diff options
Diffstat (limited to 'drivers/pci')
200 files changed, 19906 insertions, 6283 deletions
diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig index da28295b4aac..e3f848ffb52a 100644 --- a/drivers/pci/Kconfig +++ b/drivers/pci/Kconfig @@ -21,6 +21,7 @@ config GENERIC_PCI_IOMAP menuconfig PCI bool "PCI support" depends on HAVE_PCI + depends on MMU help This option enables support for the PCI local bus, including support for PCI-X and the foundations for PCI Express support. @@ -121,6 +122,24 @@ config XEN_PCIDEV_FRONTEND config PCI_ATS bool +config PCI_IDE + bool + +config PCI_TSM + bool "PCI TSM: Device security protocol support" + select PCI_IDE + select PCI_DOE + select TSM + help + The TEE (Trusted Execution Environment) Device Interface + Security Protocol (TDISP) defines a "TSM" as a platform agent + that manages device authentication, link encryption, link + integrity protection, and assignment of PCI device functions + (virtual or physical) to confidential computing VMs that can + access (DMA) guest private memory. + + Enable a platform TSM driver to use this capability. + config PCI_DOE bool "Enable PCI Data Object Exchange (DOE) support" help @@ -206,12 +225,6 @@ config PCI_P2PDMA P2P DMA transactions must be between devices behind the same root port. - Enabling this option will reduce the entropy of x86 KASLR memory - regions. For example - on a 46 bit system, the entropy goes down - from 16 bits to 15 bits. The actual reduction in entropy depends - on the physical address bits, on processor features, kernel config - (5 level page table) and physical memory present on the system. - If unsure, say N. config PCI_LABEL @@ -220,8 +233,9 @@ config PCI_LABEL config PCI_HYPERV tristate "Hyper-V PCI Frontend" - depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && SYSFS + depends on ((X86 && X86_64) || ARM64) && HYPERV_VMBUS && PCI_MSI && SYSFS select PCI_HYPERV_INTERFACE + select IRQ_MSI_LIB help The PCI device frontend driver allows the kernel to import arbitrary PCI devices from a PCI backend to support PCI driver domains. @@ -304,6 +318,7 @@ config VGA_ARB bool "VGA Arbitration" if EXPERT default y depends on (PCI && !S390) + select SCREEN_INFO if X86 help Some "legacy" VGA devices implemented on PCI typically have the same hard-decoded addresses as they did on ISA. When multiple PCI devices diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile index 67647f1880fb..41ebc3b9a518 100644 --- a/drivers/pci/Makefile +++ b/drivers/pci/Makefile @@ -4,7 +4,7 @@ obj-$(CONFIG_PCI) += access.o bus.o probe.o host-bridge.o \ remove.o pci.o pci-driver.o search.o \ - rom.o setup-res.o irq.o vpd.o \ + rebar.o rom.o setup-res.o irq.o vpd.o \ setup-bus.o vc.o mmap.o devres.o obj-$(CONFIG_PCI) += msi/ @@ -34,9 +34,12 @@ obj-$(CONFIG_PCI_P2PDMA) += p2pdma.o obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o obj-$(CONFIG_VGA_ARB) += vgaarb.o obj-$(CONFIG_PCI_DOE) += doe.o +obj-$(CONFIG_PCI_IDE) += ide.o +obj-$(CONFIG_PCI_TSM) += tsm.o obj-$(CONFIG_PCI_DYNAMIC_OF_NODES) += of_property.o obj-$(CONFIG_PCI_NPEM) += npem.o obj-$(CONFIG_PCIE_TPH) += tph.o +obj-$(CONFIG_CARDBUS) += setup-cardbus.o # Endpoint library must be initialized before its users obj-$(CONFIG_PCI_ENDPOINT) += endpoint/ @@ -45,3 +48,6 @@ obj-y += controller/ obj-y += switch/ subdir-ccflags-$(CONFIG_PCI_DEBUG) := -DDEBUG + +CFLAGS_trace.o := -I$(src) +obj-$(CONFIG_TRACING) += trace.o diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index b6851101ac36..6c1ad1f542d9 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -8,12 +8,14 @@ */ #include <linux/module.h> #include <linux/kernel.h> +#include <linux/cleanup.h> #include <linux/pci.h> #include <linux/errno.h> #include <linux/ioport.h> #include <linux/of.h> #include <linux/of_platform.h> #include <linux/platform_device.h> +#include <linux/pm_runtime.h> #include <linux/proc_fs.h> #include <linux/slab.h> @@ -63,7 +65,7 @@ void pci_bus_add_resource(struct pci_bus *bus, struct resource *res) { struct pci_bus_resource *bus_res; - bus_res = kzalloc(sizeof(struct pci_bus_resource), GFP_KERNEL); + bus_res = kzalloc_obj(struct pci_bus_resource); if (!bus_res) { dev_err(&bus->dev, "can't add %pR resource\n", res); return; @@ -204,6 +206,9 @@ static int pci_bus_alloc_from_region(struct pci_bus *bus, struct resource *res, if (!r) continue; + if (r->flags & (IORESOURCE_UNSET|IORESOURCE_DISABLED)) + continue; + /* type_mask must match */ if ((res->flags ^ r->flags) & type_mask) continue; @@ -340,8 +345,6 @@ void __weak pcibios_bus_add_device(struct pci_dev *pdev) { } void pci_bus_add_device(struct pci_dev *dev) { struct device_node *dn = dev->dev.of_node; - struct platform_device *pdev; - int retval; /* * Can not put in pci_device_add yet because resources @@ -355,24 +358,20 @@ void pci_bus_add_device(struct pci_dev *dev) pci_proc_attach_device(dev); pci_bridge_d3_update(dev); + /* Save config space for error recoverability */ + pci_save_state(dev); + /* - * If the PCI device is associated with a pwrctrl device with a - * power supply, create a device link between the PCI device and - * pwrctrl device. This ensures that pwrctrl drivers are probed - * before PCI client drivers. + * Enable runtime PM, which potentially allows the device to + * suspend immediately, only after the PCI state has been + * configured completely. */ - pdev = of_find_device_by_node(dn); - if (pdev && of_pci_supply_present(dn)) { - if (!device_link_add(&dev->dev, &pdev->dev, - DL_FLAG_AUTOREMOVE_CONSUMER)) - pci_err(dev, "failed to add device link to power control device %s\n", - pdev->name); - } + pm_runtime_enable(&dev->dev); - dev->match_driver = !dn || of_device_is_available(dn); - retval = device_attach(&dev->dev); - if (retval < 0 && retval != -EPROBE_DEFER) - pci_warn(dev, "device attach failed (%d)\n", retval); + if (!dn || of_device_is_available(dn)) + pci_dev_allow_binding(dev); + + device_initial_probe(&dev->dev); pci_dev_assign_added(dev); } @@ -426,6 +425,27 @@ static int __pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void return ret; } +static int __pci_walk_bus_reverse(struct pci_bus *top, + int (*cb)(struct pci_dev *, void *), + void *userdata) +{ + struct pci_dev *dev; + int ret = 0; + + list_for_each_entry_reverse(dev, &top->devices, bus_list) { + if (dev->subordinate) { + ret = __pci_walk_bus_reverse(dev->subordinate, cb, + userdata); + if (ret) + break; + } + ret = cb(dev, userdata); + if (ret) + break; + } + return ret; +} + /** * pci_walk_bus - walk devices on/under bus, calling callback. * @top: bus whose devices should be walked @@ -447,6 +467,23 @@ void pci_walk_bus(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void } EXPORT_SYMBOL_GPL(pci_walk_bus); +/** + * pci_walk_bus_reverse - walk devices on/under bus, calling callback. + * @top: bus whose devices should be walked + * @cb: callback to be called for each device found + * @userdata: arbitrary pointer to be passed to callback + * + * Same semantics as pci_walk_bus(), but walks the bus in reverse order. + */ +void pci_walk_bus_reverse(struct pci_bus *top, + int (*cb)(struct pci_dev *, void *), void *userdata) +{ + down_read(&pci_bus_sem); + __pci_walk_bus_reverse(top, cb, userdata); + up_read(&pci_bus_sem); +} +EXPORT_SYMBOL_GPL(pci_walk_bus_reverse); + void pci_walk_bus_locked(struct pci_bus *top, int (*cb)(struct pci_dev *, void *), void *userdata) { lockdep_assert_held(&pci_bus_sem); diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig index 9800b7681054..5aaed8ac6e44 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 @@ -51,12 +58,29 @@ config PCI_VERSATILE bool "ARM Versatile PB PCI controller" depends on ARCH_VERSATILE || COMPILE_TEST +config PCIE_ASPEED + bool "ASPEED PCIe controller" + depends on ARCH_ASPEED || COMPILE_TEST + depends on OF + depends on PCI_MSI + select IRQ_MSI_LIB + help + Enable this option to support the PCIe controller found on ASPEED + SoCs. + + This driver provides initialization and management for PCIe + Root Complex functionality, including INTx and MSI support. + + Select Y if your platform uses an ASPEED SoC and requires PCIe + connectivity. + config PCIE_BRCMSTB tristate "Broadcom Brcmstb PCIe controller" depends on ARCH_BRCMSTB || ARCH_BCM2835 || ARCH_BCMBCA || \ 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 +117,7 @@ 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 +144,6 @@ 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 +162,7 @@ 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 +172,7 @@ 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 +212,7 @@ 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 +221,7 @@ 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, @@ -224,9 +248,10 @@ config PCI_HYPERV_INTERFACE driver. config PCI_TEGRA - bool "NVIDIA Tegra PCIe controller" + tristate "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. @@ -234,7 +259,9 @@ config PCI_TEGRA config PCIE_RCAR_HOST bool "Renesas R-Car PCIe controller (host mode)" depends on ARCH_RENESAS || COMPILE_TEST + depends on OF 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 +276,20 @@ 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 +338,7 @@ 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 +348,7 @@ 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 +358,7 @@ 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 +369,7 @@ 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..ac8db283f0fe 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 @@ -39,6 +40,7 @@ obj-$(CONFIG_PCI_LOONGSON) += pci-loongson.o obj-$(CONFIG_PCIE_HISI_ERR) += pcie-hisi-error.o obj-$(CONFIG_PCIE_APPLE) += pcie-apple.o obj-$(CONFIG_PCIE_MT7621) += pcie-mt7621.o +obj-$(CONFIG_PCIE_ASPEED) += pcie-aspeed.o # pcie-hisi.o quirks are needed even without CONFIG_PCIE_DW obj-y += dwc/ 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 ef1cfdae33bb..6f2501479c70 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"); @@ -433,6 +465,7 @@ static const struct of_device_id of_j721e_pcie_match[] = { }, {}, }; +MODULE_DEVICE_TABLE(of, of_j721e_pcie_match); static int j721e_pcie_probe(struct platform_device *pdev) { @@ -444,9 +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; @@ -464,7 +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)); @@ -483,7 +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); @@ -542,7 +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; } @@ -557,12 +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) { @@ -570,18 +601,12 @@ 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; /* * Section 2.2 of the PCI Express Card Electromechanical @@ -590,15 +615,15 @@ static int j721e_pcie_probe(struct platform_device *pdev) * This shall ensure that the power and the reference clock * are stable. */ - if (gpiod) { + if (pcie->reset_gpio) { msleep(PCIE_T_PVPERL_MS); - gpiod_set_value_cansleep(gpiod, 1); + gpiod_set_value_cansleep(pcie->reset_gpio, 1); } - ret = cdns_pcie_host_setup(rc); - if (ret < 0) { - clk_disable_unprepare(pcie->refclk); - goto err_pcie_setup; + if (IS_ENABLED(CONFIG_PCI_J721E_HOST)) { + ret = cdns_pcie_host_setup(rc); + if (ret < 0) + goto err_pcie_setup; } break; @@ -609,9 +634,11 @@ static int j721e_pcie_probe(struct platform_device *pdev) goto err_get_sync; } - ret = cdns_pcie_ep_setup(ep); - if (ret < 0) - goto err_pcie_setup; + if (IS_ENABLED(CONFIG_PCI_J721E_EP)) { + ret = cdns_pcie_ep_setup(ep); + if (ret < 0) + goto err_pcie_setup; + } break; } @@ -633,9 +660,22 @@ 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 (IS_ENABLED(CONFIG_PCI_J721E_HOST) && + pcie->mode == PCI_MODE_RC) { + rc = container_of(cdns_pcie, struct cdns_pcie_rc, pcie); + cdns_pcie_host_disable(rc); + } else if (IS_ENABLED(CONFIG_PCI_J721E_EP)) { + 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); } @@ -693,10 +733,12 @@ static int j721e_pcie_resume_noirq(struct device *dev) gpiod_set_value_cansleep(pcie->reset_gpio, 1); } - ret = cdns_pcie_host_link_setup(rc); - if (ret < 0) { - clk_disable_unprepare(pcie->refclk); - return ret; + if (IS_ENABLED(CONFIG_PCI_J721E_HOST)) { + ret = cdns_pcie_host_link_setup(rc); + if (ret < 0) { + clk_disable_unprepare(pcie->refclk); + return ret; + } } /* @@ -706,10 +748,12 @@ static int j721e_pcie_resume_noirq(struct device *dev) for (enum cdns_pcie_rp_bar bar = RP_BAR0; bar <= RP_NO_BAR; bar++) rc->avail_ib_bar[bar] = true; - ret = cdns_pcie_host_init(rc); - if (ret) { - clk_disable_unprepare(pcie->refclk); - return ret; + if (IS_ENABLED(CONFIG_PCI_J721E_HOST)) { + ret = cdns_pcie_host_init(rc); + if (ret) { + clk_disable_unprepare(pcie->refclk); + return ret; + } } } @@ -730,4 +774,8 @@ 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 599ec4b1223e..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; @@ -281,24 +289,24 @@ 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 MSI-X BAR and offset */ @@ -308,7 +316,7 @@ static int cdns_pcie_ep_set_msix(struct pci_epc *epc, u8 fn, u8 vfn, /* 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); @@ -351,7 +359,7 @@ 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) | + 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); } @@ -378,11 +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. */ @@ -430,14 +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. */ @@ -480,16 +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]; @@ -563,7 +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. @@ -587,12 +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); } } @@ -606,14 +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, @@ -644,6 +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) { @@ -751,3 +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..2b0211870f02 --- /dev/null +++ b/drivers/pci/controller/cadence/pcie-cadence-host-common.c @@ -0,0 +1,298 @@ +// 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; + u64 size1, size2; + + entry1 = container_of(a, struct resource_entry, node); + entry2 = container_of(b, struct resource_entry, node); + + size1 = resource_size(entry1->res); + size2 = resource_size(entry2->res); + + if (size1 > size2) + return -1; + + if (size1 < size2) + return 1; + + return 0; +} +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 204e045aed8c..a1eada56edba 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, NULL, 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, NULL, 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) { @@ -243,6 +275,7 @@ err_phy: return ret; } +EXPORT_SYMBOL_GPL(cdns_pcie_init_phy); static int cdns_pcie_suspend_noirq(struct device *dev) { @@ -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 39ee9945c903..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_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 d9f0386396ed..d0aa031397fa 100644 --- a/drivers/pci/controller/dwc/Kconfig +++ b/drivers/pci/controller/dwc/Kconfig @@ -19,6 +19,8 @@ config PCIE_DW_DEBUGFS config PCIE_DW_HOST bool select PCIE_DW + select IRQ_MSI_LIB + select PCI_HOST_COMMON config PCIE_DW_EP bool @@ -226,7 +228,7 @@ config PCIE_TEGRA194 config PCIE_TEGRA194_HOST tristate "NVIDIA Tegra194 (and later) PCIe controller (host mode)" - depends on ARCH_TEGRA_194_SOC || COMPILE_TEST + depends on (ARCH_TEGRA && ARM64) || COMPILE_TEST depends on PCI_MSI select PCIE_DW_HOST select PHY_TEGRA194_P2U @@ -241,7 +243,7 @@ config PCIE_TEGRA194_HOST config PCIE_TEGRA194_EP tristate "NVIDIA Tegra194 (and later) PCIe controller (endpoint mode)" - depends on ARCH_TEGRA_194_SOC || COMPILE_TEST + depends on (ARCH_TEGRA && ARM64) || COMPILE_TEST depends on PCI_ENDPOINT select PCIE_DW_EP select PHY_TEGRA194_P2U @@ -254,6 +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 @@ -296,6 +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 @@ -402,6 +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 @@ -410,6 +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 @@ -444,15 +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 @@ -460,11 +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 908cb7f345db..67ba59c02038 100644 --- a/drivers/pci/controller/dwc/Makefile +++ b/drivers/pci/controller/dwc/Makefile @@ -10,8 +10,12 @@ 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 @@ -20,6 +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 @@ -30,6 +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 33d6bf460ffe..d5d26229063f 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"); @@ -424,9 +424,9 @@ static int dra7xx_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, } static const struct pci_epc_features dra7xx_pcie_epc_features = { + DWC_EPC_COMMON_FEATURES, .linkup_notifier = true, .msi_capable = true, - .msix_capable = false, }; static const struct pci_epc_features* diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c index ace736b025b1..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) @@ -295,11 +300,6 @@ 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_enabled(dev, &ep->clks); if (ret < 0) return ret; diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c index 5f267dd261b5..a5b8d0b71677 100644 --- a/drivers/pci/controller/dwc/pci-imx6.c +++ b/drivers/pci/controller/dwc/pci-imx6.c @@ -45,9 +45,16 @@ #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_CLKREQ_OVERRIDE_EN BIT(8) +#define IMX95_PCIE_CLKREQ_OVERRIDE_VAL BIT(9) +#define IMX95_PCIE_SYS_AUX_PWR_DET BIT(31) #define IMX95_PE0_GEN_CTRL_1 0x1050 #define IMX95_PCIE_DEVICE_TYPE GENMASK(3, 0) @@ -71,6 +78,9 @@ #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 { @@ -91,7 +101,7 @@ enum imx_pcie_variants { }; #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) @@ -105,6 +115,8 @@ enum imx_pcie_variants { */ #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_PCIE_FLAG_SKIP_L23_READY BIT(12) #define imx_check_flag(pci, val) (pci->drvdata->flags & val) @@ -126,14 +138,23 @@ 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); + void (*clr_clkreq_override)(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; struct clk_bulk_data *clks; int num_clks; + bool supports_clkreq; + bool enable_ext_refclk; struct regmap *iomuxc_gpr; u16 msi_ctrl; u32 controller_id; @@ -148,6 +169,8 @@ 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 */ @@ -224,18 +247,32 @@ static unsigned int imx_pcie_grp_offset(const struct imx_pcie *imx_pcie) static int imx95_pcie_init_phy(struct imx_pcie *imx_pcie) { + bool ext = imx_pcie->enable_ext_refclk; + + /* + * 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, IMX95_PCIE_PHY_CR_PARA_SEL); - regmap_update_bits(imx_pcie->iomuxc_gpr, - IMX95_PCIE_PHY_GEN_CTRL, - IMX95_PCIE_REF_USE_PAD, 0); - regmap_update_bits(imx_pcie->iomuxc_gpr, - IMX95_PCIE_SS_RW_REG_0, + regmap_update_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_PHY_GEN_CTRL, + ext ? IMX95_PCIE_REF_USE_PAD : 0, + IMX95_PCIE_REF_USE_PAD); + regmap_update_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_SS_RW_REG_0, IMX95_PCIE_REF_CLKEN, - IMX95_PCIE_REF_CLKEN); + ext ? 0 : IMX95_PCIE_REF_CLKEN); return 0; } @@ -460,6 +497,23 @@ 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; @@ -638,7 +692,7 @@ static int imx6q_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) return 0; } -static int imx8mm_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) +static void imx8mm_pcie_clkreq_override(struct imx_pcie *imx_pcie, bool enable) { int offset = imx_pcie_grp_offset(imx_pcie); @@ -648,6 +702,11 @@ static int imx8mm_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) regmap_update_bits(imx_pcie->iomuxc_gpr, offset, IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN, enable ? IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN : 0); +} + +static int imx8mm_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) +{ + imx8mm_pcie_clkreq_override(imx_pcie, enable); return 0; } @@ -659,6 +718,32 @@ static int imx7d_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) return 0; } +static void imx95_pcie_clkreq_override(struct imx_pcie *imx_pcie, bool enable) +{ + regmap_update_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_SS_RW_REG_1, + IMX95_PCIE_CLKREQ_OVERRIDE_EN, + enable ? IMX95_PCIE_CLKREQ_OVERRIDE_EN : 0); + regmap_update_bits(imx_pcie->iomuxc_gpr, IMX95_PCIE_SS_RW_REG_1, + IMX95_PCIE_CLKREQ_OVERRIDE_VAL, + enable ? IMX95_PCIE_CLKREQ_OVERRIDE_VAL : 0); +} + +static int imx95_pcie_enable_ref_clk(struct imx_pcie *imx_pcie, bool enable) +{ + imx95_pcie_clkreq_override(imx_pcie, enable); + return 0; +} + +static void imx8mm_pcie_clr_clkreq_override(struct imx_pcie *imx_pcie) +{ + imx8mm_pcie_clkreq_override(imx_pcie, false); +} + +static void imx95_pcie_clr_clkreq_override(struct imx_pcie *imx_pcie) +{ + imx95_pcie_clkreq_override(imx_pcie, false); +} + static int imx_pcie_clk_enable(struct imx_pcie *imx_pcie) { struct dw_pcie *pci = imx_pcie->pci; @@ -773,10 +858,46 @@ 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); @@ -788,7 +909,6 @@ static void imx_pcie_assert_core_reset(struct imx_pcie *imx_pcie) static int imx_pcie_deassert_core_reset(struct imx_pcie *imx_pcie) { reset_control_deassert(imx_pcie->pciephy_reset); - reset_control_deassert(imx_pcie->apps_reset); if (imx_pcie->drvdata->core_reset) imx_pcie->drvdata->core_reset(imx_pcie, false); @@ -860,6 +980,12 @@ 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 @@ -875,11 +1001,11 @@ 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); @@ -896,34 +1022,15 @@ 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"); } - 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: @@ -992,7 +1099,10 @@ static int imx_pcie_add_lut(struct imx_pcie *imx_pcie, u16 rid, u8 sid) data1 |= IMX95_PE0_LUT_VLD; regmap_write(imx_pcie->iomuxc_gpr, IMX95_PE0_LUT_DATA1, data1); - data2 = IMX95_PE0_LUT_MASK; /* Match all bits of RID */ + 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); @@ -1025,18 +1135,14 @@ static void imx_pcie_remove_lut(struct imx_pcie *imx_pcie, u16 rid) } } -static int imx_pcie_enable_device(struct pci_host_bridge *bridge, - struct pci_dev *pdev) +static int imx_pcie_add_lut_by_rid(struct imx_pcie *imx_pcie, u32 rid) { - struct imx_pcie *imx_pcie = to_imx_pcie(to_dw_pcie_from_pp(bridge->sysdata)); - u32 sid_i, sid_m, rid = pci_dev_id(pdev); + struct device *dev = imx_pcie->pci->dev; struct device_node *target; - struct device *dev; + u32 sid_i, sid_m; int err_i, err_m; u32 sid = 0; - dev = imx_pcie->pci->dev; - target = NULL; err_i = of_map_id(dev->of_node, rid, "iommu-map", "iommu-map-mask", &target, &sid_i); @@ -1111,6 +1217,13 @@ static int imx_pcie_enable_device(struct pci_host_bridge *bridge, 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) { @@ -1176,12 +1289,21 @@ 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; @@ -1214,6 +1336,38 @@ static void imx_pcie_host_exit(struct dw_pcie_rp *pp) regulator_disable(imx_pcie->vpcie); } +static void imx_pcie_host_post_init(struct dw_pcie_rp *pp) +{ + 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_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); + } + + /* Clear CLKREQ# override if supports_clkreq is true and link is up */ + if (dw_pcie_link_up(pci) && imx_pcie->supports_clkreq) { + if (imx_pcie->drvdata->clr_clkreq_override) + imx_pcie->drvdata->clr_clkreq_override(imx_pcie); + } +} + /* * In old DWC implementations, PCIE_ATU_INHIBIT_PAYLOAD in iATU Ctrl2 * register is reserved, so the generic DWC implementation of sending the @@ -1239,6 +1393,7 @@ static const struct dw_pcie_host_ops imx_pcie_host_ops = { 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 = { @@ -1276,18 +1431,18 @@ 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, + DWC_EPC_COMMON_FEATURES, .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 = { - .linkup_notifier = false, + DWC_EPC_COMMON_FEATURES, .msi_capable = true, - .msix_capable = false, .bar[BAR_1] = { .type = BAR_RESERVED, }, .bar[BAR_3] = { .type = BAR_RESERVED, }, .bar[BAR_5] = { .type = BAR_RESERVED, }, @@ -1307,6 +1462,7 @@ static const struct pci_epc_features imx8q_pcie_epc_features = { * BAR5 | Enable | 32-bit | 64 KB | Programmable Size */ static const struct pci_epc_features imx95_pcie_epc_features = { + DWC_EPC_COMMON_FEATURES, .msi_capable = true, .bar[BAR_1] = { .type = BAR_FIXED, .fixed_size = SZ_64K, }, .align = SZ_4K, @@ -1350,6 +1506,7 @@ 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) { @@ -1360,9 +1517,6 @@ 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; } @@ -1386,6 +1540,42 @@ 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); @@ -1394,6 +1584,8 @@ static int imx_pcie_suspend_noirq(struct device *dev) return 0; imx_pcie_msi_save_restore(imx_pcie, true); + 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 @@ -1438,6 +1630,8 @@ static int imx_pcie_resume_noirq(struct device *dev) 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; @@ -1455,7 +1649,7 @@ static int imx_pcie_probe(struct platform_device *pdev) struct imx_pcie *imx_pcie; struct device_node *np; struct device_node *node = dev->of_node; - int ret, domain; + int i, ret, domain; u16 val; imx_pcie = devm_kzalloc(dev, sizeof(*imx_pcie), GFP_KERNEL); @@ -1506,6 +1700,9 @@ static int imx_pcie_probe(struct platform_device *pdev) if (imx_pcie->num_clks < 0) return dev_err_probe(dev, imx_pcie->num_clks, "failed to get clocks\n"); + for (i = 0; i < imx_pcie->num_clks; i++) + if (strncmp(imx_pcie->clks[i].id, "extref", 6) == 0) + imx_pcie->enable_ext_refclk = true; if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_HAS_PHYDRV)) { imx_pcie->phy = devm_phy_get(dev, "pcie-phy"); @@ -1593,6 +1790,11 @@ static int imx_pcie_probe(struct platform_device *pdev) /* Limit link speed */ pci->max_link_speed = 1; of_property_read_u32(node, "fsl,max-link-speed", &pci->max_link_speed); + imx_pcie->supports_clkreq = of_property_read_bool(node, "supports-clkreq"); + + 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)) { @@ -1619,7 +1821,15 @@ static int imx_pcie_probe(struct platform_device *pdev) 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 { + if (imx_check_flag(imx_pcie, IMX_PCIE_FLAG_SKIP_L23_READY)) + pci->pp.skip_l23_ready = true; pci->pp.use_atu_msg = true; ret = dw_pcie_host_init(&pci->pp); if (ret < 0) @@ -1649,7 +1859,7 @@ 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, @@ -1665,7 +1875,7 @@ 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", .ltssm_off = IOMUXC_GPR12, @@ -1680,7 +1890,8 @@ static const struct imx_pcie_drvdata drvdata[] = { [IMX6QP] = { .variant = IMX6QP, .flags = IMX_PCIE_FLAG_IMX_PHY | - IMX_PCIE_FLAG_IMX_SPEED_CHANGE | + IMX_PCIE_FLAG_SPEED_CHANGE_WORKAROUND | + IMX_PCIE_FLAG_SKIP_L23_READY | IMX_PCIE_FLAG_SUPPORTS_SUSPEND, .dbi_length = 0x200, .gpr = "fsl,imx6q-iomuxc-gpr", @@ -1697,6 +1908,7 @@ static const struct imx_pcie_drvdata drvdata[] = { .variant = IMX7D, .flags = IMX_PCIE_FLAG_SUPPORTS_SUSPEND | IMX_PCIE_FLAG_HAS_APP_RESET | + IMX_PCIE_FLAG_SKIP_L23_READY | IMX_PCIE_FLAG_HAS_PHY_RESET, .gpr = "fsl,imx7d-iomuxc-gpr", .mode_off[0] = IOMUXC_GPR12, @@ -1716,6 +1928,7 @@ static const struct imx_pcie_drvdata drvdata[] = { .mode_mask[1] = IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE, .init_phy = imx8mq_pcie_init_phy, .enable_ref_clk = imx8mm_pcie_enable_ref_clk, + .clr_clkreq_override = imx8mm_pcie_clr_clkreq_override, }, [IMX8MM] = { .variant = IMX8MM, @@ -1726,6 +1939,7 @@ static const struct imx_pcie_drvdata drvdata[] = { .mode_off[0] = IOMUXC_GPR12, .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, .enable_ref_clk = imx8mm_pcie_enable_ref_clk, + .clr_clkreq_override = imx8mm_pcie_clr_clkreq_override, }, [IMX8MP] = { .variant = IMX8MP, @@ -1736,6 +1950,7 @@ static const struct imx_pcie_drvdata drvdata[] = { .mode_off[0] = IOMUXC_GPR12, .mode_mask[0] = IMX6Q_GPR12_DEVICE_TYPE, .enable_ref_clk = imx8mm_pcie_enable_ref_clk, + .clr_clkreq_override = imx8mm_pcie_clr_clkreq_override, }, [IMX8Q] = { .variant = IMX8Q, @@ -1747,12 +1962,17 @@ static const struct imx_pcie_drvdata drvdata[] = { .variant = IMX95, .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, + .enable_ref_clk = imx95_pcie_enable_ref_clk, + .clr_clkreq_override = imx95_pcie_clr_clkreq_override, }, [IMX8MQ_EP] = { .variant = IMX8MQ_EP, @@ -1764,7 +1984,7 @@ static const struct imx_pcie_drvdata drvdata[] = { .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, }, @@ -1799,13 +2019,17 @@ static const struct imx_pcie_drvdata drvdata[] = { [IMX95_EP] = { .variant = IMX95_EP, .flags = IMX_PCIE_FLAG_HAS_SERDES | + IMX_PCIE_FLAG_8GT_ECN_ERR051586 | IMX_PCIE_FLAG_SUPPORT_64BIT, .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, + .enable_ref_clk = imx95_pcie_enable_ref_clk, .mode = DW_PCIE_EP_TYPE, }, }; diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c index 76a37368ae4f..20fa4dadb82a 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> @@ -492,13 +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) @@ -761,7 +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"); @@ -778,29 +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; @@ -832,7 +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); @@ -862,15 +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; } @@ -961,7 +930,7 @@ 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, + DWC_EPC_COMMON_FEATURES, .msi_capable = true, .msix_capable = true, .bar[BAR_0] = { .type = BAR_RESERVED, }, @@ -1136,6 +1105,7 @@ 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) { @@ -1202,8 +1172,8 @@ 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); @@ -1214,11 +1184,11 @@ 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; @@ -1339,6 +1309,8 @@ 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); @@ -1381,4 +1353,45 @@ static struct platform_driver ks_pcie_driver = { .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-meson.c b/drivers/pci/controller/dwc/pci-meson.c index db9482a113e9..0694084f612b 100644 --- a/drivers/pci/controller/dwc/pci-meson.c +++ b/drivers/pci/controller/dwc/pci-meson.c @@ -37,7 +37,6 @@ #define PCIE_CFG_STATUS17 0x44 #define PM_CURRENT_STATE(x) (((x) >> 7) & 0x1) -#define WAIT_LINKUP_TIMEOUT 4000 #define PORT_CLK_RATE 100000000UL #define MAX_PAYLOAD_SIZE 256 #define MAX_READ_REQ_SIZE 256 @@ -108,10 +107,22 @@ 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)) @@ -335,43 +346,13 @@ 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; - u32 speed_okay = 0; - u32 cnt = 0; - u32 state12, state17, smlh_up, ltssm_up, rdlh_up; - - do { - state12 = meson_cfg_readl(mp, PCIE_CFG_STATUS12); - state17 = meson_cfg_readl(mp, PCIE_CFG_STATUS17); - smlh_up = IS_SMLH_LINK_UP(state12); - rdlh_up = IS_RDLH_LINK_UP(state12); - ltssm_up = IS_LTSSM_UP(state12); - - if (PM_CURRENT_STATE(state17) < PCIE_GEN3) - speed_okay = 1; - - if (smlh_up) - dev_dbg(dev, "smlh_link_up is on\n"); - if (rdlh_up) - dev_dbg(dev, "rdlh_link_up is on\n"); - if (ltssm_up) - dev_dbg(dev, "ltssm_up is on\n"); - if (speed_okay) - dev_dbg(dev, "speed_okay\n"); - - if (smlh_up && rdlh_up && ltssm_up && speed_okay) - return 1; - - cnt++; - - udelay(10); - } while (cnt < WAIT_LINKUP_TIMEOUT); - - dev_err(dev, "error: wait linkup timeout\n"); - return 0; + u32 state12; + + state12 = meson_cfg_readl(mp, PCIE_CFG_STATUS12); + return IS_SMLH_LINK_UP(state12) && IS_RDLH_LINK_UP(state12); } 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 index 4eb2a4e8189d..3c6e837465bb 100644 --- a/drivers/pci/controller/dwc/pcie-amd-mdb.c +++ b/drivers/pci/controller/dwc/pcie-amd-mdb.c @@ -18,6 +18,7 @@ #include <linux/resource.h> #include <linux/types.h> +#include "../../pci.h" #include "pcie-designware.h" #define AMD_MDB_TLP_IR_STATUS_MISC 0x4C0 @@ -56,6 +57,7 @@ * @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 { @@ -63,6 +65,7 @@ struct amd_mdb_pcie { void __iomem *slcr; struct irq_domain *intx_domain; struct irq_domain *mdb_domain; + struct gpio_desc *perst_gpio; int intx_irq; }; @@ -284,14 +287,14 @@ static int amd_mdb_pcie_init_irq_domains(struct amd_mdb_pcie *pcie, struct device_node *pcie_intc_node; int err; - pcie_intc_node = of_get_next_child(node, NULL); + 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_add_linear(pcie_intc_node, 32, - &event_domain_ops, pcie); + 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"); @@ -300,8 +303,8 @@ static int amd_mdb_pcie_init_irq_domains(struct amd_mdb_pcie *pcie, irq_domain_update_bus_token(pcie->mdb_domain, DOMAIN_BUS_NEXUS); - pcie->intx_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX, - &amd_intx_domain_ops, pcie); + 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"); @@ -402,6 +405,28 @@ static int amd_mdb_setup_irq(struct amd_mdb_pcie *pcie, 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) { @@ -426,6 +451,12 @@ static int amd_mdb_add_pcie_port(struct amd_mdb_pcie *pcie, 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); @@ -444,6 +475,7 @@ 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) @@ -454,6 +486,24 @@ static int amd_mdb_pcie_probe(struct platform_device *pdev) 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); } 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 234c8cbcae3a..e994b75986c3 100644 --- a/drivers/pci/controller/dwc/pcie-artpec6.c +++ b/drivers/pci/controller/dwc/pcie-artpec6.c @@ -370,9 +370,8 @@ static int artpec6_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, } static const struct pci_epc_features artpec6_pcie_epc_features = { - .linkup_notifier = false, + DWC_EPC_COMMON_FEATURES, .msi_capable = true, - .msix_capable = false, }; static const struct pci_epc_features * diff --git a/drivers/pci/controller/dwc/pcie-designware-debugfs.c b/drivers/pci/controller/dwc/pcie-designware-debugfs.c index 9e6f4d00f262..0d1340c9b364 100644 --- a/drivers/pci/controller/dwc/pcie-designware-debugfs.c +++ b/drivers/pci/controller/dwc/pcie-designware-debugfs.c @@ -443,63 +443,13 @@ static ssize_t counter_value_read(struct file *file, char __user *buf, 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); + seq_printf(s, "%s (0x%02x)\n", dw_pcie_ltssm_status_string(val), val); return 0; } @@ -642,16 +592,262 @@ static void dwc_pcie_ltssm_debugfs_init(struct dw_pcie *pci, struct dentry *dir) &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) +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; @@ -674,4 +870,8 @@ void dwc_pcie_debugfs_init(struct dw_pcie *pci) 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 1a0bf9341542..295076cf70de 100644 --- a/drivers/pci/controller/dwc/pcie-designware-ep.c +++ b/drivers/pci/controller/dwc/pcie-designware-ep.c @@ -69,77 +69,18 @@ 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) -{ - u8 cap_id, next_cap_ptr; - u16 reg; - - if (!cap_ptr) - return 0; - - reg = dw_pcie_ep_readw_dbi(ep, func_no, cap_ptr); - cap_id = (reg & 0x00ff); - - if (cap_id > PCI_CAP_ID_MAX) - return 0; - - if (cap_id == cap) - return cap_ptr; - - next_cap_ptr = (reg & 0xff00) >> 8; - return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap); -} - static u8 dw_pcie_ep_find_capability(struct dw_pcie_ep *ep, u8 func_no, u8 cap) { - u8 next_cap_ptr; - u16 reg; - - reg = dw_pcie_ep_readw_dbi(ep, func_no, PCI_CAPABILITY_LIST); - next_cap_ptr = (reg & 0x00ff); - - return __dw_pcie_ep_find_next_cap(ep, func_no, next_cap_ptr, cap); + return PCI_FIND_NEXT_CAP(dw_pcie_ep_read_cfg, PCI_CAPABILITY_LIST, + cap, NULL, ep, func_no); } -/** - * 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) +static u16 dw_pcie_ep_find_ext_capability(struct dw_pcie_ep *ep, + u8 func_no, u8 cap) { - u16 prev_cap_offset, cap_offset; - u32 prev_cap_header, cap_header; - - prev_cap_offset = dw_pcie_find_ext_capability(pci, prev_cap); - if (!prev_cap_offset) - return -EINVAL; - - 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); - - /* cap must immediately follow prev_cap. */ - if (PCI_EXT_CAP_ID(cap_header) != cap) - return -EINVAL; - - /* Clear next ptr. */ - prev_cap_header &= ~GENMASK(31, 20); - - /* Set next ptr to next ptr of cap. */ - prev_cap_header |= cap_header & GENMASK(31, 20); - - 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 0; + return PCI_FIND_NEXT_EXT_CAP(dw_pcie_ep_read_cfg, 0, + cap, NULL, ep, func_no); } -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) @@ -166,18 +107,23 @@ static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no, u8 vfunc_no, return 0; } -static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no, int type, - dma_addr_t parent_bus_addr, enum pci_barno bar, - size_t size) +/* BAR Match Mode inbound iATU mapping */ +static int dw_pcie_ep_ib_atu_bar(struct dw_pcie_ep *ep, u8 func_no, int type, + dma_addr_t parent_bus_addr, enum pci_barno bar, + size_t size) { int ret; u32 free_win; struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct dw_pcie_ep_func *ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); - if (!ep->bar_to_atu[bar]) + if (!ep_func) + return -EINVAL; + + if (!ep_func->bar_to_atu[bar]) free_win = find_first_zero_bit(ep->ib_window_map, pci->num_ib_windows); else - free_win = ep->bar_to_atu[bar] - 1; + free_win = ep_func->bar_to_atu[bar] - 1; if (free_win >= pci->num_ib_windows) { dev_err(pci->dev, "No free inbound window\n"); @@ -195,12 +141,191 @@ static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no, int type, * Always increment free_win before assignment, since value 0 is used to identify * unallocated mapping. */ - ep->bar_to_atu[bar] = free_win + 1; + ep_func->bar_to_atu[bar] = free_win + 1; set_bit(free_win, ep->ib_window_map); return 0; } +static void dw_pcie_ep_clear_ib_maps(struct dw_pcie_ep *ep, u8 func_no, enum pci_barno bar) +{ + struct dw_pcie_ep_func *ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + struct device *dev = pci->dev; + unsigned int i, num; + u32 atu_index; + u32 *indexes; + + if (!ep_func) + return; + + /* Tear down the BAR Match Mode mapping, if any. */ + if (ep_func->bar_to_atu[bar]) { + atu_index = ep_func->bar_to_atu[bar] - 1; + dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_IB, atu_index); + clear_bit(atu_index, ep->ib_window_map); + ep_func->bar_to_atu[bar] = 0; + return; + } + + /* Tear down all Address Match Mode mappings, if any. */ + indexes = ep_func->ib_atu_indexes[bar]; + num = ep_func->num_ib_atu_indexes[bar]; + ep_func->ib_atu_indexes[bar] = NULL; + ep_func->num_ib_atu_indexes[bar] = 0; + if (!indexes) + return; + for (i = 0; i < num; i++) { + dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_IB, indexes[i]); + clear_bit(indexes[i], ep->ib_window_map); + } + devm_kfree(dev, indexes); +} + +static u64 dw_pcie_ep_read_bar_assigned(struct dw_pcie_ep *ep, u8 func_no, + enum pci_barno bar, int flags) +{ + u32 reg = PCI_BASE_ADDRESS_0 + (4 * bar); + u32 lo, hi; + u64 addr; + + lo = dw_pcie_ep_readl_dbi(ep, func_no, reg); + + if (flags & PCI_BASE_ADDRESS_SPACE) + return lo & PCI_BASE_ADDRESS_IO_MASK; + + addr = lo & PCI_BASE_ADDRESS_MEM_MASK; + if (!(flags & PCI_BASE_ADDRESS_MEM_TYPE_64)) + return addr; + + hi = dw_pcie_ep_readl_dbi(ep, func_no, reg + 4); + return addr | ((u64)hi << 32); +} + +static int dw_pcie_ep_validate_submap(struct dw_pcie_ep *ep, + const struct pci_epf_bar_submap *submap, + unsigned int num_submap, size_t bar_size) +{ + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + u32 align = pci->region_align; + size_t off = 0; + unsigned int i; + size_t size; + + if (!align || !IS_ALIGNED(bar_size, align)) + return -EINVAL; + + /* + * The submap array order defines the BAR layout (submap[0] starts + * at offset 0 and each entry immediately follows the previous + * one). Here, validate that it forms a strict, gapless + * decomposition of the BAR: + * - each entry has a non-zero size + * - sizes, implicit offsets and phys_addr are aligned to + * pci->region_align + * - each entry lies within the BAR range + * - the entries exactly cover the whole BAR + * + * Note: dw_pcie_prog_inbound_atu() also checks alignment for the + * PCI address and the target phys_addr, but validating up-front + * avoids partially programming iATU windows in vain. + */ + for (i = 0; i < num_submap; i++) { + size = submap[i].size; + + if (!size) + return -EINVAL; + + if (!IS_ALIGNED(size, align) || !IS_ALIGNED(off, align)) + return -EINVAL; + + if (!IS_ALIGNED(submap[i].phys_addr, align)) + return -EINVAL; + + if (off > bar_size || size > bar_size - off) + return -EINVAL; + + off += size; + } + if (off != bar_size) + return -EINVAL; + + return 0; +} + +/* Address Match Mode inbound iATU mapping */ +static int dw_pcie_ep_ib_atu_addr(struct dw_pcie_ep *ep, u8 func_no, int type, + const struct pci_epf_bar *epf_bar) +{ + struct dw_pcie_ep_func *ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + const struct pci_epf_bar_submap *submap = epf_bar->submap; + struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + enum pci_barno bar = epf_bar->barno; + struct device *dev = pci->dev; + u64 pci_addr, parent_bus_addr; + u64 size, base, off = 0; + int free_win, ret; + unsigned int i; + u32 *indexes; + + if (!ep_func || !epf_bar->num_submap || !submap || !epf_bar->size) + return -EINVAL; + + ret = dw_pcie_ep_validate_submap(ep, submap, epf_bar->num_submap, + epf_bar->size); + if (ret) + return ret; + + base = dw_pcie_ep_read_bar_assigned(ep, func_no, bar, epf_bar->flags); + if (!base) { + dev_err(dev, + "BAR%u not assigned, cannot set up sub-range mappings\n", + bar); + return -EINVAL; + } + + indexes = devm_kcalloc(dev, epf_bar->num_submap, sizeof(*indexes), + GFP_KERNEL); + if (!indexes) + return -ENOMEM; + + ep_func->ib_atu_indexes[bar] = indexes; + ep_func->num_ib_atu_indexes[bar] = 0; + + for (i = 0; i < epf_bar->num_submap; i++) { + size = submap[i].size; + parent_bus_addr = submap[i].phys_addr; + + if (off > (~0ULL) - base) { + ret = -EINVAL; + goto err; + } + + pci_addr = base + off; + off += size; + + free_win = find_first_zero_bit(ep->ib_window_map, + pci->num_ib_windows); + if (free_win >= pci->num_ib_windows) { + ret = -ENOSPC; + goto err; + } + + ret = dw_pcie_prog_inbound_atu(pci, free_win, type, + parent_bus_addr, pci_addr, size); + if (ret) + goto err; + + set_bit(free_win, ep->ib_window_map); + indexes[i] = free_win; + ep_func->num_ib_atu_indexes[bar] = i + 1; + } + return 0; +err: + dw_pcie_ep_clear_ib_maps(ep, func_no, bar); + return ret; +} + static int dw_pcie_ep_outbound_atu(struct dw_pcie_ep *ep, struct dw_pcie_ob_atu_cfg *atu) { @@ -231,36 +356,35 @@ static void dw_pcie_ep_clear_bar(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); enum pci_barno bar = epf_bar->barno; - u32 atu_index = ep->bar_to_atu[bar] - 1; + struct dw_pcie_ep_func *ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); - if (!ep->bar_to_atu[bar]) + if (!ep_func || !ep_func->epf_bar[bar]) return; __dw_pcie_ep_reset_bar(pci, func_no, bar, epf_bar->flags); - dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_IB, atu_index); - clear_bit(atu_index, ep->ib_window_map); - ep->epf_bar[bar] = NULL; - ep->bar_to_atu[bar] = 0; + dw_pcie_ep_clear_ib_maps(ep, func_no, bar); + + ep_func->epf_bar[bar] = NULL; } -static unsigned int dw_pcie_ep_get_rebar_offset(struct dw_pcie *pci, +static unsigned int dw_pcie_ep_get_rebar_offset(struct dw_pcie_ep *ep, u8 func_no, 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); + offset = dw_pcie_ep_find_ext_capability(ep, func_no, PCI_EXT_CAP_ID_REBAR); if (!offset) return offset; - reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL); - nbars = (reg & PCI_REBAR_CTRL_NBAR_MASK) >> PCI_REBAR_CTRL_NBAR_SHIFT; + reg = dw_pcie_ep_readl_dbi(ep, func_no, 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 = reg & PCI_REBAR_CTRL_BAR_IDX; + reg = dw_pcie_ep_readl_dbi(ep, func_no, offset + PCI_REBAR_CTRL); + bar_index = FIELD_GET(PCI_REBAR_CTRL_BAR_IDX, reg); if (bar_index == bar) return offset; } @@ -280,7 +404,7 @@ static int dw_pcie_ep_set_bar_resizable(struct dw_pcie_ep *ep, u8 func_no, u32 rebar_cap, rebar_ctrl; int ret; - rebar_offset = dw_pcie_ep_get_rebar_offset(pci, bar); + rebar_offset = dw_pcie_ep_get_rebar_offset(ep, func_no, bar); if (!rebar_offset) return -EINVAL; @@ -310,16 +434,16 @@ static int dw_pcie_ep_set_bar_resizable(struct dw_pcie_ep *ep, u8 func_no, * 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 = dw_pcie_ep_readl_dbi(ep, func_no, rebar_offset + PCI_REBAR_CTRL); rebar_ctrl &= ~GENMASK(31, 16); - dw_pcie_writel_dbi(pci, rebar_offset + PCI_REBAR_CTRL, rebar_ctrl); + dw_pcie_ep_writel_dbi(ep, func_no, 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_ep_writel_dbi(ep, func_no, rebar_offset + PCI_REBAR_CAP, rebar_cap); dw_pcie_dbi_ro_wr_dis(pci); @@ -368,12 +492,16 @@ static int dw_pcie_ep_set_bar(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); + struct dw_pcie_ep_func *ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); 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; + if (!ep_func) + return -EINVAL; + /* * DWC does not allow BAR pairs to overlap, e.g. you cannot combine BARs * 1 and 2 to form a 64-bit BAR. @@ -387,21 +515,46 @@ static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, * calling clear_bar() would clear the BAR's PCI address assigned by the * host). */ - if (ep->epf_bar[bar]) { + if (ep_func->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. + * + * Note: this safety check only works when the caller uses + * a new struct pci_epf_bar in the second set_bar() call. + * If the same instance is updated in place and passed in, + * we cannot reliably detect invalid barno/size/flags + * changes here. */ - if (ep->epf_bar[bar]->barno != bar || - ep->epf_bar[bar]->size != size || - ep->epf_bar[bar]->flags != flags) + if (ep_func->epf_bar[bar]->barno != bar || + ep_func->epf_bar[bar]->size != size || + ep_func->epf_bar[bar]->flags != flags) return -EINVAL; /* + * When dynamically changing a BAR, tear down any existing + * mappings before re-programming. This is redundant when + * both the old and new mappings are BAR Match Mode, but + * required to handle in-place updates and match-mode + * changes reliably. + */ + dw_pcie_ep_clear_ib_maps(ep, func_no, bar); + + /* * 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; + } else { + /* + * Subrange mapping is an update-only operation. The BAR + * must have been configured once without submaps so that + * subsequent set_bar() calls can update inbound mappings + * without touching the BAR register (and clobbering the + * host-assigned address). + */ + if (epf_bar->num_submap) + return -EINVAL; } bar_type = dw_pcie_ep_get_bar_type(ep, bar); @@ -435,12 +588,16 @@ config_atu: else type = PCIE_ATU_TYPE_IO; - ret = dw_pcie_ep_inbound_atu(ep, func_no, type, epf_bar->phys_addr, bar, - size); + if (epf_bar->num_submap) + ret = dw_pcie_ep_ib_atu_addr(ep, func_no, type, epf_bar); + else + ret = dw_pcie_ep_ib_atu_bar(ep, func_no, type, + epf_bar->phys_addr, bar, size); + if (ret) return ret; - ep->epf_bar[bar] = epf_bar; + ep_func->epf_bar[bar] = epf_bar; return 0; } @@ -532,15 +689,16 @@ 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); @@ -550,7 +708,7 @@ 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); @@ -575,11 +733,11 @@ 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); @@ -595,7 +753,7 @@ 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; @@ -603,7 +761,7 @@ 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); @@ -627,6 +785,16 @@ static void dw_pcie_ep_stop(struct pci_epc *epc) struct dw_pcie_ep *ep = epc_get_drvdata(epc); struct dw_pcie *pci = to_dw_pcie_from_ep(ep); + /* + * Tear down the dedicated outbound window used for MSI + * generation. This avoids leaking an iATU window across + * endpoint stop/start cycles. + */ + if (ep->msi_iatu_mapped) { + dw_pcie_ep_unmap_addr(epc, 0, 0, ep->msi_mem_phys); + ep->msi_iatu_mapped = false; + } + dw_pcie_stop_link(pci); } @@ -671,7 +839,7 @@ 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) { @@ -690,7 +858,7 @@ 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) @@ -728,14 +896,37 @@ 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; 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, - map_size); - if (ret) - return ret; - writel(msg_data | (interrupt_num - 1), ep->msi_mem + offset); + /* + * Program the outbound iATU once and keep it enabled. + * + * The spec warns that updating iATU registers while there are + * operations in flight on the AXI bridge interface is not + * supported, so we avoid reprogramming the region on every MSI, + * specifically unmapping immediately after writel(). + */ + if (!ep->msi_iatu_mapped) { + ret = dw_pcie_ep_map_addr(epc, func_no, 0, + ep->msi_mem_phys, msg_addr, + map_size); + if (ret) + return ret; + + ep->msi_iatu_mapped = true; + ep->msi_msg_addr = msg_addr; + ep->msi_map_size = map_size; + } else if (WARN_ON_ONCE(ep->msi_msg_addr != msg_addr || + ep->msi_map_size != map_size)) { + /* + * The host changed the MSI target address or the required + * mapping size changed. Reprogramming the iATU at runtime is + * unsafe on this controller, so bail out instead of trying to + * update the existing region. + */ + return -EINVAL; + } - dw_pcie_ep_unmap_addr(epc, func_no, 0, ep->msi_mem_phys); + writel(msg_data | (interrupt_num - 1), ep->msi_mem + offset); return 0; } @@ -801,7 +992,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, bir = FIELD_GET(PCI_MSIX_TABLE_BIR, tbl_offset); tbl_offset &= PCI_MSIX_TABLE_OFFSET; - msix_tbl = ep->epf_bar[bir]->addr + tbl_offset; + msix_tbl = ep_func->epf_bar[bir]->addr + tbl_offset; msg_addr = msix_tbl[(interrupt_num - 1)].msg_addr; msg_data = msix_tbl[(interrupt_num - 1)].msg_data; vec_ctrl = msix_tbl[(interrupt_num - 1)].vector_ctrl; @@ -823,6 +1014,7 @@ int dw_pcie_ep_raise_msix_irq(struct dw_pcie_ep *ep, u8 func_no, return 0; } +EXPORT_SYMBOL_GPL(dw_pcie_ep_raise_msix_irq); /** * dw_pcie_ep_cleanup - Cleanup DWC EP resources after fundamental reset @@ -861,22 +1053,21 @@ void dw_pcie_ep_deinit(struct dw_pcie_ep *ep) } EXPORT_SYMBOL_GPL(dw_pcie_ep_deinit); -static void dw_pcie_ep_init_non_sticky_registers(struct dw_pcie *pci) +static void dw_pcie_ep_init_rebar_registers(struct dw_pcie_ep *ep, u8 func_no) { - struct dw_pcie_ep *ep = &pci->ep; - unsigned int offset; - unsigned int nbars; + struct dw_pcie_ep_func *ep_func = dw_pcie_ep_get_func_from_ep(ep, func_no); + unsigned int offset, nbars; enum pci_barno bar; u32 reg, i, val; - offset = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_REBAR); + if (!ep_func) + return; - dw_pcie_dbi_ro_wr_en(pci); + offset = dw_pcie_ep_find_ext_capability(ep, func_no, PCI_EXT_CAP_ID_REBAR); if (offset) { - reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL); - nbars = (reg & PCI_REBAR_CTRL_NBAR_MASK) >> - PCI_REBAR_CTRL_NBAR_SHIFT; + reg = dw_pcie_ep_readl_dbi(ep, func_no, offset + PCI_REBAR_CTRL); + nbars = FIELD_GET(PCI_REBAR_CTRL_NBAR_MASK, reg); /* * PCIe r6.0, sec 7.8.6.2 require us to support at least one @@ -896,16 +1087,28 @@ static void dw_pcie_ep_init_non_sticky_registers(struct dw_pcie *pci) * 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 = val & PCI_REBAR_CTRL_BAR_IDX; - if (ep->epf_bar[bar]) - pci_epc_bar_size_to_rebar_cap(ep->epf_bar[bar]->size, &val); + val = dw_pcie_ep_readl_dbi(ep, func_no, offset + PCI_REBAR_CTRL); + bar = FIELD_GET(PCI_REBAR_CTRL_BAR_IDX, val); + if (ep_func->epf_bar[bar]) + pci_epc_bar_size_to_rebar_cap(ep_func->epf_bar[bar]->size, &val); else val = BIT(4); - dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, val); + dw_pcie_ep_writel_dbi(ep, func_no, offset + PCI_REBAR_CAP, val); } } +} + +static void dw_pcie_ep_init_non_sticky_registers(struct dw_pcie *pci) +{ + struct dw_pcie_ep *ep = &pci->ep; + u8 funcs = ep->epc->max_functions; + u8 func_no; + + dw_pcie_dbi_ro_wr_en(pci); + + for (func_no = 0; func_no < funcs; func_no++) + dw_pcie_ep_init_rebar_registers(ep, func_no); dw_pcie_setup(pci); dw_pcie_dbi_ro_wr_dis(pci); @@ -993,6 +1196,18 @@ int dw_pcie_ep_init_registers(struct dw_pcie_ep *ep) if (ep->ops->init) ep->ops->init(ep); + /* + * PCIe r6.0, section 7.9.15 states that for endpoints that support + * PTM, this capability structure is required in exactly one + * function, which controls the PTM behavior of all PTM capable + * functions. This indicates the PTM capability structure + * represents controller-level registers rather than per-function + * registers. + * + * Therefore, PTM capability registers are configured using the + * standard DBI accessors, instead of func_no indexed per-function + * accessors. + */ ptm_cap_base = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_PTM); /* @@ -1013,7 +1228,7 @@ int dw_pcie_ep_init_registers(struct dw_pcie_ep *ep) dw_pcie_ep_init_non_sticky_registers(pci); - dwc_pcie_debugfs_init(pci); + dwc_pcie_debugfs_init(pci, DW_PCIE_EP_TYPE); return 0; @@ -1113,6 +1328,9 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep) struct device *dev = pci->dev; INIT_LIST_HEAD(&ep->func_list); + ep->msi_iatu_mapped = false; + ep->msi_msg_addr = 0; + ep->msi_map_size = 0; epc = devm_pci_epc_create(dev, &epc_ops); if (IS_ERR(epc)) { diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c index ecc33f6789e3..6ae6189e9b8a 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> @@ -21,69 +23,65 @@ #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); -} +#ifdef CONFIG_SMP +static void dw_irq_noop(struct irq_data *d) { } +#endif -static void dw_msi_mask_irq(struct irq_data *d) +static bool dw_pcie_init_dev_msi_info(struct device *dev, struct irq_domain *domain, + struct irq_domain *real_parent, struct msi_domain_info *info) { - pci_msi_mask_irq(d); - irq_chip_mask_parent(d); + if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info)) + return false; + +#ifdef CONFIG_SMP + info->chip->irq_ack = dw_irq_noop; + info->chip->irq_pre_redirect = irq_chip_pre_redirect_parent; +#else + info->chip->irq_ack = irq_chip_ack_parent; +#endif + return true; } -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_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, + .prefix = "DW-", + .init_dev_msi_info = dw_pcie_init_dev_msi_info, }; /* MSI int handler */ -irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp) +void dw_handle_msi_irq(struct dw_pcie_rp *pp) { - int i, pos; - unsigned long val; - u32 status, num_ctrls; - irqreturn_t ret = IRQ_NONE; struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + unsigned int i, num_ctrls; num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL; for (i = 0; i < num_ctrls; i++) { - status = dw_pcie_readl_dbi(pci, PCIE_MSI_INTR0_STATUS + - (i * MSI_REG_CTRL_BLOCK_SIZE)); + unsigned int reg_off = i * MSI_REG_CTRL_BLOCK_SIZE; + unsigned int irq_off = i * MAX_MSI_IRQS_PER_CTRL; + unsigned long status, pos; + + status = dw_pcie_readl_dbi(pci, PCIE_MSI_INTR0_STATUS + reg_off); if (!status) continue; - ret = IRQ_HANDLED; - val = status; - pos = 0; - while ((pos = find_next_bit(&val, MAX_MSI_IRQS_PER_CTRL, - pos)) != MAX_MSI_IRQS_PER_CTRL) { - generic_handle_domain_irq(pp->irq_domain, - (i * MAX_MSI_IRQS_PER_CTRL) + - pos); - pos++; - } + for_each_set_bit(pos, &status, MAX_MSI_IRQS_PER_CTRL) + generic_handle_demux_domain_irq(pp->irq_domain, irq_off + pos); } - - return ret; } /* Chained MSI interrupt service routine */ @@ -104,13 +102,10 @@ static void dw_pci_setup_msi_msg(struct irq_data *d, struct msi_msg *msg) { struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); struct dw_pcie *pci = to_dw_pcie_from_pp(pp); - u64 msi_target; - - msi_target = (u64)pp->msi_data; + u64 msi_target = (u64)pp->msi_data; msg->address_lo = lower_32_bits(msi_target); msg->address_hi = upper_32_bits(msi_target); - msg->data = d->hwirq; dev_dbg(pci->dev, "msi#%d address_hi %#x address_lo %#x\n", @@ -122,18 +117,14 @@ static void dw_pci_bottom_mask(struct irq_data *d) struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); struct dw_pcie *pci = to_dw_pcie_from_pp(pp); unsigned int res, bit, ctrl; - unsigned long flags; - - raw_spin_lock_irqsave(&pp->lock, flags); + guard(raw_spinlock)(&pp->lock); ctrl = d->hwirq / MAX_MSI_IRQS_PER_CTRL; res = ctrl * MSI_REG_CTRL_BLOCK_SIZE; bit = d->hwirq % MAX_MSI_IRQS_PER_CTRL; pp->irq_mask[ctrl] |= BIT(bit); dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_MASK + res, pp->irq_mask[ctrl]); - - raw_spin_unlock_irqrestore(&pp->lock, flags); } static void dw_pci_bottom_unmask(struct irq_data *d) @@ -141,18 +132,14 @@ static void dw_pci_bottom_unmask(struct irq_data *d) struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d); struct dw_pcie *pci = to_dw_pcie_from_pp(pp); unsigned int res, bit, ctrl; - unsigned long flags; - - raw_spin_lock_irqsave(&pp->lock, flags); + guard(raw_spinlock)(&pp->lock); ctrl = d->hwirq / MAX_MSI_IRQS_PER_CTRL; res = ctrl * MSI_REG_CTRL_BLOCK_SIZE; bit = d->hwirq % MAX_MSI_IRQS_PER_CTRL; pp->irq_mask[ctrl] &= ~BIT(bit); dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_MASK + res, pp->irq_mask[ctrl]); - - raw_spin_unlock_irqrestore(&pp->lock, flags); } static void dw_pci_bottom_ack(struct irq_data *d) @@ -169,54 +156,48 @@ static void dw_pci_bottom_ack(struct irq_data *d) } static struct irq_chip dw_pci_msi_bottom_irq_chip = { - .name = "DWPCI-MSI", - .irq_ack = dw_pci_bottom_ack, - .irq_compose_msi_msg = dw_pci_setup_msi_msg, - .irq_mask = dw_pci_bottom_mask, - .irq_unmask = dw_pci_bottom_unmask, + .name = "DWPCI-MSI", + .irq_compose_msi_msg = dw_pci_setup_msi_msg, + .irq_mask = dw_pci_bottom_mask, + .irq_unmask = dw_pci_bottom_unmask, +#ifdef CONFIG_SMP + .irq_ack = dw_irq_noop, + .irq_pre_redirect = dw_pci_bottom_ack, + .irq_set_affinity = irq_chip_redirect_set_affinity, +#else + .irq_ack = dw_pci_bottom_ack, +#endif }; -static int dw_pcie_irq_domain_alloc(struct irq_domain *domain, - unsigned int virq, unsigned int nr_irqs, - void *args) +static int dw_pcie_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs, void *args) { struct dw_pcie_rp *pp = domain->host_data; - unsigned long flags; - u32 i; int bit; - raw_spin_lock_irqsave(&pp->lock, flags); - - bit = bitmap_find_free_region(pp->msi_irq_in_use, pp->num_vectors, - order_base_2(nr_irqs)); - - raw_spin_unlock_irqrestore(&pp->lock, flags); + scoped_guard (raw_spinlock_irq, &pp->lock) { + bit = bitmap_find_free_region(pp->msi_irq_in_use, pp->num_vectors, + order_base_2(nr_irqs)); + } if (bit < 0) return -ENOSPC; - for (i = 0; i < nr_irqs; i++) - irq_domain_set_info(domain, virq + i, bit + i, - pp->msi_irq_chip, - pp, handle_edge_irq, - NULL, NULL); - + for (unsigned int i = 0; i < nr_irqs; i++) { + irq_domain_set_info(domain, virq + i, bit + i, pp->msi_irq_chip, + pp, handle_edge_irq, NULL, NULL); + } return 0; } -static void dw_pcie_irq_domain_free(struct irq_domain *domain, - unsigned int virq, unsigned int nr_irqs) +static void dw_pcie_irq_domain_free(struct irq_domain *domain, unsigned int virq, + unsigned int nr_irqs) { struct irq_data *d = irq_domain_get_irq_data(domain, virq); struct dw_pcie_rp *pp = domain->host_data; - unsigned long flags; - - raw_spin_lock_irqsave(&pp->lock, flags); - - bitmap_release_region(pp->msi_irq_in_use, d->hwirq, - order_base_2(nr_irqs)); - raw_spin_unlock_irqrestore(&pp->lock, flags); + guard(raw_spinlock_irq)(&pp->lock); + bitmap_release_region(pp->msi_irq_in_use, d->hwirq, order_base_2(nr_irqs)); } static const struct irq_domain_ops dw_pcie_msi_domain_ops = { @@ -227,55 +208,62 @@ 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; for (ctrl = 0; ctrl < MAX_MSI_CTRLS; ctrl++) { if (pp->msi_irq[ctrl] > 0) - irq_set_chained_handler_and_data(pp->msi_irq[ctrl], - NULL, NULL); + irq_set_chained_handler_and_data(pp->msi_irq[ctrl], 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) + if (!pci_msi_enabled() || !pp->use_imsi_rx) 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 +305,7 @@ 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; @@ -368,10 +356,20 @@ static int dw_pcie_msi_host_init(struct dw_pcie_rp *pp) * order not to miss MSI TLPs from those devices the MSI target * address has to be within the lowest 4GB. * - * Note until there is a better alternative found the reservation is - * done by allocating from the artificially limited DMA-coherent - * memory. + * Per DWC databook r6.21a, section 3.10.2.3, the incoming MWr TLP + * targeting the MSI_CTRL_ADDR is terminated by the iMSI-RX and never + * appears on the AXI bus. So MSI_CTRL_ADDR address doesn't need to be + * mapped and can be any memory that doesn't get allocated for the BAR + * memory. Since most of the platforms provide 32-bit address for + * 'config' region, try cfg0_base as the first option for the MSI target + * address if it's a 32-bit address. Otherwise, try 32-bit and 64-bit + * coherent memory allocation one by one. */ + if (!(pp->cfg0_base & GENMASK_ULL(63, 32))) { + pp->msi_data = pp->cfg0_base; + return 0; + } + ret = dma_set_coherent_mask(dev, DMA_BIT_MASK(32)); if (!ret) msi_vaddr = dmam_alloc_coherent(dev, sizeof(u64), &pp->msi_data, @@ -391,6 +389,7 @@ 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) { @@ -418,6 +417,92 @@ static void dw_pcie_host_request_msg_tlp_res(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); @@ -427,10 +512,6 @@ static int dw_pcie_host_get_resources(struct dw_pcie_rp *pp) struct resource *res; int ret; - ret = dw_pcie_get_resources(pci); - if (ret) - return ret; - res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config"); if (!res) { dev_err(dev, "Missing \"config\" reg space\n"); @@ -440,9 +521,32 @@ static int dw_pcie_host_get_resources(struct dw_pcie_rp *pp) pp->cfg0_size = resource_size(res); pp->cfg0_base = res->start; - pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, res); - if (IS_ERR(pp->va_cfg0_base)) - return PTR_ERR(pp->va_cfg0_base); + 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); + + /* Set default bus ops */ + pp->bridge->ops = &dw_pcie_ops; + pp->bridge->child_ops = &dw_child_pcie_ops; + pp->bridge->sysdata = pp; + } + + 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(&pp->bridge->windows, IORESOURCE_IO); @@ -481,26 +585,22 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp) if (ret) return ret; - /* Set default bus ops */ - bridge->ops = &dw_pcie_ops; - bridge->child_ops = &dw_child_pcie_ops; - 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 || + pp->use_imsi_rx = !(pp->ops->msi_init || of_property_present(np, "msi-parent") || of_property_present(np, "msi-map")); /* - * For the has_msi_ctrl case the default assignment is handled + * For the use_imsi_rx case the default assignment is handled * in the dw_pcie_msi_host_init(). */ - if (!pp->has_msi_ctrl && !pp->num_vectors) { + if (!pp->use_imsi_rx && !pp->num_vectors) { pp->num_vectors = MSI_DEF_NUM_VECTORS; } else if (pp->num_vectors > MAX_MSI_IRQS) { dev_err(dev, "Invalid number of vectors\n"); @@ -512,7 +612,7 @@ int dw_pcie_host_init(struct dw_pcie_rp *pp) ret = pp->ops->msi_init(pp); if (ret < 0) goto err_deinit_host; - } else if (pp->has_msi_ctrl) { + } else if (pp->use_imsi_rx) { ret = dw_pcie_msi_host_init(pp); if (ret < 0) goto err_deinit_host; @@ -523,6 +623,13 @@ 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; + /* * Allocate the resource for MSG TLP before programming the iATU * outbound window in dw_pcie_setup_rc(). Since the allocation depends @@ -550,15 +657,12 @@ int dw_pcie_host_init(struct dw_pcie_rp *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. + * Only fail on timeout error. Other errors indicate the device may + * become available later, so continue without failing. */ - if (!pp->use_linkup_irq) - /* Ignore errors, the link may come up later */ - dw_pcie_wait_for_link(pci); - - bridge->sysdata = pp; + ret = dw_pcie_wait_for_link(pci); + if (ret == -ETIMEDOUT) + goto err_stop_link; ret = pci_host_probe(bridge); if (ret) @@ -567,7 +671,7 @@ 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); + dwc_pcie_debugfs_init(pci, DW_PCIE_RC_TYPE); return 0; @@ -578,13 +682,17 @@ err_remove_edma: dw_pcie_edma_remove(pci); err_free_msi: - if (pp->has_msi_ctrl) + if (pp->use_imsi_rx) dw_pcie_free_msi(pp); 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); @@ -602,11 +710,14 @@ void dw_pcie_host_deinit(struct dw_pcie_rp *pp) dw_pcie_edma_remove(pci); - if (pp->has_msi_ctrl) + if (pp->use_imsi_rx) dw_pcie_free_msi(pp); if (pp->ops->deinit) pp->ops->deinit(pp); + + if (pp->cfg) + pci_ecam_free(pp->cfg); } EXPORT_SYMBOL_GPL(dw_pcie_host_deinit); @@ -720,20 +831,43 @@ 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 struct pci_ops dw_pcie_ops = { .map_bus = dw_pcie_own_conf_map_bus, .read = pci_generic_config_read, .write = pci_generic_config_write, }; +static 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) { struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct dw_pcie_ob_atu_cfg atu = { 0 }; struct resource_entry *entry; + int ob_iatu_index; + int ib_iatu_index; int i, ret; - /* Note the very first outbound ATU is used for CFG IOs */ if (!pci->num_ob_windows) { dev_err(pci->dev, "No outbound iATU found\n"); return -EINVAL; @@ -749,37 +883,74 @@ static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp) for (i = 0; i < pci->num_ib_windows; i++) dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_IB, i); - i = 0; + /* + * NOTE: For outbound address translation, outbound iATU at index 0 is + * reserved for CFG IOs (dw_pcie_other_conf_map_bus()), thus start at + * index 1. + * + * If using ECAM, outbound iATU at index 0 and index 1 is reserved for + * CFG IOs. + */ + if (pp->ecam_enabled) { + ob_iatu_index = 2; + ret = dw_pcie_config_ecam_iatu(pp); + if (ret) { + dev_err(pci->dev, "Failed to configure iATU in ECAM mode\n"); + return ret; + } + } else { + ob_iatu_index = 1; + } + resource_list_for_each_entry(entry, &pp->bridge->windows) { + resource_size_t res_size; + if (resource_type(entry->res) != IORESOURCE_MEM) continue; - if (pci->num_ob_windows <= ++i) - break; - - atu.index = i; atu.type = PCIE_ATU_TYPE_MEM; 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 */ if (pp->msg_res && pp->msg_res->parent == entry->res) - atu.size = resource_size(entry->res) - + res_size = resource_size(entry->res) - resource_size(pp->msg_res); else - atu.size = resource_size(entry->res); + res_size = resource_size(entry->res); + + while (res_size > 0) { + /* + * Return failure if we run out of windows in the + * middle. Otherwise, we would end up only partially + * mapping a single resource. + */ + if (ob_iatu_index >= pci->num_ob_windows) { + dev_err(pci->dev, "Cannot add outbound window for region: %pr\n", + entry->res); + return -ENOMEM; + } - ret = dw_pcie_prog_outbound_atu(pci, &atu); - if (ret) { - dev_err(pci->dev, "Failed to set MEM range %pr\n", - entry->res); - return ret; + atu.index = ob_iatu_index; + atu.size = MIN(pci->region_limit + 1, res_size); + + ret = dw_pcie_prog_outbound_atu(pci, &atu); + if (ret) { + dev_err(pci->dev, "Failed to set MEM range %pr\n", + entry->res); + return ret; + } + + ob_iatu_index++; + atu.parent_bus_addr += atu.size; + atu.pci_addr += atu.size; + res_size -= atu.size; } } if (pp->io_size) { - if (pci->num_ob_windows > ++i) { - atu.index = i; + if (ob_iatu_index < pci->num_ob_windows) { + atu.index = ob_iatu_index; atu.type = PCIE_ATU_TYPE_IO; atu.parent_bus_addr = pp->io_base - pci->parent_bus_offset; atu.pci_addr = pp->io_bus_addr; @@ -791,47 +962,149 @@ static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp) entry->res); return ret; } + ob_iatu_index++; } else { + /* + * If there are not enough outbound windows to give I/O + * space its own iATU, the outbound iATU at index 0 will + * be shared between I/O space and CFG IOs, by + * temporarily reconfiguring the iATU to CFG space, in + * order to do a CFG IO, and then immediately restoring + * it to I/O space. This is only implemented when using + * dw_pcie_other_conf_map_bus(), which is not the case + * when using ECAM. + */ + if (pp->ecam_enabled) { + dev_err(pci->dev, "Cannot add outbound window for I/O\n"); + return -ENOMEM; + } pp->cfg0_io_shared = true; } } - if (pci->num_ob_windows <= i) - dev_warn(pci->dev, "Ranges exceed outbound iATU size (%d)\n", - pci->num_ob_windows); - - pp->msg_atu_index = i; + if (pp->use_atu_msg) { + if (ob_iatu_index >= pci->num_ob_windows) { + dev_err(pci->dev, "Cannot add outbound window for MSG TLP\n"); + return -ENOMEM; + } + pp->msg_atu_index = ob_iatu_index++; + } - i = 0; + ib_iatu_index = 0; resource_list_for_each_entry(entry, &pp->bridge->dma_ranges) { + resource_size_t res_start, res_size, window_size; + if (resource_type(entry->res) != IORESOURCE_MEM) continue; - if (pci->num_ib_windows <= i) - break; + res_size = resource_size(entry->res); + res_start = entry->res->start; + while (res_size > 0) { + /* + * Return failure if we run out of windows in the + * middle. Otherwise, we would end up only partially + * mapping a single resource. + */ + if (ib_iatu_index >= pci->num_ib_windows) { + dev_err(pci->dev, "Cannot add inbound window for region: %pr\n", + entry->res); + return -ENOMEM; + } - ret = dw_pcie_prog_inbound_atu(pci, i++, PCIE_ATU_TYPE_MEM, - entry->res->start, - entry->res->start - entry->offset, - resource_size(entry->res)); - if (ret) { - dev_err(pci->dev, "Failed to set DMA range %pr\n", - entry->res); - return ret; + window_size = MIN(pci->region_limit + 1, res_size); + ret = dw_pcie_prog_inbound_atu(pci, ib_iatu_index, + PCIE_ATU_TYPE_MEM, res_start, + res_start - entry->offset, window_size); + if (ret) { + dev_err(pci->dev, "Failed to set DMA range %pr\n", + entry->res); + return ret; + } + + ib_iatu_index++; + res_start += window_size; + res_size -= window_size; } } - if (pci->num_ib_windows <= i) - dev_warn(pci->dev, "Dma-ranges exceed inbound iATU size (%u)\n", - pci->num_ib_windows); - 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; /* @@ -842,20 +1115,6 @@ 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 */ @@ -881,12 +1140,15 @@ 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 * ATU, so we should not program the ATU here. */ - if (pp->bridge->child_ops == &dw_child_pcie_ops) { + if (pp->bridge->child_ops == &dw_child_pcie_ops || pp->ecam_enabled) { ret = dw_pcie_iatu_setup(pp); if (ret) return ret; @@ -903,6 +1165,17 @@ int dw_pcie_setup_rc(struct dw_pcie_rp *pp) dw_pcie_dbi_ro_wr_dis(pci); + /* + * The iMSI-RX module does not support receiving MSI or MSI-X generated + * by the Root Port. If iMSI-RX is used as the MSI controller, remove + * the MSI and MSI-X capabilities of the Root Port to allow the drivers + * to fall back to INTx instead. + */ + if (pp->use_imsi_rx) { + dw_pcie_remove_capability(pci, PCI_CAP_ID_MSI); + dw_pcie_remove_capability(pci, PCI_CAP_ID_MSIX); + } + return 0; } EXPORT_SYMBOL_GPL(dw_pcie_setup_rc); @@ -946,8 +1219,11 @@ static int dw_pcie_pme_turn_off(struct dw_pcie *pci) int dw_pcie_suspend_noirq(struct dw_pcie *pci) { u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + int ret = 0; u32 val; - int ret; + + if (!dw_pcie_link_up(pci)) + goto stop_link; /* * If L1SS is supported, then do not put the link into L2 as some @@ -964,6 +1240,16 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci) return ret; } + /* + * Some SoCs do not support reading the LTSSM register after + * PME_Turn_Off broadcast. For those SoCs, skip waiting for L2/L3 Ready + * state and wait 10ms as recommended in PCIe spec r6.0, sec 5.3.3.2.1. + */ + if (pci->pp.skip_l23_ready) { + mdelay(PCIE_PME_TO_L2_TIMEOUT_US/1000); + goto stop_link; + } + ret = read_poll_timeout(dw_pcie_get_ltssm, val, val == DW_PCIE_LTSSM_L2_IDLE || val <= DW_PCIE_LTSSM_DETECT_WAIT, @@ -982,6 +1268,7 @@ int dw_pcie_suspend_noirq(struct dw_pcie *pci) */ udelay(1); +stop_link: dw_pcie_stop_link(pci); if (pci->pp.ops->deinit) pci->pp.ops->deinit(&pci->pp); @@ -1019,6 +1306,9 @@ int dw_pcie_resume_noirq(struct dw_pcie *pci) if (ret) return ret; + if (pci->pp.ops->post_init) + pci->pp.ops->post_init(&pci->pp); + return ret; } EXPORT_SYMBOL_GPL(dw_pcie_resume_noirq); diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c index 771b9d9be077..8530746ec5cb 100644 --- a/drivers/pci/controller/dwc/pcie-designware-plat.c +++ b/drivers/pci/controller/dwc/pcie-designware-plat.c @@ -61,7 +61,7 @@ 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, + DWC_EPC_COMMON_FEATURES, .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 97d76d3dc066..5741c09dde7f 100644 --- a/drivers/pci/controller/dwc/pcie-designware.c +++ b/drivers/pci/controller/dwc/pcie-designware.c @@ -54,6 +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; @@ -159,6 +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); @@ -205,85 +223,72 @@ 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; + return PCI_FIND_NEXT_CAP(dw_pcie_read_cfg, PCI_CAPABILITY_LIST, cap, + NULL, pci); +} +EXPORT_SYMBOL_GPL(dw_pcie_find_capability); - next_cap_ptr = (reg & 0xff00) >> 8; - return __dw_pcie_find_next_cap(pci, next_cap_ptr, cap); +u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap) +{ + return PCI_FIND_NEXT_EXT_CAP(dw_pcie_read_cfg, 0, cap, NULL, pci); } +EXPORT_SYMBOL_GPL(dw_pcie_find_ext_capability); -u8 dw_pcie_find_capability(struct dw_pcie *pci, u8 cap) +void dw_pcie_remove_capability(struct dw_pcie *pci, u8 cap) { - u8 next_cap_ptr; + u8 cap_pos, pre_pos, next_pos; u16 reg; - reg = dw_pcie_readw_dbi(pci, PCI_CAPABILITY_LIST); - next_cap_ptr = (reg & 0x00ff); + cap_pos = PCI_FIND_NEXT_CAP(dw_pcie_read_cfg, PCI_CAPABILITY_LIST, cap, + &pre_pos, pci); + if (!cap_pos) + return; - return __dw_pcie_find_next_cap(pci, next_cap_ptr, cap); + reg = dw_pcie_readw_dbi(pci, cap_pos); + next_pos = (reg & 0xff00) >> 8; + + dw_pcie_dbi_ro_wr_en(pci); + if (pre_pos == PCI_CAPABILITY_LIST) + dw_pcie_writeb_dbi(pci, PCI_CAPABILITY_LIST, next_pos); + else + dw_pcie_writeb_dbi(pci, pre_pos + 1, next_pos); + dw_pcie_dbi_ro_wr_dis(pci); } -EXPORT_SYMBOL_GPL(dw_pcie_find_capability); +EXPORT_SYMBOL_GPL(dw_pcie_remove_capability); -static u16 dw_pcie_find_next_ext_capability(struct dw_pcie *pci, u16 start, - u8 cap) +void dw_pcie_remove_ext_capability(struct dw_pcie *pci, u8 cap) { - u32 header; - int ttl; - int pos = PCI_CFG_SPACE_SIZE; + int cap_pos, next_pos, pre_pos; + u32 pre_header, header; - /* minimum 8 bytes per capability */ - ttl = (PCI_CFG_SPACE_EXP_SIZE - PCI_CFG_SPACE_SIZE) / 8; + cap_pos = PCI_FIND_NEXT_EXT_CAP(dw_pcie_read_cfg, 0, cap, &pre_pos, pci); + if (!cap_pos) + return; - if (start) - pos = start; + header = dw_pcie_readl_dbi(pci, cap_pos); - 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 the first cap at offset PCI_CFG_SPACE_SIZE is removed, + * only set its capid to zero as it cannot be skipped. */ - if (header == 0) - return 0; - - while (ttl-- > 0) { - if (PCI_EXT_CAP_ID(header) == cap && pos != start) - return pos; - - pos = PCI_EXT_CAP_NEXT(header); - if (pos < PCI_CFG_SPACE_SIZE) - break; - - header = dw_pcie_readl_dbi(pci, pos); + if (cap_pos == PCI_CFG_SPACE_SIZE) { + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writel_dbi(pci, cap_pos, header & 0xffff0000); + dw_pcie_dbi_ro_wr_dis(pci); + return; } - return 0; -} + pre_header = dw_pcie_readl_dbi(pci, pre_pos); + next_pos = PCI_EXT_CAP_NEXT(header); -u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap) -{ - return dw_pcie_find_next_ext_capability(pci, 0, cap); + dw_pcie_dbi_ro_wr_en(pci); + dw_pcie_writel_dbi(pci, pre_pos, + (pre_header & 0xfffff) | (next_pos << 20)); + dw_pcie_dbi_ro_wr_dis(pci); } -EXPORT_SYMBOL_GPL(dw_pcie_find_ext_capability); +EXPORT_SYMBOL_GPL(dw_pcie_remove_ext_capability); static u16 __dw_pcie_find_vsec_capability(struct dw_pcie *pci, u16 vendor_id, u16 vsec_id) @@ -294,8 +299,8 @@ static u16 __dw_pcie_find_vsec_capability(struct dw_pcie *pci, u16 vendor_id, if (vendor_id != dw_pcie_readw_dbi(pci, PCI_VENDOR_ID)) return 0; - while ((vsec = dw_pcie_find_next_ext_capability(pci, vsec, - PCI_EXT_CAP_ID_VNDR))) { + while ((vsec = PCI_FIND_NEXT_EXT_CAP(dw_pcie_read_cfg, vsec, + PCI_EXT_CAP_ID_VNDR, NULL, pci))) { header = dw_pcie_readl_dbi(pci, vsec + PCI_VNDR_HEADER); if (PCI_VNDR_HEADER_ID(header) == vsec_id) return vsec; @@ -330,6 +335,12 @@ u16 dw_pcie_find_rasdes_capability(struct dw_pcie *pci) } 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) { if (!IS_ALIGNED((uintptr_t)addr, size)) { @@ -521,6 +532,9 @@ int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, u32 retries, val; u64 limit_addr; + if (atu->index >= pci->num_ob_windows) + return -ENOSPC; + limit_addr = parent_bus_addr + atu->size - 1; if ((limit_addr & ~pci->region_limit) != (parent_bus_addr & ~pci->region_limit) || @@ -553,7 +567,7 @@ int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, 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; @@ -594,6 +608,9 @@ int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, int index, int type, u64 limit_addr = pci_addr + size - 1; u32 retries, val; + if (index >= pci->num_ib_windows) + return -ENOSPC; + if ((limit_addr & ~pci->region_limit) != (pci_addr & ~pci->region_limit) || !IS_ALIGNED(parent_bus_addr, pci->region_align) || !IS_ALIGNED(pci_addr, pci->region_align) || !size) { @@ -682,24 +699,114 @@ void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index) dw_pcie_writel_atu(pci, dir, index, PCIE_ATU_REGION_CTRL2, 0); } +const char *dw_pcie_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); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L1_1); + DW_PCIE_LTSSM_NAME(DW_PCIE_LTSSM_L1_2); + default: + str = "DW_PCIE_LTSSM_UNKNOWN"; + break; + } + + return str + strlen("DW_PCIE_LTSSM_"); +} + +/** + * dw_pcie_wait_for_link - Wait for the PCIe link to be up + * @pci: DWC instance + * + * Returns: 0 if link is up, -ENODEV if device is not found, -EIO if the device + * is found but not active and -ETIMEDOUT if the link fails to come up for other + * reasons. + */ int dw_pcie_wait_for_link(struct dw_pcie *pci) { - u32 offset, val; + u32 offset, val, ltssm; 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) { - dev_info(pci->dev, "Phy link never came up\n"); + if (retries >= PCIE_LINK_WAIT_MAX_RETRIES) { + /* + * If the link is in Detect.Quiet or Detect.Active state, it + * indicates that no device is detected. + */ + ltssm = dw_pcie_get_ltssm(pci); + if (ltssm == DW_PCIE_LTSSM_DETECT_QUIET || + ltssm == DW_PCIE_LTSSM_DETECT_ACT) { + dev_info(pci->dev, "Device not found\n"); + return -ENODEV; + + /* + * If the link is in POLL.{Active/Compliance} state, then the + * device is found to be connected to the bus, but it is not + * active i.e., the device firmware might not yet initialized. + */ + } else if (ltssm == DW_PCIE_LTSSM_POLL_ACTIVE || + ltssm == DW_PCIE_LTSSM_POLL_COMPLIANCE) { + dev_info(pci->dev, "Device found, but not active\n"); + return -EIO; + } + + dev_err(pci->dev, "Link failed to come up. LTSSM: %s\n", + dw_pcie_ltssm_status_string(ltssm)); 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); @@ -711,7 +818,7 @@ 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; @@ -781,6 +888,14 @@ 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; @@ -797,22 +912,22 @@ 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); @@ -1018,9 +1133,7 @@ static int dw_pcie_edma_irq_verify(struct dw_pcie *pci) 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"); @@ -1112,6 +1225,30 @@ 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; diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h index 56aafdbcdaca..ae6389dd9caa 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 @@ -282,6 +305,10 @@ /* Default eDMA LLP memory size */ #define DMA_LLP_MEM_SIZE PAGE_SIZE +/* Common struct pci_epc_feature bits among DWC EP glue drivers */ +#define DWC_EPC_COMMON_FEATURES .dynamic_inbound_mapping = true, \ + .subrange_mapping = true + struct dw_pcie; struct dw_pcie_rp; struct dw_pcie_ep; @@ -365,6 +392,10 @@ enum dw_pcie_ltssm { DW_PCIE_LTSSM_RCVRY_EQ2 = 0x22, DW_PCIE_LTSSM_RCVRY_EQ3 = 0x23, + /* Vendor glue drivers provide pseudo L1 substates from get_ltssm() */ + DW_PCIE_LTSSM_L1_1 = 0x141, + DW_PCIE_LTSSM_L1_2 = 0x142, + DW_PCIE_LTSSM_UNKNOWN = 0xFFFFFFFF, }; @@ -374,6 +405,7 @@ struct dw_pcie_ob_atu_cfg { u8 func_no; u8 code; u8 routing; + u32 ctrl2; u64 parent_bus_addr; u64 pci_addr; u64 size; @@ -388,7 +420,7 @@ struct dw_pcie_host_ops { }; struct dw_pcie_rp { - bool has_msi_ctrl:1; + bool use_imsi_rx:1; bool cfg0_io_shared:1; u64 cfg0_base; void __iomem *va_cfg0_base; @@ -400,7 +432,6 @@ 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; @@ -411,7 +442,11 @@ 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; + bool skip_l23_ready; }; struct dw_pcie_ep_ops { @@ -436,6 +471,12 @@ struct dw_pcie_ep_func { u8 func_no; u8 msi_cap; /* MSI capability offset */ u8 msix_cap; /* MSI-X capability offset */ + u8 bar_to_atu[PCI_STD_NUM_BARS]; + struct pci_epf_bar *epf_bar[PCI_STD_NUM_BARS]; + + /* Only for Address Match Mode inbound iATU */ + u32 *ib_atu_indexes[PCI_STD_NUM_BARS]; + unsigned int num_ib_atu_indexes[PCI_STD_NUM_BARS]; }; struct dw_pcie_ep { @@ -445,13 +486,16 @@ struct dw_pcie_ep { phys_addr_t phys_base; size_t addr_size; size_t page_size; - u8 bar_to_atu[PCI_STD_NUM_BARS]; phys_addr_t *outbound_addr; unsigned long *ib_window_map; unsigned long *ob_window_map; void __iomem *msi_mem; phys_addr_t msi_mem_phys; - struct pci_epf_bar *epf_bar[PCI_STD_NUM_BARS]; + + /* MSI outbound iATU state */ + bool msi_iatu_mapped; + u64 msi_msg_addr; + size_t msi_map_size; }; struct dw_pcie_ops { @@ -462,7 +506,7 @@ 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); @@ -479,6 +523,7 @@ 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; @@ -496,6 +541,7 @@ 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]; @@ -503,6 +549,9 @@ struct dw_pcie { 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, @@ -529,7 +578,10 @@ 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); +void dw_pcie_remove_capability(struct dw_pcie *pci, u8 cap); +void dw_pcie_remove_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); @@ -537,9 +589,10 @@ 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, @@ -548,6 +601,7 @@ int dw_pcie_prog_ep_inbound_atu(struct dw_pcie *pci, u8 func_no, int index, 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); @@ -591,6 +645,27 @@ 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) { @@ -656,6 +731,27 @@ 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) { @@ -732,10 +828,15 @@ static inline enum dw_pcie_ltssm dw_pcie_get_ltssm(struct dw_pcie *pci) return (enum dw_pcie_ltssm)FIELD_GET(PORT_LOGIC_LTSSM_STATE_MASK, val); } +const char *dw_pcie_ltssm_status_string(enum dw_pcie_ltssm ltssm); + #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_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); @@ -753,11 +854,19 @@ 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) +static inline void dw_handle_msi_irq(struct dw_pcie_rp *pp) { } + +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 IRQ_NONE; + 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; @@ -799,7 +908,6 @@ 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 @@ -857,12 +965,6 @@ 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) { @@ -871,10 +973,11 @@ dw_pcie_ep_get_func_from_ep(struct dw_pcie_ep *ep, u8 func_no) #endif #ifdef CONFIG_PCIE_DW_DEBUGFS -void dwc_pcie_debugfs_init(struct dw_pcie *pci); +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) +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) diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c index c624b7ebd118..5b17da63151d 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 +23,69 @@ #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) + +/* RASDES TBA information */ +#define PCIE_CLIENT_CDM_RASDES_TBA_INFO_CMN 0x154 +#define PCIE_CLIENT_CDM_RASDES_TBA_L1_1 BIT(4) +#define PCIE_CLIENT_CDM_RASDES_TBA_L1_2 BIT(5) + +/* 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) + +#define PCIE_TYPE0_HDR_DBI2_OFFSET 0x100000 struct rockchip_pcie { struct dw_pcie pci; @@ -62,9 +95,9 @@ 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 +135,14 @@ 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 +177,8 @@ 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"); @@ -155,33 +188,88 @@ static int rockchip_pcie_init_irq_domain(struct rockchip_pcie *rockchip) return 0; } -static u32 rockchip_pcie_get_ltssm(struct rockchip_pcie *rockchip) +static u32 rockchip_pcie_get_ltssm_reg(struct rockchip_pcie *rockchip) { return rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_LTSSM_STATUS); } +static enum dw_pcie_ltssm rockchip_pcie_get_ltssm(struct dw_pcie *pci) +{ + struct rockchip_pcie *rockchip = to_rockchip_pcie(pci); + u32 val = rockchip_pcie_readl_apb(rockchip, + PCIE_CLIENT_CDM_RASDES_TBA_INFO_CMN); + + if (val & PCIE_CLIENT_CDM_RASDES_TBA_L1_1) + return DW_PCIE_LTSSM_L1_1; + + if (val & PCIE_CLIENT_CDM_RASDES_TBA_L1_2) + return DW_PCIE_LTSSM_L1_2; + + return rockchip_pcie_get_ltssm_reg(rockchip) & PCIE_LTSSM_STATUS_MASK; +} + 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); + u32 val = rockchip_pcie_get_ltssm_reg(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; +} - return 0; +/* + * 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); + + /* 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 +290,7 @@ 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; @@ -226,6 +314,8 @@ static int rockchip_pcie_host_init(struct dw_pcie_rp *pp) if (irq < 0) return irq; + pci->dbi_base2 = pci->dbi_base + PCIE_TYPE0_HDR_DBI2_OFFSET; + ret = rockchip_pcie_init_irq_domain(rockchip); if (ret < 0) dev_err(dev, "failed to init irq domain\n"); @@ -233,6 +323,13 @@ 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); + + /* Disable Root Ports BAR0 and BAR1 as they report bogus size */ + dw_pcie_writel_dbi2(pci, PCI_BASE_ADDRESS_0, 0x0); + dw_pcie_writel_dbi2(pci, PCI_BASE_ADDRESS_1, 0x0); + return 0; } @@ -258,14 +355,7 @@ static void rockchip_pcie_ep_hide_broken_ats_cap_rk3588(struct dw_pcie_ep *ep) 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_pre_init(struct dw_pcie_ep *ep) -{ - rockchip_pcie_ep_hide_broken_ats_cap_rk3588(ep); + dw_pcie_remove_ext_capability(pci, PCI_EXT_CAP_ID_ATS); } static void rockchip_pcie_ep_init(struct dw_pcie_ep *ep) @@ -273,6 +363,9 @@ 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); }; @@ -297,10 +390,10 @@ static int rockchip_pcie_raise_irq(struct dw_pcie_ep *ep, u8 func_no, } static const struct pci_epc_features rockchip_pcie_epc_features_rk3568 = { + DWC_EPC_COMMON_FEATURES, .linkup_notifier = true, .msi_capable = true, .msix_capable = true, - .intx_capable = false, .align = SZ_64K, .bar[BAR_0] = { .type = BAR_RESIZABLE, }, .bar[BAR_1] = { .type = BAR_RESIZABLE, }, @@ -318,10 +411,10 @@ static const struct pci_epc_features rockchip_pcie_epc_features_rk3568 = { * BARs) would be overwritten, resulting in (all other BARs) no longer working. */ static const struct pci_epc_features rockchip_pcie_epc_features_rk3588 = { + DWC_EPC_COMMON_FEATURES, .linkup_notifier = true, .msi_capable = true, .msix_capable = true, - .intx_capable = false, .align = SZ_64K, .bar[BAR_0] = { .type = BAR_RESIZABLE, }, .bar[BAR_1] = { .type = BAR_RESIZABLE, }, @@ -342,7 +435,6 @@ rockchip_pcie_get_features(struct dw_pcie_ep *ep) static const struct dw_pcie_ep_ops rockchip_pcie_ep_ops = { .init = rockchip_pcie_ep_init, - .pre_init = rockchip_pcie_ep_pre_init, .raise_irq = rockchip_pcie_raise_irq, .get_features = rockchip_pcie_get_features, }; @@ -384,6 +476,9 @@ 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; } @@ -410,44 +505,17 @@ 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 = { .link_up = rockchip_pcie_link_up, .start_link = rockchip_pcie_start_link, .stop_link = rockchip_pcie_stop_link, + .get_ltssm = rockchip_pcie_get_ltssm, }; -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, val; - - 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) { - val = rockchip_pcie_get_ltssm(rockchip); - if ((val & PCIE_LINKUP) == PCIE_LINKUP) { - 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; @@ -459,16 +527,19 @@ static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg) 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)); + dev_dbg(dev, "LTSSM_STATUS: %#x\n", rockchip_pcie_get_ltssm_reg(rockchip)); 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); } @@ -477,51 +548,26 @@ static irqreturn_t rockchip_pcie_ep_sys_irq_thread(int irq, void *arg) return IRQ_HANDLED; } -static int rockchip_pcie_configure_rc(struct platform_device *pdev, - struct rockchip_pcie *rockchip) +static int rockchip_pcie_configure_rc(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; - } - - /* unmask DLL up/down indicator */ - val = HIWORD_UPDATE(PCIE_RDLH_LINK_UP_CHGED, 0); - rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_INTR_MASK_MISC); - return ret; + return dw_pcie_host_init(pp); } static int rockchip_pcie_configure_ep(struct platform_device *pdev, @@ -546,12 +592,17 @@ static int rockchip_pcie_configure_ep(struct platform_device *pdev, 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; @@ -574,7 +625,8 @@ 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 */ - val = HIWORD_UPDATE(PCIE_RDLH_LINK_UP_CHGED | PCIE_LINK_REQ_RST_NOT_INT, 0); + 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; @@ -601,6 +653,10 @@ 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; @@ -610,22 +666,15 @@ 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) @@ -637,7 +686,7 @@ static int rockchip_pcie_probe(struct platform_device *pdev) switch (data->mode) { case DW_PCIE_RC_TYPE: - ret = rockchip_pcie_configure_rc(pdev, rockchip); + ret = rockchip_pcie_configure_rc(rockchip); if (ret) goto deinit_clk; break; @@ -658,9 +707,6 @@ 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 1f2f4c28a949..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) diff --git a/drivers/pci/controller/dwc/pcie-keembay.c b/drivers/pci/controller/dwc/pcie-keembay.c index 278205db60a2..2666a9c3d67e 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 +309,7 @@ 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, + DWC_EPC_COMMON_FEATURES, .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 d0e6a3811b00..91559c8b1866 100644 --- a/drivers/pci/controller/dwc/pcie-kirin.c +++ b/drivers/pci/controller/dwc/pcie-kirin.c @@ -586,16 +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) 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..b3ec38099fa3 --- /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) + break; + } + + if (ret) + 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 46b1c6d19974..18460f01b2c6 100644 --- a/drivers/pci/controller/dwc/pcie-qcom-ep.c +++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c @@ -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) @@ -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 @@ -164,18 +168,19 @@ enum qcom_pcie_ep_link_status { * @hdma_support: HDMA support on this SoC * @override_no_snoop: Override NO_SNOOP attribute in TLP to enable cache snooping * @disable_mhi_ram_parity_check: Disable MHI RAM data parity error check + * @firmware_managed: Set if the controller is firmware managed */ struct qcom_pcie_ep_cfg { bool hdma_support; bool override_no_snoop; bool disable_mhi_ram_parity_check; + bool firmware_managed; }; /** * 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 +203,6 @@ 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 +265,11 @@ 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 +293,15 @@ 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) @@ -377,6 +379,14 @@ err_disable_clk: static void qcom_pcie_disable_resources(struct qcom_pcie_ep *pcie_ep) { + struct device *dev = pcie_ep->pci.dev; + + pm_runtime_put(dev); + + /* Skip resource disablement if controller is firmware-managed */ + if (pcie_ep->cfg && pcie_ep->cfg->firmware_managed) + return; + icc_set_bw(pcie_ep->icc_mem, 0, 0); phy_power_off(pcie_ep->phy); phy_exit(pcie_ep->phy); @@ -390,12 +400,24 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci) u32 val, offset; int ret; + ret = pm_runtime_resume_and_get(dev); + if (ret < 0) { + dev_err(dev, "Failed to enable device: %d\n", ret); + return ret; + } + + /* Skip resource enablement if controller is firmware-managed */ + if (pcie_ep->cfg && pcie_ep->cfg->firmware_managed) + goto skip_resources_enable; + ret = qcom_pcie_enable_resources(pcie_ep); if (ret) { dev_err(dev, "Failed to enable resources: %d\n", ret); + pm_runtime_put(dev); return ret; } +skip_resources_enable: /* Perform cleanup that requires refclk */ pci_epc_deinit_notify(pci->ep.epc); dw_pcie_ep_cleanup(&pci->ep); @@ -497,16 +519,20 @@ 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 @@ -575,11 +601,6 @@ 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) { @@ -631,6 +652,17 @@ static int qcom_pcie_ep_get_resources(struct platform_device *pdev, return ret; } + pcie_ep->reset = devm_gpiod_get(dev, "reset", GPIOD_IN); + if (IS_ERR(pcie_ep->reset)) + return PTR_ERR(pcie_ep->reset); + + pcie_ep->wake = devm_gpiod_get_optional(dev, "wake", GPIOD_OUT_LOW); + if (IS_ERR(pcie_ep->wake)) + return PTR_ERR(pcie_ep->wake); + + if (pcie_ep->cfg && pcie_ep->cfg->firmware_managed) + return 0; + pcie_ep->num_clks = devm_clk_bulk_get_all(dev, &pcie_ep->clks); if (pcie_ep->num_clks < 0) { dev_err(dev, "Failed to get clocks\n"); @@ -641,14 +673,6 @@ static int qcom_pcie_ep_get_resources(struct platform_device *pdev, if (IS_ERR(pcie_ep->core_reset)) return PTR_ERR(pcie_ep->core_reset); - pcie_ep->reset = devm_gpiod_get(dev, "reset", GPIOD_IN); - if (IS_ERR(pcie_ep->reset)) - return PTR_ERR(pcie_ep->reset); - - pcie_ep->wake = devm_gpiod_get_optional(dev, "wake", GPIOD_OUT_LOW); - if (IS_ERR(pcie_ep->wake)) - return PTR_ERR(pcie_ep->wake); - pcie_ep->phy = devm_phy_optional_get(dev, "pciephy"); if (IS_ERR(pcie_ep->phy)) ret = PTR_ERR(pcie_ep->phy); @@ -821,9 +845,9 @@ static void qcom_pcie_ep_init_debugfs(struct qcom_pcie_ep *pcie_ep) } static const struct pci_epc_features qcom_pcie_epc_features = { + DWC_EPC_COMMON_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, }, @@ -866,7 +890,6 @@ 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) { @@ -877,6 +900,12 @@ static int qcom_pcie_ep_probe(struct platform_device *pdev) platform_set_drvdata(pdev, pcie_ep); + pm_runtime_get_noresume(dev); + pm_runtime_set_active(dev); + ret = devm_pm_runtime_enable(dev); + if (ret) + return ret; + ret = qcom_pcie_ep_get_resources(pdev, pcie_ep); if (ret) return ret; @@ -897,6 +926,12 @@ static int qcom_pcie_ep_probe(struct platform_device *pdev) goto err_disable_irqs; } + ret = pm_runtime_put_sync(dev); + if (ret < 0) { + dev_err(dev, "Failed to suspend device: %d\n", ret); + goto err_disable_irqs; + } + pcie_ep->debugfs = debugfs_create_dir(name, NULL); qcom_pcie_ep_init_debugfs(pcie_ep); @@ -933,7 +968,15 @@ static const struct qcom_pcie_ep_cfg cfg_1_34_0 = { .disable_mhi_ram_parity_check = true, }; +static const struct qcom_pcie_ep_cfg cfg_1_34_0_fw_managed = { + .hdma_support = true, + .override_no_snoop = true, + .disable_mhi_ram_parity_check = true, + .firmware_managed = true, +}; + static const struct of_device_id qcom_pcie_ep_match[] = { + { .compatible = "qcom,sa8255p-pcie-ep", .data = &cfg_1_34_0_fw_managed}, { .compatible = "qcom,sa8775p-pcie-ep", .data = &cfg_1_34_0}, { .compatible = "qcom,sdx55-pcie-ep", }, { .compatible = "qcom,sm8450-pcie-ep", }, diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c index dc98ae63362d..67a16af69ddc 100644 --- a/drivers/pci/controller/dwc/pcie-qcom.c +++ b/drivers/pci/controller/dwc/pcie-qcom.c @@ -21,7 +21,10 @@ #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/pci-pwrctrl.h> #include <linux/pm_opp.h> #include <linux/pm_runtime.h> #include <linux/platform_device.h> @@ -34,6 +37,7 @@ #include <linux/units.h> #include "../../pci.h" +#include "../pci-host-common.h" #include "pcie-designware.h" #include "pcie-qcom-common.h" @@ -52,9 +56,6 @@ #define PARF_AXI_MSTR_WR_ADDR_HALT_V2 0x1a8 #define PARF_Q2A_FLUSH 0x1ac #define PARF_LTSSM 0x1b0 -#define PARF_INT_ALL_STATUS 0x224 -#define PARF_INT_ALL_CLEAR 0x228 -#define PARF_INT_ALL_MASK 0x22c #define PARF_SID_OFFSET 0x234 #define PARF_BDF_TRANSLATE_CFG 0x24c #define PARF_DBI_BASE_ADDR_V2 0x350 @@ -131,10 +132,6 @@ /* PARF_LTSSM register fields */ #define LTSSM_EN BIT(8) -/* 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_OVERRIDE register fields */ #define WR_NO_SNOOP_OVERRIDE_EN BIT(1) #define RD_NO_SNOOP_OVERRIDE_EN BIT(3) @@ -255,53 +252,76 @@ 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_perst { + struct list_head list; + struct gpio_desc *desc; +}; + +struct qcom_pcie_port { + struct list_head list; + struct phy *phy; + struct list_head perst; +}; + 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_pcie_perst_assert(struct qcom_pcie *pcie, bool assert) { - gpiod_set_value_cansleep(pcie->reset, 1); + struct qcom_pcie_perst *perst; + struct qcom_pcie_port *port; + int val = assert ? 1 : 0; + + list_for_each_entry(port, &pcie->ports, list) { + list_for_each_entry(perst, &port->perst, list) + gpiod_set_value_cansleep(perst->desc, val); + } + usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500); } -static void qcom_ep_reset_deassert(struct qcom_pcie *pcie) +static void qcom_pcie_perst_assert(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); + __qcom_pcie_perst_assert(pcie, true); +} + +static void qcom_pcie_perst_deassert(struct qcom_pcie *pcie) +{ + /* Ensure that PERST# has been asserted for at least 100 ms */ + msleep(PCIE_T_PVPERL_MS); + __qcom_pcie_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) @@ -390,12 +410,17 @@ 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) @@ -989,6 +1014,8 @@ 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); @@ -1010,7 +1037,6 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie) 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); return 0; @@ -1221,12 +1247,40 @@ 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) @@ -1235,27 +1289,35 @@ static int qcom_pcie_host_init(struct dw_pcie_rp *pp) struct qcom_pcie *pcie = to_qcom_pcie(pci); int ret; - qcom_ep_reset_assert(pcie); + qcom_pcie_perst_assert(pcie); ret = pcie->cfg->ops->init(pcie); if (ret) return ret; - ret = phy_set_mode_ext(pcie->phy, PHY_MODE_PCIE, PHY_MODE_PCIE_RC); + ret = qcom_pcie_phy_power_on(pcie); if (ret) goto err_deinit; - ret = phy_power_on(pcie->phy); + ret = pci_pwrctrl_create_devices(pci->dev); if (ret) - goto err_deinit; + goto err_disable_phy; + + ret = pci_pwrctrl_power_on_devices(pci->dev); + if (ret) + goto err_pwrctrl_destroy; if (pcie->cfg->ops->post_init) { ret = pcie->cfg->ops->post_init(pcie); if (ret) - goto err_disable_phy; + goto err_pwrctrl_power_off; } - qcom_ep_reset_deassert(pcie); + qcom_pcie_clear_aspm_l0s(pcie->pci); + dw_pcie_remove_capability(pcie->pci, PCI_CAP_ID_MSIX); + dw_pcie_remove_ext_capability(pcie->pci, PCI_EXT_CAP_ID_DPC); + + qcom_pcie_perst_deassert(pcie); if (pcie->cfg->ops->config_sid) { ret = pcie->cfg->ops->config_sid(pcie); @@ -1266,9 +1328,14 @@ static int qcom_pcie_host_init(struct dw_pcie_rp *pp) return 0; err_assert_reset: - qcom_ep_reset_assert(pcie); + qcom_pcie_perst_assert(pcie); +err_pwrctrl_power_off: + pci_pwrctrl_power_off_devices(pci->dev); +err_pwrctrl_destroy: + if (ret != -EPROBE_DEFER) + pci_pwrctrl_destroy_devices(pci->dev); err_disable_phy: - phy_power_off(pcie->phy); + qcom_pcie_phy_power_off(pcie); err_deinit: pcie->cfg->ops->deinit(pcie); @@ -1280,8 +1347,14 @@ static void qcom_pcie_host_deinit(struct dw_pcie_rp *pp) struct dw_pcie *pci = to_dw_pcie_from_pp(pp); struct qcom_pcie *pcie = to_qcom_pcie(pci); - qcom_ep_reset_assert(pcie); - phy_power_off(pcie->phy); + qcom_pcie_perst_assert(pcie); + + /* + * No need to destroy pwrctrl devices as this function only gets called + * during system suspend as of now. + */ + pci_pwrctrl_power_off_devices(pci->dev); + qcom_pcie_phy_power_off(pcie); pcie->cfg->ops->deinit(pcie); } @@ -1403,6 +1476,7 @@ static const struct qcom_pcie_cfg cfg_2_1_0 = { static const struct qcom_pcie_cfg cfg_2_3_2 = { .ops = &ops_2_3_2, + .no_l0s = true, }; static const struct qcom_pcie_cfg cfg_2_3_3 = { @@ -1426,6 +1500,10 @@ static const struct qcom_pcie_cfg cfg_sc8280xp = { .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, @@ -1478,6 +1556,7 @@ 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; @@ -1505,8 +1584,20 @@ 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) @@ -1554,33 +1645,200 @@ static void qcom_pcie_init_debugfs(struct qcom_pcie *pcie) qcom_pcie_link_transition_count); } -static irqreturn_t qcom_pcie_global_irq_thread(int irq, void *data) +static void qcom_pci_free_msi(void *ptr) +{ + struct dw_pcie_rp *pp = (struct dw_pcie_rp *)ptr; + + if (pp && pp->use_imsi_rx) + 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->use_imsi_rx = 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, + } +}; + +/* Parse PERST# from all nodes in depth first manner starting from @np */ +static int qcom_pcie_parse_perst(struct qcom_pcie *pcie, + struct qcom_pcie_port *port, + struct device_node *np) { - struct qcom_pcie *pcie = data; - struct dw_pcie_rp *pp = &pcie->pci->pp; struct device *dev = pcie->pci->dev; - u32 status = readl_relaxed(pcie->parf + PARF_INT_ALL_STATUS); + struct qcom_pcie_perst *perst; + struct gpio_desc *reset; + int ret; - writel_relaxed(status, pcie->parf + PARF_INT_ALL_CLEAR); + if (!of_find_property(np, "reset-gpios", NULL)) + goto parse_child_node; - if (FIELD_GET(PARF_INT_ALL_LINK_UP, status)) { - 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(); + reset = devm_fwnode_gpiod_get(dev, of_fwnode_handle(np), "reset", + GPIOD_OUT_HIGH, "PERST#"); + if (IS_ERR(reset)) { + /* + * FIXME: GPIOLIB currently supports exclusive GPIO access only. + * Non exclusive access is broken. But shared PERST# requires + * non-exclusive access. So once GPIOLIB properly supports it, + * implement it here. + */ + if (PTR_ERR(reset) == -EBUSY) + dev_err(dev, "Shared PERST# is not supported\n"); - qcom_pcie_icc_opp_update(pcie); - } else { - dev_WARN_ONCE(dev, 1, "Received unknown event. INT_STATUS: 0x%08x\n", - status); + return PTR_ERR(reset); + } + + perst = devm_kzalloc(dev, sizeof(*perst), GFP_KERNEL); + if (!perst) + return -ENOMEM; + + INIT_LIST_HEAD(&perst->list); + perst->desc = reset; + list_add_tail(&perst->list, &port->perst); + +parse_child_node: + for_each_available_child_of_node_scoped(np, child) { + ret = qcom_pcie_parse_perst(pcie, port, child); + if (ret) + return ret; } - return IRQ_HANDLED; + return 0; +} + +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 phy *phy; + int ret; + + 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; + + INIT_LIST_HEAD(&port->perst); + + ret = qcom_pcie_parse_perst(pcie, port, node); + if (ret) + return ret; + + 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 qcom_pcie_perst *perst, *tmp_perst; + struct qcom_pcie_port *port, *tmp_port; + struct device *dev = pcie->pci->dev; + int ret = -ENODEV; + + 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_port, &pcie->ports, list) { + list_for_each_entry_safe(perst, tmp_perst, &port->perst, list) + list_del(&perst->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_perst *perst; + 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; + + perst = devm_kzalloc(dev, sizeof(*perst), GFP_KERNEL); + if (!perst) + return -ENOMEM; + + port->phy = phy; + INIT_LIST_HEAD(&port->list); + list_add_tail(&port->list, &pcie->ports); + + perst->desc = reset; + INIT_LIST_HEAD(&port->perst); + INIT_LIST_HEAD(&perst->list); + list_add_tail(&perst->list, &port->perst); + + return 0; } static int qcom_pcie_probe(struct platform_device *pdev) { + struct qcom_pcie_perst *perst, *tmp_perst; + struct qcom_pcie_port *port, *tmp_port; const struct qcom_pcie_cfg *pcie_cfg; unsigned long max_freq = ULONG_MAX; struct device *dev = &pdev->dev; @@ -1589,28 +1847,67 @@ static int qcom_pcie_probe(struct platform_device *pdev) struct dw_pcie_rp *pp; struct resource *res; struct dw_pcie *pci; - int ret, irq; - char *name; + int ret; pcie_cfg = of_device_get_match_data(dev); - if (!pcie_cfg || !pcie_cfg->ops) { - dev_err(dev, "Invalid platform data\n"); - return -EINVAL; + 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; @@ -1619,24 +1916,12 @@ 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) { @@ -1647,12 +1932,6 @@ 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) { @@ -1699,43 +1978,32 @@ 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 != -ENODEV) { + dev_err_probe(pci->dev, ret, + "Failed to parse Root Port: %d\n", ret); + goto err_pm_runtime_put; + } - platform_set_drvdata(pdev, pcie); + /* + * 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; + } - irq = platform_get_irq_byname_optional(pdev, "global"); - if (irq > 0) - pp->use_linkup_irq = true; + platform_set_drvdata(pdev, pcie); ret = dw_pcie_host_init(pp); if (ret) { - dev_err(dev, "cannot initialize host\n"); + dev_err_probe(dev, ret, "cannot initialize host\n"); goto err_phy_exit; } - name = devm_kasprintf(dev, GFP_KERNEL, "qcom_pcie_global_irq%d", - pci_domain_nr(pp->bridge->bus)); - if (!name) { - ret = -ENOMEM; - goto err_host_deinit; - } - - if (irq > 0) { - ret = devm_request_threaded_irq(&pdev->dev, irq, NULL, - qcom_pcie_global_irq_thread, - IRQF_ONESHOT, name, pcie); - if (ret) { - dev_err_probe(&pdev->dev, ret, - "Failed to request Global IRQ\n"); - goto err_host_deinit; - } - - 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); if (pcie->mhi) @@ -1743,10 +2011,13 @@ static int qcom_pcie_probe(struct platform_device *pdev) return 0; -err_host_deinit: - dw_pcie_host_deinit(pp); err_phy_exit: - phy_exit(pcie->phy); + list_for_each_entry_safe(port, tmp_port, &pcie->ports, list) { + list_for_each_entry_safe(perst, tmp_perst, &port->perst, list) + list_del(&perst->list); + phy_exit(port->phy); + list_del(&port->list); + } err_pm_runtime_put: pm_runtime_put(dev); pm_runtime_disable(dev); @@ -1756,9 +2027,13 @@ 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. @@ -1812,9 +2087,13 @@ 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) { @@ -1840,6 +2119,7 @@ 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 }, @@ -1848,6 +2128,7 @@ static const struct of_device_id qcom_pcie_match[] = { { .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 }, diff --git a/drivers/pci/controller/dwc/pcie-rcar-gen4.c b/drivers/pci/controller/dwc/pcie-rcar-gen4.c index fc872dd35029..a6912e85e4dd 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 +420,11 @@ 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, + DWC_EPC_COMMON_FEATURES, .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 +722,7 @@ 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 +732,7 @@ 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; diff --git a/drivers/pci/controller/dwc/pcie-sophgo.c b/drivers/pci/controller/dwc/pcie-sophgo.c new file mode 100644 index 000000000000..044088898819 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-sophgo.c @@ -0,0 +1,275 @@ +// 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 void sophgo_pcie_disable_l0s_l1(struct dw_pcie_rp *pp) +{ + struct dw_pcie *pci = to_dw_pcie_from_pp(pp); + u32 offset, val; + + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP); + + dw_pcie_dbi_ro_wr_en(pci); + + val = dw_pcie_readl_dbi(pci, PCI_EXP_LNKCAP + offset); + val &= ~(PCI_EXP_LNKCAP_ASPM_L0S | PCI_EXP_LNKCAP_ASPM_L1); + dw_pcie_writel_dbi(pci, PCI_EXP_LNKCAP + offset, val); + + dw_pcie_dbi_ro_wr_dis(pci); +} + +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_disable_l0s_l1(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..c1944b40ce02 --- /dev/null +++ b/drivers/pci/controller/dwc/pcie-stm32-ep.c @@ -0,0 +1,344 @@ +// 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 = { + DWC_EPC_COMMON_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 5103995cd6c7..06571d806ab3 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; @@ -1721,9 +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"); @@ -1856,12 +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; @@ -1940,6 +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 */ @@ -1954,10 +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; } @@ -1996,9 +1988,9 @@ 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 = { + DWC_EPC_COMMON_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, }, @@ -2016,6 +2008,7 @@ 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, }; diff --git a/drivers/pci/controller/dwc/pcie-uniphier-ep.c b/drivers/pci/controller/dwc/pcie-uniphier-ep.c index d6e73811216e..d52753060970 100644 --- a/drivers/pci/controller/dwc/pcie-uniphier-ep.c +++ b/drivers/pci/controller/dwc/pcie-uniphier-ep.c @@ -420,6 +420,7 @@ static const struct uniphier_pcie_ep_soc_data uniphier_pro5_data = { .init = uniphier_pcie_pro5_init_ep, .wait = NULL, .features = { + DWC_EPC_COMMON_FEATURES, .linkup_notifier = false, .msi_capable = true, .msix_capable = false, @@ -438,6 +439,7 @@ static const struct uniphier_pcie_ep_soc_data uniphier_nx1_data = { .init = uniphier_pcie_nx1_init_ep, .wait = uniphier_pcie_nx1_wait_ep, .features = { + DWC_EPC_COMMON_FEATURES, .linkup_notifier = false, .msi_capable = true, .msix_capable = false, 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 a29796cce420..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; 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 f441bfd6f96a..d6258c1cffe5 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; @@ -30,7 +32,7 @@ static struct pci_config_window *gen_pci_init(struct device *dev, err = of_address_to_resource(dev->of_node, 0, &cfgres); if (err) { - dev_err(dev, "missing \"reg\" property\n"); + dev_err(dev, "missing or malformed \"reg\" property\n"); return ERR_PTR(err); } @@ -48,28 +50,21 @@ 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); @@ -81,6 +76,23 @@ int pci_host_common_probe(struct platform_device *pdev) 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) @@ -94,5 +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 4051b9b61dac..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 = { diff --git a/drivers/pci/controller/pci-hyperv-intf.c b/drivers/pci/controller/pci-hyperv-intf.c index cc96be450360..18acbda867f0 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); @@ -51,17 +52,5 @@ int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context, } EXPORT_SYMBOL_GPL(hyperv_reg_block_invalidate); -static void __exit exit_hv_pci_intf(void) -{ -} - -static int __init init_hv_pci_intf(void) -{ - return 0; -} - -module_init(init_hv_pci_intf); -module_exit(exit_hv_pci_intf); - MODULE_DESCRIPTION("Hyper-V PCI Interface"); MODULE_LICENSE("GPL v2"); diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index ac27bda5ba26..2c7a406b4ba8 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[]; }; /* @@ -501,7 +501,6 @@ struct hv_pcibus_device { struct resource *low_mmio_res; struct resource *high_mmio_res; struct completion *survey_event; - struct pci_bus *pci_bus; spinlock_t config_lock; /* Avoid two threads writing index page */ spinlock_t device_list_lock; /* Protect lists below */ void __iomem *cfg_addr; @@ -509,7 +508,6 @@ 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 +575,8 @@ 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 +598,7 @@ 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 +607,7 @@ 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 +712,20 @@ 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 +735,7 @@ 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 +827,17 @@ 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) @@ -887,13 +905,47 @@ 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); + chip_data = kzalloc_obj(*chip_data); if (!chip_data) return ret; @@ -907,9 +959,24 @@ 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"); @@ -1438,7 +1505,7 @@ 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 +1585,7 @@ 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 +1666,7 @@ 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 +1679,6 @@ 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 +1686,7 @@ 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 +1696,7 @@ 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 +1714,6 @@ 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 +1724,6 @@ 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 { @@ -1869,7 +1932,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) hv_int_desc_free(hpdev, int_desc); } - int_desc = kzalloc(sizeof(*int_desc), GFP_ATOMIC); + int_desc = kzalloc_obj(*int_desc, GFP_ATOMIC); if (!int_desc) goto drop_reference; @@ -2045,24 +2108,85 @@ 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, - .flags = IRQCHIP_MOVE_DEFERRED, -#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 +2204,14 @@ 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"); @@ -2471,7 +2592,7 @@ static struct hv_pci_dev *new_pcichild_device(struct hv_pcibus_device *hbus, unsigned long flags; int ret; - hpdev = kzalloc(sizeof(*hpdev), GFP_KERNEL); + hpdev = kzalloc_obj(*hpdev); if (!hpdev) return NULL; @@ -2482,7 +2603,7 @@ 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; @@ -2710,7 +2831,7 @@ static int hv_pci_start_relations_work(struct hv_pcibus_device *hbus, return -ENOENT; } - dr_wrk = kzalloc(sizeof(*dr_wrk), GFP_NOWAIT); + dr_wrk = kzalloc_obj(*dr_wrk, GFP_NOWAIT); if (!dr_wrk) return -ENOMEM; @@ -2750,8 +2871,7 @@ static void hv_pci_devices_present(struct hv_pcibus_device *hbus, struct hv_dr_state *dr; int i; - dr = kzalloc(struct_size(dr, func, relations->device_count), - GFP_NOWAIT); + dr = kzalloc_flex(*dr, func, relations->device_count, GFP_NOWAIT); if (!dr) return; @@ -2785,8 +2905,7 @@ static void hv_pci_devices_present2(struct hv_pcibus_device *hbus, struct hv_dr_state *dr; int i; - dr = kzalloc(struct_size(dr, func, relations->device_count), - GFP_NOWAIT); + dr = kzalloc_flex(*dr, func, relations->device_count, GFP_NOWAIT); if (!dr) return; @@ -2860,7 +2979,7 @@ 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 +3237,7 @@ 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 +3459,7 @@ 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 +3617,20 @@ 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 +3693,6 @@ 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 @@ -3628,15 +3705,15 @@ 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) return -ENOMEM; - hbus = kzalloc(sizeof(*hbus), GFP_KERNEL); + hbus = kzalloc_obj(*hbus); if (!hbus) return -ENOMEM; @@ -3657,11 +3734,14 @@ 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 +3875,7 @@ 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 +3889,7 @@ 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 +3935,10 @@ 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 +4000,6 @@ 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 +4054,18 @@ 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 +4166,13 @@ 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 b0e3bce10aa4..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; diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c index d2f88997283a..512309763d1f 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; @@ -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); @@ -2571,12 +2545,6 @@ static const struct seq_operations tegra_pcie_ports_sops = { DEFINE_SEQ_ATTRIBUTE(tegra_pcie_ports); -static void tegra_pcie_debugfs_exit(struct tegra_pcie *pcie) -{ - debugfs_remove_recursive(pcie->debugfs); - pcie->debugfs = NULL; -} - static void tegra_pcie_debugfs_init(struct tegra_pcie *pcie) { pcie->debugfs = debugfs_create_dir("pcie", NULL); @@ -2650,29 +2618,6 @@ put_resources: return err; } -static void tegra_pcie_remove(struct platform_device *pdev) -{ - struct tegra_pcie *pcie = platform_get_drvdata(pdev); - struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie); - struct tegra_pcie_port *port, *tmp; - - if (IS_ENABLED(CONFIG_DEBUG_FS)) - tegra_pcie_debugfs_exit(pcie); - - pci_stop_root_bus(host->bus); - pci_remove_root_bus(host->bus); - pm_runtime_put_sync(pcie->dev); - pm_runtime_disable(pcie->dev); - - if (IS_ENABLED(CONFIG_PCI_MSI)) - tegra_pcie_msi_teardown(pcie); - - tegra_pcie_put_resources(pcie); - - list_for_each_entry_safe(port, tmp, &pcie->ports, list) - tegra_pcie_port_free(port); -} - static int tegra_pcie_pm_suspend(struct device *dev) { struct tegra_pcie *pcie = dev_get_drvdata(dev); @@ -2776,6 +2721,8 @@ static struct platform_driver tegra_pcie_driver = { .pm = &tegra_pcie_pm_ops, }, .probe = tegra_pcie_probe, - .remove = tegra_pcie_remove, }; -module_platform_driver(tegra_pcie_driver); +builtin_platform_driver(tegra_pcie_driver); +MODULE_AUTHOR("Thierry Reding <treding@nvidia.com>"); +MODULE_DESCRIPTION("NVIDIA PCI host controller driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pci/controller/pci-thunder-ecam.c b/drivers/pci/controller/pci-thunder-ecam.c index 08161065a89c..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) diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c index f1bd5de67997..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)) diff --git a/drivers/pci/controller/pci-xgene-msi.c b/drivers/pci/controller/pci-xgene-msi.c index 7bce327897c9..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 from 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; @@ -520,9 +396,4 @@ static struct platform_driver xgene_msi_driver = { .probe = xgene_msi_probe, .remove = xgene_msi_remove, }; - -static int __init xgene_pcie_msi_init(void) -{ - return platform_driver_register(&xgene_msi_driver); -} -subsys_initcall(xgene_pcie_msi_init); +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 e1cee3c0575f..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); } diff --git a/drivers/pci/controller/pcie-altera.c b/drivers/pci/controller/pcie-altera.c index 70409e71a18f..3dbb7adc421c 100644 --- a/drivers/pci/controller/pcie-altera.c +++ b/drivers/pci/controller/pcie-altera.c @@ -852,10 +852,9 @@ static void aglx_isr(struct irq_desc *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"); diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c index 18e11b9a7f46..2d92fc79f6dd 100644 --- a/drivers/pci/controller/pcie-apple.c +++ b/drivers/pci/controller/pcie-apple.c @@ -18,10 +18,12 @@ * 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> @@ -29,6 +31,9 @@ #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 @@ -39,14 +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) @@ -100,7 +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 @@ -118,7 +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 @@ -129,11 +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; @@ -142,12 +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; }; @@ -162,27 +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); @@ -226,8 +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; @@ -251,24 +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) @@ -372,7 +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)), @@ -387,20 +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; } @@ -467,43 +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(CORE_LANE_CFG_REFCLKEN, pcie->base + CORE_LANE_CFG(port->idx)); - rmw_set(PORT_REFCLK_EN, port->base + PORT_REFCLK); + rmw_set(PHY_LANE_CFG_REFCLKEN, port->phy + PHY_LANE_CFG); + + 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, @@ -512,6 +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; @@ -524,6 +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; @@ -533,14 +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) @@ -550,8 +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); @@ -563,7 +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); @@ -571,7 +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); @@ -584,6 +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); @@ -595,11 +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", @@ -619,38 +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); @@ -716,7 +801,7 @@ static void apple_pcie_disable_device(struct pci_host_bridge *bridge, struct pci 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); @@ -731,33 +816,17 @@ static void apple_pcie_disable_device(struct pci_host_bridge *bridge, struct pci static int apple_pcie_init(struct pci_config_window *cfg) { struct device *dev = cfg->parent; - struct platform_device *platform = to_platform_device(dev); struct apple_pcie *pcie; int ret; - pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL); - if (!pcie) - return -ENOMEM; - - pcie->dev = dev; - - mutex_init(&pcie->lock); - - pcie->base = devm_platform_ioremap_resource(platform, 1); - if (IS_ERR(pcie->base)) - return PTR_ERR(pcie->base); - - cfg->priv = pcie; - INIT_LIST_HEAD(&pcie->ports); - - ret = apple_msi_init(pcie); - if (ret) - return ret; + pcie = apple_pcie_lookup(dev); + if (WARN_ON(!pcie)) + return -ENOENT; - for_each_child_of_node_scoped(dev->of_node, of_port) { + for_each_available_child_of_node_scoped(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); + dev_err(dev, "Port %pOF setup fail: %d\n", of_port, ret); return ret; } } @@ -776,14 +845,45 @@ static const struct pci_ecam_ops apple_pcie_cfg_ecam_ops = { } }; +static int apple_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct pci_host_bridge *bridge; + struct apple_pcie *pcie; + int ret; + + bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!bridge) + return -ENOMEM; + + pcie = pci_host_bridge_priv(bridge); + pcie->dev = dev; + pcie->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); + + mutex_init(&pcie->lock); + INIT_LIST_HEAD(&pcie->ports); + + ret = apple_msi_init(pcie); + if (ret) + return ret; + + return pci_host_common_init(pdev, bridge, &apple_pcie_cfg_ecam_ops); +} + 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); static struct platform_driver apple_pcie_driver = { - .probe = pci_host_common_probe, + .probe = apple_pcie_probe, .driver = { .name = "pcie-apple", .of_match_table = apple_pcie_of_match, diff --git a/drivers/pci/controller/pcie-aspeed.c b/drivers/pci/controller/pcie-aspeed.c new file mode 100644 index 000000000000..3e1a39d1e648 --- /dev/null +++ b/drivers/pci/controller/pcie-aspeed.c @@ -0,0 +1,1111 @@ +// SPDX-License-Identifier: GPL-2.0+ +/* + * Copyright 2025 Aspeed Technology Inc. + */ +#include <linux/bitfield.h> +#include <linux/clk.h> +#include <linux/interrupt.h> +#include <linux/irq.h> +#include <linux/irqdomain.h> +#include <linux/irqchip/chained_irq.h> +#include <linux/irqchip/irq-msi-lib.h> +#include <linux/kernel.h> +#include <linux/mfd/syscon.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/mutex.h> +#include <linux/of.h> +#include <linux/of_address.h> +#include <linux/of_pci.h> +#include <linux/pci.h> +#include <linux/platform_device.h> +#include <linux/phy/pcie.h> +#include <linux/phy/phy.h> +#include <linux/regmap.h> +#include <linux/reset.h> + +#include "../pci.h" + +#define MAX_MSI_HOST_IRQS 64 +#define ASPEED_RESET_RC_WAIT_MS 10 + +/* AST2600 AHBC Registers */ +#define ASPEED_AHBC_KEY 0x00 +#define ASPEED_AHBC_UNLOCK_KEY 0xaeed1a03 +#define ASPEED_AHBC_UNLOCK 0x01 +#define ASPEED_AHBC_ADDR_MAPPING 0x8c +#define ASPEED_PCIE_RC_MEMORY_EN BIT(5) + +/* AST2600 H2X Controller Registers */ +#define ASPEED_H2X_INT_STS 0x08 +#define ASPEED_PCIE_TX_IDLE_CLEAR BIT(0) +#define ASPEED_PCIE_INTX_STS GENMASK(3, 0) +#define ASPEED_H2X_HOST_RX_DESC_DATA 0x0c +#define ASPEED_H2X_TX_DESC0 0x10 +#define ASPEED_H2X_TX_DESC1 0x14 +#define ASPEED_H2X_TX_DESC2 0x18 +#define ASPEED_H2X_TX_DESC3 0x1c +#define ASPEED_H2X_TX_DESC_DATA 0x20 +#define ASPEED_H2X_STS 0x24 +#define ASPEED_PCIE_TX_IDLE BIT(31) +#define ASPEED_PCIE_STATUS_OF_TX GENMASK(25, 24) +#define ASPEED_PCIE_RC_H_TX_COMPLETE BIT(25) +#define ASPEED_PCIE_TRIGGER_TX BIT(0) +#define ASPEED_H2X_AHB_ADDR_CONFIG0 0x60 +#define ASPEED_AHB_REMAP_LO_ADDR(x) (x & GENMASK(15, 4)) +#define ASPEED_AHB_MASK_LO_ADDR(x) FIELD_PREP(GENMASK(31, 20), x) +#define ASPEED_H2X_AHB_ADDR_CONFIG1 0x64 +#define ASPEED_AHB_REMAP_HI_ADDR(x) (x) +#define ASPEED_H2X_AHB_ADDR_CONFIG2 0x68 +#define ASPEED_AHB_MASK_HI_ADDR(x) (x) +#define ASPEED_H2X_DEV_CTRL 0xc0 +#define ASPEED_PCIE_RX_DMA_EN BIT(9) +#define ASPEED_PCIE_RX_LINEAR BIT(8) +#define ASPEED_PCIE_RX_MSI_SEL BIT(7) +#define ASPEED_PCIE_RX_MSI_EN BIT(6) +#define ASPEED_PCIE_UNLOCK_RX_BUFF BIT(4) +#define ASPEED_PCIE_WAIT_RX_TLP_CLR BIT(2) +#define ASPEED_PCIE_RC_RX_ENABLE BIT(1) +#define ASPEED_PCIE_RC_ENABLE BIT(0) +#define ASPEED_H2X_DEV_STS 0xc8 +#define ASPEED_PCIE_RC_RX_DONE_ISR BIT(4) +#define ASPEED_H2X_DEV_RX_DESC_DATA 0xcc +#define ASPEED_H2X_DEV_RX_DESC1 0xd4 +#define ASPEED_H2X_DEV_TX_TAG 0xfc +#define ASPEED_RC_TLP_TX_TAG_NUM 0x28 + +/* AST2700 H2X */ +#define ASPEED_H2X_CTRL 0x00 +#define ASPEED_H2X_BRIDGE_EN BIT(0) +#define ASPEED_H2X_BRIDGE_DIRECT_EN BIT(1) +#define ASPEED_H2X_CFGE_INT_STS 0x08 +#define ASPEED_CFGE_TX_IDLE BIT(0) +#define ASPEED_CFGE_RX_BUSY BIT(1) +#define ASPEED_H2X_CFGI_TLP 0x20 +#define ASPEED_CFGI_BYTE_EN_MASK GENMASK(19, 16) +#define ASPEED_CFGI_BYTE_EN(x) \ + FIELD_PREP(ASPEED_CFGI_BYTE_EN_MASK, (x)) +#define ASPEED_H2X_CFGI_WR_DATA 0x24 +#define ASPEED_CFGI_WRITE BIT(20) +#define ASPEED_H2X_CFGI_CTRL 0x28 +#define ASPEED_CFGI_TLP_FIRE BIT(0) +#define ASPEED_H2X_CFGI_RET_DATA 0x2c +#define ASPEED_H2X_CFGE_TLP_1ST 0x30 +#define ASPEED_H2X_CFGE_TLP_NEXT 0x34 +#define ASPEED_H2X_CFGE_CTRL 0x38 +#define ASPEED_CFGE_TLP_FIRE BIT(0) +#define ASPEED_H2X_CFGE_RET_DATA 0x3c +#define ASPEED_H2X_REMAP_PREF_ADDR 0x70 +#define ASPEED_REMAP_PREF_ADDR_63_32(x) (x) +#define ASPEED_H2X_REMAP_PCI_ADDR_HI 0x74 +#define ASPEED_REMAP_PCI_ADDR_63_32(x) (((x) >> 32) & GENMASK(31, 0)) +#define ASPEED_H2X_REMAP_PCI_ADDR_LO 0x78 +#define ASPEED_REMAP_PCI_ADDR_31_12(x) ((x) & GENMASK(31, 12)) + +/* AST2700 SCU */ +#define ASPEED_SCU_60 0x60 +#define ASPEED_RC_E2M_PATH_EN BIT(0) +#define ASPEED_RC_H2XS_PATH_EN BIT(16) +#define ASPEED_RC_H2XD_PATH_EN BIT(17) +#define ASPEED_RC_H2XX_PATH_EN BIT(18) +#define ASPEED_RC_UPSTREAM_MEM_EN BIT(19) +#define ASPEED_SCU_64 0x64 +#define ASPEED_RC0_DECODE_DMA_BASE(x) FIELD_PREP(GENMASK(7, 0), x) +#define ASPEED_RC0_DECODE_DMA_LIMIT(x) FIELD_PREP(GENMASK(15, 8), x) +#define ASPEED_RC1_DECODE_DMA_BASE(x) FIELD_PREP(GENMASK(23, 16), x) +#define ASPEED_RC1_DECODE_DMA_LIMIT(x) FIELD_PREP(GENMASK(31, 24), x) +#define ASPEED_SCU_70 0x70 +#define ASPEED_DISABLE_EP_FUNC 0 + +/* Macro to combine Fmt and Type into the 8-bit field */ +#define ASPEED_TLP_FMT_TYPE(fmt, type) ((((fmt) & 0x7) << 5) | ((type) & 0x1f)) +#define ASPEED_TLP_COMMON_FIELDS GENMASK(31, 24) + +/* Completion status */ +#define CPL_STS(x) FIELD_GET(GENMASK(15, 13), (x)) +/* TLP configuration type 0 and type 1 */ +#define CFG0_READ_FMTTYPE \ + FIELD_PREP(ASPEED_TLP_COMMON_FIELDS, \ + ASPEED_TLP_FMT_TYPE(PCIE_TLP_FMT_3DW_NO_DATA, \ + PCIE_TLP_TYPE_CFG0_RD)) +#define CFG0_WRITE_FMTTYPE \ + FIELD_PREP(ASPEED_TLP_COMMON_FIELDS, \ + ASPEED_TLP_FMT_TYPE(PCIE_TLP_FMT_3DW_DATA, \ + PCIE_TLP_TYPE_CFG0_WR)) +#define CFG1_READ_FMTTYPE \ + FIELD_PREP(ASPEED_TLP_COMMON_FIELDS, \ + ASPEED_TLP_FMT_TYPE(PCIE_TLP_FMT_3DW_NO_DATA, \ + PCIE_TLP_TYPE_CFG1_RD)) +#define CFG1_WRITE_FMTTYPE \ + FIELD_PREP(ASPEED_TLP_COMMON_FIELDS, \ + ASPEED_TLP_FMT_TYPE(PCIE_TLP_FMT_3DW_DATA, \ + PCIE_TLP_TYPE_CFG1_WR)) +#define CFG_PAYLOAD_SIZE 0x01 /* 1 DWORD */ +#define TLP_HEADER_BYTE_EN(x, y) ((GENMASK((x) - 1, 0) << ((y) % 4))) +#define TLP_GET_VALUE(x, y, z) \ + (((x) >> ((((z) % 4)) * 8)) & GENMASK((8 * (y)) - 1, 0)) +#define TLP_SET_VALUE(x, y, z) \ + ((((x) & GENMASK((8 * (y)) - 1, 0)) << ((((z) % 4)) * 8))) +#define AST2600_TX_DESC1_VALUE 0x00002000 +#define AST2700_TX_DESC1_VALUE 0x00401000 + +/** + * struct aspeed_pcie_port - PCIe port information + * @list: port list + * @pcie: pointer to PCIe host info + * @clk: pointer to the port clock gate + * @phy: pointer to PCIe PHY + * @perst: pointer to port reset control + * @slot: port slot + */ +struct aspeed_pcie_port { + struct list_head list; + struct aspeed_pcie *pcie; + struct clk *clk; + struct phy *phy; + struct reset_control *perst; + u32 slot; +}; + +/** + * struct aspeed_pcie - PCIe RC information + * @host: pointer to PCIe host bridge + * @dev: pointer to device structure + * @reg: PCIe host register base address + * @ahbc: pointer to AHHC register map + * @cfg: pointer to Aspeed PCIe configuration register map + * @platform: platform specific information + * @ports: list of PCIe ports + * @tx_tag: current TX tag for the port + * @root_bus_nr: bus number of the host bridge + * @h2xrst: pointer to H2X reset control + * @intx_domain: IRQ domain for INTx interrupts + * @msi_domain: IRQ domain for MSI interrupts + * @lock: mutex to protect MSI bitmap variable + * @msi_irq_in_use: bitmap to track used MSI host IRQs + * @clear_msi_twice: AST2700 workaround to clear MSI status twice + */ +struct aspeed_pcie { + struct pci_host_bridge *host; + struct device *dev; + void __iomem *reg; + struct regmap *ahbc; + struct regmap *cfg; + const struct aspeed_pcie_rc_platform *platform; + struct list_head ports; + + u8 tx_tag; + u8 root_bus_nr; + + struct reset_control *h2xrst; + + struct irq_domain *intx_domain; + struct irq_domain *msi_domain; + struct mutex lock; + DECLARE_BITMAP(msi_irq_in_use, MAX_MSI_HOST_IRQS); + + bool clear_msi_twice; /* AST2700 workaround */ +}; + +/** + * struct aspeed_pcie_rc_platform - Platform information + * @setup: initialization function + * @pcie_map_ranges: function to map PCIe address ranges + * @reg_intx_en: INTx enable register offset + * @reg_intx_sts: INTx status register offset + * @reg_msi_en: MSI enable register offset + * @reg_msi_sts: MSI enable register offset + * @msi_address: HW fixed MSI address + */ +struct aspeed_pcie_rc_platform { + int (*setup)(struct platform_device *pdev); + void (*pcie_map_ranges)(struct aspeed_pcie *pcie, u64 pci_addr); + int reg_intx_en; + int reg_intx_sts; + int reg_msi_en; + int reg_msi_sts; + u32 msi_address; +}; + +static void aspeed_pcie_intx_irq_ack(struct irq_data *d) +{ + struct aspeed_pcie *pcie = irq_data_get_irq_chip_data(d); + int intx_en = pcie->platform->reg_intx_en; + u32 en; + + en = readl(pcie->reg + intx_en); + en |= BIT(d->hwirq); + writel(en, pcie->reg + intx_en); +} + +static void aspeed_pcie_intx_irq_mask(struct irq_data *d) +{ + struct aspeed_pcie *pcie = irq_data_get_irq_chip_data(d); + int intx_en = pcie->platform->reg_intx_en; + u32 en; + + en = readl(pcie->reg + intx_en); + en &= ~BIT(d->hwirq); + writel(en, pcie->reg + intx_en); +} + +static void aspeed_pcie_intx_irq_unmask(struct irq_data *d) +{ + struct aspeed_pcie *pcie = irq_data_get_irq_chip_data(d); + int intx_en = pcie->platform->reg_intx_en; + u32 en; + + en = readl(pcie->reg + intx_en); + en |= BIT(d->hwirq); + writel(en, pcie->reg + intx_en); +} + +static struct irq_chip aspeed_intx_irq_chip = { + .name = "INTx", + .irq_ack = aspeed_pcie_intx_irq_ack, + .irq_mask = aspeed_pcie_intx_irq_mask, + .irq_unmask = aspeed_pcie_intx_irq_unmask, +}; + +static int aspeed_pcie_intx_map(struct irq_domain *domain, unsigned int irq, + irq_hw_number_t hwirq) +{ + irq_set_chip_and_handler(irq, &aspeed_intx_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 aspeed_intx_domain_ops = { + .map = aspeed_pcie_intx_map, +}; + +static irqreturn_t aspeed_pcie_intr_handler(int irq, void *dev_id) +{ + struct aspeed_pcie *pcie = dev_id; + const struct aspeed_pcie_rc_platform *platform = pcie->platform; + unsigned long status; + unsigned long intx; + u32 bit; + int i; + + intx = FIELD_GET(ASPEED_PCIE_INTX_STS, + readl(pcie->reg + platform->reg_intx_sts)); + for_each_set_bit(bit, &intx, PCI_NUM_INTX) + generic_handle_domain_irq(pcie->intx_domain, bit); + + for (i = 0; i < 2; i++) { + int msi_sts_reg = platform->reg_msi_sts + (i * 4); + + status = readl(pcie->reg + msi_sts_reg); + writel(status, pcie->reg + msi_sts_reg); + + /* + * AST2700 workaround: + * The MSI status needs to clear one more time. + */ + if (pcie->clear_msi_twice) + writel(status, pcie->reg + msi_sts_reg); + + for_each_set_bit(bit, &status, 32) { + bit += (i * 32); + generic_handle_domain_irq(pcie->msi_domain, bit); + } + } + + return IRQ_HANDLED; +} + +static u32 aspeed_pcie_get_bdf_offset(struct pci_bus *bus, unsigned int devfn, + int where) +{ + return ((bus->number) << 24) | (PCI_SLOT(devfn) << 19) | + (PCI_FUNC(devfn) << 16) | (where & ~3); +} + +static int aspeed_ast2600_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val, u32 fmt_type, + bool write) +{ + struct aspeed_pcie *pcie = bus->sysdata; + u32 bdf_offset, cfg_val, isr; + int ret; + + bdf_offset = aspeed_pcie_get_bdf_offset(bus, devfn, where); + + /* Driver may set unlock RX buffer before triggering next TX config */ + cfg_val = readl(pcie->reg + ASPEED_H2X_DEV_CTRL); + writel(ASPEED_PCIE_UNLOCK_RX_BUFF | cfg_val, + pcie->reg + ASPEED_H2X_DEV_CTRL); + + cfg_val = fmt_type | CFG_PAYLOAD_SIZE; + writel(cfg_val, pcie->reg + ASPEED_H2X_TX_DESC0); + + cfg_val = AST2600_TX_DESC1_VALUE | + FIELD_PREP(GENMASK(11, 8), pcie->tx_tag) | + TLP_HEADER_BYTE_EN(size, where); + writel(cfg_val, pcie->reg + ASPEED_H2X_TX_DESC1); + + writel(bdf_offset, pcie->reg + ASPEED_H2X_TX_DESC2); + writel(0, pcie->reg + ASPEED_H2X_TX_DESC3); + if (write) + writel(TLP_SET_VALUE(*val, size, where), + pcie->reg + ASPEED_H2X_TX_DESC_DATA); + + cfg_val = readl(pcie->reg + ASPEED_H2X_STS); + cfg_val |= ASPEED_PCIE_TRIGGER_TX; + writel(cfg_val, pcie->reg + ASPEED_H2X_STS); + + ret = readl_poll_timeout(pcie->reg + ASPEED_H2X_STS, cfg_val, + (cfg_val & ASPEED_PCIE_TX_IDLE), 0, 50); + if (ret) { + dev_err(pcie->dev, + "%02x:%02x.%d CR tx timeout sts: 0x%08x\n", + bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn), cfg_val); + ret = PCIBIOS_SET_FAILED; + PCI_SET_ERROR_RESPONSE(val); + goto out; + } + + cfg_val = readl(pcie->reg + ASPEED_H2X_INT_STS); + cfg_val |= ASPEED_PCIE_TX_IDLE_CLEAR; + writel(cfg_val, pcie->reg + ASPEED_H2X_INT_STS); + + cfg_val = readl(pcie->reg + ASPEED_H2X_STS); + switch (cfg_val & ASPEED_PCIE_STATUS_OF_TX) { + case ASPEED_PCIE_RC_H_TX_COMPLETE: + ret = readl_poll_timeout(pcie->reg + ASPEED_H2X_DEV_STS, isr, + (isr & ASPEED_PCIE_RC_RX_DONE_ISR), 0, + 50); + if (ret) { + dev_err(pcie->dev, + "%02x:%02x.%d CR rx timeout sts: 0x%08x\n", + bus->number, PCI_SLOT(devfn), + PCI_FUNC(devfn), isr); + ret = PCIBIOS_SET_FAILED; + PCI_SET_ERROR_RESPONSE(val); + goto out; + } + if (!write) { + cfg_val = readl(pcie->reg + ASPEED_H2X_DEV_RX_DESC1); + if (CPL_STS(cfg_val) != PCIE_CPL_STS_SUCCESS) { + ret = PCIBIOS_SET_FAILED; + PCI_SET_ERROR_RESPONSE(val); + goto out; + } else { + *val = readl(pcie->reg + + ASPEED_H2X_DEV_RX_DESC_DATA); + } + } + break; + case ASPEED_PCIE_STATUS_OF_TX: + ret = PCIBIOS_SET_FAILED; + PCI_SET_ERROR_RESPONSE(val); + goto out; + default: + *val = readl(pcie->reg + ASPEED_H2X_HOST_RX_DESC_DATA); + break; + } + + cfg_val = readl(pcie->reg + ASPEED_H2X_DEV_CTRL); + cfg_val |= ASPEED_PCIE_UNLOCK_RX_BUFF; + writel(cfg_val, pcie->reg + ASPEED_H2X_DEV_CTRL); + + *val = TLP_GET_VALUE(*val, size, where); + + ret = PCIBIOS_SUCCESSFUL; +out: + cfg_val = readl(pcie->reg + ASPEED_H2X_DEV_STS); + writel(cfg_val, pcie->reg + ASPEED_H2X_DEV_STS); + pcie->tx_tag = (pcie->tx_tag + 1) % 0x8; + return ret; +} + +static int aspeed_ast2600_rd_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + /* + * AST2600 has only one Root Port on the root bus. + */ + if (PCI_SLOT(devfn) != 8) + return PCIBIOS_DEVICE_NOT_FOUND; + + return aspeed_ast2600_conf(bus, devfn, where, size, val, + CFG0_READ_FMTTYPE, false); +} + +static int aspeed_ast2600_child_rd_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + return aspeed_ast2600_conf(bus, devfn, where, size, val, + CFG1_READ_FMTTYPE, false); +} + +static int aspeed_ast2600_wr_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + /* + * AST2600 has only one Root Port on the root bus. + */ + if (PCI_SLOT(devfn) != 8) + return PCIBIOS_DEVICE_NOT_FOUND; + + return aspeed_ast2600_conf(bus, devfn, where, size, &val, + CFG0_WRITE_FMTTYPE, true); +} + +static int aspeed_ast2600_child_wr_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + return aspeed_ast2600_conf(bus, devfn, where, size, &val, + CFG1_WRITE_FMTTYPE, true); +} + +static int aspeed_ast2700_config(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val, bool write) +{ + struct aspeed_pcie *pcie = bus->sysdata; + u32 cfg_val; + + cfg_val = ASPEED_CFGI_BYTE_EN(TLP_HEADER_BYTE_EN(size, where)) | + (where & ~3); + if (write) + cfg_val |= ASPEED_CFGI_WRITE; + writel(cfg_val, pcie->reg + ASPEED_H2X_CFGI_TLP); + + writel(TLP_SET_VALUE(*val, size, where), + pcie->reg + ASPEED_H2X_CFGI_WR_DATA); + writel(ASPEED_CFGI_TLP_FIRE, pcie->reg + ASPEED_H2X_CFGI_CTRL); + *val = readl(pcie->reg + ASPEED_H2X_CFGI_RET_DATA); + *val = TLP_GET_VALUE(*val, size, where); + + return PCIBIOS_SUCCESSFUL; +} + +static int aspeed_ast2700_child_config(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val, + bool write) +{ + struct aspeed_pcie *pcie = bus->sysdata; + u32 bdf_offset, status, cfg_val; + int ret; + + bdf_offset = aspeed_pcie_get_bdf_offset(bus, devfn, where); + + cfg_val = CFG_PAYLOAD_SIZE; + if (write) + cfg_val |= (bus->number == (pcie->root_bus_nr + 1)) ? + CFG0_WRITE_FMTTYPE : + CFG1_WRITE_FMTTYPE; + else + cfg_val |= (bus->number == (pcie->root_bus_nr + 1)) ? + CFG0_READ_FMTTYPE : + CFG1_READ_FMTTYPE; + writel(cfg_val, pcie->reg + ASPEED_H2X_CFGE_TLP_1ST); + + cfg_val = AST2700_TX_DESC1_VALUE | + FIELD_PREP(GENMASK(11, 8), pcie->tx_tag) | + TLP_HEADER_BYTE_EN(size, where); + writel(cfg_val, pcie->reg + ASPEED_H2X_CFGE_TLP_NEXT); + + writel(bdf_offset, pcie->reg + ASPEED_H2X_CFGE_TLP_NEXT); + if (write) + writel(TLP_SET_VALUE(*val, size, where), + pcie->reg + ASPEED_H2X_CFGE_TLP_NEXT); + writel(ASPEED_CFGE_TX_IDLE | ASPEED_CFGE_RX_BUSY, + pcie->reg + ASPEED_H2X_CFGE_INT_STS); + writel(ASPEED_CFGE_TLP_FIRE, pcie->reg + ASPEED_H2X_CFGE_CTRL); + + ret = readl_poll_timeout(pcie->reg + ASPEED_H2X_CFGE_INT_STS, status, + (status & ASPEED_CFGE_TX_IDLE), 0, 50); + if (ret) { + dev_err(pcie->dev, + "%02x:%02x.%d CR tx timeout sts: 0x%08x\n", + bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn), status); + ret = PCIBIOS_SET_FAILED; + PCI_SET_ERROR_RESPONSE(val); + goto out; + } + + ret = readl_poll_timeout(pcie->reg + ASPEED_H2X_CFGE_INT_STS, status, + (status & ASPEED_CFGE_RX_BUSY), 0, 50); + if (ret) { + dev_err(pcie->dev, + "%02x:%02x.%d CR rx timeout sts: 0x%08x\n", + bus->number, PCI_SLOT(devfn), PCI_FUNC(devfn), status); + ret = PCIBIOS_SET_FAILED; + PCI_SET_ERROR_RESPONSE(val); + goto out; + } + *val = readl(pcie->reg + ASPEED_H2X_CFGE_RET_DATA); + *val = TLP_GET_VALUE(*val, size, where); + + ret = PCIBIOS_SUCCESSFUL; +out: + writel(status, pcie->reg + ASPEED_H2X_CFGE_INT_STS); + pcie->tx_tag = (pcie->tx_tag + 1) % 0xf; + return ret; +} + +static int aspeed_ast2700_rd_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + /* + * AST2700 has only one Root Port on the root bus. + */ + if (devfn != 0) + return PCIBIOS_DEVICE_NOT_FOUND; + + return aspeed_ast2700_config(bus, devfn, where, size, val, false); +} + +static int aspeed_ast2700_child_rd_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 *val) +{ + return aspeed_ast2700_child_config(bus, devfn, where, size, val, false); +} + +static int aspeed_ast2700_wr_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + /* + * AST2700 has only one Root Port on the root bus. + */ + if (devfn != 0) + return PCIBIOS_DEVICE_NOT_FOUND; + + return aspeed_ast2700_config(bus, devfn, where, size, &val, true); +} + +static int aspeed_ast2700_child_wr_conf(struct pci_bus *bus, unsigned int devfn, + int where, int size, u32 val) +{ + return aspeed_ast2700_child_config(bus, devfn, where, size, &val, true); +} + +static struct pci_ops aspeed_ast2600_pcie_ops = { + .read = aspeed_ast2600_rd_conf, + .write = aspeed_ast2600_wr_conf, +}; + +static struct pci_ops aspeed_ast2600_pcie_child_ops = { + .read = aspeed_ast2600_child_rd_conf, + .write = aspeed_ast2600_child_wr_conf, +}; + +static struct pci_ops aspeed_ast2700_pcie_ops = { + .read = aspeed_ast2700_rd_conf, + .write = aspeed_ast2700_wr_conf, +}; + +static struct pci_ops aspeed_ast2700_pcie_child_ops = { + .read = aspeed_ast2700_child_rd_conf, + .write = aspeed_ast2700_child_wr_conf, +}; + +static void aspeed_irq_compose_msi_msg(struct irq_data *data, + struct msi_msg *msg) +{ + struct aspeed_pcie *pcie = irq_data_get_irq_chip_data(data); + + msg->address_hi = 0; + msg->address_lo = pcie->platform->msi_address; + msg->data = data->hwirq; +} + +static struct irq_chip aspeed_msi_bottom_irq_chip = { + .name = "ASPEED MSI", + .irq_compose_msi_msg = aspeed_irq_compose_msi_msg, +}; + +static int aspeed_irq_msi_domain_alloc(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs, + void *args) +{ + struct aspeed_pcie *pcie = domain->host_data; + int bit; + int i; + + guard(mutex)(&pcie->lock); + + bit = bitmap_find_free_region(pcie->msi_irq_in_use, MAX_MSI_HOST_IRQS, + get_count_order(nr_irqs)); + + if (bit < 0) + return -ENOSPC; + + for (i = 0; i < nr_irqs; i++) { + irq_domain_set_info(domain, virq + i, bit + i, + &aspeed_msi_bottom_irq_chip, + domain->host_data, handle_simple_irq, NULL, + NULL); + } + + return 0; +} + +static void aspeed_irq_msi_domain_free(struct irq_domain *domain, + unsigned int virq, unsigned int nr_irqs) +{ + struct irq_data *data = irq_domain_get_irq_data(domain, virq); + struct aspeed_pcie *pcie = irq_data_get_irq_chip_data(data); + + guard(mutex)(&pcie->lock); + + bitmap_release_region(pcie->msi_irq_in_use, data->hwirq, + get_count_order(nr_irqs)); +} + +static const struct irq_domain_ops aspeed_msi_domain_ops = { + .alloc = aspeed_irq_msi_domain_alloc, + .free = aspeed_irq_msi_domain_free, +}; + +#define ASPEED_MSI_FLAGS_REQUIRED (MSI_FLAG_USE_DEF_DOM_OPS | \ + MSI_FLAG_USE_DEF_CHIP_OPS | \ + MSI_FLAG_NO_AFFINITY) + +#define ASPEED_MSI_FLAGS_SUPPORTED (MSI_GENERIC_FLAGS_MASK | \ + MSI_FLAG_MULTI_PCI_MSI | \ + MSI_FLAG_PCI_MSIX) + +static const struct msi_parent_ops aspeed_msi_parent_ops = { + .required_flags = ASPEED_MSI_FLAGS_REQUIRED, + .supported_flags = ASPEED_MSI_FLAGS_SUPPORTED, + .bus_select_token = DOMAIN_BUS_PCI_MSI, + .chip_flags = MSI_CHIP_FLAG_SET_ACK, + .prefix = "ASPEED-", + .init_dev_msi_info = msi_lib_init_dev_msi_info, +}; + +static int aspeed_pcie_msi_init(struct aspeed_pcie *pcie) +{ + writel(~0, pcie->reg + pcie->platform->reg_msi_en); + writel(~0, pcie->reg + pcie->platform->reg_msi_en + 0x04); + writel(~0, pcie->reg + pcie->platform->reg_msi_sts); + writel(~0, pcie->reg + pcie->platform->reg_msi_sts + 0x04); + + struct irq_domain_info info = { + .fwnode = dev_fwnode(pcie->dev), + .ops = &aspeed_msi_domain_ops, + .host_data = pcie, + .size = MAX_MSI_HOST_IRQS, + }; + + pcie->msi_domain = msi_create_parent_irq_domain(&info, + &aspeed_msi_parent_ops); + if (!pcie->msi_domain) + return dev_err_probe(pcie->dev, -ENOMEM, + "failed to create MSI domain\n"); + + return 0; +} + +static void aspeed_pcie_msi_free(struct aspeed_pcie *pcie) +{ + if (pcie->msi_domain) { + irq_domain_remove(pcie->msi_domain); + pcie->msi_domain = NULL; + } +} + +static void aspeed_pcie_irq_domain_free(void *d) +{ + struct aspeed_pcie *pcie = d; + + if (pcie->intx_domain) { + irq_domain_remove(pcie->intx_domain); + pcie->intx_domain = NULL; + } + aspeed_pcie_msi_free(pcie); +} + +static int aspeed_pcie_init_irq_domain(struct aspeed_pcie *pcie) +{ + int ret; + + pcie->intx_domain = irq_domain_add_linear(pcie->dev->of_node, + PCI_NUM_INTX, + &aspeed_intx_domain_ops, + pcie); + if (!pcie->intx_domain) { + ret = dev_err_probe(pcie->dev, -ENOMEM, + "failed to get INTx IRQ domain\n"); + goto err; + } + + writel(0, pcie->reg + pcie->platform->reg_intx_en); + writel(~0, pcie->reg + pcie->platform->reg_intx_sts); + + ret = aspeed_pcie_msi_init(pcie); + if (ret) + goto err; + + return 0; +err: + aspeed_pcie_irq_domain_free(pcie); + return ret; +} + +static int aspeed_pcie_port_init(struct aspeed_pcie_port *port) +{ + struct aspeed_pcie *pcie = port->pcie; + struct device *dev = pcie->dev; + int ret; + + ret = clk_prepare_enable(port->clk); + if (ret) + return dev_err_probe(dev, ret, + "failed to set clock for slot (%d)\n", + port->slot); + + ret = phy_init(port->phy); + if (ret) + return dev_err_probe(dev, ret, + "failed to init phy pcie for slot (%d)\n", + port->slot); + + ret = phy_set_mode_ext(port->phy, PHY_MODE_PCIE, PHY_MODE_PCIE_RC); + if (ret) + return dev_err_probe(dev, ret, + "failed to set phy mode for slot (%d)\n", + port->slot); + + reset_control_deassert(port->perst); + msleep(PCIE_RESET_CONFIG_WAIT_MS); + + return 0; +} + +static void aspeed_host_reset(struct aspeed_pcie *pcie) +{ + reset_control_assert(pcie->h2xrst); + mdelay(ASPEED_RESET_RC_WAIT_MS); + reset_control_deassert(pcie->h2xrst); +} + +static void aspeed_pcie_map_ranges(struct aspeed_pcie *pcie) +{ + struct pci_host_bridge *bridge = pcie->host; + struct resource_entry *window; + + resource_list_for_each_entry(window, &bridge->windows) { + u64 pci_addr; + + if (resource_type(window->res) != IORESOURCE_MEM) + continue; + + pci_addr = window->res->start - window->offset; + pcie->platform->pcie_map_ranges(pcie, pci_addr); + break; + } +} + +static void aspeed_ast2600_pcie_map_ranges(struct aspeed_pcie *pcie, + u64 pci_addr) +{ + u32 pci_addr_lo = pci_addr & GENMASK(31, 0); + u32 pci_addr_hi = (pci_addr >> 32) & GENMASK(31, 0); + + pci_addr_lo >>= 16; + writel(ASPEED_AHB_REMAP_LO_ADDR(pci_addr_lo) | + ASPEED_AHB_MASK_LO_ADDR(0xe00), + pcie->reg + ASPEED_H2X_AHB_ADDR_CONFIG0); + writel(ASPEED_AHB_REMAP_HI_ADDR(pci_addr_hi), + pcie->reg + ASPEED_H2X_AHB_ADDR_CONFIG1); + writel(ASPEED_AHB_MASK_HI_ADDR(~0), + pcie->reg + ASPEED_H2X_AHB_ADDR_CONFIG2); +} + +static int aspeed_ast2600_setup(struct platform_device *pdev) +{ + struct aspeed_pcie *pcie = platform_get_drvdata(pdev); + struct device *dev = pcie->dev; + + pcie->ahbc = syscon_regmap_lookup_by_phandle(dev->of_node, + "aspeed,ahbc"); + if (IS_ERR(pcie->ahbc)) + return dev_err_probe(dev, PTR_ERR(pcie->ahbc), + "failed to map ahbc base\n"); + + aspeed_host_reset(pcie); + + regmap_write(pcie->ahbc, ASPEED_AHBC_KEY, ASPEED_AHBC_UNLOCK_KEY); + regmap_update_bits(pcie->ahbc, ASPEED_AHBC_ADDR_MAPPING, + ASPEED_PCIE_RC_MEMORY_EN, ASPEED_PCIE_RC_MEMORY_EN); + regmap_write(pcie->ahbc, ASPEED_AHBC_KEY, ASPEED_AHBC_UNLOCK); + + writel(ASPEED_H2X_BRIDGE_EN, pcie->reg + ASPEED_H2X_CTRL); + + writel(ASPEED_PCIE_RX_DMA_EN | ASPEED_PCIE_RX_LINEAR | + ASPEED_PCIE_RX_MSI_SEL | ASPEED_PCIE_RX_MSI_EN | + ASPEED_PCIE_WAIT_RX_TLP_CLR | ASPEED_PCIE_RC_RX_ENABLE | + ASPEED_PCIE_RC_ENABLE, + pcie->reg + ASPEED_H2X_DEV_CTRL); + + writel(ASPEED_RC_TLP_TX_TAG_NUM, pcie->reg + ASPEED_H2X_DEV_TX_TAG); + + pcie->host->ops = &aspeed_ast2600_pcie_ops; + pcie->host->child_ops = &aspeed_ast2600_pcie_child_ops; + + return 0; +} + +static void aspeed_ast2700_pcie_map_ranges(struct aspeed_pcie *pcie, + u64 pci_addr) +{ + writel(ASPEED_REMAP_PCI_ADDR_31_12(pci_addr), + pcie->reg + ASPEED_H2X_REMAP_PCI_ADDR_LO); + writel(ASPEED_REMAP_PCI_ADDR_63_32(pci_addr), + pcie->reg + ASPEED_H2X_REMAP_PCI_ADDR_HI); +} + +static int aspeed_ast2700_setup(struct platform_device *pdev) +{ + struct aspeed_pcie *pcie = platform_get_drvdata(pdev); + struct device *dev = pcie->dev; + + pcie->cfg = syscon_regmap_lookup_by_phandle(dev->of_node, + "aspeed,pciecfg"); + if (IS_ERR(pcie->cfg)) + return dev_err_probe(dev, PTR_ERR(pcie->cfg), + "failed to map pciecfg base\n"); + + regmap_update_bits(pcie->cfg, ASPEED_SCU_60, + ASPEED_RC_E2M_PATH_EN | ASPEED_RC_H2XS_PATH_EN | + ASPEED_RC_H2XD_PATH_EN | ASPEED_RC_H2XX_PATH_EN | + ASPEED_RC_UPSTREAM_MEM_EN, + ASPEED_RC_E2M_PATH_EN | ASPEED_RC_H2XS_PATH_EN | + ASPEED_RC_H2XD_PATH_EN | ASPEED_RC_H2XX_PATH_EN | + ASPEED_RC_UPSTREAM_MEM_EN); + regmap_write(pcie->cfg, ASPEED_SCU_64, + ASPEED_RC0_DECODE_DMA_BASE(0) | + ASPEED_RC0_DECODE_DMA_LIMIT(0xff) | + ASPEED_RC1_DECODE_DMA_BASE(0) | + ASPEED_RC1_DECODE_DMA_LIMIT(0xff)); + regmap_write(pcie->cfg, ASPEED_SCU_70, ASPEED_DISABLE_EP_FUNC); + + aspeed_host_reset(pcie); + + writel(0, pcie->reg + ASPEED_H2X_CTRL); + writel(ASPEED_H2X_BRIDGE_EN | ASPEED_H2X_BRIDGE_DIRECT_EN, + pcie->reg + ASPEED_H2X_CTRL); + + /* Prepare for 64-bit BAR pref */ + writel(ASPEED_REMAP_PREF_ADDR_63_32(0x3), + pcie->reg + ASPEED_H2X_REMAP_PREF_ADDR); + + pcie->host->ops = &aspeed_ast2700_pcie_ops; + pcie->host->child_ops = &aspeed_ast2700_pcie_child_ops; + pcie->clear_msi_twice = true; + + return 0; +} + +static void aspeed_pcie_reset_release(void *d) +{ + struct reset_control *perst = d; + + if (!perst) + return; + + reset_control_put(perst); +} + +static int aspeed_pcie_parse_port(struct aspeed_pcie *pcie, + struct device_node *node, + int slot) +{ + struct aspeed_pcie_port *port; + struct device *dev = pcie->dev; + int ret; + + port = devm_kzalloc(dev, sizeof(*port), GFP_KERNEL); + if (!port) + return -ENOMEM; + + port->clk = devm_get_clk_from_child(dev, node, NULL); + if (IS_ERR(port->clk)) + return dev_err_probe(dev, PTR_ERR(port->clk), + "failed to get pcie%d clock\n", slot); + + 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 phy pcie%d\n", slot); + + port->perst = of_reset_control_get_exclusive(node, "perst"); + if (IS_ERR(port->perst)) + return dev_err_probe(dev, PTR_ERR(port->perst), + "failed to get pcie%d reset control\n", + slot); + ret = devm_add_action_or_reset(dev, aspeed_pcie_reset_release, + port->perst); + if (ret) + return ret; + reset_control_assert(port->perst); + + port->slot = slot; + port->pcie = pcie; + + INIT_LIST_HEAD(&port->list); + list_add_tail(&port->list, &pcie->ports); + + ret = aspeed_pcie_port_init(port); + if (ret) + return ret; + + return 0; +} + +static int aspeed_pcie_parse_dt(struct aspeed_pcie *pcie) +{ + struct device *dev = pcie->dev; + struct device_node *node = dev->of_node; + int ret; + + for_each_available_child_of_node_scoped(node, child) { + int slot; + const char *type; + + ret = of_property_read_string(child, "device_type", &type); + if (ret || strcmp(type, "pci")) + continue; + + ret = of_pci_get_devfn(child); + if (ret < 0) + return dev_err_probe(dev, ret, + "failed to parse devfn\n"); + + slot = PCI_SLOT(ret); + + ret = aspeed_pcie_parse_port(pcie, child, slot); + if (ret) + return ret; + } + + if (list_empty(&pcie->ports)) + return dev_err_probe(dev, -ENODEV, + "No PCIe port found in DT\n"); + + return 0; +} + +static int aspeed_pcie_probe(struct platform_device *pdev) +{ + struct device *dev = &pdev->dev; + struct pci_host_bridge *host; + struct aspeed_pcie *pcie; + struct resource_entry *entry; + const struct aspeed_pcie_rc_platform *md; + int irq, ret; + + md = of_device_get_match_data(dev); + if (!md) + return -ENODEV; + + host = devm_pci_alloc_host_bridge(dev, sizeof(*pcie)); + if (!host) + return -ENOMEM; + + pcie = pci_host_bridge_priv(host); + pcie->dev = dev; + pcie->tx_tag = 0; + platform_set_drvdata(pdev, pcie); + + pcie->platform = md; + pcie->host = host; + INIT_LIST_HEAD(&pcie->ports); + + /* Get root bus num for cfg command to decide tlp type 0 or type 1 */ + entry = resource_list_first_type(&host->windows, IORESOURCE_BUS); + if (entry) + pcie->root_bus_nr = entry->res->start; + + pcie->reg = devm_platform_ioremap_resource(pdev, 0); + if (IS_ERR(pcie->reg)) + return PTR_ERR(pcie->reg); + + pcie->h2xrst = devm_reset_control_get_exclusive(dev, "h2x"); + if (IS_ERR(pcie->h2xrst)) + return dev_err_probe(dev, PTR_ERR(pcie->h2xrst), + "failed to get h2x reset\n"); + + ret = devm_mutex_init(dev, &pcie->lock); + if (ret) + return dev_err_probe(dev, ret, "failed to init mutex\n"); + + ret = pcie->platform->setup(pdev); + if (ret) + return dev_err_probe(dev, ret, "failed to setup PCIe RC\n"); + + aspeed_pcie_map_ranges(pcie); + + ret = aspeed_pcie_parse_dt(pcie); + if (ret) + return ret; + + host->sysdata = pcie; + + ret = aspeed_pcie_init_irq_domain(pcie); + if (ret) + return ret; + + irq = platform_get_irq(pdev, 0); + if (irq < 0) + return irq; + + ret = devm_add_action_or_reset(dev, aspeed_pcie_irq_domain_free, pcie); + if (ret) + return ret; + + ret = devm_request_irq(dev, irq, aspeed_pcie_intr_handler, IRQF_SHARED, + dev_name(dev), pcie); + if (ret) + return ret; + + return pci_host_probe(host); +} + +static const struct aspeed_pcie_rc_platform pcie_rc_ast2600 = { + .setup = aspeed_ast2600_setup, + .pcie_map_ranges = aspeed_ast2600_pcie_map_ranges, + .reg_intx_en = 0xc4, + .reg_intx_sts = 0xc8, + .reg_msi_en = 0xe0, + .reg_msi_sts = 0xe8, + .msi_address = 0x1e77005c, +}; + +static const struct aspeed_pcie_rc_platform pcie_rc_ast2700 = { + .setup = aspeed_ast2700_setup, + .pcie_map_ranges = aspeed_ast2700_pcie_map_ranges, + .reg_intx_en = 0x40, + .reg_intx_sts = 0x48, + .reg_msi_en = 0x50, + .reg_msi_sts = 0x58, + .msi_address = 0x000000f0, +}; + +static const struct of_device_id aspeed_pcie_of_match[] = { + { .compatible = "aspeed,ast2600-pcie", .data = &pcie_rc_ast2600 }, + { .compatible = "aspeed,ast2700-pcie", .data = &pcie_rc_ast2700 }, + {} +}; + +static struct platform_driver aspeed_pcie_driver = { + .driver = { + .name = "aspeed-pcie", + .of_match_table = aspeed_pcie_of_match, + .suppress_bind_attrs = true, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, + .probe = aspeed_pcie_probe, +}; + +builtin_platform_driver(aspeed_pcie_driver); + +MODULE_AUTHOR("Jacky Chou <jacky_chou@aspeedtech.com>"); +MODULE_DESCRIPTION("ASPEED PCIe Root Complex"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c index e19628e13898..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" @@ -46,7 +52,7 @@ #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 +61,9 @@ #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 @@ -150,8 +159,40 @@ #define MSI_INT_MASK_SET 0x10 #define MSI_INT_MASK_CLR 0x14 +/* 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 @@ -254,6 +295,7 @@ struct pcie_cfg_data { 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 { @@ -265,7 +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; @@ -299,6 +340,10 @@ struct brcm_pcie { struct subdev_regulators *sr; bool ep_wakeup_capable; 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) @@ -306,6 +351,24 @@ static inline bool is_bmips(const struct brcm_pcie *pcie) 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; +} + /* * This is to convert the size of the inbound "BAR" region to the * non-linear values of PCIE_X_MISC_RC_BAR[123]_CONFIG_LO.SIZE @@ -465,17 +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) @@ -581,21 +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; } @@ -604,7 +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); } @@ -970,7 +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 @@ -1072,13 +1134,13 @@ 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->cfg->bridge_sw_init_set(pcie, 1); + ret = brcm_pcie_bridge_sw_init_set(pcie, 1); if (ret) return ret; @@ -1094,7 +1156,7 @@ static int brcm_pcie_setup(struct brcm_pcie *pcie) usleep_range(100, 200); /* Take the bridge out of reset */ - ret = pcie->cfg->bridge_sw_init_set(pcie, 0); + ret = brcm_pcie_bridge_sw_init_set(pcie, 0); if (ret) return ret; @@ -1172,14 +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). @@ -1333,11 +1413,7 @@ static int brcm_pcie_start_link(struct brcm_pcie *pcie) 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 @@ -1545,7 +1621,7 @@ static int brcm_pcie_turn_off(struct brcm_pcie *pcie) if (!(pcie->cfg->quirks & CFG_QUIRK_AVOID_BRIDGE_SHUTDOWN)) /* Shutdown PCIe bridge */ - ret = pcie->cfg->bridge_sw_init_set(pcie, 1); + ret = brcm_pcie_bridge_sw_init_set(pcie, 1); return ret; } @@ -1633,7 +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->cfg->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)); @@ -1687,6 +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); @@ -1705,6 +1896,9 @@ 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); } @@ -1805,6 +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 = { @@ -1901,7 +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->cfg->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); @@ -1976,6 +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: 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.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 9d52504acae4..75ddb8bee168 100644 --- a/drivers/pci/controller/pcie-mediatek-gen3.c +++ b/drivers/pci/controller/pcie-mediatek-gen3.c @@ -12,6 +12,7 @@ #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> @@ -101,6 +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) @@ -148,6 +152,7 @@ enum mtk_gen3_pcie_flags { * 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 { @@ -156,6 +161,7 @@ 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; }; @@ -187,7 +193,6 @@ struct mtk_msi_set { * @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 @@ -210,7 +215,6 @@ struct mtk_gen3_pcie { 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; @@ -436,6 +440,14 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie) 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); @@ -526,30 +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) @@ -745,8 +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; @@ -756,28 +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: @@ -792,9 +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); @@ -1344,6 +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 = { @@ -1358,6 +1363,7 @@ static const struct mtk_gen3_pcie_pdata mtk_pcie_soc_en7581 = { 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); diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c index 811a8b4acd50..5defa5cc4c2b 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"); @@ -579,8 +585,10 @@ static int mtk_pcie_init_irq_domain(struct mtk_pcie_port *port, if (IS_ENABLED(CONFIG_PCI_MSI)) { ret = mtk_pcie_allocate_msi_domains(port); - if (ret) + if (ret) { + irq_domain_remove(port->irq_domain); return ret; + } } return 0; @@ -683,31 +691,28 @@ 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 +720,7 @@ 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 +830,41 @@ 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; @@ -1103,7 +1143,7 @@ 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) @@ -1191,9 +1231,9 @@ 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 = { @@ -1203,22 +1243,29 @@ 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 }, diff --git a/drivers/pci/controller/pcie-rcar-ep.c b/drivers/pci/controller/pcie-rcar-ep.c index c5e0d025bc43..657875ef4657 100644 --- a/drivers/pci/controller/pcie-rcar-ep.c +++ b/drivers/pci/controller/pcie-rcar-ep.c @@ -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 c32b803a47c7..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; } @@ -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) diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c index 85ea36df2f59..799461335762 100644 --- a/drivers/pci/controller/pcie-rockchip-ep.c +++ b/drivers/pci/controller/pcie-rockchip-ep.c @@ -308,10 +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, @@ -319,7 +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, @@ -340,8 +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, @@ -517,9 +518,9 @@ static void rockchip_pcie_ep_retrain_link(struct rockchip_pcie *rockchip) { u32 status; - status = rockchip_pcie_read(rockchip, PCIE_EP_CONFIG_LCS); + 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_LCS); + rockchip_pcie_write(rockchip, status, PCIE_EP_CONFIG_BASE + PCI_EXP_LNKCTL); } static bool rockchip_pcie_ep_link_up(struct rockchip_pcie *rockchip) @@ -693,7 +694,7 @@ static int rockchip_pcie_ep_setup_irq(struct pci_epc *epc) static const struct pci_epc_features rockchip_pcie_epc_features = { .linkup_notifier = true, .msi_capable = true, - .msix_capable = false, + .intx_capable = true, .align = ROCKCHIP_PCIE_AT_SIZE_ALIGN, }; diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c index 6a46be17aa91..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); } /** @@ -309,14 +301,14 @@ 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, @@ -325,7 +317,7 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip) msleep(PCIE_T_PVPERL_MS); 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, @@ -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"); diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h index 14954f43e5e9..3e82a69b9c00 100644 --- a/drivers/pci/controller/pcie-rockchip.h +++ b/drivers/pci/controller/pcie-rockchip.h @@ -12,6 +12,7 @@ #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> @@ -21,10 +22,10 @@ * 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 @@ -32,21 +33,21 @@ #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_LINK_TRAIN_DISABLE HIWORD_UPDATE(0x0002, 0) -#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) @@ -155,17 +156,7 @@ #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_EP_CONFIG_LCS (PCIE_EP_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) @@ -215,20 +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) @@ -319,11 +296,12 @@ static const char * const rockchip_pci_pm_rsts[] = { "aclk", }; +/* NOTE: Do not reorder the deassert sequence of the following reset pins */ static const char * const rockchip_pci_core_rsts[] = { - "mgmt-sticky", - "core", - "mgmt", "pipe", + "mgmt", + "core", + "mgmt-sticky", }; struct rockchip_pcie { diff --git a/drivers/pci/controller/pcie-rzg3s-host.c b/drivers/pci/controller/pcie-rzg3s-host.c new file mode 100644 index 000000000000..2809112e6317 --- /dev/null +++ b/drivers/pci/controller/pcie-rzg3s-host.c @@ -0,0 +1,1742 @@ +// 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) + +/* Register is R/W1C, it doesn't require locking. */ +#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) + +/* Register is R/W1C, it doesn't require locking. */ +#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; +} + +static struct pci_ops rzg3s_pcie_root_ops = { + .read = pci_generic_config_read, + .write = pci_generic_config_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) = {0}; + 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; + + 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); + + 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); + + /* Disable access control to the CFGU */ + writel_relaxed(0, host->axi + RZG3S_PCI_PERM); + + /* 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); + + 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 __free(device_node) = + 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 13ca493d22bd..d38f27e20761 100644 --- a/drivers/pci/controller/pcie-xilinx-cpm.c +++ b/drivers/pci/controller/pcie-xilinx-cpm.c @@ -395,17 +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; 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 8d6e2a89b067..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); diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c index 0b534f73a942..4aa139abac16 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); @@ -264,41 +260,52 @@ 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; } return 0; } -static void xilinx_free_msi_domains(struct xilinx_pcie *pcie) +static void xilinx_free_irq_domains(struct xilinx_pcie *pcie) { - struct irq_domain *parent = pcie->msi_domain->parent; - irq_domain_remove(pcie->msi_domain); - irq_domain_remove(parent); + irq_domain_remove(pcie->leg_domain); } /* INTx Functions */ @@ -394,7 +401,7 @@ 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 +468,8 @@ 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"); @@ -475,8 +481,10 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie *pcie) phys_addr_t pa = ALIGN_DOWN(virt_to_phys(pcie), SZ_4K); ret = xilinx_allocate_msi_domains(pcie); - if (ret) + if (ret) { + irq_domain_remove(pcie->leg_domain); return ret; + } pcie_write(pcie, upper_32_bits(pa), XILINX_PCIE_REG_MSIBASE1); pcie_write(pcie, lower_32_bits(pa), XILINX_PCIE_REG_MSIBASE2); @@ -595,7 +603,7 @@ static int xilinx_pcie_probe(struct platform_device *pdev) err = pci_host_probe(bridge); if (err) - xilinx_free_msi_domains(pcie); + xilinx_free_irq_domains(pcie); return err; } 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 3fdfffdf0270..24bbf93b8051 100644 --- a/drivers/pci/controller/plda/pcie-microchip-host.c +++ b/drivers/pci/controller/plda/pcie-microchip-host.c @@ -23,6 +23,7 @@ #include <linux/wordpart.h> #include "../../pci.h" +#include "../pci-host-common.h" #include "pcie-plda.h" #define MC_MAX_NUM_INBOUND_WINDOWS 8 diff --git a/drivers/pci/controller/plda/pcie-plda-host.c b/drivers/pci/controller/plda/pcie-plda-host.c index 4153214ca410..3c2f68383010 100644 --- a/drivers/pci/controller/plda/pcie-plda-host.c +++ b/drivers/pci/controller/plda/pcie-plda-host.c @@ -11,6 +11,7 @@ #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> @@ -134,43 +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; } @@ -393,10 +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); @@ -405,8 +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); @@ -565,7 +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); @@ -602,8 +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 61ece26065ea..6b8665df7bf0 100644 --- a/drivers/pci/controller/plda/pcie-plda.h +++ b/drivers/pci/controller/plda/pcie-plda.h @@ -164,7 +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; diff --git a/drivers/pci/controller/plda/pcie-starfive.c b/drivers/pci/controller/plda/pcie-starfive.c index e73c1b7bc8ef..298036c3e7f9 100644 --- a/drivers/pci/controller/plda/pcie-starfive.c +++ b/drivers/pci/controller/plda/pcie-starfive.c @@ -55,7 +55,7 @@ struct starfive_jh7110_pcie { struct reset_control *resets; struct clk_bulk_data *clks; struct regmap *reg_syscon; - struct gpio_desc *power_gpio; + struct regulator *vpcie3v3; struct gpio_desc *reset_gpio; struct phy *phy; @@ -153,11 +153,13 @@ static int starfive_pcie_parse_dt(struct starfive_jh7110_pcie *pcie, return dev_err_probe(dev, PTR_ERR(pcie->reset_gpio), "failed to get perst-gpio\n"); - pcie->power_gpio = devm_gpiod_get_optional(dev, "enable", - GPIOD_OUT_LOW); - if (IS_ERR(pcie->power_gpio)) - return dev_err_probe(dev, PTR_ERR(pcie->power_gpio), - "failed to get power-gpio\n"); + pcie->vpcie3v3 = devm_regulator_get_optional(dev, "vpcie3v3"); + if (IS_ERR(pcie->vpcie3v3)) { + if (PTR_ERR(pcie->vpcie3v3) != -ENODEV) + return dev_err_probe(dev, PTR_ERR(pcie->vpcie3v3), + "failed to get vpcie3v3 regulator\n"); + pcie->vpcie3v3 = NULL; + } return 0; } @@ -270,8 +272,8 @@ static void starfive_pcie_host_deinit(struct plda_pcie_rp *plda) container_of(plda, struct starfive_jh7110_pcie, plda); starfive_pcie_clk_rst_deinit(pcie); - if (pcie->power_gpio) - gpiod_set_value_cansleep(pcie->power_gpio, 0); + if (pcie->vpcie3v3) + regulator_disable(pcie->vpcie3v3); starfive_pcie_disable_phy(pcie); } @@ -304,8 +306,11 @@ static int starfive_pcie_host_init(struct plda_pcie_rp *plda) if (ret) return ret; - if (pcie->power_gpio) - gpiod_set_value_cansleep(pcie->power_gpio, 1); + if (pcie->vpcie3v3) { + ret = regulator_enable(pcie->vpcie3v3); + if (ret) + dev_err_probe(dev, ret, "failed to enable vpcie3v3 regulator\n"); + } if (pcie->reset_gpio) gpiod_set_value_cansleep(pcie->reset_gpio, 1); @@ -368,7 +373,7 @@ 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"); diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c index 8df064b62a2f..d4ae250d4bc6 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> @@ -174,58 +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) @@ -242,113 +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_obj(*vmdirq); + 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); - - /* XXX: Potential optimization to rebalance */ - raw_spin_lock_irqsave(&list_lock, flags); - vmdirq->irq->count--; - raw_spin_unlock_irqrestore(&list_lock, flags); + struct irq_data *irq_data; + struct vmd_irq *vmdirq; - kfree(vmdirq); -} + for (int i = 0; i < nr_irqs; ++i) { + irq_data = irq_domain_get_irq_data(domain, virq + i); + vmdirq = irq_data->chip_data; -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); + synchronize_srcu(&vmdirq->irq->srcu); - if (nvec > vmd->msix_count) - return vmd->msix_count; + /* XXX: Potential optimization to rebalance */ + scoped_guard(raw_spinlock_irq, &list_lock) + vmdirq->irq->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) { /* @@ -387,29 +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; - raw_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; } - raw_spin_unlock_irqrestore(&vmd->cfg_lock, flags); - return ret; } /* @@ -422,32 +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; - raw_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; } - raw_spin_unlock_irqrestore(&vmd->cfg_lock, flags); - return ret; } static struct pci_ops vmd_ops = { @@ -565,22 +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) @@ -865,13 +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 @@ -889,12 +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); } @@ -903,9 +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; @@ -998,6 +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; @@ -1063,6 +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) @@ -1129,6 +1130,8 @@ static const struct pci_device_id vmd_ids[] = { .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); diff --git a/drivers/pci/devres.c b/drivers/pci/devres.c index 73047316889e..f075e7881c3a 100644 --- a/drivers/pci/devres.c +++ b/drivers/pci/devres.c @@ -6,30 +6,13 @@ /* * On the state of PCI's devres implementation: * - * The older devres API for PCI has two significant problems: + * The older PCI devres API has one significant problem: * - * 1. It is very strongly tied to the statically allocated mapping table in - * struct pcim_iomap_devres below. This is mostly solved in the sense of the - * pcim_ functions in this file providing things like ranged mapping by - * bypassing this table, whereas the functions that were present in the old - * API still enter the mapping addresses into the table for users of the old - * API. - * - * 2. The region-request-functions in pci.c do become managed IF the device has - * been enabled with pcim_enable_device() instead of pci_enable_device(). - * This resulted in the API becoming inconsistent: Some functions have an - * obviously managed counter-part (e.g., pci_iomap() <-> pcim_iomap()), - * whereas some don't and are never managed, while others don't and are - * _sometimes_ managed (e.g. pci_request_region()). - * - * Consequently, in the new API, region requests performed by the pcim_ - * functions are automatically cleaned up through the devres callback - * pcim_addr_resource_release(). - * - * Users of pcim_enable_device() + pci_*region*() are redirected in - * pci.c to the managed functions here in this file. This isn't exactly - * perfect, but the only alternative way would be to port ALL drivers - * using said combination to pcim_ functions. + * It is very strongly tied to the statically allocated mapping table in struct + * pcim_iomap_devres below. This is mostly solved in the sense of the pcim_ + * functions in this file providing things like ranged mapping by bypassing + * this table, whereas the functions that were present in the old API still + * enter the mapping addresses into the table for users of the old API. * * TODO: * Remove the legacy table entirely once all calls to pcim_iomap_table() in @@ -87,104 +70,6 @@ static inline void pcim_addr_devres_clear(struct pcim_addr_devres *res) res->bar = -1; } -/* - * The following functions, __pcim_*_region*, exist as counterparts to the - * versions from pci.c - which, unfortunately, can be in "hybrid mode", i.e., - * sometimes managed, sometimes not. - * - * To separate the APIs cleanly, we define our own, simplified versions here. - */ - -/** - * __pcim_request_region_range - Request a ranged region - * @pdev: PCI device the region belongs to - * @bar: BAR the range is within - * @offset: offset from the BAR's start address - * @maxlen: length in bytes, beginning at @offset - * @name: name of the driver requesting the resource - * @req_flags: flags for the request, e.g., for kernel-exclusive requests - * - * Returns: 0 on success, a negative error code on failure. - * - * Request a range within a device's PCI BAR. Sanity check the input. - */ -static int __pcim_request_region_range(struct pci_dev *pdev, int bar, - unsigned long offset, - unsigned long maxlen, - const char *name, int req_flags) -{ - resource_size_t start = pci_resource_start(pdev, bar); - resource_size_t len = pci_resource_len(pdev, bar); - unsigned long dev_flags = pci_resource_flags(pdev, bar); - - if (start == 0 || len == 0) /* Unused BAR. */ - return 0; - if (len <= offset) - return -EINVAL; - - start += offset; - len -= offset; - - if (len > maxlen && maxlen != 0) - len = maxlen; - - if (dev_flags & IORESOURCE_IO) { - if (!request_region(start, len, name)) - return -EBUSY; - } else if (dev_flags & IORESOURCE_MEM) { - if (!__request_mem_region(start, len, name, req_flags)) - return -EBUSY; - } else { - /* That's not a device we can request anything on. */ - return -ENODEV; - } - - return 0; -} - -static void __pcim_release_region_range(struct pci_dev *pdev, int bar, - unsigned long offset, - unsigned long maxlen) -{ - resource_size_t start = pci_resource_start(pdev, bar); - resource_size_t len = pci_resource_len(pdev, bar); - unsigned long flags = pci_resource_flags(pdev, bar); - - if (len <= offset || start == 0) - return; - - if (len == 0 || maxlen == 0) /* This an unused BAR. Do nothing. */ - return; - - start += offset; - len -= offset; - - if (len > maxlen) - len = maxlen; - - if (flags & IORESOURCE_IO) - release_region(start, len); - else if (flags & IORESOURCE_MEM) - release_mem_region(start, len); -} - -static int __pcim_request_region(struct pci_dev *pdev, int bar, - const char *name, int flags) -{ - unsigned long offset = 0; - unsigned long len = pci_resource_len(pdev, bar); - - return __pcim_request_region_range(pdev, bar, offset, len, name, flags); -} - -static void __pcim_release_region(struct pci_dev *pdev, int bar) -{ - unsigned long offset = 0; - unsigned long len = pci_resource_len(pdev, bar); - - __pcim_release_region_range(pdev, bar, offset, len); -} - static void pcim_addr_resource_release(struct device *dev, void *resource_raw) { struct pci_dev *pdev = to_pci_dev(dev); @@ -192,11 +77,11 @@ static void pcim_addr_resource_release(struct device *dev, void *resource_raw) switch (res->type) { case PCIM_ADDR_DEVRES_TYPE_REGION: - __pcim_release_region(pdev, res->bar); + pci_release_region(pdev, res->bar); break; case PCIM_ADDR_DEVRES_TYPE_REGION_MAPPING: pci_iounmap(pdev, res->baseaddr); - __pcim_release_region(pdev, res->bar); + pci_release_region(pdev, res->bar); break; case PCIM_ADDR_DEVRES_TYPE_MAPPING: pci_iounmap(pdev, res->baseaddr); @@ -584,9 +469,6 @@ static int pcim_add_mapping_to_legacy_table(struct pci_dev *pdev, if (!legacy_iomap_table) return -ENOMEM; - /* The legacy mechanism doesn't allow for duplicate mappings. */ - WARN_ON(legacy_iomap_table[bar]); - legacy_iomap_table[bar] = mapping; return 0; @@ -735,7 +617,7 @@ void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar, res->type = PCIM_ADDR_DEVRES_TYPE_REGION_MAPPING; res->bar = bar; - ret = __pcim_request_region(pdev, bar, name, 0); + ret = pci_request_region(pdev, bar, name); if (ret != 0) goto err_region; @@ -749,7 +631,7 @@ void __iomem *pcim_iomap_region(struct pci_dev *pdev, int bar, return res->baseaddr; err_iomap: - __pcim_release_region(pdev, bar); + pci_release_region(pdev, bar); err_region: pcim_addr_devres_free(res); @@ -823,8 +705,20 @@ err: } EXPORT_SYMBOL(pcim_iomap_regions); -static int _pcim_request_region(struct pci_dev *pdev, int bar, const char *name, - int request_flags) +/** + * pcim_request_region - Request a PCI BAR + * @pdev: PCI device to request region for + * @bar: Index of BAR to request + * @name: Name of the driver requesting the resource + * + * Returns: 0 on success, a negative error code on failure. + * + * Request region specified by @bar. + * + * The region will automatically be released on driver detach. If desired, + * release manually only with pcim_release_region(). + */ +int pcim_request_region(struct pci_dev *pdev, int bar, const char *name) { int ret; struct pcim_addr_devres *res; @@ -838,7 +732,7 @@ static int _pcim_request_region(struct pci_dev *pdev, int bar, const char *name, res->type = PCIM_ADDR_DEVRES_TYPE_REGION; res->bar = bar; - ret = __pcim_request_region(pdev, bar, name, request_flags); + ret = pci_request_region(pdev, bar, name); if (ret != 0) { pcim_addr_devres_free(res); return ret; @@ -847,45 +741,9 @@ static int _pcim_request_region(struct pci_dev *pdev, int bar, const char *name, devres_add(&pdev->dev, res); return 0; } - -/** - * pcim_request_region - Request a PCI BAR - * @pdev: PCI device to request region for - * @bar: Index of BAR to request - * @name: Name of the driver requesting the resource - * - * Returns: 0 on success, a negative error code on failure. - * - * Request region specified by @bar. - * - * The region will automatically be released on driver detach. If desired, - * release manually only with pcim_release_region(). - */ -int pcim_request_region(struct pci_dev *pdev, int bar, const char *name) -{ - return _pcim_request_region(pdev, bar, name, 0); -} EXPORT_SYMBOL(pcim_request_region); /** - * pcim_request_region_exclusive - Request a PCI BAR exclusively - * @pdev: PCI device to request region for - * @bar: Index of BAR to request - * @name: Name of the driver requesting the resource - * - * Returns: 0 on success, a negative error code on failure. - * - * Request region specified by @bar exclusively. - * - * The region will automatically be released on driver detach. If desired, - * release manually only with pcim_release_region(). - */ -int pcim_request_region_exclusive(struct pci_dev *pdev, int bar, const char *name) -{ - return _pcim_request_region(pdev, bar, name, IORESOURCE_EXCLUSIVE); -} - -/** * pcim_release_region - Release a PCI BAR * @pdev: PCI device to operate on * @bar: Index of BAR to release @@ -893,7 +751,7 @@ int pcim_request_region_exclusive(struct pci_dev *pdev, int bar, const char *nam * Release a region manually that was previously requested by * pcim_request_region(). */ -void pcim_release_region(struct pci_dev *pdev, int bar) +static void pcim_release_region(struct pci_dev *pdev, int bar) { struct pcim_addr_devres res_searched; @@ -956,30 +814,6 @@ err: EXPORT_SYMBOL(pcim_request_all_regions); /** - * pcim_iounmap_regions - Unmap and release PCI BARs (DEPRECATED) - * @pdev: PCI device to map IO resources for - * @mask: Mask of BARs to unmap and release - * - * Unmap and release regions specified by @mask. - * - * This function is DEPRECATED. Do not use it in new code. - * Use pcim_iounmap_region() instead. - */ -void pcim_iounmap_regions(struct pci_dev *pdev, int mask) -{ - int i; - - for (i = 0; i < PCI_STD_NUM_BARS; i++) { - if (!mask_contains_bar(mask, i)) - continue; - - pcim_iounmap_region(pdev, i); - pcim_remove_bar_from_legacy_table(pdev, i); - } -} -EXPORT_SYMBOL(pcim_iounmap_regions); - -/** * pcim_iomap_range - Create a ranged __iomap mapping within a PCI BAR * @pdev: PCI device to map IO resources for * @bar: Index of the BAR diff --git a/drivers/pci/doe.c b/drivers/pci/doe.c index aae9a8a00406..7b41da4ec11a 100644 --- a/drivers/pci/doe.c +++ b/drivers/pci/doe.c @@ -24,8 +24,6 @@ #include "pci.h" -#define PCI_DOE_FEATURE_DISCOVERY 0 - /* Timeout of 1 second from 6.30.2 Operation, PCI Spec r6.0 */ #define PCI_DOE_TIMEOUT HZ #define PCI_DOE_POLL_INTERVAL (PCI_DOE_TIMEOUT / 128) @@ -169,7 +167,7 @@ static int pci_doe_sysfs_feature_populate(struct pci_dev *pdev, xa_for_each(&doe_mb->feats, i, entry) num_features++; - attrs = kcalloc(num_features, sizeof(*attrs), GFP_KERNEL); + attrs = kzalloc_objs(*attrs, num_features); if (!attrs) { pci_warn(pdev, "Failed allocating the device_attribute array\n"); return -ENOMEM; @@ -643,7 +641,7 @@ static struct pci_doe_mb *pci_doe_create_mb(struct pci_dev *pdev, struct pci_doe_mb *doe_mb; int rc; - doe_mb = kzalloc(sizeof(*doe_mb), GFP_KERNEL); + doe_mb = kzalloc_obj(*doe_mb); if (!doe_mb) return ERR_PTR(-ENOMEM); diff --git a/drivers/pci/ecam.c b/drivers/pci/ecam.c index 260b7de2dbd5..119de32ff07b 100644 --- a/drivers/pci/ecam.c +++ b/drivers/pci/ecam.c @@ -37,7 +37,7 @@ struct pci_config_window *pci_ecam_create(struct device *dev, if (busr->start > busr->end) return ERR_PTR(-EINVAL); - cfg = kzalloc(sizeof(*cfg), GFP_KERNEL); + cfg = kzalloc_obj(*cfg); if (!cfg) return ERR_PTR(-ENOMEM); @@ -75,7 +75,7 @@ struct pci_config_window *pci_ecam_create(struct device *dev, } if (per_bus_mapping) { - cfg->winp = kcalloc(bus_range, sizeof(*cfg->winp), GFP_KERNEL); + cfg->winp = kzalloc_objs(*cfg->winp, bus_range); if (!cfg->winp) goto err_exit_malloc; } else { diff --git a/drivers/pci/endpoint/Kconfig b/drivers/pci/endpoint/Kconfig index 1c5d82eb57d4..8dad291be8b8 100644 --- a/drivers/pci/endpoint/Kconfig +++ b/drivers/pci/endpoint/Kconfig @@ -28,6 +28,14 @@ config PCI_ENDPOINT_CONFIGFS configure the endpoint function and used to bind the function with an endpoint controller. +config PCI_ENDPOINT_MSI_DOORBELL + bool "PCI Endpoint MSI Doorbell Support" + depends on PCI_ENDPOINT && GENERIC_MSI_IRQ + help + This enables the EP's MSI interrupt controller to function as a + doorbell. The RC can trigger doorbell in EP by writing data to a + dedicated BAR, which the EP maps to the controller's message address. + source "drivers/pci/endpoint/functions/Kconfig" endmenu diff --git a/drivers/pci/endpoint/Makefile b/drivers/pci/endpoint/Makefile index 95b2fe47e3b0..b4869d52053a 100644 --- a/drivers/pci/endpoint/Makefile +++ b/drivers/pci/endpoint/Makefile @@ -6,3 +6,4 @@ obj-$(CONFIG_PCI_ENDPOINT_CONFIGFS) += pci-ep-cfs.o obj-$(CONFIG_PCI_ENDPOINT) += pci-epc-core.o pci-epf-core.o\ pci-epc-mem.o functions/ +obj-$(CONFIG_PCI_ENDPOINT_MSI_DOORBELL) += pci-ep-msi.o diff --git a/drivers/pci/endpoint/functions/Kconfig b/drivers/pci/endpoint/functions/Kconfig index 0c9cea0698d7..bb5a23994288 100644 --- a/drivers/pci/endpoint/functions/Kconfig +++ b/drivers/pci/endpoint/functions/Kconfig @@ -6,6 +6,7 @@ config PCI_EPF_TEST tristate "PCI Endpoint Test driver" depends on PCI_ENDPOINT + select CONFIGFS_FS select CRC32 help Enable this configuration option to enable the test driver diff --git a/drivers/pci/endpoint/functions/pci-epf-mhi.c b/drivers/pci/endpoint/functions/pci-epf-mhi.c index 6643a88c7a0c..f9cf18aa5b34 100644 --- a/drivers/pci/endpoint/functions/pci-epf-mhi.c +++ b/drivers/pci/endpoint/functions/pci-epf-mhi.c @@ -525,7 +525,7 @@ static int pci_epf_mhi_edma_read_async(struct mhi_ep_cntrl *mhi_cntrl, goto err_unmap; } - transfer = kzalloc(sizeof(*transfer), GFP_KERNEL); + transfer = kzalloc_obj(*transfer); if (!transfer) { ret = -ENOMEM; goto err_unmap; @@ -604,7 +604,7 @@ static int pci_epf_mhi_edma_write_async(struct mhi_ep_cntrl *mhi_cntrl, goto err_unmap; } - transfer = kzalloc(sizeof(*transfer), GFP_KERNEL); + transfer = kzalloc_obj(*transfer); if (!transfer) { ret = -ENOMEM; goto err_unmap; @@ -686,7 +686,7 @@ static int pci_epf_mhi_dma_init(struct pci_epf_mhi *epf_mhi) goto err_release_tx; } - epf_mhi->dma_wq = alloc_workqueue("pci_epf_mhi_dma_wq", 0, 0); + epf_mhi->dma_wq = alloc_workqueue("pci_epf_mhi_dma_wq", WQ_PERCPU, 0); if (!epf_mhi->dma_wq) { ret = -ENOMEM; goto err_release_rx; diff --git a/drivers/pci/endpoint/functions/pci-epf-ntb.c b/drivers/pci/endpoint/functions/pci-epf-ntb.c index e01a98e74d21..a3a588e522e7 100644 --- a/drivers/pci/endpoint/functions/pci-epf-ntb.c +++ b/drivers/pci/endpoint/functions/pci-epf-ntb.c @@ -2124,8 +2124,13 @@ static int __init epf_ntb_init(void) { int ret; - kpcintb_workqueue = alloc_workqueue("kpcintb", WQ_MEM_RECLAIM | - WQ_HIGHPRI, 0); + kpcintb_workqueue = alloc_workqueue("kpcintb", + WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU, 0); + if (!kpcintb_workqueue) { + pr_err("Failed to allocate kpcintb workqueue\n"); + return -ENOMEM; + } + ret = pci_epf_register_driver(&epf_ntb_driver); if (ret) { destroy_workqueue(kpcintb_workqueue); diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c index 50eb4106369f..582938b7b4f1 100644 --- a/drivers/pci/endpoint/functions/pci-epf-test.c +++ b/drivers/pci/endpoint/functions/pci-epf-test.c @@ -11,12 +11,14 @@ #include <linux/dmaengine.h> #include <linux/io.h> #include <linux/module.h> +#include <linux/msi.h> #include <linux/slab.h> #include <linux/pci_ids.h> #include <linux/random.h> #include <linux/pci-epc.h> #include <linux/pci-epf.h> +#include <linux/pci-ep-msi.h> #include <linux/pci_regs.h> #define IRQ_TYPE_INTX 0 @@ -29,6 +31,10 @@ #define COMMAND_READ BIT(3) #define COMMAND_WRITE BIT(4) #define COMMAND_COPY BIT(5) +#define COMMAND_ENABLE_DOORBELL BIT(6) +#define COMMAND_DISABLE_DOORBELL BIT(7) +#define COMMAND_BAR_SUBRANGE_SETUP BIT(8) +#define COMMAND_BAR_SUBRANGE_CLEAR BIT(9) #define STATUS_READ_SUCCESS BIT(0) #define STATUS_READ_FAIL BIT(1) @@ -39,6 +45,15 @@ #define STATUS_IRQ_RAISED BIT(6) #define STATUS_SRC_ADDR_INVALID BIT(7) #define STATUS_DST_ADDR_INVALID BIT(8) +#define STATUS_DOORBELL_SUCCESS BIT(9) +#define STATUS_DOORBELL_ENABLE_SUCCESS BIT(10) +#define STATUS_DOORBELL_ENABLE_FAIL BIT(11) +#define STATUS_DOORBELL_DISABLE_SUCCESS BIT(12) +#define STATUS_DOORBELL_DISABLE_FAIL BIT(13) +#define STATUS_BAR_SUBRANGE_SETUP_SUCCESS BIT(14) +#define STATUS_BAR_SUBRANGE_SETUP_FAIL BIT(15) +#define STATUS_BAR_SUBRANGE_CLEAR_SUCCESS BIT(16) +#define STATUS_BAR_SUBRANGE_CLEAR_FAIL BIT(17) #define FLAG_USE_DMA BIT(0) @@ -48,12 +63,16 @@ #define CAP_MSI BIT(1) #define CAP_MSIX BIT(2) #define CAP_INTX BIT(3) +#define CAP_SUBRANGE_MAPPING BIT(4) + +#define PCI_EPF_TEST_BAR_SUBRANGE_NSUB 2 static struct workqueue_struct *kpcitest_workqueue; struct pci_epf_test { void *reg[PCI_STD_NUM_BARS]; struct pci_epf *epf; + struct config_group group; enum pci_barno test_reg_bar; size_t msix_table_offset; struct delayed_work cmd_handler; @@ -66,6 +85,8 @@ struct pci_epf_test { bool dma_supported; bool dma_private; const struct pci_epc_features *epc_features; + struct pci_epf_bar db_bar; + size_t bar_size[PCI_STD_NUM_BARS]; }; struct pci_epf_test_reg { @@ -80,6 +101,9 @@ struct pci_epf_test_reg { __le32 irq_number; __le32 flags; __le32 caps; + __le32 doorbell_bar; + __le32 doorbell_offset; + __le32 doorbell_data; } __packed; static struct pci_epf_header test_header = { @@ -89,7 +113,8 @@ static struct pci_epf_header test_header = { .interrupt_pin = PCI_INTERRUPT_INTA, }; -static size_t bar_size[] = { 512, 512, 1024, 16384, 131072, 1048576 }; +/* default BAR sizes, can be overridden by the user using configfs */ +static size_t default_bar_size[] = { 131072, 131072, 131072, 131072, 131072, 1048576 }; static void pci_epf_test_dma_callback(void *param) { @@ -288,15 +313,20 @@ static void pci_epf_test_clean_dma_chan(struct pci_epf_test *epf_test) if (!epf_test->dma_supported) return; - dma_release_channel(epf_test->dma_chan_tx); - if (epf_test->dma_chan_tx == epf_test->dma_chan_rx) { + if (epf_test->dma_chan_tx) { + dma_release_channel(epf_test->dma_chan_tx); + if (epf_test->dma_chan_tx == epf_test->dma_chan_rx) { + epf_test->dma_chan_tx = NULL; + epf_test->dma_chan_rx = NULL; + return; + } epf_test->dma_chan_tx = NULL; - epf_test->dma_chan_rx = NULL; - return; } - dma_release_channel(epf_test->dma_chan_rx); - epf_test->dma_chan_rx = NULL; + if (epf_test->dma_chan_rx) { + dma_release_channel(epf_test->dma_chan_rx); + epf_test->dma_chan_rx = NULL; + } } static void pci_epf_test_print_rate(struct pci_epf_test *epf_test, @@ -313,9 +343,8 @@ static void pci_epf_test_print_rate(struct pci_epf_test *epf_test, rate = div64_u64(size * NSEC_PER_SEC, ns * 1000); dev_info(&epf_test->epf->dev, - "%s => Size: %llu B, DMA: %s, Time: %llu.%09u s, Rate: %llu KB/s\n", - op, size, dma ? "YES" : "NO", - (u64)ts.tv_sec, (u32)ts.tv_nsec, rate); + "%s => Size: %llu B, DMA: %s, Time: %ptSp s, Rate: %llu KB/s\n", + op, size, dma ? "YES" : "NO", &ts, rate); } static void pci_epf_test_copy(struct pci_epf_test *epf_test, @@ -667,6 +696,277 @@ static void pci_epf_test_raise_irq(struct pci_epf_test *epf_test, } } +static irqreturn_t pci_epf_test_doorbell_handler(int irq, void *data) +{ + struct pci_epf_test *epf_test = data; + enum pci_barno test_reg_bar = epf_test->test_reg_bar; + struct pci_epf_test_reg *reg = epf_test->reg[test_reg_bar]; + u32 status = le32_to_cpu(reg->status); + + status |= STATUS_DOORBELL_SUCCESS; + reg->status = cpu_to_le32(status); + pci_epf_test_raise_irq(epf_test, reg); + + return IRQ_HANDLED; +} + +static void pci_epf_test_doorbell_cleanup(struct pci_epf_test *epf_test) +{ + struct pci_epf_test_reg *reg = epf_test->reg[epf_test->test_reg_bar]; + struct pci_epf *epf = epf_test->epf; + + free_irq(epf->db_msg[0].virq, epf_test); + reg->doorbell_bar = cpu_to_le32(NO_BAR); + + pci_epf_free_doorbell(epf); +} + +static void pci_epf_test_enable_doorbell(struct pci_epf_test *epf_test, + struct pci_epf_test_reg *reg) +{ + u32 status = le32_to_cpu(reg->status); + struct pci_epf *epf = epf_test->epf; + struct pci_epc *epc = epf->epc; + struct msi_msg *msg; + enum pci_barno bar; + size_t offset; + int ret; + + ret = pci_epf_alloc_doorbell(epf, 1); + if (ret) + goto set_status_err; + + msg = &epf->db_msg[0].msg; + bar = pci_epc_get_next_free_bar(epf_test->epc_features, epf_test->test_reg_bar + 1); + if (bar < BAR_0) + goto err_doorbell_cleanup; + + ret = request_threaded_irq(epf->db_msg[0].virq, NULL, + pci_epf_test_doorbell_handler, IRQF_ONESHOT, + "pci-ep-test-doorbell", epf_test); + if (ret) { + dev_err(&epf->dev, + "Failed to request doorbell IRQ: %d\n", + epf->db_msg[0].virq); + goto err_doorbell_cleanup; + } + + reg->doorbell_data = cpu_to_le32(msg->data); + reg->doorbell_bar = cpu_to_le32(bar); + + msg = &epf->db_msg[0].msg; + ret = pci_epf_align_inbound_addr(epf, bar, ((u64)msg->address_hi << 32) | msg->address_lo, + &epf_test->db_bar.phys_addr, &offset); + + if (ret) + goto err_doorbell_cleanup; + + reg->doorbell_offset = cpu_to_le32(offset); + + epf_test->db_bar.barno = bar; + epf_test->db_bar.size = epf->bar[bar].size; + epf_test->db_bar.flags = epf->bar[bar].flags; + + ret = pci_epc_set_bar(epc, epf->func_no, epf->vfunc_no, &epf_test->db_bar); + if (ret) + goto err_doorbell_cleanup; + + status |= STATUS_DOORBELL_ENABLE_SUCCESS; + reg->status = cpu_to_le32(status); + return; + +err_doorbell_cleanup: + pci_epf_test_doorbell_cleanup(epf_test); +set_status_err: + status |= STATUS_DOORBELL_ENABLE_FAIL; + reg->status = cpu_to_le32(status); +} + +static void pci_epf_test_disable_doorbell(struct pci_epf_test *epf_test, + struct pci_epf_test_reg *reg) +{ + enum pci_barno bar = le32_to_cpu(reg->doorbell_bar); + u32 status = le32_to_cpu(reg->status); + struct pci_epf *epf = epf_test->epf; + struct pci_epc *epc = epf->epc; + int ret; + + if (bar < BAR_0) + goto set_status_err; + + pci_epf_test_doorbell_cleanup(epf_test); + + /* + * The doorbell feature temporarily overrides the inbound translation + * to point to the address stored in epf_test->db_bar.phys_addr, i.e., + * it calls set_bar() twice without ever calling clear_bar(), as + * calling clear_bar() would clear the BAR's PCI address assigned by + * the host. Thus, when disabling the doorbell, restore the inbound + * translation to point to the memory allocated for the BAR. + */ + ret = pci_epc_set_bar(epc, epf->func_no, epf->vfunc_no, &epf->bar[bar]); + if (ret) + goto set_status_err; + + status |= STATUS_DOORBELL_DISABLE_SUCCESS; + reg->status = cpu_to_le32(status); + + return; + +set_status_err: + status |= STATUS_DOORBELL_DISABLE_FAIL; + reg->status = cpu_to_le32(status); +} + +static u8 pci_epf_test_subrange_sig_byte(enum pci_barno barno, + unsigned int subno) +{ + return 0x50 + (barno * 8) + subno; +} + +static void pci_epf_test_bar_subrange_setup(struct pci_epf_test *epf_test, + struct pci_epf_test_reg *reg) +{ + struct pci_epf_bar_submap *submap, *old_submap; + struct pci_epf *epf = epf_test->epf; + struct pci_epc *epc = epf->epc; + struct pci_epf_bar *bar; + unsigned int nsub = PCI_EPF_TEST_BAR_SUBRANGE_NSUB, old_nsub; + /* reg->size carries BAR number for BAR_SUBRANGE_* commands. */ + enum pci_barno barno = le32_to_cpu(reg->size); + u32 status = le32_to_cpu(reg->status); + unsigned int i, phys_idx; + size_t sub_size; + u8 *addr; + int ret; + + if (barno >= PCI_STD_NUM_BARS) { + dev_err(&epf->dev, "Invalid barno: %d\n", barno); + goto err; + } + + /* Host side should've avoided test_reg_bar, this is a safeguard. */ + if (barno == epf_test->test_reg_bar) { + dev_err(&epf->dev, "test_reg_bar cannot be used for subrange test\n"); + goto err; + } + + if (!epf_test->epc_features->dynamic_inbound_mapping || + !epf_test->epc_features->subrange_mapping) { + dev_err(&epf->dev, "epc driver does not support subrange mapping\n"); + goto err; + } + + bar = &epf->bar[barno]; + if (!bar->size || !bar->addr) { + dev_err(&epf->dev, "bar size/addr (%zu/%p) is invalid\n", + bar->size, bar->addr); + goto err; + } + + if (bar->size % nsub) { + dev_err(&epf->dev, "BAR size %zu is not divisible by %u\n", + bar->size, nsub); + goto err; + } + + sub_size = bar->size / nsub; + + submap = kzalloc_objs(*submap, nsub); + if (!submap) + goto err; + + for (i = 0; i < nsub; i++) { + /* Swap the two halves so RC can verify ordering. */ + phys_idx = i ^ 1; + submap[i].phys_addr = bar->phys_addr + (phys_idx * sub_size); + submap[i].size = sub_size; + } + + old_submap = bar->submap; + old_nsub = bar->num_submap; + + bar->submap = submap; + bar->num_submap = nsub; + + ret = pci_epc_set_bar(epc, epf->func_no, epf->vfunc_no, bar); + if (ret) { + dev_err(&epf->dev, "pci_epc_set_bar() failed: %d\n", ret); + bar->submap = old_submap; + bar->num_submap = old_nsub; + kfree(submap); + goto err; + } + kfree(old_submap); + + /* + * Fill deterministic signatures into the physical regions that + * each BAR subrange maps to. RC verifies these to ensure the + * submap order is really applied. + */ + addr = (u8 *)bar->addr; + for (i = 0; i < nsub; i++) { + phys_idx = i ^ 1; + memset(addr + (phys_idx * sub_size), + pci_epf_test_subrange_sig_byte(barno, i), + sub_size); + } + + status |= STATUS_BAR_SUBRANGE_SETUP_SUCCESS; + reg->status = cpu_to_le32(status); + return; + +err: + status |= STATUS_BAR_SUBRANGE_SETUP_FAIL; + reg->status = cpu_to_le32(status); +} + +static void pci_epf_test_bar_subrange_clear(struct pci_epf_test *epf_test, + struct pci_epf_test_reg *reg) +{ + struct pci_epf *epf = epf_test->epf; + struct pci_epf_bar_submap *submap; + struct pci_epc *epc = epf->epc; + /* reg->size carries BAR number for BAR_SUBRANGE_* commands. */ + enum pci_barno barno = le32_to_cpu(reg->size); + u32 status = le32_to_cpu(reg->status); + struct pci_epf_bar *bar; + unsigned int nsub; + int ret; + + if (barno >= PCI_STD_NUM_BARS) { + dev_err(&epf->dev, "Invalid barno: %d\n", barno); + goto err; + } + + bar = &epf->bar[barno]; + submap = bar->submap; + nsub = bar->num_submap; + + if (!submap || !nsub) + goto err; + + bar->submap = NULL; + bar->num_submap = 0; + + ret = pci_epc_set_bar(epc, epf->func_no, epf->vfunc_no, bar); + if (ret) { + bar->submap = submap; + bar->num_submap = nsub; + dev_err(&epf->dev, "pci_epc_set_bar() failed: %d\n", ret); + goto err; + } + kfree(submap); + + status |= STATUS_BAR_SUBRANGE_CLEAR_SUCCESS; + reg->status = cpu_to_le32(status); + return; + +err: + status |= STATUS_BAR_SUBRANGE_CLEAR_FAIL; + reg->status = cpu_to_le32(status); +} + static void pci_epf_test_cmd_handler(struct work_struct *work) { u32 command; @@ -714,6 +1014,22 @@ static void pci_epf_test_cmd_handler(struct work_struct *work) pci_epf_test_copy(epf_test, reg); pci_epf_test_raise_irq(epf_test, reg); break; + case COMMAND_ENABLE_DOORBELL: + pci_epf_test_enable_doorbell(epf_test, reg); + pci_epf_test_raise_irq(epf_test, reg); + break; + case COMMAND_DISABLE_DOORBELL: + pci_epf_test_disable_doorbell(epf_test, reg); + pci_epf_test_raise_irq(epf_test, reg); + break; + case COMMAND_BAR_SUBRANGE_SETUP: + pci_epf_test_bar_subrange_setup(epf_test, reg); + pci_epf_test_raise_irq(epf_test, reg); + break; + case COMMAND_BAR_SUBRANGE_CLEAR: + pci_epf_test_bar_subrange_clear(epf_test, reg); + pci_epf_test_raise_irq(epf_test, reg); + break; default: dev_err(dev, "Invalid command 0x%x\n", command); break; @@ -786,6 +1102,10 @@ static void pci_epf_test_set_capabilities(struct pci_epf *epf) if (epf_test->epc_features->intx_capable) caps |= CAP_INTX; + if (epf_test->epc_features->dynamic_inbound_mapping && + epf_test->epc_features->subrange_mapping) + caps |= CAP_SUBRANGE_MAPPING; + reg->caps = cpu_to_le32(caps); } @@ -920,7 +1240,12 @@ static int pci_epf_test_alloc_space(struct pci_epf *epf) if (bar == test_reg_bar) continue; - base = pci_epf_alloc_space(epf, bar_size[bar], bar, + if (epc_features->bar[bar].type == BAR_FIXED) + test_reg_size = epc_features->bar[bar].fixed_size; + else + test_reg_size = epf_test->bar_size[bar]; + + base = pci_epf_alloc_space(epf, test_reg_size, bar, epc_features, PRIMARY_INTERFACE); if (!base) dev_err(dev, "Failed to allocate space for BAR%d\n", @@ -990,6 +1315,94 @@ static void pci_epf_test_unbind(struct pci_epf *epf) pci_epf_test_free_space(epf); } +#define PCI_EPF_TEST_BAR_SIZE_R(_name, _id) \ +static ssize_t pci_epf_test_##_name##_show(struct config_item *item, \ + char *page) \ +{ \ + struct config_group *group = to_config_group(item); \ + struct pci_epf_test *epf_test = \ + container_of(group, struct pci_epf_test, group); \ + \ + return sysfs_emit(page, "%zu\n", epf_test->bar_size[_id]); \ +} + +#define PCI_EPF_TEST_BAR_SIZE_W(_name, _id) \ +static ssize_t pci_epf_test_##_name##_store(struct config_item *item, \ + const char *page, \ + size_t len) \ +{ \ + struct config_group *group = to_config_group(item); \ + struct pci_epf_test *epf_test = \ + container_of(group, struct pci_epf_test, group); \ + int val, ret; \ + \ + /* \ + * BAR sizes can only be modified before binding to an EPC, \ + * because pci_epf_test_alloc_space() is called in .bind(). \ + */ \ + if (epf_test->epf->epc) \ + return -EOPNOTSUPP; \ + \ + ret = kstrtouint(page, 0, &val); \ + if (ret) \ + return ret; \ + \ + if (!is_power_of_2(val)) \ + return -EINVAL; \ + \ + epf_test->bar_size[_id] = val; \ + \ + return len; \ +} + +PCI_EPF_TEST_BAR_SIZE_R(bar0_size, BAR_0) +PCI_EPF_TEST_BAR_SIZE_W(bar0_size, BAR_0) +PCI_EPF_TEST_BAR_SIZE_R(bar1_size, BAR_1) +PCI_EPF_TEST_BAR_SIZE_W(bar1_size, BAR_1) +PCI_EPF_TEST_BAR_SIZE_R(bar2_size, BAR_2) +PCI_EPF_TEST_BAR_SIZE_W(bar2_size, BAR_2) +PCI_EPF_TEST_BAR_SIZE_R(bar3_size, BAR_3) +PCI_EPF_TEST_BAR_SIZE_W(bar3_size, BAR_3) +PCI_EPF_TEST_BAR_SIZE_R(bar4_size, BAR_4) +PCI_EPF_TEST_BAR_SIZE_W(bar4_size, BAR_4) +PCI_EPF_TEST_BAR_SIZE_R(bar5_size, BAR_5) +PCI_EPF_TEST_BAR_SIZE_W(bar5_size, BAR_5) + +CONFIGFS_ATTR(pci_epf_test_, bar0_size); +CONFIGFS_ATTR(pci_epf_test_, bar1_size); +CONFIGFS_ATTR(pci_epf_test_, bar2_size); +CONFIGFS_ATTR(pci_epf_test_, bar3_size); +CONFIGFS_ATTR(pci_epf_test_, bar4_size); +CONFIGFS_ATTR(pci_epf_test_, bar5_size); + +static struct configfs_attribute *pci_epf_test_attrs[] = { + &pci_epf_test_attr_bar0_size, + &pci_epf_test_attr_bar1_size, + &pci_epf_test_attr_bar2_size, + &pci_epf_test_attr_bar3_size, + &pci_epf_test_attr_bar4_size, + &pci_epf_test_attr_bar5_size, + NULL, +}; + +static const struct config_item_type pci_epf_test_group_type = { + .ct_attrs = pci_epf_test_attrs, + .ct_owner = THIS_MODULE, +}; + +static struct config_group *pci_epf_test_add_cfs(struct pci_epf *epf, + struct config_group *group) +{ + struct pci_epf_test *epf_test = epf_get_drvdata(epf); + struct config_group *epf_group = &epf_test->group; + struct device *dev = &epf->dev; + + config_group_init_type_name(epf_group, dev_name(dev), + &pci_epf_test_group_type); + + return epf_group; +} + static const struct pci_epf_device_id pci_epf_test_ids[] = { { .name = "pci_epf_test", @@ -1002,6 +1415,7 @@ static int pci_epf_test_probe(struct pci_epf *epf, { struct pci_epf_test *epf_test; struct device *dev = &epf->dev; + enum pci_barno bar; epf_test = devm_kzalloc(dev, sizeof(*epf_test), GFP_KERNEL); if (!epf_test) @@ -1009,6 +1423,8 @@ static int pci_epf_test_probe(struct pci_epf *epf, epf->header = &test_header; epf_test->epf = epf; + for (bar = BAR_0; bar < PCI_STD_NUM_BARS; bar++) + epf_test->bar_size[bar] = default_bar_size[bar]; INIT_DELAYED_WORK(&epf_test->cmd_handler, pci_epf_test_cmd_handler); @@ -1021,6 +1437,7 @@ static int pci_epf_test_probe(struct pci_epf *epf, static const struct pci_epf_ops ops = { .unbind = pci_epf_test_unbind, .bind = pci_epf_test_bind, + .add_cfs = pci_epf_test_add_cfs, }; static struct pci_epf_driver test_driver = { @@ -1036,7 +1453,7 @@ static int __init pci_epf_test_init(void) int ret; kpcitest_workqueue = alloc_workqueue("kpcitest", - WQ_MEM_RECLAIM | WQ_HIGHPRI, 0); + WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU, 0); if (!kpcitest_workqueue) { pr_err("Failed to allocate the kpcitest work queue\n"); return -ENOMEM; diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c index 874cb097b093..20a400e83439 100644 --- a/drivers/pci/endpoint/functions/pci-epf-vntb.c +++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c @@ -36,11 +36,13 @@ * PCIe Root Port PCI EP */ +#include <linux/atomic.h> #include <linux/delay.h> #include <linux/io.h> #include <linux/module.h> #include <linux/slab.h> +#include <linux/pci-ep-msi.h> #include <linux/pci-epc.h> #include <linux/pci-epf.h> #include <linux/ntb.h> @@ -70,9 +72,11 @@ static struct workqueue_struct *kpcintb_workqueue; enum epf_ntb_bar { BAR_CONFIG, BAR_DB, - BAR_MW0, BAR_MW1, BAR_MW2, + BAR_MW3, + BAR_MW4, + VNTB_BAR_NUM, }; /* @@ -124,15 +128,16 @@ struct epf_ntb { u32 db_count; u32 spad_count; u64 mws_size[MAX_MW]; - u64 db; + atomic64_t db; u32 vbus_number; u16 vntb_pid; u16 vntb_vid; bool linkup; + bool msi_doorbell; u32 spad_size; - enum pci_barno epf_ntb_bar[6]; + enum pci_barno epf_ntb_bar[VNTB_BAR_NUM]; struct epf_ntb_ctrl *reg; @@ -256,9 +261,9 @@ static void epf_ntb_cmd_handler(struct work_struct *work) ntb = container_of(work, struct epf_ntb, cmd_handler.work); - for (i = 1; i < ntb->db_count; i++) { + for (i = 1; i < ntb->db_count && !ntb->msi_doorbell; i++) { if (ntb->epf_db[i]) { - ntb->db |= 1 << (i - 1); + atomic64_or(1 << (i - 1), &ntb->db); ntb_db_event(&ntb->ntb, i); ntb->epf_db[i] = 0; } @@ -317,7 +322,21 @@ static void epf_ntb_cmd_handler(struct work_struct *work) reset_handler: queue_delayed_work(kpcintb_workqueue, &ntb->cmd_handler, - msecs_to_jiffies(5)); + ntb->msi_doorbell ? msecs_to_jiffies(500) : msecs_to_jiffies(5)); +} + +static irqreturn_t epf_ntb_doorbell_handler(int irq, void *data) +{ + struct epf_ntb *ntb = data; + int i; + + for (i = 1; i < ntb->db_count; i++) + if (irq == ntb->epf->db_msg[i].virq) { + atomic64_or(1 << (i - 1), &ntb->db); + ntb_db_event(&ntb->ntb, i); + } + + return IRQ_HANDLED; } /** @@ -408,11 +427,9 @@ static void epf_ntb_config_spad_bar_free(struct epf_ntb *ntb) */ static int epf_ntb_config_spad_bar_alloc(struct epf_ntb *ntb) { - size_t align; enum pci_barno barno; struct epf_ntb_ctrl *ctrl; u32 spad_size, ctrl_size; - u64 size; struct pci_epf *epf = ntb->epf; struct device *dev = &epf->dev; u32 spad_count; @@ -422,31 +439,13 @@ static int epf_ntb_config_spad_bar_alloc(struct epf_ntb *ntb) epf->func_no, epf->vfunc_no); barno = ntb->epf_ntb_bar[BAR_CONFIG]; - size = epc_features->bar[barno].fixed_size; - align = epc_features->align; - - if ((!IS_ALIGNED(size, align))) - return -EINVAL; - spad_count = ntb->spad_count; - ctrl_size = sizeof(struct epf_ntb_ctrl); + ctrl_size = ALIGN(sizeof(struct epf_ntb_ctrl), sizeof(u32)); spad_size = 2 * spad_count * sizeof(u32); - if (!align) { - ctrl_size = roundup_pow_of_two(ctrl_size); - spad_size = roundup_pow_of_two(spad_size); - } else { - ctrl_size = ALIGN(ctrl_size, align); - spad_size = ALIGN(spad_size, align); - } - - if (!size) - size = ctrl_size + spad_size; - else if (size < ctrl_size + spad_size) - return -EINVAL; - - base = pci_epf_alloc_space(epf, size, barno, epc_features, 0); + base = pci_epf_alloc_space(epf, ctrl_size + spad_size, + barno, epc_features, 0); if (!base) { dev_err(dev, "Config/Status/SPAD alloc region fail\n"); return -ENOMEM; @@ -518,6 +517,94 @@ static int epf_ntb_configure_interrupt(struct epf_ntb *ntb) return 0; } +static int epf_ntb_db_bar_init_msi_doorbell(struct epf_ntb *ntb, + struct pci_epf_bar *db_bar, + const struct pci_epc_features *epc_features, + enum pci_barno barno) +{ + struct pci_epf *epf = ntb->epf; + dma_addr_t low, high; + struct msi_msg *msg; + size_t sz; + int ret; + int i; + + ret = pci_epf_alloc_doorbell(epf, ntb->db_count); + if (ret) + return ret; + + for (i = 0; i < ntb->db_count; i++) { + ret = request_irq(epf->db_msg[i].virq, epf_ntb_doorbell_handler, + 0, "pci_epf_vntb_db", ntb); + + if (ret) { + dev_err(&epf->dev, + "Failed to request doorbell IRQ: %d\n", + epf->db_msg[i].virq); + goto err_free_irq; + } + } + + msg = &epf->db_msg[0].msg; + + high = 0; + low = (u64)msg->address_hi << 32 | msg->address_lo; + + for (i = 0; i < ntb->db_count; i++) { + struct msi_msg *msg = &epf->db_msg[i].msg; + dma_addr_t addr = (u64)msg->address_hi << 32 | msg->address_lo; + + low = min(low, addr); + high = max(high, addr); + } + + sz = high - low + sizeof(u32); + + ret = pci_epf_assign_bar_space(epf, sz, barno, epc_features, 0, low); + if (ret) { + dev_err(&epf->dev, "Failed to assign Doorbell BAR space\n"); + goto err_free_irq; + } + + ret = pci_epc_set_bar(ntb->epf->epc, ntb->epf->func_no, + ntb->epf->vfunc_no, db_bar); + if (ret) { + dev_err(&epf->dev, "Failed to set Doorbell BAR\n"); + goto err_free_irq; + } + + for (i = 0; i < ntb->db_count; i++) { + struct msi_msg *msg = &epf->db_msg[i].msg; + dma_addr_t addr; + size_t offset; + + ret = pci_epf_align_inbound_addr(epf, db_bar->barno, + ((u64)msg->address_hi << 32) | msg->address_lo, + &addr, &offset); + + if (ret) { + ntb->msi_doorbell = false; + goto err_free_irq; + } + + ntb->reg->db_data[i] = msg->data; + ntb->reg->db_offset[i] = offset; + } + + ntb->reg->db_entry_size = 0; + + ntb->msi_doorbell = true; + + return 0; + +err_free_irq: + for (i--; i >= 0; i--) + free_irq(epf->db_msg[i].virq, ntb); + + pci_epf_free_doorbell(ntb->epf); + return ret; +} + /** * epf_ntb_db_bar_init() - Configure Doorbell window BARs * @ntb: NTB device that facilitates communication between HOST and VHOST @@ -530,7 +617,7 @@ static int epf_ntb_db_bar_init(struct epf_ntb *ntb) struct device *dev = &ntb->epf->dev; int ret; struct pci_epf_bar *epf_bar; - void __iomem *mw_addr; + void *mw_addr; enum pci_barno barno; size_t size = sizeof(u32) * ntb->db_count; @@ -538,21 +625,25 @@ static int epf_ntb_db_bar_init(struct epf_ntb *ntb) ntb->epf->func_no, ntb->epf->vfunc_no); barno = ntb->epf_ntb_bar[BAR_DB]; - - mw_addr = pci_epf_alloc_space(ntb->epf, size, barno, epc_features, 0); - if (!mw_addr) { - dev_err(dev, "Failed to allocate OB address\n"); - return -ENOMEM; - } - - ntb->epf_db = mw_addr; - epf_bar = &ntb->epf->bar[barno]; - ret = pci_epc_set_bar(ntb->epf->epc, ntb->epf->func_no, ntb->epf->vfunc_no, epf_bar); + ret = epf_ntb_db_bar_init_msi_doorbell(ntb, epf_bar, epc_features, barno); if (ret) { - dev_err(dev, "Doorbell BAR set failed\n"); + /* fall back to polling mode */ + mw_addr = pci_epf_alloc_space(ntb->epf, size, barno, epc_features, 0); + if (!mw_addr) { + dev_err(dev, "Failed to allocate OB address\n"); + return -ENOMEM; + } + + ntb->epf_db = mw_addr; + + ret = pci_epc_set_bar(ntb->epf->epc, ntb->epf->func_no, + ntb->epf->vfunc_no, epf_bar); + if (ret) { + dev_err(dev, "Doorbell BAR set failed\n"); goto err_alloc_peer_mem; + } } return ret; @@ -572,6 +663,16 @@ static void epf_ntb_db_bar_clear(struct epf_ntb *ntb) { enum pci_barno barno; + if (ntb->msi_doorbell) { + int i; + + for (i = 0; i < ntb->db_count; i++) + free_irq(ntb->epf->db_msg[i].virq, ntb); + } + + if (ntb->epf->db_msg) + pci_epf_free_doorbell(ntb->epf); + barno = ntb->epf_ntb_bar[BAR_DB]; pci_epf_free_space(ntb->epf, ntb->epf_db, barno, 0); pci_epc_clear_bar(ntb->epf->epc, @@ -596,7 +697,7 @@ static int epf_ntb_mw_bar_init(struct epf_ntb *ntb) for (i = 0; i < ntb->num_mws; i++) { size = ntb->mws_size[i]; - barno = ntb->epf_ntb_bar[BAR_MW0 + i]; + barno = ntb->epf_ntb_bar[BAR_MW1 + i]; ntb->epf->bar[barno].barno = barno; ntb->epf->bar[barno].size = size; @@ -649,7 +750,7 @@ static void epf_ntb_mw_bar_clear(struct epf_ntb *ntb, int num_mws) int i; for (i = 0; i < num_mws; i++) { - barno = ntb->epf_ntb_bar[BAR_MW0 + i]; + barno = ntb->epf_ntb_bar[BAR_MW1 + i]; pci_epc_clear_bar(ntb->epf->epc, ntb->epf->func_no, ntb->epf->vfunc_no, @@ -674,6 +775,63 @@ static void epf_ntb_epc_destroy(struct epf_ntb *ntb) pci_epc_put(ntb->epf->epc); } + +/** + * epf_ntb_is_bar_used() - Check if a bar is used in the ntb configuration + * @ntb: NTB device that facilitates communication between HOST and VHOST + * @barno: Checked bar number + * + * Returns: true if used, false if free. + */ +static bool epf_ntb_is_bar_used(struct epf_ntb *ntb, + enum pci_barno barno) +{ + int i; + + for (i = 0; i < VNTB_BAR_NUM; i++) { + if (ntb->epf_ntb_bar[i] == barno) + return true; + } + + return false; +} + +/** + * epf_ntb_find_bar() - Assign BAR number when no configuration is provided + * @ntb: NTB device that facilitates communication between HOST and VHOST + * @epc_features: The features provided by the EPC specific to this EPF + * @bar: NTB BAR index + * @barno: Bar start index + * + * When the BAR configuration was not provided through the userspace + * configuration, automatically assign BAR as it has been historically + * done by this endpoint function. + * + * Returns: the BAR number found, if any. -1 otherwise + */ +static int epf_ntb_find_bar(struct epf_ntb *ntb, + const struct pci_epc_features *epc_features, + enum epf_ntb_bar bar, + enum pci_barno barno) +{ + while (ntb->epf_ntb_bar[bar] < 0) { + barno = pci_epc_get_next_free_bar(epc_features, barno); + if (barno < 0) + break; /* No more BAR available */ + + /* + * Verify if the BAR found is not already assigned + * through the provided configuration + */ + if (!epf_ntb_is_bar_used(ntb, barno)) + ntb->epf_ntb_bar[bar] = barno; + + barno += 1; + } + + return barno; +} + /** * epf_ntb_init_epc_bar() - Identify BARs to be used for each of the NTB * constructs (scratchpad region, doorbell, memorywindow) @@ -696,23 +854,21 @@ static int epf_ntb_init_epc_bar(struct epf_ntb *ntb) epc_features = pci_epc_get_features(ntb->epf->epc, ntb->epf->func_no, ntb->epf->vfunc_no); /* These are required BARs which are mandatory for NTB functionality */ - for (bar = BAR_CONFIG; bar <= BAR_MW0; bar++, barno++) { - barno = pci_epc_get_next_free_bar(epc_features, barno); + for (bar = BAR_CONFIG; bar <= BAR_MW1; bar++) { + barno = epf_ntb_find_bar(ntb, epc_features, bar, barno); if (barno < 0) { dev_err(dev, "Fail to get NTB function BAR\n"); - return barno; + return -ENOENT; } - ntb->epf_ntb_bar[bar] = barno; } /* These are optional BARs which don't impact NTB functionality */ - for (bar = BAR_MW1, i = 1; i < num_mws; bar++, barno++, i++) { - barno = pci_epc_get_next_free_bar(epc_features, barno); + for (bar = BAR_MW1, i = 1; i < num_mws; bar++, i++) { + barno = epf_ntb_find_bar(ntb, epc_features, bar, barno); if (barno < 0) { ntb->num_mws = i; dev_dbg(dev, "BAR not available for > MW%d\n", i + 1); } - ntb->epf_ntb_bar[bar] = barno; } return 0; @@ -880,6 +1036,37 @@ static ssize_t epf_ntb_##_name##_store(struct config_item *item, \ return len; \ } +#define EPF_NTB_BAR_R(_name, _id) \ + static ssize_t epf_ntb_##_name##_show(struct config_item *item, \ + char *page) \ + { \ + struct config_group *group = to_config_group(item); \ + struct epf_ntb *ntb = to_epf_ntb(group); \ + \ + return sprintf(page, "%d\n", ntb->epf_ntb_bar[_id]); \ + } + +#define EPF_NTB_BAR_W(_name, _id) \ + static ssize_t epf_ntb_##_name##_store(struct config_item *item, \ + const char *page, size_t len) \ + { \ + struct config_group *group = to_config_group(item); \ + struct epf_ntb *ntb = to_epf_ntb(group); \ + int val; \ + int ret; \ + \ + ret = kstrtoint(page, 0, &val); \ + if (ret) \ + return ret; \ + \ + if (val < NO_BAR || val > BAR_5) \ + return -EINVAL; \ + \ + ntb->epf_ntb_bar[_id] = val; \ + \ + return len; \ + } + static ssize_t epf_ntb_num_mws_store(struct config_item *item, const char *page, size_t len) { @@ -919,6 +1106,18 @@ EPF_NTB_MW_R(mw3) EPF_NTB_MW_W(mw3) EPF_NTB_MW_R(mw4) EPF_NTB_MW_W(mw4) +EPF_NTB_BAR_R(ctrl_bar, BAR_CONFIG) +EPF_NTB_BAR_W(ctrl_bar, BAR_CONFIG) +EPF_NTB_BAR_R(db_bar, BAR_DB) +EPF_NTB_BAR_W(db_bar, BAR_DB) +EPF_NTB_BAR_R(mw1_bar, BAR_MW1) +EPF_NTB_BAR_W(mw1_bar, BAR_MW1) +EPF_NTB_BAR_R(mw2_bar, BAR_MW2) +EPF_NTB_BAR_W(mw2_bar, BAR_MW2) +EPF_NTB_BAR_R(mw3_bar, BAR_MW3) +EPF_NTB_BAR_W(mw3_bar, BAR_MW3) +EPF_NTB_BAR_R(mw4_bar, BAR_MW4) +EPF_NTB_BAR_W(mw4_bar, BAR_MW4) CONFIGFS_ATTR(epf_ntb_, spad_count); CONFIGFS_ATTR(epf_ntb_, db_count); @@ -930,6 +1129,12 @@ CONFIGFS_ATTR(epf_ntb_, mw4); CONFIGFS_ATTR(epf_ntb_, vbus_number); CONFIGFS_ATTR(epf_ntb_, vntb_pid); CONFIGFS_ATTR(epf_ntb_, vntb_vid); +CONFIGFS_ATTR(epf_ntb_, ctrl_bar); +CONFIGFS_ATTR(epf_ntb_, db_bar); +CONFIGFS_ATTR(epf_ntb_, mw1_bar); +CONFIGFS_ATTR(epf_ntb_, mw2_bar); +CONFIGFS_ATTR(epf_ntb_, mw3_bar); +CONFIGFS_ATTR(epf_ntb_, mw4_bar); static struct configfs_attribute *epf_ntb_attrs[] = { &epf_ntb_attr_spad_count, @@ -942,6 +1147,12 @@ static struct configfs_attribute *epf_ntb_attrs[] = { &epf_ntb_attr_vbus_number, &epf_ntb_attr_vntb_pid, &epf_ntb_attr_vntb_vid, + &epf_ntb_attr_ctrl_bar, + &epf_ntb_attr_db_bar, + &epf_ntb_attr_mw1_bar, + &epf_ntb_attr_mw2_bar, + &epf_ntb_attr_mw3_bar, + &epf_ntb_attr_mw4_bar, NULL, }; @@ -1068,7 +1279,7 @@ static int vntb_epf_mw_set_trans(struct ntb_dev *ndev, int pidx, int idx, struct device *dev; dev = &ntb->ntb.dev; - barno = ntb->epf_ntb_bar[BAR_MW0 + idx]; + barno = ntb->epf_ntb_bar[BAR_MW1 + idx]; epf_bar = &ntb->epf->bar[barno]; epf_bar->phys_addr = addr; epf_bar->barno = barno; @@ -1176,7 +1387,7 @@ static u64 vntb_epf_db_read(struct ntb_dev *ndev) { struct epf_ntb *ntb = ntb_ndev(ndev); - return ntb->db; + return atomic64_read(&ntb->db); } static int vntb_epf_mw_get_align(struct ntb_dev *ndev, int pidx, int idx, @@ -1216,7 +1427,7 @@ static int vntb_epf_db_clear(struct ntb_dev *ndev, u64 db_bits) { struct epf_ntb *ntb = ntb_ndev(ndev); - ntb->db &= ~db_bits; + atomic64_and(~db_bits, &ntb->db); return 0; } @@ -1399,6 +1610,7 @@ static int epf_ntb_probe(struct pci_epf *epf, { struct epf_ntb *ntb; struct device *dev; + int i; dev = &epf->dev; @@ -1409,6 +1621,11 @@ static int epf_ntb_probe(struct pci_epf *epf, epf->header = &epf_ntb_header; ntb->epf = epf; ntb->vbus_number = 0xff; + + /* Initially, no bar is assigned */ + for (i = 0; i < VNTB_BAR_NUM; i++) + ntb->epf_ntb_bar[i] = NO_BAR; + epf_set_drvdata(epf, ntb); dev_info(dev, "pci-ep epf driver loaded\n"); @@ -1434,8 +1651,13 @@ static int __init epf_ntb_init(void) { int ret; - kpcintb_workqueue = alloc_workqueue("kpcintb", WQ_MEM_RECLAIM | - WQ_HIGHPRI, 0); + kpcintb_workqueue = alloc_workqueue("kpcintb", + WQ_MEM_RECLAIM | WQ_HIGHPRI | WQ_PERCPU, 0); + if (!kpcintb_workqueue) { + pr_err("Failed to allocate kpcintb workqueue\n"); + return -ENOMEM; + } + ret = pci_epf_register_driver(&epf_ntb_driver); if (ret) { destroy_workqueue(kpcintb_workqueue); diff --git a/drivers/pci/endpoint/pci-ep-cfs.c b/drivers/pci/endpoint/pci-ep-cfs.c index d712c7a866d2..0f3921f28f17 100644 --- a/drivers/pci/endpoint/pci-ep-cfs.c +++ b/drivers/pci/endpoint/pci-ep-cfs.c @@ -23,7 +23,6 @@ struct pci_epf_group { struct config_group group; struct config_group primary_epc_group; struct config_group secondary_epc_group; - struct delayed_work cfs_work; struct pci_epf *epf; int index; }; @@ -69,8 +68,8 @@ static int pci_secondary_epc_epf_link(struct config_item *epf_item, return 0; } -static void pci_secondary_epc_epf_unlink(struct config_item *epc_item, - struct config_item *epf_item) +static void pci_secondary_epc_epf_unlink(struct config_item *epf_item, + struct config_item *epc_item) { struct pci_epf_group *epf_group = to_pci_epf_group(epf_item->ci_parent); struct pci_epc_group *epc_group = to_pci_epc_group(epc_item); @@ -103,7 +102,7 @@ static struct config_group secondary_epc_group = &epf_group->secondary_epc_group; config_group_init_type_name(secondary_epc_group, "secondary", &pci_secondary_epc_type); - configfs_register_group(&epf_group->group, secondary_epc_group); + configfs_add_default_group(secondary_epc_group, &epf_group->group); return secondary_epc_group; } @@ -133,8 +132,8 @@ static int pci_primary_epc_epf_link(struct config_item *epf_item, return 0; } -static void pci_primary_epc_epf_unlink(struct config_item *epc_item, - struct config_item *epf_item) +static void pci_primary_epc_epf_unlink(struct config_item *epf_item, + struct config_item *epc_item) { struct pci_epf_group *epf_group = to_pci_epf_group(epf_item->ci_parent); struct pci_epc_group *epc_group = to_pci_epc_group(epc_item); @@ -166,7 +165,7 @@ static struct config_group config_group_init_type_name(primary_epc_group, "primary", &pci_primary_epc_type); - configfs_register_group(&epf_group->group, primary_epc_group); + configfs_add_default_group(primary_epc_group, &epf_group->group); return primary_epc_group; } @@ -275,7 +274,7 @@ struct config_group *pci_ep_cfs_add_epc_group(const char *name) struct config_group *group; struct pci_epc_group *epc_group; - epc_group = kzalloc(sizeof(*epc_group), GFP_KERNEL); + epc_group = kzalloc_obj(*epc_group); if (!epc_group) { ret = -ENOMEM; goto err; @@ -570,15 +569,13 @@ static void pci_ep_cfs_add_type_group(struct pci_epf_group *epf_group) return; } - configfs_register_group(&epf_group->group, group); + configfs_add_default_group(group, &epf_group->group); } -static void pci_epf_cfs_work(struct work_struct *work) +static void pci_epf_cfs_add_sub_groups(struct pci_epf_group *epf_group) { - struct pci_epf_group *epf_group; struct config_group *group; - epf_group = container_of(work, struct pci_epf_group, cfs_work.work); group = pci_ep_cfs_add_primary_group(epf_group); if (IS_ERR(group)) { pr_err("failed to create 'primary' EPC interface\n"); @@ -602,7 +599,7 @@ static struct config_group *pci_epf_make(struct config_group *group, char *epf_name; int index, err; - epf_group = kzalloc(sizeof(*epf_group), GFP_KERNEL); + epf_group = kzalloc_obj(*epf_group); if (!epf_group) return ERR_PTR(-ENOMEM); @@ -637,9 +634,7 @@ static struct config_group *pci_epf_make(struct config_group *group, kfree(epf_name); - INIT_DELAYED_WORK(&epf_group->cfs_work, pci_epf_cfs_work); - queue_delayed_work(system_wq, &epf_group->cfs_work, - msecs_to_jiffies(1)); + pci_epf_cfs_add_sub_groups(epf_group); return &epf_group->group; @@ -691,6 +686,7 @@ void pci_ep_cfs_remove_epf_group(struct config_group *group) if (IS_ERR_OR_NULL(group)) return; + list_del(&group->group_entry); configfs_unregister_default_group(group); } EXPORT_SYMBOL(pci_ep_cfs_remove_epf_group); diff --git a/drivers/pci/endpoint/pci-ep-msi.c b/drivers/pci/endpoint/pci-ep-msi.c new file mode 100644 index 000000000000..51c19942a81e --- /dev/null +++ b/drivers/pci/endpoint/pci-ep-msi.c @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCI Endpoint *Controller* (EPC) MSI library + * + * Copyright (C) 2025 NXP + * Author: Frank Li <Frank.Li@nxp.com> + */ + +#include <linux/device.h> +#include <linux/export.h> +#include <linux/irqdomain.h> +#include <linux/module.h> +#include <linux/msi.h> +#include <linux/of_irq.h> +#include <linux/pci-epc.h> +#include <linux/pci-epf.h> +#include <linux/pci-ep-cfs.h> +#include <linux/pci-ep-msi.h> +#include <linux/slab.h> + +static void pci_epf_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg) +{ + struct pci_epc *epc; + struct pci_epf *epf; + + epc = pci_epc_get(dev_name(msi_desc_to_dev(desc))); + if (IS_ERR(epc)) + return; + + epf = list_first_entry_or_null(&epc->pci_epf, struct pci_epf, list); + + if (epf && epf->db_msg && desc->msi_index < epf->num_db) + memcpy(&epf->db_msg[desc->msi_index].msg, msg, sizeof(*msg)); + + pci_epc_put(epc); +} + +int pci_epf_alloc_doorbell(struct pci_epf *epf, u16 num_db) +{ + struct pci_epc *epc = epf->epc; + struct device *dev = &epf->dev; + struct irq_domain *domain; + void *msg; + int ret; + int i; + + /* TODO: Multi-EPF support */ + if (list_first_entry_or_null(&epc->pci_epf, struct pci_epf, list) != epf) { + dev_err(dev, "MSI doorbell doesn't support multiple EPF\n"); + return -EINVAL; + } + + domain = of_msi_map_get_device_domain(epc->dev.parent, 0, + DOMAIN_BUS_PLATFORM_MSI); + if (!domain) { + dev_err(dev, "Can't find MSI domain for EPC\n"); + return -ENODEV; + } + + if (!irq_domain_is_msi_parent(domain)) + return -ENODEV; + + if (!irq_domain_is_msi_immutable(domain)) { + dev_err(dev, "Mutable MSI controller not supported\n"); + return -ENODEV; + } + + dev_set_msi_domain(epc->dev.parent, domain); + + msg = kzalloc_objs(struct pci_epf_doorbell_msg, num_db); + if (!msg) + return -ENOMEM; + + epf->num_db = num_db; + epf->db_msg = msg; + + ret = platform_device_msi_init_and_alloc_irqs(epc->dev.parent, num_db, + pci_epf_write_msi_msg); + if (ret) { + dev_err(dev, "Failed to allocate MSI\n"); + kfree(msg); + return ret; + } + + for (i = 0; i < num_db; i++) + epf->db_msg[i].virq = msi_get_virq(epc->dev.parent, i); + + return ret; +} +EXPORT_SYMBOL_GPL(pci_epf_alloc_doorbell); + +void pci_epf_free_doorbell(struct pci_epf *epf) +{ + platform_device_msi_free_irqs_all(epf->epc->dev.parent); + + kfree(epf->db_msg); + epf->db_msg = NULL; + epf->num_db = 0; +} +EXPORT_SYMBOL_GPL(pci_epf_free_doorbell); diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c index beabea00af91..e546b3dbb240 100644 --- a/drivers/pci/endpoint/pci-epc-core.c +++ b/drivers/pci/endpoint/pci-epc-core.c @@ -293,8 +293,6 @@ int pci_epc_get_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no) if (interrupt < 0) return 0; - interrupt = 1 << interrupt; - return interrupt; } EXPORT_SYMBOL_GPL(pci_epc_get_msi); @@ -304,28 +302,25 @@ EXPORT_SYMBOL_GPL(pci_epc_get_msi); * @epc: the EPC device on which MSI has to be configured * @func_no: the physical endpoint function number in the EPC device * @vfunc_no: the virtual endpoint function number in the physical function - * @interrupts: number of MSI interrupts required by the EPF + * @nr_irqs: number of MSI interrupts required by the EPF * * Invoke to set the required number of MSI interrupts. */ -int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u8 interrupts) +int pci_epc_set_msi(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u8 nr_irqs) { int ret; - u8 encode_int; if (!pci_epc_function_is_valid(epc, func_no, vfunc_no)) return -EINVAL; - if (interrupts < 1 || interrupts > 32) + if (nr_irqs < 1 || nr_irqs > 32) return -EINVAL; if (!epc->ops->set_msi) return 0; - encode_int = order_base_2(interrupts); - mutex_lock(&epc->lock); - ret = epc->ops->set_msi(epc, func_no, vfunc_no, encode_int); + ret = epc->ops->set_msi(epc, func_no, vfunc_no, nr_irqs); mutex_unlock(&epc->lock); return ret; @@ -357,7 +352,7 @@ int pci_epc_get_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no) if (interrupt < 0) return 0; - return interrupt + 1; + return interrupt; } EXPORT_SYMBOL_GPL(pci_epc_get_msix); @@ -366,29 +361,28 @@ EXPORT_SYMBOL_GPL(pci_epc_get_msix); * @epc: the EPC device on which MSI-X has to be configured * @func_no: the physical endpoint function number in the EPC device * @vfunc_no: the virtual endpoint function number in the physical function - * @interrupts: number of MSI-X interrupts required by the EPF + * @nr_irqs: number of MSI-X interrupts required by the EPF * @bir: BAR where the MSI-X table resides * @offset: Offset pointing to the start of MSI-X table * * Invoke to set the required number of MSI-X interrupts. */ -int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, - u16 interrupts, enum pci_barno bir, u32 offset) +int pci_epc_set_msix(struct pci_epc *epc, u8 func_no, u8 vfunc_no, u16 nr_irqs, + enum pci_barno bir, u32 offset) { int ret; if (!pci_epc_function_is_valid(epc, func_no, vfunc_no)) return -EINVAL; - if (interrupts < 1 || interrupts > 2048) + if (nr_irqs < 1 || nr_irqs > 2048) return -EINVAL; if (!epc->ops->set_msix) return 0; mutex_lock(&epc->lock); - ret = epc->ops->set_msix(epc, func_no, vfunc_no, interrupts - 1, bir, - offset); + ret = epc->ops->set_msix(epc, func_no, vfunc_no, nr_irqs, bir, offset); mutex_unlock(&epc->lock); return ret; @@ -602,6 +596,14 @@ int pci_epc_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no, if (!epc_features) return -EINVAL; + if (epf_bar->num_submap && !epf_bar->submap) + return -EINVAL; + + if (epf_bar->num_submap && + !(epc_features->dynamic_inbound_mapping && + epc_features->subrange_mapping)) + return -EINVAL; + if (epc_features->bar[bar].type == BAR_RESIZABLE && (epf_bar->size < SZ_1M || (u64)epf_bar->size > (SZ_128G * 1024))) return -EINVAL; @@ -980,7 +982,7 @@ __pci_epc_create(struct device *dev, const struct pci_epc_ops *ops, goto err_ret; } - epc = kzalloc(sizeof(*epc), GFP_KERNEL); + epc = kzalloc_obj(*epc); if (!epc) { ret = -ENOMEM; goto err_ret; diff --git a/drivers/pci/endpoint/pci-epc-mem.c b/drivers/pci/endpoint/pci-epc-mem.c index 218a60e945db..6102a4af9d79 100644 --- a/drivers/pci/endpoint/pci-epc-mem.c +++ b/drivers/pci/endpoint/pci-epc-mem.c @@ -62,7 +62,7 @@ int pci_epc_multi_mem_init(struct pci_epc *epc, if (!windows || !num_windows) return -EINVAL; - epc->windows = kcalloc(num_windows, sizeof(*epc->windows), GFP_KERNEL); + epc->windows = kzalloc_objs(*epc->windows, num_windows); if (!epc->windows) return -ENOMEM; @@ -74,7 +74,7 @@ int pci_epc_multi_mem_init(struct pci_epc *epc, pages = windows[i].size >> page_shift; bitmap_size = BITS_TO_LONGS(pages) * sizeof(long); - mem = kzalloc(sizeof(*mem), GFP_KERNEL); + mem = kzalloc_obj(*mem); if (!mem) { ret = -ENOMEM; i--; diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c index 394395c7f8de..83fd20c11238 100644 --- a/drivers/pci/endpoint/pci-epf-core.c +++ b/drivers/pci/endpoint/pci-epf-core.c @@ -208,6 +208,48 @@ void pci_epf_remove_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf) } EXPORT_SYMBOL_GPL(pci_epf_remove_vepf); +static int pci_epf_get_required_bar_size(struct pci_epf *epf, size_t *bar_size, + size_t *aligned_mem_size, + enum pci_barno bar, + const struct pci_epc_features *epc_features, + enum pci_epc_interface_type type) +{ + u64 bar_fixed_size = epc_features->bar[bar].fixed_size; + size_t align = epc_features->align; + size_t size = *bar_size; + + if (size < 128) + size = 128; + + /* According to PCIe base spec, min size for a resizable BAR is 1 MB. */ + if (epc_features->bar[bar].type == BAR_RESIZABLE && size < SZ_1M) + size = SZ_1M; + + if (epc_features->bar[bar].type == BAR_FIXED && bar_fixed_size) { + if (size > bar_fixed_size) { + dev_err(&epf->dev, + "requested BAR size is larger than fixed size\n"); + return -ENOMEM; + } + size = bar_fixed_size; + } else { + /* BAR size must be power of two */ + size = roundup_pow_of_two(size); + } + + *bar_size = size; + + /* + * The EPC's BAR start address must meet alignment requirements. In most + * cases, the alignment will match the BAR size. However, differences + * can occur—for example, when the fixed BAR size (e.g., 128 bytes) is + * smaller than the required alignment (e.g., 4 KB). + */ + *aligned_mem_size = align ? ALIGN(size, align) : size; + + return 0; +} + /** * pci_epf_free_space() - free the allocated PCI EPF register space * @epf: the EPF device from whom to free the memory @@ -236,12 +278,13 @@ void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar, } dev = epc->dev.parent; - dma_free_coherent(dev, epf_bar[bar].size, addr, + dma_free_coherent(dev, epf_bar[bar].mem_size, addr, epf_bar[bar].phys_addr); epf_bar[bar].phys_addr = 0; epf_bar[bar].addr = NULL; epf_bar[bar].size = 0; + epf_bar[bar].mem_size = 0; epf_bar[bar].barno = 0; epf_bar[bar].flags = 0; } @@ -263,34 +306,16 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, const struct pci_epc_features *epc_features, enum pci_epc_interface_type type) { - u64 bar_fixed_size = epc_features->bar[bar].fixed_size; - size_t align = epc_features->align; struct pci_epf_bar *epf_bar; dma_addr_t phys_addr; struct pci_epc *epc; struct device *dev; + size_t mem_size; void *space; - if (size < 128) - size = 128; - - /* According to PCIe base spec, min size for a resizable BAR is 1 MB. */ - if (epc_features->bar[bar].type == BAR_RESIZABLE && size < SZ_1M) - size = SZ_1M; - - if (epc_features->bar[bar].type == BAR_FIXED && bar_fixed_size) { - if (size > bar_fixed_size) { - dev_err(&epf->dev, - "requested BAR size is larger than fixed size\n"); - return NULL; - } - size = bar_fixed_size; - } - - if (align) - size = ALIGN(size, align); - else - size = roundup_pow_of_two(size); + if (pci_epf_get_required_bar_size(epf, &size, &mem_size, bar, + epc_features, type)) + return NULL; if (type == PRIMARY_INTERFACE) { epc = epf->epc; @@ -301,7 +326,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, } dev = epc->dev.parent; - space = dma_alloc_coherent(dev, size, &phys_addr, GFP_KERNEL); + space = dma_alloc_coherent(dev, mem_size, &phys_addr, GFP_KERNEL); if (!space) { dev_err(dev, "failed to allocate mem space\n"); return NULL; @@ -310,6 +335,7 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, epf_bar[bar].phys_addr = phys_addr; epf_bar[bar].addr = space; epf_bar[bar].size = size; + epf_bar[bar].mem_size = mem_size; epf_bar[bar].barno = bar; if (upper_32_bits(size) || epc_features->bar[bar].only_64bit) epf_bar[bar].flags |= PCI_BASE_ADDRESS_MEM_TYPE_64; @@ -320,6 +346,83 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar, } EXPORT_SYMBOL_GPL(pci_epf_alloc_space); +/** + * pci_epf_assign_bar_space() - Assign PCI EPF BAR space + * @epf: EPF device to assign the BAR memory + * @size: Size of the memory that has to be assigned + * @bar: BAR number for which the memory is assigned + * @epc_features: Features provided by the EPC specific to this EPF + * @type: Identifies if the assignment is for primary EPC or secondary EPC + * @bar_addr: Address to be assigned for the @bar + * + * Invoke to assign memory for the PCI EPF BAR. + * Flag PCI_BASE_ADDRESS_MEM_TYPE_64 will automatically get set if the BAR + * can only be a 64-bit BAR, or if the requested size is larger than 2 GB. + */ +int pci_epf_assign_bar_space(struct pci_epf *epf, size_t size, + enum pci_barno bar, + const struct pci_epc_features *epc_features, + enum pci_epc_interface_type type, + dma_addr_t bar_addr) +{ + size_t bar_size, aligned_mem_size; + struct pci_epf_bar *epf_bar; + dma_addr_t limit; + int pos; + + if (!size) + return -EINVAL; + + limit = bar_addr + size - 1; + + /* + * Bits: 15 14 13 12 11 10 9 8 7 6 5 4 3 2 1 0 + * bar_addr: U U U U U U 0 X X X X X X X X X + * limit: U U U U U U 1 X X X X X X X X X + * + * bar_addr^limit 0 0 0 0 0 0 1 X X X X X X X X X + * + * U: unchanged address bits in range [bar_addr, limit] + * X: bit 0 or 1 + * + * (bar_addr^limit) & BIT_ULL(pos) will find the first set bit from MSB + * (pos). And value of (2 ^ pos) should be able to cover the BAR range. + */ + for (pos = 8 * sizeof(dma_addr_t) - 1; pos > 0; pos--) + if ((limit ^ bar_addr) & BIT_ULL(pos)) + break; + + if (pos == 8 * sizeof(dma_addr_t) - 1) + return -EINVAL; + + bar_size = BIT_ULL(pos + 1); + if (pci_epf_get_required_bar_size(epf, &bar_size, &aligned_mem_size, + bar, epc_features, type)) + return -ENOMEM; + + if (type == PRIMARY_INTERFACE) + epf_bar = epf->bar; + else + epf_bar = epf->sec_epc_bar; + + epf_bar[bar].phys_addr = ALIGN_DOWN(bar_addr, aligned_mem_size); + + if (epf_bar[bar].phys_addr + bar_size < limit) + return -ENOMEM; + + epf_bar[bar].addr = NULL; + epf_bar[bar].size = bar_size; + epf_bar[bar].mem_size = aligned_mem_size; + epf_bar[bar].barno = bar; + if (upper_32_bits(size) || epc_features->bar[bar].only_64bit) + epf_bar[bar].flags |= PCI_BASE_ADDRESS_MEM_TYPE_64; + else + epf_bar[bar].flags |= PCI_BASE_ADDRESS_MEM_TYPE_32; + + return 0; +} +EXPORT_SYMBOL_GPL(pci_epf_assign_bar_space); + static void pci_epf_remove_cfs(struct pci_epf_driver *driver) { struct config_group *group, *tmp; @@ -330,7 +433,7 @@ static void pci_epf_remove_cfs(struct pci_epf_driver *driver) mutex_lock(&pci_epf_mutex); list_for_each_entry_safe(group, tmp, &driver->epf_group, group_entry) pci_ep_cfs_remove_epf_group(group); - list_del(&driver->epf_group); + WARN_ON(!list_empty(&driver->epf_group)); mutex_unlock(&pci_epf_mutex); } @@ -432,7 +535,7 @@ struct pci_epf *pci_epf_create(const char *name) struct device *dev; int len; - epf = kzalloc(sizeof(*epf), GFP_KERNEL); + epf = kzalloc_obj(*epf); if (!epf) return ERR_PTR(-ENOMEM); @@ -469,6 +572,44 @@ struct pci_epf *pci_epf_create(const char *name) } EXPORT_SYMBOL_GPL(pci_epf_create); +/** + * pci_epf_align_inbound_addr() - Align the given address based on the BAR + * alignment requirement + * @epf: the EPF device + * @addr: inbound address to be aligned + * @bar: the BAR number corresponding to the given addr + * @base: base address matching the @bar alignment requirement + * @off: offset to be added to the @base address + * + * Helper function to align input @addr based on BAR's alignment requirement. + * The aligned base address and offset are returned via @base and @off. + * + * NOTE: The pci_epf_alloc_space() function already accounts for alignment. + * This API is primarily intended for use with other memory regions not + * allocated by pci_epf_alloc_space(), such as peripheral register spaces or + * the message address of a platform MSI controller. + * + * Return: 0 on success, errno otherwise. + */ +int pci_epf_align_inbound_addr(struct pci_epf *epf, enum pci_barno bar, + u64 addr, dma_addr_t *base, size_t *off) +{ + /* + * Most EP controllers require the BAR start address to be aligned to + * the BAR size, because they mask off the lower bits. + * + * Alignment to BAR size also works for controllers that support + * unaligned addresses. + */ + u64 align = epf->bar[bar].size; + + *base = round_down(addr, align); + *off = addr & (align - 1); + + return 0; +} +EXPORT_SYMBOL_GPL(pci_epf_align_inbound_addr); + static void pci_epf_dev_release(struct device *dev) { struct pci_epf *epf = to_pci_epf(dev); diff --git a/drivers/pci/host-bridge.c b/drivers/pci/host-bridge.c index afa50b446567..be5ef6516cff 100644 --- a/drivers/pci/host-bridge.c +++ b/drivers/pci/host-bridge.c @@ -33,6 +33,7 @@ struct device *pci_get_host_bridge_device(struct pci_dev *dev) kobject_get(&bridge->kobj); return bridge; } +EXPORT_SYMBOL_GPL(pci_get_host_bridge_device); void pci_put_host_bridge_device(struct device *dev) { diff --git a/drivers/pci/hotplug/TODO b/drivers/pci/hotplug/TODO index 92e6e20e8595..7397374af171 100644 --- a/drivers/pci/hotplug/TODO +++ b/drivers/pci/hotplug/TODO @@ -2,10 +2,6 @@ Contributions are solicited in particular to remedy the following issues: cpcihp: -* There are no implementations of the ->hardware_test, ->get_power and - ->set_power callbacks in struct cpci_hp_controller_ops. Why were they - introduced? Can they be removed from the struct? - * Returned code from pci_hp_add_bridge() is not checked. cpqphp: diff --git a/drivers/pci/hotplug/acpiphp_core.c b/drivers/pci/hotplug/acpiphp_core.c index 9dad14e80bcf..70c95166e509 100644 --- a/drivers/pci/hotplug/acpiphp_core.c +++ b/drivers/pci/hotplug/acpiphp_core.c @@ -260,7 +260,7 @@ int acpiphp_register_hotplug_slot(struct acpiphp_slot *acpiphp_slot, int retval = -ENOMEM; char name[SLOT_NAME_SIZE]; - slot = kzalloc(sizeof(*slot), GFP_KERNEL); + slot = kzalloc_obj(*slot); if (!slot) goto error; diff --git a/drivers/pci/hotplug/acpiphp_glue.c b/drivers/pci/hotplug/acpiphp_glue.c index 5b1f271c6034..78e3effbb32d 100644 --- a/drivers/pci/hotplug/acpiphp_glue.c +++ b/drivers/pci/hotplug/acpiphp_glue.c @@ -60,7 +60,7 @@ static struct acpiphp_context *acpiphp_init_context(struct acpi_device *adev) { struct acpiphp_context *context; - context = kzalloc(sizeof(*context), GFP_KERNEL); + context = kzalloc_obj(*context); if (!context) return NULL; @@ -279,7 +279,7 @@ static acpi_status acpiphp_add_context(acpi_handle handle, u32 lvl, void *data, if (slot->device == device) goto slot_found; - slot = kzalloc(sizeof(struct acpiphp_slot), GFP_KERNEL); + slot = kzalloc_obj(struct acpiphp_slot); if (!slot) { acpi_lock_hp_context(); acpiphp_put_context(context); @@ -869,7 +869,7 @@ void acpiphp_enumerate_slots(struct pci_bus *bus) return; handle = adev->handle; - bridge = kzalloc(sizeof(struct acpiphp_bridge), GFP_KERNEL); + bridge = kzalloc_obj(struct acpiphp_bridge); if (!bridge) return; @@ -889,7 +889,7 @@ void acpiphp_enumerate_slots(struct pci_bus *bus) if (pci_is_root_bus(bridge->pci_bus)) { struct acpiphp_root_context *root_context; - root_context = kzalloc(sizeof(*root_context), GFP_KERNEL); + root_context = kzalloc_obj(*root_context); if (!root_context) goto err; diff --git a/drivers/pci/hotplug/acpiphp_ibm.c b/drivers/pci/hotplug/acpiphp_ibm.c index b3aa34e3a4a2..f8016ed24523 100644 --- a/drivers/pci/hotplug/acpiphp_ibm.c +++ b/drivers/pci/hotplug/acpiphp_ibm.c @@ -98,7 +98,7 @@ static struct bin_attribute ibm_apci_table_attr __ro_after_init = { .name = "apci_table", .mode = S_IRUGO, }, - .read_new = ibm_read_apci_table, + .read = ibm_read_apci_table, .write = NULL, }; static struct acpiphp_attention_info ibm_attention_info = @@ -141,7 +141,7 @@ static union apci_descriptor *ibm_slot_from_id(int id) ibm_slot_done: if (ret) { - ret = kmalloc(sizeof(union apci_descriptor), GFP_KERNEL); + ret = kmalloc_obj(union apci_descriptor); if (ret) memcpy(ret, des, sizeof(union apci_descriptor)); } diff --git a/drivers/pci/hotplug/cpci_hotplug_core.c b/drivers/pci/hotplug/cpci_hotplug_core.c index dd93e53ea7c2..e7cd801a2655 100644 --- a/drivers/pci/hotplug/cpci_hotplug_core.c +++ b/drivers/pci/hotplug/cpci_hotplug_core.c @@ -189,7 +189,7 @@ cpci_hp_register_bus(struct pci_bus *bus, u8 first, u8 last) * with the pci_hotplug subsystem. */ for (i = first; i <= last; ++i) { - slot = kzalloc(sizeof(struct slot), GFP_KERNEL); + slot = kzalloc_obj(struct slot); if (!slot) { status = -ENOMEM; goto error; diff --git a/drivers/pci/hotplug/cpqphp_core.c b/drivers/pci/hotplug/cpqphp_core.c index 47a3ed16159a..76e26b9a9f0d 100644 --- a/drivers/pci/hotplug/cpqphp_core.c +++ b/drivers/pci/hotplug/cpqphp_core.c @@ -593,7 +593,7 @@ static int ctrl_slot_setup(struct controller *ctrl, slot_number = ctrl->first_slot; while (number_of_slots) { - slot = kzalloc(sizeof(*slot), GFP_KERNEL); + slot = kzalloc_obj(*slot); if (!slot) { result = -ENOMEM; goto error; @@ -822,7 +822,7 @@ static int cpqhpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent) goto err_disable_device; } - ctrl = kzalloc(sizeof(struct controller), GFP_KERNEL); + ctrl = kzalloc_obj(struct controller); if (!ctrl) { rc = -ENOMEM; goto err_disable_device; diff --git a/drivers/pci/hotplug/cpqphp_ctrl.c b/drivers/pci/hotplug/cpqphp_ctrl.c index 20529d1a3c44..040429028402 100644 --- a/drivers/pci/hotplug/cpqphp_ctrl.c +++ b/drivers/pci/hotplug/cpqphp_ctrl.c @@ -428,7 +428,7 @@ static struct pci_resource *do_pre_bridge_resource_split(struct pci_resource **h /* this one isn't an aligned length, so we'll make a new entry * and split it up. */ - split_node = kmalloc(sizeof(*split_node), GFP_KERNEL); + split_node = kmalloc_obj(*split_node); if (!split_node) return NULL; @@ -553,7 +553,7 @@ static struct pci_resource *get_io_resource(struct pci_resource **head, u32 size if ((node->length - (temp_dword - node->base)) < size) continue; - split_node = kmalloc(sizeof(*split_node), GFP_KERNEL); + split_node = kmalloc_obj(*split_node); if (!split_node) return NULL; @@ -573,7 +573,7 @@ static struct pci_resource *get_io_resource(struct pci_resource **head, u32 size /* this one is longer than we need * so we'll make a new entry and split it up */ - split_node = kmalloc(sizeof(*split_node), GFP_KERNEL); + split_node = kmalloc_obj(*split_node); if (!split_node) return NULL; @@ -650,7 +650,7 @@ static struct pci_resource *get_max_resource(struct pci_resource **head, u32 siz if ((max->length - (temp_dword - max->base)) < size) continue; - split_node = kmalloc(sizeof(*split_node), GFP_KERNEL); + split_node = kmalloc_obj(*split_node); if (!split_node) return NULL; @@ -668,7 +668,7 @@ static struct pci_resource *get_max_resource(struct pci_resource **head, u32 siz /* this one isn't end aligned properly at the top * so we'll make a new entry and split it up */ - split_node = kmalloc(sizeof(*split_node), GFP_KERNEL); + split_node = kmalloc_obj(*split_node); if (!split_node) return NULL; @@ -747,7 +747,7 @@ static struct pci_resource *get_resource(struct pci_resource **head, u32 size) if ((node->length - (temp_dword - node->base)) < size) continue; - split_node = kmalloc(sizeof(*split_node), GFP_KERNEL); + split_node = kmalloc_obj(*split_node); if (!split_node) return NULL; @@ -767,7 +767,7 @@ static struct pci_resource *get_resource(struct pci_resource **head, u32 size) /* this one is longer than we need * so we'll make a new entry and split it up */ - split_node = kmalloc(sizeof(*split_node), GFP_KERNEL); + split_node = kmalloc_obj(*split_node); if (!split_node) return NULL; @@ -955,7 +955,7 @@ struct pci_func *cpqhp_slot_create(u8 busnumber) struct pci_func *new_slot; struct pci_func *next; - new_slot = kzalloc(sizeof(*new_slot), GFP_KERNEL); + new_slot = kzalloc_obj(*new_slot); if (new_slot == NULL) return new_slot; @@ -1883,7 +1883,7 @@ void cpqhp_pushbutton_thread(struct timer_list *t) { u8 hp_slot; struct pci_func *func; - struct slot *p_slot = from_timer(p_slot, t, task_event); + struct slot *p_slot = timer_container_of(p_slot, t, task_event); struct controller *ctrl = (struct controller *) p_slot->ctrl; pushbutton_pending = NULL; @@ -2435,10 +2435,10 @@ static int configure_new_function(struct controller *ctrl, struct pci_func *func /* Make copies of the nodes we are going to pass down so that * if there is a problem,we can just use these to free resources */ - hold_bus_node = kmalloc(sizeof(*hold_bus_node), GFP_KERNEL); - hold_IO_node = kmalloc(sizeof(*hold_IO_node), GFP_KERNEL); - hold_mem_node = kmalloc(sizeof(*hold_mem_node), GFP_KERNEL); - hold_p_mem_node = kmalloc(sizeof(*hold_p_mem_node), GFP_KERNEL); + hold_bus_node = kmalloc_obj(*hold_bus_node); + hold_IO_node = kmalloc_obj(*hold_IO_node); + hold_mem_node = kmalloc_obj(*hold_mem_node); + hold_p_mem_node = kmalloc_obj(*hold_p_mem_node); if (!hold_bus_node || !hold_IO_node || !hold_mem_node || !hold_p_mem_node) { kfree(hold_bus_node); diff --git a/drivers/pci/hotplug/cpqphp_nvram.c b/drivers/pci/hotplug/cpqphp_nvram.c index 7a65d427ac11..a197fb98be3e 100644 --- a/drivers/pci/hotplug/cpqphp_nvram.c +++ b/drivers/pci/hotplug/cpqphp_nvram.c @@ -504,7 +504,7 @@ int compaq_nvram_load(void __iomem *rom_start, struct controller *ctrl) return 2; while (nummem--) { - mem_node = kmalloc(sizeof(struct pci_resource), GFP_KERNEL); + mem_node = kmalloc_obj(struct pci_resource); if (!mem_node) break; @@ -532,7 +532,7 @@ int compaq_nvram_load(void __iomem *rom_start, struct controller *ctrl) } while (numpmem--) { - p_mem_node = kmalloc(sizeof(struct pci_resource), GFP_KERNEL); + p_mem_node = kmalloc_obj(struct pci_resource); if (!p_mem_node) break; @@ -560,7 +560,7 @@ int compaq_nvram_load(void __iomem *rom_start, struct controller *ctrl) } while (numio--) { - io_node = kmalloc(sizeof(struct pci_resource), GFP_KERNEL); + io_node = kmalloc_obj(struct pci_resource); if (!io_node) break; @@ -588,7 +588,7 @@ int compaq_nvram_load(void __iomem *rom_start, struct controller *ctrl) } while (numbus--) { - bus_node = kmalloc(sizeof(struct pci_resource), GFP_KERNEL); + bus_node = kmalloc_obj(struct pci_resource); if (!bus_node) break; diff --git a/drivers/pci/hotplug/cpqphp_pci.c b/drivers/pci/hotplug/cpqphp_pci.c index ef7534a3ca40..81c58b1ec200 100644 --- a/drivers/pci/hotplug/cpqphp_pci.c +++ b/drivers/pci/hotplug/cpqphp_pci.c @@ -151,8 +151,8 @@ int cpqhp_set_irq(u8 bus_num, u8 dev_num, u8 int_pin, u8 irq_num) struct pci_bus *fakebus; u16 temp_word; - fakedev = kmalloc(sizeof(*fakedev), GFP_KERNEL); - fakebus = kmalloc(sizeof(*fakebus), GFP_KERNEL); + fakedev = kmalloc_obj(*fakedev); + fakebus = kmalloc_obj(*fakebus); if (!fakedev || !fakebus) { kfree(fakedev); kfree(fakebus); @@ -721,7 +721,7 @@ int cpqhp_save_used_resources(struct controller *ctrl, struct pci_func *func) pci_bus_read_config_byte(pci_bus, devfn, PCI_SECONDARY_BUS, &secondary_bus); pci_bus_read_config_byte(pci_bus, devfn, PCI_SUBORDINATE_BUS, &temp_byte); - bus_node = kmalloc(sizeof(*bus_node), GFP_KERNEL); + bus_node = kmalloc_obj(*bus_node); if (!bus_node) return -ENOMEM; @@ -736,7 +736,7 @@ int cpqhp_save_used_resources(struct controller *ctrl, struct pci_func *func) pci_bus_read_config_byte(pci_bus, devfn, PCI_IO_LIMIT, &b_length); if ((b_base <= b_length) && (save_command & 0x01)) { - io_node = kmalloc(sizeof(*io_node), GFP_KERNEL); + io_node = kmalloc_obj(*io_node); if (!io_node) return -ENOMEM; @@ -752,7 +752,7 @@ int cpqhp_save_used_resources(struct controller *ctrl, struct pci_func *func) pci_bus_read_config_word(pci_bus, devfn, PCI_MEMORY_LIMIT, &w_length); if ((w_base <= w_length) && (save_command & 0x02)) { - mem_node = kmalloc(sizeof(*mem_node), GFP_KERNEL); + mem_node = kmalloc_obj(*mem_node); if (!mem_node) return -ENOMEM; @@ -768,7 +768,7 @@ int cpqhp_save_used_resources(struct controller *ctrl, struct pci_func *func) pci_bus_read_config_word(pci_bus, devfn, PCI_PREF_MEMORY_LIMIT, &w_length); if ((w_base <= w_length) && (save_command & 0x02)) { - p_mem_node = kmalloc(sizeof(*p_mem_node), GFP_KERNEL); + p_mem_node = kmalloc_obj(*p_mem_node); if (!p_mem_node) return -ENOMEM; @@ -799,8 +799,7 @@ int cpqhp_save_used_resources(struct controller *ctrl, struct pci_func *func) temp_register = base & 0xFFFFFFFE; temp_register = (~temp_register) + 1; - io_node = kmalloc(sizeof(*io_node), - GFP_KERNEL); + io_node = kmalloc_obj(*io_node); if (!io_node) return -ENOMEM; @@ -817,8 +816,7 @@ int cpqhp_save_used_resources(struct controller *ctrl, struct pci_func *func) temp_register = base & 0xFFFFFFF0; temp_register = (~temp_register) + 1; - p_mem_node = kmalloc(sizeof(*p_mem_node), - GFP_KERNEL); + p_mem_node = kmalloc_obj(*p_mem_node); if (!p_mem_node) return -ENOMEM; @@ -834,8 +832,7 @@ int cpqhp_save_used_resources(struct controller *ctrl, struct pci_func *func) temp_register = base & 0xFFFFFFF0; temp_register = (~temp_register) + 1; - mem_node = kmalloc(sizeof(*mem_node), - GFP_KERNEL); + mem_node = kmalloc_obj(*mem_node); if (!mem_node) return -ENOMEM; @@ -871,8 +868,7 @@ int cpqhp_save_used_resources(struct controller *ctrl, struct pci_func *func) temp_register = base & 0xFFFFFFFE; temp_register = (~temp_register) + 1; - io_node = kmalloc(sizeof(*io_node), - GFP_KERNEL); + io_node = kmalloc_obj(*io_node); if (!io_node) return -ENOMEM; @@ -888,8 +884,7 @@ int cpqhp_save_used_resources(struct controller *ctrl, struct pci_func *func) temp_register = base & 0xFFFFFFF0; temp_register = (~temp_register) + 1; - p_mem_node = kmalloc(sizeof(*p_mem_node), - GFP_KERNEL); + p_mem_node = kmalloc_obj(*p_mem_node); if (!p_mem_node) return -ENOMEM; @@ -905,8 +900,7 @@ int cpqhp_save_used_resources(struct controller *ctrl, struct pci_func *func) temp_register = base & 0xFFFFFFF0; temp_register = (~temp_register) + 1; - mem_node = kmalloc(sizeof(*mem_node), - GFP_KERNEL); + mem_node = kmalloc_obj(*mem_node); if (!mem_node) return -ENOMEM; @@ -1293,7 +1287,7 @@ int cpqhp_find_available_resources(struct controller *ctrl, void __iomem *rom_st temp_dword = io_base + io_length; if ((io_base) && (temp_dword < 0x10000)) { - io_node = kmalloc(sizeof(*io_node), GFP_KERNEL); + io_node = kmalloc_obj(*io_node); if (!io_node) return -ENOMEM; @@ -1302,7 +1296,7 @@ int cpqhp_find_available_resources(struct controller *ctrl, void __iomem *rom_st dbg("found io_node(base, length) = %x, %x\n", io_node->base, io_node->length); - dbg("populated slot =%d \n", populated_slot); + dbg("populated slot = %d\n", populated_slot); if (!populated_slot) { io_node->next = ctrl->io_head; ctrl->io_head = io_node; @@ -1315,7 +1309,7 @@ int cpqhp_find_available_resources(struct controller *ctrl, void __iomem *rom_st /* If we've got a valid memory base, use it */ temp_dword = mem_base + mem_length; if ((mem_base) && (temp_dword < 0x10000)) { - mem_node = kmalloc(sizeof(*mem_node), GFP_KERNEL); + mem_node = kmalloc_obj(*mem_node); if (!mem_node) return -ENOMEM; @@ -1325,7 +1319,7 @@ int cpqhp_find_available_resources(struct controller *ctrl, void __iomem *rom_st dbg("found mem_node(base, length) = %x, %x\n", mem_node->base, mem_node->length); - dbg("populated slot =%d \n", populated_slot); + dbg("populated slot = %d\n", populated_slot); if (!populated_slot) { mem_node->next = ctrl->mem_head; ctrl->mem_head = mem_node; @@ -1340,7 +1334,7 @@ int cpqhp_find_available_resources(struct controller *ctrl, void __iomem *rom_st */ temp_dword = pre_mem_base + pre_mem_length; if ((pre_mem_base) && (temp_dword < 0x10000)) { - p_mem_node = kmalloc(sizeof(*p_mem_node), GFP_KERNEL); + p_mem_node = kmalloc_obj(*p_mem_node); if (!p_mem_node) return -ENOMEM; @@ -1349,7 +1343,7 @@ int cpqhp_find_available_resources(struct controller *ctrl, void __iomem *rom_st p_mem_node->length = pre_mem_length << 16; dbg("found p_mem_node(base, length) = %x, %x\n", p_mem_node->base, p_mem_node->length); - dbg("populated slot =%d \n", populated_slot); + dbg("populated slot = %d\n", populated_slot); if (!populated_slot) { p_mem_node->next = ctrl->p_mem_head; @@ -1365,7 +1359,7 @@ int cpqhp_find_available_resources(struct controller *ctrl, void __iomem *rom_st * populated slots that don't have PCI-PCI bridges */ if (secondary_bus && (secondary_bus != primary_bus)) { - bus_node = kmalloc(sizeof(*bus_node), GFP_KERNEL); + bus_node = kmalloc_obj(*bus_node); if (!bus_node) return -ENOMEM; @@ -1373,7 +1367,7 @@ int cpqhp_find_available_resources(struct controller *ctrl, void __iomem *rom_st bus_node->length = max_bus - secondary_bus + 1; dbg("found bus_node(base, length) = %x, %x\n", bus_node->base, bus_node->length); - dbg("populated slot =%d \n", populated_slot); + dbg("populated slot = %d\n", populated_slot); if (!populated_slot) { bus_node->next = ctrl->bus_head; ctrl->bus_head = bus_node; diff --git a/drivers/pci/hotplug/cpqphp_sysfs.c b/drivers/pci/hotplug/cpqphp_sysfs.c index 6143ebf71f21..ca153c626942 100644 --- a/drivers/pci/hotplug/cpqphp_sysfs.c +++ b/drivers/pci/hotplug/cpqphp_sysfs.c @@ -134,7 +134,7 @@ static int open(struct inode *inode, struct file *file) int retval = -ENOMEM; mutex_lock(&cpqphp_mutex); - dbg = kmalloc(sizeof(*dbg), GFP_KERNEL); + dbg = kmalloc_obj(*dbg); if (!dbg) goto exit; dbg->data = kmalloc(MAX_OUTPUT, GFP_KERNEL); diff --git a/drivers/pci/hotplug/ibmphp_core.c b/drivers/pci/hotplug/ibmphp_core.c index 197997e264a2..aca86c092d4a 100644 --- a/drivers/pci/hotplug/ibmphp_core.c +++ b/drivers/pci/hotplug/ibmphp_core.c @@ -624,11 +624,11 @@ static u8 bus_structure_fixup(u8 busno) if (pci_find_bus(0, busno) || !(ibmphp_find_same_bus_num(busno))) return 1; - bus = kmalloc(sizeof(*bus), GFP_KERNEL); + bus = kmalloc_obj(*bus); if (!bus) return 1; - dev = kmalloc(sizeof(*dev), GFP_KERNEL); + dev = kmalloc_obj(*dev); if (!dev) { kfree(bus); return 1; @@ -986,7 +986,7 @@ static int enable_slot(struct hotplug_slot *hs) goto error_power; } - slot_cur->func = kzalloc(sizeof(struct pci_func), GFP_KERNEL); + slot_cur->func = kzalloc_obj(struct pci_func); if (!slot_cur->func) { /* do update_slot_info here? */ rc = -ENOMEM; @@ -1093,7 +1093,7 @@ int ibmphp_do_disable_slot(struct slot *slot_cur) if (slot_cur->func == NULL) { /* We need this for functions that were there on bootup */ - slot_cur->func = kzalloc(sizeof(struct pci_func), GFP_KERNEL); + slot_cur->func = kzalloc_obj(struct pci_func); if (!slot_cur->func) { rc = -ENOMEM; goto error; @@ -1187,7 +1187,7 @@ static int __init ibmphp_init(void) info(DRIVER_DESC " version: " DRIVER_VERSION "\n"); - ibmphp_pci_bus = kmalloc(sizeof(*ibmphp_pci_bus), GFP_KERNEL); + ibmphp_pci_bus = kmalloc_obj(*ibmphp_pci_bus); if (!ibmphp_pci_bus) { rc = -ENOMEM; goto exit; diff --git a/drivers/pci/hotplug/ibmphp_ebda.c b/drivers/pci/hotplug/ibmphp_ebda.c index 7fb75401ad8a..c1939b88e75b 100644 --- a/drivers/pci/hotplug/ibmphp_ebda.c +++ b/drivers/pci/hotplug/ibmphp_ebda.c @@ -57,7 +57,7 @@ static int ebda_rio_table(void); static struct ebda_hpc_list * __init alloc_ebda_hpc_list(void) { - return kzalloc(sizeof(struct ebda_hpc_list), GFP_KERNEL); + return kzalloc_obj(struct ebda_hpc_list); } static struct controller *alloc_ebda_hpc(u32 slot_count, u32 bus_count) @@ -66,16 +66,16 @@ static struct controller *alloc_ebda_hpc(u32 slot_count, u32 bus_count) struct ebda_hpc_slot *slots; struct ebda_hpc_bus *buses; - controller = kzalloc(sizeof(struct controller), GFP_KERNEL); + controller = kzalloc_obj(struct controller); if (!controller) goto error; - slots = kcalloc(slot_count, sizeof(struct ebda_hpc_slot), GFP_KERNEL); + slots = kzalloc_objs(struct ebda_hpc_slot, slot_count); if (!slots) goto error_contr; controller->slots = slots; - buses = kcalloc(bus_count, sizeof(struct ebda_hpc_bus), GFP_KERNEL); + buses = kzalloc_objs(struct ebda_hpc_bus, bus_count); if (!buses) goto error_slots; controller->buses = buses; @@ -98,12 +98,12 @@ static void free_ebda_hpc(struct controller *controller) static struct ebda_rsrc_list * __init alloc_ebda_rsrc_list(void) { - return kzalloc(sizeof(struct ebda_rsrc_list), GFP_KERNEL); + return kzalloc_obj(struct ebda_rsrc_list); } static struct ebda_pci_rsrc *alloc_ebda_pci_rsrc(void) { - return kzalloc(sizeof(struct ebda_pci_rsrc), GFP_KERNEL); + return kzalloc_obj(struct ebda_pci_rsrc); } static void __init print_bus_info(void) @@ -352,7 +352,7 @@ int __init ibmphp_access_ebda(void) debug("now enter io table ---\n"); debug("rio blk id: %x\n", blk_id); - rio_table_ptr = kzalloc(sizeof(struct rio_table_hdr), GFP_KERNEL); + rio_table_ptr = kzalloc_obj(struct rio_table_hdr); if (!rio_table_ptr) { rc = -ENOMEM; goto out; @@ -408,7 +408,7 @@ static int __init ebda_rio_table(void) // we do concern about rio details for (i = 0; i < rio_table_ptr->riodev_count; i++) { - rio_detail_ptr = kzalloc(sizeof(struct rio_detail), GFP_KERNEL); + rio_detail_ptr = kzalloc_obj(struct rio_detail); if (!rio_detail_ptr) return -ENOMEM; rio_detail_ptr->rio_node_id = readb(io_mem + offset); @@ -461,7 +461,7 @@ static int __init combine_wpg_for_chassis(void) list_for_each_entry(rio_detail_ptr, &rio_vg_head, rio_detail_list) { opt_rio_ptr = search_opt_vg(rio_detail_ptr->chassis_num); if (!opt_rio_ptr) { - opt_rio_ptr = kzalloc(sizeof(struct opt_rio), GFP_KERNEL); + opt_rio_ptr = kzalloc_obj(struct opt_rio); if (!opt_rio_ptr) return -ENOMEM; opt_rio_ptr->rio_type = rio_detail_ptr->rio_type; @@ -499,7 +499,7 @@ static int combine_wpg_for_expansion(void) list_for_each_entry(rio_detail_ptr, &rio_lo_head, rio_detail_list) { opt_rio_lo_ptr = search_opt_lo(rio_detail_ptr->chassis_num); if (!opt_rio_lo_ptr) { - opt_rio_lo_ptr = kzalloc(sizeof(struct opt_rio_lo), GFP_KERNEL); + opt_rio_lo_ptr = kzalloc_obj(struct opt_rio_lo); if (!opt_rio_lo_ptr) return -ENOMEM; opt_rio_lo_ptr->rio_type = rio_detail_ptr->rio_type; @@ -738,7 +738,7 @@ static int __init ebda_rsrc_controller(void) bus_info_ptr2 = ibmphp_find_same_bus_num(slot_ptr->slot_bus_num); if (!bus_info_ptr2) { - bus_info_ptr1 = kzalloc(sizeof(struct bus_info), GFP_KERNEL); + bus_info_ptr1 = kzalloc_obj(struct bus_info); if (!bus_info_ptr1) { rc = -ENOMEM; goto error_no_slot; @@ -840,7 +840,7 @@ static int __init ebda_rsrc_controller(void) // register slots with hpc core as well as create linked list of ibm slot for (index = 0; index < hpc_ptr->slot_count; index++) { - tmp_slot = kzalloc(sizeof(*tmp_slot), GFP_KERNEL); + tmp_slot = kzalloc_obj(*tmp_slot); if (!tmp_slot) { rc = -ENOMEM; goto error_no_slot; diff --git a/drivers/pci/hotplug/ibmphp_hpc.c b/drivers/pci/hotplug/ibmphp_hpc.c index a5720d12e573..2324167656a6 100644 --- a/drivers/pci/hotplug/ibmphp_hpc.c +++ b/drivers/pci/hotplug/ibmphp_hpc.c @@ -124,7 +124,7 @@ static u8 i2c_ctrl_read(struct controller *ctlr_ptr, void __iomem *WPGBbar, u8 i unsigned long ultemp; unsigned long data; // actual data HILO format - debug_polling("%s - Entry WPGBbar[%p] index[%x] \n", __func__, WPGBbar, index); + debug_polling("%s - Entry WPGBbar[%p] index[%x]\n", __func__, WPGBbar, index); //-------------------------------------------------------------------- // READ - step 1 @@ -147,7 +147,7 @@ static u8 i2c_ctrl_read(struct controller *ctlr_ptr, void __iomem *WPGBbar, u8 i ultemp = ultemp << 8; data |= ultemp; } else { - err("this controller type is not supported \n"); + err("this controller type is not supported\n"); return HPC_ERROR; } @@ -258,7 +258,7 @@ static u8 i2c_ctrl_write(struct controller *ctlr_ptr, void __iomem *WPGBbar, u8 ultemp = ultemp << 8; data |= ultemp; } else { - err("this controller type is not supported \n"); + err("this controller type is not supported\n"); return HPC_ERROR; } diff --git a/drivers/pci/hotplug/ibmphp_pci.c b/drivers/pci/hotplug/ibmphp_pci.c index eeb412cbd9fe..cffce14879a6 100644 --- a/drivers/pci/hotplug/ibmphp_pci.c +++ b/drivers/pci/hotplug/ibmphp_pci.c @@ -152,7 +152,7 @@ int ibmphp_configure_card(struct pci_func *func, u8 slotno) cleanup_count = 6; goto error; } - newfunc = kzalloc(sizeof(*newfunc), GFP_KERNEL); + newfunc = kzalloc_obj(*newfunc); if (!newfunc) return -ENOMEM; @@ -189,7 +189,7 @@ int ibmphp_configure_card(struct pci_func *func, u8 slotno) flag = 0; for (i = 0; i < 32; i++) { if (func->devices[i]) { - newfunc = kzalloc(sizeof(*newfunc), GFP_KERNEL); + newfunc = kzalloc_obj(*newfunc); if (!newfunc) return -ENOMEM; @@ -216,7 +216,7 @@ int ibmphp_configure_card(struct pci_func *func, u8 slotno) } } - newfunc = kzalloc(sizeof(*newfunc), GFP_KERNEL); + newfunc = kzalloc_obj(*newfunc); if (!newfunc) return -ENOMEM; @@ -261,7 +261,7 @@ int ibmphp_configure_card(struct pci_func *func, u8 slotno) for (i = 0; i < 32; i++) { if (func->devices[i]) { debug("inside for loop, device is %x\n", i); - newfunc = kzalloc(sizeof(*newfunc), GFP_KERNEL); + newfunc = kzalloc_obj(*newfunc); if (!newfunc) return -ENOMEM; @@ -384,7 +384,7 @@ static int configure_device(struct pci_func *func) debug("len[count] in IO %x, count %d\n", len[count], count); - io[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL); + io[count] = kzalloc_obj(struct resource_node); if (!io[count]) return -ENOMEM; @@ -421,7 +421,7 @@ static int configure_device(struct pci_func *func) debug("len[count] in PFMEM %x, count %d\n", len[count], count); - pfmem[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL); + pfmem[count] = kzalloc_obj(struct resource_node); if (!pfmem[count]) return -ENOMEM; @@ -435,7 +435,7 @@ static int configure_device(struct pci_func *func) ibmphp_add_resource(pfmem[count]); func->pfmem[count] = pfmem[count]; } else { - mem_tmp = kzalloc(sizeof(*mem_tmp), GFP_KERNEL); + mem_tmp = kzalloc_obj(*mem_tmp); if (!mem_tmp) { kfree(pfmem[count]); return -ENOMEM; @@ -485,7 +485,7 @@ static int configure_device(struct pci_func *func) debug("len[count] in Mem %x, count %d\n", len[count], count); - mem[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL); + mem[count] = kzalloc_obj(struct resource_node); if (!mem[count]) return -ENOMEM; @@ -648,7 +648,7 @@ static int configure_bridge(struct pci_func **func_passed, u8 slotno) debug("len[count] in IO = %x\n", len[count]); - bus_io[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL); + bus_io[count] = kzalloc_obj(struct resource_node); if (!bus_io[count]) { retval = -ENOMEM; @@ -680,7 +680,7 @@ static int configure_bridge(struct pci_func **func_passed, u8 slotno) debug("len[count] in PFMEM = %x\n", len[count]); - bus_pfmem[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL); + bus_pfmem[count] = kzalloc_obj(struct resource_node); if (!bus_pfmem[count]) { retval = -ENOMEM; goto error; @@ -695,7 +695,7 @@ static int configure_bridge(struct pci_func **func_passed, u8 slotno) ibmphp_add_resource(bus_pfmem[count]); func->pfmem[count] = bus_pfmem[count]; } else { - mem_tmp = kzalloc(sizeof(*mem_tmp), GFP_KERNEL); + mem_tmp = kzalloc_obj(*mem_tmp); if (!mem_tmp) { retval = -ENOMEM; goto error; @@ -735,7 +735,7 @@ static int configure_bridge(struct pci_func **func_passed, u8 slotno) debug("len[count] in Memory is %x\n", len[count]); - bus_mem[count] = kzalloc(sizeof(struct resource_node), GFP_KERNEL); + bus_mem[count] = kzalloc_obj(struct resource_node); if (!bus_mem[count]) { retval = -ENOMEM; goto error; @@ -804,7 +804,7 @@ static int configure_bridge(struct pci_func **func_passed, u8 slotno) flag_io = 1; } else { debug("it wants %x IO behind the bridge\n", amount_needed->io); - io = kzalloc(sizeof(*io), GFP_KERNEL); + io = kzalloc_obj(*io); if (!io) { retval = -ENOMEM; @@ -826,7 +826,7 @@ static int configure_bridge(struct pci_func **func_passed, u8 slotno) flag_mem = 1; } else { debug("it wants %x memory behind the bridge\n", amount_needed->mem); - mem = kzalloc(sizeof(*mem), GFP_KERNEL); + mem = kzalloc_obj(*mem); if (!mem) { retval = -ENOMEM; goto error; @@ -847,7 +847,7 @@ static int configure_bridge(struct pci_func **func_passed, u8 slotno) flag_pfmem = 1; } else { debug("it wants %x pfmemory behind the bridge\n", amount_needed->pfmem); - pfmem = kzalloc(sizeof(*pfmem), GFP_KERNEL); + pfmem = kzalloc_obj(*pfmem); if (!pfmem) { retval = -ENOMEM; goto error; @@ -861,7 +861,7 @@ static int configure_bridge(struct pci_func **func_passed, u8 slotno) ibmphp_add_resource(pfmem); flag_pfmem = 1; } else { - mem_tmp = kzalloc(sizeof(*mem_tmp), GFP_KERNEL); + mem_tmp = kzalloc_obj(*mem_tmp); if (!mem_tmp) { retval = -ENOMEM; goto error; @@ -891,7 +891,7 @@ static int configure_bridge(struct pci_func **func_passed, u8 slotno) */ bus = ibmphp_find_res_bus(sec_number); if (!bus) { - bus = kzalloc(sizeof(*bus), GFP_KERNEL); + bus = kzalloc_obj(*bus); if (!bus) { retval = -ENOMEM; goto error; @@ -1064,7 +1064,7 @@ static struct res_needed *scan_behind_bridge(struct pci_func *func, u8 busno) }; struct res_needed *amount; - amount = kzalloc(sizeof(*amount), GFP_KERNEL); + amount = kzalloc_obj(*amount); if (amount == NULL) return NULL; @@ -1618,7 +1618,7 @@ static int add_new_bus(struct bus_node *bus, struct resource_node *io, struct re list_add(&bus->bus_list, &cur_bus->bus_list); } if (io) { - io_range = kzalloc(sizeof(*io_range), GFP_KERNEL); + io_range = kzalloc_obj(*io_range); if (!io_range) return -ENOMEM; @@ -1629,7 +1629,7 @@ static int add_new_bus(struct bus_node *bus, struct resource_node *io, struct re bus->rangeIO = io_range; } if (mem) { - mem_range = kzalloc(sizeof(*mem_range), GFP_KERNEL); + mem_range = kzalloc_obj(*mem_range); if (!mem_range) return -ENOMEM; @@ -1640,7 +1640,7 @@ static int add_new_bus(struct bus_node *bus, struct resource_node *io, struct re bus->rangeMem = mem_range; } if (pfmem) { - pfmem_range = kzalloc(sizeof(*pfmem_range), GFP_KERNEL); + pfmem_range = kzalloc_obj(*pfmem_range); if (!pfmem_range) return -ENOMEM; diff --git a/drivers/pci/hotplug/ibmphp_res.c b/drivers/pci/hotplug/ibmphp_res.c index 4a72ade2cddb..0294fd97e6db 100644 --- a/drivers/pci/hotplug/ibmphp_res.c +++ b/drivers/pci/hotplug/ibmphp_res.c @@ -41,7 +41,7 @@ static struct bus_node * __init alloc_error_bus(struct ebda_pci_rsrc *curr, u8 b return NULL; } - newbus = kzalloc(sizeof(struct bus_node), GFP_KERNEL); + newbus = kzalloc_obj(struct bus_node); if (!newbus) return NULL; @@ -62,7 +62,7 @@ static struct resource_node * __init alloc_resources(struct ebda_pci_rsrc *curr) return NULL; } - rs = kzalloc(sizeof(struct resource_node), GFP_KERNEL); + rs = kzalloc_obj(struct resource_node); if (!rs) return NULL; @@ -81,7 +81,7 @@ static int __init alloc_bus_range(struct bus_node **new_bus, struct range_node * u8 num_ranges = 0; if (first_bus) { - newbus = kzalloc(sizeof(struct bus_node), GFP_KERNEL); + newbus = kzalloc_obj(struct bus_node); if (!newbus) return -ENOMEM; @@ -101,7 +101,7 @@ static int __init alloc_bus_range(struct bus_node **new_bus, struct range_node * } } - newrange = kzalloc(sizeof(struct range_node), GFP_KERNEL); + newrange = kzalloc_obj(struct range_node); if (!newrange) { if (first_bus) kfree(newbus); @@ -1687,7 +1687,7 @@ static int __init once_over(void) bus_cur->firstPFMemFromMem = pfmem_cur; - mem = kzalloc(sizeof(struct resource_node), GFP_KERNEL); + mem = kzalloc_obj(struct resource_node); if (!mem) return -ENOMEM; @@ -1969,7 +1969,7 @@ static int __init update_bridge_ranges(struct bus_node **bus) end_address |= (upper_io_end << 16); if ((start_address) && (start_address <= end_address)) { - range = kzalloc(sizeof(struct range_node), GFP_KERNEL); + range = kzalloc_obj(struct range_node); if (!range) return -ENOMEM; @@ -1993,7 +1993,7 @@ static int __init update_bridge_ranges(struct bus_node **bus) fix_resources(bus_sec); if (ibmphp_find_resource(bus_cur, start_address, &io, IO)) { - io = kzalloc(sizeof(struct resource_node), GFP_KERNEL); + io = kzalloc_obj(struct resource_node); if (!io) { kfree(range); return -ENOMEM; @@ -2016,7 +2016,7 @@ static int __init update_bridge_ranges(struct bus_node **bus) if ((start_address) && (start_address <= end_address)) { - range = kzalloc(sizeof(struct range_node), GFP_KERNEL); + range = kzalloc_obj(struct range_node); if (!range) return -ENOMEM; @@ -2041,7 +2041,7 @@ static int __init update_bridge_ranges(struct bus_node **bus) fix_resources(bus_sec); if (ibmphp_find_resource(bus_cur, start_address, &mem, MEM)) { - mem = kzalloc(sizeof(struct resource_node), GFP_KERNEL); + mem = kzalloc_obj(struct resource_node); if (!mem) { kfree(range); return -ENOMEM; @@ -2068,7 +2068,7 @@ static int __init update_bridge_ranges(struct bus_node **bus) if ((start_address) && (start_address <= end_address)) { - range = kzalloc(sizeof(struct range_node), GFP_KERNEL); + range = kzalloc_obj(struct range_node); if (!range) return -ENOMEM; @@ -2092,7 +2092,7 @@ static int __init update_bridge_ranges(struct bus_node **bus) fix_resources(bus_sec); if (ibmphp_find_resource(bus_cur, start_address, &pfmem, PFMEM)) { - pfmem = kzalloc(sizeof(struct resource_node), GFP_KERNEL); + pfmem = kzalloc_obj(struct resource_node); if (!pfmem) { kfree(range); return -ENOMEM; diff --git a/drivers/pci/hotplug/octep_hp.c b/drivers/pci/hotplug/octep_hp.c index 2bce7296c050..a0a7f9ccb8fa 100644 --- a/drivers/pci/hotplug/octep_hp.c +++ b/drivers/pci/hotplug/octep_hp.c @@ -136,7 +136,7 @@ octep_hp_register_slot(struct octep_hp_controller *hp_ctrl, struct octep_hp_slot *hp_slot; int ret; - hp_slot = kzalloc(sizeof(*hp_slot), GFP_KERNEL); + hp_slot = kzalloc_obj(*hp_slot); if (!hp_slot) return ERR_PTR(-ENOMEM); @@ -271,7 +271,7 @@ static irqreturn_t octep_hp_intr_handler(int irq, void *data) intr_val = readq(hp_ctrl->base + OCTEP_HP_INTR_OFFSET(type)); writeq(intr_val, hp_ctrl->base + OCTEP_HP_INTR_OFFSET(type)); - hp_cmd = kzalloc(sizeof(*hp_cmd), GFP_ATOMIC); + hp_cmd = kzalloc_obj(*hp_cmd, GFP_ATOMIC); if (!hp_cmd) return IRQ_HANDLED; diff --git a/drivers/pci/hotplug/pci_hotplug_core.c b/drivers/pci/hotplug/pci_hotplug_core.c index d30f1316c98e..fadcf98a8a66 100644 --- a/drivers/pci/hotplug/pci_hotplug_core.c +++ b/drivers/pci/hotplug/pci_hotplug_core.c @@ -20,13 +20,9 @@ #include <linux/types.h> #include <linux/kobject.h> #include <linux/sysfs.h> -#include <linux/pagemap.h> #include <linux/init.h> -#include <linux/mount.h> -#include <linux/namei.h> #include <linux/pci.h> #include <linux/pci_hotplug.h> -#include <linux/uaccess.h> #include "../pci.h" #include "cpci_hotplug.h" @@ -492,6 +488,75 @@ void pci_hp_destroy(struct hotplug_slot *slot) } EXPORT_SYMBOL_GPL(pci_hp_destroy); +static DECLARE_WAIT_QUEUE_HEAD(pci_hp_link_change_wq); + +/** + * pci_hp_ignore_link_change - begin code section causing spurious link changes + * @pdev: PCI hotplug bridge + * + * Mark the beginning of a code section causing spurious link changes on the + * Secondary Bus of @pdev, e.g. as a side effect of a Secondary Bus Reset, + * D3cold transition, firmware update or FPGA reconfiguration. + * + * Hotplug drivers can thus check whether such a code section is executing + * concurrently, await it with pci_hp_spurious_link_change() and ignore the + * resulting link change events. + * + * Must be paired with pci_hp_unignore_link_change(). May be called both + * from the PCI core and from Endpoint drivers. May be called for bridges + * which are not hotplug-capable, in which case it has no effect because + * no hotplug driver is bound to the bridge. + */ +void pci_hp_ignore_link_change(struct pci_dev *pdev) +{ + set_bit(PCI_LINK_CHANGING, &pdev->priv_flags); + smp_mb__after_atomic(); /* pairs with implied barrier of wait_event() */ +} + +/** + * pci_hp_unignore_link_change - end code section causing spurious link changes + * @pdev: PCI hotplug bridge + * + * Mark the end of a code section causing spurious link changes on the + * Secondary Bus of @pdev. Must be paired with pci_hp_ignore_link_change(). + */ +void pci_hp_unignore_link_change(struct pci_dev *pdev) +{ + set_bit(PCI_LINK_CHANGED, &pdev->priv_flags); + mb(); /* ensure pci_hp_spurious_link_change() sees either bit set */ + clear_bit(PCI_LINK_CHANGING, &pdev->priv_flags); + wake_up_all(&pci_hp_link_change_wq); +} + +/** + * pci_hp_spurious_link_change - check for spurious link changes + * @pdev: PCI hotplug bridge + * + * Check whether a code section is executing concurrently which is causing + * spurious link changes on the Secondary Bus of @pdev. Await the end of the + * code section if so. + * + * May be called by hotplug drivers to check whether a link change is spurious + * and can be ignored. + * + * Because a genuine link change may have occurred in-between a spurious link + * change and the invocation of this function, hotplug drivers should perform + * sanity checks such as retrieving the current link state and bringing down + * the slot if the link is down. + * + * Return: %true if such a code section has been executing concurrently, + * otherwise %false. Also return %true if such a code section has not been + * executing concurrently, but at least once since the last invocation of this + * function. + */ +bool pci_hp_spurious_link_change(struct pci_dev *pdev) +{ + wait_event(pci_hp_link_change_wq, + !test_bit(PCI_LINK_CHANGING, &pdev->priv_flags)); + + return test_and_clear_bit(PCI_LINK_CHANGED, &pdev->priv_flags); +} + static int __init pci_hotplug_init(void) { int result; diff --git a/drivers/pci/hotplug/pciehp.h b/drivers/pci/hotplug/pciehp.h index 273dd8c66f4e..debc79b0adfb 100644 --- a/drivers/pci/hotplug/pciehp.h +++ b/drivers/pci/hotplug/pciehp.h @@ -187,6 +187,7 @@ int pciehp_card_present(struct controller *ctrl); int pciehp_card_present_or_link_active(struct controller *ctrl); int pciehp_check_link_status(struct controller *ctrl); int pciehp_check_link_active(struct controller *ctrl); +bool pciehp_device_replaced(struct controller *ctrl); void pciehp_release_ctrl(struct controller *ctrl); int pciehp_sysfs_enable_slot(struct hotplug_slot *hotplug_slot); diff --git a/drivers/pci/hotplug/pciehp_core.c b/drivers/pci/hotplug/pciehp_core.c index 997841c69893..1e9158d7bac7 100644 --- a/drivers/pci/hotplug/pciehp_core.c +++ b/drivers/pci/hotplug/pciehp_core.c @@ -55,7 +55,7 @@ static int init_slot(struct controller *ctrl) int retval; /* Setup hotplug slot ops */ - ops = kzalloc(sizeof(*ops), GFP_KERNEL); + ops = kzalloc_obj(*ops); if (!ops) return -ENOMEM; @@ -284,35 +284,6 @@ static int pciehp_suspend(struct pcie_device *dev) return 0; } -static bool pciehp_device_replaced(struct controller *ctrl) -{ - struct pci_dev *pdev __free(pci_dev_put) = NULL; - u32 reg; - - if (pci_dev_is_disconnected(ctrl->pcie->port)) - return false; - - pdev = pci_get_slot(ctrl->pcie->port->subordinate, PCI_DEVFN(0, 0)); - if (!pdev) - return true; - - if (pci_read_config_dword(pdev, PCI_VENDOR_ID, ®) || - reg != (pdev->vendor | (pdev->device << 16)) || - pci_read_config_dword(pdev, PCI_CLASS_REVISION, ®) || - reg != (pdev->revision | (pdev->class << 8))) - return true; - - if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL && - (pci_read_config_dword(pdev, PCI_SUBSYSTEM_VENDOR_ID, ®) || - reg != (pdev->subsystem_vendor | (pdev->subsystem_device << 16)))) - return true; - - if (pci_get_dsn(pdev) != ctrl->dsn) - return true; - - return false; -} - static int pciehp_resume_noirq(struct pcie_device *dev) { struct controller *ctrl = get_service_data(dev); diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index d603a7aa7483..7805f697a02c 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -19,6 +19,7 @@ #include <linux/types.h> #include <linux/pm_runtime.h> #include <linux/pci.h> +#include <trace/events/pci.h> #include "../pci.h" #include "pciehp.h" @@ -131,7 +132,7 @@ static void remove_board(struct controller *ctrl, bool safe_removal) INDICATOR_NOOP); /* Don't carry LBMS indications across */ - pcie_reset_lbms_count(ctrl->pcie->port); + pcie_reset_lbms(ctrl->pcie->port); } static int pciehp_enable_slot(struct controller *ctrl); @@ -244,12 +245,20 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) case ON_STATE: ctrl->state = POWEROFF_STATE; mutex_unlock(&ctrl->state_lock); - if (events & PCI_EXP_SLTSTA_DLLSC) + if (events & PCI_EXP_SLTSTA_DLLSC) { ctrl_info(ctrl, "Slot(%s): Link Down\n", slot_name(ctrl)); - if (events & PCI_EXP_SLTSTA_PDC) + trace_pci_hp_event(pci_name(ctrl->pcie->port), + slot_name(ctrl), + PCI_HOTPLUG_LINK_DOWN); + } + if (events & PCI_EXP_SLTSTA_PDC) { ctrl_info(ctrl, "Slot(%s): Card not present\n", slot_name(ctrl)); + trace_pci_hp_event(pci_name(ctrl->pcie->port), + slot_name(ctrl), + PCI_HOTPLUG_CARD_NOT_PRESENT); + } pciehp_disable_slot(ctrl, SURPRISE_REMOVAL); break; default: @@ -269,6 +278,9 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) INDICATOR_NOOP); ctrl_info(ctrl, "Slot(%s): Card not present\n", slot_name(ctrl)); + trace_pci_hp_event(pci_name(ctrl->pcie->port), + slot_name(ctrl), + PCI_HOTPLUG_CARD_NOT_PRESENT); } mutex_unlock(&ctrl->state_lock); return; @@ -281,12 +293,19 @@ void pciehp_handle_presence_or_link_change(struct controller *ctrl, u32 events) case OFF_STATE: ctrl->state = POWERON_STATE; mutex_unlock(&ctrl->state_lock); - if (present) + if (present) { ctrl_info(ctrl, "Slot(%s): Card present\n", slot_name(ctrl)); - if (link_active) - ctrl_info(ctrl, "Slot(%s): Link Up\n", - slot_name(ctrl)); + trace_pci_hp_event(pci_name(ctrl->pcie->port), + slot_name(ctrl), + PCI_HOTPLUG_CARD_PRESENT); + } + if (link_active) { + ctrl_info(ctrl, "Slot(%s): Link Up\n", slot_name(ctrl)); + trace_pci_hp_event(pci_name(ctrl->pcie->port), + slot_name(ctrl), + PCI_HOTPLUG_LINK_UP); + } ctrl->request_result = pciehp_enable_slot(ctrl); break; default: diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 8a09fb6083e2..4c62140a3cb4 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -320,7 +320,8 @@ int pciehp_check_link_status(struct controller *ctrl) } pcie_capability_read_word(pdev, PCI_EXP_LNKSTA2, &linksta2); - __pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status, linksta2); + __pcie_update_link_speed(ctrl->pcie->port->subordinate, PCIE_HOTPLUG, + lnk_status, linksta2); if (!found) { ctrl_info(ctrl, "Slot(%s): No device found\n", @@ -563,20 +564,50 @@ void pciehp_power_off_slot(struct controller *ctrl) PCI_EXP_SLTCTL_PWR_OFF); } -static void pciehp_ignore_dpc_link_change(struct controller *ctrl, - struct pci_dev *pdev, int irq) +bool pciehp_device_replaced(struct controller *ctrl) +{ + struct pci_dev *pdev __free(pci_dev_put) = NULL; + u32 reg; + + if (pci_dev_is_disconnected(ctrl->pcie->port)) + return false; + + pdev = pci_get_slot(ctrl->pcie->port->subordinate, PCI_DEVFN(0, 0)); + if (!pdev) + return true; + + if (pci_read_config_dword(pdev, PCI_VENDOR_ID, ®) || + reg != (pdev->vendor | (pdev->device << 16)) || + pci_read_config_dword(pdev, PCI_CLASS_REVISION, ®) || + reg != (pdev->revision | (pdev->class << 8))) + return true; + + if (pdev->hdr_type == PCI_HEADER_TYPE_NORMAL && + (pci_read_config_dword(pdev, PCI_SUBSYSTEM_VENDOR_ID, ®) || + reg != (pdev->subsystem_vendor | (pdev->subsystem_device << 16)))) + return true; + + if (pci_get_dsn(pdev) != ctrl->dsn) + return true; + + return false; +} + +static void pciehp_ignore_link_change(struct controller *ctrl, + struct pci_dev *pdev, int irq, + u16 ignored_events) { /* * Ignore link changes which occurred while waiting for DPC recovery. * Could be several if DPC triggered multiple times consecutively. + * Also ignore link changes caused by Secondary Bus Reset, etc. */ synchronize_hardirq(irq); - atomic_and(~PCI_EXP_SLTSTA_DLLSC, &ctrl->pending_events); + atomic_and(~ignored_events, &ctrl->pending_events); if (pciehp_poll_mode) pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, - PCI_EXP_SLTSTA_DLLSC); - ctrl_info(ctrl, "Slot(%s): Link Down/Up ignored (recovered by DPC)\n", - slot_name(ctrl)); + ignored_events); + ctrl_info(ctrl, "Slot(%s): Link Down/Up ignored\n", slot_name(ctrl)); /* * If the link is unexpectedly down after successful recovery, @@ -584,8 +615,8 @@ static void pciehp_ignore_dpc_link_change(struct controller *ctrl, * Synthesize it to ensure that it is acted on. */ down_read_nested(&ctrl->reset_lock, ctrl->depth); - if (!pciehp_check_link_active(ctrl)) - pciehp_request(ctrl, PCI_EXP_SLTSTA_DLLSC); + if (!pciehp_check_link_active(ctrl) || pciehp_device_replaced(ctrl)) + pciehp_request(ctrl, ignored_events); up_read(&ctrl->reset_lock); } @@ -732,12 +763,19 @@ static irqreturn_t pciehp_ist(int irq, void *dev_id) /* * Ignore Link Down/Up events caused by Downstream Port Containment - * if recovery from the error succeeded. + * if recovery succeeded, or caused by Secondary Bus Reset, + * suspend to D3cold, firmware update, FPGA reconfiguration, etc. */ - if ((events & PCI_EXP_SLTSTA_DLLSC) && pci_dpc_recovered(pdev) && + if ((events & (PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC)) && + (pci_dpc_recovered(pdev) || pci_hp_spurious_link_change(pdev)) && ctrl->state == ON_STATE) { - events &= ~PCI_EXP_SLTSTA_DLLSC; - pciehp_ignore_dpc_link_change(ctrl, pdev, irq); + u16 ignored_events = PCI_EXP_SLTSTA_DLLSC; + + if (!ctrl->inband_presence_disabled) + ignored_events |= PCI_EXP_SLTSTA_PDC; + + events &= ~ignored_events; + pciehp_ignore_link_change(ctrl, pdev, irq, ignored_events); } /* @@ -902,7 +940,6 @@ int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, bool probe) { struct controller *ctrl = to_ctrl(hotplug_slot); struct pci_dev *pdev = ctrl_dev(ctrl); - u16 stat_mask = 0, ctrl_mask = 0; int rc; if (probe) @@ -910,23 +947,11 @@ int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, bool probe) down_write_nested(&ctrl->reset_lock, ctrl->depth); - if (!ATTN_BUTTN(ctrl)) { - ctrl_mask |= PCI_EXP_SLTCTL_PDCE; - stat_mask |= PCI_EXP_SLTSTA_PDC; - } - ctrl_mask |= PCI_EXP_SLTCTL_DLLSCE; - stat_mask |= PCI_EXP_SLTSTA_DLLSC; - - pcie_write_cmd(ctrl, 0, ctrl_mask); - ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__, - pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, 0); + pci_hp_ignore_link_change(pdev); rc = pci_bridge_secondary_bus_reset(ctrl->pcie->port); - pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, stat_mask); - pcie_write_cmd_nowait(ctrl, ctrl_mask, ctrl_mask); - ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__, - pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask); + pci_hp_unignore_link_change(pdev); up_write(&ctrl->reset_lock); return rc; @@ -971,7 +996,7 @@ static inline int pcie_hotplug_depth(struct pci_dev *dev) while (bus->parent) { bus = bus->parent; - if (bus->self && bus->self->is_hotplug_bridge) + if (bus->self && bus->self->is_pciehp) depth++; } @@ -986,7 +1011,7 @@ struct controller *pcie_init(struct pcie_device *dev) struct pci_dev *pdev = dev->port; struct pci_bus *subordinate = pdev->subordinate; - ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); + ctrl = kzalloc_obj(*ctrl); if (!ctrl) return NULL; diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c index 573a41869c15..5c020831e318 100644 --- a/drivers/pci/hotplug/pnv_php.c +++ b/drivers/pci/hotplug/pnv_php.c @@ -3,12 +3,15 @@ * PCI Hotplug Driver for PowerPC PowerNV platform. * * Copyright Gavin Shan, IBM Corporation 2016. + * Copyright (C) 2025 Raptor Engineering, LLC + * Copyright (C) 2025 Raptor Computing Systems, LLC */ #include <linux/bitfield.h> #include <linux/libfdt.h> #include <linux/module.h> #include <linux/pci.h> +#include <linux/delay.h> #include <linux/pci_hotplug.h> #include <linux/of_fdt.h> @@ -36,8 +39,10 @@ static void pnv_php_register(struct device_node *dn); static void pnv_php_unregister_one(struct device_node *dn); static void pnv_php_unregister(struct device_node *dn); +static void pnv_php_enable_irq(struct pnv_php_slot *php_slot); + static void pnv_php_disable_irq(struct pnv_php_slot *php_slot, - bool disable_device) + bool disable_device, bool disable_msi) { struct pci_dev *pdev = php_slot->pdev; u16 ctrl; @@ -53,19 +58,15 @@ static void pnv_php_disable_irq(struct pnv_php_slot *php_slot, php_slot->irq = 0; } - if (php_slot->wq) { - destroy_workqueue(php_slot->wq); - php_slot->wq = NULL; - } - - if (disable_device) { + if (disable_device || disable_msi) { if (pdev->msix_enabled) pci_disable_msix(pdev); else if (pdev->msi_enabled) pci_disable_msi(pdev); + } + if (disable_device) pci_disable_device(pdev); - } } static void pnv_php_free_slot(struct kref *kref) @@ -74,7 +75,8 @@ static void pnv_php_free_slot(struct kref *kref) struct pnv_php_slot, kref); WARN_ON(!list_empty(&php_slot->children)); - pnv_php_disable_irq(php_slot, false); + pnv_php_disable_irq(php_slot, false, false); + destroy_workqueue(php_slot->wq); kfree(php_slot->name); kfree(php_slot); } @@ -391,6 +393,20 @@ static int pnv_php_get_power_state(struct hotplug_slot *slot, u8 *state) return 0; } +static int pcie_check_link_active(struct pci_dev *pdev) +{ + u16 lnk_status; + int ret; + + ret = pcie_capability_read_word(pdev, PCI_EXP_LNKSTA, &lnk_status); + if (ret == PCIBIOS_DEVICE_NOT_FOUND || PCI_POSSIBLE_ERROR(lnk_status)) + return -ENODEV; + + ret = !!(lnk_status & PCI_EXP_LNKSTA_DLLLA); + + return ret; +} + static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state) { struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); @@ -403,6 +419,19 @@ static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state) */ ret = pnv_pci_get_presence_state(php_slot->id, &presence); if (ret >= 0) { + if (pci_pcie_type(php_slot->pdev) == PCI_EXP_TYPE_DOWNSTREAM && + presence == OPAL_PCI_SLOT_EMPTY) { + /* + * Similar to pciehp_hpc, check whether the Link Active + * bit is set to account for broken downstream bridges + * that don't properly assert Presence Detect State, as + * was observed on the Microsemi Switchtec PM8533 PFX + * [11f8:8533]. + */ + if (pcie_check_link_active(php_slot->pdev) > 0) + presence = OPAL_PCI_SLOT_PRESENT; + } + *state = presence; ret = 0; } else { @@ -412,10 +441,23 @@ static int pnv_php_get_adapter_state(struct hotplug_slot *slot, u8 *state) return ret; } +static int pnv_php_get_raw_indicator_status(struct hotplug_slot *slot, u8 *state) +{ + struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); + struct pci_dev *bridge = php_slot->pdev; + u16 status; + + pcie_capability_read_word(bridge, PCI_EXP_SLTCTL, &status); + *state = (status & (PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC)) >> 6; + return 0; +} + + static int pnv_php_get_attention_state(struct hotplug_slot *slot, u8 *state) { struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); + pnv_php_get_raw_indicator_status(slot, &php_slot->attention_state); *state = php_slot->attention_state; return 0; } @@ -433,7 +475,7 @@ static int pnv_php_set_attention_state(struct hotplug_slot *slot, u8 state) mask = PCI_EXP_SLTCTL_AIC; if (state) - new = PCI_EXP_SLTCTL_ATTN_IND_ON; + new = FIELD_PREP(PCI_EXP_SLTCTL_AIC, state); else new = PCI_EXP_SLTCTL_ATTN_IND_OFF; @@ -442,6 +484,61 @@ static int pnv_php_set_attention_state(struct hotplug_slot *slot, u8 state) return 0; } +static int pnv_php_activate_slot(struct pnv_php_slot *php_slot, + struct hotplug_slot *slot) +{ + int ret, i; + + /* + * Issue initial slot activation command to firmware + * + * Firmware will power slot on, attempt to train the link, and + * discover any downstream devices. If this process fails, firmware + * will return an error code and an invalid device tree. Failure + * can be caused for multiple reasons, including a faulty + * downstream device, poor connection to the downstream device, or + * a previously latched PHB fence. On failure, issue fundamental + * reset up to three times before aborting. + */ + ret = pnv_php_set_slot_power_state(slot, OPAL_PCI_SLOT_POWER_ON); + if (ret) { + SLOT_WARN( + php_slot, + "PCI slot activation failed with error code %d, possible frozen PHB", + ret); + SLOT_WARN( + php_slot, + "Attempting complete PHB reset before retrying slot activation\n"); + for (i = 0; i < 3; i++) { + /* + * Slot activation failed, PHB may be fenced from a + * prior device failure. + * + * Use the OPAL fundamental reset call to both try a + * device reset and clear any potentially active PHB + * fence / freeze. + */ + SLOT_WARN(php_slot, "Try %d...\n", i + 1); + pci_set_pcie_reset_state(php_slot->pdev, + pcie_warm_reset); + msleep(250); + pci_set_pcie_reset_state(php_slot->pdev, + pcie_deassert_reset); + + ret = pnv_php_set_slot_power_state( + slot, OPAL_PCI_SLOT_POWER_ON); + if (!ret) + break; + } + + if (i >= 3) + SLOT_WARN(php_slot, + "Failed to bring slot online, aborting!\n"); + } + + return ret; +} + static int pnv_php_enable(struct pnv_php_slot *php_slot, bool rescan) { struct hotplug_slot *slot = &php_slot->slot; @@ -504,7 +601,7 @@ static int pnv_php_enable(struct pnv_php_slot *php_slot, bool rescan) goto scan; /* Power is off, turn it on and then scan the slot */ - ret = pnv_php_set_slot_power_state(slot, OPAL_PCI_SLOT_POWER_ON); + ret = pnv_php_activate_slot(php_slot, slot); if (ret) return ret; @@ -561,8 +658,58 @@ static int pnv_php_reset_slot(struct hotplug_slot *slot, bool probe) static int pnv_php_enable_slot(struct hotplug_slot *slot) { struct pnv_php_slot *php_slot = to_pnv_php_slot(slot); + u32 prop32; + int ret; + + ret = pnv_php_enable(php_slot, true); + if (ret) + return ret; + + /* (Re-)enable interrupt if the slot supports surprise hotplug */ + ret = of_property_read_u32(php_slot->dn, "ibm,slot-surprise-pluggable", + &prop32); + if (!ret && prop32) + pnv_php_enable_irq(php_slot); + + return 0; +} + +/* + * Disable any hotplug interrupts for all slots on the provided bus, as well as + * all downstream slots in preparation for a hot unplug. + */ +static int pnv_php_disable_all_irqs(struct pci_bus *bus) +{ + struct pci_bus *child_bus; + struct pci_slot *slot; + + /* First go down child buses */ + list_for_each_entry(child_bus, &bus->children, node) + pnv_php_disable_all_irqs(child_bus); - return pnv_php_enable(php_slot, true); + /* Disable IRQs for all pnv_php slots on this bus */ + list_for_each_entry(slot, &bus->slots, list) { + struct pnv_php_slot *php_slot = to_pnv_php_slot(slot->hotplug); + + pnv_php_disable_irq(php_slot, false, true); + } + + return 0; +} + +/* + * Disable any hotplug interrupts for all downstream slots on the provided + * bus in preparation for a hot unplug. + */ +static int pnv_php_disable_all_downstream_irqs(struct pci_bus *bus) +{ + struct pci_bus *child_bus; + + /* Go down child buses, recursively deactivating their IRQs */ + list_for_each_entry(child_bus, &bus->children, node) + pnv_php_disable_all_irqs(child_bus); + + return 0; } static int pnv_php_disable_slot(struct hotplug_slot *slot) @@ -579,6 +726,13 @@ static int pnv_php_disable_slot(struct hotplug_slot *slot) php_slot->state != PNV_PHP_STATE_REGISTERED) return 0; + /* + * Free all IRQ resources from all child slots before remove. + * Note that we do not disable the root slot IRQ here as that + * would also deactivate the slot hot (re)plug interrupt! + */ + pnv_php_disable_all_downstream_irqs(php_slot->bus); + /* Remove all devices behind the slot */ pci_lock_rescan_remove(); pci_hp_remove_devices(php_slot->bus); @@ -637,7 +791,7 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn) if (!bus) return NULL; - php_slot = kzalloc(sizeof(*php_slot), GFP_KERNEL); + php_slot = kzalloc_obj(*php_slot); if (!php_slot) return NULL; @@ -647,6 +801,15 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct device_node *dn) return NULL; } + /* Allocate workqueue for this slot's interrupt handling */ + php_slot->wq = alloc_workqueue("pciehp-%s", WQ_PERCPU, 0, php_slot->name); + if (!php_slot->wq) { + SLOT_WARN(php_slot, "Cannot alloc workqueue\n"); + kfree(php_slot->name); + kfree(php_slot); + return NULL; + } + if (dn->child && PCI_DN(dn->child)) php_slot->slot_no = PCI_SLOT(PCI_DN(dn->child)->devfn); else @@ -745,16 +908,63 @@ static int pnv_php_enable_msix(struct pnv_php_slot *php_slot) return entry.vector; } +static void +pnv_php_detect_clear_suprise_removal_freeze(struct pnv_php_slot *php_slot) +{ + struct pci_dev *pdev = php_slot->pdev; + struct eeh_dev *edev; + struct eeh_pe *pe; + int i, rc; + + /* + * When a device is surprise removed from a downstream bridge slot, + * the upstream bridge port can still end up frozen due to related EEH + * events, which will in turn block the MSI interrupts for slot hotplug + * detection. + * + * Detect and thaw any frozen upstream PE after slot deactivation. + */ + edev = pci_dev_to_eeh_dev(pdev); + pe = edev ? edev->pe : NULL; + rc = eeh_pe_get_state(pe); + if ((rc == -ENODEV) || (rc == -ENOENT)) { + SLOT_WARN( + php_slot, + "Upstream bridge PE state unknown, hotplug detect may fail\n"); + } else { + if (pe->state & EEH_PE_ISOLATED) { + SLOT_WARN( + php_slot, + "Upstream bridge PE %02x frozen, thawing...\n", + pe->addr); + for (i = 0; i < 3; i++) + if (!eeh_unfreeze_pe(pe)) + break; + if (i >= 3) + SLOT_WARN( + php_slot, + "Unable to thaw PE %02x, hotplug detect will fail!\n", + pe->addr); + else + SLOT_WARN(php_slot, + "PE %02x thawed successfully\n", + pe->addr); + } + } +} + static void pnv_php_event_handler(struct work_struct *work) { struct pnv_php_event *event = container_of(work, struct pnv_php_event, work); struct pnv_php_slot *php_slot = event->php_slot; - if (event->added) + if (event->added) { pnv_php_enable_slot(&php_slot->slot); - else + } else { pnv_php_disable_slot(&php_slot->slot); + pnv_php_detect_clear_suprise_removal_freeze(php_slot); + } kfree(event); } @@ -818,7 +1028,7 @@ static irqreturn_t pnv_php_interrupt(int irq, void *data) * The PE is left in frozen state if the event is missed. It's * fine as the PCI devices (PE) aren't functional any more. */ - event = kzalloc(sizeof(*event), GFP_ATOMIC); + event = kzalloc_obj(*event, GFP_ATOMIC); if (!event) { SLOT_WARN(php_slot, "PCI slot [%s] missed hotplug event 0x%04x\n", @@ -843,14 +1053,6 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq) u16 sts, ctrl; int ret; - /* Allocate workqueue */ - php_slot->wq = alloc_workqueue("pciehp-%s", 0, 0, php_slot->name); - if (!php_slot->wq) { - SLOT_WARN(php_slot, "Cannot alloc workqueue\n"); - pnv_php_disable_irq(php_slot, true); - return; - } - /* Check PDC (Presence Detection Change) is broken or not */ ret = of_property_read_u32(php_slot->dn, "ibm,slot-broken-pdc", &broken_pdc); @@ -869,7 +1071,7 @@ static void pnv_php_init_irq(struct pnv_php_slot *php_slot, int irq) ret = request_irq(irq, pnv_php_interrupt, IRQF_SHARED, php_slot->name, php_slot); if (ret) { - pnv_php_disable_irq(php_slot, true); + pnv_php_disable_irq(php_slot, true, true); SLOT_WARN(php_slot, "Error %d enabling IRQ %d\n", ret, irq); return; } diff --git a/drivers/pci/hotplug/rpaphp_slot.c b/drivers/pci/hotplug/rpaphp_slot.c index 779eab12e981..33ca19200c1b 100644 --- a/drivers/pci/hotplug/rpaphp_slot.c +++ b/drivers/pci/hotplug/rpaphp_slot.c @@ -32,7 +32,7 @@ struct slot *alloc_slot_struct(struct device_node *dn, { struct slot *slot; - slot = kzalloc(sizeof(struct slot), GFP_KERNEL); + slot = kzalloc_obj(struct slot); if (!slot) goto error_nomem; slot->name = kstrdup(drc_name, GFP_KERNEL); diff --git a/drivers/pci/hotplug/s390_pci_hpc.c b/drivers/pci/hotplug/s390_pci_hpc.c index 055518ee354d..a55967082ef6 100644 --- a/drivers/pci/hotplug/s390_pci_hpc.c +++ b/drivers/pci/hotplug/s390_pci_hpc.c @@ -8,8 +8,7 @@ * Jan Glauber <jang@linux.vnet.ibm.com> */ -#define KMSG_COMPONENT "zpci" -#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt +#define pr_fmt(fmt) "zpci: " fmt #include <linux/kernel.h> #include <linux/slab.h> @@ -59,16 +58,15 @@ static int disable_slot(struct hotplug_slot *hotplug_slot) pdev = pci_get_slot(zdev->zbus->bus, zdev->devfn); if (pdev && pci_num_vf(pdev)) { - pci_dev_put(pdev); rc = -EBUSY; goto out; } rc = zpci_deconfigure_device(zdev); out: - mutex_unlock(&zdev->state_lock); if (pdev) pci_dev_put(pdev); + mutex_unlock(&zdev->state_lock); return rc; } diff --git a/drivers/pci/hotplug/shpchp_core.c b/drivers/pci/hotplug/shpchp_core.c index 0c341453afc6..8d6f8eea599d 100644 --- a/drivers/pci/hotplug/shpchp_core.c +++ b/drivers/pci/hotplug/shpchp_core.c @@ -66,7 +66,7 @@ static int init_slots(struct controller *ctrl) int i; for (i = 0; i < ctrl->num_slots; i++) { - slot = kzalloc(sizeof(*slot), GFP_KERNEL); + slot = kzalloc_obj(*slot); if (!slot) { retval = -ENOMEM; goto error; @@ -80,7 +80,8 @@ static int init_slots(struct controller *ctrl) slot->device = ctrl->slot_device_offset + i; slot->number = ctrl->first_slot + (ctrl->slot_num_inc * i); - slot->wq = alloc_workqueue("shpchp-%d", 0, 0, slot->number); + slot->wq = alloc_workqueue("shpchp-%d", WQ_PERCPU, 0, + slot->number); if (!slot->wq) { retval = -ENOMEM; goto error_slot; @@ -258,7 +259,7 @@ static int shpc_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (acpi_get_hp_hw_control_from_firmware(pdev)) return -ENODEV; - ctrl = kzalloc(sizeof(*ctrl), GFP_KERNEL); + ctrl = kzalloc_obj(*ctrl); if (!ctrl) goto err_out_none; diff --git a/drivers/pci/hotplug/shpchp_ctrl.c b/drivers/pci/hotplug/shpchp_ctrl.c index e6c6f23bae27..a10cdcdcbbdc 100644 --- a/drivers/pci/hotplug/shpchp_ctrl.c +++ b/drivers/pci/hotplug/shpchp_ctrl.c @@ -29,7 +29,7 @@ static int queue_interrupt_event(struct slot *p_slot, u32 event_type) { struct event_info *info; - info = kmalloc(sizeof(*info), GFP_ATOMIC); + info = kmalloc_obj(*info, GFP_ATOMIC); if (!info) return -ENOMEM; @@ -418,7 +418,7 @@ void shpchp_queue_pushbutton_work(struct work_struct *work) struct slot *p_slot = container_of(work, struct slot, work.work); struct pushbutton_work_info *info; - info = kmalloc(sizeof(*info), GFP_KERNEL); + info = kmalloc_obj(*info); if (!info) { ctrl_err(p_slot->ctrl, "%s: Cannot allocate memory\n", __func__); diff --git a/drivers/pci/hotplug/shpchp_hpc.c b/drivers/pci/hotplug/shpchp_hpc.c index 387b85585263..183bf43510a1 100644 --- a/drivers/pci/hotplug/shpchp_hpc.c +++ b/drivers/pci/hotplug/shpchp_hpc.c @@ -211,7 +211,7 @@ static inline int shpc_indirect_read(struct controller *ctrl, int index, */ static void int_poll_timeout(struct timer_list *t) { - struct controller *ctrl = from_timer(ctrl, t, poll_timer); + struct controller *ctrl = timer_container_of(ctrl, t, poll_timer); /* Poll for interrupt events. regs == NULL => polling */ shpc_isr(0, ctrl); diff --git a/drivers/pci/ide.c b/drivers/pci/ide.c new file mode 100644 index 000000000000..be74e8f0ae21 --- /dev/null +++ b/drivers/pci/ide.c @@ -0,0 +1,811 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2024-2025 Intel Corporation. All rights reserved. */ + +/* PCIe r7.0 section 6.33 Integrity & Data Encryption (IDE) */ + +#define dev_fmt(fmt) "PCI/IDE: " fmt +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/pci.h> +#include <linux/pci-ide.h> +#include <linux/pci_regs.h> +#include <linux/slab.h> +#include <linux/sysfs.h> + +#include "pci.h" + +static int __sel_ide_offset(u16 ide_cap, u8 nr_link_ide, u8 stream_index, + u8 nr_ide_mem) +{ + u32 offset = ide_cap + PCI_IDE_LINK_STREAM_0 + + nr_link_ide * PCI_IDE_LINK_BLOCK_SIZE; + + /* + * Assume a constant number of address association resources per stream + * index + */ + return offset + stream_index * PCI_IDE_SEL_BLOCK_SIZE(nr_ide_mem); +} + +static int sel_ide_offset(struct pci_dev *pdev, + struct pci_ide_partner *settings) +{ + return __sel_ide_offset(pdev->ide_cap, pdev->nr_link_ide, + settings->stream_index, pdev->nr_ide_mem); +} + +static bool reserve_stream_index(struct pci_dev *pdev, u8 idx) +{ + int ret; + + ret = ida_alloc_range(&pdev->ide_stream_ida, idx, idx, GFP_KERNEL); + return ret >= 0; +} + +static bool reserve_stream_id(struct pci_host_bridge *hb, u8 id) +{ + int ret; + + ret = ida_alloc_range(&hb->ide_stream_ids_ida, id, id, GFP_KERNEL); + return ret >= 0; +} + +static bool claim_stream(struct pci_host_bridge *hb, u8 stream_id, + struct pci_dev *pdev, u8 stream_idx) +{ + dev_info(&hb->dev, "Stream ID %d active at init\n", stream_id); + if (!reserve_stream_id(hb, stream_id)) { + dev_info(&hb->dev, "Failed to claim %s Stream ID %d\n", + stream_id == PCI_IDE_RESERVED_STREAM_ID ? "reserved" : + "active", + stream_id); + return false; + } + + /* No stream index to reserve in the Link IDE case */ + if (!pdev) + return true; + + if (!reserve_stream_index(pdev, stream_idx)) { + pci_info(pdev, "Failed to claim active Selective Stream %d\n", + stream_idx); + return false; + } + + return true; +} + +void pci_ide_init(struct pci_dev *pdev) +{ + struct pci_host_bridge *hb = pci_find_host_bridge(pdev->bus); + u16 nr_link_ide, nr_ide_mem, nr_streams; + u16 ide_cap; + u32 val; + + /* + * Unconditionally init so that ida idle state is consistent with + * pdev->ide_cap. + */ + ida_init(&pdev->ide_stream_ida); + + if (!pci_is_pcie(pdev)) + return; + + ide_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_IDE); + if (!ide_cap) + return; + + pci_read_config_dword(pdev, ide_cap + PCI_IDE_CAP, &val); + if ((val & PCI_IDE_CAP_SELECTIVE) == 0) + return; + + /* + * Require endpoint IDE capability to be paired with IDE Root Port IDE + * capability. + */ + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ENDPOINT) { + struct pci_dev *rp = pcie_find_root_port(pdev); + + if (!rp->ide_cap) + return; + } + + pdev->ide_cfg = FIELD_GET(PCI_IDE_CAP_SEL_CFG, val); + pdev->ide_tee_limit = FIELD_GET(PCI_IDE_CAP_TEE_LIMITED, val); + + if (val & PCI_IDE_CAP_LINK) + nr_link_ide = 1 + FIELD_GET(PCI_IDE_CAP_LINK_TC_NUM, val); + else + nr_link_ide = 0; + + nr_ide_mem = 0; + nr_streams = 1 + FIELD_GET(PCI_IDE_CAP_SEL_NUM, val); + for (u16 i = 0; i < nr_streams; i++) { + int pos = __sel_ide_offset(ide_cap, nr_link_ide, i, nr_ide_mem); + int nr_assoc; + u32 val; + u8 id; + + pci_read_config_dword(pdev, pos + PCI_IDE_SEL_CAP, &val); + + /* + * Let's not entertain streams that do not have a constant + * number of address association blocks + */ + nr_assoc = FIELD_GET(PCI_IDE_SEL_CAP_ASSOC_NUM, val); + if (i && (nr_assoc != nr_ide_mem)) { + pci_info(pdev, "Unsupported Selective Stream %d capability, SKIP the rest\n", i); + nr_streams = i; + break; + } + + nr_ide_mem = nr_assoc; + + /* + * Claim Stream IDs and Selective Stream blocks that are already + * active on the device + */ + pci_read_config_dword(pdev, pos + PCI_IDE_SEL_CTL, &val); + id = FIELD_GET(PCI_IDE_SEL_CTL_ID, val); + if ((val & PCI_IDE_SEL_CTL_EN) && + !claim_stream(hb, id, pdev, i)) + return; + } + + /* Reserve link stream-ids that are already active on the device */ + for (u16 i = 0; i < nr_link_ide; ++i) { + int pos = ide_cap + PCI_IDE_LINK_STREAM_0 + i * PCI_IDE_LINK_BLOCK_SIZE; + u8 id; + + pci_read_config_dword(pdev, pos + PCI_IDE_LINK_CTL_0, &val); + id = FIELD_GET(PCI_IDE_LINK_CTL_ID, val); + if ((val & PCI_IDE_LINK_CTL_EN) && + !claim_stream(hb, id, NULL, -1)) + return; + } + + for (u16 i = 0; i < nr_streams; i++) { + int pos = __sel_ide_offset(ide_cap, nr_link_ide, i, nr_ide_mem); + + pci_read_config_dword(pdev, pos + PCI_IDE_SEL_CTL, &val); + if (val & PCI_IDE_SEL_CTL_EN) + continue; + val &= ~PCI_IDE_SEL_CTL_ID; + val |= FIELD_PREP(PCI_IDE_SEL_CTL_ID, PCI_IDE_RESERVED_STREAM_ID); + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_CTL, val); + } + + for (u16 i = 0; i < nr_link_ide; ++i) { + int pos = ide_cap + PCI_IDE_LINK_STREAM_0 + + i * PCI_IDE_LINK_BLOCK_SIZE; + + pci_read_config_dword(pdev, pos, &val); + if (val & PCI_IDE_LINK_CTL_EN) + continue; + val &= ~PCI_IDE_LINK_CTL_ID; + val |= FIELD_PREP(PCI_IDE_LINK_CTL_ID, PCI_IDE_RESERVED_STREAM_ID); + pci_write_config_dword(pdev, pos, val); + } + + pdev->ide_cap = ide_cap; + pdev->nr_link_ide = nr_link_ide; + pdev->nr_sel_ide = nr_streams; + pdev->nr_ide_mem = nr_ide_mem; +} + +struct stream_index { + struct ida *ida; + u8 stream_index; +}; + +static void free_stream_index(struct stream_index *stream) +{ + ida_free(stream->ida, stream->stream_index); +} + +DEFINE_FREE(free_stream, struct stream_index *, if (_T) free_stream_index(_T)) +static struct stream_index *alloc_stream_index(struct ida *ida, u16 max, + struct stream_index *stream) +{ + int id; + + if (!max) + return NULL; + + id = ida_alloc_max(ida, max - 1, GFP_KERNEL); + if (id < 0) + return NULL; + + *stream = (struct stream_index) { + .ida = ida, + .stream_index = id, + }; + return stream; +} + +/** + * pci_ide_stream_alloc() - Reserve stream indices and probe for settings + * @pdev: IDE capable PCIe Endpoint Physical Function + * + * Retrieve the Requester ID range of @pdev for programming its Root + * Port IDE RID Association registers, and conversely retrieve the + * Requester ID of the Root Port for programming @pdev's IDE RID + * Association registers. + * + * Allocate a Selective IDE Stream Register Block instance per port. + * + * Allocate a platform stream resource from the associated host bridge. + * Retrieve stream association parameters for Requester ID range and + * address range restrictions for the stream. + */ +struct pci_ide *pci_ide_stream_alloc(struct pci_dev *pdev) +{ + /* EP, RP, + HB Stream allocation */ + struct stream_index __stream[PCI_IDE_HB + 1]; + struct pci_bus_region pref_assoc = { 0, -1 }; + struct pci_bus_region mem_assoc = { 0, -1 }; + struct resource *mem, *pref; + struct pci_host_bridge *hb; + struct pci_dev *rp, *br; + int num_vf, rid_end; + + if (!pci_is_pcie(pdev)) + return NULL; + + if (pci_pcie_type(pdev) != PCI_EXP_TYPE_ENDPOINT) + return NULL; + + if (!pdev->ide_cap) + return NULL; + + struct pci_ide *ide __free(kfree) = kzalloc_obj(*ide); + if (!ide) + return NULL; + + hb = pci_find_host_bridge(pdev->bus); + struct stream_index *hb_stream __free(free_stream) = alloc_stream_index( + &hb->ide_stream_ida, hb->nr_ide_streams, &__stream[PCI_IDE_HB]); + if (!hb_stream) + return NULL; + + rp = pcie_find_root_port(pdev); + struct stream_index *rp_stream __free(free_stream) = alloc_stream_index( + &rp->ide_stream_ida, rp->nr_sel_ide, &__stream[PCI_IDE_RP]); + if (!rp_stream) + return NULL; + + struct stream_index *ep_stream __free(free_stream) = alloc_stream_index( + &pdev->ide_stream_ida, pdev->nr_sel_ide, &__stream[PCI_IDE_EP]); + if (!ep_stream) + return NULL; + + /* for SR-IOV case, cover all VFs */ + num_vf = pci_num_vf(pdev); + if (num_vf) + rid_end = PCI_DEVID(pci_iov_virtfn_bus(pdev, num_vf - 1), + pci_iov_virtfn_devfn(pdev, num_vf - 1)); + else + rid_end = pci_dev_id(pdev); + + br = pci_upstream_bridge(pdev); + if (!br) + return NULL; + + /* + * Check if the device consumes memory and/or prefetch-memory. Setup + * downstream address association ranges for each. + */ + mem = pci_resource_n(br, PCI_BRIDGE_MEM_WINDOW); + pref = pci_resource_n(br, PCI_BRIDGE_PREF_MEM_WINDOW); + if (resource_assigned(mem)) + pcibios_resource_to_bus(br->bus, &mem_assoc, mem); + if (resource_assigned(pref)) + pcibios_resource_to_bus(br->bus, &pref_assoc, pref); + + *ide = (struct pci_ide) { + .pdev = pdev, + .partner = { + [PCI_IDE_EP] = { + .rid_start = pci_dev_id(rp), + .rid_end = pci_dev_id(rp), + .stream_index = no_free_ptr(ep_stream)->stream_index, + /* Disable upstream address association */ + .mem_assoc = { 0, -1 }, + .pref_assoc = { 0, -1 }, + }, + [PCI_IDE_RP] = { + .rid_start = pci_dev_id(pdev), + .rid_end = rid_end, + .stream_index = no_free_ptr(rp_stream)->stream_index, + .mem_assoc = mem_assoc, + .pref_assoc = pref_assoc, + }, + }, + .host_bridge_stream = no_free_ptr(hb_stream)->stream_index, + .stream_id = -1, + }; + + return_ptr(ide); +} +EXPORT_SYMBOL_GPL(pci_ide_stream_alloc); + +/** + * pci_ide_stream_free() - unwind pci_ide_stream_alloc() + * @ide: idle IDE settings descriptor + * + * Free all of the stream index (register block) allocations acquired by + * pci_ide_stream_alloc(). The stream represented by @ide is assumed to + * be unregistered and not instantiated in any device. + */ +void pci_ide_stream_free(struct pci_ide *ide) +{ + struct pci_dev *pdev = ide->pdev; + struct pci_dev *rp = pcie_find_root_port(pdev); + struct pci_host_bridge *hb = pci_find_host_bridge(pdev->bus); + + ida_free(&pdev->ide_stream_ida, ide->partner[PCI_IDE_EP].stream_index); + ida_free(&rp->ide_stream_ida, ide->partner[PCI_IDE_RP].stream_index); + ida_free(&hb->ide_stream_ida, ide->host_bridge_stream); + kfree(ide); +} +EXPORT_SYMBOL_GPL(pci_ide_stream_free); + +/** + * pci_ide_stream_release() - unwind and release an @ide context + * @ide: partially or fully registered IDE settings descriptor + * + * In support of automatic cleanup of IDE setup routines perform IDE + * teardown in expected reverse order of setup and with respect to which + * aspects of IDE setup have successfully completed. + * + * Be careful that setup order mirrors this shutdown order. Otherwise, + * open code releasing the IDE context. + */ +void pci_ide_stream_release(struct pci_ide *ide) +{ + struct pci_dev *pdev = ide->pdev; + struct pci_dev *rp = pcie_find_root_port(pdev); + + if (ide->partner[PCI_IDE_RP].enable) + pci_ide_stream_disable(rp, ide); + + if (ide->partner[PCI_IDE_EP].enable) + pci_ide_stream_disable(pdev, ide); + + if (ide->partner[PCI_IDE_RP].setup) + pci_ide_stream_teardown(rp, ide); + + if (ide->partner[PCI_IDE_EP].setup) + pci_ide_stream_teardown(pdev, ide); + + if (ide->name) + pci_ide_stream_unregister(ide); + + pci_ide_stream_free(ide); +} +EXPORT_SYMBOL_GPL(pci_ide_stream_release); + +struct pci_ide_stream_id { + struct pci_host_bridge *hb; + u8 stream_id; +}; + +static struct pci_ide_stream_id * +request_stream_id(struct pci_host_bridge *hb, u8 stream_id, + struct pci_ide_stream_id *sid) +{ + if (!reserve_stream_id(hb, stream_id)) + return NULL; + + *sid = (struct pci_ide_stream_id) { + .hb = hb, + .stream_id = stream_id, + }; + + return sid; +} +DEFINE_FREE(free_stream_id, struct pci_ide_stream_id *, + if (_T) ida_free(&_T->hb->ide_stream_ids_ida, _T->stream_id)) + +/** + * pci_ide_stream_register() - Prepare to activate an IDE Stream + * @ide: IDE settings descriptor + * + * After a Stream ID has been acquired for @ide, record the presence of + * the stream in sysfs. The expectation is that @ide is immutable while + * registered. + */ +int pci_ide_stream_register(struct pci_ide *ide) +{ + struct pci_dev *pdev = ide->pdev; + struct pci_host_bridge *hb = pci_find_host_bridge(pdev->bus); + struct pci_ide_stream_id __sid; + u8 ep_stream, rp_stream; + int rc; + + if (ide->stream_id < 0 || ide->stream_id > U8_MAX) { + pci_err(pdev, "Setup fail: Invalid Stream ID: %d\n", ide->stream_id); + return -ENXIO; + } + + struct pci_ide_stream_id *sid __free(free_stream_id) = + request_stream_id(hb, ide->stream_id, &__sid); + if (!sid) { + pci_err(pdev, "Setup fail: Stream ID %d in use\n", ide->stream_id); + return -EBUSY; + } + + ep_stream = ide->partner[PCI_IDE_EP].stream_index; + rp_stream = ide->partner[PCI_IDE_RP].stream_index; + const char *name __free(kfree) = kasprintf(GFP_KERNEL, "stream%d.%d.%d", + ide->host_bridge_stream, + rp_stream, ep_stream); + if (!name) + return -ENOMEM; + + rc = sysfs_create_link(&hb->dev.kobj, &pdev->dev.kobj, name); + if (rc) + return rc; + + ide->name = no_free_ptr(name); + + /* Stream ID reservation recorded in @ide is now successfully registered */ + retain_and_null_ptr(sid); + + return 0; +} +EXPORT_SYMBOL_GPL(pci_ide_stream_register); + +/** + * pci_ide_stream_unregister() - unwind pci_ide_stream_register() + * @ide: idle IDE settings descriptor + * + * In preparation for freeing @ide, remove sysfs enumeration for the + * stream. + */ +void pci_ide_stream_unregister(struct pci_ide *ide) +{ + struct pci_dev *pdev = ide->pdev; + struct pci_host_bridge *hb = pci_find_host_bridge(pdev->bus); + + sysfs_remove_link(&hb->dev.kobj, ide->name); + kfree(ide->name); + ida_free(&hb->ide_stream_ids_ida, ide->stream_id); + ide->name = NULL; +} +EXPORT_SYMBOL_GPL(pci_ide_stream_unregister); + +static int pci_ide_domain(struct pci_dev *pdev) +{ + if (pdev->fm_enabled) + return pci_domain_nr(pdev->bus); + return 0; +} + +struct pci_ide_partner *pci_ide_to_settings(struct pci_dev *pdev, struct pci_ide *ide) +{ + if (!pci_is_pcie(pdev)) { + pci_warn_once(pdev, "not a PCIe device\n"); + return NULL; + } + + switch (pci_pcie_type(pdev)) { + case PCI_EXP_TYPE_ENDPOINT: + if (pdev != ide->pdev) { + pci_warn_once(pdev, "setup expected Endpoint: %s\n", pci_name(ide->pdev)); + return NULL; + } + return &ide->partner[PCI_IDE_EP]; + case PCI_EXP_TYPE_ROOT_PORT: { + struct pci_dev *rp = pcie_find_root_port(ide->pdev); + + if (pdev != rp) { + pci_warn_once(pdev, "setup expected Root Port: %s\n", + pci_name(rp)); + return NULL; + } + return &ide->partner[PCI_IDE_RP]; + } + default: + pci_warn_once(pdev, "invalid device type\n"); + return NULL; + } +} +EXPORT_SYMBOL_GPL(pci_ide_to_settings); + +static void set_ide_sel_ctl(struct pci_dev *pdev, struct pci_ide *ide, + struct pci_ide_partner *settings, int pos, + bool enable) +{ + u32 val = FIELD_PREP(PCI_IDE_SEL_CTL_ID, ide->stream_id) | + FIELD_PREP(PCI_IDE_SEL_CTL_DEFAULT, settings->default_stream) | + FIELD_PREP(PCI_IDE_SEL_CTL_CFG_EN, pdev->ide_cfg) | + FIELD_PREP(PCI_IDE_SEL_CTL_TEE_LIMITED, pdev->ide_tee_limit) | + FIELD_PREP(PCI_IDE_SEL_CTL_EN, enable); + + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_CTL, val); +} + +#define SEL_ADDR1_LOWER GENMASK(31, 20) +#define SEL_ADDR_UPPER GENMASK_ULL(63, 32) +#define PREP_PCI_IDE_SEL_ADDR1(base, limit) \ + (FIELD_PREP(PCI_IDE_SEL_ADDR_1_VALID, 1) | \ + FIELD_PREP(PCI_IDE_SEL_ADDR_1_BASE_LOW, \ + FIELD_GET(SEL_ADDR1_LOWER, (base))) | \ + FIELD_PREP(PCI_IDE_SEL_ADDR_1_LIMIT_LOW, \ + FIELD_GET(SEL_ADDR1_LOWER, (limit)))) + +static void mem_assoc_to_regs(struct pci_bus_region *region, + struct pci_ide_regs *regs, int idx) +{ + /* convert to u64 range for bitfield size checks */ + struct range r = { region->start, region->end }; + + regs->addr[idx].assoc1 = PREP_PCI_IDE_SEL_ADDR1(r.start, r.end); + regs->addr[idx].assoc2 = FIELD_GET(SEL_ADDR_UPPER, r.end); + regs->addr[idx].assoc3 = FIELD_GET(SEL_ADDR_UPPER, r.start); +} + +/** + * pci_ide_stream_to_regs() - convert IDE settings to association register values + * @pdev: PCIe device object for either a Root Port or Endpoint Partner Port + * @ide: registered IDE settings descriptor + * @regs: output register values + */ +static void pci_ide_stream_to_regs(struct pci_dev *pdev, struct pci_ide *ide, + struct pci_ide_regs *regs) +{ + struct pci_ide_partner *settings = pci_ide_to_settings(pdev, ide); + int assoc_idx = 0; + + memset(regs, 0, sizeof(*regs)); + + if (!settings) + return; + + regs->rid1 = FIELD_PREP(PCI_IDE_SEL_RID_1_LIMIT, settings->rid_end); + + regs->rid2 = FIELD_PREP(PCI_IDE_SEL_RID_2_VALID, 1) | + FIELD_PREP(PCI_IDE_SEL_RID_2_BASE, settings->rid_start) | + FIELD_PREP(PCI_IDE_SEL_RID_2_SEG, pci_ide_domain(pdev)); + + if (pdev->nr_ide_mem && pci_bus_region_size(&settings->mem_assoc)) { + mem_assoc_to_regs(&settings->mem_assoc, regs, assoc_idx); + assoc_idx++; + } + + if (pdev->nr_ide_mem > assoc_idx && + pci_bus_region_size(&settings->pref_assoc)) { + mem_assoc_to_regs(&settings->pref_assoc, regs, assoc_idx); + assoc_idx++; + } + + regs->nr_addr = assoc_idx; +} + +/** + * pci_ide_stream_setup() - program settings to Selective IDE Stream registers + * @pdev: PCIe device object for either a Root Port or Endpoint Partner Port + * @ide: registered IDE settings descriptor + * + * When @pdev is a PCI_EXP_TYPE_ENDPOINT then the PCI_IDE_EP partner + * settings are written to @pdev's Selective IDE Stream register block, + * and when @pdev is a PCI_EXP_TYPE_ROOT_PORT, the PCI_IDE_RP settings + * are selected. + */ +void pci_ide_stream_setup(struct pci_dev *pdev, struct pci_ide *ide) +{ + struct pci_ide_partner *settings = pci_ide_to_settings(pdev, ide); + struct pci_ide_regs regs; + int pos; + + if (!settings) + return; + + pci_ide_stream_to_regs(pdev, ide, ®s); + + pos = sel_ide_offset(pdev, settings); + + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_RID_1, regs.rid1); + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_RID_2, regs.rid2); + + for (int i = 0; i < regs.nr_addr; i++) { + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_1(i), + regs.addr[i].assoc1); + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_2(i), + regs.addr[i].assoc2); + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_3(i), + regs.addr[i].assoc3); + } + + /* clear extra unused address association blocks */ + for (int i = regs.nr_addr; i < pdev->nr_ide_mem; i++) { + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_1(i), 0); + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_2(i), 0); + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_3(i), 0); + } + + /* + * Setup control register early for devices that expect + * stream_id is set during key programming. + */ + set_ide_sel_ctl(pdev, ide, settings, pos, false); + settings->setup = 1; +} +EXPORT_SYMBOL_GPL(pci_ide_stream_setup); + +/** + * pci_ide_stream_teardown() - disable the stream and clear all settings + * @pdev: PCIe device object for either a Root Port or Endpoint Partner Port + * @ide: registered IDE settings descriptor + * + * For stream destruction, zero all registers that may have been written + * by pci_ide_stream_setup(). Consider pci_ide_stream_disable() to leave + * settings in place while temporarily disabling the stream. + */ +void pci_ide_stream_teardown(struct pci_dev *pdev, struct pci_ide *ide) +{ + struct pci_ide_partner *settings = pci_ide_to_settings(pdev, ide); + int pos, i; + + if (!settings) + return; + + pos = sel_ide_offset(pdev, settings); + + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_CTL, 0); + + for (i = 0; i < pdev->nr_ide_mem; i++) { + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_1(i), 0); + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_2(i), 0); + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_ADDR_3(i), 0); + } + + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_RID_2, 0); + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_RID_1, 0); + settings->setup = 0; +} +EXPORT_SYMBOL_GPL(pci_ide_stream_teardown); + +/** + * pci_ide_stream_enable() - enable a Selective IDE Stream + * @pdev: PCIe device object for either a Root Port or Endpoint Partner Port + * @ide: registered and setup IDE settings descriptor + * + * Activate the stream by writing to the Selective IDE Stream Control + * Register. + * + * Return: 0 if the stream successfully entered the "secure" state, and -EINVAL + * if @ide is invalid, and -ENXIO if the stream fails to enter the secure state. + * + * Note that the state may go "insecure" at any point after returning 0, but + * those events are equivalent to a "link down" event and handled via + * asynchronous error reporting. + * + * Caller is responsible to clear the enable bit in the -ENXIO case. + */ +int pci_ide_stream_enable(struct pci_dev *pdev, struct pci_ide *ide) +{ + struct pci_ide_partner *settings = pci_ide_to_settings(pdev, ide); + int pos; + u32 val; + + if (!settings) + return -EINVAL; + + pos = sel_ide_offset(pdev, settings); + + set_ide_sel_ctl(pdev, ide, settings, pos, true); + settings->enable = 1; + + pci_read_config_dword(pdev, pos + PCI_IDE_SEL_STS, &val); + if (FIELD_GET(PCI_IDE_SEL_STS_STATE, val) != + PCI_IDE_SEL_STS_STATE_SECURE) + return -ENXIO; + + return 0; +} +EXPORT_SYMBOL_GPL(pci_ide_stream_enable); + +/** + * pci_ide_stream_disable() - disable a Selective IDE Stream + * @pdev: PCIe device object for either a Root Port or Endpoint Partner Port + * @ide: registered and setup IDE settings descriptor + * + * Clear the Selective IDE Stream Control Register, but leave all other + * registers untouched. + */ +void pci_ide_stream_disable(struct pci_dev *pdev, struct pci_ide *ide) +{ + struct pci_ide_partner *settings = pci_ide_to_settings(pdev, ide); + int pos; + + if (!settings) + return; + + pos = sel_ide_offset(pdev, settings); + + pci_write_config_dword(pdev, pos + PCI_IDE_SEL_CTL, 0); + settings->enable = 0; +} +EXPORT_SYMBOL_GPL(pci_ide_stream_disable); + +void pci_ide_init_host_bridge(struct pci_host_bridge *hb) +{ + hb->nr_ide_streams = 256; + ida_init(&hb->ide_stream_ida); + ida_init(&hb->ide_stream_ids_ida); + reserve_stream_id(hb, PCI_IDE_RESERVED_STREAM_ID); +} + +static ssize_t available_secure_streams_show(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + struct pci_host_bridge *hb = to_pci_host_bridge(dev); + int nr = READ_ONCE(hb->nr_ide_streams); + int avail = nr; + + if (!nr) + return -ENXIO; + + /* + * Yes, this is inefficient and racy, but it is only for occasional + * platform resource surveys. Worst case is bounded to 256 streams. + */ + for (int i = 0; i < nr; i++) + if (ida_exists(&hb->ide_stream_ida, i)) + avail--; + return sysfs_emit(buf, "%d\n", avail); +} +static DEVICE_ATTR_RO(available_secure_streams); + +static struct attribute *pci_ide_attrs[] = { + &dev_attr_available_secure_streams.attr, + NULL +}; + +static umode_t pci_ide_attr_visible(struct kobject *kobj, struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct pci_host_bridge *hb = to_pci_host_bridge(dev); + + if (a == &dev_attr_available_secure_streams.attr) + if (!hb->nr_ide_streams) + return 0; + + return a->mode; +} + +const struct attribute_group pci_ide_attr_group = { + .attrs = pci_ide_attrs, + .is_visible = pci_ide_attr_visible, +}; + +/** + * pci_ide_set_nr_streams() - sets size of the pool of IDE Stream resources + * @hb: host bridge boundary for the stream pool + * @nr: number of streams + * + * Platform PCI init and/or expert test module use only. Limit IDE + * Stream establishment by setting the number of stream resources + * available at the host bridge. Platform init code must set this before + * the first pci_ide_stream_alloc() call if the platform has less than the + * default of 256 streams per host-bridge. + * + * The "PCI_IDE" symbol namespace is required because this is typically + * a detail that is settled in early PCI init. I.e. this export is not + * for endpoint drivers. + */ +void pci_ide_set_nr_streams(struct pci_host_bridge *hb, u16 nr) +{ + hb->nr_ide_streams = min(nr, 256); + WARN_ON_ONCE(!ida_is_empty(&hb->ide_stream_ida)); + sysfs_update_group(&hb->dev.kobj, &pci_ide_attr_group); +} +EXPORT_SYMBOL_NS_GPL(pci_ide_set_nr_streams, "PCI_IDE"); + +void pci_ide_destroy(struct pci_dev *pdev) +{ + ida_destroy(&pdev->ide_stream_ida); +} diff --git a/drivers/pci/iomap.c b/drivers/pci/iomap.c index fe706ed946df..ea86c282a386 100644 --- a/drivers/pci/iomap.c +++ b/drivers/pci/iomap.c @@ -25,10 +25,6 @@ * * @maxlen specifies the maximum length to map. If you want to get access to * the complete BAR from offset to the end, pass %0 here. - * - * NOTE: - * This function is never managed, even if you initialized with - * pcim_enable_device(). * */ void __iomem *pci_iomap_range(struct pci_dev *dev, int bar, @@ -76,10 +72,6 @@ EXPORT_SYMBOL(pci_iomap_range); * * @maxlen specifies the maximum length to map. If you want to get access to * the complete BAR from offset to the end, pass %0 here. - * - * NOTE: - * This function is never managed, even if you initialized with - * pcim_enable_device(). * */ void __iomem *pci_iomap_wc_range(struct pci_dev *dev, int bar, @@ -127,10 +119,6 @@ EXPORT_SYMBOL_GPL(pci_iomap_wc_range); * * @maxlen specifies the maximum length to map. If you want to get access to * the complete BAR without checking for its length first, pass %0 here. - * - * NOTE: - * This function is never managed, even if you initialized with - * pcim_enable_device(). If you need automatic cleanup, use pcim_iomap(). * */ void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen) { @@ -152,10 +140,6 @@ EXPORT_SYMBOL(pci_iomap); * * @maxlen specifies the maximum length to map. If you want to get access to * the complete BAR without checking for its length first, pass %0 here. - * - * NOTE: - * This function is never managed, even if you initialized with - * pcim_enable_device(). * */ void __iomem *pci_iomap_wc(struct pci_dev *dev, int bar, unsigned long maxlen) { diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index 10693b5d7eb6..91ac4e37ecb9 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -7,11 +7,16 @@ * Copyright (C) 2009 Intel Corporation, Yu Zhao <yu.zhao@intel.com> */ +#include <linux/bitfield.h> +#include <linux/bits.h> +#include <linux/log2.h> #include <linux/pci.h> +#include <linux/sizes.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/string.h> #include <linux/delay.h> +#include <asm/div64.h> #include "pci.h" #define VIRTFN_ID_LEN 17 /* "virtfn%u\0" for 2^32 - 1 */ @@ -150,7 +155,28 @@ resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno) if (!dev->is_physfn) return 0; - return dev->sriov->barsz[resno - PCI_IOV_RESOURCES]; + return dev->sriov->barsz[pci_resource_num_to_vf_bar(resno)]; +} + +void pci_iov_resource_set_size(struct pci_dev *dev, int resno, int size) +{ + if (!pci_resource_is_iov(resno)) { + pci_warn(dev, "%s is not an IOV resource\n", + pci_resource_name(dev, resno)); + return; + } + + resno = pci_resource_num_to_vf_bar(resno); + dev->sriov->barsz[resno] = pci_rebar_size_to_bytes(size); +} + +bool pci_iov_is_memory_decoding_enabled(struct pci_dev *dev) +{ + u16 cmd; + + pci_read_config_word(dev, dev->sriov->pos + PCI_SRIOV_CTRL, &cmd); + + return cmd & PCI_SRIOV_CTRL_MSE; } static void pci_read_vf_config_common(struct pci_dev *virtfn) @@ -341,12 +367,14 @@ int pci_iov_add_virtfn(struct pci_dev *dev, int id) virtfn->multifunction = 0; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &dev->resource[i + PCI_IOV_RESOURCES]; + int idx = pci_resource_num_from_vf_bar(i); + + res = &dev->resource[idx]; if (!res->parent) continue; virtfn->resource[i].name = pci_name(virtfn); virtfn->resource[i].flags = res->flags; - size = pci_iov_resource_size(dev, i + PCI_IOV_RESOURCES); + size = pci_iov_resource_size(dev, idx); resource_set_range(&virtfn->resource[i], res->start + size * id, size); rc = request_resource(res, &virtfn->resource[i]); @@ -467,7 +495,9 @@ static ssize_t sriov_numvfs_store(struct device *dev, if (num_vfs == 0) { /* disable VFs */ + pci_lock_rescan_remove(); ret = pdev->driver->sriov_configure(pdev, 0); + pci_unlock_rescan_remove(); goto exit; } @@ -479,7 +509,9 @@ static ssize_t sriov_numvfs_store(struct device *dev, goto exit; } + pci_lock_rescan_remove(); ret = pdev->driver->sriov_configure(pdev, num_vfs); + pci_unlock_rescan_remove(); if (ret < 0) goto exit; @@ -643,8 +675,13 @@ static int sriov_enable(struct pci_dev *dev, int nr_virtfn) nres = 0; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - bars |= (1 << (i + PCI_IOV_RESOURCES)); - res = &dev->resource[i + PCI_IOV_RESOURCES]; + int idx = pci_resource_num_from_vf_bar(i); + resource_size_t vf_bar_sz = pci_iov_resource_size(dev, idx); + + bars |= (1 << idx); + res = &dev->resource[idx]; + if (vf_bar_sz * nr_virtfn > resource_size(res)) + continue; if (res->parent) nres++; } @@ -800,7 +837,7 @@ found: pgsz &= ~(pgsz - 1); pci_write_config_dword(dev, pos + PCI_SRIOV_SYS_PGSIZE, pgsz); - iov = kzalloc(sizeof(*iov), GFP_KERNEL); + iov = kzalloc_obj(*iov); if (!iov) return -ENOMEM; @@ -810,8 +847,10 @@ found: nres = 0; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &dev->resource[i + PCI_IOV_RESOURCES]; - res_name = pci_resource_name(dev, i + PCI_IOV_RESOURCES); + int idx = pci_resource_num_from_vf_bar(i); + + res = &dev->resource[idx]; + res_name = pci_resource_name(dev, idx); /* * If it is already FIXED, don't change it, something @@ -850,6 +889,7 @@ found: pci_read_config_byte(dev, pos + PCI_SRIOV_FUNC_LINK, &iov->link); if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_END) iov->link = PCI_DEVFN(PCI_SLOT(dev->devfn), iov->link); + iov->vf_rebar_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_VF_REBAR); if (pdev) iov->dev = pci_dev_get(pdev); @@ -869,7 +909,7 @@ fail_max_buses: dev->is_physfn = 0; failed: for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - res = &dev->resource[i + PCI_IOV_RESOURCES]; + res = &dev->resource[pci_resource_num_from_vf_bar(i)]; res->flags = 0; } @@ -888,6 +928,30 @@ static void sriov_release(struct pci_dev *dev) dev->sriov = NULL; } +static void sriov_restore_vf_rebar_state(struct pci_dev *dev) +{ + unsigned int pos, nbars, i; + u32 ctrl; + + pos = pci_iov_vf_rebar_cap(dev); + if (!pos) + return; + + pci_read_config_dword(dev, pos + PCI_VF_REBAR_CTRL, &ctrl); + nbars = FIELD_GET(PCI_VF_REBAR_CTRL_NBAR_MASK, ctrl); + + for (i = 0; i < nbars; i++, pos += 8) { + int bar_idx, size; + + pci_read_config_dword(dev, pos + PCI_VF_REBAR_CTRL, &ctrl); + bar_idx = FIELD_GET(PCI_VF_REBAR_CTRL_BAR_IDX, ctrl); + size = pci_rebar_bytes_to_size(dev->sriov->barsz[bar_idx]); + ctrl &= ~PCI_VF_REBAR_CTRL_BAR_SIZE; + ctrl |= FIELD_PREP(PCI_VF_REBAR_CTRL_BAR_SIZE, size); + pci_write_config_dword(dev, pos + PCI_VF_REBAR_CTRL, ctrl); + } +} + static void sriov_restore_state(struct pci_dev *dev) { int i; @@ -907,7 +971,7 @@ static void sriov_restore_state(struct pci_dev *dev) pci_write_config_word(dev, iov->pos + PCI_SRIOV_CTRL, ctrl); for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) - pci_update_resource(dev, i + PCI_IOV_RESOURCES); + pci_update_resource(dev, pci_resource_num_from_vf_bar(i)); pci_write_config_dword(dev, iov->pos + PCI_SRIOV_SYS_PGSIZE, iov->pgsz); pci_iov_set_numvfs(dev, iov->num_VFs); @@ -973,7 +1037,7 @@ void pci_iov_update_resource(struct pci_dev *dev, int resno) { struct pci_sriov *iov = dev->is_physfn ? dev->sriov : NULL; struct resource *res = pci_resource_n(dev, resno); - int vf_bar = resno - PCI_IOV_RESOURCES; + int vf_bar = pci_resource_num_to_vf_bar(resno); struct pci_bus_region region; u16 cmd; u32 new; @@ -1047,8 +1111,10 @@ resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno) */ void pci_restore_iov_state(struct pci_dev *dev) { - if (dev->is_physfn) + if (dev->is_physfn) { + sriov_restore_vf_rebar_state(dev); sriov_restore_state(dev); + } } /** @@ -1255,3 +1321,59 @@ int pci_sriov_configure_simple(struct pci_dev *dev, int nr_virtfn) return nr_virtfn; } EXPORT_SYMBOL_GPL(pci_sriov_configure_simple); + +/** + * pci_iov_vf_bar_set_size - set a new size for a VF BAR + * @dev: the PCI device + * @resno: the resource number + * @size: new size as defined in the spec (0=1MB, 31=128TB) + * + * Set the new size of a VF BAR that supports VF resizable BAR capability. + * Unlike pci_resize_resource(), this does not cause the resource that + * reserves the MMIO space (originally up to total_VFs) to be resized, which + * means that following calls to pci_enable_sriov() can fail if the resources + * no longer fit. + * + * Return: 0 on success, or negative on failure. + */ +int pci_iov_vf_bar_set_size(struct pci_dev *dev, int resno, int size) +{ + if (!pci_resource_is_iov(resno)) + return -EINVAL; + + if (pci_iov_is_memory_decoding_enabled(dev)) + return -EBUSY; + + if (!pci_rebar_size_supported(dev, resno, size)) + return -EINVAL; + + return pci_rebar_set_size(dev, resno, size); +} +EXPORT_SYMBOL_GPL(pci_iov_vf_bar_set_size); + +/** + * pci_iov_vf_bar_get_sizes - get VF BAR sizes allowing to create up to num_vfs + * @dev: the PCI device + * @resno: the resource number + * @num_vfs: number of VFs + * + * Get the sizes of a VF resizable BAR that can accommodate @num_vfs within + * the currently assigned size of the resource @resno. + * + * Return: A bitmask of sizes in format defined in the spec (bit 0=1MB, + * bit 31=128TB). + */ +u32 pci_iov_vf_bar_get_sizes(struct pci_dev *dev, int resno, int num_vfs) +{ + u64 vf_len = pci_resource_len(dev, resno); + u64 sizes; + + if (!num_vfs) + return 0; + + do_div(vf_len, num_vfs); + sizes = (roundup_pow_of_two(vf_len + 1) - 1) >> ilog2(SZ_1M); + + return sizes & pci_rebar_get_possible_sizes(dev, resno); +} +EXPORT_SYMBOL_GPL(pci_iov_vf_bar_get_sizes); diff --git a/drivers/pci/msi/api.c b/drivers/pci/msi/api.c index 17ec6332cb1d..818d55fbad0d 100644 --- a/drivers/pci/msi/api.c +++ b/drivers/pci/msi/api.c @@ -53,10 +53,9 @@ void pci_disable_msi(struct pci_dev *dev) if (!pci_msi_enabled() || !dev || !dev->msi_enabled) return; - msi_lock_descs(&dev->dev); + guard(msi_descs_lock)(&dev->dev); pci_msi_shutdown(dev); pci_free_msi_irqs(dev); - msi_unlock_descs(&dev->dev); } EXPORT_SYMBOL(pci_disable_msi); @@ -196,10 +195,9 @@ void pci_disable_msix(struct pci_dev *dev) if (!pci_msi_enabled() || !dev || !dev->msix_enabled) return; - msi_lock_descs(&dev->dev); + guard(msi_descs_lock)(&dev->dev); pci_msix_shutdown(dev); pci_free_msi_irqs(dev); - msi_unlock_descs(&dev->dev); } EXPORT_SYMBOL(pci_disable_msix); @@ -401,7 +399,7 @@ EXPORT_SYMBOL_GPL(pci_restore_msi_state); * Return: true if MSI has not been globally disabled through ACPI FADT, * PCI bridge quirks, or the "pci=nomsi" kernel command-line option. */ -int pci_msi_enabled(void) +bool pci_msi_enabled(void) { return pci_msi_enable; } diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c index d7ba8795d60f..6e65f0f44112 100644 --- a/drivers/pci/msi/irqdomain.c +++ b/drivers/pci/msi/irqdomain.c @@ -49,119 +49,52 @@ static void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg * __pci_write_msi_msg(desc, msg); } -/** - * pci_msi_domain_calc_hwirq - Generate a unique ID for an MSI source - * @desc: Pointer to the MSI descriptor - * - * The ID number is only used within the irqdomain. +/* + * Per device MSI[-X] domain functionality */ -static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc) -{ - struct pci_dev *dev = msi_desc_to_pci_dev(desc); - - return (irq_hw_number_t)desc->msi_index | - pci_dev_id(dev) << 11 | - ((irq_hw_number_t)(pci_domain_nr(dev->bus) & 0xFFFFFFFF)) << 27; -} - -static void pci_msi_domain_set_desc(msi_alloc_info_t *arg, - struct msi_desc *desc) +static void pci_device_domain_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) { arg->desc = desc; - arg->hwirq = pci_msi_domain_calc_hwirq(desc); + arg->hwirq = desc->msi_index; } -static struct msi_domain_ops pci_msi_domain_ops_default = { - .set_desc = pci_msi_domain_set_desc, -}; - -static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info) +static void cond_shutdown_parent(struct irq_data *data) { - struct msi_domain_ops *ops = info->ops; + struct msi_domain_info *info = data->domain->host_data; - if (ops == NULL) { - info->ops = &pci_msi_domain_ops_default; - } else { - if (ops->set_desc == NULL) - ops->set_desc = pci_msi_domain_set_desc; - } + if (unlikely(info->flags & MSI_FLAG_PCI_MSI_STARTUP_PARENT)) + irq_chip_shutdown_parent(data); + else if (unlikely(info->flags & MSI_FLAG_PCI_MSI_MASK_PARENT)) + irq_chip_mask_parent(data); } -static void pci_msi_domain_update_chip_ops(struct msi_domain_info *info) +static unsigned int cond_startup_parent(struct irq_data *data) { - struct irq_chip *chip = info->chip; - - BUG_ON(!chip); - if (!chip->irq_write_msi_msg) - chip->irq_write_msi_msg = pci_msi_domain_write_msg; - if (!chip->irq_mask) - chip->irq_mask = pci_msi_mask_irq; - if (!chip->irq_unmask) - chip->irq_unmask = pci_msi_unmask_irq; -} - -/** - * pci_msi_create_irq_domain - Create a MSI interrupt domain - * @fwnode: Optional fwnode of the interrupt controller - * @info: MSI domain info - * @parent: Parent irq domain - * - * Updates the domain and chip ops and creates a MSI interrupt domain. - * - * Returns: - * A domain pointer or NULL in case of failure. - */ -struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, - struct msi_domain_info *info, - struct irq_domain *parent) -{ - if (WARN_ON(info->flags & MSI_FLAG_LEVEL_CAPABLE)) - info->flags &= ~MSI_FLAG_LEVEL_CAPABLE; - - if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS) - pci_msi_domain_update_dom_ops(info); - if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS) - pci_msi_domain_update_chip_ops(info); - - /* Let the core code free MSI descriptors when freeing interrupts */ - info->flags |= MSI_FLAG_FREE_MSI_DESCS; - - info->flags |= MSI_FLAG_ACTIVATE_EARLY | MSI_FLAG_DEV_SYSFS; - if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE)) - info->flags |= MSI_FLAG_MUST_REACTIVATE; - - /* PCI-MSI is oneshot-safe */ - info->chip->flags |= IRQCHIP_ONESHOT_SAFE; - /* Let the core update the bus token */ - info->bus_token = DOMAIN_BUS_PCI_MSI; + struct msi_domain_info *info = data->domain->host_data; - return msi_create_irq_domain(fwnode, info, parent); -} -EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain); + if (unlikely(info->flags & MSI_FLAG_PCI_MSI_STARTUP_PARENT)) + return irq_chip_startup_parent(data); + else if (unlikely(info->flags & MSI_FLAG_PCI_MSI_MASK_PARENT)) + irq_chip_unmask_parent(data); -/* - * Per device MSI[-X] domain functionality - */ -static void pci_device_domain_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) -{ - arg->desc = desc; - arg->hwirq = desc->msi_index; + return 0; } -static __always_inline void cond_mask_parent(struct irq_data *data) +static void pci_irq_shutdown_msi(struct irq_data *data) { - struct msi_domain_info *info = data->domain->host_data; + struct msi_desc *desc = irq_data_get_msi_desc(data); - if (unlikely(info->flags & MSI_FLAG_PCI_MSI_MASK_PARENT)) - irq_chip_mask_parent(data); + pci_msi_mask(desc, BIT(data->irq - desc->irq)); + cond_shutdown_parent(data); } -static __always_inline void cond_unmask_parent(struct irq_data *data) +static unsigned int pci_irq_startup_msi(struct irq_data *data) { - struct msi_domain_info *info = data->domain->host_data; + struct msi_desc *desc = irq_data_get_msi_desc(data); + unsigned int ret = cond_startup_parent(data); - if (unlikely(info->flags & MSI_FLAG_PCI_MSI_MASK_PARENT)) - irq_chip_unmask_parent(data); + pci_msi_unmask(desc, BIT(data->irq - desc->irq)); + return ret; } static void pci_irq_mask_msi(struct irq_data *data) @@ -169,14 +102,12 @@ static void pci_irq_mask_msi(struct irq_data *data) struct msi_desc *desc = irq_data_get_msi_desc(data); pci_msi_mask(desc, BIT(data->irq - desc->irq)); - cond_mask_parent(data); } static void pci_irq_unmask_msi(struct irq_data *data) { struct msi_desc *desc = irq_data_get_msi_desc(data); - cond_unmask_parent(data); pci_msi_unmask(desc, BIT(data->irq - desc->irq)); } @@ -194,6 +125,8 @@ static void pci_irq_unmask_msi(struct irq_data *data) static const struct msi_domain_template pci_msi_template = { .chip = { .name = "PCI-MSI", + .irq_startup = pci_irq_startup_msi, + .irq_shutdown = pci_irq_shutdown_msi, .irq_mask = pci_irq_mask_msi, .irq_unmask = pci_irq_unmask_msi, .irq_write_msi_msg = pci_msi_domain_write_msg, @@ -210,29 +143,44 @@ static const struct msi_domain_template pci_msi_template = { }, }; +static void pci_irq_shutdown_msix(struct irq_data *data) +{ + pci_msix_mask(irq_data_get_msi_desc(data)); + cond_shutdown_parent(data); +} + +static unsigned int pci_irq_startup_msix(struct irq_data *data) +{ + unsigned int ret = cond_startup_parent(data); + + pci_msix_unmask(irq_data_get_msi_desc(data)); + return ret; +} + static void pci_irq_mask_msix(struct irq_data *data) { pci_msix_mask(irq_data_get_msi_desc(data)); - cond_mask_parent(data); } static void pci_irq_unmask_msix(struct irq_data *data) { - cond_unmask_parent(data); pci_msix_unmask(irq_data_get_msi_desc(data)); } -static void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg, - struct msi_desc *desc) +void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg, + struct msi_desc *desc) { /* Don't fiddle with preallocated MSI descriptors */ if (!desc->pci.mask_base) msix_prepare_msi_desc(to_pci_dev(desc->dev), desc); } +EXPORT_SYMBOL_GPL(pci_msix_prepare_desc); static const struct msi_domain_template pci_msix_template = { .chip = { .name = "PCI-MSIX", + .irq_startup = pci_irq_startup_msix, + .irq_shutdown = pci_irq_shutdown_msix, .irq_mask = pci_irq_mask_msix, .irq_unmask = pci_irq_unmask_msix, .irq_write_msi_msg = pci_msi_domain_write_msg, @@ -271,6 +219,7 @@ static bool pci_create_device_domain(struct pci_dev *pdev, const struct msi_doma /** * pci_setup_msi_device_domain - Setup a device MSI interrupt domain * @pdev: The PCI device to create the domain on + * @hwsize: The maximum number of MSI vectors * * Return: * True when: @@ -287,7 +236,7 @@ static bool pci_create_device_domain(struct pci_dev *pdev, const struct msi_doma * - The device is removed * - MSI is disabled and a MSI-X domain is created */ -bool pci_setup_msi_device_domain(struct pci_dev *pdev) +bool pci_setup_msi_device_domain(struct pci_dev *pdev, unsigned int hwsize) { if (WARN_ON_ONCE(pdev->msix_enabled)) return false; @@ -297,7 +246,7 @@ bool pci_setup_msi_device_domain(struct pci_dev *pdev) if (pci_match_device_domain(pdev, DOMAIN_BUS_PCI_DEVICE_MSIX)) msi_remove_device_irq_domain(&pdev->dev, MSI_DEFAULT_DOMAIN); - return pci_create_device_domain(pdev, &pci_msi_template, 1); + return pci_create_device_domain(pdev, &pci_msi_template, hwsize); } /** @@ -420,13 +369,46 @@ u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev) pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid); of_node = irq_domain_get_of_node(domain); - rid = of_node ? of_msi_map_id(&pdev->dev, of_node, rid) : + rid = of_node ? of_msi_xlate(&pdev->dev, &of_node, rid) : iort_msi_map_id(&pdev->dev, rid); return rid; } /** + * pci_msi_map_rid_ctlr_node - Get the MSI controller fwnode_handle and MSI requester id (RID) + * @domain: The interrupt domain + * @pdev: The PCI device + * @node: Pointer to store the MSI controller fwnode_handle + * + * Use the firmware data to find the MSI controller fwnode_handle for @pdev. + * If found map the RID and initialize @node with it. @node value must + * be set to NULL on entry. + * + * Returns: The RID. + */ +u32 pci_msi_map_rid_ctlr_node(struct irq_domain *domain, struct pci_dev *pdev, + struct fwnode_handle **node) +{ + u32 rid = pci_dev_id(pdev); + + pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid); + + /* Check whether the domain fwnode is an OF node */ + if (irq_domain_get_of_node(domain)) { + struct device_node *msi_ctlr_node = NULL; + + rid = of_msi_xlate(&pdev->dev, &msi_ctlr_node, rid); + if (msi_ctlr_node) + *node = of_fwnode_handle(msi_ctlr_node); + } else { + rid = iort_msi_xlate(&pdev->dev, rid, node); + } + + return rid; +} + +/** * pci_msi_get_device_domain - Get the MSI domain for a given PCI device * @pdev: The PCI device * diff --git a/drivers/pci/msi/msi.c b/drivers/pci/msi/msi.c index 6569ba3577fe..e2412175d7af 100644 --- a/drivers/pci/msi/msi.c +++ b/drivers/pci/msi/msi.c @@ -15,7 +15,7 @@ #include "../pci.h" #include "msi.h" -int pci_msi_enable = 1; +bool pci_msi_enable = true; /** * pci_msi_supported - check whether MSI may be enabled on a device @@ -113,7 +113,8 @@ static int pci_setup_msi_context(struct pci_dev *dev) void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set) { - raw_spinlock_t *lock = &to_pci_dev(desc->dev)->msi_lock; + struct pci_dev *dev = msi_desc_to_pci_dev(desc); + raw_spinlock_t *lock = &dev->msi_lock; unsigned long flags; if (!desc->pci.msi_attrib.can_mask) @@ -122,8 +123,7 @@ void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set) raw_spin_lock_irqsave(lock, flags); desc->pci.msi_mask &= ~clear; desc->pci.msi_mask |= set; - pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->pci.mask_pos, - desc->pci.msi_mask); + pci_write_config_dword(dev, desc->pci.mask_pos, desc->pci.msi_mask); raw_spin_unlock_irqrestore(lock, flags); } @@ -321,57 +321,29 @@ static int msi_setup_msi_desc(struct pci_dev *dev, int nvec, static int msi_verify_entries(struct pci_dev *dev) { struct msi_desc *entry; + u64 address; - if (!dev->no_64bit_msi) + if (dev->msi_addr_mask == DMA_BIT_MASK(64)) return 0; msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) { - if (entry->msg.address_hi) { - pci_err(dev, "arch assigned 64-bit MSI address %#x%08x but device only supports 32 bits\n", - entry->msg.address_hi, entry->msg.address_lo); + address = (u64)entry->msg.address_hi << 32 | entry->msg.address_lo; + if (address & ~dev->msi_addr_mask) { + pci_err(dev, "arch assigned 64-bit MSI address %#llx above device MSI address mask %#llx\n", + address, dev->msi_addr_mask); break; } } return !entry ? 0 : -EIO; } -/** - * msi_capability_init - configure device's MSI capability structure - * @dev: pointer to the pci_dev data structure of MSI device function - * @nvec: number of interrupts to allocate - * @affd: description of automatic IRQ affinity assignments (may be %NULL) - * - * Setup the MSI capability structure of the device with the requested - * number of interrupts. A return value of zero indicates the successful - * setup of an entry with the new MSI IRQ. A negative return value indicates - * an error, and a positive return value indicates the number of interrupts - * which could have been allocated. - */ -static int msi_capability_init(struct pci_dev *dev, int nvec, - struct irq_affinity *affd) +static int __msi_capability_init(struct pci_dev *dev, int nvec, struct irq_affinity_desc *masks) { - struct irq_affinity_desc *masks = NULL; + int ret = msi_setup_msi_desc(dev, nvec, masks); struct msi_desc *entry, desc; - int ret; - - /* Reject multi-MSI early on irq domain enabled architectures */ - if (nvec > 1 && !pci_msi_domain_supports(dev, MSI_FLAG_MULTI_PCI_MSI, ALLOW_LEGACY)) - return 1; - /* - * Disable MSI during setup in the hardware, but mark it enabled - * so that setup code can evaluate it. - */ - pci_msi_set_enable(dev, 0); - dev->msi_enabled = 1; - - if (affd) - masks = irq_create_affinity_masks(nvec, affd); - - msi_lock_descs(&dev->dev); - ret = msi_setup_msi_desc(dev, nvec, masks); if (ret) - goto fail; + return ret; /* All MSIs are unmasked by default; mask them all */ entry = msi_first_desc(&dev->dev, MSI_DESC_ALL); @@ -393,24 +365,51 @@ static int msi_capability_init(struct pci_dev *dev, int nvec, goto err; /* Set MSI enabled bits */ + dev->msi_enabled = 1; pci_intx_for_msi(dev, 0); pci_msi_set_enable(dev, 1); pcibios_free_irq(dev); dev->irq = entry->irq; - goto unlock; - + return 0; err: pci_msi_unmask(&desc, msi_multi_mask(&desc)); pci_free_msi_irqs(dev); -fail: - dev->msi_enabled = 0; -unlock: - msi_unlock_descs(&dev->dev); - kfree(masks); return ret; } +/** + * msi_capability_init - configure device's MSI capability structure + * @dev: pointer to the pci_dev data structure of MSI device function + * @nvec: number of interrupts to allocate + * @affd: description of automatic IRQ affinity assignments (may be %NULL) + * + * Setup the MSI capability structure of the device with the requested + * number of interrupts. A return value of zero indicates the successful + * setup of an entry with the new MSI IRQ. A negative return value indicates + * an error, and a positive return value indicates the number of interrupts + * which could have been allocated. + */ +static int msi_capability_init(struct pci_dev *dev, int nvec, + struct irq_affinity *affd) +{ + /* Reject multi-MSI early on irq domain enabled architectures */ + if (nvec > 1 && !pci_msi_domain_supports(dev, MSI_FLAG_MULTI_PCI_MSI, ALLOW_LEGACY)) + return 1; + + /* + * Disable MSI during setup in the hardware, but mark it enabled + * so that setup code can evaluate it. + */ + pci_msi_set_enable(dev, 0); + + struct irq_affinity_desc *masks __free(kfree) = + affd ? irq_create_affinity_masks(nvec, affd) : NULL; + + guard(msi_descs_lock)(&dev->dev); + return __msi_capability_init(dev, nvec, masks); +} + int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, struct irq_affinity *affd) { @@ -442,16 +441,16 @@ int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, if (nvec < minvec) return -ENOSPC; - if (nvec > maxvec) - nvec = maxvec; - rc = pci_setup_msi_context(dev); if (rc) return rc; - if (!pci_setup_msi_device_domain(dev)) + if (!pci_setup_msi_device_domain(dev, nvec)) return -ENODEV; + if (nvec > maxvec) + nvec = maxvec; + for (;;) { if (affd) { nvec = irq_calc_affinity_vectors(minvec, nvec, affd); @@ -615,6 +614,9 @@ void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc) void __iomem *addr = pci_msix_desc_addr(desc); desc->pci.msi_attrib.can_mask = 1; + /* Workaround for SUN NIU insanity, which requires write before read */ + if (dev->dev_flags & PCI_DEV_FLAGS_MSIX_TOUCH_ENTRY_DATA_FIRST) + writel(0, addr + PCI_MSIX_ENTRY_DATA); desc->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL); } } @@ -663,38 +665,39 @@ static void msix_mask_all(void __iomem *base, int tsize) writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL); } -static int msix_setup_interrupts(struct pci_dev *dev, struct msix_entry *entries, - int nvec, struct irq_affinity *affd) -{ - struct irq_affinity_desc *masks = NULL; - int ret; +DEFINE_FREE(free_msi_irqs, struct pci_dev *, if (_T) pci_free_msi_irqs(_T)); - if (affd) - masks = irq_create_affinity_masks(nvec, affd); +static int __msix_setup_interrupts(struct pci_dev *__dev, struct msix_entry *entries, + int nvec, struct irq_affinity_desc *masks) +{ + struct pci_dev *dev __free(free_msi_irqs) = __dev; - msi_lock_descs(&dev->dev); - ret = msix_setup_msi_descs(dev, entries, nvec, masks); + int ret = msix_setup_msi_descs(dev, entries, nvec, masks); if (ret) - goto out_free; + return ret; ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX); if (ret) - goto out_free; + return ret; /* Check if all MSI entries honor device restrictions */ ret = msi_verify_entries(dev); if (ret) - goto out_free; + return ret; msix_update_entries(dev, entries); - goto out_unlock; + retain_and_null_ptr(dev); + return 0; +} -out_free: - pci_free_msi_irqs(dev); -out_unlock: - msi_unlock_descs(&dev->dev); - kfree(masks); - return ret; +static int msix_setup_interrupts(struct pci_dev *dev, struct msix_entry *entries, + int nvec, struct irq_affinity *affd) +{ + struct irq_affinity_desc *masks __free(kfree) = + affd ? irq_create_affinity_masks(nvec, affd) : NULL; + + guard(msi_descs_lock)(&dev->dev); + return __msix_setup_interrupts(dev, entries, nvec, masks); } /** @@ -736,7 +739,7 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, ret = msix_setup_interrupts(dev, entries, nvec, affd); if (ret) - goto out_disable; + goto out_unmap; /* Disable INTX */ pci_intx_for_msi(dev, 0); @@ -757,6 +760,8 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries, pcibios_free_irq(dev); return 0; +out_unmap: + iounmap(dev->msix_base); out_disable: dev->msix_enabled = 0; pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE, 0); @@ -870,13 +875,13 @@ void __pci_restore_msix_state(struct pci_dev *dev) write_msg = arch_restore_msi_irqs(dev); - msi_lock_descs(&dev->dev); - msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) { - if (write_msg) - __pci_write_msi_msg(entry, &entry->msg); - pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl); + scoped_guard (msi_descs_lock, &dev->dev) { + msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) { + if (write_msg) + __pci_write_msi_msg(entry, &entry->msg); + pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl); + } } - msi_unlock_descs(&dev->dev); pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0); } @@ -915,6 +920,55 @@ void pci_free_msi_irqs(struct pci_dev *dev) } } +#ifdef CONFIG_PCIE_TPH +/** + * pci_msix_write_tph_tag - Update the TPH tag for a given MSI-X vector + * @pdev: The PCIe device to update + * @index: The MSI-X index to update + * @tag: The tag to write + * + * Returns: 0 on success, error code on failure + */ +int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag) +{ + struct msi_desc *msi_desc; + struct irq_desc *irq_desc; + unsigned int virq; + + if (!pdev->msix_enabled) + return -ENXIO; + + virq = msi_get_virq(&pdev->dev, index); + if (!virq) + return -ENXIO; + + guard(msi_descs_lock)(&pdev->dev); + + /* + * This is a horrible hack, but short of implementing a PCI + * specific interrupt chip callback and a huge pile of + * infrastructure, this is the minor nuisance. It provides the + * protection against concurrent operations on this entry and keeps + * the control word cache in sync. + */ + irq_desc = irq_to_desc(virq); + if (!irq_desc) + return -ENXIO; + + guard(raw_spinlock_irq)(&irq_desc->lock); + msi_desc = irq_data_get_msi_desc(&irq_desc->irq_data); + if (!msi_desc || msi_desc->pci.msi_attrib.is_virtual) + return -ENXIO; + + msi_desc->pci.msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_ST; + msi_desc->pci.msix_ctrl |= FIELD_PREP(PCI_MSIX_ENTRY_CTRL_ST, tag); + pci_msix_write_vector_ctrl(msi_desc, msi_desc->pci.msix_ctrl); + /* Flush the write */ + readl(pci_msix_desc_addr(msi_desc)); + return 0; +} +#endif + /* Misc. infrastructure */ struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc) @@ -925,5 +979,5 @@ EXPORT_SYMBOL(msi_desc_to_pci_dev); void pci_no_msi(void) { - pci_msi_enable = 0; + pci_msi_enable = false; } diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h index ee53cf079f4e..0b420b319f50 100644 --- a/drivers/pci/msi/msi.h +++ b/drivers/pci/msi/msi.h @@ -87,7 +87,7 @@ static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc) void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc); /* Subsystem variables */ -extern int pci_msi_enable; +extern bool pci_msi_enable; /* MSI internal functions invoked from the public APIs */ void pci_msi_shutdown(struct pci_dev *dev); @@ -107,7 +107,7 @@ enum support_mode { }; bool pci_msi_domain_supports(struct pci_dev *dev, unsigned int feature_mask, enum support_mode mode); -bool pci_setup_msi_device_domain(struct pci_dev *pdev); +bool pci_setup_msi_device_domain(struct pci_dev *pdev, unsigned int hwsize); bool pci_setup_msix_device_domain(struct pci_dev *pdev, unsigned int hwsize); /* Legacy (!IRQDOMAIN) fallbacks */ diff --git a/drivers/pci/msi/pcidev_msi.c b/drivers/pci/msi/pcidev_msi.c index 5520aff53b56..0b0346813092 100644 --- a/drivers/pci/msi/pcidev_msi.c +++ b/drivers/pci/msi/pcidev_msi.c @@ -24,7 +24,7 @@ void pci_msi_init(struct pci_dev *dev) } if (!(ctrl & PCI_MSI_FLAGS_64BIT)) - dev->no_64bit_msi = 1; + dev->msi_addr_mask = DMA_BIT_MASK(32); } void pci_msix_init(struct pci_dev *dev) diff --git a/drivers/pci/npem.c b/drivers/pci/npem.c index 97507e0df769..ffeeedf6e311 100644 --- a/drivers/pci/npem.c +++ b/drivers/pci/npem.c @@ -524,7 +524,7 @@ static int pci_npem_init(struct pci_dev *dev, const struct npem_ops *ops, int led_idx = 0; int ret; - npem = kzalloc(struct_size(npem, leds, supported_cnt), GFP_KERNEL); + npem = kzalloc_flex(*npem, leds, supported_cnt); if (!npem) return -ENOMEM; diff --git a/drivers/pci/of.c b/drivers/pci/of.c index ab7a8252bf41..9f8eb5df279e 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -696,7 +696,7 @@ void of_pci_make_dev_node(struct pci_dev *pdev) if (!name) return; - cset = kmalloc(sizeof(*cset), GFP_KERNEL); + cset = kmalloc_obj(*cset); if (!cset) goto out_free_name; of_changeset_init(cset); @@ -784,7 +784,7 @@ void of_pci_make_host_bridge_node(struct pci_host_bridge *bridge) if (!name) return; - cset = kmalloc(sizeof(*cset), GFP_KERNEL); + cset = kmalloc_obj(*cset); if (!cset) goto out_free_name; of_changeset_init(cset); @@ -867,6 +867,7 @@ bool of_pci_supply_present(struct device_node *np) return false; } +EXPORT_SYMBOL_GPL(of_pci_supply_present); #endif /* CONFIG_PCI */ @@ -966,3 +967,47 @@ u32 of_pci_get_slot_power_limit(struct device_node *node, return slot_power_limit_mw; } EXPORT_SYMBOL_GPL(of_pci_get_slot_power_limit); + +/** + * of_pci_get_equalization_presets - Parses the "eq-presets-Ngts" property. + * + * @dev: Device containing the properties. + * @presets: Pointer to store the parsed data. + * @num_lanes: Maximum number of lanes supported. + * + * If the property is present, read and store the data in the @presets structure. + * Else, assign a default value of PCI_EQ_RESV. + * + * Return: 0 if the property is not available or successfully parsed else + * errno otherwise. + */ +int of_pci_get_equalization_presets(struct device *dev, + struct pci_eq_presets *presets, + int num_lanes) +{ + char name[20]; + int ret; + + presets->eq_presets_8gts[0] = PCI_EQ_RESV; + ret = of_property_read_u16_array(dev->of_node, "eq-presets-8gts", + presets->eq_presets_8gts, num_lanes); + if (ret && ret != -EINVAL) { + dev_err(dev, "Error reading eq-presets-8gts: %d\n", ret); + return ret; + } + + for (int i = 0; i < EQ_PRESET_TYPE_MAX - 1; i++) { + presets->eq_presets_Ngts[i][0] = PCI_EQ_RESV; + snprintf(name, sizeof(name), "eq-presets-%dgts", 8 << (i + 1)); + ret = of_property_read_u8_array(dev->of_node, name, + presets->eq_presets_Ngts[i], + num_lanes); + if (ret && ret != -EINVAL) { + dev_err(dev, "Error reading %s: %d\n", name, ret); + return ret; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(of_pci_get_equalization_presets); diff --git a/drivers/pci/of_property.c b/drivers/pci/of_property.c index 506fcd507113..75a358f73e69 100644 --- a/drivers/pci/of_property.c +++ b/drivers/pci/of_property.c @@ -119,7 +119,7 @@ static int of_pci_prop_ranges(struct pci_dev *pdev, struct of_changeset *ocs, res = &pdev->resource[PCI_STD_RESOURCES]; } - rp = kcalloc(num, sizeof(*rp), GFP_KERNEL); + rp = kzalloc_objs(*rp, num); if (!rp) return -ENOMEM; @@ -279,13 +279,21 @@ static int of_pci_prop_intr_map(struct pci_dev *pdev, struct of_changeset *ocs, mapp++; *mapp = out_irq[i].np->phandle; mapp++; - if (addr_sz[i]) { - ret = of_property_read_u32_array(out_irq[i].np, - "reg", mapp, - addr_sz[i]); - if (ret) - goto failed; - } + + /* + * A device address does not affect the device <-> + * interrupt-controller HW connection for all + * modern interrupt controllers; moreover, the + * kernel (i.e., of_irq_parse_raw()) ignores the + * values in the parent unit address cells while + * parsing the interrupt-map property because they + * are irrelevant for interrupt mapping in modern + * systems. + * + * Leave the parent unit address initialized to 0 -- + * just take into account the #address-cells size + * to build the property properly. + */ mapp += addr_sz[i]; memcpy(mapp, out_irq[i].args, out_irq[i].args_count * sizeof(u32)); diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c index 19214ec81fbb..e0f546166eb8 100644 --- a/drivers/pci/p2pdma.c +++ b/drivers/pci/p2pdma.c @@ -25,12 +25,12 @@ struct pci_p2pdma { struct gen_pool *pool; bool p2pmem_published; struct xarray map_types; + struct p2pdma_provider mem[PCI_STD_NUM_BARS]; }; struct pci_p2pdma_pagemap { - struct pci_dev *provider; - u64 bus_offset; struct dev_pagemap pgmap; + struct p2pdma_provider *mem; }; static struct pci_p2pdma_pagemap *to_p2p_pgmap(struct dev_pagemap *pgmap) @@ -147,11 +147,19 @@ static int p2pmem_alloc_mmap(struct file *filp, struct kobject *kobj, * we have just allocated the page no one else should be * using it. */ - VM_WARN_ON_ONCE_PAGE(!page_ref_count(page), page); + VM_WARN_ON_ONCE_PAGE(page_ref_count(page), page); set_page_count(page, 1); ret = vm_insert_page(vma, vaddr, page); if (ret) { gen_pool_free(p2pdma->pool, (uintptr_t)kaddr, len); + + /* + * Reset the page count. We don't use put_page() + * because we don't want to trigger the + * p2pdma_folio_free() path. + */ + set_page_count(page, 0); + percpu_ref_put(ref); return ret; } percpu_ref_get(ref); @@ -196,16 +204,17 @@ static const struct bin_attribute *const p2pmem_bin_attrs[] = { static const struct attribute_group p2pmem_group = { .attrs = p2pmem_attrs, - .bin_attrs_new = p2pmem_bin_attrs, + .bin_attrs = p2pmem_bin_attrs, .name = "p2pmem", }; -static void p2pdma_page_free(struct page *page) +static void p2pdma_folio_free(struct folio *folio) { + struct page *page = &folio->page; struct pci_p2pdma_pagemap *pgmap = to_p2p_pgmap(page_pgmap(page)); /* safe to dereference while a reference is held to the percpu ref */ - struct pci_p2pdma *p2pdma = - rcu_dereference_protected(pgmap->provider->p2pdma, 1); + struct pci_p2pdma *p2pdma = rcu_dereference_protected( + to_pci_dev(pgmap->mem->owner)->p2pdma, 1); struct percpu_ref *ref; gen_pool_free_owner(p2pdma->pool, (uintptr_t)page_to_virt(page), @@ -214,7 +223,7 @@ static void p2pdma_page_free(struct page *page) } static const struct dev_pagemap_ops p2pdma_pgmap_ops = { - .page_free = p2pdma_page_free, + .folio_free = p2pdma_folio_free, }; static void pci_p2pdma_release(void *data) @@ -228,56 +237,136 @@ static void pci_p2pdma_release(void *data) /* Flush and disable pci_alloc_p2p_mem() */ pdev->p2pdma = NULL; - synchronize_rcu(); + if (p2pdma->pool) + synchronize_rcu(); + xa_destroy(&p2pdma->map_types); + + if (!p2pdma->pool) + return; gen_pool_destroy(p2pdma->pool); sysfs_remove_group(&pdev->dev.kobj, &p2pmem_group); - xa_destroy(&p2pdma->map_types); } -static int pci_p2pdma_setup(struct pci_dev *pdev) +/** + * pcim_p2pdma_init - Initialise peer-to-peer DMA providers + * @pdev: The PCI device to enable P2PDMA for + * + * This function initializes the peer-to-peer DMA infrastructure + * for a PCI device. It allocates and sets up the necessary data + * structures to support P2PDMA operations, including mapping type + * tracking. + */ +int pcim_p2pdma_init(struct pci_dev *pdev) { - int error = -ENOMEM; struct pci_p2pdma *p2p; + int i, ret; + + p2p = rcu_dereference_protected(pdev->p2pdma, 1); + if (p2p) + return 0; p2p = devm_kzalloc(&pdev->dev, sizeof(*p2p), GFP_KERNEL); if (!p2p) return -ENOMEM; xa_init(&p2p->map_types); + /* + * Iterate over all standard PCI BARs and record only those that + * correspond to MMIO regions. Skip non-memory resources (e.g. I/O + * port BARs) since they cannot be used for peer-to-peer (P2P) + * transactions. + */ + for (i = 0; i < PCI_STD_NUM_BARS; i++) { + if (!(pci_resource_flags(pdev, i) & IORESOURCE_MEM)) + continue; - p2p->pool = gen_pool_create(PAGE_SHIFT, dev_to_node(&pdev->dev)); - if (!p2p->pool) - goto out; + p2p->mem[i].owner = &pdev->dev; + p2p->mem[i].bus_offset = + pci_bus_address(pdev, i) - pci_resource_start(pdev, i); + } - error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev); - if (error) - goto out_pool_destroy; + ret = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_release, pdev); + if (ret) + goto out_p2p; - error = sysfs_create_group(&pdev->dev.kobj, &p2pmem_group); - if (error) + rcu_assign_pointer(pdev->p2pdma, p2p); + return 0; + +out_p2p: + devm_kfree(&pdev->dev, p2p); + return ret; +} +EXPORT_SYMBOL_GPL(pcim_p2pdma_init); + +/** + * pcim_p2pdma_provider - Get peer-to-peer DMA provider + * @pdev: The PCI device to enable P2PDMA for + * @bar: BAR index to get provider + * + * This function gets peer-to-peer DMA provider for a PCI device. The lifetime + * of the provider (and of course the MMIO) is bound to the lifetime of the + * driver. A driver calling this function must ensure that all references to the + * provider, and any DMA mappings created for any MMIO, are all cleaned up + * before the driver remove() completes. + * + * Since P2P is almost always shared with a second driver this means some system + * to notify, invalidate and revoke the MMIO's DMA must be in place to use this + * function. For example a revoke can be built using DMABUF. + */ +struct p2pdma_provider *pcim_p2pdma_provider(struct pci_dev *pdev, int bar) +{ + struct pci_p2pdma *p2p; + + if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM)) + return NULL; + + p2p = rcu_dereference_protected(pdev->p2pdma, 1); + if (WARN_ON(!p2p)) + /* Someone forgot to call to pcim_p2pdma_init() before */ + return NULL; + + return &p2p->mem[bar]; +} +EXPORT_SYMBOL_GPL(pcim_p2pdma_provider); + +static int pci_p2pdma_setup_pool(struct pci_dev *pdev) +{ + struct pci_p2pdma *p2pdma; + int ret; + + p2pdma = rcu_dereference_protected(pdev->p2pdma, 1); + if (p2pdma->pool) + /* We already setup pools, do nothing, */ + return 0; + + p2pdma->pool = gen_pool_create(PAGE_SHIFT, dev_to_node(&pdev->dev)); + if (!p2pdma->pool) + return -ENOMEM; + + ret = sysfs_create_group(&pdev->dev.kobj, &p2pmem_group); + if (ret) goto out_pool_destroy; - rcu_assign_pointer(pdev->p2pdma, p2p); return 0; out_pool_destroy: - gen_pool_destroy(p2p->pool); -out: - devm_kfree(&pdev->dev, p2p); - return error; + gen_pool_destroy(p2pdma->pool); + p2pdma->pool = NULL; + return ret; } static void pci_p2pdma_unmap_mappings(void *data) { - struct pci_dev *pdev = data; + struct pci_p2pdma_pagemap *p2p_pgmap = data; /* * Removing the alloc attribute from sysfs will call * unmap_mapping_range() on the inode, teardown any existing userspace * mappings and prevent new ones from being created. */ - sysfs_remove_file_from_group(&pdev->dev.kobj, &p2pmem_alloc_attr.attr, + sysfs_remove_file_from_group(&p2p_pgmap->mem->owner->kobj, + &p2pmem_alloc_attr.attr, p2pmem_group.name); } @@ -295,6 +384,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, u64 offset) { struct pci_p2pdma_pagemap *p2p_pgmap; + struct p2pdma_provider *mem; struct dev_pagemap *pgmap; struct pci_p2pdma *p2pdma; void *addr; @@ -312,11 +402,21 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, if (size + offset > pci_resource_len(pdev, bar)) return -EINVAL; - if (!pdev->p2pdma) { - error = pci_p2pdma_setup(pdev); - if (error) - return error; - } + error = pcim_p2pdma_init(pdev); + if (error) + return error; + + error = pci_p2pdma_setup_pool(pdev); + if (error) + return error; + + mem = pcim_p2pdma_provider(pdev, bar); + /* + * We checked validity of BAR prior to call + * to pcim_p2pdma_provider. It should never return NULL. + */ + if (WARN_ON(!mem)) + return -EINVAL; p2p_pgmap = devm_kzalloc(&pdev->dev, sizeof(*p2p_pgmap), GFP_KERNEL); if (!p2p_pgmap) @@ -328,10 +428,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, pgmap->nr_range = 1; pgmap->type = MEMORY_DEVICE_PCI_P2PDMA; pgmap->ops = &p2pdma_pgmap_ops; - - p2p_pgmap->provider = pdev; - p2p_pgmap->bus_offset = pci_bus_address(pdev, bar) - - pci_resource_start(pdev, bar); + p2p_pgmap->mem = mem; addr = devm_memremap_pages(&pdev->dev, pgmap); if (IS_ERR(addr)) { @@ -340,7 +437,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, } error = devm_add_action_or_reset(&pdev->dev, pci_p2pdma_unmap_mappings, - pdev); + p2p_pgmap); if (error) goto pages_free; @@ -360,7 +457,7 @@ int pci_p2pdma_add_resource(struct pci_dev *pdev, int bar, size_t size, pages_free: devm_memunmap_pages(&pdev->dev, pgmap); pgmap_free: - devm_kfree(&pdev->dev, pgmap); + devm_kfree(&pdev->dev, p2p_pgmap); return error; } EXPORT_SYMBOL_GPL(pci_p2pdma_add_resource); @@ -738,7 +835,7 @@ EXPORT_SYMBOL_GPL(pci_p2pdma_distance_many); * pci_has_p2pmem - check if a given PCI device has published any p2pmem * @pdev: PCI device to check */ -bool pci_has_p2pmem(struct pci_dev *pdev) +static bool pci_has_p2pmem(struct pci_dev *pdev) { struct pci_p2pdma *p2pdma; bool res; @@ -750,7 +847,6 @@ bool pci_has_p2pmem(struct pci_dev *pdev) return res; } -EXPORT_SYMBOL_GPL(pci_has_p2pmem); /** * pci_p2pmem_find_many - find a peer-to-peer DMA memory device compatible with @@ -910,7 +1006,7 @@ struct scatterlist *pci_p2pmem_alloc_sgl(struct pci_dev *pdev, struct scatterlist *sg; void *addr; - sg = kmalloc(sizeof(*sg), GFP_KERNEL); + sg = kmalloc_obj(*sg); if (!sg) return NULL; @@ -973,16 +1069,26 @@ void pci_p2pmem_publish(struct pci_dev *pdev, bool publish) } EXPORT_SYMBOL_GPL(pci_p2pmem_publish); -static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap, - struct device *dev) +/** + * pci_p2pdma_map_type - Determine the mapping type for P2PDMA transfers + * @provider: P2PDMA provider structure + * @dev: Target device for the transfer + * + * Determines how peer-to-peer DMA transfers should be mapped between + * the provider and the target device. The mapping type indicates whether + * the transfer can be done directly through PCI switches or must go + * through the host bridge. + */ +enum pci_p2pdma_map_type pci_p2pdma_map_type(struct p2pdma_provider *provider, + struct device *dev) { enum pci_p2pdma_map_type type = PCI_P2PDMA_MAP_NOT_SUPPORTED; - struct pci_dev *provider = to_p2p_pgmap(pgmap)->provider; + struct pci_dev *pdev = to_pci_dev(provider->owner); struct pci_dev *client; struct pci_p2pdma *p2pdma; int dist; - if (!provider->p2pdma) + if (!pdev->p2pdma) return PCI_P2PDMA_MAP_NOT_SUPPORTED; if (!dev_is_pci(dev)) @@ -991,7 +1097,7 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap, client = to_pci_dev(dev); rcu_read_lock(); - p2pdma = rcu_dereference(provider->p2pdma); + p2pdma = rcu_dereference(pdev->p2pdma); if (p2pdma) type = xa_to_value(xa_load(&p2pdma->map_types, @@ -999,45 +1105,21 @@ static enum pci_p2pdma_map_type pci_p2pdma_map_type(struct dev_pagemap *pgmap, rcu_read_unlock(); if (type == PCI_P2PDMA_MAP_UNKNOWN) - return calc_map_type_and_dist(provider, client, &dist, true); + return calc_map_type_and_dist(pdev, client, &dist, true); return type; } -/** - * pci_p2pdma_map_segment - map an sg segment determining the mapping type - * @state: State structure that should be declared outside of the for_each_sg() - * loop and initialized to zero. - * @dev: DMA device that's doing the mapping operation - * @sg: scatterlist segment to map - * - * This is a helper to be used by non-IOMMU dma_map_sg() implementations where - * the sg segment is the same for the page_link and the dma_address. - * - * Attempt to map a single segment in an SGL with the PCI bus address. - * The segment must point to a PCI P2PDMA page and thus must be - * wrapped in a is_pci_p2pdma_page(sg_page(sg)) check. - * - * Returns the type of mapping used and maps the page if the type is - * PCI_P2PDMA_MAP_BUS_ADDR. - */ -enum pci_p2pdma_map_type -pci_p2pdma_map_segment(struct pci_p2pdma_map_state *state, struct device *dev, - struct scatterlist *sg) +void __pci_p2pdma_update_state(struct pci_p2pdma_map_state *state, + struct device *dev, struct page *page) { - if (state->pgmap != page_pgmap(sg_page(sg))) { - state->pgmap = page_pgmap(sg_page(sg)); - state->map = pci_p2pdma_map_type(state->pgmap, dev); - state->bus_off = to_p2p_pgmap(state->pgmap)->bus_offset; - } + struct pci_p2pdma_pagemap *p2p_pgmap = to_p2p_pgmap(page_pgmap(page)); - if (state->map == PCI_P2PDMA_MAP_BUS_ADDR) { - sg->dma_address = sg_phys(sg) + state->bus_off; - sg_dma_len(sg) = sg->length; - sg_dma_mark_bus_address(sg); - } + if (state->mem == p2p_pgmap->mem) + return; - return state->map; + state->mem = p2p_pgmap->mem; + state->map = pci_p2pdma_map_type(p2p_pgmap->mem, dev); } /** diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c index af370628e583..4d0f2cb6c695 100644 --- a/drivers/pci/pci-acpi.c +++ b/drivers/pci/pci-acpi.c @@ -9,6 +9,7 @@ #include <linux/delay.h> #include <linux/init.h> +#include <linux/iommu.h> #include <linux/irqdomain.h> #include <linux/pci.h> #include <linux/msi.h> @@ -122,6 +123,8 @@ phys_addr_t acpi_pci_root_get_mcfg_addr(acpi_handle handle) bool pci_acpi_preserve_config(struct pci_host_bridge *host_bridge) { + bool ret = false; + if (ACPI_HANDLE(&host_bridge->dev)) { union acpi_object *obj; @@ -135,11 +138,11 @@ bool pci_acpi_preserve_config(struct pci_host_bridge *host_bridge) 1, DSM_PCI_PRESERVE_BOOT_CONFIG, NULL, ACPI_TYPE_INTEGER); if (obj && obj->integer.value == 0) - return true; + ret = true; ACPI_FREE(obj); } - return false; + return ret; } /* _HPX PCI Setting Record (Type 0); same as _HPP */ @@ -269,21 +272,6 @@ static acpi_status decode_type1_hpx_record(union acpi_object *record, return AE_OK; } -static bool pcie_root_rcb_set(struct pci_dev *dev) -{ - struct pci_dev *rp = pcie_find_root_port(dev); - u16 lnkctl; - - if (!rp) - return false; - - pcie_capability_read_word(rp, PCI_EXP_LNKCTL, &lnkctl); - if (lnkctl & PCI_EXP_LNKCTL_RCB) - return true; - - return false; -} - /* _HPX PCI Express Setting Record (Type 2) */ struct hpx_type2 { u32 revision; @@ -309,6 +297,7 @@ static void program_hpx_type2(struct pci_dev *dev, struct hpx_type2 *hpx) { int pos; u32 reg32; + const struct pci_host_bridge *host; if (!hpx) return; @@ -316,6 +305,15 @@ static void program_hpx_type2(struct pci_dev *dev, struct hpx_type2 *hpx) if (!pci_is_pcie(dev)) return; + host = pci_find_host_bridge(dev->bus); + + /* + * Only do the _HPX Type 2 programming if OS owns PCIe native + * hotplug but not AER. + */ + if (!host->native_pcie_hotplug || host->native_aer) + return; + if (hpx->revision > 1) { pci_warn(dev, "PCIe settings rev %d not supported\n", hpx->revision); @@ -323,33 +321,27 @@ static void program_hpx_type2(struct pci_dev *dev, struct hpx_type2 *hpx) } /* - * Don't allow _HPX to change MPS or MRRS settings. We manage - * those to make sure they're consistent with the rest of the - * platform. + * We only allow _HPX to program DEVCTL bits related to AER, namely + * PCI_EXP_DEVCTL_CERE, PCI_EXP_DEVCTL_NFERE, PCI_EXP_DEVCTL_FERE, + * and PCI_EXP_DEVCTL_URRE. + * + * The rest of DEVCTL is managed by the OS to make sure it's + * consistent with the rest of the platform. */ - hpx->pci_exp_devctl_and |= PCI_EXP_DEVCTL_PAYLOAD | - PCI_EXP_DEVCTL_READRQ; - hpx->pci_exp_devctl_or &= ~(PCI_EXP_DEVCTL_PAYLOAD | - PCI_EXP_DEVCTL_READRQ); + hpx->pci_exp_devctl_and |= ~PCI_EXP_AER_FLAGS; + hpx->pci_exp_devctl_or &= PCI_EXP_AER_FLAGS; /* Initialize Device Control Register */ pcie_capability_clear_and_set_word(dev, PCI_EXP_DEVCTL, ~hpx->pci_exp_devctl_and, hpx->pci_exp_devctl_or); - /* Initialize Link Control Register */ + /* Log if _HPX attempts to modify Link Control Register */ if (pcie_cap_has_lnkctl(dev)) { - - /* - * If the Root Port supports Read Completion Boundary of - * 128, set RCB to 128. Otherwise, clear it. - */ - hpx->pci_exp_lnkctl_and |= PCI_EXP_LNKCTL_RCB; - hpx->pci_exp_lnkctl_or &= ~PCI_EXP_LNKCTL_RCB; - if (pcie_root_rcb_set(dev)) - hpx->pci_exp_lnkctl_or |= PCI_EXP_LNKCTL_RCB; - - pcie_capability_clear_and_set_word(dev, PCI_EXP_LNKCTL, - ~hpx->pci_exp_lnkctl_and, hpx->pci_exp_lnkctl_or); + if (hpx->pci_exp_lnkctl_and != 0xffff || + hpx->pci_exp_lnkctl_or != 0) + pci_info(dev, "_HPX attempts Link Control setting (AND %#06x OR %#06x)\n", + hpx->pci_exp_lnkctl_and, + hpx->pci_exp_lnkctl_or); } /* Find Advanced Error Reporting Enhanced Capability */ @@ -816,15 +808,10 @@ int pci_acpi_program_hp_params(struct pci_dev *dev) bool pciehp_is_native(struct pci_dev *bridge) { const struct pci_host_bridge *host; - u32 slot_cap; if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE)) return false; - pcie_capability_read_dword(bridge, PCI_EXP_SLTCAP, &slot_cap); - if (!(slot_cap & PCI_EXP_SLTCAP_HPC)) - return false; - if (pcie_ports_native) return true; @@ -850,12 +837,7 @@ bool shpchp_is_native(struct pci_dev *bridge) */ static void pci_acpi_wake_bus(struct acpi_device_wakeup_context *context) { - struct acpi_device *adev; - struct acpi_pci_root *root; - - adev = container_of(context, struct acpi_device, wakeup.context); - root = acpi_driver_data(adev); - pci_pme_wakeup_bus(root->bus); + pci_pme_wakeup_bus(to_pci_host_bridge(context->dev)->bus); } /** @@ -888,12 +870,14 @@ static void pci_acpi_wake_dev(struct acpi_device_wakeup_context *context) } /** - * pci_acpi_add_bus_pm_notifier - Register PM notifier for root PCI bus. + * pci_acpi_add_root_pm_notifier - Register PM notifier for root PCI bus. * @dev: PCI root bridge ACPI device. + * @root: PCI root corresponding to @dev. */ -acpi_status pci_acpi_add_bus_pm_notifier(struct acpi_device *dev) +acpi_status pci_acpi_add_root_pm_notifier(struct acpi_device *dev, + struct acpi_pci_root *root) { - return acpi_add_pm_notifier(dev, NULL, pci_acpi_wake_bus); + return acpi_add_pm_notifier(dev, root->bus->bridge, pci_acpi_wake_bus); } /** @@ -974,6 +958,7 @@ void pci_set_acpi_fwnode(struct pci_dev *dev) int pci_dev_acpi_reset(struct pci_dev *dev, bool probe) { acpi_handle handle = ACPI_HANDLE(&dev->dev); + int ret; if (!handle || !acpi_has_method(handle, "_RST")) return -ENOTTY; @@ -981,12 +966,19 @@ int pci_dev_acpi_reset(struct pci_dev *dev, bool probe) if (probe) return 0; + ret = pci_dev_reset_iommu_prepare(dev); + if (ret) { + pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", ret); + return ret; + } + if (ACPI_FAILURE(acpi_evaluate_object(handle, "_RST", NULL, NULL))) { pci_warn(dev, "ACPI _RST failed\n"); - return -ENOTTY; + ret = -ENOTTY; } - return 0; + pci_dev_reset_iommu_done(dev); + return ret; } bool acpi_pci_power_manageable(struct pci_dev *dev) @@ -1002,7 +994,7 @@ bool acpi_pci_bridge_d3(struct pci_dev *dev) struct acpi_device *adev, *rpadev; const union acpi_object *obj; - if (acpi_pci_disabled || !dev->is_hotplug_bridge) + if (acpi_pci_disabled || !dev->is_pciehp) return false; adev = ACPI_COMPANION(&dev->dev); @@ -1671,11 +1663,11 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) struct acpi_pci_root_ops *root_ops; struct pci_host_bridge *host; - ri = kzalloc(sizeof(*ri), GFP_KERNEL); + ri = kzalloc_obj(*ri); if (!ri) return NULL; - root_ops = kzalloc(sizeof(*root_ops), GFP_KERNEL); + root_ops = kzalloc_obj(*root_ops); if (!root_ops) { kfree(ri); return NULL; diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index c8bd71a739f7..dd9075403987 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -58,7 +58,7 @@ int pci_add_dynid(struct pci_driver *drv, { struct pci_dynid *dynid; - dynid = kzalloc(sizeof(*dynid), GFP_KERNEL); + dynid = kzalloc_obj(*dynid); if (!dynid) return -ENOMEM; @@ -203,7 +203,7 @@ static ssize_t new_id_store(struct device_driver *driver, const char *buf, return -EINVAL; if (fields != 7) { - struct pci_dev *pdev = kzalloc(sizeof(*pdev), GFP_KERNEL); + struct pci_dev *pdev = kzalloc_obj(*pdev); if (!pdev) return -ENOMEM; @@ -302,9 +302,8 @@ struct drv_dev_and_id { const struct pci_device_id *id; }; -static long local_pci_probe(void *_ddi) +static int local_pci_probe(struct drv_dev_and_id *ddi) { - struct drv_dev_and_id *ddi = _ddi; struct pci_dev *pci_dev = ddi->dev; struct pci_driver *pci_drv = ddi->drv; struct device *dev = &pci_dev->dev; @@ -338,6 +337,21 @@ static long local_pci_probe(void *_ddi) return 0; } +static struct workqueue_struct *pci_probe_wq; + +struct pci_probe_arg { + struct drv_dev_and_id *ddi; + struct work_struct work; + int ret; +}; + +static void local_pci_probe_callback(struct work_struct *work) +{ + struct pci_probe_arg *arg = container_of(work, struct pci_probe_arg, work); + + arg->ret = local_pci_probe(arg->ddi); +} + static bool pci_physfn_is_probed(struct pci_dev *dev) { #ifdef CONFIG_PCI_IOV @@ -362,40 +376,55 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev, dev->is_probed = 1; cpu_hotplug_disable(); - /* * Prevent nesting work_on_cpu() for the case where a Virtual Function * device is probed from work_on_cpu() of the Physical device. */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node) || pci_physfn_is_probed(dev)) { - cpu = nr_cpu_ids; + error = local_pci_probe(&ddi); } else { - cpumask_var_t wq_domain_mask; + struct pci_probe_arg arg = { .ddi = &ddi }; + + INIT_WORK_ONSTACK(&arg.work, local_pci_probe_callback); + /* + * The target election and the enqueue of the work must be within + * the same RCU read side section so that when the workqueue pool + * is flushed after a housekeeping cpumask update, further readers + * are guaranteed to queue the probing work to the appropriate + * targets. + */ + rcu_read_lock(); + cpu = cpumask_any_and(cpumask_of_node(node), + housekeeping_cpumask(HK_TYPE_DOMAIN)); + + if (cpu < nr_cpu_ids) { + struct workqueue_struct *wq = pci_probe_wq; - if (!zalloc_cpumask_var(&wq_domain_mask, GFP_KERNEL)) { - error = -ENOMEM; - goto out; + if (WARN_ON_ONCE(!wq)) + wq = system_percpu_wq; + queue_work_on(cpu, wq, &arg.work); + rcu_read_unlock(); + flush_work(&arg.work); + error = arg.ret; + } else { + rcu_read_unlock(); + error = local_pci_probe(&ddi); } - cpumask_and(wq_domain_mask, - housekeeping_cpumask(HK_TYPE_WQ), - housekeeping_cpumask(HK_TYPE_DOMAIN)); - cpu = cpumask_any_and(cpumask_of_node(node), - wq_domain_mask); - free_cpumask_var(wq_domain_mask); + destroy_work_on_stack(&arg.work); } - if (cpu < nr_cpu_ids) - error = work_on_cpu(cpu, local_pci_probe, &ddi); - else - error = local_pci_probe(&ddi); -out: dev->is_probed = 0; cpu_hotplug_enable(); return error; } +void pci_probe_flush_workqueue(void) +{ + flush_workqueue(pci_probe_wq); +} + /** * __pci_device_probe - check if a driver wants to claim a specific PCI device * @drv: driver to call to check if it wants the PCI device @@ -555,12 +584,6 @@ static void pci_pm_default_resume(struct pci_dev *pci_dev) pci_enable_wake(pci_dev, PCI_D0, false); } -static void pci_pm_power_up_and_verify_state(struct pci_dev *pci_dev) -{ - pci_power_up(pci_dev); - pci_update_current_state(pci_dev, PCI_D0); -} - static void pci_pm_default_resume_early(struct pci_dev *pci_dev) { pci_pm_power_up_and_verify_state(pci_dev); @@ -635,6 +658,8 @@ static int pci_legacy_suspend(struct device *dev, pm_message_t state) struct pci_dev *pci_dev = to_pci_dev(dev); struct pci_driver *drv = pci_dev->driver; + pci_dev->state_saved = false; + if (drv && drv->suspend) { pci_power_t prev = pci_dev->current_state; int error; @@ -714,6 +739,8 @@ static int pci_pm_prepare(struct device *dev) struct pci_dev *pci_dev = to_pci_dev(dev); const struct dev_pm_ops *pm = dev->driver ? dev->driver->pm : NULL; + dev_pm_set_strict_midlayer(dev, true); + if (pm && pm->prepare) { int error = pm->prepare(dev); if (error < 0) @@ -755,6 +782,8 @@ static void pci_pm_complete(struct device *dev) if (pci_dev->current_state < pre_sleep_state) pm_request_resume(dev); } + + dev_pm_set_strict_midlayer(dev, false); } #else /* !CONFIG_PM_SLEEP */ @@ -1038,6 +1067,8 @@ static int pci_pm_freeze(struct device *dev) if (!pm) { pci_pm_default_suspend(pci_dev); + if (!pm_runtime_suspended(dev)) + pci_dev->state_saved = false; return 0; } @@ -1131,8 +1162,6 @@ static int pci_pm_thaw(struct device *dev) pci_pm_reenable_device(pci_dev); } - pci_dev->state_saved = false; - return error; } @@ -1507,7 +1536,7 @@ static int pci_bus_match(struct device *dev, const struct device_driver *drv) struct pci_driver *pci_drv; const struct pci_device_id *found_id; - if (!pci_dev->match_driver) + if (pci_dev_binding_disallowed(pci_dev)) return 0; pci_drv = (struct pci_driver *)to_pci_driver(drv); @@ -1584,7 +1613,7 @@ static int pci_uevent(const struct device *dev, struct kobj_uevent_env *env) return 0; } -#if defined(CONFIG_PCIEAER) || defined(CONFIG_EEH) +#if defined(CONFIG_PCIEAER) || defined(CONFIG_EEH) || defined(CONFIG_S390) /** * pci_uevent_ers - emit a uevent during recovery path of PCI device * @pdev: PCI device undergoing error recovery @@ -1598,6 +1627,7 @@ void pci_uevent_ers(struct pci_dev *pdev, enum pci_ers_result err_type) switch (err_type) { case PCI_ERS_RESULT_NONE: case PCI_ERS_RESULT_CAN_RECOVER: + case PCI_ERS_RESULT_NEED_RESET: envp[idx++] = "ERROR_EVENT=BEGIN_RECOVERY"; envp[idx++] = "DEVICE_ONLINE=0"; break; @@ -1634,7 +1664,7 @@ static int pci_bus_num_vf(struct device *dev) */ static int pci_dma_configure(struct device *dev) { - struct pci_driver *driver = to_pci_driver(dev->driver); + const struct device_driver *drv = READ_ONCE(dev->driver); struct device *bridge; int ret = 0; @@ -1649,10 +1679,18 @@ static int pci_dma_configure(struct device *dev) ret = acpi_dma_configure(dev, acpi_get_dma_attr(adev)); } + /* + * Attempt to enable ACS regardless of capability because some Root + * Ports (e.g. those quirked with *_intel_pch_acs_*) do not have + * the standard ACS capability but still support ACS via those + * quirks. + */ + pci_enable_acs(to_pci_dev(dev)); + pci_put_host_bridge_device(bridge); - /* @driver may not be valid when we're called from the IOMMU layer */ - if (!ret && dev->driver && !driver->driver_managed_dma) { + /* @drv may not be valid when we're called from the IOMMU layer */ + if (!ret && drv && !to_pci_driver(drv)->driver_managed_dma) { ret = iommu_device_use_default_domain(dev); if (ret) arch_teardown_dma_ops(dev); @@ -1700,38 +1738,14 @@ const struct bus_type pci_bus_type = { }; EXPORT_SYMBOL(pci_bus_type); -#ifdef CONFIG_PCIEPORTBUS -static int pcie_port_bus_match(struct device *dev, const struct device_driver *drv) -{ - struct pcie_device *pciedev; - const struct pcie_port_service_driver *driver; - - if (drv->bus != &pcie_port_bus_type || dev->bus != &pcie_port_bus_type) - return 0; - - pciedev = to_pcie_device(dev); - driver = to_service_driver(drv); - - if (driver->service != pciedev->service) - return 0; - - if (driver->port_type != PCIE_ANY_PORT && - driver->port_type != pci_pcie_type(pciedev->port)) - return 0; - - return 1; -} - -const struct bus_type pcie_port_bus_type = { - .name = "pci_express", - .match = pcie_port_bus_match, -}; -#endif - static int __init pci_driver_init(void) { int ret; + pci_probe_wq = alloc_workqueue("sync_wq", WQ_PERCPU, 0); + if (!pci_probe_wq) + return -ENOMEM; + ret = bus_register(&pci_bus_type); if (ret) return ret; diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index c6cda56ca52c..16eaaf749ba9 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -30,6 +30,7 @@ #include <linux/msi.h> #include <linux/of.h> #include <linux/aperture.h> +#include <linux/unaligned.h> #include "pci.h" #ifndef ARCH_PCI_DEV_GROUPS @@ -177,6 +178,13 @@ static ssize_t resource_show(struct device *dev, struct device_attribute *attr, for (i = 0; i < max; i++) { struct resource *res = &pci_dev->resource[i]; + struct resource zerores = {}; + + /* For backwards compatibility */ + if (pci_resource_is_bridge_win(i) && + res->flags & (IORESOURCE_UNSET | IORESOURCE_DISABLED)) + res = &zerores; + pci_resource_to_user(pci_dev, i, res, &start, &end); len += sysfs_emit_at(buf, len, "0x%016llx 0x%016llx 0x%016llx\n", (unsigned long long)start, @@ -201,8 +209,14 @@ static ssize_t max_link_width_show(struct device *dev, struct device_attribute *attr, char *buf) { struct pci_dev *pdev = to_pci_dev(dev); + ssize_t ret; - return sysfs_emit(buf, "%u\n", pcie_get_width_cap(pdev)); + /* We read PCI_EXP_LNKCAP, so we need the device to be accessible. */ + pci_config_pm_runtime_get(pdev); + ret = sysfs_emit(buf, "%u\n", pcie_get_width_cap(pdev)); + pci_config_pm_runtime_put(pdev); + + return ret; } static DEVICE_ATTR_RO(max_link_width); @@ -214,7 +228,10 @@ static ssize_t current_link_speed_show(struct device *dev, int err; enum pci_bus_speed speed; + pci_config_pm_runtime_get(pci_dev); err = pcie_capability_read_word(pci_dev, PCI_EXP_LNKSTA, &linkstat); + pci_config_pm_runtime_put(pci_dev); + if (err) return -EINVAL; @@ -231,7 +248,10 @@ static ssize_t current_link_width_show(struct device *dev, u16 linkstat; int err; + pci_config_pm_runtime_get(pci_dev); err = pcie_capability_read_word(pci_dev, PCI_EXP_LNKSTA, &linkstat); + pci_config_pm_runtime_put(pci_dev); + if (err) return -EINVAL; @@ -247,7 +267,10 @@ static ssize_t secondary_bus_number_show(struct device *dev, u8 sec_bus; int err; + pci_config_pm_runtime_get(pci_dev); err = pci_read_config_byte(pci_dev, PCI_SECONDARY_BUS, &sec_bus); + pci_config_pm_runtime_put(pci_dev); + if (err) return -EINVAL; @@ -263,7 +286,10 @@ static ssize_t subordinate_bus_number_show(struct device *dev, u8 sub_bus; int err; + pci_config_pm_runtime_get(pci_dev); err = pci_read_config_byte(pci_dev, PCI_SUBORDINATE_BUS, &sub_bus); + pci_config_pm_runtime_put(pci_dev); + if (err) return -EINVAL; @@ -694,6 +720,22 @@ static ssize_t boot_vga_show(struct device *dev, struct device_attribute *attr, } static DEVICE_ATTR_RO(boot_vga); +static ssize_t serial_number_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pci_dev *pci_dev = to_pci_dev(dev); + u64 dsn; + u8 bytes[8]; + + dsn = pci_get_dsn(pci_dev); + if (!dsn) + return -EIO; + + put_unaligned_be64(dsn, bytes); + return sysfs_emit(buf, "%8phD\n", bytes); +} +static DEVICE_ATTR_ADMIN_RO(serial_number); + static ssize_t pci_read_config(struct file *filp, struct kobject *kobj, const struct bin_attribute *bin_attr, char *buf, loff_t off, size_t count) @@ -857,7 +899,7 @@ static size_t pci_dev_config_attr_bin_size(struct kobject *kobj, } static const struct attribute_group pci_dev_config_attr_group = { - .bin_attrs_new = pci_dev_config_attrs, + .bin_attrs = pci_dev_config_attrs, .bin_size = pci_dev_config_attr_bin_size, }; @@ -995,8 +1037,7 @@ void pci_create_legacy_files(struct pci_bus *b) if (!sysfs_initialized) return; - b->legacy_io = kcalloc(2, sizeof(struct bin_attribute), - GFP_ATOMIC); + b->legacy_io = kzalloc_objs(struct bin_attribute, 2, GFP_ATOMIC); if (!b->legacy_io) goto kzalloc_err; @@ -1004,8 +1045,8 @@ void pci_create_legacy_files(struct pci_bus *b) b->legacy_io->attr.name = "legacy_io"; b->legacy_io->size = 0xffff; b->legacy_io->attr.mode = 0600; - b->legacy_io->read_new = pci_read_legacy_io; - b->legacy_io->write_new = pci_write_legacy_io; + b->legacy_io->read = pci_read_legacy_io; + b->legacy_io->write = pci_write_legacy_io; /* See pci_create_attr() for motivation */ b->legacy_io->llseek = pci_llseek_resource; b->legacy_io->mmap = pci_mmap_legacy_io; @@ -1211,8 +1252,8 @@ static int pci_create_attr(struct pci_dev *pdev, int num, int write_combine) } else { sprintf(res_attr_name, "resource%d", num); if (pci_resource_flags(pdev, num) & IORESOURCE_IO) { - res_attr->read_new = pci_read_resource_io; - res_attr->write_new = pci_write_resource_io; + res_attr->read = pci_read_resource_io; + res_attr->write = pci_write_resource_io; if (arch_can_pci_mmap_io()) res_attr->mmap = pci_mmap_resource_uc; } else { @@ -1377,7 +1418,7 @@ static size_t pci_dev_rom_attr_bin_size(struct kobject *kobj, } static const struct attribute_group pci_dev_rom_attr_group = { - .bin_attrs_new = pci_dev_rom_attrs, + .bin_attrs = pci_dev_rom_attrs, .is_bin_visible = pci_dev_rom_attr_is_visible, .bin_size = pci_dev_rom_attr_bin_size, }; @@ -1475,6 +1516,10 @@ static ssize_t reset_method_store(struct device *dev, return count; } + PM_RUNTIME_ACQUIRE(dev, pm); + if (PM_RUNTIME_ACQUIRE_ERR(&pm)) + return -ENXIO; + if (sysfs_streq(buf, "default")) { pci_init_reset_methods(pdev); return count; @@ -1541,7 +1586,7 @@ static ssize_t __resource_resize_show(struct device *dev, int n, char *buf) pci_config_pm_runtime_get(pdev); ret = sysfs_emit(buf, "%016llx\n", - (u64)pci_rebar_get_possible_sizes(pdev, n)); + pci_rebar_get_possible_sizes(pdev, n)); pci_config_pm_runtime_put(pdev); @@ -1552,8 +1597,9 @@ static ssize_t __resource_resize_store(struct device *dev, int n, const char *buf, size_t count) { struct pci_dev *pdev = to_pci_dev(dev); - unsigned long size, flags; - int ret, i; + struct pci_bus *bus = pdev->bus; + unsigned long size; + int ret; u16 cmd; if (kstrtoul(buf, 0, &size) < 0) @@ -1578,19 +1624,11 @@ static ssize_t __resource_resize_store(struct device *dev, int n, pci_write_config_word(pdev, PCI_COMMAND, cmd & ~PCI_COMMAND_MEMORY); - flags = pci_resource_flags(pdev, n); - pci_remove_resource_files(pdev); - for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) { - if (pci_resource_len(pdev, i) && - pci_resource_flags(pdev, i) == flags) - pci_release_resource(pdev, i); - } - - ret = pci_resize_resource(pdev, n, size); + ret = pci_resize_resource(pdev, n, size, 0); - pci_assign_unassigned_bus_resources(pdev->bus); + pci_assign_unassigned_bus_resources(bus); if (pci_create_resource_files(pdev)) pci_warn(pdev, "Failed to recreate resource files after BAR resizing\n"); @@ -1695,6 +1733,7 @@ late_initcall(pci_sysfs_init); static struct attribute *pci_dev_dev_attrs[] = { &dev_attr_boot_vga.attr, + &dev_attr_serial_number.attr, NULL, }; @@ -1707,6 +1746,9 @@ static umode_t pci_dev_attrs_are_visible(struct kobject *kobj, if (a == &dev_attr_boot_vga.attr && pci_is_vga(pdev)) return a->mode; + if (a == &dev_attr_serial_number.attr && pci_get_dsn(pdev)) + return a->mode; + return 0; } @@ -1805,6 +1847,7 @@ const struct attribute_group *pci_dev_attr_groups[] = { &pcie_dev_attr_group, #ifdef CONFIG_PCIEAER &aer_stats_attr_group, + &aer_attr_group, #endif #ifdef CONFIG_PCIEASPM &aspm_ctrl_attr_group, @@ -1812,5 +1855,9 @@ const struct attribute_group *pci_dev_attr_groups[] = { #ifdef CONFIG_PCI_DOE &pci_doe_sysfs_group, #endif +#ifdef CONFIG_PCI_TSM + &pci_tsm_auth_attr_group, + &pci_tsm_attr_group, +#endif NULL, }; diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 4d7c9f64ea24..8479c2e1f74f 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -13,6 +13,8 @@ #include <linux/delay.h> #include <linux/dmi.h> #include <linux/init.h> +#include <linux/iommu.h> +#include <linux/lockdep.h> #include <linux/msi.h> #include <linux/of.h> #include <linux/pci.h> @@ -25,6 +27,7 @@ #include <linux/logic_pio.h> #include <linux/device.h> #include <linux/pm_runtime.h> +#include <linux/pci-ats.h> #include <linux/pci_hotplug.h> #include <linux/vmalloc.h> #include <asm/dma.h> @@ -99,12 +102,6 @@ bool pci_reset_supported(struct pci_dev *dev) int pci_domains_supported = 1; #endif -#define DEFAULT_CARDBUS_IO_SIZE (256) -#define DEFAULT_CARDBUS_MEM_SIZE (64*1024*1024) -/* pci=cbmemsize=nnM,cbiosize=nn can override this */ -unsigned long pci_cardbus_io_size = DEFAULT_CARDBUS_IO_SIZE; -unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE; - #define DEFAULT_HOTPLUG_IO_SIZE (256) #define DEFAULT_HOTPLUG_MMIO_SIZE (2*1024*1024) #define DEFAULT_HOTPLUG_MMIO_PREF_SIZE (2*1024*1024) @@ -423,36 +420,10 @@ found: return 1; } -static u8 __pci_find_next_cap_ttl(struct pci_bus *bus, unsigned int devfn, - u8 pos, int cap, int *ttl) -{ - u8 id; - u16 ent; - - pci_bus_read_config_byte(bus, devfn, pos, &pos); - - while ((*ttl)--) { - if (pos < 0x40) - break; - pos &= ~3; - pci_bus_read_config_word(bus, devfn, pos, &ent); - - id = ent & 0xff; - if (id == 0xff) - break; - if (id == cap) - return pos; - pos = (ent >> 8); - } - return 0; -} - static u8 __pci_find_next_cap(struct pci_bus *bus, unsigned int devfn, u8 pos, int cap) { - int ttl = PCI_FIND_CAP_TTL; - - return __pci_find_next_cap_ttl(bus, devfn, pos, cap, &ttl); + return PCI_FIND_NEXT_CAP(pci_bus_read_config, pos, cap, NULL, bus, devfn); } u8 pci_find_next_capability(struct pci_dev *dev, u8 pos, int cap) @@ -553,42 +524,11 @@ EXPORT_SYMBOL(pci_bus_find_capability); */ u16 pci_find_next_ext_capability(struct pci_dev *dev, u16 start, int cap) { - u32 header; - int ttl; - u16 pos = PCI_CFG_SPACE_SIZE; - - /* minimum 8 bytes per capability */ - ttl = (PCI_CFG_SPACE_EXP_SIZE - PCI_CFG_SPACE_SIZE) / 8; - if (dev->cfg_size <= PCI_CFG_SPACE_SIZE) return 0; - if (start) - pos = start; - - if (pci_read_config_dword(dev, pos, &header) != PCIBIOS_SUCCESSFUL) - return 0; - - /* - * If we have no capabilities, this is indicated by cap ID, - * cap version and next pointer all being 0. - */ - if (header == 0) - return 0; - - while (ttl-- > 0) { - if (PCI_EXT_CAP_ID(header) == cap && pos != start) - return pos; - - pos = PCI_EXT_CAP_NEXT(header); - if (pos < PCI_CFG_SPACE_SIZE) - break; - - if (pci_read_config_dword(dev, pos, &header) != PCIBIOS_SUCCESSFUL) - break; - } - - return 0; + return PCI_FIND_NEXT_EXT_CAP(pci_bus_read_config, start, cap, + NULL, dev->bus, dev->devfn); } EXPORT_SYMBOL_GPL(pci_find_next_ext_capability); @@ -648,7 +588,7 @@ EXPORT_SYMBOL_GPL(pci_get_dsn); static u8 __pci_find_next_ht_cap(struct pci_dev *dev, u8 pos, int ht_cap) { - int rc, ttl = PCI_FIND_CAP_TTL; + int rc; u8 cap, mask; if (ht_cap == HT_CAPTYPE_SLAVE || ht_cap == HT_CAPTYPE_HOST) @@ -656,8 +596,8 @@ static u8 __pci_find_next_ht_cap(struct pci_dev *dev, u8 pos, int ht_cap) else mask = HT_5BIT_CAP_MASK; - pos = __pci_find_next_cap_ttl(dev->bus, dev->devfn, pos, - PCI_CAP_ID_HT, &ttl); + pos = PCI_FIND_NEXT_CAP(pci_bus_read_config, pos, + PCI_CAP_ID_HT, NULL, dev->bus, dev->devfn); while (pos) { rc = pci_read_config_byte(dev, pos + 3, &cap); if (rc != PCIBIOS_SUCCESSFUL) @@ -666,9 +606,10 @@ static u8 __pci_find_next_ht_cap(struct pci_dev *dev, u8 pos, int ht_cap) if ((cap & mask) == ht_cap) return pos; - pos = __pci_find_next_cap_ttl(dev->bus, dev->devfn, - pos + PCI_CAP_LIST_NEXT, - PCI_CAP_ID_HT, &ttl); + pos = PCI_FIND_NEXT_CAP(pci_bus_read_config, + pos + PCI_CAP_LIST_NEXT, + PCI_CAP_ID_HT, NULL, dev->bus, + dev->devfn); } return 0; @@ -948,7 +889,6 @@ static const char *disable_acs_redir_param; static const char *config_acs_param; struct pci_acs { - u16 cap; u16 ctrl; u16 fw_ctrl; }; @@ -1051,27 +991,27 @@ static void __pci_config_acs(struct pci_dev *dev, struct pci_acs *caps, static void pci_std_enable_acs(struct pci_dev *dev, struct pci_acs *caps) { /* Source Validation */ - caps->ctrl |= (caps->cap & PCI_ACS_SV); + caps->ctrl |= (dev->acs_capabilities & PCI_ACS_SV); /* P2P Request Redirect */ - caps->ctrl |= (caps->cap & PCI_ACS_RR); + caps->ctrl |= (dev->acs_capabilities & PCI_ACS_RR); /* P2P Completion Redirect */ - caps->ctrl |= (caps->cap & PCI_ACS_CR); + caps->ctrl |= (dev->acs_capabilities & PCI_ACS_CR); /* Upstream Forwarding */ - caps->ctrl |= (caps->cap & PCI_ACS_UF); + caps->ctrl |= (dev->acs_capabilities & PCI_ACS_UF); /* Enable Translation Blocking for external devices and noats */ if (pci_ats_disabled() || dev->external_facing || dev->untrusted) - caps->ctrl |= (caps->cap & PCI_ACS_TB); + caps->ctrl |= (dev->acs_capabilities & PCI_ACS_TB); } /** * pci_enable_acs - enable ACS if hardware support it * @dev: the PCI device */ -static void pci_enable_acs(struct pci_dev *dev) +void pci_enable_acs(struct pci_dev *dev) { struct pci_acs caps; bool enable_acs = false; @@ -1087,7 +1027,6 @@ static void pci_enable_acs(struct pci_dev *dev) if (!pos) return; - pci_read_config_word(dev, pos + PCI_ACS_CAP, &caps.cap); pci_read_config_word(dev, pos + PCI_ACS_CTRL, &caps.ctrl); caps.fw_ctrl = caps.ctrl; @@ -1374,6 +1313,11 @@ int pci_power_up(struct pci_dev *dev) return -EIO; } + if (pci_dev_is_disconnected(dev)) { + dev->current_state = PCI_D3cold; + return -EIO; + } + pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); if (PCI_POSSIBLE_ERROR(pmcsr)) { pci_err(dev, "Unable to change power state from %s to D0, device inaccessible\n", @@ -1539,6 +1483,9 @@ static int pci_set_low_power_state(struct pci_dev *dev, pci_power_t state, bool || (state == PCI_D2 && !dev->d2_support)) return -EIO; + if (dev->current_state == state) + return 0; + pci_read_config_word(dev, dev->pm_cap + PCI_PM_CTRL, &pmcsr); if (PCI_POSSIBLE_ERROR(pmcsr)) { pci_err(dev, "Unable to change power state from %s to %s, device inaccessible\n", @@ -1874,41 +1821,12 @@ static void pci_restore_config_space(struct pci_dev *pdev) } } -static void pci_restore_rebar_state(struct pci_dev *pdev) -{ - unsigned int pos, nbars, i; - u32 ctrl; - - pos = pdev->rebar_cap; - if (!pos) - return; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - nbars = FIELD_GET(PCI_REBAR_CTRL_NBAR_MASK, ctrl); - - for (i = 0; i < nbars; i++, pos += 8) { - struct resource *res; - int bar_idx, size; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX; - res = pci_resource_n(pdev, bar_idx); - size = pci_rebar_bytes_to_size(resource_size(res)); - ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; - ctrl |= FIELD_PREP(PCI_REBAR_CTRL_BAR_SIZE, size); - pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); - } -} - /** * pci_restore_state - Restore the saved state of a PCI device * @dev: PCI device that we're dealing with */ void pci_restore_state(struct pci_dev *dev) { - if (!dev->state_saved) - return; - pci_restore_pcie_state(dev); pci_restore_pasid_state(dev); pci_restore_pri_state(dev); @@ -2336,7 +2254,7 @@ void pcie_clear_device_status(struct pci_dev *dev) */ void pcie_clear_root_pme_status(struct pci_dev *dev) { - pcie_capability_set_dword(dev, PCI_EXP_RTSTA, PCI_EXP_RTSTA_PME); + pcie_capability_write_dword(dev, PCI_EXP_RTSTA, PCI_EXP_RTSTA_PME); } /** @@ -2544,8 +2462,7 @@ void pci_pme_active(struct pci_dev *dev, bool enable) if (dev->pme_poll) { struct pci_pme_device *pme_dev; if (enable) { - pme_dev = kmalloc(sizeof(struct pci_pme_device), - GFP_KERNEL); + pme_dev = kmalloc_obj(struct pci_pme_device); if (!pme_dev) { pci_warn(dev, "can't enable PME#\n"); return; @@ -3030,8 +2947,12 @@ static const struct dmi_system_id bridge_d3_blacklist[] = { * pci_bridge_d3_possible - Is it possible to put the bridge into D3 * @bridge: Bridge to check * - * This function checks if it is possible to move the bridge to D3. * Currently we only allow D3 for some PCIe ports and for Thunderbolt. + * + * Return: Whether it is possible to move the bridge to D3. + * + * The return value is guaranteed to be constant across the entire lifetime + * of the bridge, including its hot-removal. */ bool pci_bridge_d3_possible(struct pci_dev *bridge) { @@ -3046,10 +2967,14 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge) return false; /* - * Hotplug ports handled by firmware in System Management Mode - * may not be put into D3 by the OS (Thunderbolt on non-Macs). + * Hotplug ports handled by platform firmware may not be put + * into D3 by the OS, e.g. ACPI slots ... */ - if (bridge->is_hotplug_bridge && !pciehp_is_native(bridge)) + if (bridge->is_hotplug_bridge && !bridge->is_pciehp) + return false; + + /* ... or PCIe hotplug ports not handled natively by the OS. */ + if (bridge->is_pciehp && !pciehp_is_native(bridge)) return false; if (pci_bridge_d3_force) @@ -3068,7 +2993,7 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge) * by vendors for runtime D3 at least until 2018 because there * was no OS support. */ - if (bridge->is_hotplug_bridge) + if (bridge->is_pciehp) return false; if (dmi_check_system(bridge_d3_blacklist)) @@ -3192,6 +3117,12 @@ void pci_d3cold_disable(struct pci_dev *dev) } EXPORT_SYMBOL_GPL(pci_d3cold_disable); +void pci_pm_power_up_and_verify_state(struct pci_dev *pci_dev) +{ + pci_power_up(pci_dev); + pci_update_current_state(pci_dev, PCI_D0); +} + /** * pci_pm_init - Initialize PM functions of given PCI device * @dev: PCI device to handle. @@ -3199,12 +3130,8 @@ EXPORT_SYMBOL_GPL(pci_d3cold_disable); void pci_pm_init(struct pci_dev *dev) { int pm; - u16 status; u16 pmc; - pm_runtime_forbid(&dev->dev); - pm_runtime_set_active(&dev->dev); - pm_runtime_enable(&dev->dev); device_enable_async_suspend(&dev->dev); dev->wakeup_prepared = false; @@ -3214,14 +3141,14 @@ void pci_pm_init(struct pci_dev *dev) /* find PCI PM capability in list */ pm = pci_find_capability(dev, PCI_CAP_ID_PM); if (!pm) - return; + goto poweron; /* Check device's ability to generate PME# */ pci_read_config_word(dev, pm + PCI_PM_PMC, &pmc); if ((pmc & PCI_PM_CAP_VER_MASK) > 3) { pci_err(dev, "unsupported PM cap regs version (%u)\n", pmc & PCI_PM_CAP_VER_MASK); - return; + goto poweron; } dev->pm_cap = pm; @@ -3263,9 +3190,17 @@ void pci_pm_init(struct pci_dev *dev) pci_pme_active(dev, false); } - pci_read_config_word(dev, PCI_STATUS, &status); - if (status & PCI_STATUS_IMM_READY) - dev->imm_ready = 1; +poweron: + pci_pm_power_up_and_verify_state(dev); + pm_runtime_forbid(&dev->dev); + + /* + * Runtime PM will be enabled for the device when it has been fully + * configured, but since its parent and suppliers may suspend in + * the meantime, prevent them from doing so by changing the + * device's runtime PM status to "active". + */ + pm_runtime_set_active(&dev->dev); } static unsigned long pci_ea_flags(struct pci_dev *dev, u8 prop) @@ -3582,7 +3517,7 @@ void pci_configure_ari(struct pci_dev *dev) static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags) { int pos; - u16 cap, ctrl; + u16 ctrl; pos = pdev->acs_cap; if (!pos) @@ -3593,8 +3528,7 @@ static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags) * or only required if controllable. Features missing from the * capability field can therefore be assumed as hard-wired enabled. */ - pci_read_config_word(pdev, pos + PCI_ACS_CAP, &cap); - acs_flags &= (cap | PCI_ACS_EC); + acs_flags &= (pdev->acs_capabilities | PCI_ACS_EC); pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl); return (ctrl & acs_flags) == acs_flags; @@ -3715,128 +3649,15 @@ bool pci_acs_path_enabled(struct pci_dev *start, */ void pci_acs_init(struct pci_dev *dev) { - dev->acs_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS); - - /* - * Attempt to enable ACS regardless of capability because some Root - * Ports (e.g. those quirked with *_intel_pch_acs_*) do not have - * the standard ACS capability but still support ACS via those - * quirks. - */ - pci_enable_acs(dev); -} - -void pci_rebar_init(struct pci_dev *pdev) -{ - pdev->rebar_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_REBAR); -} - -/** - * pci_rebar_find_pos - find position of resize ctrl reg for BAR - * @pdev: PCI device - * @bar: BAR to find - * - * Helper to find the position of the ctrl register for a BAR. - * Returns -ENOTSUPP if resizable BARs are not supported at all. - * Returns -ENOENT if no ctrl register for the BAR could be found. - */ -static int pci_rebar_find_pos(struct pci_dev *pdev, int bar) -{ - unsigned int pos, nbars, i; - u32 ctrl; - - pos = pdev->rebar_cap; - if (!pos) - return -ENOTSUPP; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - nbars = FIELD_GET(PCI_REBAR_CTRL_NBAR_MASK, ctrl); - - for (i = 0; i < nbars; i++, pos += 8) { - int bar_idx; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - bar_idx = FIELD_GET(PCI_REBAR_CTRL_BAR_IDX, ctrl); - if (bar_idx == bar) - return pos; - } - - return -ENOENT; -} - -/** - * pci_rebar_get_possible_sizes - get possible sizes for BAR - * @pdev: PCI device - * @bar: BAR to query - * - * Get the possible sizes of a resizable BAR as bitmask defined in the spec - * (bit 0=1MB, bit 31=128TB). Returns 0 if BAR isn't resizable. - */ -u32 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar) -{ int pos; - u32 cap; - - pos = pci_rebar_find_pos(pdev, bar); - if (pos < 0) - return 0; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CAP, &cap); - cap = FIELD_GET(PCI_REBAR_CAP_SIZES, cap); - /* Sapphire RX 5600 XT Pulse has an invalid cap dword for BAR 0 */ - if (pdev->vendor == PCI_VENDOR_ID_ATI && pdev->device == 0x731f && - bar == 0 && cap == 0x700) - return 0x3f00; - - return cap; -} -EXPORT_SYMBOL(pci_rebar_get_possible_sizes); - -/** - * pci_rebar_get_current_size - get the current size of a BAR - * @pdev: PCI device - * @bar: BAR to set size to - * - * Read the size of a BAR from the resizable BAR config. - * Returns size if found or negative error code. - */ -int pci_rebar_get_current_size(struct pci_dev *pdev, int bar) -{ - int pos; - u32 ctrl; - - pos = pci_rebar_find_pos(pdev, bar); - if (pos < 0) - return pos; - - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - return FIELD_GET(PCI_REBAR_CTRL_BAR_SIZE, ctrl); -} - -/** - * pci_rebar_set_size - set a new size for a BAR - * @pdev: PCI device - * @bar: BAR to set size to - * @size: new size as defined in the spec (0=1MB, 31=128TB) - * - * Set the new size of a BAR as defined in the spec. - * Returns zero if resizing was successful, error code otherwise. - */ -int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size) -{ - int pos; - u32 ctrl; - - pos = pci_rebar_find_pos(pdev, bar); - if (pos < 0) - return pos; + dev->acs_cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS); + pos = dev->acs_cap; + if (!pos) + return; - pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); - ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; - ctrl |= FIELD_PREP(PCI_REBAR_CTRL_BAR_SIZE, size); - pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); - return 0; + pci_read_config_word(dev, pos + PCI_ACS_CAP, &dev->acs_capabilities); + pci_disable_broken_acs_cap(dev); } /** @@ -3937,16 +3758,6 @@ void pci_release_region(struct pci_dev *pdev, int bar) if (!pci_bar_index_is_valid(bar)) return; - /* - * This is done for backwards compatibility, because the old PCI devres - * API had a mode in which the function became managed if it had been - * enabled with pcim_enable_device() instead of pci_enable_device(). - */ - if (pci_is_managed(pdev)) { - pcim_release_region(pdev, bar); - return; - } - if (pci_resource_len(pdev, bar) == 0) return; if (pci_resource_flags(pdev, bar) & IORESOURCE_IO) @@ -3984,13 +3795,6 @@ static int __pci_request_region(struct pci_dev *pdev, int bar, if (!pci_bar_index_is_valid(bar)) return -EINVAL; - if (pci_is_managed(pdev)) { - if (exclusive == IORESOURCE_EXCLUSIVE) - return pcim_request_region_exclusive(pdev, bar, name); - - return pcim_request_region(pdev, bar, name); - } - if (pci_resource_len(pdev, bar) == 0) return 0; @@ -4027,11 +3831,6 @@ err_out: * * Returns 0 on success, or %EBUSY on error. A warning * message is also printed on failure. - * - * NOTE: - * This is a "hybrid" function: It's normally unmanaged, but becomes managed - * when pcim_enable_device() has been called in advance. This hybrid feature is - * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_region(struct pci_dev *pdev, int bar, const char *name) { @@ -4084,11 +3883,6 @@ err_out: * @name: Name of the driver requesting the resources * * Returns: 0 on success, negative error code on failure. - * - * NOTE: - * This is a "hybrid" function: It's normally unmanaged, but becomes managed - * when pcim_enable_device() has been called in advance. This hybrid feature is - * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_selected_regions(struct pci_dev *pdev, int bars, const char *name) @@ -4104,11 +3898,6 @@ EXPORT_SYMBOL(pci_request_selected_regions); * @name: name of the driver requesting the resources * * Returns: 0 on success, negative error code on failure. - * - * NOTE: - * This is a "hybrid" function: It's normally unmanaged, but becomes managed - * when pcim_enable_device() has been called in advance. This hybrid feature is - * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_selected_regions_exclusive(struct pci_dev *pdev, int bars, const char *name) @@ -4144,11 +3933,6 @@ EXPORT_SYMBOL(pci_release_regions); * * Returns 0 on success, or %EBUSY on error. A warning * message is also printed on failure. - * - * NOTE: - * This is a "hybrid" function: It's normally unmanaged, but becomes managed - * when pcim_enable_device() has been called in advance. This hybrid feature is - * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_regions(struct pci_dev *pdev, const char *name) { @@ -4173,11 +3957,6 @@ EXPORT_SYMBOL(pci_request_regions); * * Returns 0 on success, or %EBUSY on error. A warning message is also * printed on failure. - * - * NOTE: - * This is a "hybrid" function: It's normally unmanaged, but becomes managed - * when pcim_enable_device() has been called in advance. This hybrid feature is - * DEPRECATED! If you want managed cleanup, use the pcim_* functions instead. */ int pci_request_regions_exclusive(struct pci_dev *pdev, const char *name) { @@ -4200,7 +3979,7 @@ int pci_register_io_range(const struct fwnode_handle *fwnode, phys_addr_t addr, if (!size || addr + size < addr) return -EINVAL; - range = kzalloc(sizeof(*range), GFP_ATOMIC); + range = kzalloc_obj(*range, GFP_ATOMIC); if (!range) return -ENOMEM; @@ -4257,7 +4036,7 @@ unsigned long __weak pci_address_to_pio(phys_addr_t address) #ifndef pci_remap_iospace int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr) { -#if defined(PCI_IOBASE) && defined(CONFIG_MMU) +#if defined(PCI_IOBASE) unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start; if (!(res->flags & IORESOURCE_IO)) @@ -4290,7 +4069,7 @@ EXPORT_SYMBOL(pci_remap_iospace); */ void pci_unmap_iospace(struct resource *res) { -#if defined(PCI_IOBASE) && defined(CONFIG_MMU) +#if defined(PCI_IOBASE) unsigned long vaddr = (unsigned long)PCI_IOBASE + res->start; vunmap_range(vaddr, vaddr + resource_size(res)); @@ -4553,13 +4332,22 @@ EXPORT_SYMBOL(pci_wait_for_pending_transaction); */ int pcie_flr(struct pci_dev *dev) { + int ret; + if (!pci_wait_for_pending_transaction(dev)) pci_err(dev, "timed out waiting for pending transaction; performing function level reset anyway\n"); + /* Have to call it after waiting for pending DMA transaction */ + ret = pci_dev_reset_iommu_prepare(dev); + if (ret) { + pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", ret); + return ret; + } + pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_BCR_FLR); if (dev->imm_ready) - return 0; + goto done; /* * Per PCIe r4.0, sec 6.6.2, a device must complete an FLR within @@ -4568,7 +4356,10 @@ int pcie_flr(struct pci_dev *dev) */ msleep(100); - return pci_dev_wait(dev, "FLR", PCIE_RESET_READY_POLL_MS); + ret = pci_dev_wait(dev, "FLR", PCIE_RESET_READY_POLL_MS); +done: + pci_dev_reset_iommu_done(dev); + return ret; } EXPORT_SYMBOL_GPL(pcie_flr); @@ -4596,6 +4387,7 @@ EXPORT_SYMBOL_GPL(pcie_reset_flr); static int pci_af_flr(struct pci_dev *dev, bool probe) { + int ret; int pos; u8 cap; @@ -4622,10 +4414,17 @@ static int pci_af_flr(struct pci_dev *dev, bool probe) PCI_AF_STATUS_TP << 8)) pci_err(dev, "timed out waiting for pending transaction; performing AF function level reset anyway\n"); + /* Have to call it after waiting for pending DMA transaction */ + ret = pci_dev_reset_iommu_prepare(dev); + if (ret) { + pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", ret); + return ret; + } + pci_write_config_byte(dev, pos + PCI_AF_CTRL, PCI_AF_CTRL_FLR); if (dev->imm_ready) - return 0; + goto done; /* * Per Advanced Capabilities for Conventional PCI ECN, 13 April 2006, @@ -4635,7 +4434,10 @@ static int pci_af_flr(struct pci_dev *dev, bool probe) */ msleep(100); - return pci_dev_wait(dev, "AF_FLR", PCIE_RESET_READY_POLL_MS); + ret = pci_dev_wait(dev, "AF_FLR", PCIE_RESET_READY_POLL_MS); +done: + pci_dev_reset_iommu_done(dev); + return ret; } /** @@ -4656,6 +4458,7 @@ static int pci_af_flr(struct pci_dev *dev, bool probe) static int pci_pm_reset(struct pci_dev *dev, bool probe) { u16 csr; + int ret; if (!dev->pm_cap || dev->dev_flags & PCI_DEV_FLAGS_NO_PM_RESET) return -ENOTTY; @@ -4670,6 +4473,12 @@ static int pci_pm_reset(struct pci_dev *dev, bool probe) if (dev->current_state != PCI_D0) return -EINVAL; + ret = pci_dev_reset_iommu_prepare(dev); + if (ret) { + pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", ret); + return ret; + } + csr &= ~PCI_PM_CTRL_STATE_MASK; csr |= PCI_D3hot; pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, csr); @@ -4680,7 +4489,9 @@ static int pci_pm_reset(struct pci_dev *dev, bool probe) pci_write_config_word(dev, dev->pm_cap + PCI_PM_CTRL, csr); pci_dev_d3_sleep(dev); - return pci_dev_wait(dev, "PM D3hot->D0", PCIE_RESET_READY_POLL_MS); + ret = pci_dev_wait(dev, "PM D3hot->D0", PCIE_RESET_READY_POLL_MS); + pci_dev_reset_iommu_done(dev); + return ret; } /** @@ -4718,6 +4529,11 @@ static int pcie_wait_for_link_status(struct pci_dev *pdev, * @pdev: Device whose link to retrain. * @use_lt: Use the LT bit if TRUE, or the DLLLA bit if FALSE, for status. * + * Trigger retraining of the PCIe Link and wait for the completion of the + * retraining. As link retraining is known to asserts LBMS and may change + * the Link Speed, LBMS is cleared after the retraining and the Link Speed + * of the subordinate bus is updated. + * * Retrain completion status is retrieved from the Link Status Register * according to @use_lt. It is not verified whether the use of the DLLLA * bit is valid. @@ -4757,7 +4573,19 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt) * to track link speed or width changes made by hardware itself * in attempt to correct unreliable link operation. */ - pcie_reset_lbms_count(pdev); + pcie_reset_lbms(pdev); + + /* + * Ensure the Link Speed updates after retraining in case the Link + * Speed was changed because of the retraining. While the bwctrl's + * IRQ handler normally picks up the new Link Speed, clearing LBMS + * races with the IRQ handler reading the Link Status register and + * can result in the handler returning early without updating the + * Link Speed. + */ + if (pdev->subordinate) + pcie_update_link_speed(pdev->subordinate, PCIE_LINK_RETRAIN); + return rc; } @@ -4828,7 +4656,7 @@ bool pcie_wait_for_link(struct pci_dev *pdev, bool active) * spec says 100 ms, but firmware can lower it and we allow drivers to * increase it as well. * - * Called with @pci_bus_sem locked for reading. + * Context: Called with @pci_bus_sem locked for reading. */ static int pci_bus_max_d3cold_delay(const struct pci_bus *bus) { @@ -4836,6 +4664,8 @@ static int pci_bus_max_d3cold_delay(const struct pci_bus *bus) int min_delay = 100; int max_delay = 0; + lockdep_assert_held(&pci_bus_sem); + list_for_each_entry(pdev, &bus->devices, bus_list) { if (pdev->d3cold_delay < min_delay) min_delay = pdev->d3cold_delay; @@ -4954,7 +4784,7 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type) delay); if (!pcie_wait_for_link_delay(dev, true, delay)) { /* Did not train, no need to wait any further */ - pci_info(dev, "Data Link Layer Link Active not set in 1000 msec\n"); + pci_info(dev, "Data Link Layer Link Active not set in %d msec\n", delay); return -ENOTTY; } @@ -5091,10 +4921,20 @@ static int pci_reset_bus_function(struct pci_dev *dev, bool probe) return -ENOTTY; } + rc = pci_dev_reset_iommu_prepare(dev); + if (rc) { + pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", rc); + return rc; + } + rc = pci_dev_reset_slot_function(dev, probe); if (rc != -ENOTTY) - return rc; - return pci_parent_bus_reset(dev, probe); + goto done; + + rc = pci_parent_bus_reset(dev, probe); +done: + pci_dev_reset_iommu_done(dev); + return rc; } static int cxl_reset_bus_function(struct pci_dev *dev, bool probe) @@ -5118,6 +4958,12 @@ static int cxl_reset_bus_function(struct pci_dev *dev, bool probe) if (rc) return -ENOTTY; + rc = pci_dev_reset_iommu_prepare(dev); + if (rc) { + pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", rc); + return rc; + } + if (reg & PCI_DVSEC_CXL_PORT_CTL_UNMASK_SBR) { val = reg; } else { @@ -5132,6 +4978,7 @@ static int cxl_reset_bus_function(struct pci_dev *dev, bool probe) pci_write_config_word(bridge, dvsec + PCI_DVSEC_CXL_PORT_CTL, reg); + pci_dev_reset_iommu_done(dev); return rc; } @@ -5173,6 +5020,7 @@ static void pci_dev_save_and_disable(struct pci_dev *dev) * races with ->remove() by the device lock, which must be held by * the caller. */ + device_lock_assert(&dev->dev); if (err_handler && err_handler->reset_prepare) err_handler->reset_prepare(dev); else if (dev->driver) @@ -5243,7 +5091,9 @@ const struct pci_reset_fn_method pci_reset_fn_methods[] = { * device including MSI, bus mastering, BARs, decoding IO and memory spaces, * etc. * - * Returns 0 if the device function was successfully reset or negative if the + * Context: The caller must hold the device lock. + * + * Return: 0 if the device function was successfully reset or negative if the * device doesn't support resetting a single function. */ int __pci_reset_function_locked(struct pci_dev *dev) @@ -5252,6 +5102,7 @@ int __pci_reset_function_locked(struct pci_dev *dev) const struct pci_reset_fn_method *method; might_sleep(); + device_lock_assert(&dev->dev); /* * A reset method returns -ENOTTY if it doesn't support this device and @@ -5374,13 +5225,17 @@ EXPORT_SYMBOL_GPL(pci_reset_function); * over the reset. It also differs from pci_reset_function() in that it * requires the PCI device lock to be held. * - * Returns 0 if the device function was successfully reset or negative if the + * Context: The caller must hold the device lock. + * + * Return: 0 if the device function was successfully reset or negative if the * device doesn't support resetting a single function. */ int pci_reset_function_locked(struct pci_dev *dev) { int rc; + device_lock_assert(&dev->dev); + if (!pci_reset_supported(dev)) return -ENOTTY; @@ -5429,8 +5284,6 @@ static bool pci_bus_resettable(struct pci_bus *bus) return false; list_for_each_entry(dev, &bus->devices, bus_list) { - if (!pci_reset_supported(dev)) - return false; if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || (dev->subordinate && !pci_bus_resettable(dev->subordinate))) return false; @@ -5498,17 +5351,14 @@ unlock: /* Do any devices on or below this slot prevent a bus reset? */ static bool pci_slot_resettable(struct pci_slot *slot) { - struct pci_dev *dev; + struct pci_dev *dev, *bridge = slot->bus->self; - if (slot->bus->self && - (slot->bus->self->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET)) + if (bridge && (bridge->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET)) return false; list_for_each_entry(dev, &slot->bus->devices, bus_list) { if (!dev->slot || dev->slot != slot) continue; - if (!pci_reset_supported(dev)) - return false; if (dev->dev_flags & PCI_DEV_FLAGS_NO_BUS_RESET || (dev->subordinate && !pci_bus_resettable(dev->subordinate))) return false; @@ -5520,7 +5370,10 @@ static bool pci_slot_resettable(struct pci_slot *slot) /* Lock devices from the top of the tree down */ static void pci_slot_lock(struct pci_slot *slot) { - struct pci_dev *dev; + struct pci_dev *dev, *bridge = slot->bus->self; + + if (bridge) + pci_dev_lock(bridge); list_for_each_entry(dev, &slot->bus->devices, bus_list) { if (!dev->slot || dev->slot != slot) @@ -5535,30 +5388,35 @@ static void pci_slot_lock(struct pci_slot *slot) /* Unlock devices from the bottom of the tree up */ static void pci_slot_unlock(struct pci_slot *slot) { - struct pci_dev *dev; + struct pci_dev *dev, *bridge = slot->bus->self; list_for_each_entry(dev, &slot->bus->devices, bus_list) { if (!dev->slot || dev->slot != slot) continue; if (dev->subordinate) pci_bus_unlock(dev->subordinate); - pci_dev_unlock(dev); + else + pci_dev_unlock(dev); } + + if (bridge) + pci_dev_unlock(bridge); } /* Return 1 on successful lock, 0 on contention */ static int pci_slot_trylock(struct pci_slot *slot) { - struct pci_dev *dev; + struct pci_dev *dev, *bridge = slot->bus->self; + + if (bridge && !pci_dev_trylock(bridge)) + return 0; list_for_each_entry(dev, &slot->bus->devices, bus_list) { if (!dev->slot || dev->slot != slot) continue; if (dev->subordinate) { - if (!pci_bus_trylock(dev->subordinate)) { - pci_dev_unlock(dev); + if (!pci_bus_trylock(dev->subordinate)) goto unlock; - } } else if (!pci_dev_trylock(dev)) goto unlock; } @@ -5574,6 +5432,9 @@ unlock: else pci_dev_unlock(dev); } + + if (bridge) + pci_dev_unlock(bridge); return 0; } @@ -5942,6 +5803,7 @@ int pcie_set_readrq(struct pci_dev *dev, int rq) { u16 v; int ret; + unsigned int firstbit; struct pci_host_bridge *bridge = pci_find_host_bridge(dev->bus); if (rq < 128 || rq > 4096 || !is_power_of_2(rq)) @@ -5959,7 +5821,10 @@ int pcie_set_readrq(struct pci_dev *dev, int rq) rq = mps; } - v = FIELD_PREP(PCI_EXP_DEVCTL_READRQ, ffs(rq) - 8); + firstbit = ffs(rq); + if (firstbit < 8) + return -EINVAL; + v = FIELD_PREP(PCI_EXP_DEVCTL_READRQ, firstbit - 8); if (bridge->no_inc_mrrs) { int max_mrrs = pcie_get_readrq(dev); @@ -6713,9 +6578,31 @@ static void pci_no_domains(void) #endif } +#ifdef CONFIG_PCI_DOMAINS +static DEFINE_IDA(pci_domain_nr_dynamic_ida); + +/** + * pci_bus_find_emul_domain_nr() - allocate a PCI domain number per constraints + * @hint: desired domain, 0 if any ID in the range of @min to @max is acceptable + * @min: minimum allowable domain + * @max: maximum allowable domain, no IDs higher than INT_MAX will be returned + */ +int pci_bus_find_emul_domain_nr(u32 hint, u32 min, u32 max) +{ + return ida_alloc_range(&pci_domain_nr_dynamic_ida, max(hint, min), max, + GFP_KERNEL); +} +EXPORT_SYMBOL_GPL(pci_bus_find_emul_domain_nr); + +void pci_bus_release_emul_domain_nr(int domain_nr) +{ + ida_free(&pci_domain_nr_dynamic_ida, domain_nr); +} +EXPORT_SYMBOL_GPL(pci_bus_release_emul_domain_nr); +#endif + #ifdef CONFIG_PCI_DOMAINS_GENERIC static DEFINE_IDA(pci_domain_nr_static_ida); -static DEFINE_IDA(pci_domain_nr_dynamic_ida); static void of_pci_reserve_static_domain_nr(void) { @@ -6774,7 +6661,7 @@ static void of_pci_bus_release_domain_nr(struct device *parent, int domain_nr) return; /* Release domain from IDA where it was allocated. */ - if (of_get_pci_domain_nr(parent->of_node) == domain_nr) + if (parent && of_get_pci_domain_nr(parent->of_node) == domain_nr) ida_free(&pci_domain_nr_static_ida, domain_nr); else ida_free(&pci_domain_nr_dynamic_ida, domain_nr); @@ -6806,11 +6693,6 @@ int __weak pci_ext_cfg_avail(void) return 1; } -void __weak pci_fixup_cardbus(struct pci_bus *bus) -{ -} -EXPORT_SYMBOL(pci_fixup_cardbus); - static int __init pci_setup(char *str) { while (str) { @@ -6818,7 +6700,9 @@ static int __init pci_setup(char *str) if (k) *k++ = 0; if (*str && (str = pcibios_setup(str)) && *str) { - if (!strcmp(str, "nomsi")) { + if (!pci_setup_cardbus(str)) { + /* Function handled the parameters */ + } else if (!strcmp(str, "nomsi")) { pci_no_msi(); } else if (!strncmp(str, "noats", 5)) { pr_info("PCIe: ATS is disabled\n"); @@ -6837,10 +6721,6 @@ static int __init pci_setup(char *str) pcie_ari_disabled = true; } else if (!strncmp(str, "notph", 5)) { pci_no_tph(); - } else if (!strncmp(str, "cbiosize=", 9)) { - pci_cardbus_io_size = memparse(str + 9, &str); - } else if (!strncmp(str, "cbmemsize=", 10)) { - pci_cardbus_mem_size = memparse(str + 10, &str); } else if (!strncmp(str, "resource_alignment=", 19)) { resource_alignment_param = str + 19; } else if (!strncmp(str, "ecrc=", 5)) { diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index b81e99cd4b62..13d998fbacce 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -2,12 +2,18 @@ #ifndef DRIVERS_PCI_H #define DRIVERS_PCI_H +#include <linux/align.h> +#include <linux/bitfield.h> #include <linux/pci.h> +#include <trace/events/pci.h> struct pcie_tlp_log; /* Number of possible devfns: 0.0 to 1f.7 inclusive */ #define MAX_NR_DEVFNS 256 +#define PCI_MAX_NR_DEVS 32 + +#define MAX_NR_LANES 16 #define PCI_FIND_CAP_TTL 48 @@ -34,13 +40,6 @@ struct pcie_tlp_log; #define PCIE_T_PERST_CLK_US 100 /* - * End of conventional reset (PERST# de-asserted) to first configuration - * request (device able to respond with a "Request Retry Status" completion), - * from PCIe r6.0, sec 6.6.1. - */ -#define PCIE_T_RRS_READY_MS 100 - -/* * PCIe r6.0, sec 5.3.3.2.1 <PME Synchronization> * Recommends 1ms to 10ms timeout to check L2 ready. */ @@ -59,7 +58,23 @@ struct pcie_tlp_log; * completes before sending a Configuration Request to the device * immediately below that Port." */ -#define PCIE_RESET_CONFIG_DEVICE_WAIT_MS 100 +#define PCIE_RESET_CONFIG_WAIT_MS 100 + +/* Parameters for the waiting for link up routine */ +#define PCIE_LINK_WAIT_MAX_RETRIES 10 +#define PCIE_LINK_WAIT_SLEEP_MS 90 + +/* Format of TLP; PCIe r7.0, sec 2.2.1 */ +#define PCIE_TLP_FMT_3DW_NO_DATA 0x00 /* 3DW header, no data */ +#define PCIE_TLP_FMT_4DW_NO_DATA 0x01 /* 4DW header, no data */ +#define PCIE_TLP_FMT_3DW_DATA 0x02 /* 3DW header, with data */ +#define PCIE_TLP_FMT_4DW_DATA 0x03 /* 4DW header, with data */ + +/* Type of TLP; PCIe r7.0, sec 2.2.1 */ +#define PCIE_TLP_TYPE_CFG0_RD 0x04 /* Config Type 0 Read Request */ +#define PCIE_TLP_TYPE_CFG0_WR 0x04 /* Config Type 0 Write Request */ +#define PCIE_TLP_TYPE_CFG1_RD 0x05 /* Config Type 1 Read Request */ +#define PCIE_TLP_TYPE_CFG1_WR 0x05 /* Config Type 1 Write Request */ /* Message Routing (r[2:0]); PCIe r6.0, sec 2.2.8 */ #define PCIE_MSG_TYPE_R_RC 0 @@ -82,13 +97,123 @@ struct pcie_tlp_log; #define PCIE_MSG_CODE_DEASSERT_INTC 0x26 #define PCIE_MSG_CODE_DEASSERT_INTD 0x27 +/* Cpl. status of Complete; PCIe r7.0, sec 2.2.9.1 */ +#define PCIE_CPL_STS_SUCCESS 0x00 /* Successful Completion */ + +#define PCI_BUS_BRIDGE_IO_WINDOW 0 +#define PCI_BUS_BRIDGE_MEM_WINDOW 1 +#define PCI_BUS_BRIDGE_PREF_MEM_WINDOW 2 + +#define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \ + PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE) + extern const unsigned char pcie_link_speed[]; extern bool pci_early_dump; +extern struct mutex pci_rescan_remove_lock; + bool pcie_cap_has_lnkctl(const struct pci_dev *dev); bool pcie_cap_has_lnkctl2(const struct pci_dev *dev); bool pcie_cap_has_rtctl(const struct pci_dev *dev); +/* Standard Capability finder */ +/** + * PCI_FIND_NEXT_CAP - Find a PCI standard capability + * @read_cfg: Function pointer for reading PCI config space + * @start: Starting position to begin search + * @cap: Capability ID to find + * @prev_ptr: Pointer to store position of preceding capability (optional) + * @args: Arguments to pass to read_cfg function + * + * Search the capability list in PCI config space to find @cap. If + * found, update *prev_ptr with the position of the preceding capability + * (if prev_ptr != NULL) + * Implements TTL (time-to-live) protection against infinite loops. + * + * Return: Position of the capability if found, 0 otherwise. + */ +#define PCI_FIND_NEXT_CAP(read_cfg, start, cap, prev_ptr, args...) \ +({ \ + int __ttl = PCI_FIND_CAP_TTL; \ + u8 __id, __found_pos = 0; \ + u8 __prev_pos = (start); \ + u8 __pos = (start); \ + u16 __ent; \ + \ + read_cfg##_byte(args, __pos, &__pos); \ + \ + while (__ttl--) { \ + if (__pos < PCI_STD_HEADER_SIZEOF) \ + break; \ + \ + __pos = ALIGN_DOWN(__pos, 4); \ + read_cfg##_word(args, __pos, &__ent); \ + \ + __id = FIELD_GET(PCI_CAP_ID_MASK, __ent); \ + if (__id == 0xff) \ + break; \ + \ + if (__id == (cap)) { \ + __found_pos = __pos; \ + if (prev_ptr != NULL) \ + *(u8 *)prev_ptr = __prev_pos; \ + break; \ + } \ + \ + __prev_pos = __pos; \ + __pos = FIELD_GET(PCI_CAP_LIST_NEXT_MASK, __ent); \ + } \ + __found_pos; \ +}) + +/* Extended Capability finder */ +/** + * PCI_FIND_NEXT_EXT_CAP - Find a PCI extended capability + * @read_cfg: Function pointer for reading PCI config space + * @start: Starting position to begin search (0 for initial search) + * @cap: Extended capability ID to find + * @prev_ptr: Pointer to store position of preceding capability (optional) + * @args: Arguments to pass to read_cfg function + * + * Search the extended capability list in PCI config space to find @cap. + * If found, update *prev_ptr with the position of the preceding capability + * (if prev_ptr != NULL) + * Implements TTL protection against infinite loops using a calculated + * maximum search count. + * + * Return: Position of the capability if found, 0 otherwise. + */ +#define PCI_FIND_NEXT_EXT_CAP(read_cfg, start, cap, prev_ptr, args...) \ +({ \ + u16 __pos = (start) ?: PCI_CFG_SPACE_SIZE; \ + u16 __found_pos = 0; \ + u16 __prev_pos; \ + int __ttl, __ret; \ + u32 __header; \ + \ + __prev_pos = __pos; \ + __ttl = (PCI_CFG_SPACE_EXP_SIZE - PCI_CFG_SPACE_SIZE) / 8; \ + while (__ttl-- > 0 && __pos >= PCI_CFG_SPACE_SIZE) { \ + __ret = read_cfg##_dword(args, __pos, &__header); \ + if (__ret != PCIBIOS_SUCCESSFUL) \ + break; \ + \ + if (__header == 0) \ + break; \ + \ + if (PCI_EXT_CAP_ID(__header) == (cap) && __pos != start) {\ + __found_pos = __pos; \ + if (prev_ptr != NULL) \ + *(u16 *)prev_ptr = __prev_pos; \ + break; \ + } \ + \ + __prev_pos = __pos; \ + __pos = PCI_EXT_CAP_NEXT(__header); \ + } \ + __found_pos; \ +}) + /* Functions internal to the PCI core code */ #ifdef CONFIG_DMI @@ -148,8 +273,10 @@ void pci_dev_adjust_pme(struct pci_dev *dev); void pci_dev_complete_resume(struct pci_dev *pci_dev); void pci_config_pm_runtime_get(struct pci_dev *dev); void pci_config_pm_runtime_put(struct pci_dev *dev); +void pci_pm_power_up_and_verify_state(struct pci_dev *pci_dev); void pci_pm_init(struct pci_dev *dev); void pci_ea_init(struct pci_dev *dev); +bool pci_ea_fixed_busnrs(struct pci_dev *dev, u8 *sec, u8 *sub); void pci_msi_init(struct pci_dev *dev); void pci_msix_init(struct pci_dev *dev); bool pci_bridge_d3_possible(struct pci_dev *dev); @@ -227,6 +354,7 @@ static inline int pci_proc_detach_bus(struct pci_bus *bus) { return 0; } /* Functions for PCI Hotplug drivers to use */ int pci_hp_add_bridge(struct pci_dev *dev); +bool pci_hp_spurious_link_change(struct pci_dev *pdev); #if defined(CONFIG_SYSFS) && defined(HAVE_PCI_LEGACY) void pci_create_legacy_files(struct pci_bus *bus); @@ -283,8 +411,40 @@ extern unsigned long pci_hotplug_io_size; extern unsigned long pci_hotplug_mmio_size; extern unsigned long pci_hotplug_mmio_pref_size; extern unsigned long pci_hotplug_bus_size; -extern unsigned long pci_cardbus_io_size; -extern unsigned long pci_cardbus_mem_size; + +static inline bool pci_is_cardbus_bridge(struct pci_dev *dev) +{ + return dev->hdr_type == PCI_HEADER_TYPE_CARDBUS; +} +#ifdef CONFIG_CARDBUS +unsigned long pci_cardbus_resource_alignment(struct resource *res); +int pci_bus_size_cardbus_bridge(struct pci_bus *bus, + struct list_head *realloc_head); +int pci_cardbus_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev, + u32 buses, int max, + unsigned int available_buses, int pass); +int pci_setup_cardbus(char *str); + +#else +static inline unsigned long pci_cardbus_resource_alignment(struct resource *res) +{ + return 0; +} +static inline int pci_bus_size_cardbus_bridge(struct pci_bus *bus, + struct list_head *realloc_head) +{ + return -EOPNOTSUPP; +} +static inline int pci_cardbus_scan_bridge_extend(struct pci_bus *bus, + struct pci_dev *dev, + u32 buses, int max, + unsigned int available_buses, + int pass) +{ + return max; +} +static inline int pci_setup_cardbus(char *str) { return -ENOENT; } +#endif /* CONFIG_CARDBUS */ /** * pci_match_one_device - Tell if a PCI device structure has a matching @@ -328,8 +488,10 @@ enum pci_bar_type { struct device *pci_get_host_bridge_device(struct pci_dev *dev); void pci_put_host_bridge_device(struct device *dev); +void pci_resize_resource_set_size(struct pci_dev *dev, int resno, int size); +int pci_do_resource_release_and_resize(struct pci_dev *dev, int resno, int size, + int exclude_bars); unsigned int pci_rescan_bus_bridge_resize(struct pci_dev *bridge); -int pci_reassign_bridge_resources(struct pci_dev *bridge, unsigned long type); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); int pci_configure_extended_tags(struct pci_dev *dev, void *ign); @@ -337,7 +499,6 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl, int rrs_timeout); bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl, int rrs_timeout); -int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *pl, int rrs_timeout); int pci_setup_device(struct pci_dev *dev); void __pci_size_stdbars(struct pci_dev *dev, int count, @@ -345,6 +506,10 @@ void __pci_size_stdbars(struct pci_dev *dev, int count, int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, struct resource *res, unsigned int reg, u32 *sizes); void pci_configure_ari(struct pci_dev *dev); + +int pci_dev_res_add_to_list(struct list_head *head, struct pci_dev *dev, + struct resource *res, resource_size_t add_size, + resource_size_t min_align); void __pci_bus_size_bridges(struct pci_bus *bus, struct list_head *realloc_head); void __pci_bus_assign_resources(const struct pci_bus *bus, @@ -357,6 +522,11 @@ void pci_walk_bus_locked(struct pci_bus *top, const char *pci_resource_name(struct pci_dev *dev, unsigned int i); bool pci_resource_is_optional(const struct pci_dev *dev, int resno); +static inline bool pci_resource_is_bridge_win(int resno) +{ + return resno >= PCI_BRIDGE_RESOURCES && + resno <= PCI_BRIDGE_RESOURCE_END; +} /** * pci_resource_num - Reverse lookup resource number from device resources @@ -380,6 +550,9 @@ static inline int pci_resource_num(const struct pci_dev *dev, return resno; } +void pbus_validate_busn(struct pci_bus *bus); +struct resource *pbus_select_window(struct pci_bus *bus, + const struct resource *res); void pci_reassigndev_resource_alignment(struct pci_dev *dev); void pci_disable_bridge_window(struct pci_dev *dev); struct pci_bus *pci_bus_get(struct pci_bus *bus); @@ -387,12 +560,14 @@ void pci_bus_put(struct pci_bus *bus); #define PCIE_LNKCAP_SLS2SPEED(lnkcap) \ ({ \ - ((lnkcap) == PCI_EXP_LNKCAP_SLS_64_0GB ? PCIE_SPEED_64_0GT : \ - (lnkcap) == PCI_EXP_LNKCAP_SLS_32_0GB ? PCIE_SPEED_32_0GT : \ - (lnkcap) == PCI_EXP_LNKCAP_SLS_16_0GB ? PCIE_SPEED_16_0GT : \ - (lnkcap) == PCI_EXP_LNKCAP_SLS_8_0GB ? PCIE_SPEED_8_0GT : \ - (lnkcap) == PCI_EXP_LNKCAP_SLS_5_0GB ? PCIE_SPEED_5_0GT : \ - (lnkcap) == PCI_EXP_LNKCAP_SLS_2_5GB ? PCIE_SPEED_2_5GT : \ + u32 lnkcap_sls = (lnkcap) & PCI_EXP_LNKCAP_SLS; \ + \ + (lnkcap_sls == PCI_EXP_LNKCAP_SLS_64_0GB ? PCIE_SPEED_64_0GT : \ + lnkcap_sls == PCI_EXP_LNKCAP_SLS_32_0GB ? PCIE_SPEED_32_0GT : \ + lnkcap_sls == PCI_EXP_LNKCAP_SLS_16_0GB ? PCIE_SPEED_16_0GT : \ + lnkcap_sls == PCI_EXP_LNKCAP_SLS_8_0GB ? PCIE_SPEED_8_0GT : \ + lnkcap_sls == PCI_EXP_LNKCAP_SLS_5_0GB ? PCIE_SPEED_5_0GT : \ + lnkcap_sls == PCI_EXP_LNKCAP_SLS_2_5GB ? PCIE_SPEED_2_5GT : \ PCI_SPEED_UNKNOWN); \ }) @@ -407,13 +582,17 @@ void pci_bus_put(struct pci_bus *bus); PCI_SPEED_UNKNOWN) #define PCIE_LNKCTL2_TLS2SPEED(lnkctl2) \ - ((lnkctl2) == PCI_EXP_LNKCTL2_TLS_64_0GT ? PCIE_SPEED_64_0GT : \ - (lnkctl2) == PCI_EXP_LNKCTL2_TLS_32_0GT ? PCIE_SPEED_32_0GT : \ - (lnkctl2) == PCI_EXP_LNKCTL2_TLS_16_0GT ? PCIE_SPEED_16_0GT : \ - (lnkctl2) == PCI_EXP_LNKCTL2_TLS_8_0GT ? PCIE_SPEED_8_0GT : \ - (lnkctl2) == PCI_EXP_LNKCTL2_TLS_5_0GT ? PCIE_SPEED_5_0GT : \ - (lnkctl2) == PCI_EXP_LNKCTL2_TLS_2_5GT ? PCIE_SPEED_2_5GT : \ - PCI_SPEED_UNKNOWN) +({ \ + u16 lnkctl2_tls = (lnkctl2) & PCI_EXP_LNKCTL2_TLS; \ + \ + (lnkctl2_tls == PCI_EXP_LNKCTL2_TLS_64_0GT ? PCIE_SPEED_64_0GT : \ + lnkctl2_tls == PCI_EXP_LNKCTL2_TLS_32_0GT ? PCIE_SPEED_32_0GT : \ + lnkctl2_tls == PCI_EXP_LNKCTL2_TLS_16_0GT ? PCIE_SPEED_16_0GT : \ + lnkctl2_tls == PCI_EXP_LNKCTL2_TLS_8_0GT ? PCIE_SPEED_8_0GT : \ + lnkctl2_tls == PCI_EXP_LNKCTL2_TLS_5_0GT ? PCIE_SPEED_5_0GT : \ + lnkctl2_tls == PCI_EXP_LNKCTL2_TLS_2_5GT ? PCIE_SPEED_2_5GT : \ + PCI_SPEED_UNKNOWN); \ +}) /* PCIe speed to Mb/s reduced by encoding overhead */ #define PCIE_SPEED2MBS_ENC(speed) \ @@ -452,12 +631,28 @@ const char *pci_speed_string(enum pci_bus_speed speed); void __pcie_print_link_status(struct pci_dev *dev, bool verbose); void pcie_report_downtraining(struct pci_dev *dev); -static inline void __pcie_update_link_speed(struct pci_bus *bus, u16 linksta, u16 linksta2) +enum pcie_link_change_reason { + PCIE_LINK_RETRAIN, + PCIE_ADD_BUS, + PCIE_BWCTRL_ENABLE, + PCIE_BWCTRL_IRQ, + PCIE_HOTPLUG, +}; + +static inline void __pcie_update_link_speed(struct pci_bus *bus, + enum pcie_link_change_reason reason, + u16 linksta, u16 linksta2) { bus->cur_bus_speed = pcie_link_speed[linksta & PCI_EXP_LNKSTA_CLS]; bus->flit_mode = (linksta2 & PCI_EXP_LNKSTA2_FLIT) ? 1 : 0; + + trace_pcie_link_event(bus, + reason, + FIELD_GET(PCI_EXP_LNKSTA_NLW, linksta), + linksta & PCI_EXP_LNKSTA_LINK_STATUS_MASK); } -void pcie_update_link_speed(struct pci_bus *bus); + +void pcie_update_link_speed(struct pci_bus *bus, enum pcie_link_change_reason reason); /* Single Root I/O Virtualization */ struct pci_sriov { @@ -482,6 +677,7 @@ struct pci_sriov { u16 subsystem_vendor; /* VF subsystem vendor */ u16 subsystem_device; /* VF subsystem device */ resource_size_t barsz[PCI_SRIOV_NUM_BARS]; /* VF BAR size */ + u16 vf_rebar_cap; /* VF Resizable BAR capability offset */ bool drivers_autoprobe; /* Auto probing of VFs by driver */ }; @@ -511,6 +707,27 @@ static inline void pci_doe_sysfs_init(struct pci_dev *pdev) { } static inline void pci_doe_sysfs_teardown(struct pci_dev *pdev) { } #endif +#ifdef CONFIG_PCI_IDE +void pci_ide_init(struct pci_dev *dev); +void pci_ide_init_host_bridge(struct pci_host_bridge *hb); +void pci_ide_destroy(struct pci_dev *dev); +extern const struct attribute_group pci_ide_attr_group; +#else +static inline void pci_ide_init(struct pci_dev *dev) { } +static inline void pci_ide_init_host_bridge(struct pci_host_bridge *hb) { } +static inline void pci_ide_destroy(struct pci_dev *dev) { } +#endif + +#ifdef CONFIG_PCI_TSM +void pci_tsm_init(struct pci_dev *pdev); +void pci_tsm_destroy(struct pci_dev *pdev); +extern const struct attribute_group pci_tsm_attr_group; +extern const struct attribute_group pci_tsm_auth_attr_group; +#else +static inline void pci_tsm_init(struct pci_dev *pdev) { } +static inline void pci_tsm_destroy(struct pci_dev *pdev) { } +#endif + /** * pci_dev_set_io_state - Set the new error state if possible. * @@ -557,6 +774,10 @@ static inline int pci_dev_set_disconnected(struct pci_dev *dev, void *unused) #define PCI_DPC_RECOVERED 1 #define PCI_DPC_RECOVERING 2 #define PCI_DEV_REMOVED 3 +#define PCI_LINK_CHANGED 4 +#define PCI_LINK_CHANGING 5 +#define PCI_LINK_LBMS_SEEN 6 +#define PCI_DEV_ALLOW_BINDING 7 static inline void pci_dev_assign_added(struct pci_dev *dev) { @@ -580,39 +801,78 @@ static inline bool pci_dev_test_and_set_removed(struct pci_dev *dev) return test_and_set_bit(PCI_DEV_REMOVED, &dev->priv_flags); } +static inline void pci_dev_allow_binding(struct pci_dev *dev) +{ + set_bit(PCI_DEV_ALLOW_BINDING, &dev->priv_flags); +} + +static inline bool pci_dev_binding_disallowed(struct pci_dev *dev) +{ + return !test_bit(PCI_DEV_ALLOW_BINDING, &dev->priv_flags); +} + #ifdef CONFIG_PCIEAER #include <linux/aer.h> #define AER_MAX_MULTI_ERR_DEVICES 5 /* Not likely to have more */ +/** + * struct aer_err_info - AER Error Information + * @dev: Devices reporting error + * @ratelimit_print: Flag to log or not log the devices' error. 0=NotLog/1=Log + * @__pad1: Padding for alignment + * @error_dev_num: Number of devices reporting an error + * @level: printk level to use in logging + * @id: Value from register PCI_ERR_ROOT_ERR_SRC + * @severity: AER severity, 0-UNCOR Non-fatal, 1-UNCOR fatal, 2-COR + * @root_ratelimit_print: Flag to log or not log the root's error. 0=NotLog/1=Log + * @multi_error_valid: If multiple errors are reported + * @first_error: First reported error + * @__pad2: Padding for alignment + * @is_cxl: Bus type error: 0-PCI Bus error, 1-CXL Bus error + * @tlp_header_valid: Indicates if TLP field contains error information + * @status: COR/UNCOR error status + * @mask: COR/UNCOR mask + * @tlp: Transaction packet information + */ struct aer_err_info { struct pci_dev *dev[AER_MAX_MULTI_ERR_DEVICES]; + int ratelimit_print[AER_MAX_MULTI_ERR_DEVICES]; int error_dev_num; + const char *level; unsigned int id:16; - unsigned int severity:2; /* 0:NONFATAL | 1:FATAL | 2:COR */ - unsigned int __pad1:5; + unsigned int severity:2; + unsigned int root_ratelimit_print:1; + unsigned int __pad1:4; unsigned int multi_error_valid:1; unsigned int first_error:5; - unsigned int __pad2:2; + unsigned int __pad2:1; + unsigned int is_cxl:1; unsigned int tlp_header_valid:1; - unsigned int status; /* COR/UNCOR Error Status */ - unsigned int mask; /* COR/UNCOR Error Mask */ - struct pcie_tlp_log tlp; /* TLP Header */ + unsigned int status; + unsigned int mask; + struct pcie_tlp_log tlp; }; -int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info); -void aer_print_error(struct pci_dev *dev, struct aer_err_info *info); +int aer_get_device_error_info(struct aer_err_info *info, int i); +void aer_print_error(struct aer_err_info *info, int i); + +static inline const char *aer_err_bus(struct aer_err_info *info) +{ + return info->is_cxl ? "CXL" : "PCIe"; +} int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2, unsigned int tlp_len, bool flit, struct pcie_tlp_log *log); unsigned int aer_tlp_log_len(struct pci_dev *dev, u32 aercc); void pcie_print_tlp_log(const struct pci_dev *dev, - const struct pcie_tlp_log *log, const char *pfx); + const struct pcie_tlp_log *log, const char *level, + const char *pfx); #endif /* CONFIG_PCIEAER */ #ifdef CONFIG_PCIEPORTBUS @@ -688,10 +948,27 @@ void pci_iov_update_resource(struct pci_dev *dev, int resno); resource_size_t pci_sriov_resource_alignment(struct pci_dev *dev, int resno); void pci_restore_iov_state(struct pci_dev *dev); int pci_iov_bus_range(struct pci_bus *bus); +void pci_iov_resource_set_size(struct pci_dev *dev, int resno, int size); +bool pci_iov_is_memory_decoding_enabled(struct pci_dev *dev); +static inline u16 pci_iov_vf_rebar_cap(struct pci_dev *dev) +{ + if (!dev->is_physfn) + return 0; + + return dev->sriov->vf_rebar_cap; +} static inline bool pci_resource_is_iov(int resno) { return resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END; } +static inline int pci_resource_num_from_vf_bar(int resno) +{ + return resno + PCI_IOV_RESOURCES; +} +static inline int pci_resource_num_to_vf_bar(int resno) +{ + return resno - PCI_IOV_RESOURCES; +} extern const struct attribute_group sriov_pf_dev_attr_group; extern const struct attribute_group sriov_vf_dev_attr_group; #else @@ -712,10 +989,30 @@ static inline int pci_iov_bus_range(struct pci_bus *bus) { return 0; } +static inline void pci_iov_resource_set_size(struct pci_dev *dev, int resno, + int size) { } +static inline bool pci_iov_is_memory_decoding_enabled(struct pci_dev *dev) +{ + return false; +} +static inline u16 pci_iov_vf_rebar_cap(struct pci_dev *dev) +{ + return 0; +} static inline bool pci_resource_is_iov(int resno) { return false; } +static inline int pci_resource_num_from_vf_bar(int resno) +{ + WARN_ON_ONCE(1); + return -ENODEV; +} +static inline int pci_resource_num_to_vf_bar(int resno) +{ + WARN_ON_ONCE(1); + return -ENODEV; +} #endif /* CONFIG_PCI_IOV */ #ifdef CONFIG_PCIE_TPH @@ -744,8 +1041,6 @@ static inline void pci_suspend_ptm(struct pci_dev *dev) { } static inline void pci_resume_ptm(struct pci_dev *dev) { } #endif -unsigned long pci_cardbus_resource_alignment(struct resource *); - static inline resource_size_t pci_resource_alignment(struct pci_dev *dev, struct resource *res) { @@ -759,10 +1054,12 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev, } void pci_acs_init(struct pci_dev *dev); +void pci_enable_acs(struct pci_dev *dev); #ifdef CONFIG_PCI_QUIRKS int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags); int pci_dev_specific_enable_acs(struct pci_dev *dev); int pci_dev_specific_disable_acs_redir(struct pci_dev *dev); +void pci_disable_broken_acs_cap(struct pci_dev *pdev); int pcie_failed_link_retrain(struct pci_dev *dev); #else static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev, @@ -778,6 +1075,7 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev) { return -ENOTTY; } +static inline void pci_disable_broken_acs_cap(struct pci_dev *dev) { } static inline int pcie_failed_link_retrain(struct pci_dev *dev) { return -ENOTTY; @@ -800,6 +1098,7 @@ void pci_save_aspm_l1ss_state(struct pci_dev *dev); void pci_restore_aspm_l1ss_state(struct pci_dev *dev); #ifdef CONFIG_PCIEASPM +void pcie_aspm_remove_cap(struct pci_dev *pdev, u32 lnkcap); void pcie_aspm_init_link_state(struct pci_dev *pdev); void pcie_aspm_exit_link_state(struct pci_dev *pdev); void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked); @@ -807,6 +1106,7 @@ void pcie_aspm_powersave_config_link(struct pci_dev *pdev); void pci_configure_ltr(struct pci_dev *pdev); void pci_bridge_reconfigure_ltr(struct pci_dev *pdev); #else +static inline void pcie_aspm_remove_cap(struct pci_dev *pdev, u32 lnkcap) { } static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { } static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev, bool locked) { } @@ -824,14 +1124,9 @@ static inline void pcie_ecrc_get_policy(char *str) { } #endif #ifdef CONFIG_PCIEPORTBUS -void pcie_reset_lbms_count(struct pci_dev *port); -int pcie_lbms_count(struct pci_dev *port, unsigned long *val); +void pcie_reset_lbms(struct pci_dev *port); #else -static inline void pcie_reset_lbms_count(struct pci_dev *port) {} -static inline int pcie_lbms_count(struct pci_dev *port, unsigned long *val) -{ - return -EOPNOTSUPP; -} +static inline void pcie_reset_lbms(struct pci_dev *port) {} #endif struct pci_dev_reset_methods { @@ -867,15 +1162,27 @@ static inline int acpi_get_rc_resources(struct device *dev, const char *hid, #endif void pci_rebar_init(struct pci_dev *pdev); +void pci_restore_rebar_state(struct pci_dev *pdev); int pci_rebar_get_current_size(struct pci_dev *pdev, int bar); int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size); -static inline u64 pci_rebar_size_to_bytes(int size) -{ - return 1ULL << (size + 20); -} struct device_node; +#define PCI_EQ_RESV 0xff + +enum equalization_preset_type { + EQ_PRESET_TYPE_8GTS, + EQ_PRESET_TYPE_16GTS, + EQ_PRESET_TYPE_32GTS, + EQ_PRESET_TYPE_64GTS, + EQ_PRESET_TYPE_MAX +}; + +struct pci_eq_presets { + u16 eq_presets_8gts[MAX_NR_LANES]; + u8 eq_presets_Ngts[EQ_PRESET_TYPE_MAX - 1][MAX_NR_LANES]; +}; + #ifdef CONFIG_OF int of_get_pci_domain_nr(struct device_node *node); int of_pci_get_max_link_speed(struct device_node *node); @@ -890,7 +1197,9 @@ void pci_release_bus_of_node(struct pci_bus *bus); int devm_of_pci_bridge_init(struct device *dev, struct pci_host_bridge *bridge); bool of_pci_supply_present(struct device_node *np); - +int of_pci_get_equalization_presets(struct device *dev, + struct pci_eq_presets *presets, + int num_lanes); #else static inline int of_get_pci_domain_nr(struct device_node *node) @@ -935,6 +1244,17 @@ static inline bool of_pci_supply_present(struct device_node *np) { return false; } + +static inline int of_pci_get_equalization_presets(struct device *dev, + struct pci_eq_presets *presets, + int num_lanes) +{ + presets->eq_presets_8gts[0] = PCI_EQ_RESV; + for (int i = 0; i < EQ_PRESET_TYPE_MAX - 1; i++) + presets->eq_presets_Ngts[i][0] = PCI_EQ_RESV; + + return 0; +} #endif /* CONFIG_OF */ struct of_changeset; @@ -961,6 +1281,7 @@ void pci_no_aer(void); void pci_aer_init(struct pci_dev *dev); void pci_aer_exit(struct pci_dev *dev); extern const struct attribute_group aer_stats_attr_group; +extern const struct attribute_group aer_attr_group; void pci_aer_clear_fatal_status(struct pci_dev *dev); int pci_aer_clear_status(struct pci_dev *dev); int pci_aer_raw_clear_status(struct pci_dev *dev); @@ -1059,10 +1380,14 @@ static inline pci_power_t mid_pci_get_power_state(struct pci_dev *pdev) } #endif -int pcim_intx(struct pci_dev *dev, int enable); -int pcim_request_region_exclusive(struct pci_dev *pdev, int bar, - const char *name); -void pcim_release_region(struct pci_dev *pdev, int bar); +#ifdef CONFIG_PCI_MSI +int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag); +#else +static inline int pci_msix_write_tph_tag(struct pci_dev *pdev, unsigned int index, u16 tag) +{ + return -ENODEV; +} +#endif /* * Config Address for PCI Configuration Mechanism #1 diff --git a/drivers/pci/pcie/Kconfig b/drivers/pci/pcie/Kconfig index 17919b99fa66..207c2deae35f 100644 --- a/drivers/pci/pcie/Kconfig +++ b/drivers/pci/pcie/Kconfig @@ -49,15 +49,6 @@ config PCIEAER_INJECT gotten from: https://github.com/intel/aer-inject.git -config PCIEAER_CXL - bool "PCI Express CXL RAS support" - default y - depends on PCIEAER && CXL_PCI - help - Enables CXL error handling. - - If unsure, say Y. - # # PCI Express ECRC # diff --git a/drivers/pci/pcie/Makefile b/drivers/pci/pcie/Makefile index 173829aa02e6..b0b43a18c304 100644 --- a/drivers/pci/pcie/Makefile +++ b/drivers/pci/pcie/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_PCIEPORTBUS) += pcieportdrv.o bwctrl.o obj-y += aspm.o obj-$(CONFIG_PCIEAER) += aer.o err.o tlp.o +obj-$(CONFIG_CXL_RAS) += aer_cxl_rch.o obj-$(CONFIG_PCIEAER_INJECT) += aer_inject.o obj-$(CONFIG_PCIE_PME) += pme.o obj-$(CONFIG_PCIE_DPC) += dpc.o diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c index a1cf8c7ef628..d916378bc707 100644 --- a/drivers/pci/pcie/aer.c +++ b/drivers/pci/pcie/aer.c @@ -28,7 +28,9 @@ #include <linux/interrupt.h> #include <linux/delay.h> #include <linux/kfifo.h> +#include <linux/ratelimit.h> #include <linux/slab.h> +#include <linux/vmcore_info.h> #include <acpi/apei.h> #include <acpi/ghes.h> #include <ras/ras_event.h> @@ -42,7 +44,7 @@ #define AER_ERROR_SOURCES_MAX 128 #define AER_MAX_TYPEOF_COR_ERRS 16 /* as per PCI_ERR_COR_STATUS */ -#define AER_MAX_TYPEOF_UNCOR_ERRS 27 /* as per PCI_ERR_UNCOR_STATUS*/ +#define AER_MAX_TYPEOF_UNCOR_ERRS 32 /* as per PCI_ERR_UNCOR_STATUS*/ struct aer_err_source { u32 status; /* PCI_ERR_ROOT_STATUS */ @@ -54,8 +56,8 @@ struct aer_rpc { DECLARE_KFIFO(aer_fifo, struct aer_err_source, AER_ERROR_SOURCES_MAX); }; -/* AER stats for the device */ -struct aer_stats { +/* AER info for the device */ +struct aer_info { /* * Fields for all AER capable devices. They indicate the errors @@ -88,14 +90,28 @@ struct aer_stats { u64 rootport_total_cor_errs; u64 rootport_total_fatal_errs; u64 rootport_total_nonfatal_errs; + + /* Ratelimits for errors */ + struct ratelimit_state correctable_ratelimit; + struct ratelimit_state nonfatal_ratelimit; }; #define AER_LOG_TLP_MASKS (PCI_ERR_UNC_POISON_TLP| \ + PCI_ERR_UNC_POISON_BLK | \ PCI_ERR_UNC_ECRC| \ PCI_ERR_UNC_UNSUP| \ PCI_ERR_UNC_COMP_ABORT| \ PCI_ERR_UNC_UNX_COMP| \ - PCI_ERR_UNC_MALF_TLP) + PCI_ERR_UNC_ACSV | \ + PCI_ERR_UNC_MCBTLP | \ + PCI_ERR_UNC_ATOMEG | \ + PCI_ERR_UNC_DMWR_BLK | \ + PCI_ERR_UNC_XLAT_BLK | \ + PCI_ERR_UNC_TLPPRE | \ + PCI_ERR_UNC_MALF_TLP | \ + PCI_ERR_UNC_IDE_CHECK | \ + PCI_ERR_UNC_MISR_IDE | \ + PCI_ERR_UNC_PCRC_CHECK) #define SYSTEM_ERROR_INTR_ON_MESG_MASK (PCI_EXP_RTCTL_SECEE| \ PCI_EXP_RTCTL_SENFEE| \ @@ -111,12 +127,12 @@ struct aer_stats { PCI_ERR_ROOT_MULTI_COR_RCV | \ PCI_ERR_ROOT_MULTI_UNCOR_RCV) -static int pcie_aer_disable; +static bool pcie_aer_disable; static pci_ers_result_t aer_root_reset(struct pci_dev *dev); void pci_no_aer(void) { - pcie_aer_disable = 1; + pcie_aer_disable = true; } bool pci_aer_available(void) @@ -223,9 +239,6 @@ void pcie_ecrc_get_policy(char *str) } #endif /* CONFIG_PCIE_ECRC */ -#define PCI_EXP_AER_FLAGS (PCI_EXP_DEVCTL_CERE | PCI_EXP_DEVCTL_NFERE | \ - PCI_EXP_DEVCTL_FERE | PCI_EXP_DEVCTL_URRE) - int pcie_aer_is_native(struct pci_dev *dev) { struct pci_host_bridge *host = pci_find_host_bridge(dev->bus); @@ -377,7 +390,16 @@ void pci_aer_init(struct pci_dev *dev) if (!dev->aer_cap) return; - dev->aer_stats = kzalloc(sizeof(struct aer_stats), GFP_KERNEL); + dev->aer_info = kzalloc_obj(*dev->aer_info); + if (!dev->aer_info) { + dev->aer_cap = 0; + return; + } + + ratelimit_state_init(&dev->aer_info->correctable_ratelimit, + DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); + ratelimit_state_init(&dev->aer_info->nonfatal_ratelimit, + DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST); /* * We save/restore PCI_ERR_UNCOR_MASK, PCI_ERR_UNCOR_SEVER, @@ -398,8 +420,8 @@ void pci_aer_init(struct pci_dev *dev) void pci_aer_exit(struct pci_dev *dev) { - kfree(dev->aer_stats); - dev->aer_stats = NULL; + kfree(dev->aer_info); + dev->aer_info = NULL; } #define AER_AGENT_RECEIVER 0 @@ -515,11 +537,11 @@ static const char *aer_uncorrectable_error_string[] = { "AtomicOpBlocked", /* Bit Position 24 */ "TLPBlockedErr", /* Bit Position 25 */ "PoisonTLPBlocked", /* Bit Position 26 */ - NULL, /* Bit Position 27 */ - NULL, /* Bit Position 28 */ - NULL, /* Bit Position 29 */ - NULL, /* Bit Position 30 */ - NULL, /* Bit Position 31 */ + "DMWrReqBlocked", /* Bit Position 27 */ + "IDECheck", /* Bit Position 28 */ + "MisIDETLP", /* Bit Position 29 */ + "PCRC_CHECK", /* Bit Position 30 */ + "TLPXlatBlocked", /* Bit Position 31 */ }; static const char *aer_agent_string[] = { @@ -537,10 +559,10 @@ static const char *aer_agent_string[] = { { \ unsigned int i; \ struct pci_dev *pdev = to_pci_dev(dev); \ - u64 *stats = pdev->aer_stats->stats_array; \ + u64 *stats = pdev->aer_info->stats_array; \ size_t len = 0; \ \ - for (i = 0; i < ARRAY_SIZE(pdev->aer_stats->stats_array); i++) {\ + for (i = 0; i < ARRAY_SIZE(pdev->aer_info->stats_array); i++) { \ if (strings_array[i]) \ len += sysfs_emit_at(buf, len, "%s %llu\n", \ strings_array[i], \ @@ -551,7 +573,7 @@ static const char *aer_agent_string[] = { i, stats[i]); \ } \ len += sysfs_emit_at(buf, len, "TOTAL_%s %llu\n", total_string, \ - pdev->aer_stats->total_field); \ + pdev->aer_info->total_field); \ return len; \ } \ static DEVICE_ATTR_RO(name) @@ -572,7 +594,7 @@ aer_stats_dev_attr(aer_dev_nonfatal, dev_nonfatal_errs, char *buf) \ { \ struct pci_dev *pdev = to_pci_dev(dev); \ - return sysfs_emit(buf, "%llu\n", pdev->aer_stats->field); \ + return sysfs_emit(buf, "%llu\n", pdev->aer_info->field); \ } \ static DEVICE_ATTR_RO(name) @@ -599,7 +621,7 @@ static umode_t aer_stats_attrs_are_visible(struct kobject *kobj, struct device *dev = kobj_to_dev(kobj); struct pci_dev *pdev = to_pci_dev(dev); - if (!pdev->aer_stats) + if (!pdev->aer_info) return 0; if ((a == &dev_attr_aer_rootport_total_err_cor.attr || @@ -617,31 +639,137 @@ const struct attribute_group aer_stats_attr_group = { .is_visible = aer_stats_attrs_are_visible, }; +/* + * Ratelimit interval + * <=0: disabled with ratelimit.interval = 0 + * >0: enabled with ratelimit.interval in ms + */ +#define aer_ratelimit_interval_attr(name, ratelimit) \ + static ssize_t \ + name##_show(struct device *dev, struct device_attribute *attr, \ + char *buf) \ + { \ + struct pci_dev *pdev = to_pci_dev(dev); \ + \ + return sysfs_emit(buf, "%d\n", \ + pdev->aer_info->ratelimit.interval); \ + } \ + \ + static ssize_t \ + name##_store(struct device *dev, struct device_attribute *attr, \ + const char *buf, size_t count) \ + { \ + struct pci_dev *pdev = to_pci_dev(dev); \ + int interval; \ + \ + if (!capable(CAP_SYS_ADMIN)) \ + return -EPERM; \ + \ + if (kstrtoint(buf, 0, &interval) < 0) \ + return -EINVAL; \ + \ + if (interval <= 0) \ + interval = 0; \ + else \ + interval = msecs_to_jiffies(interval); \ + \ + pdev->aer_info->ratelimit.interval = interval; \ + \ + return count; \ + } \ + static DEVICE_ATTR_RW(name); + +#define aer_ratelimit_burst_attr(name, ratelimit) \ + static ssize_t \ + name##_show(struct device *dev, struct device_attribute *attr, \ + char *buf) \ + { \ + struct pci_dev *pdev = to_pci_dev(dev); \ + \ + return sysfs_emit(buf, "%d\n", \ + pdev->aer_info->ratelimit.burst); \ + } \ + \ + static ssize_t \ + name##_store(struct device *dev, struct device_attribute *attr, \ + const char *buf, size_t count) \ + { \ + struct pci_dev *pdev = to_pci_dev(dev); \ + int burst; \ + \ + if (!capable(CAP_SYS_ADMIN)) \ + return -EPERM; \ + \ + if (kstrtoint(buf, 0, &burst) < 0) \ + return -EINVAL; \ + \ + pdev->aer_info->ratelimit.burst = burst; \ + \ + return count; \ + } \ + static DEVICE_ATTR_RW(name); + +#define aer_ratelimit_attrs(name) \ + aer_ratelimit_interval_attr(name##_ratelimit_interval_ms, \ + name##_ratelimit) \ + aer_ratelimit_burst_attr(name##_ratelimit_burst, \ + name##_ratelimit) + +aer_ratelimit_attrs(correctable) +aer_ratelimit_attrs(nonfatal) + +static struct attribute *aer_attrs[] = { + &dev_attr_correctable_ratelimit_interval_ms.attr, + &dev_attr_correctable_ratelimit_burst.attr, + &dev_attr_nonfatal_ratelimit_interval_ms.attr, + &dev_attr_nonfatal_ratelimit_burst.attr, + NULL +}; + +static umode_t aer_attrs_are_visible(struct kobject *kobj, + struct attribute *a, int n) +{ + struct device *dev = kobj_to_dev(kobj); + struct pci_dev *pdev = to_pci_dev(dev); + + if (!pdev->aer_info) + return 0; + + return a->mode; +} + +const struct attribute_group aer_attr_group = { + .name = "aer", + .attrs = aer_attrs, + .is_visible = aer_attrs_are_visible, +}; + static void pci_dev_aer_stats_incr(struct pci_dev *pdev, struct aer_err_info *info) { unsigned long status = info->status & ~info->mask; int i, max = -1; u64 *counter = NULL; - struct aer_stats *aer_stats = pdev->aer_stats; + struct aer_info *aer_info = pdev->aer_info; - if (!aer_stats) + if (!aer_info) return; switch (info->severity) { case AER_CORRECTABLE: - aer_stats->dev_total_cor_errs++; - counter = &aer_stats->dev_cor_errs[0]; + aer_info->dev_total_cor_errs++; + counter = &aer_info->dev_cor_errs[0]; max = AER_MAX_TYPEOF_COR_ERRS; break; case AER_NONFATAL: - aer_stats->dev_total_nonfatal_errs++; - counter = &aer_stats->dev_nonfatal_errs[0]; + aer_info->dev_total_nonfatal_errs++; + hwerr_log_error_type(HWERR_RECOV_PCI); + counter = &aer_info->dev_nonfatal_errs[0]; max = AER_MAX_TYPEOF_UNCOR_ERRS; break; case AER_FATAL: - aer_stats->dev_total_fatal_errs++; - counter = &aer_stats->dev_fatal_errs[0]; + aer_info->dev_total_fatal_errs++; + counter = &aer_info->dev_fatal_errs[0]; max = AER_MAX_TYPEOF_UNCOR_ERRS; break; } @@ -653,37 +781,63 @@ static void pci_dev_aer_stats_incr(struct pci_dev *pdev, static void pci_rootport_aer_stats_incr(struct pci_dev *pdev, struct aer_err_source *e_src) { - struct aer_stats *aer_stats = pdev->aer_stats; + struct aer_info *aer_info = pdev->aer_info; - if (!aer_stats) + if (!aer_info) return; if (e_src->status & PCI_ERR_ROOT_COR_RCV) - aer_stats->rootport_total_cor_errs++; + aer_info->rootport_total_cor_errs++; if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) { if (e_src->status & PCI_ERR_ROOT_FATAL_RCV) - aer_stats->rootport_total_fatal_errs++; + aer_info->rootport_total_fatal_errs++; else - aer_stats->rootport_total_nonfatal_errs++; + aer_info->rootport_total_nonfatal_errs++; + } +} + +static int aer_ratelimit(struct pci_dev *dev, unsigned int severity) +{ + if (!dev->aer_info) + return 1; + + switch (severity) { + case AER_NONFATAL: + return __ratelimit(&dev->aer_info->nonfatal_ratelimit); + case AER_CORRECTABLE: + return __ratelimit(&dev->aer_info->correctable_ratelimit); + default: + return 1; /* Don't ratelimit fatal errors */ } } -static void __aer_print_error(struct pci_dev *dev, - struct aer_err_info *info) +static bool tlp_header_logged(u32 status, u32 capctl) +{ + /* Errors for which a header is always logged (PCIe r7.0 sec 6.2.7) */ + if (status & AER_LOG_TLP_MASKS) + return true; + + /* Completion Timeout header is only logged on capable devices */ + if (status & PCI_ERR_UNC_COMP_TIME && + capctl & PCI_ERR_CAP_COMP_TIME_LOG) + return true; + + return false; +} + +static void __aer_print_error(struct pci_dev *dev, struct aer_err_info *info) { const char **strings; unsigned long status = info->status & ~info->mask; - const char *level, *errmsg; + const char *level = info->level; + const char *errmsg; int i; - if (info->severity == AER_CORRECTABLE) { + if (info->severity == AER_CORRECTABLE) strings = aer_correctable_error_string; - level = KERN_WARNING; - } else { + else strings = aer_uncorrectable_error_string; - level = KERN_ERR; - } for_each_set_bit(i, &status, 32) { errmsg = strings[i]; @@ -693,28 +847,52 @@ static void __aer_print_error(struct pci_dev *dev, aer_printk(level, dev, " [%2d] %-22s%s\n", i, errmsg, info->first_error == i ? " (First)" : ""); } - pci_dev_aer_stats_incr(dev, info); } -void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) +static void aer_print_source(struct pci_dev *dev, struct aer_err_info *info, + bool found) +{ + u16 source = info->id; + + pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d%s\n", + info->multi_error_valid ? "Multiple " : "", + aer_error_severity_string[info->severity], + pci_domain_nr(dev->bus), PCI_BUS_NUM(source), + PCI_SLOT(source), PCI_FUNC(source), + found ? "" : " (no details found"); +} + +void aer_print_error(struct aer_err_info *info, int i) { - int layer, agent; - int id = pci_dev_id(dev); - const char *level; + struct pci_dev *dev; + int layer, agent, id; + const char *level = info->level; + const char *bus_type = aer_err_bus(info); + + if (WARN_ON_ONCE(i >= AER_MAX_MULTI_ERR_DEVICES)) + return; + + dev = info->dev[i]; + id = pci_dev_id(dev); + + pci_dev_aer_stats_incr(dev, info); + trace_aer_event(pci_name(dev), (info->status & ~info->mask), + info->severity, info->tlp_header_valid, &info->tlp, bus_type); + + if (!info->ratelimit_print[i]) + return; if (!info->status) { - pci_err(dev, "PCIe Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n", - aer_error_severity_string[info->severity]); + pci_err(dev, "%s Bus Error: severity=%s, type=Inaccessible, (Unregistered Agent ID)\n", + bus_type, aer_error_severity_string[info->severity]); goto out; } layer = AER_GET_LAYER_ERROR(info->severity, info->status); agent = AER_GET_AGENT(info->severity, info->status); - level = (info->severity == AER_CORRECTABLE) ? KERN_WARNING : KERN_ERR; - - aer_printk(level, dev, "PCIe Bus Error: severity=%s, type=%s, (%s)\n", - aer_error_severity_string[info->severity], + aer_printk(level, dev, "%s Bus Error: severity=%s, type=%s, (%s)\n", + bus_type, aer_error_severity_string[info->severity], aer_error_layer[layer], aer_agent_string[agent]); aer_printk(level, dev, " device [%04x:%04x] error status/mask=%08x/%08x\n", @@ -723,26 +901,11 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info) __aer_print_error(dev, info); if (info->tlp_header_valid) - pcie_print_tlp_log(dev, &info->tlp, dev_fmt(" ")); + pcie_print_tlp_log(dev, &info->tlp, level, dev_fmt(" ")); out: if (info->id && info->error_dev_num > 1 && info->id == id) pci_err(dev, " Error of this Agent is reported first\n"); - - trace_aer_event(dev_name(&dev->dev), (info->status & ~info->mask), - info->severity, info->tlp_header_valid, &info->tlp); -} - -static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info) -{ - u8 bus = info->id >> 8; - u8 devfn = info->id & 0xff; - - pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n", - info->multi_error_valid ? "Multiple " : "", - aer_error_severity_string[info->severity], - pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn), - PCI_FUNC(devfn)); } #ifdef CONFIG_ACPI_APEI_PCIEAER @@ -763,44 +926,56 @@ EXPORT_SYMBOL_GPL(cper_severity_to_aer); void pci_print_aer(struct pci_dev *dev, int aer_severity, struct aer_capability_regs *aer) { + const char *bus_type; int layer, agent, tlp_header_valid = 0; u32 status, mask; - struct aer_err_info info; + struct aer_err_info info = { + .severity = aer_severity, + .first_error = PCI_ERR_CAP_FEP(aer->cap_control), + }; if (aer_severity == AER_CORRECTABLE) { status = aer->cor_status; mask = aer->cor_mask; + info.level = KERN_WARNING; } else { status = aer->uncor_status; mask = aer->uncor_mask; - tlp_header_valid = status & AER_LOG_TLP_MASKS; + info.level = KERN_ERR; + tlp_header_valid = tlp_header_logged(status, aer->cap_control); } - layer = AER_GET_LAYER_ERROR(aer_severity, status); - agent = AER_GET_AGENT(aer_severity, status); - - memset(&info, 0, sizeof(info)); - info.severity = aer_severity; info.status = status; info.mask = mask; - info.first_error = PCI_ERR_CAP_FEP(aer->cap_control); + info.is_cxl = pcie_is_cxl(dev); + + bus_type = aer_err_bus(&info); + + pci_dev_aer_stats_incr(dev, &info); + trace_aer_event(pci_name(dev), (status & ~mask), aer_severity, + tlp_header_valid, &aer->header_log, bus_type); + + if (!aer_ratelimit(dev, info.severity)) + return; + + layer = AER_GET_LAYER_ERROR(aer_severity, status); + agent = AER_GET_AGENT(aer_severity, status); - pci_err(dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", status, mask); + aer_printk(info.level, dev, "aer_status: 0x%08x, aer_mask: 0x%08x\n", + status, mask); __aer_print_error(dev, &info); - pci_err(dev, "aer_layer=%s, aer_agent=%s\n", - aer_error_layer[layer], aer_agent_string[agent]); + aer_printk(info.level, dev, "aer_layer=%s, aer_agent=%s\n", + aer_error_layer[layer], aer_agent_string[agent]); if (aer_severity != AER_CORRECTABLE) - pci_err(dev, "aer_uncor_severity: 0x%08x\n", - aer->uncor_severity); + aer_printk(info.level, dev, "aer_uncor_severity: 0x%08x\n", + aer->uncor_severity); if (tlp_header_valid) - pcie_print_tlp_log(dev, &aer->header_log, dev_fmt(" ")); - - trace_aer_event(dev_name(&dev->dev), (status & ~mask), - aer_severity, tlp_header_valid, &aer->header_log); + pcie_print_tlp_log(dev, &aer->header_log, info.level, + dev_fmt(" ")); } -EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL"); +EXPORT_SYMBOL_GPL(pci_print_aer); /** * add_error_device - list device to be handled @@ -809,12 +984,27 @@ EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL"); */ static int add_error_device(struct aer_err_info *e_info, struct pci_dev *dev) { - if (e_info->error_dev_num < AER_MAX_MULTI_ERR_DEVICES) { - e_info->dev[e_info->error_dev_num] = pci_dev_get(dev); - e_info->error_dev_num++; - return 0; + int i = e_info->error_dev_num; + + if (i >= AER_MAX_MULTI_ERR_DEVICES) + return -ENOSPC; + + e_info->dev[i] = pci_dev_get(dev); + e_info->error_dev_num++; + + /* + * Ratelimit AER log messages. "dev" is either the source + * identified by the root's Error Source ID or it has an unmasked + * error logged in its own AER Capability. Messages are emitted + * when "ratelimit_print[i]" is non-zero. If we will print detail + * for a downstream device, make sure we print the Error Source ID + * from the root as well. + */ + if (aer_ratelimit(dev, e_info->severity)) { + e_info->ratelimit_print[i] = 1; + e_info->root_ratelimit_print = 1; } - return -ENOSPC; + return 0; } /** @@ -884,7 +1074,8 @@ static int find_device_iter(struct pci_dev *dev, void *data) /* List this device */ if (add_error_device(e_info, dev)) { /* We cannot handle more... Stop iteration */ - /* TODO: Should print error message here? */ + pci_err(dev, "Exceeded max supported (%d) devices with errors logged\n", + AER_MAX_MULTI_ERR_DEVICES); return 1; } @@ -908,7 +1099,7 @@ static int find_device_iter(struct pci_dev *dev, void *data) * e_info->error_dev_num and e_info->dev[], based on the given information. */ static bool find_source_device(struct pci_dev *parent, - struct aer_err_info *e_info) + struct aer_err_info *e_info) { struct pci_dev *dev = parent; int result; @@ -926,20 +1117,11 @@ static bool find_source_device(struct pci_dev *parent, else pci_walk_bus(parent->subordinate, find_device_iter, e_info); - if (!e_info->error_dev_num) { - u8 bus = e_info->id >> 8; - u8 devfn = e_info->id & 0xff; - - pci_info(parent, "found no error details for %04x:%02x:%02x.%d\n", - pci_domain_nr(parent->bus), bus, PCI_SLOT(devfn), - PCI_FUNC(devfn)); + if (!e_info->error_dev_num) return false; - } return true; } -#ifdef CONFIG_PCIEAER_CXL - /** * pci_aer_unmask_internal_errors - unmask internal errors * @dev: pointer to the pci_dev data structure @@ -950,7 +1132,7 @@ static bool find_source_device(struct pci_dev *parent, * Note: AER must be enabled and supported by the device which must be * checked in advance, e.g. with pcie_aer_is_native(). */ -static void pci_aer_unmask_internal_errors(struct pci_dev *dev) +void pci_aer_unmask_internal_errors(struct pci_dev *dev) { int aer = dev->aer_cap; u32 mask; @@ -964,117 +1146,20 @@ static void pci_aer_unmask_internal_errors(struct pci_dev *dev) pci_write_config_dword(dev, aer + PCI_ERR_COR_MASK, mask); } -static bool is_cxl_mem_dev(struct pci_dev *dev) -{ - /* - * The capability, status, and control fields in Device 0, - * Function 0 DVSEC control the CXL functionality of the - * entire device (CXL 3.0, 8.1.3). - */ - if (dev->devfn != PCI_DEVFN(0, 0)) - return false; - - /* - * CXL Memory Devices must have the 502h class code set (CXL - * 3.0, 8.1.12.1). - */ - if ((dev->class >> 8) != PCI_CLASS_MEMORY_CXL) - return false; - - return true; -} - -static bool cxl_error_is_native(struct pci_dev *dev) -{ - struct pci_host_bridge *host = pci_find_host_bridge(dev->bus); - - return (pcie_ports_native || host->native_aer); -} +/* + * Internal errors are too device-specific to enable generally, however for CXL + * their behavior is standardized for conveying CXL protocol errors. + */ +EXPORT_SYMBOL_FOR_MODULES(pci_aer_unmask_internal_errors, "cxl_core"); -static bool is_internal_error(struct aer_err_info *info) +#ifdef CONFIG_CXL_RAS +bool is_aer_internal_error(struct aer_err_info *info) { if (info->severity == AER_CORRECTABLE) return info->status & PCI_ERR_COR_INTERNAL; return info->status & PCI_ERR_UNC_INTN; } - -static int cxl_rch_handle_error_iter(struct pci_dev *dev, void *data) -{ - struct aer_err_info *info = (struct aer_err_info *)data; - const struct pci_error_handlers *err_handler; - - if (!is_cxl_mem_dev(dev) || !cxl_error_is_native(dev)) - return 0; - - /* Protect dev->driver */ - device_lock(&dev->dev); - - err_handler = dev->driver ? dev->driver->err_handler : NULL; - if (!err_handler) - goto out; - - if (info->severity == AER_CORRECTABLE) { - if (err_handler->cor_error_detected) - err_handler->cor_error_detected(dev); - } else if (err_handler->error_detected) { - if (info->severity == AER_NONFATAL) - err_handler->error_detected(dev, pci_channel_io_normal); - else if (info->severity == AER_FATAL) - err_handler->error_detected(dev, pci_channel_io_frozen); - } -out: - device_unlock(&dev->dev); - return 0; -} - -static void cxl_rch_handle_error(struct pci_dev *dev, struct aer_err_info *info) -{ - /* - * Internal errors of an RCEC indicate an AER error in an - * RCH's downstream port. Check and handle them in the CXL.mem - * device driver. - */ - if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC && - is_internal_error(info)) - pcie_walk_rcec(dev, cxl_rch_handle_error_iter, info); -} - -static int handles_cxl_error_iter(struct pci_dev *dev, void *data) -{ - bool *handles_cxl = data; - - if (!*handles_cxl) - *handles_cxl = is_cxl_mem_dev(dev) && cxl_error_is_native(dev); - - /* Non-zero terminates iteration */ - return *handles_cxl; -} - -static bool handles_cxl_errors(struct pci_dev *rcec) -{ - bool handles_cxl = false; - - if (pci_pcie_type(rcec) == PCI_EXP_TYPE_RC_EC && - pcie_aer_is_native(rcec)) - pcie_walk_rcec(rcec, handles_cxl_error_iter, &handles_cxl); - - return handles_cxl; -} - -static void cxl_rch_enable_rcec(struct pci_dev *rcec) -{ - if (!handles_cxl_errors(rcec)) - return; - - pci_aer_unmask_internal_errors(rcec); - pci_info(rcec, "CXL: Internal errors unmasked"); -} - -#else -static inline void cxl_rch_enable_rcec(struct pci_dev *dev) { } -static inline void cxl_rch_handle_error(struct pci_dev *dev, - struct aer_err_info *info) { } #endif /** @@ -1141,9 +1226,10 @@ static void aer_recover_work_func(struct work_struct *work) pdev = pci_get_domain_bus_and_slot(entry.domain, entry.bus, entry.devfn); if (!pdev) { - pr_err("no pci_dev for %04x:%02x:%02x.%x\n", - entry.domain, entry.bus, - PCI_SLOT(entry.devfn), PCI_FUNC(entry.devfn)); + pr_err_ratelimited("%04x:%02x:%02x.%x: no pci_dev found\n", + entry.domain, entry.bus, + PCI_SLOT(entry.devfn), + PCI_FUNC(entry.devfn)); continue; } pci_print_aer(pdev, entry.severity, entry.regs); @@ -1199,22 +1285,30 @@ EXPORT_SYMBOL_GPL(aer_recover_queue); /** * aer_get_device_error_info - read error status from dev and store it to info - * @dev: pointer to the device expected to have an error record * @info: pointer to structure to store the error record + * @i: index into info->dev[] * * Return: 1 on success, 0 on error. * * Note that @info is reused among all error devices. Clear fields properly. */ -int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) +int aer_get_device_error_info(struct aer_err_info *info, int i) { - int type = pci_pcie_type(dev); - int aer = dev->aer_cap; + struct pci_dev *dev; + int type, aer; u32 aercc; + if (i >= AER_MAX_MULTI_ERR_DEVICES) + return 0; + + dev = info->dev[i]; + aer = dev->aer_cap; + type = pci_pcie_type(dev); + /* Must reset in this function */ info->status = 0; info->tlp_header_valid = 0; + info->is_cxl = pcie_is_cxl(dev); /* The device might not support AER */ if (!aer) @@ -1244,7 +1338,7 @@ int aer_get_device_error_info(struct pci_dev *dev, struct aer_err_info *info) pci_read_config_dword(dev, aer + PCI_ERR_CAP, &aercc); info->first_error = PCI_ERR_CAP_FEP(aercc); - if (info->status & AER_LOG_TLP_MASKS) { + if (tlp_header_logged(info->status, aercc)) { info->tlp_header_valid = 1; pcie_read_tlp_log(dev, aer + PCI_ERR_HEADER_LOG, aer + PCI_ERR_PREFIX_LOG, @@ -1263,63 +1357,87 @@ static inline void aer_process_err_devices(struct aer_err_info *e_info) /* Report all before handling them, to not lose records by reset etc. */ for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) { - if (aer_get_device_error_info(e_info->dev[i], e_info)) - aer_print_error(e_info->dev[i], e_info); + if (aer_get_device_error_info(e_info, i)) + aer_print_error(e_info, i); } for (i = 0; i < e_info->error_dev_num && e_info->dev[i]; i++) { - if (aer_get_device_error_info(e_info->dev[i], e_info)) + if (aer_get_device_error_info(e_info, i)) handle_error_source(e_info->dev[i], e_info); } } /** - * aer_isr_one_error - consume an error detected by Root Port - * @rpc: pointer to the Root Port which holds an error - * @e_src: pointer to an error source + * aer_isr_one_error_type - consume a Correctable or Uncorrectable Error + * detected by Root Port or RCEC + * @root: pointer to Root Port or RCEC that signaled AER interrupt + * @info: pointer to AER error info */ -static void aer_isr_one_error(struct aer_rpc *rpc, - struct aer_err_source *e_src) +static void aer_isr_one_error_type(struct pci_dev *root, + struct aer_err_info *info) { - struct pci_dev *pdev = rpc->rpd; - struct aer_err_info e_info; + bool found; - pci_rootport_aer_stats_incr(pdev, e_src); + found = find_source_device(root, info); /* - * There is a possibility that both correctable error and - * uncorrectable error being logged. Report correctable error first. + * If we're going to log error messages, we've already set + * "info->root_ratelimit_print" and "info->ratelimit_print[i]" to + * non-zero (which enables printing) because this is either an + * ERR_FATAL or we found a device with an error logged in its AER + * Capability. + * + * If we didn't find the Error Source device, at least log the + * Requester ID from the ERR_* Message received by the Root Port or + * RCEC, ratelimited by the RP or RCEC. */ - if (e_src->status & PCI_ERR_ROOT_COR_RCV) { - e_info.id = ERR_COR_ID(e_src->id); - e_info.severity = AER_CORRECTABLE; - - if (e_src->status & PCI_ERR_ROOT_MULTI_COR_RCV) - e_info.multi_error_valid = 1; - else - e_info.multi_error_valid = 0; - aer_print_port_info(pdev, &e_info); - - if (find_source_device(pdev, &e_info)) - aer_process_err_devices(&e_info); - } + if (info->root_ratelimit_print || + (!found && aer_ratelimit(root, info->severity))) + aer_print_source(root, info, found); - if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) { - e_info.id = ERR_UNCOR_ID(e_src->id); + if (found) + aer_process_err_devices(info); +} - if (e_src->status & PCI_ERR_ROOT_FATAL_RCV) - e_info.severity = AER_FATAL; - else - e_info.severity = AER_NONFATAL; +/** + * aer_isr_one_error - consume error(s) signaled by an AER interrupt from + * Root Port or RCEC + * @root: pointer to Root Port or RCEC that signaled AER interrupt + * @e_src: pointer to an error source + */ +static void aer_isr_one_error(struct pci_dev *root, + struct aer_err_source *e_src) +{ + u32 status = e_src->status; - if (e_src->status & PCI_ERR_ROOT_MULTI_UNCOR_RCV) - e_info.multi_error_valid = 1; - else - e_info.multi_error_valid = 0; + pci_rootport_aer_stats_incr(root, e_src); - aer_print_port_info(pdev, &e_info); + /* + * There is a possibility that both correctable error and + * uncorrectable error being logged. Report correctable error first. + */ + if (status & PCI_ERR_ROOT_COR_RCV) { + int multi = status & PCI_ERR_ROOT_MULTI_COR_RCV; + struct aer_err_info e_info = { + .id = ERR_COR_ID(e_src->id), + .severity = AER_CORRECTABLE, + .level = KERN_WARNING, + .multi_error_valid = multi ? 1 : 0, + }; + + aer_isr_one_error_type(root, &e_info); + } - if (find_source_device(pdev, &e_info)) - aer_process_err_devices(&e_info); + if (status & PCI_ERR_ROOT_UNCOR_RCV) { + int fatal = status & PCI_ERR_ROOT_FATAL_RCV; + int multi = status & PCI_ERR_ROOT_MULTI_UNCOR_RCV; + struct aer_err_info e_info = { + .id = ERR_UNCOR_ID(e_src->id), + .severity = fatal ? AER_FATAL : AER_NONFATAL, + .level = KERN_ERR, + .multi_error_valid = multi ? 1 : 0, + }; + + aer_isr_one_error_type(root, &e_info); } } @@ -1340,7 +1458,7 @@ static irqreturn_t aer_isr(int irq, void *context) return IRQ_NONE; while (kfifo_get(&rpc->aer_fifo, &e_src)) - aer_isr_one_error(rpc, &e_src); + aer_isr_one_error(rpc->rpd, &e_src); return IRQ_HANDLED; } @@ -1394,6 +1512,20 @@ static void aer_disable_irq(struct pci_dev *pdev) pci_write_config_dword(pdev, aer + PCI_ERR_ROOT_COMMAND, reg32); } +static int clear_status_iter(struct pci_dev *dev, void *data) +{ + u16 devctl; + + /* Skip if pci_enable_pcie_error_reporting() hasn't been called yet */ + pcie_capability_read_word(dev, PCI_EXP_DEVCTL, &devctl); + if (!(devctl & PCI_EXP_AER_FLAGS)) + return 0; + + pci_aer_clear_status(dev); + pcie_clear_device_status(dev); + return 0; +} + /** * aer_enable_rootport - enable Root Port's interrupts when receiving messages * @rpc: pointer to a Root Port data structure @@ -1415,9 +1547,19 @@ static void aer_enable_rootport(struct aer_rpc *rpc) pcie_capability_clear_word(pdev, PCI_EXP_RTCTL, SYSTEM_ERROR_INTR_ON_MESG_MASK); - /* Clear error status */ + /* Clear error status of this Root Port or RCEC */ pci_read_config_dword(pdev, aer + PCI_ERR_ROOT_STATUS, ®32); pci_write_config_dword(pdev, aer + PCI_ERR_ROOT_STATUS, reg32); + + /* Clear error status of agents reporting to this Root Port or RCEC */ + if (reg32 & AER_ERR_STATUS_MASK) { + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_RC_EC) + pcie_walk_rcec(pdev, clear_status_iter, NULL); + else if (pdev->subordinate) + pci_walk_bus(pdev->subordinate, clear_status_iter, + NULL); + } + pci_read_config_dword(pdev, aer + PCI_ERR_COR_STATUS, ®32); pci_write_config_dword(pdev, aer + PCI_ERR_COR_STATUS, reg32); pci_read_config_dword(pdev, aer + PCI_ERR_UNCOR_STATUS, ®32); diff --git a/drivers/pci/pcie/aer_cxl_rch.c b/drivers/pci/pcie/aer_cxl_rch.c new file mode 100644 index 000000000000..e471eefec9c4 --- /dev/null +++ b/drivers/pci/pcie/aer_cxl_rch.c @@ -0,0 +1,104 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright(c) 2023 AMD Corporation. All rights reserved. */ + +#include <linux/pci.h> +#include <linux/aer.h> +#include <linux/bitfield.h> +#include "../pci.h" +#include "portdrv.h" + +static bool is_cxl_mem_dev(struct pci_dev *dev) +{ + /* + * The capability, status, and control fields in Device 0, + * Function 0 DVSEC control the CXL functionality of the + * entire device (CXL 3.0, 8.1.3). + */ + if (dev->devfn != PCI_DEVFN(0, 0)) + return false; + + /* + * CXL Memory Devices must have the 502h class code set (CXL + * 3.0, 8.1.12.1). + */ + if ((dev->class >> 8) != PCI_CLASS_MEMORY_CXL) + return false; + + return true; +} + +static bool cxl_error_is_native(struct pci_dev *dev) +{ + struct pci_host_bridge *host = pci_find_host_bridge(dev->bus); + + return (pcie_ports_native || host->native_aer); +} + +static int cxl_rch_handle_error_iter(struct pci_dev *dev, void *data) +{ + struct aer_err_info *info = (struct aer_err_info *)data; + const struct pci_error_handlers *err_handler; + + if (!is_cxl_mem_dev(dev) || !cxl_error_is_native(dev)) + return 0; + + guard(device)(&dev->dev); + + err_handler = dev->driver ? dev->driver->err_handler : NULL; + if (!err_handler) + return 0; + + if (info->severity == AER_CORRECTABLE) { + if (err_handler->cor_error_detected) + err_handler->cor_error_detected(dev); + } else if (err_handler->error_detected) { + if (info->severity == AER_NONFATAL) + err_handler->error_detected(dev, pci_channel_io_normal); + else if (info->severity == AER_FATAL) + err_handler->error_detected(dev, pci_channel_io_frozen); + } + return 0; +} + +void cxl_rch_handle_error(struct pci_dev *dev, struct aer_err_info *info) +{ + /* + * Internal errors of an RCEC indicate an AER error in an + * RCH's downstream port. Check and handle them in the CXL.mem + * device driver. + */ + if (pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC && + is_aer_internal_error(info)) + pcie_walk_rcec(dev, cxl_rch_handle_error_iter, info); +} + +static int handles_cxl_error_iter(struct pci_dev *dev, void *data) +{ + bool *handles_cxl = data; + + if (!*handles_cxl) + *handles_cxl = is_cxl_mem_dev(dev) && cxl_error_is_native(dev); + + /* Non-zero terminates iteration */ + return *handles_cxl; +} + +static bool handles_cxl_errors(struct pci_dev *rcec) +{ + bool handles_cxl = false; + + if (pci_pcie_type(rcec) == PCI_EXP_TYPE_RC_EC && + pcie_aer_is_native(rcec)) + pcie_walk_rcec(rcec, handles_cxl_error_iter, &handles_cxl); + + return handles_cxl; +} + +void cxl_rch_enable_rcec(struct pci_dev *rcec) +{ + if (!handles_cxl_errors(rcec)) + return; + + pci_aer_unmask_internal_errors(rcec); + pci_info(rcec, "CXL: Internal errors unmasked"); +} diff --git a/drivers/pci/pcie/aer_inject.c b/drivers/pci/pcie/aer_inject.c index 91acc7b17f68..09bfc7194ef3 100644 --- a/drivers/pci/pcie/aer_inject.c +++ b/drivers/pci/pcie/aer_inject.c @@ -300,7 +300,7 @@ static int pci_bus_set_aer_ops(struct pci_bus *bus) struct pci_bus_ops *bus_ops; unsigned long flags; - bus_ops = kmalloc(sizeof(*bus_ops), GFP_KERNEL); + bus_ops = kmalloc_obj(*bus_ops); if (!bus_ops) return -ENOMEM; ops = pci_bus_set_ops(bus, &aer_inj_pci_ops); @@ -360,12 +360,12 @@ static int aer_inject(struct aer_error_inj *einj) goto out_put; } - err_alloc = kzalloc(sizeof(struct aer_error), GFP_KERNEL); + err_alloc = kzalloc_obj(struct aer_error); if (!err_alloc) { ret = -ENOMEM; goto out_put; } - rperr_alloc = kzalloc(sizeof(struct aer_error), GFP_KERNEL); + rperr_alloc = kzalloc_obj(struct aer_error); if (!rperr_alloc) { ret = -ENOMEM; goto out_put; diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c index 29fcb0689a91..21f5d23e0b61 100644 --- a/drivers/pci/pcie/aspm.c +++ b/drivers/pci/pcie/aspm.c @@ -15,6 +15,7 @@ #include <linux/math.h> #include <linux/module.h> #include <linux/moduleparam.h> +#include <linux/of.h> #include <linux/pci.h> #include <linux/pci_regs.h> #include <linux/errno.h> @@ -235,7 +236,8 @@ struct pcie_link_state { u32 aspm_support:7; /* Supported ASPM state */ u32 aspm_enabled:7; /* Enabled ASPM state */ u32 aspm_capable:7; /* Capable ASPM state with latency */ - u32 aspm_default:7; /* Default ASPM state by BIOS */ + u32 aspm_default:7; /* Default ASPM state by BIOS or + override */ u32 aspm_disable:7; /* Disabled ASPM state */ /* Clock PM state */ @@ -245,7 +247,7 @@ struct pcie_link_state { u32 clkpm_disable:1; /* Clock PM disabled */ }; -static int aspm_disabled, aspm_force; +static bool aspm_disabled, aspm_force; static bool aspm_support_enabled = true; static DEFINE_MUTEX(aspm_lock); static LIST_HEAD(link_list); @@ -788,10 +790,30 @@ static void aspm_l1ss_init(struct pcie_link_state *link) aspm_calc_l12_info(link, parent_l1ss_cap, child_l1ss_cap); } +#define FLAG(x, y, d) (((x) & (PCIE_LINK_STATE_##y)) ? d : "") + +static void pcie_aspm_override_default_link_state(struct pcie_link_state *link) +{ + struct pci_dev *pdev = link->downstream; + u32 override; + + /* For devicetree platforms, enable L0s and L1 by default */ + if (of_have_populated_dt()) { + if (link->aspm_support & PCIE_LINK_STATE_L0S) + link->aspm_default |= PCIE_LINK_STATE_L0S; + if (link->aspm_support & PCIE_LINK_STATE_L1) + link->aspm_default |= PCIE_LINK_STATE_L1; + override = link->aspm_default & ~link->aspm_enabled; + if (override) + pci_info(pdev, "ASPM: default states%s%s\n", + FLAG(override, L0S, " L0s"), + FLAG(override, L1, " L1")); + } +} + static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) { struct pci_dev *child = link->downstream, *parent = link->pdev; - u32 parent_lnkcap, child_lnkcap; u16 parent_lnkctl, child_lnkctl; struct pci_bus *linkbus = parent->subordinate; @@ -806,9 +828,8 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) * If ASPM not supported, don't mess with the clocks and link, * bail out now. */ - pcie_capability_read_dword(parent, PCI_EXP_LNKCAP, &parent_lnkcap); - pcie_capability_read_dword(child, PCI_EXP_LNKCAP, &child_lnkcap); - if (!(parent_lnkcap & child_lnkcap & PCI_EXP_LNKCAP_ASPMS)) + if (!(parent->aspm_l0s_support && child->aspm_l0s_support) && + !(parent->aspm_l1_support && child->aspm_l1_support)) return; /* Configure common clock before checking latencies */ @@ -820,8 +841,6 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) * read-only Link Capabilities may change depending on common clock * configuration (PCIe r5.0, sec 7.5.3.6). */ - pcie_capability_read_dword(parent, PCI_EXP_LNKCAP, &parent_lnkcap); - pcie_capability_read_dword(child, PCI_EXP_LNKCAP, &child_lnkcap); pcie_capability_read_word(parent, PCI_EXP_LNKCTL, &parent_lnkctl); pcie_capability_read_word(child, PCI_EXP_LNKCTL, &child_lnkctl); @@ -841,7 +860,7 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) * given link unless components on both sides of the link each * support L0s. */ - if (parent_lnkcap & child_lnkcap & PCI_EXP_LNKCAP_ASPM_L0S) + if (parent->aspm_l0s_support && child->aspm_l0s_support) link->aspm_support |= PCIE_LINK_STATE_L0S; if (child_lnkctl & PCI_EXP_LNKCTL_ASPM_L0S) @@ -850,7 +869,7 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) link->aspm_enabled |= PCIE_LINK_STATE_L0S_DW; /* Setup L1 state */ - if (parent_lnkcap & child_lnkcap & PCI_EXP_LNKCAP_ASPM_L1) + if (parent->aspm_l1_support && child->aspm_l1_support) link->aspm_support |= PCIE_LINK_STATE_L1; if (parent_lnkctl & child_lnkctl & PCI_EXP_LNKCTL_ASPM_L1) @@ -868,6 +887,8 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) /* Save default state */ link->aspm_default = link->aspm_enabled; + pcie_aspm_override_default_link_state(link); + /* Setup initial capable state. Will be updated later */ link->aspm_capable = link->aspm_support; @@ -884,10 +905,9 @@ static void pcie_aspm_cap_init(struct pcie_link_state *link, int blacklist) /* Configure the ASPM L1 substates. Caller must disable L1 first. */ static void pcie_config_aspm_l1ss(struct pcie_link_state *link, u32 state) { - u32 val; + u32 val = 0; struct pci_dev *child = link->downstream, *parent = link->pdev; - val = 0; if (state & PCIE_LINK_STATE_L1_1) val |= PCI_L1SS_CTL1_ASPM_L1_1; if (state & PCIE_LINK_STATE_L1_2) @@ -1043,7 +1063,7 @@ static struct pcie_link_state *alloc_pcie_link_state(struct pci_dev *pdev) { struct pcie_link_state *link; - link = kzalloc(sizeof(*link), GFP_KERNEL); + link = kzalloc_obj(*link); if (!link) return NULL; @@ -1506,6 +1526,19 @@ int pci_enable_link_state_locked(struct pci_dev *pdev, int state) } EXPORT_SYMBOL(pci_enable_link_state_locked); +void pcie_aspm_remove_cap(struct pci_dev *pdev, u32 lnkcap) +{ + if (lnkcap & PCI_EXP_LNKCAP_ASPM_L0S) + pdev->aspm_l0s_support = 0; + if (lnkcap & PCI_EXP_LNKCAP_ASPM_L1) + pdev->aspm_l1_support = 0; + + pci_info(pdev, "ASPM: Link Capabilities%s%s treated as unsupported to avoid device defect\n", + lnkcap & PCI_EXP_LNKCAP_ASPM_L0S ? " L0s" : "", + lnkcap & PCI_EXP_LNKCAP_ASPM_L1 ? " L1" : ""); + +} + static int pcie_aspm_set_policy(const char *val, const struct kernel_param *kp) { @@ -1712,11 +1745,11 @@ static int __init pcie_aspm_disable(char *str) { if (!strcmp(str, "off")) { aspm_policy = POLICY_DEFAULT; - aspm_disabled = 1; + aspm_disabled = true; aspm_support_enabled = false; pr_info("PCIe ASPM is disabled\n"); } else if (!strcmp(str, "force")) { - aspm_force = 1; + aspm_force = true; pr_info("PCIe ASPM is forcibly enabled\n"); } return 1; @@ -1734,7 +1767,7 @@ void pcie_no_aspm(void) */ if (!aspm_force) { aspm_policy = POLICY_DEFAULT; - aspm_disabled = 1; + aspm_disabled = true; } } diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c index d8d2aa85a229..c4c8d260bf96 100644 --- a/drivers/pci/pcie/bwctrl.c +++ b/drivers/pci/pcie/bwctrl.c @@ -38,24 +38,14 @@ /** * struct pcie_bwctrl_data - PCIe bandwidth controller * @set_speed_mutex: Serializes link speed changes - * @lbms_count: Count for LBMS (since last reset) * @cdev: Thermal cooling device associated with the port */ struct pcie_bwctrl_data { struct mutex set_speed_mutex; - atomic_t lbms_count; struct thermal_cooling_device *cdev; }; -/* - * Prevent port removal during LBMS count accessors and Link Speed changes. - * - * These have to be differentiated because pcie_bwctrl_change_speed() calls - * pcie_retrain_link() which uses LBMS count reset accessor on success - * (using just one rwsem triggers "possible recursive locking detected" - * warning). - */ -static DECLARE_RWSEM(pcie_bwctrl_lbms_rwsem); +/* Prevent port removal during Link Speed changes. */ static DECLARE_RWSEM(pcie_bwctrl_setspeed_rwsem); static bool pcie_valid_speed(enum pci_bus_speed speed) @@ -127,18 +117,7 @@ static int pcie_bwctrl_change_speed(struct pci_dev *port, u16 target_speed, bool if (ret != PCIBIOS_SUCCESSFUL) return pcibios_err_to_errno(ret); - ret = pcie_retrain_link(port, use_lt); - if (ret < 0) - return ret; - - /* - * Ensure link speed updates also with platforms that have problems - * with notifications. - */ - if (port->subordinate) - pcie_update_link_speed(port->subordinate); - - return 0; + return pcie_retrain_link(port, use_lt); } /** @@ -202,15 +181,14 @@ int pcie_set_target_speed(struct pci_dev *port, enum pci_bus_speed speed_req, static void pcie_bwnotif_enable(struct pcie_device *srv) { - struct pcie_bwctrl_data *data = srv->port->link_bwctrl; struct pci_dev *port = srv->port; u16 link_status; int ret; - /* Count LBMS seen so far as one */ + /* Note if LBMS has been seen so far */ ret = pcie_capability_read_word(port, PCI_EXP_LNKSTA, &link_status); if (ret == PCIBIOS_SUCCESSFUL && link_status & PCI_EXP_LNKSTA_LBMS) - atomic_inc(&data->lbms_count); + set_bit(PCI_LINK_LBMS_SEEN, &port->priv_flags); pcie_capability_set_word(port, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_LBMIE | PCI_EXP_LNKCTL_LABIE); @@ -221,7 +199,7 @@ static void pcie_bwnotif_enable(struct pcie_device *srv) * Update after enabling notifications & clearing status bits ensures * link speed is up to date. */ - pcie_update_link_speed(port->subordinate); + pcie_update_link_speed(port->subordinate, PCIE_BWCTRL_ENABLE); } static void pcie_bwnotif_disable(struct pci_dev *port) @@ -233,7 +211,6 @@ static void pcie_bwnotif_disable(struct pci_dev *port) static irqreturn_t pcie_bwnotif_irq(int irq, void *context) { struct pcie_device *srv = context; - struct pcie_bwctrl_data *data = srv->port->link_bwctrl; struct pci_dev *port = srv->port; u16 link_status, events; int ret; @@ -247,7 +224,7 @@ static irqreturn_t pcie_bwnotif_irq(int irq, void *context) return IRQ_NONE; if (events & PCI_EXP_LNKSTA_LBMS) - atomic_inc(&data->lbms_count); + set_bit(PCI_LINK_LBMS_SEEN, &port->priv_flags); pcie_capability_write_word(port, PCI_EXP_LNKSTA, events); @@ -257,36 +234,15 @@ static irqreturn_t pcie_bwnotif_irq(int irq, void *context) * speed (inside pcie_update_link_speed()) after LBMS has been * cleared to avoid missing link speed changes. */ - pcie_update_link_speed(port->subordinate); + pcie_update_link_speed(port->subordinate, PCIE_BWCTRL_IRQ); return IRQ_HANDLED; } -void pcie_reset_lbms_count(struct pci_dev *port) -{ - struct pcie_bwctrl_data *data; - - guard(rwsem_read)(&pcie_bwctrl_lbms_rwsem); - data = port->link_bwctrl; - if (data) - atomic_set(&data->lbms_count, 0); - else - pcie_capability_write_word(port, PCI_EXP_LNKSTA, - PCI_EXP_LNKSTA_LBMS); -} - -int pcie_lbms_count(struct pci_dev *port, unsigned long *val) +void pcie_reset_lbms(struct pci_dev *port) { - struct pcie_bwctrl_data *data; - - guard(rwsem_read)(&pcie_bwctrl_lbms_rwsem); - data = port->link_bwctrl; - if (!data) - return -ENOTTY; - - *val = atomic_read(&data->lbms_count); - - return 0; + clear_bit(PCI_LINK_LBMS_SEEN, &port->priv_flags); + pcie_capability_write_word(port, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS); } static int pcie_bwnotif_probe(struct pcie_device *srv) @@ -294,6 +250,9 @@ static int pcie_bwnotif_probe(struct pcie_device *srv) struct pci_dev *port = srv->port; int ret; + if (port->no_bw_notif) + return -ENODEV; + /* Can happen if we run out of bus numbers during enumeration. */ if (!port->subordinate) return -ENODEV; @@ -308,18 +267,16 @@ static int pcie_bwnotif_probe(struct pcie_device *srv) return ret; scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) { - scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) { - port->link_bwctrl = data; + port->link_bwctrl = data; - ret = request_irq(srv->irq, pcie_bwnotif_irq, - IRQF_SHARED, "PCIe bwctrl", srv); - if (ret) { - port->link_bwctrl = NULL; - return ret; - } - - pcie_bwnotif_enable(srv); + ret = request_irq(srv->irq, pcie_bwnotif_irq, + IRQF_SHARED, "PCIe bwctrl", srv); + if (ret) { + port->link_bwctrl = NULL; + return ret; } + + pcie_bwnotif_enable(srv); } pci_dbg(port, "enabled with IRQ %d\n", srv->irq); @@ -339,13 +296,11 @@ static void pcie_bwnotif_remove(struct pcie_device *srv) pcie_cooling_device_unregister(data->cdev); scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) { - scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) { - pcie_bwnotif_disable(srv->port); + pcie_bwnotif_disable(srv->port); - free_irq(srv->irq, srv); + free_irq(srv->irq, srv); - srv->port->link_bwctrl = NULL; - } + srv->port->link_bwctrl = NULL; } } diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c index df42f15c9829..fc18349614d7 100644 --- a/drivers/pci/pcie/dpc.c +++ b/drivers/pci/pcie/dpc.c @@ -222,7 +222,7 @@ static void dpc_process_rp_pio_error(struct pci_dev *pdev) dpc_tlp_log_len(pdev), pdev->subordinate->flit_mode, &tlp_log); - pcie_print_tlp_log(pdev, &tlp_log, dev_fmt("")); + pcie_print_tlp_log(pdev, &tlp_log, KERN_ERR, dev_fmt("")); if (pdev->dpc_rp_log_size < PCIE_STD_NUM_TLP_HEADERLOG + 1) goto clear_status; @@ -252,46 +252,59 @@ static int dpc_get_aer_uncorrect_severity(struct pci_dev *dev, else info->severity = AER_NONFATAL; + info->level = KERN_ERR; + + info->dev[0] = dev; + info->error_dev_num = 1; + return 1; } void dpc_process_error(struct pci_dev *pdev) { u16 cap = pdev->dpc_cap, status, source, reason, ext_reason; - struct aer_err_info info; + struct aer_err_info info = {}; pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status); - pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source); - - pci_info(pdev, "containment event, status:%#06x source:%#06x\n", - status, source); reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN; - ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT; - pci_warn(pdev, "%s detected\n", - (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR) ? - "unmasked uncorrectable error" : - (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE) ? - "ERR_NONFATAL" : - (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ? - "ERR_FATAL" : - (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ? - "RP PIO error" : - (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ? - "software trigger" : - "reserved error"); - - /* show RP PIO error detail information */ - if (pdev->dpc_rp_extensions && - reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT && - ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) - dpc_process_rp_pio_error(pdev); - else if (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR && - dpc_get_aer_uncorrect_severity(pdev, &info) && - aer_get_device_error_info(pdev, &info)) { - aer_print_error(pdev, &info); - pci_aer_clear_nonfatal_status(pdev); - pci_aer_clear_fatal_status(pdev); + + switch (reason) { + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR: + pci_warn(pdev, "containment event, status:%#06x: unmasked uncorrectable error detected\n", + status); + if (dpc_get_aer_uncorrect_severity(pdev, &info) && + aer_get_device_error_info(&info, 0)) { + aer_print_error(&info, 0); + pci_aer_clear_nonfatal_status(pdev); + pci_aer_clear_fatal_status(pdev); + } + break; + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE: + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE: + pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, + &source); + pci_warn(pdev, "containment event, status:%#06x, %s received from %04x:%02x:%02x.%d\n", + status, + (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ? + "ERR_FATAL" : "ERR_NONFATAL", + pci_domain_nr(pdev->bus), PCI_BUS_NUM(source), + PCI_SLOT(source), PCI_FUNC(source)); + break; + case PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT: + ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT; + pci_warn(pdev, "containment event, status:%#06x: %s detected\n", + status, + (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ? + "RP PIO error" : + (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ? + "software trigger" : + "reserved error"); + /* show RP PIO error detail information */ + if (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO && + pdev->dpc_rp_extensions) + dpc_process_rp_pio_error(pdev); + break; } } diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c index 31090770fffc..bebe4bc111d7 100644 --- a/drivers/pci/pcie/err.c +++ b/drivers/pci/pcie/err.c @@ -108,6 +108,24 @@ static int report_normal_detected(struct pci_dev *dev, void *data) return report_error_detected(dev, pci_channel_io_normal, data); } +static int report_perm_failure_detected(struct pci_dev *dev, void *data) +{ + struct pci_driver *pdrv; + const struct pci_error_handlers *err_handler; + + device_lock(&dev->dev); + pdrv = dev->driver; + if (!pdrv || !pdrv->err_handler || !pdrv->err_handler->error_detected) + goto out; + + err_handler = pdrv->err_handler; + err_handler->error_detected(dev, pci_channel_io_perm_failure); +out: + pci_uevent_ers(dev, PCI_ERS_RESULT_DISCONNECT); + device_unlock(&dev->dev); + return 0; +} + static int report_mmio_enabled(struct pci_dev *dev, void *data) { struct pci_driver *pdrv; @@ -135,7 +153,8 @@ static int report_slot_reset(struct pci_dev *dev, void *data) device_lock(&dev->dev); pdrv = dev->driver; - if (!pdrv || !pdrv->err_handler || !pdrv->err_handler->slot_reset) + if (!pci_dev_set_io_state(dev, pci_channel_io_normal) || + !pdrv || !pdrv->err_handler || !pdrv->err_handler->slot_reset) goto out; err_handler = pdrv->err_handler; @@ -217,15 +236,10 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, pci_walk_bridge(bridge, pci_pm_runtime_get_sync, NULL); pci_dbg(bridge, "broadcast error_detected message\n"); - if (state == pci_channel_io_frozen) { + if (state == pci_channel_io_frozen) pci_walk_bridge(bridge, report_frozen_detected, &status); - if (reset_subordinates(bridge) != PCI_ERS_RESULT_RECOVERED) { - pci_warn(bridge, "subordinate device reset failed\n"); - goto failed; - } - } else { + else pci_walk_bridge(bridge, report_normal_detected, &status); - } if (status == PCI_ERS_RESULT_CAN_RECOVER) { status = PCI_ERS_RESULT_RECOVERED; @@ -233,6 +247,14 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, pci_walk_bridge(bridge, report_mmio_enabled, &status); } + if (status == PCI_ERS_RESULT_NEED_RESET || + state == pci_channel_io_frozen) { + if (reset_subordinates(bridge) != PCI_ERS_RESULT_RECOVERED) { + pci_warn(bridge, "subordinate device reset failed\n"); + goto failed; + } + } + if (status == PCI_ERS_RESULT_NEED_RESET) { /* * TODO: Should call platform-specific @@ -269,9 +291,8 @@ pci_ers_result_t pcie_do_recovery(struct pci_dev *dev, failed: pci_walk_bridge(bridge, pci_pm_runtime_put, NULL); - pci_uevent_ers(bridge, PCI_ERS_RESULT_DISCONNECT); + pci_walk_bridge(bridge, report_perm_failure_detected, NULL); - /* TODO: Should kernel panic here? */ pci_info(bridge, "device recovery failed\n"); return status; diff --git a/drivers/pci/pcie/pme.c b/drivers/pci/pcie/pme.c index a2daebd9806c..4996cc4789f3 100644 --- a/drivers/pci/pcie/pme.c +++ b/drivers/pci/pcie/pme.c @@ -335,7 +335,7 @@ static int pcie_pme_probe(struct pcie_device *srv) type != PCI_EXP_TYPE_ROOT_PORT) return -ENODEV; - data = kzalloc(sizeof(*data), GFP_KERNEL); + data = kzalloc_obj(*data); if (!data) return -ENOMEM; diff --git a/drivers/pci/pcie/portdrv.c b/drivers/pci/pcie/portdrv.c index e8318fd5f6ed..2d6aa488fe7b 100644 --- a/drivers/pci/pcie/portdrv.c +++ b/drivers/pci/pcie/portdrv.c @@ -220,7 +220,7 @@ static int get_port_device_capability(struct pci_dev *dev) struct pci_host_bridge *host = pci_find_host_bridge(dev->bus); int services = 0; - if (dev->is_hotplug_bridge && + if (dev->is_pciehp && (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT || pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM) && (pcie_ports_native || host->native_pcie_hotplug)) { @@ -293,7 +293,7 @@ static int pcie_device_init(struct pci_dev *pdev, int service, int irq) struct pcie_device *pcie; struct device *device; - pcie = kzalloc(sizeof(*pcie), GFP_KERNEL); + pcie = kzalloc_obj(*pcie); if (!pcie) return -ENOMEM; pcie->port = pdev; @@ -508,23 +508,35 @@ static void pcie_port_device_remove(struct pci_dev *dev) pci_free_irq_vectors(dev); } +static int pcie_port_bus_match(struct device *dev, const struct device_driver *drv) +{ + struct pcie_device *pciedev = to_pcie_device(dev); + const struct pcie_port_service_driver *driver = to_service_driver(drv); + + if (driver->service != pciedev->service) + return 0; + + if (driver->port_type != PCIE_ANY_PORT && + driver->port_type != pci_pcie_type(pciedev->port)) + return 0; + + return 1; +} + /** - * pcie_port_probe_service - probe driver for given PCI Express port service + * pcie_port_bus_probe - probe driver for given PCI Express port service * @dev: PCI Express port service device to probe against * * If PCI Express port service driver is registered with * pcie_port_service_register(), this function will be called by the driver core * whenever match is found between the driver and a port service device. */ -static int pcie_port_probe_service(struct device *dev) +static int pcie_port_bus_probe(struct device *dev) { struct pcie_device *pciedev; struct pcie_port_service_driver *driver; int status; - if (!dev || !dev->driver) - return -ENODEV; - driver = to_service_driver(dev->driver); if (!driver || !driver->probe) return -ENODEV; @@ -539,7 +551,7 @@ static int pcie_port_probe_service(struct device *dev) } /** - * pcie_port_remove_service - detach driver from given PCI Express port service + * pcie_port_bus_remove - detach driver from given PCI Express port service * @dev: PCI Express port service device to handle * * If PCI Express port service driver is registered with @@ -547,33 +559,25 @@ static int pcie_port_probe_service(struct device *dev) * when device_unregister() is called for the port service device associated * with the driver. */ -static int pcie_port_remove_service(struct device *dev) +static void pcie_port_bus_remove(struct device *dev) { struct pcie_device *pciedev; struct pcie_port_service_driver *driver; - if (!dev || !dev->driver) - return 0; - pciedev = to_pcie_device(dev); driver = to_service_driver(dev->driver); - if (driver && driver->remove) { + if (driver && driver->remove) driver->remove(pciedev); - put_device(dev); - } - return 0; + + put_device(dev); } -/** - * pcie_port_shutdown_service - shut down given PCI Express port service - * @dev: PCI Express port service device to handle - * - * If PCI Express port service driver is registered with - * pcie_port_service_register(), this function will be called by the driver core - * when device_shutdown() is called for the port service device associated - * with the driver. - */ -static void pcie_port_shutdown_service(struct device *dev) {} +const struct bus_type pcie_port_bus_type = { + .name = "pci_express", + .match = pcie_port_bus_match, + .probe = pcie_port_bus_probe, + .remove = pcie_port_bus_remove, +}; /** * pcie_port_service_register - register PCI Express port service driver @@ -586,9 +590,6 @@ int pcie_port_service_register(struct pcie_port_service_driver *new) new->driver.name = new->name; new->driver.bus = &pcie_port_bus_type; - new->driver.probe = pcie_port_probe_service; - new->driver.remove = pcie_port_remove_service; - new->driver.shutdown = pcie_port_shutdown_service; return driver_register(&new->driver); } @@ -760,7 +761,6 @@ static pci_ers_result_t pcie_portdrv_slot_reset(struct pci_dev *dev) device_for_each_child(&dev->dev, &off, pcie_port_device_iter); pci_restore_state(dev); - pci_save_state(dev); return PCI_ERS_RESULT_RECOVERED; } diff --git a/drivers/pci/pcie/portdrv.h b/drivers/pci/pcie/portdrv.h index bd29d1cc7b8b..cc58bf2f2c84 100644 --- a/drivers/pci/pcie/portdrv.h +++ b/drivers/pci/pcie/portdrv.h @@ -123,4 +123,16 @@ static inline void pcie_pme_interrupt_enable(struct pci_dev *dev, bool en) {} #endif /* !CONFIG_PCIE_PME */ struct device *pcie_port_find_device(struct pci_dev *dev, u32 service); + +struct aer_err_info; + +#ifdef CONFIG_CXL_RAS +bool is_aer_internal_error(struct aer_err_info *info); +void cxl_rch_handle_error(struct pci_dev *dev, struct aer_err_info *info); +void cxl_rch_enable_rcec(struct pci_dev *rcec); +#else +static inline bool is_aer_internal_error(struct aer_err_info *info) { return false; } +static inline void cxl_rch_handle_error(struct pci_dev *dev, struct aer_err_info *info) { } +static inline void cxl_rch_enable_rcec(struct pci_dev *rcec) { } +#endif /* CONFIG_CXL_RAS */ #endif /* _PORTDRV_H_ */ diff --git a/drivers/pci/pcie/ptm.c b/drivers/pci/pcie/ptm.c index 7cfb6c0d5dcb..91a598ed534c 100644 --- a/drivers/pci/pcie/ptm.c +++ b/drivers/pci/pcie/ptm.c @@ -5,6 +5,7 @@ */ #include <linux/bitfield.h> +#include <linux/debugfs.h> #include <linux/module.h> #include <linux/init.h> #include <linux/pci.h> @@ -80,6 +81,11 @@ void pci_ptm_init(struct pci_dev *dev) dev->ptm_granularity = 0; } + if (cap & PCI_PTM_CAP_RES) + dev->ptm_responder = 1; + if (cap & PCI_PTM_CAP_REQ) + dev->ptm_requester = 1; + if (pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT || pci_pcie_type(dev) == PCI_EXP_TYPE_UPSTREAM) pci_enable_ptm(dev, NULL); @@ -143,6 +149,24 @@ static int __pci_enable_ptm(struct pci_dev *dev) return -EINVAL; } + switch (pci_pcie_type(dev)) { + case PCI_EXP_TYPE_ROOT_PORT: + if (!dev->ptm_root) + return -EINVAL; + break; + case PCI_EXP_TYPE_UPSTREAM: + if (!dev->ptm_responder) + return -EINVAL; + break; + case PCI_EXP_TYPE_ENDPOINT: + case PCI_EXP_TYPE_LEG_END: + if (!dev->ptm_requester) + return -EINVAL; + break; + default: + return -EINVAL; + } + pci_read_config_dword(dev, ptm + PCI_PTM_CTRL, &ctrl); ctrl |= PCI_PTM_CTRL_ENABLE; @@ -252,3 +276,307 @@ bool pcie_ptm_enabled(struct pci_dev *dev) return dev->ptm_enabled; } EXPORT_SYMBOL(pcie_ptm_enabled); + +#if IS_ENABLED(CONFIG_DEBUG_FS) +static ssize_t context_update_write(struct file *file, const char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct pci_ptm_debugfs *ptm_debugfs = file->private_data; + char buf[7]; + int ret; + u8 mode; + + if (!ptm_debugfs->ops->context_update_write) + return -EOPNOTSUPP; + + if (count < 1 || count >= sizeof(buf)) + return -EINVAL; + + ret = copy_from_user(buf, ubuf, count); + if (ret) + return -EFAULT; + + buf[count] = '\0'; + + if (sysfs_streq(buf, "auto")) + mode = PCIE_PTM_CONTEXT_UPDATE_AUTO; + else if (sysfs_streq(buf, "manual")) + mode = PCIE_PTM_CONTEXT_UPDATE_MANUAL; + else + return -EINVAL; + + mutex_lock(&ptm_debugfs->lock); + ret = ptm_debugfs->ops->context_update_write(ptm_debugfs->pdata, mode); + mutex_unlock(&ptm_debugfs->lock); + if (ret) + return ret; + + return count; +} + +static ssize_t context_update_read(struct file *file, char __user *ubuf, + size_t count, loff_t *ppos) +{ + struct pci_ptm_debugfs *ptm_debugfs = file->private_data; + char buf[8]; /* Extra space for NULL termination at the end */ + ssize_t pos; + u8 mode; + + if (!ptm_debugfs->ops->context_update_read) + return -EOPNOTSUPP; + + mutex_lock(&ptm_debugfs->lock); + ptm_debugfs->ops->context_update_read(ptm_debugfs->pdata, &mode); + mutex_unlock(&ptm_debugfs->lock); + + if (mode == PCIE_PTM_CONTEXT_UPDATE_AUTO) + pos = scnprintf(buf, sizeof(buf), "auto\n"); + else + pos = scnprintf(buf, sizeof(buf), "manual\n"); + + return simple_read_from_buffer(ubuf, count, ppos, buf, pos); +} + +static const struct file_operations context_update_fops = { + .open = simple_open, + .read = context_update_read, + .write = context_update_write, +}; + +static int context_valid_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + bool valid; + int ret; + + if (!ptm_debugfs->ops->context_valid_read) + return -EOPNOTSUPP; + + mutex_lock(&ptm_debugfs->lock); + ret = ptm_debugfs->ops->context_valid_read(ptm_debugfs->pdata, &valid); + mutex_unlock(&ptm_debugfs->lock); + if (ret) + return ret; + + *val = valid; + + return 0; +} + +static int context_valid_set(void *data, u64 val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + int ret; + + if (!ptm_debugfs->ops->context_valid_write) + return -EOPNOTSUPP; + + mutex_lock(&ptm_debugfs->lock); + ret = ptm_debugfs->ops->context_valid_write(ptm_debugfs->pdata, !!val); + mutex_unlock(&ptm_debugfs->lock); + + return ret; +} + +DEFINE_DEBUGFS_ATTRIBUTE(context_valid_fops, context_valid_get, + context_valid_set, "%llu\n"); + +static int local_clock_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->local_clock_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->local_clock_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(local_clock_fops, local_clock_get, NULL, "%llu\n"); + +static int master_clock_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->master_clock_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->master_clock_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(master_clock_fops, master_clock_get, NULL, "%llu\n"); + +static int t1_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->t1_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->t1_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(t1_fops, t1_get, NULL, "%llu\n"); + +static int t2_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->t2_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->t2_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(t2_fops, t2_get, NULL, "%llu\n"); + +static int t3_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->t3_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->t3_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(t3_fops, t3_get, NULL, "%llu\n"); + +static int t4_get(void *data, u64 *val) +{ + struct pci_ptm_debugfs *ptm_debugfs = data; + u64 clock; + int ret; + + if (!ptm_debugfs->ops->t4_read) + return -EOPNOTSUPP; + + ret = ptm_debugfs->ops->t4_read(ptm_debugfs->pdata, &clock); + if (ret) + return ret; + + *val = clock; + + return 0; +} + +DEFINE_DEBUGFS_ATTRIBUTE(t4_fops, t4_get, NULL, "%llu\n"); + +#define pcie_ptm_create_debugfs_file(pdata, mode, attr) \ + do { \ + if (ops->attr##_visible && ops->attr##_visible(pdata)) \ + debugfs_create_file(#attr, mode, ptm_debugfs->debugfs, \ + ptm_debugfs, &attr##_fops); \ + } while (0) + +/* + * pcie_ptm_create_debugfs() - Create debugfs entries for the PTM context + * @dev: PTM capable component device + * @pdata: Private data of the PTM capable component device + * @ops: PTM callback structure + * + * Create debugfs entries for exposing the PTM context of the PTM capable + * components such as Root Complex and Endpoint controllers. + * + * Return: Pointer to 'struct pci_ptm_debugfs' if success, NULL otherwise. + */ +struct pci_ptm_debugfs *pcie_ptm_create_debugfs(struct device *dev, void *pdata, + const struct pcie_ptm_ops *ops) +{ + struct pci_ptm_debugfs *ptm_debugfs; + char *dirname; + int ret; + + /* Caller must provide check_capability() callback */ + if (!ops->check_capability) + return NULL; + + /* Check for PTM capability before creating debugfs attributes */ + ret = ops->check_capability(pdata); + if (!ret) { + dev_dbg(dev, "PTM capability not present\n"); + return NULL; + } + + ptm_debugfs = kzalloc_obj(*ptm_debugfs); + if (!ptm_debugfs) + return NULL; + + dirname = devm_kasprintf(dev, GFP_KERNEL, "pcie_ptm_%s", dev_name(dev)); + if (!dirname) { + kfree(ptm_debugfs); + return NULL; + } + + ptm_debugfs->debugfs = debugfs_create_dir(dirname, NULL); + ptm_debugfs->pdata = pdata; + ptm_debugfs->ops = ops; + mutex_init(&ptm_debugfs->lock); + + pcie_ptm_create_debugfs_file(pdata, 0644, context_update); + pcie_ptm_create_debugfs_file(pdata, 0644, context_valid); + pcie_ptm_create_debugfs_file(pdata, 0444, local_clock); + pcie_ptm_create_debugfs_file(pdata, 0444, master_clock); + pcie_ptm_create_debugfs_file(pdata, 0444, t1); + pcie_ptm_create_debugfs_file(pdata, 0444, t2); + pcie_ptm_create_debugfs_file(pdata, 0444, t3); + pcie_ptm_create_debugfs_file(pdata, 0444, t4); + + return ptm_debugfs; +} +EXPORT_SYMBOL_GPL(pcie_ptm_create_debugfs); + +/* + * pcie_ptm_destroy_debugfs() - Destroy debugfs entries for the PTM context + * @ptm_debugfs: Pointer to the PTM debugfs struct + */ +void pcie_ptm_destroy_debugfs(struct pci_ptm_debugfs *ptm_debugfs) +{ + if (!ptm_debugfs) + return; + + mutex_destroy(&ptm_debugfs->lock); + debugfs_remove_recursive(ptm_debugfs->debugfs); + kfree(ptm_debugfs); +} +EXPORT_SYMBOL_GPL(pcie_ptm_destroy_debugfs); +#endif diff --git a/drivers/pci/pcie/rcec.c b/drivers/pci/pcie/rcec.c index d0bcd141ac9c..2bf6d9d549ba 100644 --- a/drivers/pci/pcie/rcec.c +++ b/drivers/pci/pcie/rcec.c @@ -160,7 +160,7 @@ void pci_rcec_init(struct pci_dev *dev) if (!rcec) return; - rcec_ea = kzalloc(sizeof(*rcec_ea), GFP_KERNEL); + rcec_ea = kzalloc_obj(*rcec_ea); if (!rcec_ea) return; diff --git a/drivers/pci/pcie/tlp.c b/drivers/pci/pcie/tlp.c index 890d5391d7f5..71f8fc9ea2ed 100644 --- a/drivers/pci/pcie/tlp.c +++ b/drivers/pci/pcie/tlp.c @@ -98,12 +98,14 @@ int pcie_read_tlp_log(struct pci_dev *dev, int where, int where2, * pcie_print_tlp_log - Print TLP Header / Prefix Log contents * @dev: PCIe device * @log: TLP Log structure + * @level: Printk log level * @pfx: String prefix * * Prints TLP Header and Prefix Log information held by @log. */ void pcie_print_tlp_log(const struct pci_dev *dev, - const struct pcie_tlp_log *log, const char *pfx) + const struct pcie_tlp_log *log, const char *level, + const char *pfx) { /* EE_PREFIX_STR fits the extended DW space needed for the Flit mode */ char buf[11 * PCIE_STD_MAX_TLP_HEADERLOG + 1]; @@ -130,6 +132,6 @@ void pcie_print_tlp_log(const struct pci_dev *dev, } } - pci_err(dev, "%sTLP Header%s: %s\n", pfx, + dev_printk(level, &dev->dev, "%sTLP Header%s: %s\n", pfx, log->flit ? " (Flit)" : "", buf); } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 364fa2a514f8..bccc7a4bdd79 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -3,6 +3,7 @@ * PCI detection and setup code */ +#include <linux/array_size.h> #include <linux/kernel.h> #include <linux/delay.h> #include <linux/init.h> @@ -13,6 +14,7 @@ #include <linux/platform_device.h> #include <linux/pci_hotplug.h> #include <linux/slab.h> +#include <linux/sprintf.h> #include <linux/module.h> #include <linux/cpumask.h> #include <linux/aer.h> @@ -21,11 +23,9 @@ #include <linux/irqdomain.h> #include <linux/pm_runtime.h> #include <linux/bitfield.h> +#include <trace/events/pci.h> #include "pci.h" -#define CARDBUS_LATENCY_TIMER 176 /* secondary latency timer */ -#define CARDBUS_RESERVE_BUSNR 3 - static struct resource busn_resource = { .name = "PCI busn", .start = 0, @@ -53,7 +53,7 @@ static struct resource *get_pci_domain_busn_res(int domain_nr) if (r->domain_nr == domain_nr) return &r->res; - r = kzalloc(sizeof(*r), GFP_KERNEL); + r = kzalloc_obj(*r); if (!r) return NULL; @@ -286,8 +286,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, if ((sizeof(pci_bus_addr_t) < 8 || sizeof(resource_size_t) < 8) && sz64 > 0x100000000ULL) { res->flags |= IORESOURCE_UNSET | IORESOURCE_DISABLED; - res->start = 0; - res->end = 0; + resource_set_range(res, 0, 0); pci_err(dev, "%s: can't handle BAR larger than 4GB (size %#010llx)\n", res_name, (unsigned long long)sz64); goto out; @@ -296,8 +295,7 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type, if ((sizeof(pci_bus_addr_t) < 8) && l) { /* Above 32-bit boundary; try to reallocate */ res->flags |= IORESOURCE_UNSET; - res->start = 0; - res->end = sz64 - 1; + resource_set_range(res, 0, sz64); pci_info(dev, "%s: can't handle BAR above 4GB (bus address %#010llx)\n", res_name, (unsigned long long)l64); goto out; @@ -419,13 +417,17 @@ static void pci_read_bridge_io(struct pci_dev *dev, struct resource *res, limit |= ((unsigned long) io_limit_hi << 16); } + res->flags = (io_base_lo & PCI_IO_RANGE_TYPE_MASK) | IORESOURCE_IO; + if (base <= limit) { - res->flags = (io_base_lo & PCI_IO_RANGE_TYPE_MASK) | IORESOURCE_IO; region.start = base; region.end = limit + io_granularity - 1; pcibios_bus_to_resource(dev->bus, res, ®ion); if (log) pci_info(dev, " bridge window %pR\n", res); + } else { + resource_set_range(res, 0, 0); + res->flags |= IORESOURCE_UNSET | IORESOURCE_DISABLED; } } @@ -440,13 +442,18 @@ static void pci_read_bridge_mmio(struct pci_dev *dev, struct resource *res, pci_read_config_word(dev, PCI_MEMORY_LIMIT, &mem_limit_lo); base = ((unsigned long) mem_base_lo & PCI_MEMORY_RANGE_MASK) << 16; limit = ((unsigned long) mem_limit_lo & PCI_MEMORY_RANGE_MASK) << 16; + + res->flags = (mem_base_lo & PCI_MEMORY_RANGE_TYPE_MASK) | IORESOURCE_MEM; + if (base <= limit) { - res->flags = (mem_base_lo & PCI_MEMORY_RANGE_TYPE_MASK) | IORESOURCE_MEM; region.start = base; region.end = limit + 0xfffff; pcibios_bus_to_resource(dev->bus, res, ®ion); if (log) pci_info(dev, " bridge window %pR\n", res); + } else { + resource_set_range(res, 0, 0); + res->flags |= IORESOURCE_UNSET | IORESOURCE_DISABLED; } } @@ -489,16 +496,20 @@ static void pci_read_bridge_mmio_pref(struct pci_dev *dev, struct resource *res, return; } + res->flags = (mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) | IORESOURCE_MEM | + IORESOURCE_PREFETCH; + if (res->flags & PCI_PREF_RANGE_TYPE_64) + res->flags |= IORESOURCE_MEM_64; + if (base <= limit) { - res->flags = (mem_base_lo & PCI_PREF_RANGE_TYPE_MASK) | - IORESOURCE_MEM | IORESOURCE_PREFETCH; - if (res->flags & PCI_PREF_RANGE_TYPE_64) - res->flags |= IORESOURCE_MEM_64; region.start = base; region.end = limit + 0xfffff; pcibios_bus_to_resource(dev->bus, res, ®ion); if (log) pci_info(dev, " bridge window %pR\n", res); + } else { + resource_set_range(res, 0, 0); + res->flags |= IORESOURCE_UNSET | IORESOURCE_DISABLED; } } @@ -511,8 +522,8 @@ static void pci_read_bridge_windows(struct pci_dev *bridge) pci_read_config_dword(bridge, PCI_PRIMARY_BUS, &buses); res.flags = IORESOURCE_BUS; - res.start = (buses >> 8) & 0xff; - res.end = (buses >> 16) & 0xff; + res.start = FIELD_GET(PCI_SECONDARY_BUS_MASK, buses); + res.end = FIELD_GET(PCI_SUBORDINATE_BUS_MASK, buses); pci_info(bridge, "PCI bridge to %pR%s\n", &res, bridge->transparent ? " (subtractive decode)" : ""); @@ -585,9 +596,13 @@ void pci_read_bridge_bases(struct pci_bus *child) for (i = 0; i < PCI_BRIDGE_RESOURCE_NUM; i++) child->resource[i] = &dev->resource[PCI_BRIDGE_RESOURCES+i]; - pci_read_bridge_io(child->self, child->resource[0], false); - pci_read_bridge_mmio(child->self, child->resource[1], false); - pci_read_bridge_mmio_pref(child->self, child->resource[2], false); + pci_read_bridge_io(child->self, + child->resource[PCI_BUS_BRIDGE_IO_WINDOW], false); + pci_read_bridge_mmio(child->self, + child->resource[PCI_BUS_BRIDGE_MEM_WINDOW], false); + pci_read_bridge_mmio_pref(child->self, + child->resource[PCI_BUS_BRIDGE_PREF_MEM_WINDOW], + false); if (!dev->transparent) return; @@ -605,7 +620,7 @@ static struct pci_bus *pci_alloc_bus(struct pci_bus *parent) { struct pci_bus *b; - b = kzalloc(sizeof(*b), GFP_KERNEL); + b = kzalloc_obj(*b); if (!b) return NULL; @@ -632,9 +647,26 @@ static void pci_release_host_bridge_dev(struct device *dev) pci_free_resource_list(&bridge->windows); pci_free_resource_list(&bridge->dma_ranges); + + /* Host bridges only have domain_nr set in the emulation case */ + if (bridge->domain_nr != PCI_DOMAIN_NR_NOT_SET) + pci_bus_release_emul_domain_nr(bridge->domain_nr); + kfree(bridge); } +static const struct attribute_group *pci_host_bridge_groups[] = { +#ifdef CONFIG_PCI_IDE + &pci_ide_attr_group, +#endif + NULL +}; + +static const struct device_type pci_host_bridge_type = { + .groups = pci_host_bridge_groups, + .release = pci_release_host_bridge_dev, +}; + static void pci_init_host_bridge(struct pci_host_bridge *bridge) { INIT_LIST_HEAD(&bridge->windows); @@ -654,6 +686,8 @@ static void pci_init_host_bridge(struct pci_host_bridge *bridge) bridge->native_dpc = 1; bridge->domain_nr = PCI_DOMAIN_NR_NOT_SET; bridge->native_cxl_error = 1; + bridge->dev.type = &pci_host_bridge_type; + pci_ide_init_host_bridge(bridge); device_initialize(&bridge->dev); } @@ -667,7 +701,6 @@ struct pci_host_bridge *pci_alloc_host_bridge(size_t priv) return NULL; pci_init_host_bridge(bridge); - bridge->dev.release = pci_release_host_bridge_dev; return bridge; } @@ -788,14 +821,16 @@ const char *pci_speed_string(enum pci_bus_speed speed) } EXPORT_SYMBOL_GPL(pci_speed_string); -void pcie_update_link_speed(struct pci_bus *bus) +void pcie_update_link_speed(struct pci_bus *bus, + enum pcie_link_change_reason reason) { struct pci_dev *bridge = bus->self; u16 linksta, linksta2; pcie_capability_read_word(bridge, PCI_EXP_LNKSTA, &linksta); pcie_capability_read_word(bridge, PCI_EXP_LNKSTA2, &linksta2); - __pcie_update_link_speed(bus, linksta, linksta2); + + __pcie_update_link_speed(bus, reason, linksta, linksta2); } EXPORT_SYMBOL_GPL(pcie_update_link_speed); @@ -882,7 +917,7 @@ static void pci_set_bus_speed(struct pci_bus *bus) pcie_capability_read_dword(bridge, PCI_EXP_LNKCAP, &linkcap); bus->max_bus_speed = pcie_link_speed[linkcap & PCI_EXP_LNKCAP_SLS]; - pcie_update_link_speed(bus); + pcie_update_link_speed(bus, PCIE_ADD_BUS); } } @@ -1112,7 +1147,8 @@ unregister: device_del(&bridge->dev); free: #ifdef CONFIG_PCI_DOMAINS_GENERIC - pci_bus_release_domain_nr(parent, bus->domain_nr); + if (bridge->domain_nr == PCI_DOMAIN_NR_NOT_SET) + pci_bus_release_domain_nr(parent, bus->domain_nr); #endif if (bus_registered) put_device(&bus->dev); @@ -1276,6 +1312,26 @@ static void pci_enable_rrs_sv(struct pci_dev *pdev) static unsigned int pci_scan_child_bus_extend(struct pci_bus *bus, unsigned int available_buses); + +void pbus_validate_busn(struct pci_bus *bus) +{ + struct pci_bus *upstream = bus->parent; + struct pci_dev *bridge = bus->self; + + /* Check that all devices are accessible */ + while (upstream->parent) { + if ((bus->busn_res.end > upstream->busn_res.end) || + (bus->number > upstream->busn_res.end) || + (bus->number < upstream->number) || + (bus->busn_res.end < upstream->number)) { + pci_info(bridge, "devices behind bridge are unusable because %pR cannot be assigned for them\n", + &bus->busn_res); + break; + } + upstream = upstream->parent; + } +} + /** * pci_ea_fixed_busnrs() - Read fixed Secondary and Subordinate bus * numbers from EA capability. @@ -1287,7 +1343,7 @@ static unsigned int pci_scan_child_bus_extend(struct pci_bus *bus, * and subordinate bus numbers, return true with the bus numbers in @sec * and @sub. Otherwise return false. */ -static bool pci_ea_fixed_busnrs(struct pci_dev *dev, u8 *sec, u8 *sub) +bool pci_ea_fixed_busnrs(struct pci_dev *dev, u8 *sec, u8 *sub) { int ea, offset; u32 dw; @@ -1341,8 +1397,7 @@ static int pci_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev, int pass) { struct pci_bus *child; - int is_cardbus = (dev->hdr_type == PCI_HEADER_TYPE_CARDBUS); - u32 buses, i, j = 0; + u32 buses; u16 bctl; u8 primary, secondary, subordinate; int broken = 0; @@ -1357,9 +1412,9 @@ static int pci_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev, pm_runtime_get_sync(&dev->dev); pci_read_config_dword(dev, PCI_PRIMARY_BUS, &buses); - primary = buses & 0xFF; - secondary = (buses >> 8) & 0xFF; - subordinate = (buses >> 16) & 0xFF; + primary = FIELD_GET(PCI_PRIMARY_BUS_MASK, buses); + secondary = FIELD_GET(PCI_SECONDARY_BUS_MASK, buses); + subordinate = FIELD_GET(PCI_SUBORDINATE_BUS_MASK, buses); pci_dbg(dev, "scanning [bus %02x-%02x] behind bridge, pass %d\n", secondary, subordinate, pass); @@ -1386,8 +1441,15 @@ static int pci_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev, pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bctl & ~PCI_BRIDGE_CTL_MASTER_ABORT); - if ((secondary || subordinate) && !pcibios_assign_all_busses() && - !is_cardbus && !broken) { + if (pci_is_cardbus_bridge(dev)) { + max = pci_cardbus_scan_bridge_extend(bus, dev, buses, max, + available_buses, + pass); + goto out; + } + + if ((secondary || subordinate) && + !pcibios_assign_all_busses() && !broken) { unsigned int cmax, buses; /* @@ -1429,7 +1491,7 @@ static int pci_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev, * do in the second pass. */ if (!pass) { - if (pcibios_assign_all_busses() || broken || is_cardbus) + if (pcibios_assign_all_busses() || broken) /* * Temporarily disable forwarding of the @@ -1440,7 +1502,7 @@ static int pci_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev, * ranges. */ pci_write_config_dword(dev, PCI_PRIMARY_BUS, - buses & ~0xffffff); + buses & PCI_SEC_LATENCY_TIMER_MASK); goto out; } @@ -1471,59 +1533,16 @@ static int pci_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev, if (available_buses) available_buses--; - buses = (buses & 0xff000000) - | ((unsigned int)(child->primary) << 0) - | ((unsigned int)(child->busn_res.start) << 8) - | ((unsigned int)(child->busn_res.end) << 16); - - /* - * yenta.c forces a secondary latency timer of 176. - * Copy that behaviour here. - */ - if (is_cardbus) { - buses &= ~0xff000000; - buses |= CARDBUS_LATENCY_TIMER << 24; - } + buses = (buses & PCI_SEC_LATENCY_TIMER_MASK) | + FIELD_PREP(PCI_PRIMARY_BUS_MASK, child->primary) | + FIELD_PREP(PCI_SECONDARY_BUS_MASK, child->busn_res.start) | + FIELD_PREP(PCI_SUBORDINATE_BUS_MASK, child->busn_res.end); /* We need to blast all three values with a single write */ pci_write_config_dword(dev, PCI_PRIMARY_BUS, buses); - if (!is_cardbus) { - child->bridge_ctl = bctl; - max = pci_scan_child_bus_extend(child, available_buses); - } else { - - /* - * For CardBus bridges, we leave 4 bus numbers as - * cards with a PCI-to-PCI bridge can be inserted - * later. - */ - for (i = 0; i < CARDBUS_RESERVE_BUSNR; i++) { - struct pci_bus *parent = bus; - if (pci_find_bus(pci_domain_nr(bus), - max+i+1)) - break; - while (parent->parent) { - if ((!pcibios_assign_all_busses()) && - (parent->busn_res.end > max) && - (parent->busn_res.end <= max+i)) { - j = 1; - } - parent = parent->parent; - } - if (j) { - - /* - * Often, there are two CardBus - * bridges -- try to leave one - * valid bus number for each one. - */ - i /= 2; - break; - } - } - max += i; - } + child->bridge_ctl = bctl; + max = pci_scan_child_bus_extend(child, available_buses); /* * Set subordinate bus number to its real value. @@ -1535,23 +1554,10 @@ static int pci_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev, pci_bus_update_busn_res_end(child, max); pci_write_config_byte(dev, PCI_SUBORDINATE_BUS, max); } + scnprintf(child->name, sizeof(child->name), "PCI Bus %04x:%02x", + pci_domain_nr(bus), child->number); - sprintf(child->name, - (is_cardbus ? "PCI CardBus %04x:%02x" : "PCI Bus %04x:%02x"), - pci_domain_nr(bus), child->number); - - /* Check that all devices are accessible */ - while (bus->parent) { - if ((child->busn_res.end > bus->busn_res.end) || - (child->number > bus->busn_res.end) || - (child->number < bus->number) || - (child->busn_res.end < bus->number)) { - dev_info(&dev->dev, "devices behind bridge are unusable because %pR cannot be assigned for them\n", - &child->busn_res); - break; - } - bus = bus->parent; - } + pbus_validate_busn(child); out: /* Clear errors in the Secondary Status Register */ @@ -1638,6 +1644,13 @@ void set_pcie_port_type(struct pci_dev *pdev) if (reg32 & PCI_EXP_LNKCAP_DLLLARC) pdev->link_active_reporting = 1; +#ifdef CONFIG_PCIEASPM + if (reg32 & PCI_EXP_LNKCAP_ASPM_L0S) + pdev->aspm_l0s_support = 1; + if (reg32 & PCI_EXP_LNKCAP_ASPM_L1) + pdev->aspm_l1_support = 1; +#endif + parent = pci_upstream_bridge(pdev); if (!parent) return; @@ -1678,7 +1691,7 @@ void set_pcie_hotplug_bridge(struct pci_dev *pdev) pcie_capability_read_dword(pdev, PCI_EXP_SLTCAP, ®32); if (reg32 & PCI_EXP_SLTCAP_HPC) - pdev->is_hotplug_bridge = 1; + pdev->is_hotplug_bridge = pdev->is_pciehp = 1; } static void set_pcie_thunderbolt(struct pci_dev *dev) @@ -1691,6 +1704,35 @@ static void set_pcie_thunderbolt(struct pci_dev *dev) dev->is_thunderbolt = 1; } +static void set_pcie_cxl(struct pci_dev *dev) +{ + struct pci_dev *bridge; + u16 dvsec, cap; + + if (!pci_is_pcie(dev)) + return; + + /* + * Update parent's CXL state because alternate protocol training + * may have changed + */ + bridge = pci_upstream_bridge(dev); + if (bridge) + set_pcie_cxl(bridge); + + dvsec = pci_find_dvsec_capability(dev, PCI_VENDOR_ID_CXL, + PCI_DVSEC_CXL_FLEXBUS_PORT); + if (!dvsec) + return; + + pci_read_config_word(dev, dvsec + PCI_DVSEC_CXL_FLEXBUS_PORT_STATUS, + &cap); + + dev->is_cxl = FIELD_GET(PCI_DVSEC_CXL_FLEXBUS_PORT_STATUS_CACHE, cap) || + FIELD_GET(PCI_DVSEC_CXL_FLEXBUS_PORT_STATUS_MEM, cap); + +} + static void set_pcie_untrusted(struct pci_dev *dev) { struct pci_dev *parent = pci_upstream_bridge(dev); @@ -1912,16 +1954,16 @@ static int pci_intx_mask_broken(struct pci_dev *dev) static void early_dump_pci_device(struct pci_dev *pdev) { - u32 value[256 / 4]; + u32 value[PCI_CFG_SPACE_SIZE / sizeof(u32)]; int i; pci_info(pdev, "config space:\n"); - for (i = 0; i < 256; i += 4) - pci_read_config_dword(pdev, i, &value[i / 4]); + for (i = 0; i < ARRAY_SIZE(value); i++) + pci_read_config_dword(pdev, i * sizeof(u32), &value[i]); print_hex_dump(KERN_INFO, "", DUMP_PREFIX_OFFSET, 16, 1, - value, 256, false); + value, ARRAY_SIZE(value) * sizeof(u32), false); } static const char *pci_type_str(struct pci_dev *dev) @@ -1985,8 +2027,8 @@ int pci_setup_device(struct pci_dev *dev) dev->sysdata = dev->bus->sysdata; dev->dev.parent = dev->bus->bridge; dev->dev.bus = &pci_bus_type; - dev->hdr_type = hdr_type & 0x7f; - dev->multifunction = !!(hdr_type & 0x80); + dev->hdr_type = FIELD_GET(PCI_HEADER_TYPE_MASK, hdr_type); + dev->multifunction = FIELD_GET(PCI_HEADER_TYPE_MFD, hdr_type); dev->error_state = pci_channel_io_normal; set_pcie_port_type(dev); @@ -2003,6 +2045,13 @@ int pci_setup_device(struct pci_dev *dev) */ dev->dma_mask = 0xffffffff; + /* + * Assume 64-bit addresses for MSI initially. Will be changed to 32-bit + * if MSI (rather than MSI-X) capability does not have + * PCI_MSI_FLAGS_64BIT. Can also be overridden by driver. + */ + dev->msi_addr_mask = DMA_BIT_MASK(64); + dev_set_name(&dev->dev, "%04x:%02x:%02x.%d", pci_domain_nr(dev->bus), dev->bus->number, PCI_SLOT(dev->devfn), PCI_FUNC(dev->devfn)); @@ -2021,6 +2070,8 @@ int pci_setup_device(struct pci_dev *dev) /* Need to have dev->cfg_size ready */ set_pcie_thunderbolt(dev); + set_pcie_cxl(dev); + set_pcie_untrusted(dev); if (pci_is_pcie(dev)) @@ -2058,7 +2109,7 @@ int pci_setup_device(struct pci_dev *dev) if (class == PCI_CLASS_BRIDGE_PCI) goto bad; pci_read_irq(dev); - pci_read_bases(dev, 6, PCI_ROM_ADDRESS); + pci_read_bases(dev, PCI_STD_NUM_BARS, PCI_ROM_ADDRESS); pci_subsystem_ids(dev, &dev->subsystem_vendor, &dev->subsystem_device); @@ -2226,7 +2277,8 @@ int pci_configure_extended_tags(struct pci_dev *dev, void *ign) u16 ctl; int ret; - if (!pci_is_pcie(dev)) + /* PCI_EXP_DEVCTL_EXT_TAG is RsvdP in VFs */ + if (!pci_is_pcie(dev) || dev->is_virtfn) return 0; ret = pcie_capability_read_dword(dev, PCI_EXP_DEVCAP, &cap); @@ -2265,6 +2317,17 @@ int pci_configure_extended_tags(struct pci_dev *dev, void *ign) return 0; } +static void pci_dev3_init(struct pci_dev *pdev) +{ + u16 cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_DEV3); + u32 val = 0; + + if (!cap) + return; + pci_read_config_dword(pdev, cap + PCI_DEV3_STA, &val); + pdev->fm_enabled = !!(val & PCI_DEV3_STA_SEGMENT); +} + /** * pcie_relaxed_ordering_enabled - Probe for PCIe relaxed ordering enable * @dev: PCI device to query @@ -2355,6 +2418,37 @@ static void pci_configure_serr(struct pci_dev *dev) } } +static void pci_configure_rcb(struct pci_dev *dev) +{ + struct pci_dev *rp; + u16 rp_lnkctl; + + /* + * Per PCIe r7.0, sec 7.5.3.7, RCB is only meaningful in Root Ports + * (where it is read-only), Endpoints, and Bridges. It may only be + * set for Endpoints and Bridges if it is set in the Root Port. For + * Endpoints, it is 'RsvdP' for Virtual Functions. + */ + if (!pci_is_pcie(dev) || + pci_pcie_type(dev) == PCI_EXP_TYPE_ROOT_PORT || + pci_pcie_type(dev) == PCI_EXP_TYPE_UPSTREAM || + pci_pcie_type(dev) == PCI_EXP_TYPE_DOWNSTREAM || + pci_pcie_type(dev) == PCI_EXP_TYPE_RC_EC || + dev->is_virtfn) + return; + + /* Root Port often not visible to virtualized guests */ + rp = pcie_find_root_port(dev); + if (!rp) + return; + + pcie_capability_read_word(rp, PCI_EXP_LNKCTL, &rp_lnkctl); + pcie_capability_clear_and_set_word(dev, PCI_EXP_LNKCTL, + PCI_EXP_LNKCTL_RCB, + (rp_lnkctl & PCI_EXP_LNKCTL_RCB) ? + PCI_EXP_LNKCTL_RCB : 0); +} + static void pci_configure_device(struct pci_dev *dev) { pci_configure_mps(dev); @@ -2364,6 +2458,7 @@ static void pci_configure_device(struct pci_dev *dev) pci_configure_aspm_l1ss(dev); pci_configure_eetlp_prefix(dev); pci_configure_serr(dev); + pci_configure_rcb(dev); pci_acpi_program_hp_params(dev); } @@ -2407,7 +2502,7 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus) { struct pci_dev *dev; - dev = kzalloc(sizeof(struct pci_dev), GFP_KERNEL); + dev = kzalloc_obj(struct pci_dev); if (!dev) return NULL; @@ -2492,52 +2587,10 @@ bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l, bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l, int timeout) { -#ifdef CONFIG_PCI_QUIRKS - struct pci_dev *bridge = bus->self; - - /* - * Certain IDT switches have an issue where they improperly trigger - * ACS Source Validation errors on completions for config reads. - */ - if (bridge && bridge->vendor == PCI_VENDOR_ID_IDT && - bridge->device == 0x80b5) - return pci_idt_bus_quirk(bus, devfn, l, timeout); -#endif - return pci_bus_generic_read_dev_vendor_id(bus, devfn, l, timeout); } EXPORT_SYMBOL(pci_bus_read_dev_vendor_id); -static struct platform_device *pci_pwrctrl_create_device(struct pci_bus *bus, int devfn) -{ - struct pci_host_bridge *host = pci_find_host_bridge(bus); - struct platform_device *pdev; - struct device_node *np; - - np = of_pci_find_child_device(dev_of_node(&bus->dev), devfn); - if (!np || of_find_device_by_node(np)) - return NULL; - - /* - * First check whether the pwrctrl device really needs to be created or - * not. This is decided based on at least one of the power supplies - * being defined in the devicetree node of the device. - */ - if (!of_pci_supply_present(np)) { - pr_debug("PCI/pwrctrl: Skipping OF node: %s\n", np->name); - return NULL; - } - - /* Now create the pwrctrl device */ - pdev = of_platform_device_create(np, NULL, &host->dev); - if (!pdev) { - pr_err("PCI/pwrctrl: Failed to create pwrctrl device for node: %s\n", np->name); - return NULL; - } - - return pdev; -} - /* * Read the config data for a PCI device, sanity-check it, * and fill in the dev structure. @@ -2547,15 +2600,6 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn) struct pci_dev *dev; u32 l; - /* - * Create pwrctrl device (if required) for the PCI device to handle the - * power state. If the pwrctrl device is created, then skip scanning - * further as the pwrctrl core will rescan the bus after powering on - * the device. - */ - if (pci_pwrctrl_create_device(bus, devfn)) - return NULL; - if (!pci_bus_read_dev_vendor_id(bus, devfn, &l, 60*1000)) return NULL; @@ -2595,6 +2639,15 @@ void pcie_report_downtraining(struct pci_dev *dev) __pcie_print_link_status(dev, false); } +static void pci_imm_ready_init(struct pci_dev *dev) +{ + u16 status; + + pci_read_config_word(dev, PCI_STATUS, &status); + if (status & PCI_STATUS_IMM_READY) + dev->imm_ready = 1; +} + static void pci_init_capabilities(struct pci_dev *dev) { pci_ea_init(dev); /* Enhanced Allocation */ @@ -2604,6 +2657,7 @@ static void pci_init_capabilities(struct pci_dev *dev) /* Buffers for saving PCIe and PCI-X capabilities */ pci_allocate_cap_save_buffers(dev); + pci_imm_ready_init(dev); /* Immediate Readiness */ pci_pm_init(dev); /* Power Management */ pci_vpd_init(dev); /* Vital Product Data */ pci_configure_ari(dev); /* Alternative Routing-ID Forwarding */ @@ -2619,6 +2673,8 @@ static void pci_init_capabilities(struct pci_dev *dev) pci_doe_init(dev); /* Data Object Exchange */ pci_tph_init(dev); /* TLP Processing Hints */ pci_rebar_init(dev); /* Resizable BAR */ + pci_dev3_init(dev); /* Device 3 capabilities */ + pci_ide_init(dev); /* Link Integrity and Data Encryption */ pcie_report_downtraining(dev); pci_init_reset_methods(dev); @@ -2692,8 +2748,6 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) pci_reassigndev_resource_alignment(dev); - dev->state_saved = false; - pci_init_capabilities(dev); /* @@ -2711,10 +2765,12 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus) pci_set_msi_domain(dev); /* Notifier could use PCI capabilities */ - dev->match_driver = false; ret = device_add(&dev->dev); WARN_ON(ret < 0); + /* Establish pdev->tsm for newly added (e.g. new SR-IOV VFs) */ + pci_tsm_init(dev); + pci_npem_create(dev); pci_doe_sysfs_init(dev); @@ -3029,14 +3085,14 @@ static unsigned int pci_scan_child_bus_extend(struct pci_bus *bus, { unsigned int used_buses, normal_bridges = 0, hotplug_bridges = 0; unsigned int start = bus->busn_res.start; - unsigned int devfn, cmax, max = start; + unsigned int devnr, cmax, max = start; struct pci_dev *dev; dev_dbg(&bus->dev, "scanning bus\n"); /* Go find them, Rover! */ - for (devfn = 0; devfn < 256; devfn += 8) - pci_scan_slot(bus, devfn); + for (devnr = 0; devnr < PCI_MAX_NR_DEVS; devnr++) + pci_scan_slot(bus, PCI_DEVFN(devnr, 0)); /* Reserve buses for SR-IOV capability */ used_buses = pci_iov_bus_range(bus); @@ -3116,8 +3172,7 @@ static unsigned int pci_scan_child_bus_extend(struct pci_bus *bus, * bus number if there is room. */ if (bus->self && bus->self->is_hotplug_bridge) { - used_buses = max_t(unsigned int, available_buses, - pci_hotplug_bus_size - 1); + used_buses = max(available_buses, pci_hotplug_bus_size - 1); if (max - start < used_buses) { max = start + used_buses; @@ -3453,7 +3508,7 @@ EXPORT_SYMBOL_GPL(pci_rescan_bus); * pci_rescan_bus(), pci_rescan_bus_bridge_resize() and PCI device removal * routines should always be executed under this mutex. */ -static DEFINE_MUTEX(pci_rescan_remove_lock); +DEFINE_MUTEX(pci_rescan_remove_lock); void pci_lock_rescan_remove(void) { diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c index 9348a0fb8084..ce36e35681e8 100644 --- a/drivers/pci/proc.c +++ b/drivers/pci/proc.c @@ -297,7 +297,7 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma) static int proc_bus_pci_open(struct inode *inode, struct file *file) { - struct pci_filp_private *fpriv = kmalloc(sizeof(*fpriv), GFP_KERNEL); + struct pci_filp_private *fpriv = kmalloc_obj(*fpriv); if (!fpriv) return -ENOMEM; diff --git a/drivers/pci/pwrctrl/Kconfig b/drivers/pci/pwrctrl/Kconfig index 990cab67d413..cd3aa15bad00 100644 --- a/drivers/pci/pwrctrl/Kconfig +++ b/drivers/pci/pwrctrl/Kconfig @@ -1,19 +1,20 @@ # SPDX-License-Identifier: GPL-2.0-only -config HAVE_PWRCTL +config HAVE_PWRCTRL bool -config PCI_PWRCTL +config PCI_PWRCTRL tristate -config PCI_PWRCTL_PWRSEQ +config PCI_PWRCTRL_PWRSEQ tristate select POWER_SEQUENCING - select PCI_PWRCTL + select PCI_PWRCTRL -config PCI_PWRCTL_SLOT +config PCI_PWRCTRL_SLOT tristate "PCI Power Control driver for PCI slots" - select PCI_PWRCTL + select POWER_SEQUENCING + select PCI_PWRCTRL help Say Y here to enable the PCI Power Control driver to control the power state of PCI slots. @@ -21,3 +22,28 @@ config PCI_PWRCTL_SLOT This is a generic driver that controls the power state of different PCI slots. The voltage regulators powering the rails of the PCI slots are expected to be defined in the devicetree node of the PCI bridge. + +config PCI_PWRCTRL_TC9563 + tristate "PCI Power Control driver for TC9563 PCIe switch" + select PCI_PWRCTRL + default m if ARCH_QCOM + depends on I2C + help + Say Y here to enable the PCI Power Control driver of TC9563 PCIe + switch. + + This driver enables power and configures the TC9563 PCIe switch + through i2c. TC9563 is a PCIe switch which has one upstream and three + downstream ports. To one of the downstream ports integrated ethernet + MAC is connected as endpoint device. Other two downstream ports are + supposed to connect to external device. + +# deprecated +config HAVE_PWRCTL + bool + select HAVE_PWRCTRL + +# deprecated +config PCI_PWRCTL_PWRSEQ + tristate + select PCI_PWRCTRL_PWRSEQ diff --git a/drivers/pci/pwrctrl/Makefile b/drivers/pci/pwrctrl/Makefile index ddfb12c5aadf..13b02282106c 100644 --- a/drivers/pci/pwrctrl/Makefile +++ b/drivers/pci/pwrctrl/Makefile @@ -1,9 +1,11 @@ # SPDX-License-Identifier: GPL-2.0-only -obj-$(CONFIG_PCI_PWRCTL) += pci-pwrctrl-core.o +obj-$(CONFIG_PCI_PWRCTRL) += pci-pwrctrl-core.o pci-pwrctrl-core-y := core.o -obj-$(CONFIG_PCI_PWRCTL_PWRSEQ) += pci-pwrctrl-pwrseq.o +obj-$(CONFIG_PCI_PWRCTRL_PWRSEQ) += pci-pwrctrl-pwrseq.o -obj-$(CONFIG_PCI_PWRCTL_SLOT) += pci-pwrctl-slot.o -pci-pwrctl-slot-y := slot.o +obj-$(CONFIG_PCI_PWRCTRL_SLOT) += pci-pwrctrl-slot.o +pci-pwrctrl-slot-y := slot.o + +obj-$(CONFIG_PCI_PWRCTRL_TC9563) += pci-pwrctrl-tc9563.o diff --git a/drivers/pci/pwrctrl/core.c b/drivers/pci/pwrctrl/core.c index 9cc7e2b7f2b5..6f7dea6746e0 100644 --- a/drivers/pci/pwrctrl/core.c +++ b/drivers/pci/pwrctrl/core.c @@ -3,14 +3,22 @@ * Copyright (C) 2024 Linaro Ltd. */ +#define dev_fmt(fmt) "pwrctrl: " fmt + #include <linux/device.h> #include <linux/export.h> #include <linux/kernel.h> +#include <linux/of.h> +#include <linux/of_graph.h> +#include <linux/of_platform.h> #include <linux/pci.h> #include <linux/pci-pwrctrl.h> +#include <linux/platform_device.h> #include <linux/property.h> #include <linux/slab.h> +#include "../pci.h" + static int pci_pwrctrl_notify(struct notifier_block *nb, unsigned long action, void *data) { @@ -38,16 +46,6 @@ static int pci_pwrctrl_notify(struct notifier_block *nb, unsigned long action, return NOTIFY_DONE; } -static void rescan_work_func(struct work_struct *work) -{ - struct pci_pwrctrl *pwrctrl = container_of(work, - struct pci_pwrctrl, work); - - pci_lock_rescan_remove(); - pci_rescan_bus(to_pci_host_bridge(pwrctrl->dev->parent)->bus); - pci_unlock_rescan_remove(); -} - /** * pci_pwrctrl_init() - Initialize the PCI power control context struct * @@ -57,7 +55,7 @@ static void rescan_work_func(struct work_struct *work) void pci_pwrctrl_init(struct pci_pwrctrl *pwrctrl, struct device *dev) { pwrctrl->dev = dev; - INIT_WORK(&pwrctrl->work, rescan_work_func); + dev_set_drvdata(dev, pwrctrl); } EXPORT_SYMBOL_GPL(pci_pwrctrl_init); @@ -87,8 +85,6 @@ int pci_pwrctrl_device_set_ready(struct pci_pwrctrl *pwrctrl) if (ret) return ret; - schedule_work(&pwrctrl->work); - return 0; } EXPORT_SYMBOL_GPL(pci_pwrctrl_device_set_ready); @@ -143,6 +139,242 @@ int devm_pci_pwrctrl_device_set_ready(struct device *dev, } EXPORT_SYMBOL_GPL(devm_pci_pwrctrl_device_set_ready); +static int __pci_pwrctrl_power_off_device(struct device *dev) +{ + struct pci_pwrctrl *pwrctrl = dev_get_drvdata(dev); + + if (!pwrctrl) + return 0; + + return pwrctrl->power_off(pwrctrl); +} + +static void pci_pwrctrl_power_off_device(struct device_node *np) +{ + struct platform_device *pdev; + int ret; + + for_each_available_child_of_node_scoped(np, child) + pci_pwrctrl_power_off_device(child); + + pdev = of_find_device_by_node(np); + if (!pdev) + return; + + if (device_is_bound(&pdev->dev)) { + ret = __pci_pwrctrl_power_off_device(&pdev->dev); + if (ret) + dev_err(&pdev->dev, "Failed to power off device: %d", ret); + } + + platform_device_put(pdev); +} + +/** + * pci_pwrctrl_power_off_devices - Power off pwrctrl devices + * + * @parent: PCI host controller device + * + * Recursively traverse all pwrctrl devices for the devicetree hierarchy + * below the specified PCI host controller and power them off in a depth + * first manner. + */ +void pci_pwrctrl_power_off_devices(struct device *parent) +{ + struct device_node *np = parent->of_node; + + for_each_available_child_of_node_scoped(np, child) + pci_pwrctrl_power_off_device(child); +} +EXPORT_SYMBOL_GPL(pci_pwrctrl_power_off_devices); + +static int __pci_pwrctrl_power_on_device(struct device *dev) +{ + struct pci_pwrctrl *pwrctrl = dev_get_drvdata(dev); + + if (!pwrctrl) + return 0; + + return pwrctrl->power_on(pwrctrl); +} + +/* + * Power on the devices in a depth first manner. Before powering on the device, + * make sure its driver is bound. + */ +static int pci_pwrctrl_power_on_device(struct device_node *np) +{ + struct platform_device *pdev; + int ret; + + for_each_available_child_of_node_scoped(np, child) { + ret = pci_pwrctrl_power_on_device(child); + if (ret) + return ret; + } + + pdev = of_find_device_by_node(np); + if (!pdev) + return 0; + + if (device_is_bound(&pdev->dev)) { + ret = __pci_pwrctrl_power_on_device(&pdev->dev); + } else { + /* FIXME: Use blocking wait instead of probe deferral */ + dev_dbg(&pdev->dev, "driver is not bound\n"); + ret = -EPROBE_DEFER; + } + + platform_device_put(pdev); + + return ret; +} + +/** + * pci_pwrctrl_power_on_devices - Power on pwrctrl devices + * + * @parent: PCI host controller device + * + * Recursively traverse all pwrctrl devices for the devicetree hierarchy + * below the specified PCI host controller and power them on in a depth + * first manner. On error, all powered on devices will be powered off. + * + * Return: 0 on success, -EPROBE_DEFER if any pwrctrl driver is not bound, an + * appropriate error code otherwise. + */ +int pci_pwrctrl_power_on_devices(struct device *parent) +{ + struct device_node *np = parent->of_node; + struct device_node *child = NULL; + int ret; + + for_each_available_child_of_node(np, child) { + ret = pci_pwrctrl_power_on_device(child); + if (ret) + goto err_power_off; + } + + return 0; + +err_power_off: + for_each_available_child_of_node_scoped(np, tmp) { + if (tmp == child) + break; + pci_pwrctrl_power_off_device(tmp); + } + of_node_put(child); + + return ret; +} +EXPORT_SYMBOL_GPL(pci_pwrctrl_power_on_devices); + +static int pci_pwrctrl_create_device(struct device_node *np, + struct device *parent) +{ + struct platform_device *pdev; + int ret; + + for_each_available_child_of_node_scoped(np, child) { + ret = pci_pwrctrl_create_device(child, parent); + if (ret) + return ret; + } + + /* Bail out if the platform device is already available for the node */ + pdev = of_find_device_by_node(np); + if (pdev) { + platform_device_put(pdev); + return 0; + } + + /* + * Sanity check to make sure that the node has the compatible property + * to allow driver binding. + */ + if (!of_property_present(np, "compatible")) + return 0; + + /* + * Check whether the pwrctrl device really needs to be created or not. + * This is decided based on at least one of the power supplies defined + * in the devicetree node of the device or the graph property. + */ + if (!of_pci_supply_present(np) && !of_graph_is_present(np)) { + dev_dbg(parent, "Skipping OF node: %s\n", np->name); + return 0; + } + + /* Now create the pwrctrl device */ + pdev = of_platform_device_create(np, NULL, parent); + if (!pdev) { + dev_err(parent, "Failed to create pwrctrl device for node: %s\n", np->name); + return -EINVAL; + } + + return 0; +} + +/** + * pci_pwrctrl_create_devices - Create pwrctrl devices + * + * @parent: PCI host controller device + * + * Recursively create pwrctrl devices for the devicetree hierarchy below + * the specified PCI host controller in a depth first manner. On error, all + * created devices will be destroyed. + * + * Return: 0 on success, negative error number on error. + */ +int pci_pwrctrl_create_devices(struct device *parent) +{ + int ret; + + for_each_available_child_of_node_scoped(parent->of_node, child) { + ret = pci_pwrctrl_create_device(child, parent); + if (ret) { + pci_pwrctrl_destroy_devices(parent); + return ret; + } + } + + return 0; +} +EXPORT_SYMBOL_GPL(pci_pwrctrl_create_devices); + +static void pci_pwrctrl_destroy_device(struct device_node *np) +{ + struct platform_device *pdev; + + for_each_available_child_of_node_scoped(np, child) + pci_pwrctrl_destroy_device(child); + + pdev = of_find_device_by_node(np); + if (!pdev) + return; + + of_device_unregister(pdev); + platform_device_put(pdev); + + of_node_clear_flag(np, OF_POPULATED); +} + +/** + * pci_pwrctrl_destroy_devices - Destroy pwrctrl devices + * + * @parent: PCI host controller device + * + * Recursively destroy pwrctrl devices for the devicetree hierarchy below + * the specified PCI host controller in a depth first manner. + */ +void pci_pwrctrl_destroy_devices(struct device *parent) +{ + struct device_node *np = parent->of_node; + + for_each_available_child_of_node_scoped(np, child) + pci_pwrctrl_destroy_device(child); +} +EXPORT_SYMBOL_GPL(pci_pwrctrl_destroy_devices); + MODULE_AUTHOR("Bartosz Golaszewski <bartosz.golaszewski@linaro.org>"); MODULE_DESCRIPTION("PCI Device Power Control core driver"); MODULE_LICENSE("GPL"); diff --git a/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c b/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c index 4e664e7b8dd2..0d0377283c37 100644 --- a/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c +++ b/drivers/pci/pwrctrl/pci-pwrctrl-pwrseq.c @@ -13,12 +13,12 @@ #include <linux/slab.h> #include <linux/types.h> -struct pci_pwrctrl_pwrseq_data { - struct pci_pwrctrl ctx; +struct pwrseq_pwrctrl { + struct pci_pwrctrl pwrctrl; struct pwrseq_desc *pwrseq; }; -struct pci_pwrctrl_pwrseq_pdata { +struct pwrseq_pwrctrl_pdata { const char *target; /* * Called before doing anything else to perform device-specific @@ -27,7 +27,7 @@ struct pci_pwrctrl_pwrseq_pdata { int (*validate_device)(struct device *dev); }; -static int pci_pwrctrl_pwrseq_qcm_wcn_validate_device(struct device *dev) +static int pwrseq_pwrctrl_qcm_wcn_validate_device(struct device *dev) { /* * Old device trees for some platforms already define wifi nodes for @@ -47,22 +47,38 @@ static int pci_pwrctrl_pwrseq_qcm_wcn_validate_device(struct device *dev) return 0; } -static const struct pci_pwrctrl_pwrseq_pdata pci_pwrctrl_pwrseq_qcom_wcn_pdata = { +static const struct pwrseq_pwrctrl_pdata pwrseq_pwrctrl_qcom_wcn_pdata = { .target = "wlan", - .validate_device = pci_pwrctrl_pwrseq_qcm_wcn_validate_device, + .validate_device = pwrseq_pwrctrl_qcm_wcn_validate_device, }; -static void devm_pci_pwrctrl_pwrseq_power_off(void *data) +static int pwrseq_pwrctrl_power_on(struct pci_pwrctrl *pwrctrl) { - struct pwrseq_desc *pwrseq = data; + struct pwrseq_pwrctrl *pwrseq = container_of(pwrctrl, + struct pwrseq_pwrctrl, pwrctrl); - pwrseq_power_off(pwrseq); + return pwrseq_power_on(pwrseq->pwrseq); } -static int pci_pwrctrl_pwrseq_probe(struct platform_device *pdev) +static int pwrseq_pwrctrl_power_off(struct pci_pwrctrl *pwrctrl) { - const struct pci_pwrctrl_pwrseq_pdata *pdata; - struct pci_pwrctrl_pwrseq_data *data; + struct pwrseq_pwrctrl *pwrseq = container_of(pwrctrl, + struct pwrseq_pwrctrl, pwrctrl); + + return pwrseq_power_off(pwrseq->pwrseq); +} + +static void devm_pwrseq_pwrctrl_power_off(void *data) +{ + struct pwrseq_pwrctrl *pwrseq = data; + + pwrseq_pwrctrl_power_off(&pwrseq->pwrctrl); +} + +static int pwrseq_pwrctrl_probe(struct platform_device *pdev) +{ + const struct pwrseq_pwrctrl_pdata *pdata; + struct pwrseq_pwrctrl *pwrseq; struct device *dev = &pdev->dev; int ret; @@ -76,28 +92,26 @@ static int pci_pwrctrl_pwrseq_probe(struct platform_device *pdev) return ret; } - data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL); - if (!data) + pwrseq = devm_kzalloc(dev, sizeof(*pwrseq), GFP_KERNEL); + if (!pwrseq) return -ENOMEM; - data->pwrseq = devm_pwrseq_get(dev, pdata->target); - if (IS_ERR(data->pwrseq)) - return dev_err_probe(dev, PTR_ERR(data->pwrseq), + pwrseq->pwrseq = devm_pwrseq_get(dev, pdata->target); + if (IS_ERR(pwrseq->pwrseq)) + return dev_err_probe(dev, PTR_ERR(pwrseq->pwrseq), "Failed to get the power sequencer\n"); - ret = pwrseq_power_on(data->pwrseq); - if (ret) - return dev_err_probe(dev, ret, - "Failed to power-on the device\n"); - - ret = devm_add_action_or_reset(dev, devm_pci_pwrctrl_pwrseq_power_off, - data->pwrseq); + ret = devm_add_action_or_reset(dev, devm_pwrseq_pwrctrl_power_off, + pwrseq); if (ret) return ret; - pci_pwrctrl_init(&data->ctx, dev); + pwrseq->pwrctrl.power_on = pwrseq_pwrctrl_power_on; + pwrseq->pwrctrl.power_off = pwrseq_pwrctrl_power_off; + + pci_pwrctrl_init(&pwrseq->pwrctrl, dev); - ret = devm_pci_pwrctrl_device_set_ready(dev, &data->ctx); + ret = devm_pci_pwrctrl_device_set_ready(dev, &pwrseq->pwrctrl); if (ret) return dev_err_probe(dev, ret, "Failed to register the pwrctrl wrapper\n"); @@ -105,34 +119,34 @@ static int pci_pwrctrl_pwrseq_probe(struct platform_device *pdev) return 0; } -static const struct of_device_id pci_pwrctrl_pwrseq_of_match[] = { +static const struct of_device_id pwrseq_pwrctrl_of_match[] = { { /* ATH11K in QCA6390 package. */ .compatible = "pci17cb,1101", - .data = &pci_pwrctrl_pwrseq_qcom_wcn_pdata, + .data = &pwrseq_pwrctrl_qcom_wcn_pdata, }, { /* ATH11K in WCN6855 package. */ .compatible = "pci17cb,1103", - .data = &pci_pwrctrl_pwrseq_qcom_wcn_pdata, + .data = &pwrseq_pwrctrl_qcom_wcn_pdata, }, { /* ATH12K in WCN7850 package. */ .compatible = "pci17cb,1107", - .data = &pci_pwrctrl_pwrseq_qcom_wcn_pdata, + .data = &pwrseq_pwrctrl_qcom_wcn_pdata, }, { } }; -MODULE_DEVICE_TABLE(of, pci_pwrctrl_pwrseq_of_match); +MODULE_DEVICE_TABLE(of, pwrseq_pwrctrl_of_match); -static struct platform_driver pci_pwrctrl_pwrseq_driver = { +static struct platform_driver pwrseq_pwrctrl_driver = { .driver = { .name = "pci-pwrctrl-pwrseq", - .of_match_table = pci_pwrctrl_pwrseq_of_match, + .of_match_table = pwrseq_pwrctrl_of_match, }, - .probe = pci_pwrctrl_pwrseq_probe, + .probe = pwrseq_pwrctrl_probe, }; -module_platform_driver(pci_pwrctrl_pwrseq_driver); +module_platform_driver(pwrseq_pwrctrl_driver); MODULE_AUTHOR("Bartosz Golaszewski <bartosz.golaszewski@linaro.org>"); MODULE_DESCRIPTION("Generic PCI Power Control module for power sequenced devices"); diff --git a/drivers/pci/pwrctrl/pci-pwrctrl-tc9563.c b/drivers/pci/pwrctrl/pci-pwrctrl-tc9563.c new file mode 100644 index 000000000000..488e1ec34a7f --- /dev/null +++ b/drivers/pci/pwrctrl/pci-pwrctrl-tc9563.c @@ -0,0 +1,662 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved. + */ + +#include <linux/array_size.h> +#include <linux/bitfield.h> +#include <linux/bits.h> +#include <linux/delay.h> +#include <linux/device.h> +#include <linux/gpio/consumer.h> +#include <linux/i2c.h> +#include <linux/mod_devicetable.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/of_platform.h> +#include <linux/pci.h> +#include <linux/pci-pwrctrl.h> +#include <linux/platform_device.h> +#include <linux/regulator/consumer.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/unaligned.h> + +#include "../pci.h" + +#define TC9563_GPIO_CONFIG 0x801208 +#define TC9563_RESET_GPIO 0x801210 + +#define TC9563_PORT_L0S_DELAY 0x82496c +#define TC9563_PORT_L1_DELAY 0x824970 + +#define TC9563_EMBEDDED_ETH_DELAY 0x8200d8 +#define TC9563_ETH_L1_DELAY_MASK GENMASK(27, 18) +#define TC9563_ETH_L1_DELAY_VALUE(x) FIELD_PREP(TC9563_ETH_L1_DELAY_MASK, x) +#define TC9563_ETH_L0S_DELAY_MASK GENMASK(17, 13) +#define TC9563_ETH_L0S_DELAY_VALUE(x) FIELD_PREP(TC9563_ETH_L0S_DELAY_MASK, x) + +#define TC9563_NFTS_2_5_GT 0x824978 +#define TC9563_NFTS_5_GT 0x82497c + +#define TC9563_PORT_LANE_ACCESS_ENABLE 0x828000 + +#define TC9563_PHY_RATE_CHANGE_OVERRIDE 0x828040 +#define TC9563_PHY_RATE_CHANGE 0x828050 + +#define TC9563_TX_MARGIN 0x828234 + +#define TC9563_DFE_ENABLE 0x828a04 +#define TC9563_DFE_EQ0_MODE 0x828a08 +#define TC9563_DFE_EQ1_MODE 0x828a0c +#define TC9563_DFE_EQ2_MODE 0x828a14 +#define TC9563_DFE_PD_MASK 0x828254 + +#define TC9563_PORT_SELECT 0x82c02c +#define TC9563_PORT_ACCESS_ENABLE 0x82c030 + +#define TC9563_POWER_CONTROL 0x82b09c +#define TC9563_POWER_CONTROL_OVREN 0x82b2c8 + +#define TC9563_GPIO_MASK 0xfffffff3 +#define TC9563_GPIO_DEASSERT_BITS 0xc /* Clear to deassert GPIO */ + +#define TC9563_TX_MARGIN_MIN_UA 400000 + +/* + * From TC9563 PORSYS rev 0.2, figure 1.1 POR boot sequence + * wait for 10ms for the internal osc frequency to stabilize. + */ +#define TC9563_OSC_STAB_DELAY_US (10 * USEC_PER_MSEC) + +#define TC9563_L0S_L1_DELAY_UNIT_NS 256 /* Each unit represents 256 ns */ + +struct tc9563_pwrctrl_reg_setting { + unsigned int offset; + unsigned int val; +}; + +enum tc9563_pwrctrl_ports { + TC9563_USP, + TC9563_DSP1, + TC9563_DSP2, + TC9563_DSP3, + TC9563_ETHERNET, + TC9563_MAX +}; + +struct tc9563_pwrctrl_cfg { + u32 l0s_delay; + u32 l1_delay; + u32 tx_amp; + u8 nfts[2]; /* GEN1 & GEN2 */ + bool disable_dfe; + bool disable_port; +}; + +#define TC9563_PWRCTL_MAX_SUPPLY 6 + +static const char *const tc9563_supply_names[TC9563_PWRCTL_MAX_SUPPLY] = { + "vddc", + "vdd18", + "vdd09", + "vddio1", + "vddio2", + "vddio18", +}; + +struct tc9563_pwrctrl { + struct pci_pwrctrl pwrctrl; + struct regulator_bulk_data supplies[TC9563_PWRCTL_MAX_SUPPLY]; + struct tc9563_pwrctrl_cfg cfg[TC9563_MAX]; + struct gpio_desc *reset_gpio; + struct i2c_adapter *adapter; + struct i2c_client *client; +}; + +/* + * downstream port power off sequence, hardcoding the address + * as we don't know register names for these register offsets. + */ +static const struct tc9563_pwrctrl_reg_setting common_pwroff_seq[] = { + {0x82900c, 0x1}, + {0x829010, 0x1}, + {0x829018, 0x0}, + {0x829020, 0x1}, + {0x82902c, 0x1}, + {0x829030, 0x1}, + {0x82903c, 0x1}, + {0x829058, 0x0}, + {0x82905c, 0x1}, + {0x829060, 0x1}, + {0x8290cc, 0x1}, + {0x8290d0, 0x1}, + {0x8290d8, 0x1}, + {0x8290e0, 0x1}, + {0x8290e8, 0x1}, + {0x8290ec, 0x1}, + {0x8290f4, 0x1}, + {0x82910c, 0x1}, + {0x829110, 0x1}, + {0x829114, 0x1}, +}; + +static const struct tc9563_pwrctrl_reg_setting dsp1_pwroff_seq[] = { + {TC9563_PORT_ACCESS_ENABLE, 0x2}, + {TC9563_PORT_LANE_ACCESS_ENABLE, 0x3}, + {TC9563_POWER_CONTROL, 0x014f4804}, + {TC9563_POWER_CONTROL_OVREN, 0x1}, + {TC9563_PORT_ACCESS_ENABLE, 0x4}, +}; + +static const struct tc9563_pwrctrl_reg_setting dsp2_pwroff_seq[] = { + {TC9563_PORT_ACCESS_ENABLE, 0x8}, + {TC9563_PORT_LANE_ACCESS_ENABLE, 0x1}, + {TC9563_POWER_CONTROL, 0x014f4804}, + {TC9563_POWER_CONTROL_OVREN, 0x1}, + {TC9563_PORT_ACCESS_ENABLE, 0x8}, +}; + +/* + * Since all transfers are initiated by the probe, no locks are necessary, + * as there are no concurrent calls. + */ +static int tc9563_pwrctrl_i2c_write(struct i2c_client *client, + u32 reg_addr, u32 reg_val) +{ + struct i2c_msg msg; + u8 msg_buf[7]; + int ret; + + msg.addr = client->addr; + msg.len = 7; + msg.flags = 0; + + /* Big Endian for reg addr */ + put_unaligned_be24(reg_addr, &msg_buf[0]); + + /* Little Endian for reg val */ + put_unaligned_le32(reg_val, &msg_buf[3]); + + msg.buf = msg_buf; + ret = i2c_transfer(client->adapter, &msg, 1); + return ret == 1 ? 0 : ret; +} + +static int tc9563_pwrctrl_i2c_read(struct i2c_client *client, + u32 reg_addr, u32 *reg_val) +{ + struct i2c_msg msg[2]; + u8 wr_data[3]; + u32 rd_data; + int ret; + + msg[0].addr = client->addr; + msg[0].len = 3; + msg[0].flags = 0; + + /* Big Endian for reg addr */ + put_unaligned_be24(reg_addr, &wr_data[0]); + + msg[0].buf = wr_data; + + msg[1].addr = client->addr; + msg[1].len = 4; + msg[1].flags = I2C_M_RD; + + msg[1].buf = (u8 *)&rd_data; + + ret = i2c_transfer(client->adapter, &msg[0], 2); + if (ret == 2) { + *reg_val = get_unaligned_le32(&rd_data); + return 0; + } + + /* If only one message successfully completed, return -EIO */ + return ret == 1 ? -EIO : ret; +} + +static int tc9563_pwrctrl_i2c_bulk_write(struct i2c_client *client, + const struct tc9563_pwrctrl_reg_setting *seq, + int len) +{ + int ret, i; + + for (i = 0; i < len; i++) { + ret = tc9563_pwrctrl_i2c_write(client, seq[i].offset, seq[i].val); + if (ret) + return ret; + } + + return 0; +} + +static int tc9563_pwrctrl_disable_port(struct tc9563_pwrctrl *tc9563, + enum tc9563_pwrctrl_ports port) +{ + struct tc9563_pwrctrl_cfg *cfg = &tc9563->cfg[port]; + const struct tc9563_pwrctrl_reg_setting *seq; + int ret, len; + + if (!cfg->disable_port) + return 0; + + if (port == TC9563_DSP1) { + seq = dsp1_pwroff_seq; + len = ARRAY_SIZE(dsp1_pwroff_seq); + } else { + seq = dsp2_pwroff_seq; + len = ARRAY_SIZE(dsp2_pwroff_seq); + } + + ret = tc9563_pwrctrl_i2c_bulk_write(tc9563->client, seq, len); + if (ret) + return ret; + + return tc9563_pwrctrl_i2c_bulk_write(tc9563->client, common_pwroff_seq, + ARRAY_SIZE(common_pwroff_seq)); +} + +static int tc9563_pwrctrl_set_l0s_l1_entry_delay(struct tc9563_pwrctrl *tc9563, + enum tc9563_pwrctrl_ports port, + bool is_l1, u32 ns) +{ + u32 rd_val, units; + int ret; + + if (ns < TC9563_L0S_L1_DELAY_UNIT_NS) + return 0; + + /* convert to units of 256ns */ + units = ns / TC9563_L0S_L1_DELAY_UNIT_NS; + + if (port == TC9563_ETHERNET) { + ret = tc9563_pwrctrl_i2c_read(tc9563->client, + TC9563_EMBEDDED_ETH_DELAY, + &rd_val); + if (ret) + return ret; + + if (is_l1) + rd_val = u32_replace_bits(rd_val, units, + TC9563_ETH_L1_DELAY_MASK); + else + rd_val = u32_replace_bits(rd_val, units, + TC9563_ETH_L0S_DELAY_MASK); + + return tc9563_pwrctrl_i2c_write(tc9563->client, + TC9563_EMBEDDED_ETH_DELAY, + rd_val); + } + + ret = tc9563_pwrctrl_i2c_write(tc9563->client, TC9563_PORT_SELECT, + BIT(port)); + if (ret) + return ret; + + return tc9563_pwrctrl_i2c_write(tc9563->client, + is_l1 ? TC9563_PORT_L1_DELAY : TC9563_PORT_L0S_DELAY, + units); +} + +static int tc9563_pwrctrl_set_tx_amplitude(struct tc9563_pwrctrl *tc9563, + enum tc9563_pwrctrl_ports port) +{ + u32 amp = tc9563->cfg[port].tx_amp; + int port_access; + + if (amp < TC9563_TX_MARGIN_MIN_UA) + return 0; + + /* txmargin = (Amp(uV) - 400000) / 3125 */ + amp = (amp - TC9563_TX_MARGIN_MIN_UA) / 3125; + + switch (port) { + case TC9563_USP: + port_access = 0x1; + break; + case TC9563_DSP1: + port_access = 0x2; + break; + case TC9563_DSP2: + port_access = 0x8; + break; + default: + return -EINVAL; + } + + struct tc9563_pwrctrl_reg_setting tx_amp_seq[] = { + {TC9563_PORT_ACCESS_ENABLE, port_access}, + {TC9563_PORT_LANE_ACCESS_ENABLE, 0x3}, + {TC9563_TX_MARGIN, amp}, + }; + + return tc9563_pwrctrl_i2c_bulk_write(tc9563->client, tx_amp_seq, + ARRAY_SIZE(tx_amp_seq)); +} + +static int tc9563_pwrctrl_disable_dfe(struct tc9563_pwrctrl *tc9563, + enum tc9563_pwrctrl_ports port) +{ + struct tc9563_pwrctrl_cfg *cfg = &tc9563->cfg[port]; + int port_access, lane_access = 0x3; + u32 phy_rate = 0x21; + + if (!cfg->disable_dfe) + return 0; + + switch (port) { + case TC9563_USP: + phy_rate = 0x1; + port_access = 0x1; + break; + case TC9563_DSP1: + port_access = 0x2; + break; + case TC9563_DSP2: + port_access = 0x8; + lane_access = 0x1; + break; + default: + return -EINVAL; + } + + struct tc9563_pwrctrl_reg_setting disable_dfe_seq[] = { + {TC9563_PORT_ACCESS_ENABLE, port_access}, + {TC9563_PORT_LANE_ACCESS_ENABLE, lane_access}, + {TC9563_DFE_ENABLE, 0x0}, + {TC9563_DFE_EQ0_MODE, 0x411}, + {TC9563_DFE_EQ1_MODE, 0x11}, + {TC9563_DFE_EQ2_MODE, 0x11}, + {TC9563_DFE_PD_MASK, 0x7}, + {TC9563_PHY_RATE_CHANGE_OVERRIDE, 0x10}, + {TC9563_PHY_RATE_CHANGE, phy_rate}, + {TC9563_PHY_RATE_CHANGE, 0x0}, + {TC9563_PHY_RATE_CHANGE_OVERRIDE, 0x0}, + }; + + return tc9563_pwrctrl_i2c_bulk_write(tc9563->client, disable_dfe_seq, + ARRAY_SIZE(disable_dfe_seq)); +} + +static int tc9563_pwrctrl_set_nfts(struct tc9563_pwrctrl *tc9563, + enum tc9563_pwrctrl_ports port) +{ + u8 *nfts = tc9563->cfg[port].nfts; + struct tc9563_pwrctrl_reg_setting nfts_seq[] = { + {TC9563_NFTS_2_5_GT, nfts[0]}, + {TC9563_NFTS_5_GT, nfts[1]}, + }; + int ret; + + if (!nfts[0]) + return 0; + + ret = tc9563_pwrctrl_i2c_write(tc9563->client, TC9563_PORT_SELECT, + BIT(port)); + if (ret) + return ret; + + return tc9563_pwrctrl_i2c_bulk_write(tc9563->client, nfts_seq, + ARRAY_SIZE(nfts_seq)); +} + +static int tc9563_pwrctrl_assert_deassert_reset(struct tc9563_pwrctrl *tc9563, + bool deassert) +{ + int ret, val; + + ret = tc9563_pwrctrl_i2c_write(tc9563->client, TC9563_GPIO_CONFIG, + TC9563_GPIO_MASK); + if (ret) + return ret; + + val = deassert ? TC9563_GPIO_DEASSERT_BITS : 0; + + return tc9563_pwrctrl_i2c_write(tc9563->client, TC9563_RESET_GPIO, val); +} + +static int tc9563_pwrctrl_parse_device_dt(struct tc9563_pwrctrl *tc9563, + struct device_node *node, + enum tc9563_pwrctrl_ports port) +{ + struct tc9563_pwrctrl_cfg *cfg = &tc9563->cfg[port]; + int ret; + + /* Disable port if the status of the port is disabled. */ + if (!of_device_is_available(node)) { + cfg->disable_port = true; + return 0; + } + + ret = of_property_read_u32(node, "aspm-l0s-entry-delay-ns", &cfg->l0s_delay); + if (ret && ret != -EINVAL) + return ret; + + ret = of_property_read_u32(node, "aspm-l1-entry-delay-ns", &cfg->l1_delay); + if (ret && ret != -EINVAL) + return ret; + + ret = of_property_read_u32(node, "toshiba,tx-amplitude-microvolt", &cfg->tx_amp); + if (ret && ret != -EINVAL) + return ret; + + ret = of_property_read_u8_array(node, "n-fts", cfg->nfts, ARRAY_SIZE(cfg->nfts)); + if (ret && ret != -EINVAL) + return ret; + + cfg->disable_dfe = of_property_read_bool(node, "toshiba,no-dfe-support"); + + return 0; +} + +static int tc9563_pwrctrl_power_off(struct pci_pwrctrl *pwrctrl) +{ + struct tc9563_pwrctrl *tc9563 = container_of(pwrctrl, + struct tc9563_pwrctrl, pwrctrl); + + gpiod_set_value(tc9563->reset_gpio, 1); + + regulator_bulk_disable(ARRAY_SIZE(tc9563->supplies), tc9563->supplies); + + return 0; +} + +static int tc9563_pwrctrl_power_on(struct pci_pwrctrl *pwrctrl) +{ + struct tc9563_pwrctrl *tc9563 = container_of(pwrctrl, + struct tc9563_pwrctrl, pwrctrl); + struct device *dev = tc9563->pwrctrl.dev; + struct tc9563_pwrctrl_cfg *cfg; + int ret, i; + + ret = regulator_bulk_enable(ARRAY_SIZE(tc9563->supplies), + tc9563->supplies); + if (ret < 0) + return dev_err_probe(dev, ret, "cannot enable regulators\n"); + + gpiod_set_value(tc9563->reset_gpio, 0); + + fsleep(TC9563_OSC_STAB_DELAY_US); + + ret = tc9563_pwrctrl_assert_deassert_reset(tc9563, false); + if (ret) + goto power_off; + + for (i = 0; i < TC9563_MAX; i++) { + cfg = &tc9563->cfg[i]; + ret = tc9563_pwrctrl_disable_port(tc9563, i); + if (ret) { + dev_err(dev, "Disabling port failed\n"); + goto power_off; + } + + ret = tc9563_pwrctrl_set_l0s_l1_entry_delay(tc9563, i, false, cfg->l0s_delay); + if (ret) { + dev_err(dev, "Setting L0s entry delay failed\n"); + goto power_off; + } + + ret = tc9563_pwrctrl_set_l0s_l1_entry_delay(tc9563, i, true, cfg->l1_delay); + if (ret) { + dev_err(dev, "Setting L1 entry delay failed\n"); + goto power_off; + } + + ret = tc9563_pwrctrl_set_tx_amplitude(tc9563, i); + if (ret) { + dev_err(dev, "Setting Tx amplitude failed\n"); + goto power_off; + } + + ret = tc9563_pwrctrl_set_nfts(tc9563, i); + if (ret) { + dev_err(dev, "Setting N_FTS failed\n"); + goto power_off; + } + + ret = tc9563_pwrctrl_disable_dfe(tc9563, i); + if (ret) { + dev_err(dev, "Disabling DFE failed\n"); + goto power_off; + } + } + + ret = tc9563_pwrctrl_assert_deassert_reset(tc9563, true); + if (!ret) + return 0; + +power_off: + tc9563_pwrctrl_power_off(&tc9563->pwrctrl); + return ret; +} + +static int tc9563_pwrctrl_probe(struct platform_device *pdev) +{ + struct device_node *node = pdev->dev.of_node; + struct device *dev = &pdev->dev; + enum tc9563_pwrctrl_ports port; + struct tc9563_pwrctrl *tc9563; + struct device_node *i2c_node; + int ret, addr; + + tc9563 = devm_kzalloc(dev, sizeof(*tc9563), GFP_KERNEL); + if (!tc9563) + return -ENOMEM; + + ret = of_property_read_u32_index(node, "i2c-parent", 1, &addr); + if (ret) + return dev_err_probe(dev, ret, "Failed to read i2c-parent property\n"); + + i2c_node = of_parse_phandle(dev->of_node, "i2c-parent", 0); + tc9563->adapter = of_find_i2c_adapter_by_node(i2c_node); + of_node_put(i2c_node); + if (!tc9563->adapter) + return dev_err_probe(dev, -EPROBE_DEFER, "Failed to find I2C adapter\n"); + + tc9563->client = i2c_new_dummy_device(tc9563->adapter, addr); + if (IS_ERR(tc9563->client)) { + dev_err(dev, "Failed to create I2C client\n"); + put_device(&tc9563->adapter->dev); + return PTR_ERR(tc9563->client); + } + + for (int i = 0; i < ARRAY_SIZE(tc9563_supply_names); i++) + tc9563->supplies[i].supply = tc9563_supply_names[i]; + + ret = devm_regulator_bulk_get(dev, TC9563_PWRCTL_MAX_SUPPLY, + tc9563->supplies); + if (ret) { + dev_err_probe(dev, ret, "failed to get supply regulator\n"); + goto remove_i2c; + } + + tc9563->reset_gpio = devm_gpiod_get(dev, "resx", GPIOD_OUT_HIGH); + if (IS_ERR(tc9563->reset_gpio)) { + ret = dev_err_probe(dev, PTR_ERR(tc9563->reset_gpio), "failed to get resx GPIO\n"); + goto remove_i2c; + } + + pci_pwrctrl_init(&tc9563->pwrctrl, dev); + + port = TC9563_USP; + ret = tc9563_pwrctrl_parse_device_dt(tc9563, node, port); + if (ret) { + dev_err(dev, "failed to parse device tree properties: %d\n", ret); + goto remove_i2c; + } + + /* + * Downstream ports are always children of the upstream port. + * The first node represents DSP1, the second node represents DSP2, + * and so on. + */ + for_each_child_of_node_scoped(node, child) { + port++; + ret = tc9563_pwrctrl_parse_device_dt(tc9563, child, port); + if (ret) + break; + /* Embedded ethernet device are under DSP3 */ + if (port == TC9563_DSP3) { + for_each_child_of_node_scoped(child, child1) { + port++; + ret = tc9563_pwrctrl_parse_device_dt(tc9563, + child1, port); + if (ret) + break; + } + } + } + if (ret) { + dev_err(dev, "failed to parse device tree properties: %d\n", ret); + goto remove_i2c; + } + + tc9563->pwrctrl.power_on = tc9563_pwrctrl_power_on; + tc9563->pwrctrl.power_off = tc9563_pwrctrl_power_off; + + ret = devm_pci_pwrctrl_device_set_ready(dev, &tc9563->pwrctrl); + if (ret) + goto power_off; + + return 0; + +power_off: + tc9563_pwrctrl_power_off(&tc9563->pwrctrl); +remove_i2c: + i2c_unregister_device(tc9563->client); + put_device(&tc9563->adapter->dev); + return ret; +} + +static void tc9563_pwrctrl_remove(struct platform_device *pdev) +{ + struct pci_pwrctrl *pwrctrl = dev_get_drvdata(&pdev->dev); + struct tc9563_pwrctrl *tc9563 = container_of(pwrctrl, + struct tc9563_pwrctrl, pwrctrl); + + tc9563_pwrctrl_power_off(&tc9563->pwrctrl); + i2c_unregister_device(tc9563->client); + put_device(&tc9563->adapter->dev); +} + +static const struct of_device_id tc9563_pwrctrl_of_match[] = { + { .compatible = "pci1179,0623"}, + { } +}; +MODULE_DEVICE_TABLE(of, tc9563_pwrctrl_of_match); + +static struct platform_driver tc9563_pwrctrl_driver = { + .driver = { + .name = "pwrctrl-tc9563", + .of_match_table = tc9563_pwrctrl_of_match, + .probe_type = PROBE_PREFER_ASYNCHRONOUS, + }, + .probe = tc9563_pwrctrl_probe, + .remove = tc9563_pwrctrl_remove, +}; +module_platform_driver(tc9563_pwrctrl_driver); + +MODULE_AUTHOR("Krishna chaitanya chundru <quic_krichai@quicinc.com>"); +MODULE_DESCRIPTION("TC956x power control driver"); +MODULE_LICENSE("GPL"); diff --git a/drivers/pci/pwrctrl/slot.c b/drivers/pci/pwrctrl/slot.c index 18becc144913..082af81efe25 100644 --- a/drivers/pci/pwrctrl/slot.c +++ b/drivers/pci/pwrctrl/slot.c @@ -4,31 +4,72 @@ * Author: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> */ +#include <linux/clk.h> #include <linux/device.h> #include <linux/mod_devicetable.h> #include <linux/module.h> +#include <linux/of_graph.h> #include <linux/pci-pwrctrl.h> #include <linux/platform_device.h> +#include <linux/pwrseq/consumer.h> #include <linux/regulator/consumer.h> #include <linux/slab.h> -struct pci_pwrctrl_slot_data { - struct pci_pwrctrl ctx; +struct slot_pwrctrl { + struct pci_pwrctrl pwrctrl; struct regulator_bulk_data *supplies; int num_supplies; + struct clk *clk; + struct pwrseq_desc *pwrseq; }; -static void devm_pci_pwrctrl_slot_power_off(void *data) +static int slot_pwrctrl_power_on(struct pci_pwrctrl *pwrctrl) { - struct pci_pwrctrl_slot_data *slot = data; + struct slot_pwrctrl *slot = container_of(pwrctrl, + struct slot_pwrctrl, pwrctrl); + int ret; + + if (slot->pwrseq) { + pwrseq_power_on(slot->pwrseq); + return 0; + } + + ret = regulator_bulk_enable(slot->num_supplies, slot->supplies); + if (ret < 0) { + dev_err(slot->pwrctrl.dev, "Failed to enable slot regulators\n"); + return ret; + } + + return clk_prepare_enable(slot->clk); +} + +static int slot_pwrctrl_power_off(struct pci_pwrctrl *pwrctrl) +{ + struct slot_pwrctrl *slot = container_of(pwrctrl, + struct slot_pwrctrl, pwrctrl); + + if (slot->pwrseq) { + pwrseq_power_off(slot->pwrseq); + return 0; + } regulator_bulk_disable(slot->num_supplies, slot->supplies); + clk_disable_unprepare(slot->clk); + + return 0; +} + +static void devm_slot_pwrctrl_release(void *data) +{ + struct slot_pwrctrl *slot = data; + + slot_pwrctrl_power_off(&slot->pwrctrl); regulator_bulk_free(slot->num_supplies, slot->supplies); } -static int pci_pwrctrl_slot_probe(struct platform_device *pdev) +static int slot_pwrctrl_probe(struct platform_device *pdev) { - struct pci_pwrctrl_slot_data *slot; + struct slot_pwrctrl *slot; struct device *dev = &pdev->dev; int ret; @@ -36,6 +77,15 @@ static int pci_pwrctrl_slot_probe(struct platform_device *pdev) if (!slot) return -ENOMEM; + if (of_graph_is_present(dev_of_node(dev))) { + slot->pwrseq = devm_pwrseq_get(dev, "pcie"); + if (IS_ERR(slot->pwrseq)) + return dev_err_probe(dev, PTR_ERR(slot->pwrseq), + "Failed to get the power sequencer\n"); + + goto skip_resources; + } + ret = of_regulator_bulk_get_all(dev, dev_of_node(dev), &slot->supplies); if (ret < 0) { @@ -44,49 +94,46 @@ static int pci_pwrctrl_slot_probe(struct platform_device *pdev) } slot->num_supplies = ret; - ret = regulator_bulk_enable(slot->num_supplies, slot->supplies); - if (ret < 0) { - dev_err_probe(dev, ret, "Failed to enable slot regulators\n"); - goto err_regulator_free; + + slot->clk = devm_clk_get_optional(dev, NULL); + if (IS_ERR(slot->clk)) { + return dev_err_probe(dev, PTR_ERR(slot->clk), + "Failed to enable slot clock\n"); } - ret = devm_add_action_or_reset(dev, devm_pci_pwrctrl_slot_power_off, - slot); +skip_resources: + slot->pwrctrl.power_on = slot_pwrctrl_power_on; + slot->pwrctrl.power_off = slot_pwrctrl_power_off; + + ret = devm_add_action_or_reset(dev, devm_slot_pwrctrl_release, slot); if (ret) - goto err_regulator_disable; + return ret; - pci_pwrctrl_init(&slot->ctx, dev); + pci_pwrctrl_init(&slot->pwrctrl, dev); - ret = devm_pci_pwrctrl_device_set_ready(dev, &slot->ctx); + ret = devm_pci_pwrctrl_device_set_ready(dev, &slot->pwrctrl); if (ret) return dev_err_probe(dev, ret, "Failed to register pwrctrl driver\n"); return 0; - -err_regulator_disable: - regulator_bulk_disable(slot->num_supplies, slot->supplies); -err_regulator_free: - regulator_bulk_free(slot->num_supplies, slot->supplies); - - return ret; } -static const struct of_device_id pci_pwrctrl_slot_of_match[] = { +static const struct of_device_id slot_pwrctrl_of_match[] = { { .compatible = "pciclass,0604", }, { } }; -MODULE_DEVICE_TABLE(of, pci_pwrctrl_slot_of_match); +MODULE_DEVICE_TABLE(of, slot_pwrctrl_of_match); -static struct platform_driver pci_pwrctrl_slot_driver = { +static struct platform_driver slot_pwrctrl_driver = { .driver = { .name = "pci-pwrctrl-slot", - .of_match_table = pci_pwrctrl_slot_of_match, + .of_match_table = slot_pwrctrl_of_match, }, - .probe = pci_pwrctrl_slot_probe, + .probe = slot_pwrctrl_probe, }; -module_platform_driver(pci_pwrctrl_slot_driver); +module_platform_driver(slot_pwrctrl_driver); MODULE_AUTHOR("Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org>"); MODULE_DESCRIPTION("Generic PCI Power Control driver for PCI Slots"); diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index 8d610c17e0f2..48946cca4be7 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -21,6 +21,7 @@ #include <linux/pci.h> #include <linux/isa-dma.h> /* isa_dma_bridge_buggy */ #include <linux/init.h> +#include <linux/iommu.h> #include <linux/delay.h> #include <linux/acpi.h> #include <linux/dmi.h> @@ -38,14 +39,10 @@ static bool pcie_lbms_seen(struct pci_dev *dev, u16 lnksta) { - unsigned long count; - int ret; - - ret = pcie_lbms_count(dev, &count); - if (ret < 0) - return lnksta & PCI_EXP_LNKSTA_LBMS; + if (test_bit(PCI_LINK_LBMS_SEEN, &dev->priv_flags)) + return true; - return count > 0; + return lnksta & PCI_EXP_LNKSTA_LBMS; } /* @@ -109,13 +106,13 @@ int pcie_failed_link_retrain(struct pci_dev *dev) !pcie_cap_has_lnkctl2(dev) || !dev->link_active_reporting) return ret; - pcie_capability_read_word(dev, PCI_EXP_LNKCTL2, &lnkctl2); pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta); if (!(lnksta & PCI_EXP_LNKSTA_DLLLA) && pcie_lbms_seen(dev, lnksta)) { - u16 oldlnkctl2 = lnkctl2; + u16 oldlnkctl2; pci_info(dev, "broken device, retraining non-functional downstream link at 2.5GT/s\n"); + pcie_capability_read_word(dev, PCI_EXP_LNKCTL2, &oldlnkctl2); ret = pcie_set_target_speed(dev, PCIE_SPEED_2_5GT, false); if (ret) { pci_info(dev, "retraining failed\n"); @@ -127,6 +124,8 @@ int pcie_failed_link_retrain(struct pci_dev *dev) pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta); } + pcie_capability_read_word(dev, PCI_EXP_LNKCTL2, &lnkctl2); + if ((lnksta & PCI_EXP_LNKSTA_DLLLA) && (lnkctl2 & PCI_EXP_LNKCTL2_TLS) == PCI_EXP_LNKCTL2_TLS_2_5GT && pci_match_id(ids, dev)) { @@ -1362,6 +1361,16 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_82380FB, quirk DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TOSHIBA, 0x605, quirk_transparent_bridge); /* + * Enabling Link Bandwidth Management Interrupts (BW notifications) can cause + * boot hangs on P45. + */ +static void quirk_p45_bw_notifications(struct pci_dev *dev) +{ + dev->no_bw_notif = 1; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x2e21, quirk_p45_bw_notifications); + +/* * Common misconfiguration of the MediaGX/Geode PCI master that will reduce * PCI bandwidth from 70MB/s to 25MB/s. See the GXM/GXLV/GX1 datasheets * found at http://www.national.com/analog for info on what these bits do. @@ -1990,12 +1999,12 @@ static void quirk_huawei_pcie_sva(struct pci_dev *pdev) device_create_managed_software_node(&pdev->dev, properties, NULL)) pci_warn(pdev, "could not add stall property"); } -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa250, quirk_huawei_pcie_sva); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa251, quirk_huawei_pcie_sva); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa255, quirk_huawei_pcie_sva); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa256, quirk_huawei_pcie_sva); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa258, quirk_huawei_pcie_sva); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_HUAWEI, 0xa259, quirk_huawei_pcie_sva); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa250, quirk_huawei_pcie_sva); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa251, quirk_huawei_pcie_sva); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa255, quirk_huawei_pcie_sva); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa256, quirk_huawei_pcie_sva); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa258, quirk_huawei_pcie_sva); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0xa259, quirk_huawei_pcie_sva); /* * It's possible for the MSI to get corrupted if SHPC and ACPI are used @@ -2496,28 +2505,27 @@ DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_INTEL, PCI_ANY_ID, */ static void quirk_disable_aspm_l0s(struct pci_dev *dev) { - pci_info(dev, "Disabling L0s\n"); - pci_disable_link_state(dev, PCIE_LINK_STATE_L0S); -} -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10a7, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10a9, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10b6, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10c6, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10c7, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10c8, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10d6, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10db, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10dd, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10e1, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10ec, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s); -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s); + pcie_aspm_remove_cap(dev, PCI_EXP_LNKCAP_ASPM_L0S); +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10a7, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10a9, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10b6, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10c6, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10c7, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10c8, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10d6, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10db, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10dd, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10e1, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10ec, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10f1, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x10f4, quirk_disable_aspm_l0s); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x1508, quirk_disable_aspm_l0s); static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev) { - pci_info(dev, "Disabling ASPM L0s/L1\n"); - pci_disable_link_state(dev, PCIE_LINK_STATE_L0S | PCIE_LINK_STATE_L1); + pcie_aspm_remove_cap(dev, + PCI_EXP_LNKCAP_ASPM_L0S | PCI_EXP_LNKCAP_ASPM_L1); } /* @@ -2525,7 +2533,10 @@ static void quirk_disable_aspm_l0s_l1(struct pci_dev *dev) * upstream PCIe root port when ASPM is enabled. At least L0s mode is affected; * disable both L0s and L1 for now to be safe. */ -DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ASMEDIA, 0x1080, quirk_disable_aspm_l0s_l1); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ASMEDIA, 0x1080, quirk_disable_aspm_l0s_l1); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_FREESCALE, 0x0451, quirk_disable_aspm_l0s_l1); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_PASEMI, 0xa002, quirk_disable_aspm_l0s_l1); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_HUAWEI, 0x1105, quirk_disable_aspm_l0s_l1); /* * Some Pericom PCIe-to-PCI bridges in reverse mode need the PCIe Retrain @@ -2719,6 +2730,7 @@ static void quirk_disable_msi(struct pci_dev *dev) DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_8131_BRIDGE, quirk_disable_msi); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_VIA, 0xa238, quirk_disable_msi); DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x5a3f, quirk_disable_msi); +DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_RDC, 0x1031, quirk_disable_msi); /* * The APC bridge device in AMD 780 family northbridges has some random @@ -3748,6 +3760,14 @@ static void quirk_no_bus_reset(struct pci_dev *dev) } /* + * After asserting Secondary Bus Reset to downstream devices via a GB10 + * Root Port, the link may not retrain correctly. + * https://lore.kernel.org/r/20251113084441.2124737-1-Johnny-CC.Chang@mediatek.com + */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x22CE, quirk_no_bus_reset); +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_NVIDIA, 0x22D0, quirk_no_bus_reset); + +/* * Some NVIDIA GPU devices do not work with bus reset, SBR needs to be * prevented for those affected devices. */ @@ -3790,6 +3810,16 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_CAVIUM, 0xa100, quirk_no_bus_reset); */ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_TI, 0xb005, quirk_no_bus_reset); +/* + * Reports from users making use of PCI device assignment with ASM1164 + * controllers indicate an issue with bus reset where the device fails to + * retrain. The issue appears more common in configurations with multiple + * controllers. The device does indicate PM reset support (NoSoftRst-), + * therefore this still leaves a viable reset method. + * https://forum.proxmox.com/threads/problems-with-pcie-passthrough-with-two-identical-devices.149003/ + */ +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ASMEDIA, 0x1164, quirk_no_bus_reset); + static void quirk_no_pm_reset(struct pci_dev *dev) { /* @@ -3831,7 +3861,7 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_MELLANOX, 0xcf80, quirk_no_pm_reset); */ static void quirk_thunderbolt_hotplug_msi(struct pci_dev *pdev) { - if (pdev->is_hotplug_bridge && + if (pdev->is_pciehp && (pdev->device != PCI_DEVICE_ID_INTEL_CACTUS_RIDGE_4C || pdev->revision <= 1)) pdev->no_msi = 1; @@ -4227,6 +4257,22 @@ static const struct pci_dev_reset_methods pci_dev_reset_methods[] = { { 0 } }; +static int __pci_dev_specific_reset(struct pci_dev *dev, bool probe, + const struct pci_dev_reset_methods *i) +{ + int ret; + + ret = pci_dev_reset_iommu_prepare(dev); + if (ret) { + pci_err(dev, "failed to stop IOMMU for a PCI reset: %d\n", ret); + return ret; + } + + ret = i->reset(dev, probe); + pci_dev_reset_iommu_done(dev); + return ret; +} + /* * These device-specific reset methods are here rather than in a driver * because when a host assigns a device to a guest VM, the host may need @@ -4241,7 +4287,7 @@ int pci_dev_specific_reset(struct pci_dev *dev, bool probe) i->vendor == (u16)PCI_ANY_ID) && (i->device == dev->device || i->device == (u16)PCI_ANY_ID)) - return i->reset(dev, probe); + return __pci_dev_specific_reset(dev, probe, i); } return -ENOTTY; @@ -4453,6 +4499,16 @@ DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_BROADCOM, 0x9084, quirk_bridge_cavm_thrx2_pcie_root); /* + * AST1150 doesn't use a real PCI bus and always forwards the requester ID + * from downstream devices. + */ +static void quirk_aspeed_pci_bridge_no_alias(struct pci_dev *pdev) +{ + pdev->dev_flags |= PCI_DEV_FLAGS_PCI_BRIDGE_NO_ALIAS; +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ASPEED, 0x1150, quirk_aspeed_pci_bridge_no_alias); + +/* * Intersil/Techwell TW686[4589]-based video capture cards have an empty (zero) * class code. Fix it. */ @@ -4995,6 +5051,18 @@ static int pci_quirk_brcm_acs(struct pci_dev *dev, u16 acs_flags) PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); } +static int pci_quirk_loongson_acs(struct pci_dev *dev, u16 acs_flags) +{ + /* + * Loongson PCIe Root Ports don't advertise an ACS capability, but + * they do not allow peer-to-peer transactions between Root Ports. + * Allow each Root Port to be in a separate IOMMU group by masking + * SV/RR/CR/UF bits. + */ + return pci_acs_ctrl_enabled(acs_flags, + PCI_ACS_SV | PCI_ACS_RR | PCI_ACS_CR | PCI_ACS_UF); +} + /* * Wangxun 40G/25G/10G/1G NICs have no ACS capability, but on * multi-function devices, the hardware isolates the functions by @@ -5094,6 +5162,10 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_QCOM, 0x0401, pci_quirk_qcom_rp_acs }, /* QCOM SA8775P root port */ { PCI_VENDOR_ID_QCOM, 0x0115, pci_quirk_qcom_rp_acs }, + /* QCOM Hamoa root port */ + { PCI_VENDOR_ID_QCOM, 0x0111, pci_quirk_qcom_rp_acs }, + /* QCOM Glymur root port */ + { PCI_VENDOR_ID_QCOM, 0x0120, pci_quirk_qcom_rp_acs }, /* HXT SD4800 root ports. The ACS design is same as QCOM QDF2xxx */ { PCI_VENDOR_ID_HXT, 0x0401, pci_quirk_qcom_rp_acs }, /* Intel PCH root ports */ @@ -5128,6 +5200,17 @@ static const struct pci_dev_acs_enabled { { PCI_VENDOR_ID_BROADCOM, 0x1762, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_BROADCOM, 0x1763, pci_quirk_mf_endpoint_acs }, { PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs }, + /* Loongson PCIe Root Ports */ + { PCI_VENDOR_ID_LOONGSON, 0x3C09, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x3C19, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x3C29, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A09, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A19, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A29, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A39, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A49, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A59, pci_quirk_loongson_acs }, + { PCI_VENDOR_ID_LOONGSON, 0x7A69, pci_quirk_loongson_acs }, /* Amazon Annapurna Labs */ { PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs }, /* Zhaoxin multi-function devices */ @@ -5557,6 +5640,7 @@ static void quirk_no_ext_tags(struct pci_dev *pdev) pci_walk_bus(bridge->bus, pci_configure_extended_tags, NULL); } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_3WARE, 0x1004, quirk_no_ext_tags); +DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_3WARE, 0x1005, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0132, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0140, quirk_no_ext_tags); DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SERVERWORKS, 0x0141, quirk_no_ext_tags); @@ -5755,7 +5839,7 @@ DECLARE_PCI_FIXUP_CLASS_RESUME_EARLY(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, /* * Some IDT switches incorrectly flag an ACS Source Validation error on - * completions for config read requests even though PCIe r4.0, sec + * completions for config read requests even though PCIe r7.0, sec * 6.12.1.1, says that completions are never affected by ACS Source * Validation. Here's the text of IDT 89H32H8G3-YC, erratum #36: * @@ -5768,44 +5852,20 @@ DECLARE_PCI_FIXUP_CLASS_RESUME_EARLY(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, * * The workaround suggested by IDT is to issue a config write to the * downstream device before issuing the first config read. This allows the - * downstream device to capture its bus and device numbers (see PCIe r4.0, - * sec 2.2.9), thus avoiding the ACS error on the completion. + * downstream device to capture its bus and device numbers (see PCIe r7.0, + * sec 2.2.9.1), thus avoiding the ACS error on the completion. * * However, we don't know when the device is ready to accept the config - * write, so we do config reads until we receive a non-Config Request Retry - * Status, then do the config write. - * - * To avoid hitting the erratum when doing the config reads, we disable ACS - * SV around this process. + * write, and the issue affects resets of the switch as well as enumeration, + * so disable use of ACS SV for these devices altogether. */ -int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *l, int timeout) +void pci_disable_broken_acs_cap(struct pci_dev *pdev) { - int pos; - u16 ctrl = 0; - bool found; - struct pci_dev *bridge = bus->self; - - pos = bridge->acs_cap; - - /* Disable ACS SV before initial config reads */ - if (pos) { - pci_read_config_word(bridge, pos + PCI_ACS_CTRL, &ctrl); - if (ctrl & PCI_ACS_SV) - pci_write_config_word(bridge, pos + PCI_ACS_CTRL, - ctrl & ~PCI_ACS_SV); + if (pdev->vendor == PCI_VENDOR_ID_IDT && + (pdev->device == 0x80b5 || pdev->device == 0x8090)) { + pci_info(pdev, "Disabling broken ACS SV; downstream device isolation reduced\n"); + pdev->acs_capabilities &= ~PCI_ACS_SV; } - - found = pci_bus_generic_read_dev_vendor_id(bus, devfn, l, timeout); - - /* Write Vendor ID (read-only) so the endpoint latches its bus/dev */ - if (found) - pci_bus_write_config_word(bus, devfn, PCI_VENDOR_ID, 0); - - /* Re-enable ACS_SV if it was previously enabled */ - if (ctrl & PCI_ACS_SV) - pci_write_config_word(bridge, pos + PCI_ACS_CTRL, ctrl); - - return found; } /* @@ -6164,6 +6224,10 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_PERICOM, 0x2303, pci_fixup_pericom_acs_store_forward); DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_PERICOM, 0x2303, pci_fixup_pericom_acs_store_forward); +DECLARE_PCI_FIXUP_ENABLE(PCI_VENDOR_ID_PERICOM, 0xb404, + pci_fixup_pericom_acs_store_forward); +DECLARE_PCI_FIXUP_RESUME(PCI_VENDOR_ID_PERICOM, 0xb404, + pci_fixup_pericom_acs_store_forward); static void nvidia_ion_ahci_fixup(struct pci_dev *pdev) { diff --git a/drivers/pci/rebar.c b/drivers/pci/rebar.c new file mode 100644 index 000000000000..39f8cf3b70d5 --- /dev/null +++ b/drivers/pci/rebar.c @@ -0,0 +1,312 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * PCI Resizable BAR Extended Capability handling. + */ + +#include <linux/bits.h> +#include <linux/bitfield.h> +#include <linux/bitops.h> +#include <linux/errno.h> +#include <linux/export.h> +#include <linux/ioport.h> +#include <linux/log2.h> +#include <linux/pci.h> +#include <linux/sizes.h> +#include <linux/types.h> + +#include "pci.h" + +#define PCI_REBAR_MIN_SIZE ((resource_size_t)SZ_1M) + +/** + * pci_rebar_bytes_to_size - Convert size in bytes to PCI BAR Size + * @bytes: size in bytes + * + * Convert size in bytes to encoded BAR Size in Resizable BAR Capability + * (PCIe r6.2, sec. 7.8.6.3). + * + * Return: encoded BAR Size as defined in the PCIe spec (0=1MB, 31=128TB) + */ +int pci_rebar_bytes_to_size(u64 bytes) +{ + int rebar_minsize = ilog2(PCI_REBAR_MIN_SIZE); + + bytes = roundup_pow_of_two(bytes); + + return max(ilog2(bytes), rebar_minsize) - rebar_minsize; +} +EXPORT_SYMBOL_GPL(pci_rebar_bytes_to_size); + +/** + * pci_rebar_size_to_bytes - Convert encoded BAR Size to size in bytes + * @size: encoded BAR Size as defined in the PCIe spec (0=1MB, 31=128TB) + * + * Return: BAR size in bytes + */ +resource_size_t pci_rebar_size_to_bytes(int size) +{ + return 1ULL << (size + ilog2(PCI_REBAR_MIN_SIZE)); +} +EXPORT_SYMBOL_GPL(pci_rebar_size_to_bytes); + +void pci_rebar_init(struct pci_dev *pdev) +{ + pdev->rebar_cap = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_REBAR); +} + +/** + * pci_rebar_find_pos - find position of resize control reg for BAR + * @pdev: PCI device + * @bar: BAR to find + * + * Helper to find the position of the control register for a BAR. + * + * Return: + * * %-ENOTSUPP if resizable BARs are not supported at all, + * * %-ENOENT if no control register for the BAR could be found. + */ +static int pci_rebar_find_pos(struct pci_dev *pdev, int bar) +{ + unsigned int pos, nbars, i; + u32 ctrl; + + if (pci_resource_is_iov(bar)) { + pos = pci_iov_vf_rebar_cap(pdev); + bar = pci_resource_num_to_vf_bar(bar); + } else { + pos = pdev->rebar_cap; + } + + if (!pos) + return -ENOTSUPP; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + nbars = FIELD_GET(PCI_REBAR_CTRL_NBAR_MASK, ctrl); + + for (i = 0; i < nbars; i++, pos += 8) { + int bar_idx; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + bar_idx = FIELD_GET(PCI_REBAR_CTRL_BAR_IDX, ctrl); + if (bar_idx == bar) + return pos; + } + + return -ENOENT; +} + +/** + * pci_rebar_get_possible_sizes - get possible sizes for Resizable BAR + * @pdev: PCI device + * @bar: BAR to query + * + * Get the possible sizes of a resizable BAR as bitmask. + * + * Return: A bitmask of possible sizes (bit 0=1MB, bit 31=128TB), or %0 if + * BAR isn't resizable. + */ +u64 pci_rebar_get_possible_sizes(struct pci_dev *pdev, int bar) +{ + int pos; + u32 cap; + + pos = pci_rebar_find_pos(pdev, bar); + if (pos < 0) + return 0; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CAP, &cap); + cap = FIELD_GET(PCI_REBAR_CAP_SIZES, cap); + + /* Sapphire RX 5600 XT Pulse has an invalid cap dword for BAR 0 */ + if (pdev->vendor == PCI_VENDOR_ID_ATI && pdev->device == 0x731f && + bar == 0 && cap == 0x700) + return 0x3f00; + + return cap; +} +EXPORT_SYMBOL(pci_rebar_get_possible_sizes); + +/** + * pci_rebar_size_supported - check if size is supported for BAR + * @pdev: PCI device + * @bar: BAR to check + * @size: encoded size as defined in the PCIe spec (0=1MB, 31=128TB) + * + * Return: %true if @bar is resizable and @size is supported, otherwise + * %false. + */ +bool pci_rebar_size_supported(struct pci_dev *pdev, int bar, int size) +{ + u64 sizes = pci_rebar_get_possible_sizes(pdev, bar); + + if (size < 0 || size > ilog2(SZ_128T) - ilog2(PCI_REBAR_MIN_SIZE)) + return false; + + return BIT(size) & sizes; +} +EXPORT_SYMBOL_GPL(pci_rebar_size_supported); + +/** + * pci_rebar_get_max_size - get the maximum supported size of a BAR + * @pdev: PCI device + * @bar: BAR to query + * + * Get the largest supported size of a resizable BAR as a size. + * + * Return: the encoded maximum BAR size as defined in the PCIe spec + * (0=1MB, 31=128TB), or %-NOENT on error. + */ +int pci_rebar_get_max_size(struct pci_dev *pdev, int bar) +{ + u64 sizes; + + sizes = pci_rebar_get_possible_sizes(pdev, bar); + if (!sizes) + return -ENOENT; + + return __fls(sizes); +} +EXPORT_SYMBOL_GPL(pci_rebar_get_max_size); + +/** + * pci_rebar_get_current_size - get the current size of a Resizable BAR + * @pdev: PCI device + * @bar: BAR to get the size from + * + * Read the current size of a BAR from the Resizable BAR config. + * + * Return: BAR Size if @bar is resizable (0=1MB, 31=128TB), or negative on + * error. + */ +int pci_rebar_get_current_size(struct pci_dev *pdev, int bar) +{ + int pos; + u32 ctrl; + + pos = pci_rebar_find_pos(pdev, bar); + if (pos < 0) + return pos; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + return FIELD_GET(PCI_REBAR_CTRL_BAR_SIZE, ctrl); +} + +/** + * pci_rebar_set_size - set a new size for a Resizable BAR + * @pdev: PCI device + * @bar: BAR to set size to + * @size: new size as defined in the PCIe spec (0=1MB, 31=128TB) + * + * Set the new size of a BAR as defined in the spec. + * + * Return: %0 if resizing was successful, or negative on error. + */ +int pci_rebar_set_size(struct pci_dev *pdev, int bar, int size) +{ + int pos; + u32 ctrl; + + pos = pci_rebar_find_pos(pdev, bar); + if (pos < 0) + return pos; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; + ctrl |= FIELD_PREP(PCI_REBAR_CTRL_BAR_SIZE, size); + pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); + + if (pci_resource_is_iov(bar)) + pci_iov_resource_set_size(pdev, bar, size); + + return 0; +} + +void pci_restore_rebar_state(struct pci_dev *pdev) +{ + unsigned int pos, nbars, i; + u32 ctrl; + + pos = pdev->rebar_cap; + if (!pos) + return; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + nbars = FIELD_GET(PCI_REBAR_CTRL_NBAR_MASK, ctrl); + + for (i = 0; i < nbars; i++, pos += 8) { + struct resource *res; + int bar_idx, size; + + pci_read_config_dword(pdev, pos + PCI_REBAR_CTRL, &ctrl); + bar_idx = ctrl & PCI_REBAR_CTRL_BAR_IDX; + res = pci_resource_n(pdev, bar_idx); + size = pci_rebar_bytes_to_size(resource_size(res)); + ctrl &= ~PCI_REBAR_CTRL_BAR_SIZE; + ctrl |= FIELD_PREP(PCI_REBAR_CTRL_BAR_SIZE, size); + pci_write_config_dword(pdev, pos + PCI_REBAR_CTRL, ctrl); + } +} + +static bool pci_resize_is_memory_decoding_enabled(struct pci_dev *dev, + int resno) +{ + u16 cmd; + + if (pci_resource_is_iov(resno)) + return pci_iov_is_memory_decoding_enabled(dev); + + pci_read_config_word(dev, PCI_COMMAND, &cmd); + + return cmd & PCI_COMMAND_MEMORY; +} + +void pci_resize_resource_set_size(struct pci_dev *dev, int resno, int size) +{ + resource_size_t res_size = pci_rebar_size_to_bytes(size); + struct resource *res = pci_resource_n(dev, resno); + + if (pci_resource_is_iov(resno)) + res_size *= pci_sriov_get_totalvfs(dev); + + resource_set_size(res, res_size); +} + +/** + * pci_resize_resource - reconfigure a Resizable BAR and resources + * @dev: the PCI device + * @resno: index of the BAR to be resized + * @size: new size as defined in the spec (0=1MB, 31=128TB) + * @exclude_bars: a mask of BARs that should not be released + * + * Reconfigure @resno to @size and re-run resource assignment algorithm + * with the new size. + * + * Prior to resize, release @dev resources that share a bridge window with + * @resno. This unpins the bridge window resource to allow changing it. + * + * The caller may prevent releasing a particular BAR by providing + * @exclude_bars mask, but this may result in the resize operation failing + * due to insufficient space. + * + * Return: 0 on success, or negative on error. In case of an error, the + * resources are restored to their original places. + */ +int pci_resize_resource(struct pci_dev *dev, int resno, int size, + int exclude_bars) +{ + struct pci_host_bridge *host; + + /* Check if we must preserve the firmware's resource assignment */ + host = pci_find_host_bridge(dev->bus); + if (host->preserve_config) + return -ENOTSUPP; + + if (pci_resize_is_memory_decoding_enabled(dev, resno)) + return -EBUSY; + + if (!pci_rebar_size_supported(dev, resno, size)) + return -EINVAL; + + return pci_do_resource_release_and_resize(dev, resno, size, exclude_bars); +} +EXPORT_SYMBOL(pci_resize_resource); diff --git a/drivers/pci/remove.c b/drivers/pci/remove.c index 445afdfa6498..e9d519993853 100644 --- a/drivers/pci/remove.c +++ b/drivers/pci/remove.c @@ -17,23 +17,6 @@ static void pci_free_resources(struct pci_dev *dev) } } -static void pci_pwrctrl_unregister(struct device *dev) -{ - struct device_node *np; - struct platform_device *pdev; - - np = dev_of_node(dev); - if (!np) - return; - - pdev = of_find_device_by_node(np); - if (!pdev) - return; - - of_device_unregister(pdev); - of_node_clear_flag(np, OF_POPULATED); -} - static void pci_stop_dev(struct pci_dev *dev) { pci_pme_active(dev, false); @@ -55,6 +38,12 @@ static void pci_destroy_dev(struct pci_dev *dev) pci_doe_sysfs_teardown(dev); pci_npem_remove(dev); + /* + * While device is in D0 drop the device from TSM link operations + * including unbind and disconnect (IDE + SPDM teardown). + */ + pci_tsm_destroy(dev); + device_del(&dev->dev); down_write(&pci_bus_sem); @@ -62,9 +51,9 @@ static void pci_destroy_dev(struct pci_dev *dev) up_write(&pci_bus_sem); pci_doe_destroy(dev); + pci_ide_destroy(dev); pcie_aspm_exit_link_state(dev); pci_bridge_d3_update(dev); - pci_pwrctrl_unregister(&dev->dev); pci_free_resources(dev); put_device(&dev->dev); } @@ -138,6 +127,7 @@ static void pci_remove_bus_device(struct pci_dev *dev) */ void pci_stop_and_remove_bus_device(struct pci_dev *dev) { + lockdep_assert_held(&pci_rescan_remove_lock); pci_stop_bus_device(dev); pci_remove_bus_device(dev); } diff --git a/drivers/pci/search.c b/drivers/pci/search.c index 53840634fbfc..e3d3177fce54 100644 --- a/drivers/pci/search.c +++ b/drivers/pci/search.c @@ -86,6 +86,8 @@ int pci_for_each_dma_alias(struct pci_dev *pdev, case PCI_EXP_TYPE_DOWNSTREAM: continue; case PCI_EXP_TYPE_PCI_BRIDGE: + if (tmp->dev_flags & PCI_DEV_FLAGS_PCI_BRIDGE_NO_ALIAS) + continue; ret = fn(tmp, PCI_DEVID(tmp->subordinate->number, PCI_DEVFN(0, 0)), data); @@ -282,6 +284,45 @@ static struct pci_dev *pci_get_dev_by_id(const struct pci_device_id *id, return pdev; } +static struct pci_dev *pci_get_dev_by_id_reverse(const struct pci_device_id *id, + struct pci_dev *from) +{ + struct device *dev; + struct device *dev_start = NULL; + struct pci_dev *pdev = NULL; + + if (from) + dev_start = &from->dev; + dev = bus_find_device_reverse(&pci_bus_type, dev_start, (void *)id, + match_pci_dev_by_id); + if (dev) + pdev = to_pci_dev(dev); + pci_dev_put(from); + return pdev; +} + +enum pci_search_direction { + PCI_SEARCH_FORWARD, + PCI_SEARCH_REVERSE, +}; + +static struct pci_dev *__pci_get_subsys(unsigned int vendor, unsigned int device, + unsigned int ss_vendor, unsigned int ss_device, + struct pci_dev *from, enum pci_search_direction dir) +{ + struct pci_device_id id = { + .vendor = vendor, + .device = device, + .subvendor = ss_vendor, + .subdevice = ss_device, + }; + + if (dir == PCI_SEARCH_FORWARD) + return pci_get_dev_by_id(&id, from); + else + return pci_get_dev_by_id_reverse(&id, from); +} + /** * pci_get_subsys - begin or continue searching for a PCI device by vendor/subvendor/device/subdevice id * @vendor: PCI vendor id to match, or %PCI_ANY_ID to match all vendor ids @@ -302,14 +343,8 @@ struct pci_dev *pci_get_subsys(unsigned int vendor, unsigned int device, unsigned int ss_vendor, unsigned int ss_device, struct pci_dev *from) { - struct pci_device_id id = { - .vendor = vendor, - .device = device, - .subvendor = ss_vendor, - .subdevice = ss_device, - }; - - return pci_get_dev_by_id(&id, from); + return __pci_get_subsys(vendor, device, ss_vendor, ss_device, from, + PCI_SEARCH_FORWARD); } EXPORT_SYMBOL(pci_get_subsys); @@ -334,6 +369,19 @@ struct pci_dev *pci_get_device(unsigned int vendor, unsigned int device, } EXPORT_SYMBOL(pci_get_device); +/* + * Same semantics as pci_get_device(), except walks the PCI device list + * in reverse discovery order. + */ +struct pci_dev *pci_get_device_reverse(unsigned int vendor, + unsigned int device, + struct pci_dev *from) +{ + return __pci_get_subsys(vendor, device, PCI_ANY_ID, PCI_ANY_ID, from, + PCI_SEARCH_REVERSE); +} +EXPORT_SYMBOL(pci_get_device_reverse); + /** * pci_get_class - begin or continue searching for a PCI device by class * @class: search for a PCI device with this class designation diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 54d6f4fa3ce1..61f769aaa2f6 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -14,9 +14,12 @@ * tighter packing. Prefetchable range support. */ +#include <linux/align.h> #include <linux/bitops.h> +#include <linux/bug.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/minmax.h> #include <linux/module.h> #include <linux/pci.h> #include <linux/errno.h> @@ -28,6 +31,10 @@ #include <linux/acpi.h> #include "pci.h" +#define PCI_RES_TYPE_MASK \ + (IORESOURCE_IO | IORESOURCE_MEM | IORESOURCE_PREFETCH |\ + IORESOURCE_MEM_64) + unsigned int pci_flags; EXPORT_SYMBOL_GPL(pci_flags); @@ -42,7 +49,7 @@ struct pci_dev_resource { unsigned long flags; }; -static void free_list(struct list_head *head) +static void pci_dev_res_free_list(struct list_head *head) { struct pci_dev_resource *dev_res, *tmp; @@ -53,20 +60,20 @@ static void free_list(struct list_head *head) } /** - * add_to_list() - Add a new resource tracker to the list + * pci_dev_res_add_to_list() - Add a new resource tracker to the list * @head: Head of the list * @dev: Device to which the resource belongs * @res: Resource to be tracked * @add_size: Additional size to be optionally added to the resource * @min_align: Minimum memory window alignment */ -static int add_to_list(struct list_head *head, struct pci_dev *dev, - struct resource *res, resource_size_t add_size, - resource_size_t min_align) +int pci_dev_res_add_to_list(struct list_head *head, struct pci_dev *dev, + struct resource *res, resource_size_t add_size, + resource_size_t min_align) { struct pci_dev_resource *tmp; - tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + tmp = kzalloc_obj(*tmp); if (!tmp) return -ENOMEM; @@ -83,7 +90,8 @@ static int add_to_list(struct list_head *head, struct pci_dev *dev, return 0; } -static void remove_from_list(struct list_head *head, struct resource *res) +static void pci_dev_res_remove_from_list(struct list_head *head, + struct resource *res) { struct pci_dev_resource *dev_res, *tmp; @@ -118,22 +126,161 @@ static resource_size_t get_res_add_size(struct list_head *head, return dev_res ? dev_res->add_size : 0; } -static resource_size_t get_res_add_align(struct list_head *head, - struct resource *res) -{ - struct pci_dev_resource *dev_res; - - dev_res = res_to_dev_res(head, res); - return dev_res ? dev_res->min_align : 0; -} - -static void restore_dev_resource(struct pci_dev_resource *dev_res) +static void pci_dev_res_restore(struct pci_dev_resource *dev_res) { struct resource *res = dev_res->res; + struct pci_dev *dev = dev_res->dev; + int idx = pci_resource_num(dev, res); + const char *res_name = pci_resource_name(dev, idx); + + if (WARN_ON_ONCE(resource_assigned(res))) + return; res->start = dev_res->start; res->end = dev_res->end; res->flags = dev_res->flags; + + pci_dbg(dev, "%s %pR: resource restored\n", res_name, res); +} + +/* + * Helper function for sizing routines. Assigned resources have non-NULL + * parent resource. + * + * Return first unassigned resource of the correct type. If there is none, + * return first assigned resource of the correct type. If none of the + * above, return NULL. + * + * Returning an assigned resource of the correct type allows the caller to + * distinguish between already assigned and no resource of the correct type. + */ +static struct resource *find_bus_resource_of_type(struct pci_bus *bus, + unsigned long type_mask, + unsigned long type) +{ + struct resource *r, *r_assigned = NULL; + + pci_bus_for_each_resource(bus, r) { + if (!r || r == &ioport_resource || r == &iomem_resource) + continue; + + if ((r->flags & type_mask) != type) + continue; + + if (!resource_assigned(r)) + return r; + if (!r_assigned) + r_assigned = r; + } + return r_assigned; +} + +/** + * pbus_select_window_for_type - Select bridge window for a resource type + * @bus: PCI bus + * @type: Resource type (resource flags can be passed as is) + * + * Select the bridge window based on a resource @type. + * + * For memory resources, the selection is done as follows: + * + * Any non-prefetchable resource is put into the non-prefetchable window. + * + * If there is no prefetchable MMIO window, put all memory resources into the + * non-prefetchable window. + * + * If there's a 64-bit prefetchable MMIO window, put all 64-bit prefetchable + * resources into it and place 32-bit prefetchable memory into the + * non-prefetchable window. + * + * Otherwise, put all prefetchable resources into the prefetchable window. + * + * Return: the bridge window resource or NULL if no bridge window is found. + */ +static struct resource *pbus_select_window_for_type(struct pci_bus *bus, + unsigned long type) +{ + int iores_type = type & IORESOURCE_TYPE_BITS; /* w/o 64bit & pref */ + struct resource *mmio, *mmio_pref, *win; + + type &= PCI_RES_TYPE_MASK; /* with 64bit & pref */ + + if ((iores_type != IORESOURCE_IO) && (iores_type != IORESOURCE_MEM)) + return NULL; + + if (pci_is_root_bus(bus)) { + win = find_bus_resource_of_type(bus, type, type); + if (win) + return win; + + type &= ~IORESOURCE_MEM_64; + win = find_bus_resource_of_type(bus, type, type); + if (win) + return win; + + type &= ~IORESOURCE_PREFETCH; + return find_bus_resource_of_type(bus, type, type); + } + + switch (iores_type) { + case IORESOURCE_IO: + win = pci_bus_resource_n(bus, PCI_BUS_BRIDGE_IO_WINDOW); + if (win && (win->flags & IORESOURCE_IO)) + return win; + return NULL; + + case IORESOURCE_MEM: + mmio = pci_bus_resource_n(bus, PCI_BUS_BRIDGE_MEM_WINDOW); + mmio_pref = pci_bus_resource_n(bus, PCI_BUS_BRIDGE_PREF_MEM_WINDOW); + + if (mmio && !(mmio->flags & IORESOURCE_MEM)) + mmio = NULL; + if (mmio_pref && !(mmio_pref->flags & IORESOURCE_MEM)) + mmio_pref = NULL; + + if (!(type & IORESOURCE_PREFETCH) || !mmio_pref) + return mmio; + + if ((type & IORESOURCE_MEM_64) || + !(mmio_pref->flags & IORESOURCE_MEM_64)) + return mmio_pref; + + return mmio; + default: + return NULL; + } +} + +/** + * pbus_select_window - Select bridge window for a resource + * @bus: PCI bus + * @res: Resource + * + * Select the bridge window for @res. If the resource is already assigned, + * return the current bridge window. + * + * For memory resources, the selection is done as follows: + * + * Any non-prefetchable resource is put into the non-prefetchable window. + * + * If there is no prefetchable MMIO window, put all memory resources into the + * non-prefetchable window. + * + * If there's a 64-bit prefetchable MMIO window, put all 64-bit prefetchable + * resources into it and place 32-bit prefetchable memory into the + * non-prefetchable window. + * + * Otherwise, put all prefetchable resources into the prefetchable window. + * + * Return: the bridge window resource or NULL if no bridge window is found. + */ +struct resource *pbus_select_window(struct pci_bus *bus, + const struct resource *res) +{ + if (resource_assigned(res)) + return res->parent; + + return pbus_select_window_for_type(bus, res->flags); } static bool pdev_resources_assignable(struct pci_dev *dev) @@ -154,6 +301,30 @@ static bool pdev_resources_assignable(struct pci_dev *dev) return true; } +static bool pdev_resource_assignable(struct pci_dev *dev, struct resource *res) +{ + int idx = pci_resource_num(dev, res); + + if (!res->flags) + return false; + + if (pci_resource_is_bridge_win(idx) && res->flags & IORESOURCE_DISABLED) + return false; + + return true; +} + +static bool pdev_resource_should_fit(struct pci_dev *dev, struct resource *res) +{ + if (resource_assigned(res)) + return false; + + if (res->flags & IORESOURCE_PCI_FIXED) + return false; + + return pdev_resource_assignable(dev, res); +} + /* Sort resources by alignment */ static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head) { @@ -169,10 +340,7 @@ static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head) resource_size_t r_align; struct list_head *n; - if (r->flags & IORESOURCE_PCI_FIXED) - continue; - - if (!(r->flags) || r->parent) + if (!pdev_resource_should_fit(dev, r)) continue; r_align = pci_resource_alignment(dev, r); @@ -182,11 +350,14 @@ static void pdev_sort_resources(struct pci_dev *dev, struct list_head *head) continue; } - tmp = kzalloc(sizeof(*tmp), GFP_KERNEL); + tmp = kzalloc_obj(*tmp); if (!tmp) panic("%s: kzalloc() failed!\n", __func__); tmp->res = r; tmp->dev = dev; + tmp->start = r->start; + tmp->end = r->end; + tmp->flags = r->flags; /* Fallback is smallest one or list is empty */ n = head; @@ -214,12 +385,24 @@ bool pci_resource_is_optional(const struct pci_dev *dev, int resno) return true; if (resno == PCI_ROM_RESOURCE && !(res->flags & IORESOURCE_ROM_ENABLE)) return true; + if (pci_resource_is_bridge_win(resno) && !resource_size(res)) + return true; return false; } -static inline void reset_resource(struct resource *res) +static void reset_resource(struct pci_dev *dev, struct resource *res) { + int idx = pci_resource_num(dev, res); + const char *res_name = pci_resource_name(dev, idx); + + if (pci_resource_is_bridge_win(idx)) { + res->flags |= IORESOURCE_UNSET; + return; + } + + pci_dbg(dev, "%s %pR: resetting resource\n", res_name, res); + res->start = 0; res->end = 0; res->flags = 0; @@ -240,7 +423,6 @@ static void reassign_resources_sorted(struct list_head *realloc_head, struct list_head *head) { struct pci_dev_resource *add_res, *tmp; - struct pci_dev_resource *dev_res; struct pci_dev *dev; struct resource *res; const char *res_name; @@ -248,8 +430,6 @@ static void reassign_resources_sorted(struct list_head *realloc_head, int idx; list_for_each_entry_safe(add_res, tmp, realloc_head, list) { - bool found_match = false; - res = add_res->res; dev = add_res->dev; idx = pci_resource_num(dev, res); @@ -258,24 +438,18 @@ static void reassign_resources_sorted(struct list_head *realloc_head, * Skip resource that failed the earlier assignment and is * not optional as it would just fail again. */ - if (!res->parent && resource_size(res) && + if (!resource_assigned(res) && resource_size(res) && !pci_resource_is_optional(dev, idx)) goto out; /* Skip this resource if not found in head list */ - list_for_each_entry(dev_res, head, list) { - if (dev_res->res == res) { - found_match = true; - break; - } - } - if (!found_match) /* Just skip */ + if (!res_to_dev_res(head, res)) continue; res_name = pci_resource_name(dev, idx); add_size = add_res->add_size; align = add_res->min_align; - if (!res->parent) { + if (!resource_assigned(res)) { resource_set_range(res, align, resource_size(res) + add_size); if (pci_assign_resource(dev, idx)) { @@ -283,7 +457,7 @@ static void reassign_resources_sorted(struct list_head *realloc_head, "%s %pR: ignoring failure in optional allocation\n", res_name, res); } - } else if (add_size > 0) { + } else if (add_size > 0 || !IS_ALIGNED(res->start, align)) { res->flags |= add_res->flags & (IORESOURCE_STARTALIGN|IORESOURCE_SIZEALIGN); if (pci_reassign_resource(dev, idx, add_size, align)) @@ -332,9 +506,9 @@ static void assign_requested_resources_sorted(struct list_head *head, if (pci_assign_resource(dev, idx)) { if (fail_head) { - add_to_list(fail_head, dev, res, - 0 /* don't care */, - 0 /* don't care */); + pci_dev_res_add_to_list(fail_head, dev, res, + 0 /* don't care */, + 0 /* don't care */); } } } @@ -381,13 +555,19 @@ static bool pci_need_to_release(unsigned long mask, struct resource *res) } /* Return: @true if assignment of a required resource failed. */ -static bool pci_required_resource_failed(struct list_head *fail_head) +static bool pci_required_resource_failed(struct list_head *fail_head, + unsigned long type) { struct pci_dev_resource *fail_res; + type &= PCI_RES_TYPE_MASK; + list_for_each_entry(fail_res, fail_head, list) { int idx = pci_resource_num(fail_res->dev, fail_res->res); + if (type && (fail_res->flags & PCI_RES_TYPE_MASK) != type) + continue; + if (!pci_resource_is_optional(fail_res->dev, idx)) return true; } @@ -425,13 +605,11 @@ static void __assign_resources_sorted(struct list_head *head, LIST_HEAD(local_fail_head); LIST_HEAD(dummy_head); struct pci_dev_resource *save_res; - struct pci_dev_resource *dev_res, *tmp_res, *dev_res2; + struct pci_dev_resource *dev_res, *tmp_res, *dev_res2, *addsize_res; struct resource *res; struct pci_dev *dev; - const char *res_name; - int idx; unsigned long fail_type; - resource_size_t add_align, align; + resource_size_t align; if (!realloc_head) realloc_head = &dummy_head; @@ -442,8 +620,9 @@ static void __assign_resources_sorted(struct list_head *head, /* Save original start, end, flags etc at first */ list_for_each_entry(dev_res, head, list) { - if (add_to_list(&save_head, dev_res->dev, dev_res->res, 0, 0)) { - free_list(&save_head); + if (pci_dev_res_add_to_list(&save_head, dev_res->dev, + dev_res->res, 0, 0)) { + pci_dev_res_free_list(&save_head); goto assign; } } @@ -452,8 +631,11 @@ static void __assign_resources_sorted(struct list_head *head, list_for_each_entry_safe(dev_res, tmp_res, head, list) { res = dev_res->res; - res->end += get_res_add_size(realloc_head, res); + addsize_res = res_to_dev_res(realloc_head, res); + if (!addsize_res) + continue; + res->end += addsize_res->add_size; /* * There are two kinds of additional resources in the list: * 1. bridge resource -- IORESOURCE_STARTALIGN @@ -463,8 +645,8 @@ static void __assign_resources_sorted(struct list_head *head, if (!(res->flags & IORESOURCE_STARTALIGN)) continue; - add_align = get_res_add_align(realloc_head, res); - + if (addsize_res->min_align <= res->start) + continue; /* * The "head" list is sorted by alignment so resources with * bigger alignment will be assigned first. After we @@ -472,17 +654,15 @@ static void __assign_resources_sorted(struct list_head *head, * need to reorder the list by alignment to make it * consistent. */ - if (add_align > res->start) { - resource_set_range(res, add_align, resource_size(res)); - - list_for_each_entry(dev_res2, head, list) { - align = pci_resource_alignment(dev_res2->dev, - dev_res2->res); - if (add_align > align) { - list_move_tail(&dev_res->list, - &dev_res2->list); - break; - } + resource_set_range(res, addsize_res->min_align, + resource_size(res)); + + list_for_each_entry(dev_res2, head, list) { + align = pci_resource_alignment(dev_res2->dev, + dev_res2->res); + if (addsize_res->min_align > align) { + list_move_tail(&dev_res->list, &dev_res2->list); + break; } } @@ -495,24 +675,25 @@ assign: if (list_empty(&local_fail_head)) { /* Remove head list from realloc_head list */ list_for_each_entry(dev_res, head, list) - remove_from_list(realloc_head, dev_res->res); - free_list(&save_head); + pci_dev_res_remove_from_list(realloc_head, + dev_res->res); + pci_dev_res_free_list(&save_head); goto out; } /* Without realloc_head and only optional fails, nothing more to do. */ - if (!pci_required_resource_failed(&local_fail_head) && + if (!pci_required_resource_failed(&local_fail_head, 0) && list_empty(realloc_head)) { list_for_each_entry(save_res, &save_head, list) { struct resource *res = save_res->res; - if (res->parent) + if (resource_assigned(res)) continue; - restore_dev_resource(save_res); + pci_dev_res_restore(save_res); } - free_list(&local_fail_head); - free_list(&save_head); + pci_dev_res_free_list(&local_fail_head); + pci_dev_res_free_list(&save_head); goto out; } @@ -522,34 +703,29 @@ assign: list_for_each_entry_safe(dev_res, tmp_res, head, list) { res = dev_res->res; - if (res->parent && !pci_need_to_release(fail_type, res)) { + if (resource_assigned(res) && + !pci_need_to_release(fail_type, res)) { /* Remove it from realloc_head list */ - remove_from_list(realloc_head, res); - remove_from_list(&save_head, res); + pci_dev_res_remove_from_list(realloc_head, res); + pci_dev_res_remove_from_list(&save_head, res); list_del(&dev_res->list); kfree(dev_res); } } - free_list(&local_fail_head); + pci_dev_res_free_list(&local_fail_head); /* Release assigned resource */ list_for_each_entry(dev_res, head, list) { res = dev_res->res; dev = dev_res->dev; - if (!res->parent) - continue; - - idx = pci_resource_num(dev, res); - res_name = pci_resource_name(dev, idx); - pci_dbg(dev, "%s %pR: releasing\n", res_name, res); - - release_resource(res); + pci_release_resource(dev, pci_resource_num(dev, res)); + pci_dev_res_restore(dev_res); } /* Restore start/end/flags from saved list */ list_for_each_entry(save_res, &save_head, list) - restore_dev_resource(save_res); - free_list(&save_head); + pci_dev_res_restore(save_res); + pci_dev_res_free_list(&save_head); /* Satisfy the must-have resource requests */ assign_requested_resources_sorted(head, NULL, false); @@ -564,19 +740,19 @@ out: res = dev_res->res; dev = dev_res->dev; - if (res->parent) + if (resource_assigned(res)) continue; if (fail_head) { - add_to_list(fail_head, dev, res, - 0 /* don't care */, - 0 /* don't care */); + pci_dev_res_add_to_list(fail_head, dev, res, + 0 /* don't care */, + 0 /* don't care */); } - reset_resource(res); + reset_resource(dev, res); } - free_list(head); + pci_dev_res_free_list(head); } static void pdev_assign_resources_sorted(struct pci_dev *dev, @@ -603,61 +779,6 @@ static void pbus_assign_resources_sorted(const struct pci_bus *bus, __assign_resources_sorted(&head, realloc_head, fail_head); } -void pci_setup_cardbus(struct pci_bus *bus) -{ - struct pci_dev *bridge = bus->self; - struct resource *res; - struct pci_bus_region region; - - pci_info(bridge, "CardBus bridge to %pR\n", - &bus->busn_res); - - res = bus->resource[0]; - pcibios_resource_to_bus(bridge->bus, ®ion, res); - if (res->flags & IORESOURCE_IO) { - /* - * The IO resource is allocated a range twice as large as it - * would normally need. This allows us to set both IO regs. - */ - pci_info(bridge, " bridge window %pR\n", res); - pci_write_config_dword(bridge, PCI_CB_IO_BASE_0, - region.start); - pci_write_config_dword(bridge, PCI_CB_IO_LIMIT_0, - region.end); - } - - res = bus->resource[1]; - pcibios_resource_to_bus(bridge->bus, ®ion, res); - if (res->flags & IORESOURCE_IO) { - pci_info(bridge, " bridge window %pR\n", res); - pci_write_config_dword(bridge, PCI_CB_IO_BASE_1, - region.start); - pci_write_config_dword(bridge, PCI_CB_IO_LIMIT_1, - region.end); - } - - res = bus->resource[2]; - pcibios_resource_to_bus(bridge->bus, ®ion, res); - if (res->flags & IORESOURCE_MEM) { - pci_info(bridge, " bridge window %pR\n", res); - pci_write_config_dword(bridge, PCI_CB_MEMORY_BASE_0, - region.start); - pci_write_config_dword(bridge, PCI_CB_MEMORY_LIMIT_0, - region.end); - } - - res = bus->resource[3]; - pcibios_resource_to_bus(bridge->bus, ®ion, res); - if (res->flags & IORESOURCE_MEM) { - pci_info(bridge, " bridge window %pR\n", res); - pci_write_config_dword(bridge, PCI_CB_MEMORY_BASE_1, - region.start); - pci_write_config_dword(bridge, PCI_CB_MEMORY_LIMIT_1, - region.end); - } -} -EXPORT_SYMBOL(pci_setup_cardbus); - /* * Initialize bridges with base/limit values we have collected. PCI-to-PCI * Bridge Architecture Specification rev. 1.1 (1998) requires that if there @@ -689,7 +810,7 @@ static void pci_setup_bridge_io(struct pci_dev *bridge) res = &bridge->resource[PCI_BRIDGE_IO_WINDOW]; res_name = pci_resource_name(bridge, PCI_BRIDGE_IO_WINDOW); pcibios_resource_to_bus(bridge->bus, ®ion, res); - if (res->flags & IORESOURCE_IO) { + if (resource_assigned(res) && res->flags & IORESOURCE_IO) { pci_read_config_word(bridge, PCI_IO_BASE, &l); io_base_lo = (region.start >> 8) & io_mask; io_limit_lo = (region.end >> 8) & io_mask; @@ -721,7 +842,7 @@ static void pci_setup_bridge_mmio(struct pci_dev *bridge) res = &bridge->resource[PCI_BRIDGE_MEM_WINDOW]; res_name = pci_resource_name(bridge, PCI_BRIDGE_MEM_WINDOW); pcibios_resource_to_bus(bridge->bus, ®ion, res); - if (res->flags & IORESOURCE_MEM) { + if (resource_assigned(res) && res->flags & IORESOURCE_MEM) { l = (region.start >> 16) & 0xfff0; l |= region.end & 0xfff00000; pci_info(bridge, " %s %pR\n", res_name, res); @@ -750,7 +871,7 @@ static void pci_setup_bridge_mmio_pref(struct pci_dev *bridge) res = &bridge->resource[PCI_BRIDGE_PREF_MEM_WINDOW]; res_name = pci_resource_name(bridge, PCI_BRIDGE_PREF_MEM_WINDOW); pcibios_resource_to_bus(bridge->bus, ®ion, res); - if (res->flags & IORESOURCE_PREFETCH) { + if (resource_assigned(res) && res->flags & IORESOURCE_PREFETCH) { l = (region.start >> 16) & 0xfff0; l |= region.end & 0xfff00000; if (res->flags & IORESOURCE_MEM_64) { @@ -772,8 +893,7 @@ static void __pci_setup_bridge(struct pci_bus *bus, unsigned long type) { struct pci_dev *bridge = bus->self; - pci_info(bridge, "PCI bridge to %pR\n", - &bus->busn_res); + pci_info(bridge, "PCI bridge to %pR\n", &bus->busn_res); if (type & IORESOURCE_IO) pci_setup_bridge_io(bridge); @@ -787,6 +907,23 @@ static void __pci_setup_bridge(struct pci_bus *bus, unsigned long type) pci_write_config_word(bridge, PCI_BRIDGE_CONTROL, bus->bridge_ctl); } +static void pci_setup_one_bridge_window(struct pci_dev *bridge, int resno) +{ + switch (resno) { + case PCI_BRIDGE_IO_WINDOW: + pci_setup_bridge_io(bridge); + break; + case PCI_BRIDGE_MEM_WINDOW: + pci_setup_bridge_mmio(bridge); + break; + case PCI_BRIDGE_PREF_MEM_WINDOW: + pci_setup_bridge_mmio_pref(bridge); + break; + default: + return; + } +} + void __weak pcibios_setup_bridge(struct pci_bus *bus, unsigned long type) { } @@ -803,7 +940,9 @@ static void pci_setup_bridge(struct pci_bus *bus) int pci_claim_bridge_resource(struct pci_dev *bridge, int i) { - if (i < PCI_BRIDGE_RESOURCES || i > PCI_BRIDGE_RESOURCE_END) + int ret = -EINVAL; + + if (!pci_resource_is_bridge_win(i)) return 0; if (pci_claim_resource(bridge, i) == 0) @@ -812,27 +951,16 @@ int pci_claim_bridge_resource(struct pci_dev *bridge, int i) if ((bridge->class >> 8) != PCI_CLASS_BRIDGE_PCI) return 0; - if (!pci_bus_clip_resource(bridge, i)) - return -EINVAL; /* Clipping didn't change anything */ - - switch (i) { - case PCI_BRIDGE_IO_WINDOW: - pci_setup_bridge_io(bridge); - break; - case PCI_BRIDGE_MEM_WINDOW: - pci_setup_bridge_mmio(bridge); - break; - case PCI_BRIDGE_PREF_MEM_WINDOW: - pci_setup_bridge_mmio_pref(bridge); - break; - default: + if (i > PCI_BRIDGE_PREF_MEM_WINDOW) return -EINVAL; - } - if (pci_claim_resource(bridge, i) == 0) - return 0; /* Claimed a smaller window */ + /* Try to clip the resource and claim the smaller window */ + if (pci_bus_clip_resource(bridge, i)) + ret = pci_claim_resource(bridge, i); - return -EINVAL; + pci_setup_one_bridge_window(bridge, i); + + return ret; } /* @@ -863,34 +991,6 @@ static void pci_bridge_check_ranges(struct pci_bus *bus) } } -/* - * Helper function for sizing routines. Assigned resources have non-NULL - * parent resource. - * - * Return first unassigned resource of the correct type. If there is none, - * return first assigned resource of the correct type. If none of the - * above, return NULL. - * - * Returning an assigned resource of the correct type allows the caller to - * distinguish between already assigned and no resource of the correct type. - */ -static struct resource *find_bus_resource_of_type(struct pci_bus *bus, - unsigned long type_mask, - unsigned long type) -{ - struct resource *r, *r_assigned = NULL; - - pci_bus_for_each_resource(bus, r) { - if (r == &ioport_resource || r == &iomem_resource) - continue; - if (r && (r->flags & type_mask) == type && !r->parent) - return r; - if (r && (r->flags & type_mask) == type && !r_assigned) - r_assigned = r; - } - return r_assigned; -} - static resource_size_t calculate_iosize(resource_size_t size, resource_size_t min_size, resource_size_t size1, @@ -918,18 +1018,11 @@ static resource_size_t calculate_iosize(resource_size_t size, static resource_size_t calculate_memsize(resource_size_t size, resource_size_t min_size, - resource_size_t add_size, resource_size_t children_add_size, - resource_size_t old_size, resource_size_t align) { - if (size < min_size) - size = min_size; - if (old_size == 1) - old_size = 0; - - size = max(size, add_size) + children_add_size; - return ALIGN(max(size, old_size), align); + size = max(size, min_size) + children_add_size; + return ALIGN(size, align); } resource_size_t __weak pcibios_window_alignment(struct pci_bus *bus, @@ -967,8 +1060,7 @@ static resource_size_t window_alignment(struct pci_bus *bus, unsigned long type) * pbus_size_io() - Size the I/O window of a given bus * * @bus: The bus - * @min_size: The minimum I/O window that must be allocated - * @add_size: Additional optional I/O window + * @add_size: Additional I/O window * @realloc_head: Track the additional I/O window on this list * * Sizing the I/O windows of the PCI-PCI bridge is trivial, since these @@ -976,13 +1068,11 @@ static resource_size_t window_alignment(struct pci_bus *bus, unsigned long type) * devices are limited to 256 bytes. We must be careful with the ISA * aliasing though. */ -static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, - resource_size_t add_size, +static void pbus_size_io(struct pci_bus *bus, resource_size_t add_size, struct list_head *realloc_head) { struct pci_dev *dev; - struct resource *b_res = find_bus_resource_of_type(bus, IORESOURCE_IO, - IORESOURCE_IO); + struct resource *b_res = pbus_select_window_for_type(bus, IORESOURCE_IO); resource_size_t size = 0, size0 = 0, size1 = 0; resource_size_t children_add_size = 0; resource_size_t min_align, align; @@ -991,7 +1081,7 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, return; /* If resource is already assigned, nothing more to do */ - if (b_res->parent) + if (resource_assigned(b_res)) return; min_align = window_alignment(bus, IORESOURCE_IO); @@ -1001,10 +1091,13 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, pci_dev_for_each_resource(dev, r) { unsigned long r_size; - if (r->parent || !(r->flags & IORESOURCE_IO)) + if (resource_assigned(r) || !(r->flags & IORESOURCE_IO)) continue; - r_size = resource_size(r); + if (!pdev_resource_assignable(dev, r)) + continue; + + r_size = resource_size(r); if (r_size < SZ_1K) /* Might be re-aligned for ISA */ size += r_size; @@ -1020,12 +1113,15 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, } } - size0 = calculate_iosize(size, min_size, size1, 0, 0, + size0 = calculate_iosize(size, realloc_head ? 0 : add_size, size1, 0, 0, resource_size(b_res), min_align); + if (size0) + b_res->flags &= ~IORESOURCE_DISABLED; + size1 = size0; if (realloc_head && (add_size > 0 || children_add_size > 0)) { - size1 = calculate_iosize(size, min_size, size1, add_size, + size1 = calculate_iosize(size, 0, size1, add_size, children_add_size, resource_size(b_res), min_align); } @@ -1034,15 +1130,16 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, if (bus->self && (b_res->start || b_res->end)) pci_info(bus->self, "disabling bridge window %pR to %pR (unused)\n", b_res, &bus->busn_res); - b_res->flags = 0; + b_res->flags |= IORESOURCE_DISABLED; return; } resource_set_range(b_res, min_align, size0); b_res->flags |= IORESOURCE_STARTALIGN; if (bus->self && size1 > size0 && realloc_head) { - add_to_list(realloc_head, bus->self, b_res, size1-size0, - min_align); + b_res->flags &= ~IORESOURCE_DISABLED; + pci_dev_res_add_to_list(realloc_head, bus->self, b_res, + size1 - size0, min_align); pci_info(bus->self, "bridge window %pR to %pR add_size %llx\n", b_res, &bus->busn_res, (unsigned long long) size1 - size0); @@ -1071,64 +1168,93 @@ static inline resource_size_t calculate_mem_align(resource_size_t *aligns, return min_align; } -/** - * pbus_upstream_space_available - Check no upstream resource limits allocation - * @bus: The bus - * @mask: Mask the resource flag, then compare it with type - * @type: The type of resource from bridge - * @size: The size required from the bridge window - * @align: Required alignment for the resource - * - * Checks that @size can fit inside the upstream bridge resources that are - * already assigned. - * - * Return: %true if enough space is available on all assigned upstream +/* + * Calculate bridge window head alignment that leaves no gaps in between * resources. */ -static bool pbus_upstream_space_available(struct pci_bus *bus, unsigned long mask, - unsigned long type, resource_size_t size, - resource_size_t align) -{ - struct resource_constraint constraint = { - .max = RESOURCE_SIZE_MAX, - .align = align, - }; - struct pci_bus *downstream = bus; - struct resource *r; +static resource_size_t calculate_head_align(resource_size_t *aligns, + int max_order) +{ + resource_size_t head_align = 1; + resource_size_t remainder = 0; + int order; - while ((bus = bus->parent)) { - if (pci_is_root_bus(bus)) - break; + /* Take the largest alignment as the starting point. */ + head_align <<= max_order + __ffs(SZ_1M); - pci_bus_for_each_resource(bus, r) { - if (!r || !r->parent || (r->flags & mask) != type) - continue; + for (order = max_order - 1; order >= 0; order--) { + resource_size_t align1 = 1; - if (resource_size(r) >= size) { - struct resource gap = {}; + align1 <<= order + __ffs(SZ_1M); - if (find_resource_space(r, &gap, size, &constraint) == 0) { - gap.flags = type; - pci_dbg(bus->self, - "Assigned bridge window %pR to %pR free space at %pR\n", - r, &bus->busn_res, &gap); - return true; - } - } + /* + * Account smaller resources with alignment < max_order that + * could be used to fill head room if alignment less than + * max_order is used. + */ + remainder += aligns[order]; - if (bus->self) { - pci_info(bus->self, - "Assigned bridge window %pR to %pR cannot fit 0x%llx required for %s bridging to %pR\n", - r, &bus->busn_res, - (unsigned long long)size, - pci_name(downstream->self), - &downstream->busn_res); - } + /* + * Test if head fill is enough to satisfy the alignment of + * the larger resources after reducing the alignment. + */ + while ((head_align > align1) && (remainder >= head_align / 2)) { + head_align /= 2; + remainder -= head_align; + } + } - return false; + return head_align; +} + +/* + * pbus_size_mem_optional - Account optional resources in bridge window + * + * Account an optional resource or the optional part of the resource in bridge + * window size. + * + * Return: %true if the resource is entirely optional. + */ +static bool pbus_size_mem_optional(struct pci_dev *dev, int resno, + resource_size_t align, + struct list_head *realloc_head, + resource_size_t *add_align, + resource_size_t *children_add_size) +{ + struct resource *res = pci_resource_n(dev, resno); + bool optional = pci_resource_is_optional(dev, resno); + resource_size_t r_size = resource_size(res); + struct pci_dev_resource *dev_res = NULL; + + if (!realloc_head) + return false; + + /* + * Only bridges have optional sizes in realloc_head at this + * point. As res_to_dev_res() walks the entire realloc_head + * list, skip calling it when known unnecessary. + */ + if (pci_resource_is_bridge_win(resno)) { + dev_res = res_to_dev_res(realloc_head, res); + if (dev_res) { + *children_add_size += dev_res->add_size; + *add_align = max(*add_align, dev_res->min_align); } } + if (!optional) + return false; + + /* + * Put requested res to the optional list if not there yet (SR-IOV, + * disabled ROM). Bridge windows with an optional part are already + * on the list. + */ + if (!dev_res) + pci_dev_res_add_to_list(realloc_head, dev, res, 0, align); + *children_add_size += r_size; + *add_align = max(align, *add_align); + return true; } @@ -1136,45 +1262,37 @@ static bool pbus_upstream_space_available(struct pci_bus *bus, unsigned long mas * pbus_size_mem() - Size the memory window of a given bus * * @bus: The bus - * @mask: Mask the resource flag, then compare it with type - * @type: The type of free resource from bridge - * @type2: Second match type - * @type3: Third match type - * @min_size: The minimum memory window that must be allocated - * @add_size: Additional optional memory window + * @b_res: The bridge window resource + * @add_size: Additional memory window * @realloc_head: Track the additional memory window on this list * - * Calculate the size of the bus and minimal alignment which guarantees - * that all child resources fit in this size. + * Calculate the size of the bridge window @b_res and minimal alignment + * which guarantees that all child resources fit in this size. + * + * Set the bus resource start/end to indicate the required size if there an + * available unassigned bus resource of the desired @type. * - * Return -ENOSPC if there's no available bus resource of the desired - * type. Otherwise, set the bus resource start/end to indicate the - * required size, add things to realloc_head (if supplied), and return 0. + * Add optional resource requests to the @realloc_head list if it is + * supplied. */ -static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, - unsigned long type, unsigned long type2, - unsigned long type3, resource_size_t min_size, - resource_size_t add_size, - struct list_head *realloc_head) +static void pbus_size_mem(struct pci_bus *bus, struct resource *b_res, + resource_size_t add_size, + struct list_head *realloc_head) { struct pci_dev *dev; resource_size_t min_align, win_align, align, size, size0, size1 = 0; - resource_size_t aligns[28]; /* Alignments from 1MB to 128TB */ + resource_size_t aligns[28] = {}; /* Alignments from 1MB to 128TB */ int order, max_order; - struct resource *b_res = find_bus_resource_of_type(bus, - mask | IORESOURCE_PREFETCH, type); resource_size_t children_add_size = 0; - resource_size_t children_add_align = 0; resource_size_t add_align = 0; if (!b_res) - return -ENOSPC; + return; /* If resource is already assigned, nothing more to do */ - if (b_res->parent) - return 0; + if (resource_assigned(b_res)) + return; - memset(aligns, 0, sizeof(aligns)); max_order = 0; size = 0; @@ -1186,216 +1304,88 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, const char *r_name = pci_resource_name(dev, i); resource_size_t r_size; - if (r->parent || (r->flags & IORESOURCE_PCI_FIXED) || - ((r->flags & mask) != type && - (r->flags & mask) != type2 && - (r->flags & mask) != type3)) + if (!pdev_resources_assignable(dev) || + !pdev_resource_should_fit(dev, r)) continue; - r_size = resource_size(r); - - /* Put SRIOV requested res to the optional list */ - if (realloc_head && pci_resource_is_optional(dev, i)) { - add_align = max(pci_resource_alignment(dev, r), add_align); - add_to_list(realloc_head, dev, r, 0, 0 /* Don't care */); - children_add_size += r_size; + if (b_res != pbus_select_window(bus, r)) continue; - } + align = pci_resource_alignment(dev, r); /* * aligns[0] is for 1MB (since bridge memory * windows are always at least 1MB aligned), so * keep "order" from being negative for smaller * resources. */ - align = pci_resource_alignment(dev, r); - order = __ffs(align) - __ffs(SZ_1M); - if (order < 0) - order = 0; + order = max_t(int, __ffs(align) - __ffs(SZ_1M), 0); if (order >= ARRAY_SIZE(aligns)) { pci_warn(dev, "%s %pR: disabling; bad alignment %#llx\n", r_name, r, (unsigned long long) align); r->flags = 0; continue; } + + if (pbus_size_mem_optional(dev, i, align, + realloc_head, &add_align, + &children_add_size)) + continue; + + r_size = resource_size(r); size += max(r_size, align); - /* - * Exclude ranges with size > align from calculation of - * the alignment. - */ - if (r_size <= align) - aligns[order] += align; + + aligns[order] += align; if (order > max_order) max_order = order; - - if (realloc_head) { - children_add_size += get_res_add_size(realloc_head, r); - children_add_align = get_res_add_align(realloc_head, r); - add_align = max(add_align, children_add_align); - } } } win_align = window_alignment(bus, b_res->flags); - min_align = calculate_mem_align(aligns, max_order); + min_align = calculate_head_align(aligns, max_order); min_align = max(min_align, win_align); - size0 = calculate_memsize(size, min_size, 0, 0, resource_size(b_res), min_align); + size0 = calculate_memsize(size, realloc_head ? 0 : add_size, + 0, win_align); - if (bus->self && size0 && - !pbus_upstream_space_available(bus, mask | IORESOURCE_PREFETCH, type, - size0, min_align)) { - min_align = 1ULL << (max_order + __ffs(SZ_1M)); - min_align = max(min_align, win_align); - size0 = calculate_memsize(size, min_size, 0, 0, resource_size(b_res), win_align); - pci_info(bus->self, "bridge window %pR to %pR requires relaxed alignment rules\n", - b_res, &bus->busn_res); + if (size0) { + resource_set_range(b_res, min_align, size0); + b_res->flags &= ~IORESOURCE_DISABLED; } if (realloc_head && (add_size > 0 || children_add_size > 0)) { add_align = max(min_align, add_align); - size1 = calculate_memsize(size, min_size, add_size, children_add_size, - resource_size(b_res), add_align); - - if (bus->self && size1 && - !pbus_upstream_space_available(bus, mask | IORESOURCE_PREFETCH, type, - size1, add_align)) { - min_align = 1ULL << (max_order + __ffs(SZ_1M)); - min_align = max(min_align, win_align); - size1 = calculate_memsize(size, min_size, add_size, children_add_size, - resource_size(b_res), win_align); - pci_info(bus->self, - "bridge window %pR to %pR requires relaxed alignment rules\n", - b_res, &bus->busn_res); - } + size1 = calculate_memsize(size, add_size, children_add_size, + win_align); } if (!size0 && !size1) { if (bus->self && (b_res->start || b_res->end)) pci_info(bus->self, "disabling bridge window %pR to %pR (unused)\n", b_res, &bus->busn_res); - b_res->flags = 0; - return 0; + b_res->flags |= IORESOURCE_DISABLED; + return; } resource_set_range(b_res, min_align, size0); b_res->flags |= IORESOURCE_STARTALIGN; - if (bus->self && size1 > size0 && realloc_head) { - add_to_list(realloc_head, bus->self, b_res, size1-size0, add_align); + if (bus->self && realloc_head && (size1 > size0 || add_align > min_align)) { + b_res->flags &= ~IORESOURCE_DISABLED; + add_size = size1 > size0 ? size1 - size0 : 0; + pci_dev_res_add_to_list(realloc_head, bus->self, b_res, + add_size, add_align); pci_info(bus->self, "bridge window %pR to %pR add_size %llx add_align %llx\n", b_res, &bus->busn_res, - (unsigned long long) (size1 - size0), + (unsigned long long) add_size, (unsigned long long) add_align); } - return 0; -} - -unsigned long pci_cardbus_resource_alignment(struct resource *res) -{ - if (res->flags & IORESOURCE_IO) - return pci_cardbus_io_size; - if (res->flags & IORESOURCE_MEM) - return pci_cardbus_mem_size; - return 0; -} - -static void pci_bus_size_cardbus(struct pci_bus *bus, - struct list_head *realloc_head) -{ - struct pci_dev *bridge = bus->self; - struct resource *b_res; - resource_size_t b_res_3_size = pci_cardbus_mem_size * 2; - u16 ctrl; - - b_res = &bridge->resource[PCI_CB_BRIDGE_IO_0_WINDOW]; - if (b_res->parent) - goto handle_b_res_1; - /* - * Reserve some resources for CardBus. We reserve a fixed amount - * of bus space for CardBus bridges. - */ - resource_set_range(b_res, pci_cardbus_io_size, pci_cardbus_io_size); - b_res->flags |= IORESOURCE_IO | IORESOURCE_STARTALIGN; - if (realloc_head) { - b_res->end -= pci_cardbus_io_size; - add_to_list(realloc_head, bridge, b_res, pci_cardbus_io_size, - pci_cardbus_io_size); - } - -handle_b_res_1: - b_res = &bridge->resource[PCI_CB_BRIDGE_IO_1_WINDOW]; - if (b_res->parent) - goto handle_b_res_2; - resource_set_range(b_res, pci_cardbus_io_size, pci_cardbus_io_size); - b_res->flags |= IORESOURCE_IO | IORESOURCE_STARTALIGN; - if (realloc_head) { - b_res->end -= pci_cardbus_io_size; - add_to_list(realloc_head, bridge, b_res, pci_cardbus_io_size, - pci_cardbus_io_size); - } - -handle_b_res_2: - /* MEM1 must not be pref MMIO */ - pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl); - if (ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM1) { - ctrl &= ~PCI_CB_BRIDGE_CTL_PREFETCH_MEM1; - pci_write_config_word(bridge, PCI_CB_BRIDGE_CONTROL, ctrl); - pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl); - } - - /* Check whether prefetchable memory is supported by this bridge. */ - pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl); - if (!(ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM0)) { - ctrl |= PCI_CB_BRIDGE_CTL_PREFETCH_MEM0; - pci_write_config_word(bridge, PCI_CB_BRIDGE_CONTROL, ctrl); - pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl); - } - - b_res = &bridge->resource[PCI_CB_BRIDGE_MEM_0_WINDOW]; - if (b_res->parent) - goto handle_b_res_3; - /* - * If we have prefetchable memory support, allocate two regions. - * Otherwise, allocate one region of twice the size. - */ - if (ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM0) { - resource_set_range(b_res, pci_cardbus_mem_size, - pci_cardbus_mem_size); - b_res->flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH | - IORESOURCE_STARTALIGN; - if (realloc_head) { - b_res->end -= pci_cardbus_mem_size; - add_to_list(realloc_head, bridge, b_res, - pci_cardbus_mem_size, pci_cardbus_mem_size); - } - - /* Reduce that to half */ - b_res_3_size = pci_cardbus_mem_size; - } - -handle_b_res_3: - b_res = &bridge->resource[PCI_CB_BRIDGE_MEM_1_WINDOW]; - if (b_res->parent) - goto handle_done; - resource_set_range(b_res, pci_cardbus_mem_size, b_res_3_size); - b_res->flags |= IORESOURCE_MEM | IORESOURCE_STARTALIGN; - if (realloc_head) { - b_res->end -= b_res_3_size; - add_to_list(realloc_head, bridge, b_res, b_res_3_size, - pci_cardbus_mem_size); - } - -handle_done: - ; } void __pci_bus_size_bridges(struct pci_bus *bus, struct list_head *realloc_head) { struct pci_dev *dev; - unsigned long mask, prefmask, type2 = 0, type3 = 0; resource_size_t additional_io_size = 0, additional_mmio_size = 0, additional_mmio_pref_size = 0; - struct resource *pref; + struct resource *b_res; struct pci_host_bridge *host; - int hdr_type, ret; + int hdr_type; list_for_each_entry(dev, &bus->devices, bus_list) { struct pci_bus *b = dev->subordinate; @@ -1404,7 +1394,8 @@ void __pci_bus_size_bridges(struct pci_bus *bus, struct list_head *realloc_head) switch (dev->hdr_type) { case PCI_HEADER_TYPE_CARDBUS: - pci_bus_size_cardbus(b, realloc_head); + if (pci_bus_size_cardbus_bridge(b, realloc_head)) + continue; break; case PCI_HEADER_TYPE_BRIDGE: @@ -1419,12 +1410,8 @@ void __pci_bus_size_bridges(struct pci_bus *bus, struct list_head *realloc_head) host = to_pci_host_bridge(bus->bridge); if (!host->size_windows) return; - pci_bus_for_each_resource(bus, pref) - if (pref && (pref->flags & IORESOURCE_PREFETCH)) - break; hdr_type = -1; /* Intentionally invalid - not a PCI device. */ } else { - pref = &bus->self->resource[PCI_BRIDGE_PREF_MEM_WINDOW]; hdr_type = bus->self->hdr_type; } @@ -1442,76 +1429,21 @@ void __pci_bus_size_bridges(struct pci_bus *bus, struct list_head *realloc_head) } fallthrough; default: - pbus_size_io(bus, realloc_head ? 0 : additional_io_size, - additional_io_size, realloc_head); - - /* - * If there's a 64-bit prefetchable MMIO window, compute - * the size required to put all 64-bit prefetchable - * resources in it. - */ - mask = IORESOURCE_MEM; - prefmask = IORESOURCE_MEM | IORESOURCE_PREFETCH; - if (pref && (pref->flags & IORESOURCE_MEM_64)) { - prefmask |= IORESOURCE_MEM_64; - ret = pbus_size_mem(bus, prefmask, prefmask, - prefmask, prefmask, - realloc_head ? 0 : additional_mmio_pref_size, - additional_mmio_pref_size, realloc_head); - - /* - * If successful, all non-prefetchable resources - * and any 32-bit prefetchable resources will go in - * the non-prefetchable window. - */ - if (ret == 0) { - mask = prefmask; - type2 = prefmask & ~IORESOURCE_MEM_64; - type3 = prefmask & ~IORESOURCE_PREFETCH; - } + pbus_size_io(bus, additional_io_size, realloc_head); + + b_res = pbus_select_window_for_type(bus, IORESOURCE_MEM | + IORESOURCE_PREFETCH | + IORESOURCE_MEM_64); + if (b_res && (b_res->flags & IORESOURCE_PREFETCH)) { + pbus_size_mem(bus, b_res, additional_mmio_pref_size, + realloc_head); } - /* - * If there is no 64-bit prefetchable window, compute the - * size required to put all prefetchable resources in the - * 32-bit prefetchable window (if there is one). - */ - if (!type2) { - prefmask &= ~IORESOURCE_MEM_64; - ret = pbus_size_mem(bus, prefmask, prefmask, - prefmask, prefmask, - realloc_head ? 0 : additional_mmio_pref_size, - additional_mmio_pref_size, realloc_head); - - /* - * If successful, only non-prefetchable resources - * will go in the non-prefetchable window. - */ - if (ret == 0) - mask = prefmask; - else - additional_mmio_size += additional_mmio_pref_size; - - type2 = type3 = IORESOURCE_MEM; + b_res = pbus_select_window_for_type(bus, IORESOURCE_MEM); + if (b_res) { + pbus_size_mem(bus, b_res, additional_mmio_size, + realloc_head); } - - /* - * Compute the size required to put everything else in the - * non-prefetchable window. This includes: - * - * - all non-prefetchable resources - * - 32-bit prefetchable resources if there's a 64-bit - * prefetchable window or no prefetchable window at all - * - 64-bit prefetchable resources if there's no prefetchable - * window at all - * - * Note that the strategy in __pci_assign_resource() must match - * that used here. Specifically, we cannot put a 32-bit - * prefetchable resource in a 64-bit prefetchable window. - */ - pbus_size_mem(bus, mask, IORESOURCE_MEM, type2, type3, - realloc_head ? 0 : additional_mmio_size, - additional_mmio_size, realloc_head); break; } } @@ -1549,12 +1481,13 @@ static void pdev_assign_fixed_resources(struct pci_dev *dev) pci_dev_for_each_resource(dev, r) { struct pci_bus *b; - if (r->parent || !(r->flags & IORESOURCE_PCI_FIXED) || + if (resource_assigned(r) || + !(r->flags & IORESOURCE_PCI_FIXED) || !(r->flags & (IORESOURCE_IO | IORESOURCE_MEM))) continue; b = dev->bus; - while (b && !r->parent) { + while (b && !resource_assigned(r)) { assign_fixed_resource_on_bus(b, r); b = b->parent; } @@ -1586,7 +1519,7 @@ void __pci_bus_assign_resources(const struct pci_bus *bus, break; case PCI_HEADER_TYPE_CARDBUS: - pci_setup_cardbus(b); + pci_setup_cardbus_bridge(b); break; default: @@ -1610,7 +1543,7 @@ static void pci_claim_device_resources(struct pci_dev *dev) for (i = 0; i < PCI_BRIDGE_RESOURCES; i++) { struct resource *r = &dev->resource[i]; - if (!r->flags || r->parent) + if (!r->flags || resource_assigned(r)) continue; pci_claim_resource(dev, i); @@ -1624,7 +1557,9 @@ static void pci_claim_bridge_resources(struct pci_dev *dev) for (i = PCI_BRIDGE_RESOURCES; i < PCI_NUM_RESOURCES; i++) { struct resource *r = &dev->resource[i]; - if (!r->flags || r->parent) + if (!r->flags || resource_assigned(r)) + continue; + if (r->flags & IORESOURCE_DISABLED) continue; pci_claim_bridge_resource(dev, i); @@ -1691,7 +1626,7 @@ static void __pci_bridge_assign_resources(const struct pci_dev *bridge, break; case PCI_CLASS_BRIDGE_CARDBUS: - pci_setup_cardbus(b); + pci_setup_cardbus_bridge(b); break; default: @@ -1701,66 +1636,25 @@ static void __pci_bridge_assign_resources(const struct pci_dev *bridge, } } -#define PCI_RES_TYPE_MASK \ - (IORESOURCE_IO | IORESOURCE_MEM | IORESOURCE_PREFETCH |\ - IORESOURCE_MEM_64) - static void pci_bridge_release_resources(struct pci_bus *bus, - unsigned long type) + struct resource *b_win) { struct pci_dev *dev = bus->self; - struct resource *r; - unsigned int old_flags; - struct resource *b_res; - int idx = 1; + int idx, ret; - b_res = &dev->resource[PCI_BRIDGE_RESOURCES]; - - /* - * 1. If IO port assignment fails, release bridge IO port. - * 2. If non pref MMIO assignment fails, release bridge nonpref MMIO. - * 3. If 64bit pref MMIO assignment fails, and bridge pref is 64bit, - * release bridge pref MMIO. - * 4. If pref MMIO assignment fails, and bridge pref is 32bit, - * release bridge pref MMIO. - * 5. If pref MMIO assignment fails, and bridge pref is not - * assigned, release bridge nonpref MMIO. - */ - if (type & IORESOURCE_IO) - idx = 0; - else if (!(type & IORESOURCE_PREFETCH)) - idx = 1; - else if ((type & IORESOURCE_MEM_64) && - (b_res[2].flags & IORESOURCE_MEM_64)) - idx = 2; - else if (!(b_res[2].flags & IORESOURCE_MEM_64) && - (b_res[2].flags & IORESOURCE_PREFETCH)) - idx = 2; - else - idx = 1; - - r = &b_res[idx]; - - if (!r->parent) + if (!resource_assigned(b_win)) return; + idx = pci_resource_num(dev, b_win); + /* If there are children, release them all */ - release_child_resources(r); - if (!release_resource(r)) { - type = old_flags = r->flags & PCI_RES_TYPE_MASK; - pci_info(dev, "resource %d %pR released\n", - PCI_BRIDGE_RESOURCES + idx, r); - /* Keep the old size */ - resource_set_range(r, 0, resource_size(r)); - r->flags = 0; + release_child_resources(b_win); - /* Avoiding touch the one without PREF */ - if (type & IORESOURCE_PREFETCH) - type = IORESOURCE_PREFETCH; - __pci_setup_bridge(bus, type); - /* For next child res under same bridge */ - r->flags = old_flags; - } + ret = pci_release_resource(dev, idx); + if (ret) + return; + + pci_setup_one_bridge_window(dev, idx); } enum release_type { @@ -1773,7 +1667,7 @@ enum release_type { * a larger window later. */ static void pci_bus_release_bridge_resources(struct pci_bus *bus, - unsigned long type, + struct resource *b_win, enum release_type rel_type) { struct pci_dev *dev; @@ -1781,6 +1675,8 @@ static void pci_bus_release_bridge_resources(struct pci_bus *bus, list_for_each_entry(dev, &bus->devices, bus_list) { struct pci_bus *b = dev->subordinate; + struct resource *res; + if (!b) continue; @@ -1789,9 +1685,15 @@ static void pci_bus_release_bridge_resources(struct pci_bus *bus, if ((dev->class >> 8) != PCI_CLASS_BRIDGE_PCI) continue; - if (rel_type == whole_subtree) - pci_bus_release_bridge_resources(b, type, - whole_subtree); + if (rel_type != whole_subtree) + continue; + + pci_bus_for_each_resource(b, res) { + if (res->parent != b_win) + continue; + + pci_bus_release_bridge_resources(b, res, rel_type); + } } if (pci_is_root_bus(bus)) @@ -1801,7 +1703,7 @@ static void pci_bus_release_bridge_resources(struct pci_bus *bus, return; if ((rel_type == whole_subtree) || is_leaf_bridge) - pci_bridge_release_resources(bus, type); + pci_bridge_release_resources(bus, b_win); } static void pci_bus_dump_res(struct pci_bus *bus) @@ -1885,7 +1787,8 @@ static int iov_resources_unassigned(struct pci_dev *dev, void *data) bool *unassigned = data; for (i = 0; i < PCI_SRIOV_NUM_BARS; i++) { - struct resource *r = &dev->resource[i + PCI_IOV_RESOURCES]; + int idx = pci_resource_num_from_vf_bar(i); + struct resource *r = &dev->resource[idx]; struct pci_bus_region region; /* Not assigned or rejected by kernel? */ @@ -1935,7 +1838,7 @@ static void adjust_bridge_window(struct pci_dev *bridge, struct resource *res, { resource_size_t add_size, size = resource_size(res); - if (res->parent) + if (resource_assigned(res)) return; if (!new_size) @@ -1957,7 +1860,7 @@ static void adjust_bridge_window(struct pci_dev *bridge, struct resource *res, /* If the resource is part of the add_list, remove it now */ if (add_list) - remove_from_list(add_list, res); + pci_dev_res_remove_from_list(add_list, res); } static void remove_dev_resource(struct resource *avail, struct pci_dev *dev, @@ -1975,33 +1878,21 @@ static void remove_dev_resource(struct resource *avail, struct pci_dev *dev, avail->start = min(avail->start + tmp, avail->end + 1); } -static void remove_dev_resources(struct pci_dev *dev, struct resource *io, - struct resource *mmio, - struct resource *mmio_pref) +static void remove_dev_resources(struct pci_dev *dev, + struct resource available[PCI_P2P_BRIDGE_RESOURCE_NUM]) { - struct resource *res; + struct resource *res, *b_win; + int idx; pci_dev_for_each_resource(dev, res) { - if (resource_type(res) == IORESOURCE_IO) { - remove_dev_resource(io, dev, res); - } else if (resource_type(res) == IORESOURCE_MEM) { + b_win = pbus_select_window(dev->bus, res); + if (!b_win) + continue; - /* - * Make sure prefetchable memory is reduced from - * the correct resource. Specifically we put 32-bit - * prefetchable memory in non-prefetchable window - * if there is a 64-bit prefetchable window. - * - * See comments in __pci_bus_size_bridges() for - * more information. - */ - if ((res->flags & IORESOURCE_PREFETCH) && - ((res->flags & IORESOURCE_MEM_64) == - (mmio_pref->flags & IORESOURCE_MEM_64))) - remove_dev_resource(mmio_pref, dev, res); - else - remove_dev_resource(mmio, dev, res); - } + idx = pci_resource_num(dev->bus->self, b_win); + idx -= PCI_BRIDGE_RESOURCES; + + remove_dev_resource(&available[idx], dev, res); } } @@ -2015,45 +1906,40 @@ static void remove_dev_resources(struct pci_dev *dev, struct resource *io, * shared with the bridges. */ static void pci_bus_distribute_available_resources(struct pci_bus *bus, - struct list_head *add_list, - struct resource io, - struct resource mmio, - struct resource mmio_pref) + struct list_head *add_list, + struct resource available_in[PCI_P2P_BRIDGE_RESOURCE_NUM]) { + struct resource available[PCI_P2P_BRIDGE_RESOURCE_NUM]; unsigned int normal_bridges = 0, hotplug_bridges = 0; - struct resource *io_res, *mmio_res, *mmio_pref_res; struct pci_dev *dev, *bridge = bus->self; - resource_size_t io_per_b, mmio_per_b, mmio_pref_per_b, align; - - io_res = &bridge->resource[PCI_BRIDGE_IO_WINDOW]; - mmio_res = &bridge->resource[PCI_BRIDGE_MEM_WINDOW]; - mmio_pref_res = &bridge->resource[PCI_BRIDGE_PREF_MEM_WINDOW]; + resource_size_t per_bridge[PCI_P2P_BRIDGE_RESOURCE_NUM]; + resource_size_t align; + int i; - /* - * The alignment of this bridge is yet to be considered, hence it must - * be done now before extending its bridge window. - */ - align = pci_resource_alignment(bridge, io_res); - if (!io_res->parent && align) - io.start = min(ALIGN(io.start, align), io.end + 1); + for (i = 0; i < PCI_P2P_BRIDGE_RESOURCE_NUM; i++) { + struct resource *res = + pci_resource_n(bridge, PCI_BRIDGE_RESOURCES + i); - align = pci_resource_alignment(bridge, mmio_res); - if (!mmio_res->parent && align) - mmio.start = min(ALIGN(mmio.start, align), mmio.end + 1); + available[i] = available_in[i]; - align = pci_resource_alignment(bridge, mmio_pref_res); - if (!mmio_pref_res->parent && align) - mmio_pref.start = min(ALIGN(mmio_pref.start, align), - mmio_pref.end + 1); + /* + * The alignment of this bridge is yet to be considered, + * hence it must be done now before extending its bridge + * window. + */ + align = pci_resource_alignment(bridge, res); + if (!resource_assigned(res) && align) + available[i].start = min(ALIGN(available[i].start, align), + available[i].end + 1); - /* - * Now that we have adjusted for alignment, update the bridge window - * resources to fill as much remaining resource space as possible. - */ - adjust_bridge_window(bridge, io_res, add_list, resource_size(&io)); - adjust_bridge_window(bridge, mmio_res, add_list, resource_size(&mmio)); - adjust_bridge_window(bridge, mmio_pref_res, add_list, - resource_size(&mmio_pref)); + /* + * Now that we have adjusted for alignment, update the + * bridge window resources to fill as much remaining + * resource space as possible. + */ + adjust_bridge_window(bridge, res, add_list, + resource_size(&available[i])); + } /* * Calculate how many hotplug bridges and normal bridges there @@ -2077,7 +1963,7 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus, */ list_for_each_entry(dev, &bus->devices, bus_list) { if (!dev->is_virtfn) - remove_dev_resources(dev, &io, &mmio, &mmio_pref); + remove_dev_resources(dev, available); } /* @@ -2089,16 +1975,9 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus, * split between non-hotplug bridges. This is to allow possible * hotplug bridges below them to get the extra space as well. */ - if (hotplug_bridges) { - io_per_b = div64_ul(resource_size(&io), hotplug_bridges); - mmio_per_b = div64_ul(resource_size(&mmio), hotplug_bridges); - mmio_pref_per_b = div64_ul(resource_size(&mmio_pref), - hotplug_bridges); - } else { - io_per_b = div64_ul(resource_size(&io), normal_bridges); - mmio_per_b = div64_ul(resource_size(&mmio), normal_bridges); - mmio_pref_per_b = div64_ul(resource_size(&mmio_pref), - normal_bridges); + for (i = 0; i < PCI_P2P_BRIDGE_RESOURCE_NUM; i++) { + per_bridge[i] = div64_ul(resource_size(&available[i]), + hotplug_bridges ?: normal_bridges); } for_each_pci_bridge(dev, bus) { @@ -2111,49 +1990,41 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus, if (hotplug_bridges && !dev->is_hotplug_bridge) continue; - res = &dev->resource[PCI_BRIDGE_IO_WINDOW]; - - /* - * Make sure the split resource space is properly aligned - * for bridge windows (align it down to avoid going above - * what is available). - */ - align = pci_resource_alignment(dev, res); - resource_set_size(&io, ALIGN_DOWN_IF_NONZERO(io_per_b, align)); + for (i = 0; i < PCI_P2P_BRIDGE_RESOURCE_NUM; i++) { + res = pci_resource_n(dev, PCI_BRIDGE_RESOURCES + i); - /* - * The x_per_b holds the extra resource space that can be - * added for each bridge but there is the minimal already - * reserved as well so adjust x.start down accordingly to - * cover the whole space. - */ - io.start -= resource_size(res); - - res = &dev->resource[PCI_BRIDGE_MEM_WINDOW]; - align = pci_resource_alignment(dev, res); - resource_set_size(&mmio, - ALIGN_DOWN_IF_NONZERO(mmio_per_b,align)); - mmio.start -= resource_size(res); + /* + * Make sure the split resource space is properly + * aligned for bridge windows (align it down to + * avoid going above what is available). + */ + align = pci_resource_alignment(dev, res); + resource_set_size(&available[i], + ALIGN_DOWN_IF_NONZERO(per_bridge[i], + align)); - res = &dev->resource[PCI_BRIDGE_PREF_MEM_WINDOW]; - align = pci_resource_alignment(dev, res); - resource_set_size(&mmio_pref, - ALIGN_DOWN_IF_NONZERO(mmio_pref_per_b, align)); - mmio_pref.start -= resource_size(res); + /* + * The per_bridge holds the extra resource space + * that can be added for each bridge but there is + * the minimal already reserved as well so adjust + * x.start down accordingly to cover the whole + * space. + */ + available[i].start -= resource_size(res); + } - pci_bus_distribute_available_resources(b, add_list, io, mmio, - mmio_pref); + pci_bus_distribute_available_resources(b, add_list, available); - io.start += io.end + 1; - mmio.start += mmio.end + 1; - mmio_pref.start += mmio_pref.end + 1; + for (i = 0; i < PCI_P2P_BRIDGE_RESOURCE_NUM; i++) + available[i].start += available[i].end + 1; } } static void pci_bridge_distribute_available_resources(struct pci_dev *bridge, struct list_head *add_list) { - struct resource available_io, available_mmio, available_mmio_pref; + struct resource *res, available[PCI_P2P_BRIDGE_RESOURCE_NUM]; + unsigned int i; if (!bridge->is_hotplug_bridge) return; @@ -2161,14 +2032,13 @@ static void pci_bridge_distribute_available_resources(struct pci_dev *bridge, pci_dbg(bridge, "distributing available resources\n"); /* Take the initial extra resources from the hotplug port */ - available_io = bridge->resource[PCI_BRIDGE_IO_WINDOW]; - available_mmio = bridge->resource[PCI_BRIDGE_MEM_WINDOW]; - available_mmio_pref = bridge->resource[PCI_BRIDGE_PREF_MEM_WINDOW]; + for (i = 0; i < PCI_P2P_BRIDGE_RESOURCE_NUM; i++) { + res = pci_resource_n(bridge, PCI_BRIDGE_RESOURCES + i); + available[i] = *res; + } pci_bus_distribute_available_resources(bridge->subordinate, - add_list, available_io, - available_mmio, - available_mmio_pref); + add_list, available); } static bool pci_bridge_resources_not_assigned(struct pci_dev *dev) @@ -2231,28 +2101,20 @@ static void pci_prepare_next_assign_round(struct list_head *fail_head, * enough to contain child device resources. */ list_for_each_entry(fail_res, fail_head, list) { - pci_bus_release_bridge_resources(fail_res->dev->bus, - fail_res->flags & PCI_RES_TYPE_MASK, - rel_type); - } - - /* Restore size and flags */ - list_for_each_entry(fail_res, fail_head, list) { - struct resource *res = fail_res->res; - struct pci_dev *dev = fail_res->dev; - int idx = pci_resource_num(dev, res); + struct pci_bus *bus = fail_res->dev->bus; + struct resource *b_win; - restore_dev_resource(fail_res); - - if (!pci_is_bridge(dev)) + b_win = pbus_select_window_for_type(bus, fail_res->flags); + if (!b_win) continue; - - if (idx >= PCI_BRIDGE_RESOURCES && - idx <= PCI_BRIDGE_RESOURCE_END) - res->flags = 0; + pci_bus_release_bridge_resources(bus, b_win, rel_type); } - free_list(fail_head); + /* Restore size and flags */ + list_for_each_entry(fail_res, fail_head, list) + pci_dev_res_restore(fail_res); + + pci_dev_res_free_list(fail_head); } /* @@ -2298,8 +2160,8 @@ void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus) /* Depth last, allocate resources and update the hardware. */ __pci_bus_assign_resources(bus, add_list, &fail_head); - if (add_list) - BUG_ON(!list_empty(add_list)); + if (WARN_ON_ONCE(add_list && !list_empty(add_list))) + pci_dev_res_free_list(add_list); tried_times++; /* Any device complain? */ @@ -2314,7 +2176,7 @@ void pci_assign_unassigned_root_bus_resources(struct pci_bus *bus) dev_info(&bus->dev, "Automatically enabled pci realloc, if you have problem, try booting with pci=realloc=off\n"); } - free_list(&fail_head); + pci_dev_res_free_list(&fail_head); break; } @@ -2361,7 +2223,8 @@ void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge) pci_bridge_distribute_available_resources(bridge, &add_list); __pci_bridge_assign_resources(bridge, &add_list, &fail_head); - BUG_ON(!list_empty(&add_list)); + if (WARN_ON_ONCE(!list_empty(&add_list))) + pci_dev_res_free_list(&add_list); tried_times++; if (list_empty(&fail_head)) @@ -2369,7 +2232,7 @@ void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge) if (tried_times >= 2) { /* Still fail, don't need to try more */ - free_list(&fail_head); + pci_dev_res_free_list(&fail_head); break; } @@ -2384,101 +2247,173 @@ void pci_assign_unassigned_bridge_resources(struct pci_dev *bridge) } EXPORT_SYMBOL_GPL(pci_assign_unassigned_bridge_resources); -int pci_reassign_bridge_resources(struct pci_dev *bridge, unsigned long type) +/* + * Walk to the root bus, find the bridge window relevant for @res and + * release it when possible. If the bridge window contains assigned + * resources, it cannot be released. + */ +static int pbus_reassign_bridge_resources(struct pci_bus *bus, struct resource *res, + struct list_head *saved) { + unsigned long type = res->flags; struct pci_dev_resource *dev_res; - struct pci_dev *next; - LIST_HEAD(saved); + struct pci_dev *bridge = NULL; LIST_HEAD(added); LIST_HEAD(failed); unsigned int i; - int ret; - - down_read(&pci_bus_sem); + int ret = 0; - /* Walk to the root hub, releasing bridge BARs when possible */ - next = bridge; - do { - bridge = next; - for (i = PCI_BRIDGE_RESOURCES; i < PCI_BRIDGE_RESOURCE_END; - i++) { - struct resource *res = &bridge->resource[i]; - const char *res_name = pci_resource_name(bridge, i); - - if ((res->flags ^ type) & PCI_RES_TYPE_MASK) - continue; + while (!pci_is_root_bus(bus)) { + bridge = bus->self; + res = pbus_select_window(bus, res); + if (!res) + break; - /* Ignore BARs which are still in use */ - if (res->child) - continue; + i = pci_resource_num(bridge, res); - ret = add_to_list(&saved, bridge, res, 0, 0); + /* Ignore BARs which are still in use */ + if (!res->child) { + ret = pci_dev_res_add_to_list(saved, bridge, res, 0, 0); if (ret) - goto cleanup; + return ret; - pci_info(bridge, "%s %pR: releasing\n", res_name, res); + pci_release_resource(bridge, i); + } else { + const char *res_name = pci_resource_name(bridge, i); - if (res->parent) - release_resource(res); - res->start = 0; - res->end = 0; - break; + pci_warn(bridge, + "%s %pR: was not released (still contains assigned resources)\n", + res_name, res); } - if (i == PCI_BRIDGE_RESOURCE_END) - break; - next = bridge->bus ? bridge->bus->self : NULL; - } while (next); + bus = bus->parent; + } - if (list_empty(&saved)) { - up_read(&pci_bus_sem); + if (!bridge) return -ENOENT; - } __pci_bus_size_bridges(bridge->subordinate, &added); __pci_bridge_assign_resources(bridge, &added, &failed); - BUG_ON(!list_empty(&added)); + if (WARN_ON_ONCE(!list_empty(&added))) + pci_dev_res_free_list(&added); if (!list_empty(&failed)) { - ret = -ENOSPC; - goto cleanup; + if (pci_required_resource_failed(&failed, type)) + ret = -ENOSPC; + pci_dev_res_free_list(&failed); + if (ret) + return ret; + + /* Only resources with unrelated types failed (again) */ } - list_for_each_entry(dev_res, &saved, list) { + list_for_each_entry(dev_res, saved, list) { + struct pci_dev *dev = dev_res->dev; + /* Skip the bridge we just assigned resources for */ - if (bridge == dev_res->dev) + if (bridge == dev) continue; - bridge = dev_res->dev; - pci_setup_bridge(bridge->subordinate); + if (!dev->subordinate) + continue; + + pci_setup_bridge(dev->subordinate); } - free_list(&saved); - up_read(&pci_bus_sem); return 0; +} -cleanup: - /* Restore size and flags */ - list_for_each_entry(dev_res, &failed, list) - restore_dev_resource(dev_res); - free_list(&failed); +int pci_do_resource_release_and_resize(struct pci_dev *pdev, int resno, int size, + int exclude_bars) +{ + struct resource *res = pci_resource_n(pdev, resno); + struct pci_dev_resource *dev_res; + struct pci_bus *bus = pdev->bus; + struct resource *b_win, *r; + LIST_HEAD(saved); + unsigned int i; + int old, ret; - /* Revert to the old configuration */ - list_for_each_entry(dev_res, &saved, list) { - struct resource *res = dev_res->res; + b_win = pbus_select_window(bus, res); + if (!b_win) + return -EINVAL; - bridge = dev_res->dev; - i = pci_resource_num(bridge, res); + old = pci_rebar_get_current_size(pdev, resno); + if (old < 0) + return old; + + ret = pci_rebar_set_size(pdev, resno, size); + if (ret) + return ret; - restore_dev_resource(dev_res); + pci_dev_for_each_resource(pdev, r, i) { + if (i >= PCI_BRIDGE_RESOURCES) + break; + + if (exclude_bars & BIT(i)) + continue; - pci_claim_resource(bridge, i); - pci_setup_bridge(bridge->subordinate); + if (b_win != pbus_select_window(bus, r)) + continue; + + ret = pci_dev_res_add_to_list(&saved, pdev, r, 0, 0); + if (ret) + goto restore; + pci_release_resource(pdev, i); } - free_list(&saved); - up_read(&pci_bus_sem); + pci_resize_resource_set_size(pdev, resno, size); + + if (!bus->self) + goto out; + + down_read(&pci_bus_sem); + ret = pbus_reassign_bridge_resources(bus, res, &saved); + if (ret) + goto restore; + +out: + up_read(&pci_bus_sem); + pci_dev_res_free_list(&saved); return ret; + +restore: + /* + * Revert to the old configuration. + * + * BAR Size must be restored first because it affects the read-only + * bits in BAR (the old address might not be restorable otherwise + * due to low address bits). + */ + pci_rebar_set_size(pdev, resno, old); + + list_for_each_entry(dev_res, &saved, list) { + struct resource *res = dev_res->res; + struct pci_dev *dev = dev_res->dev; + + i = pci_resource_num(dev, res); + + if (resource_assigned(res)) { + release_child_resources(res); + pci_release_resource(dev, i); + } + + pci_dev_res_restore(dev_res); + + if (pci_claim_resource(dev, i)) + continue; + + if (i < PCI_BRIDGE_RESOURCES) { + const char *res_name = pci_resource_name(dev, i); + + pci_update_resource(dev, i); + pci_info(dev, "%s %pR: old value restored\n", + res_name, res); + } + if (dev->subordinate) + pci_setup_bridge(dev->subordinate); + } + goto out; } void pci_assign_unassigned_bus_resources(struct pci_bus *bus) @@ -2493,6 +2428,7 @@ void pci_assign_unassigned_bus_resources(struct pci_bus *bus) __pci_bus_size_bridges(dev->subordinate, &add_list); up_read(&pci_bus_sem); __pci_bus_assign_resources(bus, &add_list, NULL); - BUG_ON(!list_empty(&add_list)); + if (WARN_ON_ONCE(!list_empty(&add_list))) + pci_dev_res_free_list(&add_list); } EXPORT_SYMBOL_GPL(pci_assign_unassigned_bus_resources); diff --git a/drivers/pci/setup-cardbus.c b/drivers/pci/setup-cardbus.c new file mode 100644 index 000000000000..1ebd13a1f730 --- /dev/null +++ b/drivers/pci/setup-cardbus.c @@ -0,0 +1,306 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Cardbus bridge setup routines. + */ + +#include <linux/bitfield.h> +#include <linux/errno.h> +#include <linux/ioport.h> +#include <linux/pci.h> +#include <linux/sizes.h> +#include <linux/sprintf.h> +#include <linux/types.h> + +#include "pci.h" + +#define CARDBUS_LATENCY_TIMER 176 /* secondary latency timer */ +#define CARDBUS_RESERVE_BUSNR 3 + +#define DEFAULT_CARDBUS_IO_SIZE SZ_256 +#define DEFAULT_CARDBUS_MEM_SIZE SZ_64M +/* pci=cbmemsize=nnM,cbiosize=nn can override this */ +static unsigned long pci_cardbus_io_size = DEFAULT_CARDBUS_IO_SIZE; +static unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE; + +unsigned long pci_cardbus_resource_alignment(struct resource *res) +{ + if (res->flags & IORESOURCE_IO) + return pci_cardbus_io_size; + if (res->flags & IORESOURCE_MEM) + return pci_cardbus_mem_size; + return 0; +} + +int pci_bus_size_cardbus_bridge(struct pci_bus *bus, + struct list_head *realloc_head) +{ + struct pci_dev *bridge = bus->self; + struct resource *b_res; + resource_size_t b_res_3_size = pci_cardbus_mem_size * 2; + u16 ctrl; + + b_res = &bridge->resource[PCI_CB_BRIDGE_IO_0_WINDOW]; + if (resource_assigned(b_res)) + goto handle_b_res_1; + /* + * Reserve some resources for CardBus. We reserve a fixed amount + * of bus space for CardBus bridges. + */ + resource_set_range(b_res, pci_cardbus_io_size, pci_cardbus_io_size); + b_res->flags |= IORESOURCE_IO | IORESOURCE_STARTALIGN; + if (realloc_head) { + b_res->end -= pci_cardbus_io_size; + pci_dev_res_add_to_list(realloc_head, bridge, b_res, + pci_cardbus_io_size, + pci_cardbus_io_size); + } + +handle_b_res_1: + b_res = &bridge->resource[PCI_CB_BRIDGE_IO_1_WINDOW]; + if (resource_assigned(b_res)) + goto handle_b_res_2; + resource_set_range(b_res, pci_cardbus_io_size, pci_cardbus_io_size); + b_res->flags |= IORESOURCE_IO | IORESOURCE_STARTALIGN; + if (realloc_head) { + b_res->end -= pci_cardbus_io_size; + pci_dev_res_add_to_list(realloc_head, bridge, b_res, + pci_cardbus_io_size, + pci_cardbus_io_size); + } + +handle_b_res_2: + /* MEM1 must not be pref MMIO */ + pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl); + if (ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM1) { + ctrl &= ~PCI_CB_BRIDGE_CTL_PREFETCH_MEM1; + pci_write_config_word(bridge, PCI_CB_BRIDGE_CONTROL, ctrl); + pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl); + } + + /* Check whether prefetchable memory is supported by this bridge. */ + pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl); + if (!(ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM0)) { + ctrl |= PCI_CB_BRIDGE_CTL_PREFETCH_MEM0; + pci_write_config_word(bridge, PCI_CB_BRIDGE_CONTROL, ctrl); + pci_read_config_word(bridge, PCI_CB_BRIDGE_CONTROL, &ctrl); + } + + b_res = &bridge->resource[PCI_CB_BRIDGE_MEM_0_WINDOW]; + if (resource_assigned(b_res)) + goto handle_b_res_3; + /* + * If we have prefetchable memory support, allocate two regions. + * Otherwise, allocate one region of twice the size. + */ + if (ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM0) { + resource_set_range(b_res, pci_cardbus_mem_size, + pci_cardbus_mem_size); + b_res->flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH | + IORESOURCE_STARTALIGN; + if (realloc_head) { + b_res->end -= pci_cardbus_mem_size; + pci_dev_res_add_to_list(realloc_head, bridge, b_res, + pci_cardbus_mem_size, + pci_cardbus_mem_size); + } + + /* Reduce that to half */ + b_res_3_size = pci_cardbus_mem_size; + } + +handle_b_res_3: + b_res = &bridge->resource[PCI_CB_BRIDGE_MEM_1_WINDOW]; + if (resource_assigned(b_res)) + goto handle_done; + resource_set_range(b_res, pci_cardbus_mem_size, b_res_3_size); + b_res->flags |= IORESOURCE_MEM | IORESOURCE_STARTALIGN; + if (realloc_head) { + b_res->end -= b_res_3_size; + pci_dev_res_add_to_list(realloc_head, bridge, b_res, + b_res_3_size, pci_cardbus_mem_size); + } + +handle_done: + return 0; +} + +void pci_setup_cardbus_bridge(struct pci_bus *bus) +{ + struct pci_dev *bridge = bus->self; + struct resource *res; + struct pci_bus_region region; + + pci_info(bridge, "CardBus bridge to %pR\n", + &bus->busn_res); + + res = bus->resource[0]; + pcibios_resource_to_bus(bridge->bus, ®ion, res); + if (resource_assigned(res) && res->flags & IORESOURCE_IO) { + /* + * The IO resource is allocated a range twice as large as it + * would normally need. This allows us to set both IO regs. + */ + pci_info(bridge, " bridge window %pR\n", res); + pci_write_config_dword(bridge, PCI_CB_IO_BASE_0, + region.start); + pci_write_config_dword(bridge, PCI_CB_IO_LIMIT_0, + region.end); + } + + res = bus->resource[1]; + pcibios_resource_to_bus(bridge->bus, ®ion, res); + if (resource_assigned(res) && res->flags & IORESOURCE_IO) { + pci_info(bridge, " bridge window %pR\n", res); + pci_write_config_dword(bridge, PCI_CB_IO_BASE_1, + region.start); + pci_write_config_dword(bridge, PCI_CB_IO_LIMIT_1, + region.end); + } + + res = bus->resource[2]; + pcibios_resource_to_bus(bridge->bus, ®ion, res); + if (resource_assigned(res) && res->flags & IORESOURCE_MEM) { + pci_info(bridge, " bridge window %pR\n", res); + pci_write_config_dword(bridge, PCI_CB_MEMORY_BASE_0, + region.start); + pci_write_config_dword(bridge, PCI_CB_MEMORY_LIMIT_0, + region.end); + } + + res = bus->resource[3]; + pcibios_resource_to_bus(bridge->bus, ®ion, res); + if (resource_assigned(res) && res->flags & IORESOURCE_MEM) { + pci_info(bridge, " bridge window %pR\n", res); + pci_write_config_dword(bridge, PCI_CB_MEMORY_BASE_1, + region.start); + pci_write_config_dword(bridge, PCI_CB_MEMORY_LIMIT_1, + region.end); + } +} +EXPORT_SYMBOL(pci_setup_cardbus_bridge); + +int pci_setup_cardbus(char *str) +{ + if (!strncmp(str, "cbiosize=", 9)) { + pci_cardbus_io_size = memparse(str + 9, &str); + return 0; + } else if (!strncmp(str, "cbmemsize=", 10)) { + pci_cardbus_mem_size = memparse(str + 10, &str); + return 0; + } + + return -ENOENT; +} + +int pci_cardbus_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev, + u32 buses, int max, + unsigned int available_buses, int pass) +{ + struct pci_bus *child; + bool fixed_buses; + u8 fixed_sec, fixed_sub; + int next_busnr; + u32 i, j = 0; + + /* + * We need to assign a number to this bus which we always do in the + * second pass. + */ + if (!pass) { + /* + * Temporarily disable forwarding of the configuration + * cycles on all bridges in this bus segment to avoid + * possible conflicts in the second pass between two bridges + * programmed with overlapping bus ranges. + */ + pci_write_config_dword(dev, PCI_PRIMARY_BUS, + buses & PCI_SEC_LATENCY_TIMER_MASK); + return max; + } + + /* Clear errors */ + pci_write_config_word(dev, PCI_STATUS, 0xffff); + + /* Read bus numbers from EA Capability (if present) */ + fixed_buses = pci_ea_fixed_busnrs(dev, &fixed_sec, &fixed_sub); + if (fixed_buses) + next_busnr = fixed_sec; + else + next_busnr = max + 1; + + /* + * Prevent assigning a bus number that already exists. This can + * happen when a bridge is hot-plugged, so in this case we only + * re-scan this bus. + */ + child = pci_find_bus(pci_domain_nr(bus), next_busnr); + if (!child) { + child = pci_add_new_bus(bus, dev, next_busnr); + if (!child) + return max; + pci_bus_insert_busn_res(child, next_busnr, bus->busn_res.end); + } + max++; + if (available_buses) + available_buses--; + + buses = (buses & PCI_SEC_LATENCY_TIMER_MASK) | + FIELD_PREP(PCI_PRIMARY_BUS_MASK, child->primary) | + FIELD_PREP(PCI_SECONDARY_BUS_MASK, child->busn_res.start) | + FIELD_PREP(PCI_SUBORDINATE_BUS_MASK, child->busn_res.end); + + /* + * yenta.c forces a secondary latency timer of 176. + * Copy that behaviour here. + */ + buses &= ~PCI_SEC_LATENCY_TIMER_MASK; + buses |= FIELD_PREP(PCI_SEC_LATENCY_TIMER_MASK, CARDBUS_LATENCY_TIMER); + + /* We need to blast all three values with a single write */ + pci_write_config_dword(dev, PCI_PRIMARY_BUS, buses); + + /* + * For CardBus bridges, we leave 4 bus numbers as cards with a + * PCI-to-PCI bridge can be inserted later. + */ + for (i = 0; i < CARDBUS_RESERVE_BUSNR; i++) { + struct pci_bus *parent = bus; + + if (pci_find_bus(pci_domain_nr(bus), max + i + 1)) + break; + + while (parent->parent) { + if (!pcibios_assign_all_busses() && + (parent->busn_res.end > max) && + (parent->busn_res.end <= max + i)) { + j = 1; + } + parent = parent->parent; + } + if (j) { + /* + * Often, there are two CardBus bridges -- try to + * leave one valid bus number for each one. + */ + i /= 2; + break; + } + } + max += i; + + /* + * Set subordinate bus number to its real value. If fixed + * subordinate bus number exists from EA capability then use it. + */ + if (fixed_buses) + max = fixed_sub; + pci_bus_update_busn_res_end(child, max); + pci_write_config_byte(dev, PCI_SUBORDINATE_BUS, max); + + scnprintf(child->name, sizeof(child->name), "PCI CardBus %04x:%02x", + pci_domain_nr(bus), child->number); + + pbus_validate_busn(child); + + return max; +} diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index c6657cdd06f6..bb2aef373d6f 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -359,6 +359,9 @@ int pci_assign_resource(struct pci_dev *dev, int resno) res->flags &= ~IORESOURCE_UNSET; res->flags &= ~IORESOURCE_STARTALIGN; + if (pci_resource_is_bridge_win(resno)) + res->flags &= ~IORESOURCE_DISABLED; + pci_info(dev, "%s %pR: assigned\n", res_name, res); if (resno < PCI_BRIDGE_RESOURCES) pci_update_resource(dev, resno); @@ -406,75 +409,27 @@ int pci_reassign_resource(struct pci_dev *dev, int resno, return 0; } -void pci_release_resource(struct pci_dev *dev, int resno) +int pci_release_resource(struct pci_dev *dev, int resno) { struct resource *res = pci_resource_n(dev, resno); const char *res_name = pci_resource_name(dev, resno); + int ret; if (!res->parent) - return; + return 0; pci_info(dev, "%s %pR: releasing\n", res_name, res); - release_resource(res); + ret = release_resource(res); + if (ret) + return ret; res->end = resource_size(res) - 1; res->start = 0; res->flags |= IORESOURCE_UNSET; -} -EXPORT_SYMBOL(pci_release_resource); -int pci_resize_resource(struct pci_dev *dev, int resno, int size) -{ - struct resource *res = pci_resource_n(dev, resno); - struct pci_host_bridge *host; - int old, ret; - u32 sizes; - u16 cmd; - - /* Check if we must preserve the firmware's resource assignment */ - host = pci_find_host_bridge(dev->bus); - if (host->preserve_config) - return -ENOTSUPP; - - /* Make sure the resource isn't assigned before resizing it. */ - if (!(res->flags & IORESOURCE_UNSET)) - return -EBUSY; - - pci_read_config_word(dev, PCI_COMMAND, &cmd); - if (cmd & PCI_COMMAND_MEMORY) - return -EBUSY; - - sizes = pci_rebar_get_possible_sizes(dev, resno); - if (!sizes) - return -ENOTSUPP; - - if (!(sizes & BIT(size))) - return -EINVAL; - - old = pci_rebar_get_current_size(dev, resno); - if (old < 0) - return old; - - ret = pci_rebar_set_size(dev, resno, size); - if (ret) - return ret; - - resource_set_size(res, pci_rebar_size_to_bytes(size)); - - /* Check if the new config works by trying to assign everything. */ - if (dev->bus->self) { - ret = pci_reassign_bridge_resources(dev->bus->self, res->flags); - if (ret) - goto error_resize; - } return 0; - -error_resize: - pci_rebar_set_size(dev, resno, old); - resource_set_size(res, pci_rebar_size_to_bytes(old)); - return ret; } -EXPORT_SYMBOL(pci_resize_resource); +EXPORT_SYMBOL(pci_release_resource); int pci_enable_resources(struct pci_dev *dev, int mask) { @@ -497,22 +452,26 @@ int pci_enable_resources(struct pci_dev *dev, int mask) if (pci_resource_is_optional(dev, i)) continue; - if (r->flags & IORESOURCE_UNSET) { - pci_err(dev, "%s %pR: not assigned; can't enable device\n", - r_name, r); - return -EINVAL; + if (i < PCI_BRIDGE_RESOURCES) { + if (r->flags & IORESOURCE_UNSET) { + pci_err(dev, "%s %pR: not assigned; can't enable device\n", + r_name, r); + return -EINVAL; + } + + if (!r->parent) { + pci_err(dev, "%s %pR: not claimed; can't enable device\n", + r_name, r); + return -EINVAL; + } } - if (!r->parent) { - pci_err(dev, "%s %pR: not claimed; can't enable device\n", - r_name, r); - return -EINVAL; + if (r->parent) { + if (r->flags & IORESOURCE_IO) + cmd |= PCI_COMMAND_IO; + if (r->flags & IORESOURCE_MEM) + cmd |= PCI_COMMAND_MEMORY; } - - if (r->flags & IORESOURCE_IO) - cmd |= PCI_COMMAND_IO; - if (r->flags & IORESOURCE_MEM) - cmd |= PCI_COMMAND_MEMORY; } if (cmd != old_cmd) { diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c index 50fb3eb595fe..787311614e5b 100644 --- a/drivers/pci/slot.c +++ b/drivers/pci/slot.c @@ -256,7 +256,7 @@ struct pci_slot *pci_create_slot(struct pci_bus *parent, int slot_nr, } placeholder: - slot = kzalloc(sizeof(*slot), GFP_KERNEL); + slot = kzalloc_obj(*slot); if (!slot) { err = -ENOMEM; goto err; diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c index b14dfab04d84..93ebec94b763 100644 --- a/drivers/pci/switch/switchtec.c +++ b/drivers/pci/switch/switchtec.c @@ -86,7 +86,7 @@ static struct switchtec_user *stuser_create(struct switchtec_dev *stdev) { struct switchtec_user *stuser; - stuser = kzalloc(sizeof(*stuser), GFP_KERNEL); + stuser = kzalloc_obj(*stuser); if (!stuser) return ERR_PTR(-ENOMEM); @@ -269,10 +269,9 @@ static void mrpc_event_work(struct work_struct *work) dev_dbg(&stdev->dev, "%s\n", __func__); - mutex_lock(&stdev->mrpc_mutex); + guard(mutex)(&stdev->mrpc_mutex); cancel_delayed_work(&stdev->mrpc_timeout); mrpc_complete_cmd(stdev); - mutex_unlock(&stdev->mrpc_mutex); } static void mrpc_error_complete_cmd(struct switchtec_dev *stdev) @@ -896,7 +895,7 @@ static int ioctl_event_summary(struct switchtec_dev *stdev, u32 reg; int ret = 0; - s = kzalloc(sizeof(*s), GFP_KERNEL); + s = kzalloc_obj(*s); if (!s) return -ENOMEM; @@ -1322,18 +1321,18 @@ static void stdev_kill(struct switchtec_dev *stdev) cancel_delayed_work_sync(&stdev->mrpc_timeout); /* Mark the hardware as unavailable and complete all completions */ - mutex_lock(&stdev->mrpc_mutex); - stdev->alive = false; - - /* Wake up and kill any users waiting on an MRPC request */ - list_for_each_entry_safe(stuser, tmpuser, &stdev->mrpc_queue, list) { - stuser->cmd_done = true; - wake_up_interruptible(&stuser->cmd_comp); - list_del_init(&stuser->list); - stuser_put(stuser); - } + scoped_guard (mutex, &stdev->mrpc_mutex) { + stdev->alive = false; + + /* Wake up and kill any users waiting on an MRPC request */ + list_for_each_entry_safe(stuser, tmpuser, &stdev->mrpc_queue, list) { + stuser->cmd_done = true; + wake_up_interruptible(&stuser->cmd_comp); + list_del_init(&stuser->list); + stuser_put(stuser); + } - mutex_unlock(&stdev->mrpc_mutex); + } /* Wake up any users waiting on event_wq */ wake_up_interruptible(&stdev->event_wq); diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c index 07de59ca2ebf..ca4f97be7538 100644 --- a/drivers/pci/tph.c +++ b/drivers/pci/tph.c @@ -155,7 +155,16 @@ static u8 get_st_modes(struct pci_dev *pdev) return reg; } -static u32 get_st_table_loc(struct pci_dev *pdev) +/** + * pcie_tph_get_st_table_loc - Return the device's ST table location + * @pdev: PCI device to query + * + * Return: + * PCI_TPH_LOC_NONE - Not present + * PCI_TPH_LOC_CAP - Located in the TPH Requester Extended Capability + * PCI_TPH_LOC_MSIX - Located in the MSI-X Table + */ +u32 pcie_tph_get_st_table_loc(struct pci_dev *pdev) { u32 reg; @@ -163,18 +172,19 @@ static u32 get_st_table_loc(struct pci_dev *pdev) return FIELD_GET(PCI_TPH_CAP_LOC_MASK, reg); } +EXPORT_SYMBOL(pcie_tph_get_st_table_loc); /* * Return the size of ST table. If ST table is not in TPH Requester Extended * Capability space, return 0. Otherwise return the ST Table Size + 1. */ -static u16 get_st_table_size(struct pci_dev *pdev) +u16 pcie_tph_get_st_table_size(struct pci_dev *pdev) { u32 reg; u32 loc; /* Check ST table location first */ - loc = get_st_table_loc(pdev); + loc = pcie_tph_get_st_table_loc(pdev); /* Convert loc to match with PCI_TPH_LOC_* defined in pci_regs.h */ loc = FIELD_PREP(PCI_TPH_CAP_LOC_MASK, loc); @@ -185,6 +195,7 @@ static u16 get_st_table_size(struct pci_dev *pdev) return FIELD_GET(PCI_TPH_CAP_ST_MASK, reg) + 1; } +EXPORT_SYMBOL(pcie_tph_get_st_table_size); /* Return device's Root Port completer capability */ static u8 get_rp_completer_type(struct pci_dev *pdev) @@ -204,48 +215,6 @@ static u8 get_rp_completer_type(struct pci_dev *pdev) return FIELD_GET(PCI_EXP_DEVCAP2_TPH_COMP_MASK, reg); } -/* Write ST to MSI-X vector control reg - Return 0 if OK, otherwise -errno */ -static int write_tag_to_msix(struct pci_dev *pdev, int msix_idx, u16 tag) -{ -#ifdef CONFIG_PCI_MSI - struct msi_desc *msi_desc = NULL; - void __iomem *vec_ctrl; - u32 val; - int err = 0; - - msi_lock_descs(&pdev->dev); - - /* Find the msi_desc entry with matching msix_idx */ - msi_for_each_desc(msi_desc, &pdev->dev, MSI_DESC_ASSOCIATED) { - if (msi_desc->msi_index == msix_idx) - break; - } - - if (!msi_desc) { - err = -ENXIO; - goto err_out; - } - - /* Get the vector control register (offset 0xc) pointed by msix_idx */ - vec_ctrl = pdev->msix_base + msix_idx * PCI_MSIX_ENTRY_SIZE; - vec_ctrl += PCI_MSIX_ENTRY_VECTOR_CTRL; - - val = readl(vec_ctrl); - val &= ~PCI_MSIX_ENTRY_CTRL_ST; - val |= FIELD_PREP(PCI_MSIX_ENTRY_CTRL_ST, tag); - writel(val, vec_ctrl); - - /* Read back to flush the update */ - val = readl(vec_ctrl); - -err_out: - msi_unlock_descs(&pdev->dev); - return err; -#else - return -ENODEV; -#endif -} - /* Write tag to ST table - Return 0 if OK, otherwise -errno */ static int write_tag_to_st_table(struct pci_dev *pdev, int index, u16 tag) { @@ -253,7 +222,7 @@ static int write_tag_to_st_table(struct pci_dev *pdev, int index, u16 tag) int offset; /* Check if index is out of bound */ - st_table_size = get_st_table_size(pdev); + st_table_size = pcie_tph_get_st_table_size(pdev); if (index >= st_table_size) return -ENXIO; @@ -340,13 +309,13 @@ int pcie_tph_set_st_entry(struct pci_dev *pdev, unsigned int index, u16 tag) */ set_ctrl_reg_req_en(pdev, PCI_TPH_REQ_DISABLE); - loc = get_st_table_loc(pdev); + loc = pcie_tph_get_st_table_loc(pdev); /* Convert loc to match with PCI_TPH_LOC_* */ loc = FIELD_PREP(PCI_TPH_CAP_LOC_MASK, loc); switch (loc) { case PCI_TPH_LOC_MSIX: - err = write_tag_to_msix(pdev, index, tag); + err = pci_msix_write_tph_tag(pdev, index, tag); break; case PCI_TPH_LOC_CAP: err = write_tag_to_st_table(pdev, index, tag); @@ -485,7 +454,7 @@ void pci_restore_tph_state(struct pci_dev *pdev) pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, *cap++); st_entry = (u16 *)cap; offset = PCI_TPH_BASE_SIZEOF; - num_entries = get_st_table_size(pdev); + num_entries = pcie_tph_get_st_table_size(pdev); for (i = 0; i < num_entries; i++) { pci_write_config_word(pdev, pdev->tph_cap + offset, *st_entry++); @@ -517,7 +486,7 @@ void pci_save_tph_state(struct pci_dev *pdev) /* Save all ST entries in extended capability structure */ st_entry = (u16 *)cap; offset = PCI_TPH_BASE_SIZEOF; - num_entries = get_st_table_size(pdev); + num_entries = pcie_tph_get_st_table_size(pdev); for (i = 0; i < num_entries; i++) { pci_read_config_word(pdev, pdev->tph_cap + offset, st_entry++); @@ -541,7 +510,7 @@ void pci_tph_init(struct pci_dev *pdev) if (!pdev->tph_cap) return; - num_entries = get_st_table_size(pdev); + num_entries = pcie_tph_get_st_table_size(pdev); save_size = sizeof(u32) + num_entries * sizeof(u16); pci_add_ext_cap_save_buffer(pdev, PCI_EXT_CAP_ID_TPH, save_size); } diff --git a/drivers/pci/trace.c b/drivers/pci/trace.c new file mode 100644 index 000000000000..cf11abca8602 --- /dev/null +++ b/drivers/pci/trace.c @@ -0,0 +1,11 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Tracepoints for PCI system + * + * Copyright (C) 2025 Alibaba Corporation + */ + +#include <linux/pci.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/pci.h> diff --git a/drivers/pci/tsm.c b/drivers/pci/tsm.c new file mode 100644 index 000000000000..5fdcd7f2e820 --- /dev/null +++ b/drivers/pci/tsm.c @@ -0,0 +1,900 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Interface with platform TEE Security Manager (TSM) objects as defined by + * PCIe r7.0 section 11 TEE Device Interface Security Protocol (TDISP) + * + * Copyright(c) 2024-2025 Intel Corporation. All rights reserved. + */ + +#define dev_fmt(fmt) "PCI/TSM: " fmt + +#include <linux/bitfield.h> +#include <linux/pci.h> +#include <linux/pci-doe.h> +#include <linux/pci-tsm.h> +#include <linux/sysfs.h> +#include <linux/tsm.h> +#include <linux/xarray.h> +#include "pci.h" + +/* + * Provide a read/write lock against the init / exit of pdev tsm + * capabilities and arrival/departure of a TSM instance + */ +static DECLARE_RWSEM(pci_tsm_rwsem); + +/* + * Count of TSMs registered that support physical link operations vs device + * security state management. + */ +static int pci_tsm_link_count; +static int pci_tsm_devsec_count; + +static const struct pci_tsm_ops *to_pci_tsm_ops(struct pci_tsm *tsm) +{ + return tsm->tsm_dev->pci_ops; +} + +static inline bool is_dsm(struct pci_dev *pdev) +{ + return pdev->tsm && pdev->tsm->dsm_dev == pdev; +} + +static inline bool has_tee(struct pci_dev *pdev) +{ + return pdev->devcap & PCI_EXP_DEVCAP_TEE; +} + +/* 'struct pci_tsm_pf0' wraps 'struct pci_tsm' when ->dsm_dev == ->pdev (self) */ +static struct pci_tsm_pf0 *to_pci_tsm_pf0(struct pci_tsm *tsm) +{ + /* + * All "link" TSM contexts reference the device that hosts the DSM + * interface for a set of devices. Walk to the DSM device and cast its + * ->tsm context to a 'struct pci_tsm_pf0 *'. + */ + struct pci_dev *pf0 = tsm->dsm_dev; + + if (!is_pci_tsm_pf0(pf0) || !is_dsm(pf0)) { + pci_WARN_ONCE(tsm->pdev, 1, "invalid context object\n"); + return NULL; + } + + return container_of(pf0->tsm, struct pci_tsm_pf0, base_tsm); +} + +static void tsm_remove(struct pci_tsm *tsm) +{ + struct pci_dev *pdev; + + if (!tsm) + return; + + pdev = tsm->pdev; + to_pci_tsm_ops(tsm)->remove(tsm); + pdev->tsm = NULL; +} +DEFINE_FREE(tsm_remove, struct pci_tsm *, if (_T) tsm_remove(_T)) + +static void pci_tsm_walk_fns(struct pci_dev *pdev, + int (*cb)(struct pci_dev *pdev, void *data), + void *data) +{ + /* Walk subordinate physical functions */ + for (int i = 0; i < 8; i++) { + struct pci_dev *pf __free(pci_dev_put) = pci_get_slot( + pdev->bus, PCI_DEVFN(PCI_SLOT(pdev->devfn), i)); + + if (!pf) + continue; + + /* on entry function 0 has already run @cb */ + if (i > 0) + cb(pf, data); + + /* walk virtual functions of each pf */ + for (int j = 0; j < pci_num_vf(pf); j++) { + struct pci_dev *vf __free(pci_dev_put) = + pci_get_domain_bus_and_slot( + pci_domain_nr(pf->bus), + pci_iov_virtfn_bus(pf, j), + pci_iov_virtfn_devfn(pf, j)); + + if (!vf) + continue; + + cb(vf, data); + } + } + + /* + * Walk downstream devices, assumes that an upstream DSM is + * limited to downstream physical functions + */ + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_UPSTREAM && is_dsm(pdev)) + pci_walk_bus(pdev->subordinate, cb, data); +} + +static void pci_tsm_walk_fns_reverse(struct pci_dev *pdev, + int (*cb)(struct pci_dev *pdev, + void *data), + void *data) +{ + /* Reverse walk downstream devices */ + if (pci_pcie_type(pdev) == PCI_EXP_TYPE_UPSTREAM && is_dsm(pdev)) + pci_walk_bus_reverse(pdev->subordinate, cb, data); + + /* Reverse walk subordinate physical functions */ + for (int i = 7; i >= 0; i--) { + struct pci_dev *pf __free(pci_dev_put) = pci_get_slot( + pdev->bus, PCI_DEVFN(PCI_SLOT(pdev->devfn), i)); + + if (!pf) + continue; + + /* reverse walk virtual functions */ + for (int j = pci_num_vf(pf) - 1; j >= 0; j--) { + struct pci_dev *vf __free(pci_dev_put) = + pci_get_domain_bus_and_slot( + pci_domain_nr(pf->bus), + pci_iov_virtfn_bus(pf, j), + pci_iov_virtfn_devfn(pf, j)); + + if (!vf) + continue; + cb(vf, data); + } + + /* on exit, caller will run @cb on function 0 */ + if (i > 0) + cb(pf, data); + } +} + +static void link_sysfs_disable(struct pci_dev *pdev) +{ + sysfs_update_group(&pdev->dev.kobj, &pci_tsm_auth_attr_group); + sysfs_update_group(&pdev->dev.kobj, &pci_tsm_attr_group); +} + +static void link_sysfs_enable(struct pci_dev *pdev) +{ + bool tee = has_tee(pdev); + + pci_dbg(pdev, "%s Security Manager detected (%s%s%s)\n", + pdev->tsm ? "Device" : "Platform TEE", + pdev->ide_cap ? "IDE" : "", pdev->ide_cap && tee ? " " : "", + tee ? "TEE" : ""); + + sysfs_update_group(&pdev->dev.kobj, &pci_tsm_auth_attr_group); + sysfs_update_group(&pdev->dev.kobj, &pci_tsm_attr_group); +} + +static int probe_fn(struct pci_dev *pdev, void *dsm) +{ + struct pci_dev *dsm_dev = dsm; + const struct pci_tsm_ops *ops = to_pci_tsm_ops(dsm_dev->tsm); + + pdev->tsm = ops->probe(dsm_dev->tsm->tsm_dev, pdev); + pci_dbg(pdev, "setup TSM context: DSM: %s status: %s\n", + pci_name(dsm_dev), pdev->tsm ? "success" : "failed"); + if (pdev->tsm) + link_sysfs_enable(pdev); + return 0; +} + +static int pci_tsm_connect(struct pci_dev *pdev, struct tsm_dev *tsm_dev) +{ + int rc; + struct pci_tsm_pf0 *tsm_pf0; + const struct pci_tsm_ops *ops = tsm_dev->pci_ops; + struct pci_tsm *pci_tsm __free(tsm_remove) = ops->probe(tsm_dev, pdev); + + /* connect() mutually exclusive with subfunction pci_tsm_init() */ + lockdep_assert_held_write(&pci_tsm_rwsem); + + if (!pci_tsm) + return -ENXIO; + + pdev->tsm = pci_tsm; + tsm_pf0 = to_pci_tsm_pf0(pdev->tsm); + + /* mutex_intr assumes connect() is always sysfs/user driven */ + ACQUIRE(mutex_intr, lock)(&tsm_pf0->lock); + if ((rc = ACQUIRE_ERR(mutex_intr, &lock))) + return rc; + + rc = ops->connect(pdev); + if (rc) + return rc; + + pdev->tsm = no_free_ptr(pci_tsm); + + /* + * Now that the DSM is established, probe() all the potential + * dependent functions. Failure to probe a function is not fatal + * to connect(), it just disables subsequent security operations + * for that function. + * + * Note this is done unconditionally, without regard to finding + * PCI_EXP_DEVCAP_TEE on the dependent function, for robustness. The DSM + * is the ultimate arbiter of security state relative to a given + * interface id, and if it says it can manage TDISP state of a function, + * let it. + */ + if (has_tee(pdev)) + pci_tsm_walk_fns(pdev, probe_fn, pdev); + return 0; +} + +static ssize_t connect_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct tsm_dev *tsm_dev; + int rc; + + ACQUIRE(rwsem_read_intr, lock)(&pci_tsm_rwsem); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &lock))) + return rc; + + if (!pdev->tsm) + return sysfs_emit(buf, "\n"); + + tsm_dev = pdev->tsm->tsm_dev; + return sysfs_emit(buf, "%s\n", dev_name(&tsm_dev->dev)); +} + +/* Is @tsm_dev managing physical link / session properties... */ +static bool is_link_tsm(struct tsm_dev *tsm_dev) +{ + return tsm_dev && tsm_dev->pci_ops && tsm_dev->pci_ops->link_ops.probe; +} + +/* ...or is @tsm_dev managing device security state ? */ +static bool is_devsec_tsm(struct tsm_dev *tsm_dev) +{ + return tsm_dev && tsm_dev->pci_ops && tsm_dev->pci_ops->devsec_ops.lock; +} + +static ssize_t connect_store(struct device *dev, struct device_attribute *attr, + const char *buf, size_t len) +{ + struct pci_dev *pdev = to_pci_dev(dev); + int rc, id; + + rc = sscanf(buf, "tsm%d\n", &id); + if (rc != 1) + return -EINVAL; + + ACQUIRE(rwsem_write_kill, lock)(&pci_tsm_rwsem); + if ((rc = ACQUIRE_ERR(rwsem_write_kill, &lock))) + return rc; + + if (pdev->tsm) + return -EBUSY; + + struct tsm_dev *tsm_dev __free(put_tsm_dev) = find_tsm_dev(id); + if (!is_link_tsm(tsm_dev)) + return -ENXIO; + + rc = pci_tsm_connect(pdev, tsm_dev); + if (rc) + return rc; + return len; +} +static DEVICE_ATTR_RW(connect); + +static int remove_fn(struct pci_dev *pdev, void *data) +{ + tsm_remove(pdev->tsm); + link_sysfs_disable(pdev); + return 0; +} + +/* + * Note, this helper only returns an error code and takes an argument for + * compatibility with the pci_walk_bus() callback prototype. pci_tsm_unbind() + * always succeeds. + */ +static int __pci_tsm_unbind(struct pci_dev *pdev, void *data) +{ + struct pci_tdi *tdi; + struct pci_tsm_pf0 *tsm_pf0; + + lockdep_assert_held(&pci_tsm_rwsem); + + if (!pdev->tsm) + return 0; + + tsm_pf0 = to_pci_tsm_pf0(pdev->tsm); + guard(mutex)(&tsm_pf0->lock); + + tdi = pdev->tsm->tdi; + if (!tdi) + return 0; + + to_pci_tsm_ops(pdev->tsm)->unbind(tdi); + pdev->tsm->tdi = NULL; + + return 0; +} + +void pci_tsm_unbind(struct pci_dev *pdev) +{ + guard(rwsem_read)(&pci_tsm_rwsem); + __pci_tsm_unbind(pdev, NULL); +} +EXPORT_SYMBOL_GPL(pci_tsm_unbind); + +/** + * pci_tsm_bind() - Bind @pdev as a TDI for @kvm + * @pdev: PCI device function to bind + * @kvm: Private memory attach context + * @tdi_id: Identifier (virtual BDF) for the TDI as referenced by the TSM and DSM + * + * Returns 0 on success, or a negative error code on failure. + * + * Context: Caller is responsible for constraining the bind lifetime to the + * registered state of the device. For example, pci_tsm_bind() / + * pci_tsm_unbind() limited to the VFIO driver bound state of the device. + */ +int pci_tsm_bind(struct pci_dev *pdev, struct kvm *kvm, u32 tdi_id) +{ + struct pci_tsm_pf0 *tsm_pf0; + struct pci_tdi *tdi; + + if (!kvm) + return -EINVAL; + + guard(rwsem_read)(&pci_tsm_rwsem); + + if (!pdev->tsm) + return -EINVAL; + + if (!is_link_tsm(pdev->tsm->tsm_dev)) + return -ENXIO; + + tsm_pf0 = to_pci_tsm_pf0(pdev->tsm); + guard(mutex)(&tsm_pf0->lock); + + /* Resolve races to bind a TDI */ + if (pdev->tsm->tdi) { + if (pdev->tsm->tdi->kvm != kvm) + return -EBUSY; + return 0; + } + + tdi = to_pci_tsm_ops(pdev->tsm)->bind(pdev, kvm, tdi_id); + if (IS_ERR(tdi)) + return PTR_ERR(tdi); + + pdev->tsm->tdi = tdi; + + return 0; +} +EXPORT_SYMBOL_GPL(pci_tsm_bind); + +/** + * pci_tsm_guest_req() - helper to marshal guest requests to the TSM driver + * @pdev: @pdev representing a bound tdi + * @scope: caller asserts this passthrough request is limited to TDISP operations + * @req_in: Input payload forwarded from the guest + * @in_len: Length of @req_in + * @req_out: Output payload buffer response to the guest + * @out_len: Length of @req_out on input, bytes filled in @req_out on output + * @tsm_code: Optional TSM arch specific result code for the guest TSM + * + * This is a common entry point for requests triggered by userspace KVM-exit + * service handlers responding to TDI information or state change requests. The + * scope parameter limits requests to TDISP state management, or limited debug. + * This path is only suitable for commands and results that are the host kernel + * has no use, the host is only facilitating guest to TSM communication. + * + * Returns 0 on success and -error on failure and positive "residue" on success + * but @req_out is filled with less then @out_len, or @req_out is NULL and a + * residue number of bytes were not consumed from @req_in. On success or + * failure @tsm_code may be populated with a TSM implementation specific result + * code for the guest to consume. + * + * Context: Caller is responsible for calling this within the pci_tsm_bind() + * state of the TDI. + */ +ssize_t pci_tsm_guest_req(struct pci_dev *pdev, enum pci_tsm_req_scope scope, + sockptr_t req_in, size_t in_len, sockptr_t req_out, + size_t out_len, u64 *tsm_code) +{ + struct pci_tsm_pf0 *tsm_pf0; + struct pci_tdi *tdi; + int rc; + + /* Forbid requests that are not directly related to TDISP operations */ + if (scope > PCI_TSM_REQ_STATE_CHANGE) + return -EINVAL; + + ACQUIRE(rwsem_read_intr, lock)(&pci_tsm_rwsem); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &lock))) + return rc; + + if (!pdev->tsm) + return -ENXIO; + + if (!is_link_tsm(pdev->tsm->tsm_dev)) + return -ENXIO; + + tsm_pf0 = to_pci_tsm_pf0(pdev->tsm); + ACQUIRE(mutex_intr, ops_lock)(&tsm_pf0->lock); + if ((rc = ACQUIRE_ERR(mutex_intr, &ops_lock))) + return rc; + + tdi = pdev->tsm->tdi; + if (!tdi) + return -ENXIO; + return to_pci_tsm_ops(pdev->tsm)->guest_req(tdi, scope, req_in, in_len, + req_out, out_len, tsm_code); +} +EXPORT_SYMBOL_GPL(pci_tsm_guest_req); + +static void pci_tsm_unbind_all(struct pci_dev *pdev) +{ + pci_tsm_walk_fns_reverse(pdev, __pci_tsm_unbind, NULL); + __pci_tsm_unbind(pdev, NULL); +} + +static void __pci_tsm_disconnect(struct pci_dev *pdev) +{ + struct pci_tsm_pf0 *tsm_pf0 = to_pci_tsm_pf0(pdev->tsm); + const struct pci_tsm_ops *ops = to_pci_tsm_ops(pdev->tsm); + + /* disconnect() mutually exclusive with subfunction pci_tsm_init() */ + lockdep_assert_held_write(&pci_tsm_rwsem); + + pci_tsm_unbind_all(pdev); + + /* + * disconnect() is uninterruptible as it may be called for device + * teardown + */ + guard(mutex)(&tsm_pf0->lock); + pci_tsm_walk_fns_reverse(pdev, remove_fn, NULL); + ops->disconnect(pdev); +} + +static void pci_tsm_disconnect(struct pci_dev *pdev) +{ + __pci_tsm_disconnect(pdev); + tsm_remove(pdev->tsm); +} + +static ssize_t disconnect_store(struct device *dev, + struct device_attribute *attr, const char *buf, + size_t len) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct tsm_dev *tsm_dev; + int rc; + + ACQUIRE(rwsem_write_kill, lock)(&pci_tsm_rwsem); + if ((rc = ACQUIRE_ERR(rwsem_write_kill, &lock))) + return rc; + + if (!pdev->tsm) + return -ENXIO; + + tsm_dev = pdev->tsm->tsm_dev; + if (!sysfs_streq(buf, dev_name(&tsm_dev->dev))) + return -EINVAL; + + pci_tsm_disconnect(pdev); + return len; +} +static DEVICE_ATTR_WO(disconnect); + +static ssize_t bound_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct pci_tsm_pf0 *tsm_pf0; + struct pci_tsm *tsm; + int rc; + + ACQUIRE(rwsem_read_intr, lock)(&pci_tsm_rwsem); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &lock))) + return rc; + + tsm = pdev->tsm; + if (!tsm) + return sysfs_emit(buf, "\n"); + tsm_pf0 = to_pci_tsm_pf0(tsm); + + ACQUIRE(mutex_intr, ops_lock)(&tsm_pf0->lock); + if ((rc = ACQUIRE_ERR(mutex_intr, &ops_lock))) + return rc; + + if (!tsm->tdi) + return sysfs_emit(buf, "\n"); + return sysfs_emit(buf, "%s\n", dev_name(&tsm->tsm_dev->dev)); +} +static DEVICE_ATTR_RO(bound); + +static ssize_t dsm_show(struct device *dev, struct device_attribute *attr, + char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + struct pci_tsm *tsm; + int rc; + + ACQUIRE(rwsem_read_intr, lock)(&pci_tsm_rwsem); + if ((rc = ACQUIRE_ERR(rwsem_read_intr, &lock))) + return rc; + + tsm = pdev->tsm; + if (!tsm) + return sysfs_emit(buf, "\n"); + + return sysfs_emit(buf, "%s\n", pci_name(tsm->dsm_dev)); +} +static DEVICE_ATTR_RO(dsm); + +/* The 'authenticated' attribute is exclusive to the presence of a 'link' TSM */ +static bool pci_tsm_link_group_visible(struct kobject *kobj) +{ + struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj)); + + if (!pci_tsm_link_count) + return false; + + if (!pci_is_pcie(pdev)) + return false; + + if (is_pci_tsm_pf0(pdev)) + return true; + + /* + * Show 'authenticated' and other attributes for the managed + * sub-functions of a DSM. + */ + if (pdev->tsm) + return true; + + return false; +} +DEFINE_SIMPLE_SYSFS_GROUP_VISIBLE(pci_tsm_link); + +/* + * 'link' and 'devsec' TSMs share the same 'tsm/' sysfs group, so the TSM type + * specific attributes need individual visibility checks. + */ +static umode_t pci_tsm_attr_visible(struct kobject *kobj, + struct attribute *attr, int n) +{ + if (pci_tsm_link_group_visible(kobj)) { + struct pci_dev *pdev = to_pci_dev(kobj_to_dev(kobj)); + + if (attr == &dev_attr_bound.attr) { + if (is_pci_tsm_pf0(pdev) && has_tee(pdev)) + return attr->mode; + if (pdev->tsm && has_tee(pdev->tsm->dsm_dev)) + return attr->mode; + } + + if (attr == &dev_attr_dsm.attr) { + if (is_pci_tsm_pf0(pdev)) + return attr->mode; + if (pdev->tsm && has_tee(pdev->tsm->dsm_dev)) + return attr->mode; + } + + if (attr == &dev_attr_connect.attr || + attr == &dev_attr_disconnect.attr) { + if (is_pci_tsm_pf0(pdev)) + return attr->mode; + } + } + + return 0; +} + +static bool pci_tsm_group_visible(struct kobject *kobj) +{ + return pci_tsm_link_group_visible(kobj); +} +DEFINE_SYSFS_GROUP_VISIBLE(pci_tsm); + +static struct attribute *pci_tsm_attrs[] = { + &dev_attr_connect.attr, + &dev_attr_disconnect.attr, + &dev_attr_bound.attr, + &dev_attr_dsm.attr, + NULL +}; + +const struct attribute_group pci_tsm_attr_group = { + .name = "tsm", + .attrs = pci_tsm_attrs, + .is_visible = SYSFS_GROUP_VISIBLE(pci_tsm), +}; + +static ssize_t authenticated_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + /* + * When the SPDM session established via TSM the 'authenticated' state + * of the device is identical to the connect state. + */ + return connect_show(dev, attr, buf); +} +static DEVICE_ATTR_RO(authenticated); + +static struct attribute *pci_tsm_auth_attrs[] = { + &dev_attr_authenticated.attr, + NULL +}; + +const struct attribute_group pci_tsm_auth_attr_group = { + .attrs = pci_tsm_auth_attrs, + .is_visible = SYSFS_GROUP_VISIBLE(pci_tsm_link), +}; + +/* + * Retrieve physical function0 device whether it has TEE capability or not + */ +static struct pci_dev *pf0_dev_get(struct pci_dev *pdev) +{ + struct pci_dev *pf_dev = pci_physfn(pdev); + + if (PCI_FUNC(pf_dev->devfn) == 0) + return pci_dev_get(pf_dev); + + return pci_get_slot(pf_dev->bus, + pf_dev->devfn - PCI_FUNC(pf_dev->devfn)); +} + +/* + * Find the PCI Device instance that serves as the Device Security Manager (DSM) + * for @pdev. Note that no additional reference is held for the resulting device + * because that resulting object always has a registered lifetime + * greater-than-or-equal to that of the @pdev argument. This is by virtue of + * @pdev being a descendant of, or identical to, the returned DSM device. + */ +static struct pci_dev *find_dsm_dev(struct pci_dev *pdev) +{ + struct device *grandparent; + struct pci_dev *uport; + + if (is_pci_tsm_pf0(pdev)) + return pdev; + + struct pci_dev *pf0 __free(pci_dev_put) = pf0_dev_get(pdev); + if (!pf0) + return NULL; + + if (is_dsm(pf0)) + return pf0; + + /* + * For cases where a switch may be hosting TDISP services on behalf of + * downstream devices, check the first upstream port relative to this + * endpoint. + */ + if (!pdev->dev.parent) + return NULL; + grandparent = pdev->dev.parent->parent; + if (!grandparent) + return NULL; + if (!dev_is_pci(grandparent)) + return NULL; + uport = to_pci_dev(grandparent); + if (!pci_is_pcie(uport) || + pci_pcie_type(uport) != PCI_EXP_TYPE_UPSTREAM) + return NULL; + + if (is_dsm(uport)) + return uport; + return NULL; +} + +/** + * pci_tsm_tdi_constructor() - base 'struct pci_tdi' initialization for link TSMs + * @pdev: PCI device function representing the TDI + * @tdi: context to initialize + * @kvm: Private memory attach context + * @tdi_id: Identifier (virtual BDF) for the TDI as referenced by the TSM and DSM + */ +void pci_tsm_tdi_constructor(struct pci_dev *pdev, struct pci_tdi *tdi, + struct kvm *kvm, u32 tdi_id) +{ + tdi->pdev = pdev; + tdi->kvm = kvm; + tdi->tdi_id = tdi_id; +} +EXPORT_SYMBOL_GPL(pci_tsm_tdi_constructor); + +/** + * pci_tsm_link_constructor() - base 'struct pci_tsm' initialization for link TSMs + * @pdev: The PCI device + * @tsm: context to initialize + * @tsm_dev: Platform TEE Security Manager, initiator of security operations + */ +int pci_tsm_link_constructor(struct pci_dev *pdev, struct pci_tsm *tsm, + struct tsm_dev *tsm_dev) +{ + if (!is_link_tsm(tsm_dev)) + return -EINVAL; + + tsm->dsm_dev = find_dsm_dev(pdev); + if (!tsm->dsm_dev) { + pci_warn(pdev, "failed to find Device Security Manager\n"); + return -ENXIO; + } + tsm->pdev = pdev; + tsm->tsm_dev = tsm_dev; + + return 0; +} +EXPORT_SYMBOL_GPL(pci_tsm_link_constructor); + +/** + * pci_tsm_pf0_constructor() - common 'struct pci_tsm_pf0' (DSM) initialization + * @pdev: Physical Function 0 PCI device (as indicated by is_pci_tsm_pf0()) + * @tsm: context to initialize + * @tsm_dev: Platform TEE Security Manager, initiator of security operations + */ +int pci_tsm_pf0_constructor(struct pci_dev *pdev, struct pci_tsm_pf0 *tsm, + struct tsm_dev *tsm_dev) +{ + mutex_init(&tsm->lock); + tsm->doe_mb = pci_find_doe_mailbox(pdev, PCI_VENDOR_ID_PCI_SIG, + PCI_DOE_FEATURE_CMA); + if (!tsm->doe_mb) { + pci_warn(pdev, "TSM init failure, no CMA mailbox\n"); + return -ENODEV; + } + + return pci_tsm_link_constructor(pdev, &tsm->base_tsm, tsm_dev); +} +EXPORT_SYMBOL_GPL(pci_tsm_pf0_constructor); + +void pci_tsm_pf0_destructor(struct pci_tsm_pf0 *pf0_tsm) +{ + mutex_destroy(&pf0_tsm->lock); +} +EXPORT_SYMBOL_GPL(pci_tsm_pf0_destructor); + +int pci_tsm_register(struct tsm_dev *tsm_dev) +{ + struct pci_dev *pdev = NULL; + + if (!tsm_dev) + return -EINVAL; + + /* The TSM device must only implement one of link_ops or devsec_ops */ + if (!is_link_tsm(tsm_dev) && !is_devsec_tsm(tsm_dev)) + return -EINVAL; + + if (is_link_tsm(tsm_dev) && is_devsec_tsm(tsm_dev)) + return -EINVAL; + + guard(rwsem_write)(&pci_tsm_rwsem); + + /* On first enable, update sysfs groups */ + if (is_link_tsm(tsm_dev) && pci_tsm_link_count++ == 0) { + for_each_pci_dev(pdev) + if (is_pci_tsm_pf0(pdev)) + link_sysfs_enable(pdev); + } else if (is_devsec_tsm(tsm_dev)) { + pci_tsm_devsec_count++; + } + + return 0; +} + +static void pci_tsm_fn_exit(struct pci_dev *pdev) +{ + __pci_tsm_unbind(pdev, NULL); + tsm_remove(pdev->tsm); +} + +/** + * __pci_tsm_destroy() - destroy the TSM context for @pdev + * @pdev: device to cleanup + * @tsm_dev: the TSM device being removed, or NULL if @pdev is being removed. + * + * At device removal or TSM unregistration all established context + * with the TSM is torn down. Additionally, if there are no more TSMs + * registered, the PCI tsm/ sysfs attributes are hidden. + */ +static void __pci_tsm_destroy(struct pci_dev *pdev, struct tsm_dev *tsm_dev) +{ + struct pci_tsm *tsm = pdev->tsm; + + lockdep_assert_held_write(&pci_tsm_rwsem); + + /* + * First, handle the TSM removal case to shutdown @pdev sysfs, this is + * skipped if the device itself is being removed since sysfs goes away + * naturally at that point + */ + if (is_link_tsm(tsm_dev) && is_pci_tsm_pf0(pdev) && !pci_tsm_link_count) + link_sysfs_disable(pdev); + + /* Nothing else to do if this device never attached to the departing TSM */ + if (!tsm) + return; + + /* Now lookup the tsm_dev to destroy TSM context */ + if (!tsm_dev) + tsm_dev = tsm->tsm_dev; + else if (tsm_dev != tsm->tsm_dev) + return; + + if (is_link_tsm(tsm_dev) && is_pci_tsm_pf0(pdev)) + pci_tsm_disconnect(pdev); + else + pci_tsm_fn_exit(pdev); +} + +void pci_tsm_destroy(struct pci_dev *pdev) +{ + guard(rwsem_write)(&pci_tsm_rwsem); + __pci_tsm_destroy(pdev, NULL); +} + +void pci_tsm_init(struct pci_dev *pdev) +{ + guard(rwsem_read)(&pci_tsm_rwsem); + + /* + * Subfunctions are either probed synchronous with connect() or later + * when either the SR-IOV configuration is changed, or, unlikely, + * connect() raced initial bus scanning. + */ + if (pdev->tsm) + return; + + if (pci_tsm_link_count) { + struct pci_dev *dsm = find_dsm_dev(pdev); + + if (!dsm) + return; + + /* + * The only path to init a Device Security Manager capable + * device is via connect(). + */ + if (!dsm->tsm) + return; + + probe_fn(pdev, dsm); + } +} + +void pci_tsm_unregister(struct tsm_dev *tsm_dev) +{ + struct pci_dev *pdev = NULL; + + guard(rwsem_write)(&pci_tsm_rwsem); + if (is_link_tsm(tsm_dev)) + pci_tsm_link_count--; + if (is_devsec_tsm(tsm_dev)) + pci_tsm_devsec_count--; + for_each_pci_dev_reverse(pdev) + __pci_tsm_destroy(pdev, tsm_dev); +} + +int pci_tsm_doe_transfer(struct pci_dev *pdev, u8 type, const void *req, + size_t req_sz, void *resp, size_t resp_sz) +{ + struct pci_tsm_pf0 *tsm; + + if (!pdev->tsm || !is_pci_tsm_pf0(pdev)) + return -ENXIO; + + tsm = to_pci_tsm_pf0(pdev->tsm); + if (!tsm->doe_mb) + return -ENXIO; + + return pci_doe(tsm->doe_mb, PCI_VENDOR_ID_PCI_SIG, type, req, req_sz, + resp, resp_sz); +} +EXPORT_SYMBOL_GPL(pci_tsm_doe_transfer); diff --git a/drivers/pci/vgaarb.c b/drivers/pci/vgaarb.c index 78748e8d2dba..d9383bf541e7 100644 --- a/drivers/pci/vgaarb.c +++ b/drivers/pci/vgaarb.c @@ -26,7 +26,7 @@ #include <linux/poll.h> #include <linux/miscdevice.h> #include <linux/slab.h> -#include <linux/screen_info.h> +#include <linux/sysfb.h> #include <linux/vt.h> #include <linux/console.h> #include <linux/acpi.h> @@ -556,34 +556,11 @@ EXPORT_SYMBOL(vga_put); static bool vga_is_firmware_default(struct pci_dev *pdev) { -#if defined(CONFIG_X86) - u64 base = screen_info.lfb_base; - u64 size = screen_info.lfb_size; - struct resource *r; - u64 limit; - - /* Select the device owning the boot framebuffer if there is one */ - - if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE) - base |= (u64)screen_info.ext_lfb_base << 32; - - limit = base + size; - - /* Does firmware framebuffer belong to us? */ - pci_dev_for_each_resource(pdev, r) { - if (resource_type(r) != IORESOURCE_MEM) - continue; - - if (!r->start || !r->end) - continue; - - if (base < r->start || limit >= r->end) - continue; - - return true; - } -#endif +#if defined CONFIG_X86 + return pdev == screen_info_pci_dev(&sysfb_primary_display.screen); +#else return false; +#endif } static bool vga_arb_integrated_gpu(struct device *dev) @@ -675,13 +652,6 @@ static bool vga_is_boot_device(struct vga_device *vgadev) return true; } - /* - * Vgadev has neither IO nor MEM enabled. If we haven't found any - * other VGA devices, it is the best candidate so far. - */ - if (!boot_vga) - return true; - return false; } @@ -765,7 +735,7 @@ static bool vga_arbiter_add_pci_device(struct pci_dev *pdev) u16 cmd; /* Allocate structure */ - vgadev = kzalloc(sizeof(struct vga_device), GFP_KERNEL); + vgadev = kzalloc_obj(struct vga_device); if (vgadev == NULL) { vgaarb_err(&pdev->dev, "failed to allocate VGA arbiter data\n"); /* @@ -1415,7 +1385,7 @@ static int vga_arb_open(struct inode *inode, struct file *file) pr_debug("%s\n", __func__); - priv = kzalloc(sizeof(*priv), GFP_KERNEL); + priv = kzalloc_obj(*priv); if (priv == NULL) return -ENOMEM; spin_lock_init(&priv->lock); diff --git a/drivers/pci/vpd.c b/drivers/pci/vpd.c index 3d29b2602d0f..153394a652d3 100644 --- a/drivers/pci/vpd.c +++ b/drivers/pci/vpd.c @@ -336,7 +336,7 @@ static umode_t vpd_attr_is_visible(struct kobject *kobj, } const struct attribute_group pci_dev_vpd_attr_group = { - .bin_attrs_new = vpd_attrs, + .bin_attrs = vpd_attrs, .is_bin_visible = vpd_attr_is_visible, }; diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c index 11636634ae51..b8aaa292c3e7 100644 --- a/drivers/pci/xen-pcifront.c +++ b/drivers/pci/xen-pcifront.c @@ -462,8 +462,8 @@ static int pcifront_scan_root(struct pcifront_device *pdev, dev_info(&pdev->xdev->dev, "Creating PCI Frontend Bus %04x:%02x\n", domain, bus); - bus_entry = kzalloc(sizeof(*bus_entry), GFP_KERNEL); - sd = kzalloc(sizeof(*sd), GFP_KERNEL); + bus_entry = kzalloc_obj(*bus_entry); + sd = kzalloc_obj(*sd); if (!bus_entry || !sd) { err = -ENOMEM; goto err_out; @@ -687,7 +687,7 @@ static struct pcifront_device *alloc_pdev(struct xenbus_device *xdev) { struct pcifront_device *pdev; - pdev = kzalloc(sizeof(struct pcifront_device), GFP_KERNEL); + pdev = kzalloc_obj(struct pcifront_device); if (pdev == NULL) goto out; |