diff options
Diffstat (limited to 'drivers/pci/controller')
104 files changed, 12880 insertions, 3729 deletions
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index 9800b7681054..c254d2b8bf17 100644 --- a/drivers/pci/controller/Kconfig +++ b/drivers/pci/controller/Kconfig @@ -3,12 +3,17 @@ menu "PCI controller drivers" depends on PCI +config PCI_HOST_COMMON + tristate + select PCI_ECAM + config PCI_AARDVARK tristate "Aardvark PCIe controller" depends on (ARCH_MVEBU && ARM64) || COMPILE_TEST depends on OF depends on PCI_MSI select PCI_BRIDGE_EMUL + select IRQ_MSI_LIB help Add support for Aardvark 64bit PCIe Host Controller. This controller is part of the South Bridge of the Marvel Armada @@ -25,6 +30,7 @@ config PCIE_ALTERA_MSI tristate "Altera PCIe MSI feature" depends on PCIE_ALTERA depends on PCI_MSI + select IRQ_MSI_LIB help Say Y here if you want PCIe MSI support for the Altera FPGA. This MSI driver supports Altera MSI to GIC controller IP. @@ -40,6 +46,7 @@ config PCIE_APPLE depends on OF depends on PCI_MSI select PCI_HOST_COMMON + select IRQ_MSI_LIB 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 @@ -57,6 +64,7 @@ config PCIE_BRCMSTB BMIPS_GENERIC || COMPILE_TEST depends on OF depends on PCI_MSI + select IRQ_MSI_LIB default ARCH_BRCMSTB || BMIPS_GENERIC help Say Y here to enable PCIe host controller support for @@ -93,6 +101,7 @@ config PCIE_IPROC_MSI bool "Broadcom iProc PCIe MSI support" depends on PCIE_IPROC_PLATFORM || PCIE_IPROC_BCMA depends on PCI_MSI + select IRQ_MSI_LIB default ARCH_BCM_IPROC help Say Y here if you want to enable MSI support for Broadcom's iProc @@ -119,10 +128,6 @@ config PCI_FTPCI100 depends on OF default ARCH_GEMINI -config PCI_HOST_COMMON - tristate - select PCI_ECAM - config PCI_HOST_GENERIC tristate "Generic PCI host controller" depends on OF @@ -141,7 +146,7 @@ config PCIE_HISI_ERR config PCI_IXP4XX bool "Intel IXP4xx PCI controller" - depends on ARM && OF + depends on OF depends on ARCH_IXP4XX || COMPILE_TEST default ARCH_IXP4XX help @@ -151,6 +156,7 @@ config PCI_IXP4XX config VMD depends on PCI_MSI && X86_64 && !UML tristate "Intel Volume Management Device Driver" + select IRQ_MSI_LIB help Adds support for the Intel Volume Management Device (VMD). VMD is a secondary PCI host bridge that allows PCI Express root ports, @@ -190,6 +196,7 @@ config PCIE_MEDIATEK depends on ARCH_AIROHA || ARCH_MEDIATEK || COMPILE_TEST depends on OF depends on PCI_MSI + select IRQ_MSI_LIB help Say Y here if you want to enable PCIe controller support on MediaTek SoCs. @@ -198,6 +205,7 @@ config PCIE_MEDIATEK_GEN3 tristate "MediaTek Gen3 PCIe controller" depends on ARCH_AIROHA || ARCH_MEDIATEK || COMPILE_TEST depends on PCI_MSI + select IRQ_MSI_LIB help Adds support for PCIe Gen3 MAC controller for MediaTek SoCs. This PCIe controller is compatible with Gen3, Gen2 and Gen1 speed, @@ -227,6 +235,7 @@ config PCI_TEGRA bool "NVIDIA Tegra PCIe controller" depends on ARCH_TEGRA || COMPILE_TEST depends on PCI_MSI + select IRQ_MSI_LIB help Say Y here if you want support for the PCIe host controller found on NVIDIA Tegra SoCs. @@ -235,6 +244,7 @@ config PCIE_RCAR_HOST bool "Renesas R-Car PCIe controller (host mode)" depends on ARCH_RENESAS || COMPILE_TEST depends on PCI_MSI + select IRQ_MSI_LIB help Say Y here if you want PCIe controller support on R-Car SoCs in host mode. @@ -249,12 +259,20 @@ config PCIE_RCAR_EP config PCI_RCAR_GEN2 bool "Renesas R-Car Gen2 Internal PCI controller" - depends on ARCH_RENESAS || COMPILE_TEST - depends on ARM + depends on (ARCH_RENESAS && ARM) || COMPILE_TEST 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. + Each internal PCI controller contains a single built-in EHCI/OHCI + host controller. + +config PCIE_RENESAS_RZG3S_HOST + bool "Renesas RZ/G3S PCIe host controller" + depends on ARCH_RENESAS || COMPILE_TEST + select MFD_SYSCON + select IRQ_MSI_LIB + help + Say Y here if you want PCIe host controller support on Renesas RZ/G3S + SoC. config PCIE_ROCKCHIP bool @@ -303,6 +321,7 @@ config PCI_XGENE_MSI bool "X-Gene v1 PCIe MSI feature" depends on PCI_XGENE depends on PCI_MSI + select IRQ_MSI_LIB default y help Say Y here if you want PCIe MSI support for the APM X-Gene v1 SoC. @@ -312,6 +331,7 @@ config PCIE_XILINX bool "Xilinx AXI PCIe controller" depends on OF depends on PCI_MSI + select IRQ_MSI_LIB help Say 'Y' here if you want kernel to support the Xilinx AXI PCIe Host Bridge driver. @@ -321,6 +341,7 @@ config PCIE_XILINX_DMA_PL depends on ARCH_ZYNQMP || COMPILE_TEST depends on PCI_MSI select PCI_HOST_COMMON + select IRQ_MSI_LIB help Say 'Y' here if you want kernel support for the Xilinx PL DMA PCIe host bridge. The controller is a Soft IP which can act as @@ -331,6 +352,7 @@ config PCIE_XILINX_NWL bool "Xilinx NWL PCIe controller" depends on ARCH_ZYNQMP || COMPILE_TEST depends on PCI_MSI + select IRQ_MSI_LIB help Say 'Y' here if you want kernel support for Xilinx NWL PCIe controller. The controller can act as Root Port diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile index 038ccbd9e3ba..229929a945c2 100644 --- a/drivers/pci/controller/Makefile +++ b/drivers/pci/controller/Makefile @@ -10,6 +10,7 @@ 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-$(CONFIG_PCIE_RENESAS_RZG3S_HOST) += pcie-rzg3s-host.o obj-$(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 diff --git a/drivers/pci/controller/cadence/Kconfig b/drivers/pci/controller/cadence/Kconfig index 8a0044bb3989..9e651d545973 100644 --- a/drivers/pci/controller/cadence/Kconfig +++ b/drivers/pci/controller/cadence/Kconfig @@ -4,25 +4,25 @@ menu "Cadence-based PCIe controllers" depends on PCI config PCIE_CADENCE - bool + tristate config PCIE_CADENCE_HOST - bool + tristate depends on OF select IRQ_DOMAIN select PCIE_CADENCE config PCIE_CADENCE_EP - bool + tristate depends on OF depends on PCI_ENDPOINT select PCIE_CADENCE config PCIE_CADENCE_PLAT - bool + tristate config PCIE_CADENCE_PLAT_HOST - bool "Cadence platform PCIe controller (host mode)" + tristate "Cadence platform PCIe controller (host mode)" depends on OF select PCIE_CADENCE_HOST select PCIE_CADENCE_PLAT @@ -32,7 +32,7 @@ config PCIE_CADENCE_PLAT_HOST vendors SoCs. config PCIE_CADENCE_PLAT_EP - bool "Cadence platform PCIe controller (endpoint mode)" + tristate "Cadence platform PCIe controller (endpoint mode)" depends on OF depends on PCI_ENDPOINT select PCIE_CADENCE_EP @@ -42,14 +42,39 @@ config PCIE_CADENCE_PLAT_EP endpoint mode. This PCIe controller may be embedded into many different vendors SoCs. +config PCI_SKY1_HOST + tristate "CIX SKY1 PCIe controller (host mode)" + depends on OF && (ARCH_CIX || COMPILE_TEST) + select PCIE_CADENCE_HOST + select PCI_ECAM + help + Say Y here if you want to support the CIX SKY1 PCIe platform + controller in host mode. CIX SKY1 PCIe controller uses Cadence + HPA (High Performance Architecture IP [Second generation of + Cadence PCIe IP]) + + This driver requires Cadence PCIe core infrastructure + (PCIE_CADENCE_HOST) and hardware platform adaptation layer + to function. + +config PCIE_SG2042_HOST + tristate "Sophgo SG2042 PCIe controller (host mode)" + depends on OF && (ARCH_SOPHGO || COMPILE_TEST) + select PCIE_CADENCE_HOST + help + Say Y here if you want to support the Sophgo SG2042 PCIe platform + controller in host mode. Sophgo SG2042 PCIe controller uses Cadence + PCIe core. + config PCI_J721E - bool + tristate + select PCIE_CADENCE_HOST if PCI_J721E_HOST != n + select PCIE_CADENCE_EP if PCI_J721E_EP != n config PCI_J721E_HOST - bool "TI J721E PCIe controller (host mode)" + tristate "TI J721E PCIe controller (host mode)" depends on ARCH_K3 || COMPILE_TEST depends on OF - select PCIE_CADENCE_HOST select PCI_J721E help Say Y here if you want to support the TI J721E PCIe platform @@ -57,14 +82,14 @@ config PCI_J721E_HOST core. config PCI_J721E_EP - bool "TI J721E PCIe controller (endpoint mode)" + tristate "TI J721E PCIe controller (endpoint mode)" depends on ARCH_K3 || COMPILE_TEST 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 index 9bac5fb2f13d..b8ec1cecfaa8 100644 --- a/drivers/pci/controller/cadence/Makefile +++ b/drivers/pci/controller/cadence/Makefile @@ -1,6 +1,12 @@ # SPDX-License-Identifier: GPL-2.0 -obj-$(CONFIG_PCIE_CADENCE) += pcie-cadence.o -obj-$(CONFIG_PCIE_CADENCE_HOST) += pcie-cadence-host.o -obj-$(CONFIG_PCIE_CADENCE_EP) += pcie-cadence-ep.o +pcie-cadence-mod-y := pcie-cadence-hpa.o pcie-cadence.o +pcie-cadence-host-mod-y := pcie-cadence-host-common.o pcie-cadence-host.o pcie-cadence-host-hpa.o +pcie-cadence-ep-mod-y := pcie-cadence-ep.o + +obj-$(CONFIG_PCIE_CADENCE) = pcie-cadence-mod.o +obj-$(CONFIG_PCIE_CADENCE_HOST) += pcie-cadence-host-mod.o +obj-$(CONFIG_PCIE_CADENCE_EP) += pcie-cadence-ep-mod.o obj-$(CONFIG_PCIE_CADENCE_PLAT) += pcie-cadence-plat.o obj-$(CONFIG_PCI_J721E) += pci-j721e.o +obj-$(CONFIG_PCIE_SG2042_HOST) += pcie-sg2042.o +obj-$(CONFIG_PCI_SKY1_HOST) += pci-sky1.o diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c index 284f2e0e4d26..ecd1b0312400 100644 --- a/drivers/pci/controller/cadence/pci-j721e.c +++ b/drivers/pci/controller/cadence/pci-j721e.c @@ -15,6 +15,7 @@ #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> #include <linux/mfd/syscon.h> +#include <linux/module.h> #include <linux/of.h> #include <linux/pci.h> #include <linux/platform_device.h> @@ -27,6 +28,7 @@ #define cdns_pcie_to_rc(p) container_of(p, struct cdns_pcie_rc, pcie) #define ENABLE_REG_SYS_2 0x108 +#define ENABLE_CLR_REG_SYS_2 0x308 #define STATUS_REG_SYS_2 0x508 #define STATUS_CLR_REG_SYS_2 0x708 #define LINK_DOWN BIT(1) @@ -116,6 +118,15 @@ static irqreturn_t j721e_pcie_link_irq_handler(int irq, void *priv) return IRQ_HANDLED; } +static void j721e_pcie_disable_link_irq(struct j721e_pcie *pcie) +{ + u32 reg; + + reg = j721e_pcie_intd_readl(pcie, ENABLE_CLR_REG_SYS_2); + reg |= pcie->linkdown_irq_regfield; + j721e_pcie_intd_writel(pcie, ENABLE_CLR_REG_SYS_2, reg); +} + static void j721e_pcie_config_link_irq(struct j721e_pcie *pcie) { u32 reg; @@ -153,11 +164,7 @@ static bool j721e_pcie_link_up(struct cdns_pcie *cdns_pcie) 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; + return (reg & LINK_STATUS) == LINK_UP_DL_COMPLETED; } static const struct cdns_pcie_ops j721e_pcie_ops = { @@ -277,6 +284,25 @@ static int j721e_pcie_ctrl_init(struct j721e_pcie *pcie) if (!ret) offset = args.args[0]; + /* + * The PCIe Controller's registers have different "reset-values" + * depending on the "strap" settings programmed into the PCIEn_CTRL + * register within the CTRL_MMR memory-mapped register space. + * The registers latch onto a "reset-value" based on the "strap" + * settings sampled after the PCIe Controller is powered on. + * To ensure that the "reset-values" are sampled accurately, power + * off the PCIe Controller before programming the "strap" settings + * and power it on after that. The runtime PM APIs namely + * pm_runtime_put_sync() and pm_runtime_get_sync() will decrement and + * increment the usage counter respectively, causing GENPD to power off + * and power on the PCIe Controller. + */ + ret = pm_runtime_put_sync(dev); + if (ret < 0) { + dev_err(dev, "Failed to power off PCIe Controller\n"); + return ret; + } + ret = j721e_pcie_set_mode(pcie, syscon, offset); if (ret < 0) { dev_err(dev, "Failed to set pci mode\n"); @@ -295,6 +321,12 @@ static int j721e_pcie_ctrl_init(struct j721e_pcie *pcie) return ret; } + ret = pm_runtime_get_sync(dev); + if (ret < 0) { + dev_err(dev, "Failed to power on PCIe Controller\n"); + return ret; + } + /* Enable ACSPCIE refclk output if the optional property exists */ syscon = syscon_regmap_lookup_by_phandle_optional(node, "ti,syscon-acspcie-proxy-ctrl"); @@ -355,6 +387,7 @@ static const struct j721e_pcie_data j7200_pcie_rc_data = { static const struct j721e_pcie_data j7200_pcie_ep_data = { .mode = PCI_MODE_EP, .quirk_detect_quiet_flag = true, + .linkdown_irq_regfield = J7200_LINK_DOWN, .quirk_disable_flr = true, .max_lanes = 2, }; @@ -376,16 +409,23 @@ static const struct j721e_pcie_data j784s4_pcie_rc_data = { .mode = PCI_MODE_RC, .quirk_retrain_flag = true, .byte_access_allowed = false, - .linkdown_irq_regfield = LINK_DOWN, + .linkdown_irq_regfield = J7200_LINK_DOWN, .max_lanes = 4, }; static const struct j721e_pcie_data j784s4_pcie_ep_data = { .mode = PCI_MODE_EP, - .linkdown_irq_regfield = LINK_DOWN, + .linkdown_irq_regfield = J7200_LINK_DOWN, .max_lanes = 4, }; +static const struct j721e_pcie_data j722s_pcie_rc_data = { + .mode = PCI_MODE_RC, + .linkdown_irq_regfield = J7200_LINK_DOWN, + .byte_access_allowed = true, + .max_lanes = 1, +}; + static const struct of_device_id of_j721e_pcie_match[] = { { .compatible = "ti,j721e-pcie-host", @@ -419,8 +459,13 @@ static const struct of_device_id of_j721e_pcie_match[] = { .compatible = "ti,j784s4-pcie-ep", .data = &j784s4_pcie_ep_data, }, + { + .compatible = "ti,j722s-pcie-host", + .data = &j722s_pcie_rc_data, + }, {}, }; +MODULE_DEVICE_TABLE(of, of_j721e_pcie_match); static int j721e_pcie_probe(struct platform_device *pdev) { @@ -432,9 +477,7 @@ static int j721e_pcie_probe(struct platform_device *pdev) 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; @@ -452,7 +495,7 @@ static int j721e_pcie_probe(struct platform_device *pdev) switch (mode) { case PCI_MODE_RC: - if (!IS_ENABLED(CONFIG_PCIE_CADENCE_HOST)) + if (!IS_ENABLED(CONFIG_PCI_J721E_HOST)) return -ENODEV; bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc)); @@ -471,7 +514,7 @@ static int j721e_pcie_probe(struct platform_device *pdev) pcie->cdns_pcie = cdns_pcie; break; case PCI_MODE_EP: - if (!IS_ENABLED(CONFIG_PCIE_CADENCE_EP)) + if (!IS_ENABLED(CONFIG_PCI_J721E_EP)) return -ENODEV; ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); @@ -530,7 +573,7 @@ static int j721e_pcie_probe(struct platform_device *pdev) ret = j721e_pcie_ctrl_init(pcie); if (ret < 0) { - dev_err_probe(dev, ret, "pm_runtime_get_sync failed\n"); + dev_err_probe(dev, ret, "j721e_pcie_ctrl_init failed\n"); goto err_get_sync; } @@ -545,12 +588,12 @@ static int j721e_pcie_probe(struct platform_device *pdev) switch (mode) { case PCI_MODE_RC: - gpiod = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); - if (IS_ERR(gpiod)) { - ret = dev_err_probe(dev, PTR_ERR(gpiod), "Failed to get reset GPIO\n"); + pcie->reset_gpio = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW); + if (IS_ERR(pcie->reset_gpio)) { + ret = dev_err_probe(dev, PTR_ERR(pcie->reset_gpio), + "Failed to get reset GPIO\n"); goto err_get_sync; } - pcie->reset_gpio = gpiod; ret = cdns_pcie_init_phy(dev, cdns_pcie); if (ret) { @@ -558,37 +601,28 @@ static int j721e_pcie_probe(struct platform_device *pdev) goto err_get_sync; } - clk = devm_clk_get_optional(dev, "pcie_refclk"); - if (IS_ERR(clk)) { - ret = dev_err_probe(dev, PTR_ERR(clk), "failed to get pcie_refclk\n"); - goto err_pcie_setup; - } - - ret = clk_prepare_enable(clk); - if (ret) { - dev_err_probe(dev, ret, "failed to enable pcie_refclk\n"); + pcie->refclk = devm_clk_get_optional_enabled(dev, "pcie_refclk"); + if (IS_ERR(pcie->refclk)) { + ret = dev_err_probe(dev, PTR_ERR(pcie->refclk), + "failed to enable pcie_refclk\n"); goto err_pcie_setup; } - pcie->refclk = clk; /* - * The "Power Sequencing and Reset Signal Timings" table of the - * PCI Express Card Electromechanical Specification, Revision - * 5.1, Section 2.9.2, Symbol "T_PERST-CLK", 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. + * Section 2.2 of the PCI Express Card Electromechanical + * Specification (Revision 5.1) mandates that the deassertion + * of the PERST# signal should be delayed by 100 ms (TPVPERL). + * This shall ensure that the power and the reference clock + * are stable. */ - if (gpiod) { - fsleep(PCIE_T_PERST_CLK_US); - gpiod_set_value_cansleep(gpiod, 1); + if (pcie->reset_gpio) { + msleep(PCIE_T_PVPERL_MS); + gpiod_set_value_cansleep(pcie->reset_gpio, 1); } ret = cdns_pcie_host_setup(rc); - if (ret < 0) { - clk_disable_unprepare(pcie->refclk); + if (ret < 0) goto err_pcie_setup; - } break; case PCI_MODE_EP: @@ -622,9 +656,21 @@ static void 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; + struct cdns_pcie_ep *ep; + struct cdns_pcie_rc *rc; + + if (pcie->mode == PCI_MODE_RC) { + rc = container_of(cdns_pcie, struct cdns_pcie_rc, pcie); + cdns_pcie_host_disable(rc); + } else { + ep = container_of(cdns_pcie, struct cdns_pcie_ep, pcie); + cdns_pcie_ep_disable(ep); + } + + gpiod_set_value_cansleep(pcie->reset_gpio, 0); - clk_disable_unprepare(pcie->refclk); cdns_pcie_disable_phy(cdns_pcie); + j721e_pcie_disable_link_irq(pcie); pm_runtime_put(dev); pm_runtime_disable(dev); } @@ -671,15 +717,14 @@ static int j721e_pcie_resume_noirq(struct device *dev) return ret; /* - * The "Power Sequencing and Reset Signal Timings" table of the - * PCI Express Card Electromechanical Specification, Revision - * 5.1, Section 2.9.2, Symbol "T_PERST-CLK", 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. + * Section 2.2 of the PCI Express Card Electromechanical + * Specification (Revision 5.1) mandates that the deassertion + * of the PERST# signal should be delayed by 100 ms (TPVPERL). + * This shall ensure that the power and the reference clock + * are stable. */ if (pcie->reset_gpio) { - fsleep(PCIE_T_PERST_CLK_US); + msleep(PCIE_T_PVPERL_MS); gpiod_set_value_cansleep(pcie->reset_gpio, 1); } @@ -712,7 +757,7 @@ static DEFINE_NOIRQ_DEV_PM_OPS(j721e_pcie_pm_ops, static struct platform_driver j721e_pcie_driver = { .probe = j721e_pcie_probe, - .remove_new = j721e_pcie_remove, + .remove = j721e_pcie_remove, .driver = { .name = "j721e-pcie", .of_match_table = of_j721e_pcie_match, @@ -720,4 +765,8 @@ static struct platform_driver j721e_pcie_driver = { .pm = pm_sleep_ptr(&j721e_pcie_pm_ops), }, }; -builtin_platform_driver(j721e_pcie_driver); +module_platform_driver(j721e_pcie_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("PCIe controller driver for TI's J721E and related SoCs"); +MODULE_AUTHOR("Kishon Vijay Abraham I <kishon@ti.com>"); diff --git a/drivers/pci/controller/cadence/pci-sky1.c b/drivers/pci/controller/cadence/pci-sky1.c new file mode 100644 index 000000000000..d8c216dc120d --- /dev/null +++ b/drivers/pci/controller/cadence/pci-sky1.c @@ -0,0 +1,238 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe controller driver for CIX's sky1 SoCs + * + * Copyright 2025 Cix Technology Group Co., Ltd. + * Author: Hans Zhang <hans.zhang@cixtech.com> + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_device.h> +#include <linux/pci.h> +#include <linux/pci-ecam.h> +#include <linux/pci_ids.h> + +#include "pcie-cadence.h" +#include "pcie-cadence-host-common.h" + +#define PCI_VENDOR_ID_CIX 0x1f6c +#define PCI_DEVICE_ID_CIX_SKY1 0x0001 + +#define STRAP_REG(n) ((n) * 0x04) +#define STATUS_REG(n) ((n) * 0x04) +#define LINK_TRAINING_ENABLE BIT(0) +#define LINK_COMPLETE BIT(0) + +#define SKY1_IP_REG_BANK 0x1000 +#define SKY1_IP_CFG_CTRL_REG_BANK 0x4c00 +#define SKY1_IP_AXI_MASTER_COMMON 0xf000 +#define SKY1_AXI_SLAVE 0x9000 +#define SKY1_AXI_MASTER 0xb000 +#define SKY1_AXI_HLS_REGISTERS 0xc000 +#define SKY1_AXI_RAS_REGISTERS 0xe000 +#define SKY1_DTI_REGISTERS 0xd000 + +#define IP_REG_I_DBG_STS_0 0x420 + +struct sky1_pcie { + struct cdns_pcie *cdns_pcie; + struct cdns_pcie_rc *cdns_pcie_rc; + + struct resource *cfg_res; + struct resource *msg_res; + struct pci_config_window *cfg; + void __iomem *strap_base; + void __iomem *status_base; + void __iomem *reg_base; + void __iomem *cfg_base; + void __iomem *msg_base; +}; + +static int sky1_pcie_resource_get(struct platform_device *pdev, + struct sky1_pcie *pcie) +{ + struct device *dev = &pdev->dev; + struct resource *res; + void __iomem *base; + + base = devm_platform_ioremap_resource_byname(pdev, "reg"); + if (IS_ERR(base)) + return dev_err_probe(dev, PTR_ERR(base), + "unable to find \"reg\" registers\n"); + pcie->reg_base = base; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg"); + if (!res) + return dev_err_probe(dev, -ENODEV, "unable to get \"cfg\" resource\n"); + pcie->cfg_res = res; + + base = devm_platform_ioremap_resource_byname(pdev, "rcsu_strap"); + if (IS_ERR(base)) + return dev_err_probe(dev, PTR_ERR(base), + "unable to find \"rcsu_strap\" registers\n"); + pcie->strap_base = base; + + base = devm_platform_ioremap_resource_byname(pdev, "rcsu_status"); + if (IS_ERR(base)) + return dev_err_probe(dev, PTR_ERR(base), + "unable to find \"rcsu_status\" registers\n"); + pcie->status_base = base; + + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "msg"); + if (!res) + return dev_err_probe(dev, -ENODEV, "unable to get \"msg\" resource\n"); + pcie->msg_res = res; + pcie->msg_base = devm_ioremap_resource(dev, res); + if (IS_ERR(pcie->msg_base)) { + return dev_err_probe(dev, PTR_ERR(pcie->msg_base), + "unable to ioremap msg resource\n"); + } + + return 0; +} + +static int sky1_pcie_start_link(struct cdns_pcie *cdns_pcie) +{ + struct sky1_pcie *pcie = dev_get_drvdata(cdns_pcie->dev); + u32 val; + + val = readl(pcie->strap_base + STRAP_REG(1)); + val |= LINK_TRAINING_ENABLE; + writel(val, pcie->strap_base + STRAP_REG(1)); + + return 0; +} + +static void sky1_pcie_stop_link(struct cdns_pcie *cdns_pcie) +{ + struct sky1_pcie *pcie = dev_get_drvdata(cdns_pcie->dev); + u32 val; + + val = readl(pcie->strap_base + STRAP_REG(1)); + val &= ~LINK_TRAINING_ENABLE; + writel(val, pcie->strap_base + STRAP_REG(1)); +} + +static bool sky1_pcie_link_up(struct cdns_pcie *cdns_pcie) +{ + u32 val; + + val = cdns_pcie_hpa_readl(cdns_pcie, REG_BANK_IP_REG, + IP_REG_I_DBG_STS_0); + return val & LINK_COMPLETE; +} + +static const struct cdns_pcie_ops sky1_pcie_ops = { + .start_link = sky1_pcie_start_link, + .stop_link = sky1_pcie_stop_link, + .link_up = sky1_pcie_link_up, +}; + +static int sky1_pcie_probe(struct platform_device *pdev) +{ + struct cdns_plat_pcie_of_data *reg_off; + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + struct cdns_pcie *cdns_pcie; + struct resource_entry *bus; + struct cdns_pcie_rc *rc; + struct sky1_pcie *pcie; + int ret; + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) + return -ENOMEM; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc)); + if (!bridge) + return -ENOMEM; + + ret = sky1_pcie_resource_get(pdev, pcie); + if (ret < 0) + return ret; + + bus = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (!bus) + return -ENODEV; + + pcie->cfg = pci_ecam_create(dev, pcie->cfg_res, bus->res, + &pci_generic_ecam_ops); + if (IS_ERR(pcie->cfg)) + return PTR_ERR(pcie->cfg); + + bridge->ops = (struct pci_ops *)&pci_generic_ecam_ops.pci_ops; + rc = pci_host_bridge_priv(bridge); + rc->ecam_supported = 1; + rc->cfg_base = pcie->cfg->win; + rc->cfg_res = &pcie->cfg->res; + + cdns_pcie = &rc->pcie; + cdns_pcie->dev = dev; + cdns_pcie->ops = &sky1_pcie_ops; + cdns_pcie->reg_base = pcie->reg_base; + cdns_pcie->msg_res = pcie->msg_res; + cdns_pcie->is_rc = 1; + + reg_off = devm_kzalloc(dev, sizeof(*reg_off), GFP_KERNEL); + if (!reg_off) + return -ENOMEM; + + reg_off->ip_reg_bank_offset = SKY1_IP_REG_BANK; + reg_off->ip_cfg_ctrl_reg_offset = SKY1_IP_CFG_CTRL_REG_BANK; + reg_off->axi_mstr_common_offset = SKY1_IP_AXI_MASTER_COMMON; + reg_off->axi_slave_offset = SKY1_AXI_SLAVE; + reg_off->axi_master_offset = SKY1_AXI_MASTER; + reg_off->axi_hls_offset = SKY1_AXI_HLS_REGISTERS; + reg_off->axi_ras_offset = SKY1_AXI_RAS_REGISTERS; + reg_off->axi_dti_offset = SKY1_DTI_REGISTERS; + cdns_pcie->cdns_pcie_reg_offsets = reg_off; + + pcie->cdns_pcie = cdns_pcie; + pcie->cdns_pcie_rc = rc; + pcie->cfg_base = rc->cfg_base; + bridge->sysdata = pcie->cfg; + + rc->vendor_id = PCI_VENDOR_ID_CIX; + rc->device_id = PCI_DEVICE_ID_CIX_SKY1; + rc->no_inbound_map = 1; + + dev_set_drvdata(dev, pcie); + + ret = cdns_pcie_hpa_host_setup(rc); + if (ret < 0) { + pci_ecam_free(pcie->cfg); + return ret; + } + + return 0; +} + +static const struct of_device_id of_sky1_pcie_match[] = { + { .compatible = "cix,sky1-pcie-host", }, + {}, +}; +MODULE_DEVICE_TABLE(of, of_sky1_pcie_match); + +static void sky1_pcie_remove(struct platform_device *pdev) +{ + struct sky1_pcie *pcie = platform_get_drvdata(pdev); + + pci_ecam_free(pcie->cfg); +} + +static struct platform_driver sky1_pcie_driver = { + .probe = sky1_pcie_probe, + .remove = sky1_pcie_remove, + .driver = { + .name = "sky1-pcie", + .of_match_table = of_sky1_pcie_match, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; +module_platform_driver(sky1_pcie_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("PCIe controller driver for CIX's sky1 SoCs"); +MODULE_AUTHOR("Hans Zhang <hans.zhang@cixtech.com>"); diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c index e0cc4560dfde..c0e1194a936b 100644 --- a/drivers/pci/controller/cadence/pcie-cadence-ep.c +++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c @@ -6,12 +6,14 @@ #include <linux/bitfield.h> #include <linux/delay.h> #include <linux/kernel.h> +#include <linux/module.h> #include <linux/of.h> #include <linux/pci-epc.h> #include <linux/platform_device.h> #include <linux/sizes.h> #include "pcie-cadence.h" +#include "../../pci.h" #define CDNS_PCIE_EP_MIN_APERTURE 128 /* 128 bytes */ #define CDNS_PCIE_EP_IRQ_PCI_ADDR_NONE 0x1 @@ -19,12 +21,13 @@ 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; + u16 cap; if (vfn == 0) return fn; + cap = cdns_pcie_find_ext_capability(pcie, PCI_EXT_CAP_ID_SRIOV); 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); @@ -36,10 +39,11 @@ 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; + u16 cap; + cap = cdns_pcie_find_ext_capability(pcie, PCI_EXT_CAP_ID_SRIOV); if (vfn > 1) { dev_err(&epc->dev, "Only Virtual Function #1 has deviceID\n"); return -EINVAL; @@ -220,13 +224,15 @@ static void cdns_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, clear_bit(r, &ep->ob_region_map); } -static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 mmc) +static int cdns_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 nr_irqs) { struct cdns_pcie_ep *ep = epc_get_drvdata(epc); struct cdns_pcie *pcie = &ep->pcie; - u32 cap = CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET; + u8 mmc = order_base_2(nr_irqs); u16 flags; + u8 cap; + cap = cdns_pcie_find_capability(pcie, PCI_CAP_ID_MSI); fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); /* @@ -246,9 +252,10 @@ 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; + u8 cap; + cap = cdns_pcie_find_capability(pcie, PCI_CAP_ID_MSI); fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); /* Validate that the MSI feature is actually enabled. */ @@ -262,16 +269,17 @@ static int cdns_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) */ mme = FIELD_GET(PCI_MSI_FLAGS_QSIZE, flags); - return mme; + return 1 << 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; + u8 cap; + cap = cdns_pcie_find_capability(pcie, PCI_CAP_ID_MSIX); func_no = cdns_pcie_get_fn_from_vfn(pcie, func_no, vfunc_no); reg = cap + PCI_MSIX_FLAGS; @@ -281,34 +289,34 @@ static int cdns_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no) val &= PCI_MSIX_FLAGS_QSIZE; - return val; + return val + 1; } static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn, - u16 interrupts, enum pci_barno bir, - u32 offset) + u16 nr_irqs, 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; + u8 cap; + cap = cdns_pcie_find_capability(pcie, PCI_CAP_ID_MSIX); 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; + val |= nr_irqs - 1; /* encoded as N-1 */ cdns_pcie_ep_fn_writew(pcie, fn, reg, val); - /* Set MSIX BAR and offset */ + /* Set MSI-X 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 */ + /* Set PBA BAR and offset. BAR must match MSI-X BAR */ reg = cap + PCI_MSIX_PBA; - val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; + val = (offset + (nr_irqs * PCI_MSIX_ENTRY_SIZE)) | bir; cdns_pcie_ep_fn_writel(pcie, fn, reg, val); return 0; @@ -337,10 +345,10 @@ static void cdns_pcie_ep_assert_intx(struct cdns_pcie_ep *ep, u8 fn, u8 intx, if (is_asserted) { ep->irq_pending |= BIT(intx); - msg_code = MSG_CODE_ASSERT_INTA + intx; + msg_code = PCIE_MSG_CODE_ASSERT_INTA + intx; } else { ep->irq_pending &= ~BIT(intx); - msg_code = MSG_CODE_DEASSERT_INTA + intx; + msg_code = PCIE_MSG_CODE_DEASSERT_INTA + intx; } spin_lock_irqsave(&ep->lock, flags); @@ -351,9 +359,8 @@ static void cdns_pcie_ep_assert_intx(struct cdns_pcie_ep *ep, u8 fn, u8 intx, } 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; + offset = CDNS_PCIE_NORMAL_MSG_ROUTING(PCIE_MSG_TYPE_R_LOCAL) | + CDNS_PCIE_NORMAL_MSG_CODE(msg_code); writel(0, ep->irq_cpu_addr + offset); } @@ -379,11 +386,11 @@ 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; + u8 msi_count, cap; + cap = cdns_pcie_find_capability(pcie, PCI_CAP_ID_MSI); fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); /* Check whether the MSI feature has been enabled by the PCI host. */ @@ -431,14 +438,14 @@ static int cdns_pcie_ep_map_msi_irq(struct pci_epc *epc, u8 fn, u8 vfn, 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; + u8 msi_count, cap; int ret; int i; + cap = cdns_pcie_find_capability(pcie, PCI_CAP_ID_MSI); fn = cdns_pcie_get_fn_from_vfn(pcie, fn, vfn); /* Check whether the MSI feature has been enabled by the PCI host. */ @@ -481,16 +488,16 @@ static int cdns_pcie_ep_map_msi_irq(struct pci_epc *epc, u8 fn, u8 vfn, 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; + u8 bir, cap; u16 flags; - u8 bir; + cap = cdns_pcie_find_capability(pcie, PCI_CAP_ID_MSIX); epf = &ep->epf[fn]; if (vfn > 0) epf = &epf->epf[vfn - 1]; @@ -564,7 +571,9 @@ static int cdns_pcie_ep_start(struct pci_epc *epc) int max_epfs = sizeof(epc->function_num_map) * 8; int ret, epf, last_fn; u32 reg, value; + u8 cap; + cap = cdns_pcie_find_capability(pcie, PCI_CAP_ID_EXP); /* * BIT(0) is hardwired to 1, hence function 0 is always enabled * and can't be disabled anyway. @@ -573,8 +582,8 @@ static int cdns_pcie_ep_start(struct pci_epc *epc) /* * Next function field in ARI_CAP_AND_CTR register for last function - * should be 0. - * Clearing Next Function Number field for the last function used. + * should be 0. Clear Next Function Number field for the last + * function used. */ last_fn = find_last_bit(&epc->function_num_map, BITS_PER_LONG); reg = CDNS_PCIE_CORE_PF_I_ARI_CAP_AND_CTRL(last_fn); @@ -588,12 +597,10 @@ static int cdns_pcie_ep_start(struct pci_epc *epc) continue; value = cdns_pcie_ep_fn_readl(pcie, epf, - CDNS_PCIE_EP_FUNC_DEV_CAP_OFFSET + - PCI_EXP_DEVCAP); + cap + 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); + cap + PCI_EXP_DEVCAP, value); } } @@ -607,14 +614,12 @@ static int cdns_pcie_ep_start(struct pci_epc *epc) } 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, @@ -645,6 +650,17 @@ static const struct pci_epc_ops cdns_pcie_epc_ops = { .get_features = cdns_pcie_ep_get_features, }; +void cdns_pcie_ep_disable(struct cdns_pcie_ep *ep) +{ + struct device *dev = ep->pcie.dev; + struct pci_epc *epc = to_pci_epc(dev); + + pci_epc_deinit_notify(epc); + pci_epc_mem_free_addr(epc, ep->irq_phys_addr, ep->irq_cpu_addr, + SZ_128K); + pci_epc_mem_exit(epc); +} +EXPORT_SYMBOL_GPL(cdns_pcie_ep_disable); int cdns_pcie_ep_setup(struct cdns_pcie_ep *ep) { @@ -752,3 +768,8 @@ int cdns_pcie_ep_setup(struct cdns_pcie_ep *ep) return ret; } +EXPORT_SYMBOL_GPL(cdns_pcie_ep_setup); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence PCIe endpoint controller driver"); +MODULE_AUTHOR("Cyrille Pitchen <cyrille.pitchen@free-electrons.com>"); diff --git a/drivers/pci/controller/cadence/pcie-cadence-host-common.c b/drivers/pci/controller/cadence/pcie-cadence-host-common.c new file mode 100644 index 000000000000..15415d7f35ee --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-host-common.c @@ -0,0 +1,288 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Cadence PCIe host controller library. + * + * Copyright (c) 2017 Cadence + * 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" +#include "pcie-cadence-host-common.h" + +#define LINK_RETRAIN_TIMEOUT HZ + +u64 bar_max_size[] = { + [RP_BAR0] = _ULL(128 * SZ_2G), + [RP_BAR1] = SZ_2G, + [RP_NO_BAR] = _BITULL(63), +}; +EXPORT_SYMBOL_GPL(bar_max_size); + +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; +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_training_complete); + +int cdns_pcie_host_wait_for_link(struct cdns_pcie *pcie, + cdns_pcie_linkup_func pcie_link_up) +{ + 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 (pcie_link_up(pcie)) { + dev_info(dev, "Link up\n"); + return 0; + } + usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX); + } + + return -ETIMEDOUT; +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_wait_for_link); + +int cdns_pcie_retrain(struct cdns_pcie *pcie, + cdns_pcie_linkup_func pcie_link_up) +{ + 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, pcie_link_up); + } + return ret; +} +EXPORT_SYMBOL_GPL(cdns_pcie_retrain); + +int cdns_pcie_host_start_link(struct cdns_pcie_rc *rc, + cdns_pcie_linkup_func pcie_link_up) +{ + struct cdns_pcie *pcie = &rc->pcie; + int ret; + + ret = cdns_pcie_host_wait_for_link(pcie, pcie_link_up); + + /* + * Retrain link for Gen2 training defect + * if quirk flag is set. + */ + if (!ret && rc->quirk_retrain_flag) + ret = cdns_pcie_retrain(pcie, pcie_link_up); + + return ret; +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_start_link); + +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; +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_find_min_bar); + +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; +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_find_max_bar); + +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); +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_dma_ranges_cmp); + +int cdns_pcie_host_bar_config(struct cdns_pcie_rc *rc, + struct resource_entry *entry, + cdns_pcie_host_bar_ib_cfg pci_host_ib_config) +{ + struct cdns_pcie *pcie = &rc->pcie; + struct device *dev = pcie->dev; + u64 cpu_addr, size, winsize; + enum cdns_pcie_rp_bar bar; + unsigned long flags; + int ret; + + cpu_addr = entry->res->start; + flags = entry->res->flags; + size = resource_size(entry->res); + + 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 = pci_host_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 = pci_host_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; +} + +int cdns_pcie_host_map_dma_ranges(struct cdns_pcie_rc *rc, + cdns_pcie_host_bar_ib_cfg pci_host_ib_config) +{ + 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 = pci_host_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, pci_host_ib_config); + if (err) { + dev_err(dev, "Fail to configure IB using dma-ranges\n"); + return err; + } + } + + return 0; +} + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence PCIe host controller driver"); diff --git a/drivers/pci/controller/cadence/pcie-cadence-host-common.h b/drivers/pci/controller/cadence/pcie-cadence-host-common.h new file mode 100644 index 000000000000..fe7d4202a8b6 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-host-common.h @@ -0,0 +1,46 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Cadence PCIe Host controller driver. + * + * Copyright (c) 2017 Cadence + * Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> + */ +#ifndef _PCIE_CADENCE_HOST_COMMON_H +#define _PCIE_CADENCE_HOST_COMMON_H + +#include <linux/kernel.h> +#include <linux/pci.h> + +extern u64 bar_max_size[]; + +typedef int (*cdns_pcie_host_bar_ib_cfg)(struct cdns_pcie_rc *, + enum cdns_pcie_rp_bar, + u64, + u64, + unsigned long); +typedef bool (*cdns_pcie_linkup_func)(struct cdns_pcie *); + +int cdns_pcie_host_training_complete(struct cdns_pcie *pcie); +int cdns_pcie_host_wait_for_link(struct cdns_pcie *pcie, + cdns_pcie_linkup_func pcie_link_up); +int cdns_pcie_retrain(struct cdns_pcie *pcie, cdns_pcie_linkup_func pcie_linkup_func); +int cdns_pcie_host_start_link(struct cdns_pcie_rc *rc, + cdns_pcie_linkup_func pcie_link_up); +enum cdns_pcie_rp_bar +cdns_pcie_host_find_min_bar(struct cdns_pcie_rc *rc, u64 size); +enum cdns_pcie_rp_bar +cdns_pcie_host_find_max_bar(struct cdns_pcie_rc *rc, u64 size); +int cdns_pcie_host_dma_ranges_cmp(void *priv, const struct list_head *a, + const struct list_head *b); +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); +int cdns_pcie_host_bar_config(struct cdns_pcie_rc *rc, + struct resource_entry *entry, + cdns_pcie_host_bar_ib_cfg pci_host_ib_config); +int cdns_pcie_host_map_dma_ranges(struct cdns_pcie_rc *rc, + cdns_pcie_host_bar_ib_cfg pci_host_ib_config); + +#endif /* _PCIE_CADENCE_HOST_COMMON_H */ diff --git a/drivers/pci/controller/cadence/pcie-cadence-host-hpa.c b/drivers/pci/controller/cadence/pcie-cadence-host-hpa.c new file mode 100644 index 000000000000..0f540bed58e8 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-host-hpa.c @@ -0,0 +1,368 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Cadence PCIe host controller driver. + * + * Copyright (c) 2024, Cadence Design Systems + * Author: Manikandan K Pillai <mpillai@cadence.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/of_irq.h> +#include <linux/platform_device.h> + +#include "pcie-cadence.h" +#include "pcie-cadence-host-common.h" + +static u8 bar_aperture_mask[] = { + [RP_BAR0] = 0x3F, + [RP_BAR1] = 0x3F, +}; + +void __iomem *cdns_pci_hpa_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, desc1, ctrl0; + u32 regval; + + 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); + } + + /* Clear AXI link-down status */ + regval = cdns_pcie_hpa_readl(pcie, REG_BANK_AXI_SLAVE, CDNS_PCIE_HPA_AT_LINKDOWN); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, CDNS_PCIE_HPA_AT_LINKDOWN, + (regval & ~GENMASK(0, 0))); + + /* Update Output registers for AXI region 0 */ + addr0 = CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_NBITS(12) | + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_DEVFN(devfn) | + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_BUS(busn); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0(0), addr0); + + desc1 = cdns_pcie_hpa_readl(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC1(0)); + desc1 &= ~CDNS_PCIE_HPA_AT_OB_REGION_DESC1_DEVFN_MASK; + desc1 |= CDNS_PCIE_HPA_AT_OB_REGION_DESC1_DEVFN(0); + ctrl0 = CDNS_PCIE_HPA_AT_OB_REGION_CTRL0_SUPPLY_BUS | + CDNS_PCIE_HPA_AT_OB_REGION_CTRL0_SUPPLY_DEV_FN; + + if (busn == bridge->busnr + 1) + desc0 = CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_CONF_TYPE0; + else + desc0 = CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_CONF_TYPE1; + + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC0(0), desc0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC1(0), desc1); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CTRL0(0), ctrl0); + + return rc->cfg_base + (where & 0xfff); +} + +static struct pci_ops cdns_pcie_hpa_host_ops = { + .map_bus = cdns_pci_hpa_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static void cdns_pcie_hpa_host_enable_ptm_response(struct cdns_pcie *pcie) +{ + u32 val; + + val = cdns_pcie_hpa_readl(pcie, REG_BANK_IP_REG, CDNS_PCIE_HPA_LM_PTM_CTRL); + cdns_pcie_hpa_writel(pcie, REG_BANK_IP_REG, CDNS_PCIE_HPA_LM_PTM_CTRL, + val | CDNS_PCIE_HPA_LM_PTM_CTRL_PTMRSEN); +} + +static int cdns_pcie_hpa_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 -ENODEV; + + rc->avail_ib_bar[bar] = false; + + aperture = ilog2(size); + if (bar == RP_NO_BAR) { + addr0 = CDNS_PCIE_HPA_AT_IB_RP_BAR_ADDR0_NBITS(aperture) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + } else { + addr0 = lower_32_bits(cpu_addr); + addr1 = upper_32_bits(cpu_addr); + } + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_MASTER, + CDNS_PCIE_HPA_AT_IB_RP_BAR_ADDR0(bar), addr0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_MASTER, + CDNS_PCIE_HPA_AT_IB_RP_BAR_ADDR1(bar), addr1); + + if (bar == RP_NO_BAR) + bar = (enum cdns_pcie_rp_bar)BAR_0; + + value = cdns_pcie_hpa_readl(pcie, REG_BANK_IP_CFG_CTRL_REG, CDNS_PCIE_HPA_LM_RC_BAR_CFG); + value &= ~(HPA_LM_RC_BAR_CFG_CTRL_MEM_64BITS(bar) | + HPA_LM_RC_BAR_CFG_CTRL_PREF_MEM_64BITS(bar) | + HPA_LM_RC_BAR_CFG_CTRL_MEM_32BITS(bar) | + HPA_LM_RC_BAR_CFG_CTRL_PREF_MEM_32BITS(bar) | + HPA_LM_RC_BAR_CFG_APERTURE(bar, bar_aperture_mask[bar] + 7)); + if (size + cpu_addr >= SZ_4G) { + value |= HPA_LM_RC_BAR_CFG_CTRL_MEM_64BITS(bar); + if ((flags & IORESOURCE_PREFETCH)) + value |= HPA_LM_RC_BAR_CFG_CTRL_PREF_MEM_64BITS(bar); + } else { + value |= HPA_LM_RC_BAR_CFG_CTRL_MEM_32BITS(bar); + if ((flags & IORESOURCE_PREFETCH)) + value |= HPA_LM_RC_BAR_CFG_CTRL_PREF_MEM_32BITS(bar); + } + + value |= HPA_LM_RC_BAR_CFG_APERTURE(bar, aperture); + cdns_pcie_hpa_writel(pcie, REG_BANK_IP_CFG_CTRL_REG, CDNS_PCIE_HPA_LM_RC_BAR_CFG, value); + + return 0; +} + +static int cdns_pcie_hpa_host_init_root_port(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + u32 value, ctrl; + + /* + * Set the root port 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_HPA_LM_BAR_CFG_CTRL_DISABLED; + value = CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR0_CTRL(ctrl) | + CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR1_CTRL(ctrl) | + CDNS_PCIE_HPA_LM_RC_BAR_CFG_PREFETCH_MEM_ENABLE | + CDNS_PCIE_HPA_LM_RC_BAR_CFG_PREFETCH_MEM_64BITS | + CDNS_PCIE_HPA_LM_RC_BAR_CFG_IO_ENABLE | + CDNS_PCIE_HPA_LM_RC_BAR_CFG_IO_32BITS; + cdns_pcie_hpa_writel(pcie, REG_BANK_IP_CFG_CTRL_REG, + CDNS_PCIE_HPA_LM_RC_BAR_CFG, value); + + if (rc->vendor_id != 0xffff) + cdns_pcie_hpa_rp_writew(pcie, PCI_VENDOR_ID, rc->vendor_id); + + if (rc->device_id != 0xffff) + cdns_pcie_hpa_rp_writew(pcie, PCI_DEVICE_ID, rc->device_id); + + cdns_pcie_hpa_rp_writeb(pcie, PCI_CLASS_REVISION, 0); + cdns_pcie_hpa_rp_writeb(pcie, PCI_CLASS_PROG, 0); + cdns_pcie_hpa_rp_writew(pcie, PCI_CLASS_DEVICE, PCI_CLASS_BRIDGE_PCI); + + /* Enable bus mastering */ + value = cdns_pcie_hpa_readl(pcie, REG_BANK_RP, PCI_COMMAND); + value |= (PCI_COMMAND_MEMORY | PCI_COMMAND_IO | PCI_COMMAND_MASTER); + cdns_pcie_hpa_writel(pcie, REG_BANK_RP, PCI_COMMAND, value); + return 0; +} + +static void cdns_pcie_hpa_create_region_for_cfg(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 busnr = 0; + + entry = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (entry) + busnr = entry->res->start; + + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_TAG_MANAGEMENT, 0x01000000); + /* + * 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 + */ + desc1 = CDNS_PCIE_HPA_AT_OB_REGION_DESC1_BUS(busnr); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR1(0), 0x0); + /* Type-1 CFG */ + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC0(0), 0x05000000); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC1(0), desc1); + + addr0 = CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0_NBITS(12) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0(0), addr0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR1(0), addr1); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CTRL0(0), 0x06000000); +} + +static int cdns_pcie_hpa_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_entry *entry; + int r = 0, busnr = 0; + + if (!rc->ecam_supported) + cdns_pcie_hpa_create_region_for_cfg(rc); + + entry = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (entry) + busnr = entry->res->start; + + r++; + if (pcie->msg_res) { + cdns_pcie_hpa_set_outbound_region_for_normal_msg(pcie, busnr, 0, r, + pcie->msg_res->start); + + r++; + } + 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_hpa_set_outbound_region(pcie, busnr, 0, r, + true, + pci_pio_to_address(res->start), + pci_addr, + resource_size(res)); + else + cdns_pcie_hpa_set_outbound_region(pcie, busnr, 0, r, + false, + res->start, + pci_addr, + resource_size(res)); + + r++; + } + + if (rc->no_inbound_map) + return 0; + else + return cdns_pcie_host_map_dma_ranges(rc, cdns_pcie_hpa_host_bar_ib_config); +} + +static int cdns_pcie_hpa_host_init(struct cdns_pcie_rc *rc) +{ + int err; + + err = cdns_pcie_hpa_host_init_root_port(rc); + if (err) + return err; + + return cdns_pcie_hpa_host_init_address_translation(rc); +} + +int cdns_pcie_hpa_host_link_setup(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + struct device *dev = rc->pcie.dev; + int ret; + + if (rc->quirk_detect_quiet_flag) + cdns_pcie_hpa_detect_quiet_min_delay_set(&rc->pcie); + + cdns_pcie_hpa_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_wait_for_link(pcie, cdns_pcie_hpa_link_up); + if (ret) + dev_dbg(dev, "PCIe link never came up\n"); + + return ret; +} +EXPORT_SYMBOL_GPL(cdns_pcie_hpa_host_link_setup); + +int cdns_pcie_hpa_host_setup(struct cdns_pcie_rc *rc) +{ + struct device *dev = rc->pcie.dev; + struct platform_device *pdev = to_platform_device(dev); + 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; + + if (!pcie->reg_base) { + 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); + } + } + + /* ECAM config space is remapped at glue layer */ + if (!rc->cfg_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; + } + + /* Put EROM Bar aperture to 0 */ + cdns_pcie_hpa_writel(pcie, REG_BANK_IP_CFG_CTRL_REG, CDNS_PCIE_EROM, 0x0); + + ret = cdns_pcie_hpa_host_link_setup(rc); + if (ret) + return ret; + + for (bar = RP_BAR0; bar <= RP_NO_BAR; bar++) + rc->avail_ib_bar[bar] = true; + + ret = cdns_pcie_hpa_host_init(rc); + if (ret) + return ret; + + if (!bridge->ops) + bridge->ops = &cdns_pcie_hpa_host_ops; + + return pci_host_probe(bridge); +} +EXPORT_SYMBOL_GPL(cdns_pcie_hpa_host_setup); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence PCIe host controller driver"); diff --git a/drivers/pci/controller/cadence/pcie-cadence-host.c b/drivers/pci/controller/cadence/pcie-cadence-host.c index 8af95e9da7ce..db3154c1eccb 100644 --- a/drivers/pci/controller/cadence/pcie-cadence-host.c +++ b/drivers/pci/controller/cadence/pcie-cadence-host.c @@ -5,20 +5,14 @@ #include <linux/delay.h> #include <linux/kernel.h> +#include <linux/module.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), -}; +#include "pcie-cadence-host-common.h" static u8 bar_aperture_mask[] = { [RP_BAR0] = 0x1F, @@ -72,6 +66,7 @@ void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn, return rc->cfg_base + (where & 0xfff); } +EXPORT_SYMBOL_GPL(cdns_pci_map_bus); static struct pci_ops cdns_pcie_host_ops = { .map_bus = cdns_pci_map_bus, @@ -79,75 +74,12 @@ static struct pci_ops cdns_pcie_host_ops = { .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) +static void cdns_pcie_host_disable_ptm_response(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; + u32 val; - ret = cdns_pcie_host_wait_for_link(pcie); - } - return ret; + 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 void cdns_pcie_host_enable_ptm_response(struct cdns_pcie *pcie) @@ -158,21 +90,24 @@ static void cdns_pcie_host_enable_ptm_response(struct cdns_pcie *pcie) 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) +static void cdns_pcie_host_deinit_root_port(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); + u32 value, ctrl; - return ret; + cdns_pcie_rp_writew(pcie, PCI_CLASS_DEVICE, 0xffff); + cdns_pcie_rp_writeb(pcie, PCI_CLASS_PROG, 0xff); + cdns_pcie_rp_writeb(pcie, PCI_CLASS_REVISION, 0xff); + cdns_pcie_writel(pcie, CDNS_PCIE_LM_ID, 0xffffffff); + cdns_pcie_rp_writew(pcie, PCI_DEVICE_ID, 0xffff); + 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); } static int cdns_pcie_host_init_root_port(struct cdns_pcie_rc *rc) @@ -215,10 +150,11 @@ static int cdns_pcie_host_init_root_port(struct cdns_pcie_rc *rc) 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) +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; @@ -260,172 +196,53 @@ static int cdns_pcie_host_bar_ib_config(struct cdns_pcie_rc *rc, return 0; } -static enum cdns_pcie_rp_bar -cdns_pcie_host_find_min_bar(struct cdns_pcie_rc *rc, u64 size) +static void cdns_pcie_host_unmap_dma_ranges(struct cdns_pcie_rc *rc) { - enum cdns_pcie_rp_bar bar, sel_bar; + struct cdns_pcie *pcie = &rc->pcie; + enum cdns_pcie_rp_bar bar; + u32 value; - sel_bar = RP_BAR_UNDEFINED; + /* Reset inbound configuration for all BARs which were being used */ for (bar = RP_BAR0; bar <= RP_NO_BAR; bar++) { - if (!rc->avail_ib_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; + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_RP_BAR_ADDR0(bar), 0); + cdns_pcie_writel(pcie, CDNS_PCIE_AT_IB_RP_BAR_ADDR1(bar), 0); - sel_bar = RP_BAR_UNDEFINED; - for (bar = RP_BAR0; bar <= RP_NO_BAR; bar++) { - if (!rc->avail_ib_bar[bar]) + if (bar == RP_NO_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; + 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)); + cdns_pcie_writel(pcie, CDNS_PCIE_LM_RC_BAR_CFG, value); } - - 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) +static void cdns_pcie_host_deinit_address_translation(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 pci_host_bridge *bridge = pci_host_bridge_from_priv(rc); struct resource_entry *entry; - u32 no_bar_nbits = 32; - int err; + int r; - 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; - } + cdns_pcie_host_unmap_dma_ranges(rc); - list_sort(NULL, &bridge->dma_ranges, cdns_pcie_host_dma_ranges_cmp); + /* + * Reset outbound region 0 which was reserved for configuration space + * accesses. + */ + cdns_pcie_reset_outbound_region(pcie, 0); - 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; - } + /* Reset rest of the outbound regions */ + r = 1; + resource_list_for_each_entry(entry, &bridge->windows) { + cdns_pcie_reset_outbound_region(pcie, r); + r++; } - - return 0; } static int cdns_pcie_host_init_address_translation(struct cdns_pcie_rc *rc) @@ -452,7 +269,7 @@ static int cdns_pcie_host_init_address_translation(struct cdns_pcie_rc *rc) 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) + if (pcie->ops && 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) | @@ -482,7 +299,13 @@ static int cdns_pcie_host_init_address_translation(struct cdns_pcie_rc *rc) r++; } - return cdns_pcie_host_map_dma_ranges(rc); + return cdns_pcie_host_map_dma_ranges(rc, cdns_pcie_host_bar_ib_config); +} + +static void cdns_pcie_host_deinit(struct cdns_pcie_rc *rc) +{ + cdns_pcie_host_deinit_address_translation(rc); + cdns_pcie_host_deinit_root_port(rc); } int cdns_pcie_host_init(struct cdns_pcie_rc *rc) @@ -495,6 +318,15 @@ int cdns_pcie_host_init(struct cdns_pcie_rc *rc) return cdns_pcie_host_init_address_translation(rc); } +EXPORT_SYMBOL_GPL(cdns_pcie_host_init); + +static void cdns_pcie_host_link_disable(struct cdns_pcie_rc *rc) +{ + struct cdns_pcie *pcie = &rc->pcie; + + cdns_pcie_stop_link(pcie); + cdns_pcie_host_disable_ptm_response(pcie); +} int cdns_pcie_host_link_setup(struct cdns_pcie_rc *rc) { @@ -513,12 +345,26 @@ int cdns_pcie_host_link_setup(struct cdns_pcie_rc *rc) return ret; } - ret = cdns_pcie_host_start_link(rc); + ret = cdns_pcie_host_start_link(rc, cdns_pcie_link_up); if (ret) dev_dbg(dev, "PCIe link never came up\n"); return 0; } +EXPORT_SYMBOL_GPL(cdns_pcie_host_link_setup); + +void cdns_pcie_host_disable(struct cdns_pcie_rc *rc) +{ + struct pci_host_bridge *bridge; + + bridge = pci_host_bridge_from_priv(rc); + pci_stop_root_bus(bridge->bus); + pci_remove_root_bus(bridge->bus); + + cdns_pcie_host_deinit(rc); + cdns_pcie_host_link_disable(rc); +} +EXPORT_SYMBOL_GPL(cdns_pcie_host_disable); int cdns_pcie_host_setup(struct cdns_pcie_rc *rc) { @@ -570,14 +416,10 @@ int cdns_pcie_host_setup(struct cdns_pcie_rc *rc) 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; + return pci_host_probe(bridge); } +EXPORT_SYMBOL_GPL(cdns_pcie_host_setup); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence PCIe host controller driver"); +MODULE_AUTHOR("Cyrille Pitchen <cyrille.pitchen@free-electrons.com>"); diff --git a/drivers/pci/controller/cadence/pcie-cadence-hpa-regs.h b/drivers/pci/controller/cadence/pcie-cadence-hpa-regs.h new file mode 100644 index 000000000000..026e131600de --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-hpa-regs.h @@ -0,0 +1,193 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Cadence PCIe controller driver. + * + * Copyright (c) 2024, Cadence Design Systems + * Author: Manikandan K Pillai <mpillai@cadence.com> + */ +#ifndef _PCIE_CADENCE_HPA_REGS_H +#define _PCIE_CADENCE_HPA_REGS_H + +#include <linux/kernel.h> +#include <linux/pci.h> +#include <linux/pci-epf.h> +#include <linux/phy/phy.h> +#include <linux/bitfield.h> + +/* High Performance Architecture (HPA) PCIe controller registers */ +#define CDNS_PCIE_HPA_IP_REG_BANK 0x01000000 +#define CDNS_PCIE_HPA_IP_CFG_CTRL_REG_BANK 0x01003C00 +#define CDNS_PCIE_HPA_IP_AXI_MASTER_COMMON 0x02020000 + +/* Address Translation Registers */ +#define CDNS_PCIE_HPA_AXI_SLAVE 0x03000000 +#define CDNS_PCIE_HPA_AXI_MASTER 0x03002000 + +/* Root Port register base address */ +#define CDNS_PCIE_HPA_RP_BASE 0x0 + +#define CDNS_PCIE_HPA_LM_ID 0x1420 + +/* Endpoint Function BARs */ +#define CDNS_PCIE_HPA_LM_EP_FUNC_BAR_CFG(bar, fn) \ + (((bar) < BAR_3) ? CDNS_PCIE_HPA_LM_EP_FUNC_BAR_CFG0(fn) : \ + CDNS_PCIE_HPA_LM_EP_FUNC_BAR_CFG1(fn)) +#define CDNS_PCIE_HPA_LM_EP_FUNC_BAR_CFG0(pfn) (0x4000 * (pfn)) +#define CDNS_PCIE_HPA_LM_EP_FUNC_BAR_CFG1(pfn) ((0x4000 * (pfn)) + 0x04) +#define CDNS_PCIE_HPA_LM_EP_VFUNC_BAR_CFG(bar, fn) \ + (((bar) < BAR_3) ? CDNS_PCIE_HPA_LM_EP_VFUNC_BAR_CFG0(fn) : \ + CDNS_PCIE_HPA_LM_EP_VFUNC_BAR_CFG1(fn)) +#define CDNS_PCIE_HPA_LM_EP_VFUNC_BAR_CFG0(vfn) ((0x4000 * (vfn)) + 0x08) +#define CDNS_PCIE_HPA_LM_EP_VFUNC_BAR_CFG1(vfn) ((0x4000 * (vfn)) + 0x0C) +#define CDNS_PCIE_HPA_LM_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(f) \ + (GENMASK(5, 0) << (0x4 + (f) * 10)) +#define CDNS_PCIE_HPA_LM_EP_FUNC_BAR_CFG_BAR_APERTURE(b, a) \ + (((a) << (4 + ((b) * 10))) & (CDNS_PCIE_HPA_LM_EP_FUNC_BAR_CFG_BAR_APERTURE_MASK(b))) +#define CDNS_PCIE_HPA_LM_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(f) \ + (GENMASK(3, 0) << ((f) * 10)) +#define CDNS_PCIE_HPA_LM_EP_FUNC_BAR_CFG_BAR_CTRL(b, c) \ + (((c) << ((b) * 10)) & (CDNS_PCIE_HPA_LM_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b))) + +/* Endpoint Function Configuration Register */ +#define CDNS_PCIE_HPA_LM_EP_FUNC_CFG 0x02C0 + +/* Root Complex BAR Configuration Register */ +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG 0x14 +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR0_APERTURE_MASK GENMASK(9, 4) +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR0_APERTURE(a) \ + FIELD_PREP(CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR0_APERTURE_MASK, a) +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR0_CTRL_MASK GENMASK(3, 0) +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR0_CTRL(c) \ + FIELD_PREP(CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR0_CTRL_MASK, c) +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR1_APERTURE_MASK GENMASK(19, 14) +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR1_APERTURE(a) \ + FIELD_PREP(CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR1_APERTURE_MASK, a) +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR1_CTRL_MASK GENMASK(13, 10) +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR1_CTRL(c) \ + FIELD_PREP(CDNS_PCIE_HPA_LM_RC_BAR_CFG_BAR1_CTRL_MASK, c) + +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_PREFETCH_MEM_ENABLE BIT(20) +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_PREFETCH_MEM_64BITS BIT(21) +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_IO_ENABLE BIT(22) +#define CDNS_PCIE_HPA_LM_RC_BAR_CFG_IO_32BITS BIT(23) + +/* BAR control values applicable to both Endpoint Function and Root Complex */ +#define CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_DISABLED 0x0 +#define CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_IO_32BITS 0x3 +#define CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_MEM_32BITS 0x1 +#define CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_PREFETCH_MEM_32BITS 0x9 +#define CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_MEM_64BITS 0x5 +#define CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_PREFETCH_MEM_64BITS 0xD + +#define HPA_LM_RC_BAR_CFG_CTRL_DISABLED(bar) \ + (CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_DISABLED << ((bar) * 10)) +#define HPA_LM_RC_BAR_CFG_CTRL_IO_32BITS(bar) \ + (CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_IO_32BITS << ((bar) * 10)) +#define HPA_LM_RC_BAR_CFG_CTRL_MEM_32BITS(bar) \ + (CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_MEM_32BITS << ((bar) * 10)) +#define HPA_LM_RC_BAR_CFG_CTRL_PREF_MEM_32BITS(bar) \ + (CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_PREFETCH_MEM_32BITS << ((bar) * 10)) +#define HPA_LM_RC_BAR_CFG_CTRL_MEM_64BITS(bar) \ + (CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_MEM_64BITS << ((bar) * 10)) +#define HPA_LM_RC_BAR_CFG_CTRL_PREF_MEM_64BITS(bar) \ + (CDNS_PCIE_HPA_LM_BAR_CFG_CTRL_PREFETCH_MEM_64BITS << ((bar) * 10)) +#define HPA_LM_RC_BAR_CFG_APERTURE(bar, aperture) \ + (((aperture) - 7) << (((bar) * 10) + 4)) + +#define CDNS_PCIE_HPA_LM_PTM_CTRL 0x0520 +#define CDNS_PCIE_HPA_LM_PTM_CTRL_PTMRSEN BIT(17) + +/* Root Port Registers PCI config space for root port function */ +#define CDNS_PCIE_HPA_RP_CAP_OFFSET 0xC0 + +/* Region r Outbound AXI to PCIe Address Translation Register 0 */ +#define CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0(r) (0x1010 + ((r) & 0x1F) * 0x0080) +#define CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_NBITS_MASK GENMASK(5, 0) +#define CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_NBITS(nbits) \ + (((nbits) - 1) & CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_NBITS_MASK) +#define CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_DEVFN_MASK GENMASK(23, 16) +#define CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_DEVFN(devfn) \ + FIELD_PREP(CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_DEVFN_MASK, devfn) +#define CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_BUS_MASK GENMASK(31, 24) +#define CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_BUS(bus) \ + FIELD_PREP(CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_BUS_MASK, bus) + +/* Region r Outbound AXI to PCIe Address Translation Register 1 */ +#define CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR1(r) (0x1014 + ((r) & 0x1F) * 0x0080) + +/* Region r Outbound PCIe Descriptor Register */ +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC0(r) (0x1008 + ((r) & 0x1F) * 0x0080) +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_MASK GENMASK(28, 24) +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_MEM \ + FIELD_PREP(CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_MASK, 0x0) +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_IO \ + FIELD_PREP(CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_MASK, 0x2) +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_CONF_TYPE0 \ + FIELD_PREP(CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_MASK, 0x4) +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_CONF_TYPE1 \ + FIELD_PREP(CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_MASK, 0x5) +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_NORMAL_MSG \ + FIELD_PREP(CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_MASK, 0x10) + +/* Region r Outbound PCIe Descriptor Register */ +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC1(r) (0x100C + ((r) & 0x1F) * 0x0080) +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC1_BUS_MASK GENMASK(31, 24) +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC1_BUS(bus) \ + FIELD_PREP(CDNS_PCIE_HPA_AT_OB_REGION_DESC1_BUS_MASK, bus) +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC1_DEVFN_MASK GENMASK(23, 16) +#define CDNS_PCIE_HPA_AT_OB_REGION_DESC1_DEVFN(devfn) \ + FIELD_PREP(CDNS_PCIE_HPA_AT_OB_REGION_DESC1_DEVFN_MASK, devfn) + +#define CDNS_PCIE_HPA_AT_OB_REGION_CTRL0(r) (0x1018 + ((r) & 0x1F) * 0x0080) +#define CDNS_PCIE_HPA_AT_OB_REGION_CTRL0_SUPPLY_BUS BIT(26) +#define CDNS_PCIE_HPA_AT_OB_REGION_CTRL0_SUPPLY_DEV_FN BIT(25) + +/* Region r AXI Region Base Address Register 0 */ +#define CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0(r) (0x1000 + ((r) & 0x1F) * 0x0080) +#define CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0_NBITS_MASK GENMASK(5, 0) +#define CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0_NBITS(nbits) \ + (((nbits) - 1) & CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0_NBITS_MASK) + +/* Region r AXI Region Base Address Register 1 */ +#define CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR1(r) (0x1004 + ((r) & 0x1F) * 0x0080) + +/* Root Port BAR Inbound PCIe to AXI Address Translation Register */ +#define CDNS_PCIE_HPA_AT_IB_RP_BAR_ADDR0(bar) (((bar) * 0x0008)) +#define CDNS_PCIE_HPA_AT_IB_RP_BAR_ADDR0_NBITS_MASK GENMASK(5, 0) +#define CDNS_PCIE_HPA_AT_IB_RP_BAR_ADDR0_NBITS(nbits) \ + (((nbits) - 1) & CDNS_PCIE_HPA_AT_IB_RP_BAR_ADDR0_NBITS_MASK) +#define CDNS_PCIE_HPA_AT_IB_RP_BAR_ADDR1(bar) (0x04 + ((bar) * 0x0008)) + +/* AXI link down register */ +#define CDNS_PCIE_HPA_AT_LINKDOWN 0x04 + +/* + * Physical Layer Configuration Register 0 + * This register contains the parameters required for functional setup + * of Physical Layer. + */ +#define CDNS_PCIE_HPA_PHY_LAYER_CFG0 0x0400 +#define CDNS_PCIE_HPA_DETECT_QUIET_MIN_DELAY_MASK GENMASK(26, 24) +#define CDNS_PCIE_HPA_DETECT_QUIET_MIN_DELAY(delay) \ + FIELD_PREP(CDNS_PCIE_HPA_DETECT_QUIET_MIN_DELAY_MASK, delay) +#define CDNS_PCIE_HPA_LINK_TRNG_EN_MASK GENMASK(27, 27) + +#define CDNS_PCIE_HPA_PHY_DBG_STS_REG0 0x0420 + +#define CDNS_PCIE_HPA_RP_MAX_IB 0x3 +#define CDNS_PCIE_HPA_MAX_OB 15 + +/* Endpoint Function BAR Inbound PCIe to AXI Address Translation Register */ +#define CDNS_PCIE_HPA_AT_IB_EP_FUNC_BAR_ADDR0(fn, bar) (((fn) * 0x0080) + ((bar) * 0x0008)) +#define CDNS_PCIE_HPA_AT_IB_EP_FUNC_BAR_ADDR1(fn, bar) (0x4 + ((fn) * 0x0080) + ((bar) * 0x0008)) + +/* Miscellaneous offsets definitions */ +#define CDNS_PCIE_HPA_TAG_MANAGEMENT 0x0 +#define CDNS_PCIE_HPA_SLAVE_RESP 0x100 + +#define I_ROOT_PORT_REQ_ID_REG 0x141c +#define LM_HAL_SBSA_CTRL 0x1170 + +#define I_PCIE_BUS_NUMBERS (CDNS_PCIE_HPA_RP_BASE + 0x18) +#define CDNS_PCIE_EROM 0x18 +#endif /* _PCIE_CADENCE_HPA_REGS_H */ diff --git a/drivers/pci/controller/cadence/pcie-cadence-hpa.c b/drivers/pci/controller/cadence/pcie-cadence-hpa.c new file mode 100644 index 000000000000..f60a16938265 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-hpa.c @@ -0,0 +1,167 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Cadence PCIe controller driver. + * + * Copyright (c) 2024, Cadence Design Systems + * Author: Manikandan K Pillai <mpillai@cadence.com> + */ +#include <linux/kernel.h> +#include <linux/of.h> + +#include "pcie-cadence.h" + +bool cdns_pcie_hpa_link_up(struct cdns_pcie *pcie) +{ + u32 pl_reg_val; + + pl_reg_val = cdns_pcie_hpa_readl(pcie, REG_BANK_IP_REG, CDNS_PCIE_HPA_PHY_DBG_STS_REG0); + if (pl_reg_val & GENMASK(0, 0)) + return true; + return false; +} +EXPORT_SYMBOL_GPL(cdns_pcie_hpa_link_up); + +void cdns_pcie_hpa_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_hpa_readl(pcie, REG_BANK_IP_REG, + CDNS_PCIE_HPA_PHY_LAYER_CFG0); + ltssm_control_cap = ((ltssm_control_cap & + ~CDNS_PCIE_HPA_DETECT_QUIET_MIN_DELAY_MASK) | + CDNS_PCIE_HPA_DETECT_QUIET_MIN_DELAY(delay)); + + cdns_pcie_hpa_writel(pcie, REG_BANK_IP_REG, + CDNS_PCIE_HPA_PHY_LAYER_CFG0, ltssm_control_cap); +} +EXPORT_SYMBOL_GPL(cdns_pcie_hpa_detect_quiet_min_delay_set); + +void cdns_pcie_hpa_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, ctrl0; + + if (nbits < 8) + nbits = 8; + + /* Set the PCI address */ + addr0 = CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0_NBITS(nbits) | + (lower_32_bits(pci_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(pci_addr); + + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0(r), addr0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR1(r), addr1); + + /* Set the PCIe header descriptor */ + if (is_io) + desc0 = CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_IO; + else + desc0 = CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_MEM; + desc1 = 0; + ctrl0 = 0; + + /* + * Whether Bit [26] is set or not inside DESC0 register of the outbound + * PCIe descriptor, the PCI function number must be set into + * Bits [31:24] of DESC1 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 [26] is mandatory when in Root Complex mode: + * then the driver must provide the bus, resp. device, number in + * Bits [31:24] of DESC1, resp. Bits[23:16] 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 [26] 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 */ + desc1 = CDNS_PCIE_HPA_AT_OB_REGION_DESC1_BUS(busnr) | + CDNS_PCIE_HPA_AT_OB_REGION_DESC1_DEVFN(0); + ctrl0 = CDNS_PCIE_HPA_AT_OB_REGION_CTRL0_SUPPLY_BUS | + CDNS_PCIE_HPA_AT_OB_REGION_CTRL0_SUPPLY_DEV_FN; + } else { + /* + * Use captured values for bus and device numbers but still + * need to set the function number + */ + desc1 |= CDNS_PCIE_HPA_AT_OB_REGION_DESC1_DEVFN(fn); + } + + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC0(r), desc0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC1(r), desc1); + + addr0 = CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0_NBITS(nbits) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0(r), addr0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR1(r), addr1); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CTRL0(r), ctrl0); +} +EXPORT_SYMBOL_GPL(cdns_pcie_hpa_set_outbound_region); + +void cdns_pcie_hpa_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, + u8 busnr, u8 fn, + u32 r, u64 cpu_addr) +{ + u32 addr0, addr1, desc0, desc1, ctrl0; + + desc0 = CDNS_PCIE_HPA_AT_OB_REGION_DESC0_TYPE_NORMAL_MSG; + desc1 = 0; + ctrl0 = 0; + + /* See cdns_pcie_set_outbound_region() comments above */ + if (pcie->is_rc) { + desc1 = CDNS_PCIE_HPA_AT_OB_REGION_DESC1_BUS(busnr) | + CDNS_PCIE_HPA_AT_OB_REGION_DESC1_DEVFN(0); + ctrl0 = CDNS_PCIE_HPA_AT_OB_REGION_CTRL0_SUPPLY_BUS | + CDNS_PCIE_HPA_AT_OB_REGION_CTRL0_SUPPLY_DEV_FN; + } else { + desc1 |= CDNS_PCIE_HPA_AT_OB_REGION_DESC1_DEVFN(fn); + } + + addr0 = CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0_NBITS(17) | + (lower_32_bits(cpu_addr) & GENMASK(31, 8)); + addr1 = upper_32_bits(cpu_addr); + + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR0(r), 0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_PCI_ADDR1(r), 0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC0(r), desc0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_DESC1(r), desc1); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR0(r), addr0); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CPU_ADDR1(r), addr1); + cdns_pcie_hpa_writel(pcie, REG_BANK_AXI_SLAVE, + CDNS_PCIE_HPA_AT_OB_REGION_CTRL0(r), ctrl0); +} +EXPORT_SYMBOL_GPL(cdns_pcie_hpa_set_outbound_region_for_normal_msg); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence PCIe controller driver"); diff --git a/drivers/pci/controller/cadence/pcie-cadence-lga-regs.h b/drivers/pci/controller/cadence/pcie-cadence-lga-regs.h new file mode 100644 index 000000000000..857b2140c5d2 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-lga-regs.h @@ -0,0 +1,230 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Cadence PCIe controller driver. + * + * Copyright (c) 2017 Cadence + * Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> + */ +#ifndef _PCIE_CADENCE_LGA_REGS_H +#define _PCIE_CADENCE_LGA_REGS_H + +#include <linux/bitfield.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 Requester 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 + +/* Endpoint PF Registers */ +#define CDNS_PCIE_CORE_PF_I_ARI_CAP_AND_CTRL(fn) (0x144 + (fn) * 0x1000) +#define CDNS_PCIE_ARI_CAP_NFN_MASK GENMASK(15, 8) + +/* 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) + +#define CDNS_PCIE_RP_MAX_IB 0x3 +#define CDNS_PCIE_MAX_OB 32 + +/* 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) + +#endif /* _PCIE_CADENCE_LGA_REGS_H */ diff --git a/drivers/pci/controller/cadence/pcie-cadence-plat.c b/drivers/pci/controller/cadence/pcie-cadence-plat.c index 0456845dabb9..b067a3296dd3 100644 --- a/drivers/pci/controller/cadence/pcie-cadence-plat.c +++ b/drivers/pci/controller/cadence/pcie-cadence-plat.c @@ -22,10 +22,6 @@ struct cdns_plat_pcie { struct cdns_pcie *pcie; }; -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) @@ -177,4 +173,7 @@ static struct platform_driver cdns_plat_pcie_driver = { .probe = cdns_plat_pcie_probe, .shutdown = cdns_plat_pcie_shutdown, }; -builtin_platform_driver(cdns_plat_pcie_driver); +module_platform_driver(cdns_plat_pcie_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence PCIe controller platform driver"); diff --git a/drivers/pci/controller/cadence/pcie-cadence.c b/drivers/pci/controller/cadence/pcie-cadence.c index 4251fac5e310..e6f1a4ac0fb7 100644 --- a/drivers/pci/controller/cadence/pcie-cadence.c +++ b/drivers/pci/controller/cadence/pcie-cadence.c @@ -4,9 +4,35 @@ // Author: Cyrille Pitchen <cyrille.pitchen@free-electrons.com> #include <linux/kernel.h> +#include <linux/module.h> #include <linux/of.h> #include "pcie-cadence.h" +#include "../../pci.h" + +u8 cdns_pcie_find_capability(struct cdns_pcie *pcie, u8 cap) +{ + return PCI_FIND_NEXT_CAP(cdns_pcie_read_cfg, PCI_CAPABILITY_LIST, + cap, pcie); +} +EXPORT_SYMBOL_GPL(cdns_pcie_find_capability); + +u16 cdns_pcie_find_ext_capability(struct cdns_pcie *pcie, u8 cap) +{ + return PCI_FIND_NEXT_EXT_CAP(cdns_pcie_read_cfg, 0, cap, pcie); +} +EXPORT_SYMBOL_GPL(cdns_pcie_find_ext_capability); + +bool cdns_pcie_linkup(struct cdns_pcie *pcie) +{ + u32 pl_reg_val; + + pl_reg_val = cdns_pcie_readl(pcie, CDNS_PCIE_LM_BASE); + if (pl_reg_val & GENMASK(0, 0)) + return true; + return false; +} +EXPORT_SYMBOL_GPL(cdns_pcie_linkup); void cdns_pcie_detect_quiet_min_delay_set(struct cdns_pcie *pcie) { @@ -23,6 +49,7 @@ void cdns_pcie_detect_quiet_min_delay_set(struct cdns_pcie *pcie) cdns_pcie_writel(pcie, CDNS_PCIE_LTSSM_CONTROL_CAP, ltssm_control_cap); } +EXPORT_SYMBOL_GPL(cdns_pcie_detect_quiet_min_delay_set); void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 busnr, u8 fn, u32 r, bool is_io, @@ -90,7 +117,7 @@ void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 busnr, u8 fn, cdns_pcie_writel(pcie, CDNS_PCIE_AT_OB_REGION_DESC1(r), desc1); /* Set the CPU address */ - if (pcie->ops->cpu_addr_fixup) + if (pcie->ops && 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) | @@ -100,6 +127,7 @@ void cdns_pcie_set_outbound_region(struct cdns_pcie *pcie, u8 busnr, u8 fn, 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); } +EXPORT_SYMBOL_GPL(cdns_pcie_set_outbound_region); void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, u8 busnr, u8 fn, @@ -120,7 +148,7 @@ void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, } /* Set the CPU address */ - if (pcie->ops->cpu_addr_fixup) + if (pcie->ops && 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) | @@ -134,6 +162,7 @@ void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, 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); } +EXPORT_SYMBOL_GPL(cdns_pcie_set_outbound_region_for_normal_msg); void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r) { @@ -146,6 +175,7 @@ void cdns_pcie_reset_outbound_region(struct cdns_pcie *pcie, u32 r) 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); } +EXPORT_SYMBOL_GPL(cdns_pcie_reset_outbound_region); void cdns_pcie_disable_phy(struct cdns_pcie *pcie) { @@ -156,6 +186,7 @@ void cdns_pcie_disable_phy(struct cdns_pcie *pcie) phy_exit(pcie->phy[i]); } } +EXPORT_SYMBOL_GPL(cdns_pcie_disable_phy); int cdns_pcie_enable_phy(struct cdns_pcie *pcie) { @@ -184,6 +215,7 @@ err_phy: return ret; } +EXPORT_SYMBOL_GPL(cdns_pcie_enable_phy); int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie) { @@ -197,7 +229,7 @@ int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie) 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"); + dev_info(dev, "no \"phy-names\" property found; PHY will not be initialized\n"); pcie->phy_count = 0; return 0; } @@ -243,6 +275,7 @@ err_phy: return ret; } +EXPORT_SYMBOL_GPL(cdns_pcie_init_phy); static int cdns_pcie_suspend_noirq(struct device *dev) { @@ -260,7 +293,7 @@ static int cdns_pcie_resume_noirq(struct device *dev) ret = cdns_pcie_enable_phy(pcie); if (ret) { - dev_err(dev, "failed to enable phy\n"); + dev_err(dev, "failed to enable PHY\n"); return ret; } @@ -271,3 +304,8 @@ const struct dev_pm_ops cdns_pcie_pm_ops = { NOIRQ_SYSTEM_SLEEP_PM_OPS(cdns_pcie_suspend_noirq, cdns_pcie_resume_noirq) }; +EXPORT_SYMBOL_GPL(cdns_pcie_pm_ops); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Cadence PCIe controller driver"); +MODULE_AUTHOR("Cyrille Pitchen <cyrille.pitchen@free-electrons.com>"); diff --git a/drivers/pci/controller/cadence/pcie-cadence.h b/drivers/pci/controller/cadence/pcie-cadence.h index f5eeff834ec1..443033c607d7 100644 --- a/drivers/pci/controller/cadence/pcie-cadence.h +++ b/drivers/pci/controller/cadence/pcie-cadence.h @@ -7,216 +7,12 @@ #define _PCIE_CADENCE_H #include <linux/kernel.h> +#include <linux/module.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 Requester 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 - -/* - * Endpoint PF Registers - */ -#define CDNS_PCIE_CORE_PF_I_ARI_CAP_AND_CTRL(fn) (0x144 + (fn) * 0x1000) -#define CDNS_PCIE_ARI_CAP_NFN_MASK GENMASK(15, 8) - -/* - * 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) +#include "pcie-cadence-lga-regs.h" +#include "pcie-cadence-hpa-regs.h" enum cdns_pcie_rp_bar { RP_BAR_UNDEFINED = -1, @@ -225,73 +21,63 @@ enum cdns_pcie_rp_bar { 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_rc; + +enum cdns_pcie_reg_bank { + REG_BANK_RP, + REG_BANK_IP_REG, + REG_BANK_IP_CFG_CTRL_REG, + REG_BANK_AXI_MASTER_COMMON, + REG_BANK_AXI_MASTER, + REG_BANK_AXI_SLAVE, + REG_BANK_AXI_HLS, + REG_BANK_AXI_RAS, + REG_BANK_AXI_DTI, + REG_BANKS_MAX, }; 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); + 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_plat_pcie_of_data - Register bank offset for a platform + * @is_rc: controller is a RC + * @ip_reg_bank_offset: ip register bank start offset + * @ip_cfg_ctrl_reg_offset: ip config control register start offset + * @axi_mstr_common_offset: AXI master common register start offset + * @axi_slave_offset: AXI slave start offset + * @axi_master_offset: AXI master start offset + * @axi_hls_offset: AXI HLS offset start + * @axi_ras_offset: AXI RAS offset + * @axi_dti_offset: AXI DTI offset + */ +struct cdns_plat_pcie_of_data { + u32 is_rc:1; + u32 ip_reg_bank_offset; + u32 ip_cfg_ctrl_reg_offset; + u32 axi_mstr_common_offset; + u32 axi_slave_offset; + u32 axi_master_offset; + u32 axi_hls_offset; + u32 axi_ras_offset; + u32 axi_dti_offset; +}; + +/** * 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 + * @msg_res: Region for send message 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 @@ -299,16 +85,19 @@ struct cdns_pcie_ops { * @link: list of pointers to corresponding device link representations * @ops: Platform-specific ops to control various inputs from Cadence PCIe * wrapper + * @cdns_pcie_reg_offsets: Register bank offsets for different SoC */ 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; + void __iomem *reg_base; + struct resource *mem_res; + struct resource *msg_res; + struct device *dev; + bool is_rc; + int phy_count; + struct phy **phy; + struct device_link **link; + const struct cdns_pcie_ops *ops; + const struct cdns_plat_pcie_of_data *cdns_pcie_reg_offsets; }; /** @@ -324,6 +113,8 @@ struct cdns_pcie { * available * @quirk_retrain_flag: Retrain link as quirk for PCIe Gen2 * @quirk_detect_quiet_flag: LTSSM Detect Quiet min delay set as quirk + * @ecam_supported: Whether the ECAM is supported + * @no_inbound_map: Whether inbound mapping is supported */ struct cdns_pcie_rc { struct cdns_pcie pcie; @@ -334,6 +125,8 @@ struct cdns_pcie_rc { bool avail_ib_bar[CDNS_PCIE_RP_MAX_IB]; unsigned int quirk_retrain_flag:1; unsigned int quirk_detect_quiet_flag:1; + unsigned int ecam_supported:1; + unsigned int no_inbound_map:1; }; /** @@ -386,6 +179,43 @@ struct cdns_pcie_ep { unsigned int quirk_disable_flr:1; }; +static inline u32 cdns_reg_bank_to_off(struct cdns_pcie *pcie, enum cdns_pcie_reg_bank bank) +{ + u32 offset = 0x0; + + switch (bank) { + case REG_BANK_RP: + offset = 0; + break; + case REG_BANK_IP_REG: + offset = pcie->cdns_pcie_reg_offsets->ip_reg_bank_offset; + break; + case REG_BANK_IP_CFG_CTRL_REG: + offset = pcie->cdns_pcie_reg_offsets->ip_cfg_ctrl_reg_offset; + break; + case REG_BANK_AXI_MASTER_COMMON: + offset = pcie->cdns_pcie_reg_offsets->axi_mstr_common_offset; + break; + case REG_BANK_AXI_MASTER: + offset = pcie->cdns_pcie_reg_offsets->axi_master_offset; + break; + case REG_BANK_AXI_SLAVE: + offset = pcie->cdns_pcie_reg_offsets->axi_slave_offset; + break; + case REG_BANK_AXI_HLS: + offset = pcie->cdns_pcie_reg_offsets->axi_hls_offset; + break; + case REG_BANK_AXI_RAS: + offset = pcie->cdns_pcie_reg_offsets->axi_ras_offset; + break; + case REG_BANK_AXI_DTI: + offset = pcie->cdns_pcie_reg_offsets->axi_dti_offset; + break; + default: + break; + } + return offset; +} /* Register access */ static inline void cdns_pcie_writel(struct cdns_pcie *pcie, u32 reg, u32 value) @@ -398,6 +228,58 @@ static inline u32 cdns_pcie_readl(struct cdns_pcie *pcie, u32 reg) return readl(pcie->reg_base + reg); } +static inline void cdns_pcie_hpa_writel(struct cdns_pcie *pcie, + enum cdns_pcie_reg_bank bank, + u32 reg, + u32 value) +{ + u32 offset = cdns_reg_bank_to_off(pcie, bank); + + reg += offset; + writel(value, pcie->reg_base + reg); +} + +static inline u32 cdns_pcie_hpa_readl(struct cdns_pcie *pcie, + enum cdns_pcie_reg_bank bank, + u32 reg) +{ + u32 offset = cdns_reg_bank_to_off(pcie, bank); + + reg += offset; + return readl(pcie->reg_base + reg); +} + +static inline u16 cdns_pcie_readw(struct cdns_pcie *pcie, u32 reg) +{ + return readw(pcie->reg_base + reg); +} + +static inline u8 cdns_pcie_readb(struct cdns_pcie *pcie, u32 reg) +{ + return readb(pcie->reg_base + reg); +} + +static inline int cdns_pcie_read_cfg_byte(struct cdns_pcie *pcie, int where, + u8 *val) +{ + *val = cdns_pcie_readb(pcie, where); + return PCIBIOS_SUCCESSFUL; +} + +static inline int cdns_pcie_read_cfg_word(struct cdns_pcie *pcie, int where, + u16 *val) +{ + *val = cdns_pcie_readw(pcie, where); + return PCIBIOS_SUCCESSFUL; +} + +static inline int cdns_pcie_read_cfg_dword(struct cdns_pcie *pcie, int where, + u32 *val) +{ + *val = cdns_pcie_readl(pcie, where); + return PCIBIOS_SUCCESSFUL; +} + static inline u32 cdns_pcie_read_sz(void __iomem *addr, int size) { void __iomem *aligned_addr = PTR_ALIGN_DOWN(addr, 0x4); @@ -462,6 +344,29 @@ static inline u16 cdns_pcie_rp_readw(struct cdns_pcie *pcie, u32 reg) return cdns_pcie_read_sz(addr, 0x2); } +static inline void cdns_pcie_hpa_rp_writeb(struct cdns_pcie *pcie, + u32 reg, u8 value) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_HPA_RP_BASE + reg; + + cdns_pcie_write_sz(addr, 0x1, value); +} + +static inline void cdns_pcie_hpa_rp_writew(struct cdns_pcie *pcie, + u32 reg, u16 value) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_HPA_RP_BASE + reg; + + cdns_pcie_write_sz(addr, 0x2, value); +} + +static inline u16 cdns_pcie_hpa_rp_readw(struct cdns_pcie *pcie, u32 reg) +{ + void __iomem *addr = pcie->reg_base + CDNS_PCIE_HPA_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) @@ -499,7 +404,7 @@ static inline u32 cdns_pcie_ep_fn_readl(struct cdns_pcie *pcie, u8 fn, u32 reg) static inline int cdns_pcie_start_link(struct cdns_pcie *pcie) { - if (pcie->ops->start_link) + if (pcie->ops && pcie->ops->start_link) return pcie->ops->start_link(pcie); return 0; @@ -507,24 +412,26 @@ static inline int cdns_pcie_start_link(struct cdns_pcie *pcie) static inline void cdns_pcie_stop_link(struct cdns_pcie *pcie) { - if (pcie->ops->stop_link) + if (pcie->ops && 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) + if (pcie->ops && pcie->ops->link_up) return pcie->ops->link_up(pcie); return true; } -#ifdef CONFIG_PCIE_CADENCE_HOST +#if IS_ENABLED(CONFIG_PCIE_CADENCE_HOST) int cdns_pcie_host_link_setup(struct cdns_pcie_rc *rc); int cdns_pcie_host_init(struct cdns_pcie_rc *rc); int cdns_pcie_host_setup(struct cdns_pcie_rc *rc); +void cdns_pcie_host_disable(struct cdns_pcie_rc *rc); void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn, int where); +int cdns_pcie_hpa_host_setup(struct cdns_pcie_rc *rc); #else static inline int cdns_pcie_host_link_setup(struct cdns_pcie_rc *rc) { @@ -541,6 +448,15 @@ static inline int cdns_pcie_host_setup(struct cdns_pcie_rc *rc) return 0; } +static inline int cdns_pcie_hpa_host_setup(struct cdns_pcie_rc *rc) +{ + return 0; +} + +static inline void cdns_pcie_host_disable(struct cdns_pcie_rc *rc) +{ +} + static inline void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int devfn, int where) { @@ -548,15 +464,31 @@ static inline void __iomem *cdns_pci_map_bus(struct pci_bus *bus, unsigned int d } #endif -#ifdef CONFIG_PCIE_CADENCE_EP +#if IS_ENABLED(CONFIG_PCIE_CADENCE_EP) int cdns_pcie_ep_setup(struct cdns_pcie_ep *ep); +void cdns_pcie_ep_disable(struct cdns_pcie_ep *ep); +int cdns_pcie_hpa_ep_setup(struct cdns_pcie_ep *ep); #else static inline int cdns_pcie_ep_setup(struct cdns_pcie_ep *ep) { return 0; } + +static inline void cdns_pcie_ep_disable(struct cdns_pcie_ep *ep) +{ +} + +static inline int cdns_pcie_hpa_ep_setup(struct cdns_pcie_ep *ep) +{ + return 0; +} + #endif +u8 cdns_pcie_find_capability(struct cdns_pcie *pcie, u8 cap); +u16 cdns_pcie_find_ext_capability(struct cdns_pcie *pcie, u8 cap); +bool cdns_pcie_linkup(struct cdns_pcie *pcie); + 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, @@ -569,8 +501,23 @@ void cdns_pcie_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, 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); +int cdns_pcie_enable_phy(struct cdns_pcie *pcie); +int cdns_pcie_init_phy(struct device *dev, struct cdns_pcie *pcie); +void cdns_pcie_hpa_detect_quiet_min_delay_set(struct cdns_pcie *pcie); +void cdns_pcie_hpa_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_hpa_set_outbound_region_for_normal_msg(struct cdns_pcie *pcie, + u8 busnr, u8 fn, + u32 r, u64 cpu_addr); +int cdns_pcie_hpa_host_link_setup(struct cdns_pcie_rc *rc); +void __iomem *cdns_pci_hpa_map_bus(struct pci_bus *bus, unsigned int devfn, + int where); +int cdns_pcie_hpa_host_start_link(struct cdns_pcie_rc *rc); +int cdns_pcie_hpa_start_link(struct cdns_pcie *pcie); +void cdns_pcie_hpa_stop_link(struct cdns_pcie *pcie); +bool cdns_pcie_hpa_link_up(struct cdns_pcie *pcie); + extern const struct dev_pm_ops cdns_pcie_pm_ops; #endif /* _PCIE_CADENCE_H */ diff --git a/drivers/pci/controller/cadence/pcie-sg2042.c b/drivers/pci/controller/cadence/pcie-sg2042.c new file mode 100644 index 000000000000..0c50c74d03ee --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-sg2042.c @@ -0,0 +1,131 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * pcie-sg2042 - PCIe controller driver for Sophgo SG2042 SoC + * + * Copyright (C) 2025 Sophgo Technology Inc. + * Copyright (C) 2025 Chen Wang <unicorn_wang@outlook.com> + */ + +#include <linux/mod_devicetable.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> + +#include "pcie-cadence.h" + +/* + * SG2042 only supports 4-byte aligned access, so for the rootbus (i.e. to + * read/write the Root Port itself, read32/write32 is required. For + * non-rootbus (i.e. to read/write the PCIe peripheral registers, supports + * 1/2/4 byte aligned access, so directly using read/write should be fine. + */ + +static struct pci_ops sg2042_pcie_root_ops = { + .map_bus = cdns_pci_map_bus, + .read = pci_generic_config_read32, + .write = pci_generic_config_write32, +}; + +static struct pci_ops sg2042_pcie_child_ops = { + .map_bus = cdns_pci_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, +}; + +static int sg2042_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + struct cdns_pcie *pcie; + struct cdns_pcie_rc *rc; + int ret; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*rc)); + if (!bridge) + return dev_err_probe(dev, -ENOMEM, "Failed to alloc host bridge!\n"); + + bridge->ops = &sg2042_pcie_root_ops; + bridge->child_ops = &sg2042_pcie_child_ops; + + rc = pci_host_bridge_priv(bridge); + pcie = &rc->pcie; + pcie->dev = dev; + + platform_set_drvdata(pdev, pcie); + + pm_runtime_set_active(dev); + pm_runtime_no_callbacks(dev); + devm_pm_runtime_enable(dev); + + ret = cdns_pcie_init_phy(dev, pcie); + if (ret) + return dev_err_probe(dev, ret, "Failed to init phy!\n"); + + ret = cdns_pcie_host_setup(rc); + if (ret) { + dev_err_probe(dev, ret, "Failed to setup host!\n"); + cdns_pcie_disable_phy(pcie); + return ret; + } + + return 0; +} + +static void sg2042_pcie_remove(struct platform_device *pdev) +{ + struct cdns_pcie *pcie = platform_get_drvdata(pdev); + struct cdns_pcie_rc *rc; + + rc = container_of(pcie, struct cdns_pcie_rc, pcie); + cdns_pcie_host_disable(rc); + + cdns_pcie_disable_phy(pcie); +} + +static int sg2042_pcie_suspend_noirq(struct device *dev) +{ + struct cdns_pcie *pcie = dev_get_drvdata(dev); + + cdns_pcie_disable_phy(pcie); + + return 0; +} + +static int sg2042_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; +} + +static DEFINE_NOIRQ_DEV_PM_OPS(sg2042_pcie_pm_ops, + sg2042_pcie_suspend_noirq, + sg2042_pcie_resume_noirq); + +static const struct of_device_id sg2042_pcie_of_match[] = { + { .compatible = "sophgo,sg2042-pcie-host" }, + {}, +}; +MODULE_DEVICE_TABLE(of, sg2042_pcie_of_match); + +static struct platform_driver sg2042_pcie_driver = { + .driver = { + .name = "sg2042-pcie", + .of_match_table = sg2042_pcie_of_match, + .pm = pm_sleep_ptr(&sg2042_pcie_pm_ops), + }, + .probe = sg2042_pcie_probe, + .remove = sg2042_pcie_remove, +}; +module_platform_driver(sg2042_pcie_driver); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("PCIe controller driver for SG2042 SoCs"); +MODULE_AUTHOR("Chen Wang <unicorn_wang@outlook.com>"); diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig index b6d6778b0698..519b59422b47 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -6,9 +6,21 @@ menu "DesignWare-based PCIe controllers" config PCIE_DW bool +config PCIE_DW_DEBUGFS + bool "DesignWare PCIe debugfs entries" + depends on DEBUG_FS + depends on PCIE_DW_HOST || PCIE_DW_EP + help + Say Y here to enable debugfs entries for the PCIe controller. These + entries provide various debug features related to the controller and + expose the RAS DES capabilities such as Silicon Debug, Error Injection + and Statistical Counters. + config PCIE_DW_HOST bool select PCIE_DW + select IRQ_MSI_LIB + select PCI_HOST_COMMON config PCIE_DW_EP bool @@ -27,6 +39,17 @@ config PCIE_AL required only for DT-based platforms. ACPI platforms with the Annapurna Labs PCIe controller don't need to enable this. +config PCIE_AMD_MDB + bool "AMD MDB Versal2 PCIe controller" + depends on OF && (ARM64 || COMPILE_TEST) + depends on PCI_MSI + select PCIE_DW_HOST + help + Say Y here if you want to enable PCIe controller support on AMD + Versal2 SoCs. The AMD MDB Versal2 PCIe controller is based on + DesignWare IP and therefore the driver re-uses the DesignWare + core functions to implement the driver. + config PCI_MESON tristate "Amlogic Meson PCIe controller" default m if ARCH_MESON @@ -233,6 +256,16 @@ config PCIE_TEGRA194_EP in order to enable device-specific features PCIE_TEGRA194_EP must be selected. This uses the DesignWare core. +config PCIE_NXP_S32G + bool "NXP S32G PCIe controller (host mode)" + depends on ARCH_S32 || COMPILE_TEST + select PCIE_DW_HOST + help + Enable support for the PCIe controller in NXP S32G based boards to + work in Host mode. The controller is based on DesignWare IP and + can work either as RC or EP. In order to enable host-specific + features PCIE_NXP_S32G must be selected. + config PCIE_DW_PLAT bool @@ -275,6 +308,8 @@ config PCIE_QCOM select PCIE_DW_HOST select CRC8 select PCIE_QCOM_COMMON + select PCI_HOST_COMMON + select PCI_PWRCTRL_SLOT help Say Y here to enable PCIe controller support on Qualcomm SoCs. The PCIe controller uses the DesignWare core plus Qualcomm-specific @@ -381,6 +416,29 @@ config PCIE_UNIPHIER_EP Say Y here if you want PCIe endpoint controller support on UniPhier SoCs. This driver supports Pro5 SoC. +config PCIE_SOPHGO_DW + bool "Sophgo DesignWare PCIe controller (host mode)" + depends on ARCH_SOPHGO || COMPILE_TEST + depends on PCI_MSI + depends on OF + select PCIE_DW_HOST + help + Say Y here if you want PCIe host controller support on + Sophgo SoCs. + +config PCIE_SPACEMIT_K1 + tristate "SpacemiT K1 PCIe controller (host mode)" + depends on ARCH_SPACEMIT || COMPILE_TEST + depends on HAS_IOMEM + select PCIE_DW_HOST + select PCI_PWRCTRL_SLOT + default ARCH_SPACEMIT + help + Enables support for the DesignWare based PCIe controller in + the SpacemiT K1 SoC operating in host mode. Three controllers + are available on the K1 SoC; the first of these shares a PHY + with a USB 3.0 host controller (one or the other can be used). + config PCIE_SPEAR13XX bool "STMicroelectronics SPEAr PCIe controller" depends on ARCH_SPEAR13XX || COMPILE_TEST @@ -389,6 +447,30 @@ config PCIE_SPEAR13XX help Say Y here if you want PCIe support on SPEAr13XX SoCs. +config PCIE_STM32_HOST + tristate "STMicroelectronics STM32MP25 PCIe Controller (host mode)" + depends on ARCH_STM32 || COMPILE_TEST + depends on PCI_MSI + select PCIE_DW_HOST + help + Enables Root Complex (RC) support for the DesignWare core based PCIe + controller found in STM32MP25 SoC. + + This driver can also be built as a module. If so, the module + will be called pcie-stm32. + +config PCIE_STM32_EP + tristate "STMicroelectronics STM32MP25 PCIe Controller (endpoint mode)" + depends on ARCH_STM32 || COMPILE_TEST + depends on PCI_ENDPOINT + select PCIE_DW_EP + help + Enables Endpoint (EP) support for the DesignWare core based PCIe + controller found in STM32MP25 SoC. + + This driver can also be built as a module. If so, the module + will be called pcie-stm32-ep. + config PCI_DRA7XX tristate @@ -423,15 +505,21 @@ config PCI_DRA7XX_EP to enable device-specific features PCI_DRA7XX_EP must be selected. This uses the DesignWare core. +# ARM32 platforms use hook_fault_code() and cannot support loadable module. config PCI_KEYSTONE bool +# On non-ARM32 platforms, loadable module can be supported. +config PCI_KEYSTONE_TRISTATE + tristate + config PCI_KEYSTONE_HOST - bool "TI Keystone PCIe controller (host mode)" + tristate "TI Keystone PCIe controller (host mode)" depends on ARCH_KEYSTONE || ARCH_K3 || COMPILE_TEST depends on PCI_MSI select PCIE_DW_HOST - select PCI_KEYSTONE + select PCI_KEYSTONE if ARM + select PCI_KEYSTONE_TRISTATE if !ARM help Enables support for the PCIe controller in the Keystone SoC to work in host mode. The PCI controller on Keystone is based on @@ -439,11 +527,12 @@ config PCI_KEYSTONE_HOST DesignWare core functions to implement the driver. config PCI_KEYSTONE_EP - bool "TI Keystone PCIe controller (endpoint mode)" + tristate "TI Keystone PCIe controller (endpoint mode)" depends on ARCH_KEYSTONE || ARCH_K3 || COMPILE_TEST depends on PCI_ENDPOINT select PCIE_DW_EP - select PCI_KEYSTONE + select PCI_KEYSTONE if ARM + select PCI_KEYSTONE_TRISTATE if !ARM help Enables support for the PCIe controller in the Keystone SoC to work in endpoint mode. The PCI controller on Keystone is based diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile index a8308d9ea986..67ba59c02038 100644 --- a/drivers/pci/controller/dwc/Makefile +++ b/drivers/pci/controller/dwc/Makefile @@ -1,15 +1,21 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_PCIE_DW) += pcie-designware.o +obj-$(CONFIG_PCIE_DW_DEBUGFS) += pcie-designware-debugfs.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_PCIE_AMD_MDB) += pcie-amd-mdb.o obj-$(CONFIG_PCIE_BT1) += pcie-bt1.o obj-$(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_NXP_S32G) += pcie-nxp-s32g.o obj-$(CONFIG_PCIE_SPEAR13XX) += pcie-spear13xx.o +# ARM32 platforms use hook_fault_code() and cannot support loadable module. obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone.o +# On non-ARM32 platforms, loadable module can be supported. +obj-$(CONFIG_PCI_KEYSTONE_TRISTATE) += pci-keystone.o obj-$(CONFIG_PCI_LAYERSCAPE) += pci-layerscape.o obj-$(CONFIG_PCI_LAYERSCAPE_EP) += pci-layerscape-ep.o obj-$(CONFIG_PCIE_QCOM_COMMON) += pcie-qcom-common.o @@ -18,6 +24,7 @@ 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) += pcie-dw-rockchip.o +obj-$(CONFIG_PCIE_SOPHGO_DW) += pcie-sophgo.o obj-$(CONFIG_PCIE_INTEL_GW) += pcie-intel-gw.o obj-$(CONFIG_PCIE_KEEMBAY) += pcie-keembay.o obj-$(CONFIG_PCIE_KIRIN) += pcie-kirin.o @@ -28,6 +35,9 @@ obj-$(CONFIG_PCIE_UNIPHIER) += pcie-uniphier.o obj-$(CONFIG_PCIE_UNIPHIER_EP) += pcie-uniphier-ep.o obj-$(CONFIG_PCIE_VISCONTI_HOST) += pcie-visconti.o obj-$(CONFIG_PCIE_RCAR_GEN4) += pcie-rcar-gen4.o +obj-$(CONFIG_PCIE_SPACEMIT_K1) += pcie-spacemit-k1.o +obj-$(CONFIG_PCIE_STM32_HOST) += pcie-stm32.o +obj-$(CONFIG_PCIE_STM32_EP) += pcie-stm32-ep.o # The following drivers are for devices that use the generic ACPI # pci_root.c driver but don't support standard ECAM config access. diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c index 5c62e1a3ba52..01cfd9aeb0b8 100644 --- a/drivers/pci/controller/dwc/pci-dra7xx.c +++ b/drivers/pci/controller/dwc/pci-dra7xx.c @@ -118,12 +118,12 @@ static u64 dra7xx_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 cpu_addr) return cpu_addr & DRA7XX_CPU_TO_BUS_ADDR; } -static int dra7xx_pcie_link_up(struct dw_pcie *pci) +static bool 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); + return reg & LINK_UP; } static void dra7xx_pcie_stop_link(struct dw_pcie *pci) @@ -359,8 +359,8 @@ static int dra7xx_pcie_init_irq_domain(struct dw_pcie_rp *pp) 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); + dra7xx->irq_domain = irq_domain_create_linear(of_fwnode_handle(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"); @@ -426,7 +426,6 @@ static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, 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* @@ -635,30 +634,20 @@ static int dra7xx_pcie_unaligned_memaccess(struct device *dev) { int ret; struct device_node *np = dev->of_node; - struct of_phandle_args args; + unsigned int args[2]; struct regmap *regmap; - regmap = syscon_regmap_lookup_by_phandle(np, - "ti,syscon-unaligned-access"); + regmap = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-unaligned-access", + 2, args); 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]); + ret = regmap_update_bits(regmap, args[0], args[1], args[1]); if (ret) dev_err(dev, "failed to enable unaligned access\n"); - of_node_put(args.np); - return ret; } @@ -671,18 +660,13 @@ static int dra7xx_pcie_configure_two_lane(struct device *dev, u32 mask; u32 val; - pcie_syscon = syscon_regmap_lookup_by_phandle(np, "ti,syscon-lane-sel"); + pcie_syscon = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-lane-sel", + 1, &pcie_reg); 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); diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c index fa45da28a218..0bb7d4f5d784 100644 --- a/drivers/pci/controller/dwc/pci-exynos.c +++ b/drivers/pci/controller/dwc/pci-exynos.c @@ -53,7 +53,6 @@ struct exynos_pcie { struct dw_pcie pci; - void __iomem *elbi_base; struct clk_bulk_data *clks; struct phy *phy; struct regulator_bulk_data supplies[2]; @@ -71,73 +70,78 @@ static u32 exynos_pcie_readl(void __iomem *base, u32 reg) static void exynos_pcie_sideband_dbi_w_mode(struct exynos_pcie *ep, bool on) { + struct dw_pcie *pci = &ep->pci; u32 val; - val = exynos_pcie_readl(ep->elbi_base, PCIE_ELBI_SLV_AWMISC); + val = exynos_pcie_readl(pci->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); + exynos_pcie_writel(pci->elbi_base, val, PCIE_ELBI_SLV_AWMISC); } static void exynos_pcie_sideband_dbi_r_mode(struct exynos_pcie *ep, bool on) { + struct dw_pcie *pci = &ep->pci; u32 val; - val = exynos_pcie_readl(ep->elbi_base, PCIE_ELBI_SLV_ARMISC); + val = exynos_pcie_readl(pci->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); + exynos_pcie_writel(pci->elbi_base, val, PCIE_ELBI_SLV_ARMISC); } static void exynos_pcie_assert_core_reset(struct exynos_pcie *ep) { + struct dw_pcie *pci = &ep->pci; u32 val; - val = exynos_pcie_readl(ep->elbi_base, PCIE_CORE_RESET); + val = exynos_pcie_readl(pci->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); + exynos_pcie_writel(pci->elbi_base, val, PCIE_CORE_RESET); + exynos_pcie_writel(pci->elbi_base, 0, PCIE_STICKY_RESET); + exynos_pcie_writel(pci->elbi_base, 0, PCIE_NONSTICKY_RESET); } static void exynos_pcie_deassert_core_reset(struct exynos_pcie *ep) { + struct dw_pcie *pci = &ep->pci; u32 val; - val = exynos_pcie_readl(ep->elbi_base, PCIE_CORE_RESET); + val = exynos_pcie_readl(pci->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); + exynos_pcie_writel(pci->elbi_base, val, PCIE_CORE_RESET); + exynos_pcie_writel(pci->elbi_base, 1, PCIE_STICKY_RESET); + exynos_pcie_writel(pci->elbi_base, 1, PCIE_NONSTICKY_RESET); + exynos_pcie_writel(pci->elbi_base, 1, PCIE_APP_INIT_RESET); + exynos_pcie_writel(pci->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 = exynos_pcie_readl(pci->elbi_base, PCIE_SW_WAKE); val &= ~PCIE_BUS_EN; - exynos_pcie_writel(ep->elbi_base, val, PCIE_SW_WAKE); + exynos_pcie_writel(pci->elbi_base, val, PCIE_SW_WAKE); /* assert LTSSM enable */ - exynos_pcie_writel(ep->elbi_base, PCIE_ELBI_LTSSM_ENABLE, + exynos_pcie_writel(pci->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); + struct dw_pcie *pci = &ep->pci; - exynos_pcie_writel(ep->elbi_base, val, PCIE_IRQ_PULSE); + u32 val = exynos_pcie_readl(pci->elbi_base, PCIE_IRQ_PULSE); + + exynos_pcie_writel(pci->elbi_base, val, PCIE_IRQ_PULSE); } static irqreturn_t exynos_pcie_irq_handler(int irq, void *arg) @@ -150,12 +154,14 @@ static irqreturn_t exynos_pcie_irq_handler(int irq, void *arg) static void exynos_pcie_enable_irq_pulse(struct exynos_pcie *ep) { + struct dw_pcie *pci = &ep->pci; + 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); + exynos_pcie_writel(pci->elbi_base, val, PCIE_IRQ_EN_PULSE); + exynos_pcie_writel(pci->elbi_base, 0, PCIE_IRQ_EN_LEVEL); + exynos_pcie_writel(pci->elbi_base, 0, PCIE_IRQ_EN_SPECIAL); } static u32 exynos_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, @@ -209,12 +215,11 @@ static struct pci_ops exynos_pci_ops = { .write = exynos_pcie_wr_own_conf, }; -static int exynos_pcie_link_up(struct dw_pcie *pci) +static bool 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); + u32 val = exynos_pcie_readl(pci->elbi_base, PCIE_ELBI_RDLH_LINKUP); - return (val & PCIE_ELBI_XMLH_LINKUP); + return val & PCIE_ELBI_XMLH_LINKUP; } static int exynos_pcie_host_init(struct dw_pcie_rp *pp) @@ -295,12 +300,7 @@ static int exynos_pcie_probe(struct platform_device *pdev) 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); - - ret = devm_clk_bulk_get_all_enable(dev, &ep->clks); + ret = devm_clk_bulk_get_all_enabled(dev, &ep->clks); if (ret < 0) return ret; @@ -383,7 +383,7 @@ static const struct of_device_id exynos_pcie_of_match[] = { static struct platform_driver exynos_pcie_driver = { .probe = exynos_pcie_probe, - .remove_new = exynos_pcie_remove, + .remove = exynos_pcie_remove, .driver = { .name = "exynos-pcie", .of_match_table = exynos_pcie_of_match, diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 808d1f105417..4668fc9648bf 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -33,6 +33,7 @@ #include <linux/pm_domain.h> #include <linux/pm_runtime.h> +#include "../../pci.h" #include "pcie-designware.h" #define IMX8MQ_GPR_PCIE_REF_USE_PAD BIT(9) @@ -40,14 +41,18 @@ #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 IMX95_PCIE_PHY_GEN_CTRL 0x0 #define IMX95_PCIE_REF_USE_PAD BIT(17) +#define IMX95_PCIE_PHY_MPLLA_CTRL 0x10 +#define IMX95_PCIE_PHY_MPLL_STATE BIT(30) + #define IMX95_PCIE_SS_RW_REG_0 0xf0 #define IMX95_PCIE_REF_CLKEN BIT(23) #define IMX95_PCIE_PHY_CR_PARA_SEL BIT(9) +#define IMX95_PCIE_SS_RW_REG_1 0xf4 +#define IMX95_PCIE_SYS_AUX_PWR_DET BIT(31) #define IMX95_PE0_GEN_CTRL_1 0x1050 #define IMX95_PCIE_DEVICE_TYPE GENMASK(3, 0) @@ -55,6 +60,25 @@ #define IMX95_PE0_GEN_CTRL_3 0x1058 #define IMX95_PCIE_LTSSM_EN BIT(0) +#define IMX95_PE0_LUT_ACSCTRL 0x1008 +#define IMX95_PEO_LUT_RWA BIT(16) +#define IMX95_PE0_LUT_ENLOC GENMASK(4, 0) + +#define IMX95_PE0_LUT_DATA1 0x100c +#define IMX95_PE0_LUT_VLD BIT(31) +#define IMX95_PE0_LUT_DAC_ID GENMASK(10, 8) +#define IMX95_PE0_LUT_STREAM_ID GENMASK(5, 0) + +#define IMX95_PE0_LUT_DATA2 0x1010 +#define IMX95_PE0_LUT_REQID GENMASK(31, 16) +#define IMX95_PE0_LUT_MASK GENMASK(15, 0) + +#define IMX95_SID_MASK GENMASK(5, 0) +#define IMX95_MAX_LUT 32 + +#define IMX95_PCIE_RST_CTRL 0x3010 +#define IMX95_PCIE_COLD_RST BIT(0) + #define to_imx_pcie(x) dev_get_drvdata((x)->dev) enum imx_pcie_variants { @@ -70,11 +94,12 @@ enum imx_pcie_variants { IMX8MQ_EP, IMX8MM_EP, IMX8MP_EP, + IMX8Q_EP, IMX95_EP, }; #define IMX_PCIE_FLAG_IMX_PHY BIT(0) -#define IMX_PCIE_FLAG_IMX_SPEED_CHANGE BIT(1) +#define IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND BIT(1) #define IMX_PCIE_FLAG_SUPPORTS_SUSPEND BIT(2) #define IMX_PCIE_FLAG_HAS_PHYDRV BIT(3) #define IMX_PCIE_FLAG_HAS_APP_RESET BIT(4) @@ -82,10 +107,16 @@ enum imx_pcie_variants { #define IMX_PCIE_FLAG_HAS_SERDES BIT(6) #define IMX_PCIE_FLAG_SUPPORT_64BIT BIT(7) #define IMX_PCIE_FLAG_CPU_ADDR_FIXUP BIT(8) +/* + * Because of ERR005723 (PCIe does not support L2 power down) we need to + * workaround suspend resume on some devices which are affected by this errata. + */ +#define IMX_PCIE_FLAG_BROKEN_SUSPEND BIT(9) +#define IMX_PCIE_FLAG_HAS_LUT BIT(10) +#define IMX_PCIE_FLAG_8GT_ECN_ERR051586 BIT(11) #define imx_check_flag(pci, val) (pci->drvdata->flags & val) -#define IMX_PCIE_MAX_CLKS 6 #define IMX_PCIE_MAX_INSTANCES 2 struct imx_pcie; @@ -96,8 +127,6 @@ struct imx_pcie_drvdata { u32 flags; int dbi_length; const char *gpr; - const char * const *clk_names; - const u32 clks_cnt; const u32 ltssm_off; const u32 ltssm_mask; const u32 mode_off[IMX_PCIE_MAX_INSTANCES]; @@ -106,19 +135,25 @@ struct imx_pcie_drvdata { int (*init_phy)(struct imx_pcie *pcie); int (*enable_ref_clk)(struct imx_pcie *pcie, bool enable); int (*core_reset)(struct imx_pcie *pcie, bool assert); + int (*wait_pll_lock)(struct imx_pcie *pcie); + const struct dw_pcie_host_ops *ops; +}; + +struct imx_lut_data { + u32 data1; + u32 data2; }; struct imx_pcie { struct dw_pcie *pci; struct gpio_desc *reset_gpiod; - bool link_is_up; - struct clk_bulk_data clks[IMX_PCIE_MAX_CLKS]; + struct clk_bulk_data *clks; + int num_clks; struct regmap *iomuxc_gpr; u16 msi_ctrl; 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; @@ -128,12 +163,17 @@ struct imx_pcie { struct regulator *vph; void __iomem *phy_base; + /* LUT data for pcie */ + struct imx_lut_data luts[IMX95_MAX_LUT]; /* power domain for pcie */ struct device *pd_pcie; /* power domain for pcie phy */ struct device *pd_pcie_phy; struct phy *phy; const struct imx_pcie_drvdata *drvdata; + + /* Ensure that only one device's LUT is configured at any given time */ + struct mutex lock; }; /* Parameters for the waiting for PCIe PHY PLL to lock on i.MX7 */ @@ -201,6 +241,19 @@ static unsigned int imx_pcie_grp_offset(const struct imx_pcie *imx_pcie) static int imx95_pcie_init_phy(struct imx_pcie *imx_pcie) { + /* + * ERR051624: The Controller Without Vaux Cannot Exit L23 Ready + * Through Beacon or PERST# De-assertion + * + * When the auxiliary power is not available, the controller + * cannot exit from L23 Ready with beacon or PERST# de-assertion + * when main power is not removed. + * + * Workaround: Set SS_RW_REG_1[SYS_AUX_PWR_DET] to 1. + */ + regmap_set_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_SS_RW_REG_1, + IMX95_PCIE_SYS_AUX_PWR_DET); + regmap_update_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_SS_RW_REG_0, IMX95_PCIE_PHY_CR_PARA_SEL, @@ -229,11 +282,11 @@ static void imx_pcie_configure_type(struct imx_pcie *imx_pcie) id = imx_pcie->controller_id; - /* If mode_mask is 0, then generic PHY driver is used to set the mode */ + /* If mode_mask is 0, generic PHY driver is used to set the mode */ if (!drvdata->mode_mask[0]) return; - /* If mode_mask[id] is zero, means each controller have its individual gpr */ + /* If mode_mask[id] is 0, each controller has its individual GPR */ if (!drvdata->mode_mask[id]) id = 0; @@ -370,14 +423,15 @@ static int pcie_phy_write(struct imx_pcie *imx_pcie, int addr, u16 data) static int imx8mq_pcie_init_phy(struct imx_pcie *imx_pcie) { - /* TODO: Currently this code assumes external oscillator is being used */ + /* TODO: This code assumes external oscillator is being used */ regmap_update_bits(imx_pcie->iomuxc_gpr, imx_pcie_grp_offset(imx_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. + * Per 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 (imx_pcie->vph && regulator_get_voltage(imx_pcie->vph) > 3000000) regmap_update_bits(imx_pcie->iomuxc_gpr, @@ -388,13 +442,6 @@ static int imx8mq_pcie_init_phy(struct imx_pcie *imx_pcie) return 0; } -static int imx7d_pcie_init_phy(struct imx_pcie *imx_pcie) -{ - regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, 0); - - return 0; -} - static int imx_pcie_init_phy(struct imx_pcie *imx_pcie) { regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, @@ -443,19 +490,37 @@ static void imx7d_pcie_wait_for_phy_pll_lock(struct imx_pcie *imx_pcie) dev_err(dev, "PCIe PLL lock timeout\n"); } +static int imx95_pcie_wait_for_phy_pll_lock(struct imx_pcie *imx_pcie) +{ + u32 val; + struct device *dev = imx_pcie->pci->dev; + + if (regmap_read_poll_timeout(imx_pcie->iomuxc_gpr, + IMX95_PCIE_PHY_MPLLA_CTRL, val, + val & IMX95_PCIE_PHY_MPLL_STATE, + PHY_PLL_LOCK_WAIT_USLEEP_MAX, + PHY_PLL_LOCK_WAIT_TIMEOUT)) { + dev_err(dev, "PCIe PLL lock timeout\n"); + return -ETIMEDOUT; + } + + return 0; +} + static int imx_setup_phy_mpll(struct imx_pcie *imx_pcie) { unsigned long phy_rate = 0; int mult, div; u16 val; int i; + struct clk_bulk_data *clks = imx_pcie->clks; if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_IMX_PHY)) return 0; - for (i = 0; i < imx_pcie->drvdata->clks_cnt; i++) - if (strncmp(imx_pcie->clks[i].id, "pcie_phy", 8) == 0) - phy_rate = clk_get_rate(imx_pcie->clks[i].clk); + for (i = 0; i < imx_pcie->num_clks; i++) + if (strncmp(clks[i].id, "pcie_phy", 8) == 0) + phy_rate = clk_get_rate(clks[i].clk); switch (phy_rate) { case 125000000: @@ -571,7 +636,7 @@ static int imx_pcie_attach_pd(struct device *dev) DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); if (!link) { - dev_err(dev, "Failed to add device_link to pcie pd.\n"); + dev_err(dev, "Failed to add device_link to pcie pd\n"); return -EINVAL; } @@ -584,7 +649,7 @@ static int imx_pcie_attach_pd(struct device *dev) DL_FLAG_PM_RUNTIME | DL_FLAG_RPM_ACTIVE); if (!link) { - dev_err(dev, "Failed to add device_link to pcie_phy pd.\n"); + dev_err(dev, "Failed to add device_link to pcie_phy pd\n"); return -EINVAL; } @@ -593,10 +658,9 @@ static int imx_pcie_attach_pd(struct device *dev) static int imx6sx_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) { - if (enable) - regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6SX_GPR12_PCIE_TEST_POWERDOWN); - + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX6SX_GPR12_PCIE_TEST_POWERDOWN, + enable ? 0 : IMX6SX_GPR12_PCIE_TEST_POWERDOWN); return 0; } @@ -606,10 +670,10 @@ static int imx6q_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) /* power up core phy and enable ref clock */ regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_TEST_PD); /* - * the async reset input need ref clock to sync internally, + * 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. + * Add a ~10us delay here. */ usleep_range(10, 100); regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR1, IMX6Q_GPR1_PCIE_REF_CLK_EN); @@ -625,19 +689,20 @@ static int imx8mm_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) { int offset = imx_pcie_grp_offset(imx_pcie); - if (enable) { - regmap_clear_bits(imx_pcie->iomuxc_gpr, offset, IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE); - regmap_set_bits(imx_pcie->iomuxc_gpr, offset, IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN); - } - + regmap_update_bits(imx_pcie->iomuxc_gpr, offset, + IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE, + enable ? 0 : IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE); + regmap_update_bits(imx_pcie->iomuxc_gpr, offset, + IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN, + enable ? IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN : 0); return 0; } static int imx7d_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) { - if (!enable) - regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX7D_GPR12_PCIE_PHY_REFCLK_SEL); + regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, + IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, + enable ? 0 : IMX7D_GPR12_PCIE_PHY_REFCLK_SEL); return 0; } @@ -647,7 +712,7 @@ static int imx_pcie_clk_enable(struct imx_pcie *imx_pcie) struct device *dev = pci->dev; int ret; - ret = clk_bulk_prepare_enable(imx_pcie->drvdata->clks_cnt, imx_pcie->clks); + ret = clk_bulk_prepare_enable(imx_pcie->num_clks, imx_pcie->clks); if (ret) return ret; @@ -664,7 +729,7 @@ static int imx_pcie_clk_enable(struct imx_pcie *imx_pcie) return 0; err_ref_clk: - clk_bulk_disable_unprepare(imx_pcie->drvdata->clks_cnt, imx_pcie->clks); + clk_bulk_disable_unprepare(imx_pcie->num_clks, imx_pcie->clks); return ret; } @@ -673,7 +738,7 @@ static void imx_pcie_clk_disable(struct imx_pcie *imx_pcie) { if (imx_pcie->drvdata->enable_ref_clk) imx_pcie->drvdata->enable_ref_clk(imx_pcie, false); - clk_bulk_disable_unprepare(imx_pcie->drvdata->clks_cnt, imx_pcie->clks); + clk_bulk_disable_unprepare(imx_pcie->num_clks, imx_pcie->clks); } static int imx6sx_pcie_core_reset(struct imx_pcie *imx_pcie, bool assert) @@ -755,10 +820,46 @@ static int imx7d_pcie_core_reset(struct imx_pcie *imx_pcie, bool assert) return 0; } +static int imx95_pcie_core_reset(struct imx_pcie *imx_pcie, bool assert) +{ + u32 val; + + if (assert) { + /* + * From i.MX95 PCIe PHY perspective, the COLD reset toggle + * should be complete after power-up by the following sequence. + * > 10us(at power-up) + * > 10ns(warm reset) + * |<------------>| + * ______________ + * phy_reset ____/ \________________ + * ____________ + * ref_clk_en_______________________/ + * Toggle COLD reset aligned with this sequence for i.MX95 PCIe. + */ + regmap_set_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_RST_CTRL, + IMX95_PCIE_COLD_RST); + /* + * Make sure the write to IMX95_PCIE_RST_CTRL is flushed to the + * hardware by doing a read. Otherwise, there is no guarantee + * that the write has reached the hardware before udelay(). + */ + regmap_read_bypassed(imx_pcie->iomuxc_gpr, IMX95_PCIE_RST_CTRL, + &val); + udelay(15); + regmap_clear_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_RST_CTRL, + IMX95_PCIE_COLD_RST); + regmap_read_bypassed(imx_pcie->iomuxc_gpr, IMX95_PCIE_RST_CTRL, + &val); + udelay(10); + } + + return 0; +} + static void imx_pcie_assert_core_reset(struct imx_pcie *imx_pcie) { reset_control_assert(imx_pcie->pciephy_reset); - reset_control_assert(imx_pcie->apps_reset); if (imx_pcie->drvdata->core_reset) imx_pcie->drvdata->core_reset(imx_pcie, true); @@ -841,6 +942,12 @@ static int imx_pcie_start_link(struct dw_pcie *pci) u32 tmp; int ret; + if (!(imx_pcie->drvdata->flags & + IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND)) { + imx_pcie_ltssm_enable(dev); + return 0; + } + /* * Force Gen1 operation when starting the link. In case the link is * started in Gen2 mode, there is a possibility the devices on the @@ -856,11 +963,11 @@ static int imx_pcie_start_link(struct dw_pcie *pci) /* Start LTSSM. */ imx_pcie_ltssm_enable(dev); - ret = dw_pcie_wait_for_link(pci); - if (ret) - goto err_reset_phy; - if (pci->max_link_speed > 1) { + ret = dw_pcie_wait_for_link(pci); + if (ret) + goto err_reset_phy; + /* 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); @@ -877,39 +984,18 @@ static int imx_pcie_start_link(struct dw_pcie *pci) dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, tmp); dw_pcie_dbi_ro_wr_dis(pci); - if (imx_pcie->drvdata->flags & - IMX_PCIE_FLAG_IMX_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 = imx_pcie_wait_for_speed_change(imx_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) + ret = imx_pcie_wait_for_speed_change(imx_pcie); + if (ret) { + dev_err(dev, "Failed to bring link up!\n"); goto err_reset_phy; + } } else { dev_info(dev, "Link: Only Gen1 is enabled\n"); } - imx_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: - imx_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)); @@ -925,6 +1011,190 @@ static void imx_pcie_stop_link(struct dw_pcie *pci) imx_pcie_ltssm_disable(dev); } +static int imx_pcie_add_lut(struct imx_pcie *imx_pcie, u16 rid, u8 sid) +{ + struct dw_pcie *pci = imx_pcie->pci; + struct device *dev = pci->dev; + u32 data1, data2; + int free = -1; + int i; + + if (sid >= 64) { + dev_err(dev, "Invalid SID for index %d\n", sid); + return -EINVAL; + } + + guard(mutex)(&imx_pcie->lock); + + /* + * Iterate through all LUT entries to check for duplicate RID and + * identify the first available entry. Configure this available entry + * immediately after verification to avoid rescanning it. + */ + for (i = 0; i < IMX95_MAX_LUT; i++) { + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_ACSCTRL, IMX95_PEO_LUT_RWA | i); + regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, &data1); + + if (!(data1 & IMX95_PE0_LUT_VLD)) { + if (free < 0) + free = i; + continue; + } + + regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, &data2); + + /* Do not add duplicate RID */ + if (rid == FIELD_GET(IMX95_PE0_LUT_REQID, data2)) { + dev_warn(dev, "Existing LUT entry available for RID (%d)", rid); + return 0; + } + } + + if (free < 0) { + dev_err(dev, "LUT entry is not available\n"); + return -ENOSPC; + } + + data1 = FIELD_PREP(IMX95_PE0_LUT_DAC_ID, 0); + data1 |= FIELD_PREP(IMX95_PE0_LUT_STREAM_ID, sid); + data1 |= IMX95_PE0_LUT_VLD; + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, data1); + + if (imx_pcie->drvdata->mode == DW_PCIE_EP_TYPE) + data2 = 0x7; /* In the EP mode, only 'Device ID' is required */ + else + data2 = IMX95_PE0_LUT_MASK; /* Match all bits of RID */ + data2 |= FIELD_PREP(IMX95_PE0_LUT_REQID, rid); + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, data2); + + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_ACSCTRL, free); + + return 0; +} + +static void imx_pcie_remove_lut(struct imx_pcie *imx_pcie, u16 rid) +{ + u32 data2; + int i; + + guard(mutex)(&imx_pcie->lock); + + for (i = 0; i < IMX95_MAX_LUT; i++) { + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_ACSCTRL, IMX95_PEO_LUT_RWA | i); + regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, &data2); + if (FIELD_GET(IMX95_PE0_LUT_REQID, data2) == rid) { + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_DATA1, 0); + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_DATA2, 0); + regmap_write(imx_pcie->iomuxc_gpr, + IMX95_PE0_LUT_ACSCTRL, i); + + break; + } + } +} + +static int imx_pcie_add_lut_by_rid(struct imx_pcie *imx_pcie, u32 rid) +{ + struct device *dev = imx_pcie->pci->dev; + struct device_node *target; + u32 sid_i, sid_m; + int err_i, err_m; + u32 sid = 0; + + target = NULL; + err_i = of_map_id(dev->of_node, rid, "iommu-map", "iommu-map-mask", + &target, &sid_i); + if (target) { + of_node_put(target); + } else { + /* + * "target == NULL && err_i == 0" means RID out of map range. + * Use 1:1 map RID to streamID. Hardware can't support this + * because the streamID is only 6 bits + */ + err_i = -EINVAL; + } + + target = NULL; + err_m = of_map_id(dev->of_node, rid, "msi-map", "msi-map-mask", + &target, &sid_m); + + /* + * err_m target + * 0 NULL RID out of range. Use 1:1 map RID to + * streamID, Current hardware can't + * support it, so return -EINVAL. + * != 0 NULL msi-map does not exist, use built-in MSI + * 0 != NULL Get correct streamID from RID + * != 0 != NULL Invalid combination + */ + if (!err_m && !target) + return -EINVAL; + else if (target) + of_node_put(target); /* Find streamID map entry for RID in msi-map */ + + /* + * msi-map iommu-map + * N N DWC MSI Ctrl + * Y Y ITS + SMMU, require the same SID + * Y N ITS + * N Y DWC MSI Ctrl + SMMU + */ + if (err_i && err_m) + return 0; + + if (!err_i && !err_m) { + /* + * Glue Layer + * <==========> + * ┌─────┐ ┌──────────┐ + * │ LUT │ 6-bit streamID │ │ + * │ │─────────────────►│ MSI │ + * └─────┘ 2-bit ctrl ID │ │ + * ┌───────────►│ │ + * (i.MX95) │ │ │ + * 00 PCIe0 │ │ │ + * 01 ENETC │ │ │ + * 10 PCIe1 │ │ │ + * │ └──────────┘ + * The MSI glue layer auto adds 2 bits controller ID ahead of + * streamID, so mask these 2 bits to get streamID. The + * IOMMU glue layer doesn't do that. + */ + if (sid_i != (sid_m & IMX95_SID_MASK)) { + dev_err(dev, "iommu-map and msi-map entries mismatch!\n"); + return -EINVAL; + } + } + + if (!err_i) + sid = sid_i; + else if (!err_m) + sid = sid_m & IMX95_SID_MASK; + + return imx_pcie_add_lut(imx_pcie, rid, sid); +} + +static int imx_pcie_enable_device(struct pci_host_bridge *bridge, struct pci_dev *pdev) +{ + struct imx_pcie *imx_pcie = to_imx_pcie(to_dw_pcie_from_pp(bridge->sysdata)); + + return imx_pcie_add_lut_by_rid(imx_pcie, pci_dev_id(pdev)); +} + +static void imx_pcie_disable_device(struct pci_host_bridge *bridge, + struct pci_dev *pdev) +{ + struct imx_pcie *imx_pcie; + + imx_pcie = to_imx_pcie(to_dw_pcie_from_pp(bridge->sysdata)); + imx_pcie_remove_lut(imx_pcie, pci_dev_id(pdev)); +} + static int imx_pcie_host_init(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); @@ -941,6 +1211,11 @@ static int imx_pcie_host_init(struct dw_pcie_rp *pp) } } + if (pp->bridge && imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_LUT)) { + pp->bridge->enable_device = imx_pcie_enable_device; + pp->bridge->disable_device = imx_pcie_disable_device; + } + imx_pcie_assert_core_reset(imx_pcie); if (imx_pcie->drvdata->init_phy) @@ -961,7 +1236,9 @@ static int imx_pcie_host_init(struct dw_pcie_rp *pp) goto err_clk_disable; } - ret = phy_set_mode_ext(imx_pcie->phy, PHY_MODE_PCIE, PHY_MODE_PCIE_RC); + ret = phy_set_mode_ext(imx_pcie->phy, PHY_MODE_PCIE, + imx_pcie->drvdata->mode == DW_PCIE_EP_TYPE ? + PHY_MODE_PCIE_EP : PHY_MODE_PCIE_RC); if (ret) { dev_err(dev, "unable to set PCIe PHY mode\n"); goto err_phy_exit; @@ -974,12 +1251,21 @@ static int imx_pcie_host_init(struct dw_pcie_rp *pp) } } + /* Make sure that PCIe LTSSM is cleared */ + imx_pcie_ltssm_disable(dev); + ret = imx_pcie_deassert_core_reset(imx_pcie); if (ret < 0) { dev_err(dev, "pcie deassert core reset failed: %d\n", ret); goto err_phy_off; } + if (imx_pcie->drvdata->wait_pll_lock) { + ret = imx_pcie->drvdata->wait_pll_lock(imx_pcie); + if (ret < 0) + goto err_phy_off; + } + imx_setup_phy_mpll(imx_pcie); return 0; @@ -1012,31 +1298,63 @@ static void imx_pcie_host_exit(struct dw_pcie_rp *pp) regulator_disable(imx_pcie->vpcie); } -static u64 imx_pcie_cpu_addr_fixup(struct dw_pcie *pcie, u64 cpu_addr) +static void imx_pcie_host_post_init(struct dw_pcie_rp *pp) { - struct imx_pcie *imx_pcie = to_imx_pcie(pcie); - struct dw_pcie_rp *pp = &pcie->pp; - struct resource_entry *entry; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct imx_pcie *imx_pcie = to_imx_pcie(pci); + u32 val; - if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_CPU_ADDR_FIXUP)) - return cpu_addr; + if (imx_pcie->drvdata->flags & IMX_PCIE_FLAG_8GT_ECN_ERR051586) { + /* + * ERR051586: Compliance with 8GT/s Receiver Impedance ECN + * + * The default value of GEN3_RELATED_OFF[GEN3_ZRXDC_NONCOMPL] + * is 1 which makes receiver non-compliant with the ZRX-DC + * parameter for 2.5 GT/s when operating at 8 GT/s or higher. + * It causes unnecessary timeout in L1. + * + * Workaround: Program GEN3_RELATED_OFF[GEN3_ZRXDC_NONCOMPL] + * to 0. + */ + dw_pcie_dbi_ro_wr_en(pci); + 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); + dw_pcie_dbi_ro_wr_dis(pci); + } +} + +/* + * In old DWC implementations, PCIE_ATU_INHIBIT_PAYLOAD in iATU Ctrl2 + * register is reserved, so the generic DWC implementation of sending the + * PME_Turn_Off message using a dummy MMIO write cannot be used. + */ +static void imx_pcie_pme_turn_off(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct imx_pcie *imx_pcie = to_imx_pcie(pci); - entry = resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM); - if (!entry) - return cpu_addr; + regmap_set_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX6SX_GPR12_PCIE_PM_TURN_OFF); + regmap_clear_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, IMX6SX_GPR12_PCIE_PM_TURN_OFF); - return cpu_addr - entry->offset; + usleep_range(PCIE_PME_TO_L2_TIMEOUT_US/10, PCIE_PME_TO_L2_TIMEOUT_US); } static const struct dw_pcie_host_ops imx_pcie_host_ops = { .init = imx_pcie_host_init, .deinit = imx_pcie_host_exit, + .pme_turn_off = imx_pcie_pme_turn_off, +}; + +static const struct dw_pcie_host_ops imx_pcie_host_dw_pme_ops = { + .init = imx_pcie_host_init, + .deinit = imx_pcie_host_exit, + .post_init = imx_pcie_host_post_init, }; static const struct dw_pcie_ops dw_pcie_ops = { .start_link = imx_pcie_start_link, .stop_link = imx_pcie_stop_link, - .cpu_addr_fixup = imx_pcie_cpu_addr_fixup, }; static void imx_pcie_ep_init(struct dw_pcie_ep *ep) @@ -1069,24 +1387,33 @@ static int imx_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, } static const struct pci_epc_features imx8m_pcie_epc_features = { - .linkup_notifier = false, .msi_capable = true, - .msix_capable = false, .bar[BAR_1] = { .type = BAR_RESERVED, }, .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_4] = { .type = BAR_FIXED, .fixed_size = SZ_256, }, + .bar[BAR_5] = { .type = BAR_RESERVED, }, + .align = SZ_64K, +}; + +static const struct pci_epc_features imx8q_pcie_epc_features = { + .msi_capable = true, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_5] = { .type = BAR_RESERVED, }, .align = SZ_64K, }; /* - * BAR# | Default BAR enable | Default BAR Type | Default BAR Size | BAR Sizing Scheme - * ================================================================================================ - * BAR0 | Enable | 64-bit | 1 MB | Programmable Size - * BAR1 | Disable | 32-bit | 64 KB | Fixed Size - * BAR1 should be disabled if BAR0 is 64bit. - * BAR2 | Enable | 32-bit | 1 MB | Programmable Size - * BAR3 | Enable | 32-bit | 64 KB | Programmable Size - * BAR4 | Enable | 32-bit | 1M | Programmable Size - * BAR5 | Enable | 32-bit | 64 KB | Programmable Size + * | Default | Default | Default | BAR Sizing + * BAR# | Enable? | Type | Size | Scheme + * ======================================================= + * BAR0 | Enable | 64-bit | 1 MB | Programmable Size + * BAR1 | Disable | 32-bit | 64 KB | Fixed Size + * (BAR1 should be disabled if BAR0 is 64-bit) + * BAR2 | Enable | 32-bit | 1 MB | Programmable Size + * BAR3 | Enable | 32-bit | 64 KB | Programmable Size + * BAR4 | Enable | 32-bit | 1 MB | Programmable Size + * BAR5 | Enable | 32-bit | 64 KB | Programmable Size */ static const struct pci_epc_features imx95_pcie_epc_features = { .msi_capable = true, @@ -1113,7 +1440,6 @@ static int imx_add_pcie_ep(struct imx_pcie *imx_pcie, struct platform_device *pdev) { int ret; - unsigned int pcie_dbi2_offset; struct dw_pcie_ep *ep; struct dw_pcie *pci = imx_pcie->pci; struct dw_pcie_rp *pp = &pci->pp; @@ -1123,28 +1449,6 @@ static int imx_add_pcie_ep(struct imx_pcie *imx_pcie, ep = &pci->ep; ep->ops = &pcie_ep_ops; - switch (imx_pcie->drvdata->variant) { - case IMX8MQ_EP: - case IMX8MM_EP: - case IMX8MP_EP: - pcie_dbi2_offset = SZ_1M; - break; - default: - pcie_dbi2_offset = SZ_4K; - break; - } - - pci->dbi_base2 = pci->dbi_base + pcie_dbi2_offset; - - /* - * FIXME: Ideally, dbi2 base address should come from DT. But since only IMX95 is defining - * "dbi2" in DT, "dbi_base2" is set to NULL here for that platform alone so that the DWC - * core code can fetch that from DT. But once all platform DTs were fixed, this and the - * above "dbi_base2" setting should be removed. - */ - if (device_property_match_string(dev, "reg-names", "dbi2") >= 0) - pci->dbi_base2 = NULL; - if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_SUPPORT_64BIT)) dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)); @@ -1155,6 +1459,7 @@ static int imx_add_pcie_ep(struct imx_pcie *imx_pcie, dev_err(dev, "failed to initialize endpoint\n"); return ret; } + imx_pcie_host_post_init(pp); ret = dw_pcie_ep_init_registers(ep); if (ret) { @@ -1165,49 +1470,9 @@ static int imx_add_pcie_ep(struct imx_pcie *imx_pcie, pci_epc_init_notify(ep->epc); - /* Start LTSSM. */ - imx_pcie_ltssm_enable(dev); - return 0; } -static void imx_pcie_pm_turnoff(struct imx_pcie *imx_pcie) -{ - struct device *dev = imx_pcie->pci->dev; - - /* Some variants have a turnoff reset in DT */ - if (imx_pcie->turnoff_reset) { - reset_control_assert(imx_pcie->turnoff_reset); - reset_control_deassert(imx_pcie->turnoff_reset); - goto pm_turnoff_sleep; - } - - /* Others poke directly at IOMUXC registers */ - switch (imx_pcie->drvdata->variant) { - case IMX6SX: - case IMX6QP: - regmap_update_bits(imx_pcie->iomuxc_gpr, IOMUXC_GPR12, - IMX6SX_GPR12_PCIE_PM_TURN_OFF, - IMX6SX_GPR12_PCIE_PM_TURN_OFF); - regmap_update_bits(imx_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 void imx_pcie_msi_save_restore(struct imx_pcie *imx_pcie, bool save) { u8 offset; @@ -1228,18 +1493,63 @@ static void imx_pcie_msi_save_restore(struct imx_pcie *imx_pcie, bool save) } } +static void imx_pcie_lut_save(struct imx_pcie *imx_pcie) +{ + u32 data1, data2; + int i; + + for (i = 0; i < IMX95_MAX_LUT; i++) { + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_ACSCTRL, + IMX95_PEO_LUT_RWA | i); + regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, &data1); + regmap_read(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, &data2); + if (data1 & IMX95_PE0_LUT_VLD) { + imx_pcie->luts[i].data1 = data1; + imx_pcie->luts[i].data2 = data2; + } else { + imx_pcie->luts[i].data1 = 0; + imx_pcie->luts[i].data2 = 0; + } + } +} + +static void imx_pcie_lut_restore(struct imx_pcie *imx_pcie) +{ + int i; + + for (i = 0; i < IMX95_MAX_LUT; i++) { + if ((imx_pcie->luts[i].data1 & IMX95_PE0_LUT_VLD) == 0) + continue; + + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, + imx_pcie->luts[i].data1); + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA2, + imx_pcie->luts[i].data2); + regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_ACSCTRL, i); + } +} + static int imx_pcie_suspend_noirq(struct device *dev) { struct imx_pcie *imx_pcie = dev_get_drvdata(dev); - struct dw_pcie_rp *pp = &imx_pcie->pci->pp; if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_SUPPORTS_SUSPEND)) return 0; imx_pcie_msi_save_restore(imx_pcie, true); - imx_pcie_pm_turnoff(imx_pcie); - imx_pcie_stop_link(imx_pcie->pci); - imx_pcie_host_exit(pp); + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_LUT)) + imx_pcie_lut_save(imx_pcie); + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_BROKEN_SUSPEND)) { + /* + * The minimum for a workaround would be to set PERST# and to + * set the PCIE_TEST_PD flag. However, we can also disable the + * clock which saves some power. + */ + imx_pcie_assert_core_reset(imx_pcie); + imx_pcie->drvdata->enable_ref_clk(imx_pcie, false); + } else { + return dw_pcie_suspend_noirq(imx_pcie->pci); + } return 0; } @@ -1248,19 +1558,34 @@ static int imx_pcie_resume_noirq(struct device *dev) { int ret; struct imx_pcie *imx_pcie = dev_get_drvdata(dev); - struct dw_pcie_rp *pp = &imx_pcie->pci->pp; if (!(imx_pcie->drvdata->flags & IMX_PCIE_FLAG_SUPPORTS_SUSPEND)) return 0; - ret = imx_pcie_host_init(pp); - if (ret) - return ret; - imx_pcie_msi_save_restore(imx_pcie, false); - dw_pcie_setup_rc(pp); + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_BROKEN_SUSPEND)) { + ret = imx_pcie->drvdata->enable_ref_clk(imx_pcie, true); + if (ret) + return ret; + ret = imx_pcie_deassert_core_reset(imx_pcie); + if (ret) + return ret; - if (imx_pcie->link_is_up) - imx_pcie_start_link(imx_pcie->pci); + /* + * Using PCIE_TEST_PD seems to disable MSI and powers down the + * root complex. This is why we have to setup the rc again and + * why we have to restore the MSI register. + */ + ret = dw_pcie_setup_rc(&imx_pcie->pci->pp); + if (ret) + return ret; + } else { + ret = dw_pcie_resume_noirq(imx_pcie->pci); + if (ret) + return ret; + } + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_LUT)) + imx_pcie_lut_restore(imx_pcie); + imx_pcie_msi_save_restore(imx_pcie, false); return 0; } @@ -1276,11 +1601,9 @@ static int imx_pcie_probe(struct platform_device *pdev) struct dw_pcie *pci; struct imx_pcie *imx_pcie; struct device_node *np; - struct resource *dbi_base; struct device_node *node = dev->of_node; - int ret; + int ret, domain; u16 val; - int i; imx_pcie = devm_kzalloc(dev, sizeof(*imx_pcie), GFP_KERNEL); if (!imx_pcie) @@ -1292,11 +1615,17 @@ static int imx_pcie_probe(struct platform_device *pdev) pci->dev = dev; pci->ops = &dw_pcie_ops; - pci->pp.ops = &imx_pcie_host_ops; imx_pcie->pci = pci; imx_pcie->drvdata = of_device_get_match_data(dev); + mutex_init(&imx_pcie->lock); + + if (imx_pcie->drvdata->ops) + pci->pp.ops = imx_pcie->drvdata->ops; + else + pci->pp.ops = &imx_pcie_host_dw_pme_ops; + /* Find the PHY if one is defined, only imx7d uses it */ np = of_parse_phandle(node, "fsl,imx7d-pcie-phy", 0); if (np) { @@ -1312,10 +1641,6 @@ static int imx_pcie_probe(struct platform_device *pdev) return PTR_ERR(imx_pcie->phy_base); } - pci->dbi_base = devm_platform_get_and_ioremap_resource(pdev, 0, &dbi_base); - if (IS_ERR(pci->dbi_base)) - return PTR_ERR(pci->dbi_base); - /* Fetch GPIOs */ imx_pcie->reset_gpiod = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_HIGH); if (IS_ERR(imx_pcie->reset_gpiod)) @@ -1323,16 +1648,11 @@ static int imx_pcie_probe(struct platform_device *pdev) "unable to get reset gpio\n"); gpiod_set_consumer_name(imx_pcie->reset_gpiod, "PCIe reset"); - if (imx_pcie->drvdata->clks_cnt >= IMX_PCIE_MAX_CLKS) - return dev_err_probe(dev, -ENOMEM, "clks_cnt is too big\n"); - - for (i = 0; i < imx_pcie->drvdata->clks_cnt; i++) - imx_pcie->clks[i].id = imx_pcie->drvdata->clk_names[i]; - /* Fetch clocks */ - ret = devm_clk_bulk_get(dev, imx_pcie->drvdata->clks_cnt, imx_pcie->clks); - if (ret) - return ret; + imx_pcie->num_clks = devm_clk_bulk_get_all(dev, &imx_pcie->clks); + if (imx_pcie->num_clks < 0) + return dev_err_probe(dev, imx_pcie->num_clks, + "failed to get clocks\n"); if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_PHYDRV)) { imx_pcie->phy = devm_phy_get(dev, "pcie-phy"); @@ -1358,21 +1678,16 @@ static int imx_pcie_probe(struct platform_device *pdev) switch (imx_pcie->drvdata->variant) { case IMX8MQ: case IMX8MQ_EP: - case IMX7D: - if (dbi_base->start == IMX8MQ_PCIE2_BASE_ADDR) - imx_pcie->controller_id = 1; + domain = of_get_pci_domain_nr(node); + if (domain < 0 || domain > 1) + return dev_err_probe(dev, -ENODEV, "no \"linux,pci-domain\" property in devicetree\n"); + + imx_pcie->controller_id = domain; break; default: break; } - /* Grab turnoff reset */ - imx_pcie->turnoff_reset = devm_reset_control_get_optional_exclusive(dev, "turnoff"); - if (IS_ERR(imx_pcie->turnoff_reset)) { - dev_err(dev, "Failed to get TURNOFF reset control\n"); - return PTR_ERR(imx_pcie->turnoff_reset); - } - if (imx_pcie->drvdata->gpr) { /* Grab GPR config register range */ imx_pcie->iomuxc_gpr = @@ -1426,6 +1741,10 @@ static int imx_pcie_probe(struct platform_device *pdev) pci->max_link_speed = 1; of_property_read_u32(node, "fsl,max-link-speed", &pci->max_link_speed); + ret = devm_regulator_get_enable_optional(&pdev->dev, "vpcie3v3aux"); + if (ret < 0 && ret != -ENODEV) + return dev_err_probe(dev, ret, "failed to enable Vaux supply\n"); + imx_pcie->vpcie = devm_regulator_get_optional(&pdev->dev, "vpcie"); if (IS_ERR(imx_pcie->vpcie)) { if (PTR_ERR(imx_pcie->vpcie) != -ENODEV) @@ -1446,11 +1765,19 @@ static int imx_pcie_probe(struct platform_device *pdev) if (ret) return ret; + pci->use_parent_dt_ranges = true; if (imx_pcie->drvdata->mode == DW_PCIE_EP_TYPE) { ret = imx_add_pcie_ep(imx_pcie, pdev); if (ret < 0) return ret; + + /* + * FIXME: Only single Device (EPF) is supported due to the + * Endpoint framework limitation. + */ + imx_pcie_add_lut_by_rid(imx_pcie, 0); } else { + pci->pp.use_atu_msg = true; ret = dw_pcie_host_init(&pci->pp); if (ret < 0) return ret; @@ -1475,21 +1802,15 @@ static void imx_pcie_shutdown(struct platform_device *pdev) imx_pcie_assert_core_reset(imx_pcie); } -static const char * const imx6q_clks[] = {"pcie_bus", "pcie", "pcie_phy"}; -static const char * const imx8mm_clks[] = {"pcie_bus", "pcie", "pcie_aux"}; -static const char * const imx8mq_clks[] = {"pcie_bus", "pcie", "pcie_phy", "pcie_aux"}; -static const char * const imx6sx_clks[] = {"pcie_bus", "pcie", "pcie_phy", "pcie_inbound_axi"}; -static const char * const imx8q_clks[] = {"mstr", "slv", "dbi"}; - static const struct imx_pcie_drvdata drvdata[] = { [IMX6Q] = { .variant = IMX6Q, .flags = IMX_PCIE_FLAG_IMX_PHY | - IMX_PCIE_FLAG_IMX_SPEED_CHANGE, + IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND | + IMX_PCIE_FLAG_BROKEN_SUSPEND | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, .dbi_length = 0x200, .gpr = "fsl,imx6q-iomuxc-gpr", - .clk_names = imx6q_clks, - .clks_cnt = ARRAY_SIZE(imx6q_clks), .ltssm_off = IOMUXC_GPR12, .ltssm_mask = IMX6Q_GPR12_PCIE_CTL_2, .mode_off[0] = IOMUXC_GPR12, @@ -1501,11 +1822,9 @@ static const struct imx_pcie_drvdata drvdata[] = { [IMX6SX] = { .variant = IMX6SX, .flags = IMX_PCIE_FLAG_IMX_PHY | - IMX_PCIE_FLAG_IMX_SPEED_CHANGE | + IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND | IMX_PCIE_FLAG_SUPPORTS_SUSPEND, .gpr = "fsl,imx6q-iomuxc-gpr", - .clk_names = imx6sx_clks, - .clks_cnt = ARRAY_SIZE(imx6sx_clks), .ltssm_off = IOMUXC_GPR12, .ltssm_mask = IMX6Q_GPR12_PCIE_CTL_2, .mode_off[0] = IOMUXC_GPR12, @@ -1513,16 +1832,15 @@ static const struct imx_pcie_drvdata drvdata[] = { .init_phy = imx6sx_pcie_init_phy, .enable_ref_clk = imx6sx_pcie_enable_ref_clk, .core_reset = imx6sx_pcie_core_reset, + .ops = &imx_pcie_host_ops, }, [IMX6QP] = { .variant = IMX6QP, .flags = IMX_PCIE_FLAG_IMX_PHY | - IMX_PCIE_FLAG_IMX_SPEED_CHANGE | + IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND | IMX_PCIE_FLAG_SUPPORTS_SUSPEND, .dbi_length = 0x200, .gpr = "fsl,imx6q-iomuxc-gpr", - .clk_names = imx6q_clks, - .clks_cnt = ARRAY_SIZE(imx6q_clks), .ltssm_off = IOMUXC_GPR12, .ltssm_mask = IMX6Q_GPR12_PCIE_CTL_2, .mode_off[0] = IOMUXC_GPR12, @@ -1530,6 +1848,7 @@ static const struct imx_pcie_drvdata drvdata[] = { .init_phy = imx_pcie_init_phy, .enable_ref_clk = imx6q_pcie_enable_ref_clk, .core_reset = imx6qp_pcie_core_reset, + .ops = &imx_pcie_host_ops, }, [IMX7D] = { .variant = IMX7D, @@ -1537,21 +1856,17 @@ static const struct imx_pcie_drvdata drvdata[] = { IMX_PCIE_FLAG_HAS_APP_RESET | IMX_PCIE_FLAG_HAS_PHY_RESET, .gpr = "fsl,imx7d-iomuxc-gpr", - .clk_names = imx6q_clks, - .clks_cnt = ARRAY_SIZE(imx6q_clks), .mode_off[0] = IOMUXC_GPR12, .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, - .init_phy = imx7d_pcie_init_phy, .enable_ref_clk = imx7d_pcie_enable_ref_clk, .core_reset = imx7d_pcie_core_reset, }, [IMX8MQ] = { .variant = IMX8MQ, .flags = IMX_PCIE_FLAG_HAS_APP_RESET | - IMX_PCIE_FLAG_HAS_PHY_RESET, + IMX_PCIE_FLAG_HAS_PHY_RESET | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, .gpr = "fsl,imx8mq-iomuxc-gpr", - .clk_names = imx8mq_clks, - .clks_cnt = ARRAY_SIZE(imx8mq_clks), .mode_off[0] = IOMUXC_GPR12, .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, .mode_off[1] = IOMUXC_GPR12, @@ -1565,8 +1880,6 @@ static const struct imx_pcie_drvdata drvdata[] = { IMX_PCIE_FLAG_HAS_PHYDRV | IMX_PCIE_FLAG_HAS_APP_RESET, .gpr = "fsl,imx8mm-iomuxc-gpr", - .clk_names = imx8mm_clks, - .clks_cnt = ARRAY_SIZE(imx8mm_clks), .mode_off[0] = IOMUXC_GPR12, .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, .enable_ref_clk = imx8mm_pcie_enable_ref_clk, @@ -1577,8 +1890,6 @@ static const struct imx_pcie_drvdata drvdata[] = { IMX_PCIE_FLAG_HAS_PHYDRV | IMX_PCIE_FLAG_HAS_APP_RESET, .gpr = "fsl,imx8mp-iomuxc-gpr", - .clk_names = imx8mm_clks, - .clks_cnt = ARRAY_SIZE(imx8mm_clks), .mode_off[0] = IOMUXC_GPR12, .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, .enable_ref_clk = imx8mm_pcie_enable_ref_clk, @@ -1586,20 +1897,22 @@ static const struct imx_pcie_drvdata drvdata[] = { [IMX8Q] = { .variant = IMX8Q, .flags = IMX_PCIE_FLAG_HAS_PHYDRV | - IMX_PCIE_FLAG_CPU_ADDR_FIXUP, - .clk_names = imx8q_clks, - .clks_cnt = ARRAY_SIZE(imx8q_clks), + IMX_PCIE_FLAG_CPU_ADDR_FIXUP | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, }, [IMX95] = { .variant = IMX95, - .flags = IMX_PCIE_FLAG_HAS_SERDES, - .clk_names = imx8mq_clks, - .clks_cnt = ARRAY_SIZE(imx8mq_clks), + .flags = IMX_PCIE_FLAG_HAS_SERDES | + IMX_PCIE_FLAG_HAS_LUT | + IMX_PCIE_FLAG_8GT_ECN_ERR051586 | + IMX_PCIE_FLAG_SUPPORTS_SUSPEND, .ltssm_off = IMX95_PE0_GEN_CTRL_3, .ltssm_mask = IMX95_PCIE_LTSSM_EN, .mode_off[0] = IMX95_PE0_GEN_CTRL_1, .mode_mask[0] = IMX95_PCIE_DEVICE_TYPE, + .core_reset = imx95_pcie_core_reset, .init_phy = imx95_pcie_init_phy, + .wait_pll_lock = imx95_pcie_wait_for_phy_pll_lock, }, [IMX8MQ_EP] = { .variant = IMX8MQ_EP, @@ -1607,13 +1920,11 @@ static const struct imx_pcie_drvdata drvdata[] = { IMX_PCIE_FLAG_HAS_PHY_RESET, .mode = DW_PCIE_EP_TYPE, .gpr = "fsl,imx8mq-iomuxc-gpr", - .clk_names = imx8mq_clks, - .clks_cnt = ARRAY_SIZE(imx8mq_clks), .mode_off[0] = IOMUXC_GPR12, .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, .mode_off[1] = IOMUXC_GPR12, .mode_mask[1] = IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE, - .epc_features = &imx8m_pcie_epc_features, + .epc_features = &imx8q_pcie_epc_features, .init_phy = imx8mq_pcie_init_phy, .enable_ref_clk = imx8mm_pcie_enable_ref_clk, }, @@ -1623,8 +1934,6 @@ static const struct imx_pcie_drvdata drvdata[] = { IMX_PCIE_FLAG_HAS_PHYDRV, .mode = DW_PCIE_EP_TYPE, .gpr = "fsl,imx8mm-iomuxc-gpr", - .clk_names = imx8mm_clks, - .clks_cnt = ARRAY_SIZE(imx8mm_clks), .mode_off[0] = IOMUXC_GPR12, .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, .epc_features = &imx8m_pcie_epc_features, @@ -1636,24 +1945,29 @@ static const struct imx_pcie_drvdata drvdata[] = { IMX_PCIE_FLAG_HAS_PHYDRV, .mode = DW_PCIE_EP_TYPE, .gpr = "fsl,imx8mp-iomuxc-gpr", - .clk_names = imx8mm_clks, - .clks_cnt = ARRAY_SIZE(imx8mm_clks), .mode_off[0] = IOMUXC_GPR12, .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, .epc_features = &imx8m_pcie_epc_features, .enable_ref_clk = imx8mm_pcie_enable_ref_clk, }, + [IMX8Q_EP] = { + .variant = IMX8Q_EP, + .flags = IMX_PCIE_FLAG_HAS_PHYDRV, + .mode = DW_PCIE_EP_TYPE, + .epc_features = &imx8q_pcie_epc_features, + }, [IMX95_EP] = { .variant = IMX95_EP, .flags = IMX_PCIE_FLAG_HAS_SERDES | + IMX_PCIE_FLAG_8GT_ECN_ERR051586 | IMX_PCIE_FLAG_SUPPORT_64BIT, - .clk_names = imx8mq_clks, - .clks_cnt = ARRAY_SIZE(imx8mq_clks), .ltssm_off = IMX95_PE0_GEN_CTRL_3, .ltssm_mask = IMX95_PCIE_LTSSM_EN, .mode_off[0] = IMX95_PE0_GEN_CTRL_1, .mode_mask[0] = IMX95_PCIE_DEVICE_TYPE, .init_phy = imx95_pcie_init_phy, + .core_reset = imx95_pcie_core_reset, + .wait_pll_lock = imx95_pcie_wait_for_phy_pll_lock, .epc_features = &imx95_pcie_epc_features, .mode = DW_PCIE_EP_TYPE, }, @@ -1672,6 +1986,7 @@ static const struct of_device_id imx_pcie_of_match[] = { { .compatible = "fsl,imx8mq-pcie-ep", .data = &drvdata[IMX8MQ_EP], }, { .compatible = "fsl,imx8mm-pcie-ep", .data = &drvdata[IMX8MM_EP], }, { .compatible = "fsl,imx8mp-pcie-ep", .data = &drvdata[IMX8MP_EP], }, + { .compatible = "fsl,imx8q-pcie-ep", .data = &drvdata[IMX8Q_EP], }, { .compatible = "fsl,imx95-pcie-ep", .data = &drvdata[IMX95_EP], }, {}, }; diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c index 2219b1a866fa..f86d9111f863 100644 --- a/drivers/pci/controller/dwc/pci-keystone.c +++ b/drivers/pci/controller/dwc/pci-keystone.c @@ -17,6 +17,7 @@ #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> #include <linux/mfd/syscon.h> +#include <linux/module.h> #include <linux/msi.h> #include <linux/of.h> #include <linux/of_irq.h> @@ -455,6 +456,17 @@ static void __iomem *ks_pcie_other_map_bus(struct pci_bus *bus, struct keystone_pcie *ks_pcie = to_keystone_pcie(pci); u32 reg; + /* + * 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; + reg = CFG_BUS(bus->number) | CFG_DEVICE(PCI_SLOT(devfn)) | CFG_FUNC(PCI_FUNC(devfn)); if (!pci_is_root_bus(bus->parent)) @@ -481,13 +493,12 @@ static struct pci_ops ks_pcie_ops = { * @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) +static bool 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); + return (val & PORT_LOGIC_LTSSM_STATE_MASK) == PORT_LOGIC_LTSSM_STATE_L0; } static void ks_pcie_stop_link(struct dw_pcie *pci) @@ -750,7 +761,7 @@ static int ks_pcie_config_intx_irq(struct keystone_pcie *ks_pcie) ks_pcie); } - intx_irq_domain = irq_domain_add_linear(intc_np, PCI_NUM_INTX, + intx_irq_domain = irq_domain_create_linear(of_fwnode_handle(intc_np), PCI_NUM_INTX, &ks_pcie_intx_irq_domain_ops, NULL); if (!intx_irq_domain) { dev_err(dev, "Failed to add irq domain for INTX irqs\n"); @@ -767,29 +778,7 @@ err: 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) +static int ks_pcie_init_id(struct keystone_pcie *ks_pcie) { int ret; unsigned int id; @@ -821,7 +810,7 @@ static int __init ks_pcie_init_id(struct keystone_pcie *ks_pcie) return 0; } -static int __init ks_pcie_host_init(struct dw_pcie_rp *pp) +static int 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); @@ -851,15 +840,6 @@ static int __init ks_pcie_host_init(struct dw_pcie_rp *pp) 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; } @@ -950,16 +930,15 @@ static int ks_pcie_am654_raise_irq(struct dw_pcie_ep *ep, u8 func_no, } static const struct pci_epc_features ks_pcie_am654_epc_features = { - .linkup_notifier = false, .msi_capable = true, .msix_capable = true, .bar[BAR_0] = { .type = BAR_RESERVED, }, .bar[BAR_1] = { .type = BAR_RESERVED, }, - .bar[BAR_2] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, + .bar[BAR_2] = { .type = BAR_RESIZABLE, }, .bar[BAR_3] = { .type = BAR_FIXED, .fixed_size = SZ_64K, }, .bar[BAR_4] = { .type = BAR_FIXED, .fixed_size = 256, }, - .bar[BAR_5] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, - .align = SZ_1M, + .bar[BAR_5] = { .type = BAR_RESIZABLE, }, + .align = SZ_64K, }; static const struct pci_epc_features* @@ -1093,6 +1072,7 @@ static int ks_pcie_am654_set_mode(struct device *dev, static const struct ks_pcie_of_data ks_pcie_rc_of_data = { .host_ops = &ks_pcie_host_ops, + .mode = DW_PCIE_RC_TYPE, .version = DW_PCIE_VER_365A, }; @@ -1124,6 +1104,7 @@ static const struct of_device_id ks_pcie_of_match[] = { }, { }, }; +MODULE_DEVICE_TABLE(of, ks_pcie_of_match); static int ks_pcie_probe(struct platform_device *pdev) { @@ -1190,8 +1171,8 @@ static int ks_pcie_probe(struct platform_device *pdev) if (irq < 0) return irq; - ret = request_irq(irq, ks_pcie_err_irq_handler, IRQF_SHARED, - "ks-pcie-error-irq", ks_pcie); + ret = devm_request_irq(dev, 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); @@ -1202,11 +1183,11 @@ static int ks_pcie_probe(struct platform_device *pdev) if (ret) num_lanes = 1; - phy = devm_kzalloc(dev, sizeof(*phy) * num_lanes, GFP_KERNEL); + phy = devm_kcalloc(dev, num_lanes, sizeof(*phy), GFP_KERNEL); if (!phy) return -ENOMEM; - link = devm_kzalloc(dev, sizeof(*link) * num_lanes, GFP_KERNEL); + link = devm_kcalloc(dev, num_lanes, sizeof(*link), GFP_KERNEL); if (!link) return -ENOMEM; @@ -1327,6 +1308,8 @@ static int ks_pcie_probe(struct platform_device *pdev) break; default: dev_err(dev, "INVALID device type %d\n", mode); + ret = -EINVAL; + goto err_get_sync; } ks_pcie_enable_error_irq(ks_pcie); @@ -1363,10 +1346,51 @@ static void ks_pcie_remove(struct platform_device *pdev) static struct platform_driver ks_pcie_driver = { .probe = ks_pcie_probe, - .remove_new = ks_pcie_remove, + .remove = ks_pcie_remove, .driver = { .name = "keystone-pcie", .of_match_table = ks_pcie_of_match, }, }; + +#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; +} + +static int __init ks_pcie_init(void) +{ + /* + * PCIe access errors that result into OCP errors are caught by ARM as + * "External aborts" + */ + if (of_find_matching_node(NULL, ks_pcie_of_match)) + hook_fault_code(17, ks_pcie_fault, SIGBUS, 0, + "Asynchronous external abort"); + + return platform_driver_register(&ks_pcie_driver); +} +device_initcall(ks_pcie_init); +#else builtin_platform_driver(ks_pcie_driver); +#endif + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("PCIe controller driver for Texas Instruments Keystone SoCs"); +MODULE_AUTHOR("Murali Karicheri <m-karicheri2@ti.com>"); diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c index ee6f52568133..a44b5c256d6e 100644 --- a/drivers/pci/controller/dwc/pci-layerscape.c +++ b/drivers/pci/controller/dwc/pci-layerscape.c @@ -329,7 +329,6 @@ static int ls_pcie_probe(struct platform_device *pdev) struct ls_pcie *pcie; struct resource *dbi_base; u32 index[2]; - int ret; pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); if (!pcie) @@ -355,16 +354,15 @@ static int ls_pcie_probe(struct platform_device *pdev) pcie->pf_lut_base = pci->dbi_base + pcie->drvdata->pf_lut_off; if (pcie->drvdata->scfg_support) { - pcie->scfg = syscon_regmap_lookup_by_phandle(dev->of_node, "fsl,pcie-scfg"); + pcie->scfg = + syscon_regmap_lookup_by_phandle_args(dev->of_node, + "fsl,pcie-scfg", 1, + index); if (IS_ERR(pcie->scfg)) { dev_err(dev, "No syscfg phandle specified\n"); return PTR_ERR(pcie->scfg); } - ret = of_property_read_u32_array(dev->of_node, "fsl,pcie-scfg", index, 2); - if (ret) - return ret; - pcie->index = index[1]; } diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c index db9482a113e9..54b6a4196f17 100644 --- a/drivers/pci/controller/dwc/pci-meson.c +++ b/drivers/pci/controller/dwc/pci-meson.c @@ -108,10 +108,22 @@ static int meson_pcie_get_mems(struct platform_device *pdev, struct meson_pcie *mp) { struct dw_pcie *pci = &mp->pci; + struct resource *res; - pci->dbi_base = devm_platform_ioremap_resource_byname(pdev, "elbi"); - if (IS_ERR(pci->dbi_base)) - return PTR_ERR(pci->dbi_base); + /* + * For the broken DTs that supply 'dbi' as 'elbi', parse the 'elbi' + * region and assign it to both 'pci->elbi_base' and 'pci->dbi_space' so + * that the DWC core can skip parsing both regions. + */ + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "elbi"); + if (res) { + pci->elbi_base = devm_pci_remap_cfg_resource(pci->dev, res); + if (IS_ERR(pci->elbi_base)) + return PTR_ERR(pci->elbi_base); + + pci->dbi_base = pci->elbi_base; + pci->dbi_phys_addr = res->start; + } mp->cfg_base = devm_platform_ioremap_resource_byname(pdev, "cfg"); if (IS_ERR(mp->cfg_base)) @@ -335,7 +347,7 @@ static struct pci_ops meson_pci_ops = { .write = pci_generic_config_write, }; -static int meson_pcie_link_up(struct dw_pcie *pci) +static bool meson_pcie_link_up(struct dw_pcie *pci) { struct meson_pcie *mp = to_meson_pcie(pci); struct device *dev = pci->dev; @@ -363,7 +375,7 @@ static int meson_pcie_link_up(struct dw_pcie *pci) dev_dbg(dev, "speed_okay\n"); if (smlh_up && rdlh_up && ltssm_up && speed_okay) - return 1; + return true; cnt++; @@ -371,7 +383,7 @@ static int meson_pcie_link_up(struct dw_pcie *pci) } while (cnt < WAIT_LINKUP_TIMEOUT); dev_err(dev, "error: wait linkup timeout\n"); - return 0; + return false; } static int meson_pcie_host_init(struct dw_pcie_rp *pp) diff --git a/drivers/pci/controller/dwc/pcie-al.c b/drivers/pci/controller/dwc/pcie-al.c index 643115f74092..345c281c74fe 100644 --- a/drivers/pci/controller/dwc/pcie-al.c +++ b/drivers/pci/controller/dwc/pcie-al.c @@ -352,6 +352,7 @@ static int al_pcie_probe(struct platform_device *pdev) return -ENOENT; } al_pcie->ecam_size = resource_size(ecam_res); + pci->pp.native_ecam = true; controller_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "controller"); diff --git a/drivers/pci/controller/dwc/pcie-amd-mdb.c b/drivers/pci/controller/dwc/pcie-amd-mdb.c new file mode 100644 index 000000000000..3c6e837465bb --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-amd-mdb.c @@ -0,0 +1,526 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for AMD MDB PCIe Bridge + * + * Copyright (C) 2024-2025, Advanced Micro Devices, Inc. + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/gpio.h> +#include <linux/interrupt.h> +#include <linux/irqdomain.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 "../../pci.h" +#include "pcie-designware.h" + +#define AMD_MDB_TLP_IR_STATUS_MISC 0x4C0 +#define AMD_MDB_TLP_IR_MASK_MISC 0x4C4 +#define AMD_MDB_TLP_IR_ENABLE_MISC 0x4C8 +#define AMD_MDB_TLP_IR_DISABLE_MISC 0x4CC + +#define AMD_MDB_TLP_PCIE_INTX_MASK GENMASK(23, 16) + +#define AMD_MDB_PCIE_INTR_INTX_ASSERT(x) BIT((x) * 2) + +/* Interrupt registers definitions. */ +#define AMD_MDB_PCIE_INTR_CMPL_TIMEOUT 15 +#define AMD_MDB_PCIE_INTR_INTX 16 +#define AMD_MDB_PCIE_INTR_PM_PME_RCVD 24 +#define AMD_MDB_PCIE_INTR_PME_TO_ACK_RCVD 25 +#define AMD_MDB_PCIE_INTR_MISC_CORRECTABLE 26 +#define AMD_MDB_PCIE_INTR_NONFATAL 27 +#define AMD_MDB_PCIE_INTR_FATAL 28 + +#define IMR(x) BIT(AMD_MDB_PCIE_INTR_ ##x) +#define AMD_MDB_PCIE_IMR_ALL_MASK \ + ( \ + IMR(CMPL_TIMEOUT) | \ + IMR(PM_PME_RCVD) | \ + IMR(PME_TO_ACK_RCVD) | \ + IMR(MISC_CORRECTABLE) | \ + IMR(NONFATAL) | \ + IMR(FATAL) | \ + AMD_MDB_TLP_PCIE_INTX_MASK \ + ) + +/** + * struct amd_mdb_pcie - PCIe port information + * @pci: DesignWare PCIe controller structure + * @slcr: MDB System Level Control and Status Register (SLCR) base + * @intx_domain: INTx IRQ domain pointer + * @mdb_domain: MDB IRQ domain pointer + * @perst_gpio: GPIO descriptor for PERST# signal handling + * @intx_irq: INTx IRQ interrupt number + */ +struct amd_mdb_pcie { + struct dw_pcie pci; + void __iomem *slcr; + struct irq_domain *intx_domain; + struct irq_domain *mdb_domain; + struct gpio_desc *perst_gpio; + int intx_irq; +}; + +static const struct dw_pcie_host_ops amd_mdb_pcie_host_ops = { +}; + +static void amd_mdb_intx_irq_mask(struct irq_data *data) +{ + struct amd_mdb_pcie *pcie = irq_data_get_irq_chip_data(data); + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *port = &pci->pp; + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = FIELD_PREP(AMD_MDB_TLP_PCIE_INTX_MASK, + AMD_MDB_PCIE_INTR_INTX_ASSERT(data->hwirq)); + + /* + * Writing '1' to a bit in AMD_MDB_TLP_IR_DISABLE_MISC disables that + * interrupt, writing '0' has no effect. + */ + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_DISABLE_MISC); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static void amd_mdb_intx_irq_unmask(struct irq_data *data) +{ + struct amd_mdb_pcie *pcie = irq_data_get_irq_chip_data(data); + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *port = &pci->pp; + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = FIELD_PREP(AMD_MDB_TLP_PCIE_INTX_MASK, + AMD_MDB_PCIE_INTR_INTX_ASSERT(data->hwirq)); + + /* + * Writing '1' to a bit in AMD_MDB_TLP_IR_ENABLE_MISC enables that + * interrupt, writing '0' has no effect. + */ + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_ENABLE_MISC); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static struct irq_chip amd_mdb_intx_irq_chip = { + .name = "AMD MDB INTx", + .irq_mask = amd_mdb_intx_irq_mask, + .irq_unmask = amd_mdb_intx_irq_unmask, +}; + +/** + * amd_mdb_pcie_intx_map - Set the handler for the INTx and mark IRQ as valid + * @domain: IRQ domain + * @irq: Virtual IRQ number + * @hwirq: Hardware interrupt number + * + * Return: Always returns '0'. + */ +static int amd_mdb_pcie_intx_map(struct irq_domain *domain, + unsigned int irq, irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &amd_mdb_intx_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 amd_intx_domain_ops = { + .map = amd_mdb_pcie_intx_map, +}; + +static irqreturn_t dw_pcie_rp_intx(int irq, void *args) +{ + struct amd_mdb_pcie *pcie = args; + unsigned long val; + int i, int_status; + + val = readl_relaxed(pcie->slcr + AMD_MDB_TLP_IR_STATUS_MISC); + int_status = FIELD_GET(AMD_MDB_TLP_PCIE_INTX_MASK, val); + + for (i = 0; i < PCI_NUM_INTX; i++) { + if (int_status & AMD_MDB_PCIE_INTR_INTX_ASSERT(i)) + generic_handle_domain_irq(pcie->intx_domain, i); + } + + return IRQ_HANDLED; +} + +#define _IC(x, s)[AMD_MDB_PCIE_INTR_ ## x] = { __stringify(x), s } + +static const struct { + const char *sym; + const char *str; +} intr_cause[32] = { + _IC(CMPL_TIMEOUT, "Completion timeout"), + _IC(PM_PME_RCVD, "PM_PME message received"), + _IC(PME_TO_ACK_RCVD, "PME_TO_ACK message received"), + _IC(MISC_CORRECTABLE, "Correctable error message"), + _IC(NONFATAL, "Non fatal error message"), + _IC(FATAL, "Fatal error message"), +}; + +static void amd_mdb_event_irq_mask(struct irq_data *d) +{ + struct amd_mdb_pcie *pcie = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *port = &pci->pp; + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = BIT(d->hwirq); + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_DISABLE_MISC); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static void amd_mdb_event_irq_unmask(struct irq_data *d) +{ + struct amd_mdb_pcie *pcie = irq_data_get_irq_chip_data(d); + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *port = &pci->pp; + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&port->lock, flags); + val = BIT(d->hwirq); + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_ENABLE_MISC); + raw_spin_unlock_irqrestore(&port->lock, flags); +} + +static struct irq_chip amd_mdb_event_irq_chip = { + .name = "AMD MDB RC-Event", + .irq_mask = amd_mdb_event_irq_mask, + .irq_unmask = amd_mdb_event_irq_unmask, +}; + +static int amd_mdb_pcie_event_map(struct irq_domain *domain, + unsigned int irq, irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &amd_mdb_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 = amd_mdb_pcie_event_map, +}; + +static irqreturn_t amd_mdb_pcie_event(int irq, void *args) +{ + struct amd_mdb_pcie *pcie = args; + unsigned long val; + int i; + + val = readl_relaxed(pcie->slcr + AMD_MDB_TLP_IR_STATUS_MISC); + val &= ~readl_relaxed(pcie->slcr + AMD_MDB_TLP_IR_MASK_MISC); + for_each_set_bit(i, &val, 32) + generic_handle_domain_irq(pcie->mdb_domain, i); + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_STATUS_MISC); + + return IRQ_HANDLED; +} + +static void amd_mdb_pcie_free_irq_domains(struct amd_mdb_pcie *pcie) +{ + if (pcie->intx_domain) { + irq_domain_remove(pcie->intx_domain); + pcie->intx_domain = NULL; + } + + if (pcie->mdb_domain) { + irq_domain_remove(pcie->mdb_domain); + pcie->mdb_domain = NULL; + } +} + +static int amd_mdb_pcie_init_port(struct amd_mdb_pcie *pcie) +{ + unsigned long val; + + /* Disable all TLP interrupts. */ + writel_relaxed(AMD_MDB_PCIE_IMR_ALL_MASK, + pcie->slcr + AMD_MDB_TLP_IR_DISABLE_MISC); + + /* Clear pending TLP interrupts. */ + val = readl_relaxed(pcie->slcr + AMD_MDB_TLP_IR_STATUS_MISC); + val &= AMD_MDB_PCIE_IMR_ALL_MASK; + writel_relaxed(val, pcie->slcr + AMD_MDB_TLP_IR_STATUS_MISC); + + /* Enable all TLP interrupts. */ + writel_relaxed(AMD_MDB_PCIE_IMR_ALL_MASK, + pcie->slcr + AMD_MDB_TLP_IR_ENABLE_MISC); + + return 0; +} + +/** + * amd_mdb_pcie_init_irq_domains - Initialize IRQ domain + * @pcie: PCIe port information + * @pdev: Platform device + * + * Return: Returns '0' on success and error value on failure. + */ +static int amd_mdb_pcie_init_irq_domains(struct amd_mdb_pcie *pcie, + struct platform_device *pdev) +{ + struct dw_pcie *pci = &pcie->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = &pdev->dev; + struct device_node *node = dev->of_node; + struct device_node *pcie_intc_node; + int err; + + pcie_intc_node = of_get_child_by_name(node, "interrupt-controller"); + if (!pcie_intc_node) { + dev_err(dev, "No PCIe Intc node found\n"); + return -ENODEV; + } + + pcie->mdb_domain = irq_domain_create_linear(of_fwnode_handle(pcie_intc_node), 32, + &event_domain_ops, pcie); + if (!pcie->mdb_domain) { + err = -ENOMEM; + dev_err(dev, "Failed to add MDB domain\n"); + goto out; + } + + irq_domain_update_bus_token(pcie->mdb_domain, DOMAIN_BUS_NEXUS); + + pcie->intx_domain = irq_domain_create_linear(of_fwnode_handle(pcie_intc_node), + PCI_NUM_INTX, &amd_intx_domain_ops, pcie); + if (!pcie->intx_domain) { + err = -ENOMEM; + dev_err(dev, "Failed to add INTx domain\n"); + goto mdb_out; + } + + of_node_put(pcie_intc_node); + irq_domain_update_bus_token(pcie->intx_domain, DOMAIN_BUS_WIRED); + + raw_spin_lock_init(&pp->lock); + + return 0; +mdb_out: + amd_mdb_pcie_free_irq_domains(pcie); +out: + of_node_put(pcie_intc_node); + return err; +} + +static irqreturn_t amd_mdb_pcie_intr_handler(int irq, void *args) +{ + struct amd_mdb_pcie *pcie = args; + struct device *dev; + struct irq_data *d; + + dev = pcie->pci.dev; + + /* + * In the future, error reporting will be hooked to the AER subsystem. + * Currently, the driver prints a warning message to the user. + */ + d = irq_domain_get_irq_data(pcie->mdb_domain, irq); + if (intr_cause[d->hwirq].str) + dev_warn(dev, "%s\n", intr_cause[d->hwirq].str); + else + dev_warn_once(dev, "Unknown IRQ %ld\n", d->hwirq); + + return IRQ_HANDLED; +} + +static int amd_mdb_setup_irq(struct amd_mdb_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 i, irq, err; + + amd_mdb_pcie_init_port(pcie); + + pp->irq = platform_get_irq(pdev, 0); + if (pp->irq < 0) + return pp->irq; + + for (i = 0; i < ARRAY_SIZE(intr_cause); i++) { + if (!intr_cause[i].str) + continue; + + irq = irq_create_mapping(pcie->mdb_domain, i); + if (!irq) { + dev_err(dev, "Failed to map MDB domain interrupt\n"); + return -ENOMEM; + } + + err = devm_request_irq(dev, irq, amd_mdb_pcie_intr_handler, + IRQF_NO_THREAD, intr_cause[i].sym, pcie); + if (err) { + dev_err(dev, "Failed to request IRQ %d, err=%d\n", + irq, err); + return err; + } + } + + pcie->intx_irq = irq_create_mapping(pcie->mdb_domain, + AMD_MDB_PCIE_INTR_INTX); + if (!pcie->intx_irq) { + dev_err(dev, "Failed to map INTx interrupt\n"); + return -ENXIO; + } + + err = devm_request_irq(dev, pcie->intx_irq, dw_pcie_rp_intx, + IRQF_NO_THREAD, NULL, pcie); + if (err) { + dev_err(dev, "Failed to request INTx IRQ %d, err=%d\n", + irq, err); + return err; + } + + /* Plug the main event handler. */ + err = devm_request_irq(dev, pp->irq, amd_mdb_pcie_event, IRQF_NO_THREAD, + "amd_mdb pcie_irq", pcie); + if (err) { + dev_err(dev, "Failed to request event IRQ %d, err=%d\n", + pp->irq, err); + return err; + } + + return 0; +} + +static int amd_mdb_parse_pcie_port(struct amd_mdb_pcie *pcie) +{ + struct device *dev = pcie->pci.dev; + struct device_node *pcie_port_node __maybe_unused; + + /* + * This platform currently supports only one Root Port, so the loop + * will execute only once. + * TODO: Enhance the driver to handle multiple Root Ports in the future. + */ + for_each_child_of_node_with_prefix(dev->of_node, pcie_port_node, "pcie") { + pcie->perst_gpio = devm_fwnode_gpiod_get(dev, of_fwnode_handle(pcie_port_node), + "reset", GPIOD_OUT_HIGH, NULL); + if (IS_ERR(pcie->perst_gpio)) + return dev_err_probe(dev, PTR_ERR(pcie->perst_gpio), + "Failed to request reset GPIO\n"); + return 0; + } + + return -ENODEV; +} + +static int amd_mdb_add_pcie_port(struct amd_mdb_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 err; + + pcie->slcr = devm_platform_ioremap_resource_byname(pdev, "slcr"); + if (IS_ERR(pcie->slcr)) + return PTR_ERR(pcie->slcr); + + err = amd_mdb_pcie_init_irq_domains(pcie, pdev); + if (err) + return err; + + err = amd_mdb_setup_irq(pcie, pdev); + if (err) { + dev_err(dev, "Failed to set up interrupts, err=%d\n", err); + goto out; + } + + pp->ops = &amd_mdb_pcie_host_ops; + + if (pcie->perst_gpio) { + mdelay(PCIE_T_PVPERL_MS); + gpiod_set_value_cansleep(pcie->perst_gpio, 0); + mdelay(PCIE_RESET_CONFIG_WAIT_MS); + } + + err = dw_pcie_host_init(pp); + if (err) { + dev_err(dev, "Failed to initialize host, err=%d\n", err); + goto out; + } + + return 0; + +out: + amd_mdb_pcie_free_irq_domains(pcie); + return err; +} + +static int amd_mdb_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct amd_mdb_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; + + platform_set_drvdata(pdev, pcie); + + ret = amd_mdb_parse_pcie_port(pcie); + /* + * If amd_mdb_parse_pcie_port returns -ENODEV, it indicates that the + * PCIe Bridge node was not found in the device tree. This is not + * considered a fatal error and will trigger a fallback where the + * reset GPIO is acquired directly from the PCIe Host Bridge node. + */ + if (ret) { + if (ret != -ENODEV) + return ret; + + pcie->perst_gpio = devm_gpiod_get_optional(dev, "reset", + GPIOD_OUT_HIGH); + if (IS_ERR(pcie->perst_gpio)) + return dev_err_probe(dev, PTR_ERR(pcie->perst_gpio), + "Failed to request reset GPIO\n"); + } + + return amd_mdb_add_pcie_port(pcie, pdev); +} + +static const struct of_device_id amd_mdb_pcie_of_match[] = { + { + .compatible = "amd,versal2-mdb-host", + }, + {}, +}; + +static struct platform_driver amd_mdb_pcie_driver = { + .driver = { + .name = "amd-mdb-pcie", + .of_match_table = amd_mdb_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = amd_mdb_pcie_probe, +}; + +builtin_platform_driver(amd_mdb_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c index b5c599ccaacf..c2650fd0d458 100644 --- a/drivers/pci/controller/dwc/pcie-armada8k.c +++ b/drivers/pci/controller/dwc/pcie-armada8k.c @@ -139,7 +139,7 @@ static int armada8k_pcie_setup_phys(struct armada8k_pcie *pcie) return ret; } -static int armada8k_pcie_link_up(struct dw_pcie *pci) +static bool armada8k_pcie_link_up(struct dw_pcie *pci) { u32 reg; u32 mask = PCIE_GLB_STS_RDLH_LINK_UP | PCIE_GLB_STS_PHY_LINK_UP; @@ -147,10 +147,10 @@ static int armada8k_pcie_link_up(struct dw_pcie *pci) reg = dw_pcie_readl_dbi(pci, PCIE_GLOBAL_STATUS_REG); if ((reg & mask) == mask) - return 1; + return true; dev_dbg(pci->dev, "No link detected (Global-Status: 0x%08x).\n", reg); - return 0; + return false; } static int armada8k_pcie_start_link(struct dw_pcie *pci) diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c index f8e7283dacd4..f4a136ee2daf 100644 --- a/drivers/pci/controller/dwc/pcie-artpec6.c +++ b/drivers/pci/controller/dwc/pcie-artpec6.c @@ -369,9 +369,20 @@ static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, return 0; } +static const struct pci_epc_features artpec6_pcie_epc_features = { + .msi_capable = true, +}; + +static const struct pci_epc_features * +artpec6_pcie_get_features(struct dw_pcie_ep *ep) +{ + return &artpec6_pcie_epc_features; +} + static const struct dw_pcie_ep_ops pcie_ep_ops = { .init = artpec6_pcie_ep_init, .raise_irq = artpec6_pcie_raise_irq, + .get_features = artpec6_pcie_get_features, }; static int artpec6_pcie_probe(struct platform_device *pdev) diff --git a/drivers/pci/controller/dwc/pcie-bt1.c b/drivers/pci/controller/dwc/pcie-bt1.c index 76d0ddea8007..1340edc18d12 100644 --- a/drivers/pci/controller/dwc/pcie-bt1.c +++ b/drivers/pci/controller/dwc/pcie-bt1.c @@ -632,7 +632,7 @@ MODULE_DEVICE_TABLE(of, bt1_pcie_of_match); static struct platform_driver bt1_pcie_driver = { .probe = bt1_pcie_probe, - .remove_new = bt1_pcie_remove, + .remove = bt1_pcie_remove, .driver = { .name = "bt1-pcie", .of_match_table = bt1_pcie_of_match, diff --git a/drivers/pci/controller/dwc/pcie-designware-debugfs.c b/drivers/pci/controller/dwc/pcie-designware-debugfs.c new file mode 100644 index 000000000000..0fbf86c0b97e --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-designware-debugfs.c @@ -0,0 +1,927 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Synopsys DesignWare PCIe controller debugfs driver + * + * Copyright (C) 2025 Samsung Electronics Co., Ltd. + * http://www.samsung.com + * + * Author: Shradha Todi <shradha.t@samsung.com> + */ + +#include <linux/debugfs.h> + +#include "pcie-designware.h" + +#define SD_STATUS_L1LANE_REG 0xb0 +#define PIPE_RXVALID BIT(18) +#define PIPE_DETECT_LANE BIT(17) +#define LANE_SELECT GENMASK(3, 0) + +#define ERR_INJ0_OFF 0x34 +#define EINJ_VAL_DIFF GENMASK(28, 16) +#define EINJ_VC_NUM GENMASK(14, 12) +#define EINJ_TYPE_SHIFT 8 +#define EINJ0_TYPE GENMASK(11, 8) +#define EINJ1_TYPE BIT(8) +#define EINJ2_TYPE GENMASK(9, 8) +#define EINJ3_TYPE GENMASK(10, 8) +#define EINJ4_TYPE GENMASK(10, 8) +#define EINJ5_TYPE BIT(8) +#define EINJ_COUNT GENMASK(7, 0) + +#define ERR_INJ_ENABLE_REG 0x30 + +#define RAS_DES_EVENT_COUNTER_DATA_REG 0xc + +#define RAS_DES_EVENT_COUNTER_CTRL_REG 0x8 +#define EVENT_COUNTER_GROUP_SELECT GENMASK(27, 24) +#define EVENT_COUNTER_EVENT_SELECT GENMASK(23, 16) +#define EVENT_COUNTER_LANE_SELECT GENMASK(11, 8) +#define EVENT_COUNTER_STATUS BIT(7) +#define EVENT_COUNTER_ENABLE GENMASK(4, 2) +#define PER_EVENT_ON 0x3 +#define PER_EVENT_OFF 0x1 + +#define DWC_DEBUGFS_BUF_MAX 128 + +/** + * struct dwc_pcie_rasdes_info - Stores controller common information + * @ras_cap_offset: RAS DES vendor specific extended capability offset + * @reg_event_lock: Mutex used for RAS DES shadow event registers + * + * Any parameter constant to all files of the debugfs hierarchy for a single + * controller will be stored in this struct. It is allocated and assigned to + * controller specific struct dw_pcie during initialization. + */ +struct dwc_pcie_rasdes_info { + u32 ras_cap_offset; + struct mutex reg_event_lock; +}; + +/** + * struct dwc_pcie_rasdes_priv - Stores file specific private data information + * @pci: Reference to the dw_pcie structure + * @idx: Index of specific file related information in array of structs + * + * All debugfs files will have this struct as its private data. + */ +struct dwc_pcie_rasdes_priv { + struct dw_pcie *pci; + int idx; +}; + +/** + * struct dwc_pcie_err_inj - Store details about each error injection + * supported by DWC RAS DES + * @name: Name of the error that can be injected + * @err_inj_group: Group number to which the error belongs. The value + * can range from 0 to 5 + * @err_inj_type: Each group can have multiple types of error + */ +struct dwc_pcie_err_inj { + const char *name; + u32 err_inj_group; + u32 err_inj_type; +}; + +static const struct dwc_pcie_err_inj err_inj_list[] = { + {"tx_lcrc", 0x0, 0x0}, + {"b16_crc_dllp", 0x0, 0x1}, + {"b16_crc_upd_fc", 0x0, 0x2}, + {"tx_ecrc", 0x0, 0x3}, + {"fcrc_tlp", 0x0, 0x4}, + {"parity_tsos", 0x0, 0x5}, + {"parity_skpos", 0x0, 0x6}, + {"rx_lcrc", 0x0, 0x8}, + {"rx_ecrc", 0x0, 0xb}, + {"tlp_err_seq", 0x1, 0x0}, + {"ack_nak_dllp_seq", 0x1, 0x1}, + {"ack_nak_dllp", 0x2, 0x0}, + {"upd_fc_dllp", 0x2, 0x1}, + {"nak_dllp", 0x2, 0x2}, + {"inv_sync_hdr_sym", 0x3, 0x0}, + {"com_pad_ts1", 0x3, 0x1}, + {"com_pad_ts2", 0x3, 0x2}, + {"com_fts", 0x3, 0x3}, + {"com_idl", 0x3, 0x4}, + {"end_edb", 0x3, 0x5}, + {"stp_sdp", 0x3, 0x6}, + {"com_skp", 0x3, 0x7}, + {"posted_tlp_hdr", 0x4, 0x0}, + {"non_post_tlp_hdr", 0x4, 0x1}, + {"cmpl_tlp_hdr", 0x4, 0x2}, + {"posted_tlp_data", 0x4, 0x4}, + {"non_post_tlp_data", 0x4, 0x5}, + {"cmpl_tlp_data", 0x4, 0x6}, + {"duplicate_tlp", 0x5, 0x0}, + {"nullified_tlp", 0x5, 0x1}, +}; + +static const u32 err_inj_type_mask[] = { + EINJ0_TYPE, + EINJ1_TYPE, + EINJ2_TYPE, + EINJ3_TYPE, + EINJ4_TYPE, + EINJ5_TYPE, +}; + +/** + * struct dwc_pcie_event_counter - Store details about each event counter + * supported in DWC RAS DES + * @name: Name of the error counter + * @group_no: Group number that the event belongs to. The value can range + * from 0 to 4 + * @event_no: Event number of the particular event. The value ranges are: + * Group 0: 0 - 10 + * Group 1: 5 - 13 + * Group 2: 0 - 7 + * Group 3: 0 - 5 + * Group 4: 0 - 1 + */ +struct dwc_pcie_event_counter { + const char *name; + u32 group_no; + u32 event_no; +}; + +static const struct dwc_pcie_event_counter event_list[] = { + {"ebuf_overflow", 0x0, 0x0}, + {"ebuf_underrun", 0x0, 0x1}, + {"decode_err", 0x0, 0x2}, + {"running_disparity_err", 0x0, 0x3}, + {"skp_os_parity_err", 0x0, 0x4}, + {"sync_header_err", 0x0, 0x5}, + {"rx_valid_deassertion", 0x0, 0x6}, + {"ctl_skp_os_parity_err", 0x0, 0x7}, + {"retimer_parity_err_1st", 0x0, 0x8}, + {"retimer_parity_err_2nd", 0x0, 0x9}, + {"margin_crc_parity_err", 0x0, 0xA}, + {"detect_ei_infer", 0x1, 0x5}, + {"receiver_err", 0x1, 0x6}, + {"rx_recovery_req", 0x1, 0x7}, + {"n_fts_timeout", 0x1, 0x8}, + {"framing_err", 0x1, 0x9}, + {"deskew_err", 0x1, 0xa}, + {"framing_err_in_l0", 0x1, 0xc}, + {"deskew_uncompleted_err", 0x1, 0xd}, + {"bad_tlp", 0x2, 0x0}, + {"lcrc_err", 0x2, 0x1}, + {"bad_dllp", 0x2, 0x2}, + {"replay_num_rollover", 0x2, 0x3}, + {"replay_timeout", 0x2, 0x4}, + {"rx_nak_dllp", 0x2, 0x5}, + {"tx_nak_dllp", 0x2, 0x6}, + {"retry_tlp", 0x2, 0x7}, + {"fc_timeout", 0x3, 0x0}, + {"poisoned_tlp", 0x3, 0x1}, + {"ecrc_error", 0x3, 0x2}, + {"unsupported_request", 0x3, 0x3}, + {"completer_abort", 0x3, 0x4}, + {"completion_timeout", 0x3, 0x5}, + {"ebuf_skp_add", 0x4, 0x0}, + {"ebuf_skp_del", 0x4, 0x1}, +}; + +static ssize_t lane_detect_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dw_pcie *pci = file->private_data; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + char debugfs_buf[DWC_DEBUGFS_BUF_MAX]; + ssize_t pos; + u32 val; + + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + SD_STATUS_L1LANE_REG); + val = FIELD_GET(PIPE_DETECT_LANE, val); + if (val) + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Lane Detected\n"); + else + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Lane Undetected\n"); + + return simple_read_from_buffer(buf, count, ppos, debugfs_buf, pos); +} + +static ssize_t lane_detect_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct dw_pcie *pci = file->private_data; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + u32 lane, val; + + val = kstrtou32_from_user(buf, count, 0, &lane); + if (val) + return val; + + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + SD_STATUS_L1LANE_REG); + val &= ~(LANE_SELECT); + val |= FIELD_PREP(LANE_SELECT, lane); + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + SD_STATUS_L1LANE_REG, val); + + return count; +} + +static ssize_t rx_valid_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dw_pcie *pci = file->private_data; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + char debugfs_buf[DWC_DEBUGFS_BUF_MAX]; + ssize_t pos; + u32 val; + + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + SD_STATUS_L1LANE_REG); + val = FIELD_GET(PIPE_RXVALID, val); + if (val) + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "RX Valid\n"); + else + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "RX Invalid\n"); + + return simple_read_from_buffer(buf, count, ppos, debugfs_buf, pos); +} + +static ssize_t rx_valid_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + return lane_detect_write(file, buf, count, ppos); +} + +static ssize_t err_inj_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + u32 val, counter, vc_num, err_group, type_mask; + int val_diff = 0; + char *kern_buf; + + err_group = err_inj_list[pdata->idx].err_inj_group; + type_mask = err_inj_type_mask[err_group]; + + kern_buf = memdup_user_nul(buf, count); + if (IS_ERR(kern_buf)) + return PTR_ERR(kern_buf); + + if (err_group == 4) { + val = sscanf(kern_buf, "%u %d %u", &counter, &val_diff, &vc_num); + if ((val != 3) || (val_diff < -4095 || val_diff > 4095)) { + kfree(kern_buf); + return -EINVAL; + } + } else if (err_group == 1) { + val = sscanf(kern_buf, "%u %d", &counter, &val_diff); + if ((val != 2) || (val_diff < -4095 || val_diff > 4095)) { + kfree(kern_buf); + return -EINVAL; + } + } else { + val = kstrtou32(kern_buf, 0, &counter); + if (val) { + kfree(kern_buf); + return val; + } + } + + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + ERR_INJ0_OFF + (0x4 * err_group)); + val &= ~(type_mask | EINJ_COUNT); + val |= ((err_inj_list[pdata->idx].err_inj_type << EINJ_TYPE_SHIFT) & type_mask); + val |= FIELD_PREP(EINJ_COUNT, counter); + + if (err_group == 1 || err_group == 4) { + val &= ~(EINJ_VAL_DIFF); + val |= FIELD_PREP(EINJ_VAL_DIFF, val_diff); + } + if (err_group == 4) { + val &= ~(EINJ_VC_NUM); + val |= FIELD_PREP(EINJ_VC_NUM, vc_num); + } + + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + ERR_INJ0_OFF + (0x4 * err_group), val); + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + ERR_INJ_ENABLE_REG, (0x1 << err_group)); + + kfree(kern_buf); + return count; +} + +static void set_event_number(struct dwc_pcie_rasdes_priv *pdata, + struct dw_pcie *pci, struct dwc_pcie_rasdes_info *rinfo) +{ + u32 val; + + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG); + val &= ~EVENT_COUNTER_ENABLE; + val &= ~(EVENT_COUNTER_GROUP_SELECT | EVENT_COUNTER_EVENT_SELECT); + val |= FIELD_PREP(EVENT_COUNTER_GROUP_SELECT, event_list[pdata->idx].group_no); + val |= FIELD_PREP(EVENT_COUNTER_EVENT_SELECT, event_list[pdata->idx].event_no); + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG, val); +} + +static ssize_t counter_enable_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + char debugfs_buf[DWC_DEBUGFS_BUF_MAX]; + ssize_t pos; + u32 val; + + mutex_lock(&rinfo->reg_event_lock); + set_event_number(pdata, pci, rinfo); + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG); + mutex_unlock(&rinfo->reg_event_lock); + val = FIELD_GET(EVENT_COUNTER_STATUS, val); + if (val) + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Counter Enabled\n"); + else + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Counter Disabled\n"); + + return simple_read_from_buffer(buf, count, ppos, debugfs_buf, pos); +} + +static ssize_t counter_enable_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + u32 val, enable; + + val = kstrtou32_from_user(buf, count, 0, &enable); + if (val) + return val; + + mutex_lock(&rinfo->reg_event_lock); + set_event_number(pdata, pci, rinfo); + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG); + if (enable) + val |= FIELD_PREP(EVENT_COUNTER_ENABLE, PER_EVENT_ON); + else + val |= FIELD_PREP(EVENT_COUNTER_ENABLE, PER_EVENT_OFF); + + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG, val); + + /* + * While enabling the counter, always read the status back to check if + * it is enabled or not. Return error if it is not enabled to let the + * users know that the counter is not supported on the platform. + */ + if (enable) { + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + + RAS_DES_EVENT_COUNTER_CTRL_REG); + if (!FIELD_GET(EVENT_COUNTER_STATUS, val)) { + mutex_unlock(&rinfo->reg_event_lock); + return -EOPNOTSUPP; + } + } + + mutex_unlock(&rinfo->reg_event_lock); + + return count; +} + +static ssize_t counter_lane_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + char debugfs_buf[DWC_DEBUGFS_BUF_MAX]; + ssize_t pos; + u32 val; + + mutex_lock(&rinfo->reg_event_lock); + set_event_number(pdata, pci, rinfo); + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG); + mutex_unlock(&rinfo->reg_event_lock); + val = FIELD_GET(EVENT_COUNTER_LANE_SELECT, val); + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Lane: %d\n", val); + + return simple_read_from_buffer(buf, count, ppos, debugfs_buf, pos); +} + +static ssize_t counter_lane_write(struct file *file, const char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + u32 val, lane; + + val = kstrtou32_from_user(buf, count, 0, &lane); + if (val) + return val; + + mutex_lock(&rinfo->reg_event_lock); + set_event_number(pdata, pci, rinfo); + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG); + val &= ~(EVENT_COUNTER_LANE_SELECT); + val |= FIELD_PREP(EVENT_COUNTER_LANE_SELECT, lane); + dw_pcie_writel_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_CTRL_REG, val); + mutex_unlock(&rinfo->reg_event_lock); + + return count; +} + +static ssize_t counter_value_read(struct file *file, char __user *buf, + size_t count, loff_t *ppos) +{ + struct dwc_pcie_rasdes_priv *pdata = file->private_data; + struct dw_pcie *pci = pdata->pci; + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + char debugfs_buf[DWC_DEBUGFS_BUF_MAX]; + ssize_t pos; + u32 val; + + mutex_lock(&rinfo->reg_event_lock); + set_event_number(pdata, pci, rinfo); + val = dw_pcie_readl_dbi(pci, rinfo->ras_cap_offset + RAS_DES_EVENT_COUNTER_DATA_REG); + mutex_unlock(&rinfo->reg_event_lock); + pos = scnprintf(debugfs_buf, DWC_DEBUGFS_BUF_MAX, "Counter value: %d\n", val); + + return simple_read_from_buffer(buf, count, ppos, debugfs_buf, pos); +} + +static const char *ltssm_status_string(enum dw_pcie_ltssm ltssm) +{ + const char *str; + + switch (ltssm) { +#define DW_PCIE_LTSSM_NAME(n) case n: str = #n; break + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DETECT_QUIET); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DETECT_ACT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_POLL_ACTIVE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_POLL_COMPLIANCE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_POLL_CONFIG); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_PRE_DETECT_QUIET); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DETECT_WAIT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_LINKWD_START); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_LINKWD_ACEPT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_LANENUM_WAI); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_LANENUM_ACEPT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_COMPLETE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_CFG_IDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_LOCK); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_SPEED); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_RCVRCFG); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_IDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L0); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L0S); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L123_SEND_EIDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L1_IDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L2_IDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L2_WAKE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DISABLED_ENTRY); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DISABLED_IDLE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_DISABLED); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_LPBK_ENTRY); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_LPBK_ACTIVE); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_LPBK_EXIT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_LPBK_EXIT_TIMEOUT); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_HOT_RESET_ENTRY); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_HOT_RESET); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_EQ0); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_EQ1); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_EQ2); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_RCVRY_EQ3); + default: + str = "DW_PCIE_LTSSM_UNKNOWN"; + break; + } + + return str + strlen("DW_PCIE_LTSSM_"); +} + +static int ltssm_status_show(struct seq_file *s, void *v) +{ + struct dw_pcie *pci = s->private; + enum dw_pcie_ltssm val; + + val = dw_pcie_get_ltssm(pci); + seq_printf(s, "%s (0x%02x)\n", ltssm_status_string(val), val); + + return 0; +} + +static int ltssm_status_open(struct inode *inode, struct file *file) +{ + return single_open(file, ltssm_status_show, inode->i_private); +} + +#define dwc_debugfs_create(name) \ +debugfs_create_file(#name, 0644, rasdes_debug, pci, \ + &dbg_ ## name ## _fops) + +#define DWC_DEBUGFS_FOPS(name) \ +static const struct file_operations dbg_ ## name ## _fops = { \ + .open = simple_open, \ + .read = name ## _read, \ + .write = name ## _write \ +} + +DWC_DEBUGFS_FOPS(lane_detect); +DWC_DEBUGFS_FOPS(rx_valid); + +static const struct file_operations dwc_pcie_err_inj_ops = { + .open = simple_open, + .write = err_inj_write, +}; + +static const struct file_operations dwc_pcie_counter_enable_ops = { + .open = simple_open, + .read = counter_enable_read, + .write = counter_enable_write, +}; + +static const struct file_operations dwc_pcie_counter_lane_ops = { + .open = simple_open, + .read = counter_lane_read, + .write = counter_lane_write, +}; + +static const struct file_operations dwc_pcie_counter_value_ops = { + .open = simple_open, + .read = counter_value_read, +}; + +static const struct file_operations dwc_pcie_ltssm_status_ops = { + .open = ltssm_status_open, + .read = seq_read, +}; + +static void dwc_pcie_rasdes_debugfs_deinit(struct dw_pcie *pci) +{ + struct dwc_pcie_rasdes_info *rinfo = pci->debugfs->rasdes_info; + + mutex_destroy(&rinfo->reg_event_lock); +} + +static int dwc_pcie_rasdes_debugfs_init(struct dw_pcie *pci, struct dentry *dir) +{ + struct dentry *rasdes_debug, *rasdes_err_inj; + struct dentry *rasdes_event_counter, *rasdes_events; + struct dwc_pcie_rasdes_info *rasdes_info; + struct dwc_pcie_rasdes_priv *priv_tmp; + struct device *dev = pci->dev; + int ras_cap, i, ret; + + /* + * If a given SoC has no RAS DES capability, the following call is + * bound to return an error, breaking some existing platforms. So, + * return 0 here, as this is not necessarily an error. + */ + ras_cap = dw_pcie_find_rasdes_capability(pci); + if (!ras_cap) { + dev_dbg(dev, "no RAS DES capability available\n"); + return 0; + } + + rasdes_info = devm_kzalloc(dev, sizeof(*rasdes_info), GFP_KERNEL); + if (!rasdes_info) + return -ENOMEM; + + /* Create subdirectories for Debug, Error Injection, Statistics. */ + rasdes_debug = debugfs_create_dir("rasdes_debug", dir); + rasdes_err_inj = debugfs_create_dir("rasdes_err_inj", dir); + rasdes_event_counter = debugfs_create_dir("rasdes_event_counter", dir); + + mutex_init(&rasdes_info->reg_event_lock); + rasdes_info->ras_cap_offset = ras_cap; + pci->debugfs->rasdes_info = rasdes_info; + + /* Create debugfs files for Debug subdirectory. */ + dwc_debugfs_create(lane_detect); + dwc_debugfs_create(rx_valid); + + /* Create debugfs files for Error Injection subdirectory. */ + for (i = 0; i < ARRAY_SIZE(err_inj_list); i++) { + priv_tmp = devm_kzalloc(dev, sizeof(*priv_tmp), GFP_KERNEL); + if (!priv_tmp) { + ret = -ENOMEM; + goto err_deinit; + } + + priv_tmp->idx = i; + priv_tmp->pci = pci; + debugfs_create_file(err_inj_list[i].name, 0200, rasdes_err_inj, priv_tmp, + &dwc_pcie_err_inj_ops); + } + + /* Create debugfs files for Statistical Counter subdirectory. */ + for (i = 0; i < ARRAY_SIZE(event_list); i++) { + priv_tmp = devm_kzalloc(dev, sizeof(*priv_tmp), GFP_KERNEL); + if (!priv_tmp) { + ret = -ENOMEM; + goto err_deinit; + } + + priv_tmp->idx = i; + priv_tmp->pci = pci; + rasdes_events = debugfs_create_dir(event_list[i].name, rasdes_event_counter); + if (event_list[i].group_no == 0 || event_list[i].group_no == 4) { + debugfs_create_file("lane_select", 0644, rasdes_events, + priv_tmp, &dwc_pcie_counter_lane_ops); + } + debugfs_create_file("counter_value", 0444, rasdes_events, priv_tmp, + &dwc_pcie_counter_value_ops); + debugfs_create_file("counter_enable", 0644, rasdes_events, priv_tmp, + &dwc_pcie_counter_enable_ops); + } + + return 0; + +err_deinit: + dwc_pcie_rasdes_debugfs_deinit(pci); + return ret; +} + +static void dwc_pcie_ltssm_debugfs_init(struct dw_pcie *pci, struct dentry *dir) +{ + debugfs_create_file("ltssm_status", 0444, dir, pci, + &dwc_pcie_ltssm_status_ops); +} + +static int dw_pcie_ptm_check_capability(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + pci->ptm_vsec_offset = dw_pcie_find_ptm_capability(pci); + + return pci->ptm_vsec_offset; +} + +static int dw_pcie_ptm_context_update_write(void *drvdata, u8 mode) +{ + struct dw_pcie *pci = drvdata; + u32 val; + + if (mode == PCIE_PTM_CONTEXT_UPDATE_AUTO) { + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + val |= PTM_REQ_AUTO_UPDATE_ENABLED; + dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val); + } else if (mode == PCIE_PTM_CONTEXT_UPDATE_MANUAL) { + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + val &= ~PTM_REQ_AUTO_UPDATE_ENABLED; + val |= PTM_REQ_START_UPDATE; + dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val); + } else { + return -EINVAL; + } + + return 0; +} + +static int dw_pcie_ptm_context_update_read(void *drvdata, u8 *mode) +{ + struct dw_pcie *pci = drvdata; + u32 val; + + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + if (FIELD_GET(PTM_REQ_AUTO_UPDATE_ENABLED, val)) + *mode = PCIE_PTM_CONTEXT_UPDATE_AUTO; + else + /* + * PTM_REQ_START_UPDATE is a self clearing register bit. So if + * PTM_REQ_AUTO_UPDATE_ENABLED is not set, then it implies that + * manual update is used. + */ + *mode = PCIE_PTM_CONTEXT_UPDATE_MANUAL; + + return 0; +} + +static int dw_pcie_ptm_context_valid_write(void *drvdata, bool valid) +{ + struct dw_pcie *pci = drvdata; + u32 val; + + if (valid) { + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + val |= PTM_RES_CCONTEXT_VALID; + dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val); + } else { + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + val &= ~PTM_RES_CCONTEXT_VALID; + dw_pcie_writel_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL, val); + } + + return 0; +} + +static int dw_pcie_ptm_context_valid_read(void *drvdata, bool *valid) +{ + struct dw_pcie *pci = drvdata; + u32 val; + + val = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_RES_REQ_CTRL); + *valid = !!FIELD_GET(PTM_RES_CCONTEXT_VALID, val); + + return 0; +} + +static int dw_pcie_ptm_local_clock_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_LOCAL_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_LOCAL_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_LOCAL_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static int dw_pcie_ptm_master_clock_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_MASTER_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_MASTER_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_MASTER_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static int dw_pcie_ptm_t1_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static int dw_pcie_ptm_t2_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T1_T2_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static int dw_pcie_ptm_t3_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static int dw_pcie_ptm_t4_read(void *drvdata, u64 *clock) +{ + struct dw_pcie *pci = drvdata; + u32 msb, lsb; + + do { + msb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB); + lsb = dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_LSB); + } while (msb != dw_pcie_readl_dbi(pci, pci->ptm_vsec_offset + PTM_T3_T4_MSB)); + + *clock = ((u64) msb) << 32 | lsb; + + return 0; +} + +static bool dw_pcie_ptm_context_update_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_EP_TYPE; +} + +static bool dw_pcie_ptm_context_valid_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_RC_TYPE; +} + +static bool dw_pcie_ptm_local_clock_visible(void *drvdata) +{ + /* PTM local clock is always visible */ + return true; +} + +static bool dw_pcie_ptm_master_clock_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_EP_TYPE; +} + +static bool dw_pcie_ptm_t1_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_EP_TYPE; +} + +static bool dw_pcie_ptm_t2_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_RC_TYPE; +} + +static bool dw_pcie_ptm_t3_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_RC_TYPE; +} + +static bool dw_pcie_ptm_t4_visible(void *drvdata) +{ + struct dw_pcie *pci = drvdata; + + return pci->mode == DW_PCIE_EP_TYPE; +} + +static const struct pcie_ptm_ops dw_pcie_ptm_ops = { + .check_capability = dw_pcie_ptm_check_capability, + .context_update_write = dw_pcie_ptm_context_update_write, + .context_update_read = dw_pcie_ptm_context_update_read, + .context_valid_write = dw_pcie_ptm_context_valid_write, + .context_valid_read = dw_pcie_ptm_context_valid_read, + .local_clock_read = dw_pcie_ptm_local_clock_read, + .master_clock_read = dw_pcie_ptm_master_clock_read, + .t1_read = dw_pcie_ptm_t1_read, + .t2_read = dw_pcie_ptm_t2_read, + .t3_read = dw_pcie_ptm_t3_read, + .t4_read = dw_pcie_ptm_t4_read, + .context_update_visible = dw_pcie_ptm_context_update_visible, + .context_valid_visible = dw_pcie_ptm_context_valid_visible, + .local_clock_visible = dw_pcie_ptm_local_clock_visible, + .master_clock_visible = dw_pcie_ptm_master_clock_visible, + .t1_visible = dw_pcie_ptm_t1_visible, + .t2_visible = dw_pcie_ptm_t2_visible, + .t3_visible = dw_pcie_ptm_t3_visible, + .t4_visible = dw_pcie_ptm_t4_visible, +}; + +void dwc_pcie_debugfs_deinit(struct dw_pcie *pci) +{ + if (!pci->debugfs) + return; + + pcie_ptm_destroy_debugfs(pci->ptm_debugfs); + dwc_pcie_rasdes_debugfs_deinit(pci); + debugfs_remove_recursive(pci->debugfs->debug_dir); +} + +void dwc_pcie_debugfs_init(struct dw_pcie *pci, enum dw_pcie_device_mode mode) +{ + char dirname[DWC_DEBUGFS_BUF_MAX]; + struct device *dev = pci->dev; + struct debugfs_info *debugfs; + struct dentry *dir; + int err; + + /* Create main directory for each platform driver. */ + snprintf(dirname, DWC_DEBUGFS_BUF_MAX, "dwc_pcie_%s", dev_name(dev)); + dir = debugfs_create_dir(dirname, NULL); + debugfs = devm_kzalloc(dev, sizeof(*debugfs), GFP_KERNEL); + if (!debugfs) + return; + + debugfs->debug_dir = dir; + pci->debugfs = debugfs; + err = dwc_pcie_rasdes_debugfs_init(pci, dir); + if (err) + dev_err(dev, "failed to initialize RAS DES debugfs, err=%d\n", + err); + + dwc_pcie_ltssm_debugfs_init(pci, dir); + + pci->mode = mode; + pci->ptm_debugfs = pcie_ptm_create_debugfs(pci->dev, pci, + &dw_pcie_ptm_ops); +} diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c index 43ba5c6738df..19571ac2b961 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -69,38 +69,50 @@ void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar) } 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) +static u8 dw_pcie_ep_find_capability(struct dw_pcie_ep *ep, u8 func_no, u8 cap) { - u8 cap_id, next_cap_ptr; - u16 reg; + return PCI_FIND_NEXT_CAP(dw_pcie_ep_read_cfg, PCI_CAPABILITY_LIST, + cap, ep, func_no); +} - if (!cap_ptr) - return 0; +/** + * dw_pcie_ep_hide_ext_capability - Hide a capability from the linked list + * @pci: DWC PCI device + * @prev_cap: Capability preceding the capability that should be hidden + * @cap: Capability that should be hidden + * + * Return: 0 if success, errno otherwise. + */ +int dw_pcie_ep_hide_ext_capability(struct dw_pcie *pci, u8 prev_cap, u8 cap) +{ + u16 prev_cap_offset, cap_offset; + u32 prev_cap_header, cap_header; - reg = dw_pcie_ep_readw_dbi(ep, func_no, cap_ptr); - cap_id = (reg & 0x00ff); + prev_cap_offset = dw_pcie_find_ext_capability(pci, prev_cap); + if (!prev_cap_offset) + return -EINVAL; - if (cap_id > PCI_CAP_ID_MAX) - return 0; + prev_cap_header = dw_pcie_readl_dbi(pci, prev_cap_offset); + cap_offset = PCI_EXT_CAP_NEXT(prev_cap_header); + cap_header = dw_pcie_readl_dbi(pci, cap_offset); - if (cap_id == cap) - return cap_ptr; + /* cap must immediately follow prev_cap. */ + if (PCI_EXT_CAP_ID(cap_header) != cap) + return -EINVAL; - next_cap_ptr = (reg & 0xff00) >> 8; - return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap); -} + /* Clear next ptr. */ + prev_cap_header &= ~GENMASK(31, 20); -static u8 dw_pcie_ep_find_capability(struct dw_pcie_ep *ep, u8 func_no, u8 cap) -{ - u8 next_cap_ptr; - u16 reg; + /* Set next ptr to next ptr of cap. */ + prev_cap_header |= cap_header & GENMASK(31, 20); - reg = dw_pcie_ep_readw_dbi(ep, func_no, PCI_CAPABILITY_LIST); - next_cap_ptr = (reg & 0x00ff); + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writel_dbi(pci, prev_cap_offset, prev_cap_header); + dw_pcie_dbi_ro_wr_dis(pci); - return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap); + return 0; } +EXPORT_SYMBOL_GPL(dw_pcie_ep_hide_ext_capability); static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_header *hdr) @@ -128,7 +140,8 @@ static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no, } 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) + dma_addr_t parent_bus_addr, enum pci_barno bar, + size_t size) { int ret; u32 free_win; @@ -145,7 +158,7 @@ static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no, int type, } ret = dw_pcie_prog_ep_inbound_atu(pci, func_no, free_win, type, - cpu_addr, bar); + parent_bus_addr, bar, size); if (ret < 0) { dev_err(pci->dev, "Failed to program IB window\n"); return ret; @@ -180,7 +193,7 @@ static int dw_pcie_ep_outbound_atu(struct dw_pcie_ep *ep, return ret; set_bit(free_win, ep->ob_window_map); - ep->outbound_addr[free_win] = atu->cpu_addr; + ep->outbound_addr[free_win] = atu->parent_bus_addr; return 0; } @@ -204,6 +217,125 @@ static void dw_pcie_ep_clear_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, ep->bar_to_atu[bar] = 0; } +static unsigned int dw_pcie_ep_get_rebar_offset(struct dw_pcie *pci, + enum pci_barno bar) +{ + u32 reg, bar_index; + unsigned int offset, nbars; + int i; + + offset = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_REBAR); + if (!offset) + return offset; + + reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL); + nbars = FIELD_GET(PCI_REBAR_CTRL_NBAR_MASK, reg); + + for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL) { + reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL); + bar_index = FIELD_GET(PCI_REBAR_CTRL_BAR_IDX, reg); + if (bar_index == bar) + return offset; + } + + return 0; +} + +static int dw_pcie_ep_set_bar_resizable(struct dw_pcie_ep *ep, u8 func_no, + struct pci_epf_bar *epf_bar) +{ + 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; + u32 reg = PCI_BASE_ADDRESS_0 + (4 * bar); + unsigned int rebar_offset; + u32 rebar_cap, rebar_ctrl; + int ret; + + rebar_offset = dw_pcie_ep_get_rebar_offset(pci, bar); + if (!rebar_offset) + return -EINVAL; + + ret = pci_epc_bar_size_to_rebar_cap(size, &rebar_cap); + if (ret) + return ret; + + dw_pcie_dbi_ro_wr_en(pci); + + /* + * A BAR mask should not be written for a resizable BAR. The BAR mask + * is automatically derived by the controller every time the "selected + * size" bits are updated, see "Figure 3-26 Resizable BAR Example for + * 32-bit Memory BAR0" in DWC EP databook 5.96a. We simply need to write + * BIT(0) to set the BAR enable bit. + */ + dw_pcie_ep_writel_dbi2(ep, func_no, reg, BIT(0)); + dw_pcie_ep_writel_dbi(ep, func_no, reg, flags); + + if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) { + dw_pcie_ep_writel_dbi2(ep, func_no, reg + 4, 0); + dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0); + } + + /* + * Bits 31:0 in PCI_REBAR_CAP define "supported sizes" bits for sizes + * 1 MB to 128 TB. Bits 31:16 in PCI_REBAR_CTRL define "supported sizes" + * bits for sizes 256 TB to 8 EB. Disallow sizes 256 TB to 8 EB. + */ + rebar_ctrl = dw_pcie_readl_dbi(pci, rebar_offset + PCI_REBAR_CTRL); + rebar_ctrl &= ~GENMASK(31, 16); + dw_pcie_writel_dbi(pci, rebar_offset + PCI_REBAR_CTRL, rebar_ctrl); + + /* + * The "selected size" (bits 13:8) in PCI_REBAR_CTRL are automatically + * updated when writing PCI_REBAR_CAP, see "Figure 3-26 Resizable BAR + * Example for 32-bit Memory BAR0" in DWC EP databook 5.96a. + */ + dw_pcie_writel_dbi(pci, rebar_offset + PCI_REBAR_CAP, rebar_cap); + + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static int dw_pcie_ep_set_bar_programmable(struct dw_pcie_ep *ep, u8 func_no, + struct pci_epf_bar *epf_bar) +{ + 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; + u32 reg = PCI_BASE_ADDRESS_0 + (4 * bar); + + dw_pcie_dbi_ro_wr_en(pci); + + dw_pcie_ep_writel_dbi2(ep, func_no, reg, lower_32_bits(size - 1)); + dw_pcie_ep_writel_dbi(ep, func_no, reg, flags); + + if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) { + dw_pcie_ep_writel_dbi2(ep, func_no, reg + 4, upper_32_bits(size - 1)); + dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0); + } + + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static enum pci_epc_bar_type dw_pcie_ep_get_bar_type(struct dw_pcie_ep *ep, + enum pci_barno bar) +{ + const struct pci_epc_features *epc_features; + + if (!ep->ops->get_features) + return BAR_PROGRAMMABLE; + + epc_features = ep->ops->get_features(ep); + + return epc_features->bar[bar].type; +} + static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct pci_epf_bar *epf_bar) { @@ -211,9 +343,9 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, struct dw_pcie *pci = to_dw_pcie_from_ep(ep); enum pci_barno bar = epf_bar->barno; size_t size = epf_bar->size; + enum pci_epc_bar_type bar_type; int flags = epf_bar->flags; int ret, type; - u32 reg; /* * DWC does not allow BAR pairs to overlap, e.g. you cannot combine BARs @@ -222,32 +354,66 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, if ((flags & PCI_BASE_ADDRESS_MEM_TYPE_64) && (bar & 1)) return -EINVAL; - reg = PCI_BASE_ADDRESS_0 + (4 * bar); + /* + * Certain EPF drivers dynamically change the physical address of a BAR + * (i.e. they call set_bar() twice, without ever calling clear_bar(), as + * calling clear_bar() would clear the BAR's PCI address assigned by the + * host). + */ + if (ep->epf_bar[bar]) { + /* + * We can only dynamically change a BAR if the new BAR size and + * BAR flags do not differ from the existing configuration. + */ + if (ep->epf_bar[bar]->barno != bar || + ep->epf_bar[bar]->size != size || + ep->epf_bar[bar]->flags != flags) + return -EINVAL; + /* + * When dynamically changing a BAR, skip writing the BAR reg, as + * that would clear the BAR's PCI address assigned by the host. + */ + goto config_atu; + } + + bar_type = dw_pcie_ep_get_bar_type(ep, bar); + switch (bar_type) { + case BAR_FIXED: + /* + * There is no need to write a BAR mask for a fixed BAR (except + * to write 1 to the LSB of the BAR mask register, to enable the + * BAR). Write the BAR mask regardless. (The fixed bits in the + * BAR mask register will be read-only anyway.) + */ + fallthrough; + case BAR_PROGRAMMABLE: + ret = dw_pcie_ep_set_bar_programmable(ep, func_no, epf_bar); + break; + case BAR_RESIZABLE: + ret = dw_pcie_ep_set_bar_resizable(ep, func_no, epf_bar); + break; + default: + ret = -EINVAL; + dev_err(pci->dev, "Invalid BAR type\n"); + break; + } + + if (ret) + return ret; + +config_atu: 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); + ret = dw_pcie_ep_inbound_atu(ep, func_no, type, epf_bar->phys_addr, bar, + size); if (ret) return ret; - if (ep->epf_bar[bar]) - return 0; - - dw_pcie_dbi_ro_wr_en(pci); - - dw_pcie_ep_writel_dbi2(ep, func_no, reg, lower_32_bits(size - 1)); - dw_pcie_ep_writel_dbi(ep, func_no, reg, flags); - - if (flags & PCI_BASE_ADDRESS_MEM_TYPE_64) { - dw_pcie_ep_writel_dbi2(ep, func_no, reg + 4, upper_32_bits(size - 1)); - dw_pcie_ep_writel_dbi(ep, func_no, reg + 4, 0); - } - ep->epf_bar[bar] = epf_bar; - dw_pcie_dbi_ro_wr_dis(pci); return 0; } @@ -258,7 +424,7 @@ static int dw_pcie_find_index(struct dw_pcie_ep *ep, phys_addr_t addr, u32 index; struct dw_pcie *pci = to_dw_pcie_from_ep(ep); - for (index = 0; index < pci->num_ob_windows; index++) { + for_each_set_bit(index, ep->ob_window_map, pci->num_ob_windows) { if (ep->outbound_addr[index] != addr) continue; *atu_index = index; @@ -268,6 +434,20 @@ static int dw_pcie_find_index(struct dw_pcie_ep *ep, phys_addr_t addr, return -EINVAL; } +static u64 dw_pcie_ep_align_addr(struct pci_epc *epc, u64 pci_addr, + size_t *pci_size, size_t *offset) +{ + struct dw_pcie_ep *ep = epc_get_drvdata(epc); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u64 mask = pci->region_align - 1; + size_t ofst = pci_addr & mask; + + *pci_size = ALIGN(ofst + *pci_size, epc->mem->window.page_size); + *offset = ofst; + + return pci_addr & ~mask; +} + static void dw_pcie_ep_unmap_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, phys_addr_t addr) { @@ -276,10 +456,12 @@ static void dw_pcie_ep_unmap_addr(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); - ret = dw_pcie_find_index(ep, addr, &atu_index); + ret = dw_pcie_find_index(ep, addr - pci->parent_bus_offset, + &atu_index); if (ret < 0) return; + ep->outbound_addr[atu_index] = 0; dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_OB, atu_index); clear_bit(atu_index, ep->ob_window_map); } @@ -294,7 +476,7 @@ static int dw_pcie_ep_map_addr(struct pci_epc *epc, u8 func_no, u8 vfunc_no, atu.func_no = func_no; atu.type = PCIE_ATU_TYPE_MEM; - atu.cpu_addr = addr; + atu.parent_bus_addr = addr - pci->parent_bus_offset; atu.pci_addr = pci_addr; atu.size = size; ret = dw_pcie_ep_outbound_atu(ep, &atu); @@ -323,15 +505,16 @@ static int dw_pcie_ep_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no) val = FIELD_GET(PCI_MSI_FLAGS_QSIZE, val); - return val; + return 1 << val; } static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, - u8 interrupts) + u8 nr_irqs) { struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); struct dw_pcie_ep_func *ep_func; + u8 mmc = order_base_2(nr_irqs); u32 val, reg; ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); @@ -341,7 +524,7 @@ static int dw_pcie_ep_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, reg = ep_func->msi_cap + PCI_MSI_FLAGS; val = dw_pcie_ep_readw_dbi(ep, func_no, reg); val &= ~PCI_MSI_FLAGS_QMASK; - val |= FIELD_PREP(PCI_MSI_FLAGS_QMASK, interrupts); + val |= FIELD_PREP(PCI_MSI_FLAGS_QMASK, mmc); dw_pcie_dbi_ro_wr_en(pci); dw_pcie_ep_writew_dbi(ep, func_no, reg, val); dw_pcie_dbi_ro_wr_dis(pci); @@ -366,11 +549,11 @@ static int dw_pcie_ep_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no) val &= PCI_MSIX_FLAGS_QSIZE; - return val; + return val + 1; } 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) + u16 nr_irqs, 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); @@ -386,7 +569,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, reg = ep_func->msix_cap + PCI_MSIX_FLAGS; val = dw_pcie_ep_readw_dbi(ep, func_no, reg); val &= ~PCI_MSIX_FLAGS_QSIZE; - val |= interrupts; + val |= nr_irqs - 1; /* encoded as N-1 */ dw_pcie_writew_dbi(pci, reg, val); reg = ep_func->msix_cap + PCI_MSIX_TABLE; @@ -394,7 +577,7 @@ static int dw_pcie_ep_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, dw_pcie_ep_writel_dbi(ep, func_no, reg, val); reg = ep_func->msix_cap + PCI_MSIX_PBA; - val = (offset + (interrupts * PCI_MSIX_ENTRY_SIZE)) | bir; + val = (offset + (nr_irqs * PCI_MSIX_ENTRY_SIZE)) | bir; dw_pcie_ep_writel_dbi(ep, func_no, reg, val); dw_pcie_dbi_ro_wr_dis(pci); @@ -444,6 +627,7 @@ 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, + .align_addr = dw_pcie_ep_align_addr, .map_addr = dw_pcie_ep_map_addr, .unmap_addr = dw_pcie_ep_unmap_addr, .set_msi = dw_pcie_ep_set_msi, @@ -461,7 +645,7 @@ static const struct pci_epc_ops epc_ops = { * @ep: DWC EP device * @func_no: Function number of the endpoint * - * Return: 0 if success, errono otherwise. + * Return: 0 if success, errno otherwise. */ int dw_pcie_ep_raise_intx_irq(struct dw_pcie_ep *ep, u8 func_no) { @@ -480,7 +664,7 @@ EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_intx_irq); * @func_no: Function number of the endpoint * @interrupt_num: Interrupt number to be raised * - * Return: 0 if success, errono otherwise. + * Return: 0 if success, errno otherwise. */ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, u8 interrupt_num) @@ -488,7 +672,8 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, u32 msg_addr_lower, msg_addr_upper, reg; struct dw_pcie_ep_func *ep_func; struct pci_epc *epc = ep->epc; - unsigned int aligned_offset; + size_t map_size = sizeof(u32); + size_t offset; u16 msg_ctrl, msg_data; bool has_upper; u64 msg_addr; @@ -516,14 +701,13 @@ int dw_pcie_ep_raise_msi_irq(struct dw_pcie_ep *ep, u8 func_no, } msg_addr = ((u64)msg_addr_upper) << 32 | msg_addr_lower; - aligned_offset = msg_addr & (epc->mem->window.page_size - 1); - msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size); + msg_addr = dw_pcie_ep_align_addr(epc, msg_addr, &map_size, &offset); ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, - epc->mem->window.page_size); + map_size); if (ret) return ret; - writel(msg_data | (interrupt_num - 1), ep->msi_mem + aligned_offset); + writel(msg_data | (interrupt_num - 1), ep->msi_mem + offset); dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys); @@ -574,8 +758,9 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, struct pci_epf_msix_tbl *msix_tbl; struct dw_pcie_ep_func *ep_func; struct pci_epc *epc = ep->epc; + size_t map_size = sizeof(u32); + size_t offset; u32 reg, msg_data, vec_ctrl; - unsigned int aligned_offset; u32 tbl_offset; u64 msg_addr; int ret; @@ -600,19 +785,19 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, return -EPERM; } - aligned_offset = msg_addr & (epc->mem->window.page_size - 1); - msg_addr = ALIGN_DOWN(msg_addr, epc->mem->window.page_size); + msg_addr = dw_pcie_ep_align_addr(epc, msg_addr, &map_size, &offset); ret = dw_pcie_ep_map_addr(epc, func_no, 0, ep->msi_mem_phys, msg_addr, - epc->mem->window.page_size); + map_size); if (ret) return ret; - writel(msg_data, ep->msi_mem + aligned_offset); + writel(msg_data, ep->msi_mem + offset); dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys); return 0; } +EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_msix_irq); /** * dw_pcie_ep_cleanup - Cleanup DWC EP resources after fundamental reset @@ -626,6 +811,7 @@ void dw_pcie_ep_cleanup(struct dw_pcie_ep *ep) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + dwc_pcie_debugfs_deinit(pci); dw_pcie_edma_remove(pci); } EXPORT_SYMBOL_GPL(dw_pcie_ep_cleanup); @@ -650,46 +836,49 @@ void dw_pcie_ep_deinit(struct dw_pcie_ep *ep) } EXPORT_SYMBOL_GPL(dw_pcie_ep_deinit); -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; -} - static void dw_pcie_ep_init_non_sticky_registers(struct dw_pcie *pci) { + struct dw_pcie_ep *ep = &pci->ep; unsigned int offset; unsigned int nbars; - u32 reg, i; + enum pci_barno bar; + u32 reg, i, val; - offset = dw_pcie_ep_find_ext_capability(pci, PCI_EXT_CAP_ID_REBAR); + offset = dw_pcie_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; + nbars = FIELD_GET(PCI_REBAR_CTRL_NBAR_MASK, reg); /* * PCIe r6.0, sec 7.8.6.2 require us to support at least one * size in the range from 1 MB to 512 GB. Advertise support * for 1 MB BAR size only. + * + * For a BAR that has been configured via dw_pcie_ep_set_bar(), + * advertise support for only that size instead. */ - for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL) - dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, 0x0); + for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL) { + /* + * While the RESBAR_CAP_REG_* fields are sticky, the + * RESBAR_CTRL_REG_BAR_SIZE field is non-sticky (it is + * sticky in certain versions of DWC PCIe, but not all). + * + * RESBAR_CTRL_REG_BAR_SIZE is updated automatically by + * the controller when RESBAR_CAP_REG is written, which + * is why RESBAR_CAP_REG is written here. + */ + val = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL); + bar = FIELD_GET(PCI_REBAR_CTRL_BAR_IDX, val); + if (ep->epf_bar[bar]) + pci_epc_bar_size_to_rebar_cap(ep->epf_bar[bar]->size, &val); + else + val = BIT(4); + + dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, val); + } } dw_pcie_setup(pci); @@ -733,6 +922,7 @@ int dw_pcie_ep_init_registers(struct dw_pcie_ep *ep) if (ret) return ret; + ret = -ENOMEM; if (!ep->ib_window_map) { ep->ib_window_map = devm_bitmap_zalloc(dev, pci->num_ib_windows, GFP_KERNEL); @@ -777,7 +967,7 @@ int dw_pcie_ep_init_registers(struct dw_pcie_ep *ep) if (ep->ops->init) ep->ops->init(ep); - ptm_cap_base = dw_pcie_ep_find_ext_capability(pci, PCI_EXT_CAP_ID_PTM); + ptm_cap_base = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_PTM); /* * PTM responder capability can be disabled only after disabling @@ -797,6 +987,8 @@ int dw_pcie_ep_init_registers(struct dw_pcie_ep *ep) dw_pcie_ep_init_non_sticky_registers(pci); + dwc_pcie_debugfs_init(pci, DW_PCIE_EP_TYPE); + return 0; err_remove_edma: @@ -843,26 +1035,15 @@ void dw_pcie_ep_linkdown(struct dw_pcie_ep *ep) } EXPORT_SYMBOL_GPL(dw_pcie_ep_linkdown); -/** - * dw_pcie_ep_init - Initialize the endpoint device - * @ep: DWC EP device - * - * Initialize the endpoint device. Allocate resources and create the EPC - * device with the endpoint framework. - * - * Return: 0 if success, errno otherwise. - */ -int dw_pcie_ep_init(struct dw_pcie_ep *ep) +static int dw_pcie_ep_get_resources(struct dw_pcie_ep *ep) { - int ret; - 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; - - INIT_LIST_HEAD(&ep->func_list); + struct pci_epc *epc = ep->epc; + struct resource *res; + int ret; ret = dw_pcie_get_resources(pci); if (ret) @@ -875,8 +1056,37 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep) ep->phys_base = res->start; ep->addr_size = resource_size(res); - if (ep->ops->pre_init) - ep->ops->pre_init(ep); + /* + * artpec6_pcie_cpu_addr_fixup() uses ep->phys_base, so call + * dw_pcie_parent_bus_offset() after setting ep->phys_base. + */ + pci->parent_bus_offset = dw_pcie_parent_bus_offset(pci, "addr_space", + ep->phys_base); + + ret = of_property_read_u8(np, "max-functions", &epc->max_functions); + if (ret < 0) + epc->max_functions = 1; + + return 0; +} + +/** + * dw_pcie_ep_init - Initialize the endpoint device + * @ep: DWC EP device + * + * Initialize the endpoint device. Allocate resources and create the EPC + * device with the endpoint framework. + * + * Return: 0 if success, errno otherwise. + */ +int dw_pcie_ep_init(struct dw_pcie_ep *ep) +{ + int ret; + struct pci_epc *epc; + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct device *dev = pci->dev; + + INIT_LIST_HEAD(&ep->func_list); epc = devm_pci_epc_create(dev, &epc_ops); if (IS_ERR(epc)) { @@ -887,9 +1097,12 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep) 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; + ret = dw_pcie_ep_get_resources(ep); + if (ret) + return ret; + + if (ep->ops->pre_init) + ep->ops->pre_init(ep); ret = pci_epc_mem_init(epc, ep->phys_base, ep->addr_size, ep->page_size); diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index 3e41865c7290..372207c33a85 100644 --- a/drivers/pci/controller/dwc/pcie-designware-host.c +++ b/drivers/pci/controller/dwc/pcie-designware-host.c @@ -8,8 +8,10 @@ * Author: Jingoo Han <jg1.han@samsung.com> */ +#include <linux/align.h> #include <linux/iopoll.h> #include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/msi.h> #include <linux/of_address.h> @@ -21,37 +23,26 @@ #include "pcie-designware.h" static struct pci_ops dw_pcie_ops; +static struct pci_ops dw_pcie_ecam_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_NO_AFFINITY | MSI_FLAG_PCI_MSIX | - MSI_FLAG_MULTI_PCI_MSI, - .chip = &dw_pcie_msi_irq_chip, +#define DW_PCIE_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY | \ + MSI_FLAG_PCI_MSI_MASK_PARENT) +#define DW_PCIE_MSI_FLAGS_SUPPORTED (MSI_FLAG_MULTI_PCI_MSI | \ + MSI_FLAG_PCI_MSIX | \ + MSI_GENERIC_FLAGS_MASK) + +#define IS_256MB_ALIGNED(x) IS_ALIGNED(x, SZ_256M) + +static const struct msi_parent_ops dw_pcie_msi_parent_ops = { + .required_flags = DW_PCIE_MSI_FLAGS_REQUIRED, + .supported_flags = DW_PCIE_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .chip_flags = MSI_CHIP_FLAG_SET_ACK, + .prefix = "DW-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; /* MSI int handler */ @@ -227,30 +218,24 @@ static const struct irq_domain_ops dw_pcie_msi_domain_ops = { 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); + struct irq_domain_info info = { + .fwnode = dev_fwnode(pci->dev), + .ops = &dw_pcie_msi_domain_ops, + .size = pp->num_vectors, + .host_data = pp, + }; + + pp->irq_domain = msi_create_parent_irq_domain(&info, &dw_pcie_msi_parent_ops); 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; } +EXPORT_SYMBOL_GPL(dw_pcie_allocate_domains); -static void dw_pcie_free_msi(struct dw_pcie_rp *pp) +void dw_pcie_free_msi(struct dw_pcie_rp *pp) { u32 ctrl; @@ -260,22 +245,36 @@ static void dw_pcie_free_msi(struct dw_pcie_rp *pp) NULL, NULL); } - irq_domain_remove(pp->msi_domain); irq_domain_remove(pp->irq_domain); } +EXPORT_SYMBOL_GPL(dw_pcie_free_msi); -static void dw_pcie_msi_init(struct dw_pcie_rp *pp) +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; + u32 ctrl, num_ctrls; if (!pci_msi_enabled() || !pp->has_msi_ctrl) return; + 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); + } + /* 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)); } +EXPORT_SYMBOL_GPL(dw_pcie_msi_init); static int dw_pcie_parse_split_msi_irq(struct dw_pcie_rp *pp) { @@ -317,7 +316,7 @@ static int dw_pcie_parse_split_msi_irq(struct dw_pcie_rp *pp) return 0; } -static int dw_pcie_msi_host_init(struct dw_pcie_rp *pp) +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; @@ -391,6 +390,7 @@ static int dw_pcie_msi_host_init(struct dw_pcie_rp *pp) return 0; } +EXPORT_SYMBOL_GPL(dw_pcie_msi_host_init); static void dw_pcie_host_request_msg_tlp_res(struct dw_pcie_rp *pp) { @@ -418,64 +418,184 @@ static void dw_pcie_host_request_msg_tlp_res(struct dw_pcie_rp *pp) } } -int dw_pcie_host_init(struct dw_pcie_rp *pp) +static int dw_pcie_config_ecam_iatu(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct dw_pcie_ob_atu_cfg atu = {0}; + resource_size_t bus_range_max; + struct resource_entry *bus; + int ret; + + bus = resource_list_first_type(&pp->bridge->windows, IORESOURCE_BUS); + + /* + * Root bus under the host bridge doesn't require any iATU configuration + * as DBI region will be used to access root bus config space. + * Immediate bus under Root Bus, needs type 0 iATU configuration and + * remaining buses need type 1 iATU configuration. + */ + atu.index = 0; + atu.type = PCIE_ATU_TYPE_CFG0; + atu.parent_bus_addr = pp->cfg0_base + SZ_1M; + /* 1MiB is to cover 1 (bus) * 32 (devices) * 8 (functions) */ + atu.size = SZ_1M; + atu.ctrl2 = PCIE_ATU_CFG_SHIFT_MODE_ENABLE; + ret = dw_pcie_prog_outbound_atu(pci, &atu); + if (ret) + return ret; + + bus_range_max = resource_size(bus->res); + + if (bus_range_max < 2) + return 0; + + /* Configure remaining buses in type 1 iATU configuration */ + atu.index = 1; + atu.type = PCIE_ATU_TYPE_CFG1; + atu.parent_bus_addr = pp->cfg0_base + SZ_2M; + atu.size = (SZ_1M * bus_range_max) - SZ_2M; + atu.ctrl2 = PCIE_ATU_CFG_SHIFT_MODE_ENABLE; + + return dw_pcie_prog_outbound_atu(pci, &atu); +} + +static int dw_pcie_create_ecam_window(struct dw_pcie_rp *pp, struct resource *res) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct device *dev = pci->dev; + struct resource_entry *bus; + + bus = resource_list_first_type(&pp->bridge->windows, IORESOURCE_BUS); + if (!bus) + return -ENODEV; + + pp->cfg = pci_ecam_create(dev, res, bus->res, &pci_generic_ecam_ops); + if (IS_ERR(pp->cfg)) + return PTR_ERR(pp->cfg); + + return 0; +} + +static bool dw_pcie_ecam_enabled(struct dw_pcie_rp *pp, struct resource *config_res) +{ + struct resource *bus_range; + u64 nr_buses; + + /* Vendor glue drivers may implement their own ECAM mechanism */ + if (pp->native_ecam) + return false; + + /* + * PCIe spec r6.0, sec 7.2.2 mandates the base address used for ECAM to + * be aligned on a 2^(n+20) byte boundary, where n is the number of bits + * used for representing 'bus' in BDF. Since the DWC cores always use 8 + * bits for representing 'bus', the base address has to be aligned to + * 2^28 byte boundary, which is 256 MiB. + */ + if (!IS_256MB_ALIGNED(config_res->start)) + return false; + + bus_range = resource_list_first_type(&pp->bridge->windows, IORESOURCE_BUS)->res; + if (!bus_range) + return false; + + nr_buses = resource_size(config_res) >> PCIE_ECAM_BUS_SHIFT; + + return nr_buses >= resource_size(bus_range); +} + +static int dw_pcie_host_get_resources(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) { + dev_err(dev, "Missing \"config\" reg space\n"); + return -ENODEV; + } - ret = dw_pcie_get_resources(pci); - if (ret) - return ret; + pp->cfg0_size = resource_size(res); + pp->cfg0_base = res->start; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config"); - if (res) { - pp->cfg0_size = resource_size(res); - pp->cfg0_base = res->start; + pp->ecam_enabled = dw_pcie_ecam_enabled(pp, res); + if (pp->ecam_enabled) { + ret = dw_pcie_create_ecam_window(pp, res); + if (ret) + return ret; + pp->bridge->ops = &dw_pcie_ecam_ops; + pp->bridge->sysdata = pp->cfg; + pp->cfg->priv = pp; + } else { 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; - } - bridge = devm_pci_alloc_host_bridge(dev, 0); - if (!bridge) - return -ENOMEM; + /* Set default bus ops */ + pp->bridge->ops = &dw_pcie_ops; + pp->bridge->child_ops = &dw_child_pcie_ops; + pp->bridge->sysdata = pp; + } - pp->bridge = bridge; + ret = dw_pcie_get_resources(pci); + if (ret) { + if (pp->cfg) + pci_ecam_free(pp->cfg); + return ret; + } /* Get the I/O range from DT */ - win = resource_list_first_type(&bridge->windows, IORESOURCE_IO); + win = resource_list_first_type(&pp->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); } - /* Set default bus ops */ - bridge->ops = &dw_pcie_ops; - bridge->child_ops = &dw_child_pcie_ops; + /* + * visconti_pcie_cpu_addr_fixup() uses pp->io_base, so we have to + * call dw_pcie_parent_bus_offset() after setting pp->io_base. + */ + pci->parent_bus_offset = dw_pcie_parent_bus_offset(pci, "config", + pp->cfg0_base); + 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 pci_host_bridge *bridge; + int ret; + + raw_spin_lock_init(&pp->lock); + + bridge = devm_pci_alloc_host_bridge(dev, 0); + if (!bridge) + return -ENOMEM; + + pp->bridge = bridge; + + ret = dw_pcie_host_get_resources(pp); + if (ret) + return ret; if (pp->ops->init) { ret = pp->ops->init(pp); if (ret) - return ret; + goto err_free_ecam; } if (pci_msi_enabled()) { pp->has_msi_ctrl = !(pp->ops->msi_init || - of_property_read_bool(np, "msi-parent") || - of_property_read_bool(np, "msi-map")); + of_property_present(np, "msi-parent") || + of_property_present(np, "msi-map")); /* * For the has_msi_ctrl case the default assignment is handled @@ -504,6 +624,21 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp) dw_pcie_iatu_detect(pci); + if (pci->num_lanes < 1) + pci->num_lanes = dw_pcie_link_get_max_link_width(pci); + + ret = of_pci_get_equalization_presets(dev, &pp->presets, pci->num_lanes); + if (ret) + goto err_free_msi; + + if (pp->ecam_enabled) { + ret = dw_pcie_config_ecam_iatu(pp); + if (ret) { + dev_err(dev, "Failed to configure iATU in ECAM mode\n"); + goto err_free_msi; + } + } + /* * Allocate the resource for MSG TLP before programming the iATU * outbound window in dw_pcie_setup_rc(). Since the allocation depends @@ -530,10 +665,14 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp) goto err_remove_edma; } - /* Ignore errors, the link may come up later */ - dw_pcie_wait_for_link(pci); - - bridge->sysdata = pp; + /* + * Note: Skip the link up delay only when a Link Up IRQ is present. + * If there is no Link Up IRQ, we should not bypass the delay + * because that would require users to manually rescan for devices. + */ + if (!pp->use_linkup_irq) + /* Ignore errors, the link may come up later */ + dw_pcie_wait_for_link(pci); ret = pci_host_probe(bridge); if (ret) @@ -542,6 +681,8 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp) if (pp->ops->post_init) pp->ops->post_init(pp); + dwc_pcie_debugfs_init(pci, DW_PCIE_RC_TYPE); + return 0; err_stop_link: @@ -558,6 +699,10 @@ err_deinit_host: if (pp->ops->deinit) pp->ops->deinit(pp); +err_free_ecam: + if (pp->cfg) + pci_ecam_free(pp->cfg); + return ret; } EXPORT_SYMBOL_GPL(dw_pcie_host_init); @@ -566,6 +711,8 @@ void dw_pcie_host_deinit(struct dw_pcie_rp *pp) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + dwc_pcie_debugfs_deinit(pci); + pci_stop_root_bus(pp->bridge->bus); pci_remove_root_bus(pp->bridge->bus); @@ -578,6 +725,9 @@ void dw_pcie_host_deinit(struct dw_pcie_rp *pp) if (pp->ops->deinit) pp->ops->deinit(pp); + + if (pp->cfg) + pci_ecam_free(pp->cfg); } EXPORT_SYMBOL_GPL(dw_pcie_host_deinit); @@ -610,7 +760,7 @@ static void __iomem *dw_pcie_other_conf_map_bus(struct pci_bus *bus, type = PCIE_ATU_TYPE_CFG1; atu.type = type; - atu.cpu_addr = pp->cfg0_base; + atu.parent_bus_addr = pp->cfg0_base - pci->parent_bus_offset; atu.pci_addr = busdev; atu.size = pp->cfg0_size; @@ -635,7 +785,7 @@ static int dw_pcie_rd_other_conf(struct pci_bus *bus, unsigned int devfn, if (pp->cfg0_io_shared) { atu.type = PCIE_ATU_TYPE_IO; - atu.cpu_addr = pp->io_base; + atu.parent_bus_addr = pp->io_base - pci->parent_bus_offset; atu.pci_addr = pp->io_bus_addr; atu.size = pp->io_size; @@ -661,7 +811,7 @@ static int dw_pcie_wr_other_conf(struct pci_bus *bus, unsigned int devfn, if (pp->cfg0_io_shared) { atu.type = PCIE_ATU_TYPE_IO; - atu.cpu_addr = pp->io_base; + atu.parent_bus_addr = pp->io_base - pci->parent_bus_offset; atu.pci_addr = pp->io_bus_addr; atu.size = pp->io_size; @@ -691,10 +841,41 @@ void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, unsigned int devfn, } EXPORT_SYMBOL_GPL(dw_pcie_own_conf_map_bus); +static void __iomem *dw_pcie_ecam_conf_map_bus(struct pci_bus *bus, unsigned int devfn, int where) +{ + struct pci_config_window *cfg = bus->sysdata; + struct dw_pcie_rp *pp = cfg->priv; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + unsigned int busn = bus->number; + + if (busn > 0) + return pci_ecam_map_bus(bus, devfn, where); + + if (PCI_SLOT(devfn) > 0) + return NULL; + + return pci->dbi_base + where; +} + +static int dw_pcie_op_assert_perst(struct pci_bus *bus, bool assert) +{ + struct dw_pcie_rp *pp = bus->sysdata; + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + + return dw_pcie_assert_perst(pci, assert); +} + 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, + .assert_perst = dw_pcie_op_assert_perst, +}; + +static struct pci_ops dw_pcie_ecam_ops = { + .map_bus = dw_pcie_ecam_conf_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, }; static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp) @@ -730,7 +911,7 @@ static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp) atu.index = i; atu.type = PCIE_ATU_TYPE_MEM; - atu.cpu_addr = entry->res->start; + atu.parent_bus_addr = entry->res->start - pci->parent_bus_offset; atu.pci_addr = entry->res->start - entry->offset; /* Adjust iATU size if MSG TLP region was allocated before */ @@ -752,7 +933,7 @@ static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp) if (pci->num_ob_windows > ++i) { atu.index = i; atu.type = PCIE_ATU_TYPE_IO; - atu.cpu_addr = pp->io_base; + atu.parent_bus_addr = pp->io_base - pci->parent_bus_offset; atu.pci_addr = pp->io_bus_addr; atu.size = pp->io_size; @@ -799,10 +980,81 @@ static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp) return 0; } +static void dw_pcie_program_presets(struct dw_pcie_rp *pp, enum pci_bus_speed speed) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + u8 lane_eq_offset, lane_reg_size, cap_id; + u8 *presets; + u32 cap; + int i; + + if (speed == PCIE_SPEED_8_0GT) { + presets = (u8 *)pp->presets.eq_presets_8gts; + lane_eq_offset = PCI_SECPCI_LE_CTRL; + cap_id = PCI_EXT_CAP_ID_SECPCI; + /* For data rate of 8 GT/S each lane equalization control is 16bits wide*/ + lane_reg_size = 0x2; + } else if (speed == PCIE_SPEED_16_0GT) { + presets = pp->presets.eq_presets_Ngts[EQ_PRESET_TYPE_16GTS - 1]; + lane_eq_offset = PCI_PL_16GT_LE_CTRL; + cap_id = PCI_EXT_CAP_ID_PL_16GT; + lane_reg_size = 0x1; + } else if (speed == PCIE_SPEED_32_0GT) { + presets = pp->presets.eq_presets_Ngts[EQ_PRESET_TYPE_32GTS - 1]; + lane_eq_offset = PCI_PL_32GT_LE_CTRL; + cap_id = PCI_EXT_CAP_ID_PL_32GT; + lane_reg_size = 0x1; + } else if (speed == PCIE_SPEED_64_0GT) { + presets = pp->presets.eq_presets_Ngts[EQ_PRESET_TYPE_64GTS - 1]; + lane_eq_offset = PCI_PL_64GT_LE_CTRL; + cap_id = PCI_EXT_CAP_ID_PL_64GT; + lane_reg_size = 0x1; + } else { + return; + } + + if (presets[0] == PCI_EQ_RESV) + return; + + cap = dw_pcie_find_ext_capability(pci, cap_id); + if (!cap) + return; + + /* + * Write preset values to the registers byte-by-byte for the given + * number of lanes and register size. + */ + for (i = 0; i < pci->num_lanes * lane_reg_size; i++) + dw_pcie_writeb_dbi(pci, cap + lane_eq_offset + i, presets[i]); +} + +static void dw_pcie_config_presets(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + enum pci_bus_speed speed = pcie_link_speed[pci->max_link_speed]; + + /* + * Lane equalization settings need to be applied for all data rates the + * controller supports and for all supported lanes. + */ + + if (speed >= PCIE_SPEED_8_0GT) + dw_pcie_program_presets(pp, PCIE_SPEED_8_0GT); + + if (speed >= PCIE_SPEED_16_0GT) + dw_pcie_program_presets(pp, PCIE_SPEED_16_0GT); + + if (speed >= PCIE_SPEED_32_0GT) + dw_pcie_program_presets(pp, PCIE_SPEED_32_0GT); + + if (speed >= PCIE_SPEED_64_0GT) + dw_pcie_program_presets(pp, PCIE_SPEED_64_0GT); +} + 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; + u32 val; int ret; /* @@ -813,20 +1065,6 @@ int dw_pcie_setup_rc(struct dw_pcie_rp *pp) 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 */ @@ -852,6 +1090,9 @@ int dw_pcie_setup_rc(struct dw_pcie_rp *pp) PCI_COMMAND_MASTER | PCI_COMMAND_SERR; dw_pcie_writel_dbi(pci, PCI_COMMAND, val); + dw_pcie_hide_unsupported_l1ss(pci); + + dw_pcie_config_presets(pp); /* * If the platform provides its own child bus config accesses, it means * the platform uses its own address translation component rather than @@ -896,13 +1137,13 @@ static int dw_pcie_pme_turn_off(struct dw_pcie *pci) atu.size = resource_size(pci->pp.msg_res); atu.index = pci->pp.msg_atu_index; - atu.cpu_addr = pci->pp.msg_res->start; + atu.parent_bus_addr = pci->pp.msg_res->start - pci->parent_bus_offset; ret = dw_pcie_prog_outbound_atu(pci, &atu); if (ret) return ret; - mem = ioremap(atu.cpu_addr, pci->region_align); + mem = ioremap(pci->pp.msg_res->start, pci->region_align); if (!mem) return -ENOMEM; @@ -918,7 +1159,7 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci) { u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); u32 val; - int ret = 0; + int ret; /* * If L1SS is supported, then do not put the link into L2 as some @@ -927,25 +1168,33 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci) if (dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKCTL) & PCI_EXP_LNKCTL_ASPM_L1) return 0; - if (dw_pcie_get_ltssm(pci) <= DW_PCIE_LTSSM_DETECT_ACT) - return 0; - - if (pci->pp.ops->pme_turn_off) + if (pci->pp.ops->pme_turn_off) { pci->pp.ops->pme_turn_off(&pci->pp); - else + } else { ret = dw_pcie_pme_turn_off(pci); + if (ret) + return ret; + } - if (ret) - return ret; - - ret = read_poll_timeout(dw_pcie_get_ltssm, val, val == DW_PCIE_LTSSM_L2_IDLE, + ret = read_poll_timeout(dw_pcie_get_ltssm, val, + val == DW_PCIE_LTSSM_L2_IDLE || + val <= DW_PCIE_LTSSM_DETECT_WAIT, PCIE_PME_TO_L2_TIMEOUT_US/10, PCIE_PME_TO_L2_TIMEOUT_US, false, pci); if (ret) { + /* Only log message when LTSSM isn't in DETECT or POLL */ dev_err(pci->dev, "Timeout waiting for L2 entry! LTSSM: 0x%x\n", val); return ret; } + /* + * Per PCIe r6.0, sec 5.3.3.2.1, software should wait at least + * 100ns after L2/L3 Ready before turning off refclock and + * main power. This is harmless when no endpoint is connected. + */ + udelay(1); + + dw_pcie_stop_link(pci); if (pci->pp.ops->deinit) pci->pp.ops->deinit(&pci->pp); diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c index 771b9d9be077..12f41886c65d 100644 --- a/drivers/pci/controller/dwc/pcie-designware-plat.c +++ b/drivers/pci/controller/dwc/pcie-designware-plat.c @@ -61,7 +61,6 @@ static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, } static const struct pci_epc_features dw_plat_pcie_epc_features = { - .linkup_notifier = false, .msi_capable = true, .msix_capable = true, }; diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c index 6d6cbc8b5b2c..75fc8b767fcc 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -16,6 +16,8 @@ #include <linux/gpio/consumer.h> #include <linux/ioport.h> #include <linux/of.h> +#include <linux/of_address.h> +#include <linux/pcie-dwc.h> #include <linux/platform_device.h> #include <linux/sizes.h> #include <linux/types.h> @@ -52,6 +54,14 @@ static const char * const dw_pcie_core_rsts[DW_PCIE_NUM_CORE_RSTS] = { [DW_PCIE_PWR_RST] = "pwr", }; +static const struct dwc_pcie_vsec_id dwc_pcie_ptm_vsec_ids[] = { + { .vendor_id = PCI_VENDOR_ID_QCOM, /* EP */ + .vsec_id = 0x03, .vsec_rev = 0x1 }, + { .vendor_id = PCI_VENDOR_ID_QCOM, /* RC */ + .vsec_id = 0x04, .vsec_rev = 0x1 }, + { } +}; + static int dw_pcie_get_clocks(struct dw_pcie *pci) { int i, ret; @@ -157,6 +167,16 @@ int dw_pcie_get_resources(struct dw_pcie *pci) } } + /* ELBI is an optional resource */ + if (!pci->elbi_base) { + res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "elbi"); + if (res) { + pci->elbi_base = devm_ioremap_resource(pci->dev, res); + if (IS_ERR(pci->elbi_base)) + return PTR_ERR(pci->elbi_base); + } + } + /* LLDD is supposed to manually switch the clocks and resets state */ if (dw_pcie_cap_is(pci, REQ_RES)) { ret = dw_pcie_get_clocks(pci); @@ -203,85 +223,69 @@ void dw_pcie_version_detect(struct dw_pcie *pci) 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 dw_pcie_find_capability(struct dw_pcie *pci, 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); + return PCI_FIND_NEXT_CAP(dw_pcie_read_cfg, PCI_CAPABILITY_LIST, cap, + pci); } +EXPORT_SYMBOL_GPL(dw_pcie_find_capability); -u8 dw_pcie_find_capability(struct dw_pcie *pci, u8 cap) +u16 dw_pcie_find_ext_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); + return PCI_FIND_NEXT_EXT_CAP(dw_pcie_read_cfg, 0, cap, pci); } -EXPORT_SYMBOL_GPL(dw_pcie_find_capability); +EXPORT_SYMBOL_GPL(dw_pcie_find_ext_capability); -static u16 dw_pcie_find_next_ext_capability(struct dw_pcie *pci, u16 start, - u8 cap) +static u16 __dw_pcie_find_vsec_capability(struct dw_pcie *pci, u16 vendor_id, + u16 vsec_id) { + u16 vsec = 0; 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) + if (vendor_id != dw_pcie_readw_dbi(pci, PCI_VENDOR_ID)) return 0; - while (ttl-- > 0) { - if (PCI_EXT_CAP_ID(header) == cap && pos != start) - return pos; + while ((vsec = PCI_FIND_NEXT_EXT_CAP(dw_pcie_read_cfg, vsec, + PCI_EXT_CAP_ID_VNDR, pci))) { + header = dw_pcie_readl_dbi(pci, vsec + PCI_VNDR_HEADER); + if (PCI_VNDR_HEADER_ID(header) == vsec_id) + return vsec; + } - pos = PCI_EXT_CAP_NEXT(header); - if (pos < PCI_CFG_SPACE_SIZE) - break; + return 0; +} - header = dw_pcie_readl_dbi(pci, pos); +static u16 dw_pcie_find_vsec_capability(struct dw_pcie *pci, + const struct dwc_pcie_vsec_id *vsec_ids) +{ + const struct dwc_pcie_vsec_id *vid; + u16 vsec; + u32 header; + + for (vid = vsec_ids; vid->vendor_id; vid++) { + vsec = __dw_pcie_find_vsec_capability(pci, vid->vendor_id, + vid->vsec_id); + if (vsec) { + header = dw_pcie_readl_dbi(pci, vsec + PCI_VNDR_HEADER); + if (PCI_VNDR_HEADER_REV(header) == vid->vsec_rev) + return vsec; + } } return 0; } -u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap) +u16 dw_pcie_find_rasdes_capability(struct dw_pcie *pci) { - return dw_pcie_find_next_ext_capability(pci, 0, cap); + return dw_pcie_find_vsec_capability(pci, dwc_pcie_rasdes_vsec_ids); } -EXPORT_SYMBOL_GPL(dw_pcie_find_ext_capability); +EXPORT_SYMBOL_GPL(dw_pcie_find_rasdes_capability); + +u16 dw_pcie_find_ptm_capability(struct dw_pcie *pci) +{ + return dw_pcie_find_vsec_capability(pci, dwc_pcie_ptm_vsec_ids); +} +EXPORT_SYMBOL_GPL(dw_pcie_find_ptm_capability); int dw_pcie_read(void __iomem *addr, int size, u32 *val) { @@ -470,25 +474,22 @@ static inline u32 dw_pcie_enable_ecrc(u32 val) int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, const struct dw_pcie_ob_atu_cfg *atu) { - u64 cpu_addr = atu->cpu_addr; + u64 parent_bus_addr = atu->parent_bus_addr; 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 = parent_bus_addr + atu->size - 1; - limit_addr = cpu_addr + atu->size - 1; - - if ((limit_addr & ~pci->region_limit) != (cpu_addr & ~pci->region_limit) || - !IS_ALIGNED(cpu_addr, pci->region_align) || + if ((limit_addr & ~pci->region_limit) != (parent_bus_addr & ~pci->region_limit) || + !IS_ALIGNED(parent_bus_addr, pci->region_align) || !IS_ALIGNED(atu->pci_addr, pci->region_align) || !atu->size) { return -EINVAL; } dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_LOWER_BASE, - lower_32_bits(cpu_addr)); + lower_32_bits(parent_bus_addr)); dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_UPPER_BASE, - upper_32_bits(cpu_addr)); + upper_32_bits(parent_bus_addr)); dw_pcie_writel_atu_ob(pci, atu->index, PCIE_ATU_LIMIT, lower_32_bits(limit_addr)); @@ -502,14 +503,14 @@ int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, upper_32_bits(atu->pci_addr)); val = atu->type | atu->routing | PCIE_ATU_FUNC_NUM(atu->func_no); - if (upper_32_bits(limit_addr) > upper_32_bits(cpu_addr) && + if (upper_32_bits(limit_addr) > upper_32_bits(parent_bus_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, atu->index, PCIE_ATU_REGION_CTRL1, val); - val = PCIE_ATU_ENABLE; + val = PCIE_ATU_ENABLE | atu->ctrl2; if (atu->type == PCIE_ATU_TYPE_MSG) { /* The data-less messages only for now */ val |= PCIE_ATU_INHIBIT_PAYLOAD | atu->code; @@ -545,13 +546,13 @@ static inline void dw_pcie_writel_atu_ib(struct dw_pcie *pci, u32 index, u32 reg } int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type, - u64 cpu_addr, u64 pci_addr, u64 size) + u64 parent_bus_addr, u64 pci_addr, u64 size) { u64 limit_addr = pci_addr + size - 1; u32 retries, val; if ((limit_addr & ~pci->region_limit) != (pci_addr & ~pci->region_limit) || - !IS_ALIGNED(cpu_addr, pci->region_align) || + !IS_ALIGNED(parent_bus_addr, pci->region_align) || !IS_ALIGNED(pci_addr, pci->region_align) || !size) { return -EINVAL; } @@ -568,9 +569,9 @@ int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type, upper_32_bits(limit_addr)); dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LOWER_TARGET, - lower_32_bits(cpu_addr)); + lower_32_bits(parent_bus_addr)); dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_UPPER_TARGET, - upper_32_bits(cpu_addr)); + upper_32_bits(parent_bus_addr)); val = type; if (upper_32_bits(limit_addr) > upper_32_bits(pci_addr) && @@ -597,17 +598,18 @@ int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type, } int dw_pcie_prog_ep_inbound_atu(struct dw_pcie *pci, u8 func_no, int index, - int type, u64 cpu_addr, u8 bar) + int type, u64 parent_bus_addr, u8 bar, size_t size) { u32 retries, val; - if (!IS_ALIGNED(cpu_addr, pci->region_align)) + if (!IS_ALIGNED(parent_bus_addr, pci->region_align) || + !IS_ALIGNED(parent_bus_addr, size)) return -EINVAL; dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LOWER_TARGET, - lower_32_bits(cpu_addr)); + lower_32_bits(parent_bus_addr)); dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_UPPER_TARGET, - upper_32_bits(cpu_addr)); + upper_32_bits(parent_bus_addr)); dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_REGION_CTRL1, type | PCIE_ATU_FUNC_NUM(func_no)); @@ -643,18 +645,26 @@ int dw_pcie_wait_for_link(struct dw_pcie *pci) int retries; /* Check if the link is up or not */ - for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) { + for (retries = 0; retries < PCIE_LINK_WAIT_MAX_RETRIES; retries++) { if (dw_pcie_link_up(pci)) break; - msleep(LINK_WAIT_SLEEP_MS); + msleep(PCIE_LINK_WAIT_SLEEP_MS); } - if (retries >= LINK_WAIT_MAX_RETRIES) { + if (retries >= PCIE_LINK_WAIT_MAX_RETRIES) { dev_info(pci->dev, "Phy link never came up\n"); return -ETIMEDOUT; } + /* + * As per PCIe r6.0, sec 6.6.1, a Downstream Port that supports Link + * speeds greater than 5.0 GT/s, software must wait a minimum of 100 ms + * after Link training completes before sending a Configuration Request. + */ + if (pci->max_link_speed > 2) + msleep(PCIE_RESET_CONFIG_WAIT_MS); + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); val = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA); @@ -666,7 +676,7 @@ int dw_pcie_wait_for_link(struct dw_pcie *pci) } EXPORT_SYMBOL_GPL(dw_pcie_wait_for_link); -int dw_pcie_link_up(struct dw_pcie *pci) +bool dw_pcie_link_up(struct dw_pcie *pci) { u32 val; @@ -736,6 +746,14 @@ static void dw_pcie_link_set_max_speed(struct dw_pcie *pci) } +int dw_pcie_link_get_max_link_width(struct dw_pcie *pci) +{ + u8 cap = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + u32 lnkcap = dw_pcie_readl_dbi(pci, cap + PCI_EXP_LNKCAP); + + return FIELD_GET(PCI_EXP_LNKCAP_MLW, lnkcap); +} + static void dw_pcie_link_set_max_link_width(struct dw_pcie *pci, u32 num_lanes) { u32 lnkcap, lwsc, plc; @@ -752,22 +770,22 @@ static void dw_pcie_link_set_max_link_width(struct dw_pcie *pci, u32 num_lanes) /* Set link width speed control register */ lwsc = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL); lwsc &= ~PORT_LOGIC_LINK_WIDTH_MASK; + lwsc |= PORT_LOGIC_LINK_WIDTH_1_LANES; switch (num_lanes) { case 1: plc |= PORT_LINK_MODE_1_LANES; - lwsc |= PORT_LOGIC_LINK_WIDTH_1_LANES; break; case 2: plc |= PORT_LINK_MODE_2_LANES; - lwsc |= PORT_LOGIC_LINK_WIDTH_2_LANES; break; case 4: plc |= PORT_LINK_MODE_4_LANES; - lwsc |= PORT_LOGIC_LINK_WIDTH_4_LANES; break; case 8: plc |= PORT_LINK_MODE_8_LANES; - lwsc |= PORT_LOGIC_LINK_WIDTH_8_LANES; + break; + case 16: + plc |= PORT_LINK_MODE_16_LANES; break; default: dev_err(pci->dev, "num-lanes %u: invalid value\n", num_lanes); @@ -970,12 +988,10 @@ static int dw_pcie_edma_irq_verify(struct dw_pcie *pci) { struct platform_device *pdev = to_platform_device(pci->dev); u16 ch_cnt = pci->edma.ll_wr_cnt + pci->edma.ll_rd_cnt; - char name[6]; + char name[15]; int ret; - if (pci->edma.nr_irqs == 1) - return 0; - else if (pci->edma.nr_irqs > 1) + if (pci->edma.nr_irqs > 1) return pci->edma.nr_irqs != ch_cnt ? -EINVAL : 0; ret = platform_get_irq_byname_optional(pdev, "dma"); @@ -1067,6 +1083,30 @@ void dw_pcie_edma_remove(struct dw_pcie *pci) dw_edma_remove(&pci->edma); } +void dw_pcie_hide_unsupported_l1ss(struct dw_pcie *pci) +{ + u16 l1ss; + u32 l1ss_cap; + + if (pci->l1ss_support) + return; + + l1ss = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_L1SS); + if (!l1ss) + return; + + /* + * Unless the driver claims "l1ss_support", don't advertise L1 PM + * Substates because they require CLKREQ# and possibly other + * device-specific configuration. + */ + l1ss_cap = dw_pcie_readl_dbi(pci, l1ss + PCI_L1SS_CAP); + l1ss_cap &= ~(PCI_L1SS_CAP_PCIPM_L1_1 | PCI_L1SS_CAP_ASPM_L1_1 | + PCI_L1SS_CAP_PCIPM_L1_2 | PCI_L1SS_CAP_ASPM_L1_2 | + PCI_L1SS_CAP_L1_PM_SS); + dw_pcie_writel_dbi(pci, l1ss + PCI_L1SS_CAP, l1ss_cap); +} + void dw_pcie_setup(struct dw_pcie *pci) { u32 val; @@ -1104,3 +1144,63 @@ void dw_pcie_setup(struct dw_pcie *pci) dw_pcie_link_set_max_link_width(pci, pci->num_lanes); } + +resource_size_t dw_pcie_parent_bus_offset(struct dw_pcie *pci, + const char *reg_name, + resource_size_t cpu_phys_addr) +{ + struct device *dev = pci->dev; + struct device_node *np = dev->of_node; + int index; + u64 reg_addr, fixup_addr; + u64 (*fixup)(struct dw_pcie *pcie, u64 cpu_addr); + + /* Look up reg_name address on parent bus */ + index = of_property_match_string(np, "reg-names", reg_name); + + if (index < 0) { + dev_err(dev, "No %s in devicetree \"reg\" property\n", reg_name); + return 0; + } + + of_property_read_reg(np, index, ®_addr, NULL); + + fixup = pci->ops ? pci->ops->cpu_addr_fixup : NULL; + if (fixup) { + fixup_addr = fixup(pci, cpu_phys_addr); + if (reg_addr == fixup_addr) { + dev_info(dev, "%s reg[%d] %#010llx == %#010llx == fixup(cpu %#010llx); %ps is redundant with this devicetree\n", + reg_name, index, reg_addr, fixup_addr, + (unsigned long long) cpu_phys_addr, fixup); + } else { + dev_warn(dev, "%s reg[%d] %#010llx != %#010llx == fixup(cpu %#010llx); devicetree is broken\n", + reg_name, index, reg_addr, fixup_addr, + (unsigned long long) cpu_phys_addr); + reg_addr = fixup_addr; + } + + return cpu_phys_addr - reg_addr; + } + + if (pci->use_parent_dt_ranges) { + + /* + * This platform once had a fixup, presumably because it + * translates between CPU and PCI controller addresses. + * Log a note if devicetree didn't describe a translation. + */ + if (reg_addr == cpu_phys_addr) + dev_info(dev, "%s reg[%d] %#010llx == cpu %#010llx\n; no fixup was ever needed for this devicetree\n", + reg_name, index, reg_addr, + (unsigned long long) cpu_phys_addr); + } else { + if (reg_addr != cpu_phys_addr) { + dev_warn(dev, "%s reg[%d] %#010llx != cpu %#010llx; no fixup and devicetree \"ranges\" is broken, assuming no translation\n", + reg_name, index, reg_addr, + (unsigned long long) cpu_phys_addr); + return 0; + } + } + + return cpu_phys_addr - reg_addr; +} diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index 347ab74ac35a..31685951a080 100644 --- a/drivers/pci/controller/dwc/pcie-designware.h +++ b/drivers/pci/controller/dwc/pcie-designware.h @@ -20,11 +20,14 @@ #include <linux/irq.h> #include <linux/msi.h> #include <linux/pci.h> +#include <linux/pci-ecam.h> #include <linux/reset.h> #include <linux/pci-epc.h> #include <linux/pci-epf.h> +#include "../../pci.h" + /* DWC PCIe IP-core versions (native support since v4.70a) */ #define DW_PCIE_VER_365A 0x3336352a #define DW_PCIE_VER_460A 0x3436302a @@ -60,10 +63,6 @@ #define dw_pcie_cap_set(_pci, _cap) \ set_bit(DW_PCIE_CAP_ ## _cap, &(_pci)->caps) -/* Parameters for the waiting for link up routine */ -#define LINK_WAIT_MAX_RETRIES 10 -#define LINK_WAIT_SLEEP_MS 90 - /* Parameters for the waiting for iATU enabled routine */ #define LINK_WAIT_MAX_IATU_RETRIES 5 #define LINK_WAIT_IATU 9 @@ -92,12 +91,13 @@ #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 PORT_LINK_MODE_16_LANES PORT_LINK_MODE(0x1f) #define PCIE_PORT_LANE_SKEW 0x714 #define PORT_LANE_SKEW_INSERT_MASK GENMASK(23, 0) #define PCIE_PORT_DEBUG0 0x728 -#define PORT_LOGIC_LTSSM_STATE_MASK 0x1f +#define PORT_LOGIC_LTSSM_STATE_MASK 0x3f #define PORT_LOGIC_LTSSM_STATE_L0 0x11 #define PCIE_PORT_DEBUG1 0x72C #define PCIE_PORT_DEBUG1_LINK_UP BIT(4) @@ -121,11 +121,11 @@ #define GEN3_RELATED_OFF 0x890 #define GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL BIT(0) +#define GEN3_RELATED_OFF_EQ_PHASE_2_3 BIT(9) #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 GEN3_RELATED_OFF_RATE_SHADOW_SEL_16_0GT 0x1 #define GEN3_EQ_CONTROL_OFF 0x8A8 #define GEN3_EQ_CONTROL_OFF_FB_MODE GENMASK(3, 0) @@ -136,8 +136,15 @@ #define GEN3_EQ_FB_MODE_DIR_CHANGE_OFF 0x8AC #define GEN3_EQ_FMDC_T_MIN_PHASE23 GENMASK(4, 0) #define GEN3_EQ_FMDC_N_EVALS GENMASK(9, 5) -#define GEN3_EQ_FMDC_MAX_PRE_CUSROR_DELTA GENMASK(13, 10) -#define GEN3_EQ_FMDC_MAX_POST_CUSROR_DELTA GENMASK(17, 14) +#define GEN3_EQ_FMDC_MAX_PRE_CURSOR_DELTA GENMASK(13, 10) +#define GEN3_EQ_FMDC_MAX_POST_CURSOR_DELTA GENMASK(17, 14) + +#define COHERENCY_CONTROL_1_OFF 0x8E0 +#define CFG_MEMTYPE_BOUNDARY_LOW_ADDR_MASK GENMASK(31, 2) +#define CFG_MEMTYPE_VALUE BIT(0) + +#define COHERENCY_CONTROL_2_OFF 0x8E4 +#define COHERENCY_CONTROL_3_OFF 0x8E8 #define PCIE_PORT_MULTI_LANE_CTRL 0x8C0 #define PORT_MLTI_UPCFG_SUPPORT BIT(7) @@ -171,6 +178,7 @@ #define PCIE_ATU_REGION_CTRL2 0x004 #define PCIE_ATU_ENABLE BIT(31) #define PCIE_ATU_BAR_MODE_ENABLE BIT(30) +#define PCIE_ATU_CFG_SHIFT_MODE_ENABLE BIT(28) #define PCIE_ATU_INHIBIT_PAYLOAD BIT(22) #define PCIE_ATU_FUNC_NUM_MATCH_EN BIT(19) #define PCIE_ATU_LOWER_BASE 0x008 @@ -260,6 +268,21 @@ #define PCIE_RAS_DES_EVENT_COUNTER_DATA 0xc +/* PTM register definitions */ +#define PTM_RES_REQ_CTRL 0x8 +#define PTM_RES_CCONTEXT_VALID BIT(0) +#define PTM_REQ_AUTO_UPDATE_ENABLED BIT(0) +#define PTM_REQ_START_UPDATE BIT(1) + +#define PTM_LOCAL_LSB 0x10 +#define PTM_LOCAL_MSB 0x14 +#define PTM_T1_T2_LSB 0x18 +#define PTM_T1_T2_MSB 0x1c +#define PTM_T3_T4_LSB 0x28 +#define PTM_T3_T4_MSB 0x2c +#define PTM_MASTER_LSB 0x38 +#define PTM_MASTER_MSB 0x3c + /* * 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 @@ -330,8 +353,40 @@ enum dw_pcie_ltssm { /* Need to align with PCIE_PORT_DEBUG0 bits 0:5 */ DW_PCIE_LTSSM_DETECT_QUIET = 0x0, DW_PCIE_LTSSM_DETECT_ACT = 0x1, + DW_PCIE_LTSSM_POLL_ACTIVE = 0x2, + DW_PCIE_LTSSM_POLL_COMPLIANCE = 0x3, + DW_PCIE_LTSSM_POLL_CONFIG = 0x4, + DW_PCIE_LTSSM_PRE_DETECT_QUIET = 0x5, + DW_PCIE_LTSSM_DETECT_WAIT = 0x6, + DW_PCIE_LTSSM_CFG_LINKWD_START = 0x7, + DW_PCIE_LTSSM_CFG_LINKWD_ACEPT = 0x8, + DW_PCIE_LTSSM_CFG_LANENUM_WAI = 0x9, + DW_PCIE_LTSSM_CFG_LANENUM_ACEPT = 0xa, + DW_PCIE_LTSSM_CFG_COMPLETE = 0xb, + DW_PCIE_LTSSM_CFG_IDLE = 0xc, + DW_PCIE_LTSSM_RCVRY_LOCK = 0xd, + DW_PCIE_LTSSM_RCVRY_SPEED = 0xe, + DW_PCIE_LTSSM_RCVRY_RCVRCFG = 0xf, + DW_PCIE_LTSSM_RCVRY_IDLE = 0x10, DW_PCIE_LTSSM_L0 = 0x11, + DW_PCIE_LTSSM_L0S = 0x12, + DW_PCIE_LTSSM_L123_SEND_EIDLE = 0x13, + DW_PCIE_LTSSM_L1_IDLE = 0x14, DW_PCIE_LTSSM_L2_IDLE = 0x15, + DW_PCIE_LTSSM_L2_WAKE = 0x16, + DW_PCIE_LTSSM_DISABLED_ENTRY = 0x17, + DW_PCIE_LTSSM_DISABLED_IDLE = 0x18, + DW_PCIE_LTSSM_DISABLED = 0x19, + DW_PCIE_LTSSM_LPBK_ENTRY = 0x1a, + DW_PCIE_LTSSM_LPBK_ACTIVE = 0x1b, + DW_PCIE_LTSSM_LPBK_EXIT = 0x1c, + DW_PCIE_LTSSM_LPBK_EXIT_TIMEOUT = 0x1d, + DW_PCIE_LTSSM_HOT_RESET_ENTRY = 0x1e, + DW_PCIE_LTSSM_HOT_RESET = 0x1f, + DW_PCIE_LTSSM_RCVRY_EQ0 = 0x20, + DW_PCIE_LTSSM_RCVRY_EQ1 = 0x21, + DW_PCIE_LTSSM_RCVRY_EQ2 = 0x22, + DW_PCIE_LTSSM_RCVRY_EQ3 = 0x23, DW_PCIE_LTSSM_UNKNOWN = 0xFFFFFFFF, }; @@ -342,7 +397,8 @@ struct dw_pcie_ob_atu_cfg { u8 func_no; u8 code; u8 routing; - u64 cpu_addr; + u32 ctrl2; + u64 parent_bus_addr; u64 pci_addr; u64 size; }; @@ -368,7 +424,6 @@ struct dw_pcie_rp { 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; @@ -379,6 +434,11 @@ struct dw_pcie_rp { bool use_atu_msg; int msg_atu_index; struct resource *msg_res; + bool use_linkup_irq; + struct pci_eq_presets presets; + struct pci_config_window *cfg; + bool ecam_enabled; + bool native_ecam; }; struct dw_pcie_ep_ops { @@ -429,10 +489,16 @@ struct dw_pcie_ops { 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); + bool (*link_up)(struct dw_pcie *pcie); enum dw_pcie_ltssm (*get_ltssm)(struct dw_pcie *pcie); int (*start_link)(struct dw_pcie *pcie); void (*stop_link)(struct dw_pcie *pcie); + int (*assert_perst)(struct dw_pcie *pcie, bool assert); +}; + +struct debugfs_info { + struct dentry *debug_dir; + void *rasdes_info; }; struct dw_pcie { @@ -441,8 +507,10 @@ struct dw_pcie { resource_size_t dbi_phys_addr; void __iomem *dbi_base2; void __iomem *atu_base; + void __iomem *elbi_base; resource_size_t atu_phys_addr; size_t atu_size; + resource_size_t parent_bus_offset; u32 num_ib_windows; u32 num_ob_windows; u32 region_align; @@ -457,12 +525,30 @@ struct dw_pcie { int max_link_speed; u8 n_fts[2]; struct dw_edma_chip edma; + bool l1ss_support; /* L1 PM Substates support */ struct clk_bulk_data app_clks[DW_PCIE_NUM_APP_CLKS]; struct clk_bulk_data core_clks[DW_PCIE_NUM_CORE_CLKS]; struct reset_control_bulk_data app_rsts[DW_PCIE_NUM_APP_RSTS]; struct reset_control_bulk_data core_rsts[DW_PCIE_NUM_CORE_RSTS]; struct gpio_desc *pe_rst; bool suspended; + struct debugfs_info *debugfs; + enum dw_pcie_device_mode mode; + u16 ptm_vsec_offset; + struct pci_ptm_debugfs *ptm_debugfs; + + /* + * If iATU input addresses are offset from CPU physical addresses, + * we previously required .cpu_addr_fixup() to convert them. We + * now rely on the devicetree instead. If .cpu_addr_fixup() + * exists, we compare its results with devicetree. + * + * If .cpu_addr_fixup() does not exist, we assume the offset is + * zero and warn if devicetree claims otherwise. If we know all + * devicetrees correctly describe the offset, set + * use_parent_dt_ranges to true to avoid this warning. + */ + bool use_parent_dt_ranges; }; #define to_dw_pcie_from_pp(port) container_of((port), struct dw_pcie, pp) @@ -476,6 +562,8 @@ 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); +u16 dw_pcie_find_rasdes_capability(struct dw_pcie *pci); +u16 dw_pcie_find_ptm_capability(struct dw_pcie *pci); int dw_pcie_read(void __iomem *addr, int size, u32 *val); int dw_pcie_write(void __iomem *addr, int size, u32 val); @@ -483,23 +571,26 @@ 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); +bool 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_link_get_max_link_width(struct dw_pcie *pci); int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, const struct dw_pcie_ob_atu_cfg *atu); int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type, - u64 cpu_addr, u64 pci_addr, u64 size); + u64 parent_bus_addr, u64 pci_addr, u64 size); int dw_pcie_prog_ep_inbound_atu(struct dw_pcie *pci, u8 func_no, int index, - int type, u64 cpu_addr, u8 bar); + int type, u64 parent_bus_addr, + u8 bar, size_t size); void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index); +void dw_pcie_hide_unsupported_l1ss(struct dw_pcie *pci); void dw_pcie_setup(struct dw_pcie *pci); void dw_pcie_iatu_detect(struct dw_pcie *pci); int dw_pcie_edma_detect(struct dw_pcie *pci); void dw_pcie_edma_remove(struct dw_pcie *pci); - -int dw_pcie_suspend_noirq(struct dw_pcie *pci); -int dw_pcie_resume_noirq(struct dw_pcie *pci); +resource_size_t dw_pcie_parent_bus_offset(struct dw_pcie *pci, + const char *reg_name, + resource_size_t cpu_phy_addr); static inline void dw_pcie_writel_dbi(struct dw_pcie *pci, u32 reg, u32 val) { @@ -536,6 +627,27 @@ 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 int dw_pcie_read_cfg_byte(struct dw_pcie *pci, int where, + u8 *val) +{ + *val = dw_pcie_readb_dbi(pci, where); + return PCIBIOS_SUCCESSFUL; +} + +static inline int dw_pcie_read_cfg_word(struct dw_pcie *pci, int where, + u16 *val) +{ + *val = dw_pcie_readw_dbi(pci, where); + return PCIBIOS_SUCCESSFUL; +} + +static inline int dw_pcie_read_cfg_dword(struct dw_pcie *pci, int where, + u32 *val) +{ + *val = dw_pcie_readl_dbi(pci, where); + return PCIBIOS_SUCCESSFUL; +} + static inline unsigned int dw_pcie_ep_get_dbi_offset(struct dw_pcie_ep *ep, u8 func_no) { @@ -601,6 +713,27 @@ static inline u8 dw_pcie_ep_readb_dbi(struct dw_pcie_ep *ep, u8 func_no, return dw_pcie_ep_read_dbi(ep, func_no, reg, 0x1); } +static inline int dw_pcie_ep_read_cfg_byte(struct dw_pcie_ep *ep, u8 func_no, + int where, u8 *val) +{ + *val = dw_pcie_ep_readb_dbi(ep, func_no, where); + return PCIBIOS_SUCCESSFUL; +} + +static inline int dw_pcie_ep_read_cfg_word(struct dw_pcie_ep *ep, u8 func_no, + int where, u16 *val) +{ + *val = dw_pcie_ep_readw_dbi(ep, func_no, where); + return PCIBIOS_SUCCESSFUL; +} + +static inline int dw_pcie_ep_read_cfg_dword(struct dw_pcie_ep *ep, u8 func_no, + int where, u32 *val) +{ + *val = dw_pcie_ep_readl_dbi(ep, func_no, where); + return PCIBIOS_SUCCESSFUL; +} + static inline unsigned int dw_pcie_ep_get_dbi2_offset(struct dw_pcie_ep *ep, u8 func_no) { @@ -665,6 +798,14 @@ static inline void dw_pcie_stop_link(struct dw_pcie *pci) pci->ops->stop_link(pci); } +static inline int dw_pcie_assert_perst(struct dw_pcie *pci, bool assert) +{ + if (pci->ops && pci->ops->assert_perst) + return pci->ops->assert_perst(pci, assert); + + return 0; +} + static inline enum dw_pcie_ltssm dw_pcie_get_ltssm(struct dw_pcie *pci) { u32 val; @@ -678,7 +819,12 @@ static inline enum dw_pcie_ltssm dw_pcie_get_ltssm(struct dw_pcie *pci) } #ifdef CONFIG_PCIE_DW_HOST +int dw_pcie_suspend_noirq(struct dw_pcie *pci); +int dw_pcie_resume_noirq(struct dw_pcie *pci); irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp); +void dw_pcie_msi_init(struct dw_pcie_rp *pp); +int dw_pcie_msi_host_init(struct dw_pcie_rp *pp); +void dw_pcie_free_msi(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); @@ -686,11 +832,32 @@ 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 int dw_pcie_suspend_noirq(struct dw_pcie *pci) +{ + return 0; +} + +static inline int dw_pcie_resume_noirq(struct dw_pcie *pci) +{ + return 0; +} + static inline irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp) { return IRQ_NONE; } +static inline void dw_pcie_msi_init(struct dw_pcie_rp *pp) +{ } + +static inline int dw_pcie_msi_host_init(struct dw_pcie_rp *pp) +{ + return -ENODEV; +} + +static inline void dw_pcie_free_msi(struct dw_pcie_rp *pp) +{ } + static inline int dw_pcie_setup_rc(struct dw_pcie_rp *pp) { return 0; @@ -732,6 +899,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, 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); +int dw_pcie_ep_hide_ext_capability(struct dw_pcie *pci, u8 prev_cap, u8 cap); struct dw_pcie_ep_func * dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no); #else @@ -789,10 +957,30 @@ static inline void dw_pcie_ep_reset_bar(struct dw_pcie *pci, enum pci_barno bar) { } +static inline int dw_pcie_ep_hide_ext_capability(struct dw_pcie *pci, + u8 prev_cap, u8 cap) +{ + return 0; +} + 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 + +#ifdef CONFIG_PCIE_DW_DEBUGFS +void dwc_pcie_debugfs_init(struct dw_pcie *pci, enum dw_pcie_device_mode mode); +void dwc_pcie_debugfs_deinit(struct dw_pcie *pci); +#else +static inline void dwc_pcie_debugfs_init(struct dw_pcie *pci, + enum dw_pcie_device_mode mode) +{ +} +static inline void dwc_pcie_debugfs_deinit(struct dw_pcie *pci) +{ +} +#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 index 1170e1107508..f8605fe61a41 100644 --- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c +++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c @@ -8,8 +8,10 @@ * Author: Simon Xue <xxm@rock-chips.com> */ +#include <linux/bitfield.h> #include <linux/clk.h> #include <linux/gpio/consumer.h> +#include <linux/hw_bitfield.h> #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> #include <linux/mfd/syscon.h> @@ -21,38 +23,62 @@ #include <linux/regmap.h> #include <linux/reset.h> +#include "../../pci.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_EP_MODE HIWORD_UPDATE(0xf0, 0x0) -#define PCIE_CLIENT_ENABLE_LTSSM HIWORD_UPDATE_BIT(0xc) -#define PCIE_CLIENT_DISABLE_LTSSM HIWORD_UPDATE(0x0c, 0x8) -#define PCIE_CLIENT_INTR_STATUS_MISC 0x10 -#define PCIE_CLIENT_INTR_MASK_MISC 0x24 -#define PCIE_SMLH_LINKUP BIT(16) -#define PCIE_RDLH_LINKUP BIT(17) -#define PCIE_LINKUP (PCIE_SMLH_LINKUP | PCIE_RDLH_LINKUP) -#define PCIE_RDLH_LINK_UP_CHGED BIT(1) -#define PCIE_LINK_REQ_RST_NOT_INT BIT(2) -#define PCIE_L0S_ENTRY 0x11 -#define PCIE_CLIENT_GENERAL_CONTROL 0x0 +/* General Control Register */ +#define PCIE_CLIENT_GENERAL_CON 0x0 +#define PCIE_CLIENT_MODE_MASK GENMASK(7, 4) +#define PCIE_CLIENT_MODE_EP 0x0UL +#define PCIE_CLIENT_MODE_RC 0x4UL +#define PCIE_CLIENT_SET_MODE(x) FIELD_PREP_WM16(PCIE_CLIENT_MODE_MASK, (x)) +#define PCIE_CLIENT_LD_RQ_RST_GRT FIELD_PREP_WM16(BIT(3), 1) +#define PCIE_CLIENT_ENABLE_LTSSM FIELD_PREP_WM16(BIT(2), 1) +#define PCIE_CLIENT_DISABLE_LTSSM FIELD_PREP_WM16(BIT(2), 0) + +/* Interrupt Status Register Related to Legacy Interrupt */ #define PCIE_CLIENT_INTR_STATUS_LEGACY 0x8 + +/* Interrupt Status Register Related to Miscellaneous Operation */ +#define PCIE_CLIENT_INTR_STATUS_MISC 0x10 +#define PCIE_RDLH_LINK_UP_CHGED BIT(1) +#define PCIE_LINK_REQ_RST_NOT_INT BIT(2) + +/* Interrupt Mask Register Related to Legacy Interrupt */ #define PCIE_CLIENT_INTR_MASK_LEGACY 0x1c -#define PCIE_CLIENT_GENERAL_DEBUG 0x104 +#define PCIE_INTR_MASK GENMASK(7, 0) +#define PCIE_INTR_CLAMP(_x) ((BIT((_x)) & PCIE_INTR_MASK)) +#define PCIE_INTR_LEGACY_MASK(x) (PCIE_INTR_CLAMP((x)) | \ + (PCIE_INTR_CLAMP((x)) << 16)) +#define PCIE_INTR_LEGACY_UNMASK(x) (PCIE_INTR_CLAMP((x)) << 16) + +/* Interrupt Mask Register Related to Miscellaneous Operation */ +#define PCIE_CLIENT_INTR_MASK_MISC 0x24 + +/* Power Management Control Register */ +#define PCIE_CLIENT_POWER_CON 0x2c +#define PCIE_CLKREQ_READY FIELD_PREP_WM16(BIT(0), 1) +#define PCIE_CLKREQ_NOT_READY FIELD_PREP_WM16(BIT(0), 0) +#define PCIE_CLKREQ_PULL_DOWN FIELD_PREP_WM16(GENMASK(13, 12), 1) + +/* Hot Reset Control Register */ #define PCIE_CLIENT_HOT_RESET_CTRL 0x180 +#define PCIE_LTSSM_APP_DLY2_EN BIT(1) +#define PCIE_LTSSM_APP_DLY2_DONE BIT(3) +#define PCIE_LTSSM_ENABLE_ENHANCE BIT(4) + +/* LTSSM Status Register */ #define PCIE_CLIENT_LTSSM_STATUS 0x300 -#define PCIE_LTSSM_ENABLE_ENHANCE BIT(4) -#define PCIE_LTSSM_STATUS_MASK GENMASK(5, 0) +#define PCIE_LINKUP 0x3 +#define PCIE_LINKUP_MASK GENMASK(17, 16) +#define PCIE_LTSSM_STATUS_MASK GENMASK(5, 0) struct rockchip_pcie { struct dw_pcie pci; @@ -62,9 +88,9 @@ struct rockchip_pcie { unsigned int clk_cnt; struct reset_control *rst; struct gpio_desc *rst_gpio; - struct regulator *vpcie3v3; struct irq_domain *irq_domain; const struct rockchip_pcie_of_data *data; + bool supports_clkreq; }; struct rockchip_pcie_of_data { @@ -102,14 +128,14 @@ static void rockchip_pcie_intx_handler(struct irq_desc *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_INTR_LEGACY_MASK(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_INTR_LEGACY_UNMASK(data->hwirq), PCIE_CLIENT_INTR_MASK_LEGACY); }; @@ -144,8 +170,8 @@ static int rockchip_pcie_init_irq_domain(struct rockchip_pcie *rockchip) return -EINVAL; } - rockchip->irq_domain = irq_domain_add_linear(intc, PCI_NUM_INTX, - &intx_domain_ops, rockchip); + rockchip->irq_domain = irq_domain_create_linear(of_fwnode_handle(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"); @@ -163,25 +189,65 @@ static u32 rockchip_pcie_get_ltssm(struct rockchip_pcie *rockchip) static void rockchip_pcie_enable_ltssm(struct rockchip_pcie *rockchip) { rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_ENABLE_LTSSM, - PCIE_CLIENT_GENERAL_CONTROL); + PCIE_CLIENT_GENERAL_CON); } static void rockchip_pcie_disable_ltssm(struct rockchip_pcie *rockchip) { rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_DISABLE_LTSSM, - PCIE_CLIENT_GENERAL_CONTROL); + PCIE_CLIENT_GENERAL_CON); } -static int rockchip_pcie_link_up(struct dw_pcie *pci) +static bool rockchip_pcie_link_up(struct dw_pcie *pci) { struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); u32 val = rockchip_pcie_get_ltssm(rockchip); - if ((val & PCIE_LINKUP) == PCIE_LINKUP && - (val & PCIE_LTSSM_STATUS_MASK) == PCIE_L0S_ENTRY) - return 1; + return FIELD_GET(PCIE_LINKUP_MASK, val) == PCIE_LINKUP; +} + +/* + * See e.g. section '11.6.6.4 L1 Substate' in the RK3588 TRM V1.0 for the steps + * needed to support L1 substates. Currently, just enable L1 substates for RC + * mode if CLKREQ# is properly connected and supports-clkreq is present in DT. + * For EP mode, there are more things should be done to actually save power in + * L1 substates, so disable L1 substates until there is proper support. + */ +static void rockchip_pcie_configure_l1ss(struct dw_pcie *pci) +{ + struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); - return 0; + /* Enable L1 substates if CLKREQ# is properly connected */ + if (rockchip->supports_clkreq) { + rockchip_pcie_writel_apb(rockchip, PCIE_CLKREQ_READY, + PCIE_CLIENT_POWER_CON); + pci->l1ss_support = true; + return; + } + + /* + * Otherwise, assert CLKREQ# unconditionally. Since + * pci->l1ss_support is not set, the DWC core will prevent L1 + * Substates support from being advertised. + */ + rockchip_pcie_writel_apb(rockchip, + PCIE_CLKREQ_PULL_DOWN | PCIE_CLKREQ_NOT_READY, + PCIE_CLIENT_POWER_CON); +} + +static void rockchip_pcie_enable_l0s(struct dw_pcie *pci) +{ + u32 cap, lnkcap; + + /* Enable L0S capability for all SoCs */ + cap = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + if (cap) { + lnkcap = dw_pcie_readl_dbi(pci, cap + PCI_EXP_LNKCAP); + lnkcap |= PCI_EXP_LNKCAP_ASPM_L0S; + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writel_dbi(pci, cap + PCI_EXP_LNKCAP, lnkcap); + dw_pcie_dbi_ro_wr_dis(pci); + } } static int rockchip_pcie_start_link(struct dw_pcie *pci) @@ -202,7 +268,7 @@ static int rockchip_pcie_start_link(struct dw_pcie *pci) * 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); + msleep(PCIE_T_PVPERL_MS); gpiod_set_value_cansleep(rockchip->rst_gpio, 1); return 0; @@ -233,6 +299,9 @@ static int rockchip_pcie_host_init(struct dw_pcie_rp *pp) irq_set_chained_handler_and_data(irq, rockchip_pcie_intx_handler, rockchip); + rockchip_pcie_configure_l1ss(pci); + rockchip_pcie_enable_l0s(pci); + return 0; } @@ -240,11 +309,37 @@ static const struct dw_pcie_host_ops rockchip_pcie_host_ops = { .init = rockchip_pcie_host_init, }; +/* + * ATS does not work on RK3588 when running in EP mode. + * + * After the host has enabled ATS on the EP side, it will send an IOTLB + * invalidation request to the EP side. However, the RK3588 will never send + * a completion back and eventually the host will print an IOTLB_INV_TIMEOUT + * error, and the EP will not be operational. If we hide the ATS capability, + * things work as expected. + */ +static void rockchip_pcie_ep_hide_broken_ats_cap_rk3588(struct dw_pcie_ep *ep) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct device *dev = pci->dev; + + /* Only hide the ATS capability for RK3588 running in EP mode. */ + if (!of_device_is_compatible(dev->of_node, "rockchip,rk3588-pcie-ep")) + return; + + if (dw_pcie_ep_hide_ext_capability(pci, PCI_EXT_CAP_ID_SECPCI, + PCI_EXT_CAP_ID_ATS)) + dev_err(dev, "failed to hide ATS capability\n"); +} + static void rockchip_pcie_ep_init(struct dw_pcie_ep *ep) { struct dw_pcie *pci = to_dw_pcie_from_ep(ep); enum pci_barno bar; + rockchip_pcie_enable_l0s(pci); + rockchip_pcie_ep_hide_broken_ats_cap_rk3588(ep); + for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) dw_pcie_ep_reset_bar(pci, bar); }; @@ -273,12 +368,12 @@ static const struct pci_epc_features rockchip_pcie_epc_features_rk3568 = { .msi_capable = true, .msix_capable = true, .align = SZ_64K, - .bar[BAR_0] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, - .bar[BAR_1] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, - .bar[BAR_2] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, - .bar[BAR_3] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, - .bar[BAR_4] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, - .bar[BAR_5] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, + .bar[BAR_0] = { .type = BAR_RESIZABLE, }, + .bar[BAR_1] = { .type = BAR_RESIZABLE, }, + .bar[BAR_2] = { .type = BAR_RESIZABLE, }, + .bar[BAR_3] = { .type = BAR_RESIZABLE, }, + .bar[BAR_4] = { .type = BAR_RESIZABLE, }, + .bar[BAR_5] = { .type = BAR_RESIZABLE, }, }; /* @@ -293,12 +388,12 @@ static const struct pci_epc_features rockchip_pcie_epc_features_rk3588 = { .msi_capable = true, .msix_capable = true, .align = SZ_64K, - .bar[BAR_0] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, - .bar[BAR_1] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, - .bar[BAR_2] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, - .bar[BAR_3] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, + .bar[BAR_0] = { .type = BAR_RESIZABLE, }, + .bar[BAR_1] = { .type = BAR_RESIZABLE, }, + .bar[BAR_2] = { .type = BAR_RESIZABLE, }, + .bar[BAR_3] = { .type = BAR_RESIZABLE, }, .bar[BAR_4] = { .type = BAR_RESERVED, }, - .bar[BAR_5] = { .type = BAR_FIXED, .fixed_size = SZ_1M, }, + .bar[BAR_5] = { .type = BAR_RESIZABLE, }, }; static const struct pci_epc_features * @@ -353,6 +448,9 @@ static int rockchip_pcie_resource_get(struct platform_device *pdev, return dev_err_probe(&pdev->dev, PTR_ERR(rockchip->rst), "failed to get reset lines\n"); + rockchip->supports_clkreq = of_property_read_bool(pdev->dev.of_node, + "supports-clkreq"); + return 0; } @@ -379,8 +477,8 @@ static int rockchip_pcie_phy_init(struct rockchip_pcie *rockchip) static void rockchip_pcie_phy_deinit(struct rockchip_pcie *rockchip) { - phy_exit(rockchip->phy); phy_power_off(rockchip->phy); + phy_exit(rockchip->phy); } static const struct dw_pcie_ops dw_pcie_ops = { @@ -389,6 +487,34 @@ static const struct dw_pcie_ops dw_pcie_ops = { .stop_link = rockchip_pcie_stop_link, }; +static irqreturn_t rockchip_pcie_rc_sys_irq_thread(int irq, void *arg) +{ + struct rockchip_pcie *rockchip = arg; + struct dw_pcie *pci = &rockchip->pci; + struct dw_pcie_rp *pp = &pci->pp; + struct device *dev = pci->dev; + u32 reg; + + reg = rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_INTR_STATUS_MISC); + rockchip_pcie_writel_apb(rockchip, reg, PCIE_CLIENT_INTR_STATUS_MISC); + + dev_dbg(dev, "PCIE_CLIENT_INTR_STATUS_MISC: %#x\n", reg); + dev_dbg(dev, "LTSSM_STATUS: %#x\n", rockchip_pcie_get_ltssm(rockchip)); + + if (reg & PCIE_RDLH_LINK_UP_CHGED) { + if (rockchip_pcie_link_up(pci)) { + msleep(PCIE_RESET_CONFIG_WAIT_MS); + dev_dbg(dev, "Received Link up event. Starting enumeration!\n"); + /* Rescan the bus to enumerate endpoint devices */ + pci_lock_rescan_remove(); + pci_rescan_bus(pp->bridge->bus); + pci_unlock_rescan_remove(); + } + } + + return IRQ_HANDLED; +} + static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg) { struct rockchip_pcie *rockchip = arg; @@ -405,11 +531,14 @@ static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg) if (reg & PCIE_LINK_REQ_RST_NOT_INT) { dev_dbg(dev, "hot reset or link-down reset\n"); dw_pcie_ep_linkdown(&pci->ep); + /* Stop delaying link training. */ + val = FIELD_PREP_WM16(PCIE_LTSSM_APP_DLY2_DONE, 1); + rockchip_pcie_writel_apb(rockchip, val, + PCIE_CLIENT_HOT_RESET_CTRL); } if (reg & PCIE_RDLH_LINK_UP_CHGED) { - val = rockchip_pcie_get_ltssm(rockchip); - if ((val & PCIE_LINKUP) == PCIE_LINKUP) { + if (rockchip_pcie_link_up(pci)) { dev_dbg(dev, "link up\n"); dw_pcie_ep_linkup(&pci->ep); } @@ -418,25 +547,52 @@ static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg) return IRQ_HANDLED; } -static int rockchip_pcie_configure_rc(struct rockchip_pcie *rockchip) +static int rockchip_pcie_configure_rc(struct platform_device *pdev, + struct rockchip_pcie *rockchip) { + struct device *dev = &pdev->dev; struct dw_pcie_rp *pp; + int irq, ret; u32 val; if (!IS_ENABLED(CONFIG_PCIE_ROCKCHIP_DW_HOST)) return -ENODEV; + irq = platform_get_irq_byname(pdev, "sys"); + if (irq < 0) + return irq; + + ret = devm_request_threaded_irq(dev, irq, NULL, + rockchip_pcie_rc_sys_irq_thread, + IRQF_ONESHOT, "pcie-sys-rc", rockchip); + if (ret) { + dev_err(dev, "failed to request PCIe sys IRQ\n"); + return ret; + } + /* LTSSM enable control mode */ - val = HIWORD_UPDATE_BIT(PCIE_LTSSM_ENABLE_ENHANCE); + val = FIELD_PREP_WM16(PCIE_LTSSM_ENABLE_ENHANCE, 1); rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_HOT_RESET_CTRL); - rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_RC_MODE, - PCIE_CLIENT_GENERAL_CONTROL); + rockchip_pcie_writel_apb(rockchip, + PCIE_CLIENT_SET_MODE(PCIE_CLIENT_MODE_RC), + PCIE_CLIENT_GENERAL_CON); pp = &rockchip->pci.pp; pp->ops = &rockchip_pcie_host_ops; + pp->use_linkup_irq = true; + + ret = dw_pcie_host_init(pp); + if (ret) { + dev_err(dev, "failed to initialize host\n"); + return ret; + } - return dw_pcie_host_init(pp); + /* unmask DLL up/down indicator */ + val = FIELD_PREP_WM16(PCIE_RDLH_LINK_UP_CHGED, 0); + rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_INTR_MASK_MISC); + + return ret; } static int rockchip_pcie_configure_ep(struct platform_device *pdev, @@ -450,25 +606,28 @@ static int rockchip_pcie_configure_ep(struct platform_device *pdev, return -ENODEV; irq = platform_get_irq_byname(pdev, "sys"); - if (irq < 0) { - dev_err(dev, "missing sys IRQ resource\n"); + if (irq < 0) return irq; - } ret = devm_request_threaded_irq(dev, irq, NULL, rockchip_pcie_ep_sys_irq_thread, - IRQF_ONESHOT, "pcie-sys", rockchip); + IRQF_ONESHOT, "pcie-sys-ep", rockchip); if (ret) { dev_err(dev, "failed to request PCIe sys IRQ\n"); return ret; } - /* LTSSM enable control mode */ - val = HIWORD_UPDATE_BIT(PCIE_LTSSM_ENABLE_ENHANCE); + /* + * LTSSM enable control mode, and automatically delay link training on + * hot reset/link-down reset. + */ + val = FIELD_PREP_WM16(PCIE_LTSSM_ENABLE_ENHANCE, 1) | + FIELD_PREP_WM16(PCIE_LTSSM_APP_DLY2_EN, 1); rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_HOT_RESET_CTRL); - rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_EP_MODE, - PCIE_CLIENT_GENERAL_CONTROL); + rockchip_pcie_writel_apb(rockchip, + PCIE_CLIENT_SET_MODE(PCIE_CLIENT_MODE_EP), + PCIE_CLIENT_GENERAL_CON); rockchip->pci.ep.ops = &rockchip_pcie_ep_ops; rockchip->pci.ep.page_size = SZ_64K; @@ -491,7 +650,9 @@ static int rockchip_pcie_configure_ep(struct platform_device *pdev, pci_epc_init_notify(rockchip->pci.ep.epc); /* unmask DLL up/down indicator and hot reset/link-down reset */ - rockchip_pcie_writel_apb(rockchip, 0x60000, PCIE_CLIENT_INTR_MASK_MISC); + val = FIELD_PREP_WM16(PCIE_RDLH_LINK_UP_CHGED, 0) | + FIELD_PREP_WM16(PCIE_LINK_REQ_RST_NOT_INT, 0); + rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_INTR_MASK_MISC); return ret; } @@ -517,6 +678,10 @@ static int rockchip_pcie_probe(struct platform_device *pdev) rockchip->pci.ops = &dw_pcie_ops; rockchip->data = data; + /* Default N_FTS value (210) is broken, override it to 255 */ + rockchip->pci.n_fts[0] = 255; /* Gen1 */ + rockchip->pci.n_fts[1] = 255; /* Gen2+ */ + ret = rockchip_pcie_resource_get(pdev, rockchip); if (ret) return ret; @@ -526,22 +691,15 @@ static int rockchip_pcie_probe(struct platform_device *pdev) 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) - return dev_err_probe(dev, ret, - "failed to enable vpcie3v3 regulator\n"); - } + ret = devm_regulator_get_enable_optional(dev, "vpcie3v3"); + if (ret < 0 && ret != -ENODEV) + return dev_err_probe(dev, ret, + "failed to enable vpcie3v3 regulator\n"); ret = rockchip_pcie_phy_init(rockchip); if (ret) - goto disable_regulator; + return dev_err_probe(dev, ret, + "failed to initialize the phy\n"); ret = reset_control_deassert(rockchip->rst); if (ret) @@ -553,7 +711,7 @@ static int rockchip_pcie_probe(struct platform_device *pdev) switch (data->mode) { case DW_PCIE_RC_TYPE: - ret = rockchip_pcie_configure_rc(rockchip); + ret = rockchip_pcie_configure_rc(pdev, rockchip); if (ret) goto deinit_clk; break; @@ -574,9 +732,6 @@ deinit_clk: 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; } diff --git a/drivers/pci/controller/dwc/pcie-hisi.c b/drivers/pci/controller/dwc/pcie-hisi.c index 8904b5b85ee5..3c17897e56fc 100644 --- a/drivers/pci/controller/dwc/pcie-hisi.c +++ b/drivers/pci/controller/dwc/pcie-hisi.c @@ -15,6 +15,7 @@ #include <linux/pci-acpi.h> #include <linux/pci-ecam.h> #include "../../pci.h" +#include "../pci-host-common.h" #if defined(CONFIG_PCI_HISI) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)) diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c index 7a11c618b9d9..a52071589377 100644 --- a/drivers/pci/controller/dwc/pcie-histb.c +++ b/drivers/pci/controller/dwc/pcie-histb.c @@ -151,7 +151,7 @@ static struct pci_ops histb_pci_ops = { .write = histb_pcie_wr_own_conf, }; -static int histb_pcie_link_up(struct dw_pcie *pci) +static bool histb_pcie_link_up(struct dw_pcie *pci) { struct histb_pcie *hipcie = to_histb_pcie(pci); u32 regval; @@ -160,11 +160,8 @@ static int histb_pcie_link_up(struct dw_pcie *pci) 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; + return ((regval & PCIE_XMLH_LINK_UP) && (regval & PCIE_RDLH_LINK_UP) && + (status == PCIE_LTSSM_STATE_ACTIVE)); } static int histb_pcie_start_link(struct dw_pcie *pci) @@ -409,16 +406,21 @@ static int histb_pcie_probe(struct platform_device *pdev) ret = histb_pcie_host_enable(pp); if (ret) { dev_err(dev, "failed to enable host\n"); - return ret; + goto err_exit_phy; } ret = dw_pcie_host_init(pp); if (ret) { dev_err(dev, "failed to initialize host\n"); - return ret; + goto err_exit_phy; } return 0; + +err_exit_phy: + phy_exit(hipcie->phy); + + return ret; } static void histb_pcie_remove(struct platform_device *pdev) @@ -427,8 +429,7 @@ static void histb_pcie_remove(struct platform_device *pdev) histb_pcie_host_disable(hipcie); - if (hipcie->phy) - phy_exit(hipcie->phy); + phy_exit(hipcie->phy); } static const struct of_device_id histb_pcie_of_match[] = { @@ -439,7 +440,7 @@ MODULE_DEVICE_TABLE(of, histb_pcie_of_match); static struct platform_driver histb_pcie_platform_driver = { .probe = histb_pcie_probe, - .remove_new = histb_pcie_remove, + .remove = histb_pcie_remove, .driver = { .name = "histb-pcie", .of_match_table = histb_pcie_of_match, diff --git a/drivers/pci/controller/dwc/pcie-intel-gw.c b/drivers/pci/controller/dwc/pcie-intel-gw.c index 676d2aba4fbd..c21906eced61 100644 --- a/drivers/pci/controller/dwc/pcie-intel-gw.c +++ b/drivers/pci/controller/dwc/pcie-intel-gw.c @@ -57,7 +57,6 @@ 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 { @@ -381,13 +380,7 @@ static int intel_pcie_rc_init(struct dw_pcie_rp *pp) 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 = { @@ -409,6 +402,7 @@ static int intel_pcie_probe(struct platform_device *pdev) platform_set_drvdata(pdev, pcie); pci = &pcie->pci; pci->dev = dev; + pci->use_parent_dt_ranges = true; pp = &pci->pp; ret = intel_pcie_get_resources(pdev); @@ -443,7 +437,7 @@ static const struct of_device_id of_intel_pcie_match[] = { static struct platform_driver intel_pcie_driver = { .probe = intel_pcie_probe, - .remove_new = intel_pcie_remove, + .remove = intel_pcie_remove, .driver = { .name = "intel-gw-pcie", .of_match_table = of_intel_pcie_match, diff --git a/drivers/pci/controller/dwc/pcie-keembay.c b/drivers/pci/controller/dwc/pcie-keembay.c index 278205db60a2..60e74ac782af 100644 --- a/drivers/pci/controller/dwc/pcie-keembay.c +++ b/drivers/pci/controller/dwc/pcie-keembay.c @@ -101,7 +101,7 @@ static void keembay_pcie_ltssm_set(struct keembay_pcie *pcie, bool enable) writel(val, pcie->apb_base + PCIE_REGS_PCIE_APP_CNTRL); } -static int keembay_pcie_link_up(struct dw_pcie *pci) +static bool keembay_pcie_link_up(struct dw_pcie *pci) { struct keembay_pcie *pcie = dev_get_drvdata(pci->dev); u32 val; @@ -309,7 +309,6 @@ static int keembay_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, } static const struct pci_epc_features keembay_pcie_epc_features = { - .linkup_notifier = false, .msi_capable = true, .msix_capable = true, .bar[BAR_0] = { .only_64bit = true, }, diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c index 85a2c77b1835..91559c8b1866 100644 --- a/drivers/pci/controller/dwc/pcie-kirin.c +++ b/drivers/pci/controller/dwc/pcie-kirin.c @@ -216,10 +216,9 @@ static int hi3660_pcie_phy_start(struct hi3660_pcie_phy *phy) 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; - } + if (reg_val & PIPE_CLK_STABLE) + return dev_err_probe(dev, -ETIMEDOUT, + "PIPE clk is not stable\n"); return 0; } @@ -371,10 +370,9 @@ static int kirin_pcie_get_gpio_enable(struct kirin_pcie *pcie, if (ret < 0) return 0; - if (ret > MAX_PCI_SLOTS) { - dev_err(dev, "Too many GPIO clock requests!\n"); - return -EINVAL; - } + if (ret > MAX_PCI_SLOTS) + return dev_err_probe(dev, -EINVAL, + "Too many GPIO clock requests!\n"); pcie->n_gpio_clkreq = ret; @@ -420,17 +418,16 @@ static int kirin_pcie_parse_port(struct kirin_pcie *pcie, "unable to get a valid reset gpio\n"); } - if (pcie->num_slots + 1 >= MAX_PCI_SLOTS) { - dev_err(dev, "Too many PCI slots!\n"); - return -EINVAL; - } + if (pcie->num_slots + 1 >= MAX_PCI_SLOTS) + return dev_err_probe(dev, -EINVAL, + "Too many PCI slots!\n"); + pcie->num_slots++; ret = of_pci_get_devfn(child); - if (ret < 0) { - dev_err(dev, "failed to parse devfn: %d\n", ret); - return ret; - } + if (ret < 0) + return dev_err_probe(dev, ret, + "failed to parse devfn\n"); slot = PCI_SLOT(ret); @@ -452,7 +449,7 @@ 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; + struct device_node *node = dev->of_node; void __iomem *apb_base; int ret; @@ -477,17 +474,13 @@ static long kirin_pcie_get_resource(struct kirin_pcie *kirin_pcie, return ret; /* Parse OF children */ - for_each_available_child_of_node(node, child) { + for_each_available_child_of_node_scoped(node, child) { ret = kirin_pcie_parse_port(kirin_pcie, pdev, child); if (ret) - goto put_node; + return ret; } return 0; - -put_node: - of_node_put(child); - return ret; } static void kirin_pcie_sideband_dbi_w_mode(struct kirin_pcie *kirin_pcie, @@ -593,16 +586,13 @@ static void kirin_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, kirin_pcie_sideband_dbi_w_mode(kirin_pcie, false); } -static int kirin_pcie_link_up(struct dw_pcie *pci) +static bool 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; + return (val & PCIE_LINKUP_ENABLE) == PCIE_LINKUP_ENABLE; } static int kirin_pcie_start_link(struct dw_pcie *pci) @@ -729,16 +719,9 @@ static int kirin_pcie_probe(struct platform_device *pdev) 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; - } + if (!data) + return dev_err_probe(dev, -EINVAL, "OF data missing\n"); kirin_pcie = devm_kzalloc(dev, sizeof(struct kirin_pcie), GFP_KERNEL); if (!kirin_pcie) @@ -769,7 +752,7 @@ static int kirin_pcie_probe(struct platform_device *pdev) static struct platform_driver kirin_pcie_driver = { .probe = kirin_pcie_probe, - .remove_new = kirin_pcie_remove, + .remove = kirin_pcie_remove, .driver = { .name = "kirin-pcie", .of_match_table = kirin_pcie_match, diff --git a/drivers/pci/controller/dwc/pcie-nxp-s32g.c b/drivers/pci/controller/dwc/pcie-nxp-s32g.c new file mode 100644 index 000000000000..47745749f75c --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-nxp-s32g.c @@ -0,0 +1,406 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe host controller driver for NXP S32G SoCs + * + * Copyright 2019-2025 NXP + */ + +#include <linux/interrupt.h> +#include <linux/io.h> +#include <linux/module.h> +#include <linux/of_device.h> +#include <linux/of_address.h> +#include <linux/pci.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/sizes.h> +#include <linux/types.h> + +#include "pcie-designware.h" + +/* PCIe controller Sub-System */ + +/* PCIe controller 0 General Control 1 */ +#define PCIE_S32G_PE0_GEN_CTRL_1 0x50 +#define DEVICE_TYPE_MASK GENMASK(3, 0) +#define SRIS_MODE BIT(8) + +/* PCIe controller 0 General Control 3 */ +#define PCIE_S32G_PE0_GEN_CTRL_3 0x58 +#define LTSSM_EN BIT(0) + +/* PCIe Controller 0 Interrupt Status */ +#define PCIE_S32G_PE0_INT_STS 0xE8 +#define HP_INT_STS BIT(6) + +/* Boundary between peripheral space and physical memory space */ +#define S32G_MEMORY_BOUNDARY_ADDR 0x80000000 + +struct s32g_pcie_port { + struct list_head list; + struct phy *phy; +}; + +struct s32g_pcie { + struct dw_pcie pci; + void __iomem *ctrl_base; + struct list_head ports; +}; + +#define to_s32g_from_dw_pcie(x) \ + container_of(x, struct s32g_pcie, pci) + +static void s32g_pcie_writel_ctrl(struct s32g_pcie *s32g_pp, u32 reg, u32 val) +{ + writel(val, s32g_pp->ctrl_base + reg); +} + +static u32 s32g_pcie_readl_ctrl(struct s32g_pcie *s32g_pp, u32 reg) +{ + return readl(s32g_pp->ctrl_base + reg); +} + +static void s32g_pcie_enable_ltssm(struct s32g_pcie *s32g_pp) +{ + u32 reg; + + reg = s32g_pcie_readl_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_3); + reg |= LTSSM_EN; + s32g_pcie_writel_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_3, reg); +} + +static void s32g_pcie_disable_ltssm(struct s32g_pcie *s32g_pp) +{ + u32 reg; + + reg = s32g_pcie_readl_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_3); + reg &= ~LTSSM_EN; + s32g_pcie_writel_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_3, reg); +} + +static int s32g_pcie_start_link(struct dw_pcie *pci) +{ + struct s32g_pcie *s32g_pp = to_s32g_from_dw_pcie(pci); + + s32g_pcie_enable_ltssm(s32g_pp); + + return 0; +} + +static void s32g_pcie_stop_link(struct dw_pcie *pci) +{ + struct s32g_pcie *s32g_pp = to_s32g_from_dw_pcie(pci); + + s32g_pcie_disable_ltssm(s32g_pp); +} + +static struct dw_pcie_ops s32g_pcie_ops = { + .start_link = s32g_pcie_start_link, + .stop_link = s32g_pcie_stop_link, +}; + +/* Configure the AMBA AXI Coherency Extensions (ACE) interface */ +static void s32g_pcie_reset_mstr_ace(struct dw_pcie *pci) +{ + u32 ddr_base_low = lower_32_bits(S32G_MEMORY_BOUNDARY_ADDR); + u32 ddr_base_high = upper_32_bits(S32G_MEMORY_BOUNDARY_ADDR); + + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writel_dbi(pci, COHERENCY_CONTROL_3_OFF, 0x0); + + /* + * Ncore is a cache-coherent interconnect module that enables the + * integration of heterogeneous coherent and non-coherent agents in + * the chip. Ncore transactions to peripheral should be non-coherent + * or it might drop them. + * + * One example where this is needed are PCIe MSIs, which use NoSnoop=0 + * and might end up routed to Ncore. PCIe coherent traffic (e.g. MSIs) + * that targets peripheral space will be dropped by Ncore because + * peripherals on S32G are not coherent as slaves. We add a hard + * boundary in the PCIe controller coherency control registers to + * separate physical memory space from peripheral space. + * + * Define the start of DDR as seen by Linux as this boundary between + * "memory" and "peripherals", with peripherals being below. + */ + dw_pcie_writel_dbi(pci, COHERENCY_CONTROL_1_OFF, + (ddr_base_low & CFG_MEMTYPE_BOUNDARY_LOW_ADDR_MASK)); + dw_pcie_writel_dbi(pci, COHERENCY_CONTROL_2_OFF, ddr_base_high); + dw_pcie_dbi_ro_wr_dis(pci); +} + +static int s32g_init_pcie_controller(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct s32g_pcie *s32g_pp = to_s32g_from_dw_pcie(pci); + u32 val; + + /* Set RP mode */ + val = s32g_pcie_readl_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_1); + val &= ~DEVICE_TYPE_MASK; + val |= FIELD_PREP(DEVICE_TYPE_MASK, PCI_EXP_TYPE_ROOT_PORT); + + /* Use default CRNS */ + val &= ~SRIS_MODE; + + s32g_pcie_writel_ctrl(s32g_pp, PCIE_S32G_PE0_GEN_CTRL_1, val); + + /* + * Make sure we use the coherency defaults (just in case the settings + * have been changed from their reset values) + */ + s32g_pcie_reset_mstr_ace(pci); + + dw_pcie_dbi_ro_wr_en(pci); + + val = dw_pcie_readl_dbi(pci, PCIE_PORT_FORCE); + val |= PORT_FORCE_DO_DESKEW_FOR_SRIS; + dw_pcie_writel_dbi(pci, PCIE_PORT_FORCE, val); + + val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + val |= GEN3_RELATED_OFF_EQ_PHASE_2_3; + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val); + + dw_pcie_dbi_ro_wr_dis(pci); + + return 0; +} + +static const struct dw_pcie_host_ops s32g_pcie_host_ops = { + .init = s32g_init_pcie_controller, +}; + +static int s32g_init_pcie_phy(struct s32g_pcie *s32g_pp) +{ + struct dw_pcie *pci = &s32g_pp->pci; + struct device *dev = pci->dev; + struct s32g_pcie_port *port, *tmp; + int ret; + + list_for_each_entry(port, &s32g_pp->ports, list) { + ret = phy_init(port->phy); + if (ret) { + dev_err(dev, "Failed to init serdes PHY\n"); + goto err_phy_revert; + } + + ret = phy_set_mode_ext(port->phy, PHY_MODE_PCIE, 0); + if (ret) { + dev_err(dev, "Failed to set mode on serdes PHY\n"); + goto err_phy_exit; + } + + ret = phy_power_on(port->phy); + if (ret) { + dev_err(dev, "Failed to power on serdes PHY\n"); + goto err_phy_exit; + } + } + + return 0; + +err_phy_exit: + phy_exit(port->phy); + +err_phy_revert: + list_for_each_entry_continue_reverse(port, &s32g_pp->ports, list) { + phy_power_off(port->phy); + phy_exit(port->phy); + } + + list_for_each_entry_safe(port, tmp, &s32g_pp->ports, list) + list_del(&port->list); + + return ret; +} + +static void s32g_deinit_pcie_phy(struct s32g_pcie *s32g_pp) +{ + struct s32g_pcie_port *port, *tmp; + + list_for_each_entry_safe(port, tmp, &s32g_pp->ports, list) { + phy_power_off(port->phy); + phy_exit(port->phy); + list_del(&port->list); + } +} + +static int s32g_pcie_init(struct device *dev, struct s32g_pcie *s32g_pp) +{ + s32g_pcie_disable_ltssm(s32g_pp); + + return s32g_init_pcie_phy(s32g_pp); +} + +static void s32g_pcie_deinit(struct s32g_pcie *s32g_pp) +{ + s32g_pcie_disable_ltssm(s32g_pp); + + s32g_deinit_pcie_phy(s32g_pp); +} + +static int s32g_pcie_parse_port(struct s32g_pcie *s32g_pp, struct device_node *node) +{ + struct device *dev = s32g_pp->pci.dev; + struct s32g_pcie_port *port; + int num_lanes; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + port->phy = devm_of_phy_get(dev, node, NULL); + if (IS_ERR(port->phy)) + return dev_err_probe(dev, PTR_ERR(port->phy), + "Failed to get serdes PHY\n"); + + INIT_LIST_HEAD(&port->list); + list_add_tail(&port->list, &s32g_pp->ports); + + /* + * The DWC core initialization code cannot yet parse the num-lanes + * attribute in the Root Port node. The S32G only supports one Root + * Port for now so its driver can parse the node and set the num_lanes + * field of struct dwc_pcie before calling dw_pcie_host_init(). + */ + if (!of_property_read_u32(node, "num-lanes", &num_lanes)) + s32g_pp->pci.num_lanes = num_lanes; + + return 0; +} + +static int s32g_pcie_parse_ports(struct device *dev, struct s32g_pcie *s32g_pp) +{ + struct s32g_pcie_port *port, *tmp; + int ret = -ENOENT; + + for_each_available_child_of_node_scoped(dev->of_node, of_port) { + if (!of_node_is_type(of_port, "pci")) + continue; + + ret = s32g_pcie_parse_port(s32g_pp, of_port); + if (ret) + goto err_port; + } + +err_port: + list_for_each_entry_safe(port, tmp, &s32g_pp->ports, list) + list_del(&port->list); + + return ret; +} + +static int s32g_pcie_get_resources(struct platform_device *pdev, + struct s32g_pcie *s32g_pp) +{ + struct dw_pcie *pci = &s32g_pp->pci; + struct device *dev = &pdev->dev; + int ret; + + pci->dev = dev; + pci->ops = &s32g_pcie_ops; + + s32g_pp->ctrl_base = devm_platform_ioremap_resource_byname(pdev, "ctrl"); + if (IS_ERR(s32g_pp->ctrl_base)) + return PTR_ERR(s32g_pp->ctrl_base); + + INIT_LIST_HEAD(&s32g_pp->ports); + + ret = s32g_pcie_parse_ports(dev, s32g_pp); + if (ret) + return dev_err_probe(dev, ret, + "Failed to parse Root Port: %d\n", ret); + + platform_set_drvdata(pdev, s32g_pp); + + return 0; +} + +static int s32g_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct s32g_pcie *s32g_pp; + struct dw_pcie_rp *pp; + int ret; + + s32g_pp = devm_kzalloc(dev, sizeof(*s32g_pp), GFP_KERNEL); + if (!s32g_pp) + return -ENOMEM; + + ret = s32g_pcie_get_resources(pdev, s32g_pp); + if (ret) + return ret; + + pm_runtime_no_callbacks(dev); + devm_pm_runtime_enable(dev); + ret = pm_runtime_get_sync(dev); + if (ret < 0) + goto err_pm_runtime_put; + + ret = s32g_pcie_init(dev, s32g_pp); + if (ret) + goto err_pm_runtime_put; + + pp = &s32g_pp->pci.pp; + pp->ops = &s32g_pcie_host_ops; + pp->use_atu_msg = true; + + ret = dw_pcie_host_init(pp); + if (ret) + goto err_pcie_deinit; + + return 0; + +err_pcie_deinit: + s32g_pcie_deinit(s32g_pp); +err_pm_runtime_put: + pm_runtime_put(dev); + + return ret; +} + +static int s32g_pcie_suspend_noirq(struct device *dev) +{ + struct s32g_pcie *s32g_pp = dev_get_drvdata(dev); + struct dw_pcie *pci = &s32g_pp->pci; + + return dw_pcie_suspend_noirq(pci); +} + +static int s32g_pcie_resume_noirq(struct device *dev) +{ + struct s32g_pcie *s32g_pp = dev_get_drvdata(dev); + struct dw_pcie *pci = &s32g_pp->pci; + + return dw_pcie_resume_noirq(pci); +} + +static const struct dev_pm_ops s32g_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(s32g_pcie_suspend_noirq, + s32g_pcie_resume_noirq) +}; + +static const struct of_device_id s32g_pcie_of_match[] = { + { .compatible = "nxp,s32g2-pcie" }, + { /* sentinel */ }, +}; +MODULE_DEVICE_TABLE(of, s32g_pcie_of_match); + +static struct platform_driver s32g_pcie_driver = { + .driver = { + .name = "s32g-pcie", + .of_match_table = s32g_pcie_of_match, + .suppress_bind_attrs = true, + .pm = pm_sleep_ptr(&s32g_pcie_pm_ops), + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, + .probe = s32g_pcie_probe, +}; + +builtin_platform_driver(s32g_pcie_driver); + +MODULE_AUTHOR("Ionut Vicovan <Ionut.Vicovan@nxp.com>"); +MODULE_DESCRIPTION("NXP S32G PCIe Host controller driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pci/controller/dwc/pcie-qcom-common.c b/drivers/pci/controller/dwc/pcie-qcom-common.c index 3aad19b56da8..01c5387e53bf 100644 --- a/drivers/pci/controller/dwc/pcie-qcom-common.c +++ b/drivers/pci/controller/dwc/pcie-qcom-common.c @@ -8,9 +8,11 @@ #include "pcie-designware.h" #include "pcie-qcom-common.h" -void qcom_pcie_common_set_16gt_equalization(struct dw_pcie *pci) +void qcom_pcie_common_set_equalization(struct dw_pcie *pci) { + struct device *dev = pci->dev; u32 reg; + u16 speed; /* * GEN3_RELATED_OFF register is repurposed to apply equalization @@ -19,32 +21,40 @@ void qcom_pcie_common_set_16gt_equalization(struct dw_pcie *pci) * determines the data rate for which these equalization settings are * applied. */ - reg = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); - reg &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL; - reg &= ~GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK; - reg |= FIELD_PREP(GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK, - GEN3_RELATED_OFF_RATE_SHADOW_SEL_16_0GT); - dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, reg); - reg = dw_pcie_readl_dbi(pci, GEN3_EQ_FB_MODE_DIR_CHANGE_OFF); - reg &= ~(GEN3_EQ_FMDC_T_MIN_PHASE23 | - GEN3_EQ_FMDC_N_EVALS | - GEN3_EQ_FMDC_MAX_PRE_CUSROR_DELTA | - GEN3_EQ_FMDC_MAX_POST_CUSROR_DELTA); - reg |= FIELD_PREP(GEN3_EQ_FMDC_T_MIN_PHASE23, 0x1) | - FIELD_PREP(GEN3_EQ_FMDC_N_EVALS, 0xd) | - FIELD_PREP(GEN3_EQ_FMDC_MAX_PRE_CUSROR_DELTA, 0x5) | - FIELD_PREP(GEN3_EQ_FMDC_MAX_POST_CUSROR_DELTA, 0x5); - dw_pcie_writel_dbi(pci, GEN3_EQ_FB_MODE_DIR_CHANGE_OFF, reg); + for (speed = PCIE_SPEED_8_0GT; speed <= pcie_link_speed[pci->max_link_speed]; speed++) { + if (speed > PCIE_SPEED_32_0GT) { + dev_warn(dev, "Skipped equalization settings for unsupported data rate\n"); + break; + } - reg = dw_pcie_readl_dbi(pci, GEN3_EQ_CONTROL_OFF); - reg &= ~(GEN3_EQ_CONTROL_OFF_FB_MODE | - GEN3_EQ_CONTROL_OFF_PHASE23_EXIT_MODE | - GEN3_EQ_CONTROL_OFF_FOM_INC_INITIAL_EVAL | - GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC); - dw_pcie_writel_dbi(pci, GEN3_EQ_CONTROL_OFF, reg); + reg = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF); + reg &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL; + reg &= ~GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK; + reg |= FIELD_PREP(GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK, + speed - PCIE_SPEED_8_0GT); + dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, reg); + + reg = dw_pcie_readl_dbi(pci, GEN3_EQ_FB_MODE_DIR_CHANGE_OFF); + reg &= ~(GEN3_EQ_FMDC_T_MIN_PHASE23 | + GEN3_EQ_FMDC_N_EVALS | + GEN3_EQ_FMDC_MAX_PRE_CURSOR_DELTA | + GEN3_EQ_FMDC_MAX_POST_CURSOR_DELTA); + reg |= FIELD_PREP(GEN3_EQ_FMDC_T_MIN_PHASE23, 0x1) | + FIELD_PREP(GEN3_EQ_FMDC_N_EVALS, 0xd) | + FIELD_PREP(GEN3_EQ_FMDC_MAX_PRE_CURSOR_DELTA, 0x5) | + FIELD_PREP(GEN3_EQ_FMDC_MAX_POST_CURSOR_DELTA, 0x5); + dw_pcie_writel_dbi(pci, GEN3_EQ_FB_MODE_DIR_CHANGE_OFF, reg); + + reg = dw_pcie_readl_dbi(pci, GEN3_EQ_CONTROL_OFF); + reg &= ~(GEN3_EQ_CONTROL_OFF_FB_MODE | + GEN3_EQ_CONTROL_OFF_PHASE23_EXIT_MODE | + GEN3_EQ_CONTROL_OFF_FOM_INC_INITIAL_EVAL | + GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC); + dw_pcie_writel_dbi(pci, GEN3_EQ_CONTROL_OFF, reg); + } } -EXPORT_SYMBOL_GPL(qcom_pcie_common_set_16gt_equalization); +EXPORT_SYMBOL_GPL(qcom_pcie_common_set_equalization); void qcom_pcie_common_set_16gt_lane_margining(struct dw_pcie *pci) { diff --git a/drivers/pci/controller/dwc/pcie-qcom-common.h b/drivers/pci/controller/dwc/pcie-qcom-common.h index 7d88d29e4766..7f5ca2fd9a72 100644 --- a/drivers/pci/controller/dwc/pcie-qcom-common.h +++ b/drivers/pci/controller/dwc/pcie-qcom-common.h @@ -8,7 +8,7 @@ struct dw_pcie; -void qcom_pcie_common_set_16gt_equalization(struct dw_pcie *pci); +void qcom_pcie_common_set_equalization(struct dw_pcie *pci); void qcom_pcie_common_set_16gt_lane_margining(struct dw_pcie *pci); #endif diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c index e588fcc54589..f1bc0ac81a92 100644 --- a/drivers/pci/controller/dwc/pcie-qcom-ep.c +++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c @@ -48,7 +48,7 @@ #define PARF_DBI_BASE_ADDR_HI 0x354 #define PARF_SLV_ADDR_SPACE_SIZE 0x358 #define PARF_SLV_ADDR_SPACE_SIZE_HI 0x35c -#define PARF_NO_SNOOP_OVERIDE 0x3d4 +#define PARF_NO_SNOOP_OVERRIDE 0x3d4 #define PARF_ATU_BASE_ADDR 0x634 #define PARF_ATU_BASE_ADDR_HI 0x638 #define PARF_SRIS_MODE 0x644 @@ -60,6 +60,7 @@ #define PARF_DEVICE_TYPE 0x1000 #define PARF_BDF_TO_SID_CFG 0x2c00 #define PARF_INT_ALL_5_MASK 0x2dcc +#define PARF_INT_ALL_3_MASK 0x2e18 /* PARF_INT_ALL_{STATUS/CLEAR/MASK} register fields */ #define PARF_INT_ALL_LINK_DOWN BIT(1) @@ -89,9 +90,9 @@ #define PARF_DEBUG_INT_CFG_BUS_MASTER_EN BIT(2) #define PARF_DEBUG_INT_RADM_PM_TURNOFF BIT(3) -/* PARF_NO_SNOOP_OVERIDE register fields */ -#define WR_NO_SNOOP_OVERIDE_EN BIT(1) -#define RD_NO_SNOOP_OVERIDE_EN BIT(3) +/* PARF_NO_SNOOP_OVERRIDE register fields */ +#define WR_NO_SNOOP_OVERRIDE_EN BIT(1) +#define RD_NO_SNOOP_OVERRIDE_EN BIT(3) /* PARF_DEVICE_TYPE register fields */ #define PARF_DEVICE_TYPE_EP 0x0 @@ -132,6 +133,9 @@ /* PARF_INT_ALL_5_MASK fields */ #define PARF_INT_ALL_5_MHI_RAM_DATA_PARITY_ERR BIT(0) +/* PARF_INT_ALL_3_MASK fields */ +#define PARF_INT_ALL_3_PTM_UPDATING BIT(4) + /* ELBI registers */ #define ELBI_SYS_STTS 0x08 #define ELBI_CS2_ENABLE 0xa4 @@ -175,7 +179,6 @@ struct qcom_pcie_ep_cfg { * 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 @@ -198,7 +201,6 @@ 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; @@ -261,12 +263,11 @@ static void qcom_pcie_ep_configure_tcsr(struct qcom_pcie_ep *pcie_ep) } } -static int qcom_pcie_dw_link_up(struct dw_pcie *pci) +static bool 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); + reg = readl_relaxed(pci->elbi_base + ELBI_SYS_STTS); return reg & XMLH_LINK_UP; } @@ -290,16 +291,15 @@ static void qcom_pcie_dw_stop_link(struct dw_pcie *pci) 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); + writel(1, pci->elbi_base + 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); + writel(0, pci->elbi_base + ELBI_CS2_ENABLE); } static void qcom_pcie_ep_icc_update(struct qcom_pcie_ep *pcie_ep) @@ -396,6 +396,10 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci) return ret; } + /* Perform cleanup that requires refclk */ + pci_epc_deinit_notify(pci->ep.epc); + dw_pcie_ep_cleanup(&pci->ep); + /* 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); @@ -493,16 +497,20 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci) writel_relaxed(val, pcie_ep->parf + PARF_INT_ALL_5_MASK); } + val = readl_relaxed(pcie_ep->parf + PARF_INT_ALL_3_MASK); + val &= ~PARF_INT_ALL_3_PTM_UPDATING; + writel_relaxed(val, pcie_ep->parf + PARF_INT_ALL_3_MASK); + ret = dw_pcie_ep_init_registers(&pcie_ep->pci.ep); if (ret) { dev_err(dev, "Failed to complete initialization: %d\n", ret); goto err_disable_resources; } - if (pcie_link_speed[pci->max_link_speed] == PCIE_SPEED_16_0GT) { - qcom_pcie_common_set_16gt_equalization(pci); + qcom_pcie_common_set_equalization(pci); + + if (pcie_link_speed[pci->max_link_speed] == PCIE_SPEED_16_0GT) qcom_pcie_common_set_16gt_lane_margining(pci); - } /* * The physical address of the MMIO region which is exposed as the BAR @@ -525,8 +533,8 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci) writel_relaxed(val, pcie_ep->parf + PARF_LTSSM); if (pcie_ep->cfg && pcie_ep->cfg->override_no_snoop) - writel_relaxed(WR_NO_SNOOP_OVERIDE_EN | RD_NO_SNOOP_OVERIDE_EN, - pcie_ep->parf + PARF_NO_SNOOP_OVERIDE); + writel_relaxed(WR_NO_SNOOP_OVERRIDE_EN | RD_NO_SNOOP_OVERRIDE_EN, + pcie_ep->parf + PARF_NO_SNOOP_OVERRIDE); return 0; @@ -540,8 +548,6 @@ static void qcom_pcie_perst_assert(struct dw_pcie *pci) { struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci); - pci_epc_deinit_notify(pci->ep.epc); - dw_pcie_ep_cleanup(&pci->ep); qcom_pcie_disable_resources(pcie_ep); pcie_ep->link_status = QCOM_PCIE_EP_LINK_DISABLED; } @@ -573,11 +579,6 @@ static int qcom_pcie_ep_get_io_resources(struct platform_device *pdev, 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) { @@ -821,8 +822,11 @@ static void qcom_pcie_ep_init_debugfs(struct qcom_pcie_ep *pcie_ep) static const struct pci_epc_features qcom_pcie_epc_features = { .linkup_notifier = true, .msi_capable = true, - .msix_capable = false, .align = SZ_4K, + .bar[BAR_0] = { .only_64bit = true, }, + .bar[BAR_1] = { .type = BAR_RESERVED, }, + .bar[BAR_2] = { .only_64bit = true, }, + .bar[BAR_3] = { .type = BAR_RESERVED, }, }; static const struct pci_epc_features * @@ -860,7 +864,6 @@ static int qcom_pcie_ep_probe(struct platform_device *pdev) pcie_ep->pci.dev = dev; pcie_ep->pci.ops = &pci_ops; pcie_ep->pci.ep.ops = &pci_ep_ops; - pcie_ep->pci.edma.nr_irqs = 1; pcie_ep->cfg = of_device_get_match_data(dev); if (pcie_ep->cfg && pcie_ep->cfg->hdma_support) { @@ -931,13 +934,14 @@ static const struct of_device_id qcom_pcie_ep_match[] = { { .compatible = "qcom,sa8775p-pcie-ep", .data = &cfg_1_34_0}, { .compatible = "qcom,sdx55-pcie-ep", }, { .compatible = "qcom,sm8450-pcie-ep", }, + { .compatible = "qcom,sar2130p-pcie-ep", }, { } }; MODULE_DEVICE_TABLE(of, qcom_pcie_ep_match); static struct platform_driver qcom_pcie_ep_driver = { .probe = qcom_pcie_ep_probe, - .remove_new = qcom_pcie_ep_remove, + .remove = qcom_pcie_ep_remove, .driver = { .name = "qcom-pcie-ep", .of_match_table = qcom_pcie_ep_match, diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index ef44a82be058..7b92e7a1c0d9 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -21,7 +21,9 @@ #include <linux/limits.h> #include <linux/init.h> #include <linux/of.h> +#include <linux/of_pci.h> #include <linux/pci.h> +#include <linux/pci-ecam.h> #include <linux/pm_opp.h> #include <linux/pm_runtime.h> #include <linux/platform_device.h> @@ -34,6 +36,7 @@ #include <linux/units.h> #include "../../pci.h" +#include "../pci-host-common.h" #include "pcie-designware.h" #include "pcie-qcom-common.h" @@ -61,7 +64,7 @@ #define PARF_DBI_BASE_ADDR_V2_HI 0x354 #define PARF_SLV_ADDR_SPACE_SIZE_V2 0x358 #define PARF_SLV_ADDR_SPACE_SIZE_V2_HI 0x35c -#define PARF_NO_SNOOP_OVERIDE 0x3d4 +#define PARF_NO_SNOOP_OVERRIDE 0x3d4 #define PARF_ATU_BASE_ADDR 0x634 #define PARF_ATU_BASE_ADDR_HI 0x638 #define PARF_DEVICE_TYPE 0x1000 @@ -133,10 +136,11 @@ /* PARF_INT_ALL_{STATUS/CLEAR/MASK} register fields */ #define PARF_INT_ALL_LINK_UP BIT(13) +#define PARF_INT_MSI_DEV_0_7 GENMASK(30, 23) -/* PARF_NO_SNOOP_OVERIDE register fields */ -#define WR_NO_SNOOP_OVERIDE_EN BIT(1) -#define RD_NO_SNOOP_OVERIDE_EN BIT(3) +/* PARF_NO_SNOOP_OVERRIDE register fields */ +#define WR_NO_SNOOP_OVERRIDE_EN BIT(1) +#define RD_NO_SNOOP_OVERRIDE_EN BIT(3) /* PARF_DEVICE_TYPE register fields */ #define DEVICE_TYPE_RC 0x4 @@ -254,53 +258,68 @@ struct qcom_pcie_ops { * @ops: qcom PCIe ops structure * @override_no_snoop: Override NO_SNOOP attribute in TLP to enable cache * snooping + * @firmware_managed: Set if the Root Complex is firmware managed */ struct qcom_pcie_cfg { const struct qcom_pcie_ops *ops; bool override_no_snoop; + bool firmware_managed; bool no_l0s; }; +struct qcom_pcie_port { + struct list_head list; + struct gpio_desc *reset; + struct phy *phy; +}; + struct qcom_pcie { struct dw_pcie *pci; void __iomem *parf; /* DT parf */ - void __iomem *elbi; /* DT elbi */ void __iomem *mhi; union qcom_pcie_resources res; - struct phy *phy; - struct gpio_desc *reset; struct icc_path *icc_mem; struct icc_path *icc_cpu; const struct qcom_pcie_cfg *cfg; struct dentry *debugfs; + struct list_head ports; bool suspended; bool use_pm_opp; }; #define to_qcom_pcie(x) dev_get_drvdata((x)->dev) -static void qcom_ep_reset_assert(struct qcom_pcie *pcie) +static void qcom_perst_assert(struct qcom_pcie *pcie, bool assert) { - gpiod_set_value_cansleep(pcie->reset, 1); + struct qcom_pcie_port *port; + int val = assert ? 1 : 0; + + list_for_each_entry(port, &pcie->ports, list) + gpiod_set_value_cansleep(port->reset, val); + usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500); } +static void qcom_ep_reset_assert(struct qcom_pcie *pcie) +{ + qcom_perst_assert(pcie, true); +} + 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); + msleep(PCIE_T_PVPERL_MS); + qcom_perst_assert(pcie, false); } static int qcom_pcie_start_link(struct dw_pcie *pci) { struct qcom_pcie *pcie = to_qcom_pcie(pci); - if (pcie_link_speed[pci->max_link_speed] == PCIE_SPEED_16_0GT) { - qcom_pcie_common_set_16gt_equalization(pci); + qcom_pcie_common_set_equalization(pci); + + if (pcie_link_speed[pci->max_link_speed] == PCIE_SPEED_16_0GT) qcom_pcie_common_set_16gt_lane_margining(pci); - } /* Enable Link Training state machine */ if (pcie->cfg->ops->ltssm_enable) @@ -389,12 +408,17 @@ static void qcom_pcie_configure_dbi_atu_base(struct qcom_pcie *pcie) static void qcom_pcie_2_1_0_ltssm_enable(struct qcom_pcie *pcie) { + struct dw_pcie *pci = pcie->pci; u32 val; + if (!pci->elbi_base) { + dev_err(pci->dev, "ELBI is not present\n"); + return; + } /* enable link training */ - val = readl(pcie->elbi + ELBI_SYS_CTRL); + val = readl(pci->elbi_base + ELBI_SYS_CTRL); val |= ELBI_SYS_CTRL_LT_ENABLE; - writel(val, pcie->elbi + ELBI_SYS_CTRL); + writel(val, pci->elbi_base + ELBI_SYS_CTRL); } static int qcom_pcie_get_resources_2_1_0(struct qcom_pcie *pcie) @@ -617,6 +641,18 @@ static int qcom_pcie_post_init_1_0_0(struct qcom_pcie *pcie) return 0; } +static int qcom_pcie_assert_perst(struct dw_pcie *pci, bool assert) +{ + struct qcom_pcie *pcie = to_qcom_pcie(pci); + + if (assert) + qcom_ep_reset_assert(pcie); + else + qcom_ep_reset_deassert(pcie); + + return 0; +} + static void qcom_pcie_2_3_2_ltssm_enable(struct qcom_pcie *pcie) { u32 val; @@ -988,6 +1024,8 @@ static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie) val &= ~REQ_NOT_ENTR_L1; writel(val, pcie->parf + PARF_PM_CTRL); + pci->l1ss_support = true; + val = readl(pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2); val |= EN; writel(val, pcie->parf + PARF_AXI_MSTR_WR_ADDR_HALT_V2); @@ -1006,8 +1044,8 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie) const struct qcom_pcie_cfg *pcie_cfg = pcie->cfg; if (pcie_cfg->override_no_snoop) - writel(WR_NO_SNOOP_OVERIDE_EN | RD_NO_SNOOP_OVERIDE_EN, - pcie->parf + PARF_NO_SNOOP_OVERIDE); + writel(WR_NO_SNOOP_OVERRIDE_EN | RD_NO_SNOOP_OVERRIDE_EN, + pcie->parf + PARF_NO_SNOOP_OVERRIDE); qcom_pcie_clear_aspm_l0s(pcie->pci); qcom_pcie_clear_hpc(pcie->pci); @@ -1220,12 +1258,40 @@ static int qcom_pcie_post_init_2_9_0(struct qcom_pcie *pcie) return 0; } -static int qcom_pcie_link_up(struct dw_pcie *pci) +static bool 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); + return val & PCI_EXP_LNKSTA_DLLLA; +} + +static void qcom_pcie_phy_power_off(struct qcom_pcie *pcie) +{ + struct qcom_pcie_port *port; + + list_for_each_entry(port, &pcie->ports, list) + phy_power_off(port->phy); +} + +static int qcom_pcie_phy_power_on(struct qcom_pcie *pcie) +{ + struct qcom_pcie_port *port; + int ret; + + list_for_each_entry(port, &pcie->ports, list) { + ret = phy_set_mode_ext(port->phy, PHY_MODE_PCIE, PHY_MODE_PCIE_RC); + if (ret) + return ret; + + ret = phy_power_on(port->phy); + if (ret) { + qcom_pcie_phy_power_off(pcie); + return ret; + } + } + + return 0; } static int qcom_pcie_host_init(struct dw_pcie_rp *pp) @@ -1240,11 +1306,7 @@ static int qcom_pcie_host_init(struct dw_pcie_rp *pp) if (ret) return ret; - ret = phy_set_mode_ext(pcie->phy, PHY_MODE_PCIE, PHY_MODE_PCIE_RC); - if (ret) - goto err_deinit; - - ret = phy_power_on(pcie->phy); + ret = qcom_pcie_phy_power_on(pcie); if (ret) goto err_deinit; @@ -1267,7 +1329,7 @@ static int qcom_pcie_host_init(struct dw_pcie_rp *pp) err_assert_reset: qcom_ep_reset_assert(pcie); err_disable_phy: - phy_power_off(pcie->phy); + qcom_pcie_phy_power_off(pcie); err_deinit: pcie->cfg->ops->deinit(pcie); @@ -1280,7 +1342,7 @@ static void qcom_pcie_host_deinit(struct dw_pcie_rp *pp) struct qcom_pcie *pcie = to_qcom_pcie(pci); qcom_ep_reset_assert(pcie); - phy_power_off(pcie->phy); + qcom_pcie_phy_power_off(pcie); pcie->cfg->ops->deinit(pcie); } @@ -1364,6 +1426,16 @@ static const struct qcom_pcie_ops ops_1_9_0 = { .config_sid = qcom_pcie_config_sid_1_9_0, }; +/* Qcom IP rev.: 1.21.0 Synopsys IP rev.: 5.60a */ +static const struct qcom_pcie_ops ops_1_21_0 = { + .get_resources = qcom_pcie_get_resources_2_7_0, + .init = qcom_pcie_init_2_7_0, + .post_init = qcom_pcie_post_init_2_7_0, + .host_post_init = qcom_pcie_host_post_init_2_7_0, + .deinit = qcom_pcie_deinit_2_7_0, + .ltssm_enable = qcom_pcie_2_3_2_ltssm_enable, +}; + /* 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, @@ -1411,13 +1483,18 @@ static const struct qcom_pcie_cfg cfg_2_9_0 = { }; static const struct qcom_pcie_cfg cfg_sc8280xp = { - .ops = &ops_1_9_0, + .ops = &ops_1_21_0, .no_l0s = true, }; +static const struct qcom_pcie_cfg cfg_fw_managed = { + .firmware_managed = true, +}; + static const struct dw_pcie_ops dw_pcie_ops = { .link_up = qcom_pcie_link_up, .start_link = qcom_pcie_start_link, + .assert_perst = qcom_pcie_assert_perst, }; static int qcom_pcie_icc_init(struct qcom_pcie *pcie) @@ -1467,6 +1544,7 @@ static void qcom_pcie_icc_opp_update(struct qcom_pcie *pcie) { u32 offset, status, width, speed; struct dw_pcie *pci = pcie->pci; + struct dev_pm_opp_key key = {}; unsigned long freq_kbps; struct dev_pm_opp *opp; int ret, freq_mbps; @@ -1494,8 +1572,20 @@ static void qcom_pcie_icc_opp_update(struct qcom_pcie *pcie) return; freq_kbps = freq_mbps * KILO; - opp = dev_pm_opp_find_freq_exact(pci->dev, freq_kbps * width, - true); + opp = dev_pm_opp_find_level_exact(pci->dev, speed); + if (IS_ERR(opp)) { + /* opp-level is not defined use only frequency */ + opp = dev_pm_opp_find_freq_exact(pci->dev, freq_kbps * width, + true); + } else { + /* put opp-level OPP */ + dev_pm_opp_put(opp); + + key.freq = freq_kbps * width; + key.level = speed; + key.bw = 0; + opp = dev_pm_opp_find_key_exact(pci->dev, &key, true); + } if (!IS_ERR(opp)) { ret = dev_pm_opp_set_opp(pci->dev, opp); if (ret) @@ -1553,11 +1643,14 @@ static irqreturn_t qcom_pcie_global_irq_thread(int irq, void *data) writel_relaxed(status, pcie->parf + PARF_INT_ALL_CLEAR); if (FIELD_GET(PARF_INT_ALL_LINK_UP, status)) { + msleep(PCIE_RESET_CONFIG_WAIT_MS); dev_dbg(dev, "Received Link up event. Starting enumeration!\n"); /* Rescan the bus to enumerate endpoint devices */ pci_lock_rescan_remove(); pci_rescan_bus(pp->bridge->bus); pci_unlock_rescan_remove(); + + qcom_pcie_icc_opp_update(pcie); } else { dev_WARN_ONCE(dev, 1, "Received unknown event. INT_STATUS: 0x%08x\n", status); @@ -1566,10 +1659,144 @@ static irqreturn_t qcom_pcie_global_irq_thread(int irq, void *data) return IRQ_HANDLED; } +static void qcom_pci_free_msi(void *ptr) +{ + struct dw_pcie_rp *pp = (struct dw_pcie_rp *)ptr; + + if (pp && pp->has_msi_ctrl) + dw_pcie_free_msi(pp); +} + +static int qcom_pcie_ecam_host_init(struct pci_config_window *cfg) +{ + struct device *dev = cfg->parent; + struct dw_pcie_rp *pp; + struct dw_pcie *pci; + int ret; + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) + return -ENOMEM; + + pci->dev = dev; + pp = &pci->pp; + pci->dbi_base = cfg->win; + pp->num_vectors = MSI_DEF_NUM_VECTORS; + + ret = dw_pcie_msi_host_init(pp); + if (ret) + return ret; + + pp->has_msi_ctrl = true; + dw_pcie_msi_init(pp); + + return devm_add_action_or_reset(dev, qcom_pci_free_msi, pp); +} + +static const struct pci_ecam_ops pci_qcom_ecam_ops = { + .init = qcom_pcie_ecam_host_init, + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } +}; + +static int qcom_pcie_parse_port(struct qcom_pcie *pcie, struct device_node *node) +{ + struct device *dev = pcie->pci->dev; + struct qcom_pcie_port *port; + struct gpio_desc *reset; + struct phy *phy; + int ret; + + reset = devm_fwnode_gpiod_get(dev, of_fwnode_handle(node), + "reset", GPIOD_OUT_HIGH, "PERST#"); + if (IS_ERR(reset)) + return PTR_ERR(reset); + + phy = devm_of_phy_get(dev, node, NULL); + if (IS_ERR(phy)) + return PTR_ERR(phy); + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + ret = phy_init(phy); + if (ret) + return ret; + + port->reset = reset; + port->phy = phy; + INIT_LIST_HEAD(&port->list); + list_add_tail(&port->list, &pcie->ports); + + return 0; +} + +static int qcom_pcie_parse_ports(struct qcom_pcie *pcie) +{ + struct device *dev = pcie->pci->dev; + struct qcom_pcie_port *port, *tmp; + int ret = -ENOENT; + + for_each_available_child_of_node_scoped(dev->of_node, of_port) { + if (!of_node_is_type(of_port, "pci")) + continue; + ret = qcom_pcie_parse_port(pcie, of_port); + if (ret) + goto err_port_del; + } + + return ret; + +err_port_del: + list_for_each_entry_safe(port, tmp, &pcie->ports, list) { + phy_exit(port->phy); + list_del(&port->list); + } + + return ret; +} + +static int qcom_pcie_parse_legacy_binding(struct qcom_pcie *pcie) +{ + struct device *dev = pcie->pci->dev; + struct qcom_pcie_port *port; + struct gpio_desc *reset; + struct phy *phy; + int ret; + + phy = devm_phy_optional_get(dev, "pciephy"); + if (IS_ERR(phy)) + return PTR_ERR(phy); + + reset = devm_gpiod_get_optional(dev, "perst", GPIOD_OUT_HIGH); + if (IS_ERR(reset)) + return PTR_ERR(reset); + + ret = phy_init(phy); + if (ret) + return ret; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + port->reset = reset; + port->phy = phy; + INIT_LIST_HEAD(&port->list); + list_add_tail(&port->list, &pcie->ports); + + return 0; +} + static int qcom_pcie_probe(struct platform_device *pdev) { const struct qcom_pcie_cfg *pcie_cfg; unsigned long max_freq = ULONG_MAX; + struct qcom_pcie_port *port, *tmp; struct device *dev = &pdev->dev; struct dev_pm_opp *opp; struct qcom_pcie *pcie; @@ -1580,24 +1807,64 @@ static int qcom_pcie_probe(struct platform_device *pdev) char *name; pcie_cfg = of_device_get_match_data(dev); - if (!pcie_cfg || !pcie_cfg->ops) { - dev_err(dev, "Invalid platform data\n"); - return -EINVAL; + if (!pcie_cfg) { + dev_err(dev, "No platform data\n"); + return -ENODATA; } - pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); - if (!pcie) - return -ENOMEM; - - pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); - if (!pci) - return -ENOMEM; + if (!pcie_cfg->firmware_managed && !pcie_cfg->ops) { + dev_err(dev, "No platform ops\n"); + return -ENODATA; + } pm_runtime_enable(dev); ret = pm_runtime_get_sync(dev); if (ret < 0) goto err_pm_runtime_put; + if (pcie_cfg->firmware_managed) { + struct pci_host_bridge *bridge; + struct pci_config_window *cfg; + + bridge = devm_pci_alloc_host_bridge(dev, 0); + if (!bridge) { + ret = -ENOMEM; + goto err_pm_runtime_put; + } + + /* Parse and map our ECAM configuration space area */ + cfg = pci_host_common_ecam_create(dev, bridge, + &pci_qcom_ecam_ops); + if (IS_ERR(cfg)) { + ret = PTR_ERR(cfg); + goto err_pm_runtime_put; + } + + bridge->sysdata = cfg; + bridge->ops = (struct pci_ops *)&pci_qcom_ecam_ops.pci_ops; + bridge->msi_domain = true; + + ret = pci_host_probe(bridge); + if (ret) + goto err_pm_runtime_put; + + return 0; + } + + pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); + if (!pcie) { + ret = -ENOMEM; + goto err_pm_runtime_put; + } + + pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL); + if (!pci) { + ret = -ENOMEM; + goto err_pm_runtime_put; + } + + INIT_LIST_HEAD(&pcie->ports); + pci->dev = dev; pci->ops = &dw_pcie_ops; pp = &pci->pp; @@ -1606,24 +1873,12 @@ static int qcom_pcie_probe(struct platform_device *pdev) 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; - } - /* MHI region is optional */ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "mhi"); if (res) { @@ -1634,12 +1889,6 @@ static int qcom_pcie_probe(struct platform_device *pdev) } } - pcie->phy = devm_phy_optional_get(dev, "pciephy"); - if (IS_ERR(pcie->phy)) { - ret = PTR_ERR(pcie->phy); - goto err_pm_runtime_put; - } - /* OPP table is optional */ ret = devm_pm_opp_of_add_table(dev); if (ret && ret != -ENODEV) { @@ -1686,12 +1935,30 @@ static int qcom_pcie_probe(struct platform_device *pdev) pp->ops = &qcom_pcie_dw_ops; - ret = phy_init(pcie->phy); - if (ret) - goto err_pm_runtime_put; + ret = qcom_pcie_parse_ports(pcie); + if (ret) { + if (ret != -ENOENT) { + dev_err_probe(pci->dev, ret, + "Failed to parse Root Port: %d\n", ret); + goto err_pm_runtime_put; + } + + /* + * In the case of properties not populated in Root Port node, + * fallback to the legacy method of parsing the Host Bridge + * node. This is to maintain DT backwards compatibility. + */ + ret = qcom_pcie_parse_legacy_binding(pcie); + if (ret) + goto err_pm_runtime_put; + } platform_set_drvdata(pdev, pcie); + irq = platform_get_irq_byname_optional(pdev, "global"); + if (irq > 0) + pp->use_linkup_irq = true; + ret = dw_pcie_host_init(pp); if (ret) { dev_err(dev, "cannot initialize host\n"); @@ -1705,7 +1972,6 @@ static int qcom_pcie_probe(struct platform_device *pdev) goto err_host_deinit; } - irq = platform_get_irq_byname_optional(pdev, "global"); if (irq > 0) { ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, qcom_pcie_global_irq_thread, @@ -1716,7 +1982,8 @@ static int qcom_pcie_probe(struct platform_device *pdev) goto err_host_deinit; } - writel_relaxed(PARF_INT_ALL_LINK_UP, pcie->parf + PARF_INT_ALL_MASK); + writel_relaxed(PARF_INT_ALL_LINK_UP | PARF_INT_MSI_DEV_0_7, + pcie->parf + PARF_INT_ALL_MASK); } qcom_pcie_icc_opp_update(pcie); @@ -1729,7 +1996,10 @@ static int qcom_pcie_probe(struct platform_device *pdev) err_host_deinit: dw_pcie_host_deinit(pp); err_phy_exit: - phy_exit(pcie->phy); + list_for_each_entry_safe(port, tmp, &pcie->ports, list) { + phy_exit(port->phy); + list_del(&port->list); + } err_pm_runtime_put: pm_runtime_put(dev); pm_runtime_disable(dev); @@ -1739,9 +2009,13 @@ err_pm_runtime_put: static int qcom_pcie_suspend_noirq(struct device *dev) { - struct qcom_pcie *pcie = dev_get_drvdata(dev); + struct qcom_pcie *pcie; int ret = 0; + pcie = dev_get_drvdata(dev); + if (!pcie) + return 0; + /* * Set minimum bandwidth required to keep data path functional during * suspend. @@ -1795,9 +2069,13 @@ static int qcom_pcie_suspend_noirq(struct device *dev) static int qcom_pcie_resume_noirq(struct device *dev) { - struct qcom_pcie *pcie = dev_get_drvdata(dev); + struct qcom_pcie *pcie; int ret; + pcie = dev_get_drvdata(dev); + if (!pcie) + return 0; + if (pm_suspend_target_state != PM_SUSPEND_MEM) { ret = icc_enable(pcie->icc_cpu); if (ret) { @@ -1823,13 +2101,16 @@ 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-ipq5018", .data = &cfg_2_9_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-ipq8074-gen3", .data = &cfg_2_9_0 }, + { .compatible = "qcom,pcie-ipq9574", .data = &cfg_2_9_0 }, { .compatible = "qcom,pcie-msm8996", .data = &cfg_2_3_2 }, { .compatible = "qcom,pcie-qcs404", .data = &cfg_2_4_0 }, + { .compatible = "qcom,pcie-sa8255p", .data = &cfg_fw_managed }, { .compatible = "qcom,pcie-sa8540p", .data = &cfg_sc8280xp }, { .compatible = "qcom,pcie-sa8775p", .data = &cfg_1_34_0}, { .compatible = "qcom,pcie-sc7280", .data = &cfg_1_9_0 }, @@ -1843,7 +2124,7 @@ static const struct of_device_id qcom_pcie_match[] = { { .compatible = "qcom,pcie-sm8450-pcie0", .data = &cfg_1_9_0 }, { .compatible = "qcom,pcie-sm8450-pcie1", .data = &cfg_1_9_0 }, { .compatible = "qcom,pcie-sm8550", .data = &cfg_1_9_0 }, - { .compatible = "qcom,pcie-x1e80100", .data = &cfg_1_9_0 }, + { .compatible = "qcom,pcie-x1e80100", .data = &cfg_sc8280xp }, { } }; diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c index 3a5511c3f7d9..80778917d2dd 100644 --- a/drivers/pci/controller/dwc/pcie-rcar-gen4.c +++ b/drivers/pci/controller/dwc/pcie-rcar-gen4.c @@ -87,7 +87,7 @@ struct rcar_gen4_pcie { #define to_rcar_gen4_pcie(_dw) container_of(_dw, struct rcar_gen4_pcie, dw) /* Common */ -static int rcar_gen4_pcie_link_up(struct dw_pcie *dw) +static bool rcar_gen4_pcie_link_up(struct dw_pcie *dw) { struct rcar_gen4_pcie *rcar = to_rcar_gen4_pcie(dw); u32 val, mask; @@ -182,8 +182,17 @@ static int rcar_gen4_pcie_common_init(struct rcar_gen4_pcie *rcar) return ret; } - if (!reset_control_status(dw->core_rsts[DW_PCIE_PWR_RST].rstc)) + if (!reset_control_status(dw->core_rsts[DW_PCIE_PWR_RST].rstc)) { reset_control_assert(dw->core_rsts[DW_PCIE_PWR_RST].rstc); + /* + * R-Car V4H Reference Manual R19UH0186EJ0130 Rev.1.30 Apr. + * 21, 2025 page 585 Figure 9.3.2 Software Reset flow (B) + * indicates that for peripherals in HSC domain, after + * reset has been asserted by writing a matching reset bit + * into register SRCR, it is mandatory to wait 1ms. + */ + fsleep(1000); + } val = readl(rcar->base + PCIEMSR0); if (rcar->drvdata->mode == DW_PCIE_RC_TYPE) { @@ -204,6 +213,19 @@ static int rcar_gen4_pcie_common_init(struct rcar_gen4_pcie *rcar) if (ret) goto err_unprepare; + /* + * Assure the reset is latched and the core is ready for DBI access. + * On R-Car V4H, the PCIe reset is asynchronous and does not take + * effect immediately, but needs a short time to complete. In case + * DBI access happens in that short time, that access generates an + * SError. To make sure that condition can never happen, read back the + * state of the reset, which should turn the asynchronous reset into + * synchronous one, and wait a little over 1ms to add additional + * safety margin. + */ + reset_control_status(dw->core_rsts[DW_PCIE_PWR_RST].rstc); + fsleep(1000); + if (rcar->drvdata->additional_common_init) rcar->drvdata->additional_common_init(rcar); @@ -398,11 +420,10 @@ static int rcar_gen4_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, } static const struct pci_epc_features rcar_gen4_pcie_epc_features = { - .linkup_notifier = false, .msi_capable = true, - .msix_capable = false, .bar[BAR_1] = { .type = BAR_RESERVED, }, .bar[BAR_3] = { .type = BAR_RESERVED, }, + .bar[BAR_4] = { .type = BAR_FIXED, .fixed_size = 256 }, .bar[BAR_5] = { .type = BAR_RESERVED, }, .align = SZ_1M, }; @@ -700,7 +721,7 @@ static int rcar_gen4_pcie_ltssm_control(struct rcar_gen4_pcie *rcar, bool enable rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x148, GENMASK(23, 22), BIT(22)); rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x148, GENMASK(18, 16), GENMASK(17, 16)); rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x148, GENMASK(7, 6), BIT(6)); - rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x148, GENMASK(2, 0), GENMASK(11, 0)); + rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x148, GENMASK(2, 0), GENMASK(1, 0)); rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x1d4, GENMASK(16, 15), GENMASK(16, 15)); rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x514, BIT(26), BIT(26)); rcar_gen4_pcie_phy_reg_update_bits(rcar, 0x0f8, BIT(16), 0); @@ -710,7 +731,7 @@ static int rcar_gen4_pcie_ltssm_control(struct rcar_gen4_pcie *rcar, bool enable val &= ~APP_HOLD_PHY_RST; writel(val, rcar->base + PCIERSTCTRL1); - ret = readl_poll_timeout(rcar->phy_base + 0x0f8, val, !(val & BIT(18)), 100, 10000); + ret = readl_poll_timeout(rcar->phy_base + 0x0f8, val, val & BIT(18), 100, 10000); if (ret < 0) return ret; @@ -775,7 +796,7 @@ static struct platform_driver rcar_gen4_pcie_driver = { .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, .probe = rcar_gen4_pcie_probe, - .remove_new = rcar_gen4_pcie_remove, + .remove = rcar_gen4_pcie_remove, }; module_platform_driver(rcar_gen4_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-sophgo.c b/drivers/pci/controller/dwc/pcie-sophgo.c new file mode 100644 index 000000000000..ad4baaa34ffa --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-sophgo.c @@ -0,0 +1,257 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Sophgo DesignWare based PCIe host controller driver + */ + +#include <linux/bits.h> +#include <linux/clk.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqdomain.h> +#include <linux/module.h> +#include <linux/property.h> +#include <linux/platform_device.h> + +#include "pcie-designware.h" + +#define to_sophgo_pcie(x) dev_get_drvdata((x)->dev) + +#define PCIE_INT_SIGNAL 0xc48 +#define PCIE_INT_EN 0xca0 + +#define PCIE_INT_SIGNAL_INTX GENMASK(8, 5) + +#define PCIE_INT_EN_INTX GENMASK(4, 1) +#define PCIE_INT_EN_INT_MSI BIT(5) + +struct sophgo_pcie { + struct dw_pcie pci; + void __iomem *app_base; + struct clk_bulk_data *clks; + unsigned int clk_cnt; + struct irq_domain *irq_domain; +}; + +static int sophgo_pcie_readl_app(struct sophgo_pcie *sophgo, u32 reg) +{ + return readl_relaxed(sophgo->app_base + reg); +} + +static void sophgo_pcie_writel_app(struct sophgo_pcie *sophgo, u32 val, u32 reg) +{ + writel_relaxed(val, sophgo->app_base + reg); +} + +static void sophgo_pcie_intx_handler(struct irq_desc *desc) +{ + struct dw_pcie_rp *pp = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct sophgo_pcie *sophgo = to_sophgo_pcie(pci); + unsigned long hwirq, reg; + + chained_irq_enter(chip, desc); + + reg = sophgo_pcie_readl_app(sophgo, PCIE_INT_SIGNAL); + reg = FIELD_GET(PCIE_INT_SIGNAL_INTX, reg); + + for_each_set_bit(hwirq, ®, PCI_NUM_INTX) + generic_handle_domain_irq(sophgo->irq_domain, hwirq); + + chained_irq_exit(chip, desc); +} + +static void sophgo_intx_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 sophgo_pcie *sophgo = to_sophgo_pcie(pci); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pp->lock, flags); + + val = sophgo_pcie_readl_app(sophgo, PCIE_INT_EN); + val &= ~FIELD_PREP(PCIE_INT_EN_INTX, BIT(d->hwirq)); + sophgo_pcie_writel_app(sophgo, val, PCIE_INT_EN); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +}; + +static void sophgo_intx_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 sophgo_pcie *sophgo = to_sophgo_pcie(pci); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pp->lock, flags); + + val = sophgo_pcie_readl_app(sophgo, PCIE_INT_EN); + val |= FIELD_PREP(PCIE_INT_EN_INTX, BIT(d->hwirq)); + sophgo_pcie_writel_app(sophgo, val, PCIE_INT_EN); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +}; + +static struct irq_chip sophgo_intx_irq_chip = { + .name = "INTx", + .irq_mask = sophgo_intx_irq_mask, + .irq_unmask = sophgo_intx_irq_unmask, +}; + +static int sophgo_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &sophgo_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 = sophgo_pcie_intx_map, +}; + +static int sophgo_pcie_init_irq_domain(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct sophgo_pcie *sophgo = to_sophgo_pcie(pci); + struct device *dev = sophgo->pci.dev; + struct fwnode_handle *intc; + int irq; + + intc = device_get_named_child_node(dev, "interrupt-controller"); + if (!intc) { + dev_err(dev, "missing child interrupt-controller node\n"); + return -ENODEV; + } + + irq = fwnode_irq_get(intc, 0); + if (irq < 0) { + dev_err(dev, "failed to get INTx irq number\n"); + fwnode_handle_put(intc); + return irq; + } + + sophgo->irq_domain = irq_domain_create_linear(intc, PCI_NUM_INTX, + &intx_domain_ops, pp); + fwnode_handle_put(intc); + if (!sophgo->irq_domain) { + dev_err(dev, "failed to get a INTx irq domain\n"); + return -EINVAL; + } + + return irq; +} + +static void sophgo_pcie_msi_enable(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct sophgo_pcie *sophgo = to_sophgo_pcie(pci); + unsigned long flags; + u32 val; + + raw_spin_lock_irqsave(&pp->lock, flags); + + val = sophgo_pcie_readl_app(sophgo, PCIE_INT_EN); + val |= PCIE_INT_EN_INT_MSI; + sophgo_pcie_writel_app(sophgo, val, PCIE_INT_EN); + + raw_spin_unlock_irqrestore(&pp->lock, flags); +} + +static int sophgo_pcie_host_init(struct dw_pcie_rp *pp) +{ + int irq; + + irq = sophgo_pcie_init_irq_domain(pp); + if (irq < 0) + return irq; + + irq_set_chained_handler_and_data(irq, sophgo_pcie_intx_handler, pp); + + sophgo_pcie_msi_enable(pp); + + return 0; +} + +static const struct dw_pcie_host_ops sophgo_pcie_host_ops = { + .init = sophgo_pcie_host_init, +}; + +static int sophgo_pcie_clk_init(struct sophgo_pcie *sophgo) +{ + struct device *dev = sophgo->pci.dev; + int ret; + + ret = devm_clk_bulk_get_all_enabled(dev, &sophgo->clks); + if (ret < 0) + return dev_err_probe(dev, ret, "failed to get clocks\n"); + + sophgo->clk_cnt = ret; + + return 0; +} + +static int sophgo_pcie_resource_get(struct platform_device *pdev, + struct sophgo_pcie *sophgo) +{ + sophgo->app_base = devm_platform_ioremap_resource_byname(pdev, "app"); + if (IS_ERR(sophgo->app_base)) + return dev_err_probe(&pdev->dev, PTR_ERR(sophgo->app_base), + "failed to map app registers\n"); + + return 0; +} + +static int sophgo_pcie_configure_rc(struct sophgo_pcie *sophgo) +{ + struct dw_pcie_rp *pp; + + pp = &sophgo->pci.pp; + pp->ops = &sophgo_pcie_host_ops; + + return dw_pcie_host_init(pp); +} + +static int sophgo_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct sophgo_pcie *sophgo; + int ret; + + sophgo = devm_kzalloc(dev, sizeof(*sophgo), GFP_KERNEL); + if (!sophgo) + return -ENOMEM; + + platform_set_drvdata(pdev, sophgo); + + sophgo->pci.dev = dev; + + ret = sophgo_pcie_resource_get(pdev, sophgo); + if (ret) + return ret; + + ret = sophgo_pcie_clk_init(sophgo); + if (ret) + return ret; + + return sophgo_pcie_configure_rc(sophgo); +} + +static const struct of_device_id sophgo_pcie_of_match[] = { + { .compatible = "sophgo,sg2044-pcie" }, + { } +}; +MODULE_DEVICE_TABLE(of, sophgo_pcie_of_match); + +static struct platform_driver sophgo_pcie_driver = { + .driver = { + .name = "sophgo-pcie", + .of_match_table = sophgo_pcie_of_match, + .suppress_bind_attrs = true, + }, + .probe = sophgo_pcie_probe, +}; +builtin_platform_driver(sophgo_pcie_driver); diff --git a/drivers/pci/controller/dwc/pcie-spacemit-k1.c b/drivers/pci/controller/dwc/pcie-spacemit-k1.c new file mode 100644 index 000000000000..be20a520255b --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-spacemit-k1.c @@ -0,0 +1,357 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * SpacemiT K1 PCIe host driver + * + * Copyright (C) 2025 by RISCstar Solutions Corporation. All rights reserved. + * Copyright (c) 2023, spacemit Corporation. + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/gfp.h> +#include <linux/mfd/syscon.h> +#include <linux/mod_devicetable.h> +#include <linux/phy/phy.h> +#include <linux/platform_device.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <linux/types.h> + +#include "pcie-designware.h" + +#define PCI_VENDOR_ID_SPACEMIT 0x201f +#define PCI_DEVICE_ID_SPACEMIT_K1 0x0001 + +/* Offsets and field definitions for link management registers */ +#define K1_PHY_AHB_IRQ_EN 0x0000 +#define PCIE_INTERRUPT_EN BIT(0) + +#define K1_PHY_AHB_LINK_STS 0x0004 +#define SMLH_LINK_UP BIT(1) +#define RDLH_LINK_UP BIT(12) + +#define INTR_ENABLE 0x0014 +#define MSI_CTRL_INT BIT(11) + +/* Some controls require APMU regmap access */ +#define SYSCON_APMU "spacemit,apmu" + +/* Offsets and field definitions for APMU registers */ +#define PCIE_CLK_RESET_CONTROL 0x0000 +#define LTSSM_EN BIT(6) +#define PCIE_AUX_PWR_DET BIT(9) +#define PCIE_RC_PERST BIT(12) /* 1: assert PERST# */ +#define APP_HOLD_PHY_RST BIT(30) +#define DEVICE_TYPE_RC BIT(31) /* 0: endpoint; 1: RC */ + +#define PCIE_CONTROL_LOGIC 0x0004 +#define PCIE_SOFT_RESET BIT(0) + +struct k1_pcie { + struct dw_pcie pci; + struct phy *phy; + void __iomem *link; + struct regmap *pmu; /* Errors ignored; MMIO-backed regmap */ + u32 pmu_off; +}; + +#define to_k1_pcie(dw_pcie) \ + platform_get_drvdata(to_platform_device((dw_pcie)->dev)) + +static void k1_pcie_toggle_soft_reset(struct k1_pcie *k1) +{ + u32 offset; + u32 val; + + /* + * Write, then read back to guarantee it has reached the device + * before we start the delay. + */ + offset = k1->pmu_off + PCIE_CONTROL_LOGIC; + regmap_set_bits(k1->pmu, offset, PCIE_SOFT_RESET); + regmap_read(k1->pmu, offset, &val); + + mdelay(2); + + regmap_clear_bits(k1->pmu, offset, PCIE_SOFT_RESET); +} + +/* Enable app clocks, deassert resets */ +static int k1_pcie_enable_resources(struct k1_pcie *k1) +{ + struct dw_pcie *pci = &k1->pci; + int ret; + + ret = clk_bulk_prepare_enable(ARRAY_SIZE(pci->app_clks), pci->app_clks); + if (ret) + return ret; + + ret = reset_control_bulk_deassert(ARRAY_SIZE(pci->app_rsts), + pci->app_rsts); + if (ret) + goto err_disable_clks; + + return 0; + +err_disable_clks: + clk_bulk_disable_unprepare(ARRAY_SIZE(pci->app_clks), pci->app_clks); + + return ret; +} + +/* Assert resets, disable app clocks */ +static void k1_pcie_disable_resources(struct k1_pcie *k1) +{ + struct dw_pcie *pci = &k1->pci; + + reset_control_bulk_assert(ARRAY_SIZE(pci->app_rsts), pci->app_rsts); + clk_bulk_disable_unprepare(ARRAY_SIZE(pci->app_clks), pci->app_clks); +} + +/* FIXME: Disable ASPM L1 to avoid errors reported on some NVMe drives */ +static void k1_pcie_disable_aspm_l1(struct k1_pcie *k1) +{ + struct dw_pcie *pci = &k1->pci; + u8 offset; + u32 val; + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + offset += PCI_EXP_LNKCAP; + + dw_pcie_dbi_ro_wr_en(pci); + val = dw_pcie_readl_dbi(pci, offset); + val &= ~PCI_EXP_LNKCAP_ASPM_L1; + dw_pcie_writel_dbi(pci, offset, val); + dw_pcie_dbi_ro_wr_dis(pci); +} + +static int k1_pcie_init(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct k1_pcie *k1 = to_k1_pcie(pci); + u32 reset_ctrl; + u32 val; + int ret; + + k1_pcie_toggle_soft_reset(k1); + + ret = k1_pcie_enable_resources(k1); + if (ret) + return ret; + + /* Set the PCI vendor and device ID */ + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writew_dbi(pci, PCI_VENDOR_ID, PCI_VENDOR_ID_SPACEMIT); + dw_pcie_writew_dbi(pci, PCI_DEVICE_ID, PCI_DEVICE_ID_SPACEMIT_K1); + dw_pcie_dbi_ro_wr_dis(pci); + + /* + * Start by asserting fundamental reset (drive PERST# low). The + * PCI CEM spec says that PERST# should be deasserted at least + * 100ms after the power becomes stable, so we'll insert that + * delay first. Write, then read it back to guarantee the write + * reaches the device before we start the delay. + */ + reset_ctrl = k1->pmu_off + PCIE_CLK_RESET_CONTROL; + regmap_set_bits(k1->pmu, reset_ctrl, PCIE_RC_PERST); + regmap_read(k1->pmu, reset_ctrl, &val); + mdelay(PCIE_T_PVPERL_MS); + + /* + * Put the controller in root complex mode, and indicate that + * Vaux (3.3v) is present. + */ + regmap_set_bits(k1->pmu, reset_ctrl, DEVICE_TYPE_RC | PCIE_AUX_PWR_DET); + + ret = phy_init(k1->phy); + if (ret) { + k1_pcie_disable_resources(k1); + + return ret; + } + + /* Deassert fundamental reset (drive PERST# high) */ + regmap_clear_bits(k1->pmu, reset_ctrl, PCIE_RC_PERST); + + /* Finally, as a workaround, disable ASPM L1 */ + k1_pcie_disable_aspm_l1(k1); + + return 0; +} + +static void k1_pcie_deinit(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + struct k1_pcie *k1 = to_k1_pcie(pci); + + /* Assert fundamental reset (drive PERST# low) */ + regmap_set_bits(k1->pmu, k1->pmu_off + PCIE_CLK_RESET_CONTROL, + PCIE_RC_PERST); + + phy_exit(k1->phy); + + k1_pcie_disable_resources(k1); +} + +static const struct dw_pcie_host_ops k1_pcie_host_ops = { + .init = k1_pcie_init, + .deinit = k1_pcie_deinit, +}; + +static bool k1_pcie_link_up(struct dw_pcie *pci) +{ + struct k1_pcie *k1 = to_k1_pcie(pci); + u32 val; + + val = readl_relaxed(k1->link + K1_PHY_AHB_LINK_STS); + + return (val & RDLH_LINK_UP) && (val & SMLH_LINK_UP); +} + +static int k1_pcie_start_link(struct dw_pcie *pci) +{ + struct k1_pcie *k1 = to_k1_pcie(pci); + u32 val; + + /* Stop holding the PHY in reset, and enable link training */ + regmap_update_bits(k1->pmu, k1->pmu_off + PCIE_CLK_RESET_CONTROL, + APP_HOLD_PHY_RST | LTSSM_EN, LTSSM_EN); + + /* Enable the MSI interrupt */ + writel_relaxed(MSI_CTRL_INT, k1->link + INTR_ENABLE); + + /* Top-level interrupt enable */ + val = readl_relaxed(k1->link + K1_PHY_AHB_IRQ_EN); + val |= PCIE_INTERRUPT_EN; + writel_relaxed(val, k1->link + K1_PHY_AHB_IRQ_EN); + + return 0; +} + +static void k1_pcie_stop_link(struct dw_pcie *pci) +{ + struct k1_pcie *k1 = to_k1_pcie(pci); + u32 val; + + /* Disable interrupts */ + val = readl_relaxed(k1->link + K1_PHY_AHB_IRQ_EN); + val &= ~PCIE_INTERRUPT_EN; + writel_relaxed(val, k1->link + K1_PHY_AHB_IRQ_EN); + + writel_relaxed(0, k1->link + INTR_ENABLE); + + /* Disable the link and hold the PHY in reset */ + regmap_update_bits(k1->pmu, k1->pmu_off + PCIE_CLK_RESET_CONTROL, + APP_HOLD_PHY_RST | LTSSM_EN, APP_HOLD_PHY_RST); +} + +static const struct dw_pcie_ops k1_pcie_ops = { + .link_up = k1_pcie_link_up, + .start_link = k1_pcie_start_link, + .stop_link = k1_pcie_stop_link, +}; + +static int k1_pcie_parse_port(struct k1_pcie *k1) +{ + struct device *dev = k1->pci.dev; + struct device_node *root_port; + struct phy *phy; + + /* We assume only one root port */ + root_port = of_get_next_available_child(dev_of_node(dev), NULL); + if (!root_port) + return -EINVAL; + + phy = devm_of_phy_get(dev, root_port, NULL); + + of_node_put(root_port); + + if (IS_ERR(phy)) + return PTR_ERR(phy); + + k1->phy = phy; + + return 0; +} + +static int k1_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct k1_pcie *k1; + int ret; + + k1 = devm_kzalloc(dev, sizeof(*k1), GFP_KERNEL); + if (!k1) + return -ENOMEM; + + k1->pmu = syscon_regmap_lookup_by_phandle_args(dev_of_node(dev), + SYSCON_APMU, 1, + &k1->pmu_off); + if (IS_ERR(k1->pmu)) + return dev_err_probe(dev, PTR_ERR(k1->pmu), + "failed to lookup PMU registers\n"); + + k1->link = devm_platform_ioremap_resource_byname(pdev, "link"); + if (IS_ERR(k1->link)) + return dev_err_probe(dev, PTR_ERR(k1->link), + "failed to map \"link\" registers\n"); + + k1->pci.dev = dev; + k1->pci.ops = &k1_pcie_ops; + k1->pci.pp.num_vectors = MAX_MSI_IRQS; + dw_pcie_cap_set(&k1->pci, REQ_RES); + + k1->pci.pp.ops = &k1_pcie_host_ops; + + /* Hold the PHY in reset until we start the link */ + regmap_set_bits(k1->pmu, k1->pmu_off + PCIE_CLK_RESET_CONTROL, + APP_HOLD_PHY_RST); + + ret = devm_regulator_get_enable(dev, "vpcie3v3"); + if (ret) + return dev_err_probe(dev, ret, + "failed to get \"vpcie3v3\" supply\n"); + + pm_runtime_set_active(dev); + pm_runtime_no_callbacks(dev); + devm_pm_runtime_enable(dev); + + platform_set_drvdata(pdev, k1); + + ret = k1_pcie_parse_port(k1); + if (ret) + return dev_err_probe(dev, ret, "failed to parse root port\n"); + + ret = dw_pcie_host_init(&k1->pci.pp); + if (ret) + return dev_err_probe(dev, ret, "failed to initialize host\n"); + + return 0; +} + +static void k1_pcie_remove(struct platform_device *pdev) +{ + struct k1_pcie *k1 = platform_get_drvdata(pdev); + + dw_pcie_host_deinit(&k1->pci.pp); +} + +static const struct of_device_id k1_pcie_of_match_table[] = { + { .compatible = "spacemit,k1-pcie", }, + { } +}; + +static struct platform_driver k1_pcie_driver = { + .probe = k1_pcie_probe, + .remove = k1_pcie_remove, + .driver = { + .name = "spacemit-k1-pcie", + .of_match_table = k1_pcie_of_match_table, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; +module_platform_driver(k1_pcie_driver); +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("SpacemiT K1 PCIe host driver"); diff --git a/drivers/pci/controller/dwc/pcie-spear13xx.c b/drivers/pci/controller/dwc/pcie-spear13xx.c index ff986ced56b2..01794a9d3ad2 100644 --- a/drivers/pci/controller/dwc/pcie-spear13xx.c +++ b/drivers/pci/controller/dwc/pcie-spear13xx.c @@ -110,15 +110,12 @@ static void spear13xx_pcie_enable_interrupts(struct spear13xx_pcie *spear13xx_pc MSI_CTRL_INT, &app_reg->int_mask); } -static int spear13xx_pcie_link_up(struct dw_pcie *pci) +static bool 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; + return readl(&app_reg->app_status_1) & XMLH_LINK_UP; } static int spear13xx_pcie_host_init(struct dw_pcie_rp *pp) diff --git a/drivers/pci/controller/dwc/pcie-stm32-ep.c b/drivers/pci/controller/dwc/pcie-stm32-ep.c new file mode 100644 index 000000000000..2cecf32d2b0f --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-stm32-ep.c @@ -0,0 +1,343 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * STMicroelectronics STM32MP25 PCIe endpoint driver. + * + * Copyright (C) 2025 STMicroelectronics + * Author: Christian Bruel <christian.bruel@foss.st.com> + */ + +#include <linux/clk.h> +#include <linux/gpio/consumer.h> +#include <linux/mfd/syscon.h> +#include <linux/of_platform.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 "pcie-designware.h" +#include "pcie-stm32.h" + +struct stm32_pcie { + struct dw_pcie pci; + struct regmap *regmap; + struct reset_control *rst; + struct phy *phy; + struct clk *clk; + struct gpio_desc *perst_gpio; + unsigned int perst_irq; +}; + +static void stm32_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 stm32_pcie_start_link(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + + enable_irq(stm32_pcie->perst_irq); + + return 0; +} + +static void stm32_pcie_stop_link(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + + disable_irq(stm32_pcie->perst_irq); +} + +static int stm32_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, + unsigned int type, u16 interrupt_num) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + + switch (type) { + case PCI_IRQ_INTX: + return dw_pcie_ep_raise_intx_irq(ep, func_no); + case PCI_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 const struct pci_epc_features stm32_pcie_epc_features = { + .msi_capable = true, + .align = SZ_64K, +}; + +static const struct pci_epc_features* +stm32_pcie_get_features(struct dw_pcie_ep *ep) +{ + return &stm32_pcie_epc_features; +} + +static const struct dw_pcie_ep_ops stm32_pcie_ep_ops = { + .init = stm32_pcie_ep_init, + .raise_irq = stm32_pcie_raise_irq, + .get_features = stm32_pcie_get_features, +}; + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = stm32_pcie_start_link, + .stop_link = stm32_pcie_stop_link, +}; + +static int stm32_pcie_enable_resources(struct stm32_pcie *stm32_pcie) +{ + int ret; + + ret = phy_init(stm32_pcie->phy); + if (ret) + return ret; + + ret = clk_prepare_enable(stm32_pcie->clk); + if (ret) + phy_exit(stm32_pcie->phy); + + return ret; +} + +static void stm32_pcie_disable_resources(struct stm32_pcie *stm32_pcie) +{ + clk_disable_unprepare(stm32_pcie->clk); + + phy_exit(stm32_pcie->phy); +} + +static void stm32_pcie_perst_assert(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + struct dw_pcie_ep *ep = &stm32_pcie->pci.ep; + struct device *dev = pci->dev; + + dev_dbg(dev, "PERST asserted by host\n"); + + regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_LTSSM_EN, 0); + + pci_epc_deinit_notify(ep->epc); + + stm32_pcie_disable_resources(stm32_pcie); + + pm_runtime_put_sync(dev); +} + +static void stm32_pcie_perst_deassert(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + struct device *dev = pci->dev; + struct dw_pcie_ep *ep = &pci->ep; + int ret; + + dev_dbg(dev, "PERST de-asserted by host\n"); + + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) { + dev_err(dev, "Failed to resume runtime PM: %d\n", ret); + return; + } + + ret = stm32_pcie_enable_resources(stm32_pcie); + if (ret) { + dev_err(dev, "Failed to enable resources: %d\n", ret); + goto err_pm_put_sync; + } + + /* + * Reprogram the configuration space registers here because the DBI + * registers were reset by the PHY RCC during phy_init(). + */ + ret = dw_pcie_ep_init_registers(ep); + if (ret) { + dev_err(dev, "Failed to complete initialization: %d\n", ret); + goto err_disable_resources; + } + + pci_epc_init_notify(ep->epc); + + /* Enable link training */ + regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_LTSSM_EN, + STM32MP25_PCIECR_LTSSM_EN); + + return; + +err_disable_resources: + stm32_pcie_disable_resources(stm32_pcie); + +err_pm_put_sync: + pm_runtime_put_sync(dev); +} + +static irqreturn_t stm32_pcie_ep_perst_irq_thread(int irq, void *data) +{ + struct stm32_pcie *stm32_pcie = data; + struct dw_pcie *pci = &stm32_pcie->pci; + u32 perst; + + perst = gpiod_get_value(stm32_pcie->perst_gpio); + if (perst) + stm32_pcie_perst_assert(pci); + else + stm32_pcie_perst_deassert(pci); + + irq_set_irq_type(gpiod_to_irq(stm32_pcie->perst_gpio), + (perst ? IRQF_TRIGGER_HIGH : IRQF_TRIGGER_LOW)); + + return IRQ_HANDLED; +} + +static int stm32_add_pcie_ep(struct stm32_pcie *stm32_pcie, + struct platform_device *pdev) +{ + struct dw_pcie_ep *ep = &stm32_pcie->pci.ep; + struct device *dev = &pdev->dev; + int ret; + + ret = regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_TYPE_MASK, + STM32MP25_PCIECR_EP); + if (ret) + return ret; + + reset_control_assert(stm32_pcie->rst); + reset_control_deassert(stm32_pcie->rst); + + ep->ops = &stm32_pcie_ep_ops; + + ep->page_size = stm32_pcie_epc_features.align; + + ret = dw_pcie_ep_init(ep); + if (ret) { + dev_err(dev, "Failed to initialize ep: %d\n", ret); + return ret; + } + + ret = stm32_pcie_enable_resources(stm32_pcie); + if (ret) { + dev_err(dev, "Failed to enable resources: %d\n", ret); + dw_pcie_ep_deinit(ep); + return ret; + } + + return 0; +} + +static int stm32_pcie_probe(struct platform_device *pdev) +{ + struct stm32_pcie *stm32_pcie; + struct device *dev = &pdev->dev; + int ret; + + stm32_pcie = devm_kzalloc(dev, sizeof(*stm32_pcie), GFP_KERNEL); + if (!stm32_pcie) + return -ENOMEM; + + stm32_pcie->pci.dev = dev; + stm32_pcie->pci.ops = &dw_pcie_ops; + + stm32_pcie->regmap = syscon_regmap_lookup_by_compatible("st,stm32mp25-syscfg"); + if (IS_ERR(stm32_pcie->regmap)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->regmap), + "No syscfg specified\n"); + + stm32_pcie->phy = devm_phy_get(dev, NULL); + if (IS_ERR(stm32_pcie->phy)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->phy), + "failed to get pcie-phy\n"); + + stm32_pcie->clk = devm_clk_get(dev, NULL); + if (IS_ERR(stm32_pcie->clk)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->clk), + "Failed to get PCIe clock source\n"); + + stm32_pcie->rst = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(stm32_pcie->rst)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->rst), + "Failed to get PCIe reset\n"); + + stm32_pcie->perst_gpio = devm_gpiod_get(dev, "reset", GPIOD_IN); + if (IS_ERR(stm32_pcie->perst_gpio)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->perst_gpio), + "Failed to get reset GPIO\n"); + + ret = phy_set_mode(stm32_pcie->phy, PHY_MODE_PCIE); + if (ret) + return ret; + + platform_set_drvdata(pdev, stm32_pcie); + + pm_runtime_get_noresume(dev); + + ret = devm_pm_runtime_enable(dev); + if (ret < 0) { + pm_runtime_put_noidle(&pdev->dev); + return dev_err_probe(dev, ret, "Failed to enable runtime PM\n"); + } + + stm32_pcie->perst_irq = gpiod_to_irq(stm32_pcie->perst_gpio); + + /* Will be enabled in start_link when device is initialized. */ + irq_set_status_flags(stm32_pcie->perst_irq, IRQ_NOAUTOEN); + + ret = devm_request_threaded_irq(dev, stm32_pcie->perst_irq, NULL, + stm32_pcie_ep_perst_irq_thread, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + "perst_irq", stm32_pcie); + if (ret) { + pm_runtime_put_noidle(&pdev->dev); + return dev_err_probe(dev, ret, "Failed to request PERST IRQ\n"); + } + + ret = stm32_add_pcie_ep(stm32_pcie, pdev); + if (ret) + pm_runtime_put_noidle(&pdev->dev); + + return ret; +} + +static void stm32_pcie_remove(struct platform_device *pdev) +{ + struct stm32_pcie *stm32_pcie = platform_get_drvdata(pdev); + struct dw_pcie *pci = &stm32_pcie->pci; + struct dw_pcie_ep *ep = &pci->ep; + + dw_pcie_stop_link(pci); + + pci_epc_deinit_notify(ep->epc); + dw_pcie_ep_deinit(ep); + + stm32_pcie_disable_resources(stm32_pcie); + + pm_runtime_put_sync(&pdev->dev); +} + +static const struct of_device_id stm32_pcie_ep_of_match[] = { + { .compatible = "st,stm32mp25-pcie-ep" }, + {}, +}; + +static struct platform_driver stm32_pcie_ep_driver = { + .probe = stm32_pcie_probe, + .remove = stm32_pcie_remove, + .driver = { + .name = "stm32-ep-pcie", + .of_match_table = stm32_pcie_ep_of_match, + }, +}; + +module_platform_driver(stm32_pcie_ep_driver); + +MODULE_AUTHOR("Christian Bruel <christian.bruel@foss.st.com>"); +MODULE_DESCRIPTION("STM32MP25 PCIe Endpoint Controller driver"); +MODULE_LICENSE("GPL"); +MODULE_DEVICE_TABLE(of, stm32_pcie_ep_of_match); diff --git a/drivers/pci/controller/dwc/pcie-stm32.c b/drivers/pci/controller/dwc/pcie-stm32.c new file mode 100644 index 000000000000..a9e77478443b --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-stm32.c @@ -0,0 +1,370 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * STMicroelectronics STM32MP25 PCIe root complex driver. + * + * Copyright (C) 2025 STMicroelectronics + * Author: Christian Bruel <christian.bruel@foss.st.com> + */ + +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/gpio/consumer.h> +#include <linux/irq.h> +#include <linux/mfd/syscon.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/phy/phy.h> +#include <linux/pinctrl/consumer.h> +#include <linux/platform_device.h> +#include <linux/pm.h> +#include <linux/pm_runtime.h> +#include <linux/pm_wakeirq.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <linux/stddef.h> + +#include "../../pci.h" + +#include "pcie-designware.h" +#include "pcie-stm32.h" + +struct stm32_pcie { + struct dw_pcie pci; + struct regmap *regmap; + struct reset_control *rst; + struct phy *phy; + struct clk *clk; + struct gpio_desc *perst_gpio; + struct gpio_desc *wake_gpio; +}; + +static void stm32_pcie_deassert_perst(struct stm32_pcie *stm32_pcie) +{ + if (stm32_pcie->perst_gpio) { + msleep(PCIE_T_PVPERL_MS); + gpiod_set_value(stm32_pcie->perst_gpio, 0); + } + + msleep(PCIE_RESET_CONFIG_WAIT_MS); +} + +static void stm32_pcie_assert_perst(struct stm32_pcie *stm32_pcie) +{ + gpiod_set_value(stm32_pcie->perst_gpio, 1); +} + +static int stm32_pcie_start_link(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + + return regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_LTSSM_EN, + STM32MP25_PCIECR_LTSSM_EN); +} + +static void stm32_pcie_stop_link(struct dw_pcie *pci) +{ + struct stm32_pcie *stm32_pcie = to_stm32_pcie(pci); + + regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_LTSSM_EN, 0); +} + +static int stm32_pcie_suspend_noirq(struct device *dev) +{ + struct stm32_pcie *stm32_pcie = dev_get_drvdata(dev); + int ret; + + ret = dw_pcie_suspend_noirq(&stm32_pcie->pci); + if (ret) + return ret; + + stm32_pcie_assert_perst(stm32_pcie); + + clk_disable_unprepare(stm32_pcie->clk); + + if (!device_wakeup_path(dev)) + phy_exit(stm32_pcie->phy); + + return pinctrl_pm_select_sleep_state(dev); +} + +static int stm32_pcie_resume_noirq(struct device *dev) +{ + struct stm32_pcie *stm32_pcie = dev_get_drvdata(dev); + int ret; + + /* + * The core clock is gated with CLKREQ# from the COMBOPHY REFCLK, + * thus if no device is present, must deassert it with a GPIO from + * pinctrl pinmux before accessing the DBI registers. + */ + ret = pinctrl_pm_select_init_state(dev); + if (ret) { + dev_err(dev, "Failed to activate pinctrl pm state: %d\n", ret); + return ret; + } + + if (!device_wakeup_path(dev)) { + ret = phy_init(stm32_pcie->phy); + if (ret) { + pinctrl_pm_select_default_state(dev); + return ret; + } + } + + ret = clk_prepare_enable(stm32_pcie->clk); + if (ret) + goto err_phy_exit; + + stm32_pcie_deassert_perst(stm32_pcie); + + ret = dw_pcie_resume_noirq(&stm32_pcie->pci); + if (ret) + goto err_disable_clk; + + pinctrl_pm_select_default_state(dev); + + return 0; + +err_disable_clk: + stm32_pcie_assert_perst(stm32_pcie); + clk_disable_unprepare(stm32_pcie->clk); + +err_phy_exit: + phy_exit(stm32_pcie->phy); + pinctrl_pm_select_default_state(dev); + + return ret; +} + +static const struct dev_pm_ops stm32_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(stm32_pcie_suspend_noirq, + stm32_pcie_resume_noirq) +}; + +static const struct dw_pcie_host_ops stm32_pcie_host_ops = { +}; + +static const struct dw_pcie_ops dw_pcie_ops = { + .start_link = stm32_pcie_start_link, + .stop_link = stm32_pcie_stop_link +}; + +static int stm32_add_pcie_port(struct stm32_pcie *stm32_pcie) +{ + struct device *dev = stm32_pcie->pci.dev; + unsigned int wake_irq; + int ret; + + ret = phy_set_mode(stm32_pcie->phy, PHY_MODE_PCIE); + if (ret) + return ret; + + ret = phy_init(stm32_pcie->phy); + if (ret) + return ret; + + ret = regmap_update_bits(stm32_pcie->regmap, SYSCFG_PCIECR, + STM32MP25_PCIECR_TYPE_MASK, + STM32MP25_PCIECR_RC); + if (ret) + goto err_phy_exit; + + stm32_pcie_deassert_perst(stm32_pcie); + + if (stm32_pcie->wake_gpio) { + wake_irq = gpiod_to_irq(stm32_pcie->wake_gpio); + ret = dev_pm_set_dedicated_wake_irq(dev, wake_irq); + if (ret) { + dev_err(dev, "Failed to enable wakeup irq %d\n", ret); + goto err_assert_perst; + } + irq_set_irq_type(wake_irq, IRQ_TYPE_EDGE_FALLING); + } + + return 0; + +err_assert_perst: + stm32_pcie_assert_perst(stm32_pcie); + +err_phy_exit: + phy_exit(stm32_pcie->phy); + + return ret; +} + +static void stm32_remove_pcie_port(struct stm32_pcie *stm32_pcie) +{ + dev_pm_clear_wake_irq(stm32_pcie->pci.dev); + + stm32_pcie_assert_perst(stm32_pcie); + + phy_exit(stm32_pcie->phy); +} + +static int stm32_pcie_parse_port(struct stm32_pcie *stm32_pcie) +{ + struct device *dev = stm32_pcie->pci.dev; + struct device_node *root_port; + + root_port = of_get_next_available_child(dev->of_node, NULL); + + stm32_pcie->phy = devm_of_phy_get(dev, root_port, NULL); + if (IS_ERR(stm32_pcie->phy)) { + of_node_put(root_port); + return dev_err_probe(dev, PTR_ERR(stm32_pcie->phy), + "Failed to get pcie-phy\n"); + } + + stm32_pcie->perst_gpio = devm_fwnode_gpiod_get(dev, of_fwnode_handle(root_port), + "reset", GPIOD_OUT_HIGH, NULL); + if (IS_ERR(stm32_pcie->perst_gpio)) { + if (PTR_ERR(stm32_pcie->perst_gpio) != -ENOENT) { + of_node_put(root_port); + return dev_err_probe(dev, PTR_ERR(stm32_pcie->perst_gpio), + "Failed to get reset GPIO\n"); + } + stm32_pcie->perst_gpio = NULL; + } + + stm32_pcie->wake_gpio = devm_fwnode_gpiod_get(dev, of_fwnode_handle(root_port), + "wake", GPIOD_IN, NULL); + + if (IS_ERR(stm32_pcie->wake_gpio)) { + if (PTR_ERR(stm32_pcie->wake_gpio) != -ENOENT) { + of_node_put(root_port); + return dev_err_probe(dev, PTR_ERR(stm32_pcie->wake_gpio), + "Failed to get wake GPIO\n"); + } + stm32_pcie->wake_gpio = NULL; + } + + of_node_put(root_port); + + return 0; +} + +static int stm32_pcie_probe(struct platform_device *pdev) +{ + struct stm32_pcie *stm32_pcie; + struct device *dev = &pdev->dev; + int ret; + + stm32_pcie = devm_kzalloc(dev, sizeof(*stm32_pcie), GFP_KERNEL); + if (!stm32_pcie) + return -ENOMEM; + + stm32_pcie->pci.dev = dev; + stm32_pcie->pci.ops = &dw_pcie_ops; + stm32_pcie->pci.pp.ops = &stm32_pcie_host_ops; + + stm32_pcie->regmap = syscon_regmap_lookup_by_compatible("st,stm32mp25-syscfg"); + if (IS_ERR(stm32_pcie->regmap)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->regmap), + "No syscfg specified\n"); + + stm32_pcie->clk = devm_clk_get(dev, NULL); + if (IS_ERR(stm32_pcie->clk)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->clk), + "Failed to get PCIe clock source\n"); + + stm32_pcie->rst = devm_reset_control_get_exclusive(dev, NULL); + if (IS_ERR(stm32_pcie->rst)) + return dev_err_probe(dev, PTR_ERR(stm32_pcie->rst), + "Failed to get PCIe reset\n"); + + ret = stm32_pcie_parse_port(stm32_pcie); + if (ret) + return ret; + + platform_set_drvdata(pdev, stm32_pcie); + + ret = stm32_add_pcie_port(stm32_pcie); + if (ret) + return ret; + + reset_control_assert(stm32_pcie->rst); + reset_control_deassert(stm32_pcie->rst); + + ret = clk_prepare_enable(stm32_pcie->clk); + if (ret) { + dev_err(dev, "Core clock enable failed %d\n", ret); + goto err_remove_port; + } + + ret = pm_runtime_set_active(dev); + if (ret < 0) { + dev_err_probe(dev, ret, "Failed to activate runtime PM\n"); + goto err_disable_clk; + } + + pm_runtime_no_callbacks(dev); + + ret = devm_pm_runtime_enable(dev); + if (ret < 0) { + dev_err_probe(dev, ret, "Failed to enable runtime PM\n"); + goto err_disable_clk; + } + + ret = dw_pcie_host_init(&stm32_pcie->pci.pp); + if (ret) + goto err_disable_clk; + + if (stm32_pcie->wake_gpio) + device_init_wakeup(dev, true); + + return 0; + +err_disable_clk: + clk_disable_unprepare(stm32_pcie->clk); + +err_remove_port: + stm32_remove_pcie_port(stm32_pcie); + + return ret; +} + +static void stm32_pcie_remove(struct platform_device *pdev) +{ + struct stm32_pcie *stm32_pcie = platform_get_drvdata(pdev); + struct dw_pcie_rp *pp = &stm32_pcie->pci.pp; + + if (stm32_pcie->wake_gpio) + device_init_wakeup(&pdev->dev, false); + + dw_pcie_host_deinit(pp); + + clk_disable_unprepare(stm32_pcie->clk); + + stm32_remove_pcie_port(stm32_pcie); + + pm_runtime_put_noidle(&pdev->dev); +} + +static const struct of_device_id stm32_pcie_of_match[] = { + { .compatible = "st,stm32mp25-pcie-rc" }, + {}, +}; + +static struct platform_driver stm32_pcie_driver = { + .probe = stm32_pcie_probe, + .remove = stm32_pcie_remove, + .driver = { + .name = "stm32-pcie", + .of_match_table = stm32_pcie_of_match, + .pm = &stm32_pcie_pm_ops, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, +}; + +module_platform_driver(stm32_pcie_driver); + +MODULE_AUTHOR("Christian Bruel <christian.bruel@foss.st.com>"); +MODULE_DESCRIPTION("STM32MP25 PCIe Controller driver"); +MODULE_LICENSE("GPL"); +MODULE_DEVICE_TABLE(of, stm32_pcie_of_match); diff --git a/drivers/pci/controller/dwc/pcie-stm32.h b/drivers/pci/controller/dwc/pcie-stm32.h new file mode 100644 index 000000000000..419cf1ff669d --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-stm32.h @@ -0,0 +1,19 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ +/* + * ST PCIe driver definitions for STM32-MP25 SoC + * + * Copyright (C) 2025 STMicroelectronics - All Rights Reserved + * Author: Christian Bruel <christian.bruel@foss.st.com> + */ + +#include <linux/bits.h> +#include <linux/device.h> + +#define to_stm32_pcie(x) dev_get_drvdata((x)->dev) + +#define STM32MP25_PCIECR_TYPE_MASK GENMASK(11, 8) +#define STM32MP25_PCIECR_EP 0 +#define STM32MP25_PCIECR_LTSSM_EN BIT(2) +#define STM32MP25_PCIECR_RC BIT(10) + +#define SYSCFG_PCIECR 0x6000 diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c index c1394f2ab63f..0ddeef70726d 100644 --- a/drivers/pci/controller/dwc/pcie-tegra194.c +++ b/drivers/pci/controller/dwc/pcie-tegra194.c @@ -260,7 +260,6 @@ struct tegra_pcie_dw { 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; @@ -475,8 +474,7 @@ static irqreturn_t tegra_pcie_ep_irq_thread(int irq, void *arg) 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))) + if (!pci->l1ss_support) return IRQ_HANDLED; /* Check if BME is set to '1' */ @@ -608,24 +606,6 @@ static struct pci_ops tegra_pci_ops = { }; #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; @@ -682,10 +662,9 @@ static int aspm_state_cnt(struct seq_file *s, void *data) static void init_host_aspm(struct tegra_pcie_dw *pcie) { struct dw_pcie *pci = &pcie->pci; - u32 val; + u32 l1ss, val; - val = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_L1SS); - pcie->cfg_link_cap_l1sub = val + PCI_L1SS_CAP; + l1ss = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_L1SS); pcie->ras_des_cap = dw_pcie_find_ext_capability(&pcie->pci, PCI_EXT_CAP_ID_VNDR); @@ -697,11 +676,14 @@ static void init_host_aspm(struct tegra_pcie_dw *pcie) 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 = dw_pcie_readl_dbi(pci, l1ss + PCI_L1SS_CAP); 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); + dw_pcie_writel_dbi(pci, l1ss + PCI_L1SS_CAP, val); + + if (pcie->supports_clkreq) + pci->l1ss_support = true; /* Program L0s and L1 entrance latencies */ val = dw_pcie_readl_dbi(pci, PCIE_PORT_AFR); @@ -713,12 +695,19 @@ static void init_host_aspm(struct tegra_pcie_dw *pcie) static void init_debugfs(struct tegra_pcie_dw *pcie) { - debugfs_create_devm_seqfile(pcie->dev, "aspm_state_cnt", pcie->debugfs, + struct device *dev = pcie->dev; + char *name; + + name = devm_kasprintf(dev, GFP_KERNEL, "%pOFP", dev->of_node); + if (!name) + return; + + pcie->debugfs = debugfs_create_dir(name, NULL); + + debugfs_create_devm_seqfile(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 @@ -922,12 +911,6 @@ static int tegra_pcie_dw_host_init(struct dw_pcie_rp *pp) 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; @@ -1027,12 +1010,12 @@ retry_link: return 0; } -static int tegra_pcie_dw_link_up(struct dw_pcie *pci) +static bool 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); + return val & PCI_EXP_LNKSTA_DLLLA; } static void tegra_pcie_dw_stop_link(struct dw_pcie *pci) @@ -1205,6 +1188,7 @@ static int tegra_pcie_bpmp_set_ctrl_state(struct tegra_pcie_dw *pcie, struct mrq_uphy_response resp; struct tegra_bpmp_message msg; struct mrq_uphy_request req; + int err; /* * Controller-5 doesn't need to have its state set by BPMP-FW in @@ -1227,7 +1211,13 @@ static int tegra_pcie_bpmp_set_ctrl_state(struct tegra_pcie_dw *pcie, msg.rx.data = &resp; msg.rx.size = sizeof(resp); - return tegra_bpmp_transfer(pcie->bpmp, &msg); + err = tegra_bpmp_transfer(pcie->bpmp, &msg); + if (err) + return err; + if (msg.rx.ret) + return -EINVAL; + + return 0; } static int tegra_pcie_bpmp_set_pll_state(struct tegra_pcie_dw *pcie, @@ -1236,6 +1226,7 @@ static int tegra_pcie_bpmp_set_pll_state(struct tegra_pcie_dw *pcie, struct mrq_uphy_response resp; struct tegra_bpmp_message msg; struct mrq_uphy_request req; + int err; memset(&req, 0, sizeof(req)); memset(&resp, 0, sizeof(resp)); @@ -1255,13 +1246,19 @@ static int tegra_pcie_bpmp_set_pll_state(struct tegra_pcie_dw *pcie, msg.rx.data = &resp; msg.rx.size = sizeof(resp); - return tegra_bpmp_transfer(pcie->bpmp, &msg); + err = tegra_bpmp_transfer(pcie->bpmp, &msg); + if (err) + return err; + if (msg.rx.ret) + return -EINVAL; + + return 0; } 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_bus *child, *root_port_bus = NULL; struct pci_dev *pdev; /* @@ -1274,19 +1271,19 @@ static void tegra_pcie_downstream_dev_to_D0(struct tegra_pcie_dw *pcie) */ 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; + root_port_bus = child; break; } } - if (!root_bus) { - dev_err(pcie->dev, "Failed to find downstream devices\n"); + if (!root_port_bus) { + dev_err(pcie->dev, "Failed to find downstream bus of Root Port\n"); return; } - list_for_each_entry(pdev, &root_bus->devices, bus_list) { + /* Bring downstream devices to D0 if they are not already in */ + list_for_each_entry(pdev, &root_port_bus->devices, bus_list) { if (PCI_SLOT(pdev->devfn) == 0) { if (pci_set_power_state(pdev, PCI_D0)) dev_err(pcie->dev, @@ -1634,7 +1631,6 @@ static void tegra_pcie_deinit_controller(struct tegra_pcie_dw *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); @@ -1664,13 +1660,6 @@ static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie) 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; @@ -1704,9 +1693,6 @@ static void pex_ep_event_pex_rst_assert(struct tegra_pcie_dw *pcie) if (ret) dev_err(pcie->dev, "Failed to go Detect state: %d\n", ret); - pci_epc_deinit_notify(pcie->pci.ep.epc); - dw_pcie_ep_cleanup(&pcie->pci.ep); - reset_control_assert(pcie->core_rst); tegra_pcie_disable_phy(pcie); @@ -1724,9 +1710,9 @@ static void pex_ep_event_pex_rst_assert(struct tegra_pcie_dw *pcie) ret); } - ret = tegra_pcie_bpmp_set_pll_state(pcie, false); + ret = tegra_pcie_bpmp_set_ctrl_state(pcie, false); if (ret) - dev_err(pcie->dev, "Failed to turn off UPHY: %d\n", ret); + dev_err(pcie->dev, "Failed to disable controller: %d\n", ret); pcie->ep_state = EP_STATE_DISABLED; dev_dbg(pcie->dev, "Uninitialization of endpoint is completed\n"); @@ -1785,6 +1771,10 @@ static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie) goto fail_phy; } + /* Perform cleanup that requires refclk */ + pci_epc_deinit_notify(pcie->pci.ep.epc); + dw_pcie_ep_cleanup(&pcie->pci.ep); + /* Clear any stale interrupt statuses */ appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L0); appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_0_0); @@ -1855,12 +1845,6 @@ static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *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; @@ -1939,6 +1923,15 @@ static irqreturn_t tegra_pcie_ep_pex_rst_irq(int irq, void *arg) return IRQ_HANDLED; } +static void tegra_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 tegra_pcie_ep_raise_intx_irq(struct tegra_pcie_dw *pcie, u16 irq) { /* Tegra194 supports only INTA */ @@ -1953,10 +1946,10 @@ static int tegra_pcie_ep_raise_intx_irq(struct tegra_pcie_dw *pcie, u16 irq) static int tegra_pcie_ep_raise_msi_irq(struct tegra_pcie_dw *pcie, u16 irq) { - if (unlikely(irq > 31)) + if (unlikely(irq > 32)) return -EINVAL; - appl_writel(pcie, BIT(irq), APPL_MSI_CTRL_1); + appl_writel(pcie, BIT(irq - 1), APPL_MSI_CTRL_1); return 0; } @@ -1996,8 +1989,7 @@ static int tegra_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no, static const struct pci_epc_features tegra_pcie_epc_features = { .linkup_notifier = true, - .msi_capable = false, - .msix_capable = false, + .msi_capable = true, .bar[BAR_0] = { .type = BAR_FIXED, .fixed_size = SZ_1M, .only_64bit = true, }, .bar[BAR_1] = { .type = BAR_RESERVED, }, @@ -2015,6 +2007,7 @@ tegra_pcie_ep_get_features(struct dw_pcie_ep *ep) } static const struct dw_pcie_ep_ops pcie_ep_ops = { + .init = tegra_pcie_ep_init, .raise_irq = tegra_pcie_ep_raise_irq, .get_features = tegra_pcie_ep_get_features, }; @@ -2493,7 +2486,7 @@ static const struct dev_pm_ops tegra_pcie_dw_pm_ops = { static struct platform_driver tegra_pcie_dw_driver = { .probe = tegra_pcie_dw_probe, - .remove_new = tegra_pcie_dw_remove, + .remove = tegra_pcie_dw_remove, .shutdown = tegra_pcie_dw_shutdown, .driver = { .name = "tegra194-pcie", diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c index 5757ca3803c9..297e7a3d9b36 100644 --- a/drivers/pci/controller/dwc/pcie-uniphier.c +++ b/drivers/pci/controller/dwc/pcie-uniphier.c @@ -135,7 +135,7 @@ static int uniphier_pcie_wait_rc(struct uniphier_pcie *pcie) return 0; } -static int uniphier_pcie_link_up(struct dw_pcie *pci) +static bool uniphier_pcie_link_up(struct dw_pcie *pci) { struct uniphier_pcie *pcie = to_uniphier_pcie(pci); u32 val, mask; @@ -279,7 +279,7 @@ static int uniphier_pcie_config_intx_irq(struct dw_pcie_rp *pp) goto out_put_node; } - pcie->intx_irq_domain = irq_domain_add_linear(np_intc, PCI_NUM_INTX, + pcie->intx_irq_domain = irq_domain_create_linear(of_fwnode_handle(np_intc), PCI_NUM_INTX, &uniphier_intx_domain_ops, pp); if (!pcie->intx_irq_domain) { dev_err(pci->dev, "Failed to get INTx domain\n"); diff --git a/drivers/pci/controller/dwc/pcie-visconti.c b/drivers/pci/controller/dwc/pcie-visconti.c index 318c278e65c8..cdeac6177143 100644 --- a/drivers/pci/controller/dwc/pcie-visconti.c +++ b/drivers/pci/controller/dwc/pcie-visconti.c @@ -121,13 +121,13 @@ 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) +static bool 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); + return val & PCIE_UL_S_L0; } static int visconti_pcie_start_link(struct dw_pcie *pci) diff --git a/drivers/pci/controller/mobiveil/Kconfig b/drivers/pci/controller/mobiveil/Kconfig index 58ce034f701a..c50c4625937f 100644 --- a/drivers/pci/controller/mobiveil/Kconfig +++ b/drivers/pci/controller/mobiveil/Kconfig @@ -9,6 +9,7 @@ config PCIE_MOBIVEIL config PCIE_MOBIVEIL_HOST bool depends on PCI_MSI + select IRQ_MSI_LIB select PCIE_MOBIVEIL config PCIE_LAYERSCAPE_GEN4 diff --git a/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c b/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c index 5af22bee913b..4919b27eaf44 100644 --- a/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c +++ b/drivers/pci/controller/mobiveil/pcie-layerscape-gen4.c @@ -53,18 +53,13 @@ static inline void ls_g4_pcie_pf_writel(struct ls_g4_pcie *pcie, iowrite32(val, pcie->pci.csr_axi_slave_base + PCIE_PF_OFF + off); } -static int ls_g4_pcie_link_up(struct mobiveil_pcie *pci) +static bool 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; + return (state & PF_DBG_LTSSM_MASK) == PF_DBG_LTSSM_L0; } static void ls_g4_pcie_disable_interrupt(struct ls_g4_pcie *pcie) @@ -174,8 +169,7 @@ static int ls_g4_pcie_interrupt_init(struct mobiveil_pcie *mv_pci) static void ls_g4_pcie_reset(struct work_struct *work) { - struct delayed_work *dwork = container_of(work, struct delayed_work, - work); + struct delayed_work *dwork = to_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; diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c index 0e088e74155d..dbc72c73fd0a 100644 --- a/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c +++ b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c @@ -12,6 +12,7 @@ #include <linux/init.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> #include <linux/kernel.h> @@ -353,16 +354,19 @@ 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, -}; +#define MOBIVEIL_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) + +#define MOBIVEIL_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_PCI_MSIX) -static struct msi_domain_info mobiveil_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_NO_AFFINITY | MSI_FLAG_PCI_MSIX, - .chip = &mobiveil_msi_irq_chip, +static const struct msi_parent_ops mobiveil_msi_parent_ops = { + .required_flags = MOBIVEIL_MSI_FLAGS_REQUIRED, + .supported_flags = MOBIVEIL_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .prefix = "Mobiveil-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; static void mobiveil_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) @@ -435,23 +439,20 @@ static const struct irq_domain_ops msi_domain_ops = { 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) { + struct irq_domain_info info = { + .fwnode = dev_fwnode(dev), + .ops = &msi_domain_ops, + .host_data = pcie, + .size = msi->num_of_vectors, + }; + + msi->dev_domain = msi_create_parent_irq_domain(&info, &mobiveil_msi_parent_ops); + if (!msi->dev_domain) { dev_err(dev, "failed to create MSI domain\n"); - irq_domain_remove(msi->dev_domain); return -ENOMEM; } @@ -461,13 +462,11 @@ static int mobiveil_allocate_msi_domains(struct mobiveil_pcie *pcie) 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); - + rp->intx_domain = irq_domain_create_linear(dev_fwnode(dev), PCI_NUM_INTX, &intx_domain_ops, + pcie); if (!rp->intx_domain) { dev_err(dev, "Failed to get a INTx IRQ domain\n"); return -ENOMEM; diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil.h b/drivers/pci/controller/mobiveil/pcie-mobiveil.h index e63abb887ee3..7246de6a7176 100644 --- a/drivers/pci/controller/mobiveil/pcie-mobiveil.h +++ b/drivers/pci/controller/mobiveil/pcie-mobiveil.h @@ -135,7 +135,6 @@ 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; @@ -160,7 +159,7 @@ struct mobiveil_root_port { }; struct mobiveil_pab_ops { - int (*link_up)(struct mobiveil_pcie *pcie); + bool (*link_up)(struct mobiveil_pcie *pcie); }; struct mobiveil_pcie { diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c index a598a98247ce..e34bea1ff0ac 100644 --- a/drivers/pci/controller/pci-aardvark.c +++ b/drivers/pci/controller/pci-aardvark.c @@ -13,6 +13,7 @@ #include <linux/gpio/consumer.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/kernel.h> #include <linux/module.h> @@ -278,7 +279,6 @@ struct advk_pcie { 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); @@ -1332,18 +1332,6 @@ static void advk_msi_irq_unmask(struct irq_data *d) 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, @@ -1436,17 +1424,20 @@ static const struct irq_domain_ops advk_pcie_irq_domain_ops = { .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_NO_AFFINITY | MSI_FLAG_MULTI_PCI_MSI | - MSI_FLAG_PCI_MSIX, - .chip = &advk_msi_irq_chip, +#define ADVK_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_PCI_MSI_MASK_PARENT | \ + MSI_FLAG_NO_AFFINITY) +#define ADVK_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_PCI_MSIX | \ + MSI_FLAG_MULTI_PCI_MSI) + +static const struct msi_parent_ops advk_msi_parent_ops = { + .required_flags = ADVK_MSI_FLAGS_REQUIRED, + .supported_flags = ADVK_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .prefix = "advk-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; static int advk_pcie_init_msi_irq_domain(struct advk_pcie *pcie) @@ -1456,27 +1447,22 @@ static int advk_pcie_init_msi_irq_domain(struct advk_pcie *pcie) 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; + struct irq_domain_info info = { + .fwnode = dev_fwnode(dev), + .ops = &advk_msi_domain_ops, + .host_data = pcie, + .size = MSI_IRQ_NUM, + }; - 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); + pcie->msi_inner_domain = msi_create_parent_irq_domain(&info, &advk_msi_parent_ops); + if (!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); } @@ -1508,9 +1494,8 @@ static int advk_pcie_init_irq_domain(struct advk_pcie *pcie) 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); + pcie->irq_domain = irq_domain_create_linear(of_fwnode_handle(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; @@ -1549,9 +1534,7 @@ static const struct irq_domain_ops advk_pcie_rp_irq_domain_ops = { 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); + pcie->rp_irq_domain = irq_domain_create_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; @@ -1996,7 +1979,7 @@ static struct platform_driver advk_pcie_driver = { .of_match_table = advk_pcie_of_match_table, }, .probe = advk_pcie_probe, - .remove_new = advk_pcie_remove, + .remove = advk_pcie_remove, }; module_platform_driver(advk_pcie_driver); diff --git a/drivers/pci/controller/pci-ftpci100.c b/drivers/pci/controller/pci-ftpci100.c index ffdeed25e961..28e43831c0f1 100644 --- a/drivers/pci/controller/pci-ftpci100.c +++ b/drivers/pci/controller/pci-ftpci100.c @@ -345,8 +345,8 @@ static int faraday_pci_setup_cascaded_irq(struct faraday_pci *p) return irq ?: -EINVAL; } - p->irqdomain = irq_domain_add_linear(intc, PCI_NUM_INTX, - &faraday_pci_irqdomain_ops, p); + p->irqdomain = irq_domain_create_linear(of_fwnode_handle(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"); diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c index cf5f59a745b3..c473e7c03bac 100644 --- a/drivers/pci/controller/pci-host-common.c +++ b/drivers/pci/controller/pci-host-common.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 /* - * Generic PCI host driver common code + * Common library for PCI host controller drivers * * Copyright (C) 2014 ARM Limited * @@ -15,12 +15,14 @@ #include <linux/pci-ecam.h> #include <linux/platform_device.h> +#include "pci-host-common.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_config_window *pci_host_common_ecam_create(struct device *dev, struct pci_host_bridge *bridge, const struct pci_ecam_ops *ops) { int err; @@ -48,37 +50,49 @@ static struct pci_config_window *gen_pci_init(struct device *dev, return cfg; } +EXPORT_SYMBOL_GPL(pci_host_common_ecam_create); -int pci_host_common_probe(struct platform_device *pdev) +int pci_host_common_init(struct platform_device *pdev, + struct pci_host_bridge *bridge, + const struct pci_ecam_ops *ops) { 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; + of_pci_check_probe_only(); platform_set_drvdata(pdev, bridge); - of_pci_check_probe_only(); - /* Parse and map our Configuration Space windows */ - cfg = gen_pci_init(dev, bridge, ops); + cfg = pci_host_common_ecam_create(dev, bridge, ops); if (IS_ERR(cfg)) return PTR_ERR(cfg); bridge->sysdata = cfg; bridge->ops = (struct pci_ops *)&ops->pci_ops; + bridge->enable_device = ops->enable_device; + bridge->disable_device = ops->disable_device; bridge->msi_domain = true; return pci_host_probe(bridge); } +EXPORT_SYMBOL_GPL(pci_host_common_init); + +int pci_host_common_probe(struct platform_device *pdev) +{ + const struct pci_ecam_ops *ops; + struct pci_host_bridge *bridge; + + ops = of_device_get_match_data(&pdev->dev); + if (!ops) + return -ENODEV; + + bridge = devm_pci_alloc_host_bridge(&pdev->dev, 0); + if (!bridge) + return -ENOMEM; + + return pci_host_common_init(pdev, bridge, ops); +} EXPORT_SYMBOL_GPL(pci_host_common_probe); void pci_host_common_remove(struct platform_device *pdev) @@ -92,5 +106,5 @@ void pci_host_common_remove(struct platform_device *pdev) } EXPORT_SYMBOL_GPL(pci_host_common_remove); -MODULE_DESCRIPTION("Generic PCI host common driver"); +MODULE_DESCRIPTION("Common library for PCI host controller drivers"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-host-common.h b/drivers/pci/controller/pci-host-common.h new file mode 100644 index 000000000000..b5075d4bd7eb --- /dev/null +++ b/drivers/pci/controller/pci-host-common.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * Common library for PCI host controller drivers + * + * Copyright (C) 2014 ARM Limited + * + * Author: Will Deacon <will.deacon@arm.com> + */ + +#ifndef _PCI_HOST_COMMON_H +#define _PCI_HOST_COMMON_H + +struct pci_ecam_ops; + +int pci_host_common_probe(struct platform_device *pdev); +int pci_host_common_init(struct platform_device *pdev, + struct pci_host_bridge *bridge, + const struct pci_ecam_ops *ops); +void pci_host_common_remove(struct platform_device *pdev); + +struct pci_config_window *pci_host_common_ecam_create(struct device *dev, + struct pci_host_bridge *bridge, const struct pci_ecam_ops *ops); +#endif diff --git a/drivers/pci/controller/pci-host-generic.c b/drivers/pci/controller/pci-host-generic.c index 5f06f94db7b1..c1bc0d34348f 100644 --- a/drivers/pci/controller/pci-host-generic.c +++ b/drivers/pci/controller/pci-host-generic.c @@ -14,6 +14,8 @@ #include <linux/pci-ecam.h> #include <linux/platform_device.h> +#include "pci-host-common.h" + static const struct pci_ecam_ops gen_pci_cfg_cam_bus_ops = { .bus_shift = 16, .pci_ops = { @@ -82,7 +84,7 @@ static struct platform_driver gen_pci_driver = { .of_match_table = gen_pci_of_match, }, .probe = pci_host_common_probe, - .remove_new = pci_host_common_remove, + .remove = pci_host_common_remove, }; module_platform_driver(gen_pci_driver); diff --git a/drivers/pci/controller/pci-hyperv-intf.c b/drivers/pci/controller/pci-hyperv-intf.c index cc96be450360..28b3e93d31c0 100644 --- a/drivers/pci/controller/pci-hyperv-intf.c +++ b/drivers/pci/controller/pci-hyperv-intf.c @@ -14,6 +14,7 @@ #include <linux/kernel.h> #include <linux/module.h> #include <linux/hyperv.h> +#include <linux/export.h> struct hyperv_pci_block_ops hvpci_block_ops; EXPORT_SYMBOL_GPL(hvpci_block_ops); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index cdd5be16021d..1e237d3538f9 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -44,12 +44,14 @@ #include <linux/delay.h> #include <linux/semaphore.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/msi.h> #include <linux/hyperv.h> #include <linux/refcount.h> #include <linux/irqdomain.h> #include <linux/acpi.h> #include <linux/sizes.h> +#include <linux/of_irq.h> #include <asm/mshyperv.h> /* @@ -309,8 +311,6 @@ struct pci_packet { void (*completion_func)(void *context, struct pci_response *resp, int resp_packet_size); void *compl_ctxt; - - struct pci_message message[]; }; /* @@ -509,7 +509,6 @@ struct hv_pcibus_device { struct list_head children; struct list_head dr_list; - struct msi_domain_info msi_info; struct irq_domain *irq_domain; struct workqueue_struct *wq; @@ -577,9 +576,8 @@ struct hv_pci_compl { 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" +#define DELIVERY_MODE APIC_DELIVERY_MODE_FIXED +#define HV_MSI_CHIP_FLAGS MSI_CHIP_FLAG_SET_ACK static int hv_pci_irqchip_init(void) { @@ -601,7 +599,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data) #define hv_msi_prepare pci_msi_prepare /** - * hv_arch_irq_unmask() - "Unmask" the IRQ by setting its current + * hv_irq_retarget_interrupt() - "Unmask" the IRQ by setting its current * affinity. * @data: Describes the IRQ * @@ -610,7 +608,7 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data) * 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) +static void hv_irq_retarget_interrupt(struct irq_data *data) { struct msi_desc *msi_desc = irq_data_get_msi_desc(data); struct hv_retarget_device_interrupt *params; @@ -715,6 +713,20 @@ out: dev_err(&hbus->hdev->device, "%s() failed: %#llx", __func__, res); } + +static void hv_arch_irq_unmask(struct irq_data *data) +{ + if (hv_root_partition()) + /* + * In case of the nested root partition, the nested hypervisor + * is taking care of interrupt remapping and thus the + * MAP_DEVICE_INTERRUPT hypercall is required instead of + * RETARGET_INTERRUPT. + */ + (void)hv_map_msi_interrupt(data, NULL); + else + hv_irq_retarget_interrupt(data); +} #elif defined(CONFIG_ARM64) /* * SPI vectors to use for vPCI; arch SPIs range is [32, 1019], but leaving a bit @@ -724,8 +736,7 @@ out: #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_CHIP_FLAGS MSI_CHIP_FLAG_SET_EOI #define hv_msi_prepare NULL struct hv_pci_chip_data { @@ -817,9 +828,17 @@ static int hv_pci_vec_irq_gic_domain_alloc(struct irq_domain *domain, int ret; fwspec.fwnode = domain->parent->fwnode; - fwspec.param_count = 2; - fwspec.param[0] = hwirq; - fwspec.param[1] = IRQ_TYPE_EDGE_RISING; + if (is_of_node(fwspec.fwnode)) { + /* SPI lines for OF translations start at offset 32 */ + fwspec.param_count = 3; + fwspec.param[0] = 0; + fwspec.param[1] = hwirq - 32; + fwspec.param[2] = IRQ_TYPE_EDGE_RISING; + } else { + 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) @@ -887,10 +906,44 @@ static const struct irq_domain_ops hv_pci_domain_ops = { .activate = hv_pci_vec_irq_domain_activate, }; +#ifdef CONFIG_OF + +static struct irq_domain *hv_pci_of_irq_domain_parent(void) +{ + struct device_node *parent; + struct irq_domain *domain; + + parent = of_irq_find_parent(hv_get_vmbus_root_device()->of_node); + if (!parent) + return NULL; + domain = irq_find_host(parent); + of_node_put(parent); + + return domain; +} + +#endif + +#ifdef CONFIG_ACPI + +static struct irq_domain *hv_pci_acpi_irq_domain_parent(void) +{ + acpi_gsi_domain_disp_fn gsi_domain_disp_fn; + + gsi_domain_disp_fn = acpi_get_gsi_dispatcher(); + if (!gsi_domain_disp_fn) + return NULL; + return irq_find_matching_fwnode(gsi_domain_disp_fn(0), + DOMAIN_BUS_ANY); +} + +#endif + static int hv_pci_irqchip_init(void) { static struct hv_pci_chip_data *chip_data; struct fwnode_handle *fn = NULL; + struct irq_domain *irq_domain_parent = NULL; int ret = -ENOMEM; chip_data = kzalloc(sizeof(*chip_data), GFP_KERNEL); @@ -907,9 +960,24 @@ static int hv_pci_irqchip_init(void) * 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); +#ifdef CONFIG_ACPI + if (!acpi_disabled) + irq_domain_parent = hv_pci_acpi_irq_domain_parent(); +#endif +#ifdef CONFIG_OF + if (!irq_domain_parent) + irq_domain_parent = hv_pci_of_irq_domain_parent(); +#endif + if (!irq_domain_parent) { + WARN_ONCE(1, "Invalid firmware configuration for VMBus interrupts\n"); + ret = -EINVAL; + goto free_chip; + } + + hv_msi_gic_irq_domain = irq_domain_create_hierarchy(irq_domain_parent, 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"); @@ -1356,7 +1424,7 @@ static struct pci_ops hv_pcifront_ops = { * * 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. + * supplied to the VF driver by this driver. * * No protocol is implied, except that supplied by the PF and VF drivers. */ @@ -1438,7 +1506,7 @@ static int hv_read_config_block(struct pci_dev *pdev, void *buf, 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 = (struct pci_read_block *)pkt.buf; read_blk->message_type.type = PCI_READ_BLOCK; read_blk->wslot.slot = devfn_to_wslot(pdev->devfn); read_blk->block_id = block_id; @@ -1518,7 +1586,7 @@ static int hv_write_config_block(struct pci_dev *pdev, void *buf, 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 = (struct pci_write_block *)pkt.buf; write_blk->message_type.type = PCI_WRITE_BLOCK; write_blk->wslot.slot = devfn_to_wslot(pdev->devfn); write_blk->block_id = block_id; @@ -1599,7 +1667,7 @@ static void hv_int_desc_free(struct hv_pci_dev *hpdev, return; } memset(&ctxt, 0, sizeof(ctxt)); - int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message; + int_pkt = (struct pci_delete_interrupt *)ctxt.buffer; int_pkt->message_type.type = PCI_DELETE_INTERRUPT_MESSAGE; int_pkt->wslot.slot = hpdev->desc.win_slot.slot; @@ -1612,7 +1680,6 @@ static void hv_int_desc_free(struct hv_pci_dev *hpdev, /** * 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 @@ -1620,8 +1687,7 @@ static void hv_int_desc_free(struct hv_pci_dev *hpdev, * 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) +static void hv_msi_free(struct irq_domain *domain, unsigned int irq) { struct hv_pcibus_device *hbus; struct hv_pci_dev *hpdev; @@ -1631,7 +1697,7 @@ static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info, struct msi_desc *msi = irq_data_get_msi_desc(irq_data); pdev = msi_desc_to_pci_dev(msi); - hbus = info->data; + hbus = domain->host_data; int_desc = irq_data_get_irq_chip_data(irq_data); if (!int_desc) return; @@ -1649,7 +1715,6 @@ static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info, 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); } @@ -1660,7 +1725,6 @@ static void hv_irq_unmask(struct irq_data *data) if (data->parent_data->chip->irq_unmask) irq_chip_unmask_parent(data); - pci_msi_unmask_irq(data); } struct compose_comp_ctxt { @@ -1757,8 +1821,7 @@ static int hv_compose_multi_msi_req_get_cpu(void) spin_lock_irqsave(&multi_msi_cpu_lock, flags); - cpu_next = cpumask_next_wrap(cpu_next, cpu_online_mask, nr_cpu_ids, - false); + cpu_next = cpumask_next_wrap(cpu_next, cpu_online_mask); cpu = cpu_next; spin_unlock_irqrestore(&multi_msi_cpu_lock, flags); @@ -2046,23 +2109,85 @@ return_null_message: msg->data = 0; } +static bool hv_pcie_init_dev_msi_info(struct device *dev, struct irq_domain *domain, + struct irq_domain *real_parent, struct msi_domain_info *info) +{ + struct irq_chip *chip = info->chip; + + if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info)) + return false; + + info->ops->msi_prepare = hv_msi_prepare; + + chip->irq_set_affinity = irq_chip_set_affinity_parent; + + if (IS_ENABLED(CONFIG_X86)) + chip->flags |= IRQCHIP_MOVE_DEFERRED; + + return true; +} + +#define HV_PCIE_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_PCI_MSI_MASK_PARENT) +#define HV_PCIE_MSI_FLAGS_SUPPORTED (MSI_FLAG_MULTI_PCI_MSI | \ + MSI_FLAG_PCI_MSIX | \ + MSI_FLAG_PCI_MSIX_ALLOC_DYN | \ + MSI_GENERIC_FLAGS_MASK) + +static const struct msi_parent_ops hv_pcie_msi_parent_ops = { + .required_flags = HV_PCIE_MSI_FLAGS_REQUIRED, + .supported_flags = HV_PCIE_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .chip_flags = HV_MSI_CHIP_FLAGS, + .prefix = "HV-", + .init_dev_msi_info = hv_pcie_init_dev_msi_info, +}; + /* 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, +static int hv_pcie_domain_alloc(struct irq_domain *d, unsigned int virq, unsigned int nr_irqs, + void *arg) +{ + /* + * TODO: Allocating and populating struct tran_int_desc in hv_compose_msi_msg() + * should be moved here. + */ + int ret; + + ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, arg); + if (ret < 0) + return ret; + + for (int i = 0; i < nr_irqs; i++) { + irq_domain_set_hwirq_and_chip(d, virq + i, 0, &hv_msi_irq_chip, NULL); + if (IS_ENABLED(CONFIG_X86)) + __irq_set_handler(virq + i, handle_edge_irq, 0, "edge"); + } + + return 0; +} + +static void hv_pcie_domain_free(struct irq_domain *d, unsigned int virq, unsigned int nr_irqs) +{ + for (int i = 0; i < nr_irqs; i++) + hv_msi_free(d, virq + i); + + irq_domain_free_irqs_top(d, virq, nr_irqs); +} + +static const struct irq_domain_ops hv_pcie_domain_ops = { + .alloc = hv_pcie_domain_alloc, + .free = hv_pcie_domain_free, }; /** @@ -2080,17 +2205,14 @@ static struct msi_domain_ops hv_msi_ops = { */ 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()); + struct irq_domain_info info = { + .fwnode = hbus->fwnode, + .ops = &hv_pcie_domain_ops, + .host_data = hbus, + .parent = hv_pci_get_root_domain(), + }; + + hbus->irq_domain = msi_create_parent_irq_domain(&info, &hv_pcie_msi_parent_ops); if (!hbus->irq_domain) { dev_err(&hbus->hdev->device, "Failed to build an MSI IRQ domain\n"); @@ -2482,7 +2604,7 @@ static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus, 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 = (struct pci_child_message *)pkt.buffer; res_req->message_type.type = PCI_QUERY_RESOURCE_REQUIREMENTS; res_req->wslot.slot = desc->win_slot.slot; @@ -2860,7 +2982,7 @@ static void hv_eject_device_work(struct work_struct *work) pci_destroy_slot(hpdev->pci_slot); memset(&ctxt, 0, sizeof(ctxt)); - ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message; + ejct_pkt = (struct pci_eject_response *)ctxt.buffer; ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE; ejct_pkt->wslot.slot = hpdev->desc.win_slot.slot; vmbus_sendpacket(hbus->hdev->channel, ejct_pkt, @@ -3118,7 +3240,7 @@ static int hv_pci_protocol_negotiation(struct hv_device *hdev, 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 = (struct pci_version_request *)(pkt + 1); version_req->message_type.type = PCI_QUERY_PROTOCOL_VERSION; for (i = 0; i < num_version; i++) { @@ -3340,7 +3462,7 @@ enter_d0_retry: 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 = (struct pci_bus_d0_entry *)(pkt + 1); d0_entry->message_type.type = PCI_BUS_D0ENTRY; d0_entry->mmio_base = hbus->mem_config->start; @@ -3498,20 +3620,20 @@ static int hv_send_resources_allocated(struct hv_device *hdev) if (hbus->protocol_version < PCI_PROTOCOL_VERSION_1_2) { res_assigned = - (struct pci_resources_assigned *)&pkt->message; + (struct pci_resources_assigned *)(pkt + 1); 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; + (struct pci_resources_assigned2 *)(pkt + 1); 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, + ret = vmbus_sendpacket(hdev->channel, pkt + 1, size_res, (unsigned long)pkt, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); @@ -3574,48 +3696,6 @@ static int hv_send_resources_released(struct hv_device *hdev) 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 @@ -3628,9 +3708,9 @@ static int hv_pci_probe(struct hv_device *hdev, { struct pci_host_bridge *bridge; struct hv_pcibus_device *hbus; - u16 dom_req, dom; + int ret, dom; + u16 dom_req; char *name; - int ret; bridge = devm_pci_alloc_host_bridge(&hdev->device, 0); if (!bridge) @@ -3657,11 +3737,14 @@ static int hv_pci_probe(struct hv_device *hdev, * 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. + * + * Because Gen1 VMs use domain 0, don't allow picking domain 0 here, + * even if bytes 4 and 5 of the instance GUID are both zero. For wider + * userspace compatibility, limit the domain ID to a 16-bit value. */ 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) { + dom = pci_bus_find_emul_domain_nr(dom_req, 1, U16_MAX); + if (dom < 0) { dev_err(&hdev->device, "Unable to use dom# 0x%x or other numbers", dom_req); ret = -EINVAL; @@ -3795,7 +3878,7 @@ close: destroy_wq: destroy_workqueue(hbus->wq); free_dom: - hv_put_dom_num(hbus->bridge->domain_nr); + pci_bus_release_emul_domain_nr(hbus->bridge->domain_nr); free_bus: kfree(hbus); return ret; @@ -3809,6 +3892,7 @@ static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs) struct pci_packet teardown_packet; u8 buffer[sizeof(struct pci_message)]; } pkt; + struct pci_message *msg; struct hv_pci_compl comp_pkt; struct hv_pci_dev *hpdev, *tmp; unsigned long flags; @@ -3854,10 +3938,10 @@ static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs) 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; + msg = (struct pci_message *)pkt.buffer; + msg->type = PCI_BUS_D0EXIT; - ret = vmbus_sendpacket_getid(chan, &pkt.teardown_packet.message, - sizeof(struct pci_message), + ret = vmbus_sendpacket_getid(chan, msg, sizeof(*msg), (unsigned long)&pkt.teardown_packet, &trans_id, VM_PKT_DATA_INBAND, VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); @@ -3919,8 +4003,6 @@ static void hv_pci_remove(struct hv_device *hdev) irq_domain_remove(hbus->irq_domain); irq_domain_free_fwnode(hbus->fwnode); - hv_put_dom_num(hbus->bridge->domain_nr); - kfree(hbus); } @@ -3975,24 +4057,18 @@ 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); + guard(msi_descs_lock)(&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; - } - + if (WARN_ON_ONCE(!irq_data)) + return -EINVAL; hv_compose_msi_msg(irq_data, &entry->msg); } - msi_unlock_descs(&pdev->dev); - - return ret; + return 0; } /* @@ -4093,13 +4169,13 @@ static int __init init_hv_pci_drv(void) if (!hv_is_hyperv_initialized()) return -ENODEV; + if (hv_root_partition() && !hv_nested) + 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; diff --git a/drivers/pci/controller/pci-ixp4xx.c b/drivers/pci/controller/pci-ixp4xx.c index acb85e0d5675..9fd401838bad 100644 --- a/drivers/pci/controller/pci-ixp4xx.c +++ b/drivers/pci/controller/pci-ixp4xx.c @@ -214,6 +214,7 @@ static u32 ixp4xx_crp_byte_lane_enable_bits(u32 n, int size) return 0xffffffff; } +#ifdef CONFIG_ARM static int ixp4xx_crp_read_config(struct ixp4xx_pci *p, int where, int size, u32 *value) { @@ -251,6 +252,7 @@ static int ixp4xx_crp_read_config(struct ixp4xx_pci *p, int where, int size, return PCIBIOS_SUCCESSFUL; } +#endif static int ixp4xx_crp_write_config(struct ixp4xx_pci *p, int where, int size, u32 value) @@ -470,6 +472,7 @@ static int ixp4xx_pci_parse_map_dma_ranges(struct ixp4xx_pci *p) return 0; } +#ifdef CONFIG_ARM /* Only used to get context for abort handling */ static struct ixp4xx_pci *ixp4xx_pci_abort_singleton; @@ -509,6 +512,7 @@ static int ixp4xx_pci_abort_handler(unsigned long addr, unsigned int fsr, return 0; } +#endif static int __init ixp4xx_pci_probe(struct platform_device *pdev) { @@ -555,10 +559,12 @@ static int __init ixp4xx_pci_probe(struct platform_device *pdev) dev_info(dev, "controller is in %s mode\n", p->host_mode ? "host" : "option"); +#ifdef CONFIG_ARM /* 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"); +#endif ret = ixp4xx_pci_parse_map_ranges(p); if (ret) diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c index 29fe09c99e7d..a72aa57591c0 100644 --- a/drivers/pci/controller/pci-mvebu.c +++ b/drivers/pci/controller/pci-mvebu.c @@ -1078,9 +1078,9 @@ static int mvebu_pcie_init_irq_domain(struct mvebu_pcie_port *port) return -ENODEV; } - port->intx_irq_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, - &mvebu_pcie_intx_irq_domain_ops, - port); + port->intx_irq_domain = irq_domain_create_linear(of_fwnode_handle(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); @@ -1168,48 +1168,27 @@ static void __iomem *mvebu_pcie_map_registers(struct platform_device *pdev, 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; + struct of_range range; + struct of_range_parser parser; *tgt = -1; *attr = -1; - range = of_get_property(np, "ranges", &rlen); - if (!range) + if (of_pci_range_parser_init(&parser, np)) 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; + for_each_of_range(&parser, &range) { + u32 slot = upper_32_bits(range.bus_addr); - if (slot == PCI_SLOT(devfn) && type == rtype) { - *tgt = DT_CPUADDR_TO_TARGET(cpuaddr); - *attr = DT_CPUADDR_TO_ATTR(cpuaddr); + if (slot == PCI_SLOT(devfn) && + type == (range.flags & IORESOURCE_TYPE_BITS)) { + *tgt = (range.parent_bus_addr >> 56) & 0xFF; + *attr = (range.parent_bus_addr >> 48) & 0xFF; return 0; } } @@ -1361,11 +1340,9 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie, goto skip; } - ret = devm_add_action(dev, mvebu_pcie_port_clk_put, port); - if (ret < 0) { - clk_put(port->clk); + ret = devm_add_action_or_reset(dev, mvebu_pcie_port_clk_put, port); + if (ret < 0) goto err; - } return 1; @@ -1422,7 +1399,7 @@ static void mvebu_pcie_powerdown(struct mvebu_pcie_port *port) } /* - * devm_of_pci_get_host_bridge_resources() only sets up translateable resources, + * devm_of_pci_get_host_bridge_resources() only sets up translatable resources, * so we need extra resource setup parsing our special DT properties encoding * the MEM and IO apertures. */ @@ -1715,6 +1692,7 @@ static const struct of_device_id mvebu_pcie_of_match_table[] = { { .compatible = "marvell,kirkwood-pcie", }, {}, }; +MODULE_DEVICE_TABLE(of, mvebu_pcie_of_match_table); static const struct dev_pm_ops mvebu_pcie_pm_ops = { NOIRQ_SYSTEM_SLEEP_PM_OPS(mvebu_pcie_suspend, mvebu_pcie_resume) @@ -1727,7 +1705,7 @@ static struct platform_driver mvebu_pcie_driver = { .pm = &mvebu_pcie_pm_ops, }, .probe = mvebu_pcie_probe, - .remove_new = mvebu_pcie_remove, + .remove = mvebu_pcie_remove, }; module_platform_driver(mvebu_pcie_driver); diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c index d7517c3976e7..942ddfca3bf6 100644 --- a/drivers/pci/controller/pci-tegra.c +++ b/drivers/pci/controller/pci-tegra.c @@ -14,6 +14,7 @@ */ #include <linux/clk.h> +#include <linux/cleanup.h> #include <linux/debugfs.h> #include <linux/delay.h> #include <linux/export.h> @@ -22,6 +23,7 @@ #include <linux/iopoll.h> #include <linux/irq.h> #include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/kernel.h> #include <linux/init.h> @@ -269,7 +271,7 @@ struct tegra_msi { DECLARE_BITMAP(used, INT_PCI_MSI_NR); struct irq_domain *domain; struct mutex map_lock; - spinlock_t mask_lock; + raw_spinlock_t mask_lock; void *virt; dma_addr_t phys; int irq; @@ -1343,7 +1345,7 @@ static int tegra_pcie_port_get_phys(struct tegra_pcie_port *port) unsigned int i; int err; - port->phys = devm_kcalloc(dev, sizeof(phy), port->lanes, GFP_KERNEL); + port->phys = devm_kcalloc(dev, port->lanes, sizeof(phy), GFP_KERNEL); if (!port->phys) return -ENOMEM; @@ -1460,7 +1462,7 @@ static int tegra_pcie_get_resources(struct tegra_pcie *pcie) pcie->cs = *res; /* constrain configuration space to 4 KiB */ - pcie->cs.end = pcie->cs.start + SZ_4K - 1; + resource_set_size(&pcie->cs, SZ_4K); pcie->cfg = devm_ioremap_resource(dev, &pcie->cs); if (IS_ERR(pcie->cfg)) { @@ -1547,7 +1549,7 @@ static void tegra_pcie_msi_irq(struct irq_desc *desc) unsigned int index = i * 32 + offset; int ret; - ret = generic_handle_domain_irq(msi->domain->parent, index); + ret = generic_handle_domain_irq(msi->domain, index); if (ret) { /* * that's weird who triggered this? @@ -1565,30 +1567,6 @@ static void tegra_pcie_msi_irq(struct irq_desc *desc) 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); @@ -1604,14 +1582,13 @@ 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); + scoped_guard(raw_spinlock_irqsave, &msi->mask_lock) { + value = afi_readl(pcie, AFI_MSI_EN_VEC(index)); + value &= ~BIT(d->hwirq % 32); + afi_writel(pcie, value, AFI_MSI_EN_VEC(index)); + } } static void tegra_msi_irq_unmask(struct irq_data *d) @@ -1619,14 +1596,13 @@ 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); + scoped_guard(raw_spinlock_irqsave, &msi->mask_lock) { + value = afi_readl(pcie, AFI_MSI_EN_VEC(index)); + value |= BIT(d->hwirq % 32); + afi_writel(pcie, value, AFI_MSI_EN_VEC(index)); + } } static void tegra_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) @@ -1690,42 +1666,40 @@ static const struct irq_domain_ops tegra_msi_domain_ops = { .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_NO_AFFINITY | MSI_FLAG_PCI_MSIX, - .chip = &tegra_msi_top_chip, +static const struct msi_parent_ops tegra_msi_parent_ops = { + .supported_flags = (MSI_GENERIC_FLAGS_MASK | + MSI_FLAG_PCI_MSIX), + .required_flags = (MSI_FLAG_USE_DEF_DOM_OPS | + MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSI_MASK_PARENT | + MSI_FLAG_NO_AFFINITY), + .chip_flags = MSI_CHIP_FLAG_SET_ACK, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; 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); + struct irq_domain_info info = { + .fwnode = fwnode, + .ops = &tegra_msi_domain_ops, + .size = INT_PCI_MSI_NR, + .host_data = msi, + }; - msi->domain = pci_msi_create_irq_domain(fwnode, &tegra_msi_info, parent); + msi->domain = msi_create_parent_irq_domain(&info, &tegra_msi_parent_ops); 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) @@ -1736,7 +1710,7 @@ static int tegra_pcie_msi_setup(struct tegra_pcie *pcie) int err; mutex_init(&msi->map_lock); - spin_lock_init(&msi->mask_lock); + raw_spin_lock_init(&msi->mask_lock); if (IS_ENABLED(CONFIG_PCI_MSI)) { err = tegra_allocate_domains(msi); @@ -2106,47 +2080,39 @@ static int tegra_pcie_get_regulators(struct tegra_pcie *pcie, u32 lane_mask) static int tegra_pcie_parse_dt(struct tegra_pcie *pcie) { struct device *dev = pcie->dev; - struct device_node *np = dev->of_node, *port; + struct device_node *np = dev->of_node; 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) { + for_each_child_of_node_scoped(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; - } + if (err < 0) + return dev_err_probe(dev, err, "failed to parse address\n"); 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; - } + if (index < 1 || index > soc->num_ports) + return dev_err_probe(dev, -EINVAL, + "invalid port number: %d\n", index); 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 (err < 0) + return dev_err_probe(dev, err, + "failed to parse # of lanes\n"); - if (value > 16) { - dev_err(dev, "invalid # of lanes: %u\n", value); - err = -EINVAL; - goto err_node_put; - } + if (value > 16) + return dev_err_probe(dev, -EINVAL, + "invalid # of lanes: %u\n", value); lanes |= value << (index << 3); @@ -2159,16 +2125,12 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie) lane += value; rp = devm_kzalloc(dev, sizeof(*rp), GFP_KERNEL); - if (!rp) { - err = -ENOMEM; - goto err_node_put; - } + if (!rp) + return -ENOMEM; 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; - } + if (err < 0) + return dev_err_probe(dev, err, "failed to parse address\n"); INIT_LIST_HEAD(&rp->list); rp->index = index; @@ -2177,16 +2139,12 @@ static int tegra_pcie_parse_dt(struct tegra_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; - } + if (IS_ERR(rp->base)) + return PTR_ERR(rp->base); label = devm_kasprintf(dev, GFP_KERNEL, "pex-reset-%u", index); - if (!label) { - err = -ENOMEM; - goto err_node_put; - } + if (!label) + return -ENOMEM; /* * Returns -ENOENT if reset-gpios property is not populated @@ -2199,34 +2157,26 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie) GPIOD_OUT_LOW, label); if (IS_ERR(rp->reset_gpio)) { - if (PTR_ERR(rp->reset_gpio) == -ENOENT) { + 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; - } + else + return dev_err_probe(dev, PTR_ERR(rp->reset_gpio), + "failed to get reset GPIO\n"); } 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; - } + if (err < 0) + return dev_err_probe(dev, err, + "invalid lane configuration\n"); err = tegra_pcie_get_regulators(pcie, mask); if (err < 0) return err; return 0; - -err_node_put: - of_node_put(port); - return err; } /* @@ -2800,6 +2750,6 @@ static struct platform_driver tegra_pcie_driver = { .pm = &tegra_pcie_pm_ops, }, .probe = tegra_pcie_probe, - .remove_new = tegra_pcie_remove, + .remove = tegra_pcie_remove, }; module_platform_driver(tegra_pcie_driver); diff --git a/drivers/pci/controller/pci-thunder-ecam.c b/drivers/pci/controller/pci-thunder-ecam.c index b5bd10a62adb..b5b4a958e6a2 100644 --- a/drivers/pci/controller/pci-thunder-ecam.c +++ b/drivers/pci/controller/pci-thunder-ecam.c @@ -11,6 +11,8 @@ #include <linux/pci-ecam.h> #include <linux/platform_device.h> +#include "pci-host-common.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) @@ -204,7 +206,7 @@ static int thunder_ecam_config_read(struct pci_bus *bus, unsigned int devfn, v = readl(addr); if (v & 0xff00) - pr_err("Bad MSIX cap header: %08x\n", v); + pr_err("Bad MSI-X cap header: %08x\n", v); v |= 0xbc00; /* next capability is EA at 0xbc */ set_val(v, where, size, val); return PCIBIOS_SUCCESSFUL; diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c index 06a9855cb431..5fa037fb61dc 100644 --- a/drivers/pci/controller/pci-thunder-pem.c +++ b/drivers/pci/controller/pci-thunder-pem.c @@ -14,6 +14,7 @@ #include <linux/platform_device.h> #include <linux/io-64-nonatomic-lo-hi.h> #include "../pci.h" +#include "pci-host-common.h" #if defined(CONFIG_PCI_HOST_THUNDER_PEM) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)) @@ -400,9 +401,9 @@ static int thunder_pem_acpi_init(struct pci_config_window *cfg) * 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; + resource_set_size(res_pem, SZ_64K); thunder_pem_reserve_range(dev, root->segment, res_pem); - res_pem->end = res_pem->start + SZ_16M - 1; + resource_set_size(res_pem, SZ_16M); /* Reserve PCI configuration space as well. */ thunder_pem_reserve_range(dev, root->segment, &cfg->res); diff --git a/drivers/pci/controller/pci-xgene-msi.c b/drivers/pci/controller/pci-xgene-msi.c index 3ce38dfd0d29..654639bccd10 100644 --- a/drivers/pci/controller/pci-xgene-msi.c +++ b/drivers/pci/controller/pci-xgene-msi.c @@ -6,12 +6,14 @@ * Author: Tanmay Inamdar <tinamdar@apm.com> * Duc Dang <dhdang@apm.com> */ +#include <linux/bitfield.h> #include <linux/cpu.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> #include <linux/module.h> #include <linux/msi.h> #include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/pci.h> #include <linux/platform_device.h> #include <linux/of_pci.h> @@ -21,46 +23,49 @@ #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) +#define NR_MSI_BITS (IDX_PER_GROUP * IRQS_PER_IDX * NR_HW_IRQS) +#define NR_MSI_VEC (NR_MSI_BITS / num_possible_cpus()) -struct xgene_msi_group { - struct xgene_msi *msi; - int gic_irq; - u32 msi_grp; -}; +#define MSI_GROUP_MASK GENMASK(22, 19) +#define MSI_INDEX_MASK GENMASK(18, 16) +#define MSI_INTR_MASK GENMASK(19, 16) + +#define MSInRx_HWIRQ_MASK GENMASK(6, 4) +#define DATA_HWIRQ_MASK GENMASK(3, 0) 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; + unsigned int gic_irq[NR_HW_IRQS]; }; /* 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, -}; +static struct xgene_msi *xgene_msi_ctrl; /* - * 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) + * X-Gene v1 has 16 frames of MSI termination registers MSInIRx, where n is + * frame number (0..15), x is index of registers in each frame (0..7). Each + * 32b register is at the beginning of a 64kB region, each frame occupying + * 512kB (and the whole thing 8MB of PA space). + * + * Each register supports 16 MSI vectors (0..15) to generate interrupts. A + * write to the MSInIRx from the PCI side generates an interrupt. A read + * from the MSInRx on the CPU side returns a bitmap of the pending MSIs in + * the lower 16 bits. A side effect of this read is that all pending + * interrupts are acknowledged and cleared). + * + * Additionally, each MSI termination frame has 1 MSIINTn register (n is + * 0..15) to indicate the MSI pending status caused by any of its 8 + * termination registers, reported as a bitmap in the lower 8 bits. Each 32b + * register is at the beginning of a 64kB region (and overall occupying an + * extra 1MB). + * + * There is one GIC IRQ assigned for each MSI termination frame, 16 in + * total. + * * The register layout is as follows: * MSI0IR0 base_addr * MSI0IR1 base_addr + 0x10000 @@ -81,107 +86,74 @@ static struct msi_domain_info xgene_msi_domain_info = { * 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) +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)); + (FIELD_PREP(MSI_GROUP_MASK, msi_grp) | + FIELD_PREP(MSI_INDEX_MASK, msir_idx))); } /* 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)); + return readl_relaxed(msi->msi_regs + MSI_INT0 + + FIELD_PREP(MSI_INTR_MASK, msi_grp)); } /* - * 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 + * In order to allow an MSI to be moved from one CPU to another without + * having to repaint both the address and the data (which cannot be done + * atomically), we statically partitions the MSI frames between CPUs. Given + * that XGene-1 has 8 CPUs, each CPU gets two frames assigned to it + * + * We adopt the convention that when an MSI is moved, it is configured to + * target the same register number in the congruent frame assigned to the + * new target CPU. This reserves a given MSI across all CPUs, and reduces + * the MSI capacity from 2048 to 256. + * + * Effectively, this amounts to: + * - hwirq[7]::cpu[2:0] is the target frame number (n in MSInIRx) + * - hwirq[6:4] is the register index in any given frame (x in MSInIRx) + * - hwirq[3:0] is the MSI data */ -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) +static irq_hw_number_t compute_hwirq(u8 frame, u8 index, u8 data) { - return ((hwirq / NR_HW_IRQS) % IRQS_PER_IDX); + return (FIELD_PREP(BIT(7), FIELD_GET(BIT(3), frame)) | + FIELD_PREP(MSInRx_HWIRQ_MASK, index) | + FIELD_PREP(DATA_HWIRQ_MASK, data)); } 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); + u64 target_addr; + u32 frame, msir; + int cpu; - msg->address_hi = upper_32_bits(target_addr); - msg->address_lo = lower_32_bits(target_addr); - msg->data = hwirq_to_msi_data(data->hwirq); -} + cpu = cpumask_first(irq_data_get_effective_affinity_mask(data)); + msir = FIELD_GET(MSInRx_HWIRQ_MASK, data->hwirq); + frame = FIELD_PREP(BIT(3), FIELD_GET(BIT(7), data->hwirq)) | cpu; -/* - * 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); -} + target_addr = msi->msi_addr; + target_addr += (FIELD_PREP(MSI_GROUP_MASK, frame) | + FIELD_PREP(MSI_INTR_MASK, msir)); -static unsigned long hwirq_to_canonical_hwirq(unsigned long hwirq) -{ - return (hwirq - hwirq_to_cpu(hwirq)); + msg->address_hi = upper_32_bits(target_addr); + msg->address_lo = lower_32_bits(target_addr); + msg->data = FIELD_GET(DATA_HWIRQ_MASK, data->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; + irq_data_update_effective_affinity(irqdata, cpumask_of(target_cpu)); + /* Force the core code to regenerate the message */ return IRQ_SET_MASK_OK; } @@ -195,25 +167,23 @@ 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; + irq_hw_number_t hwirq; 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; + hwirq = find_first_zero_bit(msi->bitmap, NR_MSI_VEC); + if (hwirq < NR_MSI_VEC) + set_bit(hwirq, msi->bitmap); mutex_unlock(&msi->bitmap_lock); - if (msi_irq < 0) - return msi_irq; + if (hwirq >= NR_MSI_VEC) + return -ENOSPC; - irq_domain_set_info(domain, virq, msi_irq, + irq_domain_set_info(domain, virq, hwirq, &xgene_msi_bottom_irq_chip, domain->host_data, handle_simple_irq, NULL, NULL); + irqd_set_resend_when_in_progress(irq_get_irq_data(virq)); return 0; } @@ -223,204 +193,149 @@ static void xgene_irq_domain_free(struct irq_domain *domain, { 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); + clear_bit(d->hwirq, msi->bitmap); mutex_unlock(&msi->bitmap_lock); irq_domain_free_irqs_parent(domain, virq, nr_irqs); } -static const struct irq_domain_ops msi_domain_ops = { +static const struct irq_domain_ops xgene_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 const struct msi_parent_ops xgene_msi_parent_ops = { + .supported_flags = (MSI_GENERIC_FLAGS_MASK | + MSI_FLAG_PCI_MSIX), + .required_flags = (MSI_FLAG_USE_DEF_DOM_OPS | + MSI_FLAG_USE_DEF_CHIP_OPS), + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .init_dev_msi_info = msi_lib_init_dev_msi_info, +}; -static void xgene_free_domains(struct xgene_msi *msi) +static int xgene_allocate_domains(struct device_node *node, + struct xgene_msi *msi) { - if (msi->msi_domain) - irq_domain_remove(msi->msi_domain); - if (msi->inner_domain) - irq_domain_remove(msi->inner_domain); + struct irq_domain_info info = { + .fwnode = of_fwnode_handle(node), + .ops = &xgene_msi_domain_ops, + .size = NR_MSI_VEC, + .host_data = msi, + }; + + msi->inner_domain = msi_create_parent_irq_domain(&info, &xgene_msi_parent_ops); + return msi->inner_domain ? 0 : -ENOMEM; } -static int xgene_msi_init_allocator(struct xgene_msi *xgene_msi) +static int xgene_msi_init_allocator(struct device *dev) { - xgene_msi->bitmap = bitmap_zalloc(NR_MSI_VEC, GFP_KERNEL); - if (!xgene_msi->bitmap) + xgene_msi_ctrl->bitmap = devm_bitmap_zalloc(dev, NR_MSI_VEC, GFP_KERNEL); + if (!xgene_msi_ctrl->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; + mutex_init(&xgene_msi_ctrl->bitmap_lock); return 0; } static void xgene_msi_isr(struct irq_desc *desc) { + unsigned int *irqp = irq_desc_get_handler_data(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; + struct xgene_msi *xgene_msi = xgene_msi_ctrl; + unsigned long grp_pending; + int msir_idx; + u32 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); + msi_grp = irqp - xgene_msi->gic_irq; + + grp_pending = xgene_msi_int_read(xgene_msi, msi_grp); + + for_each_set_bit(msir_idx, &grp_pending, IDX_PER_GROUP) { + unsigned long msir; + int intr_idx; + + msir = xgene_msi_ir_read(xgene_msi, msi_grp, msir_idx); + + for_each_set_bit(intr_idx, &msir, IRQS_PER_IDX) { + irq_hw_number_t hwirq; + int ret; + + hwirq = compute_hwirq(msi_grp, msir_idx, intr_idx); + ret = generic_handle_domain_irq(xgene_msi->inner_domain, + hwirq); 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 void 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; + for (int i = 0; i < NR_HW_IRQS; i++) { + unsigned int irq = xgene_msi_ctrl->gic_irq[i]; + if (!irq) + continue; + irq_set_chained_handler_and_data(irq, NULL, NULL); + } - xgene_free_domains(msi); + if (xgene_msi_ctrl->inner_domain) + irq_domain_remove(xgene_msi_ctrl->inner_domain); } -static int xgene_msi_hwirq_alloc(unsigned int cpu) +static int xgene_msi_handler_setup(struct platform_device *pdev) { - struct xgene_msi *msi = &xgene_msi_ctrl; - struct xgene_msi_group *msi_group; - cpumask_var_t mask; + struct xgene_msi *xgene_msi = xgene_msi_ctrl; 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; + for (i = 0; i < NR_HW_IRQS; i++) { + u32 msi_val; + int irq, err; + + /* + * 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 (int msi_idx = 0; msi_idx < IDX_PER_GROUP; msi_idx++) + xgene_msi_ir_read(xgene_msi, i, msi_idx); + + /* Read MSIINTn to confirm */ + msi_val = xgene_msi_int_read(xgene_msi, i); + if (msi_val) { + dev_err(&pdev->dev, "Failed to clear spurious IRQ\n"); + return -EINVAL; + } - irq_set_chained_handler_and_data(msi_group->gic_irq, - xgene_msi_isr, msi_group); + irq = platform_get_irq(pdev, i); + if (irq < 0) + return irq; + + xgene_msi->gic_irq[i] = irq; /* * 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; - } - + irq_set_status_flags(irq, IRQ_NO_BALANCING); + err = irq_set_affinity(irq, cpumask_of(i % num_possible_cpus())); if (err) { - irq_set_chained_handler_and_data(msi_group->gic_irq, - NULL, NULL); + pr_err("failed to set affinity for GIC IRQ"); 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); + irq_set_chained_handler_and_data(irq, xgene_msi_isr, + &xgene_msi_ctrl->gic_irq[i]); } + return 0; } @@ -432,14 +347,15 @@ static const struct of_device_id xgene_msi_match_table[] = { 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; + int rc; - xgene_msi = &xgene_msi_ctrl; + xgene_msi_ctrl = devm_kzalloc(&pdev->dev, sizeof(*xgene_msi_ctrl), + GFP_KERNEL); + if (!xgene_msi_ctrl) + return -ENOMEM; - platform_set_drvdata(pdev, xgene_msi); + xgene_msi = xgene_msi_ctrl; xgene_msi->msi_regs = devm_platform_get_and_ioremap_resource(pdev, 0, &res); if (IS_ERR(xgene_msi->msi_regs)) { @@ -447,66 +363,26 @@ static int xgene_msi_probe(struct platform_device *pdev) 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); + rc = xgene_msi_init_allocator(&pdev->dev); if (rc) { dev_err(&pdev->dev, "Error allocating MSI bitmap\n"); goto error; } - rc = xgene_allocate_domains(xgene_msi); + rc = xgene_allocate_domains(dev_of_node(&pdev->dev), 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); + rc = xgene_msi_handler_setup(pdev); if (rc) - goto err_cpuhp; + goto error; 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; @@ -518,11 +394,6 @@ static struct platform_driver xgene_msi_driver = { .of_match_table = xgene_msi_match_table, }, .probe = xgene_msi_probe, - .remove_new = xgene_msi_remove, + .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); +builtin_platform_driver(xgene_msi_driver); diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c index 1e2ebbfa36d1..b95afa35201d 100644 --- a/drivers/pci/controller/pci-xgene.c +++ b/drivers/pci/controller/pci-xgene.c @@ -12,6 +12,7 @@ #include <linux/jiffies.h> #include <linux/memblock.h> #include <linux/init.h> +#include <linux/irqdomain.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_pci.h> @@ -53,11 +54,9 @@ #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; @@ -188,7 +187,6 @@ static int xgene_pcie_config_read32(struct pci_bus *bus, unsigned int devfn, return PCIBIOS_SUCCESSFUL; } -#endif #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) static int xgene_get_csr_resource(struct acpi_device *adev, @@ -279,7 +277,6 @@ const struct pci_ecam_ops xgene_v2_pcie_ecam_ops = { }; #endif -#if defined(CONFIG_PCI_XGENE) static u64 xgene_pcie_set_ib_mask(struct xgene_pcie *port, u32 addr, u32 flags, u64 size) { @@ -594,6 +591,24 @@ static struct pci_ops xgene_pcie_ops = { .write = pci_generic_config_write32, }; +static bool xgene_check_pcie_msi_ready(void) +{ + struct device_node *np; + struct irq_domain *d; + + if (!IS_ENABLED(CONFIG_PCI_XGENE_MSI)) + return true; + + np = of_find_compatible_node(NULL, NULL, "apm,xgene1-msi"); + if (!np) + return true; + + d = irq_find_matching_host(np, DOMAIN_BUS_PCI_MSI); + of_node_put(np); + + return d && irq_domain_is_msi_parent(d); +} + static int xgene_pcie_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; @@ -602,6 +617,10 @@ static int xgene_pcie_probe(struct platform_device *pdev) struct pci_host_bridge *bridge; int ret; + if (!xgene_check_pcie_msi_ready()) + return dev_err_probe(&pdev->dev, -EPROBE_DEFER, + "MSI driver not ready\n"); + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*port)); if (!bridge) return -ENOMEM; @@ -610,10 +629,7 @@ static int xgene_pcie_probe(struct platform_device *pdev) 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; + port->version = XGENE_PCIE_IP_VER_1; ret = xgene_pcie_map_reg(port, pdev); if (ret) @@ -647,4 +663,3 @@ static struct platform_driver xgene_pcie_driver = { .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 index e36a6e158d23..ea2ca2e70f20 100644 --- a/drivers/pci/controller/pcie-altera-msi.c +++ b/drivers/pci/controller/pcie-altera-msi.c @@ -9,6 +9,7 @@ #include <linux/interrupt.h> #include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/init.h> #include <linux/module.h> @@ -29,7 +30,6 @@ 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; @@ -74,18 +74,20 @@ static void altera_msi_isr(struct irq_desc *desc) 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, -}; +#define ALTERA_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) -static struct msi_domain_info altera_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_NO_AFFINITY | MSI_FLAG_PCI_MSIX, - .chip = &altera_msi_irq_chip, -}; +#define ALTERA_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_PCI_MSIX) +static const struct msi_parent_ops altera_msi_parent_ops = { + .required_flags = ALTERA_MSI_FLAGS_REQUIRED, + .supported_flags = ALTERA_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .prefix = "Altera-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, +}; 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); @@ -164,20 +166,16 @@ static const struct irq_domain_ops msi_domain_ops = { 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); + struct irq_domain_info info = { + .fwnode = dev_fwnode(&msi->pdev->dev), + .ops = &msi_domain_ops, + .host_data = msi, + .size = msi->num_of_vectors, + }; + + msi->inner_domain = msi_create_parent_irq_domain(&info, &altera_msi_parent_ops); 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; } @@ -186,7 +184,6 @@ static int altera_allocate_domains(struct altera_msi *msi) static void altera_free_domains(struct altera_msi *msi) { - irq_domain_remove(msi->msi_domain); irq_domain_remove(msi->inner_domain); } @@ -267,7 +264,7 @@ static struct platform_driver altera_msi_driver = { .of_match_table = altera_msi_of_match, }, .probe = altera_msi_probe, - .remove_new = altera_msi_remove, + .remove = altera_msi_remove, }; static int __init altera_msi_init(void) diff --git a/drivers/pci/controller/pcie-altera.c b/drivers/pci/controller/pcie-altera.c index 650b2dd81c48..3dbb7adc421c 100644 --- a/drivers/pci/controller/pcie-altera.c +++ b/drivers/pci/controller/pcie-altera.c @@ -6,6 +6,7 @@ * Description: Altera PCIe host controller driver */ +#include <linux/bitfield.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/irqchip/chained_irq.h> @@ -77,9 +78,25 @@ #define S10_TLP_FMTTYPE_CFGWR0 0x45 #define S10_TLP_FMTTYPE_CFGWR1 0x44 +#define AGLX_RP_CFG_ADDR(pcie, reg) (((pcie)->hip_base) + (reg)) +#define AGLX_RP_SECONDARY(pcie) \ + readb(AGLX_RP_CFG_ADDR(pcie, PCI_SECONDARY_BUS)) + +#define AGLX_BDF_REG 0x00002004 +#define AGLX_ROOT_PORT_IRQ_STATUS 0x14c +#define AGLX_ROOT_PORT_IRQ_ENABLE 0x150 +#define CFG_AER BIT(4) + +#define AGLX_CFG_TARGET GENMASK(13, 12) +#define AGLX_CFG_TARGET_TYPE0 0 +#define AGLX_CFG_TARGET_TYPE1 1 +#define AGLX_CFG_TARGET_LOCAL_2000 2 +#define AGLX_CFG_TARGET_LOCAL_3000 3 + enum altera_pcie_version { ALTERA_PCIE_V1 = 0, ALTERA_PCIE_V2, + ALTERA_PCIE_V3, }; struct altera_pcie { @@ -102,6 +119,11 @@ struct altera_pcie_ops { int size, u32 *value); int (*rp_write_cfg)(struct altera_pcie *pcie, u8 busno, int where, int size, u32 value); + int (*ep_read_cfg)(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int where, int size, u32 *value); + int (*ep_write_cfg)(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int where, int size, u32 value); + void (*rp_isr)(struct irq_desc *desc); }; struct altera_pcie_data { @@ -112,6 +134,9 @@ struct altera_pcie_data { u32 cfgrd1; u32 cfgwr0; u32 cfgwr1; + u32 port_conf_offset; + u32 port_irq_status_offset; + u32 port_irq_enable_offset; }; struct tlp_rp_regpair_t { @@ -131,6 +156,28 @@ static inline u32 cra_readl(struct altera_pcie *pcie, const u32 reg) return readl_relaxed(pcie->cra_base + reg); } +static inline void cra_writew(struct altera_pcie *pcie, const u32 value, + const u32 reg) +{ + writew_relaxed(value, pcie->cra_base + reg); +} + +static inline u32 cra_readw(struct altera_pcie *pcie, const u32 reg) +{ + return readw_relaxed(pcie->cra_base + reg); +} + +static inline void cra_writeb(struct altera_pcie *pcie, const u32 value, + const u32 reg) +{ + writeb_relaxed(value, pcie->cra_base + reg); +} + +static inline u32 cra_readb(struct altera_pcie *pcie, const u32 reg) +{ + return readb_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); @@ -145,11 +192,20 @@ static bool s10_altera_pcie_link_up(struct altera_pcie *pcie) return !!(readw(addr) & PCI_EXP_LNKSTA_DLLLA); } +static bool aglx_altera_pcie_link_up(struct altera_pcie *pcie) +{ + void __iomem *addr = AGLX_RP_CFG_ADDR(pcie, + pcie->pcie_data->cap_offset + + PCI_EXP_LNKSTA); + + return (readw_relaxed(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 + * This BAR0 will also access to MSI vector when receiving MSI/MSI-X 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. @@ -425,6 +481,103 @@ static int s10_rp_write_cfg(struct altera_pcie *pcie, u8 busno, return PCIBIOS_SUCCESSFUL; } +static int aglx_rp_read_cfg(struct altera_pcie *pcie, int where, + int size, u32 *value) +{ + void __iomem *addr = AGLX_RP_CFG_ADDR(pcie, where); + + switch (size) { + case 1: + *value = readb_relaxed(addr); + break; + case 2: + *value = readw_relaxed(addr); + break; + default: + *value = readl_relaxed(addr); + break; + } + + /* Interrupt PIN not programmed in hardware, set to INTA. */ + if (where == PCI_INTERRUPT_PIN && size == 1 && !(*value)) + *value = 0x01; + else if (where == PCI_INTERRUPT_LINE && !(*value & 0xff00)) + *value |= 0x0100; + + return PCIBIOS_SUCCESSFUL; +} + +static int aglx_rp_write_cfg(struct altera_pcie *pcie, u8 busno, + int where, int size, u32 value) +{ + void __iomem *addr = AGLX_RP_CFG_ADDR(pcie, where); + + switch (size) { + case 1: + writeb_relaxed(value, addr); + break; + case 2: + writew_relaxed(value, addr); + break; + default: + writel_relaxed(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 aglx_ep_write_cfg(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int where, int size, u32 value) +{ + cra_writel(pcie, ((busno << 8) | devfn), AGLX_BDF_REG); + if (busno > AGLX_RP_SECONDARY(pcie)) + where |= FIELD_PREP(AGLX_CFG_TARGET, AGLX_CFG_TARGET_TYPE1); + + switch (size) { + case 1: + cra_writeb(pcie, value, where); + break; + case 2: + cra_writew(pcie, value, where); + break; + default: + cra_writel(pcie, value, where); + break; + } + + return PCIBIOS_SUCCESSFUL; +} + +static int aglx_ep_read_cfg(struct altera_pcie *pcie, u8 busno, + unsigned int devfn, int where, int size, u32 *value) +{ + cra_writel(pcie, ((busno << 8) | devfn), AGLX_BDF_REG); + if (busno > AGLX_RP_SECONDARY(pcie)) + where |= FIELD_PREP(AGLX_CFG_TARGET, AGLX_CFG_TARGET_TYPE1); + + switch (size) { + case 1: + *value = cra_readb(pcie, where); + break; + case 2: + *value = cra_readw(pcie, where); + break; + default: + *value = cra_readl(pcie, where); + break; + } + + return PCIBIOS_SUCCESSFUL; +} + static int _altera_pcie_cfg_read(struct altera_pcie *pcie, u8 busno, unsigned int devfn, int where, int size, u32 *value) @@ -437,6 +590,10 @@ static int _altera_pcie_cfg_read(struct altera_pcie *pcie, u8 busno, return pcie->pcie_data->ops->rp_read_cfg(pcie, where, size, value); + if (pcie->pcie_data->ops->ep_read_cfg) + return pcie->pcie_data->ops->ep_read_cfg(pcie, busno, devfn, + where, size, value); + switch (size) { case 1: byte_en = 1 << (where & 3); @@ -481,6 +638,10 @@ static int _altera_pcie_cfg_write(struct altera_pcie *pcie, u8 busno, return pcie->pcie_data->ops->rp_write_cfg(pcie, busno, where, size, value); + if (pcie->pcie_data->ops->ep_write_cfg) + return pcie->pcie_data->ops->ep_write_cfg(pcie, busno, devfn, + where, size, value); + switch (size) { case 1: data32 = (value & 0xff) << shift; @@ -659,17 +820,41 @@ static void altera_pcie_isr(struct irq_desc *desc) dev_err_ratelimited(dev, "unexpected IRQ, INT%d\n", bit); } } + chained_irq_exit(chip, desc); +} + +static void aglx_isr(struct irq_desc *desc) +{ + struct irq_chip *chip = irq_desc_get_chip(desc); + struct altera_pcie *pcie; + struct device *dev; + u32 status; + int ret; + + chained_irq_enter(chip, desc); + pcie = irq_desc_get_handler_data(desc); + dev = &pcie->pdev->dev; + + status = readl(pcie->hip_base + pcie->pcie_data->port_conf_offset + + pcie->pcie_data->port_irq_status_offset); + if (status & CFG_AER) { + writel(CFG_AER, (pcie->hip_base + pcie->pcie_data->port_conf_offset + + pcie->pcie_data->port_irq_status_offset)); + + ret = generic_handle_domain_irq(pcie->irq_domain, 0); + if (ret) + dev_err_ratelimited(dev, "unexpected IRQ %d\n", pcie->irq); + } 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, + pcie->irq_domain = irq_domain_create_linear(dev_fwnode(dev), PCI_NUM_INTX, &intx_domain_ops, pcie); if (!pcie->irq_domain) { dev_err(dev, "Failed to get a INTx IRQ domain\n"); @@ -694,9 +879,9 @@ static int altera_pcie_parse_dt(struct altera_pcie *pcie) 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 (pcie->pcie_data->version == ALTERA_PCIE_V2 || + pcie->pcie_data->version == ALTERA_PCIE_V3) { + pcie->hip_base = devm_platform_ioremap_resource_byname(pdev, "Hip"); if (IS_ERR(pcie->hip_base)) return PTR_ERR(pcie->hip_base); } @@ -706,7 +891,7 @@ static int altera_pcie_parse_dt(struct altera_pcie *pcie) if (pcie->irq < 0) return pcie->irq; - irq_set_chained_handler_and_data(pcie->irq, altera_pcie_isr, pcie); + irq_set_chained_handler_and_data(pcie->irq, pcie->pcie_data->ops->rp_isr, pcie); return 0; } @@ -719,6 +904,7 @@ 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, + .rp_isr = altera_pcie_isr, }; static const struct altera_pcie_ops altera_pcie_ops_2_0 = { @@ -727,6 +913,16 @@ static const struct altera_pcie_ops altera_pcie_ops_2_0 = { .get_link_status = s10_altera_pcie_link_up, .rp_read_cfg = s10_rp_read_cfg, .rp_write_cfg = s10_rp_write_cfg, + .rp_isr = altera_pcie_isr, +}; + +static const struct altera_pcie_ops altera_pcie_ops_3_0 = { + .rp_read_cfg = aglx_rp_read_cfg, + .rp_write_cfg = aglx_rp_write_cfg, + .get_link_status = aglx_altera_pcie_link_up, + .ep_read_cfg = aglx_ep_read_cfg, + .ep_write_cfg = aglx_ep_write_cfg, + .rp_isr = aglx_isr, }; static const struct altera_pcie_data altera_pcie_1_0_data = { @@ -749,11 +945,44 @@ static const struct altera_pcie_data altera_pcie_2_0_data = { .cfgwr1 = S10_TLP_FMTTYPE_CFGWR1, }; +static const struct altera_pcie_data altera_pcie_3_0_f_tile_data = { + .ops = &altera_pcie_ops_3_0, + .version = ALTERA_PCIE_V3, + .cap_offset = 0x70, + .port_conf_offset = 0x14000, + .port_irq_status_offset = AGLX_ROOT_PORT_IRQ_STATUS, + .port_irq_enable_offset = AGLX_ROOT_PORT_IRQ_ENABLE, +}; + +static const struct altera_pcie_data altera_pcie_3_0_p_tile_data = { + .ops = &altera_pcie_ops_3_0, + .version = ALTERA_PCIE_V3, + .cap_offset = 0x70, + .port_conf_offset = 0x104000, + .port_irq_status_offset = AGLX_ROOT_PORT_IRQ_STATUS, + .port_irq_enable_offset = AGLX_ROOT_PORT_IRQ_ENABLE, +}; + +static const struct altera_pcie_data altera_pcie_3_0_r_tile_data = { + .ops = &altera_pcie_ops_3_0, + .version = ALTERA_PCIE_V3, + .cap_offset = 0x70, + .port_conf_offset = 0x1300, + .port_irq_status_offset = 0x0, + .port_irq_enable_offset = 0x4, +}; + 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 }, + {.compatible = "altr,pcie-root-port-3.0-f-tile", + .data = &altera_pcie_3_0_f_tile_data }, + {.compatible = "altr,pcie-root-port-3.0-p-tile", + .data = &altera_pcie_3_0_p_tile_data }, + {.compatible = "altr,pcie-root-port-3.0-r-tile", + .data = &altera_pcie_3_0_r_tile_data }, {}, }; @@ -791,11 +1020,18 @@ static int altera_pcie_probe(struct platform_device *pdev) 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); + if (pcie->pcie_data->version == ALTERA_PCIE_V1 || + pcie->pcie_data->version == ALTERA_PCIE_V2) { + /* 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); + } else if (pcie->pcie_data->version == ALTERA_PCIE_V3) { + writel(CFG_AER, + pcie->hip_base + pcie->pcie_data->port_conf_offset + + pcie->pcie_data->port_irq_enable_offset); + } bridge->sysdata = pcie; bridge->busnr = pcie->root_bus_nr; @@ -815,10 +1051,10 @@ static void altera_pcie_remove(struct platform_device *pdev) } static struct platform_driver altera_pcie_driver = { - .probe = altera_pcie_probe, - .remove_new = altera_pcie_remove, + .probe = altera_pcie_probe, + .remove = altera_pcie_remove, .driver = { - .name = "altera-pcie", + .name = "altera-pcie", .of_match_table = altera_pcie_of_match, }, }; diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c index fefab2758a06..2d92fc79f6dd 100644 --- a/drivers/pci/controller/pcie-apple.c +++ b/drivers/pci/controller/pcie-apple.c @@ -18,18 +18,22 @@ * Author: Marc Zyngier <maz@kernel.org> */ +#include <linux/bitfield.h> #include <linux/gpio/consumer.h> #include <linux/kernel.h> #include <linux/iopoll.h> #include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.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> +#include "pci-host-common.h" + +/* T8103 (original M1) and related SoCs */ #define CORE_RC_PHYIF_CTL 0x00024 #define CORE_RC_PHYIF_CTL_RUN BIT(0) #define CORE_RC_PHYIF_STAT 0x00028 @@ -40,14 +44,18 @@ #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 CORE_PHY_DEFAULT_BASE(port) (0x84000 + 0x4000 * (port)) + +#define PHY_LANE_CFG 0x00000 +#define PHY_LANE_CFG_REFCLK0REQ BIT(0) +#define PHY_LANE_CFG_REFCLK1REQ BIT(1) +#define PHY_LANE_CFG_REFCLK0ACK BIT(2) +#define PHY_LANE_CFG_REFCLK1ACK BIT(3) +#define PHY_LANE_CFG_REFCLKEN (BIT(9) | BIT(10)) +#define PHY_LANE_CFG_REFCLKCGEN (BIT(30) | BIT(31)) +#define PHY_LANE_CTL 0x00004 +#define PHY_LANE_CTL_CFGACC BIT(15) #define PORT_LTSSMCTL 0x00080 #define PORT_LTSSMCTL_START BIT(0) @@ -101,7 +109,7 @@ #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 0x00828 #define PORT_RID2SID_VALID BIT(31) #define PORT_RID2SID_SID_SHIFT 16 #define PORT_RID2SID_BUS_SHIFT 8 @@ -119,7 +127,15 @@ #define PORT_TUNSTAT_PERST_ACK_PEND BIT(1) #define PORT_PREFMEM_ENABLE 0x00994 -#define MAX_RID2SID 64 +/* T602x (M2-pro and co) */ +#define PORT_T602X_MSIADDR 0x016c +#define PORT_T602X_MSIADDR_HI 0x0170 +#define PORT_T602X_PERST 0x082c +#define PORT_T602X_RID2SID 0x3000 +#define PORT_T602X_MSIMAP 0x3800 + +#define PORT_MSIMAP_ENABLE BIT(31) +#define PORT_MSIMAP_TARGET GENMASK(7, 0) /* * The doorbell address is set to 0xfffff000, which by convention @@ -130,11 +146,45 @@ */ #define DOORBELL_ADDR CONFIG_PCIE_APPLE_MSI_DOORBELL_ADDR +struct hw_info { + u32 phy_lane_ctl; + u32 port_msiaddr; + u32 port_msiaddr_hi; + u32 port_refclk; + u32 port_perst; + u32 port_rid2sid; + u32 port_msimap; + u32 max_rid2sid; +}; + +static const struct hw_info t8103_hw = { + .phy_lane_ctl = PHY_LANE_CTL, + .port_msiaddr = PORT_MSIADDR, + .port_msiaddr_hi = 0, + .port_refclk = PORT_REFCLK, + .port_perst = PORT_PERST, + .port_rid2sid = PORT_RID2SID, + .port_msimap = 0, + .max_rid2sid = 64, +}; + +static const struct hw_info t602x_hw = { + .phy_lane_ctl = 0, + .port_msiaddr = PORT_T602X_MSIADDR, + .port_msiaddr_hi = PORT_T602X_MSIADDR_HI, + .port_refclk = 0, + .port_perst = PORT_T602X_PERST, + .port_rid2sid = PORT_T602X_RID2SID, + .port_msimap = PORT_T602X_MSIMAP, + /* 16 on t602x, guess for autodetect on future HW */ + .max_rid2sid = 512, +}; + struct apple_pcie { struct mutex lock; struct device *dev; void __iomem *base; - struct irq_domain *domain; + const struct hw_info *hw; unsigned long *bitmap; struct list_head ports; struct completion event; @@ -143,12 +193,14 @@ struct apple_pcie { }; struct apple_pcie_port { + raw_spinlock_t lock; struct apple_pcie *pcie; struct device_node *np; void __iomem *base; + void __iomem *phy; struct irq_domain *domain; struct list_head entry; - DECLARE_BITMAP(sid_map, MAX_RID2SID); + unsigned long *sid_map; int sid_map_sz; int idx; }; @@ -163,27 +215,6 @@ 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); @@ -227,8 +258,7 @@ static int apple_msi_domain_alloc(struct irq_domain *domain, unsigned int virq, 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); + &apple_msi_bottom_chip, pcie); } return 0; @@ -252,24 +282,20 @@ static const struct irq_domain_ops apple_msi_domain_ops = { .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); + guard(raw_spinlock_irqsave)(&port->lock); + rmw_set(BIT(data->hwirq), port->base + PORT_INTMSK); } 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); + guard(raw_spinlock_irqsave)(&port->lock); + rmw_clear(BIT(data->hwirq), port->base + PORT_INTMSK); } static bool hwirq_is_intx(unsigned int hwirq) @@ -373,7 +399,9 @@ static void apple_port_irq_handler(struct irq_desc *desc) static int apple_pcie_port_setup_irq(struct apple_pcie_port *port) { struct fwnode_handle *fwnode = &port->np->fwnode; + struct apple_pcie *pcie = port->pcie; unsigned int irq; + u32 val = 0; /* FIXME: consider moving each interrupt under each port */ irq = irq_of_parse_and_map(to_of_node(dev_fwnode(port->pcie->dev)), @@ -388,20 +416,31 @@ static int apple_pcie_port_setup_irq(struct apple_pcie_port *port) return -ENOMEM; /* Disable all interrupts */ - writel_relaxed(~0, port->base + PORT_INTMSKSET); + writel_relaxed(~0, port->base + PORT_INTMSK); writel_relaxed(~0, port->base + PORT_INTSTAT); + writel_relaxed(~0, port->base + PORT_LINKCMDSTS); 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); + writel_relaxed(lower_32_bits(DOORBELL_ADDR), + port->base + pcie->hw->port_msiaddr); + if (pcie->hw->port_msiaddr_hi) + writel_relaxed(0, port->base + pcie->hw->port_msiaddr_hi); /* 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); + if (pcie->hw->port_msimap) { + for (int i = 0; i < pcie->nvecs; i++) + writel_relaxed(FIELD_PREP(PORT_MSIMAP_TARGET, i) | + PORT_MSIMAP_ENABLE, + port->base + pcie->hw->port_msimap + 4 * i); + } else { + writel_relaxed(0, port->base + PORT_MSIBASE); + val = ilog2(pcie->nvecs) << PORT_MSICFG_L2MSINUM_SHIFT; + } + writel_relaxed(val | PORT_MSICFG_EN, port->base + PORT_MSICFG); return 0; } @@ -468,43 +507,47 @@ static int apple_pcie_setup_refclk(struct apple_pcie *pcie, 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; + if (pcie->hw->phy_lane_ctl) + rmw_set(PHY_LANE_CTL_CFGACC, port->phy + pcie->hw->phy_lane_ctl); - 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)); + rmw_set(PHY_LANE_CFG_REFCLK0REQ, port->phy + PHY_LANE_CFG); - res = readl_relaxed_poll_timeout(pcie->base + CORE_LANE_CFG(port->idx), - stat, stat & CORE_LANE_CFG_REFCLK0ACK, + res = readl_relaxed_poll_timeout(port->phy + PHY_LANE_CFG, + stat, stat & PHY_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, + rmw_set(PHY_LANE_CFG_REFCLK1REQ, port->phy + PHY_LANE_CFG); + res = readl_relaxed_poll_timeout(port->phy + PHY_LANE_CFG, + stat, stat & PHY_LANE_CFG_REFCLK1ACK, 100, 50000); if (res < 0) return res; - rmw_clear(CORE_LANE_CTL_CFGACC, pcie->base + CORE_LANE_CTL(port->idx)); + if (pcie->hw->phy_lane_ctl) + rmw_clear(PHY_LANE_CTL_CFGACC, port->phy + pcie->hw->phy_lane_ctl); + + rmw_set(PHY_LANE_CFG_REFCLKEN, port->phy + PHY_LANE_CFG); - rmw_set(CORE_LANE_CFG_REFCLKEN, pcie->base + CORE_LANE_CFG(port->idx)); - rmw_set(PORT_REFCLK_EN, port->base + PORT_REFCLK); + if (pcie->hw->port_refclk) + rmw_set(PORT_REFCLK_EN, port->base + pcie->hw->port_refclk); return 0; } +static void __iomem *port_rid2sid_addr(struct apple_pcie_port *port, int idx) +{ + return port->base + port->pcie->hw->port_rid2sid + 4 * idx; +} + static u32 apple_pcie_rid2sid_write(struct apple_pcie_port *port, int idx, u32 val) { - writel_relaxed(val, port->base + PORT_RID2SID(idx)); + writel_relaxed(val, port_rid2sid_addr(port, idx)); /* Read back to ensure completion of the write */ - return readl_relaxed(port->base + PORT_RID2SID(idx)); + return readl_relaxed(port_rid2sid_addr(port, idx)); } static int apple_pcie_setup_port(struct apple_pcie *pcie, @@ -513,6 +556,8 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, struct platform_device *platform = to_platform_device(pcie->dev); struct apple_pcie_port *port; struct gpio_desc *reset; + struct resource *res; + char name[16]; u32 stat, idx; int ret, i; @@ -525,6 +570,10 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, if (!port) return -ENOMEM; + port->sid_map = devm_bitmap_zalloc(pcie->dev, pcie->hw->max_rid2sid, GFP_KERNEL); + if (!port->sid_map) + return -ENOMEM; + ret = of_property_read_u32_index(np, "reg", 0, &idx); if (ret) return ret; @@ -534,14 +583,28 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, port->pcie = pcie; port->np = np; - port->base = devm_platform_ioremap_resource(platform, port->idx + 2); + raw_spin_lock_init(&port->lock); + + snprintf(name, sizeof(name), "port%d", port->idx); + res = platform_get_resource_byname(platform, IORESOURCE_MEM, name); + if (!res) + res = platform_get_resource(platform, IORESOURCE_MEM, port->idx + 2); + + port->base = devm_ioremap_resource(&platform->dev, res); if (IS_ERR(port->base)) return PTR_ERR(port->base); + snprintf(name, sizeof(name), "phy%d", port->idx); + res = platform_get_resource_byname(platform, IORESOURCE_MEM, name); + if (res) + port->phy = devm_ioremap_resource(&platform->dev, res); + else + port->phy = pcie->base + CORE_PHY_DEFAULT_BASE(port->idx); + rmw_set(PORT_APPCLK_EN, port->base + PORT_APPCLK); /* Assert PERST# before setting up the clock */ - gpiod_set_value(reset, 1); + gpiod_set_value_cansleep(reset, 1); ret = apple_pcie_setup_refclk(pcie, port); if (ret < 0) @@ -551,8 +614,8 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, usleep_range(100, 200); /* Deassert PERST# */ - rmw_set(PORT_PERST_OFF, port->base + PORT_PERST); - gpiod_set_value(reset, 0); + rmw_set(PORT_PERST_OFF, port->base + pcie->hw->port_perst); + gpiod_set_value_cansleep(reset, 0); /* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */ msleep(100); @@ -564,7 +627,11 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, return ret; } - rmw_clear(PORT_REFCLK_CGDIS, port->base + PORT_REFCLK); + if (pcie->hw->port_refclk) + rmw_clear(PORT_REFCLK_CGDIS, port->base + pcie->hw->port_refclk); + else + rmw_set(PHY_LANE_CFG_REFCLKCGEN, port->phy + PHY_LANE_CFG); + rmw_clear(PORT_APPCLK_CGDIS, port->base + PORT_APPCLK); ret = apple_pcie_port_setup_irq(port); @@ -572,7 +639,7 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, return ret; /* Reset all RID/SID mappings, and check for RAZ/WI registers */ - for (i = 0; i < MAX_RID2SID; i++) { + for (i = 0; i < pcie->hw->max_rid2sid; i++) { if (apple_pcie_rid2sid_write(port, i, 0xbad1d) != 0xbad1d) break; apple_pcie_rid2sid_write(port, i, 0); @@ -585,6 +652,9 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, list_add_tail(&port->entry, &pcie->ports); init_completion(&pcie->event); + /* In the success path, we keep a reference to np around */ + of_node_get(np); + ret = apple_pcie_port_register_irqs(port); WARN_ON(ret); @@ -596,11 +666,28 @@ static int apple_pcie_setup_port(struct apple_pcie *pcie, return 0; } +static const struct msi_parent_ops apple_msi_parent_ops = { + .supported_flags = (MSI_GENERIC_FLAGS_MASK | + MSI_FLAG_PCI_MSIX | + MSI_FLAG_MULTI_PCI_MSI), + .required_flags = (MSI_FLAG_USE_DEF_DOM_OPS | + MSI_FLAG_USE_DEF_CHIP_OPS | + MSI_FLAG_PCI_MSI_MASK_PARENT), + .chip_flags = MSI_CHIP_FLAG_SET_EOI, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .init_dev_msi_info = msi_lib_init_dev_msi_info, +}; + static int apple_msi_init(struct apple_pcie *pcie) { struct fwnode_handle *fwnode = dev_fwnode(pcie->dev); + struct irq_domain_info info = { + .fwnode = fwnode, + .ops = &apple_msi_domain_ops, + .size = pcie->nvecs, + .host_data = pcie, + }; struct of_phandle_args args = {}; - struct irq_domain *parent; int ret; ret = of_parse_phandle_with_args(to_of_node(fwnode), "msi-ranges", @@ -620,38 +707,35 @@ static int apple_msi_init(struct apple_pcie *pcie) if (!pcie->bitmap) return -ENOMEM; - parent = irq_find_matching_fwspec(&pcie->fwspec, DOMAIN_BUS_WIRED); - if (!parent) { + info.parent = irq_find_matching_fwspec(&pcie->fwspec, DOMAIN_BUS_WIRED); + if (!info.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) { + if (!msi_create_parent_irq_domain(&info, &apple_msi_parent_ops)) { 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 *apple_pcie_lookup(struct device *dev) +{ + return pci_host_bridge_priv(dev_get_drvdata(dev)); +} + 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 apple_pcie *pcie; struct pci_dev *port_pdev; struct apple_pcie_port *port; + pcie = apple_pcie_lookup(cfg->parent); + if (WARN_ON(!pcie)) + return NULL; + /* Find the root port this device is on */ port_pdev = pcie_find_root_port(pdev); @@ -667,12 +751,16 @@ static struct apple_pcie_port *apple_pcie_get_port(struct pci_dev *pdev) return NULL; } -static int apple_pcie_add_device(struct apple_pcie_port *port, - struct pci_dev *pdev) +static int apple_pcie_enable_device(struct pci_host_bridge *bridge, struct pci_dev *pdev) { u32 sid, rid = pci_dev_id(pdev); + struct apple_pcie_port *port; int idx, err; + port = apple_pcie_get_port(pdev); + if (!port) + return 0; + dev_dbg(&pdev->dev, "added to bus %s, index %d\n", pci_name(pdev->bus->self), port->idx); @@ -698,18 +786,22 @@ static int apple_pcie_add_device(struct apple_pcie_port *port, return idx >= 0 ? 0 : -ENOSPC; } -static void apple_pcie_release_device(struct apple_pcie_port *port, - struct pci_dev *pdev) +static void apple_pcie_disable_device(struct pci_host_bridge *bridge, struct pci_dev *pdev) { + struct apple_pcie_port *port; u32 rid = pci_dev_id(pdev); int idx; + port = apple_pcie_get_port(pdev); + if (!port) + return; + 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)); + val = readl_relaxed(port_rid2sid_addr(port, idx)); if ((val & 0xffff) == rid) { apple_pcie_rid2sid_write(port, idx, 0); bitmap_release_region(port->sid_map, idx, 0); @@ -721,110 +813,71 @@ static void apple_pcie_release_device(struct apple_pcie_port *port, mutex_unlock(&port->pcie->lock); } -static int apple_pcie_bus_notifier(struct notifier_block *nb, - unsigned long action, - void *data) +static int apple_pcie_init(struct pci_config_window *cfg) { - struct device *dev = data; - struct pci_dev *pdev = to_pci_dev(dev); - struct apple_pcie_port *port; - int err; + struct device *dev = cfg->parent; + struct apple_pcie *pcie; + int ret; - /* - * 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; + pcie = apple_pcie_lookup(dev); + if (WARN_ON(!pcie)) + return -ENOENT; - 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; + for_each_available_child_of_node_scoped(dev->of_node, of_port) { + ret = apple_pcie_setup_port(pcie, of_port); + if (ret) { + dev_err(dev, "Port %pOF setup fail: %d\n", of_port, ret); + return ret; + } } - return NOTIFY_OK; + return 0; } -static struct notifier_block apple_pcie_nb = { - .notifier_call = apple_pcie_bus_notifier, +static const struct pci_ecam_ops apple_pcie_cfg_ecam_ops = { + .init = apple_pcie_init, + .enable_device = apple_pcie_enable_device, + .disable_device = apple_pcie_disable_device, + .pci_ops = { + .map_bus = pci_ecam_map_bus, + .read = pci_generic_config_read, + .write = pci_generic_config_write, + } }; -static int apple_pcie_init(struct pci_config_window *cfg) +static int apple_pcie_probe(struct platform_device *pdev) { - struct device *dev = cfg->parent; - struct platform_device *platform = to_platform_device(dev); - struct device_node *of_port; + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; struct apple_pcie *pcie; int ret; - pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); - if (!pcie) + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) return -ENOMEM; + pcie = pci_host_bridge_priv(bridge); pcie->dev = dev; - - mutex_init(&pcie->lock); - - pcie->base = devm_platform_ioremap_resource(platform, 1); + pcie->hw = of_device_get_match_data(dev); + if (!pcie->hw) + return -ENODEV; + pcie->base = devm_platform_ioremap_resource(pdev, 1); if (IS_ERR(pcie->base)) return PTR_ERR(pcie->base); - cfg->priv = pcie; + mutex_init(&pcie->lock); 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; + return pci_host_common_init(pdev, bridge, &apple_pcie_cfg_ecam_ops); } -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 }, + { .compatible = "apple,t6020-pcie", .data = &t602x_hw }, + { .compatible = "apple,pcie", .data = &t8103_hw }, { } }; MODULE_DEVICE_TABLE(of, apple_pcie_of_match); diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c index 9321280f6edb..062f55690012 100644 --- a/drivers/pci/controller/pcie-brcmstb.c +++ b/drivers/pci/controller/pcie-brcmstb.c @@ -12,16 +12,20 @@ #include <linux/iopoll.h> #include <linux/ioport.h> #include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> +#include <linux/kdebug.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/log2.h> #include <linux/module.h> #include <linux/msi.h> +#include <linux/notifier.h> #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/of_pci.h> #include <linux/of_platform.h> +#include <linux/panic_notifier.h> #include <linux/pci.h> #include <linux/pci-ecam.h> #include <linux/printk.h> @@ -29,7 +33,9 @@ #include <linux/reset.h> #include <linux/sizes.h> #include <linux/slab.h> +#include <linux/spinlock.h> #include <linux/string.h> +#include <linux/string_choices.h> #include <linux/types.h> #include "../pci.h" @@ -40,13 +46,13 @@ /* 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_VENDOR_SPECIFIC_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_CFG_PRIV1_LINK_CAPABILITY_MAX_LINK_WIDTH_MASK 0x1f0 #define PCIE_RC_CFG_PRIV1_ROOT_CAP 0x4f8 #define PCIE_RC_CFG_PRIV1_ROOT_CAP_L1SS_MODE_MASK 0xf8 @@ -55,6 +61,13 @@ #define PCIE_RC_DL_MDIO_WR_DATA 0x1104 #define PCIE_RC_DL_MDIO_RD_DATA 0x1108 +#define PCIE_RC_PL_REG_PHY_CTL_1 0x1804 +#define PCIE_RC_PL_REG_PHY_CTL_1_REG_P2_POWERDOWN_ENA_NOSYNC_MASK 0x8 + +#define PCIE_RC_PL_PHY_CTL_15 0x184c +#define PCIE_RC_PL_PHY_CTL_15_DIS_PLL_PD_MASK 0x400000 +#define PCIE_RC_PL_PHY_CTL_15_PM_CLK_PERIOD_MASK 0xff + #define PCIE_MISC_MISC_CTRL 0x4008 #define PCIE_MISC_MISC_CTRL_PCIE_RCB_64B_MODE_MASK 0x80 #define PCIE_MISC_MISC_CTRL_PCIE_RCB_MPS_MODE_MASK 0x400 @@ -146,11 +159,40 @@ #define MSI_INT_MASK_SET 0x10 #define MSI_INT_MASK_CLR 0x14 -#define PCIE_EXT_CFG_DATA 0x8000 -#define PCIE_EXT_CFG_INDEX 0x9000 +/* Error report registers */ +#define PCIE_OUTB_ERR_TREAT 0x6000 +#define PCIE_OUTB_ERR_TREAT_CONFIG 0x1 +#define PCIE_OUTB_ERR_TREAT_MEM 0x2 +#define PCIE_OUTB_ERR_VALID 0x6004 +#define PCIE_OUTB_ERR_CLEAR 0x6008 +#define PCIE_OUTB_ERR_ACC_INFO 0x600c +#define PCIE_OUTB_ERR_ACC_INFO_CFG_ERR BIT(0) +#define PCIE_OUTB_ERR_ACC_INFO_MEM_ERR BIT(1) +#define PCIE_OUTB_ERR_ACC_INFO_TYPE_64 BIT(2) +#define PCIE_OUTB_ERR_ACC_INFO_DIR_WRITE BIT(4) +#define PCIE_OUTB_ERR_ACC_INFO_BYTE_LANES 0xff00 +#define PCIE_OUTB_ERR_ACC_ADDR 0x6010 +#define PCIE_OUTB_ERR_ACC_ADDR_BUS 0xff00000 +#define PCIE_OUTB_ERR_ACC_ADDR_DEV 0xf8000 +#define PCIE_OUTB_ERR_ACC_ADDR_FUNC 0x7000 +#define PCIE_OUTB_ERR_ACC_ADDR_REG 0xfff +#define PCIE_OUTB_ERR_CFG_CAUSE 0x6014 +#define PCIE_OUTB_ERR_CFG_CAUSE_TIMEOUT BIT(6) +#define PCIE_OUTB_ERR_CFG_CAUSE_ABORT BIT(5) +#define PCIE_OUTB_ERR_CFG_CAUSE_UNSUPP_REQ BIT(4) +#define PCIE_OUTB_ERR_CFG_CAUSE_ACC_TIMEOUT BIT(2) +#define PCIE_OUTB_ERR_CFG_CAUSE_ACC_DISABLED BIT(1) +#define PCIE_OUTB_ERR_CFG_CAUSE_ACC_64BIT BIT(0) +#define PCIE_OUTB_ERR_MEM_ADDR_LO 0x6018 +#define PCIE_OUTB_ERR_MEM_ADDR_HI 0x601c +#define PCIE_OUTB_ERR_MEM_CAUSE 0x6020 +#define PCIE_OUTB_ERR_MEM_CAUSE_TIMEOUT BIT(6) +#define PCIE_OUTB_ERR_MEM_CAUSE_ABORT BIT(5) +#define PCIE_OUTB_ERR_MEM_CAUSE_UNSUPP_REQ BIT(4) +#define PCIE_OUTB_ERR_MEM_CAUSE_ACC_DISABLED BIT(1) +#define PCIE_OUTB_ERR_MEM_CAUSE_BAD_ADDR BIT(0) #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 @@ -174,8 +216,9 @@ #define MDIO_PORT0 0x0 #define MDIO_DATA_MASK 0x7fffffff #define MDIO_PORT_MASK 0xf0000 +#define MDIO_PORT_EXT_MASK 0x200000 #define MDIO_REGAD_MASK 0xffff -#define MDIO_CMD_MASK 0xfff00000 +#define MDIO_CMD_MASK 0x00100000 #define MDIO_CMD_READ 0x1 #define MDIO_CMD_WRITE 0x0 #define MDIO_DATA_DONE_MASK 0x80000000 @@ -191,11 +234,11 @@ #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]) -#define HARD_DEBUG(pcie) ((pcie)->reg_offsets[PCIE_HARD_DEBUG]) -#define INTR2_CPU_BASE(pcie) ((pcie)->reg_offsets[PCIE_INTR2_CPU_BASE]) +#define IDX_ADDR(pcie) ((pcie)->cfg->offsets[EXT_CFG_INDEX]) +#define DATA_ADDR(pcie) ((pcie)->cfg->offsets[EXT_CFG_DATA]) +#define PCIE_RGR1_SW_INIT_1(pcie) ((pcie)->cfg->offsets[RGR1_SW_INIT_1]) +#define HARD_DEBUG(pcie) ((pcie)->cfg->offsets[PCIE_HARD_DEBUG]) +#define INTR2_CPU_BASE(pcie) ((pcie)->cfg->offsets[PCIE_INTR2_CPU_BASE]) /* Rescal registers */ #define PCIE_DVT_PMU_PCIE_PHY_CTRL 0xc700 @@ -234,13 +277,25 @@ struct inbound_win { u64 cpu_addr; }; +/* + * The RESCAL block is tied to PCIe controller #1, regardless of the number of + * controllers, and turning off PCIe controller #1 prevents access to the RESCAL + * register blocks, therefore no other controller can access this register + * space, and depending upon the bus fabric we may get a timeout (UBUS/GISB), + * or a hang (AXI). + */ +#define CFG_QUIRK_AVOID_BRIDGE_SHUTDOWN BIT(0) + struct pcie_cfg_data { const int *offsets; const enum pcie_soc_base soc_base; const bool has_phy; + const u32 quirks; u8 num_inbound_wins; int (*perst_set)(struct brcm_pcie *pcie, u32 val); int (*bridge_sw_init_set)(struct brcm_pcie *pcie, u32 val); + int (*post_setup)(struct brcm_pcie *pcie); + bool has_err_report; }; struct subdev_regulators { @@ -252,7 +307,6 @@ 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; @@ -276,8 +330,6 @@ struct brcm_pcie { int gen; u64 msi_target_addr; struct brcm_msi *msi; - const int *reg_offsets; - enum pcie_soc_base soc_base; struct reset_control *rescal; struct reset_control *perst_reset; struct reset_control *bridge_reset; @@ -285,17 +337,36 @@ struct brcm_pcie { int num_memc; u64 memc_size[PCIE_BRCM_MAX_MEMC]; u32 hw_rev; - int (*perst_set)(struct brcm_pcie *pcie, u32 val); - int (*bridge_sw_init_set)(struct brcm_pcie *pcie, u32 val); struct subdev_regulators *sr; bool ep_wakeup_capable; - bool has_phy; - u8 num_inbound_wins; + const struct pcie_cfg_data *cfg; + bool bridge_in_reset; + struct notifier_block die_notifier; + struct notifier_block panic_notifier; + spinlock_t bridge_lock; }; static inline bool is_bmips(const struct brcm_pcie *pcie) { - return pcie->soc_base == BCM7435 || pcie->soc_base == BCM7425; + return pcie->cfg->soc_base == BCM7435 || pcie->cfg->soc_base == BCM7425; +} + +static int brcm_pcie_bridge_sw_init_set(struct brcm_pcie *pcie, u32 val) +{ + unsigned long flags; + int ret; + + if (pcie->cfg->has_err_report) + spin_lock_irqsave(&pcie->bridge_lock, flags); + + ret = pcie->cfg->bridge_sw_init_set(pcie, val); + /* If we fail, assume the bridge is in reset (off) */ + pcie->bridge_in_reset = ret ? true : val; + + if (pcie->cfg->has_err_report) + spin_unlock_irqrestore(&pcie->bridge_lock, flags); + + return ret; } /* @@ -309,8 +380,8 @@ static int brcm_pcie_encode_ibar_size(u64 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) */ + else if (log2_in >= 16 && log2_in <= 36) + /* Covers 64KB to 64GB, (inclusive) */ return log2_in - 15; /* Something is awry so disable */ return 0; @@ -320,6 +391,7 @@ static u32 brcm_pcie_mdio_form_pkt(int port, int regad, int cmd) { u32 pkt = 0; + pkt |= FIELD_PREP(MDIO_PORT_EXT_MASK, port >> 4); pkt |= FIELD_PREP(MDIO_PORT_MASK, port); pkt |= FIELD_PREP(MDIO_REGAD_MASK, regad); pkt |= FIELD_PREP(MDIO_CMD_MASK, cmd); @@ -403,12 +475,12 @@ static int brcm_pcie_set_ssc(struct brcm_pcie *pcie) 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); + u32 lnkcap = readl(pcie->base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY); - lnkcap = (lnkcap & ~PCI_EXP_LNKCAP_SLS) | gen; - writel(lnkcap, pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCAP); + u32p_replace_bits(&lnkcap, gen, PCI_EXP_LNKCAP_SLS); + writel(lnkcap, pcie->base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY); - lnkctl2 = (lnkctl2 & ~0xf) | gen; + u16p_replace_bits(&lnkctl2, gen, PCI_EXP_LNKCTL2_TLS); writew(lnkctl2, pcie->base + BRCM_PCIE_CAP_REGS + PCI_EXP_LNKCTL2); } @@ -456,17 +528,20 @@ static void brcm_pcie_set_outbound_win(struct brcm_pcie *pcie, 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, -}; +#define BRCM_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) -static struct msi_domain_info brcm_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_NO_AFFINITY | MSI_FLAG_MULTI_PCI_MSI, - .chip = &brcm_msi_irq_chip, +#define BRCM_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_MULTI_PCI_MSI) + +static const struct msi_parent_ops brcm_msi_parent_ops = { + .required_flags = BRCM_MSI_FLAGS_REQUIRED, + .supported_flags = BRCM_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .chip_flags = MSI_CHIP_FLAG_SET_ACK, + .prefix = "BRCM-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; static void brcm_pcie_msi_isr(struct irq_desc *desc) @@ -550,7 +625,7 @@ static int brcm_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, return hwirq; for (i = 0; i < nr_irqs; i++) - irq_domain_set_info(domain, virq + i, hwirq + i, + irq_domain_set_info(domain, virq + i, (irq_hw_number_t)hwirq + i, &brcm_msi_bottom_irq_chip, domain->host_data, handle_edge_irq, NULL, NULL); return 0; @@ -572,21 +647,18 @@ static const struct irq_domain_ops msi_domain_ops = { 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; - } + struct irq_domain_info info = { + .fwnode = of_fwnode_handle(msi->np), + .ops = &msi_domain_ops, + .host_data = msi, + .size = msi->nr, + }; - msi->msi_domain = pci_msi_create_irq_domain(fwnode, - &brcm_msi_domain_info, - msi->inner_domain); - if (!msi->msi_domain) { + msi->inner_domain = msi_create_parent_irq_domain(&info, &brcm_msi_parent_ops); + if (!msi->inner_domain) { dev_err(dev, "failed to create MSI domain\n"); - irq_domain_remove(msi->inner_domain); return -ENOMEM; } @@ -595,7 +667,6 @@ static int brcm_allocate_domains(struct brcm_msi *msi) static void brcm_free_domains(struct brcm_msi *msi) { - irq_domain_remove(msi->msi_domain); irq_domain_remove(msi->inner_domain); } @@ -717,8 +788,8 @@ static void __iomem *brcm_pcie_map_bus(struct pci_bus *bus, /* 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); + writel(idx, base + IDX_ADDR(pcie)); + return base + DATA_ADDR(pcie) + PCIE_ECAM_REG(where); } static void __iomem *brcm7425_pcie_map_bus(struct pci_bus *bus, @@ -821,6 +892,39 @@ static int brcm_pcie_perst_set_generic(struct brcm_pcie *pcie, u32 val) return 0; } +static int brcm_pcie_post_setup_bcm2712(struct brcm_pcie *pcie) +{ + static const u16 data[] = { 0x50b9, 0xbda1, 0x0094, 0x97b4, 0x5030, + 0x5030, 0x0007 }; + static const u8 regs[] = { 0x16, 0x17, 0x18, 0x19, 0x1b, 0x1c, 0x1e }; + int ret, i; + u32 tmp; + + /* Allow a 54MHz (xosc) refclk source */ + ret = brcm_pcie_mdio_write(pcie->base, MDIO_PORT0, SET_ADDR_OFFSET, 0x1600); + if (ret < 0) + return ret; + + for (i = 0; i < ARRAY_SIZE(regs); i++) { + ret = brcm_pcie_mdio_write(pcie->base, MDIO_PORT0, regs[i], data[i]); + if (ret < 0) + return ret; + } + + usleep_range(100, 200); + + /* + * Set L1SS sub-state timers to avoid lengthy state transitions, + * PM clock period is 18.52ns (1/54MHz, round down). + */ + tmp = readl(pcie->base + PCIE_RC_PL_PHY_CTL_15); + tmp &= ~PCIE_RC_PL_PHY_CTL_15_PM_CLK_PERIOD_MASK; + tmp |= 0x12; + writel(tmp, pcie->base + PCIE_RC_PL_PHY_CTL_15); + + return 0; +} + static void add_inbound_win(struct inbound_win *b, u8 *count, u64 size, u64 cpu_addr, u64 pci_offset) { @@ -855,7 +959,7 @@ static int brcm_pcie_get_inbound_wins(struct brcm_pcie *pcie, * security considerations, and is not implemented in our modern * SoCs. */ - if (pcie->soc_base != BCM7712) + if (pcie->cfg->soc_base != BCM7712) add_inbound_win(b++, &n, 0, 0, 0); resource_list_for_each_entry(entry, &bridge->dma_ranges) { @@ -872,10 +976,10 @@ static int brcm_pcie_get_inbound_wins(struct brcm_pcie *pcie, * That being said, each BARs size must still be a power of * two. */ - if (pcie->soc_base == BCM7712) + if (pcie->cfg->soc_base == BCM7712) add_inbound_win(b++, &n, size, cpu_start, pcie_start); - if (n > pcie->num_inbound_wins) + if (n > pcie->cfg->num_inbound_wins) break; } @@ -889,7 +993,7 @@ static int brcm_pcie_get_inbound_wins(struct brcm_pcie *pcie, * that enables multiple memory controllers. As such, it can return * now w/o doing special configuration. */ - if (pcie->soc_base == BCM7712) + if (pcie->cfg->soc_base == BCM7712) return n; ret = of_property_read_variable_u64_array(pcie->np, "brcm,scb-sizes", pcie->memc_size, 1, @@ -928,7 +1032,7 @@ static int brcm_pcie_get_inbound_wins(struct brcm_pcie *pcie, * * 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 + * addition, its size must 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 @@ -1012,7 +1116,7 @@ static void set_inbound_win_registers(struct brcm_pcie *pcie, * 7712: * All of their BARs need to be set. */ - if (pcie->soc_base == BCM7712) { + if (pcie->cfg->soc_base == BCM7712) { /* BUS remap register settings */ reg_offset = brcm_ubus_reg_offset(i); tmp = lower_32_bits(cpu_addr) & ~0xfff; @@ -1030,21 +1134,21 @@ static int brcm_pcie_setup(struct brcm_pcie *pcie) void __iomem *base = pcie->base; struct pci_host_bridge *bridge; struct resource_entry *entry; - u32 tmp, burst, aspm_support; + u32 tmp, burst, num_lanes, num_lanes_cap; u8 num_out_wins = 0; int num_inbound_wins = 0; int memc, ret; /* Reset the bridge */ - ret = pcie->bridge_sw_init_set(pcie, 1); + ret = brcm_pcie_bridge_sw_init_set(pcie, 1); if (ret) return ret; /* Ensure that PERST# is asserted; some bootloaders may deassert it. */ - if (pcie->soc_base == BCM2711) { - ret = pcie->perst_set(pcie, 1); + if (pcie->cfg->soc_base == BCM2711) { + ret = pcie->cfg->perst_set(pcie, 1); if (ret) { - pcie->bridge_sw_init_set(pcie, 0); + pcie->cfg->bridge_sw_init_set(pcie, 0); return ret; } } @@ -1052,7 +1156,7 @@ static int brcm_pcie_setup(struct brcm_pcie *pcie) usleep_range(100, 200); /* Take the bridge out of reset */ - ret = pcie->bridge_sw_init_set(pcie, 0); + ret = brcm_pcie_bridge_sw_init_set(pcie, 0); if (ret) return ret; @@ -1072,9 +1176,9 @@ static int brcm_pcie_setup(struct brcm_pcie *pcie) */ if (is_bmips(pcie)) burst = 0x1; /* 256 bytes */ - else if (pcie->soc_base == BCM2711) + else if (pcie->cfg->soc_base == BCM2711) burst = 0x0; /* 128 bytes */ - else if (pcie->soc_base == BCM7278) + else if (pcie->cfg->soc_base == BCM7278) burst = 0x3; /* 512 bytes */ else burst = 0x2; /* 512 bytes */ @@ -1130,14 +1234,32 @@ static int brcm_pcie_setup(struct brcm_pcie *pcie) /* 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); + if (of_property_read_bool(pcie->np, "aspm-no-l0s")) + tmp &= ~PCI_EXP_LNKCAP_ASPM_L0S; writel(tmp, base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY); + /* 'tmp' still holds the contents of PRIV1_LINK_CAPABILITY */ + num_lanes_cap = u32_get_bits(tmp, PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_MAX_LINK_WIDTH_MASK); + num_lanes = 0; + + /* + * Use hardware negotiated Max Link Width value by default. If the + * "num-lanes" DT property is present, assume that the chip's default + * link width capability information is incorrect/undesired and use the + * specified value instead. + */ + if (!of_property_read_u32(pcie->np, "num-lanes", &num_lanes) && + num_lanes && num_lanes <= 4 && num_lanes_cap != num_lanes) { + u32p_replace_bits(&tmp, num_lanes, + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_MAX_LINK_WIDTH_MASK); + writel(tmp, base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY); + tmp = readl(base + PCIE_RC_PL_REG_PHY_CTL_1); + u32p_replace_bits(&tmp, 1, + PCIE_RC_PL_REG_PHY_CTL_1_REG_P2_POWERDOWN_ENA_NOSYNC_MASK); + writel(tmp, base + PCIE_RC_PL_REG_PHY_CTL_1); + } + /* * For config space accesses on the RC, show the right class for * a PCIe-PCIe bridge (the default setting is to be EP mode). @@ -1180,10 +1302,16 @@ static int brcm_pcie_setup(struct brcm_pcie *pcie) /* PCIe->SCB endian mode for inbound window */ tmp = readl(base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1); - u32p_replace_bits(&tmp, PCIE_RC_CFG_VENDOR_SPCIFIC_REG1_LITTLE_ENDIAN, + u32p_replace_bits(&tmp, PCIE_RC_CFG_VENDOR_SPECIFIC_REG1_LITTLE_ENDIAN, PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1_ENDIAN_MODE_BAR2_MASK); writel(tmp, base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1); + if (pcie->cfg->post_setup) { + ret = pcie->cfg->post_setup(pcie); + if (ret < 0) + return ret; + } + return 0; } @@ -1199,7 +1327,7 @@ static void brcm_extend_rbus_timeout(struct brcm_pcie *pcie) u32 timeout_us = 4000000; /* 4 seconds, our setting for L1SS */ /* 7712 does not have this (RGR1) timer */ - if (pcie->soc_base == BCM7712) + if (pcie->cfg->soc_base == BCM7712) return; /* Each unit in timeout register is 1/216,000,000 seconds */ @@ -1276,16 +1404,16 @@ static int brcm_pcie_start_link(struct brcm_pcie *pcie) bool ssc_good = false; int ret, i; + /* Limit the generation if specified */ + if (pcie->gen) + brcm_pcie_set_gen(pcie, pcie->gen); + /* Unassert the fundamental reset */ - ret = pcie->perst_set(pcie, 0); + ret = pcie->cfg->perst_set(pcie, 0); if (ret) return ret; - /* - * Wait for 100ms after PERST# deassertion; see PCIe CEM specification - * sections 2.2, PCIe r5.0, 6.6.1. - */ - msleep(100); + msleep(PCIE_RESET_CONFIG_WAIT_MS); /* * Give the RC/EP even more time to wake up, before trying to @@ -1302,9 +1430,6 @@ static int brcm_pcie_start_link(struct brcm_pcie *pcie) brcm_config_clkreq(pcie); - if (pcie->gen) - brcm_pcie_set_gen(pcie, pcie->gen); - if (pcie->ssc) { ret = brcm_pcie_set_ssc(pcie); if (ret == 0) @@ -1367,7 +1492,8 @@ static int brcm_pcie_add_bus(struct pci_bus *bus) ret = regulator_bulk_get(dev, sr->num_supplies, sr->supplies); if (ret) { - dev_info(dev, "No regulators for downstream device\n"); + dev_info(dev, "Did not get regulators, err=%d\n", ret); + pcie->sr = NULL; goto no_regulators; } @@ -1390,7 +1516,7 @@ static void brcm_pcie_remove_bus(struct pci_bus *bus) struct subdev_regulators *sr = pcie->sr; struct device *dev = &bus->dev; - if (!sr) + if (!sr || !bus->parent || !pci_is_root_bus(bus->parent)) return; if (regulator_bulk_disable(sr->num_supplies, sr->supplies)) @@ -1463,12 +1589,12 @@ static int brcm_phy_cntl(struct brcm_pcie *pcie, const int start) static inline int brcm_phy_start(struct brcm_pcie *pcie) { - return pcie->has_phy ? brcm_phy_cntl(pcie, 1) : 0; + return pcie->cfg->has_phy ? brcm_phy_cntl(pcie, 1) : 0; } static inline int brcm_phy_stop(struct brcm_pcie *pcie) { - return pcie->has_phy ? brcm_phy_cntl(pcie, 0) : 0; + return pcie->cfg->has_phy ? brcm_phy_cntl(pcie, 0) : 0; } static int brcm_pcie_turn_off(struct brcm_pcie *pcie) @@ -1479,7 +1605,7 @@ static int brcm_pcie_turn_off(struct brcm_pcie *pcie) if (brcm_pcie_link_up(pcie)) brcm_pcie_enter_l23(pcie); /* Assert fundamental reset */ - ret = pcie->perst_set(pcie, 1); + ret = pcie->cfg->perst_set(pcie, 1); if (ret) return ret; @@ -1493,8 +1619,9 @@ static int brcm_pcie_turn_off(struct brcm_pcie *pcie) u32p_replace_bits(&tmp, 1, PCIE_MISC_HARD_PCIE_HARD_DEBUG_SERDES_IDDQ_MASK); writel(tmp, base + HARD_DEBUG(pcie)); - /* Shutdown PCIe bridge */ - ret = pcie->bridge_sw_init_set(pcie, 1); + if (!(pcie->cfg->quirks & CFG_QUIRK_AVOID_BRIDGE_SHUTDOWN)) + /* Shutdown PCIe bridge */ + ret = brcm_pcie_bridge_sw_init_set(pcie, 1); return ret; } @@ -1582,7 +1709,9 @@ static int brcm_pcie_resume_noirq(struct device *dev) goto err_reset; /* Take bridge out of reset so we can access the SERDES reg */ - pcie->bridge_sw_init_set(pcie, 0); + ret = brcm_pcie_bridge_sw_init_set(pcie, 0); + if (ret) + goto err_reset; /* SERDES_IDDQ = 0 */ tmp = readl(base + HARD_DEBUG(pcie)); @@ -1636,6 +1765,119 @@ err_disable_clk: return ret; } +/* Dump out PCIe errors on die or panic */ +static int brcm_pcie_dump_err(struct brcm_pcie *pcie, + const char *type) +{ + void __iomem *base = pcie->base; + int i, is_cfg_err, is_mem_err, lanes; + const char *width_str, *direction_str; + u32 info, cfg_addr, cfg_cause, mem_cause, lo, hi; + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie); + unsigned long flags; + char lanes_str[9]; + + spin_lock_irqsave(&pcie->bridge_lock, flags); + /* Don't access registers when the bridge is off */ + if (pcie->bridge_in_reset || readl(base + PCIE_OUTB_ERR_VALID) == 0) { + spin_unlock_irqrestore(&pcie->bridge_lock, flags); + return NOTIFY_DONE; + } + + /* Read all necessary registers so we can release the spinlock ASAP */ + info = readl(base + PCIE_OUTB_ERR_ACC_INFO); + is_cfg_err = !!(info & PCIE_OUTB_ERR_ACC_INFO_CFG_ERR); + is_mem_err = !!(info & PCIE_OUTB_ERR_ACC_INFO_MEM_ERR); + if (is_cfg_err) { + cfg_addr = readl(base + PCIE_OUTB_ERR_ACC_ADDR); + cfg_cause = readl(base + PCIE_OUTB_ERR_CFG_CAUSE); + } + if (is_mem_err) { + mem_cause = readl(base + PCIE_OUTB_ERR_MEM_CAUSE); + lo = readl(base + PCIE_OUTB_ERR_MEM_ADDR_LO); + hi = readl(base + PCIE_OUTB_ERR_MEM_ADDR_HI); + } + /* We've got all of the info, clear the error */ + writel(1, base + PCIE_OUTB_ERR_CLEAR); + spin_unlock_irqrestore(&pcie->bridge_lock, flags); + + dev_err(pcie->dev, "reporting PCIe info which may be related to %s error\n", + type); + width_str = (info & PCIE_OUTB_ERR_ACC_INFO_TYPE_64) ? "64bit" : "32bit"; + direction_str = str_read_write(!(info & PCIE_OUTB_ERR_ACC_INFO_DIR_WRITE)); + lanes = FIELD_GET(PCIE_OUTB_ERR_ACC_INFO_BYTE_LANES, info); + for (i = 0, lanes_str[8] = 0; i < 8; i++) + lanes_str[i] = (lanes & (1 << i)) ? '1' : '0'; + + if (is_cfg_err) { + int bus = FIELD_GET(PCIE_OUTB_ERR_ACC_ADDR_BUS, cfg_addr); + int dev = FIELD_GET(PCIE_OUTB_ERR_ACC_ADDR_DEV, cfg_addr); + int func = FIELD_GET(PCIE_OUTB_ERR_ACC_ADDR_FUNC, cfg_addr); + int reg = FIELD_GET(PCIE_OUTB_ERR_ACC_ADDR_REG, cfg_addr); + + dev_err(pcie->dev, "Error: CFG Acc, %s, %s (%04x:%02x:%02x.%d) reg=0x%x, lanes=%s\n", + width_str, direction_str, bridge->domain_nr, bus, dev, + func, reg, lanes_str); + dev_err(pcie->dev, " Type: TO=%d Abt=%d UnsupReq=%d AccTO=%d AccDsbld=%d Acc64bit=%d\n", + !!(cfg_cause & PCIE_OUTB_ERR_CFG_CAUSE_TIMEOUT), + !!(cfg_cause & PCIE_OUTB_ERR_CFG_CAUSE_ABORT), + !!(cfg_cause & PCIE_OUTB_ERR_CFG_CAUSE_UNSUPP_REQ), + !!(cfg_cause & PCIE_OUTB_ERR_CFG_CAUSE_ACC_TIMEOUT), + !!(cfg_cause & PCIE_OUTB_ERR_CFG_CAUSE_ACC_DISABLED), + !!(cfg_cause & PCIE_OUTB_ERR_CFG_CAUSE_ACC_64BIT)); + } + + if (is_mem_err) { + u64 addr = ((u64)hi << 32) | (u64)lo; + + dev_err(pcie->dev, "Error: Mem Acc, %s, %s, @0x%llx, lanes=%s\n", + width_str, direction_str, addr, lanes_str); + dev_err(pcie->dev, " Type: TO=%d Abt=%d UnsupReq=%d AccDsble=%d BadAddr=%d\n", + !!(mem_cause & PCIE_OUTB_ERR_MEM_CAUSE_TIMEOUT), + !!(mem_cause & PCIE_OUTB_ERR_MEM_CAUSE_ABORT), + !!(mem_cause & PCIE_OUTB_ERR_MEM_CAUSE_UNSUPP_REQ), + !!(mem_cause & PCIE_OUTB_ERR_MEM_CAUSE_ACC_DISABLED), + !!(mem_cause & PCIE_OUTB_ERR_MEM_CAUSE_BAD_ADDR)); + } + + return NOTIFY_DONE; +} + +static int brcm_pcie_die_notify_cb(struct notifier_block *self, + unsigned long v, void *p) +{ + struct brcm_pcie *pcie = + container_of(self, struct brcm_pcie, die_notifier); + + return brcm_pcie_dump_err(pcie, "Die"); +} + +static int brcm_pcie_panic_notify_cb(struct notifier_block *self, + unsigned long v, void *p) +{ + struct brcm_pcie *pcie = + container_of(self, struct brcm_pcie, panic_notifier); + + return brcm_pcie_dump_err(pcie, "Panic"); +} + +static void brcm_register_die_notifiers(struct brcm_pcie *pcie) +{ + pcie->panic_notifier.notifier_call = brcm_pcie_panic_notify_cb; + atomic_notifier_chain_register(&panic_notifier_list, + &pcie->panic_notifier); + + pcie->die_notifier.notifier_call = brcm_pcie_die_notify_cb; + register_die_notifier(&pcie->die_notifier); +} + +static void brcm_unregister_die_notifiers(struct brcm_pcie *pcie) +{ + unregister_die_notifier(&pcie->die_notifier); + atomic_notifier_chain_unregister(&panic_notifier_list, + &pcie->panic_notifier); +} + static void __brcm_pcie_remove(struct brcm_pcie *pcie) { brcm_msi_remove(pcie); @@ -1654,13 +1896,16 @@ static void brcm_pcie_remove(struct platform_device *pdev) pci_stop_root_bus(bridge->bus); pci_remove_root_bus(bridge->bus); + if (pcie->cfg->has_err_report) + brcm_unregister_die_notifiers(pcie); + __brcm_pcie_remove(pcie); } static const int pcie_offsets[] = { [RGR1_SW_INIT_1] = 0x9210, [EXT_CFG_INDEX] = 0x9000, - [EXT_CFG_DATA] = 0x9004, + [EXT_CFG_DATA] = 0x8000, [PCIE_HARD_DEBUG] = 0x4204, [PCIE_INTR2_CPU_BASE] = 0x4300, }; @@ -1668,7 +1913,7 @@ static const int pcie_offsets[] = { static const int pcie_offsets_bcm7278[] = { [RGR1_SW_INIT_1] = 0xc010, [EXT_CFG_INDEX] = 0x9000, - [EXT_CFG_DATA] = 0x9004, + [EXT_CFG_DATA] = 0x8000, [PCIE_HARD_DEBUG] = 0x4204, [PCIE_INTR2_CPU_BASE] = 0x4300, }; @@ -1682,8 +1927,9 @@ static const int pcie_offsets_bcm7425[] = { }; static const int pcie_offsets_bcm7712[] = { + [RGR1_SW_INIT_1] = 0x9210, [EXT_CFG_INDEX] = 0x9000, - [EXT_CFG_DATA] = 0x9004, + [EXT_CFG_DATA] = 0x8000, [PCIE_HARD_DEBUG] = 0x4304, [PCIE_INTR2_CPU_BASE] = 0x4400, }; @@ -1704,6 +1950,16 @@ static const struct pcie_cfg_data bcm2711_cfg = { .num_inbound_wins = 3, }; +static const struct pcie_cfg_data bcm2712_cfg = { + .offsets = pcie_offsets_bcm7712, + .soc_base = BCM7712, + .perst_set = brcm_pcie_perst_set_7278, + .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic, + .post_setup = brcm_pcie_post_setup_bcm2712, + .quirks = CFG_QUIRK_AVOID_BRIDGE_SHUTDOWN, + .num_inbound_wins = 10, +}; + static const struct pcie_cfg_data bcm4908_cfg = { .offsets = pcie_offsets, .soc_base = BCM4908, @@ -1743,6 +1999,7 @@ static const struct pcie_cfg_data bcm7216_cfg = { .bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_7278, .has_phy = true, .num_inbound_wins = 3, + .has_err_report = true, }; static const struct pcie_cfg_data bcm7712_cfg = { @@ -1755,6 +2012,7 @@ static const struct pcie_cfg_data bcm7712_cfg = { static const struct of_device_id brcm_pcie_match[] = { { .compatible = "brcm,bcm2711-pcie", .data = &bcm2711_cfg }, + { .compatible = "brcm,bcm2712-pcie", .data = &bcm2712_cfg }, { .compatible = "brcm,bcm4908-pcie", .data = &bcm4908_cfg }, { .compatible = "brcm,bcm7211-pcie", .data = &generic_cfg }, { .compatible = "brcm,bcm7216-pcie", .data = &bcm7216_cfg }, @@ -1784,7 +2042,7 @@ static struct pci_ops brcm7425_pcie_ops = { static int brcm_pcie_probe(struct platform_device *pdev) { - struct device_node *np = pdev->dev.of_node, *msi_np; + struct device_node *np = pdev->dev.of_node; struct pci_host_bridge *bridge; const struct pcie_cfg_data *data; struct brcm_pcie *pcie; @@ -1803,12 +2061,7 @@ static int brcm_pcie_probe(struct platform_device *pdev) pcie = pci_host_bridge_priv(bridge); pcie->dev = &pdev->dev; pcie->np = np; - pcie->reg_offsets = data->offsets; - pcie->soc_base = data->soc_base; - pcie->perst_set = data->perst_set; - pcie->bridge_sw_init_set = data->bridge_sw_init_set; - pcie->has_phy = data->has_phy; - pcie->num_inbound_wins = data->num_inbound_wins; + pcie->cfg = data; pcie->base = devm_platform_ioremap_resource(pdev, 0); if (IS_ERR(pcie->base)) @@ -1843,7 +2096,10 @@ static int brcm_pcie_probe(struct platform_device *pdev) if (ret) return dev_err_probe(&pdev->dev, ret, "could not enable clock\n"); - pcie->bridge_sw_init_set(pcie, 0); + ret = brcm_pcie_bridge_sw_init_set(pcie, 0); + if (ret) + return dev_err_probe(&pdev->dev, ret, + "could not de-assert bridge reset\n"); if (pcie->swinit_reset) { ret = reset_control_assert(pcie->swinit_reset); @@ -1882,22 +2138,29 @@ static int brcm_pcie_probe(struct platform_device *pdev) goto fail; pcie->hw_rev = readl(pcie->base + PCIE_MISC_REVISION); - if (pcie->soc_base == BCM4908 && pcie->hw_rev >= BRCM_PCIE_HW_REV_3_20) { + if (pcie->cfg->soc_base == 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 (pci_msi_enabled()) { + struct device_node *msi_np = of_parse_phandle(pcie->np, "msi-parent", 0); + + if (msi_np == pcie->np) + ret = brcm_pcie_enable_msi(pcie); + + of_node_put(msi_np); + if (ret) { dev_err(pcie->dev, "probe of internal MSI failed"); goto fail; } } - bridge->ops = pcie->soc_base == BCM7425 ? &brcm7425_pcie_ops : &brcm_pcie_ops; + bridge->ops = pcie->cfg->soc_base == BCM7425 ? + &brcm7425_pcie_ops : &brcm_pcie_ops; bridge->sysdata = pcie; platform_set_drvdata(pdev, pcie); @@ -1911,6 +2174,11 @@ static int brcm_pcie_probe(struct platform_device *pdev) return ret; } + if (pcie->cfg->has_err_report) { + spin_lock_init(&pcie->bridge_lock); + brcm_register_die_notifiers(pcie); + } + return 0; fail: @@ -1928,7 +2196,7 @@ static const struct dev_pm_ops brcm_pcie_pm_ops = { static struct platform_driver brcm_pcie_driver = { .probe = brcm_pcie_probe, - .remove_new = brcm_pcie_remove, + .remove = brcm_pcie_remove, .driver = { .name = "brcm-pcie", .of_match_table = brcm_pcie_match, @@ -1940,3 +2208,4 @@ module_platform_driver(brcm_pcie_driver); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Broadcom STB PCIe RC driver"); MODULE_AUTHOR("Broadcom"); +MODULE_SOFTDEP("pre: irq_bcm2712_mip"); diff --git a/drivers/pci/controller/pcie-hisi-error.c b/drivers/pci/controller/pcie-hisi-error.c index ad9d5ffcd9e3..aaf1ed2b6e59 100644 --- a/drivers/pci/controller/pcie-hisi-error.c +++ b/drivers/pci/controller/pcie-hisi-error.c @@ -317,7 +317,7 @@ static struct platform_driver hisi_pcie_error_handler_driver = { .acpi_match_table = hisi_pcie_acpi_match, }, .probe = hisi_pcie_error_handler_probe, - .remove_new = hisi_pcie_error_handler_remove, + .remove = hisi_pcie_error_handler_remove, }; module_platform_driver(hisi_pcie_error_handler_driver); diff --git a/drivers/pci/controller/pcie-iproc-msi.c b/drivers/pci/controller/pcie-iproc-msi.c index 649fcb449f34..9ba242ab9596 100644 --- a/drivers/pci/controller/pcie-iproc-msi.c +++ b/drivers/pci/controller/pcie-iproc-msi.c @@ -5,6 +5,7 @@ #include <linux/interrupt.h> #include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/msi.h> #include <linux/of_irq.h> @@ -81,7 +82,6 @@ struct iproc_msi_grp { * @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 @@ -101,7 +101,6 @@ struct iproc_msi { 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; @@ -165,16 +164,18 @@ static inline unsigned int iproc_msi_eq_offset(struct iproc_msi *msi, u32 eq) return eq * EQ_LEN * sizeof(u32); } -static struct irq_chip iproc_msi_irq_chip = { - .name = "iProc-MSI", +#define IPROC_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS) +#define IPROC_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_PCI_MSIX) + +static struct msi_parent_ops iproc_msi_parent_ops = { + .required_flags = IPROC_MSI_FLAGS_REQUIRED, + .supported_flags = IPROC_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .prefix = "iProc-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; - -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. @@ -446,27 +447,22 @@ static void iproc_msi_disable(struct iproc_msi *msi) 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); + struct irq_domain_info info = { + .fwnode = of_fwnode_handle(node), + .ops = &msi_domain_ops, + .host_data = msi, + .size = msi->nr_msi_vecs, + }; + + msi->inner_domain = msi_create_parent_irq_domain(&info, &iproc_msi_parent_ops); 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); } @@ -542,7 +538,7 @@ int iproc_msi_init(struct iproc_pcie *pcie, struct device_node *node) msi->nr_cpus = num_possible_cpus(); if (msi->nr_cpus == 1) - iproc_msi_domain_info.flags |= MSI_FLAG_MULTI_PCI_MSI; + iproc_msi_parent_ops.supported_flags |= MSI_FLAG_MULTI_PCI_MSI; msi->nr_irqs = of_irq_count(node); if (!msi->nr_irqs) { diff --git a/drivers/pci/controller/pcie-iproc-platform.c b/drivers/pci/controller/pcie-iproc-platform.c index 4e6aa882a567..0cb78c583c7e 100644 --- a/drivers/pci/controller/pcie-iproc-platform.c +++ b/drivers/pci/controller/pcie-iproc-platform.c @@ -134,7 +134,7 @@ static struct platform_driver iproc_pltfm_pcie_driver = { .of_match_table = of_match_ptr(iproc_pcie_of_match_table), }, .probe = iproc_pltfm_pcie_probe, - .remove_new = iproc_pltfm_pcie_remove, + .remove = iproc_pltfm_pcie_remove, .shutdown = iproc_pltfm_pcie_shutdown, }; module_platform_driver(iproc_pltfm_pcie_driver); diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c index 22134e95574b..ccf71993ea35 100644 --- a/drivers/pci/controller/pcie-iproc.c +++ b/drivers/pci/controller/pcie-iproc.c @@ -17,6 +17,7 @@ #include <linux/irqchip/arm-gic-v3.h> #include <linux/platform_device.h> #include <linux/of_address.h> +#include <linux/of_irq.h> #include <linux/of_pci.h> #include <linux/of_platform.h> #include <linux/phy/phy.h> @@ -1337,29 +1338,16 @@ static int iproc_pcie_msi_steer(struct iproc_pcie *pcie, static int iproc_pcie_msi_enable(struct iproc_pcie *pcie) { - struct device_node *msi_node; + struct device_node *msi_node = NULL; 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; - } + of_msi_xlate(pcie->dev, &msi_node, 0); + if (!msi_node) + return -ENODEV; /* * Certain revisions of the iProc PCIe controller require additional diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c index 66ce4b5d309b..75ddb8bee168 100644 --- a/drivers/pci/controller/pcie-mediatek-gen3.c +++ b/drivers/pci/controller/pcie-mediatek-gen3.c @@ -12,9 +12,11 @@ #include <linux/delay.h> #include <linux/iopoll.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.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/msi.h> #include <linux/of_device.h> @@ -24,11 +26,17 @@ #include <linux/platform_device.h> #include <linux/pm_domain.h> #include <linux/pm_runtime.h> +#include <linux/regmap.h> #include <linux/reset.h> #include "../pci.h" +#define PCIE_BASE_CFG_REG 0x14 +#define PCIE_BASE_CFG_SPEED GENMASK(15, 8) + #define PCIE_SETTING_REG 0x80 +#define PCIE_SETTING_LINK_WIDTH GENMASK(11, 8) +#define PCIE_SETTING_GEN_SUPPORT GENMASK(14, 12) #define PCIE_PCI_IDS_1 0x9c #define PCI_CLASS(class) (class << 8) #define PCIE_RC_MODE BIT(0) @@ -94,6 +102,9 @@ #define PCIE_MSI_SET_ADDR_HI_BASE 0xc80 #define PCIE_MSI_SET_ADDR_HI_OFFSET 0x04 +#define PCIE_RESOURCE_CTRL_REG 0xd2c +#define PCIE_RSRC_SYS_CLK_RDY_TIME_MASK GENMASK(7, 0) + #define PCIE_ICMD_PM_REG 0x198 #define PCIE_TURN_OFF_LINK BIT(4) @@ -120,15 +131,29 @@ #define MAX_NUM_PHY_RESETS 3 +#define PCIE_MTK_RESET_TIME_US 10 + /* Time in ms needed to complete PCIe reset on EN7581 SoC */ #define PCIE_EN7581_RESET_TIME_MS 100 struct mtk_gen3_pcie; +#define PCIE_CONF_LINK2_CTL_STS (PCIE_CFG_OFFSET_ADDR + 0xb0) +#define PCIE_CONF_LINK2_LCR2_LINK_SPEED GENMASK(3, 0) + +enum mtk_gen3_pcie_flags { + SKIP_PCIE_RSTB = BIT(0), /* Skip PERST# assertion during device + * probing or suspend/resume phase to + * avoid hw bugs/issues. + */ +}; + /** * struct mtk_gen3_pcie_pdata - differentiate between host generations * @power_up: pcie power_up callback * @phy_resets: phy reset lines SoC data. + * @sys_clk_rdy_time_us: System clock ready time override (microseconds) + * @flags: pcie device flags. */ struct mtk_gen3_pcie_pdata { int (*power_up)(struct mtk_gen3_pcie *pcie); @@ -136,6 +161,8 @@ struct mtk_gen3_pcie_pdata { const char *id[MAX_NUM_PHY_RESETS]; int num_resets; } phy_resets; + u8 sys_clk_rdy_time_us; + u32 flags; }; /** @@ -160,11 +187,12 @@ struct mtk_msi_set { * @phy: PHY controller block * @clks: PCIe clocks * @num_clks: PCIe clocks count for this port + * @max_link_speed: Maximum link speed (PCIe Gen) for this port + * @num_lanes: Number of PCIe lanes 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 @@ -180,12 +208,13 @@ struct mtk_gen3_pcie { struct phy *phy; struct clk_bulk_data *clks; int num_clks; + u8 max_link_speed; + u8 num_lanes; 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; @@ -329,7 +358,8 @@ static int mtk_pcie_set_trans_table(struct mtk_gen3_pcie *pcie, 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); + (unsigned long long)pci_addr, + (unsigned long long)table_size); cpu_addr += table_size; pci_addr += table_size; @@ -381,11 +411,43 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie) int err; u32 val; - /* Set as RC mode */ + /* Set as RC mode and set controller PCIe Gen speed restriction, if any */ val = readl_relaxed(pcie->base + PCIE_SETTING_REG); val |= PCIE_RC_MODE; + if (pcie->max_link_speed) { + val &= ~PCIE_SETTING_GEN_SUPPORT; + + /* Can enable link speed support only from Gen2 onwards */ + if (pcie->max_link_speed >= 2) + val |= FIELD_PREP(PCIE_SETTING_GEN_SUPPORT, + GENMASK(pcie->max_link_speed - 2, 0)); + } + if (pcie->num_lanes) { + val &= ~PCIE_SETTING_LINK_WIDTH; + + /* Zero means one lane, each bit activates x2/x4/x8/x16 */ + if (pcie->num_lanes > 1) + val |= FIELD_PREP(PCIE_SETTING_LINK_WIDTH, + GENMASK(fls(pcie->num_lanes >> 2), 0)); + } writel_relaxed(val, pcie->base + PCIE_SETTING_REG); + /* Set Link Control 2 (LNKCTL2) speed restriction, if any */ + if (pcie->max_link_speed) { + val = readl_relaxed(pcie->base + PCIE_CONF_LINK2_CTL_STS); + val &= ~PCIE_CONF_LINK2_LCR2_LINK_SPEED; + val |= FIELD_PREP(PCIE_CONF_LINK2_LCR2_LINK_SPEED, pcie->max_link_speed); + writel_relaxed(val, pcie->base + PCIE_CONF_LINK2_CTL_STS); + } + + /* If parameter is present, adjust SYS_CLK_RDY_TIME to avoid glitching */ + if (pcie->soc->sys_clk_rdy_time_us) { + val = readl_relaxed(pcie->base + PCIE_RESOURCE_CTRL_REG); + FIELD_MODIFY(PCIE_RSRC_SYS_CLK_RDY_TIME_MASK, &val, + pcie->soc->sys_clk_rdy_time_us); + writel_relaxed(val, pcie->base + PCIE_RESOURCE_CTRL_REG); + } + /* Set class code */ val = readl_relaxed(pcie->base + PCIE_PCI_IDS_1); val &= ~GENMASK(31, 8); @@ -402,22 +464,33 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie) 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. + * Airoha EN7581 has a hw bug asserting/releasing PCIE_PE_RSTB signal + * causing occasional PCIe link down. In order to overcome the issue, + * PCIE_RSTB signals are not asserted/released at this stage and the + * PCIe block is reset using en7523_reset_assert() and + * en7581_pci_enable(). */ - 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); + if (!(pcie->soc->flags & SKIP_PCIE_RSTB)) { + /* 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 revision 6.0. + * + * The deassertion of PERST# should be delayed 100ms (TPVPERL) + * for the power and clock to become stable. + */ + msleep(PCIE_T_PVPERL_MS); + + /* 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, @@ -465,30 +538,22 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie) return 0; } -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_NO_AFFINITY | MSI_FLAG_PCI_MSIX | - MSI_FLAG_MULTI_PCI_MSI, - .chip = &mtk_msi_irq_chip, +#define MTK_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY | \ + MSI_FLAG_PCI_MSI_MASK_PARENT) + +#define MTK_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_PCI_MSIX | \ + MSI_FLAG_MULTI_PCI_MSI) + +static const struct msi_parent_ops mtk_msi_parent_ops = { + .required_flags = MTK_MSI_FLAGS_REQUIRED, + .supported_flags = MTK_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .chip_flags = MSI_CHIP_FLAG_SET_ACK, + .prefix = "MTK3-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; static void mtk_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) @@ -684,8 +749,8 @@ static int mtk_pcie_init_irq_domains(struct mtk_gen3_pcie *pcie) return -ENODEV; } - pcie->intx_domain = irq_domain_add_linear(intc_node, PCI_NUM_INTX, - &intx_domain_ops, pcie); + pcie->intx_domain = irq_domain_create_linear(of_fwnode_handle(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; @@ -695,28 +760,23 @@ static int mtk_pcie_init_irq_domains(struct mtk_gen3_pcie *pcie) /* 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); + struct irq_domain_info info = { + .fwnode = dev_fwnode(dev), + .ops = &mtk_msi_bottom_domain_ops, + .host_data = pcie, + .size = PCIE_MSI_IRQS_NUM, + }; + + pcie->msi_bottom_domain = msi_create_parent_irq_domain(&info, &mtk_msi_parent_ops); 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: @@ -731,9 +791,6 @@ static void mtk_pcie_irq_teardown(struct mtk_gen3_pcie *pcie) 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); @@ -813,6 +870,7 @@ 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; + u32 num_lanes; regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pcie-mac"); if (!regs) @@ -828,7 +886,8 @@ static int mtk_pcie_parse_port(struct mtk_gen3_pcie *pcie) for (i = 0; i < num_resets; i++) pcie->phy_resets[i].id = pcie->soc->phy_resets.id[i]; - ret = devm_reset_control_bulk_get_optional_shared(dev, num_resets, pcie->phy_resets); + ret = devm_reset_control_bulk_get_optional_shared(dev, num_resets, + pcie->phy_resets); if (ret) { dev_err(dev, "failed to get PHY bulk reset\n"); return ret; @@ -858,21 +917,62 @@ static int mtk_pcie_parse_port(struct mtk_gen3_pcie *pcie) return pcie->num_clks; } + ret = of_property_read_u32(dev->of_node, "num-lanes", &num_lanes); + if (ret == 0) { + if (num_lanes == 0 || num_lanes > 16 || + (num_lanes != 1 && num_lanes % 2)) + dev_warn(dev, "invalid num-lanes, using controller defaults\n"); + else + pcie->num_lanes = num_lanes; + } + return 0; } static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie) { + struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); struct device *dev = pcie->dev; + struct resource_entry *entry; + struct regmap *pbus_regmap; + u32 val, args[2], size; + resource_size_t addr; int err; - u32 val; /* - * Wait for the time needed to complete the bulk assert in - * mtk_pcie_setup for EN7581 SoC. + * 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_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); + + /* Wait for the time needed to complete the reset lines assert. */ + msleep(PCIE_EN7581_RESET_TIME_MS); + + /* + * Configure PBus base address and base address mask to allow the + * hw to detect if a given address is accessible on PCIe controller. */ - mdelay(PCIE_EN7581_RESET_TIME_MS); + pbus_regmap = syscon_regmap_lookup_by_phandle_args(dev->of_node, + "mediatek,pbus-csr", + ARRAY_SIZE(args), + args); + if (IS_ERR(pbus_regmap)) + return PTR_ERR(pbus_regmap); + + entry = resource_list_first_type(&host->windows, IORESOURCE_MEM); + if (!entry) + return -ENODEV; + addr = entry->res->start - entry->offset; + regmap_write(pbus_regmap, args[0], lower_32_bits(addr)); + size = lower_32_bits(resource_size(entry->res)); + regmap_write(pbus_regmap, args[1], GENMASK(31, __fls(size))); + + /* + * Unlike the other MediaTek Gen3 controllers, the Airoha EN7581 + * requires PHY initialization and power-on before PHY reset deassert. + */ err = phy_init(pcie->phy); if (err) { dev_err(dev, "failed to initialize PHY\n"); @@ -885,7 +985,8 @@ static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie) goto err_phy_on; } - err = reset_control_bulk_deassert(pcie->soc->phy_resets.num_resets, pcie->phy_resets); + err = reset_control_bulk_deassert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); if (err) { dev_err(dev, "failed to deassert PHYs\n"); goto err_phy_deassert; @@ -895,17 +996,11 @@ static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie) * Wait for the time needed to complete the bulk de-assert above. * This time is specific for EN7581 SoC. */ - mdelay(PCIE_EN7581_RESET_TIME_MS); + msleep(PCIE_EN7581_RESET_TIME_MS); pm_runtime_enable(dev); pm_runtime_get_sync(dev); - err = clk_bulk_prepare(pcie->num_clks, pcie->clks); - if (err) { - dev_err(dev, "failed to prepare clock\n"); - goto err_clk_prepare; - } - val = FIELD_PREP(PCIE_VAL_LN0_DOWNSTREAM, 0x47) | FIELD_PREP(PCIE_VAL_LN1_DOWNSTREAM, 0x47) | FIELD_PREP(PCIE_VAL_LN0_UPSTREAM, 0x41) | @@ -918,20 +1013,26 @@ static int mtk_pcie_en7581_power_up(struct mtk_gen3_pcie *pcie) FIELD_PREP(PCIE_K_FINETUNE_MAX, 0xf); writel_relaxed(val, pcie->base + PCIE_PIPE4_PIE8_REG); - err = clk_bulk_enable(pcie->num_clks, pcie->clks); + err = clk_bulk_prepare_enable(pcie->num_clks, pcie->clks); if (err) { dev_err(dev, "failed to prepare clock\n"); - goto err_clk_enable; + goto err_clk_prepare_enable; } + /* + * Airoha EN7581 performs PCIe reset via clk callbacks since it has a + * hw issue with PCIE_PE_RSTB signal. Add wait for the time needed to + * complete the PCIe reset. + */ + msleep(PCIE_T_PVPERL_MS); + return 0; -err_clk_enable: - clk_bulk_unprepare(pcie->num_clks, pcie->clks); -err_clk_prepare: +err_clk_prepare_enable: pm_runtime_put_sync(dev); pm_runtime_disable(dev); - reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, pcie->phy_resets); + reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); err_phy_deassert: phy_power_off(pcie->phy); err_phy_on: @@ -945,8 +1046,18 @@ static int mtk_pcie_power_up(struct mtk_gen3_pcie *pcie) struct device *dev = pcie->dev; int 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_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); + reset_control_assert(pcie->mac_reset); + usleep_range(PCIE_MTK_RESET_TIME_US, 2 * PCIE_MTK_RESET_TIME_US); + /* PHY power on and enable pipe clock */ - err = reset_control_bulk_deassert(pcie->soc->phy_resets.num_resets, pcie->phy_resets); + err = reset_control_bulk_deassert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); if (err) { dev_err(dev, "failed to deassert PHYs\n"); return err; @@ -986,7 +1097,8 @@ err_clk_init: err_phy_on: phy_exit(pcie->phy); err_phy_init: - reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, pcie->phy_resets); + reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); return err; } @@ -1001,12 +1113,25 @@ static void mtk_pcie_power_down(struct mtk_gen3_pcie *pcie) phy_power_off(pcie->phy); phy_exit(pcie->phy); - reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, pcie->phy_resets); + reset_control_bulk_assert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); +} + +static int mtk_pcie_get_controller_max_link_speed(struct mtk_gen3_pcie *pcie) +{ + u32 val; + int ret; + + val = readl_relaxed(pcie->base + PCIE_BASE_CFG_REG); + val = FIELD_GET(PCIE_BASE_CFG_SPEED, val); + ret = fls(val); + + return ret > 0 ? ret : -EINVAL; } static int mtk_pcie_setup(struct mtk_gen3_pcie *pcie) { - int err; + int err, max_speed; err = mtk_pcie_parse_port(pcie); if (err) @@ -1016,21 +1141,28 @@ static int mtk_pcie_setup(struct mtk_gen3_pcie *pcie) * Deassert the line in order to avoid unbalance in deassert_count * counter since the bulk is shared. */ - reset_control_bulk_deassert(pcie->soc->phy_resets.num_resets, pcie->phy_resets); - /* - * 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_bulk_assert(pcie->soc->phy_resets.num_resets, pcie->phy_resets); - - reset_control_assert(pcie->mac_reset); - usleep_range(10, 20); + reset_control_bulk_deassert(pcie->soc->phy_resets.num_resets, + pcie->phy_resets); /* Don't touch the hardware registers before power up */ err = pcie->soc->power_up(pcie); if (err) return err; + err = of_pci_get_max_link_speed(pcie->dev->of_node); + if (err) { + /* Get the maximum speed supported by the controller */ + max_speed = mtk_pcie_get_controller_max_link_speed(pcie); + + /* Set max_link_speed only if the controller supports it */ + if (max_speed >= 0 && max_speed <= err) { + pcie->max_link_speed = err; + dev_info(pcie->dev, + "maximum controller link speed Gen%d, overriding to Gen%u", + max_speed, pcie->max_link_speed); + } + } + /* Try link up */ err = mtk_pcie_startup_port(pcie); if (err) @@ -1160,10 +1292,12 @@ static int mtk_pcie_suspend_noirq(struct device *dev) 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); + if (!(pcie->soc->flags & SKIP_PCIE_RSTB)) { + /* Assert 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"); @@ -1206,6 +1340,15 @@ static const struct mtk_gen3_pcie_pdata mtk_pcie_soc_mt8192 = { }, }; +static const struct mtk_gen3_pcie_pdata mtk_pcie_soc_mt8196 = { + .power_up = mtk_pcie_power_up, + .phy_resets = { + .id[0] = "phy", + .num_resets = 1, + }, + .sys_clk_rdy_time_us = 10, +}; + static const struct mtk_gen3_pcie_pdata mtk_pcie_soc_en7581 = { .power_up = mtk_pcie_en7581_power_up, .phy_resets = { @@ -1214,22 +1357,25 @@ static const struct mtk_gen3_pcie_pdata mtk_pcie_soc_en7581 = { .id[2] = "phy-lane2", .num_resets = 3, }, + .flags = SKIP_PCIE_RSTB, }; static const struct of_device_id mtk_pcie_of_match[] = { { .compatible = "airoha,en7581-pcie", .data = &mtk_pcie_soc_en7581 }, { .compatible = "mediatek,mt8192-pcie", .data = &mtk_pcie_soc_mt8192 }, + { .compatible = "mediatek,mt8196-pcie", .data = &mtk_pcie_soc_mt8196 }, {}, }; MODULE_DEVICE_TABLE(of, mtk_pcie_of_match); static struct platform_driver mtk_pcie_driver = { .probe = mtk_pcie_probe, - .remove_new = mtk_pcie_remove, + .remove = mtk_pcie_remove, .driver = { .name = "mtk-pcie-gen3", .of_match_table = mtk_pcie_of_match, .pm = &mtk_pcie_pm_ops, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, }, }; diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 7f7d04c2ea57..4b78b6528f9f 100644 --- a/drivers/pci/controller/pcie-mediatek.c +++ b/drivers/pci/controller/pcie-mediatek.c @@ -12,6 +12,7 @@ #include <linux/iopoll.h> #include <linux/irq.h> #include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/kernel.h> #include <linux/mfd/syscon.h> @@ -142,23 +143,33 @@ struct mtk_pcie_port; /** + * enum mtk_pcie_quirks - MTK PCIe quirks + * @MTK_PCIE_FIX_CLASS_ID: host's class ID needed to be fixed + * @MTK_PCIE_FIX_DEVICE_ID: host's device ID needed to be fixed + * @MTK_PCIE_NO_MSI: Bridge has no MSI support, and relies on an external block + * @MTK_PCIE_SKIP_RSTB: Skip calling RSTB bits on PCIe probe + */ +enum mtk_pcie_quirks { + MTK_PCIE_FIX_CLASS_ID = BIT(0), + MTK_PCIE_FIX_DEVICE_ID = BIT(1), + MTK_PCIE_NO_MSI = BIT(2), + MTK_PCIE_SKIP_RSTB = BIT(3), +}; + +/** * 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 + * @quirks: PCIe device quirks. */ 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); + enum mtk_pcie_quirks quirks; }; /** @@ -180,7 +191,6 @@ struct mtk_pcie_soc { * @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 */ @@ -200,7 +210,6 @@ struct mtk_pcie_port { 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); }; @@ -470,40 +479,39 @@ static const struct irq_domain_ops msi_domain_ops = { .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, -}; +#define MTK_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) -static struct msi_domain_info mtk_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_NO_AFFINITY | MSI_FLAG_PCI_MSIX, - .chip = &mtk_msi_irq_chip, +#define MTK_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_PCI_MSIX) + +static const struct msi_parent_ops mtk_msi_parent_ops = { + .required_flags = MTK_MSI_FLAGS_REQUIRED, + .supported_flags = MTK_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .chip_flags = MSI_CHIP_FLAG_SET_ACK, + .prefix = "MTK-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; 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); + struct irq_domain_info info = { + .fwnode = dev_fwnode(port->pcie->dev), + .ops = &msi_domain_ops, + .host_data = port, + .size = MTK_MSI_IRQS_NUM, + }; + + port->inner_domain = msi_create_parent_irq_domain(&info, &mtk_msi_parent_ops); 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; } @@ -532,8 +540,6 @@ static void mtk_pcie_irq_teardown(struct mtk_pcie *pcie) 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); } @@ -569,8 +575,8 @@ static int mtk_pcie_init_irq_domain(struct mtk_pcie_port *port, return -ENODEV; } - port->irq_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, - &intx_domain_ops, port); + port->irq_domain = irq_domain_create_linear(of_fwnode_handle(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"); @@ -683,31 +689,28 @@ static int mtk_pcie_startup_port_v2(struct mtk_pcie_port *port) regmap_update_bits(pcie->cfg, PCIE_SYS_CFG_V2, val, val); } - /* Assert all reset signals */ - writel(0, port->base + PCIE_RST_CTRL); + if (!(soc->quirks & MTK_PCIE_SKIP_RSTB)) { + /* 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); + /* + * 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); + msleep(PCIE_T_PVPERL_MS); - /* 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); + /* 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) { + if (soc->quirks & MTK_PCIE_FIX_CLASS_ID) { val = PCI_VENDOR_ID_MEDIATEK; writew(val, port->base + PCIE_CONF_VEND_ID); @@ -715,7 +718,7 @@ static int mtk_pcie_startup_port_v2(struct mtk_pcie_port *port) writew(val, port->base + PCIE_CONF_CLASS_ID); } - if (soc->need_fix_device_id) + if (soc->quirks & MTK_PCIE_FIX_DEVICE_ID) writew(soc->device_id, port->base + PCIE_CONF_DEVICE_ID); /* 100ms timeout value should be enough for Gen1/2 training */ @@ -825,6 +828,41 @@ static int mtk_pcie_startup_port(struct mtk_pcie_port *port) return 0; } +static int mtk_pcie_startup_port_an7583(struct mtk_pcie_port *port) +{ + struct mtk_pcie *pcie = port->pcie; + struct device *dev = pcie->dev; + struct pci_host_bridge *host; + struct resource_entry *entry; + struct regmap *pbus_regmap; + resource_size_t addr; + u32 args[2], size; + + /* + * Configure PBus base address and base address mask to allow + * the hw to detect if a given address is accessible on PCIe + * controller. + */ + pbus_regmap = syscon_regmap_lookup_by_phandle_args(dev->of_node, + "mediatek,pbus-csr", + ARRAY_SIZE(args), + args); + if (IS_ERR(pbus_regmap)) + return PTR_ERR(pbus_regmap); + + host = pci_host_bridge_from_priv(pcie); + entry = resource_list_first_type(&host->windows, IORESOURCE_MEM); + if (!entry) + return -ENODEV; + + addr = entry->res->start - entry->offset; + regmap_write(pbus_regmap, args[0], lower_32_bits(addr)); + size = lower_32_bits(resource_size(entry->res)); + regmap_write(pbus_regmap, args[1], GENMASK(31, __fls(size))); + + return mtk_pcie_startup_port_v2(port); +} + static void mtk_pcie_enable_port(struct mtk_pcie_port *port) { struct mtk_pcie *pcie = port->pcie; @@ -1041,24 +1079,22 @@ err_free_ck: static int mtk_pcie_setup(struct mtk_pcie *pcie) { struct device *dev = pcie->dev; - struct device_node *node = dev->of_node, *child; + struct device_node *node = dev->of_node; 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) { + for_each_available_child_of_node_scoped(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; - } + if (err < 0) + return dev_err_probe(dev, err, "failed to get devfn\n"); slot = PCI_SLOT(err); err = mtk_pcie_parse_port(pcie, child, slot); if (err) - goto error_put_node; + return err; } } else { err = mtk_pcie_parse_port(pcie, node, slot); @@ -1079,9 +1115,6 @@ static int mtk_pcie_setup(struct mtk_pcie *pcie) 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) @@ -1108,7 +1141,7 @@ static int mtk_pcie_probe(struct platform_device *pdev) host->ops = pcie->soc->ops; host->sysdata = pcie; - host->msi_domain = pcie->soc->no_msi; + host->msi_domain = !!(pcie->soc->quirks & MTK_PCIE_NO_MSI); err = pci_host_probe(host); if (err) @@ -1196,9 +1229,9 @@ static const struct dev_pm_ops mtk_pcie_pm_ops = { }; static const struct mtk_pcie_soc mtk_pcie_soc_v1 = { - .no_msi = true, .ops = &mtk_pcie_ops, .startup = mtk_pcie_startup_port, + .quirks = MTK_PCIE_NO_MSI, }; static const struct mtk_pcie_soc mtk_pcie_soc_mt2712 = { @@ -1208,22 +1241,29 @@ static const struct mtk_pcie_soc mtk_pcie_soc_mt2712 = { }; 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, + .quirks = MTK_PCIE_FIX_CLASS_ID, +}; + +static const struct mtk_pcie_soc mtk_pcie_soc_an7583 = { + .ops = &mtk_pcie_ops_v2, + .startup = mtk_pcie_startup_port_an7583, + .setup_irq = mtk_pcie_setup_irq, + .quirks = MTK_PCIE_FIX_CLASS_ID | MTK_PCIE_SKIP_RSTB, }; 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, + .quirks = MTK_PCIE_FIX_CLASS_ID | MTK_PCIE_FIX_DEVICE_ID, }; static const struct of_device_id mtk_pcie_ids[] = { + { .compatible = "airoha,an7583-pcie", .data = &mtk_pcie_soc_an7583 }, { .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 }, @@ -1235,7 +1275,7 @@ MODULE_DEVICE_TABLE(of, mtk_pcie_ids); static struct platform_driver mtk_pcie_driver = { .probe = mtk_pcie_probe, - .remove_new = mtk_pcie_remove, + .remove = mtk_pcie_remove, .driver = { .name = "mtk-pcie", .of_match_table = mtk_pcie_ids, diff --git a/drivers/pci/controller/pcie-mt7621.c b/drivers/pci/controller/pcie-mt7621.c index 9b4754a45515..01ead2f92e87 100644 --- a/drivers/pci/controller/pcie-mt7621.c +++ b/drivers/pci/controller/pcie-mt7621.c @@ -258,30 +258,25 @@ 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; + struct device_node *node = dev->of_node; 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) { + for_each_available_child_of_node_scoped(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; - } + if (err < 0) + return dev_err_probe(dev, err, "failed to parse devfn\n"); slot = PCI_SLOT(err); err = mt7621_pcie_parse_port(pcie, child, slot); - if (err) { - of_node_put(child); + if (err) return err; - } } return 0; @@ -541,7 +536,7 @@ MODULE_DEVICE_TABLE(of, mt7621_pcie_ids); static struct platform_driver mt7621_pcie_driver = { .probe = mt7621_pcie_probe, - .remove_new = mt7621_pcie_remove, + .remove = mt7621_pcie_remove, .driver = { .name = "mt7621-pci", .of_match_table = mt7621_pcie_ids, diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c index 047e2cef5afc..657875ef4657 100644 --- a/drivers/pci/controller/pcie-rcar-ep.c +++ b/drivers/pci/controller/pcie-rcar-ep.c @@ -107,7 +107,7 @@ static int rcar_pcie_parse_outbound_ranges(struct rcar_pcie_endpoint *ep, } if (!devm_request_mem_region(&pdev->dev, res->start, resource_size(res), - outbound_name)) { + res->name)) { dev_err(pcie->dev, "Cannot request memory region %s.\n", outbound_name); return -EIO; @@ -256,15 +256,15 @@ static void rcar_pcie_ep_clear_bar(struct pci_epc *epc, u8 fn, u8 vfn, 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) +static int rcar_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, u8 nr_irqs) { struct rcar_pcie_endpoint *ep = epc_get_drvdata(epc); struct rcar_pcie *pcie = &ep->pcie; + u8 mmc = order_base_2(nr_irqs); u32 flags; flags = rcar_pci_read_reg(pcie, MSICAP(fn)); - flags |= interrupts << MSICAP0_MMESCAP_OFFSET; + flags |= mmc << MSICAP0_MMESCAP_OFFSET; rcar_pci_write_reg(pcie, flags, MSICAP(fn)); return 0; @@ -280,7 +280,7 @@ static int rcar_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) if (!(flags & MSICAP0_MSIE)) return -EINVAL; - return ((flags & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET); + return 1 << ((flags & MSICAP0_MMESE_MASK) >> MSICAP0_MMESE_OFFSET); } static int rcar_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn, @@ -436,9 +436,7 @@ static void rcar_pcie_ep_stop(struct pci_epc *epc) } 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 */ .bar[BAR_0] = { .type = BAR_FIXED, .fixed_size = 128, .only_64bit = true, }, diff --git a/drivers/pci/controller/pcie-rcar-host.c b/drivers/pci/controller/pcie-rcar-host.c index 3dd653f3d784..213028052aa5 100644 --- a/drivers/pci/controller/pcie-rcar-host.c +++ b/drivers/pci/controller/pcie-rcar-host.c @@ -12,11 +12,13 @@ */ #include <linux/bitops.h> +#include <linux/cleanup.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/kernel.h> #include <linux/init.h> @@ -37,7 +39,7 @@ struct rcar_msi { DECLARE_BITMAP(used, INT_PCI_MSI_NR); struct irq_domain *domain; struct mutex map_lock; - spinlock_t mask_lock; + raw_spinlock_t mask_lock; int irq1; int irq2; }; @@ -51,20 +53,13 @@ struct rcar_pcie_host { 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; - } + if (!pcie_base || pm_runtime_suspended(pcie_dev)) + return -EINVAL; pmsr = readl(pcie_base + PMSR); @@ -86,8 +81,6 @@ static int rcar_pcie_wakeup(struct device *pcie_dev, void __iomem *pcie_base) writel(L1FAEG | PMEL1RX, pcie_base + PMSR); } -unlock_exit: - spin_unlock_irqrestore(&pmsr_lock, flags); return ret; } @@ -178,8 +171,8 @@ static int rcar_pcie_config_access(struct rcar_pcie_host *host, * 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. + * controller-initiated target transfer to its own config space + * results in a completer abort. * * Each channel effectively only supports a single device, but as * the same channel <-> device access works for any PCI_SLOT() @@ -583,7 +576,7 @@ static irqreturn_t rcar_pcie_msi_irq(int irq, void *data) unsigned int index = find_first_bit(®, 32); int ret; - ret = generic_handle_domain_irq(msi->domain->parent, index); + ret = generic_handle_domain_irq(msi->domain, index); if (ret) { /* Unknown MSI, just clear it */ dev_dbg(dev, "unexpected MSI\n"); @@ -597,30 +590,6 @@ static irqreturn_t rcar_pcie_msi_irq(int irq, void *data) 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); @@ -634,28 +603,26 @@ 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); + scoped_guard(raw_spinlock_irqsave, &msi->mask_lock) { + value = rcar_pci_read_reg(pcie, PCIEMSIIER); + value &= ~BIT(d->hwirq); + rcar_pci_write_reg(pcie, value, PCIEMSIIER); + } } 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); + scoped_guard(raw_spinlock_irqsave, &msi->mask_lock) { + value = rcar_pci_read_reg(pcie, PCIEMSIIER); + value |= BIT(d->hwirq); + rcar_pci_write_reg(pcie, value, PCIEMSIIER); + } } static void rcar_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) @@ -718,30 +685,36 @@ static const struct irq_domain_ops rcar_msi_domain_ops = { .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_NO_AFFINITY | MSI_FLAG_MULTI_PCI_MSI, - .chip = &rcar_msi_top_chip, +#define RCAR_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_PCI_MSI_MASK_PARENT | \ + MSI_FLAG_NO_AFFINITY) + +#define RCAR_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_MULTI_PCI_MSI) + +static const struct msi_parent_ops rcar_msi_parent_ops = { + .required_flags = RCAR_MSI_FLAGS_REQUIRED, + .supported_flags = RCAR_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .chip_flags = MSI_CHIP_FLAG_SET_ACK, + .prefix = "RCAR-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; 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); + struct irq_domain_info info = { + .fwnode = dev_fwnode(pcie->dev), + .ops = &rcar_msi_domain_ops, + .host_data = msi, + .size = INT_PCI_MSI_NR, + }; + + msi->domain = msi_create_parent_irq_domain(&info, &rcar_msi_parent_ops); if (!msi->domain) { - dev_err(pcie->dev, "failed to create MSI domain\n"); - irq_domain_remove(parent); + dev_err(pcie->dev, "failed to create IRQ domain\n"); return -ENOMEM; } @@ -750,10 +723,7 @@ static int rcar_allocate_domains(struct rcar_msi *msi) 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) @@ -765,7 +735,7 @@ static int rcar_pcie_enable_msi(struct rcar_pcie_host *host) int err; mutex_init(&msi->map_lock); - spin_lock_init(&msi->mask_lock); + raw_spin_lock_init(&msi->mask_lock); err = of_address_to_resource(dev->of_node, 0, &res); if (err) @@ -775,7 +745,7 @@ static int rcar_pcie_enable_msi(struct rcar_pcie_host *host) if (err) return err; - /* Two irqs are for MSI, but they are also used for non-MSI irqs */ + /* 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); @@ -792,12 +762,12 @@ static int rcar_pcie_enable_msi(struct rcar_pcie_host *host) goto err; } - /* disable all MSIs */ + /* 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 R-Car HW. + * Setup MSI data target using RC base address, which is guaranteed + * to be in the low 32bit range on any R-Car HW. */ rcar_pci_write_reg(pcie, lower_32_bits(res.start) | MSIFE, PCIEMSIALR); rcar_pci_write_reg(pcie, upper_32_bits(res.start), PCIEMSIAUR); @@ -892,6 +862,7 @@ static int rcar_pcie_inbound_ranges(struct rcar_pcie *pcie, 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 @@ -903,6 +874,7 @@ static int rcar_pcie_inbound_ranges(struct rcar_pcie *pcie, size = min(size, alignment); } + /* Hardware supports max 4GiB inbound region */ size = min(size, 1ULL << 32); diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index 136274533656..799461335762 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -10,12 +10,16 @@ #include <linux/configfs.h> #include <linux/delay.h> +#include <linux/gpio/consumer.h> +#include <linux/iopoll.h> #include <linux/kernel.h> +#include <linux/irq.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 <linux/workqueue.h> #include "pcie-rockchip.h" @@ -36,6 +40,10 @@ * @irq_pci_fn: the latest PCI function that has updated the mapping of * the MSI/INTX IRQ dedicated outbound region. * @irq_pending: bitmask of asserted INTX IRQs. + * @perst_irq: IRQ used for the PERST# signal. + * @perst_asserted: True if the PERST# signal was asserted. + * @link_up: True if the PCI link is up. + * @link_training: Work item to execute PCI link training. */ struct rockchip_pcie_ep { struct rockchip_pcie rockchip; @@ -48,6 +56,10 @@ struct rockchip_pcie_ep { u64 irq_pci_addr; u8 irq_pci_fn; u8 irq_pending; + int perst_irq; + bool perst_asserted; + bool link_up; + struct delayed_work link_training; }; static void rockchip_pcie_clear_ep_ob_atu(struct rockchip_pcie *rockchip, @@ -63,15 +75,25 @@ static void rockchip_pcie_clear_ep_ob_atu(struct rockchip_pcie *rockchip, ROCKCHIP_PCIE_AT_OB_REGION_DESC1(region)); } +static int rockchip_pcie_ep_ob_atu_num_bits(struct rockchip_pcie *rockchip, + u64 pci_addr, size_t size) +{ + int num_pass_bits = fls64(pci_addr ^ (pci_addr + size - 1)); + + return clamp(num_pass_bits, + ROCKCHIP_PCIE_AT_MIN_NUM_BITS, + ROCKCHIP_PCIE_AT_MAX_NUM_BITS); +} + 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); + int num_pass_bits; u32 addr0, addr1, desc0; - if (num_pass_bits < 8) - num_pass_bits = 8; + num_pass_bits = rockchip_pcie_ep_ob_atu_num_bits(rockchip, + pci_addr, size); addr0 = ((num_pass_bits - 1) & PCIE_CORE_OB_REGION_ADDR0_NUM_BITS) | (lower_32_bits(pci_addr) & PCIE_CORE_OB_REGION_ADDR0_LO_ADDR); @@ -228,6 +250,28 @@ static inline u32 rockchip_ob_region(phys_addr_t addr) return (addr >> ilog2(SZ_1M)) & 0x1f; } +static u64 rockchip_pcie_ep_align_addr(struct pci_epc *epc, u64 pci_addr, + size_t *pci_size, size_t *addr_offset) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + size_t size = *pci_size; + u64 offset, mask; + int num_bits; + + num_bits = rockchip_pcie_ep_ob_atu_num_bits(&ep->rockchip, + pci_addr, size); + mask = (1ULL << num_bits) - 1; + + offset = pci_addr & mask; + if (size + offset > SZ_1M) + size = SZ_1M - offset; + + *pci_size = ALIGN(offset + size, ROCKCHIP_PCIE_AT_SIZE_ALIGN); + *addr_offset = offset; + + return pci_addr & ~mask; +} + 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) @@ -236,6 +280,9 @@ static int rockchip_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn, struct rockchip_pcie *pcie = &ep->rockchip; u32 r = rockchip_ob_region(addr); + if (test_bit(r, &ep->ob_region_map)) + return -EBUSY; + rockchip_pcie_prog_ep_ob_atu(pcie, fn, r, addr, pci_addr, size); set_bit(r, &ep->ob_region_map); @@ -249,13 +296,9 @@ static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, { 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; + u32 r = rockchip_ob_region(addr); - if (r == ep->max_regions) + if (addr != ep->ob_addr[r] || !test_bit(r, &ep->ob_region_map)) return; rockchip_pcie_clear_ep_ob_atu(rockchip, r); @@ -265,10 +308,11 @@ static void rockchip_pcie_ep_unmap_addr(struct pci_epc *epc, u8 fn, u8 vfn, } static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, - u8 multi_msg_cap) + u8 nr_irqs) { struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); struct rockchip_pcie *rockchip = &ep->rockchip; + u8 mmc = order_base_2(nr_irqs); u32 flags; flags = rockchip_pcie_read(rockchip, @@ -276,7 +320,7 @@ static int rockchip_pcie_ep_set_msi(struct pci_epc *epc, u8 fn, u8 vfn, 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) | + (mmc << 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, @@ -297,8 +341,8 @@ static int rockchip_pcie_ep_get_msi(struct pci_epc *epc, u8 fn, u8 vfn) 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); + return 1 << ((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, @@ -351,9 +395,10 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn, { struct rockchip_pcie *rockchip = &ep->rockchip; u32 flags, mme, data, data_mask; + size_t irq_pci_size, offset; + u64 irq_pci_addr; u8 msi_count; u64 pci_addr; - u32 r; /* Check MSI enable bit */ flags = rockchip_pcie_read(&ep->rockchip, @@ -389,18 +434,21 @@ static int rockchip_pcie_ep_send_msi_irq(struct rockchip_pcie_ep *ep, u8 fn, PCI_MSI_ADDRESS_LO); /* Set the outbound region if needed. */ - if (unlikely(ep->irq_pci_addr != (pci_addr & PCIE_ADDR_MASK) || + irq_pci_size = ~PCIE_ADDR_MASK + 1; + irq_pci_addr = rockchip_pcie_ep_align_addr(ep->epc, + pci_addr & PCIE_ADDR_MASK, + &irq_pci_size, &offset); + if (unlikely(ep->irq_pci_addr != irq_pci_addr || 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); + rockchip_pcie_prog_ep_ob_atu(rockchip, fn, + rockchip_ob_region(ep->irq_phys_addr), + ep->irq_phys_addr, + irq_pci_addr, irq_pci_size); + ep->irq_pci_addr = irq_pci_addr; ep->irq_pci_fn = fn; } - writew(data, ep->irq_cpu_addr + (pci_addr & ~PCIE_ADDR_MASK)); + writew(data, ep->irq_cpu_addr + offset + (pci_addr & ~PCIE_ADDR_MASK)); return 0; } @@ -432,14 +480,222 @@ static int rockchip_pcie_ep_start(struct pci_epc *epc) rockchip_pcie_write(rockchip, cfg, PCIE_CORE_PHY_FUNC_CFG); + if (rockchip->perst_gpio) + enable_irq(ep->perst_irq); + + /* Enable configuration and start link training */ + rockchip_pcie_write(rockchip, + PCIE_CLIENT_LINK_TRAIN_ENABLE | + PCIE_CLIENT_CONF_ENABLE, + PCIE_CLIENT_CONFIG); + + if (!rockchip->perst_gpio) + schedule_delayed_work(&ep->link_training, 0); + + return 0; +} + +static void rockchip_pcie_ep_stop(struct pci_epc *epc) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + + if (rockchip->perst_gpio) { + ep->perst_asserted = true; + disable_irq(ep->perst_irq); + } + + cancel_delayed_work_sync(&ep->link_training); + + /* Stop link training and disable configuration */ + rockchip_pcie_write(rockchip, + PCIE_CLIENT_CONF_DISABLE | + PCIE_CLIENT_LINK_TRAIN_DISABLE, + PCIE_CLIENT_CONFIG); +} + +static void rockchip_pcie_ep_retrain_link(struct rockchip_pcie *rockchip) +{ + u32 status; + + status = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_BASE + PCI_EXP_LNKCTL); + status |= PCI_EXP_LNKCTL_RL; + rockchip_pcie_write(rockchip, status, PCIE_EP_CONFIG_BASE + PCI_EXP_LNKCTL); +} + +static bool rockchip_pcie_ep_link_up(struct rockchip_pcie *rockchip) +{ + u32 val = rockchip_pcie_read(rockchip, PCIE_CLIENT_BASIC_STATUS1); + + return PCIE_LINK_UP(val); +} + +static void rockchip_pcie_ep_link_training(struct work_struct *work) +{ + struct rockchip_pcie_ep *ep = + container_of(work, struct rockchip_pcie_ep, link_training.work); + struct rockchip_pcie *rockchip = &ep->rockchip; + struct device *dev = rockchip->dev; + u32 val; + int ret; + + /* Enable Gen1 training and wait for its completion */ + ret = readl_poll_timeout(rockchip->apb_base + PCIE_CORE_CTRL, + val, PCIE_LINK_TRAINING_DONE(val), 50, + LINK_TRAIN_TIMEOUT); + if (ret) + goto again; + + /* Make sure that the link is up */ + ret = readl_poll_timeout(rockchip->apb_base + PCIE_CLIENT_BASIC_STATUS1, + val, PCIE_LINK_UP(val), 50, + LINK_TRAIN_TIMEOUT); + if (ret) + goto again; + + /* + * Check the current speed: if gen2 speed was requested and we are not + * at gen2 speed yet, retrain again for gen2. + */ + val = rockchip_pcie_read(rockchip, PCIE_CORE_CTRL); + if (!PCIE_LINK_IS_GEN2(val) && rockchip->link_gen == 2) { + /* Enable retrain for gen2 */ + rockchip_pcie_ep_retrain_link(rockchip); + readl_poll_timeout(rockchip->apb_base + PCIE_CORE_CTRL, + val, PCIE_LINK_IS_GEN2(val), 50, + LINK_TRAIN_TIMEOUT); + } + + /* Check again that the link is up */ + if (!rockchip_pcie_ep_link_up(rockchip)) + goto again; + + /* + * If PERST# was asserted while polling the link, do not notify + * the function. + */ + if (ep->perst_asserted) + return; + + val = rockchip_pcie_read(rockchip, PCIE_CLIENT_BASIC_STATUS0); + dev_info(dev, + "link up (negotiated speed: %sGT/s, width: x%lu)\n", + (val & PCIE_CLIENT_NEG_LINK_SPEED) ? "5" : "2.5", + ((val & PCIE_CLIENT_NEG_LINK_WIDTH_MASK) >> + PCIE_CLIENT_NEG_LINK_WIDTH_SHIFT) << 1); + + /* Notify the function */ + pci_epc_linkup(ep->epc); + ep->link_up = true; + + return; + +again: + schedule_delayed_work(&ep->link_training, msecs_to_jiffies(5)); +} + +static void rockchip_pcie_ep_perst_assert(struct rockchip_pcie_ep *ep) +{ + struct rockchip_pcie *rockchip = &ep->rockchip; + + dev_dbg(rockchip->dev, "PERST# asserted, link down\n"); + + if (ep->perst_asserted) + return; + + ep->perst_asserted = true; + + cancel_delayed_work_sync(&ep->link_training); + + if (ep->link_up) { + pci_epc_linkdown(ep->epc); + ep->link_up = false; + } +} + +static void rockchip_pcie_ep_perst_deassert(struct rockchip_pcie_ep *ep) +{ + struct rockchip_pcie *rockchip = &ep->rockchip; + + dev_dbg(rockchip->dev, "PERST# de-asserted, starting link training\n"); + + if (!ep->perst_asserted) + return; + + ep->perst_asserted = false; + + /* Enable link re-training */ + rockchip_pcie_ep_retrain_link(rockchip); + + /* Start link training */ + schedule_delayed_work(&ep->link_training, 0); +} + +static irqreturn_t rockchip_pcie_ep_perst_irq_thread(int irq, void *data) +{ + struct pci_epc *epc = data; + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + u32 perst = gpiod_get_value(rockchip->perst_gpio); + + if (perst) + rockchip_pcie_ep_perst_assert(ep); + else + rockchip_pcie_ep_perst_deassert(ep); + + irq_set_irq_type(ep->perst_irq, + (perst ? IRQF_TRIGGER_HIGH : IRQF_TRIGGER_LOW)); + + return IRQ_HANDLED; +} + +static int rockchip_pcie_ep_setup_irq(struct pci_epc *epc) +{ + struct rockchip_pcie_ep *ep = epc_get_drvdata(epc); + struct rockchip_pcie *rockchip = &ep->rockchip; + struct device *dev = rockchip->dev; + int ret; + + if (!rockchip->perst_gpio) + return 0; + + /* PCIe reset interrupt */ + ep->perst_irq = gpiod_to_irq(rockchip->perst_gpio); + if (ep->perst_irq < 0) { + dev_err(dev, + "failed to get IRQ for PERST# GPIO: %d\n", + ep->perst_irq); + + return ep->perst_irq; + } + + /* + * The perst_gpio is active low, so when it is inactive on start, it + * is high and will trigger the perst_irq handler. So treat this initial + * IRQ as a dummy one by faking the host asserting PERST#. + */ + ep->perst_asserted = true; + irq_set_status_flags(ep->perst_irq, IRQ_NOAUTOEN); + ret = devm_request_threaded_irq(dev, ep->perst_irq, NULL, + rockchip_pcie_ep_perst_irq_thread, + IRQF_TRIGGER_HIGH | IRQF_ONESHOT, + "pcie-ep-perst", epc); + if (ret) { + dev_err(dev, + "failed to request IRQ for PERST# GPIO: %d\n", + ret); + + return ret; + } + return 0; } static const struct pci_epc_features rockchip_pcie_epc_features = { - .linkup_notifier = false, + .linkup_notifier = true, .msi_capable = true, - .msix_capable = false, - .align = 256, + .intx_capable = true, + .align = ROCKCHIP_PCIE_AT_SIZE_ALIGN, }; static const struct pci_epc_features* @@ -452,17 +708,19 @@ 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, + .align_addr = rockchip_pcie_ep_align_addr, .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, + .stop = rockchip_pcie_ep_stop, .get_features = rockchip_pcie_ep_get_features, }; -static int rockchip_pcie_parse_ep_dt(struct rockchip_pcie *rockchip, - struct rockchip_pcie_ep *ep) +static int rockchip_pcie_ep_get_resources(struct rockchip_pcie *rockchip, + struct rockchip_pcie_ep *ep) { struct device *dev = rockchip->dev; int err; @@ -496,82 +754,38 @@ static const struct of_device_id rockchip_pcie_ep_of_match[] = { {}, }; -static int rockchip_pcie_ep_probe(struct platform_device *pdev) +static int rockchip_pcie_ep_init_ob_mem(struct rockchip_pcie_ep *ep) { - struct device *dev = &pdev->dev; - struct rockchip_pcie_ep *ep; - struct rockchip_pcie *rockchip; - struct pci_epc *epc; - size_t max_regions; + struct rockchip_pcie *rockchip = &ep->rockchip; + struct device *dev = rockchip->dev; 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), + ep->ob_addr = devm_kcalloc(dev, ep->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); + if (!ep->ob_addr) + return -ENOMEM; windows = devm_kcalloc(dev, ep->max_regions, sizeof(struct pci_epc_mem_window), GFP_KERNEL); - if (!windows) { - err = -ENOMEM; - goto err_uninit_port; - } + if (!windows) + return -ENOMEM; + 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); + err = pci_epc_multi_mem_init(ep->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; + return err; } - ep->irq_cpu_addr = pci_epc_mem_alloc_addr(epc, &ep->irq_phys_addr, + ep->irq_cpu_addr = pci_epc_mem_alloc_addr(ep->epc, &ep->irq_phys_addr, SZ_1M); if (!ep->irq_cpu_addr) { dev_err(dev, "failed to reserve memory space for MSI\n"); @@ -581,6 +795,23 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev) ep->irq_pci_addr = ROCKCHIP_PCIE_EP_DUMMY_IRQ_ADDR; + return 0; + +err_epc_mem_exit: + pci_epc_mem_exit(ep->epc); + + return err; +} + +static void rockchip_pcie_ep_exit_ob_mem(struct rockchip_pcie_ep *ep) +{ + pci_epc_mem_exit(ep->epc); +} + +static void rockchip_pcie_ep_hide_broken_msix_cap(struct rockchip_pcie *rockchip) +{ + u32 cfg_msi, cfg_msix_cp; + /* * MSI-X is not supported but the controller still advertises the MSI-X * capability by default, which can lead to the Root Complex side @@ -603,19 +834,68 @@ static int rockchip_pcie_ep_probe(struct platform_device *pdev) 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); +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; + int err; + + ep = devm_kzalloc(dev, sizeof(*ep), GFP_KERNEL); + if (!ep) + return -ENOMEM; + + rockchip = &ep->rockchip; + rockchip->is_rc = false; + rockchip->dev = dev; + INIT_DELAYED_WORK(&ep->link_training, rockchip_pcie_ep_link_training); + + 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_ep_get_resources(rockchip, ep); + if (err) + return err; + + err = rockchip_pcie_ep_init_ob_mem(ep); + if (err) + return err; + + err = rockchip_pcie_enable_clocks(rockchip); + if (err) + goto err_exit_ob_mem; + + err = rockchip_pcie_init_port(rockchip); + if (err) + goto err_disable_clocks; + + rockchip_pcie_ep_hide_broken_msix_cap(rockchip); + + /* Only enable function 0 by default */ + rockchip_pcie_write(rockchip, BIT(0), PCIE_CORE_PHY_FUNC_CFG); pci_epc_init_notify(epc); + err = rockchip_pcie_ep_setup_irq(epc); + if (err < 0) + goto err_uninit_port; + 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); +err_exit_ob_mem: + rockchip_pcie_ep_exit_ob_mem(ep); return err; } diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c index cbec71114825..ee1822ca01db 100644 --- a/drivers/pci/controller/pcie-rockchip-host.c +++ b/drivers/pci/controller/pcie-rockchip-host.c @@ -11,27 +11,19 @@ * ARM PCI Host generic driver. */ +#include <linux/bitfield.h> #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.h> #include <linux/of_pci.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" @@ -40,18 +32,18 @@ static void rockchip_pcie_enable_bw_int(struct rockchip_pcie *rockchip) { u32 status; - status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); status |= (PCI_EXP_LNKCTL_LBMIE | PCI_EXP_LNKCTL_LABIE); - rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); } static void rockchip_pcie_clr_bw_int(struct rockchip_pcie *rockchip) { u32 status; - status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); status |= (PCI_EXP_LNKSTA_LBMS | PCI_EXP_LNKSTA_LABS) << 16; - rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); } static void rockchip_pcie_update_txcredit_mui(struct rockchip_pcie *rockchip) @@ -269,7 +261,7 @@ static void rockchip_pcie_set_power_limit(struct rockchip_pcie *rockchip) scale = 3; /* 0.001x */ curr = curr / 1000; /* convert to mA */ power = (curr * 3300) / 1000; /* milliwatt */ - while (power > PCIE_RC_CONFIG_DCR_CSPL_LIMIT) { + while (power > FIELD_MAX(PCI_EXP_DEVCAP_PWR_VAL)) { if (!scale) { dev_warn(rockchip->dev, "invalid power supply\n"); return; @@ -278,10 +270,10 @@ static void rockchip_pcie_set_power_limit(struct rockchip_pcie *rockchip) 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); + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_CR + PCI_EXP_DEVCAP); + status |= FIELD_PREP(PCI_EXP_DEVCAP_PWR_VAL, power); + status |= FIELD_PREP(PCI_EXP_DEVCAP_PWR_SCL, scale); + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_CR + PCI_EXP_DEVCAP); } /** @@ -294,7 +286,7 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip) int err, i = MAX_LANE_NUM; u32 status; - gpiod_set_value_cansleep(rockchip->ep_gpio, 0); + gpiod_set_value_cansleep(rockchip->perst_gpio, 0); err = rockchip_pcie_init_port(rockchip); if (err) @@ -309,23 +301,23 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip) rockchip_pcie_set_power_limit(rockchip); /* Set RC's clock architecture as common clock */ - status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); status |= PCI_EXP_LNKSTA_SLC << 16; - rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); /* Set RC's RCB to 128 */ - status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); status |= PCI_EXP_LNKCTL_RCB; - rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); /* Enable Gen1 training */ rockchip_pcie_write(rockchip, PCIE_CLIENT_LINK_TRAIN_ENABLE, PCIE_CLIENT_CONFIG); msleep(PCIE_T_PVPERL_MS); - gpiod_set_value_cansleep(rockchip->ep_gpio, 1); + gpiod_set_value_cansleep(rockchip->perst_gpio, 1); - msleep(PCIE_T_RRS_READY_MS); + msleep(PCIE_RESET_CONFIG_WAIT_MS); /* 500ms timeout value should be enough for Gen1/2 training */ err = readl_poll_timeout(rockchip->apb_base + PCIE_CLIENT_BASIC_STATUS1, @@ -341,9 +333,13 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip) * Enable retrain for gen2. This should be configured only after * gen1 finished. */ - status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_LCS); + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL2); + status &= ~PCI_EXP_LNKCTL2_TLS; + status |= PCI_EXP_LNKCTL2_TLS_5_0GT; + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL2); + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); status |= PCI_EXP_LNKCTL_RL; - rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_LCS); + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCTL); err = readl_poll_timeout(rockchip->apb_base + PCIE_CORE_CTRL, status, PCIE_LINK_IS_GEN2(status), 20, @@ -367,7 +363,7 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip) } } - rockchip_pcie_write(rockchip, ROCKCHIP_VENDOR_ID, + rockchip_pcie_write(rockchip, PCI_VENDOR_ID_ROCKCHIP, PCIE_CORE_CONFIG_VENDOR); rockchip_pcie_write(rockchip, PCI_CLASS_BRIDGE_PCI_NORMAL << 8, @@ -380,15 +376,15 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip) /* 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_CR + PCI_EXP_LNKCAP); + status &= ~PCI_EXP_LNKCAP_ASPM_L0S; + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_CR + PCI_EXP_LNKCAP); } - 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); + status = rockchip_pcie_read(rockchip, PCIE_RC_CONFIG_CR + PCI_EXP_DEVCTL); + status &= ~PCI_EXP_DEVCTL_PAYLOAD; + status |= PCI_EXP_DEVCTL_PAYLOAD_256B; + rockchip_pcie_write(rockchip, status, PCIE_RC_CONFIG_CR + PCI_EXP_DEVCTL); return 0; err_power_off_phy: @@ -439,7 +435,7 @@ static irqreturn_t rockchip_pcie_subsys_irq_handler(int irq, void *arg) 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"); + dev_dbg(dev, "Unexpected Completion 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"); @@ -489,7 +485,7 @@ static irqreturn_t rockchip_pcie_client_irq_handler(int irq, void *arg) dev_dbg(dev, "fatal error interrupt received\n"); if (reg & PCIE_CLIENT_INT_NFATAL_ERR) - dev_dbg(dev, "no fatal error interrupt received\n"); + dev_dbg(dev, "non fatal error interrupt received\n"); if (reg & PCIE_CLIENT_INT_CORR_ERR) dev_dbg(dev, "correctable error interrupt received\n"); @@ -693,8 +689,8 @@ static int rockchip_pcie_init_irq_domain(struct rockchip_pcie *rockchip) return -EINVAL; } - rockchip->irq_domain = irq_domain_add_linear(intc, PCI_NUM_INTX, - &intx_domain_ops, rockchip); + rockchip->irq_domain = irq_domain_create_linear(of_fwnode_handle(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"); @@ -1050,7 +1046,7 @@ static struct platform_driver rockchip_pcie_driver = { .pm = &rockchip_pcie_pm_ops, }, .probe = rockchip_pcie_probe, - .remove_new = rockchip_pcie_remove, + .remove = rockchip_pcie_remove, }; module_platform_driver(rockchip_pcie_driver); diff --git a/drivers/pci/controller/pcie-rockchip.c b/drivers/pci/controller/pcie-rockchip.c index c07d7129f1c7..0f88da378805 100644 --- a/drivers/pci/controller/pcie-rockchip.c +++ b/drivers/pci/controller/pcie-rockchip.c @@ -30,7 +30,7 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) struct platform_device *pdev = to_platform_device(dev); struct device_node *node = dev->of_node; struct resource *regs; - int err; + int err, i; if (rockchip->is_rc) { regs = platform_get_resource_byname(pdev, @@ -69,87 +69,38 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip) 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); - } + for (i = 0; i < ROCKCHIP_NUM_PM_RSTS; i++) + rockchip->pm_rsts[i].id = rockchip_pci_pm_rsts[i]; - 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_LOW); - if (IS_ERR(rockchip->ep_gpio)) - return dev_err_probe(dev, PTR_ERR(rockchip->ep_gpio), - "failed to get ep GPIO\n"); - } + err = devm_reset_control_bulk_get_exclusive(dev, + ROCKCHIP_NUM_PM_RSTS, + rockchip->pm_rsts); + if (err) + return dev_err_probe(dev, err, "Cannot get the PM reset\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); - } + for (i = 0; i < ROCKCHIP_NUM_CORE_RSTS; i++) + rockchip->core_rsts[i].id = rockchip_pci_core_rsts[i]; - 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); - } + err = devm_reset_control_bulk_get_exclusive(dev, + ROCKCHIP_NUM_CORE_RSTS, + rockchip->core_rsts); + if (err) + return dev_err_probe(dev, err, "Cannot get the Core resets\n"); - 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); - } + if (rockchip->is_rc) + rockchip->perst_gpio = devm_gpiod_get_optional(dev, "ep", + GPIOD_OUT_LOW); + else + rockchip->perst_gpio = devm_gpiod_get_optional(dev, "reset", + GPIOD_IN); + if (IS_ERR(rockchip->perst_gpio)) + return dev_err_probe(dev, PTR_ERR(rockchip->perst_gpio), + "failed to get PERST# GPIO\n"); - 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); - } + rockchip->num_clks = devm_clk_bulk_get_all(dev, &rockchip->clks); + if (rockchip->num_clks < 0) + return dev_err_probe(dev, rockchip->num_clks, + "failed to get clocks\n"); return 0; } @@ -167,23 +118,10 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) 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; - } + err = reset_control_bulk_assert(ROCKCHIP_NUM_PM_RSTS, + rockchip->pm_rsts); + if (err) + return dev_err_probe(dev, err, "Couldn't assert PM resets\n"); for (i = 0; i < MAX_LANE_NUM; i++) { err = phy_init(rockchip->phys[i]); @@ -193,47 +131,19 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) } } - 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); + err = reset_control_bulk_assert(ROCKCHIP_NUM_CORE_RSTS, + rockchip->core_rsts); 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); + dev_err_probe(dev, err, "Couldn't assert Core resets\n"); 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); + err = reset_control_bulk_deassert(ROCKCHIP_NUM_PM_RSTS, + rockchip->pm_rsts); 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); + dev_err(dev, "Couldn't deassert PM resets %d\n", err); goto err_exit_phy; } @@ -244,11 +154,12 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) rockchip_pcie_write(rockchip, PCIE_CLIENT_GEN_SEL_1, PCIE_CLIENT_CONFIG); - regs = PCIE_CLIENT_LINK_TRAIN_ENABLE | PCIE_CLIENT_ARI_ENABLE | + regs = PCIE_CLIENT_ARI_ENABLE | PCIE_CLIENT_CONF_LANE_NUM(rockchip->lanes); if (rockchip->is_rc) - regs |= PCIE_CLIENT_CONF_ENABLE | PCIE_CLIENT_MODE_RC; + regs |= PCIE_CLIENT_LINK_TRAIN_ENABLE | + PCIE_CLIENT_CONF_ENABLE | PCIE_CLIENT_MODE_RC; else regs |= PCIE_CLIENT_CONF_DISABLE | PCIE_CLIENT_MODE_EP; @@ -272,31 +183,10 @@ int rockchip_pcie_init_port(struct rockchip_pcie *rockchip) 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); + err = reset_control_bulk_deassert(ROCKCHIP_NUM_CORE_RSTS, + rockchip->core_rsts); if (err) { - dev_err(dev, "deassert pipe_rst err %d\n", err); + dev_err(dev, "Couldn't deassert Core reset %d\n", err); goto err_power_off_phy; } @@ -372,50 +262,18 @@ 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; - } + err = clk_bulk_prepare_enable(rockchip->num_clks, rockchip->clks); + if (err) + return dev_err_probe(dev, err, "failed to enable clocks\n"); 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) +void rockchip_pcie_disable_clocks(struct rockchip_pcie *rockchip) { - 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); + clk_bulk_disable_unprepare(rockchip->num_clks, rockchip->clks); } EXPORT_SYMBOL_GPL(rockchip_pcie_disable_clocks); diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h index 6111de35f84c..3e82a69b9c00 100644 --- a/drivers/pci/controller/pcie-rockchip.h +++ b/drivers/pci/controller/pcie-rockchip.h @@ -11,44 +11,53 @@ #ifndef _PCIE_ROCKCHIP_H #define _PCIE_ROCKCHIP_H +#include <linux/clk.h> +#include <linux/hw_bitfield.h> #include <linux/kernel.h> #include <linux/pci.h> #include <linux/pci-ecam.h> +#include <linux/reset.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 HWORD_SET_BIT(val) (FIELD_PREP_WM16_CONST((val), 1)) +#define HWORD_CLR_BIT(val) (FIELD_PREP_WM16_CONST((val), 0)) -#define ENCODE_LANES(x) ((((x) >> 1) & 3) << 4) +#define ENCODE_LANES(x) ((((x) >> 1) & 3)) #define MAX_LANE_NUM 4 #define MAX_REGION_LIMIT 32 #define MIN_EP_APERTURE 28 +#define LINK_TRAIN_TIMEOUT (500 * USEC_PER_MSEC) #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_CONF_ENABLE HWORD_SET_BIT(0x0001) +#define PCIE_CLIENT_CONF_DISABLE HWORD_CLR_BIT(0x0001) +#define PCIE_CLIENT_LINK_TRAIN_ENABLE HWORD_SET_BIT(0x0002) +#define PCIE_CLIENT_LINK_TRAIN_DISABLE HWORD_CLR_BIT(0x0002) +#define PCIE_CLIENT_ARI_ENABLE HWORD_SET_BIT(0x0008) +#define PCIE_CLIENT_CONF_LANE_NUM(x) FIELD_PREP_WM16(0x0030, ENCODE_LANES(x)) +#define PCIE_CLIENT_MODE_RC HWORD_SET_BIT(0x0040) +#define PCIE_CLIENT_MODE_EP HWORD_CLR_BIT(0x0040) +#define PCIE_CLIENT_GEN_SEL_1 HWORD_CLR_BIT(0x0080) +#define PCIE_CLIENT_GEN_SEL_2 HWORD_SET_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_INT_IN_ASSERT HWORD_SET_BIT(0x0002) +#define PCIE_CLIENT_INT_IN_DEASSERT HWORD_CLR_BIT(0x0002) +#define PCIE_CLIENT_INT_PEND_ST_PEND HWORD_SET_BIT(0x0001) +#define PCIE_CLIENT_INT_PEND_ST_NORMAL HWORD_CLR_BIT(0x0001) #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_STATUS0 (PCIE_CLIENT_BASE + 0x44) +#define PCIE_CLIENT_NEG_LINK_WIDTH_MASK GENMASK(7, 6) +#define PCIE_CLIENT_NEG_LINK_WIDTH_SHIFT 6 +#define PCIE_CLIENT_NEG_LINK_SPEED BIT(5) #define PCIE_CLIENT_BASIC_STATUS1 (PCIE_CLIENT_BASE + 0x48) #define PCIE_CLIENT_LINK_STATUS_UP 0x00300000 #define PCIE_CLIENT_LINK_STATUS_MASK 0x00300000 @@ -86,6 +95,8 @@ #define PCIE_CORE_CTRL_MGMT_BASE 0x900000 #define PCIE_CORE_CTRL (PCIE_CORE_CTRL_MGMT_BASE + 0x000) +#define PCIE_CORE_PL_CONF_LS_MASK 0x00000001 +#define PCIE_CORE_PL_CONF_LS_READY 0x00000001 #define PCIE_CORE_PL_CONF_SPEED_5G 0x00000008 #define PCIE_CORE_PL_CONF_SPEED_MASK 0x00000018 #define PCIE_CORE_PL_CONF_LANE_MASK 0x00000006 @@ -143,17 +154,9 @@ #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_EP_CONFIG_LCS (PCIE_EP_CONFIG_BASE + 0xd0) #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_CR (PCIE_RC_CONFIG_BASE + 0xc0) #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) @@ -188,9 +191,10 @@ #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_TRAINING_DONE(x) \ + (((x) & PCIE_CORE_PL_CONF_LS_MASK) == PCIE_CORE_PL_CONF_LS_READY) #define PCIE_LINK_UP(x) \ (((x) & PCIE_CLIENT_LINK_STATUS_MASK) == PCIE_CLIENT_LINK_STATUS_UP) #define PCIE_LINK_IS_GEN2(x) \ @@ -202,20 +206,6 @@ #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) @@ -241,10 +231,20 @@ #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_AT_MIN_NUM_BITS 8 +#define ROCKCHIP_PCIE_AT_MAX_NUM_BITS 20 +#define ROCKCHIP_PCIE_AT_SIZE_ALIGN (1UL << ROCKCHIP_PCIE_AT_MIN_NUM_BITS) + #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_MIN_NUM_BITS 8 +#define ROCKCHIP_PCIE_AT_MAX_NUM_BITS 20 +#define ROCKCHIP_PCIE_AT_SIZE_ALIGN (1UL << ROCKCHIP_PCIE_AT_MIN_NUM_BITS) + #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) \ @@ -287,27 +287,37 @@ (((c) << ((b) * 8 + 5)) & \ ROCKCHIP_PCIE_CORE_EP_FUNC_BAR_CFG_BAR_CTRL_MASK(b)) +#define ROCKCHIP_NUM_PM_RSTS ARRAY_SIZE(rockchip_pci_pm_rsts) +#define ROCKCHIP_NUM_CORE_RSTS ARRAY_SIZE(rockchip_pci_core_rsts) + +static const char * const rockchip_pci_pm_rsts[] = { + "pm", + "pclk", + "aclk", +}; + +/* NOTE: Do not reorder the deassert sequence of the following reset pins */ +static const char * const rockchip_pci_core_rsts[] = { + "pipe", + "mgmt", + "core", + "mgmt-sticky", +}; + 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 reset_control_bulk_data pm_rsts[ROCKCHIP_NUM_PM_RSTS]; + struct reset_control_bulk_data core_rsts[ROCKCHIP_NUM_CORE_RSTS]; + struct clk_bulk_data *clks; + int num_clks; 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; + struct gpio_desc *perst_gpio; u32 lanes; u8 lanes_map; int link_gen; @@ -336,7 +346,7 @@ 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_disable_clocks(struct rockchip_pcie *rockchip); void rockchip_pcie_cfg_configuration_accesses( struct rockchip_pcie *rockchip, u32 type); diff --git a/drivers/pci/controller/pcie-rzg3s-host.c b/drivers/pci/controller/pcie-rzg3s-host.c new file mode 100644 index 000000000000..667e6d629474 --- /dev/null +++ b/drivers/pci/controller/pcie-rzg3s-host.c @@ -0,0 +1,1761 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCIe driver for Renesas RZ/G3S SoCs + * + * Copyright (C) 2025 Renesas Electronics Corp. + * + * Based on: + * drivers/pci/controller/pcie-rcar-host.c + * Copyright (C) 2009 - 2011 Paul Mundt + */ + +#include <linux/bitfield.h> +#include <linux/bitmap.h> +#include <linux/bitops.h> +#include <linux/cleanup.h> +#include <linux/clk.h> +#include <linux/delay.h> +#include <linux/iopoll.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> +#include <linux/irqdomain.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/mutex.h> +#include <linux/msi.h> +#include <linux/of_irq.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/pm_runtime.h> +#include <linux/regmap.h> +#include <linux/reset.h> +#include <linux/sizes.h> +#include <linux/slab.h> +#include <linux/units.h> + +#include "../pci.h" + +/* AXI registers */ +#define RZG3S_PCI_REQDATA(id) (0x80 + (id) * 0x4) +#define RZG3S_PCI_REQRCVDAT 0x8c + +#define RZG3S_PCI_REQADR1 0x90 +#define RZG3S_PCI_REQADR1_BUS GENMASK(31, 24) +#define RZG3S_PCI_REQADR1_DEV GENMASK(23, 19) +#define RZG3S_PCI_REQADR1_FUNC GENMASK(18, 16) +#define RZG3S_PCI_REQADR1_REG GENMASK(11, 0) + +#define RZG3S_PCI_REQBE 0x98 +#define RZG3S_PCI_REQBE_BYTE_EN GENMASK(3, 0) + +#define RZG3S_PCI_REQISS 0x9c +#define RZG3S_PCI_REQISS_MOR_STATUS GENMASK(18, 16) +#define RZG3S_PCI_REQISS_TR_TYPE GENMASK(11, 8) +#define RZG3S_PCI_REQISS_TR_TP0_RD FIELD_PREP(RZG3S_PCI_REQISS_TR_TYPE, 0x4) +#define RZG3S_PCI_REQISS_TR_TP0_WR FIELD_PREP(RZG3S_PCI_REQISS_TR_TYPE, 0x5) +#define RZG3S_PCI_REQISS_TR_TP1_RD FIELD_PREP(RZG3S_PCI_REQISS_TR_TYPE, 0x6) +#define RZG3S_PCI_REQISS_TR_TP1_WR FIELD_PREP(RZG3S_PCI_REQISS_TR_TYPE, 0x7) +#define RZG3S_PCI_REQISS_REQ_ISSUE BIT(0) + +#define RZG3S_PCI_MSIRCVWADRL 0x100 +#define RZG3S_PCI_MSIRCVWADRL_MASK GENMASK(31, 3) +#define RZG3S_PCI_MSIRCVWADRL_MSG_DATA_ENA BIT(1) +#define RZG3S_PCI_MSIRCVWADRL_ENA BIT(0) + +#define RZG3S_PCI_MSIRCVWADRU 0x104 + +#define RZG3S_PCI_MSIRCVWMSKL 0x108 +#define RZG3S_PCI_MSIRCVWMSKL_MASK GENMASK(31, 2) + +#define RZG3S_PCI_PINTRCVIE 0x110 +#define RZG3S_PCI_PINTRCVIE_INTX(i) BIT(i) +#define RZG3S_PCI_PINTRCVIE_MSI BIT(4) + +#define RZG3S_PCI_PINTRCVIS 0x114 +#define RZG3S_PCI_PINTRCVIS_INTX(i) BIT(i) +#define RZG3S_PCI_PINTRCVIS_MSI BIT(4) + +#define RZG3S_PCI_MSGRCVIE 0x120 +#define RZG3S_PCI_MSGRCVIE_MSG_RCV BIT(24) + +#define RZG3S_PCI_MSGRCVIS 0x124 +#define RZG3S_PCI_MSGRCVIS_MRI BIT(24) + +#define RZG3S_PCI_PEIE0 0x200 + +#define RZG3S_PCI_PEIS0 0x204 +#define RZG3S_PCI_PEIS0_RX_DLLP_PM_ENTER BIT(12) +#define RZG3S_PCI_PEIS0_DL_UPDOWN BIT(9) + +#define RZG3S_PCI_PEIE1 0x208 +#define RZG3S_PCI_PEIS1 0x20c +#define RZG3S_PCI_AMEIS 0x214 +#define RZG3S_PCI_ASEIS1 0x224 + +#define RZG3S_PCI_PCSTAT1 0x408 +#define RZG3S_PCI_PCSTAT1_LTSSM_STATE GENMASK(14, 10) +#define RZG3S_PCI_PCSTAT1_DL_DOWN_STS BIT(0) + +#define RZG3S_PCI_PCCTRL2 0x410 +#define RZG3S_PCI_PCCTRL2_LS_CHG GENMASK(9, 8) +#define RZG3S_PCI_PCCTRL2_LS_CHG_REQ BIT(0) + +#define RZG3S_PCI_PCSTAT2 0x414 +#define RZG3S_PCI_PCSTAT2_LS_CHG_DONE BIT(28) +#define RZG3S_PCI_PCSTAT2_SDRIRE GENMASK(7, 1) + +#define RZG3S_PCI_PERM 0x300 +#define RZG3S_PCI_PERM_CFG_HWINIT_EN BIT(2) +#define RZG3S_PCI_PERM_PIPE_PHY_REG_EN BIT(1) + +#define RZG3S_PCI_MSIRE(id) (0x600 + (id) * 0x10) +#define RZG3S_PCI_MSIRE_ENA BIT(0) + +#define RZG3S_PCI_MSIRM(id) (0x608 + (id) * 0x10) +#define RZG3S_PCI_MSIRS(id) (0x60c + (id) * 0x10) + +#define RZG3S_PCI_AWBASEL(id) (0x1000 + (id) * 0x20) +#define RZG3S_PCI_AWBASEL_WIN_ENA BIT(0) + +#define RZG3S_PCI_AWBASEU(id) (0x1004 + (id) * 0x20) +#define RZG3S_PCI_AWMASKL(id) (0x1008 + (id) * 0x20) +#define RZG3S_PCI_AWMASKU(id) (0x100c + (id) * 0x20) +#define RZG3S_PCI_ADESTL(id) (0x1010 + (id) * 0x20) +#define RZG3S_PCI_ADESTU(id) (0x1014 + (id) * 0x20) + +#define RZG3S_PCI_PWBASEL(id) (0x1100 + (id) * 0x20) +#define RZG3S_PCI_PWBASEL_ENA BIT(0) + +#define RZG3S_PCI_PWBASEU(id) (0x1104 + (id) * 0x20) +#define RZG3S_PCI_PDESTL(id) (0x1110 + (id) * 0x20) +#define RZG3S_PCI_PDESTU(id) (0x1114 + (id) * 0x20) +#define RZG3S_PCI_PWMASKL(id) (0x1108 + (id) * 0x20) +#define RZG3S_PCI_PWMASKU(id) (0x110c + (id) * 0x20) + +/* PHY control registers */ +#define RZG3S_PCI_PHY_XCFGD(id) (0x2000 + (id) * 0x10) +#define RZG3S_PCI_PHY_XCFGD_NUM 39 + +#define RZG3S_PCI_PHY_XCFGA_CMN(id) (0x2400 + (id) * 0x10) +#define RZG3S_PCI_PHY_XCFGA_CMN_NUM 16 + +#define RZG3S_PCI_PHY_XCFGA_RX(id) (0x2500 + (id) * 0x10) +#define RZG3S_PCI_PHY_XCFGA_RX_NUM 13 + +#define RZG3S_PCI_PHY_XCFGA_TX 0x25d0 + +#define RZG3S_PCI_PHY_XCFG_CTRL 0x2a20 +#define RZG3S_PCI_PHY_XCFG_CTRL_PHYREG_SEL BIT(0) + +/* PCIe registers */ +#define RZG3S_PCI_CFG_BASE 0x6000 +#define RZG3S_PCI_CFG_BARMSK00L 0xa0 +#define RZG3S_PCI_CFG_BARMSK00U 0xa4 + +#define RZG3S_PCI_CFG_PCIEC 0x60 + +/* System controller registers */ +#define RZG3S_SYS_PCIE_RST_RSM_B 0xd74 +#define RZG3S_SYS_PCIE_RST_RSM_B_MASK BIT(0) + +/* Maximum number of windows */ +#define RZG3S_MAX_WINDOWS 8 + +/* Number of MSI interrupts per register */ +#define RZG3S_PCI_MSI_INT_PER_REG 32 +/* The number of MSI interrupts */ +#define RZG3S_PCI_MSI_INT_NR RZG3S_PCI_MSI_INT_PER_REG + +/* Timeouts experimentally determined */ +#define RZG3S_REQ_ISSUE_TIMEOUT_US 2500 + +/** + * struct rzg3s_pcie_msi - RZ/G3S PCIe MSI data structure + * @domain: IRQ domain + * @map: bitmap with the allocated MSIs + * @dma_addr: address of the allocated MSI window + * @window_base: base address of the MSI window + * @pages: allocated pages for MSI window mapping + * @map_lock: lock for bitmap with the allocated MSIs + * @irq: MSI interrupt + */ +struct rzg3s_pcie_msi { + struct irq_domain *domain; + DECLARE_BITMAP(map, RZG3S_PCI_MSI_INT_NR); + dma_addr_t dma_addr; + dma_addr_t window_base; + unsigned long pages; + struct mutex map_lock; + int irq; +}; + +struct rzg3s_pcie_host; + +/** + * struct rzg3s_pcie_soc_data - SoC specific data + * @init_phy: PHY initialization function + * @power_resets: array with the resets that need to be de-asserted after + * power-on + * @cfg_resets: array with the resets that need to be de-asserted after + * configuration + * @num_power_resets: number of power resets + * @num_cfg_resets: number of configuration resets + */ +struct rzg3s_pcie_soc_data { + int (*init_phy)(struct rzg3s_pcie_host *host); + const char * const *power_resets; + const char * const *cfg_resets; + u8 num_power_resets; + u8 num_cfg_resets; +}; + +/** + * struct rzg3s_pcie_port - RZ/G3S PCIe Root Port data structure + * @refclk: PCIe reference clock + * @vendor_id: Vendor ID + * @device_id: Device ID + */ +struct rzg3s_pcie_port { + struct clk *refclk; + u32 vendor_id; + u32 device_id; +}; + +/** + * struct rzg3s_pcie_host - RZ/G3S PCIe data structure + * @axi: base address for AXI registers + * @pcie: base address for PCIe registers + * @dev: struct device + * @power_resets: reset control signals that should be set after power up + * @cfg_resets: reset control signals that should be set after configuration + * @sysc: SYSC regmap + * @intx_domain: INTx IRQ domain + * @data: SoC specific data + * @msi: MSI data structure + * @port: PCIe Root Port + * @hw_lock: lock for access to the HW resources + * @intx_irqs: INTx interrupts + * @max_link_speed: maximum supported link speed + */ +struct rzg3s_pcie_host { + void __iomem *axi; + void __iomem *pcie; + struct device *dev; + struct reset_control_bulk_data *power_resets; + struct reset_control_bulk_data *cfg_resets; + struct regmap *sysc; + struct irq_domain *intx_domain; + const struct rzg3s_pcie_soc_data *data; + struct rzg3s_pcie_msi msi; + struct rzg3s_pcie_port port; + raw_spinlock_t hw_lock; + int intx_irqs[PCI_NUM_INTX]; + int max_link_speed; +}; + +#define rzg3s_msi_to_host(_msi) container_of(_msi, struct rzg3s_pcie_host, msi) + +static void rzg3s_pcie_update_bits(void __iomem *base, u32 offset, u32 mask, + u32 val) +{ + u32 tmp; + + tmp = readl_relaxed(base + offset); + tmp &= ~mask; + tmp |= val & mask; + writel_relaxed(tmp, base + offset); +} + +static int rzg3s_pcie_child_issue_request(struct rzg3s_pcie_host *host) +{ + u32 val; + int ret; + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_REQISS, + RZG3S_PCI_REQISS_REQ_ISSUE, + RZG3S_PCI_REQISS_REQ_ISSUE); + ret = readl_poll_timeout_atomic(host->axi + RZG3S_PCI_REQISS, val, + !(val & RZG3S_PCI_REQISS_REQ_ISSUE), + 5, RZG3S_REQ_ISSUE_TIMEOUT_US); + + if (val & RZG3S_PCI_REQISS_MOR_STATUS) + return -EIO; + + return ret; +} + +static void rzg3s_pcie_child_prepare_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct rzg3s_pcie_host *host = bus->sysdata; + unsigned int dev, func, reg; + + dev = PCI_SLOT(devfn); + func = PCI_FUNC(devfn); + reg = where & ~0x3; + + /* Set the destination */ + writel_relaxed(FIELD_PREP(RZG3S_PCI_REQADR1_BUS, bus->number) | + FIELD_PREP(RZG3S_PCI_REQADR1_DEV, dev) | + FIELD_PREP(RZG3S_PCI_REQADR1_FUNC, func) | + FIELD_PREP(RZG3S_PCI_REQADR1_REG, reg), + host->axi + RZG3S_PCI_REQADR1); + + /* Set byte enable */ + writel_relaxed(RZG3S_PCI_REQBE_BYTE_EN, host->axi + RZG3S_PCI_REQBE); +} + +static int rzg3s_pcie_child_read_conf(struct rzg3s_pcie_host *host, + struct pci_bus *bus, unsigned int devfn, + int where, u32 *data) +{ + bool type0 = pci_is_root_bus(bus->parent) ? true : false; + int ret; + + rzg3s_pcie_child_prepare_bus(bus, devfn, where); + + /* Set the type of request */ + writel_relaxed(type0 ? RZG3S_PCI_REQISS_TR_TP0_RD : + RZG3S_PCI_REQISS_TR_TP1_RD, + host->axi + RZG3S_PCI_REQISS); + + /* Issue the request and wait to finish */ + ret = rzg3s_pcie_child_issue_request(host); + if (ret) + return PCIBIOS_SET_FAILED; + + /* Read the data */ + *data = readl_relaxed(host->axi + RZG3S_PCI_REQRCVDAT); + + return PCIBIOS_SUCCESSFUL; +} + +/* Serialization is provided by 'pci_lock' in drivers/pci/access.c */ +static int rzg3s_pcie_child_read(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + struct rzg3s_pcie_host *host = bus->sysdata; + int ret; + + ret = rzg3s_pcie_child_read_conf(host, bus, devfn, where, val); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + if (size <= 2) + *val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1); + + return PCIBIOS_SUCCESSFUL; +} + +static int rzg3s_pcie_child_write_conf(struct rzg3s_pcie_host *host, + struct pci_bus *bus, unsigned int devfn, + int where, u32 data) +{ + bool type0 = pci_is_root_bus(bus->parent) ? true : false; + int ret; + + rzg3s_pcie_child_prepare_bus(bus, devfn, where); + + /* Set the write data */ + writel_relaxed(0, host->axi + RZG3S_PCI_REQDATA(0)); + writel_relaxed(0, host->axi + RZG3S_PCI_REQDATA(1)); + writel_relaxed(data, host->axi + RZG3S_PCI_REQDATA(2)); + + /* Set the type of request */ + writel_relaxed(type0 ? RZG3S_PCI_REQISS_TR_TP0_WR : + RZG3S_PCI_REQISS_TR_TP1_WR, + host->axi + RZG3S_PCI_REQISS); + + /* Issue the request and wait to finish */ + ret = rzg3s_pcie_child_issue_request(host); + if (ret) + return PCIBIOS_SET_FAILED; + + return PCIBIOS_SUCCESSFUL; +} + +/* Serialization is provided by 'pci_lock' in drivers/pci/access.c */ +static int rzg3s_pcie_child_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct rzg3s_pcie_host *host = bus->sysdata; + u32 data, shift; + int ret; + + if (size == 4) + return rzg3s_pcie_child_write_conf(host, bus, devfn, where, val); + + /* + * Controller does 32 bit accesses. To do byte accesses software need + * to do read/modify/write. This may have potential side effects. For + * example, software may perform a 16-bit write. If the hardware only + * supports 32-bit accesses, we must do a 32-bit read, merge in the 16 + * bits we intend to write, followed by a 32-bit write. If the 16 bits + * we *don't* intend to write happen to have any RW1C + * (write-one-to-clear) bits set, we just inadvertently cleared + * something we shouldn't have. + */ + if (!bus->unsafe_warn) { + dev_warn(&bus->dev, "%d-byte config write to %04x:%02x:%02x.%d offset %#x may corrupt adjacent RW1C bits\n", + size, pci_domain_nr(bus), bus->number, + PCI_SLOT(devfn), PCI_FUNC(devfn), where); + bus->unsafe_warn = 1; + } + + ret = rzg3s_pcie_child_read_conf(host, bus, devfn, where, &data); + if (ret != PCIBIOS_SUCCESSFUL) + return ret; + + 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; + } + + return rzg3s_pcie_child_write_conf(host, bus, devfn, where, data); +} + +static struct pci_ops rzg3s_pcie_child_ops = { + .read = rzg3s_pcie_child_read, + .write = rzg3s_pcie_child_write, +}; + +static void __iomem *rzg3s_pcie_root_map_bus(struct pci_bus *bus, + unsigned int devfn, int where) +{ + struct rzg3s_pcie_host *host = bus->sysdata; + + if (devfn) + return NULL; + + return host->pcie + where; +} + +/* Serialized by 'pci_lock' */ +static int rzg3s_pcie_root_write(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + struct rzg3s_pcie_host *host = bus->sysdata; + int ret; + + /* Enable access control to the CFGU */ + writel_relaxed(RZG3S_PCI_PERM_CFG_HWINIT_EN, + host->axi + RZG3S_PCI_PERM); + + ret = pci_generic_config_write(bus, devfn, where, size, val); + + /* Disable access control to the CFGU */ + writel_relaxed(0, host->axi + RZG3S_PCI_PERM); + + return ret; +} + +static struct pci_ops rzg3s_pcie_root_ops = { + .read = pci_generic_config_read, + .write = rzg3s_pcie_root_write, + .map_bus = rzg3s_pcie_root_map_bus, +}; + +static void rzg3s_pcie_intx_irq_handler(struct irq_desc *desc) +{ + struct rzg3s_pcie_host *host = irq_desc_get_handler_data(desc); + struct irq_chip *chip = irq_desc_get_chip(desc); + unsigned int irq = irq_desc_get_irq(desc); + u32 intx = irq - host->intx_irqs[0]; + + chained_irq_enter(chip, desc); + generic_handle_domain_irq(host->intx_domain, intx); + chained_irq_exit(chip, desc); +} + +static irqreturn_t rzg3s_pcie_msi_irq(int irq, void *data) +{ + u8 regs = RZG3S_PCI_MSI_INT_NR / RZG3S_PCI_MSI_INT_PER_REG; + DECLARE_BITMAP(bitmap, RZG3S_PCI_MSI_INT_NR); + struct rzg3s_pcie_host *host = data; + struct rzg3s_pcie_msi *msi = &host->msi; + unsigned long bit; + u32 status; + + status = readl_relaxed(host->axi + RZG3S_PCI_PINTRCVIS); + if (!(status & RZG3S_PCI_PINTRCVIS_MSI)) + return IRQ_NONE; + + /* Clear the MSI */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIS, + RZG3S_PCI_PINTRCVIS_MSI, + RZG3S_PCI_PINTRCVIS_MSI); + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_MSGRCVIS, + RZG3S_PCI_MSGRCVIS_MRI, RZG3S_PCI_MSGRCVIS_MRI); + + for (u8 reg_id = 0; reg_id < regs; reg_id++) { + status = readl_relaxed(host->axi + RZG3S_PCI_MSIRS(reg_id)); + bitmap_write(bitmap, status, reg_id * RZG3S_PCI_MSI_INT_PER_REG, + RZG3S_PCI_MSI_INT_PER_REG); + } + + for_each_set_bit(bit, bitmap, RZG3S_PCI_MSI_INT_NR) { + int ret; + + ret = generic_handle_domain_irq(msi->domain, bit); + if (ret) { + u8 reg_bit = bit % RZG3S_PCI_MSI_INT_PER_REG; + u8 reg_id = bit / RZG3S_PCI_MSI_INT_PER_REG; + + /* Unknown MSI, just clear it */ + writel_relaxed(BIT(reg_bit), + host->axi + RZG3S_PCI_MSIRS(reg_id)); + } + } + + return IRQ_HANDLED; +} + +static void rzg3s_pcie_msi_irq_ack(struct irq_data *d) +{ + struct rzg3s_pcie_msi *msi = irq_data_get_irq_chip_data(d); + struct rzg3s_pcie_host *host = rzg3s_msi_to_host(msi); + u8 reg_bit = d->hwirq % RZG3S_PCI_MSI_INT_PER_REG; + u8 reg_id = d->hwirq / RZG3S_PCI_MSI_INT_PER_REG; + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + writel_relaxed(BIT(reg_bit), host->axi + RZG3S_PCI_MSIRS(reg_id)); +} + +static void rzg3s_pcie_msi_irq_mask(struct irq_data *d) +{ + struct rzg3s_pcie_msi *msi = irq_data_get_irq_chip_data(d); + struct rzg3s_pcie_host *host = rzg3s_msi_to_host(msi); + u8 reg_bit = d->hwirq % RZG3S_PCI_MSI_INT_PER_REG; + u8 reg_id = d->hwirq / RZG3S_PCI_MSI_INT_PER_REG; + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_MSIRM(reg_id), BIT(reg_bit), + BIT(reg_bit)); +} + +static void rzg3s_pcie_msi_irq_unmask(struct irq_data *d) +{ + struct rzg3s_pcie_msi *msi = irq_data_get_irq_chip_data(d); + struct rzg3s_pcie_host *host = rzg3s_msi_to_host(msi); + u8 reg_bit = d->hwirq % RZG3S_PCI_MSI_INT_PER_REG; + u8 reg_id = d->hwirq / RZG3S_PCI_MSI_INT_PER_REG; + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_MSIRM(reg_id), BIT(reg_bit), + 0); +} + +static void rzg3s_pcie_irq_compose_msi_msg(struct irq_data *data, + struct msi_msg *msg) +{ + struct rzg3s_pcie_msi *msi = irq_data_get_irq_chip_data(data); + struct rzg3s_pcie_host *host = rzg3s_msi_to_host(msi); + u32 lo, hi; + + /* + * Enable and msg data enable bits are part of the address lo. Drop + * them along with the unused bit. + */ + lo = readl_relaxed(host->axi + RZG3S_PCI_MSIRCVWADRL) & + RZG3S_PCI_MSIRCVWADRL_MASK; + hi = readl_relaxed(host->axi + RZG3S_PCI_MSIRCVWADRU); + + msg->address_lo = lo; + msg->address_hi = hi; + msg->data = data->hwirq; +} + +static struct irq_chip rzg3s_pcie_msi_bottom_chip = { + .name = "rzg3s-pcie-msi", + .irq_ack = rzg3s_pcie_msi_irq_ack, + .irq_mask = rzg3s_pcie_msi_irq_mask, + .irq_unmask = rzg3s_pcie_msi_irq_unmask, + .irq_compose_msi_msg = rzg3s_pcie_irq_compose_msi_msg, +}; + +static int rzg3s_pcie_msi_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *args) +{ + struct rzg3s_pcie_msi *msi = domain->host_data; + int hwirq; + + scoped_guard(mutex, &msi->map_lock) { + hwirq = bitmap_find_free_region(msi->map, RZG3S_PCI_MSI_INT_NR, + order_base_2(nr_irqs)); + } + + if (hwirq < 0) + return -ENOSPC; + + for (unsigned int i = 0; i < nr_irqs; i++) { + irq_domain_set_info(domain, virq + i, hwirq + i, + &rzg3s_pcie_msi_bottom_chip, + domain->host_data, handle_edge_irq, NULL, + NULL); + } + + return 0; +} + +static void rzg3s_pcie_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 rzg3s_pcie_msi *msi = domain->host_data; + + guard(mutex)(&msi->map_lock); + + bitmap_release_region(msi->map, d->hwirq, order_base_2(nr_irqs)); +} + +static const struct irq_domain_ops rzg3s_pcie_msi_domain_ops = { + .alloc = rzg3s_pcie_msi_domain_alloc, + .free = rzg3s_pcie_msi_domain_free, +}; + +#define RZG3S_PCIE_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY | \ + MSI_FLAG_PCI_MSI_MASK_PARENT) + +#define RZG3S_PCIE_MSI_FLAGS_SUPPORTED (MSI_FLAG_MULTI_PCI_MSI | \ + MSI_GENERIC_FLAGS_MASK) + +static const struct msi_parent_ops rzg3s_pcie_msi_parent_ops = { + .required_flags = RZG3S_PCIE_MSI_FLAGS_REQUIRED, + .supported_flags = RZG3S_PCIE_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .chip_flags = MSI_CHIP_FLAG_SET_ACK, + .prefix = "RZG3S-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, +}; + +static int rzg3s_pcie_msi_allocate_domains(struct rzg3s_pcie_msi *msi) +{ + struct rzg3s_pcie_host *host = rzg3s_msi_to_host(msi); + struct device *dev = host->dev; + struct irq_domain_info info = { + .fwnode = dev_fwnode(dev), + .ops = &rzg3s_pcie_msi_domain_ops, + .size = RZG3S_PCI_MSI_INT_NR, + .host_data = msi, + }; + + msi->domain = msi_create_parent_irq_domain(&info, + &rzg3s_pcie_msi_parent_ops); + if (!msi->domain) + return dev_err_probe(dev, -ENOMEM, + "failed to create IRQ domain\n"); + + return 0; +} + +static int rzg3s_pcie_msi_hw_setup(struct rzg3s_pcie_host *host) +{ + u8 regs = RZG3S_PCI_MSI_INT_NR / RZG3S_PCI_MSI_INT_PER_REG; + struct rzg3s_pcie_msi *msi = &host->msi; + + /* + * Set MSI window size. HW will set the window to + * RZG3S_PCI_MSI_INT_NR * 4 bytes. + */ + writel_relaxed(FIELD_PREP(RZG3S_PCI_MSIRCVWMSKL_MASK, + RZG3S_PCI_MSI_INT_NR - 1), + host->axi + RZG3S_PCI_MSIRCVWMSKL); + + /* Set MSI window address and enable MSI window */ + writel_relaxed(upper_32_bits(msi->window_base), + host->axi + RZG3S_PCI_MSIRCVWADRU); + writel_relaxed(lower_32_bits(msi->window_base) | + RZG3S_PCI_MSIRCVWADRL_ENA | + RZG3S_PCI_MSIRCVWADRL_MSG_DATA_ENA, + host->axi + RZG3S_PCI_MSIRCVWADRL); + + /* Set MSI receive enable */ + for (u8 reg_id = 0; reg_id < regs; reg_id++) { + writel_relaxed(RZG3S_PCI_MSIRE_ENA, + host->axi + RZG3S_PCI_MSIRE(reg_id)); + } + + /* Enable message receive interrupts */ + writel_relaxed(RZG3S_PCI_MSGRCVIE_MSG_RCV, + host->axi + RZG3S_PCI_MSGRCVIE); + + /* Enable MSI */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIE, + RZG3S_PCI_PINTRCVIE_MSI, + RZG3S_PCI_PINTRCVIE_MSI); + + return 0; +} + +static int rzg3s_pcie_msi_setup(struct rzg3s_pcie_host *host) +{ + size_t size = RZG3S_PCI_MSI_INT_NR * sizeof(u32); + struct rzg3s_pcie_msi *msi = &host->msi; + struct device *dev = host->dev; + int id, ret; + + msi->pages = __get_free_pages(GFP_KERNEL | GFP_DMA, 0); + if (!msi->pages) + return -ENOMEM; + + msi->dma_addr = dma_map_single(dev, (void *)msi->pages, size * 2, + DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, msi->dma_addr)) { + ret = -ENOMEM; + goto free_pages; + } + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section 34.4.5.2 Setting + * the MSI Window) the MSI window needs to fall within one of the + * enabled AXI windows. Find an enabled AXI window to setup the MSI + * window. + */ + for (id = 0; id < RZG3S_MAX_WINDOWS; id++) { + u64 base, basel, baseu; + u64 mask, maskl, masku; + + basel = readl_relaxed(host->axi + RZG3S_PCI_AWBASEL(id)); + /* Skip checking this AXI window if it's not enabled */ + if (!(basel & RZG3S_PCI_AWBASEL_WIN_ENA)) + continue; + + baseu = readl_relaxed(host->axi + RZG3S_PCI_AWBASEU(id)); + base = baseu << 32 | basel; + + maskl = readl_relaxed(host->axi + RZG3S_PCI_AWMASKL(id)); + masku = readl_relaxed(host->axi + RZG3S_PCI_AWMASKU(id)); + mask = masku << 32 | maskl; + + if (msi->dma_addr < base || msi->dma_addr > base + mask) + continue; + + break; + } + + if (id == RZG3S_MAX_WINDOWS) { + ret = -EINVAL; + goto dma_unmap; + } + + /* The MSI base address must be aligned to the MSI size */ + msi->window_base = ALIGN(msi->dma_addr, size); + if (msi->window_base < msi->dma_addr) { + ret = -EINVAL; + goto dma_unmap; + } + + rzg3s_pcie_msi_hw_setup(host); + + return 0; + +dma_unmap: + dma_unmap_single(dev, msi->dma_addr, size * 2, DMA_BIDIRECTIONAL); +free_pages: + free_pages(msi->pages, 0); + return ret; +} + +static void rzg3s_pcie_msi_hw_teardown(struct rzg3s_pcie_host *host) +{ + u8 regs = RZG3S_PCI_MSI_INT_NR / RZG3S_PCI_MSI_INT_PER_REG; + + /* Disable MSI */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIE, + RZG3S_PCI_PINTRCVIE_MSI, 0); + + /* Disable message receive interrupts */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_MSGRCVIE, + RZG3S_PCI_MSGRCVIE_MSG_RCV, 0); + + /* Disable MSI receive enable */ + for (u8 reg_id = 0; reg_id < regs; reg_id++) + writel_relaxed(0, host->axi + RZG3S_PCI_MSIRE(reg_id)); + + /* Disable MSI window */ + writel_relaxed(0, host->axi + RZG3S_PCI_MSIRCVWADRL); +} + +static void rzg3s_pcie_teardown_msi(struct rzg3s_pcie_host *host) +{ + size_t size = RZG3S_PCI_MSI_INT_NR * sizeof(u32); + struct rzg3s_pcie_msi *msi = &host->msi; + + rzg3s_pcie_msi_hw_teardown(host); + + free_irq(msi->irq, host); + irq_domain_remove(msi->domain); + + /* Free unused memory */ + dma_unmap_single(host->dev, msi->dma_addr, size * 2, DMA_BIDIRECTIONAL); + free_pages(msi->pages, 0); +} + +static int rzg3s_pcie_init_msi(struct rzg3s_pcie_host *host) +{ + struct platform_device *pdev = to_platform_device(host->dev); + struct rzg3s_pcie_msi *msi = &host->msi; + struct device *dev = host->dev; + const char *devname; + int ret; + + ret = devm_mutex_init(dev, &msi->map_lock); + if (ret) + return ret; + + msi->irq = platform_get_irq_byname(pdev, "msi"); + if (msi->irq < 0) + return dev_err_probe(dev, msi->irq, "Failed to get MSI IRQ!\n"); + + devname = devm_kasprintf(dev, GFP_KERNEL, "%s-msi", dev_name(dev)); + if (!devname) + return -ENOMEM; + + ret = rzg3s_pcie_msi_allocate_domains(msi); + if (ret) + return ret; + + /* + * Don't use devm_request_irq() as the driver uses non-devm helpers + * to control clocks. Mixing them may lead to subtle bugs. + */ + ret = request_irq(msi->irq, rzg3s_pcie_msi_irq, 0, devname, host); + if (ret) { + dev_err_probe(dev, ret, "Failed to request IRQ: %d\n", ret); + goto free_domains; + } + + ret = rzg3s_pcie_msi_setup(host); + if (ret) { + dev_err_probe(dev, ret, "Failed to setup MSI!\n"); + goto free_irq; + } + + return 0; + +free_irq: + free_irq(msi->irq, host); +free_domains: + irq_domain_remove(msi->domain); + return ret; +} + +static void rzg3s_pcie_intx_irq_ack(struct irq_data *d) +{ + struct rzg3s_pcie_host *host = irq_data_get_irq_chip_data(d); + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIS, + RZG3S_PCI_PINTRCVIS_INTX(d->hwirq), + RZG3S_PCI_PINTRCVIS_INTX(d->hwirq)); +} + +static void rzg3s_pcie_intx_irq_mask(struct irq_data *d) +{ + struct rzg3s_pcie_host *host = irq_data_get_irq_chip_data(d); + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIE, + RZG3S_PCI_PINTRCVIE_INTX(d->hwirq), 0); +} + +static void rzg3s_pcie_intx_irq_unmask(struct irq_data *d) +{ + struct rzg3s_pcie_host *host = irq_data_get_irq_chip_data(d); + + guard(raw_spinlock_irqsave)(&host->hw_lock); + + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PINTRCVIE, + RZG3S_PCI_PINTRCVIE_INTX(d->hwirq), + RZG3S_PCI_PINTRCVIE_INTX(d->hwirq)); +} + +static struct irq_chip rzg3s_pcie_intx_irq_chip = { + .name = "PCIe INTx", + .irq_ack = rzg3s_pcie_intx_irq_ack, + .irq_mask = rzg3s_pcie_intx_irq_mask, + .irq_unmask = rzg3s_pcie_intx_irq_unmask, +}; + +static int rzg3s_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &rzg3s_pcie_intx_irq_chip, + handle_level_irq); + irq_set_chip_data(irq, domain->host_data); + + return 0; +} + +static const struct irq_domain_ops rzg3s_pcie_intx_domain_ops = { + .map = rzg3s_pcie_intx_map, + .xlate = irq_domain_xlate_onetwocell, +}; + +static int rzg3s_pcie_init_irqdomain(struct rzg3s_pcie_host *host) +{ + struct device *dev = host->dev; + struct platform_device *pdev = to_platform_device(dev); + + for (int i = 0; i < PCI_NUM_INTX; i++) { + char irq_name[5] = {0}; + int irq; + + scnprintf(irq_name, ARRAY_SIZE(irq_name), "int%c", 'a' + i); + + irq = platform_get_irq_byname(pdev, irq_name); + if (irq < 0) + return dev_err_probe(dev, -EINVAL, + "Failed to parse and map INT%c IRQ\n", + 'A' + i); + + host->intx_irqs[i] = irq; + irq_set_chained_handler_and_data(irq, + rzg3s_pcie_intx_irq_handler, + host); + } + + host->intx_domain = irq_domain_create_linear(dev_fwnode(dev), + PCI_NUM_INTX, + &rzg3s_pcie_intx_domain_ops, + host); + if (!host->intx_domain) + return dev_err_probe(dev, -EINVAL, + "Failed to add irq domain for INTx IRQs\n"); + irq_domain_update_bus_token(host->intx_domain, DOMAIN_BUS_WIRED); + + if (IS_ENABLED(CONFIG_PCI_MSI)) { + int ret = rzg3s_pcie_init_msi(host); + + if (ret) { + irq_domain_remove(host->intx_domain); + return ret; + } + } + + return 0; +} + +static void rzg3s_pcie_teardown_irqdomain(struct rzg3s_pcie_host *host) +{ + if (IS_ENABLED(CONFIG_PCI_MSI)) + rzg3s_pcie_teardown_msi(host); + + irq_domain_remove(host->intx_domain); +} + +static int rzg3s_pcie_set_max_link_speed(struct rzg3s_pcie_host *host) +{ + u32 remote_supported_link_speeds, max_supported_link_speeds; + u32 cs2, tmp, pcie_cap = RZG3S_PCI_CFG_PCIEC; + u32 cur_link_speed, link_speed; + u8 ltssm_state_l0 = 0xc; + int ret; + u16 ls; + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section 34.6.3 Caution + * when Changing the Speed Spontaneously) link speed change can be done + * only when the LTSSM is in L0. + */ + ret = readl_poll_timeout(host->axi + RZG3S_PCI_PCSTAT1, tmp, + FIELD_GET(RZG3S_PCI_PCSTAT1_LTSSM_STATE, tmp) == ltssm_state_l0, + PCIE_LINK_WAIT_SLEEP_MS * MILLI, + PCIE_LINK_WAIT_SLEEP_MS * MILLI * + PCIE_LINK_WAIT_MAX_RETRIES); + if (ret) + return ret; + + ls = readw_relaxed(host->pcie + pcie_cap + PCI_EXP_LNKSTA); + cs2 = readl_relaxed(host->axi + RZG3S_PCI_PCSTAT2); + + switch (pcie_link_speed[host->max_link_speed]) { + case PCIE_SPEED_5_0GT: + max_supported_link_speeds = GENMASK(PCI_EXP_LNKSTA_CLS_5_0GB - 1, 0); + link_speed = PCI_EXP_LNKCTL2_TLS_5_0GT; + break; + default: + /* Should not happen */ + return -EINVAL; + } + + cur_link_speed = FIELD_GET(PCI_EXP_LNKSTA_CLS, ls); + remote_supported_link_speeds = FIELD_GET(RZG3S_PCI_PCSTAT2_SDRIRE, cs2); + /* Drop reserved bits */ + remote_supported_link_speeds &= max_supported_link_speeds; + + /* + * Return if max link speed is already set or the connected device + * doesn't support it. + */ + if (cur_link_speed == host->max_link_speed || + remote_supported_link_speeds != max_supported_link_speeds) + return 0; + + /* Set target Link speed */ + rzg3s_pcie_update_bits(host->pcie, pcie_cap + PCI_EXP_LNKCTL2, + PCI_EXP_LNKCTL2_TLS, + FIELD_PREP(PCI_EXP_LNKCTL2_TLS, link_speed)); + + /* Request link speed change */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PCCTRL2, + RZG3S_PCI_PCCTRL2_LS_CHG_REQ | + RZG3S_PCI_PCCTRL2_LS_CHG, + RZG3S_PCI_PCCTRL2_LS_CHG_REQ | + FIELD_PREP(RZG3S_PCI_PCCTRL2_LS_CHG, + link_speed - 1)); + + ret = readl_poll_timeout(host->axi + RZG3S_PCI_PCSTAT2, cs2, + (cs2 & RZG3S_PCI_PCSTAT2_LS_CHG_DONE), + PCIE_LINK_WAIT_SLEEP_MS * MILLI, + PCIE_LINK_WAIT_SLEEP_MS * MILLI * + PCIE_LINK_WAIT_MAX_RETRIES); + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section 34.6.3 Caution + * when Changing the Speed Spontaneously) the PCI_PCCTRL2_LS_CHG_REQ + * should be de-asserted after checking for PCI_PCSTAT2_LS_CHG_DONE. + */ + rzg3s_pcie_update_bits(host->axi, RZG3S_PCI_PCCTRL2, + RZG3S_PCI_PCCTRL2_LS_CHG_REQ, 0); + + return ret; +} + +static int rzg3s_pcie_config_init(struct rzg3s_pcie_host *host) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + struct resource_entry *ft; + struct resource *bus; + u8 subordinate_bus; + u8 secondary_bus; + u8 primary_bus; + + ft = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (!ft) + return -ENODEV; + + bus = ft->res; + primary_bus = bus->start; + secondary_bus = bus->start + 1; + subordinate_bus = bus->end; + + /* Enable access control to the CFGU */ + writel_relaxed(RZG3S_PCI_PERM_CFG_HWINIT_EN, + host->axi + RZG3S_PCI_PERM); + + /* HW manual recommends to write 0xffffffff on initialization */ + writel_relaxed(0xffffffff, host->pcie + RZG3S_PCI_CFG_BARMSK00L); + writel_relaxed(0xffffffff, host->pcie + RZG3S_PCI_CFG_BARMSK00U); + + /* Update bus info */ + writeb_relaxed(primary_bus, host->pcie + PCI_PRIMARY_BUS); + writeb_relaxed(secondary_bus, host->pcie + PCI_SECONDARY_BUS); + writeb_relaxed(subordinate_bus, host->pcie + PCI_SUBORDINATE_BUS); + + /* Disable access control to the CFGU */ + writel_relaxed(0, host->axi + RZG3S_PCI_PERM); + + return 0; +} + +static void rzg3s_pcie_irq_init(struct rzg3s_pcie_host *host) +{ + /* + * According to the HW manual of the RZ/G3S (Rev.1.10, sections + * corresponding to all registers written with ~0U), the hardware + * ignores value written to unused bits. Writing ~0U to these registers + * should be safe. + */ + + /* Clear the link state and PM transitions */ + writel_relaxed(RZG3S_PCI_PEIS0_DL_UPDOWN | + RZG3S_PCI_PEIS0_RX_DLLP_PM_ENTER, + host->axi + RZG3S_PCI_PEIS0); + + /* Disable all interrupts */ + writel_relaxed(0, host->axi + RZG3S_PCI_PEIE0); + + /* Clear all parity and ecc error interrupts */ + writel_relaxed(~0U, host->axi + RZG3S_PCI_PEIS1); + + /* Disable all parity and ecc error interrupts */ + writel_relaxed(0, host->axi + RZG3S_PCI_PEIE1); + + /* Clear all AXI master error interrupts */ + writel_relaxed(~0U, host->axi + RZG3S_PCI_AMEIS); + + /* Clear all AXI slave error interrupts */ + writel_relaxed(~0U, host->axi + RZG3S_PCI_ASEIS1); + + /* Clear all message receive interrupts */ + writel_relaxed(~0U, host->axi + RZG3S_PCI_MSGRCVIS); +} + +static int rzg3s_pcie_power_resets_deassert(struct rzg3s_pcie_host *host) +{ + const struct rzg3s_pcie_soc_data *data = host->data; + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section + * 34.5.1.2 De-asserting the Reset) the PCIe IP needs to wait 5ms from + * power on to the de-assertion of reset. + */ + fsleep(5000); + return reset_control_bulk_deassert(data->num_power_resets, + host->power_resets); +} + +static int rzg3s_pcie_resets_prepare_and_get(struct rzg3s_pcie_host *host) +{ + const struct rzg3s_pcie_soc_data *data = host->data; + unsigned int i; + int ret; + + host->power_resets = devm_kmalloc_array(host->dev, + data->num_power_resets, + sizeof(*host->power_resets), + GFP_KERNEL); + if (!host->power_resets) + return -ENOMEM; + + for (i = 0; i < data->num_power_resets; i++) + host->power_resets[i].id = data->power_resets[i]; + + host->cfg_resets = devm_kmalloc_array(host->dev, + data->num_cfg_resets, + sizeof(*host->cfg_resets), + GFP_KERNEL); + if (!host->cfg_resets) + return -ENOMEM; + + for (i = 0; i < data->num_cfg_resets; i++) + host->cfg_resets[i].id = data->cfg_resets[i]; + + ret = devm_reset_control_bulk_get_exclusive(host->dev, + data->num_power_resets, + host->power_resets); + if (ret) + return ret; + + return devm_reset_control_bulk_get_exclusive(host->dev, + data->num_cfg_resets, + host->cfg_resets); +} + +static int rzg3s_pcie_host_parse_port(struct rzg3s_pcie_host *host) +{ + struct device_node *of_port = of_get_next_child(host->dev->of_node, NULL); + struct rzg3s_pcie_port *port = &host->port; + int ret; + + ret = of_property_read_u32(of_port, "vendor-id", &port->vendor_id); + if (ret) + return ret; + + ret = of_property_read_u32(of_port, "device-id", &port->device_id); + if (ret) + return ret; + + port->refclk = of_clk_get_by_name(of_port, "ref"); + if (IS_ERR(port->refclk)) + return PTR_ERR(port->refclk); + + return 0; +} + +static int rzg3s_pcie_host_init_port(struct rzg3s_pcie_host *host) +{ + struct rzg3s_pcie_port *port = &host->port; + struct device *dev = host->dev; + int ret; + + /* Enable access control to the CFGU */ + writel_relaxed(RZG3S_PCI_PERM_CFG_HWINIT_EN, + host->axi + RZG3S_PCI_PERM); + + /* Update vendor ID and device ID */ + writew_relaxed(port->vendor_id, host->pcie + PCI_VENDOR_ID); + writew_relaxed(port->device_id, host->pcie + PCI_DEVICE_ID); + + /* Disable access control to the CFGU */ + writel_relaxed(0, host->axi + RZG3S_PCI_PERM); + + ret = clk_prepare_enable(port->refclk); + if (ret) + return dev_err_probe(dev, ret, "Failed to enable refclk!\n"); + + /* Set the PHY, if any */ + if (host->data->init_phy) { + ret = host->data->init_phy(host); + if (ret) { + dev_err_probe(dev, ret, "Failed to set the PHY!\n"); + goto refclk_disable; + } + } + + return 0; + +refclk_disable: + clk_disable_unprepare(port->refclk); + return ret; +} + +static int rzg3s_pcie_host_init(struct rzg3s_pcie_host *host) +{ + u32 val; + int ret; + + /* Initialize the PCIe related registers */ + ret = rzg3s_pcie_config_init(host); + if (ret) + return ret; + + ret = rzg3s_pcie_host_init_port(host); + if (ret) + return ret; + + /* Initialize the interrupts */ + rzg3s_pcie_irq_init(host); + + ret = reset_control_bulk_deassert(host->data->num_cfg_resets, + host->cfg_resets); + if (ret) + goto disable_port_refclk; + + /* Wait for link up */ + ret = readl_poll_timeout(host->axi + RZG3S_PCI_PCSTAT1, val, + !(val & RZG3S_PCI_PCSTAT1_DL_DOWN_STS), + PCIE_LINK_WAIT_SLEEP_MS * MILLI, + PCIE_LINK_WAIT_SLEEP_MS * MILLI * + PCIE_LINK_WAIT_MAX_RETRIES); + if (ret) + goto cfg_resets_deassert; + + val = readl_relaxed(host->axi + RZG3S_PCI_PCSTAT2); + dev_info(host->dev, "PCIe link status [0x%x]\n", val); + + return 0; + +cfg_resets_deassert: + reset_control_bulk_assert(host->data->num_cfg_resets, + host->cfg_resets); +disable_port_refclk: + clk_disable_unprepare(host->port.refclk); + return ret; +} + +static void rzg3s_pcie_set_inbound_window(struct rzg3s_pcie_host *host, + u64 cpu_addr, u64 pci_addr, u64 size, + int id) +{ + /* Set CPU window base address */ + writel_relaxed(upper_32_bits(cpu_addr), + host->axi + RZG3S_PCI_ADESTU(id)); + writel_relaxed(lower_32_bits(cpu_addr), + host->axi + RZG3S_PCI_ADESTL(id)); + + /* Set window size */ + writel_relaxed(upper_32_bits(size), host->axi + RZG3S_PCI_AWMASKU(id)); + writel_relaxed(lower_32_bits(size), host->axi + RZG3S_PCI_AWMASKL(id)); + + /* Set PCIe window base address and enable the window */ + writel_relaxed(upper_32_bits(pci_addr), + host->axi + RZG3S_PCI_AWBASEU(id)); + writel_relaxed(lower_32_bits(pci_addr) | RZG3S_PCI_AWBASEL_WIN_ENA, + host->axi + RZG3S_PCI_AWBASEL(id)); +} + +static int rzg3s_pcie_set_inbound_windows(struct rzg3s_pcie_host *host, + struct resource_entry *entry, + int *index) +{ + u64 pci_addr = entry->res->start - entry->offset; + u64 cpu_addr = entry->res->start; + u64 cpu_end = entry->res->end; + u64 size_id = 0; + int id = *index; + u64 size; + + while (cpu_addr < cpu_end) { + if (id >= RZG3S_MAX_WINDOWS) + return dev_err_probe(host->dev, -ENOSPC, + "Failed to map inbound window for resource (%s)\n", + entry->res->name); + + size = resource_size(entry->res) - size_id; + + /* + * According to the RZ/G3S HW manual (Rev.1.10, + * section 34.3.1.71 AXI Window Mask (Lower) Registers) the min + * size is 4K. + */ + size = max(size, SZ_4K); + + /* + * According the RZ/G3S HW manual (Rev.1.10, sections: + * - 34.3.1.69 AXI Window Base (Lower) Registers + * - 34.3.1.71 AXI Window Mask (Lower) Registers + * - 34.3.1.73 AXI Destination (Lower) Registers) + * the CPU addr, PCIe addr, size should be 4K aligned and be a + * power of 2. + */ + size = ALIGN(size, SZ_4K); + size = roundup_pow_of_two(size); + + cpu_addr = ALIGN(cpu_addr, SZ_4K); + pci_addr = ALIGN(pci_addr, SZ_4K); + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section + * 34.3.1.71 AXI Window Mask (Lower) Registers) HW expects first + * 12 LSB bits to be 0xfff. Subtract 1 from size for this. + */ + rzg3s_pcie_set_inbound_window(host, cpu_addr, pci_addr, + size - 1, id); + + pci_addr += size; + cpu_addr += size; + size_id = size; + id++; + } + *index = id; + + return 0; +} + +static int rzg3s_pcie_parse_map_dma_ranges(struct rzg3s_pcie_host *host) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + struct resource_entry *entry; + int i = 0, ret; + + resource_list_for_each_entry(entry, &bridge->dma_ranges) { + ret = rzg3s_pcie_set_inbound_windows(host, entry, &i); + if (ret) + return ret; + } + + return 0; +} + +static void rzg3s_pcie_set_outbound_window(struct rzg3s_pcie_host *host, + struct resource_entry *win, int id) +{ + struct resource *res = win->res; + resource_size_t size = resource_size(res); + resource_size_t res_start; + + if (res->flags & IORESOURCE_IO) + res_start = pci_pio_to_address(res->start) - win->offset; + else + res_start = res->start - win->offset; + + /* + * According to the RZ/G3S HW manual (Rev.1.10, section 34.3.1.75 PCIe + * Window Base (Lower) Registers) the window base address need to be 4K + * aligned. + */ + res_start = ALIGN(res_start, SZ_4K); + + size = ALIGN(size, SZ_4K); + size = roundup_pow_of_two(size) - 1; + + /* Set PCIe destination */ + writel_relaxed(upper_32_bits(res_start), + host->axi + RZG3S_PCI_PDESTU(id)); + writel_relaxed(lower_32_bits(res_start), + host->axi + RZG3S_PCI_PDESTL(id)); + + /* Set PCIe window mask */ + writel_relaxed(upper_32_bits(size), host->axi + RZG3S_PCI_PWMASKU(id)); + writel_relaxed(lower_32_bits(size), host->axi + RZG3S_PCI_PWMASKL(id)); + + /* Set PCIe window base and enable the window */ + writel_relaxed(upper_32_bits(res_start), + host->axi + RZG3S_PCI_PWBASEU(id)); + writel_relaxed(lower_32_bits(res_start) | RZG3S_PCI_PWBASEL_ENA, + host->axi + RZG3S_PCI_PWBASEL(id)); +} + +static int rzg3s_pcie_parse_map_ranges(struct rzg3s_pcie_host *host) +{ + struct pci_host_bridge *bridge = pci_host_bridge_from_priv(host); + struct resource_entry *win; + int i = 0; + + resource_list_for_each_entry(win, &bridge->windows) { + struct resource *res = win->res; + + if (i >= RZG3S_MAX_WINDOWS) + return dev_err_probe(host->dev, -ENOSPC, + "Failed to map outbound window for resource (%s)\n", + res->name); + + if (!res->flags) + continue; + + switch (resource_type(res)) { + case IORESOURCE_IO: + case IORESOURCE_MEM: + rzg3s_pcie_set_outbound_window(host, win, i); + i++; + break; + } + } + + return 0; +} + +static int rzg3s_soc_pcie_init_phy(struct rzg3s_pcie_host *host) +{ + static const u32 xcfgd_settings[RZG3S_PCI_PHY_XCFGD_NUM] = { + [8] = 0xe0006801, 0x007f7e30, 0x183e0000, 0x978ff500, + 0xec000000, 0x009f1400, 0x0000d009, + [17] = 0x78000000, + [19] = 0x00880000, 0x000005c0, 0x07000000, 0x00780920, + 0xc9400ce2, 0x90000c0c, 0x000c1414, 0x00005034, + 0x00006000, 0x00000001, + }; + static const u32 xcfga_cmn_settings[RZG3S_PCI_PHY_XCFGA_CMN_NUM] = { + 0x00000d10, 0x08310100, 0x00c21404, 0x013c0010, 0x01874440, + 0x1a216082, 0x00103440, 0x00000080, 0x00000010, 0x0c1000c1, + 0x1000c100, 0x0222000c, 0x00640019, 0x00a00028, 0x01d11228, + 0x0201001d, + }; + static const u32 xcfga_rx_settings[RZG3S_PCI_PHY_XCFGA_RX_NUM] = { + 0x07d55000, 0x030e3f00, 0x00000288, 0x102c5880, 0x0000000b, + 0x04141441, 0x00641641, 0x00d63d63, 0x00641641, 0x01970377, + 0x00190287, 0x00190028, 0x00000028, + }; + unsigned int i; + + /* + * Enable access permission for physical layer control and status + * registers. + */ + writel_relaxed(RZG3S_PCI_PERM_PIPE_PHY_REG_EN, + host->axi + RZG3S_PCI_PERM); + + for (i = 0; i < RZG3S_PCI_PHY_XCFGD_NUM; i++) { + writel_relaxed(xcfgd_settings[i], + host->axi + RZG3S_PCI_PHY_XCFGD(i)); + } + + for (i = 0; i < RZG3S_PCI_PHY_XCFGA_CMN_NUM; i++) { + writel_relaxed(xcfga_cmn_settings[i], + host->axi + RZG3S_PCI_PHY_XCFGA_CMN(i)); + } + + for (i = 0; i < RZG3S_PCI_PHY_XCFGA_RX_NUM; i++) { + writel_relaxed(xcfga_rx_settings[i], + host->axi + RZG3S_PCI_PHY_XCFGA_RX(i)); + } + + writel_relaxed(0x107, host->axi + RZG3S_PCI_PHY_XCFGA_TX); + + /* Select PHY settings values */ + writel_relaxed(RZG3S_PCI_PHY_XCFG_CTRL_PHYREG_SEL, + host->axi + RZG3S_PCI_PHY_XCFG_CTRL); + + /* + * Disable access permission for physical layer control and status + * registers. + */ + writel_relaxed(0, host->axi + RZG3S_PCI_PERM); + + return 0; +} + +static int +rzg3s_pcie_host_setup(struct rzg3s_pcie_host *host, + int (*init_irqdomain)(struct rzg3s_pcie_host *host), + void (*teardown_irqdomain)(struct rzg3s_pcie_host *host)) +{ + struct device *dev = host->dev; + int ret; + + /* Set inbound windows */ + ret = rzg3s_pcie_parse_map_dma_ranges(host); + if (ret) + return dev_err_probe(dev, ret, + "Failed to set inbound windows!\n"); + + /* Set outbound windows */ + ret = rzg3s_pcie_parse_map_ranges(host); + if (ret) + return dev_err_probe(dev, ret, + "Failed to set outbound windows!\n"); + + ret = init_irqdomain(host); + if (ret) + return dev_err_probe(dev, ret, "Failed to init IRQ domain\n"); + + ret = rzg3s_pcie_host_init(host); + if (ret) { + dev_err_probe(dev, ret, "Failed to initialize the HW!\n"); + goto teardown_irqdomain; + } + + ret = rzg3s_pcie_set_max_link_speed(host); + if (ret) + dev_info(dev, "Failed to set max link speed\n"); + + msleep(PCIE_RESET_CONFIG_WAIT_MS); + + return 0; + +teardown_irqdomain: + teardown_irqdomain(host); + + return ret; +} + +static int rzg3s_pcie_probe(struct platform_device *pdev) +{ + struct pci_host_bridge *bridge; + struct device *dev = &pdev->dev; + struct device_node *np = dev->of_node; + struct device_node *sysc_np __free(device_node) = + of_parse_phandle(np, "renesas,sysc", 0); + struct rzg3s_pcie_host *host; + int ret; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*host)); + if (!bridge) + return -ENOMEM; + + host = pci_host_bridge_priv(bridge); + host->dev = dev; + host->data = device_get_match_data(dev); + platform_set_drvdata(pdev, host); + + host->axi = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(host->axi)) + return PTR_ERR(host->axi); + host->pcie = host->axi + RZG3S_PCI_CFG_BASE; + + host->max_link_speed = of_pci_get_max_link_speed(np); + if (host->max_link_speed < 0) + host->max_link_speed = 2; + + ret = rzg3s_pcie_host_parse_port(host); + if (ret) + return ret; + + host->sysc = syscon_node_to_regmap(sysc_np); + if (IS_ERR(host->sysc)) { + ret = PTR_ERR(host->sysc); + goto port_refclk_put; + } + + ret = regmap_update_bits(host->sysc, RZG3S_SYS_PCIE_RST_RSM_B, + RZG3S_SYS_PCIE_RST_RSM_B_MASK, + FIELD_PREP(RZG3S_SYS_PCIE_RST_RSM_B_MASK, 1)); + if (ret) + goto port_refclk_put; + + ret = rzg3s_pcie_resets_prepare_and_get(host); + if (ret) + goto sysc_signal_restore; + + ret = rzg3s_pcie_power_resets_deassert(host); + if (ret) + goto sysc_signal_restore; + + pm_runtime_enable(dev); + + /* + * Controller clocks are part of a clock power domain. Enable them + * through runtime PM. + */ + ret = pm_runtime_resume_and_get(dev); + if (ret) + goto rpm_disable; + + raw_spin_lock_init(&host->hw_lock); + + ret = rzg3s_pcie_host_setup(host, rzg3s_pcie_init_irqdomain, + rzg3s_pcie_teardown_irqdomain); + if (ret) + goto rpm_put; + + bridge->sysdata = host; + bridge->ops = &rzg3s_pcie_root_ops; + bridge->child_ops = &rzg3s_pcie_child_ops; + ret = pci_host_probe(bridge); + if (ret) + goto host_probe_teardown; + + return 0; + +host_probe_teardown: + rzg3s_pcie_teardown_irqdomain(host); + reset_control_bulk_deassert(host->data->num_cfg_resets, + host->cfg_resets); +rpm_put: + pm_runtime_put_sync(dev); +rpm_disable: + pm_runtime_disable(dev); + reset_control_bulk_assert(host->data->num_power_resets, + host->power_resets); +sysc_signal_restore: + /* + * SYSC RST_RSM_B signal need to be asserted before turning off the + * power to the PHY. + */ + regmap_update_bits(host->sysc, RZG3S_SYS_PCIE_RST_RSM_B, + RZG3S_SYS_PCIE_RST_RSM_B_MASK, + FIELD_PREP(RZG3S_SYS_PCIE_RST_RSM_B_MASK, 0)); +port_refclk_put: + clk_put(host->port.refclk); + + return ret; +} + +static int rzg3s_pcie_suspend_noirq(struct device *dev) +{ + struct rzg3s_pcie_host *host = dev_get_drvdata(dev); + const struct rzg3s_pcie_soc_data *data = host->data; + struct rzg3s_pcie_port *port = &host->port; + struct regmap *sysc = host->sysc; + int ret; + + ret = pm_runtime_put_sync(dev); + if (ret) + return ret; + + clk_disable_unprepare(port->refclk); + + ret = reset_control_bulk_assert(data->num_power_resets, + host->power_resets); + if (ret) + goto refclk_restore; + + ret = reset_control_bulk_assert(data->num_cfg_resets, + host->cfg_resets); + if (ret) + goto power_resets_restore; + + ret = regmap_update_bits(sysc, RZG3S_SYS_PCIE_RST_RSM_B, + RZG3S_SYS_PCIE_RST_RSM_B_MASK, + FIELD_PREP(RZG3S_SYS_PCIE_RST_RSM_B_MASK, 0)); + if (ret) + goto cfg_resets_restore; + + return 0; + + /* Restore the previous state if any error happens */ +cfg_resets_restore: + reset_control_bulk_deassert(data->num_cfg_resets, + host->cfg_resets); +power_resets_restore: + reset_control_bulk_deassert(data->num_power_resets, + host->power_resets); +refclk_restore: + clk_prepare_enable(port->refclk); + pm_runtime_resume_and_get(dev); + return ret; +} + +static int rzg3s_pcie_resume_noirq(struct device *dev) +{ + struct rzg3s_pcie_host *host = dev_get_drvdata(dev); + const struct rzg3s_pcie_soc_data *data = host->data; + struct regmap *sysc = host->sysc; + int ret; + + ret = regmap_update_bits(sysc, RZG3S_SYS_PCIE_RST_RSM_B, + RZG3S_SYS_PCIE_RST_RSM_B_MASK, + FIELD_PREP(RZG3S_SYS_PCIE_RST_RSM_B_MASK, 1)); + if (ret) + return ret; + + ret = rzg3s_pcie_power_resets_deassert(host); + if (ret) + goto assert_rst_rsm_b; + + ret = pm_runtime_resume_and_get(dev); + if (ret) + goto assert_power_resets; + + ret = rzg3s_pcie_host_setup(host, rzg3s_pcie_msi_hw_setup, + rzg3s_pcie_msi_hw_teardown); + if (ret) + goto rpm_put; + + return 0; + + /* + * If any error happens there is no way to recover the IP. Put it in the + * lowest possible power state. + */ +rpm_put: + pm_runtime_put_sync(dev); +assert_power_resets: + reset_control_bulk_assert(data->num_power_resets, + host->power_resets); +assert_rst_rsm_b: + regmap_update_bits(sysc, RZG3S_SYS_PCIE_RST_RSM_B, + RZG3S_SYS_PCIE_RST_RSM_B_MASK, + FIELD_PREP(RZG3S_SYS_PCIE_RST_RSM_B_MASK, 0)); + return ret; +} + +static const struct dev_pm_ops rzg3s_pcie_pm_ops = { + NOIRQ_SYSTEM_SLEEP_PM_OPS(rzg3s_pcie_suspend_noirq, + rzg3s_pcie_resume_noirq) +}; + +static const char * const rzg3s_soc_power_resets[] = { + "aresetn", "rst_cfg_b", "rst_load_b", +}; + +static const char * const rzg3s_soc_cfg_resets[] = { + "rst_b", "rst_ps_b", "rst_gp_b", "rst_rsm_b", +}; + +static const struct rzg3s_pcie_soc_data rzg3s_soc_data = { + .power_resets = rzg3s_soc_power_resets, + .num_power_resets = ARRAY_SIZE(rzg3s_soc_power_resets), + .cfg_resets = rzg3s_soc_cfg_resets, + .num_cfg_resets = ARRAY_SIZE(rzg3s_soc_cfg_resets), + .init_phy = rzg3s_soc_pcie_init_phy, +}; + +static const struct of_device_id rzg3s_pcie_of_match[] = { + { + .compatible = "renesas,r9a08g045-pcie", + .data = &rzg3s_soc_data, + }, + {} +}; + +static struct platform_driver rzg3s_pcie_driver = { + .driver = { + .name = "rzg3s-pcie-host", + .of_match_table = rzg3s_pcie_of_match, + .pm = pm_ptr(&rzg3s_pcie_pm_ops), + .suppress_bind_attrs = true, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, + .probe = rzg3s_pcie_probe, +}; +builtin_platform_driver(rzg3s_pcie_driver); diff --git a/drivers/pci/controller/pcie-xilinx-cpm.c b/drivers/pci/controller/pcie-xilinx-cpm.c index a0f5e1d67b04..d38f27e20761 100644 --- a/drivers/pci/controller/pcie-xilinx-cpm.c +++ b/drivers/pci/controller/pcie-xilinx-cpm.c @@ -30,11 +30,14 @@ #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_PCIE0_MISC_IR_LOCAL BIT(1) +#define XILINX_CPM_PCIE1_MISC_IR_LOCAL BIT(2) -#define XILINX_CPM_PCIE_IR_STATUS 0x000002A0 -#define XILINX_CPM_PCIE_IR_ENABLE 0x000002A8 -#define XILINX_CPM_PCIE_IR_LOCAL BIT(0) +#define XILINX_CPM_PCIE0_IR_STATUS 0x000002A0 +#define XILINX_CPM_PCIE1_IR_STATUS 0x000002B4 +#define XILINX_CPM_PCIE0_IR_ENABLE 0x000002A8 +#define XILINX_CPM_PCIE1_IR_ENABLE 0x000002BC +#define XILINX_CPM_PCIE_IR_LOCAL BIT(0) #define IMR(x) BIT(XILINX_PCIE_INTR_ ##x) @@ -80,14 +83,22 @@ enum xilinx_cpm_version { CPM, CPM5, + CPM5_HOST1, + CPM5NC_HOST, }; /** * struct xilinx_cpm_variant - CPM variant information * @version: CPM version + * @ir_status: Offset for the error interrupt status register + * @ir_enable: Offset for the CPM5 local error interrupt enable register + * @ir_misc_value: A bitmask for the miscellaneous interrupt status */ struct xilinx_cpm_variant { enum xilinx_cpm_version version; + u32 ir_status; + u32 ir_enable; + u32 ir_misc_value; }; /** @@ -269,6 +280,7 @@ 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); + const struct xilinx_cpm_variant *variant = port->variant; unsigned long val; int i; @@ -279,11 +291,11 @@ static void xilinx_cpm_pcie_event_flow(struct irq_desc *desc) 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 (variant->ir_status) { + val = readl_relaxed(port->cpm_base + variant->ir_status); if (val) writel_relaxed(val, port->cpm_base + - XILINX_CPM_PCIE_IR_STATUS); + variant->ir_status); } /* @@ -383,17 +395,15 @@ static int xilinx_cpm_pcie_init_irq_domain(struct xilinx_cpm_pcie *port) return -EINVAL; } - port->cpm_domain = irq_domain_add_linear(pcie_intc_node, 32, - &event_domain_ops, - port); + port->cpm_domain = irq_domain_create_linear(of_fwnode_handle(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); + port->intx_domain = irq_domain_create_linear(of_fwnode_handle(pcie_intc_node), PCI_NUM_INTX, + &intx_domain_ops, port); if (!port->intx_domain) goto out; @@ -465,6 +475,11 @@ static int xilinx_cpm_setup_irq(struct xilinx_cpm_pcie *port) */ static void xilinx_cpm_pcie_init_port(struct xilinx_cpm_pcie *port) { + const struct xilinx_cpm_variant *variant = port->variant; + + if (variant->version == CPM5NC_HOST) + return; + if (cpm_pcie_link_up(port)) dev_info(port->dev, "PCIe Link is UP\n"); else @@ -483,15 +498,15 @@ static void xilinx_cpm_pcie_init_port(struct xilinx_cpm_pcie *port) * XILINX_CPM_PCIE_MISC_IR_ENABLE register is mapped to * CPM SLCR block. */ - writel(XILINX_CPM_PCIE_MISC_IR_LOCAL, + writel(variant->ir_misc_value, port->cpm_base + XILINX_CPM_PCIE_MISC_IR_ENABLE); - if (port->variant->version == CPM5) { + if (variant->ir_enable) { writel(XILINX_CPM_PCIE_IR_LOCAL, - port->cpm_base + XILINX_CPM_PCIE_IR_ENABLE); + port->cpm_base + variant->ir_enable); } - /* Enable the Bridge enable bit */ + /* Set 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); @@ -525,7 +540,8 @@ static int xilinx_cpm_pcie_parse_dt(struct xilinx_cpm_pcie *port, if (IS_ERR(port->cfg)) return PTR_ERR(port->cfg); - if (port->variant->version == CPM5) { + if (port->variant->version == CPM5 || + port->variant->version == CPM5_HOST1) { port->reg_base = devm_platform_ioremap_resource_byname(pdev, "cpm_csr"); if (IS_ERR(port->reg_base)) @@ -565,28 +581,34 @@ static int xilinx_cpm_pcie_probe(struct platform_device *pdev) port->dev = dev; - err = xilinx_cpm_pcie_init_irq_domain(port); - if (err) - return err; + port->variant = of_device_get_match_data(dev); - bus = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); - if (!bus) - return -ENODEV; + if (port->variant->version != CPM5NC_HOST) { + err = xilinx_cpm_pcie_init_irq_domain(port); + if (err) + return err; + } - port->variant = of_device_get_match_data(dev); + bus = resource_list_first_type(&bridge->windows, IORESOURCE_BUS); + if (!bus) { + err = -ENODEV; + goto err_free_irq_domains; + } err = xilinx_cpm_pcie_parse_dt(port, bus->res); if (err) { dev_err(dev, "Parsing DT failed\n"); - goto err_parse_dt; + goto err_free_irq_domains; } 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; + if (port->variant->version != CPM5NC_HOST) { + 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; @@ -599,20 +621,37 @@ static int xilinx_cpm_pcie_probe(struct platform_device *pdev) return 0; err_host_bridge: - xilinx_cpm_free_interrupts(port); + if (port->variant->version != CPM5NC_HOST) + xilinx_cpm_free_interrupts(port); err_setup_irq: pci_ecam_free(port->cfg); -err_parse_dt: - xilinx_cpm_free_irq_domains(port); +err_free_irq_domains: + if (port->variant->version != CPM5NC_HOST) + xilinx_cpm_free_irq_domains(port); return err; } static const struct xilinx_cpm_variant cpm_host = { .version = CPM, + .ir_misc_value = XILINX_CPM_PCIE0_MISC_IR_LOCAL, }; static const struct xilinx_cpm_variant cpm5_host = { .version = CPM5, + .ir_misc_value = XILINX_CPM_PCIE0_MISC_IR_LOCAL, + .ir_status = XILINX_CPM_PCIE0_IR_STATUS, + .ir_enable = XILINX_CPM_PCIE0_IR_ENABLE, +}; + +static const struct xilinx_cpm_variant cpm5_host1 = { + .version = CPM5_HOST1, + .ir_misc_value = XILINX_CPM_PCIE1_MISC_IR_LOCAL, + .ir_status = XILINX_CPM_PCIE1_IR_STATUS, + .ir_enable = XILINX_CPM_PCIE1_IR_ENABLE, +}; + +static const struct xilinx_cpm_variant cpm5n_host = { + .version = CPM5NC_HOST, }; static const struct of_device_id xilinx_cpm_pcie_of_match[] = { @@ -624,6 +663,14 @@ static const struct of_device_id xilinx_cpm_pcie_of_match[] = { .compatible = "xlnx,versal-cpm5-host", .data = &cpm5_host, }, + { + .compatible = "xlnx,versal-cpm5-host1", + .data = &cpm5_host1, + }, + { + .compatible = "xlnx,versal-cpm5nc-host", + .data = &cpm5n_host, + }, {} }; diff --git a/drivers/pci/controller/pcie-xilinx-dma-pl.c b/drivers/pci/controller/pcie-xilinx-dma-pl.c index dd117f07fc95..b037c8f315e4 100644 --- a/drivers/pci/controller/pcie-xilinx-dma-pl.c +++ b/drivers/pci/controller/pcie-xilinx-dma-pl.c @@ -7,6 +7,7 @@ #include <linux/bitfield.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/kernel.h> #include <linux/module.h> @@ -90,7 +91,6 @@ struct xilinx_pl_dma_variant { }; struct xilinx_msi { - struct irq_domain *msi_domain; unsigned long *bitmap; struct irq_domain *dev_domain; struct mutex lock; /* Protect bitmap variable */ @@ -373,20 +373,20 @@ static irqreturn_t xilinx_pl_dma_pcie_intr_handler(int irq, void *dev_id) return IRQ_HANDLED; } -static struct irq_chip xilinx_msi_irq_chip = { - .name = "pl_dma: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, -}; +#define XILINX_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) -static struct msi_domain_info xilinx_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_NO_AFFINITY | MSI_FLAG_MULTI_PCI_MSI, - .chip = &xilinx_msi_irq_chip, -}; +#define XILINX_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_MULTI_PCI_MSI) +static const struct msi_parent_ops xilinx_msi_parent_ops = { + .required_flags = XILINX_MSI_FLAGS_REQUIRED, + .supported_flags = XILINX_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .prefix = "pl_dma-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, +}; static void xilinx_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { struct pl_dma_pcie *pcie = irq_data_get_irq_chip_data(data); @@ -458,11 +458,6 @@ static void xilinx_pl_dma_pcie_free_irq_domains(struct pl_dma_pcie *port) irq_domain_remove(msi->dev_domain); msi->dev_domain = NULL; } - - if (msi->msi_domain) { - irq_domain_remove(msi->msi_domain); - msi->msi_domain = NULL; - } } static int xilinx_pl_dma_pcie_init_msi_irq_domain(struct pl_dma_pcie *port) @@ -470,19 +465,17 @@ static int xilinx_pl_dma_pcie_init_msi_irq_domain(struct pl_dma_pcie *port) struct device *dev = port->dev; struct xilinx_msi *msi = &port->msi; int size = BITS_TO_LONGS(XILINX_NUM_MSI_IRQS) * sizeof(long); - struct fwnode_handle *fwnode = of_node_to_fwnode(port->dev->of_node); - - msi->dev_domain = irq_domain_add_linear(NULL, XILINX_NUM_MSI_IRQS, - &dev_msi_domain_ops, port); + struct irq_domain_info info = { + .fwnode = dev_fwnode(port->dev), + .ops = &dev_msi_domain_ops, + .host_data = port, + .size = XILINX_NUM_MSI_IRQS, + }; + + msi->dev_domain = msi_create_parent_irq_domain(&info, &xilinx_msi_parent_ops); if (!msi->dev_domain) goto out; - msi->msi_domain = pci_msi_create_irq_domain(fwnode, - &xilinx_msi_domain_info, - msi->dev_domain); - if (!msi->msi_domain) - goto out; - mutex_init(&msi->lock); msi->bitmap = kzalloc(size, GFP_KERNEL); if (!msi->bitmap) @@ -585,15 +578,15 @@ static int xilinx_pl_dma_pcie_init_irq_domain(struct pl_dma_pcie *port) return -EINVAL; } - port->pldma_domain = irq_domain_add_linear(pcie_intc_node, 32, - &event_domain_ops, port); + port->pldma_domain = irq_domain_create_linear(of_fwnode_handle(pcie_intc_node), 32, + &event_domain_ops, port); if (!port->pldma_domain) return -ENOMEM; irq_domain_update_bus_token(port->pldma_domain, DOMAIN_BUS_NEXUS); - port->intx_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, - &intx_domain_ops, port); + port->intx_domain = irq_domain_create_linear(of_fwnode_handle(pcie_intc_node), PCI_NUM_INTX, + &intx_domain_ops, port); if (!port->intx_domain) { dev_err(dev, "Failed to get a INTx IRQ domain\n"); return -ENOMEM; diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c index a8ae14474dd0..7db2c96c6cec 100644 --- a/drivers/pci/controller/pcie-xilinx-nwl.c +++ b/drivers/pci/controller/pcie-xilinx-nwl.c @@ -10,6 +10,7 @@ #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/kernel.h> #include <linux/init.h> @@ -145,7 +146,6 @@ #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 */ @@ -418,19 +418,22 @@ static const struct irq_domain_ops intx_domain_ops = { }; #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_NO_AFFINITY | MSI_FLAG_MULTI_PCI_MSI, - .chip = &nwl_msi_irq_chip, +#define NWL_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) + +#define NWL_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_MULTI_PCI_MSI) + +static const struct msi_parent_ops nwl_msi_parent_ops = { + .required_flags = NWL_MSI_FLAGS_REQUIRED, + .supported_flags = NWL_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .prefix = "nwl-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; + #endif static void nwl_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) @@ -495,23 +498,19 @@ 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); + struct irq_domain_info info = { + .fwnode = dev_fwnode(dev), + .ops = &dev_msi_domain_ops, + .host_data = pcie, + .size = INT_PCI_MSI_NR, + }; + + msi->dev_domain = msi_create_parent_irq_domain(&info, &nwl_msi_parent_ops); 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; } @@ -582,10 +581,8 @@ static int nwl_pcie_init_irq_domain(struct nwl_pcie *pcie) return -EINVAL; } - pcie->intx_irq_domain = irq_domain_add_linear(intc_node, - PCI_NUM_INTX, - &intx_domain_ops, - pcie); + pcie->intx_irq_domain = irq_domain_create_linear(of_fwnode_handle(intc_node), PCI_NUM_INTX, + &intx_domain_ops, pcie); of_node_put(intc_node); if (!pcie->intx_irq_domain) { dev_err(dev, "failed to create IRQ domain\n"); @@ -721,9 +718,10 @@ static int nwl_pcie_bridge_init(struct nwl_pcie *pcie) 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) | - (NWL_ECAM_MAX_SIZE << E_ECAM_SIZE_SHIFT), - E_ECAM_CONTROL); + ecam_val = nwl_bridge_readl(pcie, E_ECAM_CONTROL); + ecam_val &= ~E_ECAM_SIZE_LOC; + ecam_val |= NWL_ECAM_MAX_SIZE << E_ECAM_SIZE_SHIFT; + nwl_bridge_writel(pcie, ecam_val, E_ECAM_CONTROL); nwl_bridge_writel(pcie, lower_32_bits(pcie->phys_ecam_base), E_ECAM_BASE_LO); @@ -916,6 +914,6 @@ static struct platform_driver nwl_pcie_driver = { .of_match_table = nwl_pcie_of_match, }, .probe = nwl_pcie_probe, - .remove_new = nwl_pcie_remove, + .remove = nwl_pcie_remove, }; builtin_platform_driver(nwl_pcie_driver); diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c index 0b534f73a942..937ea6ae1ac4 100644 --- a/drivers/pci/controller/pcie-xilinx.c +++ b/drivers/pci/controller/pcie-xilinx.c @@ -12,6 +12,7 @@ #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/kernel.h> #include <linux/init.h> @@ -203,11 +204,6 @@ static void xilinx_msi_top_irq_ack(struct irq_data *d) */ } -static struct irq_chip xilinx_msi_top_chip = { - .name = "PCIe MSI", - .irq_ack = xilinx_msi_top_irq_ack, -}; - 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); @@ -264,29 +260,42 @@ static const struct irq_domain_ops xilinx_msi_domain_ops = { .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 | - MSI_FLAG_NO_AFFINITY, - .chip = &xilinx_msi_top_chip, +static bool xilinx_init_dev_msi_info(struct device *dev, struct irq_domain *domain, + struct irq_domain *real_parent, struct msi_domain_info *info) +{ + struct irq_chip *chip = info->chip; + + if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info)) + return false; + + chip->irq_ack = xilinx_msi_top_irq_ack; + return true; +} + +#define XILINX_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) + +static const struct msi_parent_ops xilinx_msi_parent_ops = { + .required_flags = XILINX_MSI_FLAGS_REQUIRED, + .supported_flags = MSI_GENERIC_FLAGS_MASK, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .prefix = "xilinx-", + .init_dev_msi_info = xilinx_init_dev_msi_info, }; 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); + struct irq_domain_info info = { + .fwnode = dev_fwnode(pcie->dev), + .ops = &xilinx_msi_domain_ops, + .host_data = pcie, + .size = XILINX_NUM_MSI_IRQS, + }; + + pcie->msi_domain = msi_create_parent_irq_domain(&info, &xilinx_msi_parent_ops); if (!pcie->msi_domain) { dev_err(pcie->dev, "failed to create MSI domain\n"); - irq_domain_remove(parent); return -ENOMEM; } @@ -295,10 +304,7 @@ static int xilinx_allocate_msi_domains(struct xilinx_pcie *pcie) 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 */ @@ -394,7 +400,7 @@ static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data) 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; + domain = pcie->msi_domain; } else { val = (val & XILINX_PCIE_RPIFR1_INTR_MASK) >> XILINX_PCIE_RPIFR1_INTR_SHIFT; @@ -461,9 +467,8 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie *pcie) return -ENODEV; } - pcie->leg_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, - &intx_domain_ops, - pcie); + pcie->leg_domain = irq_domain_create_linear(of_fwnode_handle(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"); diff --git a/drivers/pci/controller/plda/Kconfig b/drivers/pci/controller/plda/Kconfig index c0e14146d7e4..62120101139c 100644 --- a/drivers/pci/controller/plda/Kconfig +++ b/drivers/pci/controller/plda/Kconfig @@ -5,6 +5,7 @@ menu "PLDA-based PCIe controllers" config PCIE_PLDA_HOST bool + select IRQ_MSI_LIB config PCIE_MICROCHIP_HOST tristate "Microchip AXI PCIe controller" diff --git a/drivers/pci/controller/plda/pcie-microchip-host.c b/drivers/pci/controller/plda/pcie-microchip-host.c index 48f60a04b740..24bbf93b8051 100644 --- a/drivers/pci/controller/plda/pcie-microchip-host.c +++ b/drivers/pci/controller/plda/pcie-microchip-host.c @@ -7,27 +7,32 @@ * Author: Daire McNamara <daire.mcnamara@microchip.com> */ +#include <linux/align.h> +#include <linux/bits.h> #include <linux/bitfield.h> #include <linux/clk.h> #include <linux/irqchip/chained_irq.h> #include <linux/irqdomain.h> +#include <linux/log2.h> #include <linux/module.h> #include <linux/msi.h> #include <linux/of_address.h> #include <linux/of_pci.h> #include <linux/pci-ecam.h> #include <linux/platform_device.h> +#include <linux/wordpart.h> #include "../../pci.h" +#include "../pci-host-common.h" #include "pcie-plda.h" +#define MC_MAX_NUM_INBOUND_WINDOWS 8 +#define MPFS_NC_BOUNCE_ADDR 0x80000000 + /* 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_EVENT_CNT 0x20 #define DED_ERROR_EVENT_CNT 0x24 @@ -128,7 +133,6 @@ [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, \ @@ -136,7 +140,6 @@ .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, \ @@ -144,7 +147,6 @@ .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, \ @@ -152,7 +154,6 @@ .enb_mask = 0 #define LOCAL_EVENT(x) \ - .base = MC_PCIE_BRIDGE_ADDR, \ .offset = ISTATUS_LOCAL, \ .mask_offset = IMASK_LOCAL, \ .mask_high = 0, \ @@ -179,7 +180,8 @@ struct event_map { struct mc_pcie { struct plda_pcie_rp plda; - void __iomem *axi_base_addr; + void __iomem *bridge_base_addr; + void __iomem *ctrl_base_addr; }; struct cause { @@ -253,7 +255,6 @@ static struct event_map local_status_to_event[] = { }; static struct { - u32 base; u32 offset; u32 mask; u32 shift; @@ -325,8 +326,7 @@ static inline u32 reg_to_event(u32 reg, struct event_map field) static u32 pcie_events(struct mc_pcie *port) { - void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR; - u32 reg = readl_relaxed(ctrl_base_addr + PCIE_EVENT_INT); + u32 reg = readl_relaxed(port->ctrl_base_addr + PCIE_EVENT_INT); u32 val = 0; int i; @@ -338,8 +338,7 @@ static u32 pcie_events(struct mc_pcie *port) static u32 sec_errors(struct mc_pcie *port) { - void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR; - u32 reg = readl_relaxed(ctrl_base_addr + SEC_ERROR_INT); + u32 reg = readl_relaxed(port->ctrl_base_addr + SEC_ERROR_INT); u32 val = 0; int i; @@ -351,8 +350,7 @@ static u32 sec_errors(struct mc_pcie *port) static u32 ded_errors(struct mc_pcie *port) { - void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR; - u32 reg = readl_relaxed(ctrl_base_addr + DED_ERROR_INT); + u32 reg = readl_relaxed(port->ctrl_base_addr + DED_ERROR_INT); u32 val = 0; int i; @@ -364,8 +362,7 @@ static u32 ded_errors(struct mc_pcie *port) static u32 local_events(struct mc_pcie *port) { - void __iomem *bridge_base_addr = port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; - u32 reg = readl_relaxed(bridge_base_addr + ISTATUS_LOCAL); + u32 reg = readl_relaxed(port->bridge_base_addr + ISTATUS_LOCAL); u32 val = 0; int i; @@ -412,8 +409,12 @@ static void mc_ack_event_irq(struct irq_data *data) void __iomem *addr; u32 mask; - addr = mc_port->axi_base_addr + event_descs[event].base + - event_descs[event].offset; + if (event_descs[event].offset == ISTATUS_LOCAL) + addr = mc_port->bridge_base_addr; + else + addr = mc_port->ctrl_base_addr; + + addr += event_descs[event].offset; mask = event_descs[event].mask; mask |= event_descs[event].enb_mask; @@ -429,8 +430,12 @@ static void mc_mask_event_irq(struct irq_data *data) u32 mask; u32 val; - addr = mc_port->axi_base_addr + event_descs[event].base + - event_descs[event].mask_offset; + if (event_descs[event].offset == ISTATUS_LOCAL) + addr = mc_port->bridge_base_addr; + else + addr = mc_port->ctrl_base_addr; + + addr += event_descs[event].mask_offset; mask = event_descs[event].mask; if (event_descs[event].enb_mask) { mask <<= PCIE_EVENT_INT_ENB_SHIFT; @@ -460,8 +465,12 @@ static void mc_unmask_event_irq(struct irq_data *data) u32 mask; u32 val; - addr = mc_port->axi_base_addr + event_descs[event].base + - event_descs[event].mask_offset; + if (event_descs[event].offset == ISTATUS_LOCAL) + addr = mc_port->bridge_base_addr; + else + addr = mc_port->ctrl_base_addr; + + addr += event_descs[event].mask_offset; mask = event_descs[event].mask; if (event_descs[event].enb_mask) @@ -554,26 +563,20 @@ static const struct plda_event mc_event = { static inline void mc_clear_secs(struct mc_pcie *port) { - void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR; - - writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT, ctrl_base_addr + - SEC_ERROR_INT); - writel_relaxed(0, ctrl_base_addr + SEC_ERROR_EVENT_CNT); + writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT, + port->ctrl_base_addr + SEC_ERROR_INT); + writel_relaxed(0, port->ctrl_base_addr + SEC_ERROR_EVENT_CNT); } static inline void mc_clear_deds(struct mc_pcie *port) { - void __iomem *ctrl_base_addr = port->axi_base_addr + MC_PCIE_CTRL_ADDR; - - writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT, ctrl_base_addr + - DED_ERROR_INT); - writel_relaxed(0, ctrl_base_addr + DED_ERROR_EVENT_CNT); + writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT, + port->ctrl_base_addr + DED_ERROR_INT); + writel_relaxed(0, port->ctrl_base_addr + DED_ERROR_EVENT_CNT); } static void mc_disable_interrupts(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 val; /* Ensure ECC bypass is enabled */ @@ -581,22 +584,22 @@ static void mc_disable_interrupts(struct mc_pcie *port) ECC_CONTROL_RX_RAM_ECC_BYPASS | ECC_CONTROL_PCIE2AXI_RAM_ECC_BYPASS | ECC_CONTROL_AXI2PCIE_RAM_ECC_BYPASS; - writel_relaxed(val, ctrl_base_addr + ECC_CONTROL); + writel_relaxed(val, port->ctrl_base_addr + ECC_CONTROL); /* Disable SEC errors and clear any outstanding */ - writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT, ctrl_base_addr + - SEC_ERROR_INT_MASK); + writel_relaxed(SEC_ERROR_INT_ALL_RAM_SEC_ERR_INT, + port->ctrl_base_addr + SEC_ERROR_INT_MASK); mc_clear_secs(port); /* Disable DED errors and clear any outstanding */ - writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT, ctrl_base_addr + - DED_ERROR_INT_MASK); + writel_relaxed(DED_ERROR_INT_ALL_RAM_DED_ERR_INT, + port->ctrl_base_addr + DED_ERROR_INT_MASK); mc_clear_deds(port); /* Disable local interrupts and clear any outstanding */ - writel_relaxed(0, bridge_base_addr + IMASK_LOCAL); - writel_relaxed(GENMASK(31, 0), bridge_base_addr + ISTATUS_LOCAL); - writel_relaxed(GENMASK(31, 0), bridge_base_addr + ISTATUS_MSI); + writel_relaxed(0, port->bridge_base_addr + IMASK_LOCAL); + writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_LOCAL); + writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_MSI); /* Disable PCIe events and clear any outstanding */ val = PCIE_EVENT_INT_L2_EXIT_INT | @@ -605,11 +608,96 @@ static void mc_disable_interrupts(struct mc_pcie *port) PCIE_EVENT_INT_L2_EXIT_INT_MASK | PCIE_EVENT_INT_HOTRST_EXIT_INT_MASK | PCIE_EVENT_INT_DLUP_EXIT_INT_MASK; - writel_relaxed(val, ctrl_base_addr + PCIE_EVENT_INT); + writel_relaxed(val, port->ctrl_base_addr + PCIE_EVENT_INT); /* Disable host interrupts and clear any outstanding */ - writel_relaxed(0, bridge_base_addr + IMASK_HOST); - writel_relaxed(GENMASK(31, 0), bridge_base_addr + ISTATUS_HOST); + writel_relaxed(0, port->bridge_base_addr + IMASK_HOST); + writel_relaxed(GENMASK(31, 0), port->bridge_base_addr + ISTATUS_HOST); +} + +static void mc_pcie_setup_inbound_atr(struct mc_pcie *port, int window_index, + u64 axi_addr, u64 pcie_addr, u64 size) +{ + u32 table_offset = window_index * ATR_ENTRY_SIZE; + void __iomem *table_addr = port->bridge_base_addr + table_offset; + u32 atr_sz; + u32 val; + + atr_sz = ilog2(size) - 1; + + val = ALIGN_DOWN(lower_32_bits(pcie_addr), SZ_4K); + val |= FIELD_PREP(ATR_SIZE_MASK, atr_sz); + val |= ATR_IMPL_ENABLE; + + writel(val, table_addr + ATR0_PCIE_WIN0_SRCADDR_PARAM); + + writel(upper_32_bits(pcie_addr), table_addr + ATR0_PCIE_WIN0_SRC_ADDR); + + writel(lower_32_bits(axi_addr), table_addr + ATR0_PCIE_WIN0_TRSL_ADDR_LSB); + writel(upper_32_bits(axi_addr), table_addr + ATR0_PCIE_WIN0_TRSL_ADDR_UDW); + + writel(TRSL_ID_AXI4_MASTER_0, table_addr + ATR0_PCIE_WIN0_TRSL_PARAM); +} + +static int mc_pcie_setup_inbound_ranges(struct platform_device *pdev, + struct mc_pcie *port) +{ + struct device *dev = &pdev->dev; + struct device_node *dn = dev->of_node; + struct of_range_parser parser; + struct of_range range; + int atr_index = 0; + + /* + * MPFS PCIe Root Port is 32-bit only, behind a Fabric Interface + * Controller FPGA logic block which contains the AXI-S interface. + * + * From the point of view of the PCIe Root Port, there are only two + * supported Root Port configurations: + * + * Configuration 1: for use with fully coherent designs; supports a + * window from 0x0 (CPU space) to specified PCIe space. + * + * Configuration 2: for use with non-coherent designs; supports two + * 1 GB windows to CPU space; one mapping CPU space 0 to PCIe space + * 0x80000000 and a second mapping CPU space 0x40000000 to PCIe + * space 0xc0000000. This cfg needs two windows because of how the + * MSI space is allocated in the AXI-S range on MPFS. + * + * The FIC interface outside the PCIe block *must* complete the + * inbound address translation as per MCHP MPFS FPGA design + * guidelines. + */ + if (device_property_read_bool(dev, "dma-noncoherent")) { + /* + * Always need same two tables in this case. Need two tables + * due to hardware interactions between address and size. + */ + mc_pcie_setup_inbound_atr(port, 0, 0, + MPFS_NC_BOUNCE_ADDR, SZ_1G); + mc_pcie_setup_inbound_atr(port, 1, SZ_1G, + MPFS_NC_BOUNCE_ADDR + SZ_1G, SZ_1G); + } else { + /* Find any DMA ranges */ + if (of_pci_dma_range_parser_init(&parser, dn)) { + /* No DMA range property - setup default */ + mc_pcie_setup_inbound_atr(port, 0, 0, 0, SZ_4G); + return 0; + } + + for_each_of_range(&parser, &range) { + if (atr_index >= MC_MAX_NUM_INBOUND_WINDOWS) { + dev_err(dev, "too many inbound ranges; %d available tables\n", + MC_MAX_NUM_INBOUND_WINDOWS); + return -EINVAL; + } + mc_pcie_setup_inbound_atr(port, atr_index, 0, + range.pci_addr, range.size); + atr_index++; + } + } + + return 0; } static int mc_platform_init(struct pci_config_window *cfg) @@ -617,12 +705,10 @@ static int mc_platform_init(struct pci_config_window *cfg) struct device *dev = cfg->parent; struct platform_device *pdev = to_platform_device(dev); struct pci_host_bridge *bridge = platform_get_drvdata(pdev); - void __iomem *bridge_base_addr = - port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; int ret; /* Configure address translation table 0 for PCIe config space */ - plda_pcie_setup_window(bridge_base_addr, 0, cfg->res.start, + plda_pcie_setup_window(port->bridge_base_addr, 0, cfg->res.start, cfg->res.start, resource_size(&cfg->res)); @@ -634,6 +720,10 @@ static int mc_platform_init(struct pci_config_window *cfg) if (ret) return ret; + ret = mc_pcie_setup_inbound_ranges(pdev, port); + if (ret) + return ret; + port->plda.event_ops = &mc_event_ops; port->plda.event_irq_chip = &mc_event_irq_chip; port->plda.events_bitmap = GENMASK(NUM_EVENTS - 1, 0); @@ -649,7 +739,7 @@ static int mc_platform_init(struct pci_config_window *cfg) static int mc_host_probe(struct platform_device *pdev) { struct device *dev = &pdev->dev; - void __iomem *bridge_base_addr; + void __iomem *apb_base_addr; struct plda_pcie_rp *plda; int ret; u32 val; @@ -661,30 +751,45 @@ static int mc_host_probe(struct platform_device *pdev) plda = &port->plda; plda->dev = dev; - port->axi_base_addr = devm_platform_ioremap_resource(pdev, 1); - if (IS_ERR(port->axi_base_addr)) - return PTR_ERR(port->axi_base_addr); + port->bridge_base_addr = devm_platform_ioremap_resource_byname(pdev, + "bridge"); + port->ctrl_base_addr = devm_platform_ioremap_resource_byname(pdev, + "ctrl"); + if (!IS_ERR(port->bridge_base_addr) && !IS_ERR(port->ctrl_base_addr)) + goto addrs_set; + + /* + * The original, incorrect, binding that lumped the control and + * bridge addresses together still needs to be handled by the driver. + */ + apb_base_addr = devm_platform_ioremap_resource_byname(pdev, "apb"); + if (IS_ERR(apb_base_addr)) + return dev_err_probe(dev, PTR_ERR(apb_base_addr), + "both legacy apb register and ctrl/bridge regions missing"); + + port->bridge_base_addr = apb_base_addr + MC_PCIE1_BRIDGE_ADDR; + port->ctrl_base_addr = apb_base_addr + MC_PCIE1_CTRL_ADDR; +addrs_set: mc_disable_interrupts(port); - bridge_base_addr = port->axi_base_addr + MC_PCIE_BRIDGE_ADDR; - plda->bridge_addr = bridge_base_addr; + plda->bridge_addr = port->bridge_base_addr; plda->num_events = NUM_EVENTS; /* Allow enabling MSI by disabling MSI-X */ - val = readl(bridge_base_addr + PCIE_PCI_IRQ_DW0); + val = readl(port->bridge_base_addr + PCIE_PCI_IRQ_DW0); val &= ~MSIX_CAP_MASK; - writel(val, bridge_base_addr + PCIE_PCI_IRQ_DW0); + writel(val, port->bridge_base_addr + PCIE_PCI_IRQ_DW0); /* Pick num vectors from bitfile programmed onto FPGA fabric */ - val = readl(bridge_base_addr + PCIE_PCI_IRQ_DW0); + val = readl(port->bridge_base_addr + PCIE_PCI_IRQ_DW0); val &= NUM_MSI_MSGS_MASK; val >>= NUM_MSI_MSGS_SHIFT; plda->msi.num_vectors = 1 << val; /* Pick vector address from design */ - plda->msi.vector_phy = readl_relaxed(bridge_base_addr + IMSI_ADDR); + plda->msi.vector_phy = readl_relaxed(port->bridge_base_addr + IMSI_ADDR); ret = mc_pcie_init_clks(dev); if (ret) { diff --git a/drivers/pci/controller/plda/pcie-plda-host.c b/drivers/pci/controller/plda/pcie-plda-host.c index 8533dc618d45..3c2f68383010 100644 --- a/drivers/pci/controller/plda/pcie-plda-host.c +++ b/drivers/pci/controller/plda/pcie-plda-host.c @@ -8,11 +8,15 @@ * Author: Daire McNamara <daire.mcnamara@microchip.com> */ +#include <linux/align.h> +#include <linux/bitfield.h> #include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/irqdomain.h> #include <linux/msi.h> #include <linux/pci_regs.h> #include <linux/pci-ecam.h> +#include <linux/wordpart.h> #include "pcie-plda.h" @@ -131,43 +135,41 @@ static const struct irq_domain_ops msi_domain_ops = { .free = plda_irq_msi_domain_free, }; -static struct irq_chip plda_msi_irq_chip = { - .name = "PLDA 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 plda_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_NO_AFFINITY | MSI_FLAG_PCI_MSIX, - .chip = &plda_msi_irq_chip, +#define PLDA_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) +#define PLDA_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_PCI_MSIX) + +static const struct msi_parent_ops plda_msi_parent_ops = { + .required_flags = PLDA_MSI_FLAGS_REQUIRED, + .supported_flags = PLDA_MSI_FLAGS_SUPPORTED, + .chip_flags = MSI_CHIP_FLAG_SET_ACK, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .prefix = "PLDA-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, }; static int plda_allocate_msi_domains(struct plda_pcie_rp *port) { struct device *dev = port->dev; - struct fwnode_handle *fwnode = of_node_to_fwnode(dev->of_node); struct plda_msi *msi = &port->msi; mutex_init(&port->msi.lock); - msi->dev_domain = irq_domain_add_linear(NULL, msi->num_vectors, - &msi_domain_ops, port); + struct irq_domain_info info = { + .fwnode = dev_fwnode(dev), + .ops = &msi_domain_ops, + .host_data = port, + .size = msi->num_vectors, + }; + + msi->dev_domain = msi_create_parent_irq_domain(&info, &plda_msi_parent_ops); if (!msi->dev_domain) { dev_err(dev, "failed to create IRQ domain\n"); return -ENOMEM; } - msi->msi_domain = pci_msi_create_irq_domain(fwnode, - &plda_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; } @@ -390,10 +392,9 @@ static int plda_pcie_init_irq_domains(struct plda_pcie_rp *port) return -EINVAL; } - port->event_domain = irq_domain_add_linear(pcie_intc_node, - port->num_events, - &plda_event_domain_ops, - port); + port->event_domain = irq_domain_create_linear(of_fwnode_handle(pcie_intc_node), + port->num_events, &plda_event_domain_ops, + port); if (!port->event_domain) { dev_err(dev, "failed to get event domain\n"); of_node_put(pcie_intc_node); @@ -402,8 +403,8 @@ static int plda_pcie_init_irq_domains(struct plda_pcie_rp *port) 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); + port->intx_domain = irq_domain_create_linear(of_fwnode_handle(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); @@ -502,8 +503,9 @@ void plda_pcie_setup_window(void __iomem *bridge_base_addr, u32 index, 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; + val = ALIGN_DOWN(lower_32_bits(axi_addr), SZ_4K); + val |= FIELD_PREP(ATR_SIZE_MASK, atr_sz); + val |= ATR_IMPL_ENABLE; writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + ATR0_AXI4_SLV0_SRCADDR_PARAM); @@ -518,13 +520,20 @@ void plda_pcie_setup_window(void __iomem *bridge_base_addr, u32 index, val = upper_32_bits(pci_addr); writel(val, bridge_base_addr + (index * ATR_ENTRY_SIZE) + ATR0_AXI4_SLV0_TRSL_ADDR_UDW); +} +EXPORT_SYMBOL_GPL(plda_pcie_setup_window); + +void plda_pcie_setup_inbound_address_translation(struct plda_pcie_rp *port) +{ + void __iomem *bridge_base_addr = port->bridge_addr; + u32 val; 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); } -EXPORT_SYMBOL_GPL(plda_pcie_setup_window); +EXPORT_SYMBOL_GPL(plda_pcie_setup_inbound_address_translation); int plda_pcie_setup_iomems(struct pci_host_bridge *bridge, struct plda_pcie_rp *port) @@ -554,7 +563,6 @@ static void plda_pcie_irq_domain_deinit(struct plda_pcie_rp *pcie) irq_set_chained_handler_and_data(pcie->msi_irq, NULL, NULL); irq_set_chained_handler_and_data(pcie->intx_irq, NULL, NULL); - irq_domain_remove(pcie->msi.msi_domain); irq_domain_remove(pcie->msi.dev_domain); irq_domain_remove(pcie->intx_domain); @@ -591,8 +599,7 @@ int plda_pcie_host_init(struct plda_pcie_rp *port, struct pci_ops *ops, bridge = devm_pci_alloc_host_bridge(dev, 0); if (!bridge) - return dev_err_probe(dev, -ENOMEM, - "failed to alloc bridge\n"); + return -ENOMEM; if (port->host_ops && port->host_ops->host_init) { ret = port->host_ops->host_init(port); diff --git a/drivers/pci/controller/plda/pcie-plda.h b/drivers/pci/controller/plda/pcie-plda.h index 0e7dc0d8e5ba..6b8665df7bf0 100644 --- a/drivers/pci/controller/plda/pcie-plda.h +++ b/drivers/pci/controller/plda/pcie-plda.h @@ -89,14 +89,15 @@ /* PCIe AXI slave table init defines */ #define ATR0_AXI4_SLV0_SRCADDR_PARAM 0x800u -#define ATR_SIZE_SHIFT 1 -#define ATR_IMPL_ENABLE 1 +#define ATR_SIZE_MASK GENMASK(6, 1) +#define ATR_IMPL_ENABLE BIT(0) #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 TRSL_ID_AXI4_MASTER_0 0x00000004u #define CONFIG_SPACE_ADDR_OFFSET 0x1000u @@ -163,7 +164,6 @@ struct plda_pcie_host_ops { struct plda_msi { struct mutex lock; /* Protect used bitmap */ - struct irq_domain *msi_domain; struct irq_domain *dev_domain; u32 num_vectors; u64 vector_phy; @@ -204,6 +204,7 @@ int plda_init_interrupts(struct platform_device *pdev, void plda_pcie_setup_window(void __iomem *bridge_base_addr, u32 index, phys_addr_t axi_addr, phys_addr_t pci_addr, size_t size); +void plda_pcie_setup_inbound_address_translation(struct plda_pcie_rp *port); int plda_pcie_setup_iomems(struct pci_host_bridge *bridge, struct plda_pcie_rp *port); int plda_pcie_host_init(struct plda_pcie_rp *port, struct pci_ops *ops, diff --git a/drivers/pci/controller/plda/pcie-starfive.c b/drivers/pci/controller/plda/pcie-starfive.c index c9933ecf6833..3caf53c6c082 100644 --- a/drivers/pci/controller/plda/pcie-starfive.c +++ b/drivers/pci/controller/plda/pcie-starfive.c @@ -368,7 +368,7 @@ static int starfive_pcie_host_init(struct plda_pcie_rp *plda) * of 100ms following exit from a conventional reset before * sending a configuration request to the device. */ - msleep(PCIE_RESET_CONFIG_DEVICE_WAIT_MS); + msleep(PCIE_RESET_CONFIG_WAIT_MS); if (starfive_pcie_host_wait_for_link(pcie)) dev_info(dev, "port link down\n"); @@ -404,6 +404,9 @@ static int starfive_pcie_probe(struct platform_device *pdev) if (ret) return ret; + pm_runtime_enable(&pdev->dev); + pm_runtime_get_sync(&pdev->dev); + plda->host_ops = &sf_host_ops; plda->num_events = PLDA_MAX_EVENT_NUM; /* mask doorbell event */ @@ -413,11 +416,12 @@ static int starfive_pcie_probe(struct platform_device *pdev) plda->events_bitmap <<= PLDA_NUM_DMA_EVENTS; ret = plda_pcie_host_init(&pcie->plda, &starfive_pcie_ops, &stf_pcie_event); - if (ret) + if (ret) { + pm_runtime_put_sync(&pdev->dev); + pm_runtime_disable(&pdev->dev); return ret; + } - pm_runtime_enable(&pdev->dev); - pm_runtime_get_sync(&pdev->dev); platform_set_drvdata(pdev, pcie); return 0; @@ -480,7 +484,7 @@ static struct platform_driver starfive_pcie_driver = { .pm = pm_sleep_ptr(&starfive_pcie_pm_ops), }, .probe = starfive_pcie_probe, - .remove_new = starfive_pcie_remove, + .remove = starfive_pcie_remove, }; module_platform_driver(starfive_pcie_driver); diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 264a180403a0..ec6afc38e898 100644 --- a/drivers/pci/controller/vmd.c +++ b/drivers/pci/controller/vmd.c @@ -7,6 +7,7 @@ #include <linux/device.h> #include <linux/interrupt.h> #include <linux/irq.h> +#include <linux/irqchip/irq-msi-lib.h> #include <linux/kernel.h> #include <linux/module.h> #include <linux/msi.h> @@ -17,6 +18,8 @@ #include <linux/rculist.h> #include <linux/rcupdate.h> +#include <xen/xen.h> + #include <asm/irqdomain.h> #define VMD_CFGBAR 0 @@ -125,7 +128,7 @@ struct vmd_irq_list { struct vmd_dev { struct pci_dev *dev; - spinlock_t cfg_lock; + raw_spinlock_t cfg_lock; void __iomem *cfgbar; int msix_count; @@ -172,58 +175,63 @@ static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) 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); + scoped_guard(raw_spinlock_irqsave, &list_lock) { + WARN_ON(vmdirq->enabled); + list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); + vmdirq->enabled = true; + } +} +static void vmd_pci_msi_enable(struct irq_data *data) +{ + vmd_irq_enable(data->parent_data); data->chip->irq_unmask(data); } +static unsigned int vmd_pci_msi_startup(struct irq_data *data) +{ + vmd_pci_msi_enable(data); + return 0; +} + static void vmd_irq_disable(struct irq_data *data) { struct vmd_irq *vmdirq = data->chip_data; - unsigned long flags; + scoped_guard(raw_spinlock_irqsave, &list_lock) { + if (vmdirq->enabled) { + list_del_rcu(&vmdirq->node); + vmdirq->enabled = false; + } + } +} + +static void vmd_pci_msi_disable(struct irq_data *data) +{ data->chip->irq_mask(data); + vmd_irq_disable(data->parent_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); +static void vmd_pci_msi_shutdown(struct irq_data *data) +{ + vmd_pci_msi_disable(data); } 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, }; -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) @@ -240,113 +248,130 @@ static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *d 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); + scoped_guard(raw_spinlock_irq, &list_lock) { + 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++; + } 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) +static void vmd_msi_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs); + +static int vmd_msi_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *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); + struct msi_desc *desc = ((msi_alloc_info_t *)arg)->desc; + struct vmd_dev *vmd = domain->host_data; + struct vmd_irq *vmdirq; - if (!vmdirq) - return -ENOMEM; + for (int i = 0; i < nr_irqs; ++i) { + vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL); + if (!vmdirq) { + vmd_msi_free(domain, virq, i); + return -ENOMEM; + } - INIT_LIST_HEAD(&vmdirq->node); - vmdirq->irq = vmd_next_irq(vmd, desc); - vmdirq->virq = virq; + INIT_LIST_HEAD(&vmdirq->node); + vmdirq->irq = vmd_next_irq(vmd, desc); + vmdirq->virq = virq + i; + + irq_domain_set_info(domain, virq + i, vmdirq->irq->virq, + &vmd_msi_controller, vmdirq, + handle_untracked_irq, vmd, NULL); + } - 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) +static void vmd_msi_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) { - struct vmd_irq *vmdirq = irq_get_chip_data(virq); - unsigned long flags; - - synchronize_srcu(&vmdirq->irq->srcu); + struct irq_data *irq_data; + struct vmd_irq *vmdirq; - /* XXX: Potential optimization to rebalance */ - raw_spin_lock_irqsave(&list_lock, flags); - vmdirq->irq->count--; - raw_spin_unlock_irqrestore(&list_lock, flags); + for (int i = 0; i < nr_irqs; ++i) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + vmdirq = irq_data->chip_data; - kfree(vmdirq); -} + synchronize_srcu(&vmdirq->irq->srcu); -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); + /* XXX: Potential optimization to rebalance */ + scoped_guard(raw_spinlock_irq, &list_lock) + vmdirq->irq->count--; - if (nvec > vmd->msix_count) - return vmd->msix_count; - - memset(arg, 0, sizeof(*arg)); - return 0; + kfree(vmdirq); + } } -static void vmd_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) +static const struct irq_domain_ops vmd_msi_domain_ops = { + .alloc = vmd_msi_alloc, + .free = vmd_msi_free, +}; + +static bool vmd_init_dev_msi_info(struct device *dev, struct irq_domain *domain, + struct irq_domain *real_parent, + struct msi_domain_info *info) { - arg->desc = desc; + if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info)) + return false; + + info->chip->irq_startup = vmd_pci_msi_startup; + info->chip->irq_shutdown = vmd_pci_msi_shutdown; + info->chip->irq_enable = vmd_pci_msi_enable; + info->chip->irq_disable = vmd_pci_msi_disable; + return true; } -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, -}; +#define VMD_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | MSI_FLAG_PCI_MSIX) +#define VMD_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_NO_AFFINITY) -static struct msi_domain_info vmd_msi_domain_info = { - .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | - MSI_FLAG_NO_AFFINITY | MSI_FLAG_PCI_MSIX, - .ops = &vmd_msi_domain_ops, - .chip = &vmd_msi_controller, +static const struct msi_parent_ops vmd_msi_parent_ops = { + .supported_flags = VMD_MSI_FLAGS_SUPPORTED, + .required_flags = VMD_MSI_FLAGS_REQUIRED, + .bus_select_token = DOMAIN_BUS_VMD_MSI, + .bus_select_mask = MATCH_PCI_MSI, + .prefix = "VMD-", + .init_dev_msi_info = vmd_init_dev_msi_info, }; -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; + struct irq_domain_info info = { + .size = vmd->msix_count, + .ops = &vmd_msi_domain_ops, + .host_data = vmd, + }; - fn = irq_domain_alloc_named_id_fwnode("VMD-MSI", vmd->sysdata.domain); - if (!fn) + info.fwnode = irq_domain_alloc_named_id_fwnode("VMD-MSI", + vmd->sysdata.domain); + if (!info.fwnode) return -ENODEV; - vmd->irq_domain = pci_msi_create_irq_domain(fn, &vmd_msi_domain_info, NULL); + vmd->irq_domain = msi_create_parent_irq_domain(&info, + &vmd_msi_parent_ops); if (!vmd->irq_domain) { - irq_domain_free_fwnode(fn); + irq_domain_free_fwnode(info.fwnode); return -ENODEV; } return 0; } +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 void vmd_remove_irq_domain(struct vmd_dev *vmd) { /* @@ -385,29 +410,24 @@ static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg, { 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); + guard(raw_spinlock_irqsave)(&vmd->cfg_lock); switch (len) { case 1: *value = readb(addr); - break; + return 0; case 2: *value = readw(addr); - break; + return 0; case 4: *value = readl(addr); - break; + return 0; default: - ret = -EINVAL; - break; + return -EINVAL; } - spin_unlock_irqrestore(&vmd->cfg_lock, flags); - return ret; } /* @@ -420,32 +440,27 @@ static int vmd_pci_write(struct pci_bus *bus, unsigned int devfn, int reg, { 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); + guard(raw_spinlock_irqsave)(&vmd->cfg_lock); switch (len) { case 1: writeb(value, addr); readb(addr); - break; + return 0; case 2: writew(value, addr); readw(addr); - break; + return 0; case 4: writel(value, addr); readl(addr); - break; + return 0; default: - ret = -EINVAL; - break; + return -EINVAL; } - spin_unlock_irqrestore(&vmd->cfg_lock, flags); - return ret; } static struct pci_ops vmd_ops = { @@ -563,22 +578,6 @@ static void vmd_detach_resources(struct vmd_dev *vmd) 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) @@ -740,11 +739,9 @@ static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata) if (!(features & VMD_FEAT_BIOS_PM_QUIRK)) return 0; - pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL); - pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_LTR); if (!pos) - return 0; + goto out_state_change; /* * Skip if the max snoop LTR is non-zero, indicating BIOS has set it @@ -752,7 +749,7 @@ static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata) */ pci_read_config_dword(pdev, pos + PCI_LTR_MAX_SNOOP_LAT, <r_reg); if (!!(ltr_reg & (PCI_LTR_VALUE_MASK | PCI_LTR_SCALE_MASK))) - return 0; + goto out_state_change; /* * Set the default values to the maximum required by the platform to @@ -764,6 +761,13 @@ static int vmd_pm_enable_quirk(struct pci_dev *pdev, void *userdata) pci_write_config_dword(pdev, pos + PCI_LTR_MAX_SNOOP_LAT, ltr_reg); pci_info(pdev, "VMD: Default LTR value set by driver\n"); +out_state_change: + /* + * Ensure devices are in D0 before enabling PCI-PM L1 PM Substates, per + * PCIe r6.0, sec 5.5.4. + */ + pci_set_power_state_locked(pdev, PCI_D0); + pci_enable_link_state_locked(pdev, PCIE_LINK_STATE_ALL); return 0; } @@ -858,13 +862,6 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) .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 @@ -882,12 +879,6 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) 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); } @@ -896,9 +887,24 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) pci_add_resource_offset(&resources, &vmd->resources[1], offset[0]); pci_add_resource_offset(&resources, &vmd->resources[2], offset[1]); + sd->vmd_dev = vmd->dev; + + /* + * Emulated 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. + */ + sd->domain = pci_bus_find_emul_domain_nr(0, 0x10000, INT_MAX); + if (sd->domain < 0) + return sd->domain; + + sd->node = pcibus_to_node(vmd->dev->bus); + vmd->bus = pci_create_root_bus(&vmd->dev->dev, vmd->busn_start, &vmd_ops, sd, &resources); if (!vmd->bus) { + pci_bus_release_emul_domain_nr(sd->domain); pci_free_resource_list(&resources); vmd_remove_irq_domain(vmd); return -ENODEV; @@ -965,6 +971,24 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) struct vmd_dev *vmd; int err; + if (xen_domain()) { + /* + * Xen doesn't have knowledge about devices in the VMD bus + * because the config space of devices behind the VMD bridge is + * not known to Xen, and hence Xen cannot discover or configure + * them in any way. + * + * Bypass of MSI remapping won't work in that case as direct + * write by Linux to the MSI entries won't result in functional + * interrupts, as Xen is the entity that manages the host + * interrupt controller and must configure interrupts. However + * multiplexing of interrupts by the VMD bridge will work under + * Xen, so force the usage of that mode which must always be + * supported by VMD bridges. + */ + features &= ~VMD_FEAT_CAN_BYPASS_MSI_REMAP; + } + if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20)) return -ENOMEM; @@ -973,6 +997,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) return -ENOMEM; vmd->dev = dev; + vmd->sysdata.domain = PCI_DOMAIN_NR_NOT_SET; vmd->instance = ida_alloc(&vmd_instance_ida, GFP_KERNEL); if (vmd->instance < 0) return vmd->instance; @@ -1004,7 +1029,7 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) if (features & VMD_FEAT_OFFSET_FIRST_VECTOR) vmd->first_vec = 1; - spin_lock_init(&vmd->cfg_lock); + raw_spin_lock_init(&vmd->cfg_lock); pci_set_drvdata(dev, vmd); err = vmd_enable_domain(vmd, features); if (err) @@ -1038,6 +1063,7 @@ static void vmd_remove(struct pci_dev *dev) vmd_detach_resources(vmd); vmd_remove_irq_domain(vmd); ida_free(&vmd_instance_ida, vmd->instance); + pci_bus_release_emul_domain_nr(vmd->sysdata.domain); } static void vmd_shutdown(struct pci_dev *dev) @@ -1100,6 +1126,12 @@ static const struct pci_device_id vmd_ids[] = { .driver_data = VMD_FEATS_CLIENT,}, {PCI_VDEVICE(INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B), .driver_data = VMD_FEATS_CLIENT,}, + {PCI_VDEVICE(INTEL, 0xb60b), + .driver_data = VMD_FEATS_CLIENT,}, + {PCI_VDEVICE(INTEL, 0xb06f), + .driver_data = VMD_FEATS_CLIENT,}, + {PCI_VDEVICE(INTEL, 0xb07f), + .driver_data = VMD_FEATS_CLIENT,}, {0,} }; MODULE_DEVICE_TABLE(pci, vmd_ids); |