcie_soc_mt2712 = { + .ops = &mtk_pcie_ops_v2, + .startup = mtk_pcie_startup_port_v2, + .setup_irq = mtk_pcie_setup_irq, +}; + +static const struct mtk_pcie_soc mtk_pcie_soc_mt7622 = { + .need_fix_class_id = true, + .ops = &mtk_pcie_ops_v2, + .startup = mtk_pcie_startup_port_v2, + .setup_irq = mtk_pcie_setup_irq, +}; + +static const struct mtk_pcie_soc mtk_pcie_soc_mt7629 = { + .need_fix_class_id = true, + .need_fix_device_id = true, + .device_id = PCI_DEVICE_ID_MEDIATEK_7629, + .ops = &mtk_pcie_ops_v2, + .startup = mtk_pcie_startup_port_v2, + .setup_irq = mtk_pcie_setup_irq, +}; + +static const struct of_device_id mtk_pcie_ids[] = { + { .compatible = "mediatek,mt2701-pcie", .data = &mtk_pcie_soc_v1 }, + { .compatible = "mediatek,mt7623-pcie", .data = &mtk_pcie_soc_v1 }, + { .compatible = "mediatek,mt2712-pcie", .data = &mtk_pcie_soc_mt2712 }, + { .compatible = "mediatek,mt7622-pcie", .data = &mtk_pcie_soc_mt7622 }, + { .compatible = "mediatek,mt7629-pcie", .data = &mtk_pcie_soc_mt7629 }, + {}, +}; +MODULE_DEVICE_TABLE(of, mtk_pcie_ids); + +static struct platform_driver mtk_pcie_driver = { + .probe = mtk_pcie_probe, + .remove = mtk_pcie_remove, + .driver = { + .name = "mtk-pcie", + .of_match_table = mtk_pcie_ids, + .suppress_bind_attrs = true, + .pm = &mtk_pcie_pm_ops, + }, +}; +module_platform_driver(mtk_pcie_driver); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-microchip-host.c b/drivers/pci/controller/pcie-microchip-host.c new file mode 100644 index 000000000..5ba101efd --- /dev/null +++ b/drivers/pci/controller/pcie-microchip-host.c @@ -0,0 +1,1140 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Microchip AXI PCIe Bridge host controller driver + * + * Copyright (c) 2018 - 2020 Microchip Corporation. All rights reserved. + * + * Author: Daire McNamara <daire.mcnamara@microchip.com> + */ + +#include <linux/clk.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_pci.h> +#include <linux/pci-ecam.h> +#include <linux/platform_device.h> + +#include "../pci.h" + +/* Number of MSI IRQs */ +#define MC_NUM_MSI_IRQS 32 +#define MC_NUM_MSI_IRQS_CODED 5 + +/* PCIe Bridge Phy and Controller Phy offsets */ +#define MC_PCIE1_BRIDGE_ADDR 0x00008000u +#define MC_PCIE1_CTRL_ADDR 0x0000a000u + +#define MC_PCIE_BRIDGE_ADDR (MC_PCIE1_BRIDGE_ADDR) +#define MC_PCIE_CTRL_ADDR (MC_PCIE1_CTRL_ADDR) + +/* PCIe Controller Phy Regs */ +#define SEC_ERROR_CNT 0x20 +#define DED_ERROR_CNT 0x24 +#define SEC_ERROR_INT 0x28 +#define SEC_ERROR_INT_TX_RAM_SEC_ERR_INT GENMASK(3, 0) +#define SEC_ERROR_INT_RX_RAM_SEC_ERR_INT GENMASK(7, 4) +#define SEC_ERROR_INT_PCIE2AXI_RAM_SEC_ERR_INT GENMASK(11, 8) +#define SEC_ERROR_INT_AXI2PCIE_RAM_SEC_ERR_INT GENMASK(15, 12) +#define NUM_SEC_ERROR_INTS (4) +#define SEC_ERROR_INT_MASK 0x2c +#define DED_ERROR_INT 0x30 +#define DED_ERROR_INT_TX_RAM_DED_ERR_INT GENMASK(3, 0) +#define DED_ERROR_INT_RX_RAM_DED_ERR_INT GENMASK(7, 4) +#define DED_ERROR_INT_PCIE2AXI_RAM_DED_ERR_INT GENMASK(11, 8) +#define DED_ERROR_INT_AXI2PCIE_RAM_DED_ERR_INT GENMASK(15, 12) +#define NUM_DED_ERROR_INTS (4) +#define DED_ERROR_INT_MASK 0x34 +#define ECC_CONTROL 0x38 +#define ECC_CONTROL_TX_RAM_INJ_ERROR_0 BIT(0) +#define ECC_CONTROL_TX_RAM_INJ_ERROR_1 BIT(1) +#define ECC_CONTROL_TX_RAM_INJ_ERROR_2 BIT(2) +#define ECC_CONTROL_TX_RAM_INJ_ERROR_3 BIT(3) +#define ECC_CONTROL_RX_RAM_INJ_ERROR_0 BIT(4) +#define ECC_CONTROL_RX_RAM_INJ_ERROR_1 BIT(5) +#define ECC_CONTROL_RX_RAM_INJ_ERROR_2 BIT(6) +#define ECC_CONTROL_RX_RAM_INJ_ERROR_3 BIT(7) +#define ECC_CONTROL_PCIE2AXI_RAM_INJ_ERROR_0 BIT(8) +#define ECC_CONTROL_PCIE2AXI_RAM_INJ_ERROR_1 BIT(9) +#define ECC_CONTROL_PCIE2AXI_RAM_INJ_ERROR_2 BIT(10) +#define ECC_CONTROL_PCIE2AXI_RAM_INJ_ERROR_3 BIT(11) +#define ECC_CONTROL_AXI2PCIE_RAM_INJ_ERROR_0 BIT(12) +#define ECC_CONTROL_AXI2PCIE_RAM_INJ_ERROR_1 BIT(13) +#define ECC_CONTROL_AXI2PCIE_RAM_INJ_ERROR_2 BIT(14) +#define ECC_CONTROL_AXI2PCIE_RAM_INJ_ERROR_3 BIT(15) +#define ECC_CONTROL_TX_RAM_ECC_BYPASS BIT(24) +#define ECC_CONTROL_RX_RAM_ECC_BYPASS BIT(25) +#define ECC_CONTROL_PCIE2AXI_RAM_ECC_BYPASS BIT(26) +#define ECC_CONTROL_AXI2PCIE_RAM_ECC_BYPASS BIT(27) +#define LTSSM_STATE 0x5c +#define LTSSM_L0_STATE 0x10 +#define PCIE_EVENT_INT 0x14c +#define PCIE_EVENT_INT_L2_EXIT_INT BIT(0) +#define PCIE_EVENT_INT_HOTRST_EXIT_INT BIT(1) +#define PCIE_EVENT_INT_DLUP_EXIT_INT BIT(2) +#define PCIE_EVENT_INT_MASK GENMASK(2, 0) +#define PCIE_EVENT_INT_L2_EXIT_INT_MASK BIT(16) +#define PCIE_EVENT_INT_HOTRST_EXIT_INT_MASK BIT(17) +#define PCIE_EVENT_INT_DLUP_EXIT_INT_MASK BIT(18) +#define PCIE_EVENT_INT_ENB_MASK GENMASK(18, 16) +#define PCIE_EVENT_INT_ENB_SHIFT 16 +#define NUM_PCIE_EVENTS (3) + +/* PCIe Bridge Phy Regs */ +#define PCIE_PCI_IDS_DW1 0x9c + +/* PCIe Config space MSI capability structure */ +#define MC_MSI_CAP_CTRL_OFFSET 0xe0u +#define MC_MSI_MAX_Q_AVAIL (MC_NUM_MSI_IRQS_CODED << 1) +#define MC_MSI_Q_SIZE (MC_NUM_MSI_IRQS_CODED << 4) + +#define IMASK_LOCAL 0x180 +#define DMA_END_ENGINE_0_MASK 0x00000000u +#define DMA_END_ENGINE_0_SHIFT 0 +#define DMA_END_ENGINE_1_MASK 0x00000000u +#define DMA_END_ENGINE_1_SHIFT 1 +#define DMA_ERROR_ENGINE_0_MASK 0x00000100u +#define DMA_ERROR_ENGINE_0_SHIFT 8 +#define DMA_ERROR_ENGINE_1_MASK 0x00000200u +#define DMA_ERROR_ENGINE_1_SHIFT 9 +#define A_ATR_EVT_POST_ERR_MASK 0x00010000u +#define A_ATR_EVT_POST_ERR_SHIFT 16 +#define A_ATR_EVT_FETCH_ERR_MASK 0x00020000u +#define A_ATR_EVT_FETCH_ERR_SHIFT 17 +#define A_ATR_EVT_DISCARD_ERR_MASK 0x00040000u +#define A_ATR_EVT_DISCARD_ERR_SHIFT 18 +#define A_ATR_EVT_DOORBELL_MASK 0x00000000u +#define A_ATR_EVT_DOORBELL_SHIFT 19 +#define P_ATR_EVT_POST_ERR_MASK 0x00100000u +#define P_ATR_EVT_POST_ERR_SHIFT 20 +#define P_ATR_EVT_FETCH_ERR_MASK 0x00200000u +#define P_ATR_EVT_FETCH_ERR_SHIFT 21 +#define P_ATR_EVT_DISCARD_ERR_MASK 0x00400000u +#define P_ATR_EVT_DISCARD_ERR_SHIFT 22 +#define P_ATR_EVT_DOORBELL_MASK 0x00000000u +#define P_ATR_EVT_DOORBELL_SHIFT 23 +#define PM_MSI_INT_INTA_MASK 0x01000000u +#define PM_MSI_INT_INTA_SHIFT 24 +#define PM_MSI_INT_INTB_MASK 0x02000000u +#define PM_MSI_INT_INTB_SHIFT 25 +#define PM_MSI_INT_INTC_MASK 0x04000000u +#define PM_MSI_INT_INTC_SHIFT 26 +#define PM_MSI_INT_INTD_MASK 0x08000000u +#define PM_MSI_INT_INTD_SHIFT 27 +#define PM_MSI_INT_INTX_MASK 0x0f000000u +#define PM_MSI_INT_INTX_SHIFT 24 +#define PM_MSI_INT_MSI_MASK 0x10000000u +#define PM_MSI_INT_MSI_SHIFT 28 +#define PM_MSI_INT_AER_EVT_MASK 0x20000000u +#define PM_MSI_INT_AER_EVT_SHIFT 29 +#define PM_MSI_INT_EVENTS_MASK 0x40000000u +#define PM_MSI_INT_EVENTS_SHIFT 30 +#define PM_MSI_INT_SYS_ERR_MASK 0x80000000u +#define PM_MSI_INT_SYS_ERR_SHIFT 31 +#define NUM_LOCAL_EVENTS 15 +#define ISTATUS_LOCAL 0x184 +#define IMASK_HOST 0x188 +#define ISTATUS_HOST 0x18c +#define MSI_ADDR 0x190 +#define ISTATUS_MSI 0x194 + +/* PCIe Master table init defines */ +#define ATR0_PCIE_WIN0_SRCADDR_PARAM 0x600u +#define ATR0_PCIE_ATR_SIZE 0x25 +#define ATR0_PCIE_ATR_SIZE_SHIFT 1 +#define ATR0_PCIE_WIN0_SRC_ADDR 0x604u +#define ATR0_PCIE_WIN0_TRSL_ADDR_LSB 0x608u +#define ATR0_PCIE_WIN0_TRSL_ADDR_UDW 0x60cu +#define ATR0_PCIE_WIN0_TRSL_PARAM 0x610u + +/* PCIe AXI slave table init defines */ +#define ATR0_AXI4_SLV0_SRCADDR_PARAM 0x800u +#define ATR_SIZE_SHIFT 1 +#define ATR_IMPL_ENABLE 1 +#define ATR0_AXI4_SLV0_SRC_ADDR 0x804u +#define ATR0_AXI4_SLV0_TRSL_ADDR_LSB 0x808u +#define ATR0_AXI4_SLV0_TRSL_ADDR_UDW 0x80cu +#define ATR0_AXI4_SLV0_TRSL_PARAM 0x810u +#define PCIE_TX_RX_INTERFACE 0x00000000u +#define PCIE_CONFIG_INTERFACE 0x00000001u + +#define ATR_ENTRY_SIZE 32 + +#define EVENT_PCIE_L2_EXIT 0 +#define EVENT_PCIE_HOTRST_EXIT 1 +#define EVENT_PCIE_DLUP_EXIT 2 +#define EVENT_SEC_TX_RAM_SEC_ERR 3 +#define EVENT_SEC_RX_RAM_SEC_ERR 4 +#define EVENT_SEC_PCIE2AXI_RAM_SEC_ERR 5 +#define EVENT_SEC_AXI2PCIE_RAM_SEC_ERR 6 +#define EVENT_DED_TX_RAM_DED_ERR 7 +#define EVENT_DED_RX_RAM_DED_ERR 8 +#define EVENT_DED_PCIE2AXI_RAM_DED_ERR 9 +#define EVENT_DED_AXI2PCIE_RAM_DED_ERR 10 +#define EVENT_LOCAL_DMA_END_ENGINE_0 11 +#define EVENT_LOCAL_DMA_END_ENGINE_1 12 +#define EVENT_LOCAL_DMA_ERROR_ENGINE_0 13 +#define EVENT_LOCAL_DMA_ERROR_ENGINE_1 14 +#define EVENT_LOCAL_A_ATR_EVT_POST_ERR 15 +#define EVENT_LOCAL_A_ATR_EVT_FETCH_ERR 16 +#define EVENT_LOCAL_A_ATR_EVT_DISCARD_ERR 17 +#define EVENT_LOCAL_A_ATR_EVT_DOORBELL 18 +#define EVENT_LOCAL_P_ATR_EVT_POST_ERR 19 +#define EVENT_LOCAL_P_ATR_EVT_FETCH_ERR 20 +#define EVENT_LOCAL_P_ATR_EVT_DISCARD_ERR 21 +#define EVENT_LOCAL_P_ATR_EVT_DOORBELL 22 +#define EVENT_LOCAL_PM_MSI_INT_INTX 23 +#define EVENT_LOCAL_PM_MSI_INT_MSI 24 +#define EVENT_LOCAL_PM_MSI_INT_AER_EVT 25 +#define EVENT_LOCAL_PM_MSI_INT_EVENTS 26 +#define EVENT_LOCAL_PM_MSI_INT_SYS_ERR 27 +#define NUM_EVENTS 28 + +#define PCIE_EVENT_CAUSE(x, s) \ + [EVENT_PCIE_ ## x] = { __stringify(x), s } + +#define SEC_ERROR_CAUSE(x, s) \ + [EVENT_SEC_ ## x] = { __stringify(x), s } + +#define DED_ERROR_CAUSE(x, s) \ + [EVENT_DED_ ## x] = { __stringify(x), s } + +#define LOCAL_EVENT_CAUSE(x, s) \ + [EVENT_LOCAL_ ## x] = { __stringify(x), s } + +#define PCIE_EVENT(x) \ + .base = MC_PCIE_CTRL_ADDR, \ + .offset = PCIE_EVENT_INT, \ + .mask_offset = PCIE_EVENT_INT, \ + .mask_high = 1, \ + .mask = PCIE_EVENT_INT_ ## x ## _INT, \ + .enb_mask = PCIE_EVENT_INT_ENB_MASK + +#define SEC_EVENT(x) \ + .base = MC_PCIE_CTRL_ADDR, \ + .offset = SEC_ERROR_INT, \ + .mask_offset = SEC_ERROR_INT_MASK, \ + .mask = SEC_ERROR_INT_ ## x ## _INT, \ + .mask_high = 1, \ + .enb_mask = 0 + +#define DED_EVENT(x) \ + .base = MC_PCIE_CTRL_ADDR, \ + .offset = DED_ERROR_INT, \ + .mask_offset = DED_ERROR_INT_MASK, \ + .mask_high = 1, \ + .mask = DED_ERROR_INT_ ## x ## _INT, \ + .enb_mask = 0 + +#define LOCAL_EVENT(x) \ + .base = MC_PCIE_BRIDGE_ADDR, \ + .offset = ISTATUS_LOCAL, \ + .mask_offset = IMASK_LOCAL, \ + .mask_high = 0, \ + .mask = x ## _MASK, \ + .enb_mask = 0 + +#define PCIE_EVENT_TO_EVENT_MAP(x) \ + { PCIE_EVENT_INT_ ## x ## _INT, EVENT_PCIE_ ## x } + +#define SEC_ERROR_TO_EVENT_MAP(x) \ + { SEC_ERROR_INT_ ## x ## _INT, EVENT_SEC_ ## x } + +#define DED_ERROR_TO_EVENT_MAP(x) \ + { DED_ERROR_INT_ ## x ## _INT, EVENT_DED_ ## x } + +#define LOCAL_STATUS_TO_EVENT_MAP(x) \ + { x ## _MASK, EVENT_LOCAL_ ## x } + +struct event_map { + u32 reg_mask; + u32 event_bit; +}; + +struct mc_msi { + struct mutex lock; /* Protect used bitmap */ + struct irq_domain *msi_domain; + struct irq_domain *dev_domain; + u32 num_vectors; + u64 vector_phy; + DECLARE_BITMAP(used, MC_NUM_MSI_IRQS); +}; + +struct mc_pcie { + void __iomem *axi_base_addr; + struct device *dev; + struct irq_domain *intx_domain; + struct irq_domain *event_domain; + raw_spinlock_t lock; + struct mc_msi msi; +}; + +struct cause { + const char *sym; + const char *str; +}; + +static const struct cause event_cause[NUM_EVENTS] = { + PCIE_EVENT_CAUSE(L2_EXIT, "L2 exit event"), + PCIE_EVENT_CAUSE(HOTRST_EXIT, "Hot reset exit event"), + PCIE_EVENT_CAUSE(DLUP_EXIT, "DLUP exit event"), + SEC_ERROR_CAUSE(TX_RAM_SEC_ERR, "sec error in tx buffer"), + SEC_ERROR_CAUSE(RX_RAM_SEC_ERR, "sec error in rx buffer"), + SEC_ERROR_CAUSE(PCIE2AXI_RAM_SEC_ERR, "sec error in pcie2axi buffer"), + SEC_ERROR_CAUSE(AXI2PCIE_RAM_SEC_ERR, "sec error in axi2pcie buffer"), + DED_ERROR_CAUSE(TX_RAM_DED_ERR, "ded error in tx buffer"), + DED_ERROR_CAUSE(RX_RAM_DED_ERR, "ded error in rx buffer"), + DED_ERROR_CAUSE(PCIE2AXI_RAM_DED_ERR, "ded error in pcie2axi buffer"), + DED_ERROR_CAUSE(AXI2PCIE_RAM_DED_ERR, "ded error in axi2pcie buffer"), + LOCAL_EVENT_CAUSE(DMA_ERROR_ENGINE_0, "dma engine 0 error"), + LOCAL_EVENT_CAUSE(DMA_ERROR_ENGINE_1, "dma engine 1 error"), + LOCAL_EVENT_CAUSE(A_ATR_EVT_POST_ERR, "axi write request error"), + LOCAL_EVENT_CAUSE(A_ATR_EVT_FETCH_ERR, "axi read request error"), + LOCAL_EVENT_CAUSE(A_ATR_EVT_DISCARD_ERR, "axi read timeout"), + LOCAL_EVENT_CAUSE(P_ATR_EVT_POST_ERR, "pcie write request error"), + LOCAL_EVENT_CAUSE(P_ATR_EVT_FETCH_ERR, "pcie read request error"), + LOCAL_EVENT_CAUSE(P_ATR_EVT_DISCARD_ERR, "pcie read timeout"), + LOCAL_EVENT_CAUSE(PM_MSI_INT_AER_EVT, "aer event"), + LOCAL_EVENT_CAUSE(PM_MSI_INT_EVENTS, "pm/ltr/hotplug event"), + LOCAL_EVENT_CAUSE(PM_MSI_INT_SYS_ERR, "system error"), +}; + +static struct event_map pcie_event_to_event[] = { + PCIE_EVENT_TO_EVENT_MAP(L2_EXIT), + PCIE_EVENT_TO_EVENT_MAP(HOTRST_EXIT), + PCIE_EVENT_TO_EVENT_MAP(DLUP_EXIT), +}; + +static struct event_map sec_error_to_event[] = { + SEC_ERROR_TO_EVENT_MAP(TX_RAM_SEC_ERR), + SEC_ERROR_TO_EVENT_MAP(RX_RAM_SEC_ERR), + SEC_ERROR_TO_EVENT_MAP(PCIE2AXI_RAM_SEC_ERR), + SEC_ERROR_TO_EVENT_MAP(AXI2PCIE_RAM_SEC_ERR), +}; + +static struct event_map ded_error_to_event[] = { + DED_ERROR_TO_EVENT_MAP(TX_RAM_DED_ERR), + DED_ERROR_TO_EVENT_MAP(RX_RAM_DED_ERR), + DED_ERROR_TO_EVENT_MAP(PCIE2AXI_RAM_DED_ERR), + DED_ERROR_TO_EVENT_MAP(AXI2PCIE_RAM_DED_ERR), +}; + +static struct event_map local_status_to_event[] = { + LOCAL_STATUS_TO_EVENT_MAP(DMA_END_ENGINE_0), + LOCAL_STATUS_TO_EVENT_MAP(DMA_END_ENGINE_1), + LOCAL_STATUS_TO_EVENT_MAP(DMA_ERROR_ENGINE_0), + LOCAL_STATUS_TO_EVENT_MAP(DMA_ERROR_ENGINE_1), + LOCAL_STATUS_TO_EVENT_MAP(A_ATR_EVT_POST_ERR), + LOCAL_STATUS_TO_EVENT_MAP(A_ATR_EVT_FETCH_ERR), + LOCAL_STATUS_TO_EVENT_MAP(A_ATR_EVT_DISCARD_ERR), + LOCAL_STATUS_TO_EVENT_MAP(A_ATR_EVT_DOORBELL), + LOCAL_STATUS_TO_EVENT_MAP(P_ATR_EVT_POST_ERR), + LOCAL_STATUS_TO_EVENT_MAP(P_ATR_EVT_FETCH_ERR), + LOCAL_STATUS_TO_EVENT_MAP(P_ATR_EVT_DISCARD_ERR), + LOCAL_STATUS_TO_EVENT_MAP(P_ATR_EVT_DOORBELL), + LOCAL_STATUS_TO_EVENT_MAP(PM_MSI_INT_INTX), + LOCAL_STATUS_TO_EVENT_MAP(PM_MSI_INT_MSI), + LOCAL_STATUS_TO_EVENT_MAP(PM_MSI_INT_AER_EVT), + LOCAL_STATUS_TO_EVENT_MAP(PM_MSI_INT_EVENTS), + LOCAL_STATUS_TO_EVENT_MAP(PM_MSI_INT_SYS_ERR), +}; + +static struct { + u32 base; + u32 offset; + u32 mask; + u32 shift; + u32 enb_mask; + u32 mask_high; + u32 mask_offset; +} event_descs[] = { + { PCIE_EVENT(L2_EXIT) }, + { PCIE_EVENT(HOTRST_EXIT) }, + { PCIE_EVENT(DLUP_EXIT) }, + { SEC_EVENT(TX_RAM_SEC_ERR) }, + { SEC_EVENT(RX_RAM_SEC_ERR) }, + { SEC_EVENT(PCIE2AXI_RAM_SEC_ERR) }, + { SEC_EVENT(AXI2PCIE_RAM_SEC_ERR) }, + { DED_EVENT(TX_RAM_DED_ERR) }, + { DED_EVENT(RX_RAM_DED_ERR) }, + { DED_EVENT(PCIE2AXI_RAM_DED_ERR) }, + { DED_EVENT(AXI2PCIE_RAM_DED_ERR) }, + { LOCAL_EVENT(DMA_END_ENGINE_0) }, + { LOCAL_EVENT(DMA_END_ENGINE_1) }, + { LOCAL_EVENT(DMA_ERROR_ENGINE_0) }, + { LOCAL_EVENT(DMA_ERROR_ENGINE_1) }, + { LOCAL_EVENT(A_ATR_EVT_POST_ERR) }, + { LOCAL_EVENT(A_ATR_EVT_FETCH_ERR) }, + { LOCAL_EVENT(A_ATR_EVT_DISCARD_ERR) }, + { LOCAL_EVENT(A_ATR_EVT_DOORBELL) }, + { LOCAL_EVENT(P_ATR_EVT_POST_ERR) }, + { LOCAL_EVENT(P_ATR_EVT_FETCH_ERR) }, + { LOCAL_EVENT(P_ATR_EVT_DISCARD_ERR) }, + { LOCAL_EVENT(P_ATR_EVT_DOORBELL) }, + { LOCAL_EVENT(PM_MSI_INT_INTX) }, + { LOCAL_EVENT(PM_MSI_INT_MSI) }, + { LOCAL_EVENT(PM_MSI_INT_AER_EVT) }, + { LOCAL_EVENT(PM_MSI_INT_EVENTS) }, + { LOCAL_EVENT(PM_MSI_INT_SYS_ERR) }, +}; + +static char poss_clks[][5] = { "fic0", "fic1", "fic2", "fic3" }; + +static void mc_pcie_enable_msi(struct mc_pcie *port, void __iomem *base) +{ + struct mc_msi *msi = &port->msi; + u32 cap_offset = MC_MSI_CAP_CTRL_OFFSET; + u16 msg_ctrl = readw_relaxed(base + cap_offset + PCI_MSI_FLAGS); + + msg_ctrl |= PCI_MSI_FLAGS_ENABLE; + msg_ctrl &= ~PCI_MSI_FLAGS_QMASK; + msg_ctrl |= MC_MSI_MAX_Q_AVAIL; + msg_ctrl &= ~PCI_MSI_FLAGS_QSIZE; + msg_ctrl |= MC_MSI_Q_SIZE; + msg_ctrl |= PCI_MSI_FLAGS_64BIT; + + writew_relaxed(msg_ctrl, base + cap_offset + PCI_MSI_FLAGS); + + writel_relaxed(lower_32_bits(msi->vector_phy), + base + cap_offset + PCI_MSI_ADDRESS_LO); + writel_relaxed(upper_32_bits(msi->vector_phy), + base + cap_offset + PCI_MSI_ADDRESS_HI); +} + +static void mc_handle_msi(struct irq_desc *desc) +{ + struct mc_pcie *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + struct device *dev = port->dev; + struct mc_msi *msi = &port->msi; + void __iomem *bridge_base_addr = + port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; + unsigned long status; + u32 bit; + int ret; + + chained_irq_enter(chip, desc); + + status = readl_relaxed(bridge_base_addr + ISTATUS_LOCAL); + if (status & PM_MSI_INT_MSI_MASK) { + writel_relaxed(status & PM_MSI_INT_MSI_MASK, bridge_base_addr + ISTATUS_LOCAL); + status = readl_relaxed(bridge_base_addr + ISTATUS_MSI); + for_each_set_bit(bit, &status, msi->num_vectors) { + ret = generic_handle_domain_irq(msi->dev_domain, bit); + if (ret) + dev_err_ratelimited(dev, "bad MSI IRQ %d\n", + bit); + } + } + + chained_irq_exit(chip, desc); +} + +static void mc_msi_bottom_irq_ack(struct irq_data *data) +{ + struct mc_pcie *port = irq_data_get_irq_chip_data(data); + void __iomem *bridge_base_addr = + port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; + u32 bitpos = data->hwirq; + + writel_relaxed(BIT(bitpos), bridge_base_addr + ISTATUS_MSI); +} + +static void mc_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct mc_pcie *port = irq_data_get_irq_chip_data(data); + phys_addr_t addr = port->msi.vector_phy; + + msg->address_lo = lower_32_bits(addr); + msg->address_hi = upper_32_bits(addr); + msg->data = data->hwirq; + + dev_dbg(port->dev, "msi#%x address_hi %#x address_lo %#x\n", + (int)data->hwirq, msg->address_hi, msg->address_lo); +} + +static int mc_msi_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static struct irq_chip mc_msi_bottom_irq_chip = { + .name = "Microchip MSI", + .irq_ack = mc_msi_bottom_irq_ack, + .irq_compose_msi_msg = mc_compose_msi_msg, + .irq_set_affinity = mc_msi_set_affinity, +}; + +static int mc_irq_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct mc_pcie *port = domain->host_data; + struct mc_msi *msi = &port->msi; + void __iomem *bridge_base_addr = + port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; + unsigned long bit; + u32 val; + + mutex_lock(&msi->lock); + bit = find_first_zero_bit(msi->used, msi->num_vectors); + if (bit >= msi->num_vectors) { + mutex_unlock(&msi->lock); + return -ENOSPC; + } + + set_bit(bit, msi->used); + + irq_domain_set_info(domain, virq, bit, &mc_msi_bottom_irq_chip, + domain->host_data, handle_edge_irq, NULL, NULL); + + /* Enable MSI interrupts */ + val = readl_relaxed(bridge_base_addr + IMASK_LOCAL); + val |= PM_MSI_INT_MSI_MASK; + writel_relaxed(val, bridge_base_addr + IMASK_LOCAL); + + mutex_unlock(&msi->lock); + + return 0; +} + +static void mc_irq_msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct mc_pcie *port = irq_data_get_irq_chip_data(d); + struct mc_msi *msi = &port->msi; + + mutex_lock(&msi->lock); + + if (test_bit(d->hwirq, msi->used)) + __clear_bit(d->hwirq, msi->used); + else + dev_err(port->dev, "trying to free unused MSI%lu\n", d->hwirq); + + mutex_unlock(&msi->lock); +} + +static const struct irq_domain_ops msi_domain_ops = { + .alloc = mc_irq_msi_domain_alloc, + .free = mc_irq_msi_domain_free, +}; + +static struct irq_chip mc_msi_irq_chip = { + .name = "Microchip PCIe MSI", + .irq_ack = irq_chip_ack_parent, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, +}; + +static struct msi_domain_info mc_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX), + .chip = &mc_msi_irq_chip, +}; + +static int mc_allocate_msi_domains(struct mc_pcie *port) +{ + struct device *dev = port->dev; + struct fwnode_handle *fwnode = of_node_to_fwnode(dev->of_node); + struct mc_msi *msi = &port->msi; + + mutex_init(&port->msi.lock); + + msi->dev_domain = irq_domain_add_linear(NULL, msi->num_vectors, + &msi_domain_ops, port); + if (!msi->dev_domain) { + dev_err(dev, "failed to create IRQ domain\n"); + return -ENOMEM; + } + + msi->msi_domain = pci_msi_create_irq_domain(fwnode, &mc_msi_domain_info, + msi->dev_domain); + if (!msi->msi_domain) { + dev_err(dev, "failed to create MSI domain\n"); + irq_domain_remove(msi->dev_domain); + return -ENOMEM; + } + + return 0; +} + +static void mc_handle_intx(struct irq_desc *desc) +{ + struct mc_pcie *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + struct device *dev = port->dev; + void __iomem *bridge_base_addr = + port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; + unsigned long status; + u32 bit; + int ret; + + chained_irq_enter(chip, desc); + + status = readl_relaxed(bridge_base_addr + ISTATUS_LOCAL); + if (status & PM_MSI_INT_INTX_MASK) { + status &= PM_MSI_INT_INTX_MASK; + status >>= PM_MSI_INT_INTX_SHIFT; + for_each_set_bit(bit, &status, PCI_NUM_INTX) { + ret = generic_handle_domain_irq(port->intx_domain, bit); + if (ret) + dev_err_ratelimited(dev, "bad INTx IRQ %d\n", + bit); + } + } + + chained_irq_exit(chip, desc); +} + +static void mc_ack_intx_irq(struct irq_data *data) +{ + struct mc_pcie *port = irq_data_get_irq_chip_data(data); + void __iomem *bridge_base_addr = + port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; + u32 mask = BIT(data->hwirq + PM_MSI_INT_INTX_SHIFT); + + writel_relaxed(mask, bridge_base_addr + ISTATUS_LOCAL); +} + +static void mc_mask_intx_irq(struct irq_data *data) +{ + struct mc_pcie *port = irq_data_get_irq_chip_data(data); + void __iomem *bridge_base_addr = + port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; + unsigned long flags; + u32 mask = BIT(data->hwirq + PM_MSI_INT_INTX_SHIFT); + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = readl_relaxed(bridge_base_addr + IMASK_LOCAL); + val &= ~mask; + writel_relaxed(val, bridge_base_addr + IMASK_LOCAL); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static void mc_unmask_intx_irq(struct irq_data *data) +{ + struct mc_pcie *port = irq_data_get_irq_chip_data(data); + void __iomem *bridge_base_addr = + port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; + unsigned long flags; + u32 mask = BIT(data->hwirq + PM_MSI_INT_INTX_SHIFT); + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = readl_relaxed(bridge_base_addr + IMASK_LOCAL); + val |= mask; + writel_relaxed(val, bridge_base_addr + IMASK_LOCAL); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static struct irq_chip mc_intx_irq_chip = { + .name = "Microchip PCIe INTx", + .irq_ack = mc_ack_intx_irq, + .irq_mask = mc_mask_intx_irq, + .irq_unmask = mc_unmask_intx_irq, +}; + +static int mc_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &mc_intx_irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops intx_domain_ops = { + .map = mc_pcie_intx_map, +}; + +static inline u32 reg_to_event(u32 reg, struct event_map field) +{ + return (reg & field.reg_mask) ? BIT(field.event_bit) : 0; +} + +static u32 pcie_events(void __iomem *addr) +{ + u32 reg = readl_relaxed(addr); + u32 val = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(pcie_event_to_event); i++) + val |= reg_to_event(reg, pcie_event_to_event[i]); + + return val; +} + +static u32 sec_errors(void __iomem *addr) +{ + u32 reg = readl_relaxed(addr); + u32 val = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(sec_error_to_event); i++) + val |= reg_to_event(reg, sec_error_to_event[i]); + + return val; +} + +static u32 ded_errors(void __iomem *addr) +{ + u32 reg = readl_relaxed(addr); + u32 val = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(ded_error_to_event); i++) + val |= reg_to_event(reg, ded_error_to_event[i]); + + return val; +} + +static u32 local_events(void __iomem *addr) +{ + u32 reg = readl_relaxed(addr); + u32 val = 0; + int i; + + for (i = 0; i < ARRAY_SIZE(local_status_to_event); i++) + val |= reg_to_event(reg, local_status_to_event[i]); + + return val; +} + +static u32 get_events(struct mc_pcie *port) +{ + void __iomem *bridge_base_addr = + port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; + void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR; + u32 events = 0; + + events |= pcie_events(ctrl_base_addr + PCIE_EVENT_INT); + events |= sec_errors(ctrl_base_addr + SEC_ERROR_INT); + events |= ded_errors(ctrl_base_addr + DED_ERROR_INT); + events |= local_events(bridge_base_addr + ISTATUS_LOCAL); + + return events; +} + +static irqreturn_t mc_event_handler(int irq, void *dev_id) +{ + struct mc_pcie *port = dev_id; + struct device *dev = port->dev; + struct irq_data *data; + + data = irq_domain_get_irq_data(port->event_domain, irq); + + if (event_cause[data->hwirq].str) + dev_err_ratelimited(dev, "%s\n", event_cause[data->hwirq].str); + else + dev_err_ratelimited(dev, "bad event IRQ %ld\n", data->hwirq); + + return IRQ_HANDLED; +} + +static void mc_handle_event(struct irq_desc *desc) +{ + struct mc_pcie *port = irq_desc_get_handler_data(desc); + unsigned long events; + u32 bit; + struct irq_chip *chip = irq_desc_get_chip(desc); + + chained_irq_enter(chip, desc); + + events = get_events(port); + + for_each_set_bit(bit, &events, NUM_EVENTS) + generic_handle_domain_irq(port->event_domain, bit); + + chained_irq_exit(chip, desc); +} + +static void mc_ack_event_irq(struct irq_data *data) +{ + struct mc_pcie *port = irq_data_get_irq_chip_data(data); + u32 event = data->hwirq; + void __iomem *addr; + u32 mask; + + addr = port->axi_base_addr + event_descs[event].base + + event_descs[event].offset; + mask = event_descs[event].mask; + mask |= event_descs[event].enb_mask; + + writel_relaxed(mask, addr); +} + +static void mc_mask_event_irq(struct irq_data *data) +{ + struct mc_pcie *port = irq_data_get_irq_chip_data(data); + u32 event = data->hwirq; + void __iomem *addr; + u32 mask; + u32 val; + + addr = port->axi_base_addr + event_descs[event].base + + event_descs[event].mask_offset; + mask = event_descs[event].mask; + if (event_descs[event].enb_mask) { + mask <<= PCIE_EVENT_INT_ENB_SHIFT; + mask &= PCIE_EVENT_INT_ENB_MASK; + } + + if (!event_descs[event].mask_high) + mask = ~mask; + + raw_spin_lock(&port->lock); + val = readl_relaxed(addr); + if (event_descs[event].mask_high) + val |= mask; + else + val &= mask; + + writel_relaxed(val, addr); + raw_spin_unlock(&port->lock); +} + +static void mc_unmask_event_irq(struct irq_data *data) +{ + struct mc_pcie *port = irq_data_get_irq_chip_data(data); + u32 event = data->hwirq; + void __iomem *addr; + u32 mask; + u32 val; + + addr = port->axi_base_addr + event_descs[event].base + + event_descs[event].mask_offset; + mask = event_descs[event].mask; + + if (event_descs[event].enb_mask) + mask <<= PCIE_EVENT_INT_ENB_SHIFT; + + if (event_descs[event].mask_high) + mask = ~mask; + + if (event_descs[event].enb_mask) + mask &= PCIE_EVENT_INT_ENB_MASK; + + raw_spin_lock(&port->lock); + val = readl_relaxed(addr); + if (event_descs[event].mask_high) + val &= mask; + else + val |= mask; + writel_relaxed(val, addr); + raw_spin_unlock(&port->lock); +} + +static struct irq_chip mc_event_irq_chip = { + .name = "Microchip PCIe EVENT", + .irq_ack = mc_ack_event_irq, + .irq_mask = mc_mask_event_irq, + .irq_unmask = mc_unmask_event_irq, +}; + +static int mc_pcie_event_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &mc_event_irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops event_domain_ops = { + .map = mc_pcie_event_map, +}; + +static inline struct clk *mc_pcie_init_clk(struct device *dev, const char *id) +{ + struct clk *clk; + int ret; + + clk = devm_clk_get_optional(dev, id); + if (IS_ERR(clk)) + return clk; + if (!clk) + return clk; + + ret = clk_prepare_enable(clk); + if (ret) + return ERR_PTR(ret); + + devm_add_action_or_reset(dev, (void (*) (void *))clk_disable_unprepare, + clk); + + return clk; +} + +static int mc_pcie_init_clks(struct device *dev) +{ + int i; + struct clk *fic; + + /* + * PCIe may be clocked via Fabric Interface using between 1 and 4 + * clocks. Scan DT for clocks and enable them if present + */ + for (i = 0; i < ARRAY_SIZE(poss_clks); i++) { + fic = mc_pcie_init_clk(dev, poss_clks[i]); + if (IS_ERR(fic)) + return PTR_ERR(fic); + } + + return 0; +} + +static int mc_pcie_init_irq_domains(struct mc_pcie *port) +{ + struct device *dev = port->dev; + struct device_node *node = dev->of_node; + struct device_node *pcie_intc_node; + + /* Setup INTx */ + pcie_intc_node = of_get_next_child(node, NULL); + if (!pcie_intc_node) { + dev_err(dev, "failed to find PCIe Intc node\n"); + return -EINVAL; + } + + port->event_domain = irq_domain_add_linear(pcie_intc_node, NUM_EVENTS, + &event_domain_ops, port); + if (!port->event_domain) { + dev_err(dev, "failed to get event domain\n"); + of_node_put(pcie_intc_node); + return -ENOMEM; + } + + irq_domain_update_bus_token(port->event_domain, DOMAIN_BUS_NEXUS); + + port->intx_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, + &intx_domain_ops, port); + if (!port->intx_domain) { + dev_err(dev, "failed to get an INTx IRQ domain\n"); + of_node_put(pcie_intc_node); + return -ENOMEM; + } + + irq_domain_update_bus_token(port->intx_domain, DOMAIN_BUS_WIRED); + + of_node_put(pcie_intc_node); + raw_spin_lock_init(&port->lock); + + return mc_allocate_msi_domains(port); +} + +static void mc_pcie_setup_window(void __iomem *bridge_base_addr, u32 index, + phys_addr_t axi_addr, phys_addr_t pci_addr, + size_t size) +{ + u32 atr_sz = ilog2(size) - 1; + u32 val; + + if (index == 0) + val = PCIE_CONFIG_INTERFACE; + else + val = PCIE_TX_RX_INTERFACE; + + writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + + ATR0_AXI4_SLV0_TRSL_PARAM); + + val = lower_32_bits(axi_addr) | (atr_sz << ATR_SIZE_SHIFT) | + ATR_IMPL_ENABLE; + writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + + ATR0_AXI4_SLV0_SRCADDR_PARAM); + + val = upper_32_bits(axi_addr); + writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + + ATR0_AXI4_SLV0_SRC_ADDR); + + val = lower_32_bits(pci_addr); + writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + + ATR0_AXI4_SLV0_TRSL_ADDR_LSB); + + val = upper_32_bits(pci_addr); + writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + + ATR0_AXI4_SLV0_TRSL_ADDR_UDW); + + val = readl(bridge_base_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM); + val |= (ATR0_PCIE_ATR_SIZE << ATR0_PCIE_ATR_SIZE_SHIFT); + writel(val, bridge_base_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM); + writel(0, bridge_base_addr + ATR0_PCIE_WIN0_SRC_ADDR); +} + +static int mc_pcie_setup_windows(struct platform_device *pdev, + struct mc_pcie *port) +{ + void __iomem *bridge_base_addr = + port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; + struct pci_host_bridge *bridge = platform_get_drvdata(pdev); + struct resource_entry *entry; + u64 pci_addr; + u32 index = 1; + + resource_list_for_each_entry(entry, &bridge->windows) { + if (resource_type(entry->res) == IORESOURCE_MEM) { + pci_addr = entry->res->start - entry->offset; + mc_pcie_setup_window(bridge_base_addr, index, + entry->res->start, pci_addr, + resource_size(entry->res)); + index++; + } + } + + return 0; +} + +static int mc_platform_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct platform_device *pdev = to_platform_device(dev); + struct mc_pcie *port; + void __iomem *bridge_base_addr; + void __iomem *ctrl_base_addr; + int ret; + int irq; + int i, intx_irq, msi_irq, event_irq; + u32 val; + int err; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + port->dev = dev; + + ret = mc_pcie_init_clks(dev); + if (ret) { + dev_err(dev, "failed to get clock resources, error %d\n", ret); + return -ENODEV; + } + + port->axi_base_addr = devm_platform_ioremap_resource(pdev, 1); + if (IS_ERR(port->axi_base_addr)) + return PTR_ERR(port->axi_base_addr); + + bridge_base_addr = port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; + ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR; + + port->msi.vector_phy = MSI_ADDR; + port->msi.num_vectors = MC_NUM_MSI_IRQS; + ret = mc_pcie_init_irq_domains(port); + if (ret) { + dev_err(dev, "failed creating IRQ domains\n"); + return ret; + } + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return -ENODEV; + + for (i = 0; i < NUM_EVENTS; i++) { + event_irq = irq_create_mapping(port->event_domain, i); + if (!event_irq) { + dev_err(dev, "failed to map hwirq %d\n", i); + return -ENXIO; + } + + err = devm_request_irq(dev, event_irq, mc_event_handler, + 0, event_cause[i].sym, port); + if (err) { + dev_err(dev, "failed to request IRQ %d\n", event_irq); + return err; + } + } + + intx_irq = irq_create_mapping(port->event_domain, + EVENT_LOCAL_PM_MSI_INT_INTX); + if (!intx_irq) { + dev_err(dev, "failed to map INTx interrupt\n"); + return -ENXIO; + } + + /* Plug the INTx chained handler */ + irq_set_chained_handler_and_data(intx_irq, mc_handle_intx, port); + + msi_irq = irq_create_mapping(port->event_domain, + EVENT_LOCAL_PM_MSI_INT_MSI); + if (!msi_irq) + return -ENXIO; + + /* Plug the MSI chained handler */ + irq_set_chained_handler_and_data(msi_irq, mc_handle_msi, port); + + /* Plug the main event chained handler */ + irq_set_chained_handler_and_data(irq, mc_handle_event, port); + + /* Hardware doesn't setup MSI by default */ + mc_pcie_enable_msi(port, cfg->win); + + val = readl_relaxed(bridge_base_addr + IMASK_LOCAL); + val |= PM_MSI_INT_INTX_MASK; + writel_relaxed(val, bridge_base_addr + IMASK_LOCAL); + + writel_relaxed(val, ctrl_base_addr + ECC_CONTROL); + + val = PCIE_EVENT_INT_L2_EXIT_INT | + PCIE_EVENT_INT_HOTRST_EXIT_INT | + PCIE_EVENT_INT_DLUP_EXIT_INT; + writel_relaxed(val, ctrl_base_addr + PCIE_EVENT_INT); + + val = SEC_ERROR_INT_TX_RAM_SEC_ERR_INT | + SEC_ERROR_INT_RX_RAM_SEC_ERR_INT | + SEC_ERROR_INT_PCIE2AXI_RAM_SEC_ERR_INT | + SEC_ERROR_INT_AXI2PCIE_RAM_SEC_ERR_INT; + writel_relaxed(val, ctrl_base_addr + SEC_ERROR_INT); + writel_relaxed(0, ctrl_base_addr + SEC_ERROR_INT_MASK); + writel_relaxed(0, ctrl_base_addr + SEC_ERROR_CNT); + + val = DED_ERROR_INT_TX_RAM_DED_ERR_INT | + DED_ERROR_INT_RX_RAM_DED_ERR_INT | + DED_ERROR_INT_PCIE2AXI_RAM_DED_ERR_INT | + DED_ERROR_INT_AXI2PCIE_RAM_DED_ERR_INT; + writel_relaxed(val, ctrl_base_addr + DED_ERROR_INT); + writel_relaxed(0, ctrl_base_addr + DED_ERROR_INT_MASK); + writel_relaxed(0, ctrl_base_addr + DED_ERROR_CNT); + + writel_relaxed(0, bridge_base_addr + IMASK_HOST); + writel_relaxed(GENMASK(31, 0), bridge_base_addr + ISTATUS_HOST); + + /* Configure Address Translation Table 0 for PCIe config space */ + mc_pcie_setup_window(bridge_base_addr, 0, cfg->res.start & 0xffffffff, + cfg->res.start, resource_size(&cfg->res)); + + return mc_pcie_setup_windows(pdev, port); +} + +static const struct pci_ecam_ops mc_ecam_ops = { + .init = mc_platform_init, + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +static const struct of_device_id mc_pcie_of_match[] = { + { + .compatible = "microchip,pcie-host-1.0", + .data = &mc_ecam_ops, + }, + {}, +}; + +MODULE_DEVICE_TABLE(of, mc_pcie_of_match); + +static struct platform_driver mc_pcie_driver = { + .probe = pci_host_common_probe, + .driver = { + .name = "microchip-pcie", + .of_match_table = mc_pcie_of_match, + .suppress_bind_attrs = true, + }, +}; + +builtin_platform_driver(mc_pcie_driver); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Microchip PCIe host controller driver"); +MODULE_AUTHOR("Daire McNamara <daire.mcnamara@microchip.com>"); diff --git a/drivers/pci/controller/pcie-mt7621.c b/drivers/pci/controller/pcie-mt7621.c new file mode 100644 index 000000000..63a5f4463 --- /dev/null +++ b/drivers/pci/controller/pcie-mt7621.c @@ -0,0 +1,554 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * BRIEF MODULE DESCRIPTION + * PCI init for Ralink RT2880 solution + * + * Copyright 2007 Ralink Inc. (bruce_chang@ralinktech.com.tw) + * + * May 2007 Bruce Chang + * Initial Release + * + * May 2009 Bruce Chang + * support RT2880/RT3883 PCIe + * + * May 2011 Bruce Chang + * support RT6855/MT7620 PCIe + */ + +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/reset.h> +#include <linux/sys_soc.h> + +#include "../pci.h" + +/* MediaTek-specific configuration registers */ +#define PCIE_FTS_NUM 0x70c +#define PCIE_FTS_NUM_MASK GENMASK(15, 8) +#define PCIE_FTS_NUM_L0(x) (((x) & 0xff) << 8) + +/* Host-PCI bridge registers */ +#define RALINK_PCI_PCICFG_ADDR 0x0000 +#define RALINK_PCI_PCIMSK_ADDR 0x000c +#define RALINK_PCI_CONFIG_ADDR 0x0020 +#define RALINK_PCI_CONFIG_DATA 0x0024 +#define RALINK_PCI_MEMBASE 0x0028 +#define RALINK_PCI_IOBASE 0x002c + +/* PCIe RC control registers */ +#define RALINK_PCI_ID 0x0030 +#define RALINK_PCI_CLASS 0x0034 +#define RALINK_PCI_SUBID 0x0038 +#define RALINK_PCI_STATUS 0x0050 + +/* Some definition values */ +#define PCIE_REVISION_ID BIT(0) +#define PCIE_CLASS_CODE (0x60400 << 8) +#define PCIE_BAR_MAP_MAX GENMASK(30, 16) +#define PCIE_BAR_ENABLE BIT(0) +#define PCIE_PORT_INT_EN(x) BIT(20 + (x)) +#define PCIE_PORT_LINKUP BIT(0) +#define PCIE_PORT_CNT 3 + +#define INIT_PORTS_DELAY_MS 100 +#define PERST_DELAY_MS 100 + +/** + * struct mt7621_pcie_port - PCIe port information + * @base: I/O mapped register base + * @list: port list + * @pcie: pointer to PCIe host info + * @clk: pointer to the port clock gate + * @phy: pointer to PHY control block + * @pcie_rst: pointer to port reset control + * @gpio_rst: gpio reset + * @slot: port slot + * @enabled: indicates if port is enabled + */ +struct mt7621_pcie_port { + void __iomem *base; + struct list_head list; + struct mt7621_pcie *pcie; + struct clk *clk; + struct phy *phy; + struct reset_control *pcie_rst; + struct gpio_desc *gpio_rst; + u32 slot; + bool enabled; +}; + +/** + * struct mt7621_pcie - PCIe host information + * @base: IO Mapped Register Base + * @dev: Pointer to PCIe device + * @ports: pointer to PCIe port information + * @resets_inverted: depends on chip revision + * reset lines are inverted. + */ +struct mt7621_pcie { + struct device *dev; + void __iomem *base; + struct list_head ports; + bool resets_inverted; +}; + +static inline u32 pcie_read(struct mt7621_pcie *pcie, u32 reg) +{ + return readl_relaxed(pcie->base + reg); +} + +static inline void pcie_write(struct mt7621_pcie *pcie, u32 val, u32 reg) +{ + writel_relaxed(val, pcie->base + reg); +} + +static inline u32 pcie_port_read(struct mt7621_pcie_port *port, u32 reg) +{ + return readl_relaxed(port->base + reg); +} + +static inline void pcie_port_write(struct mt7621_pcie_port *port, + u32 val, u32 reg) +{ + writel_relaxed(val, port->base + reg); +} + +static void __iomem *mt7621_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct mt7621_pcie *pcie = bus->sysdata; + u32 address = PCI_CONF1_EXT_ADDRESS(bus->number, PCI_SLOT(devfn), + PCI_FUNC(devfn), where); + + writel_relaxed(address, pcie->base + RALINK_PCI_CONFIG_ADDR); + + return pcie->base + RALINK_PCI_CONFIG_DATA + (where & 3); +} + +static struct pci_ops mt7621_pcie_ops = { + .map_bus = mt7621_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static u32 read_config(struct mt7621_pcie *pcie, unsigned int dev, u32 reg) +{ + u32 address = PCI_CONF1_EXT_ADDRESS(0, dev, 0, reg); + + pcie_write(pcie, address, RALINK_PCI_CONFIG_ADDR); + return pcie_read(pcie, RALINK_PCI_CONFIG_DATA); +} + +static void write_config(struct mt7621_pcie *pcie, unsigned int dev, + u32 reg, u32 val) +{ + u32 address = PCI_CONF1_EXT_ADDRESS(0, dev, 0, reg); + + pcie_write(pcie, address, RALINK_PCI_CONFIG_ADDR); + pcie_write(pcie, val, RALINK_PCI_CONFIG_DATA); +} + +static inline void mt7621_rst_gpio_pcie_assert(struct mt7621_pcie_port *port) +{ + if (port->gpio_rst) + gpiod_set_value(port->gpio_rst, 1); +} + +static inline void mt7621_rst_gpio_pcie_deassert(struct mt7621_pcie_port *port) +{ + if (port->gpio_rst) + gpiod_set_value(port->gpio_rst, 0); +} + +static inline bool mt7621_pcie_port_is_linkup(struct mt7621_pcie_port *port) +{ + return (pcie_port_read(port, RALINK_PCI_STATUS) & PCIE_PORT_LINKUP) != 0; +} + +static inline void mt7621_control_assert(struct mt7621_pcie_port *port) +{ + struct mt7621_pcie *pcie = port->pcie; + + if (pcie->resets_inverted) + reset_control_assert(port->pcie_rst); + else + reset_control_deassert(port->pcie_rst); +} + +static inline void mt7621_control_deassert(struct mt7621_pcie_port *port) +{ + struct mt7621_pcie *pcie = port->pcie; + + if (pcie->resets_inverted) + reset_control_deassert(port->pcie_rst); + else + reset_control_assert(port->pcie_rst); +} + +static int mt7621_pcie_parse_port(struct mt7621_pcie *pcie, + struct device_node *node, + int slot) +{ + struct mt7621_pcie_port *port; + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + char name[10]; + int err; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + port->base = devm_platform_ioremap_resource(pdev, slot + 1); + if (IS_ERR(port->base)) + return PTR_ERR(port->base); + + port->clk = devm_get_clk_from_child(dev, node, NULL); + if (IS_ERR(port->clk)) { + dev_err(dev, "failed to get pcie%d clock\n", slot); + return PTR_ERR(port->clk); + } + + port->pcie_rst = of_reset_control_get_exclusive(node, NULL); + if (PTR_ERR(port->pcie_rst) == -EPROBE_DEFER) { + dev_err(dev, "failed to get pcie%d reset control\n", slot); + return PTR_ERR(port->pcie_rst); + } + + snprintf(name, sizeof(name), "pcie-phy%d", slot); + port->phy = devm_of_phy_get(dev, node, name); + if (IS_ERR(port->phy)) { + dev_err(dev, "failed to get pcie-phy%d\n", slot); + err = PTR_ERR(port->phy); + goto remove_reset; + } + + port->gpio_rst = devm_gpiod_get_index_optional(dev, "reset", slot, + GPIOD_OUT_LOW); + if (IS_ERR(port->gpio_rst)) { + dev_err(dev, "failed to get GPIO for PCIe%d\n", slot); + err = PTR_ERR(port->gpio_rst); + goto remove_reset; + } + + port->slot = slot; + port->pcie = pcie; + + INIT_LIST_HEAD(&port->list); + list_add_tail(&port->list, &pcie->ports); + + return 0; + +remove_reset: + reset_control_put(port->pcie_rst); + return err; +} + +static int mt7621_pcie_parse_dt(struct mt7621_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + struct device_node *node = dev->of_node, *child; + int err; + + pcie->base = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + + for_each_available_child_of_node(node, child) { + int slot; + + err = of_pci_get_devfn(child); + if (err < 0) { + of_node_put(child); + dev_err(dev, "failed to parse devfn: %d\n", err); + return err; + } + + slot = PCI_SLOT(err); + + err = mt7621_pcie_parse_port(pcie, child, slot); + if (err) { + of_node_put(child); + return err; + } + } + + return 0; +} + +static int mt7621_pcie_init_port(struct mt7621_pcie_port *port) +{ + struct mt7621_pcie *pcie = port->pcie; + struct device *dev = pcie->dev; + u32 slot = port->slot; + int err; + + err = phy_init(port->phy); + if (err) { + dev_err(dev, "failed to initialize port%d phy\n", slot); + return err; + } + + err = phy_power_on(port->phy); + if (err) { + dev_err(dev, "failed to power on port%d phy\n", slot); + phy_exit(port->phy); + return err; + } + + port->enabled = true; + + return 0; +} + +static void mt7621_pcie_reset_assert(struct mt7621_pcie *pcie) +{ + struct mt7621_pcie_port *port; + + list_for_each_entry(port, &pcie->ports, list) { + /* PCIe RC reset assert */ + mt7621_control_assert(port); + + /* PCIe EP reset assert */ + mt7621_rst_gpio_pcie_assert(port); + } + + msleep(PERST_DELAY_MS); +} + +static void mt7621_pcie_reset_rc_deassert(struct mt7621_pcie *pcie) +{ + struct mt7621_pcie_port *port; + + list_for_each_entry(port, &pcie->ports, list) + mt7621_control_deassert(port); +} + +static void mt7621_pcie_reset_ep_deassert(struct mt7621_pcie *pcie) +{ + struct mt7621_pcie_port *port; + + list_for_each_entry(port, &pcie->ports, list) + mt7621_rst_gpio_pcie_deassert(port); + + msleep(PERST_DELAY_MS); +} + +static int mt7621_pcie_init_ports(struct mt7621_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct mt7621_pcie_port *port, *tmp; + u8 num_disabled = 0; + int err; + + mt7621_pcie_reset_assert(pcie); + mt7621_pcie_reset_rc_deassert(pcie); + + list_for_each_entry_safe(port, tmp, &pcie->ports, list) { + u32 slot = port->slot; + + if (slot == 1) { + port->enabled = true; + continue; + } + + err = mt7621_pcie_init_port(port); + if (err) { + dev_err(dev, "initializing port %d failed\n", slot); + list_del(&port->list); + } + } + + msleep(INIT_PORTS_DELAY_MS); + mt7621_pcie_reset_ep_deassert(pcie); + + tmp = NULL; + list_for_each_entry(port, &pcie->ports, list) { + u32 slot = port->slot; + + if (!mt7621_pcie_port_is_linkup(port)) { + dev_err(dev, "pcie%d no card, disable it (RST & CLK)\n", + slot); + mt7621_control_assert(port); + port->enabled = false; + num_disabled++; + + if (slot == 0) { + tmp = port; + continue; + } + + if (slot == 1 && tmp && !tmp->enabled) + phy_power_off(tmp->phy); + } + } + + return (num_disabled != PCIE_PORT_CNT) ? 0 : -ENODEV; +} + +static void mt7621_pcie_enable_port(struct mt7621_pcie_port *port) +{ + struct mt7621_pcie *pcie = port->pcie; + u32 slot = port->slot; + u32 val; + + /* enable pcie interrupt */ + val = pcie_read(pcie, RALINK_PCI_PCIMSK_ADDR); + val |= PCIE_PORT_INT_EN(slot); + pcie_write(pcie, val, RALINK_PCI_PCIMSK_ADDR); + + /* map 2G DDR region */ + pcie_port_write(port, PCIE_BAR_MAP_MAX | PCIE_BAR_ENABLE, + PCI_BASE_ADDRESS_0); + + /* configure class code and revision ID */ + pcie_port_write(port, PCIE_CLASS_CODE | PCIE_REVISION_ID, + RALINK_PCI_CLASS); + + /* configure RC FTS number to 250 when it leaves L0s */ + val = read_config(pcie, slot, PCIE_FTS_NUM); + val &= ~PCIE_FTS_NUM_MASK; + val |= PCIE_FTS_NUM_L0(0x50); + write_config(pcie, slot, PCIE_FTS_NUM, val); +} + +static int mt7621_pcie_enable_ports(struct pci_host_bridge *host) +{ + struct mt7621_pcie *pcie = pci_host_bridge_priv(host); + struct device *dev = pcie->dev; + struct mt7621_pcie_port *port; + struct resource_entry *entry; + int err; + + entry = resource_list_first_type(&host->windows, IORESOURCE_IO); + if (!entry) { + dev_err(dev, "cannot get io resource\n"); + return -EINVAL; + } + + /* Setup MEMWIN and IOWIN */ + pcie_write(pcie, 0xffffffff, RALINK_PCI_MEMBASE); + pcie_write(pcie, entry->res->start - entry->offset, RALINK_PCI_IOBASE); + + list_for_each_entry(port, &pcie->ports, list) { + if (port->enabled) { + err = clk_prepare_enable(port->clk); + if (err) { + dev_err(dev, "enabling clk pcie%d\n", + port->slot); + return err; + } + + mt7621_pcie_enable_port(port); + dev_info(dev, "PCIE%d enabled\n", port->slot); + } + } + + return 0; +} + +static int mt7621_pcie_register_host(struct pci_host_bridge *host) +{ + struct mt7621_pcie *pcie = pci_host_bridge_priv(host); + + host->ops = &mt7621_pcie_ops; + host->sysdata = pcie; + return pci_host_probe(host); +} + +static const struct soc_device_attribute mt7621_pcie_quirks_match[] = { + { .soc_id = "mt7621", .revision = "E2" }, + { /* sentinel */ } +}; + +static int mt7621_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + const struct soc_device_attribute *attr; + struct mt7621_pcie_port *port; + struct mt7621_pcie *pcie; + struct pci_host_bridge *bridge; + int err; + + if (!dev->of_node) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + pcie->dev = dev; + platform_set_drvdata(pdev, pcie); + INIT_LIST_HEAD(&pcie->ports); + + attr = soc_device_match(mt7621_pcie_quirks_match); + if (attr) + pcie->resets_inverted = true; + + err = mt7621_pcie_parse_dt(pcie); + if (err) { + dev_err(dev, "parsing DT failed\n"); + return err; + } + + err = mt7621_pcie_init_ports(pcie); + if (err) { + dev_err(dev, "nothing connected in virtual bridges\n"); + return 0; + } + + err = mt7621_pcie_enable_ports(bridge); + if (err) { + dev_err(dev, "error enabling pcie ports\n"); + goto remove_resets; + } + + return mt7621_pcie_register_host(bridge); + +remove_resets: + list_for_each_entry(port, &pcie->ports, list) + reset_control_put(port->pcie_rst); + + return err; +} + +static int mt7621_pcie_remove(struct platform_device *pdev) +{ + struct mt7621_pcie *pcie = platform_get_drvdata(pdev); + struct mt7621_pcie_port *port; + + list_for_each_entry(port, &pcie->ports, list) + reset_control_put(port->pcie_rst); + + return 0; +} + +static const struct of_device_id mt7621_pcie_ids[] = { + { .compatible = "mediatek,mt7621-pci" }, + {}, +}; +MODULE_DEVICE_TABLE(of, mt7621_pcie_ids); + +static struct platform_driver mt7621_pcie_driver = { + .probe = mt7621_pcie_probe, + .remove = mt7621_pcie_remove, + .driver = { + .name = "mt7621-pci", + .of_match_table = mt7621_pcie_ids, + }, +}; +builtin_platform_driver(mt7621_pcie_driver); + +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c new file mode 100644 index 000000000..f9682df1d --- /dev/null +++ b/drivers/pci/controller/pcie-rcar-ep.c @@ -0,0 +1,561 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe endpoint driver for Renesas R-Car SoCs + * Copyright (c) 2020 Renesas Electronics Europe GmbH + * + * Author: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com> + */ + +#include <linux/delay.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/pci-epc.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> + +#include "pcie-rcar.h" + +#define RCAR_EPC_MAX_FUNCTIONS 1 + +/* Structure representing the PCIe interface */ +struct rcar_pcie_endpoint { + struct rcar_pcie pcie; + phys_addr_t *ob_mapped_addr; + struct pci_epc_mem_window *ob_window; + u8 max_functions; + unsigned int bar_to_atu[MAX_NR_INBOUND_MAPS]; + unsigned long *ib_window_map; + u32 num_ib_windows; + u32 num_ob_windows; +}; + +static void rcar_pcie_ep_hw_init(struct rcar_pcie *pcie) +{ + u32 val; + + rcar_pci_write_reg(pcie, 0, PCIETCTLR); + + /* Set endpoint mode */ + rcar_pci_write_reg(pcie, 0, PCIEMSR); + + /* Initialize default capabilities. */ + rcar_rmw32(pcie, REXPCAP(0), 0xff, PCI_CAP_ID_EXP); + rcar_rmw32(pcie, REXPCAP(PCI_EXP_FLAGS), + PCI_EXP_FLAGS_TYPE, PCI_EXP_TYPE_ENDPOINT << 4); + rcar_rmw32(pcie, RCONF(PCI_HEADER_TYPE), 0x7f, + PCI_HEADER_TYPE_NORMAL); + + /* Write out the physical slot number = 0 */ + rcar_rmw32(pcie, REXPCAP(PCI_EXP_SLTCAP), PCI_EXP_SLTCAP_PSN, 0); + + val = rcar_pci_read_reg(pcie, EXPCAP(1)); + /* device supports fixed 128 bytes MPSS */ + val &= ~GENMASK(2, 0); + rcar_pci_write_reg(pcie, val, EXPCAP(1)); + + val = rcar_pci_read_reg(pcie, EXPCAP(2)); + /* read requests size 128 bytes */ + val &= ~GENMASK(14, 12); + /* payload size 128 bytes */ + val &= ~GENMASK(7, 5); + rcar_pci_write_reg(pcie, val, EXPCAP(2)); + + /* Set target link speed to 5.0 GT/s */ + rcar_rmw32(pcie, EXPCAP(12), PCI_EXP_LNKSTA_CLS, + PCI_EXP_LNKSTA_CLS_5_0GB); + + /* Set the completion timer timeout to the maximum 50ms. */ + rcar_rmw32(pcie, TLCTLR + 1, 0x3f, 50); + + /* Terminate list of capabilities (Next Capability Offset=0) */ + rcar_rmw32(pcie, RVCCAP(0), 0xfff00000, 0); + + /* flush modifications */ + wmb(); +} + +static int rcar_pcie_ep_get_window(struct rcar_pcie_endpoint *ep, + phys_addr_t addr) +{ + int i; + + for (i = 0; i < ep->num_ob_windows; i++) + if (ep->ob_window[i].phys_base == addr) + return i; + + return -EINVAL; +} + +static int rcar_pcie_parse_outbound_ranges(struct rcar_pcie_endpoint *ep, + struct platform_device *pdev) +{ + struct rcar_pcie *pcie = &ep->pcie; + char outbound_name[10]; + struct resource *res; + unsigned int i = 0; + + ep->num_ob_windows = 0; + for (i = 0; i < RCAR_PCI_MAX_RESOURCES; i++) { + sprintf(outbound_name, "memory%u", i); + res = platform_get_resource_byname(pdev, + IORESOURCE_MEM, + outbound_name); + if (!res) { + dev_err(pcie->dev, "missing outbound window %u\n", i); + return -EINVAL; + } + if (!devm_request_mem_region(&pdev->dev, res->start, + resource_size(res), + outbound_name)) { + dev_err(pcie->dev, "Cannot request memory region %s.\n", + outbound_name); + return -EIO; + } + + ep->ob_window[i].phys_base = res->start; + ep->ob_window[i].size = resource_size(res); + /* controller doesn't support multiple allocation + * from same window, so set page_size to window size + */ + ep->ob_window[i].page_size = resource_size(res); + } + ep->num_ob_windows = i; + + return 0; +} + +static int rcar_pcie_ep_get_pdata(struct rcar_pcie_endpoint *ep, + struct platform_device *pdev) +{ + struct rcar_pcie *pcie = &ep->pcie; + struct pci_epc_mem_window *window; + struct device *dev = pcie->dev; + struct resource res; + int err; + + err = of_address_to_resource(dev->of_node, 0, &res); + if (err) + return err; + pcie->base = devm_ioremap_resource(dev, &res); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + + ep->ob_window = devm_kcalloc(dev, RCAR_PCI_MAX_RESOURCES, + sizeof(*window), GFP_KERNEL); + if (!ep->ob_window) + return -ENOMEM; + + rcar_pcie_parse_outbound_ranges(ep, pdev); + + err = of_property_read_u8(dev->of_node, "max-functions", + &ep->max_functions); + if (err < 0 || ep->max_functions > RCAR_EPC_MAX_FUNCTIONS) + ep->max_functions = RCAR_EPC_MAX_FUNCTIONS; + + return 0; +} + +static int rcar_pcie_ep_write_header(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_header *hdr) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + struct rcar_pcie *pcie = &ep->pcie; + u32 val; + + if (!fn) + val = hdr->vendorid; + else + val = rcar_pci_read_reg(pcie, IDSETR0); + val |= hdr->deviceid << 16; + rcar_pci_write_reg(pcie, val, IDSETR0); + + val = hdr->revid; + val |= hdr->progif_code << 8; + val |= hdr->subclass_code << 16; + val |= hdr->baseclass_code << 24; + rcar_pci_write_reg(pcie, val, IDSETR1); + + if (!fn) + val = hdr->subsys_vendor_id; + else + val = rcar_pci_read_reg(pcie, SUBIDSETR); + val |= hdr->subsys_id << 16; + rcar_pci_write_reg(pcie, val, SUBIDSETR); + + if (hdr->interrupt_pin > PCI_INTERRUPT_INTA) + return -EINVAL; + val = rcar_pci_read_reg(pcie, PCICONF(15)); + val |= (hdr->interrupt_pin << 8); + rcar_pci_write_reg(pcie, val, PCICONF(15)); + + return 0; +} + +static int rcar_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, + struct pci_epf_bar *epf_bar) +{ + int flags = epf_bar->flags | LAR_ENABLE | LAM_64BIT; + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + u64 size = 1ULL << fls64(epf_bar->size - 1); + dma_addr_t cpu_addr = epf_bar->phys_addr; + enum pci_barno bar = epf_bar->barno; + struct rcar_pcie *pcie = &ep->pcie; + u32 mask; + int idx; + int err; + + idx = find_first_zero_bit(ep->ib_window_map, ep->num_ib_windows); + if (idx >= ep->num_ib_windows) { + dev_err(pcie->dev, "no free inbound window\n"); + return -EINVAL; + } + + if ((flags & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) + flags |= IO_SPACE; + + ep->bar_to_atu[bar] = idx; + /* use 64-bit BARs */ + set_bit(idx, ep->ib_window_map); + set_bit(idx + 1, ep->ib_window_map); + + if (cpu_addr > 0) { + unsigned long nr_zeros = __ffs64(cpu_addr); + u64 alignment = 1ULL << nr_zeros; + + size = min(size, alignment); + } + + size = min(size, 1ULL << 32); + + mask = roundup_pow_of_two(size) - 1; + mask &= ~0xf; + + rcar_pcie_set_inbound(pcie, cpu_addr, + 0x0, mask | flags, idx, false); + + err = rcar_pcie_wait_for_phyrdy(pcie); + if (err) { + dev_err(pcie->dev, "phy not ready\n"); + return -EINVAL; + } + + return 0; +} + +static void rcar_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_bar *epf_bar) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + enum pci_barno bar = epf_bar->barno; + u32 atu_index = ep->bar_to_atu[bar]; + + rcar_pcie_set_inbound(&ep->pcie, 0x0, 0x0, 0x0, bar, false); + + clear_bit(atu_index, ep->ib_window_map); + clear_bit(atu_index + 1, ep->ib_window_map); +} + +static int rcar_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, + u8 interrupts) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + struct rcar_pcie *pcie = &ep->pcie; + u32 flags; + + flags = rcar_pci_read_reg(pcie, MSICAP(fn)); + flags |= interrupts << MSICAP0_MMESCAP_OFFSET; + rcar_pci_write_reg(pcie, flags, MSICAP(fn)); + + return 0; +} + +static int rcar_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + struct rcar_pcie *pcie = &ep->pcie; + u32 flags; + + flags = rcar_pci_read_reg(pcie, MSICAP(fn)); + if (!(flags & MSICAP0_MSIE)) + return -EINVAL; + + return ((flags & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET); +} + +static int rcar_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr, u64 pci_addr, size_t size) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + struct rcar_pcie *pcie = &ep->pcie; + struct resource_entry win; + struct resource res; + int window; + int err; + + /* check if we have a link. */ + err = rcar_pcie_wait_for_dl(pcie); + if (err) { + dev_err(pcie->dev, "link not up\n"); + return err; + } + + window = rcar_pcie_ep_get_window(ep, addr); + if (window < 0) { + dev_err(pcie->dev, "failed to get corresponding window\n"); + return -EINVAL; + } + + memset(&win, 0x0, sizeof(win)); + memset(&res, 0x0, sizeof(res)); + res.start = pci_addr; + res.end = pci_addr + size - 1; + res.flags = IORESOURCE_MEM; + win.res = &res; + + rcar_pcie_set_outbound(pcie, window, &win); + + ep->ob_mapped_addr[window] = addr; + + return 0; +} + +static void rcar_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + struct resource_entry win; + struct resource res; + int idx; + + for (idx = 0; idx < ep->num_ob_windows; idx++) + if (ep->ob_mapped_addr[idx] == addr) + break; + + if (idx >= ep->num_ob_windows) + return; + + memset(&win, 0x0, sizeof(win)); + memset(&res, 0x0, sizeof(res)); + win.res = &res; + rcar_pcie_set_outbound(&ep->pcie, idx, &win); + + ep->ob_mapped_addr[idx] = 0; +} + +static int rcar_pcie_ep_assert_intx(struct rcar_pcie_endpoint *ep, + u8 fn, u8 intx) +{ + struct rcar_pcie *pcie = &ep->pcie; + u32 val; + + val = rcar_pci_read_reg(pcie, PCIEMSITXR); + if ((val & PCI_MSI_FLAGS_ENABLE)) { + dev_err(pcie->dev, "MSI is enabled, cannot assert INTx\n"); + return -EINVAL; + } + + val = rcar_pci_read_reg(pcie, PCICONF(1)); + if ((val & INTDIS)) { + dev_err(pcie->dev, "INTx message transmission is disabled\n"); + return -EINVAL; + } + + val = rcar_pci_read_reg(pcie, PCIEINTXR); + if ((val & ASTINTX)) { + dev_err(pcie->dev, "INTx is already asserted\n"); + return -EINVAL; + } + + val |= ASTINTX; + rcar_pci_write_reg(pcie, val, PCIEINTXR); + usleep_range(1000, 1001); + val = rcar_pci_read_reg(pcie, PCIEINTXR); + val &= ~ASTINTX; + rcar_pci_write_reg(pcie, val, PCIEINTXR); + + return 0; +} + +static int rcar_pcie_ep_assert_msi(struct rcar_pcie *pcie, + u8 fn, u8 interrupt_num) +{ + u16 msi_count; + u32 val; + + /* Check MSI enable bit */ + val = rcar_pci_read_reg(pcie, MSICAP(fn)); + if (!(val & MSICAP0_MSIE)) + return -EINVAL; + + /* Get MSI numbers from MME */ + msi_count = ((val & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET); + msi_count = 1 << msi_count; + + if (!interrupt_num || interrupt_num > msi_count) + return -EINVAL; + + val = rcar_pci_read_reg(pcie, PCIEMSITXR); + rcar_pci_write_reg(pcie, val | (interrupt_num - 1), PCIEMSITXR); + + return 0; +} + +static int rcar_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn, + enum pci_epc_irq_type type, + u16 interrupt_num) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + return rcar_pcie_ep_assert_intx(ep, fn, 0); + + case PCI_EPC_IRQ_MSI: + return rcar_pcie_ep_assert_msi(&ep->pcie, fn, interrupt_num); + + default: + return -EINVAL; + } +} + +static int rcar_pcie_ep_start(struct pci_epc *epc) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + + rcar_pci_write_reg(&ep->pcie, MACCTLR_INIT_VAL, MACCTLR); + rcar_pci_write_reg(&ep->pcie, CFINIT, PCIETCTLR); + + return 0; +} + +static void rcar_pcie_ep_stop(struct pci_epc *epc) +{ + struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); + + rcar_pci_write_reg(&ep->pcie, 0, PCIETCTLR); +} + +static const struct pci_epc_features rcar_pcie_epc_features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = false, + /* use 64-bit BARs so mark BAR[1,3,5] as reserved */ + .reserved_bar = 1 << BAR_1 | 1 << BAR_3 | 1 << BAR_5, + .bar_fixed_64bit = 1 << BAR_0 | 1 << BAR_2 | 1 << BAR_4, + .bar_fixed_size[0] = 128, + .bar_fixed_size[2] = 256, + .bar_fixed_size[4] = 256, +}; + +static const struct pci_epc_features* +rcar_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) +{ + return &rcar_pcie_epc_features; +} + +static const struct pci_epc_ops rcar_pcie_epc_ops = { + .write_header = rcar_pcie_ep_write_header, + .set_bar = rcar_pcie_ep_set_bar, + .clear_bar = rcar_pcie_ep_clear_bar, + .set_msi = rcar_pcie_ep_set_msi, + .get_msi = rcar_pcie_ep_get_msi, + .map_addr = rcar_pcie_ep_map_addr, + .unmap_addr = rcar_pcie_ep_unmap_addr, + .raise_irq = rcar_pcie_ep_raise_irq, + .start = rcar_pcie_ep_start, + .stop = rcar_pcie_ep_stop, + .get_features = rcar_pcie_ep_get_features, +}; + +static const struct of_device_id rcar_pcie_ep_of_match[] = { + { .compatible = "renesas,r8a774c0-pcie-ep", }, + { .compatible = "renesas,rcar-gen3-pcie-ep" }, + { }, +}; + +static int rcar_pcie_ep_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rcar_pcie_endpoint *ep; + struct rcar_pcie *pcie; + struct pci_epc *epc; + int err; + + ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + pcie = &ep->pcie; + pcie->dev = dev; + + pm_runtime_enable(dev); + err = pm_runtime_resume_and_get(dev); + if (err < 0) { + dev_err(dev, "pm_runtime_resume_and_get failed\n"); + goto err_pm_disable; + } + + err = rcar_pcie_ep_get_pdata(ep, pdev); + if (err < 0) { + dev_err(dev, "failed to request resources: %d\n", err); + goto err_pm_put; + } + + ep->num_ib_windows = MAX_NR_INBOUND_MAPS; + ep->ib_window_map = + devm_kcalloc(dev, BITS_TO_LONGS(ep->num_ib_windows), + sizeof(long), GFP_KERNEL); + if (!ep->ib_window_map) { + err = -ENOMEM; + dev_err(dev, "failed to allocate memory for inbound map\n"); + goto err_pm_put; + } + + ep->ob_mapped_addr = devm_kcalloc(dev, ep->num_ob_windows, + sizeof(*ep->ob_mapped_addr), + GFP_KERNEL); + if (!ep->ob_mapped_addr) { + err = -ENOMEM; + dev_err(dev, "failed to allocate memory for outbound memory pointers\n"); + goto err_pm_put; + } + + epc = devm_pci_epc_create(dev, &rcar_pcie_epc_ops); + if (IS_ERR(epc)) { + dev_err(dev, "failed to create epc device\n"); + err = PTR_ERR(epc); + goto err_pm_put; + } + + epc->max_functions = ep->max_functions; + epc_set_drvdata(epc, ep); + + rcar_pcie_ep_hw_init(pcie); + + err = pci_epc_multi_mem_init(epc, ep->ob_window, ep->num_ob_windows); + if (err < 0) { + dev_err(dev, "failed to initialize the epc memory space\n"); + goto err_pm_put; + } + + return 0; + +err_pm_put: + pm_runtime_put(dev); + +err_pm_disable: + pm_runtime_disable(dev); + + return err; +} + +static struct platform_driver rcar_pcie_ep_driver = { + .driver = { + .name = "rcar-pcie-ep", + .of_match_table = rcar_pcie_ep_of_match, + .suppress_bind_attrs = true, + }, + .probe = rcar_pcie_ep_probe, +}; +builtin_platform_driver(rcar_pcie_ep_driver); diff --git a/drivers/pci/controller/pcie-rcar-host.c b/drivers/pci/controller/pcie-rcar-host.c new file mode 100644 index 000000000..e4faf90fe --- /dev/null +++ b/drivers/pci/controller/pcie-rcar-host.c @@ -0,0 +1,1176 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe driver for Renesas R-Car SoCs + * Copyright (C) 2014-2020 Renesas Electronics Europe Ltd + * + * Based on: + * arch/sh/drivers/pci/pcie-sh7786.c + * arch/sh/drivers/pci/ops-sh7786.c + * Copyright (C) 2009 - 2011 Paul Mundt + * + * Author: Phil Edworthy <phil.edworthy@renesas.com> + */ + +#include <linux/bitops.h> +#include <linux/clk.h> +#include <linux/clk-provider.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/iopoll.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_irq.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> + +#include "pcie-rcar.h" + +struct rcar_msi { + DECLARE_BITMAP(used, INT_PCI_MSI_NR); + struct irq_domain *domain; + struct mutex map_lock; + spinlock_t mask_lock; + int irq1; + int irq2; +}; + +#ifdef CONFIG_ARM +/* + * Here we keep a static copy of the remapped PCIe controller address. + * This is only used on aarch32 systems, all of which have one single + * PCIe controller, to provide quick access to the PCIe controller in + * the L1 link state fixup function, called from the ARM fault handler. + */ +static void __iomem *pcie_base; +/* + * Static copy of PCIe device pointer, so we can check whether the + * device is runtime suspended or not. + */ +static struct device *pcie_dev; +#endif + +/* Structure representing the PCIe interface */ +struct rcar_pcie_host { + struct rcar_pcie pcie; + struct phy *phy; + struct clk *bus_clk; + struct rcar_msi msi; + int (*phy_init_fn)(struct rcar_pcie_host *host); +}; + +static DEFINE_SPINLOCK(pmsr_lock); + +static int rcar_pcie_wakeup(struct device *pcie_dev, void __iomem *pcie_base) +{ + unsigned long flags; + u32 pmsr, val; + int ret = 0; + + spin_lock_irqsave(&pmsr_lock, flags); + + if (!pcie_base || pm_runtime_suspended(pcie_dev)) { + ret = -EINVAL; + goto unlock_exit; + } + + pmsr = readl(pcie_base + PMSR); + + /* + * Test if the PCIe controller received PM_ENTER_L1 DLLP and + * the PCIe controller is not in L1 link state. If true, apply + * fix, which will put the controller into L1 link state, from + * which it can return to L0s/L0 on its own. + */ + if ((pmsr & PMEL1RX) && ((pmsr & PMSTATE) != PMSTATE_L1)) { + writel(L1IATN, pcie_base + PMCTLR); + ret = readl_poll_timeout_atomic(pcie_base + PMSR, val, + val & L1FAEG, 10, 1000); + WARN(ret, "Timeout waiting for L1 link state, ret=%d\n", ret); + writel(L1FAEG | PMEL1RX, pcie_base + PMSR); + } + +unlock_exit: + spin_unlock_irqrestore(&pmsr_lock, flags); + return ret; +} + +static struct rcar_pcie_host *msi_to_host(struct rcar_msi *msi) +{ + return container_of(msi, struct rcar_pcie_host, msi); +} + +static u32 rcar_read_conf(struct rcar_pcie *pcie, int where) +{ + unsigned int shift = BITS_PER_BYTE * (where & 3); + u32 val = rcar_pci_read_reg(pcie, where & ~3); + + return val >> shift; +} + +#ifdef CONFIG_ARM +#define __rcar_pci_rw_reg_workaround(instr) \ + " .arch armv7-a\n" \ + "1: " instr " %1, [%2]\n" \ + "2: isb\n" \ + "3: .pushsection .text.fixup,\"ax\"\n" \ + " .align 2\n" \ + "4: mov %0, #" __stringify(PCIBIOS_SET_FAILED) "\n" \ + " b 3b\n" \ + " .popsection\n" \ + " .pushsection __ex_table,\"a\"\n" \ + " .align 3\n" \ + " .long 1b, 4b\n" \ + " .long 2b, 4b\n" \ + " .popsection\n" +#endif + +static int rcar_pci_write_reg_workaround(struct rcar_pcie *pcie, u32 val, + unsigned int reg) +{ + int error = PCIBIOS_SUCCESSFUL; +#ifdef CONFIG_ARM + asm volatile( + __rcar_pci_rw_reg_workaround("str") + : "+r"(error):"r"(val), "r"(pcie->base + reg) : "memory"); +#else + rcar_pci_write_reg(pcie, val, reg); +#endif + return error; +} + +static int rcar_pci_read_reg_workaround(struct rcar_pcie *pcie, u32 *val, + unsigned int reg) +{ + int error = PCIBIOS_SUCCESSFUL; +#ifdef CONFIG_ARM + asm volatile( + __rcar_pci_rw_reg_workaround("ldr") + : "+r"(error), "=r"(*val) : "r"(pcie->base + reg) : "memory"); + + if (error != PCIBIOS_SUCCESSFUL) + PCI_SET_ERROR_RESPONSE(val); +#else + *val = rcar_pci_read_reg(pcie, reg); +#endif + return error; +} + +/* Serialization is provided by 'pci_lock' in drivers/pci/access.c */ +static int rcar_pcie_config_access(struct rcar_pcie_host *host, + unsigned char access_type, struct pci_bus *bus, + unsigned int devfn, int where, u32 *data) +{ + struct rcar_pcie *pcie = &host->pcie; + unsigned int dev, func, reg, index; + int ret; + + /* Wake the bus up in case it is in L1 state. */ + ret = rcar_pcie_wakeup(pcie->dev, pcie->base); + if (ret) { + PCI_SET_ERROR_RESPONSE(data); + return PCIBIOS_SET_FAILED; + } + + dev = PCI_SLOT(devfn); + func = PCI_FUNC(devfn); + reg = where & ~3; + index = reg / 4; + + /* + * While each channel has its own memory-mapped extended config + * space, it's generally only accessible when in endpoint mode. + * When in root complex mode, the controller is unable to target + * itself with either type 0 or type 1 accesses, and indeed, any + * controller initiated target transfer to its own config space + * result in a completer abort. + * + * Each channel effectively only supports a single device, but as + * the same channel <-> device access works for any PCI_SLOT() + * value, we cheat a bit here and bind the controller's config + * space to devfn 0 in order to enable self-enumeration. In this + * case the regular ECAR/ECDR path is sidelined and the mangled + * config access itself is initiated as an internal bus transaction. + */ + if (pci_is_root_bus(bus)) { + if (dev != 0) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (access_type == RCAR_PCI_ACCESS_READ) + *data = rcar_pci_read_reg(pcie, PCICONF(index)); + else + rcar_pci_write_reg(pcie, *data, PCICONF(index)); + + return PCIBIOS_SUCCESSFUL; + } + + /* Clear errors */ + rcar_pci_write_reg(pcie, rcar_pci_read_reg(pcie, PCIEERRFR), PCIEERRFR); + + /* Set the PIO address */ + rcar_pci_write_reg(pcie, PCIE_CONF_BUS(bus->number) | + PCIE_CONF_DEV(dev) | PCIE_CONF_FUNC(func) | reg, PCIECAR); + + /* Enable the configuration access */ + if (pci_is_root_bus(bus->parent)) + rcar_pci_write_reg(pcie, CONFIG_SEND_ENABLE | TYPE0, PCIECCTLR); + else + rcar_pci_write_reg(pcie, CONFIG_SEND_ENABLE | TYPE1, PCIECCTLR); + + /* Check for errors */ + if (rcar_pci_read_reg(pcie, PCIEERRFR) & UNSUPPORTED_REQUEST) + return PCIBIOS_DEVICE_NOT_FOUND; + + /* Check for master and target aborts */ + if (rcar_read_conf(pcie, RCONF(PCI_STATUS)) & + (PCI_STATUS_REC_MASTER_ABORT | PCI_STATUS_REC_TARGET_ABORT)) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (access_type == RCAR_PCI_ACCESS_READ) + ret = rcar_pci_read_reg_workaround(pcie, data, PCIECDR); + else + ret = rcar_pci_write_reg_workaround(pcie, *data, PCIECDR); + + /* Disable the configuration access */ + rcar_pci_write_reg(pcie, 0, PCIECCTLR); + + return ret; +} + +static int rcar_pcie_read_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct rcar_pcie_host *host = bus->sysdata; + int ret; + + ret = rcar_pcie_config_access(host, RCAR_PCI_ACCESS_READ, + bus, devfn, where, val); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + if (size == 1) + *val = (*val >> (BITS_PER_BYTE * (where & 3))) & 0xff; + else if (size == 2) + *val = (*val >> (BITS_PER_BYTE * (where & 2))) & 0xffff; + + dev_dbg(&bus->dev, "pcie-config-read: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08x\n", + bus->number, devfn, where, size, *val); + + return ret; +} + +/* Serialization is provided by 'pci_lock' in drivers/pci/access.c */ +static int rcar_pcie_write_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct rcar_pcie_host *host = bus->sysdata; + unsigned int shift; + u32 data; + int ret; + + ret = rcar_pcie_config_access(host, RCAR_PCI_ACCESS_READ, + bus, devfn, where, &data); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + dev_dbg(&bus->dev, "pcie-config-write: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08x\n", + bus->number, devfn, where, size, val); + + if (size == 1) { + shift = BITS_PER_BYTE * (where & 3); + data &= ~(0xff << shift); + data |= ((val & 0xff) << shift); + } else if (size == 2) { + shift = BITS_PER_BYTE * (where & 2); + data &= ~(0xffff << shift); + data |= ((val & 0xffff) << shift); + } else + data = val; + + ret = rcar_pcie_config_access(host, RCAR_PCI_ACCESS_WRITE, + bus, devfn, where, &data); + + return ret; +} + +static struct pci_ops rcar_pcie_ops = { + .read = rcar_pcie_read_conf, + .write = rcar_pcie_write_conf, +}; + +static void rcar_pcie_force_speedup(struct rcar_pcie *pcie) +{ + struct device *dev = pcie->dev; + unsigned int timeout = 1000; + u32 macsr; + + if ((rcar_pci_read_reg(pcie, MACS2R) & LINK_SPEED) != LINK_SPEED_5_0GTS) + return; + + if (rcar_pci_read_reg(pcie, MACCTLR) & SPEED_CHANGE) { + dev_err(dev, "Speed change already in progress\n"); + return; + } + + macsr = rcar_pci_read_reg(pcie, MACSR); + if ((macsr & LINK_SPEED) == LINK_SPEED_5_0GTS) + goto done; + + /* Set target link speed to 5.0 GT/s */ + rcar_rmw32(pcie, EXPCAP(12), PCI_EXP_LNKSTA_CLS, + PCI_EXP_LNKSTA_CLS_5_0GB); + + /* Set speed change reason as intentional factor */ + rcar_rmw32(pcie, MACCGSPSETR, SPCNGRSN, 0); + + /* Clear SPCHGFIN, SPCHGSUC, and SPCHGFAIL */ + if (macsr & (SPCHGFIN | SPCHGSUC | SPCHGFAIL)) + rcar_pci_write_reg(pcie, macsr, MACSR); + + /* Start link speed change */ + rcar_rmw32(pcie, MACCTLR, SPEED_CHANGE, SPEED_CHANGE); + + while (timeout--) { + macsr = rcar_pci_read_reg(pcie, MACSR); + if (macsr & SPCHGFIN) { + /* Clear the interrupt bits */ + rcar_pci_write_reg(pcie, macsr, MACSR); + + if (macsr & SPCHGFAIL) + dev_err(dev, "Speed change failed\n"); + + goto done; + } + + msleep(1); + } + + dev_err(dev, "Speed change timed out\n"); + +done: + dev_info(dev, "Current link speed is %s GT/s\n", + (macsr & LINK_SPEED) == LINK_SPEED_5_0GTS ? "5" : "2.5"); +} + +static void rcar_pcie_hw_enable(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + struct resource_entry *win; + LIST_HEAD(res); + int i = 0; + + /* Try setting 5 GT/s link speed */ + rcar_pcie_force_speedup(pcie); + + /* Setup PCI resources */ + resource_list_for_each_entry(win, &bridge->windows) { + struct resource *res = win->res; + + if (!res->flags) + continue; + + switch (resource_type(res)) { + case IORESOURCE_IO: + case IORESOURCE_MEM: + rcar_pcie_set_outbound(pcie, i, win); + i++; + break; + } + } +} + +static int rcar_pcie_enable(struct rcar_pcie_host *host) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + + rcar_pcie_hw_enable(host); + + pci_add_flags(PCI_REASSIGN_ALL_BUS); + + bridge->sysdata = host; + bridge->ops = &rcar_pcie_ops; + + return pci_host_probe(bridge); +} + +static int phy_wait_for_ack(struct rcar_pcie *pcie) +{ + struct device *dev = pcie->dev; + unsigned int timeout = 100; + + while (timeout--) { + if (rcar_pci_read_reg(pcie, H1_PCIEPHYADRR) & PHY_ACK) + return 0; + + udelay(100); + } + + dev_err(dev, "Access to PCIe phy timed out\n"); + + return -ETIMEDOUT; +} + +static void phy_write_reg(struct rcar_pcie *pcie, + unsigned int rate, u32 addr, + unsigned int lane, u32 data) +{ + u32 phyaddr; + + phyaddr = WRITE_CMD | + ((rate & 1) << RATE_POS) | + ((lane & 0xf) << LANE_POS) | + ((addr & 0xff) << ADR_POS); + + /* Set write data */ + rcar_pci_write_reg(pcie, data, H1_PCIEPHYDOUTR); + rcar_pci_write_reg(pcie, phyaddr, H1_PCIEPHYADRR); + + /* Ignore errors as they will be dealt with if the data link is down */ + phy_wait_for_ack(pcie); + + /* Clear command */ + rcar_pci_write_reg(pcie, 0, H1_PCIEPHYDOUTR); + rcar_pci_write_reg(pcie, 0, H1_PCIEPHYADRR); + + /* Ignore errors as they will be dealt with if the data link is down */ + phy_wait_for_ack(pcie); +} + +static int rcar_pcie_hw_init(struct rcar_pcie *pcie) +{ + int err; + + /* Begin initialization */ + rcar_pci_write_reg(pcie, 0, PCIETCTLR); + + /* Set mode */ + rcar_pci_write_reg(pcie, 1, PCIEMSR); + + err = rcar_pcie_wait_for_phyrdy(pcie); + if (err) + return err; + + /* + * Initial header for port config space is type 1, set the device + * class to match. Hardware takes care of propagating the IDSETR + * settings, so there is no need to bother with a quirk. + */ + rcar_pci_write_reg(pcie, PCI_CLASS_BRIDGE_PCI_NORMAL << 8, IDSETR1); + + /* + * Setup Secondary Bus Number & Subordinate Bus Number, even though + * they aren't used, to avoid bridge being detected as broken. + */ + rcar_rmw32(pcie, RCONF(PCI_SECONDARY_BUS), 0xff, 1); + rcar_rmw32(pcie, RCONF(PCI_SUBORDINATE_BUS), 0xff, 1); + + /* Initialize default capabilities. */ + rcar_rmw32(pcie, REXPCAP(0), 0xff, PCI_CAP_ID_EXP); + rcar_rmw32(pcie, REXPCAP(PCI_EXP_FLAGS), + PCI_EXP_FLAGS_TYPE, PCI_EXP_TYPE_ROOT_PORT << 4); + rcar_rmw32(pcie, RCONF(PCI_HEADER_TYPE), 0x7f, + PCI_HEADER_TYPE_BRIDGE); + + /* Enable data link layer active state reporting */ + rcar_rmw32(pcie, REXPCAP(PCI_EXP_LNKCAP), PCI_EXP_LNKCAP_DLLLARC, + PCI_EXP_LNKCAP_DLLLARC); + + /* Write out the physical slot number = 0 */ + rcar_rmw32(pcie, REXPCAP(PCI_EXP_SLTCAP), PCI_EXP_SLTCAP_PSN, 0); + + /* Set the completion timer timeout to the maximum 50ms. */ + rcar_rmw32(pcie, TLCTLR + 1, 0x3f, 50); + + /* Terminate list of capabilities (Next Capability Offset=0) */ + rcar_rmw32(pcie, RVCCAP(0), 0xfff00000, 0); + + /* Enable MSI */ + if (IS_ENABLED(CONFIG_PCI_MSI)) + rcar_pci_write_reg(pcie, 0x801f0000, PCIEMSITXR); + + rcar_pci_write_reg(pcie, MACCTLR_INIT_VAL, MACCTLR); + + /* Finish initialization - establish a PCI Express link */ + rcar_pci_write_reg(pcie, CFINIT, PCIETCTLR); + + /* This will timeout if we don't have a link. */ + err = rcar_pcie_wait_for_dl(pcie); + if (err) + return err; + + /* Enable INTx interrupts */ + rcar_rmw32(pcie, PCIEINTXR, 0, 0xF << 8); + + wmb(); + + return 0; +} + +static int rcar_pcie_phy_init_h1(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + + /* Initialize the phy */ + phy_write_reg(pcie, 0, 0x42, 0x1, 0x0EC34191); + phy_write_reg(pcie, 1, 0x42, 0x1, 0x0EC34180); + phy_write_reg(pcie, 0, 0x43, 0x1, 0x00210188); + phy_write_reg(pcie, 1, 0x43, 0x1, 0x00210188); + phy_write_reg(pcie, 0, 0x44, 0x1, 0x015C0014); + phy_write_reg(pcie, 1, 0x44, 0x1, 0x015C0014); + phy_write_reg(pcie, 1, 0x4C, 0x1, 0x786174A0); + phy_write_reg(pcie, 1, 0x4D, 0x1, 0x048000BB); + phy_write_reg(pcie, 0, 0x51, 0x1, 0x079EC062); + phy_write_reg(pcie, 0, 0x52, 0x1, 0x20000000); + phy_write_reg(pcie, 1, 0x52, 0x1, 0x20000000); + phy_write_reg(pcie, 1, 0x56, 0x1, 0x00003806); + + phy_write_reg(pcie, 0, 0x60, 0x1, 0x004B03A5); + phy_write_reg(pcie, 0, 0x64, 0x1, 0x3F0F1F0F); + phy_write_reg(pcie, 0, 0x66, 0x1, 0x00008000); + + return 0; +} + +static int rcar_pcie_phy_init_gen2(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + + /* + * These settings come from the R-Car Series, 2nd Generation User's + * Manual, section 50.3.1 (2) Initialization of the physical layer. + */ + rcar_pci_write_reg(pcie, 0x000f0030, GEN2_PCIEPHYADDR); + rcar_pci_write_reg(pcie, 0x00381203, GEN2_PCIEPHYDATA); + rcar_pci_write_reg(pcie, 0x00000001, GEN2_PCIEPHYCTRL); + rcar_pci_write_reg(pcie, 0x00000006, GEN2_PCIEPHYCTRL); + + rcar_pci_write_reg(pcie, 0x000f0054, GEN2_PCIEPHYADDR); + /* The following value is for DC connection, no termination resistor */ + rcar_pci_write_reg(pcie, 0x13802007, GEN2_PCIEPHYDATA); + rcar_pci_write_reg(pcie, 0x00000001, GEN2_PCIEPHYCTRL); + rcar_pci_write_reg(pcie, 0x00000006, GEN2_PCIEPHYCTRL); + + return 0; +} + +static int rcar_pcie_phy_init_gen3(struct rcar_pcie_host *host) +{ + int err; + + err = phy_init(host->phy); + if (err) + return err; + + err = phy_power_on(host->phy); + if (err) + phy_exit(host->phy); + + return err; +} + +static irqreturn_t rcar_pcie_msi_irq(int irq, void *data) +{ + struct rcar_pcie_host *host = data; + struct rcar_pcie *pcie = &host->pcie; + struct rcar_msi *msi = &host->msi; + struct device *dev = pcie->dev; + unsigned long reg; + + reg = rcar_pci_read_reg(pcie, PCIEMSIFR); + + /* MSI & INTx share an interrupt - we only handle MSI here */ + if (!reg) + return IRQ_NONE; + + while (reg) { + unsigned int index = find_first_bit(®, 32); + int ret; + + ret = generic_handle_domain_irq(msi->domain->parent, index); + if (ret) { + /* Unknown MSI, just clear it */ + dev_dbg(dev, "unexpected MSI\n"); + rcar_pci_write_reg(pcie, BIT(index), PCIEMSIFR); + } + + /* see if there's any more pending in this vector */ + reg = rcar_pci_read_reg(pcie, PCIEMSIFR); + } + + return IRQ_HANDLED; +} + +static void rcar_msi_top_irq_ack(struct irq_data *d) +{ + irq_chip_ack_parent(d); +} + +static void rcar_msi_top_irq_mask(struct irq_data *d) +{ + pci_msi_mask_irq(d); + irq_chip_mask_parent(d); +} + +static void rcar_msi_top_irq_unmask(struct irq_data *d) +{ + pci_msi_unmask_irq(d); + irq_chip_unmask_parent(d); +} + +static struct irq_chip rcar_msi_top_chip = { + .name = "PCIe MSI", + .irq_ack = rcar_msi_top_irq_ack, + .irq_mask = rcar_msi_top_irq_mask, + .irq_unmask = rcar_msi_top_irq_unmask, +}; + +static void rcar_msi_irq_ack(struct irq_data *d) +{ + struct rcar_msi *msi = irq_data_get_irq_chip_data(d); + struct rcar_pcie *pcie = &msi_to_host(msi)->pcie; + + /* clear the interrupt */ + rcar_pci_write_reg(pcie, BIT(d->hwirq), PCIEMSIFR); +} + +static void rcar_msi_irq_mask(struct irq_data *d) +{ + struct rcar_msi *msi = irq_data_get_irq_chip_data(d); + struct rcar_pcie *pcie = &msi_to_host(msi)->pcie; + unsigned long flags; + u32 value; + + spin_lock_irqsave(&msi->mask_lock, flags); + value = rcar_pci_read_reg(pcie, PCIEMSIIER); + value &= ~BIT(d->hwirq); + rcar_pci_write_reg(pcie, value, PCIEMSIIER); + spin_unlock_irqrestore(&msi->mask_lock, flags); +} + +static void rcar_msi_irq_unmask(struct irq_data *d) +{ + struct rcar_msi *msi = irq_data_get_irq_chip_data(d); + struct rcar_pcie *pcie = &msi_to_host(msi)->pcie; + unsigned long flags; + u32 value; + + spin_lock_irqsave(&msi->mask_lock, flags); + value = rcar_pci_read_reg(pcie, PCIEMSIIER); + value |= BIT(d->hwirq); + rcar_pci_write_reg(pcie, value, PCIEMSIIER); + spin_unlock_irqrestore(&msi->mask_lock, flags); +} + +static int rcar_msi_set_affinity(struct irq_data *d, const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static void rcar_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct rcar_msi *msi = irq_data_get_irq_chip_data(data); + struct rcar_pcie *pcie = &msi_to_host(msi)->pcie; + + msg->address_lo = rcar_pci_read_reg(pcie, PCIEMSIALR) & ~MSIFE; + msg->address_hi = rcar_pci_read_reg(pcie, PCIEMSIAUR); + msg->data = data->hwirq; +} + +static struct irq_chip rcar_msi_bottom_chip = { + .name = "Rcar MSI", + .irq_ack = rcar_msi_irq_ack, + .irq_mask = rcar_msi_irq_mask, + .irq_unmask = rcar_msi_irq_unmask, + .irq_set_affinity = rcar_msi_set_affinity, + .irq_compose_msi_msg = rcar_compose_msi_msg, +}; + +static int rcar_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct rcar_msi *msi = domain->host_data; + unsigned int i; + int hwirq; + + mutex_lock(&msi->map_lock); + + hwirq = bitmap_find_free_region(msi->used, INT_PCI_MSI_NR, order_base_2(nr_irqs)); + + mutex_unlock(&msi->map_lock); + + if (hwirq < 0) + return -ENOSPC; + + for (i = 0; i < nr_irqs; i++) + irq_domain_set_info(domain, virq + i, hwirq + i, + &rcar_msi_bottom_chip, domain->host_data, + handle_edge_irq, NULL, NULL); + + return 0; +} + +static void rcar_msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct rcar_msi *msi = domain->host_data; + + mutex_lock(&msi->map_lock); + + bitmap_release_region(msi->used, d->hwirq, order_base_2(nr_irqs)); + + mutex_unlock(&msi->map_lock); +} + +static const struct irq_domain_ops rcar_msi_domain_ops = { + .alloc = rcar_msi_domain_alloc, + .free = rcar_msi_domain_free, +}; + +static struct msi_domain_info rcar_msi_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_MULTI_PCI_MSI), + .chip = &rcar_msi_top_chip, +}; + +static int rcar_allocate_domains(struct rcar_msi *msi) +{ + struct rcar_pcie *pcie = &msi_to_host(msi)->pcie; + struct fwnode_handle *fwnode = dev_fwnode(pcie->dev); + struct irq_domain *parent; + + parent = irq_domain_create_linear(fwnode, INT_PCI_MSI_NR, + &rcar_msi_domain_ops, msi); + if (!parent) { + dev_err(pcie->dev, "failed to create IRQ domain\n"); + return -ENOMEM; + } + irq_domain_update_bus_token(parent, DOMAIN_BUS_NEXUS); + + msi->domain = pci_msi_create_irq_domain(fwnode, &rcar_msi_info, parent); + if (!msi->domain) { + dev_err(pcie->dev, "failed to create MSI domain\n"); + irq_domain_remove(parent); + return -ENOMEM; + } + + return 0; +} + +static void rcar_free_domains(struct rcar_msi *msi) +{ + struct irq_domain *parent = msi->domain->parent; + + irq_domain_remove(msi->domain); + irq_domain_remove(parent); +} + +static int rcar_pcie_enable_msi(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + struct device *dev = pcie->dev; + struct rcar_msi *msi = &host->msi; + struct resource res; + int err; + + mutex_init(&msi->map_lock); + spin_lock_init(&msi->mask_lock); + + err = of_address_to_resource(dev->of_node, 0, &res); + if (err) + return err; + + err = rcar_allocate_domains(msi); + if (err) + return err; + + /* Two irqs are for MSI, but they are also used for non-MSI irqs */ + err = devm_request_irq(dev, msi->irq1, rcar_pcie_msi_irq, + IRQF_SHARED | IRQF_NO_THREAD, + rcar_msi_bottom_chip.name, host); + if (err < 0) { + dev_err(dev, "failed to request IRQ: %d\n", err); + goto err; + } + + err = devm_request_irq(dev, msi->irq2, rcar_pcie_msi_irq, + IRQF_SHARED | IRQF_NO_THREAD, + rcar_msi_bottom_chip.name, host); + if (err < 0) { + dev_err(dev, "failed to request IRQ: %d\n", err); + goto err; + } + + /* disable all MSIs */ + rcar_pci_write_reg(pcie, 0, PCIEMSIIER); + + /* + * Setup MSI data target using RC base address address, which + * is guaranteed to be in the low 32bit range on any RCar HW. + */ + rcar_pci_write_reg(pcie, lower_32_bits(res.start) | MSIFE, PCIEMSIALR); + rcar_pci_write_reg(pcie, upper_32_bits(res.start), PCIEMSIAUR); + + return 0; + +err: + rcar_free_domains(msi); + return err; +} + +static void rcar_pcie_teardown_msi(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + + /* Disable all MSI interrupts */ + rcar_pci_write_reg(pcie, 0, PCIEMSIIER); + + /* Disable address decoding of the MSI interrupt, MSIFE */ + rcar_pci_write_reg(pcie, 0, PCIEMSIALR); + + rcar_free_domains(&host->msi); +} + +static int rcar_pcie_get_resources(struct rcar_pcie_host *host) +{ + struct rcar_pcie *pcie = &host->pcie; + struct device *dev = pcie->dev; + struct resource res; + int err, i; + + host->phy = devm_phy_optional_get(dev, "pcie"); + if (IS_ERR(host->phy)) + return PTR_ERR(host->phy); + + err = of_address_to_resource(dev->of_node, 0, &res); + if (err) + return err; + + pcie->base = devm_ioremap_resource(dev, &res); + if (IS_ERR(pcie->base)) + return PTR_ERR(pcie->base); + + host->bus_clk = devm_clk_get(dev, "pcie_bus"); + if (IS_ERR(host->bus_clk)) { + dev_err(dev, "cannot get pcie bus clock\n"); + return PTR_ERR(host->bus_clk); + } + + i = irq_of_parse_and_map(dev->of_node, 0); + if (!i) { + dev_err(dev, "cannot get platform resources for msi interrupt\n"); + err = -ENOENT; + goto err_irq1; + } + host->msi.irq1 = i; + + i = irq_of_parse_and_map(dev->of_node, 1); + if (!i) { + dev_err(dev, "cannot get platform resources for msi interrupt\n"); + err = -ENOENT; + goto err_irq2; + } + host->msi.irq2 = i; + +#ifdef CONFIG_ARM + /* Cache static copy for L1 link state fixup hook on aarch32 */ + pcie_base = pcie->base; + pcie_dev = pcie->dev; +#endif + + return 0; + +err_irq2: + irq_dispose_mapping(host->msi.irq1); +err_irq1: + return err; +} + +static int rcar_pcie_inbound_ranges(struct rcar_pcie *pcie, + struct resource_entry *entry, + int *index) +{ + u64 restype = entry->res->flags; + u64 cpu_addr = entry->res->start; + u64 cpu_end = entry->res->end; + u64 pci_addr = entry->res->start - entry->offset; + u32 flags = LAM_64BIT | LAR_ENABLE; + u64 mask; + u64 size = resource_size(entry->res); + int idx = *index; + + if (restype & IORESOURCE_PREFETCH) + flags |= LAM_PREFETCH; + + while (cpu_addr < cpu_end) { + if (idx >= MAX_NR_INBOUND_MAPS - 1) { + dev_err(pcie->dev, "Failed to map inbound regions!\n"); + return -EINVAL; + } + /* + * If the size of the range is larger than the alignment of + * the start address, we have to use multiple entries to + * perform the mapping. + */ + if (cpu_addr > 0) { + unsigned long nr_zeros = __ffs64(cpu_addr); + u64 alignment = 1ULL << nr_zeros; + + size = min(size, alignment); + } + /* Hardware supports max 4GiB inbound region */ + size = min(size, 1ULL << 32); + + mask = roundup_pow_of_two(size) - 1; + mask &= ~0xf; + + rcar_pcie_set_inbound(pcie, cpu_addr, pci_addr, + lower_32_bits(mask) | flags, idx, true); + + pci_addr += size; + cpu_addr += size; + idx += 2; + } + *index = idx; + + return 0; +} + +static int rcar_pcie_parse_map_dma_ranges(struct rcar_pcie_host *host) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + struct resource_entry *entry; + int index = 0, err = 0; + + resource_list_for_each_entry(entry, &bridge->dma_ranges) { + err = rcar_pcie_inbound_ranges(&host->pcie, entry, &index); + if (err) + break; + } + + return err; +} + +static const struct of_device_id rcar_pcie_of_match[] = { + { .compatible = "renesas,pcie-r8a7779", + .data = rcar_pcie_phy_init_h1 }, + { .compatible = "renesas,pcie-r8a7790", + .data = rcar_pcie_phy_init_gen2 }, + { .compatible = "renesas,pcie-r8a7791", + .data = rcar_pcie_phy_init_gen2 }, + { .compatible = "renesas,pcie-rcar-gen2", + .data = rcar_pcie_phy_init_gen2 }, + { .compatible = "renesas,pcie-r8a7795", + .data = rcar_pcie_phy_init_gen3 }, + { .compatible = "renesas,pcie-rcar-gen3", + .data = rcar_pcie_phy_init_gen3 }, + {}, +}; + +static int rcar_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rcar_pcie_host *host; + struct rcar_pcie *pcie; + u32 data; + int err; + struct pci_host_bridge *bridge; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*host)); + if (!bridge) + return -ENOMEM; + + host = pci_host_bridge_priv(bridge); + pcie = &host->pcie; + pcie->dev = dev; + platform_set_drvdata(pdev, host); + + pm_runtime_enable(pcie->dev); + err = pm_runtime_get_sync(pcie->dev); + if (err < 0) { + dev_err(pcie->dev, "pm_runtime_get_sync failed\n"); + goto err_pm_put; + } + + err = rcar_pcie_get_resources(host); + if (err < 0) { + dev_err(dev, "failed to request resources: %d\n", err); + goto err_pm_put; + } + + err = clk_prepare_enable(host->bus_clk); + if (err) { + dev_err(dev, "failed to enable bus clock: %d\n", err); + goto err_unmap_msi_irqs; + } + + err = rcar_pcie_parse_map_dma_ranges(host); + if (err) + goto err_clk_disable; + + host->phy_init_fn = of_device_get_match_data(dev); + err = host->phy_init_fn(host); + if (err) { + dev_err(dev, "failed to init PCIe PHY\n"); + goto err_clk_disable; + } + + /* Failure to get a link might just be that no cards are inserted */ + if (rcar_pcie_hw_init(pcie)) { + dev_info(dev, "PCIe link down\n"); + err = -ENODEV; + goto err_phy_shutdown; + } + + data = rcar_pci_read_reg(pcie, MACSR); + dev_info(dev, "PCIe x%d: link up\n", (data >> 20) & 0x3f); + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + err = rcar_pcie_enable_msi(host); + if (err < 0) { + dev_err(dev, + "failed to enable MSI support: %d\n", + err); + goto err_phy_shutdown; + } + } + + err = rcar_pcie_enable(host); + if (err) + goto err_msi_teardown; + + return 0; + +err_msi_teardown: + if (IS_ENABLED(CONFIG_PCI_MSI)) + rcar_pcie_teardown_msi(host); + +err_phy_shutdown: + if (host->phy) { + phy_power_off(host->phy); + phy_exit(host->phy); + } + +err_clk_disable: + clk_disable_unprepare(host->bus_clk); + +err_unmap_msi_irqs: + irq_dispose_mapping(host->msi.irq2); + irq_dispose_mapping(host->msi.irq1); + +err_pm_put: + pm_runtime_put(dev); + pm_runtime_disable(dev); + + return err; +} + +static int rcar_pcie_resume(struct device *dev) +{ + struct rcar_pcie_host *host = dev_get_drvdata(dev); + struct rcar_pcie *pcie = &host->pcie; + unsigned int data; + int err; + + err = rcar_pcie_parse_map_dma_ranges(host); + if (err) + return 0; + + /* Failure to get a link might just be that no cards are inserted */ + err = host->phy_init_fn(host); + if (err) { + dev_info(dev, "PCIe link down\n"); + return 0; + } + + data = rcar_pci_read_reg(pcie, MACSR); + dev_info(dev, "PCIe x%d: link up\n", (data >> 20) & 0x3f); + + /* Enable MSI */ + if (IS_ENABLED(CONFIG_PCI_MSI)) { + struct resource res; + u32 val; + + of_address_to_resource(dev->of_node, 0, &res); + rcar_pci_write_reg(pcie, upper_32_bits(res.start), PCIEMSIAUR); + rcar_pci_write_reg(pcie, lower_32_bits(res.start) | MSIFE, PCIEMSIALR); + + bitmap_to_arr32(&val, host->msi.used, INT_PCI_MSI_NR); + rcar_pci_write_reg(pcie, val, PCIEMSIIER); + } + + rcar_pcie_hw_enable(host); + + return 0; +} + +static int rcar_pcie_resume_noirq(struct device *dev) +{ + struct rcar_pcie_host *host = dev_get_drvdata(dev); + struct rcar_pcie *pcie = &host->pcie; + + if (rcar_pci_read_reg(pcie, PMSR) && + !(rcar_pci_read_reg(pcie, PCIETCTLR) & DL_DOWN)) + return 0; + + /* Re-establish the PCIe link */ + rcar_pci_write_reg(pcie, MACCTLR_INIT_VAL, MACCTLR); + rcar_pci_write_reg(pcie, CFINIT, PCIETCTLR); + return rcar_pcie_wait_for_dl(pcie); +} + +static const struct dev_pm_ops rcar_pcie_pm_ops = { + SYSTEM_SLEEP_PM_OPS(NULL, rcar_pcie_resume) + .resume_noirq = rcar_pcie_resume_noirq, +}; + +static struct platform_driver rcar_pcie_driver = { + .driver = { + .name = "rcar-pcie", + .of_match_table = rcar_pcie_of_match, + .pm = &rcar_pcie_pm_ops, + .suppress_bind_attrs = true, + }, + .probe = rcar_pcie_probe, +}; + +#ifdef CONFIG_ARM +static int rcar_pcie_aarch32_abort_handler(unsigned long addr, + unsigned int fsr, struct pt_regs *regs) +{ + return !fixup_exception(regs); +} + +static const struct of_device_id rcar_pcie_abort_handler_of_match[] __initconst = { + { .compatible = "renesas,pcie-r8a7779" }, + { .compatible = "renesas,pcie-r8a7790" }, + { .compatible = "renesas,pcie-r8a7791" }, + { .compatible = "renesas,pcie-rcar-gen2" }, + {}, +}; + +static int __init rcar_pcie_init(void) +{ + if (of_find_matching_node(NULL, rcar_pcie_abort_handler_of_match)) { +#ifdef CONFIG_ARM_LPAE + hook_fault_code(17, rcar_pcie_aarch32_abort_handler, SIGBUS, 0, + "asynchronous external abort"); +#else + hook_fault_code(22, rcar_pcie_aarch32_abort_handler, SIGBUS, 0, + "imprecise external abort"); +#endif + } + + return platform_driver_register(&rcar_pcie_driver); +} +device_initcall(rcar_pcie_init); +#else +builtin_platform_driver(rcar_pcie_driver); +#endif diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c new file mode 100644 index 000000000..7583699ef --- /dev/null +++ b/drivers/pci/controller/pcie-rcar.c @@ -0,0 +1,120 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe driver for Renesas R-Car SoCs + * Copyright (C) 2014-2020 Renesas Electronics Europe Ltd + * + * Author: Phil Edworthy <phil.edworthy@renesas.com> + */ + +#include <linux/delay.h> +#include <linux/pci.h> + +#include "pcie-rcar.h" + +void rcar_pci_write_reg(struct rcar_pcie *pcie, u32 val, unsigned int reg) +{ + writel(val, pcie->base + reg); +} + +u32 rcar_pci_read_reg(struct rcar_pcie *pcie, unsigned int reg) +{ + return readl(pcie->base + reg); +} + +void rcar_rmw32(struct rcar_pcie *pcie, int where, u32 mask, u32 data) +{ + unsigned int shift = BITS_PER_BYTE * (where & 3); + u32 val = rcar_pci_read_reg(pcie, where & ~3); + + val &= ~(mask << shift); + val |= data << shift; + rcar_pci_write_reg(pcie, val, where & ~3); +} + +int rcar_pcie_wait_for_phyrdy(struct rcar_pcie *pcie) +{ + unsigned int timeout = 10; + + while (timeout--) { + if (rcar_pci_read_reg(pcie, PCIEPHYSR) & PHYRDY) + return 0; + + msleep(5); + } + + return -ETIMEDOUT; +} + +int rcar_pcie_wait_for_dl(struct rcar_pcie *pcie) +{ + unsigned int timeout = 10000; + + while (timeout--) { + if ((rcar_pci_read_reg(pcie, PCIETSTR) & DATA_LINK_ACTIVE)) + return 0; + + udelay(5); + cpu_relax(); + } + + return -ETIMEDOUT; +} + +void rcar_pcie_set_outbound(struct rcar_pcie *pcie, int win, + struct resource_entry *window) +{ + /* Setup PCIe address space mappings for each resource */ + struct resource *res = window->res; + resource_size_t res_start; + resource_size_t size; + u32 mask; + + rcar_pci_write_reg(pcie, 0x00000000, PCIEPTCTLR(win)); + + /* + * The PAMR mask is calculated in units of 128Bytes, which + * keeps things pretty simple. + */ + size = resource_size(res); + if (size > 128) + mask = (roundup_pow_of_two(size) / SZ_128) - 1; + else + mask = 0x0; + rcar_pci_write_reg(pcie, mask << 7, PCIEPAMR(win)); + + if (res->flags & IORESOURCE_IO) + res_start = pci_pio_to_address(res->start) - window->offset; + else + res_start = res->start - window->offset; + + rcar_pci_write_reg(pcie, upper_32_bits(res_start), PCIEPAUR(win)); + rcar_pci_write_reg(pcie, lower_32_bits(res_start) & ~0x7F, + PCIEPALR(win)); + + /* First resource is for IO */ + mask = PAR_ENABLE; + if (res->flags & IORESOURCE_IO) + mask |= IO_SPACE; + + rcar_pci_write_reg(pcie, mask, PCIEPTCTLR(win)); +} + +void rcar_pcie_set_inbound(struct rcar_pcie *pcie, u64 cpu_addr, + u64 pci_addr, u64 flags, int idx, bool host) +{ + /* + * Set up 64-bit inbound regions as the range parser doesn't + * distinguish between 32 and 64-bit types. + */ + if (host) + rcar_pci_write_reg(pcie, lower_32_bits(pci_addr), + PCIEPRAR(idx)); + rcar_pci_write_reg(pcie, lower_32_bits(cpu_addr), PCIELAR(idx)); + rcar_pci_write_reg(pcie, flags, PCIELAMR(idx)); + + if (host) + rcar_pci_write_reg(pcie, upper_32_bits(pci_addr), + PCIEPRAR(idx + 1)); + rcar_pci_write_reg(pcie, upper_32_bits(cpu_addr), PCIELAR(idx + 1)); + rcar_pci_write_reg(pcie, 0, PCIELAMR(idx + 1)); +} diff --git a/drivers/pci/controller/pcie-rcar.h b/drivers/pci/controller/pcie-rcar.h new file mode 100644 index 000000000..9bb125db8 --- /dev/null +++ b/drivers/pci/controller/pcie-rcar.h @@ -0,0 +1,147 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * PCIe driver for Renesas R-Car SoCs + * Copyright (C) 2014-2020 Renesas Electronics Europe Ltd + * + * Author: Phil Edworthy <phil.edworthy@renesas.com> + */ + +#ifndef _PCIE_RCAR_H +#define _PCIE_RCAR_H + +#define PCIECAR 0x000010 +#define PCIECCTLR 0x000018 +#define CONFIG_SEND_ENABLE BIT(31) +#define TYPE0 (0 << 8) +#define TYPE1 BIT(8) +#define PCIECDR 0x000020 +#define PCIEMSR 0x000028 +#define PCIEINTXR 0x000400 +#define ASTINTX BIT(16) +#define PCIEPHYSR 0x0007f0 +#define PHYRDY BIT(0) +#define PCIEMSITXR 0x000840 + +/* Transfer control */ +#define PCIETCTLR 0x02000 +#define DL_DOWN BIT(3) +#define CFINIT BIT(0) +#define PCIETSTR 0x02004 +#define DATA_LINK_ACTIVE BIT(0) +#define PCIEERRFR 0x02020 +#define UNSUPPORTED_REQUEST BIT(4) +#define PCIEMSIFR 0x02044 +#define PCIEMSIALR 0x02048 +#define MSIFE BIT(0) +#define PCIEMSIAUR 0x0204c +#define PCIEMSIIER 0x02050 + +/* root port address */ +#define PCIEPRAR(x) (0x02080 + ((x) * 0x4)) + +/* local address reg & mask */ +#define PCIELAR(x) (0x02200 + ((x) * 0x20)) +#define PCIELAMR(x) (0x02208 + ((x) * 0x20)) +#define LAM_PREFETCH BIT(3) +#define LAM_64BIT BIT(2) +#define LAR_ENABLE BIT(1) + +/* PCIe address reg & mask */ +#define PCIEPALR(x) (0x03400 + ((x) * 0x20)) +#define PCIEPAUR(x) (0x03404 + ((x) * 0x20)) +#define PCIEPAMR(x) (0x03408 + ((x) * 0x20)) +#define PCIEPTCTLR(x) (0x0340c + ((x) * 0x20)) +#define PAR_ENABLE BIT(31) +#define IO_SPACE BIT(8) + +/* Configuration */ +#define PCICONF(x) (0x010000 + ((x) * 0x4)) +#define INTDIS BIT(10) +#define PMCAP(x) (0x010040 + ((x) * 0x4)) +#define MSICAP(x) (0x010050 + ((x) * 0x4)) +#define MSICAP0_MSIE BIT(16) +#define MSICAP0_MMESCAP_OFFSET 17 +#define MSICAP0_MMESE_OFFSET 20 +#define MSICAP0_MMESE_MASK GENMASK(22, 20) +#define EXPCAP(x) (0x010070 + ((x) * 0x4)) +#define VCCAP(x) (0x010100 + ((x) * 0x4)) + +/* link layer */ +#define IDSETR0 0x011000 +#define IDSETR1 0x011004 +#define SUBIDSETR 0x011024 +#define TLCTLR 0x011048 +#define MACSR 0x011054 +#define SPCHGFIN BIT(4) +#define SPCHGFAIL BIT(6) +#define SPCHGSUC BIT(7) +#define LINK_SPEED (0xf << 16) +#define LINK_SPEED_2_5GTS (1 << 16) +#define LINK_SPEED_5_0GTS (2 << 16) +#define MACCTLR 0x011058 +#define MACCTLR_NFTS_MASK GENMASK(23, 16) /* The name is from SH7786 */ +#define SPEED_CHANGE BIT(24) +#define SCRAMBLE_DISABLE BIT(27) +#define LTSMDIS BIT(31) +#define MACCTLR_INIT_VAL (LTSMDIS | MACCTLR_NFTS_MASK) +#define PMSR 0x01105c +#define L1FAEG BIT(31) +#define PMEL1RX BIT(23) +#define PMSTATE GENMASK(18, 16) +#define PMSTATE_L1 (3 << 16) +#define PMCTLR 0x011060 +#define L1IATN BIT(31) + +#define MACS2R 0x011078 +#define MACCGSPSETR 0x011084 +#define SPCNGRSN BIT(31) + +/* R-Car H1 PHY */ +#define H1_PCIEPHYADRR 0x04000c +#define WRITE_CMD BIT(16) +#define PHY_ACK BIT(24) +#define RATE_POS 12 +#define LANE_POS 8 +#define ADR_POS 0 +#define H1_PCIEPHYDOUTR 0x040014 + +/* R-Car Gen2 PHY */ +#define GEN2_PCIEPHYADDR 0x780 +#define GEN2_PCIEPHYDATA 0x784 +#define GEN2_PCIEPHYCTRL 0x78c + +#define INT_PCI_MSI_NR 32 + +#define RCONF(x) (PCICONF(0) + (x)) +#define RPMCAP(x) (PMCAP(0) + (x)) +#define REXPCAP(x) (EXPCAP(0) + (x)) +#define RVCCAP(x) (VCCAP(0) + (x)) + +#define PCIE_CONF_BUS(b) (((b) & 0xff) << 24) +#define PCIE_CONF_DEV(d) (((d) & 0x1f) << 19) +#define PCIE_CONF_FUNC(f) (((f) & 0x7) << 16) + +#define RCAR_PCI_MAX_RESOURCES 4 +#define MAX_NR_INBOUND_MAPS 6 + +struct rcar_pcie { + struct device *dev; + void __iomem *base; +}; + +enum { + RCAR_PCI_ACCESS_READ, + RCAR_PCI_ACCESS_WRITE, +}; + +void rcar_pci_write_reg(struct rcar_pcie *pcie, u32 val, unsigned int reg); +u32 rcar_pci_read_reg(struct rcar_pcie *pcie, unsigned int reg); +void rcar_rmw32(struct rcar_pcie *pcie, int where, u32 mask, u32 data); +int rcar_pcie_wait_for_phyrdy(struct rcar_pcie *pcie); +int rcar_pcie_wait_for_dl(struct rcar_pcie *pcie); +void rcar_pcie_set_outbound(struct rcar_pcie *pcie, int win, + struct resource_entry *window); +void rcar_pcie_set_inbound(struct rcar_pcie *pcie, u64 cpu_addr, + u64 pci_addr, u64 flags, int idx, bool host); + +#endif diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c new file mode 100644 index 000000000..0af0e965f --- /dev/null +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -0,0 +1,631 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Rockchip AXI PCIe endpoint controller driver + * + * Copyright (c) 2018 Rockchip, Inc. + * + * Author: Shawn Lin <shawn.lin@rock-chips.com> + * Simon Xue <xxm@rock-chips.com> + */ + +#include <linux/configfs.h> +#include <linux/delay.h> +#include <linux/kernel.h> +#include <linux/of.h> +#include <linux/pci-epc.h> +#include <linux/platform_device.h> +#include <linux/pci-epf.h> +#include <linux/sizes.h> + +#include "pcie-rockchip.h" + +/** + * struct rockchip_pcie_ep - private data for PCIe endpoint controller driver + * @rockchip: Rockchip PCIe controller + * @epc: PCI EPC device + * @max_regions: maximum number of regions supported by hardware + * @ob_region_map: bitmask of mapped outbound regions + * @ob_addr: base addresses in the AXI bus where the outbound regions start + * @irq_phys_addr: base address on the AXI bus where the MSI/legacy IRQ + * dedicated outbound regions is mapped. + * @irq_cpu_addr: base address in the CPU space where a write access triggers + * the sending of a memory write (MSI) / normal message (legacy + * IRQ) TLP through the PCIe bus. + * @irq_pci_addr: used to save the current mapping of the MSI/legacy IRQ + * dedicated outbound region. + * @irq_pci_fn: the latest PCI function that has updated the mapping of + * the MSI/legacy IRQ dedicated outbound region. + * @irq_pending: bitmask of asserted legacy IRQs. + */ +struct rockchip_pcie_ep { + struct rockchip_pcie rockchip; + struct pci_epc *epc; + u32 max_regions; + unsigned long ob_region_map; + phys_addr_t *ob_addr; + phys_addr_t irq_phys_addr; + void __iomem *irq_cpu_addr; + u64 irq_pci_addr; + u8 irq_pci_fn; + u8 irq_pending; +}; + +static void rockchip_pcie_clear_ep_ob_atu(struct rockchip_pcie *rockchip, + u32 region) +{ + rockchip_pcie_write(rockchip, 0, + ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0(region)); + rockchip_pcie_write(rockchip, 0, + ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR1(region)); + rockchip_pcie_write(rockchip, 0, + ROCKCHIP_PCIE_AT_OB_REGION_DESC0(region)); + rockchip_pcie_write(rockchip, 0, + ROCKCHIP_PCIE_AT_OB_REGION_DESC1(region)); +} + +static void rockchip_pcie_prog_ep_ob_atu(struct rockchip_pcie *rockchip, u8 fn, + u32 r, u64 cpu_addr, u64 pci_addr, + size_t size) +{ + int num_pass_bits = fls64(size - 1); + u32 addr0, addr1, desc0; + + if (num_pass_bits < 8) + num_pass_bits = 8; + + addr0 = ((num_pass_bits - 1) & PCIE_CORE_OB_REGION_ADDR0_NUM_BITS) | + (lower_32_bits(pci_addr) & PCIE_CORE_OB_REGION_ADDR0_LO_ADDR); + addr1 = upper_32_bits(pci_addr); + desc0 = ROCKCHIP_PCIE_AT_OB_REGION_DESC0_DEVFN(fn) | AXI_WRAPPER_MEM_WRITE; + + /* PCI bus address region */ + rockchip_pcie_write(rockchip, addr0, + ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0(r)); + rockchip_pcie_write(rockchip, addr1, + ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR1(r)); + rockchip_pcie_write(rockchip, desc0, + ROCKCHIP_PCIE_AT_OB_REGION_DESC0(r)); + rockchip_pcie_write(rockchip, 0, + ROCKCHIP_PCIE_AT_OB_REGION_DESC1(r)); +} + +static int rockchip_pcie_ep_write_header(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_header *hdr) +{ + u32 reg; + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + + /* All functions share the same vendor ID with function 0 */ + if (fn == 0) { + u32 vid_regs = (hdr->vendorid & GENMASK(15, 0)) | + (hdr->subsys_vendor_id & GENMASK(31, 16)) << 16; + + rockchip_pcie_write(rockchip, vid_regs, + PCIE_CORE_CONFIG_VENDOR); + } + + reg = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_DID_VID); + reg = (reg & 0xFFFF) | (hdr->deviceid << 16); + rockchip_pcie_write(rockchip, reg, PCIE_EP_CONFIG_DID_VID); + + rockchip_pcie_write(rockchip, + hdr->revid | + hdr->progif_code << 8 | + hdr->subclass_code << 16 | + hdr->baseclass_code << 24, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + PCI_REVISION_ID); + rockchip_pcie_write(rockchip, hdr->cache_line_size, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + + PCI_CACHE_LINE_SIZE); + rockchip_pcie_write(rockchip, hdr->subsys_id << 16, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + + PCI_SUBSYSTEM_VENDOR_ID); + rockchip_pcie_write(rockchip, hdr->interrupt_pin << 8, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + + PCI_INTERRUPT_LINE); + + return 0; +} + +static int rockchip_pcie_ep_set_bar(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_bar *epf_bar) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + dma_addr_t bar_phys = epf_bar->phys_addr; + enum pci_barno bar = epf_bar->barno; + int flags = epf_bar->flags; + u32 addr0, addr1, reg, cfg, b, aperture, ctrl; + u64 sz; + + /* BAR size is 2^(aperture + 7) */ + sz = max_t(size_t, epf_bar->size, MIN_EP_APERTURE); + + /* + * roundup_pow_of_two() returns an unsigned long, which is not suited + * for 64bit values. + */ + sz = 1ULL << fls64(sz - 1); + aperture = ilog2(sz) - 7; /* 128B -> 0, 256B -> 1, 512B -> 2, ... */ + + if ((flags & PCI_BASE_ADDRESS_SPACE) == PCI_BASE_ADDRESS_SPACE_IO) { + ctrl = ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_IO_32BITS; + } else { + bool is_prefetch = !!(flags & PCI_BASE_ADDRESS_MEM_PREFETCH); + bool is_64bits = sz > SZ_2G; + + if (is_64bits && (bar & 1)) + return -EINVAL; + + if (is_64bits && is_prefetch) + ctrl = + ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_PREFETCH_MEM_64BITS; + else if (is_prefetch) + ctrl = + ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_PREFETCH_MEM_32BITS; + else if (is_64bits) + ctrl = ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_MEM_64BITS; + else + ctrl = ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_MEM_32BITS; + } + + if (bar < BAR_4) { + reg = ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG0(fn); + b = bar; + } else { + reg = ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG1(fn); + b = bar - BAR_4; + } + + addr0 = lower_32_bits(bar_phys); + addr1 = upper_32_bits(bar_phys); + + cfg = rockchip_pcie_read(rockchip, reg); + cfg &= ~(ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b) | + ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)); + cfg |= (ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_APERTURE(b, aperture) | + ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_CTRL(b, ctrl)); + + rockchip_pcie_write(rockchip, cfg, reg); + rockchip_pcie_write(rockchip, addr0, + ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar)); + rockchip_pcie_write(rockchip, addr1, + ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar)); + + return 0; +} + +static void rockchip_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn, + struct pci_epf_bar *epf_bar) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + u32 reg, cfg, b, ctrl; + enum pci_barno bar = epf_bar->barno; + + if (bar < BAR_4) { + reg = ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG0(fn); + b = bar; + } else { + reg = ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG1(fn); + b = bar - BAR_4; + } + + ctrl = ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_DISABLED; + cfg = rockchip_pcie_read(rockchip, reg); + cfg &= ~(ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b) | + ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)); + cfg |= ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_CTRL(b, ctrl); + + rockchip_pcie_write(rockchip, cfg, reg); + rockchip_pcie_write(rockchip, 0x0, + ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar)); + rockchip_pcie_write(rockchip, 0x0, + ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar)); +} + +static inline u32 rockchip_ob_region(phys_addr_t addr) +{ + return (addr >> ilog2(SZ_1M)) & 0x1f; +} + +static int rockchip_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr, u64 pci_addr, + size_t size) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *pcie = &ep->rockchip; + u32 r = rockchip_ob_region(addr); + + rockchip_pcie_prog_ep_ob_atu(pcie, fn, r, addr, pci_addr, size); + + set_bit(r, &ep->ob_region_map); + ep->ob_addr[r] = addr; + + return 0; +} + +static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, + phys_addr_t addr) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + u32 r; + + for (r = 0; r < ep->max_regions; r++) + if (ep->ob_addr[r] == addr) + break; + + if (r == ep->max_regions) + return; + + rockchip_pcie_clear_ep_ob_atu(rockchip, r); + + ep->ob_addr[r] = 0; + clear_bit(r, &ep->ob_region_map); +} + +static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, + u8 multi_msg_cap) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + u32 flags; + + flags = rockchip_pcie_read(rockchip, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + + ROCKCHIP_PCIE_EP_MSI_CTRL_REG); + flags &= ~ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_MASK; + flags |= + (multi_msg_cap << ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET) | + (PCI_MSI_FLAGS_64BIT << ROCKCHIP_PCIE_EP_MSI_FLAGS_OFFSET); + flags &= ~ROCKCHIP_PCIE_EP_MSI_CTRL_MASK_MSI_CAP; + rockchip_pcie_write(rockchip, flags, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + + ROCKCHIP_PCIE_EP_MSI_CTRL_REG); + return 0; +} + +static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + u32 flags; + + flags = rockchip_pcie_read(rockchip, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + + ROCKCHIP_PCIE_EP_MSI_CTRL_REG); + if (!(flags & ROCKCHIP_PCIE_EP_MSI_CTRL_ME)) + return -EINVAL; + + return ((flags & ROCKCHIP_PCIE_EP_MSI_CTRL_MME_MASK) >> + ROCKCHIP_PCIE_EP_MSI_CTRL_MME_OFFSET); +} + +static void rockchip_pcie_ep_assert_intx(struct rockchip_pcie_ep *ep, u8 fn, + u8 intx, bool do_assert) +{ + struct rockchip_pcie *rockchip = &ep->rockchip; + + intx &= 3; + + if (do_assert) { + ep->irq_pending |= BIT(intx); + rockchip_pcie_write(rockchip, + PCIE_CLIENT_INT_IN_ASSERT | + PCIE_CLIENT_INT_PEND_ST_PEND, + PCIE_CLIENT_LEGACY_INT_CTRL); + } else { + ep->irq_pending &= ~BIT(intx); + rockchip_pcie_write(rockchip, + PCIE_CLIENT_INT_IN_DEASSERT | + PCIE_CLIENT_INT_PEND_ST_NORMAL, + PCIE_CLIENT_LEGACY_INT_CTRL); + } +} + +static int rockchip_pcie_ep_send_legacy_irq(struct rockchip_pcie_ep *ep, u8 fn, + u8 intx) +{ + u16 cmd; + + cmd = rockchip_pcie_read(&ep->rockchip, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + + ROCKCHIP_PCIE_EP_CMD_STATUS); + + if (cmd & PCI_COMMAND_INTX_DISABLE) + return -EINVAL; + + /* + * Should add some delay between toggling INTx per TRM vaguely saying + * it depends on some cycles of the AHB bus clock to function it. So + * add sufficient 1ms here. + */ + rockchip_pcie_ep_assert_intx(ep, fn, intx, true); + mdelay(1); + rockchip_pcie_ep_assert_intx(ep, fn, intx, false); + return 0; +} + +static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn, + u8 interrupt_num) +{ + struct rockchip_pcie *rockchip = &ep->rockchip; + u32 flags, mme, data, data_mask; + u8 msi_count; + u64 pci_addr; + u32 r; + + /* Check MSI enable bit */ + flags = rockchip_pcie_read(&ep->rockchip, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + + ROCKCHIP_PCIE_EP_MSI_CTRL_REG); + if (!(flags & ROCKCHIP_PCIE_EP_MSI_CTRL_ME)) + return -EINVAL; + + /* Get MSI numbers from MME */ + mme = ((flags & ROCKCHIP_PCIE_EP_MSI_CTRL_MME_MASK) >> + ROCKCHIP_PCIE_EP_MSI_CTRL_MME_OFFSET); + msi_count = 1 << mme; + if (!interrupt_num || interrupt_num > msi_count) + return -EINVAL; + + /* Set MSI private data */ + data_mask = msi_count - 1; + data = rockchip_pcie_read(rockchip, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + + ROCKCHIP_PCIE_EP_MSI_CTRL_REG + + PCI_MSI_DATA_64); + data = (data & ~data_mask) | ((interrupt_num - 1) & data_mask); + + /* Get MSI PCI address */ + pci_addr = rockchip_pcie_read(rockchip, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + + ROCKCHIP_PCIE_EP_MSI_CTRL_REG + + PCI_MSI_ADDRESS_HI); + pci_addr <<= 32; + pci_addr |= rockchip_pcie_read(rockchip, + ROCKCHIP_PCIE_EP_FUNC_BASE(fn) + + ROCKCHIP_PCIE_EP_MSI_CTRL_REG + + PCI_MSI_ADDRESS_LO); + + /* Set the outbound region if needed. */ + if (unlikely(ep->irq_pci_addr != (pci_addr & PCIE_ADDR_MASK) || + ep->irq_pci_fn != fn)) { + r = rockchip_ob_region(ep->irq_phys_addr); + rockchip_pcie_prog_ep_ob_atu(rockchip, fn, r, + ep->irq_phys_addr, + pci_addr & PCIE_ADDR_MASK, + ~PCIE_ADDR_MASK + 1); + ep->irq_pci_addr = (pci_addr & PCIE_ADDR_MASK); + ep->irq_pci_fn = fn; + } + + writew(data, ep->irq_cpu_addr + (pci_addr & ~PCIE_ADDR_MASK)); + return 0; +} + +static int rockchip_pcie_ep_raise_irq(struct pci_epc *epc, u8 fn, u8 vfn, + enum pci_epc_irq_type type, + u16 interrupt_num) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + + switch (type) { + case PCI_EPC_IRQ_LEGACY: + return rockchip_pcie_ep_send_legacy_irq(ep, fn, 0); + case PCI_EPC_IRQ_MSI: + return rockchip_pcie_ep_send_msi_irq(ep, fn, interrupt_num); + default: + return -EINVAL; + } +} + +static int rockchip_pcie_ep_start(struct pci_epc *epc) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + struct pci_epf *epf; + u32 cfg; + + cfg = BIT(0); + list_for_each_entry(epf, &epc->pci_epf, list) + cfg |= BIT(epf->func_no); + + rockchip_pcie_write(rockchip, cfg, PCIE_CORE_PHY_FUNC_CFG); + + return 0; +} + +static const struct pci_epc_features rockchip_pcie_epc_features = { + .linkup_notifier = false, + .msi_capable = true, + .msix_capable = false, + .align = 256, +}; + +static const struct pci_epc_features* +rockchip_pcie_ep_get_features(struct pci_epc *epc, u8 func_no, u8 vfunc_no) +{ + return &rockchip_pcie_epc_features; +} + +static const struct pci_epc_ops rockchip_pcie_epc_ops = { + .write_header = rockchip_pcie_ep_write_header, + .set_bar = rockchip_pcie_ep_set_bar, + .clear_bar = rockchip_pcie_ep_clear_bar, + .map_addr = rockchip_pcie_ep_map_addr, + .unmap_addr = rockchip_pcie_ep_unmap_addr, + .set_msi = rockchip_pcie_ep_set_msi, + .get_msi = rockchip_pcie_ep_get_msi, + .raise_irq = rockchip_pcie_ep_raise_irq, + .start = rockchip_pcie_ep_start, + .get_features = rockchip_pcie_ep_get_features, +}; + +static int rockchip_pcie_parse_ep_dt(struct rockchip_pcie *rockchip, + struct rockchip_pcie_ep *ep) +{ + struct device *dev = rockchip->dev; + int err; + + err = rockchip_pcie_parse_dt(rockchip); + if (err) + return err; + + err = rockchip_pcie_get_phys(rockchip); + if (err) + return err; + + err = of_property_read_u32(dev->of_node, + "rockchip,max-outbound-regions", + &ep->max_regions); + if (err < 0 || ep->max_regions > MAX_REGION_LIMIT) + ep->max_regions = MAX_REGION_LIMIT; + + ep->ob_region_map = 0; + + err = of_property_read_u8(dev->of_node, "max-functions", + &ep->epc->max_functions); + if (err < 0) + ep->epc->max_functions = 1; + + return 0; +} + +static const struct of_device_id rockchip_pcie_ep_of_match[] = { + { .compatible = "rockchip,rk3399-pcie-ep"}, + {}, +}; + +static int rockchip_pcie_ep_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rockchip_pcie_ep *ep; + struct rockchip_pcie *rockchip; + struct pci_epc *epc; + size_t max_regions; + struct pci_epc_mem_window *windows = NULL; + int err, i; + u32 cfg_msi, cfg_msix_cp; + + ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + rockchip = &ep->rockchip; + rockchip->is_rc = false; + rockchip->dev = dev; + + epc = devm_pci_epc_create(dev, &rockchip_pcie_epc_ops); + if (IS_ERR(epc)) { + dev_err(dev, "failed to create epc device\n"); + return PTR_ERR(epc); + } + + ep->epc = epc; + epc_set_drvdata(epc, ep); + + err = rockchip_pcie_parse_ep_dt(rockchip, ep); + if (err) + return err; + + err = rockchip_pcie_enable_clocks(rockchip); + if (err) + return err; + + err = rockchip_pcie_init_port(rockchip); + if (err) + goto err_disable_clocks; + + /* Establish the link automatically */ + rockchip_pcie_write(rockchip, PCIE_CLIENT_LINK_TRAIN_ENABLE, + PCIE_CLIENT_CONFIG); + + max_regions = ep->max_regions; + ep->ob_addr = devm_kcalloc(dev, max_regions, sizeof(*ep->ob_addr), + GFP_KERNEL); + + if (!ep->ob_addr) { + err = -ENOMEM; + goto err_uninit_port; + } + + /* Only enable function 0 by default */ + rockchip_pcie_write(rockchip, BIT(0), PCIE_CORE_PHY_FUNC_CFG); + + windows = devm_kcalloc(dev, ep->max_regions, + sizeof(struct pci_epc_mem_window), GFP_KERNEL); + if (!windows) { + err = -ENOMEM; + goto err_uninit_port; + } + for (i = 0; i < ep->max_regions; i++) { + windows[i].phys_base = rockchip->mem_res->start + (SZ_1M * i); + windows[i].size = SZ_1M; + windows[i].page_size = SZ_1M; + } + err = pci_epc_multi_mem_init(epc, windows, ep->max_regions); + devm_kfree(dev, windows); + + if (err < 0) { + dev_err(dev, "failed to initialize the memory space\n"); + goto err_uninit_port; + } + + ep->irq_cpu_addr = pci_epc_mem_alloc_addr(epc, &ep->irq_phys_addr, + SZ_1M); + if (!ep->irq_cpu_addr) { + dev_err(dev, "failed to reserve memory space for MSI\n"); + err = -ENOMEM; + goto err_epc_mem_exit; + } + + ep->irq_pci_addr = ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR; + + /* + * MSI-X is not supported but the controller still advertises the MSI-X + * capability by default, which can lead to the Root Complex side + * allocating MSI-X vectors which cannot be used. Avoid this by skipping + * the MSI-X capability entry in the PCIe capabilities linked-list: get + * the next pointer from the MSI-X entry and set that in the MSI + * capability entry (which is the previous entry). This way the MSI-X + * entry is skipped (left out of the linked-list) and not advertised. + */ + cfg_msi = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_BASE + + ROCKCHIP_PCIE_EP_MSI_CTRL_REG); + + cfg_msi &= ~ROCKCHIP_PCIE_EP_MSI_CP1_MASK; + + cfg_msix_cp = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_BASE + + ROCKCHIP_PCIE_EP_MSIX_CAP_REG) & + ROCKCHIP_PCIE_EP_MSIX_CAP_CP_MASK; + + cfg_msi |= cfg_msix_cp; + + rockchip_pcie_write(rockchip, cfg_msi, + PCIE_EP_CONFIG_BASE + ROCKCHIP_PCIE_EP_MSI_CTRL_REG); + + rockchip_pcie_write(rockchip, PCIE_CLIENT_CONF_ENABLE, + PCIE_CLIENT_CONFIG); + + return 0; +err_epc_mem_exit: + pci_epc_mem_exit(epc); +err_uninit_port: + rockchip_pcie_deinit_phys(rockchip); +err_disable_clocks: + rockchip_pcie_disable_clocks(rockchip); + return err; +} + +static struct platform_driver rockchip_pcie_ep_driver = { + .driver = { + .name = "rockchip-pcie-ep", + .of_match_table = rockchip_pcie_ep_of_match, + }, + .probe = rockchip_pcie_ep_probe, +}; + +builtin_platform_driver(rockchip_pcie_ep_driver); diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c new file mode 100644 index 000000000..7352b5ff8 --- /dev/null +++ b/drivers/pci/controller/pcie-rockchip-host.c @@ -0,0 +1,1061 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Rockchip AXI PCIe host controller driver + * + * Copyright (c) 2016 Rockchip, Inc. + * + * Author: Shawn Lin <shawn.lin@rock-chips.com> + * Wenrui Li <wenrui.li@rock-chips.com> + * + * Bits taken from Synopsys DesignWare Host controller driver and + * ARM PCI Host generic driver. + */ + +#include <linux/bitrev.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/init.h> +#include <linux/interrupt.h> +#include <linux/iopoll.h> +#include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_device.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/of_irq.h> +#include <linux/pci.h> +#include <linux/pci_ids.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/reset.h> +#include <linux/regmap.h> + +#include "../pci.h" +#include "pcie-rockchip.h" + +static void rockchip_pcie_enable_bw_int(struct rockchip_pcie *rockchip) +{ + u32 status; + + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status |= (PCI_EXP_LNKCTL_LBMIE | PCI_EXP_LNKCTL_LABIE); + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); +} + +static void rockchip_pcie_clr_bw_int(struct rockchip_pcie *rockchip) +{ + u32 status; + + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status |= (PCI_EXP_LNKSTA_LBMS | PCI_EXP_LNKSTA_LABS) << 16; + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); +} + +static void rockchip_pcie_update_txcredit_mui(struct rockchip_pcie *rockchip) +{ + u32 val; + + /* Update Tx credit maximum update interval */ + val = rockchip_pcie_read(rockchip, PCIE_CORE_TXCREDIT_CFG1); + val &= ~PCIE_CORE_TXCREDIT_CFG1_MUI_MASK; + val |= PCIE_CORE_TXCREDIT_CFG1_MUI_ENCODE(24000); /* ns */ + rockchip_pcie_write(rockchip, val, PCIE_CORE_TXCREDIT_CFG1); +} + +static int rockchip_pcie_valid_device(struct rockchip_pcie *rockchip, + struct pci_bus *bus, int dev) +{ + /* + * Access only one slot on each root port. + * Do not read more than one device on the bus directly attached + * to RC's downstream side. + */ + if (pci_is_root_bus(bus) || pci_is_root_bus(bus->parent)) + return dev == 0; + + return 1; +} + +static u8 rockchip_pcie_lane_map(struct rockchip_pcie *rockchip) +{ + u32 val; + u8 map; + + if (rockchip->legacy_phy) + return GENMASK(MAX_LANE_NUM - 1, 0); + + val = rockchip_pcie_read(rockchip, PCIE_CORE_LANE_MAP); + map = val & PCIE_CORE_LANE_MAP_MASK; + + /* The link may be using a reverse-indexed mapping. */ + if (val & PCIE_CORE_LANE_MAP_REVERSE) + map = bitrev8(map) >> 4; + + return map; +} + +static int rockchip_pcie_rd_own_conf(struct rockchip_pcie *rockchip, + int where, int size, u32 *val) +{ + void __iomem *addr; + + addr = rockchip->apb_base + PCIE_RC_CONFIG_NORMAL_BASE + where; + + if (!IS_ALIGNED((uintptr_t)addr, size)) { + *val = 0; + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + if (size == 4) { + *val = readl(addr); + } else if (size == 2) { + *val = readw(addr); + } else if (size == 1) { + *val = readb(addr); + } else { + *val = 0; + return PCIBIOS_BAD_REGISTER_NUMBER; + } + return PCIBIOS_SUCCESSFUL; +} + +static int rockchip_pcie_wr_own_conf(struct rockchip_pcie *rockchip, + int where, int size, u32 val) +{ + u32 mask, tmp, offset; + void __iomem *addr; + + offset = where & ~0x3; + addr = rockchip->apb_base + PCIE_RC_CONFIG_NORMAL_BASE + offset; + + if (size == 4) { + writel(val, addr); + return PCIBIOS_SUCCESSFUL; + } + + mask = ~(((1 << (size * 8)) - 1) << ((where & 0x3) * 8)); + + /* + * N.B. This read/modify/write isn't safe in general because it can + * corrupt RW1C bits in adjacent registers. But the hardware + * doesn't support smaller writes. + */ + tmp = readl(addr) & mask; + tmp |= val << ((where & 0x3) * 8); + writel(tmp, addr); + + return PCIBIOS_SUCCESSFUL; +} + +static int rockchip_pcie_rd_other_conf(struct rockchip_pcie *rockchip, + struct pci_bus *bus, u32 devfn, + int where, int size, u32 *val) +{ + void __iomem *addr; + + addr = rockchip->reg_base + PCIE_ECAM_OFFSET(bus->number, devfn, where); + + if (!IS_ALIGNED((uintptr_t)addr, size)) { + *val = 0; + return PCIBIOS_BAD_REGISTER_NUMBER; + } + + if (pci_is_root_bus(bus->parent)) + rockchip_pcie_cfg_configuration_accesses(rockchip, + AXI_WRAPPER_TYPE0_CFG); + else + rockchip_pcie_cfg_configuration_accesses(rockchip, + AXI_WRAPPER_TYPE1_CFG); + + if (size == 4) { + *val = readl(addr); + } else if (size == 2) { + *val = readw(addr); + } else if (size == 1) { + *val = readb(addr); + } else { + *val = 0; + return PCIBIOS_BAD_REGISTER_NUMBER; + } + return PCIBIOS_SUCCESSFUL; +} + +static int rockchip_pcie_wr_other_conf(struct rockchip_pcie *rockchip, + struct pci_bus *bus, u32 devfn, + int where, int size, u32 val) +{ + void __iomem *addr; + + addr = rockchip->reg_base + PCIE_ECAM_OFFSET(bus->number, devfn, where); + + if (!IS_ALIGNED((uintptr_t)addr, size)) + return PCIBIOS_BAD_REGISTER_NUMBER; + + if (pci_is_root_bus(bus->parent)) + rockchip_pcie_cfg_configuration_accesses(rockchip, + AXI_WRAPPER_TYPE0_CFG); + else + rockchip_pcie_cfg_configuration_accesses(rockchip, + AXI_WRAPPER_TYPE1_CFG); + + if (size == 4) + writel(val, addr); + else if (size == 2) + writew(val, addr); + else if (size == 1) + writeb(val, addr); + else + return PCIBIOS_BAD_REGISTER_NUMBER; + + return PCIBIOS_SUCCESSFUL; +} + +static int rockchip_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where, + int size, u32 *val) +{ + struct rockchip_pcie *rockchip = bus->sysdata; + + if (!rockchip_pcie_valid_device(rockchip, bus, PCI_SLOT(devfn))) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (pci_is_root_bus(bus)) + return rockchip_pcie_rd_own_conf(rockchip, where, size, val); + + return rockchip_pcie_rd_other_conf(rockchip, bus, devfn, where, size, + val); +} + +static int rockchip_pcie_wr_conf(struct pci_bus *bus, u32 devfn, + int where, int size, u32 val) +{ + struct rockchip_pcie *rockchip = bus->sysdata; + + if (!rockchip_pcie_valid_device(rockchip, bus, PCI_SLOT(devfn))) + return PCIBIOS_DEVICE_NOT_FOUND; + + if (pci_is_root_bus(bus)) + return rockchip_pcie_wr_own_conf(rockchip, where, size, val); + + return rockchip_pcie_wr_other_conf(rockchip, bus, devfn, where, size, + val); +} + +static struct pci_ops rockchip_pcie_ops = { + .read = rockchip_pcie_rd_conf, + .write = rockchip_pcie_wr_conf, +}; + +static void rockchip_pcie_set_power_limit(struct rockchip_pcie *rockchip) +{ + int curr; + u32 status, scale, power; + + if (IS_ERR(rockchip->vpcie3v3)) + return; + + /* + * Set RC's captured slot power limit and scale if + * vpcie3v3 available. The default values are both zero + * which means the software should set these two according + * to the actual power supply. + */ + curr = regulator_get_current_limit(rockchip->vpcie3v3); + if (curr <= 0) + return; + + scale = 3; /* 0.001x */ + curr = curr / 1000; /* convert to mA */ + power = (curr * 3300) / 1000; /* milliwatt */ + while (power > PCIE_RC_CONFIG_DCR_CSPL_LIMIT) { + if (!scale) { + dev_warn(rockchip->dev, "invalid power supply\n"); + return; + } + scale--; + power = power / 10; + } + + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_DCR); + status |= (power << PCIE_RC_CONFIG_DCR_CSPL_SHIFT) | + (scale << PCIE_RC_CONFIG_DCR_CPLS_SHIFT); + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_DCR); +} + +/** + * rockchip_pcie_host_init_port - Initialize hardware + * @rockchip: PCIe port information + */ +static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->dev; + int err, i = MAX_LANE_NUM; + u32 status; + + gpiod_set_value_cansleep(rockchip->ep_gpio, 0); + + err = rockchip_pcie_init_port(rockchip); + if (err) + return err; + + /* Fix the transmitted FTS count desired to exit from L0s. */ + status = rockchip_pcie_read(rockchip, PCIE_CORE_CTRL_PLC1); + status = (status & ~PCIE_CORE_CTRL_PLC1_FTS_MASK) | + (PCIE_CORE_CTRL_PLC1_FTS_CNT << PCIE_CORE_CTRL_PLC1_FTS_SHIFT); + rockchip_pcie_write(rockchip, status, PCIE_CORE_CTRL_PLC1); + + rockchip_pcie_set_power_limit(rockchip); + + /* Set RC's clock architecture as common clock */ + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status |= PCI_EXP_LNKSTA_SLC << 16; + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); + + /* Set RC's RCB to 128 */ + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status |= PCI_EXP_LNKCTL_RCB; + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); + + /* Enable Gen1 training */ + rockchip_pcie_write(rockchip, PCIE_CLIENT_LINK_TRAIN_ENABLE, + PCIE_CLIENT_CONFIG); + + gpiod_set_value_cansleep(rockchip->ep_gpio, 1); + + /* 500ms timeout value should be enough for Gen1/2 training */ + err = readl_poll_timeout(rockchip->apb_base + PCIE_CLIENT_BASIC_STATUS1, + status, PCIE_LINK_UP(status), 20, + 500 * USEC_PER_MSEC); + if (err) { + dev_err(dev, "PCIe link training gen1 timeout!\n"); + goto err_power_off_phy; + } + + if (rockchip->link_gen == 2) { + /* + * Enable retrain for gen2. This should be configured only after + * gen1 finished. + */ + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status |= PCI_EXP_LNKCTL_RL; + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); + + err = readl_poll_timeout(rockchip->apb_base + PCIE_CORE_CTRL, + status, PCIE_LINK_IS_GEN2(status), 20, + 500 * USEC_PER_MSEC); + if (err) + dev_dbg(dev, "PCIe link training gen2 timeout, fall back to gen1!\n"); + } + + /* Check the final link width from negotiated lane counter from MGMT */ + status = rockchip_pcie_read(rockchip, PCIE_CORE_CTRL); + status = 0x1 << ((status & PCIE_CORE_PL_CONF_LANE_MASK) >> + PCIE_CORE_PL_CONF_LANE_SHIFT); + dev_dbg(dev, "current link width is x%d\n", status); + + /* Power off unused lane(s) */ + rockchip->lanes_map = rockchip_pcie_lane_map(rockchip); + for (i = 0; i < MAX_LANE_NUM; i++) { + if (!(rockchip->lanes_map & BIT(i))) { + dev_dbg(dev, "idling lane %d\n", i); + phy_power_off(rockchip->phys[i]); + } + } + + rockchip_pcie_write(rockchip, ROCKCHIP_VENDOR_ID, + PCIE_CORE_CONFIG_VENDOR); + rockchip_pcie_write(rockchip, + PCI_CLASS_BRIDGE_PCI_NORMAL << 8, + PCIE_RC_CONFIG_RID_CCR); + + /* Clear THP cap's next cap pointer to remove L1 substate cap */ + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_THP_CAP); + status &= ~PCIE_RC_CONFIG_THP_CAP_NEXT_MASK; + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_THP_CAP); + + /* Clear L0s from RC's link cap */ + if (of_property_read_bool(dev->of_node, "aspm-no-l0s")) { + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LINK_CAP); + status &= ~PCIE_RC_CONFIG_LINK_CAP_L0S; + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LINK_CAP); + } + + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_DCSR); + status &= ~PCIE_RC_CONFIG_DCSR_MPS_MASK; + status |= PCIE_RC_CONFIG_DCSR_MPS_256; + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_DCSR); + + return 0; +err_power_off_phy: + while (i--) + phy_power_off(rockchip->phys[i]); + i = MAX_LANE_NUM; + while (i--) + phy_exit(rockchip->phys[i]); + return err; +} + +static irqreturn_t rockchip_pcie_subsys_irq_handler(int irq, void *arg) +{ + struct rockchip_pcie *rockchip = arg; + struct device *dev = rockchip->dev; + u32 reg; + u32 sub_reg; + + reg = rockchip_pcie_read(rockchip, PCIE_CLIENT_INT_STATUS); + if (reg & PCIE_CLIENT_INT_LOCAL) { + dev_dbg(dev, "local interrupt received\n"); + sub_reg = rockchip_pcie_read(rockchip, PCIE_CORE_INT_STATUS); + if (sub_reg & PCIE_CORE_INT_PRFPE) + dev_dbg(dev, "parity error detected while reading from the PNP receive FIFO RAM\n"); + + if (sub_reg & PCIE_CORE_INT_CRFPE) + dev_dbg(dev, "parity error detected while reading from the Completion Receive FIFO RAM\n"); + + if (sub_reg & PCIE_CORE_INT_RRPE) + dev_dbg(dev, "parity error detected while reading from replay buffer RAM\n"); + + if (sub_reg & PCIE_CORE_INT_PRFO) + dev_dbg(dev, "overflow occurred in the PNP receive FIFO\n"); + + if (sub_reg & PCIE_CORE_INT_CRFO) + dev_dbg(dev, "overflow occurred in the completion receive FIFO\n"); + + if (sub_reg & PCIE_CORE_INT_RT) + dev_dbg(dev, "replay timer timed out\n"); + + if (sub_reg & PCIE_CORE_INT_RTR) + dev_dbg(dev, "replay timer rolled over after 4 transmissions of the same TLP\n"); + + if (sub_reg & PCIE_CORE_INT_PE) + dev_dbg(dev, "phy error detected on receive side\n"); + + if (sub_reg & PCIE_CORE_INT_MTR) + dev_dbg(dev, "malformed TLP received from the link\n"); + + if (sub_reg & PCIE_CORE_INT_UCR) + dev_dbg(dev, "malformed TLP received from the link\n"); + + if (sub_reg & PCIE_CORE_INT_FCE) + dev_dbg(dev, "an error was observed in the flow control advertisements from the other side\n"); + + if (sub_reg & PCIE_CORE_INT_CT) + dev_dbg(dev, "a request timed out waiting for completion\n"); + + if (sub_reg & PCIE_CORE_INT_UTC) + dev_dbg(dev, "unmapped TC error\n"); + + if (sub_reg & PCIE_CORE_INT_MMVC) + dev_dbg(dev, "MSI mask register changes\n"); + + rockchip_pcie_write(rockchip, sub_reg, PCIE_CORE_INT_STATUS); + } else if (reg & PCIE_CLIENT_INT_PHY) { + dev_dbg(dev, "phy link changes\n"); + rockchip_pcie_update_txcredit_mui(rockchip); + rockchip_pcie_clr_bw_int(rockchip); + } + + rockchip_pcie_write(rockchip, reg & PCIE_CLIENT_INT_LOCAL, + PCIE_CLIENT_INT_STATUS); + + return IRQ_HANDLED; +} + +static irqreturn_t rockchip_pcie_client_irq_handler(int irq, void *arg) +{ + struct rockchip_pcie *rockchip = arg; + struct device *dev = rockchip->dev; + u32 reg; + + reg = rockchip_pcie_read(rockchip, PCIE_CLIENT_INT_STATUS); + if (reg & PCIE_CLIENT_INT_LEGACY_DONE) + dev_dbg(dev, "legacy done interrupt received\n"); + + if (reg & PCIE_CLIENT_INT_MSG) + dev_dbg(dev, "message done interrupt received\n"); + + if (reg & PCIE_CLIENT_INT_HOT_RST) + dev_dbg(dev, "hot reset interrupt received\n"); + + if (reg & PCIE_CLIENT_INT_DPA) + dev_dbg(dev, "dpa interrupt received\n"); + + if (reg & PCIE_CLIENT_INT_FATAL_ERR) + dev_dbg(dev, "fatal error interrupt received\n"); + + if (reg & PCIE_CLIENT_INT_NFATAL_ERR) + dev_dbg(dev, "no fatal error interrupt received\n"); + + if (reg & PCIE_CLIENT_INT_CORR_ERR) + dev_dbg(dev, "correctable error interrupt received\n"); + + if (reg & PCIE_CLIENT_INT_PHY) + dev_dbg(dev, "phy interrupt received\n"); + + rockchip_pcie_write(rockchip, reg & (PCIE_CLIENT_INT_LEGACY_DONE | + PCIE_CLIENT_INT_MSG | PCIE_CLIENT_INT_HOT_RST | + PCIE_CLIENT_INT_DPA | PCIE_CLIENT_INT_FATAL_ERR | + PCIE_CLIENT_INT_NFATAL_ERR | + PCIE_CLIENT_INT_CORR_ERR | + PCIE_CLIENT_INT_PHY), + PCIE_CLIENT_INT_STATUS); + + return IRQ_HANDLED; +} + +static void rockchip_pcie_legacy_int_handler(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct rockchip_pcie *rockchip = irq_desc_get_handler_data(desc); + struct device *dev = rockchip->dev; + u32 reg; + u32 hwirq; + int ret; + + chained_irq_enter(chip, desc); + + reg = rockchip_pcie_read(rockchip, PCIE_CLIENT_INT_STATUS); + reg = (reg & PCIE_CLIENT_INTR_MASK) >> PCIE_CLIENT_INTR_SHIFT; + + while (reg) { + hwirq = ffs(reg) - 1; + reg &= ~BIT(hwirq); + + ret = generic_handle_domain_irq(rockchip->irq_domain, hwirq); + if (ret) + dev_err(dev, "unexpected IRQ, INT%d\n", hwirq); + } + + chained_irq_exit(chip, desc); +} + +static int rockchip_pcie_setup_irq(struct rockchip_pcie *rockchip) +{ + int irq, err; + struct device *dev = rockchip->dev; + struct platform_device *pdev = to_platform_device(dev); + + irq = platform_get_irq_byname(pdev, "sys"); + if (irq < 0) + return irq; + + err = devm_request_irq(dev, irq, rockchip_pcie_subsys_irq_handler, + IRQF_SHARED, "pcie-sys", rockchip); + if (err) { + dev_err(dev, "failed to request PCIe subsystem IRQ\n"); + return err; + } + + irq = platform_get_irq_byname(pdev, "legacy"); + if (irq < 0) + return irq; + + irq_set_chained_handler_and_data(irq, + rockchip_pcie_legacy_int_handler, + rockchip); + + irq = platform_get_irq_byname(pdev, "client"); + if (irq < 0) + return irq; + + err = devm_request_irq(dev, irq, rockchip_pcie_client_irq_handler, + IRQF_SHARED, "pcie-client", rockchip); + if (err) { + dev_err(dev, "failed to request PCIe client IRQ\n"); + return err; + } + + return 0; +} + +/** + * rockchip_pcie_parse_host_dt - Parse Device Tree + * @rockchip: PCIe port information + * + * Return: '0' on success and error value on failure + */ +static int rockchip_pcie_parse_host_dt(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->dev; + int err; + + err = rockchip_pcie_parse_dt(rockchip); + if (err) + return err; + + rockchip->vpcie12v = devm_regulator_get_optional(dev, "vpcie12v"); + if (IS_ERR(rockchip->vpcie12v)) { + if (PTR_ERR(rockchip->vpcie12v) != -ENODEV) + return PTR_ERR(rockchip->vpcie12v); + dev_info(dev, "no vpcie12v regulator found\n"); + } + + rockchip->vpcie3v3 = devm_regulator_get_optional(dev, "vpcie3v3"); + if (IS_ERR(rockchip->vpcie3v3)) { + if (PTR_ERR(rockchip->vpcie3v3) != -ENODEV) + return PTR_ERR(rockchip->vpcie3v3); + dev_info(dev, "no vpcie3v3 regulator found\n"); + } + + rockchip->vpcie1v8 = devm_regulator_get(dev, "vpcie1v8"); + if (IS_ERR(rockchip->vpcie1v8)) + return PTR_ERR(rockchip->vpcie1v8); + + rockchip->vpcie0v9 = devm_regulator_get(dev, "vpcie0v9"); + if (IS_ERR(rockchip->vpcie0v9)) + return PTR_ERR(rockchip->vpcie0v9); + + return 0; +} + +static int rockchip_pcie_set_vpcie(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->dev; + int err; + + if (!IS_ERR(rockchip->vpcie12v)) { + err = regulator_enable(rockchip->vpcie12v); + if (err) { + dev_err(dev, "fail to enable vpcie12v regulator\n"); + goto err_out; + } + } + + if (!IS_ERR(rockchip->vpcie3v3)) { + err = regulator_enable(rockchip->vpcie3v3); + if (err) { + dev_err(dev, "fail to enable vpcie3v3 regulator\n"); + goto err_disable_12v; + } + } + + err = regulator_enable(rockchip->vpcie1v8); + if (err) { + dev_err(dev, "fail to enable vpcie1v8 regulator\n"); + goto err_disable_3v3; + } + + err = regulator_enable(rockchip->vpcie0v9); + if (err) { + dev_err(dev, "fail to enable vpcie0v9 regulator\n"); + goto err_disable_1v8; + } + + return 0; + +err_disable_1v8: + regulator_disable(rockchip->vpcie1v8); +err_disable_3v3: + if (!IS_ERR(rockchip->vpcie3v3)) + regulator_disable(rockchip->vpcie3v3); +err_disable_12v: + if (!IS_ERR(rockchip->vpcie12v)) + regulator_disable(rockchip->vpcie12v); +err_out: + return err; +} + +static void rockchip_pcie_enable_interrupts(struct rockchip_pcie *rockchip) +{ + rockchip_pcie_write(rockchip, (PCIE_CLIENT_INT_CLI << 16) & + (~PCIE_CLIENT_INT_CLI), PCIE_CLIENT_INT_MASK); + rockchip_pcie_write(rockchip, (u32)(~PCIE_CORE_INT), + PCIE_CORE_INT_MASK); + + rockchip_pcie_enable_bw_int(rockchip); +} + +static int rockchip_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &dummy_irq_chip, handle_simple_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops intx_domain_ops = { + .map = rockchip_pcie_intx_map, +}; + +static int rockchip_pcie_init_irq_domain(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->dev; + struct device_node *intc = of_get_next_child(dev->of_node, NULL); + + if (!intc) { + dev_err(dev, "missing child interrupt-controller node\n"); + return -EINVAL; + } + + rockchip->irq_domain = irq_domain_add_linear(intc, PCI_NUM_INTX, + &intx_domain_ops, rockchip); + of_node_put(intc); + if (!rockchip->irq_domain) { + dev_err(dev, "failed to get a INTx IRQ domain\n"); + return -EINVAL; + } + + return 0; +} + +static int rockchip_pcie_prog_ob_atu(struct rockchip_pcie *rockchip, + int region_no, int type, u8 num_pass_bits, + u32 lower_addr, u32 upper_addr) +{ + u32 ob_addr_0; + u32 ob_addr_1; + u32 ob_desc_0; + u32 aw_offset; + + if (region_no >= MAX_AXI_WRAPPER_REGION_NUM) + return -EINVAL; + if (num_pass_bits + 1 < 8) + return -EINVAL; + if (num_pass_bits > 63) + return -EINVAL; + if (region_no == 0) { + if (AXI_REGION_0_SIZE < (2ULL << num_pass_bits)) + return -EINVAL; + } + if (region_no != 0) { + if (AXI_REGION_SIZE < (2ULL << num_pass_bits)) + return -EINVAL; + } + + aw_offset = (region_no << OB_REG_SIZE_SHIFT); + + ob_addr_0 = num_pass_bits & PCIE_CORE_OB_REGION_ADDR0_NUM_BITS; + ob_addr_0 |= lower_addr & PCIE_CORE_OB_REGION_ADDR0_LO_ADDR; + ob_addr_1 = upper_addr; + ob_desc_0 = (1 << 23 | type); + + rockchip_pcie_write(rockchip, ob_addr_0, + PCIE_CORE_OB_REGION_ADDR0 + aw_offset); + rockchip_pcie_write(rockchip, ob_addr_1, + PCIE_CORE_OB_REGION_ADDR1 + aw_offset); + rockchip_pcie_write(rockchip, ob_desc_0, + PCIE_CORE_OB_REGION_DESC0 + aw_offset); + rockchip_pcie_write(rockchip, 0, + PCIE_CORE_OB_REGION_DESC1 + aw_offset); + + return 0; +} + +static int rockchip_pcie_prog_ib_atu(struct rockchip_pcie *rockchip, + int region_no, u8 num_pass_bits, + u32 lower_addr, u32 upper_addr) +{ + u32 ib_addr_0; + u32 ib_addr_1; + u32 aw_offset; + + if (region_no > MAX_AXI_IB_ROOTPORT_REGION_NUM) + return -EINVAL; + if (num_pass_bits + 1 < MIN_AXI_ADDR_BITS_PASSED) + return -EINVAL; + if (num_pass_bits > 63) + return -EINVAL; + + aw_offset = (region_no << IB_ROOT_PORT_REG_SIZE_SHIFT); + + ib_addr_0 = num_pass_bits & PCIE_CORE_IB_REGION_ADDR0_NUM_BITS; + ib_addr_0 |= (lower_addr << 8) & PCIE_CORE_IB_REGION_ADDR0_LO_ADDR; + ib_addr_1 = upper_addr; + + rockchip_pcie_write(rockchip, ib_addr_0, PCIE_RP_IB_ADDR0 + aw_offset); + rockchip_pcie_write(rockchip, ib_addr_1, PCIE_RP_IB_ADDR1 + aw_offset); + + return 0; +} + +static int rockchip_pcie_cfg_atu(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->dev; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(rockchip); + struct resource_entry *entry; + u64 pci_addr, size; + int offset; + int err; + int reg_no; + + rockchip_pcie_cfg_configuration_accesses(rockchip, + AXI_WRAPPER_TYPE0_CFG); + entry = resource_list_first_type(&bridge->windows, IORESOURCE_MEM); + if (!entry) + return -ENODEV; + + size = resource_size(entry->res); + pci_addr = entry->res->start - entry->offset; + rockchip->msg_bus_addr = pci_addr; + + for (reg_no = 0; reg_no < (size >> 20); reg_no++) { + err = rockchip_pcie_prog_ob_atu(rockchip, reg_no + 1, + AXI_WRAPPER_MEM_WRITE, + 20 - 1, + pci_addr + (reg_no << 20), + 0); + if (err) { + dev_err(dev, "program RC mem outbound ATU failed\n"); + return err; + } + } + + err = rockchip_pcie_prog_ib_atu(rockchip, 2, 32 - 1, 0x0, 0); + if (err) { + dev_err(dev, "program RC mem inbound ATU failed\n"); + return err; + } + + entry = resource_list_first_type(&bridge->windows, IORESOURCE_IO); + if (!entry) + return -ENODEV; + + /* store the register number offset to program RC io outbound ATU */ + offset = size >> 20; + + size = resource_size(entry->res); + pci_addr = entry->res->start - entry->offset; + + for (reg_no = 0; reg_no < (size >> 20); reg_no++) { + err = rockchip_pcie_prog_ob_atu(rockchip, + reg_no + 1 + offset, + AXI_WRAPPER_IO_WRITE, + 20 - 1, + pci_addr + (reg_no << 20), + 0); + if (err) { + dev_err(dev, "program RC io outbound ATU failed\n"); + return err; + } + } + + /* assign message regions */ + rockchip_pcie_prog_ob_atu(rockchip, reg_no + 1 + offset, + AXI_WRAPPER_NOR_MSG, + 20 - 1, 0, 0); + + rockchip->msg_bus_addr += ((reg_no + offset) << 20); + return err; +} + +static int rockchip_pcie_wait_l2(struct rockchip_pcie *rockchip) +{ + u32 value; + int err; + + /* send PME_TURN_OFF message */ + writel(0x0, rockchip->msg_region + PCIE_RC_SEND_PME_OFF); + + /* read LTSSM and wait for falling into L2 link state */ + err = readl_poll_timeout(rockchip->apb_base + PCIE_CLIENT_DEBUG_OUT_0, + value, PCIE_LINK_IS_L2(value), 20, + jiffies_to_usecs(5 * HZ)); + if (err) { + dev_err(rockchip->dev, "PCIe link enter L2 timeout!\n"); + return err; + } + + return 0; +} + +static int rockchip_pcie_suspend_noirq(struct device *dev) +{ + struct rockchip_pcie *rockchip = dev_get_drvdata(dev); + int ret; + + /* disable core and cli int since we don't need to ack PME_ACK */ + rockchip_pcie_write(rockchip, (PCIE_CLIENT_INT_CLI << 16) | + PCIE_CLIENT_INT_CLI, PCIE_CLIENT_INT_MASK); + rockchip_pcie_write(rockchip, (u32)PCIE_CORE_INT, PCIE_CORE_INT_MASK); + + ret = rockchip_pcie_wait_l2(rockchip); + if (ret) { + rockchip_pcie_enable_interrupts(rockchip); + return ret; + } + + rockchip_pcie_deinit_phys(rockchip); + + rockchip_pcie_disable_clocks(rockchip); + + regulator_disable(rockchip->vpcie0v9); + + return ret; +} + +static int rockchip_pcie_resume_noirq(struct device *dev) +{ + struct rockchip_pcie *rockchip = dev_get_drvdata(dev); + int err; + + err = regulator_enable(rockchip->vpcie0v9); + if (err) { + dev_err(dev, "fail to enable vpcie0v9 regulator\n"); + return err; + } + + err = rockchip_pcie_enable_clocks(rockchip); + if (err) + goto err_disable_0v9; + + err = rockchip_pcie_host_init_port(rockchip); + if (err) + goto err_pcie_resume; + + err = rockchip_pcie_cfg_atu(rockchip); + if (err) + goto err_err_deinit_port; + + /* Need this to enter L1 again */ + rockchip_pcie_update_txcredit_mui(rockchip); + rockchip_pcie_enable_interrupts(rockchip); + + return 0; + +err_err_deinit_port: + rockchip_pcie_deinit_phys(rockchip); +err_pcie_resume: + rockchip_pcie_disable_clocks(rockchip); +err_disable_0v9: + regulator_disable(rockchip->vpcie0v9); + return err; +} + +static int rockchip_pcie_probe(struct platform_device *pdev) +{ + struct rockchip_pcie *rockchip; + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + int err; + + if (!dev->of_node) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rockchip)); + if (!bridge) + return -ENOMEM; + + rockchip = pci_host_bridge_priv(bridge); + + platform_set_drvdata(pdev, rockchip); + rockchip->dev = dev; + rockchip->is_rc = true; + + err = rockchip_pcie_parse_host_dt(rockchip); + if (err) + return err; + + err = rockchip_pcie_enable_clocks(rockchip); + if (err) + return err; + + err = rockchip_pcie_set_vpcie(rockchip); + if (err) { + dev_err(dev, "failed to set vpcie regulator\n"); + goto err_set_vpcie; + } + + err = rockchip_pcie_host_init_port(rockchip); + if (err) + goto err_vpcie; + + err = rockchip_pcie_init_irq_domain(rockchip); + if (err < 0) + goto err_deinit_port; + + err = rockchip_pcie_cfg_atu(rockchip); + if (err) + goto err_remove_irq_domain; + + rockchip->msg_region = devm_ioremap(dev, rockchip->msg_bus_addr, SZ_1M); + if (!rockchip->msg_region) { + err = -ENOMEM; + goto err_remove_irq_domain; + } + + bridge->sysdata = rockchip; + bridge->ops = &rockchip_pcie_ops; + + err = rockchip_pcie_setup_irq(rockchip); + if (err) + goto err_remove_irq_domain; + + rockchip_pcie_enable_interrupts(rockchip); + + err = pci_host_probe(bridge); + if (err < 0) + goto err_remove_irq_domain; + + return 0; + +err_remove_irq_domain: + irq_domain_remove(rockchip->irq_domain); +err_deinit_port: + rockchip_pcie_deinit_phys(rockchip); +err_vpcie: + if (!IS_ERR(rockchip->vpcie12v)) + regulator_disable(rockchip->vpcie12v); + if (!IS_ERR(rockchip->vpcie3v3)) + regulator_disable(rockchip->vpcie3v3); + regulator_disable(rockchip->vpcie1v8); + regulator_disable(rockchip->vpcie0v9); +err_set_vpcie: + rockchip_pcie_disable_clocks(rockchip); + return err; +} + +static int rockchip_pcie_remove(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct rockchip_pcie *rockchip = dev_get_drvdata(dev); + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(rockchip); + + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); + irq_domain_remove(rockchip->irq_domain); + + rockchip_pcie_deinit_phys(rockchip); + + rockchip_pcie_disable_clocks(rockchip); + + if (!IS_ERR(rockchip->vpcie12v)) + regulator_disable(rockchip->vpcie12v); + if (!IS_ERR(rockchip->vpcie3v3)) + regulator_disable(rockchip->vpcie3v3); + regulator_disable(rockchip->vpcie1v8); + regulator_disable(rockchip->vpcie0v9); + + return 0; +} + +static const struct dev_pm_ops rockchip_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(rockchip_pcie_suspend_noirq, + rockchip_pcie_resume_noirq) +}; + +static const struct of_device_id rockchip_pcie_of_match[] = { + { .compatible = "rockchip,rk3399-pcie", }, + {} +}; +MODULE_DEVICE_TABLE(of, rockchip_pcie_of_match); + +static struct platform_driver rockchip_pcie_driver = { + .driver = { + .name = "rockchip-pcie", + .of_match_table = rockchip_pcie_of_match, + .pm = &rockchip_pcie_pm_ops, + }, + .probe = rockchip_pcie_probe, + .remove = rockchip_pcie_remove, +}; +module_platform_driver(rockchip_pcie_driver); + +MODULE_AUTHOR("Rockchip Inc"); +MODULE_DESCRIPTION("Rockchip AXI PCIe driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pcie-rockchip.c b/drivers/pci/controller/pcie-rockchip.c new file mode 100644 index 000000000..1aa84035a --- /dev/null +++ b/drivers/pci/controller/pcie-rockchip.c @@ -0,0 +1,440 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Rockchip AXI PCIe host controller driver + * + * Copyright (c) 2016 Rockchip, Inc. + * + * Author: Shawn Lin <shawn.lin@rock-chips.com> + * Wenrui Li <wenrui.li@rock-chips.com> + * + * Bits taken from Synopsys DesignWare Host controller driver and + * ARM PCI Host generic driver. + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/iopoll.h> +#include <linux/of_pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/reset.h> + +#include "../pci.h" +#include "pcie-rockchip.h" + +int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->dev; + struct platform_device *pdev = to_platform_device(dev); + struct device_node *node = dev->of_node; + struct resource *regs; + int err; + + if (rockchip->is_rc) { + regs = platform_get_resource_byname(pdev, + IORESOURCE_MEM, + "axi-base"); + rockchip->reg_base = devm_pci_remap_cfg_resource(dev, regs); + if (IS_ERR(rockchip->reg_base)) + return PTR_ERR(rockchip->reg_base); + } else { + rockchip->mem_res = + platform_get_resource_byname(pdev, IORESOURCE_MEM, + "mem-base"); + if (!rockchip->mem_res) + return -EINVAL; + } + + rockchip->apb_base = + devm_platform_ioremap_resource_byname(pdev, "apb-base"); + if (IS_ERR(rockchip->apb_base)) + return PTR_ERR(rockchip->apb_base); + + err = rockchip_pcie_get_phys(rockchip); + if (err) + return err; + + rockchip->lanes = 1; + err = of_property_read_u32(node, "num-lanes", &rockchip->lanes); + if (!err && (rockchip->lanes == 0 || + rockchip->lanes == 3 || + rockchip->lanes > 4)) { + dev_warn(dev, "invalid num-lanes, default to use one lane\n"); + rockchip->lanes = 1; + } + + rockchip->link_gen = of_pci_get_max_link_speed(node); + if (rockchip->link_gen < 0 || rockchip->link_gen > 2) + rockchip->link_gen = 2; + + rockchip->core_rst = devm_reset_control_get_exclusive(dev, "core"); + if (IS_ERR(rockchip->core_rst)) { + if (PTR_ERR(rockchip->core_rst) != -EPROBE_DEFER) + dev_err(dev, "missing core reset property in node\n"); + return PTR_ERR(rockchip->core_rst); + } + + rockchip->mgmt_rst = devm_reset_control_get_exclusive(dev, "mgmt"); + if (IS_ERR(rockchip->mgmt_rst)) { + if (PTR_ERR(rockchip->mgmt_rst) != -EPROBE_DEFER) + dev_err(dev, "missing mgmt reset property in node\n"); + return PTR_ERR(rockchip->mgmt_rst); + } + + rockchip->mgmt_sticky_rst = devm_reset_control_get_exclusive(dev, + "mgmt-sticky"); + if (IS_ERR(rockchip->mgmt_sticky_rst)) { + if (PTR_ERR(rockchip->mgmt_sticky_rst) != -EPROBE_DEFER) + dev_err(dev, "missing mgmt-sticky reset property in node\n"); + return PTR_ERR(rockchip->mgmt_sticky_rst); + } + + rockchip->pipe_rst = devm_reset_control_get_exclusive(dev, "pipe"); + if (IS_ERR(rockchip->pipe_rst)) { + if (PTR_ERR(rockchip->pipe_rst) != -EPROBE_DEFER) + dev_err(dev, "missing pipe reset property in node\n"); + return PTR_ERR(rockchip->pipe_rst); + } + + rockchip->pm_rst = devm_reset_control_get_exclusive(dev, "pm"); + if (IS_ERR(rockchip->pm_rst)) { + if (PTR_ERR(rockchip->pm_rst) != -EPROBE_DEFER) + dev_err(dev, "missing pm reset property in node\n"); + return PTR_ERR(rockchip->pm_rst); + } + + rockchip->pclk_rst = devm_reset_control_get_exclusive(dev, "pclk"); + if (IS_ERR(rockchip->pclk_rst)) { + if (PTR_ERR(rockchip->pclk_rst) != -EPROBE_DEFER) + dev_err(dev, "missing pclk reset property in node\n"); + return PTR_ERR(rockchip->pclk_rst); + } + + rockchip->aclk_rst = devm_reset_control_get_exclusive(dev, "aclk"); + if (IS_ERR(rockchip->aclk_rst)) { + if (PTR_ERR(rockchip->aclk_rst) != -EPROBE_DEFER) + dev_err(dev, "missing aclk reset property in node\n"); + return PTR_ERR(rockchip->aclk_rst); + } + + if (rockchip->is_rc) { + rockchip->ep_gpio = devm_gpiod_get_optional(dev, "ep", + GPIOD_OUT_HIGH); + if (IS_ERR(rockchip->ep_gpio)) + return dev_err_probe(dev, PTR_ERR(rockchip->ep_gpio), + "failed to get ep GPIO\n"); + } + + rockchip->aclk_pcie = devm_clk_get(dev, "aclk"); + if (IS_ERR(rockchip->aclk_pcie)) { + dev_err(dev, "aclk clock not found\n"); + return PTR_ERR(rockchip->aclk_pcie); + } + + rockchip->aclk_perf_pcie = devm_clk_get(dev, "aclk-perf"); + if (IS_ERR(rockchip->aclk_perf_pcie)) { + dev_err(dev, "aclk_perf clock not found\n"); + return PTR_ERR(rockchip->aclk_perf_pcie); + } + + rockchip->hclk_pcie = devm_clk_get(dev, "hclk"); + if (IS_ERR(rockchip->hclk_pcie)) { + dev_err(dev, "hclk clock not found\n"); + return PTR_ERR(rockchip->hclk_pcie); + } + + rockchip->clk_pcie_pm = devm_clk_get(dev, "pm"); + if (IS_ERR(rockchip->clk_pcie_pm)) { + dev_err(dev, "pm clock not found\n"); + return PTR_ERR(rockchip->clk_pcie_pm); + } + + return 0; +} +EXPORT_SYMBOL_GPL(rockchip_pcie_parse_dt); + +#define rockchip_pcie_read_addr(addr) rockchip_pcie_read(rockchip, addr) +/* 100 ms max wait time for PHY PLLs to lock */ +#define RK_PHY_PLL_LOCK_TIMEOUT_US 100000 +/* Sleep should be less than 20ms */ +#define RK_PHY_PLL_LOCK_SLEEP_US 1000 + +int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->dev; + int err, i; + u32 regs; + + err = reset_control_assert(rockchip->aclk_rst); + if (err) { + dev_err(dev, "assert aclk_rst err %d\n", err); + return err; + } + + err = reset_control_assert(rockchip->pclk_rst); + if (err) { + dev_err(dev, "assert pclk_rst err %d\n", err); + return err; + } + + err = reset_control_assert(rockchip->pm_rst); + if (err) { + dev_err(dev, "assert pm_rst err %d\n", err); + return err; + } + + for (i = 0; i < MAX_LANE_NUM; i++) { + err = phy_init(rockchip->phys[i]); + if (err) { + dev_err(dev, "init phy%d err %d\n", i, err); + goto err_exit_phy; + } + } + + err = reset_control_assert(rockchip->core_rst); + if (err) { + dev_err(dev, "assert core_rst err %d\n", err); + goto err_exit_phy; + } + + err = reset_control_assert(rockchip->mgmt_rst); + if (err) { + dev_err(dev, "assert mgmt_rst err %d\n", err); + goto err_exit_phy; + } + + err = reset_control_assert(rockchip->mgmt_sticky_rst); + if (err) { + dev_err(dev, "assert mgmt_sticky_rst err %d\n", err); + goto err_exit_phy; + } + + err = reset_control_assert(rockchip->pipe_rst); + if (err) { + dev_err(dev, "assert pipe_rst err %d\n", err); + goto err_exit_phy; + } + + udelay(10); + + err = reset_control_deassert(rockchip->pm_rst); + if (err) { + dev_err(dev, "deassert pm_rst err %d\n", err); + goto err_exit_phy; + } + + err = reset_control_deassert(rockchip->aclk_rst); + if (err) { + dev_err(dev, "deassert aclk_rst err %d\n", err); + goto err_exit_phy; + } + + err = reset_control_deassert(rockchip->pclk_rst); + if (err) { + dev_err(dev, "deassert pclk_rst err %d\n", err); + goto err_exit_phy; + } + + if (rockchip->link_gen == 2) + rockchip_pcie_write(rockchip, PCIE_CLIENT_GEN_SEL_2, + PCIE_CLIENT_CONFIG); + else + rockchip_pcie_write(rockchip, PCIE_CLIENT_GEN_SEL_1, + PCIE_CLIENT_CONFIG); + + regs = PCIE_CLIENT_LINK_TRAIN_ENABLE | PCIE_CLIENT_ARI_ENABLE | + PCIE_CLIENT_CONF_LANE_NUM(rockchip->lanes); + + if (rockchip->is_rc) + regs |= PCIE_CLIENT_CONF_ENABLE | PCIE_CLIENT_MODE_RC; + else + regs |= PCIE_CLIENT_CONF_DISABLE | PCIE_CLIENT_MODE_EP; + + rockchip_pcie_write(rockchip, regs, PCIE_CLIENT_CONFIG); + + for (i = 0; i < MAX_LANE_NUM; i++) { + err = phy_power_on(rockchip->phys[i]); + if (err) { + dev_err(dev, "power on phy%d err %d\n", i, err); + goto err_power_off_phy; + } + } + + err = readx_poll_timeout(rockchip_pcie_read_addr, + PCIE_CLIENT_SIDE_BAND_STATUS, + regs, !(regs & PCIE_CLIENT_PHY_ST), + RK_PHY_PLL_LOCK_SLEEP_US, + RK_PHY_PLL_LOCK_TIMEOUT_US); + if (err) { + dev_err(dev, "PHY PLLs could not lock, %d\n", err); + goto err_power_off_phy; + } + + /* + * Please don't reorder the deassert sequence of the following + * four reset pins. + */ + err = reset_control_deassert(rockchip->mgmt_sticky_rst); + if (err) { + dev_err(dev, "deassert mgmt_sticky_rst err %d\n", err); + goto err_power_off_phy; + } + + err = reset_control_deassert(rockchip->core_rst); + if (err) { + dev_err(dev, "deassert core_rst err %d\n", err); + goto err_power_off_phy; + } + + err = reset_control_deassert(rockchip->mgmt_rst); + if (err) { + dev_err(dev, "deassert mgmt_rst err %d\n", err); + goto err_power_off_phy; + } + + err = reset_control_deassert(rockchip->pipe_rst); + if (err) { + dev_err(dev, "deassert pipe_rst err %d\n", err); + goto err_power_off_phy; + } + + return 0; +err_power_off_phy: + while (i--) + phy_power_off(rockchip->phys[i]); + i = MAX_LANE_NUM; +err_exit_phy: + while (i--) + phy_exit(rockchip->phys[i]); + return err; +} +EXPORT_SYMBOL_GPL(rockchip_pcie_init_port); + +int rockchip_pcie_get_phys(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->dev; + struct phy *phy; + char *name; + u32 i; + + phy = devm_phy_get(dev, "pcie-phy"); + if (!IS_ERR(phy)) { + rockchip->legacy_phy = true; + rockchip->phys[0] = phy; + dev_warn(dev, "legacy phy model is deprecated!\n"); + return 0; + } + + if (PTR_ERR(phy) == -EPROBE_DEFER) + return PTR_ERR(phy); + + dev_dbg(dev, "missing legacy phy; search for per-lane PHY\n"); + + for (i = 0; i < MAX_LANE_NUM; i++) { + name = kasprintf(GFP_KERNEL, "pcie-phy-%u", i); + if (!name) + return -ENOMEM; + + phy = devm_of_phy_get(dev, dev->of_node, name); + kfree(name); + + if (IS_ERR(phy)) { + if (PTR_ERR(phy) != -EPROBE_DEFER) + dev_err(dev, "missing phy for lane %d: %ld\n", + i, PTR_ERR(phy)); + return PTR_ERR(phy); + } + + rockchip->phys[i] = phy; + } + + return 0; +} +EXPORT_SYMBOL_GPL(rockchip_pcie_get_phys); + +void rockchip_pcie_deinit_phys(struct rockchip_pcie *rockchip) +{ + int i; + + for (i = 0; i < MAX_LANE_NUM; i++) { + /* inactive lanes are already powered off */ + if (rockchip->lanes_map & BIT(i)) + phy_power_off(rockchip->phys[i]); + phy_exit(rockchip->phys[i]); + } +} +EXPORT_SYMBOL_GPL(rockchip_pcie_deinit_phys); + +int rockchip_pcie_enable_clocks(struct rockchip_pcie *rockchip) +{ + struct device *dev = rockchip->dev; + int err; + + err = clk_prepare_enable(rockchip->aclk_pcie); + if (err) { + dev_err(dev, "unable to enable aclk_pcie clock\n"); + return err; + } + + err = clk_prepare_enable(rockchip->aclk_perf_pcie); + if (err) { + dev_err(dev, "unable to enable aclk_perf_pcie clock\n"); + goto err_aclk_perf_pcie; + } + + err = clk_prepare_enable(rockchip->hclk_pcie); + if (err) { + dev_err(dev, "unable to enable hclk_pcie clock\n"); + goto err_hclk_pcie; + } + + err = clk_prepare_enable(rockchip->clk_pcie_pm); + if (err) { + dev_err(dev, "unable to enable clk_pcie_pm clock\n"); + goto err_clk_pcie_pm; + } + + return 0; + +err_clk_pcie_pm: + clk_disable_unprepare(rockchip->hclk_pcie); +err_hclk_pcie: + clk_disable_unprepare(rockchip->aclk_perf_pcie); +err_aclk_perf_pcie: + clk_disable_unprepare(rockchip->aclk_pcie); + return err; +} +EXPORT_SYMBOL_GPL(rockchip_pcie_enable_clocks); + +void rockchip_pcie_disable_clocks(void *data) +{ + struct rockchip_pcie *rockchip = data; + + clk_disable_unprepare(rockchip->clk_pcie_pm); + clk_disable_unprepare(rockchip->hclk_pcie); + clk_disable_unprepare(rockchip->aclk_perf_pcie); + clk_disable_unprepare(rockchip->aclk_pcie); +} +EXPORT_SYMBOL_GPL(rockchip_pcie_disable_clocks); + +void rockchip_pcie_cfg_configuration_accesses( + struct rockchip_pcie *rockchip, u32 type) +{ + u32 ob_desc_0; + + /* Configuration Accesses for region 0 */ + rockchip_pcie_write(rockchip, 0x0, PCIE_RC_BAR_CONF); + + rockchip_pcie_write(rockchip, + (RC_REGION_0_ADDR_TRANS_L + RC_REGION_0_PASS_BITS), + PCIE_CORE_OB_REGION_ADDR0); + rockchip_pcie_write(rockchip, RC_REGION_0_ADDR_TRANS_H, + PCIE_CORE_OB_REGION_ADDR1); + ob_desc_0 = rockchip_pcie_read(rockchip, PCIE_CORE_OB_REGION_DESC0); + ob_desc_0 &= ~(RC_REGION_0_TYPE_MASK); + ob_desc_0 |= (type | (0x1 << 23)); + rockchip_pcie_write(rockchip, ob_desc_0, PCIE_CORE_OB_REGION_DESC0); + rockchip_pcie_write(rockchip, 0x0, PCIE_CORE_OB_REGION_DESC1); +} +EXPORT_SYMBOL_GPL(rockchip_pcie_cfg_configuration_accesses); diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h new file mode 100644 index 000000000..6111de35f --- /dev/null +++ b/drivers/pci/controller/pcie-rockchip.h @@ -0,0 +1,343 @@ +/* SPDX-License-Identifier: GPL-2.0+ */ +/* + * Rockchip AXI PCIe controller driver + * + * Copyright (c) 2018 Rockchip, Inc. + * + * Author: Shawn Lin <shawn.lin@rock-chips.com> + * + */ + +#ifndef _PCIE_ROCKCHIP_H +#define _PCIE_ROCKCHIP_H + +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/pci-ecam.h> + +/* + * The upper 16 bits of PCIE_CLIENT_CONFIG are a write mask for the lower 16 + * bits. This allows atomic updates of the register without locking. + */ +#define HIWORD_UPDATE(mask, val) (((mask) << 16) | (val)) +#define HIWORD_UPDATE_BIT(val) HIWORD_UPDATE(val, val) + +#define ENCODE_LANES(x) ((((x) >> 1) & 3) << 4) +#define MAX_LANE_NUM 4 +#define MAX_REGION_LIMIT 32 +#define MIN_EP_APERTURE 28 + +#define PCIE_CLIENT_BASE 0x0 +#define PCIE_CLIENT_CONFIG (PCIE_CLIENT_BASE + 0x00) +#define PCIE_CLIENT_CONF_ENABLE HIWORD_UPDATE_BIT(0x0001) +#define PCIE_CLIENT_CONF_DISABLE HIWORD_UPDATE(0x0001, 0) +#define PCIE_CLIENT_LINK_TRAIN_ENABLE HIWORD_UPDATE_BIT(0x0002) +#define PCIE_CLIENT_ARI_ENABLE HIWORD_UPDATE_BIT(0x0008) +#define PCIE_CLIENT_CONF_LANE_NUM(x) HIWORD_UPDATE(0x0030, ENCODE_LANES(x)) +#define PCIE_CLIENT_MODE_RC HIWORD_UPDATE_BIT(0x0040) +#define PCIE_CLIENT_MODE_EP HIWORD_UPDATE(0x0040, 0) +#define PCIE_CLIENT_GEN_SEL_1 HIWORD_UPDATE(0x0080, 0) +#define PCIE_CLIENT_GEN_SEL_2 HIWORD_UPDATE_BIT(0x0080) +#define PCIE_CLIENT_LEGACY_INT_CTRL (PCIE_CLIENT_BASE + 0x0c) +#define PCIE_CLIENT_INT_IN_ASSERT HIWORD_UPDATE_BIT(0x0002) +#define PCIE_CLIENT_INT_IN_DEASSERT HIWORD_UPDATE(0x0002, 0) +#define PCIE_CLIENT_INT_PEND_ST_PEND HIWORD_UPDATE_BIT(0x0001) +#define PCIE_CLIENT_INT_PEND_ST_NORMAL HIWORD_UPDATE(0x0001, 0) +#define PCIE_CLIENT_SIDE_BAND_STATUS (PCIE_CLIENT_BASE + 0x20) +#define PCIE_CLIENT_PHY_ST BIT(12) +#define PCIE_CLIENT_DEBUG_OUT_0 (PCIE_CLIENT_BASE + 0x3c) +#define PCIE_CLIENT_DEBUG_LTSSM_MASK GENMASK(5, 0) +#define PCIE_CLIENT_DEBUG_LTSSM_L1 0x18 +#define PCIE_CLIENT_DEBUG_LTSSM_L2 0x19 +#define PCIE_CLIENT_BASIC_STATUS1 (PCIE_CLIENT_BASE + 0x48) +#define PCIE_CLIENT_LINK_STATUS_UP 0x00300000 +#define PCIE_CLIENT_LINK_STATUS_MASK 0x00300000 +#define PCIE_CLIENT_INT_MASK (PCIE_CLIENT_BASE + 0x4c) +#define PCIE_CLIENT_INT_STATUS (PCIE_CLIENT_BASE + 0x50) +#define PCIE_CLIENT_INTR_MASK GENMASK(8, 5) +#define PCIE_CLIENT_INTR_SHIFT 5 +#define PCIE_CLIENT_INT_LEGACY_DONE BIT(15) +#define PCIE_CLIENT_INT_MSG BIT(14) +#define PCIE_CLIENT_INT_HOT_RST BIT(13) +#define PCIE_CLIENT_INT_DPA BIT(12) +#define PCIE_CLIENT_INT_FATAL_ERR BIT(11) +#define PCIE_CLIENT_INT_NFATAL_ERR BIT(10) +#define PCIE_CLIENT_INT_CORR_ERR BIT(9) +#define PCIE_CLIENT_INT_INTD BIT(8) +#define PCIE_CLIENT_INT_INTC BIT(7) +#define PCIE_CLIENT_INT_INTB BIT(6) +#define PCIE_CLIENT_INT_INTA BIT(5) +#define PCIE_CLIENT_INT_LOCAL BIT(4) +#define PCIE_CLIENT_INT_UDMA BIT(3) +#define PCIE_CLIENT_INT_PHY BIT(2) +#define PCIE_CLIENT_INT_HOT_PLUG BIT(1) +#define PCIE_CLIENT_INT_PWR_STCG BIT(0) + +#define PCIE_CLIENT_INT_LEGACY \ + (PCIE_CLIENT_INT_INTA | PCIE_CLIENT_INT_INTB | \ + PCIE_CLIENT_INT_INTC | PCIE_CLIENT_INT_INTD) + +#define PCIE_CLIENT_INT_CLI \ + (PCIE_CLIENT_INT_CORR_ERR | PCIE_CLIENT_INT_NFATAL_ERR | \ + PCIE_CLIENT_INT_FATAL_ERR | PCIE_CLIENT_INT_DPA | \ + PCIE_CLIENT_INT_HOT_RST | PCIE_CLIENT_INT_MSG | \ + PCIE_CLIENT_INT_LEGACY_DONE | PCIE_CLIENT_INT_LEGACY | \ + PCIE_CLIENT_INT_PHY) + +#define PCIE_CORE_CTRL_MGMT_BASE 0x900000 +#define PCIE_CORE_CTRL (PCIE_CORE_CTRL_MGMT_BASE + 0x000) +#define PCIE_CORE_PL_CONF_SPEED_5G 0x00000008 +#define PCIE_CORE_PL_CONF_SPEED_MASK 0x00000018 +#define PCIE_CORE_PL_CONF_LANE_MASK 0x00000006 +#define PCIE_CORE_PL_CONF_LANE_SHIFT 1 +#define PCIE_CORE_CTRL_PLC1 (PCIE_CORE_CTRL_MGMT_BASE + 0x004) +#define PCIE_CORE_CTRL_PLC1_FTS_MASK GENMASK(23, 8) +#define PCIE_CORE_CTRL_PLC1_FTS_SHIFT 8 +#define PCIE_CORE_CTRL_PLC1_FTS_CNT 0xffff +#define PCIE_CORE_TXCREDIT_CFG1 (PCIE_CORE_CTRL_MGMT_BASE + 0x020) +#define PCIE_CORE_TXCREDIT_CFG1_MUI_MASK 0xFFFF0000 +#define PCIE_CORE_TXCREDIT_CFG1_MUI_SHIFT 16 +#define PCIE_CORE_TXCREDIT_CFG1_MUI_ENCODE(x) \ + (((x) >> 3) << PCIE_CORE_TXCREDIT_CFG1_MUI_SHIFT) +#define PCIE_CORE_LANE_MAP (PCIE_CORE_CTRL_MGMT_BASE + 0x200) +#define PCIE_CORE_LANE_MAP_MASK 0x0000000f +#define PCIE_CORE_LANE_MAP_REVERSE BIT(16) +#define PCIE_CORE_INT_STATUS (PCIE_CORE_CTRL_MGMT_BASE + 0x20c) +#define PCIE_CORE_INT_PRFPE BIT(0) +#define PCIE_CORE_INT_CRFPE BIT(1) +#define PCIE_CORE_INT_RRPE BIT(2) +#define PCIE_CORE_INT_PRFO BIT(3) +#define PCIE_CORE_INT_CRFO BIT(4) +#define PCIE_CORE_INT_RT BIT(5) +#define PCIE_CORE_INT_RTR BIT(6) +#define PCIE_CORE_INT_PE BIT(7) +#define PCIE_CORE_INT_MTR BIT(8) +#define PCIE_CORE_INT_UCR BIT(9) +#define PCIE_CORE_INT_FCE BIT(10) +#define PCIE_CORE_INT_CT BIT(11) +#define PCIE_CORE_INT_UTC BIT(18) +#define PCIE_CORE_INT_MMVC BIT(19) +#define PCIE_CORE_CONFIG_VENDOR (PCIE_CORE_CTRL_MGMT_BASE + 0x44) +#define PCIE_CORE_INT_MASK (PCIE_CORE_CTRL_MGMT_BASE + 0x210) +#define PCIE_CORE_PHY_FUNC_CFG (PCIE_CORE_CTRL_MGMT_BASE + 0x2c0) +#define PCIE_RC_BAR_CONF (PCIE_CORE_CTRL_MGMT_BASE + 0x300) +#define ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_DISABLED 0x0 +#define ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_IO_32BITS 0x1 +#define ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_MEM_32BITS 0x4 +#define ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_PREFETCH_MEM_32BITS 0x5 +#define ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_MEM_64BITS 0x6 +#define ROCKCHIP_PCIE_CORE_BAR_CFG_CTRL_PREFETCH_MEM_64BITS 0x7 + +#define PCIE_CORE_INT \ + (PCIE_CORE_INT_PRFPE | PCIE_CORE_INT_CRFPE | \ + PCIE_CORE_INT_RRPE | PCIE_CORE_INT_CRFO | \ + PCIE_CORE_INT_RT | PCIE_CORE_INT_RTR | \ + PCIE_CORE_INT_PE | PCIE_CORE_INT_MTR | \ + PCIE_CORE_INT_UCR | PCIE_CORE_INT_FCE | \ + PCIE_CORE_INT_CT | PCIE_CORE_INT_UTC | \ + PCIE_CORE_INT_MMVC) + +#define PCIE_RC_RP_ATS_BASE 0x400000 +#define PCIE_RC_CONFIG_NORMAL_BASE 0x800000 +#define PCIE_EP_PF_CONFIG_REGS_BASE 0x800000 +#define PCIE_RC_CONFIG_BASE 0xa00000 +#define PCIE_EP_CONFIG_BASE 0xa00000 +#define PCIE_EP_CONFIG_DID_VID (PCIE_EP_CONFIG_BASE + 0x00) +#define PCIE_RC_CONFIG_RID_CCR (PCIE_RC_CONFIG_BASE + 0x08) +#define PCIE_RC_CONFIG_DCR (PCIE_RC_CONFIG_BASE + 0xc4) +#define PCIE_RC_CONFIG_DCR_CSPL_SHIFT 18 +#define PCIE_RC_CONFIG_DCR_CSPL_LIMIT 0xff +#define PCIE_RC_CONFIG_DCR_CPLS_SHIFT 26 +#define PCIE_RC_CONFIG_DCSR (PCIE_RC_CONFIG_BASE + 0xc8) +#define PCIE_RC_CONFIG_DCSR_MPS_MASK GENMASK(7, 5) +#define PCIE_RC_CONFIG_DCSR_MPS_256 (0x1 << 5) +#define PCIE_RC_CONFIG_LINK_CAP (PCIE_RC_CONFIG_BASE + 0xcc) +#define PCIE_RC_CONFIG_LINK_CAP_L0S BIT(10) +#define PCIE_RC_CONFIG_LCS (PCIE_RC_CONFIG_BASE + 0xd0) +#define PCIE_RC_CONFIG_L1_SUBSTATE_CTRL2 (PCIE_RC_CONFIG_BASE + 0x90c) +#define PCIE_RC_CONFIG_THP_CAP (PCIE_RC_CONFIG_BASE + 0x274) +#define PCIE_RC_CONFIG_THP_CAP_NEXT_MASK GENMASK(31, 20) + +#define MAX_AXI_IB_ROOTPORT_REGION_NUM 3 +#define MIN_AXI_ADDR_BITS_PASSED 8 +#define PCIE_ADDR_MASK GENMASK_ULL(63, MIN_AXI_ADDR_BITS_PASSED) +#define PCIE_CORE_AXI_CONF_BASE 0xc00000 +#define PCIE_CORE_OB_REGION_ADDR0 (PCIE_CORE_AXI_CONF_BASE + 0x0) +#define PCIE_CORE_OB_REGION_ADDR0_NUM_BITS 0x3f +#define PCIE_CORE_OB_REGION_ADDR0_LO_ADDR PCIE_ADDR_MASK +#define PCIE_CORE_OB_REGION_ADDR1 (PCIE_CORE_AXI_CONF_BASE + 0x4) +#define PCIE_CORE_OB_REGION_DESC0 (PCIE_CORE_AXI_CONF_BASE + 0x8) +#define PCIE_CORE_OB_REGION_DESC1 (PCIE_CORE_AXI_CONF_BASE + 0xc) + +#define PCIE_CORE_AXI_INBOUND_BASE 0xc00800 +#define PCIE_RP_IB_ADDR0 (PCIE_CORE_AXI_INBOUND_BASE + 0x0) +#define PCIE_CORE_IB_REGION_ADDR0_NUM_BITS 0x3f +#define PCIE_CORE_IB_REGION_ADDR0_LO_ADDR PCIE_ADDR_MASK +#define PCIE_RP_IB_ADDR1 (PCIE_CORE_AXI_INBOUND_BASE + 0x4) + +/* Size of one AXI Region (not Region 0) */ +#define AXI_REGION_SIZE BIT(20) +/* Size of Region 0, equal to sum of sizes of other regions */ +#define AXI_REGION_0_SIZE (32 * (0x1 << 20)) +#define OB_REG_SIZE_SHIFT 5 +#define IB_ROOT_PORT_REG_SIZE_SHIFT 3 +#define AXI_WRAPPER_IO_WRITE 0x6 +#define AXI_WRAPPER_MEM_WRITE 0x2 +#define AXI_WRAPPER_TYPE0_CFG 0xa +#define AXI_WRAPPER_TYPE1_CFG 0xb +#define AXI_WRAPPER_NOR_MSG 0xc + +#define PCIE_RC_SEND_PME_OFF 0x11960 +#define ROCKCHIP_VENDOR_ID 0x1d87 +#define PCIE_LINK_IS_L2(x) \ + (((x) & PCIE_CLIENT_DEBUG_LTSSM_MASK) == PCIE_CLIENT_DEBUG_LTSSM_L2) +#define PCIE_LINK_UP(x) \ + (((x) & PCIE_CLIENT_LINK_STATUS_MASK) == PCIE_CLIENT_LINK_STATUS_UP) +#define PCIE_LINK_IS_GEN2(x) \ + (((x) & PCIE_CORE_PL_CONF_SPEED_MASK) == PCIE_CORE_PL_CONF_SPEED_5G) + +#define RC_REGION_0_ADDR_TRANS_H 0x00000000 +#define RC_REGION_0_ADDR_TRANS_L 0x00000000 +#define RC_REGION_0_PASS_BITS (25 - 1) +#define RC_REGION_0_TYPE_MASK GENMASK(3, 0) +#define MAX_AXI_WRAPPER_REGION_NUM 33 + +#define ROCKCHIP_PCIE_MSG_ROUTING_TO_RC 0x0 +#define ROCKCHIP_PCIE_MSG_ROUTING_VIA_ADDR 0x1 +#define ROCKCHIP_PCIE_MSG_ROUTING_VIA_ID 0x2 +#define ROCKCHIP_PCIE_MSG_ROUTING_BROADCAST 0x3 +#define ROCKCHIP_PCIE_MSG_ROUTING_LOCAL_INTX 0x4 +#define ROCKCHIP_PCIE_MSG_ROUTING_PME_ACK 0x5 +#define ROCKCHIP_PCIE_MSG_CODE_ASSERT_INTA 0x20 +#define ROCKCHIP_PCIE_MSG_CODE_ASSERT_INTB 0x21 +#define ROCKCHIP_PCIE_MSG_CODE_ASSERT_INTC 0x22 +#define ROCKCHIP_PCIE_MSG_CODE_ASSERT_INTD 0x23 +#define ROCKCHIP_PCIE_MSG_CODE_DEASSERT_INTA 0x24 +#define ROCKCHIP_PCIE_MSG_CODE_DEASSERT_INTB 0x25 +#define ROCKCHIP_PCIE_MSG_CODE_DEASSERT_INTC 0x26 +#define ROCKCHIP_PCIE_MSG_CODE_DEASSERT_INTD 0x27 +#define ROCKCHIP_PCIE_MSG_ROUTING_MASK GENMASK(7, 5) +#define ROCKCHIP_PCIE_MSG_ROUTING(route) \ + (((route) << 5) & ROCKCHIP_PCIE_MSG_ROUTING_MASK) +#define ROCKCHIP_PCIE_MSG_CODE_MASK GENMASK(15, 8) +#define ROCKCHIP_PCIE_MSG_CODE(code) \ + (((code) << 8) & ROCKCHIP_PCIE_MSG_CODE_MASK) +#define ROCKCHIP_PCIE_MSG_NO_DATA BIT(16) + +#define ROCKCHIP_PCIE_EP_CMD_STATUS 0x4 +#define ROCKCHIP_PCIE_EP_CMD_STATUS_IS BIT(19) +#define ROCKCHIP_PCIE_EP_MSI_CTRL_REG 0x90 +#define ROCKCHIP_PCIE_EP_MSI_CP1_OFFSET 8 +#define ROCKCHIP_PCIE_EP_MSI_CP1_MASK GENMASK(15, 8) +#define ROCKCHIP_PCIE_EP_MSI_FLAGS_OFFSET 16 +#define ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_OFFSET 17 +#define ROCKCHIP_PCIE_EP_MSI_CTRL_MMC_MASK GENMASK(19, 17) +#define ROCKCHIP_PCIE_EP_MSI_CTRL_MME_OFFSET 20 +#define ROCKCHIP_PCIE_EP_MSI_CTRL_MME_MASK GENMASK(22, 20) +#define ROCKCHIP_PCIE_EP_MSI_CTRL_ME BIT(16) +#define ROCKCHIP_PCIE_EP_MSI_CTRL_MASK_MSI_CAP BIT(24) +#define ROCKCHIP_PCIE_EP_MSIX_CAP_REG 0xb0 +#define ROCKCHIP_PCIE_EP_MSIX_CAP_CP_OFFSET 8 +#define ROCKCHIP_PCIE_EP_MSIX_CAP_CP_MASK GENMASK(15, 8) +#define ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR 0x1 +#define ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR 0x3 +#define ROCKCHIP_PCIE_EP_FUNC_BASE(fn) \ + (PCIE_EP_PF_CONFIG_REGS_BASE + (((fn) << 12) & GENMASK(19, 12))) +#define ROCKCHIP_PCIE_EP_VIRT_FUNC_BASE(fn) \ + (PCIE_EP_PF_CONFIG_REGS_BASE + 0x10000 + (((fn) << 12) & GENMASK(19, 12))) +#define ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar) \ + (PCIE_CORE_AXI_CONF_BASE + 0x0828 + (fn) * 0x0040 + (bar) * 0x0008) +#define ROCKCHIP_PCIE_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar) \ + (PCIE_CORE_AXI_CONF_BASE + 0x082c + (fn) * 0x0040 + (bar) * 0x0008) +#define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0_DEVFN_MASK GENMASK(19, 12) +#define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0_DEVFN(devfn) \ + (((devfn) << 12) & \ + ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0_DEVFN_MASK) +#define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0_BUS_MASK GENMASK(27, 20) +#define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0_BUS(bus) \ + (((bus) << 20) & ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0_BUS_MASK) +#define PCIE_RC_EP_ATR_OB_REGIONS_1_32 (PCIE_CORE_AXI_CONF_BASE + 0x0020) +#define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR0(r) \ + (PCIE_RC_EP_ATR_OB_REGIONS_1_32 + 0x0000 + ((r) & 0x1f) * 0x0020) +#define ROCKCHIP_PCIE_AT_OB_REGION_PCI_ADDR1(r) \ + (PCIE_RC_EP_ATR_OB_REGIONS_1_32 + 0x0004 + ((r) & 0x1f) * 0x0020) +#define ROCKCHIP_PCIE_AT_OB_REGION_DESC0_HARDCODED_RID BIT(23) +#define ROCKCHIP_PCIE_AT_OB_REGION_DESC0_DEVFN_MASK GENMASK(31, 24) +#define ROCKCHIP_PCIE_AT_OB_REGION_DESC0_DEVFN(devfn) \ + (((devfn) << 24) & ROCKCHIP_PCIE_AT_OB_REGION_DESC0_DEVFN_MASK) +#define ROCKCHIP_PCIE_AT_OB_REGION_DESC0(r) \ + (PCIE_RC_EP_ATR_OB_REGIONS_1_32 + 0x0008 + ((r) & 0x1f) * 0x0020) +#define ROCKCHIP_PCIE_AT_OB_REGION_DESC1(r) \ + (PCIE_RC_EP_ATR_OB_REGIONS_1_32 + 0x000c + ((r) & 0x1f) * 0x0020) +#define ROCKCHIP_PCIE_AT_OB_REGION_DESC2(r) \ + (PCIE_RC_EP_ATR_OB_REGIONS_1_32 + 0x0010 + ((r) & 0x1f) * 0x0020) + +#define ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG0(fn) \ + (PCIE_CORE_CTRL_MGMT_BASE + 0x0240 + (fn) * 0x0008) +#define ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG1(fn) \ + (PCIE_CORE_CTRL_MGMT_BASE + 0x0244 + (fn) * 0x0008) +#define ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b) \ + (GENMASK(4, 0) << ((b) * 8)) +#define ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_APERTURE(b, a) \ + (((a) << ((b) * 8)) & \ + ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b)) +#define ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b) \ + (GENMASK(7, 5) << ((b) * 8)) +#define ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_CTRL(b, c) \ + (((c) << ((b) * 8 + 5)) & \ + ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)) + +struct rockchip_pcie { + void __iomem *reg_base; /* DT axi-base */ + void __iomem *apb_base; /* DT apb-base */ + bool legacy_phy; + struct phy *phys[MAX_LANE_NUM]; + struct reset_control *core_rst; + struct reset_control *mgmt_rst; + struct reset_control *mgmt_sticky_rst; + struct reset_control *pipe_rst; + struct reset_control *pm_rst; + struct reset_control *aclk_rst; + struct reset_control *pclk_rst; + struct clk *aclk_pcie; + struct clk *aclk_perf_pcie; + struct clk *hclk_pcie; + struct clk *clk_pcie_pm; + struct regulator *vpcie12v; /* 12V power supply */ + struct regulator *vpcie3v3; /* 3.3V power supply */ + struct regulator *vpcie1v8; /* 1.8V power supply */ + struct regulator *vpcie0v9; /* 0.9V power supply */ + struct gpio_desc *ep_gpio; + u32 lanes; + u8 lanes_map; + int link_gen; + struct device *dev; + struct irq_domain *irq_domain; + int offset; + void __iomem *msg_region; + phys_addr_t msg_bus_addr; + bool is_rc; + struct resource *mem_res; +}; + +static u32 rockchip_pcie_read(struct rockchip_pcie *rockchip, u32 reg) +{ + return readl(rockchip->apb_base + reg); +} + +static void rockchip_pcie_write(struct rockchip_pcie *rockchip, u32 val, + u32 reg) +{ + writel(val, rockchip->apb_base + reg); +} + +int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip); +int rockchip_pcie_init_port(struct rockchip_pcie *rockchip); +int rockchip_pcie_get_phys(struct rockchip_pcie *rockchip); +void rockchip_pcie_deinit_phys(struct rockchip_pcie *rockchip); +int rockchip_pcie_enable_clocks(struct rockchip_pcie *rockchip); +void rockchip_pcie_disable_clocks(void *data); +void rockchip_pcie_cfg_configuration_accesses( + struct rockchip_pcie *rockchip, u32 type); + +#endif /* _PCIE_ROCKCHIP_H */ diff --git a/drivers/pci/controller/pcie-xilinx-cpm.c b/drivers/pci/controller/pcie-xilinx-cpm.c new file mode 100644 index 000000000..e4ab48041 --- /dev/null +++ b/drivers/pci/controller/pcie-xilinx-cpm.c @@ -0,0 +1,664 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * PCIe host controller driver for Xilinx Versal CPM DMA Bridge + * + * (C) Copyright 2019 - 2020, Xilinx, Inc. + */ + +#include <linux/bitfield.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqchip.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/of_irq.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/pci-ecam.h> + +#include "../pci.h" + +/* Register definitions */ +#define XILINX_CPM_PCIE_REG_IDR 0x00000E10 +#define XILINX_CPM_PCIE_REG_IMR 0x00000E14 +#define XILINX_CPM_PCIE_REG_PSCR 0x00000E1C +#define XILINX_CPM_PCIE_REG_RPSC 0x00000E20 +#define XILINX_CPM_PCIE_REG_RPEFR 0x00000E2C +#define XILINX_CPM_PCIE_REG_IDRN 0x00000E38 +#define XILINX_CPM_PCIE_REG_IDRN_MASK 0x00000E3C +#define XILINX_CPM_PCIE_MISC_IR_STATUS 0x00000340 +#define XILINX_CPM_PCIE_MISC_IR_ENABLE 0x00000348 +#define XILINX_CPM_PCIE_MISC_IR_LOCAL BIT(1) + +#define XILINX_CPM_PCIE_IR_STATUS 0x000002A0 +#define XILINX_CPM_PCIE_IR_ENABLE 0x000002A8 +#define XILINX_CPM_PCIE_IR_LOCAL BIT(0) + +/* Interrupt registers definitions */ +#define XILINX_CPM_PCIE_INTR_LINK_DOWN 0 +#define XILINX_CPM_PCIE_INTR_HOT_RESET 3 +#define XILINX_CPM_PCIE_INTR_CFG_PCIE_TIMEOUT 4 +#define XILINX_CPM_PCIE_INTR_CFG_TIMEOUT 8 +#define XILINX_CPM_PCIE_INTR_CORRECTABLE 9 +#define XILINX_CPM_PCIE_INTR_NONFATAL 10 +#define XILINX_CPM_PCIE_INTR_FATAL 11 +#define XILINX_CPM_PCIE_INTR_CFG_ERR_POISON 12 +#define XILINX_CPM_PCIE_INTR_PME_TO_ACK_RCVD 15 +#define XILINX_CPM_PCIE_INTR_INTX 16 +#define XILINX_CPM_PCIE_INTR_PM_PME_RCVD 17 +#define XILINX_CPM_PCIE_INTR_SLV_UNSUPP 20 +#define XILINX_CPM_PCIE_INTR_SLV_UNEXP 21 +#define XILINX_CPM_PCIE_INTR_SLV_COMPL 22 +#define XILINX_CPM_PCIE_INTR_SLV_ERRP 23 +#define XILINX_CPM_PCIE_INTR_SLV_CMPABT 24 +#define XILINX_CPM_PCIE_INTR_SLV_ILLBUR 25 +#define XILINX_CPM_PCIE_INTR_MST_DECERR 26 +#define XILINX_CPM_PCIE_INTR_MST_SLVERR 27 +#define XILINX_CPM_PCIE_INTR_SLV_PCIE_TIMEOUT 28 + +#define IMR(x) BIT(XILINX_CPM_PCIE_INTR_ ##x) + +#define XILINX_CPM_PCIE_IMR_ALL_MASK \ + ( \ + IMR(LINK_DOWN) | \ + IMR(HOT_RESET) | \ + IMR(CFG_PCIE_TIMEOUT) | \ + IMR(CFG_TIMEOUT) | \ + IMR(CORRECTABLE) | \ + IMR(NONFATAL) | \ + IMR(FATAL) | \ + IMR(CFG_ERR_POISON) | \ + IMR(PME_TO_ACK_RCVD) | \ + IMR(INTX) | \ + IMR(PM_PME_RCVD) | \ + IMR(SLV_UNSUPP) | \ + IMR(SLV_UNEXP) | \ + IMR(SLV_COMPL) | \ + IMR(SLV_ERRP) | \ + IMR(SLV_CMPABT) | \ + IMR(SLV_ILLBUR) | \ + IMR(MST_DECERR) | \ + IMR(MST_SLVERR) | \ + IMR(SLV_PCIE_TIMEOUT) \ + ) + +#define XILINX_CPM_PCIE_IDR_ALL_MASK 0xFFFFFFFF +#define XILINX_CPM_PCIE_IDRN_MASK GENMASK(19, 16) +#define XILINX_CPM_PCIE_IDRN_SHIFT 16 + +/* Root Port Error FIFO Read Register definitions */ +#define XILINX_CPM_PCIE_RPEFR_ERR_VALID BIT(18) +#define XILINX_CPM_PCIE_RPEFR_REQ_ID GENMASK(15, 0) +#define XILINX_CPM_PCIE_RPEFR_ALL_MASK 0xFFFFFFFF + +/* Root Port Status/control Register definitions */ +#define XILINX_CPM_PCIE_REG_RPSC_BEN BIT(0) + +/* Phy Status/Control Register definitions */ +#define XILINX_CPM_PCIE_REG_PSCR_LNKUP BIT(11) + +enum xilinx_cpm_version { + CPM, + CPM5, +}; + +/** + * struct xilinx_cpm_variant - CPM variant information + * @version: CPM version + */ +struct xilinx_cpm_variant { + enum xilinx_cpm_version version; +}; + +/** + * struct xilinx_cpm_pcie - PCIe port information + * @dev: Device pointer + * @reg_base: Bridge Register Base + * @cpm_base: CPM System Level Control and Status Register(SLCR) Base + * @intx_domain: Legacy IRQ domain pointer + * @cpm_domain: CPM IRQ domain pointer + * @cfg: Holds mappings of config space window + * @intx_irq: legacy interrupt number + * @irq: Error interrupt number + * @lock: lock protecting shared register access + * @variant: CPM version check pointer + */ +struct xilinx_cpm_pcie { + struct device *dev; + void __iomem *reg_base; + void __iomem *cpm_base; + struct irq_domain *intx_domain; + struct irq_domain *cpm_domain; + struct pci_config_window *cfg; + int intx_irq; + int irq; + raw_spinlock_t lock; + const struct xilinx_cpm_variant *variant; +}; + +static u32 pcie_read(struct xilinx_cpm_pcie *port, u32 reg) +{ + return readl_relaxed(port->reg_base + reg); +} + +static void pcie_write(struct xilinx_cpm_pcie *port, + u32 val, u32 reg) +{ + writel_relaxed(val, port->reg_base + reg); +} + +static bool cpm_pcie_link_up(struct xilinx_cpm_pcie *port) +{ + return (pcie_read(port, XILINX_CPM_PCIE_REG_PSCR) & + XILINX_CPM_PCIE_REG_PSCR_LNKUP); +} + +static void cpm_pcie_clear_err_interrupts(struct xilinx_cpm_pcie *port) +{ + unsigned long val = pcie_read(port, XILINX_CPM_PCIE_REG_RPEFR); + + if (val & XILINX_CPM_PCIE_RPEFR_ERR_VALID) { + dev_dbg(port->dev, "Requester ID %lu\n", + val & XILINX_CPM_PCIE_RPEFR_REQ_ID); + pcie_write(port, XILINX_CPM_PCIE_RPEFR_ALL_MASK, + XILINX_CPM_PCIE_REG_RPEFR); + } +} + +static void xilinx_cpm_mask_leg_irq(struct irq_data *data) +{ + struct xilinx_cpm_pcie *port = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 mask; + u32 val; + + mask = BIT(data->hwirq + XILINX_CPM_PCIE_IDRN_SHIFT); + raw_spin_lock_irqsave(&port->lock, flags); + val = pcie_read(port, XILINX_CPM_PCIE_REG_IDRN_MASK); + pcie_write(port, (val & (~mask)), XILINX_CPM_PCIE_REG_IDRN_MASK); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static void xilinx_cpm_unmask_leg_irq(struct irq_data *data) +{ + struct xilinx_cpm_pcie *port = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 mask; + u32 val; + + mask = BIT(data->hwirq + XILINX_CPM_PCIE_IDRN_SHIFT); + raw_spin_lock_irqsave(&port->lock, flags); + val = pcie_read(port, XILINX_CPM_PCIE_REG_IDRN_MASK); + pcie_write(port, (val | mask), XILINX_CPM_PCIE_REG_IDRN_MASK); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static struct irq_chip xilinx_cpm_leg_irq_chip = { + .name = "INTx", + .irq_mask = xilinx_cpm_mask_leg_irq, + .irq_unmask = xilinx_cpm_unmask_leg_irq, +}; + +/** + * xilinx_cpm_pcie_intx_map - Set the handler for the INTx and mark IRQ as valid + * @domain: IRQ domain + * @irq: Virtual IRQ number + * @hwirq: HW interrupt number + * + * Return: Always returns 0. + */ +static int xilinx_cpm_pcie_intx_map(struct irq_domain *domain, + unsigned int irq, irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &xilinx_cpm_leg_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + irq_set_status_flags(irq, IRQ_LEVEL); + + return 0; +} + +/* INTx IRQ Domain operations */ +static const struct irq_domain_ops intx_domain_ops = { + .map = xilinx_cpm_pcie_intx_map, +}; + +static void xilinx_cpm_pcie_intx_flow(struct irq_desc *desc) +{ + struct xilinx_cpm_pcie *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned long val; + int i; + + chained_irq_enter(chip, desc); + + val = FIELD_GET(XILINX_CPM_PCIE_IDRN_MASK, + pcie_read(port, XILINX_CPM_PCIE_REG_IDRN)); + + for_each_set_bit(i, &val, PCI_NUM_INTX) + generic_handle_domain_irq(port->intx_domain, i); + + chained_irq_exit(chip, desc); +} + +static void xilinx_cpm_mask_event_irq(struct irq_data *d) +{ + struct xilinx_cpm_pcie *port = irq_data_get_irq_chip_data(d); + u32 val; + + raw_spin_lock(&port->lock); + val = pcie_read(port, XILINX_CPM_PCIE_REG_IMR); + val &= ~BIT(d->hwirq); + pcie_write(port, val, XILINX_CPM_PCIE_REG_IMR); + raw_spin_unlock(&port->lock); +} + +static void xilinx_cpm_unmask_event_irq(struct irq_data *d) +{ + struct xilinx_cpm_pcie *port = irq_data_get_irq_chip_data(d); + u32 val; + + raw_spin_lock(&port->lock); + val = pcie_read(port, XILINX_CPM_PCIE_REG_IMR); + val |= BIT(d->hwirq); + pcie_write(port, val, XILINX_CPM_PCIE_REG_IMR); + raw_spin_unlock(&port->lock); +} + +static struct irq_chip xilinx_cpm_event_irq_chip = { + .name = "RC-Event", + .irq_mask = xilinx_cpm_mask_event_irq, + .irq_unmask = xilinx_cpm_unmask_event_irq, +}; + +static int xilinx_cpm_pcie_event_map(struct irq_domain *domain, + unsigned int irq, irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &xilinx_cpm_event_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + irq_set_status_flags(irq, IRQ_LEVEL); + return 0; +} + +static const struct irq_domain_ops event_domain_ops = { + .map = xilinx_cpm_pcie_event_map, +}; + +static void xilinx_cpm_pcie_event_flow(struct irq_desc *desc) +{ + struct xilinx_cpm_pcie *port = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned long val; + int i; + + chained_irq_enter(chip, desc); + val = pcie_read(port, XILINX_CPM_PCIE_REG_IDR); + val &= pcie_read(port, XILINX_CPM_PCIE_REG_IMR); + for_each_set_bit(i, &val, 32) + generic_handle_domain_irq(port->cpm_domain, i); + pcie_write(port, val, XILINX_CPM_PCIE_REG_IDR); + + if (port->variant->version == CPM5) { + val = readl_relaxed(port->cpm_base + XILINX_CPM_PCIE_IR_STATUS); + if (val) + writel_relaxed(val, port->cpm_base + + XILINX_CPM_PCIE_IR_STATUS); + } + + /* + * XILINX_CPM_PCIE_MISC_IR_STATUS register is mapped to + * CPM SLCR block. + */ + val = readl_relaxed(port->cpm_base + XILINX_CPM_PCIE_MISC_IR_STATUS); + if (val) + writel_relaxed(val, + port->cpm_base + XILINX_CPM_PCIE_MISC_IR_STATUS); + + chained_irq_exit(chip, desc); +} + +#define _IC(x, s) \ + [XILINX_CPM_PCIE_INTR_ ## x] = { __stringify(x), s } + +static const struct { + const char *sym; + const char *str; +} intr_cause[32] = { + _IC(LINK_DOWN, "Link Down"), + _IC(HOT_RESET, "Hot reset"), + _IC(CFG_TIMEOUT, "ECAM access timeout"), + _IC(CORRECTABLE, "Correctable error message"), + _IC(NONFATAL, "Non fatal error message"), + _IC(FATAL, "Fatal error message"), + _IC(SLV_UNSUPP, "Slave unsupported request"), + _IC(SLV_UNEXP, "Slave unexpected completion"), + _IC(SLV_COMPL, "Slave completion timeout"), + _IC(SLV_ERRP, "Slave Error Poison"), + _IC(SLV_CMPABT, "Slave Completer Abort"), + _IC(SLV_ILLBUR, "Slave Illegal Burst"), + _IC(MST_DECERR, "Master decode error"), + _IC(MST_SLVERR, "Master slave error"), + _IC(CFG_PCIE_TIMEOUT, "PCIe ECAM access timeout"), + _IC(CFG_ERR_POISON, "ECAM poisoned completion received"), + _IC(PME_TO_ACK_RCVD, "PME_TO_ACK message received"), + _IC(PM_PME_RCVD, "PM_PME message received"), + _IC(SLV_PCIE_TIMEOUT, "PCIe completion timeout received"), +}; + +static irqreturn_t xilinx_cpm_pcie_intr_handler(int irq, void *dev_id) +{ + struct xilinx_cpm_pcie *port = dev_id; + struct device *dev = port->dev; + struct irq_data *d; + + d = irq_domain_get_irq_data(port->cpm_domain, irq); + + switch (d->hwirq) { + case XILINX_CPM_PCIE_INTR_CORRECTABLE: + case XILINX_CPM_PCIE_INTR_NONFATAL: + case XILINX_CPM_PCIE_INTR_FATAL: + cpm_pcie_clear_err_interrupts(port); + fallthrough; + + default: + if (intr_cause[d->hwirq].str) + dev_warn(dev, "%s\n", intr_cause[d->hwirq].str); + else + dev_warn(dev, "Unknown IRQ %ld\n", d->hwirq); + } + + return IRQ_HANDLED; +} + +static void xilinx_cpm_free_irq_domains(struct xilinx_cpm_pcie *port) +{ + if (port->intx_domain) { + irq_domain_remove(port->intx_domain); + port->intx_domain = NULL; + } + + if (port->cpm_domain) { + irq_domain_remove(port->cpm_domain); + port->cpm_domain = NULL; + } +} + +/** + * xilinx_cpm_pcie_init_irq_domain - Initialize IRQ domain + * @port: PCIe port information + * + * Return: '0' on success and error value on failure + */ +static int xilinx_cpm_pcie_init_irq_domain(struct xilinx_cpm_pcie *port) +{ + struct device *dev = port->dev; + struct device_node *node = dev->of_node; + struct device_node *pcie_intc_node; + + /* Setup INTx */ + pcie_intc_node = of_get_next_child(node, NULL); + if (!pcie_intc_node) { + dev_err(dev, "No PCIe Intc node found\n"); + return -EINVAL; + } + + port->cpm_domain = irq_domain_add_linear(pcie_intc_node, 32, + &event_domain_ops, + port); + if (!port->cpm_domain) + goto out; + + irq_domain_update_bus_token(port->cpm_domain, DOMAIN_BUS_NEXUS); + + port->intx_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, + &intx_domain_ops, + port); + if (!port->intx_domain) + goto out; + + irq_domain_update_bus_token(port->intx_domain, DOMAIN_BUS_WIRED); + + of_node_put(pcie_intc_node); + raw_spin_lock_init(&port->lock); + + return 0; +out: + xilinx_cpm_free_irq_domains(port); + of_node_put(pcie_intc_node); + dev_err(dev, "Failed to allocate IRQ domains\n"); + + return -ENOMEM; +} + +static int xilinx_cpm_setup_irq(struct xilinx_cpm_pcie *port) +{ + struct device *dev = port->dev; + struct platform_device *pdev = to_platform_device(dev); + int i, irq; + + port->irq = platform_get_irq(pdev, 0); + if (port->irq < 0) + return port->irq; + + for (i = 0; i < ARRAY_SIZE(intr_cause); i++) { + int err; + + if (!intr_cause[i].str) + continue; + + irq = irq_create_mapping(port->cpm_domain, i); + if (!irq) { + dev_err(dev, "Failed to map interrupt\n"); + return -ENXIO; + } + + err = devm_request_irq(dev, irq, xilinx_cpm_pcie_intr_handler, + 0, intr_cause[i].sym, port); + if (err) { + dev_err(dev, "Failed to request IRQ %d\n", irq); + return err; + } + } + + port->intx_irq = irq_create_mapping(port->cpm_domain, + XILINX_CPM_PCIE_INTR_INTX); + if (!port->intx_irq) { + dev_err(dev, "Failed to map INTx interrupt\n"); + return -ENXIO; + } + + /* Plug the INTx chained handler */ + irq_set_chained_handler_and_data(port->intx_irq, + xilinx_cpm_pcie_intx_flow, port); + + /* Plug the main event chained handler */ + irq_set_chained_handler_and_data(port->irq, + xilinx_cpm_pcie_event_flow, port); + + return 0; +} + +/** + * xilinx_cpm_pcie_init_port - Initialize hardware + * @port: PCIe port information + */ +static void xilinx_cpm_pcie_init_port(struct xilinx_cpm_pcie *port) +{ + if (cpm_pcie_link_up(port)) + dev_info(port->dev, "PCIe Link is UP\n"); + else + dev_info(port->dev, "PCIe Link is DOWN\n"); + + /* Disable all interrupts */ + pcie_write(port, ~XILINX_CPM_PCIE_IDR_ALL_MASK, + XILINX_CPM_PCIE_REG_IMR); + + /* Clear pending interrupts */ + pcie_write(port, pcie_read(port, XILINX_CPM_PCIE_REG_IDR) & + XILINX_CPM_PCIE_IMR_ALL_MASK, + XILINX_CPM_PCIE_REG_IDR); + + /* + * XILINX_CPM_PCIE_MISC_IR_ENABLE register is mapped to + * CPM SLCR block. + */ + writel(XILINX_CPM_PCIE_MISC_IR_LOCAL, + port->cpm_base + XILINX_CPM_PCIE_MISC_IR_ENABLE); + + if (port->variant->version == CPM5) { + writel(XILINX_CPM_PCIE_IR_LOCAL, + port->cpm_base + XILINX_CPM_PCIE_IR_ENABLE); + } + + /* Enable the Bridge enable bit */ + pcie_write(port, pcie_read(port, XILINX_CPM_PCIE_REG_RPSC) | + XILINX_CPM_PCIE_REG_RPSC_BEN, + XILINX_CPM_PCIE_REG_RPSC); +} + +/** + * xilinx_cpm_pcie_parse_dt - Parse Device tree + * @port: PCIe port information + * @bus_range: Bus resource + * + * Return: '0' on success and error value on failure + */ +static int xilinx_cpm_pcie_parse_dt(struct xilinx_cpm_pcie *port, + struct resource *bus_range) +{ + struct device *dev = port->dev; + struct platform_device *pdev = to_platform_device(dev); + struct resource *res; + + port->cpm_base = devm_platform_ioremap_resource_byname(pdev, + "cpm_slcr"); + if (IS_ERR(port->cpm_base)) + return PTR_ERR(port->cpm_base); + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg"); + if (!res) + return -ENXIO; + + port->cfg = pci_ecam_create(dev, res, bus_range, + &pci_generic_ecam_ops); + if (IS_ERR(port->cfg)) + return PTR_ERR(port->cfg); + + if (port->variant->version == CPM5) { + port->reg_base = devm_platform_ioremap_resource_byname(pdev, + "cpm_csr"); + if (IS_ERR(port->reg_base)) + return PTR_ERR(port->reg_base); + } else { + port->reg_base = port->cfg->win; + } + + return 0; +} + +static void xilinx_cpm_free_interrupts(struct xilinx_cpm_pcie *port) +{ + irq_set_chained_handler_and_data(port->intx_irq, NULL, NULL); + irq_set_chained_handler_and_data(port->irq, NULL, NULL); +} + +/** + * xilinx_cpm_pcie_probe - Probe function + * @pdev: Platform device pointer + * + * Return: '0' on success and error value on failure + */ +static int xilinx_cpm_pcie_probe(struct platform_device *pdev) +{ + struct xilinx_cpm_pcie *port; + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + struct resource_entry *bus; + int err; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*port)); + if (!bridge) + return -ENODEV; + + port = pci_host_bridge_priv(bridge); + + port->dev = dev; + + err = xilinx_cpm_pcie_init_irq_domain(port); + if (err) + return err; + + bus = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (!bus) + return -ENODEV; + + port->variant = of_device_get_match_data(dev); + + err = xilinx_cpm_pcie_parse_dt(port, bus->res); + if (err) { + dev_err(dev, "Parsing DT failed\n"); + goto err_parse_dt; + } + + xilinx_cpm_pcie_init_port(port); + + err = xilinx_cpm_setup_irq(port); + if (err) { + dev_err(dev, "Failed to set up interrupts\n"); + goto err_setup_irq; + } + + bridge->sysdata = port->cfg; + bridge->ops = (struct pci_ops *)&pci_generic_ecam_ops.pci_ops; + + err = pci_host_probe(bridge); + if (err < 0) + goto err_host_bridge; + + return 0; + +err_host_bridge: + xilinx_cpm_free_interrupts(port); +err_setup_irq: + pci_ecam_free(port->cfg); +err_parse_dt: + xilinx_cpm_free_irq_domains(port); + return err; +} + +static const struct xilinx_cpm_variant cpm_host = { + .version = CPM, +}; + +static const struct xilinx_cpm_variant cpm5_host = { + .version = CPM5, +}; + +static const struct of_device_id xilinx_cpm_pcie_of_match[] = { + { + .compatible = "xlnx,versal-cpm-host-1.00", + .data = &cpm_host, + }, + { + .compatible = "xlnx,versal-cpm5-host", + .data = &cpm5_host, + }, + {} +}; + +static struct platform_driver xilinx_cpm_pcie_driver = { + .driver = { + .name = "xilinx-cpm-pcie", + .of_match_table = xilinx_cpm_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = xilinx_cpm_pcie_probe, +}; + +builtin_platform_driver(xilinx_cpm_pcie_driver); diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c new file mode 100644 index 000000000..40d070e54 --- /dev/null +++ b/drivers/pci/controller/pcie-xilinx-nwl.c @@ -0,0 +1,849 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * PCIe host controller driver for NWL PCIe Bridge + * Based on pcie-xilinx.c, pci-tegra.c + * + * (C) Copyright 2014 - 2015, Xilinx, Inc. + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/of_irq.h> +#include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/platform_device.h> +#include <linux/irqchip/chained_irq.h> + +#include "../pci.h" + +/* Bridge core config registers */ +#define BRCFG_PCIE_RX0 0x00000000 +#define BRCFG_PCIE_RX1 0x00000004 +#define BRCFG_INTERRUPT 0x00000010 +#define BRCFG_PCIE_RX_MSG_FILTER 0x00000020 + +/* Egress - Bridge translation registers */ +#define E_BREG_CAPABILITIES 0x00000200 +#define E_BREG_CONTROL 0x00000208 +#define E_BREG_BASE_LO 0x00000210 +#define E_BREG_BASE_HI 0x00000214 +#define E_ECAM_CAPABILITIES 0x00000220 +#define E_ECAM_CONTROL 0x00000228 +#define E_ECAM_BASE_LO 0x00000230 +#define E_ECAM_BASE_HI 0x00000234 + +/* Ingress - address translations */ +#define I_MSII_CAPABILITIES 0x00000300 +#define I_MSII_CONTROL 0x00000308 +#define I_MSII_BASE_LO 0x00000310 +#define I_MSII_BASE_HI 0x00000314 + +#define I_ISUB_CONTROL 0x000003E8 +#define SET_ISUB_CONTROL BIT(0) +/* Rxed msg fifo - Interrupt status registers */ +#define MSGF_MISC_STATUS 0x00000400 +#define MSGF_MISC_MASK 0x00000404 +#define MSGF_LEG_STATUS 0x00000420 +#define MSGF_LEG_MASK 0x00000424 +#define MSGF_MSI_STATUS_LO 0x00000440 +#define MSGF_MSI_STATUS_HI 0x00000444 +#define MSGF_MSI_MASK_LO 0x00000448 +#define MSGF_MSI_MASK_HI 0x0000044C + +/* Msg filter mask bits */ +#define CFG_ENABLE_PM_MSG_FWD BIT(1) +#define CFG_ENABLE_INT_MSG_FWD BIT(2) +#define CFG_ENABLE_ERR_MSG_FWD BIT(3) +#define CFG_ENABLE_MSG_FILTER_MASK (CFG_ENABLE_PM_MSG_FWD | \ + CFG_ENABLE_INT_MSG_FWD | \ + CFG_ENABLE_ERR_MSG_FWD) + +/* Misc interrupt status mask bits */ +#define MSGF_MISC_SR_RXMSG_AVAIL BIT(0) +#define MSGF_MISC_SR_RXMSG_OVER BIT(1) +#define MSGF_MISC_SR_SLAVE_ERR BIT(4) +#define MSGF_MISC_SR_MASTER_ERR BIT(5) +#define MSGF_MISC_SR_I_ADDR_ERR BIT(6) +#define MSGF_MISC_SR_E_ADDR_ERR BIT(7) +#define MSGF_MISC_SR_FATAL_AER BIT(16) +#define MSGF_MISC_SR_NON_FATAL_AER BIT(17) +#define MSGF_MISC_SR_CORR_AER BIT(18) +#define MSGF_MISC_SR_UR_DETECT BIT(20) +#define MSGF_MISC_SR_NON_FATAL_DEV BIT(22) +#define MSGF_MISC_SR_FATAL_DEV BIT(23) +#define MSGF_MISC_SR_LINK_DOWN BIT(24) +#define MSGF_MSIC_SR_LINK_AUTO_BWIDTH BIT(25) +#define MSGF_MSIC_SR_LINK_BWIDTH BIT(26) + +#define MSGF_MISC_SR_MASKALL (MSGF_MISC_SR_RXMSG_AVAIL | \ + MSGF_MISC_SR_RXMSG_OVER | \ + MSGF_MISC_SR_SLAVE_ERR | \ + MSGF_MISC_SR_MASTER_ERR | \ + MSGF_MISC_SR_I_ADDR_ERR | \ + MSGF_MISC_SR_E_ADDR_ERR | \ + MSGF_MISC_SR_FATAL_AER | \ + MSGF_MISC_SR_NON_FATAL_AER | \ + MSGF_MISC_SR_CORR_AER | \ + MSGF_MISC_SR_UR_DETECT | \ + MSGF_MISC_SR_NON_FATAL_DEV | \ + MSGF_MISC_SR_FATAL_DEV | \ + MSGF_MISC_SR_LINK_DOWN | \ + MSGF_MSIC_SR_LINK_AUTO_BWIDTH | \ + MSGF_MSIC_SR_LINK_BWIDTH) + +/* Legacy interrupt status mask bits */ +#define MSGF_LEG_SR_INTA BIT(0) +#define MSGF_LEG_SR_INTB BIT(1) +#define MSGF_LEG_SR_INTC BIT(2) +#define MSGF_LEG_SR_INTD BIT(3) +#define MSGF_LEG_SR_MASKALL (MSGF_LEG_SR_INTA | MSGF_LEG_SR_INTB | \ + MSGF_LEG_SR_INTC | MSGF_LEG_SR_INTD) + +/* MSI interrupt status mask bits */ +#define MSGF_MSI_SR_LO_MASK GENMASK(31, 0) +#define MSGF_MSI_SR_HI_MASK GENMASK(31, 0) + +#define MSII_PRESENT BIT(0) +#define MSII_ENABLE BIT(0) +#define MSII_STATUS_ENABLE BIT(15) + +/* Bridge config interrupt mask */ +#define BRCFG_INTERRUPT_MASK BIT(0) +#define BREG_PRESENT BIT(0) +#define BREG_ENABLE BIT(0) +#define BREG_ENABLE_FORCE BIT(1) + +/* E_ECAM status mask bits */ +#define E_ECAM_PRESENT BIT(0) +#define E_ECAM_CR_ENABLE BIT(0) +#define E_ECAM_SIZE_LOC GENMASK(20, 16) +#define E_ECAM_SIZE_SHIFT 16 +#define NWL_ECAM_VALUE_DEFAULT 12 + +#define CFG_DMA_REG_BAR GENMASK(2, 0) +#define CFG_PCIE_CACHE GENMASK(7, 0) + +#define INT_PCI_MSI_NR (2 * 32) + +/* Readin the PS_LINKUP */ +#define PS_LINKUP_OFFSET 0x00000238 +#define PCIE_PHY_LINKUP_BIT BIT(0) +#define PHY_RDY_LINKUP_BIT BIT(1) + +/* Parameters for the waiting for link up routine */ +#define LINK_WAIT_MAX_RETRIES 10 +#define LINK_WAIT_USLEEP_MIN 90000 +#define LINK_WAIT_USLEEP_MAX 100000 + +struct nwl_msi { /* MSI information */ + struct irq_domain *msi_domain; + DECLARE_BITMAP(bitmap, INT_PCI_MSI_NR); + struct irq_domain *dev_domain; + struct mutex lock; /* protect bitmap variable */ + int irq_msi0; + int irq_msi1; +}; + +struct nwl_pcie { + struct device *dev; + void __iomem *breg_base; + void __iomem *pcireg_base; + void __iomem *ecam_base; + phys_addr_t phys_breg_base; /* Physical Bridge Register Base */ + phys_addr_t phys_pcie_reg_base; /* Physical PCIe Controller Base */ + phys_addr_t phys_ecam_base; /* Physical Configuration Base */ + u32 breg_size; + u32 pcie_reg_size; + u32 ecam_size; + int irq_intx; + int irq_misc; + u32 ecam_value; + u8 last_busno; + struct nwl_msi msi; + struct irq_domain *legacy_irq_domain; + struct clk *clk; + raw_spinlock_t leg_mask_lock; +}; + +static inline u32 nwl_bridge_readl(struct nwl_pcie *pcie, u32 off) +{ + return readl(pcie->breg_base + off); +} + +static inline void nwl_bridge_writel(struct nwl_pcie *pcie, u32 val, u32 off) +{ + writel(val, pcie->breg_base + off); +} + +static bool nwl_pcie_link_up(struct nwl_pcie *pcie) +{ + if (readl(pcie->pcireg_base + PS_LINKUP_OFFSET) & PCIE_PHY_LINKUP_BIT) + return true; + return false; +} + +static bool nwl_phy_link_up(struct nwl_pcie *pcie) +{ + if (readl(pcie->pcireg_base + PS_LINKUP_OFFSET) & PHY_RDY_LINKUP_BIT) + return true; + return false; +} + +static int nwl_wait_for_link(struct nwl_pcie *pcie) +{ + struct device *dev = pcie->dev; + int retries; + + /* check if the link is up or not */ + for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { + if (nwl_phy_link_up(pcie)) + return 0; + usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX); + } + + dev_err(dev, "PHY link never came up\n"); + return -ETIMEDOUT; +} + +static bool nwl_pcie_valid_device(struct pci_bus *bus, unsigned int devfn) +{ + struct nwl_pcie *pcie = bus->sysdata; + + /* Check link before accessing downstream ports */ + if (!pci_is_root_bus(bus)) { + if (!nwl_pcie_link_up(pcie)) + return false; + } else if (devfn > 0) + /* Only one device down on each root port */ + return false; + + return true; +} + +/** + * nwl_pcie_map_bus - Get configuration base + * + * @bus: Bus structure of current bus + * @devfn: Device/function + * @where: Offset from base + * + * Return: Base address of the configuration space needed to be + * accessed. + */ +static void __iomem *nwl_pcie_map_bus(struct pci_bus *bus, unsigned int devfn, + int where) +{ + struct nwl_pcie *pcie = bus->sysdata; + + if (!nwl_pcie_valid_device(bus, devfn)) + return NULL; + + return pcie->ecam_base + PCIE_ECAM_OFFSET(bus->number, devfn, where); +} + +/* PCIe operations */ +static struct pci_ops nwl_pcie_ops = { + .map_bus = nwl_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static irqreturn_t nwl_pcie_misc_handler(int irq, void *data) +{ + struct nwl_pcie *pcie = data; + struct device *dev = pcie->dev; + u32 misc_stat; + + /* Checking for misc interrupts */ + misc_stat = nwl_bridge_readl(pcie, MSGF_MISC_STATUS) & + MSGF_MISC_SR_MASKALL; + if (!misc_stat) + return IRQ_NONE; + + if (misc_stat & MSGF_MISC_SR_RXMSG_OVER) + dev_err(dev, "Received Message FIFO Overflow\n"); + + if (misc_stat & MSGF_MISC_SR_SLAVE_ERR) + dev_err(dev, "Slave error\n"); + + if (misc_stat & MSGF_MISC_SR_MASTER_ERR) + dev_err(dev, "Master error\n"); + + if (misc_stat & MSGF_MISC_SR_I_ADDR_ERR) + dev_err(dev, "In Misc Ingress address translation error\n"); + + if (misc_stat & MSGF_MISC_SR_E_ADDR_ERR) + dev_err(dev, "In Misc Egress address translation error\n"); + + if (misc_stat & MSGF_MISC_SR_FATAL_AER) + dev_err(dev, "Fatal Error in AER Capability\n"); + + if (misc_stat & MSGF_MISC_SR_NON_FATAL_AER) + dev_err(dev, "Non-Fatal Error in AER Capability\n"); + + if (misc_stat & MSGF_MISC_SR_CORR_AER) + dev_err(dev, "Correctable Error in AER Capability\n"); + + if (misc_stat & MSGF_MISC_SR_UR_DETECT) + dev_err(dev, "Unsupported request Detected\n"); + + if (misc_stat & MSGF_MISC_SR_NON_FATAL_DEV) + dev_err(dev, "Non-Fatal Error Detected\n"); + + if (misc_stat & MSGF_MISC_SR_FATAL_DEV) + dev_err(dev, "Fatal Error Detected\n"); + + if (misc_stat & MSGF_MSIC_SR_LINK_AUTO_BWIDTH) + dev_info(dev, "Link Autonomous Bandwidth Management Status bit set\n"); + + if (misc_stat & MSGF_MSIC_SR_LINK_BWIDTH) + dev_info(dev, "Link Bandwidth Management Status bit set\n"); + + /* Clear misc interrupt status */ + nwl_bridge_writel(pcie, misc_stat, MSGF_MISC_STATUS); + + return IRQ_HANDLED; +} + +static void nwl_pcie_leg_handler(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct nwl_pcie *pcie; + unsigned long status; + u32 bit; + + chained_irq_enter(chip, desc); + pcie = irq_desc_get_handler_data(desc); + + while ((status = nwl_bridge_readl(pcie, MSGF_LEG_STATUS) & + MSGF_LEG_SR_MASKALL) != 0) { + for_each_set_bit(bit, &status, PCI_NUM_INTX) + generic_handle_domain_irq(pcie->legacy_irq_domain, bit); + } + + chained_irq_exit(chip, desc); +} + +static void nwl_pcie_handle_msi_irq(struct nwl_pcie *pcie, u32 status_reg) +{ + struct nwl_msi *msi = &pcie->msi; + unsigned long status; + u32 bit; + + while ((status = nwl_bridge_readl(pcie, status_reg)) != 0) { + for_each_set_bit(bit, &status, 32) { + nwl_bridge_writel(pcie, 1 << bit, status_reg); + generic_handle_domain_irq(msi->dev_domain, bit); + } + } +} + +static void nwl_pcie_msi_handler_high(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct nwl_pcie *pcie = irq_desc_get_handler_data(desc); + + chained_irq_enter(chip, desc); + nwl_pcie_handle_msi_irq(pcie, MSGF_MSI_STATUS_HI); + chained_irq_exit(chip, desc); +} + +static void nwl_pcie_msi_handler_low(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct nwl_pcie *pcie = irq_desc_get_handler_data(desc); + + chained_irq_enter(chip, desc); + nwl_pcie_handle_msi_irq(pcie, MSGF_MSI_STATUS_LO); + chained_irq_exit(chip, desc); +} + +static void nwl_mask_leg_irq(struct irq_data *data) +{ + struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 mask; + u32 val; + + mask = 1 << (data->hwirq - 1); + raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags); + val = nwl_bridge_readl(pcie, MSGF_LEG_MASK); + nwl_bridge_writel(pcie, (val & (~mask)), MSGF_LEG_MASK); + raw_spin_unlock_irqrestore(&pcie->leg_mask_lock, flags); +} + +static void nwl_unmask_leg_irq(struct irq_data *data) +{ + struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data); + unsigned long flags; + u32 mask; + u32 val; + + mask = 1 << (data->hwirq - 1); + raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags); + val = nwl_bridge_readl(pcie, MSGF_LEG_MASK); + nwl_bridge_writel(pcie, (val | mask), MSGF_LEG_MASK); + raw_spin_unlock_irqrestore(&pcie->leg_mask_lock, flags); +} + +static struct irq_chip nwl_leg_irq_chip = { + .name = "nwl_pcie:legacy", + .irq_enable = nwl_unmask_leg_irq, + .irq_disable = nwl_mask_leg_irq, + .irq_mask = nwl_mask_leg_irq, + .irq_unmask = nwl_unmask_leg_irq, +}; + +static int nwl_legacy_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &nwl_leg_irq_chip, handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + irq_set_status_flags(irq, IRQ_LEVEL); + + return 0; +} + +static const struct irq_domain_ops legacy_domain_ops = { + .map = nwl_legacy_map, + .xlate = pci_irqd_intx_xlate, +}; + +#ifdef CONFIG_PCI_MSI +static struct irq_chip nwl_msi_irq_chip = { + .name = "nwl_pcie:msi", + .irq_enable = pci_msi_unmask_irq, + .irq_disable = pci_msi_mask_irq, + .irq_mask = pci_msi_mask_irq, + .irq_unmask = pci_msi_unmask_irq, +}; + +static struct msi_domain_info nwl_msi_domain_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_MULTI_PCI_MSI), + .chip = &nwl_msi_irq_chip, +}; +#endif + +static void nwl_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data); + phys_addr_t msi_addr = pcie->phys_pcie_reg_base; + + msg->address_lo = lower_32_bits(msi_addr); + msg->address_hi = upper_32_bits(msi_addr); + msg->data = data->hwirq; +} + +static int nwl_msi_set_affinity(struct irq_data *irq_data, + const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static struct irq_chip nwl_irq_chip = { + .name = "Xilinx MSI", + .irq_compose_msi_msg = nwl_compose_msi_msg, + .irq_set_affinity = nwl_msi_set_affinity, +}; + +static int nwl_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct nwl_pcie *pcie = domain->host_data; + struct nwl_msi *msi = &pcie->msi; + int bit; + int i; + + mutex_lock(&msi->lock); + bit = bitmap_find_free_region(msi->bitmap, INT_PCI_MSI_NR, + get_count_order(nr_irqs)); + if (bit < 0) { + mutex_unlock(&msi->lock); + return -ENOSPC; + } + + for (i = 0; i < nr_irqs; i++) { + irq_domain_set_info(domain, virq + i, bit + i, &nwl_irq_chip, + domain->host_data, handle_simple_irq, + NULL, NULL); + } + mutex_unlock(&msi->lock); + return 0; +} + +static void nwl_irq_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *data = irq_domain_get_irq_data(domain, virq); + struct nwl_pcie *pcie = irq_data_get_irq_chip_data(data); + struct nwl_msi *msi = &pcie->msi; + + mutex_lock(&msi->lock); + bitmap_release_region(msi->bitmap, data->hwirq, + get_count_order(nr_irqs)); + mutex_unlock(&msi->lock); +} + +static const struct irq_domain_ops dev_msi_domain_ops = { + .alloc = nwl_irq_domain_alloc, + .free = nwl_irq_domain_free, +}; + +static int nwl_pcie_init_msi_irq_domain(struct nwl_pcie *pcie) +{ +#ifdef CONFIG_PCI_MSI + struct device *dev = pcie->dev; + struct fwnode_handle *fwnode = of_node_to_fwnode(dev->of_node); + struct nwl_msi *msi = &pcie->msi; + + msi->dev_domain = irq_domain_add_linear(NULL, INT_PCI_MSI_NR, + &dev_msi_domain_ops, pcie); + if (!msi->dev_domain) { + dev_err(dev, "failed to create dev IRQ domain\n"); + return -ENOMEM; + } + msi->msi_domain = pci_msi_create_irq_domain(fwnode, + &nwl_msi_domain_info, + msi->dev_domain); + if (!msi->msi_domain) { + dev_err(dev, "failed to create msi IRQ domain\n"); + irq_domain_remove(msi->dev_domain); + return -ENOMEM; + } +#endif + return 0; +} + +static int nwl_pcie_init_irq_domain(struct nwl_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct device_node *node = dev->of_node; + struct device_node *legacy_intc_node; + + legacy_intc_node = of_get_next_child(node, NULL); + if (!legacy_intc_node) { + dev_err(dev, "No legacy intc node found\n"); + return -EINVAL; + } + + pcie->legacy_irq_domain = irq_domain_add_linear(legacy_intc_node, + PCI_NUM_INTX, + &legacy_domain_ops, + pcie); + of_node_put(legacy_intc_node); + if (!pcie->legacy_irq_domain) { + dev_err(dev, "failed to create IRQ domain\n"); + return -ENOMEM; + } + + raw_spin_lock_init(&pcie->leg_mask_lock); + nwl_pcie_init_msi_irq_domain(pcie); + return 0; +} + +static int nwl_pcie_enable_msi(struct nwl_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + struct nwl_msi *msi = &pcie->msi; + unsigned long base; + int ret; + + mutex_init(&msi->lock); + + /* Get msi_1 IRQ number */ + msi->irq_msi1 = platform_get_irq_byname(pdev, "msi1"); + if (msi->irq_msi1 < 0) + return -EINVAL; + + irq_set_chained_handler_and_data(msi->irq_msi1, + nwl_pcie_msi_handler_high, pcie); + + /* Get msi_0 IRQ number */ + msi->irq_msi0 = platform_get_irq_byname(pdev, "msi0"); + if (msi->irq_msi0 < 0) + return -EINVAL; + + irq_set_chained_handler_and_data(msi->irq_msi0, + nwl_pcie_msi_handler_low, pcie); + + /* Check for msii_present bit */ + ret = nwl_bridge_readl(pcie, I_MSII_CAPABILITIES) & MSII_PRESENT; + if (!ret) { + dev_err(dev, "MSI not present\n"); + return -EIO; + } + + /* Enable MSII */ + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, I_MSII_CONTROL) | + MSII_ENABLE, I_MSII_CONTROL); + + /* Enable MSII status */ + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, I_MSII_CONTROL) | + MSII_STATUS_ENABLE, I_MSII_CONTROL); + + /* setup AFI/FPCI range */ + base = pcie->phys_pcie_reg_base; + nwl_bridge_writel(pcie, lower_32_bits(base), I_MSII_BASE_LO); + nwl_bridge_writel(pcie, upper_32_bits(base), I_MSII_BASE_HI); + + /* + * For high range MSI interrupts: disable, clear any pending, + * and enable + */ + nwl_bridge_writel(pcie, 0, MSGF_MSI_MASK_HI); + + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, MSGF_MSI_STATUS_HI) & + MSGF_MSI_SR_HI_MASK, MSGF_MSI_STATUS_HI); + + nwl_bridge_writel(pcie, MSGF_MSI_SR_HI_MASK, MSGF_MSI_MASK_HI); + + /* + * For low range MSI interrupts: disable, clear any pending, + * and enable + */ + nwl_bridge_writel(pcie, 0, MSGF_MSI_MASK_LO); + + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, MSGF_MSI_STATUS_LO) & + MSGF_MSI_SR_LO_MASK, MSGF_MSI_STATUS_LO); + + nwl_bridge_writel(pcie, MSGF_MSI_SR_LO_MASK, MSGF_MSI_MASK_LO); + + return 0; +} + +static int nwl_pcie_bridge_init(struct nwl_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct platform_device *pdev = to_platform_device(dev); + u32 breg_val, ecam_val, first_busno = 0; + int err; + + breg_val = nwl_bridge_readl(pcie, E_BREG_CAPABILITIES) & BREG_PRESENT; + if (!breg_val) { + dev_err(dev, "BREG is not present\n"); + return breg_val; + } + + /* Write bridge_off to breg base */ + nwl_bridge_writel(pcie, lower_32_bits(pcie->phys_breg_base), + E_BREG_BASE_LO); + nwl_bridge_writel(pcie, upper_32_bits(pcie->phys_breg_base), + E_BREG_BASE_HI); + + /* Enable BREG */ + nwl_bridge_writel(pcie, ~BREG_ENABLE_FORCE & BREG_ENABLE, + E_BREG_CONTROL); + + /* Disable DMA channel registers */ + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, BRCFG_PCIE_RX0) | + CFG_DMA_REG_BAR, BRCFG_PCIE_RX0); + + /* Enable Ingress subtractive decode translation */ + nwl_bridge_writel(pcie, SET_ISUB_CONTROL, I_ISUB_CONTROL); + + /* Enable msg filtering details */ + nwl_bridge_writel(pcie, CFG_ENABLE_MSG_FILTER_MASK, + BRCFG_PCIE_RX_MSG_FILTER); + + /* This routes the PCIe DMA traffic to go through CCI path */ + if (of_dma_is_coherent(dev->of_node)) + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, BRCFG_PCIE_RX1) | + CFG_PCIE_CACHE, BRCFG_PCIE_RX1); + + err = nwl_wait_for_link(pcie); + if (err) + return err; + + ecam_val = nwl_bridge_readl(pcie, E_ECAM_CAPABILITIES) & E_ECAM_PRESENT; + if (!ecam_val) { + dev_err(dev, "ECAM is not present\n"); + return ecam_val; + } + + /* Enable ECAM */ + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, E_ECAM_CONTROL) | + E_ECAM_CR_ENABLE, E_ECAM_CONTROL); + + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, E_ECAM_CONTROL) | + (pcie->ecam_value << E_ECAM_SIZE_SHIFT), + E_ECAM_CONTROL); + + nwl_bridge_writel(pcie, lower_32_bits(pcie->phys_ecam_base), + E_ECAM_BASE_LO); + nwl_bridge_writel(pcie, upper_32_bits(pcie->phys_ecam_base), + E_ECAM_BASE_HI); + + /* Get bus range */ + ecam_val = nwl_bridge_readl(pcie, E_ECAM_CONTROL); + pcie->last_busno = (ecam_val & E_ECAM_SIZE_LOC) >> E_ECAM_SIZE_SHIFT; + /* Write primary, secondary and subordinate bus numbers */ + ecam_val = first_busno; + ecam_val |= (first_busno + 1) << 8; + ecam_val |= (pcie->last_busno << E_ECAM_SIZE_SHIFT); + writel(ecam_val, (pcie->ecam_base + PCI_PRIMARY_BUS)); + + if (nwl_pcie_link_up(pcie)) + dev_info(dev, "Link is UP\n"); + else + dev_info(dev, "Link is DOWN\n"); + + /* Get misc IRQ number */ + pcie->irq_misc = platform_get_irq_byname(pdev, "misc"); + if (pcie->irq_misc < 0) + return -EINVAL; + + err = devm_request_irq(dev, pcie->irq_misc, + nwl_pcie_misc_handler, IRQF_SHARED, + "nwl_pcie:misc", pcie); + if (err) { + dev_err(dev, "fail to register misc IRQ#%d\n", + pcie->irq_misc); + return err; + } + + /* Disable all misc interrupts */ + nwl_bridge_writel(pcie, (u32)~MSGF_MISC_SR_MASKALL, MSGF_MISC_MASK); + + /* Clear pending misc interrupts */ + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, MSGF_MISC_STATUS) & + MSGF_MISC_SR_MASKALL, MSGF_MISC_STATUS); + + /* Enable all misc interrupts */ + nwl_bridge_writel(pcie, MSGF_MISC_SR_MASKALL, MSGF_MISC_MASK); + + + /* Disable all legacy interrupts */ + nwl_bridge_writel(pcie, (u32)~MSGF_LEG_SR_MASKALL, MSGF_LEG_MASK); + + /* Clear pending legacy interrupts */ + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, MSGF_LEG_STATUS) & + MSGF_LEG_SR_MASKALL, MSGF_LEG_STATUS); + + /* Enable all legacy interrupts */ + nwl_bridge_writel(pcie, MSGF_LEG_SR_MASKALL, MSGF_LEG_MASK); + + /* Enable the bridge config interrupt */ + nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, BRCFG_INTERRUPT) | + BRCFG_INTERRUPT_MASK, BRCFG_INTERRUPT); + + return 0; +} + +static int nwl_pcie_parse_dt(struct nwl_pcie *pcie, + struct platform_device *pdev) +{ + struct device *dev = pcie->dev; + struct resource *res; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "breg"); + pcie->breg_base = devm_ioremap_resource(dev, res); + if (IS_ERR(pcie->breg_base)) + return PTR_ERR(pcie->breg_base); + pcie->phys_breg_base = res->start; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pcireg"); + pcie->pcireg_base = devm_ioremap_resource(dev, res); + if (IS_ERR(pcie->pcireg_base)) + return PTR_ERR(pcie->pcireg_base); + pcie->phys_pcie_reg_base = res->start; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg"); + pcie->ecam_base = devm_pci_remap_cfg_resource(dev, res); + if (IS_ERR(pcie->ecam_base)) + return PTR_ERR(pcie->ecam_base); + pcie->phys_ecam_base = res->start; + + /* Get intx IRQ number */ + pcie->irq_intx = platform_get_irq_byname(pdev, "intx"); + if (pcie->irq_intx < 0) + return pcie->irq_intx; + + irq_set_chained_handler_and_data(pcie->irq_intx, + nwl_pcie_leg_handler, pcie); + + return 0; +} + +static const struct of_device_id nwl_pcie_of_match[] = { + { .compatible = "xlnx,nwl-pcie-2.11", }, + {} +}; + +static int nwl_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct nwl_pcie *pcie; + struct pci_host_bridge *bridge; + int err; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENODEV; + + pcie = pci_host_bridge_priv(bridge); + + pcie->dev = dev; + pcie->ecam_value = NWL_ECAM_VALUE_DEFAULT; + + err = nwl_pcie_parse_dt(pcie, pdev); + if (err) { + dev_err(dev, "Parsing DT failed\n"); + return err; + } + + pcie->clk = devm_clk_get(dev, NULL); + if (IS_ERR(pcie->clk)) + return PTR_ERR(pcie->clk); + + err = clk_prepare_enable(pcie->clk); + if (err) { + dev_err(dev, "can't enable PCIe ref clock\n"); + return err; + } + + err = nwl_pcie_bridge_init(pcie); + if (err) { + dev_err(dev, "HW Initialization failed\n"); + return err; + } + + err = nwl_pcie_init_irq_domain(pcie); + if (err) { + dev_err(dev, "Failed creating IRQ Domain\n"); + return err; + } + + bridge->sysdata = pcie; + bridge->ops = &nwl_pcie_ops; + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + err = nwl_pcie_enable_msi(pcie); + if (err < 0) { + dev_err(dev, "failed to enable MSI support: %d\n", err); + return err; + } + } + + return pci_host_probe(bridge); +} + +static struct platform_driver nwl_pcie_driver = { + .driver = { + .name = "nwl-pcie", + .suppress_bind_attrs = true, + .of_match_table = nwl_pcie_of_match, + }, + .probe = nwl_pcie_probe, +}; +builtin_platform_driver(nwl_pcie_driver); diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c new file mode 100644 index 000000000..cb6e9f7b0 --- /dev/null +++ b/drivers/pci/controller/pcie-xilinx.c @@ -0,0 +1,621 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * PCIe host controller driver for Xilinx AXI PCIe Bridge + * + * Copyright (c) 2012 - 2014 Xilinx, Inc. + * + * Based on the Tegra PCIe driver + * + * Bits taken from Synopsys DesignWare Host controller driver and + * ARM PCI Host generic driver. + */ + +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/msi.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/of_platform.h> +#include <linux/of_irq.h> +#include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/platform_device.h> + +#include "../pci.h" + +/* Register definitions */ +#define XILINX_PCIE_REG_BIR 0x00000130 +#define XILINX_PCIE_REG_IDR 0x00000138 +#define XILINX_PCIE_REG_IMR 0x0000013c +#define XILINX_PCIE_REG_PSCR 0x00000144 +#define XILINX_PCIE_REG_RPSC 0x00000148 +#define XILINX_PCIE_REG_MSIBASE1 0x0000014c +#define XILINX_PCIE_REG_MSIBASE2 0x00000150 +#define XILINX_PCIE_REG_RPEFR 0x00000154 +#define XILINX_PCIE_REG_RPIFR1 0x00000158 +#define XILINX_PCIE_REG_RPIFR2 0x0000015c + +/* Interrupt registers definitions */ +#define XILINX_PCIE_INTR_LINK_DOWN BIT(0) +#define XILINX_PCIE_INTR_ECRC_ERR BIT(1) +#define XILINX_PCIE_INTR_STR_ERR BIT(2) +#define XILINX_PCIE_INTR_HOT_RESET BIT(3) +#define XILINX_PCIE_INTR_CFG_TIMEOUT BIT(8) +#define XILINX_PCIE_INTR_CORRECTABLE BIT(9) +#define XILINX_PCIE_INTR_NONFATAL BIT(10) +#define XILINX_PCIE_INTR_FATAL BIT(11) +#define XILINX_PCIE_INTR_INTX BIT(16) +#define XILINX_PCIE_INTR_MSI BIT(17) +#define XILINX_PCIE_INTR_SLV_UNSUPP BIT(20) +#define XILINX_PCIE_INTR_SLV_UNEXP BIT(21) +#define XILINX_PCIE_INTR_SLV_COMPL BIT(22) +#define XILINX_PCIE_INTR_SLV_ERRP BIT(23) +#define XILINX_PCIE_INTR_SLV_CMPABT BIT(24) +#define XILINX_PCIE_INTR_SLV_ILLBUR BIT(25) +#define XILINX_PCIE_INTR_MST_DECERR BIT(26) +#define XILINX_PCIE_INTR_MST_SLVERR BIT(27) +#define XILINX_PCIE_INTR_MST_ERRP BIT(28) +#define XILINX_PCIE_IMR_ALL_MASK 0x1FF30FED +#define XILINX_PCIE_IMR_ENABLE_MASK 0x1FF30F0D +#define XILINX_PCIE_IDR_ALL_MASK 0xFFFFFFFF + +/* Root Port Error FIFO Read Register definitions */ +#define XILINX_PCIE_RPEFR_ERR_VALID BIT(18) +#define XILINX_PCIE_RPEFR_REQ_ID GENMASK(15, 0) +#define XILINX_PCIE_RPEFR_ALL_MASK 0xFFFFFFFF + +/* Root Port Interrupt FIFO Read Register 1 definitions */ +#define XILINX_PCIE_RPIFR1_INTR_VALID BIT(31) +#define XILINX_PCIE_RPIFR1_MSI_INTR BIT(30) +#define XILINX_PCIE_RPIFR1_INTR_MASK GENMASK(28, 27) +#define XILINX_PCIE_RPIFR1_ALL_MASK 0xFFFFFFFF +#define XILINX_PCIE_RPIFR1_INTR_SHIFT 27 + +/* Bridge Info Register definitions */ +#define XILINX_PCIE_BIR_ECAM_SZ_MASK GENMASK(18, 16) +#define XILINX_PCIE_BIR_ECAM_SZ_SHIFT 16 + +/* Root Port Interrupt FIFO Read Register 2 definitions */ +#define XILINX_PCIE_RPIFR2_MSG_DATA GENMASK(15, 0) + +/* Root Port Status/control Register definitions */ +#define XILINX_PCIE_REG_RPSC_BEN BIT(0) + +/* Phy Status/Control Register definitions */ +#define XILINX_PCIE_REG_PSCR_LNKUP BIT(11) + +/* Number of MSI IRQs */ +#define XILINX_NUM_MSI_IRQS 128 + +/** + * struct xilinx_pcie - PCIe port information + * @dev: Device pointer + * @reg_base: IO Mapped Register Base + * @msi_map: Bitmap of allocated MSIs + * @map_lock: Mutex protecting the MSI allocation + * @msi_domain: MSI IRQ domain pointer + * @leg_domain: Legacy IRQ domain pointer + * @resources: Bus Resources + */ +struct xilinx_pcie { + struct device *dev; + void __iomem *reg_base; + unsigned long msi_map[BITS_TO_LONGS(XILINX_NUM_MSI_IRQS)]; + struct mutex map_lock; + struct irq_domain *msi_domain; + struct irq_domain *leg_domain; + struct list_head resources; +}; + +static inline u32 pcie_read(struct xilinx_pcie *pcie, u32 reg) +{ + return readl(pcie->reg_base + reg); +} + +static inline void pcie_write(struct xilinx_pcie *pcie, u32 val, u32 reg) +{ + writel(val, pcie->reg_base + reg); +} + +static inline bool xilinx_pcie_link_up(struct xilinx_pcie *pcie) +{ + return (pcie_read(pcie, XILINX_PCIE_REG_PSCR) & + XILINX_PCIE_REG_PSCR_LNKUP) ? 1 : 0; +} + +/** + * xilinx_pcie_clear_err_interrupts - Clear Error Interrupts + * @pcie: PCIe port information + */ +static void xilinx_pcie_clear_err_interrupts(struct xilinx_pcie *pcie) +{ + struct device *dev = pcie->dev; + unsigned long val = pcie_read(pcie, XILINX_PCIE_REG_RPEFR); + + if (val & XILINX_PCIE_RPEFR_ERR_VALID) { + dev_dbg(dev, "Requester ID %lu\n", + val & XILINX_PCIE_RPEFR_REQ_ID); + pcie_write(pcie, XILINX_PCIE_RPEFR_ALL_MASK, + XILINX_PCIE_REG_RPEFR); + } +} + +/** + * xilinx_pcie_valid_device - Check if a valid device is present on bus + * @bus: PCI Bus structure + * @devfn: device/function + * + * Return: 'true' on success and 'false' if invalid device is found + */ +static bool xilinx_pcie_valid_device(struct pci_bus *bus, unsigned int devfn) +{ + struct xilinx_pcie *pcie = bus->sysdata; + + /* Check if link is up when trying to access downstream pcie ports */ + if (!pci_is_root_bus(bus)) { + if (!xilinx_pcie_link_up(pcie)) + return false; + } else if (devfn > 0) { + /* Only one device down on each root port */ + return false; + } + return true; +} + +/** + * xilinx_pcie_map_bus - Get configuration base + * @bus: PCI Bus structure + * @devfn: Device/function + * @where: Offset from base + * + * Return: Base address of the configuration space needed to be + * accessed. + */ +static void __iomem *xilinx_pcie_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct xilinx_pcie *pcie = bus->sysdata; + + if (!xilinx_pcie_valid_device(bus, devfn)) + return NULL; + + return pcie->reg_base + PCIE_ECAM_OFFSET(bus->number, devfn, where); +} + +/* PCIe operations */ +static struct pci_ops xilinx_pcie_ops = { + .map_bus = xilinx_pcie_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +/* MSI functions */ + +static void xilinx_msi_top_irq_ack(struct irq_data *d) +{ + /* + * xilinx_pcie_intr_handler() will have performed the Ack. + * Eventually, this should be fixed and the Ack be moved in + * the respective callbacks for INTx and MSI. + */ +} + +static struct irq_chip xilinx_msi_top_chip = { + .name = "PCIe MSI", + .irq_ack = xilinx_msi_top_irq_ack, +}; + +static int xilinx_msi_set_affinity(struct irq_data *d, const struct cpumask *mask, bool force) +{ + return -EINVAL; +} + +static void xilinx_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct xilinx_pcie *pcie = irq_data_get_irq_chip_data(data); + phys_addr_t pa = ALIGN_DOWN(virt_to_phys(pcie), SZ_4K); + + msg->address_lo = lower_32_bits(pa); + msg->address_hi = upper_32_bits(pa); + msg->data = data->hwirq; +} + +static struct irq_chip xilinx_msi_bottom_chip = { + .name = "Xilinx MSI", + .irq_set_affinity = xilinx_msi_set_affinity, + .irq_compose_msi_msg = xilinx_compose_msi_msg, +}; + +static int xilinx_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) +{ + struct xilinx_pcie *pcie = domain->host_data; + int hwirq, i; + + mutex_lock(&pcie->map_lock); + + hwirq = bitmap_find_free_region(pcie->msi_map, XILINX_NUM_MSI_IRQS, order_base_2(nr_irqs)); + + mutex_unlock(&pcie->map_lock); + + if (hwirq < 0) + return -ENOSPC; + + for (i = 0; i < nr_irqs; i++) + irq_domain_set_info(domain, virq + i, hwirq + i, + &xilinx_msi_bottom_chip, domain->host_data, + handle_edge_irq, NULL, NULL); + + return 0; +} + +static void xilinx_msi_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) +{ + struct irq_data *d = irq_domain_get_irq_data(domain, virq); + struct xilinx_pcie *pcie = domain->host_data; + + mutex_lock(&pcie->map_lock); + + bitmap_release_region(pcie->msi_map, d->hwirq, order_base_2(nr_irqs)); + + mutex_unlock(&pcie->map_lock); +} + +static const struct irq_domain_ops xilinx_msi_domain_ops = { + .alloc = xilinx_msi_domain_alloc, + .free = xilinx_msi_domain_free, +}; + +static struct msi_domain_info xilinx_msi_info = { + .flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS), + .chip = &xilinx_msi_top_chip, +}; + +static int xilinx_allocate_msi_domains(struct xilinx_pcie *pcie) +{ + struct fwnode_handle *fwnode = dev_fwnode(pcie->dev); + struct irq_domain *parent; + + parent = irq_domain_create_linear(fwnode, XILINX_NUM_MSI_IRQS, + &xilinx_msi_domain_ops, pcie); + if (!parent) { + dev_err(pcie->dev, "failed to create IRQ domain\n"); + return -ENOMEM; + } + irq_domain_update_bus_token(parent, DOMAIN_BUS_NEXUS); + + pcie->msi_domain = pci_msi_create_irq_domain(fwnode, &xilinx_msi_info, parent); + if (!pcie->msi_domain) { + dev_err(pcie->dev, "failed to create MSI domain\n"); + irq_domain_remove(parent); + return -ENOMEM; + } + + return 0; +} + +static void xilinx_free_msi_domains(struct xilinx_pcie *pcie) +{ + struct irq_domain *parent = pcie->msi_domain->parent; + + irq_domain_remove(pcie->msi_domain); + irq_domain_remove(parent); +} + +/* INTx Functions */ + +/** + * xilinx_pcie_intx_map - Set the handler for the INTx and mark IRQ as valid + * @domain: IRQ domain + * @irq: Virtual IRQ number + * @hwirq: HW interrupt number + * + * Return: Always returns 0. + */ +static int xilinx_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &dummy_irq_chip, handle_simple_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +/* INTx IRQ Domain operations */ +static const struct irq_domain_ops intx_domain_ops = { + .map = xilinx_pcie_intx_map, + .xlate = pci_irqd_intx_xlate, +}; + +/* PCIe HW Functions */ + +/** + * xilinx_pcie_intr_handler - Interrupt Service Handler + * @irq: IRQ number + * @data: PCIe port information + * + * Return: IRQ_HANDLED on success and IRQ_NONE on failure + */ +static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data) +{ + struct xilinx_pcie *pcie = (struct xilinx_pcie *)data; + struct device *dev = pcie->dev; + u32 val, mask, status; + + /* Read interrupt decode and mask registers */ + val = pcie_read(pcie, XILINX_PCIE_REG_IDR); + mask = pcie_read(pcie, XILINX_PCIE_REG_IMR); + + status = val & mask; + if (!status) + return IRQ_NONE; + + if (status & XILINX_PCIE_INTR_LINK_DOWN) + dev_warn(dev, "Link Down\n"); + + if (status & XILINX_PCIE_INTR_ECRC_ERR) + dev_warn(dev, "ECRC failed\n"); + + if (status & XILINX_PCIE_INTR_STR_ERR) + dev_warn(dev, "Streaming error\n"); + + if (status & XILINX_PCIE_INTR_HOT_RESET) + dev_info(dev, "Hot reset\n"); + + if (status & XILINX_PCIE_INTR_CFG_TIMEOUT) + dev_warn(dev, "ECAM access timeout\n"); + + if (status & XILINX_PCIE_INTR_CORRECTABLE) { + dev_warn(dev, "Correctable error message\n"); + xilinx_pcie_clear_err_interrupts(pcie); + } + + if (status & XILINX_PCIE_INTR_NONFATAL) { + dev_warn(dev, "Non fatal error message\n"); + xilinx_pcie_clear_err_interrupts(pcie); + } + + if (status & XILINX_PCIE_INTR_FATAL) { + dev_warn(dev, "Fatal error message\n"); + xilinx_pcie_clear_err_interrupts(pcie); + } + + if (status & (XILINX_PCIE_INTR_INTX | XILINX_PCIE_INTR_MSI)) { + struct irq_domain *domain; + + val = pcie_read(pcie, XILINX_PCIE_REG_RPIFR1); + + /* Check whether interrupt valid */ + if (!(val & XILINX_PCIE_RPIFR1_INTR_VALID)) { + dev_warn(dev, "RP Intr FIFO1 read error\n"); + goto error; + } + + /* Decode the IRQ number */ + if (val & XILINX_PCIE_RPIFR1_MSI_INTR) { + val = pcie_read(pcie, XILINX_PCIE_REG_RPIFR2) & + XILINX_PCIE_RPIFR2_MSG_DATA; + domain = pcie->msi_domain->parent; + } else { + val = (val & XILINX_PCIE_RPIFR1_INTR_MASK) >> + XILINX_PCIE_RPIFR1_INTR_SHIFT; + domain = pcie->leg_domain; + } + + /* Clear interrupt FIFO register 1 */ + pcie_write(pcie, XILINX_PCIE_RPIFR1_ALL_MASK, + XILINX_PCIE_REG_RPIFR1); + + generic_handle_domain_irq(domain, val); + } + + if (status & XILINX_PCIE_INTR_SLV_UNSUPP) + dev_warn(dev, "Slave unsupported request\n"); + + if (status & XILINX_PCIE_INTR_SLV_UNEXP) + dev_warn(dev, "Slave unexpected completion\n"); + + if (status & XILINX_PCIE_INTR_SLV_COMPL) + dev_warn(dev, "Slave completion timeout\n"); + + if (status & XILINX_PCIE_INTR_SLV_ERRP) + dev_warn(dev, "Slave Error Poison\n"); + + if (status & XILINX_PCIE_INTR_SLV_CMPABT) + dev_warn(dev, "Slave Completer Abort\n"); + + if (status & XILINX_PCIE_INTR_SLV_ILLBUR) + dev_warn(dev, "Slave Illegal Burst\n"); + + if (status & XILINX_PCIE_INTR_MST_DECERR) + dev_warn(dev, "Master decode error\n"); + + if (status & XILINX_PCIE_INTR_MST_SLVERR) + dev_warn(dev, "Master slave error\n"); + + if (status & XILINX_PCIE_INTR_MST_ERRP) + dev_warn(dev, "Master error poison\n"); + +error: + /* Clear the Interrupt Decode register */ + pcie_write(pcie, status, XILINX_PCIE_REG_IDR); + + return IRQ_HANDLED; +} + +/** + * xilinx_pcie_init_irq_domain - Initialize IRQ domain + * @pcie: PCIe port information + * + * Return: '0' on success and error value on failure + */ +static int xilinx_pcie_init_irq_domain(struct xilinx_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct device_node *pcie_intc_node; + int ret; + + /* Setup INTx */ + pcie_intc_node = of_get_next_child(dev->of_node, NULL); + if (!pcie_intc_node) { + dev_err(dev, "No PCIe Intc node found\n"); + return -ENODEV; + } + + pcie->leg_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, + &intx_domain_ops, + pcie); + of_node_put(pcie_intc_node); + if (!pcie->leg_domain) { + dev_err(dev, "Failed to get a INTx IRQ domain\n"); + return -ENODEV; + } + + /* Setup MSI */ + if (IS_ENABLED(CONFIG_PCI_MSI)) { + phys_addr_t pa = ALIGN_DOWN(virt_to_phys(pcie), SZ_4K); + + ret = xilinx_allocate_msi_domains(pcie); + if (ret) + return ret; + + pcie_write(pcie, upper_32_bits(pa), XILINX_PCIE_REG_MSIBASE1); + pcie_write(pcie, lower_32_bits(pa), XILINX_PCIE_REG_MSIBASE2); + } + + return 0; +} + +/** + * xilinx_pcie_init_port - Initialize hardware + * @pcie: PCIe port information + */ +static void xilinx_pcie_init_port(struct xilinx_pcie *pcie) +{ + struct device *dev = pcie->dev; + + if (xilinx_pcie_link_up(pcie)) + dev_info(dev, "PCIe Link is UP\n"); + else + dev_info(dev, "PCIe Link is DOWN\n"); + + /* Disable all interrupts */ + pcie_write(pcie, ~XILINX_PCIE_IDR_ALL_MASK, + XILINX_PCIE_REG_IMR); + + /* Clear pending interrupts */ + pcie_write(pcie, pcie_read(pcie, XILINX_PCIE_REG_IDR) & + XILINX_PCIE_IMR_ALL_MASK, + XILINX_PCIE_REG_IDR); + + /* Enable all interrupts we handle */ + pcie_write(pcie, XILINX_PCIE_IMR_ENABLE_MASK, XILINX_PCIE_REG_IMR); + + /* Enable the Bridge enable bit */ + pcie_write(pcie, pcie_read(pcie, XILINX_PCIE_REG_RPSC) | + XILINX_PCIE_REG_RPSC_BEN, + XILINX_PCIE_REG_RPSC); +} + +/** + * xilinx_pcie_parse_dt - Parse Device tree + * @pcie: PCIe port information + * + * Return: '0' on success and error value on failure + */ +static int xilinx_pcie_parse_dt(struct xilinx_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct device_node *node = dev->of_node; + struct resource regs; + unsigned int irq; + int err; + + err = of_address_to_resource(node, 0, ®s); + if (err) { + dev_err(dev, "missing \"reg\" property\n"); + return err; + } + + pcie->reg_base = devm_pci_remap_cfg_resource(dev, ®s); + if (IS_ERR(pcie->reg_base)) + return PTR_ERR(pcie->reg_base); + + irq = irq_of_parse_and_map(node, 0); + err = devm_request_irq(dev, irq, xilinx_pcie_intr_handler, + IRQF_SHARED | IRQF_NO_THREAD, + "xilinx-pcie", pcie); + if (err) { + dev_err(dev, "unable to request irq %d\n", irq); + return err; + } + + return 0; +} + +/** + * xilinx_pcie_probe - Probe function + * @pdev: Platform device pointer + * + * Return: '0' on success and error value on failure + */ +static int xilinx_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct xilinx_pcie *pcie; + struct pci_host_bridge *bridge; + int err; + + if (!dev->of_node) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENODEV; + + pcie = pci_host_bridge_priv(bridge); + mutex_init(&pcie->map_lock); + pcie->dev = dev; + + err = xilinx_pcie_parse_dt(pcie); + if (err) { + dev_err(dev, "Parsing DT failed\n"); + return err; + } + + xilinx_pcie_init_port(pcie); + + err = xilinx_pcie_init_irq_domain(pcie); + if (err) { + dev_err(dev, "Failed creating IRQ Domain\n"); + return err; + } + + bridge->sysdata = pcie; + bridge->ops = &xilinx_pcie_ops; + + err = pci_host_probe(bridge); + if (err) + xilinx_free_msi_domains(pcie); + + return err; +} + +static const struct of_device_id xilinx_pcie_of_match[] = { + { .compatible = "xlnx,axi-pcie-host-1.00.a", }, + {} +}; + +static struct platform_driver xilinx_pcie_driver = { + .driver = { + .name = "xilinx-pcie", + .of_match_table = xilinx_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = xilinx_pcie_probe, +}; +builtin_platform_driver(xilinx_pcie_driver); diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c new file mode 100644 index 000000000..5c35884c2 --- /dev/null +++ b/drivers/pci/controller/vmd.c @@ -0,0 +1,1090 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Volume Management Device driver + * Copyright (c) 2015, Intel Corporation. + */ + +#include <linux/device.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/pci.h> +#include <linux/pci-acpi.h> +#include <linux/pci-ecam.h> +#include <linux/srcu.h> +#include <linux/rculist.h> +#include <linux/rcupdate.h> + +#include <asm/irqdomain.h> + +#define VMD_CFGBAR 0 +#define VMD_MEMBAR1 2 +#define VMD_MEMBAR2 4 + +#define PCI_REG_VMCAP 0x40 +#define BUS_RESTRICT_CAP(vmcap) (vmcap & 0x1) +#define PCI_REG_VMCONFIG 0x44 +#define BUS_RESTRICT_CFG(vmcfg) ((vmcfg >> 8) & 0x3) +#define VMCONFIG_MSI_REMAP 0x2 +#define PCI_REG_VMLOCK 0x70 +#define MB2_SHADOW_EN(vmlock) (vmlock & 0x2) + +#define MB2_SHADOW_OFFSET 0x2000 +#define MB2_SHADOW_SIZE 16 + +enum vmd_features { + /* + * Device may contain registers which hint the physical location of the + * membars, in order to allow proper address translation during + * resource assignment to enable guest virtualization + */ + VMD_FEAT_HAS_MEMBAR_SHADOW = (1 << 0), + + /* + * Device may provide root port configuration information which limits + * bus numbering + */ + VMD_FEAT_HAS_BUS_RESTRICTIONS = (1 << 1), + + /* + * Device contains physical location shadow registers in + * vendor-specific capability space + */ + VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP = (1 << 2), + + /* + * Device may use MSI-X vector 0 for software triggering and will not + * be used for MSI remapping + */ + VMD_FEAT_OFFSET_FIRST_VECTOR = (1 << 3), + + /* + * Device can bypass remapping MSI-X transactions into its MSI-X table, + * avoiding the requirement of a VMD MSI domain for child device + * interrupt handling. + */ + VMD_FEAT_CAN_BYPASS_MSI_REMAP = (1 << 4), +}; + +static DEFINE_IDA(vmd_instance_ida); + +/* + * Lock for manipulating VMD IRQ lists. + */ +static DEFINE_RAW_SPINLOCK(list_lock); + +/** + * struct vmd_irq - private data to map driver IRQ to the VMD shared vector + * @node: list item for parent traversal. + * @irq: back pointer to parent. + * @enabled: true if driver enabled IRQ + * @virq: the virtual IRQ value provided to the requesting driver. + * + * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to + * a VMD IRQ using this structure. + */ +struct vmd_irq { + struct list_head node; + struct vmd_irq_list *irq; + bool enabled; + unsigned int virq; +}; + +/** + * struct vmd_irq_list - list of driver requested IRQs mapping to a VMD vector + * @irq_list: the list of irq's the VMD one demuxes to. + * @srcu: SRCU struct for local synchronization. + * @count: number of child IRQs assigned to this vector; used to track + * sharing. + * @virq: The underlying VMD Linux interrupt number + */ +struct vmd_irq_list { + struct list_head irq_list; + struct srcu_struct srcu; + unsigned int count; + unsigned int virq; +}; + +struct vmd_dev { + struct pci_dev *dev; + + spinlock_t cfg_lock; + void __iomem *cfgbar; + + int msix_count; + struct vmd_irq_list *irqs; + + struct pci_sysdata sysdata; + struct resource resources[3]; + struct irq_domain *irq_domain; + struct pci_bus *bus; + u8 busn_start; + u8 first_vec; + char *name; + int instance; +}; + +static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus) +{ + return container_of(bus->sysdata, struct vmd_dev, sysdata); +} + +static inline unsigned int index_from_irqs(struct vmd_dev *vmd, + struct vmd_irq_list *irqs) +{ + return irqs - vmd->irqs; +} + +/* + * Drivers managing a device in a VMD domain allocate their own IRQs as before, + * but the MSI entry for the hardware it's driving will be programmed with a + * destination ID for the VMD MSI-X table. The VMD muxes interrupts in its + * domain into one of its own, and the VMD driver de-muxes these for the + * handlers sharing that VMD IRQ. The vmd irq_domain provides the operations + * and irq_chip to set this up. + */ +static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) +{ + struct vmd_irq *vmdirq = data->chip_data; + struct vmd_irq_list *irq = vmdirq->irq; + struct vmd_dev *vmd = irq_data_get_irq_handler_data(data); + + memset(msg, 0, sizeof(*msg)); + msg->address_hi = X86_MSI_BASE_ADDRESS_HIGH; + msg->arch_addr_lo.base_address = X86_MSI_BASE_ADDRESS_LOW; + msg->arch_addr_lo.destid_0_7 = index_from_irqs(vmd, irq); +} + +/* + * We rely on MSI_FLAG_USE_DEF_CHIP_OPS to set the IRQ mask/unmask ops. + */ +static void vmd_irq_enable(struct irq_data *data) +{ + struct vmd_irq *vmdirq = data->chip_data; + unsigned long flags; + + raw_spin_lock_irqsave(&list_lock, flags); + WARN_ON(vmdirq->enabled); + list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); + vmdirq->enabled = true; + raw_spin_unlock_irqrestore(&list_lock, flags); + + data->chip->irq_unmask(data); +} + +static void vmd_irq_disable(struct irq_data *data) +{ + struct vmd_irq *vmdirq = data->chip_data; + unsigned long flags; + + data->chip->irq_mask(data); + + raw_spin_lock_irqsave(&list_lock, flags); + if (vmdirq->enabled) { + list_del_rcu(&vmdirq->node); + vmdirq->enabled = false; + } + raw_spin_unlock_irqrestore(&list_lock, flags); +} + +/* + * XXX: Stubbed until we develop acceptable way to not create conflicts with + * other devices sharing the same vector. + */ +static int vmd_irq_set_affinity(struct irq_data *data, + const struct cpumask *dest, bool force) +{ + return -EINVAL; +} + +static struct irq_chip vmd_msi_controller = { + .name = "VMD-MSI", + .irq_enable = vmd_irq_enable, + .irq_disable = vmd_irq_disable, + .irq_compose_msi_msg = vmd_compose_msi_msg, + .irq_set_affinity = vmd_irq_set_affinity, +}; + +static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info, + msi_alloc_info_t *arg) +{ + return 0; +} + +/* + * XXX: We can be even smarter selecting the best IRQ once we solve the + * affinity problem. + */ +static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *desc) +{ + unsigned long flags; + int i, best; + + if (vmd->msix_count == 1 + vmd->first_vec) + return &vmd->irqs[vmd->first_vec]; + + /* + * White list for fast-interrupt handlers. All others will share the + * "slow" interrupt vector. + */ + switch (msi_desc_to_pci_dev(desc)->class) { + case PCI_CLASS_STORAGE_EXPRESS: + break; + default: + return &vmd->irqs[vmd->first_vec]; + } + + raw_spin_lock_irqsave(&list_lock, flags); + best = vmd->first_vec + 1; + for (i = best; i < vmd->msix_count; i++) + if (vmd->irqs[i].count < vmd->irqs[best].count) + best = i; + vmd->irqs[best].count++; + raw_spin_unlock_irqrestore(&list_lock, flags); + + return &vmd->irqs[best]; +} + +static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info, + unsigned int virq, irq_hw_number_t hwirq, + msi_alloc_info_t *arg) +{ + struct msi_desc *desc = arg->desc; + struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(desc)->bus); + struct vmd_irq *vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL); + + if (!vmdirq) + return -ENOMEM; + + INIT_LIST_HEAD(&vmdirq->node); + vmdirq->irq = vmd_next_irq(vmd, desc); + vmdirq->virq = virq; + + irq_domain_set_info(domain, virq, vmdirq->irq->virq, info->chip, vmdirq, + handle_untracked_irq, vmd, NULL); + return 0; +} + +static void vmd_msi_free(struct irq_domain *domain, + struct msi_domain_info *info, unsigned int virq) +{ + struct vmd_irq *vmdirq = irq_get_chip_data(virq); + unsigned long flags; + + synchronize_srcu(&vmdirq->irq->srcu); + + /* XXX: Potential optimization to rebalance */ + raw_spin_lock_irqsave(&list_lock, flags); + vmdirq->irq->count--; + raw_spin_unlock_irqrestore(&list_lock, flags); + + kfree(vmdirq); +} + +static int vmd_msi_prepare(struct irq_domain *domain, struct device *dev, + int nvec, msi_alloc_info_t *arg) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct vmd_dev *vmd = vmd_from_bus(pdev->bus); + + if (nvec > vmd->msix_count) + return vmd->msix_count; + + memset(arg, 0, sizeof(*arg)); + return 0; +} + +static void vmd_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +{ + arg->desc = desc; +} + +static struct msi_domain_ops vmd_msi_domain_ops = { + .get_hwirq = vmd_get_hwirq, + .msi_init = vmd_msi_init, + .msi_free = vmd_msi_free, + .msi_prepare = vmd_msi_prepare, + .set_desc = vmd_set_desc, +}; + +static struct msi_domain_info vmd_msi_domain_info = { + .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSIX, + .ops = &vmd_msi_domain_ops, + .chip = &vmd_msi_controller, +}; + +static void vmd_set_msi_remapping(struct vmd_dev *vmd, bool enable) +{ + u16 reg; + + pci_read_config_word(vmd->dev, PCI_REG_VMCONFIG, ®); + reg = enable ? (reg & ~VMCONFIG_MSI_REMAP) : + (reg | VMCONFIG_MSI_REMAP); + pci_write_config_word(vmd->dev, PCI_REG_VMCONFIG, reg); +} + +static int vmd_create_irq_domain(struct vmd_dev *vmd) +{ + struct fwnode_handle *fn; + + fn = irq_domain_alloc_named_id_fwnode("VMD-MSI", vmd->sysdata.domain); + if (!fn) + return -ENODEV; + + vmd->irq_domain = pci_msi_create_irq_domain(fn, &vmd_msi_domain_info, NULL); + if (!vmd->irq_domain) { + irq_domain_free_fwnode(fn); + return -ENODEV; + } + + return 0; +} + +static void vmd_remove_irq_domain(struct vmd_dev *vmd) +{ + /* + * Some production BIOS won't enable remapping between soft reboots. + * Ensure remapping is restored before unloading the driver. + */ + if (!vmd->msix_count) + vmd_set_msi_remapping(vmd, true); + + if (vmd->irq_domain) { + struct fwnode_handle *fn = vmd->irq_domain->fwnode; + + irq_domain_remove(vmd->irq_domain); + irq_domain_free_fwnode(fn); + } +} + +static void __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus, + unsigned int devfn, int reg, int len) +{ + unsigned int busnr_ecam = bus->number - vmd->busn_start; + u32 offset = PCIE_ECAM_OFFSET(busnr_ecam, devfn, reg); + + if (offset + len >= resource_size(&vmd->dev->resource[VMD_CFGBAR])) + return NULL; + + return vmd->cfgbar + offset; +} + +/* + * CPU may deadlock if config space is not serialized on some versions of this + * hardware, so all config space access is done under a spinlock. + */ +static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg, + int len, u32 *value) +{ + struct vmd_dev *vmd = vmd_from_bus(bus); + void __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); + unsigned long flags; + int ret = 0; + + if (!addr) + return -EFAULT; + + spin_lock_irqsave(&vmd->cfg_lock, flags); + switch (len) { + case 1: + *value = readb(addr); + break; + case 2: + *value = readw(addr); + break; + case 4: + *value = readl(addr); + break; + default: + ret = -EINVAL; + break; + } + spin_unlock_irqrestore(&vmd->cfg_lock, flags); + return ret; +} + +/* + * VMD h/w converts non-posted config writes to posted memory writes. The + * read-back in this function forces the completion so it returns only after + * the config space was written, as expected. + */ +static int vmd_pci_write(struct pci_bus *bus, unsigned int devfn, int reg, + int len, u32 value) +{ + struct vmd_dev *vmd = vmd_from_bus(bus); + void __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); + unsigned long flags; + int ret = 0; + + if (!addr) + return -EFAULT; + + spin_lock_irqsave(&vmd->cfg_lock, flags); + switch (len) { + case 1: + writeb(value, addr); + readb(addr); + break; + case 2: + writew(value, addr); + readw(addr); + break; + case 4: + writel(value, addr); + readl(addr); + break; + default: + ret = -EINVAL; + break; + } + spin_unlock_irqrestore(&vmd->cfg_lock, flags); + return ret; +} + +static struct pci_ops vmd_ops = { + .read = vmd_pci_read, + .write = vmd_pci_write, +}; + +#ifdef CONFIG_ACPI +static struct acpi_device *vmd_acpi_find_companion(struct pci_dev *pci_dev) +{ + struct pci_host_bridge *bridge; + u32 busnr, addr; + + if (pci_dev->bus->ops != &vmd_ops) + return NULL; + + bridge = pci_find_host_bridge(pci_dev->bus); + busnr = pci_dev->bus->number - bridge->bus->number; + /* + * The address computation below is only applicable to relative bus + * numbers below 32. + */ + if (busnr > 31) + return NULL; + + addr = (busnr << 24) | ((u32)pci_dev->devfn << 16) | 0x8000FFFFU; + + dev_dbg(&pci_dev->dev, "Looking for ACPI companion (address 0x%x)\n", + addr); + + return acpi_find_child_device(ACPI_COMPANION(bridge->dev.parent), addr, + false); +} + +static bool hook_installed; + +static void vmd_acpi_begin(void) +{ + if (pci_acpi_set_companion_lookup_hook(vmd_acpi_find_companion)) + return; + + hook_installed = true; +} + +static void vmd_acpi_end(void) +{ + if (!hook_installed) + return; + + pci_acpi_clear_companion_lookup_hook(); + hook_installed = false; +} +#else +static inline void vmd_acpi_begin(void) { } +static inline void vmd_acpi_end(void) { } +#endif /* CONFIG_ACPI */ + +static void vmd_domain_reset(struct vmd_dev *vmd) +{ + u16 bus, max_buses = resource_size(&vmd->resources[0]); + u8 dev, functions, fn, hdr_type; + char __iomem *base; + + for (bus = 0; bus < max_buses; bus++) { + for (dev = 0; dev < 32; dev++) { + base = vmd->cfgbar + PCIE_ECAM_OFFSET(bus, + PCI_DEVFN(dev, 0), 0); + + hdr_type = readb(base + PCI_HEADER_TYPE); + + functions = (hdr_type & 0x80) ? 8 : 1; + for (fn = 0; fn < functions; fn++) { + base = vmd->cfgbar + PCIE_ECAM_OFFSET(bus, + PCI_DEVFN(dev, fn), 0); + + hdr_type = readb(base + PCI_HEADER_TYPE) & + PCI_HEADER_TYPE_MASK; + + if (hdr_type != PCI_HEADER_TYPE_BRIDGE || + (readw(base + PCI_CLASS_DEVICE) != + PCI_CLASS_BRIDGE_PCI)) + continue; + + /* + * Temporarily disable the I/O range before updating + * PCI_IO_BASE. + */ + writel(0x0000ffff, base + PCI_IO_BASE_UPPER16); + /* Update lower 16 bits of I/O base/limit */ + writew(0x00f0, base + PCI_IO_BASE); + /* Update upper 16 bits of I/O base/limit */ + writel(0, base + PCI_IO_BASE_UPPER16); + + /* MMIO Base/Limit */ + writel(0x0000fff0, base + PCI_MEMORY_BASE); + + /* Prefetchable MMIO Base/Limit */ + writel(0, base + PCI_PREF_LIMIT_UPPER32); + writel(0x0000fff0, base + PCI_PREF_MEMORY_BASE); + writel(0xffffffff, base + PCI_PREF_BASE_UPPER32); + } + } + } +} + +static void vmd_attach_resources(struct vmd_dev *vmd) +{ + vmd->dev->resource[VMD_MEMBAR1].child = &vmd->resources[1]; + vmd->dev->resource[VMD_MEMBAR2].child = &vmd->resources[2]; +} + +static void vmd_detach_resources(struct vmd_dev *vmd) +{ + vmd->dev->resource[VMD_MEMBAR1].child = NULL; + vmd->dev->resource[VMD_MEMBAR2].child = NULL; +} + +/* + * VMD domains start at 0x10000 to not clash with ACPI _SEG domains. + * Per ACPI r6.0, sec 6.5.6, _SEG returns an integer, of which the lower + * 16 bits are the PCI Segment Group (domain) number. Other bits are + * currently reserved. + */ +static int vmd_find_free_domain(void) +{ + int domain = 0xffff; + struct pci_bus *bus = NULL; + + while ((bus = pci_find_next_bus(bus)) != NULL) + domain = max_t(int, domain, pci_domain_nr(bus)); + return domain + 1; +} + +static int vmd_get_phys_offsets(struct vmd_dev *vmd, bool native_hint, + resource_size_t *offset1, + resource_size_t *offset2) +{ + struct pci_dev *dev = vmd->dev; + u64 phys1, phys2; + + if (native_hint) { + u32 vmlock; + int ret; + + ret = pci_read_config_dword(dev, PCI_REG_VMLOCK, &vmlock); + if (ret || PCI_POSSIBLE_ERROR(vmlock)) + return -ENODEV; + + if (MB2_SHADOW_EN(vmlock)) { + void __iomem *membar2; + + membar2 = pci_iomap(dev, VMD_MEMBAR2, 0); + if (!membar2) + return -ENOMEM; + phys1 = readq(membar2 + MB2_SHADOW_OFFSET); + phys2 = readq(membar2 + MB2_SHADOW_OFFSET + 8); + pci_iounmap(dev, membar2); + } else + return 0; + } else { + /* Hypervisor-Emulated Vendor-Specific Capability */ + int pos = pci_find_capability(dev, PCI_CAP_ID_VNDR); + u32 reg, regu; + + pci_read_config_dword(dev, pos + 4, ®); + + /* "SHDW" */ + if (pos && reg == 0x53484457) { + pci_read_config_dword(dev, pos + 8, ®); + pci_read_config_dword(dev, pos + 12, ®u); + phys1 = (u64) regu << 32 | reg; + + pci_read_config_dword(dev, pos + 16, ®); + pci_read_config_dword(dev, pos + 20, ®u); + phys2 = (u64) regu << 32 | reg; + } else + return 0; + } + + *offset1 = dev->resource[VMD_MEMBAR1].start - + (phys1 & PCI_BASE_ADDRESS_MEM_MASK); + *offset2 = dev->resource[VMD_MEMBAR2].start - + (phys2 & PCI_BASE_ADDRESS_MEM_MASK); + + return 0; +} + +static int vmd_get_bus_number_start(struct vmd_dev *vmd) +{ + struct pci_dev *dev = vmd->dev; + u16 reg; + + pci_read_config_word(dev, PCI_REG_VMCAP, ®); + if (BUS_RESTRICT_CAP(reg)) { + pci_read_config_word(dev, PCI_REG_VMCONFIG, ®); + + switch (BUS_RESTRICT_CFG(reg)) { + case 0: + vmd->busn_start = 0; + break; + case 1: + vmd->busn_start = 128; + break; + case 2: + vmd->busn_start = 224; + break; + default: + pci_err(dev, "Unknown Bus Offset Setting (%d)\n", + BUS_RESTRICT_CFG(reg)); + return -ENODEV; + } + } + + return 0; +} + +static irqreturn_t vmd_irq(int irq, void *data) +{ + struct vmd_irq_list *irqs = data; + struct vmd_irq *vmdirq; + int idx; + + idx = srcu_read_lock(&irqs->srcu); + list_for_each_entry_rcu(vmdirq, &irqs->irq_list, node) + generic_handle_irq(vmdirq->virq); + srcu_read_unlock(&irqs->srcu, idx); + + return IRQ_HANDLED; +} + +static int vmd_alloc_irqs(struct vmd_dev *vmd) +{ + struct pci_dev *dev = vmd->dev; + int i, err; + + vmd->msix_count = pci_msix_vec_count(dev); + if (vmd->msix_count < 0) + return -ENODEV; + + vmd->msix_count = pci_alloc_irq_vectors(dev, vmd->first_vec + 1, + vmd->msix_count, PCI_IRQ_MSIX); + if (vmd->msix_count < 0) + return vmd->msix_count; + + vmd->irqs = devm_kcalloc(&dev->dev, vmd->msix_count, sizeof(*vmd->irqs), + GFP_KERNEL); + if (!vmd->irqs) + return -ENOMEM; + + for (i = 0; i < vmd->msix_count; i++) { + err = init_srcu_struct(&vmd->irqs[i].srcu); + if (err) + return err; + + INIT_LIST_HEAD(&vmd->irqs[i].irq_list); + vmd->irqs[i].virq = pci_irq_vector(dev, i); + err = devm_request_irq(&dev->dev, vmd->irqs[i].virq, + vmd_irq, IRQF_NO_THREAD, + vmd->name, &vmd->irqs[i]); + if (err) + return err; + } + + return 0; +} + +/* + * Since VMD is an aperture to regular PCIe root ports, only allow it to + * control features that the OS is allowed to control on the physical PCI bus. + */ +static void vmd_copy_host_bridge_flags(struct pci_host_bridge *root_bridge, + struct pci_host_bridge *vmd_bridge) +{ + vmd_bridge->native_pcie_hotplug = root_bridge->native_pcie_hotplug; + vmd_bridge->native_shpc_hotplug = root_bridge->native_shpc_hotplug; + vmd_bridge->native_aer = root_bridge->native_aer; + vmd_bridge->native_pme = root_bridge->native_pme; + vmd_bridge->native_ltr = root_bridge->native_ltr; + vmd_bridge->native_dpc = root_bridge->native_dpc; +} + +static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) +{ + struct pci_sysdata *sd = &vmd->sysdata; + struct resource *res; + u32 upper_bits; + unsigned long flags; + LIST_HEAD(resources); + resource_size_t offset[2] = {0}; + resource_size_t membar2_offset = 0x2000; + struct pci_bus *child; + struct pci_dev *dev; + int ret; + + /* + * Shadow registers may exist in certain VMD device ids which allow + * guests to correctly assign host physical addresses to the root ports + * and child devices. These registers will either return the host value + * or 0, depending on an enable bit in the VMD device. + */ + if (features & VMD_FEAT_HAS_MEMBAR_SHADOW) { + membar2_offset = MB2_SHADOW_OFFSET + MB2_SHADOW_SIZE; + ret = vmd_get_phys_offsets(vmd, true, &offset[0], &offset[1]); + if (ret) + return ret; + } else if (features & VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP) { + ret = vmd_get_phys_offsets(vmd, false, &offset[0], &offset[1]); + if (ret) + return ret; + } + + /* + * Certain VMD devices may have a root port configuration option which + * limits the bus range to between 0-127, 128-255, or 224-255 + */ + if (features & VMD_FEAT_HAS_BUS_RESTRICTIONS) { + ret = vmd_get_bus_number_start(vmd); + if (ret) + return ret; + } + + res = &vmd->dev->resource[VMD_CFGBAR]; + vmd->resources[0] = (struct resource) { + .name = "VMD CFGBAR", + .start = vmd->busn_start, + .end = vmd->busn_start + (resource_size(res) >> 20) - 1, + .flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED, + }; + + /* + * If the window is below 4GB, clear IORESOURCE_MEM_64 so we can + * put 32-bit resources in the window. + * + * There's no hardware reason why a 64-bit window *couldn't* + * contain a 32-bit resource, but pbus_size_mem() computes the + * bridge window size assuming a 64-bit window will contain no + * 32-bit resources. __pci_assign_resource() enforces that + * artificial restriction to make sure everything will fit. + * + * The only way we could use a 64-bit non-prefetchable MEMBAR is + * if its address is <4GB so that we can convert it to a 32-bit + * resource. To be visible to the host OS, all VMD endpoints must + * be initially configured by platform BIOS, which includes setting + * up these resources. We can assume the device is configured + * according to the platform needs. + */ + res = &vmd->dev->resource[VMD_MEMBAR1]; + upper_bits = upper_32_bits(res->end); + flags = res->flags & ~IORESOURCE_SIZEALIGN; + if (!upper_bits) + flags &= ~IORESOURCE_MEM_64; + vmd->resources[1] = (struct resource) { + .name = "VMD MEMBAR1", + .start = res->start, + .end = res->end, + .flags = flags, + .parent = res, + }; + + res = &vmd->dev->resource[VMD_MEMBAR2]; + upper_bits = upper_32_bits(res->end); + flags = res->flags & ~IORESOURCE_SIZEALIGN; + if (!upper_bits) + flags &= ~IORESOURCE_MEM_64; + vmd->resources[2] = (struct resource) { + .name = "VMD MEMBAR2", + .start = res->start + membar2_offset, + .end = res->end, + .flags = flags, + .parent = res, + }; + + sd->vmd_dev = vmd->dev; + sd->domain = vmd_find_free_domain(); + if (sd->domain < 0) + return sd->domain; + + sd->node = pcibus_to_node(vmd->dev->bus); + + /* + * Currently MSI remapping must be enabled in guest passthrough mode + * due to some missing interrupt remapping plumbing. This is probably + * acceptable because the guest is usually CPU-limited and MSI + * remapping doesn't become a performance bottleneck. + */ + if (!(features & VMD_FEAT_CAN_BYPASS_MSI_REMAP) || + offset[0] || offset[1]) { + ret = vmd_alloc_irqs(vmd); + if (ret) + return ret; + + vmd_set_msi_remapping(vmd, true); + + ret = vmd_create_irq_domain(vmd); + if (ret) + return ret; + + /* + * Override the IRQ domain bus token so the domain can be + * distinguished from a regular PCI/MSI domain. + */ + irq_domain_update_bus_token(vmd->irq_domain, DOMAIN_BUS_VMD_MSI); + } else { + vmd_set_msi_remapping(vmd, false); + } + + pci_add_resource(&resources, &vmd->resources[0]); + pci_add_resource_offset(&resources, &vmd->resources[1], offset[0]); + pci_add_resource_offset(&resources, &vmd->resources[2], offset[1]); + + vmd->bus = pci_create_root_bus(&vmd->dev->dev, vmd->busn_start, + &vmd_ops, sd, &resources); + if (!vmd->bus) { + pci_free_resource_list(&resources); + vmd_remove_irq_domain(vmd); + return -ENODEV; + } + + vmd_copy_host_bridge_flags(pci_find_host_bridge(vmd->dev->bus), + to_pci_host_bridge(vmd->bus->bridge)); + + vmd_attach_resources(vmd); + if (vmd->irq_domain) + dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain); + else + dev_set_msi_domain(&vmd->bus->dev, + dev_get_msi_domain(&vmd->dev->dev)); + + vmd_acpi_begin(); + + pci_scan_child_bus(vmd->bus); + vmd_domain_reset(vmd); + + /* When Intel VMD is enabled, the OS does not discover the Root Ports + * owned by Intel VMD within the MMCFG space. pci_reset_bus() applies + * a reset to the parent of the PCI device supplied as argument. This + * is why we pass a child device, so the reset can be triggered at + * the Intel bridge level and propagated to all the children in the + * hierarchy. + */ + list_for_each_entry(child, &vmd->bus->children, node) { + if (!list_empty(&child->devices)) { + dev = list_first_entry(&child->devices, + struct pci_dev, bus_list); + ret = pci_reset_bus(dev); + if (ret) + pci_warn(dev, "can't reset device: %d\n", ret); + + break; + } + } + + pci_assign_unassigned_bus_resources(vmd->bus); + + /* + * VMD root buses are virtual and don't return true on pci_is_pcie() + * and will fail pcie_bus_configure_settings() early. It can instead be + * run on each of the real root ports. + */ + list_for_each_entry(child, &vmd->bus->children, node) + pcie_bus_configure_settings(child); + + pci_bus_add_devices(vmd->bus); + + vmd_acpi_end(); + + WARN(sysfs_create_link(&vmd->dev->dev.kobj, &vmd->bus->dev.kobj, + "domain"), "Can't create symlink to domain\n"); + return 0; +} + +static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) +{ + unsigned long features = (unsigned long) id->driver_data; + struct vmd_dev *vmd; + int err; + + if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20)) + return -ENOMEM; + + vmd = devm_kzalloc(&dev->dev, sizeof(*vmd), GFP_KERNEL); + if (!vmd) + return -ENOMEM; + + vmd->dev = dev; + vmd->instance = ida_simple_get(&vmd_instance_ida, 0, 0, GFP_KERNEL); + if (vmd->instance < 0) + return vmd->instance; + + vmd->name = devm_kasprintf(&dev->dev, GFP_KERNEL, "vmd%d", + vmd->instance); + if (!vmd->name) { + err = -ENOMEM; + goto out_release_instance; + } + + err = pcim_enable_device(dev); + if (err < 0) + goto out_release_instance; + + vmd->cfgbar = pcim_iomap(dev, VMD_CFGBAR, 0); + if (!vmd->cfgbar) { + err = -ENOMEM; + goto out_release_instance; + } + + pci_set_master(dev); + if (dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(64)) && + dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32))) { + err = -ENODEV; + goto out_release_instance; + } + + if (features & VMD_FEAT_OFFSET_FIRST_VECTOR) + vmd->first_vec = 1; + + spin_lock_init(&vmd->cfg_lock); + pci_set_drvdata(dev, vmd); + err = vmd_enable_domain(vmd, features); + if (err) + goto out_release_instance; + + dev_info(&vmd->dev->dev, "Bound to PCI domain %04x\n", + vmd->sysdata.domain); + return 0; + + out_release_instance: + ida_simple_remove(&vmd_instance_ida, vmd->instance); + return err; +} + +static void vmd_cleanup_srcu(struct vmd_dev *vmd) +{ + int i; + + for (i = 0; i < vmd->msix_count; i++) + cleanup_srcu_struct(&vmd->irqs[i].srcu); +} + +static void vmd_remove(struct pci_dev *dev) +{ + struct vmd_dev *vmd = pci_get_drvdata(dev); + + sysfs_remove_link(&vmd->dev->dev.kobj, "domain"); + pci_stop_root_bus(vmd->bus); + pci_remove_root_bus(vmd->bus); + vmd_cleanup_srcu(vmd); + vmd_detach_resources(vmd); + vmd_remove_irq_domain(vmd); + ida_simple_remove(&vmd_instance_ida, vmd->instance); +} + +static void vmd_shutdown(struct pci_dev *dev) +{ + struct vmd_dev *vmd = pci_get_drvdata(dev); + + vmd_remove_irq_domain(vmd); +} + +#ifdef CONFIG_PM_SLEEP +static int vmd_suspend(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct vmd_dev *vmd = pci_get_drvdata(pdev); + int i; + + for (i = 0; i < vmd->msix_count; i++) + devm_free_irq(dev, vmd->irqs[i].virq, &vmd->irqs[i]); + + return 0; +} + +static int vmd_resume(struct device *dev) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct vmd_dev *vmd = pci_get_drvdata(pdev); + int err, i; + + if (vmd->irq_domain) + vmd_set_msi_remapping(vmd, true); + else + vmd_set_msi_remapping(vmd, false); + + for (i = 0; i < vmd->msix_count; i++) { + err = devm_request_irq(dev, vmd->irqs[i].virq, + vmd_irq, IRQF_NO_THREAD, + vmd->name, &vmd->irqs[i]); + if (err) + return err; + } + + return 0; +} +#endif +static SIMPLE_DEV_PM_OPS(vmd_dev_pm_ops, vmd_suspend, vmd_resume); + +static const struct pci_device_id vmd_ids[] = { + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_201D), + .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP,}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0), + .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW | + VMD_FEAT_HAS_BUS_RESTRICTIONS | + VMD_FEAT_CAN_BYPASS_MSI_REMAP,}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x467f), + .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP | + VMD_FEAT_HAS_BUS_RESTRICTIONS | + VMD_FEAT_OFFSET_FIRST_VECTOR,}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4c3d), + .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP | + VMD_FEAT_HAS_BUS_RESTRICTIONS | + VMD_FEAT_OFFSET_FIRST_VECTOR,}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xa77f), + .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP | + VMD_FEAT_HAS_BUS_RESTRICTIONS | + VMD_FEAT_OFFSET_FIRST_VECTOR,}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x7d0b), + .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP | + VMD_FEAT_HAS_BUS_RESTRICTIONS | + VMD_FEAT_OFFSET_FIRST_VECTOR,}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xad0b), + .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP | + VMD_FEAT_HAS_BUS_RESTRICTIONS | + VMD_FEAT_OFFSET_FIRST_VECTOR,}, + {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B), + .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP | + VMD_FEAT_HAS_BUS_RESTRICTIONS | + VMD_FEAT_OFFSET_FIRST_VECTOR,}, + {0,} +}; +MODULE_DEVICE_TABLE(pci, vmd_ids); + +static struct pci_driver vmd_drv = { + .name = "vmd", + .id_table = vmd_ids, + .probe = vmd_probe, + .remove = vmd_remove, + .shutdown = vmd_shutdown, + .driver = { + .pm = &vmd_dev_pm_ops, + }, +}; +module_pci_driver(vmd_drv); + +MODULE_AUTHOR("Intel Corporation"); +MODULE_LICENSE("GPL v2"); +MODULE_VERSION("0.6"); |